diff options
4034 files changed, 106629 insertions, 48325 deletions
diff --git a/.mailmap b/.mailmap index b9d358217586..6d484937f901 100644 --- a/.mailmap +++ b/.mailmap @@ -45,6 +45,7 @@ Andrey Konovalov <andreyknvl@gmail.com> <andreyknvl@google.com> Andrey Ryabinin <ryabinin.a.a@gmail.com> <a.ryabinin@samsung.com> Andrey Ryabinin <ryabinin.a.a@gmail.com> <aryabinin@virtuozzo.com> Andrzej Hajda <andrzej.hajda@intel.com> <a.hajda@samsung.com> +André Almeida <andrealmeid@igalia.com> <andrealmeid@collabora.com> Andy Adamson <andros@citi.umich.edu> Antoine Tenart <atenart@kernel.org> <antoine.tenart@bootlin.com> Antoine Tenart <atenart@kernel.org> <antoine.tenart@free-electrons.com> @@ -204,6 +205,7 @@ Juha Yrjola <at solidboot.com> Juha Yrjola <juha.yrjola@nokia.com> Juha Yrjola <juha.yrjola@solidboot.com> Julien Thierry <julien.thierry.kdev@gmail.com> <julien.thierry@arm.com> +Kalle Valo <kvalo@kernel.org> <kvalo@codeaurora.org> Kalyan Thota <quic_kalyant@quicinc.com> <kalyan_t@codeaurora.org> Kay Sievers <kay.sievers@vrfy.org> Kees Cook <keescook@chromium.org> <kees.cook@canonical.com> @@ -249,6 +251,7 @@ Mark Yao <markyao0591@gmail.com> <mark.yao@rock-chips.com> Martin Kepplinger <martink@posteo.de> <martin.kepplinger@ginzinger.com> Martin Kepplinger <martink@posteo.de> <martin.kepplinger@puri.sm> Martin Kepplinger <martink@posteo.de> <martin.kepplinger@theobroma-systems.com> +Martyna Szapar-Mudlaw <martyna.szapar-mudlaw@linux.intel.com> <martyna.szapar-mudlaw@intel.com> Mathieu Othacehe <m.othacehe@gmail.com> Matthew Wilcox <willy@infradead.org> <matthew.r.wilcox@intel.com> Matthew Wilcox <willy@infradead.org> <matthew@wil.cx> @@ -391,6 +394,11 @@ Uwe Kleine-König <ukleinek@strlen.de> Uwe Kleine-König <ukl@pengutronix.de> Uwe Kleine-König <Uwe.Kleine-Koenig@digi.com> Valdis Kletnieks <Valdis.Kletnieks@vt.edu> +Vasily Averin <vasily.averin@linux.dev> <vvs@virtuozzo.com> +Vasily Averin <vasily.averin@linux.dev> <vvs@openvz.org> +Vasily Averin <vasily.averin@linux.dev> <vvs@parallels.com> +Vasily Averin <vasily.averin@linux.dev> <vvs@sw.ru> +Valentin Schneider <vschneid@redhat.com> <valentin.schneider@arm.com> Vinod Koul <vkoul@kernel.org> <vinod.koul@intel.com> Vinod Koul <vkoul@kernel.org> <vinod.koul@linux.intel.com> Vinod Koul <vkoul@kernel.org> <vkoul@infradead.org> diff --git a/Documentation/ABI/stable/sysfs-driver-mlxreg-io b/Documentation/ABI/stable/sysfs-driver-mlxreg-io index 12c3f895cd2f..b312242d4f40 100644 --- a/Documentation/ABI/stable/sysfs-driver-mlxreg-io +++ b/Documentation/ABI/stable/sysfs-driver-mlxreg-io @@ -467,3 +467,39 @@ Description: These files provide the maximum powered required for line card feeding and line card configuration Id. The files are read only. + +What: /sys/devices/platform/mlxplat/mlxreg-io/hwmon/hwmon*/phy_reset +Date: May 2022 +KernelVersion: 5.19 +Contact: Vadim Pasternak <vadimpmellanox.com> +Description: This file allows to reset PHY 88E1548 when attribute is set 0 + due to some abnormal PHY behavior. + Expected behavior: + When phy_reset is written 1, all PHY 88E1548 are released + from the reset state, when 0 - are hold in reset state. + + The files are read/write. + +What: /sys/devices/platform/mlxplat/mlxreg-io/hwmon/hwmon*/mac_reset +Date: May 2022 +KernelVersion: 5.19 +Contact: Vadim Pasternak <vadimpmellanox.com> +Description: This file allows to reset ASIC MT52132 when attribute is set 0 + due to some abnormal ASIC behavior. + Expected behavior: + When mac_reset is written 1, the ASIC MT52132 is released + from the reset state, when 0 - is hold in reset state. + + The files are read/write. + +What: /sys/devices/platform/mlxplat/mlxreg-io/hwmon/hwmon*/qsfp_pwr_good +Date: May 2022 +KernelVersion: 5.19 +Contact: Vadim Pasternak <vadimpmellanox.com> +Description: This file shows QSFP ports power status. The value is set to 0 + when one of any QSFP ports is plugged. The value is set to 1 when + there are no any QSFP ports are plugged. + The possible values are: + 0 - Power good, 1 - Not power good. + + The files are read only. diff --git a/Documentation/ABI/testing/ima_policy b/Documentation/ABI/testing/ima_policy index 839fab811b18..db17fc8a0c9f 100644 --- a/Documentation/ABI/testing/ima_policy +++ b/Documentation/ABI/testing/ima_policy @@ -27,8 +27,9 @@ Description: [fowner=] [fgroup=]] lsm: [[subj_user=] [subj_role=] [subj_type=] [obj_user=] [obj_role=] [obj_type=]] - option: [[appraise_type=]] [template=] [permit_directio] - [appraise_flag=] [appraise_algos=] [keyrings=] + option: [digest_type=] [template=] [permit_directio] + [appraise_type=] [appraise_flag=] + [appraise_algos=] [keyrings=] base: func:= [BPRM_CHECK][MMAP_CHECK][CREDS_CHECK][FILE_CHECK][MODULE_CHECK] [FIRMWARE_CHECK] @@ -47,10 +48,21 @@ Description: fgroup:= decimal value lsm: are LSM specific option: - appraise_type:= [imasig] [imasig|modsig] + appraise_type:= [imasig] | [imasig|modsig] | [sigv3] + where 'imasig' is the original or the signature + format v2. + where 'modsig' is an appended signature, + where 'sigv3' is the signature format v3. (Currently + limited to fsverity digest based signatures + stored in security.ima xattr. Requires + specifying "digest_type=verity" first.) + appraise_flag:= [check_blacklist] Currently, blacklist check is only for files signed with appended signature. + digest_type:= verity + Require fs-verity's file digest instead of the + regular IMA file hash. keyrings:= list of keyrings (eg, .builtin_trusted_keys|.ima). Only valid when action is "measure" and func is KEY_CHECK. @@ -149,3 +161,30 @@ Description: security.ima xattr of a file: appraise func=SETXATTR_CHECK appraise_algos=sha256,sha384,sha512 + + Example of a 'measure' rule requiring fs-verity's digests + with indication of type of digest in the measurement list. + + measure func=FILE_CHECK digest_type=verity \ + template=ima-ngv2 + + Example of 'measure' and 'appraise' rules requiring fs-verity + signatures (format version 3) stored in security.ima xattr. + + The 'measure' rule specifies the 'ima-sigv3' template option, + which includes the indication of type of digest and the file + signature in the measurement list. + + measure func=BPRM_CHECK digest_type=verity \ + template=ima-sigv3 + + + The 'appraise' rule specifies the type and signature format + version (sigv3) required. + + appraise func=BPRM_CHECK digest_type=verity \ + appraise_type=sigv3 + + All of these policy rules could, for example, be constrained + either based on a filesystem's UUID (fsuuid) or based on LSM + labels. diff --git a/Documentation/ABI/testing/securityfs-secrets-coco b/Documentation/ABI/testing/securityfs-secrets-coco new file mode 100644 index 000000000000..f2b6909155f9 --- /dev/null +++ b/Documentation/ABI/testing/securityfs-secrets-coco @@ -0,0 +1,51 @@ +What: security/secrets/coco +Date: February 2022 +Contact: Dov Murik <dovmurik@linux.ibm.com> +Description: + Exposes confidential computing (coco) EFI secrets to + userspace via securityfs. + + EFI can declare memory area used by confidential computing + platforms (such as AMD SEV and SEV-ES) for secret injection by + the Guest Owner during VM's launch. The secrets are encrypted + by the Guest Owner and decrypted inside the trusted enclave, + and therefore are not readable by the untrusted host. + + The efi_secret module exposes the secrets to userspace. Each + secret appears as a file under <securityfs>/secrets/coco, + where the filename is the GUID of the entry in the secrets + table. This module is loaded automatically by the EFI driver + if the EFI secret area is populated. + + Two operations are supported for the files: read and unlink. + Reading the file returns the content of secret entry. + Unlinking the file overwrites the secret data with zeroes and + removes the entry from the filesystem. A secret cannot be read + after it has been unlinked. + + For example, listing the available secrets:: + + # modprobe efi_secret + # ls -l /sys/kernel/security/secrets/coco + -r--r----- 1 root root 0 Jun 28 11:54 736870e5-84f0-4973-92ec-06879ce3da0b + -r--r----- 1 root root 0 Jun 28 11:54 83c83f7f-1356-4975-8b7e-d3a0b54312c6 + -r--r----- 1 root root 0 Jun 28 11:54 9553f55d-3da2-43ee-ab5d-ff17f78864d2 + -r--r----- 1 root root 0 Jun 28 11:54 e6f5a162-d67f-4750-a67c-5d065f2a9910 + + Reading the secret data by reading a file:: + + # cat /sys/kernel/security/secrets/coco/e6f5a162-d67f-4750-a67c-5d065f2a9910 + the-content-of-the-secret-data + + Wiping a secret by unlinking a file:: + + # rm /sys/kernel/security/secrets/coco/e6f5a162-d67f-4750-a67c-5d065f2a9910 + # ls -l /sys/kernel/security/secrets/coco + -r--r----- 1 root root 0 Jun 28 11:54 736870e5-84f0-4973-92ec-06879ce3da0b + -r--r----- 1 root root 0 Jun 28 11:54 83c83f7f-1356-4975-8b7e-d3a0b54312c6 + -r--r----- 1 root root 0 Jun 28 11:54 9553f55d-3da2-43ee-ab5d-ff17f78864d2 + + Note: The binary format of the secrets table injected by the + Guest Owner is described in + drivers/virt/coco/efi_secret/efi_secret.c under "Structure of + the EFI secret area". diff --git a/Documentation/ABI/testing/sysfs-class-firmware-attributes b/Documentation/ABI/testing/sysfs-class-firmware-attributes index 05820365f1ec..4cdba3477176 100644 --- a/Documentation/ABI/testing/sysfs-class-firmware-attributes +++ b/Documentation/ABI/testing/sysfs-class-firmware-attributes @@ -116,7 +116,7 @@ Description: <value>[ForceIf:<attribute>=<value>] <value>[ForceIfNot:<attribute>=<value>] - For example: + For example:: LegacyOrom/dell_value_modifier has value: Disabled[ForceIf:SecureBoot=Enabled] @@ -212,7 +212,7 @@ Description: the next boot. Lenovo specific class extensions - ------------------------------ + -------------------------------- On Lenovo systems the following additional settings are available: @@ -246,9 +246,7 @@ Description: that is being referenced (e.g hdd0, hdd1 etc) This attribute defaults to device 0. - certificate: - signature: - save_signature: + certificate, signature, save_signature: These attributes are used for certificate based authentication. This is used in conjunction with a signing server as an alternative to password based authentication. @@ -257,22 +255,27 @@ Description: The attributes can be displayed to check the stored value. Some usage examples: - Installing a certificate to enable feature: - echo <supervisor password > authentication/Admin/current_password - echo <signed certificate> > authentication/Admin/certificate - Updating the installed certificate: - echo <signature> > authentication/Admin/signature - echo <signed certificate> > authentication/Admin/certificate + Installing a certificate to enable feature:: + + echo "supervisor password" > authentication/Admin/current_password + echo "signed certificate" > authentication/Admin/certificate + + Updating the installed certificate:: + + echo "signature" > authentication/Admin/signature + echo "signed certificate" > authentication/Admin/certificate - Removing the installed certificate: - echo <signature> > authentication/Admin/signature - echo '' > authentication/Admin/certificate + Removing the installed certificate:: - Changing a BIOS setting: - echo <signature> > authentication/Admin/signature - echo <save signature> > authentication/Admin/save_signature - echo Enable > attribute/PasswordBeep/current_value + echo "signature" > authentication/Admin/signature + echo "" > authentication/Admin/certificate + + Changing a BIOS setting:: + + echo "signature" > authentication/Admin/signature + echo "save signature" > authentication/Admin/save_signature + echo Enable > attribute/PasswordBeep/current_value You cannot enable certificate authentication if a supervisor password has not been set. @@ -288,9 +291,10 @@ Description: certificate_to_password: Write only attribute used to switch from certificate based authentication back to password based. - Usage: - echo <signature> > authentication/Admin/signature - echo <password> > authentication/Admin/certificate_to_password + Usage:: + + echo "signature" > authentication/Admin/signature + echo "password" > authentication/Admin/certificate_to_password What: /sys/class/firmware-attributes/*/attributes/pending_reboot @@ -345,7 +349,7 @@ Description: # echo "factory" > /sys/class/firmware-attributes/*/device/attributes/reset_bios # cat /sys/class/firmware-attributes/*/device/attributes/reset_bios - # builtinsafe lastknowngood [factory] custom + builtinsafe lastknowngood [factory] custom Note that any changes to this attribute requires a reboot for changes to take effect. diff --git a/Documentation/ABI/testing/sysfs-class-regulator b/Documentation/ABI/testing/sysfs-class-regulator index 8516f08806dd..475b9a372657 100644 --- a/Documentation/ABI/testing/sysfs-class-regulator +++ b/Documentation/ABI/testing/sysfs-class-regulator @@ -370,3 +370,84 @@ Description: 'unknown' means software cannot determine the state, or the reported state is invalid. + +What: /sys/class/regulator/.../under_voltage +Date: April 2022 +KernelVersion: 5.18 +Contact: Zev Weiss <zev@bewilderbeest.net> +Description: + Some regulator directories will contain a field called + under_voltage. This indicates if the device reports an + under-voltage fault (1) or not (0). + +What: /sys/class/regulator/.../over_current +Date: April 2022 +KernelVersion: 5.18 +Contact: Zev Weiss <zev@bewilderbeest.net> +Description: + Some regulator directories will contain a field called + over_current. This indicates if the device reports an + over-current fault (1) or not (0). + +What: /sys/class/regulator/.../regulation_out +Date: April 2022 +KernelVersion: 5.18 +Contact: Zev Weiss <zev@bewilderbeest.net> +Description: + Some regulator directories will contain a field called + regulation_out. This indicates if the device reports an + out-of-regulation fault (1) or not (0). + +What: /sys/class/regulator/.../fail +Date: April 2022 +KernelVersion: 5.18 +Contact: Zev Weiss <zev@bewilderbeest.net> +Description: + Some regulator directories will contain a field called + fail. This indicates if the device reports an output failure + (1) or not (0). + +What: /sys/class/regulator/.../over_temp +Date: April 2022 +KernelVersion: 5.18 +Contact: Zev Weiss <zev@bewilderbeest.net> +Description: + Some regulator directories will contain a field called + over_temp. This indicates if the device reports an + over-temperature fault (1) or not (0). + +What: /sys/class/regulator/.../under_voltage_warn +Date: April 2022 +KernelVersion: 5.18 +Contact: Zev Weiss <zev@bewilderbeest.net> +Description: + Some regulator directories will contain a field called + under_voltage_warn. This indicates if the device reports an + under-voltage warning (1) or not (0). + +What: /sys/class/regulator/.../over_current_warn +Date: April 2022 +KernelVersion: 5.18 +Contact: Zev Weiss <zev@bewilderbeest.net> +Description: + Some regulator directories will contain a field called + over_current_warn. This indicates if the device reports an + over-current warning (1) or not (0). + +What: /sys/class/regulator/.../over_voltage_warn +Date: April 2022 +KernelVersion: 5.18 +Contact: Zev Weiss <zev@bewilderbeest.net> +Description: + Some regulator directories will contain a field called + over_voltage_warn. This indicates if the device reports an + over-voltage warning (1) or not (0). + +What: /sys/class/regulator/.../over_temp_warn +Date: April 2022 +KernelVersion: 5.18 +Contact: Zev Weiss <zev@bewilderbeest.net> +Description: + Some regulator directories will contain a field called + over_temp_warn. This indicates if the device reports an + over-temperature warning (1) or not (0). diff --git a/Documentation/ABI/testing/sysfs-driver-intel_sdsi b/Documentation/ABI/testing/sysfs-driver-intel_sdsi index ab122125ff9a..96b92c105ec4 100644 --- a/Documentation/ABI/testing/sysfs-driver-intel_sdsi +++ b/Documentation/ABI/testing/sysfs-driver-intel_sdsi @@ -13,17 +13,19 @@ Description: Should the operation fail, one of the following error codes may be returned: + ========== ===== Error Code Cause - ---------- ----- - EIO General mailbox failure. Log may indicate cause. - EBUSY Mailbox is owned by another agent. - EPERM SDSI capability is not enabled in hardware. - EPROTO Failure in mailbox protocol detected by driver. + ========== ===== + EIO General mailbox failure. Log may indicate cause. + EBUSY Mailbox is owned by another agent. + EPERM SDSI capability is not enabled in hardware. + EPROTO Failure in mailbox protocol detected by driver. See log for details. - EOVERFLOW For provision commands, the size of the data + EOVERFLOW For provision commands, the size of the data exceeds what may be written. - ESPIPE Seeking is not allowed. - ETIMEDOUT Failure to complete mailbox transaction in time. + ESPIPE Seeking is not allowed. + ETIMEDOUT Failure to complete mailbox transaction in time. + ========== ===== What: /sys/bus/auxiliary/devices/intel_vsec.sdsi.X/guid Date: Feb 2022 diff --git a/Documentation/ABI/testing/sysfs-driver-xen-blkback b/Documentation/ABI/testing/sysfs-driver-xen-blkback index a74dfe52dd76..7faf719af165 100644 --- a/Documentation/ABI/testing/sysfs-driver-xen-blkback +++ b/Documentation/ABI/testing/sysfs-driver-xen-blkback @@ -29,7 +29,7 @@ Description: What: /sys/module/xen_blkback/parameters/buffer_squeeze_duration_ms Date: December 2019 KernelVersion: 5.6 -Contact: SeongJae Park <sj@kernel.org> +Contact: Maximilian Heyne <mheyne@amazon.de> Description: When memory pressure is reported to blkback this option controls the duration in milliseconds that blkback will not @@ -39,7 +39,7 @@ Description: What: /sys/module/xen_blkback/parameters/feature_persistent Date: September 2020 KernelVersion: 5.10 -Contact: SeongJae Park <sj@kernel.org> +Contact: Maximilian Heyne <mheyne@amazon.de> Description: Whether to enable the persistent grants feature or not. Note that this option only takes effect on newly created backends. diff --git a/Documentation/ABI/testing/sysfs-driver-xen-blkfront b/Documentation/ABI/testing/sysfs-driver-xen-blkfront index 61fd173fabfe..7f646c58832e 100644 --- a/Documentation/ABI/testing/sysfs-driver-xen-blkfront +++ b/Documentation/ABI/testing/sysfs-driver-xen-blkfront @@ -12,7 +12,7 @@ Description: What: /sys/module/xen_blkfront/parameters/feature_persistent Date: September 2020 KernelVersion: 5.10 -Contact: SeongJae Park <sj@kernel.org> +Contact: Maximilian Heyne <mheyne@amazon.de> Description: Whether to enable the persistent grants feature or not. Note that this option only takes effect on newly created frontends. diff --git a/Documentation/ABI/testing/sysfs-fs-erofs b/Documentation/ABI/testing/sysfs-fs-erofs index 05482374a741..bb4681a01811 100644 --- a/Documentation/ABI/testing/sysfs-fs-erofs +++ b/Documentation/ABI/testing/sysfs-fs-erofs @@ -9,8 +9,9 @@ Description: Shows all enabled kernel features. What: /sys/fs/erofs/<disk>/sync_decompress Date: November 2021 Contact: "Huang Jianan" <huangjianan@oppo.com> -Description: Control strategy of sync decompression +Description: Control strategy of sync decompression: + - 0 (default, auto): enable for readpage, and enable for - readahead on atomic contexts only, + readahead on atomic contexts only. - 1 (force on): enable for readpage and readahead. - 2 (force off): disable for all situations. diff --git a/Documentation/ABI/testing/sysfs-platform-intel-ifs b/Documentation/ABI/testing/sysfs-platform-intel-ifs new file mode 100644 index 000000000000..486d6d2ff8a0 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-platform-intel-ifs @@ -0,0 +1,39 @@ +What: /sys/devices/virtual/misc/intel_ifs_<N>/run_test +Date: April 21 2022 +KernelVersion: 5.19 +Contact: "Jithu Joseph" <jithu.joseph@intel.com> +Description: Write <cpu#> to trigger IFS test for one online core. + Note that the test is per core. The cpu# can be + for any thread on the core. Running on one thread + completes the test for the core containing that thread. + Example: to test the core containing cpu5: echo 5 > + /sys/devices/platform/intel_ifs.<N>/run_test + +What: /sys/devices/virtual/misc/intel_ifs_<N>/status +Date: April 21 2022 +KernelVersion: 5.19 +Contact: "Jithu Joseph" <jithu.joseph@intel.com> +Description: The status of the last test. It can be one of "pass", "fail" + or "untested". + +What: /sys/devices/virtual/misc/intel_ifs_<N>/details +Date: April 21 2022 +KernelVersion: 5.19 +Contact: "Jithu Joseph" <jithu.joseph@intel.com> +Description: Additional information regarding the last test. The details file reports + the hex value of the SCAN_STATUS MSR. Note that the error_code field + may contain driver defined software code not defined in the Intel SDM. + +What: /sys/devices/virtual/misc/intel_ifs_<N>/image_version +Date: April 21 2022 +KernelVersion: 5.19 +Contact: "Jithu Joseph" <jithu.joseph@intel.com> +Description: Version (hexadecimal) of loaded IFS binary image. If no scan image + is loaded reports "none". + +What: /sys/devices/virtual/misc/intel_ifs_<N>/reload +Date: April 21 2022 +KernelVersion: 5.19 +Contact: "Jithu Joseph" <jithu.joseph@intel.com> +Description: Write "1" (or "y" or "Y") to reload the IFS image from + /lib/firmware/intel/ifs/ff-mm-ss.scan. diff --git a/Documentation/RCU/Design/Data-Structures/Data-Structures.rst b/Documentation/RCU/Design/Data-Structures/Data-Structures.rst index f4efd6897b09..b34990c7c377 100644 --- a/Documentation/RCU/Design/Data-Structures/Data-Structures.rst +++ b/Documentation/RCU/Design/Data-Structures/Data-Structures.rst @@ -973,7 +973,7 @@ The ``->dynticks`` field counts the corresponding CPU's transitions to and from either dyntick-idle or user mode, so that this counter has an even value when the CPU is in dyntick-idle mode or user mode and an odd value otherwise. The transitions to/from user mode need to be counted -for user mode adaptive-ticks support (see timers/NO_HZ.txt). +for user mode adaptive-ticks support (see Documentation/timers/no_hz.rst). The ``->rcu_need_heavy_qs`` field is used to record the fact that the RCU core code would really like to see a quiescent state from the diff --git a/Documentation/RCU/Design/Expedited-Grace-Periods/Expedited-Grace-Periods.rst b/Documentation/RCU/Design/Expedited-Grace-Periods/Expedited-Grace-Periods.rst index 6f89cf1e567d..c9c957c85bac 100644 --- a/Documentation/RCU/Design/Expedited-Grace-Periods/Expedited-Grace-Periods.rst +++ b/Documentation/RCU/Design/Expedited-Grace-Periods/Expedited-Grace-Periods.rst @@ -406,7 +406,7 @@ In earlier implementations, the task requesting the expedited grace period also drove it to completion. This straightforward approach had the disadvantage of needing to account for POSIX signals sent to user tasks, so more recent implemementations use the Linux kernel's -`workqueues <https://www.kernel.org/doc/Documentation/core-api/workqueue.rst>`__. +workqueues (see Documentation/core-api/workqueue.rst). The requesting task still does counter snapshotting and funnel-lock processing, but the task reaching the top of the funnel lock does a diff --git a/Documentation/RCU/Design/Requirements/Requirements.rst b/Documentation/RCU/Design/Requirements/Requirements.rst index 45278e2974c0..04ed8bf27a0e 100644 --- a/Documentation/RCU/Design/Requirements/Requirements.rst +++ b/Documentation/RCU/Design/Requirements/Requirements.rst @@ -370,8 +370,8 @@ pointer fetched by rcu_dereference() may not be used outside of the outermost RCU read-side critical section containing that rcu_dereference(), unless protection of the corresponding data element has been passed from RCU to some other synchronization -mechanism, most commonly locking or `reference -counting <https://www.kernel.org/doc/Documentation/RCU/rcuref.txt>`__. +mechanism, most commonly locking or reference counting +(see ../../rcuref.rst). .. |high-quality implementation of C11 memory_order_consume [PDF]| replace:: high-quality implementation of C11 ``memory_order_consume`` [PDF] .. _high-quality implementation of C11 memory_order_consume [PDF]: http://www.rdrop.com/users/paulmck/RCU/consume.2015.07.13a.pdf @@ -2654,6 +2654,38 @@ synchronize_rcu(), and rcu_barrier(), respectively. In three APIs are therefore implemented by separate functions that check for voluntary context switches. +Tasks Rude RCU +~~~~~~~~~~~~~~ + +Some forms of tracing need to wait for all preemption-disabled regions +of code running on any online CPU, including those executed when RCU is +not watching. This means that synchronize_rcu() is insufficient, and +Tasks Rude RCU must be used instead. This flavor of RCU does its work by +forcing a workqueue to be scheduled on each online CPU, hence the "Rude" +moniker. And this operation is considered to be quite rude by real-time +workloads that don't want their ``nohz_full`` CPUs receiving IPIs and +by battery-powered systems that don't want their idle CPUs to be awakened. + +The tasks-rude-RCU API is also reader-marking-free and thus quite compact, +consisting of call_rcu_tasks_rude(), synchronize_rcu_tasks_rude(), +and rcu_barrier_tasks_rude(). + +Tasks Trace RCU +~~~~~~~~~~~~~~~ + +Some forms of tracing need to sleep in readers, but cannot tolerate +SRCU's read-side overhead, which includes a full memory barrier in both +srcu_read_lock() and srcu_read_unlock(). This need is handled by a +Tasks Trace RCU that uses scheduler locking and IPIs to synchronize with +readers. Real-time systems that cannot tolerate IPIs may build their +kernels with ``CONFIG_TASKS_TRACE_RCU_READ_MB=y``, which avoids the IPIs at +the expense of adding full memory barriers to the read-side primitives. + +The tasks-trace-RCU API is also reasonably compact, +consisting of rcu_read_lock_trace(), rcu_read_unlock_trace(), +rcu_read_lock_trace_held(), call_rcu_tasks_trace(), +synchronize_rcu_tasks_trace(), and rcu_barrier_tasks_trace(). + Possible Future Changes ----------------------- diff --git a/Documentation/RCU/arrayRCU.rst b/Documentation/RCU/arrayRCU.rst index 4051ea3871ef..a5f2ff8fc54c 100644 --- a/Documentation/RCU/arrayRCU.rst +++ b/Documentation/RCU/arrayRCU.rst @@ -33,8 +33,8 @@ Situation 1: Hash Tables Hash tables are often implemented as an array, where each array entry has a linked-list hash chain. Each hash chain can be protected by RCU -as described in the listRCU.txt document. This approach also applies -to other array-of-list situations, such as radix trees. +as described in listRCU.rst. This approach also applies to other +array-of-list situations, such as radix trees. .. _static_arrays: diff --git a/Documentation/RCU/checklist.rst b/Documentation/RCU/checklist.rst index f4545b7c9a63..42cc5d891bd2 100644 --- a/Documentation/RCU/checklist.rst +++ b/Documentation/RCU/checklist.rst @@ -140,8 +140,7 @@ over a rather long period of time, but improvements are always welcome! prevents destructive compiler optimizations. However, with a bit of devious creativity, it is possible to mishandle the return value from rcu_dereference(). - Please see rcu_dereference.txt in this directory for - more information. + Please see rcu_dereference.rst for more information. The rcu_dereference() primitive is used by the various "_rcu()" list-traversal primitives, such @@ -151,7 +150,7 @@ over a rather long period of time, but improvements are always welcome! primitives. This is particularly useful in code that is common to readers and updaters. However, lockdep will complain if you access rcu_dereference() outside - of an RCU read-side critical section. See lockdep.txt + of an RCU read-side critical section. See lockdep.rst to learn what to do about this. Of course, neither rcu_dereference() nor the "_rcu()" @@ -323,7 +322,7 @@ over a rather long period of time, but improvements are always welcome! primitives when the update-side lock is held is that doing so can be quite helpful in reducing code bloat when common code is shared between readers and updaters. Additional primitives - are provided for this case, as discussed in lockdep.txt. + are provided for this case, as discussed in lockdep.rst. One exception to this rule is when data is only ever added to the linked data structure, and is never removed during any @@ -480,4 +479,4 @@ over a rather long period of time, but improvements are always welcome! both rcu_barrier() and synchronize_rcu(), if necessary, using something like workqueues to to execute them concurrently. - See rcubarrier.txt for more information. + See rcubarrier.rst for more information. diff --git a/Documentation/RCU/rcu.rst b/Documentation/RCU/rcu.rst index 0e03c6ef3147..3cfe01ba9a49 100644 --- a/Documentation/RCU/rcu.rst +++ b/Documentation/RCU/rcu.rst @@ -10,9 +10,8 @@ A "grace period" must elapse between the two parts, and this grace period must be long enough that any readers accessing the item being deleted have since dropped their references. For example, an RCU-protected deletion from a linked list would first remove the item from the list, wait for -a grace period to elapse, then free the element. See the -:ref:`Documentation/RCU/listRCU.rst <list_rcu_doc>` for more information on -using RCU with linked lists. +a grace period to elapse, then free the element. See listRCU.rst for more +information on using RCU with linked lists. Frequently Asked Questions -------------------------- @@ -50,7 +49,7 @@ Frequently Asked Questions - If I am running on a uniprocessor kernel, which can only do one thing at a time, why should I wait for a grace period? - See :ref:`Documentation/RCU/UP.rst <up_doc>` for more information. + See UP.rst for more information. - How can I see where RCU is currently used in the Linux kernel? @@ -64,13 +63,13 @@ Frequently Asked Questions - What guidelines should I follow when writing code that uses RCU? - See the checklist.txt file in this directory. + See checklist.rst. - Why the name "RCU"? "RCU" stands for "read-copy update". - :ref:`Documentation/RCU/listRCU.rst <list_rcu_doc>` has more information on where - this name came from, search for "read-copy update" to find it. + listRCU.rst has more information on where this name came from, search + for "read-copy update" to find it. - I hear that RCU is patented? What is with that? diff --git a/Documentation/RCU/rculist_nulls.rst b/Documentation/RCU/rculist_nulls.rst index a9fc774bc400..ca4692775ad4 100644 --- a/Documentation/RCU/rculist_nulls.rst +++ b/Documentation/RCU/rculist_nulls.rst @@ -8,7 +8,7 @@ This section describes how to use hlist_nulls to protect read-mostly linked lists and objects using SLAB_TYPESAFE_BY_RCU allocations. -Please read the basics in Documentation/RCU/listRCU.rst +Please read the basics in listRCU.rst. Using 'nulls' ============= diff --git a/Documentation/RCU/stallwarn.rst b/Documentation/RCU/stallwarn.rst index 78404625bad2..794837eb519b 100644 --- a/Documentation/RCU/stallwarn.rst +++ b/Documentation/RCU/stallwarn.rst @@ -162,6 +162,26 @@ CONFIG_RCU_CPU_STALL_TIMEOUT Stall-warning messages may be enabled and disabled completely via /sys/module/rcupdate/parameters/rcu_cpu_stall_suppress. +CONFIG_RCU_EXP_CPU_STALL_TIMEOUT +-------------------------------- + + Same as the CONFIG_RCU_CPU_STALL_TIMEOUT parameter but only for + the expedited grace period. This parameter defines the period + of time that RCU will wait from the beginning of an expedited + grace period until it issues an RCU CPU stall warning. This time + period is normally 20 milliseconds on Android devices. A zero + value causes the CONFIG_RCU_CPU_STALL_TIMEOUT value to be used, + after conversion to milliseconds. + + This configuration parameter may be changed at runtime via the + /sys/module/rcupdate/parameters/rcu_exp_cpu_stall_timeout, however + this parameter is checked only at the beginning of a cycle. If you + are in a current stall cycle, setting it to a new value will change + the timeout for the -next- stall. + + Stall-warning messages may be enabled and disabled completely via + /sys/module/rcupdate/parameters/rcu_cpu_stall_suppress. + RCU_STALL_DELAY_DELTA --------------------- diff --git a/Documentation/RCU/whatisRCU.rst b/Documentation/RCU/whatisRCU.rst index c34d2212eaca..77ea260efd12 100644 --- a/Documentation/RCU/whatisRCU.rst +++ b/Documentation/RCU/whatisRCU.rst @@ -224,7 +224,7 @@ synchronize_rcu() be delayed. This property results in system resilience in face of denial-of-service attacks. Code using call_rcu() should limit update rate in order to gain this same sort of resilience. See - checklist.txt for some approaches to limiting the update rate. + checklist.rst for some approaches to limiting the update rate. rcu_assign_pointer() ^^^^^^^^^^^^^^^^^^^^ @@ -318,7 +318,7 @@ rcu_dereference() must prohibit. The rcu_dereference_protected() variant takes a lockdep expression to indicate which locks must be acquired by the caller. If the indicated protection is not provided, - a lockdep splat is emitted. See Documentation/RCU/Design/Requirements/Requirements.rst + a lockdep splat is emitted. See Design/Requirements/Requirements.rst and the API's code comments for more details and example usage. .. [2] If the list_for_each_entry_rcu() instance might be used by @@ -399,8 +399,7 @@ for specialized uses, but are relatively uncommon. This section shows a simple use of the core RCU API to protect a global pointer to a dynamically allocated structure. More-typical -uses of RCU may be found in :ref:`listRCU.rst <list_rcu_doc>`, -:ref:`arrayRCU.rst <array_rcu_doc>`, and :ref:`NMI-RCU.rst <NMI_rcu_doc>`. +uses of RCU may be found in listRCU.rst, arrayRCU.rst, and NMI-RCU.rst. :: struct foo { @@ -482,10 +481,9 @@ So, to sum up: RCU read-side critical sections that might be referencing that data item. -See checklist.txt for additional rules to follow when using RCU. -And again, more-typical uses of RCU may be found in :ref:`listRCU.rst -<list_rcu_doc>`, :ref:`arrayRCU.rst <array_rcu_doc>`, and :ref:`NMI-RCU.rst -<NMI_rcu_doc>`. +See checklist.rst for additional rules to follow when using RCU. +And again, more-typical uses of RCU may be found in listRCU.rst, +arrayRCU.rst, and NMI-RCU.rst. .. _4_whatisRCU: @@ -579,7 +577,7 @@ to avoid having to write your own callback:: kfree_rcu(old_fp, rcu); -Again, see checklist.txt for additional rules governing the use of RCU. +Again, see checklist.rst for additional rules governing the use of RCU. .. _5_whatisRCU: @@ -663,7 +661,7 @@ been able to write-acquire the lock otherwise. The smp_mb__after_spinlock() promotes synchronize_rcu() to a full memory barrier in compliance with the "Memory-Barrier Guarantees" listed in: - Documentation/RCU/Design/Requirements/Requirements.rst + Design/Requirements/Requirements.rst It is possible to nest rcu_read_lock(), since reader-writer locks may be recursively acquired. Note also that rcu_read_lock() is immune diff --git a/Documentation/accounting/psi.rst b/Documentation/accounting/psi.rst index 860fe651d645..5e40b3f437f9 100644 --- a/Documentation/accounting/psi.rst +++ b/Documentation/accounting/psi.rst @@ -37,11 +37,7 @@ Pressure interface Pressure information for each resource is exported through the respective file in /proc/pressure/ -- cpu, memory, and io. -The format for CPU is as such:: - - some avg10=0.00 avg60=0.00 avg300=0.00 total=0 - -and for memory and IO:: +The format is as such:: some avg10=0.00 avg60=0.00 avg300=0.00 total=0 full avg10=0.00 avg60=0.00 avg300=0.00 total=0 @@ -58,6 +54,9 @@ situation from a state where some tasks are stalled but the CPU is still doing productive work. As such, time spent in this subset of the stall state is tracked separately and exported in the "full" averages. +CPU full is undefined at the system level, but has been reported +since 5.13, so it is set to zero for backward compatibility. + The ratios (in %) are tracked as recent trends over ten, sixty, and three hundred second windows, which gives insight into short term events as well as medium and long term trends. The total absolute stall time diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 53c0144e150b..a9066cfb85a0 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -564,12 +564,17 @@ cio_ignore= [S390] See Documentation/s390/common_io.rst for details. - clearcpuid=BITNUM[,BITNUM...] [X86] + clearcpuid=X[,X...] [X86] Disable CPUID feature X for the kernel. See arch/x86/include/asm/cpufeatures.h for the valid bit - numbers. Note the Linux specific bits are not necessarily - stable over kernel options, but the vendor specific + numbers X. Note the Linux-specific bits are not necessarily + stable over kernel options, but the vendor-specific ones should be. + X can also be a string as appearing in the flags: line + in /proc/cpuinfo which does not have the above + instability issue. However, not all features have names + in /proc/cpuinfo. + Note that using this option will taint your kernel. Also note that user programs calling CPUID directly or using the feature without checking anything will still see it. This just prevents it from @@ -831,7 +836,7 @@ Documentation/admin-guide/kdump/kdump.rst for an example. crashkernel=size[KMG],high - [KNL, X86-64] range could be above 4G. Allow kernel + [KNL, X86-64, ARM64] range could be above 4G. Allow kernel to allocate physical memory region from top, so could be above 4G if system have more than 4G ram installed. Otherwise memory region will be allocated below 4G, if @@ -844,14 +849,20 @@ that require some amount of low memory, e.g. swiotlb requires at least 64M+32K low memory, also enough extra low memory is needed to make sure DMA buffers for 32-bit - devices won't run out. Kernel would try to allocate at + devices won't run out. Kernel would try to allocate at least 256M below 4G automatically. - This one let user to specify own low range under 4G + This one lets the user specify own low range under 4G for second kernel instead. 0: to disable low allocation. It will be ignored when crashkernel=X,high is not used or memory reserved is below 4G. + [KNL, ARM64] range in low memory. + This one lets the user specify a low range in the + DMA zone for the crash dump kernel. + It will be ignored when crashkernel=X,high is not used + or memory reserved is located in the DMA zones. + cryptomgr.notests [KNL] Disable crypto self-tests @@ -1917,7 +1928,8 @@ ima_template= [IMA] Select one of defined IMA measurements template formats. - Formats: { "ima" | "ima-ng" | "ima-sig" } + Formats: { "ima" | "ima-ng" | "ima-ngv2" | "ima-sig" | + "ima-sigv2" } Default: "ima-ng" ima_template_fmt= @@ -2636,14 +2648,14 @@ when set. Format: <int> - libata.force= [LIBATA] Force configurations. The format is comma- - separated list of "[ID:]VAL" where ID is - PORT[.DEVICE]. PORT and DEVICE are decimal numbers - matching port, link or device. Basically, it matches - the ATA ID string printed on console by libata. If - the whole ID part is omitted, the last PORT and DEVICE - values are used. If ID hasn't been specified yet, the - configuration applies to all ports, links and devices. + libata.force= [LIBATA] Force configurations. The format is a comma- + separated list of "[ID:]VAL" where ID is PORT[.DEVICE]. + PORT and DEVICE are decimal numbers matching port, link + or device. Basically, it matches the ATA ID string + printed on console by libata. If the whole ID part is + omitted, the last PORT and DEVICE values are used. If + ID hasn't been specified yet, the configuration applies + to all ports, links and devices. If only DEVICE is omitted, the parameter applies to the port and all links and devices behind it. DEVICE @@ -2653,7 +2665,7 @@ host link and device attached to it. The VAL specifies the configuration to force. As long - as there's no ambiguity shortcut notation is allowed. + as there is no ambiguity, shortcut notation is allowed. For example, both 1.5 and 1.5G would work for 1.5Gbps. The following configurations can be forced. @@ -2666,19 +2678,58 @@ udma[/][16,25,33,44,66,100,133] notation is also allowed. + * nohrst, nosrst, norst: suppress hard, soft and both + resets. + + * rstonce: only attempt one reset during hot-unplug + link recovery. + + * [no]dbdelay: Enable or disable the extra 200ms delay + before debouncing a link PHY and device presence + detection. + * [no]ncq: Turn on or off NCQ. - * [no]ncqtrim: Turn off queued DSM TRIM. + * [no]ncqtrim: Enable or disable queued DSM TRIM. + + * [no]ncqati: Enable or disable NCQ trim on ATI chipset. + + * [no]trim: Enable or disable (unqueued) TRIM. + + * trim_zero: Indicate that TRIM command zeroes data. + + * max_trim_128m: Set 128M maximum trim size limit. + + * [no]dma: Turn on or off DMA transfers. + + * atapi_dmadir: Enable ATAPI DMADIR bridge support. + + * atapi_mod16_dma: Enable the use of ATAPI DMA for + commands that are not a multiple of 16 bytes. + + * [no]dmalog: Enable or disable the use of the + READ LOG DMA EXT command to access logs. + + * [no]iddevlog: Enable or disable access to the + identify device data log. - * nohrst, nosrst, norst: suppress hard, soft - and both resets. + * [no]logdir: Enable or disable access to the general + purpose log directory. - * rstonce: only attempt one reset during - hot-unplug link recovery + * max_sec_128: Set transfer size limit to 128 sectors. - * dump_id: dump IDENTIFY data. + * max_sec_1024: Set or clear transfer size limit to + 1024 sectors. - * atapi_dmadir: Enable ATAPI DMADIR bridge support + * max_sec_lba48: Set or clear transfer size limit to + 65535 sectors. + + * [no]lpm: Enable or disable link power management. + + * [no]setxfer: Indicate if transfer speed mode setting + should be skipped. + + * dump_id: Dump IDENTIFY data. * disable: Disable this device. @@ -3117,6 +3168,7 @@ mds=off [X86] tsx_async_abort=off [X86] kvm.nx_huge_pages=off [X86] + srbds=off [X86,INTEL] no_entry_flush [PPC] no_uaccess_flush [PPC] @@ -3443,8 +3495,6 @@ nocache [ARM] - noclflush [BUGS=X86] Don't use the CLFLUSH instruction - nodsp [SH] Disable hardware DSP at boot time. noefi Disable EFI runtime services support. @@ -3453,16 +3503,11 @@ noexec [IA-64] - noexec [X86] - On X86-32 available only on PAE configured kernels. - noexec=on: enable non-executable mappings (default) - noexec=off: disable non-executable mappings - - nosmap [X86,PPC] + nosmap [PPC] Disable SMAP (Supervisor Mode Access Prevention) even if it is supported by processor. - nosmep [X86,PPC64s] + nosmep [PPC64s] Disable SMEP (Supervisor Mode Execution Prevention) even if it is supported by processor. @@ -3662,8 +3707,6 @@ nosbagart [IA-64] - nosep [BUGS=X86-32] Disables x86 SYSENTER/SYSEXIT support. - nosgx [X86-64,SGX] Disables Intel SGX kernel support. nosmp [SMP] Tells an SMP kernel to act as a UP kernel, @@ -4883,6 +4926,18 @@ rcupdate.rcu_cpu_stall_timeout= [KNL] Set timeout for RCU CPU stall warning messages. + The value is in seconds and the maximum allowed + value is 300 seconds. + + rcupdate.rcu_exp_cpu_stall_timeout= [KNL] + Set timeout for expedited RCU CPU stall warning + messages. The value is in milliseconds + and the maximum allowed value is 21000 + milliseconds. Please note that this value is + adjusted to an arch timer tick resolution. + Setting this to zero causes the value from + rcupdate.rcu_cpu_stall_timeout to be used (after + conversion from seconds to milliseconds). rcupdate.rcu_expedited= [KNL] Use expedited grace-period primitives, for @@ -4945,10 +5000,34 @@ number avoids disturbing real-time workloads, but lengthens grace periods. + rcupdate.rcu_task_stall_info= [KNL] + Set initial timeout in jiffies for RCU task stall + informational messages, which give some indication + of the problem for those not patient enough to + wait for ten minutes. Informational messages are + only printed prior to the stall-warning message + for a given grace period. Disable with a value + less than or equal to zero. Defaults to ten + seconds. A change in value does not take effect + until the beginning of the next grace period. + + rcupdate.rcu_task_stall_info_mult= [KNL] + Multiplier for time interval between successive + RCU task stall informational messages for a given + RCU tasks grace period. This value is clamped + to one through ten, inclusive. It defaults to + the value three, so that the first informational + message is printed 10 seconds into the grace + period, the second at 40 seconds, the third at + 160 seconds, and then the stall warning at 600 + seconds would prevent a fourth at 640 seconds. + rcupdate.rcu_task_stall_timeout= [KNL] - Set timeout in jiffies for RCU task stall warning - messages. Disable with a value less than or equal - to zero. + Set timeout in jiffies for RCU task stall + warning messages. Disable with a value less + than or equal to zero. Defaults to ten minutes. + A change in value does not take effect until + the beginning of the next grace period. rcupdate.rcu_self_test= [KNL] Run the RCU early boot self tests @@ -5289,6 +5368,8 @@ serialnumber [BUGS=X86-32] + sev=option[,option...] [X86-64] See Documentation/x86/x86_64/boot-options.rst + shapers= [NET] Maximal number of shapers. @@ -5358,6 +5439,17 @@ smart2= [HW] Format: <io1>[,<io2>[,...,<io8>]] + smp.csd_lock_timeout= [KNL] + Specify the period of time in milliseconds + that smp_call_function() and friends will wait + for a CPU to release the CSD lock. This is + useful when diagnosing bugs involving CPUs + disabling interrupts for extended periods + of time. Defaults to 5,000 milliseconds, and + setting a value of zero disables this feature. + This feature may be more efficiently disabled + using the csdlock_debug- kernel parameter. + smsc-ircc2.nopnp [HW] Don't use PNP to discover SMC devices smsc-ircc2.ircc_cfg= [HW] Device configuration I/O port smsc-ircc2.ircc_sir= [HW] SIR base I/O port @@ -5589,6 +5681,30 @@ off: Disable mitigation and remove performance impact to RDRAND and RDSEED + srcutree.big_cpu_lim [KNL] + Specifies the number of CPUs constituting a + large system, such that srcu_struct structures + should immediately allocate an srcu_node array. + This kernel-boot parameter defaults to 128, + but takes effect only when the low-order four + bits of srcutree.convert_to_big is equal to 3 + (decide at boot). + + srcutree.convert_to_big [KNL] + Specifies under what conditions an SRCU tree + srcu_struct structure will be converted to big + form, that is, with an rcu_node tree: + + 0: Never. + 1: At init_srcu_struct() time. + 2: When rcutorture decides to. + 3: Decide at boot time (default). + 0x1X: Above plus if high contention. + + Either way, the srcu_node tree will be sized based + on the actual runtime number of CPUs (nr_cpu_ids) + instead of the compile-time CONFIG_NR_CPUS. + srcutree.counter_wrap_check [KNL] Specifies how frequently to check for grace-period sequence counter wrap for the @@ -5606,6 +5722,14 @@ expediting. Set to zero to disable automatic expediting. + srcutree.small_contention_lim [KNL] + Specifies the number of update-side contention + events per jiffy will be tolerated before + initiating a conversion of an srcu_struct + structure to big form. Note that the value of + srcutree.convert_to_big must have the 0x10 bit + set for contention-based conversions to occur. + ssbd= [ARM64,HW] Speculative Store Bypass Disable control @@ -5963,11 +6087,22 @@ sources: - "tpm" - "tee" + - "caam" If not specified then it defaults to iterating through the trust source list starting with TPM and assigns the first trust source as a backend which is initialized successfully during iteration. + trusted.rng= [KEYS] + Format: <string> + The RNG used to generate key material for trusted keys. + Can be one of: + - "kernel" + - the same value as trusted.source: "tpm" or "tee" + - "default" + If not specified, "default" is used. In this case, + the RNG's choice is left to each individual trust source. + tsc= Disable clocksource stability checks for TSC. Format: <string> [x86] reliable: mark tsc clocksource as reliable, this diff --git a/Documentation/admin-guide/media/vimc.dot b/Documentation/admin-guide/media/vimc.dot index 57863a13fa39..8e829c164626 100644 --- a/Documentation/admin-guide/media/vimc.dot +++ b/Documentation/admin-guide/media/vimc.dot @@ -9,14 +9,14 @@ digraph board { n00000003:port0 -> n00000008:port0 [style=bold] n00000003:port0 -> n0000000f [style=bold] n00000005 [label="{{<port0> 0} | Debayer A\n/dev/v4l-subdev2 | {<port1> 1}}", shape=Mrecord, style=filled, fillcolor=green] - n00000005:port1 -> n00000017:port0 + n00000005:port1 -> n00000015:port0 n00000008 [label="{{<port0> 0} | Debayer B\n/dev/v4l-subdev3 | {<port1> 1}}", shape=Mrecord, style=filled, fillcolor=green] - n00000008:port1 -> n00000017:port0 [style=dashed] + n00000008:port1 -> n00000015:port0 [style=dashed] n0000000b [label="Raw Capture 0\n/dev/video0", shape=box, style=filled, fillcolor=yellow] n0000000f [label="Raw Capture 1\n/dev/video1", shape=box, style=filled, fillcolor=yellow] - n00000013 [label="RGB/YUV Input\n/dev/video2", shape=box, style=filled, fillcolor=yellow] - n00000013 -> n00000017:port0 [style=dashed] - n00000017 [label="{{<port0> 0} | Scaler\n/dev/v4l-subdev4 | {<port1> 1}}", shape=Mrecord, style=filled, fillcolor=green] - n00000017:port1 -> n0000001a [style=bold] - n0000001a [label="RGB/YUV Capture\n/dev/video3", shape=box, style=filled, fillcolor=yellow] + n00000013 [label="{{} | RGB/YUV Input\n/dev/v4l-subdev4 | {<port0> 0}}", shape=Mrecord, style=filled, fillcolor=green] + n00000013:port0 -> n00000015:port0 [style=dashed] + n00000015 [label="{{<port0> 0} | Scaler\n/dev/v4l-subdev5 | {<port1> 1}}", shape=Mrecord, style=filled, fillcolor=green] + n00000015:port1 -> n00000018 [style=bold] + n00000018 [label="RGB/YUV Capture\n/dev/video2", shape=box, style=filled, fillcolor=yellow] } diff --git a/Documentation/admin-guide/sysctl/kernel.rst b/Documentation/admin-guide/sysctl/kernel.rst index 545d2d7420a1..ddccd1077462 100644 --- a/Documentation/admin-guide/sysctl/kernel.rst +++ b/Documentation/admin-guide/sysctl/kernel.rst @@ -1001,6 +1001,9 @@ This is a directory, with the following entries: * ``boot_id``: a UUID generated the first time this is retrieved, and unvarying after that; +* ``uuid``: a UUID generated every time this is retrieved (this can + thus be used to generate UUIDs at will); + * ``entropy_avail``: the pool's entropy count, in bits; * ``poolsize``: the entropy pool size, in bits; @@ -1008,10 +1011,7 @@ This is a directory, with the following entries: * ``urandom_min_reseed_secs``: obsolete (used to determine the minimum number of seconds between urandom pool reseeding). This file is writable for compatibility purposes, but writing to it has no effect - on any RNG behavior. - -* ``uuid``: a UUID generated every time this is retrieved (this can - thus be used to generate UUIDs at will); + on any RNG behavior; * ``write_wakeup_threshold``: when the entropy count drops below this (as a number of bits), processes waiting to write to ``/dev/random`` diff --git a/Documentation/arm64/booting.rst b/Documentation/arm64/booting.rst index 29884b261aa9..8aefa1001ae5 100644 --- a/Documentation/arm64/booting.rst +++ b/Documentation/arm64/booting.rst @@ -350,6 +350,16 @@ Before jumping into the kernel, the following conditions must be met: - SMCR_EL2.FA64 (bit 31) must be initialised to 0b1. + For CPUs with the Memory Tagging Extension feature (FEAT_MTE2): + + - If EL3 is present: + + - SCR_EL3.ATA (bit 26) must be initialised to 0b1. + + - If the kernel is entered at EL1 and EL2 is present: + + - HCR_EL2.ATA (bit 56) must be initialised to 0b1. + The requirements described above for CPU mode, caches, MMUs, architected timers, coherency and system registers apply to all CPUs. All CPUs must enter the kernel in the same exception level. Where the values documented diff --git a/Documentation/arm64/elf_hwcaps.rst b/Documentation/arm64/elf_hwcaps.rst index a8f30963e550..f8d818eaaff5 100644 --- a/Documentation/arm64/elf_hwcaps.rst +++ b/Documentation/arm64/elf_hwcaps.rst @@ -264,6 +264,39 @@ HWCAP2_MTE3 Functionality implied by ID_AA64PFR1_EL1.MTE == 0b0011, as described by Documentation/arm64/memory-tagging-extension.rst. +HWCAP2_SME + + Functionality implied by ID_AA64PFR1_EL1.SME == 0b0001, as described + by Documentation/arm64/sme.rst. + +HWCAP2_SME_I16I64 + + Functionality implied by ID_AA64SMFR0_EL1.I16I64 == 0b1111. + +HWCAP2_SME_F64F64 + + Functionality implied by ID_AA64SMFR0_EL1.F64F64 == 0b1. + +HWCAP2_SME_I8I32 + + Functionality implied by ID_AA64SMFR0_EL1.I8I32 == 0b1111. + +HWCAP2_SME_F16F32 + + Functionality implied by ID_AA64SMFR0_EL1.F16F32 == 0b1. + +HWCAP2_SME_B16F32 + + Functionality implied by ID_AA64SMFR0_EL1.B16F32 == 0b1. + +HWCAP2_SME_F32F32 + + Functionality implied by ID_AA64SMFR0_EL1.F32F32 == 0b1. + +HWCAP2_SME_FA64 + + Functionality implied by ID_AA64SMFR0_EL1.FA64 == 0b1. + 4. Unused AT_HWCAP bits ----------------------- diff --git a/Documentation/arm64/index.rst b/Documentation/arm64/index.rst index 4f840bac083e..ae21f8118830 100644 --- a/Documentation/arm64/index.rst +++ b/Documentation/arm64/index.rst @@ -21,6 +21,7 @@ ARM64 Architecture perf pointer-authentication silicon-errata + sme sve tagged-address-abi tagged-pointers diff --git a/Documentation/arm64/memory-tagging-extension.rst b/Documentation/arm64/memory-tagging-extension.rst index dd27f78d7608..dbae47bba25e 100644 --- a/Documentation/arm64/memory-tagging-extension.rst +++ b/Documentation/arm64/memory-tagging-extension.rst @@ -228,10 +228,10 @@ Core dump support ----------------- The allocation tags for user memory mapped with ``PROT_MTE`` are dumped -in the core file as additional ``PT_ARM_MEMTAG_MTE`` segments. The +in the core file as additional ``PT_AARCH64_MEMTAG_MTE`` segments. The program header for such segment is defined as: -:``p_type``: ``PT_ARM_MEMTAG_MTE`` +:``p_type``: ``PT_AARCH64_MEMTAG_MTE`` :``p_flags``: 0 :``p_offset``: segment file offset :``p_vaddr``: segment virtual address, same as the corresponding diff --git a/Documentation/arm64/silicon-errata.rst b/Documentation/arm64/silicon-errata.rst index 466cb9e89047..d27db84d585e 100644 --- a/Documentation/arm64/silicon-errata.rst +++ b/Documentation/arm64/silicon-errata.rst @@ -189,6 +189,9 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | Qualcomm Tech. | Kryo4xx Silver | N/A | ARM64_ERRATUM_1024718 | +----------------+-----------------+-----------------+-----------------------------+ +| Qualcomm Tech. | Kryo4xx Gold | N/A | ARM64_ERRATUM_1286807 | ++----------------+-----------------+-----------------+-----------------------------+ + +----------------+-----------------+-----------------+-----------------------------+ | Fujitsu | A64FX | E#010001 | FUJITSU_ERRATUM_010001 | +----------------+-----------------+-----------------+-----------------------------+ diff --git a/Documentation/arm64/sme.rst b/Documentation/arm64/sme.rst new file mode 100644 index 000000000000..8ba677b87e90 --- /dev/null +++ b/Documentation/arm64/sme.rst @@ -0,0 +1,428 @@ +=================================================== +Scalable Matrix Extension support for AArch64 Linux +=================================================== + +This document outlines briefly the interface provided to userspace by Linux in +order to support use of the ARM Scalable Matrix Extension (SME). + +This is an outline of the most important features and issues only and not +intended to be exhaustive. It should be read in conjunction with the SVE +documentation in sve.rst which provides details on the Streaming SVE mode +included in SME. + +This document does not aim to describe the SME architecture or programmer's +model. To aid understanding, a minimal description of relevant programmer's +model features for SME is included in Appendix A. + + +1. General +----------- + +* PSTATE.SM, PSTATE.ZA, the streaming mode vector length, the ZA + register state and TPIDR2_EL0 are tracked per thread. + +* The presence of SME is reported to userspace via HWCAP2_SME in the aux vector + AT_HWCAP2 entry. Presence of this flag implies the presence of the SME + instructions and registers, and the Linux-specific system interfaces + described in this document. SME is reported in /proc/cpuinfo as "sme". + +* Support for the execution of SME instructions in userspace can also be + detected by reading the CPU ID register ID_AA64PFR1_EL1 using an MRS + instruction, and checking that the value of the SME field is nonzero. [3] + + It does not guarantee the presence of the system interfaces described in the + following sections: software that needs to verify that those interfaces are + present must check for HWCAP2_SME instead. + +* There are a number of optional SME features, presence of these is reported + through AT_HWCAP2 through: + + HWCAP2_SME_I16I64 + HWCAP2_SME_F64F64 + HWCAP2_SME_I8I32 + HWCAP2_SME_F16F32 + HWCAP2_SME_B16F32 + HWCAP2_SME_F32F32 + HWCAP2_SME_FA64 + + This list may be extended over time as the SME architecture evolves. + + These extensions are also reported via the CPU ID register ID_AA64SMFR0_EL1, + which userspace can read using an MRS instruction. See elf_hwcaps.txt and + cpu-feature-registers.txt for details. + +* Debuggers should restrict themselves to interacting with the target via the + NT_ARM_SVE, NT_ARM_SSVE and NT_ARM_ZA regsets. The recommended way + of detecting support for these regsets is to connect to a target process + first and then attempt a + + ptrace(PTRACE_GETREGSET, pid, NT_ARM_<regset>, &iov). + +* Whenever ZA register values are exchanged in memory between userspace and + the kernel, the register value is encoded in memory as a series of horizontal + vectors from 0 to VL/8-1 stored in the same endianness invariant format as is + used for SVE vectors. + +* On thread creation TPIDR2_EL0 is preserved unless CLONE_SETTLS is specified, + in which case it is set to 0. + +2. Vector lengths +------------------ + +SME defines a second vector length similar to the SVE vector length which is +controls the size of the streaming mode SVE vectors and the ZA matrix array. +The ZA matrix is square with each side having as many bytes as a streaming +mode SVE vector. + + +3. Sharing of streaming and non-streaming mode SVE state +--------------------------------------------------------- + +It is implementation defined which if any parts of the SVE state are shared +between streaming and non-streaming modes. When switching between modes +via software interfaces such as ptrace if no register content is provided as +part of switching no state will be assumed to be shared and everything will +be zeroed. + + +4. System call behaviour +------------------------- + +* On syscall PSTATE.ZA is preserved, if PSTATE.ZA==1 then the contents of the + ZA matrix are preserved. + +* On syscall PSTATE.SM will be cleared and the SVE registers will be handled + as per the standard SVE ABI. + +* Neither the SVE registers nor ZA are used to pass arguments to or receive + results from any syscall. + +* On process creation (eg, clone()) the newly created process will have + PSTATE.SM cleared. + +* All other SME state of a thread, including the currently configured vector + length, the state of the PR_SME_VL_INHERIT flag, and the deferred vector + length (if any), is preserved across all syscalls, subject to the specific + exceptions for execve() described in section 6. + + +5. Signal handling +------------------- + +* Signal handlers are invoked with streaming mode and ZA disabled. + +* A new signal frame record za_context encodes the ZA register contents on + signal delivery. [1] + +* The signal frame record for ZA always contains basic metadata, in particular + the thread's vector length (in za_context.vl). + +* The ZA matrix may or may not be included in the record, depending on + the value of PSTATE.ZA. The registers are present if and only if: + za_context.head.size >= ZA_SIG_CONTEXT_SIZE(sve_vq_from_vl(za_context.vl)) + in which case PSTATE.ZA == 1. + +* If matrix data is present, the remainder of the record has a vl-dependent + size and layout. Macros ZA_SIG_* are defined [1] to facilitate access to + them. + +* The matrix is stored as a series of horizontal vectors in the same format as + is used for SVE vectors. + +* If the ZA context is too big to fit in sigcontext.__reserved[], then extra + space is allocated on the stack, an extra_context record is written in + __reserved[] referencing this space. za_context is then written in the + extra space. Refer to [1] for further details about this mechanism. + + +5. Signal return +----------------- + +When returning from a signal handler: + +* If there is no za_context record in the signal frame, or if the record is + present but contains no register data as described in the previous section, + then ZA is disabled. + +* If za_context is present in the signal frame and contains matrix data then + PSTATE.ZA is set to 1 and ZA is populated with the specified data. + +* The vector length cannot be changed via signal return. If za_context.vl in + the signal frame does not match the current vector length, the signal return + attempt is treated as illegal, resulting in a forced SIGSEGV. + + +6. prctl extensions +-------------------- + +Some new prctl() calls are added to allow programs to manage the SME vector +length: + +prctl(PR_SME_SET_VL, unsigned long arg) + + Sets the vector length of the calling thread and related flags, where + arg == vl | flags. Other threads of the calling process are unaffected. + + vl is the desired vector length, where sve_vl_valid(vl) must be true. + + flags: + + PR_SME_VL_INHERIT + + Inherit the current vector length across execve(). Otherwise, the + vector length is reset to the system default at execve(). (See + Section 9.) + + PR_SME_SET_VL_ONEXEC + + Defer the requested vector length change until the next execve() + performed by this thread. + + The effect is equivalent to implicit execution of the following + call immediately after the next execve() (if any) by the thread: + + prctl(PR_SME_SET_VL, arg & ~PR_SME_SET_VL_ONEXEC) + + This allows launching of a new program with a different vector + length, while avoiding runtime side effects in the caller. + + Without PR_SME_SET_VL_ONEXEC, the requested change takes effect + immediately. + + + Return value: a nonnegative on success, or a negative value on error: + EINVAL: SME not supported, invalid vector length requested, or + invalid flags. + + + On success: + + * Either the calling thread's vector length or the deferred vector length + to be applied at the next execve() by the thread (dependent on whether + PR_SME_SET_VL_ONEXEC is present in arg), is set to the largest value + supported by the system that is less than or equal to vl. If vl == + SVE_VL_MAX, the value set will be the largest value supported by the + system. + + * Any previously outstanding deferred vector length change in the calling + thread is cancelled. + + * The returned value describes the resulting configuration, encoded as for + PR_SME_GET_VL. The vector length reported in this value is the new + current vector length for this thread if PR_SME_SET_VL_ONEXEC was not + present in arg; otherwise, the reported vector length is the deferred + vector length that will be applied at the next execve() by the calling + thread. + + * Changing the vector length causes all of ZA, P0..P15, FFR and all bits of + Z0..Z31 except for Z0 bits [127:0] .. Z31 bits [127:0] to become + unspecified, including both streaming and non-streaming SVE state. + Calling PR_SME_SET_VL with vl equal to the thread's current vector + length, or calling PR_SME_SET_VL with the PR_SVE_SET_VL_ONEXEC flag, + does not constitute a change to the vector length for this purpose. + + * Changing the vector length causes PSTATE.ZA and PSTATE.SM to be cleared. + Calling PR_SME_SET_VL with vl equal to the thread's current vector + length, or calling PR_SME_SET_VL with the PR_SVE_SET_VL_ONEXEC flag, + does not constitute a change to the vector length for this purpose. + + +prctl(PR_SME_GET_VL) + + Gets the vector length of the calling thread. + + The following flag may be OR-ed into the result: + + PR_SME_VL_INHERIT + + Vector length will be inherited across execve(). + + There is no way to determine whether there is an outstanding deferred + vector length change (which would only normally be the case between a + fork() or vfork() and the corresponding execve() in typical use). + + To extract the vector length from the result, bitwise and it with + PR_SME_VL_LEN_MASK. + + Return value: a nonnegative value on success, or a negative value on error: + EINVAL: SME not supported. + + +7. ptrace extensions +--------------------- + +* A new regset NT_ARM_SSVE is defined for access to streaming mode SVE + state via PTRACE_GETREGSET and PTRACE_SETREGSET, this is documented in + sve.rst. + +* A new regset NT_ARM_ZA is defined for ZA state for access to ZA state via + PTRACE_GETREGSET and PTRACE_SETREGSET. + + Refer to [2] for definitions. + +The regset data starts with struct user_za_header, containing: + + size + + Size of the complete regset, in bytes. + This depends on vl and possibly on other things in the future. + + If a call to PTRACE_GETREGSET requests less data than the value of + size, the caller can allocate a larger buffer and retry in order to + read the complete regset. + + max_size + + Maximum size in bytes that the regset can grow to for the target + thread. The regset won't grow bigger than this even if the target + thread changes its vector length etc. + + vl + + Target thread's current streaming vector length, in bytes. + + max_vl + + Maximum possible streaming vector length for the target thread. + + flags + + Zero or more of the following flags, which have the same + meaning and behaviour as the corresponding PR_SET_VL_* flags: + + SME_PT_VL_INHERIT + + SME_PT_VL_ONEXEC (SETREGSET only). + +* The effects of changing the vector length and/or flags are equivalent to + those documented for PR_SME_SET_VL. + + The caller must make a further GETREGSET call if it needs to know what VL is + actually set by SETREGSET, unless is it known in advance that the requested + VL is supported. + +* The size and layout of the payload depends on the header fields. The + SME_PT_ZA_*() macros are provided to facilitate access to the data. + +* In either case, for SETREGSET it is permissible to omit the payload, in which + case the vector length and flags are changed and PSTATE.ZA is set to 0 + (along with any consequences of those changes). If a payload is provided + then PSTATE.ZA will be set to 1. + +* For SETREGSET, if the requested VL is not supported, the effect will be the + same as if the payload were omitted, except that an EIO error is reported. + No attempt is made to translate the payload data to the correct layout + for the vector length actually set. It is up to the caller to translate the + payload layout for the actual VL and retry. + +* The effect of writing a partial, incomplete payload is unspecified. + + +8. ELF coredump extensions +--------------------------- + +* NT_ARM_SSVE notes will be added to each coredump for + each thread of the dumped process. The contents will be equivalent to the + data that would have been read if a PTRACE_GETREGSET of the corresponding + type were executed for each thread when the coredump was generated. + +* A NT_ARM_ZA note will be added to each coredump for each thread of the + dumped process. The contents will be equivalent to the data that would have + been read if a PTRACE_GETREGSET of NT_ARM_ZA were executed for each thread + when the coredump was generated. + + +9. System runtime configuration +-------------------------------- + +* To mitigate the ABI impact of expansion of the signal frame, a policy + mechanism is provided for administrators, distro maintainers and developers + to set the default vector length for userspace processes: + +/proc/sys/abi/sme_default_vector_length + + Writing the text representation of an integer to this file sets the system + default vector length to the specified value, unless the value is greater + than the maximum vector length supported by the system in which case the + default vector length is set to that maximum. + + The result can be determined by reopening the file and reading its + contents. + + At boot, the default vector length is initially set to 32 or the maximum + supported vector length, whichever is smaller and supported. This + determines the initial vector length of the init process (PID 1). + + Reading this file returns the current system default vector length. + +* At every execve() call, the new vector length of the new process is set to + the system default vector length, unless + + * PR_SME_VL_INHERIT (or equivalently SME_PT_VL_INHERIT) is set for the + calling thread, or + + * a deferred vector length change is pending, established via the + PR_SME_SET_VL_ONEXEC flag (or SME_PT_VL_ONEXEC). + +* Modifying the system default vector length does not affect the vector length + of any existing process or thread that does not make an execve() call. + + +Appendix A. SME programmer's model (informative) +================================================= + +This section provides a minimal description of the additions made by SVE to the +ARMv8-A programmer's model that are relevant to this document. + +Note: This section is for information only and not intended to be complete or +to replace any architectural specification. + +A.1. Registers +--------------- + +In A64 state, SME adds the following: + +* A new mode, streaming mode, in which a subset of the normal FPSIMD and SVE + features are available. When supported EL0 software may enter and leave + streaming mode at any time. + + For best system performance it is strongly encouraged for software to enable + streaming mode only when it is actively being used. + +* A new vector length controlling the size of ZA and the Z registers when in + streaming mode, separately to the vector length used for SVE when not in + streaming mode. There is no requirement that either the currently selected + vector length or the set of vector lengths supported for the two modes in + a given system have any relationship. The streaming mode vector length + is referred to as SVL. + +* A new ZA matrix register. This is a square matrix of SVLxSVL bits. Most + operations on ZA require that streaming mode be enabled but ZA can be + enabled without streaming mode in order to load, save and retain data. + + For best system performance it is strongly encouraged for software to enable + ZA only when it is actively being used. + +* Two new 1 bit fields in PSTATE which may be controlled via the SMSTART and + SMSTOP instructions or by access to the SVCR system register: + + * PSTATE.ZA, if this is 1 then the ZA matrix is accessible and has valid + data while if it is 0 then ZA can not be accessed. When PSTATE.ZA is + changed from 0 to 1 all bits in ZA are cleared. + + * PSTATE.SM, if this is 1 then the PE is in streaming mode. When the value + of PSTATE.SM is changed then it is implementation defined if the subset + of the floating point register bits valid in both modes may be retained. + Any other bits will be cleared. + + +References +========== + +[1] arch/arm64/include/uapi/asm/sigcontext.h + AArch64 Linux signal ABI definitions + +[2] arch/arm64/include/uapi/asm/ptrace.h + AArch64 Linux ptrace ABI definitions + +[3] Documentation/arm64/cpu-feature-registers.rst diff --git a/Documentation/arm64/sve.rst b/Documentation/arm64/sve.rst index 9d9a4de5bc34..93c2c2990584 100644 --- a/Documentation/arm64/sve.rst +++ b/Documentation/arm64/sve.rst @@ -7,7 +7,9 @@ Author: Dave Martin <Dave.Martin@arm.com> Date: 4 August 2017 This document outlines briefly the interface provided to userspace by Linux in -order to support use of the ARM Scalable Vector Extension (SVE). +order to support use of the ARM Scalable Vector Extension (SVE), including +interactions with Streaming SVE mode added by the Scalable Matrix Extension +(SME). This is an outline of the most important features and issues only and not intended to be exhaustive. @@ -23,6 +25,10 @@ model features for SVE is included in Appendix A. * SVE registers Z0..Z31, P0..P15 and FFR and the current vector length VL, are tracked per-thread. +* In streaming mode FFR is not accessible unless HWCAP2_SME_FA64 is present + in the system, when it is not supported and these interfaces are used to + access streaming mode FFR is read and written as zero. + * The presence of SVE is reported to userspace via HWCAP_SVE in the aux vector AT_HWCAP entry. Presence of this flag implies the presence of the SVE instructions and registers, and the Linux-specific system interfaces @@ -53,10 +59,19 @@ model features for SVE is included in Appendix A. which userspace can read using an MRS instruction. See elf_hwcaps.txt and cpu-feature-registers.txt for details. +* On hardware that supports the SME extensions, HWCAP2_SME will also be + reported in the AT_HWCAP2 aux vector entry. Among other things SME adds + streaming mode which provides a subset of the SVE feature set using a + separate SME vector length and the same Z/V registers. See sme.rst + for more details. + * Debuggers should restrict themselves to interacting with the target via the NT_ARM_SVE regset. The recommended way of detecting support for this regset is to connect to a target process first and then attempt a - ptrace(PTRACE_GETREGSET, pid, NT_ARM_SVE, &iov). + ptrace(PTRACE_GETREGSET, pid, NT_ARM_SVE, &iov). Note that when SME is + present and streaming SVE mode is in use the FPSIMD subset of registers + will be read via NT_ARM_SVE and NT_ARM_SVE writes will exit streaming mode + in the target. * Whenever SVE scalable register values (Zn, Pn, FFR) are exchanged in memory between userspace and the kernel, the register value is encoded in memory in @@ -126,6 +141,11 @@ the SVE instruction set architecture. are only present in fpsimd_context. For convenience, the content of V0..V31 is duplicated between sve_context and fpsimd_context. +* The record contains a flag field which includes a flag SVE_SIG_FLAG_SM which + if set indicates that the thread is in streaming mode and the vector length + and register data (if present) describe the streaming SVE data and vector + length. + * The signal frame record for SVE always contains basic metadata, in particular the thread's vector length (in sve_context.vl). @@ -170,6 +190,11 @@ When returning from a signal handler: the signal frame does not match the current vector length, the signal return attempt is treated as illegal, resulting in a forced SIGSEGV. +* It is permitted to enter or leave streaming mode by setting or clearing + the SVE_SIG_FLAG_SM flag but applications should take care to ensure that + when doing so sve_context.vl and any register data are appropriate for the + vector length in the new mode. + 6. prctl extensions -------------------- @@ -265,8 +290,14 @@ prctl(PR_SVE_GET_VL) 7. ptrace extensions --------------------- -* A new regset NT_ARM_SVE is defined for use with PTRACE_GETREGSET and - PTRACE_SETREGSET. +* New regsets NT_ARM_SVE and NT_ARM_SSVE are defined for use with + PTRACE_GETREGSET and PTRACE_SETREGSET. NT_ARM_SSVE describes the + streaming mode SVE registers and NT_ARM_SVE describes the + non-streaming mode SVE registers. + + In this description a register set is referred to as being "live" when + the target is in the appropriate streaming or non-streaming mode and is + using data beyond the subset shared with the FPSIMD Vn registers. Refer to [2] for definitions. @@ -297,7 +328,7 @@ The regset data starts with struct user_sve_header, containing: flags - either + at most one of SVE_PT_REGS_FPSIMD @@ -331,6 +362,10 @@ The regset data starts with struct user_sve_header, containing: SVE_PT_VL_ONEXEC (SETREGSET only). + If neither FPSIMD nor SVE flags are provided then no register + payload is available, this is only possible when SME is implemented. + + * The effects of changing the vector length and/or flags are equivalent to those documented for PR_SVE_SET_VL. @@ -346,6 +381,13 @@ The regset data starts with struct user_sve_header, containing: case only the vector length and flags are changed (along with any consequences of those changes). +* In systems supporting SME when in streaming mode a GETREGSET for + NT_REG_SVE will return only the user_sve_header with no register data, + similarly a GETREGSET for NT_REG_SSVE will not return any register data + when not in streaming mode. + +* A GETREGSET for NT_ARM_SSVE will never return SVE_PT_REGS_FPSIMD. + * For SETREGSET, if an SVE_PT_REGS_SVE payload is present and the requested VL is not supported, the effect will be the same as if the payload were omitted, except that an EIO error is reported. No @@ -355,17 +397,25 @@ The regset data starts with struct user_sve_header, containing: unspecified. It is up to the caller to translate the payload layout for the actual VL and retry. +* Where SME is implemented it is not possible to GETREGSET the register + state for normal SVE when in streaming mode, nor the streaming mode + register state when in normal mode, regardless of the implementation defined + behaviour of the hardware for sharing data between the two modes. + +* Any SETREGSET of NT_ARM_SVE will exit streaming mode if the target was in + streaming mode and any SETREGSET of NT_ARM_SSVE will enter streaming mode + if the target was not in streaming mode. + * The effect of writing a partial, incomplete payload is unspecified. 8. ELF coredump extensions --------------------------- -* A NT_ARM_SVE note will be added to each coredump for each thread of the - dumped process. The contents will be equivalent to the data that would have - been read if a PTRACE_GETREGSET of NT_ARM_SVE were executed for each thread - when the coredump was generated. - +* NT_ARM_SVE and NT_ARM_SSVE notes will be added to each coredump for + each thread of the dumped process. The contents will be equivalent to the + data that would have been read if a PTRACE_GETREGSET of the corresponding + type were executed for each thread when the coredump was generated. 9. System runtime configuration -------------------------------- diff --git a/Documentation/cdrom/cdrom-standard.rst b/Documentation/cdrom/cdrom-standard.rst index 52ea7b6b2fe8..7964fe134277 100644 --- a/Documentation/cdrom/cdrom-standard.rst +++ b/Documentation/cdrom/cdrom-standard.rst @@ -218,7 +218,6 @@ current *struct* is:: int (*tray_move)(struct cdrom_device_info *, int); int (*lock_door)(struct cdrom_device_info *, int); int (*select_speed)(struct cdrom_device_info *, int); - int (*select_disc)(struct cdrom_device_info *, int); int (*get_last_session) (struct cdrom_device_info *, struct cdrom_multisession *); int (*get_mcn)(struct cdrom_device_info *, struct cdrom_mcn *); @@ -421,15 +420,6 @@ return value indicates an error. :: - int select_disc(struct cdrom_device_info *cdi, int number) - -If the drive can store multiple discs (a juke-box) this function -will perform disc selection. It should return the number of the -selected disc on success, a negative value on error. Currently, only -the ide-cd driver supports this functionality. - -:: - int get_last_session(struct cdrom_device_info *cdi, struct cdrom_multisession *ms_info) diff --git a/Documentation/core-api/index.rst b/Documentation/core-api/index.rst index 2bfbf7093338..dedd4d853329 100644 --- a/Documentation/core-api/index.rst +++ b/Documentation/core-api/index.rst @@ -21,6 +21,7 @@ it. watch_queue printk-basics printk-formats + printk-index symbol-namespaces Data structures and low-level utilities diff --git a/Documentation/core-api/printk-index.rst b/Documentation/core-api/printk-index.rst new file mode 100644 index 000000000000..3062f37d119b --- /dev/null +++ b/Documentation/core-api/printk-index.rst @@ -0,0 +1,137 @@ +.. SPDX-License-Identifier: GPL-2.0 + +============ +Printk Index +============ + +There are many ways how to monitor the state of the system. One important +source of information is the system log. It provides a lot of information, +including more or less important warnings and error messages. + +There are monitoring tools that filter and take action based on messages +logged. + +The kernel messages are evolving together with the code. As a result, +particular kernel messages are not KABI and never will be! + +It is a huge challenge for maintaining the system log monitors. It requires +knowing what messages were updated in a particular kernel version and why. +Finding these changes in the sources would require non-trivial parsers. +Also it would require matching the sources with the binary kernel which +is not always trivial. Various changes might be backported. Various kernel +versions might be used on different monitored systems. + +This is where the printk index feature might become useful. It provides +a dump of printk formats used all over the source code used for the kernel +and modules on the running system. It is accessible at runtime via debugfs. + +The printk index helps to find changes in the message formats. Also it helps +to track the strings back to the kernel sources and the related commit. + + +User Interface +============== + +The index of printk formats are split in into separate files. The files are +named according to the binaries where the printk formats are built-in. There +is always "vmlinux" and optionally also modules, for example:: + + /sys/kernel/debug/printk/index/vmlinux + /sys/kernel/debug/printk/index/ext4 + /sys/kernel/debug/printk/index/scsi_mod + +Note that only loaded modules are shown. Also printk formats from a module +might appear in "vmlinux" when the module is built-in. + +The content is inspired by the dynamic debug interface and looks like:: + + $> head -1 /sys/kernel/debug/printk/index/vmlinux; shuf -n 5 vmlinux + # <level[,flags]> filename:line function "format" + <5> block/blk-settings.c:661 disk_stack_limits "%s: Warning: Device %s is misaligned\n" + <4> kernel/trace/trace.c:8296 trace_create_file "Could not create tracefs '%s' entry\n" + <6> arch/x86/kernel/hpet.c:144 _hpet_print_config "hpet: %s(%d):\n" + <6> init/do_mounts.c:605 prepare_namespace "Waiting for root device %s...\n" + <6> drivers/acpi/osl.c:1410 acpi_no_auto_serialize_setup "ACPI: auto-serialization disabled\n" + +, where the meaning is: + + - :level: log level value: 0-7 for particular severity, -1 as default, + 'c' as continuous line without an explicit log level + - :flags: optional flags: currently only 'c' for KERN_CONT + - :filename\:line: source filename and line number of the related + printk() call. Note that there are many wrappers, for example, + pr_warn(), pr_warn_once(), dev_warn(). + - :function: function name where the printk() call is used. + - :format: format string + +The extra information makes it a bit harder to find differences +between various kernels. Especially the line number might change +very often. On the other hand, it helps a lot to confirm that +it is the same string or find the commit that is responsible +for eventual changes. + + +printk() Is Not a Stable KABI +============================= + +Several developers are afraid that exporting all these implementation +details into the user space will transform particular printk() calls +into KABI. + +But it is exactly the opposite. printk() calls must _not_ be KABI. +And the printk index helps user space tools to deal with this. + + +Subsystem specific printk wrappers +================================== + +The printk index is generated using extra metadata that are stored in +a dedicated .elf section ".printk_index". It is achieved using macro +wrappers doing __printk_index_emit() together with the real printk() +call. The same technique is used also for the metadata used by +the dynamic debug feature. + +The metadata are stored for a particular message only when it is printed +using these special wrappers. It is implemented for the commonly +used printk() calls, including, for example, pr_warn(), or pr_once(). + +Additional changes are necessary for various subsystem specific wrappers +that call the original printk() via a common helper function. These needs +their own wrappers adding __printk_index_emit(). + +Only few subsystem specific wrappers have been updated so far, +for example, dev_printk(). As a result, the printk formats from +some subsystes can be missing in the printk index. + + +Subsystem specific prefix +========================= + +The macro pr_fmt() macro allows to define a prefix that is printed +before the string generated by the related printk() calls. + +Subsystem specific wrappers usually add even more complicated +prefixes. + +These prefixes can be stored into the printk index metadata +by an optional parameter of __printk_index_emit(). The debugfs +interface might then show the printk formats including these prefixes. +For example, drivers/acpi/osl.c contains:: + + #define pr_fmt(fmt) "ACPI: OSL: " fmt + + static int __init acpi_no_auto_serialize_setup(char *str) + { + acpi_gbl_auto_serialize_methods = FALSE; + pr_info("Auto-serialization disabled\n"); + + return 1; + } + +This results in the following printk index entry:: + + <6> drivers/acpi/osl.c:1410 acpi_no_auto_serialize_setup "ACPI: auto-serialization disabled\n" + +It helps matching messages from the real log with printk index. +Then the source file name, line number, and function name can +be used to match the string with the source code. diff --git a/Documentation/core-api/timekeeping.rst b/Documentation/core-api/timekeeping.rst index 729e24864fe7..22ec68f24421 100644 --- a/Documentation/core-api/timekeeping.rst +++ b/Documentation/core-api/timekeeping.rst @@ -132,6 +132,7 @@ Some additional variants exist for more specialized cases: .. c:function:: u64 ktime_get_mono_fast_ns( void ) u64 ktime_get_raw_fast_ns( void ) u64 ktime_get_boot_fast_ns( void ) + u64 ktime_get_tai_fast_ns( void ) u64 ktime_get_real_fast_ns( void ) These variants are safe to call from any context, including from diff --git a/Documentation/dev-tools/kunit/start.rst b/Documentation/dev-tools/kunit/start.rst index ad168d16968f..867a4bba6bf6 100644 --- a/Documentation/dev-tools/kunit/start.rst +++ b/Documentation/dev-tools/kunit/start.rst @@ -41,13 +41,18 @@ or ``VFAT_FS``. To run ``FAT_KUNIT_TEST``, the ``.kunitconfig`` has: CONFIG_MSDOS_FS=y CONFIG_FAT_KUNIT_TEST=y -1. A good starting point for the ``.kunitconfig``, is the KUnit default - config. Run the command: +1. A good starting point for the ``.kunitconfig`` is the KUnit default config. + You can generate it by running: .. code-block:: bash cd $PATH_TO_LINUX_REPO - cp tools/testing/kunit/configs/default.config .kunitconfig + tools/testing/kunit/kunit.py config + cat .kunit/.kunitconfig + +.. note :: + ``.kunitconfig`` lives in the ``--build_dir`` used by kunit.py, which is + ``.kunit`` by default. .. note :: You may want to remove CONFIG_KUNIT_ALL_TESTS from the ``.kunitconfig`` as diff --git a/Documentation/devicetree/bindings/arm/tegra/nvidia,tegra20-pmc.yaml b/Documentation/devicetree/bindings/arm/tegra/nvidia,tegra20-pmc.yaml index 0afec83cc723..564ae6aaccf7 100644 --- a/Documentation/devicetree/bindings/arm/tegra/nvidia,tegra20-pmc.yaml +++ b/Documentation/devicetree/bindings/arm/tegra/nvidia,tegra20-pmc.yaml @@ -14,7 +14,6 @@ properties: compatible: enum: - nvidia,tegra20-pmc - - nvidia,tegra20-pmc - nvidia,tegra30-pmc - nvidia,tegra114-pmc - nvidia,tegra124-pmc diff --git a/Documentation/devicetree/bindings/ata/renesas,rcar-sata.yaml b/Documentation/devicetree/bindings/ata/renesas,rcar-sata.yaml index c060c7914cae..c4e4a9eab658 100644 --- a/Documentation/devicetree/bindings/ata/renesas,rcar-sata.yaml +++ b/Documentation/devicetree/bindings/ata/renesas,rcar-sata.yaml @@ -26,6 +26,7 @@ properties: - items: - enum: - renesas,sata-r8a774b1 # RZ/G2N + - renesas,sata-r8a774e1 # RZ/G2H - renesas,sata-r8a7795 # R-Car H3 - renesas,sata-r8a77965 # R-Car M3-N - const: renesas,rcar-gen3-sata # generic R-Car Gen3 or RZ/G2 diff --git a/Documentation/devicetree/bindings/bus/ti-sysc.yaml b/Documentation/devicetree/bindings/bus/ti-sysc.yaml index bd40213302da..fced4082b047 100644 --- a/Documentation/devicetree/bindings/bus/ti-sysc.yaml +++ b/Documentation/devicetree/bindings/bus/ti-sysc.yaml @@ -35,7 +35,6 @@ properties: - items: - enum: - ti,sysc-omap2 - - ti,sysc-omap2 - ti,sysc-omap4 - ti,sysc-omap4-simple - ti,sysc-omap2-timer diff --git a/Documentation/devicetree/bindings/clock/imx8m-clock.yaml b/Documentation/devicetree/bindings/clock/imx8m-clock.yaml index 625f573a7b90..458c7645ee68 100644 --- a/Documentation/devicetree/bindings/clock/imx8m-clock.yaml +++ b/Documentation/devicetree/bindings/clock/imx8m-clock.yaml @@ -55,8 +55,6 @@ allOf: then: properties: clocks: - minItems: 7 - maxItems: 7 items: - description: 32k osc - description: 25m osc @@ -66,8 +64,6 @@ allOf: - description: ext3 clock input - description: ext4 clock input clock-names: - minItems: 7 - maxItems: 7 items: - const: ckil - const: osc_25m diff --git a/Documentation/devicetree/bindings/clock/microchip,mpfs.yaml b/Documentation/devicetree/bindings/clock/microchip,mpfs.yaml index 0c15afa2214c..016a4f378b9b 100644 --- a/Documentation/devicetree/bindings/clock/microchip,mpfs.yaml +++ b/Documentation/devicetree/bindings/clock/microchip,mpfs.yaml @@ -22,7 +22,16 @@ properties: const: microchip,mpfs-clkcfg reg: - maxItems: 1 + items: + - description: | + clock config registers: + These registers contain enable, reset & divider tables for the, cpu, + axi, ahb and rtc/mtimer reference clocks as well as enable and reset + for the peripheral clocks. + - description: | + mss pll dri registers: + Block of registers responsible for dynamic reconfiguration of the mss + pll clocks: maxItems: 1 @@ -51,7 +60,7 @@ examples: #size-cells = <2>; clkcfg: clock-controller@20002000 { compatible = "microchip,mpfs-clkcfg"; - reg = <0x0 0x20002000 0x0 0x1000>; + reg = <0x0 0x20002000 0x0 0x1000>, <0x0 0x3E001000 0x0 0x1000>; clocks = <&ref>; #clock-cells = <1>; }; diff --git a/Documentation/devicetree/bindings/clock/samsung,exynos-audss-clock.yaml b/Documentation/devicetree/bindings/clock/samsung,exynos-audss-clock.yaml index f14f1d39da36..d819dfaafff9 100644 --- a/Documentation/devicetree/bindings/clock/samsung,exynos-audss-clock.yaml +++ b/Documentation/devicetree/bindings/clock/samsung,exynos-audss-clock.yaml @@ -8,7 +8,7 @@ title: Samsung Exynos SoC Audio SubSystem clock controller maintainers: - Chanwoo Choi <cw00.choi@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Sylwester Nawrocki <s.nawrocki@samsung.com> - Tomasz Figa <tomasz.figa@gmail.com> diff --git a/Documentation/devicetree/bindings/clock/samsung,exynos-clock.yaml b/Documentation/devicetree/bindings/clock/samsung,exynos-clock.yaml index 4e8062860986..0589a63e273a 100644 --- a/Documentation/devicetree/bindings/clock/samsung,exynos-clock.yaml +++ b/Documentation/devicetree/bindings/clock/samsung,exynos-clock.yaml @@ -8,7 +8,7 @@ title: Samsung Exynos SoC clock controller maintainers: - Chanwoo Choi <cw00.choi@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Sylwester Nawrocki <s.nawrocki@samsung.com> - Tomasz Figa <tomasz.figa@gmail.com> diff --git a/Documentation/devicetree/bindings/clock/samsung,exynos-ext-clock.yaml b/Documentation/devicetree/bindings/clock/samsung,exynos-ext-clock.yaml index 64d027dbe3b2..c98eff64f2b5 100644 --- a/Documentation/devicetree/bindings/clock/samsung,exynos-ext-clock.yaml +++ b/Documentation/devicetree/bindings/clock/samsung,exynos-ext-clock.yaml @@ -8,7 +8,7 @@ title: Samsung SoC external/osc/XXTI/XusbXTI clock maintainers: - Chanwoo Choi <cw00.choi@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Sylwester Nawrocki <s.nawrocki@samsung.com> - Tomasz Figa <tomasz.figa@gmail.com> diff --git a/Documentation/devicetree/bindings/clock/samsung,exynos4412-isp-clock.yaml b/Documentation/devicetree/bindings/clock/samsung,exynos4412-isp-clock.yaml index 1ed64add4355..b644bbd0df38 100644 --- a/Documentation/devicetree/bindings/clock/samsung,exynos4412-isp-clock.yaml +++ b/Documentation/devicetree/bindings/clock/samsung,exynos4412-isp-clock.yaml @@ -8,7 +8,7 @@ title: Samsung Exynos4412 SoC ISP clock controller maintainers: - Chanwoo Choi <cw00.choi@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Sylwester Nawrocki <s.nawrocki@samsung.com> - Tomasz Figa <tomasz.figa@gmail.com> diff --git a/Documentation/devicetree/bindings/clock/samsung,exynos5260-clock.yaml b/Documentation/devicetree/bindings/clock/samsung,exynos5260-clock.yaml index a3fac5c6809d..b05f83533e3d 100644 --- a/Documentation/devicetree/bindings/clock/samsung,exynos5260-clock.yaml +++ b/Documentation/devicetree/bindings/clock/samsung,exynos5260-clock.yaml @@ -8,7 +8,7 @@ title: Samsung Exynos5260 SoC clock controller maintainers: - Chanwoo Choi <cw00.choi@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Sylwester Nawrocki <s.nawrocki@samsung.com> - Tomasz Figa <tomasz.figa@gmail.com> diff --git a/Documentation/devicetree/bindings/clock/samsung,exynos5410-clock.yaml b/Documentation/devicetree/bindings/clock/samsung,exynos5410-clock.yaml index 032862e9f55b..b737c9d35a1c 100644 --- a/Documentation/devicetree/bindings/clock/samsung,exynos5410-clock.yaml +++ b/Documentation/devicetree/bindings/clock/samsung,exynos5410-clock.yaml @@ -8,7 +8,7 @@ title: Samsung Exynos5410 SoC clock controller maintainers: - Chanwoo Choi <cw00.choi@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Sylwester Nawrocki <s.nawrocki@samsung.com> - Tomasz Figa <tomasz.figa@gmail.com> diff --git a/Documentation/devicetree/bindings/clock/samsung,exynos5433-clock.yaml b/Documentation/devicetree/bindings/clock/samsung,exynos5433-clock.yaml index edd1b4ac4334..3f9326e09f79 100644 --- a/Documentation/devicetree/bindings/clock/samsung,exynos5433-clock.yaml +++ b/Documentation/devicetree/bindings/clock/samsung,exynos5433-clock.yaml @@ -8,7 +8,7 @@ title: Samsung Exynos5433 SoC clock controller maintainers: - Chanwoo Choi <cw00.choi@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Sylwester Nawrocki <s.nawrocki@samsung.com> - Tomasz Figa <tomasz.figa@gmail.com> diff --git a/Documentation/devicetree/bindings/clock/samsung,exynos7-clock.yaml b/Documentation/devicetree/bindings/clock/samsung,exynos7-clock.yaml index 599baf0b7231..c137c6744ef9 100644 --- a/Documentation/devicetree/bindings/clock/samsung,exynos7-clock.yaml +++ b/Documentation/devicetree/bindings/clock/samsung,exynos7-clock.yaml @@ -8,7 +8,7 @@ title: Samsung Exynos7 SoC clock controller maintainers: - Chanwoo Choi <cw00.choi@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Sylwester Nawrocki <s.nawrocki@samsung.com> - Tomasz Figa <tomasz.figa@gmail.com> diff --git a/Documentation/devicetree/bindings/clock/samsung,exynos7885-clock.yaml b/Documentation/devicetree/bindings/clock/samsung,exynos7885-clock.yaml index 7e5a9cac2fd2..5073e569a47f 100644 --- a/Documentation/devicetree/bindings/clock/samsung,exynos7885-clock.yaml +++ b/Documentation/devicetree/bindings/clock/samsung,exynos7885-clock.yaml @@ -9,7 +9,7 @@ title: Samsung Exynos7885 SoC clock controller maintainers: - Dávid Virág <virag.david003@gmail.com> - Chanwoo Choi <cw00.choi@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Sylwester Nawrocki <s.nawrocki@samsung.com> - Tomasz Figa <tomasz.figa@gmail.com> diff --git a/Documentation/devicetree/bindings/clock/samsung,exynos850-clock.yaml b/Documentation/devicetree/bindings/clock/samsung,exynos850-clock.yaml index 80ba60838f2b..aa11815ad3a3 100644 --- a/Documentation/devicetree/bindings/clock/samsung,exynos850-clock.yaml +++ b/Documentation/devicetree/bindings/clock/samsung,exynos850-clock.yaml @@ -9,7 +9,7 @@ title: Samsung Exynos850 SoC clock controller maintainers: - Sam Protsenko <semen.protsenko@linaro.org> - Chanwoo Choi <cw00.choi@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Sylwester Nawrocki <s.nawrocki@samsung.com> - Tomasz Figa <tomasz.figa@gmail.com> diff --git a/Documentation/devicetree/bindings/clock/samsung,s2mps11.yaml b/Documentation/devicetree/bindings/clock/samsung,s2mps11.yaml index 1410c51e0e7d..9248bfc16d48 100644 --- a/Documentation/devicetree/bindings/clock/samsung,s2mps11.yaml +++ b/Documentation/devicetree/bindings/clock/samsung,s2mps11.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung S2M and S5M family clock generator block maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for S2M and S5M family of Power diff --git a/Documentation/devicetree/bindings/clock/samsung,s5pv210-audss-clock.yaml b/Documentation/devicetree/bindings/clock/samsung,s5pv210-audss-clock.yaml index ae8f8fc93233..2659854ea1c0 100644 --- a/Documentation/devicetree/bindings/clock/samsung,s5pv210-audss-clock.yaml +++ b/Documentation/devicetree/bindings/clock/samsung,s5pv210-audss-clock.yaml @@ -8,7 +8,7 @@ title: Samsung S5Pv210 SoC Audio SubSystem clock controller maintainers: - Chanwoo Choi <cw00.choi@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Sylwester Nawrocki <s.nawrocki@samsung.com> - Tomasz Figa <tomasz.figa@gmail.com> diff --git a/Documentation/devicetree/bindings/clock/samsung,s5pv210-clock.yaml b/Documentation/devicetree/bindings/clock/samsung,s5pv210-clock.yaml index dcb29a2d1159..67a33665cf00 100644 --- a/Documentation/devicetree/bindings/clock/samsung,s5pv210-clock.yaml +++ b/Documentation/devicetree/bindings/clock/samsung,s5pv210-clock.yaml @@ -8,7 +8,7 @@ title: Samsung S5P6442/S5PC110/S5PV210 SoC clock controller maintainers: - Chanwoo Choi <cw00.choi@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Sylwester Nawrocki <s.nawrocki@samsung.com> - Tomasz Figa <tomasz.figa@gmail.com> diff --git a/Documentation/devicetree/bindings/devfreq/event/samsung,exynos-nocp.yaml b/Documentation/devicetree/bindings/devfreq/event/samsung,exynos-nocp.yaml index d318fccf78f1..2bdd05af6079 100644 --- a/Documentation/devicetree/bindings/devfreq/event/samsung,exynos-nocp.yaml +++ b/Documentation/devicetree/bindings/devfreq/event/samsung,exynos-nocp.yaml @@ -8,7 +8,7 @@ title: Samsung Exynos NoC (Network on Chip) Probe maintainers: - Chanwoo Choi <cw00.choi@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | The Samsung Exynos542x SoC has a NoC (Network on Chip) Probe for NoC bus. diff --git a/Documentation/devicetree/bindings/devfreq/event/samsung,exynos-ppmu.yaml b/Documentation/devicetree/bindings/devfreq/event/samsung,exynos-ppmu.yaml index c9a8cb5fd555..e300df4b47f3 100644 --- a/Documentation/devicetree/bindings/devfreq/event/samsung,exynos-ppmu.yaml +++ b/Documentation/devicetree/bindings/devfreq/event/samsung,exynos-ppmu.yaml @@ -8,7 +8,7 @@ title: Samsung Exynos SoC PPMU (Platform Performance Monitoring Unit) maintainers: - Chanwoo Choi <cw00.choi@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | The Samsung Exynos SoC has PPMU (Platform Performance Monitoring Unit) for diff --git a/Documentation/devicetree/bindings/devfreq/rk3399_dmc.txt b/Documentation/devicetree/bindings/devfreq/rk3399_dmc.txt deleted file mode 100644 index 58fc8a6cebc7..000000000000 --- a/Documentation/devicetree/bindings/devfreq/rk3399_dmc.txt +++ /dev/null @@ -1,212 +0,0 @@ -* Rockchip rk3399 DMC (Dynamic Memory Controller) device - -Required properties: -- compatible: Must be "rockchip,rk3399-dmc". -- devfreq-events: Node to get DDR loading, Refer to - Documentation/devicetree/bindings/devfreq/event/ - rockchip-dfi.txt -- clocks: Phandles for clock specified in "clock-names" property -- clock-names : The name of clock used by the DFI, must be - "pclk_ddr_mon"; -- operating-points-v2: Refer to Documentation/devicetree/bindings/opp/opp-v2.yaml - for details. -- center-supply: DMC supply node. -- status: Marks the node enabled/disabled. -- rockchip,pmu: Phandle to the syscon managing the "PMU general register - files". - -Optional properties: -- interrupts: The CPU interrupt number. The interrupt specifier - format depends on the interrupt controller. - It should be a DCF interrupt. When DDR DVFS finishes - a DCF interrupt is triggered. -- rockchip,pmu: Phandle to the syscon managing the "PMU general register - files". - -Following properties relate to DDR timing: - -- rockchip,dram_speed_bin : Value reference include/dt-bindings/clock/rk3399-ddr.h, - it selects the DDR3 cl-trp-trcd type. It must be - set according to "Speed Bin" in DDR3 datasheet, - DO NOT use a smaller "Speed Bin" than specified - for the DDR3 being used. - -- rockchip,pd_idle : Configure the PD_IDLE value. Defines the - power-down idle period in which memories are - placed into power-down mode if bus is idle - for PD_IDLE DFI clock cycles. - -- rockchip,sr_idle : Configure the SR_IDLE value. Defines the - self-refresh idle period in which memories are - placed into self-refresh mode if bus is idle - for SR_IDLE * 1024 DFI clock cycles (DFI - clocks freq is half of DRAM clock), default - value is "0". - -- rockchip,sr_mc_gate_idle : Defines the memory self-refresh and controller - clock gating idle period. Memories are placed - into self-refresh mode and memory controller - clock arg gating started if bus is idle for - sr_mc_gate_idle*1024 DFI clock cycles. - -- rockchip,srpd_lite_idle : Defines the self-refresh power down idle - period in which memories are placed into - self-refresh power down mode if bus is idle - for srpd_lite_idle * 1024 DFI clock cycles. - This parameter is for LPDDR4 only. - -- rockchip,standby_idle : Defines the standby idle period in which - memories are placed into self-refresh mode. - The controller, pi, PHY and DRAM clock will - be gated if bus is idle for standby_idle * DFI - clock cycles. - -- rockchip,dram_dll_dis_freq : Defines the DDR3 DLL bypass frequency in MHz. - When DDR frequency is less than DRAM_DLL_DISB_FREQ, - DDR3 DLL will be bypassed. Note: if DLL was bypassed, - the odt will also stop working. - -- rockchip,phy_dll_dis_freq : Defines the PHY dll bypass frequency in - MHz (Mega Hz). When DDR frequency is less than - DRAM_DLL_DISB_FREQ, PHY DLL will be bypassed. - Note: PHY DLL and PHY ODT are independent. - -- rockchip,ddr3_odt_dis_freq : When the DRAM type is DDR3, this parameter defines - the ODT disable frequency in MHz (Mega Hz). - when the DDR frequency is less then ddr3_odt_dis_freq, - the ODT on the DRAM side and controller side are - both disabled. - -- rockchip,ddr3_drv : When the DRAM type is DDR3, this parameter defines - the DRAM side driver strength in ohms. Default - value is 40. - -- rockchip,ddr3_odt : When the DRAM type is DDR3, this parameter defines - the DRAM side ODT strength in ohms. Default value - is 120. - -- rockchip,phy_ddr3_ca_drv : When the DRAM type is DDR3, this parameter defines - the phy side CA line (incluing command line, - address line and clock line) driver strength. - Default value is 40. - -- rockchip,phy_ddr3_dq_drv : When the DRAM type is DDR3, this parameter defines - the PHY side DQ line (including DQS/DQ/DM line) - driver strength. Default value is 40. - -- rockchip,phy_ddr3_odt : When the DRAM type is DDR3, this parameter defines - the PHY side ODT strength. Default value is 240. - -- rockchip,lpddr3_odt_dis_freq : When the DRAM type is LPDDR3, this parameter defines - then ODT disable frequency in MHz (Mega Hz). - When DDR frequency is less then ddr3_odt_dis_freq, - the ODT on the DRAM side and controller side are - both disabled. - -- rockchip,lpddr3_drv : When the DRAM type is LPDDR3, this parameter defines - the DRAM side driver strength in ohms. Default - value is 34. - -- rockchip,lpddr3_odt : When the DRAM type is LPDDR3, this parameter defines - the DRAM side ODT strength in ohms. Default value - is 240. - -- rockchip,phy_lpddr3_ca_drv : When the DRAM type is LPDDR3, this parameter defines - the PHY side CA line (including command line, - address line and clock line) driver strength. - Default value is 40. - -- rockchip,phy_lpddr3_dq_drv : When the DRAM type is LPDDR3, this parameter defines - the PHY side DQ line (including DQS/DQ/DM line) - driver strength. Default value is 40. - -- rockchip,phy_lpddr3_odt : When dram type is LPDDR3, this parameter define - the phy side odt strength, default value is 240. - -- rockchip,lpddr4_odt_dis_freq : When the DRAM type is LPDDR4, this parameter - defines the ODT disable frequency in - MHz (Mega Hz). When the DDR frequency is less then - ddr3_odt_dis_freq, the ODT on the DRAM side and - controller side are both disabled. - -- rockchip,lpddr4_drv : When the DRAM type is LPDDR4, this parameter defines - the DRAM side driver strength in ohms. Default - value is 60. - -- rockchip,lpddr4_dq_odt : When the DRAM type is LPDDR4, this parameter defines - the DRAM side ODT on DQS/DQ line strength in ohms. - Default value is 40. - -- rockchip,lpddr4_ca_odt : When the DRAM type is LPDDR4, this parameter defines - the DRAM side ODT on CA line strength in ohms. - Default value is 40. - -- rockchip,phy_lpddr4_ca_drv : When the DRAM type is LPDDR4, this parameter defines - the PHY side CA line (including command address - line) driver strength. Default value is 40. - -- rockchip,phy_lpddr4_ck_cs_drv : When the DRAM type is LPDDR4, this parameter defines - the PHY side clock line and CS line driver - strength. Default value is 80. - -- rockchip,phy_lpddr4_dq_drv : When the DRAM type is LPDDR4, this parameter defines - the PHY side DQ line (including DQS/DQ/DM line) - driver strength. Default value is 80. - -- rockchip,phy_lpddr4_odt : When the DRAM type is LPDDR4, this parameter defines - the PHY side ODT strength. Default value is 60. - -Example: - dmc_opp_table: dmc_opp_table { - compatible = "operating-points-v2"; - - opp00 { - opp-hz = /bits/ 64 <300000000>; - opp-microvolt = <900000>; - }; - opp01 { - opp-hz = /bits/ 64 <666000000>; - opp-microvolt = <900000>; - }; - }; - - dmc: dmc { - compatible = "rockchip,rk3399-dmc"; - devfreq-events = <&dfi>; - interrupts = <GIC_SPI 1 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&cru SCLK_DDRC>; - clock-names = "dmc_clk"; - operating-points-v2 = <&dmc_opp_table>; - center-supply = <&ppvar_centerlogic>; - upthreshold = <15>; - downdifferential = <10>; - rockchip,ddr3_speed_bin = <21>; - rockchip,pd_idle = <0x40>; - rockchip,sr_idle = <0x2>; - rockchip,sr_mc_gate_idle = <0x3>; - rockchip,srpd_lite_idle = <0x4>; - rockchip,standby_idle = <0x2000>; - rockchip,dram_dll_dis_freq = <300>; - rockchip,phy_dll_dis_freq = <125>; - rockchip,auto_pd_dis_freq = <666>; - rockchip,ddr3_odt_dis_freq = <333>; - rockchip,ddr3_drv = <40>; - rockchip,ddr3_odt = <120>; - rockchip,phy_ddr3_ca_drv = <40>; - rockchip,phy_ddr3_dq_drv = <40>; - rockchip,phy_ddr3_odt = <240>; - rockchip,lpddr3_odt_dis_freq = <333>; - rockchip,lpddr3_drv = <34>; - rockchip,lpddr3_odt = <240>; - rockchip,phy_lpddr3_ca_drv = <40>; - rockchip,phy_lpddr3_dq_drv = <40>; - rockchip,phy_lpddr3_odt = <240>; - rockchip,lpddr4_odt_dis_freq = <333>; - rockchip,lpddr4_drv = <60>; - rockchip,lpddr4_dq_odt = <40>; - rockchip,lpddr4_ca_odt = <40>; - rockchip,phy_lpddr4_ca_drv = <40>; - rockchip,phy_lpddr4_ck_cs_drv = <80>; - rockchip,phy_lpddr4_dq_drv = <80>; - rockchip,phy_lpddr4_odt = <60>; - }; diff --git a/Documentation/devicetree/bindings/display/bridge/chipone,icn6211.yaml b/Documentation/devicetree/bindings/display/bridge/chipone,icn6211.yaml index 62c3bd4cb28d..7257fd0ae4da 100644 --- a/Documentation/devicetree/bindings/display/bridge/chipone,icn6211.yaml +++ b/Documentation/devicetree/bindings/display/bridge/chipone,icn6211.yaml @@ -51,7 +51,6 @@ properties: Video port for MIPI DPI output (panel or connector). required: - - port@0 - port@1 required: diff --git a/Documentation/devicetree/bindings/display/bridge/renesas,lvds.yaml b/Documentation/devicetree/bindings/display/bridge/renesas,lvds.yaml index a51baf8a4c76..bb9dbfb9beaf 100644 --- a/Documentation/devicetree/bindings/display/bridge/renesas,lvds.yaml +++ b/Documentation/devicetree/bindings/display/bridge/renesas,lvds.yaml @@ -95,7 +95,6 @@ then: properties: clocks: minItems: 1 - maxItems: 4 items: - description: Functional clock - description: EXTAL input clock @@ -104,7 +103,6 @@ then: clock-names: minItems: 1 - maxItems: 4 items: - const: fck # The LVDS encoder can use the EXTAL or DU_DOTCLKINx clocks. @@ -128,12 +126,10 @@ then: else: properties: clocks: - maxItems: 1 items: - description: Functional clock clock-names: - maxItems: 1 items: - const: fck diff --git a/Documentation/devicetree/bindings/display/bridge/toshiba,tc358762.yaml b/Documentation/devicetree/bindings/display/bridge/toshiba,tc358762.yaml index 5216c27fc0ad..a412a1da950f 100644 --- a/Documentation/devicetree/bindings/display/bridge/toshiba,tc358762.yaml +++ b/Documentation/devicetree/bindings/display/bridge/toshiba,tc358762.yaml @@ -39,7 +39,6 @@ properties: Video port for MIPI DPI output (panel or connector). required: - - port@0 - port@1 required: diff --git a/Documentation/devicetree/bindings/display/msm/dpu-qcm2290.yaml b/Documentation/devicetree/bindings/display/msm/dpu-qcm2290.yaml index d31483a78eab..6fb7e321f011 100644 --- a/Documentation/devicetree/bindings/display/msm/dpu-qcm2290.yaml +++ b/Documentation/devicetree/bindings/display/msm/dpu-qcm2290.yaml @@ -160,7 +160,7 @@ examples: mdss: mdss@5e00000 { #address-cells = <1>; #size-cells = <1>; - compatible = "qcom,qcm2290-mdss", "qcom,mdss"; + compatible = "qcom,qcm2290-mdss"; reg = <0x05e00000 0x1000>; reg-names = "mdss"; power-domains = <&dispcc MDSS_GDSC>; @@ -180,7 +180,7 @@ examples: <&apps_smmu 0x421 0x0>; ranges; - mdss_mdp: mdp@5e01000 { + mdss_mdp: display-controller@5e01000 { compatible = "qcom,qcm2290-dpu"; reg = <0x05e01000 0x8f000>, <0x05eb0000 0x2008>; diff --git a/Documentation/devicetree/bindings/display/panel/panel-mipi-dbi-spi.yaml b/Documentation/devicetree/bindings/display/panel/panel-mipi-dbi-spi.yaml index f29789994b18..c2df8d28aaf5 100644 --- a/Documentation/devicetree/bindings/display/panel/panel-mipi-dbi-spi.yaml +++ b/Documentation/devicetree/bindings/display/panel/panel-mipi-dbi-spi.yaml @@ -83,6 +83,8 @@ properties: required: - compatible - reg + - width-mm + - height-mm - panel-timing unevaluatedProperties: false diff --git a/Documentation/devicetree/bindings/display/panel/panel-timing.yaml b/Documentation/devicetree/bindings/display/panel/panel-timing.yaml index 9bf592dc3033..7749de95ee40 100644 --- a/Documentation/devicetree/bindings/display/panel/panel-timing.yaml +++ b/Documentation/devicetree/bindings/display/panel/panel-timing.yaml @@ -71,78 +71,72 @@ properties: hfront-porch: description: Horizontal front porch panel timing + $ref: /schemas/types.yaml#/definitions/uint32-array oneOf: - - $ref: /schemas/types.yaml#/definitions/uint32 - maxItems: 1 + - maxItems: 1 items: description: typical number of pixels - - $ref: /schemas/types.yaml#/definitions/uint32-array - minItems: 3 + - minItems: 3 maxItems: 3 items: description: min, typ, max number of pixels hback-porch: description: Horizontal back porch timing + $ref: /schemas/types.yaml#/definitions/uint32-array oneOf: - - $ref: /schemas/types.yaml#/definitions/uint32 - maxItems: 1 + - maxItems: 1 items: description: typical number of pixels - - $ref: /schemas/types.yaml#/definitions/uint32-array - minItems: 3 + - minItems: 3 maxItems: 3 items: description: min, typ, max number of pixels hsync-len: description: Horizontal sync length panel timing + $ref: /schemas/types.yaml#/definitions/uint32-array oneOf: - - $ref: /schemas/types.yaml#/definitions/uint32 - maxItems: 1 + - maxItems: 1 items: description: typical number of pixels - - $ref: /schemas/types.yaml#/definitions/uint32-array - minItems: 3 + - minItems: 3 maxItems: 3 items: description: min, typ, max number of pixels vfront-porch: description: Vertical front porch panel timing + $ref: /schemas/types.yaml#/definitions/uint32-array oneOf: - - $ref: /schemas/types.yaml#/definitions/uint32 - maxItems: 1 + - maxItems: 1 items: description: typical number of lines - - $ref: /schemas/types.yaml#/definitions/uint32-array - minItems: 3 + - minItems: 3 maxItems: 3 items: description: min, typ, max number of lines vback-porch: description: Vertical back porch panel timing + $ref: /schemas/types.yaml#/definitions/uint32-array oneOf: - - $ref: /schemas/types.yaml#/definitions/uint32 - maxItems: 1 + - maxItems: 1 items: description: typical number of lines - - $ref: /schemas/types.yaml#/definitions/uint32-array - minItems: 3 + - minItems: 3 maxItems: 3 items: description: min, typ, max number of lines vsync-len: description: Vertical sync length panel timing + $ref: /schemas/types.yaml#/definitions/uint32-array oneOf: - - $ref: /schemas/types.yaml#/definitions/uint32 - maxItems: 1 + - maxItems: 1 items: description: typical number of lines - - $ref: /schemas/types.yaml#/definitions/uint32-array - minItems: 3 + - minItems: 3 maxItems: 3 items: description: min, typ, max number of lines diff --git a/Documentation/devicetree/bindings/display/renesas,du.yaml b/Documentation/devicetree/bindings/display/renesas,du.yaml index 56cedcd6d576..b3e588022082 100644 --- a/Documentation/devicetree/bindings/display/renesas,du.yaml +++ b/Documentation/devicetree/bindings/display/renesas,du.yaml @@ -109,7 +109,6 @@ allOf: properties: clocks: minItems: 1 - maxItems: 3 items: - description: Functional clock - description: DU_DOTCLKIN0 input clock @@ -117,7 +116,6 @@ allOf: clock-names: minItems: 1 - maxItems: 3 items: - const: du.0 - pattern: '^dclkin\.[01]$' @@ -159,7 +157,6 @@ allOf: properties: clocks: minItems: 2 - maxItems: 4 items: - description: Functional clock for DU0 - description: Functional clock for DU1 @@ -168,7 +165,6 @@ allOf: clock-names: minItems: 2 - maxItems: 4 items: - const: du.0 - const: du.1 @@ -216,7 +212,6 @@ allOf: properties: clocks: minItems: 2 - maxItems: 4 items: - description: Functional clock for DU0 - description: Functional clock for DU1 @@ -225,7 +220,6 @@ allOf: clock-names: minItems: 2 - maxItems: 4 items: - const: du.0 - const: du.1 @@ -271,7 +265,6 @@ allOf: properties: clocks: minItems: 2 - maxItems: 4 items: - description: Functional clock for DU0 - description: Functional clock for DU1 @@ -280,7 +273,6 @@ allOf: clock-names: minItems: 2 - maxItems: 4 items: - const: du.0 - const: du.1 @@ -327,7 +319,6 @@ allOf: properties: clocks: minItems: 2 - maxItems: 4 items: - description: Functional clock for DU0 - description: Functional clock for DU1 @@ -336,7 +327,6 @@ allOf: clock-names: minItems: 2 - maxItems: 4 items: - const: du.0 - const: du.1 @@ -386,7 +376,6 @@ allOf: properties: clocks: minItems: 3 - maxItems: 6 items: - description: Functional clock for DU0 - description: Functional clock for DU1 @@ -397,7 +386,6 @@ allOf: clock-names: minItems: 3 - maxItems: 6 items: - const: du.0 - const: du.1 @@ -448,7 +436,6 @@ allOf: properties: clocks: minItems: 4 - maxItems: 8 items: - description: Functional clock for DU0 - description: Functional clock for DU1 @@ -461,7 +448,6 @@ allOf: clock-names: minItems: 4 - maxItems: 8 items: - const: du.0 - const: du.1 @@ -525,7 +511,6 @@ allOf: properties: clocks: minItems: 3 - maxItems: 6 items: - description: Functional clock for DU0 - description: Functional clock for DU1 @@ -536,7 +521,6 @@ allOf: clock-names: minItems: 3 - maxItems: 6 items: - const: du.0 - const: du.1 @@ -596,7 +580,6 @@ allOf: properties: clocks: minItems: 3 - maxItems: 6 items: - description: Functional clock for DU0 - description: Functional clock for DU1 @@ -607,7 +590,6 @@ allOf: clock-names: minItems: 3 - maxItems: 6 items: - const: du.0 - const: du.1 @@ -666,14 +648,12 @@ allOf: properties: clocks: minItems: 1 - maxItems: 2 items: - description: Functional clock for DU0 - description: DU_DOTCLKIN0 input clock clock-names: minItems: 1 - maxItems: 2 items: - const: du.0 - const: dclkin.0 @@ -723,7 +703,6 @@ allOf: properties: clocks: minItems: 2 - maxItems: 4 items: - description: Functional clock for DU0 - description: Functional clock for DU1 @@ -732,7 +711,6 @@ allOf: clock-names: minItems: 2 - maxItems: 4 items: - const: du.0 - const: du.1 @@ -791,7 +769,6 @@ allOf: - description: Functional clock clock-names: - maxItems: 1 items: - const: du.0 diff --git a/Documentation/devicetree/bindings/display/samsung/samsung,exynos-hdmi-ddc.yaml b/Documentation/devicetree/bindings/display/samsung/samsung,exynos-hdmi-ddc.yaml index f998a3a5b71f..919734c05c0b 100644 --- a/Documentation/devicetree/bindings/display/samsung/samsung,exynos-hdmi-ddc.yaml +++ b/Documentation/devicetree/bindings/display/samsung/samsung,exynos-hdmi-ddc.yaml @@ -11,7 +11,7 @@ maintainers: - Joonyoung Shim <jy0922.shim@samsung.com> - Seung-Woo Kim <sw0312.kim@samsung.com> - Kyungmin Park <kyungmin.park@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/display/samsung/samsung,exynos-hdmi.yaml b/Documentation/devicetree/bindings/display/samsung/samsung,exynos-hdmi.yaml index cb8e735ce3bd..63379fae3636 100644 --- a/Documentation/devicetree/bindings/display/samsung/samsung,exynos-hdmi.yaml +++ b/Documentation/devicetree/bindings/display/samsung/samsung,exynos-hdmi.yaml @@ -11,7 +11,7 @@ maintainers: - Joonyoung Shim <jy0922.shim@samsung.com> - Seung-Woo Kim <sw0312.kim@samsung.com> - Kyungmin Park <kyungmin.park@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/display/samsung/samsung,exynos-mixer.yaml b/Documentation/devicetree/bindings/display/samsung/samsung,exynos-mixer.yaml index ba40284ac66f..00e325a19cb1 100644 --- a/Documentation/devicetree/bindings/display/samsung/samsung,exynos-mixer.yaml +++ b/Documentation/devicetree/bindings/display/samsung/samsung,exynos-mixer.yaml @@ -11,7 +11,7 @@ maintainers: - Joonyoung Shim <jy0922.shim@samsung.com> - Seung-Woo Kim <sw0312.kim@samsung.com> - Kyungmin Park <kyungmin.park@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: Samsung Exynos SoC Mixer is responsible for mixing and blending multiple data diff --git a/Documentation/devicetree/bindings/display/samsung/samsung,exynos5433-decon.yaml b/Documentation/devicetree/bindings/display/samsung/samsung,exynos5433-decon.yaml index 6f796835ea03..7c37470bd329 100644 --- a/Documentation/devicetree/bindings/display/samsung/samsung,exynos5433-decon.yaml +++ b/Documentation/devicetree/bindings/display/samsung/samsung,exynos5433-decon.yaml @@ -11,7 +11,7 @@ maintainers: - Joonyoung Shim <jy0922.shim@samsung.com> - Seung-Woo Kim <sw0312.kim@samsung.com> - Kyungmin Park <kyungmin.park@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | DECON (Display and Enhancement Controller) is the Display Controller for the diff --git a/Documentation/devicetree/bindings/display/samsung/samsung,exynos5433-mic.yaml b/Documentation/devicetree/bindings/display/samsung/samsung,exynos5433-mic.yaml index 01fccb138ebd..c5c6239c28d0 100644 --- a/Documentation/devicetree/bindings/display/samsung/samsung,exynos5433-mic.yaml +++ b/Documentation/devicetree/bindings/display/samsung/samsung,exynos5433-mic.yaml @@ -11,7 +11,7 @@ maintainers: - Joonyoung Shim <jy0922.shim@samsung.com> - Seung-Woo Kim <sw0312.kim@samsung.com> - Kyungmin Park <kyungmin.park@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | MIC (Mobile Image Compressor) resides between DECON and MIPI DSI. MIPI DSI is diff --git a/Documentation/devicetree/bindings/display/samsung/samsung,exynos7-decon.yaml b/Documentation/devicetree/bindings/display/samsung/samsung,exynos7-decon.yaml index afa137d47922..320eedc61a5b 100644 --- a/Documentation/devicetree/bindings/display/samsung/samsung,exynos7-decon.yaml +++ b/Documentation/devicetree/bindings/display/samsung/samsung,exynos7-decon.yaml @@ -11,7 +11,7 @@ maintainers: - Joonyoung Shim <jy0922.shim@samsung.com> - Seung-Woo Kim <sw0312.kim@samsung.com> - Kyungmin Park <kyungmin.park@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | DECON (Display and Enhancement Controller) is the Display Controller for the diff --git a/Documentation/devicetree/bindings/display/samsung/samsung,fimd.yaml b/Documentation/devicetree/bindings/display/samsung/samsung,fimd.yaml index 9cf5f120d516..c62ea9d22843 100644 --- a/Documentation/devicetree/bindings/display/samsung/samsung,fimd.yaml +++ b/Documentation/devicetree/bindings/display/samsung/samsung,fimd.yaml @@ -11,7 +11,7 @@ maintainers: - Joonyoung Shim <jy0922.shim@samsung.com> - Seung-Woo Kim <sw0312.kim@samsung.com> - Kyungmin Park <kyungmin.park@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/dma/qcom,gpi.yaml b/Documentation/devicetree/bindings/dma/qcom,gpi.yaml index e614fe3187bb..d09d79d7406a 100644 --- a/Documentation/devicetree/bindings/dma/qcom,gpi.yaml +++ b/Documentation/devicetree/bindings/dma/qcom,gpi.yaml @@ -29,6 +29,7 @@ properties: interrupts: description: Interrupt lines for each GPI instance + minItems: 1 maxItems: 13 "#dma-cells": diff --git a/Documentation/devicetree/bindings/extcon/maxim,max77843.yaml b/Documentation/devicetree/bindings/extcon/maxim,max77843.yaml index f9ffe3d6f957..128960545640 100644 --- a/Documentation/devicetree/bindings/extcon/maxim,max77843.yaml +++ b/Documentation/devicetree/bindings/extcon/maxim,max77843.yaml @@ -8,7 +8,7 @@ title: Maxim MAX77843 MicroUSB and Companion Power Management IC Extcon maintainers: - Chanwoo Choi <cw00.choi@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for Maxim MAX77843 MicroUSB @@ -25,7 +25,7 @@ properties: $ref: /schemas/connector/usb-connector.yaml# ports: - $ref: /schemas/graph.yaml#/properties/port + $ref: /schemas/graph.yaml#/properties/ports description: Any connector to the data bus of this controller should be modelled using the OF graph bindings specified diff --git a/Documentation/devicetree/bindings/gpu/arm,mali-bifrost.yaml b/Documentation/devicetree/bindings/gpu/arm,mali-bifrost.yaml index 4d6bfae0653c..85f8d4764740 100644 --- a/Documentation/devicetree/bindings/gpu/arm,mali-bifrost.yaml +++ b/Documentation/devicetree/bindings/gpu/arm,mali-bifrost.yaml @@ -20,6 +20,7 @@ properties: - mediatek,mt8183-mali - realtek,rtd1619-mali - renesas,r9a07g044-mali + - renesas,r9a07g054-mali - rockchip,px30-mali - rockchip,rk3568-mali - const: arm,mali-bifrost # Mali Bifrost GPU model/revision is fully discoverable @@ -109,7 +110,9 @@ allOf: properties: compatible: contains: - const: renesas,r9a07g044-mali + enum: + - renesas,r9a07g044-mali + - renesas,r9a07g054-mali then: properties: interrupts: diff --git a/Documentation/devicetree/bindings/hwmon/adt7475.yaml b/Documentation/devicetree/bindings/hwmon/adt7475.yaml index 7d9c083632b9..22beb37f1bf1 100644 --- a/Documentation/devicetree/bindings/hwmon/adt7475.yaml +++ b/Documentation/devicetree/bindings/hwmon/adt7475.yaml @@ -61,6 +61,26 @@ patternProperties: $ref: /schemas/types.yaml#/definitions/uint32 enum: [0, 1] + "adi,pin(5|10)-function": + description: | + Configures the function for pin 5 on the adi,adt7473 and adi,adt7475. Or + pin 10 on the adi,adt7476 and adi,adt7490. + $ref: /schemas/types.yaml#/definitions/string + enum: + - pwm2 + - smbalert# + + "adi,pin(9|14)-function": + description: | + Configures the function for pin 9 on the adi,adt7473 and adi,adt7475. Or + pin 14 on the adi,adt7476 and adi,adt7490 + $ref: /schemas/types.yaml#/definitions/string + enum: + - tach4 + - therm# + - smbalert# + - gpio + required: - compatible - reg @@ -79,6 +99,8 @@ examples: adi,bypass-attenuator-in0 = <1>; adi,bypass-attenuator-in1 = <0>; adi,pwm-active-state = <1 0 1>; + adi,pin10-function = "smbalert#"; + adi,pin14-function = "tach4"; }; }; diff --git a/Documentation/devicetree/bindings/hwmon/lltc,ltc4151.yaml b/Documentation/devicetree/bindings/hwmon/lltc,ltc4151.yaml index 4b5851c326f7..b1a4c235376e 100644 --- a/Documentation/devicetree/bindings/hwmon/lltc,ltc4151.yaml +++ b/Documentation/devicetree/bindings/hwmon/lltc,ltc4151.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: LTC4151 High Voltage I2C Current and Voltage Monitor maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/hwmon/lm75.yaml b/Documentation/devicetree/bindings/hwmon/lm75.yaml index 72980d083c21..8226e3b5d028 100644 --- a/Documentation/devicetree/bindings/hwmon/lm75.yaml +++ b/Documentation/devicetree/bindings/hwmon/lm75.yaml @@ -14,6 +14,7 @@ properties: compatible: enum: - adi,adt75 + - atmel,at30ts74 - dallas,ds1775 - dallas,ds75 - dallas,ds7505 diff --git a/Documentation/devicetree/bindings/hwmon/microchip,lan966x.yaml b/Documentation/devicetree/bindings/hwmon/microchip,lan966x.yaml new file mode 100644 index 000000000000..390dd6755ff5 --- /dev/null +++ b/Documentation/devicetree/bindings/hwmon/microchip,lan966x.yaml @@ -0,0 +1,53 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/hwmon/microchip,lan966x.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Microchip LAN966x Hardware Monitor + +maintainers: + - Michael Walle <michael@walle.cc> + +description: | + Microchip LAN966x temperature monitor and fan controller + +properties: + compatible: + enum: + - microchip,lan9668-hwmon + + reg: + items: + - description: PVT registers + - description: FAN registers + + reg-names: + items: + - const: pvt + - const: fan + + clocks: + maxItems: 1 + + '#thermal-sensor-cells': + const: 0 + +required: + - compatible + - reg + - reg-names + - clocks + +additionalProperties: false + +examples: + - | + hwmon: hwmon@e2010180 { + compatible = "microchip,lan9668-hwmon"; + reg = <0xe2010180 0xc>, + <0xe20042a8 0xc>; + reg-names = "pvt", "fan"; + clocks = <&sys_clk>; + #thermal-sensor-cells = <0>; + }; diff --git a/Documentation/devicetree/bindings/hwmon/microchip,mcp3021.yaml b/Documentation/devicetree/bindings/hwmon/microchip,mcp3021.yaml index c42051f8a191..028d6e570131 100644 --- a/Documentation/devicetree/bindings/hwmon/microchip,mcp3021.yaml +++ b/Documentation/devicetree/bindings/hwmon/microchip,mcp3021.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Microchip MCP3021 A/D converter maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/hwmon/national,lm90.yaml b/Documentation/devicetree/bindings/hwmon/national,lm90.yaml index 30db92977937..b04657849852 100644 --- a/Documentation/devicetree/bindings/hwmon/national,lm90.yaml +++ b/Documentation/devicetree/bindings/hwmon/national,lm90.yaml @@ -34,6 +34,7 @@ properties: - nxp,sa56004 - onnn,nct1008 - ti,tmp451 + - ti,tmp461 - winbond,w83l771 @@ -52,10 +53,29 @@ properties: vcc-supply: description: phandle to the regulator that provides the +VCC supply + ti,extended-range-enable: + description: Set to enable extended range temperature. + type: boolean + required: - compatible - reg +allOf: + - if: + not: + properties: + compatible: + contains: + enum: + - adi,adt7461 + - adi,adt7461a + - ti,tmp451 + - ti,tmp461 + then: + properties: + ti,extended-range-enable: false + additionalProperties: false examples: diff --git a/Documentation/devicetree/bindings/hwmon/nuvoton,nct6775.yaml b/Documentation/devicetree/bindings/hwmon/nuvoton,nct6775.yaml new file mode 100644 index 000000000000..358b262431fc --- /dev/null +++ b/Documentation/devicetree/bindings/hwmon/nuvoton,nct6775.yaml @@ -0,0 +1,57 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- + +$id: http://devicetree.org/schemas/hwmon/nuvoton,nct6775.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Nuvoton NCT6775 and compatible Super I/O chips + +maintainers: + - Zev Weiss <zev@bewilderbeest.net> + +properties: + compatible: + enum: + - nuvoton,nct6106 + - nuvoton,nct6116 + - nuvoton,nct6775 + - nuvoton,nct6776 + - nuvoton,nct6779 + - nuvoton,nct6791 + - nuvoton,nct6792 + - nuvoton,nct6793 + - nuvoton,nct6795 + - nuvoton,nct6796 + - nuvoton,nct6797 + - nuvoton,nct6798 + + reg: + maxItems: 1 + + nuvoton,tsi-channel-mask: + description: + Bitmask indicating which TSI temperature sensor channels are + active. LSB is TSI0, bit 1 is TSI1, etc. + $ref: /schemas/types.yaml#/definitions/uint32 + maximum: 0xff + default: 0 + +required: + - compatible + - reg + +additionalProperties: false + +examples: + - | + i2c { + #address-cells = <1>; + #size-cells = <0>; + + superio@4d { + compatible = "nuvoton,nct6779"; + reg = <0x4d>; + nuvoton,tsi-channel-mask = <0x03>; + }; + }; diff --git a/Documentation/devicetree/bindings/hwmon/sensirion,sht15.yaml b/Documentation/devicetree/bindings/hwmon/sensirion,sht15.yaml index 4669217d01e1..80df7182ea28 100644 --- a/Documentation/devicetree/bindings/hwmon/sensirion,sht15.yaml +++ b/Documentation/devicetree/bindings/hwmon/sensirion,sht15.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Sensirion SHT15 humidity and temperature sensor maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/hwmon/ti,tmp102.yaml b/Documentation/devicetree/bindings/hwmon/ti,tmp102.yaml index d3eff4fac107..c5a889e3e27b 100644 --- a/Documentation/devicetree/bindings/hwmon/ti,tmp102.yaml +++ b/Documentation/devicetree/bindings/hwmon/ti,tmp102.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: TMP102 temperature sensor maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/hwmon/ti,tmp108.yaml b/Documentation/devicetree/bindings/hwmon/ti,tmp108.yaml index eda55bbc172d..dcbc6fbc3b48 100644 --- a/Documentation/devicetree/bindings/hwmon/ti,tmp108.yaml +++ b/Documentation/devicetree/bindings/hwmon/ti,tmp108.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: TMP108 temperature sensor maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/hwmon/ti,tmp401.yaml b/Documentation/devicetree/bindings/hwmon/ti,tmp401.yaml new file mode 100644 index 000000000000..fe0ac08faa1a --- /dev/null +++ b/Documentation/devicetree/bindings/hwmon/ti,tmp401.yaml @@ -0,0 +1,105 @@ +# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/hwmon/ti,tmp401.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: TMP401, TPM411 and TMP43x temperature sensor + +maintainers: + - Guenter Roeck <linux@roeck-us.net> + +description: | + ±1°C Remote and Local temperature sensor + + Datasheets: + https://www.ti.com/lit/ds/symlink/tmp401.pdf + https://www.ti.com/lit/ds/symlink/tmp411.pdf + https://www.ti.com/lit/ds/symlink/tmp431.pdf + https://www.ti.com/lit/ds/symlink/tmp435.pdf + +properties: + compatible: + enum: + - ti,tmp401 + - ti,tmp411 + - ti,tmp431 + - ti,tmp432 + - ti,tmp435 + + reg: + maxItems: 1 + + ti,extended-range-enable: + description: + When set, this sensor measures over extended temperature range. + type: boolean + + ti,n-factor: + description: + value to be used for converting remote channel measurements to + temperature. + $ref: /schemas/types.yaml#/definitions/int32 + items: + minimum: -128 + maximum: 127 + + ti,beta-compensation: + description: + value to select beta correction range. + $ref: /schemas/types.yaml#/definitions/uint32 + minimum: 0 + maximum: 15 + +allOf: + - if: + properties: + compatible: + contains: + enum: + - ti,tmp401 + then: + properties: + ti,n-factor: false + + - if: + properties: + compatible: + contains: + enum: + - ti,tmp401 + - ti,tmp411 + then: + properties: + ti,beta-compensation: false + +required: + - compatible + - reg + +additionalProperties: false + +examples: + - | + i2c { + #address-cells = <1>; + #size-cells = <0>; + + sensor@4c { + compatible = "ti,tmp401"; + reg = <0x4c>; + }; + }; + - | + i2c { + #address-cells = <1>; + #size-cells = <0>; + + sensor@4c { + compatible = "ti,tmp431"; + reg = <0x4c>; + ti,extended-range-enable; + ti,n-factor = <0x3b>; + ti,beta-compensation = <0x7>; + }; + }; diff --git a/Documentation/devicetree/bindings/hwmon/ti,tmp421.yaml b/Documentation/devicetree/bindings/hwmon/ti,tmp421.yaml index 36f649938fb7..a6f1fa75a67c 100644 --- a/Documentation/devicetree/bindings/hwmon/ti,tmp421.yaml +++ b/Documentation/devicetree/bindings/hwmon/ti,tmp421.yaml @@ -58,10 +58,9 @@ patternProperties: description: | The value (two's complement) to be programmed in the channel specific N correction register. For remote channels only. - $ref: /schemas/types.yaml#/definitions/uint32 - items: - minimum: 0 - maximum: 255 + $ref: /schemas/types.yaml#/definitions/int32 + minimum: -128 + maximum: 127 required: - reg diff --git a/Documentation/devicetree/bindings/hwmon/ti,tmp464.yaml b/Documentation/devicetree/bindings/hwmon/ti,tmp464.yaml index 801ca9ba7d34..e7493e25a7d2 100644 --- a/Documentation/devicetree/bindings/hwmon/ti,tmp464.yaml +++ b/Documentation/devicetree/bindings/hwmon/ti,tmp464.yaml @@ -58,9 +58,8 @@ patternProperties: The value (two's complement) to be programmed in the channel specific N correction register. For remote channels only. $ref: /schemas/types.yaml#/definitions/int32 - items: - minimum: -128 - maximum: 127 + minimum: -128 + maximum: 127 required: - reg diff --git a/Documentation/devicetree/bindings/i2c/i2c-exynos5.yaml b/Documentation/devicetree/bindings/i2c/i2c-exynos5.yaml index 19874e8b73b9..3e52a0db6c41 100644 --- a/Documentation/devicetree/bindings/i2c/i2c-exynos5.yaml +++ b/Documentation/devicetree/bindings/i2c/i2c-exynos5.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung's High Speed I2C controller maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | The Samsung's High Speed I2C controller is used to interface with I2C devices diff --git a/Documentation/devicetree/bindings/i2c/samsung,s3c2410-i2c.yaml b/Documentation/devicetree/bindings/i2c/samsung,s3c2410-i2c.yaml index 84051b0129c2..c26230518957 100644 --- a/Documentation/devicetree/bindings/i2c/samsung,s3c2410-i2c.yaml +++ b/Documentation/devicetree/bindings/i2c/samsung,s3c2410-i2c.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung S3C/S5P/Exynos SoC I2C Controller maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/iio/adc/adi,ad7476.yaml b/Documentation/devicetree/bindings/iio/adc/adi,ad7476.yaml index cf711082ad7d..666414a9c0de 100644 --- a/Documentation/devicetree/bindings/iio/adc/adi,ad7476.yaml +++ b/Documentation/devicetree/bindings/iio/adc/adi,ad7476.yaml @@ -98,6 +98,7 @@ allOf: - ti,adc121s - ti,ads7866 - ti,ads7868 + then: required: - vcc-supply # Devices with a vref diff --git a/Documentation/devicetree/bindings/iio/adc/st,stm32-adc.yaml b/Documentation/devicetree/bindings/iio/adc/st,stm32-adc.yaml index 4d6074518b5c..fa8da42cb1e6 100644 --- a/Documentation/devicetree/bindings/iio/adc/st,stm32-adc.yaml +++ b/Documentation/devicetree/bindings/iio/adc/st,stm32-adc.yaml @@ -138,7 +138,6 @@ allOf: - const: bus - const: adc minItems: 1 - maxItems: 2 interrupts: items: @@ -170,7 +169,6 @@ allOf: - const: bus - const: adc minItems: 1 - maxItems: 2 interrupts: items: diff --git a/Documentation/devicetree/bindings/iio/adc/st,stm32-dfsdm-adc.yaml b/Documentation/devicetree/bindings/iio/adc/st,stm32-dfsdm-adc.yaml index 7c260f209687..92f9472a77ae 100644 --- a/Documentation/devicetree/bindings/iio/adc/st,stm32-dfsdm-adc.yaml +++ b/Documentation/devicetree/bindings/iio/adc/st,stm32-dfsdm-adc.yaml @@ -108,9 +108,7 @@ patternProperties: - [1-5]: order 1 to 5. For audio purpose it is recommended to use order 3 to 5. $ref: /schemas/types.yaml#/definitions/uint32 - items: - minimum: 0 - maximum: 5 + maximum: 5 "#io-channel-cells": const: 1 @@ -174,7 +172,7 @@ patternProperties: contains: const: st,stm32-dfsdm-adc - - then: + then: properties: st,adc-channels: minItems: 1 @@ -206,7 +204,7 @@ patternProperties: contains: const: st,stm32-dfsdm-dmic - - then: + then: properties: st,adc-channels: maxItems: 1 @@ -254,7 +252,7 @@ allOf: contains: const: st,stm32h7-dfsdm - - then: + then: patternProperties: "^filter@[0-9]+$": properties: @@ -269,7 +267,7 @@ allOf: contains: const: st,stm32mp1-dfsdm - - then: + then: patternProperties: "^filter@[0-9]+$": properties: diff --git a/Documentation/devicetree/bindings/iio/dac/adi,ad5360.yaml b/Documentation/devicetree/bindings/iio/dac/adi,ad5360.yaml index 0d8fb56f4b09..65f86f26947c 100644 --- a/Documentation/devicetree/bindings/iio/dac/adi,ad5360.yaml +++ b/Documentation/devicetree/bindings/iio/dac/adi,ad5360.yaml @@ -59,9 +59,9 @@ allOf: contains: enum: - adi,ad5371 - then: - required: - - vref2-supply + then: + required: + - vref2-supply examples: - | diff --git a/Documentation/devicetree/bindings/input/mediatek,mt6779-keypad.yaml b/Documentation/devicetree/bindings/input/mediatek,mt6779-keypad.yaml index b1770640f94b..03ebd2665d07 100644 --- a/Documentation/devicetree/bindings/input/mediatek,mt6779-keypad.yaml +++ b/Documentation/devicetree/bindings/input/mediatek,mt6779-keypad.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Mediatek's Keypad Controller device tree bindings maintainers: - - Fengping Yu <fengping.yu@mediatek.com> + - Mattijs Korpershoek <mkorpershoek@baylibre.com> allOf: - $ref: "/schemas/input/matrix-keymap.yaml#" diff --git a/Documentation/devicetree/bindings/interconnect/qcom,rpm.yaml b/Documentation/devicetree/bindings/interconnect/qcom,rpm.yaml index 89853b482513..8a676fef8c1d 100644 --- a/Documentation/devicetree/bindings/interconnect/qcom,rpm.yaml +++ b/Documentation/devicetree/bindings/interconnect/qcom,rpm.yaml @@ -93,48 +93,48 @@ allOf: - qcom,sdm660-gnoc - qcom,sdm660-snoc - then: - properties: - clock-names: - items: - - const: bus - - const: bus_a - - clocks: - items: - - description: Bus Clock - - description: Bus A Clock - - # Child node's properties - patternProperties: - '^interconnect-[a-z0-9]+$': - type: object - description: - snoc-mm is a child of snoc, sharing snoc's register address space. - - properties: - compatible: - enum: - - qcom,msm8939-snoc-mm - - '#interconnect-cells': - const: 1 - - clock-names: - items: - - const: bus - - const: bus_a - - clocks: - items: - - description: Bus Clock - - description: Bus A Clock - - required: - - compatible - - '#interconnect-cells' - - clock-names - - clocks + then: + properties: + clock-names: + items: + - const: bus + - const: bus_a + + clocks: + items: + - description: Bus Clock + - description: Bus A Clock + + # Child node's properties + patternProperties: + '^interconnect-[a-z0-9]+$': + type: object + description: + snoc-mm is a child of snoc, sharing snoc's register address space. + + properties: + compatible: + enum: + - qcom,msm8939-snoc-mm + + '#interconnect-cells': + const: 1 + + clock-names: + items: + - const: bus + - const: bus_a + + clocks: + items: + - description: Bus Clock + - description: Bus A Clock + + required: + - compatible + - '#interconnect-cells' + - clock-names + - clocks - if: properties: diff --git a/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.yaml b/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.yaml index b7197f78e158..3912a89162f0 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.yaml +++ b/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: ARM Generic Interrupt Controller, version 3 maintainers: - - Marc Zyngier <marc.zyngier@arm.com> + - Marc Zyngier <maz@kernel.org> description: | AArch64 SMP cores are often associated with a GICv3, providing Private @@ -78,7 +78,11 @@ properties: - GIC Hypervisor interface (GICH) - GIC Virtual CPU interface (GICV) - GICC, GICH and GICV are optional. + GICC, GICH and GICV are optional, but must be described if the CPUs + support them. Examples of such CPUs are ARM's implementations of the + ARMv8.0 architecture such as Cortex-A32, A34, A35, A53, A57, A72 and + A73 (this list is not exhaustive). + minItems: 2 maxItems: 4096 # Should be enough? diff --git a/Documentation/devicetree/bindings/interrupt-controller/mrvl,intc.yaml b/Documentation/devicetree/bindings/interrupt-controller/mrvl,intc.yaml index 372ccbfae771..5a583bf3dbc1 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/mrvl,intc.yaml +++ b/Documentation/devicetree/bindings/interrupt-controller/mrvl,intc.yaml @@ -7,10 +7,8 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Marvell MMP/Orion Interrupt controller bindings maintainers: - - Thomas Gleixner <tglx@linutronix.de> - - Jason Cooper <jason@lakedaemon.net> - - Marc Zyngier <maz@kernel.org> - - Rob Herring <robh+dt@kernel.org> + - Andrew Lunn <andrew@lunn.ch> + - Gregory Clement <gregory.clement@bootlin.com> allOf: - if: diff --git a/Documentation/devicetree/bindings/interrupt-controller/samsung,exynos4210-combiner.yaml b/Documentation/devicetree/bindings/interrupt-controller/samsung,exynos4210-combiner.yaml index d631b7589d50..72456a07dac9 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/samsung,exynos4210-combiner.yaml +++ b/Documentation/devicetree/bindings/interrupt-controller/samsung,exynos4210-combiner.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung Exynos SoC Interrupt Combiner Controller maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | Samsung's Exynos4 architecture includes a interrupt combiner controller which diff --git a/Documentation/devicetree/bindings/leds/leds-mt6360.yaml b/Documentation/devicetree/bindings/leds/leds-mt6360.yaml index b2fe6eb89389..10f95bf1d666 100644 --- a/Documentation/devicetree/bindings/leds/leds-mt6360.yaml +++ b/Documentation/devicetree/bindings/leds/leds-mt6360.yaml @@ -43,8 +43,6 @@ patternProperties: - 4 # LED output FLASH1 - 5 # LED output FLASH2 -unevaluatedProperties: false - required: - compatible - "#address-cells" diff --git a/Documentation/devicetree/bindings/leds/maxim,max77693.yaml b/Documentation/devicetree/bindings/leds/maxim,max77693.yaml index 86a0005cf156..e27f57bb52ae 100644 --- a/Documentation/devicetree/bindings/leds/maxim,max77693.yaml +++ b/Documentation/devicetree/bindings/leds/maxim,max77693.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Maxim MAX77693 MicroUSB and Companion Power Management IC LEDs maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for Maxim MAX77693 MicroUSB Integrated diff --git a/Documentation/devicetree/bindings/media/coda.yaml b/Documentation/devicetree/bindings/media/coda.yaml index 36781ee4617f..c9d5adbc8c4a 100644 --- a/Documentation/devicetree/bindings/media/coda.yaml +++ b/Documentation/devicetree/bindings/media/coda.yaml @@ -65,7 +65,6 @@ properties: iram: $ref: /schemas/types.yaml#/definitions/phandle description: phandle pointing to the SRAM device node - maxItems: 1 required: - compatible diff --git a/Documentation/devicetree/bindings/media/i2c/dongwoon,dw9807-vcm.txt b/Documentation/devicetree/bindings/media/i2c/dongwoon,dw9807-vcm.txt deleted file mode 100644 index c4701f1eaaf6..000000000000 --- a/Documentation/devicetree/bindings/media/i2c/dongwoon,dw9807-vcm.txt +++ /dev/null @@ -1,9 +0,0 @@ -Dongwoon Anatech DW9807 voice coil lens driver - -DW9807 is a 10-bit DAC with current sink capability. It is intended for -controlling voice coil lenses. - -Mandatory properties: - -- compatible: "dongwoon,dw9807-vcm" -- reg: I2C slave address diff --git a/Documentation/devicetree/bindings/media/i2c/dongwoon,dw9807-vcm.yaml b/Documentation/devicetree/bindings/media/i2c/dongwoon,dw9807-vcm.yaml new file mode 100644 index 000000000000..aae246ca3fcf --- /dev/null +++ b/Documentation/devicetree/bindings/media/i2c/dongwoon,dw9807-vcm.yaml @@ -0,0 +1,41 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +# Copyright (C) 2018, 2021 Intel Corporation +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/media/i2c/dongwoon,dw9807-vcm.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Dongwoon Anatech DW9807 voice coil lens driver + +maintainers: + - Sakari Ailus <sakari.ailus@linux.intel.com> + +description: | + DW9807 is a 10-bit DAC with current sink capability. It is intended for + controlling voice coil lenses. + +properties: + compatible: + const: dongwoon,dw9807-vcm + + reg: + maxItems: 1 + +required: + - compatible + - reg + +additionalProperties: false + +examples: + - | + i2c { + #address-cells = <1>; + #size-cells = <0>; + + lens@e { + compatible = "dongwoon,dw9807-vcm"; + reg = <0x0e>; + }; + }; +... diff --git a/Documentation/devicetree/bindings/media/i2c/sony,imx412.yaml b/Documentation/devicetree/bindings/media/i2c/sony,imx412.yaml index afcf70947f7e..26d1807d0bb6 100644 --- a/Documentation/devicetree/bindings/media/i2c/sony,imx412.yaml +++ b/Documentation/devicetree/bindings/media/i2c/sony,imx412.yaml @@ -32,6 +32,15 @@ properties: description: Clock frequency 6MHz, 12MHz, 18MHz, 24MHz or 27MHz maxItems: 1 + dovdd-supply: + description: Interface power supply. + + avdd-supply: + description: Analog power supply. + + dvdd-supply: + description: Digital power supply. + reset-gpios: description: Reference to the GPIO connected to the XCLR pin, if any. maxItems: 1 diff --git a/Documentation/devicetree/bindings/media/mediatek,vcodec-decoder.yaml b/Documentation/devicetree/bindings/media/mediatek,vcodec-decoder.yaml index 9b179bb44dfb..aa55ca65d6ed 100644 --- a/Documentation/devicetree/bindings/media/mediatek,vcodec-decoder.yaml +++ b/Documentation/devicetree/bindings/media/mediatek,vcodec-decoder.yaml @@ -63,13 +63,11 @@ properties: mediatek,vpu: $ref: /schemas/types.yaml#/definitions/phandle - maxItems: 1 description: Describes point to vpu. mediatek,scp: $ref: /schemas/types.yaml#/definitions/phandle - maxItems: 1 description: Describes point to scp. diff --git a/Documentation/devicetree/bindings/media/mediatek,vcodec-encoder.yaml b/Documentation/devicetree/bindings/media/mediatek,vcodec-encoder.yaml index e7b65a91c92c..d36fcca04cbc 100644 --- a/Documentation/devicetree/bindings/media/mediatek,vcodec-encoder.yaml +++ b/Documentation/devicetree/bindings/media/mediatek,vcodec-encoder.yaml @@ -55,16 +55,17 @@ properties: mediatek,vpu: $ref: /schemas/types.yaml#/definitions/phandle - maxItems: 1 description: Describes point to vpu. mediatek,scp: $ref: /schemas/types.yaml#/definitions/phandle - maxItems: 1 description: Describes point to scp. + power-domains: + maxItems: 1 + required: - compatible - reg @@ -106,7 +107,6 @@ allOf: enum: - mediatek,mt8173-vcodec-enc - mediatek,mt8192-vcodec-enc - - mediatek,mt8173-vcodec-enc then: properties: diff --git a/Documentation/devicetree/bindings/media/mediatek,vcodec-subdev-decoder.yaml b/Documentation/devicetree/bindings/media/mediatek,vcodec-subdev-decoder.yaml index 7687be0f50aa..440646e44c0d 100644 --- a/Documentation/devicetree/bindings/media/mediatek,vcodec-subdev-decoder.yaml +++ b/Documentation/devicetree/bindings/media/mediatek,vcodec-subdev-decoder.yaml @@ -47,7 +47,9 @@ description: | properties: compatible: - const: mediatek,mt8192-vcodec-dec + enum: + - mediatek,mt8192-vcodec-dec + - mediatek,mt8186-vcodec-dec reg: maxItems: 1 @@ -61,7 +63,6 @@ properties: mediatek,scp: $ref: /schemas/types.yaml#/definitions/phandle - maxItems: 1 description: | The node of system control processor (SCP), using the remoteproc & rpmsg framework. diff --git a/Documentation/devicetree/bindings/media/microchip,xisc.yaml b/Documentation/devicetree/bindings/media/microchip,xisc.yaml index 086e1430af4f..3be8f64c3e21 100644 --- a/Documentation/devicetree/bindings/media/microchip,xisc.yaml +++ b/Documentation/devicetree/bindings/media/microchip,xisc.yaml @@ -67,7 +67,7 @@ properties: remote-endpoint: true bus-width: - enum: [8, 9, 10, 11, 12] + enum: [8, 9, 10, 11, 12, 14] default: 12 hsync-active: diff --git a/Documentation/devicetree/bindings/media/rockchip,vdec.yaml b/Documentation/devicetree/bindings/media/rockchip,vdec.yaml index 089f11d21b25..3bcfb8e12333 100644 --- a/Documentation/devicetree/bindings/media/rockchip,vdec.yaml +++ b/Documentation/devicetree/bindings/media/rockchip,vdec.yaml @@ -18,7 +18,9 @@ properties: oneOf: - const: rockchip,rk3399-vdec - items: - - const: rockchip,rk3228-vdec + - enum: + - rockchip,rk3228-vdec + - rockchip,rk3328-vdec - const: rockchip,rk3399-vdec reg: diff --git a/Documentation/devicetree/bindings/media/rockchip-vpu.yaml b/Documentation/devicetree/bindings/media/rockchip-vpu.yaml index bacb60a34989..6cc4d3e5a61d 100644 --- a/Documentation/devicetree/bindings/media/rockchip-vpu.yaml +++ b/Documentation/devicetree/bindings/media/rockchip-vpu.yaml @@ -23,6 +23,7 @@ properties: - rockchip,rk3328-vpu - rockchip,rk3399-vpu - rockchip,px30-vpu + - rockchip,rk3568-vpu - items: - const: rockchip,rk3188-vpu - const: rockchip,rk3066-vpu diff --git a/Documentation/devicetree/bindings/media/video-interfaces.yaml b/Documentation/devicetree/bindings/media/video-interfaces.yaml index 4391dce2caee..68c3b9871cf3 100644 --- a/Documentation/devicetree/bindings/media/video-interfaces.yaml +++ b/Documentation/devicetree/bindings/media/video-interfaces.yaml @@ -93,6 +93,7 @@ properties: - 4 # MIPI CSI-2 D-PHY - 5 # Parallel - 6 # BT.656 + - 7 # DPI description: Data bus type. diff --git a/Documentation/devicetree/bindings/memory-controllers/brcm,dpfe-cpu.yaml b/Documentation/devicetree/bindings/memory-controllers/brcm,dpfe-cpu.yaml index 769f13250047..08cbdcddfead 100644 --- a/Documentation/devicetree/bindings/memory-controllers/brcm,dpfe-cpu.yaml +++ b/Documentation/devicetree/bindings/memory-controllers/brcm,dpfe-cpu.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: DDR PHY Front End (DPFE) for Broadcom STB maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Markus Mayer <mmayer@broadcom.com> properties: diff --git a/Documentation/devicetree/bindings/memory-controllers/ddr/jedec,lpddr2-timings.yaml b/Documentation/devicetree/bindings/memory-controllers/ddr/jedec,lpddr2-timings.yaml index f3e62ee07126..1daa66592477 100644 --- a/Documentation/devicetree/bindings/memory-controllers/ddr/jedec,lpddr2-timings.yaml +++ b/Documentation/devicetree/bindings/memory-controllers/ddr/jedec,lpddr2-timings.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: LPDDR2 SDRAM AC timing parameters for a given speed-bin maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/memory-controllers/ddr/jedec,lpddr2.yaml b/Documentation/devicetree/bindings/memory-controllers/ddr/jedec,lpddr2.yaml index dd2141cad866..9d78f140609b 100644 --- a/Documentation/devicetree/bindings/memory-controllers/ddr/jedec,lpddr2.yaml +++ b/Documentation/devicetree/bindings/memory-controllers/ddr/jedec,lpddr2.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: LPDDR2 SDRAM compliant to JEDEC JESD209-2 maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/memory-controllers/ddr/jedec,lpddr3-timings.yaml b/Documentation/devicetree/bindings/memory-controllers/ddr/jedec,lpddr3-timings.yaml index 97c3e988af5f..5c6512c1e1e3 100644 --- a/Documentation/devicetree/bindings/memory-controllers/ddr/jedec,lpddr3-timings.yaml +++ b/Documentation/devicetree/bindings/memory-controllers/ddr/jedec,lpddr3-timings.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: LPDDR3 SDRAM AC timing parameters for a given speed-bin maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/memory-controllers/ddr/jedec,lpddr3.yaml b/Documentation/devicetree/bindings/memory-controllers/ddr/jedec,lpddr3.yaml index c542f32c39fa..48908a19473c 100644 --- a/Documentation/devicetree/bindings/memory-controllers/ddr/jedec,lpddr3.yaml +++ b/Documentation/devicetree/bindings/memory-controllers/ddr/jedec,lpddr3.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: LPDDR3 SDRAM compliant to JEDEC JESD209-3 maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/memory-controllers/fsl/fsl,ddr.yaml b/Documentation/devicetree/bindings/memory-controllers/fsl/fsl,ddr.yaml index af5147f9da72..84f778a99546 100644 --- a/Documentation/devicetree/bindings/memory-controllers/fsl/fsl,ddr.yaml +++ b/Documentation/devicetree/bindings/memory-controllers/fsl/fsl,ddr.yaml @@ -25,12 +25,6 @@ properties: - const: fsl,qoriq-memory-controller - enum: - fsl,bsc9132-memory-controller - - fsl,8540-memory-controller - - fsl,8541-memory-controller - - fsl,8544-memory-controller - - fsl,8548-memory-controller - - fsl,8555-memory-controller - - fsl,8568-memory-controller - fsl,mpc8536-memory-controller - fsl,mpc8540-memory-controller - fsl,mpc8541-memory-controller diff --git a/Documentation/devicetree/bindings/memory-controllers/marvell,mvebu-sdram-controller.yaml b/Documentation/devicetree/bindings/memory-controllers/marvell,mvebu-sdram-controller.yaml index 14a6bc8f421f..9249624c4fa0 100644 --- a/Documentation/devicetree/bindings/memory-controllers/marvell,mvebu-sdram-controller.yaml +++ b/Documentation/devicetree/bindings/memory-controllers/marvell,mvebu-sdram-controller.yaml @@ -8,7 +8,7 @@ title: Marvell MVEBU SDRAM controller maintainers: - Jan Luebbe <jlu@pengutronix.de> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/memory-controllers/qca,ath79-ddr-controller.yaml b/Documentation/devicetree/bindings/memory-controllers/qca,ath79-ddr-controller.yaml index 9566b3421f03..0c511ab906bf 100644 --- a/Documentation/devicetree/bindings/memory-controllers/qca,ath79-ddr-controller.yaml +++ b/Documentation/devicetree/bindings/memory-controllers/qca,ath79-ddr-controller.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Qualcomm Atheros AR7xxx/AR9xxx DDR controller maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | The DDR controller of the AR7xxx and AR9xxx families provides an interface to diff --git a/Documentation/devicetree/bindings/memory-controllers/renesas,h8300-bsc.yaml b/Documentation/devicetree/bindings/memory-controllers/renesas,h8300-bsc.yaml index 2b18cef99511..514b2c5f8858 100644 --- a/Documentation/devicetree/bindings/memory-controllers/renesas,h8300-bsc.yaml +++ b/Documentation/devicetree/bindings/memory-controllers/renesas,h8300-bsc.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: H8/300 bus controller maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Yoshinori Sato <ysato@users.sourceforge.jp> properties: diff --git a/Documentation/devicetree/bindings/memory-controllers/rockchip,rk3399-dmc.yaml b/Documentation/devicetree/bindings/memory-controllers/rockchip,rk3399-dmc.yaml new file mode 100644 index 000000000000..fb4920397d08 --- /dev/null +++ b/Documentation/devicetree/bindings/memory-controllers/rockchip,rk3399-dmc.yaml @@ -0,0 +1,384 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +# %YAML 1.2 +--- +$id: http://devicetree.org/schemas/memory-controllers/rockchip,rk3399-dmc.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Rockchip rk3399 DMC (Dynamic Memory Controller) device + +maintainers: + - Brian Norris <briannorris@chromium.org> + +properties: + compatible: + enum: + - rockchip,rk3399-dmc + + devfreq-events: + $ref: /schemas/types.yaml#/definitions/phandle + description: + Node to get DDR loading. Refer to + Documentation/devicetree/bindings/devfreq/event/rockchip-dfi.txt. + + clocks: + maxItems: 1 + + clock-names: + items: + - const: dmc_clk + + operating-points-v2: true + + center-supply: + description: + DMC regulator supply. + + rockchip,pmu: + $ref: /schemas/types.yaml#/definitions/phandle + description: + Phandle to the syscon managing the "PMU general register files". + + interrupts: + maxItems: 1 + description: + The CPU interrupt number. It should be a DCF interrupt. When DDR DVFS + finishes, a DCF interrupt is triggered. + + rockchip,ddr3_speed_bin: + deprecated: true + $ref: /schemas/types.yaml#/definitions/uint32 + description: + For values, reference include/dt-bindings/clock/rk3399-ddr.h. Selects the + DDR3 cl-trp-trcd type. It must be set according to "Speed Bin" in DDR3 + datasheet; DO NOT use a smaller "Speed Bin" than specified for the DDR3 + being used. + + rockchip,pd_idle: + deprecated: true + $ref: /schemas/types.yaml#/definitions/uint32 + description: + Configure the PD_IDLE value. Defines the power-down idle period in which + memories are placed into power-down mode if bus is idle for PD_IDLE DFI + clock cycles. + See also rockchip,pd-idle-ns. + + rockchip,sr_idle: + deprecated: true + $ref: /schemas/types.yaml#/definitions/uint32 + description: + Configure the SR_IDLE value. Defines the self-refresh idle period in + which memories are placed into self-refresh mode if bus is idle for + SR_IDLE * 1024 DFI clock cycles (DFI clocks freq is half of DRAM clock). + See also rockchip,sr-idle-ns. + default: 0 + + rockchip,sr_mc_gate_idle: + deprecated: true + $ref: /schemas/types.yaml#/definitions/uint32 + description: + Defines the memory self-refresh and controller clock gating idle period. + Memories are placed into self-refresh mode and memory controller clock + arg gating started if bus is idle for sr_mc_gate_idle*1024 DFI clock + cycles. + See also rockchip,sr-mc-gate-idle-ns. + + rockchip,srpd_lite_idle: + deprecated: true + $ref: /schemas/types.yaml#/definitions/uint32 + description: + Defines the self-refresh power down idle period in which memories are + placed into self-refresh power down mode if bus is idle for + srpd_lite_idle * 1024 DFI clock cycles. This parameter is for LPDDR4 + only. + See also rockchip,srpd-lite-idle-ns. + + rockchip,standby_idle: + deprecated: true + $ref: /schemas/types.yaml#/definitions/uint32 + description: + Defines the standby idle period in which memories are placed into + self-refresh mode. The controller, pi, PHY and DRAM clock will be gated + if bus is idle for standby_idle * DFI clock cycles. + See also rockchip,standby-idle-ns. + + rockchip,dram_dll_dis_freq: + deprecated: true + $ref: /schemas/types.yaml#/definitions/uint32 + description: | + Defines the DDR3 DLL bypass frequency in MHz. When DDR frequency is less + than DRAM_DLL_DISB_FREQ, DDR3 DLL will be bypassed. + Note: if DLL was bypassed, the odt will also stop working. + + rockchip,phy_dll_dis_freq: + deprecated: true + $ref: /schemas/types.yaml#/definitions/uint32 + description: | + Defines the PHY dll bypass frequency in MHz (Mega Hz). When DDR frequency + is less than DRAM_DLL_DISB_FREQ, PHY DLL will be bypassed. + Note: PHY DLL and PHY ODT are independent. + + rockchip,auto_pd_dis_freq: + deprecated: true + $ref: /schemas/types.yaml#/definitions/uint32 + description: + Defines the auto PD disable frequency in MHz. + + rockchip,ddr3_odt_dis_freq: + $ref: /schemas/types.yaml#/definitions/uint32 + minimum: 1000000 # In case anyone thought this was MHz. + description: + When the DRAM type is DDR3, this parameter defines the ODT disable + frequency in Hz. When the DDR frequency is less then ddr3_odt_dis_freq, + the ODT on the DRAM side and controller side are both disabled. + + rockchip,ddr3_drv: + deprecated: true + $ref: /schemas/types.yaml#/definitions/uint32 + description: + When the DRAM type is DDR3, this parameter defines the DRAM side drive + strength in ohms. + default: 40 + + rockchip,ddr3_odt: + deprecated: true + $ref: /schemas/types.yaml#/definitions/uint32 + description: + When the DRAM type is DDR3, this parameter defines the DRAM side ODT + strength in ohms. + default: 120 + + rockchip,phy_ddr3_ca_drv: + deprecated: true + $ref: /schemas/types.yaml#/definitions/uint32 + description: + When the DRAM type is DDR3, this parameter defines the phy side CA line + (incluing command line, address line and clock line) drive strength. + default: 40 + + rockchip,phy_ddr3_dq_drv: + deprecated: true + $ref: /schemas/types.yaml#/definitions/uint32 + description: + When the DRAM type is DDR3, this parameter defines the PHY side DQ line + (including DQS/DQ/DM line) drive strength. + default: 40 + + rockchip,phy_ddr3_odt: + deprecated: true + $ref: /schemas/types.yaml#/definitions/uint32 + description: + When the DRAM type is DDR3, this parameter defines the PHY side ODT + strength. + default: 240 + + rockchip,lpddr3_odt_dis_freq: + $ref: /schemas/types.yaml#/definitions/uint32 + minimum: 1000000 # In case anyone thought this was MHz. + description: + When the DRAM type is LPDDR3, this parameter defines then ODT disable + frequency in Hz. When DDR frequency is less then ddr3_odt_dis_freq, the + ODT on the DRAM side and controller side are both disabled. + + rockchip,lpddr3_drv: + deprecated: true + $ref: /schemas/types.yaml#/definitions/uint32 + description: + When the DRAM type is LPDDR3, this parameter defines the DRAM side drive + strength in ohms. + default: 34 + + rockchip,lpddr3_odt: + deprecated: true + $ref: /schemas/types.yaml#/definitions/uint32 + description: + When the DRAM type is LPDDR3, this parameter defines the DRAM side ODT + strength in ohms. + default: 240 + + rockchip,phy_lpddr3_ca_drv: + deprecated: true + $ref: /schemas/types.yaml#/definitions/uint32 + description: + When the DRAM type is LPDDR3, this parameter defines the PHY side CA line + (including command line, address line and clock line) drive strength. + default: 40 + + rockchip,phy_lpddr3_dq_drv: + deprecated: true + $ref: /schemas/types.yaml#/definitions/uint32 + description: + When the DRAM type is LPDDR3, this parameter defines the PHY side DQ line + (including DQS/DQ/DM line) drive strength. + default: 40 + + rockchip,phy_lpddr3_odt: + deprecated: true + $ref: /schemas/types.yaml#/definitions/uint32 + description: + When dram type is LPDDR3, this parameter define the phy side odt + strength, default value is 240. + + rockchip,lpddr4_odt_dis_freq: + $ref: /schemas/types.yaml#/definitions/uint32 + minimum: 1000000 # In case anyone thought this was MHz. + description: + When the DRAM type is LPDDR4, this parameter defines the ODT disable + frequency in Hz. When the DDR frequency is less then ddr3_odt_dis_freq, + the ODT on the DRAM side and controller side are both disabled. + + rockchip,lpddr4_drv: + deprecated: true + $ref: /schemas/types.yaml#/definitions/uint32 + description: + When the DRAM type is LPDDR4, this parameter defines the DRAM side drive + strength in ohms. + default: 60 + + rockchip,lpddr4_dq_odt: + deprecated: true + $ref: /schemas/types.yaml#/definitions/uint32 + description: + When the DRAM type is LPDDR4, this parameter defines the DRAM side ODT on + DQS/DQ line strength in ohms. + default: 40 + + rockchip,lpddr4_ca_odt: + deprecated: true + $ref: /schemas/types.yaml#/definitions/uint32 + description: + When the DRAM type is LPDDR4, this parameter defines the DRAM side ODT on + CA line strength in ohms. + default: 40 + + rockchip,phy_lpddr4_ca_drv: + deprecated: true + $ref: /schemas/types.yaml#/definitions/uint32 + description: + When the DRAM type is LPDDR4, this parameter defines the PHY side CA line + (including command address line) drive strength. + default: 40 + + rockchip,phy_lpddr4_ck_cs_drv: + deprecated: true + $ref: /schemas/types.yaml#/definitions/uint32 + description: + When the DRAM type is LPDDR4, this parameter defines the PHY side clock + line and CS line drive strength. + default: 80 + + rockchip,phy_lpddr4_dq_drv: + deprecated: true + $ref: /schemas/types.yaml#/definitions/uint32 + description: + When the DRAM type is LPDDR4, this parameter defines the PHY side DQ line + (including DQS/DQ/DM line) drive strength. + default: 80 + + rockchip,phy_lpddr4_odt: + deprecated: true + $ref: /schemas/types.yaml#/definitions/uint32 + description: + When the DRAM type is LPDDR4, this parameter defines the PHY side ODT + strength. + default: 60 + + rockchip,pd-idle-ns: + description: + Configure the PD_IDLE value in nanoseconds. Defines the power-down idle + period in which memories are placed into power-down mode if bus is idle + for PD_IDLE nanoseconds. + + rockchip,sr-idle-ns: + description: + Configure the SR_IDLE value in nanoseconds. Defines the self-refresh idle + period in which memories are placed into self-refresh mode if bus is idle + for SR_IDLE nanoseconds. + default: 0 + + rockchip,sr-mc-gate-idle-ns: + description: + Defines the memory self-refresh and controller clock gating idle period in nanoseconds. + Memories are placed into self-refresh mode and memory controller clock + arg gating started if bus is idle for sr_mc_gate_idle nanoseconds. + + rockchip,srpd-lite-idle-ns: + description: + Defines the self-refresh power down idle period in which memories are + placed into self-refresh power down mode if bus is idle for + srpd_lite_idle nanoseonds. This parameter is for LPDDR4 only. + + rockchip,standby-idle-ns: + description: + Defines the standby idle period in which memories are placed into + self-refresh mode. The controller, pi, PHY and DRAM clock will be gated + if bus is idle for standby_idle nanoseconds. + + rockchip,pd-idle-dis-freq-hz: + description: + Defines the power-down idle disable frequency in Hz. When the DDR + frequency is greater than pd-idle-dis-freq, power-down idle is disabled. + See also rockchip,pd-idle-ns. + + rockchip,sr-idle-dis-freq-hz: + description: + Defines the self-refresh idle disable frequency in Hz. When the DDR + frequency is greater than sr-idle-dis-freq, self-refresh idle is + disabled. See also rockchip,sr-idle-ns. + + rockchip,sr-mc-gate-idle-dis-freq-hz: + description: + Defines the self-refresh and memory-controller clock gating disable + frequency in Hz. When the DDR frequency is greater than + sr-mc-gate-idle-dis-freq, the clock will not be gated when idle. See also + rockchip,sr-mc-gate-idle-ns. + + rockchip,srpd-lite-idle-dis-freq-hz: + description: + Defines the self-refresh power down idle disable frequency in Hz. When + the DDR frequency is greater than srpd-lite-idle-dis-freq, memory will + not be placed into self-refresh power down mode when idle. See also + rockchip,srpd-lite-idle-ns. + + rockchip,standby-idle-dis-freq-hz: + description: + Defines the standby idle disable frequency in Hz. When the DDR frequency + is greater than standby-idle-dis-freq, standby idle is disabled. See also + rockchip,standby-idle-ns. + +required: + - compatible + - devfreq-events + - clocks + - clock-names + - operating-points-v2 + - center-supply + +additionalProperties: false + +examples: + - | + #include <dt-bindings/clock/rk3399-cru.h> + #include <dt-bindings/interrupt-controller/arm-gic.h> + memory-controller { + compatible = "rockchip,rk3399-dmc"; + devfreq-events = <&dfi>; + rockchip,pmu = <&pmu>; + interrupts = <GIC_SPI 1 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&cru SCLK_DDRC>; + clock-names = "dmc_clk"; + operating-points-v2 = <&dmc_opp_table>; + center-supply = <&ppvar_centerlogic>; + rockchip,pd-idle-ns = <160>; + rockchip,sr-idle-ns = <10240>; + rockchip,sr-mc-gate-idle-ns = <40960>; + rockchip,srpd-lite-idle-ns = <61440>; + rockchip,standby-idle-ns = <81920>; + rockchip,ddr3_odt_dis_freq = <333000000>; + rockchip,lpddr3_odt_dis_freq = <333000000>; + rockchip,lpddr4_odt_dis_freq = <333000000>; + rockchip,pd-idle-dis-freq-hz = <1000000000>; + rockchip,sr-idle-dis-freq-hz = <1000000000>; + rockchip,sr-mc-gate-idle-dis-freq-hz = <1000000000>; + rockchip,srpd-lite-idle-dis-freq-hz = <0>; + rockchip,standby-idle-dis-freq-hz = <928000000>; + }; diff --git a/Documentation/devicetree/bindings/memory-controllers/samsung,exynos5422-dmc.yaml b/Documentation/devicetree/bindings/memory-controllers/samsung,exynos5422-dmc.yaml index f152243f6b18..098348b2b815 100644 --- a/Documentation/devicetree/bindings/memory-controllers/samsung,exynos5422-dmc.yaml +++ b/Documentation/devicetree/bindings/memory-controllers/samsung,exynos5422-dmc.yaml @@ -9,7 +9,7 @@ title: | Controller device maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Lukasz Luba <lukasz.luba@arm.com> description: | diff --git a/Documentation/devicetree/bindings/memory-controllers/synopsys,ddrc-ecc.yaml b/Documentation/devicetree/bindings/memory-controllers/synopsys,ddrc-ecc.yaml index fb7ae38a9c86..f46e95704f53 100644 --- a/Documentation/devicetree/bindings/memory-controllers/synopsys,ddrc-ecc.yaml +++ b/Documentation/devicetree/bindings/memory-controllers/synopsys,ddrc-ecc.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Synopsys IntelliDDR Multi Protocol memory controller maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Manish Narani <manish.narani@xilinx.com> - Michal Simek <michal.simek@xilinx.com> @@ -24,9 +24,9 @@ description: | properties: compatible: enum: + - snps,ddrc-3.80a - xlnx,zynq-ddrc-a05 - xlnx,zynqmp-ddrc-2.40a - - snps,ddrc-3.80a interrupts: maxItems: 1 @@ -43,7 +43,9 @@ allOf: properties: compatible: contains: - const: xlnx,zynqmp-ddrc-2.40a + enum: + - snps,ddrc-3.80a + - xlnx,zynqmp-ddrc-2.40a then: required: - interrupts diff --git a/Documentation/devicetree/bindings/memory-controllers/ti,da8xx-ddrctl.yaml b/Documentation/devicetree/bindings/memory-controllers/ti,da8xx-ddrctl.yaml index 9ed51185ff99..382ddab60fbd 100644 --- a/Documentation/devicetree/bindings/memory-controllers/ti,da8xx-ddrctl.yaml +++ b/Documentation/devicetree/bindings/memory-controllers/ti,da8xx-ddrctl.yaml @@ -8,7 +8,7 @@ title: Texas Instruments da8xx DDR2/mDDR memory controller maintainers: - Bartosz Golaszewski <bgolaszewski@baylibre.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | Documentation: diff --git a/Documentation/devicetree/bindings/mfd/atmel-flexcom.txt b/Documentation/devicetree/bindings/mfd/atmel-flexcom.txt index 692300117c64..9d837535637b 100644 --- a/Documentation/devicetree/bindings/mfd/atmel-flexcom.txt +++ b/Documentation/devicetree/bindings/mfd/atmel-flexcom.txt @@ -54,7 +54,7 @@ flexcom@f8034000 { clock-names = "spi_clk"; atmel,fifo-size = <32>; - mtd_dataflash@0 { + flash@0 { compatible = "atmel,at25f512b"; reg = <0>; spi-max-frequency = <20000000>; diff --git a/Documentation/devicetree/bindings/mfd/maxim,max14577.yaml b/Documentation/devicetree/bindings/mfd/maxim,max14577.yaml index 27870b8760a6..52edd1bf549f 100644 --- a/Documentation/devicetree/bindings/mfd/maxim,max14577.yaml +++ b/Documentation/devicetree/bindings/mfd/maxim,max14577.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Maxim MAX14577/MAX77836 MicroUSB and Companion Power Management IC maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for Maxim MAX14577/MAX77836 MicroUSB diff --git a/Documentation/devicetree/bindings/mfd/maxim,max77686.yaml b/Documentation/devicetree/bindings/mfd/maxim,max77686.yaml index 859655a789c3..d027aabe453b 100644 --- a/Documentation/devicetree/bindings/mfd/maxim,max77686.yaml +++ b/Documentation/devicetree/bindings/mfd/maxim,max77686.yaml @@ -8,7 +8,7 @@ title: Maxim MAX77686 Power Management IC maintainers: - Chanwoo Choi <cw00.choi@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for Maxim MAX77686 Power Management diff --git a/Documentation/devicetree/bindings/mfd/maxim,max77693.yaml b/Documentation/devicetree/bindings/mfd/maxim,max77693.yaml index 906101197e11..1b06a77ec798 100644 --- a/Documentation/devicetree/bindings/mfd/maxim,max77693.yaml +++ b/Documentation/devicetree/bindings/mfd/maxim,max77693.yaml @@ -8,7 +8,7 @@ title: Maxim MAX77693 MicroUSB and Companion Power Management IC maintainers: - Chanwoo Choi <cw00.choi@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for Maxim MAX77693 MicroUSB diff --git a/Documentation/devicetree/bindings/mfd/maxim,max77802.yaml b/Documentation/devicetree/bindings/mfd/maxim,max77802.yaml index baa1346ac5d5..ad2013900b03 100644 --- a/Documentation/devicetree/bindings/mfd/maxim,max77802.yaml +++ b/Documentation/devicetree/bindings/mfd/maxim,max77802.yaml @@ -8,7 +8,7 @@ title: Maxim MAX77802 Power Management IC maintainers: - Javier Martinez Canillas <javier@dowhile0.org> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for Maxim MAX77802 Power Management diff --git a/Documentation/devicetree/bindings/mfd/maxim,max77843.yaml b/Documentation/devicetree/bindings/mfd/maxim,max77843.yaml index 61a0f9dcb983..f30f96bbff43 100644 --- a/Documentation/devicetree/bindings/mfd/maxim,max77843.yaml +++ b/Documentation/devicetree/bindings/mfd/maxim,max77843.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Maxim MAX77843 MicroUSB and Companion Power Management IC maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for Maxim MAX77843 MicroUSB diff --git a/Documentation/devicetree/bindings/mfd/samsung,exynos5433-lpass.yaml b/Documentation/devicetree/bindings/mfd/samsung,exynos5433-lpass.yaml index bae55c98961c..f7bb67d10eff 100644 --- a/Documentation/devicetree/bindings/mfd/samsung,exynos5433-lpass.yaml +++ b/Documentation/devicetree/bindings/mfd/samsung,exynos5433-lpass.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung Exynos SoC Low Power Audio Subsystem (LPASS) maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Sylwester Nawrocki <s.nawrocki@samsung.com> properties: diff --git a/Documentation/devicetree/bindings/mfd/samsung,s2mpa01.yaml b/Documentation/devicetree/bindings/mfd/samsung,s2mpa01.yaml index 017befdf8adb..055dfc337c2f 100644 --- a/Documentation/devicetree/bindings/mfd/samsung,s2mpa01.yaml +++ b/Documentation/devicetree/bindings/mfd/samsung,s2mpa01.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung S2MPA01 Power Management IC maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for S2M and S5M family of Power diff --git a/Documentation/devicetree/bindings/mfd/samsung,s2mps11.yaml b/Documentation/devicetree/bindings/mfd/samsung,s2mps11.yaml index 771b3f16da96..5ff6546c72b7 100644 --- a/Documentation/devicetree/bindings/mfd/samsung,s2mps11.yaml +++ b/Documentation/devicetree/bindings/mfd/samsung,s2mps11.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung S2MPS11/13/14/15 and S2MPU02 Power Management IC maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for S2M and S5M family of Power diff --git a/Documentation/devicetree/bindings/mfd/samsung,s5m8767.yaml b/Documentation/devicetree/bindings/mfd/samsung,s5m8767.yaml index 5531718abdf0..10c7b408f33a 100644 --- a/Documentation/devicetree/bindings/mfd/samsung,s5m8767.yaml +++ b/Documentation/devicetree/bindings/mfd/samsung,s5m8767.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung S5M8767 Power Management IC maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for S2M and S5M family of Power diff --git a/Documentation/devicetree/bindings/mmc/brcm,sdhci-brcmstb.yaml b/Documentation/devicetree/bindings/mmc/brcm,sdhci-brcmstb.yaml index dccd5ad96981..b672202fff4e 100644 --- a/Documentation/devicetree/bindings/mmc/brcm,sdhci-brcmstb.yaml +++ b/Documentation/devicetree/bindings/mmc/brcm,sdhci-brcmstb.yaml @@ -31,7 +31,7 @@ properties: - const: brcm,sdhci-brcmstb reg: - minItems: 2 + maxItems: 2 reg-names: items: @@ -65,15 +65,15 @@ unevaluatedProperties: false examples: - | mmc@84b0000 { - sd-uhs-sdr50; - sd-uhs-ddr50; - sd-uhs-sdr104; - sdhci,auto-cmd12; compatible = "brcm,bcm7216-sdhci", "brcm,bcm7445-sdhci", "brcm,sdhci-brcmstb"; reg = <0x84b0000 0x260>, <0x84b0300 0x200>; reg-names = "host", "cfg"; + sd-uhs-sdr50; + sd-uhs-ddr50; + sd-uhs-sdr104; + sdhci,auto-cmd12; interrupts = <0x0 0x26 0x4>; interrupt-names = "sdio0_0"; clocks = <&scmi_clk 245>; @@ -81,6 +81,11 @@ examples: }; mmc@84b1000 { + compatible = "brcm,bcm7216-sdhci", + "brcm,bcm7445-sdhci", + "brcm,sdhci-brcmstb"; + reg = <0x84b1000 0x260>, <0x84b1300 0x200>; + reg-names = "host", "cfg"; mmc-ddr-1_8v; mmc-hs200-1_8v; mmc-hs400-1_8v; @@ -88,11 +93,6 @@ examples: supports-cqe; non-removable; bus-width = <0x8>; - compatible = "brcm,bcm7216-sdhci", - "brcm,bcm7445-sdhci", - "brcm,sdhci-brcmstb"; - reg = <0x84b1000 0x260>, <0x84b1300 0x200>; - reg-names = "host", "cfg"; interrupts = <0x0 0x27 0x4>; interrupt-names = "sdio1_0"; clocks = <&scmi_clk 245>; diff --git a/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.yaml b/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.yaml index 7dbbcae9485c..29339d0196ec 100644 --- a/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.yaml +++ b/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.yaml @@ -34,22 +34,47 @@ properties: - fsl,imx6ull-usdhc - fsl,imx7d-usdhc - fsl,imx7ulp-usdhc + - fsl,imx8mm-usdhc - fsl,imxrt1050-usdhc - nxp,s32g2-usdhc - items: - enum: + - fsl,imx8mq-usdhc + - const: fsl,imx7d-usdhc + - items: + - enum: + - fsl,imx8mn-usdhc + - fsl,imx8mp-usdhc + - fsl,imx93-usdhc + - fsl,imx8ulp-usdhc + - const: fsl,imx8mm-usdhc + - items: + - enum: + - fsl,imx8qm-usdhc + - const: fsl,imx8qxp-usdhc + - items: + - enum: + - fsl,imx8dxl-usdhc - fsl,imx8mm-usdhc - fsl,imx8mn-usdhc - fsl,imx8mp-usdhc - - fsl,imx8mq-usdhc - fsl,imx8qm-usdhc - fsl,imx8qxp-usdhc - const: fsl,imx7d-usdhc + deprecated: true - items: - enum: - - fsl,imx93-usdhc - - fsl,imx8ulp-usdhc + - fsl,imx8mn-usdhc + - fsl,imx8mp-usdhc - const: fsl,imx8mm-usdhc + - const: fsl,imx7d-usdhc + deprecated: true + - items: + - enum: + - fsl,imx8qm-usdhc + - const: fsl,imx8qxp-usdhc + - const: fsl,imx7d-usdhc + deprecated: true reg: maxItems: 1 diff --git a/Documentation/devicetree/bindings/mmc/marvell,dove-sdhci.yaml b/Documentation/devicetree/bindings/mmc/marvell,dove-sdhci.yaml new file mode 100644 index 000000000000..7c9c652ad59c --- /dev/null +++ b/Documentation/devicetree/bindings/mmc/marvell,dove-sdhci.yaml @@ -0,0 +1,44 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/mmc/marvell,dove-sdhci.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Marvell sdhci-dove controller + +maintainers: + - Adrian Hunter <adrian.hunter@intel.com> + - Ulf Hansson <ulf.hansson@linaro.org> + +allOf: + - $ref: mmc-controller.yaml# + +properties: + compatible: + const: marvell,dove-sdhci + + reg: + maxItems: 1 + + interrupts: + minItems: 1 + maxItems: 2 + + clocks: + maxItems: 1 + +required: + - compatible + - reg + - interrupts + +unevaluatedProperties: false + +examples: + - | + sdio0: mmc@92000 { + compatible = "marvell,dove-sdhci"; + reg = <0x92000 0x100>; + interrupts = <35>; + clocks = <&gate_clk 9>; + }; diff --git a/Documentation/devicetree/bindings/mmc/marvell,orion-sdio.yaml b/Documentation/devicetree/bindings/mmc/marvell,orion-sdio.yaml new file mode 100644 index 000000000000..8a97ded15aed --- /dev/null +++ b/Documentation/devicetree/bindings/mmc/marvell,orion-sdio.yaml @@ -0,0 +1,44 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/mmc/marvell,orion-sdio.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Marvell orion-sdio controller + +maintainers: + - Nicolas Pitre <nico@fluxnic.net> + - Ulf Hansson <ulf.hansson@linaro.org> + +allOf: + - $ref: mmc-controller.yaml# + +properties: + compatible: + const: marvell,orion-sdio + + reg: + maxItems: 1 + + interrupts: + maxItems: 1 + + clocks: + maxItems: 1 + +required: + - compatible + - reg + - interrupts + - clocks + +unevaluatedProperties: false + +examples: + - | + mmc@d00d4000 { + compatible = "marvell,orion-sdio"; + reg = <0xd00d4000 0x200>; + interrupts = <54>; + clocks = <&gateclk 17>; + }; diff --git a/Documentation/devicetree/bindings/mmc/marvell,xenon-sdhci.txt b/Documentation/devicetree/bindings/mmc/marvell,xenon-sdhci.txt deleted file mode 100644 index c51a62d751dc..000000000000 --- a/Documentation/devicetree/bindings/mmc/marvell,xenon-sdhci.txt +++ /dev/null @@ -1,173 +0,0 @@ -Marvell Xenon SDHCI Controller device tree bindings -This file documents differences between the core mmc properties -described by mmc.txt and the properties used by the Xenon implementation. - -Multiple SDHCs might be put into a single Xenon IP, to save size and cost. -Each SDHC is independent and owns independent resources, such as register sets, -clock and PHY. -Each SDHC should have an independent device tree node. - -Required Properties: -- compatible: should be one of the following - - "marvell,armada-3700-sdhci": For controllers on Armada-3700 SoC. - Must provide a second register area and marvell,pad-type. - - "marvell,armada-ap806-sdhci": For controllers on Armada AP806. - - "marvell,armada-ap807-sdhci": For controllers on Armada AP807. - - "marvell,armada-cp110-sdhci": For controllers on Armada CP110. - -- clocks: - Array of clocks required for SDHC. - Require at least input clock for Xenon IP core. For Armada AP806 and - CP110, the AXI clock is also mandatory. - -- clock-names: - Array of names corresponding to clocks property. - The input clock for Xenon IP core should be named as "core". - The input clock for the AXI bus must be named as "axi". - -- reg: - * For "marvell,armada-3700-sdhci", two register areas. - The first one for Xenon IP register. The second one for the Armada 3700 SoC - PHY PAD Voltage Control register. - Please follow the examples with compatible "marvell,armada-3700-sdhci" - in below. - Please also check property marvell,pad-type in below. - - * For other compatible strings, one register area for Xenon IP. - -Optional Properties: -- marvell,xenon-sdhc-id: - Indicate the corresponding bit index of current SDHC in - SDHC System Operation Control Register Bit[7:0]. - Set/clear the corresponding bit to enable/disable current SDHC. - If Xenon IP contains only one SDHC, this property is optional. - -- marvell,xenon-phy-type: - Xenon support multiple types of PHYs. - To select eMMC 5.1 PHY, set: - marvell,xenon-phy-type = "emmc 5.1 phy" - eMMC 5.1 PHY is the default choice if this property is not provided. - To select eMMC 5.0 PHY, set: - marvell,xenon-phy-type = "emmc 5.0 phy" - - All those types of PHYs can support eMMC, SD and SDIO. - Please note that this property only presents the type of PHY. - It doesn't stand for the entire SDHC type or property. - For example, "emmc 5.1 phy" doesn't mean that this Xenon SDHC only - supports eMMC 5.1. - -- marvell,xenon-phy-znr: - Set PHY ZNR value. - Only available for eMMC PHY. - Valid range = [0:0x1F]. - ZNR is set as 0xF by default if this property is not provided. - -- marvell,xenon-phy-zpr: - Set PHY ZPR value. - Only available for eMMC PHY. - Valid range = [0:0x1F]. - ZPR is set as 0xF by default if this property is not provided. - -- marvell,xenon-phy-nr-success-tun: - Set the number of required consecutive successful sampling points - used to identify a valid sampling window, in tuning process. - Valid range = [1:7]. - Set as 0x4 by default if this property is not provided. - -- marvell,xenon-phy-tun-step-divider: - Set the divider for calculating TUN_STEP. - Set as 64 by default if this property is not provided. - -- marvell,xenon-phy-slow-mode: - If this property is selected, transfers will bypass PHY. - Only available when bus frequency lower than 55MHz in SDR mode. - Disabled by default. Please only try this property if timing issues - always occur with PHY enabled in eMMC HS SDR, SD SDR12, SD SDR25, - SD Default Speed and HS mode and eMMC legacy speed mode. - -- marvell,xenon-tun-count: - Xenon SDHC SoC usually doesn't provide re-tuning counter in - Capabilities Register 3 Bit[11:8]. - This property provides the re-tuning counter. - If this property is not set, default re-tuning counter will - be set as 0x9 in driver. - -- marvell,pad-type: - Type of Armada 3700 SoC PHY PAD Voltage Controller register. - Only valid when "marvell,armada-3700-sdhci" is selected. - Two types: "sd" and "fixed-1-8v". - If "sd" is selected, SoC PHY PAD is set as 3.3V at the beginning and is - switched to 1.8V when later in higher speed mode. - If "fixed-1-8v" is selected, SoC PHY PAD is fixed 1.8V, such as for eMMC. - Please follow the examples with compatible "marvell,armada-3700-sdhci" - in below. - -Example: -- For eMMC: - - sdhci@aa0000 { - compatible = "marvell,armada-ap806-sdhci"; - reg = <0xaa0000 0x1000>; - interrupts = <GIC_SPI 13 IRQ_TYPE_LEVEL_HIGH> - clocks = <&emmc_clk>,<&axi_clk>; - clock-names = "core", "axi"; - bus-width = <4>; - marvell,xenon-phy-slow-mode; - marvell,xenon-tun-count = <11>; - non-removable; - no-sd; - no-sdio; - - /* Vmmc and Vqmmc are both fixed */ - }; - -- For SD/SDIO: - - sdhci@ab0000 { - compatible = "marvell,armada-cp110-sdhci"; - reg = <0xab0000 0x1000>; - interrupts = <GIC_SPI 55 IRQ_TYPE_LEVEL_HIGH> - vqmmc-supply = <&sd_vqmmc_regulator>; - vmmc-supply = <&sd_vmmc_regulator>; - clocks = <&sdclk>, <&axi_clk>; - clock-names = "core", "axi"; - bus-width = <4>; - marvell,xenon-tun-count = <9>; - }; - -- For eMMC with compatible "marvell,armada-3700-sdhci": - - sdhci@aa0000 { - compatible = "marvell,armada-3700-sdhci"; - reg = <0xaa0000 0x1000>, - <phy_addr 0x4>; - interrupts = <GIC_SPI 13 IRQ_TYPE_LEVEL_HIGH> - clocks = <&emmcclk>; - clock-names = "core"; - bus-width = <8>; - mmc-ddr-1_8v; - mmc-hs400-1_8v; - non-removable; - no-sd; - no-sdio; - - /* Vmmc and Vqmmc are both fixed */ - - marvell,pad-type = "fixed-1-8v"; - }; - -- For SD/SDIO with compatible "marvell,armada-3700-sdhci": - - sdhci@ab0000 { - compatible = "marvell,armada-3700-sdhci"; - reg = <0xab0000 0x1000>, - <phy_addr 0x4>; - interrupts = <GIC_SPI 55 IRQ_TYPE_LEVEL_HIGH> - vqmmc-supply = <&sd_regulator>; - /* Vmmc is fixed */ - clocks = <&sdclk>; - clock-names = "core"; - bus-width = <4>; - - marvell,pad-type = "sd"; - }; diff --git a/Documentation/devicetree/bindings/mmc/marvell,xenon-sdhci.yaml b/Documentation/devicetree/bindings/mmc/marvell,xenon-sdhci.yaml new file mode 100644 index 000000000000..c79639e9027e --- /dev/null +++ b/Documentation/devicetree/bindings/mmc/marvell,xenon-sdhci.yaml @@ -0,0 +1,275 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/mmc/marvell,xenon-sdhci.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Marvell Xenon SDHCI Controller + +description: | + This file documents differences between the core MMC properties described by + mmc-controller.yaml and the properties used by the Xenon implementation. + + Multiple SDHCs might be put into a single Xenon IP, to save size and cost. + Each SDHC is independent and owns independent resources, such as register + sets, clock and PHY. + + Each SDHC should have an independent device tree node. + +maintainers: + - Ulf Hansson <ulf.hansson@linaro.org> + +properties: + compatible: + oneOf: + - enum: + - marvell,armada-cp110-sdhci + - marvell,armada-ap806-sdhci + + - items: + - const: marvell,armada-ap807-sdhci + - const: marvell,armada-ap806-sdhci + + - items: + - const: marvell,armada-3700-sdhci + - const: marvell,sdhci-xenon + + reg: + minItems: 1 + maxItems: 2 + description: | + For "marvell,armada-3700-sdhci", two register areas. The first one + for Xenon IP register. The second one for the Armada 3700 SoC PHY PAD + Voltage Control register. Please follow the examples with compatible + "marvell,armada-3700-sdhci" in below. + Please also check property marvell,pad-type in below. + + For other compatible strings, one register area for Xenon IP. + + clocks: + minItems: 1 + maxItems: 2 + + clock-names: + minItems: 1 + items: + - const: core + - const: axi + + marvell,xenon-sdhc-id: + $ref: /schemas/types.yaml#/definitions/uint32 + minimum: 0 + maximum: 7 + description: | + Indicate the corresponding bit index of current SDHC in SDHC System + Operation Control Register Bit[7:0]. Set/clear the corresponding bit to + enable/disable current SDHC. + + marvell,xenon-phy-type: + $ref: /schemas/types.yaml#/definitions/string + enum: + - "emmc 5.1 phy" + - "emmc 5.0 phy" + description: | + Xenon support multiple types of PHYs. To select eMMC 5.1 PHY, set: + marvell,xenon-phy-type = "emmc 5.1 phy" eMMC 5.1 PHY is the default + choice if this property is not provided. To select eMMC 5.0 PHY, set: + marvell,xenon-phy-type = "emmc 5.0 phy" + + All those types of PHYs can support eMMC, SD and SDIO. Please note that + this property only presents the type of PHY. It doesn't stand for the + entire SDHC type or property. For example, "emmc 5.1 phy" doesn't mean + that this Xenon SDHC only supports eMMC 5.1. + + marvell,xenon-phy-znr: + $ref: /schemas/types.yaml#/definitions/uint32 + minimum: 0 + maximum: 0x1f + default: 0xf + description: | + Set PHY ZNR value. + Only available for eMMC PHY. + + marvell,xenon-phy-zpr: + $ref: /schemas/types.yaml#/definitions/uint32 + minimum: 0 + maximum: 0x1f + default: 0xf + description: | + Set PHY ZPR value. + Only available for eMMC PHY. + + marvell,xenon-phy-nr-success-tun: + $ref: /schemas/types.yaml#/definitions/uint32 + minimum: 1 + maximum: 7 + default: 0x4 + description: | + Set the number of required consecutive successful sampling points + used to identify a valid sampling window, in tuning process. + + marvell,xenon-phy-tun-step-divider: + $ref: /schemas/types.yaml#/definitions/uint32 + default: 64 + description: | + Set the divider for calculating TUN_STEP. + + marvell,xenon-phy-slow-mode: + type: boolean + description: | + If this property is selected, transfers will bypass PHY. + Only available when bus frequency lower than 55MHz in SDR mode. + Disabled by default. Please only try this property if timing issues + always occur with PHY enabled in eMMC HS SDR, SD SDR12, SD SDR25, + SD Default Speed and HS mode and eMMC legacy speed mode. + + marvell,xenon-tun-count: + $ref: /schemas/types.yaml#/definitions/uint32 + default: 0x9 + description: | + Xenon SDHC SoC usually doesn't provide re-tuning counter in + Capabilities Register 3 Bit[11:8]. + This property provides the re-tuning counter. + +allOf: + - $ref: mmc-controller.yaml# + - if: + properties: + compatible: + contains: + const: marvell,armada-3700-sdhci + + then: + properties: + reg: + items: + - description: Xenon IP registers + - description: Armada 3700 SoC PHY PAD Voltage Control register + minItems: 2 + + marvell,pad-type: + $ref: /schemas/types.yaml#/definitions/string + enum: + - sd + - fixed-1-8v + description: | + Type of Armada 3700 SoC PHY PAD Voltage Controller register. + If "sd" is selected, SoC PHY PAD is set as 3.3V at the beginning + and is switched to 1.8V when later in higher speed mode. + If "fixed-1-8v" is selected, SoC PHY PAD is fixed 1.8V, such as for + eMMC. + Please follow the examples with compatible + "marvell,armada-3700-sdhci" in below. + + required: + - marvell,pad-type + + - if: + properties: + compatible: + contains: + enum: + - marvell,armada-cp110-sdhci + - marvell,armada-ap807-sdhci + - marvell,armada-ap806-sdhci + + then: + properties: + clocks: + minItems: 2 + + clock-names: + items: + - const: core + - const: axi + + +required: + - compatible + - reg + - clocks + - clock-names + +unevaluatedProperties: false + +examples: + - | + // For eMMC + #include <dt-bindings/interrupt-controller/arm-gic.h> + #include <dt-bindings/interrupt-controller/irq.h> + + mmc@aa0000 { + compatible = "marvell,armada-ap807-sdhci", "marvell,armada-ap806-sdhci"; + reg = <0xaa0000 0x1000>; + interrupts = <GIC_SPI 13 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&emmc_clk 0>, <&axi_clk 0>; + clock-names = "core", "axi"; + bus-width = <4>; + marvell,xenon-phy-slow-mode; + marvell,xenon-tun-count = <11>; + non-removable; + no-sd; + no-sdio; + + /* Vmmc and Vqmmc are both fixed */ + }; + + - | + // For SD/SDIO + #include <dt-bindings/interrupt-controller/arm-gic.h> + #include <dt-bindings/interrupt-controller/irq.h> + + mmc@ab0000 { + compatible = "marvell,armada-cp110-sdhci"; + reg = <0xab0000 0x1000>; + interrupts = <GIC_SPI 55 IRQ_TYPE_LEVEL_HIGH>; + vqmmc-supply = <&sd_vqmmc_regulator>; + vmmc-supply = <&sd_vmmc_regulator>; + clocks = <&sdclk 0>, <&axi_clk 0>; + clock-names = "core", "axi"; + bus-width = <4>; + marvell,xenon-tun-count = <9>; + }; + + - | + // For eMMC with compatible "marvell,armada-3700-sdhci": + #include <dt-bindings/interrupt-controller/arm-gic.h> + #include <dt-bindings/interrupt-controller/irq.h> + + mmc@aa0000 { + compatible = "marvell,armada-3700-sdhci", "marvell,sdhci-xenon"; + reg = <0xaa0000 0x1000>, + <0x17808 0x4>; + interrupts = <GIC_SPI 13 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&emmcclk 0>; + clock-names = "core"; + bus-width = <8>; + mmc-ddr-1_8v; + mmc-hs400-1_8v; + non-removable; + no-sd; + no-sdio; + + /* Vmmc and Vqmmc are both fixed */ + + marvell,pad-type = "fixed-1-8v"; + }; + + - | + // For SD/SDIO with compatible "marvell,armada-3700-sdhci": + #include <dt-bindings/interrupt-controller/arm-gic.h> + #include <dt-bindings/interrupt-controller/irq.h> + + mmc@ab0000 { + compatible = "marvell,armada-3700-sdhci", "marvell,sdhci-xenon"; + reg = <0xab0000 0x1000>, + <0x17808 0x4>; + interrupts = <GIC_SPI 55 IRQ_TYPE_LEVEL_HIGH>; + vqmmc-supply = <&sd_regulator>; + /* Vmmc is fixed */ + clocks = <&sdclk 0>; + clock-names = "core"; + bus-width = <4>; + + marvell,pad-type = "sd"; + }; diff --git a/Documentation/devicetree/bindings/mmc/mmc-controller.yaml b/Documentation/devicetree/bindings/mmc/mmc-controller.yaml index 513f3c8758aa..ff5ce89e5111 100644 --- a/Documentation/devicetree/bindings/mmc/mmc-controller.yaml +++ b/Documentation/devicetree/bindings/mmc/mmc-controller.yaml @@ -298,7 +298,10 @@ properties: vqmmc-supply: description: - Supply for the bus IO line power + Supply for the bus IO line power, such as a level shifter. + If the level shifter is controlled by a GPIO line, this shall + be modeled as a "regulator-fixed" with a GPIO line for + switching the level shifter on/off. mmc-pwrseq: $ref: /schemas/types.yaml#/definitions/phandle diff --git a/Documentation/devicetree/bindings/mmc/mtk-sd.yaml b/Documentation/devicetree/bindings/mmc/mtk-sd.yaml index 297ada03e3de..2a2e9fa8c188 100644 --- a/Documentation/devicetree/bindings/mmc/mtk-sd.yaml +++ b/Documentation/devicetree/bindings/mmc/mtk-sd.yaml @@ -40,7 +40,10 @@ properties: - const: mediatek,mt8183-mmc reg: - maxItems: 1 + minItems: 1 + items: + - description: base register (required). + - description: top base register (required for MT8183). clocks: description: @@ -168,6 +171,16 @@ required: - vmmc-supply - vqmmc-supply +if: + properties: + compatible: + contains: + const: mediatek,mt8183-mmc +then: + properties: + reg: + minItems: 2 + unevaluatedProperties: false examples: diff --git a/Documentation/devicetree/bindings/mmc/nvidia,tegra20-sdhci.yaml b/Documentation/devicetree/bindings/mmc/nvidia,tegra20-sdhci.yaml index ce64b3498378..fe0270207622 100644 --- a/Documentation/devicetree/bindings/mmc/nvidia,tegra20-sdhci.yaml +++ b/Documentation/devicetree/bindings/mmc/nvidia,tegra20-sdhci.yaml @@ -197,25 +197,22 @@ allOf: - nvidia,tegra30-sdhci - nvidia,tegra114-sdhci - nvidia,tegra124-sdhci + then: + properties: clocks: items: - description: module clock - minItems: 1 - maxItems: 1 else: properties: clocks: items: - description: module clock - description: timeout clock - minItems: 2 - maxItems: 2 + clock-names: items: - const: sdhci - const: tmclk - minItems: 2 - maxItems: 2 required: - clock-names diff --git a/Documentation/devicetree/bindings/mmc/orion-sdio.txt b/Documentation/devicetree/bindings/mmc/orion-sdio.txt deleted file mode 100644 index 10f0818a34c5..000000000000 --- a/Documentation/devicetree/bindings/mmc/orion-sdio.txt +++ /dev/null @@ -1,16 +0,0 @@ -* Marvell orion-sdio controller - -This file documents differences between the core properties in mmc.txt -and the properties used by the orion-sdio driver. - -- compatible: Should be "marvell,orion-sdio" -- clocks: reference to the clock of the SDIO interface - -Example: - - mvsdio@d00d4000 { - compatible = "marvell,orion-sdio"; - reg = <0xd00d4000 0x200>; - interrupts = <54>; - clocks = <&gateclk 17>; - }; diff --git a/Documentation/devicetree/bindings/mmc/sdhci-am654.yaml b/Documentation/devicetree/bindings/mmc/sdhci-am654.yaml index 0566493c4def..0ab07759b472 100644 --- a/Documentation/devicetree/bindings/mmc/sdhci-am654.yaml +++ b/Documentation/devicetree/bindings/mmc/sdhci-am654.yaml @@ -186,6 +186,13 @@ properties: description: Clock Delay Buffer Select $ref: "/schemas/types.yaml#/definitions/uint32" + ti,fails-without-test-cd: + $ref: /schemas/types.yaml#/definitions/flag + description: + When present, indicates that the CD line is not connected + and the controller is required to be forced into Test mode + to set the TESTCD bit. + required: - compatible - reg diff --git a/Documentation/devicetree/bindings/mmc/sdhci-dove.txt b/Documentation/devicetree/bindings/mmc/sdhci-dove.txt deleted file mode 100644 index ae9aab9abcd7..000000000000 --- a/Documentation/devicetree/bindings/mmc/sdhci-dove.txt +++ /dev/null @@ -1,14 +0,0 @@ -* Marvell sdhci-dove controller - -This file documents differences between the core properties in mmc.txt -and the properties used by the sdhci-pxav2 and sdhci-pxav3 drivers. - -- compatible: Should be "marvell,dove-sdhci". - -Example: - -sdio0: sdio@92000 { - compatible = "marvell,dove-sdhci"; - reg = <0x92000 0x100>; - interrupts = <35>; -}; diff --git a/Documentation/devicetree/bindings/mmc/sdhci-msm.txt b/Documentation/devicetree/bindings/mmc/sdhci-msm.txt deleted file mode 100644 index 6216ed777343..000000000000 --- a/Documentation/devicetree/bindings/mmc/sdhci-msm.txt +++ /dev/null @@ -1,123 +0,0 @@ -* Qualcomm SDHCI controller (sdhci-msm) - -This file documents differences between the core properties in mmc.txt -and the properties used by the sdhci-msm driver. - -Required properties: -- compatible: Should contain a SoC-specific string and a IP version string: - version strings: - "qcom,sdhci-msm-v4" for sdcc versions less than 5.0 - "qcom,sdhci-msm-v5" for sdcc version 5.0 - For SDCC version 5.0.0, MCI registers are removed from SDCC - interface and some registers are moved to HC. New compatible - string is added to support this change - "qcom,sdhci-msm-v5". - full compatible strings with SoC and version: - "qcom,apq8084-sdhci", "qcom,sdhci-msm-v4" - "qcom,msm8226-sdhci", "qcom,sdhci-msm-v4" - "qcom,msm8953-sdhci", "qcom,sdhci-msm-v4" - "qcom,msm8974-sdhci", "qcom,sdhci-msm-v4" - "qcom,msm8916-sdhci", "qcom,sdhci-msm-v4" - "qcom,msm8992-sdhci", "qcom,sdhci-msm-v4" - "qcom,msm8994-sdhci", "qcom,sdhci-msm-v4" - "qcom,msm8996-sdhci", "qcom,sdhci-msm-v4" - "qcom,qcs404-sdhci", "qcom,sdhci-msm-v5" - "qcom,sc7180-sdhci", "qcom,sdhci-msm-v5"; - "qcom,sc7280-sdhci", "qcom,sdhci-msm-v5"; - "qcom,sdm845-sdhci", "qcom,sdhci-msm-v5" - "qcom,sdx55-sdhci", "qcom,sdhci-msm-v5"; - "qcom,sm8250-sdhci", "qcom,sdhci-msm-v5" - NOTE that some old device tree files may be floating around that only - have the string "qcom,sdhci-msm-v4" without the SoC compatible string - but doing that should be considered a deprecated practice. - -- reg: Base address and length of the register in the following order: - - Host controller register map (required) - - SD Core register map (required for controllers earlier than msm-v5) - - CQE register map (Optional, CQE support is present on SDHC instance meant - for eMMC and version v4.2 and above) - - Inline Crypto Engine register map (optional) -- reg-names: When CQE register map is supplied, below reg-names are required - - "hc" for Host controller register map - - "core" for SD core register map - - "cqhci" for CQE register map - - "ice" for Inline Crypto Engine register map (optional) -- interrupts: Should contain an interrupt-specifiers for the interrupts: - - Host controller interrupt (required) -- pinctrl-names: Should contain only one value - "default". -- pinctrl-0: Should specify pin control groups used for this controller. -- clocks: A list of phandle + clock-specifier pairs for the clocks listed in clock-names. -- clock-names: Should contain the following: - "iface" - Main peripheral bus clock (PCLK/HCLK - AHB Bus clock) (required) - "core" - SDC MMC clock (MCLK) (required) - "bus" - SDCC bus voter clock (optional) - "xo" - TCXO clock (optional) - "cal" - reference clock for RCLK delay calibration (optional) - "sleep" - sleep clock for RCLK delay calibration (optional) - "ice" - clock for Inline Crypto Engine (optional) - -- qcom,ddr-config: Certain chipsets and platforms require particular settings - for the DDR_CONFIG register. Use this field to specify the register - value as per the Hardware Programming Guide. - -- qcom,dll-config: Chipset and Platform specific value. Use this field to - specify the DLL_CONFIG register value as per Hardware Programming Guide. - -Optional Properties: -* Following bus parameters are required for interconnect bandwidth scaling: -- interconnects: Pairs of phandles and interconnect provider specifier - to denote the edge source and destination ports of - the interconnect path. - -- interconnect-names: For sdhc, we have two main paths. - 1. Data path : sdhc to ddr - 2. Config path : cpu to sdhc - For Data interconnect path the name supposed to be - is "sdhc-ddr" and for config interconnect path it is - "cpu-sdhc". - Please refer to Documentation/devicetree/bindings/ - interconnect/ for more details. - -Example: - - sdhc_1: sdhci@f9824900 { - compatible = "qcom,msm8974-sdhci", "qcom,sdhci-msm-v4"; - reg = <0xf9824900 0x11c>, <0xf9824000 0x800>; - interrupts = <0 123 0>; - bus-width = <8>; - non-removable; - - vmmc-supply = <&pm8941_l20>; - vqmmc-supply = <&pm8941_s3>; - - pinctrl-names = "default"; - pinctrl-0 = <&sdc1_clk &sdc1_cmd &sdc1_data>; - - clocks = <&gcc GCC_SDCC1_APPS_CLK>, <&gcc GCC_SDCC1_AHB_CLK>; - clock-names = "core", "iface"; - interconnects = <&qnoc MASTER_SDCC_ID &qnoc SLAVE_DDR_ID>, - <&qnoc MASTER_CPU_ID &qnoc SLAVE_SDCC_ID>; - interconnect-names = "sdhc-ddr","cpu-sdhc"; - - qcom,dll-config = <0x000f642c>; - qcom,ddr-config = <0x80040868>; - }; - - sdhc_2: sdhci@f98a4900 { - compatible = "qcom,msm8974-sdhci", "qcom,sdhci-msm-v4"; - reg = <0xf98a4900 0x11c>, <0xf98a4000 0x800>; - interrupts = <0 125 0>; - bus-width = <4>; - cd-gpios = <&msmgpio 62 0x1>; - - vmmc-supply = <&pm8941_l21>; - vqmmc-supply = <&pm8941_l13>; - - pinctrl-names = "default"; - pinctrl-0 = <&sdc2_clk &sdc2_cmd &sdc2_data>; - - clocks = <&gcc GCC_SDCC2_APPS_CLK>, <&gcc GCC_SDCC2_AHB_CLK>; - clock-names = "core", "iface"; - - qcom,dll-config = <0x0007642c>; - qcom,ddr-config = <0x80040868>; - }; diff --git a/Documentation/devicetree/bindings/mmc/sdhci-msm.yaml b/Documentation/devicetree/bindings/mmc/sdhci-msm.yaml new file mode 100644 index 000000000000..e4236334e748 --- /dev/null +++ b/Documentation/devicetree/bindings/mmc/sdhci-msm.yaml @@ -0,0 +1,194 @@ +# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) + +%YAML 1.2 +--- +$id: "http://devicetree.org/schemas/mmc/sdhci-msm.yaml#" +$schema: "http://devicetree.org/meta-schemas/core.yaml#" + +title: Qualcomm SDHCI controller (sdhci-msm) + +maintainers: + - Bhupesh Sharma <bhupesh.sharma@linaro.org> + +description: + Secure Digital Host Controller Interface (SDHCI) present on + Qualcomm SOCs supports SD/MMC/SDIO devices. + +properties: + compatible: + oneOf: + - items: + - enum: + - qcom,apq8084-sdhci + - qcom,msm8226-sdhci + - qcom,msm8953-sdhci + - qcom,msm8974-sdhci + - qcom,msm8916-sdhci + - qcom,msm8992-sdhci + - qcom,msm8994-sdhci + - qcom,msm8996-sdhci + - qcom,qcs404-sdhci + - qcom,sc7180-sdhci + - qcom,sc7280-sdhci + - qcom,sdm630-sdhci + - qcom,sdm845-sdhci + - qcom,sdx55-sdhci + - qcom,sdx65-sdhci + - qcom,sm6125-sdhci + - qcom,sm6350-sdhci + - qcom,sm8150-sdhci + - qcom,sm8250-sdhci + - enum: + - qcom,sdhci-msm-v4 # for sdcc versions less than 5.0 + - qcom,sdhci-msm-v5 # for sdcc version 5.0 + - items: + - const: qcom,sdhci-msm-v4 # Deprecated (only for backward compatibility) + # for sdcc versions less than 5.0 + + reg: + minItems: 1 + items: + - description: Host controller register map + - description: SD Core register map + - description: CQE register map + - description: Inline Crypto Engine register map + + clocks: + minItems: 3 + items: + - description: Main peripheral bus clock, PCLK/HCLK - AHB Bus clock + - description: SDC MMC clock, MCLK + - description: TCXO clock + - description: clock for Inline Crypto Engine + - description: SDCC bus voter clock + - description: reference clock for RCLK delay calibration + - description: sleep clock for RCLK delay calibration + + clock-names: + minItems: 2 + items: + - const: iface + - const: core + - const: xo + - const: ice + - const: bus + - const: cal + - const: sleep + + interrupts: + maxItems: 2 + + interrupt-names: + items: + - const: hc_irq + - const: pwr_irq + + pinctrl-names: + minItems: 1 + items: + - const: default + - const: sleep + + pinctrl-0: + description: + Should specify pin control groups used for this controller. + + qcom,ddr-config: + $ref: /schemas/types.yaml#/definitions/uint32 + description: platform specific settings for DDR_CONFIG reg. + + qcom,dll-config: + $ref: /schemas/types.yaml#/definitions/uint32 + description: platform specific settings for DLL_CONFIG reg. + + iommus: + minItems: 1 + maxItems: 8 + description: | + phandle to apps_smmu node with sid mask. + + interconnects: + items: + - description: data path, sdhc to ddr + - description: config path, cpu to sdhc + + interconnect-names: + items: + - const: sdhc-ddr + - const: cpu-sdhc + + power-domains: + description: A phandle to sdhci power domain node + maxItems: 1 + +patternProperties: + '^opp-table(-[a-z0-9]+)?$': + if: + properties: + compatible: + const: operating-points-v2 + then: + patternProperties: + '^opp-?[0-9]+$': + required: + - required-opps + +required: + - compatible + - reg + - clocks + - clock-names + - interrupts + +additionalProperties: true + +examples: + - | + #include <dt-bindings/interrupt-controller/arm-gic.h> + #include <dt-bindings/clock/qcom,gcc-sm8250.h> + #include <dt-bindings/clock/qcom,rpmh.h> + #include <dt-bindings/power/qcom-rpmpd.h> + + sdhc_2: sdhci@8804000 { + compatible = "qcom,sm8250-sdhci", "qcom,sdhci-msm-v5"; + reg = <0 0x08804000 0 0x1000>; + + interrupts = <GIC_SPI 204 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 222 IRQ_TYPE_LEVEL_HIGH>; + interrupt-names = "hc_irq", "pwr_irq"; + + clocks = <&gcc GCC_SDCC2_AHB_CLK>, + <&gcc GCC_SDCC2_APPS_CLK>, + <&rpmhcc RPMH_CXO_CLK>; + clock-names = "iface", "core", "xo"; + iommus = <&apps_smmu 0x4a0 0x0>; + qcom,dll-config = <0x0007642c>; + qcom,ddr-config = <0x80040868>; + power-domains = <&rpmhpd SM8250_CX>; + + operating-points-v2 = <&sdhc2_opp_table>; + + sdhc2_opp_table: opp-table { + compatible = "operating-points-v2"; + + opp-19200000 { + opp-hz = /bits/ 64 <19200000>; + required-opps = <&rpmhpd_opp_min_svs>; + }; + + opp-50000000 { + opp-hz = /bits/ 64 <50000000>; + required-opps = <&rpmhpd_opp_low_svs>; + }; + + opp-100000000 { + opp-hz = /bits/ 64 <100000000>; + required-opps = <&rpmhpd_opp_svs>; + }; + + opp-202000000 { + opp-hz = /bits/ 64 <202000000>; + required-opps = <&rpmhpd_opp_svs_l1>; + }; + }; + }; diff --git a/Documentation/devicetree/bindings/mmc/snps,dwcmshc-sdhci.yaml b/Documentation/devicetree/bindings/mmc/snps,dwcmshc-sdhci.yaml index f300ced4cdf3..71f8e726d641 100644 --- a/Documentation/devicetree/bindings/mmc/snps,dwcmshc-sdhci.yaml +++ b/Documentation/devicetree/bindings/mmc/snps,dwcmshc-sdhci.yaml @@ -17,6 +17,7 @@ properties: compatible: enum: - rockchip,rk3568-dwcmshc + - rockchip,rk3588-dwcmshc - snps,dwcmshc-sdhci reg: diff --git a/Documentation/devicetree/bindings/mtd/aspeed-smc.txt b/Documentation/devicetree/bindings/mtd/aspeed-smc.txt deleted file mode 100644 index 49f6528ef547..000000000000 --- a/Documentation/devicetree/bindings/mtd/aspeed-smc.txt +++ /dev/null @@ -1,51 +0,0 @@ -* Aspeed Firmware Memory controller -* Aspeed SPI Flash Memory Controller - -The Firmware Memory Controller in the Aspeed AST2500 SoC supports -three chip selects, two of which are always of SPI type and the third -can be SPI or NOR type flash. These bindings only describe SPI. - -The two SPI flash memory controllers in the AST2500 each support two -chip selects. - -Required properties: - - compatible : Should be one of - "aspeed,ast2400-fmc" for the AST2400 Firmware Memory Controller - "aspeed,ast2400-spi" for the AST2400 SPI Flash memory Controller - "aspeed,ast2500-fmc" for the AST2500 Firmware Memory Controller - "aspeed,ast2500-spi" for the AST2500 SPI flash memory controllers - - - reg : the first contains the control register location and length, - the second contains the memory window mapping address and length - - #address-cells : must be 1 corresponding to chip select child binding - - #size-cells : must be 0 corresponding to chip select child binding - -Optional properties: - - interrupts : Should contain the interrupt for the dma device if an - FMC - -The child nodes are the SPI flash modules which must have a compatible -property as specified in bindings/mtd/jedec,spi-nor.txt - -Optionally, the child node can contain properties for SPI mode (may be -ignored): - - spi-max-frequency - max frequency of spi bus - - -Example: -fmc: fmc@1e620000 { - compatible = "aspeed,ast2500-fmc"; - reg = < 0x1e620000 0x94 - 0x20000000 0x02000000 >; - #address-cells = <1>; - #size-cells = <0>; - interrupts = <19>; - flash@0 { - reg = < 0 >; - compatible = "jedec,spi-nor"; - /* spi-max-frequency = <>; */ - /* m25p,fast-read; */ - #address-cells = <1>; - #size-cells = <1>; - }; -}; diff --git a/Documentation/devicetree/bindings/mtd/elm.txt b/Documentation/devicetree/bindings/mtd/elm.txt deleted file mode 100644 index 59ddc61c1076..000000000000 --- a/Documentation/devicetree/bindings/mtd/elm.txt +++ /dev/null @@ -1,16 +0,0 @@ -Error location module - -Required properties: -- compatible: Must be "ti,am3352-elm" -- reg: physical base address and size of the registers map. -- interrupts: Interrupt number for the elm. - -Optional properties: -- ti,hwmods: Name of the hwmod associated to the elm - -Example: -elm: elm@0 { - compatible = "ti,am3352-elm"; - reg = <0x48080000 0x2000>; - interrupts = <4>; -}; diff --git a/Documentation/devicetree/bindings/mtd/gpmi-nand.yaml b/Documentation/devicetree/bindings/mtd/gpmi-nand.yaml index 9d764e654e1d..849aeae319a9 100644 --- a/Documentation/devicetree/bindings/mtd/gpmi-nand.yaml +++ b/Documentation/devicetree/bindings/mtd/gpmi-nand.yaml @@ -147,8 +147,6 @@ allOf: - description: SoC gpmi io clock - description: SoC gpmi bch apb clock clock-names: - minItems: 2 - maxItems: 2 items: - const: gpmi_io - const: gpmi_bch_apb diff --git a/Documentation/devicetree/bindings/mtd/jedec,spi-nor.yaml b/Documentation/devicetree/bindings/mtd/jedec,spi-nor.yaml index 4abfb4cfc157..7149784a36ac 100644 --- a/Documentation/devicetree/bindings/mtd/jedec,spi-nor.yaml +++ b/Documentation/devicetree/bindings/mtd/jedec,spi-nor.yaml @@ -50,10 +50,6 @@ properties: minItems: 1 maxItems: 2 - spi-max-frequency: true - spi-rx-bus-width: true - spi-tx-bus-width: true - m25p,fast-read: type: boolean description: @@ -74,8 +70,6 @@ properties: be used on such systems, to denote the absence of a reliable reset mechanism. - label: true - partitions: type: object @@ -99,8 +93,6 @@ examples: #size-cells = <0>; flash@0 { - #address-cells = <1>; - #size-cells = <1>; compatible = "spansion,m25p80", "jedec,spi-nor"; reg = <0>; spi-max-frequency = <40000000>; diff --git a/Documentation/devicetree/bindings/mtd/partitions/fixed-partitions.yaml b/Documentation/devicetree/bindings/mtd/partitions/fixed-partitions.yaml index ea4cace6a955..ad3ccd250802 100644 --- a/Documentation/devicetree/bindings/mtd/partitions/fixed-partitions.yaml +++ b/Documentation/devicetree/bindings/mtd/partitions/fixed-partitions.yaml @@ -19,7 +19,11 @@ maintainers: properties: compatible: - const: fixed-partitions + oneOf: + - const: fixed-partitions + - items: + - const: sercomm,sc-partitions + - const: fixed-partitions "#address-cells": true @@ -27,7 +31,24 @@ properties: patternProperties: "@[0-9a-f]+$": - $ref: "partition.yaml#" + allOf: + - $ref: "partition.yaml#" + - if: + properties: + compatible: + contains: + const: sercomm,sc-partitions + then: + properties: + sercomm,scpart-id: + description: Partition id in Sercomm partition map. Mtd + parser uses this id to find a record in the partition map + containing offset and size of the current partition. The + values from partition map overrides partition offset and + size defined in reg property of the dts. Frequently these + values are the same, but may differ if device has bad + eraseblocks on a flash. + $ref: /schemas/types.yaml#/definitions/uint32 required: - "#address-cells" @@ -52,6 +73,7 @@ examples: reg = <0x0100000 0x200000>; }; }; + - | partitions { compatible = "fixed-partitions"; @@ -64,6 +86,7 @@ examples: reg = <0x00000000 0x1 0x00000000>; }; }; + - | partitions { compatible = "fixed-partitions"; @@ -82,6 +105,7 @@ examples: reg = <0x2 0x00000000 0x1 0x00000000>; }; }; + - | partitions { compatible = "fixed-partitions"; @@ -119,3 +143,30 @@ examples: }; }; }; + + - | + partitions { + compatible = "sercomm,sc-partitions", "fixed-partitions"; + #address-cells = <1>; + #size-cells = <1>; + + partition@0 { + label = "u-boot"; + reg = <0x0 0x100000>; + sercomm,scpart-id = <0>; + read-only; + }; + + partition@100000 { + label = "dynamic partition map"; + reg = <0x100000 0x100000>; + sercomm,scpart-id = <1>; + }; + + partition@200000 { + label = "Factory"; + reg = <0x200000 0x100000>; + sercomm,scpart-id = <2>; + read-only; + }; + }; diff --git a/Documentation/devicetree/bindings/mtd/renesas-nandc.yaml b/Documentation/devicetree/bindings/mtd/renesas-nandc.yaml index 2870d36361c4..7b18bc5cc8b3 100644 --- a/Documentation/devicetree/bindings/mtd/renesas-nandc.yaml +++ b/Documentation/devicetree/bindings/mtd/renesas-nandc.yaml @@ -36,11 +36,15 @@ properties: - const: hclk - const: eclk + power-domains: + maxItems: 1 + required: - compatible - reg - clocks - clock-names + - power-domains - interrupts unevaluatedProperties: false @@ -56,6 +60,7 @@ examples: interrupts = <GIC_SPI 58 IRQ_TYPE_LEVEL_HIGH>; clocks = <&sysctrl R9A06G032_HCLK_NAND>, <&sysctrl R9A06G032_CLK_NAND>; clock-names = "hclk", "eclk"; + power-domains = <&sysctrl>; #address-cells = <1>; #size-cells = <0>; }; diff --git a/Documentation/devicetree/bindings/mtd/ti,elm.yaml b/Documentation/devicetree/bindings/mtd/ti,elm.yaml new file mode 100644 index 000000000000..87128c004596 --- /dev/null +++ b/Documentation/devicetree/bindings/mtd/ti,elm.yaml @@ -0,0 +1,72 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/mtd/ti,elm.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Texas Instruments Error Location Module (ELM). + +maintainers: + - Roger Quadros <rogerq@kernel.org> + +description: + ELM module is used together with GPMC and NAND Flash to detect + errors and the location of the error based on BCH algorithms + so they can be corrected if possible. + +properties: + compatible: + enum: + - ti,am3352-elm + - ti,am64-elm + + reg: + maxItems: 1 + + interrupts: + maxItems: 1 + + clocks: + maxItems: 1 + description: Functional clock. + + clock-names: + items: + - const: fck + + power-domains: + maxItems: 1 + + ti,hwmods: + description: + Name of the HWMOD associated with ELM. This is for legacy + platforms only. + $ref: /schemas/types.yaml#/definitions/string + deprecated: true + +required: + - compatible + - reg + - interrupts + +allOf: + - if: + properties: + compatible: + contains: + const: ti,am64-elm + then: + required: + - clocks + - clock-names + - power-domains + +additionalProperties: false + +examples: + - | + elm: ecc@0 { + compatible = "ti,am3352-elm"; + reg = <0x0 0x2000>; + interrupts = <4>; + }; diff --git a/Documentation/devicetree/bindings/net/can/bosch,c_can.yaml b/Documentation/devicetree/bindings/net/can/bosch,c_can.yaml index 8bad328b184d..51aa89ac7e85 100644 --- a/Documentation/devicetree/bindings/net/can/bosch,c_can.yaml +++ b/Documentation/devicetree/bindings/net/can/bosch,c_can.yaml @@ -80,8 +80,6 @@ if: then: properties: interrupts: - minItems: 4 - maxItems: 4 items: - description: Error and status IRQ - description: Message object IRQ @@ -91,7 +89,6 @@ then: else: properties: interrupts: - maxItems: 1 items: - description: Error and status IRQ diff --git a/Documentation/devicetree/bindings/net/dsa/realtek.yaml b/Documentation/devicetree/bindings/net/dsa/realtek.yaml index 8756060895a8..99ee4b5b9346 100644 --- a/Documentation/devicetree/bindings/net/dsa/realtek.yaml +++ b/Documentation/devicetree/bindings/net/dsa/realtek.yaml @@ -27,32 +27,25 @@ description: The realtek-mdio driver is an MDIO driver and it must be inserted inside an MDIO node. + The compatible string is only used to identify which (silicon) family the + switch belongs to. Roughly speaking, a family is any set of Realtek switches + whose chip identification register(s) have a common location and semantics. + The different models in a given family can be automatically disambiguated by + parsing the chip identification register(s) according to the given family, + avoiding the need for a unique compatible string for each model. + properties: compatible: enum: - realtek,rtl8365mb - - realtek,rtl8366 - realtek,rtl8366rb - - realtek,rtl8366s - - realtek,rtl8367 - - realtek,rtl8367b - - realtek,rtl8367rb - - realtek,rtl8367s - - realtek,rtl8368s - - realtek,rtl8369 - - realtek,rtl8370 description: | - realtek,rtl8365mb: 4+1 ports - realtek,rtl8366: 5+1 ports - realtek,rtl8366rb: 5+1 ports - realtek,rtl8366s: 5+1 ports - realtek,rtl8367: - realtek,rtl8367b: - realtek,rtl8367rb: 5+2 ports - realtek,rtl8367s: 5+2 ports - realtek,rtl8368s: 8 ports - realtek,rtl8369: 8+1 ports - realtek,rtl8370: 8+2 ports + realtek,rtl8365mb: + Use with models RTL8363NB, RTL8363NB-VB, RTL8363SC, RTL8363SC-VB, + RTL8364NB, RTL8364NB-VB, RTL8365MB, RTL8366SC, RTL8367RB-VB, RTL8367S, + RTL8367SB, RTL8370MB, RTL8310SR + realtek,rtl8366rb: + Use with models RTL8366RB, RTL8366S mdc-gpios: description: GPIO line for the MDC clock line. @@ -335,7 +328,7 @@ examples: #size-cells = <0>; switch@29 { - compatible = "realtek,rtl8367s"; + compatible = "realtek,rtl8365mb"; reg = <29>; reset-gpios = <&gpio2 20 GPIO_ACTIVE_LOW>; diff --git a/Documentation/devicetree/bindings/net/ethernet-controller.yaml b/Documentation/devicetree/bindings/net/ethernet-controller.yaml index 817794e56227..4f15463611f8 100644 --- a/Documentation/devicetree/bindings/net/ethernet-controller.yaml +++ b/Documentation/devicetree/bindings/net/ethernet-controller.yaml @@ -106,6 +106,12 @@ properties: phy-mode: $ref: "#/properties/phy-connection-type" + pcs-handle: + $ref: /schemas/types.yaml#/definitions/phandle + description: + Specifies a reference to a node representing a PCS PHY device on a MDIO + bus to link with an external PHY (phy-handle) if exists. + phy-handle: $ref: /schemas/types.yaml#/definitions/phandle description: diff --git a/Documentation/devicetree/bindings/net/micrel.txt b/Documentation/devicetree/bindings/net/micrel.txt index c5ab62c39133..8d157f0295a5 100644 --- a/Documentation/devicetree/bindings/net/micrel.txt +++ b/Documentation/devicetree/bindings/net/micrel.txt @@ -45,20 +45,3 @@ Optional properties: In fiber mode, auto-negotiation is disabled and the PHY can only work in 100base-fx (full and half duplex) modes. - - - lan8814,ignore-ts: If present the PHY will not support timestamping. - - This option acts as check whether Timestamping is supported by - hardware or not. LAN8814 phy support hardware tmestamping. - - - lan8814,latency_rx_10: Configures Latency value of phy in ingress at 10 Mbps. - - - lan8814,latency_tx_10: Configures Latency value of phy in egress at 10 Mbps. - - - lan8814,latency_rx_100: Configures Latency value of phy in ingress at 100 Mbps. - - - lan8814,latency_tx_100: Configures Latency value of phy in egress at 100 Mbps. - - - lan8814,latency_rx_1000: Configures Latency value of phy in ingress at 1000 Mbps. - - - lan8814,latency_tx_1000: Configures Latency value of phy in egress at 1000 Mbps. diff --git a/Documentation/devicetree/bindings/net/nfc/marvell,nci.yaml b/Documentation/devicetree/bindings/net/nfc/marvell,nci.yaml index 15a45db3899a..1bcaf6ba822c 100644 --- a/Documentation/devicetree/bindings/net/nfc/marvell,nci.yaml +++ b/Documentation/devicetree/bindings/net/nfc/marvell,nci.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Marvell International Ltd. NCI NFC controller maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/net/nfc/nxp,nci.yaml b/Documentation/devicetree/bindings/net/nfc/nxp,nci.yaml index 7465aea2e1c0..e381a3c14836 100644 --- a/Documentation/devicetree/bindings/net/nfc/nxp,nci.yaml +++ b/Documentation/devicetree/bindings/net/nfc/nxp,nci.yaml @@ -8,7 +8,7 @@ title: NXP Semiconductors NCI NFC controller maintainers: - Charles Gorand <charles.gorand@effinnov.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/net/nfc/nxp,pn532.yaml b/Documentation/devicetree/bindings/net/nfc/nxp,pn532.yaml index d8ba5a18db98..0509e0166345 100644 --- a/Documentation/devicetree/bindings/net/nfc/nxp,pn532.yaml +++ b/Documentation/devicetree/bindings/net/nfc/nxp,pn532.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: NXP Semiconductors PN532 NFC controller maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/net/nfc/nxp,pn544.yaml b/Documentation/devicetree/bindings/net/nfc/nxp,pn544.yaml index d520414de463..18b3a7d819df 100644 --- a/Documentation/devicetree/bindings/net/nfc/nxp,pn544.yaml +++ b/Documentation/devicetree/bindings/net/nfc/nxp,pn544.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: NXP Semiconductors PN544 NFC Controller maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/net/nfc/st,st-nci.yaml b/Documentation/devicetree/bindings/net/nfc/st,st-nci.yaml index a6a1bc788d29..ef1155038a2f 100644 --- a/Documentation/devicetree/bindings/net/nfc/st,st-nci.yaml +++ b/Documentation/devicetree/bindings/net/nfc/st,st-nci.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: STMicroelectronics ST NCI NFC controller maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/net/nfc/st,st21nfca.yaml b/Documentation/devicetree/bindings/net/nfc/st,st21nfca.yaml index 4356eacde8aa..8a7274357b46 100644 --- a/Documentation/devicetree/bindings/net/nfc/st,st21nfca.yaml +++ b/Documentation/devicetree/bindings/net/nfc/st,st21nfca.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: STMicroelectronics SAS ST21NFCA NFC controller maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/net/nfc/st,st95hf.yaml b/Documentation/devicetree/bindings/net/nfc/st,st95hf.yaml index d3bca376039e..963d9531a856 100644 --- a/Documentation/devicetree/bindings/net/nfc/st,st95hf.yaml +++ b/Documentation/devicetree/bindings/net/nfc/st,st95hf.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: STMicroelectronics ST95HF NFC controller maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/net/nfc/ti,trf7970a.yaml b/Documentation/devicetree/bindings/net/nfc/ti,trf7970a.yaml index 40da2ac98978..404c8df99364 100644 --- a/Documentation/devicetree/bindings/net/nfc/ti,trf7970a.yaml +++ b/Documentation/devicetree/bindings/net/nfc/ti,trf7970a.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Texas Instruments TRF7970A RFID/NFC/15693 Transceiver maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Mark Greer <mgreer@animalcreek.com> properties: diff --git a/Documentation/devicetree/bindings/net/snps,dwmac.yaml b/Documentation/devicetree/bindings/net/snps,dwmac.yaml index 2d5248f5b919..36c85eb3dc0d 100644 --- a/Documentation/devicetree/bindings/net/snps,dwmac.yaml +++ b/Documentation/devicetree/bindings/net/snps,dwmac.yaml @@ -53,20 +53,18 @@ properties: - allwinner,sun8i-r40-gmac - allwinner,sun8i-v3s-emac - allwinner,sun50i-a64-emac - - loongson,ls2k-dwmac - - loongson,ls7a-dwmac - amlogic,meson6-dwmac - amlogic,meson8b-dwmac - amlogic,meson8m2-dwmac - amlogic,meson-gxbb-dwmac - amlogic,meson-axg-dwmac - - loongson,ls2k-dwmac - - loongson,ls7a-dwmac - ingenic,jz4775-mac - ingenic,x1000-mac - ingenic,x1600-mac - ingenic,x1830-mac - ingenic,x2000-mac + - loongson,ls2k-dwmac + - loongson,ls7a-dwmac - rockchip,px30-gmac - rockchip,rk3128-gmac - rockchip,rk3228-gmac diff --git a/Documentation/devicetree/bindings/net/socionext,uniphier-ave4.yaml b/Documentation/devicetree/bindings/net/socionext,uniphier-ave4.yaml index e602761f7b14..b0ebcef6801c 100644 --- a/Documentation/devicetree/bindings/net/socionext,uniphier-ave4.yaml +++ b/Documentation/devicetree/bindings/net/socionext,uniphier-ave4.yaml @@ -13,9 +13,6 @@ description: | This describes the devicetree bindings for AVE ethernet controller implemented on Socionext UniPhier SoCs. -allOf: - - $ref: ethernet-controller.yaml# - properties: compatible: enum: @@ -44,25 +41,13 @@ properties: minItems: 1 maxItems: 4 - clock-names: - oneOf: - - items: # for Pro4 - - const: gio - - const: ether - - const: ether-gb - - const: ether-phy - - const: ether # for others + clock-names: true resets: minItems: 1 maxItems: 2 - reset-names: - oneOf: - - items: # for Pro4 - - const: gio - - const: ether - - const: ether # for others + reset-names: true socionext,syscon-phy-mode: $ref: /schemas/types.yaml#/definitions/phandle-array @@ -78,6 +63,42 @@ properties: $ref: mdio.yaml# unevaluatedProperties: false +allOf: + - $ref: ethernet-controller.yaml# + - if: + properties: + compatible: + contains: + const: socionext,uniphier-pro4-ave4 + then: + properties: + clocks: + minItems: 4 + maxItems: 4 + clock-names: + items: + - const: gio + - const: ether + - const: ether-gb + - const: ether-phy + resets: + minItems: 2 + maxItems: 2 + reset-names: + items: + - const: gio + - const: ether + else: + properties: + clocks: + maxItems: 1 + clock-names: + const: ether + resets: + maxItems: 1 + reset-names: + const: ether + required: - compatible - reg @@ -90,7 +111,7 @@ required: - reset-names - mdio -additionalProperties: false +unevaluatedProperties: false examples: - | diff --git a/Documentation/devicetree/bindings/net/ti,davinci-mdio.yaml b/Documentation/devicetree/bindings/net/ti,davinci-mdio.yaml index dbfca5ee9139..6f44f9516c36 100644 --- a/Documentation/devicetree/bindings/net/ti,davinci-mdio.yaml +++ b/Documentation/devicetree/bindings/net/ti,davinci-mdio.yaml @@ -56,6 +56,7 @@ if: compatible: contains: const: ti,davinci_mdio +then: required: - bus_freq diff --git a/Documentation/devicetree/bindings/net/xilinx_axienet.txt b/Documentation/devicetree/bindings/net/xilinx_axienet.txt index b8e4894bc634..1aa4c6006cd0 100644 --- a/Documentation/devicetree/bindings/net/xilinx_axienet.txt +++ b/Documentation/devicetree/bindings/net/xilinx_axienet.txt @@ -26,7 +26,8 @@ Required properties: specified, the TX/RX DMA interrupts should be on that node instead, and only the Ethernet core interrupt is optionally specified here. -- phy-handle : Should point to the external phy device. +- phy-handle : Should point to the external phy device if exists. Pointing + this to the PCS/PMA PHY is deprecated and should be avoided. See ethernet.txt file in the same directory. - xlnx,rxmem : Set to allocated memory buffer for Rx/Tx in the hardware @@ -68,6 +69,11 @@ Optional properties: required through the core's MDIO interface (i.e. always, unless the PHY is accessed through a different bus). + - pcs-handle: Phandle to the internal PCS/PMA PHY in SGMII or 1000Base-X + modes, where "pcs-handle" should be used to point + to the PCS/PMA PHY, and "phy-handle" should point to an + external PHY if exists. + Example: axi_ethernet_eth: ethernet@40c00000 { compatible = "xlnx,axi-ethernet-1.00.a"; diff --git a/Documentation/devicetree/bindings/pci/apple,pcie.yaml b/Documentation/devicetree/bindings/pci/apple,pcie.yaml index 7f01e15fc81c..daf602ac0d0f 100644 --- a/Documentation/devicetree/bindings/pci/apple,pcie.yaml +++ b/Documentation/devicetree/bindings/pci/apple,pcie.yaml @@ -142,7 +142,6 @@ examples: device_type = "pci"; reg = <0x0 0x0 0x0 0x0 0x0>; reset-gpios = <&pinctrl_ap 152 0>; - max-link-speed = <2>; #address-cells = <3>; #size-cells = <2>; @@ -153,7 +152,6 @@ examples: device_type = "pci"; reg = <0x800 0x0 0x0 0x0 0x0>; reset-gpios = <&pinctrl_ap 153 0>; - max-link-speed = <2>; #address-cells = <3>; #size-cells = <2>; @@ -164,7 +162,6 @@ examples: device_type = "pci"; reg = <0x1000 0x0 0x0 0x0 0x0>; reset-gpios = <&pinctrl_ap 33 0>; - max-link-speed = <1>; #address-cells = <3>; #size-cells = <2>; diff --git a/Documentation/devicetree/bindings/perf/arm,cmn.yaml b/Documentation/devicetree/bindings/perf/arm,cmn.yaml index 2d4219ec7eda..2e51072e794a 100644 --- a/Documentation/devicetree/bindings/perf/arm,cmn.yaml +++ b/Documentation/devicetree/bindings/perf/arm,cmn.yaml @@ -14,6 +14,8 @@ properties: compatible: enum: - arm,cmn-600 + - arm,cmn-650 + - arm,cmn-700 - arm,ci-700 reg: diff --git a/Documentation/devicetree/bindings/phy/brcm,sata-phy.yaml b/Documentation/devicetree/bindings/phy/brcm,sata-phy.yaml index cb1aa325336f..435b971dfd9b 100644 --- a/Documentation/devicetree/bindings/phy/brcm,sata-phy.yaml +++ b/Documentation/devicetree/bindings/phy/brcm,sata-phy.yaml @@ -102,19 +102,17 @@ if: then: properties: reg: - maxItems: 2 + minItems: 2 + reg-names: - items: - - const: "phy" - - const: "phy-ctrl" + minItems: 2 else: properties: reg: maxItems: 1 + reg-names: maxItems: 1 - items: - - const: "phy" required: - compatible diff --git a/Documentation/devicetree/bindings/phy/nvidia,tegra20-usb-phy.yaml b/Documentation/devicetree/bindings/phy/nvidia,tegra20-usb-phy.yaml index dfde0eaf66e1..d61585c96e31 100644 --- a/Documentation/devicetree/bindings/phy/nvidia,tegra20-usb-phy.yaml +++ b/Documentation/devicetree/bindings/phy/nvidia,tegra20-usb-phy.yaml @@ -275,17 +275,17 @@ allOf: - nvidia,hssquelch-level - nvidia,hsdiscon-level - else: - properties: - clocks: - maxItems: 4 + else: + properties: + clocks: + maxItems: 4 - clock-names: - items: - - const: reg - - const: pll_u - - const: timer - - const: utmi-pads + clock-names: + items: + - const: reg + - const: pll_u + - const: timer + - const: utmi-pads - if: properties: diff --git a/Documentation/devicetree/bindings/phy/qcom,usb-hs-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,usb-hs-phy.yaml index e23e5590eaa3..0655e485b260 100644 --- a/Documentation/devicetree/bindings/phy/qcom,usb-hs-phy.yaml +++ b/Documentation/devicetree/bindings/phy/qcom,usb-hs-phy.yaml @@ -14,24 +14,24 @@ if: compatible: contains: const: qcom,usb-hs-phy-apq8064 - then: - properties: - resets: - maxItems: 1 +then: + properties: + resets: + maxItems: 1 - reset-names: - const: por + reset-names: + const: por - else: - properties: - resets: - minItems: 2 - maxItems: 2 +else: + properties: + resets: + minItems: 2 + maxItems: 2 - reset-names: - items: - - const: phy - - const: por + reset-names: + items: + - const: phy + - const: por properties: compatible: @@ -92,6 +92,8 @@ additionalProperties: false examples: - | otg: usb-controller { + #reset-cells = <1>; + ulpi { phy { compatible = "qcom,usb-hs-phy-msm8974", "qcom,usb-hs-phy"; diff --git a/Documentation/devicetree/bindings/phy/samsung,dp-video-phy.yaml b/Documentation/devicetree/bindings/phy/samsung,dp-video-phy.yaml index 838c6d480ce6..b03b2f00cc5b 100644 --- a/Documentation/devicetree/bindings/phy/samsung,dp-video-phy.yaml +++ b/Documentation/devicetree/bindings/phy/samsung,dp-video-phy.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung Exynos SoC DisplayPort PHY maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Marek Szyprowski <m.szyprowski@samsung.com> - Sylwester Nawrocki <s.nawrocki@samsung.com> diff --git a/Documentation/devicetree/bindings/phy/samsung,exynos-hdmi-phy.yaml b/Documentation/devicetree/bindings/phy/samsung,exynos-hdmi-phy.yaml index c61574e10b2a..3e5f035de2e9 100644 --- a/Documentation/devicetree/bindings/phy/samsung,exynos-hdmi-phy.yaml +++ b/Documentation/devicetree/bindings/phy/samsung,exynos-hdmi-phy.yaml @@ -11,7 +11,7 @@ maintainers: - Joonyoung Shim <jy0922.shim@samsung.com> - Seung-Woo Kim <sw0312.kim@samsung.com> - Kyungmin Park <kyungmin.park@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/phy/samsung,exynos5250-sata-phy.yaml b/Documentation/devicetree/bindings/phy/samsung,exynos5250-sata-phy.yaml index 62b39bb46585..8751e559484f 100644 --- a/Documentation/devicetree/bindings/phy/samsung,exynos5250-sata-phy.yaml +++ b/Documentation/devicetree/bindings/phy/samsung,exynos5250-sata-phy.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung Exynos5250 SoC SATA PHY maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Marek Szyprowski <m.szyprowski@samsung.com> - Sylwester Nawrocki <s.nawrocki@samsung.com> diff --git a/Documentation/devicetree/bindings/phy/samsung,mipi-video-phy.yaml b/Documentation/devicetree/bindings/phy/samsung,mipi-video-phy.yaml index 54aa056b224d..415440aaad89 100644 --- a/Documentation/devicetree/bindings/phy/samsung,mipi-video-phy.yaml +++ b/Documentation/devicetree/bindings/phy/samsung,mipi-video-phy.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung S5P/Exynos SoC MIPI CSIS/DSIM DPHY maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Marek Szyprowski <m.szyprowski@samsung.com> - Sylwester Nawrocki <s.nawrocki@samsung.com> diff --git a/Documentation/devicetree/bindings/phy/samsung,usb2-phy.yaml b/Documentation/devicetree/bindings/phy/samsung,usb2-phy.yaml index 056e270a4e88..d9f22a801cbf 100644 --- a/Documentation/devicetree/bindings/phy/samsung,usb2-phy.yaml +++ b/Documentation/devicetree/bindings/phy/samsung,usb2-phy.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung S5P/Exynos SoC USB 2.0 PHY maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Marek Szyprowski <m.szyprowski@samsung.com> - Sylwester Nawrocki <s.nawrocki@samsung.com> diff --git a/Documentation/devicetree/bindings/phy/samsung,usb3-drd-phy.yaml b/Documentation/devicetree/bindings/phy/samsung,usb3-drd-phy.yaml index f83f0f8135b9..5ba55f9f20cc 100644 --- a/Documentation/devicetree/bindings/phy/samsung,usb3-drd-phy.yaml +++ b/Documentation/devicetree/bindings/phy/samsung,usb3-drd-phy.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung Exynos SoC USB 3.0 DRD PHY USB 2.0 PHY maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Marek Szyprowski <m.szyprowski@samsung.com> - Sylwester Nawrocki <s.nawrocki@samsung.com> diff --git a/Documentation/devicetree/bindings/pinctrl/aspeed,ast2600-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/aspeed,ast2600-pinctrl.yaml index 57b68d6c7c70..3666ac5b6518 100644 --- a/Documentation/devicetree/bindings/pinctrl/aspeed,ast2600-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/aspeed,ast2600-pinctrl.yaml @@ -33,7 +33,7 @@ patternProperties: $ref: "/schemas/types.yaml#/definitions/string" enum: [ ADC0, ADC1, ADC10, ADC11, ADC12, ADC13, ADC14, ADC15, ADC2, ADC3, ADC4, ADC5, ADC6, ADC7, ADC8, ADC9, BMCINT, EMMC, ESPI, ESPIALT, - FSI1, FSI2, FWSPIABR, FWSPID, FWSPIWP, GPIT0, GPIT1, GPIT2, GPIT3, + FSI1, FSI2, FWQSPI, FWSPIABR, FWSPID, FWSPIWP, GPIT0, GPIT1, GPIT2, GPIT3, GPIT4, GPIT5, GPIT6, GPIT7, GPIU0, GPIU1, GPIU2, GPIU3, GPIU4, GPIU5, GPIU6, GPIU7, I2C1, I2C10, I2C11, I2C12, I2C13, I2C14, I2C15, I2C16, I2C2, I2C3, I2C4, I2C5, I2C6, I2C7, I2C8, I2C9, I3C3, I3C4, I3C5, @@ -58,7 +58,7 @@ patternProperties: $ref: "/schemas/types.yaml#/definitions/string" enum: [ ADC0, ADC1, ADC10, ADC11, ADC12, ADC13, ADC14, ADC15, ADC2, ADC3, ADC4, ADC5, ADC6, ADC7, ADC8, ADC9, BMCINT, EMMCG1, EMMCG4, - EMMCG8, ESPI, ESPIALT, FSI1, FSI2, FWSPIABR, FWSPID, FWQSPID, FWSPIWP, + EMMCG8, ESPI, ESPIALT, FSI1, FSI2, FWQSPI, FWSPIABR, FWSPID, FWSPIWP, GPIT0, GPIT1, GPIT2, GPIT3, GPIT4, GPIT5, GPIT6, GPIT7, GPIU0, GPIU1, GPIU2, GPIU3, GPIU4, GPIU5, GPIU6, GPIU7, HVI3C3, HVI3C4, I2C1, I2C10, I2C11, I2C12, I2C13, I2C14, I2C15, I2C16, I2C2, I2C3, I2C4, I2C5, diff --git a/Documentation/devicetree/bindings/pinctrl/cirrus,madera.yaml b/Documentation/devicetree/bindings/pinctrl/cirrus,madera.yaml index 8a90d8273767..6bd42e43cdab 100644 --- a/Documentation/devicetree/bindings/pinctrl/cirrus,madera.yaml +++ b/Documentation/devicetree/bindings/pinctrl/cirrus,madera.yaml @@ -48,13 +48,12 @@ properties: Name of one pin group to configure. enum: [ aif1, aif2, aif3, aif4, mif1, mif2, mif3, pdmspk1, pdmspk2, dmic4, dmic5, dmic6, gpio1, gpio2, gpio3, - gpio4, gpio5, gpio6, gpio7, gpio7, gpio8, gpio9, + gpio4, gpio5, gpio6, gpio7, gpio8, gpio9, gpio10, gpio11, gpio12, gpio13, gpio14, gpio15, - gpio16, gpio17, gpio17, gpio18, gpio19, gpio20, - gpio21, gpio22, gpio23, gpio24, gpio25, gpio26, - gpio27, gpio27, gpio28, gpio29, gpio30, gpio31, - gpio32, gpio33, gpio34, gpio35, gpio36, gpio37, - gpio37, gpio38, gpio39 ] + gpio16, gpio17, gpio18, gpio19, gpio20, gpio21, + gpio22, gpio23, gpio24, gpio25, gpio26, gpio27, + gpio28, gpio29, gpio30, gpio31, gpio32, gpio33, + gpio34, gpio35, gpio36, gpio37, gpio38, gpio39 ] function: description: diff --git a/Documentation/devicetree/bindings/pinctrl/pincfg-node.yaml b/Documentation/devicetree/bindings/pinctrl/pincfg-node.yaml index 4b22a9e3a447..f5a121311f61 100644 --- a/Documentation/devicetree/bindings/pinctrl/pincfg-node.yaml +++ b/Documentation/devicetree/bindings/pinctrl/pincfg-node.yaml @@ -52,11 +52,19 @@ properties: hardware supporting it the pull strength in Ohm. drive-push-pull: - type: boolean + oneOf: + - type: boolean + - $ref: /schemas/types.yaml#/definitions/uint32 + enum: [ 0, 1 ] + deprecated: true description: drive actively high and low drive-open-drain: - type: boolean + oneOf: + - type: boolean + - $ref: /schemas/types.yaml#/definitions/uint32 + const: 1 # No known cases of 0 + deprecated: true description: drive with open drain drive-open-source: diff --git a/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-gpio-bank.yaml b/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-gpio-bank.yaml index f73348c54748..8cf3c47ab86b 100644 --- a/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-gpio-bank.yaml +++ b/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-gpio-bank.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung S3C/S5P/Exynos SoC pin controller - gpio bank maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Sylwester Nawrocki <s.nawrocki@samsung.com> - Tomasz Figa <tomasz.figa@gmail.com> diff --git a/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-pins-cfg.yaml b/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-pins-cfg.yaml index c71939ac8b63..9869d4dceddb 100644 --- a/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-pins-cfg.yaml +++ b/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-pins-cfg.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung S3C/S5P/Exynos SoC pin controller - pins configuration maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Sylwester Nawrocki <s.nawrocki@samsung.com> - Tomasz Figa <tomasz.figa@gmail.com> diff --git a/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml b/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml index a822f70f5702..1de91a51234d 100644 --- a/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml +++ b/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung S3C/S5P/Exynos SoC pin controller - wake-up interrupt controller maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Sylwester Nawrocki <s.nawrocki@samsung.com> - Tomasz Figa <tomasz.figa@gmail.com> diff --git a/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl.yaml index 989e48c051cf..3a65c66ca71d 100644 --- a/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung S3C/S5P/Exynos SoC pin controller maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Sylwester Nawrocki <s.nawrocki@samsung.com> - Tomasz Figa <tomasz.figa@gmail.com> diff --git a/Documentation/devicetree/bindings/power/renesas,apmu.yaml b/Documentation/devicetree/bindings/power/renesas,apmu.yaml index 4d293b2b2f84..d77fc88050c8 100644 --- a/Documentation/devicetree/bindings/power/renesas,apmu.yaml +++ b/Documentation/devicetree/bindings/power/renesas,apmu.yaml @@ -36,7 +36,8 @@ properties: cpus: $ref: /schemas/types.yaml#/definitions/phandle-array items: - maxItems: 1 + minItems: 1 + maxItems: 4 description: | Array of phandles pointing to CPU cores, which should match the order of CPU cores used by the WUPCR and PSTR registers in the Advanced Power diff --git a/Documentation/devicetree/bindings/power/supply/bq2415x.yaml b/Documentation/devicetree/bindings/power/supply/bq2415x.yaml index f8461f06e6f4..118cf484cc69 100644 --- a/Documentation/devicetree/bindings/power/supply/bq2415x.yaml +++ b/Documentation/devicetree/bindings/power/supply/bq2415x.yaml @@ -17,7 +17,6 @@ properties: compatible: enum: - ti,bq24150 - - ti,bq24150 - ti,bq24150a - ti,bq24151 - ti,bq24151a diff --git a/Documentation/devicetree/bindings/power/supply/maxim,max14577.yaml b/Documentation/devicetree/bindings/power/supply/maxim,max14577.yaml index 3978b48299de..4d3a1d09036f 100644 --- a/Documentation/devicetree/bindings/power/supply/maxim,max14577.yaml +++ b/Documentation/devicetree/bindings/power/supply/maxim,max14577.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Maxim MAX14577/MAX77836 MicroUSB and Companion Power Management IC Charger maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for Maxim MAX14577/MAX77836 MicroUSB diff --git a/Documentation/devicetree/bindings/power/supply/maxim,max77693.yaml b/Documentation/devicetree/bindings/power/supply/maxim,max77693.yaml index a21dc1a8890f..f5fd53debbc8 100644 --- a/Documentation/devicetree/bindings/power/supply/maxim,max77693.yaml +++ b/Documentation/devicetree/bindings/power/supply/maxim,max77693.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Maxim MAX77693 MicroUSB and Companion Power Management IC Charger maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for Maxim MAX77693 MicroUSB Integrated diff --git a/Documentation/devicetree/bindings/powerpc/fsl/l2cache.txt b/Documentation/devicetree/bindings/powerpc/fsl/l2cache.txt index 8a70696395a7..22ad012660e9 100644 --- a/Documentation/devicetree/bindings/powerpc/fsl/l2cache.txt +++ b/Documentation/devicetree/bindings/powerpc/fsl/l2cache.txt @@ -6,12 +6,6 @@ The cache bindings explained below are Devicetree Specification compliant Required Properties: - compatible : Should include one of the following: - "fsl,8540-l2-cache-controller" - "fsl,8541-l2-cache-controller" - "fsl,8544-l2-cache-controller" - "fsl,8548-l2-cache-controller" - "fsl,8555-l2-cache-controller" - "fsl,8568-l2-cache-controller" "fsl,b4420-l2-cache-controller" "fsl,b4860-l2-cache-controller" "fsl,bsc9131-l2-cache-controller" diff --git a/Documentation/devicetree/bindings/regulator/fixed-regulator.yaml b/Documentation/devicetree/bindings/regulator/fixed-regulator.yaml index 9b131c6facbc..84eeaef179a5 100644 --- a/Documentation/devicetree/bindings/regulator/fixed-regulator.yaml +++ b/Documentation/devicetree/bindings/regulator/fixed-regulator.yaml @@ -18,23 +18,23 @@ description: allOf: - $ref: "regulator.yaml#" - -if: - properties: - compatible: - contains: - const: regulator-fixed-clock - required: - - clocks -else: - if: - properties: - compatible: - contains: - const: regulator-fixed-domain - required: - - power-domains - - required-opps + - if: + properties: + compatible: + contains: + const: regulator-fixed-clock + then: + required: + - clocks + - if: + properties: + compatible: + contains: + const: regulator-fixed-domain + then: + required: + - power-domains + - required-opps properties: compatible: diff --git a/Documentation/devicetree/bindings/regulator/maxim,max14577.yaml b/Documentation/devicetree/bindings/regulator/maxim,max14577.yaml index 16f01886a601..285dc7122977 100644 --- a/Documentation/devicetree/bindings/regulator/maxim,max14577.yaml +++ b/Documentation/devicetree/bindings/regulator/maxim,max14577.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Maxim MAX14577/MAX77836 MicroUSB and Companion Power Management IC regulators maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for Maxim MAX14577/MAX77836 MicroUSB diff --git a/Documentation/devicetree/bindings/regulator/maxim,max77686.yaml b/Documentation/devicetree/bindings/regulator/maxim,max77686.yaml index bb64b679f765..0e7cd4b3ace0 100644 --- a/Documentation/devicetree/bindings/regulator/maxim,max77686.yaml +++ b/Documentation/devicetree/bindings/regulator/maxim,max77686.yaml @@ -8,7 +8,7 @@ title: Maxim MAX77686 Power Management IC regulators maintainers: - Chanwoo Choi <cw00.choi@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for Maxim MAX77686 Power Management diff --git a/Documentation/devicetree/bindings/regulator/maxim,max77693.yaml b/Documentation/devicetree/bindings/regulator/maxim,max77693.yaml index 20d8559bdc2b..945a539749e8 100644 --- a/Documentation/devicetree/bindings/regulator/maxim,max77693.yaml +++ b/Documentation/devicetree/bindings/regulator/maxim,max77693.yaml @@ -8,7 +8,7 @@ title: Maxim MAX77693 MicroUSB and Companion Power Management IC regulators maintainers: - Chanwoo Choi <cw00.choi@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for Maxim MAX77693 MicroUSB Integrated diff --git a/Documentation/devicetree/bindings/regulator/maxim,max77802.yaml b/Documentation/devicetree/bindings/regulator/maxim,max77802.yaml index f2b4dd15a0f3..236348c4710c 100644 --- a/Documentation/devicetree/bindings/regulator/maxim,max77802.yaml +++ b/Documentation/devicetree/bindings/regulator/maxim,max77802.yaml @@ -8,7 +8,7 @@ title: Maxim MAX77802 Power Management IC regulators maintainers: - Javier Martinez Canillas <javier@dowhile0.org> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for Maxim MAX77802 Power Management diff --git a/Documentation/devicetree/bindings/regulator/maxim,max77843.yaml b/Documentation/devicetree/bindings/regulator/maxim,max77843.yaml index a963025e96c1..9695e7242882 100644 --- a/Documentation/devicetree/bindings/regulator/maxim,max77843.yaml +++ b/Documentation/devicetree/bindings/regulator/maxim,max77843.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Maxim MAX77843 MicroUSB and Companion Power Management IC regulators maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for Maxim MAX77843 MicroUSB Integrated diff --git a/Documentation/devicetree/bindings/regulator/maxim,max8952.yaml b/Documentation/devicetree/bindings/regulator/maxim,max8952.yaml index e4e8c58f6046..3ff0d7d980e9 100644 --- a/Documentation/devicetree/bindings/regulator/maxim,max8952.yaml +++ b/Documentation/devicetree/bindings/regulator/maxim,max8952.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Maxim MAX8952 voltage regulator maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> allOf: - $ref: regulator.yaml# diff --git a/Documentation/devicetree/bindings/regulator/maxim,max8973.yaml b/Documentation/devicetree/bindings/regulator/maxim,max8973.yaml index 5898dcf10f06..b92eef68c19f 100644 --- a/Documentation/devicetree/bindings/regulator/maxim,max8973.yaml +++ b/Documentation/devicetree/bindings/regulator/maxim,max8973.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Maxim MAX8973/MAX77621 voltage regulator maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> allOf: - $ref: regulator.yaml# diff --git a/Documentation/devicetree/bindings/regulator/maxim,max8997.yaml b/Documentation/devicetree/bindings/regulator/maxim,max8997.yaml index d5a44ca3df04..4321f061a7f6 100644 --- a/Documentation/devicetree/bindings/regulator/maxim,max8997.yaml +++ b/Documentation/devicetree/bindings/regulator/maxim,max8997.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Maxim MAX8997 Power Management IC maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | The Maxim MAX8997 is a Power Management IC which includes voltage and current diff --git a/Documentation/devicetree/bindings/regulator/mt6315-regulator.yaml b/Documentation/devicetree/bindings/regulator/mt6315-regulator.yaml index 61dd5af80db6..5d2d989de893 100644 --- a/Documentation/devicetree/bindings/regulator/mt6315-regulator.yaml +++ b/Documentation/devicetree/bindings/regulator/mt6315-regulator.yaml @@ -31,7 +31,7 @@ properties: $ref: "regulator.yaml#" properties: - regulator-name: + regulator-compatible: pattern: "^vbuck[1-4]$" additionalProperties: false diff --git a/Documentation/devicetree/bindings/regulator/mt6358-regulator.txt b/Documentation/devicetree/bindings/regulator/mt6358-regulator.txt index 9a90a92f2d7e..7034cdca54e0 100644 --- a/Documentation/devicetree/bindings/regulator/mt6358-regulator.txt +++ b/Documentation/devicetree/bindings/regulator/mt6358-regulator.txt @@ -8,14 +8,14 @@ Documentation/devicetree/bindings/regulator/regulator.txt. The valid names for regulators are:: BUCK: - buck_vdram1, buck_vcore, buck_vpa, buck_vproc11, buck_vproc12, buck_vgpu, - buck_vs2, buck_vmodem, buck_vs1 + buck_vdram1, buck_vcore, buck_vcore_sshub, buck_vpa, buck_vproc11, + buck_vproc12, buck_vgpu, buck_vs2, buck_vmodem, buck_vs1 LDO: ldo_vdram2, ldo_vsim1, ldo_vibr, ldo_vrf12, ldo_vio18, ldo_vusb, ldo_vcamio, ldo_vcamd, ldo_vcn18, ldo_vfe28, ldo_vsram_proc11, ldo_vcn28, ldo_vsram_others, - ldo_vsram_gpu, ldo_vxo22, ldo_vefuse, ldo_vaux18, ldo_vmch, ldo_vbif28, - ldo_vsram_proc12, ldo_vcama1, ldo_vemc, ldo_vio28, ldo_va12, ldo_vrf18, - ldo_vcn33_bt, ldo_vcn33_wifi, ldo_vcama2, ldo_vmc, ldo_vldo28, ldo_vaud28, + ldo_vsram_others_sshub, ldo_vsram_gpu, ldo_vxo22, ldo_vefuse, ldo_vaux18, + ldo_vmch, ldo_vbif28, ldo_vsram_proc12, ldo_vcama1, ldo_vemc, ldo_vio28, ldo_va12, + ldo_vrf18, ldo_vcn33_bt, ldo_vcn33_wifi, ldo_vcama2, ldo_vmc, ldo_vldo28, ldo_vaud28, ldo_vsim2 Example: @@ -354,5 +354,17 @@ Example: regulator-max-microvolt = <3100000>; regulator-enable-ramp-delay = <540>; }; + + mt6358_vcore_sshub_reg: buck_vcore_sshub { + regulator-name = "vcore_sshub"; + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <1293750>; + }; + + mt6358_vsram_others_sshub_reg: ldo_vsram_others_sshub { + regulator-name = "vsram_others_sshub"; + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <1293750>; + }; }; }; diff --git a/Documentation/devicetree/bindings/regulator/nxp,pca9450-regulator.yaml b/Documentation/devicetree/bindings/regulator/nxp,pca9450-regulator.yaml index f70f2e758a00..b539781e39aa 100644 --- a/Documentation/devicetree/bindings/regulator/nxp,pca9450-regulator.yaml +++ b/Documentation/devicetree/bindings/regulator/nxp,pca9450-regulator.yaml @@ -92,6 +92,17 @@ properties: LDO5CTRL_L or LDO5CTRL_H register. Use this if the SD_VSEL signal is connected to a host GPIO. + nxp,i2c-lt-enable: + type: boolean + description: + Indicates that the I2C Level Translator is used. + + nxp,wdog_b-warm-reset: + type: boolean + description: + When WDOG_B signal is asserted a warm reset will be done instead of cold + reset. + required: - compatible - reg diff --git a/Documentation/devicetree/bindings/regulator/qcom,rpmh-regulator.yaml b/Documentation/devicetree/bindings/regulator/qcom,rpmh-regulator.yaml index e28ee9e46788..9a36bee750af 100644 --- a/Documentation/devicetree/bindings/regulator/qcom,rpmh-regulator.yaml +++ b/Documentation/devicetree/bindings/regulator/qcom,rpmh-regulator.yaml @@ -7,7 +7,8 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Qualcomm Technologies, Inc. RPMh Regulators maintainers: - - David Collins <collinsd@codeaurora.org> + - Bjorn Andersson <bjorn.andersson@linaro.org> + - Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> description: | rpmh-regulator devices support PMIC regulator management via the Voltage @@ -78,7 +79,7 @@ properties: RPMh resource name suffix used for the regulators found on this PMIC. $ref: /schemas/types.yaml#/definitions/string - enum: [a, b, c, d, e, f] + enum: [a, b, c, d, e, f, h, k] qcom,always-wait-for-ack: description: | @@ -94,35 +95,264 @@ properties: vdd-rgb-supply: description: Input supply phandle of rgb. - vin-lvs-1-2-supply: - description: Input supply phandle of one or more regulators. - - vdd-bob-supply: - description: BOB regulator parent supply phandle. - bob: type: object $ref: "regulator.yaml#" description: BOB regulator node. patternProperties: - "^vdd-s([0-9]+)-supply$": - description: Input supply phandle(s) of one or more regulators. - - "^vdd-(l[0-9]+[-]){1,5}supply$": - description: Input supply phandle(s) of one or more regulators. - "^(smps|ldo|lvs)[0-9]+$": type: object $ref: "regulator.yaml#" description: smps/ldo regulator nodes(s). -additionalProperties: false - required: - compatible - qcom,pmic-id +allOf: + - if: + properties: + compatible: + enum: + - qcom,pm6150-rpmh-regulators + then: + properties: + vdd-l2-l3-supply: true + vdd-l4-l7-l8-supply: true + vdd-l5-l16-l17-l18-l19-supply: true + vdd-l10-l14-l15-supply: true + vdd-l11-l12-l13-supply: true + patternProperties: + "^vdd-l[169]-supply$": true + "^vdd-s[1-5]-supply$": true + + - if: + properties: + compatible: + enum: + - qcom,pm6150l-rpmh-regulators + then: + properties: + vdd-bob-supply: + description: BOB regulator parent supply phandle. + vdd-l1-l8-supply: true + vdd-l2-l3-supply: true + vdd-l4-l5-l6-supply: true + vdd-l7-l11-supply: true + vdd-l9-l10-supply: true + patternProperties: + "^vdd-s[1-8]-supply$": true + + - if: + properties: + compatible: + enum: + - qcom,pm7325-rpmh-regulators + then: + properties: + vdd-l1-l4-l12-l15-supply: true + vdd-l2-l7-supply: true + vdd-l6-l9-l10-supply: true + vdd-l11-l17-l18-l19-supply: true + vdd-l13-supply: true + vdd-l14-l16-supply: true + patternProperties: + "^vdd-l[358]-supply$": true + "^vdd-s[1-8]-supply$": true + + - if: + properties: + compatible: + enum: + - qcom,pm8005-rpmh-regulators + then: + patternProperties: + "^vdd-s[1-4]-supply$": true + + - if: + properties: + compatible: + enum: + - qcom,pm8009-rpmh-regulators + - qcom,pm8009-1-rpmh-regulators + then: + properties: + vdd-l5-l6-supply: true + patternProperties: + "^vdd-l[1-47]-supply$": true + "^vdd-s[1-2]-supply$": true + + - if: + properties: + compatible: + enum: + - qcom,pm8150-rpmh-regulators + - qcom,pmm8155au-rpmh-regulators + then: + properties: + vdd-l1-l8-l11-supply: true + vdd-l2-l10-supply: true + vdd-l3-l4-l5-l18-supply: true + vdd-l6-l9-supply: true + vdd-l7-l12-l14-l15-supply: true + vdd-l13-l16-l17-supply: true + patternProperties: + "^vdd-s([1-9]|10)-supply$": true + + - if: + properties: + compatible: + enum: + - qcom,pm8150l-rpmh-regulators + then: + properties: + vdd-bob-supply: + description: BOB regulator parent supply phandle. + vdd-l1-l8-supply: true + vdd-l2-l3-supply: true + vdd-l4-l5-l6-supply: true + vdd-l7-l11-supply: true + vdd-l9-l10-supply: true + patternProperties: + "^vdd-s[1-8]-supply$": true + + - if: + properties: + compatible: + enum: + - qcom,pm8350-rpmh-regulators + then: + properties: + vdd-l1-l4-supply: true + vdd-l2-l7-supply: true + vdd-l3-l5-supply: true + vdd-l6-l9-l10-supply: true + vdd-l8-supply: true + patternProperties: + "^vdd-s([1-9]|1[0-2])-supply$": true + + - if: + properties: + compatible: + enum: + - qcom,pm8350c-rpmh-regulators + then: + properties: + vdd-bob-supply: + description: BOB regulator parent supply phandle. + vdd-l1-l12-supply: true + vdd-l2-l8-supply: true + vdd-l3-l4-l5-l7-l13-supply: true + vdd-l6-l9-l11-supply: true + vdd-l10-supply: true + patternProperties: + "^vdd-s([1-9]|10)-supply$": true + + - if: + properties: + compatible: + enum: + - qcom,pm8450-rpmh-regulators + then: + patternProperties: + "^vdd-l[1-4]-supply$": true + "^vdd-s[1-6]-supply$": true + + - if: + properties: + compatible: + enum: + - qcom,pm8998-rpmh-regulators + then: + properties: + vdd-l1-l27-supply: true + vdd-l2-l8-l17-supply: true + vdd-l3-l11-supply: true + vdd-l4-l5-supply: true + vdd-l6-supply: true + vdd-l7-l12-l14-l15-supply: true + vdd-l9-supply: true + vdd-l10-l23-l25-supply: true + vdd-l13-l19-l21-supply: true + vdd-l16-l28-supply: true + vdd-l18-l22-supply: true + vdd-l20-l24-supply: true + vdd-l26-supply: true + vin-lvs-1-2-supply: true + patternProperties: + "^vdd-s([1-9]|1[0-3])-supply$": true + + - if: + properties: + compatible: + enum: + - qcom,pmg1110-rpmh-regulators + then: + properties: + vdd-s1-supply: true + + - if: + properties: + compatible: + enum: + - qcom,pmi8998-rpmh-regulators + then: + properties: + vdd-bob-supply: + description: BOB regulator parent supply phandle. + + - if: + properties: + compatible: + enum: + - qcom,pmr735a-rpmh-regulators + then: + properties: + vdd-l1-l2-supply: true + vdd-l3-supply: true + vdd-l4-supply: true + vdd-l5-l6-supply: true + vdd-l7-bob-supply: true + patternProperties: + "^vdd-s[1-3]-supply$": true + + - if: + properties: + compatible: + enum: + - qcom,pmx55-rpmh-regulators + then: + properties: + vdd-l1-l2-supply: true + vdd-l3-l9-supply: true + vdd-l4-l12-supply: true + vdd-l5-l6-supply: true + vdd-l7-l8-supply: true + vdd-l10-l11-l13-supply: true + patternProperties: + "^vdd-l1[4-6]-supply$": true + "^vdd-s[1-7]-supply$": true + + - if: + properties: + compatible: + enum: + - qcom,pmx65-rpmh-regulators + then: + properties: + vdd-l2-l18-supply: true + vdd-l5-l6-l16-supply: true + vdd-l8-l9-supply: true + vdd-l11-l13-supply: true + patternProperties: + "^vdd-l[1347]-supply$": true + "^vdd-l1[0245789]-supply$": true + "^vdd-l2[01]-supply$": true + "^vdd-s[1-8]-supply$": true + +unevaluatedProperties: false + examples: - | #include <dt-bindings/regulator/qcom,rpmh-regulator.h> diff --git a/Documentation/devicetree/bindings/regulator/richtek,rt4801-regulator.yaml b/Documentation/devicetree/bindings/regulator/richtek,rt4801-regulator.yaml index 235e593b3b2c..091150c4e579 100644 --- a/Documentation/devicetree/bindings/regulator/richtek,rt4801-regulator.yaml +++ b/Documentation/devicetree/bindings/regulator/richtek,rt4801-regulator.yaml @@ -17,9 +17,6 @@ description: | Datasheet is available at https://www.richtek.com/assets/product_file/RT4801H/DS4801H-00.pdf -#The valid names for RT4801 regulator nodes are: -#DSVP, DSVN - properties: compatible: enum: @@ -33,10 +30,13 @@ properties: The first one is ENP to enable DSVP, and second one is ENM to enable DSVN. Number of GPIO in the array list could be 1 or 2. If only one gpio is specified, only one gpio used to control ENP/ENM. - Else both are spefied, DSVP/DSVN could be controlled individually. - Othersie, this property not specified. treat both as always-on regulator. + Else if both are specified, DSVP/DSVN could be controlled individually. + If this property not specified, treat both as always-on regulators. + + Property is deprecated. Use enable-gpios in each regulator. minItems: 1 maxItems: 2 + deprecated: true patternProperties: "^DSV(P|N)$": @@ -45,6 +45,14 @@ patternProperties: description: Properties for single display bias regulator. + properties: + enable-gpios: + description: + GPIO to use to enable DSVP/DSVN regulator. One GPIO can be configured + for controlling both regulators. If this property not specified for + any regulator, treat both as always-on regulators. + maxItems: 1 + required: - compatible - reg @@ -60,19 +68,20 @@ examples: rt4801@73 { compatible = "richtek,rt4801"; reg = <0x73>; - enable-gpios = <&gpio26 2 0>, <&gpio26 3 0>; dsvp: DSVP { regulator-name = "rt4801,dsvp"; regulator-min-microvolt = <4000000>; regulator-max-microvolt = <6000000>; regulator-boot-on; + enable-gpios = <&gpio26 2 0>; }; dsvn: DSVN { regulator-name = "rt4801,dsvn"; regulator-min-microvolt = <4000000>; regulator-max-microvolt = <6000000>; regulator-boot-on; + enable-gpios = <&gpio26 3 0>; }; }; diff --git a/Documentation/devicetree/bindings/regulator/richtek,rt5190a-regulator.yaml b/Documentation/devicetree/bindings/regulator/richtek,rt5190a-regulator.yaml index 28725c5467fc..edb411be0390 100644 --- a/Documentation/devicetree/bindings/regulator/richtek,rt5190a-regulator.yaml +++ b/Documentation/devicetree/bindings/regulator/richtek,rt5190a-regulator.yaml @@ -58,7 +58,7 @@ properties: type: object $ref: regulator.yaml# description: | - regulator description for buck1 and buck4. + regulator description for buck1 to buck4, and ldo. properties: regulator-allowed-modes: diff --git a/Documentation/devicetree/bindings/regulator/richtek,rt5759-regulator.yaml b/Documentation/devicetree/bindings/regulator/richtek,rt5759-regulator.yaml new file mode 100644 index 000000000000..0a4c9576a432 --- /dev/null +++ b/Documentation/devicetree/bindings/regulator/richtek,rt5759-regulator.yaml @@ -0,0 +1,90 @@ +# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/regulator/richtek,rt5759-regulator.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Richtek RT5759 High Performance DCDC Converter + +maintainers: + - ChiYuan Huang <cy_huang@richtek.com> + +description: | + The RT5759 is a high-performance, synchronous step-down DC-DC converter that + can deliver up to 9A output current from 3V to 6.5V input supply, The output + voltage can be programmable with I2C controlled 7-Bit VID. + + Datasheet is available at + https://www.richtek.com/assets/product_file/RT5759/DS5759-00.pdf + +properties: + compatible: + enum: + - richtek,rt5759 + - richtek,rt5759a + + reg: + maxItems: 1 + + regulator-allowed-modes: + description: | + buck allowed operating mode + 0: auto mode (PSKIP: pulse skipping) + 1: force pwm mode + items: + enum: [0, 1] + + richtek,watchdog-enable: + description: enable the external watchdog reset pin listening + type: boolean + +allOf: + - $ref: regulator.yaml# + + - if: + properties: + compatible: + contains: + const: richtek,rt5759 + then: + properties: + richtek,watchdog-enable: false + +required: + - compatible + - reg + +unevaluatedProperties: false + +examples: + # example 1 for RT5759 + - | + i2c { + #address-cells = <1>; + #size-cells = <0>; + + regulator@62 { + compatible = "richtek,rt5759"; + reg = <0x62>; + regulator-name = "rt5759-buck"; + regulator-min-microvolt = <600000>; + regulator-max-microvolt = <1500000>; + regulator-boot-on; + }; + }; + # example 2 for RT5759A + - | + i2c { + #address-cells = <1>; + #size-cells = <0>; + + regulator@62 { + compatible = "richtek,rt5759a"; + reg = <0x62>; + regulator-name = "rt5759a-buck"; + regulator-min-microvolt = <600000>; + regulator-max-microvolt = <1725000>; + regulator-boot-on; + richtek,watchdog-enable; + }; + }; diff --git a/Documentation/devicetree/bindings/regulator/samsung,s2mpa01.yaml b/Documentation/devicetree/bindings/regulator/samsung,s2mpa01.yaml index 0627dec513da..0f9eb317ba9a 100644 --- a/Documentation/devicetree/bindings/regulator/samsung,s2mpa01.yaml +++ b/Documentation/devicetree/bindings/regulator/samsung,s2mpa01.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung S2MPA01 Power Management IC regulators maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for S2M and S5M family of Power diff --git a/Documentation/devicetree/bindings/regulator/samsung,s2mps11.yaml b/Documentation/devicetree/bindings/regulator/samsung,s2mps11.yaml index e3b780715f44..f1c50dcd0b04 100644 --- a/Documentation/devicetree/bindings/regulator/samsung,s2mps11.yaml +++ b/Documentation/devicetree/bindings/regulator/samsung,s2mps11.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung S2MPS11 Power Management IC regulators maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for S2M and S5M family of Power diff --git a/Documentation/devicetree/bindings/regulator/samsung,s2mps13.yaml b/Documentation/devicetree/bindings/regulator/samsung,s2mps13.yaml index 579d77aefc3f..53b105a4ead1 100644 --- a/Documentation/devicetree/bindings/regulator/samsung,s2mps13.yaml +++ b/Documentation/devicetree/bindings/regulator/samsung,s2mps13.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung S2MPS13 Power Management IC regulators maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for S2M and S5M family of Power diff --git a/Documentation/devicetree/bindings/regulator/samsung,s2mps14.yaml b/Documentation/devicetree/bindings/regulator/samsung,s2mps14.yaml index fdea290b3e94..01f9d4e236e9 100644 --- a/Documentation/devicetree/bindings/regulator/samsung,s2mps14.yaml +++ b/Documentation/devicetree/bindings/regulator/samsung,s2mps14.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung S2MPS14 Power Management IC regulators maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for S2M and S5M family of Power diff --git a/Documentation/devicetree/bindings/regulator/samsung,s2mps15.yaml b/Documentation/devicetree/bindings/regulator/samsung,s2mps15.yaml index b3a883c94628..9576c2df45a6 100644 --- a/Documentation/devicetree/bindings/regulator/samsung,s2mps15.yaml +++ b/Documentation/devicetree/bindings/regulator/samsung,s2mps15.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung S2MPS15 Power Management IC regulators maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for S2M and S5M family of Power diff --git a/Documentation/devicetree/bindings/regulator/samsung,s2mpu02.yaml b/Documentation/devicetree/bindings/regulator/samsung,s2mpu02.yaml index 0ded6953e3b6..39b652c3c3c4 100644 --- a/Documentation/devicetree/bindings/regulator/samsung,s2mpu02.yaml +++ b/Documentation/devicetree/bindings/regulator/samsung,s2mpu02.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung S2MPU02 Power Management IC regulators maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for S2M and S5M family of Power diff --git a/Documentation/devicetree/bindings/regulator/samsung,s5m8767.yaml b/Documentation/devicetree/bindings/regulator/samsung,s5m8767.yaml index 3c1617b66861..172631ca3c25 100644 --- a/Documentation/devicetree/bindings/regulator/samsung,s5m8767.yaml +++ b/Documentation/devicetree/bindings/regulator/samsung,s5m8767.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung S5M8767 Power Management IC regulators maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for S2M and S5M family of Power diff --git a/Documentation/devicetree/bindings/regulator/siliconmitus,sm5703-regulator.yaml b/Documentation/devicetree/bindings/regulator/siliconmitus,sm5703-regulator.yaml new file mode 100644 index 000000000000..9d84117530ca --- /dev/null +++ b/Documentation/devicetree/bindings/regulator/siliconmitus,sm5703-regulator.yaml @@ -0,0 +1,49 @@ +# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/regulator/siliconmitus,sm5703-regulator.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Silicon Mitus SM5703 multi function device regulators + +maintainers: + - Markuss Broks <markuss.broks@gmail.com> + +description: | + SM5703 regulators node should be a sub node of the SM5703 MFD node. See SM5703 MFD + bindings at Documentation/devicetree/bindings/mfd/siliconmitus,sm5703.yaml + Regulator nodes should be named as USBLDO_<number>, BUCK, VBUS, LDO_<number>. + The definition for each of these nodes is defined using the standard + binding for regulators at Documentation/devicetree/bindings/regulator/regulator.txt. + +properties: + buck: + type: object + $ref: regulator.yaml# + unevaluatedProperties: false + description: + Properties for the BUCK regulator. + + vbus: + type: object + $ref: regulator.yaml# + unevaluatedProperties: false + description: + Properties for the VBUS regulator. + +patternProperties: + "^ldo[1-3]$": + type: object + $ref: regulator.yaml# + unevaluatedProperties: false + description: + Properties for single LDO regulator. + + "^usbldo[1-2]$": + type: object + $ref: regulator.yaml# + unevaluatedProperties: false + description: + Properties for a single USBLDO regulator. + +additionalProperties: false diff --git a/Documentation/devicetree/bindings/regulator/socionext,uniphier-regulator.yaml b/Documentation/devicetree/bindings/regulator/socionext,uniphier-regulator.yaml index 1218f21ba320..75087c6e001c 100644 --- a/Documentation/devicetree/bindings/regulator/socionext,uniphier-regulator.yaml +++ b/Documentation/devicetree/bindings/regulator/socionext,uniphier-regulator.yaml @@ -14,9 +14,6 @@ description: | maintainers: - Kunihiko Hayashi <hayashi.kunihiko@socionext.com> -allOf: - - $ref: "regulator.yaml#" - # USB3 Controller properties: @@ -36,27 +33,51 @@ properties: minItems: 1 maxItems: 2 - clock-names: - oneOf: - - items: # for Pro4, Pro5 - - const: gio - - const: link - - items: # for others - - const: link + clock-names: true resets: minItems: 1 maxItems: 2 - reset-names: - oneOf: - - items: # for Pro4, Pro5 - - const: gio - - const: link - - items: - - const: link + reset-names: true -additionalProperties: false +allOf: + - $ref: "regulator.yaml#" + - if: + properties: + compatible: + contains: + enum: + - socionext,uniphier-pro4-usb3-regulator + - socionext,uniphier-pro5-usb3-regulator + then: + properties: + clocks: + minItems: 2 + maxItems: 2 + clock-names: + items: + - const: gio + - const: link + resets: + minItems: 2 + maxItems: 2 + reset-names: + items: + - const: gio + - const: link + else: + properties: + clocks: + maxItems: 1 + clock-names: + const: link + resets: + maxItems: 1 + reset-names: + const: link + +unevaluatedProperties: false required: - compatible diff --git a/Documentation/devicetree/bindings/remoteproc/qcom,sc7280-wpss-pil.yaml b/Documentation/devicetree/bindings/remoteproc/qcom,sc7280-wpss-pil.yaml index 2424de733ee4..d99a729d2710 100644 --- a/Documentation/devicetree/bindings/remoteproc/qcom,sc7280-wpss-pil.yaml +++ b/Documentation/devicetree/bindings/remoteproc/qcom,sc7280-wpss-pil.yaml @@ -104,8 +104,7 @@ properties: qcom,smem-state-names: $ref: /schemas/types.yaml#/definitions/string description: The names of the state bits used for SMP2P output - items: - - const: stop + const: stop glink-edge: type: object @@ -130,7 +129,6 @@ properties: qcom,remote-pid: $ref: /schemas/types.yaml#/definitions/uint32 description: ID of the shared memory used by GLINK for communication with WPSS - maxItems: 1 required: - interrupts diff --git a/Documentation/devicetree/bindings/reserved-memory/phram.yaml b/Documentation/devicetree/bindings/reserved-memory/phram.yaml new file mode 100644 index 000000000000..6c4db28015f1 --- /dev/null +++ b/Documentation/devicetree/bindings/reserved-memory/phram.yaml @@ -0,0 +1,47 @@ +# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/reserved-memory/phram.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: MTD/block device in RAM + +description: | + Specifies that the reserved memory region can be used as an MTD or block + device. + + The "phram" node is named after the "MTD in PHysical RAM" driver which + provides an implementation of this functionality in Linux. + +maintainers: + - Vincent Whitchurch <vincent.whitchurch@axis.com> + +allOf: + - $ref: "reserved-memory.yaml" + - $ref: "/schemas/mtd/mtd.yaml" + +properties: + compatible: + const: phram + + reg: + description: region of memory that can be used as an MTD/block device + +required: + - compatible + - reg + +unevaluatedProperties: false + +examples: + - | + reserved-memory { + #address-cells = <1>; + #size-cells = <1>; + + phram: flash@12340000 { + compatible = "phram"; + label = "rootfs"; + reg = <0x12340000 0x00800000>; + }; + }; diff --git a/Documentation/devicetree/bindings/reset/hisilicon,hi3660-reset.yaml b/Documentation/devicetree/bindings/reset/hisilicon,hi3660-reset.yaml index b0c41ab1a746..cdfcf32c53fa 100644 --- a/Documentation/devicetree/bindings/reset/hisilicon,hi3660-reset.yaml +++ b/Documentation/devicetree/bindings/reset/hisilicon,hi3660-reset.yaml @@ -24,6 +24,11 @@ properties: - const: hisilicon,hi3670-reset - const: hisilicon,hi3660-reset + hisi,rst-syscon: + deprecated: true + description: phandle of the reset's syscon, use hisilicon,rst-syscon instead + $ref: /schemas/types.yaml#/definitions/phandle + hisilicon,rst-syscon: description: phandle of the reset's syscon. $ref: /schemas/types.yaml#/definitions/phandle diff --git a/Documentation/devicetree/bindings/reset/socionext,uniphier-reset.yaml b/Documentation/devicetree/bindings/reset/socionext,uniphier-reset.yaml index 377a7d242323..6566804ec567 100644 --- a/Documentation/devicetree/bindings/reset/socionext,uniphier-reset.yaml +++ b/Documentation/devicetree/bindings/reset/socionext,uniphier-reset.yaml @@ -55,6 +55,9 @@ properties: "#reset-cells": const: 1 + resets: + maxItems: 1 + additionalProperties: false required: diff --git a/Documentation/devicetree/bindings/rng/samsung,exynos5250-trng.yaml b/Documentation/devicetree/bindings/rng/samsung,exynos5250-trng.yaml index a50c34d5d199..765d9f9edd6e 100644 --- a/Documentation/devicetree/bindings/rng/samsung,exynos5250-trng.yaml +++ b/Documentation/devicetree/bindings/rng/samsung,exynos5250-trng.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung Exynos SoC True Random Number Generator maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Łukasz Stelmach <l.stelmach@samsung.com> properties: diff --git a/Documentation/devicetree/bindings/rng/timeriomem_rng.yaml b/Documentation/devicetree/bindings/rng/timeriomem_rng.yaml index 84bf518a5549..4754174e9849 100644 --- a/Documentation/devicetree/bindings/rng/timeriomem_rng.yaml +++ b/Documentation/devicetree/bindings/rng/timeriomem_rng.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: TimerIO Random Number Generator maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/rtc/allwinner,sun6i-a31-rtc.yaml b/Documentation/devicetree/bindings/rtc/allwinner,sun6i-a31-rtc.yaml index 0b767fec39d8..6b38bd7eb3b4 100644 --- a/Documentation/devicetree/bindings/rtc/allwinner,sun6i-a31-rtc.yaml +++ b/Documentation/devicetree/bindings/rtc/allwinner,sun6i-a31-rtc.yaml @@ -71,7 +71,6 @@ allOf: then: properties: clock-output-names: - minItems: 1 maxItems: 1 - if: @@ -102,7 +101,6 @@ allOf: properties: clock-output-names: minItems: 3 - maxItems: 3 - if: properties: @@ -113,16 +111,12 @@ allOf: then: properties: clocks: - minItems: 3 - maxItems: 3 items: - description: Bus clock for register access - description: 24 MHz oscillator - description: 32 kHz clock from the CCU clock-names: - minItems: 3 - maxItems: 3 items: - const: bus - const: hosc @@ -142,7 +136,6 @@ allOf: properties: clocks: minItems: 3 - maxItems: 4 items: - description: Bus clock for register access - description: 24 MHz oscillator @@ -151,7 +144,6 @@ allOf: clock-names: minItems: 3 - maxItems: 4 items: - const: bus - const: hosc @@ -174,14 +166,12 @@ allOf: then: properties: interrupts: - minItems: 1 maxItems: 1 else: properties: interrupts: minItems: 2 - maxItems: 2 required: - "#clock-cells" diff --git a/Documentation/devicetree/bindings/rtc/microchip,mfps-rtc.yaml b/Documentation/devicetree/bindings/rtc/microchip,mfps-rtc.yaml index a2e984ea3553..500c62becd6b 100644 --- a/Documentation/devicetree/bindings/rtc/microchip,mfps-rtc.yaml +++ b/Documentation/devicetree/bindings/rtc/microchip,mfps-rtc.yaml @@ -31,11 +31,19 @@ properties: to that of the RTC's count register. clocks: - maxItems: 1 + items: + - description: | + AHB clock + - description: | + Reference clock: divided by the prescaler to create a time-based + strobe (typically 1 Hz) for the calendar counter. By default, the rtc + on the PolarFire SoC shares it's reference with MTIMER so this will + be a 1 MHz clock. clock-names: items: - const: rtc + - const: rtcref required: - compatible @@ -48,11 +56,12 @@ additionalProperties: false examples: - | + #include "dt-bindings/clock/microchip,mpfs-clock.h" rtc@20124000 { compatible = "microchip,mpfs-rtc"; reg = <0x20124000 0x1000>; - clocks = <&clkcfg 21>; - clock-names = "rtc"; + clocks = <&clkcfg CLK_RTC>, <&clkcfg CLK_RTCREF>; + clock-names = "rtc", "rtcref"; interrupts = <80>, <81>; }; ... diff --git a/Documentation/devicetree/bindings/serial/samsung_uart.yaml b/Documentation/devicetree/bindings/serial/samsung_uart.yaml index d4688e317fc5..901c1e2cea28 100644 --- a/Documentation/devicetree/bindings/serial/samsung_uart.yaml +++ b/Documentation/devicetree/bindings/serial/samsung_uart.yaml @@ -100,7 +100,6 @@ allOf: maxItems: 3 clock-names: minItems: 2 - maxItems: 3 items: - const: uart - pattern: '^clk_uart_baud[0-1]$' @@ -118,11 +117,8 @@ allOf: then: properties: clocks: - minItems: 2 maxItems: 2 clock-names: - minItems: 2 - maxItems: 2 items: - const: uart - const: clk_uart_baud0 diff --git a/Documentation/devicetree/bindings/soc/samsung/exynos-usi.yaml b/Documentation/devicetree/bindings/soc/samsung/exynos-usi.yaml index a98ed66d092e..0cabb773c397 100644 --- a/Documentation/devicetree/bindings/soc/samsung/exynos-usi.yaml +++ b/Documentation/devicetree/bindings/soc/samsung/exynos-usi.yaml @@ -8,7 +8,7 @@ title: Samsung's Exynos USI (Universal Serial Interface) binding maintainers: - Sam Protsenko <semen.protsenko@linaro.org> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | USI IP-core provides selectable serial protocol (UART, SPI or High-Speed I2C). diff --git a/Documentation/devicetree/bindings/sound/allwinner,sun4i-a10-i2s.yaml b/Documentation/devicetree/bindings/sound/allwinner,sun4i-a10-i2s.yaml index c21c807b667c..34f6ee9de392 100644 --- a/Documentation/devicetree/bindings/sound/allwinner,sun4i-a10-i2s.yaml +++ b/Documentation/devicetree/bindings/sound/allwinner,sun4i-a10-i2s.yaml @@ -89,7 +89,6 @@ allOf: properties: dmas: minItems: 1 - maxItems: 2 items: - description: RX DMA Channel - description: TX DMA Channel diff --git a/Documentation/devicetree/bindings/sound/samsung,arndale.yaml b/Documentation/devicetree/bindings/sound/samsung,arndale.yaml index cea2bf3544f0..9bc4585bb6e5 100644 --- a/Documentation/devicetree/bindings/sound/samsung,arndale.yaml +++ b/Documentation/devicetree/bindings/sound/samsung,arndale.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Insignal Arndale boards audio complex maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Sylwester Nawrocki <s.nawrocki@samsung.com> properties: diff --git a/Documentation/devicetree/bindings/sound/samsung,smdk5250.yaml b/Documentation/devicetree/bindings/sound/samsung,smdk5250.yaml index cb51af90435e..ac151d3c1d77 100644 --- a/Documentation/devicetree/bindings/sound/samsung,smdk5250.yaml +++ b/Documentation/devicetree/bindings/sound/samsung,smdk5250.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung SMDK5250 audio complex with WM8994 codec maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Sylwester Nawrocki <s.nawrocki@samsung.com> properties: diff --git a/Documentation/devicetree/bindings/sound/samsung,snow.yaml b/Documentation/devicetree/bindings/sound/samsung,snow.yaml index 0c3b3302b842..51a83d3c7274 100644 --- a/Documentation/devicetree/bindings/sound/samsung,snow.yaml +++ b/Documentation/devicetree/bindings/sound/samsung,snow.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Google Snow audio complex with MAX9809x codec maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Sylwester Nawrocki <s.nawrocki@samsung.com> properties: diff --git a/Documentation/devicetree/bindings/sound/samsung,tm2.yaml b/Documentation/devicetree/bindings/sound/samsung,tm2.yaml index 74712d6f3ef4..491e08019c04 100644 --- a/Documentation/devicetree/bindings/sound/samsung,tm2.yaml +++ b/Documentation/devicetree/bindings/sound/samsung,tm2.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung Exynos5433 TM2(E) audio complex with WM5110 codec maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Sylwester Nawrocki <s.nawrocki@samsung.com> properties: diff --git a/Documentation/devicetree/bindings/sound/st,stm32-sai.yaml b/Documentation/devicetree/bindings/sound/st,stm32-sai.yaml index b3dbcba33e41..fe2e15504ebc 100644 --- a/Documentation/devicetree/bindings/sound/st,stm32-sai.yaml +++ b/Documentation/devicetree/bindings/sound/st,stm32-sai.yaml @@ -136,8 +136,7 @@ allOf: compatible: contains: const: st,stm32f4-sai - - - then: + then: properties: clocks: items: @@ -148,8 +147,7 @@ allOf: items: - const: x8k - const: x11k - - - else: + else: properties: clocks: items: diff --git a/Documentation/devicetree/bindings/sound/ti,j721e-cpb-audio.yaml b/Documentation/devicetree/bindings/sound/ti,j721e-cpb-audio.yaml index 6806f53a4aed..20ea5883b7ff 100644 --- a/Documentation/devicetree/bindings/sound/ti,j721e-cpb-audio.yaml +++ b/Documentation/devicetree/bindings/sound/ti,j721e-cpb-audio.yaml @@ -80,7 +80,6 @@ allOf: then: properties: clocks: - minItems: 6 items: - description: AUXCLK clock for McASP used by CPB audio - description: Parent for CPB_McASP auxclk (for 48KHz) @@ -107,7 +106,6 @@ allOf: then: properties: clocks: - maxItems: 4 items: - description: AUXCLK clock for McASP used by CPB audio - description: Parent for CPB_McASP auxclk (for 48KHz) diff --git a/Documentation/devicetree/bindings/spi/aspeed,ast2600-fmc.yaml b/Documentation/devicetree/bindings/spi/aspeed,ast2600-fmc.yaml new file mode 100644 index 000000000000..fa8f4ac20985 --- /dev/null +++ b/Documentation/devicetree/bindings/spi/aspeed,ast2600-fmc.yaml @@ -0,0 +1,82 @@ +# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/spi/aspeed,ast2600-fmc.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Aspeed SMC controllers bindings + +maintainers: + - Chin-Ting Kuo <chin-ting_kuo@aspeedtech.com> + - Cédric Le Goater <clg@kaod.org> + +description: | + This binding describes the Aspeed Static Memory Controllers (FMC and + SPI) of the AST2400, AST2500 and AST2600 SOCs. + +allOf: + - $ref: "spi-controller.yaml#" + +properties: + compatible: + enum: + - aspeed,ast2600-fmc + - aspeed,ast2600-spi + - aspeed,ast2500-fmc + - aspeed,ast2500-spi + - aspeed,ast2400-fmc + - aspeed,ast2400-spi + + reg: + items: + - description: registers + - description: memory mapping + + clocks: + maxItems: 1 + + interrupts: + maxItems: 1 + +required: + - compatible + - reg + - clocks + +unevaluatedProperties: false + +examples: + - | + #include <dt-bindings/interrupt-controller/arm-gic.h> + #include <dt-bindings/interrupt-controller/aspeed-scu-ic.h> + #include <dt-bindings/clock/ast2600-clock.h> + + spi@1e620000 { + reg = <0x1e620000 0xc4>, <0x20000000 0x10000000>; + #address-cells = <1>; + #size-cells = <0>; + compatible = "aspeed,ast2600-fmc"; + clocks = <&syscon ASPEED_CLK_AHB>; + interrupts = <GIC_SPI 39 IRQ_TYPE_LEVEL_HIGH>; + + flash@0 { + reg = < 0 >; + compatible = "jedec,spi-nor"; + spi-max-frequency = <50000000>; + spi-rx-bus-width = <2>; + }; + + flash@1 { + reg = < 1 >; + compatible = "jedec,spi-nor"; + spi-max-frequency = <50000000>; + spi-rx-bus-width = <2>; + }; + + flash@2 { + reg = < 2 >; + compatible = "jedec,spi-nor"; + spi-max-frequency = <50000000>; + spi-rx-bus-width = <2>; + }; + }; diff --git a/Documentation/devicetree/bindings/spi/ingenic,spi.yaml b/Documentation/devicetree/bindings/spi/ingenic,spi.yaml index 5b1c7a2a6a31..360f76c226d9 100644 --- a/Documentation/devicetree/bindings/spi/ingenic,spi.yaml +++ b/Documentation/devicetree/bindings/spi/ingenic,spi.yaml @@ -18,7 +18,10 @@ properties: oneOf: - enum: - ingenic,jz4750-spi + - ingenic,jz4775-spi - ingenic,jz4780-spi + - ingenic,x1000-spi + - ingenic,x2000-spi - items: - enum: - ingenic,jz4760-spi diff --git a/Documentation/devicetree/bindings/spi/mediatek,spi-mt65xx.yaml b/Documentation/devicetree/bindings/spi/mediatek,spi-mt65xx.yaml index 818130b11bb9..94ef0552bd42 100644 --- a/Documentation/devicetree/bindings/spi/mediatek,spi-mt65xx.yaml +++ b/Documentation/devicetree/bindings/spi/mediatek,spi-mt65xx.yaml @@ -53,16 +53,20 @@ properties: maxItems: 1 clocks: + minItems: 3 items: - description: clock used for the parent clock - description: clock used for the muxes clock - description: clock used for the clock gate + - description: clock used for the AHB bus, this clock is optional clock-names: + minItems: 3 items: - const: parent-clk - const: sel-clk - const: spi-clk + - const: hclk mediatek,pad-select: $ref: /schemas/types.yaml#/definitions/uint32-array diff --git a/Documentation/devicetree/bindings/spi/mediatek,spi-mtk-snfi.yaml b/Documentation/devicetree/bindings/spi/mediatek,spi-mtk-snfi.yaml new file mode 100644 index 000000000000..6e6e02c91780 --- /dev/null +++ b/Documentation/devicetree/bindings/spi/mediatek,spi-mtk-snfi.yaml @@ -0,0 +1,88 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/spi/mediatek,spi-mtk-snfi.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: SPI-NAND flash controller for MediaTek ARM SoCs + +maintainers: + - Chuanhong Guo <gch981213@gmail.com> + +description: | + The Mediatek SPI-NAND flash controller is an extended version of + the Mediatek NAND flash controller. It can perform standard SPI + instructions with one continuous write and one read for up-to 0xa0 + bytes. It also supports typical SPI-NAND page cache operations + in single, dual or quad IO mode with pipelined ECC encoding/decoding + using the accompanying ECC engine. There should be only one spi + slave device following generic spi bindings. + +allOf: + - $ref: /schemas/spi/spi-controller.yaml# + +properties: + compatible: + enum: + - mediatek,mt7622-snand + - mediatek,mt7629-snand + + reg: + items: + - description: core registers + + interrupts: + items: + - description: NFI interrupt + + clocks: + items: + - description: clock used for the controller + - description: clock used for the SPI bus + + clock-names: + items: + - const: nfi_clk + - const: pad_clk + + nand-ecc-engine: + description: device-tree node of the accompanying ECC engine. + $ref: /schemas/types.yaml#/definitions/phandle + +required: + - compatible + - reg + - interrupts + - clocks + - clock-names + - nand-ecc-engine + +unevaluatedProperties: false + +examples: + - | + #include <dt-bindings/interrupt-controller/irq.h> + #include <dt-bindings/interrupt-controller/arm-gic.h> + #include <dt-bindings/clock/mt7622-clk.h> + soc { + #address-cells = <2>; + #size-cells = <2>; + snfi: spi@1100d000 { + compatible = "mediatek,mt7622-snand"; + reg = <0 0x1100d000 0 0x1000>; + interrupts = <GIC_SPI 96 IRQ_TYPE_LEVEL_LOW>; + clocks = <&pericfg CLK_PERI_NFI_PD>, <&pericfg CLK_PERI_SNFI_PD>; + clock-names = "nfi_clk", "pad_clk"; + nand-ecc-engine = <&bch>; + #address-cells = <1>; + #size-cells = <0>; + + flash@0 { + compatible = "spi-nand"; + reg = <0>; + spi-tx-bus-width = <4>; + spi-rx-bus-width = <4>; + nand-ecc-engine = <&snfi>; + }; + }; + }; diff --git a/Documentation/devicetree/bindings/spi/qcom,spi-qcom-qspi.yaml b/Documentation/devicetree/bindings/spi/qcom,spi-qcom-qspi.yaml index 5a60fba14bba..44d08aa3fd85 100644 --- a/Documentation/devicetree/bindings/spi/qcom,spi-qcom-qspi.yaml +++ b/Documentation/devicetree/bindings/spi/qcom,spi-qcom-qspi.yaml @@ -49,6 +49,7 @@ properties: maxItems: 2 interconnect-names: + minItems: 1 items: - const: qspi-config - const: qspi-memory diff --git a/Documentation/devicetree/bindings/spi/renesas,rspi.yaml b/Documentation/devicetree/bindings/spi/renesas,rspi.yaml index 2c3c6bd6ec45..f45d3b75d6de 100644 --- a/Documentation/devicetree/bindings/spi/renesas,rspi.yaml +++ b/Documentation/devicetree/bindings/spi/renesas,rspi.yaml @@ -21,6 +21,7 @@ properties: - enum: - renesas,rspi-r7s72100 # RZ/A1H - renesas,rspi-r7s9210 # RZ/A2 + - renesas,r9a07g043-rspi # RZ/G2UL - renesas,r9a07g044-rspi # RZ/G2{L,LC} - renesas,r9a07g054-rspi # RZ/V2L - const: renesas,rspi-rz @@ -124,6 +125,7 @@ allOf: contains: enum: - renesas,qspi + - renesas,r9a07g043-rspi - renesas,r9a07g044-rspi - renesas,r9a07g054-rspi then: diff --git a/Documentation/devicetree/bindings/spi/renesas,sh-msiof.yaml b/Documentation/devicetree/bindings/spi/renesas,sh-msiof.yaml index b104899205f6..5de710adfa63 100644 --- a/Documentation/devicetree/bindings/spi/renesas,sh-msiof.yaml +++ b/Documentation/devicetree/bindings/spi/renesas,sh-msiof.yaml @@ -124,7 +124,6 @@ properties: description: | Override the default TX fifo size. Unit is words. Ignored if 0. $ref: /schemas/types.yaml#/definitions/uint32 - maxItems: 1 default: 64 renesas,rx-fifo-size: @@ -132,7 +131,6 @@ properties: description: | Override the default RX fifo size. Unit is words. Ignored if 0. $ref: /schemas/types.yaml#/definitions/uint32 - maxItems: 1 default: 64 required: diff --git a/Documentation/devicetree/bindings/spi/samsung,spi-peripheral-props.yaml b/Documentation/devicetree/bindings/spi/samsung,spi-peripheral-props.yaml index f0db3fb3d688..25b1b6c12d4d 100644 --- a/Documentation/devicetree/bindings/spi/samsung,spi-peripheral-props.yaml +++ b/Documentation/devicetree/bindings/spi/samsung,spi-peripheral-props.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Peripheral-specific properties for Samsung S3C/S5P/Exynos SoC SPI controller maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: See spi-peripheral-props.yaml for more info. diff --git a/Documentation/devicetree/bindings/spi/samsung,spi.yaml b/Documentation/devicetree/bindings/spi/samsung,spi.yaml index bf9a76d931d2..a50f24f9359d 100644 --- a/Documentation/devicetree/bindings/spi/samsung,spi.yaml +++ b/Documentation/devicetree/bindings/spi/samsung,spi.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung S3C/S5P/Exynos SoC SPI controller maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: All the SPI controller nodes should be represented in the aliases node using diff --git a/Documentation/devicetree/bindings/sram/sram.yaml b/Documentation/devicetree/bindings/sram/sram.yaml index 668a9a41a775..993430be355b 100644 --- a/Documentation/devicetree/bindings/sram/sram.yaml +++ b/Documentation/devicetree/bindings/sram/sram.yaml @@ -136,14 +136,14 @@ required: - reg if: - properties: - compatible: - contains: - enum: - - qcom,rpm-msg-ram - - rockchip,rk3288-pmu-sram - -else: + not: + properties: + compatible: + contains: + enum: + - qcom,rpm-msg-ram + - rockchip,rk3288-pmu-sram +then: required: - "#address-cells" - "#size-cells" diff --git a/Documentation/devicetree/bindings/thermal/qcom-lmh.yaml b/Documentation/devicetree/bindings/thermal/qcom-lmh.yaml index a9b7388ca9ac..e1587ddf7de3 100644 --- a/Documentation/devicetree/bindings/thermal/qcom-lmh.yaml +++ b/Documentation/devicetree/bindings/thermal/qcom-lmh.yaml @@ -18,6 +18,7 @@ description: properties: compatible: enum: + - qcom,sc8180x-lmh - qcom,sdm845-lmh - qcom,sm8150-lmh diff --git a/Documentation/devicetree/bindings/thermal/qcom-spmi-adc-tm5.yaml b/Documentation/devicetree/bindings/thermal/qcom-spmi-adc-tm5.yaml index 3ea8c0c1f45f..feb390d50696 100644 --- a/Documentation/devicetree/bindings/thermal/qcom-spmi-adc-tm5.yaml +++ b/Documentation/devicetree/bindings/thermal/qcom-spmi-adc-tm5.yaml @@ -10,7 +10,9 @@ maintainers: properties: compatible: - const: qcom,spmi-adc-tm5 + enum: + - qcom,spmi-adc-tm5 + - qcom,spmi-adc-tm5-gen2 reg: maxItems: 1 @@ -33,6 +35,7 @@ properties: qcom,avg-samples: $ref: /schemas/types.yaml#/definitions/uint32 description: Number of samples to be used for measurement. + Not applicable for Gen2 ADC_TM peripheral. enum: - 1 - 2 @@ -45,6 +48,7 @@ properties: $ref: /schemas/types.yaml#/definitions/uint32 description: This parameter is used to decrease ADC sampling rate. Quicker measurements can be made by reducing decimation ratio. + Not applicable for Gen2 ADC_TM peripheral. enum: - 250 - 420 @@ -93,6 +97,29 @@ patternProperties: - const: 1 - enum: [ 1, 3, 4, 6, 20, 8, 10 ] + qcom,avg-samples: + $ref: /schemas/types.yaml#/definitions/uint32 + description: Number of samples to be used for measurement. + This property in child node is applicable only for Gen2 ADC_TM peripheral. + enum: + - 1 + - 2 + - 4 + - 8 + - 16 + default: 1 + + qcom,decimation: + $ref: /schemas/types.yaml#/definitions/uint32 + description: This parameter is used to decrease ADC sampling rate. + Quicker measurements can be made by reducing decimation ratio. + This property in child node is applicable only for Gen2 ADC_TM peripheral. + enum: + - 85 + - 340 + - 1360 + default: 1360 + required: - reg - io-channels @@ -100,6 +127,31 @@ patternProperties: additionalProperties: false +allOf: + - if: + properties: + compatible: + contains: + const: qcom,spmi-adc-tm5 + + then: + patternProperties: + "^([-a-z0-9]*)@[0-7]$": + properties: + qcom,decimation: false + qcom,avg-samples: false + + - if: + properties: + compatible: + contains: + const: qcom,spmi-adc-tm5-gen2 + + then: + properties: + qcom,avg-samples: false + qcom,decimation: false + required: - compatible - reg @@ -124,7 +176,7 @@ examples: #size-cells = <0>; #io-channel-cells = <1>; - /* Other propreties are omitted */ + /* Other properties are omitted */ conn-therm@4f { reg = <ADC5_AMUX_THM3_100K_PU>; qcom,ratiometric; @@ -148,4 +200,58 @@ examples: }; }; }; + + - | + #include <dt-bindings/iio/qcom,spmi-adc7-pmk8350.h> + #include <dt-bindings/iio/qcom,spmi-adc7-pm8350.h> + #include <dt-bindings/interrupt-controller/irq.h> + spmi_bus { + #address-cells = <1>; + #size-cells = <0>; + pmk8350_vadc: adc@3100 { + reg = <0x3100>; + compatible = "qcom,spmi-adc7"; + #address-cells = <1>; + #size-cells = <0>; + #io-channel-cells = <1>; + + /* Other properties are omitted */ + xo-therm@44 { + reg = <PMK8350_ADC7_AMUX_THM1_100K_PU>; + qcom,ratiometric; + qcom,hw-settle-time = <200>; + }; + + conn-therm@47 { + reg = <PM8350_ADC7_AMUX_THM4_100K_PU>; + qcom,ratiometric; + qcom,hw-settle-time = <200>; + }; + }; + + pmk8350_adc_tm: adc-tm@3400 { + compatible = "qcom,spmi-adc-tm5-gen2"; + reg = <0x3400>; + interrupts = <0x0 0x34 0x0 IRQ_TYPE_EDGE_RISING>; + #thermal-sensor-cells = <1>; + #address-cells = <1>; + #size-cells = <0>; + + pmk8350-xo-therm@0 { + reg = <0>; + io-channels = <&pmk8350_vadc PMK8350_ADC7_AMUX_THM1_100K_PU>; + qcom,decimation = <340>; + qcom,ratiometric; + qcom,hw-settle-time-us = <200>; + }; + + conn-therm@1 { + reg = <1>; + io-channels = <&pmk8350_vadc PM8350_ADC7_AMUX_THM4_100K_PU>; + qcom,avg-samples = <2>; + qcom,ratiometric; + qcom,hw-settle-time-us = <200>; + }; + }; + }; ... diff --git a/Documentation/devicetree/bindings/thermal/qcom-tsens.yaml b/Documentation/devicetree/bindings/thermal/qcom-tsens.yaml index b6406bcc683f..a24baf9b9f64 100644 --- a/Documentation/devicetree/bindings/thermal/qcom-tsens.yaml +++ b/Documentation/devicetree/bindings/thermal/qcom-tsens.yaml @@ -19,10 +19,11 @@ description: | properties: compatible: oneOf: - - description: msm9860 TSENS based + - description: msm8960 TSENS based items: - enum: - qcom,ipq8064-tsens + - qcom,msm8960-tsens - description: v0.1 of TSENS items: @@ -49,6 +50,7 @@ properties: - qcom,sc7180-tsens - qcom,sc7280-tsens - qcom,sc8180x-tsens + - qcom,sc8280xp-tsens - qcom,sdm630-tsens - qcom,sdm845-tsens - qcom,sm8150-tsens @@ -116,6 +118,7 @@ allOf: - qcom,ipq8064-tsens - qcom,mdm9607-tsens - qcom,msm8916-tsens + - qcom,msm8960-tsens - qcom,msm8974-tsens - qcom,msm8976-tsens - qcom,qcs404-tsens diff --git a/Documentation/devicetree/bindings/thermal/rcar-gen3-thermal.yaml b/Documentation/devicetree/bindings/thermal/rcar-gen3-thermal.yaml index f963204e0b16..1368d90da0e8 100644 --- a/Documentation/devicetree/bindings/thermal/rcar-gen3-thermal.yaml +++ b/Documentation/devicetree/bindings/thermal/rcar-gen3-thermal.yaml @@ -67,7 +67,6 @@ then: properties: reg: minItems: 2 - maxItems: 3 items: - description: TSC1 registers - description: TSC2 registers diff --git a/Documentation/devicetree/bindings/thermal/rzg2l-thermal.yaml b/Documentation/devicetree/bindings/thermal/rzg2l-thermal.yaml index ccab9511a042..1d8373397848 100644 --- a/Documentation/devicetree/bindings/thermal/rzg2l-thermal.yaml +++ b/Documentation/devicetree/bindings/thermal/rzg2l-thermal.yaml @@ -17,7 +17,9 @@ properties: compatible: items: - enum: + - renesas,r9a07g043-tsu # RZ/G2UL - renesas,r9a07g044-tsu # RZ/G2{L,LC} + - renesas,r9a07g054-tsu # RZ/V2L - const: renesas,rzg2l-tsu reg: diff --git a/Documentation/devicetree/bindings/thermal/samsung,exynos-thermal.yaml b/Documentation/devicetree/bindings/thermal/samsung,exynos-thermal.yaml index 17129f75d962..1344df708e2d 100644 --- a/Documentation/devicetree/bindings/thermal/samsung,exynos-thermal.yaml +++ b/Documentation/devicetree/bindings/thermal/samsung,exynos-thermal.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung Exynos SoC Thermal Management Unit (TMU) maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | For multi-instance tmu each instance should have an alias correctly numbered diff --git a/Documentation/devicetree/bindings/thermal/ti,j72xx-thermal.yaml b/Documentation/devicetree/bindings/thermal/ti,j72xx-thermal.yaml new file mode 100644 index 000000000000..c74f124ebfc0 --- /dev/null +++ b/Documentation/devicetree/bindings/thermal/ti,j72xx-thermal.yaml @@ -0,0 +1,63 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/thermal/ti,j72xx-thermal.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Texas Instruments J72XX VTM (DTS) binding + +maintainers: + - Keerthy <j-keerthy@ti.com> + +properties: + compatible: + enum: + - ti,j721e-vtm + - ti,j7200-vtm + + reg: + items: + - description: VTM cfg1 register space + - description: VTM cfg2 register space + - description: VTM efuse register space + + power-domains: + maxItems: 1 + + "#thermal-sensor-cells": + const: 1 + +required: + - compatible + - reg + - power-domains + - "#thermal-sensor-cells" + +additionalProperties: false + +examples: + - | + #include <dt-bindings/soc/ti,sci_pm_domain.h> + wkup_vtm0: thermal-sensor@42040000 { + compatible = "ti,j721e-vtm"; + reg = <0x42040000 0x350>, + <0x42050000 0x350>, + <0x43000300 0x10>; + power-domains = <&k3_pds 154 TI_SCI_PD_EXCLUSIVE>; + #thermal-sensor-cells = <1>; + }; + + mpu_thermal: mpu-thermal { + polling-delay-passive = <250>; /* milliseconds */ + polling-delay = <500>; /* milliseconds */ + thermal-sensors = <&wkup_vtm0 0>; + + trips { + mpu_crit: mpu-crit { + temperature = <125000>; /* milliCelsius */ + hysteresis = <2000>; /* milliCelsius */ + type = "critical"; + }; + }; + }; +... diff --git a/Documentation/devicetree/bindings/trivial-devices.yaml b/Documentation/devicetree/bindings/trivial-devices.yaml index 550a2e5c9e05..c11520347a9d 100644 --- a/Documentation/devicetree/bindings/trivial-devices.yaml +++ b/Documentation/devicetree/bindings/trivial-devices.yaml @@ -143,6 +143,10 @@ properties: - infineon,xdpe12254 # Infineon Multi-phase Digital VR Controller xdpe12284 - infineon,xdpe12284 + # Infineon Multi-phase Digital VR Controller xdpe15284 + - infineon,xdpe15284 + # Infineon Multi-phase Digital VR Controller xdpe152c4 + - infineon,xdpe152c4 # Injoinic IP5108 2.0A Power Bank IC with I2C - injoinic,ip5108 # Injoinic IP5109 2.1A Power Bank IC with I2C diff --git a/Documentation/devicetree/bindings/ufs/cdns,ufshc.yaml b/Documentation/devicetree/bindings/ufs/cdns,ufshc.yaml index d227dea368be..fb45f66d6454 100644 --- a/Documentation/devicetree/bindings/ufs/cdns,ufshc.yaml +++ b/Documentation/devicetree/bindings/ufs/cdns,ufshc.yaml @@ -43,6 +43,9 @@ properties: - const: phy_clk - const: ref_clk + power-domains: + maxItems: 1 + reg: maxItems: 1 diff --git a/Documentation/devicetree/bindings/usb/samsung,exynos-dwc3.yaml b/Documentation/devicetree/bindings/usb/samsung,exynos-dwc3.yaml index 22b91a27d776..6b9a3bcb3926 100644 --- a/Documentation/devicetree/bindings/usb/samsung,exynos-dwc3.yaml +++ b/Documentation/devicetree/bindings/usb/samsung,exynos-dwc3.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung Exynos SoC USB 3.0 DWC3 Controller maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/usb/samsung,exynos-usb2.yaml b/Documentation/devicetree/bindings/usb/samsung,exynos-usb2.yaml index fbf07d6e707a..9c92defbba01 100644 --- a/Documentation/devicetree/bindings/usb/samsung,exynos-usb2.yaml +++ b/Documentation/devicetree/bindings/usb/samsung,exynos-usb2.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung Exynos SoC USB 2.0 EHCI/OHCI Controller maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: @@ -62,6 +62,7 @@ required: - interrupts - phys - phy-names + - reg allOf: - if: diff --git a/Documentation/devicetree/bindings/vendor-prefixes.yaml b/Documentation/devicetree/bindings/vendor-prefixes.yaml index 01430973ecec..65ff22364fb3 100644 --- a/Documentation/devicetree/bindings/vendor-prefixes.yaml +++ b/Documentation/devicetree/bindings/vendor-prefixes.yaml @@ -1082,6 +1082,8 @@ patternProperties: description: Sensirion AG "^sensortek,.*": description: Sensortek Technology Corporation + "^sercomm,.*": + description: Sercomm (Suzhou) Corporation "^sff,.*": description: Small Form Factor Committee "^sgd,.*": diff --git a/Documentation/dontdiff b/Documentation/dontdiff index 910b30a2a7d9..352ff53a2306 100644 --- a/Documentation/dontdiff +++ b/Documentation/dontdiff @@ -211,6 +211,7 @@ r200_reg_safe.h r300_reg_safe.h r420_reg_safe.h r600_reg_safe.h +randstruct.seed randomize_layout_hash.h randomize_layout_seed.h recordmcount diff --git a/Documentation/driver-api/dma-buf.rst b/Documentation/driver-api/dma-buf.rst index 55006678394a..36a76cbe9095 100644 --- a/Documentation/driver-api/dma-buf.rst +++ b/Documentation/driver-api/dma-buf.rst @@ -185,6 +185,12 @@ DMA Fence Chain .. kernel-doc:: include/linux/dma-fence-chain.h :internal: +DMA Fence unwrap +~~~~~~~~~~~~~~~~ + +.. kernel-doc:: include/linux/dma-fence-unwrap.h + :internal: + DMA Fence uABI/Sync File ~~~~~~~~~~~~~~~~~~~~~~~~ diff --git a/Documentation/driver-api/gpio/driver.rst b/Documentation/driver-api/gpio/driver.rst index bbc53920d4dd..a1ddefa1f55f 100644 --- a/Documentation/driver-api/gpio/driver.rst +++ b/Documentation/driver-api/gpio/driver.rst @@ -417,30 +417,66 @@ struct gpio_irq_chip inside struct gpio_chip before adding the gpio_chip. If you do this, the additional irq_chip will be set up by gpiolib at the same time as setting up the rest of the GPIO functionality. The following is a typical example of a chained cascaded interrupt handler using -the gpio_irq_chip: +the gpio_irq_chip. Note how the mask/unmask (or disable/enable) functions +call into the core gpiolib code: .. code-block:: c - /* Typical state container with dynamic irqchip */ + /* Typical state container */ struct my_gpio { struct gpio_chip gc; - struct irq_chip irq; + }; + + static void my_gpio_mask_irq(struct irq_data *d) + { + struct gpio_chip *gc = irq_desc_get_handler_data(d); + + /* + * Perform any necessary action to mask the interrupt, + * and then call into the core code to synchronise the + * state. + */ + + gpiochip_disable_irq(gc, d->hwirq); + } + + static void my_gpio_unmask_irq(struct irq_data *d) + { + struct gpio_chip *gc = irq_desc_get_handler_data(d); + + gpiochip_enable_irq(gc, d->hwirq); + + /* + * Perform any necessary action to unmask the interrupt, + * after having called into the core code to synchronise + * the state. + */ + } + + /* + * Statically populate the irqchip. Note that it is made const + * (further indicated by the IRQCHIP_IMMUTABLE flag), and that + * the GPIOCHIP_IRQ_RESOURCE_HELPER macro adds some extra + * callbacks to the structure. + */ + static const struct irq_chip my_gpio_irq_chip = { + .name = "my_gpio_irq", + .irq_ack = my_gpio_ack_irq, + .irq_mask = my_gpio_mask_irq, + .irq_unmask = my_gpio_unmask_irq, + .irq_set_type = my_gpio_set_irq_type, + .flags = IRQCHIP_IMMUTABLE, + /* Provide the gpio resource callbacks */ + GPIOCHIP_IRQ_RESOURCE_HELPERS, }; int irq; /* from platform etc */ struct my_gpio *g; struct gpio_irq_chip *girq; - /* Set up the irqchip dynamically */ - g->irq.name = "my_gpio_irq"; - g->irq.irq_ack = my_gpio_ack_irq; - g->irq.irq_mask = my_gpio_mask_irq; - g->irq.irq_unmask = my_gpio_unmask_irq; - g->irq.irq_set_type = my_gpio_set_irq_type; - /* Get a pointer to the gpio_irq_chip */ girq = &g->gc.irq; - girq->chip = &g->irq; + gpio_irq_chip_set_chip(girq, &my_gpio_irq_chip); girq->parent_handler = ftgpio_gpio_irq_handler; girq->num_parents = 1; girq->parents = devm_kcalloc(dev, 1, sizeof(*girq->parents), @@ -458,23 +494,58 @@ the interrupt separately and go with it: .. code-block:: c - /* Typical state container with dynamic irqchip */ + /* Typical state container */ struct my_gpio { struct gpio_chip gc; - struct irq_chip irq; + }; + + static void my_gpio_mask_irq(struct irq_data *d) + { + struct gpio_chip *gc = irq_desc_get_handler_data(d); + + /* + * Perform any necessary action to mask the interrupt, + * and then call into the core code to synchronise the + * state. + */ + + gpiochip_disable_irq(gc, d->hwirq); + } + + static void my_gpio_unmask_irq(struct irq_data *d) + { + struct gpio_chip *gc = irq_desc_get_handler_data(d); + + gpiochip_enable_irq(gc, d->hwirq); + + /* + * Perform any necessary action to unmask the interrupt, + * after having called into the core code to synchronise + * the state. + */ + } + + /* + * Statically populate the irqchip. Note that it is made const + * (further indicated by the IRQCHIP_IMMUTABLE flag), and that + * the GPIOCHIP_IRQ_RESOURCE_HELPER macro adds some extra + * callbacks to the structure. + */ + static const struct irq_chip my_gpio_irq_chip = { + .name = "my_gpio_irq", + .irq_ack = my_gpio_ack_irq, + .irq_mask = my_gpio_mask_irq, + .irq_unmask = my_gpio_unmask_irq, + .irq_set_type = my_gpio_set_irq_type, + .flags = IRQCHIP_IMMUTABLE, + /* Provide the gpio resource callbacks */ + GPIOCHIP_IRQ_RESOURCE_HELPERS, }; int irq; /* from platform etc */ struct my_gpio *g; struct gpio_irq_chip *girq; - /* Set up the irqchip dynamically */ - g->irq.name = "my_gpio_irq"; - g->irq.irq_ack = my_gpio_ack_irq; - g->irq.irq_mask = my_gpio_mask_irq; - g->irq.irq_unmask = my_gpio_unmask_irq; - g->irq.irq_set_type = my_gpio_set_irq_type; - ret = devm_request_threaded_irq(dev, irq, NULL, irq_thread_fn, IRQF_ONESHOT, "my-chip", g); if (ret < 0) @@ -482,7 +553,7 @@ the interrupt separately and go with it: /* Get a pointer to the gpio_irq_chip */ girq = &g->gc.irq; - girq->chip = &g->irq; + gpio_irq_chip_set_chip(girq, &my_gpio_irq_chip); /* This will let us handle the parent IRQ in the driver */ girq->parent_handler = NULL; girq->num_parents = 0; @@ -500,24 +571,61 @@ In this case the typical set-up will look like this: /* Typical state container with dynamic irqchip */ struct my_gpio { struct gpio_chip gc; - struct irq_chip irq; struct fwnode_handle *fwnode; }; - int irq; /* from platform etc */ + static void my_gpio_mask_irq(struct irq_data *d) + { + struct gpio_chip *gc = irq_desc_get_handler_data(d); + + /* + * Perform any necessary action to mask the interrupt, + * and then call into the core code to synchronise the + * state. + */ + + gpiochip_disable_irq(gc, d->hwirq); + irq_mask_mask_parent(d); + } + + static void my_gpio_unmask_irq(struct irq_data *d) + { + struct gpio_chip *gc = irq_desc_get_handler_data(d); + + gpiochip_enable_irq(gc, d->hwirq); + + /* + * Perform any necessary action to unmask the interrupt, + * after having called into the core code to synchronise + * the state. + */ + + irq_mask_unmask_parent(d); + } + + /* + * Statically populate the irqchip. Note that it is made const + * (further indicated by the IRQCHIP_IMMUTABLE flag), and that + * the GPIOCHIP_IRQ_RESOURCE_HELPER macro adds some extra + * callbacks to the structure. + */ + static const struct irq_chip my_gpio_irq_chip = { + .name = "my_gpio_irq", + .irq_ack = my_gpio_ack_irq, + .irq_mask = my_gpio_mask_irq, + .irq_unmask = my_gpio_unmask_irq, + .irq_set_type = my_gpio_set_irq_type, + .flags = IRQCHIP_IMMUTABLE, + /* Provide the gpio resource callbacks */ + GPIOCHIP_IRQ_RESOURCE_HELPERS, + }; + struct my_gpio *g; struct gpio_irq_chip *girq; - /* Set up the irqchip dynamically */ - g->irq.name = "my_gpio_irq"; - g->irq.irq_ack = my_gpio_ack_irq; - g->irq.irq_mask = my_gpio_mask_irq; - g->irq.irq_unmask = my_gpio_unmask_irq; - g->irq.irq_set_type = my_gpio_set_irq_type; - /* Get a pointer to the gpio_irq_chip */ girq = &g->gc.irq; - girq->chip = &g->irq; + gpio_irq_chip_set_chip(girq, &my_gpio_irq_chip); girq->default_type = IRQ_TYPE_NONE; girq->handler = handle_bad_irq; girq->fwnode = g->fwnode; @@ -605,8 +713,9 @@ When implementing an irqchip inside a GPIO driver, these two functions should typically be called in the .irq_disable() and .irq_enable() callbacks from the irqchip. -When using the gpiolib irqchip helpers, these callbacks are automatically -assigned. +When IRQCHIP_IMMUTABLE is not advertised by the irqchip, these callbacks +are automatically assigned. This behaviour is deprecated and on its way +to be removed from the kernel. Real-Time compliance for GPIO IRQ chips diff --git a/Documentation/driver-api/libata.rst b/Documentation/driver-api/libata.rst index d477e296bda5..311af516a3fd 100644 --- a/Documentation/driver-api/libata.rst +++ b/Documentation/driver-api/libata.rst @@ -424,12 +424,6 @@ How commands are issued ----------------------- Internal commands - First, qc is allocated and initialized using :c:func:`ata_qc_new_init`. - Although :c:func:`ata_qc_new_init` doesn't implement any wait or retry - mechanism when qc is not available, internal commands are currently - issued only during initialization and error recovery, so no other - command is active and allocation is guaranteed to succeed. - Once allocated qc's taskfile is initialized for the command to be executed. qc currently has two mechanisms to notify completion. One is via ``qc->complete_fn()`` callback and the other is completion @@ -447,11 +441,6 @@ SCSI commands translated. No qc is involved in processing a simulated scmd. The result is computed right away and the scmd is completed. - For a translated scmd, :c:func:`ata_qc_new_init` is invoked to allocate a - qc and the scmd is translated into the qc. SCSI midlayer's - completion notification function pointer is stored into - ``qc->scsidone``. - ``qc->complete_fn()`` callback is used for completion notification. ATA commands use :c:func:`ata_scsi_qc_complete` while ATAPI commands use :c:func:`atapi_qc_complete`. Both functions end up calling ``qc->scsidone`` diff --git a/Documentation/driver-api/media/cec-core.rst b/Documentation/driver-api/media/cec-core.rst index c6194ee81c41..ae0d20798edc 100644 --- a/Documentation/driver-api/media/cec-core.rst +++ b/Documentation/driver-api/media/cec-core.rst @@ -109,6 +109,7 @@ your driver: int (*adap_monitor_all_enable)(struct cec_adapter *adap, bool enable); int (*adap_monitor_pin_enable)(struct cec_adapter *adap, bool enable); int (*adap_log_addr)(struct cec_adapter *adap, u8 logical_addr); + void (*adap_configured)(struct cec_adapter *adap, bool configured); int (*adap_transmit)(struct cec_adapter *adap, u8 attempts, u32 signal_free_time, struct cec_msg *msg); void (*adap_status)(struct cec_adapter *adap, struct seq_file *file); @@ -117,7 +118,7 @@ your driver: /* Error injection callbacks */ ... - /* High-level callbacks */ + /* High-level callback */ ... }; @@ -178,6 +179,16 @@ can receive directed messages to that address. Note that adap_log_addr must return 0 if logical_addr is CEC_LOG_ADDR_INVALID. +Called when the adapter is fully configured or unconfigured:: + + void (*adap_configured)(struct cec_adapter *adap, bool configured); + +If configured == true, then the adapter is fully configured, i.e. all logical +addresses have been successfully claimed. If configured == false, then the +adapter is unconfigured. If the driver has to take specific actions after +(un)configuration, then that can be done through this optional callback. + + To transmit a new message:: int (*adap_transmit)(struct cec_adapter *adap, u8 attempts, diff --git a/Documentation/driver-api/media/mc-core.rst b/Documentation/driver-api/media/mc-core.rst index 57b5bbba944e..02481a2513b9 100644 --- a/Documentation/driver-api/media/mc-core.rst +++ b/Documentation/driver-api/media/mc-core.rst @@ -42,9 +42,16 @@ Allocation of the structure is handled by the media device driver, usually by embedding the :c:type:`media_device` instance in a larger driver-specific structure. -Drivers register media device instances by calling -:c:func:`__media_device_register()` via the macro ``media_device_register()`` -and unregistered by calling :c:func:`media_device_unregister()`. +Drivers initialise media device instances by calling +:c:func:`media_device_init()`. After initialising a media device instance, it is +registered by calling :c:func:`__media_device_register()` via the macro +``media_device_register()`` and unregistered by calling +:c:func:`media_device_unregister()`. An initialised media device must be +eventually cleaned up by calling :c:func:`media_device_cleanup()`. + +Note that it is not allowed to unregister a media device instance that was not +previously registered, or clean up a media device instance that was not +previously initialised. Entities ^^^^^^^^ diff --git a/Documentation/driver-api/media/v4l2-subdev.rst b/Documentation/driver-api/media/v4l2-subdev.rst index 08ea2673b19e..cf3b52bdbfb9 100644 --- a/Documentation/driver-api/media/v4l2-subdev.rst +++ b/Documentation/driver-api/media/v4l2-subdev.rst @@ -518,6 +518,75 @@ The :c:func:`v4l2_i2c_new_subdev` function will call :c:type:`i2c_board_info` structure using the ``client_type`` and the ``addr`` to fill it. +Centrally managed subdev active state +------------------------------------- + +Traditionally V4L2 subdev drivers maintained internal state for the active +device configuration. This is often implemented as e.g. an array of struct +v4l2_mbus_framefmt, one entry for each pad, and similarly for crop and compose +rectangles. + +In addition to the active configuration, each subdev file handle has an array of +struct v4l2_subdev_pad_config, managed by the V4L2 core, which contains the try +configuration. + +To simplify the subdev drivers the V4L2 subdev API now optionally supports a +centrally managed active configuration represented by +:c:type:`v4l2_subdev_state`. One instance of state, which contains the active +device configuration, is stored in the sub-device itself as part of +the :c:type:`v4l2_subdev` structure, while the core associates a try state to +each open file handle, to store the try configuration related to that file +handle. + +Sub-device drivers can opt-in and use state to manage their active configuration +by initializing the subdevice state with a call to v4l2_subdev_init_finalize() +before registering the sub-device. They must also call v4l2_subdev_cleanup() +to release all the allocated resources before unregistering the sub-device. +The core automatically allocates and initializes a state for each open file +handle to store the try configurations and frees it when closing the file +handle. + +V4L2 sub-device operations that use both the :ref:`ACTIVE and TRY formats +<v4l2-subdev-format-whence>` receive the correct state to operate on through +the 'state' parameter. The state must be locked and unlocked by the +caller by calling :c:func:`v4l2_subdev_lock_state()` and +:c:func:`v4l2_subdev_unlock_state()`. The caller can do so by calling the subdev +operation through the :c:func:`v4l2_subdev_call_state_active()` macro. + +Operations that do not receive a state parameter implicitly operate on the +subdevice active state, which drivers can exclusively access by +calling :c:func:`v4l2_subdev_lock_and_get_active_state()`. The sub-device active +state must equally be released by calling :c:func:`v4l2_subdev_unlock_state()`. + +Drivers must never manually access the state stored in the :c:type:`v4l2_subdev` +or in the file handle without going through the designated helpers. + +While the V4L2 core passes the correct try or active state to the subdevice +operations, many existing device drivers pass a NULL state when calling +operations with :c:func:`v4l2_subdev_call()`. This legacy construct causes +issues with subdevice drivers that let the V4L2 core manage the active state, +as they expect to receive the appropriate state as a parameter. To help the +conversion of subdevice drivers to a managed active state without having to +convert all callers at the same time, an additional wrapper layer has been +added to v4l2_subdev_call(), which handles the NULL case by geting and locking +the callee's active state with :c:func:`v4l2_subdev_lock_and_get_active_state()`, +and unlocking the state after the call. + +The whole subdev state is in reality split into three parts: the +v4l2_subdev_state, subdev controls and subdev driver's internal state. In the +future these parts should be combined into a single state. For the time being +we need a way to handle the locking for these parts. This can be accomplished +by sharing a lock. The v4l2_ctrl_handler already supports this via its 'lock' +pointer and the same model is used with states. The driver can do the following +before calling v4l2_subdev_init_finalize(): + +.. code-block:: c + + sd->ctrl_handler->lock = &priv->mutex; + sd->state_lock = &priv->mutex; + +This shares the driver's private mutex between the controls and the states. + V4L2 sub-device functions and data structures --------------------------------------------- diff --git a/Documentation/features/debug/debug-vm-pgtable/arch-support.txt b/Documentation/features/debug/debug-vm-pgtable/arch-support.txt index 83eafe1a7f68..ff21a83abe62 100644 --- a/Documentation/features/debug/debug-vm-pgtable/arch-support.txt +++ b/Documentation/features/debug/debug-vm-pgtable/arch-support.txt @@ -27,5 +27,5 @@ | sparc: | TODO | | um: | TODO | | x86: | ok | - | xtensa: | TODO | + | xtensa: | ok | ----------------------- diff --git a/Documentation/features/time/context-tracking/arch-support.txt b/Documentation/features/time/context-tracking/arch-support.txt index bb1c1801553e..72e7aadeda7e 100644 --- a/Documentation/features/time/context-tracking/arch-support.txt +++ b/Documentation/features/time/context-tracking/arch-support.txt @@ -27,5 +27,5 @@ | sparc: | ok | | um: | TODO | | x86: | ok | - | xtensa: | TODO | + | xtensa: | ok | ----------------------- diff --git a/Documentation/features/time/virt-cpuacct/arch-support.txt b/Documentation/features/time/virt-cpuacct/arch-support.txt index 5163a60a1c1e..c905aa3c1d81 100644 --- a/Documentation/features/time/virt-cpuacct/arch-support.txt +++ b/Documentation/features/time/virt-cpuacct/arch-support.txt @@ -27,5 +27,5 @@ | sparc: | ok | | um: | TODO | | x86: | ok | - | xtensa: | TODO | + | xtensa: | ok | ----------------------- diff --git a/Documentation/filesystems/caching/backend-api.rst b/Documentation/filesystems/caching/backend-api.rst index be793c49a772..d7507becf674 100644 --- a/Documentation/filesystems/caching/backend-api.rst +++ b/Documentation/filesystems/caching/backend-api.rst @@ -73,7 +73,7 @@ busy. If successful, the cache backend can then start setting up the cache. In the event that the initialisation fails, the cache backend should call:: - void fscache_relinquish_cookie(struct fscache_cache *cache); + void fscache_relinquish_cache(struct fscache_cache *cache); to reset and discard the cookie. @@ -110,9 +110,9 @@ to withdraw them, calling:: on the cookie that each object belongs to. This schedules the specified cookie for withdrawal. This gets offloaded to a workqueue. The cache backend can -test for completion by calling:: +wait for completion by calling:: - bool fscache_are_objects_withdrawn(struct fscache_cookie *cache); + void fscache_wait_for_objects(struct fscache_cache *cache); Once all the cookies are withdrawn, a cache backend can withdraw all the volumes, calling:: @@ -125,7 +125,7 @@ outstanding accesses on the volume to complete before returning. When the the cache is completely withdrawn, fscache should be notified by calling:: - void fscache_cache_relinquish(struct fscache_cache *cache); + void fscache_relinquish_cache(struct fscache_cache *cache); to clear fields in the cookie and discard the caller's ref on it. diff --git a/Documentation/filesystems/caching/cachefiles.rst b/Documentation/filesystems/caching/cachefiles.rst index 8bf396b76359..fc7abf712315 100644 --- a/Documentation/filesystems/caching/cachefiles.rst +++ b/Documentation/filesystems/caching/cachefiles.rst @@ -28,6 +28,7 @@ Cache on Already Mounted Filesystem (*) Debugging. + (*) On-demand Read. Overview @@ -482,3 +483,180 @@ the control file. For example:: echo $((1|4|8)) >/sys/module/cachefiles/parameters/debug will turn on all function entry debugging. + + +On-demand Read +============== + +When working in its original mode, CacheFiles serves as a local cache for a +remote networking fs - while in on-demand read mode, CacheFiles can boost the +scenario where on-demand read semantics are needed, e.g. container image +distribution. + +The essential difference between these two modes is seen when a cache miss +occurs: In the original mode, the netfs will fetch the data from the remote +server and then write it to the cache file; in on-demand read mode, fetching +the data and writing it into the cache is delegated to a user daemon. + +``CONFIG_CACHEFILES_ONDEMAND`` should be enabled to support on-demand read mode. + + +Protocol Communication +---------------------- + +The on-demand read mode uses a simple protocol for communication between kernel +and user daemon. The protocol can be modeled as:: + + kernel --[request]--> user daemon --[reply]--> kernel + +CacheFiles will send requests to the user daemon when needed. The user daemon +should poll the devnode ('/dev/cachefiles') to check if there's a pending +request to be processed. A POLLIN event will be returned when there's a pending +request. + +The user daemon then reads the devnode to fetch a request to process. It should +be noted that each read only gets one request. When it has finished processing +the request, the user daemon should write the reply to the devnode. + +Each request starts with a message header of the form:: + + struct cachefiles_msg { + __u32 msg_id; + __u32 opcode; + __u32 len; + __u32 object_id; + __u8 data[]; + }; + +where: + + * ``msg_id`` is a unique ID identifying this request among all pending + requests. + + * ``opcode`` indicates the type of this request. + + * ``object_id`` is a unique ID identifying the cache file operated on. + + * ``data`` indicates the payload of this request. + + * ``len`` indicates the whole length of this request, including the + header and following type-specific payload. + + +Turning on On-demand Mode +------------------------- + +An optional parameter becomes available to the "bind" command:: + + bind [ondemand] + +When the "bind" command is given no argument, it defaults to the original mode. +When it is given the "ondemand" argument, i.e. "bind ondemand", on-demand read +mode will be enabled. + + +The OPEN Request +---------------- + +When the netfs opens a cache file for the first time, a request with the +CACHEFILES_OP_OPEN opcode, a.k.a an OPEN request will be sent to the user +daemon. The payload format is of the form:: + + struct cachefiles_open { + __u32 volume_key_size; + __u32 cookie_key_size; + __u32 fd; + __u32 flags; + __u8 data[]; + }; + +where: + + * ``data`` contains the volume_key followed directly by the cookie_key. + The volume key is a NUL-terminated string; the cookie key is binary + data. + + * ``volume_key_size`` indicates the size of the volume key in bytes. + + * ``cookie_key_size`` indicates the size of the cookie key in bytes. + + * ``fd`` indicates an anonymous fd referring to the cache file, through + which the user daemon can perform write/llseek file operations on the + cache file. + + +The user daemon can use the given (volume_key, cookie_key) pair to distinguish +the requested cache file. With the given anonymous fd, the user daemon can +fetch the data and write it to the cache file in the background, even when +kernel has not triggered a cache miss yet. + +Be noted that each cache file has a unique object_id, while it may have multiple +anonymous fds. The user daemon may duplicate anonymous fds from the initial +anonymous fd indicated by the @fd field through dup(). Thus each object_id can +be mapped to multiple anonymous fds, while the usr daemon itself needs to +maintain the mapping. + +When implementing a user daemon, please be careful of RLIMIT_NOFILE, +``/proc/sys/fs/nr_open`` and ``/proc/sys/fs/file-max``. Typically these needn't +be huge since they're related to the number of open device blobs rather than +open files of each individual filesystem. + +The user daemon should reply the OPEN request by issuing a "copen" (complete +open) command on the devnode:: + + copen <msg_id>,<cache_size> + +where: + + * ``msg_id`` must match the msg_id field of the OPEN request. + + * When >= 0, ``cache_size`` indicates the size of the cache file; + when < 0, ``cache_size`` indicates any error code encountered by the + user daemon. + + +The CLOSE Request +----------------- + +When a cookie withdrawn, a CLOSE request (opcode CACHEFILES_OP_CLOSE) will be +sent to the user daemon. This tells the user daemon to close all anonymous fds +associated with the given object_id. The CLOSE request has no extra payload, +and shouldn't be replied. + + +The READ Request +---------------- + +When a cache miss is encountered in on-demand read mode, CacheFiles will send a +READ request (opcode CACHEFILES_OP_READ) to the user daemon. This tells the user +daemon to fetch the contents of the requested file range. The payload is of the +form:: + + struct cachefiles_read { + __u64 off; + __u64 len; + }; + +where: + + * ``off`` indicates the starting offset of the requested file range. + + * ``len`` indicates the length of the requested file range. + + +When it receives a READ request, the user daemon should fetch the requested data +and write it to the cache file identified by object_id. + +When it has finished processing the READ request, the user daemon should reply +by using the CACHEFILES_IOC_READ_COMPLETE ioctl on one of the anonymous fds +associated with the object_id given in the READ request. The ioctl is of the +form:: + + ioctl(fd, CACHEFILES_IOC_READ_COMPLETE, msg_id); + +where: + + * ``fd`` is one of the anonymous fds associated with the object_id + given. + + * ``msg_id`` must match the msg_id field of the READ request. diff --git a/Documentation/filesystems/caching/netfs-api.rst b/Documentation/filesystems/caching/netfs-api.rst index 5066113acad5..1d18e9def183 100644 --- a/Documentation/filesystems/caching/netfs-api.rst +++ b/Documentation/filesystems/caching/netfs-api.rst @@ -404,22 +404,21 @@ schedule a write of that region:: And if an error occurs before that point is reached, the marks can be removed by calling:: - void fscache_clear_page_bits(struct fscache_cookie *cookie, - struct address_space *mapping, + void fscache_clear_page_bits(struct address_space *mapping, loff_t start, size_t len, bool caching) -In both of these functions, the cookie representing the cache object to be -written to and a pointer to the mapping to which the source pages are attached -are passed in; start and len indicate the size of the region that's going to be -written (it doesn't have to align to page boundaries necessarily, but it does -have to align to DIO boundaries on the backing filesystem). The caching -parameter indicates if caching should be skipped, and if false, the functions -do nothing. +In these functions, a pointer to the mapping to which the source pages are +attached is passed in and start and len indicate the size of the region that's +going to be written (it doesn't have to align to page boundaries necessarily, +but it does have to align to DIO boundaries on the backing filesystem). The +caching parameter indicates if caching should be skipped, and if false, the +functions do nothing. -The write function takes some additional parameters: i_size indicates the size -of the netfs file and term_func indicates an optional completion function, to -which term_func_priv will be passed, along with the error or amount written. +The write function takes some additional parameters: the cookie representing +the cache object to be written to, i_size indicates the size of the netfs file +and term_func indicates an optional completion function, to which +term_func_priv will be passed, along with the error or amount written. Note that the write function will always run asynchronously and will unmark all the pages upon completion before calling term_func. @@ -434,11 +433,11 @@ has done a write and then the page it wrote from has been released by the VM, after which it *has* to look in the cache. To inform fscache that a page might now be in the cache, the following function -should be called from the ``releasepage`` address space op:: +should be called from the ``release_folio`` address space op:: void fscache_note_page_release(struct fscache_cookie *cookie); -if the page has been released (ie. releasepage returned true). +if the page has been released (ie. release_folio returned true). Page release and page invalidation should also wait for any mark left on the page to say that a DIO write is underway from that page:: diff --git a/Documentation/filesystems/ext4/attributes.rst b/Documentation/filesystems/ext4/attributes.rst index 54386a010a8d..871d2da7a0a9 100644 --- a/Documentation/filesystems/ext4/attributes.rst +++ b/Documentation/filesystems/ext4/attributes.rst @@ -76,7 +76,7 @@ The beginning of an extended attribute block is in - Checksum of the extended attribute block. * - 0x14 - \_\_u32 - - h\_reserved[2] + - h\_reserved[3] - Zero. The checksum is calculated against the FS UUID, the 64-bit block number diff --git a/Documentation/filesystems/f2fs.rst b/Documentation/filesystems/f2fs.rst index 4a2426f0485a..ad8dc8c040a2 100644 --- a/Documentation/filesystems/f2fs.rst +++ b/Documentation/filesystems/f2fs.rst @@ -235,12 +235,6 @@ offgrpjquota Turn off group journalled quota. offprjjquota Turn off project journalled quota. quota Enable plain user disk quota accounting. noquota Disable all plain disk quota option. -whint_mode=%s Control which write hints are passed down to block - layer. This supports "off", "user-based", and - "fs-based". In "off" mode (default), f2fs does not pass - down hints. In "user-based" mode, f2fs tries to pass - down hints given by users. And in "fs-based" mode, f2fs - passes down hints with its policy. alloc_mode=%s Adjust block allocation policy, which supports "reuse" and "default". fsync_mode=%s Control the policy of fsync. Currently supports "posix", @@ -751,70 +745,6 @@ In order to identify whether the data in the victim segment are valid or not, F2FS manages a bitmap. Each bit represents the validity of a block, and the bitmap is composed of a bit stream covering whole blocks in main area. -Write-hint Policy ------------------ - -1) whint_mode=off. F2FS only passes down WRITE_LIFE_NOT_SET. - -2) whint_mode=user-based. F2FS tries to pass down hints given by -users. - -===================== ======================== =================== -User F2FS Block -===================== ======================== =================== -N/A META WRITE_LIFE_NOT_SET -N/A HOT_NODE " -N/A WARM_NODE " -N/A COLD_NODE " -ioctl(COLD) COLD_DATA WRITE_LIFE_EXTREME -extension list " " - --- buffered io -WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME -WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT -WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_NOT_SET -WRITE_LIFE_NONE " " -WRITE_LIFE_MEDIUM " " -WRITE_LIFE_LONG " " - --- direct io -WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME -WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT -WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_NOT_SET -WRITE_LIFE_NONE " WRITE_LIFE_NONE -WRITE_LIFE_MEDIUM " WRITE_LIFE_MEDIUM -WRITE_LIFE_LONG " WRITE_LIFE_LONG -===================== ======================== =================== - -3) whint_mode=fs-based. F2FS passes down hints with its policy. - -===================== ======================== =================== -User F2FS Block -===================== ======================== =================== -N/A META WRITE_LIFE_MEDIUM; -N/A HOT_NODE WRITE_LIFE_NOT_SET -N/A WARM_NODE " -N/A COLD_NODE WRITE_LIFE_NONE -ioctl(COLD) COLD_DATA WRITE_LIFE_EXTREME -extension list " " - --- buffered io -WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME -WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT -WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_LONG -WRITE_LIFE_NONE " " -WRITE_LIFE_MEDIUM " " -WRITE_LIFE_LONG " " - --- direct io -WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME -WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT -WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_NOT_SET -WRITE_LIFE_NONE " WRITE_LIFE_NONE -WRITE_LIFE_MEDIUM " WRITE_LIFE_MEDIUM -WRITE_LIFE_LONG " WRITE_LIFE_LONG -===================== ======================== =================== - Fallocate(2) Policy ------------------- diff --git a/Documentation/filesystems/fscrypt.rst b/Documentation/filesystems/fscrypt.rst index 6ccd5efb25b7..2e9aaa295125 100644 --- a/Documentation/filesystems/fscrypt.rst +++ b/Documentation/filesystems/fscrypt.rst @@ -1256,7 +1256,7 @@ inline encryption hardware will encrypt/decrypt the file contents. When inline encryption isn't used, filesystems must encrypt/decrypt the file contents themselves, as described below: -For the read path (->readpage()) of regular files, filesystems can +For the read path (->read_folio()) of regular files, filesystems can read the ciphertext into the page cache and decrypt it in-place. The page lock must be held until decryption has finished, to prevent the page from becoming visible to userspace prematurely. diff --git a/Documentation/filesystems/fsverity.rst b/Documentation/filesystems/fsverity.rst index 8cc536d08f51..756f2c215ba1 100644 --- a/Documentation/filesystems/fsverity.rst +++ b/Documentation/filesystems/fsverity.rst @@ -70,12 +70,23 @@ must live on a read-write filesystem because they are independently updated and potentially user-installed, so dm-verity cannot be used. The base fs-verity feature is a hashing mechanism only; actually -authenticating the files is up to userspace. However, to meet some -users' needs, fs-verity optionally supports a simple signature -verification mechanism where users can configure the kernel to require -that all fs-verity files be signed by a key loaded into a keyring; see -`Built-in signature verification`_. Support for fs-verity file hashes -in IMA (Integrity Measurement Architecture) policies is also planned. +authenticating the files may be done by: + +* Userspace-only + +* Builtin signature verification + userspace policy + + fs-verity optionally supports a simple signature verification + mechanism where users can configure the kernel to require that + all fs-verity files be signed by a key loaded into a keyring; + see `Built-in signature verification`_. + +* Integrity Measurement Architecture (IMA) + + IMA supports including fs-verity file digests and signatures in the + IMA measurement list and verifying fs-verity based file signatures + stored as security.ima xattrs, based on policy. + User API ======== @@ -548,7 +559,7 @@ already verified). Below, we describe how filesystems implement this. Pagecache ~~~~~~~~~ -For filesystems using Linux's pagecache, the ``->readpage()`` and +For filesystems using Linux's pagecache, the ``->read_folio()`` and ``->readahead()`` methods must be modified to verify pages before they are marked Uptodate. Merely hooking ``->read_iter()`` would be insufficient, since ``->read_iter()`` is not used for memory maps. @@ -653,12 +664,12 @@ weren't already directly answered in other parts of this document. hashed and what to do with those hashes, such as log them, authenticate them, or add them to a measurement list. - IMA is planned to support the fs-verity hashing mechanism as an - alternative to doing full file hashes, for people who want the - performance and security benefits of the Merkle tree based hash. - But it doesn't make sense to force all uses of fs-verity to be - through IMA. As a standalone filesystem feature, fs-verity - already meets many users' needs, and it's testable like other + IMA supports the fs-verity hashing mechanism as an alternative + to full file hashes, for those who want the performance and + security benefits of the Merkle tree based hash. However, it + doesn't make sense to force all uses of fs-verity to be through + IMA. fs-verity already meets many users' needs even as a + standalone filesystem feature, and it's testable like other filesystem features e.g. with xfstests. :Q: Isn't fs-verity useless because the attacker can just modify the diff --git a/Documentation/filesystems/idmappings.rst b/Documentation/filesystems/idmappings.rst index 7a879ec3b6bf..c1db8748389c 100644 --- a/Documentation/filesystems/idmappings.rst +++ b/Documentation/filesystems/idmappings.rst @@ -369,6 +369,11 @@ kernel maps the caller's userspace id down into a kernel id according to the caller's idmapping and then maps that kernel id up according to the filesystem's idmapping. +Let's see some examples with caller/filesystem idmapping but without mount +idmappings. This will exhibit some problems we can hit. After that we will +revisit/reconsider these examples, this time using mount idmappings, to see how +they can solve the problems we observed before. + Example 1 ~~~~~~~~~ diff --git a/Documentation/filesystems/locking.rst b/Documentation/filesystems/locking.rst index c26d854275a0..515bc48ab58b 100644 --- a/Documentation/filesystems/locking.rst +++ b/Documentation/filesystems/locking.rst @@ -237,20 +237,20 @@ address_space_operations prototypes:: int (*writepage)(struct page *page, struct writeback_control *wbc); - int (*readpage)(struct file *, struct page *); + int (*read_folio)(struct file *, struct folio *); int (*writepages)(struct address_space *, struct writeback_control *); bool (*dirty_folio)(struct address_space *, struct folio *folio); void (*readahead)(struct readahead_control *); int (*write_begin)(struct file *, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, + loff_t pos, unsigned len, struct page **pagep, void **fsdata); int (*write_end)(struct file *, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata); sector_t (*bmap)(struct address_space *, sector_t); void (*invalidate_folio) (struct folio *, size_t start, size_t len); - int (*releasepage) (struct page *, int); - void (*freepage)(struct page *); + bool (*release_folio)(struct folio *, gfp_t); + void (*free_folio)(struct folio *); int (*direct_IO)(struct kiocb *, struct iov_iter *iter); bool (*isolate_page) (struct page *, isolate_mode_t); int (*migratepage)(struct address_space *, struct page *, struct page *); @@ -262,22 +262,22 @@ prototypes:: int (*swap_deactivate)(struct file *); locking rules: - All except dirty_folio and freepage may block + All except dirty_folio and free_folio may block ====================== ======================== ========= =============== -ops PageLocked(page) i_rwsem invalidate_lock +ops folio locked i_rwsem invalidate_lock ====================== ======================== ========= =============== writepage: yes, unlocks (see below) -readpage: yes, unlocks shared +read_folio: yes, unlocks shared writepages: -dirty_folio maybe +dirty_folio: maybe readahead: yes, unlocks shared write_begin: locks the page exclusive write_end: yes, unlocks exclusive bmap: invalidate_folio: yes exclusive -releasepage: yes -freepage: yes +release_folio: yes +free_folio: yes direct_IO: isolate_page: yes migratepage: yes (both) @@ -289,13 +289,13 @@ swap_activate: no swap_deactivate: no ====================== ======================== ========= =============== -->write_begin(), ->write_end() and ->readpage() may be called from +->write_begin(), ->write_end() and ->read_folio() may be called from the request handler (/dev/loop). -->readpage() unlocks the page, either synchronously or via I/O +->read_folio() unlocks the folio, either synchronously or via I/O completion. -->readahead() unlocks the pages that I/O is attempted on like ->readpage(). +->readahead() unlocks the folios that I/O is attempted on like ->read_folio(). ->writepage() is used for two purposes: for "memory cleansing" and for "sync". These are quite different operations and the behaviour may differ @@ -372,12 +372,12 @@ invalidate_lock before invalidating page cache in truncate / hole punch path (and thus calling into ->invalidate_folio) to block races between page cache invalidation and page cache filling functions (fault, read, ...). -->releasepage() is called when the kernel is about to try to drop the -buffers from the page in preparation for freeing it. It returns zero to -indicate that the buffers are (or may be) freeable. If ->releasepage is zero, -the kernel assumes that the fs has no private interest in the buffers. +->release_folio() is called when the kernel is about to try to drop the +buffers from the folio in preparation for freeing it. It returns false to +indicate that the buffers are (or may be) freeable. If ->release_folio is +NULL, the kernel assumes that the fs has no private interest in the buffers. -->freepage() is called when the kernel is done dropping the page +->free_folio() is called when the kernel has dropped the folio from the page cache. ->launder_folio() may be called prior to releasing a folio if diff --git a/Documentation/filesystems/netfs_library.rst b/Documentation/filesystems/netfs_library.rst index 69f00179fdfe..a80a59941d2f 100644 --- a/Documentation/filesystems/netfs_library.rst +++ b/Documentation/filesystems/netfs_library.rst @@ -96,7 +96,7 @@ attached to an inode (or NULL if fscache is disabled):: Buffered Read Helpers ===================== -The library provides a set of read helpers that handle the ->readpage(), +The library provides a set of read helpers that handle the ->read_folio(), ->readahead() and much of the ->write_begin() VM operations and translate them into a common call framework. @@ -136,20 +136,19 @@ Read Helper Functions Three read helpers are provided:: void netfs_readahead(struct readahead_control *ractl); - int netfs_readpage(struct file *file, - struct page *page); + int netfs_read_folio(struct file *file, + struct folio *folio); int netfs_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned int len, - unsigned int flags, struct folio **_folio, void **_fsdata); Each corresponds to a VM address space operation. These operations use the state in the per-inode context. -For ->readahead() and ->readpage(), the network filesystem just point directly +For ->readahead() and ->read_folio(), the network filesystem just point directly at the corresponding read helper; whereas for ->write_begin(), it may be a little more complicated as the network filesystem might want to flush conflicting writes or track dirty data and needs to put the acquired folio if diff --git a/Documentation/filesystems/porting.rst b/Documentation/filesystems/porting.rst index 7c1583dbeb59..2e0e4f0e0c6f 100644 --- a/Documentation/filesystems/porting.rst +++ b/Documentation/filesystems/porting.rst @@ -624,7 +624,7 @@ any symlink that might use page_follow_link_light/page_put_link() must have inode_nohighmem(inode) called before anything might start playing with its pagecache. No highmem pages should end up in the pagecache of such symlinks. That includes any preseeding that might be done during symlink -creation. __page_symlink() will honour the mapping gfp flags, so once +creation. page_symlink() will honour the mapping gfp flags, so once you've done inode_nohighmem() it's safe to use, but if you allocate and insert the page manually, make sure to use the right gfp flags. diff --git a/Documentation/filesystems/proc.rst b/Documentation/filesystems/proc.rst index 061744c436d9..6a0dd99786f9 100644 --- a/Documentation/filesystems/proc.rst +++ b/Documentation/filesystems/proc.rst @@ -1183,85 +1183,7 @@ Provides counts of softirq handlers serviced since boot time, for each CPU. HRTIMER: 0 0 0 0 RCU: 1678 1769 2178 2250 - -1.3 IDE devices in /proc/ide ----------------------------- - -The subdirectory /proc/ide contains information about all IDE devices of which -the kernel is aware. There is one subdirectory for each IDE controller, the -file drivers and a link for each IDE device, pointing to the device directory -in the controller specific subtree. - -The file 'drivers' contains general information about the drivers used for the -IDE devices:: - - > cat /proc/ide/drivers - ide-cdrom version 4.53 - ide-disk version 1.08 - -More detailed information can be found in the controller specific -subdirectories. These are named ide0, ide1 and so on. Each of these -directories contains the files shown in table 1-6. - - -.. table:: Table 1-6: IDE controller info in /proc/ide/ide? - - ======= ======================================= - File Content - ======= ======================================= - channel IDE channel (0 or 1) - config Configuration (only for PCI/IDE bridge) - mate Mate name - model Type/Chipset of IDE controller - ======= ======================================= - -Each device connected to a controller has a separate subdirectory in the -controllers directory. The files listed in table 1-7 are contained in these -directories. - - -.. table:: Table 1-7: IDE device information - - ================ ========================================== - File Content - ================ ========================================== - cache The cache - capacity Capacity of the medium (in 512Byte blocks) - driver driver and version - geometry physical and logical geometry - identify device identify block - media media type - model device identifier - settings device setup - smart_thresholds IDE disk management thresholds - smart_values IDE disk management values - ================ ========================================== - -The most interesting file is ``settings``. This file contains a nice -overview of the drive parameters:: - - # cat /proc/ide/ide0/hda/settings - name value min max mode - ---- ----- --- --- ---- - bios_cyl 526 0 65535 rw - bios_head 255 0 255 rw - bios_sect 63 0 63 rw - breada_readahead 4 0 127 rw - bswap 0 0 1 r - file_readahead 72 0 2097151 rw - io_32bit 0 0 3 rw - keepsettings 0 0 1 rw - max_kb_per_request 122 1 127 rw - multcount 0 0 8 rw - nice1 1 0 1 rw - nowerr 0 0 1 rw - pio_mode write-only 0 255 w - slow 0 0 1 rw - unmaskirq 0 0 1 rw - using_dma 0 0 1 rw - - -1.4 Networking info in /proc/net +1.3 Networking info in /proc/net -------------------------------- The subdirectory /proc/net follows the usual pattern. Table 1-8 shows the @@ -1340,7 +1262,7 @@ It will contain information that is specific to that bond, such as the current slaves of the bond, the link status of the slaves, and how many times the slaves link has failed. -1.5 SCSI info +1.4 SCSI info ------------- If you have a SCSI host adapter in your system, you'll find a subdirectory @@ -1403,7 +1325,7 @@ AHA-2940 SCSI adapter:: Total transfers 0 (0 reads and 0 writes) -1.6 Parallel port info in /proc/parport +1.5 Parallel port info in /proc/parport --------------------------------------- The directory /proc/parport contains information about the parallel ports of @@ -1428,7 +1350,7 @@ These directories contain the four files shown in Table 1-10. number or none). ========= ==================================================================== -1.7 TTY info in /proc/tty +1.6 TTY info in /proc/tty ------------------------- Information about the available and actually used tty's can be found in the @@ -1463,7 +1385,7 @@ To see which tty's are currently in use, you can simply look into the file unknown /dev/tty 4 1-63 console -1.8 Miscellaneous kernel statistics in /proc/stat +1.7 Miscellaneous kernel statistics in /proc/stat ------------------------------------------------- Various pieces of information about kernel activity are available in the @@ -1536,7 +1458,7 @@ softirqs serviced; each subsequent column is the total for that particular softirq. -1.9 Ext4 file system parameters +1.8 Ext4 file system parameters ------------------------------- Information about mounted ext4 file systems can be found in @@ -1552,7 +1474,7 @@ in Table 1-12, below. mb_groups details of multiblock allocator buddy cache of free blocks ============== ========================================================== -1.10 /proc/consoles +1.9 /proc/consoles ------------------- Shows registered system console lines. diff --git a/Documentation/filesystems/vfs.rst b/Documentation/filesystems/vfs.rst index 794bd1a66bfb..12a011d2cbc6 100644 --- a/Documentation/filesystems/vfs.rst +++ b/Documentation/filesystems/vfs.rst @@ -620,9 +620,9 @@ Writeback. The first can be used independently to the others. The VM can try to either write dirty pages in order to clean them, or release clean pages in order to reuse them. To do this it can call the ->writepage method -on dirty pages, and ->releasepage on clean pages with PagePrivate set. -Clean pages without PagePrivate and with no external references will be -released without notice being given to the address_space. +on dirty pages, and ->release_folio on clean folios with the private +flag set. Clean pages without PagePrivate and with no external references +will be released without notice being given to the address_space. To achieve this functionality, pages need to be placed on an LRU with lru_cache_add and mark_page_active needs to be called whenever the page @@ -656,7 +656,7 @@ by memory-mapping the page. Data is written into the address space by the application, and then written-back to storage typically in whole pages, however the address_space has finer control of write sizes. -The read process essentially only requires 'readpage'. The write +The read process essentially only requires 'read_folio'. The write process is more complicated and uses write_begin/write_end or dirty_folio to write data into the address_space, and writepage and writepages to writeback data to storage. @@ -722,20 +722,20 @@ cache in your filesystem. The following members are defined: struct address_space_operations { int (*writepage)(struct page *page, struct writeback_control *wbc); - int (*readpage)(struct file *, struct page *); + int (*read_folio)(struct file *, struct folio *); int (*writepages)(struct address_space *, struct writeback_control *); bool (*dirty_folio)(struct address_space *, struct folio *); void (*readahead)(struct readahead_control *); int (*write_begin)(struct file *, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, + loff_t pos, unsigned len, struct page **pagep, void **fsdata); int (*write_end)(struct file *, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata); sector_t (*bmap)(struct address_space *, sector_t); void (*invalidate_folio) (struct folio *, size_t start, size_t len); - int (*releasepage) (struct page *, int); - void (*freepage)(struct page *); + bool (*release_folio)(struct folio *, gfp_t); + void (*free_folio)(struct folio *); ssize_t (*direct_IO)(struct kiocb *, struct iov_iter *iter); /* isolate a page for migration */ bool (*isolate_page) (struct page *, isolate_mode_t); @@ -747,7 +747,7 @@ cache in your filesystem. The following members are defined: bool (*is_partially_uptodate) (struct folio *, size_t from, size_t count); - void (*is_dirty_writeback) (struct page *, bool *, bool *); + void (*is_dirty_writeback)(struct folio *, bool *, bool *); int (*error_remove_page) (struct mapping *mapping, struct page *page); int (*swap_activate)(struct file *); int (*swap_deactivate)(struct file *); @@ -772,14 +772,14 @@ cache in your filesystem. The following members are defined: See the file "Locking" for more details. -``readpage`` - called by the VM to read a page from backing store. The page - will be Locked when readpage is called, and should be unlocked - and marked uptodate once the read completes. If ->readpage - discovers that it needs to unlock the page for some reason, it - can do so, and then return AOP_TRUNCATED_PAGE. In this case, - the page will be relocated, relocked and if that all succeeds, - ->readpage will be called again. +``read_folio`` + called by the VM to read a folio from backing store. The folio + will be locked when read_folio is called, and should be unlocked + and marked uptodate once the read completes. If ->read_folio + discovers that it cannot perform the I/O at this time, it can + unlock the folio and return AOP_TRUNCATED_PAGE. In this case, + the folio will be looked up again, relocked and if that all succeeds, + ->read_folio will be called again. ``writepages`` called by the VM to write out pages associated with the @@ -832,9 +832,6 @@ cache in your filesystem. The following members are defined: passed to write_begin is greater than the number of bytes copied into the page). - flags is a field for AOP_FLAG_xxx flags, described in - include/linux/fs.h. - A void * may be returned in fsdata, which then gets passed into write_end. @@ -867,36 +864,35 @@ cache in your filesystem. The following members are defined: address space. This generally corresponds to either a truncation, punch hole or a complete invalidation of the address space (in the latter case 'offset' will always be 0 and 'length' - will be folio_size()). Any private data associated with the page + will be folio_size()). Any private data associated with the folio should be updated to reflect this truncation. If offset is 0 and length is folio_size(), then the private data should be - released, because the page must be able to be completely - discarded. This may be done by calling the ->releasepage + released, because the folio must be able to be completely + discarded. This may be done by calling the ->release_folio function, but in this case the release MUST succeed. -``releasepage`` - releasepage is called on PagePrivate pages to indicate that the - page should be freed if possible. ->releasepage should remove - any private data from the page and clear the PagePrivate flag. - If releasepage() fails for some reason, it must indicate failure - with a 0 return value. releasepage() is used in two distinct - though related cases. The first is when the VM finds a clean - page with no active users and wants to make it a free page. If - ->releasepage succeeds, the page will be removed from the - address_space and become free. +``release_folio`` + release_folio is called on folios with private data to tell the + filesystem that the folio is about to be freed. ->release_folio + should remove any private data from the folio and clear the + private flag. If release_folio() fails, it should return false. + release_folio() is used in two distinct though related cases. + The first is when the VM wants to free a clean folio with no + active users. If ->release_folio succeeds, the folio will be + removed from the address_space and be freed. The second case is when a request has been made to invalidate - some or all pages in an address_space. This can happen through - the fadvise(POSIX_FADV_DONTNEED) system call or by the - filesystem explicitly requesting it as nfs and 9fs do (when they + some or all folios in an address_space. This can happen + through the fadvise(POSIX_FADV_DONTNEED) system call or by the + filesystem explicitly requesting it as nfs and 9p do (when they believe the cache may be out of date with storage) by calling invalidate_inode_pages2(). If the filesystem makes such a call, - and needs to be certain that all pages are invalidated, then its - releasepage will need to ensure this. Possibly it can clear the - PageUptodate bit if it cannot free private data yet. + and needs to be certain that all folios are invalidated, then + its release_folio will need to ensure this. Possibly it can + clear the uptodate flag if it cannot free private data yet. -``freepage`` - freepage is called once the page is no longer visible in the +``free_folio`` + free_folio is called once the folio is no longer visible in the page cache in order to allow the cleanup of any private data. Since it may be called by the memory reclaimer, it should not assume that the original address_space mapping still exists, and @@ -935,14 +931,14 @@ cache in your filesystem. The following members are defined: without needing I/O to bring the whole page up to date. ``is_dirty_writeback`` - Called by the VM when attempting to reclaim a page. The VM uses + Called by the VM when attempting to reclaim a folio. The VM uses dirty and writeback information to determine if it needs to stall to allow flushers a chance to complete some IO. - Ordinarily it can use PageDirty and PageWriteback but some - filesystems have more complex state (unstable pages in NFS + Ordinarily it can use folio_test_dirty and folio_test_writeback but + some filesystems have more complex state (unstable folios in NFS prevent reclaim) or do not set those flags due to locking problems. This callback allows a filesystem to indicate to the - VM if a page should be treated as dirty or writeback for the + VM if a folio should be treated as dirty or writeback for the purposes of stalling. ``error_remove_page`` diff --git a/Documentation/filesystems/zonefs.rst b/Documentation/filesystems/zonefs.rst index 6b213fe9a33e..394b9f15dce0 100644 --- a/Documentation/filesystems/zonefs.rst +++ b/Documentation/filesystems/zonefs.rst @@ -306,8 +306,15 @@ Further notes: Mount options ------------- -zonefs define the "errors=<behavior>" mount option to allow the user to specify -zonefs behavior in response to I/O errors, inode size inconsistencies or zone +zonefs defines several mount options: +* errors=<behavior> +* explicit-open + +"errors=<behavior>" option +~~~~~~~~~~~~~~~~~~~~~~~~~~ + +The "errors=<behavior>" option mount option allows the user to specify zonefs +behavior in response to I/O errors, inode size inconsistencies or zone condition changes. The defined behaviors are as follow: * remount-ro (default) @@ -326,6 +333,9 @@ discover the amount of data that has been written to the zone. In the case of a read-only zone discovered at run-time, as indicated in the previous section. The size of the zone file is left unchanged from its last updated value. +"explicit-open" option +~~~~~~~~~~~~~~~~~~~~~~ + A zoned block device (e.g. an NVMe Zoned Namespace device) may have limits on the number of zones that can be active, that is, zones that are in the implicit open, explicit open or closed conditions. This potential limitation @@ -341,6 +351,44 @@ guaranteed that write requests can be processed. Conversely, the to the device on the last close() of a zone file if the zone is not full nor empty. +Runtime sysfs attributes +------------------------ + +zonefs defines several sysfs attributes for mounted devices. All attributes +are user readable and can be found in the directory /sys/fs/zonefs/<dev>/, +where <dev> is the name of the mounted zoned block device. + +The attributes defined are as follows. + +* **max_wro_seq_files**: This attribute reports the maximum number of + sequential zone files that can be open for writing. This number corresponds + to the maximum number of explicitly or implicitly open zones that the device + supports. A value of 0 means that the device has no limit and that any zone + (any file) can be open for writing and written at any time, regardless of the + state of other zones. When the *explicit-open* mount option is used, zonefs + will fail any open() system call requesting to open a sequential zone file for + writing when the number of sequential zone files already open for writing has + reached the *max_wro_seq_files* limit. +* **nr_wro_seq_files**: This attribute reports the current number of sequential + zone files open for writing. When the "explicit-open" mount option is used, + this number can never exceed *max_wro_seq_files*. If the *explicit-open* + mount option is not used, the reported number can be greater than + *max_wro_seq_files*. In such case, it is the responsibility of the + application to not write simultaneously more than *max_wro_seq_files* + sequential zone files. Failure to do so can result in write errors. +* **max_active_seq_files**: This attribute reports the maximum number of + sequential zone files that are in an active state, that is, sequential zone + files that are partially writen (not empty nor full) or that have a zone that + is explicitly open (which happens only if the *explicit-open* mount option is + used). This number is always equal to the maximum number of active zones that + the device supports. A value of 0 means that the mounted device has no limit + on the number of sequential zone files that can be active. +* **nr_active_seq_files**: This attributes reports the current number of + sequential zone files that are active. If *max_active_seq_files* is not 0, + then the value of *nr_active_seq_files* can never exceed the value of + *nr_active_seq_files*, regardless of the use of the *explicit-open* mount + option. + Zonefs User Space Tools ======================= diff --git a/Documentation/firmware-guide/acpi/enumeration.rst b/Documentation/firmware-guide/acpi/enumeration.rst index 47fb4d6d4557..6b62425ef9cd 100644 --- a/Documentation/firmware-guide/acpi/enumeration.rst +++ b/Documentation/firmware-guide/acpi/enumeration.rst @@ -167,8 +167,7 @@ The table below shows an example of its usage:: Name (_DSD, Package () { ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"), Package () { - Package () {"interrupt-names", - Package (2) {"default", "alert"}}, + Package () { "interrupt-names", Package () { "default", "alert" } }, } ... }) diff --git a/Documentation/hwmon/aquacomputer_d5next.rst b/Documentation/hwmon/aquacomputer_d5next.rst index 3373e27b707d..717e28226cde 100644 --- a/Documentation/hwmon/aquacomputer_d5next.rst +++ b/Documentation/hwmon/aquacomputer_d5next.rst @@ -6,7 +6,9 @@ Kernel driver aquacomputer-d5next Supported devices: * Aquacomputer D5 Next watercooling pump +* Aquacomputer Farbwerk RGB controller * Aquacomputer Farbwerk 360 RGB controller +* Aquacomputer Octo fan controller Author: Aleksa Savic @@ -28,7 +30,10 @@ seems to require sending it a complete configuration. That includes addressable RGB LEDs, for which there is no standard sysfs interface. Thus, that task is better suited for userspace tools. -The Farbwerk 360 exposes four temperature sensors. Depending on the device, +The Octo exposes four temperature sensors and eight PWM controllable fans, along +with their speed (in RPM), power, voltage and current. + +The Farbwerk and Farbwerk 360 expose four temperature sensors. Depending on the device, not all sysfs and debugfs entries will be available. Usage notes diff --git a/Documentation/hwmon/asus_ec_sensors.rst b/Documentation/hwmon/asus_ec_sensors.rst index e7e8f1640f45..78ca69eda877 100644 --- a/Documentation/hwmon/asus_ec_sensors.rst +++ b/Documentation/hwmon/asus_ec_sensors.rst @@ -4,17 +4,20 @@ Kernel driver asus_ec_sensors ================================= Supported boards: - * PRIME X570-PRO, - * Pro WS X570-ACE, - * ROG CROSSHAIR VIII DARK HERO, + * PRIME X470-PRO + * PRIME X570-PRO + * Pro WS X570-ACE + * ProArt X570-CREATOR WIFI + * ROG CROSSHAIR VIII DARK HERO * ROG CROSSHAIR VIII HERO (WI-FI) - * ROG CROSSHAIR VIII FORMULA, - * ROG CROSSHAIR VIII HERO, - * ROG CROSSHAIR VIII IMPACT, - * ROG STRIX B550-E GAMING, - * ROG STRIX B550-I GAMING, - * ROG STRIX X570-E GAMING, - * ROG STRIX X570-F GAMING, + * ROG CROSSHAIR VIII FORMULA + * ROG CROSSHAIR VIII HERO + * ROG CROSSHAIR VIII IMPACT + * ROG STRIX B550-E GAMING + * ROG STRIX B550-I GAMING + * ROG STRIX X570-E GAMING + * ROG STRIX X570-E GAMING WIFI II + * ROG STRIX X570-F GAMING * ROG STRIX X570-I GAMING Authors: @@ -52,3 +55,5 @@ Module Parameters the path is mostly identical for them). If ASUS changes this path in a future BIOS update, this parameter can be used to override the stored in the driver value until it gets updated. + A special string ":GLOBAL_LOCK" can be passed to use the ACPI + global lock instead of a dedicated mutex. diff --git a/Documentation/hwmon/dell-smm-hwmon.rst b/Documentation/hwmon/dell-smm-hwmon.rst index d3323a96665d..e5d85e40972c 100644 --- a/Documentation/hwmon/dell-smm-hwmon.rst +++ b/Documentation/hwmon/dell-smm-hwmon.rst @@ -86,6 +86,13 @@ probe the BIOS on your machine and discover the appropriate codes. Again, when you find new codes, we'd be happy to have your patches! +``thermal`` interface +--------------------------- + +The driver also exports the fans as thermal cooling devices with +``type`` set to ``dell-smm-fan[1-3]``. This allows for easy fan control +using one of the thermal governors. + Module parameters ----------------- @@ -324,6 +331,8 @@ Reading of fan types causes erratic fan behaviour. Studio XPS 8000 Inspiron 580 + Inspiron 3505 + Fan-related SMM calls take too long (about 500ms). Inspiron 7720 Vostro 3360 diff --git a/Documentation/hwmon/hwmon-kernel-api.rst b/Documentation/hwmon/hwmon-kernel-api.rst index c41eb6108103..f3276b3a381a 100644 --- a/Documentation/hwmon/hwmon-kernel-api.rst +++ b/Documentation/hwmon/hwmon-kernel-api.rst @@ -50,6 +50,10 @@ register/unregister functions:: void devm_hwmon_device_unregister(struct device *dev); + char *hwmon_sanitize_name(const char *name); + + char *devm_hwmon_sanitize_name(struct device *dev, const char *name); + hwmon_device_register_with_groups registers a hardware monitoring device. The first parameter of this function is a pointer to the parent device. The name parameter is a pointer to the hwmon device name. The registration @@ -72,7 +76,7 @@ hwmon_device_register_with_info is the most comprehensive and preferred means to register a hardware monitoring device. It creates the standard sysfs attributes in the hardware monitoring core, letting the driver focus on reading from and writing to the chip instead of having to bother with sysfs attributes. -The parent device parameter cannot be NULL with non-NULL chip info. Its +The parent device parameter as well as the chip parameter must not be NULL. Its parameters are described in more detail below. devm_hwmon_device_register_with_info is similar to @@ -95,6 +99,18 @@ All supported hwmon device registration functions only accept valid device names. Device names including invalid characters (whitespace, '*', or '-') will be rejected. The 'name' parameter is mandatory. +If the driver doesn't use a static device name (for example it uses +dev_name()), and therefore cannot make sure the name only contains valid +characters, hwmon_sanitize_name can be used. This convenience function +will duplicate the string and replace any invalid characters with an +underscore. It will allocate memory for the new string and it is the +responsibility of the caller to release the memory when the device is +removed. + +devm_hwmon_sanitize_name is the resource managed version of +hwmon_sanitize_name; the memory will be freed automatically on device +removal. + Using devm_hwmon_device_register_with_info() -------------------------------------------- diff --git a/Documentation/hwmon/index.rst b/Documentation/hwmon/index.rst index 863b76289159..a72c16872ec2 100644 --- a/Documentation/hwmon/index.rst +++ b/Documentation/hwmon/index.rst @@ -90,6 +90,7 @@ Hardware Monitoring Kernel Drivers jc42 k10temp k8temp + lan966x lineage-pem lm25066 lm63 @@ -223,6 +224,7 @@ Hardware Monitoring Kernel Drivers wm8350 xgene-hwmon xdpe12284 + xdpe152c4 zl6100 .. only:: subproject and html diff --git a/Documentation/hwmon/lan966x.rst b/Documentation/hwmon/lan966x.rst new file mode 100644 index 000000000000..1d1724afa5d2 --- /dev/null +++ b/Documentation/hwmon/lan966x.rst @@ -0,0 +1,40 @@ +.. SPDX-License-Identifier: GPL-2.0 + +Kernel driver lan966x-hwmon +=========================== + +Supported chips: + + * Microchip LAN9668 (sensor in SoC) + + Prefix: 'lan9668-hwmon' + + Datasheet: https://microchip-ung.github.io/lan9668_reginfo + +Authors: + + Michael Walle <michael@walle.cc> + +Description +----------- + +This driver implements support for the Microchip LAN9668 on-chip +temperature sensor as well as its fan controller. It provides one +temperature sensor and one fan controller. The temperature range +of the sensor is specified from -40 to +125 degrees Celsius and +its accuracy is +/- 5 degrees Celsius. The fan controller has a +tacho input and a PWM output with a customizable PWM output +frequency ranging from ~20Hz to ~650kHz. + +No alarms are supported by the SoC. + +The driver exports temperature values, fan tacho input and PWM +settings via the following sysfs files: + +**temp1_input** + +**fan1_input** + +**pwm1** + +**pwm1_freq** diff --git a/Documentation/hwmon/max16601.rst b/Documentation/hwmon/max16601.rst index 92c0a7d7808c..6a4eef8efbaf 100644 --- a/Documentation/hwmon/max16601.rst +++ b/Documentation/hwmon/max16601.rst @@ -21,6 +21,14 @@ Supported chips: Datasheet: Not published + * Maxim MAX16602 + + Prefix: 'max16602' + + Addresses scanned: - + + Datasheet: https://datasheets.maximintegrated.com/en/ds/MAX16602.pdf + Author: Guenter Roeck <linux@roeck-us.net> diff --git a/Documentation/hwmon/xdpe152c4.rst b/Documentation/hwmon/xdpe152c4.rst new file mode 100644 index 000000000000..ab92c32d4d69 --- /dev/null +++ b/Documentation/hwmon/xdpe152c4.rst @@ -0,0 +1,118 @@ +.. SPDX-License-Identifier: GPL-2.0 + +Kernel driver xdpe152 +===================== + +Supported chips: + + * Infineon XDPE152C4 + + Prefix: 'xdpe152c4' + + * Infineon XDPE15284 + + Prefix: 'xdpe15284' + +Authors: + + Greg Schwendimann <greg.schwendimann@infineon.com> + +Description +----------- + +This driver implements support for Infineon Digital Multi-phase Controller +XDPE152C4 and XDPE15284 dual loop voltage regulators. +The devices are compliant with: + +- Intel VR13, VR13HC and VR14 rev 1.86 + converter specification. +- Intel SVID rev 1.93. protocol. +- PMBus rev 1.3.1 interface. + +Devices support linear format for reading input and output voltage, input +and output current, input and output power and temperature. + +Devices support two pages for telemetry. + +The driver provides for current: input, maximum and critical thresholds +and maximum and critical alarms. Low Critical thresholds and Low critical alarm are +supported only for current output. +The driver exports the following attributes for via the sysfs files, where +indexes 1, 2 are for "iin" and 3, 4 for "iout": + +**curr[1-4]_crit** + +**curr[1-4]_crit_alarm** + +**curr[1-4]_input** + +**curr[1-4]_label** + +**curr[1-4]_max** + +**curr[1-4]_max_alarm** + +**curr[3-4]_lcrit** + +**curr[3-4]_lcrit_alarm** + +**curr[3-4]_rated_max** + +The driver provides for voltage: input, critical and low critical thresholds +and critical and low critical alarms. +The driver exports the following attributes for via the sysfs files, where +indexes 1, 2 are for "vin" and 3, 4 for "vout": + +**in[1-4]_min** + +**in[1-4]_crit** + +**in[1-4_crit_alarm** + +**in[1-4]_input** + +**in[1-4]_label** + +**in[1-4]_max** + +**in[1-4]_max_alarm** + +**in[1-4]_min** + +**in[1-4]_min_alarm** + +**in[3-4]_lcrit** + +**in[3-4]_lcrit_alarm** + +**in[3-4]_rated_max** + +**in[3-4]_rated_min** + +The driver provides for power: input and alarms. +The driver exports the following attributes for via the sysfs files, where +indexes 1, 2 are for "pin" and 3, 4 for "pout": + +**power[1-2]_alarm** + +**power[1-4]_input** + +**power[1-4]_label** + +**power[1-4]_max** + +**power[1-4]_rated_max** + +The driver provides for temperature: input, maximum and critical thresholds +and maximum and critical alarms. +The driver exports the following attributes for via the sysfs files: + +**temp[1-2]_crit** + +**temp[1-2]_crit_alarm** + +**temp[1-2]_input** + +**temp[1-2]_max** + +**temp[1-2]_max_alarm** diff --git a/Documentation/kbuild/reproducible-builds.rst b/Documentation/kbuild/reproducible-builds.rst index 3b25655e441b..071f0151a7a4 100644 --- a/Documentation/kbuild/reproducible-builds.rst +++ b/Documentation/kbuild/reproducible-builds.rst @@ -99,10 +99,10 @@ unreproducible parts can be treated as sources: Structure randomisation ----------------------- -If you enable ``CONFIG_GCC_PLUGIN_RANDSTRUCT``, you will need to -pre-generate the random seed in -``scripts/gcc-plugins/randomize_layout_seed.h`` so the same value -is used in rebuilds. +If you enable ``CONFIG_RANDSTRUCT``, you will need to pre-generate +the random seed in ``scripts/basic/randstruct.seed`` so the same +value is used by each build. See ``scripts/gen-randstruct-seed.sh`` +for details. Debug info conflicts -------------------- diff --git a/Documentation/networking/bonding.rst b/Documentation/networking/bonding.rst index 525e6842dd33..43be3782e5df 100644 --- a/Documentation/networking/bonding.rst +++ b/Documentation/networking/bonding.rst @@ -894,7 +894,7 @@ xmit_hash_policy Uses XOR of hardware MAC addresses and packet type ID field to generate the hash. The formula is - hash = source MAC XOR destination MAC XOR packet type ID + hash = source MAC[5] XOR destination MAC[5] XOR packet type ID slave number = hash modulo slave count This algorithm will place all traffic to a particular @@ -910,7 +910,7 @@ xmit_hash_policy Uses XOR of hardware MAC addresses and IP addresses to generate the hash. The formula is - hash = source MAC XOR destination MAC XOR packet type ID + hash = source MAC[5] XOR destination MAC[5] XOR packet type ID hash = hash XOR source IP XOR destination IP hash = hash XOR (hash RSHIFT 16) hash = hash XOR (hash RSHIFT 8) diff --git a/Documentation/networking/dsa/dsa.rst b/Documentation/networking/dsa/dsa.rst index 89bb4fa4c362..ddc1dd039337 100644 --- a/Documentation/networking/dsa/dsa.rst +++ b/Documentation/networking/dsa/dsa.rst @@ -10,21 +10,21 @@ in joining the effort. Design principles ================= -The Distributed Switch Architecture is a subsystem which was primarily designed -to support Marvell Ethernet switches (MV88E6xxx, a.k.a Linkstreet product line) -using Linux, but has since evolved to support other vendors as well. +The Distributed Switch Architecture subsystem was primarily designed to +support Marvell Ethernet switches (MV88E6xxx, a.k.a. Link Street product +line) using Linux, but has since evolved to support other vendors as well. The original philosophy behind this design was to be able to use unmodified Linux tools such as bridge, iproute2, ifconfig to work transparently whether they configured/queried a switch port network device or a regular network device. -An Ethernet switch is typically comprised of multiple front-panel ports, and one -or more CPU or management port. The DSA subsystem currently relies on the +An Ethernet switch typically comprises multiple front-panel ports and one +or more CPU or management ports. The DSA subsystem currently relies on the presence of a management port connected to an Ethernet controller capable of receiving Ethernet frames from the switch. This is a very common setup for all kinds of Ethernet switches found in Small Home and Office products: routers, -gateways, or even top-of-the rack switches. This host Ethernet controller will +gateways, or even top-of-rack switches. This host Ethernet controller will be later referred to as "master" and "cpu" in DSA terminology and code. The D in DSA stands for Distributed, because the subsystem has been designed @@ -33,14 +33,14 @@ using upstream and downstream Ethernet links between switches. These specific ports are referred to as "dsa" ports in DSA terminology and code. A collection of multiple switches connected to each other is called a "switch tree". -For each front-panel port, DSA will create specialized network devices which are +For each front-panel port, DSA creates specialized network devices which are used as controlling and data-flowing endpoints for use by the Linux networking stack. These specialized network interfaces are referred to as "slave" network interfaces in DSA terminology and code. The ideal case for using DSA is when an Ethernet switch supports a "switch tag" which is a hardware feature making the switch insert a specific tag for each -Ethernet frames it received to/from specific ports to help the management +Ethernet frame it receives to/from specific ports to help the management interface figure out: - what port is this frame coming from @@ -125,7 +125,7 @@ other switches from the same fabric, and in this case, the outermost switch ports must decapsulate the packet. Note that in certain cases, it might be the case that the tagging format used -by a leaf switch (not connected directly to the CPU) to not be the same as what +by a leaf switch (not connected directly to the CPU) is not the same as what the network stack sees. This can be seen with Marvell switch trees, where the CPU port can be configured to use either the DSA or the Ethertype DSA (EDSA) format, but the DSA links are configured to use the shorter (without Ethertype) @@ -270,21 +270,21 @@ These interfaces are specialized in order to: to/from specific switch ports - query the switch for ethtool operations: statistics, link state, Wake-on-LAN, register dumps... -- external/internal PHY management: link, auto-negotiation etc. +- manage external/internal PHY: link, auto-negotiation, etc. These slave network devices have custom net_device_ops and ethtool_ops function pointers which allow DSA to introduce a level of layering between the networking -stack/ethtool, and the switch driver implementation. +stack/ethtool and the switch driver implementation. Upon frame transmission from these slave network devices, DSA will look up which -switch tagging protocol is currently registered with these network devices, and +switch tagging protocol is currently registered with these network devices and invoke a specific transmit routine which takes care of adding the relevant switch tag in the Ethernet frames. These frames are then queued for transmission using the master network device -``ndo_start_xmit()`` function, since they contain the appropriate switch tag, the +``ndo_start_xmit()`` function. Since they contain the appropriate switch tag, the Ethernet switch will be able to process these incoming frames from the -management interface and delivers these frames to the physical switch port. +management interface and deliver them to the physical switch port. Graphical representation ------------------------ @@ -330,9 +330,9 @@ MDIO reads/writes towards specific PHY addresses. In most MDIO-connected switches, these functions would utilize direct or indirect PHY addressing mode to return standard MII registers from the switch builtin PHYs, allowing the PHY library and/or to return link status, link partner pages, auto-negotiation -results etc.. +results, etc. -For Ethernet switches which have both external and internal MDIO busses, the +For Ethernet switches which have both external and internal MDIO buses, the slave MII bus can be utilized to mux/demux MDIO reads and writes towards either internal or external MDIO devices this switch might be connected to: internal PHYs, external PHYs, or even external switches. @@ -349,7 +349,7 @@ DSA data structures are defined in ``include/net/dsa.h`` as well as table indication (when cascading switches) - ``dsa_platform_data``: platform device configuration data which can reference - a collection of dsa_chip_data structure if multiples switches are cascaded, + a collection of dsa_chip_data structures if multiple switches are cascaded, the master network device this switch tree is attached to needs to be referenced @@ -426,7 +426,7 @@ logic basically looks like this: "phy-handle" property, if found, this PHY device is created and registered using ``of_phy_connect()`` -- if Device Tree is used, and the PHY device is "fixed", that is, conforms to +- if Device Tree is used and the PHY device is "fixed", that is, conforms to the definition of a non-MDIO managed PHY as defined in ``Documentation/devicetree/bindings/net/fixed-link.txt``, the PHY is registered and connected transparently using the special fixed MDIO bus driver @@ -481,7 +481,7 @@ Device Tree DSA features a standardized binding which is documented in ``Documentation/devicetree/bindings/net/dsa/dsa.txt``. PHY/MDIO library helper functions such as ``of_get_phy_mode()``, ``of_phy_connect()`` are also used to query -per-port PHY specific details: interface connection, MDIO bus location etc.. +per-port PHY specific details: interface connection, MDIO bus location, etc. Driver development ================== @@ -509,7 +509,7 @@ Switch configuration - ``setup``: setup function for the switch, this function is responsible for setting up the ``dsa_switch_ops`` private structure with all it needs: register maps, - interrupts, mutexes, locks etc.. This function is also expected to properly + interrupts, mutexes, locks, etc. This function is also expected to properly configure the switch to separate all network interfaces from each other, that is, they should be isolated by the switch hardware itself, typically by creating a Port-based VLAN ID for each port and allowing only the CPU port and the @@ -526,13 +526,13 @@ PHY devices and link management - ``get_phy_flags``: Some switches are interfaced to various kinds of Ethernet PHYs, if the PHY library PHY driver needs to know about information it cannot obtain on its own (e.g.: coming from switch memory mapped registers), this function - should return a 32-bits bitmask of "flags", that is private between the switch + should return a 32-bit bitmask of "flags" that is private between the switch driver and the Ethernet PHY driver in ``drivers/net/phy/\*``. - ``phy_read``: Function invoked by the DSA slave MDIO bus when attempting to read the switch port MDIO registers. If unavailable, return 0xffff for each read. For builtin switch Ethernet PHYs, this function should allow reading the link - status, auto-negotiation results, link partner pages etc.. + status, auto-negotiation results, link partner pages, etc. - ``phy_write``: Function invoked by the DSA slave MDIO bus when attempting to write to the switch port MDIO registers. If unavailable return a negative error @@ -554,7 +554,7 @@ Ethtool operations ------------------ - ``get_strings``: ethtool function used to query the driver's strings, will - typically return statistics strings, private flags strings etc. + typically return statistics strings, private flags strings, etc. - ``get_ethtool_stats``: ethtool function used to query per-port statistics and return their values. DSA overlays slave network devices general statistics: @@ -564,7 +564,7 @@ Ethtool operations - ``get_sset_count``: ethtool function used to query the number of statistics items - ``get_wol``: ethtool function used to obtain Wake-on-LAN settings per-port, this - function may, for certain implementations also query the master network device + function may for certain implementations also query the master network device Wake-on-LAN settings if this interface needs to participate in Wake-on-LAN - ``set_wol``: ethtool function used to configure Wake-on-LAN settings per-port, @@ -607,14 +607,14 @@ Power management in a fully active state - ``port_enable``: function invoked by the DSA slave network device ndo_open - function when a port is administratively brought up, this function should be - fully enabling a given switch port. DSA takes care of marking the port with + function when a port is administratively brought up, this function should + fully enable a given switch port. DSA takes care of marking the port with ``BR_STATE_BLOCKING`` if the port is a bridge member, or ``BR_STATE_FORWARDING`` if it was not, and propagating these changes down to the hardware - ``port_disable``: function invoked by the DSA slave network device ndo_close - function when a port is administratively brought down, this function should be - fully disabling a given switch port. DSA takes care of marking the port with + function when a port is administratively brought down, this function should + fully disable a given switch port. DSA takes care of marking the port with ``BR_STATE_DISABLED`` and propagating changes to the hardware if this port is disabled while being a bridge member @@ -622,12 +622,12 @@ Bridge layer ------------ - ``port_bridge_join``: bridge layer function invoked when a given switch port is - added to a bridge, this function should be doing the necessary at the switch - level to permit the joining port from being added to the relevant logical + added to a bridge, this function should do what's necessary at the switch + level to permit the joining port to be added to the relevant logical domain for it to ingress/egress traffic with other members of the bridge. - ``port_bridge_leave``: bridge layer function invoked when a given switch port is - removed from a bridge, this function should be doing the necessary at the + removed from a bridge, this function should do what's necessary at the switch level to deny the leaving port from ingress/egress traffic from the remaining bridge members. When the port leaves the bridge, it should be aged out at the switch hardware for the switch to (re) learn MAC addresses behind @@ -663,7 +663,7 @@ Bridge layer point for drivers that need to configure the hardware for enabling this feature. -- ``port_bridge_tx_fwd_unoffload``: bridge layer function invoken when a driver +- ``port_bridge_tx_fwd_unoffload``: bridge layer function invoked when a driver leaves a bridge port which had the TX forwarding offload feature enabled. Bridge VLAN filtering diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index b0024aa7b051..66828293d9cb 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -267,6 +267,13 @@ ipfrag_max_dist - INTEGER from different IP datagrams, which could result in data corruption. Default: 64 +bc_forwarding - INTEGER + bc_forwarding enables the feature described in rfc1812#section-5.3.5.2 + and rfc2644. It allows the router to forward directed broadcast. + To enable this feature, the 'all' entry and the input interface entry + should be set to 1. + Default: 0 + INET peer storage ================= diff --git a/Documentation/power/energy-model.rst b/Documentation/power/energy-model.rst index 49549aab41b4..feb257b7f350 100644 --- a/Documentation/power/energy-model.rst +++ b/Documentation/power/energy-model.rst @@ -123,6 +123,26 @@ allows a platform to register EM power values which are reflecting total power (static + dynamic). These power values might be coming directly from experiments and measurements. +Registration of 'artificial' EM +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +There is an option to provide a custom callback for drivers missing detailed +knowledge about power value for each performance state. The callback +.get_cost() is optional and provides the 'cost' values used by the EAS. +This is useful for platforms that only provide information on relative +efficiency between CPU types, where one could use the information to +create an abstract power model. But even an abstract power model can +sometimes be hard to fit in, given the input power value size restrictions. +The .get_cost() allows to provide the 'cost' values which reflect the +efficiency of the CPUs. This would allow to provide EAS information which +has different relation than what would be forced by the EM internal +formulas calculating 'cost' values. To register an EM for such platform, the +driver must set the flag 'milliwatts' to 0, provide .get_power() callback +and provide .get_cost() callback. The EM framework would handle such platform +properly during registration. A flag EM_PERF_DOMAIN_ARTIFICIAL is set for such +platform. Special care should be taken by other frameworks which are using EM +to test and treat this flag properly. + Registration of 'simple' EM ~~~~~~~~~~~~~~~~~~~~~~~~~~~ @@ -181,8 +201,8 @@ EM framework:: -> drivers/cpufreq/foo_cpufreq.c - 01 static int est_power(unsigned long *mW, unsigned long *KHz, - 02 struct device *dev) + 01 static int est_power(struct device *dev, unsigned long *mW, + 02 unsigned long *KHz) 03 { 04 long freq, power; 05 diff --git a/Documentation/process/embargoed-hardware-issues.rst b/Documentation/process/embargoed-hardware-issues.rst index 41a2afaaea75..95999302d279 100644 --- a/Documentation/process/embargoed-hardware-issues.rst +++ b/Documentation/process/embargoed-hardware-issues.rst @@ -244,10 +244,11 @@ disclosure of a particular issue, unless requested by a response team or by an involved disclosed party. The current ambassadors list: ============= ======================================================== - ARM Catalin Marinas <catalin.marinas@arm.com> AMD Tom Lendacky <tom.lendacky@amd.com> - IBM Z Christian Borntraeger <borntraeger@de.ibm.com> - IBM Power Anton Blanchard <anton@linux.ibm.com> + Ampere Darren Hart <darren@os.amperecomputing.com> + ARM Catalin Marinas <catalin.marinas@arm.com> + IBM Power Anton Blanchard <anton@linux.ibm.com> + IBM Z Christian Borntraeger <borntraeger@de.ibm.com> Intel Tony Luck <tony.luck@intel.com> Qualcomm Trilok Soni <tsoni@codeaurora.org> diff --git a/Documentation/process/maintainer-tip.rst b/Documentation/process/maintainer-tip.rst index c74f4a81588b..572a3289c9cb 100644 --- a/Documentation/process/maintainer-tip.rst +++ b/Documentation/process/maintainer-tip.rst @@ -437,6 +437,20 @@ in a private repository which allows interested people to easily pull the series for testing. The usual way to offer this is a git URL in the cover letter of the patch series. +Testing +^^^^^^^ + +Code should be tested before submitting to the tip maintainers. Anything +other than minor changes should be built, booted and tested with +comprehensive (and heavyweight) kernel debugging options enabled. + +These debugging options can be found in kernel/configs/x86_debug.config +and can be added to an existing kernel config by running: + + make x86_debug.config + +Some of these options are x86-specific and can be left out when testing +on other architectures. Coding style notes ------------------ diff --git a/Documentation/security/IMA-templates.rst b/Documentation/security/IMA-templates.rst index 1a91d92950a7..15b4add314fc 100644 --- a/Documentation/security/IMA-templates.rst +++ b/Documentation/security/IMA-templates.rst @@ -66,12 +66,13 @@ descriptors by adding their identifier to the format string calculated with the SHA1 or MD5 hash algorithm; - 'n': the name of the event (i.e. the file name), with size up to 255 bytes; - 'd-ng': the digest of the event, calculated with an arbitrary hash - algorithm (field format: [<hash algo>:]digest, where the digest - prefix is shown only if the hash algorithm is not SHA1 or MD5); + algorithm (field format: <hash algo>:digest); + - 'd-ngv2': same as d-ng, but prefixed with the "ima" or "verity" digest type + (field format: <digest type>:<hash algo>:digest); - 'd-modsig': the digest of the event without the appended modsig; - 'n-ng': the name of the event, without size limitations; - - 'sig': the file signature, or the EVM portable signature if the file - signature is not found; + - 'sig': the file signature, based on either the file's/fsverity's digest[1], + or the EVM portable signature, if 'security.ima' contains a file hash. - 'modsig' the appended file signature; - 'buf': the buffer data that was used to generate the hash without size limitations; - 'evmsig': the EVM portable signature; @@ -88,7 +89,9 @@ Below, there is the list of defined template descriptors: - "ima": its format is ``d|n``; - "ima-ng" (default): its format is ``d-ng|n-ng``; + - "ima-ngv2": its format is ``d-ngv2|n-ng``; - "ima-sig": its format is ``d-ng|n-ng|sig``; + - "ima-sigv2": its format is ``d-ngv2|n-ng|sig``; - "ima-buf": its format is ``d-ng|n-ng|buf``; - "ima-modsig": its format is ``d-ng|n-ng|sig|d-modsig|modsig``; - "evm-sig": its format is ``d-ng|n-ng|evmsig|xattrnames|xattrlengths|xattrvalues|iuid|igid|imode``; diff --git a/Documentation/security/index.rst b/Documentation/security/index.rst index 16335de04e8c..6ed8d2fa6f9e 100644 --- a/Documentation/security/index.rst +++ b/Documentation/security/index.rst @@ -17,3 +17,4 @@ Security Documentation tpm/index digsig landlock + secrets/index diff --git a/Documentation/security/keys/trusted-encrypted.rst b/Documentation/security/keys/trusted-encrypted.rst index f614dad7de12..0bfb4c339748 100644 --- a/Documentation/security/keys/trusted-encrypted.rst +++ b/Documentation/security/keys/trusted-encrypted.rst @@ -35,6 +35,13 @@ safe. Rooted to Hardware Unique Key (HUK) which is generally burnt in on-chip fuses and is accessible to TEE only. + (3) CAAM (Cryptographic Acceleration and Assurance Module: IP on NXP SoCs) + + When High Assurance Boot (HAB) is enabled and the CAAM is in secure + mode, trust is rooted to the OTPMK, a never-disclosed 256-bit key + randomly generated and fused into each SoC at manufacturing time. + Otherwise, a common fixed test key is used instead. + * Execution isolation (1) TPM @@ -46,6 +53,10 @@ safe. Customizable set of operations running in isolated execution environment verified via Secure/Trusted boot process. + (3) CAAM + + Fixed set of operations running in isolated execution environment. + * Optional binding to platform integrity state (1) TPM @@ -63,6 +74,11 @@ safe. Relies on Secure/Trusted boot process for platform integrity. It can be extended with TEE based measured boot process. + (3) CAAM + + Relies on the High Assurance Boot (HAB) mechanism of NXP SoCs + for platform integrity. + * Interfaces and APIs (1) TPM @@ -74,10 +90,13 @@ safe. TEEs have well-documented, standardized client interface and APIs. For more details refer to ``Documentation/staging/tee.rst``. + (3) CAAM + + Interface is specific to silicon vendor. * Threat model - The strength and appropriateness of a particular TPM or TEE for a given + The strength and appropriateness of a particular trust source for a given purpose must be assessed when using them to protect security-relevant data. @@ -87,22 +106,32 @@ Key Generation Trusted Keys ------------ -New keys are created from random numbers generated in the trust source. They -are encrypted/decrypted using a child key in the storage key hierarchy. -Encryption and decryption of the child key must be protected by a strong -access control policy within the trust source. +New keys are created from random numbers. They are encrypted/decrypted using +a child key in the storage key hierarchy. Encryption and decryption of the +child key must be protected by a strong access control policy within the +trust source. The random number generator in use differs according to the +selected trust source: - * TPM (hardware device) based RNG + * TPM: hardware device based RNG - Strength of random numbers may vary from one device manufacturer to - another. + Keys are generated within the TPM. Strength of random numbers may vary + from one device manufacturer to another. - * TEE (OP-TEE based on Arm TrustZone) based RNG + * TEE: OP-TEE based on Arm TrustZone based RNG RNG is customizable as per platform needs. It can either be direct output from platform specific hardware RNG or a software based Fortuna CSPRNG which can be seeded via multiple entropy sources. + * CAAM: Kernel RNG + + The normal kernel random number generator is used. To seed it from the + CAAM HWRNG, enable CRYPTO_DEV_FSL_CAAM_RNG_API and ensure the device + is probed. + +Users may override this by specifying ``trusted.rng=kernel`` on the kernel +command-line to override the used RNG with the kernel's random number pool. + Encrypted Keys -------------- @@ -189,6 +218,19 @@ Usage:: specific to TEE device implementation. The key length for new keys is always in bytes. Trusted Keys can be 32 - 128 bytes (256 - 1024 bits). +Trusted Keys usage: CAAM +------------------------ + +Usage:: + + keyctl add trusted name "new keylen" ring + keyctl add trusted name "load hex_blob" ring + keyctl print keyid + +"keyctl print" returns an ASCII hex copy of the sealed key, which is in a +CAAM-specific format. The key length for new keys is always in bytes. +Trusted Keys can be 32 - 128 bytes (256 - 1024 bits). + Encrypted Keys usage -------------------- diff --git a/Documentation/security/landlock.rst b/Documentation/security/landlock.rst index 3df68cb1d10f..5c77730b4479 100644 --- a/Documentation/security/landlock.rst +++ b/Documentation/security/landlock.rst @@ -7,7 +7,7 @@ Landlock LSM: kernel documentation ================================== :Author: Mickaël Salaün -:Date: March 2021 +:Date: May 2022 Landlock's goal is to create scoped access-control (i.e. sandboxing). To harden a whole system, this feature should be available to any process, @@ -42,6 +42,21 @@ Guiding principles for safe access controls * Computation related to Landlock operations (e.g. enforcing a ruleset) shall only impact the processes requesting them. +Design choices +============== + +Filesystem access rights +------------------------ + +All access rights are tied to an inode and what can be accessed through it. +Reading the content of a directory doesn't imply to be allowed to read the +content of a listed inode. Indeed, a file name is local to its parent +directory, and an inode can be referenced by multiple file names thanks to +(hard) links. Being able to unlink a file only has a direct impact on the +directory, not the unlinked inode. This is the reason why +`LANDLOCK_ACCESS_FS_REMOVE_FILE` or `LANDLOCK_ACCESS_FS_REFER` are not allowed +to be tied to files but only to directories. + Tests ===== diff --git a/Documentation/security/secrets/coco.rst b/Documentation/security/secrets/coco.rst new file mode 100644 index 000000000000..262e7abb1b24 --- /dev/null +++ b/Documentation/security/secrets/coco.rst @@ -0,0 +1,103 @@ +.. SPDX-License-Identifier: GPL-2.0 + +============================== +Confidential Computing secrets +============================== + +This document describes how Confidential Computing secret injection is handled +from the firmware to the operating system, in the EFI driver and the efi_secret +kernel module. + + +Introduction +============ + +Confidential Computing (coco) hardware such as AMD SEV (Secure Encrypted +Virtualization) allows guest owners to inject secrets into the VMs +memory without the host/hypervisor being able to read them. In SEV, +secret injection is performed early in the VM launch process, before the +guest starts running. + +The efi_secret kernel module allows userspace applications to access these +secrets via securityfs. + + +Secret data flow +================ + +The guest firmware may reserve a designated memory area for secret injection, +and publish its location (base GPA and length) in the EFI configuration table +under a ``LINUX_EFI_COCO_SECRET_AREA_GUID`` entry +(``adf956ad-e98c-484c-ae11-b51c7d336447``). This memory area should be marked +by the firmware as ``EFI_RESERVED_TYPE``, and therefore the kernel should not +be use it for its own purposes. + +During the VM's launch, the virtual machine manager may inject a secret to that +area. In AMD SEV and SEV-ES this is performed using the +``KVM_SEV_LAUNCH_SECRET`` command (see [sev]_). The strucutre of the injected +Guest Owner secret data should be a GUIDed table of secret values; the binary +format is described in ``drivers/virt/coco/efi_secret/efi_secret.c`` under +"Structure of the EFI secret area". + +On kernel start, the kernel's EFI driver saves the location of the secret area +(taken from the EFI configuration table) in the ``efi.coco_secret`` field. +Later it checks if the secret area is populated: it maps the area and checks +whether its content begins with ``EFI_SECRET_TABLE_HEADER_GUID`` +(``1e74f542-71dd-4d66-963e-ef4287ff173b``). If the secret area is populated, +the EFI driver will autoload the efi_secret kernel module, which exposes the +secrets to userspace applications via securityfs. The details of the +efi_secret filesystem interface are in [secrets-coco-abi]_. + + +Application usage example +========================= + +Consider a guest performing computations on encrypted files. The Guest Owner +provides the decryption key (= secret) using the secret injection mechanism. +The guest application reads the secret from the efi_secret filesystem and +proceeds to decrypt the files into memory and then performs the needed +computations on the content. + +In this example, the host can't read the files from the disk image +because they are encrypted. Host can't read the decryption key because +it is passed using the secret injection mechanism (= secure channel). +Host can't read the decrypted content from memory because it's a +confidential (memory-encrypted) guest. + +Here is a simple example for usage of the efi_secret module in a guest +to which an EFI secret area with 4 secrets was injected during launch:: + + # ls -la /sys/kernel/security/secrets/coco + total 0 + drwxr-xr-x 2 root root 0 Jun 28 11:54 . + drwxr-xr-x 3 root root 0 Jun 28 11:54 .. + -r--r----- 1 root root 0 Jun 28 11:54 736870e5-84f0-4973-92ec-06879ce3da0b + -r--r----- 1 root root 0 Jun 28 11:54 83c83f7f-1356-4975-8b7e-d3a0b54312c6 + -r--r----- 1 root root 0 Jun 28 11:54 9553f55d-3da2-43ee-ab5d-ff17f78864d2 + -r--r----- 1 root root 0 Jun 28 11:54 e6f5a162-d67f-4750-a67c-5d065f2a9910 + + # hd /sys/kernel/security/secrets/coco/e6f5a162-d67f-4750-a67c-5d065f2a9910 + 00000000 74 68 65 73 65 2d 61 72 65 2d 74 68 65 2d 6b 61 |these-are-the-ka| + 00000010 74 61 2d 73 65 63 72 65 74 73 00 01 02 03 04 05 |ta-secrets......| + 00000020 06 07 |..| + 00000022 + + # rm /sys/kernel/security/secrets/coco/e6f5a162-d67f-4750-a67c-5d065f2a9910 + + # ls -la /sys/kernel/security/secrets/coco + total 0 + drwxr-xr-x 2 root root 0 Jun 28 11:55 . + drwxr-xr-x 3 root root 0 Jun 28 11:54 .. + -r--r----- 1 root root 0 Jun 28 11:54 736870e5-84f0-4973-92ec-06879ce3da0b + -r--r----- 1 root root 0 Jun 28 11:54 83c83f7f-1356-4975-8b7e-d3a0b54312c6 + -r--r----- 1 root root 0 Jun 28 11:54 9553f55d-3da2-43ee-ab5d-ff17f78864d2 + + +References +========== + +See [sev-api-spec]_ for more info regarding SEV ``LAUNCH_SECRET`` operation. + +.. [sev] Documentation/virt/kvm/amd-memory-encryption.rst +.. [secrets-coco-abi] Documentation/ABI/testing/securityfs-secrets-coco +.. [sev-api-spec] https://www.amd.com/system/files/TechDocs/55766_SEV-KM_API_Specification.pdf diff --git a/Documentation/security/secrets/index.rst b/Documentation/security/secrets/index.rst new file mode 100644 index 000000000000..ced34e9c43bd --- /dev/null +++ b/Documentation/security/secrets/index.rst @@ -0,0 +1,9 @@ +.. SPDX-License-Identifier: GPL-2.0 + +===================== +Secrets documentation +===================== + +.. toctree:: + + coco diff --git a/Documentation/security/siphash.rst b/Documentation/security/siphash.rst index bd9363025fcb..a10380cb78e5 100644 --- a/Documentation/security/siphash.rst +++ b/Documentation/security/siphash.rst @@ -121,26 +121,36 @@ even scarier, uses an easily brute-forcable 64-bit key (with a 32-bit output) instead of SipHash's 128-bit key. However, this may appeal to some high-performance `jhash` users. -Danger! - -Do not ever use HalfSipHash except for as a hashtable key function, and only -then when you can be absolutely certain that the outputs will never be -transmitted out of the kernel. This is only remotely useful over `jhash` as a -means of mitigating hashtable flooding denial of service attacks. - -Generating a HalfSipHash key -============================ +HalfSipHash support is provided through the "hsiphash" family of functions. + +.. warning:: + Do not ever use the hsiphash functions except for as a hashtable key + function, and only then when you can be absolutely certain that the outputs + will never be transmitted out of the kernel. This is only remotely useful + over `jhash` as a means of mitigating hashtable flooding denial of service + attacks. + +On 64-bit kernels, the hsiphash functions actually implement SipHash-1-3, a +reduced-round variant of SipHash, instead of HalfSipHash-1-3. This is because in +64-bit code, SipHash-1-3 is no slower than HalfSipHash-1-3, and can be faster. +Note, this does *not* mean that in 64-bit kernels the hsiphash functions are the +same as the siphash ones, or that they are secure; the hsiphash functions still +use a less secure reduced-round algorithm and truncate their outputs to 32 +bits. + +Generating a hsiphash key +========================= Keys should always be generated from a cryptographically secure source of -random numbers, either using get_random_bytes or get_random_once: +random numbers, either using get_random_bytes or get_random_once:: -hsiphash_key_t key; -get_random_bytes(&key, sizeof(key)); + hsiphash_key_t key; + get_random_bytes(&key, sizeof(key)); If you're not deriving your key from here, you're doing it wrong. -Using the HalfSipHash functions -=============================== +Using the hsiphash functions +============================ There are two variants of the function, one that takes a list of integers, and one that takes a buffer:: @@ -183,7 +193,7 @@ You may then iterate like usual over the returned hash bucket. Performance =========== -HalfSipHash is roughly 3 times slower than JenkinsHash. For many replacements, -this will not be a problem, as the hashtable lookup isn't the bottleneck. And -in general, this is probably a good sacrifice to make for the security and DoS -resistance of HalfSipHash. +hsiphash() is roughly 3 times slower than jhash(). For many replacements, this +will not be a problem, as the hashtable lookup isn't the bottleneck. And in +general, this is probably a good sacrifice to make for the security and DoS +resistance of hsiphash(). diff --git a/Documentation/userspace-api/ioctl/cdrom.rst b/Documentation/userspace-api/ioctl/cdrom.rst index 682948fc88a3..2ad91dbebd7c 100644 --- a/Documentation/userspace-api/ioctl/cdrom.rst +++ b/Documentation/userspace-api/ioctl/cdrom.rst @@ -718,6 +718,9 @@ CDROMPLAYBLK CDROMGETSPINDOWN + Obsolete, was ide-cd only + + usage:: char spindown; @@ -736,6 +739,9 @@ CDROMGETSPINDOWN CDROMSETSPINDOWN + Obsolete, was ide-cd only + + usage:: char spindown diff --git a/Documentation/userspace-api/landlock.rst b/Documentation/userspace-api/landlock.rst index f35552ff19ba..b8ea59493964 100644 --- a/Documentation/userspace-api/landlock.rst +++ b/Documentation/userspace-api/landlock.rst @@ -1,14 +1,14 @@ .. SPDX-License-Identifier: GPL-2.0 .. Copyright © 2017-2020 Mickaël Salaün <mic@digikod.net> .. Copyright © 2019-2020 ANSSI -.. Copyright © 2021 Microsoft Corporation +.. Copyright © 2021-2022 Microsoft Corporation ===================================== Landlock: unprivileged access control ===================================== :Author: Mickaël Salaün -:Date: March 2021 +:Date: May 2022 The goal of Landlock is to enable to restrict ambient rights (e.g. global filesystem access) for a set of processes. Because Landlock is a stackable @@ -18,6 +18,13 @@ is expected to help mitigate the security impact of bugs or unexpected/malicious behaviors in user space applications. Landlock empowers any process, including unprivileged ones, to securely restrict themselves. +We can quickly make sure that Landlock is enabled in the running system by +looking for "landlock: Up and running" in kernel logs (as root): ``dmesg | grep +landlock || journalctl -kg landlock`` . Developers can also easily check for +Landlock support with a :ref:`related system call <landlock_abi_versions>`. If +Landlock is not currently supported, we need to :ref:`configure the kernel +appropriately <kernel_support>`. + Landlock rules ============== @@ -29,14 +36,15 @@ the thread enforcing it, and its future children. Defining and enforcing a security policy ---------------------------------------- -We first need to create the ruleset that will contain our rules. For this +We first need to define the ruleset that will contain our rules. For this example, the ruleset will contain rules that only allow read actions, but write actions will be denied. The ruleset then needs to handle both of these kind of -actions. +actions. This is required for backward and forward compatibility (i.e. the +kernel and user space may not know each other's supported restrictions), hence +the need to be explicit about the denied-by-default access rights. .. code-block:: c - int ruleset_fd; struct landlock_ruleset_attr ruleset_attr = { .handled_access_fs = LANDLOCK_ACCESS_FS_EXECUTE | @@ -51,9 +59,34 @@ actions. LANDLOCK_ACCESS_FS_MAKE_SOCK | LANDLOCK_ACCESS_FS_MAKE_FIFO | LANDLOCK_ACCESS_FS_MAKE_BLOCK | - LANDLOCK_ACCESS_FS_MAKE_SYM, + LANDLOCK_ACCESS_FS_MAKE_SYM | + LANDLOCK_ACCESS_FS_REFER, }; +Because we may not know on which kernel version an application will be +executed, it is safer to follow a best-effort security approach. Indeed, we +should try to protect users as much as possible whatever the kernel they are +using. To avoid binary enforcement (i.e. either all security features or +none), we can leverage a dedicated Landlock command to get the current version +of the Landlock ABI and adapt the handled accesses. Let's check if we should +remove the `LANDLOCK_ACCESS_FS_REFER` access right which is only supported +starting with the second version of the ABI. + +.. code-block:: c + + int abi; + + abi = landlock_create_ruleset(NULL, 0, LANDLOCK_CREATE_RULESET_VERSION); + if (abi < 2) { + ruleset_attr.handled_access_fs &= ~LANDLOCK_ACCESS_FS_REFER; + } + +This enables to create an inclusive ruleset that will contain our rules. + +.. code-block:: c + + int ruleset_fd; + ruleset_fd = landlock_create_ruleset(&ruleset_attr, sizeof(ruleset_attr), 0); if (ruleset_fd < 0) { perror("Failed to create a ruleset"); @@ -92,6 +125,11 @@ descriptor. return 1; } +It may also be required to create rules following the same logic as explained +for the ruleset creation, by filtering access rights according to the Landlock +ABI version. In this example, this is not required because +`LANDLOCK_ACCESS_FS_REFER` is not allowed by any rule. + We now have a ruleset with one rule allowing read access to ``/usr`` while denying all other handled accesses for the filesystem. The next step is to restrict the current thread from gaining more privileges (e.g. thanks to a SUID @@ -125,6 +163,27 @@ ruleset. Full working code can be found in `samples/landlock/sandboxer.c`_. +Good practices +-------------- + +It is recommended setting access rights to file hierarchy leaves as much as +possible. For instance, it is better to be able to have ``~/doc/`` as a +read-only hierarchy and ``~/tmp/`` as a read-write hierarchy, compared to +``~/`` as a read-only hierarchy and ``~/tmp/`` as a read-write hierarchy. +Following this good practice leads to self-sufficient hierarchies that don't +depend on their location (i.e. parent directories). This is particularly +relevant when we want to allow linking or renaming. Indeed, having consistent +access rights per directory enables to change the location of such directory +without relying on the destination directory access rights (except those that +are required for this operation, see `LANDLOCK_ACCESS_FS_REFER` documentation). +Having self-sufficient hierarchies also helps to tighten the required access +rights to the minimal set of data. This also helps avoid sinkhole directories, +i.e. directories where data can be linked to but not linked from. However, +this depends on data organization, which might not be controlled by developers. +In this case, granting read-write access to ``~/tmp/``, instead of write-only +access, would potentially allow to move ``~/tmp/`` to a non-readable directory +and still keep the ability to list the content of ``~/tmp/``. + Layers of file path access rights --------------------------------- @@ -192,6 +251,58 @@ To be allowed to use :manpage:`ptrace(2)` and related syscalls on a target process, a sandboxed process should have a subset of the target process rules, which means the tracee must be in a sub-domain of the tracer. +Compatibility +============= + +Backward and forward compatibility +---------------------------------- + +Landlock is designed to be compatible with past and future versions of the +kernel. This is achieved thanks to the system call attributes and the +associated bitflags, particularly the ruleset's `handled_access_fs`. Making +handled access right explicit enables the kernel and user space to have a clear +contract with each other. This is required to make sure sandboxing will not +get stricter with a system update, which could break applications. + +Developers can subscribe to the `Landlock mailing list +<https://subspace.kernel.org/lists.linux.dev.html>`_ to knowingly update and +test their applications with the latest available features. In the interest of +users, and because they may use different kernel versions, it is strongly +encouraged to follow a best-effort security approach by checking the Landlock +ABI version at runtime and only enforcing the supported features. + +.. _landlock_abi_versions: + +Landlock ABI versions +--------------------- + +The Landlock ABI version can be read with the sys_landlock_create_ruleset() +system call: + +.. code-block:: c + + int abi; + + abi = landlock_create_ruleset(NULL, 0, LANDLOCK_CREATE_RULESET_VERSION); + if (abi < 0) { + switch (errno) { + case ENOSYS: + printf("Landlock is not supported by the current kernel.\n"); + break; + case EOPNOTSUPP: + printf("Landlock is currently disabled.\n"); + break; + } + return 0; + } + if (abi >= 2) { + printf("Landlock supports LANDLOCK_ACCESS_FS_REFER.\n"); + } + +The following kernel interfaces are implicitly supported by the first ABI +version. Features only supported from a specific version are explicitly marked +as such. + Kernel interface ================ @@ -228,21 +339,6 @@ Enforcing a ruleset Current limitations =================== -File renaming and linking -------------------------- - -Because Landlock targets unprivileged access controls, it is needed to properly -handle composition of rules. Such property also implies rules nesting. -Properly handling multiple layers of ruleset, each one of them able to restrict -access to files, also implies to inherit the ruleset restrictions from a parent -to its hierarchy. Because files are identified and restricted by their -hierarchy, moving or linking a file from one directory to another implies to -propagate the hierarchy constraints. To protect against privilege escalations -through renaming or linking, and for the sake of simplicity, Landlock currently -limits linking and renaming to the same directory. Future Landlock evolutions -will enable more flexibility for renaming and linking, with dedicated ruleset -flags. - Filesystem topology modification -------------------------------- @@ -267,8 +363,8 @@ restrict such paths with dedicated ruleset flags. Ruleset layers -------------- -There is a limit of 64 layers of stacked rulesets. This can be an issue for a -task willing to enforce a new ruleset in complement to its 64 inherited +There is a limit of 16 layers of stacked rulesets. This can be an issue for a +task willing to enforce a new ruleset in complement to its 16 inherited rulesets. Once this limit is reached, sys_landlock_restrict_self() returns E2BIG. It is then strongly suggested to carefully build rulesets once in the life of a thread, especially for applications able to launch other applications @@ -281,6 +377,44 @@ Memory usage Kernel memory allocated to create rulesets is accounted and can be restricted by the Documentation/admin-guide/cgroup-v1/memory.rst. +Previous limitations +==================== + +File renaming and linking (ABI 1) +--------------------------------- + +Because Landlock targets unprivileged access controls, it needs to properly +handle composition of rules. Such property also implies rules nesting. +Properly handling multiple layers of rulesets, each one of them able to +restrict access to files, also implies inheritance of the ruleset restrictions +from a parent to its hierarchy. Because files are identified and restricted by +their hierarchy, moving or linking a file from one directory to another implies +propagation of the hierarchy constraints, or restriction of these actions +according to the potentially lost constraints. To protect against privilege +escalations through renaming or linking, and for the sake of simplicity, +Landlock previously limited linking and renaming to the same directory. +Starting with the Landlock ABI version 2, it is now possible to securely +control renaming and linking thanks to the new `LANDLOCK_ACCESS_FS_REFER` +access right. + +.. _kernel_support: + +Kernel support +============== + +Landlock was first introduced in Linux 5.13 but it must be configured at build +time with `CONFIG_SECURITY_LANDLOCK=y`. Landlock must also be enabled at boot +time as the other security modules. The list of security modules enabled by +default is set with `CONFIG_LSM`. The kernel configuration should then +contains `CONFIG_LSM=landlock,[...]` with `[...]` as the list of other +potentially useful security modules for the running system (see the +`CONFIG_LSM` help). + +If the running kernel doesn't have `landlock` in `CONFIG_LSM`, then we can +still enable it by adding ``lsm=landlock,[...]`` to +Documentation/admin-guide/kernel-parameters.rst thanks to the bootloader +configuration. + Questions and answers ===================== diff --git a/Documentation/userspace-api/media/drivers/uvcvideo.rst b/Documentation/userspace-api/media/drivers/uvcvideo.rst index e5fd8fad333c..a290f9fadae9 100644 --- a/Documentation/userspace-api/media/drivers/uvcvideo.rst +++ b/Documentation/userspace-api/media/drivers/uvcvideo.rst @@ -7,7 +7,7 @@ This file documents some driver-specific aspects of the UVC driver, such as driver-specific ioctls and implementation notes. Questions and remarks can be sent to the Linux UVC development mailing list at -linux-uvc-devel@lists.berlios.de. +linux-media@vger.kernel.org. Extension Unit (XU) support diff --git a/Documentation/userspace-api/media/mediactl/media-controller-model.rst b/Documentation/userspace-api/media/mediactl/media-controller-model.rst index 222cb99debb5..78bfdfb2a322 100644 --- a/Documentation/userspace-api/media/mediactl/media-controller-model.rst +++ b/Documentation/userspace-api/media/mediactl/media-controller-model.rst @@ -33,3 +33,9 @@ are: - An **interface link** is a point-to-point bidirectional control connection between a Linux Kernel interface and an entity. + +- An **ancillary link** is a point-to-point connection denoting that two + entities form a single logical unit. For example this could represent the + fact that a particular camera sensor and lens controller form a single + physical module, meaning this lens controller drives the lens for this + camera sensor. \ No newline at end of file diff --git a/Documentation/userspace-api/media/mediactl/media-types.rst b/Documentation/userspace-api/media/mediactl/media-types.rst index 0a26397bd01d..0ffeece1e0c8 100644 --- a/Documentation/userspace-api/media/mediactl/media-types.rst +++ b/Documentation/userspace-api/media/mediactl/media-types.rst @@ -412,14 +412,21 @@ must be set for every pad. is set by drivers and is read-only for applications. * - ``MEDIA_LNK_FL_LINK_TYPE`` - - This is a bitmask that defines the type of the link. Currently, - two types of links are supported: + - This is a bitmask that defines the type of the link. The following + link types are currently supported: .. _MEDIA-LNK-FL-DATA-LINK: - ``MEDIA_LNK_FL_DATA_LINK`` if the link is between two pads + ``MEDIA_LNK_FL_DATA_LINK`` for links that represent a data connection + between two pads. .. _MEDIA-LNK-FL-INTERFACE-LINK: - ``MEDIA_LNK_FL_INTERFACE_LINK`` if the link is between an - interface and an entity + ``MEDIA_LNK_FL_INTERFACE_LINK`` for links that associate an entity to its + interface. + + .. _MEDIA-LNK-FL-ANCILLARY-LINK: + + ``MEDIA_LNK_FL_ANCILLARY_LINK`` for links that represent a physical + relationship between two entities. The link may or may not be + immutable, so applications must not assume either case. diff --git a/Documentation/userspace-api/media/v4l/dev-decoder.rst b/Documentation/userspace-api/media/v4l/dev-decoder.rst index 3cf2b496f2d0..675bc2c3c6b8 100644 --- a/Documentation/userspace-api/media/v4l/dev-decoder.rst +++ b/Documentation/userspace-api/media/v4l/dev-decoder.rst @@ -72,6 +72,12 @@ coded resolution coded width width for given coded resolution. +coding tree unit + processing unit of the HEVC codec (corresponds to macroblock units in + H.264, VP8, VP9), + can use block structures of up to 64×64 pixels. + Good at sub-partitioning the picture into variable sized structures. + decode order the order in which frames are decoded; may differ from display order if the coded format includes a feature of frame reordering; for decoders, @@ -104,7 +110,8 @@ keyframe macroblock a processing unit in image and video compression formats based on linear block transforms (e.g. H.264, VP8, VP9); codec-specific, but for most of - popular codecs the size is 16x16 samples (pixels). + popular codecs the size is 16x16 samples (pixels). The HEVC codec uses a + slightly more flexible processing unit called coding tree unit (CTU). OUTPUT the source buffer queue; for decoders, the queue of buffers containing diff --git a/Documentation/userspace-api/media/v4l/ext-ctrls-codec-stateless.rst b/Documentation/userspace-api/media/v4l/ext-ctrls-codec-stateless.rst index 6541e4c32b26..bee73065e993 100644 --- a/Documentation/userspace-api/media/v4l/ext-ctrls-codec-stateless.rst +++ b/Documentation/userspace-api/media/v4l/ext-ctrls-codec-stateless.rst @@ -649,10 +649,16 @@ Stateless Codec Control ID :c:type:`timeval` in struct :c:type:`v4l2_buffer` to a __u64. * - __u32 - ``pic_num`` - - + - For short term references, this must match the derived value PicNum + (8-28) and for long term references it must match the derived value + LongTermPicNum (8-29). When decoding frames (as opposed to fields) + pic_num is the same as FrameNumWrap. * - __u16 - ``frame_num`` - - + - For short term references, this must match the frame_num value from + the slice header syntax (the driver will wrap the value if needed). For + long term references, this must be set to the value of + long_term_frame_idx described in the dec_ref_pic_marking() syntax. * - __u8 - ``fields`` - Specifies how the DPB entry is referenced. See :ref:`Reference Fields <h264_ref_fields>` diff --git a/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst b/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst index 4cd7c541fc30..6183f43f4d73 100644 --- a/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst +++ b/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst @@ -1180,6 +1180,28 @@ enum v4l2_mpeg_video_h264_entropy_mode - is set to non zero value. Applicable to H264, H263 and MPEG4 encoder. +``V4L2_CID_MPEG_VIDEO_INTRA_REFRESH_PERIOD_TYPE (enum)`` + +enum v4l2_mpeg_video_intra_refresh_period_type - + Sets the type of intra refresh. The period to refresh + the whole frame is specified by V4L2_CID_MPEG_VIDEO_INTRA_REFRESH_PERIOD. + Note that if this control is not present, then it is undefined what + refresh type is used and it is up to the driver to decide. + Applicable to H264 and HEVC encoders. Possible values are: + +.. tabularcolumns:: |p{9.6cm}|p{7.9cm}| + +.. flat-table:: + :header-rows: 0 + :stub-columns: 0 + + * - ``V4L2_MPEG_VIDEO_INTRA_REFRESH_PERIOD_TYPE_RANDOM`` + - The whole frame is completely refreshed randomly + after the specified period. + * - ``V4L2_MPEG_VIDEO_INTRA_REFRESH_PERIOD_TYPE_CYCLIC`` + - The whole frame MBs are completely refreshed in cyclic order + after the specified period. + ``V4L2_CID_MPEG_VIDEO_INTRA_REFRESH_PERIOD (integer)`` Intra macroblock refresh period. This sets the period to refresh the whole frame. In other words, this defines the number of frames diff --git a/Documentation/userspace-api/media/v4l/pixfmt-reserved.rst b/Documentation/userspace-api/media/v4l/pixfmt-reserved.rst index cabfa34b7db5..0ff68cd8cf62 100644 --- a/Documentation/userspace-api/media/v4l/pixfmt-reserved.rst +++ b/Documentation/userspace-api/media/v4l/pixfmt-reserved.rst @@ -239,6 +239,25 @@ please make a proposal on the linux-media mailing list. It remains an opaque intermediate format and the MDP hardware must be used to convert ``V4L2_PIX_FMT_MT21C`` to ``V4L2_PIX_FMT_NV12M``, ``V4L2_PIX_FMT_YUV420M`` or ``V4L2_PIX_FMT_YVU420``. + * .. _V4L2-PIX-FMT-QC08C: + + - ``V4L2_PIX_FMT_QC08C`` + - 'QC08C' + - Compressed Macro-tile 8-Bit YUV420 format used by Qualcomm platforms. + It is an opaque intermediate format. The used compression is lossless + and it is used by various multimedia hardware blocks like GPU, display + controllers, ISP and video accelerators. + It contains four planes for progressive video and eight planes for + interlaced video. + * .. _V4L2-PIX-FMT-QC10C: + + - ``V4L2_PIX_FMT_QC10C`` + - 'QC10C' + - Compressed Macro-tile 10-Bit YUV420 format used by Qualcomm platforms. + It is an opaque intermediate format. The used compression is lossless + and it is used by various multimedia hardware blocks like GPU, display + controllers, ISP and video accelerators. + It contains four planes for progressive video. .. raw:: latex \normalsize diff --git a/Documentation/userspace-api/media/v4l/pixfmt-yuv-luma.rst b/Documentation/userspace-api/media/v4l/pixfmt-yuv-luma.rst index 8ebd58c3588f..6a387f9df3ba 100644 --- a/Documentation/userspace-api/media/v4l/pixfmt-yuv-luma.rst +++ b/Documentation/userspace-api/media/v4l/pixfmt-yuv-luma.rst @@ -48,6 +48,17 @@ are often referred to as greyscale formats. - ... - ... + * .. _V4L2-PIX-FMT-IPU3-Y10: + + - ``V4L2_PIX_FMT_IPU3_Y10`` + - 'ip3y' + + - Y'\ :sub:`0`\ [7:0] + - Y'\ :sub:`1`\ [5:0] Y'\ :sub:`0`\ [9:8] + - Y'\ :sub:`2`\ [3:0] Y'\ :sub:`1`\ [9:6] + - Y'\ :sub:`3`\ [1:0] Y'\ :sub:`2`\ [9:4] + - Y'\ :sub:`3`\ [9:2] + * .. _V4L2-PIX-FMT-Y10: - ``V4L2_PIX_FMT_Y10`` @@ -133,4 +144,5 @@ are often referred to as greyscale formats. For the Y16 and Y16_BE formats, the actual sampling precision may be lower than 16 bits. For example, 10 bits per pixel uses values in the range 0 to - 1023. + 1023. For the IPU3_Y10 format 25 pixels are packed into 32 bytes, which + leaves the 6 most significant bits of the last byte padded with 0. diff --git a/Documentation/userspace-api/media/v4l/vidioc-streamon.rst b/Documentation/userspace-api/media/v4l/vidioc-streamon.rst index 0bc86f06947b..1a79313a29fa 100644 --- a/Documentation/userspace-api/media/v4l/vidioc-streamon.rst +++ b/Documentation/userspace-api/media/v4l/vidioc-streamon.rst @@ -43,8 +43,7 @@ the capture or output process during streaming Capture hardware is disabled and no input buffers are filled (if there are any empty buffers in the incoming queue) until ``VIDIOC_STREAMON`` has been called. Output hardware is disabled and no video signal is -produced until ``VIDIOC_STREAMON`` has been called. The ioctl will -succeed when at least one output buffer is in the incoming queue. +produced until ``VIDIOC_STREAMON`` has been called. Memory-to-memory devices will not start until ``VIDIOC_STREAMON`` has been called for both the capture and output stream types. diff --git a/Documentation/userspace-api/seccomp_filter.rst b/Documentation/userspace-api/seccomp_filter.rst index 539e9d4a4860..d1e2b9193f09 100644 --- a/Documentation/userspace-api/seccomp_filter.rst +++ b/Documentation/userspace-api/seccomp_filter.rst @@ -271,6 +271,16 @@ notifying process it will be replaced. The supervisor can also add an FD, and respond atomically by using the ``SECCOMP_ADDFD_FLAG_SEND`` flag and the return value will be the injected file descriptor number. +The notifying process can be preempted, resulting in the notification being +aborted. This can be problematic when trying to take actions on behalf of the +notifying process that are long-running and typically retryable (mounting a +filesytem). Alternatively, at filter installation time, the +``SECCOMP_FILTER_FLAG_WAIT_KILLABLE_RECV`` flag can be set. This flag makes it +such that when a user notification is received by the supervisor, the notifying +process will ignore non-fatal signals until the response is sent. Signals that +are sent prior to the notification being received by userspace are handled +normally. + It is worth noting that ``struct seccomp_data`` contains the values of register arguments to the syscall, but does not contain pointers to memory. The task's memory is accessible to suitably privileged traces via ``ptrace()`` or diff --git a/Documentation/virt/coco/sev-guest.rst b/Documentation/virt/coco/sev-guest.rst new file mode 100644 index 000000000000..bf593e88cfd9 --- /dev/null +++ b/Documentation/virt/coco/sev-guest.rst @@ -0,0 +1,155 @@ +.. SPDX-License-Identifier: GPL-2.0 + +=================================================================== +The Definitive SEV Guest API Documentation +=================================================================== + +1. General description +====================== + +The SEV API is a set of ioctls that are used by the guest or hypervisor +to get or set a certain aspect of the SEV virtual machine. The ioctls belong +to the following classes: + + - Hypervisor ioctls: These query and set global attributes which affect the + whole SEV firmware. These ioctl are used by platform provisioning tools. + + - Guest ioctls: These query and set attributes of the SEV virtual machine. + +2. API description +================== + +This section describes ioctls that is used for querying the SEV guest report +from the SEV firmware. For each ioctl, the following information is provided +along with a description: + + Technology: + which SEV technology provides this ioctl. SEV, SEV-ES, SEV-SNP or all. + + Type: + hypervisor or guest. The ioctl can be used inside the guest or the + hypervisor. + + Parameters: + what parameters are accepted by the ioctl. + + Returns: + the return value. General error numbers (-ENOMEM, -EINVAL) + are not detailed, but errors with specific meanings are. + +The guest ioctl should be issued on a file descriptor of the /dev/sev-guest device. +The ioctl accepts struct snp_user_guest_request. The input and output structure is +specified through the req_data and resp_data field respectively. If the ioctl fails +to execute due to a firmware error, then fw_err code will be set otherwise the +fw_err will be set to 0x00000000000000ff. + +The firmware checks that the message sequence counter is one greater than +the guests message sequence counter. If guest driver fails to increment message +counter (e.g. counter overflow), then -EIO will be returned. + +:: + + struct snp_guest_request_ioctl { + /* Message version number */ + __u32 msg_version; + + /* Request and response structure address */ + __u64 req_data; + __u64 resp_data; + + /* firmware error code on failure (see psp-sev.h) */ + __u64 fw_err; + }; + +2.1 SNP_GET_REPORT +------------------ + +:Technology: sev-snp +:Type: guest ioctl +:Parameters (in): struct snp_report_req +:Returns (out): struct snp_report_resp on success, -negative on error + +The SNP_GET_REPORT ioctl can be used to query the attestation report from the +SEV-SNP firmware. The ioctl uses the SNP_GUEST_REQUEST (MSG_REPORT_REQ) command +provided by the SEV-SNP firmware to query the attestation report. + +On success, the snp_report_resp.data will contains the report. The report +contain the format described in the SEV-SNP specification. See the SEV-SNP +specification for further details. + +2.2 SNP_GET_DERIVED_KEY +----------------------- +:Technology: sev-snp +:Type: guest ioctl +:Parameters (in): struct snp_derived_key_req +:Returns (out): struct snp_derived_key_resp on success, -negative on error + +The SNP_GET_DERIVED_KEY ioctl can be used to get a key derive from a root key. +The derived key can be used by the guest for any purpose, such as sealing keys +or communicating with external entities. + +The ioctl uses the SNP_GUEST_REQUEST (MSG_KEY_REQ) command provided by the +SEV-SNP firmware to derive the key. See SEV-SNP specification for further details +on the various fields passed in the key derivation request. + +On success, the snp_derived_key_resp.data contains the derived key value. See +the SEV-SNP specification for further details. + + +2.3 SNP_GET_EXT_REPORT +---------------------- +:Technology: sev-snp +:Type: guest ioctl +:Parameters (in/out): struct snp_ext_report_req +:Returns (out): struct snp_report_resp on success, -negative on error + +The SNP_GET_EXT_REPORT ioctl is similar to the SNP_GET_REPORT. The difference is +related to the additional certificate data that is returned with the report. +The certificate data returned is being provided by the hypervisor through the +SNP_SET_EXT_CONFIG. + +The ioctl uses the SNP_GUEST_REQUEST (MSG_REPORT_REQ) command provided by the SEV-SNP +firmware to get the attestation report. + +On success, the snp_ext_report_resp.data will contain the attestation report +and snp_ext_report_req.certs_address will contain the certificate blob. If the +length of the blob is smaller than expected then snp_ext_report_req.certs_len will +be updated with the expected value. + +See GHCB specification for further detail on how to parse the certificate blob. + +3. SEV-SNP CPUID Enforcement +============================ + +SEV-SNP guests can access a special page that contains a table of CPUID values +that have been validated by the PSP as part of the SNP_LAUNCH_UPDATE firmware +command. It provides the following assurances regarding the validity of CPUID +values: + + - Its address is obtained via bootloader/firmware (via CC blob), and those + binaries will be measured as part of the SEV-SNP attestation report. + - Its initial state will be encrypted/pvalidated, so attempts to modify + it during run-time will result in garbage being written, or #VC exceptions + being generated due to changes in validation state if the hypervisor tries + to swap the backing page. + - Attempts to bypass PSP checks by the hypervisor by using a normal page, or + a non-CPUID encrypted page will change the measurement provided by the + SEV-SNP attestation report. + - The CPUID page contents are *not* measured, but attempts to modify the + expected contents of a CPUID page as part of guest initialization will be + gated by the PSP CPUID enforcement policy checks performed on the page + during SNP_LAUNCH_UPDATE, and noticeable later if the guest owner + implements their own checks of the CPUID values. + +It is important to note that this last assurance is only useful if the kernel +has taken care to make use of the SEV-SNP CPUID throughout all stages of boot. +Otherwise, guest owner attestation provides no assurance that the kernel wasn't +fed incorrect values at some point during boot. + + +Reference +--------- + +SEV-SNP and GHCB specification: developer.amd.com/sev + +The driver is based on SEV-SNP firmware spec 0.9 and GHCB spec version 2.0. diff --git a/Documentation/virt/index.rst b/Documentation/virt/index.rst index edea7fea95a8..492f0920b988 100644 --- a/Documentation/virt/index.rst +++ b/Documentation/virt/index.rst @@ -13,6 +13,7 @@ Linux Virtualization Support guest-halt-polling ne_overview acrn/index + coco/sev-guest .. only:: html and subproject diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index d13fa6600467..c8e2e9cd84dc 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -5713,6 +5713,8 @@ affect the device's behavior. Current defined flags:: #define KVM_RUN_X86_SMM (1 << 0) /* x86, set if bus lock detected in VM */ #define KVM_RUN_BUS_LOCK (1 << 1) + /* arm64, set for KVM_EXIT_DEBUG */ + #define KVM_DEBUG_ARCH_HSR_HIGH_VALID (1 << 0) :: @@ -5986,16 +5988,16 @@ should put the acknowledged interrupt vector into the 'epr' field. #define KVM_SYSTEM_EVENT_RESET 2 #define KVM_SYSTEM_EVENT_CRASH 3 __u32 type; - __u64 flags; + __u32 ndata; + __u64 data[16]; } system_event; If exit_reason is KVM_EXIT_SYSTEM_EVENT then the vcpu has triggered a system-level event using some architecture specific mechanism (hypercall or some special instruction). In case of ARM64, this is triggered using -HVC instruction based PSCI call from the vcpu. The 'type' field describes -the system-level event type. The 'flags' field describes architecture -specific flags for the system-level event. +HVC instruction based PSCI call from the vcpu. +The 'type' field describes the system-level event type. Valid values for 'type' are: - KVM_SYSTEM_EVENT_SHUTDOWN -- the guest has requested a shutdown of the @@ -6010,10 +6012,20 @@ Valid values for 'type' are: to ignore the request, or to gather VM memory core dump and/or reset/shutdown of the VM. -Valid flags are: +If KVM_CAP_SYSTEM_EVENT_DATA is present, the 'data' field can contain +architecture specific information for the system-level event. Only +the first `ndata` items (possibly zero) of the data array are valid. - - KVM_SYSTEM_EVENT_RESET_FLAG_PSCI_RESET2 (arm64 only) -- the guest issued - a SYSTEM_RESET2 call according to v1.1 of the PSCI specification. + - for arm64, data[0] is set to KVM_SYSTEM_EVENT_RESET_FLAG_PSCI_RESET2 if + the guest issued a SYSTEM_RESET2 call according to v1.1 of the PSCI + specification. + + - for RISC-V, data[0] is set to the value of the second argument of the + ``sbi_system_reset`` call. + +Previous versions of Linux defined a `flags` member in this struct. The +field is now aliased to `data[0]`. Userspace can assume that it is only +written if ndata is greater than 0. :: @@ -6190,6 +6202,7 @@ Valid values for 'type' are: unsigned long args[6]; unsigned long ret[2]; } riscv_sbi; + If exit reason is KVM_EXIT_RISCV_SBI then it indicates that the VCPU has done a SBI call which is not handled by KVM RISC-V kernel module. The details of the SBI call are available in 'riscv_sbi' member of kvm_run structure. The diff --git a/Documentation/virt/kvm/vcpu-requests.rst b/Documentation/virt/kvm/vcpu-requests.rst index db43ee571f5a..31f62b64e07b 100644 --- a/Documentation/virt/kvm/vcpu-requests.rst +++ b/Documentation/virt/kvm/vcpu-requests.rst @@ -1,3 +1,5 @@ +.. SPDX-License-Identifier: GPL-2.0 + ================= KVM VCPU Requests ================= diff --git a/Documentation/virt/kvm/x86/amd-memory-encryption.rst b/Documentation/virt/kvm/x86/amd-memory-encryption.rst index 1c6847fff304..2d307811978c 100644 --- a/Documentation/virt/kvm/x86/amd-memory-encryption.rst +++ b/Documentation/virt/kvm/x86/amd-memory-encryption.rst @@ -1,3 +1,5 @@ +.. SPDX-License-Identifier: GPL-2.0 + ====================================== Secure Encrypted Virtualization (SEV) ====================================== diff --git a/Documentation/virt/kvm/x86/errata.rst b/Documentation/virt/kvm/x86/errata.rst index 806f049b6975..410e0aa63493 100644 --- a/Documentation/virt/kvm/x86/errata.rst +++ b/Documentation/virt/kvm/x86/errata.rst @@ -1,3 +1,4 @@ +.. SPDX-License-Identifier: GPL-2.0 ======================================= Known limitations of CPU virtualization @@ -36,4 +37,3 @@ Nested virtualization features ------------------------------ TBD - diff --git a/Documentation/virt/kvm/x86/running-nested-guests.rst b/Documentation/virt/kvm/x86/running-nested-guests.rst index bd70c69468ae..a27e6768d900 100644 --- a/Documentation/virt/kvm/x86/running-nested-guests.rst +++ b/Documentation/virt/kvm/x86/running-nested-guests.rst @@ -1,3 +1,5 @@ +.. SPDX-License-Identifier: GPL-2.0 + ============================== Running nested guests with KVM ============================== diff --git a/Documentation/vm/page_owner.rst b/Documentation/vm/page_owner.rst index 65204d7f004f..7e0c3f574e78 100644 --- a/Documentation/vm/page_owner.rst +++ b/Documentation/vm/page_owner.rst @@ -110,7 +110,7 @@ Usage If you want to sort by the page nums of buf, use the ``-m`` parameter. The detailed parameters are: - fundamental function: + fundamental function:: Sort: -a Sort by memory allocation time. @@ -122,7 +122,7 @@ Usage -s Sort by stack trace. -t Sort by times (default). - additional function: + additional function:: Cull: --cull <rules> @@ -153,6 +153,7 @@ Usage STANDARD FORMAT SPECIFIERS ========================== +:: KEY LONG DESCRIPTION p pid process ID diff --git a/Documentation/vm/slub.rst b/Documentation/vm/slub.rst index d3028554b1e9..43063ade737a 100644 --- a/Documentation/vm/slub.rst +++ b/Documentation/vm/slub.rst @@ -384,5 +384,69 @@ c) Execute ``slabinfo-gnuplot.sh`` in '-t' mode, passing all of the 40,60`` range will plot only samples collected between 40th and 60th seconds). + +DebugFS files for SLUB +====================== + +For more information about current state of SLUB caches with the user tracking +debug option enabled, debugfs files are available, typically under +/sys/kernel/debug/slab/<cache>/ (created only for caches with enabled user +tracking). There are 2 types of these files with the following debug +information: + +1. alloc_traces:: + + Prints information about unique allocation traces of the currently + allocated objects. The output is sorted by frequency of each trace. + + Information in the output: + Number of objects, allocating function, minimal/average/maximal jiffies since alloc, + pid range of the allocating processes, cpu mask of allocating cpus, and stack trace. + + Example::: + + 1085 populate_error_injection_list+0x97/0x110 age=166678/166680/166682 pid=1 cpus=1:: + __slab_alloc+0x6d/0x90 + kmem_cache_alloc_trace+0x2eb/0x300 + populate_error_injection_list+0x97/0x110 + init_error_injection+0x1b/0x71 + do_one_initcall+0x5f/0x2d0 + kernel_init_freeable+0x26f/0x2d7 + kernel_init+0xe/0x118 + ret_from_fork+0x22/0x30 + + +2. free_traces:: + + Prints information about unique freeing traces of the currently allocated + objects. The freeing traces thus come from the previous life-cycle of the + objects and are reported as not available for objects allocated for the first + time. The output is sorted by frequency of each trace. + + Information in the output: + Number of objects, freeing function, minimal/average/maximal jiffies since free, + pid range of the freeing processes, cpu mask of freeing cpus, and stack trace. + + Example::: + + 1980 <not-available> age=4294912290 pid=0 cpus=0 + 51 acpi_ut_update_ref_count+0x6a6/0x782 age=236886/237027/237772 pid=1 cpus=1 + kfree+0x2db/0x420 + acpi_ut_update_ref_count+0x6a6/0x782 + acpi_ut_update_object_reference+0x1ad/0x234 + acpi_ut_remove_reference+0x7d/0x84 + acpi_rs_get_prt_method_data+0x97/0xd6 + acpi_get_irq_routing_table+0x82/0xc4 + acpi_pci_irq_find_prt_entry+0x8e/0x2e0 + acpi_pci_irq_lookup+0x3a/0x1e0 + acpi_pci_irq_enable+0x77/0x240 + pcibios_enable_device+0x39/0x40 + do_pci_enable_device.part.0+0x5d/0xe0 + pci_enable_device_flags+0xfc/0x120 + pci_enable_device+0x13/0x20 + virtio_pci_probe+0x9e/0x170 + local_pci_probe+0x48/0x80 + pci_device_probe+0x105/0x1c0 + Christoph Lameter, May 30, 2007 Sergey Senozhatsky, October 23, 2015 diff --git a/Documentation/x86/cpuinfo.rst b/Documentation/x86/cpuinfo.rst index 5d54c39a063f..08246e8ac835 100644 --- a/Documentation/x86/cpuinfo.rst +++ b/Documentation/x86/cpuinfo.rst @@ -140,9 +140,8 @@ from #define X86_FEATURE_UMIP (16*32 + 2). In addition, there exists a variety of custom command-line parameters that disable specific features. The list of parameters includes, but is not limited -to, nofsgsbase, nosmap, and nosmep. 5-level paging can also be disabled using -"no5lvl". SMAP and SMEP are disabled with the aforementioned parameters, -respectively. +to, nofsgsbase, nosgx, noxsave, etc. 5-level paging can also be disabled using +"no5lvl". e: The feature was known to be non-functional. ---------------------------------------------- diff --git a/Documentation/x86/ifs.rst b/Documentation/x86/ifs.rst new file mode 100644 index 000000000000..97abb696a680 --- /dev/null +++ b/Documentation/x86/ifs.rst @@ -0,0 +1,2 @@ +.. SPDX-License-Identifier: GPL-2.0 +.. kernel-doc:: drivers/platform/x86/intel/ifs/ifs.h diff --git a/Documentation/x86/index.rst b/Documentation/x86/index.rst index 1f720227bb73..c73d133fd37c 100644 --- a/Documentation/x86/index.rst +++ b/Documentation/x86/index.rst @@ -26,6 +26,7 @@ x86-specific Documentation intel_txt amd-memory-encryption amd_hsmp + tdx pti mds microcode @@ -35,6 +36,7 @@ x86-specific Documentation usb-legacy-support i386/index x86_64/index + ifs sva sgx features diff --git a/Documentation/x86/tdx.rst b/Documentation/x86/tdx.rst new file mode 100644 index 000000000000..b8fa4329e1a5 --- /dev/null +++ b/Documentation/x86/tdx.rst @@ -0,0 +1,218 @@ +.. SPDX-License-Identifier: GPL-2.0 + +===================================== +Intel Trust Domain Extensions (TDX) +===================================== + +Intel's Trust Domain Extensions (TDX) protect confidential guest VMs from +the host and physical attacks by isolating the guest register state and by +encrypting the guest memory. In TDX, a special module running in a special +mode sits between the host and the guest and manages the guest/host +separation. + +Since the host cannot directly access guest registers or memory, much +normal functionality of a hypervisor must be moved into the guest. This is +implemented using a Virtualization Exception (#VE) that is handled by the +guest kernel. A #VE is handled entirely inside the guest kernel, but some +require the hypervisor to be consulted. + +TDX includes new hypercall-like mechanisms for communicating from the +guest to the hypervisor or the TDX module. + +New TDX Exceptions +================== + +TDX guests behave differently from bare-metal and traditional VMX guests. +In TDX guests, otherwise normal instructions or memory accesses can cause +#VE or #GP exceptions. + +Instructions marked with an '*' conditionally cause exceptions. The +details for these instructions are discussed below. + +Instruction-based #VE +--------------------- + +- Port I/O (INS, OUTS, IN, OUT) +- HLT +- MONITOR, MWAIT +- WBINVD, INVD +- VMCALL +- RDMSR*,WRMSR* +- CPUID* + +Instruction-based #GP +--------------------- + +- All VMX instructions: INVEPT, INVVPID, VMCLEAR, VMFUNC, VMLAUNCH, + VMPTRLD, VMPTRST, VMREAD, VMRESUME, VMWRITE, VMXOFF, VMXON +- ENCLS, ENCLU +- GETSEC +- RSM +- ENQCMD +- RDMSR*,WRMSR* + +RDMSR/WRMSR Behavior +-------------------- + +MSR access behavior falls into three categories: + +- #GP generated +- #VE generated +- "Just works" + +In general, the #GP MSRs should not be used in guests. Their use likely +indicates a bug in the guest. The guest may try to handle the #GP with a +hypercall but it is unlikely to succeed. + +The #VE MSRs are typically able to be handled by the hypervisor. Guests +can make a hypercall to the hypervisor to handle the #VE. + +The "just works" MSRs do not need any special guest handling. They might +be implemented by directly passing through the MSR to the hardware or by +trapping and handling in the TDX module. Other than possibly being slow, +these MSRs appear to function just as they would on bare metal. + +CPUID Behavior +-------------- + +For some CPUID leaves and sub-leaves, the virtualized bit fields of CPUID +return values (in guest EAX/EBX/ECX/EDX) are configurable by the +hypervisor. For such cases, the Intel TDX module architecture defines two +virtualization types: + +- Bit fields for which the hypervisor controls the value seen by the guest + TD. + +- Bit fields for which the hypervisor configures the value such that the + guest TD either sees their native value or a value of 0. For these bit + fields, the hypervisor can mask off the native values, but it can not + turn *on* values. + +A #VE is generated for CPUID leaves and sub-leaves that the TDX module does +not know how to handle. The guest kernel may ask the hypervisor for the +value with a hypercall. + +#VE on Memory Accesses +====================== + +There are essentially two classes of TDX memory: private and shared. +Private memory receives full TDX protections. Its content is protected +against access from the hypervisor. Shared memory is expected to be +shared between guest and hypervisor and does not receive full TDX +protections. + +A TD guest is in control of whether its memory accesses are treated as +private or shared. It selects the behavior with a bit in its page table +entries. This helps ensure that a guest does not place sensitive +information in shared memory, exposing it to the untrusted hypervisor. + +#VE on Shared Memory +-------------------- + +Access to shared mappings can cause a #VE. The hypervisor ultimately +controls whether a shared memory access causes a #VE, so the guest must be +careful to only reference shared pages it can safely handle a #VE. For +instance, the guest should be careful not to access shared memory in the +#VE handler before it reads the #VE info structure (TDG.VP.VEINFO.GET). + +Shared mapping content is entirely controlled by the hypervisor. The guest +should only use shared mappings for communicating with the hypervisor. +Shared mappings must never be used for sensitive memory content like kernel +stacks. A good rule of thumb is that hypervisor-shared memory should be +treated the same as memory mapped to userspace. Both the hypervisor and +userspace are completely untrusted. + +MMIO for virtual devices is implemented as shared memory. The guest must +be careful not to access device MMIO regions unless it is also prepared to +handle a #VE. + +#VE on Private Pages +-------------------- + +An access to private mappings can also cause a #VE. Since all kernel +memory is also private memory, the kernel might theoretically need to +handle a #VE on arbitrary kernel memory accesses. This is not feasible, so +TDX guests ensure that all guest memory has been "accepted" before memory +is used by the kernel. + +A modest amount of memory (typically 512M) is pre-accepted by the firmware +before the kernel runs to ensure that the kernel can start up without +being subjected to a #VE. + +The hypervisor is permitted to unilaterally move accepted pages to a +"blocked" state. However, if it does this, page access will not generate a +#VE. It will, instead, cause a "TD Exit" where the hypervisor is required +to handle the exception. + +Linux #VE handler +================= + +Just like page faults or #GP's, #VE exceptions can be either handled or be +fatal. Typically, an unhandled userspace #VE results in a SIGSEGV. +An unhandled kernel #VE results in an oops. + +Handling nested exceptions on x86 is typically nasty business. A #VE +could be interrupted by an NMI which triggers another #VE and hilarity +ensues. The TDX #VE architecture anticipated this scenario and includes a +feature to make it slightly less nasty. + +During #VE handling, the TDX module ensures that all interrupts (including +NMIs) are blocked. The block remains in place until the guest makes a +TDG.VP.VEINFO.GET TDCALL. This allows the guest to control when interrupts +or a new #VE can be delivered. + +However, the guest kernel must still be careful to avoid potential +#VE-triggering actions (discussed above) while this block is in place. +While the block is in place, any #VE is elevated to a double fault (#DF) +which is not recoverable. + +MMIO handling +============= + +In non-TDX VMs, MMIO is usually implemented by giving a guest access to a +mapping which will cause a VMEXIT on access, and then the hypervisor +emulates the access. That is not possible in TDX guests because VMEXIT +will expose the register state to the host. TDX guests don't trust the host +and can't have their state exposed to the host. + +In TDX, MMIO regions typically trigger a #VE exception in the guest. The +guest #VE handler then emulates the MMIO instruction inside the guest and +converts it into a controlled TDCALL to the host, rather than exposing +guest state to the host. + +MMIO addresses on x86 are just special physical addresses. They can +theoretically be accessed with any instruction that accesses memory. +However, the kernel instruction decoding method is limited. It is only +designed to decode instructions like those generated by io.h macros. + +MMIO access via other means (like structure overlays) may result in an +oops. + +Shared Memory Conversions +========================= + +All TDX guest memory starts out as private at boot. This memory can not +be accessed by the hypervisor. However, some kernel users like device +drivers might have a need to share data with the hypervisor. To do this, +memory must be converted between shared and private. This can be +accomplished using some existing memory encryption helpers: + + * set_memory_decrypted() converts a range of pages to shared. + * set_memory_encrypted() converts memory back to private. + +Device drivers are the primary user of shared memory, but there's no need +to touch every driver. DMA buffers and ioremap() do the conversions +automatically. + +TDX uses SWIOTLB for most DMA allocations. The SWIOTLB buffer is +converted to shared on boot. + +For coherent DMA allocation, the DMA buffer gets converted on the +allocation. Check force_dma_unencrypted() for details. + +References +========== + +TDX reference material is collected here: + +https://www.intel.com/content/www/us/en/developer/articles/technical/intel-trust-domain-extensions.html diff --git a/Documentation/x86/x86_64/boot-options.rst b/Documentation/x86/x86_64/boot-options.rst index 07aa0007f346..03ec9cf01181 100644 --- a/Documentation/x86/x86_64/boot-options.rst +++ b/Documentation/x86/x86_64/boot-options.rst @@ -157,15 +157,6 @@ Rebooting newer BIOS, or newer board) using this option will ignore the built-in quirk table, and use the generic default reboot actions. -Non Executable Mappings -======================= - - noexec=on|off - on - Enable(default) - off - Disable - NUMA ==== @@ -310,3 +301,17 @@ Miscellaneous Do not use GB pages for kernel direct mappings. gbpages Use GB pages for kernel direct mappings. + + +AMD SEV (Secure Encrypted Virtualization) +========================================= +Options relating to AMD SEV, specified via the following format: + +:: + + sev=option1[,option2] + +The available options are: + + debug + Enable debug messages. diff --git a/Documentation/x86/zero-page.rst b/Documentation/x86/zero-page.rst index f088f5881666..45aa9cceb4f1 100644 --- a/Documentation/x86/zero-page.rst +++ b/Documentation/x86/zero-page.rst @@ -19,6 +19,7 @@ Offset/Size Proto Name Meaning 058/008 ALL tboot_addr Physical address of tboot shared page 060/010 ALL ist_info Intel SpeedStep (IST) BIOS support information (struct ist_info) +070/008 ALL acpi_rsdp_addr Physical address of ACPI RSDP table 080/010 ALL hd0_info hd0 disk parameter, OBSOLETE!! 090/010 ALL hd1_info hd1 disk parameter, OBSOLETE!! 0A0/010 ALL sys_desc_table System description table (struct sys_desc_table), @@ -27,6 +28,7 @@ Offset/Size Proto Name Meaning 0C0/004 ALL ext_ramdisk_image ramdisk_image high 32bits 0C4/004 ALL ext_ramdisk_size ramdisk_size high 32bits 0C8/004 ALL ext_cmd_line_ptr cmd_line_ptr high 32bits +13C/004 ALL cc_blob_address Physical address of Confidential Computing blob 140/080 ALL edid_info Video mode setup (struct edid_info) 1C0/020 ALL efi_info EFI 32 information (struct efi_info) 1E0/004 ALL alt_mem_k Alternative mem check, in KB diff --git a/MAINTAINERS b/MAINTAINERS index 86f1e0be8322..e7ce3f103c62 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -201,6 +201,7 @@ F: include/net/ieee80211_radiotap.h F: include/net/iw_handler.h F: include/net/wext.h F: include/uapi/linux/nl80211.h +F: include/uapi/linux/wireless.h F: net/wireless/ 8169 10/100/1000 GIGABIT ETHERNET DRIVER @@ -1043,7 +1044,6 @@ F: arch/arm64/boot/dts/amd/amd-seattle-xgbe*.dtsi F: drivers/net/ethernet/amd/xgbe/ AMD SENSOR FUSION HUB DRIVER -M: Nehal Shah <nehal-bakulchandra.shah@amd.com> M: Basavaraj Natikar <basavaraj.natikar@amd.com> L: linux-input@vger.kernel.org S: Maintained @@ -1446,6 +1446,7 @@ F: drivers/media/i2c/aptina-pll.* AQUACOMPUTER D5 NEXT PUMP SENSOR DRIVER M: Aleksa Savic <savicaleksa83@gmail.com> +M: Jack Doan <me@jackdoan.com> L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/aquacomputer_d5next.rst @@ -2636,13 +2637,14 @@ F: sound/soc/rockchip/ N: rockchip ARM/SAMSUNG S3C, S5P AND EXYNOS ARM ARCHITECTURES -M: Krzysztof Kozlowski <krzk@kernel.org> +M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> R: Alim Akhtar <alim.akhtar@samsung.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) L: linux-samsung-soc@vger.kernel.org S: Maintained C: irc://irc.libera.chat/linux-exynos Q: https://patchwork.kernel.org/project/linux-samsung-soc/list/ +B: mailto:linux-samsung-soc@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/krzk/linux.git F: Documentation/arm/samsung/ F: Documentation/devicetree/bindings/arm/samsung/ @@ -3099,6 +3101,16 @@ S: Maintained F: Documentation/devicetree/bindings/mmc/aspeed,sdhci.yaml F: drivers/mmc/host/sdhci-of-aspeed* +ASPEED SMC SPI DRIVER +M: Chin-Ting Kuo <chin-ting_kuo@aspeedtech.com> +M: Cédric Le Goater <clg@kaod.org> +L: linux-aspeed@lists.ozlabs.org (moderated for non-subscribers) +L: openbmc@lists.ozlabs.org (moderated for non-subscribers) +L: linux-spi@vger.kernel.org +S: Maintained +F: Documentation/devicetree/bindings/spi/aspeed,ast2600-fmc.yaml +F: drivers/spi/spi-aspeed-smc.c + ASPEED VIDEO ENGINE DRIVER M: Eddie James <eajames@linux.ibm.com> L: linux-media@vger.kernel.org @@ -3569,8 +3581,9 @@ M: Andy Gospodarek <andy@greyhouse.net> L: netdev@vger.kernel.org S: Supported W: http://sourceforge.net/projects/bonding/ +F: Documentation/networking/bonding.rst F: drivers/net/bonding/ -F: include/net/bonding.h +F: include/net/bond* F: include/uapi/linux/if_bonding.h BOSCH SENSORTEC BMA400 ACCELEROMETER IIO DRIVER @@ -3742,7 +3755,7 @@ F: include/linux/platform_data/b53.h BROADCOM BCM2711/BCM2835 ARM ARCHITECTURE M: Nicolas Saenz Julienne <nsaenz@kernel.org> -L: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: linux-rpi-kernel@lists.infradead.org (moderated for non-subscribers) L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained @@ -3757,7 +3770,7 @@ BROADCOM BCM281XX/BCM11XXX/BCM216XX ARM ARCHITECTURE M: Florian Fainelli <f.fainelli@gmail.com> M: Ray Jui <rjui@broadcom.com> M: Scott Branden <sbranden@broadcom.com> -M: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> S: Maintained T: git git://github.com/broadcom/mach-bcm F: arch/arm/mach-bcm/ @@ -3777,7 +3790,7 @@ F: arch/mips/include/asm/mach-bcm47xx/* BROADCOM BCM4908 ETHERNET DRIVER M: Rafał Miłecki <rafal@milecki.pl> -M: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: netdev@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/net/brcm,bcm4908-enet.yaml @@ -3786,7 +3799,7 @@ F: drivers/net/ethernet/broadcom/unimac.h BROADCOM BCM4908 PINMUX DRIVER M: Rafał Miłecki <rafal@milecki.pl> -M: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: linux-gpio@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/pinctrl/brcm,bcm4908-pinctrl.yaml @@ -3796,7 +3809,7 @@ BROADCOM BCM5301X ARM ARCHITECTURE M: Florian Fainelli <f.fainelli@gmail.com> M: Hauke Mehrtens <hauke@hauke-m.de> M: Rafał Miłecki <zajec5@gmail.com> -M: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained F: arch/arm/boot/dts/bcm470* @@ -3807,7 +3820,7 @@ F: arch/arm/mach-bcm/bcm_5301x.c BROADCOM BCM53573 ARM ARCHITECTURE M: Florian Fainelli <f.fainelli@gmail.com> M: Rafał Miłecki <rafal@milecki.pl> -L: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained F: arch/arm/boot/dts/bcm47189* @@ -3815,7 +3828,7 @@ F: arch/arm/boot/dts/bcm53573* BROADCOM BCM63XX ARM ARCHITECTURE M: Florian Fainelli <f.fainelli@gmail.com> -M: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained T: git git://github.com/broadcom/stblinux.git @@ -3829,7 +3842,7 @@ F: drivers/usb/gadget/udc/bcm63xx_udc.* BROADCOM BCM7XXX ARM ARCHITECTURE M: Florian Fainelli <f.fainelli@gmail.com> -M: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained T: git git://github.com/broadcom/stblinux.git @@ -3847,21 +3860,21 @@ N: bcm7120 BROADCOM BDC DRIVER M: Al Cooper <alcooperx@gmail.com> L: linux-usb@vger.kernel.org -L: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> S: Maintained F: Documentation/devicetree/bindings/usb/brcm,bdc.yaml F: drivers/usb/gadget/udc/bdc/ BROADCOM BMIPS CPUFREQ DRIVER M: Markus Mayer <mmayer@broadcom.com> -M: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: linux-pm@vger.kernel.org S: Maintained F: drivers/cpufreq/bmips-cpufreq.c BROADCOM BMIPS MIPS ARCHITECTURE M: Florian Fainelli <f.fainelli@gmail.com> -L: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: linux-mips@vger.kernel.org S: Maintained T: git git://github.com/broadcom/stblinux.git @@ -3912,7 +3925,9 @@ BROADCOM BNXT_EN 50 GIGABIT ETHERNET DRIVER M: Michael Chan <michael.chan@broadcom.com> L: netdev@vger.kernel.org S: Supported +F: drivers/firmware/broadcom/tee_bnxt_fw.c F: drivers/net/ethernet/broadcom/bnxt/ +F: include/linux/firmware/broadcom/tee_bnxt_fw.h BROADCOM BRCM80211 IEEE802.11n WIRELESS DRIVER M: Arend van Spriel <aspriel@gmail.com> @@ -3927,53 +3942,53 @@ F: drivers/net/wireless/broadcom/brcm80211/ BROADCOM BRCMSTB GPIO DRIVER M: Doug Berger <opendmb@gmail.com> M: Florian Fainelli <f.fainelli@gmail.com> -L: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> S: Supported F: Documentation/devicetree/bindings/gpio/brcm,brcmstb-gpio.yaml F: drivers/gpio/gpio-brcmstb.c BROADCOM BRCMSTB I2C DRIVER M: Kamal Dasu <kdasu.kdev@gmail.com> +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: linux-i2c@vger.kernel.org -L: bcm-kernel-feedback-list@broadcom.com S: Supported F: Documentation/devicetree/bindings/i2c/brcm,brcmstb-i2c.yaml F: drivers/i2c/busses/i2c-brcmstb.c BROADCOM BRCMSTB UART DRIVER M: Al Cooper <alcooperx@gmail.com> +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: linux-serial@vger.kernel.org -L: bcm-kernel-feedback-list@broadcom.com S: Maintained F: Documentation/devicetree/bindings/serial/brcm,bcm7271-uart.yaml F: drivers/tty/serial/8250/8250_bcm7271.c BROADCOM BRCMSTB USB EHCI DRIVER M: Al Cooper <alcooperx@gmail.com> +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: linux-usb@vger.kernel.org -L: bcm-kernel-feedback-list@broadcom.com S: Maintained F: Documentation/devicetree/bindings/usb/brcm,bcm7445-ehci.yaml F: drivers/usb/host/ehci-brcm.* BROADCOM BRCMSTB USB PIN MAP DRIVER M: Al Cooper <alcooperx@gmail.com> +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: linux-usb@vger.kernel.org -L: bcm-kernel-feedback-list@broadcom.com S: Maintained F: Documentation/devicetree/bindings/usb/brcm,usb-pinmap.yaml F: drivers/usb/misc/brcmstb-usb-pinmap.c BROADCOM BRCMSTB USB2 and USB3 PHY DRIVER M: Al Cooper <alcooperx@gmail.com> +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: linux-kernel@vger.kernel.org -L: bcm-kernel-feedback-list@broadcom.com S: Maintained F: drivers/phy/broadcom/phy-brcm-usb* BROADCOM ETHERNET PHY DRIVERS M: Florian Fainelli <f.fainelli@gmail.com> -L: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: netdev@vger.kernel.org S: Supported F: Documentation/devicetree/bindings/net/broadcom-bcm87xx.txt @@ -3984,7 +3999,7 @@ F: include/linux/brcmphy.h BROADCOM GENET ETHERNET DRIVER M: Doug Berger <opendmb@gmail.com> M: Florian Fainelli <f.fainelli@gmail.com> -L: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: netdev@vger.kernel.org S: Supported F: Documentation/devicetree/bindings/net/brcm,bcmgenet.yaml @@ -3998,7 +4013,7 @@ F: include/linux/platform_data/mdio-bcm-unimac.h BROADCOM IPROC ARM ARCHITECTURE M: Ray Jui <rjui@broadcom.com> M: Scott Branden <sbranden@broadcom.com> -M: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained T: git git://github.com/broadcom/stblinux.git @@ -4026,7 +4041,7 @@ N: stingray BROADCOM IPROC GBIT ETHERNET DRIVER M: Rafał Miłecki <rafal@milecki.pl> -M: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: netdev@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/net/brcm,amac.yaml @@ -4035,7 +4050,7 @@ F: drivers/net/ethernet/broadcom/unimac.h BROADCOM KONA GPIO DRIVER M: Ray Jui <rjui@broadcom.com> -L: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> S: Supported F: Documentation/devicetree/bindings/gpio/brcm,kona-gpio.txt F: drivers/gpio/gpio-bcm-kona.c @@ -4068,7 +4083,7 @@ F: drivers/firmware/broadcom/* BROADCOM PMB (POWER MANAGEMENT BUS) DRIVER M: Rafał Miłecki <rafal@milecki.pl> M: Florian Fainelli <f.fainelli@gmail.com> -M: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: linux-pm@vger.kernel.org S: Maintained T: git git://github.com/broadcom/stblinux.git @@ -4084,7 +4099,7 @@ F: include/linux/bcma/ BROADCOM SPI DRIVER M: Kamal Dasu <kdasu.kdev@gmail.com> -M: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> S: Maintained F: Documentation/devicetree/bindings/spi/brcm,spi-bcm-qspi.yaml F: drivers/spi/spi-bcm-qspi.* @@ -4093,7 +4108,7 @@ F: drivers/spi/spi-iproc-qspi.c BROADCOM STB AVS CPUFREQ DRIVER M: Markus Mayer <mmayer@broadcom.com> -M: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: linux-pm@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/cpufreq/brcm,stb-avs-cpu-freq.txt @@ -4101,7 +4116,7 @@ F: drivers/cpufreq/brcmstb* BROADCOM STB AVS TMON DRIVER M: Markus Mayer <mmayer@broadcom.com> -M: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: linux-pm@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/thermal/brcm,avs-tmon.yaml @@ -4109,7 +4124,7 @@ F: drivers/thermal/broadcom/brcmstb* BROADCOM STB DPFE DRIVER M: Markus Mayer <mmayer@broadcom.com> -M: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained F: Documentation/devicetree/bindings/memory-controllers/brcm,dpfe-cpu.yaml @@ -4118,8 +4133,8 @@ F: drivers/memory/brcmstb_dpfe.c BROADCOM STB NAND FLASH DRIVER M: Brian Norris <computersforpeace@gmail.com> M: Kamal Dasu <kdasu.kdev@gmail.com> +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: linux-mtd@lists.infradead.org -L: bcm-kernel-feedback-list@broadcom.com S: Maintained F: drivers/mtd/nand/raw/brcmnand/ F: include/linux/platform_data/brcmnand.h @@ -4128,7 +4143,7 @@ BROADCOM STB PCIE DRIVER M: Jim Quinlan <jim2101024@gmail.com> M: Nicolas Saenz Julienne <nsaenz@kernel.org> M: Florian Fainelli <f.fainelli@gmail.com> -M: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: linux-pci@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/pci/brcm,stb-pcie.yaml @@ -4136,7 +4151,7 @@ F: drivers/pci/controller/pcie-brcmstb.c BROADCOM SYSTEMPORT ETHERNET DRIVER M: Florian Fainelli <f.fainelli@gmail.com> -L: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: netdev@vger.kernel.org S: Supported F: drivers/net/ethernet/broadcom/bcmsysport.* @@ -4153,7 +4168,7 @@ F: drivers/net/ethernet/broadcom/tg3.* BROADCOM VK DRIVER M: Scott Branden <scott.branden@broadcom.com> -L: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> S: Supported F: drivers/misc/bcm-vk/ F: include/uapi/linux/misc/bcm_vk.h @@ -4570,7 +4585,9 @@ L: keyrings@vger.kernel.org S: Maintained F: Documentation/admin-guide/module-signing.rst F: certs/ +F: scripts/check-blacklist-hashes.awk F: scripts/sign-file.c +F: tools/certs/ CFAG12864B LCD DRIVER M: Miguel Ojeda <ojeda@kernel.org> @@ -4792,6 +4809,7 @@ F: .clang-format CLANG/LLVM BUILD SUPPORT M: Nathan Chancellor <nathan@kernel.org> M: Nick Desaulniers <ndesaulniers@google.com> +R: Tom Rix <trix@redhat.com> L: llvm@lists.linux.dev S: Supported W: https://clangbuiltlinux.github.io/ @@ -5435,6 +5453,7 @@ F: net/ax25/sysctl_net_ax25.c DATA ACCESS MONITOR M: SeongJae Park <sj@kernel.org> +L: damon@lists.linux.dev L: linux-mm@kvack.org S: Maintained F: Documentation/ABI/testing/sysfs-kernel-mm-damon @@ -5716,7 +5735,7 @@ W: http://lanana.org/docs/device-list/index.html DEVICE RESOURCE MANAGEMENT HELPERS M: Hans de Goede <hdegoede@redhat.com> -R: Matti Vaittinen <matti.vaittinen@fi.rohmeurope.com> +R: Matti Vaittinen <mazziesaccount@gmail.com> S: Maintained F: include/linux/devm-helpers.h @@ -5913,7 +5932,7 @@ R: Benjamin Gaignard <benjamin.gaignard@collabora.com> R: Liam Mark <lmark@codeaurora.org> R: Laura Abbott <labbott@redhat.com> R: Brian Starkey <Brian.Starkey@arm.com> -R: John Stultz <john.stultz@linaro.org> +R: John Stultz <jstultz@google.com> L: linux-media@vger.kernel.org L: dri-devel@lists.freedesktop.org L: linaro-mm-sig@lists.linaro.org (moderated for non-subscribers) @@ -6589,7 +6608,7 @@ F: drivers/gpu/drm/gma500/ DRM DRIVERS FOR HISILICON M: Xinliang Liu <xinliang.liu@linaro.org> M: Tian Tao <tiantao6@hisilicon.com> -R: John Stultz <john.stultz@linaro.org> +R: John Stultz <jstultz@google.com> R: Xinwei Kong <kong.kongxinwei@hisilicon.com> R: Chen Feng <puck.chen@hisilicon.com> L: dri-devel@lists.freedesktop.org @@ -7385,7 +7404,6 @@ L: linux-mm@kvack.org S: Supported T: git git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git for-next/execve F: arch/alpha/kernel/binfmt_loader.c -F: arch/x86/ia32/ia32_aout.c F: fs/*binfmt_*.c F: fs/exec.c F: include/linux/binfmts.h @@ -7501,7 +7519,7 @@ F: Documentation/hwmon/f71805f.rst F: drivers/hwmon/f71805f.c FADDR2LINE -M: Josh Poimboeuf <jpoimboe@redhat.com> +M: Josh Poimboeuf <jpoimboe@kernel.org> S: Maintained F: scripts/faddr2line @@ -8114,7 +8132,7 @@ M: Ingo Molnar <mingo@redhat.com> R: Peter Zijlstra <peterz@infradead.org> R: Darren Hart <dvhart@infradead.org> R: Davidlohr Bueso <dave@stgolabs.net> -R: André Almeida <andrealmeid@collabora.com> +R: André Almeida <andrealmeid@igalia.com> L: linux-kernel@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git locking/core @@ -8387,7 +8405,7 @@ M: Linus Walleij <linus.walleij@linaro.org> M: Bartosz Golaszewski <brgl@bgdev.pl> L: linux-gpio@vger.kernel.org S: Maintained -T: git git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-gpio.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/brgl/linux.git F: Documentation/ABI/obsolete/sysfs-gpio F: Documentation/ABI/testing/gpio-cdev F: Documentation/admin-guide/gpio/ @@ -8682,7 +8700,6 @@ F: include/linux/cciss*.h F: include/uapi/linux/cciss*.h HFI1 DRIVER -M: Mike Marciniszyn <mike.marciniszyn@cornelisnetworks.com> M: Dennis Dalessandro <dennis.dalessandro@cornelisnetworks.com> L: linux-rdma@vger.kernel.org S: Supported @@ -8755,6 +8772,14 @@ F: drivers/hid/hid-sensor-* F: drivers/iio/*/hid-* F: include/linux/hid-sensor-* +HID WACOM DRIVER +M: Ping Cheng <ping.cheng@wacom.com> +M: Jason Gerecke <jason.gerecke@wacom.com> +L: linux-input@vger.kernel.org +S: Maintained +F: drivers/hid/wacom.h +F: drivers/hid/wacom_* + HIGH-RESOLUTION TIMERS, CLOCKEVENTS M: Thomas Gleixner <tglx@linutronix.de> L: linux-kernel@vger.kernel.org @@ -8851,7 +8876,7 @@ F: Documentation/devicetree/bindings/net/hisilicon*.txt F: drivers/net/ethernet/hisilicon/ HIKEY960 ONBOARD USB GPIO HUB DRIVER -M: John Stultz <john.stultz@linaro.org> +M: John Stultz <jstultz@google.com> L: linux-kernel@vger.kernel.org S: Maintained F: drivers/misc/hisi_hikey_usb.c @@ -9343,14 +9368,12 @@ F: drivers/pci/hotplug/rpaphp* IBM Power SRIOV Virtual NIC Device Driver M: Dany Madden <drt@linux.ibm.com> -M: Sukadev Bhattiprolu <sukadev@linux.ibm.com> R: Thomas Falcon <tlfalcon@linux.ibm.com> L: netdev@vger.kernel.org S: Supported F: drivers/net/ethernet/ibm/ibmvnic.* IBM Power Virtual Accelerator Switchboard -M: Sukadev Bhattiprolu <sukadev@linux.ibm.com> L: linuxppc-dev@lists.ozlabs.org S: Supported F: arch/powerpc/include/asm/vas.h @@ -9605,6 +9628,7 @@ F: drivers/iio/pressure/dps310.c INFINIBAND SUBSYSTEM M: Jason Gunthorpe <jgg@nvidia.com> +M: Leon Romanovsky <leonro@nvidia.com> L: linux-rdma@vger.kernel.org S: Supported W: https://github.com/linux-rdma/rdma-core @@ -9866,6 +9890,14 @@ B: https://bugzilla.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/lenb/linux.git F: drivers/idle/intel_idle.c +INTEL IN FIELD SCAN (IFS) DEVICE +M: Jithu Joseph <jithu.joseph@intel.com> +R: Ashok Raj <ashok.raj@intel.com> +R: Tony Luck <tony.luck@intel.com> +S: Maintained +F: drivers/platform/x86/intel/ifs +F: include/trace/events/intel_ifs.h + INTEL INTEGRATED SENSOR HUB DRIVER M: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com> M: Jiri Kosina <jikos@kernel.org> @@ -10135,7 +10167,7 @@ S: Supported F: drivers/net/wireless/intel/iwlegacy/ INTEL WIRELESS WIFI LINK (iwlwifi) -M: Luca Coelho <luciano.coelho@intel.com> +M: Gregory Greenman <gregory.greenman@intel.com> L: linux-wireless@vger.kernel.org S: Supported W: https://wireless.wiki.kernel.org/en/users/drivers/iwlwifi @@ -10244,8 +10276,6 @@ F: drivers/net/ethernet/sgi/ioc3-eth.c IOMAP FILESYSTEM LIBRARY M: Christoph Hellwig <hch@infradead.org> M: Darrick J. Wong <djwong@kernel.org> -M: linux-xfs@vger.kernel.org -M: linux-fsdevel@vger.kernel.org L: linux-xfs@vger.kernel.org L: linux-fsdevel@vger.kernel.org S: Supported @@ -10376,6 +10406,7 @@ F: include/linux/isapnp.h ISCSI M: Lee Duncan <lduncan@suse.com> M: Chris Leech <cleech@redhat.com> +M: Mike Christie <michael.christie@oracle.com> L: open-iscsi@googlegroups.com L: linux-scsi@vger.kernel.org S: Maintained @@ -10553,6 +10584,7 @@ M: Andrey Ryabinin <ryabinin.a.a@gmail.com> R: Alexander Potapenko <glider@google.com> R: Andrey Konovalov <andreyknvl@gmail.com> R: Dmitry Vyukov <dvyukov@google.com> +R: Vincenzo Frascino <vincenzo.frascino@arm.com> L: kasan-dev@googlegroups.com S: Maintained F: Documentation/dev-tools/kasan.rst @@ -10860,6 +10892,15 @@ S: Supported F: include/keys/trusted_tee.h F: security/keys/trusted-keys/trusted_tee.c +KEYS-TRUSTED-CAAM +M: Ahmad Fatoum <a.fatoum@pengutronix.de> +R: Pengutronix Kernel Team <kernel@pengutronix.de> +L: linux-integrity@vger.kernel.org +L: keyrings@vger.kernel.org +S: Maintained +F: include/keys/trusted_caam.h +F: security/keys/trusted-keys/trusted_caam.c + KEYS/KEYRINGS M: David Howells <dhowells@redhat.com> M: Jarkko Sakkinen <jarkko@kernel.org> @@ -11215,7 +11256,7 @@ F: scripts/spdxcheck.py LINEAR RANGES HELPERS M: Mark Brown <broonie@kernel.org> -R: Matti Vaittinen <matti.vaittinen@fi.rohmeurope.com> +R: Matti Vaittinen <mazziesaccount@gmail.com> F: lib/linear_ranges.c F: lib/test_linear_ranges.c F: include/linux/linear_range.h @@ -11352,7 +11393,7 @@ F: drivers/mmc/host/litex_mmc.c N: litex LIVE PATCHING -M: Josh Poimboeuf <jpoimboe@redhat.com> +M: Josh Poimboeuf <jpoimboe@kernel.org> M: Jiri Kosina <jikos@kernel.org> M: Miroslav Benes <mbenes@suse.cz> M: Petr Mladek <pmladek@suse.com> @@ -11832,7 +11873,7 @@ MARVELL XENON MMC/SD/SDIO HOST CONTROLLER DRIVER M: Hu Ziji <huziji@marvell.com> L: linux-mmc@vger.kernel.org S: Supported -F: Documentation/devicetree/bindings/mmc/marvell,xenon-sdhci.txt +F: Documentation/devicetree/bindings/mmc/marvell,xenon-sdhci.yaml F: drivers/mmc/host/sdhci-xenon* MATROX FRAMEBUFFER DRIVER @@ -11912,7 +11953,7 @@ F: drivers/iio/proximity/mb1232.c MAXIM MAX17040 FAMILY FUEL GAUGE DRIVERS R: Iskren Chernev <iskren.chernev@gmail.com> -R: Krzysztof Kozlowski <krzk@kernel.org> +R: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> R: Marek Szyprowski <m.szyprowski@samsung.com> R: Matheus Castello <matheus@castello.eng.br> L: linux-pm@vger.kernel.org @@ -11922,7 +11963,7 @@ F: drivers/power/supply/max17040_battery.c MAXIM MAX17042 FAMILY FUEL GAUGE DRIVERS R: Hans de Goede <hdegoede@redhat.com> -R: Krzysztof Kozlowski <krzk@kernel.org> +R: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> R: Marek Szyprowski <m.szyprowski@samsung.com> R: Sebastian Krzyszkowiak <sebastian.krzyszkowiak@puri.sm> R: Purism Kernel Team <kernel@puri.sm> @@ -11974,10 +12015,11 @@ F: Documentation/devicetree/bindings/power/supply/maxim,max77976.yaml F: drivers/power/supply/max77976_charger.c MAXIM MUIC CHARGER DRIVERS FOR EXYNOS BASED BOARDS -M: Krzysztof Kozlowski <krzk@kernel.org> +M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> M: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com> L: linux-pm@vger.kernel.org S: Supported +B: mailto:linux-samsung-soc@vger.kernel.org F: Documentation/devicetree/bindings/power/supply/maxim,max14577.yaml F: Documentation/devicetree/bindings/power/supply/maxim,max77693.yaml F: drivers/power/supply/max14577_charger.c @@ -11985,10 +12027,11 @@ F: drivers/power/supply/max77693_charger.c MAXIM PMIC AND MUIC DRIVERS FOR EXYNOS BASED BOARDS M: Chanwoo Choi <cw00.choi@samsung.com> -M: Krzysztof Kozlowski <krzk@kernel.org> +M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> M: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com> L: linux-kernel@vger.kernel.org S: Supported +B: mailto:linux-samsung-soc@vger.kernel.org F: Documentation/devicetree/bindings/*/maxim,max14577.yaml F: Documentation/devicetree/bindings/*/maxim,max77686.yaml F: Documentation/devicetree/bindings/*/maxim,max77693.yaml @@ -12158,7 +12201,7 @@ T: git git://linuxtv.org/media_tree.git F: Documentation/admin-guide/media/imx7.rst F: Documentation/devicetree/bindings/media/nxp,imx-mipi-csi2.yaml F: Documentation/devicetree/bindings/media/nxp,imx7-csi.yaml -F: drivers/media/platform/imx/imx-mipi-csis.c +F: drivers/media/platform/nxp/imx-mipi-csis.c F: drivers/staging/media/imx/imx7-media-csi.c MEDIA DRIVERS FOR HELENE @@ -12213,7 +12256,7 @@ L: linux-media@vger.kernel.org L: linux-tegra@vger.kernel.org S: Maintained T: git git://linuxtv.org/media_tree.git -F: Documentation/devicetree/bindings/media/nvidia,tegra-vde.txt +F: Documentation/devicetree/bindings/media/nvidia,tegra-vde.yaml F: drivers/media/platform/nvidia/tegra-vde/ MEDIA DRIVERS FOR RENESAS - CEU @@ -12376,10 +12419,9 @@ F: drivers/iommu/mtk_iommu* F: include/dt-bindings/memory/mt*-port.h MEDIATEK JPEG DRIVER -M: Rick Chang <rick.chang@mediatek.com> M: Bin Liu <bin.liu@mediatek.com> S: Supported -F: Documentation/devicetree/bindings/media/mediatek-jpeg-decoder.txt +F: Documentation/devicetree/bindings/media/mediatek-jpeg-*.yaml F: drivers/media/platform/mediatek/jpeg/ MEDIATEK MDP DRIVER @@ -12395,7 +12437,7 @@ MEDIATEK MEDIA DRIVER M: Tiffany Lin <tiffany.lin@mediatek.com> M: Andrew-CT Chen <andrew-ct.chen@mediatek.com> S: Supported -F: Documentation/devicetree/bindings/media/mediatek-vcodec.txt +F: Documentation/devicetree/bindings/media/mediatek,vcodec*.yaml F: Documentation/devicetree/bindings/media/mediatek-vpu.txt F: drivers/media/platform/mediatek/vcodec/ F: drivers/media/platform/mediatek/vpu/ @@ -12408,7 +12450,7 @@ F: drivers/mmc/host/mtk-sd.c MEDIATEK MT76 WIRELESS LAN DRIVER M: Felix Fietkau <nbd@nbd.name> -M: Lorenzo Bianconi <lorenzo.bianconi83@gmail.com> +M: Lorenzo Bianconi <lorenzo@kernel.org> M: Ryder Lee <ryder.lee@mediatek.com> R: Shayne Chen <shayne.chen@mediatek.com> R: Sean Wang <sean.wang@mediatek.com> @@ -12679,9 +12721,10 @@ F: mm/memblock.c F: tools/testing/memblock/ MEMORY CONTROLLER DRIVERS -M: Krzysztof Kozlowski <krzk@kernel.org> +M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> L: linux-kernel@vger.kernel.org S: Maintained +B: mailto:krzysztof.kozlowski@linaro.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/krzk/linux-mem-ctrl.git F: Documentation/devicetree/bindings/memory-controllers/ F: drivers/memory/ @@ -13535,12 +13578,21 @@ M: Samuel Mendoza-Jonas <sam@mendozajonas.com> S: Maintained F: net/ncsi/ -NCT6775 HARDWARE MONITOR DRIVER +NCT6775 HARDWARE MONITOR DRIVER - CORE & PLATFORM DRIVER M: Guenter Roeck <linux@roeck-us.net> L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/nct6775.rst -F: drivers/hwmon/nct6775.c +F: drivers/hwmon/nct6775-core.c +F: drivers/hwmon/nct6775-platform.c +F: drivers/hwmon/nct6775.h + +NCT6775 HARDWARE MONITOR DRIVER - I2C DRIVER +M: Zev Weiss <zev@bewilderbeest.net> +L: linux-hwmon@vger.kernel.org +S: Maintained +F: Documentation/devicetree/bindings/hwmon/nuvoton,nct6775.yaml +F: drivers/hwmon/nct6775-i2c.c NETDEVSIM M: Jakub Kicinski <kuba@kernel.org> @@ -13630,6 +13682,7 @@ F: net/core/drop_monitor.c NETWORKING DRIVERS M: "David S. Miller" <davem@davemloft.net> +M: Eric Dumazet <edumazet@google.com> M: Jakub Kicinski <kuba@kernel.org> M: Paolo Abeni <pabeni@redhat.com> L: netdev@vger.kernel.org @@ -13677,6 +13730,7 @@ F: tools/testing/selftests/drivers/net/dsa/ NETWORKING [GENERAL] M: "David S. Miller" <davem@davemloft.net> +M: Eric Dumazet <edumazet@google.com> M: Jakub Kicinski <kuba@kernel.org> M: Paolo Abeni <pabeni@redhat.com> L: netdev@vger.kernel.org @@ -13823,10 +13877,11 @@ F: include/uapi/linux/nexthop.h F: net/ipv4/nexthop.c NFC SUBSYSTEM -M: Krzysztof Kozlowski <krzk@kernel.org> +M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> L: linux-nfc@lists.01.org (subscribers-only) L: netdev@vger.kernel.org S: Maintained +B: mailto:linux-nfc@lists.01.org F: Documentation/devicetree/bindings/net/nfc/ F: drivers/nfc/ F: include/linux/platform_data/nfcmrvl.h @@ -14140,7 +14195,7 @@ F: Documentation/devicetree/bindings/regulator/nxp,pf8x00-regulator.yaml F: drivers/regulator/pf8x00-regulator.c NXP PTN5150A CC LOGIC AND EXTCON DRIVER -M: Krzysztof Kozlowski <krzk@kernel.org> +M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> L: linux-kernel@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/extcon/extcon-ptn5150.yaml @@ -14197,7 +14252,7 @@ R: NXP Linux Team <linux-imx@nxp.com> L: linux-media@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/media/nxp,imx8-jpeg.yaml -F: drivers/media/platform/imx-jpeg +F: drivers/media/platform/nxp/imx-jpeg NZXT-KRAKEN2 HARDWARE MONITORING DRIVER M: Jonas Malaco <jonas@protocubo.io> @@ -14222,7 +14277,7 @@ F: lib/objagg.c F: lib/test_objagg.c OBJTOOL -M: Josh Poimboeuf <jpoimboe@redhat.com> +M: Josh Poimboeuf <jpoimboe@kernel.org> M: Peter Zijlstra <peterz@infradead.org> S: Supported F: tools/objtool/ @@ -14370,7 +14425,6 @@ F: arch/arm/*omap*/*pm* F: drivers/cpufreq/omap-cpufreq.c OMAP POWERDOMAIN SOC ADAPTATION LAYER SUPPORT -M: Rajendra Nayak <rnayak@codeaurora.org> M: Paul Walmsley <paul@pwsan.com> L: linux-omap@vger.kernel.org S: Maintained @@ -14663,7 +14717,6 @@ F: drivers/rtc/rtc-optee.c OPA-VNIC DRIVER M: Dennis Dalessandro <dennis.dalessandro@cornelisnetworks.com> -M: Mike Marciniszyn <mike.marciniszyn@cornelisnetworks.com> L: linux-rdma@vger.kernel.org S: Supported F: drivers/infiniband/ulp/opa_vnic @@ -14694,7 +14747,7 @@ F: scripts/dtc/ OPEN FIRMWARE AND FLATTENED DEVICE TREE BINDINGS M: Rob Herring <robh+dt@kernel.org> -M: Krzysztof Kozlowski <krzk+dt@kernel.org> +M: Krzysztof Kozlowski <krzysztof.kozlowski+dt@linaro.org> L: devicetree@vger.kernel.org S: Maintained C: irc://irc.libera.chat/devicetree @@ -14832,6 +14885,19 @@ F: Documentation/core-api/padata.rst F: include/linux/padata.h F: kernel/padata.c +PAGE CACHE +M: Matthew Wilcox (Oracle) <willy@infradead.org> +L: linux-fsdevel@vger.kernel.org +S: Supported +T: git git://git.infradead.org/users/willy/pagecache.git +F: Documentation/filesystems/locking.rst +F: Documentation/filesystems/vfs.rst +F: include/linux/pagemap.h +F: mm/filemap.c +F: mm/page-writeback.c +F: mm/readahead.c +F: mm/truncate.c + PAGE POOL M: Jesper Dangaard Brouer <hawk@kernel.org> M: Ilias Apalodimas <ilias.apalodimas@linaro.org> @@ -15474,7 +15540,8 @@ F: tools/perf/ PERFORMANCE EVENTS TOOLING ARM64 R: John Garry <john.garry@huawei.com> R: Will Deacon <will@kernel.org> -R: Mathieu Poirier <mathieu.poirier@linaro.org> +R: James Clark <james.clark@arm.com> +R: Mike Leach <mike.leach@linaro.org> R: Leo Yan <leo.yan@linaro.org> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Supported @@ -15606,7 +15673,7 @@ F: drivers/pinctrl/renesas/ PIN CONTROLLER - SAMSUNG M: Tomasz Figa <tomasz.figa@gmail.com> -M: Krzysztof Kozlowski <krzk@kernel.org> +M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> M: Sylwester Nawrocki <s.nawrocki@samsung.com> R: Alim Akhtar <alim.akhtar@samsung.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) @@ -15614,6 +15681,7 @@ L: linux-samsung-soc@vger.kernel.org S: Maintained C: irc://irc.libera.chat/linux-exynos Q: https://patchwork.kernel.org/project/linux-samsung-soc/list/ +B: mailto:linux-samsung-soc@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/pinctrl/samsung.git F: Documentation/devicetree/bindings/pinctrl/samsung,pinctrl*yaml F: drivers/pinctrl/samsung/ @@ -15862,7 +15930,9 @@ F: kernel/printk/ PRINTK INDEXING R: Chris Down <chris@chrisdown.name> S: Maintained +F: Documentation/core-api/printk-index.rst F: kernel/printk/index.c +K: printk_index PROC FILESYSTEM L: linux-kernel@vger.kernel.org @@ -16105,7 +16175,6 @@ F: include/uapi/linux/qemu_fw_cfg.h QIB DRIVER M: Dennis Dalessandro <dennis.dalessandro@cornelisnetworks.com> -M: Mike Marciniszyn <mike.marciniszyn@cornelisnetworks.com> L: linux-rdma@vger.kernel.org S: Supported F: drivers/infiniband/hw/qib/ @@ -16623,7 +16692,6 @@ F: drivers/net/ethernet/rdc/r6040.c RDMAVT - RDMA verbs software M: Dennis Dalessandro <dennis.dalessandro@cornelisnetworks.com> -M: Mike Marciniszyn <mike.marciniszyn@cornelisnetworks.com> L: linux-rdma@vger.kernel.org S: Supported F: drivers/infiniband/sw/rdmavt @@ -17018,8 +17086,7 @@ S: Odd Fixes F: drivers/tty/serial/rp2.* ROHM BD99954 CHARGER IC -R: Matti Vaittinen <matti.vaittinen@fi.rohmeurope.com> -L: linux-power@fi.rohmeurope.com +R: Matti Vaittinen <mazziesaccount@gmail.com> S: Supported F: drivers/power/supply/bd99954-charger.c F: drivers/power/supply/bd99954-charger.h @@ -17042,8 +17109,7 @@ F: drivers/regulator/bd9571mwv-regulator.c F: include/linux/mfd/bd9571mwv.h ROHM POWER MANAGEMENT IC DEVICE DRIVERS -R: Matti Vaittinen <matti.vaittinen@fi.rohmeurope.com> -L: linux-power@fi.rohmeurope.com +R: Matti Vaittinen <mazziesaccount@gmail.com> S: Supported F: drivers/clk/clk-bd718x7.c F: drivers/gpio/gpio-bd71815.c @@ -17285,7 +17351,7 @@ W: http://www.ibm.com/developerworks/linux/linux390/ F: drivers/s390/scsi/zfcp_* S3C ADC BATTERY DRIVER -M: Krzysztof Kozlowski <krzk@kernel.org> +M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> L: linux-samsung-soc@vger.kernel.org S: Odd Fixes F: drivers/power/supply/s3c_adc_battery.c @@ -17330,15 +17396,16 @@ F: Documentation/admin-guide/LSM/SafeSetID.rst F: security/safesetid/ SAMSUNG AUDIO (ASoC) DRIVERS -M: Krzysztof Kozlowski <krzk@kernel.org> +M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> M: Sylwester Nawrocki <s.nawrocki@samsung.com> L: alsa-devel@alsa-project.org (moderated for non-subscribers) S: Supported +B: mailto:linux-samsung-soc@vger.kernel.org F: Documentation/devicetree/bindings/sound/samsung* F: sound/soc/samsung/ SAMSUNG EXYNOS PSEUDO RANDOM NUMBER GENERATOR (RNG) DRIVER -M: Krzysztof Kozlowski <krzk@kernel.org> +M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> L: linux-crypto@vger.kernel.org L: linux-samsung-soc@vger.kernel.org S: Maintained @@ -17373,11 +17440,12 @@ S: Maintained F: drivers/platform/x86/samsung-laptop.c SAMSUNG MULTIFUNCTION PMIC DEVICE DRIVERS -M: Krzysztof Kozlowski <krzk@kernel.org> +M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> M: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com> L: linux-kernel@vger.kernel.org L: linux-samsung-soc@vger.kernel.org S: Supported +B: mailto:linux-samsung-soc@vger.kernel.org F: Documentation/devicetree/bindings/clock/samsung,s2mps11.yaml F: Documentation/devicetree/bindings/mfd/samsung,s2m*.yaml F: Documentation/devicetree/bindings/mfd/samsung,s5m*.yaml @@ -17399,7 +17467,7 @@ F: drivers/media/platform/samsung/s3c-camif/ F: include/media/drv-intf/s3c_camif.h SAMSUNG S3FWRN5 NFC DRIVER -M: Krzysztof Kozlowski <krzk@kernel.org> +M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> M: Krzysztof Opasiak <k.opasiak@samsung.com> L: linux-nfc@lists.01.org (subscribers-only) S: Maintained @@ -17421,7 +17489,7 @@ S: Supported F: drivers/media/i2c/s5k5baf.c SAMSUNG S5P Security SubSystem (SSS) DRIVER -M: Krzysztof Kozlowski <krzk@kernel.org> +M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> M: Vladimir Zapolskiy <vz@mleia.com> L: linux-crypto@vger.kernel.org L: linux-samsung-soc@vger.kernel.org @@ -17456,7 +17524,7 @@ F: include/linux/clk/samsung.h F: include/linux/platform_data/clk-s3c2410.h SAMSUNG SPI DRIVERS -M: Krzysztof Kozlowski <krzk@kernel.org> +M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> M: Andi Shyti <andi@etezian.org> L: linux-spi@vger.kernel.org L: linux-samsung-soc@vger.kernel.org @@ -17474,7 +17542,7 @@ F: drivers/net/ethernet/samsung/sxgbe/ SAMSUNG THERMAL DRIVER M: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com> -M: Krzysztof Kozlowski <krzk@kernel.org> +M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> L: linux-pm@vger.kernel.org L: linux-samsung-soc@vger.kernel.org S: Maintained @@ -17515,6 +17583,7 @@ R: Steven Rostedt <rostedt@goodmis.org> (SCHED_FIFO/SCHED_RR) R: Ben Segall <bsegall@google.com> (CONFIG_CFS_BANDWIDTH) R: Mel Gorman <mgorman@suse.de> (CONFIG_NUMA_BALANCING) R: Daniel Bristot de Oliveira <bristot@redhat.com> (SCHED_DEADLINE) +R: Valentin Schneider <vschneid@redhat.com> (TOPOLOGY) L: linux-kernel@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git sched/core @@ -17658,8 +17727,8 @@ K: \bTIF_SECCOMP\b SECURE DIGITAL HOST CONTROLLER INTERFACE (SDHCI) Broadcom BRCMSTB DRIVER M: Al Cooper <alcooperx@gmail.com> +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: linux-mmc@vger.kernel.org -L: bcm-kernel-feedback-list@broadcom.com S: Maintained F: drivers/mmc/host/sdhci-brcmstb* @@ -18103,6 +18172,7 @@ M: Joonsoo Kim <iamjoonsoo.kim@lge.com> M: Andrew Morton <akpm@linux-foundation.org> M: Vlastimil Babka <vbabka@suse.cz> R: Roman Gushchin <roman.gushchin@linux.dev> +R: Hyeonggon Yoo <42.hyeyoo@gmail.com> L: linux-mm@kvack.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/vbabka/slab.git @@ -18792,7 +18862,7 @@ F: include/dt-bindings/reset/starfive-jh7100.h STATIC BRANCH/CALL M: Peter Zijlstra <peterz@infradead.org> -M: Josh Poimboeuf <jpoimboe@redhat.com> +M: Josh Poimboeuf <jpoimboe@kernel.org> M: Jason Baron <jbaron@akamai.com> R: Steven Rostedt <rostedt@goodmis.org> R: Ard Biesheuvel <ardb@kernel.org> @@ -19541,6 +19611,7 @@ F: drivers/thermal/ F: include/linux/cpu_cooling.h F: include/linux/thermal.h F: include/uapi/linux/thermal.h +F: tools/lib/thermal/ F: tools/thermal/ THERMAL DRIVER FOR AMLOGIC SOCS @@ -19793,7 +19864,7 @@ F: drivers/net/wireless/ti/ F: include/linux/wl12xx.h TIMEKEEPING, CLOCKSOURCE CORE, NTP, ALARMTIMER -M: John Stultz <john.stultz@linaro.org> +M: John Stultz <jstultz@google.com> M: Thomas Gleixner <tglx@linutronix.de> R: Stephen Boyd <sboyd@kernel.org> L: linux-kernel@vger.kernel.org @@ -19840,6 +19911,7 @@ F: drivers/media/usb/tm6000/ TMIO/SDHI MMC DRIVER M: Wolfram Sang <wsa+renesas@sang-engineering.com> L: linux-mmc@vger.kernel.org +L: linux-renesas-soc@vger.kernel.org S: Supported F: drivers/mmc/host/renesas_sdhi* F: drivers/mmc/host/tmio_mmc* @@ -19849,6 +19921,7 @@ TMP401 HARDWARE MONITOR DRIVER M: Guenter Roeck <linux@roeck-us.net> L: linux-hwmon@vger.kernel.org S: Maintained +F: Documentation/devicetree/bindings/hwmon/ti,tmp401.yaml F: Documentation/hwmon/tmp401.rst F: drivers/hwmon/tmp401.c @@ -20532,7 +20605,6 @@ F: drivers/usb/host/uhci* USB VIDEO CLASS M: Laurent Pinchart <laurent.pinchart@ideasonboard.com> -L: linux-uvc-devel@lists.sourceforge.net (subscribers-only) L: linux-media@vger.kernel.org S: Maintained W: http://www.ideasonboard.org/uvc/ @@ -21125,7 +21197,7 @@ F: include/linux/regulator/ K: regulator_get_optional VOLTAGE AND CURRENT REGULATOR IRQ HELPERS -R: Matti Vaittinen <matti.vaittinen@fi.rohmeurope.com> +R: Matti Vaittinen <mazziesaccount@gmail.com> F: drivers/regulator/irq_helpers.c VRF @@ -21238,10 +21310,8 @@ S: Maintained F: drivers/hid/hid-wiimote* WILOCITY WIL6210 WIRELESS DRIVER -M: Maya Erez <merez@codeaurora.org> L: linux-wireless@vger.kernel.org -L: wil6210@qti.qualcomm.com -S: Supported +S: Orphan W: https://wireless.wiki.kernel.org/en/users/Drivers/wil6210 F: drivers/net/wireless/ath/wil6210/ @@ -21445,6 +21515,15 @@ F: arch/x86/include/asm/uv/ F: arch/x86/kernel/apic/x2apic_uv_x.c F: arch/x86/platform/uv/ +X86 STACK UNWINDING +M: Josh Poimboeuf <jpoimboe@kernel.org> +M: Peter Zijlstra <peterz@infradead.org> +S: Supported +F: arch/x86/include/asm/unwind*.h +F: arch/x86/kernel/dumpstack.c +F: arch/x86/kernel/stacktrace.c +F: arch/x86/kernel/unwind_*.c + X86 VDSO M: Andy Lutomirski <luto@kernel.org> L: linux-kernel@vger.kernel.org @@ -21607,7 +21686,6 @@ F: drivers/xen/*swiotlb* XFS FILESYSTEM C: irc://irc.oftc.net/xfs M: Darrick J. Wong <djwong@kernel.org> -M: linux-xfs@vger.kernel.org L: linux-xfs@vger.kernel.org S: Supported W: http://xfs.org/ diff --git a/Makefile b/Makefile index 8c7de9a72ea2..bbcd3abf2f4d 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 18 SUBLEVEL = 0 -EXTRAVERSION = -rc1 +EXTRAVERSION = NAME = Superb Owl # *DOCUMENTATION* @@ -1011,6 +1011,7 @@ include-$(CONFIG_KASAN) += scripts/Makefile.kasan include-$(CONFIG_KCSAN) += scripts/Makefile.kcsan include-$(CONFIG_UBSAN) += scripts/Makefile.ubsan include-$(CONFIG_KCOV) += scripts/Makefile.kcov +include-$(CONFIG_RANDSTRUCT) += scripts/Makefile.randstruct include-$(CONFIG_GCC_PLUGINS) += scripts/Makefile.gcc-plugins include $(addprefix $(srctree)/, $(include-y)) @@ -1302,7 +1303,7 @@ install: sub_make_done := # --------------------------------------------------------------------------- # Tools -ifdef CONFIG_STACK_VALIDATION +ifdef CONFIG_OBJTOOL prepare: tools/objtool endif diff --git a/arch/Kconfig b/arch/Kconfig index 29b0167c088b..763b1b5e4f41 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -24,6 +24,13 @@ config KEXEC_ELF config HAVE_IMA_KEXEC bool +config ARCH_HAS_SUBPAGE_FAULTS + bool + help + Select if the architecture can check permissions at sub-page + granularity (e.g. arm64 MTE). The probe_user_*() functions + must be implemented. + config HOTPLUG_SMT bool @@ -35,6 +42,7 @@ config KPROBES depends on MODULES depends on HAVE_KPROBES select KALLSYMS + select TASKS_RCU if PREEMPTION help Kprobes allows you to trap at almost any kernel address and execute a callback function. register_kprobe() establishes @@ -46,6 +54,7 @@ config JUMP_LABEL bool "Optimize very unlikely/likely branches" depends on HAVE_ARCH_JUMP_LABEL depends on CC_HAS_ASM_GOTO + select OBJTOOL if HAVE_JUMP_LABEL_HACK help This option enables a transparent branch optimization that makes certain almost-always-true or almost-always-false branch @@ -723,10 +732,7 @@ config ARCH_SUPPORTS_CFI_CLANG config CFI_CLANG bool "Use Clang's Control Flow Integrity (CFI)" depends on LTO_CLANG && ARCH_SUPPORTS_CFI_CLANG - # Clang >= 12: - # - https://bugs.llvm.org/show_bug.cgi?id=46258 - # - https://bugs.llvm.org/show_bug.cgi?id=47479 - depends on CLANG_VERSION >= 120000 + depends on CLANG_VERSION >= 140000 select KALLSYMS help This option enables Clang’s forward-edge Control Flow Integrity @@ -854,10 +860,8 @@ config HAVE_ARCH_HUGE_VMAP # # Archs that select this would be capable of PMD-sized vmaps (i.e., -# arch_vmap_pmd_supported() returns true), and they must make no assumptions -# that vmalloc memory is mapped with PAGE_SIZE ptes. The VM_NO_HUGE_VMAP flag -# can be used to prohibit arch-specific allocations from using hugepages to -# help with this (e.g., modules may require it). +# arch_vmap_pmd_supported() returns true). The VM_ALLOW_HUGE_VMAP flag +# must be used to enable allocations to use hugepages. # config HAVE_ARCH_HUGE_VMALLOC depends on HAVE_ARCH_HUGE_VMAP @@ -1028,11 +1032,23 @@ config ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT depends on MMU select ARCH_HAS_ELF_RANDOMIZE +config HAVE_OBJTOOL + bool + +config HAVE_JUMP_LABEL_HACK + bool + +config HAVE_NOINSTR_HACK + bool + +config HAVE_NOINSTR_VALIDATION + bool + config HAVE_STACK_VALIDATION bool help - Architecture supports the 'objtool check' host tool command, which - performs compile-time stack metadata validation. + Architecture supports objtool compile-time frame pointer rule + validation. config HAVE_RELIABLE_STACKTRACE bool @@ -1302,6 +1318,7 @@ config HAVE_STATIC_CALL config HAVE_STATIC_CALL_INLINE bool depends on HAVE_STATIC_CALL + select OBJTOOL config HAVE_PREEMPT_DYNAMIC bool diff --git a/arch/alpha/include/asm/timex.h b/arch/alpha/include/asm/timex.h index b565cc6f408e..f89798da8a14 100644 --- a/arch/alpha/include/asm/timex.h +++ b/arch/alpha/include/asm/timex.h @@ -28,5 +28,6 @@ static inline cycles_t get_cycles (void) __asm__ __volatile__ ("rpcc %0" : "=r"(ret)); return ret; } +#define get_cycles get_cycles #endif diff --git a/arch/arc/boot/dts/hsdk.dts b/arch/arc/boot/dts/hsdk.dts index dcaa44e408ac..f48ba03e9b5e 100644 --- a/arch/arc/boot/dts/hsdk.dts +++ b/arch/arc/boot/dts/hsdk.dts @@ -275,7 +275,7 @@ cs-gpios = <&creg_gpio 0 GPIO_ACTIVE_LOW>, <&creg_gpio 1 GPIO_ACTIVE_LOW>; - spi-flash@0 { + flash@0 { compatible = "sst26wf016b", "jedec,spi-nor"; reg = <0>; #address-cells = <1>; diff --git a/arch/arc/include/asm/atomic-llsc.h b/arch/arc/include/asm/atomic-llsc.h index 088d348781c1..1b0ffaeee16d 100644 --- a/arch/arc/include/asm/atomic-llsc.h +++ b/arch/arc/include/asm/atomic-llsc.h @@ -5,7 +5,7 @@ #define arch_atomic_set(v, i) WRITE_ONCE(((v)->counter), (i)) -#define ATOMIC_OP(op, c_op, asm_op) \ +#define ATOMIC_OP(op, asm_op) \ static inline void arch_atomic_##op(int i, atomic_t *v) \ { \ unsigned int val; \ @@ -21,7 +21,7 @@ static inline void arch_atomic_##op(int i, atomic_t *v) \ : "cc"); \ } \ -#define ATOMIC_OP_RETURN(op, c_op, asm_op) \ +#define ATOMIC_OP_RETURN(op, asm_op) \ static inline int arch_atomic_##op##_return_relaxed(int i, atomic_t *v) \ { \ unsigned int val; \ @@ -42,7 +42,7 @@ static inline int arch_atomic_##op##_return_relaxed(int i, atomic_t *v) \ #define arch_atomic_add_return_relaxed arch_atomic_add_return_relaxed #define arch_atomic_sub_return_relaxed arch_atomic_sub_return_relaxed -#define ATOMIC_FETCH_OP(op, c_op, asm_op) \ +#define ATOMIC_FETCH_OP(op, asm_op) \ static inline int arch_atomic_fetch_##op##_relaxed(int i, atomic_t *v) \ { \ unsigned int val, orig; \ @@ -69,23 +69,23 @@ static inline int arch_atomic_fetch_##op##_relaxed(int i, atomic_t *v) \ #define arch_atomic_fetch_or_relaxed arch_atomic_fetch_or_relaxed #define arch_atomic_fetch_xor_relaxed arch_atomic_fetch_xor_relaxed -#define ATOMIC_OPS(op, c_op, asm_op) \ - ATOMIC_OP(op, c_op, asm_op) \ - ATOMIC_OP_RETURN(op, c_op, asm_op) \ - ATOMIC_FETCH_OP(op, c_op, asm_op) +#define ATOMIC_OPS(op, asm_op) \ + ATOMIC_OP(op, asm_op) \ + ATOMIC_OP_RETURN(op, asm_op) \ + ATOMIC_FETCH_OP(op, asm_op) -ATOMIC_OPS(add, +=, add) -ATOMIC_OPS(sub, -=, sub) +ATOMIC_OPS(add, add) +ATOMIC_OPS(sub, sub) #undef ATOMIC_OPS -#define ATOMIC_OPS(op, c_op, asm_op) \ - ATOMIC_OP(op, c_op, asm_op) \ - ATOMIC_FETCH_OP(op, c_op, asm_op) +#define ATOMIC_OPS(op, asm_op) \ + ATOMIC_OP(op, asm_op) \ + ATOMIC_FETCH_OP(op, asm_op) -ATOMIC_OPS(and, &=, and) -ATOMIC_OPS(andnot, &= ~, bic) -ATOMIC_OPS(or, |=, or) -ATOMIC_OPS(xor, ^=, xor) +ATOMIC_OPS(and, and) +ATOMIC_OPS(andnot, bic) +ATOMIC_OPS(or, or) +ATOMIC_OPS(xor, xor) #define arch_atomic_andnot arch_atomic_andnot diff --git a/arch/arc/include/asm/pgtable-levels.h b/arch/arc/include/asm/pgtable-levels.h index 7848348719b2..64ca25d199be 100644 --- a/arch/arc/include/asm/pgtable-levels.h +++ b/arch/arc/include/asm/pgtable-levels.h @@ -98,9 +98,6 @@ /* * 1st level paging: pgd */ -#define pgd_index(addr) ((addr) >> PGDIR_SHIFT) -#define pgd_offset(mm, addr) (((mm)->pgd) + pgd_index(addr)) -#define pgd_offset_k(addr) pgd_offset(&init_mm, addr) #define pgd_ERROR(e) \ pr_crit("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e)) diff --git a/arch/arc/kernel/disasm.c b/arch/arc/kernel/disasm.c index 03f8b1be0c3a..1e1db51b6941 100644 --- a/arch/arc/kernel/disasm.c +++ b/arch/arc/kernel/disasm.c @@ -366,7 +366,7 @@ void __kprobes disasm_instr(unsigned long addr, struct disasm_state *state, case op_SP: /* LD_S|LDB_S b,[sp,u7], ST_S|STB_S b,[sp,u7] */ /* note: we are ignoring possibility of: * ADD_S, SUB_S, PUSH_S, POP_S as these should not - * cause unaliged exception anyway */ + * cause unaligned exception anyway */ state->write = BITS(state->words[0], 6, 6); state->zz = BITS(state->words[0], 5, 5); if (state->zz) @@ -503,7 +503,6 @@ int __kprobes disasm_next_pc(unsigned long pc, struct pt_regs *regs, { struct disasm_state instr; - memset(&instr, 0, sizeof(struct disasm_state)); disasm_instr(pc, &instr, 0, regs, cregs); *next_pc = pc + instr.instr_len; diff --git a/arch/arc/kernel/entry.S b/arch/arc/kernel/entry.S index dd77a0c8f740..66ba549b520f 100644 --- a/arch/arc/kernel/entry.S +++ b/arch/arc/kernel/entry.S @@ -196,6 +196,7 @@ tracesys_exit: st r0, [sp, PT_r0] ; sys call return value in pt_regs ;POST Sys Call Ptrace Hook + mov r0, sp ; pt_regs needed bl @syscall_trace_exit b ret_from_exception ; NOT ret_from_system_call at is saves r0 which ; we'd done before calling post hook above diff --git a/arch/arc/kernel/signal.c b/arch/arc/kernel/signal.c index f748483628f2..3c1590c27fae 100644 --- a/arch/arc/kernel/signal.c +++ b/arch/arc/kernel/signal.c @@ -319,7 +319,7 @@ setup_rt_frame(struct ksignal *ksig, sigset_t *set, struct pt_regs *regs) regs->ret = (unsigned long)ksig->ka.sa.sa_handler; /* - * handler returns using sigreturn stub provided already by userpsace + * handler returns using sigreturn stub provided already by userspace * If not, nuke the process right away */ if(!(ksig->ka.sa.sa_flags & SA_RESTORER)) diff --git a/arch/arc/kernel/smp.c b/arch/arc/kernel/smp.c index 78e6d069b1c1..d947473f1e6d 100644 --- a/arch/arc/kernel/smp.c +++ b/arch/arc/kernel/smp.c @@ -35,7 +35,7 @@ EXPORT_SYMBOL_GPL(smp_atomic_ops_lock); struct plat_smp_ops __weak plat_smp_ops; -/* XXX: per cpu ? Only needed once in early seconday boot */ +/* XXX: per cpu ? Only needed once in early secondary boot */ struct task_struct *secondary_idle_tsk; /* Called from start_kernel */ @@ -274,7 +274,7 @@ static void ipi_send_msg_one(int cpu, enum ipi_msg_type msg) * and read back old value */ do { - new = old = READ_ONCE(*ipi_data_ptr); + new = old = *ipi_data_ptr; new |= 1U << msg; } while (cmpxchg(ipi_data_ptr, old, new) != old); diff --git a/arch/arc/kernel/unaligned.c b/arch/arc/kernel/unaligned.c index d63ebd81f1c6..99a9b92ed98d 100644 --- a/arch/arc/kernel/unaligned.c +++ b/arch/arc/kernel/unaligned.c @@ -237,7 +237,7 @@ int misaligned_fixup(unsigned long address, struct pt_regs *regs, if (state.fault) goto fault; - /* clear any remanants of delay slot */ + /* clear any remnants of delay slot */ if (delay_mode(regs)) { regs->ret = regs->bta & ~1U; regs->status32 &= ~STATUS_DE_MASK; diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c index 8aa1231865d1..5446967ea98d 100644 --- a/arch/arc/mm/cache.c +++ b/arch/arc/mm/cache.c @@ -401,7 +401,7 @@ static inline void __before_dc_op(const int op) { if (op == OP_FLUSH_N_INV) { /* Dcache provides 2 cmd: FLUSH or INV - * INV inturn has sub-modes: DISCARD or FLUSH-BEFORE + * INV in turn has sub-modes: DISCARD or FLUSH-BEFORE * flush-n-inv is achieved by INV cmd but with IM=1 * So toggle INV sub-mode depending on op request and default */ diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 2e8091e2d8a8..0dcf88e7f9cf 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -972,6 +972,17 @@ config ARM_ERRATA_764369 relevant cache maintenance functions and sets a specific bit in the diagnostic control register of the SCU. +config ARM_ERRATA_764319 + bool "ARM errata: Read to DBGPRSR and DBGOSLSR may generate Undefined instruction" + depends on CPU_V7 + help + This option enables the workaround for the 764319 Cortex A-9 erratum. + CP14 read accesses to the DBGPRSR and DBGOSLSR registers generate an + unexpected Undefined Instruction exception when the DBGSWENABLE + external pin is set to 0, even when the CP14 accesses are performed + from a privileged mode. This work around catches the exception in a + way the kernel does not stop execution. + config ARM_ERRATA_775420 bool "ARM errata: A data cache maintenance operation which aborts, might lead to deadlock" depends on CPU_V7 diff --git a/arch/arm/boot/dts/am33xx-l4.dtsi b/arch/arm/boot/dts/am33xx-l4.dtsi index c9629cb5ccd1..7da42a5b959c 100644 --- a/arch/arm/boot/dts/am33xx-l4.dtsi +++ b/arch/arm/boot/dts/am33xx-l4.dtsi @@ -263,6 +263,8 @@ compatible = "ti,am3359-tscadc"; reg = <0x0 0x1000>; interrupts = <16>; + clocks = <&adc_tsc_fck>; + clock-names = "fck"; status = "disabled"; dmas = <&edma 53 0>, <&edma 57 0>; dma-names = "fifo0", "fifo1"; diff --git a/arch/arm/boot/dts/am3517-evm.dts b/arch/arm/boot/dts/am3517-evm.dts index 0d2fac98ce7d..c8b80f156ec9 100644 --- a/arch/arm/boot/dts/am3517-evm.dts +++ b/arch/arm/boot/dts/am3517-evm.dts @@ -161,6 +161,8 @@ /* HS USB Host PHY on PORT 1 */ hsusb1_phy: hsusb1_phy { + pinctrl-names = "default"; + pinctrl-0 = <&hsusb1_rst_pins>; compatible = "usb-nop-xceiv"; reset-gpios = <&gpio2 25 GPIO_ACTIVE_LOW>; /* gpio_57 */ #phy-cells = <0>; @@ -168,7 +170,9 @@ }; &davinci_emac { - status = "okay"; + pinctrl-names = "default"; + pinctrl-0 = <ðernet_pins>; + status = "okay"; }; &davinci_mdio { @@ -193,6 +197,8 @@ }; &i2c2 { + pinctrl-names = "default"; + pinctrl-0 = <&i2c2_pins>; clock-frequency = <400000>; /* User DIP swithes [1:8] / User LEDS [1:2] */ tca6416: gpio@21 { @@ -205,6 +211,8 @@ }; &i2c3 { + pinctrl-names = "default"; + pinctrl-0 = <&i2c3_pins>; clock-frequency = <400000>; }; @@ -223,6 +231,8 @@ }; &usbhshost { + pinctrl-names = "default"; + pinctrl-0 = <&hsusb1_pins>; port1-mode = "ehci-phy"; }; @@ -231,8 +241,35 @@ }; &omap3_pmx_core { - pinctrl-names = "default"; - pinctrl-0 = <&hsusb1_rst_pins>; + + ethernet_pins: pinmux_ethernet_pins { + pinctrl-single,pins = < + OMAP3_CORE1_IOPAD(0x21fe, PIN_INPUT | MUX_MODE0) /* rmii_mdio_data */ + OMAP3_CORE1_IOPAD(0x2200, MUX_MODE0) /* rmii_mdio_clk */ + OMAP3_CORE1_IOPAD(0x2202, PIN_INPUT_PULLDOWN | MUX_MODE0) /* rmii_rxd0 */ + OMAP3_CORE1_IOPAD(0x2204, PIN_INPUT_PULLDOWN | MUX_MODE0) /* rmii_rxd1 */ + OMAP3_CORE1_IOPAD(0x2206, PIN_INPUT_PULLDOWN | MUX_MODE0) /* rmii_crs_dv */ + OMAP3_CORE1_IOPAD(0x2208, PIN_OUTPUT_PULLDOWN | MUX_MODE0) /* rmii_rxer */ + OMAP3_CORE1_IOPAD(0x220a, PIN_OUTPUT_PULLDOWN | MUX_MODE0) /* rmii_txd0 */ + OMAP3_CORE1_IOPAD(0x220c, PIN_OUTPUT_PULLDOWN | MUX_MODE0) /* rmii_txd1 */ + OMAP3_CORE1_IOPAD(0x220e, PIN_OUTPUT_PULLDOWN |MUX_MODE0) /* rmii_txen */ + OMAP3_CORE1_IOPAD(0x2210, PIN_INPUT_PULLDOWN | MUX_MODE0) /* rmii_50mhz_clk */ + >; + }; + + i2c2_pins: pinmux_i2c2_pins { + pinctrl-single,pins = < + OMAP3_CORE1_IOPAD(0x21be, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c2_scl */ + OMAP3_CORE1_IOPAD(0x21c0, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c2_sda */ + >; + }; + + i2c3_pins: pinmux_i2c3_pins { + pinctrl-single,pins = < + OMAP3_CORE1_IOPAD(0x21c2, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c3_scl */ + OMAP3_CORE1_IOPAD(0x21c4, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c3_sda */ + >; + }; leds_pins: pinmux_leds_pins { pinctrl-single,pins = < @@ -300,8 +337,6 @@ }; &omap3_pmx_core2 { - pinctrl-names = "default"; - pinctrl-0 = <&hsusb1_pins>; hsusb1_pins: pinmux_hsusb1_pins { pinctrl-single,pins = < diff --git a/arch/arm/boot/dts/am3517-som.dtsi b/arch/arm/boot/dts/am3517-som.dtsi index 8b669e2eafec..f7b680f6c48a 100644 --- a/arch/arm/boot/dts/am3517-som.dtsi +++ b/arch/arm/boot/dts/am3517-som.dtsi @@ -69,6 +69,8 @@ }; &i2c1 { + pinctrl-names = "default"; + pinctrl-0 = <&i2c1_pins>; clock-frequency = <400000>; s35390a: s35390a@30 { @@ -179,6 +181,13 @@ &omap3_pmx_core { + i2c1_pins: pinmux_i2c1_pins { + pinctrl-single,pins = < + OMAP3_CORE1_IOPAD(0x21ba, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c1_scl */ + OMAP3_CORE1_IOPAD(0x21bc, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c1_sda */ + >; + }; + wl12xx_buffer_pins: pinmux_wl12xx_buffer_pins { pinctrl-single,pins = < OMAP3_CORE1_IOPAD(0x2156, PIN_OUTPUT | MUX_MODE4) /* mmc1_dat7.gpio_129 */ diff --git a/arch/arm/boot/dts/aspeed-bmc-asrock-romed8hm3.dts b/arch/arm/boot/dts/aspeed-bmc-asrock-romed8hm3.dts index e71ccfd1df63..ff4c07c69af1 100644 --- a/arch/arm/boot/dts/aspeed-bmc-asrock-romed8hm3.dts +++ b/arch/arm/boot/dts/aspeed-bmc-asrock-romed8hm3.dts @@ -100,12 +100,14 @@ lm25066@40 { compatible = "lm25066"; reg = <0x40>; + shunt-resistor-micro-ohms = <1000>; }; /* 12VSB PMIC */ lm25066@41 { compatible = "lm25066"; reg = <0x41>; + shunt-resistor-micro-ohms = <10000>; }; }; @@ -196,7 +198,7 @@ gpio-line-names = /* A */ "LOCATORLED_STATUS_N", "BMC_MAC2_INTB", "NMI_BTN_N", "BMC_NMI", "", "", "", "", - /* B */ "DDR_MEM_TEMP", "", "", "", "", "", "", "", + /* B */ "POST_COMPLETE_N", "", "", "", "", "", "", "", /* C */ "", "", "", "", "PCIE_HP_SEL_N", "PCIE_SATA_SEL_N", "LOCATORBTN", "", /* D */ "BMC_PSIN", "BMC_PSOUT", "BMC_RESETCON", "RESETCON", "", "", "", "PSU_FAN_FAIL_N", diff --git a/arch/arm/boot/dts/aspeed-g6-pinctrl.dtsi b/arch/arm/boot/dts/aspeed-g6-pinctrl.dtsi index e4775bbceecc..7cd4f075e325 100644 --- a/arch/arm/boot/dts/aspeed-g6-pinctrl.dtsi +++ b/arch/arm/boot/dts/aspeed-g6-pinctrl.dtsi @@ -117,9 +117,9 @@ groups = "FWSPID"; }; - pinctrl_fwqspid_default: fwqspid_default { - function = "FWSPID"; - groups = "FWQSPID"; + pinctrl_fwqspi_default: fwqspi_default { + function = "FWQSPI"; + groups = "FWQSPI"; }; pinctrl_fwspiwp_default: fwspiwp_default { @@ -653,12 +653,12 @@ }; pinctrl_qspi1_default: qspi1_default { - function = "QSPI1"; + function = "SPI1"; groups = "QSPI1"; }; pinctrl_qspi2_default: qspi2_default { - function = "QSPI2"; + function = "SPI2"; groups = "QSPI2"; }; diff --git a/arch/arm/boot/dts/aspeed-g6.dtsi b/arch/arm/boot/dts/aspeed-g6.dtsi index 3d5ce9da42c3..9d2a0ce4ca06 100644 --- a/arch/arm/boot/dts/aspeed-g6.dtsi +++ b/arch/arm/boot/dts/aspeed-g6.dtsi @@ -389,6 +389,16 @@ reg = <0x1e6f2000 0x1000>; }; + video: video@1e700000 { + compatible = "aspeed,ast2600-video-engine"; + reg = <0x1e700000 0x1000>; + clocks = <&syscon ASPEED_CLK_GATE_VCLK>, + <&syscon ASPEED_CLK_GATE_ECLK>; + clock-names = "vclk", "eclk"; + interrupts = <GIC_SPI 7 IRQ_TYPE_LEVEL_HIGH>; + status = "disabled"; + }; + gpio0: gpio@1e780000 { #gpio-cells = <2>; gpio-controller; diff --git a/arch/arm/boot/dts/at91-dvk_su60_somc.dtsi b/arch/arm/boot/dts/at91-dvk_su60_somc.dtsi index c1c8650dafce..3542ad8a243e 100644 --- a/arch/arm/boot/dts/at91-dvk_su60_somc.dtsi +++ b/arch/arm/boot/dts/at91-dvk_su60_somc.dtsi @@ -44,7 +44,7 @@ status = "okay"; /* spi0.0: 4M Flash Macronix MX25R4035FM1IL0 */ - spi-flash@0 { + flash@0 { compatible = "mxicy,mx25u4035", "jedec,spi-nor"; spi-max-frequency = <33000000>; reg = <0>; diff --git a/arch/arm/boot/dts/at91-q5xr5.dts b/arch/arm/boot/dts/at91-q5xr5.dts index 47a00062f01f..9cf60b6f695c 100644 --- a/arch/arm/boot/dts/at91-q5xr5.dts +++ b/arch/arm/boot/dts/at91-q5xr5.dts @@ -125,7 +125,7 @@ cs-gpios = <&pioA 3 GPIO_ACTIVE_HIGH>, <&pioC 11 GPIO_ACTIVE_LOW>, <0>, <0>; status = "okay"; - m25p80@0 { + flash@0 { compatible = "jedec,spi-nor"; spi-max-frequency = <20000000>; reg = <0>; diff --git a/arch/arm/boot/dts/at91-sam9_l9260.dts b/arch/arm/boot/dts/at91-sam9_l9260.dts index 1e2a28c2f365..2fb51b9aca2a 100644 --- a/arch/arm/boot/dts/at91-sam9_l9260.dts +++ b/arch/arm/boot/dts/at91-sam9_l9260.dts @@ -101,7 +101,7 @@ nand0: nand@40000000 { nand-bus-width = <8>; nand-ecc-mode = "soft"; - nand-on-flash-bbt = <1>; + nand-on-flash-bbt; status = "okay"; }; diff --git a/arch/arm/boot/dts/at91-sama5d27_wlsom1.dtsi b/arch/arm/boot/dts/at91-sama5d27_wlsom1.dtsi index 21c86171e462..ba621783acdb 100644 --- a/arch/arm/boot/dts/at91-sama5d27_wlsom1.dtsi +++ b/arch/arm/boot/dts/at91-sama5d27_wlsom1.dtsi @@ -214,7 +214,7 @@ pinctrl-0 = <&pinctrl_qspi1_default>; status = "disabled"; - qspi1_flash: spi_flash@0 { + qspi1_flash: flash@0 { #address-cells = <1>; #size-cells = <1>; compatible = "jedec,spi-nor"; diff --git a/arch/arm/boot/dts/at91-sama5d27_wlsom1_ek.dts b/arch/arm/boot/dts/at91-sama5d27_wlsom1_ek.dts index c145c4e5ef58..5e8755f22784 100644 --- a/arch/arm/boot/dts/at91-sama5d27_wlsom1_ek.dts +++ b/arch/arm/boot/dts/at91-sama5d27_wlsom1_ek.dts @@ -191,7 +191,7 @@ &qspi1 { status = "okay"; - qspi1_flash: spi_flash@0 { + qspi1_flash: flash@0 { status = "okay"; }; }; diff --git a/arch/arm/boot/dts/at91-sama5d2_xplained.dts b/arch/arm/boot/dts/at91-sama5d2_xplained.dts index 9bf2ec0ba3e2..cdfe891f9a9e 100644 --- a/arch/arm/boot/dts/at91-sama5d2_xplained.dts +++ b/arch/arm/boot/dts/at91-sama5d2_xplained.dts @@ -137,7 +137,7 @@ pinctrl-0 = <&pinctrl_spi0_default>; status = "okay"; - m25p80@0 { + flash@0 { compatible = "atmel,at25df321a"; reg = <0>; spi-max-frequency = <50000000>; diff --git a/arch/arm/boot/dts/at91-sama5d3_xplained.dts b/arch/arm/boot/dts/at91-sama5d3_xplained.dts index d72c042f2850..a49c2966b41e 100644 --- a/arch/arm/boot/dts/at91-sama5d3_xplained.dts +++ b/arch/arm/boot/dts/at91-sama5d3_xplained.dts @@ -57,8 +57,8 @@ }; spi0: spi@f0004000 { - pinctrl-names = "default"; - pinctrl-0 = <&pinctrl_spi0_cs>; + pinctrl-names = "default", "cs"; + pinctrl-1 = <&pinctrl_spi0_cs>; cs-gpios = <&pioD 13 0>, <0>, <0>, <&pioD 16 0>; status = "okay"; }; @@ -171,8 +171,8 @@ }; spi1: spi@f8008000 { - pinctrl-names = "default"; - pinctrl-0 = <&pinctrl_spi1_cs>; + pinctrl-names = "default", "cs"; + pinctrl-1 = <&pinctrl_spi1_cs>; cs-gpios = <&pioC 25 0>; status = "okay"; }; diff --git a/arch/arm/boot/dts/at91-sama5d4_ma5d4.dtsi b/arch/arm/boot/dts/at91-sama5d4_ma5d4.dtsi index 710cb72bda5a..fd1086f52b40 100644 --- a/arch/arm/boot/dts/at91-sama5d4_ma5d4.dtsi +++ b/arch/arm/boot/dts/at91-sama5d4_ma5d4.dtsi @@ -49,7 +49,7 @@ cs-gpios = <&pioC 3 0>, <0>, <0>, <0>; status = "okay"; - m25p80@0 { + flash@0 { compatible = "atmel,at25df321a"; spi-max-frequency = <50000000>; reg = <0>; diff --git a/arch/arm/boot/dts/at91-sama5d4_xplained.dts b/arch/arm/boot/dts/at91-sama5d4_xplained.dts index d241c24f0d83..e519d2747936 100644 --- a/arch/arm/boot/dts/at91-sama5d4_xplained.dts +++ b/arch/arm/boot/dts/at91-sama5d4_xplained.dts @@ -81,8 +81,8 @@ }; spi1: spi@fc018000 { - pinctrl-names = "default"; - pinctrl-0 = <&pinctrl_spi0_cs>; + pinctrl-names = "default", "cs"; + pinctrl-1 = <&pinctrl_spi1_cs>; cs-gpios = <&pioB 21 0>; status = "okay"; }; @@ -140,7 +140,7 @@ atmel,pins = <AT91_PIOE 1 AT91_PERIPH_GPIO AT91_PINCTRL_PULL_UP_DEGLITCH>; }; - pinctrl_spi0_cs: spi0_cs_default { + pinctrl_spi1_cs: spi1_cs_default { atmel,pins = <AT91_PIOB 21 AT91_PERIPH_GPIO AT91_PINCTRL_NONE>; }; diff --git a/arch/arm/boot/dts/at91-sama5d4ek.dts b/arch/arm/boot/dts/at91-sama5d4ek.dts index fe432b6b7e95..7017f626f362 100644 --- a/arch/arm/boot/dts/at91-sama5d4ek.dts +++ b/arch/arm/boot/dts/at91-sama5d4ek.dts @@ -65,7 +65,7 @@ spi0: spi@f8010000 { cs-gpios = <&pioC 3 0>, <0>, <0>, <0>; status = "okay"; - m25p80@0 { + flash@0 { compatible = "atmel,at25df321a"; spi-max-frequency = <50000000>; reg = <0>; diff --git a/arch/arm/boot/dts/at91-sama7g5ek.dts b/arch/arm/boot/dts/at91-sama7g5ek.dts index 08685a10eda1..d83f76a6cd6a 100644 --- a/arch/arm/boot/dts/at91-sama7g5ek.dts +++ b/arch/arm/boot/dts/at91-sama7g5ek.dts @@ -495,7 +495,7 @@ pinctrl_flx3_default: flx3_default { pinmux = <PIN_PD16__FLEXCOM3_IO0>, <PIN_PD17__FLEXCOM3_IO1>; - bias-disable; + bias-pull-up; }; pinctrl_flx4_default: flx4_default { @@ -655,7 +655,7 @@ <PIN_PB21__QSPI0_INT>; bias-disable; slew-rate = <0>; - atmel,drive-strength = <ATMEL_PIO_DRVSTR_HI>; + atmel,drive-strength = <ATMEL_PIO_DRVSTR_ME>; }; pinctrl_sdmmc0_default: sdmmc0_default { diff --git a/arch/arm/boot/dts/at91-vinco.dts b/arch/arm/boot/dts/at91-vinco.dts index a51a3372afa1..ebeaa6ab500e 100644 --- a/arch/arm/boot/dts/at91-vinco.dts +++ b/arch/arm/boot/dts/at91-vinco.dts @@ -59,7 +59,7 @@ spi0: spi@f8010000 { cs-gpios = <&pioC 3 0>, <0>, <0>, <0>; status = "okay"; - m25p80@0 { + flash@0 { compatible = "n25q32b", "jedec,spi-nor"; spi-max-frequency = <50000000>; reg = <0>; diff --git a/arch/arm/boot/dts/at91rm9200ek.dts b/arch/arm/boot/dts/at91rm9200ek.dts index e1ef4e44e663..4624a6f076f8 100644 --- a/arch/arm/boot/dts/at91rm9200ek.dts +++ b/arch/arm/boot/dts/at91rm9200ek.dts @@ -73,7 +73,7 @@ spi0: spi@fffe0000 { status = "okay"; cs-gpios = <&pioA 3 0>, <0>, <0>, <0>; - mtd_dataflash@0 { + flash@0 { compatible = "atmel,at45", "atmel,dataflash"; spi-max-frequency = <15000000>; reg = <0>; @@ -94,7 +94,7 @@ status = "okay"; }; - nor_flash@10000000 { + flash@10000000 { compatible = "cfi-flash"; reg = <0x10000000 0x800000>; linux,mtd-name = "physmap-flash.0"; diff --git a/arch/arm/boot/dts/at91sam9260ek.dts b/arch/arm/boot/dts/at91sam9260ek.dts index ce96345d28a3..6381088ba24f 100644 --- a/arch/arm/boot/dts/at91sam9260ek.dts +++ b/arch/arm/boot/dts/at91sam9260ek.dts @@ -92,7 +92,7 @@ spi0: spi@fffc8000 { cs-gpios = <0>, <&pioC 11 0>, <0>, <0>; - mtd_dataflash@1 { + flash@1 { compatible = "atmel,at45", "atmel,dataflash"; spi-max-frequency = <50000000>; reg = <1>; diff --git a/arch/arm/boot/dts/at91sam9261ek.dts b/arch/arm/boot/dts/at91sam9261ek.dts index beed819609e8..8f11c0b7d76d 100644 --- a/arch/arm/boot/dts/at91sam9261ek.dts +++ b/arch/arm/boot/dts/at91sam9261ek.dts @@ -145,7 +145,7 @@ cs-gpios = <&pioA 3 0>, <0>, <&pioA 28 0>, <0>; status = "okay"; - mtd_dataflash@0 { + flash@0 { compatible = "atmel,at45", "atmel,dataflash"; reg = <0>; spi-max-frequency = <15000000>; diff --git a/arch/arm/boot/dts/at91sam9263ek.dts b/arch/arm/boot/dts/at91sam9263ek.dts index 71f60576761a..42e734020235 100644 --- a/arch/arm/boot/dts/at91sam9263ek.dts +++ b/arch/arm/boot/dts/at91sam9263ek.dts @@ -95,7 +95,7 @@ spi0: spi@fffa4000 { status = "okay"; cs-gpios = <&pioA 5 0>, <0>, <0>, <0>; - mtd_dataflash@0 { + flash@0 { compatible = "atmel,at45", "atmel,dataflash"; spi-max-frequency = <50000000>; reg = <0>; diff --git a/arch/arm/boot/dts/at91sam9g20ek_common.dtsi b/arch/arm/boot/dts/at91sam9g20ek_common.dtsi index 87bb39060e8b..85c17dd1c8d5 100644 --- a/arch/arm/boot/dts/at91sam9g20ek_common.dtsi +++ b/arch/arm/boot/dts/at91sam9g20ek_common.dtsi @@ -110,7 +110,7 @@ spi0: spi@fffc8000 { cs-gpios = <0>, <&pioC 11 0>, <0>, <0>; - mtd_dataflash@1 { + flash@1 { compatible = "atmel,at45", "atmel,dataflash"; spi-max-frequency = <50000000>; reg = <1>; @@ -214,11 +214,23 @@ 24c512@50 { compatible = "atmel,24c512"; reg = <0x50>; + vcc-supply = <®_3v3>; }; wm8731: wm8731@1b { compatible = "wm8731"; reg = <0x1b>; + + /* PCK0 at 12MHz */ + clocks = <&pmc PMC_TYPE_SYSTEM 8>; + clock-names = "mclk"; + assigned-clocks = <&pmc PMC_TYPE_SYSTEM 8>; + assigned-clock-rates = <12000000>; + + HPVDD-supply = <&vcc_dac>; + AVDD-supply = <&vcc_dac>; + DCVDD-supply = <®_3v3>; + DBVDD-supply = <®_3v3>; }; }; @@ -254,4 +266,35 @@ atmel,ssc-controller = <&ssc0>; atmel,audio-codec = <&wm8731>; }; + + reg_5v: fixedregulator0 { + compatible = "regulator-fixed"; + regulator-name = "5V"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + }; + + reg_3v3: fixedregulator1 { + compatible = "regulator-fixed"; + regulator-name = "3V3"; + vin-supply = <®_5v>; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + }; + + reg_1v: fixedregulator2 { + compatible = "regulator-fixed"; + regulator-name = "1V"; + vin-supply = <®_5v>; + regulator-min-microvolt = <1000000>; + regulator-max-microvolt = <1000000>; + }; + + vcc_dac: fixedregulator3 { + compatible = "regulator-fixed"; + regulator-name = "VCC_DAC"; + vin-supply = <®_3v3>; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + }; }; diff --git a/arch/arm/boot/dts/at91sam9m10g45ek.dts b/arch/arm/boot/dts/at91sam9m10g45ek.dts index b6256a20fbc7..e5db198a87a8 100644 --- a/arch/arm/boot/dts/at91sam9m10g45ek.dts +++ b/arch/arm/boot/dts/at91sam9m10g45ek.dts @@ -167,7 +167,7 @@ spi0: spi@fffa4000{ status = "okay"; cs-gpios = <&pioB 3 0>, <0>, <0>, <0>; - mtd_dataflash@0 { + flash@0 { compatible = "atmel,at45", "atmel,dataflash"; spi-max-frequency = <13000000>; reg = <0>; diff --git a/arch/arm/boot/dts/at91sam9n12ek.dts b/arch/arm/boot/dts/at91sam9n12ek.dts index 2bc4e6e0a923..c905d7bfc771 100644 --- a/arch/arm/boot/dts/at91sam9n12ek.dts +++ b/arch/arm/boot/dts/at91sam9n12ek.dts @@ -119,7 +119,7 @@ spi0: spi@f0000000 { status = "okay"; cs-gpios = <&pioA 14 0>, <0>, <0>, <0>; - m25p80@0 { + flash@0 { compatible = "atmel,at25df321a"; spi-max-frequency = <50000000>; reg = <0>; diff --git a/arch/arm/boot/dts/at91sam9rlek.dts b/arch/arm/boot/dts/at91sam9rlek.dts index 62981b39c815..d74b8d9d84aa 100644 --- a/arch/arm/boot/dts/at91sam9rlek.dts +++ b/arch/arm/boot/dts/at91sam9rlek.dts @@ -180,7 +180,7 @@ spi0: spi@fffcc000 { status = "okay"; cs-gpios = <&pioA 28 0>, <0>, <0>, <0>; - mtd_dataflash@0 { + flash@0 { compatible = "atmel,at45", "atmel,dataflash"; spi-max-frequency = <15000000>; reg = <0>; diff --git a/arch/arm/boot/dts/at91sam9x5ek.dtsi b/arch/arm/boot/dts/at91sam9x5ek.dtsi index 6d1264de6060..5f4eaa618ab4 100644 --- a/arch/arm/boot/dts/at91sam9x5ek.dtsi +++ b/arch/arm/boot/dts/at91sam9x5ek.dtsi @@ -125,7 +125,7 @@ cs-gpios = <&pioA 14 0>, <0>, <0>, <0>; status = "disabled"; /* conflicts with mmc1 */ - m25p80@0 { + flash@0 { compatible = "atmel,at25df321a"; spi-max-frequency = <50000000>; reg = <0>; diff --git a/arch/arm/boot/dts/da850-evm.dts b/arch/arm/boot/dts/da850-evm.dts index 87c517d65f62..e9aecac4f5b5 100644 --- a/arch/arm/boot/dts/da850-evm.dts +++ b/arch/arm/boot/dts/da850-evm.dts @@ -278,7 +278,7 @@ status = "okay"; pinctrl-names = "default"; pinctrl-0 = <&spi1_pins &spi1_cs0_pin>; - flash: m25p80@0 { + flash: flash@0 { #address-cells = <1>; #size-cells = <1>; compatible = "jedec,spi-nor"; diff --git a/arch/arm/boot/dts/dm8168-evm.dts b/arch/arm/boot/dts/dm8168-evm.dts index 5126e2d72ed7..778796c10af8 100644 --- a/arch/arm/boot/dts/dm8168-evm.dts +++ b/arch/arm/boot/dts/dm8168-evm.dts @@ -177,7 +177,7 @@ pinctrl-names = "default"; pinctrl-0 = <&mcspi1_pins>; - m25p80@0 { + flash@0 { compatible = "w25x32"; spi-max-frequency = <48000000>; reg = <0>; diff --git a/arch/arm/boot/dts/dra7-l4.dtsi b/arch/arm/boot/dts/dra7-l4.dtsi index 0a11bacffc1f..5733e3a4ea8e 100644 --- a/arch/arm/boot/dts/dra7-l4.dtsi +++ b/arch/arm/boot/dts/dra7-l4.dtsi @@ -4188,11 +4188,11 @@ reg = <0x1d0010 0x4>; reg-names = "sysc"; ti,sysc-midle = <SYSC_IDLE_FORCE>, - <SYSC_IDLE_NO>, - <SYSC_IDLE_SMART>; + <SYSC_IDLE_NO>; ti,sysc-sidle = <SYSC_IDLE_FORCE>, <SYSC_IDLE_NO>, <SYSC_IDLE_SMART>; + power-domains = <&prm_vpe>; clocks = <&vpe_clkctrl DRA7_VPE_VPE_CLKCTRL 0>; clock-names = "fck"; #address-cells = <1>; diff --git a/arch/arm/boot/dts/imx28-ts4600.dts b/arch/arm/boot/dts/imx28-ts4600.dts index 097ec35c62d8..0d58da1c0cc5 100644 --- a/arch/arm/boot/dts/imx28-ts4600.dts +++ b/arch/arm/boot/dts/imx28-ts4600.dts @@ -26,7 +26,7 @@ pinctrl-0 = <&mmc0_4bit_pins_a &mmc0_sck_cfg &en_sd_pwr>; - broken-cd = <1>; + broken-cd; bus-width = <4>; vmmc-supply = <®_vddio_sd0>; status = "okay"; diff --git a/arch/arm/boot/dts/imx6qdl-apalis.dtsi b/arch/arm/boot/dts/imx6qdl-apalis.dtsi index ed2739e39085..bd763bae596b 100644 --- a/arch/arm/boot/dts/imx6qdl-apalis.dtsi +++ b/arch/arm/boot/dts/imx6qdl-apalis.dtsi @@ -286,6 +286,8 @@ codec: sgtl5000@a { compatible = "fsl,sgtl5000"; reg = <0x0a>; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_sgtl5000>; clocks = <&clks IMX6QDL_CLK_CKO>; VDDA-supply = <®_module_3v3_audio>; VDDIO-supply = <®_module_3v3>; @@ -517,8 +519,6 @@ MX6QDL_PAD_DISP0_DAT21__AUD4_TXD 0x130b0 MX6QDL_PAD_DISP0_DAT22__AUD4_TXFS 0x130b0 MX6QDL_PAD_DISP0_DAT23__AUD4_RXD 0x130b0 - /* SGTL5000 sys_mclk */ - MX6QDL_PAD_GPIO_5__CCM_CLKO1 0x130b0 >; }; @@ -811,6 +811,12 @@ >; }; + pinctrl_sgtl5000: sgtl5000grp { + fsl,pins = < + MX6QDL_PAD_GPIO_5__CCM_CLKO1 0x130b0 + >; + }; + pinctrl_spdif: spdifgrp { fsl,pins = < MX6QDL_PAD_GPIO_16__SPDIF_IN 0x1b0b0 diff --git a/arch/arm/boot/dts/imx6qdl-aristainetos2.dtsi b/arch/arm/boot/dts/imx6qdl-aristainetos2.dtsi index 563bf9d44fe0..0b90c3f59f89 100644 --- a/arch/arm/boot/dts/imx6qdl-aristainetos2.dtsi +++ b/arch/arm/boot/dts/imx6qdl-aristainetos2.dtsi @@ -154,112 +154,112 @@ regulators { bcore1 { regulator-name = "bcore1"; - regulator-always-on = <1>; + regulator-always-on; regulator-min-microvolt = <300000>; regulator-max-microvolt = <3300000>; }; bcore2 { regulator-name = "bcore2"; - regulator-always-on = <1>; + regulator-always-on; regulator-min-microvolt = <300000>; regulator-max-microvolt = <3300000>; }; bpro { regulator-name = "bpro"; - regulator-always-on = <1>; + regulator-always-on; regulator-min-microvolt = <300000>; regulator-max-microvolt = <3300000>; }; bperi { regulator-name = "bperi"; - regulator-always-on = <1>; + regulator-always-on; regulator-min-microvolt = <300000>; regulator-max-microvolt = <3300000>; }; bmem { regulator-name = "bmem"; - regulator-always-on = <1>; + regulator-always-on; regulator-min-microvolt = <300000>; regulator-max-microvolt = <3300000>; }; ldo2 { regulator-name = "ldo2"; - regulator-always-on = <1>; + regulator-always-on; regulator-min-microvolt = <300000>; regulator-max-microvolt = <1800000>; }; ldo3 { regulator-name = "ldo3"; - regulator-always-on = <1>; + regulator-always-on; regulator-min-microvolt = <300000>; regulator-max-microvolt = <3300000>; }; ldo4 { regulator-name = "ldo4"; - regulator-always-on = <1>; + regulator-always-on; regulator-min-microvolt = <300000>; regulator-max-microvolt = <3300000>; }; ldo5 { regulator-name = "ldo5"; - regulator-always-on = <1>; + regulator-always-on; regulator-min-microvolt = <300000>; regulator-max-microvolt = <3300000>; }; ldo6 { regulator-name = "ldo6"; - regulator-always-on = <1>; + regulator-always-on; regulator-min-microvolt = <300000>; regulator-max-microvolt = <3300000>; }; ldo7 { regulator-name = "ldo7"; - regulator-always-on = <1>; + regulator-always-on; regulator-min-microvolt = <300000>; regulator-max-microvolt = <3300000>; }; ldo8 { regulator-name = "ldo8"; - regulator-always-on = <1>; + regulator-always-on; regulator-min-microvolt = <300000>; regulator-max-microvolt = <3300000>; }; ldo9 { regulator-name = "ldo9"; - regulator-always-on = <1>; + regulator-always-on; regulator-min-microvolt = <300000>; regulator-max-microvolt = <3300000>; }; ldo10 { regulator-name = "ldo10"; - regulator-always-on = <1>; + regulator-always-on; regulator-min-microvolt = <300000>; regulator-max-microvolt = <3300000>; }; ldo11 { regulator-name = "ldo11"; - regulator-always-on = <1>; + regulator-always-on; regulator-min-microvolt = <300000>; regulator-max-microvolt = <3300000>; }; bio { regulator-name = "bio"; - regulator-always-on = <1>; + regulator-always-on; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; }; diff --git a/arch/arm/boot/dts/imx6ul-phytec-segin-peb-av-02.dtsi b/arch/arm/boot/dts/imx6ul-phytec-segin-peb-av-02.dtsi index 7cda6944501d..205e4d462702 100644 --- a/arch/arm/boot/dts/imx6ul-phytec-segin-peb-av-02.dtsi +++ b/arch/arm/boot/dts/imx6ul-phytec-segin-peb-av-02.dtsi @@ -72,8 +72,8 @@ st,settling = <2>; st,fraction-z = <7>; st,i-drive = <1>; - touchscreen-inverted-x = <1>; - touchscreen-inverted-y = <1>; + touchscreen-inverted-x; + touchscreen-inverted-y; }; }; }; diff --git a/arch/arm/boot/dts/imx6ull-colibri.dtsi b/arch/arm/boot/dts/imx6ull-colibri.dtsi index 7f35a06dff95..951a2a6c5a65 100644 --- a/arch/arm/boot/dts/imx6ull-colibri.dtsi +++ b/arch/arm/boot/dts/imx6ull-colibri.dtsi @@ -37,7 +37,7 @@ reg_sd1_vmmc: regulator-sd1-vmmc { compatible = "regulator-gpio"; - gpio = <&gpio5 9 GPIO_ACTIVE_HIGH>; + gpios = <&gpio5 9 GPIO_ACTIVE_HIGH>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_snvs_reg_sd>; regulator-always-on; diff --git a/arch/arm/boot/dts/logicpd-som-lv-35xx-devkit.dts b/arch/arm/boot/dts/logicpd-som-lv-35xx-devkit.dts index 2a0a98fe67f0..3240c67e0c39 100644 --- a/arch/arm/boot/dts/logicpd-som-lv-35xx-devkit.dts +++ b/arch/arm/boot/dts/logicpd-som-lv-35xx-devkit.dts @@ -11,3 +11,18 @@ model = "LogicPD Zoom OMAP35xx SOM-LV Development Kit"; compatible = "logicpd,dm3730-som-lv-devkit", "ti,omap3430", "ti,omap3"; }; + +&omap3_pmx_core2 { + pinctrl-names = "default"; + pinctrl-0 = <&hsusb2_2_pins>; + hsusb2_2_pins: pinmux_hsusb2_2_pins { + pinctrl-single,pins = < + OMAP3430_CORE2_IOPAD(0x25f0, PIN_OUTPUT | MUX_MODE3) /* etk_d10.hsusb2_clk */ + OMAP3430_CORE2_IOPAD(0x25f2, PIN_OUTPUT | MUX_MODE3) /* etk_d11.hsusb2_stp */ + OMAP3430_CORE2_IOPAD(0x25f4, PIN_INPUT_PULLDOWN | MUX_MODE3) /* etk_d12.hsusb2_dir */ + OMAP3430_CORE2_IOPAD(0x25f6, PIN_INPUT_PULLDOWN | MUX_MODE3) /* etk_d13.hsusb2_nxt */ + OMAP3430_CORE2_IOPAD(0x25f8, PIN_INPUT_PULLDOWN | MUX_MODE3) /* etk_d14.hsusb2_data0 */ + OMAP3430_CORE2_IOPAD(0x25fa, PIN_INPUT_PULLDOWN | MUX_MODE3) /* etk_d15.hsusb2_data1 */ + >; + }; +}; diff --git a/arch/arm/boot/dts/logicpd-som-lv-37xx-devkit.dts b/arch/arm/boot/dts/logicpd-som-lv-37xx-devkit.dts index a604d92221a4..c757f0d7781c 100644 --- a/arch/arm/boot/dts/logicpd-som-lv-37xx-devkit.dts +++ b/arch/arm/boot/dts/logicpd-som-lv-37xx-devkit.dts @@ -11,3 +11,18 @@ model = "LogicPD Zoom DM3730 SOM-LV Development Kit"; compatible = "logicpd,dm3730-som-lv-devkit", "ti,omap3630", "ti,omap3"; }; + +&omap3_pmx_core2 { + pinctrl-names = "default"; + pinctrl-0 = <&hsusb2_2_pins>; + hsusb2_2_pins: pinmux_hsusb2_2_pins { + pinctrl-single,pins = < + OMAP3630_CORE2_IOPAD(0x25f0, PIN_OUTPUT | MUX_MODE3) /* etk_d10.hsusb2_clk */ + OMAP3630_CORE2_IOPAD(0x25f2, PIN_OUTPUT | MUX_MODE3) /* etk_d11.hsusb2_stp */ + OMAP3630_CORE2_IOPAD(0x25f4, PIN_INPUT_PULLDOWN | MUX_MODE3) /* etk_d12.hsusb2_dir */ + OMAP3630_CORE2_IOPAD(0x25f6, PIN_INPUT_PULLDOWN | MUX_MODE3) /* etk_d13.hsusb2_nxt */ + OMAP3630_CORE2_IOPAD(0x25f8, PIN_INPUT_PULLDOWN | MUX_MODE3) /* etk_d14.hsusb2_data0 */ + OMAP3630_CORE2_IOPAD(0x25fa, PIN_INPUT_PULLDOWN | MUX_MODE3) /* etk_d15.hsusb2_data1 */ + >; + }; +}; diff --git a/arch/arm/boot/dts/logicpd-som-lv.dtsi b/arch/arm/boot/dts/logicpd-som-lv.dtsi index b56524cc7fe2..55b619c99e24 100644 --- a/arch/arm/boot/dts/logicpd-som-lv.dtsi +++ b/arch/arm/boot/dts/logicpd-som-lv.dtsi @@ -265,21 +265,6 @@ }; }; -&omap3_pmx_core2 { - pinctrl-names = "default"; - pinctrl-0 = <&hsusb2_2_pins>; - hsusb2_2_pins: pinmux_hsusb2_2_pins { - pinctrl-single,pins = < - OMAP3630_CORE2_IOPAD(0x25f0, PIN_OUTPUT | MUX_MODE3) /* etk_d10.hsusb2_clk */ - OMAP3630_CORE2_IOPAD(0x25f2, PIN_OUTPUT | MUX_MODE3) /* etk_d11.hsusb2_stp */ - OMAP3630_CORE2_IOPAD(0x25f4, PIN_INPUT_PULLDOWN | MUX_MODE3) /* etk_d12.hsusb2_dir */ - OMAP3630_CORE2_IOPAD(0x25f6, PIN_INPUT_PULLDOWN | MUX_MODE3) /* etk_d13.hsusb2_nxt */ - OMAP3630_CORE2_IOPAD(0x25f8, PIN_INPUT_PULLDOWN | MUX_MODE3) /* etk_d14.hsusb2_data0 */ - OMAP3630_CORE2_IOPAD(0x25fa, PIN_INPUT_PULLDOWN | MUX_MODE3) /* etk_d15.hsusb2_data1 */ - >; - }; -}; - &uart2 { interrupts-extended = <&intc 73 &omap3_pmx_core OMAP3_UART2_RX>; pinctrl-names = "default"; diff --git a/arch/arm/boot/dts/logicpd-torpedo-baseboard.dtsi b/arch/arm/boot/dts/logicpd-torpedo-baseboard.dtsi index b4664ab00256..d3da8b1b473b 100644 --- a/arch/arm/boot/dts/logicpd-torpedo-baseboard.dtsi +++ b/arch/arm/boot/dts/logicpd-torpedo-baseboard.dtsi @@ -118,8 +118,8 @@ gpmc,device-width = <2>; gpmc,wait-pin = <0>; gpmc,burst-length = <4>; - gpmc,cycle2cycle-samecsen = <1>; - gpmc,cycle2cycle-diffcsen = <1>; + gpmc,cycle2cycle-samecsen; + gpmc,cycle2cycle-diffcsen; gpmc,cs-on-ns = <0>; gpmc,cs-rd-off-ns = <45>; gpmc,cs-wr-off-ns = <45>; diff --git a/arch/arm/boot/dts/omap3-gta04.dtsi b/arch/arm/boot/dts/omap3-gta04.dtsi index 7e3d8147e2c1..0365f06165e9 100644 --- a/arch/arm/boot/dts/omap3-gta04.dtsi +++ b/arch/arm/boot/dts/omap3-gta04.dtsi @@ -31,6 +31,8 @@ aliases { display0 = &lcd; display1 = &tv0; + /delete-property/ mmc2; + /delete-property/ mmc3; }; ldo_3v3: fixedregulator { diff --git a/arch/arm/boot/dts/qcom-apq8064-pins.dtsi b/arch/arm/boot/dts/qcom-apq8064-pins.dtsi index cbe42c4153a0..b4d286a6fab1 100644 --- a/arch/arm/boot/dts/qcom-apq8064-pins.dtsi +++ b/arch/arm/boot/dts/qcom-apq8064-pins.dtsi @@ -76,7 +76,7 @@ pinconf { pins = "gpio20", "gpio21"; drive-strength = <2>; - bias-disable = <0>; + bias-disable; }; }; @@ -116,7 +116,7 @@ pinconf { pins = "gpio24", "gpio25"; drive-strength = <2>; - bias-disable = <0>; + bias-disable; }; }; @@ -141,7 +141,7 @@ pinconf { pins = "gpio8", "gpio9"; drive-strength = <2>; - bias-disable = <0>; + bias-disable; }; }; @@ -166,7 +166,7 @@ pinconf { pins = "gpio12", "gpio13"; drive-strength = <2>; - bias-disable = <0>; + bias-disable; }; }; @@ -229,7 +229,7 @@ pinconf { pins = "gpio16", "gpio17"; drive-strength = <2>; - bias-disable = <0>; + bias-disable; }; }; @@ -282,7 +282,7 @@ pinconf { pins = "gpio84", "gpio85"; drive-strength = <2>; - bias-disable = <0>; + bias-disable; }; }; diff --git a/arch/arm/boot/dts/qcom-ipq8064.dtsi b/arch/arm/boot/dts/qcom-ipq8064.dtsi index 996f4458d9fc..8cb04aa8ed2f 100644 --- a/arch/arm/boot/dts/qcom-ipq8064.dtsi +++ b/arch/arm/boot/dts/qcom-ipq8064.dtsi @@ -972,7 +972,7 @@ snps,axi-config = <&stmmac_axi_setup>; snps,pbl = <32>; - snps,aal = <1>; + snps,aal; qcom,nss-common = <&nss_common>; qcom,qsgmii-csr = <&qsgmii_csr>; @@ -996,7 +996,7 @@ snps,axi-config = <&stmmac_axi_setup>; snps,pbl = <32>; - snps,aal = <1>; + snps,aal; qcom,nss-common = <&nss_common>; qcom,qsgmii-csr = <&qsgmii_csr>; @@ -1020,7 +1020,7 @@ snps,axi-config = <&stmmac_axi_setup>; snps,pbl = <32>; - snps,aal = <1>; + snps,aal; qcom,nss-common = <&nss_common>; qcom,qsgmii-csr = <&qsgmii_csr>; @@ -1044,7 +1044,7 @@ snps,axi-config = <&stmmac_axi_setup>; snps,pbl = <32>; - snps,aal = <1>; + snps,aal; qcom,nss-common = <&nss_common>; qcom,qsgmii-csr = <&qsgmii_csr>; diff --git a/arch/arm/boot/dts/sama5d3xmb.dtsi b/arch/arm/boot/dts/sama5d3xmb.dtsi index a499de8a7a64..3652c9e24124 100644 --- a/arch/arm/boot/dts/sama5d3xmb.dtsi +++ b/arch/arm/boot/dts/sama5d3xmb.dtsi @@ -26,7 +26,7 @@ spi0: spi@f0004000 { dmas = <0>, <0>; /* Do not use DMA for spi0 */ - m25p80@0 { + flash@0 { compatible = "atmel,at25df321a"; spi-max-frequency = <50000000>; reg = <0>; diff --git a/arch/arm/boot/dts/sama5d3xmb_cmp.dtsi b/arch/arm/boot/dts/sama5d3xmb_cmp.dtsi index fa9e5e2a745d..5d9e97fecf83 100644 --- a/arch/arm/boot/dts/sama5d3xmb_cmp.dtsi +++ b/arch/arm/boot/dts/sama5d3xmb_cmp.dtsi @@ -25,7 +25,7 @@ spi0: spi@f0004000 { dmas = <0>, <0>; /* Do not use DMA for spi0 */ - m25p80@0 { + flash@0 { compatible = "atmel,at25df321a"; spi-max-frequency = <50000000>; reg = <0>; diff --git a/arch/arm/boot/dts/sama7g5.dtsi b/arch/arm/boot/dts/sama7g5.dtsi index 4decd3a91a76..f691c8f08d04 100644 --- a/arch/arm/boot/dts/sama7g5.dtsi +++ b/arch/arm/boot/dts/sama7g5.dtsi @@ -601,9 +601,9 @@ #size-cells = <0>; clocks = <&pmc PMC_TYPE_PERIPHERAL 39>; atmel,fifo-size = <32>; - dmas = <&dma0 AT91_XDMAC_DT_PERID(7)>, - <&dma0 AT91_XDMAC_DT_PERID(8)>; - dma-names = "rx", "tx"; + dmas = <&dma0 AT91_XDMAC_DT_PERID(8)>, + <&dma0 AT91_XDMAC_DT_PERID(7)>; + dma-names = "tx", "rx"; status = "disabled"; }; }; @@ -786,9 +786,9 @@ #size-cells = <0>; clocks = <&pmc PMC_TYPE_PERIPHERAL 46>; atmel,fifo-size = <32>; - dmas = <&dma0 AT91_XDMAC_DT_PERID(21)>, - <&dma0 AT91_XDMAC_DT_PERID(22)>; - dma-names = "rx", "tx"; + dmas = <&dma0 AT91_XDMAC_DT_PERID(22)>, + <&dma0 AT91_XDMAC_DT_PERID(21)>; + dma-names = "tx", "rx"; status = "disabled"; }; }; @@ -810,9 +810,9 @@ #size-cells = <0>; clocks = <&pmc PMC_TYPE_PERIPHERAL 47>; atmel,fifo-size = <32>; - dmas = <&dma0 AT91_XDMAC_DT_PERID(23)>, - <&dma0 AT91_XDMAC_DT_PERID(24)>; - dma-names = "rx", "tx"; + dmas = <&dma0 AT91_XDMAC_DT_PERID(24)>, + <&dma0 AT91_XDMAC_DT_PERID(23)>; + dma-names = "tx", "rx"; status = "disabled"; }; }; diff --git a/arch/arm/boot/dts/spear1310-evb.dts b/arch/arm/boot/dts/spear1310-evb.dts index 4cbadcb41084..ddd1cf4d0554 100644 --- a/arch/arm/boot/dts/spear1310-evb.dts +++ b/arch/arm/boot/dts/spear1310-evb.dts @@ -379,7 +379,7 @@ }; }; - m25p80@1 { + flash@1 { compatible = "st,m25p80"; reg = <1>; spi-max-frequency = <12000000>; diff --git a/arch/arm/boot/dts/spear1340-evb.dts b/arch/arm/boot/dts/spear1340-evb.dts index fd194ebeedc9..3a51a41eb5e4 100644 --- a/arch/arm/boot/dts/spear1340-evb.dts +++ b/arch/arm/boot/dts/spear1340-evb.dts @@ -439,7 +439,7 @@ cs-gpios = <&gpiopinctrl 80 0>, <&gpiopinctrl 24 0>, <&gpiopinctrl 85 0>; - m25p80@0 { + flash@0 { compatible = "m25p80"; reg = <0>; spi-max-frequency = <12000000>; diff --git a/arch/arm/boot/dts/stm32mp157c-emstamp-argon.dtsi b/arch/arm/boot/dts/stm32mp157c-emstamp-argon.dtsi index 33ae5e0590df..ac53ee3c496b 100644 --- a/arch/arm/boot/dts/stm32mp157c-emstamp-argon.dtsi +++ b/arch/arm/boot/dts/stm32mp157c-emstamp-argon.dtsi @@ -398,7 +398,7 @@ #size-cells = <0>; status = "okay"; - flash0: is25lp016d@0 { + flash0: flash@0 { compatible = "jedec,spi-nor"; reg = <0>; spi-max-frequency = <133000000>; diff --git a/arch/arm/boot/dts/stm32mp157c-ev1.dts b/arch/arm/boot/dts/stm32mp157c-ev1.dts index e222d2d2cb44..d142dd30e16b 100644 --- a/arch/arm/boot/dts/stm32mp157c-ev1.dts +++ b/arch/arm/boot/dts/stm32mp157c-ev1.dts @@ -262,7 +262,7 @@ #size-cells = <0>; status = "okay"; - flash0: mx66l51235l@0 { + flash0: flash@0 { compatible = "jedec,spi-nor"; reg = <0>; spi-rx-bus-width = <4>; @@ -271,7 +271,7 @@ #size-cells = <1>; }; - flash1: mx66l51235l@1 { + flash1: flash@1 { compatible = "jedec,spi-nor"; reg = <1>; spi-rx-bus-width = <4>; diff --git a/arch/arm/boot/dts/usb_a9263.dts b/arch/arm/boot/dts/usb_a9263.dts index 8a0cfbfd0c45..b6cb9cdf8197 100644 --- a/arch/arm/boot/dts/usb_a9263.dts +++ b/arch/arm/boot/dts/usb_a9263.dts @@ -60,7 +60,7 @@ spi0: spi@fffa4000 { cs-gpios = <&pioB 15 GPIO_ACTIVE_HIGH>; status = "okay"; - mtd_dataflash@0 { + flash@0 { compatible = "atmel,at45", "atmel,dataflash"; reg = <0>; spi-max-frequency = <15000000>; diff --git a/arch/arm/configs/gemini_defconfig b/arch/arm/configs/gemini_defconfig index a7acfee11ffc..a80bc8a43091 100644 --- a/arch/arm/configs/gemini_defconfig +++ b/arch/arm/configs/gemini_defconfig @@ -49,11 +49,13 @@ CONFIG_ATA=y CONFIG_PATA_FTIDE010=y CONFIG_NETDEVICES=y CONFIG_TUN=y +CONFIG_NET_DSA_REALTEK=y CONFIG_NET_DSA_REALTEK_SMI=y +CONFIG_NET_DSA_REALTEK_RTL8366RB=y CONFIG_GEMINI_ETHERNET=y +CONFIG_MARVELL_PHY=y CONFIG_MDIO_BITBANG=y CONFIG_MDIO_GPIO=y -CONFIG_MARVELL_PHY=y CONFIG_INPUT_EVDEV=y CONFIG_KEYBOARD_GPIO=y # CONFIG_INPUT_MOUSE is not set @@ -66,6 +68,7 @@ CONFIG_SERIAL_OF_PLATFORM=y CONFIG_I2C_GPIO=y CONFIG_SPI=y CONFIG_SPI_GPIO=y +CONFIG_SENSORS_DRIVETEMP=y CONFIG_SENSORS_GPIO_FAN=y CONFIG_SENSORS_LM75=y CONFIG_THERMAL=y diff --git a/arch/arm/configs/imote2_defconfig b/arch/arm/configs/imote2_defconfig deleted file mode 100644 index 015b7ef237de..000000000000 --- a/arch/arm/configs/imote2_defconfig +++ /dev/null @@ -1,365 +0,0 @@ -# CONFIG_LOCALVERSION_AUTO is not set -CONFIG_SYSVIPC=y -CONFIG_LOG_BUF_SHIFT=14 -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_BLK_DEV_INITRD=y -CONFIG_RD_BZIP2=y -CONFIG_RD_LZMA=y -CONFIG_EXPERT=y -# CONFIG_COMPAT_BRK is not set -CONFIG_SLAB=y -CONFIG_MODULES=y -CONFIG_MODULE_UNLOAD=y -CONFIG_MODULE_FORCE_UNLOAD=y -CONFIG_MODVERSIONS=y -# CONFIG_BLK_DEV_BSG is not set -CONFIG_ARCH_PXA=y -CONFIG_MACH_INTELMOTE2=y -CONFIG_NO_HZ=y -CONFIG_HIGH_RES_TIMERS=y -CONFIG_PREEMPT=y -CONFIG_AEABI=y -CONFIG_ZBOOT_ROM_TEXT=0x0 -CONFIG_ZBOOT_ROM_BSS=0x0 -CONFIG_CMDLINE="root=/dev/mtdblock2 rootfstype=jffs2 console=ttyS2,115200 mem=32M" -CONFIG_KEXEC=y -CONFIG_FPE_NWFPE=y -CONFIG_BINFMT_AOUT=m -CONFIG_BINFMT_MISC=m -CONFIG_PM=y -CONFIG_APM_EMULATION=y -CONFIG_NET=y -CONFIG_PACKET=y -CONFIG_UNIX=y -CONFIG_INET=y -CONFIG_IP_PNP=y -CONFIG_IP_PNP_DHCP=y -CONFIG_IP_PNP_BOOTP=y -CONFIG_IP_PNP_RARP=y -CONFIG_SYN_COOKIES=y -# CONFIG_INET_XFRM_MODE_TRANSPORT is not set -# CONFIG_INET_XFRM_MODE_TUNNEL is not set -# CONFIG_INET_XFRM_MODE_BEET is not set -# CONFIG_INET_DIAG is not set -CONFIG_INET6_AH=m -CONFIG_INET6_ESP=m -CONFIG_INET6_IPCOMP=m -CONFIG_IPV6_MIP6=m -CONFIG_IPV6_TUNNEL=m -CONFIG_IPV6_MULTIPLE_TABLES=y -CONFIG_IPV6_SUBTREES=y -CONFIG_NETFILTER=y -CONFIG_NETFILTER_NETLINK_QUEUE=m -CONFIG_NF_CONNTRACK=m -CONFIG_NF_CONNTRACK_EVENTS=y -CONFIG_NF_CT_PROTO_SCTP=y -CONFIG_NF_CT_PROTO_UDPLITE=y -CONFIG_NF_CONNTRACK_AMANDA=m -CONFIG_NF_CONNTRACK_FTP=m -CONFIG_NF_CONNTRACK_H323=m -CONFIG_NF_CONNTRACK_IRC=m -CONFIG_NF_CONNTRACK_NETBIOS_NS=m -CONFIG_NF_CONNTRACK_PPTP=m -CONFIG_NF_CONNTRACK_SANE=m -CONFIG_NF_CONNTRACK_SIP=m -CONFIG_NF_CONNTRACK_TFTP=m -CONFIG_NF_CT_NETLINK=m -CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m -CONFIG_NETFILTER_XT_TARGET_LED=m -CONFIG_NETFILTER_XT_TARGET_MARK=m -CONFIG_NETFILTER_XT_TARGET_NFLOG=m -CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m -CONFIG_NETFILTER_XT_TARGET_TCPMSS=m -CONFIG_NETFILTER_XT_MATCH_COMMENT=m -CONFIG_NETFILTER_XT_MATCH_CONNBYTES=m -CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=m -CONFIG_NETFILTER_XT_MATCH_CONNMARK=m -CONFIG_NETFILTER_XT_MATCH_CONNTRACK=m -CONFIG_NETFILTER_XT_MATCH_DCCP=m -CONFIG_NETFILTER_XT_MATCH_DSCP=m -CONFIG_NETFILTER_XT_MATCH_ESP=m -CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m -CONFIG_NETFILTER_XT_MATCH_HELPER=m -CONFIG_NETFILTER_XT_MATCH_LENGTH=m -CONFIG_NETFILTER_XT_MATCH_LIMIT=m -CONFIG_NETFILTER_XT_MATCH_MAC=m -CONFIG_NETFILTER_XT_MATCH_MARK=m -CONFIG_NETFILTER_XT_MATCH_MULTIPORT=m -CONFIG_NETFILTER_XT_MATCH_POLICY=m -CONFIG_NETFILTER_XT_MATCH_PKTTYPE=m -CONFIG_NETFILTER_XT_MATCH_QUOTA=m -CONFIG_NETFILTER_XT_MATCH_REALM=m -CONFIG_NETFILTER_XT_MATCH_SCTP=m -CONFIG_NETFILTER_XT_MATCH_STATE=m -CONFIG_NETFILTER_XT_MATCH_STATISTIC=m -CONFIG_NETFILTER_XT_MATCH_STRING=m -CONFIG_NETFILTER_XT_MATCH_TCPMSS=m -CONFIG_NETFILTER_XT_MATCH_TIME=m -CONFIG_NETFILTER_XT_MATCH_U32=m -CONFIG_NF_CONNTRACK_IPV4=m -CONFIG_IP_NF_IPTABLES=m -CONFIG_IP_NF_MATCH_ADDRTYPE=m -CONFIG_IP_NF_MATCH_AH=m -CONFIG_IP_NF_MATCH_ECN=m -CONFIG_IP_NF_MATCH_TTL=m -CONFIG_IP_NF_FILTER=m -CONFIG_IP_NF_TARGET_REJECT=m -CONFIG_IP_NF_TARGET_LOG=m -CONFIG_NF_NAT=m -CONFIG_IP_NF_TARGET_MASQUERADE=m -CONFIG_IP_NF_TARGET_NETMAP=m -CONFIG_IP_NF_TARGET_REDIRECT=m -CONFIG_NF_NAT_SNMP_BASIC=m -CONFIG_IP_NF_MANGLE=m -CONFIG_IP_NF_TARGET_CLUSTERIP=m -CONFIG_IP_NF_TARGET_ECN=m -CONFIG_IP_NF_TARGET_TTL=m -CONFIG_IP_NF_RAW=m -CONFIG_IP_NF_ARPTABLES=m -CONFIG_IP_NF_ARPFILTER=m -CONFIG_IP_NF_ARP_MANGLE=m -CONFIG_NF_CONNTRACK_IPV6=m -CONFIG_IP6_NF_IPTABLES=m -CONFIG_IP6_NF_MATCH_AH=m -CONFIG_IP6_NF_MATCH_EUI64=m -CONFIG_IP6_NF_MATCH_FRAG=m -CONFIG_IP6_NF_MATCH_OPTS=m -CONFIG_IP6_NF_MATCH_HL=m -CONFIG_IP6_NF_MATCH_IPV6HEADER=m -CONFIG_IP6_NF_MATCH_MH=m -CONFIG_IP6_NF_MATCH_RT=m -CONFIG_IP6_NF_TARGET_HL=m -CONFIG_IP6_NF_FILTER=m -CONFIG_IP6_NF_TARGET_REJECT=m -CONFIG_IP6_NF_MANGLE=m -CONFIG_IP6_NF_RAW=m -CONFIG_BRIDGE=m -# CONFIG_BRIDGE_IGMP_SNOOPING is not set -CONFIG_IEEE802154=y -# CONFIG_WIRELESS is not set -CONFIG_DEVTMPFS=y -CONFIG_DEVTMPFS_MOUNT=y -CONFIG_FW_LOADER=m -CONFIG_CONNECTOR=m -CONFIG_MTD=y -CONFIG_MTD_CMDLINE_PARTS=y -CONFIG_MTD_AFS_PARTS=y -CONFIG_MTD_AR7_PARTS=y -CONFIG_MTD_BLOCK=y -CONFIG_MTD_CFI=y -CONFIG_MTD_CFI_ADV_OPTIONS=y -CONFIG_MTD_CFI_GEOMETRY=y -# CONFIG_MTD_MAP_BANK_WIDTH_1 is not set -# CONFIG_MTD_MAP_BANK_WIDTH_4 is not set -# CONFIG_MTD_CFI_I2 is not set -CONFIG_MTD_OTP=y -CONFIG_MTD_CFI_INTELEXT=y -CONFIG_MTD_PXA2XX=y -CONFIG_BLK_DEV_LOOP=m -CONFIG_BLK_DEV_CRYPTOLOOP=m -CONFIG_BLK_DEV_NBD=m -CONFIG_BLK_DEV_RAM=y -CONFIG_NETDEVICES=y -CONFIG_DUMMY=y -# CONFIG_WLAN is not set -CONFIG_PPP=m -CONFIG_PPP_MULTILINK=y -CONFIG_PPP_FILTER=y -CONFIG_PPP_ASYNC=m -CONFIG_PPP_SYNC_TTY=m -CONFIG_PPP_DEFLATE=m -CONFIG_PPP_BSDCOMP=m -# CONFIG_INPUT_MOUSEDEV is not set -CONFIG_INPUT_EVDEV=y -# CONFIG_KEYBOARD_ATKBD is not set -CONFIG_KEYBOARD_GPIO=y -CONFIG_KEYBOARD_PXA27x=y -# CONFIG_INPUT_MOUSE is not set -CONFIG_INPUT_TOUCHSCREEN=y -CONFIG_INPUT_MISC=y -CONFIG_INPUT_UINPUT=y -# CONFIG_SERIO is not set -CONFIG_SERIAL_PXA=y -CONFIG_SERIAL_PXA_CONSOLE=y -CONFIG_LEGACY_PTY_COUNT=8 -# CONFIG_HW_RANDOM is not set -CONFIG_I2C=y -CONFIG_I2C_CHARDEV=y -CONFIG_I2C_PXA=y -CONFIG_SPI=y -CONFIG_SPI_PXA2XX=y -CONFIG_GPIO_SYSFS=y -CONFIG_POWER_SUPPLY=y -# CONFIG_HWMON is not set -CONFIG_PMIC_DA903X=y -CONFIG_REGULATOR=y -CONFIG_REGULATOR_DEBUG=y -CONFIG_REGULATOR_DA903X=y -CONFIG_MEDIA_SUPPORT=y -CONFIG_VIDEO_DEV=y -CONFIG_MEDIA_TUNER_CUSTOMISE=y -# CONFIG_MEDIA_TUNER_SIMPLE is not set -# CONFIG_MEDIA_TUNER_TDA8290 is not set -# CONFIG_MEDIA_TUNER_TDA827X is not set -# CONFIG_MEDIA_TUNER_TDA18271 is not set -# CONFIG_MEDIA_TUNER_TDA9887 is not set -# CONFIG_MEDIA_TUNER_TEA5761 is not set -# CONFIG_MEDIA_TUNER_TEA5767 is not set -# CONFIG_MEDIA_TUNER_MT20XX is not set -# CONFIG_MEDIA_TUNER_MT2060 is not set -# CONFIG_MEDIA_TUNER_MT2266 is not set -# CONFIG_MEDIA_TUNER_MT2131 is not set -# CONFIG_MEDIA_TUNER_QT1010 is not set -# CONFIG_MEDIA_TUNER_XC2028 is not set -# CONFIG_MEDIA_TUNER_XC5000 is not set -# CONFIG_MEDIA_TUNER_MXL5005S is not set -# CONFIG_MEDIA_TUNER_MXL5007T is not set -# CONFIG_MEDIA_TUNER_MC44S803 is not set -# CONFIG_VIDEO_HELPER_CHIPS_AUTO is not set -CONFIG_VIDEO_PXA27x=y -# CONFIG_V4L_USB_DRIVERS is not set -# CONFIG_RADIO_ADAPTERS is not set -CONFIG_FB=y -CONFIG_FB_PXA=y -CONFIG_FB_PXA_OVERLAY=y -CONFIG_FB_PXA_PARAMETERS=y -# CONFIG_LCD_CLASS_DEVICE is not set -CONFIG_BACKLIGHT_CLASS_DEVICE=y -# CONFIG_VGA_CONSOLE is not set -CONFIG_FRAMEBUFFER_CONSOLE=y -CONFIG_FONTS=y -CONFIG_FONT_MINI_4x6=y -CONFIG_SOUND=y -CONFIG_SND=y -CONFIG_SND_MIXER_OSS=y -CONFIG_SND_PCM_OSS=y -# CONFIG_SND_DRIVERS is not set -# CONFIG_SND_ARM is not set -# CONFIG_SND_SPI is not set -# CONFIG_SND_USB is not set -CONFIG_SND_SOC=y -CONFIG_SND_PXA2XX_SOC=y -# CONFIG_USB_HID is not set -CONFIG_USB=y -CONFIG_USB_OHCI_HCD=y -CONFIG_USB_GADGET=y -CONFIG_USB_PXA27X=y -CONFIG_USB_ETH=m -# CONFIG_USB_ETH_RNDIS is not set -CONFIG_MMC=y -CONFIG_SDIO_UART=m -CONFIG_MMC_PXA=y -CONFIG_MMC_SPI=y -CONFIG_NEW_LEDS=y -CONFIG_LEDS_CLASS=y -CONFIG_LEDS_LP3944=y -CONFIG_LEDS_TRIGGERS=y -CONFIG_LEDS_TRIGGER_TIMER=y -CONFIG_LEDS_TRIGGER_HEARTBEAT=y -CONFIG_LEDS_TRIGGER_BACKLIGHT=y -CONFIG_LEDS_TRIGGER_GPIO=y -CONFIG_LEDS_TRIGGER_DEFAULT_ON=y -CONFIG_RTC_CLASS=y -CONFIG_RTC_DRV_PXA=y -CONFIG_EXT2_FS=y -CONFIG_EXT3_FS=m -CONFIG_AUTOFS4_FS=y -CONFIG_FUSE_FS=m -CONFIG_CUSE=m -CONFIG_MSDOS_FS=m -CONFIG_VFAT_FS=m -CONFIG_TMPFS=y -CONFIG_JFFS2_FS=y -CONFIG_JFFS2_FS_WBUF_VERIFY=y -CONFIG_JFFS2_SUMMARY=y -CONFIG_JFFS2_FS_XATTR=y -CONFIG_JFFS2_COMPRESSION_OPTIONS=y -CONFIG_JFFS2_LZO=y -CONFIG_JFFS2_RUBIN=y -CONFIG_CRAMFS=m -CONFIG_SQUASHFS=m -CONFIG_ROMFS_FS=m -CONFIG_NFS_FS=y -CONFIG_NFS_V3=y -CONFIG_NFS_V3_ACL=y -CONFIG_NFSD=m -CONFIG_NFSD_V3_ACL=y -CONFIG_SMB_FS=m -CONFIG_CIFS=m -CONFIG_CIFS_STATS=y -CONFIG_CIFS_XATTR=y -CONFIG_CIFS_POSIX=y -CONFIG_NLS_CODEPAGE_437=m -CONFIG_NLS_CODEPAGE_737=m -CONFIG_NLS_CODEPAGE_775=m -CONFIG_NLS_CODEPAGE_850=m -CONFIG_NLS_CODEPAGE_852=m -CONFIG_NLS_CODEPAGE_855=m -CONFIG_NLS_CODEPAGE_857=m -CONFIG_NLS_CODEPAGE_860=m -CONFIG_NLS_CODEPAGE_861=m -CONFIG_NLS_CODEPAGE_862=m -CONFIG_NLS_CODEPAGE_863=m -CONFIG_NLS_CODEPAGE_864=m -CONFIG_NLS_CODEPAGE_865=m -CONFIG_NLS_CODEPAGE_866=m -CONFIG_NLS_CODEPAGE_869=m -CONFIG_NLS_CODEPAGE_936=m -CONFIG_NLS_CODEPAGE_950=m -CONFIG_NLS_CODEPAGE_932=m -CONFIG_NLS_CODEPAGE_949=m -CONFIG_NLS_CODEPAGE_874=m -CONFIG_NLS_ISO8859_8=m -CONFIG_NLS_CODEPAGE_1250=m -CONFIG_NLS_CODEPAGE_1251=m -CONFIG_NLS_ASCII=m -CONFIG_NLS_ISO8859_1=m -CONFIG_NLS_ISO8859_2=m -CONFIG_NLS_ISO8859_3=m -CONFIG_NLS_ISO8859_4=m -CONFIG_NLS_ISO8859_5=m -CONFIG_NLS_ISO8859_6=m -CONFIG_NLS_ISO8859_7=m -CONFIG_NLS_ISO8859_9=m -CONFIG_NLS_ISO8859_13=m -CONFIG_NLS_ISO8859_14=m -CONFIG_NLS_ISO8859_15=m -CONFIG_NLS_KOI8_R=m -CONFIG_NLS_KOI8_U=m -CONFIG_NLS_UTF8=m -CONFIG_PRINTK_TIME=y -CONFIG_DEBUG_FS=y -CONFIG_DEBUG_KERNEL=y -# CONFIG_SCHED_DEBUG is not set -CONFIG_DEBUG_RT_MUTEXES=y -CONFIG_PROVE_LOCKING=y -# CONFIG_FTRACE is not set -CONFIG_DEBUG_USER=y -CONFIG_CRYPTO_NULL=m -CONFIG_CRYPTO_CRYPTD=m -CONFIG_CRYPTO_TEST=m -CONFIG_CRYPTO_ECB=m -CONFIG_CRYPTO_LRW=m -CONFIG_CRYPTO_PCBC=m -CONFIG_CRYPTO_XTS=m -CONFIG_CRYPTO_XCBC=m -CONFIG_CRYPTO_VMAC=m -CONFIG_CRYPTO_GHASH=m -CONFIG_CRYPTO_MD4=m -CONFIG_CRYPTO_MICHAEL_MIC=m -CONFIG_CRYPTO_SHA256=m -CONFIG_CRYPTO_SHA512=m -CONFIG_CRYPTO_TGR192=m -CONFIG_CRYPTO_AES=m -CONFIG_CRYPTO_ARC4=m -CONFIG_CRYPTO_BLOWFISH=m -CONFIG_CRYPTO_CAST5=m -CONFIG_CRYPTO_CAST6=m -CONFIG_CRYPTO_FCRYPT=m -CONFIG_CRYPTO_KHAZAD=m -CONFIG_CRYPTO_SEED=m -CONFIG_CRYPTO_SERPENT=m -CONFIG_CRYPTO_TEA=m -CONFIG_CRYPTO_TWOFISH=m -# CONFIG_CRYPTO_ANSI_CPRNG is not set -CONFIG_CRC16=y diff --git a/arch/arm/configs/lpc18xx_defconfig b/arch/arm/configs/lpc18xx_defconfig index be882ea0eee4..688c9849eec8 100644 --- a/arch/arm/configs/lpc18xx_defconfig +++ b/arch/arm/configs/lpc18xx_defconfig @@ -30,7 +30,6 @@ CONFIG_ARM_APPENDED_DTB=y # CONFIG_BLK_DEV_BSG is not set CONFIG_BINFMT_FLAT=y CONFIG_BINFMT_ZFLAT=y -CONFIG_BINFMT_SHARED_FLAT=y # CONFIG_COREDUMP is not set CONFIG_NET=y CONFIG_PACKET=y diff --git a/arch/arm/configs/mps2_defconfig b/arch/arm/configs/mps2_defconfig index 89f4a6ff30bd..c1e98e33a348 100644 --- a/arch/arm/configs/mps2_defconfig +++ b/arch/arm/configs/mps2_defconfig @@ -23,7 +23,6 @@ CONFIG_PREEMPT_VOLUNTARY=y CONFIG_ZBOOT_ROM_TEXT=0x0 CONFIG_ZBOOT_ROM_BSS=0x0 CONFIG_BINFMT_FLAT=y -CONFIG_BINFMT_SHARED_FLAT=y # CONFIG_COREDUMP is not set # CONFIG_SUSPEND is not set CONFIG_NET=y diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig index 6e0c8c19b35c..d6a6811f0539 100644 --- a/arch/arm/configs/multi_v7_defconfig +++ b/arch/arm/configs/multi_v7_defconfig @@ -673,6 +673,7 @@ CONFIG_VIDEO_STI_DELTA=m CONFIG_VIDEO_RENESAS_FDP1=m CONFIG_VIDEO_RENESAS_JPU=m CONFIG_VIDEO_RENESAS_VSP1=m +CONFIG_VIDEO_TEGRA_VDE=m CONFIG_V4L_TEST_DRIVERS=y CONFIG_VIDEO_VIVID=m CONFIG_VIDEO_ADV7180=m diff --git a/arch/arm/configs/stm32_defconfig b/arch/arm/configs/stm32_defconfig index 551db328009d..71d6bfcf4551 100644 --- a/arch/arm/configs/stm32_defconfig +++ b/arch/arm/configs/stm32_defconfig @@ -28,7 +28,6 @@ CONFIG_ZBOOT_ROM_BSS=0x0 CONFIG_XIP_KERNEL=y CONFIG_XIP_PHYS_ADDR=0x08008000 CONFIG_BINFMT_FLAT=y -CONFIG_BINFMT_SHARED_FLAT=y # CONFIG_COREDUMP is not set CONFIG_DEVTMPFS=y CONFIG_DEVTMPFS_MOUNT=y diff --git a/arch/arm/configs/tegra_defconfig b/arch/arm/configs/tegra_defconfig index 289d022acc4b..c209722399d7 100644 --- a/arch/arm/configs/tegra_defconfig +++ b/arch/arm/configs/tegra_defconfig @@ -286,7 +286,8 @@ CONFIG_SERIO_NVEC_PS2=y CONFIG_NVEC_POWER=y CONFIG_NVEC_PAZ00=y CONFIG_STAGING_MEDIA=y -CONFIG_TEGRA_VDE=y +CONFIG_V4L_MEM2MEM_DRIVERS=y +CONFIG_VIDEO_TEGRA_VDE=y CONFIG_CHROME_PLATFORMS=y CONFIG_CROS_EC=y CONFIG_CROS_EC_I2C=m diff --git a/arch/arm/configs/u8500_defconfig b/arch/arm/configs/u8500_defconfig index 3b30913d7d8d..a352207a64d7 100644 --- a/arch/arm/configs/u8500_defconfig +++ b/arch/arm/configs/u8500_defconfig @@ -20,7 +20,6 @@ CONFIG_VFP=y CONFIG_NEON=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y -# CONFIG_BLK_DEV_BSG is not set CONFIG_PARTITION_ADVANCED=y CONFIG_CMA=y CONFIG_NET=y @@ -41,6 +40,8 @@ CONFIG_MAC80211_LEDS=y CONFIG_CAIF=y CONFIG_DEVTMPFS=y CONFIG_DEVTMPFS_MOUNT=y +CONFIG_GNSS=y +CONFIG_GNSS_SIRF_SERIAL=y CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=65536 CONFIG_NETDEVICES=y @@ -83,6 +84,8 @@ CONFIG_SPI_GPIO=y CONFIG_SPI_PL022=y CONFIG_GPIO_STMPE=y CONFIG_GPIO_TC3589X=y +CONFIG_BATTERY_SAMSUNG_SDI=y +CONFIG_AB8500_BM=y CONFIG_SENSORS_IIO_HWMON=y CONFIG_SENSORS_NTC_THERMISTOR=y CONFIG_THERMAL=y @@ -98,10 +101,13 @@ CONFIG_VIDEO_V4L2_SUBDEV_API=y CONFIG_V4L2_FLASH_LED_CLASS=y CONFIG_DRM=y CONFIG_DRM_PANEL_NOVATEK_NT35510=y +CONFIG_DRM_PANEL_NOVATEK_NT35560=y +CONFIG_DRM_PANEL_SAMSUNG_DB7430=y CONFIG_DRM_PANEL_SAMSUNG_S6D16D0=y +CONFIG_DRM_PANEL_SAMSUNG_S6D27A1=y CONFIG_DRM_PANEL_SAMSUNG_S6E63M0=y CONFIG_DRM_PANEL_SAMSUNG_S6E63M0_DSI=y -CONFIG_DRM_PANEL_SONY_ACX424AKP=y +CONFIG_DRM_PANEL_WIDECHIPS_WS2401=y CONFIG_DRM_LIMA=y CONFIG_DRM_MCDE=y CONFIG_FB=y @@ -129,6 +135,7 @@ CONFIG_LEDS_LM3530=y CONFIG_LEDS_GPIO=y CONFIG_LEDS_LP55XX_COMMON=y CONFIG_LEDS_LP5521=y +CONFIG_LEDS_REGULATOR=y CONFIG_LEDS_RT8515=y CONFIG_LEDS_TRIGGER_HEARTBEAT=y CONFIG_RTC_CLASS=y @@ -144,17 +151,22 @@ CONFIG_IIO_SW_TRIGGER=y CONFIG_BMA180=y CONFIG_BMC150_ACCEL=y CONFIG_IIO_ST_ACCEL_3AXIS=y +# CONFIG_IIO_ST_ACCEL_SPI_3AXIS is not set CONFIG_IIO_RESCALE=y CONFIG_MPU3050_I2C=y CONFIG_IIO_ST_GYRO_3AXIS=y +# CONFIG_IIO_ST_GYRO_SPI_3AXIS is not set CONFIG_INV_MPU6050_I2C=y CONFIG_BH1780=y CONFIG_GP2AP002=y +CONFIG_TSL2772=y CONFIG_AK8974=y CONFIG_IIO_ST_MAGN_3AXIS=y +# CONFIG_IIO_ST_MAGN_SPI_3AXIS is not set CONFIG_YAMAHA_YAS530=y CONFIG_IIO_HRTIMER_TRIGGER=y CONFIG_IIO_ST_PRESS=y +# CONFIG_IIO_ST_PRESS_SPI is not set CONFIG_EXT2_FS=y CONFIG_EXT2_FS_XATTR=y CONFIG_EXT2_FS_POSIX_ACL=y @@ -173,10 +185,9 @@ CONFIG_CRYPTO_DEV_UX500_CRYP=y CONFIG_CRYPTO_DEV_UX500_HASH=y CONFIG_CRYPTO_DEV_UX500_DEBUG=y CONFIG_PRINTK_TIME=y -CONFIG_DEBUG_INFO=y +CONFIG_DEBUG_KERNEL=y CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_FS=y -CONFIG_DEBUG_KERNEL=y # CONFIG_SCHED_DEBUG is not set # CONFIG_FTRACE is not set CONFIG_DEBUG_USER=y diff --git a/arch/arm/configs/vf610m4_defconfig b/arch/arm/configs/vf610m4_defconfig index a89f035c3b01..70fdbfd83484 100644 --- a/arch/arm/configs/vf610m4_defconfig +++ b/arch/arm/configs/vf610m4_defconfig @@ -18,7 +18,6 @@ CONFIG_XIP_KERNEL=y CONFIG_XIP_PHYS_ADDR=0x0f000080 CONFIG_BINFMT_FLAT=y CONFIG_BINFMT_ZFLAT=y -CONFIG_BINFMT_SHARED_FLAT=y # CONFIG_SUSPEND is not set # CONFIG_UEVENT_HELPER is not set # CONFIG_STANDALONE is not set diff --git a/arch/arm/include/asm/arch_gicv3.h b/arch/arm/include/asm/arch_gicv3.h index 413abfb42989..f82a819eb0db 100644 --- a/arch/arm/include/asm/arch_gicv3.h +++ b/arch/arm/include/asm/arch_gicv3.h @@ -48,6 +48,7 @@ static inline u32 read_ ## a64(void) \ return read_sysreg(a32); \ } \ +CPUIF_MAP(ICC_EOIR1, ICC_EOIR1_EL1) CPUIF_MAP(ICC_PMR, ICC_PMR_EL1) CPUIF_MAP(ICC_AP0R0, ICC_AP0R0_EL1) CPUIF_MAP(ICC_AP0R1, ICC_AP0R1_EL1) @@ -63,12 +64,6 @@ CPUIF_MAP(ICC_AP1R3, ICC_AP1R3_EL1) /* Low-level accessors */ -static inline void gic_write_eoir(u32 irq) -{ - write_sysreg(irq, ICC_EOIR1); - isb(); -} - static inline void gic_write_dir(u32 val) { write_sysreg(val, ICC_DIR); diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h index 34fe8d2dd5d1..90fbe4a3f9c8 100644 --- a/arch/arm/include/asm/assembler.h +++ b/arch/arm/include/asm/assembler.h @@ -666,12 +666,11 @@ THUMB( orr \reg , \reg , #PSR_T_BIT ) __adldst_l str, \src, \sym, \tmp, \cond .endm - .macro __ldst_va, op, reg, tmp, sym, cond + .macro __ldst_va, op, reg, tmp, sym, cond, offset #if __LINUX_ARM_ARCH__ >= 7 || \ !defined(CONFIG_ARM_HAS_GROUP_RELOCS) || \ (defined(MODULE) && defined(CONFIG_ARM_MODULE_PLTS)) mov_l \tmp, \sym, \cond - \op\cond \reg, [\tmp] #else /* * Avoid a literal load, by emitting a sequence of ADD/LDR instructions @@ -683,24 +682,29 @@ THUMB( orr \reg , \reg , #PSR_T_BIT ) .reloc .L0_\@, R_ARM_ALU_PC_G0_NC, \sym .reloc .L1_\@, R_ARM_ALU_PC_G1_NC, \sym .reloc .L2_\@, R_ARM_LDR_PC_G2, \sym -.L0_\@: sub\cond \tmp, pc, #8 -.L1_\@: sub\cond \tmp, \tmp, #4 -.L2_\@: \op\cond \reg, [\tmp, #0] +.L0_\@: sub\cond \tmp, pc, #8 - \offset +.L1_\@: sub\cond \tmp, \tmp, #4 - \offset +.L2_\@: #endif + \op\cond \reg, [\tmp, #\offset] .endm /* * ldr_va - load a 32-bit word from the virtual address of \sym */ - .macro ldr_va, rd:req, sym:req, cond - __ldst_va ldr, \rd, \rd, \sym, \cond + .macro ldr_va, rd:req, sym:req, cond, tmp, offset=0 + .ifnb \tmp + __ldst_va ldr, \rd, \tmp, \sym, \cond, \offset + .else + __ldst_va ldr, \rd, \rd, \sym, \cond, \offset + .endif .endm /* * str_va - store a 32-bit word to the virtual address of \sym */ .macro str_va, rn:req, sym:req, tmp:req, cond - __ldst_va str, \rn, \tmp, \sym, \cond + __ldst_va str, \rn, \tmp, \sym, \cond, 0 .endm /* @@ -727,9 +731,11 @@ THUMB( orr \reg , \reg , #PSR_T_BIT ) * are permitted to overlap with 'rd' if != sp */ .macro ldr_this_cpu, rd:req, sym:req, t1:req, t2:req -#if __LINUX_ARM_ARCH__ >= 7 || \ - !defined(CONFIG_ARM_HAS_GROUP_RELOCS) || \ - (defined(MODULE) && defined(CONFIG_ARM_MODULE_PLTS)) +#ifndef CONFIG_SMP + ldr_va \rd, \sym, tmp=\t1 +#elif __LINUX_ARM_ARCH__ >= 7 || \ + !defined(CONFIG_ARM_HAS_GROUP_RELOCS) || \ + (defined(MODULE) && defined(CONFIG_ARM_MODULE_PLTS)) this_cpu_offset \t1 mov_l \t2, \sym ldr \rd, [\t1, \t2] diff --git a/arch/arm/include/asm/io.h b/arch/arm/include/asm/io.h index 0c70eb688a00..2a0739a2350b 100644 --- a/arch/arm/include/asm/io.h +++ b/arch/arm/include/asm/io.h @@ -440,6 +440,9 @@ extern void pci_iounmap(struct pci_dev *dev, void __iomem *addr); #define ARCH_HAS_VALID_PHYS_ADDR_RANGE extern int valid_phys_addr_range(phys_addr_t addr, size_t size); extern int valid_mmap_phys_addr_range(unsigned long pfn, size_t size); +extern bool arch_memremap_can_ram_remap(resource_size_t offset, size_t size, + unsigned long flags); +#define arch_memremap_can_ram_remap arch_memremap_can_ram_remap #endif /* diff --git a/arch/arm/include/asm/module.h b/arch/arm/include/asm/module.h index cfffae67c04e..5546c9751478 100644 --- a/arch/arm/include/asm/module.h +++ b/arch/arm/include/asm/module.h @@ -3,20 +3,10 @@ #define _ASM_ARM_MODULE_H #include <asm-generic/module.h> - -struct unwind_table; +#include <asm/unwind.h> #ifdef CONFIG_ARM_UNWIND -enum { - ARM_SEC_INIT, - ARM_SEC_DEVINIT, - ARM_SEC_CORE, - ARM_SEC_EXIT, - ARM_SEC_DEVEXIT, - ARM_SEC_HOT, - ARM_SEC_UNLIKELY, - ARM_SEC_MAX, -}; +#define ELF_SECTION_UNWIND 0x70000001 #endif #define PLT_ENT_STRIDE L1_CACHE_BYTES @@ -36,7 +26,8 @@ struct mod_plt_sec { struct mod_arch_specific { #ifdef CONFIG_ARM_UNWIND - struct unwind_table *unwind[ARM_SEC_MAX]; + struct list_head unwind_list; + struct unwind_table *init_table; #endif #ifdef CONFIG_ARM_MODULE_PLTS struct mod_plt_sec core; diff --git a/arch/arm/include/asm/timex.h b/arch/arm/include/asm/timex.h index 7c3b3671d6c2..6d1337c169cd 100644 --- a/arch/arm/include/asm/timex.h +++ b/arch/arm/include/asm/timex.h @@ -11,5 +11,6 @@ typedef unsigned long cycles_t; #define get_cycles() ({ cycles_t c; read_current_timer(&c) ? 0 : c; }) +#define random_get_entropy() (((unsigned long)get_cycles()) ?: random_get_entropy_fallback()) #endif diff --git a/arch/arm/include/asm/unwind.h b/arch/arm/include/asm/unwind.h index 0f8a3439902d..b51f85417f58 100644 --- a/arch/arm/include/asm/unwind.h +++ b/arch/arm/include/asm/unwind.h @@ -24,6 +24,7 @@ struct unwind_idx { struct unwind_table { struct list_head list; + struct list_head mod_list; const struct unwind_idx *start; const struct unwind_idx *origin; const struct unwind_idx *stop; diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S index 06508698abb8..c39303e5c234 100644 --- a/arch/arm/kernel/entry-armv.S +++ b/arch/arm/kernel/entry-armv.S @@ -61,9 +61,8 @@ .macro pabt_helper @ PABORT handler takes pt_regs in r2, fault address in r4 and psr in r5 #ifdef MULTI_PABORT - ldr ip, .LCprocfns - mov lr, pc - ldr pc, [ip, #PROCESSOR_PABT_FUNC] + ldr_va ip, processor, offset=PROCESSOR_PABT_FUNC + bl_r ip #else bl CPU_PABORT_HANDLER #endif @@ -82,9 +81,8 @@ @ the fault status register in r1. r9 must be preserved. @ #ifdef MULTI_DABORT - ldr ip, .LCprocfns - mov lr, pc - ldr pc, [ip, #PROCESSOR_DABT_FUNC] + ldr_va ip, processor, offset=PROCESSOR_DABT_FUNC + bl_r ip #else bl CPU_DABORT_HANDLER #endif @@ -302,16 +300,6 @@ __fiq_svc: UNWIND(.fnend ) ENDPROC(__fiq_svc) - .align 5 -.LCcralign: - .word cr_alignment -#ifdef MULTI_DABORT -.LCprocfns: - .word processor -#endif -.LCfp: - .word fp_enter - /* * Abort mode handlers */ @@ -370,7 +358,7 @@ ENDPROC(__fiq_abt) THUMB( stmia sp, {r0 - r12} ) ATRAP( mrc p15, 0, r7, c1, c0, 0) - ATRAP( ldr r8, .LCcralign) + ATRAP( ldr_va r8, cr_alignment) ldmia r0, {r3 - r5} add r0, sp, #S_PC @ here for interlock avoidance @@ -379,8 +367,6 @@ ENDPROC(__fiq_abt) str r3, [sp] @ save the "real" r0 copied @ from the exception stack - ATRAP( ldr r8, [r8, #0]) - @ @ We are now ready to fill in the remaining blanks on the stack: @ @@ -505,9 +491,7 @@ __und_usr_thumb: */ #if __LINUX_ARM_ARCH__ < 7 /* If the target CPU may not be Thumb-2-capable, a run-time check is needed: */ -#define NEED_CPU_ARCHITECTURE - ldr r5, .LCcpu_architecture - ldr r5, [r5] + ldr_va r5, cpu_architecture cmp r5, #CPU_ARCH_ARMv7 blo __und_usr_fault_16 @ 16bit undefined instruction /* @@ -654,12 +638,6 @@ call_fpe: ret.w lr @ CP#14 (Debug) ret.w lr @ CP#15 (Control) -#ifdef NEED_CPU_ARCHITECTURE - .align 2 -.LCcpu_architecture: - .word __cpu_architecture -#endif - #ifdef CONFIG_NEON .align 6 @@ -685,9 +663,8 @@ call_fpe: #endif do_fpe: - ldr r4, .LCfp add r10, r10, #TI_FPSTATE @ r10 = workspace - ldr pc, [r4] @ Call FP module USR entry point + ldr_va pc, fp_enter, tmp=r4 @ Call FP module USR entry point /* * The FP module is called with these registers set: @@ -1101,6 +1078,12 @@ __kuser_helper_end: */ .macro vector_stub, name, mode, correction=0 .align 5 +#ifdef CONFIG_HARDEN_BRANCH_HISTORY +vector_bhb_bpiall_\name: + mcr p15, 0, r0, c7, c5, 6 @ BPIALL + @ isb not needed due to "movs pc, lr" in the vector stub + @ which gives a "context synchronisation". +#endif vector_\name: .if \correction @@ -1111,7 +1094,8 @@ vector_\name: stmia sp, {r0, lr} @ save r0, lr @ Save spsr_<exception> (parent CPSR) -2: mrs lr, spsr +.Lvec_\name: + mrs lr, spsr str lr, [sp, #8] @ save spsr @ @@ -1145,28 +1129,14 @@ vector_bhb_loop8_\name: @ bhb workaround mov r0, #8 -3: b . + 4 +3: W(b) . + 4 subs r0, r0, #1 bne 3b - dsb - isb - b 2b -ENDPROC(vector_bhb_loop8_\name) - -vector_bhb_bpiall_\name: - .if \correction - sub lr, lr, #\correction - .endif - - @ Save r0, lr_<exception> (parent PC) - stmia sp, {r0, lr} - - @ bhb workaround - mcr p15, 0, r0, c7, c5, 6 @ BPIALL + dsb nsh @ isb not needed due to "movs pc, lr" in the vector stub @ which gives a "context synchronisation". - b 2b -ENDPROC(vector_bhb_bpiall_\name) + b .Lvec_\name +ENDPROC(vector_bhb_loop8_\name) .previous #endif @@ -1176,10 +1146,15 @@ ENDPROC(vector_bhb_bpiall_\name) .endm .section .stubs, "ax", %progbits - @ This must be the first word + @ These need to remain at the start of the section so that + @ they are in range of the 'SWI' entries in the vector tables + @ located 4k down. +.L__vector_swi: .word vector_swi #ifdef CONFIG_HARDEN_BRANCH_HISTORY +.L__vector_bhb_loop8_swi: .word vector_bhb_loop8_swi +.L__vector_bhb_bpiall_swi: .word vector_bhb_bpiall_swi #endif @@ -1322,10 +1297,11 @@ vector_addrexcptn: .globl vector_fiq .section .vectors, "ax", %progbits -.L__vectors_start: W(b) vector_rst W(b) vector_und - W(ldr) pc, .L__vectors_start + 0x1000 +ARM( .reloc ., R_ARM_LDR_PC_G0, .L__vector_swi ) +THUMB( .reloc ., R_ARM_THM_PC12, .L__vector_swi ) + W(ldr) pc, . W(b) vector_pabt W(b) vector_dabt W(b) vector_addrexcptn @@ -1334,10 +1310,11 @@ vector_addrexcptn: #ifdef CONFIG_HARDEN_BRANCH_HISTORY .section .vectors.bhb.loop8, "ax", %progbits -.L__vectors_bhb_loop8_start: W(b) vector_rst W(b) vector_bhb_loop8_und - W(ldr) pc, .L__vectors_bhb_loop8_start + 0x1004 +ARM( .reloc ., R_ARM_LDR_PC_G0, .L__vector_bhb_loop8_swi ) +THUMB( .reloc ., R_ARM_THM_PC12, .L__vector_bhb_loop8_swi ) + W(ldr) pc, . W(b) vector_bhb_loop8_pabt W(b) vector_bhb_loop8_dabt W(b) vector_addrexcptn @@ -1345,10 +1322,11 @@ vector_addrexcptn: W(b) vector_bhb_loop8_fiq .section .vectors.bhb.bpiall, "ax", %progbits -.L__vectors_bhb_bpiall_start: W(b) vector_rst W(b) vector_bhb_bpiall_und - W(ldr) pc, .L__vectors_bhb_bpiall_start + 0x1008 +ARM( .reloc ., R_ARM_LDR_PC_G0, .L__vector_bhb_bpiall_swi ) +THUMB( .reloc ., R_ARM_THM_PC12, .L__vector_bhb_bpiall_swi ) + W(ldr) pc, . W(b) vector_bhb_bpiall_pabt W(b) vector_bhb_bpiall_dabt W(b) vector_addrexcptn diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S index 90d40f4d56cf..7aa3ded4af92 100644 --- a/arch/arm/kernel/entry-common.S +++ b/arch/arm/kernel/entry-common.S @@ -164,7 +164,7 @@ ENTRY(vector_bhb_loop8_swi) 1: b 2f 2: subs r8, r8, #1 bne 1b - dsb + dsb nsh isb b 3f ENDPROC(vector_bhb_loop8_swi) @@ -198,7 +198,7 @@ ENTRY(vector_swi) #endif reload_current r10, ip zero_fp - alignment_trap r10, ip, __cr_alignment + alignment_trap r10, ip, cr_alignment asm_trace_hardirqs_on save=0 enable_irq_notrace ct_user_exit save=0 @@ -328,14 +328,6 @@ __sys_trace_return: bl syscall_trace_exit b ret_slow_syscall - .align 5 -#ifdef CONFIG_ALIGNMENT_TRAP - .type __cr_alignment, #object -__cr_alignment: - .word cr_alignment -#endif - .ltorg - .macro syscall_table_start, sym .equ __sys_nr, 0 .type \sym, #object diff --git a/arch/arm/kernel/entry-header.S b/arch/arm/kernel/entry-header.S index 9a1dc142f782..5865621bf691 100644 --- a/arch/arm/kernel/entry-header.S +++ b/arch/arm/kernel/entry-header.S @@ -48,8 +48,7 @@ .macro alignment_trap, rtmp1, rtmp2, label #ifdef CONFIG_ALIGNMENT_TRAP mrc p15, 0, \rtmp2, c1, c0, 0 - ldr \rtmp1, \label - ldr \rtmp1, [\rtmp1] + ldr_va \rtmp1, \label teq \rtmp1, \rtmp2 mcrne p15, 0, \rtmp1, c1, c0, 0 #endif diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c index b1423fb130ea..054e9199f30d 100644 --- a/arch/arm/kernel/hw_breakpoint.c +++ b/arch/arm/kernel/hw_breakpoint.c @@ -941,6 +941,23 @@ static int hw_breakpoint_pending(unsigned long addr, unsigned int fsr, return ret; } +#ifdef CONFIG_ARM_ERRATA_764319 +static int oslsr_fault; + +static int debug_oslsr_trap(struct pt_regs *regs, unsigned int instr) +{ + oslsr_fault = 1; + instruction_pointer(regs) += 4; + return 0; +} + +static struct undef_hook debug_oslsr_hook = { + .instr_mask = 0xffffffff, + .instr_val = 0xee115e91, + .fn = debug_oslsr_trap, +}; +#endif + /* * One-time initialisation. */ @@ -974,7 +991,16 @@ static bool core_has_os_save_restore(void) case ARM_DEBUG_ARCH_V7_1: return true; case ARM_DEBUG_ARCH_V7_ECP14: +#ifdef CONFIG_ARM_ERRATA_764319 + oslsr_fault = 0; + register_undef_hook(&debug_oslsr_hook); ARM_DBG_READ(c1, c1, 4, oslsr); + unregister_undef_hook(&debug_oslsr_hook); + if (oslsr_fault) + return false; +#else + ARM_DBG_READ(c1, c1, 4, oslsr); +#endif if (oslsr & ARM_OSLSR_OSLM0) return true; fallthrough; diff --git a/arch/arm/kernel/module.c b/arch/arm/kernel/module.c index 549abcedf795..d59c36dc0494 100644 --- a/arch/arm/kernel/module.c +++ b/arch/arm/kernel/module.c @@ -459,46 +459,40 @@ int module_finalize(const Elf32_Ehdr *hdr, const Elf_Shdr *sechdrs, #ifdef CONFIG_ARM_UNWIND const char *secstrs = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset; const Elf_Shdr *sechdrs_end = sechdrs + hdr->e_shnum; - struct mod_unwind_map maps[ARM_SEC_MAX]; - int i; + struct list_head *unwind_list = &mod->arch.unwind_list; - memset(maps, 0, sizeof(maps)); + INIT_LIST_HEAD(unwind_list); + mod->arch.init_table = NULL; for (s = sechdrs; s < sechdrs_end; s++) { const char *secname = secstrs + s->sh_name; + const char *txtname; + const Elf_Shdr *txt_sec; - if (!(s->sh_flags & SHF_ALLOC)) + if (!(s->sh_flags & SHF_ALLOC) || + s->sh_type != ELF_SECTION_UNWIND) continue; - if (strcmp(".ARM.exidx.init.text", secname) == 0) - maps[ARM_SEC_INIT].unw_sec = s; - else if (strcmp(".ARM.exidx", secname) == 0) - maps[ARM_SEC_CORE].unw_sec = s; - else if (strcmp(".ARM.exidx.exit.text", secname) == 0) - maps[ARM_SEC_EXIT].unw_sec = s; - else if (strcmp(".ARM.exidx.text.unlikely", secname) == 0) - maps[ARM_SEC_UNLIKELY].unw_sec = s; - else if (strcmp(".ARM.exidx.text.hot", secname) == 0) - maps[ARM_SEC_HOT].unw_sec = s; - else if (strcmp(".init.text", secname) == 0) - maps[ARM_SEC_INIT].txt_sec = s; - else if (strcmp(".text", secname) == 0) - maps[ARM_SEC_CORE].txt_sec = s; - else if (strcmp(".exit.text", secname) == 0) - maps[ARM_SEC_EXIT].txt_sec = s; - else if (strcmp(".text.unlikely", secname) == 0) - maps[ARM_SEC_UNLIKELY].txt_sec = s; - else if (strcmp(".text.hot", secname) == 0) - maps[ARM_SEC_HOT].txt_sec = s; - } + if (!strcmp(".ARM.exidx", secname)) + txtname = ".text"; + else + txtname = secname + strlen(".ARM.exidx"); + txt_sec = find_mod_section(hdr, sechdrs, txtname); + + if (txt_sec) { + struct unwind_table *table = + unwind_table_add(s->sh_addr, + s->sh_size, + txt_sec->sh_addr, + txt_sec->sh_size); - for (i = 0; i < ARM_SEC_MAX; i++) - if (maps[i].unw_sec && maps[i].txt_sec) - mod->arch.unwind[i] = - unwind_table_add(maps[i].unw_sec->sh_addr, - maps[i].unw_sec->sh_size, - maps[i].txt_sec->sh_addr, - maps[i].txt_sec->sh_size); + list_add(&table->mod_list, unwind_list); + + /* save init table for module_arch_freeing_init */ + if (strcmp(".ARM.exidx.init.text", secname) == 0) + mod->arch.init_table = table; + } + } #endif #ifdef CONFIG_ARM_PATCH_PHYS_VIRT s = find_mod_section(hdr, sechdrs, ".pv_table"); @@ -519,19 +513,27 @@ void module_arch_cleanup(struct module *mod) { #ifdef CONFIG_ARM_UNWIND - int i; + struct unwind_table *tmp; + struct unwind_table *n; - for (i = 0; i < ARM_SEC_MAX; i++) { - unwind_table_del(mod->arch.unwind[i]); - mod->arch.unwind[i] = NULL; + list_for_each_entry_safe(tmp, n, + &mod->arch.unwind_list, mod_list) { + list_del(&tmp->mod_list); + unwind_table_del(tmp); } + mod->arch.init_table = NULL; #endif } void __weak module_arch_freeing_init(struct module *mod) { #ifdef CONFIG_ARM_UNWIND - unwind_table_del(mod->arch.unwind[ARM_SEC_INIT]); - mod->arch.unwind[ARM_SEC_INIT] = NULL; + struct unwind_table *init = mod->arch.init_table; + + if (init) { + mod->arch.init_table = NULL; + list_del(&init->mod_list); + unwind_table_del(init); + } #endif } diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c index 459abc5d1819..ea128e32e8ca 100644 --- a/arch/arm/kernel/signal.c +++ b/arch/arm/kernel/signal.c @@ -708,6 +708,7 @@ static_assert(offsetof(siginfo_t, si_upper) == 0x18); static_assert(offsetof(siginfo_t, si_pkey) == 0x14); static_assert(offsetof(siginfo_t, si_perf_data) == 0x10); static_assert(offsetof(siginfo_t, si_perf_type) == 0x14); +static_assert(offsetof(siginfo_t, si_perf_flags) == 0x18); static_assert(offsetof(siginfo_t, si_band) == 0x0c); static_assert(offsetof(siginfo_t, si_fd) == 0x10); static_assert(offsetof(siginfo_t, si_call_addr) == 0x0c); diff --git a/arch/arm/mach-davinci/board-da850-evm.c b/arch/arm/mach-davinci/board-da850-evm.c index 428012687a80..7f7f6bae21c2 100644 --- a/arch/arm/mach-davinci/board-da850-evm.c +++ b/arch/arm/mach-davinci/board-da850-evm.c @@ -1101,11 +1101,13 @@ static int __init da850_evm_config_emac(void) int ret; u32 val; struct davinci_soc_info *soc_info = &davinci_soc_info; - u8 rmii_en = soc_info->emac_pdata->rmii_en; + u8 rmii_en; if (!machine_is_davinci_da850_evm()) return 0; + rmii_en = soc_info->emac_pdata->rmii_en; + cfg_chip3_base = DA8XX_SYSCFG0_VIRT(DA8XX_CFGCHIP3_REG); val = __raw_readl(cfg_chip3_base); diff --git a/arch/arm/mach-ep93xx/clock.c b/arch/arm/mach-ep93xx/clock.c index cc75087134d3..4fa6ea5461b7 100644 --- a/arch/arm/mach-ep93xx/clock.c +++ b/arch/arm/mach-ep93xx/clock.c @@ -148,8 +148,10 @@ static struct clk_hw *ep93xx_clk_register_gate(const char *name, psc->lock = &clk_lock; clk = clk_register(NULL, &psc->hw); - if (IS_ERR(clk)) + if (IS_ERR(clk)) { kfree(psc); + return ERR_CAST(clk); + } return &psc->hw; } @@ -207,7 +209,7 @@ static int ep93xx_mux_determine_rate(struct clk_hw *hw, struct clk_rate_request *req) { unsigned long rate = req->rate; - struct clk *best_parent = 0; + struct clk *best_parent = NULL; unsigned long __parent_rate; unsigned long best_rate = 0, actual_rate, mclk_rate; unsigned long best_parent_rate; diff --git a/arch/arm/mach-exynos/Kconfig b/arch/arm/mach-exynos/Kconfig index f7d993628cb7..a9c1efcf7c9c 100644 --- a/arch/arm/mach-exynos/Kconfig +++ b/arch/arm/mach-exynos/Kconfig @@ -17,7 +17,6 @@ menuconfig ARCH_EXYNOS select EXYNOS_PMU select EXYNOS_SROM select EXYNOS_PM_DOMAINS if PM_GENERIC_DOMAINS - select GPIOLIB select HAVE_ARM_ARCH_TIMER if ARCH_EXYNOS5 select HAVE_ARM_SCU if SMP select PINCTRL diff --git a/arch/arm/mach-iop32x/cp6.c b/arch/arm/mach-iop32x/cp6.c index 2882674a1c39..7135a0ac9949 100644 --- a/arch/arm/mach-iop32x/cp6.c +++ b/arch/arm/mach-iop32x/cp6.c @@ -7,6 +7,8 @@ #include <asm/traps.h> #include <asm/ptrace.h> +#include "iop3xx.h" + void iop_enable_cp6(void) { u32 temp; diff --git a/arch/arm/mach-omap2/omap4-common.c b/arch/arm/mach-omap2/omap4-common.c index 5c3845730dbf..0b80f8bcd304 100644 --- a/arch/arm/mach-omap2/omap4-common.c +++ b/arch/arm/mach-omap2/omap4-common.c @@ -314,10 +314,12 @@ void __init omap_gic_of_init(void) np = of_find_compatible_node(NULL, NULL, "arm,cortex-a9-gic"); gic_dist_base_addr = of_iomap(np, 0); + of_node_put(np); WARN_ON(!gic_dist_base_addr); np = of_find_compatible_node(NULL, NULL, "arm,cortex-a9-twd-timer"); twd_base = of_iomap(np, 0); + of_node_put(np); WARN_ON(!twd_base); skip_errata_init: diff --git a/arch/arm/mach-sunxi/Kconfig b/arch/arm/mach-sunxi/Kconfig index e5c2fce281cd..abdb99fe1e97 100644 --- a/arch/arm/mach-sunxi/Kconfig +++ b/arch/arm/mach-sunxi/Kconfig @@ -4,10 +4,7 @@ menuconfig ARCH_SUNXI depends on ARCH_MULTI_V5 || ARCH_MULTI_V7 select ARCH_HAS_RESET_CONTROLLER select CLKSRC_MMIO - select GENERIC_IRQ_CHIP select GPIOLIB - select IRQ_DOMAIN_HIERARCHY - select IRQ_FASTEOI_HIERARCHY_HANDLERS select PINCTRL select PM_OPP select SUN4I_TIMER @@ -22,10 +19,12 @@ if ARCH_MULTI_V7 config MACH_SUN4I bool "Allwinner A10 (sun4i) SoCs support" default ARCH_SUNXI + select SUN4I_INTC config MACH_SUN5I bool "Allwinner A10s / A13 (sun5i) SoCs support" default ARCH_SUNXI + select SUN4I_INTC select SUN5I_HSTIMER config MACH_SUN6I @@ -34,6 +33,8 @@ config MACH_SUN6I select ARM_GIC select MFD_SUN6I_PRCM select SUN5I_HSTIMER + select SUN6I_R_INTC + select SUNXI_NMI_INTC config MACH_SUN7I bool "Allwinner A20 (sun7i) SoCs support" @@ -43,17 +44,21 @@ config MACH_SUN7I select ARCH_SUPPORTS_BIG_ENDIAN select HAVE_ARM_ARCH_TIMER select SUN5I_HSTIMER + select SUNXI_NMI_INTC config MACH_SUN8I bool "Allwinner sun8i Family SoCs support" default ARCH_SUNXI select ARM_GIC select MFD_SUN6I_PRCM + select SUN6I_R_INTC + select SUNXI_NMI_INTC config MACH_SUN9I bool "Allwinner (sun9i) SoCs support" default ARCH_SUNXI select ARM_GIC + select SUNXI_NMI_INTC config ARCH_SUNXI_MC_SMP bool @@ -69,6 +74,7 @@ if ARCH_MULTI_V5 config MACH_SUNIV bool "Allwinner ARMv5 F-series (suniv) SoCs support" default ARCH_SUNXI + select SUN4I_INTC help Support for Allwinner suniv ARMv5 SoCs. (F1C100A, F1C100s, F1C200s, F1C500, F1C600) diff --git a/arch/arm/mach-vexpress/spc.c b/arch/arm/mach-vexpress/spc.c index 1da11bdb1dfb..6e6985e756af 100644 --- a/arch/arm/mach-vexpress/spc.c +++ b/arch/arm/mach-vexpress/spc.c @@ -122,13 +122,13 @@ static inline bool cluster_is_a15(u32 cluster) } /** - * ve_spc_global_wakeup_irq() + * ve_spc_global_wakeup_irq() - sets/clears global wakeup IRQs + * + * @set: if true, global wake-up IRQs are set, if false they are cleared * * Function to set/clear global wakeup IRQs. Not protected by locking since * it might be used in code paths where normal cacheable locks are not * working. Locking must be provided by the caller to ensure atomicity. - * - * @set: if true, global wake-up IRQs are set, if false they are cleared */ void ve_spc_global_wakeup_irq(bool set) { @@ -145,15 +145,15 @@ void ve_spc_global_wakeup_irq(bool set) } /** - * ve_spc_cpu_wakeup_irq() - * - * Function to set/clear per-CPU wake-up IRQs. Not protected by locking since - * it might be used in code paths where normal cacheable locks are not - * working. Locking must be provided by the caller to ensure atomicity. + * ve_spc_cpu_wakeup_irq() - sets/clears per-CPU wake-up IRQs * * @cluster: mpidr[15:8] bitfield describing cluster affinity level * @cpu: mpidr[7:0] bitfield describing cpu affinity level * @set: if true, wake-up IRQs are set, if false they are cleared + * + * Function to set/clear per-CPU wake-up IRQs. Not protected by locking since + * it might be used in code paths where normal cacheable locks are not + * working. Locking must be provided by the caller to ensure atomicity. */ void ve_spc_cpu_wakeup_irq(u32 cluster, u32 cpu, bool set) { @@ -200,14 +200,14 @@ void ve_spc_set_resume_addr(u32 cluster, u32 cpu, u32 addr) } /** - * ve_spc_powerdown() + * ve_spc_powerdown() - enables/disables cluster powerdown + * + * @cluster: mpidr[15:8] bitfield describing cluster affinity level + * @enable: if true enables powerdown, if false disables it * * Function to enable/disable cluster powerdown. Not protected by locking * since it might be used in code paths where normal cacheable locks are not * working. Locking must be provided by the caller to ensure atomicity. - * - * @cluster: mpidr[15:8] bitfield describing cluster affinity level - * @enable: if true enables powerdown, if false disables it */ void ve_spc_powerdown(u32 cluster, bool enable) { @@ -228,7 +228,7 @@ static u32 standbywfi_cpu_mask(u32 cpu, u32 cluster) } /** - * ve_spc_cpu_in_wfi(u32 cpu, u32 cluster) + * ve_spc_cpu_in_wfi() - Checks if the specified CPU is in WFI or not * * @cpu: mpidr[7:0] bitfield describing CPU affinity level within cluster * @cluster: mpidr[15:8] bitfield describing cluster affinity level @@ -580,7 +580,7 @@ static int __init ve_spc_clk_init(void) } cluster = topology_physical_package_id(cpu_dev->id); - if (init_opp_table[cluster]) + if (cluster < 0 || init_opp_table[cluster]) continue; if (ve_init_opp_table(cpu_dev)) diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c index aa08bcb72db9..290702328a33 100644 --- a/arch/arm/mm/ioremap.c +++ b/arch/arm/mm/ioremap.c @@ -493,3 +493,11 @@ void __init early_ioremap_init(void) { early_ioremap_setup(); } + +bool arch_memremap_can_ram_remap(resource_size_t offset, size_t size, + unsigned long flags) +{ + unsigned long pfn = PHYS_PFN(offset); + + return memblock_is_map_memory(pfn); +} diff --git a/arch/arm/mm/proc-v7-bugs.c b/arch/arm/mm/proc-v7-bugs.c index 06dbfb968182..fb9f3eb6bf48 100644 --- a/arch/arm/mm/proc-v7-bugs.c +++ b/arch/arm/mm/proc-v7-bugs.c @@ -288,6 +288,7 @@ void cpu_v7_ca15_ibe(void) { if (check_spectre_auxcr(this_cpu_ptr(&spectre_warned), BIT(0))) cpu_v7_spectre_v2_init(); + cpu_v7_spectre_bhb_init(); } void cpu_v7_bugs_init(void) diff --git a/arch/arm/vdso/Makefile b/arch/arm/vdso/Makefile index ec52b776f926..8ca1c9f262a2 100644 --- a/arch/arm/vdso/Makefile +++ b/arch/arm/vdso/Makefile @@ -28,7 +28,7 @@ CPPFLAGS_vdso.lds += -P -C -U$(ARCH) CFLAGS_REMOVE_vdso.o = -pg # Force -O2 to avoid libgcc dependencies -CFLAGS_REMOVE_vgettimeofday.o = -pg -Os $(GCC_PLUGINS_CFLAGS) +CFLAGS_REMOVE_vgettimeofday.o = -pg -Os $(RANDSTRUCT_CFLAGS) $(GCC_PLUGINS_CFLAGS) ifeq ($(c-gettimeofday-y),) CFLAGS_vgettimeofday.o = -O2 else diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c index ec5b082f3de6..07eb69f9e7df 100644 --- a/arch/arm/xen/enlighten.c +++ b/arch/arm/xen/enlighten.c @@ -337,12 +337,15 @@ int __init arch_xen_unpopulated_init(struct resource **res) if (!nr_reg) { pr_err("No extended regions are found\n"); + of_node_put(np); return -EINVAL; } regs = kcalloc(nr_reg, sizeof(*regs), GFP_KERNEL); - if (!regs) + if (!regs) { + of_node_put(np); return -ENOMEM; + } /* * Create resource from extended regions provided by the hypervisor to be @@ -403,8 +406,8 @@ int __init arch_xen_unpopulated_init(struct resource **res) *res = &xen_resource; err: + of_node_put(np); kfree(regs); - return rc; } #endif @@ -424,8 +427,10 @@ static void __init xen_dt_guest_init(void) if (of_address_to_resource(xen_node, GRANT_TABLE_INDEX, &res)) { pr_err("Xen grant table region is not found\n"); + of_node_put(xen_node); return; } + of_node_put(xen_node); xen_grant_frames = res.start; } diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 57c4c995965f..d550f5acfaf3 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -175,8 +175,6 @@ config ARM64 select HAVE_DEBUG_KMEMLEAK select HAVE_DMA_CONTIGUOUS select HAVE_DYNAMIC_FTRACE - select HAVE_DYNAMIC_FTRACE_WITH_REGS \ - if $(cc-option,-fpatchable-function-entry=2) select FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY \ if DYNAMIC_FTRACE_WITH_REGS select HAVE_EFFICIENT_UNALIGNED_ACCESS @@ -228,6 +226,17 @@ config ARM64 help ARM 64-bit (AArch64) Linux support. +config CLANG_SUPPORTS_DYNAMIC_FTRACE_WITH_REGS + def_bool CC_IS_CLANG + # https://github.com/ClangBuiltLinux/linux/issues/1507 + depends on AS_IS_GNU || (AS_IS_LLVM && (LD_IS_LLD || LD_VERSION >= 23600)) + select HAVE_DYNAMIC_FTRACE_WITH_REGS + +config GCC_SUPPORTS_DYNAMIC_FTRACE_WITH_REGS + def_bool CC_IS_GCC + depends on $(cc-option,-fpatchable-function-entry=2) + select HAVE_DYNAMIC_FTRACE_WITH_REGS + config 64BIT def_bool y @@ -253,31 +262,31 @@ config ARM64_CONT_PMD_SHIFT default 4 config ARCH_MMAP_RND_BITS_MIN - default 14 if ARM64_64K_PAGES - default 16 if ARM64_16K_PAGES - default 18 + default 14 if ARM64_64K_PAGES + default 16 if ARM64_16K_PAGES + default 18 # max bits determined by the following formula: # VA_BITS - PAGE_SHIFT - 3 config ARCH_MMAP_RND_BITS_MAX - default 19 if ARM64_VA_BITS=36 - default 24 if ARM64_VA_BITS=39 - default 27 if ARM64_VA_BITS=42 - default 30 if ARM64_VA_BITS=47 - default 29 if ARM64_VA_BITS=48 && ARM64_64K_PAGES - default 31 if ARM64_VA_BITS=48 && ARM64_16K_PAGES - default 33 if ARM64_VA_BITS=48 - default 14 if ARM64_64K_PAGES - default 16 if ARM64_16K_PAGES - default 18 + default 19 if ARM64_VA_BITS=36 + default 24 if ARM64_VA_BITS=39 + default 27 if ARM64_VA_BITS=42 + default 30 if ARM64_VA_BITS=47 + default 29 if ARM64_VA_BITS=48 && ARM64_64K_PAGES + default 31 if ARM64_VA_BITS=48 && ARM64_16K_PAGES + default 33 if ARM64_VA_BITS=48 + default 14 if ARM64_64K_PAGES + default 16 if ARM64_16K_PAGES + default 18 config ARCH_MMAP_RND_COMPAT_BITS_MIN - default 7 if ARM64_64K_PAGES - default 9 if ARM64_16K_PAGES - default 11 + default 7 if ARM64_64K_PAGES + default 9 if ARM64_16K_PAGES + default 11 config ARCH_MMAP_RND_COMPAT_BITS_MAX - default 16 + default 16 config NO_IOPORT_MAP def_bool y if !PCI @@ -304,7 +313,7 @@ config GENERIC_HWEIGHT def_bool y config GENERIC_CSUM - def_bool y + def_bool y config GENERIC_CALIBRATE_DELAY def_bool y @@ -678,7 +687,7 @@ config ARM64_ERRATUM_2051678 default y help This options adds the workaround for ARM Cortex-A510 erratum ARM64_ERRATUM_2051678. - Affected Coretex-A510 might not respect the ordering rules for + Affected Cortex-A510 might not respect the ordering rules for hardware update of the page table's dirty bit. The workaround is to not enable the feature on affected CPUs. @@ -1037,8 +1046,7 @@ config SOCIONEXT_SYNQUACER_PREITS If unsure, say Y. -endmenu - +endmenu # "ARM errata workarounds via the alternatives framework" choice prompt "Page size" @@ -1566,9 +1574,9 @@ config SETEND_EMULATION be unexpected results in the applications. If unsure, say Y -endif +endif # ARMV8_DEPRECATED -endif +endif # COMPAT menu "ARMv8.1 architectural features" @@ -1593,15 +1601,15 @@ config ARM64_PAN bool "Enable support for Privileged Access Never (PAN)" default y help - Privileged Access Never (PAN; part of the ARMv8.1 Extensions) - prevents the kernel or hypervisor from accessing user-space (EL0) - memory directly. + Privileged Access Never (PAN; part of the ARMv8.1 Extensions) + prevents the kernel or hypervisor from accessing user-space (EL0) + memory directly. - Choosing this option will cause any unprotected (not using - copy_to_user et al) memory access to fail with a permission fault. + Choosing this option will cause any unprotected (not using + copy_to_user et al) memory access to fail with a permission fault. - The feature is detected at runtime, and will remain as a 'nop' - instruction if the cpu does not implement the feature. + The feature is detected at runtime, and will remain as a 'nop' + instruction if the cpu does not implement the feature. config AS_HAS_LDAPR def_bool $(as-instr,.arch_extension rcpc) @@ -1629,15 +1637,15 @@ config ARM64_USE_LSE_ATOMICS built with binutils >= 2.25 in order for the new instructions to be used. -endmenu +endmenu # "ARMv8.1 architectural features" menu "ARMv8.2 architectural features" config AS_HAS_ARMV8_2 - def_bool $(cc-option,-Wa$(comma)-march=armv8.2-a) + def_bool $(cc-option,-Wa$(comma)-march=armv8.2-a) config AS_HAS_SHA3 - def_bool $(as-instr,.arch armv8.2-a+sha3) + def_bool $(as-instr,.arch armv8.2-a+sha3) config ARM64_PMEM bool "Enable support for persistent memory" @@ -1681,7 +1689,7 @@ config ARM64_CNP at runtime, and does not affect PEs that do not implement this feature. -endmenu +endmenu # "ARMv8.2 architectural features" menu "ARMv8.3 architectural features" @@ -1744,7 +1752,7 @@ config AS_HAS_PAC config AS_HAS_CFI_NEGATE_RA_STATE def_bool $(as-instr,.cfi_startproc\n.cfi_negate_ra_state\n.cfi_endproc\n) -endmenu +endmenu # "ARMv8.3 architectural features" menu "ARMv8.4 architectural features" @@ -1785,7 +1793,7 @@ config ARM64_TLB_RANGE The feature introduces new assembly instructions, and they were support when binutils >= 2.30. -endmenu +endmenu # "ARMv8.4 architectural features" menu "ARMv8.5 architectural features" @@ -1871,6 +1879,7 @@ config ARM64_MTE depends on AS_HAS_LSE_ATOMICS # Required for tag checking in the uaccess routines depends on ARM64_PAN + select ARCH_HAS_SUBPAGE_FAULTS select ARCH_USES_HIGH_VMA_FLAGS help Memory Tagging (part of the ARMv8.5 Extensions) provides @@ -1892,7 +1901,7 @@ config ARM64_MTE Documentation/arm64/memory-tagging-extension.rst. -endmenu +endmenu # "ARMv8.5 architectural features" menu "ARMv8.7 architectural features" @@ -1901,12 +1910,12 @@ config ARM64_EPAN default y depends on ARM64_PAN help - Enhanced Privileged Access Never (EPAN) allows Privileged - Access Never to be used with Execute-only mappings. + Enhanced Privileged Access Never (EPAN) allows Privileged + Access Never to be used with Execute-only mappings. - The feature is detected at runtime, and will remain disabled - if the cpu does not implement the feature. -endmenu + The feature is detected at runtime, and will remain disabled + if the cpu does not implement the feature. +endmenu # "ARMv8.7 architectural features" config ARM64_SVE bool "ARM Scalable Vector Extension support" @@ -1939,6 +1948,17 @@ config ARM64_SVE booting the kernel. If unsure and you are not observing these symptoms, you should assume that it is safe to say Y. +config ARM64_SME + bool "ARM Scalable Matrix Extension support" + default y + depends on ARM64_SVE + help + The Scalable Matrix Extension (SME) is an extension to the AArch64 + execution state which utilises a substantial subset of the SVE + instruction set, together with the addition of new architectural + register state capable of holding two dimensional matrix tiles to + enable various matrix operations. + config ARM64_MODULE_PLTS bool "Use PLTs to allow module memory to spill over into vmalloc area" depends on MODULES @@ -1982,7 +2002,7 @@ config ARM64_DEBUG_PRIORITY_MASKING the validity of ICC_PMR_EL1 when calling concerned functions. If unsure, say N -endif +endif # ARM64_PSEUDO_NMI config RELOCATABLE bool "Build a relocatable kernel image" if EXPERT @@ -2041,7 +2061,19 @@ config STACKPROTECTOR_PER_TASK def_bool y depends on STACKPROTECTOR && CC_HAVE_STACKPROTECTOR_SYSREG -endmenu +# The GPIO number here must be sorted by descending number. In case of +# a multiplatform kernel, we just want the highest value required by the +# selected platforms. +config ARCH_NR_GPIO + int + default 2048 if ARCH_APPLE + default 0 + help + Maximum number of GPIOs in the system. + + If unsure, leave the default value. + +endmenu # "Kernel Features" menu "Boot options" @@ -2105,7 +2137,7 @@ config EFI help This option provides support for runtime services provided by UEFI firmware (such as non-volatile variables, realtime - clock, and platform reset). A UEFI stub is also provided to + clock, and platform reset). A UEFI stub is also provided to allow the kernel to be booted as an EFI application. This is only useful on systems that have UEFI firmware. @@ -2120,7 +2152,7 @@ config DMI However, even with this option, the resultant kernel should continue to boot on existing non-UEFI platforms. -endmenu +endmenu # "Boot options" config SYSVIPC_COMPAT def_bool y @@ -2141,7 +2173,7 @@ config ARCH_HIBERNATION_HEADER config ARCH_SUSPEND_POSSIBLE def_bool y -endmenu +endmenu # "Power management options" menu "CPU Power Management" @@ -2149,7 +2181,7 @@ source "drivers/cpuidle/Kconfig" source "drivers/cpufreq/Kconfig" -endmenu +endmenu # "CPU Power Management" source "drivers/acpi/Kconfig" @@ -2157,4 +2189,4 @@ source "arch/arm64/kvm/Kconfig" if CRYPTO source "arch/arm64/crypto/Kconfig" -endif +endif # CRYPTO diff --git a/arch/arm64/Kconfig.platforms b/arch/arm64/Kconfig.platforms index 30b123cde02c..4e6d635a1731 100644 --- a/arch/arm64/Kconfig.platforms +++ b/arch/arm64/Kconfig.platforms @@ -11,12 +11,11 @@ config ARCH_ACTIONS config ARCH_SUNXI bool "Allwinner sunxi 64-bit SoC Family" select ARCH_HAS_RESET_CONTROLLER - select GENERIC_IRQ_CHIP - select IRQ_DOMAIN_HIERARCHY - select IRQ_FASTEOI_HIERARCHY_HANDLERS select PINCTRL select RESET_CONTROLLER select SUN4I_TIMER + select SUN6I_R_INTC + select SUNXI_NMI_INTC help This enables support for Allwinner sunxi based SoCs like the A64. @@ -253,6 +252,7 @@ config ARCH_INTEL_SOCFPGA config ARCH_SYNQUACER bool "Socionext SynQuacer SoC Family" + select IRQ_FASTEOI_HIERARCHY_HANDLERS config ARCH_TEGRA bool "NVIDIA Tegra SoC Family" @@ -325,4 +325,4 @@ config ARCH_ZYNQMP help This enables support for Xilinx ZynqMP Family -endmenu +endmenu # "Platform selection" diff --git a/arch/arm64/boot/dts/amlogic/meson-g12b-a311d.dtsi b/arch/arm64/boot/dts/amlogic/meson-g12b-a311d.dtsi index d61f43052a34..8e9ad1e51d66 100644 --- a/arch/arm64/boot/dts/amlogic/meson-g12b-a311d.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-g12b-a311d.dtsi @@ -11,26 +11,6 @@ compatible = "operating-points-v2"; opp-shared; - opp-100000000 { - opp-hz = /bits/ 64 <100000000>; - opp-microvolt = <731000>; - }; - - opp-250000000 { - opp-hz = /bits/ 64 <250000000>; - opp-microvolt = <731000>; - }; - - opp-500000000 { - opp-hz = /bits/ 64 <500000000>; - opp-microvolt = <731000>; - }; - - opp-667000000 { - opp-hz = /bits/ 64 <667000000>; - opp-microvolt = <731000>; - }; - opp-1000000000 { opp-hz = /bits/ 64 <1000000000>; opp-microvolt = <761000>; @@ -71,26 +51,6 @@ compatible = "operating-points-v2"; opp-shared; - opp-100000000 { - opp-hz = /bits/ 64 <100000000>; - opp-microvolt = <731000>; - }; - - opp-250000000 { - opp-hz = /bits/ 64 <250000000>; - opp-microvolt = <731000>; - }; - - opp-500000000 { - opp-hz = /bits/ 64 <500000000>; - opp-microvolt = <731000>; - }; - - opp-667000000 { - opp-hz = /bits/ 64 <667000000>; - opp-microvolt = <731000>; - }; - opp-1000000000 { opp-hz = /bits/ 64 <1000000000>; opp-microvolt = <731000>; diff --git a/arch/arm64/boot/dts/amlogic/meson-g12b-s922x.dtsi b/arch/arm64/boot/dts/amlogic/meson-g12b-s922x.dtsi index 1e5d0ee5d541..44c23c984034 100644 --- a/arch/arm64/boot/dts/amlogic/meson-g12b-s922x.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-g12b-s922x.dtsi @@ -11,26 +11,6 @@ compatible = "operating-points-v2"; opp-shared; - opp-100000000 { - opp-hz = /bits/ 64 <100000000>; - opp-microvolt = <731000>; - }; - - opp-250000000 { - opp-hz = /bits/ 64 <250000000>; - opp-microvolt = <731000>; - }; - - opp-500000000 { - opp-hz = /bits/ 64 <500000000>; - opp-microvolt = <731000>; - }; - - opp-667000000 { - opp-hz = /bits/ 64 <667000000>; - opp-microvolt = <731000>; - }; - opp-1000000000 { opp-hz = /bits/ 64 <1000000000>; opp-microvolt = <731000>; @@ -76,26 +56,6 @@ compatible = "operating-points-v2"; opp-shared; - opp-100000000 { - opp-hz = /bits/ 64 <100000000>; - opp-microvolt = <751000>; - }; - - opp-250000000 { - opp-hz = /bits/ 64 <250000000>; - opp-microvolt = <751000>; - }; - - opp-500000000 { - opp-hz = /bits/ 64 <500000000>; - opp-microvolt = <751000>; - }; - - opp-667000000 { - opp-hz = /bits/ 64 <667000000>; - opp-microvolt = <751000>; - }; - opp-1000000000 { opp-hz = /bits/ 64 <1000000000>; opp-microvolt = <771000>; diff --git a/arch/arm64/boot/dts/amlogic/meson-s4.dtsi b/arch/arm64/boot/dts/amlogic/meson-s4.dtsi index bf9ae1e1016b..480afa2cc61f 100644 --- a/arch/arm64/boot/dts/amlogic/meson-s4.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-s4.dtsi @@ -13,28 +13,28 @@ cpu0: cpu@0 { device_type = "cpu"; - compatible = "arm,cortex-a35","arm,armv8"; + compatible = "arm,cortex-a35"; reg = <0x0 0x0>; enable-method = "psci"; }; cpu1: cpu@1 { device_type = "cpu"; - compatible = "arm,cortex-a35","arm,armv8"; + compatible = "arm,cortex-a35"; reg = <0x0 0x1>; enable-method = "psci"; }; cpu2: cpu@2 { device_type = "cpu"; - compatible = "arm,cortex-a35","arm,armv8"; + compatible = "arm,cortex-a35"; reg = <0x0 0x2>; enable-method = "psci"; }; cpu3: cpu@3 { device_type = "cpu"; - compatible = "arm,cortex-a35","arm,armv8"; + compatible = "arm,cortex-a35"; reg = <0x0 0x3>; enable-method = "psci"; }; diff --git a/arch/arm64/boot/dts/amlogic/meson-sm1-bananapi-m5.dts b/arch/arm64/boot/dts/amlogic/meson-sm1-bananapi-m5.dts index 5751c48620ed..cadba194b149 100644 --- a/arch/arm64/boot/dts/amlogic/meson-sm1-bananapi-m5.dts +++ b/arch/arm64/boot/dts/amlogic/meson-sm1-bananapi-m5.dts @@ -437,6 +437,7 @@ "", "eMMC_RST#", /* BOOT_12 */ "eMMC_DS", /* BOOT_13 */ + "", "", /* GPIOC */ "SD_D0_B", /* GPIOC_0 */ "SD_D1_B", /* GPIOC_1 */ diff --git a/arch/arm64/boot/dts/amlogic/meson-sm1.dtsi b/arch/arm64/boot/dts/amlogic/meson-sm1.dtsi index 3c07a89bfd27..80737731af3f 100644 --- a/arch/arm64/boot/dts/amlogic/meson-sm1.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-sm1.dtsi @@ -95,26 +95,6 @@ compatible = "operating-points-v2"; opp-shared; - opp-100000000 { - opp-hz = /bits/ 64 <100000000>; - opp-microvolt = <730000>; - }; - - opp-250000000 { - opp-hz = /bits/ 64 <250000000>; - opp-microvolt = <730000>; - }; - - opp-500000000 { - opp-hz = /bits/ 64 <500000000>; - opp-microvolt = <730000>; - }; - - opp-667000000 { - opp-hz = /bits/ 64 <666666666>; - opp-microvolt = <750000>; - }; - opp-1000000000 { opp-hz = /bits/ 64 <1000000000>; opp-microvolt = <770000>; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-var-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-var-som.dtsi index 1dc9d187601c..a0bd540f27d3 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-var-som.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-var-som.dtsi @@ -89,12 +89,12 @@ pendown-gpio = <&gpio1 3 GPIO_ACTIVE_LOW>; ti,x-min = /bits/ 16 <125>; - touchscreen-size-x = /bits/ 16 <4008>; + touchscreen-size-x = <4008>; ti,y-min = /bits/ 16 <282>; - touchscreen-size-y = /bits/ 16 <3864>; + touchscreen-size-y = <3864>; ti,x-plate-ohms = /bits/ 16 <180>; - touchscreen-max-pressure = /bits/ 16 <255>; - touchscreen-average-samples = /bits/ 16 <10>; + touchscreen-max-pressure = <255>; + touchscreen-average-samples = <10>; ti,debounce-tol = /bits/ 16 <3>; ti,debounce-rep = /bits/ 16 <1>; ti,settle-delay-usec = /bits/ 16 <150>; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw71xx.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw71xx.dtsi index 73addc0b8e57..cce55c3c5df0 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw71xx.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw71xx.dtsi @@ -146,12 +146,14 @@ &usbotg1 { dr_mode = "otg"; + over-current-active-low; vbus-supply = <®_usb_otg1_vbus>; status = "okay"; }; &usbotg2 { dr_mode = "host"; + disable-over-current; status = "okay"; }; @@ -215,7 +217,7 @@ fsl,pins = < MX8MM_IOMUXC_ECSPI2_SCLK_ECSPI2_SCLK 0xd6 MX8MM_IOMUXC_ECSPI2_MOSI_ECSPI2_MOSI 0xd6 - MX8MM_IOMUXC_ECSPI2_SCLK_ECSPI2_SCLK 0xd6 + MX8MM_IOMUXC_ECSPI2_MISO_ECSPI2_MISO 0xd6 MX8MM_IOMUXC_ECSPI2_SS0_GPIO5_IO13 0xd6 >; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw72xx.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw72xx.dtsi index 1e7badb2a82e..f61e4847fa49 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw72xx.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw72xx.dtsi @@ -211,12 +211,14 @@ &usbotg1 { dr_mode = "otg"; + over-current-active-low; vbus-supply = <®_usb_otg1_vbus>; status = "okay"; }; &usbotg2 { dr_mode = "host"; + disable-over-current; vbus-supply = <®_usb_otg2_vbus>; status = "okay"; }; @@ -309,7 +311,7 @@ fsl,pins = < MX8MM_IOMUXC_ECSPI2_SCLK_ECSPI2_SCLK 0xd6 MX8MM_IOMUXC_ECSPI2_MOSI_ECSPI2_MOSI 0xd6 - MX8MM_IOMUXC_ECSPI2_SCLK_ECSPI2_SCLK 0xd6 + MX8MM_IOMUXC_ECSPI2_MISO_ECSPI2_MISO 0xd6 MX8MM_IOMUXC_ECSPI2_SS0_GPIO5_IO13 0xd6 >; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw73xx.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw73xx.dtsi index 426483ec1f88..023619648966 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw73xx.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw73xx.dtsi @@ -238,12 +238,14 @@ &usbotg1 { dr_mode = "otg"; + over-current-active-low; vbus-supply = <®_usb_otg1_vbus>; status = "okay"; }; &usbotg2 { dr_mode = "host"; + disable-over-current; vbus-supply = <®_usb_otg2_vbus>; status = "okay"; }; @@ -358,7 +360,7 @@ fsl,pins = < MX8MM_IOMUXC_ECSPI2_SCLK_ECSPI2_SCLK 0xd6 MX8MM_IOMUXC_ECSPI2_MOSI_ECSPI2_MOSI 0xd6 - MX8MM_IOMUXC_ECSPI2_SCLK_ECSPI2_SCLK 0xd6 + MX8MM_IOMUXC_ECSPI2_MISO_ECSPI2_MISO 0xd6 MX8MM_IOMUXC_ECSPI2_SS0_GPIO5_IO13 0xd6 >; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mn-ddr4-evk.dts b/arch/arm64/boot/dts/freescale/imx8mn-ddr4-evk.dts index 7dfee715a2c4..d8ce217c6016 100644 --- a/arch/arm64/boot/dts/freescale/imx8mn-ddr4-evk.dts +++ b/arch/arm64/boot/dts/freescale/imx8mn-ddr4-evk.dts @@ -59,6 +59,10 @@ interrupts = <3 IRQ_TYPE_LEVEL_LOW>; rohm,reset-snvs-powered; + #clock-cells = <0>; + clocks = <&osc_32k 0>; + clock-output-names = "clk-32k-out"; + regulators { buck1_reg: BUCK1 { regulator-name = "buck1"; diff --git a/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi index b16c7caf34c1..87b5e23c766f 100644 --- a/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi @@ -70,12 +70,12 @@ pendown-gpio = <&gpio1 3 GPIO_ACTIVE_LOW>; ti,x-min = /bits/ 16 <125>; - touchscreen-size-x = /bits/ 16 <4008>; + touchscreen-size-x = <4008>; ti,y-min = /bits/ 16 <282>; - touchscreen-size-y = /bits/ 16 <3864>; + touchscreen-size-y = <3864>; ti,x-plate-ohms = /bits/ 16 <180>; - touchscreen-max-pressure = /bits/ 16 <255>; - touchscreen-average-samples = /bits/ 16 <10>; + touchscreen-max-pressure = <255>; + touchscreen-average-samples = <10>; ti,debounce-tol = /bits/ 16 <3>; ti,debounce-rep = /bits/ 16 <1>; ti,settle-delay-usec = /bits/ 16 <150>; diff --git a/arch/arm64/boot/dts/freescale/imx8mn.dtsi b/arch/arm64/boot/dts/freescale/imx8mn.dtsi index 99f0f5026674..5c0ca2490561 100644 --- a/arch/arm64/boot/dts/freescale/imx8mn.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mn.dtsi @@ -293,7 +293,7 @@ ranges; sai2: sai@30020000 { - compatible = "fsl,imx8mm-sai", "fsl,imx8mq-sai"; + compatible = "fsl,imx8mn-sai", "fsl,imx8mq-sai"; reg = <0x30020000 0x10000>; interrupts = <GIC_SPI 96 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clk IMX8MN_CLK_SAI2_IPG>, @@ -307,7 +307,7 @@ }; sai3: sai@30030000 { - compatible = "fsl,imx8mm-sai", "fsl,imx8mq-sai"; + compatible = "fsl,imx8mn-sai", "fsl,imx8mq-sai"; reg = <0x30030000 0x10000>; interrupts = <GIC_SPI 50 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clk IMX8MN_CLK_SAI3_IPG>, @@ -321,7 +321,7 @@ }; sai5: sai@30050000 { - compatible = "fsl,imx8mm-sai", "fsl,imx8mq-sai"; + compatible = "fsl,imx8mn-sai", "fsl,imx8mq-sai"; reg = <0x30050000 0x10000>; interrupts = <GIC_SPI 90 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clk IMX8MN_CLK_SAI5_IPG>, @@ -337,7 +337,7 @@ }; sai6: sai@30060000 { - compatible = "fsl,imx8mm-sai", "fsl,imx8mq-sai"; + compatible = "fsl,imx8mn-sai", "fsl,imx8mq-sai"; reg = <0x30060000 0x10000>; interrupts = <GIC_SPI 90 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clk IMX8MN_CLK_SAI6_IPG>, @@ -394,7 +394,7 @@ }; sai7: sai@300b0000 { - compatible = "fsl,imx8mm-sai", "fsl,imx8mq-sai"; + compatible = "fsl,imx8mn-sai", "fsl,imx8mq-sai"; reg = <0x300b0000 0x10000>; interrupts = <GIC_SPI 111 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clk IMX8MN_CLK_SAI7_IPG>, diff --git a/arch/arm64/boot/dts/freescale/imx8mq-tqma8mq.dtsi b/arch/arm64/boot/dts/freescale/imx8mq-tqma8mq.dtsi index 38ffcd145b33..899e8e7dbc24 100644 --- a/arch/arm64/boot/dts/freescale/imx8mq-tqma8mq.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mq-tqma8mq.dtsi @@ -253,7 +253,7 @@ #address-cells = <1>; #size-cells = <1>; spi-max-frequency = <84000000>; - spi-tx-bus-width = <4>; + spi-tx-bus-width = <1>; spi-rx-bus-width = <4>; }; }; diff --git a/arch/arm64/boot/dts/freescale/imx8qm.dtsi b/arch/arm64/boot/dts/freescale/imx8qm.dtsi index be8c76a0554c..4f767012f1f5 100644 --- a/arch/arm64/boot/dts/freescale/imx8qm.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8qm.dtsi @@ -196,7 +196,7 @@ }; clk: clock-controller { - compatible = "fsl,imx8qxp-clk", "fsl,scu-clk"; + compatible = "fsl,imx8qm-clk", "fsl,scu-clk"; #clock-cells = <2>; }; diff --git a/arch/arm64/boot/dts/qcom/msm8996.dtsi b/arch/arm64/boot/dts/qcom/msm8996.dtsi index f0f81c23c16f..b9a48cfd760f 100644 --- a/arch/arm64/boot/dts/qcom/msm8996.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8996.dtsi @@ -1249,14 +1249,14 @@ pins = "gpio47", "gpio48"; function = "blsp_i2c3"; drive-strength = <16>; - bias-disable = <0>; + bias-disable; }; blsp1_i2c3_sleep: blsp1-i2c2-sleep { pins = "gpio47", "gpio48"; function = "gpio"; drive-strength = <2>; - bias-disable = <0>; + bias-disable; }; blsp2_uart3_4pins_default: blsp2-uart2-4pins { diff --git a/arch/arm64/boot/dts/qcom/sc7180-trogdor-pompom.dtsi b/arch/arm64/boot/dts/qcom/sc7180-trogdor-pompom.dtsi index e90f99ef5323..e47c74e513af 100644 --- a/arch/arm64/boot/dts/qcom/sc7180-trogdor-pompom.dtsi +++ b/arch/arm64/boot/dts/qcom/sc7180-trogdor-pompom.dtsi @@ -33,7 +33,7 @@ ap_h1_spi: &spi0 {}; }; &alc5682 { - realtek,dmic-clk-driving-high = "true"; + realtek,dmic-clk-driving-high; }; &cpu6_alert0 { diff --git a/arch/arm64/boot/dts/qcom/sdm845-oneplus-common.dtsi b/arch/arm64/boot/dts/qcom/sdm845-oneplus-common.dtsi index 1084d5ce9ac7..07b729f9fec5 100644 --- a/arch/arm64/boot/dts/qcom/sdm845-oneplus-common.dtsi +++ b/arch/arm64/boot/dts/qcom/sdm845-oneplus-common.dtsi @@ -630,7 +630,7 @@ pins = "gpio6", "gpio25", "gpio26"; function = "gpio"; drive-strength = <8>; - bias-disable = <0>; + bias-disable; }; }; diff --git a/arch/arm64/boot/dts/qcom/sdm845-shift-axolotl.dts b/arch/arm64/boot/dts/qcom/sdm845-shift-axolotl.dts index 8553c8bf79bd..103cc40816fd 100644 --- a/arch/arm64/boot/dts/qcom/sdm845-shift-axolotl.dts +++ b/arch/arm64/boot/dts/qcom/sdm845-shift-axolotl.dts @@ -563,7 +563,7 @@ config { pins = "gpio6", "gpio11"; drive-strength = <8>; - bias-disable = <0>; + bias-disable; }; }; diff --git a/arch/arm64/boot/dts/qcom/sm8250-mtp.dts b/arch/arm64/boot/dts/qcom/sm8250-mtp.dts index fb99cc2827c7..7ab3627cc347 100644 --- a/arch/arm64/boot/dts/qcom/sm8250-mtp.dts +++ b/arch/arm64/boot/dts/qcom/sm8250-mtp.dts @@ -622,6 +622,10 @@ status = "okay"; }; +&rxmacro { + status = "okay"; +}; + &slpi { status = "okay"; firmware-name = "qcom/sm8250/slpi.mbn"; @@ -773,6 +777,8 @@ }; &swr1 { + status = "okay"; + wcd_rx: wcd9380-rx@0,4 { compatible = "sdw20217010d00"; reg = <0 4>; @@ -781,6 +787,8 @@ }; &swr2 { + status = "okay"; + wcd_tx: wcd9380-tx@0,3 { compatible = "sdw20217010d00"; reg = <0 3>; @@ -819,6 +827,10 @@ }; }; +&txmacro { + status = "okay"; +}; + &uart12 { status = "okay"; }; diff --git a/arch/arm64/boot/dts/qcom/sm8250.dtsi b/arch/arm64/boot/dts/qcom/sm8250.dtsi index af8f22636436..1304b86af1a0 100644 --- a/arch/arm64/boot/dts/qcom/sm8250.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8250.dtsi @@ -2255,6 +2255,7 @@ pinctrl-0 = <&rx_swr_active>; compatible = "qcom,sm8250-lpass-rx-macro"; reg = <0 0x3200000 0 0x1000>; + status = "disabled"; clocks = <&q6afecc LPASS_CLK_ID_TX_CORE_MCLK LPASS_CLK_ATTRIBUTE_COUPLE_NO>, <&q6afecc LPASS_CLK_ID_TX_CORE_NPL_MCLK LPASS_CLK_ATTRIBUTE_COUPLE_NO>, @@ -2273,6 +2274,7 @@ swr1: soundwire-controller@3210000 { reg = <0 0x3210000 0 0x2000>; compatible = "qcom,soundwire-v1.5.1"; + status = "disabled"; interrupts = <GIC_SPI 298 IRQ_TYPE_LEVEL_HIGH>; clocks = <&rxmacro>; clock-names = "iface"; @@ -2300,6 +2302,7 @@ pinctrl-0 = <&tx_swr_active>; compatible = "qcom,sm8250-lpass-tx-macro"; reg = <0 0x3220000 0 0x1000>; + status = "disabled"; clocks = <&q6afecc LPASS_CLK_ID_TX_CORE_MCLK LPASS_CLK_ATTRIBUTE_COUPLE_NO>, <&q6afecc LPASS_CLK_ID_TX_CORE_NPL_MCLK LPASS_CLK_ATTRIBUTE_COUPLE_NO>, @@ -2323,6 +2326,7 @@ compatible = "qcom,soundwire-v1.5.1"; interrupts-extended = <&intc GIC_SPI 297 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "core"; + status = "disabled"; clocks = <&txmacro>; clock-names = "iface"; diff --git a/arch/arm64/boot/dts/rockchip/rk3568-bpi-r2-pro.dts b/arch/arm64/boot/dts/rockchip/rk3568-bpi-r2-pro.dts index a01886b467ed..067fe4a6b178 100644 --- a/arch/arm64/boot/dts/rockchip/rk3568-bpi-r2-pro.dts +++ b/arch/arm64/boot/dts/rockchip/rk3568-bpi-r2-pro.dts @@ -16,6 +16,7 @@ aliases { ethernet0 = &gmac0; + ethernet1 = &gmac1; mmc0 = &sdmmc0; mmc1 = &sdhci; }; @@ -78,7 +79,6 @@ assigned-clocks = <&cru SCLK_GMAC0_RX_TX>, <&cru SCLK_GMAC0>; assigned-clock-parents = <&cru SCLK_GMAC0_RGMII_SPEED>, <&cru CLK_MAC0_2TOP>; clock_in_out = "input"; - phy-handle = <&rgmii_phy0>; phy-mode = "rgmii"; pinctrl-names = "default"; pinctrl-0 = <&gmac0_miim @@ -90,8 +90,38 @@ snps,reset-active-low; /* Reset time is 20ms, 100ms for rtl8211f */ snps,reset-delays-us = <0 20000 100000>; + tx_delay = <0x4f>; + rx_delay = <0x0f>; + status = "okay"; + + fixed-link { + speed = <1000>; + full-duplex; + pause; + }; +}; + +&gmac1 { + assigned-clocks = <&cru SCLK_GMAC1_RX_TX>, <&cru SCLK_GMAC1>; + assigned-clock-parents = <&cru SCLK_GMAC1_RGMII_SPEED>, <&cru CLK_MAC1_2TOP>; + clock_in_out = "output"; + phy-handle = <&rgmii_phy1>; + phy-mode = "rgmii"; + pinctrl-names = "default"; + pinctrl-0 = <&gmac1m1_miim + &gmac1m1_tx_bus2 + &gmac1m1_rx_bus2 + &gmac1m1_rgmii_clk + &gmac1m1_rgmii_bus>; + + snps,reset-gpio = <&gpio3 RK_PB0 GPIO_ACTIVE_LOW>; + snps,reset-active-low; + /* Reset time is 20ms, 100ms for rtl8211f */ + snps,reset-delays-us = <0 20000 100000>; + tx_delay = <0x3c>; rx_delay = <0x2f>; + status = "okay"; }; @@ -315,8 +345,8 @@ status = "disabled"; }; -&mdio0 { - rgmii_phy0: ethernet-phy@0 { +&mdio1 { + rgmii_phy1: ethernet-phy@0 { compatible = "ethernet-phy-ieee802.3-c22"; reg = <0x0>; }; @@ -345,9 +375,9 @@ pmuio2-supply = <&vcc3v3_pmu>; vccio1-supply = <&vccio_acodec>; vccio3-supply = <&vccio_sd>; - vccio4-supply = <&vcc_1v8>; + vccio4-supply = <&vcc_3v3>; vccio5-supply = <&vcc_3v3>; - vccio6-supply = <&vcc_3v3>; + vccio6-supply = <&vcc_1v8>; vccio7-supply = <&vcc_3v3>; status = "okay"; }; diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild index 345fe98605ba..5c8ee5a541d2 100644 --- a/arch/arm64/include/asm/Kbuild +++ b/arch/arm64/include/asm/Kbuild @@ -7,3 +7,4 @@ generic-y += parport.h generic-y += user.h generated-y += cpucaps.h +generated-y += sysreg-defs.h diff --git a/arch/arm64/include/asm/arch_gicv3.h b/arch/arm64/include/asm/arch_gicv3.h index 8bd5afc7b692..48d4473e8eee 100644 --- a/arch/arm64/include/asm/arch_gicv3.h +++ b/arch/arm64/include/asm/arch_gicv3.h @@ -26,12 +26,6 @@ * sets the GP register's most significant bits to 0 with an explicit cast. */ -static inline void gic_write_eoir(u32 irq) -{ - write_sysreg_s(irq, SYS_ICC_EOIR1_EL1); - isb(); -} - static __always_inline void gic_write_dir(u32 irq) { write_sysreg_s(irq, SYS_ICC_DIR_EL1); diff --git a/arch/arm64/include/asm/archrandom.h b/arch/arm64/include/asm/archrandom.h index d1bb5e71df25..3a6b6d38c5b8 100644 --- a/arch/arm64/include/asm/archrandom.h +++ b/arch/arm64/include/asm/archrandom.h @@ -142,7 +142,7 @@ static inline bool __init __early_cpu_has_rndr(void) { /* Open code as we run prior to the first call to cpufeature. */ unsigned long ftr = read_sysreg_s(SYS_ID_AA64ISAR0_EL1); - return (ftr >> ID_AA64ISAR0_RNDR_SHIFT) & 0xf; + return (ftr >> ID_AA64ISAR0_EL1_RNDR_SHIFT) & 0xf; } static inline bool __init __must_check diff --git a/arch/arm64/include/asm/asm-bug.h b/arch/arm64/include/asm/asm-bug.h index 03f52f84a4f3..c762038ba400 100644 --- a/arch/arm64/include/asm/asm-bug.h +++ b/arch/arm64/include/asm/asm-bug.h @@ -14,7 +14,7 @@ 14472: .string file; \ .popsection; \ \ - .long 14472b - 14470b; \ + .long 14472b - .; \ .short line; #else #define _BUGVERBOSE_LOCATION(file, line) @@ -25,7 +25,7 @@ #define __BUG_ENTRY(flags) \ .pushsection __bug_table,"aw"; \ .align 2; \ - 14470: .long 14471f - 14470b; \ + 14470: .long 14471f - .; \ _BUGVERBOSE_LOCATION(__FILE__, __LINE__) \ .short flags; \ .popsection; \ diff --git a/arch/arm64/include/asm/compiler.h b/arch/arm64/include/asm/compiler.h index dc3ea4080e2e..6fb2e6bcc392 100644 --- a/arch/arm64/include/asm/compiler.h +++ b/arch/arm64/include/asm/compiler.h @@ -23,20 +23,4 @@ #define __builtin_return_address(val) \ (void *)(ptrauth_clear_pac((unsigned long)__builtin_return_address(val))) -#ifdef CONFIG_CFI_CLANG -/* - * With CONFIG_CFI_CLANG, the compiler replaces function address - * references with the address of the function's CFI jump table - * entry. The function_nocfi macro always returns the address of the - * actual function instead. - */ -#define function_nocfi(x) ({ \ - void *addr; \ - asm("adrp %0, " __stringify(x) "\n\t" \ - "add %0, %0, :lo12:" __stringify(x) \ - : "=r" (addr)); \ - addr; \ -}) -#endif - #endif /* __ASM_COMPILER_H */ diff --git a/arch/arm64/include/asm/cpu.h b/arch/arm64/include/asm/cpu.h index a58e366f0b07..115cdec1ae87 100644 --- a/arch/arm64/include/asm/cpu.h +++ b/arch/arm64/include/asm/cpu.h @@ -58,11 +58,15 @@ struct cpuinfo_arm64 { u64 reg_id_aa64pfr0; u64 reg_id_aa64pfr1; u64 reg_id_aa64zfr0; + u64 reg_id_aa64smfr0; struct cpuinfo_32bit aarch32; /* pseudo-ZCR for recording maximum ZCR_EL1 LEN value: */ u64 reg_zcr; + + /* pseudo-SMCR for recording maximum SMCR_EL1 LEN value: */ + u64 reg_smcr; }; DECLARE_PER_CPU(struct cpuinfo_arm64, cpu_data); diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index c62e7e5e2f0c..14a8f3d93add 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -622,6 +622,13 @@ static inline bool id_aa64pfr0_sve(u64 pfr0) return val > 0; } +static inline bool id_aa64pfr1_sme(u64 pfr1) +{ + u32 val = cpuid_feature_extract_unsigned_field(pfr1, ID_AA64PFR1_SME_SHIFT); + + return val > 0; +} + static inline bool id_aa64pfr1_mte(u64 pfr1) { u32 val = cpuid_feature_extract_unsigned_field(pfr1, ID_AA64PFR1_MTE_SHIFT); @@ -759,6 +766,23 @@ static __always_inline bool system_supports_sve(void) cpus_have_const_cap(ARM64_SVE); } +static __always_inline bool system_supports_sme(void) +{ + return IS_ENABLED(CONFIG_ARM64_SME) && + cpus_have_const_cap(ARM64_SME); +} + +static __always_inline bool system_supports_fa64(void) +{ + return IS_ENABLED(CONFIG_ARM64_SME) && + cpus_have_const_cap(ARM64_SME_FA64); +} + +static __always_inline bool system_supports_tpidr2(void) +{ + return system_supports_sme(); +} + static __always_inline bool system_supports_cnp(void) { return IS_ENABLED(CONFIG_ARM64_CNP) && diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 232b439cbaf3..92331c07c2d1 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -36,7 +36,7 @@ #define MIDR_VARIANT(midr) \ (((midr) & MIDR_VARIANT_MASK) >> MIDR_VARIANT_SHIFT) #define MIDR_IMPLEMENTOR_SHIFT 24 -#define MIDR_IMPLEMENTOR_MASK (0xff << MIDR_IMPLEMENTOR_SHIFT) +#define MIDR_IMPLEMENTOR_MASK (0xffU << MIDR_IMPLEMENTOR_SHIFT) #define MIDR_IMPLEMENTOR(midr) \ (((midr) & MIDR_IMPLEMENTOR_MASK) >> MIDR_IMPLEMENTOR_SHIFT) @@ -75,6 +75,7 @@ #define ARM_CPU_PART_CORTEX_A77 0xD0D #define ARM_CPU_PART_NEOVERSE_V1 0xD40 #define ARM_CPU_PART_CORTEX_A78 0xD41 +#define ARM_CPU_PART_CORTEX_A78AE 0xD42 #define ARM_CPU_PART_CORTEX_X1 0xD44 #define ARM_CPU_PART_CORTEX_A510 0xD46 #define ARM_CPU_PART_CORTEX_A710 0xD47 @@ -130,6 +131,7 @@ #define MIDR_CORTEX_A77 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A77) #define MIDR_NEOVERSE_V1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V1) #define MIDR_CORTEX_A78 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78) +#define MIDR_CORTEX_A78AE MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78AE) #define MIDR_CORTEX_X1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1) #define MIDR_CORTEX_A510 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A510) #define MIDR_CORTEX_A710 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A710) diff --git a/arch/arm64/include/asm/debug-monitors.h b/arch/arm64/include/asm/debug-monitors.h index 00c291067e57..7b7e05c02691 100644 --- a/arch/arm64/include/asm/debug-monitors.h +++ b/arch/arm64/include/asm/debug-monitors.h @@ -64,7 +64,7 @@ struct task_struct; struct step_hook { struct list_head node; - int (*fn)(struct pt_regs *regs, unsigned int esr); + int (*fn)(struct pt_regs *regs, unsigned long esr); }; void register_user_step_hook(struct step_hook *hook); @@ -75,7 +75,7 @@ void unregister_kernel_step_hook(struct step_hook *hook); struct break_hook { struct list_head node; - int (*fn)(struct pt_regs *regs, unsigned int esr); + int (*fn)(struct pt_regs *regs, unsigned long esr); u16 imm; u16 mask; /* These bits are ignored when comparing with imm */ }; diff --git a/arch/arm64/include/asm/el2_setup.h b/arch/arm64/include/asm/el2_setup.h index 7f3c87f7a0ce..34ceff08cac4 100644 --- a/arch/arm64/include/asm/el2_setup.h +++ b/arch/arm64/include/asm/el2_setup.h @@ -107,7 +107,7 @@ isb // Make sure SRE is now set mrs_s x0, SYS_ICC_SRE_EL2 // Read SRE back, tbz x0, #0, .Lskip_gicv3_\@ // and check that it sticks - msr_s SYS_ICH_HCR_EL2, xzr // Reset ICC_HCR_EL2 to defaults + msr_s SYS_ICH_HCR_EL2, xzr // Reset ICH_HCR_EL2 to defaults .Lskip_gicv3_\@: .endm @@ -143,6 +143,50 @@ .Lskip_sve_\@: .endm +/* SME register access and priority mapping */ +.macro __init_el2_nvhe_sme + mrs x1, id_aa64pfr1_el1 + ubfx x1, x1, #ID_AA64PFR1_SME_SHIFT, #4 + cbz x1, .Lskip_sme_\@ + + bic x0, x0, #CPTR_EL2_TSM // Also disable SME traps + msr cptr_el2, x0 // Disable copro. traps to EL2 + isb + + mrs x1, sctlr_el2 + orr x1, x1, #SCTLR_ELx_ENTP2 // Disable TPIDR2 traps + msr sctlr_el2, x1 + isb + + mov x1, #0 // SMCR controls + + mrs_s x2, SYS_ID_AA64SMFR0_EL1 + ubfx x2, x2, #ID_AA64SMFR0_FA64_SHIFT, #1 // Full FP in SM? + cbz x2, .Lskip_sme_fa64_\@ + + orr x1, x1, SMCR_ELx_FA64_MASK +.Lskip_sme_fa64_\@: + + orr x1, x1, #SMCR_ELx_LEN_MASK // Enable full SME vector + msr_s SYS_SMCR_EL2, x1 // length for EL1. + + mrs_s x1, SYS_SMIDR_EL1 // Priority mapping supported? + ubfx x1, x1, #SMIDR_EL1_SMPS_SHIFT, #1 + cbz x1, .Lskip_sme_\@ + + msr_s SYS_SMPRIMAP_EL2, xzr // Make all priorities equal + + mrs x1, id_aa64mmfr1_el1 // HCRX_EL2 present? + ubfx x1, x1, #ID_AA64MMFR1_HCX_SHIFT, #4 + cbz x1, .Lskip_sme_\@ + + mrs_s x1, SYS_HCRX_EL2 + orr x1, x1, #HCRX_EL2_SMPME_MASK // Enable priority mapping + msr_s SYS_HCRX_EL2, x1 + +.Lskip_sme_\@: +.endm + /* Disable any fine grained traps */ .macro __init_el2_fgt mrs x1, id_aa64mmfr0_el1 @@ -153,15 +197,26 @@ mrs x1, id_aa64dfr0_el1 ubfx x1, x1, #ID_AA64DFR0_PMSVER_SHIFT, #4 cmp x1, #3 - b.lt .Lset_fgt_\@ + b.lt .Lset_debug_fgt_\@ /* Disable PMSNEVFR_EL1 read and write traps */ orr x0, x0, #(1 << 62) -.Lset_fgt_\@: +.Lset_debug_fgt_\@: msr_s SYS_HDFGRTR_EL2, x0 msr_s SYS_HDFGWTR_EL2, x0 - msr_s SYS_HFGRTR_EL2, xzr - msr_s SYS_HFGWTR_EL2, xzr + + mov x0, xzr + mrs x1, id_aa64pfr1_el1 + ubfx x1, x1, #ID_AA64PFR1_SME_SHIFT, #4 + cbz x1, .Lset_fgt_\@ + + /* Disable nVHE traps of TPIDR2 and SMPRI */ + orr x0, x0, #HFGxTR_EL2_nSMPRI_EL1_MASK + orr x0, x0, #HFGxTR_EL2_nTPIDR2_EL0_MASK + +.Lset_fgt_\@: + msr_s SYS_HFGRTR_EL2, x0 + msr_s SYS_HFGWTR_EL2, x0 msr_s SYS_HFGITR_EL2, xzr mrs x1, id_aa64pfr0_el1 // AMU traps UNDEF without AMU @@ -196,6 +251,7 @@ __init_el2_nvhe_idregs __init_el2_nvhe_cptr __init_el2_nvhe_sve + __init_el2_nvhe_sme __init_el2_fgt __init_el2_nvhe_prepare_eret .endm diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h index d52a0b269ee8..8f236de7359c 100644 --- a/arch/arm64/include/asm/esr.h +++ b/arch/arm64/include/asm/esr.h @@ -37,7 +37,8 @@ #define ESR_ELx_EC_ERET (0x1a) /* EL2 only */ /* Unallocated EC: 0x1B */ #define ESR_ELx_EC_FPAC (0x1C) /* EL1 and above */ -/* Unallocated EC: 0x1D - 0x1E */ +#define ESR_ELx_EC_SME (0x1D) +/* Unallocated EC: 0x1E */ #define ESR_ELx_EC_IMP_DEF (0x1f) /* EL3 only */ #define ESR_ELx_EC_IABT_LOW (0x20) #define ESR_ELx_EC_IABT_CUR (0x21) @@ -75,6 +76,7 @@ #define ESR_ELx_IL_SHIFT (25) #define ESR_ELx_IL (UL(1) << ESR_ELx_IL_SHIFT) #define ESR_ELx_ISS_MASK (ESR_ELx_IL - 1) +#define ESR_ELx_ISS(esr) ((esr) & ESR_ELx_ISS_MASK) /* ISS field definitions shared by different classes */ #define ESR_ELx_WNR_SHIFT (6) @@ -136,7 +138,7 @@ #define ESR_ELx_WFx_ISS_TI (UL(1) << 0) #define ESR_ELx_WFx_ISS_WFI (UL(0) << 0) #define ESR_ELx_WFx_ISS_WFE (UL(1) << 0) -#define ESR_ELx_xVC_IMM_MASK ((1UL << 16) - 1) +#define ESR_ELx_xVC_IMM_MASK ((UL(1) << 16) - 1) #define DISR_EL1_IDS (UL(1) << 24) /* @@ -327,17 +329,26 @@ #define ESR_ELx_CP15_32_ISS_SYS_CNTFRQ (ESR_ELx_CP15_32_ISS_SYS_VAL(0, 0, 14, 0) |\ ESR_ELx_CP15_32_ISS_DIR_READ) +/* + * ISS values for SME traps + */ + +#define ESR_ELx_SME_ISS_SME_DISABLED 0 +#define ESR_ELx_SME_ISS_ILL 1 +#define ESR_ELx_SME_ISS_SM_DISABLED 2 +#define ESR_ELx_SME_ISS_ZA_DISABLED 3 + #ifndef __ASSEMBLY__ #include <asm/types.h> -static inline bool esr_is_data_abort(u32 esr) +static inline bool esr_is_data_abort(unsigned long esr) { - const u32 ec = ESR_ELx_EC(esr); + const unsigned long ec = ESR_ELx_EC(esr); return ec == ESR_ELx_EC_DABT_LOW || ec == ESR_ELx_EC_DABT_CUR; } -const char *esr_get_class_string(u32 esr); +const char *esr_get_class_string(unsigned long esr); #endif /* __ASSEMBLY */ #endif /* __ASM_ESR_H */ diff --git a/arch/arm64/include/asm/exception.h b/arch/arm64/include/asm/exception.h index 339477dca551..d94aecff9690 100644 --- a/arch/arm64/include/asm/exception.h +++ b/arch/arm64/include/asm/exception.h @@ -19,9 +19,9 @@ #define __exception_irq_entry __kprobes #endif -static inline u32 disr_to_esr(u64 disr) +static inline unsigned long disr_to_esr(u64 disr) { - unsigned int esr = ESR_ELx_EC_SERROR << ESR_ELx_EC_SHIFT; + unsigned long esr = ESR_ELx_EC_SERROR << ESR_ELx_EC_SHIFT; if ((disr & DISR_EL1_IDS) == 0) esr |= (disr & DISR_EL1_ESR_MASK); @@ -57,23 +57,24 @@ asmlinkage void call_on_irq_stack(struct pt_regs *regs, void (*func)(struct pt_regs *)); asmlinkage void asm_exit_to_user_mode(struct pt_regs *regs); -void do_mem_abort(unsigned long far, unsigned int esr, struct pt_regs *regs); +void do_mem_abort(unsigned long far, unsigned long esr, struct pt_regs *regs); void do_undefinstr(struct pt_regs *regs); void do_bti(struct pt_regs *regs); -void do_debug_exception(unsigned long addr_if_watchpoint, unsigned int esr, +void do_debug_exception(unsigned long addr_if_watchpoint, unsigned long esr, struct pt_regs *regs); -void do_fpsimd_acc(unsigned int esr, struct pt_regs *regs); -void do_sve_acc(unsigned int esr, struct pt_regs *regs); -void do_fpsimd_exc(unsigned int esr, struct pt_regs *regs); -void do_sysinstr(unsigned int esr, struct pt_regs *regs); -void do_sp_pc_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs); -void bad_el0_sync(struct pt_regs *regs, int reason, unsigned int esr); -void do_cp15instr(unsigned int esr, struct pt_regs *regs); +void do_fpsimd_acc(unsigned long esr, struct pt_regs *regs); +void do_sve_acc(unsigned long esr, struct pt_regs *regs); +void do_sme_acc(unsigned long esr, struct pt_regs *regs); +void do_fpsimd_exc(unsigned long esr, struct pt_regs *regs); +void do_sysinstr(unsigned long esr, struct pt_regs *regs); +void do_sp_pc_abort(unsigned long addr, unsigned long esr, struct pt_regs *regs); +void bad_el0_sync(struct pt_regs *regs, int reason, unsigned long esr); +void do_cp15instr(unsigned long esr, struct pt_regs *regs); void do_el0_svc(struct pt_regs *regs); void do_el0_svc_compat(struct pt_regs *regs); -void do_ptrauth_fault(struct pt_regs *regs, unsigned int esr); -void do_serror(struct pt_regs *regs, unsigned int esr); +void do_ptrauth_fault(struct pt_regs *regs, unsigned long esr); +void do_serror(struct pt_regs *regs, unsigned long esr); void do_notify_resume(struct pt_regs *regs, unsigned long thread_flags); -void panic_bad_stack(struct pt_regs *regs, unsigned int esr, unsigned long far); +void panic_bad_stack(struct pt_regs *regs, unsigned long esr, unsigned long far); #endif /* __ASM_EXCEPTION_H */ diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h index cb24385e3632..9bb1873f5295 100644 --- a/arch/arm64/include/asm/fpsimd.h +++ b/arch/arm64/include/asm/fpsimd.h @@ -32,6 +32,18 @@ #define VFP_STATE_SIZE ((32 * 8) + 4) #endif +/* + * When we defined the maximum SVE vector length we defined the ABI so + * that the maximum vector length included all the reserved for future + * expansion bits in ZCR rather than those just currently defined by + * the architecture. While SME follows a similar pattern the fact that + * it includes a square matrix means that any allocations that attempt + * to cover the maximum potential vector length (such as happen with + * the regset used for ptrace) end up being extremely large. Define + * the much lower actual limit for use in such situations. + */ +#define SME_VQ_MAX 16 + struct task_struct; extern void fpsimd_save_state(struct user_fpsimd_state *state); @@ -46,11 +58,23 @@ extern void fpsimd_restore_current_state(void); extern void fpsimd_update_current_state(struct user_fpsimd_state const *state); extern void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *state, - void *sve_state, unsigned int sve_vl); + void *sve_state, unsigned int sve_vl, + void *za_state, unsigned int sme_vl, + u64 *svcr); extern void fpsimd_flush_task_state(struct task_struct *target); extern void fpsimd_save_and_flush_cpu_state(void); +static inline bool thread_sm_enabled(struct thread_struct *thread) +{ + return system_supports_sme() && (thread->svcr & SVCR_SM_MASK); +} + +static inline bool thread_za_enabled(struct thread_struct *thread) +{ + return system_supports_sme() && (thread->svcr & SVCR_ZA_MASK); +} + /* Maximum VL that SVE/SME VL-agnostic software can transparently support */ #define VL_ARCH_MAX 0x100 @@ -62,7 +86,14 @@ static inline size_t sve_ffr_offset(int vl) static inline void *sve_pffr(struct thread_struct *thread) { - return (char *)thread->sve_state + sve_ffr_offset(thread_get_sve_vl(thread)); + unsigned int vl; + + if (system_supports_sme() && thread_sm_enabled(thread)) + vl = thread_get_sme_vl(thread); + else + vl = thread_get_sve_vl(thread); + + return (char *)thread->sve_state + sve_ffr_offset(vl); } extern void sve_save_state(void *state, u32 *pfpsr, int save_ffr); @@ -71,11 +102,17 @@ extern void sve_load_state(void const *state, u32 const *pfpsr, extern void sve_flush_live(bool flush_ffr, unsigned long vq_minus_1); extern unsigned int sve_get_vl(void); extern void sve_set_vq(unsigned long vq_minus_1); +extern void sme_set_vq(unsigned long vq_minus_1); +extern void za_save_state(void *state); +extern void za_load_state(void const *state); struct arm64_cpu_capabilities; extern void sve_kernel_enable(const struct arm64_cpu_capabilities *__unused); +extern void sme_kernel_enable(const struct arm64_cpu_capabilities *__unused); +extern void fa64_kernel_enable(const struct arm64_cpu_capabilities *__unused); extern u64 read_zcr_features(void); +extern u64 read_smcr_features(void); /* * Helpers to translate bit indices in sve_vq_map to VQ values (and @@ -119,6 +156,7 @@ struct vl_info { extern void sve_alloc(struct task_struct *task); extern void fpsimd_release_task(struct task_struct *task); extern void fpsimd_sync_to_sve(struct task_struct *task); +extern void fpsimd_force_sync_to_sve(struct task_struct *task); extern void sve_sync_to_fpsimd(struct task_struct *task); extern void sve_sync_from_fpsimd_zeropad(struct task_struct *task); @@ -171,6 +209,12 @@ static inline void write_vl(enum vec_type type, u64 val) write_sysreg_s(tmp | val, SYS_ZCR_EL1); break; #endif +#ifdef CONFIG_ARM64_SME + case ARM64_VEC_SME: + tmp = read_sysreg_s(SYS_SMCR_EL1) & ~SMCR_ELx_LEN_MASK; + write_sysreg_s(tmp | val, SYS_SMCR_EL1); + break; +#endif default: WARN_ON_ONCE(1); break; @@ -208,6 +252,8 @@ static inline bool sve_vq_available(unsigned int vq) return vq_available(ARM64_VEC_SVE, vq); } +size_t sve_state_size(struct task_struct const *task); + #else /* ! CONFIG_ARM64_SVE */ static inline void sve_alloc(struct task_struct *task) { } @@ -247,8 +293,93 @@ static inline void vec_update_vq_map(enum vec_type t) { } static inline int vec_verify_vq_map(enum vec_type t) { return 0; } static inline void sve_setup(void) { } +static inline size_t sve_state_size(struct task_struct const *task) +{ + return 0; +} + #endif /* ! CONFIG_ARM64_SVE */ +#ifdef CONFIG_ARM64_SME + +static inline void sme_user_disable(void) +{ + sysreg_clear_set(cpacr_el1, CPACR_EL1_SMEN_EL0EN, 0); +} + +static inline void sme_user_enable(void) +{ + sysreg_clear_set(cpacr_el1, 0, CPACR_EL1_SMEN_EL0EN); +} + +static inline void sme_smstart_sm(void) +{ + asm volatile(__msr_s(SYS_SVCR_SMSTART_SM_EL0, "xzr")); +} + +static inline void sme_smstop_sm(void) +{ + asm volatile(__msr_s(SYS_SVCR_SMSTOP_SM_EL0, "xzr")); +} + +static inline void sme_smstop(void) +{ + asm volatile(__msr_s(SYS_SVCR_SMSTOP_SMZA_EL0, "xzr")); +} + +extern void __init sme_setup(void); + +static inline int sme_max_vl(void) +{ + return vec_max_vl(ARM64_VEC_SME); +} + +static inline int sme_max_virtualisable_vl(void) +{ + return vec_max_virtualisable_vl(ARM64_VEC_SME); +} + +extern void sme_alloc(struct task_struct *task); +extern unsigned int sme_get_vl(void); +extern int sme_set_current_vl(unsigned long arg); +extern int sme_get_current_vl(void); + +/* + * Return how many bytes of memory are required to store the full SME + * specific state (currently just ZA) for task, given task's currently + * configured vector length. + */ +static inline size_t za_state_size(struct task_struct const *task) +{ + unsigned int vl = task_get_sme_vl(task); + + return ZA_SIG_REGS_SIZE(sve_vq_from_vl(vl)); +} + +#else + +static inline void sme_user_disable(void) { BUILD_BUG(); } +static inline void sme_user_enable(void) { BUILD_BUG(); } + +static inline void sme_smstart_sm(void) { } +static inline void sme_smstop_sm(void) { } +static inline void sme_smstop(void) { } + +static inline void sme_alloc(struct task_struct *task) { } +static inline void sme_setup(void) { } +static inline unsigned int sme_get_vl(void) { return 0; } +static inline int sme_max_vl(void) { return 0; } +static inline int sme_max_virtualisable_vl(void) { return 0; } +static inline int sme_set_current_vl(unsigned long arg) { return -EINVAL; } +static inline int sme_get_current_vl(void) { return -EINVAL; } + +static inline size_t za_state_size(struct task_struct const *task) +{ + return 0; +} + +#endif /* ! CONFIG_ARM64_SME */ + /* For use by EFI runtime services calls only */ extern void __efi_fpsimd_begin(void); extern void __efi_fpsimd_end(void); diff --git a/arch/arm64/include/asm/fpsimdmacros.h b/arch/arm64/include/asm/fpsimdmacros.h index 2509d7dde55a..5e0910cf4832 100644 --- a/arch/arm64/include/asm/fpsimdmacros.h +++ b/arch/arm64/include/asm/fpsimdmacros.h @@ -93,6 +93,12 @@ .endif .endm +.macro _sme_check_wv v + .if (\v) < 12 || (\v) > 15 + .error "Bad vector select register \v." + .endif +.endm + /* SVE instruction encodings for non-SVE-capable assemblers */ /* (pre binutils 2.28, all kernel capable clang versions support SVE) */ @@ -174,6 +180,54 @@ | (\np) .endm +/* SME instruction encodings for non-SME-capable assemblers */ +/* (pre binutils 2.38/LLVM 13) */ + +/* RDSVL X\nx, #\imm */ +.macro _sme_rdsvl nx, imm + _check_general_reg \nx + _check_num (\imm), -0x20, 0x1f + .inst 0x04bf5800 \ + | (\nx) \ + | (((\imm) & 0x3f) << 5) +.endm + +/* + * STR (vector from ZA array): + * STR ZA[\nw, #\offset], [X\nxbase, #\offset, MUL VL] + */ +.macro _sme_str_zav nw, nxbase, offset=0 + _sme_check_wv \nw + _check_general_reg \nxbase + _check_num (\offset), -0x100, 0xff + .inst 0xe1200000 \ + | (((\nw) & 3) << 13) \ + | ((\nxbase) << 5) \ + | ((\offset) & 7) +.endm + +/* + * LDR (vector to ZA array): + * LDR ZA[\nw, #\offset], [X\nxbase, #\offset, MUL VL] + */ +.macro _sme_ldr_zav nw, nxbase, offset=0 + _sme_check_wv \nw + _check_general_reg \nxbase + _check_num (\offset), -0x100, 0xff + .inst 0xe1000000 \ + | (((\nw) & 3) << 13) \ + | ((\nxbase) << 5) \ + | ((\offset) & 7) +.endm + +/* + * Zero the entire ZA array + * ZERO ZA + */ +.macro zero_za + .inst 0xc00800ff +.endm + .macro __for from:req, to:req .if (\from) == (\to) _for__body %\from @@ -208,6 +262,17 @@ 921: .endm +/* Update SMCR_EL1.LEN with the new VQ */ +.macro sme_load_vq xvqminus1, xtmp, xtmp2 + mrs_s \xtmp, SYS_SMCR_EL1 + bic \xtmp2, \xtmp, SMCR_ELx_LEN_MASK + orr \xtmp2, \xtmp2, \xvqminus1 + cmp \xtmp2, \xtmp + b.eq 921f + msr_s SYS_SMCR_EL1, \xtmp2 //self-synchronising +921: +.endm + /* Preserve the first 128-bits of Znz and zero the rest. */ .macro _sve_flush_z nz _sve_check_zreg \nz @@ -254,3 +319,25 @@ ldr w\nxtmp, [\xpfpsr, #4] msr fpcr, x\nxtmp .endm + +.macro sme_save_za nxbase, xvl, nw + mov w\nw, #0 + +423: + _sme_str_zav \nw, \nxbase + add x\nxbase, x\nxbase, \xvl + add x\nw, x\nw, #1 + cmp \xvl, x\nw + bne 423b +.endm + +.macro sme_load_za nxbase, xvl, nw + mov w\nw, #0 + +423: + _sme_ldr_zav \nw, \nxbase + add x\nxbase, x\nxbase, \xvl + add x\nw, x\nw, #1 + cmp \xvl, x\nw + bne 423b +.endm diff --git a/arch/arm64/include/asm/ftrace.h b/arch/arm64/include/asm/ftrace.h index 1494cfa8639b..dbc45a4157fa 100644 --- a/arch/arm64/include/asm/ftrace.h +++ b/arch/arm64/include/asm/ftrace.h @@ -80,8 +80,15 @@ static inline unsigned long ftrace_call_adjust(unsigned long addr) #ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS struct dyn_ftrace; +struct ftrace_ops; +struct ftrace_regs; + int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec); #define ftrace_init_nop ftrace_init_nop + +void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct ftrace_regs *fregs); +#define ftrace_graph_func ftrace_graph_func #endif #define ftrace_return_address(n) return_address(n) diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h index 1242f71937f8..d656822b13f1 100644 --- a/arch/arm64/include/asm/hugetlb.h +++ b/arch/arm64/include/asm/hugetlb.h @@ -44,6 +44,8 @@ extern void huge_ptep_clear_flush(struct vm_area_struct *vma, #define __HAVE_ARCH_HUGE_PTE_CLEAR extern void huge_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned long sz); +#define __HAVE_ARCH_HUGE_PTEP_GET +extern pte_t huge_ptep_get(pte_t *ptep); extern void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte, unsigned long sz); #define set_huge_swap_pte_at set_huge_swap_pte_at diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h index 8db5ec0089db..9f0ce004fdbc 100644 --- a/arch/arm64/include/asm/hwcap.h +++ b/arch/arm64/include/asm/hwcap.h @@ -109,6 +109,14 @@ #define KERNEL_HWCAP_AFP __khwcap2_feature(AFP) #define KERNEL_HWCAP_RPRES __khwcap2_feature(RPRES) #define KERNEL_HWCAP_MTE3 __khwcap2_feature(MTE3) +#define KERNEL_HWCAP_SME __khwcap2_feature(SME) +#define KERNEL_HWCAP_SME_I16I64 __khwcap2_feature(SME_I16I64) +#define KERNEL_HWCAP_SME_F64F64 __khwcap2_feature(SME_F64F64) +#define KERNEL_HWCAP_SME_I8I32 __khwcap2_feature(SME_I8I32) +#define KERNEL_HWCAP_SME_F16F32 __khwcap2_feature(SME_F16F32) +#define KERNEL_HWCAP_SME_B16F32 __khwcap2_feature(SME_B16F32) +#define KERNEL_HWCAP_SME_F32F32 __khwcap2_feature(SME_F32F32) +#define KERNEL_HWCAP_SME_FA64 __khwcap2_feature(SME_FA64) /* * This yields a mask that user programs can use to figure out what diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h index 7fd836bea7eb..3995652daf81 100644 --- a/arch/arm64/include/asm/io.h +++ b/arch/arm64/include/asm/io.h @@ -192,4 +192,8 @@ extern void __iomem *ioremap_cache(phys_addr_t phys_addr, size_t size); extern int valid_phys_addr_range(phys_addr_t addr, size_t size); extern int valid_mmap_phys_addr_range(unsigned long pfn, size_t size); +extern bool arch_memremap_can_ram_remap(resource_size_t offset, size_t size, + unsigned long flags); +#define arch_memremap_can_ram_remap arch_memremap_can_ram_remap + #endif /* __ASM_IO_H */ diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index 1767ded83888..13ae232ec4a1 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -279,6 +279,7 @@ #define CPTR_EL2_TCPAC (1U << 31) #define CPTR_EL2_TAM (1 << 30) #define CPTR_EL2_TTA (1 << 20) +#define CPTR_EL2_TSM (1 << 12) #define CPTR_EL2_TFP (1 << CPTR_EL2_TFP_SHIFT) #define CPTR_EL2_TZ (1 << 8) #define CPTR_NVHE_EL2_RES1 0x000032ff /* known RES1 bits in CPTR_EL2 (nVHE) */ diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index d62405ce3e6d..08233172e7a9 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -40,13 +40,26 @@ void kvm_inject_undefined(struct kvm_vcpu *vcpu); void kvm_inject_vabt(struct kvm_vcpu *vcpu); void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr); void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr); +void kvm_inject_size_fault(struct kvm_vcpu *vcpu); void kvm_vcpu_wfi(struct kvm_vcpu *vcpu); +#if defined(__KVM_VHE_HYPERVISOR__) || defined(__KVM_NVHE_HYPERVISOR__) static __always_inline bool vcpu_el1_is_32bit(struct kvm_vcpu *vcpu) { return !(vcpu->arch.hcr_el2 & HCR_RW); } +#else +static __always_inline bool vcpu_el1_is_32bit(struct kvm_vcpu *vcpu) +{ + struct kvm *kvm = vcpu->kvm; + + WARN_ON_ONCE(!test_bit(KVM_ARCH_FLAG_REG_WIDTH_CONFIGURED, + &kvm->arch.flags)); + + return test_bit(KVM_ARCH_FLAG_EL1_32BIT, &kvm->arch.flags); +} +#endif static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu) { @@ -72,15 +85,14 @@ static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu) vcpu->arch.hcr_el2 |= HCR_TVM; } - if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features)) + if (vcpu_el1_is_32bit(vcpu)) vcpu->arch.hcr_el2 &= ~HCR_RW; - - /* - * TID3: trap feature register accesses that we virtualise. - * For now this is conditional, since no AArch32 feature regs - * are currently virtualised. - */ - if (!vcpu_el1_is_32bit(vcpu)) + else + /* + * TID3: trap feature register accesses that we virtualise. + * For now this is conditional, since no AArch32 feature regs + * are currently virtualised. + */ vcpu->arch.hcr_el2 |= HCR_TID3; if (cpus_have_const_cap(ARM64_MISMATCHED_CACHE_TYPE) || @@ -224,14 +236,14 @@ static inline bool vcpu_mode_priv(const struct kvm_vcpu *vcpu) return mode != PSR_MODE_EL0t; } -static __always_inline u32 kvm_vcpu_get_esr(const struct kvm_vcpu *vcpu) +static __always_inline u64 kvm_vcpu_get_esr(const struct kvm_vcpu *vcpu) { return vcpu->arch.fault.esr_el2; } static __always_inline int kvm_vcpu_get_condition(const struct kvm_vcpu *vcpu) { - u32 esr = kvm_vcpu_get_esr(vcpu); + u64 esr = kvm_vcpu_get_esr(vcpu); if (esr & ESR_ELx_CV) return (esr & ESR_ELx_COND_MASK) >> ESR_ELx_COND_SHIFT; @@ -362,7 +374,7 @@ static __always_inline bool kvm_vcpu_abt_issea(const struct kvm_vcpu *vcpu) static __always_inline int kvm_vcpu_sys_get_rt(struct kvm_vcpu *vcpu) { - u32 esr = kvm_vcpu_get_esr(vcpu); + u64 esr = kvm_vcpu_get_esr(vcpu); return ESR_ELx_SYS64_ISS_RT(esr); } diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index e3b25dc6c367..d5888dedf02a 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -127,6 +127,16 @@ struct kvm_arch { #define KVM_ARCH_FLAG_MTE_ENABLED 1 /* At least one vCPU has ran in the VM */ #define KVM_ARCH_FLAG_HAS_RAN_ONCE 2 + /* + * The following two bits are used to indicate the guest's EL1 + * register width configuration. A value of KVM_ARCH_FLAG_EL1_32BIT + * bit is valid only when KVM_ARCH_FLAG_REG_WIDTH_CONFIGURED is set. + * Otherwise, the guest's EL1 register width has not yet been + * determined yet. + */ +#define KVM_ARCH_FLAG_REG_WIDTH_CONFIGURED 3 +#define KVM_ARCH_FLAG_EL1_32BIT 4 + unsigned long flags; /* @@ -143,7 +153,7 @@ struct kvm_arch { }; struct kvm_vcpu_fault_info { - u32 esr_el2; /* Hyp Syndrom Register */ + u64 esr_el2; /* Hyp Syndrom Register */ u64 far_el2; /* Hyp Fault Address Register */ u64 hpfar_el2; /* Hyp IPA Fault Address Register */ u64 disr_el1; /* Deferred [SError] Status Register */ @@ -285,8 +295,11 @@ struct vcpu_reset_state { struct kvm_vcpu_arch { struct kvm_cpu_context ctxt; + + /* Guest floating point state */ void *sve_state; unsigned int sve_max_vl; + u64 svcr; /* Stage 2 paging state used by the hardware on next switch */ struct kvm_s2_mmu *hw_mmu; @@ -441,6 +454,7 @@ struct kvm_vcpu_arch { #define KVM_ARM64_DEBUG_STATE_SAVE_TRBE (1 << 13) /* Save TRBE context if active */ #define KVM_ARM64_FP_FOREIGN_FPSTATE (1 << 14) #define KVM_ARM64_ON_UNSUPPORTED_CPU (1 << 15) /* Physical CPU not in supported_cpus */ +#define KVM_ARM64_HOST_SME_ENABLED (1 << 16) /* SME enabled for EL0 */ #define KVM_GUESTDBG_VALID_MASK (KVM_GUESTDBG_ENABLE | \ KVM_GUESTDBG_USE_SW_BP | \ diff --git a/arch/arm64/include/asm/kvm_ras.h b/arch/arm64/include/asm/kvm_ras.h index 8ac6ee77437c..87e10d9a635b 100644 --- a/arch/arm64/include/asm/kvm_ras.h +++ b/arch/arm64/include/asm/kvm_ras.h @@ -14,7 +14,7 @@ * Was this synchronous external abort a RAS notification? * Returns '0' for errors handled by some RAS subsystem, or -ENOENT. */ -static inline int kvm_handle_guest_sea(phys_addr_t addr, unsigned int esr) +static inline int kvm_handle_guest_sea(phys_addr_t addr, u64 esr) { /* apei_claim_sea(NULL) expects to mask interrupts itself */ lockdep_assert_irqs_enabled(); diff --git a/arch/arm64/include/asm/mte.h b/arch/arm64/include/asm/mte.h index adcb937342f1..aa523591a44e 100644 --- a/arch/arm64/include/asm/mte.h +++ b/arch/arm64/include/asm/mte.h @@ -47,6 +47,7 @@ long set_mte_ctrl(struct task_struct *task, unsigned long arg); long get_mte_ctrl(struct task_struct *task); int mte_ptrace_copy_tags(struct task_struct *child, long request, unsigned long addr, unsigned long data); +size_t mte_probe_user_range(const char __user *uaddr, size_t size); #else /* CONFIG_ARM64_MTE */ diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h index 66671ff05183..dd3d12bce07b 100644 --- a/arch/arm64/include/asm/pgtable-hwdef.h +++ b/arch/arm64/include/asm/pgtable-hwdef.h @@ -49,7 +49,7 @@ #define PMD_SHIFT ARM64_HW_PGTABLE_LEVEL_SHIFT(2) #define PMD_SIZE (_AC(1, UL) << PMD_SHIFT) #define PMD_MASK (~(PMD_SIZE-1)) -#define PTRS_PER_PMD PTRS_PER_PTE +#define PTRS_PER_PMD (1 << (PAGE_SHIFT - 3)) #endif /* @@ -59,7 +59,7 @@ #define PUD_SHIFT ARM64_HW_PGTABLE_LEVEL_SHIFT(1) #define PUD_SIZE (_AC(1, UL) << PUD_SHIFT) #define PUD_MASK (~(PUD_SIZE-1)) -#define PTRS_PER_PUD PTRS_PER_PTE +#define PTRS_PER_PUD (1 << (PAGE_SHIFT - 3)) #endif /* diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 94e147e5456c..45c358538f13 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -535,7 +535,7 @@ extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, PMD_TYPE_TABLE) #define pmd_sect(pmd) ((pmd_val(pmd) & PMD_TYPE_MASK) == \ PMD_TYPE_SECT) -#define pmd_leaf(pmd) pmd_sect(pmd) +#define pmd_leaf(pmd) (pmd_present(pmd) && !pmd_table(pmd)) #define pmd_bad(pmd) (!pmd_table(pmd)) #define pmd_leaf_size(pmd) (pmd_cont(pmd) ? CONT_PMD_SIZE : PMD_SIZE) @@ -625,7 +625,7 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd) #define pud_none(pud) (!pud_val(pud)) #define pud_bad(pud) (!pud_table(pud)) #define pud_present(pud) pte_present(pud_pte(pud)) -#define pud_leaf(pud) pud_sect(pud) +#define pud_leaf(pud) (pud_present(pud) && !pud_table(pud)) #define pud_valid(pud) pte_valid(pud_pte(pud)) static inline void set_pud(pud_t *pudp, pud_t pud) @@ -1001,7 +1001,8 @@ static inline void update_mmu_cache(struct vm_area_struct *vma, */ static inline bool arch_faults_on_old_pte(void) { - WARN_ON(preemptible()); + /* The register read below requires a stable CPU to make any sense */ + cant_migrate(); return !cpu_has_hw_af(); } diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index 73e38d9a540c..bf8aafee1eac 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -118,6 +118,7 @@ struct debug_info { enum vec_type { ARM64_VEC_SVE = 0, + ARM64_VEC_SME, ARM64_VEC_MAX, }; @@ -153,6 +154,7 @@ struct thread_struct { unsigned int fpsimd_cpu; void *sve_state; /* SVE registers, if any */ + void *za_state; /* ZA register, if any */ unsigned int vl[ARM64_VEC_MAX]; /* vector length */ unsigned int vl_onexec[ARM64_VEC_MAX]; /* vl after next exec */ unsigned long fault_address; /* fault info */ @@ -168,6 +170,8 @@ struct thread_struct { u64 mte_ctrl; #endif u64 sctlr_user; + u64 svcr; + u64 tpidr2_el0; }; static inline unsigned int thread_get_vl(struct thread_struct *thread, @@ -181,6 +185,19 @@ static inline unsigned int thread_get_sve_vl(struct thread_struct *thread) return thread_get_vl(thread, ARM64_VEC_SVE); } +static inline unsigned int thread_get_sme_vl(struct thread_struct *thread) +{ + return thread_get_vl(thread, ARM64_VEC_SME); +} + +static inline unsigned int thread_get_cur_vl(struct thread_struct *thread) +{ + if (system_supports_sme() && (thread->svcr & SVCR_SM_MASK)) + return thread_get_sme_vl(thread); + else + return thread_get_sve_vl(thread); +} + unsigned int task_get_vl(const struct task_struct *task, enum vec_type type); void task_set_vl(struct task_struct *task, enum vec_type type, unsigned long vl); @@ -194,6 +211,11 @@ static inline unsigned int task_get_sve_vl(const struct task_struct *task) return task_get_vl(task, ARM64_VEC_SVE); } +static inline unsigned int task_get_sme_vl(const struct task_struct *task) +{ + return task_get_vl(task, ARM64_VEC_SME); +} + static inline void task_set_sve_vl(struct task_struct *task, unsigned long vl) { task_set_vl(task, ARM64_VEC_SVE, vl); @@ -354,9 +376,11 @@ extern void __init minsigstksz_setup(void); */ #include <asm/fpsimd.h> -/* Userspace interface for PR_SVE_{SET,GET}_VL prctl()s: */ +/* Userspace interface for PR_S[MV]E_{SET,GET}_VL prctl()s: */ #define SVE_SET_VL(arg) sve_set_current_vl(arg) #define SVE_GET_VL() sve_get_current_vl() +#define SME_SET_VL(arg) sme_set_current_vl(arg) +#define SME_GET_VL() sme_get_current_vl() /* PR_PAC_RESET_KEYS prctl */ #define PAC_RESET_KEYS(tsk, arg) ptrauth_prctl_reset_keys(tsk, arg) @@ -381,12 +405,10 @@ long get_tagged_addr_ctrl(struct task_struct *task); * of header definitions for the use of task_stack_page. */ -#define current_top_of_stack() \ -({ \ - struct stack_info _info; \ - BUG_ON(!on_accessible_stack(current, current_stack_pointer, 1, &_info)); \ - _info.high; \ -}) +/* + * The top of the current task's task stack + */ +#define current_top_of_stack() ((unsigned long)current->stack + THREAD_SIZE) #define on_thread_stack() (on_task_stack(current, current_stack_pointer, 1, NULL)) #endif /* __ASSEMBLY__ */ diff --git a/arch/arm64/include/asm/stacktrace.h b/arch/arm64/include/asm/stacktrace.h index e77cdef9ca29..aec9315bf156 100644 --- a/arch/arm64/include/asm/stacktrace.h +++ b/arch/arm64/include/asm/stacktrace.h @@ -31,38 +31,6 @@ struct stack_info { enum stack_type type; }; -/* - * A snapshot of a frame record or fp/lr register values, along with some - * accounting information necessary for robust unwinding. - * - * @fp: The fp value in the frame record (or the real fp) - * @pc: The lr value in the frame record (or the real lr) - * - * @stacks_done: Stacks which have been entirely unwound, for which it is no - * longer valid to unwind to. - * - * @prev_fp: The fp that pointed to this frame record, or a synthetic value - * of 0. This is used to ensure that within a stack, each - * subsequent frame record is at an increasing address. - * @prev_type: The type of stack this frame record was on, or a synthetic - * value of STACK_TYPE_UNKNOWN. This is used to detect a - * transition from one stack to another. - * - * @kr_cur: When KRETPROBES is selected, holds the kretprobe instance - * associated with the most recently encountered replacement lr - * value. - */ -struct stackframe { - unsigned long fp; - unsigned long pc; - DECLARE_BITMAP(stacks_done, __NR_STACK_TYPES); - unsigned long prev_fp; - enum stack_type prev_type; -#ifdef CONFIG_KRETPROBES - struct llist_node *kr_cur; -#endif -}; - extern void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk, const char *loglvl); diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index fbf5f8bb9055..55f998c3dc28 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -115,9 +115,21 @@ #define SYS_DC_CISW sys_insn(1, 0, 7, 14, 2) /* + * Automatically generated definitions for system registers, the + * manual encodings below are in the process of being converted to + * come from here. The header relies on the definition of sys_reg() + * earlier in this file. + */ +#include "asm/sysreg-defs.h" + +/* * System registers, organised loosely by encoding but grouped together * where the architected name contains an index. e.g. ID_MMFR<n>_EL1. */ +#define SYS_SVCR_SMSTOP_SM_EL0 sys_reg(0, 3, 4, 2, 3) +#define SYS_SVCR_SMSTART_SM_EL0 sys_reg(0, 3, 4, 3, 3) +#define SYS_SVCR_SMSTOP_SMZA_EL0 sys_reg(0, 3, 4, 6, 3) + #define SYS_OSDTRRX_EL1 sys_reg(2, 0, 0, 0, 2) #define SYS_MDCCINT_EL1 sys_reg(2, 0, 0, 2, 0) #define SYS_MDSCR_EL1 sys_reg(2, 0, 0, 2, 2) @@ -181,6 +193,7 @@ #define SYS_ID_AA64PFR0_EL1 sys_reg(3, 0, 0, 4, 0) #define SYS_ID_AA64PFR1_EL1 sys_reg(3, 0, 0, 4, 1) #define SYS_ID_AA64ZFR0_EL1 sys_reg(3, 0, 0, 4, 4) +#define SYS_ID_AA64SMFR0_EL1 sys_reg(3, 0, 0, 4, 5) #define SYS_ID_AA64DFR0_EL1 sys_reg(3, 0, 0, 5, 0) #define SYS_ID_AA64DFR1_EL1 sys_reg(3, 0, 0, 5, 1) @@ -188,7 +201,6 @@ #define SYS_ID_AA64AFR0_EL1 sys_reg(3, 0, 0, 5, 4) #define SYS_ID_AA64AFR1_EL1 sys_reg(3, 0, 0, 5, 5) -#define SYS_ID_AA64ISAR0_EL1 sys_reg(3, 0, 0, 6, 0) #define SYS_ID_AA64ISAR1_EL1 sys_reg(3, 0, 0, 6, 1) #define SYS_ID_AA64ISAR2_EL1 sys_reg(3, 0, 0, 6, 2) @@ -196,17 +208,12 @@ #define SYS_ID_AA64MMFR1_EL1 sys_reg(3, 0, 0, 7, 1) #define SYS_ID_AA64MMFR2_EL1 sys_reg(3, 0, 0, 7, 2) -#define SYS_SCTLR_EL1 sys_reg(3, 0, 1, 0, 0) #define SYS_ACTLR_EL1 sys_reg(3, 0, 1, 0, 1) -#define SYS_CPACR_EL1 sys_reg(3, 0, 1, 0, 2) #define SYS_RGSR_EL1 sys_reg(3, 0, 1, 0, 5) #define SYS_GCR_EL1 sys_reg(3, 0, 1, 0, 6) -#define SYS_ZCR_EL1 sys_reg(3, 0, 1, 2, 0) #define SYS_TRFCR_EL1 sys_reg(3, 0, 1, 2, 1) -#define SYS_TTBR0_EL1 sys_reg(3, 0, 2, 0, 0) -#define SYS_TTBR1_EL1 sys_reg(3, 0, 2, 0, 1) #define SYS_TCR_EL1 sys_reg(3, 0, 2, 0, 2) #define SYS_APIAKEYLO_EL1 sys_reg(3, 0, 2, 1, 0) @@ -242,7 +249,6 @@ #define SYS_TFSR_EL1 sys_reg(3, 0, 5, 6, 0) #define SYS_TFSRE0_EL1 sys_reg(3, 0, 5, 6, 1) -#define SYS_FAR_EL1 sys_reg(3, 0, 6, 0, 0) #define SYS_PAR_EL1 sys_reg(3, 0, 7, 4, 0) #define SYS_PAR_EL1_F BIT(0) @@ -441,7 +447,6 @@ #define SYS_ICC_IGRPEN0_EL1 sys_reg(3, 0, 12, 12, 6) #define SYS_ICC_IGRPEN1_EL1 sys_reg(3, 0, 12, 12, 7) -#define SYS_CONTEXTIDR_EL1 sys_reg(3, 0, 13, 0, 1) #define SYS_TPIDR_EL1 sys_reg(3, 0, 13, 0, 4) #define SYS_SCXTNUM_EL1 sys_reg(3, 0, 13, 0, 7) @@ -449,11 +454,12 @@ #define SYS_CNTKCTL_EL1 sys_reg(3, 0, 14, 1, 0) #define SYS_CCSIDR_EL1 sys_reg(3, 1, 0, 0, 0) -#define SYS_CLIDR_EL1 sys_reg(3, 1, 0, 0, 1) #define SYS_GMID_EL1 sys_reg(3, 1, 0, 0, 4) #define SYS_AIDR_EL1 sys_reg(3, 1, 0, 0, 7) -#define SYS_CSSELR_EL1 sys_reg(3, 2, 0, 0, 0) +#define SMIDR_EL1_IMPLEMENTER_SHIFT 24 +#define SMIDR_EL1_SMPS_SHIFT 15 +#define SMIDR_EL1_AFFINITY_SHIFT 0 #define SYS_CTR_EL0 sys_reg(3, 3, 0, 0, 1) #define SYS_DCZID_EL0 sys_reg(3, 3, 0, 0, 7) @@ -477,6 +483,7 @@ #define SYS_TPIDR_EL0 sys_reg(3, 3, 13, 0, 2) #define SYS_TPIDRRO_EL0 sys_reg(3, 3, 13, 0, 3) +#define SYS_TPIDR2_EL0 sys_reg(3, 3, 13, 0, 5) #define SYS_SCXTNUM_EL0 sys_reg(3, 3, 13, 0, 7) @@ -544,9 +551,8 @@ #define SYS_HFGRTR_EL2 sys_reg(3, 4, 1, 1, 4) #define SYS_HFGWTR_EL2 sys_reg(3, 4, 1, 1, 5) #define SYS_HFGITR_EL2 sys_reg(3, 4, 1, 1, 6) -#define SYS_ZCR_EL2 sys_reg(3, 4, 1, 2, 0) #define SYS_TRFCR_EL2 sys_reg(3, 4, 1, 2, 1) -#define SYS_DACR32_EL2 sys_reg(3, 4, 3, 0, 0) +#define SYS_HCRX_EL2 sys_reg(3, 4, 1, 2, 2) #define SYS_HDFGRTR_EL2 sys_reg(3, 4, 3, 1, 4) #define SYS_HDFGWTR_EL2 sys_reg(3, 4, 3, 1, 5) #define SYS_HAFGRTR_EL2 sys_reg(3, 4, 3, 1, 6) @@ -557,7 +563,6 @@ #define SYS_VSESR_EL2 sys_reg(3, 4, 5, 2, 3) #define SYS_FPEXC32_EL2 sys_reg(3, 4, 5, 3, 0) #define SYS_TFSR_EL2 sys_reg(3, 4, 5, 6, 0) -#define SYS_FAR_EL2 sys_reg(3, 4, 6, 0, 0) #define SYS_VDISR_EL2 sys_reg(3, 4, 12, 1, 1) #define __SYS__AP0Rx_EL2(x) sys_reg(3, 4, 12, 8, x) @@ -603,8 +608,6 @@ /* VHE encodings for architectural EL0/1 system registers */ #define SYS_SCTLR_EL12 sys_reg(3, 5, 1, 0, 0) -#define SYS_CPACR_EL12 sys_reg(3, 5, 1, 0, 2) -#define SYS_ZCR_EL12 sys_reg(3, 5, 1, 2, 0) #define SYS_TTBR0_EL12 sys_reg(3, 5, 2, 0, 0) #define SYS_TTBR1_EL12 sys_reg(3, 5, 2, 0, 1) #define SYS_TCR_EL12 sys_reg(3, 5, 2, 0, 2) @@ -614,11 +617,9 @@ #define SYS_AFSR1_EL12 sys_reg(3, 5, 5, 1, 1) #define SYS_ESR_EL12 sys_reg(3, 5, 5, 2, 0) #define SYS_TFSR_EL12 sys_reg(3, 5, 5, 6, 0) -#define SYS_FAR_EL12 sys_reg(3, 5, 6, 0, 0) #define SYS_MAIR_EL12 sys_reg(3, 5, 10, 2, 0) #define SYS_AMAIR_EL12 sys_reg(3, 5, 10, 3, 0) #define SYS_VBAR_EL12 sys_reg(3, 5, 12, 0, 0) -#define SYS_CONTEXTIDR_EL12 sys_reg(3, 5, 13, 0, 1) #define SYS_CNTKCTL_EL12 sys_reg(3, 5, 14, 1, 0) #define SYS_CNTP_TVAL_EL02 sys_reg(3, 5, 14, 2, 0) #define SYS_CNTP_CTL_EL02 sys_reg(3, 5, 14, 2, 1) @@ -628,31 +629,30 @@ #define SYS_CNTV_CVAL_EL02 sys_reg(3, 5, 14, 3, 2) /* Common SCTLR_ELx flags. */ +#define SCTLR_ELx_ENTP2 (BIT(60)) #define SCTLR_ELx_DSSBS (BIT(44)) #define SCTLR_ELx_ATA (BIT(43)) -#define SCTLR_ELx_TCF_SHIFT 40 -#define SCTLR_ELx_TCF_NONE (UL(0x0) << SCTLR_ELx_TCF_SHIFT) -#define SCTLR_ELx_TCF_SYNC (UL(0x1) << SCTLR_ELx_TCF_SHIFT) -#define SCTLR_ELx_TCF_ASYNC (UL(0x2) << SCTLR_ELx_TCF_SHIFT) -#define SCTLR_ELx_TCF_ASYMM (UL(0x3) << SCTLR_ELx_TCF_SHIFT) -#define SCTLR_ELx_TCF_MASK (UL(0x3) << SCTLR_ELx_TCF_SHIFT) - #define SCTLR_ELx_ENIA_SHIFT 31 -#define SCTLR_ELx_ITFSB (BIT(37)) -#define SCTLR_ELx_ENIA (BIT(SCTLR_ELx_ENIA_SHIFT)) -#define SCTLR_ELx_ENIB (BIT(30)) -#define SCTLR_ELx_ENDA (BIT(27)) -#define SCTLR_ELx_EE (BIT(25)) -#define SCTLR_ELx_IESB (BIT(21)) -#define SCTLR_ELx_WXN (BIT(19)) -#define SCTLR_ELx_ENDB (BIT(13)) -#define SCTLR_ELx_I (BIT(12)) -#define SCTLR_ELx_SA (BIT(3)) -#define SCTLR_ELx_C (BIT(2)) -#define SCTLR_ELx_A (BIT(1)) -#define SCTLR_ELx_M (BIT(0)) +#define SCTLR_ELx_ITFSB (BIT(37)) +#define SCTLR_ELx_ENIA (BIT(SCTLR_ELx_ENIA_SHIFT)) +#define SCTLR_ELx_ENIB (BIT(30)) +#define SCTLR_ELx_LSMAOE (BIT(29)) +#define SCTLR_ELx_nTLSMD (BIT(28)) +#define SCTLR_ELx_ENDA (BIT(27)) +#define SCTLR_ELx_EE (BIT(25)) +#define SCTLR_ELx_EIS (BIT(22)) +#define SCTLR_ELx_IESB (BIT(21)) +#define SCTLR_ELx_TSCXT (BIT(20)) +#define SCTLR_ELx_WXN (BIT(19)) +#define SCTLR_ELx_ENDB (BIT(13)) +#define SCTLR_ELx_I (BIT(12)) +#define SCTLR_ELx_EOS (BIT(11)) +#define SCTLR_ELx_SA (BIT(3)) +#define SCTLR_ELx_C (BIT(2)) +#define SCTLR_ELx_A (BIT(1)) +#define SCTLR_ELx_M (BIT(0)) /* SCTLR_EL2 specific flags. */ #define SCTLR_EL2_RES1 ((BIT(4)) | (BIT(5)) | (BIT(11)) | (BIT(16)) | \ @@ -674,34 +674,6 @@ (SCTLR_EL2_RES1 | ENDIAN_SET_EL2) /* SCTLR_EL1 specific flags. */ -#define SCTLR_EL1_EPAN (BIT(57)) -#define SCTLR_EL1_ATA0 (BIT(42)) - -#define SCTLR_EL1_TCF0_SHIFT 38 -#define SCTLR_EL1_TCF0_NONE (UL(0x0) << SCTLR_EL1_TCF0_SHIFT) -#define SCTLR_EL1_TCF0_SYNC (UL(0x1) << SCTLR_EL1_TCF0_SHIFT) -#define SCTLR_EL1_TCF0_ASYNC (UL(0x2) << SCTLR_EL1_TCF0_SHIFT) -#define SCTLR_EL1_TCF0_ASYMM (UL(0x3) << SCTLR_EL1_TCF0_SHIFT) -#define SCTLR_EL1_TCF0_MASK (UL(0x3) << SCTLR_EL1_TCF0_SHIFT) - -#define SCTLR_EL1_BT1 (BIT(36)) -#define SCTLR_EL1_BT0 (BIT(35)) -#define SCTLR_EL1_UCI (BIT(26)) -#define SCTLR_EL1_E0E (BIT(24)) -#define SCTLR_EL1_SPAN (BIT(23)) -#define SCTLR_EL1_NTWE (BIT(18)) -#define SCTLR_EL1_NTWI (BIT(16)) -#define SCTLR_EL1_UCT (BIT(15)) -#define SCTLR_EL1_DZE (BIT(14)) -#define SCTLR_EL1_UMA (BIT(9)) -#define SCTLR_EL1_SED (BIT(8)) -#define SCTLR_EL1_ITD (BIT(7)) -#define SCTLR_EL1_CP15BEN (BIT(5)) -#define SCTLR_EL1_SA0 (BIT(4)) - -#define SCTLR_EL1_RES1 ((BIT(11)) | (BIT(20)) | (BIT(22)) | (BIT(28)) | \ - (BIT(29))) - #ifdef CONFIG_CPU_BIG_ENDIAN #define ENDIAN_SET_EL1 (SCTLR_EL1_E0E | SCTLR_ELx_EE) #else @@ -709,13 +681,17 @@ #endif #define INIT_SCTLR_EL1_MMU_OFF \ - (ENDIAN_SET_EL1 | SCTLR_EL1_RES1) + (ENDIAN_SET_EL1 | SCTLR_EL1_LSMAOE | SCTLR_EL1_nTLSMD | \ + SCTLR_EL1_EIS | SCTLR_EL1_TSCXT | SCTLR_EL1_EOS) #define INIT_SCTLR_EL1_MMU_ON \ - (SCTLR_ELx_M | SCTLR_ELx_C | SCTLR_ELx_SA | SCTLR_EL1_SA0 | \ - SCTLR_EL1_SED | SCTLR_ELx_I | SCTLR_EL1_DZE | SCTLR_EL1_UCT | \ - SCTLR_EL1_NTWE | SCTLR_ELx_IESB | SCTLR_EL1_SPAN | SCTLR_ELx_ITFSB | \ - ENDIAN_SET_EL1 | SCTLR_EL1_UCI | SCTLR_EL1_EPAN | SCTLR_EL1_RES1) + (SCTLR_ELx_M | SCTLR_ELx_C | SCTLR_ELx_SA | \ + SCTLR_EL1_SA0 | SCTLR_EL1_SED | SCTLR_ELx_I | \ + SCTLR_EL1_DZE | SCTLR_EL1_UCT | SCTLR_EL1_nTWE | \ + SCTLR_ELx_IESB | SCTLR_EL1_SPAN | SCTLR_ELx_ITFSB | \ + ENDIAN_SET_EL1 | SCTLR_EL1_UCI | SCTLR_EL1_EPAN | \ + SCTLR_EL1_LSMAOE | SCTLR_EL1_nTLSMD | SCTLR_EL1_EIS | \ + SCTLR_EL1_TSCXT | SCTLR_EL1_EOS) /* MAIR_ELx memory attributes (used by Linux) */ #define MAIR_ATTR_DEVICE_nGnRnE UL(0x00) @@ -728,25 +704,6 @@ /* Position the attr at the correct index */ #define MAIR_ATTRIDX(attr, idx) ((attr) << ((idx) * 8)) -/* id_aa64isar0 */ -#define ID_AA64ISAR0_RNDR_SHIFT 60 -#define ID_AA64ISAR0_TLB_SHIFT 56 -#define ID_AA64ISAR0_TS_SHIFT 52 -#define ID_AA64ISAR0_FHM_SHIFT 48 -#define ID_AA64ISAR0_DP_SHIFT 44 -#define ID_AA64ISAR0_SM4_SHIFT 40 -#define ID_AA64ISAR0_SM3_SHIFT 36 -#define ID_AA64ISAR0_SHA3_SHIFT 32 -#define ID_AA64ISAR0_RDM_SHIFT 28 -#define ID_AA64ISAR0_ATOMICS_SHIFT 20 -#define ID_AA64ISAR0_CRC32_SHIFT 16 -#define ID_AA64ISAR0_SHA2_SHIFT 12 -#define ID_AA64ISAR0_SHA1_SHIFT 8 -#define ID_AA64ISAR0_AES_SHIFT 4 - -#define ID_AA64ISAR0_TLB_RANGE_NI 0x0 -#define ID_AA64ISAR0_TLB_RANGE 0x2 - /* id_aa64isar1 */ #define ID_AA64ISAR1_I8MM_SHIFT 52 #define ID_AA64ISAR1_DGH_SHIFT 48 @@ -836,6 +793,7 @@ #define ID_AA64PFR0_ELx_32BIT_64BIT 0x2 /* id_aa64pfr1 */ +#define ID_AA64PFR1_SME_SHIFT 24 #define ID_AA64PFR1_MPAMFRAC_SHIFT 16 #define ID_AA64PFR1_RASFRAC_SHIFT 12 #define ID_AA64PFR1_MTE_SHIFT 8 @@ -846,6 +804,7 @@ #define ID_AA64PFR1_SSBS_PSTATE_ONLY 1 #define ID_AA64PFR1_SSBS_PSTATE_INSNS 2 #define ID_AA64PFR1_BT_BTI 0x1 +#define ID_AA64PFR1_SME 1 #define ID_AA64PFR1_MTE_NI 0x0 #define ID_AA64PFR1_MTE_EL0 0x1 @@ -874,6 +833,23 @@ #define ID_AA64ZFR0_AES_PMULL 0x2 #define ID_AA64ZFR0_SVEVER_SVE2 0x1 +/* id_aa64smfr0 */ +#define ID_AA64SMFR0_FA64_SHIFT 63 +#define ID_AA64SMFR0_I16I64_SHIFT 52 +#define ID_AA64SMFR0_F64F64_SHIFT 48 +#define ID_AA64SMFR0_I8I32_SHIFT 36 +#define ID_AA64SMFR0_F16F32_SHIFT 35 +#define ID_AA64SMFR0_B16F32_SHIFT 34 +#define ID_AA64SMFR0_F32F32_SHIFT 32 + +#define ID_AA64SMFR0_FA64 0x1 +#define ID_AA64SMFR0_I16I64 0x4 +#define ID_AA64SMFR0_F64F64 0x1 +#define ID_AA64SMFR0_I8I32 0x4 +#define ID_AA64SMFR0_F16F32 0x1 +#define ID_AA64SMFR0_B16F32 0x1 +#define ID_AA64SMFR0_F32F32 0x1 + /* id_aa64mmfr0 */ #define ID_AA64MMFR0_ECV_SHIFT 60 #define ID_AA64MMFR0_FGT_SHIFT 56 @@ -926,6 +902,7 @@ /* id_aa64mmfr1 */ #define ID_AA64MMFR1_ECBHB_SHIFT 60 +#define ID_AA64MMFR1_HCX_SHIFT 40 #define ID_AA64MMFR1_AFP_SHIFT 44 #define ID_AA64MMFR1_ETS_SHIFT 36 #define ID_AA64MMFR1_TWED_SHIFT 32 @@ -1110,18 +1087,12 @@ #define DCZID_DZP_SHIFT 4 #define DCZID_BS_SHIFT 0 -/* - * The ZCR_ELx_LEN_* definitions intentionally include bits [8:4] which - * are reserved by the SVE architecture for future expansion of the LEN - * field, with compatible semantics. - */ -#define ZCR_ELx_LEN_SHIFT 0 -#define ZCR_ELx_LEN_SIZE 9 -#define ZCR_ELx_LEN_MASK 0x1ff - #define CPACR_EL1_FPEN_EL1EN (BIT(20)) /* enable EL1 access */ #define CPACR_EL1_FPEN_EL0EN (BIT(21)) /* enable EL0 access, if EL1EN set */ +#define CPACR_EL1_SMEN_EL1EN (BIT(24)) /* enable EL1 access */ +#define CPACR_EL1_SMEN_EL0EN (BIT(25)) /* enable EL0 access, if EL1EN set */ + #define CPACR_EL1_ZEN_EL1EN (BIT(16)) /* enable EL1 access */ #define CPACR_EL1_ZEN_EL0EN (BIT(17)) /* enable EL0 access, if EL1EN set */ @@ -1170,6 +1141,8 @@ #define TRFCR_ELx_ExTRE BIT(1) #define TRFCR_ELx_E0TRE BIT(0) +/* HCRX_EL2 definitions */ +#define HCRX_EL2_SMPME_MASK (1 << 5) /* GIC Hypervisor interface registers */ /* ICH_MISR_EL2 bit definitions */ @@ -1233,6 +1206,12 @@ #define ICH_VTR_TDS_SHIFT 19 #define ICH_VTR_TDS_MASK (1 << ICH_VTR_TDS_SHIFT) +/* HFG[WR]TR_EL2 bit definitions */ +#define HFGxTR_EL2_nTPIDR2_EL0_SHIFT 55 +#define HFGxTR_EL2_nTPIDR2_EL0_MASK BIT_MASK(HFGxTR_EL2_nTPIDR2_EL0_SHIFT) +#define HFGxTR_EL2_nSMPRI_EL1_SHIFT 54 +#define HFGxTR_EL2_nSMPRI_EL1_MASK BIT_MASK(HFGxTR_EL2_nSMPRI_EL1_SHIFT) + #define ARM64_FEATURE_FIELD_BITS 4 /* Create a mask for the feature bits of the specified feature. */ @@ -1345,4 +1324,10 @@ #endif +#define SYS_FIELD_PREP(reg, field, val) \ + FIELD_PREP(reg##_##field##_MASK, val) + +#define SYS_FIELD_PREP_ENUM(reg, field, val) \ + FIELD_PREP(reg##_##field##_MASK, reg##_##field##_##val) + #endif /* __ASM_SYSREG_H */ diff --git a/arch/arm64/include/asm/system_misc.h b/arch/arm64/include/asm/system_misc.h index 305a7157c6a6..0eb7709422e2 100644 --- a/arch/arm64/include/asm/system_misc.h +++ b/arch/arm64/include/asm/system_misc.h @@ -23,9 +23,9 @@ void die(const char *msg, struct pt_regs *regs, int err); struct siginfo; void arm64_notify_die(const char *str, struct pt_regs *regs, int signo, int sicode, unsigned long far, - int err); + unsigned long err); -void hook_debug_fault_code(int nr, int (*fn)(unsigned long, unsigned int, +void hook_debug_fault_code(int nr, int (*fn)(unsigned long, unsigned long, struct pt_regs *), int sig, int code, const char *name); diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h index e1317b7c4525..848739c15de8 100644 --- a/arch/arm64/include/asm/thread_info.h +++ b/arch/arm64/include/asm/thread_info.h @@ -82,6 +82,8 @@ int arch_dup_task_struct(struct task_struct *dst, #define TIF_SVE_VL_INHERIT 24 /* Inherit SVE vl_onexec across exec */ #define TIF_SSBD 25 /* Wants SSB mitigation */ #define TIF_TAGGED_ADDR 26 /* Allow tagged user addresses */ +#define TIF_SME 27 /* SME in use */ +#define TIF_SME_VL_INHERIT 28 /* Inherit SME vl_onexec across exec */ #define _TIF_SIGPENDING (1 << TIF_SIGPENDING) #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) diff --git a/arch/arm64/include/asm/traps.h b/arch/arm64/include/asm/traps.h index 54f32a0675df..6e5826470bea 100644 --- a/arch/arm64/include/asm/traps.h +++ b/arch/arm64/include/asm/traps.h @@ -24,7 +24,7 @@ struct undef_hook { void register_undef_hook(struct undef_hook *hook); void unregister_undef_hook(struct undef_hook *hook); -void force_signal_inject(int signal, int code, unsigned long address, unsigned int err); +void force_signal_inject(int signal, int code, unsigned long address, unsigned long err); void arm64_notify_segfault(unsigned long addr); void arm64_force_sig_fault(int signo, int code, unsigned long far, const char *str); void arm64_force_sig_mceerr(int code, unsigned long far, short lsb, const char *str); @@ -57,7 +57,7 @@ static inline int in_entry_text(unsigned long ptr) * errors share the same encoding as an all-zeros encoding from a CPU that * doesn't support RAS. */ -static inline bool arm64_is_ras_serror(u32 esr) +static inline bool arm64_is_ras_serror(unsigned long esr) { WARN_ON(preemptible()); @@ -77,9 +77,9 @@ static inline bool arm64_is_ras_serror(u32 esr) * We treat them as Uncontainable. * Non-RAS SError's are reported as Uncontained/Uncategorized. */ -static inline u32 arm64_ras_serror_get_severity(u32 esr) +static inline unsigned long arm64_ras_serror_get_severity(unsigned long esr) { - u32 aet = esr & ESR_ELx_AET; + unsigned long aet = esr & ESR_ELx_AET; if (!arm64_is_ras_serror(esr)) { /* Not a RAS error, we can't interpret the ESR. */ @@ -98,6 +98,6 @@ static inline u32 arm64_ras_serror_get_severity(u32 esr) return aet; } -bool arm64_is_fatal_ras_serror(struct pt_regs *regs, unsigned int esr); -void __noreturn arm64_serror_panic(struct pt_regs *regs, u32 esr); +bool arm64_is_fatal_ras_serror(struct pt_regs *regs, unsigned long esr); +void __noreturn arm64_serror_panic(struct pt_regs *regs, unsigned long esr); #endif diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h index e8dce0cc5eaa..63f9c828f1a7 100644 --- a/arch/arm64/include/asm/uaccess.h +++ b/arch/arm64/include/asm/uaccess.h @@ -460,4 +460,19 @@ static inline int __copy_from_user_flushcache(void *dst, const void __user *src, } #endif +#ifdef CONFIG_ARCH_HAS_SUBPAGE_FAULTS + +/* + * Return 0 on success, the number of bytes not probed otherwise. + */ +static inline size_t probe_subpage_writeable(const char __user *uaddr, + size_t size) +{ + if (!system_supports_mte()) + return 0; + return mte_probe_user_range(uaddr, size); +} + +#endif /* CONFIG_ARCH_HAS_SUBPAGE_FAULTS */ + #endif /* __ASM_UACCESS_H */ diff --git a/arch/arm64/include/uapi/asm/hwcap.h b/arch/arm64/include/uapi/asm/hwcap.h index 99cb5d383048..b0256cec63b5 100644 --- a/arch/arm64/include/uapi/asm/hwcap.h +++ b/arch/arm64/include/uapi/asm/hwcap.h @@ -79,5 +79,13 @@ #define HWCAP2_AFP (1 << 20) #define HWCAP2_RPRES (1 << 21) #define HWCAP2_MTE3 (1 << 22) +#define HWCAP2_SME (1 << 23) +#define HWCAP2_SME_I16I64 (1 << 24) +#define HWCAP2_SME_F64F64 (1 << 25) +#define HWCAP2_SME_I8I32 (1 << 26) +#define HWCAP2_SME_F16F32 (1 << 27) +#define HWCAP2_SME_B16F32 (1 << 28) +#define HWCAP2_SME_F32F32 (1 << 29) +#define HWCAP2_SME_FA64 (1 << 30) #endif /* _UAPI__ASM_HWCAP_H */ diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h index c1b6ddc02d2f..ab585359242d 100644 --- a/arch/arm64/include/uapi/asm/kvm.h +++ b/arch/arm64/include/uapi/asm/kvm.h @@ -139,8 +139,10 @@ struct kvm_guest_debug_arch { __u64 dbg_wvr[KVM_ARM_MAX_DBG_REGS]; }; +#define KVM_DEBUG_ARCH_HSR_HIGH_VALID (1 << 0) struct kvm_debug_exit_arch { __u32 hsr; + __u32 hsr_high; /* ESR_EL2[61:32] */ __u64 far; /* used for watchpoints */ }; diff --git a/arch/arm64/include/uapi/asm/ptrace.h b/arch/arm64/include/uapi/asm/ptrace.h index 758ae984ff97..7fa2f7036aa7 100644 --- a/arch/arm64/include/uapi/asm/ptrace.h +++ b/arch/arm64/include/uapi/asm/ptrace.h @@ -109,7 +109,7 @@ struct user_hwdebug_state { } dbg_regs[16]; }; -/* SVE/FP/SIMD state (NT_ARM_SVE) */ +/* SVE/FP/SIMD state (NT_ARM_SVE & NT_ARM_SSVE) */ struct user_sve_header { __u32 size; /* total meaningful regset content in bytes */ @@ -220,6 +220,7 @@ struct user_sve_header { (SVE_PT_SVE_PREG_OFFSET(vq, __SVE_NUM_PREGS) - \ SVE_PT_SVE_PREGS_OFFSET(vq)) +/* For streaming mode SVE (SSVE) FFR must be read and written as zero */ #define SVE_PT_SVE_FFR_OFFSET(vq) \ (SVE_PT_REGS_OFFSET + __SVE_FFR_OFFSET(vq)) @@ -240,10 +241,12 @@ struct user_sve_header { - SVE_PT_SVE_OFFSET + (__SVE_VQ_BYTES - 1)) \ / __SVE_VQ_BYTES * __SVE_VQ_BYTES) -#define SVE_PT_SIZE(vq, flags) \ - (((flags) & SVE_PT_REGS_MASK) == SVE_PT_REGS_SVE ? \ - SVE_PT_SVE_OFFSET + SVE_PT_SVE_SIZE(vq, flags) \ - : SVE_PT_FPSIMD_OFFSET + SVE_PT_FPSIMD_SIZE(vq, flags)) +#define SVE_PT_SIZE(vq, flags) \ + (((flags) & SVE_PT_REGS_MASK) == SVE_PT_REGS_SVE ? \ + SVE_PT_SVE_OFFSET + SVE_PT_SVE_SIZE(vq, flags) \ + : ((((flags) & SVE_PT_REGS_MASK) == SVE_PT_REGS_FPSIMD ? \ + SVE_PT_FPSIMD_OFFSET + SVE_PT_FPSIMD_SIZE(vq, flags) \ + : SVE_PT_REGS_OFFSET))) /* pointer authentication masks (NT_ARM_PAC_MASK) */ @@ -265,6 +268,62 @@ struct user_pac_generic_keys { __uint128_t apgakey; }; +/* ZA state (NT_ARM_ZA) */ + +struct user_za_header { + __u32 size; /* total meaningful regset content in bytes */ + __u32 max_size; /* maxmium possible size for this thread */ + __u16 vl; /* current vector length */ + __u16 max_vl; /* maximum possible vector length */ + __u16 flags; + __u16 __reserved; +}; + +/* + * Common ZA_PT_* flags: + * These must be kept in sync with prctl interface in <linux/prctl.h> + */ +#define ZA_PT_VL_INHERIT ((1 << 17) /* PR_SME_VL_INHERIT */ >> 16) +#define ZA_PT_VL_ONEXEC ((1 << 18) /* PR_SME_SET_VL_ONEXEC */ >> 16) + + +/* + * The remainder of the ZA state follows struct user_za_header. The + * total size of the ZA state (including header) depends on the + * metadata in the header: ZA_PT_SIZE(vq, flags) gives the total size + * of the state in bytes, including the header. + * + * Refer to <asm/sigcontext.h> for details of how to pass the correct + * "vq" argument to these macros. + */ + +/* Offset from the start of struct user_za_header to the register data */ +#define ZA_PT_ZA_OFFSET \ + ((sizeof(struct user_za_header) + (__SVE_VQ_BYTES - 1)) \ + / __SVE_VQ_BYTES * __SVE_VQ_BYTES) + +/* + * The payload starts at offset ZA_PT_ZA_OFFSET, and is of size + * ZA_PT_ZA_SIZE(vq, flags). + * + * The ZA array is stored as a sequence of horizontal vectors ZAV of SVL/8 + * bytes each, starting from vector 0. + * + * Additional data might be appended in the future. + * + * The ZA matrix is represented in memory in an endianness-invariant layout + * which differs from the layout used for the FPSIMD V-registers on big-endian + * systems: see sigcontext.h for more explanation. + */ + +#define ZA_PT_ZAV_OFFSET(vq, n) \ + (ZA_PT_ZA_OFFSET + ((vq * __SVE_VQ_BYTES) * n)) + +#define ZA_PT_ZA_SIZE(vq) ((vq * __SVE_VQ_BYTES) * (vq * __SVE_VQ_BYTES)) + +#define ZA_PT_SIZE(vq) \ + (ZA_PT_ZA_OFFSET + ZA_PT_ZA_SIZE(vq)) + #endif /* __ASSEMBLY__ */ #endif /* _UAPI__ASM_PTRACE_H */ diff --git a/arch/arm64/include/uapi/asm/sigcontext.h b/arch/arm64/include/uapi/asm/sigcontext.h index 0c796c795dbe..4aaf31e3bf16 100644 --- a/arch/arm64/include/uapi/asm/sigcontext.h +++ b/arch/arm64/include/uapi/asm/sigcontext.h @@ -134,6 +134,17 @@ struct extra_context { struct sve_context { struct _aarch64_ctx head; __u16 vl; + __u16 flags; + __u16 __reserved[2]; +}; + +#define SVE_SIG_FLAG_SM 0x1 /* Context describes streaming mode */ + +#define ZA_MAGIC 0x54366345 + +struct za_context { + struct _aarch64_ctx head; + __u16 vl; __u16 __reserved[3]; }; @@ -186,9 +197,16 @@ struct sve_context { * sve_context.vl must equal the thread's current vector length when * doing a sigreturn. * + * On systems with support for SME the SVE register state may reflect either + * streaming or non-streaming mode. In streaming mode the streaming mode + * vector length will be used and the flag SVE_SIG_FLAG_SM will be set in + * the flags field. It is permitted to enter or leave streaming mode in + * a signal return, applications should take care to ensure that any difference + * in vector length between the two modes is handled, including any resizing + * and movement of context blocks. * - * Note: for all these macros, the "vq" argument denotes the SVE - * vector length in quadwords (i.e., units of 128 bits). + * Note: for all these macros, the "vq" argument denotes the vector length + * in quadwords (i.e., units of 128 bits). * * The correct way to obtain vq is to use sve_vq_from_vl(vl). The * result is valid if and only if sve_vl_valid(vl) is true. This is @@ -249,4 +267,37 @@ struct sve_context { #define SVE_SIG_CONTEXT_SIZE(vq) \ (SVE_SIG_REGS_OFFSET + SVE_SIG_REGS_SIZE(vq)) +/* + * If the ZA register is enabled for the thread at signal delivery then, + * za_context.head.size >= ZA_SIG_CONTEXT_SIZE(sve_vq_from_vl(za_context.vl)) + * and the register data may be accessed using the ZA_SIG_*() macros. + * + * If za_context.head.size < ZA_SIG_CONTEXT_SIZE(sve_vq_from_vl(za_context.vl)) + * then ZA was not enabled and no register data was included in which case + * ZA register was not enabled for the thread and no register data + * the ZA_SIG_*() macros should not be used except for this check. + * + * The same convention applies when returning from a signal: a caller + * will need to remove or resize the za_context block if it wants to + * enable the ZA register when it was previously non-live or vice-versa. + * This may require the caller to allocate fresh memory and/or move other + * context blocks in the signal frame. + * + * Changing the vector length during signal return is not permitted: + * za_context.vl must equal the thread's current SME vector length when + * doing a sigreturn. + */ + +#define ZA_SIG_REGS_OFFSET \ + ((sizeof(struct za_context) + (__SVE_VQ_BYTES - 1)) \ + / __SVE_VQ_BYTES * __SVE_VQ_BYTES) + +#define ZA_SIG_REGS_SIZE(vq) ((vq * __SVE_VQ_BYTES) * (vq * __SVE_VQ_BYTES)) + +#define ZA_SIG_ZAV_OFFSET(vq, n) (ZA_SIG_REGS_OFFSET + \ + (SVE_SIG_ZREG_SIZE(vq) * n)) + +#define ZA_SIG_CONTEXT_SIZE(vq) \ + (ZA_SIG_REGS_OFFSET + ZA_SIG_REGS_SIZE(vq)) + #endif /* _UAPI__ASM_SIGCONTEXT_H */ diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index 986837d7ec82..fa7981d0d917 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -75,6 +75,10 @@ obj-$(CONFIG_ARM64_MTE) += mte.o obj-y += vdso-wrap.o obj-$(CONFIG_COMPAT_VDSO) += vdso32-wrap.o +# Force dependency (vdso*-wrap.S includes vdso.so through incbin) +$(obj)/vdso-wrap.o: $(obj)/vdso/vdso.so +$(obj)/vdso32-wrap.o: $(obj)/vdso32/vdso.so + obj-y += probes/ head-y := head.o extra-y += $(head-y) vmlinux.lds diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c index 3fb79b76e9d9..7bbf5104b7b7 100644 --- a/arch/arm64/kernel/alternative.c +++ b/arch/arm64/kernel/alternative.c @@ -42,7 +42,7 @@ bool alternative_is_applied(u16 cpufeature) /* * Check if the target PC is within an alternative block. */ -static bool branch_insn_requires_update(struct alt_instr *alt, unsigned long pc) +static __always_inline bool branch_insn_requires_update(struct alt_instr *alt, unsigned long pc) { unsigned long replptr = (unsigned long)ALT_REPL_PTR(alt); return !(pc >= replptr && pc <= (replptr + alt->alt_len)); @@ -50,7 +50,7 @@ static bool branch_insn_requires_update(struct alt_instr *alt, unsigned long pc) #define align_down(x, a) ((unsigned long)(x) & ~(((unsigned long)(a)) - 1)) -static u32 get_alt_insn(struct alt_instr *alt, __le32 *insnptr, __le32 *altinsnptr) +static __always_inline u32 get_alt_insn(struct alt_instr *alt, __le32 *insnptr, __le32 *altinsnptr) { u32 insn; @@ -95,7 +95,7 @@ static u32 get_alt_insn(struct alt_instr *alt, __le32 *insnptr, __le32 *altinsnp return insn; } -static void patch_alternative(struct alt_instr *alt, +static noinstr void patch_alternative(struct alt_instr *alt, __le32 *origptr, __le32 *updptr, int nr_inst) { __le32 *replptr; diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 4c9b5b4b7a0b..c05cc3b6162e 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -208,6 +208,8 @@ static const struct arm64_cpu_capabilities arm64_repeat_tlbi_list[] = { #ifdef CONFIG_ARM64_ERRATUM_1286807 { ERRATA_MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 3, 0), + /* Kryo4xx Gold (rcpe to rfpe) => (r0p0 to r3p0) */ + ERRATA_MIDR_RANGE(MIDR_QCOM_KRYO_4XX_GOLD, 0xc, 0xe, 0xf, 0xe), }, #endif {}, @@ -215,7 +217,7 @@ static const struct arm64_cpu_capabilities arm64_repeat_tlbi_list[] = { #endif #ifdef CONFIG_CAVIUM_ERRATUM_23154 -const struct midr_range cavium_erratum_23154_cpus[] = { +static const struct midr_range cavium_erratum_23154_cpus[] = { MIDR_ALL_VERSIONS(MIDR_THUNDERX), MIDR_ALL_VERSIONS(MIDR_THUNDERX_81XX), MIDR_ALL_VERSIONS(MIDR_THUNDERX_83XX), diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index d72c4b4d389c..4ccddf382e5b 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -191,20 +191,20 @@ static bool __system_matches_cap(unsigned int n); * sync with the documentation of the CPU feature register ABI. */ static const struct arm64_ftr_bits ftr_id_aa64isar0[] = { - ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_RNDR_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_TLB_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_TS_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_FHM_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_DP_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_SM4_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_SM3_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_SHA3_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_RDM_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_ATOMICS_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_CRC32_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_SHA2_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_SHA1_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_AES_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_EL1_RNDR_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_EL1_TLB_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_EL1_TS_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_EL1_FHM_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_EL1_DP_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_EL1_SM4_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_EL1_SM3_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_EL1_SHA3_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_EL1_RDM_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_EL1_ATOMIC_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_EL1_CRC32_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_EL1_SHA2_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_EL1_SHA1_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_EL1_AES_SHIFT, 4, 0), ARM64_FTR_END, }; @@ -261,6 +261,8 @@ static const struct arm64_ftr_bits ftr_id_aa64pfr0[] = { }; static const struct arm64_ftr_bits ftr_id_aa64pfr1[] = { + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), + FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_SME_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_MPAMFRAC_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_RASFRAC_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_MTE), @@ -293,6 +295,24 @@ static const struct arm64_ftr_bits ftr_id_aa64zfr0[] = { ARM64_FTR_END, }; +static const struct arm64_ftr_bits ftr_id_aa64smfr0[] = { + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), + FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_FA64_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), + FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_I16I64_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), + FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_F64F64_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), + FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_I8I32_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), + FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_F16F32_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), + FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_B16F32_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), + FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_F32F32_SHIFT, 1, 0), + ARM64_FTR_END, +}; + static const struct arm64_ftr_bits ftr_id_aa64mmfr0[] = { ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_ECV_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_FGT_SHIFT, 4, 0), @@ -557,7 +577,13 @@ static const struct arm64_ftr_bits ftr_id_dfr1[] = { static const struct arm64_ftr_bits ftr_zcr[] = { ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, - ZCR_ELx_LEN_SHIFT, ZCR_ELx_LEN_SIZE, 0), /* LEN */ + ZCR_ELx_LEN_SHIFT, ZCR_ELx_LEN_WIDTH, 0), /* LEN */ + ARM64_FTR_END, +}; + +static const struct arm64_ftr_bits ftr_smcr[] = { + ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, + SMCR_ELx_LEN_SHIFT, SMCR_ELx_LEN_WIDTH, 0), /* LEN */ ARM64_FTR_END, }; @@ -645,6 +671,7 @@ static const struct __ftr_reg_entry { ARM64_FTR_REG_OVERRIDE(SYS_ID_AA64PFR1_EL1, ftr_id_aa64pfr1, &id_aa64pfr1_override), ARM64_FTR_REG(SYS_ID_AA64ZFR0_EL1, ftr_id_aa64zfr0), + ARM64_FTR_REG(SYS_ID_AA64SMFR0_EL1, ftr_id_aa64smfr0), /* Op1 = 0, CRn = 0, CRm = 5 */ ARM64_FTR_REG(SYS_ID_AA64DFR0_EL1, ftr_id_aa64dfr0), @@ -654,7 +681,6 @@ static const struct __ftr_reg_entry { ARM64_FTR_REG(SYS_ID_AA64ISAR0_EL1, ftr_id_aa64isar0), ARM64_FTR_REG_OVERRIDE(SYS_ID_AA64ISAR1_EL1, ftr_id_aa64isar1, &id_aa64isar1_override), - ARM64_FTR_REG(SYS_ID_AA64ISAR2_EL1, ftr_id_aa64isar2), ARM64_FTR_REG_OVERRIDE(SYS_ID_AA64ISAR2_EL1, ftr_id_aa64isar2, &id_aa64isar2_override), @@ -666,6 +692,7 @@ static const struct __ftr_reg_entry { /* Op1 = 0, CRn = 1, CRm = 2 */ ARM64_FTR_REG(SYS_ZCR_EL1, ftr_zcr), + ARM64_FTR_REG(SYS_SMCR_EL1, ftr_smcr), /* Op1 = 1, CRn = 0, CRm = 0 */ ARM64_FTR_REG(SYS_GMID_EL1, ftr_gmid), @@ -810,7 +837,7 @@ static void __init sort_ftr_regs(void) * to sys_id for subsequent binary search in get_arm64_ftr_reg() * to work correctly. */ - BUG_ON(arm64_ftr_regs[i].sys_id < arm64_ftr_regs[i - 1].sys_id); + BUG_ON(arm64_ftr_regs[i].sys_id <= arm64_ftr_regs[i - 1].sys_id); } } @@ -960,6 +987,7 @@ void __init init_cpu_features(struct cpuinfo_arm64 *info) init_cpu_ftr_reg(SYS_ID_AA64PFR0_EL1, info->reg_id_aa64pfr0); init_cpu_ftr_reg(SYS_ID_AA64PFR1_EL1, info->reg_id_aa64pfr1); init_cpu_ftr_reg(SYS_ID_AA64ZFR0_EL1, info->reg_id_aa64zfr0); + init_cpu_ftr_reg(SYS_ID_AA64SMFR0_EL1, info->reg_id_aa64smfr0); if (id_aa64pfr0_32bit_el0(info->reg_id_aa64pfr0)) init_32bit_cpu_features(&info->aarch32); @@ -969,6 +997,12 @@ void __init init_cpu_features(struct cpuinfo_arm64 *info) vec_init_vq_map(ARM64_VEC_SVE); } + if (id_aa64pfr1_sme(info->reg_id_aa64pfr1)) { + init_cpu_ftr_reg(SYS_SMCR_EL1, info->reg_smcr); + if (IS_ENABLED(CONFIG_ARM64_SME)) + vec_init_vq_map(ARM64_VEC_SME); + } + if (id_aa64pfr1_mte(info->reg_id_aa64pfr1)) init_cpu_ftr_reg(SYS_GMID_EL1, info->reg_gmid); @@ -1195,6 +1229,9 @@ void update_cpu_features(int cpu, taint |= check_update_ftr_reg(SYS_ID_AA64ZFR0_EL1, cpu, info->reg_id_aa64zfr0, boot->reg_id_aa64zfr0); + taint |= check_update_ftr_reg(SYS_ID_AA64SMFR0_EL1, cpu, + info->reg_id_aa64smfr0, boot->reg_id_aa64smfr0); + if (id_aa64pfr0_sve(info->reg_id_aa64pfr0)) { taint |= check_update_ftr_reg(SYS_ZCR_EL1, cpu, info->reg_zcr, boot->reg_zcr); @@ -1205,6 +1242,16 @@ void update_cpu_features(int cpu, vec_update_vq_map(ARM64_VEC_SVE); } + if (id_aa64pfr1_sme(info->reg_id_aa64pfr1)) { + taint |= check_update_ftr_reg(SYS_SMCR_EL1, cpu, + info->reg_smcr, boot->reg_smcr); + + /* Probe vector lengths, unless we already gave up on SME */ + if (id_aa64pfr1_sme(read_sanitised_ftr_reg(SYS_ID_AA64PFR1_EL1)) && + !system_capabilities_finalized()) + vec_update_vq_map(ARM64_VEC_SME); + } + /* * The kernel uses the LDGM/STGM instructions and the number of tags * they read/write depends on the GMID_EL1.BS field. Check that the @@ -1288,6 +1335,7 @@ u64 __read_sysreg_by_encoding(u32 sys_id) read_sysreg_case(SYS_ID_AA64PFR0_EL1); read_sysreg_case(SYS_ID_AA64PFR1_EL1); read_sysreg_case(SYS_ID_AA64ZFR0_EL1); + read_sysreg_case(SYS_ID_AA64SMFR0_EL1); read_sysreg_case(SYS_ID_AA64DFR0_EL1); read_sysreg_case(SYS_ID_AA64DFR1_EL1); read_sysreg_case(SYS_ID_AA64MMFR0_EL1); @@ -2013,7 +2061,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_cpuid_feature, .sys_reg = SYS_ID_AA64ISAR0_EL1, - .field_pos = ID_AA64ISAR0_ATOMICS_SHIFT, + .field_pos = ID_AA64ISAR0_EL1_ATOMIC_SHIFT, .field_width = 4, .sign = FTR_UNSIGNED, .min_field_value = 2, @@ -2195,10 +2243,10 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_cpuid_feature, .sys_reg = SYS_ID_AA64ISAR0_EL1, - .field_pos = ID_AA64ISAR0_TLB_SHIFT, + .field_pos = ID_AA64ISAR0_EL1_TLB_SHIFT, .field_width = 4, .sign = FTR_UNSIGNED, - .min_field_value = ID_AA64ISAR0_TLB_RANGE, + .min_field_value = ID_AA64ISAR0_EL1_TLB_RANGE, }, #ifdef CONFIG_ARM64_HW_AFDBM { @@ -2227,7 +2275,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_cpuid_feature, .sys_reg = SYS_ID_AA64ISAR0_EL1, - .field_pos = ID_AA64ISAR0_CRC32_SHIFT, + .field_pos = ID_AA64ISAR0_EL1_CRC32_SHIFT, .field_width = 4, .min_field_value = 1, }, @@ -2382,7 +2430,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_cpuid_feature, .sys_reg = SYS_ID_AA64ISAR0_EL1, - .field_pos = ID_AA64ISAR0_RNDR_SHIFT, + .field_pos = ID_AA64ISAR0_EL1_RNDR_SHIFT, .field_width = 4, .sign = FTR_UNSIGNED, .min_field_value = 1, @@ -2442,6 +2490,33 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .matches = has_cpuid_feature, .min_field_value = 1, }, +#ifdef CONFIG_ARM64_SME + { + .desc = "Scalable Matrix Extension", + .type = ARM64_CPUCAP_SYSTEM_FEATURE, + .capability = ARM64_SME, + .sys_reg = SYS_ID_AA64PFR1_EL1, + .sign = FTR_UNSIGNED, + .field_pos = ID_AA64PFR1_SME_SHIFT, + .field_width = 4, + .min_field_value = ID_AA64PFR1_SME, + .matches = has_cpuid_feature, + .cpu_enable = sme_kernel_enable, + }, + /* FA64 should be sorted after the base SME capability */ + { + .desc = "FA64", + .type = ARM64_CPUCAP_SYSTEM_FEATURE, + .capability = ARM64_SME_FA64, + .sys_reg = SYS_ID_AA64SMFR0_EL1, + .sign = FTR_UNSIGNED, + .field_pos = ID_AA64SMFR0_FA64_SHIFT, + .field_width = 1, + .min_field_value = ID_AA64SMFR0_FA64, + .matches = has_cpuid_feature, + .cpu_enable = fa64_kernel_enable, + }, +#endif /* CONFIG_ARM64_SME */ {}, }; @@ -2514,22 +2589,22 @@ static const struct arm64_cpu_capabilities ptr_auth_hwcap_gen_matches[] = { #endif static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { - HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_AES_SHIFT, 4, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_PMULL), - HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_AES_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_AES), - HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA1_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SHA1), - HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA2_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SHA2), - HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA2_SHIFT, 4, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_SHA512), - HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_CRC32_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_CRC32), - HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_ATOMICS_SHIFT, 4, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_ATOMICS), - HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_RDM_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ASIMDRDM), - HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA3_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SHA3), - HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SM3_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SM3), - HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SM4_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SM4), - HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_DP_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ASIMDDP), - HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_FHM_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ASIMDFHM), - HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_TS_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_FLAGM), - HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_TS_SHIFT, 4, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_FLAGM2), - HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_RNDR_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_RNG), + HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_AES_SHIFT, 4, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_PMULL), + HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_AES_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_AES), + HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_SHA1_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SHA1), + HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_SHA2_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SHA2), + HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_SHA2_SHIFT, 4, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_SHA512), + HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_CRC32_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_CRC32), + HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_ATOMIC_SHIFT, 4, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_ATOMICS), + HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_RDM_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ASIMDRDM), + HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_SHA3_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SHA3), + HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_SM3_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SM3), + HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_SM4_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SM4), + HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_DP_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ASIMDDP), + HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_FHM_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ASIMDFHM), + HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_TS_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_FLAGM), + HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_TS_SHIFT, 4, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_FLAGM2), + HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_RNDR_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_RNG), HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_FP_SHIFT, 4, FTR_SIGNED, 0, CAP_HWCAP, KERNEL_HWCAP_FP), HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_FP_SHIFT, 4, FTR_SIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_FPHP), HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_ASIMD_SHIFT, 4, FTR_SIGNED, 0, CAP_HWCAP, KERNEL_HWCAP_ASIMD), @@ -2575,6 +2650,16 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(SYS_ID_AA64MMFR0_EL1, ID_AA64MMFR0_ECV_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ECV), HWCAP_CAP(SYS_ID_AA64MMFR1_EL1, ID_AA64MMFR1_AFP_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_AFP), HWCAP_CAP(SYS_ID_AA64ISAR2_EL1, ID_AA64ISAR2_RPRES_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_RPRES), +#ifdef CONFIG_ARM64_SME + HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_SME_SHIFT, 4, FTR_UNSIGNED, ID_AA64PFR1_SME, CAP_HWCAP, KERNEL_HWCAP_SME), + HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_FA64_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_FA64, CAP_HWCAP, KERNEL_HWCAP_SME_FA64), + HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_I16I64_SHIFT, 4, FTR_UNSIGNED, ID_AA64SMFR0_I16I64, CAP_HWCAP, KERNEL_HWCAP_SME_I16I64), + HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_F64F64_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_F64F64, CAP_HWCAP, KERNEL_HWCAP_SME_F64F64), + HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_I8I32_SHIFT, 4, FTR_UNSIGNED, ID_AA64SMFR0_I8I32, CAP_HWCAP, KERNEL_HWCAP_SME_I8I32), + HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_F16F32_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_F16F32, CAP_HWCAP, KERNEL_HWCAP_SME_F16F32), + HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_B16F32_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_B16F32, CAP_HWCAP, KERNEL_HWCAP_SME_B16F32), + HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_F32F32_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_F32F32, CAP_HWCAP, KERNEL_HWCAP_SME_F32F32), +#endif /* CONFIG_ARM64_SME */ {}, }; @@ -2872,6 +2957,23 @@ static void verify_sve_features(void) /* Add checks on other ZCR bits here if necessary */ } +static void verify_sme_features(void) +{ + u64 safe_smcr = read_sanitised_ftr_reg(SYS_SMCR_EL1); + u64 smcr = read_smcr_features(); + + unsigned int safe_len = safe_smcr & SMCR_ELx_LEN_MASK; + unsigned int len = smcr & SMCR_ELx_LEN_MASK; + + if (len < safe_len || vec_verify_vq_map(ARM64_VEC_SME)) { + pr_crit("CPU%d: SME: vector length support mismatch\n", + smp_processor_id()); + cpu_die_early(); + } + + /* Add checks on other SMCR bits here if necessary */ +} + static void verify_hyp_capabilities(void) { u64 safe_mmfr1, mmfr0, mmfr1; @@ -2924,6 +3026,9 @@ static void verify_local_cpu_capabilities(void) if (system_supports_sve()) verify_sve_features(); + if (system_supports_sme()) + verify_sme_features(); + if (is_hyp_mode_available()) verify_hyp_capabilities(); } @@ -3041,6 +3146,7 @@ void __init setup_cpu_features(void) pr_info("emulated: Privileged Access Never (PAN) using TTBR0_EL1 switching\n"); sve_setup(); + sme_setup(); minsigstksz_setup(); /* Advertise that we have computed the system capabilities */ diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c index 330b92ea863a..8a8136a096ac 100644 --- a/arch/arm64/kernel/cpuinfo.c +++ b/arch/arm64/kernel/cpuinfo.c @@ -98,6 +98,14 @@ static const char *const hwcap_str[] = { [KERNEL_HWCAP_AFP] = "afp", [KERNEL_HWCAP_RPRES] = "rpres", [KERNEL_HWCAP_MTE3] = "mte3", + [KERNEL_HWCAP_SME] = "sme", + [KERNEL_HWCAP_SME_I16I64] = "smei16i64", + [KERNEL_HWCAP_SME_F64F64] = "smef64f64", + [KERNEL_HWCAP_SME_I8I32] = "smei8i32", + [KERNEL_HWCAP_SME_F16F32] = "smef16f32", + [KERNEL_HWCAP_SME_B16F32] = "smeb16f32", + [KERNEL_HWCAP_SME_F32F32] = "smef32f32", + [KERNEL_HWCAP_SME_FA64] = "smefa64", }; #ifdef CONFIG_COMPAT @@ -401,6 +409,7 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info) info->reg_id_aa64pfr0 = read_cpuid(ID_AA64PFR0_EL1); info->reg_id_aa64pfr1 = read_cpuid(ID_AA64PFR1_EL1); info->reg_id_aa64zfr0 = read_cpuid(ID_AA64ZFR0_EL1); + info->reg_id_aa64smfr0 = read_cpuid(ID_AA64SMFR0_EL1); if (id_aa64pfr1_mte(info->reg_id_aa64pfr1)) info->reg_gmid = read_cpuid(GMID_EL1); @@ -412,6 +421,10 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info) id_aa64pfr0_sve(info->reg_id_aa64pfr0)) info->reg_zcr = read_zcr_features(); + if (IS_ENABLED(CONFIG_ARM64_SME) && + id_aa64pfr1_sme(info->reg_id_aa64pfr1)) + info->reg_smcr = read_smcr_features(); + cpuinfo_detect_icache_policy(info); } diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c index 4f3661eeb7ec..bf9fe71589bc 100644 --- a/arch/arm64/kernel/debug-monitors.c +++ b/arch/arm64/kernel/debug-monitors.c @@ -202,7 +202,7 @@ void unregister_kernel_step_hook(struct step_hook *hook) * So we call all the registered handlers, until the right handler is * found which returns zero. */ -static int call_step_hook(struct pt_regs *regs, unsigned int esr) +static int call_step_hook(struct pt_regs *regs, unsigned long esr) { struct step_hook *hook; struct list_head *list; @@ -238,7 +238,7 @@ static void send_user_sigtrap(int si_code) "User debug trap"); } -static int single_step_handler(unsigned long unused, unsigned int esr, +static int single_step_handler(unsigned long unused, unsigned long esr, struct pt_regs *regs) { bool handler_found = false; @@ -299,11 +299,11 @@ void unregister_kernel_break_hook(struct break_hook *hook) unregister_debug_hook(&hook->node); } -static int call_break_hook(struct pt_regs *regs, unsigned int esr) +static int call_break_hook(struct pt_regs *regs, unsigned long esr) { struct break_hook *hook; struct list_head *list; - int (*fn)(struct pt_regs *regs, unsigned int esr) = NULL; + int (*fn)(struct pt_regs *regs, unsigned long esr) = NULL; list = user_mode(regs) ? &user_break_hook : &kernel_break_hook; @@ -312,7 +312,7 @@ static int call_break_hook(struct pt_regs *regs, unsigned int esr) * entirely not preemptible, and we can use rcu list safely here. */ list_for_each_entry_rcu(hook, list, node) { - unsigned int comment = esr & ESR_ELx_BRK64_ISS_COMMENT_MASK; + unsigned long comment = esr & ESR_ELx_BRK64_ISS_COMMENT_MASK; if ((comment & ~hook->mask) == hook->imm) fn = hook->fn; @@ -322,7 +322,7 @@ static int call_break_hook(struct pt_regs *regs, unsigned int esr) } NOKPROBE_SYMBOL(call_break_hook); -static int brk_handler(unsigned long unused, unsigned int esr, +static int brk_handler(unsigned long unused, unsigned long esr, struct pt_regs *regs) { if (call_break_hook(regs, esr) == DBG_HOOK_HANDLED) diff --git a/arch/arm64/kernel/elfcore.c b/arch/arm64/kernel/elfcore.c index 3ed39c61a510..98d67444a5b6 100644 --- a/arch/arm64/kernel/elfcore.c +++ b/arch/arm64/kernel/elfcore.c @@ -8,16 +8,9 @@ #include <asm/cpufeature.h> #include <asm/mte.h> -#ifndef VMA_ITERATOR -#define VMA_ITERATOR(name, mm, addr) \ - struct mm_struct *name = mm -#define for_each_vma(vmi, vma) \ - for (vma = vmi->mmap; vma; vma = vma->vm_next) -#endif - -#define for_each_mte_vma(vmi, vma) \ +#define for_each_mte_vma(tsk, vma) \ if (system_supports_mte()) \ - for_each_vma(vmi, vma) \ + for (vma = tsk->mm->mmap; vma; vma = vma->vm_next) \ if (vma->vm_flags & VM_MTE) static unsigned long mte_vma_tag_dump_size(struct vm_area_struct *vma) @@ -32,10 +25,11 @@ static unsigned long mte_vma_tag_dump_size(struct vm_area_struct *vma) static int mte_dump_tag_range(struct coredump_params *cprm, unsigned long start, unsigned long end) { + int ret = 1; unsigned long addr; + void *tags = NULL; for (addr = start; addr < end; addr += PAGE_SIZE) { - char tags[MTE_PAGE_TAG_STORAGE]; struct page *page = get_dump_page(addr); /* @@ -59,22 +53,36 @@ static int mte_dump_tag_range(struct coredump_params *cprm, continue; } + if (!tags) { + tags = mte_allocate_tag_storage(); + if (!tags) { + put_page(page); + ret = 0; + break; + } + } + mte_save_page_tags(page_address(page), tags); put_page(page); - if (!dump_emit(cprm, tags, MTE_PAGE_TAG_STORAGE)) - return 0; + if (!dump_emit(cprm, tags, MTE_PAGE_TAG_STORAGE)) { + mte_free_tag_storage(tags); + ret = 0; + break; + } } - return 1; + if (tags) + mte_free_tag_storage(tags); + + return ret; } Elf_Half elf_core_extra_phdrs(void) { struct vm_area_struct *vma; int vma_count = 0; - VMA_ITERATOR(vmi, current->mm, 0); - for_each_mte_vma(vmi, vma) + for_each_mte_vma(current, vma) vma_count++; return vma_count; @@ -83,12 +91,11 @@ Elf_Half elf_core_extra_phdrs(void) int elf_core_write_extra_phdrs(struct coredump_params *cprm, loff_t offset) { struct vm_area_struct *vma; - VMA_ITERATOR(vmi, current->mm, 0); - for_each_mte_vma(vmi, vma) { + for_each_mte_vma(current, vma) { struct elf_phdr phdr; - phdr.p_type = PT_ARM_MEMTAG_MTE; + phdr.p_type = PT_AARCH64_MEMTAG_MTE; phdr.p_offset = offset; phdr.p_vaddr = vma->vm_start; phdr.p_paddr = 0; @@ -109,9 +116,8 @@ size_t elf_core_extra_data_size(void) { struct vm_area_struct *vma; size_t data_size = 0; - VMA_ITERATOR(vmi, current->mm, 0); - for_each_mte_vma(vmi, vma) + for_each_mte_vma(current, vma) data_size += mte_vma_tag_dump_size(vma); return data_size; @@ -120,9 +126,8 @@ size_t elf_core_extra_data_size(void) int elf_core_write_extra_data(struct coredump_params *cprm) { struct vm_area_struct *vma; - VMA_ITERATOR(vmi, current->mm, 0); - for_each_mte_vma(vmi, vma) { + for_each_mte_vma(current, vma) { if (vma->vm_flags & VM_DONTDUMP) continue; diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c index 878c65aa7206..56cefd33eb8e 100644 --- a/arch/arm64/kernel/entry-common.c +++ b/arch/arm64/kernel/entry-common.c @@ -75,7 +75,7 @@ static __always_inline void __exit_to_kernel_mode(struct pt_regs *regs) if (interrupts_enabled(regs)) { if (regs->exit_rcu) { trace_hardirqs_on_prepare(); - lockdep_hardirqs_on_prepare(CALLER_ADDR0); + lockdep_hardirqs_on_prepare(); rcu_irq_exit(); lockdep_hardirqs_on(CALLER_ADDR0); return; @@ -121,7 +121,7 @@ static __always_inline void enter_from_user_mode(struct pt_regs *regs) static __always_inline void __exit_to_user_mode(void) { trace_hardirqs_on_prepare(); - lockdep_hardirqs_on_prepare(CALLER_ADDR0); + lockdep_hardirqs_on_prepare(); user_enter_irqoff(); lockdep_hardirqs_on(CALLER_ADDR0); } @@ -179,7 +179,7 @@ static void noinstr arm64_exit_nmi(struct pt_regs *regs) ftrace_nmi_exit(); if (restore) { trace_hardirqs_on_prepare(); - lockdep_hardirqs_on_prepare(CALLER_ADDR0); + lockdep_hardirqs_on_prepare(); } rcu_nmi_exit(); @@ -215,7 +215,7 @@ static void noinstr arm64_exit_el1_dbg(struct pt_regs *regs) if (restore) { trace_hardirqs_on_prepare(); - lockdep_hardirqs_on_prepare(CALLER_ADDR0); + lockdep_hardirqs_on_prepare(); } rcu_nmi_exit(); @@ -282,13 +282,13 @@ extern void (*handle_arch_irq)(struct pt_regs *); extern void (*handle_arch_fiq)(struct pt_regs *); static void noinstr __panic_unhandled(struct pt_regs *regs, const char *vector, - unsigned int esr) + unsigned long esr) { arm64_enter_nmi(regs); console_verbose(); - pr_crit("Unhandled %s exception on CPU%d, ESR 0x%08x -- %s\n", + pr_crit("Unhandled %s exception on CPU%d, ESR 0x%016lx -- %s\n", vector, smp_processor_id(), esr, esr_get_class_string(esr)); @@ -537,6 +537,14 @@ static void noinstr el0_sve_acc(struct pt_regs *regs, unsigned long esr) exit_to_user_mode(regs); } +static void noinstr el0_sme_acc(struct pt_regs *regs, unsigned long esr) +{ + enter_from_user_mode(regs); + local_daif_restore(DAIF_PROCCTX); + do_sme_acc(esr, regs); + exit_to_user_mode(regs); +} + static void noinstr el0_fpsimd_exc(struct pt_regs *regs, unsigned long esr) { enter_from_user_mode(regs); @@ -645,6 +653,9 @@ asmlinkage void noinstr el0t_64_sync_handler(struct pt_regs *regs) case ESR_ELx_EC_SVE: el0_sve_acc(regs, esr); break; + case ESR_ELx_EC_SME: + el0_sme_acc(regs, esr); + break; case ESR_ELx_EC_FP_EXC64: el0_fpsimd_exc(regs, esr); break; @@ -818,7 +829,7 @@ UNHANDLED(el0t, 32, error) #ifdef CONFIG_VMAP_STACK asmlinkage void noinstr handle_bad_stack(struct pt_regs *regs) { - unsigned int esr = read_sysreg(esr_el1); + unsigned long esr = read_sysreg(esr_el1); unsigned long far = read_sysreg(far_el1); arm64_enter_nmi(regs); diff --git a/arch/arm64/kernel/entry-fpsimd.S b/arch/arm64/kernel/entry-fpsimd.S index dc242e269f9a..229436f33df5 100644 --- a/arch/arm64/kernel/entry-fpsimd.S +++ b/arch/arm64/kernel/entry-fpsimd.S @@ -86,3 +86,39 @@ SYM_FUNC_START(sve_flush_live) SYM_FUNC_END(sve_flush_live) #endif /* CONFIG_ARM64_SVE */ + +#ifdef CONFIG_ARM64_SME + +SYM_FUNC_START(sme_get_vl) + _sme_rdsvl 0, 1 + ret +SYM_FUNC_END(sme_get_vl) + +SYM_FUNC_START(sme_set_vq) + sme_load_vq x0, x1, x2 + ret +SYM_FUNC_END(sme_set_vq) + +/* + * Save the SME state + * + * x0 - pointer to buffer for state + */ +SYM_FUNC_START(za_save_state) + _sme_rdsvl 1, 1 // x1 = VL/8 + sme_save_za 0, x1, 12 + ret +SYM_FUNC_END(za_save_state) + +/* + * Load the SME state + * + * x0 - pointer to buffer for state + */ +SYM_FUNC_START(za_load_state) + _sme_rdsvl 1, 1 // x1 = VL/8 + sme_load_za 0, x1, 12 + ret +SYM_FUNC_END(za_load_state) + +#endif /* CONFIG_ARM64_SME */ diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S index e535480a4069..d42a205ef625 100644 --- a/arch/arm64/kernel/entry-ftrace.S +++ b/arch/arm64/kernel/entry-ftrace.S @@ -97,12 +97,6 @@ SYM_CODE_START(ftrace_common) SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL) bl ftrace_stub -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -SYM_INNER_LABEL(ftrace_graph_call, SYM_L_GLOBAL) // ftrace_graph_caller(); - nop // If enabled, this will be replaced - // "b ftrace_graph_caller" -#endif - /* * At the callsite x0-x8 and x19-x30 were live. Any C code will have preserved * x19-x29 per the AAPCS, and we created frame records upon entry, so we need @@ -127,17 +121,6 @@ ftrace_common_return: ret x9 SYM_CODE_END(ftrace_common) -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -SYM_CODE_START(ftrace_graph_caller) - ldr x0, [sp, #S_PC] - sub x0, x0, #AARCH64_INSN_SIZE // ip (callsite's BL insn) - add x1, sp, #S_LR // parent_ip (callsite's LR) - ldr x2, [sp, #PT_REGS_SIZE] // parent fp (callsite's FP) - bl prepare_ftrace_return - b ftrace_common_return -SYM_CODE_END(ftrace_graph_caller) -#endif - #else /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */ /* diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index ede028dee81b..5b82b9292400 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -596,7 +596,7 @@ SYM_CODE_START_LOCAL(ret_to_user) ldr x19, [tsk, #TSK_TI_FLAGS] // re-check for single-step enable_step_tsk x19, x2 #ifdef CONFIG_GCC_PLUGIN_STACKLEAK - bl stackleak_erase + bl stackleak_erase_on_task_stack #endif kernel_exit 0 SYM_CODE_END(ret_to_user) diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 47af76e53221..819979398127 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -121,7 +121,10 @@ struct fpsimd_last_state_struct { struct user_fpsimd_state *st; void *sve_state; + void *za_state; + u64 *svcr; unsigned int sve_vl; + unsigned int sme_vl; }; static DEFINE_PER_CPU(struct fpsimd_last_state_struct, fpsimd_last_state); @@ -136,6 +139,12 @@ __ro_after_init struct vl_info vl_info[ARM64_VEC_MAX] = { .max_virtualisable_vl = SVE_VL_MIN, }, #endif +#ifdef CONFIG_ARM64_SME + [ARM64_VEC_SME] = { + .type = ARM64_VEC_SME, + .name = "SME", + }, +#endif }; static unsigned int vec_vl_inherit_flag(enum vec_type type) @@ -143,6 +152,8 @@ static unsigned int vec_vl_inherit_flag(enum vec_type type) switch (type) { case ARM64_VEC_SVE: return TIF_SVE_VL_INHERIT; + case ARM64_VEC_SME: + return TIF_SME_VL_INHERIT; default: WARN_ON_ONCE(1); return 0; @@ -186,6 +197,26 @@ extern void __percpu *efi_sve_state; #endif /* ! CONFIG_ARM64_SVE */ +#ifdef CONFIG_ARM64_SME + +static int get_sme_default_vl(void) +{ + return get_default_vl(ARM64_VEC_SME); +} + +static void set_sme_default_vl(int val) +{ + set_default_vl(ARM64_VEC_SME, val); +} + +static void sme_free(struct task_struct *); + +#else + +static inline void sme_free(struct task_struct *t) { } + +#endif + DEFINE_PER_CPU(bool, fpsimd_context_busy); EXPORT_PER_CPU_SYMBOL(fpsimd_context_busy); @@ -206,10 +237,19 @@ static void __get_cpu_fpsimd_context(void) * * The double-underscore version must only be called if you know the task * can't be preempted. + * + * On RT kernels local_bh_disable() is not sufficient because it only + * serializes soft interrupt related sections via a local lock, but stays + * preemptible. Disabling preemption is the right choice here as bottom + * half processing is always in thread context on RT kernels so it + * implicitly prevents bottom half processing as well. */ static void get_cpu_fpsimd_context(void) { - local_bh_disable(); + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + local_bh_disable(); + else + preempt_disable(); __get_cpu_fpsimd_context(); } @@ -230,7 +270,10 @@ static void __put_cpu_fpsimd_context(void) static void put_cpu_fpsimd_context(void) { __put_cpu_fpsimd_context(); - local_bh_enable(); + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + local_bh_enable(); + else + preempt_enable(); } static bool have_cpu_fpsimd_context(void) @@ -238,23 +281,6 @@ static bool have_cpu_fpsimd_context(void) return !preemptible() && __this_cpu_read(fpsimd_context_busy); } -/* - * Call __sve_free() directly only if you know task can't be scheduled - * or preempted. - */ -static void __sve_free(struct task_struct *task) -{ - kfree(task->thread.sve_state); - task->thread.sve_state = NULL; -} - -static void sve_free(struct task_struct *task) -{ - WARN_ON(test_tsk_thread_flag(task, TIF_SVE)); - - __sve_free(task); -} - unsigned int task_get_vl(const struct task_struct *task, enum vec_type type) { return task->thread.vl[type]; @@ -279,16 +305,27 @@ void task_set_vl_onexec(struct task_struct *task, enum vec_type type, } /* + * TIF_SME controls whether a task can use SME without trapping while + * in userspace, when TIF_SME is set then we must have storage + * alocated in sve_state and za_state to store the contents of both ZA + * and the SVE registers for both streaming and non-streaming modes. + * + * If both SVCR.ZA and SVCR.SM are disabled then at any point we + * may disable TIF_SME and reenable traps. + */ + + +/* * TIF_SVE controls whether a task can use SVE without trapping while - * in userspace, and also the way a task's FPSIMD/SVE state is stored - * in thread_struct. + * in userspace, and also (together with TIF_SME) the way a task's + * FPSIMD/SVE state is stored in thread_struct. * * The kernel uses this flag to track whether a user task is actively * using SVE, and therefore whether full SVE register state needs to * be tracked. If not, the cheaper FPSIMD context handling code can * be used instead of the more costly SVE equivalents. * - * * TIF_SVE set: + * * TIF_SVE or SVCR.SM set: * * The task can execute SVE instructions while in userspace without * trapping to the kernel. @@ -296,7 +333,8 @@ void task_set_vl_onexec(struct task_struct *task, enum vec_type type, * When stored, Z0-Z31 (incorporating Vn in bits[127:0] or the * corresponding Zn), P0-P15 and FFR are encoded in in * task->thread.sve_state, formatted appropriately for vector - * length task->thread.sve_vl. + * length task->thread.sve_vl or, if SVCR.SM is set, + * task->thread.sme_vl. * * task->thread.sve_state must point to a valid buffer at least * sve_state_size(task) bytes in size. @@ -334,16 +372,44 @@ void task_set_vl_onexec(struct task_struct *task, enum vec_type type, */ static void task_fpsimd_load(void) { + bool restore_sve_regs = false; + bool restore_ffr; + WARN_ON(!system_supports_fpsimd()); WARN_ON(!have_cpu_fpsimd_context()); + /* Check if we should restore SVE first */ if (IS_ENABLED(CONFIG_ARM64_SVE) && test_thread_flag(TIF_SVE)) { sve_set_vq(sve_vq_from_vl(task_get_sve_vl(current)) - 1); + restore_sve_regs = true; + restore_ffr = true; + } + + /* Restore SME, override SVE register configuration if needed */ + if (system_supports_sme()) { + unsigned long sme_vl = task_get_sme_vl(current); + + /* Ensure VL is set up for restoring data */ + if (test_thread_flag(TIF_SME)) + sme_set_vq(sve_vq_from_vl(sme_vl) - 1); + + write_sysreg_s(current->thread.svcr, SYS_SVCR); + + if (thread_za_enabled(¤t->thread)) + za_load_state(current->thread.za_state); + + if (thread_sm_enabled(¤t->thread)) { + restore_sve_regs = true; + restore_ffr = system_supports_fa64(); + } + } + + if (restore_sve_regs) sve_load_state(sve_pffr(¤t->thread), - ¤t->thread.uw.fpsimd_state.fpsr, true); - } else { + ¤t->thread.uw.fpsimd_state.fpsr, + restore_ffr); + else fpsimd_load_state(¤t->thread.uw.fpsimd_state); - } } /* @@ -361,6 +427,9 @@ static void fpsimd_save(void) struct fpsimd_last_state_struct const *last = this_cpu_ptr(&fpsimd_last_state); /* set by fpsimd_bind_task_to_cpu() or fpsimd_bind_state_to_cpu() */ + bool save_sve_regs = false; + bool save_ffr; + unsigned int vl; WARN_ON(!system_supports_fpsimd()); WARN_ON(!have_cpu_fpsimd_context()); @@ -368,9 +437,32 @@ static void fpsimd_save(void) if (test_thread_flag(TIF_FOREIGN_FPSTATE)) return; - if (IS_ENABLED(CONFIG_ARM64_SVE) && - test_thread_flag(TIF_SVE)) { - if (WARN_ON(sve_get_vl() != last->sve_vl)) { + if (test_thread_flag(TIF_SVE)) { + save_sve_regs = true; + save_ffr = true; + vl = last->sve_vl; + } + + if (system_supports_sme()) { + u64 *svcr = last->svcr; + *svcr = read_sysreg_s(SYS_SVCR); + + *svcr = read_sysreg_s(SYS_SVCR); + + if (*svcr & SVCR_ZA_MASK) + za_save_state(last->za_state); + + /* If we are in streaming mode override regular SVE. */ + if (*svcr & SVCR_SM_MASK) { + save_sve_regs = true; + save_ffr = system_supports_fa64(); + vl = last->sme_vl; + } + } + + if (IS_ENABLED(CONFIG_ARM64_SVE) && save_sve_regs) { + /* Get the configured VL from RDVL, will account for SM */ + if (WARN_ON(sve_get_vl() != vl)) { /* * Can't save the user regs, so current would * re-enter user with corrupt state. @@ -381,8 +473,8 @@ static void fpsimd_save(void) } sve_save_state((char *)last->sve_state + - sve_ffr_offset(last->sve_vl), - &last->st->fpsr, true); + sve_ffr_offset(vl), + &last->st->fpsr, save_ffr); } else { fpsimd_save_state(last->st); } @@ -409,6 +501,8 @@ static unsigned int find_supported_vector_length(enum vec_type type, if (vl > max_vl) vl = max_vl; + if (vl < info->min_vl) + vl = info->min_vl; bit = find_next_bit(info->vq_map, SVE_VQ_MAX, __vq_to_bit(sve_vq_from_vl(vl))); @@ -467,6 +561,30 @@ static int __init sve_sysctl_init(void) static int __init sve_sysctl_init(void) { return 0; } #endif /* ! (CONFIG_ARM64_SVE && CONFIG_SYSCTL) */ +#if defined(CONFIG_ARM64_SME) && defined(CONFIG_SYSCTL) +static struct ctl_table sme_default_vl_table[] = { + { + .procname = "sme_default_vector_length", + .mode = 0644, + .proc_handler = vec_proc_do_default_vl, + .extra1 = &vl_info[ARM64_VEC_SME], + }, + { } +}; + +static int __init sme_sysctl_init(void) +{ + if (system_supports_sme()) + if (!register_sysctl("abi", sme_default_vl_table)) + return -EINVAL; + + return 0; +} + +#else /* ! (CONFIG_ARM64_SME && CONFIG_SYSCTL) */ +static int __init sme_sysctl_init(void) { return 0; } +#endif /* ! (CONFIG_ARM64_SME && CONFIG_SYSCTL) */ + #define ZREG(sve_state, vq, n) ((char *)(sve_state) + \ (SVE_SIG_ZREG_OFFSET(vq, n) - SVE_SIG_REGS_OFFSET)) @@ -520,7 +638,7 @@ static void fpsimd_to_sve(struct task_struct *task) if (!system_supports_sve()) return; - vq = sve_vq_from_vl(task_get_sve_vl(task)); + vq = sve_vq_from_vl(thread_get_cur_vl(&task->thread)); __fpsimd_to_sve(sst, fst, vq); } @@ -537,7 +655,7 @@ static void fpsimd_to_sve(struct task_struct *task) */ static void sve_to_fpsimd(struct task_struct *task) { - unsigned int vq; + unsigned int vq, vl; void const *sst = task->thread.sve_state; struct user_fpsimd_state *fst = &task->thread.uw.fpsimd_state; unsigned int i; @@ -546,7 +664,8 @@ static void sve_to_fpsimd(struct task_struct *task) if (!system_supports_sve()) return; - vq = sve_vq_from_vl(task_get_sve_vl(task)); + vl = thread_get_cur_vl(&task->thread); + vq = sve_vq_from_vl(vl); for (i = 0; i < SVE_NUM_ZREGS; ++i) { p = (__uint128_t const *)ZREG(sst, vq, i); fst->vregs[i] = arm64_le128_to_cpu(*p); @@ -554,14 +673,37 @@ static void sve_to_fpsimd(struct task_struct *task) } #ifdef CONFIG_ARM64_SVE +/* + * Call __sve_free() directly only if you know task can't be scheduled + * or preempted. + */ +static void __sve_free(struct task_struct *task) +{ + kfree(task->thread.sve_state); + task->thread.sve_state = NULL; +} + +static void sve_free(struct task_struct *task) +{ + WARN_ON(test_tsk_thread_flag(task, TIF_SVE)); + + __sve_free(task); +} /* * Return how many bytes of memory are required to store the full SVE * state for task, given task's currently configured vector length. */ -static size_t sve_state_size(struct task_struct const *task) +size_t sve_state_size(struct task_struct const *task) { - return SVE_SIG_REGS_SIZE(sve_vq_from_vl(task_get_sve_vl(task))); + unsigned int vl = 0; + + if (system_supports_sve()) + vl = task_get_sve_vl(task); + if (system_supports_sme()) + vl = max(vl, task_get_sme_vl(task)); + + return SVE_SIG_REGS_SIZE(sve_vq_from_vl(vl)); } /* @@ -588,6 +730,19 @@ void sve_alloc(struct task_struct *task) /* + * Force the FPSIMD state shared with SVE to be updated in the SVE state + * even if the SVE state is the current active state. + * + * This should only be called by ptrace. task must be non-runnable. + * task->thread.sve_state must point to at least sve_state_size(task) + * bytes of allocated kernel memory. + */ +void fpsimd_force_sync_to_sve(struct task_struct *task) +{ + fpsimd_to_sve(task); +} + +/* * Ensure that task->thread.sve_state is up to date with respect to * the user task, irrespective of when SVE is in use or not. * @@ -597,7 +752,8 @@ void sve_alloc(struct task_struct *task) */ void fpsimd_sync_to_sve(struct task_struct *task) { - if (!test_tsk_thread_flag(task, TIF_SVE)) + if (!test_tsk_thread_flag(task, TIF_SVE) && + !thread_sm_enabled(&task->thread)) fpsimd_to_sve(task); } @@ -611,7 +767,8 @@ void fpsimd_sync_to_sve(struct task_struct *task) */ void sve_sync_to_fpsimd(struct task_struct *task) { - if (test_tsk_thread_flag(task, TIF_SVE)) + if (test_tsk_thread_flag(task, TIF_SVE) || + thread_sm_enabled(&task->thread)) sve_to_fpsimd(task); } @@ -636,7 +793,7 @@ void sve_sync_from_fpsimd_zeropad(struct task_struct *task) if (!test_tsk_thread_flag(task, TIF_SVE)) return; - vq = sve_vq_from_vl(task_get_sve_vl(task)); + vq = sve_vq_from_vl(thread_get_cur_vl(&task->thread)); memset(sst, 0, SVE_SIG_REGS_SIZE(vq)); __fpsimd_to_sve(sst, fst, vq); @@ -680,8 +837,7 @@ int vec_set_vector_length(struct task_struct *task, enum vec_type type, /* * To ensure the FPSIMD bits of the SVE vector registers are preserved, * write any live register state back to task_struct, and convert to a - * regular FPSIMD thread. Since the vector length can only be changed - * with a syscall we can't be in streaming mode while reconfiguring. + * regular FPSIMD thread. */ if (task == current) { get_cpu_fpsimd_context(); @@ -690,17 +846,26 @@ int vec_set_vector_length(struct task_struct *task, enum vec_type type, } fpsimd_flush_task_state(task); - if (test_and_clear_tsk_thread_flag(task, TIF_SVE)) + if (test_and_clear_tsk_thread_flag(task, TIF_SVE) || + thread_sm_enabled(&task->thread)) sve_to_fpsimd(task); + if (system_supports_sme() && type == ARM64_VEC_SME) { + task->thread.svcr &= ~(SVCR_SM_MASK | + SVCR_ZA_MASK); + clear_thread_flag(TIF_SME); + } + if (task == current) put_cpu_fpsimd_context(); /* - * Force reallocation of task SVE state to the correct size - * on next use: + * Force reallocation of task SVE and SME state to the correct + * size on next use: */ sve_free(task); + if (system_supports_sme() && type == ARM64_VEC_SME) + sme_free(task); task_set_vl(task, type, vl); @@ -761,6 +926,36 @@ int sve_get_current_vl(void) return vec_prctl_status(ARM64_VEC_SVE, 0); } +#ifdef CONFIG_ARM64_SME +/* PR_SME_SET_VL */ +int sme_set_current_vl(unsigned long arg) +{ + unsigned long vl, flags; + int ret; + + vl = arg & PR_SME_VL_LEN_MASK; + flags = arg & ~vl; + + if (!system_supports_sme() || is_compat_task()) + return -EINVAL; + + ret = vec_set_vector_length(current, ARM64_VEC_SME, vl, flags); + if (ret) + return ret; + + return vec_prctl_status(ARM64_VEC_SME, flags); +} + +/* PR_SME_GET_VL */ +int sme_get_current_vl(void) +{ + if (!system_supports_sme() || is_compat_task()) + return -EINVAL; + + return vec_prctl_status(ARM64_VEC_SME, 0); +} +#endif /* CONFIG_ARM64_SME */ + static void vec_probe_vqs(struct vl_info *info, DECLARE_BITMAP(map, SVE_VQ_MAX)) { @@ -770,7 +965,23 @@ static void vec_probe_vqs(struct vl_info *info, for (vq = SVE_VQ_MAX; vq >= SVE_VQ_MIN; --vq) { write_vl(info->type, vq - 1); /* self-syncing */ - vl = sve_get_vl(); + + switch (info->type) { + case ARM64_VEC_SVE: + vl = sve_get_vl(); + break; + case ARM64_VEC_SME: + vl = sme_get_vl(); + break; + default: + vl = 0; + break; + } + + /* Minimum VL identified? */ + if (sve_vq_from_vl(vl) > vq) + break; + vq = sve_vq_from_vl(vl); /* skip intervening lengths */ set_bit(__vq_to_bit(vq), map); } @@ -856,21 +1067,25 @@ int vec_verify_vq_map(enum vec_type type) static void __init sve_efi_setup(void) { - struct vl_info *info = &vl_info[ARM64_VEC_SVE]; + int max_vl = 0; + int i; if (!IS_ENABLED(CONFIG_EFI)) return; + for (i = 0; i < ARRAY_SIZE(vl_info); i++) + max_vl = max(vl_info[i].max_vl, max_vl); + /* * alloc_percpu() warns and prints a backtrace if this goes wrong. * This is evidence of a crippled system and we are returning void, * so no attempt is made to handle this situation here. */ - if (!sve_vl_valid(info->max_vl)) + if (!sve_vl_valid(max_vl)) goto fail; efi_sve_state = __alloc_percpu( - SVE_SIG_REGS_SIZE(sve_vq_from_vl(info->max_vl)), SVE_VQ_BYTES); + SVE_SIG_REGS_SIZE(sve_vq_from_vl(max_vl)), SVE_VQ_BYTES); if (!efi_sve_state) goto fail; @@ -989,10 +1204,172 @@ void __init sve_setup(void) void fpsimd_release_task(struct task_struct *dead_task) { __sve_free(dead_task); + sme_free(dead_task); } #endif /* CONFIG_ARM64_SVE */ +#ifdef CONFIG_ARM64_SME + +/* + * Ensure that task->thread.za_state is allocated and sufficiently large. + * + * This function should be used only in preparation for replacing + * task->thread.za_state with new data. The memory is always zeroed + * here to prevent stale data from showing through: this is done in + * the interest of testability and predictability, the architecture + * guarantees that when ZA is enabled it will be zeroed. + */ +void sme_alloc(struct task_struct *task) +{ + if (task->thread.za_state) { + memset(task->thread.za_state, 0, za_state_size(task)); + return; + } + + /* This could potentially be up to 64K. */ + task->thread.za_state = + kzalloc(za_state_size(task), GFP_KERNEL); +} + +static void sme_free(struct task_struct *task) +{ + kfree(task->thread.za_state); + task->thread.za_state = NULL; +} + +void sme_kernel_enable(const struct arm64_cpu_capabilities *__always_unused p) +{ + /* Set priority for all PEs to architecturally defined minimum */ + write_sysreg_s(read_sysreg_s(SYS_SMPRI_EL1) & ~SMPRI_EL1_PRIORITY_MASK, + SYS_SMPRI_EL1); + + /* Allow SME in kernel */ + write_sysreg(read_sysreg(CPACR_EL1) | CPACR_EL1_SMEN_EL1EN, CPACR_EL1); + isb(); + + /* Allow EL0 to access TPIDR2 */ + write_sysreg(read_sysreg(SCTLR_EL1) | SCTLR_ELx_ENTP2, SCTLR_EL1); + isb(); +} + +/* + * This must be called after sme_kernel_enable(), we rely on the + * feature table being sorted to ensure this. + */ +void fa64_kernel_enable(const struct arm64_cpu_capabilities *__always_unused p) +{ + /* Allow use of FA64 */ + write_sysreg_s(read_sysreg_s(SYS_SMCR_EL1) | SMCR_ELx_FA64_MASK, + SYS_SMCR_EL1); +} + +/* + * Read the pseudo-SMCR used by cpufeatures to identify the supported + * vector length. + * + * Use only if SME is present. + * This function clobbers the SME vector length. + */ +u64 read_smcr_features(void) +{ + u64 smcr; + unsigned int vq_max; + + sme_kernel_enable(NULL); + sme_smstart_sm(); + + /* + * Set the maximum possible VL. + */ + write_sysreg_s(read_sysreg_s(SYS_SMCR_EL1) | SMCR_ELx_LEN_MASK, + SYS_SMCR_EL1); + + smcr = read_sysreg_s(SYS_SMCR_EL1); + smcr &= ~(u64)SMCR_ELx_LEN_MASK; /* Only the LEN field */ + vq_max = sve_vq_from_vl(sve_get_vl()); + smcr |= vq_max - 1; /* set LEN field to maximum effective value */ + + sme_smstop_sm(); + + return smcr; +} + +void __init sme_setup(void) +{ + struct vl_info *info = &vl_info[ARM64_VEC_SME]; + u64 smcr; + int min_bit; + + if (!system_supports_sme()) + return; + + /* + * SME doesn't require any particular vector length be + * supported but it does require at least one. We should have + * disabled the feature entirely while bringing up CPUs but + * let's double check here. + */ + WARN_ON(bitmap_empty(info->vq_map, SVE_VQ_MAX)); + + min_bit = find_last_bit(info->vq_map, SVE_VQ_MAX); + info->min_vl = sve_vl_from_vq(__bit_to_vq(min_bit)); + + smcr = read_sanitised_ftr_reg(SYS_SMCR_EL1); + info->max_vl = sve_vl_from_vq((smcr & SMCR_ELx_LEN_MASK) + 1); + + /* + * Sanity-check that the max VL we determined through CPU features + * corresponds properly to sme_vq_map. If not, do our best: + */ + if (WARN_ON(info->max_vl != find_supported_vector_length(ARM64_VEC_SME, + info->max_vl))) + info->max_vl = find_supported_vector_length(ARM64_VEC_SME, + info->max_vl); + + WARN_ON(info->min_vl > info->max_vl); + + /* + * For the default VL, pick the maximum supported value <= 32 + * (256 bits) if there is one since this is guaranteed not to + * grow the signal frame when in streaming mode, otherwise the + * minimum available VL will be used. + */ + set_sme_default_vl(find_supported_vector_length(ARM64_VEC_SME, 32)); + + pr_info("SME: minimum available vector length %u bytes per vector\n", + info->min_vl); + pr_info("SME: maximum available vector length %u bytes per vector\n", + info->max_vl); + pr_info("SME: default vector length %u bytes per vector\n", + get_sme_default_vl()); +} + +#endif /* CONFIG_ARM64_SME */ + +static void sve_init_regs(void) +{ + /* + * Convert the FPSIMD state to SVE, zeroing all the state that + * is not shared with FPSIMD. If (as is likely) the current + * state is live in the registers then do this there and + * update our metadata for the current task including + * disabling the trap, otherwise update our in-memory copy. + * We are guaranteed to not be in streaming mode, we can only + * take a SVE trap when not in streaming mode and we can't be + * in streaming mode when taking a SME trap. + */ + if (!test_thread_flag(TIF_FOREIGN_FPSTATE)) { + unsigned long vq_minus_one = + sve_vq_from_vl(task_get_sve_vl(current)) - 1; + sve_set_vq(vq_minus_one); + sve_flush_live(true, vq_minus_one); + fpsimd_bind_task_to_cpu(); + } else { + fpsimd_to_sve(current); + } +} + /* * Trapped SVE access * @@ -1004,7 +1381,7 @@ void fpsimd_release_task(struct task_struct *dead_task) * would have disabled the SVE access trap for userspace during * ret_to_user, making an SVE access trap impossible in that case. */ -void do_sve_acc(unsigned int esr, struct pt_regs *regs) +void do_sve_acc(unsigned long esr, struct pt_regs *regs) { /* Even if we chose not to use SVE, the hardware could still trap: */ if (unlikely(!system_supports_sve()) || WARN_ON(is_compat_task())) { @@ -1024,29 +1401,84 @@ void do_sve_acc(unsigned int esr, struct pt_regs *regs) WARN_ON(1); /* SVE access shouldn't have trapped */ /* - * Convert the FPSIMD state to SVE, zeroing all the state that - * is not shared with FPSIMD. If (as is likely) the current - * state is live in the registers then do this there and - * update our metadata for the current task including - * disabling the trap, otherwise update our in-memory copy. + * Even if the task can have used streaming mode we can only + * generate SVE access traps in normal SVE mode and + * transitioning out of streaming mode may discard any + * streaming mode state. Always clear the high bits to avoid + * any potential errors tracking what is properly initialised. + */ + sve_init_regs(); + + put_cpu_fpsimd_context(); +} + +/* + * Trapped SME access + * + * Storage is allocated for the full SVE and SME state, the current + * FPSIMD register contents are migrated to SVE if SVE is not already + * active, and the access trap is disabled. + * + * TIF_SME should be clear on entry: otherwise, fpsimd_restore_current_state() + * would have disabled the SME access trap for userspace during + * ret_to_user, making an SVE access trap impossible in that case. + */ +void do_sme_acc(unsigned long esr, struct pt_regs *regs) +{ + /* Even if we chose not to use SME, the hardware could still trap: */ + if (unlikely(!system_supports_sme()) || WARN_ON(is_compat_task())) { + force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc, 0); + return; + } + + /* + * If this not a trap due to SME being disabled then something + * is being used in the wrong mode, report as SIGILL. */ + if (ESR_ELx_ISS(esr) != ESR_ELx_SME_ISS_SME_DISABLED) { + force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc, 0); + return; + } + + sve_alloc(current); + sme_alloc(current); + if (!current->thread.sve_state || !current->thread.za_state) { + force_sig(SIGKILL); + return; + } + + get_cpu_fpsimd_context(); + + /* With TIF_SME userspace shouldn't generate any traps */ + if (test_and_set_thread_flag(TIF_SME)) + WARN_ON(1); + if (!test_thread_flag(TIF_FOREIGN_FPSTATE)) { unsigned long vq_minus_one = - sve_vq_from_vl(task_get_sve_vl(current)) - 1; - sve_set_vq(vq_minus_one); - sve_flush_live(true, vq_minus_one); + sve_vq_from_vl(task_get_sme_vl(current)) - 1; + sme_set_vq(vq_minus_one); + fpsimd_bind_task_to_cpu(); - } else { - fpsimd_to_sve(current); } + /* + * If SVE was not already active initialise the SVE registers, + * any non-shared state between the streaming and regular SVE + * registers is architecturally guaranteed to be zeroed when + * we enter streaming mode. We do not need to initialize ZA + * since ZA must be disabled at this point and enabling ZA is + * architecturally defined to zero ZA. + */ + if (system_supports_sve() && !test_thread_flag(TIF_SVE)) + sve_init_regs(); + put_cpu_fpsimd_context(); } /* * Trapped FP/ASIMD access. */ -void do_fpsimd_acc(unsigned int esr, struct pt_regs *regs) +void do_fpsimd_acc(unsigned long esr, struct pt_regs *regs) { /* TODO: implement lazy context saving/restoring */ WARN_ON(1); @@ -1055,7 +1487,7 @@ void do_fpsimd_acc(unsigned int esr, struct pt_regs *regs) /* * Raise a SIGFPE for the current process. */ -void do_fpsimd_exc(unsigned int esr, struct pt_regs *regs) +void do_fpsimd_exc(unsigned long esr, struct pt_regs *regs) { unsigned int si_code = FPE_FLTUNK; @@ -1141,6 +1573,9 @@ static void fpsimd_flush_thread_vl(enum vec_type type) void fpsimd_flush_thread(void) { + void *sve_state = NULL; + void *za_state = NULL; + if (!system_supports_fpsimd()) return; @@ -1152,11 +1587,28 @@ void fpsimd_flush_thread(void) if (system_supports_sve()) { clear_thread_flag(TIF_SVE); - sve_free(current); + + /* Defer kfree() while in atomic context */ + sve_state = current->thread.sve_state; + current->thread.sve_state = NULL; + fpsimd_flush_thread_vl(ARM64_VEC_SVE); } + if (system_supports_sme()) { + clear_thread_flag(TIF_SME); + + /* Defer kfree() while in atomic context */ + za_state = current->thread.za_state; + current->thread.za_state = NULL; + + fpsimd_flush_thread_vl(ARM64_VEC_SME); + current->thread.svcr = 0; + } + put_cpu_fpsimd_context(); + kfree(sve_state); + kfree(za_state); } /* @@ -1198,22 +1650,34 @@ static void fpsimd_bind_task_to_cpu(void) WARN_ON(!system_supports_fpsimd()); last->st = ¤t->thread.uw.fpsimd_state; last->sve_state = current->thread.sve_state; + last->za_state = current->thread.za_state; last->sve_vl = task_get_sve_vl(current); + last->sme_vl = task_get_sme_vl(current); + last->svcr = ¤t->thread.svcr; current->thread.fpsimd_cpu = smp_processor_id(); + /* + * Toggle SVE and SME trapping for userspace if needed, these + * are serialsied by ret_to_user(). + */ + if (system_supports_sme()) { + if (test_thread_flag(TIF_SME)) + sme_user_enable(); + else + sme_user_disable(); + } + if (system_supports_sve()) { - /* Toggle SVE trapping for userspace if needed */ if (test_thread_flag(TIF_SVE)) sve_user_enable(); else sve_user_disable(); - - /* Serialised by exception return to user */ } } void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *st, void *sve_state, - unsigned int sve_vl) + unsigned int sve_vl, void *za_state, + unsigned int sme_vl, u64 *svcr) { struct fpsimd_last_state_struct *last = this_cpu_ptr(&fpsimd_last_state); @@ -1222,8 +1686,11 @@ void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *st, void *sve_state, WARN_ON(!in_softirq() && !irqs_disabled()); last->st = st; + last->svcr = svcr; last->sve_state = sve_state; + last->za_state = za_state; last->sve_vl = sve_vl; + last->sme_vl = sme_vl; } /* @@ -1320,6 +1787,15 @@ static void fpsimd_flush_cpu_state(void) { WARN_ON(!system_supports_fpsimd()); __this_cpu_write(fpsimd_last_state.st, NULL); + + /* + * Leaving streaming mode enabled will cause issues for any kernel + * NEON and leaving streaming mode or ZA enabled may increase power + * consumption. + */ + if (system_supports_sme()) + sme_smstop(); + set_thread_flag(TIF_FOREIGN_FPSTATE); } @@ -1397,6 +1873,7 @@ EXPORT_SYMBOL(kernel_neon_end); static DEFINE_PER_CPU(struct user_fpsimd_state, efi_fpsimd_state); static DEFINE_PER_CPU(bool, efi_fpsimd_state_used); static DEFINE_PER_CPU(bool, efi_sve_state_used); +static DEFINE_PER_CPU(bool, efi_sm_state); /* * EFI runtime services support functions @@ -1431,12 +1908,28 @@ void __efi_fpsimd_begin(void) */ if (system_supports_sve() && likely(efi_sve_state)) { char *sve_state = this_cpu_ptr(efi_sve_state); + bool ffr = true; + u64 svcr; __this_cpu_write(efi_sve_state_used, true); + if (system_supports_sme()) { + svcr = read_sysreg_s(SYS_SVCR); + + if (!system_supports_fa64()) + ffr = svcr & SVCR_SM_MASK; + + __this_cpu_write(efi_sm_state, ffr); + } + sve_save_state(sve_state + sve_ffr_offset(sve_max_vl()), &this_cpu_ptr(&efi_fpsimd_state)->fpsr, - true); + ffr); + + if (system_supports_sme()) + sysreg_clear_set_s(SYS_SVCR, + SVCR_SM_MASK, 0); + } else { fpsimd_save_state(this_cpu_ptr(&efi_fpsimd_state)); } @@ -1459,11 +1952,26 @@ void __efi_fpsimd_end(void) if (system_supports_sve() && likely(__this_cpu_read(efi_sve_state_used))) { char const *sve_state = this_cpu_ptr(efi_sve_state); + bool ffr = true; + + /* + * Restore streaming mode; EFI calls are + * normal function calls so should not return in + * streaming mode. + */ + if (system_supports_sme()) { + if (__this_cpu_read(efi_sm_state)) { + sysreg_clear_set_s(SYS_SVCR, + 0, + SVCR_SM_MASK); + if (!system_supports_fa64()) + ffr = efi_sm_state; + } + } - sve_set_vq(sve_vq_from_vl(sve_get_vl()) - 1); sve_load_state(sve_state + sve_ffr_offset(sve_max_vl()), &this_cpu_ptr(&efi_fpsimd_state)->fpsr, - true); + ffr); __this_cpu_write(efi_sve_state_used, false); } else { @@ -1538,6 +2046,13 @@ static int __init fpsimd_init(void) if (!cpu_have_named_feature(ASIMD)) pr_notice("Advanced SIMD is not implemented\n"); - return sve_sysctl_init(); + + if (cpu_have_named_feature(SME) && !cpu_have_named_feature(SVE)) + pr_notice("SME is implemented but not SVE\n"); + + sve_sysctl_init(); + sme_sysctl_init(); + + return 0; } core_initcall(fpsimd_init); diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c index 4506c4a90ac1..f447c4a36f69 100644 --- a/arch/arm64/kernel/ftrace.c +++ b/arch/arm64/kernel/ftrace.c @@ -268,6 +268,22 @@ void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent, } #ifdef CONFIG_DYNAMIC_FTRACE + +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS +void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct ftrace_regs *fregs) +{ + /* + * When DYNAMIC_FTRACE_WITH_REGS is selected, `fregs` can never be NULL + * and arch_ftrace_get_regs(fregs) will always give a non-NULL pt_regs + * in which we can safely modify the LR. + */ + struct pt_regs *regs = arch_ftrace_get_regs(fregs); + unsigned long *parent = (unsigned long *)&procedure_link_pointer(regs); + + prepare_ftrace_return(ip, parent, frame_pointer(regs)); +} +#else /* * Turn on/off the call to ftrace_graph_caller() in ftrace_caller() * depending on @enable. @@ -297,5 +313,6 @@ int ftrace_disable_ftrace_graph_caller(void) { return ftrace_modify_graph_caller(false); } +#endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */ #endif /* CONFIG_DYNAMIC_FTRACE */ #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c index 712e97c03e54..b29a311bb055 100644 --- a/arch/arm64/kernel/hw_breakpoint.c +++ b/arch/arm64/kernel/hw_breakpoint.c @@ -617,7 +617,7 @@ NOKPROBE_SYMBOL(toggle_bp_registers); /* * Debug exception handlers. */ -static int breakpoint_handler(unsigned long unused, unsigned int esr, +static int breakpoint_handler(unsigned long unused, unsigned long esr, struct pt_regs *regs) { int i, step = 0, *kernel_step; @@ -701,7 +701,7 @@ NOKPROBE_SYMBOL(breakpoint_handler); * addresses. There is no straight-forward way, short of disassembling the * offending instruction, to map that address back to the watchpoint. This * function computes the distance of the memory access from the watchpoint as a - * heuristic for the likelyhood that a given access triggered the watchpoint. + * heuristic for the likelihood that a given access triggered the watchpoint. * * See Section D2.10.5 "Determining the memory location that caused a Watchpoint * exception" of ARMv8 Architecture Reference Manual for details. @@ -751,7 +751,7 @@ static int watchpoint_report(struct perf_event *wp, unsigned long addr, return step; } -static int watchpoint_handler(unsigned long addr, unsigned int esr, +static int watchpoint_handler(unsigned long addr, unsigned long esr, struct pt_regs *regs) { int i, step = 0, *kernel_step, access, closest_match = 0; diff --git a/arch/arm64/kernel/kgdb.c b/arch/arm64/kernel/kgdb.c index 2aede780fb80..cda9c1e9864f 100644 --- a/arch/arm64/kernel/kgdb.c +++ b/arch/arm64/kernel/kgdb.c @@ -232,14 +232,14 @@ int kgdb_arch_handle_exception(int exception_vector, int signo, return err; } -static int kgdb_brk_fn(struct pt_regs *regs, unsigned int esr) +static int kgdb_brk_fn(struct pt_regs *regs, unsigned long esr) { kgdb_handle_exception(1, SIGTRAP, 0, regs); return DBG_HOOK_HANDLED; } NOKPROBE_SYMBOL(kgdb_brk_fn) -static int kgdb_compiled_brk_fn(struct pt_regs *regs, unsigned int esr) +static int kgdb_compiled_brk_fn(struct pt_regs *regs, unsigned long esr) { compiled_break = 1; kgdb_handle_exception(1, SIGTRAP, 0, regs); @@ -248,7 +248,7 @@ static int kgdb_compiled_brk_fn(struct pt_regs *regs, unsigned int esr) } NOKPROBE_SYMBOL(kgdb_compiled_brk_fn); -static int kgdb_step_brk_fn(struct pt_regs *regs, unsigned int esr) +static int kgdb_step_brk_fn(struct pt_regs *regs, unsigned long esr) { if (!kgdb_single_step) return DBG_HOOK_ERROR; diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c index e16b248699d5..19c2d487cb08 100644 --- a/arch/arm64/kernel/machine_kexec.c +++ b/arch/arm64/kernel/machine_kexec.c @@ -329,8 +329,13 @@ bool crash_is_nosave(unsigned long pfn) /* in reserved memory? */ addr = __pfn_to_phys(pfn); - if ((addr < crashk_res.start) || (crashk_res.end < addr)) - return false; + if ((addr < crashk_res.start) || (crashk_res.end < addr)) { + if (!crashk_low_res.end) + return false; + + if ((addr < crashk_low_res.start) || (crashk_low_res.end < addr)) + return false; + } if (!kexec_crash_image) return true; diff --git a/arch/arm64/kernel/machine_kexec_file.c b/arch/arm64/kernel/machine_kexec_file.c index 59c648d51848..889951291cc0 100644 --- a/arch/arm64/kernel/machine_kexec_file.c +++ b/arch/arm64/kernel/machine_kexec_file.c @@ -65,10 +65,18 @@ static int prepare_elf_headers(void **addr, unsigned long *sz) /* Exclude crashkernel region */ ret = crash_exclude_mem_range(cmem, crashk_res.start, crashk_res.end); + if (ret) + goto out; + + if (crashk_low_res.end) { + ret = crash_exclude_mem_range(cmem, crashk_low_res.start, crashk_low_res.end); + if (ret) + goto out; + } - if (!ret) - ret = crash_prepare_elf64_headers(cmem, true, addr, sz); + ret = crash_prepare_elf64_headers(cmem, true, addr, sz); +out: kfree(cmem); return ret; } diff --git a/arch/arm64/kernel/module-plts.c b/arch/arm64/kernel/module-plts.c index e53493d8b208..a3d0494f25a9 100644 --- a/arch/arm64/kernel/module-plts.c +++ b/arch/arm64/kernel/module-plts.c @@ -220,7 +220,7 @@ static unsigned int count_plts(Elf64_Sym *syms, Elf64_Rela *rela, int num, * increasing the section's alignment so that the * resulting address of this instruction is guaranteed * to equal the offset in that particular bit (as well - * as all less signficant bits). This ensures that the + * as all less significant bits). This ensures that the * address modulo 4 KB != 0xfff8 or 0xfffc (which would * have all ones in bits [11:3]) */ diff --git a/arch/arm64/kernel/mte.c b/arch/arm64/kernel/mte.c index 78b3e0f8e997..57b30bcf9f21 100644 --- a/arch/arm64/kernel/mte.c +++ b/arch/arm64/kernel/mte.c @@ -15,6 +15,7 @@ #include <linux/swapops.h> #include <linux/thread_info.h> #include <linux/types.h> +#include <linux/uaccess.h> #include <linux/uio.h> #include <asm/barrier.h> @@ -76,6 +77,9 @@ void mte_sync_tags(pte_t old_pte, pte_t pte) mte_sync_page_tags(page, old_pte, check_swap, pte_is_tagged); } + + /* ensure the tags are visible before the PTE is set */ + smp_wmb(); } int memcmp_pages(struct page *page1, struct page *page2) @@ -106,7 +110,8 @@ int memcmp_pages(struct page *page1, struct page *page2) static inline void __mte_enable_kernel(const char *mode, unsigned long tcf) { /* Enable MTE Sync Mode for EL1. */ - sysreg_clear_set(sctlr_el1, SCTLR_ELx_TCF_MASK, tcf); + sysreg_clear_set(sctlr_el1, SCTLR_EL1_TCF_MASK, + SYS_FIELD_PREP(SCTLR_EL1, TCF, tcf)); isb(); pr_info_once("MTE: enabled in %s mode at EL1\n", mode); @@ -122,12 +127,12 @@ void mte_enable_kernel_sync(void) WARN_ONCE(system_uses_mte_async_or_asymm_mode(), "MTE async mode enabled system wide!"); - __mte_enable_kernel("synchronous", SCTLR_ELx_TCF_SYNC); + __mte_enable_kernel("synchronous", SCTLR_EL1_TCF_SYNC); } void mte_enable_kernel_async(void) { - __mte_enable_kernel("asynchronous", SCTLR_ELx_TCF_ASYNC); + __mte_enable_kernel("asynchronous", SCTLR_EL1_TCF_ASYNC); /* * MTE async mode is set system wide by the first PE that @@ -144,7 +149,7 @@ void mte_enable_kernel_async(void) void mte_enable_kernel_asymm(void) { if (cpus_have_cap(ARM64_MTE_ASYMM)) { - __mte_enable_kernel("asymmetric", SCTLR_ELx_TCF_ASYMM); + __mte_enable_kernel("asymmetric", SCTLR_EL1_TCF_ASYMM); /* * MTE asymm mode behaves as async mode for store @@ -216,11 +221,11 @@ static void mte_update_sctlr_user(struct task_struct *task) * default order. */ if (resolved_mte_tcf & MTE_CTRL_TCF_ASYMM) - sctlr |= SCTLR_EL1_TCF0_ASYMM; + sctlr |= SYS_FIELD_PREP_ENUM(SCTLR_EL1, TCF0, ASYMM); else if (resolved_mte_tcf & MTE_CTRL_TCF_ASYNC) - sctlr |= SCTLR_EL1_TCF0_ASYNC; + sctlr |= SYS_FIELD_PREP_ENUM(SCTLR_EL1, TCF0, ASYNC); else if (resolved_mte_tcf & MTE_CTRL_TCF_SYNC) - sctlr |= SCTLR_EL1_TCF0_SYNC; + sctlr |= SYS_FIELD_PREP_ENUM(SCTLR_EL1, TCF0, SYNC); task->thread.sctlr_user = sctlr; } @@ -543,3 +548,32 @@ static int register_mte_tcf_preferred_sysctl(void) return 0; } subsys_initcall(register_mte_tcf_preferred_sysctl); + +/* + * Return 0 on success, the number of bytes not probed otherwise. + */ +size_t mte_probe_user_range(const char __user *uaddr, size_t size) +{ + const char __user *end = uaddr + size; + int err = 0; + char val; + + __raw_get_user(val, uaddr, err); + if (err) + return size; + + uaddr = PTR_ALIGN(uaddr, MTE_GRANULE_SIZE); + while (uaddr < end) { + /* + * A read is sufficient for mte, the caller should have probed + * for the pte write permission if required. + */ + __raw_get_user(val, uaddr, err); + if (err) + return end - uaddr; + uaddr += MTE_GRANULE_SIZE; + } + (void)val; + + return 0; +} diff --git a/arch/arm64/kernel/paravirt.c b/arch/arm64/kernel/paravirt.c index 75fed4460407..57c7c211f8c7 100644 --- a/arch/arm64/kernel/paravirt.c +++ b/arch/arm64/kernel/paravirt.c @@ -35,7 +35,7 @@ static u64 native_steal_clock(int cpu) DEFINE_STATIC_CALL(pv_steal_clock, native_steal_clock); struct pv_time_stolen_time_region { - struct pvclock_vcpu_stolen_time *kaddr; + struct pvclock_vcpu_stolen_time __rcu *kaddr; }; static DEFINE_PER_CPU(struct pv_time_stolen_time_region, stolen_time_region); @@ -52,7 +52,9 @@ early_param("no-steal-acc", parse_no_stealacc); /* return stolen time in ns by asking the hypervisor */ static u64 para_steal_clock(int cpu) { + struct pvclock_vcpu_stolen_time *kaddr = NULL; struct pv_time_stolen_time_region *reg; + u64 ret = 0; reg = per_cpu_ptr(&stolen_time_region, cpu); @@ -61,28 +63,37 @@ static u64 para_steal_clock(int cpu) * online notification callback runs. Until the callback * has run we just return zero. */ - if (!reg->kaddr) + rcu_read_lock(); + kaddr = rcu_dereference(reg->kaddr); + if (!kaddr) { + rcu_read_unlock(); return 0; + } - return le64_to_cpu(READ_ONCE(reg->kaddr->stolen_time)); + ret = le64_to_cpu(READ_ONCE(kaddr->stolen_time)); + rcu_read_unlock(); + return ret; } static int stolen_time_cpu_down_prepare(unsigned int cpu) { + struct pvclock_vcpu_stolen_time *kaddr = NULL; struct pv_time_stolen_time_region *reg; reg = this_cpu_ptr(&stolen_time_region); if (!reg->kaddr) return 0; - memunmap(reg->kaddr); - memset(reg, 0, sizeof(*reg)); + kaddr = rcu_replace_pointer(reg->kaddr, NULL, true); + synchronize_rcu(); + memunmap(kaddr); return 0; } static int stolen_time_cpu_online(unsigned int cpu) { + struct pvclock_vcpu_stolen_time *kaddr = NULL; struct pv_time_stolen_time_region *reg; struct arm_smccc_res res; @@ -93,17 +104,19 @@ static int stolen_time_cpu_online(unsigned int cpu) if (res.a0 == SMCCC_RET_NOT_SUPPORTED) return -EINVAL; - reg->kaddr = memremap(res.a0, + kaddr = memremap(res.a0, sizeof(struct pvclock_vcpu_stolen_time), MEMREMAP_WB); + rcu_assign_pointer(reg->kaddr, kaddr); + if (!reg->kaddr) { pr_warn("Failed to map stolen time data structure\n"); return -ENOMEM; } - if (le32_to_cpu(reg->kaddr->revision) != 0 || - le32_to_cpu(reg->kaddr->attributes) != 0) { + if (le32_to_cpu(kaddr->revision) != 0 || + le32_to_cpu(kaddr->attributes) != 0) { pr_warn_once("Unexpected revision or attributes in stolen time data\n"); return -ENXIO; } diff --git a/arch/arm64/kernel/patching.c b/arch/arm64/kernel/patching.c index 771f543464e0..33e0fabc0b79 100644 --- a/arch/arm64/kernel/patching.c +++ b/arch/arm64/kernel/patching.c @@ -117,8 +117,8 @@ static int __kprobes aarch64_insn_patch_text_cb(void *arg) int i, ret = 0; struct aarch64_insn_patch *pp = arg; - /* The first CPU becomes master */ - if (atomic_inc_return(&pp->cpu_count) == 1) { + /* The last CPU becomes master */ + if (atomic_inc_return(&pp->cpu_count) == num_online_cpus()) { for (i = 0; ret == 0 && i < pp->insn_cnt; i++) ret = aarch64_insn_patch_text_nosync(pp->text_addrs[i], pp->new_insns[i]); diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c index d9dfa82c1f18..d1d182320245 100644 --- a/arch/arm64/kernel/probes/kprobes.c +++ b/arch/arm64/kernel/probes/kprobes.c @@ -335,7 +335,7 @@ static void __kprobes kprobe_handler(struct pt_regs *regs) } static int __kprobes -kprobe_breakpoint_ss_handler(struct pt_regs *regs, unsigned int esr) +kprobe_breakpoint_ss_handler(struct pt_regs *regs, unsigned long esr) { struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); unsigned long addr = instruction_pointer(regs); @@ -359,7 +359,7 @@ static struct break_hook kprobes_break_ss_hook = { }; static int __kprobes -kprobe_breakpoint_handler(struct pt_regs *regs, unsigned int esr) +kprobe_breakpoint_handler(struct pt_regs *regs, unsigned long esr) { kprobe_handler(regs); return DBG_HOOK_HANDLED; diff --git a/arch/arm64/kernel/probes/uprobes.c b/arch/arm64/kernel/probes/uprobes.c index 9be668f3f034..d49aef2657cd 100644 --- a/arch/arm64/kernel/probes/uprobes.c +++ b/arch/arm64/kernel/probes/uprobes.c @@ -166,7 +166,7 @@ int arch_uprobe_exception_notify(struct notifier_block *self, } static int uprobe_breakpoint_handler(struct pt_regs *regs, - unsigned int esr) + unsigned long esr) { if (uprobe_pre_sstep_notifier(regs)) return DBG_HOOK_HANDLED; @@ -175,7 +175,7 @@ static int uprobe_breakpoint_handler(struct pt_regs *regs, } static int uprobe_single_step_handler(struct pt_regs *regs, - unsigned int esr) + unsigned long esr) { struct uprobe_task *utask = current->utask; diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 7fa97df55e3a..9734c9fb1a32 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -250,6 +250,8 @@ void show_regs(struct pt_regs *regs) static void tls_thread_flush(void) { write_sysreg(0, tpidr_el0); + if (system_supports_tpidr2()) + write_sysreg_s(0, SYS_TPIDR2_EL0); if (is_compat_task()) { current->thread.uw.tp_value = 0; @@ -298,16 +300,42 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) /* * Detach src's sve_state (if any) from dst so that it does not - * get erroneously used or freed prematurely. dst's sve_state + * get erroneously used or freed prematurely. dst's copies * will be allocated on demand later on if dst uses SVE. * For consistency, also clear TIF_SVE here: this could be done * later in copy_process(), but to avoid tripping up future - * maintainers it is best not to leave TIF_SVE and sve_state in + * maintainers it is best not to leave TIF flags and buffers in * an inconsistent state, even temporarily. */ dst->thread.sve_state = NULL; clear_tsk_thread_flag(dst, TIF_SVE); + /* + * In the unlikely event that we create a new thread with ZA + * enabled we should retain the ZA state so duplicate it here. + * This may be shortly freed if we exec() or if CLONE_SETTLS + * but it's simpler to do it here. To avoid confusing the rest + * of the code ensure that we have a sve_state allocated + * whenever za_state is allocated. + */ + if (thread_za_enabled(&src->thread)) { + dst->thread.sve_state = kzalloc(sve_state_size(src), + GFP_KERNEL); + if (!dst->thread.sve_state) + return -ENOMEM; + dst->thread.za_state = kmemdup(src->thread.za_state, + za_state_size(src), + GFP_KERNEL); + if (!dst->thread.za_state) { + kfree(dst->thread.sve_state); + dst->thread.sve_state = NULL; + return -ENOMEM; + } + } else { + dst->thread.za_state = NULL; + clear_tsk_thread_flag(dst, TIF_SME); + } + /* clear any pending asynchronous tag fault raised by the parent */ clear_tsk_thread_flag(dst, TIF_MTE_ASYNC_FAULT); @@ -343,6 +371,8 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start, * out-of-sync with the saved value. */ *task_user_tls(p) = read_sysreg(tpidr_el0); + if (system_supports_tpidr2()) + p->thread.tpidr2_el0 = read_sysreg_s(SYS_TPIDR2_EL0); if (stack_start) { if (is_compat_thread(task_thread_info(p))) @@ -353,10 +383,12 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start, /* * If a TLS pointer was passed to clone, use it for the new - * thread. + * thread. We also reset TPIDR2 if it's in use. */ - if (clone_flags & CLONE_SETTLS) + if (clone_flags & CLONE_SETTLS) { p->thread.uw.tp_value = tls; + p->thread.tpidr2_el0 = 0; + } } else { /* * A kthread has no context to ERET to, so ensure any buggy @@ -387,6 +419,8 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start, void tls_preserve_current_state(void) { *task_user_tls(current) = read_sysreg(tpidr_el0); + if (system_supports_tpidr2() && !is_compat_task()) + current->thread.tpidr2_el0 = read_sysreg_s(SYS_TPIDR2_EL0); } static void tls_thread_switch(struct task_struct *next) @@ -399,6 +433,8 @@ static void tls_thread_switch(struct task_struct *next) write_sysreg(0, tpidrro_el0); write_sysreg(*task_user_tls(next), tpidr_el0); + if (system_supports_tpidr2()) + write_sysreg_s(next->thread.tpidr2_el0, SYS_TPIDR2_EL0); } /* diff --git a/arch/arm64/kernel/proton-pack.c b/arch/arm64/kernel/proton-pack.c index 5777929d35bf..40be3a7c2c53 100644 --- a/arch/arm64/kernel/proton-pack.c +++ b/arch/arm64/kernel/proton-pack.c @@ -853,6 +853,7 @@ u8 spectre_bhb_loop_affected(int scope) if (scope == SCOPE_LOCAL_CPU) { static const struct midr_range spectre_bhb_k32_list[] = { MIDR_ALL_VERSIONS(MIDR_CORTEX_A78), + MIDR_ALL_VERSIONS(MIDR_CORTEX_A78AE), MIDR_ALL_VERSIONS(MIDR_CORTEX_A78C), MIDR_ALL_VERSIONS(MIDR_CORTEX_X1), MIDR_ALL_VERSIONS(MIDR_CORTEX_A710), diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 230a47b9189e..21da83187a60 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -713,21 +713,51 @@ static int system_call_set(struct task_struct *target, #ifdef CONFIG_ARM64_SVE static void sve_init_header_from_task(struct user_sve_header *header, - struct task_struct *target) + struct task_struct *target, + enum vec_type type) { unsigned int vq; + bool active; + bool fpsimd_only; + enum vec_type task_type; memset(header, 0, sizeof(*header)); - header->flags = test_tsk_thread_flag(target, TIF_SVE) ? - SVE_PT_REGS_SVE : SVE_PT_REGS_FPSIMD; - if (test_tsk_thread_flag(target, TIF_SVE_VL_INHERIT)) - header->flags |= SVE_PT_VL_INHERIT; + /* Check if the requested registers are active for the task */ + if (thread_sm_enabled(&target->thread)) + task_type = ARM64_VEC_SME; + else + task_type = ARM64_VEC_SVE; + active = (task_type == type); + + switch (type) { + case ARM64_VEC_SVE: + if (test_tsk_thread_flag(target, TIF_SVE_VL_INHERIT)) + header->flags |= SVE_PT_VL_INHERIT; + fpsimd_only = !test_tsk_thread_flag(target, TIF_SVE); + break; + case ARM64_VEC_SME: + if (test_tsk_thread_flag(target, TIF_SME_VL_INHERIT)) + header->flags |= SVE_PT_VL_INHERIT; + fpsimd_only = false; + break; + default: + WARN_ON_ONCE(1); + return; + } - header->vl = task_get_sve_vl(target); + if (active) { + if (fpsimd_only) { + header->flags |= SVE_PT_REGS_FPSIMD; + } else { + header->flags |= SVE_PT_REGS_SVE; + } + } + + header->vl = task_get_vl(target, type); vq = sve_vq_from_vl(header->vl); - header->max_vl = sve_max_vl(); + header->max_vl = vec_max_vl(type); header->size = SVE_PT_SIZE(vq, header->flags); header->max_size = SVE_PT_SIZE(sve_vq_from_vl(header->max_vl), SVE_PT_REGS_SVE); @@ -738,19 +768,17 @@ static unsigned int sve_size_from_header(struct user_sve_header const *header) return ALIGN(header->size, SVE_VQ_BYTES); } -static int sve_get(struct task_struct *target, - const struct user_regset *regset, - struct membuf to) +static int sve_get_common(struct task_struct *target, + const struct user_regset *regset, + struct membuf to, + enum vec_type type) { struct user_sve_header header; unsigned int vq; unsigned long start, end; - if (!system_supports_sve()) - return -EINVAL; - /* Header */ - sve_init_header_from_task(&header, target); + sve_init_header_from_task(&header, target, type); vq = sve_vq_from_vl(header.vl); membuf_write(&to, &header, sizeof(header)); @@ -758,49 +786,61 @@ static int sve_get(struct task_struct *target, if (target == current) fpsimd_preserve_current_state(); - /* Registers: FPSIMD-only case */ - BUILD_BUG_ON(SVE_PT_FPSIMD_OFFSET != sizeof(header)); - if ((header.flags & SVE_PT_REGS_MASK) == SVE_PT_REGS_FPSIMD) + BUILD_BUG_ON(SVE_PT_SVE_OFFSET != sizeof(header)); + + switch ((header.flags & SVE_PT_REGS_MASK)) { + case SVE_PT_REGS_FPSIMD: return __fpr_get(target, regset, to); - /* Otherwise: full SVE case */ + case SVE_PT_REGS_SVE: + start = SVE_PT_SVE_OFFSET; + end = SVE_PT_SVE_FFR_OFFSET(vq) + SVE_PT_SVE_FFR_SIZE(vq); + membuf_write(&to, target->thread.sve_state, end - start); - BUILD_BUG_ON(SVE_PT_SVE_OFFSET != sizeof(header)); - start = SVE_PT_SVE_OFFSET; - end = SVE_PT_SVE_FFR_OFFSET(vq) + SVE_PT_SVE_FFR_SIZE(vq); - membuf_write(&to, target->thread.sve_state, end - start); + start = end; + end = SVE_PT_SVE_FPSR_OFFSET(vq); + membuf_zero(&to, end - start); - start = end; - end = SVE_PT_SVE_FPSR_OFFSET(vq); - membuf_zero(&to, end - start); + /* + * Copy fpsr, and fpcr which must follow contiguously in + * struct fpsimd_state: + */ + start = end; + end = SVE_PT_SVE_FPCR_OFFSET(vq) + SVE_PT_SVE_FPCR_SIZE; + membuf_write(&to, &target->thread.uw.fpsimd_state.fpsr, + end - start); - /* - * Copy fpsr, and fpcr which must follow contiguously in - * struct fpsimd_state: - */ - start = end; - end = SVE_PT_SVE_FPCR_OFFSET(vq) + SVE_PT_SVE_FPCR_SIZE; - membuf_write(&to, &target->thread.uw.fpsimd_state.fpsr, end - start); + start = end; + end = sve_size_from_header(&header); + return membuf_zero(&to, end - start); - start = end; - end = sve_size_from_header(&header); - return membuf_zero(&to, end - start); + default: + return 0; + } } -static int sve_set(struct task_struct *target, +static int sve_get(struct task_struct *target, const struct user_regset *regset, - unsigned int pos, unsigned int count, - const void *kbuf, const void __user *ubuf) + struct membuf to) +{ + if (!system_supports_sve()) + return -EINVAL; + + return sve_get_common(target, regset, to, ARM64_VEC_SVE); +} + +static int sve_set_common(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf, + enum vec_type type) { int ret; struct user_sve_header header; unsigned int vq; unsigned long start, end; - if (!system_supports_sve()) - return -EINVAL; - /* Header */ if (count < sizeof(header)) return -EINVAL; @@ -813,13 +853,37 @@ static int sve_set(struct task_struct *target, * Apart from SVE_PT_REGS_MASK, all SVE_PT_* flags are consumed by * vec_set_vector_length(), which will also validate them for us: */ - ret = vec_set_vector_length(target, ARM64_VEC_SVE, header.vl, + ret = vec_set_vector_length(target, type, header.vl, ((unsigned long)header.flags & ~SVE_PT_REGS_MASK) << 16); if (ret) goto out; /* Actual VL set may be less than the user asked for: */ - vq = sve_vq_from_vl(task_get_sve_vl(target)); + vq = sve_vq_from_vl(task_get_vl(target, type)); + + /* Enter/exit streaming mode */ + if (system_supports_sme()) { + u64 old_svcr = target->thread.svcr; + + switch (type) { + case ARM64_VEC_SVE: + target->thread.svcr &= ~SVCR_SM_MASK; + break; + case ARM64_VEC_SME: + target->thread.svcr |= SVCR_SM_MASK; + break; + default: + WARN_ON_ONCE(1); + return -EINVAL; + } + + /* + * If we switched then invalidate any existing SVE + * state and ensure there's storage. + */ + if (target->thread.svcr != old_svcr) + sve_alloc(target); + } /* Registers: FPSIMD-only case */ @@ -828,10 +892,15 @@ static int sve_set(struct task_struct *target, ret = __fpr_set(target, regset, pos, count, kbuf, ubuf, SVE_PT_FPSIMD_OFFSET); clear_tsk_thread_flag(target, TIF_SVE); + if (type == ARM64_VEC_SME) + fpsimd_force_sync_to_sve(target); goto out; } - /* Otherwise: full SVE case */ + /* + * Otherwise: no registers or full SVE case. For backwards + * compatibility reasons we treat empty flags as SVE registers. + */ /* * If setting a different VL from the requested VL and there is @@ -852,8 +921,9 @@ static int sve_set(struct task_struct *target, /* * Ensure target->thread.sve_state is up to date with target's - * FPSIMD regs, so that a short copyin leaves trailing registers - * unmodified. + * FPSIMD regs, so that a short copyin leaves trailing + * registers unmodified. Always enable SVE even if going into + * streaming mode. */ fpsimd_sync_to_sve(target); set_tsk_thread_flag(target, TIF_SVE); @@ -889,8 +959,181 @@ out: return ret; } +static int sve_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + if (!system_supports_sve()) + return -EINVAL; + + return sve_set_common(target, regset, pos, count, kbuf, ubuf, + ARM64_VEC_SVE); +} + #endif /* CONFIG_ARM64_SVE */ +#ifdef CONFIG_ARM64_SME + +static int ssve_get(struct task_struct *target, + const struct user_regset *regset, + struct membuf to) +{ + if (!system_supports_sme()) + return -EINVAL; + + return sve_get_common(target, regset, to, ARM64_VEC_SME); +} + +static int ssve_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + if (!system_supports_sme()) + return -EINVAL; + + return sve_set_common(target, regset, pos, count, kbuf, ubuf, + ARM64_VEC_SME); +} + +static int za_get(struct task_struct *target, + const struct user_regset *regset, + struct membuf to) +{ + struct user_za_header header; + unsigned int vq; + unsigned long start, end; + + if (!system_supports_sme()) + return -EINVAL; + + /* Header */ + memset(&header, 0, sizeof(header)); + + if (test_tsk_thread_flag(target, TIF_SME_VL_INHERIT)) + header.flags |= ZA_PT_VL_INHERIT; + + header.vl = task_get_sme_vl(target); + vq = sve_vq_from_vl(header.vl); + header.max_vl = sme_max_vl(); + header.max_size = ZA_PT_SIZE(vq); + + /* If ZA is not active there is only the header */ + if (thread_za_enabled(&target->thread)) + header.size = ZA_PT_SIZE(vq); + else + header.size = ZA_PT_ZA_OFFSET; + + membuf_write(&to, &header, sizeof(header)); + + BUILD_BUG_ON(ZA_PT_ZA_OFFSET != sizeof(header)); + end = ZA_PT_ZA_OFFSET; + + if (target == current) + fpsimd_preserve_current_state(); + + /* Any register data to include? */ + if (thread_za_enabled(&target->thread)) { + start = end; + end = ZA_PT_SIZE(vq); + membuf_write(&to, target->thread.za_state, end - start); + } + + /* Zero any trailing padding */ + start = end; + end = ALIGN(header.size, SVE_VQ_BYTES); + return membuf_zero(&to, end - start); +} + +static int za_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + int ret; + struct user_za_header header; + unsigned int vq; + unsigned long start, end; + + if (!system_supports_sme()) + return -EINVAL; + + /* Header */ + if (count < sizeof(header)) + return -EINVAL; + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &header, + 0, sizeof(header)); + if (ret) + goto out; + + /* + * All current ZA_PT_* flags are consumed by + * vec_set_vector_length(), which will also validate them for + * us: + */ + ret = vec_set_vector_length(target, ARM64_VEC_SME, header.vl, + ((unsigned long)header.flags) << 16); + if (ret) + goto out; + + /* Actual VL set may be less than the user asked for: */ + vq = sve_vq_from_vl(task_get_sme_vl(target)); + + /* Ensure there is some SVE storage for streaming mode */ + if (!target->thread.sve_state) { + sve_alloc(target); + if (!target->thread.sve_state) { + clear_thread_flag(TIF_SME); + ret = -ENOMEM; + goto out; + } + } + + /* Allocate/reinit ZA storage */ + sme_alloc(target); + if (!target->thread.za_state) { + ret = -ENOMEM; + clear_tsk_thread_flag(target, TIF_SME); + goto out; + } + + /* If there is no data then disable ZA */ + if (!count) { + target->thread.svcr &= ~SVCR_ZA_MASK; + goto out; + } + + /* + * If setting a different VL from the requested VL and there is + * register data, the data layout will be wrong: don't even + * try to set the registers in this case. + */ + if (vq != sve_vq_from_vl(header.vl)) { + ret = -EIO; + goto out; + } + + BUILD_BUG_ON(ZA_PT_ZA_OFFSET != sizeof(header)); + start = ZA_PT_ZA_OFFSET; + end = ZA_PT_SIZE(vq); + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + target->thread.za_state, + start, end); + if (ret) + goto out; + + /* Mark ZA as active and let userspace use it */ + set_tsk_thread_flag(target, TIF_SME); + target->thread.svcr |= SVCR_ZA_MASK; + +out: + fpsimd_flush_task_state(target); + return ret; +} + +#endif /* CONFIG_ARM64_SME */ + #ifdef CONFIG_ARM64_PTR_AUTH static int pac_mask_get(struct task_struct *target, const struct user_regset *regset, @@ -1108,6 +1351,10 @@ enum aarch64_regset { #ifdef CONFIG_ARM64_SVE REGSET_SVE, #endif +#ifdef CONFIG_ARM64_SVE + REGSET_SSVE, + REGSET_ZA, +#endif #ifdef CONFIG_ARM64_PTR_AUTH REGSET_PAC_MASK, REGSET_PAC_ENABLED_KEYS, @@ -1188,6 +1435,33 @@ static const struct user_regset aarch64_regsets[] = { .set = sve_set, }, #endif +#ifdef CONFIG_ARM64_SME + [REGSET_SSVE] = { /* Streaming mode SVE */ + .core_note_type = NT_ARM_SSVE, + .n = DIV_ROUND_UP(SVE_PT_SIZE(SME_VQ_MAX, SVE_PT_REGS_SVE), + SVE_VQ_BYTES), + .size = SVE_VQ_BYTES, + .align = SVE_VQ_BYTES, + .regset_get = ssve_get, + .set = ssve_set, + }, + [REGSET_ZA] = { /* SME ZA */ + .core_note_type = NT_ARM_ZA, + /* + * ZA is a single register but it's variably sized and + * the ptrace core requires that the size of any data + * be an exact multiple of the configured register + * size so report as though we had SVE_VQ_BYTES + * registers. These values aren't exposed to + * userspace. + */ + .n = DIV_ROUND_UP(ZA_PT_SIZE(SME_VQ_MAX), SVE_VQ_BYTES), + .size = SVE_VQ_BYTES, + .align = SVE_VQ_BYTES, + .regset_get = za_get, + .set = za_set, + }, +#endif #ifdef CONFIG_ARM64_PTR_AUTH [REGSET_PAC_MASK] = { .core_note_type = NT_ARM_PAC_MASK, diff --git a/arch/arm64/kernel/relocate_kernel.S b/arch/arm64/kernel/relocate_kernel.S index f0a3df9e18a3..413f899e4ac6 100644 --- a/arch/arm64/kernel/relocate_kernel.S +++ b/arch/arm64/kernel/relocate_kernel.S @@ -37,6 +37,15 @@ * safe memory that has been set up to be preserved during the copy operation. */ SYM_CODE_START(arm64_relocate_new_kernel) + /* + * The kimage structure isn't allocated specially and may be clobbered + * during relocation. We must load any values we need from it prior to + * any relocation occurring. + */ + ldr x28, [x0, #KIMAGE_START] + ldr x27, [x0, #KIMAGE_ARCH_EL2_VECTORS] + ldr x26, [x0, #KIMAGE_ARCH_DTB_MEM] + /* Setup the list loop variables. */ ldr x18, [x0, #KIMAGE_ARCH_ZERO_PAGE] /* x18 = zero page for BBM */ ldr x17, [x0, #KIMAGE_ARCH_TTBR1] /* x17 = linear map copy */ @@ -72,21 +81,20 @@ SYM_CODE_START(arm64_relocate_new_kernel) ic iallu dsb nsh isb - ldr x4, [x0, #KIMAGE_START] /* relocation start */ - ldr x1, [x0, #KIMAGE_ARCH_EL2_VECTORS] /* relocation start */ - ldr x0, [x0, #KIMAGE_ARCH_DTB_MEM] /* dtb address */ turn_off_mmu x12, x13 /* Start new image. */ - cbz x1, .Lel1 - mov x1, x4 /* relocation start */ - mov x2, x0 /* dtb address */ + cbz x27, .Lel1 + mov x1, x28 /* kernel entry point */ + mov x2, x26 /* dtb address */ mov x3, xzr mov x4, xzr mov x0, #HVC_SOFT_RESTART hvc #0 /* Jumps from el2 */ .Lel1: + mov x0, x26 /* dtb address */ + mov x1, xzr mov x2, xzr mov x3, xzr - br x4 /* Jumps from el1 */ + br x28 /* Jumps from el1 */ SYM_CODE_END(arm64_relocate_new_kernel) diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index 3505789cf4bd..fea3223704b6 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -225,6 +225,8 @@ static void __init request_standard_resources(void) kernel_code.end = __pa_symbol(__init_begin - 1); kernel_data.start = __pa_symbol(_sdata); kernel_data.end = __pa_symbol(_end - 1); + insert_resource(&iomem_resource, &kernel_code); + insert_resource(&iomem_resource, &kernel_data); num_standard_resources = memblock.memory.cnt; res_size = num_standard_resources * sizeof(*standard_resources); @@ -246,20 +248,7 @@ static void __init request_standard_resources(void) res->end = __pfn_to_phys(memblock_region_memory_end_pfn(region)) - 1; } - request_resource(&iomem_resource, res); - - if (kernel_code.start >= res->start && - kernel_code.end <= res->end) - request_resource(res, &kernel_code); - if (kernel_data.start >= res->start && - kernel_data.end <= res->end) - request_resource(res, &kernel_data); -#ifdef CONFIG_KEXEC_CORE - /* Userspace will find "Crash kernel" region in /proc/iomem. */ - if (crashk_res.end && crashk_res.start >= res->start && - crashk_res.end <= res->end) - request_resource(res, &crashk_res); -#endif + insert_resource(&iomem_resource, res); } } diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index 4a4122ef6f39..edb2d9206a78 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -56,6 +56,7 @@ struct rt_sigframe_user_layout { unsigned long fpsimd_offset; unsigned long esr_offset; unsigned long sve_offset; + unsigned long za_offset; unsigned long extra_offset; unsigned long end_offset; }; @@ -218,6 +219,7 @@ static int restore_fpsimd_context(struct fpsimd_context __user *ctx) struct user_ctxs { struct fpsimd_context __user *fpsimd; struct sve_context __user *sve; + struct za_context __user *za; }; #ifdef CONFIG_ARM64_SVE @@ -226,11 +228,17 @@ static int preserve_sve_context(struct sve_context __user *ctx) { int err = 0; u16 reserved[ARRAY_SIZE(ctx->__reserved)]; + u16 flags = 0; unsigned int vl = task_get_sve_vl(current); unsigned int vq = 0; - if (test_thread_flag(TIF_SVE)) + if (thread_sm_enabled(¤t->thread)) { + vl = task_get_sme_vl(current); vq = sve_vq_from_vl(vl); + flags |= SVE_SIG_FLAG_SM; + } else if (test_thread_flag(TIF_SVE)) { + vq = sve_vq_from_vl(vl); + } memset(reserved, 0, sizeof(reserved)); @@ -238,6 +246,7 @@ static int preserve_sve_context(struct sve_context __user *ctx) __put_user_error(round_up(SVE_SIG_CONTEXT_SIZE(vq), 16), &ctx->head.size, err); __put_user_error(vl, &ctx->vl, err); + __put_user_error(flags, &ctx->flags, err); BUILD_BUG_ON(sizeof(ctx->__reserved) != sizeof(reserved)); err |= __copy_to_user(&ctx->__reserved, reserved, sizeof(reserved)); @@ -258,18 +267,28 @@ static int preserve_sve_context(struct sve_context __user *ctx) static int restore_sve_fpsimd_context(struct user_ctxs *user) { int err; - unsigned int vq; + unsigned int vl, vq; struct user_fpsimd_state fpsimd; struct sve_context sve; if (__copy_from_user(&sve, user->sve, sizeof(sve))) return -EFAULT; - if (sve.vl != task_get_sve_vl(current)) + if (sve.flags & SVE_SIG_FLAG_SM) { + if (!system_supports_sme()) + return -EINVAL; + + vl = task_get_sme_vl(current); + } else { + vl = task_get_sve_vl(current); + } + + if (sve.vl != vl) return -EINVAL; if (sve.head.size <= sizeof(*user->sve)) { clear_thread_flag(TIF_SVE); + current->thread.svcr &= ~SVCR_SM_MASK; goto fpsimd_only; } @@ -301,7 +320,10 @@ static int restore_sve_fpsimd_context(struct user_ctxs *user) if (err) return -EFAULT; - set_thread_flag(TIF_SVE); + if (sve.flags & SVE_SIG_FLAG_SM) + current->thread.svcr |= SVCR_SM_MASK; + else + set_thread_flag(TIF_SVE); fpsimd_only: /* copy the FP and status/control registers */ @@ -326,6 +348,101 @@ extern int restore_sve_fpsimd_context(struct user_ctxs *user); #endif /* ! CONFIG_ARM64_SVE */ +#ifdef CONFIG_ARM64_SME + +static int preserve_za_context(struct za_context __user *ctx) +{ + int err = 0; + u16 reserved[ARRAY_SIZE(ctx->__reserved)]; + unsigned int vl = task_get_sme_vl(current); + unsigned int vq; + + if (thread_za_enabled(¤t->thread)) + vq = sve_vq_from_vl(vl); + else + vq = 0; + + memset(reserved, 0, sizeof(reserved)); + + __put_user_error(ZA_MAGIC, &ctx->head.magic, err); + __put_user_error(round_up(ZA_SIG_CONTEXT_SIZE(vq), 16), + &ctx->head.size, err); + __put_user_error(vl, &ctx->vl, err); + BUILD_BUG_ON(sizeof(ctx->__reserved) != sizeof(reserved)); + err |= __copy_to_user(&ctx->__reserved, reserved, sizeof(reserved)); + + if (vq) { + /* + * This assumes that the ZA state has already been saved to + * the task struct by calling the function + * fpsimd_signal_preserve_current_state(). + */ + err |= __copy_to_user((char __user *)ctx + ZA_SIG_REGS_OFFSET, + current->thread.za_state, + ZA_SIG_REGS_SIZE(vq)); + } + + return err ? -EFAULT : 0; +} + +static int restore_za_context(struct user_ctxs __user *user) +{ + int err; + unsigned int vq; + struct za_context za; + + if (__copy_from_user(&za, user->za, sizeof(za))) + return -EFAULT; + + if (za.vl != task_get_sme_vl(current)) + return -EINVAL; + + if (za.head.size <= sizeof(*user->za)) { + current->thread.svcr &= ~SVCR_ZA_MASK; + return 0; + } + + vq = sve_vq_from_vl(za.vl); + + if (za.head.size < ZA_SIG_CONTEXT_SIZE(vq)) + return -EINVAL; + + /* + * Careful: we are about __copy_from_user() directly into + * thread.za_state with preemption enabled, so protection is + * needed to prevent a racing context switch from writing stale + * registers back over the new data. + */ + + fpsimd_flush_task_state(current); + /* From now, fpsimd_thread_switch() won't touch thread.sve_state */ + + sme_alloc(current); + if (!current->thread.za_state) { + current->thread.svcr &= ~SVCR_ZA_MASK; + clear_thread_flag(TIF_SME); + return -ENOMEM; + } + + err = __copy_from_user(current->thread.za_state, + (char __user const *)user->za + + ZA_SIG_REGS_OFFSET, + ZA_SIG_REGS_SIZE(vq)); + if (err) + return -EFAULT; + + set_thread_flag(TIF_SME); + current->thread.svcr |= SVCR_ZA_MASK; + + return 0; +} +#else /* ! CONFIG_ARM64_SME */ + +/* Turn any non-optimised out attempts to use these into a link error: */ +extern int preserve_za_context(void __user *ctx); +extern int restore_za_context(struct user_ctxs *user); + +#endif /* ! CONFIG_ARM64_SME */ static int parse_user_sigframe(struct user_ctxs *user, struct rt_sigframe __user *sf) @@ -340,6 +457,7 @@ static int parse_user_sigframe(struct user_ctxs *user, user->fpsimd = NULL; user->sve = NULL; + user->za = NULL; if (!IS_ALIGNED((unsigned long)base, 16)) goto invalid; @@ -393,7 +511,7 @@ static int parse_user_sigframe(struct user_ctxs *user, break; case SVE_MAGIC: - if (!system_supports_sve()) + if (!system_supports_sve() && !system_supports_sme()) goto invalid; if (user->sve) @@ -405,6 +523,19 @@ static int parse_user_sigframe(struct user_ctxs *user, user->sve = (struct sve_context __user *)head; break; + case ZA_MAGIC: + if (!system_supports_sme()) + goto invalid; + + if (user->za) + goto invalid; + + if (size < sizeof(*user->za)) + goto invalid; + + user->za = (struct za_context __user *)head; + break; + case EXTRA_MAGIC: if (have_extra_context) goto invalid; @@ -528,6 +659,9 @@ static int restore_sigframe(struct pt_regs *regs, } } + if (err == 0 && system_supports_sme() && user.za) + err = restore_za_context(&user); + return err; } @@ -594,11 +728,12 @@ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user, if (system_supports_sve()) { unsigned int vq = 0; - if (add_all || test_thread_flag(TIF_SVE)) { - int vl = sve_max_vl(); + if (add_all || test_thread_flag(TIF_SVE) || + thread_sm_enabled(¤t->thread)) { + int vl = max(sve_max_vl(), sme_max_vl()); if (!add_all) - vl = task_get_sve_vl(current); + vl = thread_get_cur_vl(¤t->thread); vq = sve_vq_from_vl(vl); } @@ -609,6 +744,24 @@ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user, return err; } + if (system_supports_sme()) { + unsigned int vl; + unsigned int vq = 0; + + if (add_all) + vl = sme_max_vl(); + else + vl = task_get_sme_vl(current); + + if (thread_za_enabled(¤t->thread)) + vq = sve_vq_from_vl(vl); + + err = sigframe_alloc(user, &user->za_offset, + ZA_SIG_CONTEXT_SIZE(vq)); + if (err) + return err; + } + return sigframe_alloc_end(user); } @@ -649,13 +802,21 @@ static int setup_sigframe(struct rt_sigframe_user_layout *user, __put_user_error(current->thread.fault_code, &esr_ctx->esr, err); } - /* Scalable Vector Extension state, if present */ - if (system_supports_sve() && err == 0 && user->sve_offset) { + /* Scalable Vector Extension state (including streaming), if present */ + if ((system_supports_sve() || system_supports_sme()) && + err == 0 && user->sve_offset) { struct sve_context __user *sve_ctx = apply_user_offset(user, user->sve_offset); err |= preserve_sve_context(sve_ctx); } + /* ZA state if present */ + if (system_supports_sme() && err == 0 && user->za_offset) { + struct za_context __user *za_ctx = + apply_user_offset(user, user->za_offset); + err |= preserve_za_context(za_ctx); + } + if (err == 0 && user->extra_offset) { char __user *sfp = (char __user *)user->sigframe; char __user *userp = @@ -759,6 +920,13 @@ static void setup_return(struct pt_regs *regs, struct k_sigaction *ka, /* TCO (Tag Check Override) always cleared for signal handlers */ regs->pstate &= ~PSR_TCO_BIT; + /* Signal handlers are invoked with ZA and streaming mode disabled */ + if (system_supports_sme()) { + current->thread.svcr &= ~(SVCR_ZA_MASK | + SVCR_SM_MASK); + sme_smstop(); + } + if (ka->sa.sa_flags & SA_RESTORER) sigtramp = ka->sa.sa_restorer; else @@ -1011,6 +1179,7 @@ static_assert(offsetof(siginfo_t, si_upper) == 0x28); static_assert(offsetof(siginfo_t, si_pkey) == 0x20); static_assert(offsetof(siginfo_t, si_perf_data) == 0x18); static_assert(offsetof(siginfo_t, si_perf_type) == 0x20); +static_assert(offsetof(siginfo_t, si_perf_flags) == 0x24); static_assert(offsetof(siginfo_t, si_band) == 0x10); static_assert(offsetof(siginfo_t, si_fd) == 0x18); static_assert(offsetof(siginfo_t, si_call_addr) == 0x10); diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c index d984282b979f..4700f8522d27 100644 --- a/arch/arm64/kernel/signal32.c +++ b/arch/arm64/kernel/signal32.c @@ -487,6 +487,7 @@ static_assert(offsetof(compat_siginfo_t, si_upper) == 0x18); static_assert(offsetof(compat_siginfo_t, si_pkey) == 0x14); static_assert(offsetof(compat_siginfo_t, si_perf_data) == 0x10); static_assert(offsetof(compat_siginfo_t, si_perf_type) == 0x14); +static_assert(offsetof(compat_siginfo_t, si_perf_flags) == 0x18); static_assert(offsetof(compat_siginfo_t, si_band) == 0x0c); static_assert(offsetof(compat_siginfo_t, si_fd) == 0x10); static_assert(offsetof(compat_siginfo_t, si_call_addr) == 0x0c); diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index 27df5c1e6baa..62ed361a4376 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -234,6 +234,7 @@ asmlinkage notrace void secondary_start_kernel(void) * Log the CPU info before it is marked online and might get read. */ cpuinfo_store_cpu(); + store_cpu_topology(cpu); /* * Enable GIC and timers. @@ -242,7 +243,6 @@ asmlinkage notrace void secondary_start_kernel(void) ipi_setup(cpu); - store_cpu_topology(cpu); numa_add_cpu(cpu); /* @@ -512,6 +512,7 @@ struct acpi_madt_generic_interrupt *acpi_cpu_get_madt_gicc(int cpu) { return &cpu_madt_gicc[cpu]; } +EXPORT_SYMBOL_GPL(acpi_cpu_get_madt_gicc); /* * acpi_map_gic_cpu_interface - parse processor MADT entry diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c index e4103e085681..0467cb79f080 100644 --- a/arch/arm64/kernel/stacktrace.c +++ b/arch/arm64/kernel/stacktrace.c @@ -19,43 +19,60 @@ #include <asm/stacktrace.h> /* - * AArch64 PCS assigns the frame pointer to x29. + * A snapshot of a frame record or fp/lr register values, along with some + * accounting information necessary for robust unwinding. * - * A simple function prologue looks like this: - * sub sp, sp, #0x10 - * stp x29, x30, [sp] - * mov x29, sp + * @fp: The fp value in the frame record (or the real fp) + * @pc: The lr value in the frame record (or the real lr) * - * A simple function epilogue looks like this: - * mov sp, x29 - * ldp x29, x30, [sp] - * add sp, sp, #0x10 + * @stacks_done: Stacks which have been entirely unwound, for which it is no + * longer valid to unwind to. + * + * @prev_fp: The fp that pointed to this frame record, or a synthetic value + * of 0. This is used to ensure that within a stack, each + * subsequent frame record is at an increasing address. + * @prev_type: The type of stack this frame record was on, or a synthetic + * value of STACK_TYPE_UNKNOWN. This is used to detect a + * transition from one stack to another. + * + * @kr_cur: When KRETPROBES is selected, holds the kretprobe instance + * associated with the most recently encountered replacement lr + * value. */ +struct unwind_state { + unsigned long fp; + unsigned long pc; + DECLARE_BITMAP(stacks_done, __NR_STACK_TYPES); + unsigned long prev_fp; + enum stack_type prev_type; +#ifdef CONFIG_KRETPROBES + struct llist_node *kr_cur; +#endif +}; - -static notrace void start_backtrace(struct stackframe *frame, unsigned long fp, - unsigned long pc) +static notrace void unwind_init(struct unwind_state *state, unsigned long fp, + unsigned long pc) { - frame->fp = fp; - frame->pc = pc; + state->fp = fp; + state->pc = pc; #ifdef CONFIG_KRETPROBES - frame->kr_cur = NULL; + state->kr_cur = NULL; #endif /* * Prime the first unwind. * - * In unwind_frame() we'll check that the FP points to a valid stack, + * In unwind_next() we'll check that the FP points to a valid stack, * which can't be STACK_TYPE_UNKNOWN, and the first unwind will be * treated as a transition to whichever stack that happens to be. The * prev_fp value won't be used, but we set it to 0 such that it is * definitely not an accessible stack address. */ - bitmap_zero(frame->stacks_done, __NR_STACK_TYPES); - frame->prev_fp = 0; - frame->prev_type = STACK_TYPE_UNKNOWN; + bitmap_zero(state->stacks_done, __NR_STACK_TYPES); + state->prev_fp = 0; + state->prev_type = STACK_TYPE_UNKNOWN; } -NOKPROBE_SYMBOL(start_backtrace); +NOKPROBE_SYMBOL(unwind_init); /* * Unwind from one frame record (A) to the next frame record (B). @@ -64,15 +81,12 @@ NOKPROBE_SYMBOL(start_backtrace); * records (e.g. a cycle), determined based on the location and fp value of A * and the location (but not the fp value) of B. */ -static int notrace unwind_frame(struct task_struct *tsk, - struct stackframe *frame) +static int notrace unwind_next(struct task_struct *tsk, + struct unwind_state *state) { - unsigned long fp = frame->fp; + unsigned long fp = state->fp; struct stack_info info; - if (!tsk) - tsk = current; - /* Final frame; nothing to unwind */ if (fp == (unsigned long)task_pt_regs(tsk)->stackframe) return -ENOENT; @@ -83,7 +97,7 @@ static int notrace unwind_frame(struct task_struct *tsk, if (!on_accessible_stack(tsk, fp, 16, &info)) return -EINVAL; - if (test_bit(info.type, frame->stacks_done)) + if (test_bit(info.type, state->stacks_done)) return -EINVAL; /* @@ -99,27 +113,27 @@ static int notrace unwind_frame(struct task_struct *tsk, * stack to another, it's never valid to unwind back to that first * stack. */ - if (info.type == frame->prev_type) { - if (fp <= frame->prev_fp) + if (info.type == state->prev_type) { + if (fp <= state->prev_fp) return -EINVAL; } else { - set_bit(frame->prev_type, frame->stacks_done); + set_bit(state->prev_type, state->stacks_done); } /* * Record this frame record's values and location. The prev_fp and - * prev_type are only meaningful to the next unwind_frame() invocation. + * prev_type are only meaningful to the next unwind_next() invocation. */ - frame->fp = READ_ONCE_NOCHECK(*(unsigned long *)(fp)); - frame->pc = READ_ONCE_NOCHECK(*(unsigned long *)(fp + 8)); - frame->prev_fp = fp; - frame->prev_type = info.type; + state->fp = READ_ONCE_NOCHECK(*(unsigned long *)(fp)); + state->pc = READ_ONCE_NOCHECK(*(unsigned long *)(fp + 8)); + state->prev_fp = fp; + state->prev_type = info.type; - frame->pc = ptrauth_strip_insn_pac(frame->pc); + state->pc = ptrauth_strip_insn_pac(state->pc); #ifdef CONFIG_FUNCTION_GRAPH_TRACER if (tsk->ret_stack && - (frame->pc == (unsigned long)return_to_handler)) { + (state->pc == (unsigned long)return_to_handler)) { unsigned long orig_pc; /* * This is a case where function graph tracer has @@ -127,37 +141,37 @@ static int notrace unwind_frame(struct task_struct *tsk, * to hook a function return. * So replace it to an original value. */ - orig_pc = ftrace_graph_ret_addr(tsk, NULL, frame->pc, - (void *)frame->fp); - if (WARN_ON_ONCE(frame->pc == orig_pc)) + orig_pc = ftrace_graph_ret_addr(tsk, NULL, state->pc, + (void *)state->fp); + if (WARN_ON_ONCE(state->pc == orig_pc)) return -EINVAL; - frame->pc = orig_pc; + state->pc = orig_pc; } #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ #ifdef CONFIG_KRETPROBES - if (is_kretprobe_trampoline(frame->pc)) - frame->pc = kretprobe_find_ret_addr(tsk, (void *)frame->fp, &frame->kr_cur); + if (is_kretprobe_trampoline(state->pc)) + state->pc = kretprobe_find_ret_addr(tsk, (void *)state->fp, &state->kr_cur); #endif return 0; } -NOKPROBE_SYMBOL(unwind_frame); +NOKPROBE_SYMBOL(unwind_next); -static void notrace walk_stackframe(struct task_struct *tsk, - struct stackframe *frame, - bool (*fn)(void *, unsigned long), void *data) +static void notrace unwind(struct task_struct *tsk, + struct unwind_state *state, + stack_trace_consume_fn consume_entry, void *cookie) { while (1) { int ret; - if (!fn(data, frame->pc)) + if (!consume_entry(cookie, state->pc)) break; - ret = unwind_frame(tsk, frame); + ret = unwind_next(tsk, state); if (ret < 0) break; } } -NOKPROBE_SYMBOL(walk_stackframe); +NOKPROBE_SYMBOL(unwind); static bool dump_backtrace_entry(void *arg, unsigned long where) { @@ -196,17 +210,17 @@ noinline notrace void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie, struct task_struct *task, struct pt_regs *regs) { - struct stackframe frame; + struct unwind_state state; if (regs) - start_backtrace(&frame, regs->regs[29], regs->pc); + unwind_init(&state, regs->regs[29], regs->pc); else if (task == current) - start_backtrace(&frame, + unwind_init(&state, (unsigned long)__builtin_frame_address(1), (unsigned long)__builtin_return_address(0)); else - start_backtrace(&frame, thread_saved_fp(task), + unwind_init(&state, thread_saved_fp(task), thread_saved_pc(task)); - walk_stackframe(task, &frame, consume_entry, cookie); + unwind(task, &state, consume_entry, cookie); } diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c index 19ee7c33769d..2b0887e58a7c 100644 --- a/arch/arm64/kernel/suspend.c +++ b/arch/arm64/kernel/suspend.c @@ -140,7 +140,7 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long)) /* * Restore pstate flags. OS lock and mdscr have been already * restored, so from this point onwards, debugging is fully - * renabled if it was enabled when core started shutdown. + * reenabled if it was enabled when core started shutdown. */ local_daif_restore(flags); diff --git a/arch/arm64/kernel/sys_compat.c b/arch/arm64/kernel/sys_compat.c index 12c6864e51e1..df14336c3a29 100644 --- a/arch/arm64/kernel/sys_compat.c +++ b/arch/arm64/kernel/sys_compat.c @@ -113,6 +113,6 @@ long compat_arm_syscall(struct pt_regs *regs, int scno) addr = instruction_pointer(regs) - (compat_thumb_mode(regs) ? 2 : 4); arm64_notify_die("Oops - bad compat syscall(2)", regs, - SIGILL, ILL_ILLTRP, addr, scno); + SIGILL, ILL_ILLTRP, addr, 0); return 0; } diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c index c938603b3ba0..733451fe7e41 100644 --- a/arch/arm64/kernel/syscall.c +++ b/arch/arm64/kernel/syscall.c @@ -158,11 +158,36 @@ trace_exit: syscall_trace_exit(regs); } -static inline void sve_user_discard(void) +/* + * As per the ABI exit SME streaming mode and clear the SVE state not + * shared with FPSIMD on syscall entry. + */ +static inline void fp_user_discard(void) { + /* + * If SME is active then exit streaming mode. If ZA is active + * then flush the SVE registers but leave userspace access to + * both SVE and SME enabled, otherwise disable SME for the + * task and fall through to disabling SVE too. This means + * that after a syscall we never have any streaming mode + * register state to track, if this changes the KVM code will + * need updating. + */ + if (system_supports_sme() && test_thread_flag(TIF_SME)) { + u64 svcr = read_sysreg_s(SYS_SVCR); + + if (svcr & SVCR_SM_MASK) + sme_smstop_sm(); + } + if (!system_supports_sve()) return; + /* + * If SME is not active then disable SVE, the registers will + * be cleared when userspace next attempts to access them and + * we do not need to track the SVE register state until then. + */ clear_thread_flag(TIF_SVE); /* @@ -177,7 +202,7 @@ static inline void sve_user_discard(void) void do_el0_svc(struct pt_regs *regs) { - sve_user_discard(); + fp_user_discard(); el0_svc_common(regs, regs->regs[8], __NR_syscalls, sys_call_table); } diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index 0529fd57567e..9ac7a81b79be 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -242,7 +242,7 @@ static void arm64_show_signal(int signo, const char *str) static DEFINE_RATELIMIT_STATE(rs, DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST); struct task_struct *tsk = current; - unsigned int esr = tsk->thread.fault_code; + unsigned long esr = tsk->thread.fault_code; struct pt_regs *regs = task_pt_regs(tsk); /* Leave if the signal won't be shown */ @@ -253,7 +253,7 @@ static void arm64_show_signal(int signo, const char *str) pr_info("%s[%d]: unhandled exception: ", tsk->comm, task_pid_nr(tsk)); if (esr) - pr_cont("%s, ESR 0x%08x, ", esr_get_class_string(esr), esr); + pr_cont("%s, ESR 0x%016lx, ", esr_get_class_string(esr), esr); pr_cont("%s", str); print_vma_addr(KERN_CONT " in ", regs->pc); @@ -287,7 +287,7 @@ void arm64_force_sig_ptrace_errno_trap(int errno, unsigned long far, void arm64_notify_die(const char *str, struct pt_regs *regs, int signo, int sicode, unsigned long far, - int err) + unsigned long err) { if (user_mode(regs)) { WARN_ON(regs != current_pt_regs()); @@ -439,7 +439,7 @@ exit: return fn ? fn(regs, instr) : 1; } -void force_signal_inject(int signal, int code, unsigned long address, unsigned int err) +void force_signal_inject(int signal, int code, unsigned long address, unsigned long err) { const char *desc; struct pt_regs *regs = current_pt_regs(); @@ -506,7 +506,7 @@ void do_bti(struct pt_regs *regs) } NOKPROBE_SYMBOL(do_bti); -void do_ptrauth_fault(struct pt_regs *regs, unsigned int esr) +void do_ptrauth_fault(struct pt_regs *regs, unsigned long esr) { /* * Unexpected FPAC exception or pointer authentication failure in @@ -532,7 +532,7 @@ NOKPROBE_SYMBOL(do_ptrauth_fault); uaccess_ttbr0_disable(); \ } -static void user_cache_maint_handler(unsigned int esr, struct pt_regs *regs) +static void user_cache_maint_handler(unsigned long esr, struct pt_regs *regs) { unsigned long tagged_address, address; int rt = ESR_ELx_SYS64_ISS_RT(esr); @@ -572,7 +572,7 @@ static void user_cache_maint_handler(unsigned int esr, struct pt_regs *regs) arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE); } -static void ctr_read_handler(unsigned int esr, struct pt_regs *regs) +static void ctr_read_handler(unsigned long esr, struct pt_regs *regs) { int rt = ESR_ELx_SYS64_ISS_RT(esr); unsigned long val = arm64_ftr_reg_user_value(&arm64_ftr_reg_ctrel0); @@ -591,7 +591,7 @@ static void ctr_read_handler(unsigned int esr, struct pt_regs *regs) arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE); } -static void cntvct_read_handler(unsigned int esr, struct pt_regs *regs) +static void cntvct_read_handler(unsigned long esr, struct pt_regs *regs) { int rt = ESR_ELx_SYS64_ISS_RT(esr); @@ -599,7 +599,7 @@ static void cntvct_read_handler(unsigned int esr, struct pt_regs *regs) arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE); } -static void cntfrq_read_handler(unsigned int esr, struct pt_regs *regs) +static void cntfrq_read_handler(unsigned long esr, struct pt_regs *regs) { int rt = ESR_ELx_SYS64_ISS_RT(esr); @@ -607,7 +607,7 @@ static void cntfrq_read_handler(unsigned int esr, struct pt_regs *regs) arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE); } -static void mrs_handler(unsigned int esr, struct pt_regs *regs) +static void mrs_handler(unsigned long esr, struct pt_regs *regs) { u32 sysreg, rt; @@ -618,15 +618,15 @@ static void mrs_handler(unsigned int esr, struct pt_regs *regs) force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc, 0); } -static void wfi_handler(unsigned int esr, struct pt_regs *regs) +static void wfi_handler(unsigned long esr, struct pt_regs *regs) { arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE); } struct sys64_hook { - unsigned int esr_mask; - unsigned int esr_val; - void (*handler)(unsigned int esr, struct pt_regs *regs); + unsigned long esr_mask; + unsigned long esr_val; + void (*handler)(unsigned long esr, struct pt_regs *regs); }; static const struct sys64_hook sys64_hooks[] = { @@ -675,7 +675,7 @@ static const struct sys64_hook sys64_hooks[] = { }; #ifdef CONFIG_COMPAT -static bool cp15_cond_valid(unsigned int esr, struct pt_regs *regs) +static bool cp15_cond_valid(unsigned long esr, struct pt_regs *regs) { int cond; @@ -695,7 +695,7 @@ static bool cp15_cond_valid(unsigned int esr, struct pt_regs *regs) return aarch32_opcode_cond_checks[cond](regs->pstate); } -static void compat_cntfrq_read_handler(unsigned int esr, struct pt_regs *regs) +static void compat_cntfrq_read_handler(unsigned long esr, struct pt_regs *regs) { int reg = (esr & ESR_ELx_CP15_32_ISS_RT_MASK) >> ESR_ELx_CP15_32_ISS_RT_SHIFT; @@ -712,7 +712,7 @@ static const struct sys64_hook cp15_32_hooks[] = { {}, }; -static void compat_cntvct_read_handler(unsigned int esr, struct pt_regs *regs) +static void compat_cntvct_read_handler(unsigned long esr, struct pt_regs *regs) { int rt = (esr & ESR_ELx_CP15_64_ISS_RT_MASK) >> ESR_ELx_CP15_64_ISS_RT_SHIFT; int rt2 = (esr & ESR_ELx_CP15_64_ISS_RT2_MASK) >> ESR_ELx_CP15_64_ISS_RT2_SHIFT; @@ -737,7 +737,7 @@ static const struct sys64_hook cp15_64_hooks[] = { {}, }; -void do_cp15instr(unsigned int esr, struct pt_regs *regs) +void do_cp15instr(unsigned long esr, struct pt_regs *regs) { const struct sys64_hook *hook, *hook_base; @@ -778,7 +778,7 @@ void do_cp15instr(unsigned int esr, struct pt_regs *regs) NOKPROBE_SYMBOL(do_cp15instr); #endif -void do_sysinstr(unsigned int esr, struct pt_regs *regs) +void do_sysinstr(unsigned long esr, struct pt_regs *regs) { const struct sys64_hook *hook; @@ -821,6 +821,7 @@ static const char *esr_class_str[] = { [ESR_ELx_EC_SVE] = "SVE", [ESR_ELx_EC_ERET] = "ERET/ERETAA/ERETAB", [ESR_ELx_EC_FPAC] = "FPAC", + [ESR_ELx_EC_SME] = "SME", [ESR_ELx_EC_IMP_DEF] = "EL3 IMP DEF", [ESR_ELx_EC_IABT_LOW] = "IABT (lower EL)", [ESR_ELx_EC_IABT_CUR] = "IABT (current EL)", @@ -842,7 +843,7 @@ static const char *esr_class_str[] = { [ESR_ELx_EC_BRK64] = "BRK (AArch64)", }; -const char *esr_get_class_string(u32 esr) +const char *esr_get_class_string(unsigned long esr) { return esr_class_str[ESR_ELx_EC(esr)]; } @@ -851,7 +852,7 @@ const char *esr_get_class_string(u32 esr) * bad_el0_sync handles unexpected, but potentially recoverable synchronous * exceptions taken from EL0. */ -void bad_el0_sync(struct pt_regs *regs, int reason, unsigned int esr) +void bad_el0_sync(struct pt_regs *regs, int reason, unsigned long esr) { unsigned long pc = instruction_pointer(regs); @@ -867,7 +868,7 @@ void bad_el0_sync(struct pt_regs *regs, int reason, unsigned int esr) DEFINE_PER_CPU(unsigned long [OVERFLOW_STACK_SIZE/sizeof(long)], overflow_stack) __aligned(16); -void panic_bad_stack(struct pt_regs *regs, unsigned int esr, unsigned long far) +void panic_bad_stack(struct pt_regs *regs, unsigned long esr, unsigned long far) { unsigned long tsk_stk = (unsigned long)current->stack; unsigned long irq_stk = (unsigned long)this_cpu_read(irq_stack_ptr); @@ -876,7 +877,7 @@ void panic_bad_stack(struct pt_regs *regs, unsigned int esr, unsigned long far) console_verbose(); pr_emerg("Insufficient stack space to handle exception!"); - pr_emerg("ESR: 0x%08x -- %s\n", esr, esr_get_class_string(esr)); + pr_emerg("ESR: 0x%016lx -- %s\n", esr, esr_get_class_string(esr)); pr_emerg("FAR: 0x%016lx\n", far); pr_emerg("Task stack: [0x%016lx..0x%016lx]\n", @@ -897,11 +898,11 @@ void panic_bad_stack(struct pt_regs *regs, unsigned int esr, unsigned long far) } #endif -void __noreturn arm64_serror_panic(struct pt_regs *regs, u32 esr) +void __noreturn arm64_serror_panic(struct pt_regs *regs, unsigned long esr) { console_verbose(); - pr_crit("SError Interrupt on CPU%d, code 0x%08x -- %s\n", + pr_crit("SError Interrupt on CPU%d, code 0x%016lx -- %s\n", smp_processor_id(), esr, esr_get_class_string(esr)); if (regs) __show_regs(regs); @@ -912,9 +913,9 @@ void __noreturn arm64_serror_panic(struct pt_regs *regs, u32 esr) unreachable(); } -bool arm64_is_fatal_ras_serror(struct pt_regs *regs, unsigned int esr) +bool arm64_is_fatal_ras_serror(struct pt_regs *regs, unsigned long esr) { - u32 aet = arm64_ras_serror_get_severity(esr); + unsigned long aet = arm64_ras_serror_get_severity(esr); switch (aet) { case ESR_ELx_AET_CE: /* corrected error */ @@ -944,7 +945,7 @@ bool arm64_is_fatal_ras_serror(struct pt_regs *regs, unsigned int esr) } } -void do_serror(struct pt_regs *regs, unsigned int esr) +void do_serror(struct pt_regs *regs, unsigned long esr) { /* non-RAS errors are not containable */ if (!arm64_is_ras_serror(esr) || arm64_is_fatal_ras_serror(regs, esr)) @@ -965,7 +966,7 @@ int is_valid_bugaddr(unsigned long addr) return 1; } -static int bug_handler(struct pt_regs *regs, unsigned int esr) +static int bug_handler(struct pt_regs *regs, unsigned long esr) { switch (report_bug(regs->pc, regs)) { case BUG_TRAP_TYPE_BUG: @@ -990,7 +991,7 @@ static struct break_hook bug_break_hook = { .imm = BUG_BRK_IMM, }; -static int reserved_fault_handler(struct pt_regs *regs, unsigned int esr) +static int reserved_fault_handler(struct pt_regs *regs, unsigned long esr) { pr_err("%s generated an invalid instruction at %pS!\n", "Kernel text patching", @@ -1012,7 +1013,7 @@ static struct break_hook fault_break_hook = { #define KASAN_ESR_SIZE_MASK 0x0f #define KASAN_ESR_SIZE(esr) (1 << ((esr) & KASAN_ESR_SIZE_MASK)) -static int kasan_handler(struct pt_regs *regs, unsigned int esr) +static int kasan_handler(struct pt_regs *regs, unsigned long esr) { bool recover = esr & KASAN_ESR_RECOVER; bool write = esr & KASAN_ESR_WRITE; @@ -1055,11 +1056,11 @@ static struct break_hook kasan_break_hook = { * Initial handler for AArch64 BRK exceptions * This handler only used until debug_traps_init(). */ -int __init early_brk64(unsigned long addr, unsigned int esr, +int __init early_brk64(unsigned long addr, unsigned long esr, struct pt_regs *regs) { #ifdef CONFIG_KASAN_SW_TAGS - unsigned int comment = esr & ESR_ELx_BRK64_ISS_COMMENT_MASK; + unsigned long comment = esr & ESR_ELx_BRK64_ISS_COMMENT_MASK; if ((comment & ~KASAN_BRK_MASK) == KASAN_BRK_IMM) return kasan_handler(regs, esr) != DBG_HOOK_HANDLED; diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile index 172452f79e46..f6e25d7c346a 100644 --- a/arch/arm64/kernel/vdso/Makefile +++ b/arch/arm64/kernel/vdso/Makefile @@ -32,7 +32,8 @@ ccflags-y += -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO # -Wmissing-prototypes and -Wmissing-declarations are removed from # the CFLAGS of vgettimeofday.c to make possible to build the # kernel with CONFIG_WERROR enabled. -CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) -Os $(CC_FLAGS_SCS) $(GCC_PLUGINS_CFLAGS) \ +CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) -Os $(CC_FLAGS_SCS) \ + $(RANDSTRUCT_CFLAGS) $(GCC_PLUGINS_CFLAGS) \ $(CC_FLAGS_LTO) -Wmissing-prototypes -Wmissing-declarations KASAN_SANITIZE := n KCSAN_SANITIZE := n @@ -52,9 +53,6 @@ GCOV_PROFILE := n targets += vdso.lds CPPFLAGS_vdso.lds += -P -C -U$(ARCH) -# Force dependency (incbin is bad) -$(obj)/vdso.o : $(obj)/vdso.so - # Link rule for the .so file, .lds has to be first $(obj)/vdso.so.dbg: $(obj)/vdso.lds $(obj-vdso) FORCE $(call if_changed,vdsold_and_vdso_check) diff --git a/arch/arm64/kernel/vdso32/Makefile b/arch/arm64/kernel/vdso32/Makefile index ed181bedbffc..05ba1aae1b6f 100644 --- a/arch/arm64/kernel/vdso32/Makefile +++ b/arch/arm64/kernel/vdso32/Makefile @@ -131,9 +131,6 @@ obj-vdso := $(c-obj-vdso) $(c-obj-vdso-gettimeofday) $(asm-obj-vdso) targets += vdso.lds CPPFLAGS_vdso.lds += -P -C -U$(ARCH) -# Force dependency (vdso.s includes vdso.so through incbin) -$(obj)/vdso.o: $(obj)/vdso.so - include/generated/vdso32-offsets.h: $(obj)/vdso.so.dbg FORCE $(call if_changed,vdsosym) diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S index edaf0faf766f..2d4a8f995175 100644 --- a/arch/arm64/kernel/vmlinux.lds.S +++ b/arch/arm64/kernel/vmlinux.lds.S @@ -93,7 +93,6 @@ jiffies = jiffies_64; #ifdef CONFIG_HIBERNATION #define HIBERNATE_TEXT \ - . = ALIGN(SZ_4K); \ __hibernate_exit_text_start = .; \ *(.hibernate_exit.text) \ __hibernate_exit_text_end = .; @@ -103,7 +102,6 @@ jiffies = jiffies_64; #ifdef CONFIG_KEXEC_CORE #define KEXEC_TEXT \ - . = ALIGN(SZ_4K); \ __relocate_new_kernel_start = .; \ *(.kexec_relocate.text) \ __relocate_new_kernel_end = .; @@ -170,9 +168,6 @@ SECTIONS KPROBES_TEXT HYPERVISOR_TEXT IDMAP_TEXT - HIBERNATE_TEXT - KEXEC_TEXT - TRAMP_TEXT *(.gnu.warning) . = ALIGN(16); *(.got) /* Global offset table */ @@ -194,6 +189,14 @@ SECTIONS HYPERVISOR_DATA_SECTIONS + /* code sections that are never executed via the kernel mapping */ + .rodata.text : { + TRAMP_TEXT + HIBERNATE_TEXT + KEXEC_TEXT + . = ALIGN(PAGE_SIZE); + } + idmap_pg_dir = .; . += IDMAP_DIR_SIZE; idmap_pg_end = .; @@ -337,8 +340,8 @@ ASSERT(__hyp_idmap_text_end - __hyp_idmap_text_start <= PAGE_SIZE, ASSERT(__idmap_text_end - (__idmap_text_start & ~(SZ_4K - 1)) <= SZ_4K, "ID map text too big or misaligned") #ifdef CONFIG_HIBERNATION -ASSERT(__hibernate_exit_text_end - (__hibernate_exit_text_start & ~(SZ_4K - 1)) - <= SZ_4K, "Hibernate exit text too big or misaligned") +ASSERT(__hibernate_exit_text_end - __hibernate_exit_text_start <= SZ_4K, + "Hibernate exit text is bigger than 4 KiB") #endif #ifdef CONFIG_UNMAP_KERNEL_AT_EL0 ASSERT((__entry_tramp_text_end - __entry_tramp_text_start) <= 3*PAGE_SIZE, @@ -362,7 +365,7 @@ ASSERT(swapper_pg_dir - tramp_pg_dir == TRAMP_SWAPPER_OFFSET, #ifdef CONFIG_KEXEC_CORE /* kexec relocation code should fit into one KEXEC_CONTROL_PAGE_SIZE */ -ASSERT(__relocate_new_kernel_end - (__relocate_new_kernel_start & ~(SZ_4K - 1)) - <= SZ_4K, "kexec relocation code is too big or misaligned") +ASSERT(__relocate_new_kernel_end - __relocate_new_kernel_start <= SZ_4K, + "kexec relocation code is bigger than 4 KiB") ASSERT(KEXEC_CONTROL_PAGE_SIZE >= SZ_4K, "KEXEC_CONTROL_PAGE_SIZE is broken") #endif diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 523bc934fe2f..cedc3ba2c098 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -783,6 +783,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) ret = 1; run->exit_reason = KVM_EXIT_UNKNOWN; + run->flags = 0; while (ret > 0) { /* * Check conditions before entering the guest @@ -1436,7 +1437,8 @@ static int kvm_init_vector_slots(void) base = kern_hyp_va(kvm_ksym_ref(__bp_harden_hyp_vecs)); kvm_init_vector_slot(base, HYP_VECTOR_SPECTRE_DIRECT); - if (kvm_system_needs_idmapped_vectors() && !has_vhe()) { + if (kvm_system_needs_idmapped_vectors() && + !is_protected_kvm_enabled()) { err = create_hyp_exec_mappings(__pa_symbol(__bp_harden_hyp_vecs), __BP_HARDEN_HYP_VECS_SZ, &base); if (err) diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c index 397fdac75cb1..3d251a4d2cf7 100644 --- a/arch/arm64/kvm/fpsimd.c +++ b/arch/arm64/kvm/fpsimd.c @@ -82,6 +82,26 @@ void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu) if (read_sysreg(cpacr_el1) & CPACR_EL1_ZEN_EL0EN) vcpu->arch.flags |= KVM_ARM64_HOST_SVE_ENABLED; + + /* + * We don't currently support SME guests but if we leave + * things in streaming mode then when the guest starts running + * FPSIMD or SVE code it may generate SME traps so as a + * special case if we are in streaming mode we force the host + * state to be saved now and exit streaming mode so that we + * don't have to handle any SME traps for valid guest + * operations. Do this for ZA as well for now for simplicity. + */ + if (system_supports_sme()) { + if (read_sysreg(cpacr_el1) & CPACR_EL1_SMEN_EL0EN) + vcpu->arch.flags |= KVM_ARM64_HOST_SME_ENABLED; + + if (read_sysreg_s(SYS_SVCR) & + (SVCR_SM_MASK | SVCR_ZA_MASK)) { + vcpu->arch.flags &= ~KVM_ARM64_FP_HOST; + fpsimd_save_and_flush_cpu_state(); + } + } } /* @@ -109,9 +129,14 @@ void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu) WARN_ON_ONCE(!irqs_disabled()); if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED) { + /* + * Currently we do not support SME guests so SVCR is + * always 0 and we just need a variable to point to. + */ fpsimd_bind_state_to_cpu(&vcpu->arch.ctxt.fp_regs, vcpu->arch.sve_state, - vcpu->arch.sve_max_vl); + vcpu->arch.sve_max_vl, + NULL, 0, &vcpu->arch.svcr); clear_thread_flag(TIF_FOREIGN_FPSTATE); update_thread_flag(TIF_SVE, vcpu_has_sve(vcpu)); @@ -130,6 +155,22 @@ void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu) local_irq_save(flags); + /* + * If we have VHE then the Hyp code will reset CPACR_EL1 to + * CPACR_EL1_DEFAULT and we need to reenable SME. + */ + if (has_vhe() && system_supports_sme()) { + /* Also restore EL0 state seen on entry */ + if (vcpu->arch.flags & KVM_ARM64_HOST_SME_ENABLED) + sysreg_clear_set(CPACR_EL1, 0, + CPACR_EL1_SMEN_EL0EN | + CPACR_EL1_SMEN_EL1EN); + else + sysreg_clear_set(CPACR_EL1, + CPACR_EL1_SMEN_EL0EN, + CPACR_EL1_SMEN_EL1EN); + } + if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED) { if (vcpu_has_sve(vcpu)) { __vcpu_sys_reg(vcpu, ZCR_EL1) = read_sysreg_el1(SYS_ZCR); diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c index 97fe14aab1a3..0b829292dc54 100644 --- a/arch/arm64/kvm/handle_exit.c +++ b/arch/arm64/kvm/handle_exit.c @@ -26,7 +26,7 @@ typedef int (*exit_handle_fn)(struct kvm_vcpu *); -static void kvm_handle_guest_serror(struct kvm_vcpu *vcpu, u32 esr) +static void kvm_handle_guest_serror(struct kvm_vcpu *vcpu, u64 esr) { if (!arm64_is_ras_serror(esr) || arm64_is_fatal_ras_serror(NULL, esr)) kvm_inject_vabt(vcpu); @@ -117,10 +117,12 @@ static int kvm_handle_wfx(struct kvm_vcpu *vcpu) static int kvm_handle_guest_debug(struct kvm_vcpu *vcpu) { struct kvm_run *run = vcpu->run; - u32 esr = kvm_vcpu_get_esr(vcpu); + u64 esr = kvm_vcpu_get_esr(vcpu); run->exit_reason = KVM_EXIT_DEBUG; - run->debug.arch.hsr = esr; + run->debug.arch.hsr = lower_32_bits(esr); + run->debug.arch.hsr_high = upper_32_bits(esr); + run->flags = KVM_DEBUG_ARCH_HSR_HIGH_VALID; if (ESR_ELx_EC(esr) == ESR_ELx_EC_WATCHPT_LOW) run->debug.arch.far = vcpu->arch.fault.far_el2; @@ -130,9 +132,9 @@ static int kvm_handle_guest_debug(struct kvm_vcpu *vcpu) static int kvm_handle_unknown_ec(struct kvm_vcpu *vcpu) { - u32 esr = kvm_vcpu_get_esr(vcpu); + u64 esr = kvm_vcpu_get_esr(vcpu); - kvm_pr_unimpl("Unknown exception class: esr: %#08x -- %s\n", + kvm_pr_unimpl("Unknown exception class: esr: %#016llx -- %s\n", esr, esr_get_class_string(esr)); kvm_inject_undefined(vcpu); @@ -187,7 +189,7 @@ static exit_handle_fn arm_exit_handlers[] = { static exit_handle_fn kvm_get_exit_handler(struct kvm_vcpu *vcpu) { - u32 esr = kvm_vcpu_get_esr(vcpu); + u64 esr = kvm_vcpu_get_esr(vcpu); u8 esr_ec = ESR_ELx_EC(esr); return arm_exit_handlers[esr_ec]; @@ -334,6 +336,6 @@ void __noreturn __cold nvhe_hyp_panic_handler(u64 esr, u64 spsr, */ kvm_err("Hyp Offset: 0x%llx\n", hyp_offset); - panic("HYP panic:\nPS:%08llx PC:%016llx ESR:%08llx\nFAR:%016llx HPFAR:%016llx PAR:%016llx\nVCPU:%016lx\n", + panic("HYP panic:\nPS:%08llx PC:%016llx ESR:%016llx\nFAR:%016llx HPFAR:%016llx PAR:%016llx\nVCPU:%016lx\n", spsr, elr_virt, esr, far, hpfar, par, vcpu); } diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index 5d31f6c64c8c..37d9f211c200 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -266,7 +266,7 @@ static inline bool handle_tx2_tvm(struct kvm_vcpu *vcpu) return true; } -static inline bool esr_is_ptrauth_trap(u32 esr) +static inline bool esr_is_ptrauth_trap(u64 esr) { switch (esr_sys64_to_sysreg(esr)) { case SYS_APIAKEYLO_EL1: diff --git a/arch/arm64/kvm/hyp/include/nvhe/fixed_config.h b/arch/arm64/kvm/hyp/include/nvhe/fixed_config.h index 5ad626527d41..fd55014b3497 100644 --- a/arch/arm64/kvm/hyp/include/nvhe/fixed_config.h +++ b/arch/arm64/kvm/hyp/include/nvhe/fixed_config.h @@ -159,20 +159,20 @@ * No restrictions on instructions implemented in AArch64. */ #define PVM_ID_AA64ISAR0_ALLOW (\ - ARM64_FEATURE_MASK(ID_AA64ISAR0_AES) | \ - ARM64_FEATURE_MASK(ID_AA64ISAR0_SHA1) | \ - ARM64_FEATURE_MASK(ID_AA64ISAR0_SHA2) | \ - ARM64_FEATURE_MASK(ID_AA64ISAR0_CRC32) | \ - ARM64_FEATURE_MASK(ID_AA64ISAR0_ATOMICS) | \ - ARM64_FEATURE_MASK(ID_AA64ISAR0_RDM) | \ - ARM64_FEATURE_MASK(ID_AA64ISAR0_SHA3) | \ - ARM64_FEATURE_MASK(ID_AA64ISAR0_SM3) | \ - ARM64_FEATURE_MASK(ID_AA64ISAR0_SM4) | \ - ARM64_FEATURE_MASK(ID_AA64ISAR0_DP) | \ - ARM64_FEATURE_MASK(ID_AA64ISAR0_FHM) | \ - ARM64_FEATURE_MASK(ID_AA64ISAR0_TS) | \ - ARM64_FEATURE_MASK(ID_AA64ISAR0_TLB) | \ - ARM64_FEATURE_MASK(ID_AA64ISAR0_RNDR) \ + ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_AES) | \ + ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_SHA1) | \ + ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_SHA2) | \ + ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_CRC32) | \ + ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_ATOMIC) | \ + ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_RDM) | \ + ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_SHA3) | \ + ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_SM3) | \ + ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_SM4) | \ + ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_DP) | \ + ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_FHM) | \ + ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_TS) | \ + ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_TLB) | \ + ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_RNDR) \ ) #define PVM_ID_AA64ISAR1_ALLOW (\ diff --git a/arch/arm64/kvm/hyp/nvhe/host.S b/arch/arm64/kvm/hyp/nvhe/host.S index 3d613e721a75..727c979b2b69 100644 --- a/arch/arm64/kvm/hyp/nvhe/host.S +++ b/arch/arm64/kvm/hyp/nvhe/host.S @@ -198,15 +198,15 @@ SYM_CODE_START(__kvm_hyp_host_vector) invalid_host_el2_vect // FIQ EL2h invalid_host_el2_vect // Error EL2h - host_el1_sync_vect // Synchronous 64-bit EL1 - invalid_host_el1_vect // IRQ 64-bit EL1 - invalid_host_el1_vect // FIQ 64-bit EL1 - invalid_host_el1_vect // Error 64-bit EL1 - - invalid_host_el1_vect // Synchronous 32-bit EL1 - invalid_host_el1_vect // IRQ 32-bit EL1 - invalid_host_el1_vect // FIQ 32-bit EL1 - invalid_host_el1_vect // Error 32-bit EL1 + host_el1_sync_vect // Synchronous 64-bit EL1/EL0 + invalid_host_el1_vect // IRQ 64-bit EL1/EL0 + invalid_host_el1_vect // FIQ 64-bit EL1/EL0 + invalid_host_el1_vect // Error 64-bit EL1/EL0 + + host_el1_sync_vect // Synchronous 32-bit EL1/EL0 + invalid_host_el1_vect // IRQ 32-bit EL1/EL0 + invalid_host_el1_vect // FIQ 32-bit EL1/EL0 + invalid_host_el1_vect // Error 32-bit EL1/EL0 SYM_CODE_END(__kvm_hyp_host_vector) /* diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c index 6410d21d8695..caace61ea459 100644 --- a/arch/arm64/kvm/hyp/nvhe/switch.c +++ b/arch/arm64/kvm/hyp/nvhe/switch.c @@ -47,10 +47,24 @@ static void __activate_traps(struct kvm_vcpu *vcpu) val |= CPTR_EL2_TFP | CPTR_EL2_TZ; __activate_traps_fpsimd32(vcpu); } + if (cpus_have_final_cap(ARM64_SME)) + val |= CPTR_EL2_TSM; write_sysreg(val, cptr_el2); write_sysreg(__this_cpu_read(kvm_hyp_vector), vbar_el2); + if (cpus_have_final_cap(ARM64_SME)) { + val = read_sysreg_s(SYS_HFGRTR_EL2); + val &= ~(HFGxTR_EL2_nTPIDR2_EL0_MASK | + HFGxTR_EL2_nSMPRI_EL1_MASK); + write_sysreg_s(val, SYS_HFGRTR_EL2); + + val = read_sysreg_s(SYS_HFGWTR_EL2); + val &= ~(HFGxTR_EL2_nTPIDR2_EL0_MASK | + HFGxTR_EL2_nSMPRI_EL1_MASK); + write_sysreg_s(val, SYS_HFGWTR_EL2); + } + if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) { struct kvm_cpu_context *ctxt = &vcpu->arch.ctxt; @@ -94,9 +108,25 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu) write_sysreg(this_cpu_ptr(&kvm_init_params)->hcr_el2, hcr_el2); + if (cpus_have_final_cap(ARM64_SME)) { + u64 val; + + val = read_sysreg_s(SYS_HFGRTR_EL2); + val |= HFGxTR_EL2_nTPIDR2_EL0_MASK | + HFGxTR_EL2_nSMPRI_EL1_MASK; + write_sysreg_s(val, SYS_HFGRTR_EL2); + + val = read_sysreg_s(SYS_HFGWTR_EL2); + val |= HFGxTR_EL2_nTPIDR2_EL0_MASK | + HFGxTR_EL2_nSMPRI_EL1_MASK; + write_sysreg_s(val, SYS_HFGWTR_EL2); + } + cptr = CPTR_EL2_DEFAULT; if (vcpu_has_sve(vcpu) && (vcpu->arch.flags & KVM_ARM64_FP_ENABLED)) cptr |= CPTR_EL2_TZ; + if (cpus_have_final_cap(ARM64_SME)) + cptr &= ~CPTR_EL2_TSM; write_sysreg(cptr, cptr_el2); write_sysreg(__kvm_hyp_host_vector, vbar_el2); diff --git a/arch/arm64/kvm/hyp/nvhe/sys_regs.c b/arch/arm64/kvm/hyp/nvhe/sys_regs.c index 33f5181af330..619f94fc95fa 100644 --- a/arch/arm64/kvm/hyp/nvhe/sys_regs.c +++ b/arch/arm64/kvm/hyp/nvhe/sys_regs.c @@ -33,7 +33,7 @@ u64 id_aa64mmfr2_el1_sys_val; */ static void inject_undef64(struct kvm_vcpu *vcpu) { - u32 esr = (ESR_ELx_EC_UNKNOWN << ESR_ELx_EC_SHIFT); + u64 esr = (ESR_ELx_EC_UNKNOWN << ESR_ELx_EC_SHIFT); *vcpu_pc(vcpu) = read_sysreg_el2(SYS_ELR); *vcpu_cpsr(vcpu) = read_sysreg_el2(SYS_SPSR); diff --git a/arch/arm64/kvm/hyp/vgic-v3-sr.c b/arch/arm64/kvm/hyp/vgic-v3-sr.c index 4fb419f7b8b6..6cb638b184b1 100644 --- a/arch/arm64/kvm/hyp/vgic-v3-sr.c +++ b/arch/arm64/kvm/hyp/vgic-v3-sr.c @@ -473,7 +473,7 @@ static int __vgic_v3_bpr_min(void) static int __vgic_v3_get_group(struct kvm_vcpu *vcpu) { - u32 esr = kvm_vcpu_get_esr(vcpu); + u64 esr = kvm_vcpu_get_esr(vcpu); u8 crm = (esr & ESR_ELx_SYS64_ISS_CRM_MASK) >> ESR_ELx_SYS64_ISS_CRM_SHIFT; return crm != 8; @@ -1016,7 +1016,7 @@ static void __vgic_v3_write_ctlr(struct kvm_vcpu *vcpu, u32 vmcr, int rt) int __vgic_v3_perform_cpuif_access(struct kvm_vcpu *vcpu) { int rt; - u32 esr; + u64 esr; u32 vmcr; void (*fn)(struct kvm_vcpu *, u32, int); bool is_read; diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c index 262dfe03134d..969f20daf97a 100644 --- a/arch/arm64/kvm/hyp/vhe/switch.c +++ b/arch/arm64/kvm/hyp/vhe/switch.c @@ -41,7 +41,8 @@ static void __activate_traps(struct kvm_vcpu *vcpu) val = read_sysreg(cpacr_el1); val |= CPACR_EL1_TTA; - val &= ~(CPACR_EL1_ZEN_EL0EN | CPACR_EL1_ZEN_EL1EN); + val &= ~(CPACR_EL1_ZEN_EL0EN | CPACR_EL1_ZEN_EL1EN | + CPACR_EL1_SMEN_EL0EN | CPACR_EL1_SMEN_EL1EN); /* * With VHE (HCR.E2H == 1), accesses to CPACR_EL1 are routed to @@ -62,6 +63,10 @@ static void __activate_traps(struct kvm_vcpu *vcpu) __activate_traps_fpsimd32(vcpu); } + if (cpus_have_final_cap(ARM64_SME)) + write_sysreg(read_sysreg(sctlr_el2) & ~SCTLR_ELx_ENTP2, + sctlr_el2); + write_sysreg(val, cpacr_el1); write_sysreg(__this_cpu_read(kvm_hyp_vector), vbar_el1); @@ -83,6 +88,10 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu) */ asm(ALTERNATIVE("nop", "isb", ARM64_WORKAROUND_SPECULATIVE_AT)); + if (cpus_have_final_cap(ARM64_SME)) + write_sysreg(read_sysreg(sctlr_el2) | SCTLR_ELx_ENTP2, + sctlr_el2); + write_sysreg(CPACR_EL1_DEFAULT, cpacr_el1); if (!arm64_kernel_unmapped_at_el0()) diff --git a/arch/arm64/kvm/inject_fault.c b/arch/arm64/kvm/inject_fault.c index b47df73e98d7..55a5dbe957e0 100644 --- a/arch/arm64/kvm/inject_fault.c +++ b/arch/arm64/kvm/inject_fault.c @@ -18,7 +18,7 @@ static void inject_abt64(struct kvm_vcpu *vcpu, bool is_iabt, unsigned long addr { unsigned long cpsr = *vcpu_cpsr(vcpu); bool is_aarch32 = vcpu_mode_is_32bit(vcpu); - u32 esr = 0; + u64 esr = 0; vcpu->arch.flags |= (KVM_ARM64_EXCEPT_AA64_EL1 | KVM_ARM64_EXCEPT_AA64_ELx_SYNC | @@ -50,7 +50,7 @@ static void inject_abt64(struct kvm_vcpu *vcpu, bool is_iabt, unsigned long addr static void inject_undef64(struct kvm_vcpu *vcpu) { - u32 esr = (ESR_ELx_EC_UNKNOWN << ESR_ELx_EC_SHIFT); + u64 esr = (ESR_ELx_EC_UNKNOWN << ESR_ELx_EC_SHIFT); vcpu->arch.flags |= (KVM_ARM64_EXCEPT_AA64_EL1 | KVM_ARM64_EXCEPT_AA64_ELx_SYNC | @@ -145,6 +145,34 @@ void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr) inject_abt64(vcpu, true, addr); } +void kvm_inject_size_fault(struct kvm_vcpu *vcpu) +{ + unsigned long addr, esr; + + addr = kvm_vcpu_get_fault_ipa(vcpu); + addr |= kvm_vcpu_get_hfar(vcpu) & GENMASK(11, 0); + + if (kvm_vcpu_trap_is_iabt(vcpu)) + kvm_inject_pabt(vcpu, addr); + else + kvm_inject_dabt(vcpu, addr); + + /* + * If AArch64 or LPAE, set FSC to 0 to indicate an Address + * Size Fault at level 0, as if exceeding PARange. + * + * Non-LPAE guests will only get the external abort, as there + * is no way to to describe the ASF. + */ + if (vcpu_el1_is_32bit(vcpu) && + !(vcpu_read_sys_reg(vcpu, TCR_EL1) & TTBCR_EAE)) + return; + + esr = vcpu_read_sys_reg(vcpu, ESR_EL1); + esr &= ~GENMASK_ULL(5, 0); + vcpu_write_sys_reg(vcpu, esr, ESR_EL1); +} + /** * kvm_inject_undefined - inject an undefined instruction into the guest * @vcpu: The vCPU in which to inject the exception diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index 0d19259454d8..5400fc020164 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -1079,7 +1079,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, gfn_t gfn; kvm_pfn_t pfn; bool logging_active = memslot_is_logging(memslot); - bool logging_perm_fault = false; + bool use_read_lock = false; unsigned long fault_level = kvm_vcpu_trap_get_fault_level(vcpu); unsigned long vma_pagesize, fault_granule; enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_R; @@ -1114,7 +1114,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, if (logging_active) { force_pte = true; vma_shift = PAGE_SHIFT; - logging_perm_fault = (fault_status == FSC_PERM && write_fault); + use_read_lock = (fault_status == FSC_PERM && write_fault && + fault_granule == PAGE_SIZE); } else { vma_shift = get_vma_page_shift(vma, hva); } @@ -1218,7 +1219,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, * logging dirty logging, only acquire read lock for permission * relaxation. */ - if (logging_perm_fault) + if (use_read_lock) read_lock(&kvm->mmu_lock); else write_lock(&kvm->mmu_lock); @@ -1268,6 +1269,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, if (fault_status == FSC_PERM && vma_pagesize == fault_granule) { ret = kvm_pgtable_stage2_relax_perms(pgt, fault_ipa, prot); } else { + WARN_ONCE(use_read_lock, "Attempted stage-2 map outside of write lock\n"); + ret = kvm_pgtable_stage2_map(pgt, fault_ipa, vma_pagesize, __pfn_to_phys(pfn), prot, memcache); @@ -1280,7 +1283,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, } out_unlock: - if (logging_perm_fault) + if (use_read_lock) read_unlock(&kvm->mmu_lock); else write_unlock(&kvm->mmu_lock); @@ -1334,6 +1337,25 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu) fault_ipa = kvm_vcpu_get_fault_ipa(vcpu); is_iabt = kvm_vcpu_trap_is_iabt(vcpu); + if (fault_status == FSC_FAULT) { + /* Beyond sanitised PARange (which is the IPA limit) */ + if (fault_ipa >= BIT_ULL(get_kvm_ipa_limit())) { + kvm_inject_size_fault(vcpu); + return 1; + } + + /* Falls between the IPA range and the PARange? */ + if (fault_ipa >= BIT_ULL(vcpu->arch.hw_mmu->pgt->ia_bits)) { + fault_ipa |= kvm_vcpu_get_hfar(vcpu) & GENMASK(11, 0); + + if (is_iabt) + kvm_inject_pabt(vcpu, fault_ipa); + else + kvm_inject_dabt(vcpu, fault_ipa); + return 1; + } + } + /* Synchronous External Abort? */ if (kvm_vcpu_abt_issea(vcpu)) { /* diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c index 78fdc443adc7..3dc990ac4f44 100644 --- a/arch/arm64/kvm/pmu-emul.c +++ b/arch/arm64/kvm/pmu-emul.c @@ -177,6 +177,9 @@ u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu, u64 select_idx) struct kvm_pmu *pmu = &vcpu->arch.pmu; struct kvm_pmc *pmc = &pmu->pmc[select_idx]; + if (!kvm_vcpu_has_pmu(vcpu)) + return 0; + counter = kvm_pmu_get_pair_counter_value(vcpu, pmc); if (kvm_pmu_pmc_is_chained(pmc) && @@ -198,6 +201,9 @@ void kvm_pmu_set_counter_value(struct kvm_vcpu *vcpu, u64 select_idx, u64 val) { u64 reg; + if (!kvm_vcpu_has_pmu(vcpu)) + return; + reg = (select_idx == ARMV8_PMU_CYCLE_IDX) ? PMCCNTR_EL0 : PMEVCNTR0_EL0 + select_idx; __vcpu_sys_reg(vcpu, reg) += (s64)val - kvm_pmu_get_counter_value(vcpu, select_idx); @@ -322,6 +328,9 @@ void kvm_pmu_enable_counter_mask(struct kvm_vcpu *vcpu, u64 val) struct kvm_pmu *pmu = &vcpu->arch.pmu; struct kvm_pmc *pmc; + if (!kvm_vcpu_has_pmu(vcpu)) + return; + if (!(__vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMU_PMCR_E) || !val) return; @@ -357,7 +366,7 @@ void kvm_pmu_disable_counter_mask(struct kvm_vcpu *vcpu, u64 val) struct kvm_pmu *pmu = &vcpu->arch.pmu; struct kvm_pmc *pmc; - if (!val) + if (!kvm_vcpu_has_pmu(vcpu) || !val) return; for (i = 0; i < ARMV8_PMU_MAX_COUNTERS; i++) { @@ -527,6 +536,9 @@ void kvm_pmu_software_increment(struct kvm_vcpu *vcpu, u64 val) struct kvm_pmu *pmu = &vcpu->arch.pmu; int i; + if (!kvm_vcpu_has_pmu(vcpu)) + return; + if (!(__vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMU_PMCR_E)) return; @@ -576,6 +588,9 @@ void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val) { int i; + if (!kvm_vcpu_has_pmu(vcpu)) + return; + if (val & ARMV8_PMU_PMCR_E) { kvm_pmu_enable_counter_mask(vcpu, __vcpu_sys_reg(vcpu, PMCNTENSET_EL0)); @@ -739,6 +754,9 @@ void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u64 data, { u64 reg, mask; + if (!kvm_vcpu_has_pmu(vcpu)) + return; + mask = ARMV8_PMU_EVTYPE_MASK; mask &= ~ARMV8_PMU_EVTYPE_EVENT; mask |= kvm_pmu_event_mask(vcpu->kvm); @@ -827,6 +845,9 @@ u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1) u64 val, mask = 0; int base, i, nr_events; + if (!kvm_vcpu_has_pmu(vcpu)) + return 0; + if (!pmceid1) { val = read_sysreg(pmceid0_el0); base = 0; diff --git a/arch/arm64/kvm/psci.c b/arch/arm64/kvm/psci.c index 372da09a2fab..708d80e8e60d 100644 --- a/arch/arm64/kvm/psci.c +++ b/arch/arm64/kvm/psci.c @@ -181,7 +181,8 @@ static void kvm_prepare_system_event(struct kvm_vcpu *vcpu, u32 type, u64 flags) memset(&vcpu->run->system_event, 0, sizeof(vcpu->run->system_event)); vcpu->run->system_event.type = type; - vcpu->run->system_event.flags = flags; + vcpu->run->system_event.ndata = 1; + vcpu->run->system_event.data[0] = flags; vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT; } @@ -215,15 +216,11 @@ static void kvm_psci_narrow_to_32bit(struct kvm_vcpu *vcpu) static unsigned long kvm_psci_check_allowed_function(struct kvm_vcpu *vcpu, u32 fn) { - switch(fn) { - case PSCI_0_2_FN64_CPU_SUSPEND: - case PSCI_0_2_FN64_CPU_ON: - case PSCI_0_2_FN64_AFFINITY_INFO: - /* Disallow these functions for 32bit guests */ - if (vcpu_mode_is_32bit(vcpu)) - return PSCI_RET_NOT_SUPPORTED; - break; - } + /* + * Prevent 32 bit guests from calling 64 bit PSCI functions. + */ + if ((fn & PSCI_0_2_64BIT) && vcpu_mode_is_32bit(vcpu)) + return PSCI_RET_NOT_SUPPORTED; return 0; } @@ -235,10 +232,6 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu) unsigned long val; int ret = 1; - val = kvm_psci_check_allowed_function(vcpu, psci_fn); - if (val) - goto out; - switch (psci_fn) { case PSCI_0_2_FN_PSCI_VERSION: /* @@ -306,7 +299,6 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu) break; } -out: smccc_set_retval(vcpu, val, 0, 0, 0); return ret; } @@ -318,9 +310,6 @@ static int kvm_psci_1_x_call(struct kvm_vcpu *vcpu, u32 minor) unsigned long val; int ret = 1; - if (minor > 1) - return -EINVAL; - switch(psci_fn) { case PSCI_0_2_FN_PSCI_VERSION: val = minor == 0 ? KVM_ARM_PSCI_1_0 : KVM_ARM_PSCI_1_1; @@ -426,6 +415,15 @@ static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu) */ int kvm_psci_call(struct kvm_vcpu *vcpu) { + u32 psci_fn = smccc_get_function(vcpu); + unsigned long val; + + val = kvm_psci_check_allowed_function(vcpu, psci_fn); + if (val) { + smccc_set_retval(vcpu, val, 0, 0, 0); + return 1; + } + switch (kvm_psci_version(vcpu)) { case KVM_ARM_PSCI_1_1: return kvm_psci_1_x_call(vcpu, 1); diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c index ecc40c8cd6f6..6c70c6f61c70 100644 --- a/arch/arm64/kvm/reset.c +++ b/arch/arm64/kvm/reset.c @@ -181,27 +181,51 @@ static int kvm_vcpu_enable_ptrauth(struct kvm_vcpu *vcpu) return 0; } -static bool vcpu_allowed_register_width(struct kvm_vcpu *vcpu) +/** + * kvm_set_vm_width() - set the register width for the guest + * @vcpu: Pointer to the vcpu being configured + * + * Set both KVM_ARCH_FLAG_EL1_32BIT and KVM_ARCH_FLAG_REG_WIDTH_CONFIGURED + * in the VM flags based on the vcpu's requested register width, the HW + * capabilities and other options (such as MTE). + * When REG_WIDTH_CONFIGURED is already set, the vcpu settings must be + * consistent with the value of the FLAG_EL1_32BIT bit in the flags. + * + * Return: 0 on success, negative error code on failure. + */ +static int kvm_set_vm_width(struct kvm_vcpu *vcpu) { - struct kvm_vcpu *tmp; + struct kvm *kvm = vcpu->kvm; bool is32bit; - unsigned long i; is32bit = vcpu_has_feature(vcpu, KVM_ARM_VCPU_EL1_32BIT); + + lockdep_assert_held(&kvm->lock); + + if (test_bit(KVM_ARCH_FLAG_REG_WIDTH_CONFIGURED, &kvm->arch.flags)) { + /* + * The guest's register width is already configured. + * Make sure that the vcpu is consistent with it. + */ + if (is32bit == test_bit(KVM_ARCH_FLAG_EL1_32BIT, &kvm->arch.flags)) + return 0; + + return -EINVAL; + } + if (!cpus_have_const_cap(ARM64_HAS_32BIT_EL1) && is32bit) - return false; + return -EINVAL; /* MTE is incompatible with AArch32 */ - if (kvm_has_mte(vcpu->kvm) && is32bit) - return false; + if (kvm_has_mte(kvm) && is32bit) + return -EINVAL; - /* Check that the vcpus are either all 32bit or all 64bit */ - kvm_for_each_vcpu(i, tmp, vcpu->kvm) { - if (vcpu_has_feature(tmp, KVM_ARM_VCPU_EL1_32BIT) != is32bit) - return false; - } + if (is32bit) + set_bit(KVM_ARCH_FLAG_EL1_32BIT, &kvm->arch.flags); - return true; + set_bit(KVM_ARCH_FLAG_REG_WIDTH_CONFIGURED, &kvm->arch.flags); + + return 0; } /** @@ -230,10 +254,16 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu) u32 pstate; mutex_lock(&vcpu->kvm->lock); - reset_state = vcpu->arch.reset_state; - WRITE_ONCE(vcpu->arch.reset_state.reset, false); + ret = kvm_set_vm_width(vcpu); + if (!ret) { + reset_state = vcpu->arch.reset_state; + WRITE_ONCE(vcpu->arch.reset_state.reset, false); + } mutex_unlock(&vcpu->kvm->lock); + if (ret) + return ret; + /* Reset PMU outside of the non-preemptible section */ kvm_pmu_vcpu_reset(vcpu); @@ -260,14 +290,9 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu) } } - if (!vcpu_allowed_register_width(vcpu)) { - ret = -EINVAL; - goto out; - } - switch (vcpu->arch.target) { default: - if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features)) { + if (vcpu_el1_is_32bit(vcpu)) { pstate = VCPU_RESET_PSTATE_SVC; } else { pstate = VCPU_RESET_PSTATE_EL1; diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 7b45c040cc27..18b403b58b53 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -1123,8 +1123,7 @@ static u64 read_id_reg(const struct kvm_vcpu *vcpu, val |= FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR0_CSV2), (u64)vcpu->kvm->arch.pfr0_csv2); val &= ~ARM64_FEATURE_MASK(ID_AA64PFR0_CSV3); val |= FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR0_CSV3), (u64)vcpu->kvm->arch.pfr0_csv3); - if (irqchip_in_kernel(vcpu->kvm) && - vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) { + if (kvm_vgic_global_state.type == VGIC_V3) { val &= ~ARM64_FEATURE_MASK(ID_AA64PFR0_GIC); val |= FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR0_GIC), 1); } @@ -1132,6 +1131,8 @@ static u64 read_id_reg(const struct kvm_vcpu *vcpu, case SYS_ID_AA64PFR1_EL1: if (!kvm_has_mte(vcpu->kvm)) val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_MTE); + + val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_SME); break; case SYS_ID_AA64ISAR1_EL1: if (!vcpu_has_ptrauth(vcpu)) @@ -1553,7 +1554,7 @@ static const struct sys_reg_desc sys_reg_descs[] = { ID_UNALLOCATED(4,2), ID_UNALLOCATED(4,3), ID_SANITISED(ID_AA64ZFR0_EL1), - ID_UNALLOCATED(4,5), + ID_HIDDEN(ID_AA64SMFR0_EL1), ID_UNALLOCATED(4,6), ID_UNALLOCATED(4,7), @@ -1596,6 +1597,8 @@ static const struct sys_reg_desc sys_reg_descs[] = { { SYS_DESC(SYS_ZCR_EL1), NULL, reset_val, ZCR_EL1, 0, .visibility = sve_visibility }, { SYS_DESC(SYS_TRFCR_EL1), undef_access }, + { SYS_DESC(SYS_SMPRI_EL1), undef_access }, + { SYS_DESC(SYS_SMCR_EL1), undef_access }, { SYS_DESC(SYS_TTBR0_EL1), access_vm_reg, reset_unknown, TTBR0_EL1 }, { SYS_DESC(SYS_TTBR1_EL1), access_vm_reg, reset_unknown, TTBR1_EL1 }, { SYS_DESC(SYS_TCR_EL1), access_vm_reg, reset_val, TCR_EL1, 0 }, @@ -1678,8 +1681,10 @@ static const struct sys_reg_desc sys_reg_descs[] = { { SYS_DESC(SYS_CCSIDR_EL1), access_ccsidr }, { SYS_DESC(SYS_CLIDR_EL1), access_clidr }, + { SYS_DESC(SYS_SMIDR_EL1), undef_access }, { SYS_DESC(SYS_CSSELR_EL1), access_csselr, reset_unknown, CSSELR_EL1 }, { SYS_DESC(SYS_CTR_EL0), access_ctr }, + { SYS_DESC(SYS_SVCR), undef_access }, { PMU_SYS_REG(SYS_PMCR_EL0), .access = access_pmcr, .reset = reset_pmcr, .reg = PMCR_EL0 }, @@ -1719,6 +1724,7 @@ static const struct sys_reg_desc sys_reg_descs[] = { { SYS_DESC(SYS_TPIDR_EL0), NULL, reset_unknown, TPIDR_EL0 }, { SYS_DESC(SYS_TPIDRRO_EL0), NULL, reset_unknown, TPIDRRO_EL0 }, + { SYS_DESC(SYS_TPIDR2_EL0), undef_access }, { SYS_DESC(SYS_SCXTNUM_EL0), undef_access }, @@ -2304,7 +2310,7 @@ static int kvm_handle_cp_64(struct kvm_vcpu *vcpu, size_t nr_global) { struct sys_reg_params params; - u32 esr = kvm_vcpu_get_esr(vcpu); + u64 esr = kvm_vcpu_get_esr(vcpu); int Rt = kvm_vcpu_sys_get_rt(vcpu); int Rt2 = (esr >> 10) & 0x1f; @@ -2354,7 +2360,7 @@ static int kvm_handle_cp_32(struct kvm_vcpu *vcpu, size_t nr_global) { struct sys_reg_params params; - u32 esr = kvm_vcpu_get_esr(vcpu); + u64 esr = kvm_vcpu_get_esr(vcpu); int Rt = kvm_vcpu_sys_get_rt(vcpu); params.CRm = (esr >> 1) & 0xf; diff --git a/arch/arm64/kvm/vgic/vgic-debug.c b/arch/arm64/kvm/vgic/vgic-debug.c index f38c40a76251..78cde687383c 100644 --- a/arch/arm64/kvm/vgic/vgic-debug.c +++ b/arch/arm64/kvm/vgic/vgic-debug.c @@ -82,7 +82,7 @@ static bool end_of_vgic(struct vgic_state_iter *iter) static void *vgic_debug_start(struct seq_file *s, loff_t *pos) { - struct kvm *kvm = (struct kvm *)s->private; + struct kvm *kvm = s->private; struct vgic_state_iter *iter; mutex_lock(&kvm->lock); @@ -110,7 +110,7 @@ out: static void *vgic_debug_next(struct seq_file *s, void *v, loff_t *pos) { - struct kvm *kvm = (struct kvm *)s->private; + struct kvm *kvm = s->private; struct vgic_state_iter *iter = kvm->arch.vgic.iter; ++*pos; @@ -122,7 +122,7 @@ static void *vgic_debug_next(struct seq_file *s, void *v, loff_t *pos) static void vgic_debug_stop(struct seq_file *s, void *v) { - struct kvm *kvm = (struct kvm *)s->private; + struct kvm *kvm = s->private; struct vgic_state_iter *iter; /* @@ -229,8 +229,8 @@ static void print_irq_state(struct seq_file *s, struct vgic_irq *irq, static int vgic_debug_show(struct seq_file *s, void *v) { - struct kvm *kvm = (struct kvm *)s->private; - struct vgic_state_iter *iter = (struct vgic_state_iter *)v; + struct kvm *kvm = s->private; + struct vgic_state_iter *iter = v; struct vgic_irq *irq; struct kvm_vcpu *vcpu = NULL; unsigned long flags; diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c index 089fc2ffcb43..2e13402be3bd 100644 --- a/arch/arm64/kvm/vgic/vgic-its.c +++ b/arch/arm64/kvm/vgic/vgic-its.c @@ -2143,7 +2143,7 @@ static int vgic_its_save_ite(struct vgic_its *its, struct its_device *dev, static int vgic_its_restore_ite(struct vgic_its *its, u32 event_id, void *ptr, void *opaque) { - struct its_device *dev = (struct its_device *)opaque; + struct its_device *dev = opaque; struct its_collection *collection; struct kvm *kvm = its->dev->kvm; struct kvm_vcpu *vcpu = NULL; diff --git a/arch/arm64/lib/mte.S b/arch/arm64/lib/mte.S index 8590af3c98c0..eeb9e45bcce8 100644 --- a/arch/arm64/lib/mte.S +++ b/arch/arm64/lib/mte.S @@ -93,7 +93,7 @@ SYM_FUNC_START(mte_copy_tags_from_user) mov x3, x1 cbz x2, 2f 1: - user_ldst 2f, ldtrb, w4, x1, 0 +USER(2f, ldtrb w4, [x1]) lsl x4, x4, #MTE_TAG_SHIFT stg x4, [x0], #MTE_GRANULE_SIZE add x1, x1, #1 @@ -120,7 +120,7 @@ SYM_FUNC_START(mte_copy_tags_to_user) 1: ldg x4, [x1] ubfx x4, x4, #MTE_TAG_SHIFT, #MTE_TAG_SIZE - user_ldst 2f, sttrb, w4, x0, 0 +USER(2f, sttrb w4, [x0]) add x0, x0, #1 add x1, x1, #MTE_GRANULE_SIZE subs x2, x2, #1 diff --git a/arch/arm64/mm/copypage.c b/arch/arm64/mm/copypage.c index b5447e53cd73..0dea80bf6de4 100644 --- a/arch/arm64/mm/copypage.c +++ b/arch/arm64/mm/copypage.c @@ -16,8 +16,8 @@ void copy_highpage(struct page *to, struct page *from) { - struct page *kto = page_address(to); - struct page *kfrom = page_address(from); + void *kto = page_address(to); + void *kfrom = page_address(from); copy_page(kto, kfrom); diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 77341b160aca..c5e11768e5c1 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -43,7 +43,7 @@ #include <asm/traps.h> struct fault_info { - int (*fn)(unsigned long far, unsigned int esr, + int (*fn)(unsigned long far, unsigned long esr, struct pt_regs *regs); int sig; int code; @@ -53,17 +53,17 @@ struct fault_info { static const struct fault_info fault_info[]; static struct fault_info debug_fault_info[]; -static inline const struct fault_info *esr_to_fault_info(unsigned int esr) +static inline const struct fault_info *esr_to_fault_info(unsigned long esr) { return fault_info + (esr & ESR_ELx_FSC); } -static inline const struct fault_info *esr_to_debug_fault_info(unsigned int esr) +static inline const struct fault_info *esr_to_debug_fault_info(unsigned long esr) { return debug_fault_info + DBG_ESR_EVT(esr); } -static void data_abort_decode(unsigned int esr) +static void data_abort_decode(unsigned long esr) { pr_alert("Data abort info:\n"); @@ -85,11 +85,11 @@ static void data_abort_decode(unsigned int esr) (esr & ESR_ELx_WNR) >> ESR_ELx_WNR_SHIFT); } -static void mem_abort_decode(unsigned int esr) +static void mem_abort_decode(unsigned long esr) { pr_alert("Mem abort info:\n"); - pr_alert(" ESR = 0x%08x\n", esr); + pr_alert(" ESR = 0x%016lx\n", esr); pr_alert(" EC = 0x%02lx: %s, IL = %u bits\n", ESR_ELx_EC(esr), esr_get_class_string(esr), (esr & ESR_ELx_IL) ? 32 : 16); @@ -99,7 +99,7 @@ static void mem_abort_decode(unsigned int esr) pr_alert(" EA = %lu, S1PTW = %lu\n", (esr & ESR_ELx_EA) >> ESR_ELx_EA_SHIFT, (esr & ESR_ELx_S1PTW) >> ESR_ELx_S1PTW_SHIFT); - pr_alert(" FSC = 0x%02x: %s\n", (esr & ESR_ELx_FSC), + pr_alert(" FSC = 0x%02lx: %s\n", (esr & ESR_ELx_FSC), esr_to_fault_info(esr)->name); if (esr_is_data_abort(esr)) @@ -229,20 +229,20 @@ int ptep_set_access_flags(struct vm_area_struct *vma, return 1; } -static bool is_el1_instruction_abort(unsigned int esr) +static bool is_el1_instruction_abort(unsigned long esr) { return ESR_ELx_EC(esr) == ESR_ELx_EC_IABT_CUR; } -static bool is_el1_data_abort(unsigned int esr) +static bool is_el1_data_abort(unsigned long esr) { return ESR_ELx_EC(esr) == ESR_ELx_EC_DABT_CUR; } -static inline bool is_el1_permission_fault(unsigned long addr, unsigned int esr, +static inline bool is_el1_permission_fault(unsigned long addr, unsigned long esr, struct pt_regs *regs) { - unsigned int fsc_type = esr & ESR_ELx_FSC_TYPE; + unsigned long fsc_type = esr & ESR_ELx_FSC_TYPE; if (!is_el1_data_abort(esr) && !is_el1_instruction_abort(esr)) return false; @@ -258,7 +258,7 @@ static inline bool is_el1_permission_fault(unsigned long addr, unsigned int esr, } static bool __kprobes is_spurious_el1_translation_fault(unsigned long addr, - unsigned int esr, + unsigned long esr, struct pt_regs *regs) { unsigned long flags; @@ -290,7 +290,7 @@ static bool __kprobes is_spurious_el1_translation_fault(unsigned long addr, } static void die_kernel_fault(const char *msg, unsigned long addr, - unsigned int esr, struct pt_regs *regs) + unsigned long esr, struct pt_regs *regs) { bust_spinlocks(1); @@ -308,7 +308,7 @@ static void die_kernel_fault(const char *msg, unsigned long addr, } #ifdef CONFIG_KASAN_HW_TAGS -static void report_tag_fault(unsigned long addr, unsigned int esr, +static void report_tag_fault(unsigned long addr, unsigned long esr, struct pt_regs *regs) { /* @@ -320,11 +320,11 @@ static void report_tag_fault(unsigned long addr, unsigned int esr, } #else /* Tag faults aren't enabled without CONFIG_KASAN_HW_TAGS. */ -static inline void report_tag_fault(unsigned long addr, unsigned int esr, +static inline void report_tag_fault(unsigned long addr, unsigned long esr, struct pt_regs *regs) { } #endif -static void do_tag_recovery(unsigned long addr, unsigned int esr, +static void do_tag_recovery(unsigned long addr, unsigned long esr, struct pt_regs *regs) { @@ -335,13 +335,14 @@ static void do_tag_recovery(unsigned long addr, unsigned int esr, * It will be done lazily on the other CPUs when they will hit a * tag fault. */ - sysreg_clear_set(sctlr_el1, SCTLR_ELx_TCF_MASK, SCTLR_ELx_TCF_NONE); + sysreg_clear_set(sctlr_el1, SCTLR_EL1_TCF_MASK, + SYS_FIELD_PREP_ENUM(SCTLR_EL1, TCF, NONE)); isb(); } -static bool is_el1_mte_sync_tag_check_fault(unsigned int esr) +static bool is_el1_mte_sync_tag_check_fault(unsigned long esr) { - unsigned int fsc = esr & ESR_ELx_FSC; + unsigned long fsc = esr & ESR_ELx_FSC; if (!is_el1_data_abort(esr)) return false; @@ -352,7 +353,7 @@ static bool is_el1_mte_sync_tag_check_fault(unsigned int esr) return false; } -static void __do_kernel_fault(unsigned long addr, unsigned int esr, +static void __do_kernel_fault(unsigned long addr, unsigned long esr, struct pt_regs *regs) { const char *msg; @@ -393,7 +394,7 @@ static void __do_kernel_fault(unsigned long addr, unsigned int esr, die_kernel_fault(msg, addr, esr, regs); } -static void set_thread_esr(unsigned long address, unsigned int esr) +static void set_thread_esr(unsigned long address, unsigned long esr) { current->thread.fault_address = address; @@ -441,7 +442,7 @@ static void set_thread_esr(unsigned long address, unsigned int esr) * exception level). Fail safe by not providing an ESR * context record at all. */ - WARN(1, "ESR 0x%x is not DABT or IABT from EL0\n", esr); + WARN(1, "ESR 0x%lx is not DABT or IABT from EL0\n", esr); esr = 0; break; } @@ -450,7 +451,7 @@ static void set_thread_esr(unsigned long address, unsigned int esr) current->thread.fault_code = esr; } -static void do_bad_area(unsigned long far, unsigned int esr, +static void do_bad_area(unsigned long far, unsigned long esr, struct pt_regs *regs) { unsigned long addr = untagged_addr(far); @@ -501,7 +502,7 @@ static vm_fault_t __do_page_fault(struct mm_struct *mm, unsigned long addr, return handle_mm_fault(vma, addr, mm_flags, regs); } -static bool is_el0_instruction_abort(unsigned int esr) +static bool is_el0_instruction_abort(unsigned long esr) { return ESR_ELx_EC(esr) == ESR_ELx_EC_IABT_LOW; } @@ -510,12 +511,12 @@ static bool is_el0_instruction_abort(unsigned int esr) * Note: not valid for EL1 DC IVAC, but we never use that such that it * should fault. EL0 cannot issue DC IVAC (undef). */ -static bool is_write_abort(unsigned int esr) +static bool is_write_abort(unsigned long esr) { return (esr & ESR_ELx_WNR) && !(esr & ESR_ELx_CM); } -static int __kprobes do_page_fault(unsigned long far, unsigned int esr, +static int __kprobes do_page_fault(unsigned long far, unsigned long esr, struct pt_regs *regs) { const struct fault_info *inf; @@ -671,7 +672,7 @@ no_context: } static int __kprobes do_translation_fault(unsigned long far, - unsigned int esr, + unsigned long esr, struct pt_regs *regs) { unsigned long addr = untagged_addr(far); @@ -683,19 +684,19 @@ static int __kprobes do_translation_fault(unsigned long far, return 0; } -static int do_alignment_fault(unsigned long far, unsigned int esr, +static int do_alignment_fault(unsigned long far, unsigned long esr, struct pt_regs *regs) { do_bad_area(far, esr, regs); return 0; } -static int do_bad(unsigned long far, unsigned int esr, struct pt_regs *regs) +static int do_bad(unsigned long far, unsigned long esr, struct pt_regs *regs) { return 1; /* "fault" */ } -static int do_sea(unsigned long far, unsigned int esr, struct pt_regs *regs) +static int do_sea(unsigned long far, unsigned long esr, struct pt_regs *regs) { const struct fault_info *inf; unsigned long siaddr; @@ -725,7 +726,7 @@ static int do_sea(unsigned long far, unsigned int esr, struct pt_regs *regs) return 0; } -static int do_tag_check_fault(unsigned long far, unsigned int esr, +static int do_tag_check_fault(unsigned long far, unsigned long esr, struct pt_regs *regs) { /* @@ -805,7 +806,7 @@ static const struct fault_info fault_info[] = { { do_bad, SIGKILL, SI_KERNEL, "unknown 63" }, }; -void do_mem_abort(unsigned long far, unsigned int esr, struct pt_regs *regs) +void do_mem_abort(unsigned long far, unsigned long esr, struct pt_regs *regs) { const struct fault_info *inf = esr_to_fault_info(esr); unsigned long addr = untagged_addr(far); @@ -825,14 +826,14 @@ void do_mem_abort(unsigned long far, unsigned int esr, struct pt_regs *regs) } NOKPROBE_SYMBOL(do_mem_abort); -void do_sp_pc_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs) +void do_sp_pc_abort(unsigned long addr, unsigned long esr, struct pt_regs *regs) { arm64_notify_die("SP/PC alignment exception", regs, SIGBUS, BUS_ADRALN, addr, esr); } NOKPROBE_SYMBOL(do_sp_pc_abort); -int __init early_brk64(unsigned long addr, unsigned int esr, +int __init early_brk64(unsigned long addr, unsigned long esr, struct pt_regs *regs); /* @@ -852,7 +853,7 @@ static struct fault_info __refdata debug_fault_info[] = { }; void __init hook_debug_fault_code(int nr, - int (*fn)(unsigned long, unsigned int, struct pt_regs *), + int (*fn)(unsigned long, unsigned long, struct pt_regs *), int sig, int code, const char *name) { BUG_ON(nr < 0 || nr >= ARRAY_SIZE(debug_fault_info)); @@ -885,7 +886,7 @@ static void debug_exception_exit(struct pt_regs *regs) } NOKPROBE_SYMBOL(debug_exception_exit); -void do_debug_exception(unsigned long addr_if_watchpoint, unsigned int esr, +void do_debug_exception(unsigned long addr_if_watchpoint, unsigned long esr, struct pt_regs *regs) { const struct fault_info *inf = esr_to_debug_fault_info(esr); diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index cbace1c9e137..64bb078e2e7b 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -158,6 +158,28 @@ static inline int num_contig_ptes(unsigned long size, size_t *pgsize) return contig_ptes; } +pte_t huge_ptep_get(pte_t *ptep) +{ + int ncontig, i; + size_t pgsize; + pte_t orig_pte = ptep_get(ptep); + + if (!pte_present(orig_pte) || !pte_cont(orig_pte)) + return orig_pte; + + ncontig = num_contig_ptes(page_size(pte_page(orig_pte)), &pgsize); + for (i = 0; i < ncontig; i++, ptep++) { + pte_t pte = ptep_get(ptep); + + if (pte_dirty(pte)) + orig_pte = pte_mkdirty(orig_pte); + + if (pte_young(pte)) + orig_pte = pte_mkyoung(orig_pte); + } + return orig_pte; +} + /* * Changing some bits of contiguous entries requires us to follow a * Break-Before-Make approach, breaking the whole contiguous set @@ -166,15 +188,14 @@ static inline int num_contig_ptes(unsigned long size, size_t *pgsize) * * This helper performs the break step. */ -static pte_t get_clear_flush(struct mm_struct *mm, +static pte_t get_clear_contig(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned long pgsize, unsigned long ncontig) { - pte_t orig_pte = huge_ptep_get(ptep); - bool valid = pte_valid(orig_pte); - unsigned long i, saddr = addr; + pte_t orig_pte = ptep_get(ptep); + unsigned long i; for (i = 0; i < ncontig; i++, addr += pgsize, ptep++) { pte_t pte = ptep_get_and_clear(mm, addr, ptep); @@ -190,11 +211,6 @@ static pte_t get_clear_flush(struct mm_struct *mm, if (pte_young(pte)) orig_pte = pte_mkyoung(orig_pte); } - - if (valid) { - struct vm_area_struct vma = TLB_FLUSH_VMA(mm, 0); - flush_tlb_range(&vma, saddr, addr); - } return orig_pte; } @@ -385,14 +401,14 @@ pte_t huge_ptep_get_and_clear(struct mm_struct *mm, { int ncontig; size_t pgsize; - pte_t orig_pte = huge_ptep_get(ptep); + pte_t orig_pte = ptep_get(ptep); if (!pte_cont(orig_pte)) return ptep_get_and_clear(mm, addr, ptep); ncontig = find_num_contig(mm, addr, ptep, &pgsize); - return get_clear_flush(mm, addr, ptep, pgsize, ncontig); + return get_clear_contig(mm, addr, ptep, pgsize, ncontig); } /* @@ -408,11 +424,11 @@ static int __cont_access_flags_changed(pte_t *ptep, pte_t pte, int ncontig) { int i; - if (pte_write(pte) != pte_write(huge_ptep_get(ptep))) + if (pte_write(pte) != pte_write(ptep_get(ptep))) return 1; for (i = 0; i < ncontig; i++) { - pte_t orig_pte = huge_ptep_get(ptep + i); + pte_t orig_pte = ptep_get(ptep + i); if (pte_dirty(pte) != pte_dirty(orig_pte)) return 1; @@ -443,7 +459,7 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma, if (!__cont_access_flags_changed(ptep, pte, ncontig)) return 0; - orig_pte = get_clear_flush(vma->vm_mm, addr, ptep, pgsize, ncontig); + orig_pte = get_clear_contig(vma->vm_mm, addr, ptep, pgsize, ncontig); /* Make sure we don't lose the dirty or young state */ if (pte_dirty(orig_pte)) @@ -476,7 +492,7 @@ void huge_ptep_set_wrprotect(struct mm_struct *mm, ncontig = find_num_contig(mm, addr, ptep, &pgsize); dpfn = pgsize >> PAGE_SHIFT; - pte = get_clear_flush(mm, addr, ptep, pgsize, ncontig); + pte = get_clear_contig(mm, addr, ptep, pgsize, ncontig); pte = pte_wrprotect(pte); hugeprot = pte_pgprot(pte); diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 8ac25f19084e..a1410143ea62 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -73,7 +73,7 @@ EXPORT_SYMBOL(memstart_addr); * In this scheme a comparatively quicker boot is observed. * * If ZONE_DMA configs are defined, crash kernel memory reservation - * is delayed until DMA zone memory range size initilazation performed in + * is delayed until DMA zone memory range size initialization performed in * zone_sizes_init(). The defer is necessary to steer clear of DMA zone * memory range to avoid overlap allocation. So crash kernel memory boundaries * are not known when mapping all bank memory ranges, which otherwise means @@ -81,7 +81,7 @@ EXPORT_SYMBOL(memstart_addr); * so page-granularity mappings are created for the entire memory range. * Hence a slightly slower boot is observed. * - * Note: Page-granularity mapppings are necessary for crash kernel memory + * Note: Page-granularity mappings are necessary for crash kernel memory * range for shrinking its size via /sys/kernel/kexec_crash_size interface. */ #if IS_ENABLED(CONFIG_ZONE_DMA) || IS_ENABLED(CONFIG_ZONE_DMA32) @@ -90,6 +90,32 @@ phys_addr_t __ro_after_init arm64_dma_phys_limit; phys_addr_t __ro_after_init arm64_dma_phys_limit = PHYS_MASK + 1; #endif +/* Current arm64 boot protocol requires 2MB alignment */ +#define CRASH_ALIGN SZ_2M + +#define CRASH_ADDR_LOW_MAX arm64_dma_phys_limit +#define CRASH_ADDR_HIGH_MAX (PHYS_MASK + 1) + +static int __init reserve_crashkernel_low(unsigned long long low_size) +{ + unsigned long long low_base; + + low_base = memblock_phys_alloc_range(low_size, CRASH_ALIGN, 0, CRASH_ADDR_LOW_MAX); + if (!low_base) { + pr_err("cannot allocate crashkernel low memory (size:0x%llx).\n", low_size); + return -ENOMEM; + } + + pr_info("crashkernel low memory reserved: 0x%08llx - 0x%08llx (%lld MB)\n", + low_base, low_base + low_size, low_size >> 20); + + crashk_low_res.start = low_base; + crashk_low_res.end = low_base + low_size - 1; + insert_resource(&iomem_resource, &crashk_low_res); + + return 0; +} + /* * reserve_crashkernel() - reserves memory for crash kernel * @@ -100,17 +126,35 @@ phys_addr_t __ro_after_init arm64_dma_phys_limit = PHYS_MASK + 1; static void __init reserve_crashkernel(void) { unsigned long long crash_base, crash_size; - unsigned long long crash_max = arm64_dma_phys_limit; + unsigned long long crash_low_size = 0; + unsigned long long crash_max = CRASH_ADDR_LOW_MAX; + char *cmdline = boot_command_line; int ret; if (!IS_ENABLED(CONFIG_KEXEC_CORE)) return; - ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(), + /* crashkernel=X[@offset] */ + ret = parse_crashkernel(cmdline, memblock_phys_mem_size(), &crash_size, &crash_base); - /* no crashkernel= or invalid value specified */ - if (ret || !crash_size) + if (ret == -ENOENT) { + ret = parse_crashkernel_high(cmdline, 0, &crash_size, &crash_base); + if (ret || !crash_size) + return; + + /* + * crashkernel=Y,low can be specified or not, but invalid value + * is not allowed. + */ + ret = parse_crashkernel_low(cmdline, 0, &crash_low_size, &crash_base); + if (ret && (ret != -ENOENT)) + return; + + crash_max = CRASH_ADDR_HIGH_MAX; + } else if (ret || !crash_size) { + /* The specified value is invalid */ return; + } crash_size = PAGE_ALIGN(crash_size); @@ -118,8 +162,7 @@ static void __init reserve_crashkernel(void) if (crash_base) crash_max = crash_base + crash_size; - /* Current arm64 boot protocol requires 2MB alignment */ - crash_base = memblock_phys_alloc_range(crash_size, SZ_2M, + crash_base = memblock_phys_alloc_range(crash_size, CRASH_ALIGN, crash_base, crash_max); if (!crash_base) { pr_warn("cannot allocate crashkernel (size:0x%llx)\n", @@ -127,6 +170,12 @@ static void __init reserve_crashkernel(void) return; } + if ((crash_base >= CRASH_ADDR_LOW_MAX) && + crash_low_size && reserve_crashkernel_low(crash_low_size)) { + memblock_phys_free(crash_base, crash_size); + return; + } + pr_info("crashkernel reserved: 0x%016llx - 0x%016llx (%lld MB)\n", crash_base, crash_base + crash_size, crash_size >> 20); @@ -135,8 +184,12 @@ static void __init reserve_crashkernel(void) * map. Inform kmemleak so that it won't try to access it. */ kmemleak_ignore_phys(crash_base); + if (crashk_low_res.end) + kmemleak_ignore_phys(crashk_low_res.start); + crashk_res.start = crash_base; crashk_res.end = crash_base + crash_size - 1; + insert_resource(&iomem_resource, &crashk_res); } /* @@ -157,7 +210,7 @@ static phys_addr_t __init max_zone_phys(unsigned int zone_bits) return min(zone_mask, memblock_end_of_DRAM() - 1) + 1; } -static void __init zone_sizes_init(unsigned long min, unsigned long max) +static void __init zone_sizes_init(void) { unsigned long max_zone_pfns[MAX_NR_ZONES] = {0}; unsigned int __maybe_unused acpi_zone_dma_bits; @@ -176,7 +229,7 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max) if (!arm64_dma_phys_limit) arm64_dma_phys_limit = dma32_phys_limit; #endif - max_zone_pfns[ZONE_NORMAL] = max; + max_zone_pfns[ZONE_NORMAL] = max_pfn; free_area_init(max_zone_pfns); } @@ -374,7 +427,7 @@ void __init bootmem_init(void) * done after the fixed reservations */ sparse_init(); - zone_sizes_init(min, max); + zone_sizes_init(); /* * Reserve the CMA area after arm64_dma_phys_limit was initialised. diff --git a/arch/arm64/mm/ioremap.c b/arch/arm64/mm/ioremap.c index b7c81dacabf0..b21f91cd830d 100644 --- a/arch/arm64/mm/ioremap.c +++ b/arch/arm64/mm/ioremap.c @@ -99,3 +99,11 @@ void __init early_ioremap_init(void) { early_ioremap_setup(); } + +bool arch_memremap_can_ram_remap(resource_size_t offset, size_t size, + unsigned long flags) +{ + unsigned long pfn = PHYS_PFN(offset); + + return pfn_is_map_memory(pfn); +} diff --git a/arch/arm64/mm/trans_pgd.c b/arch/arm64/mm/trans_pgd.c index d7da8ca40d2e..4ea2eefbc053 100644 --- a/arch/arm64/mm/trans_pgd.c +++ b/arch/arm64/mm/trans_pgd.c @@ -238,7 +238,7 @@ int trans_pgd_idmap_page(struct trans_pgd_info *info, phys_addr_t *trans_ttbr0, int this_level, index, level_lsb, level_msb; dst_addr &= PAGE_MASK; - prev_level_entry = pte_val(pfn_pte(pfn, PAGE_KERNEL_EXEC)); + prev_level_entry = pte_val(pfn_pte(pfn, PAGE_KERNEL_ROX)); for (this_level = 3; this_level >= 0; this_level--) { levels[this_level] = trans_alloc(info); diff --git a/arch/arm64/tools/Makefile b/arch/arm64/tools/Makefile index cf1307188150..07a93ab21a62 100644 --- a/arch/arm64/tools/Makefile +++ b/arch/arm64/tools/Makefile @@ -3,7 +3,7 @@ gen := arch/$(ARCH)/include/generated kapi := $(gen)/asm -kapi-hdrs-y := $(kapi)/cpucaps.h +kapi-hdrs-y := $(kapi)/cpucaps.h $(kapi)/sysreg-defs.h targets += $(addprefix ../../../, $(kapi-hdrs-y)) @@ -14,5 +14,11 @@ kapi: $(kapi-hdrs-y) quiet_cmd_gen_cpucaps = GEN $@ cmd_gen_cpucaps = mkdir -p $(dir $@); $(AWK) -f $(real-prereqs) > $@ +quiet_cmd_gen_sysreg = GEN $@ + cmd_gen_sysreg = mkdir -p $(dir $@); $(AWK) -f $(real-prereqs) > $@ + $(kapi)/cpucaps.h: $(src)/gen-cpucaps.awk $(src)/cpucaps FORCE $(call if_changed,gen_cpucaps) + +$(kapi)/sysreg-defs.h: $(src)/gen-sysreg.awk $(src)/sysreg FORCE + $(call if_changed,gen_sysreg) diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps index 3ed418f70e3b..e52b289a27c2 100644 --- a/arch/arm64/tools/cpucaps +++ b/arch/arm64/tools/cpucaps @@ -43,6 +43,8 @@ KVM_PROTECTED_MODE MISMATCHED_CACHE_TYPE MTE MTE_ASYMM +SME +SME_FA64 SPECTRE_V2 SPECTRE_V3A SPECTRE_V4 diff --git a/arch/arm64/tools/gen-sysreg.awk b/arch/arm64/tools/gen-sysreg.awk new file mode 100755 index 000000000000..89bfb74e28de --- /dev/null +++ b/arch/arm64/tools/gen-sysreg.awk @@ -0,0 +1,268 @@ +#!/bin/awk -f +# SPDX-License-Identifier: GPL-2.0 +# gen-sysreg.awk: arm64 sysreg header generator +# +# Usage: awk -f gen-sysreg.awk sysregs.txt + +# Log an error and terminate +function fatal(msg) { + print "Error at " NR ": " msg > "/dev/stderr" + exit 1 +} + +# Sanity check that the start or end of a block makes sense at this point in +# the file. If not, produce an error and terminate. +# +# @this - the $Block or $EndBlock +# @prev - the only valid block to already be in (value of @block) +# @new - the new value of @block +function change_block(this, prev, new) { + if (block != prev) + fatal("unexpected " this " (inside " block ")") + + block = new +} + +# Sanity check the number of records for a field makes sense. If not, produce +# an error and terminate. +function expect_fields(nf) { + if (NF != nf) + fatal(NF " fields found where " nf " expected") +} + +# Print a CPP macro definition, padded with spaces so that the macro bodies +# line up in a column +function define(name, val) { + printf "%-48s%s\n", "#define " name, val +} + +# Print standard BITMASK/SHIFT/WIDTH CPP definitions for a field +function define_field(reg, field, msb, lsb) { + define(reg "_" field, "GENMASK(" msb ", " lsb ")") + define(reg "_" field "_MASK", "GENMASK(" msb ", " lsb ")") + define(reg "_" field "_SHIFT", lsb) + define(reg "_" field "_WIDTH", msb - lsb + 1) +} + +# Parse a "<msb>[:<lsb>]" string into the global variables @msb and @lsb +function parse_bitdef(reg, field, bitdef, _bits) +{ + if (bitdef ~ /^[0-9]+$/) { + msb = bitdef + lsb = bitdef + } else if (split(bitdef, _bits, ":") == 2) { + msb = _bits[1] + lsb = _bits[2] + } else { + fatal("invalid bit-range definition '" bitdef "'") + } + + + if (msb != next_bit) + fatal(reg "." field " starts at " msb " not " next_bit) + if (63 < msb || msb < 0) + fatal(reg "." field " invalid high bit in '" bitdef "'") + if (63 < lsb || lsb < 0) + fatal(reg "." field " invalid low bit in '" bitdef "'") + if (msb < lsb) + fatal(reg "." field " invalid bit-range '" bitdef "'") + if (low > high) + fatal(reg "." field " has invalid range " high "-" low) + + next_bit = lsb - 1 +} + +BEGIN { + print "#ifndef __ASM_SYSREG_DEFS_H" + print "#define __ASM_SYSREG_DEFS_H" + print "" + print "/* Generated file - do not edit */" + print "" + + block = "None" +} + +END { + print "#endif /* __ASM_SYSREG_DEFS_H */" +} + +# skip blank lines and comment lines +/^$/ { next } +/^#/ { next } + +/^SysregFields/ { + change_block("SysregFields", "None", "SysregFields") + expect_fields(2) + + reg = $2 + + res0 = "UL(0)" + res1 = "UL(0)" + + next_bit = 63 + + next +} + +/^EndSysregFields/ { + if (next_bit > 0) + fatal("Unspecified bits in " reg) + + change_block("EndSysregFields", "SysregFields", "None") + + define(reg "_RES0", "(" res0 ")") + define(reg "_RES1", "(" res1 ")") + print "" + + reg = null + res0 = null + res1 = null + + next +} + +/^Sysreg/ { + change_block("Sysreg", "None", "Sysreg") + expect_fields(7) + + reg = $2 + op0 = $3 + op1 = $4 + crn = $5 + crm = $6 + op2 = $7 + + res0 = "UL(0)" + res1 = "UL(0)" + + define("REG_" reg, "S" op0 "_" op1 "_C" crn "_C" crm "_" op2) + define("SYS_" reg, "sys_reg(" op0 ", " op1 ", " crn ", " crm ", " op2 ")") + + define("SYS_" reg "_Op0", op0) + define("SYS_" reg "_Op1", op1) + define("SYS_" reg "_CRn", crn) + define("SYS_" reg "_CRm", crm) + define("SYS_" reg "_Op2", op2) + + print "" + + next_bit = 63 + + next +} + +/^EndSysreg/ { + if (next_bit > 0) + fatal("Unspecified bits in " reg) + + change_block("EndSysreg", "Sysreg", "None") + + if (res0 != null) + define(reg "_RES0", "(" res0 ")") + if (res1 != null) + define(reg "_RES1", "(" res1 ")") + if (res0 != null || res1 != null) + print "" + + reg = null + op0 = null + op1 = null + crn = null + crm = null + op2 = null + res0 = null + res1 = null + + next +} + +# Currently this is effectivey a comment, in future we may want to emit +# defines for the fields. +/^Fields/ && (block == "Sysreg") { + expect_fields(2) + + if (next_bit != 63) + fatal("Some fields already defined for " reg) + + print "/* For " reg " fields see " $2 " */" + print "" + + next_bit = 0 + res0 = null + res1 = null + + next +} + + +/^Res0/ && (block == "Sysreg" || block == "SysregFields") { + expect_fields(2) + parse_bitdef(reg, "RES0", $2) + field = "RES0_" msb "_" lsb + + res0 = res0 " | GENMASK_ULL(" msb ", " lsb ")" + + next +} + +/^Res1/ && (block == "Sysreg" || block == "SysregFields") { + expect_fields(2) + parse_bitdef(reg, "RES1", $2) + field = "RES1_" msb "_" lsb + + res1 = res1 " | GENMASK_ULL(" msb ", " lsb ")" + + next +} + +/^Field/ && (block == "Sysreg" || block == "SysregFields") { + expect_fields(3) + field = $3 + parse_bitdef(reg, field, $2) + + define_field(reg, field, msb, lsb) + print "" + + next +} + +/^Raz/ && (block == "Sysreg" || block == "SysregFields") { + expect_fields(2) + parse_bitdef(reg, field, $2) + + next +} + +/^Enum/ { + change_block("Enum", "Sysreg", "Enum") + expect_fields(3) + field = $3 + parse_bitdef(reg, field, $2) + + define_field(reg, field, msb, lsb) + + next +} + +/^EndEnum/ { + change_block("EndEnum", "Enum", "Sysreg") + field = null + msb = null + lsb = null + print "" + next +} + +/0b[01]+/ && block = "Enum" { + expect_fields(2) + val = $1 + name = $2 + + define(reg "_" field "_" name, "UL(" val ")") + next +} + +# Any lines not handled by previous rules are unexpected +{ + fatal("unhandled statement") +} diff --git a/arch/arm64/tools/sysreg b/arch/arm64/tools/sysreg new file mode 100644 index 000000000000..ff5e552f7420 --- /dev/null +++ b/arch/arm64/tools/sysreg @@ -0,0 +1,369 @@ +# SPDX-License-Identifier: GPL-2.0-only +# +# System register metadata + +# Each System register is described by a Sysreg block: + +# Sysreg <name> <op0> <op1> <crn> <crm> <op2> +# <field> +# ... +# EndSysreg + +# Within a Sysreg block, each field can be described as one of: + +# Res0 <msb>[:<lsb>] + +# Res1 <msb>[:<lsb>] + +# Field <msb>[:<lsb>] <name> + +# Enum <msb>[:<lsb>] <name> +# <enumval> <enumname> +# ... +# EndEnum + +# Alternatively if multiple registers share the same layout then +# a SysregFields block can be used to describe the shared layout + +# SysregFields <fieldsname> +# <field> +# ... +# EndSysregFields + +# and referenced from within the Sysreg: + +# Sysreg <name> <op0> <op1> <crn> <crm> <op2> +# Fields <fieldsname> +# EndSysreg + +# For ID registers we adopt a few conventions for translating the +# language in the ARM into defines: +# +# NI - Not implemented +# IMP - Implemented +# +# In general it is recommended that new enumeration items be named for the +# feature that introduces them (eg, FEAT_LS64_ACCDATA introduces enumeration +# item ACCDATA) though it may be more taseful to do something else. + +Sysreg ID_AA64ISAR0_EL1 3 0 0 6 0 +Enum 63:60 RNDR + 0b0000 NI + 0b0001 IMP +EndEnum +Enum 59:56 TLB + 0b0000 NI + 0b0001 OS + 0b0010 RANGE +EndEnum +Enum 55:52 TS + 0b0000 NI + 0b0001 FLAGM + 0b0010 FLAGM2 +EndEnum +Enum 51:48 FHM + 0b0000 NI + 0b0001 IMP +EndEnum +Enum 47:44 DP + 0b0000 NI + 0b0001 IMP +EndEnum +Enum 43:40 SM4 + 0b0000 NI + 0b0001 IMP +EndEnum +Enum 39:36 SM3 + 0b0000 NI + 0b0001 IMP +EndEnum +Enum 35:32 SHA3 + 0b0000 NI + 0b0001 IMP +EndEnum +Enum 31:28 RDM + 0b0000 NI + 0b0001 IMP +EndEnum +Enum 27:24 TME + 0b0000 NI + 0b0001 IMP +EndEnum +Enum 23:20 ATOMIC + 0b0000 NI + 0b0010 IMP +EndEnum +Enum 19:16 CRC32 + 0b0000 NI + 0b0001 IMP +EndEnum +Enum 15:12 SHA2 + 0b0000 NI + 0b0001 SHA256 + 0b0010 SHA512 +EndEnum +Enum 11:8 SHA1 + 0b0000 NI + 0b0001 IMP +EndEnum +Enum 7:4 AES + 0b0000 NI + 0b0001 AES + 0b0010 PMULL +EndEnum +Res0 3:0 +EndSysreg + +Sysreg SCTLR_EL1 3 0 1 0 0 +Field 63 TIDCP +Field 62 SPINMASK +Field 61 NMI +Field 60 EnTP2 +Res0 59:58 +Field 57 EPAN +Field 56 EnALS +Field 55 EnAS0 +Field 54 EnASR +Field 53 TME +Field 52 TME0 +Field 51 TMT +Field 50 TMT0 +Field 49:46 TWEDEL +Field 45 TWEDEn +Field 44 DSSBS +Field 43 ATA +Field 42 ATA0 +Enum 41:40 TCF + 0b00 NONE + 0b01 SYNC + 0b10 ASYNC + 0b11 ASYMM +EndEnum +Enum 39:38 TCF0 + 0b00 NONE + 0b01 SYNC + 0b10 ASYNC + 0b11 ASYMM +EndEnum +Field 37 ITFSB +Field 36 BT1 +Field 35 BT0 +Res0 34 +Field 33 MSCEn +Field 32 CMOW +Field 31 EnIA +Field 30 EnIB +Field 29 LSMAOE +Field 28 nTLSMD +Field 27 EnDA +Field 26 UCI +Field 25 EE +Field 24 E0E +Field 23 SPAN +Field 22 EIS +Field 21 IESB +Field 20 TSCXT +Field 19 WXN +Field 18 nTWE +Res0 17 +Field 16 nTWI +Field 15 UCT +Field 14 DZE +Field 13 EnDB +Field 12 I +Field 11 EOS +Field 10 EnRCTX +Field 9 UMA +Field 8 SED +Field 7 ITD +Field 6 nAA +Field 5 CP15BEN +Field 4 SA0 +Field 3 SA +Field 2 C +Field 1 A +Field 0 M +EndSysreg + +SysregFields CPACR_ELx +Res0 63:29 +Field 28 TTA +Res0 27:26 +Field 25:24 SMEN +Res0 23:22 +Field 21:20 FPEN +Res0 19:18 +Field 17:16 ZEN +Res0 15:0 +EndSysregFields + +Sysreg CPACR_EL1 3 0 1 0 2 +Fields CPACR_ELx +EndSysreg + +Sysreg SMPRI_EL1 3 0 1 2 4 +Res0 63:4 +Field 3:0 PRIORITY +EndSysreg + +SysregFields ZCR_ELx +Res0 63:9 +Raz 8:4 +Field 3:0 LEN +EndSysregFields + +Sysreg ZCR_EL1 3 0 1 2 0 +Fields ZCR_ELx +EndSysreg + +SysregFields SMCR_ELx +Res0 63:32 +Field 31 FA64 +Res0 30:9 +Raz 8:4 +Field 3:0 LEN +EndSysregFields + +Sysreg SMCR_EL1 3 0 1 2 6 +Fields SMCR_ELx +EndSysreg + +Sysreg FAR_EL1 3 0 6 0 0 +Field 63:0 ADDR +EndSysreg + +SysregFields CONTEXTIDR_ELx +Res0 63:32 +Field 31:0 PROCID +EndSysregFields + +Sysreg CONTEXTIDR_EL1 3 0 13 0 1 +Fields CONTEXTIDR_ELx +EndSysreg + +Sysreg CLIDR_EL1 3 1 0 0 1 +Res0 63:47 +Field 46:33 Ttypen +Field 32:30 ICB +Field 29:27 LoUU +Field 26:24 LoC +Field 23:21 LoUIS +Field 20:18 Ctype7 +Field 17:15 Ctype6 +Field 14:12 Ctype5 +Field 11:9 Ctype4 +Field 8:6 Ctype3 +Field 5:3 Ctype2 +Field 2:0 Ctype1 +EndSysreg + +Sysreg SMIDR_EL1 3 1 0 0 6 +Res0 63:32 +Field 31:24 IMPLEMENTER +Field 23:16 REVISION +Field 15 SMPS +Res0 14:12 +Field 11:0 AFFINITY +EndSysreg + +Sysreg CSSELR_EL1 3 2 0 0 0 +Res0 63:5 +Field 4 TnD +Field 3:1 Level +Field 0 InD +EndSysreg + +Sysreg SVCR 3 3 4 2 2 +Res0 63:2 +Field 1 ZA +Field 0 SM +EndSysreg + +Sysreg ZCR_EL2 3 4 1 2 0 +Fields ZCR_ELx +EndSysreg + +Sysreg SMPRIMAP_EL2 3 4 1 2 5 +Field 63:60 P15 +Field 59:56 P14 +Field 55:52 P13 +Field 51:48 P12 +Field 47:44 P11 +Field 43:40 P10 +Field 39:36 F9 +Field 35:32 P8 +Field 31:28 P7 +Field 27:24 P6 +Field 23:20 P5 +Field 19:16 P4 +Field 15:12 P3 +Field 11:8 P2 +Field 7:4 P1 +Field 3:0 P0 +EndSysreg + +Sysreg SMCR_EL2 3 4 1 2 6 +Fields SMCR_ELx +EndSysreg + +Sysreg DACR32_EL2 3 4 3 0 0 +Res0 63:32 +Field 31:30 D15 +Field 29:28 D14 +Field 27:26 D13 +Field 25:24 D12 +Field 23:22 D11 +Field 21:20 D10 +Field 19:18 D9 +Field 17:16 D8 +Field 15:14 D7 +Field 13:12 D6 +Field 11:10 D5 +Field 9:8 D4 +Field 7:6 D3 +Field 5:4 D2 +Field 3:2 D1 +Field 1:0 D0 +EndSysreg + +Sysreg FAR_EL2 3 4 6 0 0 +Field 63:0 ADDR +EndSysreg + +Sysreg CONTEXTIDR_EL2 3 4 13 0 1 +Fields CONTEXTIDR_ELx +EndSysreg + +Sysreg CPACR_EL12 3 5 1 0 2 +Fields CPACR_ELx +EndSysreg + +Sysreg ZCR_EL12 3 5 1 2 0 +Fields ZCR_ELx +EndSysreg + +Sysreg SMCR_EL12 3 5 1 2 6 +Fields SMCR_ELx +EndSysreg + +Sysreg FAR_EL12 3 5 6 0 0 +Field 63:0 ADDR +EndSysreg + +Sysreg CONTEXTIDR_EL12 3 5 13 0 1 +Fields CONTEXTIDR_ELx +EndSysreg + +SysregFields TTBRx_EL1 +Field 63:48 ASID +Field 47:1 BADDR +Field 0 CnP +EndSysregFields + +Sysreg TTBR0_EL1 3 0 2 0 0 +Fields TTBRx_EL1 +EndSysreg + +Sysreg TTBR1_EL1 3 0 2 0 1 +Fields TTBRx_EL1 +EndSysreg diff --git a/arch/csky/Kbuild b/arch/csky/Kbuild index 4e39f7abdeb6..0621eaea4196 100644 --- a/arch/csky/Kbuild +++ b/arch/csky/Kbuild @@ -1,4 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-only +obj-y += kernel/ mm/ + # for cleaning subdir- += boot diff --git a/arch/csky/Kconfig b/arch/csky/Kconfig index 75ef86605d69..21d72b078eef 100644 --- a/arch/csky/Kconfig +++ b/arch/csky/Kconfig @@ -320,6 +320,14 @@ config HOTPLUG_CPU controlled through /sys/devices/system/cpu/cpu1/hotplug/target. Say N if you want to disable CPU hotplug. + +config HAVE_EFFICIENT_UNALIGNED_STRING_OPS + bool "Enable EFFICIENT_UNALIGNED_STRING_OPS for abiv2" + depends on CPU_CK807 || CPU_CK810 || CPU_CK860 + help + Say Y here to enable EFFICIENT_UNALIGNED_STRING_OPS. Some CPU models could + deal with unaligned access by hardware. + endmenu source "arch/csky/Kconfig.platforms" diff --git a/arch/csky/Makefile b/arch/csky/Makefile index 866805077636..4e1d619fd5c6 100644 --- a/arch/csky/Makefile +++ b/arch/csky/Makefile @@ -61,15 +61,12 @@ KBUILD_AFLAGS += $(KBUILD_CFLAGS) head-y := arch/csky/kernel/head.o -core-y += arch/csky/kernel/ -core-y += arch/csky/mm/ core-y += arch/csky/$(CSKYABI)/ libs-y += arch/csky/lib/ \ $(shell $(CC) $(KBUILD_CFLAGS) $(KCFLAGS) -print-libgcc-file-name) boot := arch/csky/boot -core-y += $(boot)/dts/ all: zImage diff --git a/arch/csky/abiv1/Makefile b/arch/csky/abiv1/Makefile index 601ce3b2fb85..a4b2ade0fc67 100644 --- a/arch/csky/abiv1/Makefile +++ b/arch/csky/abiv1/Makefile @@ -4,5 +4,3 @@ obj-y += bswapdi.o obj-y += bswapsi.o obj-y += cacheflush.o obj-y += mmap.o -obj-y += memcpy.o -obj-y += strksyms.o diff --git a/arch/csky/abiv1/memcpy.S b/arch/csky/abiv1/memcpy.S deleted file mode 100644 index 5078eb5169fa..000000000000 --- a/arch/csky/abiv1/memcpy.S +++ /dev/null @@ -1,347 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd. - -#include <linux/linkage.h> - -.macro GET_FRONT_BITS rx y -#ifdef __cskyLE__ - lsri \rx, \y -#else - lsli \rx, \y -#endif -.endm - -.macro GET_AFTER_BITS rx y -#ifdef __cskyLE__ - lsli \rx, \y -#else - lsri \rx, \y -#endif -.endm - -/* void *memcpy(void *dest, const void *src, size_t n); */ -ENTRY(memcpy) - mov r7, r2 - cmplti r4, 4 - bt .L_copy_by_byte - mov r6, r2 - andi r6, 3 - cmpnei r6, 0 - jbt .L_dest_not_aligned - mov r6, r3 - andi r6, 3 - cmpnei r6, 0 - jbt .L_dest_aligned_but_src_not_aligned -.L0: - cmplti r4, 16 - jbt .L_aligned_and_len_less_16bytes - subi sp, 8 - stw r8, (sp, 0) -.L_aligned_and_len_larger_16bytes: - ldw r1, (r3, 0) - ldw r5, (r3, 4) - ldw r8, (r3, 8) - stw r1, (r7, 0) - ldw r1, (r3, 12) - stw r5, (r7, 4) - stw r8, (r7, 8) - stw r1, (r7, 12) - subi r4, 16 - addi r3, 16 - addi r7, 16 - cmplti r4, 16 - jbf .L_aligned_and_len_larger_16bytes - ldw r8, (sp, 0) - addi sp, 8 - cmpnei r4, 0 - jbf .L_return - -.L_aligned_and_len_less_16bytes: - cmplti r4, 4 - bt .L_copy_by_byte -.L1: - ldw r1, (r3, 0) - stw r1, (r7, 0) - subi r4, 4 - addi r3, 4 - addi r7, 4 - cmplti r4, 4 - jbf .L1 - br .L_copy_by_byte - -.L_return: - rts - -.L_copy_by_byte: /* len less than 4 bytes */ - cmpnei r4, 0 - jbf .L_return -.L4: - ldb r1, (r3, 0) - stb r1, (r7, 0) - addi r3, 1 - addi r7, 1 - decne r4 - jbt .L4 - rts - -/* - * If dest is not aligned, just copying some bytes makes the dest align. - * Afther that, we judge whether the src is aligned. - */ -.L_dest_not_aligned: - mov r5, r3 - rsub r5, r5, r7 - abs r5, r5 - cmplt r5, r4 - bt .L_copy_by_byte - mov r5, r7 - sub r5, r3 - cmphs r5, r4 - bf .L_copy_by_byte - mov r5, r6 -.L5: - ldb r1, (r3, 0) /* makes the dest align. */ - stb r1, (r7, 0) - addi r5, 1 - subi r4, 1 - addi r3, 1 - addi r7, 1 - cmpnei r5, 4 - jbt .L5 - cmplti r4, 4 - jbt .L_copy_by_byte - mov r6, r3 /* judge whether the src is aligned. */ - andi r6, 3 - cmpnei r6, 0 - jbf .L0 - -/* Judge the number of misaligned, 1, 2, 3? */ -.L_dest_aligned_but_src_not_aligned: - mov r5, r3 - rsub r5, r5, r7 - abs r5, r5 - cmplt r5, r4 - bt .L_copy_by_byte - bclri r3, 0 - bclri r3, 1 - ldw r1, (r3, 0) - addi r3, 4 - cmpnei r6, 2 - bf .L_dest_aligned_but_src_not_aligned_2bytes - cmpnei r6, 3 - bf .L_dest_aligned_but_src_not_aligned_3bytes - -.L_dest_aligned_but_src_not_aligned_1byte: - mov r5, r7 - sub r5, r3 - cmphs r5, r4 - bf .L_copy_by_byte - cmplti r4, 16 - bf .L11 -.L10: /* If the len is less than 16 bytes */ - GET_FRONT_BITS r1 8 - mov r5, r1 - ldw r6, (r3, 0) - mov r1, r6 - GET_AFTER_BITS r6 24 - or r5, r6 - stw r5, (r7, 0) - subi r4, 4 - addi r3, 4 - addi r7, 4 - cmplti r4, 4 - bf .L10 - subi r3, 3 - br .L_copy_by_byte -.L11: - subi sp, 16 - stw r8, (sp, 0) - stw r9, (sp, 4) - stw r10, (sp, 8) - stw r11, (sp, 12) -.L12: - ldw r5, (r3, 0) - ldw r11, (r3, 4) - ldw r8, (r3, 8) - ldw r9, (r3, 12) - - GET_FRONT_BITS r1 8 /* little or big endian? */ - mov r10, r5 - GET_AFTER_BITS r5 24 - or r5, r1 - - GET_FRONT_BITS r10 8 - mov r1, r11 - GET_AFTER_BITS r11 24 - or r11, r10 - - GET_FRONT_BITS r1 8 - mov r10, r8 - GET_AFTER_BITS r8 24 - or r8, r1 - - GET_FRONT_BITS r10 8 - mov r1, r9 - GET_AFTER_BITS r9 24 - or r9, r10 - - stw r5, (r7, 0) - stw r11, (r7, 4) - stw r8, (r7, 8) - stw r9, (r7, 12) - subi r4, 16 - addi r3, 16 - addi r7, 16 - cmplti r4, 16 - jbf .L12 - ldw r8, (sp, 0) - ldw r9, (sp, 4) - ldw r10, (sp, 8) - ldw r11, (sp, 12) - addi sp , 16 - cmplti r4, 4 - bf .L10 - subi r3, 3 - br .L_copy_by_byte - -.L_dest_aligned_but_src_not_aligned_2bytes: - cmplti r4, 16 - bf .L21 -.L20: - GET_FRONT_BITS r1 16 - mov r5, r1 - ldw r6, (r3, 0) - mov r1, r6 - GET_AFTER_BITS r6 16 - or r5, r6 - stw r5, (r7, 0) - subi r4, 4 - addi r3, 4 - addi r7, 4 - cmplti r4, 4 - bf .L20 - subi r3, 2 - br .L_copy_by_byte - rts - -.L21: /* n > 16 */ - subi sp, 16 - stw r8, (sp, 0) - stw r9, (sp, 4) - stw r10, (sp, 8) - stw r11, (sp, 12) - -.L22: - ldw r5, (r3, 0) - ldw r11, (r3, 4) - ldw r8, (r3, 8) - ldw r9, (r3, 12) - - GET_FRONT_BITS r1 16 - mov r10, r5 - GET_AFTER_BITS r5 16 - or r5, r1 - - GET_FRONT_BITS r10 16 - mov r1, r11 - GET_AFTER_BITS r11 16 - or r11, r10 - - GET_FRONT_BITS r1 16 - mov r10, r8 - GET_AFTER_BITS r8 16 - or r8, r1 - - GET_FRONT_BITS r10 16 - mov r1, r9 - GET_AFTER_BITS r9 16 - or r9, r10 - - stw r5, (r7, 0) - stw r11, (r7, 4) - stw r8, (r7, 8) - stw r9, (r7, 12) - subi r4, 16 - addi r3, 16 - addi r7, 16 - cmplti r4, 16 - jbf .L22 - ldw r8, (sp, 0) - ldw r9, (sp, 4) - ldw r10, (sp, 8) - ldw r11, (sp, 12) - addi sp, 16 - cmplti r4, 4 - bf .L20 - subi r3, 2 - br .L_copy_by_byte - - -.L_dest_aligned_but_src_not_aligned_3bytes: - cmplti r4, 16 - bf .L31 -.L30: - GET_FRONT_BITS r1 24 - mov r5, r1 - ldw r6, (r3, 0) - mov r1, r6 - GET_AFTER_BITS r6 8 - or r5, r6 - stw r5, (r7, 0) - subi r4, 4 - addi r3, 4 - addi r7, 4 - cmplti r4, 4 - bf .L30 - subi r3, 1 - br .L_copy_by_byte -.L31: - subi sp, 16 - stw r8, (sp, 0) - stw r9, (sp, 4) - stw r10, (sp, 8) - stw r11, (sp, 12) -.L32: - ldw r5, (r3, 0) - ldw r11, (r3, 4) - ldw r8, (r3, 8) - ldw r9, (r3, 12) - - GET_FRONT_BITS r1 24 - mov r10, r5 - GET_AFTER_BITS r5 8 - or r5, r1 - - GET_FRONT_BITS r10 24 - mov r1, r11 - GET_AFTER_BITS r11 8 - or r11, r10 - - GET_FRONT_BITS r1 24 - mov r10, r8 - GET_AFTER_BITS r8 8 - or r8, r1 - - GET_FRONT_BITS r10 24 - mov r1, r9 - GET_AFTER_BITS r9 8 - or r9, r10 - - stw r5, (r7, 0) - stw r11, (r7, 4) - stw r8, (r7, 8) - stw r9, (r7, 12) - subi r4, 16 - addi r3, 16 - addi r7, 16 - cmplti r4, 16 - jbf .L32 - ldw r8, (sp, 0) - ldw r9, (sp, 4) - ldw r10, (sp, 8) - ldw r11, (sp, 12) - addi sp, 16 - cmplti r4, 4 - bf .L30 - subi r3, 1 - br .L_copy_by_byte diff --git a/arch/csky/abiv1/strksyms.c b/arch/csky/abiv1/strksyms.c deleted file mode 100644 index c7ccbb27e8d7..000000000000 --- a/arch/csky/abiv1/strksyms.c +++ /dev/null @@ -1,6 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd. - -#include <linux/module.h> - -EXPORT_SYMBOL(memcpy); diff --git a/arch/csky/abiv2/Makefile b/arch/csky/abiv2/Makefile index c561efa5533c..ea8005fe01a8 100644 --- a/arch/csky/abiv2/Makefile +++ b/arch/csky/abiv2/Makefile @@ -2,9 +2,11 @@ obj-y += cacheflush.o obj-$(CONFIG_CPU_HAS_FPU) += fpu.o obj-y += memcmp.o +ifeq ($(CONFIG_HAVE_EFFICIENT_UNALIGNED_STRING_OPS), y) obj-y += memcpy.o obj-y += memmove.o obj-y += memset.o +endif obj-y += strcmp.o obj-y += strcpy.o obj-y += strlen.o diff --git a/arch/csky/abiv2/strksyms.c b/arch/csky/abiv2/strksyms.c index 06da723d8202..8d1fd28c6cf9 100644 --- a/arch/csky/abiv2/strksyms.c +++ b/arch/csky/abiv2/strksyms.c @@ -3,10 +3,12 @@ #include <linux/module.h> +#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_STRING_OPS EXPORT_SYMBOL(memcpy); EXPORT_SYMBOL(memset); -EXPORT_SYMBOL(memcmp); EXPORT_SYMBOL(memmove); +#endif +EXPORT_SYMBOL(memcmp); EXPORT_SYMBOL(strcmp); EXPORT_SYMBOL(strcpy); EXPORT_SYMBOL(strlen); diff --git a/arch/csky/boot/Makefile b/arch/csky/boot/Makefile index dbc9b1bd72f0..c3cfde28f8e6 100644 --- a/arch/csky/boot/Makefile +++ b/arch/csky/boot/Makefile @@ -1,6 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only targets := Image zImage uImage -targets += $(dtb-y) $(obj)/Image: vmlinux FORCE $(call if_changed,objcopy) diff --git a/arch/csky/include/asm/atomic.h b/arch/csky/include/asm/atomic.h new file mode 100644 index 000000000000..60406ef9c2bb --- /dev/null +++ b/arch/csky/include/asm/atomic.h @@ -0,0 +1,237 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __ASM_CSKY_ATOMIC_H +#define __ASM_CSKY_ATOMIC_H + +#ifdef CONFIG_SMP +#include <asm-generic/atomic64.h> + +#include <asm/cmpxchg.h> +#include <asm/barrier.h> + +#define __atomic_acquire_fence() __bar_brarw() + +#define __atomic_release_fence() __bar_brwaw() + +static __always_inline int arch_atomic_read(const atomic_t *v) +{ + return READ_ONCE(v->counter); +} +static __always_inline void arch_atomic_set(atomic_t *v, int i) +{ + WRITE_ONCE(v->counter, i); +} + +#define ATOMIC_OP(op) \ +static __always_inline \ +void arch_atomic_##op(int i, atomic_t *v) \ +{ \ + unsigned long tmp; \ + __asm__ __volatile__ ( \ + "1: ldex.w %0, (%2) \n" \ + " " #op " %0, %1 \n" \ + " stex.w %0, (%2) \n" \ + " bez %0, 1b \n" \ + : "=&r" (tmp) \ + : "r" (i), "r" (&v->counter) \ + : "memory"); \ +} + +ATOMIC_OP(add) +ATOMIC_OP(sub) +ATOMIC_OP(and) +ATOMIC_OP( or) +ATOMIC_OP(xor) + +#undef ATOMIC_OP + +#define ATOMIC_FETCH_OP(op) \ +static __always_inline \ +int arch_atomic_fetch_##op##_relaxed(int i, atomic_t *v) \ +{ \ + register int ret, tmp; \ + __asm__ __volatile__ ( \ + "1: ldex.w %0, (%3) \n" \ + " mov %1, %0 \n" \ + " " #op " %0, %2 \n" \ + " stex.w %0, (%3) \n" \ + " bez %0, 1b \n" \ + : "=&r" (tmp), "=&r" (ret) \ + : "r" (i), "r"(&v->counter) \ + : "memory"); \ + return ret; \ +} + +#define ATOMIC_OP_RETURN(op, c_op) \ +static __always_inline \ +int arch_atomic_##op##_return_relaxed(int i, atomic_t *v) \ +{ \ + return arch_atomic_fetch_##op##_relaxed(i, v) c_op i; \ +} + +#define ATOMIC_OPS(op, c_op) \ + ATOMIC_FETCH_OP(op) \ + ATOMIC_OP_RETURN(op, c_op) + +ATOMIC_OPS(add, +) +ATOMIC_OPS(sub, -) + +#define arch_atomic_fetch_add_relaxed arch_atomic_fetch_add_relaxed +#define arch_atomic_fetch_sub_relaxed arch_atomic_fetch_sub_relaxed + +#define arch_atomic_add_return_relaxed arch_atomic_add_return_relaxed +#define arch_atomic_sub_return_relaxed arch_atomic_sub_return_relaxed + +#undef ATOMIC_OPS +#undef ATOMIC_OP_RETURN + +#define ATOMIC_OPS(op) \ + ATOMIC_FETCH_OP(op) + +ATOMIC_OPS(and) +ATOMIC_OPS( or) +ATOMIC_OPS(xor) + +#define arch_atomic_fetch_and_relaxed arch_atomic_fetch_and_relaxed +#define arch_atomic_fetch_or_relaxed arch_atomic_fetch_or_relaxed +#define arch_atomic_fetch_xor_relaxed arch_atomic_fetch_xor_relaxed + +#undef ATOMIC_OPS + +#undef ATOMIC_FETCH_OP + +static __always_inline int +arch_atomic_fetch_add_unless(atomic_t *v, int a, int u) +{ + int prev, tmp; + + __asm__ __volatile__ ( + RELEASE_FENCE + "1: ldex.w %0, (%3) \n" + " cmpne %0, %4 \n" + " bf 2f \n" + " mov %1, %0 \n" + " add %1, %2 \n" + " stex.w %1, (%3) \n" + " bez %1, 1b \n" + FULL_FENCE + "2:\n" + : "=&r" (prev), "=&r" (tmp) + : "r" (a), "r" (&v->counter), "r" (u) + : "memory"); + + return prev; +} +#define arch_atomic_fetch_add_unless arch_atomic_fetch_add_unless + +static __always_inline bool +arch_atomic_inc_unless_negative(atomic_t *v) +{ + int rc, tmp; + + __asm__ __volatile__ ( + RELEASE_FENCE + "1: ldex.w %0, (%2) \n" + " movi %1, 0 \n" + " blz %0, 2f \n" + " movi %1, 1 \n" + " addi %0, 1 \n" + " stex.w %0, (%2) \n" + " bez %0, 1b \n" + FULL_FENCE + "2:\n" + : "=&r" (tmp), "=&r" (rc) + : "r" (&v->counter) + : "memory"); + + return tmp ? true : false; + +} +#define arch_atomic_inc_unless_negative arch_atomic_inc_unless_negative + +static __always_inline bool +arch_atomic_dec_unless_positive(atomic_t *v) +{ + int rc, tmp; + + __asm__ __volatile__ ( + RELEASE_FENCE + "1: ldex.w %0, (%2) \n" + " movi %1, 0 \n" + " bhz %0, 2f \n" + " movi %1, 1 \n" + " subi %0, 1 \n" + " stex.w %0, (%2) \n" + " bez %0, 1b \n" + FULL_FENCE + "2:\n" + : "=&r" (tmp), "=&r" (rc) + : "r" (&v->counter) + : "memory"); + + return tmp ? true : false; +} +#define arch_atomic_dec_unless_positive arch_atomic_dec_unless_positive + +static __always_inline int +arch_atomic_dec_if_positive(atomic_t *v) +{ + int dec, tmp; + + __asm__ __volatile__ ( + RELEASE_FENCE + "1: ldex.w %0, (%2) \n" + " subi %1, %0, 1 \n" + " blz %1, 2f \n" + " stex.w %1, (%2) \n" + " bez %1, 1b \n" + FULL_FENCE + "2:\n" + : "=&r" (dec), "=&r" (tmp) + : "r" (&v->counter) + : "memory"); + + return dec - 1; +} +#define arch_atomic_dec_if_positive arch_atomic_dec_if_positive + +#define ATOMIC_OP() \ +static __always_inline \ +int arch_atomic_xchg_relaxed(atomic_t *v, int n) \ +{ \ + return __xchg_relaxed(n, &(v->counter), 4); \ +} \ +static __always_inline \ +int arch_atomic_cmpxchg_relaxed(atomic_t *v, int o, int n) \ +{ \ + return __cmpxchg_relaxed(&(v->counter), o, n, 4); \ +} \ +static __always_inline \ +int arch_atomic_cmpxchg_acquire(atomic_t *v, int o, int n) \ +{ \ + return __cmpxchg_acquire(&(v->counter), o, n, 4); \ +} \ +static __always_inline \ +int arch_atomic_cmpxchg(atomic_t *v, int o, int n) \ +{ \ + return __cmpxchg(&(v->counter), o, n, 4); \ +} + +#define ATOMIC_OPS() \ + ATOMIC_OP() + +ATOMIC_OPS() + +#define arch_atomic_xchg_relaxed arch_atomic_xchg_relaxed +#define arch_atomic_cmpxchg_relaxed arch_atomic_cmpxchg_relaxed +#define arch_atomic_cmpxchg_acquire arch_atomic_cmpxchg_acquire +#define arch_atomic_cmpxchg arch_atomic_cmpxchg + +#undef ATOMIC_OPS +#undef ATOMIC_OP + +#else +#include <asm-generic/atomic.h> +#endif + +#endif /* __ASM_CSKY_ATOMIC_H */ diff --git a/arch/csky/include/asm/barrier.h b/arch/csky/include/asm/barrier.h index f4045dd53e17..15de58b10aec 100644 --- a/arch/csky/include/asm/barrier.h +++ b/arch/csky/include/asm/barrier.h @@ -37,17 +37,21 @@ * bar.brar * bar.bwaw */ +#define FULL_FENCE ".long 0x842fc000\n" +#define ACQUIRE_FENCE ".long 0x8427c000\n" +#define RELEASE_FENCE ".long 0x842ec000\n" + #define __bar_brw() asm volatile (".long 0x842cc000\n":::"memory") #define __bar_br() asm volatile (".long 0x8424c000\n":::"memory") #define __bar_bw() asm volatile (".long 0x8428c000\n":::"memory") #define __bar_arw() asm volatile (".long 0x8423c000\n":::"memory") #define __bar_ar() asm volatile (".long 0x8421c000\n":::"memory") #define __bar_aw() asm volatile (".long 0x8422c000\n":::"memory") -#define __bar_brwarw() asm volatile (".long 0x842fc000\n":::"memory") -#define __bar_brarw() asm volatile (".long 0x8427c000\n":::"memory") +#define __bar_brwarw() asm volatile (FULL_FENCE:::"memory") +#define __bar_brarw() asm volatile (ACQUIRE_FENCE:::"memory") #define __bar_bwarw() asm volatile (".long 0x842bc000\n":::"memory") #define __bar_brwar() asm volatile (".long 0x842dc000\n":::"memory") -#define __bar_brwaw() asm volatile (".long 0x842ec000\n":::"memory") +#define __bar_brwaw() asm volatile (RELEASE_FENCE:::"memory") #define __bar_brar() asm volatile (".long 0x8425c000\n":::"memory") #define __bar_brar() asm volatile (".long 0x8425c000\n":::"memory") #define __bar_bwaw() asm volatile (".long 0x842ac000\n":::"memory") @@ -56,7 +60,6 @@ #define __smp_rmb() __bar_brar() #define __smp_wmb() __bar_bwaw() -#define ACQUIRE_FENCE ".long 0x8427c000\n" #define __smp_acquire_fence() __bar_brarw() #define __smp_release_fence() __bar_brwaw() diff --git a/arch/csky/include/asm/cmpxchg.h b/arch/csky/include/asm/cmpxchg.h index d1bef11f8dc9..5b8faccd65e4 100644 --- a/arch/csky/include/asm/cmpxchg.h +++ b/arch/csky/include/asm/cmpxchg.h @@ -64,15 +64,71 @@ extern void __bad_xchg(void); #define arch_cmpxchg_relaxed(ptr, o, n) \ (__cmpxchg_relaxed((ptr), (o), (n), sizeof(*(ptr)))) -#define arch_cmpxchg(ptr, o, n) \ +#define __cmpxchg_acquire(ptr, old, new, size) \ ({ \ + __typeof__(ptr) __ptr = (ptr); \ + __typeof__(new) __new = (new); \ + __typeof__(new) __tmp; \ + __typeof__(old) __old = (old); \ + __typeof__(*(ptr)) __ret; \ + switch (size) { \ + case 4: \ + asm volatile ( \ + "1: ldex.w %0, (%3) \n" \ + " cmpne %0, %4 \n" \ + " bt 2f \n" \ + " mov %1, %2 \n" \ + " stex.w %1, (%3) \n" \ + " bez %1, 1b \n" \ + ACQUIRE_FENCE \ + "2: \n" \ + : "=&r" (__ret), "=&r" (__tmp) \ + : "r" (__new), "r"(__ptr), "r"(__old) \ + :); \ + break; \ + default: \ + __bad_xchg(); \ + } \ + __ret; \ +}) + +#define arch_cmpxchg_acquire(ptr, o, n) \ + (__cmpxchg_acquire((ptr), (o), (n), sizeof(*(ptr)))) + +#define __cmpxchg(ptr, old, new, size) \ +({ \ + __typeof__(ptr) __ptr = (ptr); \ + __typeof__(new) __new = (new); \ + __typeof__(new) __tmp; \ + __typeof__(old) __old = (old); \ __typeof__(*(ptr)) __ret; \ - __smp_release_fence(); \ - __ret = arch_cmpxchg_relaxed(ptr, o, n); \ - __smp_acquire_fence(); \ + switch (size) { \ + case 4: \ + asm volatile ( \ + RELEASE_FENCE \ + "1: ldex.w %0, (%3) \n" \ + " cmpne %0, %4 \n" \ + " bt 2f \n" \ + " mov %1, %2 \n" \ + " stex.w %1, (%3) \n" \ + " bez %1, 1b \n" \ + FULL_FENCE \ + "2: \n" \ + : "=&r" (__ret), "=&r" (__tmp) \ + : "r" (__new), "r"(__ptr), "r"(__old) \ + :); \ + break; \ + default: \ + __bad_xchg(); \ + } \ __ret; \ }) +#define arch_cmpxchg(ptr, o, n) \ + (__cmpxchg((ptr), (o), (n), sizeof(*(ptr)))) + +#define arch_cmpxchg_local(ptr, o, n) \ + (__cmpxchg_relaxed((ptr), (o), (n), sizeof(*(ptr)))) #else #include <asm-generic/cmpxchg.h> #endif diff --git a/arch/csky/include/asm/io.h b/arch/csky/include/asm/io.h index f82654053dc0..4725bb977b0f 100644 --- a/arch/csky/include/asm/io.h +++ b/arch/csky/include/asm/io.h @@ -5,7 +5,6 @@ #include <linux/pgtable.h> #include <linux/types.h> -#include <linux/version.h> /* * I/O memory access primitives. Reads are ordered relative to any @@ -33,6 +32,17 @@ #endif /* + * String version of I/O memory access operations. + */ +extern void __memcpy_fromio(void *, const volatile void __iomem *, size_t); +extern void __memcpy_toio(volatile void __iomem *, const void *, size_t); +extern void __memset_io(volatile void __iomem *, int, size_t); + +#define memset_io(c,v,l) __memset_io((c),(v),(l)) +#define memcpy_fromio(a,c,l) __memcpy_fromio((a),(c),(l)) +#define memcpy_toio(c,a,l) __memcpy_toio((c),(a),(l)) + +/* * I/O memory mapping functions. */ #define ioremap_wc(addr, size) \ diff --git a/arch/csky/kernel/Makefile b/arch/csky/kernel/Makefile index 6c0f36010ed0..4eb41421ca5b 100644 --- a/arch/csky/kernel/Makefile +++ b/arch/csky/kernel/Makefile @@ -2,7 +2,7 @@ extra-y := head.o vmlinux.lds obj-y += entry.o atomic.o signal.o traps.o irq.o time.o vdso.o vdso/ -obj-y += power.o syscall.o syscall_table.o setup.o +obj-y += power.o syscall.o syscall_table.o setup.o io.o obj-y += process.o cpu-probe.o ptrace.o stacktrace.o obj-y += probes/ diff --git a/arch/csky/kernel/io.c b/arch/csky/kernel/io.c new file mode 100644 index 000000000000..5883f13fa2b1 --- /dev/null +++ b/arch/csky/kernel/io.c @@ -0,0 +1,91 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/export.h> +#include <linux/types.h> +#include <linux/io.h> + +/* + * Copy data from IO memory space to "real" memory space. + */ +void __memcpy_fromio(void *to, const volatile void __iomem *from, size_t count) +{ + while (count && !IS_ALIGNED((unsigned long)from, 4)) { + *(u8 *)to = __raw_readb(from); + from++; + to++; + count--; + } + + while (count >= 4) { + *(u32 *)to = __raw_readl(from); + from += 4; + to += 4; + count -= 4; + } + + while (count) { + *(u8 *)to = __raw_readb(from); + from++; + to++; + count--; + } +} +EXPORT_SYMBOL(__memcpy_fromio); + +/* + * Copy data from "real" memory space to IO memory space. + */ +void __memcpy_toio(volatile void __iomem *to, const void *from, size_t count) +{ + while (count && !IS_ALIGNED((unsigned long)to, 4)) { + __raw_writeb(*(u8 *)from, to); + from++; + to++; + count--; + } + + while (count >= 4) { + __raw_writel(*(u32 *)from, to); + from += 4; + to += 4; + count -= 4; + } + + while (count) { + __raw_writeb(*(u8 *)from, to); + from++; + to++; + count--; + } +} +EXPORT_SYMBOL(__memcpy_toio); + +/* + * "memset" on IO memory space. + */ +void __memset_io(volatile void __iomem *dst, int c, size_t count) +{ + u32 qc = (u8)c; + + qc |= qc << 8; + qc |= qc << 16; + + while (count && !IS_ALIGNED((unsigned long)dst, 4)) { + __raw_writeb(c, dst); + dst++; + count--; + } + + while (count >= 4) { + __raw_writel(qc, dst); + dst += 4; + count -= 4; + } + + while (count) { + __raw_writeb(c, dst); + dst++; + count--; + } +} +EXPORT_SYMBOL(__memset_io); diff --git a/arch/csky/kernel/module.c b/arch/csky/kernel/module.c index 6cd82d69c655..f11b3e573344 100644 --- a/arch/csky/kernel/module.c +++ b/arch/csky/kernel/module.c @@ -68,7 +68,7 @@ int apply_relocate_add(Elf32_Shdr *sechdrs, const char *strtab, *location = rel[i].r_addend + sym->st_value; break; case R_CSKY_PC32: - /* Add the value, subtract its postition */ + /* Add the value, subtract its position */ *location = rel[i].r_addend + sym->st_value - (uint32_t)location; break; diff --git a/arch/csky/kernel/probes/kprobes.c b/arch/csky/kernel/probes/kprobes.c index 42920f25e73c..34ba684d5962 100644 --- a/arch/csky/kernel/probes/kprobes.c +++ b/arch/csky/kernel/probes/kprobes.c @@ -30,7 +30,7 @@ static int __kprobes patch_text_cb(void *priv) struct csky_insn_patch *param = priv; unsigned int addr = (unsigned int)param->addr; - if (atomic_inc_return(¶m->cpu_count) == 1) { + if (atomic_inc_return(¶m->cpu_count) == num_online_cpus()) { *(u16 *) addr = cpu_to_le16(param->opcode); dcache_wb_range(addr, addr + 2); atomic_inc(¶m->cpu_count); diff --git a/arch/csky/kernel/probes/uprobes.c b/arch/csky/kernel/probes/uprobes.c index 1a9e0961b2b5..2d31a12e46cf 100644 --- a/arch/csky/kernel/probes/uprobes.c +++ b/arch/csky/kernel/probes/uprobes.c @@ -102,7 +102,7 @@ void arch_uprobe_abort_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) struct uprobe_task *utask = current->utask; /* - * Task has received a fatal signal, so reset back to probbed + * Task has received a fatal signal, so reset back to probed * address. */ instruction_pointer_set(regs, utask->vaddr); diff --git a/arch/csky/kernel/process.c b/arch/csky/kernel/process.c index 3d0ca22cd0e2..5de04707aa07 100644 --- a/arch/csky/kernel/process.c +++ b/arch/csky/kernel/process.c @@ -2,7 +2,6 @@ // Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd. #include <linux/module.h> -#include <linux/version.h> #include <linux/sched.h> #include <linux/sched/task_stack.h> #include <linux/sched/debug.h> diff --git a/arch/csky/lib/Makefile b/arch/csky/lib/Makefile index 7fbdbb2c4d12..d0ce6e2d7ab2 100644 --- a/arch/csky/lib/Makefile +++ b/arch/csky/lib/Makefile @@ -1,3 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-only lib-y := usercopy.o delay.o obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o +ifneq ($(CONFIG_HAVE_EFFICIENT_UNALIGNED_STRING_OPS), y) +lib-y += string.o +endif diff --git a/arch/csky/lib/string.c b/arch/csky/lib/string.c new file mode 100644 index 000000000000..d65626fcaeac --- /dev/null +++ b/arch/csky/lib/string.c @@ -0,0 +1,134 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * String functions optimized for hardware which doesn't + * handle unaligned memory accesses efficiently. + * + * Copyright (C) 2021 Matteo Croce + */ + +#include <linux/types.h> +#include <linux/module.h> + +/* Minimum size for a word copy to be convenient */ +#define BYTES_LONG sizeof(long) +#define WORD_MASK (BYTES_LONG - 1) +#define MIN_THRESHOLD (BYTES_LONG * 2) + +/* convenience union to avoid cast between different pointer types */ +union types { + u8 *as_u8; + unsigned long *as_ulong; + uintptr_t as_uptr; +}; + +union const_types { + const u8 *as_u8; + unsigned long *as_ulong; + uintptr_t as_uptr; +}; + +void *memcpy(void *dest, const void *src, size_t count) +{ + union const_types s = { .as_u8 = src }; + union types d = { .as_u8 = dest }; + int distance = 0; + + if (count < MIN_THRESHOLD) + goto copy_remainder; + + /* Copy a byte at time until destination is aligned. */ + for (; d.as_uptr & WORD_MASK; count--) + *d.as_u8++ = *s.as_u8++; + + distance = s.as_uptr & WORD_MASK; + + if (distance) { + unsigned long last, next; + + /* + * s is distance bytes ahead of d, and d just reached + * the alignment boundary. Move s backward to word align it + * and shift data to compensate for distance, in order to do + * word-by-word copy. + */ + s.as_u8 -= distance; + + next = s.as_ulong[0]; + for (; count >= BYTES_LONG; count -= BYTES_LONG) { + last = next; + next = s.as_ulong[1]; + + d.as_ulong[0] = last >> (distance * 8) | + next << ((BYTES_LONG - distance) * 8); + + d.as_ulong++; + s.as_ulong++; + } + + /* Restore s with the original offset. */ + s.as_u8 += distance; + } else { + /* + * If the source and dest lower bits are the same, do a simple + * 32/64 bit wide copy. + */ + for (; count >= BYTES_LONG; count -= BYTES_LONG) + *d.as_ulong++ = *s.as_ulong++; + } + +copy_remainder: + while (count--) + *d.as_u8++ = *s.as_u8++; + + return dest; +} +EXPORT_SYMBOL(memcpy); + +/* + * Simply check if the buffer overlaps an call memcpy() in case, + * otherwise do a simple one byte at time backward copy. + */ +void *memmove(void *dest, const void *src, size_t count) +{ + if (dest < src || src + count <= dest) + return memcpy(dest, src, count); + + if (dest > src) { + const char *s = src + count; + char *tmp = dest + count; + + while (count--) + *--tmp = *--s; + } + return dest; +} +EXPORT_SYMBOL(memmove); + +void *memset(void *s, int c, size_t count) +{ + union types dest = { .as_u8 = s }; + + if (count >= MIN_THRESHOLD) { + unsigned long cu = (unsigned long)c; + + /* Compose an ulong with 'c' repeated 4/8 times */ + cu |= cu << 8; + cu |= cu << 16; + /* Suppress warning on 32 bit machines */ + cu |= (cu << 16) << 16; + + for (; count && dest.as_uptr & WORD_MASK; count--) + *dest.as_u8++ = c; + + /* Copy using the largest size allowed */ + for (; count >= BYTES_LONG; count -= BYTES_LONG) + *dest.as_ulong++ = cu; + } + + /* copy the remainder */ + while (count--) + *dest.as_u8++ = c; + + return s; +} +EXPORT_SYMBOL(memset); diff --git a/arch/csky/mm/dma-mapping.c b/arch/csky/mm/dma-mapping.c index c3a775a7e8f9..82447029feb4 100644 --- a/arch/csky/mm/dma-mapping.c +++ b/arch/csky/mm/dma-mapping.c @@ -9,7 +9,6 @@ #include <linux/mm.h> #include <linux/scatterlist.h> #include <linux/types.h> -#include <linux/version.h> #include <asm/cache.h> static inline void cache_op(phys_addr_t paddr, size_t size, diff --git a/arch/ia64/include/asm/timex.h b/arch/ia64/include/asm/timex.h index 869a3ac6bf23..7ccc077a60be 100644 --- a/arch/ia64/include/asm/timex.h +++ b/arch/ia64/include/asm/timex.h @@ -39,6 +39,7 @@ get_cycles (void) ret = ia64_getreg(_IA64_REG_AR_ITC); return ret; } +#define get_cycles get_cycles extern void ia64_cpu_local_tick (void); extern unsigned long long ia64_native_sched_clock (void); diff --git a/arch/m68k/Kbuild b/arch/m68k/Kbuild index 18abb35c26a1..7762af9f6def 100644 --- a/arch/m68k/Kbuild +++ b/arch/m68k/Kbuild @@ -17,3 +17,4 @@ obj-$(CONFIG_M68060) += ifpsp060/ obj-$(CONFIG_M68KFPU_EMU) += math-emu/ obj-$(CONFIG_M68000) += 68000/ obj-$(CONFIG_COLDFIRE) += coldfire/ +obj-$(CONFIG_VIRT) += virt/ diff --git a/arch/m68k/Kconfig.cpu b/arch/m68k/Kconfig.cpu index 16ea9a67723c..3d5da25c73b5 100644 --- a/arch/m68k/Kconfig.cpu +++ b/arch/m68k/Kconfig.cpu @@ -327,7 +327,7 @@ comment "Processor Specific Options" config M68KFPU_EMU bool "Math emulation support" - depends on MMU + depends on M68KCLASSIC && FPU help At some point in the future, this will cause floating-point math instructions to be emulated by the kernel on machines that lack a diff --git a/arch/m68k/Kconfig.machine b/arch/m68k/Kconfig.machine index eeab4f3e6c19..188a8f8a0104 100644 --- a/arch/m68k/Kconfig.machine +++ b/arch/m68k/Kconfig.machine @@ -149,6 +149,23 @@ config SUN3 If you don't want to compile a kernel exclusively for a Sun 3, say N. +config VIRT + bool "Virtual M68k Machine support" + depends on MMU + select GENERIC_CLOCKEVENTS + select GOLDFISH + select GOLDFISH_TIMER + select GOLDFISH_TTY + select M68040 + select MMU_MOTOROLA if MMU + select RTC_CLASS + select RTC_DRV_GOLDFISH + select TTY + select VIRTIO_MMIO + help + This options enable a pure virtual machine based on m68k, + VIRTIO MMIO devices and GOLDFISH interfaces (TTY, RTC, PIC) + config PILOT bool diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig index 114aaa3f955a..c181030218bf 100644 --- a/arch/m68k/configs/amiga_defconfig +++ b/arch/m68k/configs/amiga_defconfig @@ -42,7 +42,6 @@ CONFIG_MQ_IOSCHED_DEADLINE=m CONFIG_MQ_IOSCHED_KYBER=m CONFIG_IOSCHED_BFQ=m # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set -CONFIG_BINFMT_AOUT=m CONFIG_BINFMT_MISC=m # CONFIG_COMPACTION is not set CONFIG_ZPOOL=m @@ -581,6 +580,7 @@ CONFIG_CRYPTO_MD4=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD160=m CONFIG_CRYPTO_SHA3=m +CONFIG_CRYPTO_SM3=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_AES=y CONFIG_CRYPTO_AES_TI=m @@ -613,7 +613,6 @@ CONFIG_CRYPTO_USER_API_AEAD=m # CONFIG_CRYPTO_HW is not set CONFIG_PRIME_NUMBERS=m CONFIG_CRC32_SELFTEST=m -CONFIG_CRC64=m CONFIG_XZ_DEC_TEST=m CONFIG_GLOB_SELFTEST=m # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set @@ -638,7 +637,6 @@ CONFIG_TEST_SCANF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m CONFIG_TEST_XARRAY=m -CONFIG_TEST_OVERFLOW=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_SIPHASH=m CONFIG_TEST_IDA=m @@ -659,6 +657,5 @@ CONFIG_TEST_UDELAY=m CONFIG_TEST_STATIC_KEYS=m CONFIG_TEST_KMOD=m CONFIG_TEST_MEMCAT_P=m -CONFIG_TEST_STACKINIT=m CONFIG_TEST_MEMINIT=m CONFIG_TEST_FREE_PAGES=m diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig index 30b9d932b930..40755648fb6c 100644 --- a/arch/m68k/configs/apollo_defconfig +++ b/arch/m68k/configs/apollo_defconfig @@ -38,7 +38,6 @@ CONFIG_MQ_IOSCHED_DEADLINE=m CONFIG_MQ_IOSCHED_KYBER=m CONFIG_IOSCHED_BFQ=m # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set -CONFIG_BINFMT_AOUT=m CONFIG_BINFMT_MISC=m # CONFIG_COMPACTION is not set CONFIG_ZPOOL=m @@ -538,6 +537,7 @@ CONFIG_CRYPTO_MD4=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD160=m CONFIG_CRYPTO_SHA3=m +CONFIG_CRYPTO_SM3=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_AES=y CONFIG_CRYPTO_AES_TI=m @@ -570,7 +570,6 @@ CONFIG_CRYPTO_USER_API_AEAD=m # CONFIG_CRYPTO_HW is not set CONFIG_PRIME_NUMBERS=m CONFIG_CRC32_SELFTEST=m -CONFIG_CRC64=m CONFIG_XZ_DEC_TEST=m # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set CONFIG_MAGIC_SYSRQ=y @@ -594,7 +593,6 @@ CONFIG_TEST_SCANF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m CONFIG_TEST_XARRAY=m -CONFIG_TEST_OVERFLOW=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_SIPHASH=m CONFIG_TEST_IDA=m @@ -615,6 +613,5 @@ CONFIG_TEST_UDELAY=m CONFIG_TEST_STATIC_KEYS=m CONFIG_TEST_KMOD=m CONFIG_TEST_MEMCAT_P=m -CONFIG_TEST_STACKINIT=m CONFIG_TEST_MEMINIT=m CONFIG_TEST_FREE_PAGES=m diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig index 51ff3180e69d..be0d9155fc5b 100644 --- a/arch/m68k/configs/atari_defconfig +++ b/arch/m68k/configs/atari_defconfig @@ -45,7 +45,6 @@ CONFIG_MQ_IOSCHED_DEADLINE=m CONFIG_MQ_IOSCHED_KYBER=m CONFIG_IOSCHED_BFQ=m # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set -CONFIG_BINFMT_AOUT=m CONFIG_BINFMT_MISC=m # CONFIG_COMPACTION is not set CONFIG_ZPOOL=m @@ -558,6 +557,7 @@ CONFIG_CRYPTO_MD4=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD160=m CONFIG_CRYPTO_SHA3=m +CONFIG_CRYPTO_SM3=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_AES=y CONFIG_CRYPTO_AES_TI=m @@ -590,7 +590,6 @@ CONFIG_CRYPTO_USER_API_AEAD=m # CONFIG_CRYPTO_HW is not set CONFIG_PRIME_NUMBERS=m CONFIG_CRC32_SELFTEST=m -CONFIG_CRC64=m CONFIG_XZ_DEC_TEST=m CONFIG_GLOB_SELFTEST=m # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set @@ -615,7 +614,6 @@ CONFIG_TEST_SCANF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m CONFIG_TEST_XARRAY=m -CONFIG_TEST_OVERFLOW=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_SIPHASH=m CONFIG_TEST_IDA=m @@ -636,6 +634,5 @@ CONFIG_TEST_UDELAY=m CONFIG_TEST_STATIC_KEYS=m CONFIG_TEST_KMOD=m CONFIG_TEST_MEMCAT_P=m -CONFIG_TEST_STACKINIT=m CONFIG_TEST_MEMINIT=m CONFIG_TEST_FREE_PAGES=m diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig index 7d95ca4366e4..9af0e2d0d153 100644 --- a/arch/m68k/configs/bvme6000_defconfig +++ b/arch/m68k/configs/bvme6000_defconfig @@ -35,7 +35,6 @@ CONFIG_MQ_IOSCHED_DEADLINE=m CONFIG_MQ_IOSCHED_KYBER=m CONFIG_IOSCHED_BFQ=m # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set -CONFIG_BINFMT_AOUT=m CONFIG_BINFMT_MISC=m # CONFIG_COMPACTION is not set CONFIG_ZPOOL=m @@ -530,6 +529,7 @@ CONFIG_CRYPTO_MD4=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD160=m CONFIG_CRYPTO_SHA3=m +CONFIG_CRYPTO_SM3=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_AES=y CONFIG_CRYPTO_AES_TI=m @@ -562,7 +562,6 @@ CONFIG_CRYPTO_USER_API_AEAD=m # CONFIG_CRYPTO_HW is not set CONFIG_PRIME_NUMBERS=m CONFIG_CRC32_SELFTEST=m -CONFIG_CRC64=m CONFIG_XZ_DEC_TEST=m # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set CONFIG_MAGIC_SYSRQ=y @@ -586,7 +585,6 @@ CONFIG_TEST_SCANF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m CONFIG_TEST_XARRAY=m -CONFIG_TEST_OVERFLOW=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_SIPHASH=m CONFIG_TEST_IDA=m @@ -607,6 +605,5 @@ CONFIG_TEST_UDELAY=m CONFIG_TEST_STATIC_KEYS=m CONFIG_TEST_KMOD=m CONFIG_TEST_MEMCAT_P=m -CONFIG_TEST_STACKINIT=m CONFIG_TEST_MEMINIT=m CONFIG_TEST_FREE_PAGES=m diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig index e306e3813607..49341d66feb6 100644 --- a/arch/m68k/configs/hp300_defconfig +++ b/arch/m68k/configs/hp300_defconfig @@ -37,7 +37,6 @@ CONFIG_MQ_IOSCHED_DEADLINE=m CONFIG_MQ_IOSCHED_KYBER=m CONFIG_IOSCHED_BFQ=m # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set -CONFIG_BINFMT_AOUT=m CONFIG_BINFMT_MISC=m # CONFIG_COMPACTION is not set CONFIG_ZPOOL=m @@ -540,6 +539,7 @@ CONFIG_CRYPTO_MD4=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD160=m CONFIG_CRYPTO_SHA3=m +CONFIG_CRYPTO_SM3=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_AES=y CONFIG_CRYPTO_AES_TI=m @@ -572,7 +572,6 @@ CONFIG_CRYPTO_USER_API_AEAD=m # CONFIG_CRYPTO_HW is not set CONFIG_PRIME_NUMBERS=m CONFIG_CRC32_SELFTEST=m -CONFIG_CRC64=m CONFIG_XZ_DEC_TEST=m # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set CONFIG_MAGIC_SYSRQ=y @@ -596,7 +595,6 @@ CONFIG_TEST_SCANF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m CONFIG_TEST_XARRAY=m -CONFIG_TEST_OVERFLOW=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_SIPHASH=m CONFIG_TEST_IDA=m @@ -617,6 +615,5 @@ CONFIG_TEST_UDELAY=m CONFIG_TEST_STATIC_KEYS=m CONFIG_TEST_KMOD=m CONFIG_TEST_MEMCAT_P=m -CONFIG_TEST_STACKINIT=m CONFIG_TEST_MEMINIT=m CONFIG_TEST_FREE_PAGES=m diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig index 41316cf02441..92b33d5ffab1 100644 --- a/arch/m68k/configs/mac_defconfig +++ b/arch/m68k/configs/mac_defconfig @@ -36,7 +36,6 @@ CONFIG_MQ_IOSCHED_DEADLINE=m CONFIG_MQ_IOSCHED_KYBER=m CONFIG_IOSCHED_BFQ=m # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set -CONFIG_BINFMT_AOUT=m CONFIG_BINFMT_MISC=m # CONFIG_COMPACTION is not set CONFIG_ZPOOL=m @@ -560,6 +559,7 @@ CONFIG_CRYPTO_MD4=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD160=m CONFIG_CRYPTO_SHA3=m +CONFIG_CRYPTO_SM3=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_AES=y CONFIG_CRYPTO_AES_TI=m @@ -592,7 +592,6 @@ CONFIG_CRYPTO_USER_API_AEAD=m # CONFIG_CRYPTO_HW is not set CONFIG_PRIME_NUMBERS=m CONFIG_CRC32_SELFTEST=m -CONFIG_CRC64=m CONFIG_XZ_DEC_TEST=m CONFIG_GLOB_SELFTEST=m # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set @@ -617,7 +616,6 @@ CONFIG_TEST_SCANF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m CONFIG_TEST_XARRAY=m -CONFIG_TEST_OVERFLOW=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_SIPHASH=m CONFIG_TEST_IDA=m @@ -638,6 +636,5 @@ CONFIG_TEST_UDELAY=m CONFIG_TEST_STATIC_KEYS=m CONFIG_TEST_KMOD=m CONFIG_TEST_MEMCAT_P=m -CONFIG_TEST_STACKINIT=m CONFIG_TEST_MEMINIT=m CONFIG_TEST_FREE_PAGES=m diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig index 2fc3f0df6d43..6aaa947bc849 100644 --- a/arch/m68k/configs/multi_defconfig +++ b/arch/m68k/configs/multi_defconfig @@ -56,7 +56,6 @@ CONFIG_MQ_IOSCHED_DEADLINE=m CONFIG_MQ_IOSCHED_KYBER=m CONFIG_IOSCHED_BFQ=m # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set -CONFIG_BINFMT_AOUT=m CONFIG_BINFMT_MISC=m # CONFIG_COMPACTION is not set CONFIG_ZPOOL=m @@ -646,6 +645,7 @@ CONFIG_CRYPTO_MD4=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD160=m CONFIG_CRYPTO_SHA3=m +CONFIG_CRYPTO_SM3=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_AES=y CONFIG_CRYPTO_AES_TI=m @@ -678,7 +678,6 @@ CONFIG_CRYPTO_USER_API_AEAD=m # CONFIG_CRYPTO_HW is not set CONFIG_PRIME_NUMBERS=m CONFIG_CRC32_SELFTEST=m -CONFIG_CRC64=m CONFIG_XZ_DEC_TEST=m CONFIG_GLOB_SELFTEST=m # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set @@ -703,7 +702,6 @@ CONFIG_TEST_SCANF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m CONFIG_TEST_XARRAY=m -CONFIG_TEST_OVERFLOW=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_SIPHASH=m CONFIG_TEST_IDA=m @@ -724,6 +722,5 @@ CONFIG_TEST_UDELAY=m CONFIG_TEST_STATIC_KEYS=m CONFIG_TEST_KMOD=m CONFIG_TEST_MEMCAT_P=m -CONFIG_TEST_STACKINIT=m CONFIG_TEST_MEMINIT=m CONFIG_TEST_FREE_PAGES=m diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig index 9603f4396469..b62d65e59938 100644 --- a/arch/m68k/configs/mvme147_defconfig +++ b/arch/m68k/configs/mvme147_defconfig @@ -34,7 +34,6 @@ CONFIG_MQ_IOSCHED_DEADLINE=m CONFIG_MQ_IOSCHED_KYBER=m CONFIG_IOSCHED_BFQ=m # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set -CONFIG_BINFMT_AOUT=m CONFIG_BINFMT_MISC=m # CONFIG_COMPACTION is not set CONFIG_ZPOOL=m @@ -529,6 +528,7 @@ CONFIG_CRYPTO_MD4=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD160=m CONFIG_CRYPTO_SHA3=m +CONFIG_CRYPTO_SM3=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_AES=y CONFIG_CRYPTO_AES_TI=m @@ -561,7 +561,6 @@ CONFIG_CRYPTO_USER_API_AEAD=m # CONFIG_CRYPTO_HW is not set CONFIG_PRIME_NUMBERS=m CONFIG_CRC32_SELFTEST=m -CONFIG_CRC64=m CONFIG_XZ_DEC_TEST=m # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set CONFIG_MAGIC_SYSRQ=y @@ -585,7 +584,6 @@ CONFIG_TEST_SCANF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m CONFIG_TEST_XARRAY=m -CONFIG_TEST_OVERFLOW=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_SIPHASH=m CONFIG_TEST_IDA=m @@ -606,6 +604,5 @@ CONFIG_TEST_UDELAY=m CONFIG_TEST_STATIC_KEYS=m CONFIG_TEST_KMOD=m CONFIG_TEST_MEMCAT_P=m -CONFIG_TEST_STACKINIT=m CONFIG_TEST_MEMINIT=m CONFIG_TEST_FREE_PAGES=m diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig index c9cabd3344df..8ecf261487d4 100644 --- a/arch/m68k/configs/mvme16x_defconfig +++ b/arch/m68k/configs/mvme16x_defconfig @@ -35,7 +35,6 @@ CONFIG_MQ_IOSCHED_DEADLINE=m CONFIG_MQ_IOSCHED_KYBER=m CONFIG_IOSCHED_BFQ=m # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set -CONFIG_BINFMT_AOUT=m CONFIG_BINFMT_MISC=m # CONFIG_COMPACTION is not set CONFIG_ZPOOL=m @@ -530,6 +529,7 @@ CONFIG_CRYPTO_MD4=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD160=m CONFIG_CRYPTO_SHA3=m +CONFIG_CRYPTO_SM3=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_AES=y CONFIG_CRYPTO_AES_TI=m @@ -562,7 +562,6 @@ CONFIG_CRYPTO_USER_API_AEAD=m # CONFIG_CRYPTO_HW is not set CONFIG_PRIME_NUMBERS=m CONFIG_CRC32_SELFTEST=m -CONFIG_CRC64=m CONFIG_XZ_DEC_TEST=m # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set CONFIG_MAGIC_SYSRQ=y @@ -586,7 +585,6 @@ CONFIG_TEST_SCANF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m CONFIG_TEST_XARRAY=m -CONFIG_TEST_OVERFLOW=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_SIPHASH=m CONFIG_TEST_IDA=m @@ -607,6 +605,5 @@ CONFIG_TEST_UDELAY=m CONFIG_TEST_STATIC_KEYS=m CONFIG_TEST_KMOD=m CONFIG_TEST_MEMCAT_P=m -CONFIG_TEST_STACKINIT=m CONFIG_TEST_MEMINIT=m CONFIG_TEST_FREE_PAGES=m diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig index 5f994bf44fb8..7540d908897b 100644 --- a/arch/m68k/configs/q40_defconfig +++ b/arch/m68k/configs/q40_defconfig @@ -36,7 +36,6 @@ CONFIG_MQ_IOSCHED_DEADLINE=m CONFIG_MQ_IOSCHED_KYBER=m CONFIG_IOSCHED_BFQ=m # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set -CONFIG_BINFMT_AOUT=m CONFIG_BINFMT_MISC=m # CONFIG_COMPACTION is not set CONFIG_ZPOOL=m @@ -547,6 +546,7 @@ CONFIG_CRYPTO_MD4=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD160=m CONFIG_CRYPTO_SHA3=m +CONFIG_CRYPTO_SM3=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_AES=y CONFIG_CRYPTO_AES_TI=m @@ -579,7 +579,6 @@ CONFIG_CRYPTO_USER_API_AEAD=m # CONFIG_CRYPTO_HW is not set CONFIG_PRIME_NUMBERS=m CONFIG_CRC32_SELFTEST=m -CONFIG_CRC64=m CONFIG_XZ_DEC_TEST=m CONFIG_GLOB_SELFTEST=m # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set @@ -604,7 +603,6 @@ CONFIG_TEST_SCANF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m CONFIG_TEST_XARRAY=m -CONFIG_TEST_OVERFLOW=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_SIPHASH=m CONFIG_TEST_IDA=m @@ -625,6 +623,5 @@ CONFIG_TEST_UDELAY=m CONFIG_TEST_STATIC_KEYS=m CONFIG_TEST_KMOD=m CONFIG_TEST_MEMCAT_P=m -CONFIG_TEST_STACKINIT=m CONFIG_TEST_MEMINIT=m CONFIG_TEST_FREE_PAGES=m diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig index 183e33f7d4a0..832b45944617 100644 --- a/arch/m68k/configs/sun3_defconfig +++ b/arch/m68k/configs/sun3_defconfig @@ -32,7 +32,6 @@ CONFIG_MQ_IOSCHED_DEADLINE=m CONFIG_MQ_IOSCHED_KYBER=m CONFIG_IOSCHED_BFQ=m # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set -CONFIG_BINFMT_AOUT=m CONFIG_BINFMT_MISC=m # CONFIG_COMPACTION is not set CONFIG_ZPOOL=m @@ -529,6 +528,7 @@ CONFIG_CRYPTO_MD4=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD160=m CONFIG_CRYPTO_SHA3=m +CONFIG_CRYPTO_SM3=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_AES=y CONFIG_CRYPTO_AES_TI=m @@ -561,7 +561,6 @@ CONFIG_CRYPTO_USER_API_AEAD=m # CONFIG_CRYPTO_HW is not set CONFIG_PRIME_NUMBERS=m CONFIG_CRC32_SELFTEST=m -CONFIG_CRC64=m CONFIG_XZ_DEC_TEST=m # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set CONFIG_MAGIC_SYSRQ=y @@ -584,7 +583,6 @@ CONFIG_TEST_SCANF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m CONFIG_TEST_XARRAY=m -CONFIG_TEST_OVERFLOW=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_SIPHASH=m CONFIG_TEST_IDA=m @@ -605,6 +603,5 @@ CONFIG_TEST_UDELAY=m CONFIG_TEST_STATIC_KEYS=m CONFIG_TEST_KMOD=m CONFIG_TEST_MEMCAT_P=m -CONFIG_TEST_STACKINIT=m CONFIG_TEST_MEMINIT=m CONFIG_TEST_FREE_PAGES=m diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig index 8214263b9ab8..9171b687e565 100644 --- a/arch/m68k/configs/sun3x_defconfig +++ b/arch/m68k/configs/sun3x_defconfig @@ -32,7 +32,6 @@ CONFIG_MQ_IOSCHED_DEADLINE=m CONFIG_MQ_IOSCHED_KYBER=m CONFIG_IOSCHED_BFQ=m # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set -CONFIG_BINFMT_AOUT=m CONFIG_BINFMT_MISC=m # CONFIG_COMPACTION is not set CONFIG_ZPOOL=m @@ -528,6 +527,7 @@ CONFIG_CRYPTO_MD4=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD160=m CONFIG_CRYPTO_SHA3=m +CONFIG_CRYPTO_SM3=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_AES=y CONFIG_CRYPTO_AES_TI=m @@ -560,7 +560,6 @@ CONFIG_CRYPTO_USER_API_AEAD=m # CONFIG_CRYPTO_HW is not set CONFIG_PRIME_NUMBERS=m CONFIG_CRC32_SELFTEST=m -CONFIG_CRC64=m CONFIG_XZ_DEC_TEST=m # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set CONFIG_MAGIC_SYSRQ=y @@ -584,7 +583,6 @@ CONFIG_TEST_SCANF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m CONFIG_TEST_XARRAY=m -CONFIG_TEST_OVERFLOW=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_SIPHASH=m CONFIG_TEST_IDA=m @@ -605,6 +603,5 @@ CONFIG_TEST_UDELAY=m CONFIG_TEST_STATIC_KEYS=m CONFIG_TEST_KMOD=m CONFIG_TEST_MEMCAT_P=m -CONFIG_TEST_STACKINIT=m CONFIG_TEST_MEMINIT=m CONFIG_TEST_FREE_PAGES=m diff --git a/arch/m68k/configs/virt_defconfig b/arch/m68k/configs/virt_defconfig new file mode 100644 index 000000000000..8059bd618370 --- /dev/null +++ b/arch/m68k/configs/virt_defconfig @@ -0,0 +1,68 @@ +CONFIG_LOCALVERSION="-virt" +CONFIG_SYSVIPC=y +CONFIG_CGROUPS=y +CONFIG_BLK_CGROUP=y +CONFIG_CGROUP_SCHED=y +CONFIG_CGROUP_PIDS=y +CONFIG_CGROUP_RDMA=y +CONFIG_CGROUP_FREEZER=y +CONFIG_CGROUP_DEVICE=y +CONFIG_CGROUP_CPUACCT=y +CONFIG_VIRT=y +CONFIG_PROC_HARDWARE=y +CONFIG_PARTITION_ADVANCED=y +CONFIG_AMIGA_PARTITION=y +CONFIG_ATARI_PARTITION=y +CONFIG_MAC_PARTITION=y +CONFIG_BSD_DISKLABEL=y +CONFIG_MINIX_SUBPARTITION=y +CONFIG_SOLARIS_X86_PARTITION=y +CONFIG_UNIXWARE_DISKLABEL=y +CONFIG_LDM_PARTITION=y +CONFIG_LDM_DEBUG=y +CONFIG_SUN_PARTITION=y +CONFIG_SYSV68_PARTITION=y +CONFIG_NET=y +CONFIG_PACKET=y +CONFIG_UNIX=y +CONFIG_INET=y +CONFIG_IP_PNP=y +CONFIG_IP_PNP_DHCP=y +CONFIG_IP_PNP_BOOTP=y +CONFIG_CGROUP_NET_PRIO=y +CONFIG_CGROUP_NET_CLASSID=y +CONFIG_NET_9P=y +CONFIG_NET_9P_VIRTIO=y +CONFIG_DEVTMPFS=y +CONFIG_BLK_DEV_LOOP=y +CONFIG_BLK_DEV_RAM=y +CONFIG_VIRTIO_BLK=y +CONFIG_SCSI=y +CONFIG_BLK_DEV_SR=y +CONFIG_SCSI_VIRTIO=y +CONFIG_NETDEVICES=y +CONFIG_VIRTIO_NET=y +CONFIG_INPUT_MOUSEDEV=y +CONFIG_INPUT_EVDEV=y +CONFIG_VIRTIO_CONSOLE=y +CONFIG_HW_RANDOM_VIRTIO=y +CONFIG_DRM=y +CONFIG_DRM_VIRTIO_GPU=y +CONFIG_FB=y +CONFIG_SOUND=y +CONFIG_SND=y +CONFIG_SND_VIRTIO=y +CONFIG_VIRT_DRIVERS=y +CONFIG_VIRTIO_INPUT=y +CONFIG_EXT4_FS=y +CONFIG_AUTOFS_FS=y +CONFIG_ISO9660_FS=y +CONFIG_JOLIET=y +CONFIG_ZISOFS=y +CONFIG_UDF_FS=y +CONFIG_TMPFS=y +CONFIG_TMPFS_POSIX_ACL=y +CONFIG_9P_FS=y +CONFIG_9P_FS_POSIX_ACL=y +CONFIG_9P_FS_SECURITY=y +CONFIG_EARLY_PRINTK=y diff --git a/arch/m68k/include/asm/config.h b/arch/m68k/include/asm/config.h index e73ffa23c4f5..9bb888ab5009 100644 --- a/arch/m68k/include/asm/config.h +++ b/arch/m68k/include/asm/config.h @@ -17,6 +17,7 @@ extern int mac_parse_bootinfo(const struct bi_record *record); extern int mvme147_parse_bootinfo(const struct bi_record *record); extern int mvme16x_parse_bootinfo(const struct bi_record *record); extern int q40_parse_bootinfo(const struct bi_record *record); +extern int virt_parse_bootinfo(const struct bi_record *record); extern void config_amiga(void); extern void config_apollo(void); @@ -29,5 +30,6 @@ extern void config_mvme16x(void); extern void config_q40(void); extern void config_sun3(void); extern void config_sun3x(void); +extern void config_virt(void); #endif /* _M68K_CONFIG_H */ diff --git a/arch/m68k/include/asm/io.h b/arch/m68k/include/asm/io.h index aabe6420ead2..aaeabc65e63c 100644 --- a/arch/m68k/include/asm/io.h +++ b/arch/m68k/include/asm/io.h @@ -8,6 +8,9 @@ #include <asm/io_mm.h> #endif +#define gf_ioread32 ioread32be +#define gf_iowrite32 iowrite32be + #include <asm-generic/io.h> #endif /* _M68K_IO_H */ diff --git a/arch/m68k/include/asm/irq.h b/arch/m68k/include/asm/irq.h index 91dd493791d7..7829e955ca04 100644 --- a/arch/m68k/include/asm/irq.h +++ b/arch/m68k/include/asm/irq.h @@ -12,7 +12,8 @@ */ #if defined(CONFIG_COLDFIRE) #define NR_IRQS 256 -#elif defined(CONFIG_VME) || defined(CONFIG_SUN3) || defined(CONFIG_SUN3X) +#elif defined(CONFIG_VME) || defined(CONFIG_SUN3) || \ + defined(CONFIG_SUN3X) || defined(CONFIG_VIRT) #define NR_IRQS 200 #elif defined(CONFIG_ATARI) #define NR_IRQS 141 diff --git a/arch/m68k/include/asm/pgtable_mm.h b/arch/m68k/include/asm/pgtable_mm.h index 143ba7de9bda..9b4e2fe2ac82 100644 --- a/arch/m68k/include/asm/pgtable_mm.h +++ b/arch/m68k/include/asm/pgtable_mm.h @@ -80,6 +80,9 @@ #elif defined(CONFIG_COLDFIRE) #define KMAP_START 0xe0000000 #define KMAP_END 0xf0000000 +#elif defined(CONFIG_VIRT) +#define KMAP_START 0xdf000000 +#define KMAP_END 0xff000000 #else #define KMAP_START 0xd0000000 #define KMAP_END 0xf0000000 @@ -92,6 +95,10 @@ extern unsigned long m68k_vmalloc_end; #elif defined(CONFIG_COLDFIRE) #define VMALLOC_START 0xd0000000 #define VMALLOC_END 0xe0000000 +#elif defined(CONFIG_VIRT) +#define VMALLOC_OFFSET PAGE_SIZE +#define VMALLOC_START (((unsigned long) high_memory + VMALLOC_OFFSET) & ~(VMALLOC_OFFSET-1)) +#define VMALLOC_END KMAP_START #else /* Just any arbitrary offset to the start of the vmalloc VM area: the * current 8MB value just means that there will be a 8MB "hole" after the diff --git a/arch/m68k/include/asm/raw_io.h b/arch/m68k/include/asm/raw_io.h index 80eb2396d01e..3ba40bc1dfaa 100644 --- a/arch/m68k/include/asm/raw_io.h +++ b/arch/m68k/include/asm/raw_io.h @@ -80,14 +80,14 @@ ({ u16 __v = le16_to_cpu(*(__force volatile u16 *) (addr)); __v; }) #define rom_out_8(addr, b) \ - ({u8 __maybe_unused __w, __v = (b); u32 _addr = ((u32) (addr)); \ + (void)({u8 __maybe_unused __w, __v = (b); u32 _addr = ((u32) (addr)); \ __w = ((*(__force volatile u8 *) ((_addr | 0x10000) + (__v<<1)))); }) #define rom_out_be16(addr, w) \ - ({u16 __maybe_unused __w, __v = (w); u32 _addr = ((u32) (addr)); \ + (void)({u16 __maybe_unused __w, __v = (w); u32 _addr = ((u32) (addr)); \ __w = ((*(__force volatile u16 *) ((_addr & 0xFFFF0000UL) + ((__v & 0xFF)<<1)))); \ __w = ((*(__force volatile u16 *) ((_addr | 0x10000) + ((__v >> 8)<<1)))); }) #define rom_out_le16(addr, w) \ - ({u16 __maybe_unused __w, __v = (w); u32 _addr = ((u32) (addr)); \ + (void)({u16 __maybe_unused __w, __v = (w); u32 _addr = ((u32) (addr)); \ __w = ((*(__force volatile u16 *) ((_addr & 0xFFFF0000UL) + ((__v >> 8)<<1)))); \ __w = ((*(__force volatile u16 *) ((_addr | 0x10000) + ((__v & 0xFF)<<1)))); }) diff --git a/arch/m68k/include/asm/setup.h b/arch/m68k/include/asm/setup.h index 8f2023f8c1c4..2c99477aaf89 100644 --- a/arch/m68k/include/asm/setup.h +++ b/arch/m68k/include/asm/setup.h @@ -37,7 +37,8 @@ extern unsigned long m68k_machtype; #elif defined(CONFIG_ATARI) || defined(CONFIG_MAC) || defined(CONFIG_APOLLO) \ || defined(CONFIG_MVME16x) || defined(CONFIG_BVME6000) \ || defined(CONFIG_HP300) || defined(CONFIG_Q40) \ - || defined(CONFIG_SUN3X) || defined(CONFIG_MVME147) + || defined(CONFIG_SUN3X) || defined(CONFIG_MVME147) \ + || defined(CONFIG_VIRT) # define MACH_IS_AMIGA (m68k_machtype == MACH_AMIGA) #else # define MACH_AMIGA_ONLY @@ -50,7 +51,8 @@ extern unsigned long m68k_machtype; #elif defined(CONFIG_AMIGA) || defined(CONFIG_MAC) || defined(CONFIG_APOLLO) \ || defined(CONFIG_MVME16x) || defined(CONFIG_BVME6000) \ || defined(CONFIG_HP300) || defined(CONFIG_Q40) \ - || defined(CONFIG_SUN3X) || defined(CONFIG_MVME147) + || defined(CONFIG_SUN3X) || defined(CONFIG_MVME147) \ + || defined(CONFIG_VIRT) # define MACH_IS_ATARI (m68k_machtype == MACH_ATARI) #else # define MACH_ATARI_ONLY @@ -63,7 +65,8 @@ extern unsigned long m68k_machtype; #elif defined(CONFIG_AMIGA) || defined(CONFIG_ATARI) || defined(CONFIG_APOLLO) \ || defined(CONFIG_MVME16x) || defined(CONFIG_BVME6000) \ || defined(CONFIG_HP300) || defined(CONFIG_Q40) \ - || defined(CONFIG_SUN3X) || defined(CONFIG_MVME147) + || defined(CONFIG_SUN3X) || defined(CONFIG_MVME147) \ + || defined(CONFIG_VIRT) # define MACH_IS_MAC (m68k_machtype == MACH_MAC) #else # define MACH_MAC_ONLY @@ -84,7 +87,8 @@ extern unsigned long m68k_machtype; #elif defined(CONFIG_AMIGA) || defined(CONFIG_MAC) || defined(CONFIG_ATARI) \ || defined(CONFIG_MVME16x) || defined(CONFIG_BVME6000) \ || defined(CONFIG_HP300) || defined(CONFIG_Q40) \ - || defined(CONFIG_SUN3X) || defined(CONFIG_MVME147) + || defined(CONFIG_SUN3X) || defined(CONFIG_MVME147) \ + || defined(CONFIG_VIRT) # define MACH_IS_APOLLO (m68k_machtype == MACH_APOLLO) #else # define MACH_APOLLO_ONLY @@ -97,7 +101,8 @@ extern unsigned long m68k_machtype; #elif defined(CONFIG_AMIGA) || defined(CONFIG_MAC) || defined(CONFIG_ATARI) \ || defined(CONFIG_APOLLO) || defined(CONFIG_BVME6000) \ || defined(CONFIG_HP300) || defined(CONFIG_Q40) \ - || defined(CONFIG_SUN3X) || defined(CONFIG_MVME16x) + || defined(CONFIG_SUN3X) || defined(CONFIG_MVME16x) \ + || defined(CONFIG_VIRT) # define MACH_IS_MVME147 (m68k_machtype == MACH_MVME147) #else # define MACH_MVME147_ONLY @@ -110,7 +115,8 @@ extern unsigned long m68k_machtype; #elif defined(CONFIG_AMIGA) || defined(CONFIG_MAC) || defined(CONFIG_ATARI) \ || defined(CONFIG_APOLLO) || defined(CONFIG_BVME6000) \ || defined(CONFIG_HP300) || defined(CONFIG_Q40) \ - || defined(CONFIG_SUN3X) || defined(CONFIG_MVME147) + || defined(CONFIG_SUN3X) || defined(CONFIG_MVME147) \ + || defined(CONFIG_VIRT) # define MACH_IS_MVME16x (m68k_machtype == MACH_MVME16x) #else # define MACH_MVME16x_ONLY @@ -123,7 +129,8 @@ extern unsigned long m68k_machtype; #elif defined(CONFIG_AMIGA) || defined(CONFIG_MAC) || defined(CONFIG_ATARI) \ || defined(CONFIG_APOLLO) || defined(CONFIG_MVME16x) \ || defined(CONFIG_HP300) || defined(CONFIG_Q40) \ - || defined(CONFIG_SUN3X) || defined(CONFIG_MVME147) + || defined(CONFIG_SUN3X) || defined(CONFIG_MVME147) \ + || defined(CONFIG_VIRT) # define MACH_IS_BVME6000 (m68k_machtype == MACH_BVME6000) #else # define MACH_BVME6000_ONLY @@ -136,7 +143,8 @@ extern unsigned long m68k_machtype; #elif defined(CONFIG_AMIGA) || defined(CONFIG_MAC) || defined(CONFIG_ATARI) \ || defined(CONFIG_APOLLO) || defined(CONFIG_MVME16x) \ || defined(CONFIG_BVME6000) || defined(CONFIG_Q40) \ - || defined(CONFIG_SUN3X) || defined(CONFIG_MVME147) + || defined(CONFIG_SUN3X) || defined(CONFIG_MVME147) \ + || defined(CONFIG_VIRT) # define MACH_IS_HP300 (m68k_machtype == MACH_HP300) #else # define MACH_HP300_ONLY @@ -149,7 +157,8 @@ extern unsigned long m68k_machtype; #elif defined(CONFIG_AMIGA) || defined(CONFIG_MAC) || defined(CONFIG_ATARI) \ || defined(CONFIG_APOLLO) || defined(CONFIG_MVME16x) \ || defined(CONFIG_BVME6000) || defined(CONFIG_HP300) \ - || defined(CONFIG_SUN3X) || defined(CONFIG_MVME147) + || defined(CONFIG_SUN3X) || defined(CONFIG_MVME147) \ + || defined(CONFIG_VIRT) # define MACH_IS_Q40 (m68k_machtype == MACH_Q40) #else # define MACH_Q40_ONLY @@ -162,7 +171,8 @@ extern unsigned long m68k_machtype; #elif defined(CONFIG_AMIGA) || defined(CONFIG_MAC) || defined(CONFIG_ATARI) \ || defined(CONFIG_APOLLO) || defined(CONFIG_MVME16x) \ || defined(CONFIG_BVME6000) || defined(CONFIG_HP300) \ - || defined(CONFIG_Q40) || defined(CONFIG_MVME147) + || defined(CONFIG_Q40) || defined(CONFIG_MVME147) \ + || defined(CONFIG_VIRT) # define MACH_IS_SUN3X (m68k_machtype == MACH_SUN3X) #else # define CONFIG_SUN3X_ONLY @@ -170,6 +180,20 @@ extern unsigned long m68k_machtype; # define MACH_TYPE (MACH_SUN3X) #endif +#if !defined(CONFIG_VIRT) +# define MACH_IS_VIRT (0) +#elif defined(CONFIG_AMIGA) || defined(CONFIG_MAC) || defined(CONFIG_ATARI) \ + || defined(CONFIG_APOLLO) || defined(CONFIG_MVME16x) \ + || defined(CONFIG_BVME6000) || defined(CONFIG_HP300) \ + || defined(CONFIG_Q40) || defined(CONFIG_SUN3X) \ + || defined(CONFIG_MVME147) +# define MACH_IS_VIRT (m68k_machtype == MACH_VIRT) +#else +# define MACH_VIRT_ONLY +# define MACH_IS_VIRT (1) +# define MACH_TYPE (MACH_VIRT) +#endif + #ifndef MACH_TYPE # define MACH_TYPE (m68k_machtype) #endif diff --git a/arch/m68k/include/asm/timex.h b/arch/m68k/include/asm/timex.h index 6a21d9358280..f4a7a340f4ca 100644 --- a/arch/m68k/include/asm/timex.h +++ b/arch/m68k/include/asm/timex.h @@ -35,7 +35,7 @@ static inline unsigned long random_get_entropy(void) { if (mach_random_get_entropy) return mach_random_get_entropy(); - return 0; + return random_get_entropy_fallback(); } #define random_get_entropy random_get_entropy diff --git a/arch/m68k/include/asm/virt.h b/arch/m68k/include/asm/virt.h new file mode 100644 index 000000000000..d3320c954796 --- /dev/null +++ b/arch/m68k/include/asm/virt.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_VIRT_H +#define __ASM_VIRT_H + +#define NUM_VIRT_SOURCES 200 + +struct virt_booter_device_data { + u32 mmio; + u32 irq; +}; + +struct virt_booter_data { + u32 qemu_version; + struct virt_booter_device_data pic; + struct virt_booter_device_data rtc; + struct virt_booter_device_data tty; + struct virt_booter_device_data ctrl; + struct virt_booter_device_data virtio; +}; + +extern struct virt_booter_data virt_bi_data; + +extern void __init virt_init_IRQ(void); + +#endif diff --git a/arch/m68k/include/uapi/asm/bootinfo-virt.h b/arch/m68k/include/uapi/asm/bootinfo-virt.h new file mode 100644 index 000000000000..e4db7e2213ab --- /dev/null +++ b/arch/m68k/include/uapi/asm/bootinfo-virt.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * asm/bootinfo-virt.h -- Virtual-m68k-specific boot information definitions + */ + +#ifndef _UAPI_ASM_M68K_BOOTINFO_VIRT_H +#define _UAPI_ASM_M68K_BOOTINFO_VIRT_H + +#define BI_VIRT_QEMU_VERSION 0x8000 +#define BI_VIRT_GF_PIC_BASE 0x8001 +#define BI_VIRT_GF_RTC_BASE 0x8002 +#define BI_VIRT_GF_TTY_BASE 0x8003 +#define BI_VIRT_VIRTIO_BASE 0x8004 +#define BI_VIRT_CTRL_BASE 0x8005 + +#define VIRT_BOOTI_VERSION MK_BI_VERSION(2, 0) + +#endif /* _UAPI_ASM_M68K_BOOTINFO_MAC_H */ diff --git a/arch/m68k/include/uapi/asm/bootinfo.h b/arch/m68k/include/uapi/asm/bootinfo.h index 38d3140381fa..203d9cbf9630 100644 --- a/arch/m68k/include/uapi/asm/bootinfo.h +++ b/arch/m68k/include/uapi/asm/bootinfo.h @@ -83,6 +83,7 @@ struct mem_info { #define MACH_SUN3X 11 #define MACH_M54XX 12 #define MACH_M5441X 13 +#define MACH_VIRT 14 /* diff --git a/arch/m68k/kernel/Makefile b/arch/m68k/kernel/Makefile index dbac7f8743fc..c0833da6a2ca 100644 --- a/arch/m68k/kernel/Makefile +++ b/arch/m68k/kernel/Makefile @@ -11,6 +11,7 @@ extra-$(CONFIG_VME) := head.o extra-$(CONFIG_HP300) := head.o extra-$(CONFIG_Q40) := head.o extra-$(CONFIG_SUN3X) := head.o +extra-$(CONFIG_VIRT) := head.o extra-$(CONFIG_SUN3) := sun3-head.o extra-y += vmlinux.lds diff --git a/arch/m68k/kernel/entry.S b/arch/m68k/kernel/entry.S index 9434fca68de5..18f278bdbd21 100644 --- a/arch/m68k/kernel/entry.S +++ b/arch/m68k/kernel/entry.S @@ -181,7 +181,7 @@ do_trace_entry: movel #-ENOSYS,%sp@(PT_OFF_D0)| needed for strace subql #4,%sp SAVE_SWITCH_STACK - jbsr syscall_trace + jbsr syscall_trace_enter RESTORE_SWITCH_STACK addql #4,%sp movel %sp@(PT_OFF_ORIG_D0),%d0 @@ -194,7 +194,7 @@ badsys: do_trace_exit: subql #4,%sp SAVE_SWITCH_STACK - jbsr syscall_trace + jbsr syscall_trace_leave RESTORE_SWITCH_STACK addql #4,%sp jra .Lret_from_exception diff --git a/arch/m68k/kernel/head.S b/arch/m68k/kernel/head.S index 493c95db0e51..9e812d8606be 100644 --- a/arch/m68k/kernel/head.S +++ b/arch/m68k/kernel/head.S @@ -262,6 +262,7 @@ #include <asm/bootinfo-hp300.h> #include <asm/bootinfo-mac.h> #include <asm/bootinfo-q40.h> +#include <asm/bootinfo-virt.h> #include <asm/bootinfo-vme.h> #include <asm/setup.h> #include <asm/entry.h> @@ -534,6 +535,7 @@ func_define putn,1 #define is_not_apollo(lab) cmpl &MACH_APOLLO,%pc@(m68k_machtype); jne lab #define is_not_q40(lab) cmpl &MACH_Q40,%pc@(m68k_machtype); jne lab #define is_not_sun3x(lab) cmpl &MACH_SUN3X,%pc@(m68k_machtype); jne lab +#define is_not_virt(lab) cmpl &MACH_VIRT,%pc@(m68k_machtype); jne lab #define hasnt_leds(lab) cmpl &MACH_HP300,%pc@(m68k_machtype); \ jeq 42f; \ @@ -647,6 +649,14 @@ ENTRY(__start) L(test_notmac): #endif /* CONFIG_MAC */ +#ifdef CONFIG_VIRT + is_not_virt(L(test_notvirt)) + + get_bi_record BI_VIRT_GF_TTY_BASE + lea %pc@(L(virt_gf_tty_base)),%a1 + movel %a0@,%a1@ +L(test_notvirt): +#endif /* CONFIG_VIRT */ /* * There are ultimately two pieces of information we want for all kinds of @@ -1237,6 +1247,13 @@ L(mmu_init_not_mac): L(notsun3x): #endif +#ifdef CONFIG_VIRT + is_not_virt(L(novirt)) + mmu_map_tt #1,#0xFF000000,#0x01000000,#_PAGE_NOCACHE_S + jbra L(mmu_init_done) +L(novirt): +#endif + #ifdef CONFIG_APOLLO is_not_apollo(L(notapollo)) @@ -3186,6 +3203,14 @@ func_start serial_putc,%d0/%d1/%a0/%a1 3: #endif +#ifdef CONFIG_VIRT + is_not_virt(1f) + + movel L(virt_gf_tty_base),%a1 + movel %d0,%a1@(GF_PUT_CHAR) +1: +#endif + L(serial_putc_done): func_return serial_putc @@ -3865,3 +3890,9 @@ q40_mem_cptr: L(q40_do_debug): .long 0 #endif + +#if defined(CONFIG_VIRT) +GF_PUT_CHAR = 0x00 +L(virt_gf_tty_base): + .long 0 +#endif /* CONFIG_VIRT */ diff --git a/arch/m68k/kernel/ptrace.c b/arch/m68k/kernel/ptrace.c index 6342ff4d2073..daebccdd2c09 100644 --- a/arch/m68k/kernel/ptrace.c +++ b/arch/m68k/kernel/ptrace.c @@ -270,12 +270,6 @@ out_eio: return -EIO; } -asmlinkage void syscall_trace(void) -{ - ptrace_report_syscall(0); -} - -#if defined(CONFIG_COLDFIRE) || !defined(CONFIG_MMU) asmlinkage int syscall_trace_enter(void) { int ret = 0; @@ -290,4 +284,3 @@ asmlinkage void syscall_trace_leave(void) if (test_thread_flag(TIF_SYSCALL_TRACE)) ptrace_report_syscall_exit(task_pt_regs(current), 0); } -#endif /* CONFIG_COLDFIRE */ diff --git a/arch/m68k/kernel/setup_mm.c b/arch/m68k/kernel/setup_mm.c index 8f94feed969c..78ab562beb31 100644 --- a/arch/m68k/kernel/setup_mm.c +++ b/arch/m68k/kernel/setup_mm.c @@ -181,6 +181,8 @@ static void __init m68k_parse_bootinfo(const struct bi_record *record) unknown = hp300_parse_bootinfo(record); else if (MACH_IS_APOLLO) unknown = apollo_parse_bootinfo(record); + else if (MACH_IS_VIRT) + unknown = virt_parse_bootinfo(record); else unknown = 1; } @@ -312,6 +314,11 @@ void __init setup_arch(char **cmdline_p) config_BSP(NULL, 0); break; #endif +#ifdef CONFIG_VIRT + case MACH_VIRT: + config_virt(); + break; +#endif default: panic("No configuration setup"); } diff --git a/arch/m68k/kernel/signal.c b/arch/m68k/kernel/signal.c index 49533f65958a..b9f6908a31bc 100644 --- a/arch/m68k/kernel/signal.c +++ b/arch/m68k/kernel/signal.c @@ -625,6 +625,7 @@ static inline void siginfo_build_tests(void) /* _sigfault._perf */ BUILD_BUG_ON(offsetof(siginfo_t, si_perf_data) != 0x10); BUILD_BUG_ON(offsetof(siginfo_t, si_perf_type) != 0x14); + BUILD_BUG_ON(offsetof(siginfo_t, si_perf_flags) != 0x18); /* _sigpoll */ BUILD_BUG_ON(offsetof(siginfo_t, si_band) != 0x0c); diff --git a/arch/m68k/math-emu/fp_arith.c b/arch/m68k/math-emu/fp_arith.c index d9033238d097..f4a06492cd7a 100644 --- a/arch/m68k/math-emu/fp_arith.c +++ b/arch/m68k/math-emu/fp_arith.c @@ -243,7 +243,7 @@ fp_fdiv(struct fp_ext *dest, struct fp_ext *src) /* infinity / infinity = NaN (quiet, as always) */ if (IS_INF(src)) fp_set_nan(dest); - /* infinity / anything else = infinity (with approprate sign) */ + /* infinity / anything else = infinity (with appropriate sign) */ return dest; } if (IS_INF(src)) { diff --git a/arch/m68k/mm/kmap.c b/arch/m68k/mm/kmap.c index 20ddf71b43d0..7594a945732b 100644 --- a/arch/m68k/mm/kmap.c +++ b/arch/m68k/mm/kmap.c @@ -179,6 +179,12 @@ void __iomem *__ioremap(unsigned long physaddr, unsigned long size, int cachefla return (void __iomem *)physaddr; } #endif +#ifdef CONFIG_VIRT + if (MACH_IS_VIRT) { + if (physaddr >= 0xff000000 && cacheflag == IOMAP_NOCACHE_SER) + return (void __iomem *)physaddr; + } +#endif #ifdef CONFIG_COLDFIRE if (__cf_internalio(physaddr)) return (void __iomem *) physaddr; @@ -293,17 +299,20 @@ EXPORT_SYMBOL(__ioremap); void iounmap(void __iomem *addr) { #ifdef CONFIG_AMIGA - if ((!MACH_IS_AMIGA) || - (((unsigned long)addr < 0x40000000) || - ((unsigned long)addr > 0x60000000))) - free_io_area((__force void *)addr); -#else + if (MACH_IS_AMIGA && + ((unsigned long)addr >= 0x40000000) && + ((unsigned long)addr < 0x60000000)) + return; +#endif +#ifdef CONFIG_VIRT + if (MACH_IS_VIRT && (unsigned long)addr >= 0xff000000) + return; +#endif #ifdef CONFIG_COLDFIRE if (cf_internalio(addr)) return; #endif free_io_area((__force void *)addr); -#endif } EXPORT_SYMBOL(iounmap); diff --git a/arch/m68k/virt/Makefile b/arch/m68k/virt/Makefile new file mode 100644 index 000000000000..54b9b2866654 --- /dev/null +++ b/arch/m68k/virt/Makefile @@ -0,0 +1,6 @@ +# SPDX-License-Identifier: GPL-2.0-only +# +# Makefile for Linux arch/m68k/virt source directory +# + +obj-y := config.o ints.o platform.o diff --git a/arch/m68k/virt/config.c b/arch/m68k/virt/config.c new file mode 100644 index 000000000000..68d29c8b87e1 --- /dev/null +++ b/arch/m68k/virt/config.c @@ -0,0 +1,130 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/serial_core.h> +#include <clocksource/timer-goldfish.h> + +#include <asm/bootinfo.h> +#include <asm/bootinfo-virt.h> +#include <asm/byteorder.h> +#include <asm/machdep.h> +#include <asm/virt.h> +#include <asm/config.h> + +struct virt_booter_data virt_bi_data; + +#define VIRT_CTRL_REG_FEATURES 0x00 +#define VIRT_CTRL_REG_CMD 0x04 + +static struct resource ctrlres; + +enum { + CMD_NOOP, + CMD_RESET, + CMD_HALT, + CMD_PANIC, +}; + +static void virt_get_model(char *str) +{ + /* str is 80 characters long */ + sprintf(str, "QEMU Virtual M68K Machine (%u.%u.%u)", + (u8)(virt_bi_data.qemu_version >> 24), + (u8)(virt_bi_data.qemu_version >> 16), + (u8)(virt_bi_data.qemu_version >> 8)); +} + +static void virt_halt(void) +{ + void __iomem *base = (void __iomem *)virt_bi_data.ctrl.mmio; + + iowrite32be(CMD_HALT, base + VIRT_CTRL_REG_CMD); + local_irq_disable(); + while (1) + ; +} + +static void virt_reset(void) +{ + void __iomem *base = (void __iomem *)virt_bi_data.ctrl.mmio; + + iowrite32be(CMD_RESET, base + VIRT_CTRL_REG_CMD); + local_irq_disable(); + while (1) + ; +} + +/* + * Parse a virtual-m68k-specific record in the bootinfo + */ + +int __init virt_parse_bootinfo(const struct bi_record *record) +{ + int unknown = 0; + const void *data = record->data; + + switch (be16_to_cpu(record->tag)) { + case BI_VIRT_QEMU_VERSION: + virt_bi_data.qemu_version = be32_to_cpup(data); + break; + case BI_VIRT_GF_PIC_BASE: + virt_bi_data.pic.mmio = be32_to_cpup(data); + data += 4; + virt_bi_data.pic.irq = be32_to_cpup(data); + break; + case BI_VIRT_GF_RTC_BASE: + virt_bi_data.rtc.mmio = be32_to_cpup(data); + data += 4; + virt_bi_data.rtc.irq = be32_to_cpup(data); + break; + case BI_VIRT_GF_TTY_BASE: + virt_bi_data.tty.mmio = be32_to_cpup(data); + data += 4; + virt_bi_data.tty.irq = be32_to_cpup(data); + break; + case BI_VIRT_CTRL_BASE: + virt_bi_data.ctrl.mmio = be32_to_cpup(data); + data += 4; + virt_bi_data.ctrl.irq = be32_to_cpup(data); + break; + case BI_VIRT_VIRTIO_BASE: + virt_bi_data.virtio.mmio = be32_to_cpup(data); + data += 4; + virt_bi_data.virtio.irq = be32_to_cpup(data); + break; + default: + unknown = 1; + break; + } + return unknown; +} + +static void __init virt_sched_init(void) +{ + goldfish_timer_init(virt_bi_data.rtc.irq, + (void __iomem *)virt_bi_data.rtc.mmio); +} + +void __init config_virt(void) +{ + char earlycon[24]; + + snprintf(earlycon, sizeof(earlycon), "early_gf_tty,0x%08x", + virt_bi_data.tty.mmio); + setup_earlycon(earlycon); + + ctrlres = (struct resource) + DEFINE_RES_MEM_NAMED(virt_bi_data.ctrl.mmio, 0x100, + "virtctrl"); + + if (request_resource(&iomem_resource, &ctrlres)) { + pr_err("Cannot allocate virt controller resource\n"); + return; + } + + mach_init_IRQ = virt_init_IRQ; + mach_sched_init = virt_sched_init; + mach_get_model = virt_get_model; + mach_reset = virt_reset; + mach_halt = virt_halt; + mach_power_off = virt_halt; +} diff --git a/arch/m68k/virt/ints.c b/arch/m68k/virt/ints.c new file mode 100644 index 000000000000..95818f901ebe --- /dev/null +++ b/arch/m68k/virt/ints.c @@ -0,0 +1,155 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/delay.h> +#include <linux/interrupt.h> +#include <linux/irq.h> +#include <linux/kernel.h> +#include <linux/sched.h> +#include <linux/sched/debug.h> +#include <linux/types.h> +#include <linux/ioport.h> + +#include <asm/hwtest.h> +#include <asm/irq.h> +#include <asm/irq_regs.h> +#include <asm/virt.h> + +#define GFPIC_REG_IRQ_PENDING 0x04 +#define GFPIC_REG_IRQ_DISABLE_ALL 0x08 +#define GFPIC_REG_IRQ_DISABLE 0x0c +#define GFPIC_REG_IRQ_ENABLE 0x10 + +extern void show_registers(struct pt_regs *regs); + +static struct resource picres[6]; +static const char *picname[6] = { + "goldfish_pic.0", + "goldfish_pic.1", + "goldfish_pic.2", + "goldfish_pic.3", + "goldfish_pic.4", + "goldfish_pic.5" +}; + +/* + * 6 goldfish-pic for CPU IRQ #1 to IRQ #6 + * CPU IRQ #1 -> PIC #1 + * IRQ #1 to IRQ #31 -> unused + * IRQ #32 -> goldfish-tty + * CPU IRQ #2 -> PIC #2 + * IRQ #1 to IRQ #32 -> virtio-mmio from 1 to 32 + * CPU IRQ #3 -> PIC #3 + * IRQ #1 to IRQ #32 -> virtio-mmio from 33 to 64 + * CPU IRQ #4 -> PIC #4 + * IRQ #1 to IRQ #32 -> virtio-mmio from 65 to 96 + * CPU IRQ #5 -> PIC #5 + * IRQ #1 to IRQ #32 -> virtio-mmio from 97 to 128 + * CPU IRQ #6 -> PIC #6 + * IRQ #1 -> goldfish-timer + * IRQ #2 -> goldfish-rtc + * IRQ #3 to IRQ #32 -> unused + * CPU IRQ #7 -> NMI + */ + +static u32 gfpic_read(int pic, int reg) +{ + void __iomem *base = (void __iomem *)(virt_bi_data.pic.mmio + + pic * 0x1000); + + return ioread32be(base + reg); +} + +static void gfpic_write(u32 value, int pic, int reg) +{ + void __iomem *base = (void __iomem *)(virt_bi_data.pic.mmio + + pic * 0x1000); + + iowrite32be(value, base + reg); +} + +#define GF_PIC(irq) ((irq - IRQ_USER) / 32) +#define GF_IRQ(irq) ((irq - IRQ_USER) % 32) + +static void virt_irq_enable(struct irq_data *data) +{ + gfpic_write(BIT(GF_IRQ(data->irq)), GF_PIC(data->irq), + GFPIC_REG_IRQ_ENABLE); +} + +static void virt_irq_disable(struct irq_data *data) +{ + gfpic_write(BIT(GF_IRQ(data->irq)), GF_PIC(data->irq), + GFPIC_REG_IRQ_DISABLE); +} + +static unsigned int virt_irq_startup(struct irq_data *data) +{ + virt_irq_enable(data); + return 0; +} + +static irqreturn_t virt_nmi_handler(int irq, void *dev_id) +{ + static int in_nmi; + + if (READ_ONCE(in_nmi)) + return IRQ_HANDLED; + WRITE_ONCE(in_nmi, 1); + + pr_warn("Non-Maskable Interrupt\n"); + show_registers(get_irq_regs()); + + WRITE_ONCE(in_nmi, 0); + return IRQ_HANDLED; +} + +static struct irq_chip virt_irq_chip = { + .name = "virt", + .irq_enable = virt_irq_enable, + .irq_disable = virt_irq_disable, + .irq_startup = virt_irq_startup, + .irq_shutdown = virt_irq_disable, +}; + +static void goldfish_pic_irq(struct irq_desc *desc) +{ + u32 irq_pending; + unsigned int irq_num; + unsigned int pic = desc->irq_data.irq - 1; + + irq_pending = gfpic_read(pic, GFPIC_REG_IRQ_PENDING); + irq_num = IRQ_USER + pic * 32; + + do { + if (irq_pending & 1) + generic_handle_irq(irq_num); + ++irq_num; + irq_pending >>= 1; + } while (irq_pending); +} + +void __init virt_init_IRQ(void) +{ + unsigned int i; + + m68k_setup_irq_controller(&virt_irq_chip, handle_simple_irq, IRQ_USER, + NUM_VIRT_SOURCES - IRQ_USER); + + for (i = 0; i < 6; i++) { + + picres[i] = (struct resource) + DEFINE_RES_MEM_NAMED(virt_bi_data.pic.mmio + i * 0x1000, + 0x1000, picname[i]); + if (request_resource(&iomem_resource, &picres[i])) { + pr_err("Cannot allocate %s resource\n", picname[i]); + return; + } + + irq_set_chained_handler(virt_bi_data.pic.irq + i, + goldfish_pic_irq); + } + + if (request_irq(IRQ_AUTO_7, virt_nmi_handler, 0, "NMI", + virt_nmi_handler)) + pr_err("Couldn't register NMI\n"); +} diff --git a/arch/m68k/virt/platform.c b/arch/m68k/virt/platform.c new file mode 100644 index 000000000000..cb820f19a221 --- /dev/null +++ b/arch/m68k/virt/platform.c @@ -0,0 +1,72 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/platform_device.h> +#include <linux/interrupt.h> +#include <linux/memblock.h> +#include <asm/virt.h> +#include <asm/irq.h> + +#define VIRTIO_BUS_NB 128 + +static int __init virt_virtio_init(unsigned int id) +{ + const struct resource res[] = { + DEFINE_RES_MEM(virt_bi_data.virtio.mmio + id * 0x200, 0x200), + DEFINE_RES_IRQ(virt_bi_data.virtio.irq + id), + }; + struct platform_device *pdev; + + pdev = platform_device_register_simple("virtio-mmio", id, + res, ARRAY_SIZE(res)); + if (IS_ERR(pdev)) + return PTR_ERR(pdev); + + return 0; +} + +static int __init virt_platform_init(void) +{ + const struct resource goldfish_tty_res[] = { + DEFINE_RES_MEM(virt_bi_data.tty.mmio, 1), + DEFINE_RES_IRQ(virt_bi_data.tty.irq), + }; + /* this is the second gf-rtc, the first one is used by the scheduler */ + const struct resource goldfish_rtc_res[] = { + DEFINE_RES_MEM(virt_bi_data.rtc.mmio + 0x1000, 0x1000), + DEFINE_RES_IRQ(virt_bi_data.rtc.irq + 1), + }; + struct platform_device *pdev; + unsigned int i; + + if (!MACH_IS_VIRT) + return -ENODEV; + + /* We need this to have DMA'able memory provided to goldfish-tty */ + min_low_pfn = 0; + + pdev = platform_device_register_simple("goldfish_tty", + PLATFORM_DEVID_NONE, + goldfish_tty_res, + ARRAY_SIZE(goldfish_tty_res)); + if (IS_ERR(pdev)) + return PTR_ERR(pdev); + + pdev = platform_device_register_simple("goldfish_rtc", + PLATFORM_DEVID_NONE, + goldfish_rtc_res, + ARRAY_SIZE(goldfish_rtc_res)); + if (IS_ERR(pdev)) + return PTR_ERR(pdev); + + for (i = 0; i < VIRTIO_BUS_NB; i++) { + int err; + + err = virt_virtio_init(i); + if (err) + return err; + } + + return 0; +} + +arch_initcall(virt_platform_init); diff --git a/arch/mips/include/asm/timex.h b/arch/mips/include/asm/timex.h index b05bb70a2e46..2e107886f97a 100644 --- a/arch/mips/include/asm/timex.h +++ b/arch/mips/include/asm/timex.h @@ -40,9 +40,9 @@ typedef unsigned int cycles_t; /* - * On R4000/R4400 before version 5.0 an erratum exists such that if the - * cycle counter is read in the exact moment that it is matching the - * compare register, no interrupt will be generated. + * On R4000/R4400 an erratum exists such that if the cycle counter is + * read in the exact moment that it is matching the compare register, + * no interrupt will be generated. * * There is a suggested workaround and also the erratum can't strike if * the compare interrupt isn't being used as the clock source device. @@ -63,7 +63,7 @@ static inline int can_use_mips_counter(unsigned int prid) if (!__builtin_constant_p(cpu_has_counter)) asm volatile("" : "=m" (cpu_data[0].options)); if (likely(cpu_has_counter && - prid >= (PRID_IMP_R4000 | PRID_REV_ENCODE_44(5, 0)))) + prid > (PRID_IMP_R4000 | PRID_REV_ENCODE_44(15, 15)))) return 1; else return 0; @@ -76,25 +76,24 @@ static inline cycles_t get_cycles(void) else return 0; /* no usable counter */ } +#define get_cycles get_cycles /* * Like get_cycles - but where c0_count is not available we desperately * use c0_random in an attempt to get at least a little bit of entropy. - * - * R6000 and R6000A neither have a count register nor a random register. - * That leaves no entropy source in the CPU itself. */ static inline unsigned long random_get_entropy(void) { - unsigned int prid = read_c0_prid(); - unsigned int imp = prid & PRID_IMP_MASK; + unsigned int c0_random; - if (can_use_mips_counter(prid)) + if (can_use_mips_counter(read_c0_prid())) return read_c0_count(); - else if (likely(imp != PRID_IMP_R6000 && imp != PRID_IMP_R6000A)) - return read_c0_random(); + + if (cpu_has_3kex) + c0_random = (read_c0_random() >> 8) & 0x3f; else - return 0; /* no usable register */ + c0_random = read_c0_random() & 0x3f; + return (random_get_entropy_fallback() << 6) | (0x3f - c0_random); } #define random_get_entropy random_get_entropy diff --git a/arch/mips/kernel/time.c b/arch/mips/kernel/time.c index caa01457dce6..ed339d7979f3 100644 --- a/arch/mips/kernel/time.c +++ b/arch/mips/kernel/time.c @@ -141,15 +141,10 @@ static __init int cpu_has_mfc0_count_bug(void) case CPU_R4400MC: /* * The published errata for the R4400 up to 3.0 say the CPU - * has the mfc0 from count bug. + * has the mfc0 from count bug. This seems the last version + * produced. */ - if ((current_cpu_data.processor_id & 0xff) <= 0x30) - return 1; - - /* - * we assume newer revisions are ok - */ - return 0; + return 1; } return 0; diff --git a/arch/nios2/include/asm/timex.h b/arch/nios2/include/asm/timex.h index a769f871b28d..40a1adc9bd03 100644 --- a/arch/nios2/include/asm/timex.h +++ b/arch/nios2/include/asm/timex.h @@ -8,5 +8,8 @@ typedef unsigned long cycles_t; extern cycles_t get_cycles(void); +#define get_cycles get_cycles + +#define random_get_entropy() (((unsigned long)get_cycles()) ?: random_get_entropy_fallback()) #endif diff --git a/arch/openrisc/include/asm/timex.h b/arch/openrisc/include/asm/timex.h index d52b4e536e3f..5487fa93dd9b 100644 --- a/arch/openrisc/include/asm/timex.h +++ b/arch/openrisc/include/asm/timex.h @@ -23,6 +23,7 @@ static inline cycles_t get_cycles(void) { return mfspr(SPR_TTCR); } +#define get_cycles get_cycles /* This isn't really used any more */ #define CLOCK_TICK_RATE 1000 diff --git a/arch/openrisc/kernel/head.S b/arch/openrisc/kernel/head.S index 15f1b38dfe03..2fa6cefa62ca 100644 --- a/arch/openrisc/kernel/head.S +++ b/arch/openrisc/kernel/head.S @@ -521,6 +521,15 @@ _start: l.ori r3,r0,0x1 l.mtspr r0,r3,SPR_SR + /* + * Start the TTCR as early as possible, so that the RNG can make use of + * measurements of boot time from the earliest opportunity. Especially + * important is that the TTCR does not return zero by the time we reach + * random_init(). + */ + l.movhi r3,hi(SPR_TTMR_CR) + l.mtspr r0,r3,SPR_TTMR + CLEAR_GPR(r1) CLEAR_GPR(r2) CLEAR_GPR(r3) diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index 52e550b45692..bd22578859d0 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -38,6 +38,7 @@ config PARISC select ARCH_HAVE_NMI_SAFE_CMPXCHG select GENERIC_SMP_IDLE_THREAD select GENERIC_ARCH_TOPOLOGY if SMP + select GENERIC_CPU_DEVICES if !SMP select GENERIC_LIB_DEVMEM_IS_ALLOWED select SYSCTL_ARCH_UNALIGN_ALLOW select SYSCTL_EXCEPTION_TRACE diff --git a/arch/parisc/configs/generic-32bit_defconfig b/arch/parisc/configs/generic-32bit_defconfig index a5fee10d76ee..8ce0ae370680 100644 --- a/arch/parisc/configs/generic-32bit_defconfig +++ b/arch/parisc/configs/generic-32bit_defconfig @@ -6,6 +6,9 @@ CONFIG_BSD_PROCESS_ACCT=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y CONFIG_LOG_BUF_SHIFT=16 +CONFIG_CGROUPS=y +CONFIG_NAMESPACES=y +CONFIG_USER_NS=y CONFIG_BLK_DEV_INITRD=y CONFIG_EXPERT=y CONFIG_PERF_EVENTS=y @@ -47,7 +50,6 @@ CONFIG_PARPORT=y CONFIG_PARPORT_PC=m CONFIG_PARPORT_1284=y CONFIG_BLK_DEV_LOOP=y -CONFIG_BLK_DEV_CRYPTOLOOP=y CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=6144 CONFIG_BLK_DEV_SD=y diff --git a/arch/parisc/configs/generic-64bit_defconfig b/arch/parisc/configs/generic-64bit_defconfig index 1b8fd80cbe7f..57501b0aed92 100644 --- a/arch/parisc/configs/generic-64bit_defconfig +++ b/arch/parisc/configs/generic-64bit_defconfig @@ -16,6 +16,7 @@ CONFIG_CGROUPS=y CONFIG_MEMCG=y CONFIG_CGROUP_PIDS=y CONFIG_CPUSETS=y +CONFIG_USER_NS=y CONFIG_RELAY=y CONFIG_BLK_DEV_INITRD=y CONFIG_CC_OPTIMIZE_FOR_SIZE=y @@ -267,9 +268,9 @@ CONFIG_CRYPTO_DEFLATE=m CONFIG_CRC_CCITT=m CONFIG_LIBCRC32C=y CONFIG_PRINTK_TIME=y +CONFIG_DEBUG_KERNEL=y CONFIG_STRIP_ASM_SYMS=y CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_FS=y -CONFIG_DEBUG_KERNEL=y CONFIG_DEBUG_STACKOVERFLOW=y # CONFIG_SCHED_DEBUG is not set diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h index e8b4a03343d3..8d03b3b26229 100644 --- a/arch/parisc/include/asm/cacheflush.h +++ b/arch/parisc/include/asm/cacheflush.h @@ -59,20 +59,12 @@ void flush_dcache_page(struct page *page); flush_kernel_icache_range_asm(s,e); \ } while (0) -#define copy_to_user_page(vma, page, vaddr, dst, src, len) \ -do { \ - flush_cache_page(vma, vaddr, page_to_pfn(page)); \ - memcpy(dst, src, len); \ - flush_kernel_dcache_range_asm((unsigned long)dst, (unsigned long)dst + len); \ -} while (0) - -#define copy_from_user_page(vma, page, vaddr, dst, src, len) \ -do { \ - flush_cache_page(vma, vaddr, page_to_pfn(page)); \ - memcpy(dst, src, len); \ -} while (0) - -void flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, unsigned long pfn); +void copy_to_user_page(struct vm_area_struct *vma, struct page *page, + unsigned long user_vaddr, void *dst, void *src, int len); +void copy_from_user_page(struct vm_area_struct *vma, struct page *page, + unsigned long user_vaddr, void *dst, void *src, int len); +void flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, + unsigned long pfn); void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); @@ -80,16 +72,7 @@ void flush_cache_range(struct vm_area_struct *vma, void flush_dcache_page_asm(unsigned long phys_addr, unsigned long vaddr); #define ARCH_HAS_FLUSH_ANON_PAGE -static inline void -flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned long vmaddr) -{ - if (PageAnon(page)) { - flush_tlb_page(vma, vmaddr); - preempt_disable(); - flush_dcache_page_asm(page_to_phys(page), vmaddr); - preempt_enable(); - } -} +void flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned long vmaddr); #define ARCH_HAS_FLUSH_ON_KUNMAP static inline void kunmap_flush_on_unmap(void *addr) diff --git a/arch/parisc/include/asm/page.h b/arch/parisc/include/asm/page.h index 0561568f7b48..6faaaa3ebe9b 100644 --- a/arch/parisc/include/asm/page.h +++ b/arch/parisc/include/asm/page.h @@ -26,12 +26,14 @@ #define copy_page(to, from) copy_page_asm((void *)(to), (void *)(from)) struct page; +struct vm_area_struct; void clear_page_asm(void *page); void copy_page_asm(void *to, void *from); #define clear_user_page(vto, vaddr, page) clear_page_asm(vto) -void copy_user_page(void *vto, void *vfrom, unsigned long vaddr, - struct page *pg); +void copy_user_highpage(struct page *to, struct page *from, unsigned long vaddr, + struct vm_area_struct *vma); +#define __HAVE_ARCH_COPY_USER_HIGHPAGE /* * These are used to make use of C type-checking.. diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h index 939db6fe620b..69765a6dbe89 100644 --- a/arch/parisc/include/asm/pgtable.h +++ b/arch/parisc/include/asm/pgtable.h @@ -160,7 +160,7 @@ extern void __update_cache(pte_t pte); #define SPACEID_SHIFT (MAX_ADDRBITS - 32) #else #define MAX_ADDRBITS (BITS_PER_LONG) -#define MAX_ADDRESS (1UL << MAX_ADDRBITS) +#define MAX_ADDRESS (1ULL << MAX_ADDRBITS) #define SPACEID_SHIFT 0 #endif diff --git a/arch/parisc/include/asm/timex.h b/arch/parisc/include/asm/timex.h index 06b510f8172e..b4622cb06a75 100644 --- a/arch/parisc/include/asm/timex.h +++ b/arch/parisc/include/asm/timex.h @@ -13,9 +13,10 @@ typedef unsigned long cycles_t; -static inline cycles_t get_cycles (void) +static inline cycles_t get_cycles(void) { return mfctl(16); } +#define get_cycles get_cycles #endif diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c index 23348199f3f8..0fd04073d4b6 100644 --- a/arch/parisc/kernel/cache.c +++ b/arch/parisc/kernel/cache.c @@ -27,6 +27,7 @@ #include <asm/processor.h> #include <asm/sections.h> #include <asm/shmparam.h> +#include <asm/mmu_context.h> int split_tlb __ro_after_init; int dcache_stride __ro_after_init; @@ -91,7 +92,7 @@ static inline void flush_data_cache(void) } -/* Virtual address of pfn. */ +/* Kernel virtual address of pfn. */ #define pfn_va(pfn) __va(PFN_PHYS(pfn)) void @@ -124,11 +125,13 @@ show_cache_info(struct seq_file *m) cache_info.ic_size/1024 ); if (cache_info.dc_loop != 1) snprintf(buf, 32, "%lu-way associative", cache_info.dc_loop); - seq_printf(m, "D-cache\t\t: %ld KB (%s%s, %s)\n", + seq_printf(m, "D-cache\t\t: %ld KB (%s%s, %s, alias=%d)\n", cache_info.dc_size/1024, (cache_info.dc_conf.cc_wt ? "WT":"WB"), (cache_info.dc_conf.cc_sh ? ", shared I/D":""), - ((cache_info.dc_loop == 1) ? "direct mapped" : buf)); + ((cache_info.dc_loop == 1) ? "direct mapped" : buf), + cache_info.dc_conf.cc_alias + ); seq_printf(m, "ITLB entries\t: %ld\n" "DTLB entries\t: %ld%s\n", cache_info.it_size, cache_info.dt_size, @@ -324,25 +327,81 @@ __flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, preempt_enable(); } -static inline void -__purge_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, - unsigned long physaddr) +static void flush_user_cache_page(struct vm_area_struct *vma, unsigned long vmaddr) { - if (!static_branch_likely(&parisc_has_cache)) - return; + unsigned long flags, space, pgd, prot; +#ifdef CONFIG_TLB_PTLOCK + unsigned long pgd_lock; +#endif + + vmaddr &= PAGE_MASK; + preempt_disable(); - purge_dcache_page_asm(physaddr, vmaddr); + + /* Set context for flush */ + local_irq_save(flags); + prot = mfctl(8); + space = mfsp(SR_USER); + pgd = mfctl(25); +#ifdef CONFIG_TLB_PTLOCK + pgd_lock = mfctl(28); +#endif + switch_mm_irqs_off(NULL, vma->vm_mm, NULL); + local_irq_restore(flags); + + flush_user_dcache_range_asm(vmaddr, vmaddr + PAGE_SIZE); if (vma->vm_flags & VM_EXEC) - flush_icache_page_asm(physaddr, vmaddr); + flush_user_icache_range_asm(vmaddr, vmaddr + PAGE_SIZE); + flush_tlb_page(vma, vmaddr); + + /* Restore previous context */ + local_irq_save(flags); +#ifdef CONFIG_TLB_PTLOCK + mtctl(pgd_lock, 28); +#endif + mtctl(pgd, 25); + mtsp(space, SR_USER); + mtctl(prot, 8); + local_irq_restore(flags); + preempt_enable(); } +static inline pte_t *get_ptep(struct mm_struct *mm, unsigned long addr) +{ + pte_t *ptep = NULL; + pgd_t *pgd = mm->pgd; + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + + if (!pgd_none(*pgd)) { + p4d = p4d_offset(pgd, addr); + if (!p4d_none(*p4d)) { + pud = pud_offset(p4d, addr); + if (!pud_none(*pud)) { + pmd = pmd_offset(pud, addr); + if (!pmd_none(*pmd)) + ptep = pte_offset_map(pmd, addr); + } + } + } + return ptep; +} + +static inline bool pte_needs_flush(pte_t pte) +{ + return (pte_val(pte) & (_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_NO_CACHE)) + == (_PAGE_PRESENT | _PAGE_ACCESSED); +} + void flush_dcache_page(struct page *page) { struct address_space *mapping = page_mapping_file(page); struct vm_area_struct *mpnt; unsigned long offset; unsigned long addr, old_addr = 0; + unsigned long count = 0; pgoff_t pgoff; if (mapping && !mapping_mapped(mapping)) { @@ -357,33 +416,52 @@ void flush_dcache_page(struct page *page) pgoff = page->index; - /* We have carefully arranged in arch_get_unmapped_area() that + /* + * We have carefully arranged in arch_get_unmapped_area() that * *any* mappings of a file are always congruently mapped (whether * declared as MAP_PRIVATE or MAP_SHARED), so we only need - * to flush one address here for them all to become coherent */ - + * to flush one address here for them all to become coherent + * on machines that support equivalent aliasing + */ flush_dcache_mmap_lock(mapping); vma_interval_tree_foreach(mpnt, &mapping->i_mmap, pgoff, pgoff) { offset = (pgoff - mpnt->vm_pgoff) << PAGE_SHIFT; addr = mpnt->vm_start + offset; + if (parisc_requires_coherency()) { + pte_t *ptep; - /* The TLB is the engine of coherence on parisc: The - * CPU is entitled to speculate any page with a TLB - * mapping, so here we kill the mapping then flush the - * page along a special flush only alias mapping. - * This guarantees that the page is no-longer in the - * cache for any process and nor may it be - * speculatively read in (until the user or kernel - * specifically accesses it, of course) */ - - flush_tlb_page(mpnt, addr); - if (old_addr == 0 || (old_addr & (SHM_COLOUR - 1)) - != (addr & (SHM_COLOUR - 1))) { - __flush_cache_page(mpnt, addr, page_to_phys(page)); - if (parisc_requires_coherency() && old_addr) - printk(KERN_ERR "INEQUIVALENT ALIASES 0x%lx and 0x%lx in file %pD\n", old_addr, addr, mpnt->vm_file); - old_addr = addr; + ptep = get_ptep(mpnt->vm_mm, addr); + if (ptep && pte_needs_flush(*ptep)) + flush_user_cache_page(mpnt, addr); + } else { + /* + * The TLB is the engine of coherence on parisc: + * The CPU is entitled to speculate any page + * with a TLB mapping, so here we kill the + * mapping then flush the page along a special + * flush only alias mapping. This guarantees that + * the page is no-longer in the cache for any + * process and nor may it be speculatively read + * in (until the user or kernel specifically + * accesses it, of course) + */ + flush_tlb_page(mpnt, addr); + if (old_addr == 0 || (old_addr & (SHM_COLOUR - 1)) + != (addr & (SHM_COLOUR - 1))) { + __flush_cache_page(mpnt, addr, page_to_phys(page)); + /* + * Software is allowed to have any number + * of private mappings to a page. + */ + if (!(mpnt->vm_flags & VM_SHARED)) + continue; + if (old_addr) + pr_err("INEQUIVALENT ALIASES 0x%lx and 0x%lx in file %pD\n", + old_addr, addr, mpnt->vm_file); + old_addr = addr; + } } + WARN_ON(++count == 4096); } flush_dcache_mmap_unlock(mapping); } @@ -417,23 +495,16 @@ void __init parisc_setup_cache_timing(void) printk(KERN_DEBUG "Whole cache flush %lu cycles, flushing %lu bytes %lu cycles\n", alltime, size, rangetime); - threshold = L1_CACHE_ALIGN(size * alltime / rangetime); + threshold = L1_CACHE_ALIGN((unsigned long)((uint64_t)size * alltime / rangetime)); + pr_info("Calculated flush threshold is %lu KiB\n", + threshold/1024); /* - * The threshold computed above isn't very reliable since the - * flush times depend greatly on the percentage of dirty lines - * in the flush range. Further, the whole cache time doesn't - * include the time to refill lines that aren't in the mm/vma - * being flushed. By timing glibc build and checks on mako cpus, - * the following formula seems to work reasonably well. The - * value from the timing calculation is too small, and increases - * build and check times by almost a factor two. + * The threshold computed above isn't very reliable. The following + * heuristic works reasonably well on c8000/rp3440. */ threshold2 = cache_info.dc_size * num_online_cpus(); - if (threshold2 > threshold) - threshold = threshold2; - if (threshold) - parisc_cache_flush_threshold = threshold; + parisc_cache_flush_threshold = threshold2; printk(KERN_INFO "Cache flush threshold set to %lu KiB\n", parisc_cache_flush_threshold/1024); @@ -489,19 +560,47 @@ void flush_kernel_dcache_page_addr(void *addr) } EXPORT_SYMBOL(flush_kernel_dcache_page_addr); -void copy_user_page(void *vto, void *vfrom, unsigned long vaddr, - struct page *pg) +static void flush_cache_page_if_present(struct vm_area_struct *vma, + unsigned long vmaddr, unsigned long pfn) { - /* Copy using kernel mapping. No coherency is needed (all in - kunmap) for the `to' page. However, the `from' page needs to - be flushed through a mapping equivalent to the user mapping - before it can be accessed through the kernel mapping. */ - preempt_disable(); - flush_dcache_page_asm(__pa(vfrom), vaddr); - copy_page_asm(vto, vfrom); - preempt_enable(); + pte_t *ptep = get_ptep(vma->vm_mm, vmaddr); + + /* + * The pte check is racy and sometimes the flush will trigger + * a non-access TLB miss. Hopefully, the page has already been + * flushed. + */ + if (ptep && pte_needs_flush(*ptep)) + flush_cache_page(vma, vmaddr, pfn); +} + +void copy_user_highpage(struct page *to, struct page *from, + unsigned long vaddr, struct vm_area_struct *vma) +{ + void *kto, *kfrom; + + kfrom = kmap_local_page(from); + kto = kmap_local_page(to); + flush_cache_page_if_present(vma, vaddr, page_to_pfn(from)); + copy_page_asm(kto, kfrom); + kunmap_local(kto); + kunmap_local(kfrom); +} + +void copy_to_user_page(struct vm_area_struct *vma, struct page *page, + unsigned long user_vaddr, void *dst, void *src, int len) +{ + flush_cache_page_if_present(vma, user_vaddr, page_to_pfn(page)); + memcpy(dst, src, len); + flush_kernel_dcache_range_asm((unsigned long)dst, (unsigned long)dst + len); +} + +void copy_from_user_page(struct vm_area_struct *vma, struct page *page, + unsigned long user_vaddr, void *dst, void *src, int len) +{ + flush_cache_page_if_present(vma, user_vaddr, page_to_pfn(page)); + memcpy(dst, src, len); } -EXPORT_SYMBOL(copy_user_page); /* __flush_tlb_range() * @@ -532,92 +631,105 @@ int __flush_tlb_range(unsigned long sid, unsigned long start, return 0; } -static inline unsigned long mm_total_size(struct mm_struct *mm) +static void flush_cache_pages(struct vm_area_struct *vma, unsigned long start, unsigned long end) { - struct vm_area_struct *vma; - unsigned long usize = 0; - - for (vma = mm->mmap; vma; vma = vma->vm_next) - usize += vma->vm_end - vma->vm_start; - return usize; -} - -static inline pte_t *get_ptep(pgd_t *pgd, unsigned long addr) -{ - pte_t *ptep = NULL; + unsigned long addr, pfn; + pte_t *ptep; - if (!pgd_none(*pgd)) { - p4d_t *p4d = p4d_offset(pgd, addr); - if (!p4d_none(*p4d)) { - pud_t *pud = pud_offset(p4d, addr); - if (!pud_none(*pud)) { - pmd_t *pmd = pmd_offset(pud, addr); - if (!pmd_none(*pmd)) - ptep = pte_offset_map(pmd, addr); + for (addr = start; addr < end; addr += PAGE_SIZE) { + /* + * The vma can contain pages that aren't present. Although + * the pte search is expensive, we need the pte to find the + * page pfn and to check whether the page should be flushed. + */ + ptep = get_ptep(vma->vm_mm, addr); + if (ptep && pte_needs_flush(*ptep)) { + if (parisc_requires_coherency()) { + flush_user_cache_page(vma, addr); + } else { + pfn = pte_pfn(*ptep); + if (WARN_ON(!pfn_valid(pfn))) + return; + __flush_cache_page(vma, addr, PFN_PHYS(pfn)); } } } - return ptep; } -static void flush_cache_pages(struct vm_area_struct *vma, struct mm_struct *mm, - unsigned long start, unsigned long end) +static inline unsigned long mm_total_size(struct mm_struct *mm) { - unsigned long addr, pfn; - pte_t *ptep; + struct vm_area_struct *vma; + unsigned long usize = 0; - for (addr = start; addr < end; addr += PAGE_SIZE) { - ptep = get_ptep(mm->pgd, addr); - if (ptep) { - pfn = pte_pfn(*ptep); - flush_cache_page(vma, addr, pfn); - } - } + for (vma = mm->mmap; vma && usize < parisc_cache_flush_threshold; vma = vma->vm_next) + usize += vma->vm_end - vma->vm_start; + return usize; } void flush_cache_mm(struct mm_struct *mm) { struct vm_area_struct *vma; - /* Flushing the whole cache on each cpu takes forever on - rp3440, etc. So, avoid it if the mm isn't too big. */ - if ((!IS_ENABLED(CONFIG_SMP) || !arch_irqs_disabled()) && - mm_total_size(mm) >= parisc_cache_flush_threshold) { - if (mm->context.space_id) - flush_tlb_all(); + /* + * Flushing the whole cache on each cpu takes forever on + * rp3440, etc. So, avoid it if the mm isn't too big. + * + * Note that we must flush the entire cache on machines + * with aliasing caches to prevent random segmentation + * faults. + */ + if (!parisc_requires_coherency() + || mm_total_size(mm) >= parisc_cache_flush_threshold) { + if (WARN_ON(IS_ENABLED(CONFIG_SMP) && arch_irqs_disabled())) + return; + flush_tlb_all(); flush_cache_all(); return; } + /* Flush mm */ for (vma = mm->mmap; vma; vma = vma->vm_next) - flush_cache_pages(vma, mm, vma->vm_start, vma->vm_end); + flush_cache_pages(vma, vma->vm_start, vma->vm_end); } -void flush_cache_range(struct vm_area_struct *vma, - unsigned long start, unsigned long end) +void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end) { - if ((!IS_ENABLED(CONFIG_SMP) || !arch_irqs_disabled()) && - end - start >= parisc_cache_flush_threshold) { - if (vma->vm_mm->context.space_id) - flush_tlb_range(vma, start, end); + if (!parisc_requires_coherency() + || end - start >= parisc_cache_flush_threshold) { + if (WARN_ON(IS_ENABLED(CONFIG_SMP) && arch_irqs_disabled())) + return; + flush_tlb_range(vma, start, end); flush_cache_all(); return; } - flush_cache_pages(vma, vma->vm_mm, start, end); + flush_cache_pages(vma, start, end); } -void -flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, unsigned long pfn) +void flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, unsigned long pfn) { - if (pfn_valid(pfn)) { - if (likely(vma->vm_mm->context.space_id)) { - flush_tlb_page(vma, vmaddr); - __flush_cache_page(vma, vmaddr, PFN_PHYS(pfn)); - } else { - __purge_cache_page(vma, vmaddr, PFN_PHYS(pfn)); - } + if (WARN_ON(!pfn_valid(pfn))) + return; + if (parisc_requires_coherency()) + flush_user_cache_page(vma, vmaddr); + else + __flush_cache_page(vma, vmaddr, PFN_PHYS(pfn)); +} + +void flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned long vmaddr) +{ + if (!PageAnon(page)) + return; + + if (parisc_requires_coherency()) { + flush_user_cache_page(vma, vmaddr); + return; } + + flush_tlb_page(vma, vmaddr); + preempt_disable(); + flush_dcache_page_asm(page_to_phys(page), vmaddr); + preempt_enable(); } void flush_kernel_vmap_range(void *vaddr, int size) diff --git a/arch/parisc/kernel/kprobes.c b/arch/parisc/kernel/kprobes.c index 3343d2fb7889..6e0b86652f30 100644 --- a/arch/parisc/kernel/kprobes.c +++ b/arch/parisc/kernel/kprobes.c @@ -152,7 +152,7 @@ int __kprobes parisc_kprobe_ss_handler(struct pt_regs *regs) /* for absolute branch instructions we can copy iaoq_b. for relative * branch instructions we need to calculate the new address based on the * difference between iaoq_f and iaoq_b. We cannot use iaoq_b without - * modificationt because it's based on our ainsn.insn address. + * modifications because it's based on our ainsn.insn address. */ if (p->post_handler) diff --git a/arch/parisc/kernel/processor.c b/arch/parisc/kernel/processor.c index d98692115221..26eb568f8b96 100644 --- a/arch/parisc/kernel/processor.c +++ b/arch/parisc/kernel/processor.c @@ -171,6 +171,7 @@ static int __init processor_probe(struct parisc_device *dev) p->cpu_num = cpu_info.cpu_num; p->cpu_loc = cpu_info.cpu_loc; + set_cpu_possible(cpuid, true); store_cpu_topology(cpuid); #ifdef CONFIG_SMP @@ -419,8 +420,7 @@ show_cpuinfo (struct seq_file *m, void *v) } seq_printf(m, " (0x%02lx)\n", boot_cpu_data.pdc.capabilities); - seq_printf(m, "model\t\t: %s\n" - "model name\t: %s\n", + seq_printf(m, "model\t\t: %s - %s\n", boot_cpu_data.pdc.sys_model_name, cpuinfo->dev ? cpuinfo->dev->name : "Unknown"); @@ -461,6 +461,13 @@ static struct parisc_driver cpu_driver __refdata = { */ void __init processor_init(void) { + unsigned int cpu; + reset_cpu_topology(); + + /* reset possible mask. We will mark those which are possible. */ + for_each_possible_cpu(cpu) + set_cpu_possible(cpu, false); + register_parisc_driver(&cpu_driver); } diff --git a/arch/parisc/kernel/setup.c b/arch/parisc/kernel/setup.c index b91cb45ffd4e..f005ddedb50e 100644 --- a/arch/parisc/kernel/setup.c +++ b/arch/parisc/kernel/setup.c @@ -161,6 +161,8 @@ void __init setup_arch(char **cmdline_p) #ifdef CONFIG_PA11 dma_ops_init(); #endif + + clear_sched_clock_stable(); } /* diff --git a/arch/parisc/kernel/time.c b/arch/parisc/kernel/time.c index bb27dfeeddfc..9714fbd7c42d 100644 --- a/arch/parisc/kernel/time.c +++ b/arch/parisc/kernel/time.c @@ -251,13 +251,9 @@ void __init time_init(void) static int __init init_cr16_clocksource(void) { /* - * The cr16 interval timers are not syncronized across CPUs, even if - * they share the same socket. + * The cr16 interval timers are not synchronized across CPUs. */ if (num_online_cpus() > 1 && !running_on_qemu) { - /* mark sched_clock unstable */ - clear_sched_clock_stable(); - clocksource_cr16.name = "cr16_unstable"; clocksource_cr16.flags = CLOCK_SOURCE_UNSTABLE; clocksource_cr16.rating = 0; diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c index a6e61cf2cad0..b78f1b9d45c1 100644 --- a/arch/parisc/kernel/traps.c +++ b/arch/parisc/kernel/traps.c @@ -469,7 +469,7 @@ void parisc_terminate(char *msg, struct pt_regs *regs, int code, unsigned long o * panic notifiers, and we should call panic * directly from the location that we wish. * e.g. We should not call panic from - * parisc_terminate, but rather the oter way around. + * parisc_terminate, but rather the other way around. * This hack works, prints the panic message twice, * and it enables reboot timers! */ diff --git a/arch/parisc/math-emu/dfadd.c b/arch/parisc/math-emu/dfadd.c index ec487e07f004..00e561d4aa55 100644 --- a/arch/parisc/math-emu/dfadd.c +++ b/arch/parisc/math-emu/dfadd.c @@ -253,7 +253,7 @@ dbl_fadd( return(NOEXCEPTION); } right_exponent = 1; /* Set exponent to reflect different bias - * with denomalized numbers. */ + * with denormalized numbers. */ } else { diff --git a/arch/parisc/math-emu/dfsub.c b/arch/parisc/math-emu/dfsub.c index c4f30acf2d48..4f03782284bd 100644 --- a/arch/parisc/math-emu/dfsub.c +++ b/arch/parisc/math-emu/dfsub.c @@ -256,7 +256,7 @@ dbl_fsub( return(NOEXCEPTION); } right_exponent = 1; /* Set exponent to reflect different bias - * with denomalized numbers. */ + * with denormalized numbers. */ } else { diff --git a/arch/parisc/math-emu/sfadd.c b/arch/parisc/math-emu/sfadd.c index 838758279d5b..9b98c874dfac 100644 --- a/arch/parisc/math-emu/sfadd.c +++ b/arch/parisc/math-emu/sfadd.c @@ -249,7 +249,7 @@ sgl_fadd( return(NOEXCEPTION); } right_exponent = 1; /* Set exponent to reflect different bias - * with denomalized numbers. */ + * with denormalized numbers. */ } else { diff --git a/arch/parisc/math-emu/sfsub.c b/arch/parisc/math-emu/sfsub.c index 583d3ace4634..29d9eed09d12 100644 --- a/arch/parisc/math-emu/sfsub.c +++ b/arch/parisc/math-emu/sfsub.c @@ -252,7 +252,7 @@ sgl_fsub( return(NOEXCEPTION); } right_exponent = 1; /* Set exponent to reflect different bias - * with denomalized numbers. */ + * with denormalized numbers. */ } else { diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c index f114e102aaf2..84bc437be5cd 100644 --- a/arch/parisc/mm/fault.c +++ b/arch/parisc/mm/fault.c @@ -22,6 +22,8 @@ #include <asm/traps.h> +#define DEBUG_NATLB 0 + /* Various important other fields */ #define bit22set(x) (x & 0x00000200) #define bits23_25set(x) (x & 0x000001c0) @@ -450,8 +452,8 @@ handle_nadtlb_fault(struct pt_regs *regs) fallthrough; case 0x380: /* PDC and FIC instructions */ - if (printk_ratelimit()) { - pr_warn("BUG: nullifying cache flush/purge instruction\n"); + if (DEBUG_NATLB && printk_ratelimit()) { + pr_warn("WARNING: nullifying cache flush/purge instruction\n"); show_regs(regs); } if (insn & 0x20) { diff --git a/arch/powerpc/include/asm/bug.h b/arch/powerpc/include/asm/bug.h index ecbae1832de3..61a4736355c2 100644 --- a/arch/powerpc/include/asm/bug.h +++ b/arch/powerpc/include/asm/bug.h @@ -13,7 +13,8 @@ #ifdef CONFIG_DEBUG_BUGVERBOSE .macro __EMIT_BUG_ENTRY addr,file,line,flags .section __bug_table,"aw" -5001: .4byte \addr - 5001b, 5002f - 5001b +5001: .4byte \addr - . + .4byte 5002f - . .short \line, \flags .org 5001b+BUG_ENTRY_SIZE .previous @@ -24,7 +25,7 @@ #else .macro __EMIT_BUG_ENTRY addr,file,line,flags .section __bug_table,"aw" -5001: .4byte \addr - 5001b +5001: .4byte \addr - . .short \flags .org 5001b+BUG_ENTRY_SIZE .previous @@ -49,15 +50,16 @@ #ifdef CONFIG_DEBUG_BUGVERBOSE #define _EMIT_BUG_ENTRY \ ".section __bug_table,\"aw\"\n" \ - "2:\t.4byte 1b - 2b, %0 - 2b\n" \ - "\t.short %1, %2\n" \ + "2: .4byte 1b - .\n" \ + " .4byte %0 - .\n" \ + " .short %1, %2\n" \ ".org 2b+%3\n" \ ".previous\n" #else #define _EMIT_BUG_ENTRY \ ".section __bug_table,\"aw\"\n" \ - "2:\t.4byte 1b - 2b\n" \ - "\t.short %2\n" \ + "2: .4byte 1b - .\n" \ + " .short %2\n" \ ".org 2b+%3\n" \ ".previous\n" #endif diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h index 827038a33064..4def2bd17b9b 100644 --- a/arch/powerpc/include/asm/kvm_book3s_64.h +++ b/arch/powerpc/include/asm/kvm_book3s_64.h @@ -16,18 +16,6 @@ #include <asm/ppc-opcode.h> #include <asm/pte-walk.h> -#ifdef CONFIG_PPC_PSERIES -static inline bool kvmhv_on_pseries(void) -{ - return !cpu_has_feature(CPU_FTR_HVMODE); -} -#else -static inline bool kvmhv_on_pseries(void) -{ - return false; -} -#endif - /* * Structure for a nested guest, that is, for a guest that is managed by * one of our guests. diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index c583d0c37f31..838d4cb460b7 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -586,6 +586,18 @@ static inline bool kvm_hv_mode_active(void) { return false; } #endif +#ifdef CONFIG_PPC_PSERIES +static inline bool kvmhv_on_pseries(void) +{ + return !cpu_has_feature(CPU_FTR_HVMODE); +} +#else +static inline bool kvmhv_on_pseries(void) +{ + return false; +} +#endif + #ifdef CONFIG_KVM_XICS static inline int kvmppc_xics_enabled(struct kvm_vcpu *vcpu) { diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h index 254687258f42..f2c5c26869f1 100644 --- a/arch/powerpc/include/asm/page.h +++ b/arch/powerpc/include/asm/page.h @@ -132,7 +132,11 @@ static inline bool pfn_valid(unsigned long pfn) #define virt_to_page(kaddr) pfn_to_page(virt_to_pfn(kaddr)) #define pfn_to_kaddr(pfn) __va((pfn) << PAGE_SHIFT) -#define virt_addr_valid(kaddr) pfn_valid(virt_to_pfn(kaddr)) +#define virt_addr_valid(vaddr) ({ \ + unsigned long _addr = (unsigned long)vaddr; \ + _addr >= PAGE_OFFSET && _addr < (unsigned long)high_memory && \ + pfn_valid(virt_to_pfn(_addr)); \ +}) /* * On Book-E parts we need __va to parse the device tree and we can't diff --git a/arch/powerpc/include/asm/setup.h b/arch/powerpc/include/asm/setup.h index 049ca26893e6..8fa37ef5da4d 100644 --- a/arch/powerpc/include/asm/setup.h +++ b/arch/powerpc/include/asm/setup.h @@ -28,11 +28,13 @@ void setup_panic(void); #define ARCH_PANIC_TIMEOUT 180 #ifdef CONFIG_PPC_PSERIES +extern bool pseries_reloc_on_exception(void); extern bool pseries_enable_reloc_on_exc(void); extern void pseries_disable_reloc_on_exc(void); extern void pseries_big_endian_exceptions(void); void __init pseries_little_endian_exceptions(void); #else +static inline bool pseries_reloc_on_exception(void) { return false; } static inline bool pseries_enable_reloc_on_exc(void) { return false; } static inline void pseries_disable_reloc_on_exc(void) {} static inline void pseries_big_endian_exceptions(void) {} diff --git a/arch/powerpc/include/asm/static_call.h b/arch/powerpc/include/asm/static_call.h index 0a0bc79bd1fa..de1018cc522b 100644 --- a/arch/powerpc/include/asm/static_call.h +++ b/arch/powerpc/include/asm/static_call.h @@ -24,5 +24,6 @@ #define ARCH_DEFINE_STATIC_CALL_TRAMP(name, func) __PPC_SCT(name, "b " #func) #define ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name) __PPC_SCT(name, "blr") +#define ARCH_DEFINE_STATIC_CALL_RET0_TRAMP(name) __PPC_SCT(name, "b .+20") #endif /* _ASM_POWERPC_STATIC_CALL_H */ diff --git a/arch/powerpc/include/asm/timex.h b/arch/powerpc/include/asm/timex.h index fa2e76e4093a..14b4489de52c 100644 --- a/arch/powerpc/include/asm/timex.h +++ b/arch/powerpc/include/asm/timex.h @@ -19,6 +19,7 @@ static inline cycles_t get_cycles(void) { return mftb(); } +#define get_cycles get_cycles #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_TIMEX_H */ diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 55caeee37c08..b66dd6f775a4 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -809,6 +809,10 @@ __start_interrupts: * - MSR_EE|MSR_RI is clear (no reentrant exceptions) * - Standard kernel environment is set up (stack, paca, etc) * + * KVM: + * These interrupts do not elevate HV 0->1, so HV is not involved. PR KVM + * ensures that FSCR[SCV] is disabled whenever it has to force AIL off. + * * Call convention: * * syscall register convention is in Documentation/powerpc/syscall64-abi.rst diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c index 65562c4a0a69..4c09c6688ac6 100644 --- a/arch/powerpc/kernel/fadump.c +++ b/arch/powerpc/kernel/fadump.c @@ -752,7 +752,7 @@ u32 *__init fadump_regs_to_elf_notes(u32 *buf, struct pt_regs *regs) * FIXME: How do i get PID? Do I really need it? * prstatus.pr_pid = ???? */ - elf_core_copy_kernel_regs(&prstatus.pr_reg, regs); + elf_core_copy_regs(&prstatus.pr_reg, regs); buf = append_elf_note(buf, CRASH_CORE_NOTE_NAME, NT_PRSTATUS, &prstatus, sizeof(prstatus)); return buf; diff --git a/arch/powerpc/kernel/module.c b/arch/powerpc/kernel/module.c index 40a583e9d3c7..97a76a8619fb 100644 --- a/arch/powerpc/kernel/module.c +++ b/arch/powerpc/kernel/module.c @@ -101,7 +101,7 @@ __module_alloc(unsigned long size, unsigned long start, unsigned long end, bool * too. */ return __vmalloc_node_range(size, 1, start, end, gfp, prot, - VM_FLUSH_RESET_PERMS | VM_NO_HUGE_VMAP, + VM_FLUSH_RESET_PERMS, NUMA_NO_NODE, __builtin_return_address(0)); } diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index e547066a06aa..a96f05063bc9 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -196,6 +196,34 @@ static void __init configure_exceptions(void) /* Under a PAPR hypervisor, we need hypercalls */ if (firmware_has_feature(FW_FEATURE_SET_MODE)) { + /* + * - PR KVM does not support AIL mode interrupts in the host + * while a PR guest is running. + * + * - SCV system call interrupt vectors are only implemented for + * AIL mode interrupts. + * + * - On pseries, AIL mode can only be enabled and disabled + * system-wide so when a PR VM is created on a pseries host, + * all CPUs of the host are set to AIL=0 mode. + * + * - Therefore host CPUs must not execute scv while a PR VM + * exists. + * + * - SCV support can not be disabled dynamically because the + * feature is advertised to host userspace. Disabling the + * facility and emulating it would be possible but is not + * implemented. + * + * - So SCV support is blanket disabled if PR KVM could possibly + * run. That is, PR support compiled in, booting on pseries + * with hash MMU. + */ + if (IS_ENABLED(CONFIG_KVM_BOOK3S_PR_POSSIBLE) && !radix_enabled()) { + init_task.thread.fscr &= ~FSCR_SCV; + cur_cpu_spec->cpu_user_features2 &= ~PPC_FEATURE2_SCV; + } + /* Enable AIL if possible */ if (!pseries_enable_reloc_on_exc()) { init_task.thread.fscr &= ~FSCR_SCV; diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index f5cbfe5efd25..f80cce0e3899 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -615,23 +615,22 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(timer_interrupt) return; } - /* Conditionally hard-enable interrupts. */ - if (should_hard_irq_enable()) { - /* - * Ensure a positive value is written to the decrementer, or - * else some CPUs will continue to take decrementer exceptions. - * When the PPC_WATCHDOG (decrementer based) is configured, - * keep this at most 31 bits, which is about 4 seconds on most - * systems, which gives the watchdog a chance of catching timer - * interrupt hard lockups. - */ - if (IS_ENABLED(CONFIG_PPC_WATCHDOG)) - set_dec(0x7fffffff); - else - set_dec(decrementer_max); + /* + * Ensure a positive value is written to the decrementer, or + * else some CPUs will continue to take decrementer exceptions. + * When the PPC_WATCHDOG (decrementer based) is configured, + * keep this at most 31 bits, which is about 4 seconds on most + * systems, which gives the watchdog a chance of catching timer + * interrupt hard lockups. + */ + if (IS_ENABLED(CONFIG_PPC_WATCHDOG)) + set_dec(0x7fffffff); + else + set_dec(decrementer_max); + /* Conditionally hard-enable interrupts. */ + if (should_hard_irq_enable()) do_hard_irq_enable(); - } #if defined(CONFIG_PPC32) && defined(CONFIG_PPC_PMAC) if (atomic_read(&ppc_n_lost_interrupts) != 0) diff --git a/arch/powerpc/kernel/vdso/gettimeofday.S b/arch/powerpc/kernel/vdso/gettimeofday.S index eb9c81e1c218..0c4ecc8fec5a 100644 --- a/arch/powerpc/kernel/vdso/gettimeofday.S +++ b/arch/powerpc/kernel/vdso/gettimeofday.S @@ -22,12 +22,15 @@ .macro cvdso_call funct call_time=0 .cfi_startproc PPC_STLU r1, -PPC_MIN_STKFRM(r1) + .cfi_adjust_cfa_offset PPC_MIN_STKFRM mflr r0 - .cfi_register lr, r0 PPC_STLU r1, -PPC_MIN_STKFRM(r1) + .cfi_adjust_cfa_offset PPC_MIN_STKFRM PPC_STL r0, PPC_MIN_STKFRM + PPC_LR_STKOFF(r1) + .cfi_rel_offset lr, PPC_MIN_STKFRM + PPC_LR_STKOFF #ifdef __powerpc64__ PPC_STL r2, PPC_MIN_STKFRM + STK_GOT(r1) + .cfi_rel_offset r2, PPC_MIN_STKFRM + STK_GOT #endif get_datapage r5 .ifeq \call_time @@ -39,13 +42,15 @@ PPC_LL r0, PPC_MIN_STKFRM + PPC_LR_STKOFF(r1) #ifdef __powerpc64__ PPC_LL r2, PPC_MIN_STKFRM + STK_GOT(r1) + .cfi_restore r2 #endif .ifeq \call_time cmpwi r3, 0 .endif mtlr r0 - .cfi_restore lr addi r1, r1, 2 * PPC_MIN_STKFRM + .cfi_restore lr + .cfi_def_cfa_offset 0 crclr so .ifeq \call_time beqlr+ diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig index 18e58085447c..ddd88179110a 100644 --- a/arch/powerpc/kvm/Kconfig +++ b/arch/powerpc/kvm/Kconfig @@ -112,12 +112,21 @@ config KVM_BOOK3S_64_PR guest in user mode (problem state) and emulating all privileged instructions and registers. + This is only available for hash MMU mode and only supports + guests that use hash MMU mode. + This is not as fast as using hypervisor mode, but works on machines where hypervisor mode is not available or not usable, and can emulate processors that are different from the host processor, including emulating 32-bit processors on a 64-bit host. + Selecting this option will cause the SCV facility to be + disabled when the kernel is booted on the pseries platform in + hash MMU mode (regardless of PR VMs running). When any PR VMs + are running, "AIL" mode is disabled which may slow interrupts + and system calls on the host. + config KVM_BOOK3S_HV_EXIT_TIMING bool "Detailed timing for hypervisor real-mode code" depends on KVM_BOOK3S_HV_POSSIBLE && DEBUG_FS diff --git a/arch/powerpc/kvm/book3s_32_sr.S b/arch/powerpc/kvm/book3s_32_sr.S index e3ab9df6cf19..6cfcd20d4668 100644 --- a/arch/powerpc/kvm/book3s_32_sr.S +++ b/arch/powerpc/kvm/book3s_32_sr.S @@ -122,11 +122,27 @@ /* 0x0 - 0xb */ - /* 'current->mm' needs to be in r4 */ - tophys(r4, r2) - lwz r4, MM(r4) - tophys(r4, r4) - /* This only clobbers r0, r3, r4 and r5 */ + /* switch_mmu_context() needs paging, let's enable it */ + mfmsr r9 + ori r11, r9, MSR_DR + mtmsr r11 + sync + + /* switch_mmu_context() clobbers r12, rescue it */ + SAVE_GPR(12, r1) + + /* Calling switch_mmu_context(<inv>, current->mm, <inv>); */ + lwz r4, MM(r2) bl switch_mmu_context + /* restore r12 */ + REST_GPR(12, r1) + + /* Disable paging again */ + mfmsr r9 + li r6, MSR_DR + andc r9, r9, r6 + mtmsr r9 + sync + .endm diff --git a/arch/powerpc/kvm/book3s_64_entry.S b/arch/powerpc/kvm/book3s_64_entry.S index 05e003eb5d90..e42d1c609e47 100644 --- a/arch/powerpc/kvm/book3s_64_entry.S +++ b/arch/powerpc/kvm/book3s_64_entry.S @@ -414,10 +414,16 @@ END_FTR_SECTION_IFSET(CPU_FTR_DAWR1) */ ld r10,HSTATE_SCRATCH0(r13) cmpwi r10,BOOK3S_INTERRUPT_MACHINE_CHECK - beq machine_check_common + beq .Lcall_machine_check_common cmpwi r10,BOOK3S_INTERRUPT_SYSTEM_RESET - beq system_reset_common + beq .Lcall_system_reset_common b . + +.Lcall_machine_check_common: + b machine_check_common + +.Lcall_system_reset_common: + b system_reset_common #endif diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c index e4ce2a35483f..42851c32ff3b 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_radix.c +++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c @@ -168,9 +168,10 @@ int kvmppc_mmu_walk_radix_tree(struct kvm_vcpu *vcpu, gva_t eaddr, return -EINVAL; /* Read the entry from guest memory */ addr = base + (index * sizeof(rpte)); - vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); + + kvm_vcpu_srcu_read_lock(vcpu); ret = kvm_read_guest(kvm, addr, &rpte, sizeof(rpte)); - srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); if (ret) { if (pte_ret_p) *pte_ret_p = addr; @@ -246,9 +247,9 @@ int kvmppc_mmu_radix_translate_table(struct kvm_vcpu *vcpu, gva_t eaddr, /* Read the table to find the root of the radix tree */ ptbl = (table & PRTB_MASK) + (table_index * sizeof(entry)); - vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); ret = kvm_read_guest(kvm, ptbl, &entry, sizeof(entry)); - srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); if (ret) return ret; diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c index d42b4b6d4a79..85cfa6328222 100644 --- a/arch/powerpc/kvm/book3s_64_vio.c +++ b/arch/powerpc/kvm/book3s_64_vio.c @@ -420,13 +420,19 @@ static void kvmppc_tce_put(struct kvmppc_spapr_tce_table *stt, tbl[idx % TCES_PER_PAGE] = tce; } -static void kvmppc_clear_tce(struct mm_struct *mm, struct iommu_table *tbl, - unsigned long entry) +static void kvmppc_clear_tce(struct mm_struct *mm, struct kvmppc_spapr_tce_table *stt, + struct iommu_table *tbl, unsigned long entry) { - unsigned long hpa = 0; - enum dma_data_direction dir = DMA_NONE; + unsigned long i; + unsigned long subpages = 1ULL << (stt->page_shift - tbl->it_page_shift); + unsigned long io_entry = entry << (stt->page_shift - tbl->it_page_shift); + + for (i = 0; i < subpages; ++i) { + unsigned long hpa = 0; + enum dma_data_direction dir = DMA_NONE; - iommu_tce_xchg_no_kill(mm, tbl, entry, &hpa, &dir); + iommu_tce_xchg_no_kill(mm, tbl, io_entry + i, &hpa, &dir); + } } static long kvmppc_tce_iommu_mapped_dec(struct kvm *kvm, @@ -485,6 +491,8 @@ static long kvmppc_tce_iommu_unmap(struct kvm *kvm, break; } + iommu_tce_kill(tbl, io_entry, subpages); + return ret; } @@ -544,6 +552,8 @@ static long kvmppc_tce_iommu_map(struct kvm *kvm, break; } + iommu_tce_kill(tbl, io_entry, subpages); + return ret; } @@ -590,10 +600,9 @@ long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn, ret = kvmppc_tce_iommu_map(vcpu->kvm, stt, stit->tbl, entry, ua, dir); - iommu_tce_kill(stit->tbl, entry, 1); if (ret != H_SUCCESS) { - kvmppc_clear_tce(vcpu->kvm->mm, stit->tbl, entry); + kvmppc_clear_tce(vcpu->kvm->mm, stt, stit->tbl, entry); goto unlock_exit; } } @@ -669,13 +678,13 @@ long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu, */ if (get_user(tce, tces + i)) { ret = H_TOO_HARD; - goto invalidate_exit; + goto unlock_exit; } tce = be64_to_cpu(tce); if (kvmppc_tce_to_ua(vcpu->kvm, tce, &ua)) { ret = H_PARAMETER; - goto invalidate_exit; + goto unlock_exit; } list_for_each_entry_lockless(stit, &stt->iommu_tables, next) { @@ -684,19 +693,15 @@ long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu, iommu_tce_direction(tce)); if (ret != H_SUCCESS) { - kvmppc_clear_tce(vcpu->kvm->mm, stit->tbl, - entry); - goto invalidate_exit; + kvmppc_clear_tce(vcpu->kvm->mm, stt, stit->tbl, + entry + i); + goto unlock_exit; } } kvmppc_tce_put(stt, entry + i, tce); } -invalidate_exit: - list_for_each_entry_lockless(stit, &stt->iommu_tables, next) - iommu_tce_kill(stit->tbl, entry, npages); - unlock_exit: srcu_read_unlock(&vcpu->kvm->srcu, idx); @@ -735,20 +740,16 @@ long kvmppc_h_stuff_tce(struct kvm_vcpu *vcpu, continue; if (ret == H_TOO_HARD) - goto invalidate_exit; + return ret; WARN_ON_ONCE(1); - kvmppc_clear_tce(vcpu->kvm->mm, stit->tbl, entry); + kvmppc_clear_tce(vcpu->kvm->mm, stt, stit->tbl, entry + i); } } for (i = 0; i < npages; ++i, ioba += (1ULL << stt->page_shift)) kvmppc_tce_put(stt, ioba >> stt->page_shift, tce_value); -invalidate_exit: - list_for_each_entry_lockless(stit, &stt->iommu_tables, next) - iommu_tce_kill(stit->tbl, ioba >> stt->page_shift, npages); - return ret; } EXPORT_SYMBOL_GPL(kvmppc_h_stuff_tce); diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c index 870b7f0c7ea5..fdeda6a9cff4 100644 --- a/arch/powerpc/kvm/book3s_64_vio_hv.c +++ b/arch/powerpc/kvm/book3s_64_vio_hv.c @@ -247,13 +247,19 @@ static void iommu_tce_kill_rm(struct iommu_table *tbl, tbl->it_ops->tce_kill(tbl, entry, pages, true); } -static void kvmppc_rm_clear_tce(struct kvm *kvm, struct iommu_table *tbl, - unsigned long entry) +static void kvmppc_rm_clear_tce(struct kvm *kvm, struct kvmppc_spapr_tce_table *stt, + struct iommu_table *tbl, unsigned long entry) { - unsigned long hpa = 0; - enum dma_data_direction dir = DMA_NONE; + unsigned long i; + unsigned long subpages = 1ULL << (stt->page_shift - tbl->it_page_shift); + unsigned long io_entry = entry << (stt->page_shift - tbl->it_page_shift); + + for (i = 0; i < subpages; ++i) { + unsigned long hpa = 0; + enum dma_data_direction dir = DMA_NONE; - iommu_tce_xchg_no_kill_rm(kvm->mm, tbl, entry, &hpa, &dir); + iommu_tce_xchg_no_kill_rm(kvm->mm, tbl, io_entry + i, &hpa, &dir); + } } static long kvmppc_rm_tce_iommu_mapped_dec(struct kvm *kvm, @@ -316,6 +322,8 @@ static long kvmppc_rm_tce_iommu_unmap(struct kvm *kvm, break; } + iommu_tce_kill_rm(tbl, io_entry, subpages); + return ret; } @@ -379,6 +387,8 @@ static long kvmppc_rm_tce_iommu_map(struct kvm *kvm, break; } + iommu_tce_kill_rm(tbl, io_entry, subpages); + return ret; } @@ -420,10 +430,8 @@ long kvmppc_rm_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn, ret = kvmppc_rm_tce_iommu_map(vcpu->kvm, stt, stit->tbl, entry, ua, dir); - iommu_tce_kill_rm(stit->tbl, entry, 1); - if (ret != H_SUCCESS) { - kvmppc_rm_clear_tce(vcpu->kvm, stit->tbl, entry); + kvmppc_rm_clear_tce(vcpu->kvm, stt, stit->tbl, entry); return ret; } } @@ -561,7 +569,7 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu, ua = 0; if (kvmppc_rm_tce_to_ua(vcpu->kvm, tce, &ua)) { ret = H_PARAMETER; - goto invalidate_exit; + goto unlock_exit; } list_for_each_entry_lockless(stit, &stt->iommu_tables, next) { @@ -570,19 +578,15 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu, iommu_tce_direction(tce)); if (ret != H_SUCCESS) { - kvmppc_rm_clear_tce(vcpu->kvm, stit->tbl, - entry); - goto invalidate_exit; + kvmppc_rm_clear_tce(vcpu->kvm, stt, stit->tbl, + entry + i); + goto unlock_exit; } } kvmppc_rm_tce_put(stt, entry + i, tce); } -invalidate_exit: - list_for_each_entry_lockless(stit, &stt->iommu_tables, next) - iommu_tce_kill_rm(stit->tbl, entry, npages); - unlock_exit: if (!prereg) arch_spin_unlock(&kvm->mmu_lock.rlock.raw_lock); @@ -620,20 +624,16 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu, continue; if (ret == H_TOO_HARD) - goto invalidate_exit; + return ret; WARN_ON_ONCE_RM(1); - kvmppc_rm_clear_tce(vcpu->kvm, stit->tbl, entry); + kvmppc_rm_clear_tce(vcpu->kvm, stt, stit->tbl, entry + i); } } for (i = 0; i < npages; ++i, ioba += (1ULL << stt->page_shift)) kvmppc_rm_tce_put(stt, ioba >> stt->page_shift, tce_value); -invalidate_exit: - list_for_each_entry_lockless(stit, &stt->iommu_tables, next) - iommu_tce_kill_rm(stit->tbl, ioba >> stt->page_shift, npages); - return ret; } diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index c886557638a1..6fa518f6501d 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -225,6 +225,13 @@ static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu) int cpu; struct rcuwait *waitp; + /* + * rcuwait_wake_up contains smp_mb() which orders prior stores that + * create pending work vs below loads of cpu fields. The other side + * is the barrier in vcpu run that orders setting the cpu fields vs + * testing for pending work. + */ + waitp = kvm_arch_vcpu_get_wait(vcpu); if (rcuwait_wake_up(waitp)) ++vcpu->stat.generic.halt_wakeup; @@ -1089,7 +1096,7 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu) break; } tvcpu->arch.prodded = 1; - smp_mb(); + smp_mb(); /* This orders prodded store vs ceded load */ if (tvcpu->arch.ceded) kvmppc_fast_vcpu_kick_hv(tvcpu); break; @@ -3766,6 +3773,14 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) pvc = core_info.vc[sub]; pvc->pcpu = pcpu + thr; for_each_runnable_thread(i, vcpu, pvc) { + /* + * XXX: is kvmppc_start_thread called too late here? + * It updates vcpu->cpu and vcpu->arch.thread_cpu + * which are used by kvmppc_fast_vcpu_kick_hv(), but + * kick is called after new exceptions become available + * and exceptions are checked earlier than here, by + * kvmppc_core_prepare_to_enter. + */ kvmppc_start_thread(vcpu, pvc); kvmppc_create_dtl_entry(vcpu, pvc); trace_kvm_guest_enter(vcpu); @@ -4487,6 +4502,21 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, if (need_resched() || !kvm->arch.mmu_ready) goto out; + vcpu->cpu = pcpu; + vcpu->arch.thread_cpu = pcpu; + vc->pcpu = pcpu; + local_paca->kvm_hstate.kvm_vcpu = vcpu; + local_paca->kvm_hstate.ptid = 0; + local_paca->kvm_hstate.fake_suspend = 0; + + /* + * Orders set cpu/thread_cpu vs testing for pending interrupts and + * doorbells below. The other side is when these fields are set vs + * kvmppc_fast_vcpu_kick_hv reading the cpu/thread_cpu fields to + * kick a vCPU to notice the pending interrupt. + */ + smp_mb(); + if (!nested) { kvmppc_core_prepare_to_enter(vcpu); if (test_bit(BOOK3S_IRQPRIO_EXTERNAL, @@ -4506,13 +4536,6 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, tb = mftb(); - vcpu->cpu = pcpu; - vcpu->arch.thread_cpu = pcpu; - vc->pcpu = pcpu; - local_paca->kvm_hstate.kvm_vcpu = vcpu; - local_paca->kvm_hstate.ptid = 0; - local_paca->kvm_hstate.fake_suspend = 0; - __kvmppc_create_dtl_entry(vcpu, pcpu, tb + vc->tb_offset, 0); trace_kvm_guest_enter(vcpu); @@ -4614,6 +4637,8 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, run->exit_reason = KVM_EXIT_INTR; vcpu->arch.ret = -EINTR; out: + vcpu->cpu = -1; + vcpu->arch.thread_cpu = -1; powerpc_local_irq_pmu_restore(flags); preempt_enable(); goto done; diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c index 9d373f8963ee..c943a051c6e7 100644 --- a/arch/powerpc/kvm/book3s_hv_nested.c +++ b/arch/powerpc/kvm/book3s_hv_nested.c @@ -306,10 +306,10 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu) /* copy parameters in */ hv_ptr = kvmppc_get_gpr(vcpu, 4); regs_ptr = kvmppc_get_gpr(vcpu, 5); - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); err = kvmhv_read_guest_state_and_regs(vcpu, &l2_hv, &l2_regs, hv_ptr, regs_ptr); - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); if (err) return H_PARAMETER; @@ -410,10 +410,10 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu) byteswap_hv_regs(&l2_hv); byteswap_pt_regs(&l2_regs); } - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); err = kvmhv_write_guest_state_and_regs(vcpu, &l2_hv, &l2_regs, hv_ptr, regs_ptr); - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); if (err) return H_AUTHORITY; @@ -600,16 +600,16 @@ long kvmhv_copy_tofrom_guest_nested(struct kvm_vcpu *vcpu) goto not_found; /* Write what was loaded into our buffer back to the L1 guest */ - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); rc = kvm_vcpu_write_guest(vcpu, gp_to, buf, n); - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); if (rc) goto not_found; } else { /* Load the data to be stored from the L1 guest into our buf */ - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); rc = kvm_vcpu_read_guest(vcpu, gp_from, buf, n); - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); if (rc) goto not_found; diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c index 34a801c3604a..7bf9e6ca5c2d 100644 --- a/arch/powerpc/kvm/book3s_pr.c +++ b/arch/powerpc/kvm/book3s_pr.c @@ -137,12 +137,15 @@ static void kvmppc_core_vcpu_load_pr(struct kvm_vcpu *vcpu, int cpu) svcpu->slb_max = to_book3s(vcpu)->slb_shadow_max; svcpu->in_use = 0; svcpu_put(svcpu); -#endif /* Disable AIL if supported */ - if (cpu_has_feature(CPU_FTR_HVMODE) && - cpu_has_feature(CPU_FTR_ARCH_207S)) - mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) & ~LPCR_AIL); + if (cpu_has_feature(CPU_FTR_HVMODE)) { + if (cpu_has_feature(CPU_FTR_ARCH_207S)) + mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) & ~LPCR_AIL); + if (cpu_has_feature(CPU_FTR_ARCH_300) && (current->thread.fscr & FSCR_SCV)) + mtspr(SPRN_FSCR, mfspr(SPRN_FSCR) & ~FSCR_SCV); + } +#endif vcpu->cpu = smp_processor_id(); #ifdef CONFIG_PPC_BOOK3S_32 @@ -165,6 +168,14 @@ static void kvmppc_core_vcpu_put_pr(struct kvm_vcpu *vcpu) memcpy(to_book3s(vcpu)->slb_shadow, svcpu->slb, sizeof(svcpu->slb)); to_book3s(vcpu)->slb_shadow_max = svcpu->slb_max; svcpu_put(svcpu); + + /* Enable AIL if supported */ + if (cpu_has_feature(CPU_FTR_HVMODE)) { + if (cpu_has_feature(CPU_FTR_ARCH_207S)) + mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) | LPCR_AIL_3); + if (cpu_has_feature(CPU_FTR_ARCH_300) && (current->thread.fscr & FSCR_SCV)) + mtspr(SPRN_FSCR, mfspr(SPRN_FSCR) | FSCR_SCV); + } #endif if (kvmppc_is_split_real(vcpu)) @@ -174,11 +185,6 @@ static void kvmppc_core_vcpu_put_pr(struct kvm_vcpu *vcpu) kvmppc_giveup_fac(vcpu, FSCR_TAR_LG); kvmppc_save_tm_pr(vcpu); - /* Enable AIL if supported */ - if (cpu_has_feature(CPU_FTR_HVMODE) && - cpu_has_feature(CPU_FTR_ARCH_207S)) - mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) | LPCR_AIL_3); - vcpu->cpu = -1; } @@ -1037,6 +1043,8 @@ static int kvmppc_handle_fac(struct kvm_vcpu *vcpu, ulong fac) void kvmppc_set_fscr(struct kvm_vcpu *vcpu, u64 fscr) { + if (fscr & FSCR_SCV) + fscr &= ~FSCR_SCV; /* SCV must not be enabled */ if ((vcpu->arch.fscr & FSCR_TAR) && !(fscr & FSCR_TAR)) { /* TAR got dropped, drop it in shadow too */ kvmppc_giveup_fac(vcpu, FSCR_TAR_LG); diff --git a/arch/powerpc/kvm/book3s_pr_papr.c b/arch/powerpc/kvm/book3s_pr_papr.c index 1f10e7dfcdd0..dc4f51ac84bc 100644 --- a/arch/powerpc/kvm/book3s_pr_papr.c +++ b/arch/powerpc/kvm/book3s_pr_papr.c @@ -281,6 +281,22 @@ static int kvmppc_h_pr_logical_ci_store(struct kvm_vcpu *vcpu) return EMULATE_DONE; } +static int kvmppc_h_pr_set_mode(struct kvm_vcpu *vcpu) +{ + unsigned long mflags = kvmppc_get_gpr(vcpu, 4); + unsigned long resource = kvmppc_get_gpr(vcpu, 5); + + if (resource == H_SET_MODE_RESOURCE_ADDR_TRANS_MODE) { + /* KVM PR does not provide AIL!=0 to guests */ + if (mflags == 0) + kvmppc_set_gpr(vcpu, 3, H_SUCCESS); + else + kvmppc_set_gpr(vcpu, 3, H_UNSUPPORTED_FLAG_START - 63); + return EMULATE_DONE; + } + return EMULATE_FAIL; +} + #ifdef CONFIG_SPAPR_TCE_IOMMU static int kvmppc_h_pr_put_tce(struct kvm_vcpu *vcpu) { @@ -384,6 +400,8 @@ int kvmppc_h_pr(struct kvm_vcpu *vcpu, unsigned long cmd) return kvmppc_h_pr_logical_ci_load(vcpu); case H_LOGICAL_CI_STORE: return kvmppc_h_pr_logical_ci_store(vcpu); + case H_SET_MODE: + return kvmppc_h_pr_set_mode(vcpu); case H_XIRR: case H_CPPR: case H_EOI: @@ -421,6 +439,7 @@ int kvmppc_hcall_impl_pr(unsigned long cmd) case H_CEDE: case H_LOGICAL_CI_LOAD: case H_LOGICAL_CI_STORE: + case H_SET_MODE: #ifdef CONFIG_KVM_XICS case H_XIRR: case H_CPPR: @@ -447,6 +466,7 @@ static unsigned int default_hcall_list[] = { H_BULK_REMOVE, H_PUT_TCE, H_CEDE, + H_SET_MODE, #ifdef CONFIG_KVM_XICS H_XIRR, H_CPPR, diff --git a/arch/powerpc/kvm/book3s_rtas.c b/arch/powerpc/kvm/book3s_rtas.c index 0f847f1e5ddd..6808bda0dbc1 100644 --- a/arch/powerpc/kvm/book3s_rtas.c +++ b/arch/powerpc/kvm/book3s_rtas.c @@ -229,9 +229,9 @@ int kvmppc_rtas_hcall(struct kvm_vcpu *vcpu) */ args_phys = kvmppc_get_gpr(vcpu, 4) & KVM_PAM; - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); rc = kvm_read_guest(vcpu->kvm, args_phys, &args, sizeof(args)); - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); if (rc) goto fail; diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 9772b176e406..533c4232e5ab 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -425,9 +425,9 @@ int kvmppc_ld(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr, return EMULATE_DONE; } - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); rc = kvm_read_guest(vcpu->kvm, pte.raddr, ptr, size); - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); if (rc) return EMULATE_DO_MMIO; @@ -705,6 +705,23 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = 1; break; #endif + case KVM_CAP_PPC_AIL_MODE_3: + r = 0; + /* + * KVM PR, POWER7, and some POWER9s don't support AIL=3 mode. + * The POWER9s can support it if the guest runs in hash mode, + * but QEMU doesn't necessarily query the capability in time. + */ + if (hv_enabled) { + if (kvmhv_on_pseries()) { + if (pseries_reloc_on_exception()) + r = 1; + } else if (cpu_has_feature(CPU_FTR_ARCH_207S) && + !cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG)) { + r = 1; + } + } + break; default: r = 0; break; diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 8e301cd8925b..4d221d033804 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -255,7 +255,7 @@ void __init mem_init(void) #endif high_memory = (void *) __va(max_low_pfn * PAGE_SIZE); - set_max_mapnr(max_low_pfn); + set_max_mapnr(max_pfn); kasan_late_init(); diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index b9b7fefbb64b..13022d734951 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -1436,7 +1436,7 @@ int find_and_online_cpu_nid(int cpu) if (new_nid < 0 || !node_possible(new_nid)) new_nid = first_online_node; - if (NODE_DATA(new_nid) == NULL) { + if (!node_online(new_nid)) { #ifdef CONFIG_MEMORY_HOTPLUG /* * Need to ensure that NODE_DATA is initialized for a node from diff --git a/arch/powerpc/perf/Makefile b/arch/powerpc/perf/Makefile index 2f46e31c7612..4f53d0b97539 100644 --- a/arch/powerpc/perf/Makefile +++ b/arch/powerpc/perf/Makefile @@ -3,11 +3,11 @@ obj-y += callchain.o callchain_$(BITS).o perf_regs.o obj-$(CONFIG_COMPAT) += callchain_32.o -obj-$(CONFIG_PPC_PERF_CTRS) += core-book3s.o bhrb.o +obj-$(CONFIG_PPC_PERF_CTRS) += core-book3s.o obj64-$(CONFIG_PPC_PERF_CTRS) += ppc970-pmu.o power5-pmu.o \ power5+-pmu.o power6-pmu.o power7-pmu.o \ isa207-common.o power8-pmu.o power9-pmu.o \ - generic-compat-pmu.o power10-pmu.o + generic-compat-pmu.o power10-pmu.o bhrb.o obj32-$(CONFIG_PPC_PERF_CTRS) += mpc7450-pmu.o obj-$(CONFIG_PPC_POWERNV) += imc-pmu.o diff --git a/arch/powerpc/perf/power10-pmu.c b/arch/powerpc/perf/power10-pmu.c index d3398100a60f..c6d51e7093cf 100644 --- a/arch/powerpc/perf/power10-pmu.c +++ b/arch/powerpc/perf/power10-pmu.c @@ -91,8 +91,8 @@ extern u64 PERF_REG_EXTENDED_MASK; /* Table of alternatives, sorted by column 0 */ static const unsigned int power10_event_alternatives[][MAX_ALT] = { - { PM_CYC_ALT, PM_CYC }, { PM_INST_CMPL_ALT, PM_INST_CMPL }, + { PM_CYC_ALT, PM_CYC }, }; static int power10_get_alternatives(u64 event, unsigned int flags, u64 alt[]) diff --git a/arch/powerpc/perf/power9-pmu.c b/arch/powerpc/perf/power9-pmu.c index c9eb5232e68b..c393e837648e 100644 --- a/arch/powerpc/perf/power9-pmu.c +++ b/arch/powerpc/perf/power9-pmu.c @@ -133,11 +133,11 @@ int p9_dd22_bl_ev[] = { /* Table of alternatives, sorted by column 0 */ static const unsigned int power9_event_alternatives[][MAX_ALT] = { - { PM_INST_DISP, PM_INST_DISP_ALT }, - { PM_RUN_CYC_ALT, PM_RUN_CYC }, - { PM_RUN_INST_CMPL_ALT, PM_RUN_INST_CMPL }, - { PM_LD_MISS_L1, PM_LD_MISS_L1_ALT }, { PM_BR_2PATH, PM_BR_2PATH_ALT }, + { PM_INST_DISP, PM_INST_DISP_ALT }, + { PM_RUN_CYC_ALT, PM_RUN_CYC }, + { PM_LD_MISS_L1, PM_LD_MISS_L1_ALT }, + { PM_RUN_INST_CMPL_ALT, PM_RUN_INST_CMPL }, }; static int power9_get_alternatives(u64 event, unsigned int flags, u64 alt[]) diff --git a/arch/powerpc/platforms/powernv/opal-core.c b/arch/powerpc/platforms/powernv/opal-core.c index b97bc179f65a..adcb1a1a2bfe 100644 --- a/arch/powerpc/platforms/powernv/opal-core.c +++ b/arch/powerpc/platforms/powernv/opal-core.c @@ -112,7 +112,7 @@ static void __init fill_prstatus(struct elf_prstatus *prstatus, int pir, struct pt_regs *regs) { memset(prstatus, 0, sizeof(struct elf_prstatus)); - elf_core_copy_kernel_regs(&(prstatus->pr_reg), regs); + elf_core_copy_regs(&(prstatus->pr_reg), regs); /* * Overload PID with PIR value. diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c index f58728d5f10d..39962c905542 100644 --- a/arch/powerpc/platforms/pseries/papr_scm.c +++ b/arch/powerpc/platforms/pseries/papr_scm.c @@ -462,7 +462,6 @@ static int papr_scm_pmu_check_events(struct papr_scm_priv *p, struct nvdimm_pmu { struct papr_scm_perf_stat *stat; struct papr_scm_perf_stats *stats; - char *statid; int index, rc, count; u32 available_events; @@ -493,14 +492,12 @@ static int papr_scm_pmu_check_events(struct papr_scm_priv *p, struct nvdimm_pmu for (index = 0, stat = stats->scm_statistic, count = 0; index < available_events; index++, ++stat) { - statid = kzalloc(strlen(stat->stat_id) + 1, GFP_KERNEL); - if (!statid) { + p->nvdimm_events_map[count] = kmemdup_nul(stat->stat_id, 8, GFP_KERNEL); + if (!p->nvdimm_events_map[count]) { rc = -ENOMEM; goto out_nvdimm_events_map; } - strcpy(statid, stat->stat_id); - p->nvdimm_events_map[count] = statid; count++; } p->nvdimm_events_map[count] = NULL; diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 069d7b3bb142..955ff8aa1644 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -353,6 +353,14 @@ static void pseries_lpar_idle(void) pseries_idle_epilog(); } +static bool pseries_reloc_on_exception_enabled; + +bool pseries_reloc_on_exception(void) +{ + return pseries_reloc_on_exception_enabled; +} +EXPORT_SYMBOL_GPL(pseries_reloc_on_exception); + /* * Enable relocation on during exceptions. This has partition wide scope and * may take a while to complete, if it takes longer than one second we will @@ -377,6 +385,7 @@ bool pseries_enable_reloc_on_exc(void) " on exceptions: %ld\n", rc); return false; } + pseries_reloc_on_exception_enabled = true; return true; } @@ -404,7 +413,9 @@ void pseries_disable_reloc_on_exc(void) break; mdelay(get_longbusy_msecs(rc)); } - if (rc != H_SUCCESS) + if (rc == H_SUCCESS) + pseries_reloc_on_exception_enabled = false; + else pr_warn("Warning: Failed to disable relocation on exceptions: %ld\n", rc); } diff --git a/arch/powerpc/platforms/pseries/vas-sysfs.c b/arch/powerpc/platforms/pseries/vas-sysfs.c index 4a7fcde5afc0..ec65586cbeb3 100644 --- a/arch/powerpc/platforms/pseries/vas-sysfs.c +++ b/arch/powerpc/platforms/pseries/vas-sysfs.c @@ -27,22 +27,31 @@ struct vas_caps_entry { /* * This function is used to get the notification from the drmgr when - * QoS credits are changed. Though receiving the target total QoS - * credits here, get the official QoS capabilities from the hypervisor. + * QoS credits are changed. */ -static ssize_t update_total_credits_trigger(struct vas_cop_feat_caps *caps, +static ssize_t update_total_credits_store(struct vas_cop_feat_caps *caps, const char *buf, size_t count) { int err; u16 creds; err = kstrtou16(buf, 0, &creds); + /* + * The user space interface from the management console + * notifies OS with the new QoS credits and then the + * hypervisor. So OS has to use this new credits value + * and reconfigure VAS windows (close or reopen depends + * on the credits available) instead of depending on VAS + * QoS capabilities from the hypervisor. + */ if (!err) - err = vas_reconfig_capabilties(caps->win_type); + err = vas_reconfig_capabilties(caps->win_type, creds); if (err) return -EINVAL; + pr_info("Set QoS total credits %u\n", creds); + return count; } @@ -92,13 +101,14 @@ VAS_ATTR_RO(nr_total_credits); VAS_ATTR_RO(nr_used_credits); static struct vas_sysfs_entry update_total_credits_attribute = - __ATTR(update_total_credits, 0200, NULL, update_total_credits_trigger); + __ATTR(update_total_credits, 0200, NULL, update_total_credits_store); static struct attribute *vas_def_capab_attrs[] = { &nr_total_credits_attribute.attr, &nr_used_credits_attribute.attr, NULL, }; +ATTRIBUTE_GROUPS(vas_def_capab); static struct attribute *vas_qos_capab_attrs[] = { &nr_total_credits_attribute.attr, @@ -106,6 +116,7 @@ static struct attribute *vas_qos_capab_attrs[] = { &update_total_credits_attribute.attr, NULL, }; +ATTRIBUTE_GROUPS(vas_qos_capab); static ssize_t vas_type_show(struct kobject *kobj, struct attribute *attr, char *buf) @@ -154,13 +165,13 @@ static const struct sysfs_ops vas_sysfs_ops = { static struct kobj_type vas_def_attr_type = { .release = vas_type_release, .sysfs_ops = &vas_sysfs_ops, - .default_attrs = vas_def_capab_attrs, + .default_groups = vas_def_capab_groups, }; static struct kobj_type vas_qos_attr_type = { .release = vas_type_release, .sysfs_ops = &vas_sysfs_ops, - .default_attrs = vas_qos_capab_attrs, + .default_groups = vas_qos_capab_groups, }; static char *vas_caps_kobj_name(struct vas_caps_entry *centry, diff --git a/arch/powerpc/platforms/pseries/vas.c b/arch/powerpc/platforms/pseries/vas.c index 1f59d78c77a1..ec643bbdb67f 100644 --- a/arch/powerpc/platforms/pseries/vas.c +++ b/arch/powerpc/platforms/pseries/vas.c @@ -779,10 +779,10 @@ static int reconfig_close_windows(struct vas_caps *vcap, int excess_creds, * changes. Reconfig window configurations based on the credits * availability from this new capabilities. */ -int vas_reconfig_capabilties(u8 type) +int vas_reconfig_capabilties(u8 type, int new_nr_creds) { struct vas_cop_feat_caps *caps; - int old_nr_creds, new_nr_creds; + int old_nr_creds; struct vas_caps *vcaps; int rc = 0, nr_active_wins; @@ -795,12 +795,6 @@ int vas_reconfig_capabilties(u8 type) caps = &vcaps->caps; mutex_lock(&vas_pseries_mutex); - rc = h_query_vas_capabilities(H_QUERY_VAS_CAPABILITIES, vcaps->feat, - (u64)virt_to_phys(&hv_cop_caps)); - if (rc) - goto out; - - new_nr_creds = be16_to_cpu(hv_cop_caps.target_lpar_creds); old_nr_creds = atomic_read(&caps->nr_total_credits); @@ -832,7 +826,6 @@ int vas_reconfig_capabilties(u8 type) false); } -out: mutex_unlock(&vas_pseries_mutex); return rc; } @@ -850,7 +843,7 @@ static int pseries_vas_notifier(struct notifier_block *nb, struct of_reconfig_data *rd = data; struct device_node *dn = rd->dn; const __be32 *intserv = NULL; - int len, rc = 0; + int new_nr_creds, len, rc = 0; if ((action == OF_RECONFIG_ATTACH_NODE) || (action == OF_RECONFIG_DETACH_NODE)) @@ -862,7 +855,15 @@ static int pseries_vas_notifier(struct notifier_block *nb, if (!intserv) return NOTIFY_OK; - rc = vas_reconfig_capabilties(VAS_GZIP_DEF_FEAT_TYPE); + rc = h_query_vas_capabilities(H_QUERY_VAS_CAPABILITIES, + vascaps[VAS_GZIP_DEF_FEAT_TYPE].feat, + (u64)virt_to_phys(&hv_cop_caps)); + if (!rc) { + new_nr_creds = be16_to_cpu(hv_cop_caps.target_lpar_creds); + rc = vas_reconfig_capabilties(VAS_GZIP_DEF_FEAT_TYPE, + new_nr_creds); + } + if (rc) pr_err("Failed reconfig VAS capabilities with DLPAR\n"); diff --git a/arch/powerpc/platforms/pseries/vas.h b/arch/powerpc/platforms/pseries/vas.h index 34177881e998..333ffa2f9f42 100644 --- a/arch/powerpc/platforms/pseries/vas.h +++ b/arch/powerpc/platforms/pseries/vas.h @@ -135,7 +135,7 @@ struct pseries_vas_window { }; int sysfs_add_vas_caps(struct vas_cop_feat_caps *caps); -int vas_reconfig_capabilties(u8 type); +int vas_reconfig_capabilties(u8 type, int new_nr_creds); int __init sysfs_pseries_vas_init(struct vas_all_caps *vas_caps); #ifdef CONFIG_PPC_VAS diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 00fd9c548f26..3ac2a81a55eb 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -468,7 +468,7 @@ config CC_HAVE_STACKPROTECTOR_TLS config STACKPROTECTOR_PER_TASK def_bool y - depends on !GCC_PLUGIN_RANDSTRUCT + depends on !RANDSTRUCT depends on STACKPROTECTOR && CC_HAVE_STACKPROTECTOR_TLS config PHYS_RAM_BASE_FIXED diff --git a/arch/riscv/Kconfig.socs b/arch/riscv/Kconfig.socs index 34592d00dde8..f6ef358d8a2c 100644 --- a/arch/riscv/Kconfig.socs +++ b/arch/riscv/Kconfig.socs @@ -38,7 +38,7 @@ config SOC_VIRT select SIFIVE_PLIC select PM_GENERIC_DOMAINS if PM select PM_GENERIC_DOMAINS_OF if PM && OF - select RISCV_SBI_CPUIDLE if CPU_IDLE + select RISCV_SBI_CPUIDLE if CPU_IDLE && RISCV_SBI help This enables support for QEMU Virt Machine. diff --git a/arch/riscv/boot/dts/microchip/microchip-mpfs-fabric.dtsi b/arch/riscv/boot/dts/microchip/microchip-mpfs-fabric.dtsi index 854320e17b28..ccaac3371cf9 100644 --- a/arch/riscv/boot/dts/microchip/microchip-mpfs-fabric.dtsi +++ b/arch/riscv/boot/dts/microchip/microchip-mpfs-fabric.dtsi @@ -7,7 +7,7 @@ reg = <0x0 0x41000000 0x0 0xF0>; microchip,sync-update-mask = /bits/ 32 <0>; #pwm-cells = <2>; - clocks = <&clkcfg CLK_FIC3>; + clocks = <&fabric_clk3>; status = "disabled"; }; @@ -16,10 +16,22 @@ reg = <0x0 0x44000000 0x0 0x1000>; #address-cells = <1>; #size-cells = <0>; - clocks = <&clkcfg CLK_FIC3>; + clocks = <&fabric_clk3>; interrupt-parent = <&plic>; interrupts = <122>; clock-frequency = <100000>; status = "disabled"; }; + + fabric_clk3: fabric-clk3 { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <62500000>; + }; + + fabric_clk1: fabric-clk1 { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <125000000>; + }; }; diff --git a/arch/riscv/boot/dts/microchip/microchip-mpfs-icicle-kit.dts b/arch/riscv/boot/dts/microchip/microchip-mpfs-icicle-kit.dts index cd2fe80fa81a..3392153dd0f1 100644 --- a/arch/riscv/boot/dts/microchip/microchip-mpfs-icicle-kit.dts +++ b/arch/riscv/boot/dts/microchip/microchip-mpfs-icicle-kit.dts @@ -45,7 +45,7 @@ }; &refclk { - clock-frequency = <600000000>; + clock-frequency = <125000000>; }; &mmuart1 { diff --git a/arch/riscv/boot/dts/microchip/microchip-mpfs.dtsi b/arch/riscv/boot/dts/microchip/microchip-mpfs.dtsi index c5c9d1360de0..cf2f55e1dcb6 100644 --- a/arch/riscv/boot/dts/microchip/microchip-mpfs.dtsi +++ b/arch/riscv/boot/dts/microchip/microchip-mpfs.dtsi @@ -141,7 +141,7 @@ }; }; - refclk: msspllclk { + refclk: mssrefclk { compatible = "fixed-clock"; #clock-cells = <0>; }; @@ -190,7 +190,7 @@ clkcfg: clkcfg@20002000 { compatible = "microchip,mpfs-clkcfg"; - reg = <0x0 0x20002000 0x0 0x1000>; + reg = <0x0 0x20002000 0x0 0x1000>, <0x0 0x3E001000 0x0 0x1000>; clocks = <&refclk>; #clock-cells = <1>; }; @@ -366,7 +366,7 @@ gpio1: gpio@20121000 { compatible = "microchip,mpfs-gpio"; - reg = <000 0x20121000 0x0 0x1000>; + reg = <0x0 0x20121000 0x0 0x1000>; interrupt-parent = <&plic>; interrupt-controller; #interrupt-cells = <1>; @@ -393,8 +393,8 @@ reg = <0x0 0x20124000 0x0 0x1000>; interrupt-parent = <&plic>; interrupts = <80>, <81>; - clocks = <&clkcfg CLK_RTC>; - clock-names = "rtc"; + clocks = <&clkcfg CLK_RTC>, <&clkcfg CLK_RTCREF>; + clock-names = "rtc", "rtcref"; status = "disabled"; }; @@ -424,7 +424,7 @@ <0 0 0 3 &pcie_intc 2>, <0 0 0 4 &pcie_intc 3>; interrupt-map-mask = <0 0 0 7>; - clocks = <&clkcfg CLK_FIC0>, <&clkcfg CLK_FIC1>, <&clkcfg CLK_FIC3>; + clocks = <&fabric_clk1>, <&fabric_clk1>, <&fabric_clk3>; clock-names = "fic0", "fic1", "fic3"; ranges = <0x3000000 0x0 0x8000000 0x20 0x8000000 0x0 0x80000000>; msi-parent = <&pcie>; diff --git a/arch/riscv/boot/dts/sifive/fu540-c000.dtsi b/arch/riscv/boot/dts/sifive/fu540-c000.dtsi index aad45d7f498f..5c638fd5b35c 100644 --- a/arch/riscv/boot/dts/sifive/fu540-c000.dtsi +++ b/arch/riscv/boot/dts/sifive/fu540-c000.dtsi @@ -167,7 +167,7 @@ clocks = <&prci FU540_PRCI_CLK_TLCLK>; status = "disabled"; }; - dma: dma@3000000 { + dma: dma-controller@3000000 { compatible = "sifive,fu540-c000-pdma"; reg = <0x0 0x3000000 0x0 0x8000>; interrupt-parent = <&plic0>; diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig index 30e3017f22bc..0cc17db8aaba 100644 --- a/arch/riscv/configs/defconfig +++ b/arch/riscv/configs/defconfig @@ -101,6 +101,7 @@ CONFIG_VIRTIO_BALLOON=y CONFIG_VIRTIO_INPUT=y CONFIG_VIRTIO_MMIO=y CONFIG_RPMSG_CHAR=y +CONFIG_RPMSG_CTRL=y CONFIG_RPMSG_VIRTIO=y CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y diff --git a/arch/riscv/configs/rv32_defconfig b/arch/riscv/configs/rv32_defconfig index 7e5efdc3829d..6cd9d84d3e13 100644 --- a/arch/riscv/configs/rv32_defconfig +++ b/arch/riscv/configs/rv32_defconfig @@ -93,6 +93,7 @@ CONFIG_VIRTIO_BALLOON=y CONFIG_VIRTIO_INPUT=y CONFIG_VIRTIO_MMIO=y CONFIG_RPMSG_CHAR=y +CONFIG_RPMSG_CTRL=y CONFIG_RPMSG_VIRTIO=y CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y diff --git a/arch/riscv/include/asm/bug.h b/arch/riscv/include/asm/bug.h index d3804a2f9aad..1aaea81fb141 100644 --- a/arch/riscv/include/asm/bug.h +++ b/arch/riscv/include/asm/bug.h @@ -30,8 +30,8 @@ typedef u32 bug_insn_t; #ifdef CONFIG_GENERIC_BUG_RELATIVE_POINTERS -#define __BUG_ENTRY_ADDR RISCV_INT " 1b - 2b" -#define __BUG_ENTRY_FILE RISCV_INT " %0 - 2b" +#define __BUG_ENTRY_ADDR RISCV_INT " 1b - ." +#define __BUG_ENTRY_FILE RISCV_INT " %0 - ." #else #define __BUG_ENTRY_ADDR RISCV_PTR " 1b" #define __BUG_ENTRY_FILE RISCV_PTR " %0" diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h index 78da839657e5..cd4bbcecb0fb 100644 --- a/arch/riscv/include/asm/kvm_host.h +++ b/arch/riscv/include/asm/kvm_host.h @@ -193,9 +193,6 @@ struct kvm_vcpu_arch { /* Don't run the VCPU (blocked) */ bool pause; - - /* SRCU lock index for in-kernel run loop */ - int srcu_idx; }; static inline void kvm_arch_hardware_unsetup(void) {} diff --git a/arch/riscv/include/asm/timex.h b/arch/riscv/include/asm/timex.h index 507cae273bc6..d6a7428f6248 100644 --- a/arch/riscv/include/asm/timex.h +++ b/arch/riscv/include/asm/timex.h @@ -41,7 +41,7 @@ static inline u32 get_cycles_hi(void) static inline unsigned long random_get_entropy(void) { if (unlikely(clint_time_val == NULL)) - return 0; + return random_get_entropy_fallback(); return get_cycles(); } #define random_get_entropy() random_get_entropy() diff --git a/arch/riscv/kernel/patch.c b/arch/riscv/kernel/patch.c index 0b552873a577..765004b60513 100644 --- a/arch/riscv/kernel/patch.c +++ b/arch/riscv/kernel/patch.c @@ -104,7 +104,7 @@ static int patch_text_cb(void *data) struct patch_insn *patch = data; int ret = 0; - if (atomic_inc_return(&patch->cpu_count) == 1) { + if (atomic_inc_return(&patch->cpu_count) == num_online_cpus()) { ret = patch_text_nosync(patch->addr, &patch->insn, GET_INSN_LENGTH(patch->insn)); diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c index 624166004e36..7461f964d20a 100644 --- a/arch/riscv/kvm/vcpu.c +++ b/arch/riscv/kvm/vcpu.c @@ -38,14 +38,16 @@ const struct kvm_stats_header kvm_vcpu_stats_header = { sizeof(kvm_vcpu_stats_desc), }; -#define KVM_RISCV_ISA_ALLOWED (riscv_isa_extension_mask(a) | \ - riscv_isa_extension_mask(c) | \ - riscv_isa_extension_mask(d) | \ - riscv_isa_extension_mask(f) | \ - riscv_isa_extension_mask(i) | \ - riscv_isa_extension_mask(m) | \ - riscv_isa_extension_mask(s) | \ - riscv_isa_extension_mask(u)) +#define KVM_RISCV_ISA_DISABLE_ALLOWED (riscv_isa_extension_mask(d) | \ + riscv_isa_extension_mask(f)) + +#define KVM_RISCV_ISA_DISABLE_NOT_ALLOWED (riscv_isa_extension_mask(a) | \ + riscv_isa_extension_mask(c) | \ + riscv_isa_extension_mask(i) | \ + riscv_isa_extension_mask(m)) + +#define KVM_RISCV_ISA_ALLOWED (KVM_RISCV_ISA_DISABLE_ALLOWED | \ + KVM_RISCV_ISA_DISABLE_NOT_ALLOWED) static void kvm_riscv_reset_vcpu(struct kvm_vcpu *vcpu) { @@ -219,7 +221,8 @@ static int kvm_riscv_vcpu_set_reg_config(struct kvm_vcpu *vcpu, switch (reg_num) { case KVM_REG_RISCV_CONFIG_REG(isa): if (!vcpu->arch.ran_atleast_once) { - vcpu->arch.isa = reg_val; + /* Ignore the disable request for these extensions */ + vcpu->arch.isa = reg_val | KVM_RISCV_ISA_DISABLE_NOT_ALLOWED; vcpu->arch.isa &= riscv_isa_extension_base(NULL); vcpu->arch.isa &= KVM_RISCV_ISA_ALLOWED; kvm_riscv_vcpu_fp_reset(vcpu); @@ -653,8 +656,6 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) vcpu->arch.isa); kvm_riscv_vcpu_host_fp_restore(&vcpu->arch.host_context); - csr_write(CSR_HGATP, 0); - csr->vsstatus = csr_read(CSR_VSSTATUS); csr->vsie = csr_read(CSR_VSIE); csr->vstvec = csr_read(CSR_VSTVEC); @@ -726,13 +727,13 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) /* Mark this VCPU ran at least once */ vcpu->arch.ran_atleast_once = true; - vcpu->arch.srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); /* Process MMIO value returned from user-space */ if (run->exit_reason == KVM_EXIT_MMIO) { ret = kvm_riscv_vcpu_mmio_return(vcpu, vcpu->run); if (ret) { - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->arch.srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); return ret; } } @@ -741,13 +742,13 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) if (run->exit_reason == KVM_EXIT_RISCV_SBI) { ret = kvm_riscv_vcpu_sbi_return(vcpu, vcpu->run); if (ret) { - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->arch.srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); return ret; } } if (run->immediate_exit) { - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->arch.srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); return -EINTR; } @@ -786,7 +787,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) */ vcpu->mode = IN_GUEST_MODE; - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->arch.srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); smp_mb__after_srcu_read_unlock(); /* @@ -804,7 +805,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) vcpu->mode = OUTSIDE_GUEST_MODE; local_irq_enable(); preempt_enable(); - vcpu->arch.srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); continue; } @@ -848,7 +849,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) preempt_enable(); - vcpu->arch.srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); ret = kvm_riscv_vcpu_exit(vcpu, run, &trap); } @@ -857,7 +858,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) vcpu_put(vcpu); - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->arch.srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); return ret; } diff --git a/arch/riscv/kvm/vcpu_exit.c b/arch/riscv/kvm/vcpu_exit.c index aa8af129e4bb..a72c15d4b42a 100644 --- a/arch/riscv/kvm/vcpu_exit.c +++ b/arch/riscv/kvm/vcpu_exit.c @@ -456,9 +456,9 @@ static int stage2_page_fault(struct kvm_vcpu *vcpu, struct kvm_run *run, void kvm_riscv_vcpu_wfi(struct kvm_vcpu *vcpu) { if (!kvm_arch_vcpu_runnable(vcpu)) { - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->arch.srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); kvm_vcpu_halt(vcpu); - vcpu->arch.srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); kvm_clear_request(KVM_REQ_UNHALT, vcpu); } } diff --git a/arch/riscv/kvm/vcpu_fp.c b/arch/riscv/kvm/vcpu_fp.c index 4449a976e5a6..d4308c512007 100644 --- a/arch/riscv/kvm/vcpu_fp.c +++ b/arch/riscv/kvm/vcpu_fp.c @@ -11,6 +11,7 @@ #include <linux/err.h> #include <linux/kvm_host.h> #include <linux/uaccess.h> +#include <asm/hwcap.h> #ifdef CONFIG_FPU void kvm_riscv_vcpu_fp_reset(struct kvm_vcpu *vcpu) diff --git a/arch/riscv/kvm/vcpu_sbi.c b/arch/riscv/kvm/vcpu_sbi.c index a09ecb97b890..d45e7da3f0d3 100644 --- a/arch/riscv/kvm/vcpu_sbi.c +++ b/arch/riscv/kvm/vcpu_sbi.c @@ -83,7 +83,7 @@ void kvm_riscv_vcpu_sbi_forward(struct kvm_vcpu *vcpu, struct kvm_run *run) void kvm_riscv_vcpu_sbi_system_reset(struct kvm_vcpu *vcpu, struct kvm_run *run, - u32 type, u64 flags) + u32 type, u64 reason) { unsigned long i; struct kvm_vcpu *tmp; @@ -94,7 +94,8 @@ void kvm_riscv_vcpu_sbi_system_reset(struct kvm_vcpu *vcpu, memset(&run->system_event, 0, sizeof(run->system_event)); run->system_event.type = type; - run->system_event.flags = flags; + run->system_event.ndata = 1; + run->system_event.data[0] = reason; run->exit_reason = KVM_EXIT_SYSTEM_EVENT; } diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 9535bea8688c..05ed641a1134 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -208,8 +208,25 @@ static void __init setup_bootmem(void) * early_init_fdt_reserve_self() since __pa() does * not work for DTB pointers that are fixmap addresses */ - if (!IS_ENABLED(CONFIG_BUILTIN_DTB)) - memblock_reserve(dtb_early_pa, fdt_totalsize(dtb_early_va)); + if (!IS_ENABLED(CONFIG_BUILTIN_DTB)) { + /* + * In case the DTB is not located in a memory region we won't + * be able to locate it later on via the linear mapping and + * get a segfault when accessing it via __va(dtb_early_pa). + * To avoid this situation copy DTB to a memory region. + * Note that memblock_phys_alloc will also reserve DTB region. + */ + if (!memblock_is_memory(dtb_early_pa)) { + size_t fdt_size = fdt_totalsize(dtb_early_va); + phys_addr_t new_dtb_early_pa = memblock_phys_alloc(fdt_size, PAGE_SIZE); + void *new_dtb_early_va = early_memremap(new_dtb_early_pa, fdt_size); + + memcpy(new_dtb_early_va, dtb_early_va, fdt_size); + early_memunmap(new_dtb_early_va, fdt_size); + _dtb_early_pa = new_dtb_early_pa; + } else + memblock_reserve(dtb_early_pa, fdt_totalsize(dtb_early_va)); + } early_init_fdt_scan_reserved_mem(); dma_contiguous_reserve(dma32_phys_limit); @@ -718,6 +735,7 @@ retry: if (!check_l4) { disable_pgtable_l5(); check_l4 = true; + memset(early_pg_dir, 0, PAGE_SIZE); goto retry; } disable_pgtable_l4(); diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 77b5a03de13a..e084c72104f8 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -255,6 +255,10 @@ config HAVE_MARCH_Z15_FEATURES def_bool n select HAVE_MARCH_Z14_FEATURES +config HAVE_MARCH_Z16_FEATURES + def_bool n + select HAVE_MARCH_Z15_FEATURES + choice prompt "Processor type" default MARCH_Z196 @@ -312,6 +316,14 @@ config MARCH_Z15 and 8561 series). The kernel will be slightly faster but will not work on older machines. +config MARCH_Z16 + bool "IBM z16" + select HAVE_MARCH_Z16_FEATURES + depends on $(cc-option,-march=z16) + help + Select this to enable optimizations for IBM z16 (3931 and + 3932 series). + endchoice config MARCH_Z10_TUNE @@ -332,6 +344,9 @@ config MARCH_Z14_TUNE config MARCH_Z15_TUNE def_bool TUNE_Z15 || MARCH_Z15 && TUNE_DEFAULT +config MARCH_Z16_TUNE + def_bool TUNE_Z16 || MARCH_Z16 && TUNE_DEFAULT + choice prompt "Tune code generation" default TUNE_DEFAULT @@ -372,6 +387,10 @@ config TUNE_Z15 bool "IBM z15" depends on $(cc-option,-mtune=z15) +config TUNE_Z16 + bool "IBM z16" + depends on $(cc-option,-mtune=z16) + endchoice config 64BIT diff --git a/arch/s390/Makefile b/arch/s390/Makefile index 7a65bca1e5af..80eb3ee84ff1 100644 --- a/arch/s390/Makefile +++ b/arch/s390/Makefile @@ -20,7 +20,9 @@ LDFLAGS_vmlinux := -pie endif aflags_dwarf := -Wa,-gdwarf-2 KBUILD_AFLAGS_DECOMPRESSOR := $(CLANG_FLAGS) -m64 -D__ASSEMBLY__ +ifndef CONFIG_AS_IS_LLVM KBUILD_AFLAGS_DECOMPRESSOR += $(if $(CONFIG_DEBUG_INFO),$(aflags_dwarf)) +endif KBUILD_CFLAGS_DECOMPRESSOR := $(CLANG_FLAGS) -m64 -O2 -mpacked-stack KBUILD_CFLAGS_DECOMPRESSOR += -DDISABLE_BRANCH_PROFILING -D__NO_FORTIFY KBUILD_CFLAGS_DECOMPRESSOR += -fno-delete-null-pointer-checks -msoft-float -mbackchain @@ -30,6 +32,16 @@ KBUILD_CFLAGS_DECOMPRESSOR += -fno-stack-protector KBUILD_CFLAGS_DECOMPRESSOR += $(call cc-disable-warning, address-of-packed-member) KBUILD_CFLAGS_DECOMPRESSOR += $(if $(CONFIG_DEBUG_INFO),-g) KBUILD_CFLAGS_DECOMPRESSOR += $(if $(CONFIG_DEBUG_INFO_DWARF4), $(call cc-option, -gdwarf-4,)) + +ifdef CONFIG_CC_IS_GCC + ifeq ($(call cc-ifversion, -ge, 1200, y), y) + ifeq ($(call cc-ifversion, -lt, 1300, y), y) + KBUILD_CFLAGS += $(call cc-disable-warning, array-bounds) + KBUILD_CFLAGS_DECOMPRESSOR += $(call cc-disable-warning, array-bounds) + endif + endif +endif + UTS_MACHINE := s390x STACK_SIZE := $(if $(CONFIG_KASAN),65536,16384) CHECKFLAGS += -D__s390__ -D__s390x__ @@ -42,6 +54,7 @@ mflags-$(CONFIG_MARCH_ZEC12) := -march=zEC12 mflags-$(CONFIG_MARCH_Z13) := -march=z13 mflags-$(CONFIG_MARCH_Z14) := -march=z14 mflags-$(CONFIG_MARCH_Z15) := -march=z15 +mflags-$(CONFIG_MARCH_Z16) := -march=z16 export CC_FLAGS_MARCH := $(mflags-y) @@ -54,6 +67,7 @@ cflags-$(CONFIG_MARCH_ZEC12_TUNE) += -mtune=zEC12 cflags-$(CONFIG_MARCH_Z13_TUNE) += -mtune=z13 cflags-$(CONFIG_MARCH_Z14_TUNE) += -mtune=z14 cflags-$(CONFIG_MARCH_Z15_TUNE) += -mtune=z15 +cflags-$(CONFIG_MARCH_Z16_TUNE) += -mtune=z16 cflags-y += -Wa,-I$(srctree)/arch/$(ARCH)/include diff --git a/arch/s390/boot/.gitignore b/arch/s390/boot/.gitignore index b265bfede188..f56591bc0897 100644 --- a/arch/s390/boot/.gitignore +++ b/arch/s390/boot/.gitignore @@ -2,3 +2,6 @@ image bzImage section_cmp.* +vmlinux +vmlinux.lds +vmlinux.syms diff --git a/arch/s390/boot/Makefile b/arch/s390/boot/Makefile index 0ba646899131..883357a211a3 100644 --- a/arch/s390/boot/Makefile +++ b/arch/s390/boot/Makefile @@ -37,14 +37,21 @@ CFLAGS_sclp_early_core.o += -I$(srctree)/drivers/s390/char obj-y := head.o als.o startup.o mem_detect.o ipl_parm.o ipl_report.o obj-y += string.o ebcdic.o sclp_early_core.o mem.o ipl_vmparm.o cmdline.o -obj-y += version.o pgm_check_info.o ctype.o +obj-y += version.o pgm_check_info.o ctype.o ipl_data.o obj-$(findstring y, $(CONFIG_PROTECTED_VIRTUALIZATION_GUEST) $(CONFIG_PGSTE)) += uv.o obj-$(CONFIG_RELOCATABLE) += machine_kexec_reloc.o obj-$(CONFIG_RANDOMIZE_BASE) += kaslr.o -targets := bzImage startup.a section_cmp.boot.data section_cmp.boot.preserved.data $(obj-y) -subdir- := compressed +obj-y += $(if $(CONFIG_KERNEL_UNCOMPRESSED),,decompressor.o) info.o +obj-$(CONFIG_KERNEL_ZSTD) += clz_ctz.o +obj-all := $(obj-y) piggy.o syms.o + +targets := bzImage section_cmp.boot.data section_cmp.boot.preserved.data $(obj-y) +targets += vmlinux.lds vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 +targets += vmlinux.bin.xz vmlinux.bin.lzma vmlinux.bin.lzo vmlinux.bin.lz4 +targets += vmlinux.bin.zst info.bin syms.bin vmlinux.syms $(obj-all) OBJECTS := $(addprefix $(obj)/,$(obj-y)) +OBJECTS_ALL := $(addprefix $(obj)/,$(obj-all)) quiet_cmd_section_cmp = SECTCMP $* define cmd_section_cmp @@ -59,14 +66,67 @@ define cmd_section_cmp touch $@ endef -$(obj)/bzImage: $(obj)/compressed/vmlinux $(obj)/section_cmp.boot.data $(obj)/section_cmp.boot.preserved.data FORCE +$(obj)/bzImage: $(obj)/vmlinux $(obj)/section_cmp.boot.data $(obj)/section_cmp.boot.preserved.data FORCE $(call if_changed,objcopy) -$(obj)/section_cmp%: vmlinux $(obj)/compressed/vmlinux FORCE +$(obj)/section_cmp%: vmlinux $(obj)/vmlinux FORCE $(call if_changed,section_cmp) -$(obj)/compressed/vmlinux: $(obj)/startup.a FORCE - $(Q)$(MAKE) $(build)=$(obj)/compressed $@ +LDFLAGS_vmlinux := --oformat $(LD_BFD) -e startup --build-id=sha1 -T +$(obj)/vmlinux: $(obj)/vmlinux.lds $(OBJECTS_ALL) FORCE + $(call if_changed,ld) + +LDFLAGS_vmlinux.syms := --oformat $(LD_BFD) -e startup -T +$(obj)/vmlinux.syms: $(obj)/vmlinux.lds $(OBJECTS) FORCE + $(call if_changed,ld) + +quiet_cmd_dumpsyms = DUMPSYMS $< +define cmd_dumpsyms + $(NM) -n -S --format=bsd "$<" | sed -nE 's/^0*([0-9a-fA-F]+) 0*([0-9a-fA-F]+) [tT] ([^ ]*)$$/\1 \2 \3/p' | tr '\n' '\0' > "$@" +endef + +$(obj)/syms.bin: $(obj)/vmlinux.syms FORCE + $(call if_changed,dumpsyms) + +OBJCOPYFLAGS_syms.o := -I binary -O elf64-s390 -B s390:64-bit --rename-section .data=.decompressor.syms +$(obj)/syms.o: $(obj)/syms.bin FORCE + $(call if_changed,objcopy) + +OBJCOPYFLAGS_info.bin := -O binary --only-section=.vmlinux.info --set-section-flags .vmlinux.info=load +$(obj)/info.bin: vmlinux FORCE + $(call if_changed,objcopy) + +OBJCOPYFLAGS_info.o := -I binary -O elf64-s390 -B s390:64-bit --rename-section .data=.vmlinux.info +$(obj)/info.o: $(obj)/info.bin FORCE + $(call if_changed,objcopy) + +OBJCOPYFLAGS_vmlinux.bin := -O binary --remove-section=.comment --remove-section=.vmlinux.info -S +$(obj)/vmlinux.bin: vmlinux FORCE + $(call if_changed,objcopy) + +suffix-$(CONFIG_KERNEL_GZIP) := .gz +suffix-$(CONFIG_KERNEL_BZIP2) := .bz2 +suffix-$(CONFIG_KERNEL_LZ4) := .lz4 +suffix-$(CONFIG_KERNEL_LZMA) := .lzma +suffix-$(CONFIG_KERNEL_LZO) := .lzo +suffix-$(CONFIG_KERNEL_XZ) := .xz +suffix-$(CONFIG_KERNEL_ZSTD) := .zst -$(obj)/startup.a: $(OBJECTS) FORCE - $(call if_changed,ar) +$(obj)/vmlinux.bin.gz: $(obj)/vmlinux.bin FORCE + $(call if_changed,gzip) +$(obj)/vmlinux.bin.bz2: $(obj)/vmlinux.bin FORCE + $(call if_changed,bzip2_with_size) +$(obj)/vmlinux.bin.lz4: $(obj)/vmlinux.bin FORCE + $(call if_changed,lz4_with_size) +$(obj)/vmlinux.bin.lzma: $(obj)/vmlinux.bin FORCE + $(call if_changed,lzma_with_size) +$(obj)/vmlinux.bin.lzo: $(obj)/vmlinux.bin FORCE + $(call if_changed,lzo_with_size) +$(obj)/vmlinux.bin.xz: $(obj)/vmlinux.bin FORCE + $(call if_changed,xzkern_with_size) +$(obj)/vmlinux.bin.zst: $(obj)/vmlinux.bin FORCE + $(call if_changed,zstd22_with_size) + +OBJCOPYFLAGS_piggy.o := -I binary -O elf64-s390 -B s390:64-bit --rename-section .data=.vmlinux.bin.compressed +$(obj)/piggy.o: $(obj)/vmlinux.bin$(suffix-y) FORCE + $(call if_changed,objcopy) diff --git a/arch/s390/boot/boot.h b/arch/s390/boot/boot.h index 641ce0fc5c3e..70418389414d 100644 --- a/arch/s390/boot/boot.h +++ b/arch/s390/boot/boot.h @@ -2,9 +2,12 @@ #ifndef BOOT_BOOT_H #define BOOT_BOOT_H -#include <asm/extable.h> #include <linux/types.h> +#define IPL_START 0x200 + +#ifndef __ASSEMBLY__ + void startup_kernel(void); unsigned long detect_memory(void); bool is_ipl_block_dump(void); @@ -31,4 +34,5 @@ extern char _stack_start[], _stack_end[]; unsigned long read_ipl_report(unsigned long safe_offset); +#endif /* __ASSEMBLY__ */ #endif /* BOOT_BOOT_H */ diff --git a/arch/s390/boot/compressed/clz_ctz.c b/arch/s390/boot/clz_ctz.c index c3ebf248596b..c3ebf248596b 100644 --- a/arch/s390/boot/compressed/clz_ctz.c +++ b/arch/s390/boot/clz_ctz.c diff --git a/arch/s390/boot/compressed/Makefile b/arch/s390/boot/compressed/Makefile deleted file mode 100644 index d04e0e7de0b3..000000000000 --- a/arch/s390/boot/compressed/Makefile +++ /dev/null @@ -1,86 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -# -# linux/arch/s390/boot/compressed/Makefile -# -# create a compressed vmlinux image from the original vmlinux -# - -KCOV_INSTRUMENT := n -GCOV_PROFILE := n -UBSAN_SANITIZE := n -KASAN_SANITIZE := n -KCSAN_SANITIZE := n - -obj-y := $(if $(CONFIG_KERNEL_UNCOMPRESSED),,decompressor.o) info.o -obj-$(CONFIG_KERNEL_ZSTD) += clz_ctz.o -obj-all := $(obj-y) piggy.o syms.o -targets := vmlinux.lds vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 -targets += vmlinux.bin.xz vmlinux.bin.lzma vmlinux.bin.lzo vmlinux.bin.lz4 -targets += vmlinux.bin.zst -targets += info.bin syms.bin vmlinux.syms $(obj-all) - -KBUILD_AFLAGS := $(KBUILD_AFLAGS_DECOMPRESSOR) -KBUILD_CFLAGS := $(KBUILD_CFLAGS_DECOMPRESSOR) -OBJCOPYFLAGS := - -OBJECTS := $(addprefix $(obj)/,$(obj-y)) -OBJECTS_ALL := $(addprefix $(obj)/,$(obj-all)) - -LDFLAGS_vmlinux := --oformat $(LD_BFD) -e startup --build-id=sha1 -T -$(obj)/vmlinux: $(obj)/vmlinux.lds $(objtree)/arch/s390/boot/startup.a $(OBJECTS_ALL) FORCE - $(call if_changed,ld) - -LDFLAGS_vmlinux.syms := --oformat $(LD_BFD) -e startup -T -$(obj)/vmlinux.syms: $(obj)/vmlinux.lds $(objtree)/arch/s390/boot/startup.a $(OBJECTS) FORCE - $(call if_changed,ld) - -quiet_cmd_dumpsyms = DUMPSYMS $< -define cmd_dumpsyms - $(NM) -n -S --format=bsd "$<" | sed -nE 's/^0*([0-9a-fA-F]+) 0*([0-9a-fA-F]+) [tT] ([^ ]*)$$/\1 \2 \3/p' | tr '\n' '\0' > "$@" -endef - -$(obj)/syms.bin: $(obj)/vmlinux.syms FORCE - $(call if_changed,dumpsyms) - -OBJCOPYFLAGS_syms.o := -I binary -O elf64-s390 -B s390:64-bit --rename-section .data=.decompressor.syms -$(obj)/syms.o: $(obj)/syms.bin FORCE - $(call if_changed,objcopy) - -OBJCOPYFLAGS_info.bin := -O binary --only-section=.vmlinux.info --set-section-flags .vmlinux.info=load -$(obj)/info.bin: vmlinux FORCE - $(call if_changed,objcopy) - -OBJCOPYFLAGS_info.o := -I binary -O elf64-s390 -B s390:64-bit --rename-section .data=.vmlinux.info -$(obj)/info.o: $(obj)/info.bin FORCE - $(call if_changed,objcopy) - -OBJCOPYFLAGS_vmlinux.bin := -O binary --remove-section=.comment --remove-section=.vmlinux.info -S -$(obj)/vmlinux.bin: vmlinux FORCE - $(call if_changed,objcopy) - -suffix-$(CONFIG_KERNEL_GZIP) := .gz -suffix-$(CONFIG_KERNEL_BZIP2) := .bz2 -suffix-$(CONFIG_KERNEL_LZ4) := .lz4 -suffix-$(CONFIG_KERNEL_LZMA) := .lzma -suffix-$(CONFIG_KERNEL_LZO) := .lzo -suffix-$(CONFIG_KERNEL_XZ) := .xz -suffix-$(CONFIG_KERNEL_ZSTD) := .zst - -$(obj)/vmlinux.bin.gz: $(obj)/vmlinux.bin FORCE - $(call if_changed,gzip) -$(obj)/vmlinux.bin.bz2: $(obj)/vmlinux.bin FORCE - $(call if_changed,bzip2_with_size) -$(obj)/vmlinux.bin.lz4: $(obj)/vmlinux.bin FORCE - $(call if_changed,lz4_with_size) -$(obj)/vmlinux.bin.lzma: $(obj)/vmlinux.bin FORCE - $(call if_changed,lzma_with_size) -$(obj)/vmlinux.bin.lzo: $(obj)/vmlinux.bin FORCE - $(call if_changed,lzo_with_size) -$(obj)/vmlinux.bin.xz: $(obj)/vmlinux.bin FORCE - $(call if_changed,xzkern_with_size) -$(obj)/vmlinux.bin.zst: $(obj)/vmlinux.bin FORCE - $(call if_changed,zstd22_with_size) - -OBJCOPYFLAGS_piggy.o := -I binary -O elf64-s390 -B s390:64-bit --rename-section .data=.vmlinux.bin.compressed -$(obj)/piggy.o: $(obj)/vmlinux.bin$(suffix-y) FORCE - $(call if_changed,objcopy) diff --git a/arch/s390/boot/compressed/decompressor.c b/arch/s390/boot/decompressor.c index e27c2140d620..e27c2140d620 100644 --- a/arch/s390/boot/compressed/decompressor.c +++ b/arch/s390/boot/decompressor.c diff --git a/arch/s390/boot/compressed/decompressor.h b/arch/s390/boot/decompressor.h index f75cc31a77dd..f75cc31a77dd 100644 --- a/arch/s390/boot/compressed/decompressor.h +++ b/arch/s390/boot/decompressor.h diff --git a/arch/s390/boot/head.S b/arch/s390/boot/head.S index 666692429db0..3f79b9efb803 100644 --- a/arch/s390/boot/head.S +++ b/arch/s390/boot/head.S @@ -27,234 +27,181 @@ #include <asm/page.h> #include <asm/ptrace.h> #include <asm/sclp.h> - -#define ARCH_OFFSET 4 +#include "boot.h" #define EP_OFFSET 0x10008 #define EP_STRING "S390EP" +#define IPL_BS 0x730 __HEAD - -#define IPL_BS 0x730 - .org 0 - .long 0x00080000,0x80000000+iplstart # The first 24 bytes are loaded - .long 0x02000018,0x60000050 # by ipl to addresses 0-23. - .long 0x02000068,0x60000050 # (a PSW and two CCWs). - .fill 80-24,1,0x40 # bytes 24-79 are discarded !! - .long 0x020000f0,0x60000050 # The next 160 byte are loaded - .long 0x02000140,0x60000050 # to addresses 0x18-0xb7 - .long 0x02000190,0x60000050 # They form the continuation - .long 0x020001e0,0x60000050 # of the CCW program started - .long 0x02000230,0x60000050 # by ipl and load the range - .long 0x02000280,0x60000050 # 0x0f0-0x730 from the image - .long 0x020002d0,0x60000050 # to the range 0x0f0-0x730 - .long 0x02000320,0x60000050 # in memory. At the end of - .long 0x02000370,0x60000050 # the channel program the PSW - .long 0x020003c0,0x60000050 # at location 0 is loaded. - .long 0x02000410,0x60000050 # Initial processing starts - .long 0x02000460,0x60000050 # at 0x200 = iplstart. - .long 0x020004b0,0x60000050 - .long 0x02000500,0x60000050 - .long 0x02000550,0x60000050 - .long 0x020005a0,0x60000050 - .long 0x020005f0,0x60000050 - .long 0x02000640,0x60000050 - .long 0x02000690,0x60000050 - .long 0x020006e0,0x20000050 - - .org __LC_RST_NEW_PSW # 0x1a0 - .quad 0,iplstart - .org __LC_EXT_NEW_PSW # 0x1b0 - .quad 0x0002000180000000,0x1b0 # disabled wait - .org __LC_PGM_NEW_PSW # 0x1d0 - .quad 0x0000000180000000,startup_pgm_check_handler - .org __LC_IO_NEW_PSW # 0x1f0 - .quad 0x0002000180000000,0x1f0 # disabled wait - - .org 0x200 - +ipl_start: + mvi __LC_AR_MODE_ID,1 # set esame flag + slr %r0,%r0 # set cpuid to zero + lhi %r1,2 # mode 2 = esame (dump) + sigp %r1,%r0,0x12 # switch to esame mode + sam64 # switch to 64 bit addressing mode + lgh %r1,__LC_SUBCHANNEL_ID # test if subchannel number + brctg %r1,.Lnoload # is valid + llgf %r1,__LC_SUBCHANNEL_ID # load ipl subchannel number + lghi %r2,IPL_BS # load start address + bras %r14,.Lloader # load rest of ipl image + larl %r12,parmarea # pointer to parameter area + stg %r1,IPL_DEVICE-PARMAREA(%r12) # save ipl device number +# +# load parameter file from ipl device +# +.Lagain1: + larl %r2,_end # ramdisk loc. is temp + bras %r14,.Lloader # load parameter file + ltgr %r2,%r2 # got anything ? + jz .Lnopf + lg %r3,MAX_COMMAND_LINE_SIZE-PARMAREA(%r12) + aghi %r3,-1 + clgr %r2,%r3 + jl .Lnotrunc + lgr %r2,%r3 +.Lnotrunc: + larl %r4,_end + larl %r13,.L_hdr + clc 0(3,%r4),0(%r13) # if it is HDRx + jz .Lagain1 # skip dataset header + larl %r13,.L_eof + clc 0(3,%r4),0(%r13) # if it is EOFx + jz .Lagain1 # skip dateset trailer + lgr %r5,%r2 + la %r6,COMMAND_LINE-PARMAREA(%r12) + lgr %r7,%r2 + aghi %r7,1 + mvcl %r6,%r4 +.Lnopf: +# +# load ramdisk from ipl device +# +.Lagain2: + larl %r2,_end # addr of ramdisk + stg %r2,INITRD_START-PARMAREA(%r12) + bras %r14,.Lloader # load ramdisk + stg %r2,INITRD_SIZE-PARMAREA(%r12) # store size of rd + ltgr %r2,%r2 + jnz .Lrdcont + stg %r2,INITRD_START-PARMAREA(%r12) # no ramdisk found +.Lrdcont: + larl %r2,_end + larl %r13,.L_hdr # skip HDRx and EOFx + clc 0(3,%r2),0(%r13) + jz .Lagain2 + larl %r13,.L_eof + clc 0(3,%r2),0(%r13) + jz .Lagain2 +# +# reset files in VM reader +# + larl %r13,.Lcpuid + stidp 0(%r13) # store cpuid + tm 0(%r13),0xff # running VM ? + jno .Lnoreset + larl %r2,.Lreset + lghi %r3,26 + diag %r2,%r3,8 + larl %r5,.Lirb + stsch 0(%r5) # check if irq is pending + tm 30(%r5),0x0f # by verifying if any of the + jnz .Lwaitforirq # activity or status control + tm 31(%r5),0xff # bits is set in the schib + jz .Lnoreset +.Lwaitforirq: + bras %r14,.Lirqwait # wait for IO interrupt + c %r1,__LC_SUBCHANNEL_ID # compare subchannel number + jne .Lwaitforirq + larl %r5,.Lirb + tsch 0(%r5) +.Lnoreset: + j .Lnoload +# +# everything loaded, go for it +# +.Lnoload: + jg startup # # subroutine to wait for end I/O # .Lirqwait: - mvc __LC_IO_NEW_PSW(16),.Lnewpsw # set up IO interrupt psw - lpsw .Lwaitpsw + larl %r13,.Lnewpswmask # set up IO interrupt psw + mvc __LC_IO_NEW_PSW(8),0(%r13) + stg %r14,__LC_IO_NEW_PSW+8 + larl %r13,.Lwaitpsw + lpswe 0(%r13) .Lioint: - br %r14 - .align 8 -.Lnewpsw: - .quad 0x0000000080000000,.Lioint -.Lwaitpsw: - .long 0x020a0000,0x80000000+.Lioint - # # subroutine for loading cards from the reader # .Lloader: - la %r4,0(%r14) - la %r3,.Lorb # r2 = address of orb into r2 - la %r5,.Lirb # r4 = address of irb - la %r6,.Lccws - la %r7,20 + lgr %r4,%r14 + larl %r3,.Lorb # r2 = address of orb into r2 + larl %r5,.Lirb # r4 = address of irb + larl %r6,.Lccws + lghi %r7,20 .Linit: st %r2,4(%r6) # initialize CCW data addresses la %r2,0x50(%r2) la %r6,8(%r6) - bct 7,.Linit - - lctl %c6,%c6,.Lcr6 # set IO subclass mask - slr %r2,%r2 + brctg %r7,.Linit + larl %r13,.Lcr6 + lctlg %c6,%c6,0(%r13) + xgr %r2,%r2 .Lldlp: ssch 0(%r3) # load chunk of 1600 bytes - bnz .Llderr + jnz .Llderr .Lwait4irq: - bas %r14,.Lirqwait + bras %r14,.Lirqwait c %r1,__LC_SUBCHANNEL_ID # compare subchannel number - bne .Lwait4irq + jne .Lwait4irq tsch 0(%r5) - - slr %r0,%r0 + xgr %r0,%r0 ic %r0,8(%r5) # get device status - chi %r0,8 # channel end ? - be .Lcont - chi %r0,12 # channel end + device end ? - be .Lcont - - l %r0,4(%r5) - s %r0,8(%r3) # r0/8 = number of ccws executed - mhi %r0,10 # *10 = number of bytes in ccws - lh %r3,10(%r5) # get residual count - sr %r0,%r3 # #ccws*80-residual=#bytes read - ar %r2,%r0 - + cghi %r0,8 # channel end ? + je .Lcont + cghi %r0,12 # channel end + device end ? + je .Lcont + llgf %r0,4(%r5) + sgf %r0,8(%r3) # r0/8 = number of ccws executed + mghi %r0,10 # *10 = number of bytes in ccws + llgh %r3,10(%r5) # get residual count + sgr %r0,%r3 # #ccws*80-residual=#bytes read + agr %r2,%r0 br %r4 # r2 contains the total size - .Lcont: - ahi %r2,0x640 # add 0x640 to total size - la %r6,.Lccws - la %r7,20 + aghi %r2,0x640 # add 0x640 to total size + larl %r6,.Lccws + lghi %r7,20 .Lincr: l %r0,4(%r6) # update CCW data addresses - ahi %r0,0x640 + aghi %r0,0x640 st %r0,4(%r6) - ahi %r6,8 - bct 7,.Lincr - - b .Lldlp + aghi %r6,8 + brctg %r7,.Lincr + j .Lldlp .Llderr: - lpsw .Lcrash + larl %r13,.Lcrash + lpsw 0(%r13) .align 8 +.Lwaitpsw: + .quad 0x0202000180000000,.Lioint +.Lnewpswmask: + .quad 0x0000000180000000 + .align 8 .Lorb: .long 0x00000000,0x0080ff00,.Lccws .Lirb: .long 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0 -.Lcr6: .long 0xff000000 -.Lloadp:.long 0,0 + .align 8 +.Lcr6: .quad 0x00000000ff000000 .align 8 .Lcrash:.long 0x000a0000,0x00000000 - .align 8 .Lccws: .rept 19 .long 0x02600050,0x00000000 .endr .long 0x02200050,0x00000000 - -iplstart: - mvi __LC_AR_MODE_ID,1 # set esame flag - slr %r0,%r0 # set cpuid to zero - lhi %r1,2 # mode 2 = esame (dump) - sigp %r1,%r0,0x12 # switch to esame mode - bras %r13,0f - .fill 16,4,0x0 -0: lmh %r0,%r15,0(%r13) # clear high-order half of gprs - sam31 # switch to 31 bit addressing mode - lh %r1,__LC_SUBCHANNEL_ID # test if subchannel number - bct %r1,.Lnoload # is valid - l %r1,__LC_SUBCHANNEL_ID # load ipl subchannel number - la %r2,IPL_BS # load start address - bas %r14,.Lloader # load rest of ipl image - l %r12,.Lparm # pointer to parameter area - st %r1,IPL_DEVICE+ARCH_OFFSET-PARMAREA(%r12) # save ipl device number - -# -# load parameter file from ipl device -# -.Lagain1: - l %r2,.Linitrd # ramdisk loc. is temp - bas %r14,.Lloader # load parameter file - ltr %r2,%r2 # got anything ? - bz .Lnopf - l %r3,MAX_COMMAND_LINE_SIZE+ARCH_OFFSET-PARMAREA(%r12) - ahi %r3,-1 - clr %r2,%r3 - bl .Lnotrunc - lr %r2,%r3 -.Lnotrunc: - l %r4,.Linitrd - clc 0(3,%r4),.L_hdr # if it is HDRx - bz .Lagain1 # skip dataset header - clc 0(3,%r4),.L_eof # if it is EOFx - bz .Lagain1 # skip dateset trailer - - lr %r5,%r2 - la %r6,COMMAND_LINE-PARMAREA(%r12) - lr %r7,%r2 - ahi %r7,1 - mvcl %r6,%r4 -.Lnopf: - -# -# load ramdisk from ipl device -# -.Lagain2: - l %r2,.Linitrd # addr of ramdisk - st %r2,INITRD_START+ARCH_OFFSET-PARMAREA(%r12) - bas %r14,.Lloader # load ramdisk - st %r2,INITRD_SIZE+ARCH_OFFSET-PARMAREA(%r12) # store size of rd - ltr %r2,%r2 - bnz .Lrdcont - st %r2,INITRD_START+ARCH_OFFSET-PARMAREA(%r12) # no ramdisk found -.Lrdcont: - l %r2,.Linitrd - - clc 0(3,%r2),.L_hdr # skip HDRx and EOFx - bz .Lagain2 - clc 0(3,%r2),.L_eof - bz .Lagain2 - -# -# reset files in VM reader -# - stidp .Lcpuid # store cpuid - tm .Lcpuid,0xff # running VM ? - bno .Lnoreset - la %r2,.Lreset - lhi %r3,26 - diag %r2,%r3,8 - la %r5,.Lirb - stsch 0(%r5) # check if irq is pending - tm 30(%r5),0x0f # by verifying if any of the - bnz .Lwaitforirq # activity or status control - tm 31(%r5),0xff # bits is set in the schib - bz .Lnoreset -.Lwaitforirq: - bas %r14,.Lirqwait # wait for IO interrupt - c %r1,__LC_SUBCHANNEL_ID # compare subchannel number - bne .Lwaitforirq - la %r5,.Lirb - tsch 0(%r5) -.Lnoreset: - b .Lnoload - -# -# everything loaded, go for it -# -.Lnoload: - l %r1,.Lstartup - br %r1 - -.Linitrd:.long _end # default address of initrd -.Lparm: .long PARMAREA -.Lstartup: .long startup .Lreset:.byte 0xc3,0xc8,0xc1,0xd5,0xc7,0xc5,0x40,0xd9,0xc4,0xd9,0x40 .byte 0xc1,0xd3,0xd3,0x40,0xd2,0xc5,0xc5,0xd7,0x40,0xd5,0xd6 .byte 0xc8,0xd6,0xd3,0xc4 # "change rdr all keep nohold" @@ -268,10 +215,10 @@ iplstart: # this is called either by the ipl loader or directly by PSW restart # or linload or SALIPL # - .org STARTUP_NORMAL_OFFSET + .org STARTUP_NORMAL_OFFSET - IPL_START SYM_CODE_START(startup) j startup_normal - .org EP_OFFSET + .org EP_OFFSET - IPL_START # # This is a list of s390 kernel entry points. At address 0x1000f the number of # valid entry points is stored. @@ -283,7 +230,7 @@ SYM_CODE_START(startup) # # kdump startup-code, running in 64 bit absolute addressing mode # - .org STARTUP_KDUMP_OFFSET + .org STARTUP_KDUMP_OFFSET - IPL_START j startup_kdump SYM_CODE_END(startup) SYM_CODE_START_LOCAL(startup_normal) @@ -295,20 +242,23 @@ SYM_CODE_START_LOCAL(startup_normal) .fill 16,4,0x0 0: lmh %r0,%r15,0(%r13) # clear high-order half of gprs sam64 # switch to 64 bit addressing mode - basr %r13,0 # get base -.LPG0: - mvc __LC_EXT_NEW_PSW(16),.Lext_new_psw-.LPG0(%r13) - mvc __LC_PGM_NEW_PSW(16),.Lpgm_new_psw-.LPG0(%r13) - mvc __LC_IO_NEW_PSW(16),.Lio_new_psw-.LPG0(%r13) + larl %r13,.Lext_new_psw + mvc __LC_EXT_NEW_PSW(16),0(%r13) + larl %r13,.Lpgm_new_psw + mvc __LC_PGM_NEW_PSW(16),0(%r13) + larl %r13,.Lio_new_psw + mvc __LC_IO_NEW_PSW(16),0(%r13) xc 0x200(256),0x200 # partially clear lowcore xc 0x300(256),0x300 xc 0xe00(256),0xe00 xc 0xf00(256),0xf00 - lctlg %c0,%c15,.Lctl-.LPG0(%r13) # load control registers + larl %r13,.Lctl + lctlg %c0,%c15,0(%r13) # load control registers stcke __LC_BOOT_CLOCK mvc __LC_LAST_UPDATE_CLOCK(8),__LC_BOOT_CLOCK+1 - spt 6f-.LPG0(%r13) - mvc __LC_LAST_UPDATE_TIMER(8),6f-.LPG0(%r13) + larl %r13,6f + spt 0(%r13) + mvc __LC_LAST_UPDATE_TIMER(8),0(%r13) larl %r15,_stack_end-STACK_FRAME_OVERHEAD brasl %r14,sclp_early_setup_buffer brasl %r14,verify_facilities @@ -368,23 +318,3 @@ SYM_CODE_START_LOCAL(startup_pgm_check_handler) lmg %r0,%r15,__LC_GPREGS_SAVE_AREA-4095(%r8) lpswe __LC_RETURN_PSW # disabled wait SYM_CODE_END(startup_pgm_check_handler) - -# -# params at 10400 (setup.h) -# Must be keept in sync with struct parmarea in setup.h -# - .org PARMAREA -SYM_DATA_START(parmarea) - .quad 0 # IPL_DEVICE - .quad 0 # INITRD_START - .quad 0 # INITRD_SIZE - .quad 0 # OLDMEM_BASE - .quad 0 # OLDMEM_SIZE - .quad kernel_version # points to kernel version string - .quad COMMAND_LINE_SIZE - - .org COMMAND_LINE - .byte "root=/dev/ram0 ro" - .byte 0 - .org PARMAREA+__PARMAREA_SIZE -SYM_DATA_END(parmarea) diff --git a/arch/s390/boot/ipl_data.c b/arch/s390/boot/ipl_data.c new file mode 100644 index 000000000000..0846e2b249c6 --- /dev/null +++ b/arch/s390/boot/ipl_data.c @@ -0,0 +1,84 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/compat.h> +#include <linux/ptrace.h> +#include <asm/cio.h> +#include <asm/asm-offsets.h> +#include "boot.h" + +#define CCW0(cmd, addr, cnt, flg) \ + { .cmd_code = cmd, .cda = addr, .count = cnt, .flags = flg, } + +#define PSW_MASK_DISABLED (PSW_MASK_WAIT | PSW_MASK_EA | PSW_MASK_BA) + +struct ipl_lowcore { + psw_t32 ipl_psw; /* 0x0000 */ + struct ccw0 ccwpgm[2]; /* 0x0008 */ + u8 fill[56]; /* 0x0018 */ + struct ccw0 ccwpgmcc[20]; /* 0x0050 */ + u8 pad_0xf0[0x01a0-0x00f0]; /* 0x00f0 */ + psw_t restart_psw; /* 0x01a0 */ + psw_t external_new_psw; /* 0x01b0 */ + psw_t svc_new_psw; /* 0x01c0 */ + psw_t program_new_psw; /* 0x01d0 */ + psw_t mcck_new_psw; /* 0x01e0 */ + psw_t io_new_psw; /* 0x01f0 */ +}; + +/* + * Initial lowcore for IPL: the first 24 bytes are loaded by IPL to + * addresses 0-23 (a PSW and two CCWs). Bytes 24-79 are discarded. + * The next 160 bytes are loaded to addresses 0x18-0xb7. They form + * the continuation of the CCW program started by IPL and load the + * range 0x0f0-0x730 from the image to the range 0x0f0-0x730 in + * memory. At the end of the channel program the PSW at location 0 is + * loaded. + * Initial processing starts at 0x200 = iplstart. + * + * The restart psw points to iplstart which allows to load a kernel + * image into memory and starting it by a psw restart on any cpu. All + * other default psw new locations contain a disabled wait psw where + * the address indicates which psw was loaded. + * + * Note that the 'file' utility can detect s390 kernel images. For + * that to succeed the two initial CCWs, and the 0x40 fill bytes must + * be present. + */ +static struct ipl_lowcore ipl_lowcore __used __section(".ipldata") = { + .ipl_psw = { .mask = PSW32_MASK_BASE, .addr = PSW32_ADDR_AMODE | IPL_START }, + .ccwpgm = { + [ 0] = CCW0(CCW_CMD_READ_IPL, 0x018, 0x50, CCW_FLAG_SLI | CCW_FLAG_CC), + [ 1] = CCW0(CCW_CMD_READ_IPL, 0x068, 0x50, CCW_FLAG_SLI | CCW_FLAG_CC), + }, + .fill = { + [ 0 ... 55] = 0x40, + }, + .ccwpgmcc = { + [ 0] = CCW0(CCW_CMD_READ_IPL, 0x0f0, 0x50, CCW_FLAG_SLI | CCW_FLAG_CC), + [ 1] = CCW0(CCW_CMD_READ_IPL, 0x140, 0x50, CCW_FLAG_SLI | CCW_FLAG_CC), + [ 2] = CCW0(CCW_CMD_READ_IPL, 0x190, 0x50, CCW_FLAG_SLI | CCW_FLAG_CC), + [ 3] = CCW0(CCW_CMD_READ_IPL, 0x1e0, 0x50, CCW_FLAG_SLI | CCW_FLAG_CC), + [ 4] = CCW0(CCW_CMD_READ_IPL, 0x230, 0x50, CCW_FLAG_SLI | CCW_FLAG_CC), + [ 5] = CCW0(CCW_CMD_READ_IPL, 0x280, 0x50, CCW_FLAG_SLI | CCW_FLAG_CC), + [ 6] = CCW0(CCW_CMD_READ_IPL, 0x2d0, 0x50, CCW_FLAG_SLI | CCW_FLAG_CC), + [ 7] = CCW0(CCW_CMD_READ_IPL, 0x320, 0x50, CCW_FLAG_SLI | CCW_FLAG_CC), + [ 8] = CCW0(CCW_CMD_READ_IPL, 0x370, 0x50, CCW_FLAG_SLI | CCW_FLAG_CC), + [ 9] = CCW0(CCW_CMD_READ_IPL, 0x3c0, 0x50, CCW_FLAG_SLI | CCW_FLAG_CC), + [10] = CCW0(CCW_CMD_READ_IPL, 0x410, 0x50, CCW_FLAG_SLI | CCW_FLAG_CC), + [11] = CCW0(CCW_CMD_READ_IPL, 0x460, 0x50, CCW_FLAG_SLI | CCW_FLAG_CC), + [12] = CCW0(CCW_CMD_READ_IPL, 0x4b0, 0x50, CCW_FLAG_SLI | CCW_FLAG_CC), + [13] = CCW0(CCW_CMD_READ_IPL, 0x500, 0x50, CCW_FLAG_SLI | CCW_FLAG_CC), + [14] = CCW0(CCW_CMD_READ_IPL, 0x550, 0x50, CCW_FLAG_SLI | CCW_FLAG_CC), + [15] = CCW0(CCW_CMD_READ_IPL, 0x5a0, 0x50, CCW_FLAG_SLI | CCW_FLAG_CC), + [16] = CCW0(CCW_CMD_READ_IPL, 0x5f0, 0x50, CCW_FLAG_SLI | CCW_FLAG_CC), + [17] = CCW0(CCW_CMD_READ_IPL, 0x640, 0x50, CCW_FLAG_SLI | CCW_FLAG_CC), + [18] = CCW0(CCW_CMD_READ_IPL, 0x690, 0x50, CCW_FLAG_SLI | CCW_FLAG_CC), + [19] = CCW0(CCW_CMD_READ_IPL, 0x6e0, 0x50, CCW_FLAG_SLI), + }, + .restart_psw = { .mask = 0, .addr = IPL_START, }, + .external_new_psw = { .mask = PSW_MASK_DISABLED, .addr = __LC_EXT_NEW_PSW, }, + .svc_new_psw = { .mask = PSW_MASK_DISABLED, .addr = __LC_SVC_NEW_PSW, }, + .program_new_psw = { .mask = PSW_MASK_DISABLED, .addr = __LC_PGM_NEW_PSW, }, + .mcck_new_psw = { .mask = PSW_MASK_DISABLED, .addr = __LC_MCK_NEW_PSW, }, + .io_new_psw = { .mask = PSW_MASK_DISABLED, .addr = __LC_IO_NEW_PSW, }, +}; diff --git a/arch/s390/boot/ipl_parm.c b/arch/s390/boot/ipl_parm.c index 9ed7e29c81d9..ca78d6162245 100644 --- a/arch/s390/boot/ipl_parm.c +++ b/arch/s390/boot/ipl_parm.c @@ -8,9 +8,16 @@ #include <asm/sections.h> #include <asm/boot_data.h> #include <asm/facility.h> +#include <asm/setup.h> #include <asm/uv.h> #include "boot.h" +struct parmarea parmarea __section(".parmarea") = { + .kernel_version = (unsigned long)kernel_version, + .max_command_line_size = COMMAND_LINE_SIZE, + .command_line = "root=/dev/ram0 ro", +}; + char __bootdata(early_command_line)[COMMAND_LINE_SIZE]; int __bootdata(noexec_disabled); diff --git a/arch/s390/boot/kaslr.c b/arch/s390/boot/kaslr.c index d8984462071f..e8d74d4f62aa 100644 --- a/arch/s390/boot/kaslr.c +++ b/arch/s390/boot/kaslr.c @@ -8,7 +8,7 @@ #include <asm/timex.h> #include <asm/sclp.h> #include <asm/kasan.h> -#include "compressed/decompressor.h" +#include "decompressor.h" #include "boot.h" #define PRNG_MODE_TDES 1 diff --git a/arch/s390/boot/mem_detect.c b/arch/s390/boot/mem_detect.c index 2f949cd9076b..7fa1a32ea0f3 100644 --- a/arch/s390/boot/mem_detect.c +++ b/arch/s390/boot/mem_detect.c @@ -7,7 +7,7 @@ #include <asm/sections.h> #include <asm/mem_detect.h> #include <asm/sparsemem.h> -#include "compressed/decompressor.h" +#include "decompressor.h" #include "boot.h" struct mem_detect_info __bootdata(mem_detect); diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c index 1aa11a8f57dd..863e6bcaa5a1 100644 --- a/arch/s390/boot/startup.c +++ b/arch/s390/boot/startup.c @@ -10,7 +10,7 @@ #include <asm/sclp.h> #include <asm/diag.h> #include <asm/uv.h> -#include "compressed/decompressor.h" +#include "decompressor.h" #include "boot.h" #include "uv.h" diff --git a/arch/s390/boot/compressed/vmlinux.lds.S b/arch/s390/boot/vmlinux.lds.S index 918e05137d4c..af5c6860e0a1 100644 --- a/arch/s390/boot/compressed/vmlinux.lds.S +++ b/arch/s390/boot/vmlinux.lds.S @@ -4,6 +4,7 @@ #include <asm/thread_info.h> #include <asm/page.h> #include <asm/sclp.h> +#include "boot.h" OUTPUT_FORMAT("elf64-s390", "elf64-s390", "elf64-s390") OUTPUT_ARCH(s390:64-bit) @@ -13,11 +14,19 @@ ENTRY(startup) SECTIONS { . = 0; + .ipldata : { + *(.ipldata) + } + . = IPL_START; .head.text : { _head = . ; HEAD_TEXT _ehead = . ; } + . = PARMAREA; + .parmarea : { + *(.parmarea) + } .text : { _text = .; /* Text */ *(.text) diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 498bed9b261b..f6dfde577ce8 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -499,11 +499,13 @@ CONFIG_NLMON=m # CONFIG_NET_VENDOR_CHELSIO is not set # CONFIG_NET_VENDOR_CISCO is not set # CONFIG_NET_VENDOR_CORTINA is not set +# CONFIG_NET_VENDOR_DAVICOM is not set # CONFIG_NET_VENDOR_DEC is not set # CONFIG_NET_VENDOR_DLINK is not set # CONFIG_NET_VENDOR_EMULEX is not set # CONFIG_NET_VENDOR_ENGLEDER is not set # CONFIG_NET_VENDOR_EZCHIP is not set +# CONFIG_NET_VENDOR_FUNGIBLE is not set # CONFIG_NET_VENDOR_GOOGLE is not set # CONFIG_NET_VENDOR_HUAWEI is not set # CONFIG_NET_VENDOR_INTEL is not set @@ -588,13 +590,13 @@ CONFIG_MLX5_INFINIBAND=m CONFIG_SYNC_FILE=y CONFIG_VFIO=m CONFIG_VFIO_PCI=m +CONFIG_MLX5_VFIO_PCI=m CONFIG_VFIO_MDEV=m CONFIG_VIRTIO_PCI=m CONFIG_VIRTIO_BALLOON=m CONFIG_VIRTIO_INPUT=y CONFIG_VHOST_NET=m CONFIG_VHOST_VSOCK=m -# CONFIG_SURFACE_PLATFORMS is not set CONFIG_S390_CCW_IOMMU=y CONFIG_S390_AP_IOMMU=y CONFIG_EXT4_FS=y @@ -690,6 +692,7 @@ CONFIG_ENCRYPTED_KEYS=m CONFIG_KEY_NOTIFICATIONS=y CONFIG_SECURITY=y CONFIG_SECURITY_NETWORK=y +CONFIG_HARDENED_USERCOPY=y CONFIG_FORTIFY_SOURCE=y CONFIG_SECURITY_SELINUX=y CONFIG_SECURITY_SELINUX_BOOTPARAM=y @@ -733,6 +736,7 @@ CONFIG_CRYPTO_MD5=y CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD160=m CONFIG_CRYPTO_SHA3=m +CONFIG_CRYPTO_SM3=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_AES_TI=m CONFIG_CRYPTO_ANUBIS=m @@ -786,7 +790,6 @@ CONFIG_DMA_CMA=y CONFIG_CMA_SIZE_MBYTES=0 CONFIG_PRINTK_TIME=y CONFIG_DYNAMIC_DEBUG=y -CONFIG_DEBUG_INFO=y CONFIG_DEBUG_INFO_DWARF4=y CONFIG_DEBUG_INFO_BTF=y CONFIG_GDB_SCRIPTS=y @@ -814,6 +817,7 @@ CONFIG_DEBUG_MEMORY_INIT=y CONFIG_MEMORY_NOTIFIER_ERROR_INJECT=m CONFIG_DEBUG_PER_CPU_MAPS=y CONFIG_KFENCE=y +CONFIG_KFENCE_DEFERRABLE=y CONFIG_KFENCE_STATIC_KEYS=y CONFIG_DEBUG_SHIRQ=y CONFIG_PANIC_ON_OOPS=y diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index 61e36b999f67..706df3a4a867 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -490,11 +490,13 @@ CONFIG_NLMON=m # CONFIG_NET_VENDOR_CHELSIO is not set # CONFIG_NET_VENDOR_CISCO is not set # CONFIG_NET_VENDOR_CORTINA is not set +# CONFIG_NET_VENDOR_DAVICOM is not set # CONFIG_NET_VENDOR_DEC is not set # CONFIG_NET_VENDOR_DLINK is not set # CONFIG_NET_VENDOR_EMULEX is not set # CONFIG_NET_VENDOR_ENGLEDER is not set # CONFIG_NET_VENDOR_EZCHIP is not set +# CONFIG_NET_VENDOR_FUNGIBLE is not set # CONFIG_NET_VENDOR_GOOGLE is not set # CONFIG_NET_VENDOR_HUAWEI is not set # CONFIG_NET_VENDOR_INTEL is not set @@ -578,13 +580,13 @@ CONFIG_MLX5_INFINIBAND=m CONFIG_SYNC_FILE=y CONFIG_VFIO=m CONFIG_VFIO_PCI=m +CONFIG_MLX5_VFIO_PCI=m CONFIG_VFIO_MDEV=m CONFIG_VIRTIO_PCI=m CONFIG_VIRTIO_BALLOON=m CONFIG_VIRTIO_INPUT=y CONFIG_VHOST_NET=m CONFIG_VHOST_VSOCK=m -# CONFIG_SURFACE_PLATFORMS is not set CONFIG_S390_CCW_IOMMU=y CONFIG_S390_AP_IOMMU=y CONFIG_EXT4_FS=y @@ -720,6 +722,7 @@ CONFIG_CRYPTO_MD5=y CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD160=m CONFIG_CRYPTO_SHA3=m +CONFIG_CRYPTO_SM3=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_AES_TI=m CONFIG_CRYPTO_ANUBIS=m @@ -772,7 +775,6 @@ CONFIG_DMA_CMA=y CONFIG_CMA_SIZE_MBYTES=0 CONFIG_PRINTK_TIME=y CONFIG_DYNAMIC_DEBUG=y -CONFIG_DEBUG_INFO=y CONFIG_DEBUG_INFO_DWARF4=y CONFIG_DEBUG_INFO_BTF=y CONFIG_GDB_SCRIPTS=y diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig index c55c668dc3c7..a87fcc45e307 100644 --- a/arch/s390/configs/zfcpdump_defconfig +++ b/arch/s390/configs/zfcpdump_defconfig @@ -26,6 +26,7 @@ CONFIG_CRASH_DUMP=y # CONFIG_S390_GUEST is not set # CONFIG_SECCOMP is not set # CONFIG_GCC_PLUGINS is not set +# CONFIG_BLOCK_LEGACY_AUTOLOAD is not set CONFIG_PARTITION_ADVANCED=y # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set # CONFIG_COMPACTION is not set @@ -60,7 +61,6 @@ CONFIG_ZFCP=y # CONFIG_HID is not set # CONFIG_VIRTIO_MENU is not set # CONFIG_VHOST_MENU is not set -# CONFIG_SURFACE_PLATFORMS is not set # CONFIG_IOMMU_SUPPORT is not set # CONFIG_DNOTIFY is not set # CONFIG_INOTIFY_USER is not set @@ -71,10 +71,10 @@ CONFIG_LSM="yama,loadpin,safesetid,integrity" CONFIG_XZ_DEC_MICROLZMA=y CONFIG_PRINTK_TIME=y # CONFIG_SYMBOLIC_ERRNAME is not set -CONFIG_DEBUG_INFO=y +CONFIG_DEBUG_KERNEL=y +CONFIG_DEBUG_INFO_DWARF4=y CONFIG_DEBUG_INFO_BTF=y CONFIG_DEBUG_FS=y -CONFIG_DEBUG_KERNEL=y CONFIG_PANIC_ON_OOPS=y # CONFIG_SCHED_DEBUG is not set CONFIG_RCU_CPU_STALL_TIMEOUT=60 diff --git a/arch/s390/crypto/des_s390.c b/arch/s390/crypto/des_s390.c index bfbafd35bcbd..e013088b5115 100644 --- a/arch/s390/crypto/des_s390.c +++ b/arch/s390/crypto/des_s390.c @@ -194,7 +194,7 @@ static struct skcipher_alg cbc_des_alg = { * same as DES. Implementers MUST reject keys that exhibit this * property. * - * In fips mode additinally check for all 3 keys are unique. + * In fips mode additionally check for all 3 keys are unique. * */ static int des3_setkey(struct crypto_tfm *tfm, const u8 *key, diff --git a/arch/s390/crypto/prng.c b/arch/s390/crypto/prng.c index 234d791ca59d..ae382bafc772 100644 --- a/arch/s390/crypto/prng.c +++ b/arch/s390/crypto/prng.c @@ -528,7 +528,7 @@ static ssize_t prng_tdes_read(struct file *file, char __user *ubuf, /* give mutex free before calling schedule() */ mutex_unlock(&prng_data->mutex); schedule(); - /* occopy mutex again */ + /* occupy mutex again */ if (mutex_lock_interruptible(&prng_data->mutex)) { if (ret == 0) ret = -ERESTARTSYS; diff --git a/arch/s390/hypfs/hypfs_vm.c b/arch/s390/hypfs/hypfs_vm.c index 3765c2d81df5..a3d881ca0a98 100644 --- a/arch/s390/hypfs/hypfs_vm.c +++ b/arch/s390/hypfs/hypfs_vm.c @@ -190,7 +190,7 @@ int hypfs_vm_create_files(struct dentry *root) if (IS_ERR(data)) return PTR_ERR(data); - /* Hpervisor Info */ + /* Hypervisor Info */ dir = hypfs_mkdir(root, "hyp"); if (IS_ERR(dir)) { rc = PTR_ERR(dir); diff --git a/arch/s390/include/asm/alternative-asm.h b/arch/s390/include/asm/alternative-asm.h index bb3837d7387c..7db046596b93 100644 --- a/arch/s390/include/asm/alternative-asm.h +++ b/arch/s390/include/asm/alternative-asm.h @@ -5,19 +5,6 @@ #ifdef __ASSEMBLY__ /* - * Check the length of an instruction sequence. The length may not be larger - * than 254 bytes and it has to be divisible by 2. - */ -.macro alt_len_check start,end - .if ( \end - \start ) > 254 - .error "cpu alternatives does not support instructions blocks > 254 bytes\n" - .endif - .if ( \end - \start ) % 2 - .error "cpu alternatives instructions length is odd\n" - .endif -.endm - -/* * Issue one struct alt_instr descriptor entry (need to put it into * the section .altinstructions, see below). This entry contains * enough information for the alternatives patching code to patch an @@ -28,66 +15,29 @@ .long \alt_start - . .word \feature .byte \orig_end - \orig_start - .byte \alt_end - \alt_start -.endm - -/* - * Fill up @bytes with nops. The macro emits 6-byte nop instructions - * for the bulk of the area, possibly followed by a 4-byte and/or - * a 2-byte nop if the size of the area is not divisible by 6. - */ -.macro alt_pad_fill bytes - .rept ( \bytes ) / 6 - brcl 0,0 - .endr - .rept ( \bytes ) % 6 / 4 - nop - .endr - .rept ( \bytes ) % 6 % 4 / 2 - nopr - .endr -.endm - -/* - * Fill up @bytes with nops. If the number of bytes is larger - * than 6, emit a jg instruction to branch over all nops, then - * fill an area of size (@bytes - 6) with nop instructions. - */ -.macro alt_pad bytes - .if ( \bytes > 0 ) - .if ( \bytes > 6 ) - jg . + \bytes - alt_pad_fill \bytes - 6 - .else - alt_pad_fill \bytes - .endif - .endif + .org . - ( \orig_end - \orig_start ) + ( \alt_end - \alt_start ) + .org . - ( \alt_end - \alt_start ) + ( \orig_end - \orig_start ) .endm /* * Define an alternative between two instructions. If @feature is * present, early code in apply_alternatives() replaces @oldinstr with - * @newinstr. ".skip" directive takes care of proper instruction padding - * in case @newinstr is longer than @oldinstr. + * @newinstr. */ .macro ALTERNATIVE oldinstr, newinstr, feature .pushsection .altinstr_replacement,"ax" 770: \newinstr 771: .popsection 772: \oldinstr -773: alt_len_check 770b, 771b - alt_len_check 772b, 773b - alt_pad ( ( 771b - 770b ) - ( 773b - 772b ) ) -774: .pushsection .altinstructions,"a" - alt_entry 772b, 774b, 770b, 771b, \feature +773: .pushsection .altinstructions,"a" + alt_entry 772b, 773b, 770b, 771b, \feature .popsection .endm /* * Define an alternative between two instructions. If @feature is * present, early code in apply_alternatives() replaces @oldinstr with - * @newinstr. ".skip" directive takes care of proper instruction padding - * in case @newinstr is longer than @oldinstr. + * @newinstr. */ .macro ALTERNATIVE_2 oldinstr, newinstr1, feature1, newinstr2, feature2 .pushsection .altinstr_replacement,"ax" @@ -95,17 +45,9 @@ 771: \newinstr2 772: .popsection 773: \oldinstr -774: alt_len_check 770b, 771b - alt_len_check 771b, 772b - alt_len_check 773b, 774b - .if ( 771b - 770b > 772b - 771b ) - alt_pad ( ( 771b - 770b ) - ( 774b - 773b ) ) - .else - alt_pad ( ( 772b - 771b ) - ( 774b - 773b ) ) - .endif -775: .pushsection .altinstructions,"a" - alt_entry 773b, 775b, 770b, 771b,\feature1 - alt_entry 773b, 775b, 771b, 772b,\feature2 +774: .pushsection .altinstructions,"a" + alt_entry 773b, 774b, 770b, 771b,\feature1 + alt_entry 773b, 774b, 771b, 772b,\feature2 .popsection .endm diff --git a/arch/s390/include/asm/alternative.h b/arch/s390/include/asm/alternative.h index 3f2856ed6808..904dd049f954 100644 --- a/arch/s390/include/asm/alternative.h +++ b/arch/s390/include/asm/alternative.h @@ -13,32 +13,25 @@ struct alt_instr { s32 repl_offset; /* offset to replacement instruction */ u16 facility; /* facility bit set for replacement */ u8 instrlen; /* length of original instruction */ - u8 replacementlen; /* length of new instruction */ } __packed; void apply_alternative_instructions(void); void apply_alternatives(struct alt_instr *start, struct alt_instr *end); /* - * |661: |662: |6620 |663: - * +-----------+---------------------+ - * | oldinstr | oldinstr_padding | - * | +----------+----------+ - * | | | | - * | | >6 bytes |6/4/2 nops| - * | |6 bytes jg-----------> - * +-----------+---------------------+ - * ^^ static padding ^^ + * +---------------------------------+ + * |661: |662: + * | oldinstr | + * +---------------------------------+ * * .altinstr_replacement section - * +---------------------+-----------+ + * +---------------------------------+ * |6641: |6651: * | alternative instr 1 | - * +-----------+---------+- - - - - -+ - * |6642: |6652: | - * | alternative instr 2 | padding - * +---------------------+- - - - - -+ - * ^ runtime ^ + * +---------------------------------+ + * |6642: |6652: + * | alternative instr 2 | + * +---------------------------------+ * * .altinstructions section * +---------------------------------+ @@ -47,77 +40,31 @@ void apply_alternatives(struct alt_instr *start, struct alt_instr *end); * +---------------------------------+ */ -#define b_altinstr(num) "664"#num -#define e_altinstr(num) "665"#num - -#define e_oldinstr_pad_end "663" +#define b_altinstr(num) "664"#num +#define e_altinstr(num) "665"#num #define oldinstr_len "662b-661b" -#define oldinstr_total_len e_oldinstr_pad_end"b-661b" #define altinstr_len(num) e_altinstr(num)"b-"b_altinstr(num)"b" -#define oldinstr_pad_len(num) \ - "-(((" altinstr_len(num) ")-(" oldinstr_len ")) > 0) * " \ - "((" altinstr_len(num) ")-(" oldinstr_len "))" - -#define INSTR_LEN_SANITY_CHECK(len) \ - ".if " len " > 254\n" \ - "\t.error \"cpu alternatives does not support instructions " \ - "blocks > 254 bytes\"\n" \ - ".endif\n" \ - ".if (" len ") %% 2\n" \ - "\t.error \"cpu alternatives instructions length is odd\"\n" \ - ".endif\n" - -#define OLDINSTR_PADDING(oldinstr, num) \ - ".if " oldinstr_pad_len(num) " > 6\n" \ - "\tjg " e_oldinstr_pad_end "f\n" \ - "6620:\n" \ - "\t.rept (" oldinstr_pad_len(num) " - (6620b-662b)) / 2\n" \ - "\tnopr\n" \ - ".else\n" \ - "\t.rept " oldinstr_pad_len(num) " / 6\n" \ - "\t.brcl 0,0\n" \ - "\t.endr\n" \ - "\t.rept " oldinstr_pad_len(num) " %% 6 / 4\n" \ - "\tnop\n" \ - "\t.endr\n" \ - "\t.rept " oldinstr_pad_len(num) " %% 6 %% 4 / 2\n" \ - "\tnopr\n" \ - ".endr\n" \ - ".endif\n" - -#define OLDINSTR(oldinstr, num) \ - "661:\n\t" oldinstr "\n662:\n" \ - OLDINSTR_PADDING(oldinstr, num) \ - e_oldinstr_pad_end ":\n" \ - INSTR_LEN_SANITY_CHECK(oldinstr_len) - -#define OLDINSTR_2(oldinstr, num1, num2) \ - "661:\n\t" oldinstr "\n662:\n" \ - ".if " altinstr_len(num1) " < " altinstr_len(num2) "\n" \ - OLDINSTR_PADDING(oldinstr, num2) \ - ".else\n" \ - OLDINSTR_PADDING(oldinstr, num1) \ - ".endif\n" \ - e_oldinstr_pad_end ":\n" \ - INSTR_LEN_SANITY_CHECK(oldinstr_len) + +#define OLDINSTR(oldinstr) \ + "661:\n\t" oldinstr "\n662:\n" #define ALTINSTR_ENTRY(facility, num) \ "\t.long 661b - .\n" /* old instruction */ \ "\t.long " b_altinstr(num)"b - .\n" /* alt instruction */ \ "\t.word " __stringify(facility) "\n" /* facility bit */ \ - "\t.byte " oldinstr_total_len "\n" /* source len */ \ - "\t.byte " altinstr_len(num) "\n" /* alt instruction len */ + "\t.byte " oldinstr_len "\n" /* instruction len */ \ + "\t.org . - (" oldinstr_len ") + (" altinstr_len(num) ")\n" \ + "\t.org . - (" altinstr_len(num) ") + (" oldinstr_len ")\n" #define ALTINSTR_REPLACEMENT(altinstr, num) /* replacement */ \ - b_altinstr(num)":\n\t" altinstr "\n" e_altinstr(num) ":\n" \ - INSTR_LEN_SANITY_CHECK(altinstr_len(num)) + b_altinstr(num)":\n\t" altinstr "\n" e_altinstr(num) ":\n" /* alternative assembly primitive: */ #define ALTERNATIVE(oldinstr, altinstr, facility) \ ".pushsection .altinstr_replacement, \"ax\"\n" \ ALTINSTR_REPLACEMENT(altinstr, 1) \ ".popsection\n" \ - OLDINSTR(oldinstr, 1) \ + OLDINSTR(oldinstr) \ ".pushsection .altinstructions,\"a\"\n" \ ALTINSTR_ENTRY(facility, 1) \ ".popsection\n" @@ -127,7 +74,7 @@ void apply_alternatives(struct alt_instr *start, struct alt_instr *end); ALTINSTR_REPLACEMENT(altinstr1, 1) \ ALTINSTR_REPLACEMENT(altinstr2, 2) \ ".popsection\n" \ - OLDINSTR_2(oldinstr, 1, 2) \ + OLDINSTR(oldinstr) \ ".pushsection .altinstructions,\"a\"\n" \ ALTINSTR_ENTRY(facility1, 1) \ ALTINSTR_ENTRY(facility2, 2) \ diff --git a/arch/s390/include/asm/asm-extable.h b/arch/s390/include/asm/asm-extable.h index fb62df5e16a2..f24d9591aaed 100644 --- a/arch/s390/include/asm/asm-extable.h +++ b/arch/s390/include/asm/asm-extable.h @@ -26,16 +26,16 @@ stringify_in_c(.long (_target) - .;) \ stringify_in_c(.short (_type);) \ stringify_in_c(.macro extable_reg reg;) \ - stringify_in_c(.set found, 0;) \ - stringify_in_c(.set regnr, 0;) \ + stringify_in_c(.set .Lfound, 0;) \ + stringify_in_c(.set .Lregnr, 0;) \ stringify_in_c(.irp rs,r0,r1,r2,r3,r4,r5,r6,r7,r8,r9,r10,r11,r12,r13,r14,r15;) \ stringify_in_c(.ifc "\reg", "%%\rs";) \ - stringify_in_c(.set found, 1;) \ - stringify_in_c(.short regnr;) \ + stringify_in_c(.set .Lfound, 1;) \ + stringify_in_c(.short .Lregnr;) \ stringify_in_c(.endif;) \ - stringify_in_c(.set regnr, regnr+1;) \ + stringify_in_c(.set .Lregnr, .Lregnr+1;) \ stringify_in_c(.endr;) \ - stringify_in_c(.ifne (found != 1);) \ + stringify_in_c(.ifne (.Lfound != 1);) \ stringify_in_c(.error "extable_reg: bad register argument";) \ stringify_in_c(.endif;) \ stringify_in_c(.endm;) \ diff --git a/arch/s390/include/asm/barrier.h b/arch/s390/include/asm/barrier.h index 2c057e1f3200..82de2a7c4160 100644 --- a/arch/s390/include/asm/barrier.h +++ b/arch/s390/include/asm/barrier.h @@ -26,14 +26,14 @@ static __always_inline void bcr_serialize(void) asm volatile(__ASM_BCR_SERIALIZE : : : "memory"); } -#define mb() bcr_serialize() -#define rmb() barrier() -#define wmb() barrier() -#define dma_rmb() mb() -#define dma_wmb() mb() -#define __smp_mb() mb() -#define __smp_rmb() rmb() -#define __smp_wmb() wmb() +#define __mb() bcr_serialize() +#define __rmb() barrier() +#define __wmb() barrier() +#define __dma_rmb() __mb() +#define __dma_wmb() __mb() +#define __smp_mb() __mb() +#define __smp_rmb() __rmb() +#define __smp_wmb() __wmb() #define __smp_store_release(p, v) \ do { \ diff --git a/arch/s390/include/asm/bug.h b/arch/s390/include/asm/bug.h index 0b25f28351ed..aebe1e22c7be 100644 --- a/arch/s390/include/asm/bug.h +++ b/arch/s390/include/asm/bug.h @@ -15,7 +15,8 @@ "1: .asciz \""__FILE__"\"\n" \ ".previous\n" \ ".section __bug_table,\"awM\",@progbits,%2\n" \ - "2: .long 0b-2b,1b-2b\n" \ + "2: .long 0b-.\n" \ + " .long 1b-.\n" \ " .short %0,%1\n" \ " .org 2b+%2\n" \ ".previous\n" \ @@ -30,7 +31,7 @@ asm_inline volatile( \ "0: mc 0,0\n" \ ".section __bug_table,\"awM\",@progbits,%1\n" \ - "1: .long 0b-1b\n" \ + "1: .long 0b-.\n" \ " .short %0\n" \ " .org 1b+%1\n" \ ".previous\n" \ diff --git a/arch/s390/include/asm/cio.h b/arch/s390/include/asm/cio.h index 1effac6a0152..1c4f585dd39b 100644 --- a/arch/s390/include/asm/cio.h +++ b/arch/s390/include/asm/cio.h @@ -369,7 +369,7 @@ void cio_gp_dma_destroy(struct gen_pool *gp_dma, struct device *dma_dev); struct gen_pool *cio_gp_dma_create(struct device *dma_dev, int nr_pages); /* Function from drivers/s390/cio/chsc.c */ -int chsc_sstpc(void *page, unsigned int op, u16 ctrl, u64 *clock_delta); +int chsc_sstpc(void *page, unsigned int op, u16 ctrl, long *clock_delta); int chsc_sstpi(void *page, void *result, size_t size); int chsc_stzi(void *page, void *result, size_t size); int chsc_sgib(u32 origin); diff --git a/arch/s390/include/asm/compat.h b/arch/s390/include/asm/compat.h index cdc7ae72529d..7d6fe813ac39 100644 --- a/arch/s390/include/asm/compat.h +++ b/arch/s390/include/asm/compat.h @@ -8,6 +8,7 @@ #include <linux/sched.h> #include <linux/sched/task_stack.h> #include <linux/thread_info.h> +#include <asm/ptrace.h> #define compat_mode_t compat_mode_t typedef u16 compat_mode_t; @@ -22,32 +23,8 @@ typedef u16 compat_mode_t; (__force t)(__TYPE_IS_PTR(t) ? ((v) & 0x7fffffff) : (v)); \ }) -#define PSW32_MASK_PER 0x40000000UL -#define PSW32_MASK_DAT 0x04000000UL -#define PSW32_MASK_IO 0x02000000UL -#define PSW32_MASK_EXT 0x01000000UL -#define PSW32_MASK_KEY 0x00F00000UL -#define PSW32_MASK_BASE 0x00080000UL /* Always one */ -#define PSW32_MASK_MCHECK 0x00040000UL -#define PSW32_MASK_WAIT 0x00020000UL -#define PSW32_MASK_PSTATE 0x00010000UL -#define PSW32_MASK_ASC 0x0000C000UL -#define PSW32_MASK_CC 0x00003000UL -#define PSW32_MASK_PM 0x00000f00UL -#define PSW32_MASK_RI 0x00000080UL - #define PSW32_MASK_USER 0x0000FF00UL -#define PSW32_ADDR_AMODE 0x80000000UL -#define PSW32_ADDR_INSN 0x7FFFFFFFUL - -#define PSW32_DEFAULT_KEY (((u32) PAGE_DEFAULT_ACC) << 20) - -#define PSW32_ASC_PRIMARY 0x00000000UL -#define PSW32_ASC_ACCREG 0x00004000UL -#define PSW32_ASC_SECONDARY 0x00008000UL -#define PSW32_ASC_HOME 0x0000C000UL - #define PSW32_USER_BITS (PSW32_MASK_DAT | PSW32_MASK_IO | PSW32_MASK_EXT | \ PSW32_DEFAULT_KEY | PSW32_MASK_BASE | \ PSW32_MASK_MCHECK | PSW32_MASK_PSTATE | \ diff --git a/arch/s390/include/asm/ctl_reg.h b/arch/s390/include/asm/ctl_reg.h index 82388da3f95f..267a8f88e143 100644 --- a/arch/s390/include/asm/ctl_reg.h +++ b/arch/s390/include/asm/ctl_reg.h @@ -93,7 +93,9 @@ union ctlreg0 { unsigned long tcx : 1; /* Transactional-Execution control */ unsigned long pifo : 1; /* Transactional-Execution Program- Interruption-Filtering Override */ - unsigned long : 22; + unsigned long : 3; + unsigned long ccc : 1; /* Cryptography counter control */ + unsigned long : 18; unsigned long : 3; unsigned long lap : 1; /* Low-address-protection control */ unsigned long : 4; diff --git a/arch/s390/include/asm/entry-common.h b/arch/s390/include/asm/entry-common.h index eabab24b71dd..000de2b1e67a 100644 --- a/arch/s390/include/asm/entry-common.h +++ b/arch/s390/include/asm/entry-common.h @@ -9,19 +9,21 @@ #include <linux/uaccess.h> #include <asm/timex.h> #include <asm/fpu/api.h> +#include <asm/pai.h> #define ARCH_EXIT_TO_USER_MODE_WORK (_TIF_GUARDED_STORAGE | _TIF_PER_TRAP) void do_per_trap(struct pt_regs *regs); -#ifdef CONFIG_DEBUG_ENTRY -static __always_inline void arch_check_user_regs(struct pt_regs *regs) +static __always_inline void arch_enter_from_user_mode(struct pt_regs *regs) { - debug_user_asce(0); + if (IS_ENABLED(CONFIG_DEBUG_ENTRY)) + debug_user_asce(0); + + pai_kernel_enter(regs); } -#define arch_check_user_regs arch_check_user_regs -#endif /* CONFIG_DEBUG_ENTRY */ +#define arch_enter_from_user_mode arch_enter_from_user_mode static __always_inline void arch_exit_to_user_mode_work(struct pt_regs *regs, unsigned long ti_work) @@ -44,6 +46,8 @@ static __always_inline void arch_exit_to_user_mode(void) if (IS_ENABLED(CONFIG_DEBUG_ENTRY)) debug_user_asce(1); + + pai_kernel_exit(current_pt_regs()); } #define arch_exit_to_user_mode arch_exit_to_user_mode @@ -58,7 +62,7 @@ static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs, static inline bool on_thread_stack(void) { - return !(((unsigned long)(current->stack) ^ current_stack_pointer()) & ~(THREAD_SIZE - 1)); + return !(((unsigned long)(current->stack) ^ current_stack_pointer) & ~(THREAD_SIZE - 1)); } #endif diff --git a/arch/s390/include/asm/ipl.h b/arch/s390/include/asm/ipl.h index 3f8ee257f9aa..a405b6bb89fb 100644 --- a/arch/s390/include/asm/ipl.h +++ b/arch/s390/include/asm/ipl.h @@ -133,6 +133,8 @@ int ipl_report_add_certificate(struct ipl_report *report, void *key, * DIAG 308 support */ enum diag308_subcode { + DIAG308_CLEAR_RESET = 0, + DIAG308_LOAD_NORMAL_RESET = 1, DIAG308_REL_HSA = 2, DIAG308_LOAD_CLEAR = 3, DIAG308_LOAD_NORMAL_DUMP = 4, @@ -141,6 +143,10 @@ enum diag308_subcode { DIAG308_LOAD_NORMAL = 7, }; +enum diag308_subcode_flags { + DIAG308_FLAG_EI = 1UL << 16, +}; + enum diag308_rc { DIAG308_RC_OK = 0x0001, DIAG308_RC_NOCONFIG = 0x0102, diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h index 56002aeacabf..26fe5e535728 100644 --- a/arch/s390/include/asm/lowcore.h +++ b/arch/s390/include/asm/lowcore.h @@ -200,7 +200,10 @@ struct lowcore { __u64 last_break_save_area; /* 0x1338 */ __u32 access_regs_save_area[16]; /* 0x1340 */ __u64 cregs_save_area[16]; /* 0x1380 */ - __u8 pad_0x1400[0x1800-0x1400]; /* 0x1400 */ + __u8 pad_0x1400[0x1500-0x1400]; /* 0x1400 */ + /* Cryptography-counter designation */ + __u64 ccd; /* 0x1500 */ + __u8 pad_0x1508[0x1800-0x1508]; /* 0x1508 */ /* Transaction abort diagnostic block */ struct pgm_tdb pgm_tdb; /* 0x1800 */ diff --git a/arch/s390/include/asm/nmi.h b/arch/s390/include/asm/nmi.h index 292083083830..af1cd3a6f406 100644 --- a/arch/s390/include/asm/nmi.h +++ b/arch/s390/include/asm/nmi.h @@ -101,7 +101,7 @@ void nmi_alloc_mcesa_early(u64 *mcesad); int nmi_alloc_mcesa(u64 *mcesad); void nmi_free_mcesa(u64 *mcesad); -void s390_handle_mcck(void); +void s390_handle_mcck(struct pt_regs *regs); void __s390_handle_mcck(void); int s390_do_machine_check(struct pt_regs *regs); diff --git a/arch/s390/include/asm/nospec-insn.h b/arch/s390/include/asm/nospec-insn.h index 2cfcd5ac3a8b..d910d71b5bb5 100644 --- a/arch/s390/include/asm/nospec-insn.h +++ b/arch/s390/include/asm/nospec-insn.h @@ -54,31 +54,31 @@ .endm .macro __DECODE_R expand,reg - .set __decode_fail,1 + .set .L__decode_fail,1 .irp r1,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15 .ifc \reg,%r\r1 \expand \r1 - .set __decode_fail,0 + .set .L__decode_fail,0 .endif .endr - .if __decode_fail == 1 + .if .L__decode_fail == 1 .error "__DECODE_R failed" .endif .endm .macro __DECODE_RR expand,rsave,rtarget - .set __decode_fail,1 + .set .L__decode_fail,1 .irp r1,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15 .ifc \rsave,%r\r1 .irp r2,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15 .ifc \rtarget,%r\r2 \expand \r1,\r2 - .set __decode_fail,0 + .set .L__decode_fail,0 .endif .endr .endif .endr - .if __decode_fail == 1 + .if .L__decode_fail == 1 .error "__DECODE_RR failed" .endif .endm diff --git a/arch/s390/include/asm/pai.h b/arch/s390/include/asm/pai.h new file mode 100644 index 000000000000..5b7e33ac6f0b --- /dev/null +++ b/arch/s390/include/asm/pai.h @@ -0,0 +1,74 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Processor Activity Instrumentation support for cryptography counters + * + * Copyright IBM Corp. 2022 + * Author(s): Thomas Richter <tmricht@linux.ibm.com> + */ +#ifndef _ASM_S390_PAI_H +#define _ASM_S390_PAI_H + +#include <linux/jump_label.h> +#include <asm/lowcore.h> +#include <asm/ptrace.h> + +struct qpaci_info_block { + u64 header; + struct { + u64 : 8; + u64 num_cc : 8; /* # of supported crypto counters */ + u64 : 48; + }; +}; + +static inline int qpaci(struct qpaci_info_block *info) +{ + /* Size of info (in double words minus one) */ + size_t size = sizeof(*info) / sizeof(u64) - 1; + int cc; + + asm volatile( + " lgr 0,%[size]\n" + " .insn s,0xb28f0000,%[info]\n" + " lgr %[size],0\n" + " ipm %[cc]\n" + " srl %[cc],28\n" + : [cc] "=d" (cc), [info] "=Q" (*info), [size] "+&d" (size) + : + : "0", "cc", "memory"); + return cc ? (size + 1) * sizeof(u64) : 0; +} + +#define PAI_CRYPTO_BASE 0x1000 /* First event number */ +#define PAI_CRYPTO_MAXCTR 256 /* Max # of event counters */ +#define PAI_CRYPTO_KERNEL_OFFSET 2048 + +DECLARE_STATIC_KEY_FALSE(pai_key); + +static __always_inline void pai_kernel_enter(struct pt_regs *regs) +{ + if (!IS_ENABLED(CONFIG_PERF_EVENTS)) + return; + if (!static_branch_unlikely(&pai_key)) + return; + if (!S390_lowcore.ccd) + return; + if (!user_mode(regs)) + return; + WRITE_ONCE(S390_lowcore.ccd, S390_lowcore.ccd | PAI_CRYPTO_KERNEL_OFFSET); +} + +static __always_inline void pai_kernel_exit(struct pt_regs *regs) +{ + if (!IS_ENABLED(CONFIG_PERF_EVENTS)) + return; + if (!static_branch_unlikely(&pai_key)) + return; + if (!S390_lowcore.ccd) + return; + if (!user_mode(regs)) + return; + WRITE_ONCE(S390_lowcore.ccd, S390_lowcore.ccd & ~PAI_CRYPTO_KERNEL_OFFSET); +} + +#endif diff --git a/arch/s390/include/asm/pci_debug.h b/arch/s390/include/asm/pci_debug.h index 5dfe47588277..3bb4e7e33a0e 100644 --- a/arch/s390/include/asm/pci_debug.h +++ b/arch/s390/include/asm/pci_debug.h @@ -17,9 +17,14 @@ extern debug_info_t *pci_debug_err_id; debug_text_event(pci_debug_err_id, 0, debug_buffer); \ } while (0) +static inline void zpci_err_hex_level(int level, void *addr, int len) +{ + debug_event(pci_debug_err_id, level, addr, len); +} + static inline void zpci_err_hex(void *addr, int len) { - debug_event(pci_debug_err_id, 0, addr, len); + zpci_err_hex_level(0, addr, len); } #endif diff --git a/arch/s390/include/asm/preempt.h b/arch/s390/include/asm/preempt.h index d9d5350cc3ec..bf15da0fedbc 100644 --- a/arch/s390/include/asm/preempt.h +++ b/arch/s390/include/asm/preempt.h @@ -46,10 +46,17 @@ static inline bool test_preempt_need_resched(void) static inline void __preempt_count_add(int val) { - if (__builtin_constant_p(val) && (val >= -128) && (val <= 127)) - __atomic_add_const(val, &S390_lowcore.preempt_count); - else - __atomic_add(val, &S390_lowcore.preempt_count); + /* + * With some obscure config options and CONFIG_PROFILE_ALL_BRANCHES + * enabled, gcc 12 fails to handle __builtin_constant_p(). + */ + if (!IS_ENABLED(CONFIG_PROFILE_ALL_BRANCHES)) { + if (__builtin_constant_p(val) && (val >= -128) && (val <= 127)) { + __atomic_add_const(val, &S390_lowcore.preempt_count); + return; + } + } + __atomic_add(val, &S390_lowcore.preempt_count); } static inline void __preempt_count_sub(int val) diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index eee8d96fb38e..add764a2be8c 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -83,6 +83,7 @@ void cpu_detect_mhz_feature(void); extern const struct seq_operations cpuinfo_op; extern void execve_tail(void); extern void __bpon(void); +unsigned long vdso_size(void); /* * User space process size: 2GB for 31 bit, 4TB or 8PT for 64 bit. @@ -94,9 +95,10 @@ extern void __bpon(void); (_REGION3_SIZE >> 1) : (_REGION2_SIZE >> 1)) #define TASK_SIZE_MAX (-PAGE_SIZE) -#define STACK_TOP (test_thread_flag(TIF_31BIT) ? \ - _REGION3_SIZE : _REGION2_SIZE) -#define STACK_TOP_MAX _REGION2_SIZE +#define VDSO_BASE (STACK_TOP + PAGE_SIZE) +#define VDSO_LIMIT (test_thread_flag(TIF_31BIT) ? _REGION3_SIZE : _REGION2_SIZE) +#define STACK_TOP (VDSO_LIMIT - vdso_size() - PAGE_SIZE) +#define STACK_TOP_MAX (_REGION2_SIZE - vdso_size() - PAGE_SIZE) #define HAVE_ARCH_PICK_MMAP_LAYOUT @@ -200,13 +202,7 @@ unsigned long __get_wchan(struct task_struct *p); /* Has task runtime instrumentation enabled ? */ #define is_ri_task(tsk) (!!(tsk)->thread.ri_cb) -static __always_inline unsigned long current_stack_pointer(void) -{ - unsigned long sp; - - asm volatile("la %0,0(15)" : "=a" (sp)); - return sp; -} +register unsigned long current_stack_pointer asm("r15"); static __always_inline unsigned short stap(void) { diff --git a/arch/s390/include/asm/ptrace.h b/arch/s390/include/asm/ptrace.h index ddb70fb13fbc..8bae33ab320a 100644 --- a/arch/s390/include/asm/ptrace.h +++ b/arch/s390/include/asm/ptrace.h @@ -71,6 +71,35 @@ enum { &(*(struct psw_bits *)(&(__psw))); \ })) +#define PSW32_MASK_PER 0x40000000UL +#define PSW32_MASK_DAT 0x04000000UL +#define PSW32_MASK_IO 0x02000000UL +#define PSW32_MASK_EXT 0x01000000UL +#define PSW32_MASK_KEY 0x00F00000UL +#define PSW32_MASK_BASE 0x00080000UL /* Always one */ +#define PSW32_MASK_MCHECK 0x00040000UL +#define PSW32_MASK_WAIT 0x00020000UL +#define PSW32_MASK_PSTATE 0x00010000UL +#define PSW32_MASK_ASC 0x0000C000UL +#define PSW32_MASK_CC 0x00003000UL +#define PSW32_MASK_PM 0x00000f00UL +#define PSW32_MASK_RI 0x00000080UL + +#define PSW32_ADDR_AMODE 0x80000000UL +#define PSW32_ADDR_INSN 0x7FFFFFFFUL + +#define PSW32_DEFAULT_KEY (((u32)PAGE_DEFAULT_ACC) << 20) + +#define PSW32_ASC_PRIMARY 0x00000000UL +#define PSW32_ASC_ACCREG 0x00004000UL +#define PSW32_ASC_SECONDARY 0x00008000UL +#define PSW32_ASC_HOME 0x0000C000UL + +typedef struct { + unsigned int mask; + unsigned int addr; +} psw_t32 __aligned(8); + #define PGM_INT_CODE_MASK 0x7f #define PGM_INT_CODE_PER 0x80 diff --git a/arch/s390/include/asm/sclp.h b/arch/s390/include/asm/sclp.h index 04cb1e7582a6..236b34b75ddb 100644 --- a/arch/s390/include/asm/sclp.h +++ b/arch/s390/include/asm/sclp.h @@ -87,6 +87,7 @@ struct sclp_info { unsigned char has_diag318 : 1; unsigned char has_sipl : 1; unsigned char has_dirq : 1; + unsigned char has_iplcc : 1; unsigned int ibc; unsigned int mtid; unsigned int mtid_cp; diff --git a/arch/s390/include/asm/scsw.h b/arch/s390/include/asm/scsw.h index a7c3ccf681da..7ce584aff5bb 100644 --- a/arch/s390/include/asm/scsw.h +++ b/arch/s390/include/asm/scsw.h @@ -508,9 +508,21 @@ static inline int scsw_cmd_is_valid_zcc(union scsw *scsw) */ static inline int scsw_cmd_is_valid_ectl(union scsw *scsw) { - return (scsw->cmd.stctl & SCSW_STCTL_STATUS_PEND) && - !(scsw->cmd.stctl & SCSW_STCTL_INTER_STATUS) && - (scsw->cmd.stctl & SCSW_STCTL_ALERT_STATUS); + /* Must be status pending. */ + if (!(scsw->cmd.stctl & SCSW_STCTL_STATUS_PEND)) + return 0; + + /* Must have alert status. */ + if (!(scsw->cmd.stctl & SCSW_STCTL_ALERT_STATUS)) + return 0; + + /* Must be alone or together with primary, secondary or both, + * => no intermediate status. + */ + if (scsw->cmd.stctl & SCSW_STCTL_INTER_STATUS) + return 0; + + return 1; } /** @@ -522,10 +534,25 @@ static inline int scsw_cmd_is_valid_ectl(union scsw *scsw) */ static inline int scsw_cmd_is_valid_pno(union scsw *scsw) { - return (scsw->cmd.fctl != 0) && - (scsw->cmd.stctl & SCSW_STCTL_STATUS_PEND) && - (!(scsw->cmd.stctl & SCSW_STCTL_INTER_STATUS) || - (scsw->cmd.actl & SCSW_ACTL_SUSPENDED)); + /* Must indicate at least one I/O function. */ + if (!scsw->cmd.fctl) + return 0; + + /* Must be status pending. */ + if (!(scsw->cmd.stctl & SCSW_STCTL_STATUS_PEND)) + return 0; + + /* Can be status pending alone, or with any combination of primary, + * secondary and alert => no intermediate status. + */ + if (!(scsw->cmd.stctl & SCSW_STCTL_INTER_STATUS)) + return 1; + + /* If intermediate, must be suspended. */ + if (scsw->cmd.actl & SCSW_ACTL_SUSPENDED) + return 1; + + return 0; } /** @@ -675,9 +702,21 @@ static inline int scsw_tm_is_valid_q(union scsw *scsw) */ static inline int scsw_tm_is_valid_ectl(union scsw *scsw) { - return (scsw->tm.stctl & SCSW_STCTL_STATUS_PEND) && - !(scsw->tm.stctl & SCSW_STCTL_INTER_STATUS) && - (scsw->tm.stctl & SCSW_STCTL_ALERT_STATUS); + /* Must be status pending. */ + if (!(scsw->tm.stctl & SCSW_STCTL_STATUS_PEND)) + return 0; + + /* Must have alert status. */ + if (!(scsw->tm.stctl & SCSW_STCTL_ALERT_STATUS)) + return 0; + + /* Must be alone or together with primary, secondary or both, + * => no intermediate status. + */ + if (scsw->tm.stctl & SCSW_STCTL_INTER_STATUS) + return 0; + + return 1; } /** @@ -689,11 +728,25 @@ static inline int scsw_tm_is_valid_ectl(union scsw *scsw) */ static inline int scsw_tm_is_valid_pno(union scsw *scsw) { - return (scsw->tm.fctl != 0) && - (scsw->tm.stctl & SCSW_STCTL_STATUS_PEND) && - (!(scsw->tm.stctl & SCSW_STCTL_INTER_STATUS) || - ((scsw->tm.stctl & SCSW_STCTL_INTER_STATUS) && - (scsw->tm.actl & SCSW_ACTL_SUSPENDED))); + /* Must indicate at least one I/O function. */ + if (!scsw->tm.fctl) + return 0; + + /* Must be status pending. */ + if (!(scsw->tm.stctl & SCSW_STCTL_STATUS_PEND)) + return 0; + + /* Can be status pending alone, or with any combination of primary, + * secondary and alert => no intermediate status. + */ + if (!(scsw->tm.stctl & SCSW_STCTL_INTER_STATUS)) + return 1; + + /* If intermediate, must be suspended. */ + if (scsw->tm.actl & SCSW_ACTL_SUSPENDED) + return 1; + + return 0; } /** diff --git a/arch/s390/include/asm/spinlock.h b/arch/s390/include/asm/spinlock.h index 24a54443c865..37127cd7749e 100644 --- a/arch/s390/include/asm/spinlock.h +++ b/arch/s390/include/asm/spinlock.h @@ -77,8 +77,9 @@ static inline int arch_spin_trylock(arch_spinlock_t *lp) static inline void arch_spin_unlock(arch_spinlock_t *lp) { typecheck(int, lp->lock); + kcsan_release(); asm_inline volatile( - ALTERNATIVE("", ".insn rre,0xb2fa0000,7,0", 49) /* NIAI 7 */ + ALTERNATIVE("nop", ".insn rre,0xb2fa0000,7,0", 49) /* NIAI 7 */ " sth %1,%0\n" : "=R" (((unsigned short *) &lp->lock)[1]) : "d" (0) : "cc", "memory"); diff --git a/arch/s390/include/asm/stacktrace.h b/arch/s390/include/asm/stacktrace.h index 275f4258fbd5..f8500191993d 100644 --- a/arch/s390/include/asm/stacktrace.h +++ b/arch/s390/include/asm/stacktrace.h @@ -46,7 +46,7 @@ struct stack_frame { }; /* - * Unlike current_stack_pointer() which simply returns current value of %r15 + * Unlike current_stack_pointer which simply contains the current value of %r15 * current_frame_address() returns function stack frame address, which matches * %r15 upon function invocation. It may differ from %r15 later if function * allocates stack for local variables or new stack frame to call other diff --git a/arch/s390/include/asm/stp.h b/arch/s390/include/asm/stp.h index ba07463897c1..4d74d7e33340 100644 --- a/arch/s390/include/asm/stp.h +++ b/arch/s390/include/asm/stp.h @@ -44,8 +44,8 @@ struct stp_sstpi { u32 : 32; u32 ctnid[3]; u32 : 32; - u32 todoff[4]; - u32 rsvd[48]; + u64 todoff; + u32 rsvd[50]; } __packed; struct stp_tzib { diff --git a/arch/s390/include/asm/timex.h b/arch/s390/include/asm/timex.h index 2cfce42aa7fc..ce878e85b6e4 100644 --- a/arch/s390/include/asm/timex.h +++ b/arch/s390/include/asm/timex.h @@ -197,6 +197,7 @@ static inline cycles_t get_cycles(void) { return (cycles_t) get_tod_clock() >> 2; } +#define get_cycles get_cycles int get_phys_clock(unsigned long *clock); void init_cpu_timer(void); diff --git a/arch/s390/include/asm/vx-insn.h b/arch/s390/include/asm/vx-insn.h index 87e6cc2aeba4..95480ed9149e 100644 --- a/arch/s390/include/asm/vx-insn.h +++ b/arch/s390/include/asm/vx-insn.h @@ -366,7 +366,7 @@ .macro VLM vfrom, vto, disp, base, hint=3 VX_NUM v1, \vfrom VX_NUM v3, \vto - GR_NUM b2, \base /* Base register */ + GR_NUM b2, \base .word 0xE700 | ((v1&15) << 4) | (v3&15) .word (b2 << 12) | (\disp) MRXBOPC \hint, 0x36, v1, v3 @@ -376,7 +376,7 @@ .macro VST vr1, disp, index="%r0", base VX_NUM v1, \vr1 GR_NUM x2, \index - GR_NUM b2, \base /* Base register */ + GR_NUM b2, \base .word 0xE700 | ((v1&15) << 4) | (x2&15) .word (b2 << 12) | (\disp) MRXBOPC 0, 0x0E, v1 @@ -386,7 +386,7 @@ .macro VSTM vfrom, vto, disp, base, hint=3 VX_NUM v1, \vfrom VX_NUM v3, \vto - GR_NUM b2, \base /* Base register */ + GR_NUM b2, \base .word 0xE700 | ((v1&15) << 4) | (v3&15) .word (b2 << 12) | (\disp) MRXBOPC \hint, 0x3E, v1, v3 diff --git a/arch/s390/include/uapi/asm/pkey.h b/arch/s390/include/uapi/asm/pkey.h index 7349e96d28a0..924b876f992c 100644 --- a/arch/s390/include/uapi/asm/pkey.h +++ b/arch/s390/include/uapi/asm/pkey.h @@ -171,7 +171,7 @@ struct pkey_skey2pkey { #define PKEY_SKEY2PKEY _IOWR(PKEY_IOCTL_MAGIC, 0x06, struct pkey_skey2pkey) /* - * Verify the given CCA AES secure key for being able to be useable with + * Verify the given CCA AES secure key for being able to be usable with * the pkey module. Check for correct key type and check for having at * least one crypto card being able to handle this key (master key * or old master key verification pattern matches). diff --git a/arch/s390/include/uapi/asm/zcrypt.h b/arch/s390/include/uapi/asm/zcrypt.h index 2f04a5499d74..d83713f67530 100644 --- a/arch/s390/include/uapi/asm/zcrypt.h +++ b/arch/s390/include/uapi/asm/zcrypt.h @@ -4,7 +4,7 @@ * * zcrypt 2.2.1 (user-visible header) * - * Copyright IBM Corp. 2001, 2019 + * Copyright IBM Corp. 2001, 2022 * Author(s): Robert Burroughs * Eric Rossman (edrossma@us.ibm.com) * @@ -85,7 +85,7 @@ struct ica_rsa_modexpo_crt { struct CPRBX { __u16 cprb_len; /* CPRB length 220 */ __u8 cprb_ver_id; /* CPRB version id. 0x02 */ - __u8 pad_000[3]; /* Alignment pad bytes */ + __u8 _pad_000[3]; /* Alignment pad bytes */ __u8 func_id[2]; /* function id 0x5432 */ __u8 cprb_flags[4]; /* Flags */ __u32 req_parml; /* request parameter buffer len */ @@ -95,19 +95,19 @@ struct CPRBX { __u32 rpl_datal; /* reply data block len */ __u32 rpld_datal; /* replied data block len */ __u32 req_extbl; /* request extension block len */ - __u8 pad_001[4]; /* reserved */ + __u8 _pad_001[4]; /* reserved */ __u32 rpld_extbl; /* replied extension block len */ - __u8 padx000[16 - sizeof(__u8 *)]; + __u8 _pad_002[16 - sizeof(__u8 *)]; __u8 __user *req_parmb; /* request parm block 'address' */ - __u8 padx001[16 - sizeof(__u8 *)]; + __u8 _pad_003[16 - sizeof(__u8 *)]; __u8 __user *req_datab; /* request data block 'address' */ - __u8 padx002[16 - sizeof(__u8 *)]; + __u8 _pad_004[16 - sizeof(__u8 *)]; __u8 __user *rpl_parmb; /* reply parm block 'address' */ - __u8 padx003[16 - sizeof(__u8 *)]; + __u8 _pad_005[16 - sizeof(__u8 *)]; __u8 __user *rpl_datab; /* reply data block 'address' */ - __u8 padx004[16 - sizeof(__u8 *)]; + __u8 _pad_006[16 - sizeof(__u8 *)]; __u8 __user *req_extb; /* request extension block 'addr'*/ - __u8 padx005[16 - sizeof(__u8 *)]; + __u8 _pad_007[16 - sizeof(__u8 *)]; __u8 __user *rpl_extb; /* reply extension block 'address'*/ __u16 ccp_rtcode; /* server return code */ __u16 ccp_rscode; /* server reason code */ @@ -115,12 +115,10 @@ struct CPRBX { __u8 logon_id[8]; /* Logon Identifier */ __u8 mac_value[8]; /* Mac Value */ __u8 mac_content_flgs; /* Mac content flag byte */ - __u8 pad_002; /* Alignment */ + __u8 _pad_008; /* Alignment */ __u16 domain; /* Domain */ - __u8 usage_domain[4]; /* Usage domain */ - __u8 cntrl_domain[4]; /* Control domain */ - __u8 S390enf_mask[4]; /* S/390 enforcement mask */ - __u8 pad_004[36]; /* reserved */ + __u8 _pad_009[12]; /* reserved, checked for zeros */ + __u8 _pad_010[36]; /* reserved */ } __attribute__((packed)); /** @@ -238,8 +236,8 @@ struct zcrypt_device_matrix_ext { }; #define AUTOSELECT 0xFFFFFFFF -#define AUTOSEL_AP ((__u16) 0xFFFF) -#define AUTOSEL_DOM ((__u16) 0xFFFF) +#define AUTOSEL_AP ((__u16)0xFFFF) +#define AUTOSEL_DOM ((__u16)0xFFFF) #define ZCRYPT_IOCTL_MAGIC 'z' @@ -305,12 +303,12 @@ struct zcrypt_device_matrix_ext { /** * Supported ioctl calls */ -#define ICARSAMODEXPO _IOC(_IOC_READ|_IOC_WRITE, ZCRYPT_IOCTL_MAGIC, 0x05, 0) -#define ICARSACRT _IOC(_IOC_READ|_IOC_WRITE, ZCRYPT_IOCTL_MAGIC, 0x06, 0) -#define ZSECSENDCPRB _IOC(_IOC_READ|_IOC_WRITE, ZCRYPT_IOCTL_MAGIC, 0x81, 0) -#define ZSENDEP11CPRB _IOC(_IOC_READ|_IOC_WRITE, ZCRYPT_IOCTL_MAGIC, 0x04, 0) +#define ICARSAMODEXPO _IOC(_IOC_READ | _IOC_WRITE, ZCRYPT_IOCTL_MAGIC, 0x05, 0) +#define ICARSACRT _IOC(_IOC_READ | _IOC_WRITE, ZCRYPT_IOCTL_MAGIC, 0x06, 0) +#define ZSECSENDCPRB _IOC(_IOC_READ | _IOC_WRITE, ZCRYPT_IOCTL_MAGIC, 0x81, 0) +#define ZSENDEP11CPRB _IOC(_IOC_READ | _IOC_WRITE, ZCRYPT_IOCTL_MAGIC, 0x04, 0) -#define ZCRYPT_DEVICE_STATUS _IOC(_IOC_READ|_IOC_WRITE, ZCRYPT_IOCTL_MAGIC, 0x5f, 0) +#define ZCRYPT_DEVICE_STATUS _IOC(_IOC_READ | _IOC_WRITE, ZCRYPT_IOCTL_MAGIC, 0x5f, 0) #define ZCRYPT_STATUS_MASK _IOR(ZCRYPT_IOCTL_MAGIC, 0x58, char[MAX_ZDEV_CARDIDS_EXT]) #define ZCRYPT_QDEPTH_MASK _IOR(ZCRYPT_IOCTL_MAGIC, 0x59, char[MAX_ZDEV_CARDIDS_EXT]) #define ZCRYPT_PERDEV_REQCNT _IOR(ZCRYPT_IOCTL_MAGIC, 0x5a, int[MAX_ZDEV_CARDIDS_EXT]) @@ -352,7 +350,7 @@ struct zcrypt_device_matrix { }; /* Deprecated: use ZCRYPT_DEVICE_STATUS */ -#define ZDEVICESTATUS _IOC(_IOC_READ|_IOC_WRITE, ZCRYPT_IOCTL_MAGIC, 0x4f, 0) +#define ZDEVICESTATUS _IOC(_IOC_READ | _IOC_WRITE, ZCRYPT_IOCTL_MAGIC, 0x4f, 0) /* Deprecated: use ZCRYPT_STATUS_MASK */ #define Z90STAT_STATUS_MASK _IOR(ZCRYPT_IOCTL_MAGIC, 0x48, char[64]) /* Deprecated: use ZCRYPT_QDEPTH_MASK */ diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile index c8d1b6aa823e..5851041bb214 100644 --- a/arch/s390/kernel/Makefile +++ b/arch/s390/kernel/Makefile @@ -72,6 +72,7 @@ obj-$(CONFIG_IMA_SECURE_AND_OR_TRUSTED_BOOT) += ima_arch.o obj-$(CONFIG_PERF_EVENTS) += perf_event.o perf_cpum_cf_common.o obj-$(CONFIG_PERF_EVENTS) += perf_cpum_cf.o perf_cpum_sf.o obj-$(CONFIG_PERF_EVENTS) += perf_cpum_cf_events.o perf_regs.o +obj-$(CONFIG_PERF_EVENTS) += perf_pai_crypto.o obj-$(CONFIG_TRACEPOINTS) += trace.o obj-$(findstring y, $(CONFIG_PROTECTED_VIRTUALIZATION_GUEST) $(CONFIG_PGSTE)) += uv.o diff --git a/arch/s390/kernel/alternative.c b/arch/s390/kernel/alternative.c index cce0ddee2d02..e7bca29f9c34 100644 --- a/arch/s390/kernel/alternative.c +++ b/arch/s390/kernel/alternative.c @@ -7,8 +7,6 @@ #include <asm/facility.h> #include <asm/nospec-branch.h> -#define MAX_PATCH_LEN (255 - 1) - static int __initdata_or_module alt_instr_disabled; static int __init disable_alternative_instructions(char *str) @@ -19,85 +17,30 @@ static int __init disable_alternative_instructions(char *str) early_param("noaltinstr", disable_alternative_instructions); -struct brcl_insn { - u16 opc; - s32 disp; -} __packed; - -static u16 __initdata_or_module nop16 = 0x0700; -static u32 __initdata_or_module nop32 = 0x47000000; -static struct brcl_insn __initdata_or_module nop48 = { - 0xc004, 0 -}; - -static const void *nops[] __initdata_or_module = { - &nop16, - &nop32, - &nop48 -}; - -static void __init_or_module add_jump_padding(void *insns, unsigned int len) -{ - struct brcl_insn brcl = { - 0xc0f4, - len / 2 - }; - - memcpy(insns, &brcl, sizeof(brcl)); - insns += sizeof(brcl); - len -= sizeof(brcl); - - while (len > 0) { - memcpy(insns, &nop16, 2); - insns += 2; - len -= 2; - } -} - -static void __init_or_module add_padding(void *insns, unsigned int len) -{ - if (len > 6) - add_jump_padding(insns, len); - else if (len >= 2) - memcpy(insns, nops[len / 2 - 1], len); -} - static void __init_or_module __apply_alternatives(struct alt_instr *start, struct alt_instr *end) { struct alt_instr *a; u8 *instr, *replacement; - u8 insnbuf[MAX_PATCH_LEN]; /* * The scan order should be from start to end. A later scanned * alternative code can overwrite previously scanned alternative code. */ for (a = start; a < end; a++) { - int insnbuf_sz = 0; - instr = (u8 *)&a->instr_offset + a->instr_offset; replacement = (u8 *)&a->repl_offset + a->repl_offset; if (!__test_facility(a->facility, alt_stfle_fac_list)) continue; - if (unlikely(a->instrlen % 2 || a->replacementlen % 2)) { + if (unlikely(a->instrlen % 2)) { WARN_ONCE(1, "cpu alternatives instructions length is " "odd, skipping patching\n"); continue; } - memcpy(insnbuf, replacement, a->replacementlen); - insnbuf_sz = a->replacementlen; - - if (a->instrlen > a->replacementlen) { - add_padding(insnbuf + a->replacementlen, - a->instrlen - a->replacementlen); - insnbuf_sz += a->instrlen - a->replacementlen; - } - - s390_kernel_write(instr, insnbuf, insnbuf_sz); + s390_kernel_write(instr, replacement, a->instrlen); } } diff --git a/arch/s390/kernel/compat_linux.h b/arch/s390/kernel/compat_linux.h index 64509e7dbd3b..ef23739b277c 100644 --- a/arch/s390/kernel/compat_linux.h +++ b/arch/s390/kernel/compat_linux.h @@ -5,69 +5,59 @@ #include <linux/compat.h> #include <linux/socket.h> #include <linux/syscalls.h> +#include <asm/ptrace.h> -/* Macro that masks the high order bit of an 32 bit pointer and converts it*/ -/* to a 64 bit pointer */ -#define A(__x) ((unsigned long)((__x) & 0x7FFFFFFFUL)) -#define AA(__x) \ - ((unsigned long)(__x)) +/* + * Macro that masks the high order bit of a 32 bit pointer and + * converts it to a 64 bit pointer. + */ +#define A(__x) ((unsigned long)((__x) & 0x7FFFFFFFUL)) +#define AA(__x) ((unsigned long)(__x)) /* Now 32bit compatibility types */ struct ipc_kludge_32 { - __u32 msgp; /* pointer */ - __s32 msgtyp; + __u32 msgp; /* pointer */ + __s32 msgtyp; }; /* asm/sigcontext.h */ -typedef union -{ - __u64 d; - __u32 f; +typedef union { + __u64 d; + __u32 f; } freg_t32; -typedef struct -{ +typedef struct { unsigned int fpc; unsigned int pad; - freg_t32 fprs[__NUM_FPRS]; + freg_t32 fprs[__NUM_FPRS]; } _s390_fp_regs32; -typedef struct -{ - __u32 mask; - __u32 addr; -} _psw_t32 __attribute__ ((aligned(8))); - -typedef struct -{ - _psw_t32 psw; +typedef struct { + psw_t32 psw; __u32 gprs[__NUM_GPRS]; __u32 acrs[__NUM_ACRS]; } _s390_regs_common32; -typedef struct -{ +typedef struct { _s390_regs_common32 regs; - _s390_fp_regs32 fpregs; + _s390_fp_regs32 fpregs; } _sigregs32; -typedef struct -{ - __u32 gprs_high[__NUM_GPRS]; - __u64 vxrs_low[__NUM_VXRS_LOW]; - __vector128 vxrs_high[__NUM_VXRS_HIGH]; - __u8 __reserved[128]; +typedef struct { + __u32 gprs_high[__NUM_GPRS]; + __u64 vxrs_low[__NUM_VXRS_LOW]; + __vector128 vxrs_high[__NUM_VXRS_HIGH]; + __u8 __reserved[128]; } _sigregs_ext32; #define _SIGCONTEXT_NSIG32 64 #define _SIGCONTEXT_NSIG_BPW32 32 #define __SIGNAL_FRAMESIZE32 96 -#define _SIGMASK_COPY_SIZE32 (sizeof(u32)*2) +#define _SIGMASK_COPY_SIZE32 (sizeof(u32) * 2) -struct sigcontext32 -{ +struct sigcontext32 { __u32 oldmask[_COMPAT_NSIG_WORDS]; - __u32 sregs; /* pointer */ + __u32 sregs; /* pointer */ }; /* asm/signal.h */ @@ -75,11 +65,11 @@ struct sigcontext32 /* asm/ucontext.h */ struct ucontext32 { __u32 uc_flags; - __u32 uc_link; /* pointer */ + __u32 uc_link; /* pointer */ compat_stack_t uc_stack; _sigregs32 uc_mcontext; compat_sigset_t uc_sigmask; - /* Allow for uc_sigmask growth. Glibc uses a 1024-bit sigset_t. */ + /* Allow for uc_sigmask growth. Glibc uses a 1024-bit sigset_t. */ unsigned char __unused[128 - sizeof(compat_sigset_t)]; _sigregs_ext32 uc_mcontext_ext; }; @@ -88,25 +78,6 @@ struct stat64_emu31; struct mmap_arg_struct_emu31; struct fadvise64_64_args; -long compat_sys_s390_chown16(const char __user *filename, u16 user, u16 group); -long compat_sys_s390_lchown16(const char __user *filename, u16 user, u16 group); -long compat_sys_s390_fchown16(unsigned int fd, u16 user, u16 group); -long compat_sys_s390_setregid16(u16 rgid, u16 egid); -long compat_sys_s390_setgid16(u16 gid); -long compat_sys_s390_setreuid16(u16 ruid, u16 euid); -long compat_sys_s390_setuid16(u16 uid); -long compat_sys_s390_setresuid16(u16 ruid, u16 euid, u16 suid); -long compat_sys_s390_getresuid16(u16 __user *ruid, u16 __user *euid, u16 __user *suid); -long compat_sys_s390_setresgid16(u16 rgid, u16 egid, u16 sgid); -long compat_sys_s390_getresgid16(u16 __user *rgid, u16 __user *egid, u16 __user *sgid); -long compat_sys_s390_setfsuid16(u16 uid); -long compat_sys_s390_setfsgid16(u16 gid); -long compat_sys_s390_getgroups16(int gidsetsize, u16 __user *grouplist); -long compat_sys_s390_setgroups16(int gidsetsize, u16 __user *grouplist); -long compat_sys_s390_getuid16(void); -long compat_sys_s390_geteuid16(void); -long compat_sys_s390_getgid16(void); -long compat_sys_s390_getegid16(void); long compat_sys_s390_truncate64(const char __user *path, u32 high, u32 low); long compat_sys_s390_ftruncate64(unsigned int fd, u32 high, u32 low); long compat_sys_s390_pread64(unsigned int fd, char __user *ubuf, compat_size_t count, u32 high, u32 low); @@ -118,8 +89,8 @@ long compat_sys_s390_fstat64(unsigned int fd, struct stat64_emu31 __user *statbu long compat_sys_s390_fstatat64(unsigned int dfd, const char __user *filename, struct stat64_emu31 __user *statbuf, int flag); long compat_sys_s390_old_mmap(struct mmap_arg_struct_emu31 __user *arg); long compat_sys_s390_mmap2(struct mmap_arg_struct_emu31 __user *arg); -long compat_sys_s390_read(unsigned int fd, char __user * buf, compat_size_t count); -long compat_sys_s390_write(unsigned int fd, const char __user * buf, compat_size_t count); +long compat_sys_s390_read(unsigned int fd, char __user *buf, compat_size_t count); +long compat_sys_s390_write(unsigned int fd, const char __user *buf, compat_size_t count); long compat_sys_s390_fadvise64(int fd, u32 high, u32 low, compat_size_t len, int advise); long compat_sys_s390_fadvise64_64(struct fadvise64_64_args __user *args); long compat_sys_s390_sync_file_range(int fd, u32 offhigh, u32 offlow, u32 nhigh, u32 nlow, unsigned int flags); diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 59b69c8ab5e1..df41132ccd06 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -53,19 +53,19 @@ STACK_INIT = STACK_SIZE - STACK_FRAME_OVERHEAD - __PT_SIZE _LPP_OFFSET = __LC_LPP .macro STBEAR address - ALTERNATIVE "", ".insn s,0xb2010000,\address", 193 + ALTERNATIVE "nop", ".insn s,0xb2010000,\address", 193 .endm .macro LBEAR address - ALTERNATIVE "", ".insn s,0xb2000000,\address", 193 + ALTERNATIVE "nop", ".insn s,0xb2000000,\address", 193 .endm .macro LPSWEY address,lpswe - ALTERNATIVE "b \lpswe", ".insn siy,0xeb0000000071,\address,0", 193 + ALTERNATIVE "b \lpswe; nopr", ".insn siy,0xeb0000000071,\address,0", 193 .endm .macro MBEAR reg - ALTERNATIVE "", __stringify(mvc __PT_LAST_BREAK(8,\reg),__LC_LAST_BREAK), 193 + ALTERNATIVE "brcl 0,0", __stringify(mvc __PT_LAST_BREAK(8,\reg),__LC_LAST_BREAK), 193 .endm .macro CHECK_STACK savearea @@ -121,16 +121,16 @@ _LPP_OFFSET = __LC_LPP .endm .macro BPOFF - ALTERNATIVE "", ".insn rrf,0xb2e80000,0,0,12,0", 82 + ALTERNATIVE "nop", ".insn rrf,0xb2e80000,0,0,12,0", 82 .endm .macro BPON - ALTERNATIVE "", ".insn rrf,0xb2e80000,0,0,13,0", 82 + ALTERNATIVE "nop", ".insn rrf,0xb2e80000,0,0,13,0", 82 .endm .macro BPENTER tif_ptr,tif_mask ALTERNATIVE "TSTMSK \tif_ptr,\tif_mask; jz .+8; .insn rrf,0xb2e80000,0,0,13,0", \ - "", 82 + "j .+12; nop; nop", 82 .endm .macro BPEXIT tif_ptr,tif_mask @@ -172,9 +172,19 @@ _LPP_OFFSET = __LC_LPP lgr %r14,\reg larl %r13,\start slgr %r14,%r13 - lghi %r13,\end - \start - clgr %r14,%r13 +#ifdef CONFIG_AS_IS_LLVM + clgfrl %r14,.Lrange_size\@ +#else + clgfi %r14,\end - \start +#endif jhe \outside_label +#ifdef CONFIG_AS_IS_LLVM + .section .rodata, "a" + .align 4 +.Lrange_size\@: + .long \end - \start + .previous +#endif .endm .macro SIEEXIT @@ -226,7 +236,7 @@ ENTRY(__switch_to) aghi %r3,__TASK_pid mvc __LC_CURRENT_PID(4,%r0),0(%r3) # store pid of next lmg %r6,%r15,__SF_GPRS(%r15) # load gprs of next task - ALTERNATIVE "", "lpp _LPP_OFFSET", 40 + ALTERNATIVE "nop", "lpp _LPP_OFFSET", 40 BR_EX %r14 ENDPROC(__switch_to) @@ -473,10 +483,7 @@ ENTRY(\name) mvc __PT_R8(64,%r11),__LC_SAVE_AREA_ASYNC MBEAR %r11 stmg %r8,%r9,__PT_PSW(%r11) - tm %r8,0x0001 # coming from user space? - jno 1f - lctlg %c1,%c1,__LC_KERNEL_ASCE -1: lgr %r2,%r11 # pass pointer to pt_regs + lgr %r2,%r11 # pass pointer to pt_regs brasl %r14,\handler mvc __LC_RETURN_PSW(16),__PT_PSW(%r11) tmhh %r8,0x0001 # returning to user ? @@ -602,6 +609,7 @@ ENTRY(mcck_int_handler) mvc STACK_FRAME_OVERHEAD(__PT_SIZE,%r1),0(%r11) xc __SF_BACKCHAIN(8,%r1),__SF_BACKCHAIN(%r1) la %r11,STACK_FRAME_OVERHEAD(%r1) + lgr %r2,%r11 lgr %r15,%r1 brasl %r14,s390_handle_mcck .Lmcck_return: @@ -612,7 +620,7 @@ ENTRY(mcck_int_handler) jno 0f BPEXIT __TI_flags(%r12),_TIF_ISOLATE_BP stpt __LC_EXIT_TIMER -0: ALTERNATIVE "", __stringify(lghi %r12,__LC_LAST_BREAK_SAVE_AREA),193 +0: ALTERNATIVE "nop", __stringify(lghi %r12,__LC_LAST_BREAK_SAVE_AREA),193 LBEAR 0(%r12) lmg %r11,%r15,__PT_R11(%r11) LPSWEY __LC_RETURN_MCCK_PSW,__LC_RETURN_MCCK_LPSWE @@ -648,7 +656,7 @@ ENTRY(mcck_int_handler) ENDPROC(mcck_int_handler) ENTRY(restart_int_handler) - ALTERNATIVE "", "lpp _LPP_OFFSET", 40 + ALTERNATIVE "nop", "lpp _LPP_OFFSET", 40 stg %r15,__LC_SAVE_AREA_RESTART TSTMSK __LC_RESTART_FLAGS,RESTART_FLAG_CTLREGS,4 jz 0f diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c index 3033f616e256..45393919fe61 100644 --- a/arch/s390/kernel/irq.c +++ b/arch/s390/kernel/irq.c @@ -205,7 +205,7 @@ static void show_msi_interrupt(struct seq_file *p, int irq) unsigned long flags; int cpu; - irq_lock_sparse(); + rcu_read_lock(); desc = irq_to_desc(irq); if (!desc) goto out; @@ -224,7 +224,7 @@ static void show_msi_interrupt(struct seq_file *p, int irq) seq_putc(p, '\n'); raw_spin_unlock_irqrestore(&desc->lock, flags); out: - irq_unlock_sparse(); + rcu_read_unlock(); } /* diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c index b2ef014a9287..ab761c008f98 100644 --- a/arch/s390/kernel/machine_kexec.c +++ b/arch/s390/kernel/machine_kexec.c @@ -26,8 +26,10 @@ #include <asm/stacktrace.h> #include <asm/switch_to.h> #include <asm/nmi.h> +#include <asm/sclp.h> -typedef void (*relocate_kernel_t)(kimage_entry_t *, unsigned long); +typedef void (*relocate_kernel_t)(kimage_entry_t *, unsigned long, + unsigned long); extern const unsigned char relocate_kernel[]; extern const unsigned long long relocate_kernel_len; @@ -54,7 +56,7 @@ static void __do_machine_kdump(void *image) * This need to be done *after* s390_reset_system set the * prefix register of this CPU to zero */ - memcpy((void *) __LC_FPREGS_SAVE_AREA, + memcpy(absolute_pointer(__LC_FPREGS_SAVE_AREA), (void *)(prefix + __LC_FPREGS_SAVE_AREA), 512); __load_psw_mask(PSW_MASK_BASE | PSW_DEFAULT_KEY | PSW_MASK_EA | PSW_MASK_BA); @@ -243,6 +245,7 @@ void machine_crash_shutdown(struct pt_regs *regs) */ static void __do_machine_kexec(void *data) { + unsigned long diag308_subcode; relocate_kernel_t data_mover; struct kimage *image = data; @@ -251,7 +254,10 @@ static void __do_machine_kexec(void *data) __arch_local_irq_stnsm(0xfb); /* disable DAT - avoid no-execute */ /* Call the moving routine */ - (*data_mover)(&image->head, image->start); + diag308_subcode = DIAG308_CLEAR_RESET; + if (sclp.has_iplcc) + diag308_subcode |= DIAG308_FLAG_EI; + (*data_mover)(&image->head, image->start, diag308_subcode); /* Die if kexec returns */ disabled_wait(); diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c index fc60e29b8690..53ed3884fe64 100644 --- a/arch/s390/kernel/nmi.c +++ b/arch/s390/kernel/nmi.c @@ -29,6 +29,8 @@ #include <asm/switch_to.h> #include <asm/ctl_reg.h> #include <asm/asm-offsets.h> +#include <asm/pai.h> + #include <linux/kvm_host.h> struct mcck_struct { @@ -169,10 +171,12 @@ void __s390_handle_mcck(void) } } -void noinstr s390_handle_mcck(void) +void noinstr s390_handle_mcck(struct pt_regs *regs) { trace_hardirqs_off(); + pai_kernel_enter(regs); __s390_handle_mcck(); + pai_kernel_exit(regs); trace_hardirqs_on(); } /* diff --git a/arch/s390/kernel/perf_cpum_cf_events.c b/arch/s390/kernel/perf_cpum_cf_events.c index 52c1fe23b823..0d64aafd158f 100644 --- a/arch/s390/kernel/perf_cpum_cf_events.c +++ b/arch/s390/kernel/perf_cpum_cf_events.c @@ -295,6 +295,76 @@ CPUMF_EVENT_ATTR(cf_z15, DFLT_CC, 0x00108); CPUMF_EVENT_ATTR(cf_z15, DFLT_CCFINISH, 0x00109); CPUMF_EVENT_ATTR(cf_z15, MT_DIAG_CYCLES_ONE_THR_ACTIVE, 0x01c0); CPUMF_EVENT_ATTR(cf_z15, MT_DIAG_CYCLES_TWO_THR_ACTIVE, 0x01c1); +CPUMF_EVENT_ATTR(cf_z16, L1D_RO_EXCL_WRITES, 0x0080); +CPUMF_EVENT_ATTR(cf_z16, DTLB2_WRITES, 0x0081); +CPUMF_EVENT_ATTR(cf_z16, DTLB2_MISSES, 0x0082); +CPUMF_EVENT_ATTR(cf_z16, CRSTE_1MB_WRITES, 0x0083); +CPUMF_EVENT_ATTR(cf_z16, DTLB2_GPAGE_WRITES, 0x0084); +CPUMF_EVENT_ATTR(cf_z16, ITLB2_WRITES, 0x0086); +CPUMF_EVENT_ATTR(cf_z16, ITLB2_MISSES, 0x0087); +CPUMF_EVENT_ATTR(cf_z16, TLB2_PTE_WRITES, 0x0089); +CPUMF_EVENT_ATTR(cf_z16, TLB2_CRSTE_WRITES, 0x008a); +CPUMF_EVENT_ATTR(cf_z16, TLB2_ENGINES_BUSY, 0x008b); +CPUMF_EVENT_ATTR(cf_z16, TX_C_TEND, 0x008c); +CPUMF_EVENT_ATTR(cf_z16, TX_NC_TEND, 0x008d); +CPUMF_EVENT_ATTR(cf_z16, L1C_TLB2_MISSES, 0x008f); +CPUMF_EVENT_ATTR(cf_z16, DCW_REQ, 0x0091); +CPUMF_EVENT_ATTR(cf_z16, DCW_REQ_IV, 0x0092); +CPUMF_EVENT_ATTR(cf_z16, DCW_REQ_CHIP_HIT, 0x0093); +CPUMF_EVENT_ATTR(cf_z16, DCW_REQ_DRAWER_HIT, 0x0094); +CPUMF_EVENT_ATTR(cf_z16, DCW_ON_CHIP, 0x0095); +CPUMF_EVENT_ATTR(cf_z16, DCW_ON_CHIP_IV, 0x0096); +CPUMF_EVENT_ATTR(cf_z16, DCW_ON_CHIP_CHIP_HIT, 0x0097); +CPUMF_EVENT_ATTR(cf_z16, DCW_ON_CHIP_DRAWER_HIT, 0x0098); +CPUMF_EVENT_ATTR(cf_z16, DCW_ON_MODULE, 0x0099); +CPUMF_EVENT_ATTR(cf_z16, DCW_ON_DRAWER, 0x009a); +CPUMF_EVENT_ATTR(cf_z16, DCW_OFF_DRAWER, 0x009b); +CPUMF_EVENT_ATTR(cf_z16, DCW_ON_CHIP_MEMORY, 0x009c); +CPUMF_EVENT_ATTR(cf_z16, DCW_ON_MODULE_MEMORY, 0x009d); +CPUMF_EVENT_ATTR(cf_z16, DCW_ON_DRAWER_MEMORY, 0x009e); +CPUMF_EVENT_ATTR(cf_z16, DCW_OFF_DRAWER_MEMORY, 0x009f); +CPUMF_EVENT_ATTR(cf_z16, IDCW_ON_MODULE_IV, 0x00a0); +CPUMF_EVENT_ATTR(cf_z16, IDCW_ON_MODULE_CHIP_HIT, 0x00a1); +CPUMF_EVENT_ATTR(cf_z16, IDCW_ON_MODULE_DRAWER_HIT, 0x00a2); +CPUMF_EVENT_ATTR(cf_z16, IDCW_ON_DRAWER_IV, 0x00a3); +CPUMF_EVENT_ATTR(cf_z16, IDCW_ON_DRAWER_CHIP_HIT, 0x00a4); +CPUMF_EVENT_ATTR(cf_z16, IDCW_ON_DRAWER_DRAWER_HIT, 0x00a5); +CPUMF_EVENT_ATTR(cf_z16, IDCW_OFF_DRAWER_IV, 0x00a6); +CPUMF_EVENT_ATTR(cf_z16, IDCW_OFF_DRAWER_CHIP_HIT, 0x00a7); +CPUMF_EVENT_ATTR(cf_z16, IDCW_OFF_DRAWER_DRAWER_HIT, 0x00a8); +CPUMF_EVENT_ATTR(cf_z16, ICW_REQ, 0x00a9); +CPUMF_EVENT_ATTR(cf_z16, ICW_REQ_IV, 0x00aa); +CPUMF_EVENT_ATTR(cf_z16, ICW_REQ_CHIP_HIT, 0x00ab); +CPUMF_EVENT_ATTR(cf_z16, ICW_REQ_DRAWER_HIT, 0x00ac); +CPUMF_EVENT_ATTR(cf_z16, ICW_ON_CHIP, 0x00ad); +CPUMF_EVENT_ATTR(cf_z16, ICW_ON_CHIP_IV, 0x00ae); +CPUMF_EVENT_ATTR(cf_z16, ICW_ON_CHIP_CHIP_HIT, 0x00af); +CPUMF_EVENT_ATTR(cf_z16, ICW_ON_CHIP_DRAWER_HIT, 0x00b0); +CPUMF_EVENT_ATTR(cf_z16, ICW_ON_MODULE, 0x00b1); +CPUMF_EVENT_ATTR(cf_z16, ICW_ON_DRAWER, 0x00b2); +CPUMF_EVENT_ATTR(cf_z16, ICW_OFF_DRAWER, 0x00b3); +CPUMF_EVENT_ATTR(cf_z16, ICW_ON_CHIP_MEMORY, 0x00b4); +CPUMF_EVENT_ATTR(cf_z16, ICW_ON_MODULE_MEMORY, 0x00b5); +CPUMF_EVENT_ATTR(cf_z16, ICW_ON_DRAWER_MEMORY, 0x00b6); +CPUMF_EVENT_ATTR(cf_z16, ICW_OFF_DRAWER_MEMORY, 0x00b7); +CPUMF_EVENT_ATTR(cf_z16, BCD_DFP_EXECUTION_SLOTS, 0x00e0); +CPUMF_EVENT_ATTR(cf_z16, VX_BCD_EXECUTION_SLOTS, 0x00e1); +CPUMF_EVENT_ATTR(cf_z16, DECIMAL_INSTRUCTIONS, 0x00e2); +CPUMF_EVENT_ATTR(cf_z16, LAST_HOST_TRANSLATIONS, 0x00e8); +CPUMF_EVENT_ATTR(cf_z16, TX_NC_TABORT, 0x00f4); +CPUMF_EVENT_ATTR(cf_z16, TX_C_TABORT_NO_SPECIAL, 0x00f5); +CPUMF_EVENT_ATTR(cf_z16, TX_C_TABORT_SPECIAL, 0x00f6); +CPUMF_EVENT_ATTR(cf_z16, DFLT_ACCESS, 0x00f8); +CPUMF_EVENT_ATTR(cf_z16, DFLT_CYCLES, 0x00fd); +CPUMF_EVENT_ATTR(cf_z16, SORTL, 0x0100); +CPUMF_EVENT_ATTR(cf_z16, DFLT_CC, 0x0109); +CPUMF_EVENT_ATTR(cf_z16, DFLT_CCFINISH, 0x010a); +CPUMF_EVENT_ATTR(cf_z16, NNPA_INVOCATIONS, 0x010b); +CPUMF_EVENT_ATTR(cf_z16, NNPA_COMPLETIONS, 0x010c); +CPUMF_EVENT_ATTR(cf_z16, NNPA_WAIT_LOCK, 0x010d); +CPUMF_EVENT_ATTR(cf_z16, NNPA_HOLD_LOCK, 0x010e); +CPUMF_EVENT_ATTR(cf_z16, MT_DIAG_CYCLES_ONE_THR_ACTIVE, 0x01c0); +CPUMF_EVENT_ATTR(cf_z16, MT_DIAG_CYCLES_TWO_THR_ACTIVE, 0x01c1); static struct attribute *cpumcf_fvn1_pmu_event_attr[] __initdata = { CPUMF_EVENT_PTR(cf_fvn1, CPU_CYCLES), @@ -635,6 +705,80 @@ static struct attribute *cpumcf_z15_pmu_event_attr[] __initdata = { NULL, }; +static struct attribute *cpumcf_z16_pmu_event_attr[] __initdata = { + CPUMF_EVENT_PTR(cf_z16, L1D_RO_EXCL_WRITES), + CPUMF_EVENT_PTR(cf_z16, DTLB2_WRITES), + CPUMF_EVENT_PTR(cf_z16, DTLB2_MISSES), + CPUMF_EVENT_PTR(cf_z16, CRSTE_1MB_WRITES), + CPUMF_EVENT_PTR(cf_z16, DTLB2_GPAGE_WRITES), + CPUMF_EVENT_PTR(cf_z16, ITLB2_WRITES), + CPUMF_EVENT_PTR(cf_z16, ITLB2_MISSES), + CPUMF_EVENT_PTR(cf_z16, TLB2_PTE_WRITES), + CPUMF_EVENT_PTR(cf_z16, TLB2_CRSTE_WRITES), + CPUMF_EVENT_PTR(cf_z16, TLB2_ENGINES_BUSY), + CPUMF_EVENT_PTR(cf_z16, TX_C_TEND), + CPUMF_EVENT_PTR(cf_z16, TX_NC_TEND), + CPUMF_EVENT_PTR(cf_z16, L1C_TLB2_MISSES), + CPUMF_EVENT_PTR(cf_z16, DCW_REQ), + CPUMF_EVENT_PTR(cf_z16, DCW_REQ_IV), + CPUMF_EVENT_PTR(cf_z16, DCW_REQ_CHIP_HIT), + CPUMF_EVENT_PTR(cf_z16, DCW_REQ_DRAWER_HIT), + CPUMF_EVENT_PTR(cf_z16, DCW_ON_CHIP), + CPUMF_EVENT_PTR(cf_z16, DCW_ON_CHIP_IV), + CPUMF_EVENT_PTR(cf_z16, DCW_ON_CHIP_CHIP_HIT), + CPUMF_EVENT_PTR(cf_z16, DCW_ON_CHIP_DRAWER_HIT), + CPUMF_EVENT_PTR(cf_z16, DCW_ON_MODULE), + CPUMF_EVENT_PTR(cf_z16, DCW_ON_DRAWER), + CPUMF_EVENT_PTR(cf_z16, DCW_OFF_DRAWER), + CPUMF_EVENT_PTR(cf_z16, DCW_ON_CHIP_MEMORY), + CPUMF_EVENT_PTR(cf_z16, DCW_ON_MODULE_MEMORY), + CPUMF_EVENT_PTR(cf_z16, DCW_ON_DRAWER_MEMORY), + CPUMF_EVENT_PTR(cf_z16, DCW_OFF_DRAWER_MEMORY), + CPUMF_EVENT_PTR(cf_z16, IDCW_ON_MODULE_IV), + CPUMF_EVENT_PTR(cf_z16, IDCW_ON_MODULE_CHIP_HIT), + CPUMF_EVENT_PTR(cf_z16, IDCW_ON_MODULE_DRAWER_HIT), + CPUMF_EVENT_PTR(cf_z16, IDCW_ON_DRAWER_IV), + CPUMF_EVENT_PTR(cf_z16, IDCW_ON_DRAWER_CHIP_HIT), + CPUMF_EVENT_PTR(cf_z16, IDCW_ON_DRAWER_DRAWER_HIT), + CPUMF_EVENT_PTR(cf_z16, IDCW_OFF_DRAWER_IV), + CPUMF_EVENT_PTR(cf_z16, IDCW_OFF_DRAWER_CHIP_HIT), + CPUMF_EVENT_PTR(cf_z16, IDCW_OFF_DRAWER_DRAWER_HIT), + CPUMF_EVENT_PTR(cf_z16, ICW_REQ), + CPUMF_EVENT_PTR(cf_z16, ICW_REQ_IV), + CPUMF_EVENT_PTR(cf_z16, ICW_REQ_CHIP_HIT), + CPUMF_EVENT_PTR(cf_z16, ICW_REQ_DRAWER_HIT), + CPUMF_EVENT_PTR(cf_z16, ICW_ON_CHIP), + CPUMF_EVENT_PTR(cf_z16, ICW_ON_CHIP_IV), + CPUMF_EVENT_PTR(cf_z16, ICW_ON_CHIP_CHIP_HIT), + CPUMF_EVENT_PTR(cf_z16, ICW_ON_CHIP_DRAWER_HIT), + CPUMF_EVENT_PTR(cf_z16, ICW_ON_MODULE), + CPUMF_EVENT_PTR(cf_z16, ICW_ON_DRAWER), + CPUMF_EVENT_PTR(cf_z16, ICW_OFF_DRAWER), + CPUMF_EVENT_PTR(cf_z16, ICW_ON_CHIP_MEMORY), + CPUMF_EVENT_PTR(cf_z16, ICW_ON_MODULE_MEMORY), + CPUMF_EVENT_PTR(cf_z16, ICW_ON_DRAWER_MEMORY), + CPUMF_EVENT_PTR(cf_z16, ICW_OFF_DRAWER_MEMORY), + CPUMF_EVENT_PTR(cf_z16, BCD_DFP_EXECUTION_SLOTS), + CPUMF_EVENT_PTR(cf_z16, VX_BCD_EXECUTION_SLOTS), + CPUMF_EVENT_PTR(cf_z16, DECIMAL_INSTRUCTIONS), + CPUMF_EVENT_PTR(cf_z16, LAST_HOST_TRANSLATIONS), + CPUMF_EVENT_PTR(cf_z16, TX_NC_TABORT), + CPUMF_EVENT_PTR(cf_z16, TX_C_TABORT_NO_SPECIAL), + CPUMF_EVENT_PTR(cf_z16, TX_C_TABORT_SPECIAL), + CPUMF_EVENT_PTR(cf_z16, DFLT_ACCESS), + CPUMF_EVENT_PTR(cf_z16, DFLT_CYCLES), + CPUMF_EVENT_PTR(cf_z16, SORTL), + CPUMF_EVENT_PTR(cf_z16, DFLT_CC), + CPUMF_EVENT_PTR(cf_z16, DFLT_CCFINISH), + CPUMF_EVENT_PTR(cf_z16, NNPA_INVOCATIONS), + CPUMF_EVENT_PTR(cf_z16, NNPA_COMPLETIONS), + CPUMF_EVENT_PTR(cf_z16, NNPA_WAIT_LOCK), + CPUMF_EVENT_PTR(cf_z16, NNPA_HOLD_LOCK), + CPUMF_EVENT_PTR(cf_z16, MT_DIAG_CYCLES_ONE_THR_ACTIVE), + CPUMF_EVENT_PTR(cf_z16, MT_DIAG_CYCLES_TWO_THR_ACTIVE), + NULL, +}; + /* END: CPUM_CF COUNTER DEFINITIONS ===================================== */ static struct attribute_group cpumcf_pmu_events_group = { @@ -749,6 +893,10 @@ __init const struct attribute_group **cpumf_cf_event_group(void) case 0x8562: model = cpumcf_z15_pmu_event_attr; break; + case 0x3931: + case 0x3932: + model = cpumcf_z16_pmu_event_attr; + break; default: model = none; break; diff --git a/arch/s390/kernel/perf_pai_crypto.c b/arch/s390/kernel/perf_pai_crypto.c new file mode 100644 index 000000000000..8c1545946d85 --- /dev/null +++ b/arch/s390/kernel/perf_pai_crypto.c @@ -0,0 +1,688 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Performance event support - Processor Activity Instrumentation Facility + * + * Copyright IBM Corp. 2022 + * Author(s): Thomas Richter <tmricht@linux.ibm.com> + */ +#define KMSG_COMPONENT "pai_crypto" +#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt + +#include <linux/kernel.h> +#include <linux/kernel_stat.h> +#include <linux/percpu.h> +#include <linux/notifier.h> +#include <linux/init.h> +#include <linux/export.h> +#include <linux/io.h> +#include <linux/perf_event.h> + +#include <asm/ctl_reg.h> +#include <asm/pai.h> +#include <asm/debug.h> + +static debug_info_t *cfm_dbg; +static unsigned int paicrypt_cnt; /* Size of the mapped counter sets */ + /* extracted with QPACI instruction */ + +DEFINE_STATIC_KEY_FALSE(pai_key); + +struct pai_userdata { + u16 num; + u64 value; +} __packed; + +struct paicrypt_map { + unsigned long *page; /* Page for CPU to store counters */ + struct pai_userdata *save; /* Page to store no-zero counters */ + unsigned int users; /* # of PAI crypto users */ + unsigned int sampler; /* # of PAI crypto samplers */ + unsigned int counter; /* # of PAI crypto counters */ + struct perf_event *event; /* Perf event for sampling */ +}; + +static DEFINE_PER_CPU(struct paicrypt_map, paicrypt_map); + +/* Release the PMU if event is the last perf event */ +static DEFINE_MUTEX(pai_reserve_mutex); + +/* Adjust usage counters and remove allocated memory when all users are + * gone. + */ +static void paicrypt_event_destroy(struct perf_event *event) +{ + struct paicrypt_map *cpump = per_cpu_ptr(&paicrypt_map, event->cpu); + + cpump->event = NULL; + static_branch_dec(&pai_key); + mutex_lock(&pai_reserve_mutex); + if (event->attr.sample_period) + cpump->sampler -= 1; + else + cpump->counter -= 1; + debug_sprintf_event(cfm_dbg, 5, "%s event %#llx cpu %d" + " sampler %d counter %d\n", __func__, + event->attr.config, event->cpu, cpump->sampler, + cpump->counter); + if (!cpump->counter && !cpump->sampler) { + debug_sprintf_event(cfm_dbg, 4, "%s page %#lx save %p\n", + __func__, (unsigned long)cpump->page, + cpump->save); + free_page((unsigned long)cpump->page); + cpump->page = NULL; + kvfree(cpump->save); + cpump->save = NULL; + } + mutex_unlock(&pai_reserve_mutex); +} + +static u64 paicrypt_getctr(struct paicrypt_map *cpump, int nr, bool kernel) +{ + if (kernel) + nr += PAI_CRYPTO_MAXCTR; + return cpump->page[nr]; +} + +/* Read the counter values. Return value from location in CMP. For event + * CRYPTO_ALL sum up all events. + */ +static u64 paicrypt_getdata(struct perf_event *event, bool kernel) +{ + struct paicrypt_map *cpump = this_cpu_ptr(&paicrypt_map); + u64 sum = 0; + int i; + + if (event->attr.config != PAI_CRYPTO_BASE) { + return paicrypt_getctr(cpump, + event->attr.config - PAI_CRYPTO_BASE, + kernel); + } + + for (i = 1; i <= paicrypt_cnt; i++) { + u64 val = paicrypt_getctr(cpump, i, kernel); + + if (!val) + continue; + sum += val; + } + return sum; +} + +static u64 paicrypt_getall(struct perf_event *event) +{ + u64 sum = 0; + + if (!event->attr.exclude_kernel) + sum += paicrypt_getdata(event, true); + if (!event->attr.exclude_user) + sum += paicrypt_getdata(event, false); + + return sum; +} + +/* Used to avoid races in checking concurrent access of counting and + * sampling for crypto events + * + * Only one instance of event pai_crypto/CRYPTO_ALL/ for sampling is + * allowed and when this event is running, no counting event is allowed. + * Several counting events are allowed in parallel, but no sampling event + * is allowed while one (or more) counting events are running. + * + * This function is called in process context and it is save to block. + * When the event initialization functions fails, no other call back will + * be invoked. + * + * Allocate the memory for the event. + */ +static int paicrypt_busy(struct perf_event_attr *a, struct paicrypt_map *cpump) +{ + unsigned int *use_ptr; + int rc = 0; + + mutex_lock(&pai_reserve_mutex); + if (a->sample_period) { /* Sampling requested */ + use_ptr = &cpump->sampler; + if (cpump->counter || cpump->sampler) + rc = -EBUSY; /* ... sampling/counting active */ + } else { /* Counting requested */ + use_ptr = &cpump->counter; + if (cpump->sampler) + rc = -EBUSY; /* ... and sampling active */ + } + if (rc) + goto unlock; + + /* Allocate memory for counter page and counter extraction. + * Only the first counting event has to allocate a page. + */ + if (cpump->page) + goto unlock; + + rc = -ENOMEM; + cpump->page = (unsigned long *)get_zeroed_page(GFP_KERNEL); + if (!cpump->page) + goto unlock; + cpump->save = kvmalloc_array(paicrypt_cnt + 1, + sizeof(struct pai_userdata), GFP_KERNEL); + if (!cpump->save) { + free_page((unsigned long)cpump->page); + cpump->page = NULL; + goto unlock; + } + rc = 0; + +unlock: + /* If rc is non-zero, do not increment counter/sampler. */ + if (!rc) + *use_ptr += 1; + debug_sprintf_event(cfm_dbg, 5, "%s sample_period %#llx sampler %d" + " counter %d page %#lx save %p rc %d\n", __func__, + a->sample_period, cpump->sampler, cpump->counter, + (unsigned long)cpump->page, cpump->save, rc); + mutex_unlock(&pai_reserve_mutex); + return rc; +} + +/* Might be called on different CPU than the one the event is intended for. */ +static int paicrypt_event_init(struct perf_event *event) +{ + struct perf_event_attr *a = &event->attr; + struct paicrypt_map *cpump; + int rc; + + /* PAI crypto PMU registered as PERF_TYPE_RAW, check event type */ + if (a->type != PERF_TYPE_RAW && event->pmu->type != a->type) + return -ENOENT; + /* PAI crypto event must be valid */ + if (a->config > PAI_CRYPTO_BASE + paicrypt_cnt) + return -EINVAL; + /* Allow only CPU wide operation, no process context for now. */ + if (event->hw.target || event->cpu == -1) + return -ENOENT; + /* Allow only CRYPTO_ALL for sampling. */ + if (a->sample_period && a->config != PAI_CRYPTO_BASE) + return -EINVAL; + + cpump = per_cpu_ptr(&paicrypt_map, event->cpu); + rc = paicrypt_busy(a, cpump); + if (rc) + return rc; + + cpump->event = event; + event->destroy = paicrypt_event_destroy; + + if (a->sample_period) { + a->sample_period = 1; + a->freq = 0; + /* Register for paicrypt_sched_task() to be called */ + event->attach_state |= PERF_ATTACH_SCHED_CB; + /* Add raw data which contain the memory mapped counters */ + a->sample_type |= PERF_SAMPLE_RAW; + /* Turn off inheritance */ + a->inherit = 0; + } + + static_branch_inc(&pai_key); + return 0; +} + +static void paicrypt_read(struct perf_event *event) +{ + u64 prev, new, delta; + + prev = local64_read(&event->hw.prev_count); + new = paicrypt_getall(event); + local64_set(&event->hw.prev_count, new); + delta = (prev <= new) ? new - prev + : (-1ULL - prev) + new + 1; /* overflow */ + local64_add(delta, &event->count); +} + +static void paicrypt_start(struct perf_event *event, int flags) +{ + u64 sum; + + sum = paicrypt_getall(event); /* Get current value */ + local64_set(&event->hw.prev_count, sum); + local64_set(&event->count, 0); +} + +static int paicrypt_add(struct perf_event *event, int flags) +{ + struct paicrypt_map *cpump = this_cpu_ptr(&paicrypt_map); + unsigned long ccd; + + if (cpump->users++ == 0) { + ccd = virt_to_phys(cpump->page) | PAI_CRYPTO_KERNEL_OFFSET; + WRITE_ONCE(S390_lowcore.ccd, ccd); + __ctl_set_bit(0, 50); + } + cpump->event = event; + if (flags & PERF_EF_START && !event->attr.sample_period) { + /* Only counting needs initial counter value */ + paicrypt_start(event, PERF_EF_RELOAD); + } + event->hw.state = 0; + if (event->attr.sample_period) + perf_sched_cb_inc(event->pmu); + return 0; +} + +static void paicrypt_stop(struct perf_event *event, int flags) +{ + paicrypt_read(event); + event->hw.state = PERF_HES_STOPPED; +} + +static void paicrypt_del(struct perf_event *event, int flags) +{ + struct paicrypt_map *cpump = this_cpu_ptr(&paicrypt_map); + + if (event->attr.sample_period) + perf_sched_cb_dec(event->pmu); + if (!event->attr.sample_period) + /* Only counting needs to read counter */ + paicrypt_stop(event, PERF_EF_UPDATE); + if (cpump->users-- == 1) { + __ctl_clear_bit(0, 50); + WRITE_ONCE(S390_lowcore.ccd, 0); + } +} + +/* Create raw data and save it in buffer. Returns number of bytes copied. + * Saves only positive counter entries of the form + * 2 bytes: Number of counter + * 8 bytes: Value of counter + */ +static size_t paicrypt_copy(struct pai_userdata *userdata, + struct paicrypt_map *cpump, + bool exclude_user, bool exclude_kernel) +{ + int i, outidx = 0; + + for (i = 1; i <= paicrypt_cnt; i++) { + u64 val = 0; + + if (!exclude_kernel) + val += paicrypt_getctr(cpump, i, true); + if (!exclude_user) + val += paicrypt_getctr(cpump, i, false); + if (val) { + userdata[outidx].num = i; + userdata[outidx].value = val; + outidx++; + } + } + return outidx * sizeof(struct pai_userdata); +} + +static int paicrypt_push_sample(void) +{ + struct paicrypt_map *cpump = this_cpu_ptr(&paicrypt_map); + struct perf_event *event = cpump->event; + struct perf_sample_data data; + struct perf_raw_record raw; + struct pt_regs regs; + size_t rawsize; + int overflow; + + if (!cpump->event) /* No event active */ + return 0; + rawsize = paicrypt_copy(cpump->save, cpump, + cpump->event->attr.exclude_user, + cpump->event->attr.exclude_kernel); + if (!rawsize) /* No incremented counters */ + return 0; + + /* Setup perf sample */ + memset(®s, 0, sizeof(regs)); + memset(&raw, 0, sizeof(raw)); + memset(&data, 0, sizeof(data)); + perf_sample_data_init(&data, 0, event->hw.last_period); + if (event->attr.sample_type & PERF_SAMPLE_TID) { + data.tid_entry.pid = task_tgid_nr(current); + data.tid_entry.tid = task_pid_nr(current); + } + if (event->attr.sample_type & PERF_SAMPLE_TIME) + data.time = event->clock(); + if (event->attr.sample_type & (PERF_SAMPLE_ID | PERF_SAMPLE_IDENTIFIER)) + data.id = event->id; + if (event->attr.sample_type & PERF_SAMPLE_CPU) { + data.cpu_entry.cpu = smp_processor_id(); + data.cpu_entry.reserved = 0; + } + if (event->attr.sample_type & PERF_SAMPLE_RAW) { + raw.frag.size = rawsize; + raw.frag.data = cpump->save; + raw.size = raw.frag.size; + data.raw = &raw; + } + + overflow = perf_event_overflow(event, &data, ®s); + perf_event_update_userpage(event); + /* Clear lowcore page after read */ + memset(cpump->page, 0, PAGE_SIZE); + return overflow; +} + +/* Called on schedule-in and schedule-out. No access to event structure, + * but for sampling only event CRYPTO_ALL is allowed. + */ +static void paicrypt_sched_task(struct perf_event_context *ctx, bool sched_in) +{ + /* We started with a clean page on event installation. So read out + * results on schedule_out and if page was dirty, clear values. + */ + if (!sched_in) + paicrypt_push_sample(); +} + +/* Attribute definitions for paicrypt interface. As with other CPU + * Measurement Facilities, there is one attribute per mapped counter. + * The number of mapped counters may vary per machine generation. Use + * the QUERY PROCESSOR ACTIVITY COUNTER INFORMATION (QPACI) instruction + * to determine the number of mapped counters. The instructions returns + * a positive number, which is the highest number of supported counters. + * All counters less than this number are also supported, there are no + * holes. A returned number of zero means no support for mapped counters. + * + * The identification of the counter is a unique number. The chosen range + * is 0x1000 + offset in mapped kernel page. + * All CPU Measurement Facility counters identifiers must be unique and + * the numbers from 0 to 496 are already used for the CPU Measurement + * Counter facility. Numbers 0xb0000, 0xbc000 and 0xbd000 are already + * used for the CPU Measurement Sampling facility. + */ +PMU_FORMAT_ATTR(event, "config:0-63"); + +static struct attribute *paicrypt_format_attr[] = { + &format_attr_event.attr, + NULL, +}; + +static struct attribute_group paicrypt_events_group = { + .name = "events", + .attrs = NULL /* Filled in attr_event_init() */ +}; + +static struct attribute_group paicrypt_format_group = { + .name = "format", + .attrs = paicrypt_format_attr, +}; + +static const struct attribute_group *paicrypt_attr_groups[] = { + &paicrypt_events_group, + &paicrypt_format_group, + NULL, +}; + +/* Performance monitoring unit for mapped counters */ +static struct pmu paicrypt = { + .task_ctx_nr = perf_invalid_context, + .event_init = paicrypt_event_init, + .add = paicrypt_add, + .del = paicrypt_del, + .start = paicrypt_start, + .stop = paicrypt_stop, + .read = paicrypt_read, + .sched_task = paicrypt_sched_task, + .attr_groups = paicrypt_attr_groups +}; + +/* List of symbolic PAI counter names. */ +static const char * const paicrypt_ctrnames[] = { + [0] = "CRYPTO_ALL", + [1] = "KM_DEA", + [2] = "KM_TDEA_128", + [3] = "KM_TDEA_192", + [4] = "KM_ENCRYPTED_DEA", + [5] = "KM_ENCRYPTED_TDEA_128", + [6] = "KM_ENCRYPTED_TDEA_192", + [7] = "KM_AES_128", + [8] = "KM_AES_192", + [9] = "KM_AES_256", + [10] = "KM_ENCRYPTED_AES_128", + [11] = "KM_ENCRYPTED_AES_192", + [12] = "KM_ENCRYPTED_AES_256", + [13] = "KM_XTS_AES_128", + [14] = "KM_XTS_AES_256", + [15] = "KM_XTS_ENCRYPTED_AES_128", + [16] = "KM_XTS_ENCRYPTED_AES_256", + [17] = "KMC_DEA", + [18] = "KMC_TDEA_128", + [19] = "KMC_TDEA_192", + [20] = "KMC_ENCRYPTED_DEA", + [21] = "KMC_ENCRYPTED_TDEA_128", + [22] = "KMC_ENCRYPTED_TDEA_192", + [23] = "KMC_AES_128", + [24] = "KMC_AES_192", + [25] = "KMC_AES_256", + [26] = "KMC_ENCRYPTED_AES_128", + [27] = "KMC_ENCRYPTED_AES_192", + [28] = "KMC_ENCRYPTED_AES_256", + [29] = "KMC_PRNG", + [30] = "KMA_GCM_AES_128", + [31] = "KMA_GCM_AES_192", + [32] = "KMA_GCM_AES_256", + [33] = "KMA_GCM_ENCRYPTED_AES_128", + [34] = "KMA_GCM_ENCRYPTED_AES_192", + [35] = "KMA_GCM_ENCRYPTED_AES_256", + [36] = "KMF_DEA", + [37] = "KMF_TDEA_128", + [38] = "KMF_TDEA_192", + [39] = "KMF_ENCRYPTED_DEA", + [40] = "KMF_ENCRYPTED_TDEA_128", + [41] = "KMF_ENCRYPTED_TDEA_192", + [42] = "KMF_AES_128", + [43] = "KMF_AES_192", + [44] = "KMF_AES_256", + [45] = "KMF_ENCRYPTED_AES_128", + [46] = "KMF_ENCRYPTED_AES_192", + [47] = "KMF_ENCRYPTED_AES_256", + [48] = "KMCTR_DEA", + [49] = "KMCTR_TDEA_128", + [50] = "KMCTR_TDEA_192", + [51] = "KMCTR_ENCRYPTED_DEA", + [52] = "KMCTR_ENCRYPTED_TDEA_128", + [53] = "KMCTR_ENCRYPTED_TDEA_192", + [54] = "KMCTR_AES_128", + [55] = "KMCTR_AES_192", + [56] = "KMCTR_AES_256", + [57] = "KMCTR_ENCRYPTED_AES_128", + [58] = "KMCTR_ENCRYPTED_AES_192", + [59] = "KMCTR_ENCRYPTED_AES_256", + [60] = "KMO_DEA", + [61] = "KMO_TDEA_128", + [62] = "KMO_TDEA_192", + [63] = "KMO_ENCRYPTED_DEA", + [64] = "KMO_ENCRYPTED_TDEA_128", + [65] = "KMO_ENCRYPTED_TDEA_192", + [66] = "KMO_AES_128", + [67] = "KMO_AES_192", + [68] = "KMO_AES_256", + [69] = "KMO_ENCRYPTED_AES_128", + [70] = "KMO_ENCRYPTED_AES_192", + [71] = "KMO_ENCRYPTED_AES_256", + [72] = "KIMD_SHA_1", + [73] = "KIMD_SHA_256", + [74] = "KIMD_SHA_512", + [75] = "KIMD_SHA3_224", + [76] = "KIMD_SHA3_256", + [77] = "KIMD_SHA3_384", + [78] = "KIMD_SHA3_512", + [79] = "KIMD_SHAKE_128", + [80] = "KIMD_SHAKE_256", + [81] = "KIMD_GHASH", + [82] = "KLMD_SHA_1", + [83] = "KLMD_SHA_256", + [84] = "KLMD_SHA_512", + [85] = "KLMD_SHA3_224", + [86] = "KLMD_SHA3_256", + [87] = "KLMD_SHA3_384", + [88] = "KLMD_SHA3_512", + [89] = "KLMD_SHAKE_128", + [90] = "KLMD_SHAKE_256", + [91] = "KMAC_DEA", + [92] = "KMAC_TDEA_128", + [93] = "KMAC_TDEA_192", + [94] = "KMAC_ENCRYPTED_DEA", + [95] = "KMAC_ENCRYPTED_TDEA_128", + [96] = "KMAC_ENCRYPTED_TDEA_192", + [97] = "KMAC_AES_128", + [98] = "KMAC_AES_192", + [99] = "KMAC_AES_256", + [100] = "KMAC_ENCRYPTED_AES_128", + [101] = "KMAC_ENCRYPTED_AES_192", + [102] = "KMAC_ENCRYPTED_AES_256", + [103] = "PCC_COMPUTE_LAST_BLOCK_CMAC_USING_DEA", + [104] = "PCC_COMPUTE_LAST_BLOCK_CMAC_USING_TDEA_128", + [105] = "PCC_COMPUTE_LAST_BLOCK_CMAC_USING_TDEA_192", + [106] = "PCC_COMPUTE_LAST_BLOCK_CMAC_USING_ENCRYPTED_DEA", + [107] = "PCC_COMPUTE_LAST_BLOCK_CMAC_USING_ENCRYPTED_TDEA_128", + [108] = "PCC_COMPUTE_LAST_BLOCK_CMAC_USING_ENCRYPTED_TDEA_192", + [109] = "PCC_COMPUTE_LAST_BLOCK_CMAC_USING_AES_128", + [110] = "PCC_COMPUTE_LAST_BLOCK_CMAC_USING_AES_192", + [111] = "PCC_COMPUTE_LAST_BLOCK_CMAC_USING_AES_256", + [112] = "PCC_COMPUTE_LAST_BLOCK_CMAC_USING_ENCRYPTED_AES_128", + [113] = "PCC_COMPUTE_LAST_BLOCK_CMAC_USING_ENCRYPTED_AES_192", + [114] = "PCC_COMPUTE_LAST_BLOCK_CMAC_USING_ENCRYPTED_AES_256A", + [115] = "PCC_COMPUTE_XTS_PARAMETER_USING_AES_128", + [116] = "PCC_COMPUTE_XTS_PARAMETER_USING_AES_256", + [117] = "PCC_COMPUTE_XTS_PARAMETER_USING_ENCRYPTED_AES_128", + [118] = "PCC_COMPUTE_XTS_PARAMETER_USING_ENCRYPTED_AES_256", + [119] = "PCC_SCALAR_MULTIPLY_P256", + [120] = "PCC_SCALAR_MULTIPLY_P384", + [121] = "PCC_SCALAR_MULTIPLY_P521", + [122] = "PCC_SCALAR_MULTIPLY_ED25519", + [123] = "PCC_SCALAR_MULTIPLY_ED448", + [124] = "PCC_SCALAR_MULTIPLY_X25519", + [125] = "PCC_SCALAR_MULTIPLY_X448", + [126] = "PRNO_SHA_512_DRNG", + [127] = "PRNO_TRNG_QUERY_RAW_TO_CONDITIONED_RATIO", + [128] = "PRNO_TRNG", + [129] = "KDSA_ECDSA_VERIFY_P256", + [130] = "KDSA_ECDSA_VERIFY_P384", + [131] = "KDSA_ECDSA_VERIFY_P521", + [132] = "KDSA_ECDSA_SIGN_P256", + [133] = "KDSA_ECDSA_SIGN_P384", + [134] = "KDSA_ECDSA_SIGN_P521", + [135] = "KDSA_ENCRYPTED_ECDSA_SIGN_P256", + [136] = "KDSA_ENCRYPTED_ECDSA_SIGN_P384", + [137] = "KDSA_ENCRYPTED_ECDSA_SIGN_P521", + [138] = "KDSA_EDDSA_VERIFY_ED25519", + [139] = "KDSA_EDDSA_VERIFY_ED448", + [140] = "KDSA_EDDSA_SIGN_ED25519", + [141] = "KDSA_EDDSA_SIGN_ED448", + [142] = "KDSA_ENCRYPTED_EDDSA_SIGN_ED25519", + [143] = "KDSA_ENCRYPTED_EDDSA_SIGN_ED448", + [144] = "PCKMO_ENCRYPT_DEA_KEY", + [145] = "PCKMO_ENCRYPT_TDEA_128_KEY", + [146] = "PCKMO_ENCRYPT_TDEA_192_KEY", + [147] = "PCKMO_ENCRYPT_AES_128_KEY", + [148] = "PCKMO_ENCRYPT_AES_192_KEY", + [149] = "PCKMO_ENCRYPT_AES_256_KEY", + [150] = "PCKMO_ENCRYPT_ECC_P256_KEY", + [151] = "PCKMO_ENCRYPT_ECC_P384_KEY", + [152] = "PCKMO_ENCRYPT_ECC_P521_KEY", + [153] = "PCKMO_ENCRYPT_ECC_ED25519_KEY", + [154] = "PCKMO_ENCRYPT_ECC_ED448_KEY", + [155] = "IBM_RESERVED_155", + [156] = "IBM_RESERVED_156", +}; + +static void __init attr_event_free(struct attribute **attrs, int num) +{ + struct perf_pmu_events_attr *pa; + int i; + + for (i = 0; i < num; i++) { + struct device_attribute *dap; + + dap = container_of(attrs[i], struct device_attribute, attr); + pa = container_of(dap, struct perf_pmu_events_attr, attr); + kfree(pa); + } + kfree(attrs); +} + +static int __init attr_event_init_one(struct attribute **attrs, int num) +{ + struct perf_pmu_events_attr *pa; + + pa = kzalloc(sizeof(*pa), GFP_KERNEL); + if (!pa) + return -ENOMEM; + + sysfs_attr_init(&pa->attr.attr); + pa->id = PAI_CRYPTO_BASE + num; + pa->attr.attr.name = paicrypt_ctrnames[num]; + pa->attr.attr.mode = 0444; + pa->attr.show = cpumf_events_sysfs_show; + pa->attr.store = NULL; + attrs[num] = &pa->attr.attr; + return 0; +} + +/* Create PMU sysfs event attributes on the fly. */ +static int __init attr_event_init(void) +{ + struct attribute **attrs; + int ret, i; + + attrs = kmalloc_array(ARRAY_SIZE(paicrypt_ctrnames) + 1, sizeof(*attrs), + GFP_KERNEL); + if (!attrs) + return -ENOMEM; + for (i = 0; i < ARRAY_SIZE(paicrypt_ctrnames); i++) { + ret = attr_event_init_one(attrs, i); + if (ret) { + attr_event_free(attrs, i - 1); + return ret; + } + } + attrs[i] = NULL; + paicrypt_events_group.attrs = attrs; + return 0; +} + +static int __init paicrypt_init(void) +{ + struct qpaci_info_block ib; + int rc; + + if (!test_facility(196)) + return 0; + + qpaci(&ib); + paicrypt_cnt = ib.num_cc; + if (paicrypt_cnt == 0) + return 0; + if (paicrypt_cnt >= PAI_CRYPTO_MAXCTR) + paicrypt_cnt = PAI_CRYPTO_MAXCTR - 1; + + rc = attr_event_init(); /* Export known PAI crypto events */ + if (rc) { + pr_err("Creation of PMU pai_crypto /sysfs failed\n"); + return rc; + } + + /* Setup s390dbf facility */ + cfm_dbg = debug_register(KMSG_COMPONENT, 2, 256, 128); + if (!cfm_dbg) { + pr_err("Registration of s390dbf pai_crypto failed\n"); + return -ENOMEM; + } + debug_register_view(cfm_dbg, &debug_sprintf_view); + + rc = perf_pmu_register(&paicrypt, "pai_crypto", -1); + if (rc) { + pr_err("Registering the pai_crypto PMU failed with rc=%i\n", + rc); + debug_unregister_view(cfm_dbg, &debug_sprintf_view); + debug_unregister(cfm_dbg); + return rc; + } + return 0; +} + +device_initcall(paicrypt_init); diff --git a/arch/s390/kernel/processor.c b/arch/s390/kernel/processor.c index 7a74ea5f7531..aa0e0e7fc773 100644 --- a/arch/s390/kernel/processor.c +++ b/arch/s390/kernel/processor.c @@ -283,6 +283,10 @@ static int __init setup_elf_platform(void) case 0x8562: strcpy(elf_platform, "z15"); break; + case 0x3931: + case 0x3932: + strcpy(elf_platform, "z16"); + break; } return 0; } diff --git a/arch/s390/kernel/relocate_kernel.S b/arch/s390/kernel/relocate_kernel.S index 9438368c3632..a9a1a6f45375 100644 --- a/arch/s390/kernel/relocate_kernel.S +++ b/arch/s390/kernel/relocate_kernel.S @@ -14,6 +14,7 @@ * moves the new kernel to its destination... * %r2 = pointer to first kimage_entry_t * %r3 = start address - where to jump to after the job is done... + * %r4 = subcode * * %r5 will be used as temp. storage * %r6 holds the destination address @@ -56,7 +57,7 @@ ENTRY(relocate_kernel) jo 0b j .base .done: - sgr %r0,%r0 # clear register r0 + lgr %r0,%r4 # subcode cghi %r3,0 je .diag la %r4,load_psw-.base(%r13) # load psw-address into the register diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index d860ac300919..8d91eccc0963 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -494,7 +494,7 @@ static void __init setup_lowcore_dat_off(void) lc->return_mcck_lpswe = gen_lpswe(__LC_RETURN_MCCK_PSW); lc->preempt_count = PREEMPT_DISABLED; - set_prefix((u32)(unsigned long) lc); + set_prefix(__pa(lc)); lowcore_ptr[0] = lc; } diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index 326cb8f75f58..6b7b6d5e3632 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -364,7 +364,7 @@ static inline int check_sync_clock(void) * Apply clock delta to the global data structures. * This is called once on the CPU that performed the clock sync. */ -static void clock_sync_global(unsigned long delta) +static void clock_sync_global(long delta) { unsigned long now, adj; struct ptff_qto qto; @@ -400,7 +400,7 @@ static void clock_sync_global(unsigned long delta) * Apply clock delta to the per-CPU data structures of this CPU. * This is called for each online CPU after the call to clock_sync_global. */ -static void clock_sync_local(unsigned long delta) +static void clock_sync_local(long delta) { /* Add the delta to the clock comparator. */ if (S390_lowcore.clock_comparator != clock_comparator_max) { @@ -424,7 +424,7 @@ static void __init time_init_wq(void) struct clock_sync_data { atomic_t cpus; int in_sync; - unsigned long clock_delta; + long clock_delta; }; /* @@ -544,7 +544,7 @@ static int stpinfo_valid(void) static int stp_sync_clock(void *data) { struct clock_sync_data *sync = data; - u64 clock_delta, flags; + long clock_delta, flags; static int first; int rc; @@ -554,9 +554,7 @@ static int stp_sync_clock(void *data) while (atomic_read(&sync->cpus) != 0) cpu_relax(); rc = 0; - if (stp_info.todoff[0] || stp_info.todoff[1] || - stp_info.todoff[2] || stp_info.todoff[3] || - stp_info.tmd != 2) { + if (stp_info.todoff || stp_info.tmd != 2) { flags = vdso_update_begin(); rc = chsc_sstpc(stp_page, STP_OP_SYNC, 0, &clock_delta); diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c index 99694260cac9..5075cde77b29 100644 --- a/arch/s390/kernel/vdso.c +++ b/arch/s390/kernel/vdso.c @@ -16,6 +16,7 @@ #include <linux/slab.h> #include <linux/smp.h> #include <linux/time_namespace.h> +#include <linux/random.h> #include <vdso/datapage.h> #include <asm/vdso.h> @@ -160,10 +161,9 @@ int vdso_getcpu_init(void) } early_initcall(vdso_getcpu_init); /* Must be called before SMP init */ -int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) +static int map_vdso(unsigned long addr, unsigned long vdso_mapping_len) { - unsigned long vdso_text_len, vdso_mapping_len; - unsigned long vvar_start, vdso_text_start; + unsigned long vvar_start, vdso_text_start, vdso_text_len; struct vm_special_mapping *vdso_mapping; struct mm_struct *mm = current->mm; struct vm_area_struct *vma; @@ -180,8 +180,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) vdso_text_len = vdso64_end - vdso64_start; vdso_mapping = &vdso64_mapping; } - vdso_mapping_len = vdso_text_len + VVAR_NR_PAGES * PAGE_SIZE; - vvar_start = get_unmapped_area(NULL, 0, vdso_mapping_len, 0, 0); + vvar_start = get_unmapped_area(NULL, addr, vdso_mapping_len, 0, 0); rc = vvar_start; if (IS_ERR_VALUE(vvar_start)) goto out; @@ -210,6 +209,52 @@ out: return rc; } +static unsigned long vdso_addr(unsigned long start, unsigned long len) +{ + unsigned long addr, end, offset; + + /* + * Round up the start address. It can start out unaligned as a result + * of stack start randomization. + */ + start = PAGE_ALIGN(start); + + /* Round the lowest possible end address up to a PMD boundary. */ + end = (start + len + PMD_SIZE - 1) & PMD_MASK; + if (end >= VDSO_BASE) + end = VDSO_BASE; + end -= len; + + if (end > start) { + offset = get_random_int() % (((end - start) >> PAGE_SHIFT) + 1); + addr = start + (offset << PAGE_SHIFT); + } else { + addr = start; + } + return addr; +} + +unsigned long vdso_size(void) +{ + unsigned long size = VVAR_NR_PAGES * PAGE_SIZE; + + if (is_compat_task()) + size += vdso32_end - vdso32_start; + else + size += vdso64_end - vdso64_start; + return PAGE_ALIGN(size); +} + +int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) +{ + unsigned long addr = VDSO_BASE; + unsigned long size = vdso_size(); + + if (current->flags & PF_RANDOMIZE) + addr = vdso_addr(current->mm->start_stack + PAGE_SIZE, size); + return map_vdso(addr, size); +} + static struct page ** __init vdso_setup_pages(void *start, void *end) { int pages = (end - start) >> PAGE_SHIFT; diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 9b30beac904d..af96dc0549a4 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -1334,11 +1334,11 @@ int kvm_s390_handle_wait(struct kvm_vcpu *vcpu) hrtimer_start(&vcpu->arch.ckc_timer, sltime, HRTIMER_MODE_REL); VCPU_EVENT(vcpu, 4, "enabled wait: %llu ns", sltime); no_timer: - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); kvm_vcpu_halt(vcpu); vcpu->valid_wakeup = false; __unset_cpu_idle(vcpu); - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); hrtimer_cancel(&vcpu->arch.ckc_timer); return 0; diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 156d1c25a3c1..76ad6408cb2c 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -2384,7 +2384,16 @@ static int kvm_s390_vm_mem_op(struct kvm *kvm, struct kvm_s390_mem_op *mop) return -EINVAL; if (mop->size > MEM_OP_MAX_SIZE) return -E2BIG; - if (kvm_s390_pv_is_protected(kvm)) + /* + * This is technically a heuristic only, if the kvm->lock is not + * taken, it is not guaranteed that the vm is/remains non-protected. + * This is ok from a kernel perspective, wrongdoing is detected + * on the access, -EFAULT is returned and the vm may crash the + * next time it accesses the memory in question. + * There is no sane usecase to do switching and a memop on two + * different CPUs at the same time. + */ + if (kvm_s390_pv_get_handle(kvm)) return -EINVAL; if (mop->flags & KVM_S390_MEMOP_F_SKEY_PROTECTION) { if (access_key_invalid(mop->key)) @@ -4237,14 +4246,14 @@ static int __vcpu_run(struct kvm_vcpu *vcpu) * We try to hold kvm->srcu during most of vcpu_run (except when run- * ning the guest), so that memslots (and other stuff) are protected */ - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); do { rc = vcpu_pre_run(vcpu); if (rc) break; - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); /* * As PF_VCPU will be used in fault handler, between * guest_enter and guest_exit should be no uaccess. @@ -4281,12 +4290,12 @@ static int __vcpu_run(struct kvm_vcpu *vcpu) __enable_cpu_timer_accounting(vcpu); guest_exit_irqoff(); local_irq_enable(); - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); rc = vcpu_post_run(vcpu, exit_reason); } while (!signal_pending(current) && !guestdbg_exit_pending(vcpu) && !rc); - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); return rc; } diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index 5beb7a4a11b3..83bb5cf97282 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -11,7 +11,6 @@ #include <linux/kvm.h> #include <linux/gfp.h> #include <linux/errno.h> -#include <linux/compat.h> #include <linux/mm_types.h> #include <linux/pgtable.h> diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c index 7f7c0d6af2ce..cc7c9599f43e 100644 --- a/arch/s390/kvm/pv.c +++ b/arch/s390/kvm/pv.c @@ -137,12 +137,7 @@ static int kvm_s390_pv_alloc_vm(struct kvm *kvm) /* Allocate variable storage */ vlen = ALIGN(virt * ((npages * PAGE_SIZE) / HPAGE_SIZE), PAGE_SIZE); vlen += uv_info.guest_virt_base_stor_len; - /* - * The Create Secure Configuration Ultravisor Call does not support - * using large pages for the virtual memory area. - * This is a hardware limitation. - */ - kvm->arch.pv.stor_var = vmalloc_no_huge(vlen); + kvm->arch.pv.stor_var = vzalloc(vlen); if (!kvm->arch.pv.stor_var) goto out_err; return 0; diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c index acda4b6fc851..dada78b92691 100644 --- a/arch/s390/kvm/vsie.c +++ b/arch/s390/kvm/vsie.c @@ -1091,7 +1091,7 @@ static int do_vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) handle_last_fault(vcpu, vsie_page); - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); /* save current guest state of bp isolation override */ guest_bp_isolation = test_thread_flag(TIF_ISOLATE_BP_GUEST); @@ -1133,7 +1133,7 @@ static int do_vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) if (!guest_bp_isolation) clear_thread_flag(TIF_ISOLATE_BP_GUEST); - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); if (rc == -EINTR) { VCPU_EVENT(vcpu, 3, "%s", "machine check"); diff --git a/arch/s390/lib/spinlock.c b/arch/s390/lib/spinlock.c index 5e7ea8b111e8..04d4c6cf898e 100644 --- a/arch/s390/lib/spinlock.c +++ b/arch/s390/lib/spinlock.c @@ -75,7 +75,7 @@ static inline int arch_load_niai4(int *lock) int owner; asm_inline volatile( - ALTERNATIVE("", ".insn rre,0xb2fa0000,4,0", 49) /* NIAI 4 */ + ALTERNATIVE("nop", ".insn rre,0xb2fa0000,4,0", 49) /* NIAI 4 */ " l %0,%1\n" : "=d" (owner) : "Q" (*lock) : "memory"); return owner; @@ -86,7 +86,7 @@ static inline int arch_cmpxchg_niai8(int *lock, int old, int new) int expected = old; asm_inline volatile( - ALTERNATIVE("", ".insn rre,0xb2fa0000,8,0", 49) /* NIAI 8 */ + ALTERNATIVE("nop", ".insn rre,0xb2fa0000,8,0", 49) /* NIAI 8 */ " cs %0,%3,%1\n" : "=d" (old), "=Q" (*lock) : "0" (old), "d" (new), "Q" (*lock) diff --git a/arch/s390/lib/test_unwind.c b/arch/s390/lib/test_unwind.c index 9bb067321ab4..5a053b393d5c 100644 --- a/arch/s390/lib/test_unwind.c +++ b/arch/s390/lib/test_unwind.c @@ -147,7 +147,7 @@ static __always_inline struct pt_regs fake_pt_regs(void) struct pt_regs regs; memset(®s, 0, sizeof(regs)); - regs.gprs[15] = current_stack_pointer(); + regs.gprs[15] = current_stack_pointer; asm volatile( "basr %[psw_addr],0\n" diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c index af03cacf34ec..1ac73917a8d3 100644 --- a/arch/s390/mm/gmap.c +++ b/arch/s390/mm/gmap.c @@ -1183,6 +1183,7 @@ EXPORT_SYMBOL_GPL(gmap_read_table); static inline void gmap_insert_rmap(struct gmap *sg, unsigned long vmaddr, struct gmap_rmap *rmap) { + struct gmap_rmap *temp; void __rcu **slot; BUG_ON(!gmap_is_shadow(sg)); @@ -1190,6 +1191,12 @@ static inline void gmap_insert_rmap(struct gmap *sg, unsigned long vmaddr, if (slot) { rmap->next = radix_tree_deref_slot_protected(slot, &sg->guest_table_lock); + for (temp = rmap->next; temp; temp = temp->next) { + if (temp->raddr == rmap->raddr) { + kfree(rmap); + return; + } + } radix_tree_replace_slot(&sg->host_to_rmap, slot, rmap); } else { rmap->next = NULL; diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c index e54f928503c5..d545f5c39f7e 100644 --- a/arch/s390/mm/mmap.c +++ b/arch/s390/mm/mmap.c @@ -58,9 +58,9 @@ static inline unsigned long mmap_base(unsigned long rnd, /* * Top of mmap area (just below the process stack). - * Leave at least a ~32 MB hole. + * Leave at least a ~128 MB hole. */ - gap_min = 32 * 1024 * 1024UL; + gap_min = SZ_128M; gap_max = (STACK_TOP / 6) * 5; if (gap < gap_min) diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index e563cb65c0c4..bc980fd313d5 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -799,7 +799,7 @@ struct zpci_dev *zpci_create_device(u32 fid, u32 fh, enum zpci_state state) struct zpci_dev *zdev; int rc; - zpci_dbg(3, "add fid:%x, fh:%x, c:%d\n", fid, fh, state); + zpci_dbg(1, "add fid:%x, fh:%x, c:%d\n", fid, fh, state); zdev = kzalloc(sizeof(*zdev), GFP_KERNEL); if (!zdev) return ERR_PTR(-ENOMEM); diff --git a/arch/s390/pci/pci_clp.c b/arch/s390/pci/pci_clp.c index 1057d7af4a55..375e0a5120bc 100644 --- a/arch/s390/pci/pci_clp.c +++ b/arch/s390/pci/pci_clp.c @@ -30,7 +30,7 @@ bool zpci_unique_uid; void update_uid_checking(bool new) { if (zpci_unique_uid != new) - zpci_dbg(1, "uid checking:%d\n", new); + zpci_dbg(3, "uid checking:%d\n", new); zpci_unique_uid = new; } diff --git a/arch/s390/pci/pci_debug.c b/arch/s390/pci/pci_debug.c index 3408c0df3ebf..ca6bd98eec13 100644 --- a/arch/s390/pci/pci_debug.c +++ b/arch/s390/pci/pci_debug.c @@ -196,7 +196,7 @@ int __init zpci_debug_init(void) if (!pci_debug_err_id) return -EINVAL; debug_register_view(pci_debug_err_id, &debug_hex_ascii_view); - debug_set_level(pci_debug_err_id, 6); + debug_set_level(pci_debug_err_id, 3); debugfs_root = debugfs_create_dir("pci", NULL); return 0; diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c index ea9db5cea64e..b9324ca2eb94 100644 --- a/arch/s390/pci/pci_event.c +++ b/arch/s390/pci/pci_event.c @@ -321,9 +321,6 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf) zpci_dbg(3, "avl fid:%x, fh:%x, pec:%x\n", ccdf->fid, ccdf->fh, ccdf->pec); - zpci_err("avail CCDF:\n"); - zpci_err_hex(ccdf, sizeof(*ccdf)); - switch (ccdf->pec) { case 0x0301: /* Reserved|Standby -> Configured */ if (!zdev) { diff --git a/arch/s390/pci/pci_insn.c b/arch/s390/pci/pci_insn.c index 1710d006ee93..1a822b7799f8 100644 --- a/arch/s390/pci/pci_insn.c +++ b/arch/s390/pci/pci_insn.c @@ -18,16 +18,40 @@ #define ZPCI_INSN_BUSY_DELAY 1 /* 1 microsecond */ -static inline void zpci_err_insn(u8 cc, u8 status, u64 req, u64 offset) +struct zpci_err_insn_data { + u8 insn; + u8 cc; + u8 status; + union { + struct { + u64 req; + u64 offset; + }; + struct { + u64 addr; + u64 len; + }; + }; +} __packed; + +static inline void zpci_err_insn_req(int lvl, u8 insn, u8 cc, u8 status, + u64 req, u64 offset) { - struct { - u64 req; - u64 offset; - u8 cc; - u8 status; - } __packed data = {req, offset, cc, status}; - - zpci_err_hex(&data, sizeof(data)); + struct zpci_err_insn_data data = { + .insn = insn, .cc = cc, .status = status, + .req = req, .offset = offset}; + + zpci_err_hex_level(lvl, &data, sizeof(data)); +} + +static inline void zpci_err_insn_addr(int lvl, u8 insn, u8 cc, u8 status, + u64 addr, u64 len) +{ + struct zpci_err_insn_data data = { + .insn = insn, .cc = cc, .status = status, + .addr = addr, .len = len}; + + zpci_err_hex_level(lvl, &data, sizeof(data)); } /* Modify PCI Function Controls */ @@ -47,16 +71,24 @@ static inline u8 __mpcifc(u64 req, struct zpci_fib *fib, u8 *status) u8 zpci_mod_fc(u64 req, struct zpci_fib *fib, u8 *status) { + bool retried = false; u8 cc; do { cc = __mpcifc(req, fib, status); - if (cc == 2) + if (cc == 2) { msleep(ZPCI_INSN_BUSY_DELAY); + if (!retried) { + zpci_err_insn_req(1, 'M', cc, *status, req, 0); + retried = true; + } + } } while (cc == 2); if (cc) - zpci_err_insn(cc, *status, req, 0); + zpci_err_insn_req(0, 'M', cc, *status, req, 0); + else if (retried) + zpci_err_insn_req(1, 'M', cc, *status, req, 0); return cc; } @@ -80,16 +112,24 @@ static inline u8 __rpcit(u64 fn, u64 addr, u64 range, u8 *status) int zpci_refresh_trans(u64 fn, u64 addr, u64 range) { + bool retried = false; u8 cc, status; do { cc = __rpcit(fn, addr, range, &status); - if (cc == 2) + if (cc == 2) { udelay(ZPCI_INSN_BUSY_DELAY); + if (!retried) { + zpci_err_insn_addr(1, 'R', cc, status, addr, range); + retried = true; + } + } } while (cc == 2); if (cc) - zpci_err_insn(cc, status, addr, range); + zpci_err_insn_addr(0, 'R', cc, status, addr, range); + else if (retried) + zpci_err_insn_addr(1, 'R', cc, status, addr, range); if (cc == 1 && (status == 4 || status == 16)) return -ENOMEM; @@ -144,17 +184,25 @@ static inline int __pcilg(u64 *data, u64 req, u64 offset, u8 *status) int __zpci_load(u64 *data, u64 req, u64 offset) { + bool retried = false; u8 status; int cc; do { cc = __pcilg(data, req, offset, &status); - if (cc == 2) + if (cc == 2) { udelay(ZPCI_INSN_BUSY_DELAY); + if (!retried) { + zpci_err_insn_req(1, 'l', cc, status, req, offset); + retried = true; + } + } } while (cc == 2); if (cc) - zpci_err_insn(cc, status, req, offset); + zpci_err_insn_req(0, 'l', cc, status, req, offset); + else if (retried) + zpci_err_insn_req(1, 'l', cc, status, req, offset); return (cc > 0) ? -EIO : cc; } @@ -198,7 +246,7 @@ int zpci_load(u64 *data, const volatile void __iomem *addr, unsigned long len) cc = __pcilg_mio(data, (__force u64) addr, len, &status); if (cc) - zpci_err_insn(cc, status, 0, (__force u64) addr); + zpci_err_insn_addr(0, 'L', cc, status, (__force u64) addr, len); return (cc > 0) ? -EIO : cc; } @@ -225,17 +273,25 @@ static inline int __pcistg(u64 data, u64 req, u64 offset, u8 *status) int __zpci_store(u64 data, u64 req, u64 offset) { + bool retried = false; u8 status; int cc; do { cc = __pcistg(data, req, offset, &status); - if (cc == 2) + if (cc == 2) { udelay(ZPCI_INSN_BUSY_DELAY); + if (!retried) { + zpci_err_insn_req(1, 's', cc, status, req, offset); + retried = true; + } + } } while (cc == 2); if (cc) - zpci_err_insn(cc, status, req, offset); + zpci_err_insn_req(0, 's', cc, status, req, offset); + else if (retried) + zpci_err_insn_req(1, 's', cc, status, req, offset); return (cc > 0) ? -EIO : cc; } @@ -278,7 +334,7 @@ int zpci_store(const volatile void __iomem *addr, u64 data, unsigned long len) cc = __pcistg_mio(data, (__force u64) addr, len, &status); if (cc) - zpci_err_insn(cc, status, 0, (__force u64) addr); + zpci_err_insn_addr(0, 'S', cc, status, (__force u64) addr, len); return (cc > 0) ? -EIO : cc; } @@ -304,17 +360,25 @@ static inline int __pcistb(const u64 *data, u64 req, u64 offset, u8 *status) int __zpci_store_block(const u64 *data, u64 req, u64 offset) { + bool retried = false; u8 status; int cc; do { cc = __pcistb(data, req, offset, &status); - if (cc == 2) + if (cc == 2) { udelay(ZPCI_INSN_BUSY_DELAY); + if (!retried) { + zpci_err_insn_req(0, 'b', cc, status, req, offset); + retried = true; + } + } } while (cc == 2); if (cc) - zpci_err_insn(cc, status, req, offset); + zpci_err_insn_req(0, 'b', cc, status, req, offset); + else if (retried) + zpci_err_insn_req(1, 'b', cc, status, req, offset); return (cc > 0) ? -EIO : cc; } @@ -358,7 +422,7 @@ int zpci_write_block(volatile void __iomem *dst, cc = __pcistb_mio(src, (__force u64) dst, len, &status); if (cc) - zpci_err_insn(cc, status, 0, (__force u64) dst); + zpci_err_insn_addr(0, 'B', cc, status, (__force u64) dst, len); return (cc > 0) ? -EIO : cc; } diff --git a/arch/s390/purgatory/head.S b/arch/s390/purgatory/head.S index 3d1c31e0cf3d..6f835124ee82 100644 --- a/arch/s390/purgatory/head.S +++ b/arch/s390/purgatory/head.S @@ -44,11 +44,14 @@ .endm .macro MEMSWAP dst,src,buf,len -10: cghi \len,bufsz +10: larl %r0,purgatory_end + larl %r1,stack + slgr %r0,%r1 + cgr \len,%r0 jh 11f lgr %r4,\len j 12f -11: lghi %r4,bufsz +11: lgr %r4,%r0 12: MEMCPY \buf,\dst,%r4 MEMCPY \dst,\src,%r4 @@ -135,12 +138,18 @@ ENTRY(purgatory_start) .start_crash_kernel: /* Location of purgatory_start in crash memory */ + larl %r0,.base_crash + larl %r1,purgatory_start + slgr %r0,%r1 lgr %r8,%r13 - aghi %r8,-(.base_crash-purgatory_start) + sgr %r8,%r0 /* Destination for this code i.e. end of memory to be swapped. */ + larl %r0,purgatory_end + larl %r1,purgatory_start + slgr %r0,%r1 lg %r9,crash_size-.base_crash(%r13) - aghi %r9,-(purgatory_end-purgatory_start) + sgr %r9,%r0 /* Destination in crash memory, i.e. same as r9 but in crash memory. */ lg %r10,crash_start-.base_crash(%r13) @@ -149,15 +158,19 @@ ENTRY(purgatory_start) /* Buffer location (in crash memory) and size. As the purgatory is * behind the point of no return it can re-use the stack as buffer. */ - lghi %r11,bufsz + larl %r11,purgatory_end larl %r12,stack + slgr %r11,%r12 MEMCPY %r12,%r9,%r11 /* dst -> (crash) buf */ MEMCPY %r9,%r8,%r11 /* self -> dst */ /* Jump to new location. */ lgr %r7,%r9 - aghi %r7,.jump_to_dst-purgatory_start + larl %r0,.jump_to_dst + larl %r1,purgatory_start + slgr %r0,%r1 + agr %r7,%r0 br %r7 .jump_to_dst: @@ -169,7 +182,10 @@ ENTRY(purgatory_start) /* Load new buffer location after jump */ larl %r7,stack - aghi %r10,stack-purgatory_start + lgr %r0,%r7 + larl %r1,purgatory_start + slgr %r0,%r1 + agr %r10,%r0 MEMCPY %r10,%r7,%r11 /* (new) buf -> (crash) buf */ /* Now the code is set up to run from its designated location. Start diff --git a/arch/sh/boards/board-sh7757lcr.c b/arch/sh/boards/board-sh7757lcr.c index c32b4c6229d3..f39c8196efdf 100644 --- a/arch/sh/boards/board-sh7757lcr.c +++ b/arch/sh/boards/board-sh7757lcr.c @@ -16,7 +16,7 @@ #include <linux/io.h> #include <linux/mfd/tmio.h> #include <linux/mmc/host.h> -#include <linux/mmc/sh_mmcif.h> +#include <linux/platform_data/sh_mmcif.h> #include <linux/sh_eth.h> #include <linux/sh_intc.h> #include <linux/usb/renesas_usbhs.h> diff --git a/arch/sh/boards/mach-ecovec24/setup.c b/arch/sh/boards/mach-ecovec24/setup.c index 4c9522dd351f..674da7ebd8b7 100644 --- a/arch/sh/boards/mach-ecovec24/setup.c +++ b/arch/sh/boards/mach-ecovec24/setup.c @@ -19,7 +19,7 @@ #include <linux/memblock.h> #include <linux/mfd/tmio.h> #include <linux/mmc/host.h> -#include <linux/mmc/sh_mmcif.h> +#include <linux/platform_data/sh_mmcif.h> #include <linux/mtd/physmap.h> #include <linux/gpio.h> #include <linux/gpio/machine.h> diff --git a/arch/sh/boot/romimage/mmcif-sh7724.c b/arch/sh/boot/romimage/mmcif-sh7724.c index 6595b6b45bf1..d30123d859e0 100644 --- a/arch/sh/boot/romimage/mmcif-sh7724.c +++ b/arch/sh/boot/romimage/mmcif-sh7724.c @@ -8,7 +8,7 @@ * for more details. */ -#include <linux/mmc/sh_mmcif.h> +#include <linux/platform_data/sh_mmcif.h> #include <mach/romimage.h> #define MMCIF_BASE (void __iomem *)0xa4ca0000 diff --git a/arch/sh/configs/rsk7201_defconfig b/arch/sh/configs/rsk7201_defconfig index e41526120be1..619c18699459 100644 --- a/arch/sh/configs/rsk7201_defconfig +++ b/arch/sh/configs/rsk7201_defconfig @@ -25,7 +25,6 @@ CONFIG_CMDLINE_OVERWRITE=y CONFIG_CMDLINE="console=ttySC0,115200 earlyprintk=serial ignore_loglevel" CONFIG_BINFMT_FLAT=y CONFIG_BINFMT_ZFLAT=y -CONFIG_BINFMT_SHARED_FLAT=y CONFIG_PM=y CONFIG_CPU_IDLE=y # CONFIG_STANDALONE is not set diff --git a/arch/sh/configs/rsk7203_defconfig b/arch/sh/configs/rsk7203_defconfig index 6af08fa1ddf8..5a54e2b883f0 100644 --- a/arch/sh/configs/rsk7203_defconfig +++ b/arch/sh/configs/rsk7203_defconfig @@ -30,7 +30,6 @@ CONFIG_CMDLINE_OVERWRITE=y CONFIG_CMDLINE="console=ttySC0,115200 earlyprintk=serial ignore_loglevel" CONFIG_BINFMT_FLAT=y CONFIG_BINFMT_ZFLAT=y -CONFIG_BINFMT_SHARED_FLAT=y CONFIG_PM=y CONFIG_CPU_IDLE=y CONFIG_NET=y diff --git a/arch/sh/configs/se7206_defconfig b/arch/sh/configs/se7206_defconfig index 601d062250d1..122216123e63 100644 --- a/arch/sh/configs/se7206_defconfig +++ b/arch/sh/configs/se7206_defconfig @@ -40,7 +40,6 @@ CONFIG_CMDLINE_OVERWRITE=y CONFIG_CMDLINE="console=ttySC3,115200 ignore_loglevel earlyprintk=serial" CONFIG_BINFMT_FLAT=y CONFIG_BINFMT_ZFLAT=y -CONFIG_BINFMT_SHARED_FLAT=y CONFIG_BINFMT_MISC=y CONFIG_NET=y CONFIG_PACKET=y diff --git a/arch/sparc/include/asm/cacheflush_32.h b/arch/sparc/include/asm/cacheflush_32.h index 41c6d734a474..adb6991d0455 100644 --- a/arch/sparc/include/asm/cacheflush_32.h +++ b/arch/sparc/include/asm/cacheflush_32.h @@ -35,6 +35,7 @@ #define flush_page_for_dma(addr) \ sparc32_cachetlb_ops->page_for_dma(addr) +struct page; void sparc_flush_page_to_ram(struct page *page); #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 diff --git a/arch/sparc/include/asm/timex_32.h b/arch/sparc/include/asm/timex_32.h index 542915b46209..f86326a6f89e 100644 --- a/arch/sparc/include/asm/timex_32.h +++ b/arch/sparc/include/asm/timex_32.h @@ -9,8 +9,6 @@ #define CLOCK_TICK_RATE 1193180 /* Underlying HZ */ -/* XXX Maybe do something better at some point... -DaveM */ -typedef unsigned long cycles_t; -#define get_cycles() (0) +#include <asm-generic/timex.h> #endif diff --git a/arch/sparc/kernel/signal32.c b/arch/sparc/kernel/signal32.c index f9fe502b81c6..dad38960d1a8 100644 --- a/arch/sparc/kernel/signal32.c +++ b/arch/sparc/kernel/signal32.c @@ -779,5 +779,6 @@ static_assert(offsetof(compat_siginfo_t, si_upper) == 0x18); static_assert(offsetof(compat_siginfo_t, si_pkey) == 0x14); static_assert(offsetof(compat_siginfo_t, si_perf_data) == 0x10); static_assert(offsetof(compat_siginfo_t, si_perf_type) == 0x14); +static_assert(offsetof(compat_siginfo_t, si_perf_flags) == 0x18); static_assert(offsetof(compat_siginfo_t, si_band) == 0x0c); static_assert(offsetof(compat_siginfo_t, si_fd) == 0x10); diff --git a/arch/sparc/kernel/signal_64.c b/arch/sparc/kernel/signal_64.c index 8b9fc76cd3e0..570e43e6fda5 100644 --- a/arch/sparc/kernel/signal_64.c +++ b/arch/sparc/kernel/signal_64.c @@ -590,5 +590,6 @@ static_assert(offsetof(siginfo_t, si_upper) == 0x28); static_assert(offsetof(siginfo_t, si_pkey) == 0x20); static_assert(offsetof(siginfo_t, si_perf_data) == 0x18); static_assert(offsetof(siginfo_t, si_perf_type) == 0x20); +static_assert(offsetof(siginfo_t, si_perf_flags) == 0x24); static_assert(offsetof(siginfo_t, si_band) == 0x10); static_assert(offsetof(siginfo_t, si_fd) == 0x14); diff --git a/arch/sparc/vdso/Makefile b/arch/sparc/vdso/Makefile index c5e1545bc5cf..77d7b9032158 100644 --- a/arch/sparc/vdso/Makefile +++ b/arch/sparc/vdso/Makefile @@ -58,7 +58,7 @@ CFL := $(PROFILING) -mcmodel=medlow -fPIC -O2 -fasynchronous-unwind-tables -m64 SPARC_REG_CFLAGS = -ffixed-g4 -ffixed-g5 -fcall-used-g5 -fcall-used-g7 -$(vobjs): KBUILD_CFLAGS := $(filter-out $(GCC_PLUGINS_CFLAGS) $(SPARC_REG_CFLAGS),$(KBUILD_CFLAGS)) $(CFL) +$(vobjs): KBUILD_CFLAGS := $(filter-out $(RANDSTRUCT_CFLAGS) $(GCC_PLUGINS_CFLAGS) $(SPARC_REG_CFLAGS),$(KBUILD_CFLAGS)) $(CFL) # # vDSO code runs in userspace and -pg doesn't help with profiling anyway. @@ -88,6 +88,7 @@ $(obj)/vdso32.so.dbg: asflags-$(CONFIG_SPARC64) += -m32 KBUILD_CFLAGS_32 := $(filter-out -m64,$(KBUILD_CFLAGS)) KBUILD_CFLAGS_32 := $(filter-out -mcmodel=medlow,$(KBUILD_CFLAGS_32)) KBUILD_CFLAGS_32 := $(filter-out -fno-pic,$(KBUILD_CFLAGS_32)) +KBUILD_CFLAGS_32 := $(filter-out $(RANDSTRUCT_CFLAGS),$(KBUILD_CFLAGS_32)) KBUILD_CFLAGS_32 := $(filter-out $(GCC_PLUGINS_CFLAGS),$(KBUILD_CFLAGS_32)) KBUILD_CFLAGS_32 := $(filter-out $(SPARC_REG_CFLAGS),$(KBUILD_CFLAGS_32)) KBUILD_CFLAGS_32 += -m32 -msoft-float -fpic diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c index b03269faef71..c4344b67628d 100644 --- a/arch/um/drivers/ubd_kern.c +++ b/arch/um/drivers/ubd_kern.c @@ -483,7 +483,6 @@ static void ubd_handler(void) if ((io_req->error == BLK_STS_NOTSUPP) && (req_op(io_req->req) == REQ_OP_DISCARD)) { blk_queue_max_discard_sectors(io_req->req->q, 0); blk_queue_max_write_zeroes_sectors(io_req->req->q, 0); - blk_queue_flag_clear(QUEUE_FLAG_DISCARD, io_req->req->q); } blk_mq_end_request(io_req->req, io_req->error); kfree(io_req); @@ -800,10 +799,8 @@ static int ubd_open_dev(struct ubd *ubd_dev) } if (ubd_dev->no_trim == 0) { ubd_dev->queue->limits.discard_granularity = SECTOR_SIZE; - ubd_dev->queue->limits.discard_alignment = SECTOR_SIZE; blk_queue_max_discard_sectors(ubd_dev->queue, UBD_MAX_REQUEST); blk_queue_max_write_zeroes_sectors(ubd_dev->queue, UBD_MAX_REQUEST); - blk_queue_flag_set(QUEUE_FLAG_DISCARD, ubd_dev->queue); } blk_queue_flag_set(QUEUE_FLAG_NONROT, ubd_dev->queue); return 0; diff --git a/arch/um/include/asm/timex.h b/arch/um/include/asm/timex.h index e392a9a5bc9b..9f27176adb26 100644 --- a/arch/um/include/asm/timex.h +++ b/arch/um/include/asm/timex.h @@ -2,13 +2,8 @@ #ifndef __UM_TIMEX_H #define __UM_TIMEX_H -typedef unsigned long cycles_t; - -static inline cycles_t get_cycles (void) -{ - return 0; -} - #define CLOCK_TICK_RATE (HZ) +#include <asm-generic/timex.h> + #endif diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index b0142e01002e..762a0b6ab8b6 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -188,7 +188,7 @@ config X86 select HAVE_CONTEXT_TRACKING if X86_64 select HAVE_CONTEXT_TRACKING_OFFSTACK if HAVE_CONTEXT_TRACKING select HAVE_C_RECORDMCOUNT - select HAVE_OBJTOOL_MCOUNT if STACK_VALIDATION + select HAVE_OBJTOOL_MCOUNT if HAVE_OBJTOOL select HAVE_BUILDTIME_MCOUNT_SORT select HAVE_DEBUG_KMEMLEAK select HAVE_DMA_CONTIGUOUS @@ -212,6 +212,7 @@ config X86 select HAVE_IOREMAP_PROT select HAVE_IRQ_EXIT_ON_IRQ_STACK if X86_64 select HAVE_IRQ_TIME_ACCOUNTING + select HAVE_JUMP_LABEL_HACK if HAVE_OBJTOOL select HAVE_KERNEL_BZIP2 select HAVE_KERNEL_GZIP select HAVE_KERNEL_LZ4 @@ -230,7 +231,10 @@ config X86 select HAVE_MOD_ARCH_SPECIFIC select HAVE_MOVE_PMD select HAVE_MOVE_PUD + select HAVE_NOINSTR_HACK if HAVE_OBJTOOL select HAVE_NMI + select HAVE_NOINSTR_VALIDATION if HAVE_OBJTOOL + select HAVE_OBJTOOL if X86_64 select HAVE_OPTPROBES select HAVE_PCSPKR_PLATFORM select HAVE_PERF_EVENTS @@ -239,17 +243,17 @@ config X86 select HAVE_PCI select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP - select MMU_GATHER_RCU_TABLE_FREE if PARAVIRT + select MMU_GATHER_RCU_TABLE_FREE if PARAVIRT select HAVE_POSIX_CPU_TIMERS_TASK_WORK select HAVE_REGS_AND_STACK_ACCESS_API - select HAVE_RELIABLE_STACKTRACE if X86_64 && (UNWINDER_FRAME_POINTER || UNWINDER_ORC) && STACK_VALIDATION + select HAVE_RELIABLE_STACKTRACE if UNWINDER_ORC || STACK_VALIDATION select HAVE_FUNCTION_ARG_ACCESS_API select HAVE_SETUP_PER_CPU_AREA select HAVE_SOFTIRQ_ON_OWN_STACK select HAVE_STACKPROTECTOR if CC_HAS_SANE_STACKPROTECTOR - select HAVE_STACK_VALIDATION if X86_64 + select HAVE_STACK_VALIDATION if HAVE_OBJTOOL select HAVE_STATIC_CALL - select HAVE_STATIC_CALL_INLINE if HAVE_STACK_VALIDATION + select HAVE_STATIC_CALL_INLINE if HAVE_OBJTOOL select HAVE_PREEMPT_DYNAMIC_CALL select HAVE_RSEQ select HAVE_SYSCALL_TRACEPOINTS @@ -268,7 +272,6 @@ config X86 select RTC_MC146818_LIB select SPARSE_IRQ select SRCU - select STACK_VALIDATION if HAVE_STACK_VALIDATION && (HAVE_STATIC_CALL_INLINE || RETPOLINE) select SYSCTL_EXCEPTION_TRACE select THREAD_INFO_IN_TASK select TRACE_IRQFLAGS_SUPPORT @@ -459,6 +462,7 @@ config GOLDFISH config RETPOLINE bool "Avoid speculative indirect branches in kernel" + select OBJTOOL if HAVE_OBJTOOL default y help Compile kernel with the retpoline compiler options to guard against @@ -472,6 +476,7 @@ config CC_HAS_SLS config SLS bool "Mitigate Straight-Line-Speculation" depends on CC_HAS_SLS && X86_64 + select OBJTOOL if HAVE_OBJTOOL default n help Compile the kernel with straight-line-speculation options to guard @@ -878,6 +883,21 @@ config ACRN_GUEST IOT with small footprint and real-time features. More details can be found in https://projectacrn.org/. +config INTEL_TDX_GUEST + bool "Intel TDX (Trust Domain Extensions) - Guest Support" + depends on X86_64 && CPU_SUP_INTEL + depends on X86_X2APIC + select ARCH_HAS_CC_PLATFORM + select X86_MEM_ENCRYPT + select X86_MCE + help + Support running as a guest under Intel TDX. Without this support, + the guest kernel can not boot or run under TDX. + TDX includes memory encryption and integrity capabilities + which protect the confidentiality and integrity of guest + memory contents and CPU state. TDX guests are protected from + some attacks from the VMM. + endif #HYPERVISOR_GUEST source "arch/x86/Kconfig.cpu" @@ -1313,7 +1333,7 @@ config MICROCODE config MICROCODE_INTEL bool "Intel microcode loading support" - depends on MICROCODE + depends on CPU_SUP_INTEL && MICROCODE default MICROCODE help This options enables microcode patch loading support for Intel @@ -1325,7 +1345,7 @@ config MICROCODE_INTEL config MICROCODE_AMD bool "AMD microcode loading support" - depends on MICROCODE + depends on CPU_SUP_AMD && MICROCODE help If you select this option, microcode patch loading support for AMD processors will be enabled. @@ -1816,17 +1836,6 @@ config ARCH_RANDOM If supported, this is a high bandwidth, cryptographically secure hardware random number generator. -config X86_SMAP - def_bool y - prompt "Supervisor Mode Access Prevention" if EXPERT - help - Supervisor Mode Access Prevention (SMAP) is a security - feature in newer Intel processors. There is a small - performance cost if this enabled and turned on; there is - also a small increase in the kernel size if this is enabled. - - If unsure, say Y. - config X86_UMIP def_bool y prompt "User Mode Instruction Prevention" if EXPERT @@ -1855,9 +1864,10 @@ config CC_HAS_IBT config X86_KERNEL_IBT prompt "Indirect Branch Tracking" bool - depends on X86_64 && CC_HAS_IBT && STACK_VALIDATION + depends on X86_64 && CC_HAS_IBT && HAVE_OBJTOOL # https://github.com/llvm/llvm-project/commit/9d7001eba9c4cb311e03cd8cdc231f9e579f2d0f depends on !LD_IS_LLD || LLD_VERSION >= 140000 + select OBJTOOL help Build the kernel with support for Indirect Branch Tracking, a hardware support course-grain forward-edge Control Flow Integrity @@ -1866,7 +1876,7 @@ config X86_KERNEL_IBT code with them to make this happen. In addition to building the kernel with IBT, seal all functions that - are not indirect call targets, avoiding them ever becomming one. + are not indirect call targets, avoiding them ever becoming one. This requires LTO like objtool runs and will slow down the build. It does significantly reduce the number of ENDBR instructions in the @@ -2326,7 +2336,9 @@ choice it can be used to assist security vulnerability exploitation. This setting can be changed at boot time via the kernel command - line parameter vsyscall=[emulate|xonly|none]. + line parameter vsyscall=[emulate|xonly|none]. Emulate mode + is deprecated and can only be enabled using the kernel command + line. On a system with recent enough glibc (2.14 or newer) and no static binaries, you can say None without a performance penalty @@ -2334,20 +2346,6 @@ choice If unsure, select "Emulate execution only". - config LEGACY_VSYSCALL_EMULATE - bool "Full emulation" - help - The kernel traps and emulates calls into the fixed vsyscall - address mapping. This makes the mapping non-executable, but - it still contains readable known contents, which could be - used in certain rare security vulnerability exploits. This - configuration is recommended when using legacy userspace - that still uses vsyscalls along with legacy binary - instrumentation tools that require code to be readable. - - An example of this type of legacy userspace is running - Pin on an old binary that still uses vsyscalls. - config LEGACY_VSYSCALL_XONLY bool "Emulate execution only" help @@ -2838,13 +2836,6 @@ config IA32_EMULATION 64-bit kernel. You should likely turn this on, unless you're 100% sure that you don't have any 32-bit programs left. -config IA32_AOUT - tristate "IA32 a.out support" - depends on IA32_EMULATION - depends on BROKEN - help - Support old a.out binaries in the 32bit emulation. - config X86_X32_ABI bool "x32 ABI for 64-bit mode" depends on X86_64 diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index d3a6f74a94bd..d872a7522e55 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -237,7 +237,7 @@ choice config UNWINDER_ORC bool "ORC unwinder" depends on X86_64 - select STACK_VALIDATION + select OBJTOOL help This option enables the ORC (Oops Rewind Capability) unwinder for unwinding kernel stack traces. It uses a custom data format which is diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 63d50f65b828..1abd7cc9d6cd 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -313,5 +313,6 @@ define archhelp echo '' echo ' kvm_guest.config - Enable Kconfig items for running this kernel as a KVM guest' echo ' xen.config - Enable Kconfig items for running this kernel as a Xen guest' + echo ' x86_debug.config - Enable tip tree debugging options for testing' endef diff --git a/arch/x86/boot/boot.h b/arch/x86/boot/boot.h index 34c9dbb6a47d..148ba5c5106e 100644 --- a/arch/x86/boot/boot.h +++ b/arch/x86/boot/boot.h @@ -26,6 +26,7 @@ #include "bitops.h" #include "ctype.h" #include "cpuflags.h" +#include "io.h" /* Useful macros */ #define ARRAY_SIZE(x) (sizeof(x) / sizeof(*(x))) @@ -35,44 +36,10 @@ extern struct boot_params boot_params; #define cpu_relax() asm volatile("rep; nop") -/* Basic port I/O */ -static inline void outb(u8 v, u16 port) -{ - asm volatile("outb %0,%1" : : "a" (v), "dN" (port)); -} -static inline u8 inb(u16 port) -{ - u8 v; - asm volatile("inb %1,%0" : "=a" (v) : "dN" (port)); - return v; -} - -static inline void outw(u16 v, u16 port) -{ - asm volatile("outw %0,%1" : : "a" (v), "dN" (port)); -} -static inline u16 inw(u16 port) -{ - u16 v; - asm volatile("inw %1,%0" : "=a" (v) : "dN" (port)); - return v; -} - -static inline void outl(u32 v, u16 port) -{ - asm volatile("outl %0,%1" : : "a" (v), "dN" (port)); -} -static inline u32 inl(u16 port) -{ - u32 v; - asm volatile("inl %1,%0" : "=a" (v) : "dN" (port)); - return v; -} - static inline void io_delay(void) { const u16 DELAY_PORT = 0x80; - asm volatile("outb %%al,%0" : : "dN" (DELAY_PORT)); + outb(0, DELAY_PORT); } /* These functions are used to reference data in other segments. */ @@ -110,66 +77,78 @@ typedef unsigned int addr_t; static inline u8 rdfs8(addr_t addr) { + u8 *ptr = (u8 *)absolute_pointer(addr); u8 v; - asm volatile("movb %%fs:%1,%0" : "=q" (v) : "m" (*(u8 *)addr)); + asm volatile("movb %%fs:%1,%0" : "=q" (v) : "m" (*ptr)); return v; } static inline u16 rdfs16(addr_t addr) { + u16 *ptr = (u16 *)absolute_pointer(addr); u16 v; - asm volatile("movw %%fs:%1,%0" : "=r" (v) : "m" (*(u16 *)addr)); + asm volatile("movw %%fs:%1,%0" : "=r" (v) : "m" (*ptr)); return v; } static inline u32 rdfs32(addr_t addr) { + u32 *ptr = (u32 *)absolute_pointer(addr); u32 v; - asm volatile("movl %%fs:%1,%0" : "=r" (v) : "m" (*(u32 *)addr)); + asm volatile("movl %%fs:%1,%0" : "=r" (v) : "m" (*ptr)); return v; } static inline void wrfs8(u8 v, addr_t addr) { - asm volatile("movb %1,%%fs:%0" : "+m" (*(u8 *)addr) : "qi" (v)); + u8 *ptr = (u8 *)absolute_pointer(addr); + asm volatile("movb %1,%%fs:%0" : "+m" (*ptr) : "qi" (v)); } static inline void wrfs16(u16 v, addr_t addr) { - asm volatile("movw %1,%%fs:%0" : "+m" (*(u16 *)addr) : "ri" (v)); + u16 *ptr = (u16 *)absolute_pointer(addr); + asm volatile("movw %1,%%fs:%0" : "+m" (*ptr) : "ri" (v)); } static inline void wrfs32(u32 v, addr_t addr) { - asm volatile("movl %1,%%fs:%0" : "+m" (*(u32 *)addr) : "ri" (v)); + u32 *ptr = (u32 *)absolute_pointer(addr); + asm volatile("movl %1,%%fs:%0" : "+m" (*ptr) : "ri" (v)); } static inline u8 rdgs8(addr_t addr) { + u8 *ptr = (u8 *)absolute_pointer(addr); u8 v; - asm volatile("movb %%gs:%1,%0" : "=q" (v) : "m" (*(u8 *)addr)); + asm volatile("movb %%gs:%1,%0" : "=q" (v) : "m" (*ptr)); return v; } static inline u16 rdgs16(addr_t addr) { + u16 *ptr = (u16 *)absolute_pointer(addr); u16 v; - asm volatile("movw %%gs:%1,%0" : "=r" (v) : "m" (*(u16 *)addr)); + asm volatile("movw %%gs:%1,%0" : "=r" (v) : "m" (*ptr)); return v; } static inline u32 rdgs32(addr_t addr) { + u32 *ptr = (u32 *)absolute_pointer(addr); u32 v; - asm volatile("movl %%gs:%1,%0" : "=r" (v) : "m" (*(u32 *)addr)); + asm volatile("movl %%gs:%1,%0" : "=r" (v) : "m" (*ptr)); return v; } static inline void wrgs8(u8 v, addr_t addr) { - asm volatile("movb %1,%%gs:%0" : "+m" (*(u8 *)addr) : "qi" (v)); + u8 *ptr = (u8 *)absolute_pointer(addr); + asm volatile("movb %1,%%gs:%0" : "+m" (*ptr) : "qi" (v)); } static inline void wrgs16(u16 v, addr_t addr) { - asm volatile("movw %1,%%gs:%0" : "+m" (*(u16 *)addr) : "ri" (v)); + u16 *ptr = (u16 *)absolute_pointer(addr); + asm volatile("movw %1,%%gs:%0" : "+m" (*ptr) : "ri" (v)); } static inline void wrgs32(u32 v, addr_t addr) { - asm volatile("movl %1,%%gs:%0" : "+m" (*(u32 *)addr) : "ri" (v)); + u32 *ptr = (u32 *)absolute_pointer(addr); + asm volatile("movl %1,%%gs:%0" : "+m" (*ptr) : "ri" (v)); } /* Note: these only return true/false, not a signed return value! */ diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index 6115274fe10f..19e1905dcbf6 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -101,8 +101,10 @@ ifdef CONFIG_X86_64 endif vmlinux-objs-$(CONFIG_ACPI) += $(obj)/acpi.o +vmlinux-objs-$(CONFIG_INTEL_TDX_GUEST) += $(obj)/tdx.o $(obj)/tdcall.o vmlinux-objs-$(CONFIG_EFI_MIXED) += $(obj)/efi_thunk_$(BITS).o +vmlinux-objs-$(CONFIG_EFI) += $(obj)/efi.o efi-obj-$(CONFIG_EFI_STUB) = $(objtree)/drivers/firmware/efi/libstub/lib.a $(obj)/vmlinux: $(vmlinux-objs-y) $(efi-obj-y) FORCE diff --git a/arch/x86/boot/compressed/acpi.c b/arch/x86/boot/compressed/acpi.c index 8bcbcee54aa1..9caf89063e77 100644 --- a/arch/x86/boot/compressed/acpi.c +++ b/arch/x86/boot/compressed/acpi.c @@ -3,10 +3,9 @@ #include "misc.h" #include "error.h" #include "../string.h" +#include "efi.h" #include <linux/numa.h> -#include <linux/efi.h> -#include <asm/efi.h> /* * Longest parameter of 'acpi=' is 'copy_dsdt', plus an extra '\0' @@ -20,153 +19,56 @@ */ struct mem_vector immovable_mem[MAX_NUMNODES*2]; -/* - * Search EFI system tables for RSDP. If both ACPI_20_TABLE_GUID and - * ACPI_TABLE_GUID are found, take the former, which has more features. - */ static acpi_physical_address -__efi_get_rsdp_addr(unsigned long config_tables, unsigned int nr_tables, - bool efi_64) +__efi_get_rsdp_addr(unsigned long cfg_tbl_pa, unsigned int cfg_tbl_len) { - acpi_physical_address rsdp_addr = 0; - #ifdef CONFIG_EFI - int i; - - /* Get EFI tables from systab. */ - for (i = 0; i < nr_tables; i++) { - acpi_physical_address table; - efi_guid_t guid; - - if (efi_64) { - efi_config_table_64_t *tbl = (efi_config_table_64_t *)config_tables + i; - - guid = tbl->guid; - table = tbl->table; - - if (!IS_ENABLED(CONFIG_X86_64) && table >> 32) { - debug_putstr("Error getting RSDP address: EFI config table located above 4GB.\n"); - return 0; - } - } else { - efi_config_table_32_t *tbl = (efi_config_table_32_t *)config_tables + i; - - guid = tbl->guid; - table = tbl->table; - } + unsigned long rsdp_addr; + int ret; - if (!(efi_guidcmp(guid, ACPI_TABLE_GUID))) - rsdp_addr = table; - else if (!(efi_guidcmp(guid, ACPI_20_TABLE_GUID))) - return table; - } + /* + * Search EFI system tables for RSDP. Preferred is ACPI_20_TABLE_GUID to + * ACPI_TABLE_GUID because it has more features. + */ + rsdp_addr = efi_find_vendor_table(boot_params, cfg_tbl_pa, cfg_tbl_len, + ACPI_20_TABLE_GUID); + if (rsdp_addr) + return (acpi_physical_address)rsdp_addr; + + /* No ACPI_20_TABLE_GUID found, fallback to ACPI_TABLE_GUID. */ + rsdp_addr = efi_find_vendor_table(boot_params, cfg_tbl_pa, cfg_tbl_len, + ACPI_TABLE_GUID); + if (rsdp_addr) + return (acpi_physical_address)rsdp_addr; + + debug_putstr("Error getting RSDP address.\n"); #endif - return rsdp_addr; -} - -/* EFI/kexec support is 64-bit only. */ -#ifdef CONFIG_X86_64 -static struct efi_setup_data *get_kexec_setup_data_addr(void) -{ - struct setup_data *data; - u64 pa_data; - - pa_data = boot_params->hdr.setup_data; - while (pa_data) { - data = (struct setup_data *)pa_data; - if (data->type == SETUP_EFI) - return (struct efi_setup_data *)(pa_data + sizeof(struct setup_data)); - - pa_data = data->next; - } - return NULL; -} - -static acpi_physical_address kexec_get_rsdp_addr(void) -{ - efi_system_table_64_t *systab; - struct efi_setup_data *esd; - struct efi_info *ei; - char *sig; - - esd = (struct efi_setup_data *)get_kexec_setup_data_addr(); - if (!esd) - return 0; - - if (!esd->tables) { - debug_putstr("Wrong kexec SETUP_EFI data.\n"); - return 0; - } - - ei = &boot_params->efi_info; - sig = (char *)&ei->efi_loader_signature; - if (strncmp(sig, EFI64_LOADER_SIGNATURE, 4)) { - debug_putstr("Wrong kexec EFI loader signature.\n"); - return 0; - } - - /* Get systab from boot params. */ - systab = (efi_system_table_64_t *) (ei->efi_systab | ((__u64)ei->efi_systab_hi << 32)); - if (!systab) - error("EFI system table not found in kexec boot_params."); - - return __efi_get_rsdp_addr((unsigned long)esd->tables, systab->nr_tables, true); + return 0; } -#else -static acpi_physical_address kexec_get_rsdp_addr(void) { return 0; } -#endif /* CONFIG_X86_64 */ static acpi_physical_address efi_get_rsdp_addr(void) { #ifdef CONFIG_EFI - unsigned long systab, config_tables; + unsigned long cfg_tbl_pa = 0; + unsigned int cfg_tbl_len; + unsigned long systab_pa; unsigned int nr_tables; - struct efi_info *ei; - bool efi_64; - char *sig; - - ei = &boot_params->efi_info; - sig = (char *)&ei->efi_loader_signature; - - if (!strncmp(sig, EFI64_LOADER_SIGNATURE, 4)) { - efi_64 = true; - } else if (!strncmp(sig, EFI32_LOADER_SIGNATURE, 4)) { - efi_64 = false; - } else { - debug_putstr("Wrong EFI loader signature.\n"); - return 0; - } + enum efi_type et; + int ret; - /* Get systab from boot params. */ -#ifdef CONFIG_X86_64 - systab = ei->efi_systab | ((__u64)ei->efi_systab_hi << 32); -#else - if (ei->efi_systab_hi || ei->efi_memmap_hi) { - debug_putstr("Error getting RSDP address: EFI system table located above 4GB.\n"); + et = efi_get_type(boot_params); + if (et == EFI_TYPE_NONE) return 0; - } - systab = ei->efi_systab; -#endif - if (!systab) - error("EFI system table not found."); - /* Handle EFI bitness properly */ - if (efi_64) { - efi_system_table_64_t *stbl = (efi_system_table_64_t *)systab; + systab_pa = efi_get_system_table(boot_params); + if (!systab_pa) + error("EFI support advertised, but unable to locate system table."); - config_tables = stbl->tables; - nr_tables = stbl->nr_tables; - } else { - efi_system_table_32_t *stbl = (efi_system_table_32_t *)systab; + ret = efi_get_conf_table(boot_params, &cfg_tbl_pa, &cfg_tbl_len); + if (ret || !cfg_tbl_pa) + error("EFI config table not found."); - config_tables = stbl->tables; - nr_tables = stbl->nr_tables; - } - - if (!config_tables) - error("EFI config tables not found."); - - return __efi_get_rsdp_addr(config_tables, nr_tables, efi_64); + return __efi_get_rsdp_addr(cfg_tbl_pa, cfg_tbl_len); #else return 0; #endif @@ -256,14 +158,6 @@ acpi_physical_address get_rsdp_addr(void) pa = boot_params->acpi_rsdp_addr; - /* - * Try to get EFI data from setup_data. This can happen when we're a - * kexec'ed kernel and kexec(1) has passed all the required EFI info to - * us. - */ - if (!pa) - pa = kexec_get_rsdp_addr(); - if (!pa) pa = efi_get_rsdp_addr(); diff --git a/arch/x86/boot/compressed/early_serial_console.c b/arch/x86/boot/compressed/early_serial_console.c index 261e81fb9582..70a8d1706d0f 100644 --- a/arch/x86/boot/compressed/early_serial_console.c +++ b/arch/x86/boot/compressed/early_serial_console.c @@ -1,5 +1,6 @@ #include "misc.h" -int early_serial_base; +/* This might be accessed before .bss is cleared, so use .data instead. */ +int early_serial_base __section(".data"); #include "../early_serial_console.c" diff --git a/arch/x86/boot/compressed/efi.c b/arch/x86/boot/compressed/efi.c new file mode 100644 index 000000000000..6edd034b0b30 --- /dev/null +++ b/arch/x86/boot/compressed/efi.c @@ -0,0 +1,234 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Helpers for early access to EFI configuration table. + * + * Originally derived from arch/x86/boot/compressed/acpi.c + */ + +#include "misc.h" + +/** + * efi_get_type - Given a pointer to boot_params, determine the type of EFI environment. + * + * @bp: pointer to boot_params + * + * Return: EFI_TYPE_{32,64} for valid EFI environments, EFI_TYPE_NONE otherwise. + */ +enum efi_type efi_get_type(struct boot_params *bp) +{ + struct efi_info *ei; + enum efi_type et; + const char *sig; + + ei = &bp->efi_info; + sig = (char *)&ei->efi_loader_signature; + + if (!strncmp(sig, EFI64_LOADER_SIGNATURE, 4)) { + et = EFI_TYPE_64; + } else if (!strncmp(sig, EFI32_LOADER_SIGNATURE, 4)) { + et = EFI_TYPE_32; + } else { + debug_putstr("No EFI environment detected.\n"); + et = EFI_TYPE_NONE; + } + +#ifndef CONFIG_X86_64 + /* + * Existing callers like acpi.c treat this case as an indicator to + * fall-through to non-EFI, rather than an error, so maintain that + * functionality here as well. + */ + if (ei->efi_systab_hi || ei->efi_memmap_hi) { + debug_putstr("EFI system table is located above 4GB and cannot be accessed.\n"); + et = EFI_TYPE_NONE; + } +#endif + + return et; +} + +/** + * efi_get_system_table - Given a pointer to boot_params, retrieve the physical address + * of the EFI system table. + * + * @bp: pointer to boot_params + * + * Return: EFI system table address on success. On error, return 0. + */ +unsigned long efi_get_system_table(struct boot_params *bp) +{ + unsigned long sys_tbl_pa; + struct efi_info *ei; + enum efi_type et; + + /* Get systab from boot params. */ + ei = &bp->efi_info; +#ifdef CONFIG_X86_64 + sys_tbl_pa = ei->efi_systab | ((__u64)ei->efi_systab_hi << 32); +#else + sys_tbl_pa = ei->efi_systab; +#endif + if (!sys_tbl_pa) { + debug_putstr("EFI system table not found."); + return 0; + } + + return sys_tbl_pa; +} + +/* + * EFI config table address changes to virtual address after boot, which may + * not be accessible for the kexec'd kernel. To address this, kexec provides + * the initial physical address via a struct setup_data entry, which is + * checked for here, along with some sanity checks. + */ +static struct efi_setup_data *get_kexec_setup_data(struct boot_params *bp, + enum efi_type et) +{ +#ifdef CONFIG_X86_64 + struct efi_setup_data *esd = NULL; + struct setup_data *data; + u64 pa_data; + + pa_data = bp->hdr.setup_data; + while (pa_data) { + data = (struct setup_data *)pa_data; + if (data->type == SETUP_EFI) { + esd = (struct efi_setup_data *)(pa_data + sizeof(struct setup_data)); + break; + } + + pa_data = data->next; + } + + /* + * Original ACPI code falls back to attempting normal EFI boot in these + * cases, so maintain existing behavior by indicating non-kexec + * environment to the caller, but print them for debugging. + */ + if (esd && !esd->tables) { + debug_putstr("kexec EFI environment missing valid configuration table.\n"); + return NULL; + } + + return esd; +#endif + return NULL; +} + +/** + * efi_get_conf_table - Given a pointer to boot_params, locate and return the physical + * address of EFI configuration table. + * + * @bp: pointer to boot_params + * @cfg_tbl_pa: location to store physical address of config table + * @cfg_tbl_len: location to store number of config table entries + * + * Return: 0 on success. On error, return params are left unchanged. + */ +int efi_get_conf_table(struct boot_params *bp, unsigned long *cfg_tbl_pa, + unsigned int *cfg_tbl_len) +{ + unsigned long sys_tbl_pa; + enum efi_type et; + int ret; + + if (!cfg_tbl_pa || !cfg_tbl_len) + return -EINVAL; + + sys_tbl_pa = efi_get_system_table(bp); + if (!sys_tbl_pa) + return -EINVAL; + + /* Handle EFI bitness properly */ + et = efi_get_type(bp); + if (et == EFI_TYPE_64) { + efi_system_table_64_t *stbl = (efi_system_table_64_t *)sys_tbl_pa; + struct efi_setup_data *esd; + + /* kexec provides an alternative EFI conf table, check for it. */ + esd = get_kexec_setup_data(bp, et); + + *cfg_tbl_pa = esd ? esd->tables : stbl->tables; + *cfg_tbl_len = stbl->nr_tables; + } else if (et == EFI_TYPE_32) { + efi_system_table_32_t *stbl = (efi_system_table_32_t *)sys_tbl_pa; + + *cfg_tbl_pa = stbl->tables; + *cfg_tbl_len = stbl->nr_tables; + } else { + return -EINVAL; + } + + return 0; +} + +/* Get vendor table address/guid from EFI config table at the given index */ +static int get_vendor_table(void *cfg_tbl, unsigned int idx, + unsigned long *vendor_tbl_pa, + efi_guid_t *vendor_tbl_guid, + enum efi_type et) +{ + if (et == EFI_TYPE_64) { + efi_config_table_64_t *tbl_entry = (efi_config_table_64_t *)cfg_tbl + idx; + + if (!IS_ENABLED(CONFIG_X86_64) && tbl_entry->table >> 32) { + debug_putstr("Error: EFI config table entry located above 4GB.\n"); + return -EINVAL; + } + + *vendor_tbl_pa = tbl_entry->table; + *vendor_tbl_guid = tbl_entry->guid; + + } else if (et == EFI_TYPE_32) { + efi_config_table_32_t *tbl_entry = (efi_config_table_32_t *)cfg_tbl + idx; + + *vendor_tbl_pa = tbl_entry->table; + *vendor_tbl_guid = tbl_entry->guid; + } else { + return -EINVAL; + } + + return 0; +} + +/** + * efi_find_vendor_table - Given EFI config table, search it for the physical + * address of the vendor table associated with GUID. + * + * @bp: pointer to boot_params + * @cfg_tbl_pa: pointer to EFI configuration table + * @cfg_tbl_len: number of entries in EFI configuration table + * @guid: GUID of vendor table + * + * Return: vendor table address on success. On error, return 0. + */ +unsigned long efi_find_vendor_table(struct boot_params *bp, + unsigned long cfg_tbl_pa, + unsigned int cfg_tbl_len, + efi_guid_t guid) +{ + enum efi_type et; + unsigned int i; + + et = efi_get_type(bp); + if (et == EFI_TYPE_NONE) + return 0; + + for (i = 0; i < cfg_tbl_len; i++) { + unsigned long vendor_tbl_pa; + efi_guid_t vendor_tbl_guid; + int ret; + + ret = get_vendor_table((void *)cfg_tbl_pa, i, + &vendor_tbl_pa, + &vendor_tbl_guid, et); + if (ret) + return 0; + + if (!efi_guidcmp(guid, vendor_tbl_guid)) + return vendor_tbl_pa; + } + + return 0; +} diff --git a/arch/x86/boot/compressed/efi.h b/arch/x86/boot/compressed/efi.h new file mode 100644 index 000000000000..7db2f41b54cd --- /dev/null +++ b/arch/x86/boot/compressed/efi.h @@ -0,0 +1,126 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef BOOT_COMPRESSED_EFI_H +#define BOOT_COMPRESSED_EFI_H + +#if defined(_LINUX_EFI_H) || defined(_ASM_X86_EFI_H) +#error Please do not include kernel proper namespace headers +#endif + +typedef guid_t efi_guid_t __aligned(__alignof__(u32)); + +#define EFI_GUID(a, b, c, d...) (efi_guid_t){ { \ + (a) & 0xff, ((a) >> 8) & 0xff, ((a) >> 16) & 0xff, ((a) >> 24) & 0xff, \ + (b) & 0xff, ((b) >> 8) & 0xff, \ + (c) & 0xff, ((c) >> 8) & 0xff, d } } + +#define ACPI_TABLE_GUID EFI_GUID(0xeb9d2d30, 0x2d88, 0x11d3, 0x9a, 0x16, 0x00, 0x90, 0x27, 0x3f, 0xc1, 0x4d) +#define ACPI_20_TABLE_GUID EFI_GUID(0x8868e871, 0xe4f1, 0x11d3, 0xbc, 0x22, 0x00, 0x80, 0xc7, 0x3c, 0x88, 0x81) +#define EFI_CC_BLOB_GUID EFI_GUID(0x067b1f5f, 0xcf26, 0x44c5, 0x85, 0x54, 0x93, 0xd7, 0x77, 0x91, 0x2d, 0x42) + +#define EFI32_LOADER_SIGNATURE "EL32" +#define EFI64_LOADER_SIGNATURE "EL64" + +/* + * Generic EFI table header + */ +typedef struct { + u64 signature; + u32 revision; + u32 headersize; + u32 crc32; + u32 reserved; +} efi_table_hdr_t; + +#define EFI_CONVENTIONAL_MEMORY 7 + +#define EFI_MEMORY_MORE_RELIABLE \ + ((u64)0x0000000000010000ULL) /* higher reliability */ +#define EFI_MEMORY_SP ((u64)0x0000000000040000ULL) /* soft reserved */ + +#define EFI_PAGE_SHIFT 12 + +typedef struct { + u32 type; + u32 pad; + u64 phys_addr; + u64 virt_addr; + u64 num_pages; + u64 attribute; +} efi_memory_desc_t; + +#define efi_early_memdesc_ptr(map, desc_size, n) \ + (efi_memory_desc_t *)((void *)(map) + ((n) * (desc_size))) + +typedef struct { + efi_guid_t guid; + u64 table; +} efi_config_table_64_t; + +typedef struct { + efi_guid_t guid; + u32 table; +} efi_config_table_32_t; + +typedef struct { + efi_table_hdr_t hdr; + u64 fw_vendor; /* physical addr of CHAR16 vendor string */ + u32 fw_revision; + u32 __pad1; + u64 con_in_handle; + u64 con_in; + u64 con_out_handle; + u64 con_out; + u64 stderr_handle; + u64 stderr; + u64 runtime; + u64 boottime; + u32 nr_tables; + u32 __pad2; + u64 tables; +} efi_system_table_64_t; + +typedef struct { + efi_table_hdr_t hdr; + u32 fw_vendor; /* physical addr of CHAR16 vendor string */ + u32 fw_revision; + u32 con_in_handle; + u32 con_in; + u32 con_out_handle; + u32 con_out; + u32 stderr_handle; + u32 stderr; + u32 runtime; + u32 boottime; + u32 nr_tables; + u32 tables; +} efi_system_table_32_t; + +/* kexec external ABI */ +struct efi_setup_data { + u64 fw_vendor; + u64 __unused; + u64 tables; + u64 smbios; + u64 reserved[8]; +}; + +static inline int efi_guidcmp (efi_guid_t left, efi_guid_t right) +{ + return memcmp(&left, &right, sizeof (efi_guid_t)); +} + +#ifdef CONFIG_EFI +bool __pure __efi_soft_reserve_enabled(void); + +static inline bool __pure efi_soft_reserve_enabled(void) +{ + return IS_ENABLED(CONFIG_EFI_SOFT_RESERVE) + && __efi_soft_reserve_enabled(); +} +#else +static inline bool efi_soft_reserve_enabled(void) +{ + return false; +} +#endif /* CONFIG_EFI */ +#endif /* BOOT_COMPRESSED_EFI_H */ diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index dea95301196b..d33f060900d2 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -189,11 +189,11 @@ SYM_FUNC_START(startup_32) subl $32, %eax /* Encryption bit is always above bit 31 */ bts %eax, %edx /* Set encryption mask for page tables */ /* - * Mark SEV as active in sev_status so that startup32_check_sev_cbit() - * will do a check. The sev_status memory will be fully initialized - * with the contents of MSR_AMD_SEV_STATUS later in - * set_sev_encryption_mask(). For now it is sufficient to know that SEV - * is active. + * Set MSR_AMD64_SEV_ENABLED_BIT in sev_status so that + * startup32_check_sev_cbit() will do a check. sev_enable() will + * initialize sev_status with all the bits reported by + * MSR_AMD_SEV_STATUS later, but only MSR_AMD64_SEV_ENABLED_BIT + * needs to be set for now. */ movl $1, rva(sev_status)(%ebp) 1: @@ -289,7 +289,7 @@ SYM_FUNC_START(startup_32) pushl %eax /* Enter paged protected Mode, activating Long Mode */ - movl $(X86_CR0_PG | X86_CR0_PE), %eax /* Enable Paging and Protected mode */ + movl $CR0_STATE, %eax movl %eax, %cr0 /* Jump from 32bit compatibility mode into 64bit mode. */ @@ -447,6 +447,23 @@ SYM_CODE_START(startup_64) call load_stage1_idt popq %rsi +#ifdef CONFIG_AMD_MEM_ENCRYPT + /* + * Now that the stage1 interrupt handlers are set up, #VC exceptions from + * CPUID instructions can be properly handled for SEV-ES guests. + * + * For SEV-SNP, the CPUID table also needs to be set up in advance of any + * CPUID instructions being issued, so go ahead and do that now via + * sev_enable(), which will also handle the rest of the SEV-related + * detection/setup to ensure that has been done in advance of any dependent + * code. + */ + pushq %rsi + movq %rsi, %rdi /* real mode address */ + call sev_enable + popq %rsi +#endif + /* * paging_prepare() sets up the trampoline and checks if we need to * enable 5-level paging. @@ -558,17 +575,7 @@ SYM_FUNC_START_LOCAL_NOALIGN(.Lrelocated) shrq $3, %rcx rep stosq -/* - * If running as an SEV guest, the encryption mask is required in the - * page-table setup code below. When the guest also has SEV-ES enabled - * set_sev_encryption_mask() will cause #VC exceptions, but the stage2 - * handler can't map its GHCB because the page-table is not set up yet. - * So set up the encryption mask here while still on the stage1 #VC - * handler. Then load stage2 IDT and switch to the kernel's own - * page-table. - */ pushq %rsi - call set_sev_encryption_mask call load_stage2_idt /* Pass boot_params to initialize_identity_maps() */ @@ -642,12 +649,28 @@ SYM_CODE_START(trampoline_32bit_src) movl $MSR_EFER, %ecx rdmsr btsl $_EFER_LME, %eax + /* Avoid writing EFER if no change was made (for TDX guest) */ + jc 1f wrmsr - popl %edx +1: popl %edx popl %ecx +#ifdef CONFIG_X86_MCE + /* + * Preserve CR4.MCE if the kernel will enable #MC support. + * Clearing MCE may fault in some environments (that also force #MC + * support). Any machine check that occurs before #MC support is fully + * configured will crash the system regardless of the CR4.MCE value set + * here. + */ + movl %cr4, %eax + andl $X86_CR4_MCE, %eax +#else + movl $0, %eax +#endif + /* Enable PAE and LA57 (if required) paging modes */ - movl $X86_CR4_PAE, %eax + orl $X86_CR4_PAE, %eax testl %edx, %edx jz 1f orl $X86_CR4_LA57, %eax @@ -661,8 +684,9 @@ SYM_CODE_START(trampoline_32bit_src) pushl $__KERNEL_CS pushl %eax - /* Enable paging again */ - movl $(X86_CR0_PG | X86_CR0_PE), %eax + /* Enable paging again. */ + movl %cr0, %eax + btsl $X86_CR0_PG_BIT, %eax movl %eax, %cr0 lret diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c index f7213d0943b8..44c350d627c7 100644 --- a/arch/x86/boot/compressed/ident_map_64.c +++ b/arch/x86/boot/compressed/ident_map_64.c @@ -90,7 +90,7 @@ static struct x86_mapping_info mapping_info; /* * Adds the specified range to the identity mappings. */ -static void add_identity_map(unsigned long start, unsigned long end) +void kernel_add_identity_map(unsigned long start, unsigned long end) { int ret; @@ -157,14 +157,15 @@ void initialize_identity_maps(void *rmode) * explicitly here in case the compressed kernel does not touch them, * or does not touch all the pages covering them. */ - add_identity_map((unsigned long)_head, (unsigned long)_end); + kernel_add_identity_map((unsigned long)_head, (unsigned long)_end); boot_params = rmode; - add_identity_map((unsigned long)boot_params, (unsigned long)(boot_params + 1)); + kernel_add_identity_map((unsigned long)boot_params, (unsigned long)(boot_params + 1)); cmdline = get_cmd_line_ptr(); - add_identity_map(cmdline, cmdline + COMMAND_LINE_SIZE); + kernel_add_identity_map(cmdline, cmdline + COMMAND_LINE_SIZE); + + sev_prep_identity_maps(top_level_pgt); /* Load the new page-table. */ - sev_verify_cbit(top_level_pgt); write_cr3(top_level_pgt); } @@ -246,10 +247,10 @@ static int set_clr_page_flags(struct x86_mapping_info *info, * It should already exist, but keep things generic. * * To map the page just read from it and fault it in if there is no - * mapping yet. add_identity_map() can't be called here because that - * would unconditionally map the address on PMD level, destroying any - * PTE-level mappings that might already exist. Use assembly here so - * the access won't be optimized away. + * mapping yet. kernel_add_identity_map() can't be called here because + * that would unconditionally map the address on PMD level, destroying + * any PTE-level mappings that might already exist. Use assembly here + * so the access won't be optimized away. */ asm volatile("mov %[address], %%r9" :: [address] "g" (*(unsigned long *)address) @@ -275,15 +276,31 @@ static int set_clr_page_flags(struct x86_mapping_info *info, * Changing encryption attributes of a page requires to flush it from * the caches. */ - if ((set | clr) & _PAGE_ENC) + if ((set | clr) & _PAGE_ENC) { clflush_page(address); + /* + * If the encryption attribute is being cleared, change the page state + * to shared in the RMP table. + */ + if (clr) + snp_set_page_shared(__pa(address & PAGE_MASK)); + } + /* Update PTE */ pte = *ptep; pte = pte_set_flags(pte, set); pte = pte_clear_flags(pte, clr); set_pte(ptep, pte); + /* + * If the encryption attribute is being set, then change the page state to + * private in the RMP entry. The page state change must be done after the PTE + * is updated. + */ + if (set & _PAGE_ENC) + snp_set_page_private(__pa(address & PAGE_MASK)); + /* Flush TLB after changing encryption attribute */ write_cr3(top_level_pgt); @@ -347,5 +364,5 @@ void do_boot_page_fault(struct pt_regs *regs, unsigned long error_code) * Error code is sane - now identity map the 2M region around * the faulting address. */ - add_identity_map(address, end); + kernel_add_identity_map(address, end); } diff --git a/arch/x86/boot/compressed/idt_64.c b/arch/x86/boot/compressed/idt_64.c index 9b93567d663a..6debb816e83d 100644 --- a/arch/x86/boot/compressed/idt_64.c +++ b/arch/x86/boot/compressed/idt_64.c @@ -39,7 +39,23 @@ void load_stage1_idt(void) load_boot_idt(&boot_idt_desc); } -/* Setup IDT after kernel jumping to .Lrelocated */ +/* + * Setup IDT after kernel jumping to .Lrelocated. + * + * initialize_identity_maps() needs a #PF handler to be setup + * in order to be able to fault-in identity mapping ranges; see + * do_boot_page_fault(). + * + * This #PF handler setup needs to happen in load_stage2_idt() where the + * IDT is loaded and there the #VC IDT entry gets setup too. + * + * In order to be able to handle #VCs, one needs a GHCB which + * gets setup with an already set up pagetable, which is done in + * initialize_identity_maps(). And there's the catch 22: the boot #VC + * handler do_boot_stage2_vc() needs to call early_setup_ghcb() itself + * (and, especially set_page_decrypted()) because the SEV-ES setup code + * cannot initialize a GHCB as there's no #PF handler yet... + */ void load_stage2_idt(void) { boot_idt_desc.address = (unsigned long)boot_idt; diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c index 411b268bc0a2..4a3f223973f4 100644 --- a/arch/x86/boot/compressed/kaslr.c +++ b/arch/x86/boot/compressed/kaslr.c @@ -22,15 +22,14 @@ #include "misc.h" #include "error.h" #include "../string.h" +#include "efi.h" #include <generated/compile.h> #include <linux/module.h> #include <linux/uts.h> #include <linux/utsname.h> #include <linux/ctype.h> -#include <linux/efi.h> #include <generated/utsrelease.h> -#include <asm/efi.h> #define _SETUP #include <asm/setup.h> /* For COMMAND_LINE_SIZE */ diff --git a/arch/x86/boot/compressed/mem_encrypt.S b/arch/x86/boot/compressed/mem_encrypt.S index a63424d13627..a73e4d783cae 100644 --- a/arch/x86/boot/compressed/mem_encrypt.S +++ b/arch/x86/boot/compressed/mem_encrypt.S @@ -187,42 +187,6 @@ SYM_CODE_END(startup32_vc_handler) .code64 #include "../../kernel/sev_verify_cbit.S" -SYM_FUNC_START(set_sev_encryption_mask) -#ifdef CONFIG_AMD_MEM_ENCRYPT - push %rbp - push %rdx - - movq %rsp, %rbp /* Save current stack pointer */ - - call get_sev_encryption_bit /* Get the encryption bit position */ - testl %eax, %eax - jz .Lno_sev_mask - - bts %rax, sme_me_mask(%rip) /* Create the encryption mask */ - - /* - * Read MSR_AMD64_SEV again and store it to sev_status. Can't do this in - * get_sev_encryption_bit() because this function is 32-bit code and - * shared between 64-bit and 32-bit boot path. - */ - movl $MSR_AMD64_SEV, %ecx /* Read the SEV MSR */ - rdmsr - - /* Store MSR value in sev_status */ - shlq $32, %rdx - orq %rdx, %rax - movq %rax, sev_status(%rip) - -.Lno_sev_mask: - movq %rbp, %rsp /* Restore original stack pointer */ - - pop %rdx - pop %rbp -#endif - - xor %rax, %rax - RET -SYM_FUNC_END(set_sev_encryption_mask) .data diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index 1cdcaf34ee36..cf690d8712f4 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -48,12 +48,17 @@ void *memmove(void *dest, const void *src, size_t n); */ struct boot_params *boot_params; +struct port_io_ops pio_ops; + memptr free_mem_ptr; memptr free_mem_end_ptr; static char *vidmem; static int vidport; -static int lines, cols; + +/* These might be accessed before .bss is cleared, so use .data instead. */ +static int lines __section(".data"); +static int cols __section(".data"); #ifdef CONFIG_KERNEL_GZIP #include "../../../../lib/decompress_inflate.c" @@ -371,6 +376,16 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap, lines = boot_params->screen_info.orig_video_lines; cols = boot_params->screen_info.orig_video_cols; + init_default_io_ops(); + + /* + * Detect TDX guest environment. + * + * It has to be done before console_init() in order to use + * paravirtualized port I/O operations if needed. + */ + early_tdx_detect(); + console_init(); /* diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index 16ed360b6692..4910bf230d7b 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -22,17 +22,21 @@ #include <linux/linkage.h> #include <linux/screen_info.h> #include <linux/elf.h> -#include <linux/io.h> #include <asm/page.h> #include <asm/boot.h> #include <asm/bootparam.h> #include <asm/desc_defs.h> +#include "tdx.h" + #define BOOT_CTYPE_H #include <linux/acpi.h> #define BOOT_BOOT_H #include "../ctype.h" +#include "../io.h" + +#include "efi.h" #ifdef CONFIG_X86_64 #define memptr long @@ -120,17 +124,23 @@ static inline void console_init(void) { } #endif -void set_sev_encryption_mask(void); - #ifdef CONFIG_AMD_MEM_ENCRYPT +void sev_enable(struct boot_params *bp); void sev_es_shutdown_ghcb(void); extern bool sev_es_check_ghcb_fault(unsigned long address); +void snp_set_page_private(unsigned long paddr); +void snp_set_page_shared(unsigned long paddr); +void sev_prep_identity_maps(unsigned long top_level_pgt); #else +static inline void sev_enable(struct boot_params *bp) { } static inline void sev_es_shutdown_ghcb(void) { } static inline bool sev_es_check_ghcb_fault(unsigned long address) { return false; } +static inline void snp_set_page_private(unsigned long paddr) { } +static inline void snp_set_page_shared(unsigned long paddr) { } +static inline void sev_prep_identity_maps(unsigned long top_level_pgt) { } #endif /* acpi.c */ @@ -151,6 +161,7 @@ static inline int count_immovable_mem_regions(void) { return 0; } #ifdef CONFIG_X86_5LEVEL extern unsigned int __pgtable_l5_enabled, pgdir_shift, ptrs_per_p4d; #endif +extern void kernel_add_identity_map(unsigned long start, unsigned long end); /* Used by PAGE_KERN* macros: */ extern pteval_t __default_kernel_pte_mask; @@ -172,4 +183,47 @@ void boot_stage2_vc(void); unsigned long sev_verify_cbit(unsigned long cr3); +enum efi_type { + EFI_TYPE_64, + EFI_TYPE_32, + EFI_TYPE_NONE, +}; + +#ifdef CONFIG_EFI +/* helpers for early EFI config table access */ +enum efi_type efi_get_type(struct boot_params *bp); +unsigned long efi_get_system_table(struct boot_params *bp); +int efi_get_conf_table(struct boot_params *bp, unsigned long *cfg_tbl_pa, + unsigned int *cfg_tbl_len); +unsigned long efi_find_vendor_table(struct boot_params *bp, + unsigned long cfg_tbl_pa, + unsigned int cfg_tbl_len, + efi_guid_t guid); +#else +static inline enum efi_type efi_get_type(struct boot_params *bp) +{ + return EFI_TYPE_NONE; +} + +static inline unsigned long efi_get_system_table(struct boot_params *bp) +{ + return 0; +} + +static inline int efi_get_conf_table(struct boot_params *bp, + unsigned long *cfg_tbl_pa, + unsigned int *cfg_tbl_len) +{ + return -ENOENT; +} + +static inline unsigned long efi_find_vendor_table(struct boot_params *bp, + unsigned long cfg_tbl_pa, + unsigned int cfg_tbl_len, + efi_guid_t guid) +{ + return 0; +} +#endif /* CONFIG_EFI */ + #endif /* BOOT_COMPRESSED_MISC_H */ diff --git a/arch/x86/boot/compressed/pgtable.h b/arch/x86/boot/compressed/pgtable.h index 6ff7e81b5628..cc9b2529a086 100644 --- a/arch/x86/boot/compressed/pgtable.h +++ b/arch/x86/boot/compressed/pgtable.h @@ -6,7 +6,7 @@ #define TRAMPOLINE_32BIT_PGTABLE_OFFSET 0 #define TRAMPOLINE_32BIT_CODE_OFFSET PAGE_SIZE -#define TRAMPOLINE_32BIT_CODE_SIZE 0x70 +#define TRAMPOLINE_32BIT_CODE_SIZE 0x80 #define TRAMPOLINE_32BIT_STACK_END TRAMPOLINE_32BIT_SIZE diff --git a/arch/x86/boot/compressed/pgtable_64.c b/arch/x86/boot/compressed/pgtable_64.c index a1733319a22a..2ac12ff4111b 100644 --- a/arch/x86/boot/compressed/pgtable_64.c +++ b/arch/x86/boot/compressed/pgtable_64.c @@ -1,11 +1,10 @@ // SPDX-License-Identifier: GPL-2.0 #include "misc.h" -#include <linux/efi.h> #include <asm/e820/types.h> #include <asm/processor.h> -#include <asm/efi.h> #include "pgtable.h" #include "../string.h" +#include "efi.h" #define BIOS_START_MIN 0x20000U /* 128K, less than this is insane */ #define BIOS_START_MAX 0x9f000U /* 640K, absolute maximum */ diff --git a/arch/x86/boot/compressed/sev.c b/arch/x86/boot/compressed/sev.c index 28bcf04c022e..52f989f6acc2 100644 --- a/arch/x86/boot/compressed/sev.c +++ b/arch/x86/boot/compressed/sev.c @@ -20,8 +20,10 @@ #include <asm/fpu/xcr.h> #include <asm/ptrace.h> #include <asm/svm.h> +#include <asm/cpuid.h> #include "error.h" +#include "../msr.h" struct ghcb boot_ghcb_page __aligned(PAGE_SIZE); struct ghcb *boot_ghcb; @@ -56,23 +58,19 @@ static unsigned long insn_get_seg_base(struct pt_regs *regs, int seg_reg_idx) static inline u64 sev_es_rd_ghcb_msr(void) { - unsigned long low, high; + struct msr m; - asm volatile("rdmsr" : "=a" (low), "=d" (high) : - "c" (MSR_AMD64_SEV_ES_GHCB)); + boot_rdmsr(MSR_AMD64_SEV_ES_GHCB, &m); - return ((high << 32) | low); + return m.q; } static inline void sev_es_wr_ghcb_msr(u64 val) { - u32 low, high; + struct msr m; - low = val & 0xffffffffUL; - high = val >> 32; - - asm volatile("wrmsr" : : "c" (MSR_AMD64_SEV_ES_GHCB), - "a"(low), "d" (high) : "memory"); + m.q = val; + boot_wrmsr(MSR_AMD64_SEV_ES_GHCB, &m); } static enum es_result vc_decode_insn(struct es_em_ctxt *ctxt) @@ -119,11 +117,54 @@ static enum es_result vc_read_mem(struct es_em_ctxt *ctxt, /* Include code for early handlers */ #include "../../kernel/sev-shared.c" -static bool early_setup_sev_es(void) +static inline bool sev_snp_enabled(void) +{ + return sev_status & MSR_AMD64_SEV_SNP_ENABLED; +} + +static void __page_state_change(unsigned long paddr, enum psc_op op) +{ + u64 val; + + if (!sev_snp_enabled()) + return; + + /* + * If private -> shared then invalidate the page before requesting the + * state change in the RMP table. + */ + if (op == SNP_PAGE_STATE_SHARED && pvalidate(paddr, RMP_PG_SIZE_4K, 0)) + sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PVALIDATE); + + /* Issue VMGEXIT to change the page state in RMP table. */ + sev_es_wr_ghcb_msr(GHCB_MSR_PSC_REQ_GFN(paddr >> PAGE_SHIFT, op)); + VMGEXIT(); + + /* Read the response of the VMGEXIT. */ + val = sev_es_rd_ghcb_msr(); + if ((GHCB_RESP_CODE(val) != GHCB_MSR_PSC_RESP) || GHCB_MSR_PSC_RESP_VAL(val)) + sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PSC); + + /* + * Now that page state is changed in the RMP table, validate it so that it is + * consistent with the RMP entry. + */ + if (op == SNP_PAGE_STATE_PRIVATE && pvalidate(paddr, RMP_PG_SIZE_4K, 1)) + sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PVALIDATE); +} + +void snp_set_page_private(unsigned long paddr) +{ + __page_state_change(paddr, SNP_PAGE_STATE_PRIVATE); +} + +void snp_set_page_shared(unsigned long paddr) { - if (!sev_es_negotiate_protocol()) - sev_es_terminate(GHCB_SEV_ES_PROT_UNSUPPORTED); + __page_state_change(paddr, SNP_PAGE_STATE_SHARED); +} +static bool early_setup_ghcb(void) +{ if (set_page_decrypted((unsigned long)&boot_ghcb_page)) return false; @@ -135,6 +176,10 @@ static bool early_setup_sev_es(void) /* Initialize lookup tables for the instruction decoder */ inat_init_tables(); + /* SNP guest requires the GHCB GPA must be registered */ + if (sev_snp_enabled()) + snp_register_ghcb_early(__pa(&boot_ghcb_page)); + return true; } @@ -174,8 +219,8 @@ void do_boot_stage2_vc(struct pt_regs *regs, unsigned long exit_code) struct es_em_ctxt ctxt; enum es_result result; - if (!boot_ghcb && !early_setup_sev_es()) - sev_es_terminate(GHCB_SEV_ES_GEN_REQ); + if (!boot_ghcb && !early_setup_ghcb()) + sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ); vc_ghcb_invalidate(boot_ghcb); result = vc_init_em_ctxt(&ctxt, regs, exit_code); @@ -202,5 +247,191 @@ finish: if (result == ES_OK) vc_finish_insn(&ctxt); else if (result != ES_RETRY) - sev_es_terminate(GHCB_SEV_ES_GEN_REQ); + sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ); +} + +static void enforce_vmpl0(void) +{ + u64 attrs; + int err; + + /* + * RMPADJUST modifies RMP permissions of a lesser-privileged (numerically + * higher) privilege level. Here, clear the VMPL1 permission mask of the + * GHCB page. If the guest is not running at VMPL0, this will fail. + * + * If the guest is running at VMPL0, it will succeed. Even if that operation + * modifies permission bits, it is still ok to do so currently because Linux + * SNP guests are supported only on VMPL0 so VMPL1 or higher permission masks + * changing is a don't-care. + */ + attrs = 1; + if (rmpadjust((unsigned long)&boot_ghcb_page, RMP_PG_SIZE_4K, attrs)) + sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_NOT_VMPL0); +} + +void sev_enable(struct boot_params *bp) +{ + unsigned int eax, ebx, ecx, edx; + struct msr m; + bool snp; + + /* + * Setup/preliminary detection of SNP. This will be sanity-checked + * against CPUID/MSR values later. + */ + snp = snp_init(bp); + + /* Check for the SME/SEV support leaf */ + eax = 0x80000000; + ecx = 0; + native_cpuid(&eax, &ebx, &ecx, &edx); + if (eax < 0x8000001f) + return; + + /* + * Check for the SME/SEV feature: + * CPUID Fn8000_001F[EAX] + * - Bit 0 - Secure Memory Encryption support + * - Bit 1 - Secure Encrypted Virtualization support + * CPUID Fn8000_001F[EBX] + * - Bits 5:0 - Pagetable bit position used to indicate encryption + */ + eax = 0x8000001f; + ecx = 0; + native_cpuid(&eax, &ebx, &ecx, &edx); + /* Check whether SEV is supported */ + if (!(eax & BIT(1))) { + if (snp) + error("SEV-SNP support indicated by CC blob, but not CPUID."); + return; + } + + /* Set the SME mask if this is an SEV guest. */ + boot_rdmsr(MSR_AMD64_SEV, &m); + sev_status = m.q; + if (!(sev_status & MSR_AMD64_SEV_ENABLED)) + return; + + /* Negotiate the GHCB protocol version. */ + if (sev_status & MSR_AMD64_SEV_ES_ENABLED) { + if (!sev_es_negotiate_protocol()) + sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_PROT_UNSUPPORTED); + } + + /* + * SNP is supported in v2 of the GHCB spec which mandates support for HV + * features. + */ + if (sev_status & MSR_AMD64_SEV_SNP_ENABLED) { + if (!(get_hv_features() & GHCB_HV_FT_SNP)) + sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED); + + enforce_vmpl0(); + } + + if (snp && !(sev_status & MSR_AMD64_SEV_SNP_ENABLED)) + error("SEV-SNP supported indicated by CC blob, but not SEV status MSR."); + + sme_me_mask = BIT_ULL(ebx & 0x3f); +} + +/* Search for Confidential Computing blob in the EFI config table. */ +static struct cc_blob_sev_info *find_cc_blob_efi(struct boot_params *bp) +{ + unsigned long cfg_table_pa; + unsigned int cfg_table_len; + int ret; + + ret = efi_get_conf_table(bp, &cfg_table_pa, &cfg_table_len); + if (ret) + return NULL; + + return (struct cc_blob_sev_info *)efi_find_vendor_table(bp, cfg_table_pa, + cfg_table_len, + EFI_CC_BLOB_GUID); +} + +/* + * Initial set up of SNP relies on information provided by the + * Confidential Computing blob, which can be passed to the boot kernel + * by firmware/bootloader in the following ways: + * + * - via an entry in the EFI config table + * - via a setup_data structure, as defined by the Linux Boot Protocol + * + * Scan for the blob in that order. + */ +static struct cc_blob_sev_info *find_cc_blob(struct boot_params *bp) +{ + struct cc_blob_sev_info *cc_info; + + cc_info = find_cc_blob_efi(bp); + if (cc_info) + goto found_cc_info; + + cc_info = find_cc_blob_setup_data(bp); + if (!cc_info) + return NULL; + +found_cc_info: + if (cc_info->magic != CC_BLOB_SEV_HDR_MAGIC) + sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED); + + return cc_info; +} + +/* + * Indicate SNP based on presence of SNP-specific CC blob. Subsequent checks + * will verify the SNP CPUID/MSR bits. + */ +bool snp_init(struct boot_params *bp) +{ + struct cc_blob_sev_info *cc_info; + + if (!bp) + return false; + + cc_info = find_cc_blob(bp); + if (!cc_info) + return false; + + /* + * If a SNP-specific Confidential Computing blob is present, then + * firmware/bootloader have indicated SNP support. Verifying this + * involves CPUID checks which will be more reliable if the SNP + * CPUID table is used. See comments over snp_setup_cpuid_table() for + * more details. + */ + setup_cpuid_table(cc_info); + + /* + * Pass run-time kernel a pointer to CC info via boot_params so EFI + * config table doesn't need to be searched again during early startup + * phase. + */ + bp->cc_blob_address = (u32)(unsigned long)cc_info; + + return true; +} + +void sev_prep_identity_maps(unsigned long top_level_pgt) +{ + /* + * The Confidential Computing blob is used very early in uncompressed + * kernel to find the in-memory CPUID table to handle CPUID + * instructions. Make sure an identity-mapping exists so it can be + * accessed after switchover. + */ + if (sev_snp_enabled()) { + unsigned long cc_info_pa = boot_params->cc_blob_address; + struct cc_blob_sev_info *cc_info; + + kernel_add_identity_map(cc_info_pa, cc_info_pa + sizeof(*cc_info)); + + cc_info = (struct cc_blob_sev_info *)cc_info_pa; + kernel_add_identity_map(cc_info->cpuid_phys, cc_info->cpuid_phys + cc_info->cpuid_len); + } + + sev_verify_cbit(top_level_pgt); } diff --git a/arch/x86/boot/compressed/tdcall.S b/arch/x86/boot/compressed/tdcall.S new file mode 100644 index 000000000000..46d0495e0d3a --- /dev/null +++ b/arch/x86/boot/compressed/tdcall.S @@ -0,0 +1,3 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#include "../../coco/tdx/tdcall.S" diff --git a/arch/x86/boot/compressed/tdx.c b/arch/x86/boot/compressed/tdx.c new file mode 100644 index 000000000000..918a7606f53c --- /dev/null +++ b/arch/x86/boot/compressed/tdx.c @@ -0,0 +1,77 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "../cpuflags.h" +#include "../string.h" +#include "../io.h" +#include "error.h" + +#include <vdso/limits.h> +#include <uapi/asm/vmx.h> + +#include <asm/shared/tdx.h> + +/* Called from __tdx_hypercall() for unrecoverable failure */ +void __tdx_hypercall_failed(void) +{ + error("TDVMCALL failed. TDX module bug?"); +} + +static inline unsigned int tdx_io_in(int size, u16 port) +{ + struct tdx_hypercall_args args = { + .r10 = TDX_HYPERCALL_STANDARD, + .r11 = EXIT_REASON_IO_INSTRUCTION, + .r12 = size, + .r13 = 0, + .r14 = port, + }; + + if (__tdx_hypercall(&args, TDX_HCALL_HAS_OUTPUT)) + return UINT_MAX; + + return args.r11; +} + +static inline void tdx_io_out(int size, u16 port, u32 value) +{ + struct tdx_hypercall_args args = { + .r10 = TDX_HYPERCALL_STANDARD, + .r11 = EXIT_REASON_IO_INSTRUCTION, + .r12 = size, + .r13 = 1, + .r14 = port, + .r15 = value, + }; + + __tdx_hypercall(&args, 0); +} + +static inline u8 tdx_inb(u16 port) +{ + return tdx_io_in(1, port); +} + +static inline void tdx_outb(u8 value, u16 port) +{ + tdx_io_out(1, port, value); +} + +static inline void tdx_outw(u16 value, u16 port) +{ + tdx_io_out(2, port, value); +} + +void early_tdx_detect(void) +{ + u32 eax, sig[3]; + + cpuid_count(TDX_CPUID_LEAF_ID, 0, &eax, &sig[0], &sig[2], &sig[1]); + + if (memcmp(TDX_IDENT, sig, sizeof(sig))) + return; + + /* Use hypercalls instead of I/O instructions */ + pio_ops.f_inb = tdx_inb; + pio_ops.f_outb = tdx_outb; + pio_ops.f_outw = tdx_outw; +} diff --git a/arch/x86/boot/compressed/tdx.h b/arch/x86/boot/compressed/tdx.h new file mode 100644 index 000000000000..9055482cd35c --- /dev/null +++ b/arch/x86/boot/compressed/tdx.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef BOOT_COMPRESSED_TDX_H +#define BOOT_COMPRESSED_TDX_H + +#include <linux/types.h> + +#ifdef CONFIG_INTEL_TDX_GUEST +void early_tdx_detect(void); +#else +static inline void early_tdx_detect(void) { }; +#endif + +#endif /* BOOT_COMPRESSED_TDX_H */ diff --git a/arch/x86/boot/cpucheck.c b/arch/x86/boot/cpucheck.c index e1478d32de1a..fed8d13ce252 100644 --- a/arch/x86/boot/cpucheck.c +++ b/arch/x86/boot/cpucheck.c @@ -27,6 +27,7 @@ #include <asm/required-features.h> #include <asm/msr-index.h> #include "string.h" +#include "msr.h" static u32 err_flags[NCAPINTS]; @@ -130,12 +131,11 @@ int check_cpu(int *cpu_level_ptr, int *req_level_ptr, u32 **err_flags_ptr) /* If this is an AMD and we're only missing SSE+SSE2, try to turn them on */ - u32 ecx = MSR_K7_HWCR; - u32 eax, edx; + struct msr m; - asm("rdmsr" : "=a" (eax), "=d" (edx) : "c" (ecx)); - eax &= ~(1 << 15); - asm("wrmsr" : : "a" (eax), "d" (edx), "c" (ecx)); + boot_rdmsr(MSR_K7_HWCR, &m); + m.l &= ~(1 << 15); + boot_wrmsr(MSR_K7_HWCR, &m); get_cpuflags(); /* Make sure it really did something */ err = check_cpuflags(); @@ -145,28 +145,28 @@ int check_cpu(int *cpu_level_ptr, int *req_level_ptr, u32 **err_flags_ptr) /* If this is a VIA C3, we might have to enable CX8 explicitly */ - u32 ecx = MSR_VIA_FCR; - u32 eax, edx; + struct msr m; - asm("rdmsr" : "=a" (eax), "=d" (edx) : "c" (ecx)); - eax |= (1<<1)|(1<<7); - asm("wrmsr" : : "a" (eax), "d" (edx), "c" (ecx)); + boot_rdmsr(MSR_VIA_FCR, &m); + m.l |= (1 << 1) | (1 << 7); + boot_wrmsr(MSR_VIA_FCR, &m); set_bit(X86_FEATURE_CX8, cpu.flags); err = check_cpuflags(); } else if (err == 0x01 && is_transmeta()) { /* Transmeta might have masked feature bits in word 0 */ - u32 ecx = 0x80860004; - u32 eax, edx; + struct msr m, m_tmp; u32 level = 1; - asm("rdmsr" : "=a" (eax), "=d" (edx) : "c" (ecx)); - asm("wrmsr" : : "a" (~0), "d" (edx), "c" (ecx)); + boot_rdmsr(0x80860004, &m); + m_tmp = m; + m_tmp.l = ~0; + boot_wrmsr(0x80860004, &m_tmp); asm("cpuid" : "+a" (level), "=d" (cpu.flags[0]) : : "ecx", "ebx"); - asm("wrmsr" : : "a" (eax), "d" (edx), "c" (ecx)); + boot_wrmsr(0x80860004, &m); err = check_cpuflags(); } else if (err == 0x01 && diff --git a/arch/x86/boot/cpuflags.c b/arch/x86/boot/cpuflags.c index a0b75f73dc63..a83d67ec627d 100644 --- a/arch/x86/boot/cpuflags.c +++ b/arch/x86/boot/cpuflags.c @@ -71,8 +71,7 @@ int has_eflag(unsigned long mask) # define EBX_REG "=b" #endif -static inline void cpuid_count(u32 id, u32 count, - u32 *a, u32 *b, u32 *c, u32 *d) +void cpuid_count(u32 id, u32 count, u32 *a, u32 *b, u32 *c, u32 *d) { asm volatile(".ifnc %%ebx,%3 ; movl %%ebx,%3 ; .endif \n\t" "cpuid \n\t" diff --git a/arch/x86/boot/cpuflags.h b/arch/x86/boot/cpuflags.h index 2e20814d3ce3..475b8fde90f7 100644 --- a/arch/x86/boot/cpuflags.h +++ b/arch/x86/boot/cpuflags.h @@ -17,5 +17,6 @@ extern u32 cpu_vendor[3]; int has_eflag(unsigned long mask); void get_cpuflags(void); +void cpuid_count(u32 id, u32 count, u32 *a, u32 *b, u32 *c, u32 *d); #endif diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S index 6dbd7e9f74c9..0352e4589efa 100644 --- a/arch/x86/boot/header.S +++ b/arch/x86/boot/header.S @@ -163,7 +163,11 @@ extra_header_fields: .long 0x200 # SizeOfHeaders .long 0 # CheckSum .word IMAGE_SUBSYSTEM_EFI_APPLICATION # Subsystem (EFI application) +#ifdef CONFIG_DXE_MEM_ATTRIBUTES + .word IMAGE_DLL_CHARACTERISTICS_NX_COMPAT # DllCharacteristics +#else .word 0 # DllCharacteristics +#endif #ifdef CONFIG_X86_32 .long 0 # SizeOfStackReserve .long 0 # SizeOfStackCommit diff --git a/arch/x86/boot/io.h b/arch/x86/boot/io.h new file mode 100644 index 000000000000..110880907f87 --- /dev/null +++ b/arch/x86/boot/io.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef BOOT_IO_H +#define BOOT_IO_H + +#include <asm/shared/io.h> + +#undef inb +#undef inw +#undef inl +#undef outb +#undef outw +#undef outl + +struct port_io_ops { + u8 (*f_inb)(u16 port); + void (*f_outb)(u8 v, u16 port); + void (*f_outw)(u16 v, u16 port); +}; + +extern struct port_io_ops pio_ops; + +/* + * Use the normal I/O instructions by default. + * TDX guests override these to use hypercalls. + */ +static inline void init_default_io_ops(void) +{ + pio_ops.f_inb = __inb; + pio_ops.f_outb = __outb; + pio_ops.f_outw = __outw; +} + +/* + * Redirect port I/O operations via pio_ops callbacks. + * TDX guests override these callbacks with TDX-specific helpers. + */ +#define inb pio_ops.f_inb +#define outb pio_ops.f_outb +#define outw pio_ops.f_outw + +#endif diff --git a/arch/x86/boot/main.c b/arch/x86/boot/main.c index e3add857c2c9..c4ea5258ab55 100644 --- a/arch/x86/boot/main.c +++ b/arch/x86/boot/main.c @@ -17,6 +17,8 @@ struct boot_params boot_params __attribute__((aligned(16))); +struct port_io_ops pio_ops; + char *HEAP = _end; char *heap_end = _end; /* Default end of heap = no heap */ @@ -33,7 +35,7 @@ static void copy_boot_params(void) u16 cl_offset; }; const struct old_cmdline * const oldcmd = - (const struct old_cmdline *)OLD_CL_ADDRESS; + absolute_pointer(OLD_CL_ADDRESS); BUILD_BUG_ON(sizeof(boot_params) != 4096); memcpy(&boot_params.hdr, &hdr, sizeof(hdr)); @@ -133,6 +135,8 @@ static void init_heap(void) void main(void) { + init_default_io_ops(); + /* First, copy the boot header into the "zeropage" */ copy_boot_params(); diff --git a/arch/x86/boot/msr.h b/arch/x86/boot/msr.h new file mode 100644 index 000000000000..aed66f7ae199 --- /dev/null +++ b/arch/x86/boot/msr.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Helpers/definitions related to MSR access. + */ + +#ifndef BOOT_MSR_H +#define BOOT_MSR_H + +#include <asm/shared/msr.h> + +/* + * The kernel proper already defines rdmsr()/wrmsr(), but they are not for the + * boot kernel since they rely on tracepoint/exception handling infrastructure + * that's not available here. + */ +static inline void boot_rdmsr(unsigned int reg, struct msr *m) +{ + asm volatile("rdmsr" : "=a" (m->l), "=d" (m->h) : "c" (reg)); +} + +static inline void boot_wrmsr(unsigned int reg, const struct msr *m) +{ + asm volatile("wrmsr" : : "c" (reg), "a"(m->l), "d" (m->h) : "memory"); +} + +#endif /* BOOT_MSR_H */ diff --git a/arch/x86/coco/Makefile b/arch/x86/coco/Makefile index c1ead00017a7..c816acf78b6a 100644 --- a/arch/x86/coco/Makefile +++ b/arch/x86/coco/Makefile @@ -4,3 +4,5 @@ KASAN_SANITIZE_core.o := n CFLAGS_core.o += -fno-stack-protector obj-y += core.o + +obj-$(CONFIG_INTEL_TDX_GUEST) += tdx/ diff --git a/arch/x86/coco/core.c b/arch/x86/coco/core.c index fc1365dd927e..49b44f881484 100644 --- a/arch/x86/coco/core.c +++ b/arch/x86/coco/core.c @@ -18,7 +18,15 @@ static u64 cc_mask __ro_after_init; static bool intel_cc_platform_has(enum cc_attr attr) { - return false; + switch (attr) { + case CC_ATTR_GUEST_UNROLL_STRING_IO: + case CC_ATTR_HOTPLUG_DISABLED: + case CC_ATTR_GUEST_MEM_ENCRYPT: + case CC_ATTR_MEM_ENCRYPT: + return true; + default: + return false; + } } /* @@ -57,6 +65,9 @@ static bool amd_cc_platform_has(enum cc_attr attr) return (sev_status & MSR_AMD64_SEV_ENABLED) && !(sev_status & MSR_AMD64_SEV_ES_ENABLED); + case CC_ATTR_GUEST_SEV_SNP: + return sev_status & MSR_AMD64_SEV_SNP_ENABLED; + default: return false; } @@ -87,9 +98,18 @@ EXPORT_SYMBOL_GPL(cc_platform_has); u64 cc_mkenc(u64 val) { + /* + * Both AMD and Intel use a bit in the page table to indicate + * encryption status of the page. + * + * - for AMD, bit *set* means the page is encrypted + * - for Intel *clear* means encrypted. + */ switch (vendor) { case CC_VENDOR_AMD: return val | cc_mask; + case CC_VENDOR_INTEL: + return val & ~cc_mask; default: return val; } @@ -97,9 +117,12 @@ u64 cc_mkenc(u64 val) u64 cc_mkdec(u64 val) { + /* See comment in cc_mkenc() */ switch (vendor) { case CC_VENDOR_AMD: return val & ~cc_mask; + case CC_VENDOR_INTEL: + return val | cc_mask; default: return val; } diff --git a/arch/x86/coco/tdx/Makefile b/arch/x86/coco/tdx/Makefile new file mode 100644 index 000000000000..46c55998557d --- /dev/null +++ b/arch/x86/coco/tdx/Makefile @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0 + +obj-y += tdx.o tdcall.o diff --git a/arch/x86/coco/tdx/tdcall.S b/arch/x86/coco/tdx/tdcall.S new file mode 100644 index 000000000000..f9eb1134f22d --- /dev/null +++ b/arch/x86/coco/tdx/tdcall.S @@ -0,0 +1,205 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <asm/asm-offsets.h> +#include <asm/asm.h> +#include <asm/frame.h> +#include <asm/unwind_hints.h> + +#include <linux/linkage.h> +#include <linux/bits.h> +#include <linux/errno.h> + +#include "../../virt/vmx/tdx/tdxcall.S" + +/* + * Bitmasks of exposed registers (with VMM). + */ +#define TDX_R10 BIT(10) +#define TDX_R11 BIT(11) +#define TDX_R12 BIT(12) +#define TDX_R13 BIT(13) +#define TDX_R14 BIT(14) +#define TDX_R15 BIT(15) + +/* + * These registers are clobbered to hold arguments for each + * TDVMCALL. They are safe to expose to the VMM. + * Each bit in this mask represents a register ID. Bit field + * details can be found in TDX GHCI specification, section + * titled "TDCALL [TDG.VP.VMCALL] leaf". + */ +#define TDVMCALL_EXPOSE_REGS_MASK ( TDX_R10 | TDX_R11 | \ + TDX_R12 | TDX_R13 | \ + TDX_R14 | TDX_R15 ) + +/* + * __tdx_module_call() - Used by TDX guests to request services from + * the TDX module (does not include VMM services) using TDCALL instruction. + * + * Transforms function call register arguments into the TDCALL register ABI. + * After TDCALL operation, TDX module output is saved in @out (if it is + * provided by the user). + * + *------------------------------------------------------------------------- + * TDCALL ABI: + *------------------------------------------------------------------------- + * Input Registers: + * + * RAX - TDCALL Leaf number. + * RCX,RDX,R8-R9 - TDCALL Leaf specific input registers. + * + * Output Registers: + * + * RAX - TDCALL instruction error code. + * RCX,RDX,R8-R11 - TDCALL Leaf specific output registers. + * + *------------------------------------------------------------------------- + * + * __tdx_module_call() function ABI: + * + * @fn (RDI) - TDCALL Leaf ID, moved to RAX + * @rcx (RSI) - Input parameter 1, moved to RCX + * @rdx (RDX) - Input parameter 2, moved to RDX + * @r8 (RCX) - Input parameter 3, moved to R8 + * @r9 (R8) - Input parameter 4, moved to R9 + * + * @out (R9) - struct tdx_module_output pointer + * stored temporarily in R12 (not + * shared with the TDX module). It + * can be NULL. + * + * Return status of TDCALL via RAX. + */ +SYM_FUNC_START(__tdx_module_call) + FRAME_BEGIN + TDX_MODULE_CALL host=0 + FRAME_END + RET +SYM_FUNC_END(__tdx_module_call) + +/* + * __tdx_hypercall() - Make hypercalls to a TDX VMM using TDVMCALL leaf + * of TDCALL instruction + * + * Transforms values in function call argument struct tdx_hypercall_args @args + * into the TDCALL register ABI. After TDCALL operation, VMM output is saved + * back in @args. + * + *------------------------------------------------------------------------- + * TD VMCALL ABI: + *------------------------------------------------------------------------- + * + * Input Registers: + * + * RAX - TDCALL instruction leaf number (0 - TDG.VP.VMCALL) + * RCX - BITMAP which controls which part of TD Guest GPR + * is passed as-is to the VMM and back. + * R10 - Set 0 to indicate TDCALL follows standard TDX ABI + * specification. Non zero value indicates vendor + * specific ABI. + * R11 - VMCALL sub function number + * RBX, RBP, RDI, RSI - Used to pass VMCALL sub function specific arguments. + * R8-R9, R12-R15 - Same as above. + * + * Output Registers: + * + * RAX - TDCALL instruction status (Not related to hypercall + * output). + * R10 - Hypercall output error code. + * R11-R15 - Hypercall sub function specific output values. + * + *------------------------------------------------------------------------- + * + * __tdx_hypercall() function ABI: + * + * @args (RDI) - struct tdx_hypercall_args for input and output + * @flags (RSI) - TDX_HCALL_* flags + * + * On successful completion, return the hypercall error code. + */ +SYM_FUNC_START(__tdx_hypercall) + FRAME_BEGIN + + /* Save callee-saved GPRs as mandated by the x86_64 ABI */ + push %r15 + push %r14 + push %r13 + push %r12 + + /* Mangle function call ABI into TDCALL ABI: */ + /* Set TDCALL leaf ID (TDVMCALL (0)) in RAX */ + xor %eax, %eax + + /* Copy hypercall registers from arg struct: */ + movq TDX_HYPERCALL_r10(%rdi), %r10 + movq TDX_HYPERCALL_r11(%rdi), %r11 + movq TDX_HYPERCALL_r12(%rdi), %r12 + movq TDX_HYPERCALL_r13(%rdi), %r13 + movq TDX_HYPERCALL_r14(%rdi), %r14 + movq TDX_HYPERCALL_r15(%rdi), %r15 + + movl $TDVMCALL_EXPOSE_REGS_MASK, %ecx + + /* + * For the idle loop STI needs to be called directly before the TDCALL + * that enters idle (EXIT_REASON_HLT case). STI instruction enables + * interrupts only one instruction later. If there is a window between + * STI and the instruction that emulates the HALT state, there is a + * chance for interrupts to happen in this window, which can delay the + * HLT operation indefinitely. Since this is the not the desired + * result, conditionally call STI before TDCALL. + */ + testq $TDX_HCALL_ISSUE_STI, %rsi + jz .Lskip_sti + sti +.Lskip_sti: + tdcall + + /* + * RAX==0 indicates a failure of the TDVMCALL mechanism itself and that + * something has gone horribly wrong with the TDX module. + * + * The return status of the hypercall operation is in a separate + * register (in R10). Hypercall errors are a part of normal operation + * and are handled by callers. + */ + testq %rax, %rax + jne .Lpanic + + /* TDVMCALL leaf return code is in R10 */ + movq %r10, %rax + + /* Copy hypercall result registers to arg struct if needed */ + testq $TDX_HCALL_HAS_OUTPUT, %rsi + jz .Lout + + movq %r10, TDX_HYPERCALL_r10(%rdi) + movq %r11, TDX_HYPERCALL_r11(%rdi) + movq %r12, TDX_HYPERCALL_r12(%rdi) + movq %r13, TDX_HYPERCALL_r13(%rdi) + movq %r14, TDX_HYPERCALL_r14(%rdi) + movq %r15, TDX_HYPERCALL_r15(%rdi) +.Lout: + /* + * Zero out registers exposed to the VMM to avoid speculative execution + * with VMM-controlled values. This needs to include all registers + * present in TDVMCALL_EXPOSE_REGS_MASK (except R12-R15). R12-R15 + * context will be restored. + */ + xor %r10d, %r10d + xor %r11d, %r11d + + /* Restore callee-saved GPRs as mandated by the x86_64 ABI */ + pop %r12 + pop %r13 + pop %r14 + pop %r15 + + FRAME_END + + RET +.Lpanic: + call __tdx_hypercall_failed + /* __tdx_hypercall_failed never returns */ + REACHABLE + jmp .Lpanic +SYM_FUNC_END(__tdx_hypercall) diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c new file mode 100644 index 000000000000..03deb4d6920d --- /dev/null +++ b/arch/x86/coco/tdx/tdx.c @@ -0,0 +1,692 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2021-2022 Intel Corporation */ + +#undef pr_fmt +#define pr_fmt(fmt) "tdx: " fmt + +#include <linux/cpufeature.h> +#include <asm/coco.h> +#include <asm/tdx.h> +#include <asm/vmx.h> +#include <asm/insn.h> +#include <asm/insn-eval.h> +#include <asm/pgtable.h> + +/* TDX module Call Leaf IDs */ +#define TDX_GET_INFO 1 +#define TDX_GET_VEINFO 3 +#define TDX_ACCEPT_PAGE 6 + +/* TDX hypercall Leaf IDs */ +#define TDVMCALL_MAP_GPA 0x10001 + +/* MMIO direction */ +#define EPT_READ 0 +#define EPT_WRITE 1 + +/* Port I/O direction */ +#define PORT_READ 0 +#define PORT_WRITE 1 + +/* See Exit Qualification for I/O Instructions in VMX documentation */ +#define VE_IS_IO_IN(e) ((e) & BIT(3)) +#define VE_GET_IO_SIZE(e) (((e) & GENMASK(2, 0)) + 1) +#define VE_GET_PORT_NUM(e) ((e) >> 16) +#define VE_IS_IO_STRING(e) ((e) & BIT(4)) + +/* + * Wrapper for standard use of __tdx_hypercall with no output aside from + * return code. + */ +static inline u64 _tdx_hypercall(u64 fn, u64 r12, u64 r13, u64 r14, u64 r15) +{ + struct tdx_hypercall_args args = { + .r10 = TDX_HYPERCALL_STANDARD, + .r11 = fn, + .r12 = r12, + .r13 = r13, + .r14 = r14, + .r15 = r15, + }; + + return __tdx_hypercall(&args, 0); +} + +/* Called from __tdx_hypercall() for unrecoverable failure */ +void __tdx_hypercall_failed(void) +{ + panic("TDVMCALL failed. TDX module bug?"); +} + +/* + * The TDG.VP.VMCALL-Instruction-execution sub-functions are defined + * independently from but are currently matched 1:1 with VMX EXIT_REASONs. + * Reusing the KVM EXIT_REASON macros makes it easier to connect the host and + * guest sides of these calls. + */ +static u64 hcall_func(u64 exit_reason) +{ + return exit_reason; +} + +#ifdef CONFIG_KVM_GUEST +long tdx_kvm_hypercall(unsigned int nr, unsigned long p1, unsigned long p2, + unsigned long p3, unsigned long p4) +{ + struct tdx_hypercall_args args = { + .r10 = nr, + .r11 = p1, + .r12 = p2, + .r13 = p3, + .r14 = p4, + }; + + return __tdx_hypercall(&args, 0); +} +EXPORT_SYMBOL_GPL(tdx_kvm_hypercall); +#endif + +/* + * Used for TDX guests to make calls directly to the TD module. This + * should only be used for calls that have no legitimate reason to fail + * or where the kernel can not survive the call failing. + */ +static inline void tdx_module_call(u64 fn, u64 rcx, u64 rdx, u64 r8, u64 r9, + struct tdx_module_output *out) +{ + if (__tdx_module_call(fn, rcx, rdx, r8, r9, out)) + panic("TDCALL %lld failed (Buggy TDX module!)\n", fn); +} + +static u64 get_cc_mask(void) +{ + struct tdx_module_output out; + unsigned int gpa_width; + + /* + * TDINFO TDX module call is used to get the TD execution environment + * information like GPA width, number of available vcpus, debug mode + * information, etc. More details about the ABI can be found in TDX + * Guest-Host-Communication Interface (GHCI), section 2.4.2 TDCALL + * [TDG.VP.INFO]. + * + * The GPA width that comes out of this call is critical. TDX guests + * can not meaningfully run without it. + */ + tdx_module_call(TDX_GET_INFO, 0, 0, 0, 0, &out); + + gpa_width = out.rcx & GENMASK(5, 0); + + /* + * The highest bit of a guest physical address is the "sharing" bit. + * Set it for shared pages and clear it for private pages. + */ + return BIT_ULL(gpa_width - 1); +} + +static u64 __cpuidle __halt(const bool irq_disabled, const bool do_sti) +{ + struct tdx_hypercall_args args = { + .r10 = TDX_HYPERCALL_STANDARD, + .r11 = hcall_func(EXIT_REASON_HLT), + .r12 = irq_disabled, + }; + + /* + * Emulate HLT operation via hypercall. More info about ABI + * can be found in TDX Guest-Host-Communication Interface + * (GHCI), section 3.8 TDG.VP.VMCALL<Instruction.HLT>. + * + * The VMM uses the "IRQ disabled" param to understand IRQ + * enabled status (RFLAGS.IF) of the TD guest and to determine + * whether or not it should schedule the halted vCPU if an + * IRQ becomes pending. E.g. if IRQs are disabled, the VMM + * can keep the vCPU in virtual HLT, even if an IRQ is + * pending, without hanging/breaking the guest. + */ + return __tdx_hypercall(&args, do_sti ? TDX_HCALL_ISSUE_STI : 0); +} + +static bool handle_halt(void) +{ + /* + * Since non safe halt is mainly used in CPU offlining + * and the guest will always stay in the halt state, don't + * call the STI instruction (set do_sti as false). + */ + const bool irq_disabled = irqs_disabled(); + const bool do_sti = false; + + if (__halt(irq_disabled, do_sti)) + return false; + + return true; +} + +void __cpuidle tdx_safe_halt(void) +{ + /* + * For do_sti=true case, __tdx_hypercall() function enables + * interrupts using the STI instruction before the TDCALL. So + * set irq_disabled as false. + */ + const bool irq_disabled = false; + const bool do_sti = true; + + /* + * Use WARN_ONCE() to report the failure. + */ + if (__halt(irq_disabled, do_sti)) + WARN_ONCE(1, "HLT instruction emulation failed\n"); +} + +static bool read_msr(struct pt_regs *regs) +{ + struct tdx_hypercall_args args = { + .r10 = TDX_HYPERCALL_STANDARD, + .r11 = hcall_func(EXIT_REASON_MSR_READ), + .r12 = regs->cx, + }; + + /* + * Emulate the MSR read via hypercall. More info about ABI + * can be found in TDX Guest-Host-Communication Interface + * (GHCI), section titled "TDG.VP.VMCALL<Instruction.RDMSR>". + */ + if (__tdx_hypercall(&args, TDX_HCALL_HAS_OUTPUT)) + return false; + + regs->ax = lower_32_bits(args.r11); + regs->dx = upper_32_bits(args.r11); + return true; +} + +static bool write_msr(struct pt_regs *regs) +{ + struct tdx_hypercall_args args = { + .r10 = TDX_HYPERCALL_STANDARD, + .r11 = hcall_func(EXIT_REASON_MSR_WRITE), + .r12 = regs->cx, + .r13 = (u64)regs->dx << 32 | regs->ax, + }; + + /* + * Emulate the MSR write via hypercall. More info about ABI + * can be found in TDX Guest-Host-Communication Interface + * (GHCI) section titled "TDG.VP.VMCALL<Instruction.WRMSR>". + */ + return !__tdx_hypercall(&args, 0); +} + +static bool handle_cpuid(struct pt_regs *regs) +{ + struct tdx_hypercall_args args = { + .r10 = TDX_HYPERCALL_STANDARD, + .r11 = hcall_func(EXIT_REASON_CPUID), + .r12 = regs->ax, + .r13 = regs->cx, + }; + + /* + * Only allow VMM to control range reserved for hypervisor + * communication. + * + * Return all-zeros for any CPUID outside the range. It matches CPU + * behaviour for non-supported leaf. + */ + if (regs->ax < 0x40000000 || regs->ax > 0x4FFFFFFF) { + regs->ax = regs->bx = regs->cx = regs->dx = 0; + return true; + } + + /* + * Emulate the CPUID instruction via a hypercall. More info about + * ABI can be found in TDX Guest-Host-Communication Interface + * (GHCI), section titled "VP.VMCALL<Instruction.CPUID>". + */ + if (__tdx_hypercall(&args, TDX_HCALL_HAS_OUTPUT)) + return false; + + /* + * As per TDX GHCI CPUID ABI, r12-r15 registers contain contents of + * EAX, EBX, ECX, EDX registers after the CPUID instruction execution. + * So copy the register contents back to pt_regs. + */ + regs->ax = args.r12; + regs->bx = args.r13; + regs->cx = args.r14; + regs->dx = args.r15; + + return true; +} + +static bool mmio_read(int size, unsigned long addr, unsigned long *val) +{ + struct tdx_hypercall_args args = { + .r10 = TDX_HYPERCALL_STANDARD, + .r11 = hcall_func(EXIT_REASON_EPT_VIOLATION), + .r12 = size, + .r13 = EPT_READ, + .r14 = addr, + .r15 = *val, + }; + + if (__tdx_hypercall(&args, TDX_HCALL_HAS_OUTPUT)) + return false; + *val = args.r11; + return true; +} + +static bool mmio_write(int size, unsigned long addr, unsigned long val) +{ + return !_tdx_hypercall(hcall_func(EXIT_REASON_EPT_VIOLATION), size, + EPT_WRITE, addr, val); +} + +static bool handle_mmio(struct pt_regs *regs, struct ve_info *ve) +{ + char buffer[MAX_INSN_SIZE]; + unsigned long *reg, val; + struct insn insn = {}; + enum mmio_type mmio; + int size, extend_size; + u8 extend_val = 0; + + /* Only in-kernel MMIO is supported */ + if (WARN_ON_ONCE(user_mode(regs))) + return false; + + if (copy_from_kernel_nofault(buffer, (void *)regs->ip, MAX_INSN_SIZE)) + return false; + + if (insn_decode(&insn, buffer, MAX_INSN_SIZE, INSN_MODE_64)) + return false; + + mmio = insn_decode_mmio(&insn, &size); + if (WARN_ON_ONCE(mmio == MMIO_DECODE_FAILED)) + return false; + + if (mmio != MMIO_WRITE_IMM && mmio != MMIO_MOVS) { + reg = insn_get_modrm_reg_ptr(&insn, regs); + if (!reg) + return false; + } + + ve->instr_len = insn.length; + + /* Handle writes first */ + switch (mmio) { + case MMIO_WRITE: + memcpy(&val, reg, size); + return mmio_write(size, ve->gpa, val); + case MMIO_WRITE_IMM: + val = insn.immediate.value; + return mmio_write(size, ve->gpa, val); + case MMIO_READ: + case MMIO_READ_ZERO_EXTEND: + case MMIO_READ_SIGN_EXTEND: + /* Reads are handled below */ + break; + case MMIO_MOVS: + case MMIO_DECODE_FAILED: + /* + * MMIO was accessed with an instruction that could not be + * decoded or handled properly. It was likely not using io.h + * helpers or accessed MMIO accidentally. + */ + return false; + default: + WARN_ONCE(1, "Unknown insn_decode_mmio() decode value?"); + return false; + } + + /* Handle reads */ + if (!mmio_read(size, ve->gpa, &val)) + return false; + + switch (mmio) { + case MMIO_READ: + /* Zero-extend for 32-bit operation */ + extend_size = size == 4 ? sizeof(*reg) : 0; + break; + case MMIO_READ_ZERO_EXTEND: + /* Zero extend based on operand size */ + extend_size = insn.opnd_bytes; + break; + case MMIO_READ_SIGN_EXTEND: + /* Sign extend based on operand size */ + extend_size = insn.opnd_bytes; + if (size == 1 && val & BIT(7)) + extend_val = 0xFF; + else if (size > 1 && val & BIT(15)) + extend_val = 0xFF; + break; + default: + /* All other cases has to be covered with the first switch() */ + WARN_ON_ONCE(1); + return false; + } + + if (extend_size) + memset(reg, extend_val, extend_size); + memcpy(reg, &val, size); + return true; +} + +static bool handle_in(struct pt_regs *regs, int size, int port) +{ + struct tdx_hypercall_args args = { + .r10 = TDX_HYPERCALL_STANDARD, + .r11 = hcall_func(EXIT_REASON_IO_INSTRUCTION), + .r12 = size, + .r13 = PORT_READ, + .r14 = port, + }; + u64 mask = GENMASK(BITS_PER_BYTE * size, 0); + bool success; + + /* + * Emulate the I/O read via hypercall. More info about ABI can be found + * in TDX Guest-Host-Communication Interface (GHCI) section titled + * "TDG.VP.VMCALL<Instruction.IO>". + */ + success = !__tdx_hypercall(&args, TDX_HCALL_HAS_OUTPUT); + + /* Update part of the register affected by the emulated instruction */ + regs->ax &= ~mask; + if (success) + regs->ax |= args.r11 & mask; + + return success; +} + +static bool handle_out(struct pt_regs *regs, int size, int port) +{ + u64 mask = GENMASK(BITS_PER_BYTE * size, 0); + + /* + * Emulate the I/O write via hypercall. More info about ABI can be found + * in TDX Guest-Host-Communication Interface (GHCI) section titled + * "TDG.VP.VMCALL<Instruction.IO>". + */ + return !_tdx_hypercall(hcall_func(EXIT_REASON_IO_INSTRUCTION), size, + PORT_WRITE, port, regs->ax & mask); +} + +/* + * Emulate I/O using hypercall. + * + * Assumes the IO instruction was using ax, which is enforced + * by the standard io.h macros. + * + * Return True on success or False on failure. + */ +static bool handle_io(struct pt_regs *regs, u32 exit_qual) +{ + int size, port; + bool in; + + if (VE_IS_IO_STRING(exit_qual)) + return false; + + in = VE_IS_IO_IN(exit_qual); + size = VE_GET_IO_SIZE(exit_qual); + port = VE_GET_PORT_NUM(exit_qual); + + + if (in) + return handle_in(regs, size, port); + else + return handle_out(regs, size, port); +} + +/* + * Early #VE exception handler. Only handles a subset of port I/O. + * Intended only for earlyprintk. If failed, return false. + */ +__init bool tdx_early_handle_ve(struct pt_regs *regs) +{ + struct ve_info ve; + + tdx_get_ve_info(&ve); + + if (ve.exit_reason != EXIT_REASON_IO_INSTRUCTION) + return false; + + return handle_io(regs, ve.exit_qual); +} + +void tdx_get_ve_info(struct ve_info *ve) +{ + struct tdx_module_output out; + + /* + * Called during #VE handling to retrieve the #VE info from the + * TDX module. + * + * This has to be called early in #VE handling. A "nested" #VE which + * occurs before this will raise a #DF and is not recoverable. + * + * The call retrieves the #VE info from the TDX module, which also + * clears the "#VE valid" flag. This must be done before anything else + * because any #VE that occurs while the valid flag is set will lead to + * #DF. + * + * Note, the TDX module treats virtual NMIs as inhibited if the #VE + * valid flag is set. It means that NMI=>#VE will not result in a #DF. + */ + tdx_module_call(TDX_GET_VEINFO, 0, 0, 0, 0, &out); + + /* Transfer the output parameters */ + ve->exit_reason = out.rcx; + ve->exit_qual = out.rdx; + ve->gla = out.r8; + ve->gpa = out.r9; + ve->instr_len = lower_32_bits(out.r10); + ve->instr_info = upper_32_bits(out.r10); +} + +/* Handle the user initiated #VE */ +static bool virt_exception_user(struct pt_regs *regs, struct ve_info *ve) +{ + switch (ve->exit_reason) { + case EXIT_REASON_CPUID: + return handle_cpuid(regs); + default: + pr_warn("Unexpected #VE: %lld\n", ve->exit_reason); + return false; + } +} + +/* Handle the kernel #VE */ +static bool virt_exception_kernel(struct pt_regs *regs, struct ve_info *ve) +{ + switch (ve->exit_reason) { + case EXIT_REASON_HLT: + return handle_halt(); + case EXIT_REASON_MSR_READ: + return read_msr(regs); + case EXIT_REASON_MSR_WRITE: + return write_msr(regs); + case EXIT_REASON_CPUID: + return handle_cpuid(regs); + case EXIT_REASON_EPT_VIOLATION: + return handle_mmio(regs, ve); + case EXIT_REASON_IO_INSTRUCTION: + return handle_io(regs, ve->exit_qual); + default: + pr_warn("Unexpected #VE: %lld\n", ve->exit_reason); + return false; + } +} + +bool tdx_handle_virt_exception(struct pt_regs *regs, struct ve_info *ve) +{ + bool ret; + + if (user_mode(regs)) + ret = virt_exception_user(regs, ve); + else + ret = virt_exception_kernel(regs, ve); + + /* After successful #VE handling, move the IP */ + if (ret) + regs->ip += ve->instr_len; + + return ret; +} + +static bool tdx_tlb_flush_required(bool private) +{ + /* + * TDX guest is responsible for flushing TLB on private->shared + * transition. VMM is responsible for flushing on shared->private. + * + * The VMM _can't_ flush private addresses as it can't generate PAs + * with the guest's HKID. Shared memory isn't subject to integrity + * checking, i.e. the VMM doesn't need to flush for its own protection. + * + * There's no need to flush when converting from shared to private, + * as flushing is the VMM's responsibility in this case, e.g. it must + * flush to avoid integrity failures in the face of a buggy or + * malicious guest. + */ + return !private; +} + +static bool tdx_cache_flush_required(void) +{ + /* + * AMD SME/SEV can avoid cache flushing if HW enforces cache coherence. + * TDX doesn't have such capability. + * + * Flush cache unconditionally. + */ + return true; +} + +static bool try_accept_one(phys_addr_t *start, unsigned long len, + enum pg_level pg_level) +{ + unsigned long accept_size = page_level_size(pg_level); + u64 tdcall_rcx; + u8 page_size; + + if (!IS_ALIGNED(*start, accept_size)) + return false; + + if (len < accept_size) + return false; + + /* + * Pass the page physical address to the TDX module to accept the + * pending, private page. + * + * Bits 2:0 of RCX encode page size: 0 - 4K, 1 - 2M, 2 - 1G. + */ + switch (pg_level) { + case PG_LEVEL_4K: + page_size = 0; + break; + case PG_LEVEL_2M: + page_size = 1; + break; + case PG_LEVEL_1G: + page_size = 2; + break; + default: + return false; + } + + tdcall_rcx = *start | page_size; + if (__tdx_module_call(TDX_ACCEPT_PAGE, tdcall_rcx, 0, 0, 0, NULL)) + return false; + + *start += accept_size; + return true; +} + +/* + * Inform the VMM of the guest's intent for this physical page: shared with + * the VMM or private to the guest. The VMM is expected to change its mapping + * of the page in response. + */ +static bool tdx_enc_status_changed(unsigned long vaddr, int numpages, bool enc) +{ + phys_addr_t start = __pa(vaddr); + phys_addr_t end = __pa(vaddr + numpages * PAGE_SIZE); + + if (!enc) { + /* Set the shared (decrypted) bits: */ + start |= cc_mkdec(0); + end |= cc_mkdec(0); + } + + /* + * Notify the VMM about page mapping conversion. More info about ABI + * can be found in TDX Guest-Host-Communication Interface (GHCI), + * section "TDG.VP.VMCALL<MapGPA>" + */ + if (_tdx_hypercall(TDVMCALL_MAP_GPA, start, end - start, 0, 0)) + return false; + + /* private->shared conversion requires only MapGPA call */ + if (!enc) + return true; + + /* + * For shared->private conversion, accept the page using + * TDX_ACCEPT_PAGE TDX module call. + */ + while (start < end) { + unsigned long len = end - start; + + /* + * Try larger accepts first. It gives chance to VMM to keep + * 1G/2M SEPT entries where possible and speeds up process by + * cutting number of hypercalls (if successful). + */ + + if (try_accept_one(&start, len, PG_LEVEL_1G)) + continue; + + if (try_accept_one(&start, len, PG_LEVEL_2M)) + continue; + + if (!try_accept_one(&start, len, PG_LEVEL_4K)) + return false; + } + + return true; +} + +void __init tdx_early_init(void) +{ + u64 cc_mask; + u32 eax, sig[3]; + + cpuid_count(TDX_CPUID_LEAF_ID, 0, &eax, &sig[0], &sig[2], &sig[1]); + + if (memcmp(TDX_IDENT, sig, sizeof(sig))) + return; + + setup_force_cpu_cap(X86_FEATURE_TDX_GUEST); + + cc_set_vendor(CC_VENDOR_INTEL); + cc_mask = get_cc_mask(); + cc_set_mask(cc_mask); + + /* + * All bits above GPA width are reserved and kernel treats shared bit + * as flag, not as part of physical address. + * + * Adjust physical mask to only cover valid GPA bits. + */ + physical_mask &= cc_mask - 1; + + x86_platform.guest.enc_cache_flush_required = tdx_cache_flush_required; + x86_platform.guest.enc_tlb_flush_required = tdx_tlb_flush_required; + x86_platform.guest.enc_status_change_finish = tdx_enc_status_changed; + + pr_info("Guest detected\n"); +} diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index a4c061fb7c6e..29b36e9e4e74 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -63,7 +63,7 @@ For 32-bit we have the following conventions - kernel is built with * for assembly code: */ -.macro PUSH_REGS rdx=%rdx rax=%rax save_ret=0 +.macro PUSH_REGS rdx=%rdx rcx=%rcx rax=%rax save_ret=0 .if \save_ret pushq %rsi /* pt_regs->si */ movq 8(%rsp), %rsi /* temporarily store the return address in %rsi */ @@ -73,7 +73,7 @@ For 32-bit we have the following conventions - kernel is built with pushq %rsi /* pt_regs->si */ .endif pushq \rdx /* pt_regs->dx */ - pushq %rcx /* pt_regs->cx */ + pushq \rcx /* pt_regs->cx */ pushq \rax /* pt_regs->ax */ pushq %r8 /* pt_regs->r8 */ pushq %r9 /* pt_regs->r9 */ @@ -99,6 +99,7 @@ For 32-bit we have the following conventions - kernel is built with * well before they could be put to use in a speculative execution * gadget. */ + xorl %esi, %esi /* nospec si */ xorl %edx, %edx /* nospec dx */ xorl %ecx, %ecx /* nospec cx */ xorl %r8d, %r8d /* nospec r8 */ @@ -114,32 +115,24 @@ For 32-bit we have the following conventions - kernel is built with .endm -.macro PUSH_AND_CLEAR_REGS rdx=%rdx rax=%rax save_ret=0 - PUSH_REGS rdx=\rdx, rax=\rax, save_ret=\save_ret +.macro PUSH_AND_CLEAR_REGS rdx=%rdx rcx=%rcx rax=%rax save_ret=0 + PUSH_REGS rdx=\rdx, rcx=\rcx, rax=\rax, save_ret=\save_ret CLEAR_REGS .endm -.macro POP_REGS pop_rdi=1 skip_r11rcx=0 +.macro POP_REGS pop_rdi=1 popq %r15 popq %r14 popq %r13 popq %r12 popq %rbp popq %rbx - .if \skip_r11rcx - popq %rsi - .else popq %r11 - .endif popq %r10 popq %r9 popq %r8 popq %rax - .if \skip_r11rcx - popq %rsi - .else popq %rcx - .endif popq %rdx popq %rsi .if \pop_rdi diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 4faac48ebec5..4300ba49b5ee 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -191,8 +191,7 @@ SYM_INNER_LABEL(entry_SYSCALL_64_after_hwframe, SYM_L_GLOBAL) * perf profiles. Nothing jumps here. */ syscall_return_via_sysret: - /* rcx and r11 are already restored (see code above) */ - POP_REGS pop_rdi=0 skip_r11rcx=1 + POP_REGS pop_rdi=0 /* * Now all regs are restored except RSP and RDI. @@ -215,8 +214,13 @@ syscall_return_via_sysret: popq %rdi popq %rsp +SYM_INNER_LABEL(entry_SYSRETQ_unsafe_stack, SYM_L_GLOBAL) + ANNOTATE_NOENDBR swapgs sysretq +SYM_INNER_LABEL(entry_SYSRETQ_end, SYM_L_GLOBAL) + ANNOTATE_NOENDBR + int3 SYM_CODE_END(entry_SYSCALL_64) /* @@ -318,6 +322,14 @@ SYM_CODE_END(ret_from_fork) #endif .endm +/* Save all registers in pt_regs */ +SYM_CODE_START_LOCAL(push_and_clear_regs) + UNWIND_HINT_FUNC + PUSH_AND_CLEAR_REGS save_ret=1 + ENCODE_FRAME_POINTER 8 + RET +SYM_CODE_END(push_and_clear_regs) + /** * idtentry_body - Macro to emit code calling the C function * @cfunc: C function to be called @@ -325,7 +337,21 @@ SYM_CODE_END(ret_from_fork) */ .macro idtentry_body cfunc has_error_code:req - call error_entry + call push_and_clear_regs + UNWIND_HINT_REGS + + /* + * Call error_entry() and switch to the task stack if from userspace. + * + * When in XENPV, it is already in the task stack, and it can't fault + * for native_iret() nor native_load_gs_index() since XENPV uses its + * own pvops for IRET and load_gs_index(). And it doesn't need to + * switch the CR3. So it can skip invoking error_entry(). + */ + ALTERNATIVE "call error_entry; movq %rax, %rsp", \ + "", X86_FEATURE_XENPV + + ENCODE_FRAME_POINTER UNWIND_HINT_REGS movq %rsp, %rdi /* pt_regs pointer into 1st argument*/ @@ -337,6 +363,9 @@ SYM_CODE_END(ret_from_fork) call \cfunc + /* For some configurations \cfunc ends up being a noreturn. */ + REACHABLE + jmp error_return .endm @@ -355,6 +384,7 @@ SYM_CODE_START(\asmsym) UNWIND_HINT_IRET_REGS offset=\has_error_code*8 ENDBR ASM_CLAC + cld .if \has_error_code == 0 pushq $-1 /* ORIG_RAX: no syscall to restart */ @@ -423,6 +453,7 @@ SYM_CODE_START(\asmsym) UNWIND_HINT_IRET_REGS ENDBR ASM_CLAC + cld pushq $-1 /* ORIG_RAX: no syscall to restart */ @@ -479,6 +510,7 @@ SYM_CODE_START(\asmsym) UNWIND_HINT_IRET_REGS ENDBR ASM_CLAC + cld /* * If the entry is from userspace, switch stacks and treat it as @@ -505,6 +537,7 @@ SYM_CODE_START(\asmsym) call vc_switch_off_ist movq %rax, %rsp /* Switch to new stack */ + ENCODE_FRAME_POINTER UNWIND_HINT_REGS /* Update pt_regs */ @@ -541,6 +574,7 @@ SYM_CODE_START(\asmsym) UNWIND_HINT_IRET_REGS offset=8 ENDBR ASM_CLAC + cld /* paranoid_entry returns GS information for paranoid_exit in EBX. */ call paranoid_entry @@ -866,7 +900,6 @@ SYM_CODE_END(xen_failsafe_callback) */ SYM_CODE_START_LOCAL(paranoid_entry) UNWIND_HINT_FUNC - cld PUSH_AND_CLEAR_REGS save_ret=1 ENCODE_FRAME_POINTER 8 @@ -980,13 +1013,10 @@ SYM_CODE_START_LOCAL(paranoid_exit) SYM_CODE_END(paranoid_exit) /* - * Save all registers in pt_regs, and switch GS if needed. + * Switch GS and CR3 if needed. */ SYM_CODE_START_LOCAL(error_entry) UNWIND_HINT_FUNC - cld - PUSH_AND_CLEAR_REGS save_ret=1 - ENCODE_FRAME_POINTER 8 testb $3, CS+8(%rsp) jz .Lerror_kernelspace @@ -994,19 +1024,15 @@ SYM_CODE_START_LOCAL(error_entry) * We entered from user mode or we're pretending to have entered * from user mode due to an IRET fault. */ - SWAPGS + swapgs FENCE_SWAPGS_USER_ENTRY /* We have user CR3. Change to kernel CR3. */ SWITCH_TO_KERNEL_CR3 scratch_reg=%rax + leaq 8(%rsp), %rdi /* arg0 = pt_regs pointer */ .Lerror_entry_from_usermode_after_swapgs: /* Put us onto the real thread stack. */ - popq %r12 /* save return addr in %12 */ - movq %rsp, %rdi /* arg0 = pt_regs pointer */ call sync_regs - movq %rax, %rsp /* switch stack */ - ENCODE_FRAME_POINTER - pushq %r12 RET /* @@ -1030,7 +1056,7 @@ SYM_CODE_START_LOCAL(error_entry) * gsbase and proceed. We'll fix up the exception and land in * .Lgs_change's error handler with kernel gsbase. */ - SWAPGS + swapgs /* * Issue an LFENCE to prevent GS speculation, regardless of whether it is a @@ -1038,6 +1064,7 @@ SYM_CODE_START_LOCAL(error_entry) */ .Lerror_entry_done_lfence: FENCE_SWAPGS_KERNEL_ENTRY + leaq 8(%rsp), %rax /* return pt_regs pointer */ RET .Lbstep_iret: @@ -1050,7 +1077,7 @@ SYM_CODE_START_LOCAL(error_entry) * We came from an IRET to user mode, so we have user * gsbase and CR3. Switch to kernel gsbase and CR3: */ - SWAPGS + swapgs FENCE_SWAPGS_USER_ENTRY SWITCH_TO_KERNEL_CR3 scratch_reg=%rax @@ -1058,9 +1085,9 @@ SYM_CODE_START_LOCAL(error_entry) * Pretend that the exception came from user mode: set up pt_regs * as if we faulted immediately after IRET. */ - mov %rsp, %rdi + leaq 8(%rsp), %rdi /* arg0 = pt_regs pointer */ call fixup_bad_iret - mov %rax, %rsp + mov %rax, %rdi jmp .Lerror_entry_from_usermode_after_swapgs SYM_CODE_END(error_entry) @@ -1123,6 +1150,7 @@ SYM_CODE_START(asm_exc_nmi) */ ASM_CLAC + cld /* Use %rdx as our temp variable throughout */ pushq %rdx @@ -1142,7 +1170,6 @@ SYM_CODE_START(asm_exc_nmi) */ swapgs - cld FENCE_SWAPGS_USER_ENTRY SWITCH_TO_KERNEL_CR3 scratch_reg=%rdx movq %rsp, %rdx diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index 4fdb007cddbd..d1052742ad0c 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -50,7 +50,7 @@ SYM_CODE_START(entry_SYSENTER_compat) UNWIND_HINT_EMPTY ENDBR /* Interrupts are off on entry. */ - SWAPGS + swapgs pushq %rax SWITCH_TO_KERNEL_CR3 scratch_reg=%rax @@ -83,32 +83,7 @@ SYM_INNER_LABEL(entry_SYSENTER_compat_after_hwframe, SYM_L_GLOBAL) movl %eax, %eax pushq %rax /* pt_regs->orig_ax */ - pushq %rdi /* pt_regs->di */ - pushq %rsi /* pt_regs->si */ - pushq %rdx /* pt_regs->dx */ - pushq %rcx /* pt_regs->cx */ - pushq $-ENOSYS /* pt_regs->ax */ - pushq $0 /* pt_regs->r8 = 0 */ - xorl %r8d, %r8d /* nospec r8 */ - pushq $0 /* pt_regs->r9 = 0 */ - xorl %r9d, %r9d /* nospec r9 */ - pushq $0 /* pt_regs->r10 = 0 */ - xorl %r10d, %r10d /* nospec r10 */ - pushq $0 /* pt_regs->r11 = 0 */ - xorl %r11d, %r11d /* nospec r11 */ - pushq %rbx /* pt_regs->rbx */ - xorl %ebx, %ebx /* nospec rbx */ - pushq %rbp /* pt_regs->rbp (will be overwritten) */ - xorl %ebp, %ebp /* nospec rbp */ - pushq $0 /* pt_regs->r12 = 0 */ - xorl %r12d, %r12d /* nospec r12 */ - pushq $0 /* pt_regs->r13 = 0 */ - xorl %r13d, %r13d /* nospec r13 */ - pushq $0 /* pt_regs->r14 = 0 */ - xorl %r14d, %r14d /* nospec r14 */ - pushq $0 /* pt_regs->r15 = 0 */ - xorl %r15d, %r15d /* nospec r15 */ - + PUSH_AND_CLEAR_REGS rax=$-ENOSYS UNWIND_HINT_REGS cld @@ -225,35 +200,7 @@ SYM_INNER_LABEL(entry_SYSCALL_compat_safe_stack, SYM_L_GLOBAL) SYM_INNER_LABEL(entry_SYSCALL_compat_after_hwframe, SYM_L_GLOBAL) movl %eax, %eax /* discard orig_ax high bits */ pushq %rax /* pt_regs->orig_ax */ - pushq %rdi /* pt_regs->di */ - pushq %rsi /* pt_regs->si */ - xorl %esi, %esi /* nospec si */ - pushq %rdx /* pt_regs->dx */ - xorl %edx, %edx /* nospec dx */ - pushq %rbp /* pt_regs->cx (stashed in bp) */ - xorl %ecx, %ecx /* nospec cx */ - pushq $-ENOSYS /* pt_regs->ax */ - pushq $0 /* pt_regs->r8 = 0 */ - xorl %r8d, %r8d /* nospec r8 */ - pushq $0 /* pt_regs->r9 = 0 */ - xorl %r9d, %r9d /* nospec r9 */ - pushq $0 /* pt_regs->r10 = 0 */ - xorl %r10d, %r10d /* nospec r10 */ - pushq $0 /* pt_regs->r11 = 0 */ - xorl %r11d, %r11d /* nospec r11 */ - pushq %rbx /* pt_regs->rbx */ - xorl %ebx, %ebx /* nospec rbx */ - pushq %rbp /* pt_regs->rbp (will be overwritten) */ - xorl %ebp, %ebp /* nospec rbp */ - pushq $0 /* pt_regs->r12 = 0 */ - xorl %r12d, %r12d /* nospec r12 */ - pushq $0 /* pt_regs->r13 = 0 */ - xorl %r13d, %r13d /* nospec r13 */ - pushq $0 /* pt_regs->r14 = 0 */ - xorl %r14d, %r14d /* nospec r14 */ - pushq $0 /* pt_regs->r15 = 0 */ - xorl %r15d, %r15d /* nospec r15 */ - + PUSH_AND_CLEAR_REGS rcx=%rbp rax=$-ENOSYS UNWIND_HINT_REGS movq %rsp, %rdi @@ -297,6 +244,8 @@ sysret32_from_system_call: * code. We zero R8-R10 to avoid info leaks. */ movq RSP-ORIG_RAX(%rsp), %rsp +SYM_INNER_LABEL(entry_SYSRETL_compat_unsafe_stack, SYM_L_GLOBAL) + ANNOTATE_NOENDBR /* * The original userspace %rsp (RSP-ORIG_RAX(%rsp)) is stored @@ -314,6 +263,9 @@ sysret32_from_system_call: xorl %r10d, %r10d swapgs sysretl +SYM_INNER_LABEL(entry_SYSRETL_compat_end, SYM_L_GLOBAL) + ANNOTATE_NOENDBR + int3 SYM_CODE_END(entry_SYSCALL_compat) /* @@ -362,54 +314,25 @@ SYM_CODE_START(entry_INT80_compat) /* switch to thread stack expects orig_ax and rdi to be pushed */ pushq %rax /* pt_regs->orig_ax */ - pushq %rdi /* pt_regs->di */ /* Need to switch before accessing the thread stack. */ - SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi + SWITCH_TO_KERNEL_CR3 scratch_reg=%rax /* In the Xen PV case we already run on the thread stack. */ ALTERNATIVE "", "jmp .Lint80_keep_stack", X86_FEATURE_XENPV - movq %rsp, %rdi + movq %rsp, %rax movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp - pushq 6*8(%rdi) /* regs->ss */ - pushq 5*8(%rdi) /* regs->rsp */ - pushq 4*8(%rdi) /* regs->eflags */ - pushq 3*8(%rdi) /* regs->cs */ - pushq 2*8(%rdi) /* regs->ip */ - pushq 1*8(%rdi) /* regs->orig_ax */ - pushq (%rdi) /* pt_regs->di */ + pushq 5*8(%rax) /* regs->ss */ + pushq 4*8(%rax) /* regs->rsp */ + pushq 3*8(%rax) /* regs->eflags */ + pushq 2*8(%rax) /* regs->cs */ + pushq 1*8(%rax) /* regs->ip */ + pushq 0*8(%rax) /* regs->orig_ax */ .Lint80_keep_stack: - pushq %rsi /* pt_regs->si */ - xorl %esi, %esi /* nospec si */ - pushq %rdx /* pt_regs->dx */ - xorl %edx, %edx /* nospec dx */ - pushq %rcx /* pt_regs->cx */ - xorl %ecx, %ecx /* nospec cx */ - pushq $-ENOSYS /* pt_regs->ax */ - pushq %r8 /* pt_regs->r8 */ - xorl %r8d, %r8d /* nospec r8 */ - pushq %r9 /* pt_regs->r9 */ - xorl %r9d, %r9d /* nospec r9 */ - pushq %r10 /* pt_regs->r10*/ - xorl %r10d, %r10d /* nospec r10 */ - pushq %r11 /* pt_regs->r11 */ - xorl %r11d, %r11d /* nospec r11 */ - pushq %rbx /* pt_regs->rbx */ - xorl %ebx, %ebx /* nospec rbx */ - pushq %rbp /* pt_regs->rbp */ - xorl %ebp, %ebp /* nospec rbp */ - pushq %r12 /* pt_regs->r12 */ - xorl %r12d, %r12d /* nospec r12 */ - pushq %r13 /* pt_regs->r13 */ - xorl %r13d, %r13d /* nospec r13 */ - pushq %r14 /* pt_regs->r14 */ - xorl %r14d, %r14d /* nospec r14 */ - pushq %r15 /* pt_regs->r15 */ - xorl %r15d, %r15d /* nospec r15 */ - + PUSH_AND_CLEAR_REGS rax=$-ENOSYS UNWIND_HINT_REGS cld diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile index 693f8b9031fb..c2a8b76ae0bc 100644 --- a/arch/x86/entry/vdso/Makefile +++ b/arch/x86/entry/vdso/Makefile @@ -91,7 +91,7 @@ ifneq ($(RETPOLINE_VDSO_CFLAGS),) endif endif -$(vobjs): KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_LTO) $(GCC_PLUGINS_CFLAGS) $(RETPOLINE_CFLAGS),$(KBUILD_CFLAGS)) $(CFL) +$(vobjs): KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_LTO) $(RANDSTRUCT_CFLAGS) $(GCC_PLUGINS_CFLAGS) $(RETPOLINE_CFLAGS),$(KBUILD_CFLAGS)) $(CFL) # # vDSO code runs in userspace and -pg doesn't help with profiling anyway. @@ -148,6 +148,7 @@ KBUILD_CFLAGS_32 := $(filter-out -m64,$(KBUILD_CFLAGS)) KBUILD_CFLAGS_32 := $(filter-out -mcmodel=kernel,$(KBUILD_CFLAGS_32)) KBUILD_CFLAGS_32 := $(filter-out -fno-pic,$(KBUILD_CFLAGS_32)) KBUILD_CFLAGS_32 := $(filter-out -mfentry,$(KBUILD_CFLAGS_32)) +KBUILD_CFLAGS_32 := $(filter-out $(RANDSTRUCT_CFLAGS),$(KBUILD_CFLAGS_32)) KBUILD_CFLAGS_32 := $(filter-out $(GCC_PLUGINS_CFLAGS),$(KBUILD_CFLAGS_32)) KBUILD_CFLAGS_32 := $(filter-out $(RETPOLINE_CFLAGS),$(KBUILD_CFLAGS_32)) KBUILD_CFLAGS_32 := $(filter-out $(CC_FLAGS_LTO),$(KBUILD_CFLAGS_32)) diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c index 235a5794296a..1000d457c332 100644 --- a/arch/x86/entry/vdso/vma.c +++ b/arch/x86/entry/vdso/vma.c @@ -438,7 +438,7 @@ bool arch_syscall_is_vdso_sigreturn(struct pt_regs *regs) static __init int vdso_setup(char *s) { vdso64_enabled = simple_strtoul(s, NULL, 0); - return 0; + return 1; } __setup("vdso=", vdso_setup); diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c index fd2ee9408e91..4af81df133ee 100644 --- a/arch/x86/entry/vsyscall/vsyscall_64.c +++ b/arch/x86/entry/vsyscall/vsyscall_64.c @@ -48,7 +48,7 @@ static enum { EMULATE, XONLY, NONE } vsyscall_mode __ro_after_init = #elif defined(CONFIG_LEGACY_VSYSCALL_XONLY) XONLY; #else - EMULATE; + #error VSYSCALL config is broken #endif static int __init vsyscall_setup(char *str) diff --git a/arch/x86/events/Kconfig b/arch/x86/events/Kconfig index d6cdfe631674..09c56965750a 100644 --- a/arch/x86/events/Kconfig +++ b/arch/x86/events/Kconfig @@ -44,4 +44,12 @@ config PERF_EVENTS_AMD_UNCORE To compile this driver as a module, choose M here: the module will be called 'amd-uncore'. + +config PERF_EVENTS_AMD_BRS + depends on PERF_EVENTS && CPU_SUP_AMD + bool "AMD Zen3 Branch Sampling support" + help + Enable AMD Zen3 branch sampling support (BRS) which samples up to + 16 consecutive taken branches in registers. + endmenu diff --git a/arch/x86/events/amd/Makefile b/arch/x86/events/amd/Makefile index 6cbe38d5fd9d..b9f5d4610256 100644 --- a/arch/x86/events/amd/Makefile +++ b/arch/x86/events/amd/Makefile @@ -1,5 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_CPU_SUP_AMD) += core.o +obj-$(CONFIG_PERF_EVENTS_AMD_BRS) += brs.o obj-$(CONFIG_PERF_EVENTS_AMD_POWER) += power.o obj-$(CONFIG_X86_LOCAL_APIC) += ibs.o obj-$(CONFIG_PERF_EVENTS_AMD_UNCORE) += amd-uncore.o diff --git a/arch/x86/events/amd/brs.c b/arch/x86/events/amd/brs.c new file mode 100644 index 000000000000..bee8765a1e9b --- /dev/null +++ b/arch/x86/events/amd/brs.c @@ -0,0 +1,367 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Implement support for AMD Fam19h Branch Sampling feature + * Based on specifications published in AMD PPR Fam19 Model 01 + * + * Copyright 2021 Google LLC + * Contributed by Stephane Eranian <eranian@google.com> + */ +#include <linux/kernel.h> +#include <linux/jump_label.h> +#include <asm/msr.h> +#include <asm/cpufeature.h> + +#include "../perf_event.h" + +#define BRS_POISON 0xFFFFFFFFFFFFFFFEULL /* mark limit of valid entries */ + +/* Debug Extension Configuration register layout */ +union amd_debug_extn_cfg { + __u64 val; + struct { + __u64 rsvd0:2, /* reserved */ + brsmen:1, /* branch sample enable */ + rsvd4_3:2,/* reserved - must be 0x3 */ + vb:1, /* valid branches recorded */ + rsvd2:10, /* reserved */ + msroff:4, /* index of next entry to write */ + rsvd3:4, /* reserved */ + pmc:3, /* #PMC holding the sampling event */ + rsvd4:37; /* reserved */ + }; +}; + +static inline unsigned int brs_from(int idx) +{ + return MSR_AMD_SAMP_BR_FROM + 2 * idx; +} + +static inline unsigned int brs_to(int idx) +{ + return MSR_AMD_SAMP_BR_FROM + 2 * idx + 1; +} + +static inline void set_debug_extn_cfg(u64 val) +{ + /* bits[4:3] must always be set to 11b */ + wrmsrl(MSR_AMD_DBG_EXTN_CFG, val | 3ULL << 3); +} + +static inline u64 get_debug_extn_cfg(void) +{ + u64 val; + + rdmsrl(MSR_AMD_DBG_EXTN_CFG, val); + return val; +} + +static bool __init amd_brs_detect(void) +{ + if (!cpu_feature_enabled(X86_FEATURE_BRS)) + return false; + + switch (boot_cpu_data.x86) { + case 0x19: /* AMD Fam19h (Zen3) */ + x86_pmu.lbr_nr = 16; + + /* No hardware filtering supported */ + x86_pmu.lbr_sel_map = NULL; + x86_pmu.lbr_sel_mask = 0; + break; + default: + return false; + } + + return true; +} + +/* + * Current BRS implementation does not support branch type or privilege level + * filtering. Therefore, this function simply enforces these limitations. No need for + * a br_sel_map. Software filtering is not supported because it would not correlate well + * with a sampling period. + */ +int amd_brs_setup_filter(struct perf_event *event) +{ + u64 type = event->attr.branch_sample_type; + + /* No BRS support */ + if (!x86_pmu.lbr_nr) + return -EOPNOTSUPP; + + /* Can only capture all branches, i.e., no filtering */ + if ((type & ~PERF_SAMPLE_BRANCH_PLM_ALL) != PERF_SAMPLE_BRANCH_ANY) + return -EINVAL; + + return 0; +} + +/* tos = top of stack, i.e., last valid entry written */ +static inline int amd_brs_get_tos(union amd_debug_extn_cfg *cfg) +{ + /* + * msroff: index of next entry to write so top-of-stack is one off + * if BRS is full then msroff is set back to 0. + */ + return (cfg->msroff ? cfg->msroff : x86_pmu.lbr_nr) - 1; +} + +/* + * make sure we have a sane BRS offset to begin with + * especially with kexec + */ +void amd_brs_reset(void) +{ + if (!cpu_feature_enabled(X86_FEATURE_BRS)) + return; + + /* + * Reset config + */ + set_debug_extn_cfg(0); + + /* + * Mark first entry as poisoned + */ + wrmsrl(brs_to(0), BRS_POISON); +} + +int __init amd_brs_init(void) +{ + if (!amd_brs_detect()) + return -EOPNOTSUPP; + + pr_cont("%d-deep BRS, ", x86_pmu.lbr_nr); + + return 0; +} + +void amd_brs_enable(void) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + union amd_debug_extn_cfg cfg; + + /* Activate only on first user */ + if (++cpuc->brs_active > 1) + return; + + cfg.val = 0; /* reset all fields */ + cfg.brsmen = 1; /* enable branch sampling */ + + /* Set enable bit */ + set_debug_extn_cfg(cfg.val); +} + +void amd_brs_enable_all(void) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + if (cpuc->lbr_users) + amd_brs_enable(); +} + +void amd_brs_disable(void) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + union amd_debug_extn_cfg cfg; + + /* Check if active (could be disabled via x86_pmu_disable_all()) */ + if (!cpuc->brs_active) + return; + + /* Only disable for last user */ + if (--cpuc->brs_active) + return; + + /* + * Clear the brsmen bit but preserve the others as they contain + * useful state such as vb and msroff + */ + cfg.val = get_debug_extn_cfg(); + + /* + * When coming in on interrupt and BRS is full, then hw will have + * already stopped BRS, no need to issue wrmsr again + */ + if (cfg.brsmen) { + cfg.brsmen = 0; + set_debug_extn_cfg(cfg.val); + } +} + +void amd_brs_disable_all(void) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + if (cpuc->lbr_users) + amd_brs_disable(); +} + +static bool amd_brs_match_plm(struct perf_event *event, u64 to) +{ + int type = event->attr.branch_sample_type; + int plm_k = PERF_SAMPLE_BRANCH_KERNEL | PERF_SAMPLE_BRANCH_HV; + int plm_u = PERF_SAMPLE_BRANCH_USER; + + if (!(type & plm_k) && kernel_ip(to)) + return 0; + + if (!(type & plm_u) && !kernel_ip(to)) + return 0; + + return 1; +} + +/* + * Caller must ensure amd_brs_inuse() is true before calling + * return: + */ +void amd_brs_drain(void) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + struct perf_event *event = cpuc->events[0]; + struct perf_branch_entry *br = cpuc->lbr_entries; + union amd_debug_extn_cfg cfg; + u32 i, nr = 0, num, tos, start; + u32 shift = 64 - boot_cpu_data.x86_virt_bits; + + /* + * BRS event forced on PMC0, + * so check if there is an event. + * It is possible to have lbr_users > 0 but the event + * not yet scheduled due to long latency PMU irq + */ + if (!event) + goto empty; + + cfg.val = get_debug_extn_cfg(); + + /* Sanity check [0-x86_pmu.lbr_nr] */ + if (WARN_ON_ONCE(cfg.msroff >= x86_pmu.lbr_nr)) + goto empty; + + /* No valid branch */ + if (cfg.vb == 0) + goto empty; + + /* + * msr.off points to next entry to be written + * tos = most recent entry index = msr.off - 1 + * BRS register buffer saturates, so we know we have + * start < tos and that we have to read from start to tos + */ + start = 0; + tos = amd_brs_get_tos(&cfg); + + num = tos - start + 1; + + /* + * BRS is only one pass (saturation) from MSROFF to depth-1 + * MSROFF wraps to zero when buffer is full + */ + for (i = 0; i < num; i++) { + u32 brs_idx = tos - i; + u64 from, to; + + rdmsrl(brs_to(brs_idx), to); + + /* Entry does not belong to us (as marked by kernel) */ + if (to == BRS_POISON) + break; + + /* + * Sign-extend SAMP_BR_TO to 64 bits, bits 61-63 are reserved. + * Necessary to generate proper virtual addresses suitable for + * symbolization + */ + to = (u64)(((s64)to << shift) >> shift); + + if (!amd_brs_match_plm(event, to)) + continue; + + rdmsrl(brs_from(brs_idx), from); + + perf_clear_branch_entry_bitfields(br+nr); + + br[nr].from = from; + br[nr].to = to; + + nr++; + } +empty: + /* Record number of sampled branches */ + cpuc->lbr_stack.nr = nr; +} + +/* + * Poison most recent entry to prevent reuse by next task + * required because BRS entry are not tagged by PID + */ +static void amd_brs_poison_buffer(void) +{ + union amd_debug_extn_cfg cfg; + unsigned int idx; + + /* Get current state */ + cfg.val = get_debug_extn_cfg(); + + /* idx is most recently written entry */ + idx = amd_brs_get_tos(&cfg); + + /* Poison target of entry */ + wrmsrl(brs_to(idx), BRS_POISON); +} + +/* + * On context switch in, we need to make sure no samples from previous user + * are left in the BRS. + * + * On ctxswin, sched_in = true, called after the PMU has started + * On ctxswout, sched_in = false, called before the PMU is stopped + */ +void amd_pmu_brs_sched_task(struct perf_event_context *ctx, bool sched_in) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + + /* no active users */ + if (!cpuc->lbr_users) + return; + + /* + * On context switch in, we need to ensure we do not use entries + * from previous BRS user on that CPU, so we poison the buffer as + * a faster way compared to resetting all entries. + */ + if (sched_in) + amd_brs_poison_buffer(); +} + +/* + * called from ACPI processor_idle.c or acpi_pad.c + * with interrupts disabled + */ +void perf_amd_brs_lopwr_cb(bool lopwr_in) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + union amd_debug_extn_cfg cfg; + + /* + * on mwait in, we may end up in non C0 state. + * we must disable branch sampling to avoid holding the NMI + * for too long. We disable it in hardware but we + * keep the state in cpuc, so we can re-enable. + * + * The hardware will deliver the NMI if needed when brsmen cleared + */ + if (cpuc->brs_active) { + cfg.val = get_debug_extn_cfg(); + cfg.brsmen = !lopwr_in; + set_debug_extn_cfg(cfg.val); + } +} + +DEFINE_STATIC_CALL_NULL(perf_lopwr_cb, perf_amd_brs_lopwr_cb); +EXPORT_STATIC_CALL_TRAMP_GPL(perf_lopwr_cb); + +void __init amd_brs_lopwr_init(void) +{ + static_call_update(perf_lopwr_cb, perf_amd_brs_lopwr_cb); +} diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c index 9687a8aef01c..9ac3718410ce 100644 --- a/arch/x86/events/amd/core.c +++ b/arch/x86/events/amd/core.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only #include <linux/perf_event.h> +#include <linux/jump_label.h> #include <linux/export.h> #include <linux/types.h> #include <linux/init.h> @@ -7,6 +8,7 @@ #include <linux/delay.h> #include <linux/jiffies.h> #include <asm/apicdef.h> +#include <asm/apic.h> #include <asm/nmi.h> #include "../perf_event.h" @@ -18,6 +20,9 @@ static unsigned long perf_nmi_window; #define AMD_MERGE_EVENT ((0xFULL << 32) | 0xFFULL) #define AMD_MERGE_EVENT_ENABLE (AMD_MERGE_EVENT | ARCH_PERFMON_EVENTSEL_ENABLE) +/* PMC Enable and Overflow bits for PerfCntrGlobal* registers */ +static u64 amd_pmu_global_cntr_mask __read_mostly; + static __initconst const u64 amd_hw_cache_event_ids [PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] @@ -325,8 +330,16 @@ static inline bool amd_is_pair_event_code(struct hw_perf_event *hwc) } } +#define AMD_FAM19H_BRS_EVENT 0xc4 /* RETIRED_TAKEN_BRANCH_INSTRUCTIONS */ +static inline int amd_is_brs_event(struct perf_event *e) +{ + return (e->hw.config & AMD64_RAW_EVENT_MASK) == AMD_FAM19H_BRS_EVENT; +} + static int amd_core_hw_config(struct perf_event *event) { + int ret = 0; + if (event->attr.exclude_host && event->attr.exclude_guest) /* * When HO == GO == 1 the hardware treats that as GO == HO == 0 @@ -343,7 +356,66 @@ static int amd_core_hw_config(struct perf_event *event) if ((x86_pmu.flags & PMU_FL_PAIR) && amd_is_pair_event_code(&event->hw)) event->hw.flags |= PERF_X86_EVENT_PAIR; - return 0; + /* + * if branch stack is requested + */ + if (has_branch_stack(event)) { + /* + * Due to interrupt holding, BRS is not recommended in + * counting mode. + */ + if (!is_sampling_event(event)) + return -EINVAL; + + /* + * Due to the way BRS operates by holding the interrupt until + * lbr_nr entries have been captured, it does not make sense + * to allow sampling on BRS with an event that does not match + * what BRS is capturing, i.e., retired taken branches. + * Otherwise the correlation with the event's period is even + * more loose: + * + * With retired taken branch: + * Effective P = P + 16 + X + * With any other event: + * Effective P = P + Y + X + * + * Where X is the number of taken branches due to interrupt + * skid. Skid is large. + * + * Where Y is the occurences of the event while BRS is + * capturing the lbr_nr entries. + * + * By using retired taken branches, we limit the impact on the + * Y variable. We know it cannot be more than the depth of + * BRS. + */ + if (!amd_is_brs_event(event)) + return -EINVAL; + + /* + * BRS implementation does not work with frequency mode + * reprogramming of the period. + */ + if (event->attr.freq) + return -EINVAL; + /* + * The kernel subtracts BRS depth from period, so it must + * be big enough. + */ + if (event->attr.sample_period <= x86_pmu.lbr_nr) + return -EINVAL; + + /* + * Check if we can allow PERF_SAMPLE_BRANCH_STACK + */ + ret = amd_brs_setup_filter(event); + + /* only set in case of success */ + if (!ret) + event->hw.flags |= PERF_X86_EVENT_AMD_BRS; + } + return ret; } static inline int amd_is_nb_event(struct hw_perf_event *hwc) @@ -366,7 +438,7 @@ static int amd_pmu_hw_config(struct perf_event *event) if (event->attr.precise_ip && get_ibs_caps()) return -ENOENT; - if (has_branch_stack(event)) + if (has_branch_stack(event) && !x86_pmu.lbr_nr) return -EOPNOTSUPP; ret = x86_pmu_hw_config(event); @@ -510,6 +582,18 @@ static struct amd_nb *amd_alloc_nb(int cpu) return nb; } +static void amd_pmu_cpu_reset(int cpu) +{ + if (x86_pmu.version < 2) + return; + + /* Clear enable bits i.e. PerfCntrGlobalCtl.PerfCntrEn */ + wrmsrl(MSR_AMD64_PERF_CNTR_GLOBAL_CTL, 0); + + /* Clear overflow bits i.e. PerfCntrGLobalStatus.PerfCntrOvfl */ + wrmsrl(MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR, amd_pmu_global_cntr_mask); +} + static int amd_pmu_cpu_prepare(int cpu) { struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu); @@ -555,6 +639,9 @@ static void amd_pmu_cpu_starting(int cpu) cpuc->amd_nb->nb_id = nb_id; cpuc->amd_nb->refcnt++; + + amd_brs_reset(); + amd_pmu_cpu_reset(cpu); } static void amd_pmu_cpu_dead(int cpu) @@ -574,8 +661,54 @@ static void amd_pmu_cpu_dead(int cpu) cpuhw->amd_nb = NULL; } + + amd_pmu_cpu_reset(cpu); +} + +static inline void amd_pmu_set_global_ctl(u64 ctl) +{ + wrmsrl(MSR_AMD64_PERF_CNTR_GLOBAL_CTL, ctl); } +static inline u64 amd_pmu_get_global_status(void) +{ + u64 status; + + /* PerfCntrGlobalStatus is read-only */ + rdmsrl(MSR_AMD64_PERF_CNTR_GLOBAL_STATUS, status); + + return status & amd_pmu_global_cntr_mask; +} + +static inline void amd_pmu_ack_global_status(u64 status) +{ + /* + * PerfCntrGlobalStatus is read-only but an overflow acknowledgment + * mechanism exists; writing 1 to a bit in PerfCntrGlobalStatusClr + * clears the same bit in PerfCntrGlobalStatus + */ + + /* Only allow modifications to PerfCntrGlobalStatus.PerfCntrOvfl */ + status &= amd_pmu_global_cntr_mask; + wrmsrl(MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR, status); +} + +static bool amd_pmu_test_overflow_topbit(int idx) +{ + u64 counter; + + rdmsrl(x86_pmu_event_addr(idx), counter); + + return !(counter & BIT_ULL(x86_pmu.cntval_bits - 1)); +} + +static bool amd_pmu_test_overflow_status(int idx) +{ + return amd_pmu_get_global_status() & BIT_ULL(idx); +} + +DEFINE_STATIC_CALL(amd_pmu_test_overflow, amd_pmu_test_overflow_topbit); + /* * When a PMC counter overflows, an NMI is used to process the event and * reset the counter. NMI latency can result in the counter being updated @@ -588,7 +721,6 @@ static void amd_pmu_cpu_dead(int cpu) static void amd_pmu_wait_on_overflow(int idx) { unsigned int i; - u64 counter; /* * Wait for the counter to be reset if it has overflowed. This loop @@ -596,8 +728,7 @@ static void amd_pmu_wait_on_overflow(int idx) * forever... */ for (i = 0; i < OVERFLOW_WAIT_COUNT; i++) { - rdmsrl(x86_pmu_event_addr(idx), counter); - if (counter & (1ULL << (x86_pmu.cntval_bits - 1))) + if (!static_call(amd_pmu_test_overflow)(idx)) break; /* Might be in IRQ context, so can't sleep */ @@ -605,13 +736,11 @@ static void amd_pmu_wait_on_overflow(int idx) } } -static void amd_pmu_disable_all(void) +static void amd_pmu_check_overflow(void) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); int idx; - x86_pmu_disable_all(); - /* * This shouldn't be called from NMI context, but add a safeguard here * to return, since if we're in NMI context we can't wait for an NMI @@ -634,6 +763,47 @@ static void amd_pmu_disable_all(void) } } +static void amd_pmu_enable_event(struct perf_event *event) +{ + x86_pmu_enable_event(event); +} + +static void amd_pmu_enable_all(int added) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + int idx; + + amd_brs_enable_all(); + + for (idx = 0; idx < x86_pmu.num_counters; idx++) { + /* only activate events which are marked as active */ + if (!test_bit(idx, cpuc->active_mask)) + continue; + + amd_pmu_enable_event(cpuc->events[idx]); + } +} + +static void amd_pmu_v2_enable_event(struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + + /* + * Testing cpu_hw_events.enabled should be skipped in this case unlike + * in x86_pmu_enable_event(). + * + * Since cpu_hw_events.enabled is set only after returning from + * x86_pmu_start(), the PMCs must be programmed and kept ready. + * Counting starts only after x86_pmu_enable_all() is called. + */ + __x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE); +} + +static void amd_pmu_v2_enable_all(int added) +{ + amd_pmu_set_global_ctl(amd_pmu_global_cntr_mask); +} + static void amd_pmu_disable_event(struct perf_event *event) { x86_pmu_disable_event(event); @@ -651,6 +821,32 @@ static void amd_pmu_disable_event(struct perf_event *event) amd_pmu_wait_on_overflow(event->hw.idx); } +static void amd_pmu_disable_all(void) +{ + amd_brs_disable_all(); + x86_pmu_disable_all(); + amd_pmu_check_overflow(); +} + +static void amd_pmu_v2_disable_all(void) +{ + /* Disable all PMCs */ + amd_pmu_set_global_ctl(0); + amd_pmu_check_overflow(); +} + +static void amd_pmu_add_event(struct perf_event *event) +{ + if (needs_branch_stack(event)) + amd_pmu_brs_add(event); +} + +static void amd_pmu_del_event(struct perf_event *event) +{ + if (needs_branch_stack(event)) + amd_pmu_brs_del(event); +} + /* * Because of NMI latency, if multiple PMC counters are active or other sources * of NMIs are received, the perf NMI handler can handle one or more overflowed @@ -669,13 +865,8 @@ static void amd_pmu_disable_event(struct perf_event *event) * handled a counter. When an un-handled NMI is received, it will be claimed * only if arriving within that window. */ -static int amd_pmu_handle_irq(struct pt_regs *regs) +static inline int amd_pmu_adjust_nmi_window(int handled) { - int handled; - - /* Process any counter overflows */ - handled = x86_pmu_handle_irq(regs); - /* * If a counter was handled, record a timestamp such that un-handled * NMIs will be claimed if arriving within that window. @@ -692,6 +883,113 @@ static int amd_pmu_handle_irq(struct pt_regs *regs) return NMI_HANDLED; } +static int amd_pmu_handle_irq(struct pt_regs *regs) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + int handled; + int pmu_enabled; + + /* + * Save the PMU state. + * It needs to be restored when leaving the handler. + */ + pmu_enabled = cpuc->enabled; + cpuc->enabled = 0; + + /* stop everything (includes BRS) */ + amd_pmu_disable_all(); + + /* Drain BRS is in use (could be inactive) */ + if (cpuc->lbr_users) + amd_brs_drain(); + + /* Process any counter overflows */ + handled = x86_pmu_handle_irq(regs); + + cpuc->enabled = pmu_enabled; + if (pmu_enabled) + amd_pmu_enable_all(0); + + return amd_pmu_adjust_nmi_window(handled); +} + +static int amd_pmu_v2_handle_irq(struct pt_regs *regs) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + struct perf_sample_data data; + struct hw_perf_event *hwc; + struct perf_event *event; + int handled = 0, idx; + u64 status, mask; + bool pmu_enabled; + + /* + * Save the PMU state as it needs to be restored when leaving the + * handler + */ + pmu_enabled = cpuc->enabled; + cpuc->enabled = 0; + + /* Stop counting */ + amd_pmu_v2_disable_all(); + + status = amd_pmu_get_global_status(); + + /* Check if any overflows are pending */ + if (!status) + goto done; + + for (idx = 0; idx < x86_pmu.num_counters; idx++) { + if (!test_bit(idx, cpuc->active_mask)) + continue; + + event = cpuc->events[idx]; + hwc = &event->hw; + x86_perf_event_update(event); + mask = BIT_ULL(idx); + + if (!(status & mask)) + continue; + + /* Event overflow */ + handled++; + perf_sample_data_init(&data, 0, hwc->last_period); + + if (!x86_perf_event_set_period(event)) + continue; + + if (perf_event_overflow(event, &data, regs)) + x86_pmu_stop(event, 0); + + status &= ~mask; + } + + /* + * It should never be the case that some overflows are not handled as + * the corresponding PMCs are expected to be inactive according to the + * active_mask + */ + WARN_ON(status > 0); + + /* Clear overflow bits */ + amd_pmu_ack_global_status(~status); + + /* + * Unmasking the LVTPC is not required as the Mask (M) bit of the LVT + * PMI entry is not set by the local APIC when a PMC overflow occurs + */ + inc_irq_stat(apic_perf_irqs); + +done: + cpuc->enabled = pmu_enabled; + + /* Resume counting only if PMU is active */ + if (pmu_enabled) + amd_pmu_v2_enable_all(0); + + return amd_pmu_adjust_nmi_window(handled); +} + static struct event_constraint * amd_get_event_constraints(struct cpu_hw_events *cpuc, int idx, struct perf_event *event) @@ -897,6 +1195,51 @@ static void amd_put_event_constraints_f17h(struct cpu_hw_events *cpuc, --cpuc->n_pair; } +/* + * Because of the way BRS operates with an inactive and active phases, and + * the link to one counter, it is not possible to have two events using BRS + * scheduled at the same time. There would be an issue with enforcing the + * period of each one and given that the BRS saturates, it would not be possible + * to guarantee correlated content for all events. Therefore, in situations + * where multiple events want to use BRS, the kernel enforces mutual exclusion. + * Exclusion is enforced by chosing only one counter for events using BRS. + * The event scheduling logic will then automatically multiplex the + * events and ensure that at most one event is actively using BRS. + * + * The BRS counter could be any counter, but there is no constraint on Fam19h, + * therefore all counters are equal and thus we pick the first one: PMC0 + */ +static struct event_constraint amd_fam19h_brs_cntr0_constraint = + EVENT_CONSTRAINT(0, 0x1, AMD64_RAW_EVENT_MASK); + +static struct event_constraint amd_fam19h_brs_pair_cntr0_constraint = + __EVENT_CONSTRAINT(0, 0x1, AMD64_RAW_EVENT_MASK, 1, 0, PERF_X86_EVENT_PAIR); + +static struct event_constraint * +amd_get_event_constraints_f19h(struct cpu_hw_events *cpuc, int idx, + struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + bool has_brs = has_amd_brs(hwc); + + /* + * In case BRS is used with an event requiring a counter pair, + * the kernel allows it but only on counter 0 & 1 to enforce + * multiplexing requiring to protect BRS in case of multiple + * BRS users + */ + if (amd_is_pair_event_code(hwc)) { + return has_brs ? &amd_fam19h_brs_pair_cntr0_constraint + : &pair_constraint; + } + + if (has_brs) + return &amd_fam19h_brs_cntr0_constraint; + + return &unconstrained; +} + + static ssize_t amd_event_sysfs_show(char *page, u64 config) { u64 event = (config & ARCH_PERFMON_EVENTSEL_EVENT) | @@ -905,12 +1248,31 @@ static ssize_t amd_event_sysfs_show(char *page, u64 config) return x86_event_sysfs_show(page, config, event); } +static void amd_pmu_sched_task(struct perf_event_context *ctx, + bool sched_in) +{ + if (sched_in && x86_pmu.lbr_nr) + amd_pmu_brs_sched_task(ctx, sched_in); +} + +static u64 amd_pmu_limit_period(struct perf_event *event, u64 left) +{ + /* + * Decrease period by the depth of the BRS feature to get the last N + * taken branches and approximate the desired period + */ + if (has_branch_stack(event) && left > x86_pmu.lbr_nr) + left -= x86_pmu.lbr_nr; + + return left; +} + static __initconst const struct x86_pmu amd_pmu = { .name = "AMD", .handle_irq = amd_pmu_handle_irq, .disable_all = amd_pmu_disable_all, - .enable_all = x86_pmu_enable_all, - .enable = x86_pmu_enable_event, + .enable_all = amd_pmu_enable_all, + .enable = amd_pmu_enable_event, .disable = amd_pmu_disable_event, .hw_config = amd_pmu_hw_config, .schedule_events = x86_schedule_events, @@ -920,6 +1282,8 @@ static __initconst const struct x86_pmu amd_pmu = { .event_map = amd_pmu_event_map, .max_events = ARRAY_SIZE(amd_perfmon_event_map), .num_counters = AMD64_NUM_COUNTERS, + .add = amd_pmu_add_event, + .del = amd_pmu_del_event, .cntval_bits = 48, .cntval_mask = (1ULL << 48) - 1, .apic = 1, @@ -938,8 +1302,55 @@ static __initconst const struct x86_pmu amd_pmu = { .amd_nb_constraints = 1, }; +static ssize_t branches_show(struct device *cdev, + struct device_attribute *attr, + char *buf) +{ + return snprintf(buf, PAGE_SIZE, "%d\n", x86_pmu.lbr_nr); +} + +static DEVICE_ATTR_RO(branches); + +static struct attribute *amd_pmu_brs_attrs[] = { + &dev_attr_branches.attr, + NULL, +}; + +static umode_t +amd_brs_is_visible(struct kobject *kobj, struct attribute *attr, int i) +{ + return x86_pmu.lbr_nr ? attr->mode : 0; +} + +static struct attribute_group group_caps_amd_brs = { + .name = "caps", + .attrs = amd_pmu_brs_attrs, + .is_visible = amd_brs_is_visible, +}; + +EVENT_ATTR_STR(branch-brs, amd_branch_brs, + "event=" __stringify(AMD_FAM19H_BRS_EVENT)"\n"); + +static struct attribute *amd_brs_events_attrs[] = { + EVENT_PTR(amd_branch_brs), + NULL, +}; + +static struct attribute_group group_events_amd_brs = { + .name = "events", + .attrs = amd_brs_events_attrs, + .is_visible = amd_brs_is_visible, +}; + +static const struct attribute_group *amd_attr_update[] = { + &group_caps_amd_brs, + &group_events_amd_brs, + NULL, +}; + static int __init amd_core_pmu_init(void) { + union cpuid_0x80000022_ebx ebx; u64 even_ctr_mask = 0ULL; int i; @@ -957,6 +1368,27 @@ static int __init amd_core_pmu_init(void) x86_pmu.eventsel = MSR_F15H_PERF_CTL; x86_pmu.perfctr = MSR_F15H_PERF_CTR; x86_pmu.num_counters = AMD64_NUM_COUNTERS_CORE; + + /* Check for Performance Monitoring v2 support */ + if (boot_cpu_has(X86_FEATURE_PERFMON_V2)) { + ebx.full = cpuid_ebx(EXT_PERFMON_DEBUG_FEATURES); + + /* Update PMU version for later usage */ + x86_pmu.version = 2; + + /* Find the number of available Core PMCs */ + x86_pmu.num_counters = ebx.split.num_core_pmc; + + amd_pmu_global_cntr_mask = (1ULL << x86_pmu.num_counters) - 1; + + /* Update PMC handling functions */ + x86_pmu.enable_all = amd_pmu_v2_enable_all; + x86_pmu.disable_all = amd_pmu_v2_disable_all; + x86_pmu.enable = amd_pmu_v2_enable_event; + x86_pmu.handle_irq = amd_pmu_v2_handle_irq; + static_call_update(amd_pmu_test_overflow, amd_pmu_test_overflow_status); + } + /* * AMD Core perfctr has separate MSRs for the NB events, see * the amd/uncore.c driver. @@ -989,6 +1421,23 @@ static int __init amd_core_pmu_init(void) x86_pmu.flags |= PMU_FL_PAIR; } + /* + * BRS requires special event constraints and flushing on ctxsw. + */ + if (boot_cpu_data.x86 >= 0x19 && !amd_brs_init()) { + x86_pmu.get_event_constraints = amd_get_event_constraints_f19h; + x86_pmu.sched_task = amd_pmu_sched_task; + x86_pmu.limit_period = amd_pmu_limit_period; + /* + * put_event_constraints callback same as Fam17h, set above + */ + + /* branch sampling must be stopped when entering low power */ + amd_brs_lopwr_init(); + } + + x86_pmu.attr_update = amd_attr_update; + pr_cont("core perfctr, "); return 0; } @@ -1023,6 +1472,24 @@ __init int amd_pmu_init(void) return 0; } +static inline void amd_pmu_reload_virt(void) +{ + if (x86_pmu.version >= 2) { + /* + * Clear global enable bits, reprogram the PERF_CTL + * registers with updated perf_ctr_virt_mask and then + * set global enable bits once again + */ + amd_pmu_v2_disable_all(); + amd_pmu_enable_all(0); + amd_pmu_v2_enable_all(0); + return; + } + + amd_pmu_disable_all(); + amd_pmu_enable_all(0); +} + void amd_pmu_enable_virt(void) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); @@ -1030,8 +1497,7 @@ void amd_pmu_enable_virt(void) cpuc->perf_ctr_virt_mask = 0; /* Reload all events */ - amd_pmu_disable_all(); - x86_pmu_enable_all(0); + amd_pmu_reload_virt(); } EXPORT_SYMBOL_GPL(amd_pmu_enable_virt); @@ -1048,7 +1514,6 @@ void amd_pmu_disable_virt(void) cpuc->perf_ctr_virt_mask = AMD64_EVENTSEL_HOSTONLY; /* Reload all events */ - amd_pmu_disable_all(); - x86_pmu_enable_all(0); + amd_pmu_reload_virt(); } EXPORT_SYMBOL_GPL(amd_pmu_disable_virt); diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c index 9739019d4b67..c251bc44c088 100644 --- a/arch/x86/events/amd/ibs.c +++ b/arch/x86/events/amd/ibs.c @@ -94,10 +94,6 @@ struct perf_ibs { unsigned int fetch_ignore_if_zero_rip : 1; struct cpu_perf_ibs __percpu *pcpu; - struct attribute **format_attrs; - struct attribute_group format_group; - const struct attribute_group *attr_groups[2]; - u64 (*get_count)(u64 config); }; @@ -304,6 +300,16 @@ static int perf_ibs_init(struct perf_event *event) hwc->config_base = perf_ibs->msr; hwc->config = config; + /* + * rip recorded by IbsOpRip will not be consistent with rsp and rbp + * recorded as part of interrupt regs. Thus we need to use rip from + * interrupt regs while unwinding call stack. Setting _EARLY flag + * makes sure we unwind call-stack before perf sample rip is set to + * IbsOpRip. + */ + if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) + event->attr.sample_type |= __PERF_SAMPLE_CALLCHAIN_EARLY; + return 0; } @@ -518,16 +524,118 @@ static void perf_ibs_del(struct perf_event *event, int flags) static void perf_ibs_read(struct perf_event *event) { } +/* + * We need to initialize with empty group if all attributes in the + * group are dynamic. + */ +static struct attribute *attrs_empty[] = { + NULL, +}; + +static struct attribute_group empty_format_group = { + .name = "format", + .attrs = attrs_empty, +}; + +static struct attribute_group empty_caps_group = { + .name = "caps", + .attrs = attrs_empty, +}; + +static const struct attribute_group *empty_attr_groups[] = { + &empty_format_group, + &empty_caps_group, + NULL, +}; + PMU_FORMAT_ATTR(rand_en, "config:57"); PMU_FORMAT_ATTR(cnt_ctl, "config:19"); +PMU_EVENT_ATTR_STRING(l3missonly, fetch_l3missonly, "config:59"); +PMU_EVENT_ATTR_STRING(l3missonly, op_l3missonly, "config:16"); +PMU_EVENT_ATTR_STRING(zen4_ibs_extensions, zen4_ibs_extensions, "1"); -static struct attribute *ibs_fetch_format_attrs[] = { +static umode_t +zen4_ibs_extensions_is_visible(struct kobject *kobj, struct attribute *attr, int i) +{ + return ibs_caps & IBS_CAPS_ZEN4 ? attr->mode : 0; +} + +static struct attribute *rand_en_attrs[] = { &format_attr_rand_en.attr, NULL, }; -static struct attribute *ibs_op_format_attrs[] = { - NULL, /* &format_attr_cnt_ctl.attr if IBS_CAPS_OPCNT */ +static struct attribute *fetch_l3missonly_attrs[] = { + &fetch_l3missonly.attr.attr, + NULL, +}; + +static struct attribute *zen4_ibs_extensions_attrs[] = { + &zen4_ibs_extensions.attr.attr, + NULL, +}; + +static struct attribute_group group_rand_en = { + .name = "format", + .attrs = rand_en_attrs, +}; + +static struct attribute_group group_fetch_l3missonly = { + .name = "format", + .attrs = fetch_l3missonly_attrs, + .is_visible = zen4_ibs_extensions_is_visible, +}; + +static struct attribute_group group_zen4_ibs_extensions = { + .name = "caps", + .attrs = zen4_ibs_extensions_attrs, + .is_visible = zen4_ibs_extensions_is_visible, +}; + +static const struct attribute_group *fetch_attr_groups[] = { + &group_rand_en, + &empty_caps_group, + NULL, +}; + +static const struct attribute_group *fetch_attr_update[] = { + &group_fetch_l3missonly, + &group_zen4_ibs_extensions, + NULL, +}; + +static umode_t +cnt_ctl_is_visible(struct kobject *kobj, struct attribute *attr, int i) +{ + return ibs_caps & IBS_CAPS_OPCNT ? attr->mode : 0; +} + +static struct attribute *cnt_ctl_attrs[] = { + &format_attr_cnt_ctl.attr, + NULL, +}; + +static struct attribute *op_l3missonly_attrs[] = { + &op_l3missonly.attr.attr, + NULL, +}; + +static struct attribute_group group_cnt_ctl = { + .name = "format", + .attrs = cnt_ctl_attrs, + .is_visible = cnt_ctl_is_visible, +}; + +static struct attribute_group group_op_l3missonly = { + .name = "format", + .attrs = op_l3missonly_attrs, + .is_visible = zen4_ibs_extensions_is_visible, +}; + +static const struct attribute_group *op_attr_update[] = { + &group_cnt_ctl, + &group_op_l3missonly, + &group_zen4_ibs_extensions, NULL, }; @@ -551,7 +659,6 @@ static struct perf_ibs perf_ibs_fetch = { .max_period = IBS_FETCH_MAX_CNT << 4, .offset_mask = { MSR_AMD64_IBSFETCH_REG_MASK }, .offset_max = MSR_AMD64_IBSFETCH_REG_COUNT, - .format_attrs = ibs_fetch_format_attrs, .get_count = get_ibs_fetch_count, }; @@ -577,7 +684,6 @@ static struct perf_ibs perf_ibs_op = { .max_period = IBS_OP_MAX_CNT << 4, .offset_mask = { MSR_AMD64_IBSOP_REG_MASK }, .offset_max = MSR_AMD64_IBSOP_REG_COUNT, - .format_attrs = ibs_op_format_attrs, .get_count = get_ibs_op_count, }; @@ -687,6 +793,14 @@ fail: data.raw = &raw; } + /* + * rip recorded by IbsOpRip will not be consistent with rsp and rbp + * recorded as part of interrupt regs. Thus we need to use rip from + * interrupt regs while unwinding call stack. + */ + if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) + data.callchain = perf_callchain(event, iregs); + throttle = perf_event_overflow(event, &data, ®s); out: if (throttle) { @@ -739,17 +853,6 @@ static __init int perf_ibs_pmu_init(struct perf_ibs *perf_ibs, char *name) perf_ibs->pcpu = pcpu; - /* register attributes */ - if (perf_ibs->format_attrs[0]) { - memset(&perf_ibs->format_group, 0, sizeof(perf_ibs->format_group)); - perf_ibs->format_group.name = "format"; - perf_ibs->format_group.attrs = perf_ibs->format_attrs; - - memset(&perf_ibs->attr_groups, 0, sizeof(perf_ibs->attr_groups)); - perf_ibs->attr_groups[0] = &perf_ibs->format_group; - perf_ibs->pmu.attr_groups = perf_ibs->attr_groups; - } - ret = perf_pmu_register(&perf_ibs->pmu, name, -1); if (ret) { perf_ibs->pcpu = NULL; @@ -759,10 +862,8 @@ static __init int perf_ibs_pmu_init(struct perf_ibs *perf_ibs, char *name) return ret; } -static __init void perf_event_ibs_init(void) +static __init int perf_ibs_fetch_init(void) { - struct attribute **attr = ibs_op_format_attrs; - /* * Some chips fail to reset the fetch count when it is written; instead * they need a 0-1 transition of IbsFetchEn. @@ -773,12 +874,19 @@ static __init void perf_event_ibs_init(void) if (boot_cpu_data.x86 == 0x19 && boot_cpu_data.x86_model < 0x10) perf_ibs_fetch.fetch_ignore_if_zero_rip = 1; - perf_ibs_pmu_init(&perf_ibs_fetch, "ibs_fetch"); + if (ibs_caps & IBS_CAPS_ZEN4) + perf_ibs_fetch.config_mask |= IBS_FETCH_L3MISSONLY; + + perf_ibs_fetch.pmu.attr_groups = fetch_attr_groups; + perf_ibs_fetch.pmu.attr_update = fetch_attr_update; - if (ibs_caps & IBS_CAPS_OPCNT) { + return perf_ibs_pmu_init(&perf_ibs_fetch, "ibs_fetch"); +} + +static __init int perf_ibs_op_init(void) +{ + if (ibs_caps & IBS_CAPS_OPCNT) perf_ibs_op.config_mask |= IBS_OP_CNT_CTL; - *attr++ = &format_attr_cnt_ctl.attr; - } if (ibs_caps & IBS_CAPS_OPCNTEXT) { perf_ibs_op.max_period |= IBS_OP_MAX_CNT_EXT_MASK; @@ -786,15 +894,52 @@ static __init void perf_event_ibs_init(void) perf_ibs_op.cnt_mask |= IBS_OP_MAX_CNT_EXT_MASK; } - perf_ibs_pmu_init(&perf_ibs_op, "ibs_op"); + if (ibs_caps & IBS_CAPS_ZEN4) + perf_ibs_op.config_mask |= IBS_OP_L3MISSONLY; + + perf_ibs_op.pmu.attr_groups = empty_attr_groups; + perf_ibs_op.pmu.attr_update = op_attr_update; + + return perf_ibs_pmu_init(&perf_ibs_op, "ibs_op"); +} + +static __init int perf_event_ibs_init(void) +{ + int ret; + + ret = perf_ibs_fetch_init(); + if (ret) + return ret; + + ret = perf_ibs_op_init(); + if (ret) + goto err_op; + + ret = register_nmi_handler(NMI_LOCAL, perf_ibs_nmi_handler, 0, "perf_ibs"); + if (ret) + goto err_nmi; - register_nmi_handler(NMI_LOCAL, perf_ibs_nmi_handler, 0, "perf_ibs"); pr_info("perf: AMD IBS detected (0x%08x)\n", ibs_caps); + return 0; + +err_nmi: + perf_pmu_unregister(&perf_ibs_op.pmu); + free_percpu(perf_ibs_op.pcpu); + perf_ibs_op.pcpu = NULL; +err_op: + perf_pmu_unregister(&perf_ibs_fetch.pmu); + free_percpu(perf_ibs_fetch.pcpu); + perf_ibs_fetch.pcpu = NULL; + + return ret; } #else /* defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_AMD) */ -static __init void perf_event_ibs_init(void) { } +static __init int perf_event_ibs_init(void) +{ + return 0; +} #endif @@ -1064,9 +1209,7 @@ static __init int amd_ibs_init(void) x86_pmu_amd_ibs_starting_cpu, x86_pmu_amd_ibs_dying_cpu); - perf_event_ibs_init(); - - return 0; + return perf_event_ibs_init(); } /* Since we need the pci subsystem to init ibs we can't do this earlier: */ diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index eef816fc216d..30788894124f 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -1338,6 +1338,10 @@ static void x86_pmu_enable(struct pmu *pmu) if (hwc->state & PERF_HES_ARCH) continue; + /* + * if cpuc->enabled = 0, then no wrmsr as + * per x86_pmu_enable_event() + */ x86_pmu_start(event, PERF_EF_RELOAD); } cpuc->n_added = 0; @@ -1704,11 +1708,15 @@ int x86_pmu_handle_irq(struct pt_regs *regs) * event overflow */ handled++; - perf_sample_data_init(&data, 0, event->hw.last_period); if (!x86_perf_event_set_period(event)) continue; + perf_sample_data_init(&data, 0, event->hw.last_period); + + if (has_branch_stack(event)) + data.br_stack = &cpuc->lbr_stack; + if (perf_event_overflow(event, &data, regs)) x86_pmu_stop(event, 0); } @@ -1837,7 +1845,7 @@ ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr, cha /* string trumps id */ if (pmu_attr->event_str) - return sprintf(page, "%s", pmu_attr->event_str); + return sprintf(page, "%s\n", pmu_attr->event_str); return x86_pmu.events_sysfs_show(page, config); } diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index e88791b420ee..955ae91c56dc 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -302,7 +302,7 @@ static struct extra_reg intel_spr_extra_regs[] __read_mostly = { INTEL_UEVENT_EXTRA_REG(0x012a, MSR_OFFCORE_RSP_0, 0x3fffffffffull, RSP_0), INTEL_UEVENT_EXTRA_REG(0x012b, MSR_OFFCORE_RSP_1, 0x3fffffffffull, RSP_1), INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd), - INTEL_UEVENT_EXTRA_REG(0x01c6, MSR_PEBS_FRONTEND, 0x7fff17, FE), + INTEL_UEVENT_EXTRA_REG(0x01c6, MSR_PEBS_FRONTEND, 0x7fff1f, FE), INTEL_UEVENT_EXTRA_REG(0x40ad, MSR_PEBS_FRONTEND, 0x7, FE), INTEL_UEVENT_EXTRA_REG(0x04c2, MSR_PEBS_FRONTEND, 0x8, FE), EVENT_EXTRA_END @@ -5536,7 +5536,11 @@ static void intel_pmu_check_event_constraints(struct event_constraint *event_con /* Disabled fixed counters which are not in CPUID */ c->idxmsk64 &= intel_ctrl; - if (c->idxmsk64 != INTEL_PMC_MSK_FIXED_REF_CYCLES) + /* + * Don't extend the pseudo-encoding to the + * generic counters + */ + if (!use_fixed_pseudo_encoding(c->code)) c->idxmsk64 |= (1ULL << num_counters) - 1; } c->idxmsk64 &= @@ -6212,6 +6216,9 @@ __init int intel_pmu_init(void) case INTEL_FAM6_ALDERLAKE: case INTEL_FAM6_ALDERLAKE_L: + case INTEL_FAM6_ALDERLAKE_N: + case INTEL_FAM6_RAPTORLAKE: + case INTEL_FAM6_RAPTORLAKE_P: /* * Alder Lake has 2 types of CPU, core and atom. * diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index c6262b154c3a..8ec23f47fee9 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -40,7 +40,7 @@ * Model specific counters: * MSR_CORE_C1_RES: CORE C1 Residency Counter * perf code: 0x00 - * Available model: SLM,AMT,GLM,CNL,ICX,TNT,ADL + * Available model: SLM,AMT,GLM,CNL,ICX,TNT,ADL,RPL * Scope: Core (each processor core has a MSR) * MSR_CORE_C3_RESIDENCY: CORE C3 Residency Counter * perf code: 0x01 @@ -51,49 +51,50 @@ * perf code: 0x02 * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW, * SKL,KNL,GLM,CNL,KBL,CML,ICL,ICX, - * TGL,TNT,RKL,ADL + * TGL,TNT,RKL,ADL,RPL,SPR * Scope: Core * MSR_CORE_C7_RESIDENCY: CORE C7 Residency Counter * perf code: 0x03 * Available model: SNB,IVB,HSW,BDW,SKL,CNL,KBL,CML, - * ICL,TGL,RKL,ADL + * ICL,TGL,RKL,ADL,RPL * Scope: Core * MSR_PKG_C2_RESIDENCY: Package C2 Residency Counter. * perf code: 0x00 * Available model: SNB,IVB,HSW,BDW,SKL,KNL,GLM,CNL, - * KBL,CML,ICL,ICX,TGL,TNT,RKL,ADL + * KBL,CML,ICL,ICX,TGL,TNT,RKL,ADL, + * RPL,SPR * Scope: Package (physical package) * MSR_PKG_C3_RESIDENCY: Package C3 Residency Counter. * perf code: 0x01 * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,KNL, * GLM,CNL,KBL,CML,ICL,TGL,TNT,RKL, - * ADL + * ADL,RPL * Scope: Package (physical package) * MSR_PKG_C6_RESIDENCY: Package C6 Residency Counter. * perf code: 0x02 * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW, * SKL,KNL,GLM,CNL,KBL,CML,ICL,ICX, - * TGL,TNT,RKL,ADL + * TGL,TNT,RKL,ADL,RPL,SPR * Scope: Package (physical package) * MSR_PKG_C7_RESIDENCY: Package C7 Residency Counter. * perf code: 0x03 * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,CNL, - * KBL,CML,ICL,TGL,RKL,ADL + * KBL,CML,ICL,TGL,RKL,ADL,RPL * Scope: Package (physical package) * MSR_PKG_C8_RESIDENCY: Package C8 Residency Counter. * perf code: 0x04 * Available model: HSW ULT,KBL,CNL,CML,ICL,TGL,RKL, - * ADL + * ADL,RPL * Scope: Package (physical package) * MSR_PKG_C9_RESIDENCY: Package C9 Residency Counter. * perf code: 0x05 * Available model: HSW ULT,KBL,CNL,CML,ICL,TGL,RKL, - * ADL + * ADL,RPL * Scope: Package (physical package) * MSR_PKG_C10_RESIDENCY: Package C10 Residency Counter. * perf code: 0x06 * Available model: HSW ULT,KBL,GLM,CNL,CML,ICL,TGL, - * TNT,RKL,ADL + * TNT,RKL,ADL,RPL * Scope: Package (physical package) * */ @@ -674,12 +675,16 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(ICELAKE, &icl_cstates), X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X, &icx_cstates), X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_D, &icx_cstates), + X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &icx_cstates), X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE_L, &icl_cstates), X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE, &icl_cstates), X86_MATCH_INTEL_FAM6_MODEL(ROCKETLAKE, &icl_cstates), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE, &adl_cstates), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, &adl_cstates), + X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_N, &adl_cstates), + X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE, &adl_cstates), + X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P, &adl_cstates), { }, }; MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match); diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index fe1742c4ca49..13179f31fe10 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -769,6 +769,7 @@ void intel_pmu_lbr_disable_all(void) void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc) { unsigned long mask = x86_pmu.lbr_nr - 1; + struct perf_branch_entry *br = cpuc->lbr_entries; u64 tos = intel_pmu_lbr_tos(); int i; @@ -784,15 +785,11 @@ void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc) rdmsrl(x86_pmu.lbr_from + lbr_idx, msr_lastbranch.lbr); - cpuc->lbr_entries[i].from = msr_lastbranch.from; - cpuc->lbr_entries[i].to = msr_lastbranch.to; - cpuc->lbr_entries[i].mispred = 0; - cpuc->lbr_entries[i].predicted = 0; - cpuc->lbr_entries[i].in_tx = 0; - cpuc->lbr_entries[i].abort = 0; - cpuc->lbr_entries[i].cycles = 0; - cpuc->lbr_entries[i].type = 0; - cpuc->lbr_entries[i].reserved = 0; + perf_clear_branch_entry_bitfields(br); + + br->from = msr_lastbranch.from; + br->to = msr_lastbranch.to; + br++; } cpuc->lbr_stack.nr = i; cpuc->lbr_stack.hw_idx = tos; @@ -807,6 +804,7 @@ void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc) { bool need_info = false, call_stack = false; unsigned long mask = x86_pmu.lbr_nr - 1; + struct perf_branch_entry *br = cpuc->lbr_entries; u64 tos = intel_pmu_lbr_tos(); int i; int out = 0; @@ -878,15 +876,14 @@ void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc) if (abort && x86_pmu.lbr_double_abort && out > 0) out--; - cpuc->lbr_entries[out].from = from; - cpuc->lbr_entries[out].to = to; - cpuc->lbr_entries[out].mispred = mis; - cpuc->lbr_entries[out].predicted = pred; - cpuc->lbr_entries[out].in_tx = in_tx; - cpuc->lbr_entries[out].abort = abort; - cpuc->lbr_entries[out].cycles = cycles; - cpuc->lbr_entries[out].type = 0; - cpuc->lbr_entries[out].reserved = 0; + perf_clear_branch_entry_bitfields(br+out); + br[out].from = from; + br[out].to = to; + br[out].mispred = mis; + br[out].predicted = pred; + br[out].in_tx = in_tx; + br[out].abort = abort; + br[out].cycles = cycles; out++; } cpuc->lbr_stack.nr = out; @@ -951,6 +948,8 @@ static void intel_pmu_store_lbr(struct cpu_hw_events *cpuc, to = rdlbr_to(i, lbr); info = rdlbr_info(i, lbr); + perf_clear_branch_entry_bitfields(e); + e->from = from; e->to = to; e->mispred = get_lbr_mispred(info); @@ -959,7 +958,6 @@ static void intel_pmu_store_lbr(struct cpu_hw_events *cpuc, e->abort = !!(info & LBR_INFO_ABORT); e->cycles = get_lbr_cycles(info); e->type = get_lbr_br_type(info); - e->reserved = 0; } cpuc->lbr_stack.nr = i; diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index e497da9bf427..db6c31bca809 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -1828,6 +1828,9 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(ROCKETLAKE, &rkl_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE, &adl_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, &adl_uncore_init), + X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_N, &adl_uncore_init), + X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE, &adl_uncore_init), + X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P, &adl_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &spr_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D, &snr_uncore_init), {}, diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c index f698a55bde81..ce440011cc4e 100644 --- a/arch/x86/events/intel/uncore_snb.c +++ b/arch/x86/events/intel/uncore_snb.c @@ -79,6 +79,43 @@ #define PCI_DEVICE_ID_INTEL_ADL_14_IMC 0x4650 #define PCI_DEVICE_ID_INTEL_ADL_15_IMC 0x4668 #define PCI_DEVICE_ID_INTEL_ADL_16_IMC 0x4670 +#define PCI_DEVICE_ID_INTEL_ADL_17_IMC 0x4614 +#define PCI_DEVICE_ID_INTEL_ADL_18_IMC 0x4617 +#define PCI_DEVICE_ID_INTEL_ADL_19_IMC 0x4618 +#define PCI_DEVICE_ID_INTEL_ADL_20_IMC 0x461B +#define PCI_DEVICE_ID_INTEL_ADL_21_IMC 0x461C +#define PCI_DEVICE_ID_INTEL_RPL_1_IMC 0xA700 +#define PCI_DEVICE_ID_INTEL_RPL_2_IMC 0xA702 +#define PCI_DEVICE_ID_INTEL_RPL_3_IMC 0xA706 +#define PCI_DEVICE_ID_INTEL_RPL_4_IMC 0xA709 +#define PCI_DEVICE_ID_INTEL_RPL_5_IMC 0xA701 +#define PCI_DEVICE_ID_INTEL_RPL_6_IMC 0xA703 +#define PCI_DEVICE_ID_INTEL_RPL_7_IMC 0xA704 +#define PCI_DEVICE_ID_INTEL_RPL_8_IMC 0xA705 +#define PCI_DEVICE_ID_INTEL_RPL_9_IMC 0xA706 +#define PCI_DEVICE_ID_INTEL_RPL_10_IMC 0xA707 +#define PCI_DEVICE_ID_INTEL_RPL_11_IMC 0xA708 +#define PCI_DEVICE_ID_INTEL_RPL_12_IMC 0xA709 +#define PCI_DEVICE_ID_INTEL_RPL_13_IMC 0xA70a +#define PCI_DEVICE_ID_INTEL_RPL_14_IMC 0xA70b +#define PCI_DEVICE_ID_INTEL_RPL_15_IMC 0xA715 +#define PCI_DEVICE_ID_INTEL_RPL_16_IMC 0xA716 +#define PCI_DEVICE_ID_INTEL_RPL_17_IMC 0xA717 +#define PCI_DEVICE_ID_INTEL_RPL_18_IMC 0xA718 +#define PCI_DEVICE_ID_INTEL_RPL_19_IMC 0xA719 +#define PCI_DEVICE_ID_INTEL_RPL_20_IMC 0xA71A +#define PCI_DEVICE_ID_INTEL_RPL_21_IMC 0xA71B +#define PCI_DEVICE_ID_INTEL_RPL_22_IMC 0xA71C +#define PCI_DEVICE_ID_INTEL_RPL_23_IMC 0xA728 +#define PCI_DEVICE_ID_INTEL_RPL_24_IMC 0xA729 +#define PCI_DEVICE_ID_INTEL_RPL_25_IMC 0xA72A + + +#define IMC_UNCORE_DEV(a) \ +{ \ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_##a##_IMC), \ + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), \ +} /* SNB event control */ #define SNB_UNC_CTL_EV_SEL_MASK 0x000000ff @@ -845,242 +882,80 @@ static struct intel_uncore_type *snb_pci_uncores[] = { }; static const struct pci_device_id snb_uncore_pci_ids[] = { - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SNB_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, + IMC_UNCORE_DEV(SNB), { /* end: all zeroes */ }, }; static const struct pci_device_id ivb_uncore_pci_ids[] = { - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IVB_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IVB_E3_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, + IMC_UNCORE_DEV(IVB), + IMC_UNCORE_DEV(IVB_E3), { /* end: all zeroes */ }, }; static const struct pci_device_id hsw_uncore_pci_ids[] = { - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_HSW_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_HSW_U_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, + IMC_UNCORE_DEV(HSW), + IMC_UNCORE_DEV(HSW_U), { /* end: all zeroes */ }, }; static const struct pci_device_id bdw_uncore_pci_ids[] = { - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_BDW_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, + IMC_UNCORE_DEV(BDW), { /* end: all zeroes */ }, }; static const struct pci_device_id skl_uncore_pci_ids[] = { - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_Y_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_U_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_HD_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_HQ_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_SD_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_SQ_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_E3_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBL_Y_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBL_U_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBL_UQ_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBL_SD_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBL_SQ_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBL_HQ_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBL_WQ_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_2U_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_4U_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_4H_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_6H_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_2S_D_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_4S_D_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_6S_D_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_8S_D_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_4S_W_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_6S_W_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_8S_W_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_4S_S_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_6S_S_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_8S_S_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_AML_YD_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_AML_YQ_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_WHL_UQ_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_WHL_4_UQ_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_WHL_UD_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CML_H1_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CML_H2_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CML_H3_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CML_U1_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CML_U2_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CML_U3_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CML_S1_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CML_S2_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CML_S3_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CML_S4_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CML_S5_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, + IMC_UNCORE_DEV(SKL_Y), + IMC_UNCORE_DEV(SKL_U), + IMC_UNCORE_DEV(SKL_HD), + IMC_UNCORE_DEV(SKL_HQ), + IMC_UNCORE_DEV(SKL_SD), + IMC_UNCORE_DEV(SKL_SQ), + IMC_UNCORE_DEV(SKL_E3), + IMC_UNCORE_DEV(KBL_Y), + IMC_UNCORE_DEV(KBL_U), + IMC_UNCORE_DEV(KBL_UQ), + IMC_UNCORE_DEV(KBL_SD), + IMC_UNCORE_DEV(KBL_SQ), + IMC_UNCORE_DEV(KBL_HQ), + IMC_UNCORE_DEV(KBL_WQ), + IMC_UNCORE_DEV(CFL_2U), + IMC_UNCORE_DEV(CFL_4U), + IMC_UNCORE_DEV(CFL_4H), + IMC_UNCORE_DEV(CFL_6H), + IMC_UNCORE_DEV(CFL_2S_D), + IMC_UNCORE_DEV(CFL_4S_D), + IMC_UNCORE_DEV(CFL_6S_D), + IMC_UNCORE_DEV(CFL_8S_D), + IMC_UNCORE_DEV(CFL_4S_W), + IMC_UNCORE_DEV(CFL_6S_W), + IMC_UNCORE_DEV(CFL_8S_W), + IMC_UNCORE_DEV(CFL_4S_S), + IMC_UNCORE_DEV(CFL_6S_S), + IMC_UNCORE_DEV(CFL_8S_S), + IMC_UNCORE_DEV(AML_YD), + IMC_UNCORE_DEV(AML_YQ), + IMC_UNCORE_DEV(WHL_UQ), + IMC_UNCORE_DEV(WHL_4_UQ), + IMC_UNCORE_DEV(WHL_UD), + IMC_UNCORE_DEV(CML_H1), + IMC_UNCORE_DEV(CML_H2), + IMC_UNCORE_DEV(CML_H3), + IMC_UNCORE_DEV(CML_U1), + IMC_UNCORE_DEV(CML_U2), + IMC_UNCORE_DEV(CML_U3), + IMC_UNCORE_DEV(CML_S1), + IMC_UNCORE_DEV(CML_S2), + IMC_UNCORE_DEV(CML_S3), + IMC_UNCORE_DEV(CML_S4), + IMC_UNCORE_DEV(CML_S5), { /* end: all zeroes */ }, }; static const struct pci_device_id icl_uncore_pci_ids[] = { - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICL_U_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICL_U2_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_RKL_1_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_RKL_2_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, + IMC_UNCORE_DEV(ICL_U), + IMC_UNCORE_DEV(ICL_U2), + IMC_UNCORE_DEV(RKL_1), + IMC_UNCORE_DEV(RKL_2), { /* end: all zeroes */ }, }; @@ -1322,90 +1197,57 @@ void nhm_uncore_cpu_init(void) /* Tiger Lake MMIO uncore support */ static const struct pci_device_id tgl_uncore_pci_ids[] = { - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_TGL_U1_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_TGL_U2_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_TGL_U3_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_TGL_U4_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_TGL_H_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_1_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_2_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_3_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_4_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_5_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_6_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_7_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_8_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_9_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_10_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_11_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_12_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_13_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_14_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_15_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_16_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, + IMC_UNCORE_DEV(TGL_U1), + IMC_UNCORE_DEV(TGL_U2), + IMC_UNCORE_DEV(TGL_U3), + IMC_UNCORE_DEV(TGL_U4), + IMC_UNCORE_DEV(TGL_H), + IMC_UNCORE_DEV(ADL_1), + IMC_UNCORE_DEV(ADL_2), + IMC_UNCORE_DEV(ADL_3), + IMC_UNCORE_DEV(ADL_4), + IMC_UNCORE_DEV(ADL_5), + IMC_UNCORE_DEV(ADL_6), + IMC_UNCORE_DEV(ADL_7), + IMC_UNCORE_DEV(ADL_8), + IMC_UNCORE_DEV(ADL_9), + IMC_UNCORE_DEV(ADL_10), + IMC_UNCORE_DEV(ADL_11), + IMC_UNCORE_DEV(ADL_12), + IMC_UNCORE_DEV(ADL_13), + IMC_UNCORE_DEV(ADL_14), + IMC_UNCORE_DEV(ADL_15), + IMC_UNCORE_DEV(ADL_16), + IMC_UNCORE_DEV(ADL_17), + IMC_UNCORE_DEV(ADL_18), + IMC_UNCORE_DEV(ADL_19), + IMC_UNCORE_DEV(ADL_20), + IMC_UNCORE_DEV(ADL_21), + IMC_UNCORE_DEV(RPL_1), + IMC_UNCORE_DEV(RPL_2), + IMC_UNCORE_DEV(RPL_3), + IMC_UNCORE_DEV(RPL_4), + IMC_UNCORE_DEV(RPL_5), + IMC_UNCORE_DEV(RPL_6), + IMC_UNCORE_DEV(RPL_7), + IMC_UNCORE_DEV(RPL_8), + IMC_UNCORE_DEV(RPL_9), + IMC_UNCORE_DEV(RPL_10), + IMC_UNCORE_DEV(RPL_11), + IMC_UNCORE_DEV(RPL_12), + IMC_UNCORE_DEV(RPL_13), + IMC_UNCORE_DEV(RPL_14), + IMC_UNCORE_DEV(RPL_15), + IMC_UNCORE_DEV(RPL_16), + IMC_UNCORE_DEV(RPL_17), + IMC_UNCORE_DEV(RPL_18), + IMC_UNCORE_DEV(RPL_19), + IMC_UNCORE_DEV(RPL_20), + IMC_UNCORE_DEV(RPL_21), + IMC_UNCORE_DEV(RPL_22), + IMC_UNCORE_DEV(RPL_23), + IMC_UNCORE_DEV(RPL_24), + IMC_UNCORE_DEV(RPL_25), { /* end: all zeroes */ } }; diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c index 96c775abe31f..ac542f98c070 100644 --- a/arch/x86/events/msr.c +++ b/arch/x86/events/msr.c @@ -103,6 +103,9 @@ static bool test_intel(int idx, void *data) case INTEL_FAM6_ROCKETLAKE: case INTEL_FAM6_ALDERLAKE: case INTEL_FAM6_ALDERLAKE_L: + case INTEL_FAM6_ALDERLAKE_N: + case INTEL_FAM6_RAPTORLAKE: + case INTEL_FAM6_RAPTORLAKE_P: if (idx == PERF_MSR_SMI || idx == PERF_MSR_PPERF) return true; break; diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index 150261d929b9..21a5482bcf84 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -67,22 +67,23 @@ static inline bool constraint_match(struct event_constraint *c, u64 ecode) /* * struct hw_perf_event.flags flags */ -#define PERF_X86_EVENT_PEBS_LDLAT 0x0001 /* ld+ldlat data address sampling */ -#define PERF_X86_EVENT_PEBS_ST 0x0002 /* st data address sampling */ -#define PERF_X86_EVENT_PEBS_ST_HSW 0x0004 /* haswell style datala, store */ -#define PERF_X86_EVENT_PEBS_LD_HSW 0x0008 /* haswell style datala, load */ -#define PERF_X86_EVENT_PEBS_NA_HSW 0x0010 /* haswell style datala, unknown */ -#define PERF_X86_EVENT_EXCL 0x0020 /* HT exclusivity on counter */ -#define PERF_X86_EVENT_DYNAMIC 0x0040 /* dynamic alloc'd constraint */ - -#define PERF_X86_EVENT_EXCL_ACCT 0x0100 /* accounted EXCL event */ -#define PERF_X86_EVENT_AUTO_RELOAD 0x0200 /* use PEBS auto-reload */ -#define PERF_X86_EVENT_LARGE_PEBS 0x0400 /* use large PEBS */ -#define PERF_X86_EVENT_PEBS_VIA_PT 0x0800 /* use PT buffer for PEBS */ -#define PERF_X86_EVENT_PAIR 0x1000 /* Large Increment per Cycle */ -#define PERF_X86_EVENT_LBR_SELECT 0x2000 /* Save/Restore MSR_LBR_SELECT */ -#define PERF_X86_EVENT_TOPDOWN 0x4000 /* Count Topdown slots/metrics events */ -#define PERF_X86_EVENT_PEBS_STLAT 0x8000 /* st+stlat data address sampling */ +#define PERF_X86_EVENT_PEBS_LDLAT 0x00001 /* ld+ldlat data address sampling */ +#define PERF_X86_EVENT_PEBS_ST 0x00002 /* st data address sampling */ +#define PERF_X86_EVENT_PEBS_ST_HSW 0x00004 /* haswell style datala, store */ +#define PERF_X86_EVENT_PEBS_LD_HSW 0x00008 /* haswell style datala, load */ +#define PERF_X86_EVENT_PEBS_NA_HSW 0x00010 /* haswell style datala, unknown */ +#define PERF_X86_EVENT_EXCL 0x00020 /* HT exclusivity on counter */ +#define PERF_X86_EVENT_DYNAMIC 0x00040 /* dynamic alloc'd constraint */ + +#define PERF_X86_EVENT_EXCL_ACCT 0x00100 /* accounted EXCL event */ +#define PERF_X86_EVENT_AUTO_RELOAD 0x00200 /* use PEBS auto-reload */ +#define PERF_X86_EVENT_LARGE_PEBS 0x00400 /* use large PEBS */ +#define PERF_X86_EVENT_PEBS_VIA_PT 0x00800 /* use PT buffer for PEBS */ +#define PERF_X86_EVENT_PAIR 0x01000 /* Large Increment per Cycle */ +#define PERF_X86_EVENT_LBR_SELECT 0x02000 /* Save/Restore MSR_LBR_SELECT */ +#define PERF_X86_EVENT_TOPDOWN 0x04000 /* Count Topdown slots/metrics events */ +#define PERF_X86_EVENT_PEBS_STLAT 0x08000 /* st+stlat data address sampling */ +#define PERF_X86_EVENT_AMD_BRS 0x10000 /* AMD Branch Sampling */ static inline bool is_topdown_count(struct perf_event *event) { @@ -325,6 +326,8 @@ struct cpu_hw_events { * AMD specific bits */ struct amd_nb *amd_nb; + int brs_active; /* BRS is enabled */ + /* Inverted mask of bits to clear in the perf_ctr ctrl registers */ u64 perf_ctr_virt_mask; int n_pair; /* Large increment events */ @@ -1105,6 +1108,11 @@ int x86_pmu_hw_config(struct perf_event *event); void x86_pmu_disable_all(void); +static inline bool has_amd_brs(struct hw_perf_event *hwc) +{ + return hwc->flags & PERF_X86_EVENT_AMD_BRS; +} + static inline bool is_counter_pair(struct hw_perf_event *hwc) { return hwc->flags & PERF_X86_EVENT_PAIR; @@ -1211,6 +1219,75 @@ static inline bool fixed_counter_disabled(int i, struct pmu *pmu) int amd_pmu_init(void); +#ifdef CONFIG_PERF_EVENTS_AMD_BRS +int amd_brs_init(void); +void amd_brs_disable(void); +void amd_brs_enable(void); +void amd_brs_enable_all(void); +void amd_brs_disable_all(void); +void amd_brs_drain(void); +void amd_brs_lopwr_init(void); +void amd_brs_disable_all(void); +int amd_brs_setup_filter(struct perf_event *event); +void amd_brs_reset(void); + +static inline void amd_pmu_brs_add(struct perf_event *event) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + + perf_sched_cb_inc(event->ctx->pmu); + cpuc->lbr_users++; + /* + * No need to reset BRS because it is reset + * on brs_enable() and it is saturating + */ +} + +static inline void amd_pmu_brs_del(struct perf_event *event) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + + cpuc->lbr_users--; + WARN_ON_ONCE(cpuc->lbr_users < 0); + + perf_sched_cb_dec(event->ctx->pmu); +} + +void amd_pmu_brs_sched_task(struct perf_event_context *ctx, bool sched_in); +#else +static inline int amd_brs_init(void) +{ + return 0; +} +static inline void amd_brs_disable(void) {} +static inline void amd_brs_enable(void) {} +static inline void amd_brs_drain(void) {} +static inline void amd_brs_lopwr_init(void) {} +static inline void amd_brs_disable_all(void) {} +static inline int amd_brs_setup_filter(struct perf_event *event) +{ + return 0; +} +static inline void amd_brs_reset(void) {} + +static inline void amd_pmu_brs_add(struct perf_event *event) +{ +} + +static inline void amd_pmu_brs_del(struct perf_event *event) +{ +} + +static inline void amd_pmu_brs_sched_task(struct perf_event_context *ctx, bool sched_in) +{ +} + +static inline void amd_brs_enable_all(void) +{ +} + +#endif + #else /* CONFIG_CPU_SUP_AMD */ static inline int amd_pmu_init(void) @@ -1218,6 +1295,22 @@ static inline int amd_pmu_init(void) return 0; } +static inline int amd_brs_init(void) +{ + return -EOPNOTSUPP; +} + +static inline void amd_brs_drain(void) +{ +} + +static inline void amd_brs_enable_all(void) +{ +} + +static inline void amd_brs_disable_all(void) +{ +} #endif /* CONFIG_CPU_SUP_AMD */ static inline int is_pebs_pt(struct perf_event *event) diff --git a/arch/x86/ia32/Makefile b/arch/x86/ia32/Makefile index 8e4d0391ff6c..e481056698de 100644 --- a/arch/x86/ia32/Makefile +++ b/arch/x86/ia32/Makefile @@ -5,7 +5,5 @@ obj-$(CONFIG_IA32_EMULATION) := ia32_signal.o -obj-$(CONFIG_IA32_AOUT) += ia32_aout.o - audit-class-$(CONFIG_AUDIT) := audit.o obj-$(CONFIG_IA32_EMULATION) += $(audit-class-y) diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c deleted file mode 100644 index 9bd15241fadb..000000000000 --- a/arch/x86/ia32/ia32_aout.c +++ /dev/null @@ -1,325 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * a.out loader for x86-64 - * - * Copyright (C) 1991, 1992, 1996 Linus Torvalds - * Hacked together by Andi Kleen - */ - -#include <linux/module.h> - -#include <linux/time.h> -#include <linux/kernel.h> -#include <linux/mm.h> -#include <linux/mman.h> -#include <linux/a.out.h> -#include <linux/errno.h> -#include <linux/signal.h> -#include <linux/string.h> -#include <linux/fs.h> -#include <linux/file.h> -#include <linux/stat.h> -#include <linux/fcntl.h> -#include <linux/ptrace.h> -#include <linux/user.h> -#include <linux/binfmts.h> -#include <linux/personality.h> -#include <linux/init.h> -#include <linux/jiffies.h> -#include <linux/perf_event.h> -#include <linux/sched/task_stack.h> - -#include <linux/uaccess.h> -#include <asm/cacheflush.h> -#include <asm/user32.h> -#include <asm/ia32.h> - -#undef WARN_OLD - -static int load_aout_binary(struct linux_binprm *); -static int load_aout_library(struct file *); - -static struct linux_binfmt aout_format = { - .module = THIS_MODULE, - .load_binary = load_aout_binary, - .load_shlib = load_aout_library, -}; - -static int set_brk(unsigned long start, unsigned long end) -{ - start = PAGE_ALIGN(start); - end = PAGE_ALIGN(end); - if (end <= start) - return 0; - return vm_brk(start, end - start); -} - - -/* - * create_aout_tables() parses the env- and arg-strings in new user - * memory and creates the pointer tables from them, and puts their - * addresses on the "stack", returning the new stack pointer value. - */ -static u32 __user *create_aout_tables(char __user *p, struct linux_binprm *bprm) -{ - u32 __user *argv, *envp, *sp; - int argc = bprm->argc, envc = bprm->envc; - - sp = (u32 __user *) ((-(unsigned long)sizeof(u32)) & (unsigned long) p); - sp -= envc+1; - envp = sp; - sp -= argc+1; - argv = sp; - put_user((unsigned long) envp, --sp); - put_user((unsigned long) argv, --sp); - put_user(argc, --sp); - current->mm->arg_start = (unsigned long) p; - while (argc-- > 0) { - char c; - - put_user((u32)(unsigned long)p, argv++); - do { - get_user(c, p++); - } while (c); - } - put_user(0, argv); - current->mm->arg_end = current->mm->env_start = (unsigned long) p; - while (envc-- > 0) { - char c; - - put_user((u32)(unsigned long)p, envp++); - do { - get_user(c, p++); - } while (c); - } - put_user(0, envp); - current->mm->env_end = (unsigned long) p; - return sp; -} - -/* - * These are the functions used to load a.out style executables and shared - * libraries. There is no binary dependent code anywhere else. - */ -static int load_aout_binary(struct linux_binprm *bprm) -{ - unsigned long error, fd_offset, rlim; - struct pt_regs *regs = current_pt_regs(); - struct exec ex; - int retval; - - ex = *((struct exec *) bprm->buf); /* exec-header */ - if ((N_MAGIC(ex) != ZMAGIC && N_MAGIC(ex) != OMAGIC && - N_MAGIC(ex) != QMAGIC && N_MAGIC(ex) != NMAGIC) || - N_TRSIZE(ex) || N_DRSIZE(ex) || - i_size_read(file_inode(bprm->file)) < - ex.a_text+ex.a_data+N_SYMSIZE(ex)+N_TXTOFF(ex)) { - return -ENOEXEC; - } - - fd_offset = N_TXTOFF(ex); - - /* Check initial limits. This avoids letting people circumvent - * size limits imposed on them by creating programs with large - * arrays in the data or bss. - */ - rlim = rlimit(RLIMIT_DATA); - if (rlim >= RLIM_INFINITY) - rlim = ~0; - if (ex.a_data + ex.a_bss > rlim) - return -ENOMEM; - - /* Flush all traces of the currently running executable */ - retval = begin_new_exec(bprm); - if (retval) - return retval; - - /* OK, This is the point of no return */ - set_personality(PER_LINUX); - set_personality_ia32(false); - - setup_new_exec(bprm); - - regs->cs = __USER32_CS; - regs->r8 = regs->r9 = regs->r10 = regs->r11 = regs->r12 = - regs->r13 = regs->r14 = regs->r15 = 0; - - current->mm->end_code = ex.a_text + - (current->mm->start_code = N_TXTADDR(ex)); - current->mm->end_data = ex.a_data + - (current->mm->start_data = N_DATADDR(ex)); - current->mm->brk = ex.a_bss + - (current->mm->start_brk = N_BSSADDR(ex)); - - retval = setup_arg_pages(bprm, IA32_STACK_TOP, EXSTACK_DEFAULT); - if (retval < 0) - return retval; - - if (N_MAGIC(ex) == OMAGIC) { - unsigned long text_addr, map_size; - - text_addr = N_TXTADDR(ex); - map_size = ex.a_text+ex.a_data; - - error = vm_brk(text_addr & PAGE_MASK, map_size); - - if (error) - return error; - - error = read_code(bprm->file, text_addr, 32, - ex.a_text + ex.a_data); - if ((signed long)error < 0) - return error; - } else { -#ifdef WARN_OLD - static unsigned long error_time, error_time2; - if ((ex.a_text & 0xfff || ex.a_data & 0xfff) && - (N_MAGIC(ex) != NMAGIC) && - time_after(jiffies, error_time2 + 5*HZ)) { - printk(KERN_NOTICE "executable not page aligned\n"); - error_time2 = jiffies; - } - - if ((fd_offset & ~PAGE_MASK) != 0 && - time_after(jiffies, error_time + 5*HZ)) { - printk(KERN_WARNING - "fd_offset is not page aligned. Please convert " - "program: %pD\n", - bprm->file); - error_time = jiffies; - } -#endif - - if (!bprm->file->f_op->mmap || (fd_offset & ~PAGE_MASK) != 0) { - error = vm_brk(N_TXTADDR(ex), ex.a_text+ex.a_data); - if (error) - return error; - - read_code(bprm->file, N_TXTADDR(ex), fd_offset, - ex.a_text+ex.a_data); - goto beyond_if; - } - - error = vm_mmap(bprm->file, N_TXTADDR(ex), ex.a_text, - PROT_READ | PROT_EXEC, - MAP_FIXED | MAP_PRIVATE | MAP_32BIT, - fd_offset); - - if (error != N_TXTADDR(ex)) - return error; - - error = vm_mmap(bprm->file, N_DATADDR(ex), ex.a_data, - PROT_READ | PROT_WRITE | PROT_EXEC, - MAP_FIXED | MAP_PRIVATE | MAP_32BIT, - fd_offset + ex.a_text); - if (error != N_DATADDR(ex)) - return error; - } - -beyond_if: - error = set_brk(current->mm->start_brk, current->mm->brk); - if (error) - return error; - - set_binfmt(&aout_format); - - current->mm->start_stack = - (unsigned long)create_aout_tables((char __user *)bprm->p, bprm); - /* start thread */ - loadsegment(fs, 0); - loadsegment(ds, __USER32_DS); - loadsegment(es, __USER32_DS); - load_gs_index(0); - (regs)->ip = ex.a_entry; - (regs)->sp = current->mm->start_stack; - (regs)->flags = 0x200; - (regs)->cs = __USER32_CS; - (regs)->ss = __USER32_DS; - regs->r8 = regs->r9 = regs->r10 = regs->r11 = - regs->r12 = regs->r13 = regs->r14 = regs->r15 = 0; - return 0; -} - -static int load_aout_library(struct file *file) -{ - unsigned long bss, start_addr, len, error; - int retval; - struct exec ex; - loff_t pos = 0; - - retval = -ENOEXEC; - error = kernel_read(file, &ex, sizeof(ex), &pos); - if (error != sizeof(ex)) - goto out; - - /* We come in here for the regular a.out style of shared libraries */ - if ((N_MAGIC(ex) != ZMAGIC && N_MAGIC(ex) != QMAGIC) || N_TRSIZE(ex) || - N_DRSIZE(ex) || ((ex.a_entry & 0xfff) && N_MAGIC(ex) == ZMAGIC) || - i_size_read(file_inode(file)) < - ex.a_text+ex.a_data+N_SYMSIZE(ex)+N_TXTOFF(ex)) { - goto out; - } - - if (N_FLAGS(ex)) - goto out; - - /* For QMAGIC, the starting address is 0x20 into the page. We mask - this off to get the starting address for the page */ - - start_addr = ex.a_entry & 0xfffff000; - - if ((N_TXTOFF(ex) & ~PAGE_MASK) != 0) { -#ifdef WARN_OLD - static unsigned long error_time; - if (time_after(jiffies, error_time + 5*HZ)) { - printk(KERN_WARNING - "N_TXTOFF is not page aligned. Please convert " - "library: %pD\n", - file); - error_time = jiffies; - } -#endif - retval = vm_brk(start_addr, ex.a_text + ex.a_data + ex.a_bss); - if (retval) - goto out; - - read_code(file, start_addr, N_TXTOFF(ex), - ex.a_text + ex.a_data); - retval = 0; - goto out; - } - /* Now use mmap to map the library into memory. */ - error = vm_mmap(file, start_addr, ex.a_text + ex.a_data, - PROT_READ | PROT_WRITE | PROT_EXEC, - MAP_FIXED | MAP_PRIVATE | MAP_32BIT, - N_TXTOFF(ex)); - retval = error; - if (error != start_addr) - goto out; - - len = PAGE_ALIGN(ex.a_text + ex.a_data); - bss = ex.a_text + ex.a_data + ex.a_bss; - if (bss > len) { - retval = vm_brk(start_addr + len, bss - len); - if (retval) - goto out; - } - retval = 0; -out: - return retval; -} - -static int __init init_aout_binfmt(void) -{ - register_binfmt(&aout_format); - return 0; -} - -static void __exit exit_aout_binfmt(void) -{ - unregister_binfmt(&aout_format); -} - -module_init(init_aout_binfmt); -module_exit(exit_aout_binfmt); -MODULE_LICENSE("GPL"); diff --git a/arch/x86/include/asm/acenv.h b/arch/x86/include/asm/acenv.h index 9aff97f0de7f..d937c55e717e 100644 --- a/arch/x86/include/asm/acenv.h +++ b/arch/x86/include/asm/acenv.h @@ -13,7 +13,19 @@ /* Asm macros */ -#define ACPI_FLUSH_CPU_CACHE() wbinvd() +/* + * ACPI_FLUSH_CPU_CACHE() flushes caches on entering sleep states. + * It is required to prevent data loss. + * + * While running inside virtual machine, the kernel can bypass cache flushing. + * Changing sleep state in a virtual machine doesn't affect the host system + * sleep state and cannot lead to data loss. + */ +#define ACPI_FLUSH_CPU_CACHE() \ +do { \ + if (!cpu_feature_enabled(X86_FEATURE_HYPERVISOR)) \ + wbinvd(); \ +} while (0) int __acpi_acquire_global_lock(unsigned int *lock); int __acpi_release_global_lock(unsigned int *lock); diff --git a/arch/x86/include/asm/amd-ibs.h b/arch/x86/include/asm/amd-ibs.h index 46e1df45efc0..aabdbb5ab920 100644 --- a/arch/x86/include/asm/amd-ibs.h +++ b/arch/x86/include/asm/amd-ibs.h @@ -49,7 +49,7 @@ union ibs_op_ctl { }; }; -/* MSR 0xc0011035: IBS Op Data 2 */ +/* MSR 0xc0011035: IBS Op Data 1 */ union ibs_op_data { __u64 val; struct { diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h index 00d1a400b7a1..ed0eaf65c437 100644 --- a/arch/x86/include/asm/amd_nb.h +++ b/arch/x86/include/asm/amd_nb.h @@ -16,7 +16,6 @@ extern const struct amd_nb_bus_dev_range amd_nb_bus_dev_ranges[]; extern bool early_is_amd_nb(u32 value); extern struct resource *amd_get_mmconfig_range(struct resource *res); -extern int amd_cache_northbridges(void); extern void amd_flush_garts(void); extern int amd_numa_init(void); extern int amd_get_subcaches(int); diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index 48067af94678..bd8ae0a7010a 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -328,6 +328,8 @@ struct apic { /* wakeup_secondary_cpu */ int (*wakeup_secondary_cpu)(int apicid, unsigned long start_eip); + /* wakeup secondary CPU using 64-bit wakeup point */ + int (*wakeup_secondary_cpu_64)(int apicid, unsigned long start_eip); void (*inquire_remote_apic)(int apicid); @@ -488,6 +490,11 @@ static inline unsigned int read_apic_id(void) return apic->get_apic_id(reg); } +#ifdef CONFIG_X86_64 +typedef int (*wakeup_cpu_handler)(int apicid, unsigned long start_eip); +extern void acpi_wake_cpu_handler_update(wakeup_cpu_handler handler); +#endif + extern int default_apic_id_valid(u32 apicid); extern int default_acpi_madt_oem_check(char *, char *); extern void default_setup_apic_routing(void); diff --git a/arch/x86/include/asm/apicdef.h b/arch/x86/include/asm/apicdef.h index 5716f22f81ac..92035eb3afee 100644 --- a/arch/x86/include/asm/apicdef.h +++ b/arch/x86/include/asm/apicdef.h @@ -95,12 +95,6 @@ #define APIC_LVTTHMR 0x330 #define APIC_LVTPC 0x340 #define APIC_LVT0 0x350 -#define APIC_LVT_TIMER_BASE_MASK (0x3 << 18) -#define GET_APIC_TIMER_BASE(x) (((x) >> 18) & 0x3) -#define SET_APIC_TIMER_BASE(x) (((x) << 18)) -#define APIC_TIMER_BASE_CLKIN 0x0 -#define APIC_TIMER_BASE_TMBASE 0x1 -#define APIC_TIMER_BASE_DIV 0x2 #define APIC_LVT_TIMER_ONESHOT (0 << 17) #define APIC_LVT_TIMER_PERIODIC (1 << 17) #define APIC_LVT_TIMER_TSCDEADLINE (2 << 17) diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h index c878fed3056f..fbcfec4dc4cc 100644 --- a/arch/x86/include/asm/asm.h +++ b/arch/x86/include/asm/asm.h @@ -154,24 +154,24 @@ # define DEFINE_EXTABLE_TYPE_REG \ ".macro extable_type_reg type:req reg:req\n" \ - ".set found, 0\n" \ - ".set regnr, 0\n" \ + ".set .Lfound, 0\n" \ + ".set .Lregnr, 0\n" \ ".irp rs,rax,rcx,rdx,rbx,rsp,rbp,rsi,rdi,r8,r9,r10,r11,r12,r13,r14,r15\n" \ ".ifc \\reg, %%\\rs\n" \ - ".set found, found+1\n" \ - ".long \\type + (regnr << 8)\n" \ + ".set .Lfound, .Lfound+1\n" \ + ".long \\type + (.Lregnr << 8)\n" \ ".endif\n" \ - ".set regnr, regnr+1\n" \ + ".set .Lregnr, .Lregnr+1\n" \ ".endr\n" \ - ".set regnr, 0\n" \ + ".set .Lregnr, 0\n" \ ".irp rs,eax,ecx,edx,ebx,esp,ebp,esi,edi,r8d,r9d,r10d,r11d,r12d,r13d,r14d,r15d\n" \ ".ifc \\reg, %%\\rs\n" \ - ".set found, found+1\n" \ - ".long \\type + (regnr << 8)\n" \ + ".set .Lfound, .Lfound+1\n" \ + ".long \\type + (.Lregnr << 8)\n" \ ".endif\n" \ - ".set regnr, regnr+1\n" \ + ".set .Lregnr, .Lregnr+1\n" \ ".endr\n" \ - ".if (found != 1)\n" \ + ".if (.Lfound != 1)\n" \ ".error \"extable_type_reg: bad register argument\"\n" \ ".endif\n" \ ".endm\n" diff --git a/arch/x86/include/asm/bootparam_utils.h b/arch/x86/include/asm/bootparam_utils.h index 981fe923a59f..53e9b0620d96 100644 --- a/arch/x86/include/asm/bootparam_utils.h +++ b/arch/x86/include/asm/bootparam_utils.h @@ -74,6 +74,7 @@ static void sanitize_boot_params(struct boot_params *boot_params) BOOT_PARAM_PRESERVE(hdr), BOOT_PARAM_PRESERVE(e820_table), BOOT_PARAM_PRESERVE(eddbuf), + BOOT_PARAM_PRESERVE(cc_blob_address), }; memset(&scratch, 0, sizeof(scratch)); diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h index 4d20a293c6fd..a3ec87d198ac 100644 --- a/arch/x86/include/asm/bug.h +++ b/arch/x86/include/asm/bug.h @@ -18,7 +18,7 @@ #ifdef CONFIG_X86_32 # define __BUG_REL(val) ".long " __stringify(val) #else -# define __BUG_REL(val) ".long " __stringify(val) " - 2b" +# define __BUG_REL(val) ".long " __stringify(val) " - ." #endif #ifdef CONFIG_DEBUG_BUGVERBOSE @@ -78,9 +78,9 @@ do { \ */ #define __WARN_FLAGS(flags) \ do { \ - __auto_type f = BUGFLAG_WARNING|(flags); \ + __auto_type __flags = BUGFLAG_WARNING|(flags); \ instrumentation_begin(); \ - _BUG_FLAGS(ASM_UD2, f, ASM_REACHABLE); \ + _BUG_FLAGS(ASM_UD2, __flags, ASM_REACHABLE); \ instrumentation_end(); \ } while (0) diff --git a/arch/x86/include/asm/cmpxchg_32.h b/arch/x86/include/asm/cmpxchg_32.h index 0a7fe0321613..215f5a65790f 100644 --- a/arch/x86/include/asm/cmpxchg_32.h +++ b/arch/x86/include/asm/cmpxchg_32.h @@ -42,6 +42,9 @@ static inline void set_64bit(volatile u64 *ptr, u64 value) #define arch_cmpxchg64_local(ptr, o, n) \ ((__typeof__(*(ptr)))__cmpxchg64_local((ptr), (unsigned long long)(o), \ (unsigned long long)(n))) +#define arch_try_cmpxchg64(ptr, po, n) \ + __try_cmpxchg64((ptr), (unsigned long long *)(po), \ + (unsigned long long)(n)) #endif static inline u64 __cmpxchg64(volatile u64 *ptr, u64 old, u64 new) @@ -70,6 +73,24 @@ static inline u64 __cmpxchg64_local(volatile u64 *ptr, u64 old, u64 new) return prev; } +static inline bool __try_cmpxchg64(volatile u64 *ptr, u64 *pold, u64 new) +{ + bool success; + u64 old = *pold; + asm volatile(LOCK_PREFIX "cmpxchg8b %[ptr]" + CC_SET(z) + : CC_OUT(z) (success), + [ptr] "+m" (*ptr), + "+A" (old) + : "b" ((u32)new), + "c" ((u32)(new >> 32)) + : "memory"); + + if (unlikely(!success)) + *pold = old; + return success; +} + #ifndef CONFIG_X86_CMPXCHG64 /* * Building a kernel capable running on 80386 and 80486. It may be necessary diff --git a/arch/x86/include/asm/cmpxchg_64.h b/arch/x86/include/asm/cmpxchg_64.h index 072e5459fe2f..250187ac8248 100644 --- a/arch/x86/include/asm/cmpxchg_64.h +++ b/arch/x86/include/asm/cmpxchg_64.h @@ -19,6 +19,12 @@ static inline void set_64bit(volatile u64 *ptr, u64 val) arch_cmpxchg_local((ptr), (o), (n)); \ }) +#define arch_try_cmpxchg64(ptr, po, n) \ +({ \ + BUILD_BUG_ON(sizeof(*(ptr)) != 8); \ + arch_try_cmpxchg((ptr), (po), (n)); \ +}) + #define system_has_cmpxchg_double() boot_cpu_has(X86_FEATURE_CX16) #endif /* _ASM_X86_CMPXCHG_64_H */ diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h index 7516e4199b3c..20fd0acd7d80 100644 --- a/arch/x86/include/asm/compat.h +++ b/arch/x86/include/asm/compat.h @@ -28,15 +28,13 @@ typedef u16 compat_ipc_pid_t; typedef __kernel_fsid_t compat_fsid_t; struct compat_stat { - compat_dev_t st_dev; - u16 __pad1; + u32 st_dev; compat_ino_t st_ino; compat_mode_t st_mode; compat_nlink_t st_nlink; __compat_uid_t st_uid; __compat_gid_t st_gid; - compat_dev_t st_rdev; - u16 __pad2; + u32 st_rdev; u32 st_size; u32 st_blksize; u32 st_blocks; diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h index 86e5e4e26fcb..8cbf623f0ecf 100644 --- a/arch/x86/include/asm/cpu.h +++ b/arch/x86/include/asm/cpu.h @@ -36,6 +36,8 @@ extern int _debug_hotplug_cpu(int cpu, int action); #endif #endif +extern void ap_init_aperfmperf(void); + int mwait_usable(const struct cpuinfo_x86 *); unsigned int x86_family(unsigned int sig); @@ -43,14 +45,12 @@ unsigned int x86_model(unsigned int sig); unsigned int x86_stepping(unsigned int sig); #ifdef CONFIG_CPU_SUP_INTEL extern void __init sld_setup(struct cpuinfo_x86 *c); -extern void switch_to_sld(unsigned long tifn); extern bool handle_user_split_lock(struct pt_regs *regs, long error_code); extern bool handle_guest_split_lock(unsigned long ip); extern void handle_bus_lock(struct pt_regs *regs); u8 get_this_hybrid_cpu_type(void); #else static inline void __init sld_setup(struct cpuinfo_x86 *c) {} -static inline void switch_to_sld(unsigned long tifn) {} static inline bool handle_user_split_lock(struct pt_regs *regs, long error_code) { return false; @@ -76,4 +76,22 @@ static inline void init_ia32_feat_ctl(struct cpuinfo_x86 *c) {} extern __noendbr void cet_disable(void); +struct ucode_cpu_info; + +int intel_cpu_collect_info(struct ucode_cpu_info *uci); + +static inline bool intel_cpu_signatures_match(unsigned int s1, unsigned int p1, + unsigned int s2, unsigned int p2) +{ + if (s1 != s2) + return false; + + /* Processor flags are either both 0 ... */ + if (!p1 && !p2) + return true; + + /* ... or they intersect. */ + return p1 & p2; +} + #endif /* _ASM_X86_CPU_H */ diff --git a/arch/x86/include/asm/cpu_entry_area.h b/arch/x86/include/asm/cpu_entry_area.h index dd5ea1bdf04c..75efc4c6f076 100644 --- a/arch/x86/include/asm/cpu_entry_area.h +++ b/arch/x86/include/asm/cpu_entry_area.h @@ -143,7 +143,7 @@ extern void cea_set_pte(void *cea_vaddr, phys_addr_t pa, pgprot_t flags); extern struct cpu_entry_area *get_cpu_entry_area(int cpu); -static inline struct entry_stack *cpu_entry_stack(int cpu) +static __always_inline struct entry_stack *cpu_entry_stack(int cpu) { return &get_cpu_entry_area(cpu)->entry_stack_page.stack; } diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 1261842d006c..66d3e3b1d24d 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -34,14 +34,17 @@ enum cpuid_leafs CPUID_8000_001F_EAX, }; +#define X86_CAP_FMT_NUM "%d:%d" +#define x86_cap_flag_num(flag) ((flag) >> 5), ((flag) & 31) + #ifdef CONFIG_X86_FEATURE_NAMES extern const char * const x86_cap_flags[NCAPINTS*32]; extern const char * const x86_power_flags[32]; #define X86_CAP_FMT "%s" #define x86_cap_flag(flag) x86_cap_flags[flag] #else -#define X86_CAP_FMT "%d:%d" -#define x86_cap_flag(flag) ((flag) >> 5), ((flag) & 31) +#define X86_CAP_FMT X86_CAP_FMT_NUM +#define x86_cap_flag x86_cap_flag_num #endif /* diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 73e643ae94b6..21bb78dfd41d 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -201,7 +201,7 @@ #define X86_FEATURE_INVPCID_SINGLE ( 7*32+ 7) /* Effectively INVPCID && CR4.PCIDE=1 */ #define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */ #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ -/* FREE! ( 7*32+10) */ +#define X86_FEATURE_XCOMPACTED ( 7*32+10) /* "" Use compacted XSTATE (XSAVES or XSAVEC) */ #define X86_FEATURE_PTI ( 7*32+11) /* Kernel Page Table Isolation enabled */ #define X86_FEATURE_RETPOLINE ( 7*32+12) /* "" Generic Retpoline mitigation for Spectre variant 2 */ #define X86_FEATURE_RETPOLINE_LFENCE ( 7*32+13) /* "" Use LFENCE for Spectre variant 2 */ @@ -211,7 +211,7 @@ #define X86_FEATURE_SSBD ( 7*32+17) /* Speculative Store Bypass Disable */ #define X86_FEATURE_MBA ( 7*32+18) /* Memory Bandwidth Allocation */ #define X86_FEATURE_RSB_CTXSW ( 7*32+19) /* "" Fill RSB on context switches */ -/* FREE! ( 7*32+20) */ +#define X86_FEATURE_PERFMON_V2 ( 7*32+20) /* AMD Performance Monitoring Version 2 */ #define X86_FEATURE_USE_IBPB ( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */ #define X86_FEATURE_USE_IBRS_FW ( 7*32+22) /* "" Use IBRS during runtime firmware calls */ #define X86_FEATURE_SPEC_STORE_BYPASS_DISABLE ( 7*32+23) /* "" Disable Speculative Store Bypass. */ @@ -238,6 +238,7 @@ #define X86_FEATURE_VMW_VMMCALL ( 8*32+19) /* "" VMware prefers VMMCALL hypercall instruction */ #define X86_FEATURE_PVUNLOCK ( 8*32+20) /* "" PV unlock function */ #define X86_FEATURE_VCPUPREEMPT ( 8*32+21) /* "" PV vcpu_is_preempted function */ +#define X86_FEATURE_TDX_GUEST ( 8*32+22) /* Intel Trust Domain Extensions Guest */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */ #define X86_FEATURE_FSGSBASE ( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/ @@ -315,6 +316,7 @@ #define X86_FEATURE_VIRT_SSBD (13*32+25) /* Virtualized Speculative Store Bypass Disable */ #define X86_FEATURE_AMD_SSB_NO (13*32+26) /* "" Speculative Store Bypass is fixed in hardware. */ #define X86_FEATURE_CPPC (13*32+27) /* Collaborative Processor Performance Control */ +#define X86_FEATURE_BRS (13*32+31) /* Branch Sampling available */ /* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */ #define X86_FEATURE_DTHERM (14*32+ 0) /* Digital Thermal Sensor */ diff --git a/arch/x86/include/asm/cpuid.h b/arch/x86/include/asm/cpuid.h new file mode 100644 index 000000000000..70b2db18165e --- /dev/null +++ b/arch/x86/include/asm/cpuid.h @@ -0,0 +1,34 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * CPUID-related helpers/definitions + * + * Derived from arch/x86/kvm/cpuid.c + */ + +#ifndef _ASM_X86_CPUID_H +#define _ASM_X86_CPUID_H + +static __always_inline bool cpuid_function_is_indexed(u32 function) +{ + switch (function) { + case 4: + case 7: + case 0xb: + case 0xd: + case 0xf: + case 0x10: + case 0x12: + case 0x14: + case 0x17: + case 0x18: + case 0x1d: + case 0x1e: + case 0x1f: + case 0x8000001d: + return true; + } + + return false; +} + +#endif /* _ASM_X86_CPUID_H */ diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h index 1231d63f836d..36369e76cc63 100644 --- a/arch/x86/include/asm/disabled-features.h +++ b/arch/x86/include/asm/disabled-features.h @@ -10,12 +10,6 @@ * cpu_feature_enabled(). */ -#ifdef CONFIG_X86_SMAP -# define DISABLE_SMAP 0 -#else -# define DISABLE_SMAP (1<<(X86_FEATURE_SMAP & 31)) -#endif - #ifdef CONFIG_X86_UMIP # define DISABLE_UMIP 0 #else @@ -68,6 +62,12 @@ # define DISABLE_SGX (1 << (X86_FEATURE_SGX & 31)) #endif +#ifdef CONFIG_INTEL_TDX_GUEST +# define DISABLE_TDX_GUEST 0 +#else +# define DISABLE_TDX_GUEST (1 << (X86_FEATURE_TDX_GUEST & 31)) +#endif + /* * Make sure to add features to the correct mask */ @@ -79,8 +79,8 @@ #define DISABLED_MASK5 0 #define DISABLED_MASK6 0 #define DISABLED_MASK7 (DISABLE_PTI) -#define DISABLED_MASK8 0 -#define DISABLED_MASK9 (DISABLE_SMAP|DISABLE_SGX) +#define DISABLED_MASK8 (DISABLE_TDX_GUEST) +#define DISABLED_MASK9 (DISABLE_SGX) #define DISABLED_MASK10 0 #define DISABLED_MASK11 0 #define DISABLED_MASK12 0 diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 98938a68251c..bed74a0f2932 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -357,6 +357,11 @@ static inline u32 efi64_convert_status(efi_status_t status) runtime), \ func, __VA_ARGS__)) +#define efi_dxe_call(func, ...) \ + (efi_is_native() \ + ? efi_dxe_table->func(__VA_ARGS__) \ + : __efi64_thunk_map(efi_dxe_table, func, __VA_ARGS__)) + #else /* CONFIG_EFI_MIXED */ static inline bool efi_is_64bit(void) diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h index 29fea180a665..cb0ff1055ab1 100644 --- a/arch/x86/include/asm/elf.h +++ b/arch/x86/include/asm/elf.h @@ -116,7 +116,7 @@ extern unsigned int vdso32_enabled; * now struct_user_regs, they are different) */ -#define ELF_CORE_COPY_REGS_COMMON(pr_reg, regs) \ +#define ELF_CORE_COPY_REGS(pr_reg, regs) \ do { \ pr_reg[0] = regs->bx; \ pr_reg[1] = regs->cx; \ @@ -128,6 +128,7 @@ do { \ pr_reg[7] = regs->ds; \ pr_reg[8] = regs->es; \ pr_reg[9] = regs->fs; \ + savesegment(gs, pr_reg[10]); \ pr_reg[11] = regs->orig_ax; \ pr_reg[12] = regs->ip; \ pr_reg[13] = regs->cs; \ @@ -136,18 +137,6 @@ do { \ pr_reg[16] = regs->ss; \ } while (0); -#define ELF_CORE_COPY_REGS(pr_reg, regs) \ -do { \ - ELF_CORE_COPY_REGS_COMMON(pr_reg, regs);\ - pr_reg[10] = get_user_gs(regs); \ -} while (0); - -#define ELF_CORE_COPY_KERNEL_REGS(pr_reg, regs) \ -do { \ - ELF_CORE_COPY_REGS_COMMON(pr_reg, regs);\ - savesegment(gs, pr_reg[10]); \ -} while (0); - #define ELF_PLATFORM (utsname()->machine) #define set_personality_64bit() do { } while (0) diff --git a/arch/x86/include/asm/entry-common.h b/arch/x86/include/asm/entry-common.h index 43184640b579..674ed46d3ced 100644 --- a/arch/x86/include/asm/entry-common.h +++ b/arch/x86/include/asm/entry-common.h @@ -10,7 +10,7 @@ #include <asm/fpu/api.h> /* Check that the stack and regs on entry from user mode are sane. */ -static __always_inline void arch_check_user_regs(struct pt_regs *regs) +static __always_inline void arch_enter_from_user_mode(struct pt_regs *regs) { if (IS_ENABLED(CONFIG_DEBUG_ENTRY)) { /* @@ -42,7 +42,7 @@ static __always_inline void arch_check_user_regs(struct pt_regs *regs) WARN_ON_ONCE(regs != task_pt_regs(current)); } } -#define arch_check_user_regs arch_check_user_regs +#define arch_enter_from_user_mode arch_enter_from_user_mode static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs, unsigned long ti_work) diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h index c83b3020350a..6b0f31fb53f7 100644 --- a/arch/x86/include/asm/fpu/api.h +++ b/arch/x86/include/asm/fpu/api.h @@ -162,7 +162,6 @@ static inline bool fpstate_is_confidential(struct fpu_guest *gfpu) } /* prctl */ -struct task_struct; -extern long fpu_xstate_prctl(struct task_struct *tsk, int option, unsigned long arg2); +extern long fpu_xstate_prctl(int option, unsigned long arg2); #endif /* _ASM_X86_FPU_API_H */ diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h deleted file mode 100644 index e69de29bb2d1..000000000000 --- a/arch/x86/include/asm/fpu/internal.h +++ /dev/null diff --git a/arch/x86/include/asm/highmem.h b/arch/x86/include/asm/highmem.h index 032e020853aa..731ee7cc40a5 100644 --- a/arch/x86/include/asm/highmem.h +++ b/arch/x86/include/asm/highmem.h @@ -26,6 +26,7 @@ #include <asm/tlbflush.h> #include <asm/paravirt.h> #include <asm/fixmap.h> +#include <asm/pgtable_areas.h> /* declarations for highmem.c */ extern unsigned long highstart_pfn, highend_pfn; diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h index 7924f27f5c8b..72184b0b2219 100644 --- a/arch/x86/include/asm/idtentry.h +++ b/arch/x86/include/asm/idtentry.h @@ -632,6 +632,10 @@ DECLARE_IDTENTRY_XENCB(X86_TRAP_OTHER, exc_xen_hypervisor_callback); DECLARE_IDTENTRY_RAW(X86_TRAP_OTHER, exc_xen_unknown_trap); #endif +#ifdef CONFIG_INTEL_TDX_GUEST +DECLARE_IDTENTRY(X86_TRAP_VE, exc_virtualization_exception); +#endif + /* Device interrupts common/spurious */ DECLARE_IDTENTRY_IRQ(X86_TRAP_OTHER, common_interrupt); #ifdef CONFIG_X86_LOCAL_APIC diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index 048b6d5aff50..def6ca121111 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -26,6 +26,7 @@ * _G - parts with extra graphics on * _X - regular server parts * _D - micro server parts + * _N,_P - other mobile parts * * Historical OPTDIFFs: * @@ -107,8 +108,10 @@ #define INTEL_FAM6_ALDERLAKE 0x97 /* Golden Cove / Gracemont */ #define INTEL_FAM6_ALDERLAKE_L 0x9A /* Golden Cove / Gracemont */ +#define INTEL_FAM6_ALDERLAKE_N 0xBE #define INTEL_FAM6_RAPTORLAKE 0xB7 +#define INTEL_FAM6_RAPTORLAKE_P 0xBA /* "Small Core" Processors (Atom) */ diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h index f6d91ecb8026..1870b99c3356 100644 --- a/arch/x86/include/asm/io.h +++ b/arch/x86/include/asm/io.h @@ -44,6 +44,7 @@ #include <asm/page.h> #include <asm/early_ioremap.h> #include <asm/pgtable_types.h> +#include <asm/shared/io.h> #define build_mmio_read(name, size, type, reg, barrier) \ static inline type name(const volatile void __iomem *addr) \ @@ -210,8 +211,6 @@ void __iomem *ioremap(resource_size_t offset, unsigned long size); extern void iounmap(volatile void __iomem *addr); #define iounmap iounmap -extern void set_iounmap_nonlazy(void); - #ifdef __KERNEL__ void memcpy_fromio(void *, const volatile void __iomem *, size_t); @@ -258,37 +257,23 @@ static inline void slow_down_io(void) #endif #define BUILDIO(bwl, bw, type) \ -static inline void out##bwl(unsigned type value, int port) \ -{ \ - asm volatile("out" #bwl " %" #bw "0, %w1" \ - : : "a"(value), "Nd"(port)); \ -} \ - \ -static inline unsigned type in##bwl(int port) \ -{ \ - unsigned type value; \ - asm volatile("in" #bwl " %w1, %" #bw "0" \ - : "=a"(value) : "Nd"(port)); \ - return value; \ -} \ - \ -static inline void out##bwl##_p(unsigned type value, int port) \ +static inline void out##bwl##_p(type value, u16 port) \ { \ out##bwl(value, port); \ slow_down_io(); \ } \ \ -static inline unsigned type in##bwl##_p(int port) \ +static inline type in##bwl##_p(u16 port) \ { \ - unsigned type value = in##bwl(port); \ + type value = in##bwl(port); \ slow_down_io(); \ return value; \ } \ \ -static inline void outs##bwl(int port, const void *addr, unsigned long count) \ +static inline void outs##bwl(u16 port, const void *addr, unsigned long count) \ { \ if (cc_platform_has(CC_ATTR_GUEST_UNROLL_STRING_IO)) { \ - unsigned type *value = (unsigned type *)addr; \ + type *value = (type *)addr; \ while (count) { \ out##bwl(*value, port); \ value++; \ @@ -301,10 +286,10 @@ static inline void outs##bwl(int port, const void *addr, unsigned long count) \ } \ } \ \ -static inline void ins##bwl(int port, void *addr, unsigned long count) \ +static inline void ins##bwl(u16 port, void *addr, unsigned long count) \ { \ if (cc_platform_has(CC_ATTR_GUEST_UNROLL_STRING_IO)) { \ - unsigned type *value = (unsigned type *)addr; \ + type *value = (type *)addr; \ while (count) { \ *value = in##bwl(port); \ value++; \ @@ -317,13 +302,11 @@ static inline void ins##bwl(int port, void *addr, unsigned long count) \ } \ } -BUILDIO(b, b, char) -BUILDIO(w, w, short) -BUILDIO(l, , int) +BUILDIO(b, b, u8) +BUILDIO(w, w, u16) +BUILDIO(l, , u32) +#undef BUILDIO -#define inb inb -#define inw inw -#define inl inl #define inb_p inb_p #define inw_p inw_p #define inl_p inl_p @@ -331,9 +314,6 @@ BUILDIO(l, , int) #define insw insw #define insl insl -#define outb outb -#define outw outw -#define outl outl #define outb_p outb_p #define outw_p outw_p #define outl_p outl_p diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h index 111104d1c2cd..7793e52d6237 100644 --- a/arch/x86/include/asm/irqflags.h +++ b/arch/x86/include/asm/irqflags.h @@ -137,14 +137,6 @@ static __always_inline void arch_local_irq_restore(unsigned long flags) if (!arch_irqs_disabled_flags(flags)) arch_local_irq_enable(); } -#else -#ifdef CONFIG_X86_64 -#ifdef CONFIG_XEN_PV -#define SWAPGS ALTERNATIVE "swapgs", "", X86_FEATURE_XENPV -#else -#define SWAPGS swapgs -#endif -#endif #endif /* !__ASSEMBLY__ */ #endif diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h index 0449b125d27f..071572e23d3a 100644 --- a/arch/x86/include/asm/jump_label.h +++ b/arch/x86/include/asm/jump_label.h @@ -20,7 +20,7 @@ _ASM_PTR "%c0 + %c1 - .\n\t" \ ".popsection \n\t" -#ifdef CONFIG_STACK_VALIDATION +#ifdef CONFIG_HAVE_JUMP_LABEL_HACK static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { @@ -34,7 +34,7 @@ l_yes: return true; } -#else +#else /* !CONFIG_HAVE_JUMP_LABEL_HACK */ static __always_inline bool arch_static_branch(struct static_key * const key, const bool branch) { @@ -48,7 +48,7 @@ l_yes: return true; } -#endif /* STACK_VALIDATION */ +#endif /* CONFIG_HAVE_JUMP_LABEL_HACK */ static __always_inline bool arch_static_branch_jump(struct static_key * const key, const bool branch) { diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h index 3c368b639c04..1a6d7e3f6c32 100644 --- a/arch/x86/include/asm/kvm-x86-ops.h +++ b/arch/x86/include/asm/kvm-x86-ops.h @@ -118,6 +118,7 @@ KVM_X86_OP_OPTIONAL(mem_enc_register_region) KVM_X86_OP_OPTIONAL(mem_enc_unregister_region) KVM_X86_OP_OPTIONAL(vm_copy_enc_context_from) KVM_X86_OP_OPTIONAL(vm_move_enc_context_from) +KVM_X86_OP_OPTIONAL(guest_memory_reclaimed) KVM_X86_OP(get_msr_feature) KVM_X86_OP(can_emulate_instruction) KVM_X86_OP(apic_init_signal_blocked) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index d23e80a56eb8..4ff36610af6a 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -974,12 +974,10 @@ enum hv_tsc_page_status { HV_TSC_PAGE_UNSET = 0, /* TSC page MSR was written by the guest, update pending */ HV_TSC_PAGE_GUEST_CHANGED, - /* TSC page MSR was written by KVM userspace, update pending */ + /* TSC page update was triggered from the host side */ HV_TSC_PAGE_HOST_CHANGED, /* TSC page was properly set up and is currently active */ HV_TSC_PAGE_SET, - /* TSC page is currently being updated and therefore is inactive */ - HV_TSC_PAGE_UPDATING, /* TSC page was set up with an inaccessible GPA */ HV_TSC_PAGE_BROKEN, }; @@ -1052,6 +1050,7 @@ enum kvm_apicv_inhibit { APICV_INHIBIT_REASON_X2APIC, APICV_INHIBIT_REASON_BLOCKIRQ, APICV_INHIBIT_REASON_ABSENT, + APICV_INHIBIT_REASON_SEV, }; struct kvm_arch { @@ -1485,6 +1484,7 @@ struct kvm_x86_ops { int (*mem_enc_unregister_region)(struct kvm *kvm, struct kvm_enc_region *argp); int (*vm_copy_enc_context_from)(struct kvm *kvm, unsigned int source_fd); int (*vm_move_enc_context_from)(struct kvm *kvm, unsigned int source_fd); + void (*guest_memory_reclaimed)(struct kvm *kvm); int (*get_msr_feature)(struct kvm_msr_entry *entry); @@ -1585,8 +1585,9 @@ static inline int kvm_arch_flush_remote_tlb(struct kvm *kvm) #define kvm_arch_pmi_in_guest(vcpu) \ ((vcpu) && (vcpu)->arch.handling_intr_from_guest) -int kvm_mmu_module_init(void); -void kvm_mmu_module_exit(void); +void kvm_mmu_x86_module_init(void); +int kvm_mmu_vendor_module_init(void); +void kvm_mmu_vendor_module_exit(void); void kvm_mmu_destroy(struct kvm_vcpu *vcpu); int kvm_mmu_create(struct kvm_vcpu *vcpu); diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h index 56935ebb1dfe..57bc74e112f2 100644 --- a/arch/x86/include/asm/kvm_para.h +++ b/arch/x86/include/asm/kvm_para.h @@ -7,6 +7,8 @@ #include <linux/interrupt.h> #include <uapi/asm/kvm_para.h> +#include <asm/tdx.h> + #ifdef CONFIG_KVM_GUEST bool kvm_check_and_clear_guest_paused(void); #else @@ -32,6 +34,10 @@ static inline bool kvm_check_and_clear_guest_paused(void) static inline long kvm_hypercall0(unsigned int nr) { long ret; + + if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) + return tdx_kvm_hypercall(nr, 0, 0, 0, 0); + asm volatile(KVM_HYPERCALL : "=a"(ret) : "a"(nr) @@ -42,6 +48,10 @@ static inline long kvm_hypercall0(unsigned int nr) static inline long kvm_hypercall1(unsigned int nr, unsigned long p1) { long ret; + + if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) + return tdx_kvm_hypercall(nr, p1, 0, 0, 0); + asm volatile(KVM_HYPERCALL : "=a"(ret) : "a"(nr), "b"(p1) @@ -53,6 +63,10 @@ static inline long kvm_hypercall2(unsigned int nr, unsigned long p1, unsigned long p2) { long ret; + + if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) + return tdx_kvm_hypercall(nr, p1, p2, 0, 0); + asm volatile(KVM_HYPERCALL : "=a"(ret) : "a"(nr), "b"(p1), "c"(p2) @@ -64,6 +78,10 @@ static inline long kvm_hypercall3(unsigned int nr, unsigned long p1, unsigned long p2, unsigned long p3) { long ret; + + if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) + return tdx_kvm_hypercall(nr, p1, p2, p3, 0); + asm volatile(KVM_HYPERCALL : "=a"(ret) : "a"(nr), "b"(p1), "c"(p2), "d"(p3) @@ -76,6 +94,10 @@ static inline long kvm_hypercall4(unsigned int nr, unsigned long p1, unsigned long p4) { long ret; + + if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) + return tdx_kvm_hypercall(nr, p1, p2, p3, p4); + asm volatile(KVM_HYPERCALL : "=a"(ret) : "a"(nr), "b"(p1), "c"(p2), "d"(p3), "S"(p4) diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h index e2c6f433ed10..88ceaf3648b3 100644 --- a/arch/x86/include/asm/mem_encrypt.h +++ b/arch/x86/include/asm/mem_encrypt.h @@ -49,9 +49,6 @@ void __init early_set_mem_enc_dec_hypercall(unsigned long vaddr, int npages, void __init mem_encrypt_free_decrypted_mem(void); -/* Architecture __weak replacement functions */ -void __init mem_encrypt_init(void); - void __init sev_es_init_vc_handling(void); #define __bss_decrypted __section(".bss..decrypted") @@ -89,6 +86,9 @@ static inline void mem_encrypt_free_decrypted_mem(void) { } #endif /* CONFIG_AMD_MEM_ENCRYPT */ +/* Architecture __weak replacement functions */ +void __init mem_encrypt_init(void); + /* * The __sme_pa() and __sme_pa_nodebug() macros are meant for use when * writing to or comparing values from the cr3 register. Having the diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h index d6bfdfb0f0af..0c3d3440fe27 100644 --- a/arch/x86/include/asm/microcode.h +++ b/arch/x86/include/asm/microcode.h @@ -131,10 +131,12 @@ extern void __init load_ucode_bsp(void); extern void load_ucode_ap(void); void reload_early_microcode(void); extern bool initrd_gone; +void microcode_bsp_resume(void); #else static inline void __init load_ucode_bsp(void) { } static inline void load_ucode_ap(void) { } static inline void reload_early_microcode(void) { } +static inline void microcode_bsp_resume(void) { } #endif #endif /* _ASM_X86_MICROCODE_H */ diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 27516046117a..b8d40ddeab00 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -141,7 +141,7 @@ do { \ #ifdef CONFIG_X86_32 #define deactivate_mm(tsk, mm) \ do { \ - lazy_load_gs(0); \ + loadsegment(gs, 0); \ } while (0) #else #define deactivate_mm(tsk, mm) \ diff --git a/arch/x86/include/asm/mmx.h b/arch/x86/include/asm/mmx.h deleted file mode 100644 index e69de29bb2d1..000000000000 --- a/arch/x86/include/asm/mmx.h +++ /dev/null diff --git a/arch/x86/include/asm/msi.h b/arch/x86/include/asm/msi.h index b85147d75626..d71c7e8b738d 100644 --- a/arch/x86/include/asm/msi.h +++ b/arch/x86/include/asm/msi.h @@ -12,14 +12,17 @@ int pci_msi_prepare(struct irq_domain *domain, struct device *dev, int nvec, /* Structs and defines for the X86 specific MSI message format */ typedef struct x86_msi_data { - u32 vector : 8, - delivery_mode : 3, - dest_mode_logical : 1, - reserved : 2, - active_low : 1, - is_level : 1; - - u32 dmar_subhandle; + union { + struct { + u32 vector : 8, + delivery_mode : 3, + dest_mode_logical : 1, + reserved : 2, + active_low : 1, + is_level : 1; + }; + u32 dmar_subhandle; + }; } __attribute__ ((packed)) arch_msi_msg_data_t; #define arch_msi_msg_data x86_msi_data diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 0eb90d21049e..403e83b4adc8 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -76,6 +76,8 @@ /* Abbreviated from Intel SDM name IA32_CORE_CAPABILITIES */ #define MSR_IA32_CORE_CAPS 0x000000cf +#define MSR_IA32_CORE_CAPS_INTEGRITY_CAPS_BIT 2 +#define MSR_IA32_CORE_CAPS_INTEGRITY_CAPS BIT(MSR_IA32_CORE_CAPS_INTEGRITY_CAPS_BIT) #define MSR_IA32_CORE_CAPS_SPLIT_LOCK_DETECT_BIT 5 #define MSR_IA32_CORE_CAPS_SPLIT_LOCK_DETECT BIT(MSR_IA32_CORE_CAPS_SPLIT_LOCK_DETECT_BIT) @@ -128,9 +130,9 @@ #define TSX_CTRL_RTM_DISABLE BIT(0) /* Disable RTM feature */ #define TSX_CTRL_CPUID_CLEAR BIT(1) /* Disable TSX enumeration */ -/* SRBDS support */ #define MSR_IA32_MCU_OPT_CTRL 0x00000123 -#define RNGDS_MITG_DIS BIT(0) +#define RNGDS_MITG_DIS BIT(0) /* SRBDS support */ +#define RTM_ALLOW BIT(1) /* TSX development mode */ #define MSR_IA32_SYSENTER_CS 0x00000174 #define MSR_IA32_SYSENTER_ESP 0x00000175 @@ -154,6 +156,11 @@ #define MSR_IA32_POWER_CTL 0x000001fc #define MSR_IA32_POWER_CTL_BIT_EE 19 +/* Abbreviated from Intel SDM name IA32_INTEGRITY_CAPABILITIES */ +#define MSR_INTEGRITY_CAPS 0x000002d9 +#define MSR_INTEGRITY_CAPS_PERIODIC_BIST_BIT 4 +#define MSR_INTEGRITY_CAPS_PERIODIC_BIST BIT(MSR_INTEGRITY_CAPS_PERIODIC_BIST_BIT) + #define MSR_LBR_NHM_FROM 0x00000680 #define MSR_LBR_NHM_TO 0x000006c0 #define MSR_LBR_CORE_FROM 0x00000040 @@ -312,6 +319,7 @@ /* Run Time Average Power Limiting (RAPL) Interface */ +#define MSR_VR_CURRENT_CONFIG 0x00000601 #define MSR_RAPL_POWER_UNIT 0x00000606 #define MSR_PKG_POWER_LIMIT 0x00000610 @@ -502,8 +510,10 @@ #define MSR_AMD64_SEV 0xc0010131 #define MSR_AMD64_SEV_ENABLED_BIT 0 #define MSR_AMD64_SEV_ES_ENABLED_BIT 1 +#define MSR_AMD64_SEV_SNP_ENABLED_BIT 2 #define MSR_AMD64_SEV_ENABLED BIT_ULL(MSR_AMD64_SEV_ENABLED_BIT) #define MSR_AMD64_SEV_ES_ENABLED BIT_ULL(MSR_AMD64_SEV_ES_ENABLED_BIT) +#define MSR_AMD64_SEV_SNP_ENABLED BIT_ULL(MSR_AMD64_SEV_SNP_ENABLED_BIT) #define MSR_AMD64_VIRT_SPEC_CTRL 0xc001011f @@ -524,6 +534,11 @@ #define AMD_CPPC_DES_PERF(x) (((x) & 0xff) << 16) #define AMD_CPPC_ENERGY_PERF_PREF(x) (((x) & 0xff) << 24) +/* AMD Performance Counter Global Status and Control MSRs */ +#define MSR_AMD64_PERF_CNTR_GLOBAL_STATUS 0xc0000300 +#define MSR_AMD64_PERF_CNTR_GLOBAL_CTL 0xc0000301 +#define MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR 0xc0000302 + /* Fam 17h MSRs */ #define MSR_F17H_IRPERF 0xc00000e9 @@ -688,6 +703,10 @@ #define MSR_IA32_PERF_CTL 0x00000199 #define INTEL_PERF_CTL_MASK 0xffff +/* AMD Branch Sampling configuration */ +#define MSR_AMD_DBG_EXTN_CFG 0xc000010f +#define MSR_AMD_SAMP_BR_FROM 0xc0010300 + #define MSR_IA32_MPERF 0x000000e7 #define MSR_IA32_APERF 0x000000e8 diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h index d42e6c6b47b1..65ec1965cd28 100644 --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -10,16 +10,7 @@ #include <asm/errno.h> #include <asm/cpumask.h> #include <uapi/asm/msr.h> - -struct msr { - union { - struct { - u32 l; - u32 h; - }; - u64 q; - }; -}; +#include <asm/shared/msr.h> struct msr_info { u32 msr_no; diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h index 1cb9c17a4cb4..5c5f1e56c404 100644 --- a/arch/x86/include/asm/nmi.h +++ b/arch/x86/include/asm/nmi.h @@ -47,6 +47,7 @@ struct nmiaction { #define register_nmi_handler(t, fn, fg, n, init...) \ ({ \ static struct nmiaction init fn##_na = { \ + .list = LIST_HEAD_INIT(fn##_na.list), \ .handler = (fn), \ .name = (n), \ .flags = (fg), \ diff --git a/arch/x86/include/asm/page_64.h b/arch/x86/include/asm/page_64.h index e9c86299b835..baa70451b8df 100644 --- a/arch/x86/include/asm/page_64.h +++ b/arch/x86/include/asm/page_64.h @@ -16,7 +16,7 @@ extern unsigned long page_offset_base; extern unsigned long vmalloc_base; extern unsigned long vmemmap_base; -static inline unsigned long __phys_addr_nodebug(unsigned long x) +static __always_inline unsigned long __phys_addr_nodebug(unsigned long x) { unsigned long y = x - __START_KERNEL_map; diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h index a0627dfae541..1307cd689d2a 100644 --- a/arch/x86/include/asm/pci_x86.h +++ b/arch/x86/include/asm/pci_x86.h @@ -93,6 +93,15 @@ struct irq_routing_table { struct irq_info slots[]; } __attribute__((packed)); +struct irt_routing_table { + u32 signature; /* IRT_SIGNATURE should be here */ + u8 size; /* Number of entries provided */ + u8 used; /* Number of entries actually used */ + u16 exclusive_irqs; /* IRQs devoted exclusively to + PCI usage */ + struct irq_info slots[]; +} __attribute__((packed)); + extern unsigned int pcibios_irq_mask; extern raw_spinlock_t pci_config_lock; diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h index a3c33b79fb86..13c0d63ed55e 100644 --- a/arch/x86/include/asm/percpu.h +++ b/arch/x86/include/asm/percpu.h @@ -38,9 +38,9 @@ #define arch_raw_cpu_ptr(ptr) \ ({ \ unsigned long tcp_ptr__; \ - asm volatile("add " __percpu_arg(1) ", %0" \ - : "=r" (tcp_ptr__) \ - : "m" (this_cpu_off), "0" (ptr)); \ + asm ("add " __percpu_arg(1) ", %0" \ + : "=r" (tcp_ptr__) \ + : "m" (this_cpu_off), "0" (ptr)); \ (typeof(*(ptr)) __kernel __force *)tcp_ptr__; \ }) #else diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 58d9e4b1fa0a..409725e86f42 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -2,6 +2,8 @@ #ifndef _ASM_X86_PERF_EVENT_H #define _ASM_X86_PERF_EVENT_H +#include <linux/static_call.h> + /* * Performance event hw details: */ @@ -184,6 +186,18 @@ union cpuid28_ecx { unsigned int full; }; +/* + * AMD "Extended Performance Monitoring and Debug" CPUID + * detection/enumeration details: + */ +union cpuid_0x80000022_ebx { + struct { + /* Number of Core Performance Counters */ + unsigned int num_core_pmc:4; + } split; + unsigned int full; +}; + struct x86_pmu_capability { int version; int num_counters_gp; @@ -241,6 +255,11 @@ struct x86_pmu_capability { #define INTEL_PMC_IDX_FIXED_SLOTS (INTEL_PMC_IDX_FIXED + 3) #define INTEL_PMC_MSK_FIXED_SLOTS (1ULL << INTEL_PMC_IDX_FIXED_SLOTS) +static inline bool use_fixed_pseudo_encoding(u64 code) +{ + return !(code & 0xff); +} + /* * We model BTS tracing as another fixed-mode PMC. * @@ -366,6 +385,11 @@ struct pebs_xmm { }; /* + * AMD Extended Performance Monitoring and Debug cpuid feature detection + */ +#define EXT_PERFMON_DEBUG_FEATURES 0x80000022 + +/* * IBS cpuid feature detection */ @@ -386,6 +410,7 @@ struct pebs_xmm { #define IBS_CAPS_OPBRNFUSE (1U<<8) #define IBS_CAPS_FETCHCTLEXTD (1U<<9) #define IBS_CAPS_OPDATA4 (1U<<10) +#define IBS_CAPS_ZEN4 (1U<<11) #define IBS_CAPS_DEFAULT (IBS_CAPS_AVAIL \ | IBS_CAPS_FETCHSAM \ @@ -399,6 +424,7 @@ struct pebs_xmm { #define IBSCTL_LVT_OFFSET_MASK 0x0F /* IBS fetch bits/masks */ +#define IBS_FETCH_L3MISSONLY (1ULL<<59) #define IBS_FETCH_RAND_EN (1ULL<<57) #define IBS_FETCH_VAL (1ULL<<49) #define IBS_FETCH_ENABLE (1ULL<<48) @@ -415,6 +441,7 @@ struct pebs_xmm { #define IBS_OP_CNT_CTL (1ULL<<19) #define IBS_OP_VAL (1ULL<<18) #define IBS_OP_ENABLE (1ULL<<17) +#define IBS_OP_L3MISSONLY (1ULL<<16) #define IBS_OP_MAX_CNT 0x0000FFFFULL #define IBS_OP_MAX_CNT_EXT 0x007FFFFFULL /* not a register bit mask */ #define IBS_OP_MAX_CNT_EXT_MASK (0x7FULL<<20) /* separate upper 7 bits */ @@ -513,6 +540,27 @@ static inline void intel_pt_handle_vmx(int on) #if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_AMD) extern void amd_pmu_enable_virt(void); extern void amd_pmu_disable_virt(void); + +#if defined(CONFIG_PERF_EVENTS_AMD_BRS) + +#define PERF_NEEDS_LOPWR_CB 1 + +/* + * architectural low power callback impacts + * drivers/acpi/processor_idle.c + * drivers/acpi/acpi_pad.c + */ +extern void perf_amd_brs_lopwr_cb(bool lopwr_in); + +DECLARE_STATIC_CALL(perf_lopwr_cb, perf_amd_brs_lopwr_cb); + +static inline void perf_lopwr_cb(bool lopwr_in) +{ + static_call_mod(perf_lopwr_cb)(lopwr_in); +} + +#endif /* PERF_NEEDS_LOPWR_CB */ + #else static inline void amd_pmu_enable_virt(void) { } static inline void amd_pmu_disable_virt(void) { } diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index 40497a9020c6..407084d9fd99 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -559,10 +559,6 @@ static inline void update_page_count(int level, unsigned long pages) { } extern pte_t *lookup_address(unsigned long address, unsigned int *level); extern pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address, unsigned int *level); - -struct mm_struct; -extern pte_t *lookup_address_in_mm(struct mm_struct *mm, unsigned long address, - unsigned int *level); extern pmd_t *lookup_pmd_address(unsigned long address); extern phys_addr_t slow_virt_to_phys(void *__address); extern int __init kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, diff --git a/arch/x86/include/asm/pkeys.h b/arch/x86/include/asm/pkeys.h index 1d5f14aff5f6..2e6c04d8a45b 100644 --- a/arch/x86/include/asm/pkeys.h +++ b/arch/x86/include/asm/pkeys.h @@ -41,9 +41,6 @@ static inline int arch_override_mprotect_pkey(struct vm_area_struct *vma, return __arch_override_mprotect_pkey(vma, prot, pkey); } -extern int __arch_set_user_pkey_access(struct task_struct *tsk, int pkey, - unsigned long init_val); - #define ARCH_VM_PKEY_FLAGS (VM_PKEY_BIT0 | VM_PKEY_BIT1 | VM_PKEY_BIT2 | VM_PKEY_BIT3) #define mm_pkey_allocation_map(mm) (mm->context.pkey_allocation_map) @@ -118,11 +115,6 @@ int mm_pkey_free(struct mm_struct *mm, int pkey) return 0; } -extern int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, - unsigned long init_val); -extern int __arch_set_user_pkey_access(struct task_struct *tsk, int pkey, - unsigned long init_val); - static inline int vma_pkey(struct vm_area_struct *vma) { unsigned long vma_pkey_mask = VM_PKEY_BIT0 | VM_PKEY_BIT1 | diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h index feed36d44d04..12ef86b19910 100644 --- a/arch/x86/include/asm/proto.h +++ b/arch/x86/include/asm/proto.h @@ -13,6 +13,8 @@ void syscall_init(void); #ifdef CONFIG_X86_64 void entry_SYSCALL_64(void); void entry_SYSCALL_64_safe_stack(void); +void entry_SYSRETQ_unsafe_stack(void); +void entry_SYSRETQ_end(void); long do_arch_prctl_64(struct task_struct *task, int option, unsigned long arg2); #endif @@ -28,6 +30,8 @@ void entry_SYSENTER_compat(void); void __end_entry_SYSENTER_compat(void); void entry_SYSCALL_compat(void); void entry_SYSCALL_compat_safe_stack(void); +void entry_SYSRETL_compat_unsafe_stack(void); +void entry_SYSRETL_compat_end(void); void entry_INT80_compat(void); #ifdef CONFIG_XEN_PV void xen_entry_INT80_compat(void); @@ -35,11 +39,9 @@ void xen_entry_INT80_compat(void); #endif void x86_configure_nx(void); -void x86_report_nx(void); extern int reboot_force; -long do_arch_prctl_common(struct task_struct *task, int option, - unsigned long arg2); +long do_arch_prctl_common(int option, unsigned long arg2); #endif /* _ASM_X86_PROTO_H */ diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h index 4357e0f2cd5f..f4db78b09c8f 100644 --- a/arch/x86/include/asm/ptrace.h +++ b/arch/x86/include/asm/ptrace.h @@ -186,9 +186,13 @@ static __always_inline bool ip_within_syscall_gap(struct pt_regs *regs) bool ret = (regs->ip >= (unsigned long)entry_SYSCALL_64 && regs->ip < (unsigned long)entry_SYSCALL_64_safe_stack); + ret = ret || (regs->ip >= (unsigned long)entry_SYSRETQ_unsafe_stack && + regs->ip < (unsigned long)entry_SYSRETQ_end); #ifdef CONFIG_IA32_EMULATION ret = ret || (regs->ip >= (unsigned long)entry_SYSCALL_compat && regs->ip < (unsigned long)entry_SYSCALL_compat_safe_stack); + ret = ret || (regs->ip >= (unsigned long)entry_SYSRETL_compat_unsafe_stack && + regs->ip < (unsigned long)entry_SYSRETL_compat_end); #endif return ret; diff --git a/arch/x86/include/asm/realmode.h b/arch/x86/include/asm/realmode.h index 331474b150f1..fd6f6e5b755a 100644 --- a/arch/x86/include/asm/realmode.h +++ b/arch/x86/include/asm/realmode.h @@ -25,6 +25,7 @@ struct real_mode_header { u32 sev_es_trampoline_start; #endif #ifdef CONFIG_X86_64 + u32 trampoline_start64; u32 trampoline_pgd; #endif /* ACPI S3 wakeup */ diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h index 656ed6531d03..2e7890dd58a4 100644 --- a/arch/x86/include/asm/segment.h +++ b/arch/x86/include/asm/segment.h @@ -350,18 +350,6 @@ static inline void __loadsegment_fs(unsigned short value) #define savesegment(seg, value) \ asm("mov %%" #seg ",%0":"=r" (value) : : "memory") -/* - * x86-32 user GS accessors. This is ugly and could do with some cleaning up. - */ -#ifdef CONFIG_X86_32 -# define get_user_gs(regs) (u16)({ unsigned long v; savesegment(gs, v); v; }) -# define set_user_gs(regs, v) loadsegment(gs, (unsigned long)(v)) -# define task_user_gs(tsk) ((tsk)->thread.gs) -# define lazy_save_gs(v) savesegment(gs, (v)) -# define lazy_load_gs(v) loadsegment(gs, (v)) -# define load_gs_index(v) loadsegment(gs, (v)) -#endif /* X86_32 */ - #endif /* !__ASSEMBLY__ */ #endif /* __KERNEL__ */ diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index 896e48d45828..7590ac2570b9 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -50,7 +50,6 @@ extern unsigned long saved_video_mode; extern void reserve_standard_io_resources(void); extern void i386_reserve_resources(void); extern unsigned long __startup_64(unsigned long physaddr, struct boot_params *bp); -extern unsigned long __startup_secondary_64(void); extern void startup_64_setup_env(unsigned long physbase); extern void early_setup_idt(void); extern void __init do_early_exception(struct pt_regs *regs, int trapnr); @@ -109,27 +108,19 @@ extern unsigned long _brk_end; void *extend_brk(size_t size, size_t align); /* - * Reserve space in the brk section. The name must be unique within - * the file, and somewhat descriptive. The size is in bytes. Must be - * used at file scope. + * Reserve space in the brk section. The name must be unique within the file, + * and somewhat descriptive. The size is in bytes. * - * (This uses a temp function to wrap the asm so we can pass it the - * size parameter; otherwise we wouldn't be able to. We can't use a - * "section" attribute on a normal variable because it always ends up - * being @progbits, which ends up allocating space in the vmlinux - * executable.) + * The allocation is done using inline asm (rather than using a section + * attribute on a normal variable) in order to allow the use of @nobits, so + * that it doesn't take up any space in the vmlinux file. */ -#define RESERVE_BRK(name,sz) \ - static void __section(".discard.text") __noendbr __used notrace \ - __brk_reservation_fn_##name##__(void) { \ - asm volatile ( \ - ".pushsection .brk_reservation,\"aw\",@nobits;" \ - ".brk." #name ":" \ - " 1:.skip %c0;" \ - " .size .brk." #name ", . - 1b;" \ - " .popsection" \ - : : "i" (sz)); \ - } +#define RESERVE_BRK(name, size) \ + asm(".pushsection .brk_reservation,\"aw\",@nobits\n\t" \ + ".brk." #name ":\n\t" \ + ".skip " __stringify(size) "\n\t" \ + ".size .brk." #name ", " __stringify(size) "\n\t" \ + ".popsection\n\t") extern void probe_roms(void); #ifdef __i386__ diff --git a/arch/x86/include/asm/sev-common.h b/arch/x86/include/asm/sev-common.h index 1b2fd32b42fe..b8357d6ecd47 100644 --- a/arch/x86/include/asm/sev-common.h +++ b/arch/x86/include/asm/sev-common.h @@ -57,9 +57,79 @@ #define GHCB_MSR_AP_RESET_HOLD_REQ 0x006 #define GHCB_MSR_AP_RESET_HOLD_RESP 0x007 +/* GHCB GPA Register */ +#define GHCB_MSR_REG_GPA_REQ 0x012 +#define GHCB_MSR_REG_GPA_REQ_VAL(v) \ + /* GHCBData[63:12] */ \ + (((u64)((v) & GENMASK_ULL(51, 0)) << 12) | \ + /* GHCBData[11:0] */ \ + GHCB_MSR_REG_GPA_REQ) + +#define GHCB_MSR_REG_GPA_RESP 0x013 +#define GHCB_MSR_REG_GPA_RESP_VAL(v) \ + /* GHCBData[63:12] */ \ + (((u64)(v) & GENMASK_ULL(63, 12)) >> 12) + +/* + * SNP Page State Change Operation + * + * GHCBData[55:52] - Page operation: + * 0x0001 Page assignment, Private + * 0x0002 Page assignment, Shared + */ +enum psc_op { + SNP_PAGE_STATE_PRIVATE = 1, + SNP_PAGE_STATE_SHARED, +}; + +#define GHCB_MSR_PSC_REQ 0x014 +#define GHCB_MSR_PSC_REQ_GFN(gfn, op) \ + /* GHCBData[55:52] */ \ + (((u64)((op) & 0xf) << 52) | \ + /* GHCBData[51:12] */ \ + ((u64)((gfn) & GENMASK_ULL(39, 0)) << 12) | \ + /* GHCBData[11:0] */ \ + GHCB_MSR_PSC_REQ) + +#define GHCB_MSR_PSC_RESP 0x015 +#define GHCB_MSR_PSC_RESP_VAL(val) \ + /* GHCBData[63:32] */ \ + (((u64)(val) & GENMASK_ULL(63, 32)) >> 32) + /* GHCB Hypervisor Feature Request/Response */ #define GHCB_MSR_HV_FT_REQ 0x080 #define GHCB_MSR_HV_FT_RESP 0x081 +#define GHCB_MSR_HV_FT_RESP_VAL(v) \ + /* GHCBData[63:12] */ \ + (((u64)(v) & GENMASK_ULL(63, 12)) >> 12) + +#define GHCB_HV_FT_SNP BIT_ULL(0) +#define GHCB_HV_FT_SNP_AP_CREATION BIT_ULL(1) + +/* SNP Page State Change NAE event */ +#define VMGEXIT_PSC_MAX_ENTRY 253 + +struct psc_hdr { + u16 cur_entry; + u16 end_entry; + u32 reserved; +} __packed; + +struct psc_entry { + u64 cur_page : 12, + gfn : 40, + operation : 4, + pagesize : 1, + reserved : 7; +} __packed; + +struct snp_psc_desc { + struct psc_hdr hdr; + struct psc_entry entries[VMGEXIT_PSC_MAX_ENTRY]; +} __packed; + +/* Guest message request error code */ +#define SNP_GUEST_REQ_INVALID_LEN BIT_ULL(32) #define GHCB_MSR_TERM_REQ 0x100 #define GHCB_MSR_TERM_REASON_SET_POS 12 @@ -73,8 +143,20 @@ /* GHCBData[23:16] */ \ ((((u64)reason_val) & 0xff) << 16)) +/* Error codes from reason set 0 */ +#define SEV_TERM_SET_GEN 0 #define GHCB_SEV_ES_GEN_REQ 0 #define GHCB_SEV_ES_PROT_UNSUPPORTED 1 +#define GHCB_SNP_UNSUPPORTED 2 + +/* Linux-specific reason codes (used with reason set 1) */ +#define SEV_TERM_SET_LINUX 1 +#define GHCB_TERM_REGISTER 0 /* GHCB GPA registration failure */ +#define GHCB_TERM_PSC 1 /* Page State Change failure */ +#define GHCB_TERM_PVALIDATE 2 /* Pvalidate failure */ +#define GHCB_TERM_NOT_VMPL0 3 /* SNP guest is not running at VMPL-0 */ +#define GHCB_TERM_CPUID 4 /* CPUID-validation failure */ +#define GHCB_TERM_CPUID_HV 5 /* CPUID failure during hypervisor fallback */ #define GHCB_RESP_CODE(v) ((v) & GHCB_MSR_INFO_MASK) diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h index ec060c433589..19514524f0f8 100644 --- a/arch/x86/include/asm/sev.h +++ b/arch/x86/include/asm/sev.h @@ -11,9 +11,10 @@ #include <linux/types.h> #include <asm/insn.h> #include <asm/sev-common.h> +#include <asm/bootparam.h> -#define GHCB_PROTO_OUR 0x0001UL -#define GHCB_PROTOCOL_MAX 1ULL +#define GHCB_PROTOCOL_MIN 1ULL +#define GHCB_PROTOCOL_MAX 2ULL #define GHCB_DEFAULT_USAGE 0ULL #define VMGEXIT() { asm volatile("rep; vmmcall\n\r"); } @@ -42,6 +43,24 @@ struct es_em_ctxt { struct es_fault_info fi; }; +/* + * AMD SEV Confidential computing blob structure. The structure is + * defined in OVMF UEFI firmware header: + * https://github.com/tianocore/edk2/blob/master/OvmfPkg/Include/Guid/ConfidentialComputingSevSnpBlob.h + */ +#define CC_BLOB_SEV_HDR_MAGIC 0x45444d41 +struct cc_blob_sev_info { + u32 magic; + u16 version; + u16 reserved; + u64 secrets_phys; + u32 secrets_len; + u32 rsvd1; + u64 cpuid_phys; + u32 cpuid_len; + u32 rsvd2; +} __packed; + void do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code); static inline u64 lower_bits(u64 val, unsigned int bits) @@ -60,6 +79,61 @@ extern void vc_no_ghcb(void); extern void vc_boot_ghcb(void); extern bool handle_vc_boot_ghcb(struct pt_regs *regs); +/* Software defined (when rFlags.CF = 1) */ +#define PVALIDATE_FAIL_NOUPDATE 255 + +/* RMP page size */ +#define RMP_PG_SIZE_4K 0 + +#define RMPADJUST_VMSA_PAGE_BIT BIT(16) + +/* SNP Guest message request */ +struct snp_req_data { + unsigned long req_gpa; + unsigned long resp_gpa; + unsigned long data_gpa; + unsigned int data_npages; +}; + +struct sev_guest_platform_data { + u64 secrets_gpa; +}; + +/* + * The secrets page contains 96-bytes of reserved field that can be used by + * the guest OS. The guest OS uses the area to save the message sequence + * number for each VMPCK. + * + * See the GHCB spec section Secret page layout for the format for this area. + */ +struct secrets_os_area { + u32 msg_seqno_0; + u32 msg_seqno_1; + u32 msg_seqno_2; + u32 msg_seqno_3; + u64 ap_jump_table_pa; + u8 rsvd[40]; + u8 guest_usage[32]; +} __packed; + +#define VMPCK_KEY_LEN 32 + +/* See the SNP spec version 0.9 for secrets page format */ +struct snp_secrets_page_layout { + u32 version; + u32 imien : 1, + rsvd1 : 31; + u32 fms; + u32 rsvd2; + u8 gosvw[16]; + u8 vmpck0[VMPCK_KEY_LEN]; + u8 vmpck1[VMPCK_KEY_LEN]; + u8 vmpck2[VMPCK_KEY_LEN]; + u8 vmpck3[VMPCK_KEY_LEN]; + struct secrets_os_area os_area; + u8 rsvd3[3840]; +} __packed; + #ifdef CONFIG_AMD_MEM_ENCRYPT extern struct static_key_false sev_es_enable_key; extern void __sev_es_ist_enter(struct pt_regs *regs); @@ -87,12 +161,71 @@ extern enum es_result sev_es_ghcb_hv_call(struct ghcb *ghcb, struct es_em_ctxt *ctxt, u64 exit_code, u64 exit_info_1, u64 exit_info_2); +static inline int rmpadjust(unsigned long vaddr, bool rmp_psize, unsigned long attrs) +{ + int rc; + + /* "rmpadjust" mnemonic support in binutils 2.36 and newer */ + asm volatile(".byte 0xF3,0x0F,0x01,0xFE\n\t" + : "=a"(rc) + : "a"(vaddr), "c"(rmp_psize), "d"(attrs) + : "memory", "cc"); + + return rc; +} +static inline int pvalidate(unsigned long vaddr, bool rmp_psize, bool validate) +{ + bool no_rmpupdate; + int rc; + + /* "pvalidate" mnemonic support in binutils 2.36 and newer */ + asm volatile(".byte 0xF2, 0x0F, 0x01, 0xFF\n\t" + CC_SET(c) + : CC_OUT(c) (no_rmpupdate), "=a"(rc) + : "a"(vaddr), "c"(rmp_psize), "d"(validate) + : "memory", "cc"); + + if (no_rmpupdate) + return PVALIDATE_FAIL_NOUPDATE; + + return rc; +} +void setup_ghcb(void); +void __init early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr, + unsigned int npages); +void __init early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr, + unsigned int npages); +void __init snp_prep_memory(unsigned long paddr, unsigned int sz, enum psc_op op); +void snp_set_memory_shared(unsigned long vaddr, unsigned int npages); +void snp_set_memory_private(unsigned long vaddr, unsigned int npages); +void snp_set_wakeup_secondary_cpu(void); +bool snp_init(struct boot_params *bp); +void snp_abort(void); +int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, unsigned long *fw_err); #else static inline void sev_es_ist_enter(struct pt_regs *regs) { } static inline void sev_es_ist_exit(void) { } static inline int sev_es_setup_ap_jump_table(struct real_mode_header *rmh) { return 0; } static inline void sev_es_nmi_complete(void) { } static inline int sev_es_efi_map_ghcbs(pgd_t *pgd) { return 0; } +static inline int pvalidate(unsigned long vaddr, bool rmp_psize, bool validate) { return 0; } +static inline int rmpadjust(unsigned long vaddr, bool rmp_psize, unsigned long attrs) { return 0; } +static inline void setup_ghcb(void) { } +static inline void __init +early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr, unsigned int npages) { } +static inline void __init +early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr, unsigned int npages) { } +static inline void __init snp_prep_memory(unsigned long paddr, unsigned int sz, enum psc_op op) { } +static inline void snp_set_memory_shared(unsigned long vaddr, unsigned int npages) { } +static inline void snp_set_memory_private(unsigned long vaddr, unsigned int npages) { } +static inline void snp_set_wakeup_secondary_cpu(void) { } +static inline bool snp_init(struct boot_params *bp) { return false; } +static inline void snp_abort(void) { } +static inline int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, + unsigned long *fw_err) +{ + return -ENOTTY; +} #endif #endif diff --git a/arch/x86/include/asm/shared/io.h b/arch/x86/include/asm/shared/io.h new file mode 100644 index 000000000000..c0ef921c0586 --- /dev/null +++ b/arch/x86/include/asm/shared/io.h @@ -0,0 +1,34 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_SHARED_IO_H +#define _ASM_X86_SHARED_IO_H + +#include <linux/types.h> + +#define BUILDIO(bwl, bw, type) \ +static inline void __out##bwl(type value, u16 port) \ +{ \ + asm volatile("out" #bwl " %" #bw "0, %w1" \ + : : "a"(value), "Nd"(port)); \ +} \ + \ +static inline type __in##bwl(u16 port) \ +{ \ + type value; \ + asm volatile("in" #bwl " %w1, %" #bw "0" \ + : "=a"(value) : "Nd"(port)); \ + return value; \ +} + +BUILDIO(b, b, u8) +BUILDIO(w, w, u16) +BUILDIO(l, , u32) +#undef BUILDIO + +#define inb __inb +#define inw __inw +#define inl __inl +#define outb __outb +#define outw __outw +#define outl __outl + +#endif diff --git a/arch/x86/include/asm/shared/msr.h b/arch/x86/include/asm/shared/msr.h new file mode 100644 index 000000000000..1e6ec10b3a15 --- /dev/null +++ b/arch/x86/include/asm/shared/msr.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_SHARED_MSR_H +#define _ASM_X86_SHARED_MSR_H + +struct msr { + union { + struct { + u32 l; + u32 h; + }; + u64 q; + }; +}; + +#endif /* _ASM_X86_SHARED_MSR_H */ diff --git a/arch/x86/include/asm/shared/tdx.h b/arch/x86/include/asm/shared/tdx.h new file mode 100644 index 000000000000..e53f26228fbb --- /dev/null +++ b/arch/x86/include/asm/shared/tdx.h @@ -0,0 +1,40 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_SHARED_TDX_H +#define _ASM_X86_SHARED_TDX_H + +#include <linux/bits.h> +#include <linux/types.h> + +#define TDX_HYPERCALL_STANDARD 0 + +#define TDX_HCALL_HAS_OUTPUT BIT(0) +#define TDX_HCALL_ISSUE_STI BIT(1) + +#define TDX_CPUID_LEAF_ID 0x21 +#define TDX_IDENT "IntelTDX " + +#ifndef __ASSEMBLY__ + +/* + * Used in __tdx_hypercall() to pass down and get back registers' values of + * the TDCALL instruction when requesting services from the VMM. + * + * This is a software only structure and not part of the TDX module/VMM ABI. + */ +struct tdx_hypercall_args { + u64 r10; + u64 r11; + u64 r12; + u64 r13; + u64 r14; + u64 r15; +}; + +/* Used to request services from the VMM */ +u64 __tdx_hypercall(struct tdx_hypercall_args *args, unsigned long flags); + +/* Called from __tdx_hypercall() for unrecoverable failure */ +void __tdx_hypercall_failed(void); + +#endif /* !__ASSEMBLY__ */ +#endif /* _ASM_X86_SHARED_TDX_H */ diff --git a/arch/x86/include/asm/smap.h b/arch/x86/include/asm/smap.h index d17b39893b79..bab490379c65 100644 --- a/arch/x86/include/asm/smap.h +++ b/arch/x86/include/asm/smap.h @@ -19,25 +19,14 @@ #ifdef __ASSEMBLY__ -#ifdef CONFIG_X86_SMAP - #define ASM_CLAC \ ALTERNATIVE "", __ASM_CLAC, X86_FEATURE_SMAP #define ASM_STAC \ ALTERNATIVE "", __ASM_STAC, X86_FEATURE_SMAP -#else /* CONFIG_X86_SMAP */ - -#define ASM_CLAC -#define ASM_STAC - -#endif /* CONFIG_X86_SMAP */ - #else /* __ASSEMBLY__ */ -#ifdef CONFIG_X86_SMAP - static __always_inline void clac(void) { /* Note: a barrier is implicit in alternative() */ @@ -76,19 +65,6 @@ static __always_inline void smap_restore(unsigned long flags) #define ASM_STAC \ ALTERNATIVE("", __ASM_STAC, X86_FEATURE_SMAP) -#else /* CONFIG_X86_SMAP */ - -static inline void clac(void) { } -static inline void stac(void) { } - -static inline unsigned long smap_save(void) { return 0; } -static inline void smap_restore(unsigned long flags) { } - -#define ASM_CLAC -#define ASM_STAC - -#endif /* CONFIG_X86_SMAP */ - #endif /* __ASSEMBLY__ */ #endif /* _ASM_X86_SMAP_H */ diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h index 68c257a3de0d..45b18eb94fa1 100644 --- a/arch/x86/include/asm/special_insns.h +++ b/arch/x86/include/asm/special_insns.h @@ -184,14 +184,15 @@ static inline void wbinvd(void) native_wbinvd(); } -#ifdef CONFIG_X86_64 static inline void load_gs_index(unsigned int selector) { +#ifdef CONFIG_X86_64 native_load_gs_index(selector); -} - +#else + loadsegment(gs, selector); #endif +} #endif /* CONFIG_PARAVIRT_XXL */ diff --git a/arch/x86/include/asm/static_call.h b/arch/x86/include/asm/static_call.h index ed4f8bb6c2d9..2d8dacd02643 100644 --- a/arch/x86/include/asm/static_call.h +++ b/arch/x86/include/asm/static_call.h @@ -26,6 +26,7 @@ ".align 4 \n" \ ".globl " STATIC_CALL_TRAMP_STR(name) " \n" \ STATIC_CALL_TRAMP_STR(name) ": \n" \ + ANNOTATE_NOENDBR \ insns " \n" \ ".byte 0x53, 0x43, 0x54 \n" \ ".type " STATIC_CALL_TRAMP_STR(name) ", @function \n" \ @@ -38,6 +39,8 @@ #define ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name) \ __ARCH_DEFINE_STATIC_CALL_TRAMP(name, "ret; int3; nop; nop; nop") +#define ARCH_DEFINE_STATIC_CALL_RET0_TRAMP(name) \ + ARCH_DEFINE_STATIC_CALL_TRAMP(name, __static_call_return0) #define ARCH_ADD_TRAMP_KEY(name) \ asm(".pushsection .static_call_tramp_key, \"a\" \n" \ diff --git a/arch/x86/include/asm/suspend_32.h b/arch/x86/include/asm/suspend_32.h index 7b132d0312eb..a800abb1a992 100644 --- a/arch/x86/include/asm/suspend_32.h +++ b/arch/x86/include/asm/suspend_32.h @@ -19,7 +19,6 @@ struct saved_context { u16 gs; unsigned long cr0, cr2, cr3, cr4; u64 misc_enable; - bool misc_enable_saved; struct saved_msrs saved_msrs; struct desc_ptr gdt_desc; struct desc_ptr idt; @@ -28,6 +27,7 @@ struct saved_context { unsigned long tr; unsigned long safety; unsigned long return_address; + bool misc_enable_saved; } __attribute__((packed)); /* routines for saving/restoring kernel state */ diff --git a/arch/x86/include/asm/suspend_64.h b/arch/x86/include/asm/suspend_64.h index 35bb35d28733..54df06687d83 100644 --- a/arch/x86/include/asm/suspend_64.h +++ b/arch/x86/include/asm/suspend_64.h @@ -14,9 +14,13 @@ * Image of the saved processor state, used by the low level ACPI suspend to * RAM code and by the low level hibernation code. * - * If you modify it, fix arch/x86/kernel/acpi/wakeup_64.S and make sure that - * __save/__restore_processor_state(), defined in arch/x86/kernel/suspend_64.c, - * still work as required. + * If you modify it, check how it is used in arch/x86/kernel/acpi/wakeup_64.S + * and make sure that __save/__restore_processor_state(), defined in + * arch/x86/power/cpu.c, still work as required. + * + * Because the structure is packed, make sure to avoid unaligned members. For + * optimisation purposes but also because tools like kmemleak only search for + * pointers that are aligned. */ struct saved_context { struct pt_regs regs; @@ -36,7 +40,6 @@ struct saved_context { unsigned long cr0, cr2, cr3, cr4; u64 misc_enable; - bool misc_enable_saved; struct saved_msrs saved_msrs; unsigned long efer; u16 gdt_pad; /* Unused */ @@ -48,6 +51,7 @@ struct saved_context { unsigned long tr; unsigned long safety; unsigned long return_address; + bool misc_enable_saved; } __attribute__((packed)); #define loaddebug(thread,register) \ diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h index f70a5108d464..1b07fba11704 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -271,6 +271,7 @@ struct vmcb_seg { u64 base; } __packed; +/* Save area definition for legacy and SEV-MEM guests */ struct vmcb_save_area { struct vmcb_seg es; struct vmcb_seg cs; @@ -282,12 +283,12 @@ struct vmcb_save_area { struct vmcb_seg ldtr; struct vmcb_seg idtr; struct vmcb_seg tr; - u8 reserved_1[43]; + u8 reserved_1[42]; + u8 vmpl; u8 cpl; u8 reserved_2[4]; u64 efer; - u8 reserved_3[104]; - u64 xss; /* Valid for SEV-ES only */ + u8 reserved_3[112]; u64 cr4; u64 cr3; u64 cr0; @@ -297,7 +298,9 @@ struct vmcb_save_area { u64 rip; u8 reserved_4[88]; u64 rsp; - u8 reserved_5[24]; + u64 s_cet; + u64 ssp; + u64 isst_addr; u64 rax; u64 star; u64 lstar; @@ -308,29 +311,145 @@ struct vmcb_save_area { u64 sysenter_esp; u64 sysenter_eip; u64 cr2; - u8 reserved_6[32]; + u8 reserved_5[32]; u64 g_pat; u64 dbgctl; u64 br_from; u64 br_to; u64 last_excp_from; u64 last_excp_to; - - /* - * The following part of the save area is valid only for - * SEV-ES guests when referenced through the GHCB or for - * saving to the host save area. - */ - u8 reserved_7[72]; + u8 reserved_6[72]; u32 spec_ctrl; /* Guest version of SPEC_CTRL at 0x2E0 */ - u8 reserved_7b[4]; +} __packed; + +/* Save area definition for SEV-ES and SEV-SNP guests */ +struct sev_es_save_area { + struct vmcb_seg es; + struct vmcb_seg cs; + struct vmcb_seg ss; + struct vmcb_seg ds; + struct vmcb_seg fs; + struct vmcb_seg gs; + struct vmcb_seg gdtr; + struct vmcb_seg ldtr; + struct vmcb_seg idtr; + struct vmcb_seg tr; + u64 vmpl0_ssp; + u64 vmpl1_ssp; + u64 vmpl2_ssp; + u64 vmpl3_ssp; + u64 u_cet; + u8 reserved_1[2]; + u8 vmpl; + u8 cpl; + u8 reserved_2[4]; + u64 efer; + u8 reserved_3[104]; + u64 xss; + u64 cr4; + u64 cr3; + u64 cr0; + u64 dr7; + u64 dr6; + u64 rflags; + u64 rip; + u64 dr0; + u64 dr1; + u64 dr2; + u64 dr3; + u64 dr0_addr_mask; + u64 dr1_addr_mask; + u64 dr2_addr_mask; + u64 dr3_addr_mask; + u8 reserved_4[24]; + u64 rsp; + u64 s_cet; + u64 ssp; + u64 isst_addr; + u64 rax; + u64 star; + u64 lstar; + u64 cstar; + u64 sfmask; + u64 kernel_gs_base; + u64 sysenter_cs; + u64 sysenter_esp; + u64 sysenter_eip; + u64 cr2; + u8 reserved_5[32]; + u64 g_pat; + u64 dbgctl; + u64 br_from; + u64 br_to; + u64 last_excp_from; + u64 last_excp_to; + u8 reserved_7[80]; u32 pkru; - u8 reserved_7a[20]; - u64 reserved_8; /* rax already available at 0x01f8 */ + u8 reserved_8[20]; + u64 reserved_9; /* rax already available at 0x01f8 */ + u64 rcx; + u64 rdx; + u64 rbx; + u64 reserved_10; /* rsp already available at 0x01d8 */ + u64 rbp; + u64 rsi; + u64 rdi; + u64 r8; + u64 r9; + u64 r10; + u64 r11; + u64 r12; + u64 r13; + u64 r14; + u64 r15; + u8 reserved_11[16]; + u64 guest_exit_info_1; + u64 guest_exit_info_2; + u64 guest_exit_int_info; + u64 guest_nrip; + u64 sev_features; + u64 vintr_ctrl; + u64 guest_exit_code; + u64 virtual_tom; + u64 tlb_id; + u64 pcpu_id; + u64 event_inj; + u64 xcr0; + u8 reserved_12[16]; + + /* Floating point area */ + u64 x87_dp; + u32 mxcsr; + u16 x87_ftw; + u16 x87_fsw; + u16 x87_fcw; + u16 x87_fop; + u16 x87_ds; + u16 x87_cs; + u64 x87_rip; + u8 fpreg_x87[80]; + u8 fpreg_xmm[256]; + u8 fpreg_ymm[256]; +} __packed; + +struct ghcb_save_area { + u8 reserved_1[203]; + u8 cpl; + u8 reserved_2[116]; + u64 xss; + u8 reserved_3[24]; + u64 dr7; + u8 reserved_4[16]; + u64 rip; + u8 reserved_5[88]; + u64 rsp; + u8 reserved_6[24]; + u64 rax; + u8 reserved_7[264]; u64 rcx; u64 rdx; u64 rbx; - u64 reserved_9; /* rsp already available at 0x01d8 */ + u8 reserved_8[8]; u64 rbp; u64 rsi; u64 rdi; @@ -342,22 +461,24 @@ struct vmcb_save_area { u64 r13; u64 r14; u64 r15; - u8 reserved_10[16]; + u8 reserved_9[16]; u64 sw_exit_code; u64 sw_exit_info_1; u64 sw_exit_info_2; u64 sw_scratch; - u8 reserved_11[56]; + u8 reserved_10[56]; u64 xcr0; u8 valid_bitmap[16]; u64 x87_state_gpa; } __packed; +#define GHCB_SHARED_BUF_SIZE 2032 + struct ghcb { - struct vmcb_save_area save; - u8 reserved_save[2048 - sizeof(struct vmcb_save_area)]; + struct ghcb_save_area save; + u8 reserved_save[2048 - sizeof(struct ghcb_save_area)]; - u8 shared_buffer[2032]; + u8 shared_buffer[GHCB_SHARED_BUF_SIZE]; u8 reserved_1[10]; u16 protocol_version; /* negotiated SEV-ES/GHCB protocol version */ @@ -365,13 +486,17 @@ struct ghcb { } __packed; -#define EXPECTED_VMCB_SAVE_AREA_SIZE 1032 +#define EXPECTED_VMCB_SAVE_AREA_SIZE 740 +#define EXPECTED_GHCB_SAVE_AREA_SIZE 1032 +#define EXPECTED_SEV_ES_SAVE_AREA_SIZE 1648 #define EXPECTED_VMCB_CONTROL_AREA_SIZE 1024 #define EXPECTED_GHCB_SIZE PAGE_SIZE static inline void __unused_size_checks(void) { BUILD_BUG_ON(sizeof(struct vmcb_save_area) != EXPECTED_VMCB_SAVE_AREA_SIZE); + BUILD_BUG_ON(sizeof(struct ghcb_save_area) != EXPECTED_GHCB_SAVE_AREA_SIZE); + BUILD_BUG_ON(sizeof(struct sev_es_save_area) != EXPECTED_SEV_ES_SAVE_AREA_SIZE); BUILD_BUG_ON(sizeof(struct vmcb_control_area) != EXPECTED_VMCB_CONTROL_AREA_SIZE); BUILD_BUG_ON(sizeof(struct ghcb) != EXPECTED_GHCB_SIZE); } @@ -441,26 +566,26 @@ struct vmcb { /* GHCB Accessor functions */ #define GHCB_BITMAP_IDX(field) \ - (offsetof(struct vmcb_save_area, field) / sizeof(u64)) + (offsetof(struct ghcb_save_area, field) / sizeof(u64)) #define DEFINE_GHCB_ACCESSORS(field) \ - static inline bool ghcb_##field##_is_valid(const struct ghcb *ghcb) \ + static __always_inline bool ghcb_##field##_is_valid(const struct ghcb *ghcb) \ { \ return test_bit(GHCB_BITMAP_IDX(field), \ (unsigned long *)&ghcb->save.valid_bitmap); \ } \ \ - static inline u64 ghcb_get_##field(struct ghcb *ghcb) \ + static __always_inline u64 ghcb_get_##field(struct ghcb *ghcb) \ { \ return ghcb->save.field; \ } \ \ - static inline u64 ghcb_get_##field##_if_valid(struct ghcb *ghcb) \ + static __always_inline u64 ghcb_get_##field##_if_valid(struct ghcb *ghcb) \ { \ return ghcb_##field##_is_valid(ghcb) ? ghcb->save.field : 0; \ } \ \ - static inline void ghcb_set_##field(struct ghcb *ghcb, u64 value) \ + static __always_inline void ghcb_set_##field(struct ghcb *ghcb, u64 value) \ { \ __set_bit(GHCB_BITMAP_IDX(field), \ (unsigned long *)&ghcb->save.valid_bitmap); \ diff --git a/arch/x86/include/asm/tdx.h b/arch/x86/include/asm/tdx.h new file mode 100644 index 000000000000..020c81a7c729 --- /dev/null +++ b/arch/x86/include/asm/tdx.h @@ -0,0 +1,91 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2021-2022 Intel Corporation */ +#ifndef _ASM_X86_TDX_H +#define _ASM_X86_TDX_H + +#include <linux/init.h> +#include <linux/bits.h> +#include <asm/ptrace.h> +#include <asm/shared/tdx.h> + +/* + * SW-defined error codes. + * + * Bits 47:40 == 0xFF indicate Reserved status code class that never used by + * TDX module. + */ +#define TDX_ERROR _BITUL(63) +#define TDX_SW_ERROR (TDX_ERROR | GENMASK_ULL(47, 40)) +#define TDX_SEAMCALL_VMFAILINVALID (TDX_SW_ERROR | _UL(0xFFFF0000)) + +#ifndef __ASSEMBLY__ + +/* + * Used to gather the output registers values of the TDCALL and SEAMCALL + * instructions when requesting services from the TDX module. + * + * This is a software only structure and not part of the TDX module/VMM ABI. + */ +struct tdx_module_output { + u64 rcx; + u64 rdx; + u64 r8; + u64 r9; + u64 r10; + u64 r11; +}; + +/* + * Used by the #VE exception handler to gather the #VE exception + * info from the TDX module. This is a software only structure + * and not part of the TDX module/VMM ABI. + */ +struct ve_info { + u64 exit_reason; + u64 exit_qual; + /* Guest Linear (virtual) Address */ + u64 gla; + /* Guest Physical Address */ + u64 gpa; + u32 instr_len; + u32 instr_info; +}; + +#ifdef CONFIG_INTEL_TDX_GUEST + +void __init tdx_early_init(void); + +/* Used to communicate with the TDX module */ +u64 __tdx_module_call(u64 fn, u64 rcx, u64 rdx, u64 r8, u64 r9, + struct tdx_module_output *out); + +void tdx_get_ve_info(struct ve_info *ve); + +bool tdx_handle_virt_exception(struct pt_regs *regs, struct ve_info *ve); + +void tdx_safe_halt(void); + +bool tdx_early_handle_ve(struct pt_regs *regs); + +#else + +static inline void tdx_early_init(void) { }; +static inline void tdx_safe_halt(void) { }; + +static inline bool tdx_early_handle_ve(struct pt_regs *regs) { return false; } + +#endif /* CONFIG_INTEL_TDX_GUEST */ + +#if defined(CONFIG_KVM_GUEST) && defined(CONFIG_INTEL_TDX_GUEST) +long tdx_kvm_hypercall(unsigned int nr, unsigned long p1, unsigned long p2, + unsigned long p3, unsigned long p4); +#else +static inline long tdx_kvm_hypercall(unsigned int nr, unsigned long p1, + unsigned long p2, unsigned long p3, + unsigned long p4) +{ + return -ENODEV; +} +#endif /* CONFIG_INTEL_TDX_GUEST && CONFIG_KVM_GUEST */ +#endif /* !__ASSEMBLY__ */ +#endif /* _ASM_X86_TDX_H */ diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index ebec69c35e95..f0cb881c1d69 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -92,7 +92,6 @@ struct thread_info { #define TIF_NOCPUID 15 /* CPUID is not accessible in userland */ #define TIF_NOTSC 16 /* TSC is not accessible in userland */ #define TIF_NOTIFY_SIGNAL 17 /* signal notifications exist */ -#define TIF_SLD 18 /* Restore split lock detection on context switch */ #define TIF_MEMDIE 20 /* is terminating due to OOM killer */ #define TIF_POLLING_NRFLAG 21 /* idle is polling for TIF_NEED_RESCHED */ #define TIF_IO_BITMAP 22 /* uses I/O bitmap */ @@ -116,7 +115,6 @@ struct thread_info { #define _TIF_NOCPUID (1 << TIF_NOCPUID) #define _TIF_NOTSC (1 << TIF_NOTSC) #define _TIF_NOTIFY_SIGNAL (1 << TIF_NOTIFY_SIGNAL) -#define _TIF_SLD (1 << TIF_SLD) #define _TIF_POLLING_NRFLAG (1 << TIF_POLLING_NRFLAG) #define _TIF_IO_BITMAP (1 << TIF_IO_BITMAP) #define _TIF_SPEC_FORCE_UPDATE (1 << TIF_SPEC_FORCE_UPDATE) @@ -128,7 +126,7 @@ struct thread_info { /* flags to check in __switch_to() */ #define _TIF_WORK_CTXSW_BASE \ (_TIF_NOCPUID | _TIF_NOTSC | _TIF_BLOCKSTEP | \ - _TIF_SSBD | _TIF_SPEC_FORCE_UPDATE | _TIF_SLD) + _TIF_SSBD | _TIF_SPEC_FORCE_UPDATE) /* * Avoid calls to __switch_to_xtra() on UP as STIBP is not evaluated. diff --git a/arch/x86/include/asm/timex.h b/arch/x86/include/asm/timex.h index a4a8b1b16c0c..956e4145311b 100644 --- a/arch/x86/include/asm/timex.h +++ b/arch/x86/include/asm/timex.h @@ -5,6 +5,15 @@ #include <asm/processor.h> #include <asm/tsc.h> +static inline unsigned long random_get_entropy(void) +{ + if (!IS_ENABLED(CONFIG_X86_TSC) && + !cpu_feature_enabled(X86_FEATURE_TSC)) + return random_get_entropy_fallback(); + return rdtsc(); +} +#define random_get_entropy random_get_entropy + /* Assume we use the PIT time source for the clock tick */ #define CLOCK_TICK_RATE PIT_TICK_RATE diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h index 9619385bf749..458c891a8273 100644 --- a/arch/x86/include/asm/topology.h +++ b/arch/x86/include/asm/topology.h @@ -212,30 +212,19 @@ static inline long arch_scale_freq_capacity(int cpu) } #define arch_scale_freq_capacity arch_scale_freq_capacity -extern void arch_scale_freq_tick(void); -#define arch_scale_freq_tick arch_scale_freq_tick - extern void arch_set_max_freq_ratio(bool turbo_disabled); -void init_freq_invariance(bool secondary, bool cppc_ready); +extern void freq_invariance_set_perf_ratio(u64 ratio, bool turbo_disabled); #else -static inline void arch_set_max_freq_ratio(bool turbo_disabled) -{ -} -static inline void init_freq_invariance(bool secondary, bool cppc_ready) -{ -} +static inline void arch_set_max_freq_ratio(bool turbo_disabled) { } +static inline void freq_invariance_set_perf_ratio(u64 ratio, bool turbo_disabled) { } #endif +extern void arch_scale_freq_tick(void); +#define arch_scale_freq_tick arch_scale_freq_tick + #ifdef CONFIG_ACPI_CPPC_LIB void init_freq_invariance_cppc(void); #define arch_init_invariance_cppc init_freq_invariance_cppc - -bool amd_set_max_freq_ratio(u64 *ratio); -#else -static inline bool amd_set_max_freq_ratio(u64 *ratio) -{ - return false; -} #endif #endif /* _ASM_X86_TOPOLOGY_H */ diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h index 35317c5c551d..47ecfff2c83d 100644 --- a/arch/x86/include/asm/traps.h +++ b/arch/x86/include/asm/traps.h @@ -13,7 +13,7 @@ #ifdef CONFIG_X86_64 asmlinkage __visible notrace struct pt_regs *sync_regs(struct pt_regs *eregs); asmlinkage __visible notrace -struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s); +struct pt_regs *fixup_bad_iret(struct pt_regs *bad_regs); void __init trap_init(void); asmlinkage __visible noinstr struct pt_regs *vc_switch_off_ist(struct pt_regs *eregs); #endif diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h index 01a300a9700b..fbdc3d951494 100644 --- a/arch/x86/include/asm/tsc.h +++ b/arch/x86/include/asm/tsc.h @@ -20,13 +20,12 @@ extern void disable_TSC(void); static inline cycles_t get_cycles(void) { -#ifndef CONFIG_X86_TSC - if (!boot_cpu_has(X86_FEATURE_TSC)) + if (!IS_ENABLED(CONFIG_X86_TSC) && + !cpu_feature_enabled(X86_FEATURE_TSC)) return 0; -#endif - return rdtsc(); } +#define get_cycles get_cycles extern struct system_counterval_t convert_art_to_tsc(u64 art); extern struct system_counterval_t convert_art_ns_to_tsc(u64 art_ns); diff --git a/arch/x86/include/uapi/asm/amd_hsmp.h b/arch/x86/include/uapi/asm/amd_hsmp.h index 7ee7ba0d63a3..769b939444ae 100644 --- a/arch/x86/include/uapi/asm/amd_hsmp.h +++ b/arch/x86/include/uapi/asm/amd_hsmp.h @@ -31,9 +31,22 @@ enum hsmp_message_ids { HSMP_GET_CCLK_THROTTLE_LIMIT, /* 10h Get CCLK frequency limit in socket */ HSMP_GET_C0_PERCENT, /* 11h Get average C0 residency in socket */ HSMP_SET_NBIO_DPM_LEVEL, /* 12h Set max/min LCLK DPM Level for a given NBIO */ - /* 13h Reserved */ - HSMP_GET_DDR_BANDWIDTH = 0x14, /* 14h Get theoretical maximum and current DDR Bandwidth */ - HSMP_GET_TEMP_MONITOR, /* 15h Get per-DIMM temperature and refresh rates */ + HSMP_GET_NBIO_DPM_LEVEL, /* 13h Get LCLK DPM level min and max for a given NBIO */ + HSMP_GET_DDR_BANDWIDTH, /* 14h Get theoretical maximum and current DDR Bandwidth */ + HSMP_GET_TEMP_MONITOR, /* 15h Get socket temperature */ + HSMP_GET_DIMM_TEMP_RANGE, /* 16h Get per-DIMM temperature range and refresh rate */ + HSMP_GET_DIMM_POWER, /* 17h Get per-DIMM power consumption */ + HSMP_GET_DIMM_THERMAL, /* 18h Get per-DIMM thermal sensors */ + HSMP_GET_SOCKET_FREQ_LIMIT, /* 19h Get current active frequency per socket */ + HSMP_GET_CCLK_CORE_LIMIT, /* 1Ah Get CCLK frequency limit per core */ + HSMP_GET_RAILS_SVI, /* 1Bh Get SVI-based Telemetry for all rails */ + HSMP_GET_SOCKET_FMAX_FMIN, /* 1Ch Get Fmax and Fmin per socket */ + HSMP_GET_IOLINK_BANDWITH, /* 1Dh Get current bandwidth on IO Link */ + HSMP_GET_XGMI_BANDWITH, /* 1Eh Get current bandwidth on xGMI Link */ + HSMP_SET_GMI3_WIDTH, /* 1Fh Set max and min GMI3 Link width */ + HSMP_SET_PCI_RATE, /* 20h Control link rate on PCIe devices */ + HSMP_SET_POWER_MODE, /* 21h Select power efficiency profile policy */ + HSMP_SET_PSTATE_MAX_MIN, /* 22h Set the max and min DF P-State */ HSMP_MSG_ID_MAX, }; @@ -175,8 +188,12 @@ static const struct hsmp_msg_desc hsmp_msg_desc_table[] = { */ {1, 0, HSMP_SET}, - /* RESERVED message */ - {0, 0, HSMP_RSVD}, + /* + * HSMP_GET_NBIO_DPM_LEVEL, num_args = 1, response_sz = 1 + * input: args[0] = nbioid[23:16] + * output: args[0] = max dpm level[15:8] + min dpm level[7:0] + */ + {1, 1, HSMP_GET}, /* * HSMP_GET_DDR_BANDWIDTH, num_args = 0, response_sz = 1 @@ -191,6 +208,93 @@ static const struct hsmp_msg_desc hsmp_msg_desc_table[] = { * [7:5] fractional part */ {0, 1, HSMP_GET}, + + /* + * HSMP_GET_DIMM_TEMP_RANGE, num_args = 1, response_sz = 1 + * input: args[0] = DIMM address[7:0] + * output: args[0] = refresh rate[3] + temperature range[2:0] + */ + {1, 1, HSMP_GET}, + + /* + * HSMP_GET_DIMM_POWER, num_args = 1, response_sz = 1 + * input: args[0] = DIMM address[7:0] + * output: args[0] = DIMM power in mW[31:17] + update rate in ms[16:8] + + * DIMM address[7:0] + */ + {1, 1, HSMP_GET}, + + /* + * HSMP_GET_DIMM_THERMAL, num_args = 1, response_sz = 1 + * input: args[0] = DIMM address[7:0] + * output: args[0] = temperature in degree celcius[31:21] + update rate in ms[16:8] + + * DIMM address[7:0] + */ + {1, 1, HSMP_GET}, + + /* + * HSMP_GET_SOCKET_FREQ_LIMIT, num_args = 0, response_sz = 1 + * output: args[0] = frequency in MHz[31:16] + frequency source[15:0] + */ + {0, 1, HSMP_GET}, + + /* + * HSMP_GET_CCLK_CORE_LIMIT, num_args = 1, response_sz = 1 + * input: args[0] = apic id [31:0] + * output: args[0] = frequency in MHz[31:0] + */ + {1, 1, HSMP_GET}, + + /* + * HSMP_GET_RAILS_SVI, num_args = 0, response_sz = 1 + * output: args[0] = power in mW[31:0] + */ + {0, 1, HSMP_GET}, + + /* + * HSMP_GET_SOCKET_FMAX_FMIN, num_args = 0, response_sz = 1 + * output: args[0] = fmax in MHz[31:16] + fmin in MHz[15:0] + */ + {0, 1, HSMP_GET}, + + /* + * HSMP_GET_IOLINK_BANDWITH, num_args = 1, response_sz = 1 + * input: args[0] = link id[15:8] + bw type[2:0] + * output: args[0] = io bandwidth in Mbps[31:0] + */ + {1, 1, HSMP_GET}, + + /* + * HSMP_GET_XGMI_BANDWITH, num_args = 1, response_sz = 1 + * input: args[0] = link id[15:8] + bw type[2:0] + * output: args[0] = xgmi bandwidth in Mbps[31:0] + */ + {1, 1, HSMP_GET}, + + /* + * HSMP_SET_GMI3_WIDTH, num_args = 1, response_sz = 0 + * input: args[0] = min link width[15:8] + max link width[7:0] + */ + {1, 0, HSMP_SET}, + + /* + * HSMP_SET_PCI_RATE, num_args = 1, response_sz = 1 + * input: args[0] = link rate control value + * output: args[0] = previous link rate control value + */ + {1, 1, HSMP_SET}, + + /* + * HSMP_SET_POWER_MODE, num_args = 1, response_sz = 0 + * input: args[0] = power efficiency mode[2:0] + */ + {1, 0, HSMP_SET}, + + /* + * HSMP_SET_PSTATE_MAX_MIN, num_args = 1, response_sz = 0 + * input: args[0] = min df pstate[15:8] + max df pstate[7:0] + */ + {1, 0, HSMP_SET}, }; /* Reset to default packing */ diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h index b25d3f82c2f3..bea5cdcdf532 100644 --- a/arch/x86/include/uapi/asm/bootparam.h +++ b/arch/x86/include/uapi/asm/bootparam.h @@ -10,6 +10,7 @@ #define SETUP_EFI 4 #define SETUP_APPLE_PROPERTIES 5 #define SETUP_JAILHOUSE 6 +#define SETUP_CC_BLOB 7 #define SETUP_INDIRECT (1<<31) @@ -187,7 +188,8 @@ struct boot_params { __u32 ext_ramdisk_image; /* 0x0c0 */ __u32 ext_ramdisk_size; /* 0x0c4 */ __u32 ext_cmd_line_ptr; /* 0x0c8 */ - __u8 _pad4[116]; /* 0x0cc */ + __u8 _pad4[112]; /* 0x0cc */ + __u32 cc_blob_address; /* 0x13c */ struct edid_info edid_info; /* 0x140 */ struct efi_info efi_info; /* 0x1c0 */ __u32 alt_mem_k; /* 0x1e0 */ diff --git a/arch/x86/include/uapi/asm/svm.h b/arch/x86/include/uapi/asm/svm.h index efa969325ede..f69c168391aa 100644 --- a/arch/x86/include/uapi/asm/svm.h +++ b/arch/x86/include/uapi/asm/svm.h @@ -108,6 +108,14 @@ #define SVM_VMGEXIT_AP_JUMP_TABLE 0x80000005 #define SVM_VMGEXIT_SET_AP_JUMP_TABLE 0 #define SVM_VMGEXIT_GET_AP_JUMP_TABLE 1 +#define SVM_VMGEXIT_PSC 0x80000010 +#define SVM_VMGEXIT_GUEST_REQUEST 0x80000011 +#define SVM_VMGEXIT_EXT_GUEST_REQUEST 0x80000012 +#define SVM_VMGEXIT_AP_CREATION 0x80000013 +#define SVM_VMGEXIT_AP_CREATE_ON_INIT 0 +#define SVM_VMGEXIT_AP_CREATE 1 +#define SVM_VMGEXIT_AP_DESTROY 2 +#define SVM_VMGEXIT_HV_FEATURES 0x8000fffd #define SVM_VMGEXIT_UNSUPPORTED_EVENT 0x8000ffff /* Exit code reserved for hypervisor/software use */ @@ -218,6 +226,11 @@ { SVM_VMGEXIT_NMI_COMPLETE, "vmgexit_nmi_complete" }, \ { SVM_VMGEXIT_AP_HLT_LOOP, "vmgexit_ap_hlt_loop" }, \ { SVM_VMGEXIT_AP_JUMP_TABLE, "vmgexit_ap_jump_table" }, \ + { SVM_VMGEXIT_PSC, "vmgexit_page_state_change" }, \ + { SVM_VMGEXIT_GUEST_REQUEST, "vmgexit_guest_request" }, \ + { SVM_VMGEXIT_EXT_GUEST_REQUEST, "vmgexit_ext_guest_request" }, \ + { SVM_VMGEXIT_AP_CREATION, "vmgexit_ap_creation" }, \ + { SVM_VMGEXIT_HV_FEATURES, "vmgexit_hypervisor_feature" }, \ { SVM_EXIT_ERR, "invalid_guest_state" } diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index c41ef42adbe8..1a2dc328cb5e 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -46,8 +46,6 @@ endif # non-deterministic coverage. KCOV_INSTRUMENT := n -CFLAGS_head$(BITS).o += -fno-stack-protector - CFLAGS_irq.o := -I $(srctree)/$(src)/../include/asm/trace obj-y := process_$(BITS).o signal.o diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 0d01e7f5078c..907cc98b1938 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -65,6 +65,13 @@ static u64 acpi_lapic_addr __initdata = APIC_DEFAULT_PHYS_BASE; static bool acpi_support_online_capable; #endif +#ifdef CONFIG_X86_64 +/* Physical address of the Multiprocessor Wakeup Structure mailbox */ +static u64 acpi_mp_wake_mailbox_paddr; +/* Virtual address of the Multiprocessor Wakeup Structure mailbox */ +static struct acpi_madt_multiproc_wakeup_mailbox *acpi_mp_wake_mailbox; +#endif + #ifdef CONFIG_X86_IO_APIC /* * Locks related to IOAPIC hotplug @@ -336,7 +343,60 @@ acpi_parse_lapic_nmi(union acpi_subtable_headers * header, const unsigned long e return 0; } -#endif /*CONFIG_X86_LOCAL_APIC */ +#ifdef CONFIG_X86_64 +static int acpi_wakeup_cpu(int apicid, unsigned long start_ip) +{ + /* + * Remap mailbox memory only for the first call to acpi_wakeup_cpu(). + * + * Wakeup of secondary CPUs is fully serialized in the core code. + * No need to protect acpi_mp_wake_mailbox from concurrent accesses. + */ + if (!acpi_mp_wake_mailbox) { + acpi_mp_wake_mailbox = memremap(acpi_mp_wake_mailbox_paddr, + sizeof(*acpi_mp_wake_mailbox), + MEMREMAP_WB); + } + + /* + * Mailbox memory is shared between the firmware and OS. Firmware will + * listen on mailbox command address, and once it receives the wakeup + * command, the CPU associated with the given apicid will be booted. + * + * The value of 'apic_id' and 'wakeup_vector' must be visible to the + * firmware before the wakeup command is visible. smp_store_release() + * ensures ordering and visibility. + */ + acpi_mp_wake_mailbox->apic_id = apicid; + acpi_mp_wake_mailbox->wakeup_vector = start_ip; + smp_store_release(&acpi_mp_wake_mailbox->command, + ACPI_MP_WAKE_COMMAND_WAKEUP); + + /* + * Wait for the CPU to wake up. + * + * The CPU being woken up is essentially in a spin loop waiting to be + * woken up. It should not take long for it wake up and acknowledge by + * zeroing out ->command. + * + * ACPI specification doesn't provide any guidance on how long kernel + * has to wait for a wake up acknowledgement. It also doesn't provide + * a way to cancel a wake up request if it takes too long. + * + * In TDX environment, the VMM has control over how long it takes to + * wake up secondary. It can postpone scheduling secondary vCPU + * indefinitely. Giving up on wake up request and reporting error opens + * possible attack vector for VMM: it can wake up a secondary CPU when + * kernel doesn't expect it. Wait until positive result of the wake up + * request. + */ + while (READ_ONCE(acpi_mp_wake_mailbox->command)) + cpu_relax(); + + return 0; +} +#endif /* CONFIG_X86_64 */ +#endif /* CONFIG_X86_LOCAL_APIC */ #ifdef CONFIG_X86_IO_APIC #define MP_ISA_BUS 0 @@ -375,7 +435,7 @@ static void __init mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger, isa_irq_to_gsi[bus_irq] = gsi; } -static int mp_config_acpi_gsi(struct device *dev, u32 gsi, int trigger, +static void mp_config_acpi_gsi(struct device *dev, u32 gsi, int trigger, int polarity) { #ifdef CONFIG_X86_MPPARSE @@ -387,9 +447,9 @@ static int mp_config_acpi_gsi(struct device *dev, u32 gsi, int trigger, u8 pin; if (!acpi_ioapic) - return 0; + return; if (!dev || !dev_is_pci(dev)) - return 0; + return; pdev = to_pci_dev(dev); number = pdev->bus->number; @@ -408,7 +468,6 @@ static int mp_config_acpi_gsi(struct device *dev, u32 gsi, int trigger, mp_save_irq(&mp_irq); #endif - return 0; } static int __init mp_register_ioapic_irq(u8 bus_irq, u8 polarity, @@ -1083,6 +1142,29 @@ static int __init acpi_parse_madt_lapic_entries(void) } return 0; } + +#ifdef CONFIG_X86_64 +static int __init acpi_parse_mp_wake(union acpi_subtable_headers *header, + const unsigned long end) +{ + struct acpi_madt_multiproc_wakeup *mp_wake; + + if (!IS_ENABLED(CONFIG_SMP)) + return -ENODEV; + + mp_wake = (struct acpi_madt_multiproc_wakeup *)header; + if (BAD_MADT_ENTRY(mp_wake, end)) + return -EINVAL; + + acpi_table_print_madt_entry(&header->common); + + acpi_mp_wake_mailbox_paddr = mp_wake->base_address; + + acpi_wake_cpu_handler_update(acpi_wakeup_cpu); + + return 0; +} +#endif /* CONFIG_X86_64 */ #endif /* CONFIG_X86_LOCAL_APIC */ #ifdef CONFIG_X86_IO_APIC @@ -1278,6 +1360,14 @@ static void __init acpi_process_madt(void) smp_found_config = 1; } + +#ifdef CONFIG_X86_64 + /* + * Parse MADT MP Wake entry. + */ + acpi_table_parse_madt(ACPI_MADT_TYPE_MULTIPROC_WAKEUP, + acpi_parse_mp_wake, 1); +#endif } if (error == -EINVAL) { /* @@ -1772,7 +1862,7 @@ int __acpi_release_global_lock(unsigned int *lock) void __init arch_reserve_mem_area(acpi_physical_address addr, size_t size) { - e820__range_add(addr, size, E820_TYPE_ACPI); + e820__range_add(addr, size, E820_TYPE_NVS); e820__update_table_print(); } diff --git a/arch/x86/kernel/acpi/cppc.c b/arch/x86/kernel/acpi/cppc.c index df1644d9b3b6..8b8cbf22461a 100644 --- a/arch/x86/kernel/acpi/cppc.c +++ b/arch/x86/kernel/acpi/cppc.c @@ -50,20 +50,17 @@ int cpc_write_ffh(int cpunum, struct cpc_reg *reg, u64 val) return err; } -bool amd_set_max_freq_ratio(u64 *ratio) +static void amd_set_max_freq_ratio(void) { struct cppc_perf_caps perf_caps; u64 highest_perf, nominal_perf; u64 perf_ratio; int rc; - if (!ratio) - return false; - rc = cppc_get_perf_caps(0, &perf_caps); if (rc) { pr_debug("Could not retrieve perf counters (%d)\n", rc); - return false; + return; } highest_perf = amd_get_highest_perf(); @@ -71,7 +68,7 @@ bool amd_set_max_freq_ratio(u64 *ratio) if (!highest_perf || !nominal_perf) { pr_debug("Could not retrieve highest or nominal performance\n"); - return false; + return; } perf_ratio = div_u64(highest_perf * SCHED_CAPACITY_SCALE, nominal_perf); @@ -79,25 +76,27 @@ bool amd_set_max_freq_ratio(u64 *ratio) perf_ratio = (perf_ratio + SCHED_CAPACITY_SCALE) >> 1; if (!perf_ratio) { pr_debug("Non-zero highest/nominal perf values led to a 0 ratio\n"); - return false; + return; } - *ratio = perf_ratio; - arch_set_max_freq_ratio(false); - - return true; + freq_invariance_set_perf_ratio(perf_ratio, false); } static DEFINE_MUTEX(freq_invariance_lock); void init_freq_invariance_cppc(void) { - static bool secondary; + static bool init_done; - mutex_lock(&freq_invariance_lock); + if (!cpu_feature_enabled(X86_FEATURE_APERFMPERF)) + return; - init_freq_invariance(secondary, true); - secondary = true; + if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) + return; + mutex_lock(&freq_invariance_lock); + if (!init_done) + amd_set_max_freq_ratio(); + init_done = true; mutex_unlock(&freq_invariance_lock); } diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index d374cb3cf024..3c66073e7645 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -338,7 +338,7 @@ next: } } -#if defined(CONFIG_RETPOLINE) && defined(CONFIG_STACK_VALIDATION) +#if defined(CONFIG_RETPOLINE) && defined(CONFIG_OBJTOOL) /* * CALL/JMP *%\reg @@ -507,11 +507,11 @@ void __init_or_module noinline apply_retpolines(s32 *start, s32 *end) } } -#else /* !RETPOLINES || !CONFIG_STACK_VALIDATION */ +#else /* !CONFIG_RETPOLINE || !CONFIG_OBJTOOL */ void __init_or_module noinline apply_retpolines(s32 *start, s32 *end) { } -#endif /* CONFIG_RETPOLINE && CONFIG_STACK_VALIDATION */ +#endif /* CONFIG_RETPOLINE && CONFIG_OBJTOOL */ #ifdef CONFIG_X86_KERNEL_IBT diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index 020c906f7934..190e0f763375 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -188,7 +188,7 @@ int amd_smn_write(u16 node, u32 address, u32 value) EXPORT_SYMBOL_GPL(amd_smn_write); -int amd_cache_northbridges(void) +static int amd_cache_northbridges(void) { const struct pci_device_id *misc_ids = amd_nb_misc_ids; const struct pci_device_id *link_ids = amd_nb_link_ids; @@ -210,14 +210,14 @@ int amd_cache_northbridges(void) } misc = NULL; - while ((misc = next_northbridge(misc, misc_ids)) != NULL) + while ((misc = next_northbridge(misc, misc_ids))) misc_count++; if (!misc_count) return -ENODEV; root = NULL; - while ((root = next_northbridge(root, root_ids)) != NULL) + while ((root = next_northbridge(root, root_ids))) root_count++; if (root_count) { @@ -290,7 +290,6 @@ int amd_cache_northbridges(void) return 0; } -EXPORT_SYMBOL_GPL(amd_cache_northbridges); /* * Ignores subdevice/subvendor but as far as I can figure out diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index b70344bf6600..189d3a5e471a 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -170,7 +170,7 @@ static __init int setup_apicpmtimer(char *s) { apic_calibrate_pmtmr = 1; notsc_setup(NULL); - return 0; + return 1; } __setup("apicpmtimer", setup_apicpmtimer); #endif @@ -320,6 +320,9 @@ int lapic_get_maxlvt(void) #define APIC_DIVISOR 16 #define TSC_DIVISOR 8 +/* i82489DX specific */ +#define I82489DX_BASE_DIVIDER (((0x2) << 18)) + /* * This function sets up the local APIC timer, with a timeout of * 'clocks' APIC bus clock. During calibration we actually call @@ -340,8 +343,14 @@ static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen) else if (boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER)) lvtt_value |= APIC_LVT_TIMER_TSCDEADLINE; + /* + * The i82489DX APIC uses bit 18 and 19 for the base divider. This + * overlaps with bit 18 on integrated APICs, but is not documented + * in the SDM. No problem though. i82489DX equipped systems do not + * have TSC deadline timer. + */ if (!lapic_is_integrated()) - lvtt_value |= SET_APIC_TIMER_BASE(APIC_TIMER_BASE_DIV); + lvtt_value |= I82489DX_BASE_DIVIDER; if (!irqen) lvtt_value |= APIC_LVT_MASKED; @@ -1419,22 +1428,21 @@ void __init apic_intr_mode_init(void) return; case APIC_VIRTUAL_WIRE: pr_info("APIC: Switch to virtual wire mode setup\n"); - default_setup_apic_routing(); break; case APIC_VIRTUAL_WIRE_NO_CONFIG: pr_info("APIC: Switch to virtual wire mode setup with no configuration\n"); upmode = true; - default_setup_apic_routing(); break; case APIC_SYMMETRIC_IO: pr_info("APIC: Switch to symmetric I/O mode setup\n"); - default_setup_apic_routing(); break; case APIC_SYMMETRIC_IO_NO_ROUTING: pr_info("APIC: Switch to symmetric I/O mode setup in no SMP routine\n"); break; } + default_setup_apic_routing(); + if (x86_platform.apic_post_init) x86_platform.apic_post_init(); @@ -2551,6 +2559,16 @@ u32 x86_msi_msg_get_destid(struct msi_msg *msg, bool extid) } EXPORT_SYMBOL_GPL(x86_msi_msg_get_destid); +#ifdef CONFIG_X86_64 +void __init acpi_wake_cpu_handler_update(wakeup_cpu_handler handler) +{ + struct apic **drv; + + for (drv = __apicdrivers; drv < __apicdrivers_end; drv++) + (*drv)->wakeup_secondary_cpu_64 = handler; +} +#endif + /* * Override the generic EOI implementation with an optimized version. * Only called during early boot when only one CPU is active and with diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index c1bb384935b0..a868b76cd3d4 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -65,6 +65,7 @@ #include <asm/irq_remapping.h> #include <asm/hw_irq.h> #include <asm/apic.h> +#include <asm/pgtable.h> #define for_each_ioapic(idx) \ for ((idx) = 0; (idx) < nr_ioapics; (idx)++) @@ -2677,6 +2678,19 @@ static struct resource * __init ioapic_setup_resources(void) return res; } +static void io_apic_set_fixmap(enum fixed_addresses idx, phys_addr_t phys) +{ + pgprot_t flags = FIXMAP_PAGE_NOCACHE; + + /* + * Ensure fixmaps for IOAPIC MMIO respect memory encryption pgprot + * bits, just like normal ioremap(): + */ + flags = pgprot_decrypted(flags); + + __set_fixmap(idx, phys, flags); +} + void __init io_apic_init_mappings(void) { unsigned long ioapic_phys, idx = FIX_IO_APIC_BASE_0; @@ -2709,7 +2723,7 @@ fake_ioapic_page: __func__, PAGE_SIZE, PAGE_SIZE); ioapic_phys = __pa(ioapic_phys); } - set_fixmap_nocache(idx, ioapic_phys); + io_apic_set_fixmap(idx, ioapic_phys); apic_printk(APIC_VERBOSE, "mapped IOAPIC to %08lx (%08lx)\n", __fix_to_virt(idx) + (ioapic_phys & ~PAGE_MASK), ioapic_phys); @@ -2838,7 +2852,7 @@ int mp_register_ioapic(int id, u32 address, u32 gsi_base, ioapics[idx].mp_config.flags = MPC_APIC_USABLE; ioapics[idx].mp_config.apicaddr = address; - set_fixmap_nocache(FIX_IO_APIC_BASE_0 + idx, address); + io_apic_set_fixmap(FIX_IO_APIC_BASE_0 + idx, address); if (bad_ioapic_register(idx)) { clear_fixmap(FIX_IO_APIC_BASE_0 + idx); return -ENODEV; diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index f5a48e66e4f5..482855227964 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -199,7 +199,13 @@ static void __init uv_tsc_check_sync(void) int mmr_shift; char *state; - /* Different returns from different UV BIOS versions */ + /* UV5 guarantees synced TSCs; do not zero TSC_ADJUST */ + if (!is_uv(UV2|UV3|UV4)) { + mark_tsc_async_resets("UV5+"); + return; + } + + /* UV2,3,4, UV BIOS TSC sync state available */ mmr = uv_early_read_mmr(UVH_TSC_SYNC_MMR); mmr_shift = is_uv2_hub() ? UVH_TSC_SYNC_SHIFT_UV2K : UVH_TSC_SYNC_SHIFT; @@ -1340,7 +1346,7 @@ static void __init decode_gam_params(unsigned long ptr) static void __init decode_gam_rng_tbl(unsigned long ptr) { struct uv_gam_range_entry *gre = (struct uv_gam_range_entry *)ptr; - unsigned long lgre = 0; + unsigned long lgre = 0, gend = 0; int index = 0; int sock_min = 999999, pnode_min = 99999; int sock_max = -1, pnode_max = -1; @@ -1374,6 +1380,9 @@ static void __init decode_gam_rng_tbl(unsigned long ptr) flag, size, suffix[order], gre->type, gre->nasid, gre->sockid, gre->pnode); + if (gre->type == UV_GAM_RANGE_TYPE_HOLE) + gend = (unsigned long)gre->limit << UV_GAM_RANGE_SHFT; + /* update to next range start */ lgre = gre->limit; if (sock_min > gre->sockid) @@ -1391,7 +1400,8 @@ static void __init decode_gam_rng_tbl(unsigned long ptr) _max_pnode = pnode_max; _gr_table_len = index; - pr_info("UV: GRT: %d entries, sockets(min:%x,max:%x) pnodes(min:%x,max:%x)\n", index, _min_socket, _max_socket, _min_pnode, _max_pnode); + pr_info("UV: GRT: %d entries, sockets(min:%x,max:%x), pnodes(min:%x,max:%x), gap_end(%d)\n", + index, _min_socket, _max_socket, _min_pnode, _max_pnode, fls64(gend)); } /* Walk through UVsystab decoding the fields */ diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c index 9fb0a2f8b62a..437308004ef2 100644 --- a/arch/x86/kernel/asm-offsets.c +++ b/arch/x86/kernel/asm-offsets.c @@ -18,6 +18,7 @@ #include <asm/bootparam.h> #include <asm/suspend.h> #include <asm/tlbflush.h> +#include <asm/tdx.h> #ifdef CONFIG_XEN #include <xen/interface/xen.h> @@ -66,6 +67,22 @@ static void __used common(void) #endif BLANK(); + OFFSET(TDX_MODULE_rcx, tdx_module_output, rcx); + OFFSET(TDX_MODULE_rdx, tdx_module_output, rdx); + OFFSET(TDX_MODULE_r8, tdx_module_output, r8); + OFFSET(TDX_MODULE_r9, tdx_module_output, r9); + OFFSET(TDX_MODULE_r10, tdx_module_output, r10); + OFFSET(TDX_MODULE_r11, tdx_module_output, r11); + + BLANK(); + OFFSET(TDX_HYPERCALL_r10, tdx_hypercall_args, r10); + OFFSET(TDX_HYPERCALL_r11, tdx_hypercall_args, r11); + OFFSET(TDX_HYPERCALL_r12, tdx_hypercall_args, r12); + OFFSET(TDX_HYPERCALL_r13, tdx_hypercall_args, r13); + OFFSET(TDX_HYPERCALL_r14, tdx_hypercall_args, r14); + OFFSET(TDX_HYPERCALL_r15, tdx_hypercall_args, r15); + + BLANK(); OFFSET(BP_scratch, boot_params, scratch); OFFSET(BP_secure_boot, boot_params, secure_boot); OFFSET(BP_loadflags, boot_params, hdr.loadflags); diff --git a/arch/x86/kernel/cpu/aperfmperf.c b/arch/x86/kernel/cpu/aperfmperf.c index 9ca008f9e9b1..1f60a2b27936 100644 --- a/arch/x86/kernel/cpu/aperfmperf.c +++ b/arch/x86/kernel/cpu/aperfmperf.c @@ -6,146 +6,446 @@ * Copyright (C) 2017 Intel Corp. * Author: Len Brown <len.brown@intel.com> */ - +#include <linux/cpufreq.h> #include <linux/delay.h> #include <linux/ktime.h> #include <linux/math64.h> #include <linux/percpu.h> -#include <linux/cpufreq.h> -#include <linux/smp.h> -#include <linux/sched/isolation.h> #include <linux/rcupdate.h> +#include <linux/sched/isolation.h> +#include <linux/sched/topology.h> +#include <linux/smp.h> +#include <linux/syscore_ops.h> + +#include <asm/cpu.h> +#include <asm/cpu_device_id.h> +#include <asm/intel-family.h> #include "cpu.h" -struct aperfmperf_sample { - unsigned int khz; - atomic_t scfpending; - ktime_t time; - u64 aperf; - u64 mperf; +struct aperfmperf { + seqcount_t seq; + unsigned long last_update; + u64 acnt; + u64 mcnt; + u64 aperf; + u64 mperf; }; -static DEFINE_PER_CPU(struct aperfmperf_sample, samples); +static DEFINE_PER_CPU_SHARED_ALIGNED(struct aperfmperf, cpu_samples) = { + .seq = SEQCNT_ZERO(cpu_samples.seq) +}; -#define APERFMPERF_CACHE_THRESHOLD_MS 10 -#define APERFMPERF_REFRESH_DELAY_MS 10 -#define APERFMPERF_STALE_THRESHOLD_MS 1000 +static void init_counter_refs(void) +{ + u64 aperf, mperf; + + rdmsrl(MSR_IA32_APERF, aperf); + rdmsrl(MSR_IA32_MPERF, mperf); + this_cpu_write(cpu_samples.aperf, aperf); + this_cpu_write(cpu_samples.mperf, mperf); +} + +#if defined(CONFIG_X86_64) && defined(CONFIG_SMP) /* - * aperfmperf_snapshot_khz() - * On the current CPU, snapshot APERF, MPERF, and jiffies - * unless we already did it within 10ms - * calculate kHz, save snapshot + * APERF/MPERF frequency ratio computation. + * + * The scheduler wants to do frequency invariant accounting and needs a <1 + * ratio to account for the 'current' frequency, corresponding to + * freq_curr / freq_max. + * + * Since the frequency freq_curr on x86 is controlled by micro-controller and + * our P-state setting is little more than a request/hint, we need to observe + * the effective frequency 'BusyMHz', i.e. the average frequency over a time + * interval after discarding idle time. This is given by: + * + * BusyMHz = delta_APERF / delta_MPERF * freq_base + * + * where freq_base is the max non-turbo P-state. + * + * The freq_max term has to be set to a somewhat arbitrary value, because we + * can't know which turbo states will be available at a given point in time: + * it all depends on the thermal headroom of the entire package. We set it to + * the turbo level with 4 cores active. + * + * Benchmarks show that's a good compromise between the 1C turbo ratio + * (freq_curr/freq_max would rarely reach 1) and something close to freq_base, + * which would ignore the entire turbo range (a conspicuous part, making + * freq_curr/freq_max always maxed out). + * + * An exception to the heuristic above is the Atom uarch, where we choose the + * highest turbo level for freq_max since Atom's are generally oriented towards + * power efficiency. + * + * Setting freq_max to anything less than the 1C turbo ratio makes the ratio + * freq_curr / freq_max to eventually grow >1, in which case we clip it to 1. */ -static void aperfmperf_snapshot_khz(void *dummy) + +DEFINE_STATIC_KEY_FALSE(arch_scale_freq_key); + +static u64 arch_turbo_freq_ratio = SCHED_CAPACITY_SCALE; +static u64 arch_max_freq_ratio = SCHED_CAPACITY_SCALE; + +void arch_set_max_freq_ratio(bool turbo_disabled) { - u64 aperf, aperf_delta; - u64 mperf, mperf_delta; - struct aperfmperf_sample *s = this_cpu_ptr(&samples); - unsigned long flags; + arch_max_freq_ratio = turbo_disabled ? SCHED_CAPACITY_SCALE : + arch_turbo_freq_ratio; +} +EXPORT_SYMBOL_GPL(arch_set_max_freq_ratio); - local_irq_save(flags); - rdmsrl(MSR_IA32_APERF, aperf); - rdmsrl(MSR_IA32_MPERF, mperf); - local_irq_restore(flags); +static bool __init turbo_disabled(void) +{ + u64 misc_en; + int err; + + err = rdmsrl_safe(MSR_IA32_MISC_ENABLE, &misc_en); + if (err) + return false; + + return (misc_en & MSR_IA32_MISC_ENABLE_TURBO_DISABLE); +} + +static bool __init slv_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq) +{ + int err; + + err = rdmsrl_safe(MSR_ATOM_CORE_RATIOS, base_freq); + if (err) + return false; + + err = rdmsrl_safe(MSR_ATOM_CORE_TURBO_RATIOS, turbo_freq); + if (err) + return false; + + *base_freq = (*base_freq >> 16) & 0x3F; /* max P state */ + *turbo_freq = *turbo_freq & 0x3F; /* 1C turbo */ + + return true; +} + +#define X86_MATCH(model) \ + X86_MATCH_VENDOR_FAM_MODEL_FEATURE(INTEL, 6, \ + INTEL_FAM6_##model, X86_FEATURE_APERFMPERF, NULL) + +static const struct x86_cpu_id has_knl_turbo_ratio_limits[] __initconst = { + X86_MATCH(XEON_PHI_KNL), + X86_MATCH(XEON_PHI_KNM), + {} +}; + +static const struct x86_cpu_id has_skx_turbo_ratio_limits[] __initconst = { + X86_MATCH(SKYLAKE_X), + {} +}; + +static const struct x86_cpu_id has_glm_turbo_ratio_limits[] __initconst = { + X86_MATCH(ATOM_GOLDMONT), + X86_MATCH(ATOM_GOLDMONT_D), + X86_MATCH(ATOM_GOLDMONT_PLUS), + {} +}; + +static bool __init knl_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq, + int num_delta_fratio) +{ + int fratio, delta_fratio, found; + int err, i; + u64 msr; + + err = rdmsrl_safe(MSR_PLATFORM_INFO, base_freq); + if (err) + return false; + + *base_freq = (*base_freq >> 8) & 0xFF; /* max P state */ + + err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT, &msr); + if (err) + return false; + + fratio = (msr >> 8) & 0xFF; + i = 16; + found = 0; + do { + if (found >= num_delta_fratio) { + *turbo_freq = fratio; + return true; + } + + delta_fratio = (msr >> (i + 5)) & 0x7; + + if (delta_fratio) { + found += 1; + fratio -= delta_fratio; + } + + i += 8; + } while (i < 64); + + return true; +} + +static bool __init skx_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq, int size) +{ + u64 ratios, counts; + u32 group_size; + int err, i; + + err = rdmsrl_safe(MSR_PLATFORM_INFO, base_freq); + if (err) + return false; + + *base_freq = (*base_freq >> 8) & 0xFF; /* max P state */ + + err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT, &ratios); + if (err) + return false; + + err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT1, &counts); + if (err) + return false; + + for (i = 0; i < 64; i += 8) { + group_size = (counts >> i) & 0xFF; + if (group_size >= size) { + *turbo_freq = (ratios >> i) & 0xFF; + return true; + } + } + + return false; +} - aperf_delta = aperf - s->aperf; - mperf_delta = mperf - s->mperf; +static bool __init core_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq) +{ + u64 msr; + int err; + + err = rdmsrl_safe(MSR_PLATFORM_INFO, base_freq); + if (err) + return false; + + err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT, &msr); + if (err) + return false; + + *base_freq = (*base_freq >> 8) & 0xFF; /* max P state */ + *turbo_freq = (msr >> 24) & 0xFF; /* 4C turbo */ + + /* The CPU may have less than 4 cores */ + if (!*turbo_freq) + *turbo_freq = msr & 0xFF; /* 1C turbo */ + + return true; +} + +static bool __init intel_set_max_freq_ratio(void) +{ + u64 base_freq, turbo_freq; + u64 turbo_ratio; + if (slv_set_max_freq_ratio(&base_freq, &turbo_freq)) + goto out; + + if (x86_match_cpu(has_glm_turbo_ratio_limits) && + skx_set_max_freq_ratio(&base_freq, &turbo_freq, 1)) + goto out; + + if (x86_match_cpu(has_knl_turbo_ratio_limits) && + knl_set_max_freq_ratio(&base_freq, &turbo_freq, 1)) + goto out; + + if (x86_match_cpu(has_skx_turbo_ratio_limits) && + skx_set_max_freq_ratio(&base_freq, &turbo_freq, 4)) + goto out; + + if (core_set_max_freq_ratio(&base_freq, &turbo_freq)) + goto out; + + return false; + +out: /* - * There is no architectural guarantee that MPERF - * increments faster than we can read it. + * Some hypervisors advertise X86_FEATURE_APERFMPERF + * but then fill all MSR's with zeroes. + * Some CPUs have turbo boost but don't declare any turbo ratio + * in MSR_TURBO_RATIO_LIMIT. */ - if (mperf_delta == 0) - return; + if (!base_freq || !turbo_freq) { + pr_debug("Couldn't determine cpu base or turbo frequency, necessary for scale-invariant accounting.\n"); + return false; + } - s->time = ktime_get(); - s->aperf = aperf; - s->mperf = mperf; - s->khz = div64_u64((cpu_khz * aperf_delta), mperf_delta); - atomic_set_release(&s->scfpending, 0); + turbo_ratio = div_u64(turbo_freq * SCHED_CAPACITY_SCALE, base_freq); + if (!turbo_ratio) { + pr_debug("Non-zero turbo and base frequencies led to a 0 ratio.\n"); + return false; + } + + arch_turbo_freq_ratio = turbo_ratio; + arch_set_max_freq_ratio(turbo_disabled()); + + return true; } -static bool aperfmperf_snapshot_cpu(int cpu, ktime_t now, bool wait) +#ifdef CONFIG_PM_SLEEP +static struct syscore_ops freq_invariance_syscore_ops = { + .resume = init_counter_refs, +}; + +static void register_freq_invariance_syscore_ops(void) { - s64 time_delta = ktime_ms_delta(now, per_cpu(samples.time, cpu)); - struct aperfmperf_sample *s = per_cpu_ptr(&samples, cpu); + register_syscore_ops(&freq_invariance_syscore_ops); +} +#else +static inline void register_freq_invariance_syscore_ops(void) {} +#endif - /* Don't bother re-computing within the cache threshold time. */ - if (time_delta < APERFMPERF_CACHE_THRESHOLD_MS) - return true; +static void freq_invariance_enable(void) +{ + if (static_branch_unlikely(&arch_scale_freq_key)) { + WARN_ON_ONCE(1); + return; + } + static_branch_enable(&arch_scale_freq_key); + register_freq_invariance_syscore_ops(); + pr_info("Estimated ratio of average max frequency by base frequency (times 1024): %llu\n", arch_max_freq_ratio); +} + +void freq_invariance_set_perf_ratio(u64 ratio, bool turbo_disabled) +{ + arch_turbo_freq_ratio = ratio; + arch_set_max_freq_ratio(turbo_disabled); + freq_invariance_enable(); +} + +static void __init bp_init_freq_invariance(void) +{ + if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) + return; - if (!atomic_xchg(&s->scfpending, 1) || wait) - smp_call_function_single(cpu, aperfmperf_snapshot_khz, NULL, wait); + if (intel_set_max_freq_ratio()) + freq_invariance_enable(); +} - /* Return false if the previous iteration was too long ago. */ - return time_delta <= APERFMPERF_STALE_THRESHOLD_MS; +static void disable_freq_invariance_workfn(struct work_struct *work) +{ + static_branch_disable(&arch_scale_freq_key); } -unsigned int aperfmperf_get_khz(int cpu) +static DECLARE_WORK(disable_freq_invariance_work, + disable_freq_invariance_workfn); + +DEFINE_PER_CPU(unsigned long, arch_freq_scale) = SCHED_CAPACITY_SCALE; + +static void scale_freq_tick(u64 acnt, u64 mcnt) { - if (!cpu_khz) - return 0; + u64 freq_scale; - if (!boot_cpu_has(X86_FEATURE_APERFMPERF)) - return 0; + if (!arch_scale_freq_invariant()) + return; - if (!housekeeping_cpu(cpu, HK_TYPE_MISC)) - return 0; + if (check_shl_overflow(acnt, 2*SCHED_CAPACITY_SHIFT, &acnt)) + goto error; - if (rcu_is_idle_cpu(cpu)) - return 0; /* Idle CPUs are completely uninteresting. */ + if (check_mul_overflow(mcnt, arch_max_freq_ratio, &mcnt) || !mcnt) + goto error; - aperfmperf_snapshot_cpu(cpu, ktime_get(), true); - return per_cpu(samples.khz, cpu); + freq_scale = div64_u64(acnt, mcnt); + if (!freq_scale) + goto error; + + if (freq_scale > SCHED_CAPACITY_SCALE) + freq_scale = SCHED_CAPACITY_SCALE; + + this_cpu_write(arch_freq_scale, freq_scale); + return; + +error: + pr_warn("Scheduler frequency invariance went wobbly, disabling!\n"); + schedule_work(&disable_freq_invariance_work); } +#else +static inline void bp_init_freq_invariance(void) { } +static inline void scale_freq_tick(u64 acnt, u64 mcnt) { } +#endif /* CONFIG_X86_64 && CONFIG_SMP */ -void arch_freq_prepare_all(void) +void arch_scale_freq_tick(void) { - ktime_t now = ktime_get(); - bool wait = false; - int cpu; + struct aperfmperf *s = this_cpu_ptr(&cpu_samples); + u64 acnt, mcnt, aperf, mperf; - if (!cpu_khz) + if (!cpu_feature_enabled(X86_FEATURE_APERFMPERF)) return; - if (!boot_cpu_has(X86_FEATURE_APERFMPERF)) - return; + rdmsrl(MSR_IA32_APERF, aperf); + rdmsrl(MSR_IA32_MPERF, mperf); + acnt = aperf - s->aperf; + mcnt = mperf - s->mperf; - for_each_online_cpu(cpu) { - if (!housekeeping_cpu(cpu, HK_TYPE_MISC)) - continue; - if (rcu_is_idle_cpu(cpu)) - continue; /* Idle CPUs are completely uninteresting. */ - if (!aperfmperf_snapshot_cpu(cpu, now, false)) - wait = true; - } + s->aperf = aperf; + s->mperf = mperf; + + raw_write_seqcount_begin(&s->seq); + s->last_update = jiffies; + s->acnt = acnt; + s->mcnt = mcnt; + raw_write_seqcount_end(&s->seq); - if (wait) - msleep(APERFMPERF_REFRESH_DELAY_MS); + scale_freq_tick(acnt, mcnt); } +/* + * Discard samples older than the define maximum sample age of 20ms. There + * is no point in sending IPIs in such a case. If the scheduler tick was + * not running then the CPU is either idle or isolated. + */ +#define MAX_SAMPLE_AGE ((unsigned long)HZ / 50) + unsigned int arch_freq_get_on_cpu(int cpu) { - struct aperfmperf_sample *s = per_cpu_ptr(&samples, cpu); + struct aperfmperf *s = per_cpu_ptr(&cpu_samples, cpu); + unsigned int seq, freq; + unsigned long last; + u64 acnt, mcnt; - if (!cpu_khz) - return 0; + if (!cpu_feature_enabled(X86_FEATURE_APERFMPERF)) + goto fallback; - if (!boot_cpu_has(X86_FEATURE_APERFMPERF)) - return 0; + do { + seq = raw_read_seqcount_begin(&s->seq); + last = s->last_update; + acnt = s->acnt; + mcnt = s->mcnt; + } while (read_seqcount_retry(&s->seq, seq)); - if (!housekeeping_cpu(cpu, HK_TYPE_MISC)) - return 0; + /* + * Bail on invalid count and when the last update was too long ago, + * which covers idle and NOHZ full CPUs. + */ + if (!mcnt || (jiffies - last) > MAX_SAMPLE_AGE) + goto fallback; + + return div64_u64((cpu_khz * acnt), mcnt); + +fallback: + freq = cpufreq_quick_get(cpu); + return freq ? freq : cpu_khz; +} - if (aperfmperf_snapshot_cpu(cpu, ktime_get(), true)) - return per_cpu(samples.khz, cpu); +static int __init bp_init_aperfmperf(void) +{ + if (!cpu_feature_enabled(X86_FEATURE_APERFMPERF)) + return 0; - msleep(APERFMPERF_REFRESH_DELAY_MS); - atomic_set(&s->scfpending, 1); - smp_mb(); /* ->scfpending before smp_call_function_single(). */ - smp_call_function_single(cpu, aperfmperf_snapshot_khz, NULL, 1); + init_counter_refs(); + bp_init_freq_invariance(); + return 0; +} +early_initcall(bp_init_aperfmperf); - return per_cpu(samples.khz, cpu); +void ap_init_aperfmperf(void) +{ + if (cpu_feature_enabled(X86_FEATURE_APERFMPERF)) + init_counter_refs(); } diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 6296e1ebed1d..d879a6c93609 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -446,6 +446,13 @@ void update_srbds_msr(void) if (srbds_mitigation == SRBDS_MITIGATION_UCODE_NEEDED) return; + /* + * A MDS_NO CPU for which SRBDS mitigation is not needed due to TSX + * being disabled and it hasn't received the SRBDS MSR microcode. + */ + if (!boot_cpu_has(X86_FEATURE_SRBDS_CTRL)) + return; + rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl); switch (srbds_mitigation) { diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index ed4417500700..2e9142797c99 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -60,6 +60,7 @@ #include <asm/uv/uv.h> #include <asm/sigframe.h> #include <asm/traps.h> +#include <asm/sev.h> #include "cpu.h" @@ -298,13 +299,6 @@ static int __init cachesize_setup(char *str) } __setup("cachesize=", cachesize_setup); -static int __init x86_sep_setup(char *s) -{ - setup_clear_cpu_cap(X86_FEATURE_SEP); - return 1; -} -__setup("nosep", x86_sep_setup); - /* Standard macro to see if a specific flag is changeable */ static inline int flag_is_changeable_p(u32 flag) { @@ -376,26 +370,12 @@ static inline void squash_the_stupid_serial_number(struct cpuinfo_x86 *c) } #endif -static __init int setup_disable_smep(char *arg) -{ - setup_clear_cpu_cap(X86_FEATURE_SMEP); - return 1; -} -__setup("nosmep", setup_disable_smep); - static __always_inline void setup_smep(struct cpuinfo_x86 *c) { if (cpu_has(c, X86_FEATURE_SMEP)) cr4_set_bits(X86_CR4_SMEP); } -static __init int setup_disable_smap(char *arg) -{ - setup_clear_cpu_cap(X86_FEATURE_SMAP); - return 1; -} -__setup("nosmap", setup_disable_smap); - static __always_inline void setup_smap(struct cpuinfo_x86 *c) { unsigned long eflags = native_save_fl(); @@ -403,14 +383,8 @@ static __always_inline void setup_smap(struct cpuinfo_x86 *c) /* This should have been cleared long ago */ BUG_ON(eflags & X86_EFLAGS_AC); - if (cpu_has(c, X86_FEATURE_SMAP)) { -#ifdef CONFIG_X86_SMAP + if (cpu_has(c, X86_FEATURE_SMAP)) cr4_set_bits(X86_CR4_SMAP); -#else - clear_cpu_cap(c, X86_FEATURE_SMAP); - cr4_clear_bits(X86_CR4_SMAP); -#endif - } } static __always_inline void setup_umip(struct cpuinfo_x86 *c) @@ -1368,8 +1342,8 @@ static void detect_nopl(void) static void __init cpu_parse_early_param(void) { char arg[128]; - char *argptr = arg; - int arglen, res, bit; + char *argptr = arg, *opt; + int arglen, taint = 0; #ifdef CONFIG_X86_32 if (cmdline_find_option_bool(boot_command_line, "no387")) @@ -1397,21 +1371,61 @@ static void __init cpu_parse_early_param(void) return; pr_info("Clearing CPUID bits:"); - do { - res = get_option(&argptr, &bit); - if (res == 0 || res == 3) - break; - /* If the argument was too long, the last bit may be cut off */ - if (res == 1 && arglen >= sizeof(arg)) - break; + while (argptr) { + bool found __maybe_unused = false; + unsigned int bit; - if (bit >= 0 && bit < NCAPINTS * 32) { - pr_cont(" " X86_CAP_FMT, x86_cap_flag(bit)); + opt = strsep(&argptr, ","); + + /* + * Handle naked numbers first for feature flags which don't + * have names. + */ + if (!kstrtouint(opt, 10, &bit)) { + if (bit < NCAPINTS * 32) { + +#ifdef CONFIG_X86_FEATURE_NAMES + /* empty-string, i.e., ""-defined feature flags */ + if (!x86_cap_flags[bit]) + pr_cont(" " X86_CAP_FMT_NUM, x86_cap_flag_num(bit)); + else +#endif + pr_cont(" " X86_CAP_FMT, x86_cap_flag(bit)); + + setup_clear_cpu_cap(bit); + taint++; + } + /* + * The assumption is that there are no feature names with only + * numbers in the name thus go to the next argument. + */ + continue; + } + +#ifdef CONFIG_X86_FEATURE_NAMES + for (bit = 0; bit < 32 * NCAPINTS; bit++) { + if (!x86_cap_flag(bit)) + continue; + + if (strcmp(x86_cap_flag(bit), opt)) + continue; + + pr_cont(" %s", opt); setup_clear_cpu_cap(bit); + taint++; + found = true; + break; } - } while (res == 2); + + if (!found) + pr_cont(" (unknown: %s)", opt); +#endif + } pr_cont("\n"); + + if (taint) + add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_STILL_OK); } /* @@ -1855,15 +1869,9 @@ void identify_secondary_cpu(struct cpuinfo_x86 *c) validate_apic_and_package_id(c); x86_spec_ctrl_setup_ap(); update_srbds_msr(); -} -static __init int setup_noclflush(char *arg) -{ - setup_clear_cpu_cap(X86_FEATURE_CLFLUSH); - setup_clear_cpu_cap(X86_FEATURE_CLFLUSHOPT); - return 1; + tsx_ap_init(); } -__setup("noclflush", setup_noclflush); void print_cpu_info(struct cpuinfo_x86 *c) { @@ -2124,6 +2132,9 @@ void cpu_init_exception_handling(void) load_TR_desc(); + /* GHCB needs to be setup to handle #VC. */ + setup_ghcb(); + /* Finally load the IDT */ load_current_idt(); } diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h index ee6f23f7587d..2a8e584fc991 100644 --- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -55,11 +55,10 @@ enum tsx_ctrl_states { extern __ro_after_init enum tsx_ctrl_states tsx_ctrl_state; extern void __init tsx_init(void); -extern void tsx_enable(void); -extern void tsx_disable(void); -extern void tsx_clear_cpuid(void); +void tsx_ap_init(void); #else static inline void tsx_init(void) { } +static inline void tsx_ap_init(void) { } #endif /* CONFIG_CPU_SUP_INTEL */ extern void get_cpu_cap(struct cpuinfo_x86 *c); diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 8321c43554a1..fd5dead8371c 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -7,10 +7,13 @@ #include <linux/smp.h> #include <linux/sched.h> #include <linux/sched/clock.h> +#include <linux/semaphore.h> #include <linux/thread_info.h> #include <linux/init.h> #include <linux/uaccess.h> +#include <linux/workqueue.h> #include <linux/delay.h> +#include <linux/cpuhotplug.h> #include <asm/cpufeature.h> #include <asm/msr.h> @@ -91,7 +94,7 @@ static bool ring3mwait_disabled __read_mostly; static int __init ring3mwait_disable(char *__unused) { ring3mwait_disabled = true; - return 0; + return 1; } __setup("ring3mwait=disable", ring3mwait_disable); @@ -181,6 +184,38 @@ static bool bad_spectre_microcode(struct cpuinfo_x86 *c) return false; } +int intel_cpu_collect_info(struct ucode_cpu_info *uci) +{ + unsigned int val[2]; + unsigned int family, model; + struct cpu_signature csig = { 0 }; + unsigned int eax, ebx, ecx, edx; + + memset(uci, 0, sizeof(*uci)); + + eax = 0x00000001; + ecx = 0; + native_cpuid(&eax, &ebx, &ecx, &edx); + csig.sig = eax; + + family = x86_family(eax); + model = x86_model(eax); + + if (model >= 5 || family > 6) { + /* get processor flags from MSR 0x17 */ + native_rdmsr(MSR_IA32_PLATFORM_ID, val[0], val[1]); + csig.pf = 1 << ((val[1] >> 18) & 7); + } + + csig.rev = intel_get_microcode_revision(); + + uci->cpu_sig = csig; + uci->valid = 1; + + return 0; +} +EXPORT_SYMBOL_GPL(intel_cpu_collect_info); + static void early_init_intel(struct cpuinfo_x86 *c) { u64 misc_enable; @@ -717,13 +752,6 @@ static void init_intel(struct cpuinfo_x86 *c) init_intel_misc_features(c); - if (tsx_ctrl_state == TSX_CTRL_ENABLE) - tsx_enable(); - else if (tsx_ctrl_state == TSX_CTRL_DISABLE) - tsx_disable(); - else if (tsx_ctrl_state == TSX_CTRL_RTM_ALWAYS_ABORT) - tsx_clear_cpuid(); - split_lock_init(); bus_lock_init(); @@ -1006,6 +1034,8 @@ static const struct { static struct ratelimit_state bld_ratelimit; +static DEFINE_SEMAPHORE(buslock_sem); + static inline bool match_option(const char *arg, int arglen, const char *opt) { int len = strlen(opt), ratelimit; @@ -1116,18 +1146,52 @@ static void split_lock_init(void) split_lock_verify_msr(sld_state != sld_off); } +static void __split_lock_reenable(struct work_struct *work) +{ + sld_update_msr(true); + up(&buslock_sem); +} + +/* + * If a CPU goes offline with pending delayed work to re-enable split lock + * detection then the delayed work will be executed on some other CPU. That + * handles releasing the buslock_sem, but because it executes on a + * different CPU probably won't re-enable split lock detection. This is a + * problem on HT systems since the sibling CPU on the same core may then be + * left running with split lock detection disabled. + * + * Unconditionally re-enable detection here. + */ +static int splitlock_cpu_offline(unsigned int cpu) +{ + sld_update_msr(true); + + return 0; +} + +static DECLARE_DELAYED_WORK(split_lock_reenable, __split_lock_reenable); + static void split_lock_warn(unsigned long ip) { - pr_warn_ratelimited("#AC: %s/%d took a split_lock trap at address: 0x%lx\n", - current->comm, current->pid, ip); + int cpu; - /* - * Disable the split lock detection for this task so it can make - * progress and set TIF_SLD so the detection is re-enabled via - * switch_to_sld() when the task is scheduled out. - */ + if (!current->reported_split_lock) + pr_warn_ratelimited("#AC: %s/%d took a split_lock trap at address: 0x%lx\n", + current->comm, current->pid, ip); + current->reported_split_lock = 1; + + /* misery factor #1, sleep 10ms before trying to execute split lock */ + if (msleep_interruptible(10) > 0) + return; + /* Misery factor #2, only allow one buslocked disabled core at a time */ + if (down_interruptible(&buslock_sem) == -EINTR) + return; + cpu = get_cpu(); + schedule_delayed_work_on(cpu, &split_lock_reenable, 2); + + /* Disable split lock detection on this CPU to make progress */ sld_update_msr(false); - set_tsk_thread_flag(current, TIF_SLD); + put_cpu(); } bool handle_guest_split_lock(unsigned long ip) @@ -1201,18 +1265,6 @@ void handle_bus_lock(struct pt_regs *regs) } /* - * This function is called only when switching between tasks with - * different split-lock detection modes. It sets the MSR for the - * mode of the new task. This is right most of the time, but since - * the MSR is shared by hyperthreads on a physical core there can - * be glitches when the two threads need different modes. - */ -void switch_to_sld(unsigned long tifn) -{ - sld_update_msr(!(tifn & _TIF_SLD)); -} - -/* * Bits in the IA32_CORE_CAPABILITIES are not architectural, so they should * only be trusted if it is confirmed that a CPU model implements a * specific feature at a particular bit position. @@ -1237,6 +1289,7 @@ static const struct x86_cpu_id split_lock_cpu_ids[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, 1), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE, 1), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, 1), + X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE, 1), {} }; @@ -1281,10 +1334,14 @@ static void sld_state_show(void) pr_info("disabled\n"); break; case sld_warn: - if (boot_cpu_has(X86_FEATURE_SPLIT_LOCK_DETECT)) + if (boot_cpu_has(X86_FEATURE_SPLIT_LOCK_DETECT)) { pr_info("#AC: crashing the kernel on kernel split_locks and warning on user-space split_locks\n"); - else if (boot_cpu_has(X86_FEATURE_BUS_LOCK_DETECT)) + if (cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, + "x86/splitlock", NULL, splitlock_cpu_offline) < 0) + pr_warn("No splitlock CPU offline handler\n"); + } else if (boot_cpu_has(X86_FEATURE_BUS_LOCK_DETECT)) { pr_info("#DB: warning on user-space bus_locks\n"); + } break; case sld_fatal: if (boot_cpu_has(X86_FEATURE_SPLIT_LOCK_DETECT)) { diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c index 1940d305db1c..1c87501e0fa3 100644 --- a/arch/x86/kernel/cpu/mce/amd.c +++ b/arch/x86/kernel/cpu/mce/amd.c @@ -1294,10 +1294,23 @@ out_free: kfree(bank); } +static void __threshold_remove_device(struct threshold_bank **bp) +{ + unsigned int bank, numbanks = this_cpu_read(mce_num_banks); + + for (bank = 0; bank < numbanks; bank++) { + if (!bp[bank]) + continue; + + threshold_remove_bank(bp[bank]); + bp[bank] = NULL; + } + kfree(bp); +} + int mce_threshold_remove_device(unsigned int cpu) { struct threshold_bank **bp = this_cpu_read(threshold_banks); - unsigned int bank, numbanks = this_cpu_read(mce_num_banks); if (!bp) return 0; @@ -1308,13 +1321,7 @@ int mce_threshold_remove_device(unsigned int cpu) */ this_cpu_write(threshold_banks, NULL); - for (bank = 0; bank < numbanks; bank++) { - if (bp[bank]) { - threshold_remove_bank(bp[bank]); - bp[bank] = NULL; - } - } - kfree(bp); + __threshold_remove_device(bp); return 0; } @@ -1351,15 +1358,14 @@ int mce_threshold_create_device(unsigned int cpu) if (!(this_cpu_read(bank_map) & (1 << bank))) continue; err = threshold_create_bank(bp, cpu, bank); - if (err) - goto out_err; + if (err) { + __threshold_remove_device(bp); + return err; + } } this_cpu_write(threshold_banks, bp); if (thresholding_irq_en) mce_threshold_vector = amd_threshold_interrupt; return 0; -out_err: - mce_threshold_remove_device(cpu); - return err; } diff --git a/arch/x86/kernel/cpu/mce/apei.c b/arch/x86/kernel/cpu/mce/apei.c index 0e3ae64d3b76..717192915f28 100644 --- a/arch/x86/kernel/cpu/mce/apei.c +++ b/arch/x86/kernel/cpu/mce/apei.c @@ -177,16 +177,14 @@ retry: /* no more record */ if (*record_id == APEI_ERST_INVALID_RECORD_ID) goto out; - rc = erst_read(*record_id, &rcd.hdr, sizeof(rcd)); + rc = erst_read_record(*record_id, &rcd.hdr, sizeof(rcd), sizeof(rcd), + &CPER_CREATOR_MCE); /* someone else has cleared the record, try next one */ if (rc == -ENOENT) goto retry; else if (rc < 0) goto out; - /* try to skip other type records in storage */ - else if (rc != sizeof(rcd) || - !guid_equal(&rcd.hdr.creator_id, &CPER_CREATOR_MCE)) - goto retry; + memcpy(m, &rcd.mce, sizeof(*m)); rc = sizeof(*m); out: diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 981496e6bc0e..d775fcd74e98 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -69,7 +69,9 @@ DEFINE_PER_CPU_READ_MOSTLY(unsigned int, mce_num_banks); struct mce_bank { u64 ctl; /* subevents to enable */ - bool init; /* initialise bank? */ + + __u64 init : 1, /* initialise bank? */ + __reserved_1 : 63; }; static DEFINE_PER_CPU_READ_MOSTLY(struct mce_bank[MAX_NR_BANKS], mce_banks_array); diff --git a/arch/x86/kernel/cpu/mce/severity.c b/arch/x86/kernel/cpu/mce/severity.c index 1add86935349..00483d1c27e4 100644 --- a/arch/x86/kernel/cpu/mce/severity.c +++ b/arch/x86/kernel/cpu/mce/severity.c @@ -301,85 +301,65 @@ static noinstr int error_context(struct mce *m, struct pt_regs *regs) } } -static __always_inline int mce_severity_amd_smca(struct mce *m, enum context err_ctx) +/* See AMD PPR(s) section Machine Check Error Handling. */ +static noinstr int mce_severity_amd(struct mce *m, struct pt_regs *regs, char **msg, bool is_excp) { - u64 mcx_cfg; + char *panic_msg = NULL; + int ret; /* - * We need to look at the following bits: - * - "succor" bit (data poisoning support), and - * - TCC bit (Task Context Corrupt) - * in MCi_STATUS to determine error severity. + * Default return value: Action required, the error must be handled + * immediately. */ - if (!mce_flags.succor) - return MCE_PANIC_SEVERITY; - - mcx_cfg = mce_rdmsrl(MSR_AMD64_SMCA_MCx_CONFIG(m->bank)); - - /* TCC (Task context corrupt). If set and if IN_KERNEL, panic. */ - if ((mcx_cfg & MCI_CONFIG_MCAX) && - (m->status & MCI_STATUS_TCC) && - (err_ctx == IN_KERNEL)) - return MCE_PANIC_SEVERITY; - - /* ...otherwise invoke hwpoison handler. */ - return MCE_AR_SEVERITY; -} - -/* - * See AMD Error Scope Hierarchy table in a newer BKDG. For example - * 49125_15h_Models_30h-3Fh_BKDG.pdf, section "RAS Features" - */ -static noinstr int mce_severity_amd(struct mce *m, struct pt_regs *regs, char **msg, bool is_excp) -{ - enum context ctx = error_context(m, regs); + ret = MCE_AR_SEVERITY; /* Processor Context Corrupt, no need to fumble too much, die! */ - if (m->status & MCI_STATUS_PCC) - return MCE_PANIC_SEVERITY; - - if (m->status & MCI_STATUS_UC) { - - if (ctx == IN_KERNEL) - return MCE_PANIC_SEVERITY; + if (m->status & MCI_STATUS_PCC) { + panic_msg = "Processor Context Corrupt"; + ret = MCE_PANIC_SEVERITY; + goto out; + } - /* - * On older systems where overflow_recov flag is not present, we - * should simply panic if an error overflow occurs. If - * overflow_recov flag is present and set, then software can try - * to at least kill process to prolong system operation. - */ - if (mce_flags.overflow_recov) { - if (mce_flags.smca) - return mce_severity_amd_smca(m, ctx); - - /* kill current process */ - return MCE_AR_SEVERITY; - } else { - /* at least one error was not logged */ - if (m->status & MCI_STATUS_OVER) - return MCE_PANIC_SEVERITY; - } - - /* - * For any other case, return MCE_UC_SEVERITY so that we log the - * error and exit #MC handler. - */ - return MCE_UC_SEVERITY; + if (m->status & MCI_STATUS_DEFERRED) { + ret = MCE_DEFERRED_SEVERITY; + goto out; } /* - * deferred error: poll handler catches these and adds to mce_ring so - * memory-failure can take recovery actions. + * If the UC bit is not set, the system either corrected or deferred + * the error. No action will be required after logging the error. */ - if (m->status & MCI_STATUS_DEFERRED) - return MCE_DEFERRED_SEVERITY; + if (!(m->status & MCI_STATUS_UC)) { + ret = MCE_KEEP_SEVERITY; + goto out; + } /* - * corrected error: poll handler catches these and passes responsibility - * of decoding the error to EDAC + * On MCA overflow, without the MCA overflow recovery feature the + * system will not be able to recover, panic. */ - return MCE_KEEP_SEVERITY; + if ((m->status & MCI_STATUS_OVER) && !mce_flags.overflow_recov) { + panic_msg = "Overflowed uncorrected error without MCA Overflow Recovery"; + ret = MCE_PANIC_SEVERITY; + goto out; + } + + if (!mce_flags.succor) { + panic_msg = "Uncorrected error without MCA Recovery"; + ret = MCE_PANIC_SEVERITY; + goto out; + } + + if (error_context(m, regs) == IN_KERNEL) { + panic_msg = "Uncorrected unrecoverable error in kernel context"; + ret = MCE_PANIC_SEVERITY; + } + +out: + if (msg && panic_msg) + *msg = panic_msg; + + return ret; } static noinstr int mce_severity_intel(struct mce *m, struct pt_regs *regs, char **msg, bool is_excp) diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index f955d25076ba..239ff5fcec6a 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -758,9 +758,9 @@ static struct subsys_interface mc_cpu_interface = { }; /** - * mc_bp_resume - Update boot CPU microcode during resume. + * microcode_bsp_resume - Update boot CPU microcode during resume. */ -static void mc_bp_resume(void) +void microcode_bsp_resume(void) { int cpu = smp_processor_id(); struct ucode_cpu_info *uci = ucode_cpu_info + cpu; @@ -772,7 +772,7 @@ static void mc_bp_resume(void) } static struct syscore_ops mc_syscore_ops = { - .resume = mc_bp_resume, + .resume = microcode_bsp_resume, }; static int mc_cpu_starting(unsigned int cpu) diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index d28a9f8f3fec..025c8f0cd948 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -45,20 +45,6 @@ static struct microcode_intel *intel_ucode_patch; /* last level cache size per core */ static int llc_size_per_core; -static inline bool cpu_signatures_match(unsigned int s1, unsigned int p1, - unsigned int s2, unsigned int p2) -{ - if (s1 != s2) - return false; - - /* Processor flags are either both 0 ... */ - if (!p1 && !p2) - return true; - - /* ... or they intersect. */ - return p1 & p2; -} - /* * Returns 1 if update has been found, 0 otherwise. */ @@ -69,7 +55,7 @@ static int find_matching_signature(void *mc, unsigned int csig, int cpf) struct extended_signature *ext_sig; int i; - if (cpu_signatures_match(csig, cpf, mc_hdr->sig, mc_hdr->pf)) + if (intel_cpu_signatures_match(csig, cpf, mc_hdr->sig, mc_hdr->pf)) return 1; /* Look for ext. headers: */ @@ -80,7 +66,7 @@ static int find_matching_signature(void *mc, unsigned int csig, int cpf) ext_sig = (void *)ext_hdr + EXT_HEADER_SIZE; for (i = 0; i < ext_hdr->count; i++) { - if (cpu_signatures_match(csig, cpf, ext_sig->sig, ext_sig->pf)) + if (intel_cpu_signatures_match(csig, cpf, ext_sig->sig, ext_sig->pf)) return 1; ext_sig++; } @@ -342,37 +328,6 @@ next: return patch; } -static int collect_cpu_info_early(struct ucode_cpu_info *uci) -{ - unsigned int val[2]; - unsigned int family, model; - struct cpu_signature csig = { 0 }; - unsigned int eax, ebx, ecx, edx; - - memset(uci, 0, sizeof(*uci)); - - eax = 0x00000001; - ecx = 0; - native_cpuid(&eax, &ebx, &ecx, &edx); - csig.sig = eax; - - family = x86_family(eax); - model = x86_model(eax); - - if ((model >= 5) || (family > 6)) { - /* get processor flags from MSR 0x17 */ - native_rdmsr(MSR_IA32_PLATFORM_ID, val[0], val[1]); - csig.pf = 1 << ((val[1] >> 18) & 7); - } - - csig.rev = intel_get_microcode_revision(); - - uci->cpu_sig = csig; - uci->valid = 1; - - return 0; -} - static void show_saved_mc(void) { #ifdef DEBUG @@ -386,7 +341,7 @@ static void show_saved_mc(void) return; } - collect_cpu_info_early(&uci); + intel_cpu_collect_info(&uci); sig = uci.cpu_sig.sig; pf = uci.cpu_sig.pf; @@ -502,7 +457,7 @@ void show_ucode_info_early(void) struct ucode_cpu_info uci; if (delay_ucode_info) { - collect_cpu_info_early(&uci); + intel_cpu_collect_info(&uci); print_ucode_info(&uci, current_mc_date); delay_ucode_info = 0; } @@ -604,7 +559,7 @@ int __init save_microcode_in_initrd_intel(void) if (!(cp.data && cp.size)) return 0; - collect_cpu_info_early(&uci); + intel_cpu_collect_info(&uci); scan_microcode(cp.data, cp.size, &uci, true); @@ -637,7 +592,7 @@ static struct microcode_intel *__load_ucode_intel(struct ucode_cpu_info *uci) if (!(cp.data && cp.size)) return NULL; - collect_cpu_info_early(uci); + intel_cpu_collect_info(uci); return scan_microcode(cp.data, cp.size, uci, false); } @@ -712,7 +667,7 @@ void reload_ucode_intel(void) struct microcode_intel *p; struct ucode_cpu_info uci; - collect_cpu_info_early(&uci); + intel_cpu_collect_info(&uci); p = find_patch(&uci); if (!p) diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c index 4eec8889b0ff..099b6f0d96bd 100644 --- a/arch/x86/kernel/cpu/proc.c +++ b/arch/x86/kernel/cpu/proc.c @@ -84,14 +84,9 @@ static int show_cpuinfo(struct seq_file *m, void *v) seq_printf(m, "microcode\t: 0x%x\n", c->microcode); if (cpu_has(c, X86_FEATURE_TSC)) { - unsigned int freq = aperfmperf_get_khz(cpu); - - if (!freq) - freq = cpufreq_quick_get(cpu); - if (!freq) - freq = cpu_khz; - seq_printf(m, "cpu MHz\t\t: %u.%03u\n", - freq / 1000, (freq % 1000)); + unsigned int freq = arch_freq_get_on_cpu(cpu); + + seq_printf(m, "cpu MHz\t\t: %u.%03u\n", freq / 1000, (freq % 1000)); } /* Cache size */ diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 83f901e2c2df..f276aff521e8 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -341,14 +341,14 @@ static int cpus_mon_write(struct rdtgroup *rdtgrp, cpumask_var_t newmask, /* Check whether cpus belong to parent ctrl group */ cpumask_andnot(tmpmask, newmask, &prgrp->cpu_mask); - if (cpumask_weight(tmpmask)) { + if (!cpumask_empty(tmpmask)) { rdt_last_cmd_puts("Can only add CPUs to mongroup that belong to parent\n"); return -EINVAL; } /* Check whether cpus are dropped from this group */ cpumask_andnot(tmpmask, &rdtgrp->cpu_mask, newmask); - if (cpumask_weight(tmpmask)) { + if (!cpumask_empty(tmpmask)) { /* Give any dropped cpus to parent rdtgroup */ cpumask_or(&prgrp->cpu_mask, &prgrp->cpu_mask, tmpmask); update_closid_rmid(tmpmask, prgrp); @@ -359,7 +359,7 @@ static int cpus_mon_write(struct rdtgroup *rdtgrp, cpumask_var_t newmask, * and update per-cpu rmid */ cpumask_andnot(tmpmask, newmask, &rdtgrp->cpu_mask); - if (cpumask_weight(tmpmask)) { + if (!cpumask_empty(tmpmask)) { head = &prgrp->mon.crdtgrp_list; list_for_each_entry(crgrp, head, mon.crdtgrp_list) { if (crgrp == rdtgrp) @@ -394,7 +394,7 @@ static int cpus_ctrl_write(struct rdtgroup *rdtgrp, cpumask_var_t newmask, /* Check whether cpus are dropped from this group */ cpumask_andnot(tmpmask, &rdtgrp->cpu_mask, newmask); - if (cpumask_weight(tmpmask)) { + if (!cpumask_empty(tmpmask)) { /* Can't drop from default group */ if (rdtgrp == &rdtgroup_default) { rdt_last_cmd_puts("Can't drop CPUs from default group\n"); @@ -413,12 +413,12 @@ static int cpus_ctrl_write(struct rdtgroup *rdtgrp, cpumask_var_t newmask, * and update per-cpu closid/rmid. */ cpumask_andnot(tmpmask, newmask, &rdtgrp->cpu_mask); - if (cpumask_weight(tmpmask)) { + if (!cpumask_empty(tmpmask)) { list_for_each_entry(r, &rdt_all_groups, rdtgroup_list) { if (r == rdtgrp) continue; cpumask_and(tmpmask1, &r->cpu_mask, tmpmask); - if (cpumask_weight(tmpmask1)) + if (!cpumask_empty(tmpmask1)) cpumask_rdtgrp_clear(r, tmpmask1); } update_closid_rmid(tmpmask, rdtgrp); @@ -488,7 +488,7 @@ static ssize_t rdtgroup_cpus_write(struct kernfs_open_file *of, /* check that user didn't specify any offline cpus */ cpumask_andnot(tmpmask, newmask, cpu_online_mask); - if (cpumask_weight(tmpmask)) { + if (!cpumask_empty(tmpmask)) { ret = -EINVAL; rdt_last_cmd_puts("Can only assign online CPUs\n"); goto unlock; diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index 4143b1e4c5c6..dbaa8326d6f2 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -43,6 +43,7 @@ static const struct cpuid_bit cpuid_bits[] = { { X86_FEATURE_CPB, CPUID_EDX, 9, 0x80000007, 0 }, { X86_FEATURE_PROC_FEEDBACK, CPUID_EDX, 11, 0x80000007, 0 }, { X86_FEATURE_MBA, CPUID_EBX, 6, 0x80000008, 0 }, + { X86_FEATURE_PERFMON_V2, CPUID_EAX, 0, 0x80000022, 0 }, { 0, 0, 0, 0, 0 } }; diff --git a/arch/x86/kernel/cpu/sgx/encl.c b/arch/x86/kernel/cpu/sgx/encl.c index 7c63a1911fae..3c24e6124d95 100644 --- a/arch/x86/kernel/cpu/sgx/encl.c +++ b/arch/x86/kernel/cpu/sgx/encl.c @@ -12,6 +12,92 @@ #include "encls.h" #include "sgx.h" +#define PCMDS_PER_PAGE (PAGE_SIZE / sizeof(struct sgx_pcmd)) +/* + * 32 PCMD entries share a PCMD page. PCMD_FIRST_MASK is used to + * determine the page index associated with the first PCMD entry + * within a PCMD page. + */ +#define PCMD_FIRST_MASK GENMASK(4, 0) + +/** + * reclaimer_writing_to_pcmd() - Query if any enclave page associated with + * a PCMD page is in process of being reclaimed. + * @encl: Enclave to which PCMD page belongs + * @start_addr: Address of enclave page using first entry within the PCMD page + * + * When an enclave page is reclaimed some Paging Crypto MetaData (PCMD) is + * stored. The PCMD data of a reclaimed enclave page contains enough + * information for the processor to verify the page at the time + * it is loaded back into the Enclave Page Cache (EPC). + * + * The backing storage to which enclave pages are reclaimed is laid out as + * follows: + * Encrypted enclave pages:SECS page:PCMD pages + * + * Each PCMD page contains the PCMD metadata of + * PAGE_SIZE/sizeof(struct sgx_pcmd) enclave pages. + * + * A PCMD page can only be truncated if it is (a) empty, and (b) not in the + * process of getting data (and thus soon being non-empty). (b) is tested with + * a check if an enclave page sharing the PCMD page is in the process of being + * reclaimed. + * + * The reclaimer sets the SGX_ENCL_PAGE_BEING_RECLAIMED flag when it + * intends to reclaim that enclave page - it means that the PCMD page + * associated with that enclave page is about to get some data and thus + * even if the PCMD page is empty, it should not be truncated. + * + * Context: Enclave mutex (&sgx_encl->lock) must be held. + * Return: 1 if the reclaimer is about to write to the PCMD page + * 0 if the reclaimer has no intention to write to the PCMD page + */ +static int reclaimer_writing_to_pcmd(struct sgx_encl *encl, + unsigned long start_addr) +{ + int reclaimed = 0; + int i; + + /* + * PCMD_FIRST_MASK is based on number of PCMD entries within + * PCMD page being 32. + */ + BUILD_BUG_ON(PCMDS_PER_PAGE != 32); + + for (i = 0; i < PCMDS_PER_PAGE; i++) { + struct sgx_encl_page *entry; + unsigned long addr; + + addr = start_addr + i * PAGE_SIZE; + + /* + * Stop when reaching the SECS page - it does not + * have a page_array entry and its reclaim is + * started and completed with enclave mutex held so + * it does not use the SGX_ENCL_PAGE_BEING_RECLAIMED + * flag. + */ + if (addr == encl->base + encl->size) + break; + + entry = xa_load(&encl->page_array, PFN_DOWN(addr)); + if (!entry) + continue; + + /* + * VA page slot ID uses same bit as the flag so it is important + * to ensure that the page is not already in backing store. + */ + if (entry->epc_page && + (entry->desc & SGX_ENCL_PAGE_BEING_RECLAIMED)) { + reclaimed = 1; + break; + } + } + + return reclaimed; +} + /* * Calculate byte offset of a PCMD struct associated with an enclave page. PCMD's * follow right after the EPC data in the backing storage. In addition to the @@ -47,6 +133,7 @@ static int __sgx_encl_eldu(struct sgx_encl_page *encl_page, unsigned long va_offset = encl_page->desc & SGX_ENCL_PAGE_VA_OFFSET_MASK; struct sgx_encl *encl = encl_page->encl; pgoff_t page_index, page_pcmd_off; + unsigned long pcmd_first_page; struct sgx_pageinfo pginfo; struct sgx_backing b; bool pcmd_page_empty; @@ -58,6 +145,11 @@ static int __sgx_encl_eldu(struct sgx_encl_page *encl_page, else page_index = PFN_DOWN(encl->size); + /* + * Address of enclave page using the first entry within the PCMD page. + */ + pcmd_first_page = PFN_PHYS(page_index & ~PCMD_FIRST_MASK) + encl->base; + page_pcmd_off = sgx_encl_get_backing_page_pcmd_offset(encl, page_index); ret = sgx_encl_get_backing(encl, page_index, &b); @@ -84,6 +176,7 @@ static int __sgx_encl_eldu(struct sgx_encl_page *encl_page, } memset(pcmd_page + b.pcmd_offset, 0, sizeof(struct sgx_pcmd)); + set_page_dirty(b.pcmd); /* * The area for the PCMD in the page was zeroed above. Check if the @@ -94,12 +187,20 @@ static int __sgx_encl_eldu(struct sgx_encl_page *encl_page, kunmap_atomic(pcmd_page); kunmap_atomic((void *)(unsigned long)pginfo.contents); - sgx_encl_put_backing(&b, false); + get_page(b.pcmd); + sgx_encl_put_backing(&b); sgx_encl_truncate_backing_page(encl, page_index); - if (pcmd_page_empty) + if (pcmd_page_empty && !reclaimer_writing_to_pcmd(encl, pcmd_first_page)) { sgx_encl_truncate_backing_page(encl, PFN_DOWN(page_pcmd_off)); + pcmd_page = kmap_atomic(b.pcmd); + if (memchr_inv(pcmd_page, 0, PAGE_SIZE)) + pr_warn("PCMD page not empty after truncate.\n"); + kunmap_atomic(pcmd_page); + } + + put_page(b.pcmd); return ret; } @@ -645,15 +746,9 @@ int sgx_encl_get_backing(struct sgx_encl *encl, unsigned long page_index, /** * sgx_encl_put_backing() - Unpin the backing storage * @backing: data for accessing backing storage for the page - * @do_write: mark pages dirty */ -void sgx_encl_put_backing(struct sgx_backing *backing, bool do_write) +void sgx_encl_put_backing(struct sgx_backing *backing) { - if (do_write) { - set_page_dirty(backing->pcmd); - set_page_dirty(backing->contents); - } - put_page(backing->pcmd); put_page(backing->contents); } diff --git a/arch/x86/kernel/cpu/sgx/encl.h b/arch/x86/kernel/cpu/sgx/encl.h index fec43ca65065..d44e7372151f 100644 --- a/arch/x86/kernel/cpu/sgx/encl.h +++ b/arch/x86/kernel/cpu/sgx/encl.h @@ -107,7 +107,7 @@ void sgx_encl_release(struct kref *ref); int sgx_encl_mm_add(struct sgx_encl *encl, struct mm_struct *mm); int sgx_encl_get_backing(struct sgx_encl *encl, unsigned long page_index, struct sgx_backing *backing); -void sgx_encl_put_backing(struct sgx_backing *backing, bool do_write); +void sgx_encl_put_backing(struct sgx_backing *backing); int sgx_encl_test_and_clear_young(struct mm_struct *mm, struct sgx_encl_page *page); diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c index 8e4bc6453d26..ab4ec54bbdd9 100644 --- a/arch/x86/kernel/cpu/sgx/main.c +++ b/arch/x86/kernel/cpu/sgx/main.c @@ -191,6 +191,8 @@ static int __sgx_encl_ewb(struct sgx_epc_page *epc_page, void *va_slot, backing->pcmd_offset; ret = __ewb(&pginfo, sgx_get_epc_virt_addr(epc_page), va_slot); + set_page_dirty(backing->pcmd); + set_page_dirty(backing->contents); kunmap_atomic((void *)(unsigned long)(pginfo.metadata - backing->pcmd_offset)); @@ -308,6 +310,7 @@ static void sgx_reclaimer_write(struct sgx_epc_page *epc_page, sgx_encl_ewb(epc_page, backing); encl_page->epc_page = NULL; encl->secs_child_cnt--; + sgx_encl_put_backing(backing); if (!encl->secs_child_cnt && test_bit(SGX_ENCL_INITIALIZED, &encl->flags)) { ret = sgx_encl_get_backing(encl, PFN_DOWN(encl->size), @@ -320,7 +323,7 @@ static void sgx_reclaimer_write(struct sgx_epc_page *epc_page, sgx_encl_free_epc_page(encl->secs.epc_page); encl->secs.epc_page = NULL; - sgx_encl_put_backing(&secs_backing, true); + sgx_encl_put_backing(&secs_backing); } out: @@ -379,11 +382,14 @@ static void sgx_reclaim_pages(void) goto skip; page_index = PFN_DOWN(encl_page->desc - encl_page->encl->base); + + mutex_lock(&encl_page->encl->lock); ret = sgx_encl_get_backing(encl_page->encl, page_index, &backing[i]); - if (ret) + if (ret) { + mutex_unlock(&encl_page->encl->lock); goto skip; + } - mutex_lock(&encl_page->encl->lock); encl_page->desc |= SGX_ENCL_PAGE_BEING_RECLAIMED; mutex_unlock(&encl_page->encl->lock); continue; @@ -411,7 +417,6 @@ skip: encl_page = epc_page->owner; sgx_reclaimer_write(epc_page, &backing[i]); - sgx_encl_put_backing(&backing[i], true); kref_put(&encl_page->encl->refcount, sgx_encl_release); epc_page->flags &= ~SGX_EPC_PAGE_RECLAIMER_TRACKED; diff --git a/arch/x86/kernel/cpu/tsx.c b/arch/x86/kernel/cpu/tsx.c index 9c7a5f049292..ec7bbac3a9f2 100644 --- a/arch/x86/kernel/cpu/tsx.c +++ b/arch/x86/kernel/cpu/tsx.c @@ -19,7 +19,7 @@ enum tsx_ctrl_states tsx_ctrl_state __ro_after_init = TSX_CTRL_NOT_SUPPORTED; -void tsx_disable(void) +static void tsx_disable(void) { u64 tsx; @@ -39,7 +39,7 @@ void tsx_disable(void) wrmsrl(MSR_IA32_TSX_CTRL, tsx); } -void tsx_enable(void) +static void tsx_enable(void) { u64 tsx; @@ -58,7 +58,7 @@ void tsx_enable(void) wrmsrl(MSR_IA32_TSX_CTRL, tsx); } -static bool __init tsx_ctrl_is_supported(void) +static bool tsx_ctrl_is_supported(void) { u64 ia32_cap = x86_read_arch_cap_msr(); @@ -84,7 +84,45 @@ static enum tsx_ctrl_states x86_get_tsx_auto_mode(void) return TSX_CTRL_ENABLE; } -void tsx_clear_cpuid(void) +/* + * Disabling TSX is not a trivial business. + * + * First of all, there's a CPUID bit: X86_FEATURE_RTM_ALWAYS_ABORT + * which says that TSX is practically disabled (all transactions are + * aborted by default). When that bit is set, the kernel unconditionally + * disables TSX. + * + * In order to do that, however, it needs to dance a bit: + * + * 1. The first method to disable it is through MSR_TSX_FORCE_ABORT and + * the MSR is present only when *two* CPUID bits are set: + * + * - X86_FEATURE_RTM_ALWAYS_ABORT + * - X86_FEATURE_TSX_FORCE_ABORT + * + * 2. The second method is for CPUs which do not have the above-mentioned + * MSR: those use a different MSR - MSR_IA32_TSX_CTRL and disable TSX + * through that one. Those CPUs can also have the initially mentioned + * CPUID bit X86_FEATURE_RTM_ALWAYS_ABORT set and for those the same strategy + * applies: TSX gets disabled unconditionally. + * + * When either of the two methods are present, the kernel disables TSX and + * clears the respective RTM and HLE feature flags. + * + * An additional twist in the whole thing presents late microcode loading + * which, when done, may cause for the X86_FEATURE_RTM_ALWAYS_ABORT CPUID + * bit to be set after the update. + * + * A subsequent hotplug operation on any logical CPU except the BSP will + * cause for the supported CPUID feature bits to get re-detected and, if + * RTM and HLE get cleared all of a sudden, but, userspace did consult + * them before the update, then funny explosions will happen. Long story + * short: the kernel doesn't modify CPUID feature bits after booting. + * + * That's why, this function's call in init_intel() doesn't clear the + * feature flags. + */ +static void tsx_clear_cpuid(void) { u64 msr; @@ -97,6 +135,39 @@ void tsx_clear_cpuid(void) rdmsrl(MSR_TSX_FORCE_ABORT, msr); msr |= MSR_TFA_TSX_CPUID_CLEAR; wrmsrl(MSR_TSX_FORCE_ABORT, msr); + } else if (tsx_ctrl_is_supported()) { + rdmsrl(MSR_IA32_TSX_CTRL, msr); + msr |= TSX_CTRL_CPUID_CLEAR; + wrmsrl(MSR_IA32_TSX_CTRL, msr); + } +} + +/* + * Disable TSX development mode + * + * When the microcode released in Feb 2022 is applied, TSX will be disabled by + * default on some processors. MSR 0x122 (TSX_CTRL) and MSR 0x123 + * (IA32_MCU_OPT_CTRL) can be used to re-enable TSX for development, doing so is + * not recommended for production deployments. In particular, applying MD_CLEAR + * flows for mitigation of the Intel TSX Asynchronous Abort (TAA) transient + * execution attack may not be effective on these processors when Intel TSX is + * enabled with updated microcode. + */ +static void tsx_dev_mode_disable(void) +{ + u64 mcu_opt_ctrl; + + /* Check if RTM_ALLOW exists */ + if (!boot_cpu_has_bug(X86_BUG_TAA) || !tsx_ctrl_is_supported() || + !cpu_feature_enabled(X86_FEATURE_SRBDS_CTRL)) + return; + + rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_opt_ctrl); + + if (mcu_opt_ctrl & RTM_ALLOW) { + mcu_opt_ctrl &= ~RTM_ALLOW; + wrmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_opt_ctrl); + setup_force_cpu_cap(X86_FEATURE_RTM_ALWAYS_ABORT); } } @@ -105,14 +176,14 @@ void __init tsx_init(void) char arg[5] = {}; int ret; + tsx_dev_mode_disable(); + /* - * Hardware will always abort a TSX transaction if both CPUID bits - * RTM_ALWAYS_ABORT and TSX_FORCE_ABORT are set. In this case, it is - * better not to enumerate CPUID.RTM and CPUID.HLE bits. Clear them - * here. + * Hardware will always abort a TSX transaction when the CPUID bit + * RTM_ALWAYS_ABORT is set. In this case, it is better not to enumerate + * CPUID.RTM and CPUID.HLE bits. Clear them here. */ - if (boot_cpu_has(X86_FEATURE_RTM_ALWAYS_ABORT) && - boot_cpu_has(X86_FEATURE_TSX_FORCE_ABORT)) { + if (boot_cpu_has(X86_FEATURE_RTM_ALWAYS_ABORT)) { tsx_ctrl_state = TSX_CTRL_RTM_ALWAYS_ABORT; tsx_clear_cpuid(); setup_clear_cpu_cap(X86_FEATURE_RTM); @@ -175,3 +246,16 @@ void __init tsx_init(void) setup_force_cpu_cap(X86_FEATURE_HLE); } } + +void tsx_ap_init(void) +{ + tsx_dev_mode_disable(); + + if (tsx_ctrl_state == TSX_CTRL_ENABLE) + tsx_enable(); + else if (tsx_ctrl_state == TSX_CTRL_DISABLE) + tsx_disable(); + else if (tsx_ctrl_state == TSX_CTRL_RTM_ALWAYS_ABORT) + /* See comment over that function for more details. */ + tsx_clear_cpuid(); +} diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index e8326a8d1c5d..9730c88530fc 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -407,7 +407,7 @@ int crash_load_segments(struct kimage *image) } image->elf_load_addr = kbuf.mem; pr_debug("Loaded ELF headers at 0x%lx bufsz=0x%lx memsz=0x%lx\n", - image->elf_load_addr, kbuf.bufsz, kbuf.bufsz); + image->elf_load_addr, kbuf.bufsz, kbuf.memsz); return ret; } diff --git a/arch/x86/kernel/crash_dump_64.c b/arch/x86/kernel/crash_dump_64.c index a7f617a3981d..97529552dd24 100644 --- a/arch/x86/kernel/crash_dump_64.c +++ b/arch/x86/kernel/crash_dump_64.c @@ -37,7 +37,6 @@ static ssize_t __copy_oldmem_page(unsigned long pfn, char *buf, size_t csize, } else memcpy(buf, vaddr + offset, csize); - set_iounmap_nonlazy(); iounmap((void __iomem *)vaddr); return csize; } diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index c049561f373a..e28ab0ecc537 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -41,17 +41,7 @@ struct fpu_state_config fpu_user_cfg __ro_after_init; */ struct fpstate init_fpstate __ro_after_init; -/* - * Track whether the kernel is using the FPU state - * currently. - * - * This flag is used: - * - * - by IRQ context code to potentially use the FPU - * if it's unused. - * - * - to debug kernel_fpu_begin()/end() correctness - */ +/* Track in-kernel FPU usage */ static DEFINE_PER_CPU(bool, in_kernel_fpu); /* @@ -59,42 +49,37 @@ static DEFINE_PER_CPU(bool, in_kernel_fpu); */ DEFINE_PER_CPU(struct fpu *, fpu_fpregs_owner_ctx); -static bool kernel_fpu_disabled(void) -{ - return this_cpu_read(in_kernel_fpu); -} - -static bool interrupted_kernel_fpu_idle(void) -{ - return !kernel_fpu_disabled(); -} - -/* - * Were we in user mode (or vm86 mode) when we were - * interrupted? - * - * Doing kernel_fpu_begin/end() is ok if we are running - * in an interrupt context from user mode - we'll just - * save the FPU state as required. - */ -static bool interrupted_user_mode(void) -{ - struct pt_regs *regs = get_irq_regs(); - return regs && user_mode(regs); -} - /* * Can we use the FPU in kernel mode with the * whole "kernel_fpu_begin/end()" sequence? - * - * It's always ok in process context (ie "not interrupt") - * but it is sometimes ok even from an irq. */ bool irq_fpu_usable(void) { - return !in_interrupt() || - interrupted_user_mode() || - interrupted_kernel_fpu_idle(); + if (WARN_ON_ONCE(in_nmi())) + return false; + + /* In kernel FPU usage already active? */ + if (this_cpu_read(in_kernel_fpu)) + return false; + + /* + * When not in NMI or hard interrupt context, FPU can be used in: + * + * - Task context except from within fpregs_lock()'ed critical + * regions. + * + * - Soft interrupt processing context which cannot happen + * while in a fpregs_lock()'ed critical region. + */ + if (!in_hardirq()) + return true; + + /* + * In hard interrupt context it's safe when soft interrupts + * are enabled, which means the interrupt did not hit in + * a fpregs_lock()'ed critical region. + */ + return !softirq_count(); } EXPORT_SYMBOL(irq_fpu_usable); diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 39e1c8626ab9..c8340156bfd2 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -142,7 +142,8 @@ static unsigned int xfeature_get_offset(u64 xcomp_bv, int xfeature) * Non-compacted format and legacy features use the cached fixed * offsets. */ - if (!cpu_feature_enabled(X86_FEATURE_XSAVES) || xfeature <= XFEATURE_SSE) + if (!cpu_feature_enabled(X86_FEATURE_XCOMPACTED) || + xfeature <= XFEATURE_SSE) return xstate_offsets[xfeature]; /* @@ -369,12 +370,12 @@ static void __init setup_init_fpu_buf(void) /* * All components are now in init state. Read the state back so * that init_fpstate contains all non-zero init state. This only - * works with XSAVE, but not with XSAVEOPT and XSAVES because + * works with XSAVE, but not with XSAVEOPT and XSAVEC/S because * those use the init optimization which skips writing data for * components in init state. * * XSAVE could be used, but that would require to reshuffle the - * data when XSAVES is available because XSAVES uses xstate + * data when XSAVEC/S is available because XSAVEC/S uses xstate * compaction. But doing so is a pointless exercise because most * components have an all zeros init state except for the legacy * ones (FP and SSE). Those can be saved with FXSAVE into the @@ -584,7 +585,8 @@ static unsigned int xstate_calculate_size(u64 xfeatures, bool compacted) */ static bool __init paranoid_xstate_size_valid(unsigned int kernel_size) { - bool compacted = cpu_feature_enabled(X86_FEATURE_XSAVES); + bool compacted = cpu_feature_enabled(X86_FEATURE_XCOMPACTED); + bool xsaves = cpu_feature_enabled(X86_FEATURE_XSAVES); unsigned int size = FXSAVE_SIZE + XSAVE_HDR_SIZE; int i; @@ -595,7 +597,7 @@ static bool __init paranoid_xstate_size_valid(unsigned int kernel_size) * Supervisor state components can be managed only by * XSAVES. */ - if (!compacted && xfeature_is_supervisor(i)) { + if (!xsaves && xfeature_is_supervisor(i)) { XSTATE_WARN_ON(1); return false; } @@ -612,8 +614,11 @@ static bool __init paranoid_xstate_size_valid(unsigned int kernel_size) * the size of the *user* states. If we use it to size a buffer * that we use 'XSAVES' on, we could potentially overflow the * buffer because 'XSAVES' saves system states too. + * + * This also takes compaction into account. So this works for + * XSAVEC as well. */ -static unsigned int __init get_xsaves_size(void) +static unsigned int __init get_compacted_size(void) { unsigned int eax, ebx, ecx, edx; /* @@ -623,6 +628,10 @@ static unsigned int __init get_xsaves_size(void) * containing all the state components * corresponding to bits currently set in * XCR0 | IA32_XSS. + * + * When XSAVES is not available but XSAVEC is (virt), then there + * are no supervisor states, but XSAVEC still uses compacted + * format. */ cpuid_count(XSTATE_CPUID, 1, &eax, &ebx, &ecx, &edx); return ebx; @@ -632,13 +641,13 @@ static unsigned int __init get_xsaves_size(void) * Get the total size of the enabled xstates without the independent supervisor * features. */ -static unsigned int __init get_xsaves_size_no_independent(void) +static unsigned int __init get_xsave_compacted_size(void) { u64 mask = xfeatures_mask_independent(); unsigned int size; if (!mask) - return get_xsaves_size(); + return get_compacted_size(); /* Disable independent features. */ wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor()); @@ -647,7 +656,7 @@ static unsigned int __init get_xsaves_size_no_independent(void) * Ask the hardware what size is required of the buffer. * This is the size required for the task->fpu buffer. */ - size = get_xsaves_size(); + size = get_compacted_size(); /* Re-enable independent features so XSAVES will work on them again. */ wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor() | mask); @@ -687,20 +696,21 @@ static int __init init_xstate_size(void) { /* Recompute the context size for enabled features: */ unsigned int user_size, kernel_size, kernel_default_size; - bool compacted = cpu_feature_enabled(X86_FEATURE_XSAVES); + bool compacted = cpu_feature_enabled(X86_FEATURE_XCOMPACTED); /* Uncompacted user space size */ user_size = get_xsave_size_user(); /* - * XSAVES kernel size includes supervisor states and - * uses compacted format when available. + * XSAVES kernel size includes supervisor states and uses compacted + * format. XSAVEC uses compacted format, but does not save + * supervisor states. * - * XSAVE does not support supervisor states so - * kernel and user size is identical. + * XSAVE[OPT] do not support supervisor states so kernel and user + * size is identical. */ if (compacted) - kernel_size = get_xsaves_size_no_independent(); + kernel_size = get_xsave_compacted_size(); else kernel_size = user_size; @@ -813,8 +823,11 @@ void __init fpu__init_system_xstate(unsigned int legacy_size) if (!cpu_feature_enabled(X86_FEATURE_XFD)) fpu_kernel_cfg.max_features &= ~XFEATURE_MASK_USER_DYNAMIC; - fpu_kernel_cfg.max_features &= XFEATURE_MASK_USER_SUPPORTED | - XFEATURE_MASK_SUPERVISOR_SUPPORTED; + if (!cpu_feature_enabled(X86_FEATURE_XSAVES)) + fpu_kernel_cfg.max_features &= XFEATURE_MASK_USER_SUPPORTED; + else + fpu_kernel_cfg.max_features &= XFEATURE_MASK_USER_SUPPORTED | + XFEATURE_MASK_SUPERVISOR_SUPPORTED; fpu_user_cfg.max_features = fpu_kernel_cfg.max_features; fpu_user_cfg.max_features &= XFEATURE_MASK_USER_SUPPORTED; @@ -837,6 +850,11 @@ void __init fpu__init_system_xstate(unsigned int legacy_size) */ init_fpstate.xfd = fpu_user_cfg.max_features & XFEATURE_MASK_USER_DYNAMIC; + /* Set up compaction feature bit */ + if (cpu_feature_enabled(X86_FEATURE_XSAVEC) || + cpu_feature_enabled(X86_FEATURE_XSAVES)) + setup_force_cpu_cap(X86_FEATURE_XCOMPACTED); + /* Enable xstate instructions to be able to continue with initialization: */ fpu__init_cpu_xstate(); @@ -873,7 +891,7 @@ void __init fpu__init_system_xstate(unsigned int legacy_size) pr_info("x86/fpu: Enabled xstate features 0x%llx, context size is %d bytes, using '%s' format.\n", fpu_kernel_cfg.max_features, fpu_kernel_cfg.max_size, - boot_cpu_has(X86_FEATURE_XSAVES) ? "compacted" : "standard"); + boot_cpu_has(X86_FEATURE_XCOMPACTED) ? "compacted" : "standard"); return; out_disable: @@ -917,7 +935,7 @@ static void *__raw_xsave_addr(struct xregs_state *xsave, int xfeature_nr) if (WARN_ON_ONCE(!xfeature_enabled(xfeature_nr))) return NULL; - if (cpu_feature_enabled(X86_FEATURE_XSAVES)) { + if (cpu_feature_enabled(X86_FEATURE_XCOMPACTED)) { if (WARN_ON_ONCE(!(xcomp_bv & BIT_ULL(xfeature_nr)))) return NULL; } @@ -1215,7 +1233,7 @@ static int copy_uabi_to_xstate(struct fpstate *fpstate, const void *kbuf, } for (i = 0; i < XFEATURE_MAX; i++) { - u64 mask = ((u64)1 << i); + mask = BIT_ULL(i); if (hdr.xfeatures & mask) { void *dst = __raw_xsave_addr(xsave, i); @@ -1525,7 +1543,7 @@ static int __xstate_request_perm(u64 permitted, u64 requested, bool guest) * vendors into extending XFD for the pre AMX states, especially * AVX512. */ - bool compacted = cpu_feature_enabled(X86_FEATURE_XSAVES); + bool compacted = cpu_feature_enabled(X86_FEATURE_XCOMPACTED); struct fpu *fpu = ¤t->group_leader->thread.fpu; struct fpu_state_perm *perm; unsigned int ksize, usize; @@ -1687,16 +1705,13 @@ EXPORT_SYMBOL_GPL(xstate_get_guest_group_perm); * e.g. for AMX which requires XFEATURE_XTILE_CFG(17) and * XFEATURE_XTILE_DATA(18) this would be XFEATURE_XTILE_DATA(18). */ -long fpu_xstate_prctl(struct task_struct *tsk, int option, unsigned long arg2) +long fpu_xstate_prctl(int option, unsigned long arg2) { u64 __user *uptr = (u64 __user *)arg2; u64 permitted, supported; unsigned long idx = arg2; bool guest = false; - if (tsk != current) - return -EPERM; - switch (option) { case ARCH_GET_XCOMP_SUPP: supported = fpu_user_cfg.max_features | fpu_user_cfg.legacy_features; diff --git a/arch/x86/kernel/fpu/xstate.h b/arch/x86/kernel/fpu/xstate.h index d22ace092ca2..5ad47031383b 100644 --- a/arch/x86/kernel/fpu/xstate.h +++ b/arch/x86/kernel/fpu/xstate.h @@ -16,7 +16,7 @@ static inline void xstate_init_xcomp_bv(struct xregs_state *xsave, u64 mask) * XRSTORS requires these bits set in xcomp_bv, or it will * trigger #GP: */ - if (cpu_feature_enabled(X86_FEATURE_XSAVES)) + if (cpu_feature_enabled(X86_FEATURE_XCOMPACTED)) xsave->header.xcomp_bv = mask | XCOMP_BV_COMPACTED_FORMAT; } @@ -79,6 +79,7 @@ static inline u64 xfeatures_mask_independent(void) /* These macros all use (%edi)/(%rdi) as the single memory argument. */ #define XSAVE ".byte " REX_PREFIX "0x0f,0xae,0x27" #define XSAVEOPT ".byte " REX_PREFIX "0x0f,0xae,0x37" +#define XSAVEC ".byte " REX_PREFIX "0x0f,0xc7,0x27" #define XSAVES ".byte " REX_PREFIX "0x0f,0xc7,0x2f" #define XRSTOR ".byte " REX_PREFIX "0x0f,0xae,0x2f" #define XRSTORS ".byte " REX_PREFIX "0x0f,0xc7,0x1f" @@ -97,9 +98,11 @@ static inline u64 xfeatures_mask_independent(void) : "memory") /* - * If XSAVES is enabled, it replaces XSAVEOPT because it supports a compact - * format and supervisor states in addition to modified optimization in - * XSAVEOPT. + * If XSAVES is enabled, it replaces XSAVEC because it supports supervisor + * states in addition to XSAVEC. + * + * Otherwise if XSAVEC is enabled, it replaces XSAVEOPT because it supports + * compacted storage format in addition to XSAVEOPT. * * Otherwise, if XSAVEOPT is enabled, XSAVEOPT replaces XSAVE because XSAVEOPT * supports modified optimization which is not supported by XSAVE. @@ -111,8 +114,9 @@ static inline u64 xfeatures_mask_independent(void) * address of the instruction where we might get an exception at. */ #define XSTATE_XSAVE(st, lmask, hmask, err) \ - asm volatile(ALTERNATIVE_2(XSAVE, \ + asm volatile(ALTERNATIVE_3(XSAVE, \ XSAVEOPT, X86_FEATURE_XSAVEOPT, \ + XSAVEC, X86_FEATURE_XSAVEC, \ XSAVES, X86_FEATURE_XSAVES) \ "\n" \ "xor %[err], %[err]\n" \ diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 1e31c7d21597..b09d73c2ba89 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -579,9 +579,7 @@ void arch_ftrace_trampoline_free(struct ftrace_ops *ops) #ifdef CONFIG_FUNCTION_GRAPH_TRACER -#ifdef CONFIG_DYNAMIC_FTRACE - -#ifndef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS +#if defined(CONFIG_DYNAMIC_FTRACE) && !defined(CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS) extern void ftrace_graph_call(void); static const char *ftrace_jmp_replace(unsigned long ip, unsigned long addr) { @@ -610,18 +608,7 @@ int ftrace_disable_ftrace_graph_caller(void) return ftrace_mod_jmp(ip, &ftrace_stub); } -#else /* !CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS */ -int ftrace_enable_ftrace_graph_caller(void) -{ - return 0; -} - -int ftrace_disable_ftrace_graph_caller(void) -{ - return 0; -} -#endif /* CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS */ -#endif /* !CONFIG_DYNAMIC_FTRACE */ +#endif /* CONFIG_DYNAMIC_FTRACE && !CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS */ /* * Hook the return address and push it in the stack of return addrs diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 4f5ecbbaae77..bd4a34100ed0 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -40,6 +40,7 @@ #include <asm/extable.h> #include <asm/trapnr.h> #include <asm/sev.h> +#include <asm/tdx.h> /* * Manage page tables very early on. @@ -143,7 +144,20 @@ static unsigned long __head sme_postprocess_startup(struct boot_params *bp, pmdv if (sme_get_me_mask()) { vaddr = (unsigned long)__start_bss_decrypted; vaddr_end = (unsigned long)__end_bss_decrypted; + for (; vaddr < vaddr_end; vaddr += PMD_SIZE) { + /* + * On SNP, transition the page to shared in the RMP table so that + * it is consistent with the page table attribute change. + * + * __start_bss_decrypted has a virtual address in the high range + * mapping (kernel .text). PVALIDATE, by way of + * early_snp_set_memory_shared(), requires a valid virtual + * address but the kernel is currently running off of the identity + * mapping so use __pa() to get a *currently* valid virtual address. + */ + early_snp_set_memory_shared(__pa(vaddr), __pa(vaddr), PTRS_PER_PMD); + i = pmd_index(vaddr); pmd[i] -= sme_get_me_mask(); } @@ -192,9 +206,6 @@ unsigned long __head __startup_64(unsigned long physaddr, if (load_delta & ~PMD_PAGE_MASK) for (;;); - /* Activate Secure Memory Encryption (SME) if supported and enabled */ - sme_enable(bp); - /* Include the SME encryption mask in the fixup value */ load_delta += sme_get_me_mask(); @@ -308,15 +319,6 @@ unsigned long __head __startup_64(unsigned long physaddr, return sme_postprocess_startup(bp, pmd); } -unsigned long __startup_secondary_64(void) -{ - /* - * Return the SME encryption mask (if SME is active) to be used as a - * modifier for the initial pgdir entry programmed into CR3. - */ - return sme_get_me_mask(); -} - /* Wipe all early page tables except for the kernel symbol map */ static void __init reset_early_page_tables(void) { @@ -416,6 +418,9 @@ void __init do_early_exception(struct pt_regs *regs, int trapnr) trapnr == X86_TRAP_VC && handle_vc_boot_ghcb(regs)) return; + if (trapnr == X86_TRAP_VE && tdx_early_handle_ve(regs)) + return; + early_fixup_exception(regs, trapnr); } @@ -514,6 +519,9 @@ asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data) idt_setup_early_handler(); + /* Needed before cc_platform_has() can be used for TDX */ + tdx_early_init(); + copy_bootdata(__va(real_mode_data)); /* @@ -600,8 +608,10 @@ static void startup_64_load_idt(unsigned long physbase) void early_setup_idt(void) { /* VMM Communication Exception */ - if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT)) + if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT)) { + setup_ghcb(); set_bringup_idt_handler(bringup_idt_table, X86_TRAP_VC, vc_boot_ghcb); + } bringup_idt_descr.address = (unsigned long)bringup_idt_table; native_load_idt(&bringup_idt_descr); diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index b8e3019547a5..92c4afa2b729 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -65,10 +65,39 @@ SYM_CODE_START_NOALIGN(startup_64) leaq (__end_init_task - FRAME_SIZE)(%rip), %rsp leaq _text(%rip), %rdi + + /* + * initial_gs points to initial fixed_percpu_data struct with storage for + * the stack protector canary. Global pointer fixups are needed at this + * stage, so apply them as is done in fixup_pointer(), and initialize %gs + * such that the canary can be accessed at %gs:40 for subsequent C calls. + */ + movl $MSR_GS_BASE, %ecx + movq initial_gs(%rip), %rax + movq $_text, %rdx + subq %rdx, %rax + addq %rdi, %rax + movq %rax, %rdx + shrq $32, %rdx + wrmsr + pushq %rsi call startup_64_setup_env popq %rsi +#ifdef CONFIG_AMD_MEM_ENCRYPT + /* + * Activate SEV/SME memory encryption if supported/enabled. This needs to + * be done now, since this also includes setup of the SEV-SNP CPUID table, + * which needs to be done before any CPUID instructions are executed in + * subsequent code. + */ + movq %rsi, %rdi + pushq %rsi + call sme_enable + popq %rsi +#endif + /* Now switch to __KERNEL_CS so IRET works reliably */ pushq $__KERNEL_CS leaq .Lon_kernel_cs(%rip), %rax @@ -134,16 +163,32 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL) * Retrieve the modifier (SME encryption mask if SME is active) to be * added to the initial pgdir entry that will be programmed into CR3. */ - pushq %rsi - call __startup_secondary_64 - popq %rsi +#ifdef CONFIG_AMD_MEM_ENCRYPT + movq sme_me_mask, %rax +#else + xorq %rax, %rax +#endif /* Form the CR3 value being sure to include the CR3 modifier */ addq $(init_top_pgt - __START_KERNEL_map), %rax 1: +#ifdef CONFIG_X86_MCE + /* + * Preserve CR4.MCE if the kernel will enable #MC support. + * Clearing MCE may fault in some environments (that also force #MC + * support). Any machine check that occurs before #MC support is fully + * configured will crash the system regardless of the CR4.MCE value set + * here. + */ + movq %cr4, %rcx + andl $X86_CR4_MCE, %ecx +#else + movl $0, %ecx +#endif + /* Enable PAE mode, PGE and LA57 */ - movl $(X86_CR4_PAE | X86_CR4_PGE), %ecx + orl $(X86_CR4_PAE | X86_CR4_PGE), %ecx #ifdef CONFIG_X86_5LEVEL testl $1, __pgtable_l5_enabled(%rip) jz 1f @@ -249,13 +294,23 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL) /* Setup EFER (Extended Feature Enable Register) */ movl $MSR_EFER, %ecx rdmsr + /* + * Preserve current value of EFER for comparison and to skip + * EFER writes if no change was made (for TDX guest) + */ + movl %eax, %edx btsl $_EFER_SCE, %eax /* Enable System Call */ btl $20,%edi /* No Execute supported? */ jnc 1f btsl $_EFER_NX, %eax btsq $_PAGE_BIT_NX,early_pmd_flags(%rip) -1: wrmsr /* Make changes effective */ + /* Avoid writing EFER if no change was made (for TDX guest) */ +1: cmpl %edx, %eax + je 1f + xor %edx, %edx + wrmsr /* Make changes effective */ +1: /* Setup cr0 */ movl $CR0_STATE, %eax /* Make changes effective */ diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c index 608eb63bf044..a58c6bc1cd68 100644 --- a/arch/x86/kernel/idt.c +++ b/arch/x86/kernel/idt.c @@ -69,6 +69,9 @@ static const __initconst struct idt_data early_idts[] = { */ INTG(X86_TRAP_PF, asm_exc_page_fault), #endif +#ifdef CONFIG_INTEL_TDX_GUEST + INTG(X86_TRAP_VE, asm_exc_virtualization_exception), +#endif }; /* diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index a22deb58f86d..8b1c45c9cda8 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -69,6 +69,7 @@ static DEFINE_PER_CPU_DECRYPTED(struct kvm_vcpu_pv_apf_data, apf_reason) __align DEFINE_PER_CPU_DECRYPTED(struct kvm_steal_time, steal_time) __aligned(64) __visible; static int has_steal_clock = 0; +static int has_guest_poll = 0; /* * No need for any "IO delay" on KVM */ @@ -706,14 +707,26 @@ static int kvm_cpu_down_prepare(unsigned int cpu) static int kvm_suspend(void) { + u64 val = 0; + kvm_guest_cpu_offline(false); +#ifdef CONFIG_ARCH_CPUIDLE_HALTPOLL + if (kvm_para_has_feature(KVM_FEATURE_POLL_CONTROL)) + rdmsrl(MSR_KVM_POLL_CONTROL, val); + has_guest_poll = !(val & 1); +#endif return 0; } static void kvm_resume(void) { kvm_cpu_online(raw_smp_processor_id()); + +#ifdef CONFIG_ARCH_CPUIDLE_HALTPOLL + if (kvm_para_has_feature(KVM_FEATURE_POLL_CONTROL) && has_guest_poll) + wrmsrl(MSR_KVM_POLL_CONTROL, 0); +#endif } static struct syscore_ops kvm_syscore_ops = { diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index e73f7df362f5..cec0bfa3bc04 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -157,7 +157,7 @@ int __register_nmi_handler(unsigned int type, struct nmiaction *action) struct nmi_desc *desc = nmi_to_desc(type); unsigned long flags; - if (!action->handler) + if (WARN_ON_ONCE(!action->handler || !list_empty(&action->list))) return -EINVAL; raw_spin_lock_irqsave(&desc->lock, flags); @@ -177,7 +177,7 @@ int __register_nmi_handler(unsigned int type, struct nmiaction *action) list_add_rcu(&action->list, &desc->head); else list_add_tail_rcu(&action->list, &desc->head); - + raw_spin_unlock_irqrestore(&desc->lock, flags); return 0; } @@ -186,7 +186,7 @@ EXPORT_SYMBOL(__register_nmi_handler); void unregister_nmi_handler(unsigned int type, const char *name) { struct nmi_desc *desc = nmi_to_desc(type); - struct nmiaction *n; + struct nmiaction *n, *found = NULL; unsigned long flags; raw_spin_lock_irqsave(&desc->lock, flags); @@ -200,12 +200,16 @@ void unregister_nmi_handler(unsigned int type, const char *name) WARN(in_nmi(), "Trying to free NMI (%s) from NMI context!\n", n->name); list_del_rcu(&n->list); + found = n; break; } } raw_spin_unlock_irqrestore(&desc->lock, flags); - synchronize_rcu(); + if (found) { + synchronize_rcu(); + INIT_LIST_HEAD(&found->list); + } } EXPORT_SYMBOL_GPL(unregister_nmi_handler); diff --git a/arch/x86/kernel/probe_roms.c b/arch/x86/kernel/probe_roms.c index 36e84d904260..319fef37d9dc 100644 --- a/arch/x86/kernel/probe_roms.c +++ b/arch/x86/kernel/probe_roms.c @@ -21,6 +21,7 @@ #include <asm/sections.h> #include <asm/io.h> #include <asm/setup_arch.h> +#include <asm/sev.h> static struct resource system_rom_resource = { .name = "System ROM", @@ -197,11 +198,21 @@ static int __init romchecksum(const unsigned char *rom, unsigned long length) void __init probe_roms(void) { - const unsigned char *rom; unsigned long start, length, upper; + const unsigned char *rom; unsigned char c; int i; + /* + * The ROM memory range is not part of the e820 table and is therefore not + * pre-validated by BIOS. The kernel page table maps the ROM region as encrypted + * memory, and SNP requires encrypted memory to be validated before access. + * Do that here. + */ + snp_prep_memory(video_rom_resource.start, + ((system_rom_resource.end + 1) - video_rom_resource.start), + SNP_PAGE_STATE_PRIVATE); + /* video rom */ upper = adapter_rom_resources[0].start; for (start = video_rom_resource.start; start < upper; start += 2048) { diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index b370767f5b19..58fb48d3004f 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -46,6 +46,7 @@ #include <asm/proto.h> #include <asm/frame.h> #include <asm/unwind.h> +#include <asm/tdx.h> #include "process.h" @@ -160,6 +161,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long arg, savesegment(ds, p->thread.ds); #else p->thread.sp0 = (unsigned long) (childregs + 1); + savesegment(gs, p->thread.gs); /* * Clear all status flags including IF and set fixed bit. 64bit * does not have this initialization as the frame does not contain @@ -191,10 +193,6 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long arg, if (sp) childregs->sp = sp; -#ifdef CONFIG_X86_32 - task_user_gs(p) = get_user_gs(current_pt_regs()); -#endif - if (unlikely(p->flags & PF_IO_WORKER)) { /* * An IO thread is a user space thread, but it doesn't @@ -334,7 +332,7 @@ static int get_cpuid_mode(void) return !test_thread_flag(TIF_NOCPUID); } -static int set_cpuid_mode(struct task_struct *task, unsigned long cpuid_enabled) +static int set_cpuid_mode(unsigned long cpuid_enabled) { if (!boot_cpu_has(X86_FEATURE_CPUID_FAULT)) return -ENODEV; @@ -405,7 +403,7 @@ static void tss_copy_io_bitmap(struct tss_struct *tss, struct io_bitmap *iobm) } /** - * tss_update_io_bitmap - Update I/O bitmap before exiting to usermode + * native_tss_update_io_bitmap - Update I/O bitmap before exiting to user mode */ void native_tss_update_io_bitmap(void) { @@ -686,9 +684,6 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p) /* Enforce MSR update to ensure consistent state */ __speculation_ctrl_update(~tifn, tifn); } - - if ((tifp ^ tifn) & _TIF_SLD) - switch_to_sld(tifn); } /* @@ -873,6 +868,9 @@ void select_idle_routine(const struct cpuinfo_x86 *c) } else if (prefer_mwait_c1_over_halt(c)) { pr_info("using mwait in idle threads\n"); x86_idle = mwait_idle; + } else if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) { + pr_info("using TDX aware idle routine\n"); + x86_idle = tdx_safe_halt; } else x86_idle = default_idle; } @@ -985,20 +983,19 @@ unsigned long __get_wchan(struct task_struct *p) return addr; } -long do_arch_prctl_common(struct task_struct *task, int option, - unsigned long arg2) +long do_arch_prctl_common(int option, unsigned long arg2) { switch (option) { case ARCH_GET_CPUID: return get_cpuid_mode(); case ARCH_SET_CPUID: - return set_cpuid_mode(task, arg2); + return set_cpuid_mode(arg2); case ARCH_GET_XCOMP_SUPP: case ARCH_GET_XCOMP_PERM: case ARCH_REQ_XCOMP_PERM: case ARCH_GET_XCOMP_GUEST_PERM: case ARCH_REQ_XCOMP_GUEST_PERM: - return fpu_xstate_prctl(task, option, arg2); + return fpu_xstate_prctl(option, arg2); } return -EINVAL; diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 26edb1cd07a4..2f314b170c9f 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -63,10 +63,7 @@ void __show_regs(struct pt_regs *regs, enum show_regs_mode mode, unsigned long d0, d1, d2, d3, d6, d7; unsigned short gs; - if (user_mode(regs)) - gs = get_user_gs(regs); - else - savesegment(gs, gs); + savesegment(gs, gs); show_ip(regs, log_lvl); @@ -114,7 +111,7 @@ void release_thread(struct task_struct *dead_task) void start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp) { - set_user_gs(regs, 0); + loadsegment(gs, 0); regs->fs = 0; regs->ds = __USER_DS; regs->es = __USER_DS; @@ -177,7 +174,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) * used %fs or %gs (it does not today), or if the kernel is * running inside of a hypervisor layer. */ - lazy_save_gs(prev->gs); + savesegment(gs, prev->gs); /* * Load the per-thread Thread-Local Storage descriptor. @@ -208,7 +205,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) * Restore %gs if needed (which is common) */ if (prev->gs | next->gs) - lazy_load_gs(next->gs); + loadsegment(gs, next->gs); this_cpu_write(current_task, next_p); @@ -222,5 +219,5 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2) { - return do_arch_prctl_common(current, option, arg2); + return do_arch_prctl_common(option, arg2); } diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index e459253649be..1962008fe743 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -844,7 +844,7 @@ SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2) ret = do_arch_prctl_64(current, option, arg2); if (ret == -EINVAL) - ret = do_arch_prctl_common(current, option, arg2); + ret = do_arch_prctl_common(option, arg2); return ret; } @@ -852,7 +852,7 @@ SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2) #ifdef CONFIG_IA32_EMULATION COMPAT_SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2) { - return do_arch_prctl_common(current, option, arg2); + return do_arch_prctl_common(option, arg2); } #endif diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 98d10ef60571..37c12fb92906 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -170,9 +170,9 @@ static u16 get_segment_reg(struct task_struct *task, unsigned long offset) retval = *pt_regs_access(task_pt_regs(task), offset); else { if (task == current) - retval = get_user_gs(task_pt_regs(task)); + savesegment(gs, retval); else - retval = task_user_gs(task); + retval = task->thread.gs; } return retval; } @@ -210,7 +210,7 @@ static int set_segment_reg(struct task_struct *task, break; case offsetof(struct user_regs_struct, gs): - task_user_gs(task) = value; + task->thread.gs = value; } return 0; diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index c95b9ac5a457..249981bf3d8a 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -756,6 +756,30 @@ dump_kernel_offset(struct notifier_block *self, unsigned long v, void *p) return 0; } +void x86_configure_nx(void) +{ + if (boot_cpu_has(X86_FEATURE_NX)) + __supported_pte_mask |= _PAGE_NX; + else + __supported_pte_mask &= ~_PAGE_NX; +} + +static void __init x86_report_nx(void) +{ + if (!boot_cpu_has(X86_FEATURE_NX)) { + printk(KERN_NOTICE "Notice: NX (Execute Disable) protection " + "missing in CPU!\n"); + } else { +#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE) + printk(KERN_INFO "NX (Execute Disable) protection: active\n"); +#else + /* 32bit non-PAE kernel, NX cannot be used */ + printk(KERN_NOTICE "Notice: NX (Execute Disable) protection " + "cannot be enabled: non-PAE kernel!\n"); +#endif + } +} + /* * Determine if we were loaded by an EFI loader. If so, then we have also been * passed the efi memmap, systab, etc., so we should use these data structures @@ -896,9 +920,7 @@ void __init setup_arch(char **cmdline_p) /* * x86_configure_nx() is called before parse_early_param() to detect * whether hardware doesn't support NX (so that the early EHCI debug - * console setup can safely call set_fixmap()). It may then be called - * again from within noexec_setup() during parsing early parameters - * to honor the respective command line option. + * console setup can safely call set_fixmap()). */ x86_configure_nx(); diff --git a/arch/x86/kernel/sev-shared.c b/arch/x86/kernel/sev-shared.c index ce987688bbc0..b478edf43bec 100644 --- a/arch/x86/kernel/sev-shared.c +++ b/arch/x86/kernel/sev-shared.c @@ -14,6 +14,68 @@ #define has_cpuflag(f) boot_cpu_has(f) #endif +/* I/O parameters for CPUID-related helpers */ +struct cpuid_leaf { + u32 fn; + u32 subfn; + u32 eax; + u32 ebx; + u32 ecx; + u32 edx; +}; + +/* + * Individual entries of the SNP CPUID table, as defined by the SNP + * Firmware ABI, Revision 0.9, Section 7.1, Table 14. + */ +struct snp_cpuid_fn { + u32 eax_in; + u32 ecx_in; + u64 xcr0_in; + u64 xss_in; + u32 eax; + u32 ebx; + u32 ecx; + u32 edx; + u64 __reserved; +} __packed; + +/* + * SNP CPUID table, as defined by the SNP Firmware ABI, Revision 0.9, + * Section 8.14.2.6. Also noted there is the SNP firmware-enforced limit + * of 64 entries per CPUID table. + */ +#define SNP_CPUID_COUNT_MAX 64 + +struct snp_cpuid_table { + u32 count; + u32 __reserved1; + u64 __reserved2; + struct snp_cpuid_fn fn[SNP_CPUID_COUNT_MAX]; +} __packed; + +/* + * Since feature negotiation related variables are set early in the boot + * process they must reside in the .data section so as not to be zeroed + * out when the .bss section is later cleared. + * + * GHCB protocol version negotiated with the hypervisor. + */ +static u16 ghcb_version __ro_after_init; + +/* Copy of the SNP firmware's CPUID page. */ +static struct snp_cpuid_table cpuid_table_copy __ro_after_init; + +/* + * These will be initialized based on CPUID table so that non-present + * all-zero leaves (for sparse tables) can be differentiated from + * invalid/out-of-range leaves. This is needed since all-zero leaves + * still need to be post-processed. + */ +static u32 cpuid_std_range_max __ro_after_init; +static u32 cpuid_hyp_range_max __ro_after_init; +static u32 cpuid_ext_range_max __ro_after_init; + static bool __init sev_es_check_cpu_features(void) { if (!has_cpuflag(X86_FEATURE_RDRAND)) { @@ -24,15 +86,12 @@ static bool __init sev_es_check_cpu_features(void) return true; } -static void __noreturn sev_es_terminate(unsigned int reason) +static void __noreturn sev_es_terminate(unsigned int set, unsigned int reason) { u64 val = GHCB_MSR_TERM_REQ; - /* - * Tell the hypervisor what went wrong - only reason-set 0 is - * currently supported. - */ - val |= GHCB_SEV_TERM_REASON(0, reason); + /* Tell the hypervisor what went wrong. */ + val |= GHCB_SEV_TERM_REASON(set, reason); /* Request Guest Termination from Hypvervisor */ sev_es_wr_ghcb_msr(val); @@ -42,6 +101,42 @@ static void __noreturn sev_es_terminate(unsigned int reason) asm volatile("hlt\n" : : : "memory"); } +/* + * The hypervisor features are available from GHCB version 2 onward. + */ +static u64 get_hv_features(void) +{ + u64 val; + + if (ghcb_version < 2) + return 0; + + sev_es_wr_ghcb_msr(GHCB_MSR_HV_FT_REQ); + VMGEXIT(); + + val = sev_es_rd_ghcb_msr(); + if (GHCB_RESP_CODE(val) != GHCB_MSR_HV_FT_RESP) + return 0; + + return GHCB_MSR_HV_FT_RESP_VAL(val); +} + +static void snp_register_ghcb_early(unsigned long paddr) +{ + unsigned long pfn = paddr >> PAGE_SHIFT; + u64 val; + + sev_es_wr_ghcb_msr(GHCB_MSR_REG_GPA_REQ_VAL(pfn)); + VMGEXIT(); + + val = sev_es_rd_ghcb_msr(); + + /* If the response GPA is not ours then abort the guest */ + if ((GHCB_RESP_CODE(val) != GHCB_MSR_REG_GPA_RESP) || + (GHCB_MSR_REG_GPA_RESP_VAL(val) != pfn)) + sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_REGISTER); +} + static bool sev_es_negotiate_protocol(void) { u64 val; @@ -54,10 +149,12 @@ static bool sev_es_negotiate_protocol(void) if (GHCB_MSR_INFO(val) != GHCB_MSR_SEV_INFO_RESP) return false; - if (GHCB_MSR_PROTO_MAX(val) < GHCB_PROTO_OUR || - GHCB_MSR_PROTO_MIN(val) > GHCB_PROTO_OUR) + if (GHCB_MSR_PROTO_MAX(val) < GHCB_PROTOCOL_MIN || + GHCB_MSR_PROTO_MIN(val) > GHCB_PROTOCOL_MAX) return false; + ghcb_version = min_t(size_t, GHCB_MSR_PROTO_MAX(val), GHCB_PROTOCOL_MAX); + return true; } @@ -104,10 +201,7 @@ static enum es_result verify_exception_info(struct ghcb *ghcb, struct es_em_ctxt if (ret == 1) { u64 info = ghcb->save.sw_exit_info_2; - unsigned long v; - - info = ghcb->save.sw_exit_info_2; - v = info & SVM_EVTINJ_VEC_MASK; + unsigned long v = info & SVM_EVTINJ_VEC_MASK; /* Check if exception information from hypervisor is sane. */ if ((info & SVM_EVTINJ_VALID) && @@ -130,7 +224,7 @@ enum es_result sev_es_ghcb_hv_call(struct ghcb *ghcb, bool set_ghcb_msr, u64 exit_info_1, u64 exit_info_2) { /* Fill in protocol and format specifiers */ - ghcb->protocol_version = GHCB_PROTOCOL_MAX; + ghcb->protocol_version = ghcb_version; ghcb->ghcb_usage = GHCB_DEFAULT_USAGE; ghcb_set_sw_exit_code(ghcb, exit_code); @@ -150,6 +244,290 @@ enum es_result sev_es_ghcb_hv_call(struct ghcb *ghcb, bool set_ghcb_msr, return verify_exception_info(ghcb, ctxt); } +static int __sev_cpuid_hv(u32 fn, int reg_idx, u32 *reg) +{ + u64 val; + + sev_es_wr_ghcb_msr(GHCB_CPUID_REQ(fn, reg_idx)); + VMGEXIT(); + val = sev_es_rd_ghcb_msr(); + if (GHCB_RESP_CODE(val) != GHCB_MSR_CPUID_RESP) + return -EIO; + + *reg = (val >> 32); + + return 0; +} + +static int sev_cpuid_hv(struct cpuid_leaf *leaf) +{ + int ret; + + /* + * MSR protocol does not support fetching non-zero subfunctions, but is + * sufficient to handle current early-boot cases. Should that change, + * make sure to report an error rather than ignoring the index and + * grabbing random values. If this issue arises in the future, handling + * can be added here to use GHCB-page protocol for cases that occur late + * enough in boot that GHCB page is available. + */ + if (cpuid_function_is_indexed(leaf->fn) && leaf->subfn) + return -EINVAL; + + ret = __sev_cpuid_hv(leaf->fn, GHCB_CPUID_REQ_EAX, &leaf->eax); + ret = ret ? : __sev_cpuid_hv(leaf->fn, GHCB_CPUID_REQ_EBX, &leaf->ebx); + ret = ret ? : __sev_cpuid_hv(leaf->fn, GHCB_CPUID_REQ_ECX, &leaf->ecx); + ret = ret ? : __sev_cpuid_hv(leaf->fn, GHCB_CPUID_REQ_EDX, &leaf->edx); + + return ret; +} + +/* + * This may be called early while still running on the initial identity + * mapping. Use RIP-relative addressing to obtain the correct address + * while running with the initial identity mapping as well as the + * switch-over to kernel virtual addresses later. + */ +static const struct snp_cpuid_table *snp_cpuid_get_table(void) +{ + void *ptr; + + asm ("lea cpuid_table_copy(%%rip), %0" + : "=r" (ptr) + : "p" (&cpuid_table_copy)); + + return ptr; +} + +/* + * The SNP Firmware ABI, Revision 0.9, Section 7.1, details the use of + * XCR0_IN and XSS_IN to encode multiple versions of 0xD subfunctions 0 + * and 1 based on the corresponding features enabled by a particular + * combination of XCR0 and XSS registers so that a guest can look up the + * version corresponding to the features currently enabled in its XCR0/XSS + * registers. The only values that differ between these versions/table + * entries is the enabled XSAVE area size advertised via EBX. + * + * While hypervisors may choose to make use of this support, it is more + * robust/secure for a guest to simply find the entry corresponding to the + * base/legacy XSAVE area size (XCR0=1 or XCR0=3), and then calculate the + * XSAVE area size using subfunctions 2 through 64, as documented in APM + * Volume 3, Rev 3.31, Appendix E.3.8, which is what is done here. + * + * Since base/legacy XSAVE area size is documented as 0x240, use that value + * directly rather than relying on the base size in the CPUID table. + * + * Return: XSAVE area size on success, 0 otherwise. + */ +static u32 snp_cpuid_calc_xsave_size(u64 xfeatures_en, bool compacted) +{ + const struct snp_cpuid_table *cpuid_table = snp_cpuid_get_table(); + u64 xfeatures_found = 0; + u32 xsave_size = 0x240; + int i; + + for (i = 0; i < cpuid_table->count; i++) { + const struct snp_cpuid_fn *e = &cpuid_table->fn[i]; + + if (!(e->eax_in == 0xD && e->ecx_in > 1 && e->ecx_in < 64)) + continue; + if (!(xfeatures_en & (BIT_ULL(e->ecx_in)))) + continue; + if (xfeatures_found & (BIT_ULL(e->ecx_in))) + continue; + + xfeatures_found |= (BIT_ULL(e->ecx_in)); + + if (compacted) + xsave_size += e->eax; + else + xsave_size = max(xsave_size, e->eax + e->ebx); + } + + /* + * Either the guest set unsupported XCR0/XSS bits, or the corresponding + * entries in the CPUID table were not present. This is not a valid + * state to be in. + */ + if (xfeatures_found != (xfeatures_en & GENMASK_ULL(63, 2))) + return 0; + + return xsave_size; +} + +static bool +snp_cpuid_get_validated_func(struct cpuid_leaf *leaf) +{ + const struct snp_cpuid_table *cpuid_table = snp_cpuid_get_table(); + int i; + + for (i = 0; i < cpuid_table->count; i++) { + const struct snp_cpuid_fn *e = &cpuid_table->fn[i]; + + if (e->eax_in != leaf->fn) + continue; + + if (cpuid_function_is_indexed(leaf->fn) && e->ecx_in != leaf->subfn) + continue; + + /* + * For 0xD subfunctions 0 and 1, only use the entry corresponding + * to the base/legacy XSAVE area size (XCR0=1 or XCR0=3, XSS=0). + * See the comments above snp_cpuid_calc_xsave_size() for more + * details. + */ + if (e->eax_in == 0xD && (e->ecx_in == 0 || e->ecx_in == 1)) + if (!(e->xcr0_in == 1 || e->xcr0_in == 3) || e->xss_in) + continue; + + leaf->eax = e->eax; + leaf->ebx = e->ebx; + leaf->ecx = e->ecx; + leaf->edx = e->edx; + + return true; + } + + return false; +} + +static void snp_cpuid_hv(struct cpuid_leaf *leaf) +{ + if (sev_cpuid_hv(leaf)) + sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_CPUID_HV); +} + +static int snp_cpuid_postprocess(struct cpuid_leaf *leaf) +{ + struct cpuid_leaf leaf_hv = *leaf; + + switch (leaf->fn) { + case 0x1: + snp_cpuid_hv(&leaf_hv); + + /* initial APIC ID */ + leaf->ebx = (leaf_hv.ebx & GENMASK(31, 24)) | (leaf->ebx & GENMASK(23, 0)); + /* APIC enabled bit */ + leaf->edx = (leaf_hv.edx & BIT(9)) | (leaf->edx & ~BIT(9)); + + /* OSXSAVE enabled bit */ + if (native_read_cr4() & X86_CR4_OSXSAVE) + leaf->ecx |= BIT(27); + break; + case 0x7: + /* OSPKE enabled bit */ + leaf->ecx &= ~BIT(4); + if (native_read_cr4() & X86_CR4_PKE) + leaf->ecx |= BIT(4); + break; + case 0xB: + leaf_hv.subfn = 0; + snp_cpuid_hv(&leaf_hv); + + /* extended APIC ID */ + leaf->edx = leaf_hv.edx; + break; + case 0xD: { + bool compacted = false; + u64 xcr0 = 1, xss = 0; + u32 xsave_size; + + if (leaf->subfn != 0 && leaf->subfn != 1) + return 0; + + if (native_read_cr4() & X86_CR4_OSXSAVE) + xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); + if (leaf->subfn == 1) { + /* Get XSS value if XSAVES is enabled. */ + if (leaf->eax & BIT(3)) { + unsigned long lo, hi; + + asm volatile("rdmsr" : "=a" (lo), "=d" (hi) + : "c" (MSR_IA32_XSS)); + xss = (hi << 32) | lo; + } + + /* + * The PPR and APM aren't clear on what size should be + * encoded in 0xD:0x1:EBX when compaction is not enabled + * by either XSAVEC (feature bit 1) or XSAVES (feature + * bit 3) since SNP-capable hardware has these feature + * bits fixed as 1. KVM sets it to 0 in this case, but + * to avoid this becoming an issue it's safer to simply + * treat this as unsupported for SNP guests. + */ + if (!(leaf->eax & (BIT(1) | BIT(3)))) + return -EINVAL; + + compacted = true; + } + + xsave_size = snp_cpuid_calc_xsave_size(xcr0 | xss, compacted); + if (!xsave_size) + return -EINVAL; + + leaf->ebx = xsave_size; + } + break; + case 0x8000001E: + snp_cpuid_hv(&leaf_hv); + + /* extended APIC ID */ + leaf->eax = leaf_hv.eax; + /* compute ID */ + leaf->ebx = (leaf->ebx & GENMASK(31, 8)) | (leaf_hv.ebx & GENMASK(7, 0)); + /* node ID */ + leaf->ecx = (leaf->ecx & GENMASK(31, 8)) | (leaf_hv.ecx & GENMASK(7, 0)); + break; + default: + /* No fix-ups needed, use values as-is. */ + break; + } + + return 0; +} + +/* + * Returns -EOPNOTSUPP if feature not enabled. Any other non-zero return value + * should be treated as fatal by caller. + */ +static int snp_cpuid(struct cpuid_leaf *leaf) +{ + const struct snp_cpuid_table *cpuid_table = snp_cpuid_get_table(); + + if (!cpuid_table->count) + return -EOPNOTSUPP; + + if (!snp_cpuid_get_validated_func(leaf)) { + /* + * Some hypervisors will avoid keeping track of CPUID entries + * where all values are zero, since they can be handled the + * same as out-of-range values (all-zero). This is useful here + * as well as it allows virtually all guest configurations to + * work using a single SNP CPUID table. + * + * To allow for this, there is a need to distinguish between + * out-of-range entries and in-range zero entries, since the + * CPUID table entries are only a template that may need to be + * augmented with additional values for things like + * CPU-specific information during post-processing. So if it's + * not in the table, set the values to zero. Then, if they are + * within a valid CPUID range, proceed with post-processing + * using zeros as the initial values. Otherwise, skip + * post-processing and just return zeros immediately. + */ + leaf->eax = leaf->ebx = leaf->ecx = leaf->edx = 0; + + /* Skip post-processing for out-of-range zero leafs. */ + if (!(leaf->fn <= cpuid_std_range_max || + (leaf->fn >= 0x40000000 && leaf->fn <= cpuid_hyp_range_max) || + (leaf->fn >= 0x80000000 && leaf->fn <= cpuid_ext_range_max))) + return 0; + } + + return snp_cpuid_postprocess(leaf); +} + /* * Boot VC Handler - This is the first VC handler during boot, there is no GHCB * page yet, so it only supports the MSR based communication with the @@ -157,40 +535,33 @@ enum es_result sev_es_ghcb_hv_call(struct ghcb *ghcb, bool set_ghcb_msr, */ void __init do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code) { + unsigned int subfn = lower_bits(regs->cx, 32); unsigned int fn = lower_bits(regs->ax, 32); - unsigned long val; + struct cpuid_leaf leaf; + int ret; /* Only CPUID is supported via MSR protocol */ if (exit_code != SVM_EXIT_CPUID) goto fail; - sev_es_wr_ghcb_msr(GHCB_CPUID_REQ(fn, GHCB_CPUID_REQ_EAX)); - VMGEXIT(); - val = sev_es_rd_ghcb_msr(); - if (GHCB_RESP_CODE(val) != GHCB_MSR_CPUID_RESP) - goto fail; - regs->ax = val >> 32; + leaf.fn = fn; + leaf.subfn = subfn; - sev_es_wr_ghcb_msr(GHCB_CPUID_REQ(fn, GHCB_CPUID_REQ_EBX)); - VMGEXIT(); - val = sev_es_rd_ghcb_msr(); - if (GHCB_RESP_CODE(val) != GHCB_MSR_CPUID_RESP) - goto fail; - regs->bx = val >> 32; + ret = snp_cpuid(&leaf); + if (!ret) + goto cpuid_done; - sev_es_wr_ghcb_msr(GHCB_CPUID_REQ(fn, GHCB_CPUID_REQ_ECX)); - VMGEXIT(); - val = sev_es_rd_ghcb_msr(); - if (GHCB_RESP_CODE(val) != GHCB_MSR_CPUID_RESP) + if (ret != -EOPNOTSUPP) goto fail; - regs->cx = val >> 32; - sev_es_wr_ghcb_msr(GHCB_CPUID_REQ(fn, GHCB_CPUID_REQ_EDX)); - VMGEXIT(); - val = sev_es_rd_ghcb_msr(); - if (GHCB_RESP_CODE(val) != GHCB_MSR_CPUID_RESP) + if (sev_cpuid_hv(&leaf)) goto fail; - regs->dx = val >> 32; + +cpuid_done: + regs->ax = leaf.eax; + regs->bx = leaf.ebx; + regs->cx = leaf.ecx; + regs->dx = leaf.edx; /* * This is a VC handler and the #VC is only raised when SEV-ES is @@ -221,7 +592,7 @@ void __init do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code) fail: /* Terminate the guest */ - sev_es_terminate(GHCB_SEV_ES_GEN_REQ); + sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ); } static enum es_result vc_insn_string_read(struct es_em_ctxt *ctxt, @@ -481,12 +852,37 @@ static enum es_result vc_handle_ioio(struct ghcb *ghcb, struct es_em_ctxt *ctxt) return ret; } +static int vc_handle_cpuid_snp(struct pt_regs *regs) +{ + struct cpuid_leaf leaf; + int ret; + + leaf.fn = regs->ax; + leaf.subfn = regs->cx; + ret = snp_cpuid(&leaf); + if (!ret) { + regs->ax = leaf.eax; + regs->bx = leaf.ebx; + regs->cx = leaf.ecx; + regs->dx = leaf.edx; + } + + return ret; +} + static enum es_result vc_handle_cpuid(struct ghcb *ghcb, struct es_em_ctxt *ctxt) { struct pt_regs *regs = ctxt->regs; u32 cr4 = native_read_cr4(); enum es_result ret; + int snp_cpuid_ret; + + snp_cpuid_ret = vc_handle_cpuid_snp(regs); + if (!snp_cpuid_ret) + return ES_OK; + if (snp_cpuid_ret != -EOPNOTSUPP) + return ES_VMM_ERROR; ghcb_set_rax(ghcb, regs->ax); ghcb_set_rcx(ghcb, regs->cx); @@ -538,3 +934,67 @@ static enum es_result vc_handle_rdtsc(struct ghcb *ghcb, return ES_OK; } + +struct cc_setup_data { + struct setup_data header; + u32 cc_blob_address; +}; + +/* + * Search for a Confidential Computing blob passed in as a setup_data entry + * via the Linux Boot Protocol. + */ +static struct cc_blob_sev_info *find_cc_blob_setup_data(struct boot_params *bp) +{ + struct cc_setup_data *sd = NULL; + struct setup_data *hdr; + + hdr = (struct setup_data *)bp->hdr.setup_data; + + while (hdr) { + if (hdr->type == SETUP_CC_BLOB) { + sd = (struct cc_setup_data *)hdr; + return (struct cc_blob_sev_info *)(unsigned long)sd->cc_blob_address; + } + hdr = (struct setup_data *)hdr->next; + } + + return NULL; +} + +/* + * Initialize the kernel's copy of the SNP CPUID table, and set up the + * pointer that will be used to access it. + * + * Maintaining a direct mapping of the SNP CPUID table used by firmware would + * be possible as an alternative, but the approach is brittle since the + * mapping needs to be updated in sync with all the changes to virtual memory + * layout and related mapping facilities throughout the boot process. + */ +static void __init setup_cpuid_table(const struct cc_blob_sev_info *cc_info) +{ + const struct snp_cpuid_table *cpuid_table_fw, *cpuid_table; + int i; + + if (!cc_info || !cc_info->cpuid_phys || cc_info->cpuid_len < PAGE_SIZE) + sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_CPUID); + + cpuid_table_fw = (const struct snp_cpuid_table *)cc_info->cpuid_phys; + if (!cpuid_table_fw->count || cpuid_table_fw->count > SNP_CPUID_COUNT_MAX) + sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_CPUID); + + cpuid_table = snp_cpuid_get_table(); + memcpy((void *)cpuid_table, cpuid_table_fw, sizeof(*cpuid_table)); + + /* Initialize CPUID ranges for range-checking. */ + for (i = 0; i < cpuid_table->count; i++) { + const struct snp_cpuid_fn *fn = &cpuid_table->fn[i]; + + if (fn->eax_in == 0x0) + cpuid_std_range_max = fn->eax; + else if (fn->eax_in == 0x40000000) + cpuid_hyp_range_max = fn->eax; + else if (fn->eax_in == 0x80000000) + cpuid_ext_range_max = fn->eax; + } +} diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c index e6d316a01fdd..c05f0124c410 100644 --- a/arch/x86/kernel/sev.c +++ b/arch/x86/kernel/sev.c @@ -18,6 +18,10 @@ #include <linux/memblock.h> #include <linux/kernel.h> #include <linux/mm.h> +#include <linux/cpumask.h> +#include <linux/efi.h> +#include <linux/platform_device.h> +#include <linux/io.h> #include <asm/cpu_entry_area.h> #include <asm/stacktrace.h> @@ -31,9 +35,28 @@ #include <asm/svm.h> #include <asm/smp.h> #include <asm/cpu.h> +#include <asm/apic.h> +#include <asm/cpuid.h> +#include <asm/cmdline.h> #define DR7_RESET_VALUE 0x400 +/* AP INIT values as documented in the APM2 section "Processor Initialization State" */ +#define AP_INIT_CS_LIMIT 0xffff +#define AP_INIT_DS_LIMIT 0xffff +#define AP_INIT_LDTR_LIMIT 0xffff +#define AP_INIT_GDTR_LIMIT 0xffff +#define AP_INIT_IDTR_LIMIT 0xffff +#define AP_INIT_TR_LIMIT 0xffff +#define AP_INIT_RFLAGS_DEFAULT 0x2 +#define AP_INIT_DR6_DEFAULT 0xffff0ff0 +#define AP_INIT_GPAT_DEFAULT 0x0007040600070406ULL +#define AP_INIT_XCR0_DEFAULT 0x1 +#define AP_INIT_X87_FTW_DEFAULT 0x5555 +#define AP_INIT_X87_FCW_DEFAULT 0x0040 +#define AP_INIT_CR0_DEFAULT 0x60000010 +#define AP_INIT_MXCSR_DEFAULT 0x1f80 + /* For early boot hypervisor communication in SEV-ES enabled guests */ static struct ghcb boot_ghcb_page __bss_decrypted __aligned(PAGE_SIZE); @@ -41,7 +64,10 @@ static struct ghcb boot_ghcb_page __bss_decrypted __aligned(PAGE_SIZE); * Needs to be in the .data section because we need it NULL before bss is * cleared */ -static struct ghcb __initdata *boot_ghcb; +static struct ghcb *boot_ghcb __section(".data"); + +/* Bitmap of SEV features supported by the hypervisor */ +static u64 sev_hv_features __ro_after_init; /* #VC handler runtime per-CPU data */ struct sev_es_runtime_data { @@ -87,6 +113,15 @@ struct ghcb_state { static DEFINE_PER_CPU(struct sev_es_runtime_data*, runtime_data); DEFINE_STATIC_KEY_FALSE(sev_es_enable_key); +static DEFINE_PER_CPU(struct sev_es_save_area *, sev_vmsa); + +struct sev_config { + __u64 debug : 1, + __reserved : 63; +}; + +static struct sev_config sev_cfg __read_mostly; + static __always_inline bool on_vc_stack(struct pt_regs *regs) { unsigned long sp = regs->sp; @@ -523,13 +558,68 @@ void noinstr __sev_es_nmi_complete(void) __sev_put_ghcb(&state); } -static u64 get_jump_table_addr(void) +static u64 __init get_secrets_page(void) +{ + u64 pa_data = boot_params.cc_blob_address; + struct cc_blob_sev_info info; + void *map; + + /* + * The CC blob contains the address of the secrets page, check if the + * blob is present. + */ + if (!pa_data) + return 0; + + map = early_memremap(pa_data, sizeof(info)); + if (!map) { + pr_err("Unable to locate SNP secrets page: failed to map the Confidential Computing blob.\n"); + return 0; + } + memcpy(&info, map, sizeof(info)); + early_memunmap(map, sizeof(info)); + + /* smoke-test the secrets page passed */ + if (!info.secrets_phys || info.secrets_len != PAGE_SIZE) + return 0; + + return info.secrets_phys; +} + +static u64 __init get_snp_jump_table_addr(void) +{ + struct snp_secrets_page_layout *layout; + void __iomem *mem; + u64 pa, addr; + + pa = get_secrets_page(); + if (!pa) + return 0; + + mem = ioremap_encrypted(pa, PAGE_SIZE); + if (!mem) { + pr_err("Unable to locate AP jump table address: failed to map the SNP secrets page.\n"); + return 0; + } + + layout = (__force struct snp_secrets_page_layout *)mem; + + addr = layout->os_area.ap_jump_table_pa; + iounmap(mem); + + return addr; +} + +static u64 __init get_jump_table_addr(void) { struct ghcb_state state; unsigned long flags; struct ghcb *ghcb; u64 ret = 0; + if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) + return get_snp_jump_table_addr(); + local_irq_save(flags); ghcb = __sev_get_ghcb(&state); @@ -553,7 +643,496 @@ static u64 get_jump_table_addr(void) return ret; } -int sev_es_setup_ap_jump_table(struct real_mode_header *rmh) +static void pvalidate_pages(unsigned long vaddr, unsigned int npages, bool validate) +{ + unsigned long vaddr_end; + int rc; + + vaddr = vaddr & PAGE_MASK; + vaddr_end = vaddr + (npages << PAGE_SHIFT); + + while (vaddr < vaddr_end) { + rc = pvalidate(vaddr, RMP_PG_SIZE_4K, validate); + if (WARN(rc, "Failed to validate address 0x%lx ret %d", vaddr, rc)) + sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PVALIDATE); + + vaddr = vaddr + PAGE_SIZE; + } +} + +static void __init early_set_pages_state(unsigned long paddr, unsigned int npages, enum psc_op op) +{ + unsigned long paddr_end; + u64 val; + + paddr = paddr & PAGE_MASK; + paddr_end = paddr + (npages << PAGE_SHIFT); + + while (paddr < paddr_end) { + /* + * Use the MSR protocol because this function can be called before + * the GHCB is established. + */ + sev_es_wr_ghcb_msr(GHCB_MSR_PSC_REQ_GFN(paddr >> PAGE_SHIFT, op)); + VMGEXIT(); + + val = sev_es_rd_ghcb_msr(); + + if (WARN(GHCB_RESP_CODE(val) != GHCB_MSR_PSC_RESP, + "Wrong PSC response code: 0x%x\n", + (unsigned int)GHCB_RESP_CODE(val))) + goto e_term; + + if (WARN(GHCB_MSR_PSC_RESP_VAL(val), + "Failed to change page state to '%s' paddr 0x%lx error 0x%llx\n", + op == SNP_PAGE_STATE_PRIVATE ? "private" : "shared", + paddr, GHCB_MSR_PSC_RESP_VAL(val))) + goto e_term; + + paddr = paddr + PAGE_SIZE; + } + + return; + +e_term: + sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PSC); +} + +void __init early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr, + unsigned int npages) +{ + if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) + return; + + /* + * Ask the hypervisor to mark the memory pages as private in the RMP + * table. + */ + early_set_pages_state(paddr, npages, SNP_PAGE_STATE_PRIVATE); + + /* Validate the memory pages after they've been added in the RMP table. */ + pvalidate_pages(vaddr, npages, true); +} + +void __init early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr, + unsigned int npages) +{ + if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) + return; + + /* Invalidate the memory pages before they are marked shared in the RMP table. */ + pvalidate_pages(vaddr, npages, false); + + /* Ask hypervisor to mark the memory pages shared in the RMP table. */ + early_set_pages_state(paddr, npages, SNP_PAGE_STATE_SHARED); +} + +void __init snp_prep_memory(unsigned long paddr, unsigned int sz, enum psc_op op) +{ + unsigned long vaddr, npages; + + vaddr = (unsigned long)__va(paddr); + npages = PAGE_ALIGN(sz) >> PAGE_SHIFT; + + if (op == SNP_PAGE_STATE_PRIVATE) + early_snp_set_memory_private(vaddr, paddr, npages); + else if (op == SNP_PAGE_STATE_SHARED) + early_snp_set_memory_shared(vaddr, paddr, npages); + else + WARN(1, "invalid memory op %d\n", op); +} + +static int vmgexit_psc(struct snp_psc_desc *desc) +{ + int cur_entry, end_entry, ret = 0; + struct snp_psc_desc *data; + struct ghcb_state state; + struct es_em_ctxt ctxt; + unsigned long flags; + struct ghcb *ghcb; + + /* + * __sev_get_ghcb() needs to run with IRQs disabled because it is using + * a per-CPU GHCB. + */ + local_irq_save(flags); + + ghcb = __sev_get_ghcb(&state); + if (!ghcb) { + ret = 1; + goto out_unlock; + } + + /* Copy the input desc into GHCB shared buffer */ + data = (struct snp_psc_desc *)ghcb->shared_buffer; + memcpy(ghcb->shared_buffer, desc, min_t(int, GHCB_SHARED_BUF_SIZE, sizeof(*desc))); + + /* + * As per the GHCB specification, the hypervisor can resume the guest + * before processing all the entries. Check whether all the entries + * are processed. If not, then keep retrying. Note, the hypervisor + * will update the data memory directly to indicate the status, so + * reference the data->hdr everywhere. + * + * The strategy here is to wait for the hypervisor to change the page + * state in the RMP table before guest accesses the memory pages. If the + * page state change was not successful, then later memory access will + * result in a crash. + */ + cur_entry = data->hdr.cur_entry; + end_entry = data->hdr.end_entry; + + while (data->hdr.cur_entry <= data->hdr.end_entry) { + ghcb_set_sw_scratch(ghcb, (u64)__pa(data)); + + /* This will advance the shared buffer data points to. */ + ret = sev_es_ghcb_hv_call(ghcb, true, &ctxt, SVM_VMGEXIT_PSC, 0, 0); + + /* + * Page State Change VMGEXIT can pass error code through + * exit_info_2. + */ + if (WARN(ret || ghcb->save.sw_exit_info_2, + "SNP: PSC failed ret=%d exit_info_2=%llx\n", + ret, ghcb->save.sw_exit_info_2)) { + ret = 1; + goto out; + } + + /* Verify that reserved bit is not set */ + if (WARN(data->hdr.reserved, "Reserved bit is set in the PSC header\n")) { + ret = 1; + goto out; + } + + /* + * Sanity check that entry processing is not going backwards. + * This will happen only if hypervisor is tricking us. + */ + if (WARN(data->hdr.end_entry > end_entry || cur_entry > data->hdr.cur_entry, +"SNP: PSC processing going backward, end_entry %d (got %d) cur_entry %d (got %d)\n", + end_entry, data->hdr.end_entry, cur_entry, data->hdr.cur_entry)) { + ret = 1; + goto out; + } + } + +out: + __sev_put_ghcb(&state); + +out_unlock: + local_irq_restore(flags); + + return ret; +} + +static void __set_pages_state(struct snp_psc_desc *data, unsigned long vaddr, + unsigned long vaddr_end, int op) +{ + struct psc_hdr *hdr; + struct psc_entry *e; + unsigned long pfn; + int i; + + hdr = &data->hdr; + e = data->entries; + + memset(data, 0, sizeof(*data)); + i = 0; + + while (vaddr < vaddr_end) { + if (is_vmalloc_addr((void *)vaddr)) + pfn = vmalloc_to_pfn((void *)vaddr); + else + pfn = __pa(vaddr) >> PAGE_SHIFT; + + e->gfn = pfn; + e->operation = op; + hdr->end_entry = i; + + /* + * Current SNP implementation doesn't keep track of the RMP page + * size so use 4K for simplicity. + */ + e->pagesize = RMP_PG_SIZE_4K; + + vaddr = vaddr + PAGE_SIZE; + e++; + i++; + } + + if (vmgexit_psc(data)) + sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PSC); +} + +static void set_pages_state(unsigned long vaddr, unsigned int npages, int op) +{ + unsigned long vaddr_end, next_vaddr; + struct snp_psc_desc *desc; + + desc = kmalloc(sizeof(*desc), GFP_KERNEL_ACCOUNT); + if (!desc) + panic("SNP: failed to allocate memory for PSC descriptor\n"); + + vaddr = vaddr & PAGE_MASK; + vaddr_end = vaddr + (npages << PAGE_SHIFT); + + while (vaddr < vaddr_end) { + /* Calculate the last vaddr that fits in one struct snp_psc_desc. */ + next_vaddr = min_t(unsigned long, vaddr_end, + (VMGEXIT_PSC_MAX_ENTRY * PAGE_SIZE) + vaddr); + + __set_pages_state(desc, vaddr, next_vaddr, op); + + vaddr = next_vaddr; + } + + kfree(desc); +} + +void snp_set_memory_shared(unsigned long vaddr, unsigned int npages) +{ + if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) + return; + + pvalidate_pages(vaddr, npages, false); + + set_pages_state(vaddr, npages, SNP_PAGE_STATE_SHARED); +} + +void snp_set_memory_private(unsigned long vaddr, unsigned int npages) +{ + if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) + return; + + set_pages_state(vaddr, npages, SNP_PAGE_STATE_PRIVATE); + + pvalidate_pages(vaddr, npages, true); +} + +static int snp_set_vmsa(void *va, bool vmsa) +{ + u64 attrs; + + /* + * Running at VMPL0 allows the kernel to change the VMSA bit for a page + * using the RMPADJUST instruction. However, for the instruction to + * succeed it must target the permissions of a lesser privileged + * (higher numbered) VMPL level, so use VMPL1 (refer to the RMPADJUST + * instruction in the AMD64 APM Volume 3). + */ + attrs = 1; + if (vmsa) + attrs |= RMPADJUST_VMSA_PAGE_BIT; + + return rmpadjust((unsigned long)va, RMP_PG_SIZE_4K, attrs); +} + +#define __ATTR_BASE (SVM_SELECTOR_P_MASK | SVM_SELECTOR_S_MASK) +#define INIT_CS_ATTRIBS (__ATTR_BASE | SVM_SELECTOR_READ_MASK | SVM_SELECTOR_CODE_MASK) +#define INIT_DS_ATTRIBS (__ATTR_BASE | SVM_SELECTOR_WRITE_MASK) + +#define INIT_LDTR_ATTRIBS (SVM_SELECTOR_P_MASK | 2) +#define INIT_TR_ATTRIBS (SVM_SELECTOR_P_MASK | 3) + +static void *snp_alloc_vmsa_page(void) +{ + struct page *p; + + /* + * Allocate VMSA page to work around the SNP erratum where the CPU will + * incorrectly signal an RMP violation #PF if a large page (2MB or 1GB) + * collides with the RMP entry of VMSA page. The recommended workaround + * is to not use a large page. + * + * Allocate an 8k page which is also 8k-aligned. + */ + p = alloc_pages(GFP_KERNEL_ACCOUNT | __GFP_ZERO, 1); + if (!p) + return NULL; + + split_page(p, 1); + + /* Free the first 4k. This page may be 2M/1G aligned and cannot be used. */ + __free_page(p); + + return page_address(p + 1); +} + +static void snp_cleanup_vmsa(struct sev_es_save_area *vmsa) +{ + int err; + + err = snp_set_vmsa(vmsa, false); + if (err) + pr_err("clear VMSA page failed (%u), leaking page\n", err); + else + free_page((unsigned long)vmsa); +} + +static int wakeup_cpu_via_vmgexit(int apic_id, unsigned long start_ip) +{ + struct sev_es_save_area *cur_vmsa, *vmsa; + struct ghcb_state state; + unsigned long flags; + struct ghcb *ghcb; + u8 sipi_vector; + int cpu, ret; + u64 cr4; + + /* + * The hypervisor SNP feature support check has happened earlier, just check + * the AP_CREATION one here. + */ + if (!(sev_hv_features & GHCB_HV_FT_SNP_AP_CREATION)) + return -EOPNOTSUPP; + + /* + * Verify the desired start IP against the known trampoline start IP + * to catch any future new trampolines that may be introduced that + * would require a new protected guest entry point. + */ + if (WARN_ONCE(start_ip != real_mode_header->trampoline_start, + "Unsupported SNP start_ip: %lx\n", start_ip)) + return -EINVAL; + + /* Override start_ip with known protected guest start IP */ + start_ip = real_mode_header->sev_es_trampoline_start; + + /* Find the logical CPU for the APIC ID */ + for_each_present_cpu(cpu) { + if (arch_match_cpu_phys_id(cpu, apic_id)) + break; + } + if (cpu >= nr_cpu_ids) + return -EINVAL; + + cur_vmsa = per_cpu(sev_vmsa, cpu); + + /* + * A new VMSA is created each time because there is no guarantee that + * the current VMSA is the kernels or that the vCPU is not running. If + * an attempt was done to use the current VMSA with a running vCPU, a + * #VMEXIT of that vCPU would wipe out all of the settings being done + * here. + */ + vmsa = (struct sev_es_save_area *)snp_alloc_vmsa_page(); + if (!vmsa) + return -ENOMEM; + + /* CR4 should maintain the MCE value */ + cr4 = native_read_cr4() & X86_CR4_MCE; + + /* Set the CS value based on the start_ip converted to a SIPI vector */ + sipi_vector = (start_ip >> 12); + vmsa->cs.base = sipi_vector << 12; + vmsa->cs.limit = AP_INIT_CS_LIMIT; + vmsa->cs.attrib = INIT_CS_ATTRIBS; + vmsa->cs.selector = sipi_vector << 8; + + /* Set the RIP value based on start_ip */ + vmsa->rip = start_ip & 0xfff; + + /* Set AP INIT defaults as documented in the APM */ + vmsa->ds.limit = AP_INIT_DS_LIMIT; + vmsa->ds.attrib = INIT_DS_ATTRIBS; + vmsa->es = vmsa->ds; + vmsa->fs = vmsa->ds; + vmsa->gs = vmsa->ds; + vmsa->ss = vmsa->ds; + + vmsa->gdtr.limit = AP_INIT_GDTR_LIMIT; + vmsa->ldtr.limit = AP_INIT_LDTR_LIMIT; + vmsa->ldtr.attrib = INIT_LDTR_ATTRIBS; + vmsa->idtr.limit = AP_INIT_IDTR_LIMIT; + vmsa->tr.limit = AP_INIT_TR_LIMIT; + vmsa->tr.attrib = INIT_TR_ATTRIBS; + + vmsa->cr4 = cr4; + vmsa->cr0 = AP_INIT_CR0_DEFAULT; + vmsa->dr7 = DR7_RESET_VALUE; + vmsa->dr6 = AP_INIT_DR6_DEFAULT; + vmsa->rflags = AP_INIT_RFLAGS_DEFAULT; + vmsa->g_pat = AP_INIT_GPAT_DEFAULT; + vmsa->xcr0 = AP_INIT_XCR0_DEFAULT; + vmsa->mxcsr = AP_INIT_MXCSR_DEFAULT; + vmsa->x87_ftw = AP_INIT_X87_FTW_DEFAULT; + vmsa->x87_fcw = AP_INIT_X87_FCW_DEFAULT; + + /* SVME must be set. */ + vmsa->efer = EFER_SVME; + + /* + * Set the SNP-specific fields for this VMSA: + * VMPL level + * SEV_FEATURES (matches the SEV STATUS MSR right shifted 2 bits) + */ + vmsa->vmpl = 0; + vmsa->sev_features = sev_status >> 2; + + /* Switch the page over to a VMSA page now that it is initialized */ + ret = snp_set_vmsa(vmsa, true); + if (ret) { + pr_err("set VMSA page failed (%u)\n", ret); + free_page((unsigned long)vmsa); + + return -EINVAL; + } + + /* Issue VMGEXIT AP Creation NAE event */ + local_irq_save(flags); + + ghcb = __sev_get_ghcb(&state); + + vc_ghcb_invalidate(ghcb); + ghcb_set_rax(ghcb, vmsa->sev_features); + ghcb_set_sw_exit_code(ghcb, SVM_VMGEXIT_AP_CREATION); + ghcb_set_sw_exit_info_1(ghcb, ((u64)apic_id << 32) | SVM_VMGEXIT_AP_CREATE); + ghcb_set_sw_exit_info_2(ghcb, __pa(vmsa)); + + sev_es_wr_ghcb_msr(__pa(ghcb)); + VMGEXIT(); + + if (!ghcb_sw_exit_info_1_is_valid(ghcb) || + lower_32_bits(ghcb->save.sw_exit_info_1)) { + pr_err("SNP AP Creation error\n"); + ret = -EINVAL; + } + + __sev_put_ghcb(&state); + + local_irq_restore(flags); + + /* Perform cleanup if there was an error */ + if (ret) { + snp_cleanup_vmsa(vmsa); + vmsa = NULL; + } + + /* Free up any previous VMSA page */ + if (cur_vmsa) + snp_cleanup_vmsa(cur_vmsa); + + /* Record the current VMSA page */ + per_cpu(sev_vmsa, cpu) = vmsa; + + return ret; +} + +void snp_set_wakeup_secondary_cpu(void) +{ + if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) + return; + + /* + * Always set this override if SNP is enabled. This makes it the + * required method to start APs under SNP. If the hypervisor does + * not support AP creation, then no APs will be started. + */ + apic->wakeup_secondary_cpu = wakeup_cpu_via_vmgexit; +} + +int __init sev_es_setup_ap_jump_table(struct real_mode_header *rmh) { u16 startup_cs, startup_ip; phys_addr_t jump_table_pa; @@ -644,15 +1223,39 @@ static enum es_result vc_handle_msr(struct ghcb *ghcb, struct es_em_ctxt *ctxt) return ret; } -/* - * This function runs on the first #VC exception after the kernel - * switched to virtual addresses. - */ -static bool __init sev_es_setup_ghcb(void) +static void snp_register_per_cpu_ghcb(void) +{ + struct sev_es_runtime_data *data; + struct ghcb *ghcb; + + data = this_cpu_read(runtime_data); + ghcb = &data->ghcb_page; + + snp_register_ghcb_early(__pa(ghcb)); +} + +void setup_ghcb(void) { + if (!cc_platform_has(CC_ATTR_GUEST_STATE_ENCRYPT)) + return; + /* First make sure the hypervisor talks a supported protocol. */ if (!sev_es_negotiate_protocol()) - return false; + sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ); + + /* + * Check whether the runtime #VC exception handler is active. It uses + * the per-CPU GHCB page which is set up by sev_es_init_vc_handling(). + * + * If SNP is active, register the per-CPU GHCB page so that the runtime + * exception handler can use it. + */ + if (initial_vc_handler == (unsigned long)kernel_exc_vmm_communication) { + if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) + snp_register_per_cpu_ghcb(); + + return; + } /* * Clear the boot_ghcb. The first exception comes in before the bss @@ -663,7 +1266,9 @@ static bool __init sev_es_setup_ghcb(void) /* Alright - Make the boot-ghcb public */ boot_ghcb = &boot_ghcb_page; - return true; + /* SNP guest requires that GHCB GPA must be registered. */ + if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) + snp_register_ghcb_early(__pa(&boot_ghcb_page)); } #ifdef CONFIG_HOTPLUG_CPU @@ -766,6 +1371,17 @@ void __init sev_es_init_vc_handling(void) if (!sev_es_check_cpu_features()) panic("SEV-ES CPU Features missing"); + /* + * SNP is supported in v2 of the GHCB spec which mandates support for HV + * features. + */ + if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) { + sev_hv_features = get_hv_features(); + + if (!(sev_hv_features & GHCB_HV_FT_SNP)) + sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED); + } + /* Enable SEV-ES special handling */ static_branch_enable(&sev_es_enable_key); @@ -1337,7 +1953,7 @@ DEFINE_IDTENTRY_VC_KERNEL(exc_vmm_communication) show_regs(regs); /* Ask hypervisor to sev_es_terminate */ - sev_es_terminate(GHCB_SEV_ES_GEN_REQ); + sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ); /* If that fails and we get here - just panic */ panic("Returned from Terminate-Request to Hypervisor\n"); @@ -1383,10 +1999,6 @@ bool __init handle_vc_boot_ghcb(struct pt_regs *regs) struct es_em_ctxt ctxt; enum es_result result; - /* Do initial setup or terminate the guest */ - if (unlikely(boot_ghcb == NULL && !sev_es_setup_ghcb())) - sev_es_terminate(GHCB_SEV_ES_GEN_REQ); - vc_ghcb_invalidate(boot_ghcb); result = vc_init_em_ctxt(&ctxt, regs, exit_code); @@ -1425,6 +2037,215 @@ bool __init handle_vc_boot_ghcb(struct pt_regs *regs) fail: show_regs(regs); - while (true) - halt(); + sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ); +} + +/* + * Initial set up of SNP relies on information provided by the + * Confidential Computing blob, which can be passed to the kernel + * in the following ways, depending on how it is booted: + * + * - when booted via the boot/decompress kernel: + * - via boot_params + * + * - when booted directly by firmware/bootloader (e.g. CONFIG_PVH): + * - via a setup_data entry, as defined by the Linux Boot Protocol + * + * Scan for the blob in that order. + */ +static __init struct cc_blob_sev_info *find_cc_blob(struct boot_params *bp) +{ + struct cc_blob_sev_info *cc_info; + + /* Boot kernel would have passed the CC blob via boot_params. */ + if (bp->cc_blob_address) { + cc_info = (struct cc_blob_sev_info *)(unsigned long)bp->cc_blob_address; + goto found_cc_info; + } + + /* + * If kernel was booted directly, without the use of the + * boot/decompression kernel, the CC blob may have been passed via + * setup_data instead. + */ + cc_info = find_cc_blob_setup_data(bp); + if (!cc_info) + return NULL; + +found_cc_info: + if (cc_info->magic != CC_BLOB_SEV_HDR_MAGIC) + snp_abort(); + + return cc_info; +} + +bool __init snp_init(struct boot_params *bp) +{ + struct cc_blob_sev_info *cc_info; + + if (!bp) + return false; + + cc_info = find_cc_blob(bp); + if (!cc_info) + return false; + + setup_cpuid_table(cc_info); + + /* + * The CC blob will be used later to access the secrets page. Cache + * it here like the boot kernel does. + */ + bp->cc_blob_address = (u32)(unsigned long)cc_info; + + return true; +} + +void __init snp_abort(void) +{ + sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED); +} + +static void dump_cpuid_table(void) +{ + const struct snp_cpuid_table *cpuid_table = snp_cpuid_get_table(); + int i = 0; + + pr_info("count=%d reserved=0x%x reserved2=0x%llx\n", + cpuid_table->count, cpuid_table->__reserved1, cpuid_table->__reserved2); + + for (i = 0; i < SNP_CPUID_COUNT_MAX; i++) { + const struct snp_cpuid_fn *fn = &cpuid_table->fn[i]; + + pr_info("index=%3d fn=0x%08x subfn=0x%08x: eax=0x%08x ebx=0x%08x ecx=0x%08x edx=0x%08x xcr0_in=0x%016llx xss_in=0x%016llx reserved=0x%016llx\n", + i, fn->eax_in, fn->ecx_in, fn->eax, fn->ebx, fn->ecx, + fn->edx, fn->xcr0_in, fn->xss_in, fn->__reserved); + } +} + +/* + * It is useful from an auditing/testing perspective to provide an easy way + * for the guest owner to know that the CPUID table has been initialized as + * expected, but that initialization happens too early in boot to print any + * sort of indicator, and there's not really any other good place to do it, + * so do it here. + */ +static int __init report_cpuid_table(void) +{ + const struct snp_cpuid_table *cpuid_table = snp_cpuid_get_table(); + + if (!cpuid_table->count) + return 0; + + pr_info("Using SNP CPUID table, %d entries present.\n", + cpuid_table->count); + + if (sev_cfg.debug) + dump_cpuid_table(); + + return 0; +} +arch_initcall(report_cpuid_table); + +static int __init init_sev_config(char *str) +{ + char *s; + + while ((s = strsep(&str, ","))) { + if (!strcmp(s, "debug")) { + sev_cfg.debug = true; + continue; + } + + pr_info("SEV command-line option '%s' was not recognized\n", s); + } + + return 1; +} +__setup("sev=", init_sev_config); + +int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, unsigned long *fw_err) +{ + struct ghcb_state state; + struct es_em_ctxt ctxt; + unsigned long flags; + struct ghcb *ghcb; + int ret; + + if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) + return -ENODEV; + + if (!fw_err) + return -EINVAL; + + /* + * __sev_get_ghcb() needs to run with IRQs disabled because it is using + * a per-CPU GHCB. + */ + local_irq_save(flags); + + ghcb = __sev_get_ghcb(&state); + if (!ghcb) { + ret = -EIO; + goto e_restore_irq; + } + + vc_ghcb_invalidate(ghcb); + + if (exit_code == SVM_VMGEXIT_EXT_GUEST_REQUEST) { + ghcb_set_rax(ghcb, input->data_gpa); + ghcb_set_rbx(ghcb, input->data_npages); + } + + ret = sev_es_ghcb_hv_call(ghcb, true, &ctxt, exit_code, input->req_gpa, input->resp_gpa); + if (ret) + goto e_put; + + if (ghcb->save.sw_exit_info_2) { + /* Number of expected pages are returned in RBX */ + if (exit_code == SVM_VMGEXIT_EXT_GUEST_REQUEST && + ghcb->save.sw_exit_info_2 == SNP_GUEST_REQ_INVALID_LEN) + input->data_npages = ghcb_get_rbx(ghcb); + + *fw_err = ghcb->save.sw_exit_info_2; + + ret = -EIO; + } + +e_put: + __sev_put_ghcb(&state); +e_restore_irq: + local_irq_restore(flags); + + return ret; +} +EXPORT_SYMBOL_GPL(snp_issue_guest_request); + +static struct platform_device sev_guest_device = { + .name = "sev-guest", + .id = -1, +}; + +static int __init snp_init_platform_device(void) +{ + struct sev_guest_platform_data data; + u64 gpa; + + if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) + return -ENODEV; + + gpa = get_secrets_page(); + if (!gpa) + return -ENODEV; + + data.secrets_gpa = gpa; + if (platform_device_add_data(&sev_guest_device, &data, sizeof(data))) + return -ENODEV; + + if (platform_device_register(&sev_guest_device)) + return -ENODEV; + + pr_info("SNP guest platform device initialized.\n"); + return 0; } +device_initcall(snp_init_platform_device); diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index e439eb14325f..9c7265b524c7 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -93,7 +93,7 @@ static bool restore_sigcontext(struct pt_regs *regs, return false; #ifdef CONFIG_X86_32 - set_user_gs(regs, sc.gs); + loadsegment(gs, sc.gs); regs->fs = sc.fs; regs->es = sc.es; regs->ds = sc.ds; @@ -146,8 +146,10 @@ __unsafe_setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate, struct pt_regs *regs, unsigned long mask) { #ifdef CONFIG_X86_32 - unsafe_put_user(get_user_gs(regs), - (unsigned int __user *)&sc->gs, Efault); + unsigned int gs; + savesegment(gs, gs); + + unsafe_put_user(gs, (unsigned int __user *)&sc->gs, Efault); unsafe_put_user(regs->fs, (unsigned int __user *)&sc->fs, Efault); unsafe_put_user(regs->es, (unsigned int __user *)&sc->es, Efault); unsafe_put_user(regs->ds, (unsigned int __user *)&sc->ds, Efault); diff --git a/arch/x86/kernel/signal_compat.c b/arch/x86/kernel/signal_compat.c index b52407c56000..879ef8c72f5c 100644 --- a/arch/x86/kernel/signal_compat.c +++ b/arch/x86/kernel/signal_compat.c @@ -149,8 +149,10 @@ static inline void signal_compat_build_tests(void) BUILD_BUG_ON(offsetof(siginfo_t, si_perf_data) != 0x18); BUILD_BUG_ON(offsetof(siginfo_t, si_perf_type) != 0x20); + BUILD_BUG_ON(offsetof(siginfo_t, si_perf_flags) != 0x24); BUILD_BUG_ON(offsetof(compat_siginfo_t, si_perf_data) != 0x10); BUILD_BUG_ON(offsetof(compat_siginfo_t, si_perf_type) != 0x14); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_perf_flags) != 0x18); CHECK_CSI_OFFSET(_sigpoll); CHECK_CSI_SIZE (_sigpoll, 2*sizeof(int)); diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 2ef14772dc04..5e7f9532a10d 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -56,7 +56,6 @@ #include <linux/numa.h> #include <linux/pgtable.h> #include <linux/overflow.h> -#include <linux/syscore_ops.h> #include <asm/acpi.h> #include <asm/desc.h> @@ -82,6 +81,7 @@ #include <asm/spec-ctrl.h> #include <asm/hw_irq.h> #include <asm/stackprotector.h> +#include <asm/sev.h> /* representing HT siblings of each logical CPU */ DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_sibling_map); @@ -187,7 +187,7 @@ static void smp_callin(void) */ set_cpu_sibling_map(raw_smp_processor_id()); - init_freq_invariance(true, false); + ap_init_aperfmperf(); /* * Get our bogomips. @@ -1082,6 +1082,11 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle, unsigned long boot_error = 0; unsigned long timeout; +#ifdef CONFIG_X86_64 + /* If 64-bit wakeup method exists, use the 64-bit mode trampoline IP */ + if (apic->wakeup_secondary_cpu_64) + start_ip = real_mode_header->trampoline_start64; +#endif idle->thread.sp = (unsigned long)task_pt_regs(idle); early_gdt_descr.address = (unsigned long)get_cpu_gdt_rw(cpu); initial_code = (unsigned long)start_secondary; @@ -1123,11 +1128,14 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle, /* * Wake up a CPU in difference cases: - * - Use the method in the APIC driver if it's defined + * - Use a method from the APIC driver if one defined, with wakeup + * straight to 64-bit mode preferred over wakeup to RM. * Otherwise, * - Use an INIT boot APIC message for APs or NMI for BSP. */ - if (apic->wakeup_secondary_cpu) + if (apic->wakeup_secondary_cpu_64) + boot_error = apic->wakeup_secondary_cpu_64(apicid, start_ip); + else if (apic->wakeup_secondary_cpu) boot_error = apic->wakeup_secondary_cpu(apicid, start_ip); else boot_error = wakeup_cpu_via_init_nmi(cpu, start_ip, apicid, @@ -1397,7 +1405,6 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) { smp_prepare_cpus_common(); - init_freq_invariance(false, false); smp_sanity_check(); switch (apic_intr_mode) { @@ -1430,6 +1437,8 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) smp_quirk_init_udelay(); speculative_store_bypass_ht_init(); + + snp_set_wakeup_secondary_cpu(); } void arch_thaw_secondary_cpus_begin(void) @@ -1847,357 +1856,3 @@ void native_play_dead(void) } #endif - -#ifdef CONFIG_X86_64 -/* - * APERF/MPERF frequency ratio computation. - * - * The scheduler wants to do frequency invariant accounting and needs a <1 - * ratio to account for the 'current' frequency, corresponding to - * freq_curr / freq_max. - * - * Since the frequency freq_curr on x86 is controlled by micro-controller and - * our P-state setting is little more than a request/hint, we need to observe - * the effective frequency 'BusyMHz', i.e. the average frequency over a time - * interval after discarding idle time. This is given by: - * - * BusyMHz = delta_APERF / delta_MPERF * freq_base - * - * where freq_base is the max non-turbo P-state. - * - * The freq_max term has to be set to a somewhat arbitrary value, because we - * can't know which turbo states will be available at a given point in time: - * it all depends on the thermal headroom of the entire package. We set it to - * the turbo level with 4 cores active. - * - * Benchmarks show that's a good compromise between the 1C turbo ratio - * (freq_curr/freq_max would rarely reach 1) and something close to freq_base, - * which would ignore the entire turbo range (a conspicuous part, making - * freq_curr/freq_max always maxed out). - * - * An exception to the heuristic above is the Atom uarch, where we choose the - * highest turbo level for freq_max since Atom's are generally oriented towards - * power efficiency. - * - * Setting freq_max to anything less than the 1C turbo ratio makes the ratio - * freq_curr / freq_max to eventually grow >1, in which case we clip it to 1. - */ - -DEFINE_STATIC_KEY_FALSE(arch_scale_freq_key); - -static DEFINE_PER_CPU(u64, arch_prev_aperf); -static DEFINE_PER_CPU(u64, arch_prev_mperf); -static u64 arch_turbo_freq_ratio = SCHED_CAPACITY_SCALE; -static u64 arch_max_freq_ratio = SCHED_CAPACITY_SCALE; - -void arch_set_max_freq_ratio(bool turbo_disabled) -{ - arch_max_freq_ratio = turbo_disabled ? SCHED_CAPACITY_SCALE : - arch_turbo_freq_ratio; -} -EXPORT_SYMBOL_GPL(arch_set_max_freq_ratio); - -static bool turbo_disabled(void) -{ - u64 misc_en; - int err; - - err = rdmsrl_safe(MSR_IA32_MISC_ENABLE, &misc_en); - if (err) - return false; - - return (misc_en & MSR_IA32_MISC_ENABLE_TURBO_DISABLE); -} - -static bool slv_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq) -{ - int err; - - err = rdmsrl_safe(MSR_ATOM_CORE_RATIOS, base_freq); - if (err) - return false; - - err = rdmsrl_safe(MSR_ATOM_CORE_TURBO_RATIOS, turbo_freq); - if (err) - return false; - - *base_freq = (*base_freq >> 16) & 0x3F; /* max P state */ - *turbo_freq = *turbo_freq & 0x3F; /* 1C turbo */ - - return true; -} - -#define X86_MATCH(model) \ - X86_MATCH_VENDOR_FAM_MODEL_FEATURE(INTEL, 6, \ - INTEL_FAM6_##model, X86_FEATURE_APERFMPERF, NULL) - -static const struct x86_cpu_id has_knl_turbo_ratio_limits[] = { - X86_MATCH(XEON_PHI_KNL), - X86_MATCH(XEON_PHI_KNM), - {} -}; - -static const struct x86_cpu_id has_skx_turbo_ratio_limits[] = { - X86_MATCH(SKYLAKE_X), - {} -}; - -static const struct x86_cpu_id has_glm_turbo_ratio_limits[] = { - X86_MATCH(ATOM_GOLDMONT), - X86_MATCH(ATOM_GOLDMONT_D), - X86_MATCH(ATOM_GOLDMONT_PLUS), - {} -}; - -static bool knl_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq, - int num_delta_fratio) -{ - int fratio, delta_fratio, found; - int err, i; - u64 msr; - - err = rdmsrl_safe(MSR_PLATFORM_INFO, base_freq); - if (err) - return false; - - *base_freq = (*base_freq >> 8) & 0xFF; /* max P state */ - - err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT, &msr); - if (err) - return false; - - fratio = (msr >> 8) & 0xFF; - i = 16; - found = 0; - do { - if (found >= num_delta_fratio) { - *turbo_freq = fratio; - return true; - } - - delta_fratio = (msr >> (i + 5)) & 0x7; - - if (delta_fratio) { - found += 1; - fratio -= delta_fratio; - } - - i += 8; - } while (i < 64); - - return true; -} - -static bool skx_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq, int size) -{ - u64 ratios, counts; - u32 group_size; - int err, i; - - err = rdmsrl_safe(MSR_PLATFORM_INFO, base_freq); - if (err) - return false; - - *base_freq = (*base_freq >> 8) & 0xFF; /* max P state */ - - err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT, &ratios); - if (err) - return false; - - err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT1, &counts); - if (err) - return false; - - for (i = 0; i < 64; i += 8) { - group_size = (counts >> i) & 0xFF; - if (group_size >= size) { - *turbo_freq = (ratios >> i) & 0xFF; - return true; - } - } - - return false; -} - -static bool core_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq) -{ - u64 msr; - int err; - - err = rdmsrl_safe(MSR_PLATFORM_INFO, base_freq); - if (err) - return false; - - err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT, &msr); - if (err) - return false; - - *base_freq = (*base_freq >> 8) & 0xFF; /* max P state */ - *turbo_freq = (msr >> 24) & 0xFF; /* 4C turbo */ - - /* The CPU may have less than 4 cores */ - if (!*turbo_freq) - *turbo_freq = msr & 0xFF; /* 1C turbo */ - - return true; -} - -static bool intel_set_max_freq_ratio(void) -{ - u64 base_freq, turbo_freq; - u64 turbo_ratio; - - if (slv_set_max_freq_ratio(&base_freq, &turbo_freq)) - goto out; - - if (x86_match_cpu(has_glm_turbo_ratio_limits) && - skx_set_max_freq_ratio(&base_freq, &turbo_freq, 1)) - goto out; - - if (x86_match_cpu(has_knl_turbo_ratio_limits) && - knl_set_max_freq_ratio(&base_freq, &turbo_freq, 1)) - goto out; - - if (x86_match_cpu(has_skx_turbo_ratio_limits) && - skx_set_max_freq_ratio(&base_freq, &turbo_freq, 4)) - goto out; - - if (core_set_max_freq_ratio(&base_freq, &turbo_freq)) - goto out; - - return false; - -out: - /* - * Some hypervisors advertise X86_FEATURE_APERFMPERF - * but then fill all MSR's with zeroes. - * Some CPUs have turbo boost but don't declare any turbo ratio - * in MSR_TURBO_RATIO_LIMIT. - */ - if (!base_freq || !turbo_freq) { - pr_debug("Couldn't determine cpu base or turbo frequency, necessary for scale-invariant accounting.\n"); - return false; - } - - turbo_ratio = div_u64(turbo_freq * SCHED_CAPACITY_SCALE, base_freq); - if (!turbo_ratio) { - pr_debug("Non-zero turbo and base frequencies led to a 0 ratio.\n"); - return false; - } - - arch_turbo_freq_ratio = turbo_ratio; - arch_set_max_freq_ratio(turbo_disabled()); - - return true; -} - -static void init_counter_refs(void) -{ - u64 aperf, mperf; - - rdmsrl(MSR_IA32_APERF, aperf); - rdmsrl(MSR_IA32_MPERF, mperf); - - this_cpu_write(arch_prev_aperf, aperf); - this_cpu_write(arch_prev_mperf, mperf); -} - -#ifdef CONFIG_PM_SLEEP -static struct syscore_ops freq_invariance_syscore_ops = { - .resume = init_counter_refs, -}; - -static void register_freq_invariance_syscore_ops(void) -{ - /* Bail out if registered already. */ - if (freq_invariance_syscore_ops.node.prev) - return; - - register_syscore_ops(&freq_invariance_syscore_ops); -} -#else -static inline void register_freq_invariance_syscore_ops(void) {} -#endif - -void init_freq_invariance(bool secondary, bool cppc_ready) -{ - bool ret = false; - - if (!boot_cpu_has(X86_FEATURE_APERFMPERF)) - return; - - if (secondary) { - if (static_branch_likely(&arch_scale_freq_key)) { - init_counter_refs(); - } - return; - } - - if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) - ret = intel_set_max_freq_ratio(); - else if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) { - if (!cppc_ready) { - return; - } - ret = amd_set_max_freq_ratio(&arch_turbo_freq_ratio); - } - - if (ret) { - init_counter_refs(); - static_branch_enable(&arch_scale_freq_key); - register_freq_invariance_syscore_ops(); - pr_info("Estimated ratio of average max frequency by base frequency (times 1024): %llu\n", arch_max_freq_ratio); - } else { - pr_debug("Couldn't determine max cpu frequency, necessary for scale-invariant accounting.\n"); - } -} - -static void disable_freq_invariance_workfn(struct work_struct *work) -{ - static_branch_disable(&arch_scale_freq_key); -} - -static DECLARE_WORK(disable_freq_invariance_work, - disable_freq_invariance_workfn); - -DEFINE_PER_CPU(unsigned long, arch_freq_scale) = SCHED_CAPACITY_SCALE; - -void arch_scale_freq_tick(void) -{ - u64 freq_scale; - u64 aperf, mperf; - u64 acnt, mcnt; - - if (!arch_scale_freq_invariant()) - return; - - rdmsrl(MSR_IA32_APERF, aperf); - rdmsrl(MSR_IA32_MPERF, mperf); - - acnt = aperf - this_cpu_read(arch_prev_aperf); - mcnt = mperf - this_cpu_read(arch_prev_mperf); - - this_cpu_write(arch_prev_aperf, aperf); - this_cpu_write(arch_prev_mperf, mperf); - - if (check_shl_overflow(acnt, 2*SCHED_CAPACITY_SHIFT, &acnt)) - goto error; - - if (check_mul_overflow(mcnt, arch_max_freq_ratio, &mcnt) || !mcnt) - goto error; - - freq_scale = div64_u64(acnt, mcnt); - if (!freq_scale) - goto error; - - if (freq_scale > SCHED_CAPACITY_SCALE) - freq_scale = SCHED_CAPACITY_SCALE; - - this_cpu_write(arch_freq_scale, freq_scale); - return; - -error: - pr_warn("Scheduler frequency invariance went wobbly, disabling!\n"); - schedule_work(&disable_freq_invariance_work); -} -#endif /* CONFIG_X86_64 */ diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c index 531fb4cbb63f..aa72cefdd5be 100644 --- a/arch/x86/kernel/static_call.c +++ b/arch/x86/kernel/static_call.c @@ -12,10 +12,9 @@ enum insn_type { }; /* - * data16 data16 xorq %rax, %rax - a single 5 byte instruction that clears %rax - * The REX.W cancels the effect of any data16. + * cs cs cs xorl %eax, %eax - a single 5 byte instruction that clears %[er]ax */ -static const u8 xor5rax[] = { 0x66, 0x66, 0x48, 0x31, 0xc0 }; +static const u8 xor5rax[] = { 0x2e, 0x2e, 0x2e, 0x31, 0xc0 }; static const u8 retinsn[] = { RET_INSN_OPCODE, 0xcc, 0xcc, 0xcc, 0xcc }; diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c index 660b78827638..8cc653ffdccd 100644 --- a/arch/x86/kernel/sys_x86_64.c +++ b/arch/x86/kernel/sys_x86_64.c @@ -68,9 +68,6 @@ static int __init control_va_addr_alignment(char *str) if (*str == 0) return 1; - if (*str == '=') - str++; - if (!strcmp(str, "32")) va_align.flags = ALIGN_VA_32; else if (!strcmp(str, "64")) @@ -80,11 +77,11 @@ static int __init control_va_addr_alignment(char *str) else if (!strcmp(str, "on")) va_align.flags = ALIGN_VA_32 | ALIGN_VA_64; else - return 0; + pr_warn("invalid option value: 'align_va_addr=%s'\n", str); return 1; } -__setup("align_va_addr", control_va_addr_alignment); +__setup("align_va_addr=", control_va_addr_alignment); SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len, unsigned long, prot, unsigned long, flags, diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 1563fb995005..d62b2cb85cea 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -62,6 +62,7 @@ #include <asm/insn.h> #include <asm/insn-eval.h> #include <asm/vdso.h> +#include <asm/tdx.h> #ifdef CONFIG_X86_64 #include <asm/x86_init.h> @@ -686,13 +687,40 @@ static bool try_fixup_enqcmd_gp(void) #endif } +static bool gp_try_fixup_and_notify(struct pt_regs *regs, int trapnr, + unsigned long error_code, const char *str) +{ + if (fixup_exception(regs, trapnr, error_code, 0)) + return true; + + current->thread.error_code = error_code; + current->thread.trap_nr = trapnr; + + /* + * To be potentially processing a kprobe fault and to trust the result + * from kprobe_running(), we have to be non-preemptible. + */ + if (!preemptible() && kprobe_running() && + kprobe_fault_handler(regs, trapnr)) + return true; + + return notify_die(DIE_GPF, str, regs, error_code, trapnr, SIGSEGV) == NOTIFY_STOP; +} + +static void gp_user_force_sig_segv(struct pt_regs *regs, int trapnr, + unsigned long error_code, const char *str) +{ + current->thread.error_code = error_code; + current->thread.trap_nr = trapnr; + show_signal(current, SIGSEGV, "", str, regs, error_code); + force_sig(SIGSEGV); +} + DEFINE_IDTENTRY_ERRORCODE(exc_general_protection) { char desc[sizeof(GPFSTR) + 50 + 2*sizeof(unsigned long) + 1] = GPFSTR; enum kernel_gp_hint hint = GP_NO_HINT; - struct task_struct *tsk; unsigned long gp_addr; - int ret; if (user_mode(regs) && try_fixup_enqcmd_gp()) return; @@ -711,40 +739,18 @@ DEFINE_IDTENTRY_ERRORCODE(exc_general_protection) return; } - tsk = current; - if (user_mode(regs)) { if (fixup_iopl_exception(regs)) goto exit; - tsk->thread.error_code = error_code; - tsk->thread.trap_nr = X86_TRAP_GP; - if (fixup_vdso_exception(regs, X86_TRAP_GP, error_code, 0)) goto exit; - show_signal(tsk, SIGSEGV, "", desc, regs, error_code); - force_sig(SIGSEGV); + gp_user_force_sig_segv(regs, X86_TRAP_GP, error_code, desc); goto exit; } - if (fixup_exception(regs, X86_TRAP_GP, error_code, 0)) - goto exit; - - tsk->thread.error_code = error_code; - tsk->thread.trap_nr = X86_TRAP_GP; - - /* - * To be potentially processing a kprobe fault and to trust the result - * from kprobe_running(), we have to be non-preemptible. - */ - if (!preemptible() && - kprobe_running() && - kprobe_fault_handler(regs, X86_TRAP_GP)) - goto exit; - - ret = notify_die(DIE_GPF, desc, regs, error_code, X86_TRAP_GP, SIGSEGV); - if (ret == NOTIFY_STOP) + if (gp_try_fixup_and_notify(regs, X86_TRAP_GP, error_code, desc)) goto exit; if (error_code) @@ -892,14 +898,10 @@ sync: } #endif -struct bad_iret_stack { - void *error_entry_ret; - struct pt_regs regs; -}; - -asmlinkage __visible noinstr -struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s) +asmlinkage __visible noinstr struct pt_regs *fixup_bad_iret(struct pt_regs *bad_regs) { + struct pt_regs tmp, *new_stack; + /* * This is called from entry_64.S early in handling a fault * caused by a bad iret to user mode. To handle the fault @@ -908,19 +910,18 @@ struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s) * just below the IRET frame) and we want to pretend that the * exception came from the IRET target. */ - struct bad_iret_stack tmp, *new_stack = - (struct bad_iret_stack *)__this_cpu_read(cpu_tss_rw.x86_tss.sp0) - 1; + new_stack = (struct pt_regs *)__this_cpu_read(cpu_tss_rw.x86_tss.sp0) - 1; /* Copy the IRET target to the temporary storage. */ - __memcpy(&tmp.regs.ip, (void *)s->regs.sp, 5*8); + __memcpy(&tmp.ip, (void *)bad_regs->sp, 5*8); /* Copy the remainder of the stack from the current stack. */ - __memcpy(&tmp, s, offsetof(struct bad_iret_stack, regs.ip)); + __memcpy(&tmp, bad_regs, offsetof(struct pt_regs, ip)); /* Update the entry stack */ __memcpy(new_stack, &tmp, sizeof(tmp)); - BUG_ON(!user_mode(&new_stack->regs)); + BUG_ON(!user_mode(new_stack)); return new_stack; } #endif @@ -1343,6 +1344,91 @@ DEFINE_IDTENTRY(exc_device_not_available) } } +#ifdef CONFIG_INTEL_TDX_GUEST + +#define VE_FAULT_STR "VE fault" + +static void ve_raise_fault(struct pt_regs *regs, long error_code) +{ + if (user_mode(regs)) { + gp_user_force_sig_segv(regs, X86_TRAP_VE, error_code, VE_FAULT_STR); + return; + } + + if (gp_try_fixup_and_notify(regs, X86_TRAP_VE, error_code, VE_FAULT_STR)) + return; + + die_addr(VE_FAULT_STR, regs, error_code, 0); +} + +/* + * Virtualization Exceptions (#VE) are delivered to TDX guests due to + * specific guest actions which may happen in either user space or the + * kernel: + * + * * Specific instructions (WBINVD, for example) + * * Specific MSR accesses + * * Specific CPUID leaf accesses + * * Access to specific guest physical addresses + * + * In the settings that Linux will run in, virtualization exceptions are + * never generated on accesses to normal, TD-private memory that has been + * accepted (by BIOS or with tdx_enc_status_changed()). + * + * Syscall entry code has a critical window where the kernel stack is not + * yet set up. Any exception in this window leads to hard to debug issues + * and can be exploited for privilege escalation. Exceptions in the NMI + * entry code also cause issues. Returning from the exception handler with + * IRET will re-enable NMIs and nested NMI will corrupt the NMI stack. + * + * For these reasons, the kernel avoids #VEs during the syscall gap and + * the NMI entry code. Entry code paths do not access TD-shared memory, + * MMIO regions, use #VE triggering MSRs, instructions, or CPUID leaves + * that might generate #VE. VMM can remove memory from TD at any point, + * but access to unaccepted (or missing) private memory leads to VM + * termination, not to #VE. + * + * Similarly to page faults and breakpoints, #VEs are allowed in NMI + * handlers once the kernel is ready to deal with nested NMIs. + * + * During #VE delivery, all interrupts, including NMIs, are blocked until + * TDGETVEINFO is called. It prevents #VE nesting until the kernel reads + * the VE info. + * + * If a guest kernel action which would normally cause a #VE occurs in + * the interrupt-disabled region before TDGETVEINFO, a #DF (fault + * exception) is delivered to the guest which will result in an oops. + * + * The entry code has been audited carefully for following these expectations. + * Changes in the entry code have to be audited for correctness vs. this + * aspect. Similarly to #PF, #VE in these places will expose kernel to + * privilege escalation or may lead to random crashes. + */ +DEFINE_IDTENTRY(exc_virtualization_exception) +{ + struct ve_info ve; + + /* + * NMIs/Machine-checks/Interrupts will be in a disabled state + * till TDGETVEINFO TDCALL is executed. This ensures that VE + * info cannot be overwritten by a nested #VE. + */ + tdx_get_ve_info(&ve); + + cond_local_irq_enable(regs); + + /* + * If tdx_handle_virt_exception() could not process + * it successfully, treat it as #GP(0) and handle it. + */ + if (!tdx_handle_virt_exception(regs, &ve)) + ve_raise_fault(regs, 0); + + cond_local_irq_disable(regs); +} + +#endif + #ifdef CONFIG_X86_32 DEFINE_IDTENTRY_SW(iret_error) { diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index 794fdef2501a..38185aedf7d1 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -339,11 +339,11 @@ static bool stack_access_ok(struct unwind_state *state, unsigned long _addr, struct stack_info *info = &state->stack_info; void *addr = (void *)_addr; - if (!on_stack(info, addr, len) && - (get_stack_info(addr, state->task, info, &state->stack_mask))) - return false; + if (on_stack(info, addr, len)) + return true; - return true; + return !get_stack_info(addr, state->task, info, &state->stack_mask) && + on_stack(info, addr, len); } static bool deref_stack_reg(struct unwind_state *state, unsigned long addr, diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index c21bcd668284..e9e803a4d44c 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -151,7 +151,7 @@ exit_vm86: memcpy(®s->pt, &vm86->regs32, sizeof(struct pt_regs)); - lazy_load_gs(vm86->regs32.gs); + loadsegment(gs, vm86->regs32.gs); regs->pt.ax = retval; return; @@ -325,7 +325,7 @@ static long do_sys_vm86(struct vm86plus_struct __user *user_vm86, bool plus) * Save old state */ vm86->saved_sp0 = tsk->thread.sp0; - lazy_save_gs(vm86->regs32.gs); + savesegment(gs, vm86->regs32.gs); /* make room for real-mode segments */ preempt_disable(); diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index b24ca7f4ed7c..de6d44e07e34 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -19,6 +19,7 @@ #include <asm/user.h> #include <asm/fpu/xstate.h> #include <asm/sgx.h> +#include <asm/cpuid.h> #include "cpuid.h" #include "lapic.h" #include "mmu.h" @@ -744,24 +745,8 @@ static struct kvm_cpuid_entry2 *do_host_cpuid(struct kvm_cpuid_array *array, cpuid_count(entry->function, entry->index, &entry->eax, &entry->ebx, &entry->ecx, &entry->edx); - switch (function) { - case 4: - case 7: - case 0xb: - case 0xd: - case 0xf: - case 0x10: - case 0x12: - case 0x14: - case 0x17: - case 0x18: - case 0x1d: - case 0x1e: - case 0x1f: - case 0x8000001d: + if (cpuid_function_is_indexed(function)) entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; - break; - } return entry; } @@ -887,6 +872,11 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) union cpuid10_eax eax; union cpuid10_edx edx; + if (!static_cpu_has(X86_FEATURE_ARCH_PERFMON)) { + entry->eax = entry->ebx = entry->ecx = entry->edx = 0; + break; + } + perf_get_x86_pmu_capability(&cap); /* @@ -1085,12 +1075,21 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) case 0x80000000: entry->eax = min(entry->eax, 0x80000021); /* - * Serializing LFENCE is reported in a multitude of ways, - * and NullSegClearsBase is not reported in CPUID on Zen2; - * help userspace by providing the CPUID leaf ourselves. + * Serializing LFENCE is reported in a multitude of ways, and + * NullSegClearsBase is not reported in CPUID on Zen2; help + * userspace by providing the CPUID leaf ourselves. + * + * However, only do it if the host has CPUID leaf 0x8000001d. + * QEMU thinks that it can query the host blindly for that + * CPUID leaf if KVM reports that it supports 0x8000001d or + * above. The processor merrily returns values from the + * highest Intel leaf which QEMU tries to use as the guest's + * 0x8000001d. Even worse, this can result in an infinite + * loop if said highest leaf has no subleaves indexed by ECX. */ - if (static_cpu_has(X86_FEATURE_LFENCE_RDTSC) - || !static_cpu_has_bug(X86_BUG_NULL_SEG)) + if (entry->eax >= 0x8000001d && + (static_cpu_has(X86_FEATURE_LFENCE_RDTSC) + || !static_cpu_has_bug(X86_BUG_NULL_SEG))) entry->eax = max(entry->eax, 0x80000021); break; case 0x80000001: diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 123b677111c5..a0702b6be3e8 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -1135,11 +1135,13 @@ void kvm_hv_setup_tsc_page(struct kvm *kvm, BUILD_BUG_ON(sizeof(tsc_seq) != sizeof(hv->tsc_ref.tsc_sequence)); BUILD_BUG_ON(offsetof(struct ms_hyperv_tsc_page, tsc_sequence) != 0); + mutex_lock(&hv->hv_lock); + if (hv->hv_tsc_page_status == HV_TSC_PAGE_BROKEN || + hv->hv_tsc_page_status == HV_TSC_PAGE_SET || hv->hv_tsc_page_status == HV_TSC_PAGE_UNSET) - return; + goto out_unlock; - mutex_lock(&hv->hv_lock); if (!(hv->hv_tsc_page & HV_X64_MSR_TSC_REFERENCE_ENABLE)) goto out_unlock; @@ -1201,45 +1203,19 @@ out_unlock: mutex_unlock(&hv->hv_lock); } -void kvm_hv_invalidate_tsc_page(struct kvm *kvm) +void kvm_hv_request_tsc_page_update(struct kvm *kvm) { struct kvm_hv *hv = to_kvm_hv(kvm); - u64 gfn; - int idx; - - if (hv->hv_tsc_page_status == HV_TSC_PAGE_BROKEN || - hv->hv_tsc_page_status == HV_TSC_PAGE_UNSET || - tsc_page_update_unsafe(hv)) - return; mutex_lock(&hv->hv_lock); - if (!(hv->hv_tsc_page & HV_X64_MSR_TSC_REFERENCE_ENABLE)) - goto out_unlock; - - /* Preserve HV_TSC_PAGE_GUEST_CHANGED/HV_TSC_PAGE_HOST_CHANGED states */ - if (hv->hv_tsc_page_status == HV_TSC_PAGE_SET) - hv->hv_tsc_page_status = HV_TSC_PAGE_UPDATING; + if (hv->hv_tsc_page_status == HV_TSC_PAGE_SET && + !tsc_page_update_unsafe(hv)) + hv->hv_tsc_page_status = HV_TSC_PAGE_HOST_CHANGED; - gfn = hv->hv_tsc_page >> HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT; - - hv->tsc_ref.tsc_sequence = 0; - - /* - * Take the srcu lock as memslots will be accessed to check the gfn - * cache generation against the memslots generation. - */ - idx = srcu_read_lock(&kvm->srcu); - if (kvm_write_guest(kvm, gfn_to_gpa(gfn), - &hv->tsc_ref, sizeof(hv->tsc_ref.tsc_sequence))) - hv->hv_tsc_page_status = HV_TSC_PAGE_BROKEN; - srcu_read_unlock(&kvm->srcu, idx); - -out_unlock: mutex_unlock(&hv->hv_lock); } - static bool hv_check_msr_access(struct kvm_vcpu_hv *hv_vcpu, u32 msr) { if (!hv_vcpu->enforce_cpuid) @@ -1938,7 +1914,7 @@ static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc) struct hv_send_ipi_ex send_ipi_ex; struct hv_send_ipi send_ipi; DECLARE_BITMAP(vcpu_mask, KVM_MAX_VCPUS); - unsigned long valid_bank_mask; + u64 valid_bank_mask; u64 sparse_banks[KVM_HV_MAX_SPARSE_VCPU_SET_BITS]; u32 vector; bool all_cpus; @@ -1980,7 +1956,7 @@ static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc) valid_bank_mask = send_ipi_ex.vp_set.valid_bank_mask; all_cpus = send_ipi_ex.vp_set.format == HV_GENERIC_SET_ALL; - if (hc->var_cnt != bitmap_weight(&valid_bank_mask, 64)) + if (hc->var_cnt != bitmap_weight((unsigned long *)&valid_bank_mask, 64)) return HV_STATUS_INVALID_HYPERCALL_INPUT; if (all_cpus) diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h index e19c00ee9ab3..da2737f2a956 100644 --- a/arch/x86/kvm/hyperv.h +++ b/arch/x86/kvm/hyperv.h @@ -137,7 +137,7 @@ void kvm_hv_process_stimers(struct kvm_vcpu *vcpu); void kvm_hv_setup_tsc_page(struct kvm *kvm, struct pvclock_vcpu_time_info *hv_clock); -void kvm_hv_invalidate_tsc_page(struct kvm *kvm); +void kvm_hv_request_tsc_page_update(struct kvm *kvm); void kvm_hv_init_vm(struct kvm *kvm); void kvm_hv_destroy_vm(struct kvm *kvm); diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index e6cae6f22683..a335e7f1f69e 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -65,6 +65,30 @@ static __always_inline u64 rsvd_bits(int s, int e) return ((2ULL << (e - s)) - 1) << s; } +/* + * The number of non-reserved physical address bits irrespective of features + * that repurpose legal bits, e.g. MKTME. + */ +extern u8 __read_mostly shadow_phys_bits; + +static inline gfn_t kvm_mmu_max_gfn(void) +{ + /* + * Note that this uses the host MAXPHYADDR, not the guest's. + * EPT/NPT cannot support GPAs that would exceed host.MAXPHYADDR; + * assuming KVM is running on bare metal, guest accesses beyond + * host.MAXPHYADDR will hit a #PF(RSVD) and never cause a vmexit + * (either EPT Violation/Misconfig or #NPF), and so KVM will never + * install a SPTE for such addresses. If KVM is running as a VM + * itself, on the other hand, it might see a MAXPHYADDR that is less + * than hardware's real MAXPHYADDR. Using the host MAXPHYADDR + * disallows such SPTEs entirely and simplifies the TDP MMU. + */ + int max_gpa_bits = likely(tdp_enabled) ? shadow_phys_bits : 52; + + return (1ULL << (max_gpa_bits - PAGE_SHIFT)) - 1; +} + void kvm_mmu_set_mmio_spte_mask(u64 mmio_value, u64 mmio_mask, u64 access_mask); void kvm_mmu_set_ept_masks(bool has_ad_bits, bool has_exec_only); diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 8f19ea752704..45e1573f8f1d 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -473,30 +473,6 @@ retry: } #endif -static bool spte_has_volatile_bits(u64 spte) -{ - if (!is_shadow_present_pte(spte)) - return false; - - /* - * Always atomically update spte if it can be updated - * out of mmu-lock, it can ensure dirty bit is not lost, - * also, it can help us to get a stable is_writable_pte() - * to ensure tlb flush is not missed. - */ - if (spte_can_locklessly_be_made_writable(spte) || - is_access_track_spte(spte)) - return true; - - if (spte_ad_enabled(spte)) { - if ((spte & shadow_accessed_mask) == 0 || - (is_writable_pte(spte) && (spte & shadow_dirty_mask) == 0)) - return true; - } - - return false; -} - /* Rules for using mmu_spte_set: * Set the sptep from nonpresent to present. * Note: the sptep being assigned *must* be either not present @@ -557,7 +533,7 @@ static bool mmu_spte_update(u64 *sptep, u64 new_spte) * we always atomically update it, see the comments in * spte_has_volatile_bits(). */ - if (spte_can_locklessly_be_made_writable(old_spte) && + if (is_mmu_writable_spte(old_spte) && !is_writable_pte(new_spte)) flush = true; @@ -591,7 +567,8 @@ static int mmu_spte_clear_track_bits(struct kvm *kvm, u64 *sptep) u64 old_spte = *sptep; int level = sptep_to_sp(sptep)->role.level; - if (!spte_has_volatile_bits(old_spte)) + if (!is_shadow_present_pte(old_spte) || + !spte_has_volatile_bits(old_spte)) __update_clear_spte_fast(sptep, 0ull); else old_spte = __update_clear_spte_slow(sptep, 0ull); @@ -1187,7 +1164,7 @@ static bool spte_write_protect(u64 *sptep, bool pt_protect) u64 spte = *sptep; if (!is_writable_pte(spte) && - !(pt_protect && spte_can_locklessly_be_made_writable(spte))) + !(pt_protect && is_mmu_writable_spte(spte))) return false; rmap_printk("spte %p %llx\n", sptep, *sptep); @@ -2804,8 +2781,12 @@ static int host_pfn_mapping_level(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, const struct kvm_memory_slot *slot) { unsigned long hva; - pte_t *pte; - int level; + unsigned long flags; + int level = PG_LEVEL_4K; + pgd_t pgd; + p4d_t p4d; + pud_t pud; + pmd_t pmd; if (!PageCompound(pfn_to_page(pfn)) && !kvm_is_zone_device_pfn(pfn)) return PG_LEVEL_4K; @@ -2820,10 +2801,43 @@ static int host_pfn_mapping_level(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, */ hva = __gfn_to_hva_memslot(slot, gfn); - pte = lookup_address_in_mm(kvm->mm, hva, &level); - if (unlikely(!pte)) - return PG_LEVEL_4K; + /* + * Lookup the mapping level in the current mm. The information + * may become stale soon, but it is safe to use as long as + * 1) mmu_notifier_retry was checked after taking mmu_lock, and + * 2) mmu_lock is taken now. + * + * We still need to disable IRQs to prevent concurrent tear down + * of page tables. + */ + local_irq_save(flags); + + pgd = READ_ONCE(*pgd_offset(kvm->mm, hva)); + if (pgd_none(pgd)) + goto out; + p4d = READ_ONCE(*p4d_offset(&pgd, hva)); + if (p4d_none(p4d) || !p4d_present(p4d)) + goto out; + + pud = READ_ONCE(*pud_offset(&p4d, hva)); + if (pud_none(pud) || !pud_present(pud)) + goto out; + + if (pud_large(pud)) { + level = PG_LEVEL_1G; + goto out; + } + + pmd = READ_ONCE(*pmd_offset(&pud, hva)); + if (pmd_none(pmd) || !pmd_present(pmd)) + goto out; + + if (pmd_large(pmd)) + level = PG_LEVEL_2M; + +out: + local_irq_restore(flags); return level; } @@ -2992,9 +3006,15 @@ static bool handle_abnormal_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fa /* * If MMIO caching is disabled, emulate immediately without * touching the shadow page tables as attempting to install an - * MMIO SPTE will just be an expensive nop. + * MMIO SPTE will just be an expensive nop. Do not cache MMIO + * whose gfn is greater than host.MAXPHYADDR, any guest that + * generates such gfns is running nested and is being tricked + * by L0 userspace (you can observe gfn > L1.MAXPHYADDR if + * and only if L1's MAXPHYADDR is inaccurate with respect to + * the hardware's). */ - if (unlikely(!shadow_mmio_value)) { + if (unlikely(!shadow_mmio_value) || + unlikely(fault->gfn > kvm_mmu_max_gfn())) { *ret_val = RET_PF_EMULATE; return true; } @@ -3153,8 +3173,7 @@ static int fast_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) * be removed in the fast path only if the SPTE was * write-protected for dirty-logging or access tracking. */ - if (fault->write && - spte_can_locklessly_be_made_writable(spte)) { + if (fault->write && is_mmu_writable_spte(spte)) { new_spte |= PT_WRITABLE_MASK; /* @@ -5451,14 +5470,16 @@ void kvm_mmu_invpcid_gva(struct kvm_vcpu *vcpu, gva_t gva, unsigned long pcid) uint i; if (pcid == kvm_get_active_pcid(vcpu)) { - mmu->invlpg(vcpu, gva, mmu->root.hpa); + if (mmu->invlpg) + mmu->invlpg(vcpu, gva, mmu->root.hpa); tlb_flush = true; } for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) { if (VALID_PAGE(mmu->prev_roots[i].hpa) && pcid == kvm_get_pcid(vcpu, mmu->prev_roots[i].pgd)) { - mmu->invlpg(vcpu, gva, mmu->prev_roots[i].hpa); + if (mmu->invlpg) + mmu->invlpg(vcpu, gva, mmu->prev_roots[i].hpa); tlb_flush = true; } } @@ -5646,6 +5667,7 @@ static void kvm_zap_obsolete_pages(struct kvm *kvm) { struct kvm_mmu_page *sp, *node; int nr_zapped, batch = 0; + bool unstable; restart: list_for_each_entry_safe_reverse(sp, node, @@ -5677,11 +5699,12 @@ restart: goto restart; } - if (__kvm_mmu_prepare_zap_page(kvm, sp, - &kvm->arch.zapped_obsolete_pages, &nr_zapped)) { - batch += nr_zapped; + unstable = __kvm_mmu_prepare_zap_page(kvm, sp, + &kvm->arch.zapped_obsolete_pages, &nr_zapped); + batch += nr_zapped; + + if (unstable) goto restart; - } } /* @@ -6237,12 +6260,24 @@ static int set_nx_huge_pages(const char *val, const struct kernel_param *kp) return 0; } -int kvm_mmu_module_init(void) +/* + * nx_huge_pages needs to be resolved to true/false when kvm.ko is loaded, as + * its default value of -1 is technically undefined behavior for a boolean. + */ +void kvm_mmu_x86_module_init(void) { - int ret = -ENOMEM; - if (nx_huge_pages == -1) __set_nx_huge_pages(get_nx_auto_mode()); +} + +/* + * The bulk of the MMU initialization is deferred until the vendor module is + * loaded as many of the masks/values may be modified by VMX or SVM, i.e. need + * to be reset when a potentially different vendor module is loaded. + */ +int kvm_mmu_vendor_module_init(void) +{ + int ret = -ENOMEM; /* * MMU roles use union aliasing which is, generally speaking, an @@ -6290,7 +6325,7 @@ void kvm_mmu_destroy(struct kvm_vcpu *vcpu) mmu_free_memory_caches(vcpu); } -void kvm_mmu_module_exit(void) +void kvm_mmu_vendor_module_exit(void) { mmu_destroy_caches(); percpu_counter_destroy(&kvm_total_used_mmu_pages); diff --git a/arch/x86/kvm/mmu/spte.c b/arch/x86/kvm/mmu/spte.c index 4739b53c9734..e5c0b6db6f2c 100644 --- a/arch/x86/kvm/mmu/spte.c +++ b/arch/x86/kvm/mmu/spte.c @@ -90,6 +90,34 @@ static bool kvm_is_mmio_pfn(kvm_pfn_t pfn) E820_TYPE_RAM); } +/* + * Returns true if the SPTE has bits that may be set without holding mmu_lock. + * The caller is responsible for checking if the SPTE is shadow-present, and + * for determining whether or not the caller cares about non-leaf SPTEs. + */ +bool spte_has_volatile_bits(u64 spte) +{ + /* + * Always atomically update spte if it can be updated + * out of mmu-lock, it can ensure dirty bit is not lost, + * also, it can help us to get a stable is_writable_pte() + * to ensure tlb flush is not missed. + */ + if (!is_writable_pte(spte) && is_mmu_writable_spte(spte)) + return true; + + if (is_access_track_spte(spte)) + return true; + + if (spte_ad_enabled(spte)) { + if (!(spte & shadow_accessed_mask) || + (is_writable_pte(spte) && !(spte & shadow_dirty_mask))) + return true; + } + + return false; +} + bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, const struct kvm_memory_slot *slot, unsigned int pte_access, gfn_t gfn, kvm_pfn_t pfn, diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h index 73f12615416f..80ab0f5cff01 100644 --- a/arch/x86/kvm/mmu/spte.h +++ b/arch/x86/kvm/mmu/spte.h @@ -201,12 +201,6 @@ static inline bool is_removed_spte(u64 spte) */ extern u64 __read_mostly shadow_nonpresent_or_rsvd_lower_gfn_mask; -/* - * The number of non-reserved physical address bits irrespective of features - * that repurpose legal bits, e.g. MKTME. - */ -extern u8 __read_mostly shadow_phys_bits; - static inline bool is_mmio_spte(u64 spte) { return (spte & shadow_mmio_mask) == shadow_mmio_value && @@ -396,7 +390,7 @@ static inline void check_spte_writable_invariants(u64 spte) "kvm: Writable SPTE is not MMU-writable: %llx", spte); } -static inline bool spte_can_locklessly_be_made_writable(u64 spte) +static inline bool is_mmu_writable_spte(u64 spte) { return spte & shadow_mmu_writable_mask; } @@ -410,6 +404,8 @@ static inline u64 get_mmio_spte_generation(u64 spte) return gen; } +bool spte_has_volatile_bits(u64 spte); + bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, const struct kvm_memory_slot *slot, unsigned int pte_access, gfn_t gfn, kvm_pfn_t pfn, diff --git a/arch/x86/kvm/mmu/tdp_iter.h b/arch/x86/kvm/mmu/tdp_iter.h index b1eaf6ec0e0b..f0af385c56e0 100644 --- a/arch/x86/kvm/mmu/tdp_iter.h +++ b/arch/x86/kvm/mmu/tdp_iter.h @@ -6,6 +6,7 @@ #include <linux/kvm_host.h> #include "mmu.h" +#include "spte.h" /* * TDP MMU SPTEs are RCU protected to allow paging structures (non-leaf SPTEs) @@ -17,9 +18,38 @@ static inline u64 kvm_tdp_mmu_read_spte(tdp_ptep_t sptep) { return READ_ONCE(*rcu_dereference(sptep)); } -static inline void kvm_tdp_mmu_write_spte(tdp_ptep_t sptep, u64 val) + +static inline u64 kvm_tdp_mmu_write_spte_atomic(tdp_ptep_t sptep, u64 new_spte) +{ + return xchg(rcu_dereference(sptep), new_spte); +} + +static inline void __kvm_tdp_mmu_write_spte(tdp_ptep_t sptep, u64 new_spte) +{ + WRITE_ONCE(*rcu_dereference(sptep), new_spte); +} + +static inline u64 kvm_tdp_mmu_write_spte(tdp_ptep_t sptep, u64 old_spte, + u64 new_spte, int level) { - WRITE_ONCE(*rcu_dereference(sptep), val); + /* + * Atomically write the SPTE if it is a shadow-present, leaf SPTE with + * volatile bits, i.e. has bits that can be set outside of mmu_lock. + * The Writable bit can be set by KVM's fast page fault handler, and + * Accessed and Dirty bits can be set by the CPU. + * + * Note, non-leaf SPTEs do have Accessed bits and those bits are + * technically volatile, but KVM doesn't consume the Accessed bit of + * non-leaf SPTEs, i.e. KVM doesn't care if it clobbers the bit. This + * logic needs to be reassessed if KVM were to use non-leaf Accessed + * bits, e.g. to skip stepping down into child SPTEs when aging SPTEs. + */ + if (is_shadow_present_pte(old_spte) && is_last_spte(old_spte, level) && + spte_has_volatile_bits(old_spte)) + return kvm_tdp_mmu_write_spte_atomic(sptep, new_spte); + + __kvm_tdp_mmu_write_spte(sptep, new_spte); + return old_spte; } /* diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index d71d177ae6b8..922b06bf4b94 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -51,7 +51,7 @@ void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm) if (!kvm->arch.tdp_mmu_enabled) return; - flush_workqueue(kvm->arch.tdp_mmu_zap_wq); + /* Also waits for any queued work items. */ destroy_workqueue(kvm->arch.tdp_mmu_zap_wq); WARN_ON(!list_empty(&kvm->arch.tdp_mmu_pages)); @@ -426,9 +426,9 @@ static void handle_removed_pt(struct kvm *kvm, tdp_ptep_t pt, bool shared) tdp_mmu_unlink_sp(kvm, sp, shared); for (i = 0; i < PT64_ENT_PER_PAGE; i++) { - u64 *sptep = rcu_dereference(pt) + i; + tdp_ptep_t sptep = pt + i; gfn_t gfn = base_gfn + i * KVM_PAGES_PER_HPAGE(level); - u64 old_child_spte; + u64 old_spte; if (shared) { /* @@ -440,8 +440,8 @@ static void handle_removed_pt(struct kvm *kvm, tdp_ptep_t pt, bool shared) * value to the removed SPTE value. */ for (;;) { - old_child_spte = xchg(sptep, REMOVED_SPTE); - if (!is_removed_spte(old_child_spte)) + old_spte = kvm_tdp_mmu_write_spte_atomic(sptep, REMOVED_SPTE); + if (!is_removed_spte(old_spte)) break; cpu_relax(); } @@ -455,23 +455,43 @@ static void handle_removed_pt(struct kvm *kvm, tdp_ptep_t pt, bool shared) * are guarded by the memslots generation, not by being * unreachable. */ - old_child_spte = READ_ONCE(*sptep); - if (!is_shadow_present_pte(old_child_spte)) + old_spte = kvm_tdp_mmu_read_spte(sptep); + if (!is_shadow_present_pte(old_spte)) continue; /* - * Marking the SPTE as a removed SPTE is not - * strictly necessary here as the MMU lock will - * stop other threads from concurrently modifying - * this SPTE. Using the removed SPTE value keeps - * the two branches consistent and simplifies - * the function. + * Use the common helper instead of a raw WRITE_ONCE as + * the SPTE needs to be updated atomically if it can be + * modified by a different vCPU outside of mmu_lock. + * Even though the parent SPTE is !PRESENT, the TLB + * hasn't yet been flushed, and both Intel and AMD + * document that A/D assists can use upper-level PxE + * entries that are cached in the TLB, i.e. the CPU can + * still access the page and mark it dirty. + * + * No retry is needed in the atomic update path as the + * sole concern is dropping a Dirty bit, i.e. no other + * task can zap/remove the SPTE as mmu_lock is held for + * write. Marking the SPTE as a removed SPTE is not + * strictly necessary for the same reason, but using + * the remove SPTE value keeps the shared/exclusive + * paths consistent and allows the handle_changed_spte() + * call below to hardcode the new value to REMOVED_SPTE. + * + * Note, even though dropping a Dirty bit is the only + * scenario where a non-atomic update could result in a + * functional bug, simply checking the Dirty bit isn't + * sufficient as a fast page fault could read the upper + * level SPTE before it is zapped, and then make this + * target SPTE writable, resume the guest, and set the + * Dirty bit between reading the SPTE above and writing + * it here. */ - WRITE_ONCE(*sptep, REMOVED_SPTE); + old_spte = kvm_tdp_mmu_write_spte(sptep, old_spte, + REMOVED_SPTE, level); } handle_changed_spte(kvm, kvm_mmu_page_as_id(sp), gfn, - old_child_spte, REMOVED_SPTE, level, - shared); + old_spte, REMOVED_SPTE, level, shared); } call_rcu(&sp->rcu_head, tdp_mmu_free_sp_rcu_callback); @@ -667,14 +687,13 @@ static inline int tdp_mmu_zap_spte_atomic(struct kvm *kvm, KVM_PAGES_PER_HPAGE(iter->level)); /* - * No other thread can overwrite the removed SPTE as they - * must either wait on the MMU lock or use - * tdp_mmu_set_spte_atomic which will not overwrite the - * special removed SPTE value. No bookkeeping is needed - * here since the SPTE is going from non-present - * to non-present. + * No other thread can overwrite the removed SPTE as they must either + * wait on the MMU lock or use tdp_mmu_set_spte_atomic() which will not + * overwrite the special removed SPTE value. No bookkeeping is needed + * here since the SPTE is going from non-present to non-present. Use + * the raw write helper to avoid an unnecessary check on volatile bits. */ - kvm_tdp_mmu_write_spte(iter->sptep, 0); + __kvm_tdp_mmu_write_spte(iter->sptep, 0); return 0; } @@ -699,10 +718,13 @@ static inline int tdp_mmu_zap_spte_atomic(struct kvm *kvm, * unless performing certain dirty logging operations. * Leaving record_dirty_log unset in that case prevents page * writes from being double counted. + * + * Returns the old SPTE value, which _may_ be different than @old_spte if the + * SPTE had voldatile bits. */ -static void __tdp_mmu_set_spte(struct kvm *kvm, int as_id, tdp_ptep_t sptep, - u64 old_spte, u64 new_spte, gfn_t gfn, int level, - bool record_acc_track, bool record_dirty_log) +static u64 __tdp_mmu_set_spte(struct kvm *kvm, int as_id, tdp_ptep_t sptep, + u64 old_spte, u64 new_spte, gfn_t gfn, int level, + bool record_acc_track, bool record_dirty_log) { lockdep_assert_held_write(&kvm->mmu_lock); @@ -715,7 +737,7 @@ static void __tdp_mmu_set_spte(struct kvm *kvm, int as_id, tdp_ptep_t sptep, */ WARN_ON(is_removed_spte(old_spte) || is_removed_spte(new_spte)); - kvm_tdp_mmu_write_spte(sptep, new_spte); + old_spte = kvm_tdp_mmu_write_spte(sptep, old_spte, new_spte, level); __handle_changed_spte(kvm, as_id, gfn, old_spte, new_spte, level, false); @@ -724,6 +746,7 @@ static void __tdp_mmu_set_spte(struct kvm *kvm, int as_id, tdp_ptep_t sptep, if (record_dirty_log) handle_changed_spte_dirty_log(kvm, as_id, gfn, old_spte, new_spte, level); + return old_spte; } static inline void _tdp_mmu_set_spte(struct kvm *kvm, struct tdp_iter *iter, @@ -732,9 +755,10 @@ static inline void _tdp_mmu_set_spte(struct kvm *kvm, struct tdp_iter *iter, { WARN_ON_ONCE(iter->yielded); - __tdp_mmu_set_spte(kvm, iter->as_id, iter->sptep, iter->old_spte, - new_spte, iter->gfn, iter->level, - record_acc_track, record_dirty_log); + iter->old_spte = __tdp_mmu_set_spte(kvm, iter->as_id, iter->sptep, + iter->old_spte, new_spte, + iter->gfn, iter->level, + record_acc_track, record_dirty_log); } static inline void tdp_mmu_set_spte(struct kvm *kvm, struct tdp_iter *iter, @@ -815,14 +839,15 @@ static inline bool __must_check tdp_mmu_iter_cond_resched(struct kvm *kvm, return iter->yielded; } -static inline gfn_t tdp_mmu_max_gfn_host(void) +static inline gfn_t tdp_mmu_max_gfn_exclusive(void) { /* - * Bound TDP MMU walks at host.MAXPHYADDR, guest accesses beyond that - * will hit a #PF(RSVD) and never hit an EPT Violation/Misconfig / #NPF, - * and so KVM will never install a SPTE for such addresses. + * Bound TDP MMU walks at host.MAXPHYADDR. KVM disallows memslots with + * a gpa range that would exceed the max gfn, and KVM does not create + * MMIO SPTEs for "impossible" gfns, instead sending such accesses down + * the slow emulation path every time. */ - return 1ULL << (shadow_phys_bits - PAGE_SHIFT); + return kvm_mmu_max_gfn() + 1; } static void __tdp_mmu_zap_root(struct kvm *kvm, struct kvm_mmu_page *root, @@ -830,7 +855,7 @@ static void __tdp_mmu_zap_root(struct kvm *kvm, struct kvm_mmu_page *root, { struct tdp_iter iter; - gfn_t end = tdp_mmu_max_gfn_host(); + gfn_t end = tdp_mmu_max_gfn_exclusive(); gfn_t start = 0; for_each_tdp_pte_min_level(iter, root, zap_level, start, end) { @@ -923,7 +948,7 @@ static bool tdp_mmu_zap_leafs(struct kvm *kvm, struct kvm_mmu_page *root, { struct tdp_iter iter; - end = min(end, tdp_mmu_max_gfn_host()); + end = min(end, tdp_mmu_max_gfn_exclusive()); lockdep_assert_held_write(&kvm->mmu_lock); diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index eca39f56c231..0604bc29f0b8 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -171,9 +171,12 @@ static bool pmc_resume_counter(struct kvm_pmc *pmc) return true; } -static int cmp_u64(const void *a, const void *b) +static int cmp_u64(const void *pa, const void *pb) { - return *(__u64 *)a - *(__u64 *)b; + u64 a = *(u64 *)pa; + u64 b = *(u64 *)pb; + + return (a > b) - (a < b); } void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel) diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h index 9e66fba1d6a3..22992b049d38 100644 --- a/arch/x86/kvm/pmu.h +++ b/arch/x86/kvm/pmu.h @@ -138,6 +138,15 @@ static inline u64 get_sample_period(struct kvm_pmc *pmc, u64 counter_value) return sample_period; } +static inline void pmc_update_sample_period(struct kvm_pmc *pmc) +{ + if (!pmc->perf_event || pmc->is_paused) + return; + + perf_event_period(pmc->perf_event, + get_sample_period(pmc, pmc->counter)); +} + void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel); void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 ctrl, int fixed_idx); void reprogram_counter(struct kvm_pmu *pmu, int pmc_idx); diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index a1cf9c31273b..421619540ff9 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -837,7 +837,8 @@ bool avic_check_apicv_inhibit_reasons(enum kvm_apicv_inhibit reason) BIT(APICV_INHIBIT_REASON_IRQWIN) | BIT(APICV_INHIBIT_REASON_PIT_REINJ) | BIT(APICV_INHIBIT_REASON_X2APIC) | - BIT(APICV_INHIBIT_REASON_BLOCKIRQ); + BIT(APICV_INHIBIT_REASON_BLOCKIRQ) | + BIT(APICV_INHIBIT_REASON_SEV); return supported & BIT(reason); } diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c index 24eb935b6f85..16a5ebb420cf 100644 --- a/arch/x86/kvm/svm/pmu.c +++ b/arch/x86/kvm/svm/pmu.c @@ -45,6 +45,22 @@ static struct kvm_event_hw_type_mapping amd_event_mapping[] = { [7] = { 0xd1, 0x00, PERF_COUNT_HW_STALLED_CYCLES_BACKEND }, }; +/* duplicated from amd_f17h_perfmon_event_map. */ +static struct kvm_event_hw_type_mapping amd_f17h_event_mapping[] = { + [0] = { 0x76, 0x00, PERF_COUNT_HW_CPU_CYCLES }, + [1] = { 0xc0, 0x00, PERF_COUNT_HW_INSTRUCTIONS }, + [2] = { 0x60, 0xff, PERF_COUNT_HW_CACHE_REFERENCES }, + [3] = { 0x64, 0x09, PERF_COUNT_HW_CACHE_MISSES }, + [4] = { 0xc2, 0x00, PERF_COUNT_HW_BRANCH_INSTRUCTIONS }, + [5] = { 0xc3, 0x00, PERF_COUNT_HW_BRANCH_MISSES }, + [6] = { 0x87, 0x02, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND }, + [7] = { 0x87, 0x01, PERF_COUNT_HW_STALLED_CYCLES_BACKEND }, +}; + +/* amd_pmc_perf_hw_id depends on these being the same size */ +static_assert(ARRAY_SIZE(amd_event_mapping) == + ARRAY_SIZE(amd_f17h_event_mapping)); + static unsigned int get_msr_base(struct kvm_pmu *pmu, enum pmu_type type) { struct kvm_vcpu *vcpu = pmu_to_vcpu(pmu); @@ -140,6 +156,7 @@ static inline struct kvm_pmc *get_gp_pmc_amd(struct kvm_pmu *pmu, u32 msr, static unsigned int amd_pmc_perf_hw_id(struct kvm_pmc *pmc) { + struct kvm_event_hw_type_mapping *event_mapping; u8 event_select = pmc->eventsel & ARCH_PERFMON_EVENTSEL_EVENT; u8 unit_mask = (pmc->eventsel & ARCH_PERFMON_EVENTSEL_UMASK) >> 8; int i; @@ -148,15 +165,20 @@ static unsigned int amd_pmc_perf_hw_id(struct kvm_pmc *pmc) if (WARN_ON(pmc_is_fixed(pmc))) return PERF_COUNT_HW_MAX; + if (guest_cpuid_family(pmc->vcpu) >= 0x17) + event_mapping = amd_f17h_event_mapping; + else + event_mapping = amd_event_mapping; + for (i = 0; i < ARRAY_SIZE(amd_event_mapping); i++) - if (amd_event_mapping[i].eventsel == event_select - && amd_event_mapping[i].unit_mask == unit_mask) + if (event_mapping[i].eventsel == event_select + && event_mapping[i].unit_mask == unit_mask) break; if (i == ARRAY_SIZE(amd_event_mapping)) return PERF_COUNT_HW_MAX; - return amd_event_mapping[i].event_type; + return event_mapping[i].event_type; } /* check if a PMC is enabled by comparing it against global_ctrl bits. Because @@ -257,6 +279,7 @@ static int amd_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) pmc = get_gp_pmc_amd(pmu, msr, PMU_TYPE_COUNTER); if (pmc) { pmc->counter += data - pmc_read_counter(pmc); + pmc_update_sample_period(pmc); return 0; } /* MSR_EVNTSELn */ diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 75fa6dd268f0..636c77ef55fc 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -260,6 +260,8 @@ static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp) INIT_LIST_HEAD(&sev->regions_list); INIT_LIST_HEAD(&sev->mirror_vms); + kvm_set_apicv_inhibit(kvm, APICV_INHIBIT_REASON_SEV); + return 0; e_free: @@ -465,6 +467,7 @@ static void sev_clflush_pages(struct page *pages[], unsigned long npages) page_virtual = kmap_atomic(pages[i]); clflush_cache_range(page_virtual, PAGE_SIZE); kunmap_atomic(page_virtual); + cond_resched(); } } @@ -559,12 +562,20 @@ e_unpin: static int sev_es_sync_vmsa(struct vcpu_svm *svm) { - struct vmcb_save_area *save = &svm->vmcb->save; + struct sev_es_save_area *save = svm->sev_es.vmsa; /* Check some debug related fields before encrypting the VMSA */ - if (svm->vcpu.guest_debug || (save->dr7 & ~DR7_FIXED_1)) + if (svm->vcpu.guest_debug || (svm->vmcb->save.dr7 & ~DR7_FIXED_1)) return -EINVAL; + /* + * SEV-ES will use a VMSA that is pointed to by the VMCB, not + * the traditional VMSA that is part of the VMCB. Copy the + * traditional VMSA as it has been built so far (in prep + * for LAUNCH_UPDATE_VMSA) to be the initial SEV-ES state. + */ + memcpy(save, &svm->vmcb->save, sizeof(svm->vmcb->save)); + /* Sync registgers */ save->rax = svm->vcpu.arch.regs[VCPU_REGS_RAX]; save->rbx = svm->vcpu.arch.regs[VCPU_REGS_RBX]; @@ -592,14 +603,6 @@ static int sev_es_sync_vmsa(struct vcpu_svm *svm) save->xss = svm->vcpu.arch.ia32_xss; save->dr6 = svm->vcpu.arch.dr6; - /* - * SEV-ES will use a VMSA that is pointed to by the VMCB, not - * the traditional VMSA that is part of the VMCB. Copy the - * traditional VMSA as it has been built so far (in prep - * for LAUNCH_UPDATE_VMSA) to be the initial SEV-ES state. - */ - memcpy(svm->sev_es.vmsa, save, sizeof(*save)); - return 0; } @@ -1591,24 +1594,51 @@ static void sev_unlock_two_vms(struct kvm *dst_kvm, struct kvm *src_kvm) atomic_set_release(&src_sev->migration_in_progress, 0); } +/* vCPU mutex subclasses. */ +enum sev_migration_role { + SEV_MIGRATION_SOURCE = 0, + SEV_MIGRATION_TARGET, + SEV_NR_MIGRATION_ROLES, +}; -static int sev_lock_vcpus_for_migration(struct kvm *kvm) +static int sev_lock_vcpus_for_migration(struct kvm *kvm, + enum sev_migration_role role) { struct kvm_vcpu *vcpu; unsigned long i, j; + bool first = true; kvm_for_each_vcpu(i, vcpu, kvm) { - if (mutex_lock_killable(&vcpu->mutex)) + if (mutex_lock_killable_nested(&vcpu->mutex, role)) goto out_unlock; + + if (first) { + /* + * Reset the role to one that avoids colliding with + * the role used for the first vcpu mutex. + */ + role = SEV_NR_MIGRATION_ROLES; + first = false; + } else { + mutex_release(&vcpu->mutex.dep_map, _THIS_IP_); + } } return 0; out_unlock: + + first = true; kvm_for_each_vcpu(j, vcpu, kvm) { if (i == j) break; + if (first) + first = false; + else + mutex_acquire(&vcpu->mutex.dep_map, role, 0, _THIS_IP_); + + mutex_unlock(&vcpu->mutex); } return -EINTR; @@ -1618,8 +1648,15 @@ static void sev_unlock_vcpus_for_migration(struct kvm *kvm) { struct kvm_vcpu *vcpu; unsigned long i; + bool first = true; kvm_for_each_vcpu(i, vcpu, kvm) { + if (first) + first = false; + else + mutex_acquire(&vcpu->mutex.dep_map, + SEV_NR_MIGRATION_ROLES, 0, _THIS_IP_); + mutex_unlock(&vcpu->mutex); } } @@ -1745,10 +1782,10 @@ int sev_vm_move_enc_context_from(struct kvm *kvm, unsigned int source_fd) charged = true; } - ret = sev_lock_vcpus_for_migration(kvm); + ret = sev_lock_vcpus_for_migration(kvm, SEV_MIGRATION_SOURCE); if (ret) goto out_dst_cgroup; - ret = sev_lock_vcpus_for_migration(source_kvm); + ret = sev_lock_vcpus_for_migration(source_kvm, SEV_MIGRATION_TARGET); if (ret) goto out_dst_vcpu; @@ -2223,51 +2260,47 @@ int sev_cpu_init(struct svm_cpu_data *sd) * Pages used by hardware to hold guest encrypted state must be flushed before * returning them to the system. */ -static void sev_flush_guest_memory(struct vcpu_svm *svm, void *va, - unsigned long len) +static void sev_flush_encrypted_page(struct kvm_vcpu *vcpu, void *va) { + int asid = to_kvm_svm(vcpu->kvm)->sev_info.asid; + /* - * If hardware enforced cache coherency for encrypted mappings of the - * same physical page is supported, nothing to do. + * Note! The address must be a kernel address, as regular page walk + * checks are performed by VM_PAGE_FLUSH, i.e. operating on a user + * address is non-deterministic and unsafe. This function deliberately + * takes a pointer to deter passing in a user address. */ - if (boot_cpu_has(X86_FEATURE_SME_COHERENT)) - return; + unsigned long addr = (unsigned long)va; /* - * If the VM Page Flush MSR is supported, use it to flush the page - * (using the page virtual address and the guest ASID). + * If CPU enforced cache coherency for encrypted mappings of the + * same physical page is supported, use CLFLUSHOPT instead. NOTE: cache + * flush is still needed in order to work properly with DMA devices. */ - if (boot_cpu_has(X86_FEATURE_VM_PAGE_FLUSH)) { - struct kvm_sev_info *sev; - unsigned long va_start; - u64 start, stop; - - /* Align start and stop to page boundaries. */ - va_start = (unsigned long)va; - start = (u64)va_start & PAGE_MASK; - stop = PAGE_ALIGN((u64)va_start + len); - - if (start < stop) { - sev = &to_kvm_svm(svm->vcpu.kvm)->sev_info; + if (boot_cpu_has(X86_FEATURE_SME_COHERENT)) { + clflush_cache_range(va, PAGE_SIZE); + return; + } - while (start < stop) { - wrmsrl(MSR_AMD64_VM_PAGE_FLUSH, - start | sev->asid); + /* + * VM Page Flush takes a host virtual address and a guest ASID. Fall + * back to WBINVD if this faults so as not to make any problems worse + * by leaving stale encrypted data in the cache. + */ + if (WARN_ON_ONCE(wrmsrl_safe(MSR_AMD64_VM_PAGE_FLUSH, addr | asid))) + goto do_wbinvd; - start += PAGE_SIZE; - } + return; - return; - } +do_wbinvd: + wbinvd_on_all_cpus(); +} - WARN(1, "Address overflow, using WBINVD\n"); - } +void sev_guest_memory_reclaimed(struct kvm *kvm) +{ + if (!sev_guest(kvm)) + return; - /* - * Hardware should always have one of the above features, - * but if not, use WBINVD and issue a warning. - */ - WARN_ONCE(1, "Using WBINVD to flush guest memory\n"); wbinvd_on_all_cpus(); } @@ -2281,7 +2314,8 @@ void sev_free_vcpu(struct kvm_vcpu *vcpu) svm = to_svm(vcpu); if (vcpu->arch.guest_state_protected) - sev_flush_guest_memory(svm, svm->sev_es.vmsa, PAGE_SIZE); + sev_flush_encrypted_page(vcpu, svm->sev_es.vmsa); + __free_page(virt_to_page(svm->sev_es.vmsa)); if (svm->sev_es.ghcb_sa_free) @@ -2932,7 +2966,7 @@ void sev_es_vcpu_reset(struct vcpu_svm *svm) sev_enc_bit)); } -void sev_es_prepare_switch_to_guest(struct vmcb_save_area *hostsa) +void sev_es_prepare_switch_to_guest(struct sev_es_save_area *hostsa) { /* * As an SEV-ES guest, hardware will restore the host state on VMEXIT, diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index bd4c64b362d2..17d334ef5430 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -1270,8 +1270,8 @@ static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu) */ vmsave(__sme_page_pa(sd->save_area)); if (sev_es_guest(vcpu->kvm)) { - struct vmcb_save_area *hostsa; - hostsa = (struct vmcb_save_area *)(page_address(sd->save_area) + 0x400); + struct sev_es_save_area *hostsa; + hostsa = (struct sev_es_save_area *)(page_address(sd->save_area) + 0x400); sev_es_prepare_switch_to_guest(hostsa); } @@ -3117,8 +3117,8 @@ static void dump_vmcb(struct kvm_vcpu *vcpu) "tr:", save01->tr.selector, save01->tr.attrib, save01->tr.limit, save01->tr.base); - pr_err("cpl: %d efer: %016llx\n", - save->cpl, save->efer); + pr_err("vmpl: %d cpl: %d efer: %016llx\n", + save->vmpl, save->cpl, save->efer); pr_err("%-15s %016llx %-13s %016llx\n", "cr0:", save->cr0, "cr2:", save->cr2); pr_err("%-15s %016llx %-13s %016llx\n", @@ -4620,6 +4620,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .mem_enc_ioctl = sev_mem_enc_ioctl, .mem_enc_register_region = sev_mem_enc_register_region, .mem_enc_unregister_region = sev_mem_enc_unregister_region, + .guest_memory_reclaimed = sev_guest_memory_reclaimed, .vm_copy_enc_context_from = sev_vm_copy_enc_context_from, .vm_move_enc_context_from = sev_vm_move_enc_context_from, diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index f77a7d2d39dd..2d83845b9032 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -181,7 +181,7 @@ struct svm_nested_state { struct vcpu_sev_es_state { /* SEV-ES support */ - struct vmcb_save_area *vmsa; + struct sev_es_save_area *vmsa; struct ghcb *ghcb; struct kvm_host_map ghcb_map; bool received_first_sipi; @@ -609,6 +609,8 @@ int sev_mem_enc_unregister_region(struct kvm *kvm, struct kvm_enc_region *range); int sev_vm_copy_enc_context_from(struct kvm *kvm, unsigned int source_fd); int sev_vm_move_enc_context_from(struct kvm *kvm, unsigned int source_fd); +void sev_guest_memory_reclaimed(struct kvm *kvm); + void pre_sev_run(struct vcpu_svm *svm, int cpu); void __init sev_set_cpu_caps(void); void __init sev_hardware_setup(void); @@ -620,7 +622,7 @@ int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in); void sev_es_init_vmcb(struct vcpu_svm *svm); void sev_es_vcpu_reset(struct vcpu_svm *svm); void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector); -void sev_es_prepare_switch_to_guest(struct vmcb_save_area *hostsa); +void sev_es_prepare_switch_to_guest(struct sev_es_save_area *hostsa); void sev_es_unmap_ghcb(struct vcpu_svm *svm); /* vmenter.S */ diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index f18744f7ff82..856c87563883 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -4618,6 +4618,11 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu); } + if (vmx->nested.update_vmcs01_apicv_status) { + vmx->nested.update_vmcs01_apicv_status = false; + kvm_make_request(KVM_REQ_APICV_UPDATE, vcpu); + } + if ((vm_exit_reason != -1) && (enable_shadow_vmcs || evmptr_is_valid(vmx->nested.hv_evmcs_vmptr))) vmx->nested.need_vmcs12_to_shadow_sync = true; diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index bc3f8512bb64..b82b6709d7a8 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -431,15 +431,11 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) !(msr & MSR_PMC_FULL_WIDTH_BIT)) data = (s64)(s32)data; pmc->counter += data - pmc_read_counter(pmc); - if (pmc->perf_event && !pmc->is_paused) - perf_event_period(pmc->perf_event, - get_sample_period(pmc, data)); + pmc_update_sample_period(pmc); return 0; } else if ((pmc = get_fixed_pmc(pmu, msr))) { pmc->counter += data - pmc_read_counter(pmc); - if (pmc->perf_event && !pmc->is_paused) - perf_event_period(pmc->perf_event, - get_sample_period(pmc, data)); + pmc_update_sample_period(pmc); return 0; } else if ((pmc = get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0))) { if (data == pmc->eventsel) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 04d170c4b61e..610355b9ccce 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -4174,6 +4174,11 @@ static void vmx_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); + if (is_guest_mode(vcpu)) { + vmx->nested.update_vmcs01_apicv_status = true; + return; + } + pin_controls_set(vmx, vmx_pin_based_exec_ctrl(vmx)); if (cpu_has_secondary_exec_ctrls()) { if (kvm_vcpu_apicv_active(vcpu)) @@ -5467,7 +5472,7 @@ static bool vmx_emulation_required_with_pending_exception(struct kvm_vcpu *vcpu) struct vcpu_vmx *vmx = to_vmx(vcpu); return vmx->emulation_required && !vmx->rmode.vm86_active && - vcpu->arch.exception.pending; + (vcpu->arch.exception.pending || vcpu->arch.exception.injected); } static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 9c6bfcd84008..b98c7e96697a 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -183,6 +183,7 @@ struct nested_vmx { bool change_vmcs01_virtual_apic_mode; bool reload_vmcs01_apic_access_page; bool update_vmcs01_cpu_dirty_logging; + bool update_vmcs01_apicv_status; /* * Enlightened VMCS has been enabled. It does not mean that L1 has to diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 0c0ca599a353..4790f0d7d40b 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -2901,7 +2901,7 @@ static void kvm_end_pvclock_update(struct kvm *kvm) static void kvm_update_masterclock(struct kvm *kvm) { - kvm_hv_invalidate_tsc_page(kvm); + kvm_hv_request_tsc_page_update(kvm); kvm_start_pvclock_update(kvm); pvclock_update_vm_gtod_copy(kvm); kvm_end_pvclock_update(kvm); @@ -3113,8 +3113,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) offsetof(struct compat_vcpu_info, time)); if (vcpu->xen.vcpu_time_info_set) kvm_setup_pvclock_page(v, &vcpu->xen.vcpu_time_info_cache, 0); - if (!v->vcpu_idx) - kvm_hv_setup_tsc_page(v->kvm, &vcpu->hv_clock); + kvm_hv_setup_tsc_page(v->kvm, &vcpu->hv_clock); return 0; } @@ -6241,7 +6240,7 @@ static int kvm_vm_ioctl_set_clock(struct kvm *kvm, void __user *argp) if (data.flags & ~KVM_CLOCK_VALID_FLAGS) return -EINVAL; - kvm_hv_invalidate_tsc_page(kvm); + kvm_hv_request_tsc_page_update(kvm); kvm_start_pvclock_update(kvm); pvclock_update_vm_gtod_copy(kvm); @@ -8926,7 +8925,7 @@ int kvm_arch_init(void *opaque) } kvm_nr_uret_msrs = 0; - r = kvm_mmu_module_init(); + r = kvm_mmu_vendor_module_init(); if (r) goto out_free_percpu; @@ -8974,7 +8973,7 @@ void kvm_arch_exit(void) cancel_work_sync(&pvclock_gtod_work); #endif kvm_x86_ops.hardware_enable = NULL; - kvm_mmu_module_exit(); + kvm_mmu_vendor_module_exit(); free_percpu(user_return_msrs); kmem_cache_destroy(x86_emulator_cache); #ifdef CONFIG_KVM_XEN @@ -9112,7 +9111,7 @@ static void kvm_apicv_init(struct kvm *kvm) if (!enable_apicv) set_or_clear_apicv_inhibit(inhibits, - APICV_INHIBIT_REASON_ABSENT, true); + APICV_INHIBIT_REASON_DISABLE, true); } static void kvm_sched_yield(struct kvm_vcpu *vcpu, unsigned long dest_id) @@ -9890,6 +9889,11 @@ void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, kvm_make_all_cpus_request(kvm, KVM_REQ_APIC_PAGE_RELOAD); } +void kvm_arch_guest_memory_reclaimed(struct kvm *kvm) +{ + static_call_cond(kvm_x86_guest_memory_reclaimed)(kvm); +} + static void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu) { if (!lapic_in_kernel(vcpu)) @@ -10016,12 +10020,14 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (kvm_check_request(KVM_REQ_HV_CRASH, vcpu)) { vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT; vcpu->run->system_event.type = KVM_SYSTEM_EVENT_CRASH; + vcpu->run->system_event.ndata = 0; r = 0; goto out; } if (kvm_check_request(KVM_REQ_HV_RESET, vcpu)) { vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT; vcpu->run->system_event.type = KVM_SYSTEM_EVENT_RESET; + vcpu->run->system_event.ndata = 0; r = 0; goto out; } @@ -10098,7 +10104,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) /* Store vcpu->apicv_active before vcpu->mode. */ smp_store_release(&vcpu->mode, IN_GUEST_MODE); - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); /* * 1) We should set ->mode before checking ->requests. Please see @@ -10129,7 +10135,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) smp_wmb(); local_irq_enable(); preempt_enable(); - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); r = 1; goto cancel_injection; } @@ -10255,7 +10261,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) local_irq_enable(); preempt_enable(); - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); /* * Profile KVM exit RIPs: @@ -10285,7 +10291,7 @@ out: } /* Called within kvm->srcu read side. */ -static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu) +static inline int vcpu_block(struct kvm_vcpu *vcpu) { bool hv_timer; @@ -10301,12 +10307,12 @@ static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu) if (hv_timer) kvm_lapic_switch_to_sw_timer(vcpu); - srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED) kvm_vcpu_halt(vcpu); else kvm_vcpu_block(vcpu); - vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); if (hv_timer) kvm_lapic_switch_to_hv_timer(vcpu); @@ -10348,7 +10354,6 @@ static inline bool kvm_vcpu_running(struct kvm_vcpu *vcpu) static int vcpu_run(struct kvm_vcpu *vcpu) { int r; - struct kvm *kvm = vcpu->kvm; vcpu->arch.l1tf_flush_l1d = true; @@ -10356,7 +10361,7 @@ static int vcpu_run(struct kvm_vcpu *vcpu) if (kvm_vcpu_running(vcpu)) { r = vcpu_enter_guest(vcpu); } else { - r = vcpu_block(kvm, vcpu); + r = vcpu_block(vcpu); } if (r <= 0) @@ -10375,9 +10380,9 @@ static int vcpu_run(struct kvm_vcpu *vcpu) } if (__xfer_to_guest_mode_work_pending()) { - srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); r = xfer_to_guest_mode_handle_work(vcpu); - vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); if (r) return r; } @@ -10388,12 +10393,7 @@ static int vcpu_run(struct kvm_vcpu *vcpu) static inline int complete_emulated_io(struct kvm_vcpu *vcpu) { - int r; - - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); - r = kvm_emulate_instruction(vcpu, EMULTYPE_NO_DECODE); - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); - return r; + return kvm_emulate_instruction(vcpu, EMULTYPE_NO_DECODE); } static int complete_emulated_pio(struct kvm_vcpu *vcpu) @@ -10485,7 +10485,6 @@ static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) { struct kvm_run *kvm_run = vcpu->run; - struct kvm *kvm = vcpu->kvm; int r; vcpu_load(vcpu); @@ -10493,7 +10492,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) kvm_run->flags = 0; kvm_load_guest_fpu(vcpu); - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); if (unlikely(vcpu->arch.mp_state == KVM_MP_STATE_UNINITIALIZED)) { if (kvm_run->immediate_exit) { r = -EINTR; @@ -10505,9 +10504,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) */ WARN_ON_ONCE(kvm_lapic_hv_timer_in_use(vcpu)); - srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); kvm_vcpu_block(vcpu); - vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); if (kvm_apic_accept_events(vcpu) < 0) { r = 0; @@ -10568,7 +10567,7 @@ out: if (kvm_run->kvm_valid_regs) store_regs(vcpu); post_kvm_run_save(vcpu); - srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); kvm_sigset_deactivate(vcpu); vcpu_put(vcpu); @@ -10986,6 +10985,9 @@ static void kvm_arch_vcpu_guestdbg_update_apicv_inhibit(struct kvm *kvm) struct kvm_vcpu *vcpu; unsigned long i; + if (!enable_apicv) + return; + down_write(&kvm->arch.apicv_update_lock); kvm_for_each_vcpu(i, vcpu, kvm) { @@ -11197,8 +11199,21 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) r = kvm_create_lapic(vcpu, lapic_timer_advance_ns); if (r < 0) goto fail_mmu_destroy; - if (kvm_apicv_activated(vcpu->kvm)) + + /* + * Defer evaluating inhibits until the vCPU is first run, as + * this vCPU will not get notified of any changes until this + * vCPU is visible to other vCPUs (marked online and added to + * the set of vCPUs). Opportunistically mark APICv active as + * VMX in particularly is highly unlikely to have inhibits. + * Ignore the current per-VM APICv state so that vCPU creation + * is guaranteed to run with a deterministic value, the request + * will ensure the vCPU gets the correct state before VM-Entry. + */ + if (enable_apicv) { vcpu->arch.apicv_active = true; + kvm_make_request(KVM_REQ_APICV_UPDATE, vcpu); + } } else static_branch_inc(&kvm_has_noapic_vcpu); @@ -11996,8 +12011,12 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *new, enum kvm_mr_change change) { - if (change == KVM_MR_CREATE || change == KVM_MR_MOVE) + if (change == KVM_MR_CREATE || change == KVM_MR_MOVE) { + if ((new->base_gfn + new->npages - 1) > kvm_mmu_max_gfn()) + return -EINVAL; + return kvm_alloc_memslot_metadata(kvm, new); + } if (change == KVM_MR_FLAGS_ONLY) memcpy(&new->arch, &old->arch, sizeof(old->arch)); @@ -12986,3 +13005,19 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_enter); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_exit); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_msr_protocol_enter); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_msr_protocol_exit); + +static int __init kvm_x86_init(void) +{ + kvm_mmu_x86_module_init(); + return 0; +} +module_init(kvm_x86_init); + +static void __exit kvm_x86_exit(void) +{ + /* + * If module_init() is implemented, module_exit() must also be + * implemented to allow module unload. + */ +} +module_exit(kvm_x86_exit); diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S index 8ca5ecf16dc4..9dec1b38a98f 100644 --- a/arch/x86/lib/copy_user_64.S +++ b/arch/x86/lib/copy_user_64.S @@ -53,12 +53,12 @@ SYM_FUNC_START(copy_user_generic_unrolled) ASM_STAC cmpl $8,%edx - jb 20f /* less then 8 bytes, go to byte copy loop */ + jb .Lcopy_user_short_string_bytes ALIGN_DESTINATION movl %edx,%ecx andl $63,%edx shrl $6,%ecx - jz .L_copy_short_string + jz copy_user_short_string 1: movq (%rsi),%r8 2: movq 1*8(%rsi),%r9 3: movq 2*8(%rsi),%r10 @@ -79,37 +79,11 @@ SYM_FUNC_START(copy_user_generic_unrolled) leaq 64(%rdi),%rdi decl %ecx jnz 1b -.L_copy_short_string: - movl %edx,%ecx - andl $7,%edx - shrl $3,%ecx - jz 20f -18: movq (%rsi),%r8 -19: movq %r8,(%rdi) - leaq 8(%rsi),%rsi - leaq 8(%rdi),%rdi - decl %ecx - jnz 18b -20: andl %edx,%edx - jz 23f - movl %edx,%ecx -21: movb (%rsi),%al -22: movb %al,(%rdi) - incq %rsi - incq %rdi - decl %ecx - jnz 21b -23: xor %eax,%eax - ASM_CLAC - RET + jmp copy_user_short_string 30: shll $6,%ecx addl %ecx,%edx - jmp 60f -40: leal (%rdx,%rcx,8),%edx - jmp 60f -50: movl %ecx,%edx -60: jmp .Lcopy_user_handle_tail /* ecx is zerorest also */ + jmp .Lcopy_user_handle_tail _ASM_EXTABLE_CPY(1b, 30b) _ASM_EXTABLE_CPY(2b, 30b) @@ -127,10 +101,6 @@ SYM_FUNC_START(copy_user_generic_unrolled) _ASM_EXTABLE_CPY(14b, 30b) _ASM_EXTABLE_CPY(15b, 30b) _ASM_EXTABLE_CPY(16b, 30b) - _ASM_EXTABLE_CPY(18b, 40b) - _ASM_EXTABLE_CPY(19b, 40b) - _ASM_EXTABLE_CPY(21b, 50b) - _ASM_EXTABLE_CPY(22b, 50b) SYM_FUNC_END(copy_user_generic_unrolled) EXPORT_SYMBOL(copy_user_generic_unrolled) @@ -191,7 +161,7 @@ EXPORT_SYMBOL(copy_user_generic_string) SYM_FUNC_START(copy_user_enhanced_fast_string) ASM_STAC /* CPUs without FSRM should avoid rep movsb for short copies */ - ALTERNATIVE "cmpl $64, %edx; jb .L_copy_short_string", "", X86_FEATURE_FSRM + ALTERNATIVE "cmpl $64, %edx; jb copy_user_short_string", "", X86_FEATURE_FSRM movl %edx,%ecx 1: rep movsb xorl %eax,%eax @@ -244,6 +214,53 @@ SYM_CODE_START_LOCAL(.Lcopy_user_handle_tail) SYM_CODE_END(.Lcopy_user_handle_tail) /* + * Finish memcpy of less than 64 bytes. #AC should already be set. + * + * Input: + * rdi destination + * rsi source + * rdx count (< 64) + * + * Output: + * eax uncopied bytes or 0 if successful. + */ +SYM_CODE_START_LOCAL(copy_user_short_string) + movl %edx,%ecx + andl $7,%edx + shrl $3,%ecx + jz .Lcopy_user_short_string_bytes +18: movq (%rsi),%r8 +19: movq %r8,(%rdi) + leaq 8(%rsi),%rsi + leaq 8(%rdi),%rdi + decl %ecx + jnz 18b +.Lcopy_user_short_string_bytes: + andl %edx,%edx + jz 23f + movl %edx,%ecx +21: movb (%rsi),%al +22: movb %al,(%rdi) + incq %rsi + incq %rdi + decl %ecx + jnz 21b +23: xor %eax,%eax + ASM_CLAC + RET + +40: leal (%rdx,%rcx,8),%edx + jmp 60f +50: movl %ecx,%edx /* ecx is zerorest also */ +60: jmp .Lcopy_user_handle_tail + + _ASM_EXTABLE_CPY(18b, 40b) + _ASM_EXTABLE_CPY(19b, 40b) + _ASM_EXTABLE_CPY(21b, 50b) + _ASM_EXTABLE_CPY(22b, 50b) +SYM_CODE_END(copy_user_short_string) + +/* * copy_user_nocache - Uncached memory copy with exception handling * This will force destination out of cache for more performance. * diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c index 65d15df6212d..0e65d00e2339 100644 --- a/arch/x86/lib/delay.c +++ b/arch/x86/lib/delay.c @@ -54,8 +54,8 @@ static void delay_loop(u64 __loops) " jnz 2b \n" "3: dec %0 \n" - : /* we don't need output */ - :"a" (loops) + : "+a" (loops) + : ); } diff --git a/arch/x86/lib/insn-eval.c b/arch/x86/lib/insn-eval.c index b781d324211b..21104c41cba0 100644 --- a/arch/x86/lib/insn-eval.c +++ b/arch/x86/lib/insn-eval.c @@ -342,9 +342,9 @@ static int resolve_seg_reg(struct insn *insn, struct pt_regs *regs, int regoff) */ static short get_segment_selector(struct pt_regs *regs, int seg_reg_idx) { -#ifdef CONFIG_X86_64 unsigned short sel; +#ifdef CONFIG_X86_64 switch (seg_reg_idx) { case INAT_SEG_REG_IGNORE: return 0; @@ -402,7 +402,8 @@ static short get_segment_selector(struct pt_regs *regs, int seg_reg_idx) case INAT_SEG_REG_FS: return (unsigned short)(regs->fs & 0xffff); case INAT_SEG_REG_GS: - return get_user_gs(regs); + savesegment(gs, sel); + return sel; case INAT_SEG_REG_IGNORE: default: return -EINVAL; diff --git a/arch/x86/lib/kaslr.c b/arch/x86/lib/kaslr.c index 2b3eb8c948a3..a58f451a7dd3 100644 --- a/arch/x86/lib/kaslr.c +++ b/arch/x86/lib/kaslr.c @@ -11,7 +11,7 @@ #include <asm/msr.h> #include <asm/archrandom.h> #include <asm/e820/api.h> -#include <asm/io.h> +#include <asm/shared/io.h> /* * When built for the regular kernel, several functions need to be stubbed out diff --git a/arch/x86/lib/mmx_32.c b/arch/x86/lib/mmx_32.c deleted file mode 100644 index e69de29bb2d1..000000000000 --- a/arch/x86/lib/mmx_32.c +++ /dev/null diff --git a/arch/x86/lib/putuser.S b/arch/x86/lib/putuser.S index ecb2049c1273..b7dfd60243b7 100644 --- a/arch/x86/lib/putuser.S +++ b/arch/x86/lib/putuser.S @@ -48,6 +48,7 @@ SYM_FUNC_START(__put_user_1) cmp %_ASM_BX,%_ASM_CX jae .Lbad_put_user SYM_INNER_LABEL(__put_user_nocheck_1, SYM_L_GLOBAL) + ENDBR ASM_STAC 1: movb %al,(%_ASM_CX) xor %ecx,%ecx @@ -62,6 +63,7 @@ SYM_FUNC_START(__put_user_2) cmp %_ASM_BX,%_ASM_CX jae .Lbad_put_user SYM_INNER_LABEL(__put_user_nocheck_2, SYM_L_GLOBAL) + ENDBR ASM_STAC 2: movw %ax,(%_ASM_CX) xor %ecx,%ecx @@ -76,6 +78,7 @@ SYM_FUNC_START(__put_user_4) cmp %_ASM_BX,%_ASM_CX jae .Lbad_put_user SYM_INNER_LABEL(__put_user_nocheck_4, SYM_L_GLOBAL) + ENDBR ASM_STAC 3: movl %eax,(%_ASM_CX) xor %ecx,%ecx @@ -90,6 +93,7 @@ SYM_FUNC_START(__put_user_8) cmp %_ASM_BX,%_ASM_CX jae .Lbad_put_user SYM_INNER_LABEL(__put_user_nocheck_8, SYM_L_GLOBAL) + ENDBR ASM_STAC 4: mov %_ASM_AX,(%_ASM_CX) #ifdef CONFIG_X86_32 diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index 5f87bab4fb8d..b2b2366885a2 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -31,6 +31,7 @@ .align RETPOLINE_THUNK_SIZE SYM_INNER_LABEL(__x86_indirect_thunk_\reg, SYM_L_GLOBAL) UNWIND_HINT_EMPTY + ANNOTATE_NOENDBR ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), \ __stringify(RETPOLINE \reg), X86_FEATURE_RETPOLINE, \ @@ -55,7 +56,6 @@ SYM_INNER_LABEL(__x86_indirect_thunk_\reg, SYM_L_GLOBAL) .align RETPOLINE_THUNK_SIZE SYM_CODE_START(__x86_indirect_thunk_array) - ANNOTATE_NOENDBR // apply_retpolines #define GEN(reg) THUNK reg #include <asm/GEN-for-each-reg.h> diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c index 0402a749f3a0..0ae6cf804197 100644 --- a/arch/x86/lib/usercopy_64.c +++ b/arch/x86/lib/usercopy_64.c @@ -119,7 +119,7 @@ void __memcpy_flushcache(void *_dst, const void *_src, size_t size) /* cache copy and flush to align dest */ if (!IS_ALIGNED(dest, 8)) { - unsigned len = min_t(unsigned, size, ALIGN(dest, 8) - dest); + size_t len = min_t(size_t, size, ALIGN(dest, 8) - dest); memcpy((void *) dest, (void *) source, len); clean_cache_range((void *) dest, len); diff --git a/arch/x86/math-emu/get_address.c b/arch/x86/math-emu/get_address.c index b82ca14ba718..4a9fd9029a53 100644 --- a/arch/x86/math-emu/get_address.c +++ b/arch/x86/math-emu/get_address.c @@ -153,7 +153,7 @@ static long pm_address(u_char FPU_modrm, u_char segment, switch (segment) { case PREFIX_GS_ - 1: /* user gs handling can be lazy, use special accessors */ - addr->selector = get_user_gs(FPU_info->regs); + savesegment(gs, addr->selector); break; default: addr->selector = PM_REG_(segment); diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index fe3d3061fc11..d957dc15b371 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -20,13 +20,12 @@ CFLAGS_REMOVE_mem_encrypt_identity.o = -pg endif obj-y := init.o init_$(BITS).o fault.o ioremap.o extable.o mmap.o \ - pgtable.o physaddr.o setup_nx.o tlb.o cpu_entry_area.o maccess.o + pgtable.o physaddr.o tlb.o cpu_entry_area.o maccess.o obj-y += pat/ # Make sure __phys_addr has no stackprotector CFLAGS_physaddr.o := -fno-stack-protector -CFLAGS_setup_nx.o := -fno-stack-protector CFLAGS_mem_encrypt_identity.o := -fno-stack-protector CFLAGS_fault.o := -I $(srctree)/$(src)/../include/asm/trace diff --git a/arch/x86/mm/amdtopology.c b/arch/x86/mm/amdtopology.c index 058b2f36b3a6..b3ca7d23e4b0 100644 --- a/arch/x86/mm/amdtopology.c +++ b/arch/x86/mm/amdtopology.c @@ -154,7 +154,7 @@ int __init amd_numa_init(void) node_set(nodeid, numa_nodes_parsed); } - if (!nodes_weight(numa_nodes_parsed)) + if (nodes_empty(numa_nodes_parsed)) return -ENOENT; /* diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index d0074c6ed31a..fad8faa29d04 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -149,7 +149,7 @@ is_prefetch(struct pt_regs *regs, unsigned long error_code, unsigned long addr) unsigned char opcode; if (user_mode(regs)) { - if (get_user(opcode, instr)) + if (get_user(opcode, (unsigned char __user *) instr)) break; } else { if (get_kernel_nofault(opcode, instr)) diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 96d34ebb20a9..61d0ab154f96 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -110,7 +110,6 @@ int force_personality32; /* * noexec32=on|off * Control non executable heap for 32bit processes. - * To control the stack too use noexec=off * * on PROT_READ does not imply PROT_EXEC for 32-bit processes (default) * off PROT_READ implies PROT_EXEC @@ -902,6 +901,8 @@ static void __meminit vmemmap_use_sub_pmd(unsigned long start, unsigned long end static void __meminit vmemmap_use_new_sub_pmd(unsigned long start, unsigned long end) { + const unsigned long page = ALIGN_DOWN(start, PMD_SIZE); + vmemmap_flush_unused_pmd(); /* @@ -914,8 +915,7 @@ static void __meminit vmemmap_use_new_sub_pmd(unsigned long start, unsigned long * Mark with PAGE_UNUSED the unused parts of the new memmap range */ if (!IS_ALIGNED(start, PMD_SIZE)) - memset((void *)start, PAGE_UNUSED, - start - ALIGN_DOWN(start, PMD_SIZE)); + memset((void *)page, PAGE_UNUSED, start - page); /* * We want to avoid memset(PAGE_UNUSED) when populating the vmemmap of diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 17a492c27306..1ad0228f8ceb 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -242,10 +242,15 @@ __ioremap_caller(resource_size_t phys_addr, unsigned long size, * If the page being mapped is in memory and SEV is active then * make sure the memory encryption attribute is enabled in the * resulting mapping. + * In TDX guests, memory is marked private by default. If encryption + * is not requested (using encrypted), explicitly set decrypt + * attribute in all IOREMAPPED memory. */ prot = PAGE_KERNEL_IO; if ((io_desc.flags & IORES_MAP_ENCRYPTED) || encrypted) prot = pgprot_encrypted(prot); + else + prot = pgprot_decrypted(prot); switch (pcm) { case _PAGE_CACHE_MODE_UC: diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c index 50d209939c66..11350e2fd736 100644 --- a/arch/x86/mm/mem_encrypt.c +++ b/arch/x86/mm/mem_encrypt.c @@ -42,7 +42,14 @@ bool force_dma_unencrypted(struct device *dev) static void print_mem_encrypt_feature_info(void) { - pr_info("AMD Memory Encryption Features active:"); + pr_info("Memory Encryption Features active:"); + + if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) { + pr_cont(" Intel TDX\n"); + return; + } + + pr_cont(" AMD"); /* Secure Memory Encryption */ if (cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT)) { @@ -62,6 +69,10 @@ static void print_mem_encrypt_feature_info(void) if (cc_platform_has(CC_ATTR_GUEST_STATE_ENCRYPT)) pr_cont(" SEV-ES"); + /* Secure Nested Paging */ + if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) + pr_cont(" SEV-SNP"); + pr_cont("\n"); } diff --git a/arch/x86/mm/mem_encrypt_amd.c b/arch/x86/mm/mem_encrypt_amd.c index 6169053c2854..d3c88d9ef8d6 100644 --- a/arch/x86/mm/mem_encrypt_amd.c +++ b/arch/x86/mm/mem_encrypt_amd.c @@ -31,6 +31,7 @@ #include <asm/processor-flags.h> #include <asm/msr.h> #include <asm/cmdline.h> +#include <asm/sev.h> #include "mm_internal.h" @@ -48,6 +49,36 @@ EXPORT_SYMBOL(sme_me_mask); static char sme_early_buffer[PAGE_SIZE] __initdata __aligned(PAGE_SIZE); /* + * SNP-specific routine which needs to additionally change the page state from + * private to shared before copying the data from the source to destination and + * restore after the copy. + */ +static inline void __init snp_memcpy(void *dst, void *src, size_t sz, + unsigned long paddr, bool decrypt) +{ + unsigned long npages = PAGE_ALIGN(sz) >> PAGE_SHIFT; + + if (decrypt) { + /* + * @paddr needs to be accessed decrypted, mark the page shared in + * the RMP table before copying it. + */ + early_snp_set_memory_shared((unsigned long)__va(paddr), paddr, npages); + + memcpy(dst, src, sz); + + /* Restore the page state after the memcpy. */ + early_snp_set_memory_private((unsigned long)__va(paddr), paddr, npages); + } else { + /* + * @paddr need to be accessed encrypted, no need for the page state + * change. + */ + memcpy(dst, src, sz); + } +} + +/* * This routine does not change the underlying encryption setting of the * page(s) that map this memory. It assumes that eventually the memory is * meant to be accessed as either encrypted or decrypted but the contents @@ -95,8 +126,13 @@ static void __init __sme_early_enc_dec(resource_size_t paddr, * Use a temporary buffer, of cache-line multiple size, to * avoid data corruption as documented in the APM. */ - memcpy(sme_early_buffer, src, len); - memcpy(dst, sme_early_buffer, len); + if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) { + snp_memcpy(sme_early_buffer, src, len, paddr, enc); + snp_memcpy(dst, sme_early_buffer, len, paddr, !enc); + } else { + memcpy(sme_early_buffer, src, len); + memcpy(dst, sme_early_buffer, len); + } early_memunmap(dst, len); early_memunmap(src, len); @@ -280,11 +316,24 @@ static void enc_dec_hypercall(unsigned long vaddr, int npages, bool enc) static void amd_enc_status_change_prepare(unsigned long vaddr, int npages, bool enc) { + /* + * To maintain the security guarantees of SEV-SNP guests, make sure + * to invalidate the memory before encryption attribute is cleared. + */ + if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP) && !enc) + snp_set_memory_shared(vaddr, npages); } /* Return true unconditionally: return value doesn't matter for the SEV side */ static bool amd_enc_status_change_finish(unsigned long vaddr, int npages, bool enc) { + /* + * After memory is mapped encrypted in the page table, validate it + * so that it is consistent with the page table updates. + */ + if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP) && enc) + snp_set_memory_private(vaddr, npages); + if (!cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT)) enc_dec_hypercall(vaddr, npages, enc); @@ -322,14 +371,28 @@ static void __init __set_clr_pte_enc(pte_t *kpte, int level, bool enc) clflush_cache_range(__va(pa), size); /* Encrypt/decrypt the contents in-place */ - if (enc) + if (enc) { sme_early_encrypt(pa, size); - else + } else { sme_early_decrypt(pa, size); + /* + * ON SNP, the page state in the RMP table must happen + * before the page table updates. + */ + early_snp_set_memory_shared((unsigned long)__va(pa), pa, 1); + } + /* Change the page encryption mask. */ new_pte = pfn_pte(pfn, new_prot); set_pte_atomic(kpte, new_pte); + + /* + * If page is set encrypted in the page table, then update the RMP table to + * add this page as private. + */ + if (enc) + early_snp_set_memory_private((unsigned long)__va(pa), pa, 1); } static int __init early_set_memory_enc_dec(unsigned long vaddr, diff --git a/arch/x86/mm/mem_encrypt_identity.c b/arch/x86/mm/mem_encrypt_identity.c index b43bc24d2bb6..f415498d3175 100644 --- a/arch/x86/mm/mem_encrypt_identity.c +++ b/arch/x86/mm/mem_encrypt_identity.c @@ -45,6 +45,7 @@ #include <asm/sections.h> #include <asm/cmdline.h> #include <asm/coco.h> +#include <asm/sev.h> #include "mm_internal.h" @@ -509,8 +510,11 @@ void __init sme_enable(struct boot_params *bp) bool active_by_default; unsigned long me_mask; char buffer[16]; + bool snp; u64 msr; + snp = snp_init(bp); + /* Check for the SME/SEV support leaf */ eax = 0x80000000; ecx = 0; @@ -542,6 +546,10 @@ void __init sme_enable(struct boot_params *bp) sev_status = __rdmsr(MSR_AMD64_SEV); feature_mask = (sev_status & MSR_AMD64_SEV_ENABLED) ? AMD_SEV_BIT : AMD_SME_BIT; + /* The SEV-SNP CC blob should never be present unless SEV-SNP is enabled. */ + if (snp && !(sev_status & MSR_AMD64_SEV_SNP_ENABLED)) + snp_abort(); + /* Check if memory encryption is enabled */ if (feature_mask == AMD_SME_BIT) { /* diff --git a/arch/x86/mm/mmio-mod.c b/arch/x86/mm/mmio-mod.c index 933a2ebad471..c3317f0650d8 100644 --- a/arch/x86/mm/mmio-mod.c +++ b/arch/x86/mm/mmio-mod.c @@ -400,7 +400,7 @@ static void leave_uniprocessor(void) int cpu; int err; - if (!cpumask_available(downed_cpus) || cpumask_weight(downed_cpus) == 0) + if (!cpumask_available(downed_cpus) || cpumask_empty(downed_cpus)) return; pr_notice("Re-enabling CPUs...\n"); for_each_cpu(cpu, downed_cpus) { diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c index 1a02b791d273..9a9305367fdd 100644 --- a/arch/x86/mm/numa_emulation.c +++ b/arch/x86/mm/numa_emulation.c @@ -123,7 +123,7 @@ static int __init split_nodes_interleave(struct numa_meminfo *ei, * Continue to fill physical nodes with fake nodes until there is no * memory left on any of them. */ - while (nodes_weight(physnode_mask)) { + while (!nodes_empty(physnode_mask)) { for_each_node_mask(i, physnode_mask) { u64 dma32_end = PFN_PHYS(MAX_DMA32_PFN); u64 start, limit, end; @@ -270,7 +270,7 @@ static int __init split_nodes_size_interleave_uniform(struct numa_meminfo *ei, * Fill physical nodes with fake nodes of size until there is no memory * left on any of them. */ - while (nodes_weight(physnode_mask)) { + while (!nodes_empty(physnode_mask)) { for_each_node_mask(i, physnode_mask) { u64 dma32_end = PFN_PHYS(MAX_DMA32_PFN); u64 start, limit, end; diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c index 4ba2a3ee4bce..d5ef64ddd35e 100644 --- a/arch/x86/mm/pat/memtype.c +++ b/arch/x86/mm/pat/memtype.c @@ -101,7 +101,7 @@ int pat_debug_enable; static int __init pat_debug_setup(char *str) { pat_debug_enable = 1; - return 0; + return 1; } __setup("debugpat", pat_debug_setup); diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c index abf5ed76e4b7..0656db33574d 100644 --- a/arch/x86/mm/pat/set_memory.c +++ b/arch/x86/mm/pat/set_memory.c @@ -638,17 +638,6 @@ pte_t *lookup_address(unsigned long address, unsigned int *level) } EXPORT_SYMBOL_GPL(lookup_address); -/* - * Lookup the page table entry for a virtual address in a given mm. Return a - * pointer to the entry and the level of the mapping. - */ -pte_t *lookup_address_in_mm(struct mm_struct *mm, unsigned long address, - unsigned int *level) -{ - return lookup_address_in_pgd(pgd_offset(mm, address), address, level); -} -EXPORT_SYMBOL_GPL(lookup_address_in_mm); - static pte_t *_lookup_address_cpa(struct cpa_data *cpa, unsigned long address, unsigned int *level) { diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c index 5d5c7bb50ce9..ffe3b3a087fe 100644 --- a/arch/x86/mm/pti.c +++ b/arch/x86/mm/pti.c @@ -540,7 +540,7 @@ static inline bool pti_kernel_image_global_ok(void) * cases where RANDSTRUCT is in use to help keep the layout a * secret. */ - if (IS_ENABLED(CONFIG_GCC_PLUGIN_RANDSTRUCT)) + if (IS_ENABLED(CONFIG_RANDSTRUCT)) return false; return true; diff --git a/arch/x86/mm/setup_nx.c b/arch/x86/mm/setup_nx.c deleted file mode 100644 index ed5667f5169f..000000000000 --- a/arch/x86/mm/setup_nx.c +++ /dev/null @@ -1,62 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <linux/spinlock.h> -#include <linux/errno.h> -#include <linux/init.h> -#include <linux/pgtable.h> - -#include <asm/proto.h> -#include <asm/cpufeature.h> - -static int disable_nx; - -/* - * noexec = on|off - * - * Control non-executable mappings for processes. - * - * on Enable - * off Disable - */ -static int __init noexec_setup(char *str) -{ - if (!str) - return -EINVAL; - if (!strncmp(str, "on", 2)) { - disable_nx = 0; - } else if (!strncmp(str, "off", 3)) { - disable_nx = 1; - } - x86_configure_nx(); - return 0; -} -early_param("noexec", noexec_setup); - -void x86_configure_nx(void) -{ - if (boot_cpu_has(X86_FEATURE_NX) && !disable_nx) - __supported_pte_mask |= _PAGE_NX; - else - __supported_pte_mask &= ~_PAGE_NX; -} - -void __init x86_report_nx(void) -{ - if (!boot_cpu_has(X86_FEATURE_NX)) { - printk(KERN_NOTICE "Notice: NX (Execute Disable) protection " - "missing in CPU!\n"); - } else { -#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE) - if (disable_nx) { - printk(KERN_INFO "NX (Execute Disable) protection: " - "disabled by kernel command line option\n"); - } else { - printk(KERN_INFO "NX (Execute Disable) protection: " - "active\n"); - } -#else - /* 32bit non-PAE kernel, NX cannot be used */ - printk(KERN_NOTICE "Notice: NX (Execute Disable) protection " - "cannot be enabled: non-PAE kernel!\n"); -#endif - } -} diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 6eb4d91d5365..d400b6d9d246 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -855,13 +855,11 @@ done: nr_invalidate); } -static bool tlb_is_not_lazy(int cpu) +static bool tlb_is_not_lazy(int cpu, void *data) { return !per_cpu(cpu_tlbstate_shared.is_lazy, cpu); } -static DEFINE_PER_CPU(cpumask_t, flush_tlb_mask); - DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state_shared, cpu_tlbstate_shared); EXPORT_PER_CPU_SYMBOL(cpu_tlbstate_shared); @@ -890,36 +888,11 @@ STATIC_NOPV void native_flush_tlb_multi(const struct cpumask *cpumask, * up on the new contents of what used to be page tables, while * doing a speculative memory access. */ - if (info->freed_tables) { + if (info->freed_tables) on_each_cpu_mask(cpumask, flush_tlb_func, (void *)info, true); - } else { - /* - * Although we could have used on_each_cpu_cond_mask(), - * open-coding it has performance advantages, as it eliminates - * the need for indirect calls or retpolines. In addition, it - * allows to use a designated cpumask for evaluating the - * condition, instead of allocating one. - * - * This code works under the assumption that there are no nested - * TLB flushes, an assumption that is already made in - * flush_tlb_mm_range(). - * - * cond_cpumask is logically a stack-local variable, but it is - * more efficient to have it off the stack and not to allocate - * it on demand. Preemption is disabled and this code is - * non-reentrant. - */ - struct cpumask *cond_cpumask = this_cpu_ptr(&flush_tlb_mask); - int cpu; - - cpumask_clear(cond_cpumask); - - for_each_cpu(cpu, cpumask) { - if (tlb_is_not_lazy(cpu)) - __cpumask_set_cpu(cpu, cond_cpumask); - } - on_each_cpu_mask(cond_cpumask, flush_tlb_func, (void *)info, true); - } + else + on_each_cpu_cond_mask(tlb_is_not_lazy, flush_tlb_func, + (void *)info, 1, cpumask); } void flush_tlb_multi(const struct cpumask *cpumask, diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 8fe35ed11fd6..16b6efacf7c6 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -412,6 +412,7 @@ static void emit_indirect_jump(u8 **pprog, int reg, u8 *ip) EMIT_LFENCE(); EMIT2(0xFF, 0xE0 + reg); } else if (cpu_feature_enabled(X86_FEATURE_RETPOLINE)) { + OPTIMIZER_HIDE_VAR(reg); emit_jump(&prog, &__x86_indirect_thunk_array[reg], ip); } else #endif diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c index 97b63e35e152..a498b847d740 100644 --- a/arch/x86/pci/irq.c +++ b/arch/x86/pci/irq.c @@ -25,6 +25,8 @@ #define PIRQ_SIGNATURE (('$' << 0) + ('P' << 8) + ('I' << 16) + ('R' << 24)) #define PIRQ_VERSION 0x0100 +#define IRT_SIGNATURE (('$' << 0) + ('I' << 8) + ('R' << 16) + ('T' << 24)) + static int broken_hp_bios_irq9; static int acer_tm360_irqrouting; @@ -68,30 +70,99 @@ void (*pcibios_disable_irq)(struct pci_dev *dev) = pirq_disable_irq; * and perform checksum verification. */ -static inline struct irq_routing_table *pirq_check_routing_table(u8 *addr) +static inline struct irq_routing_table *pirq_check_routing_table(u8 *addr, + u8 *limit) { struct irq_routing_table *rt; int i; u8 sum; - rt = (struct irq_routing_table *) addr; + rt = (struct irq_routing_table *)addr; if (rt->signature != PIRQ_SIGNATURE || rt->version != PIRQ_VERSION || rt->size % 16 || - rt->size < sizeof(struct irq_routing_table)) + rt->size < sizeof(struct irq_routing_table) || + (limit && rt->size > limit - addr)) return NULL; sum = 0; for (i = 0; i < rt->size; i++) sum += addr[i]; if (!sum) { - DBG(KERN_DEBUG "PCI: Interrupt Routing Table found at 0x%p\n", - rt); + DBG(KERN_DEBUG "PCI: Interrupt Routing Table found at 0x%lx\n", + __pa(rt)); return rt; } return NULL; } +/* + * Handle the $IRT PCI IRQ Routing Table format used by AMI for its BCP + * (BIOS Configuration Program) external tool meant for tweaking BIOS + * structures without the need to rebuild it from sources. The $IRT + * format has been invented by AMI before Microsoft has come up with its + * $PIR format and a $IRT table is therefore there in some systems that + * lack a $PIR table. + * + * It uses the same PCI BIOS 2.1 format for interrupt routing entries + * themselves but has a different simpler header prepended instead, + * occupying 8 bytes, where a `$IRT' signature is followed by one byte + * specifying the total number of interrupt routing entries allocated in + * the table, then one byte specifying the actual number of entries used + * (which the BCP tool can take advantage of when modifying the table), + * and finally a 16-bit word giving the IRQs devoted exclusively to PCI. + * Unlike with the $PIR table there is no alignment guarantee. + * + * Given the similarity of the two formats the $IRT one is trivial to + * convert to the $PIR one, which we do here, except that obviously we + * have no information as to the router device to use, but we can handle + * it by matching PCI device IDs actually seen on the bus against ones + * that our individual routers recognise. + * + * Reportedly there is another $IRT table format where a 16-bit word + * follows the header instead that points to interrupt routing entries + * in a $PIR table provided elsewhere. In that case this code will not + * be reached though as the $PIR table will have been chosen instead. + */ +static inline struct irq_routing_table *pirq_convert_irt_table(u8 *addr, + u8 *limit) +{ + struct irt_routing_table *ir; + struct irq_routing_table *rt; + u16 size; + u8 sum; + int i; + + ir = (struct irt_routing_table *)addr; + if (ir->signature != IRT_SIGNATURE || !ir->used || ir->size < ir->used) + return NULL; + + size = sizeof(*ir) + ir->used * sizeof(ir->slots[0]); + if (size > limit - addr) + return NULL; + + DBG(KERN_DEBUG "PCI: $IRT Interrupt Routing Table found at 0x%lx\n", + __pa(ir)); + size = sizeof(*rt) + ir->used * sizeof(rt->slots[0]); + rt = kzalloc(size, GFP_KERNEL); + if (!rt) + return NULL; + + rt->signature = PIRQ_SIGNATURE; + rt->version = PIRQ_VERSION; + rt->size = size; + rt->exclusive_irqs = ir->exclusive_irqs; + for (i = 0; i < ir->used; i++) + rt->slots[i] = ir->slots[i]; + + addr = (u8 *)rt; + sum = 0; + for (i = 0; i < size; i++) + sum += addr[i]; + rt->checksum = -sum; + + return rt; +} /* * Search 0xf0000 -- 0xfffff for the PCI IRQ Routing Table. @@ -99,17 +170,29 @@ static inline struct irq_routing_table *pirq_check_routing_table(u8 *addr) static struct irq_routing_table * __init pirq_find_routing_table(void) { + u8 * const bios_start = (u8 *)__va(0xf0000); + u8 * const bios_end = (u8 *)__va(0x100000); u8 *addr; struct irq_routing_table *rt; if (pirq_table_addr) { - rt = pirq_check_routing_table((u8 *) __va(pirq_table_addr)); + rt = pirq_check_routing_table((u8 *)__va(pirq_table_addr), + NULL); if (rt) return rt; printk(KERN_WARNING "PCI: PIRQ table NOT found at pirqaddr\n"); } - for (addr = (u8 *) __va(0xf0000); addr < (u8 *) __va(0x100000); addr += 16) { - rt = pirq_check_routing_table(addr); + for (addr = bios_start; + addr < bios_end - sizeof(struct irq_routing_table); + addr += 16) { + rt = pirq_check_routing_table(addr, bios_end); + if (rt) + return rt; + } + for (addr = bios_start; + addr < bios_end - sizeof(struct irt_routing_table); + addr++) { + rt = pirq_convert_irt_table(addr, bios_end); if (rt) return rt; } @@ -135,7 +218,8 @@ static void __init pirq_peer_trick(void) #ifdef DEBUG { int j; - DBG(KERN_DEBUG "%02x:%02x slot=%02x", e->bus, e->devfn/8, e->slot); + DBG(KERN_DEBUG "%02x:%02x.%x slot=%02x", + e->bus, e->devfn / 8, e->devfn % 8, e->slot); for (j = 0; j < 4; j++) DBG(" %d:%02x/%04x", j, e->irq[j].link, e->irq[j].bitmap); DBG("\n"); @@ -253,6 +337,15 @@ static void write_pc_conf_nybble(u8 base, u8 index, u8 val) pc_conf_set(reg, x); } +/* + * FinALi pirq rules are as follows: + * + * - bit 0 selects between INTx Routing Table Mapping Registers, + * + * - bit 3 selects the nibble within the INTx Routing Table Mapping Register, + * + * - bits 7:4 map to bits 3:0 of the PCI INTx Sensitivity Register. + */ static int pirq_finali_get(struct pci_dev *router, struct pci_dev *dev, int pirq) { @@ -260,11 +353,13 @@ static int pirq_finali_get(struct pci_dev *router, struct pci_dev *dev, 0, 9, 3, 10, 4, 5, 7, 6, 0, 11, 0, 12, 0, 14, 0, 15 }; unsigned long flags; + u8 index; u8 x; + index = (pirq & 1) << 1 | (pirq & 8) >> 3; raw_spin_lock_irqsave(&pc_conf_lock, flags); pc_conf_set(PC_CONF_FINALI_LOCK, PC_CONF_FINALI_LOCK_KEY); - x = irqmap[read_pc_conf_nybble(PC_CONF_FINALI_PCI_INTX_RT1, pirq - 1)]; + x = irqmap[read_pc_conf_nybble(PC_CONF_FINALI_PCI_INTX_RT1, index)]; pc_conf_set(PC_CONF_FINALI_LOCK, 0); raw_spin_unlock_irqrestore(&pc_conf_lock, flags); return x; @@ -278,13 +373,15 @@ static int pirq_finali_set(struct pci_dev *router, struct pci_dev *dev, }; u8 val = irqmap[irq]; unsigned long flags; + u8 index; if (!val) return 0; + index = (pirq & 1) << 1 | (pirq & 8) >> 3; raw_spin_lock_irqsave(&pc_conf_lock, flags); pc_conf_set(PC_CONF_FINALI_LOCK, PC_CONF_FINALI_LOCK_KEY); - write_pc_conf_nybble(PC_CONF_FINALI_PCI_INTX_RT1, pirq - 1, val); + write_pc_conf_nybble(PC_CONF_FINALI_PCI_INTX_RT1, index, val); pc_conf_set(PC_CONF_FINALI_LOCK, 0); raw_spin_unlock_irqrestore(&pc_conf_lock, flags); return 1; @@ -293,7 +390,7 @@ static int pirq_finali_set(struct pci_dev *router, struct pci_dev *dev, static int pirq_finali_lvl(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq) { - u8 mask = ~(1u << (pirq - 1)); + u8 mask = ~((pirq & 0xf0u) >> 4); unsigned long flags; u8 trig; @@ -579,6 +676,81 @@ static int pirq_cyrix_set(struct pci_dev *router, struct pci_dev *dev, int pirq, return 1; } + +/* + * PIRQ routing for the SiS85C497 AT Bus Controller & Megacell (ATM) + * ISA bridge used with the SiS 85C496/497 486 Green PC VESA/ISA/PCI + * Chipset. + * + * There are four PCI INTx#-to-IRQ Link registers provided in the + * SiS85C497 part of the peculiar combined 85C496/497 configuration + * space decoded by the SiS85C496 PCI & CPU Memory Controller (PCM) + * host bridge, at 0xc0/0xc1/0xc2/0xc3 respectively for the PCI INT + * A/B/C/D lines. Bit 7 enables the respective link if set and bits + * 3:0 select the 8259A IRQ line as follows: + * + * 0000 : Reserved + * 0001 : Reserved + * 0010 : Reserved + * 0011 : IRQ3 + * 0100 : IRQ4 + * 0101 : IRQ5 + * 0110 : IRQ6 + * 0111 : IRQ7 + * 1000 : Reserved + * 1001 : IRQ9 + * 1010 : IRQ10 + * 1011 : IRQ11 + * 1100 : IRQ12 + * 1101 : Reserved + * 1110 : IRQ14 + * 1111 : IRQ15 + * + * We avoid using a reserved value for disabled links, hence the + * choice of IRQ15 for that case. + * + * References: + * + * "486 Green PC VESA/ISA/PCI Chipset, SiS 85C496/497", Rev 3.0, + * Silicon Integrated Systems Corp., July 1995 + */ + +#define PCI_SIS497_INTA_TO_IRQ_LINK 0xc0u + +#define PIRQ_SIS497_IRQ_MASK 0x0fu +#define PIRQ_SIS497_IRQ_ENABLE 0x80u + +static int pirq_sis497_get(struct pci_dev *router, struct pci_dev *dev, + int pirq) +{ + int reg; + u8 x; + + reg = pirq; + if (reg >= 1 && reg <= 4) + reg += PCI_SIS497_INTA_TO_IRQ_LINK - 1; + + pci_read_config_byte(router, reg, &x); + return (x & PIRQ_SIS497_IRQ_ENABLE) ? (x & PIRQ_SIS497_IRQ_MASK) : 0; +} + +static int pirq_sis497_set(struct pci_dev *router, struct pci_dev *dev, + int pirq, int irq) +{ + int reg; + u8 x; + + reg = pirq; + if (reg >= 1 && reg <= 4) + reg += PCI_SIS497_INTA_TO_IRQ_LINK - 1; + + pci_read_config_byte(router, reg, &x); + x &= ~(PIRQ_SIS497_IRQ_MASK | PIRQ_SIS497_IRQ_ENABLE); + x |= irq ? (PIRQ_SIS497_IRQ_ENABLE | irq) : PIRQ_SIS497_IRQ_MASK; + pci_write_config_byte(router, reg, x); + return 1; +} + /* * PIRQ routing for SiS 85C503 router used in several SiS chipsets. * We have to deal with the following issues here: @@ -640,11 +812,12 @@ static int pirq_cyrix_set(struct pci_dev *router, struct pci_dev *dev, int pirq, * bit 6-4 are probably unused, not like 5595 */ -#define PIRQ_SIS_IRQ_MASK 0x0f -#define PIRQ_SIS_IRQ_DISABLE 0x80 -#define PIRQ_SIS_USB_ENABLE 0x40 +#define PIRQ_SIS503_IRQ_MASK 0x0f +#define PIRQ_SIS503_IRQ_DISABLE 0x80 +#define PIRQ_SIS503_USB_ENABLE 0x40 -static int pirq_sis_get(struct pci_dev *router, struct pci_dev *dev, int pirq) +static int pirq_sis503_get(struct pci_dev *router, struct pci_dev *dev, + int pirq) { u8 x; int reg; @@ -653,10 +826,11 @@ static int pirq_sis_get(struct pci_dev *router, struct pci_dev *dev, int pirq) if (reg >= 0x01 && reg <= 0x04) reg += 0x40; pci_read_config_byte(router, reg, &x); - return (x & PIRQ_SIS_IRQ_DISABLE) ? 0 : (x & PIRQ_SIS_IRQ_MASK); + return (x & PIRQ_SIS503_IRQ_DISABLE) ? 0 : (x & PIRQ_SIS503_IRQ_MASK); } -static int pirq_sis_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq) +static int pirq_sis503_set(struct pci_dev *router, struct pci_dev *dev, + int pirq, int irq) { u8 x; int reg; @@ -665,8 +839,8 @@ static int pirq_sis_set(struct pci_dev *router, struct pci_dev *dev, int pirq, i if (reg >= 0x01 && reg <= 0x04) reg += 0x40; pci_read_config_byte(router, reg, &x); - x &= ~(PIRQ_SIS_IRQ_MASK | PIRQ_SIS_IRQ_DISABLE); - x |= irq ? irq: PIRQ_SIS_IRQ_DISABLE; + x &= ~(PIRQ_SIS503_IRQ_MASK | PIRQ_SIS503_IRQ_DISABLE); + x |= irq ? irq : PIRQ_SIS503_IRQ_DISABLE; pci_write_config_byte(router, reg, x); return 1; } @@ -958,13 +1132,19 @@ static __init int serverworks_router_probe(struct irq_router *r, static __init int sis_router_probe(struct irq_router *r, struct pci_dev *router, u16 device) { - if (device != PCI_DEVICE_ID_SI_503) - return 0; - - r->name = "SIS"; - r->get = pirq_sis_get; - r->set = pirq_sis_set; - return 1; + switch (device) { + case PCI_DEVICE_ID_SI_496: + r->name = "SiS85C497"; + r->get = pirq_sis497_get; + r->set = pirq_sis497_set; + return 1; + case PCI_DEVICE_ID_SI_503: + r->name = "SiS85C503"; + r->get = pirq_sis503_get; + r->set = pirq_sis503_set; + return 1; + } + return 0; } static __init int cyrix_router_probe(struct irq_router *r, struct pci_dev *router, u16 device) @@ -1084,10 +1264,32 @@ static struct pci_dev *pirq_router_dev; * chipset" ? */ +static bool __init pirq_try_router(struct irq_router *r, + struct irq_routing_table *rt, + struct pci_dev *dev) +{ + struct irq_router_handler *h; + + DBG(KERN_DEBUG "PCI: Trying IRQ router for [%04x:%04x]\n", + dev->vendor, dev->device); + + for (h = pirq_routers; h->vendor; h++) { + /* First look for a router match */ + if (rt->rtr_vendor == h->vendor && + h->probe(r, dev, rt->rtr_device)) + return true; + /* Fall back to a device match */ + if (dev->vendor == h->vendor && + h->probe(r, dev, dev->device)) + return true; + } + return false; +} + static void __init pirq_find_router(struct irq_router *r) { struct irq_routing_table *rt = pirq_table; - struct irq_router_handler *h; + struct pci_dev *dev; #ifdef CONFIG_PCI_BIOS if (!rt->signature) { @@ -1106,50 +1308,94 @@ static void __init pirq_find_router(struct irq_router *r) DBG(KERN_DEBUG "PCI: Attempting to find IRQ router for [%04x:%04x]\n", rt->rtr_vendor, rt->rtr_device); - pirq_router_dev = pci_get_domain_bus_and_slot(0, rt->rtr_bus, - rt->rtr_devfn); - if (!pirq_router_dev) { - DBG(KERN_DEBUG "PCI: Interrupt router not found at " - "%02x:%02x\n", rt->rtr_bus, rt->rtr_devfn); - return; + /* Use any vendor:device provided by the routing table or try all. */ + if (rt->rtr_vendor) { + dev = pci_get_domain_bus_and_slot(0, rt->rtr_bus, + rt->rtr_devfn); + if (dev && pirq_try_router(r, rt, dev)) + pirq_router_dev = dev; + } else { + dev = NULL; + for_each_pci_dev(dev) { + if (pirq_try_router(r, rt, dev)) { + pirq_router_dev = dev; + break; + } + } } - for (h = pirq_routers; h->vendor; h++) { - /* First look for a router match */ - if (rt->rtr_vendor == h->vendor && - h->probe(r, pirq_router_dev, rt->rtr_device)) - break; - /* Fall back to a device match */ - if (pirq_router_dev->vendor == h->vendor && - h->probe(r, pirq_router_dev, pirq_router_dev->device)) - break; - } - dev_info(&pirq_router_dev->dev, "%s IRQ router [%04x:%04x]\n", - pirq_router.name, - pirq_router_dev->vendor, pirq_router_dev->device); + if (pirq_router_dev) + dev_info(&pirq_router_dev->dev, "%s IRQ router [%04x:%04x]\n", + pirq_router.name, + pirq_router_dev->vendor, pirq_router_dev->device); + else + DBG(KERN_DEBUG "PCI: Interrupt router not found at " + "%02x:%02x\n", rt->rtr_bus, rt->rtr_devfn); /* The device remains referenced for the kernel lifetime */ } -static struct irq_info *pirq_get_info(struct pci_dev *dev) +/* + * We're supposed to match on the PCI device only and not the function, + * but some BIOSes build their tables with the PCI function included + * for motherboard devices, so if a complete match is found, then give + * it precedence over a slot match. + */ +static struct irq_info *pirq_get_dev_info(struct pci_dev *dev) { struct irq_routing_table *rt = pirq_table; int entries = (rt->size - sizeof(struct irq_routing_table)) / sizeof(struct irq_info); + struct irq_info *slotinfo = NULL; struct irq_info *info; for (info = rt->slots; entries--; info++) - if (info->bus == dev->bus->number && - PCI_SLOT(info->devfn) == PCI_SLOT(dev->devfn)) - return info; - return NULL; + if (info->bus == dev->bus->number) { + if (info->devfn == dev->devfn) + return info; + if (!slotinfo && + PCI_SLOT(info->devfn) == PCI_SLOT(dev->devfn)) + slotinfo = info; + } + return slotinfo; +} + +/* + * Buses behind bridges are typically not listed in the PIRQ routing table. + * Do the usual dance then and walk the tree of bridges up adjusting the + * pin number accordingly on the way until the originating root bus device + * has been reached and then use its routing information. + */ +static struct irq_info *pirq_get_info(struct pci_dev *dev, u8 *pin) +{ + struct pci_dev *temp_dev = dev; + struct irq_info *info; + u8 temp_pin = *pin; + u8 dpin = temp_pin; + + info = pirq_get_dev_info(dev); + while (!info && temp_dev->bus->parent) { + struct pci_dev *bridge = temp_dev->bus->self; + + temp_pin = pci_swizzle_interrupt_pin(temp_dev, temp_pin); + info = pirq_get_dev_info(bridge); + if (info) + dev_warn(&dev->dev, + "using bridge %s INT %c to get INT %c\n", + pci_name(bridge), + 'A' + temp_pin - 1, 'A' + dpin - 1); + + temp_dev = bridge; + } + *pin = temp_pin; + return info; } static int pcibios_lookup_irq(struct pci_dev *dev, int assign) { - u8 pin; struct irq_info *info; int i, pirq, newirq; + u8 dpin, pin; int irq = 0; u32 mask; struct irq_router *r = &pirq_router; @@ -1157,8 +1403,8 @@ static int pcibios_lookup_irq(struct pci_dev *dev, int assign) char *msg = NULL; /* Find IRQ pin */ - pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &pin); - if (!pin) { + pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &dpin); + if (!dpin) { dev_dbg(&dev->dev, "no interrupt pin\n"); return 0; } @@ -1171,20 +1417,21 @@ static int pcibios_lookup_irq(struct pci_dev *dev, int assign) if (!pirq_table) return 0; - info = pirq_get_info(dev); + pin = dpin; + info = pirq_get_info(dev, &pin); if (!info) { dev_dbg(&dev->dev, "PCI INT %c not found in routing table\n", - 'A' + pin - 1); + 'A' + dpin - 1); return 0; } pirq = info->irq[pin - 1].link; mask = info->irq[pin - 1].bitmap; if (!pirq) { - dev_dbg(&dev->dev, "PCI INT %c not routed\n", 'A' + pin - 1); + dev_dbg(&dev->dev, "PCI INT %c not routed\n", 'A' + dpin - 1); return 0; } dev_dbg(&dev->dev, "PCI INT %c -> PIRQ %02x, mask %04x, excl %04x", - 'A' + pin - 1, pirq, mask, pirq_table->exclusive_irqs); + 'A' + dpin - 1, pirq, mask, pirq_table->exclusive_irqs); mask &= pcibios_irq_mask; /* Work around broken HP Pavilion Notebooks which assign USB to @@ -1226,7 +1473,7 @@ static int pcibios_lookup_irq(struct pci_dev *dev, int assign) newirq = i; } } - dev_dbg(&dev->dev, "PCI INT %c -> newirq %d", 'A' + pin - 1, newirq); + dev_dbg(&dev->dev, "PCI INT %c -> newirq %d", 'A' + dpin - 1, newirq); /* Check if it is hardcoded */ if ((pirq & 0xf0) == 0xf0) { @@ -1260,15 +1507,17 @@ static int pcibios_lookup_irq(struct pci_dev *dev, int assign) return 0; } } - dev_info(&dev->dev, "%s PCI INT %c -> IRQ %d\n", msg, 'A' + pin - 1, irq); + dev_info(&dev->dev, "%s PCI INT %c -> IRQ %d\n", + msg, 'A' + dpin - 1, irq); /* Update IRQ for all devices with the same pirq value */ for_each_pci_dev(dev2) { - pci_read_config_byte(dev2, PCI_INTERRUPT_PIN, &pin); - if (!pin) + pci_read_config_byte(dev2, PCI_INTERRUPT_PIN, &dpin); + if (!dpin) continue; - info = pirq_get_info(dev2); + pin = dpin; + info = pirq_get_info(dev2, &pin); if (!info) continue; if (info->irq[pin - 1].link == pirq) { diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index 9bb1e2941179..b94f727251b6 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -467,7 +467,6 @@ static __init void xen_setup_pci_msi(void) else xen_msi_ops.setup_msi_irqs = xen_setup_msi_irqs; xen_msi_ops.teardown_msi_irqs = xen_pv_teardown_msi_irqs; - pci_msi_ignore_mask = 1; } else if (xen_hvm_domain()) { xen_msi_ops.setup_msi_irqs = xen_hvm_setup_msi_irqs; xen_msi_ops.teardown_msi_irqs = xen_teardown_msi_irqs; @@ -481,6 +480,11 @@ static __init void xen_setup_pci_msi(void) * in allocating the native domain and never use it. */ x86_init.irqs.create_pci_msi_domain = xen_create_pci_msi_domain; + /* + * With XEN PIRQ/Eventchannels in use PCI/MSI[-X] masking is solely + * controlled by the hypervisor. + */ + pci_msi_ignore_mask = 1; } #else /* CONFIG_PCI_MSI */ diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index 147c30a81f15..1591d67e0bcd 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -93,6 +93,9 @@ static const unsigned long * const efi_tables[] = { #ifdef CONFIG_LOAD_UEFI_KEYS &efi.mokvar_table, #endif +#ifdef CONFIG_EFI_COCO_SECRET + &efi.coco_secret, +#endif }; u64 efi_setup; /* efi setup_data physical address */ diff --git a/arch/x86/platform/pvh/head.S b/arch/x86/platform/pvh/head.S index 72c1e42d121d..7fe564eaf228 100644 --- a/arch/x86/platform/pvh/head.S +++ b/arch/x86/platform/pvh/head.S @@ -50,6 +50,7 @@ #define PVH_DS_SEL (PVH_GDT_ENTRY_DS * 8) SYM_CODE_START_LOCAL(pvh_start_xen) + UNWIND_HINT_EMPTY cld lgdt (_pa(gdt)) diff --git a/arch/x86/platform/uv/uv_nmi.c b/arch/x86/platform/uv/uv_nmi.c index 1e9ff28bc2e0..a60af0230e27 100644 --- a/arch/x86/platform/uv/uv_nmi.c +++ b/arch/x86/platform/uv/uv_nmi.c @@ -244,8 +244,10 @@ static inline bool uv_nmi_action_is(const char *action) /* Setup which NMI support is present in system */ static void uv_nmi_setup_mmrs(void) { + bool new_nmi_method_only = false; + /* First determine arch specific MMRs to handshake with BIOS */ - if (UVH_EVENT_OCCURRED0_EXTIO_INT0_MASK) { + if (UVH_EVENT_OCCURRED0_EXTIO_INT0_MASK) { /* UV2,3,4 setup */ uvh_nmi_mmrx = UVH_EVENT_OCCURRED0; uvh_nmi_mmrx_clear = UVH_EVENT_OCCURRED0_ALIAS; uvh_nmi_mmrx_shift = UVH_EVENT_OCCURRED0_EXTIO_INT0_SHFT; @@ -255,26 +257,25 @@ static void uv_nmi_setup_mmrs(void) uvh_nmi_mmrx_req = UVH_BIOS_KERNEL_MMR_ALIAS_2; uvh_nmi_mmrx_req_shift = 62; - } else if (UVH_EVENT_OCCURRED1_EXTIO_INT0_MASK) { + } else if (UVH_EVENT_OCCURRED1_EXTIO_INT0_MASK) { /* UV5+ setup */ uvh_nmi_mmrx = UVH_EVENT_OCCURRED1; uvh_nmi_mmrx_clear = UVH_EVENT_OCCURRED1_ALIAS; uvh_nmi_mmrx_shift = UVH_EVENT_OCCURRED1_EXTIO_INT0_SHFT; uvh_nmi_mmrx_type = "OCRD1-EXTIO_INT0"; - uvh_nmi_mmrx_supported = UVH_EXTIO_INT0_BROADCAST; - uvh_nmi_mmrx_req = UVH_BIOS_KERNEL_MMR_ALIAS_2; - uvh_nmi_mmrx_req_shift = 62; + new_nmi_method_only = true; /* Newer nmi always valid on UV5+ */ + uvh_nmi_mmrx_req = 0; /* no request bit to clear */ } else { - pr_err("UV:%s:cannot find EVENT_OCCURRED*_EXTIO_INT0\n", - __func__); + pr_err("UV:%s:NMI support not available on this system\n", __func__); return; } /* Then find out if new NMI is supported */ - if (likely(uv_read_local_mmr(uvh_nmi_mmrx_supported))) { - uv_write_local_mmr(uvh_nmi_mmrx_req, - 1UL << uvh_nmi_mmrx_req_shift); + if (new_nmi_method_only || uv_read_local_mmr(uvh_nmi_mmrx_supported)) { + if (uvh_nmi_mmrx_req) + uv_write_local_mmr(uvh_nmi_mmrx_req, + 1UL << uvh_nmi_mmrx_req_shift); nmi_mmr = uvh_nmi_mmrx; nmi_mmr_clear = uvh_nmi_mmrx_clear; nmi_mmr_pending = 1UL << uvh_nmi_mmrx_shift; @@ -985,7 +986,7 @@ static int uv_handle_nmi(unsigned int reason, struct pt_regs *regs) /* Clear global flags */ if (master) { - if (cpumask_weight(uv_nmi_cpu_mask)) + if (!cpumask_empty(uv_nmi_cpu_mask)) uv_nmi_cleanup_mask(); atomic_set(&uv_nmi_cpus_in_nmi, -1); atomic_set(&uv_nmi_cpu, -1); diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index 9f2b251e83c5..bb176c72891c 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -25,6 +25,7 @@ #include <asm/cpu.h> #include <asm/mmu_context.h> #include <asm/cpu_device_id.h> +#include <asm/microcode.h> #ifdef CONFIG_X86_32 __visible unsigned long saved_context_ebx; @@ -40,7 +41,8 @@ static void msr_save_context(struct saved_context *ctxt) struct saved_msr *end = msr + ctxt->saved_msrs.num; while (msr < end) { - msr->valid = !rdmsrl_safe(msr->info.msr_no, &msr->info.reg.q); + if (msr->valid) + rdmsrl(msr->info.msr_no, msr->info.reg.q); msr++; } } @@ -261,11 +263,18 @@ static void notrace __restore_processor_state(struct saved_context *ctxt) x86_platform.restore_sched_clock_state(); mtrr_bp_restore(); perf_restore_debug_store(); - msr_restore_context(ctxt); c = &cpu_data(smp_processor_id()); if (cpu_has(c, X86_FEATURE_MSR_IA32_FEAT_CTL)) init_ia32_feat_ctl(c); + + microcode_bsp_resume(); + + /* + * This needs to happen after the microcode has been updated upon resume + * because some of the MSRs are "emulated" in microcode. + */ + msr_restore_context(ctxt); } /* Needed by apm.c */ @@ -424,8 +433,10 @@ static int msr_build_context(const u32 *msr_id, const int num) } for (i = saved_msrs->num, j = 0; i < total_num; i++, j++) { + u64 dummy; + msr_array[i].info.msr_no = msr_id[j]; - msr_array[i].valid = false; + msr_array[i].valid = !rdmsrl_safe(msr_id[j], &dummy); msr_array[i].info.reg.q = 0; } saved_msrs->num = total_num; @@ -500,10 +511,24 @@ static int pm_cpu_check(const struct x86_cpu_id *c) return ret; } +static void pm_save_spec_msr(void) +{ + u32 spec_msr_id[] = { + MSR_IA32_SPEC_CTRL, + MSR_IA32_TSX_CTRL, + MSR_TSX_FORCE_ABORT, + MSR_IA32_MCU_OPT_CTRL, + MSR_AMD64_LS_CFG, + }; + + msr_build_context(spec_msr_id, ARRAY_SIZE(spec_msr_id)); +} + static int pm_check_save_msr(void) { dmi_check_system(msr_save_dmi_table); pm_cpu_check(msr_save_cpu_table); + pm_save_spec_msr(); return 0; } diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c index c5e29db02a46..41d7669a97ad 100644 --- a/arch/x86/realmode/init.c +++ b/arch/x86/realmode/init.c @@ -67,7 +67,7 @@ void __init reserve_real_mode(void) memblock_reserve(0, SZ_1M); } -static void sme_sev_setup_real_mode(struct trampoline_header *th) +static void __init sme_sev_setup_real_mode(struct trampoline_header *th) { #ifdef CONFIG_AMD_MEM_ENCRYPT if (cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT)) diff --git a/arch/x86/realmode/rm/header.S b/arch/x86/realmode/rm/header.S index 8c1db5bf5d78..2eb62be6d256 100644 --- a/arch/x86/realmode/rm/header.S +++ b/arch/x86/realmode/rm/header.S @@ -24,6 +24,7 @@ SYM_DATA_START(real_mode_header) .long pa_sev_es_trampoline_start #endif #ifdef CONFIG_X86_64 + .long pa_trampoline_start64 .long pa_trampoline_pgd; #endif /* ACPI S3 wakeup */ diff --git a/arch/x86/realmode/rm/trampoline_64.S b/arch/x86/realmode/rm/trampoline_64.S index cc8391f86cdb..e38d61d6562e 100644 --- a/arch/x86/realmode/rm/trampoline_64.S +++ b/arch/x86/realmode/rm/trampoline_64.S @@ -70,7 +70,7 @@ SYM_CODE_START(trampoline_start) movw $__KERNEL_DS, %dx # Data segment descriptor # Enable protected mode - movl $X86_CR0_PE, %eax # protected mode (PE) bit + movl $(CR0_STATE & ~X86_CR0_PG), %eax movl %eax, %cr0 # into protected mode # flush prefetch and jump to startup_32 @@ -143,13 +143,24 @@ SYM_CODE_START(startup_32) movl %eax, %cr3 # Set up EFER + movl $MSR_EFER, %ecx + rdmsr + /* + * Skip writing to EFER if the register already has desired + * value (to avoid #VE for the TDX guest). + */ + cmp pa_tr_efer, %eax + jne .Lwrite_efer + cmp pa_tr_efer + 4, %edx + je .Ldone_efer +.Lwrite_efer: movl pa_tr_efer, %eax movl pa_tr_efer + 4, %edx - movl $MSR_EFER, %ecx wrmsr - # Enable paging and in turn activate Long Mode - movl $(X86_CR0_PG | X86_CR0_WP | X86_CR0_PE), %eax +.Ldone_efer: + # Enable paging and in turn activate Long Mode. + movl $CR0_STATE, %eax movl %eax, %cr0 /* @@ -161,6 +172,19 @@ SYM_CODE_START(startup_32) ljmpl $__KERNEL_CS, $pa_startup_64 SYM_CODE_END(startup_32) +SYM_CODE_START(pa_trampoline_compat) + /* + * In compatibility mode. Prep ESP and DX for startup_32, then disable + * paging and complete the switch to legacy 32-bit mode. + */ + movl $rm_stack_end, %esp + movw $__KERNEL_DS, %dx + + movl $(CR0_STATE & ~X86_CR0_PG), %eax + movl %eax, %cr0 + ljmpl $__KERNEL32_CS, $pa_startup_32 +SYM_CODE_END(pa_trampoline_compat) + .section ".text64","ax" .code64 .balign 4 @@ -169,6 +193,20 @@ SYM_CODE_START(startup_64) jmpq *tr_start(%rip) SYM_CODE_END(startup_64) +SYM_CODE_START(trampoline_start64) + /* + * APs start here on a direct transfer from 64-bit BIOS with identity + * mapped page tables. Load the kernel's GDT in order to gear down to + * 32-bit mode (to handle 4-level vs. 5-level paging), and to (re)load + * segment registers. Load the zero IDT so any fault triggers a + * shutdown instead of jumping back into BIOS. + */ + lidt tr_idt(%rip) + lgdt tr_gdt64(%rip) + + ljmpl *tr_compat(%rip) +SYM_CODE_END(trampoline_start64) + .section ".rodata","a" # Duplicate the global descriptor table # so the kernel can live anywhere @@ -182,6 +220,17 @@ SYM_DATA_START(tr_gdt) .quad 0x00cf93000000ffff # __KERNEL_DS SYM_DATA_END_LABEL(tr_gdt, SYM_L_LOCAL, tr_gdt_end) +SYM_DATA_START(tr_gdt64) + .short tr_gdt_end - tr_gdt - 1 # gdt limit + .long pa_tr_gdt + .long 0 +SYM_DATA_END(tr_gdt64) + +SYM_DATA_START(tr_compat) + .long pa_trampoline_compat + .short __KERNEL32_CS +SYM_DATA_END(tr_compat) + .bss .balign PAGE_SIZE SYM_DATA(trampoline_pgd, .space PAGE_SIZE) diff --git a/arch/x86/realmode/rm/trampoline_common.S b/arch/x86/realmode/rm/trampoline_common.S index 5033e640f957..4331c32c47f8 100644 --- a/arch/x86/realmode/rm/trampoline_common.S +++ b/arch/x86/realmode/rm/trampoline_common.S @@ -1,4 +1,14 @@ /* SPDX-License-Identifier: GPL-2.0 */ .section ".rodata","a" .balign 16 -SYM_DATA_LOCAL(tr_idt, .fill 1, 6, 0) + +/* + * When a bootloader hands off to the kernel in 32-bit mode an + * IDT with a 2-byte limit and 4-byte base is needed. When a boot + * loader hands off to a kernel 64-bit mode the base address + * extends to 8-bytes. Reserve enough space for either scenario. + */ +SYM_DATA_START_LOCAL(tr_idt) + .short 0 + .quad 0 +SYM_DATA_END(tr_idt) diff --git a/arch/x86/realmode/rm/wakemain.c b/arch/x86/realmode/rm/wakemain.c index 1d6437e6d2ba..a6f4d8388ad8 100644 --- a/arch/x86/realmode/rm/wakemain.c +++ b/arch/x86/realmode/rm/wakemain.c @@ -62,8 +62,12 @@ static void send_morse(const char *pattern) } } +struct port_io_ops pio_ops; + void main(void) { + init_default_io_ops(); + /* Kill machine if structures are wrong */ if (wakeup_header.real_magic != 0x12345678) while (1) diff --git a/arch/x86/virt/vmx/tdx/tdxcall.S b/arch/x86/virt/vmx/tdx/tdxcall.S new file mode 100644 index 000000000000..49a54356ae99 --- /dev/null +++ b/arch/x86/virt/vmx/tdx/tdxcall.S @@ -0,0 +1,96 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <asm/asm-offsets.h> +#include <asm/tdx.h> + +/* + * TDCALL and SEAMCALL are supported in Binutils >= 2.36. + */ +#define tdcall .byte 0x66,0x0f,0x01,0xcc +#define seamcall .byte 0x66,0x0f,0x01,0xcf + +/* + * TDX_MODULE_CALL - common helper macro for both + * TDCALL and SEAMCALL instructions. + * + * TDCALL - used by TDX guests to make requests to the + * TDX module and hypercalls to the VMM. + * SEAMCALL - used by TDX hosts to make requests to the + * TDX module. + */ +.macro TDX_MODULE_CALL host:req + /* + * R12 will be used as temporary storage for struct tdx_module_output + * pointer. Since R12-R15 registers are not used by TDCALL/SEAMCALL + * services supported by this function, it can be reused. + */ + + /* Callee saved, so preserve it */ + push %r12 + + /* + * Push output pointer to stack. + * After the operation, it will be fetched into R12 register. + */ + push %r9 + + /* Mangle function call ABI into TDCALL/SEAMCALL ABI: */ + /* Move Leaf ID to RAX */ + mov %rdi, %rax + /* Move input 4 to R9 */ + mov %r8, %r9 + /* Move input 3 to R8 */ + mov %rcx, %r8 + /* Move input 1 to RCX */ + mov %rsi, %rcx + /* Leave input param 2 in RDX */ + + .if \host + seamcall + /* + * SEAMCALL instruction is essentially a VMExit from VMX root + * mode to SEAM VMX root mode. VMfailInvalid (CF=1) indicates + * that the targeted SEAM firmware is not loaded or disabled, + * or P-SEAMLDR is busy with another SEAMCALL. %rax is not + * changed in this case. + * + * Set %rax to TDX_SEAMCALL_VMFAILINVALID for VMfailInvalid. + * This value will never be used as actual SEAMCALL error code as + * it is from the Reserved status code class. + */ + jnc .Lno_vmfailinvalid + mov $TDX_SEAMCALL_VMFAILINVALID, %rax +.Lno_vmfailinvalid: + + .else + tdcall + .endif + + /* + * Fetch output pointer from stack to R12 (It is used + * as temporary storage) + */ + pop %r12 + + /* + * Since this macro can be invoked with NULL as an output pointer, + * check if caller provided an output struct before storing output + * registers. + * + * Update output registers, even if the call failed (RAX != 0). + * Other registers may contain details of the failure. + */ + test %r12, %r12 + jz .Lno_output_struct + + /* Copy result registers to output struct: */ + movq %rcx, TDX_MODULE_rcx(%r12) + movq %rdx, TDX_MODULE_rdx(%r12) + movq %r8, TDX_MODULE_r8(%r12) + movq %r9, TDX_MODULE_r9(%r12) + movq %r10, TDX_MODULE_r10(%r12) + movq %r11, TDX_MODULE_r11(%r12) + +.Lno_output_struct: + /* Restore the state of R12 register */ + pop %r12 +.endm diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index 5038edb79ad5..ca85d1409917 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -30,7 +30,6 @@ #include <linux/pci.h> #include <linux/gfp.h> #include <linux/edd.h> -#include <linux/objtool.h> #include <xen/xen.h> #include <xen/events.h> @@ -165,7 +164,6 @@ static void xen_cpuid(unsigned int *ax, unsigned int *bx, *bx &= maskebx; } -STACK_FRAME_NON_STANDARD(xen_cpuid); /* XEN_EMULATE_PREFIX */ static bool __init xen_check_mwait(void) { diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c index 688aa8b6ae29..ba7af2eca755 100644 --- a/arch/x86/xen/smp_pv.c +++ b/arch/x86/xen/smp_pv.c @@ -260,8 +260,11 @@ cpu_initialize_context(unsigned int cpu, struct task_struct *idle) return 0; ctxt = kzalloc(sizeof(*ctxt), GFP_KERNEL); - if (ctxt == NULL) + if (ctxt == NULL) { + cpumask_clear_cpu(cpu, xen_cpu_initialized_map); + cpumask_clear_cpu(cpu, cpu_callout_mask); return -ENOMEM; + } gdt = get_cpu_gdt_rw(cpu); diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S index ac17196e2518..3a2cd93bf059 100644 --- a/arch/x86/xen/xen-head.S +++ b/arch/x86/xen/xen-head.S @@ -45,6 +45,7 @@ SYM_CODE_END(hypercall_page) __INIT SYM_CODE_START(startup_xen) UNWIND_HINT_EMPTY + ANNOTATE_NOENDBR cld /* Clear .bss */ diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig index bd113bc6e192..0b0f0172cced 100644 --- a/arch/xtensa/Kconfig +++ b/arch/xtensa/Kconfig @@ -4,6 +4,7 @@ config XTENSA select ARCH_32BIT_OFF_T select ARCH_HAS_BINFMT_FLAT if !MMU select ARCH_HAS_CURRENT_STACK_POINTER + select ARCH_HAS_DEBUG_VM_PGTABLE select ARCH_HAS_DMA_PREP_COHERENT if MMU select ARCH_HAS_SYNC_DMA_FOR_CPU if MMU select ARCH_HAS_SYNC_DMA_FOR_DEVICE if MMU @@ -29,8 +30,10 @@ config XTENSA select HAVE_ARCH_AUDITSYSCALL select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL select HAVE_ARCH_KASAN if MMU && !XIP_KERNEL + select HAVE_ARCH_KCSAN select HAVE_ARCH_SECCOMP_FILTER select HAVE_ARCH_TRACEHOOK + select HAVE_CONTEXT_TRACKING select HAVE_DEBUG_KMEMLEAK select HAVE_DMA_CONTIGUOUS select HAVE_EXIT_THREAD @@ -42,6 +45,7 @@ config XTENSA select HAVE_PERF_EVENTS select HAVE_STACKPROTECTOR select HAVE_SYSCALL_TRACEPOINTS + select HAVE_VIRT_CPU_ACCOUNTING_GEN select IRQ_DOMAIN select MODULES_USE_ELF_RELA select PERF_USE_VMALLOC @@ -79,6 +83,7 @@ config STACKTRACE_SUPPORT config MMU def_bool n + select PFAULT config HAVE_XTENSA_GPIO32 def_bool n @@ -178,6 +183,16 @@ config XTENSA_FAKE_NMI If unsure, say N. +config PFAULT + bool "Handle protection faults" if EXPERT && !MMU + default y + help + Handle protection faults. MMU configurations must enable it. + noMMU configurations may disable it if used memory map never + generates protection faults or faults are always fatal. + + If unsure, say Y. + config XTENSA_UNALIGNED_USER bool "Unaligned memory access in user space" help @@ -773,6 +788,9 @@ endmenu menu "Power management options" +config ARCH_HIBERNATION_POSSIBLE + def_bool y + source "kernel/power/Kconfig" endmenu diff --git a/arch/xtensa/boot/lib/Makefile b/arch/xtensa/boot/lib/Makefile index e3d717c7bfa1..162d10af36f3 100644 --- a/arch/xtensa/boot/lib/Makefile +++ b/arch/xtensa/boot/lib/Makefile @@ -16,6 +16,7 @@ CFLAGS_REMOVE_inffast.o = -pg endif KASAN_SANITIZE := n +KCSAN_SANITIZE := n CFLAGS_REMOVE_inflate.o += -fstack-protector -fstack-protector-strong CFLAGS_REMOVE_zmem.o += -fstack-protector -fstack-protector-strong diff --git a/arch/xtensa/include/asm/barrier.h b/arch/xtensa/include/asm/barrier.h index d6f8d4ddc2bc..898ea397e9bc 100644 --- a/arch/xtensa/include/asm/barrier.h +++ b/arch/xtensa/include/asm/barrier.h @@ -11,9 +11,15 @@ #include <asm/core.h> -#define mb() ({ __asm__ __volatile__("memw" : : : "memory"); }) -#define rmb() barrier() -#define wmb() mb() +#define __mb() ({ __asm__ __volatile__("memw" : : : "memory"); }) +#define __rmb() barrier() +#define __wmb() __mb() + +#ifdef CONFIG_SMP +#define __smp_mb() __mb() +#define __smp_rmb() __rmb() +#define __smp_wmb() __wmb() +#endif #if XCHAL_HAVE_S32C1I #define __smp_mb__before_atomic() barrier() diff --git a/arch/xtensa/include/asm/bitops.h b/arch/xtensa/include/asm/bitops.h index cd225896c40f..e02ec5833389 100644 --- a/arch/xtensa/include/asm/bitops.h +++ b/arch/xtensa/include/asm/bitops.h @@ -99,7 +99,7 @@ static inline unsigned long __fls(unsigned long word) #if XCHAL_HAVE_EXCLUSIVE #define BIT_OP(op, insn, inv) \ -static inline void op##_bit(unsigned int bit, volatile unsigned long *p)\ +static inline void arch_##op##_bit(unsigned int bit, volatile unsigned long *p)\ { \ unsigned long tmp; \ unsigned long mask = 1UL << (bit & 31); \ @@ -119,7 +119,7 @@ static inline void op##_bit(unsigned int bit, volatile unsigned long *p)\ #define TEST_AND_BIT_OP(op, insn, inv) \ static inline int \ -test_and_##op##_bit(unsigned int bit, volatile unsigned long *p) \ +arch_test_and_##op##_bit(unsigned int bit, volatile unsigned long *p) \ { \ unsigned long tmp, value; \ unsigned long mask = 1UL << (bit & 31); \ @@ -142,7 +142,7 @@ test_and_##op##_bit(unsigned int bit, volatile unsigned long *p) \ #elif XCHAL_HAVE_S32C1I #define BIT_OP(op, insn, inv) \ -static inline void op##_bit(unsigned int bit, volatile unsigned long *p)\ +static inline void arch_##op##_bit(unsigned int bit, volatile unsigned long *p)\ { \ unsigned long tmp, value; \ unsigned long mask = 1UL << (bit & 31); \ @@ -163,7 +163,7 @@ static inline void op##_bit(unsigned int bit, volatile unsigned long *p)\ #define TEST_AND_BIT_OP(op, insn, inv) \ static inline int \ -test_and_##op##_bit(unsigned int bit, volatile unsigned long *p) \ +arch_test_and_##op##_bit(unsigned int bit, volatile unsigned long *p) \ { \ unsigned long tmp, value; \ unsigned long mask = 1UL << (bit & 31); \ @@ -205,6 +205,8 @@ BIT_OPS(change, "xor", ) #undef BIT_OP #undef TEST_AND_BIT_OP +#include <asm-generic/bitops/instrumented-atomic.h> + #include <asm-generic/bitops/le.h> #include <asm-generic/bitops/ext2-atomic-setbit.h> diff --git a/arch/xtensa/include/asm/coprocessor.h b/arch/xtensa/include/asm/coprocessor.h index 0fbe2a740b8d..3b1a0d5d2169 100644 --- a/arch/xtensa/include/asm/coprocessor.h +++ b/arch/xtensa/include/asm/coprocessor.h @@ -142,11 +142,12 @@ typedef struct { XCHAL_CP6_SA_LIST(2) } xtregs_cp6_t typedef struct { XCHAL_CP7_SA_LIST(2) } xtregs_cp7_t __attribute__ ((aligned (XCHAL_CP7_SA_ALIGN))); -extern struct thread_info* coprocessor_owner[XCHAL_CP_MAX]; -extern void coprocessor_flush(struct thread_info*, int); - -extern void coprocessor_release_all(struct thread_info*); -extern void coprocessor_flush_all(struct thread_info*); +struct thread_info; +void coprocessor_flush(struct thread_info *ti, int cp_index); +void coprocessor_release_all(struct thread_info *ti); +void coprocessor_flush_all(struct thread_info *ti); +void coprocessor_flush_release_all(struct thread_info *ti); +void local_coprocessors_flush_release_all(void); #endif /* XTENSA_HAVE_COPROCESSORS */ diff --git a/arch/xtensa/include/asm/processor.h b/arch/xtensa/include/asm/processor.h index 4489a27d527a..76bc63127c66 100644 --- a/arch/xtensa/include/asm/processor.h +++ b/arch/xtensa/include/asm/processor.h @@ -246,6 +246,13 @@ extern unsigned long __get_wchan(struct task_struct *p); v; \ }) +#define xtensa_xsr(x, sr) \ + ({ \ + unsigned int __v__ = (unsigned int)(x); \ + __asm__ __volatile__ ("xsr %0, " __stringify(sr) : "+a"(__v__)); \ + __v__; \ + }) + #if XCHAL_HAVE_EXTERN_REGS static inline void set_er(unsigned long value, unsigned long addr) diff --git a/arch/xtensa/include/asm/sections.h b/arch/xtensa/include/asm/sections.h index a8c42d08e281..3bc6b9afa993 100644 --- a/arch/xtensa/include/asm/sections.h +++ b/arch/xtensa/include/asm/sections.h @@ -29,7 +29,7 @@ extern char _Level5InterruptVector_text_end[]; extern char _Level6InterruptVector_text_start[]; extern char _Level6InterruptVector_text_end[]; #endif -#ifdef CONFIG_SMP +#ifdef CONFIG_SECONDARY_RESET_VECTOR extern char _SecondaryResetVector_text_start[]; extern char _SecondaryResetVector_text_end[]; #endif diff --git a/arch/xtensa/include/asm/thread_info.h b/arch/xtensa/include/asm/thread_info.h index f6fcbba1d02f..326db1c1d5d8 100644 --- a/arch/xtensa/include/asm/thread_info.h +++ b/arch/xtensa/include/asm/thread_info.h @@ -52,12 +52,21 @@ struct thread_info { __u32 cpu; /* current CPU */ __s32 preempt_count; /* 0 => preemptable,< 0 => BUG*/ - unsigned long cpenable; #if XCHAL_HAVE_EXCLUSIVE /* result of the most recent exclusive store */ unsigned long atomctl8; #endif +#ifdef CONFIG_USER_ABI_CALL0_PROBE + /* Address where PS.WOE was enabled by the ABI probing code */ + unsigned long ps_woe_fix_addr; +#endif + /* + * If i-th bit is set then coprocessor state is loaded into the + * coprocessor i on CPU cp_owner_cpu. + */ + unsigned long cpenable; + u32 cp_owner_cpu; /* Allocate storage for extra user states and coprocessor states. */ #if XTENSA_HAVE_COPROCESSORS xtregs_coprocessor_t xtregs_cp; diff --git a/arch/xtensa/include/asm/timex.h b/arch/xtensa/include/asm/timex.h index 233ec75e60c6..3f2462f2d027 100644 --- a/arch/xtensa/include/asm/timex.h +++ b/arch/xtensa/include/asm/timex.h @@ -29,10 +29,6 @@ extern unsigned long ccount_freq; -typedef unsigned long long cycles_t; - -#define get_cycles() (0) - void local_timer_setup(unsigned cpu); /* @@ -59,4 +55,6 @@ static inline void set_linux_timer (unsigned long ccompare) xtensa_set_sr(ccompare, SREG_CCOMPARE + LINUX_TIMER); } +#include <asm-generic/timex.h> + #endif /* _XTENSA_TIMEX_H */ diff --git a/arch/xtensa/include/asm/traps.h b/arch/xtensa/include/asm/traps.h index 6fa47cd8e02d..6f74ccc0c7ea 100644 --- a/arch/xtensa/include/asm/traps.h +++ b/arch/xtensa/include/asm/traps.h @@ -12,6 +12,8 @@ #include <asm/ptrace.h> +typedef void xtensa_exception_handler(struct pt_regs *regs); + /* * Per-CPU exception handling data structure. * EXCSAVE1 points to it. @@ -25,31 +27,47 @@ struct exc_table { void *fixup; /* For passing a parameter to fixup */ void *fixup_param; +#if XTENSA_HAVE_COPROCESSORS + /* Pointers to owner struct thread_info */ + struct thread_info *coprocessor_owner[XCHAL_CP_MAX]; +#endif /* Fast user exception handlers */ void *fast_user_handler[EXCCAUSE_N]; /* Fast kernel exception handlers */ void *fast_kernel_handler[EXCCAUSE_N]; /* Default C-Handlers */ - void *default_handler[EXCCAUSE_N]; + xtensa_exception_handler *default_handler[EXCCAUSE_N]; }; -/* - * handler must be either of the following: - * void (*)(struct pt_regs *regs); - * void (*)(struct pt_regs *regs, unsigned long exccause); - */ -extern void * __init trap_set_handler(int cause, void *handler); -extern void do_unhandled(struct pt_regs *regs, unsigned long exccause); -void fast_second_level_miss(void); +DECLARE_PER_CPU(struct exc_table, exc_table); + +xtensa_exception_handler * +__init trap_set_handler(int cause, xtensa_exception_handler *handler); + +asmlinkage void fast_illegal_instruction_user(void); +asmlinkage void fast_syscall_user(void); +asmlinkage void fast_alloca(void); +asmlinkage void fast_unaligned(void); +asmlinkage void fast_second_level_miss(void); +asmlinkage void fast_store_prohibited(void); +asmlinkage void fast_coprocessor(void); + +asmlinkage void kernel_exception(void); +asmlinkage void user_exception(void); +asmlinkage void system_call(struct pt_regs *regs); + +void do_IRQ(int hwirq, struct pt_regs *regs); +void do_page_fault(struct pt_regs *regs); +void do_unhandled(struct pt_regs *regs); /* Initialize minimal exc_table structure sufficient for basic paging */ static inline void __init early_trap_init(void) { - static struct exc_table exc_table __initdata = { + static struct exc_table init_exc_table __initdata = { .fast_kernel_handler[EXCCAUSE_DTLB_MISS] = fast_second_level_miss, }; - __asm__ __volatile__("wsr %0, excsave1\n" : : "a" (&exc_table)); + xtensa_set_sr(&init_exc_table, excsave1); } void secondary_trap_init(void); diff --git a/arch/xtensa/kernel/Makefile b/arch/xtensa/kernel/Makefile index 5fd6cd15e0fb..897c1c741058 100644 --- a/arch/xtensa/kernel/Makefile +++ b/arch/xtensa/kernel/Makefile @@ -19,6 +19,7 @@ obj-$(CONFIG_XTENSA_VARIANT_HAVE_PERF_EVENTS) += perf_event.o obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o obj-$(CONFIG_S32C1I_SELFTEST) += s32c1i_selftest.o obj-$(CONFIG_JUMP_LABEL) += jump_label.o +obj-$(CONFIG_HIBERNATION) += hibernate.o # In the Xtensa architecture, assembly generates literals which must always # precede the L32R instruction with a relative offset less than 256 kB. diff --git a/arch/xtensa/kernel/asm-offsets.c b/arch/xtensa/kernel/asm-offsets.c index 37278e2785fb..da38de20ae59 100644 --- a/arch/xtensa/kernel/asm-offsets.c +++ b/arch/xtensa/kernel/asm-offsets.c @@ -21,6 +21,7 @@ #include <linux/ptrace.h> #include <linux/mm.h> #include <linux/kbuild.h> +#include <linux/suspend.h> #include <asm/ptrace.h> #include <asm/traps.h> @@ -87,14 +88,19 @@ int main(void) OFFSET(TI_STSTUS, thread_info, status); OFFSET(TI_CPU, thread_info, cpu); OFFSET(TI_PRE_COUNT, thread_info, preempt_count); +#ifdef CONFIG_USER_ABI_CALL0_PROBE + OFFSET(TI_PS_WOE_FIX_ADDR, thread_info, ps_woe_fix_addr); +#endif /* struct thread_info (offset from start_struct) */ DEFINE(THREAD_RA, offsetof (struct task_struct, thread.ra)); DEFINE(THREAD_SP, offsetof (struct task_struct, thread.sp)); - DEFINE(THREAD_CPENABLE, offsetof (struct thread_info, cpenable)); #if XCHAL_HAVE_EXCLUSIVE DEFINE(THREAD_ATOMCTL8, offsetof (struct thread_info, atomctl8)); #endif + DEFINE(THREAD_CPENABLE, offsetof(struct thread_info, cpenable)); + DEFINE(THREAD_CPU, offsetof(struct thread_info, cpu)); + DEFINE(THREAD_CP_OWNER_CPU, offsetof(struct thread_info, cp_owner_cpu)); #if XTENSA_HAVE_COPROCESSORS DEFINE(THREAD_XTREGS_CP0, offsetof(struct thread_info, xtregs_cp.cp0)); DEFINE(THREAD_XTREGS_CP1, offsetof(struct thread_info, xtregs_cp.cp1)); @@ -137,11 +143,22 @@ int main(void) DEFINE(EXC_TABLE_DOUBLE_SAVE, offsetof(struct exc_table, double_save)); DEFINE(EXC_TABLE_FIXUP, offsetof(struct exc_table, fixup)); DEFINE(EXC_TABLE_PARAM, offsetof(struct exc_table, fixup_param)); +#if XTENSA_HAVE_COPROCESSORS + DEFINE(EXC_TABLE_COPROCESSOR_OWNER, + offsetof(struct exc_table, coprocessor_owner)); +#endif DEFINE(EXC_TABLE_FAST_USER, offsetof(struct exc_table, fast_user_handler)); DEFINE(EXC_TABLE_FAST_KERNEL, offsetof(struct exc_table, fast_kernel_handler)); DEFINE(EXC_TABLE_DEFAULT, offsetof(struct exc_table, default_handler)); +#ifdef CONFIG_HIBERNATION + DEFINE(PBE_ADDRESS, offsetof(struct pbe, address)); + DEFINE(PBE_ORIG_ADDRESS, offsetof(struct pbe, orig_address)); + DEFINE(PBE_NEXT, offsetof(struct pbe, next)); + DEFINE(PBE_SIZE, sizeof(struct pbe)); +#endif + return 0; } diff --git a/arch/xtensa/kernel/coprocessor.S b/arch/xtensa/kernel/coprocessor.S index 45cc0ae0af6f..ef33e76e07d8 100644 --- a/arch/xtensa/kernel/coprocessor.S +++ b/arch/xtensa/kernel/coprocessor.S @@ -19,6 +19,26 @@ #include <asm/current.h> #include <asm/regs.h> +/* + * Rules for coprocessor state manipulation on SMP: + * + * - a task may have live coprocessors only on one CPU. + * + * - whether coprocessor context of task T is live on some CPU is + * denoted by T's thread_info->cpenable. + * + * - non-zero thread_info->cpenable means that thread_info->cp_owner_cpu + * is valid in the T's thread_info. Zero thread_info->cpenable means that + * coprocessor context is valid in the T's thread_info. + * + * - if a coprocessor context of task T is live on CPU X, only CPU X changes + * T's thread_info->cpenable, cp_owner_cpu and coprocessor save area. + * This is done by making sure that for the task T with live coprocessor + * on CPU X cpenable SR is 0 when T runs on any other CPU Y. + * When fast_coprocessor exception is taken on CPU Y it goes to the + * C-level do_coprocessor that uses IPI to make CPU X flush T's coprocessors. + */ + #if XTENSA_HAVE_COPROCESSORS /* @@ -29,35 +49,31 @@ .if XTENSA_HAVE_COPROCESSOR(x); \ .align 4; \ .Lsave_cp_regs_cp##x: \ - xchal_cp##x##_store a2 a4 a5 a6 a7; \ - jx a0; \ + xchal_cp##x##_store a2 a3 a4 a5 a6; \ + ret; \ .endif -#define SAVE_CP_REGS_TAB(x) \ - .if XTENSA_HAVE_COPROCESSOR(x); \ - .long .Lsave_cp_regs_cp##x; \ - .else; \ - .long 0; \ - .endif; \ - .long THREAD_XTREGS_CP##x - - #define LOAD_CP_REGS(x) \ .if XTENSA_HAVE_COPROCESSOR(x); \ .align 4; \ .Lload_cp_regs_cp##x: \ - xchal_cp##x##_load a2 a4 a5 a6 a7; \ - jx a0; \ + xchal_cp##x##_load a2 a3 a4 a5 a6; \ + ret; \ .endif -#define LOAD_CP_REGS_TAB(x) \ +#define CP_REGS_TAB(x) \ .if XTENSA_HAVE_COPROCESSOR(x); \ + .long .Lsave_cp_regs_cp##x; \ .long .Lload_cp_regs_cp##x; \ .else; \ - .long 0; \ + .long 0, 0; \ .endif; \ .long THREAD_XTREGS_CP##x +#define CP_REGS_TAB_SAVE 0 +#define CP_REGS_TAB_LOAD 4 +#define CP_REGS_TAB_OFFSET 8 + __XTENSA_HANDLER SAVE_CP_REGS(0) @@ -79,25 +95,15 @@ LOAD_CP_REGS(7) .align 4 -.Lsave_cp_regs_jump_table: - SAVE_CP_REGS_TAB(0) - SAVE_CP_REGS_TAB(1) - SAVE_CP_REGS_TAB(2) - SAVE_CP_REGS_TAB(3) - SAVE_CP_REGS_TAB(4) - SAVE_CP_REGS_TAB(5) - SAVE_CP_REGS_TAB(6) - SAVE_CP_REGS_TAB(7) - -.Lload_cp_regs_jump_table: - LOAD_CP_REGS_TAB(0) - LOAD_CP_REGS_TAB(1) - LOAD_CP_REGS_TAB(2) - LOAD_CP_REGS_TAB(3) - LOAD_CP_REGS_TAB(4) - LOAD_CP_REGS_TAB(5) - LOAD_CP_REGS_TAB(6) - LOAD_CP_REGS_TAB(7) +.Lcp_regs_jump_table: + CP_REGS_TAB(0) + CP_REGS_TAB(1) + CP_REGS_TAB(2) + CP_REGS_TAB(3) + CP_REGS_TAB(4) + CP_REGS_TAB(5) + CP_REGS_TAB(6) + CP_REGS_TAB(7) /* * Entry condition: @@ -115,9 +121,37 @@ ENTRY(fast_coprocessor) + s32i a3, a2, PT_AREG3 + +#ifdef CONFIG_SMP + /* + * Check if any coprocessor context is live on another CPU + * and if so go through the C-level coprocessor exception handler + * to flush it to memory. + */ + GET_THREAD_INFO (a0, a2) + l32i a3, a0, THREAD_CPENABLE + beqz a3, .Lload_local + + /* + * Pairs with smp_wmb in local_coprocessor_release_all + * and with both memws below. + */ + memw + l32i a3, a0, THREAD_CPU + l32i a0, a0, THREAD_CP_OWNER_CPU + beq a0, a3, .Lload_local + + rsr a0, ps + l32i a3, a2, PT_AREG3 + bbci.l a0, PS_UM_BIT, 1f + call0 user_exception +1: call0 kernel_exception +#endif + /* Save remaining registers a1-a3 and SAR */ - s32i a3, a2, PT_AREG3 +.Lload_local: rsr a3, sar s32i a1, a2, PT_AREG1 s32i a3, a2, PT_SAR @@ -125,13 +159,15 @@ ENTRY(fast_coprocessor) rsr a2, depc s32i a2, a1, PT_AREG2 - /* - * The hal macros require up to 4 temporary registers. We use a3..a6. - */ + /* The hal macros require up to 4 temporary registers. We use a3..a6. */ s32i a4, a1, PT_AREG4 s32i a5, a1, PT_AREG5 s32i a6, a1, PT_AREG6 + s32i a7, a1, PT_AREG7 + s32i a8, a1, PT_AREG8 + s32i a9, a1, PT_AREG9 + s32i a10, a1, PT_AREG10 /* Find coprocessor number. Subtract first CP EXCCAUSE from EXCCAUSE */ @@ -148,58 +184,74 @@ ENTRY(fast_coprocessor) wsr a0, cpenable rsync - /* Retrieve previous owner. (a3 still holds CP number) */ + /* Get coprocessor save/load table entry (a7). */ - movi a0, coprocessor_owner # list of owners - addx4 a0, a3, a0 # entry for CP - l32i a4, a0, 0 + movi a7, .Lcp_regs_jump_table + addx8 a7, a3, a7 + addx4 a7, a3, a7 - beqz a4, 1f # skip 'save' if no previous owner + /* Retrieve previous owner (a8). */ - /* Disable coprocessor for previous owner. (a2 = 1 << CP number) */ + rsr a0, excsave1 # exc_table + addx4 a0, a3, a0 # entry for CP + l32i a8, a0, EXC_TABLE_COPROCESSOR_OWNER + + /* Set new owner (a9). */ - l32i a5, a4, THREAD_CPENABLE - xor a5, a5, a2 # (1 << cp-id) still in a2 - s32i a5, a4, THREAD_CPENABLE + GET_THREAD_INFO (a9, a1) + l32i a4, a9, THREAD_CPU + s32i a9, a0, EXC_TABLE_COPROCESSOR_OWNER + s32i a4, a9, THREAD_CP_OWNER_CPU /* - * Get context save area and 'call' save routine. - * (a4 still holds previous owner (thread_info), a3 CP number) + * Enable coprocessor for the new owner. (a2 = 1 << CP number) + * This can be done before loading context into the coprocessor. */ + l32i a4, a9, THREAD_CPENABLE + or a4, a4, a2 - movi a5, .Lsave_cp_regs_jump_table - movi a0, 2f # a0: 'return' address - addx8 a3, a3, a5 # a3: coprocessor number - l32i a2, a3, 4 # a2: xtregs offset - l32i a3, a3, 0 # a3: jump address - add a2, a2, a4 - jx a3 + /* + * Make sure THREAD_CP_OWNER_CPU is in memory before updating + * THREAD_CPENABLE + */ + memw # (2) + s32i a4, a9, THREAD_CPENABLE - /* Note that only a0 and a1 were preserved. */ + beqz a8, 1f # skip 'save' if no previous owner -2: rsr a3, exccause - addi a3, a3, -EXCCAUSE_COPROCESSOR0_DISABLED - movi a0, coprocessor_owner - addx4 a0, a3, a0 + /* Disable coprocessor for previous owner. (a2 = 1 << CP number) */ - /* Set new 'owner' (a0 points to the CP owner, a3 contains the CP nr) */ + l32i a10, a8, THREAD_CPENABLE + xor a10, a10, a2 -1: GET_THREAD_INFO (a4, a1) - s32i a4, a0, 0 + /* Get context save area and call save routine. */ - /* Get context save area and 'call' load routine. */ + l32i a2, a7, CP_REGS_TAB_OFFSET + l32i a3, a7, CP_REGS_TAB_SAVE + add a2, a2, a8 + callx0 a3 - movi a5, .Lload_cp_regs_jump_table - movi a0, 1f - addx8 a3, a3, a5 - l32i a2, a3, 4 # a2: xtregs offset - l32i a3, a3, 0 # a3: jump address - add a2, a2, a4 - jx a3 + /* + * Make sure coprocessor context and THREAD_CP_OWNER_CPU are in memory + * before updating THREAD_CPENABLE + */ + memw # (3) + s32i a10, a8, THREAD_CPENABLE +1: + /* Get context save area and call load routine. */ + + l32i a2, a7, CP_REGS_TAB_OFFSET + l32i a3, a7, CP_REGS_TAB_LOAD + add a2, a2, a9 + callx0 a3 /* Restore all registers and return from exception handler. */ -1: l32i a6, a1, PT_AREG6 + l32i a10, a1, PT_AREG10 + l32i a9, a1, PT_AREG9 + l32i a8, a1, PT_AREG8 + l32i a7, a1, PT_AREG7 + l32i a6, a1, PT_AREG6 l32i a5, a1, PT_AREG5 l32i a4, a1, PT_AREG4 @@ -230,29 +282,21 @@ ENDPROC(fast_coprocessor) ENTRY(coprocessor_flush) - /* reserve 4 bytes on stack to save a0 */ - abi_entry(4) - - s32i a0, a1, 0 - movi a0, .Lsave_cp_regs_jump_table - addx8 a3, a3, a0 - l32i a4, a3, 4 - l32i a3, a3, 0 - add a2, a2, a4 - beqz a3, 1f - callx0 a3 -1: l32i a0, a1, 0 - - abi_ret(4) + abi_entry_default + + movi a4, .Lcp_regs_jump_table + addx8 a4, a3, a4 + addx4 a3, a3, a4 + l32i a4, a3, CP_REGS_TAB_SAVE + beqz a4, 1f + l32i a3, a3, CP_REGS_TAB_OFFSET + add a2, a2, a3 + mov a7, a0 + callx0 a4 + mov a0, a7 +1: + abi_ret_default ENDPROC(coprocessor_flush) - .data - -ENTRY(coprocessor_owner) - - .fill XCHAL_CP_MAX, 4, 0 - -END(coprocessor_owner) - #endif /* XTENSA_HAVE_COPROCESSORS */ diff --git a/arch/xtensa/kernel/entry.S b/arch/xtensa/kernel/entry.S index 6b6eff658795..e3eae648ba2e 100644 --- a/arch/xtensa/kernel/entry.S +++ b/arch/xtensa/kernel/entry.S @@ -28,15 +28,6 @@ #include <asm/tlbflush.h> #include <variant/tie-asm.h> -/* Unimplemented features. */ - -#undef KERNEL_STACK_OVERFLOW_CHECK - -/* Not well tested. - * - * - fast_coprocessor - */ - /* * Macro to find first bit set in WINDOWBASE from the left + 1 * @@ -178,28 +169,26 @@ _user_exception: /* Save only live registers. */ -UABI_W _bbsi.l a2, 1, 1f +UABI_W _bbsi.l a2, 1, .Lsave_window_registers s32i a4, a1, PT_AREG4 s32i a5, a1, PT_AREG5 s32i a6, a1, PT_AREG6 s32i a7, a1, PT_AREG7 -UABI_W _bbsi.l a2, 2, 1f +UABI_W _bbsi.l a2, 2, .Lsave_window_registers s32i a8, a1, PT_AREG8 s32i a9, a1, PT_AREG9 s32i a10, a1, PT_AREG10 s32i a11, a1, PT_AREG11 -UABI_W _bbsi.l a2, 3, 1f +UABI_W _bbsi.l a2, 3, .Lsave_window_registers s32i a12, a1, PT_AREG12 s32i a13, a1, PT_AREG13 s32i a14, a1, PT_AREG14 s32i a15, a1, PT_AREG15 #if defined(USER_SUPPORT_WINDOWED) - _bnei a2, 1, 1f # only one valid frame? + /* If only one valid frame skip saving regs. */ - /* Only one valid frame, skip saving regs. */ - - j 2f + beqi a2, 1, common_exception /* Save the remaining registers. * We have to save all registers up to the first '1' from @@ -208,8 +197,8 @@ UABI_W _bbsi.l a2, 3, 1f * All register frames starting from the top field to the marked '1' * must be saved. */ - -1: addi a3, a2, -1 # eliminate '1' in bit 0: yyyyxxww0 +.Lsave_window_registers: + addi a3, a2, -1 # eliminate '1' in bit 0: yyyyxxww0 neg a3, a3 # yyyyxxww0 -> YYYYXXWW1+1 and a3, a3, a2 # max. only one bit is set @@ -250,7 +239,7 @@ UABI_W _bbsi.l a2, 3, 1f /* We are back to the original stack pointer (a1) */ #endif -2: /* Now, jump to the common exception handler. */ + /* Now, jump to the common exception handler. */ j common_exception @@ -350,15 +339,6 @@ KABI_W _bbsi.l a2, 3, 1f l32i a0, a1, PT_AREG0 # restore saved a0 wsr a0, depc -#ifdef KERNEL_STACK_OVERFLOW_CHECK - - /* Stack overflow check, for debugging */ - extui a2, a1, TASK_SIZE_BITS,XX - movi a3, SIZE?? - _bge a2, a3, out_of_stack_panic - -#endif - /* * This is the common exception handler. * We get here from the user exception handler or simply by falling through @@ -442,7 +422,6 @@ KABI_W or a3, a3, a0 moveqz a3, a0, a2 # a3 = LOCKLEVEL iff interrupt KABI_W movi a2, PS_WOE_MASK KABI_W or a3, a3, a2 - rsr a2, exccause #endif /* restore return address (or 0 if return to userspace) */ @@ -469,42 +448,56 @@ KABI_W or a3, a3, a2 save_xtregs_opt a1 a3 a4 a5 a6 a7 PT_XTREGS_OPT +#ifdef CONFIG_TRACE_IRQFLAGS + rsr abi_tmp0, ps + extui abi_tmp0, abi_tmp0, PS_INTLEVEL_SHIFT, PS_INTLEVEL_WIDTH + beqz abi_tmp0, 1f + abi_call trace_hardirqs_off +1: +#endif +#ifdef CONFIG_CONTEXT_TRACKING + l32i abi_tmp0, a1, PT_PS + bbci.l abi_tmp0, PS_UM_BIT, 1f + abi_call context_tracking_user_exit +1: +#endif + /* Go to second-level dispatcher. Set up parameters to pass to the * exception handler and call the exception handler. */ - rsr a4, excsave1 - addx4 a4, a2, a4 - l32i a4, a4, EXC_TABLE_DEFAULT # load handler - mov abi_arg1, a2 # pass EXCCAUSE - mov abi_arg0, a1 # pass stack frame + l32i abi_arg1, a1, PT_EXCCAUSE # pass EXCCAUSE + rsr abi_tmp0, excsave1 + addx4 abi_tmp0, abi_arg1, abi_tmp0 + l32i abi_tmp0, abi_tmp0, EXC_TABLE_DEFAULT # load handler + mov abi_arg0, a1 # pass stack frame /* Call the second-level handler */ - abi_callx a4 + abi_callx abi_tmp0 /* Jump here for exception exit */ .global common_exception_return common_exception_return: #if XTENSA_FAKE_NMI - l32i abi_tmp0, a1, PT_EXCCAUSE - movi abi_tmp1, EXCCAUSE_MAPPED_NMI - l32i abi_saved1, a1, PT_PS - beq abi_tmp0, abi_tmp1, .Lrestore_state + l32i abi_tmp0, a1, PT_EXCCAUSE + movi abi_tmp1, EXCCAUSE_MAPPED_NMI + l32i abi_saved1, a1, PT_PS + beq abi_tmp0, abi_tmp1, .Lrestore_state #endif .Ltif_loop: - irq_save a2, a3 + irq_save abi_tmp0, abi_tmp1 #ifdef CONFIG_TRACE_IRQFLAGS abi_call trace_hardirqs_off #endif /* Jump if we are returning from kernel exceptions. */ - l32i abi_saved1, a1, PT_PS - GET_THREAD_INFO(a2, a1) - l32i a4, a2, TI_FLAGS - _bbci.l abi_saved1, PS_UM_BIT, .Lexit_tif_loop_kernel + l32i abi_saved1, a1, PT_PS + GET_THREAD_INFO(abi_tmp0, a1) + l32i abi_saved0, abi_tmp0, TI_FLAGS + _bbci.l abi_saved1, PS_UM_BIT, .Lexit_tif_loop_kernel /* Specific to a user exception exit: * We need to check some flags for signal handling and rescheduling, @@ -513,75 +506,80 @@ common_exception_return: * Note that we don't disable interrupts here. */ - _bbsi.l a4, TIF_NEED_RESCHED, .Lresched - movi a2, _TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NOTIFY_SIGNAL - bnone a4, a2, .Lexit_tif_loop_user + _bbsi.l abi_saved0, TIF_NEED_RESCHED, .Lresched + movi abi_tmp0, _TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NOTIFY_SIGNAL + bnone abi_saved0, abi_tmp0, .Lexit_tif_loop_user - l32i a4, a1, PT_DEPC - bgeui a4, VALID_DOUBLE_EXCEPTION_ADDRESS, .Lrestore_state + l32i abi_tmp0, a1, PT_DEPC + bgeui abi_tmp0, VALID_DOUBLE_EXCEPTION_ADDRESS, .Lrestore_state /* Call do_signal() */ #ifdef CONFIG_TRACE_IRQFLAGS abi_call trace_hardirqs_on #endif - rsil a2, 0 - mov abi_arg0, a1 + rsil abi_tmp0, 0 + mov abi_arg0, a1 abi_call do_notify_resume # int do_notify_resume(struct pt_regs*) - j .Ltif_loop + j .Ltif_loop .Lresched: #ifdef CONFIG_TRACE_IRQFLAGS abi_call trace_hardirqs_on #endif - rsil a2, 0 + rsil abi_tmp0, 0 abi_call schedule # void schedule (void) - j .Ltif_loop + j .Ltif_loop .Lexit_tif_loop_kernel: #ifdef CONFIG_PREEMPTION - _bbci.l a4, TIF_NEED_RESCHED, .Lrestore_state + _bbci.l abi_saved0, TIF_NEED_RESCHED, .Lrestore_state /* Check current_thread_info->preempt_count */ - l32i a4, a2, TI_PRE_COUNT - bnez a4, .Lrestore_state + l32i abi_tmp1, abi_tmp0, TI_PRE_COUNT + bnez abi_tmp1, .Lrestore_state abi_call preempt_schedule_irq #endif - j .Lrestore_state + j .Lrestore_state .Lexit_tif_loop_user: +#ifdef CONFIG_CONTEXT_TRACKING + abi_call context_tracking_user_enter +#endif #ifdef CONFIG_HAVE_HW_BREAKPOINT - _bbci.l a4, TIF_DB_DISABLED, 1f + _bbci.l abi_saved0, TIF_DB_DISABLED, 1f abi_call restore_dbreak 1: #endif #ifdef CONFIG_DEBUG_TLB_SANITY - l32i a4, a1, PT_DEPC - bgeui a4, VALID_DOUBLE_EXCEPTION_ADDRESS, .Lrestore_state + l32i abi_tmp0, a1, PT_DEPC + bgeui abi_tmp0, VALID_DOUBLE_EXCEPTION_ADDRESS, .Lrestore_state abi_call check_tlb_sanity #endif .Lrestore_state: #ifdef CONFIG_TRACE_IRQFLAGS - extui a4, abi_saved1, PS_INTLEVEL_SHIFT, PS_INTLEVEL_WIDTH - bgei a4, LOCKLEVEL, 1f + extui abi_tmp0, abi_saved1, PS_INTLEVEL_SHIFT, PS_INTLEVEL_WIDTH + bgei abi_tmp0, LOCKLEVEL, 1f abi_call trace_hardirqs_on 1: #endif - /* Restore optional registers. */ + /* + * Restore optional registers. + * abi_arg* are used as temporary registers here. + */ - load_xtregs_opt a1 a2 a4 a5 a6 a7 PT_XTREGS_OPT + load_xtregs_opt a1 abi_tmp0 abi_arg0 abi_arg1 abi_arg2 abi_arg3 PT_XTREGS_OPT /* Restore SCOMPARE1 */ #if XCHAL_HAVE_S32C1I - l32i a2, a1, PT_SCOMPARE1 - wsr a2, scompare1 + l32i abi_tmp0, a1, PT_SCOMPARE1 + wsr abi_tmp0, scompare1 #endif - wsr abi_saved1, ps /* disable interrupts */ - - _bbci.l abi_saved1, PS_UM_BIT, kernel_exception_exit + wsr abi_saved1, ps /* disable interrupts */ + _bbci.l abi_saved1, PS_UM_BIT, kernel_exception_exit user_exception_exit: @@ -795,7 +793,7 @@ ENDPROC(kernel_exception) ENTRY(debug_exception) rsr a0, SREG_EPS + XCHAL_DEBUGLEVEL - bbsi.l a0, PS_EXCM_BIT, 1f # exception mode + bbsi.l a0, PS_EXCM_BIT, .Ldebug_exception_in_exception # exception mode /* Set EPC1 and EXCCAUSE */ @@ -814,10 +812,10 @@ ENTRY(debug_exception) /* Switch to kernel/user stack, restore jump vector, and save a0 */ - bbsi.l a2, PS_UM_BIT, 2f # jump if user mode - + bbsi.l a2, PS_UM_BIT, .Ldebug_exception_user # jump if user mode addi a2, a1, -16 - PT_KERNEL_SIZE # assume kernel stack -3: + +.Ldebug_exception_continue: l32i a0, a3, DT_DEBUG_SAVE s32i a1, a2, PT_AREG1 s32i a0, a2, PT_AREG0 @@ -845,10 +843,12 @@ ENTRY(debug_exception) bbsi.l a2, PS_UM_BIT, _user_exception j _kernel_exception -2: rsr a2, excsave1 +.Ldebug_exception_user: + rsr a2, excsave1 l32i a2, a2, EXC_TABLE_KSTK # load kernel stack pointer - j 3b + j .Ldebug_exception_continue +.Ldebug_exception_in_exception: #ifdef CONFIG_HAVE_HW_BREAKPOINT /* Debug exception while in exception mode. This may happen when * window overflow/underflow handler or fast exception handler hits @@ -856,8 +856,8 @@ ENTRY(debug_exception) * breakpoints, single-step faulting instruction and restore data * breakpoints. */ -1: - bbci.l a0, PS_UM_BIT, 1b # jump if kernel mode + + bbci.l a0, PS_UM_BIT, .Ldebug_exception_in_exception # jump if kernel mode rsr a0, debugcause bbsi.l a0, DEBUGCAUSE_DBREAK_BIT, .Ldebug_save_dbreak @@ -901,7 +901,7 @@ ENTRY(debug_exception) rfi XCHAL_DEBUGLEVEL #else /* Debug exception while in exception mode. Should not happen. */ -1: j 1b // FIXME!! + j .Ldebug_exception_in_exception // FIXME!! #endif ENDPROC(debug_exception) @@ -1056,6 +1056,11 @@ ENTRY(fast_illegal_instruction_user) movi a3, PS_WOE_MASK or a0, a0, a3 wsr a0, ps +#ifdef CONFIG_USER_ABI_CALL0_PROBE + GET_THREAD_INFO(a3, a2) + rsr a0, epc1 + s32i a0, a3, TI_PS_WOE_FIX_ADDR +#endif l32i a3, a2, PT_AREG3 l32i a0, a2, PT_AREG0 rsr a2, depc @@ -1630,12 +1635,13 @@ ENTRY(fast_second_level_miss) GET_CURRENT(a1,a2) l32i a0, a1, TASK_MM # tsk->mm - beqz a0, 9f + beqz a0, .Lfast_second_level_miss_no_mm -8: rsr a3, excvaddr # fault address +.Lfast_second_level_miss_continue: + rsr a3, excvaddr # fault address _PGD_OFFSET(a0, a3, a1) l32i a0, a0, 0 # read pmdval - beqz a0, 2f + beqz a0, .Lfast_second_level_miss_no_pmd /* Read ptevaddr and convert to top of page-table page. * @@ -1678,12 +1684,13 @@ ENTRY(fast_second_level_miss) addi a3, a3, DTLB_WAY_PGD add a1, a1, a3 # ... + way_number -3: wdtlb a0, a1 +.Lfast_second_level_miss_wdtlb: + wdtlb a0, a1 dsync /* Exit critical section. */ - -4: rsr a3, excsave1 +.Lfast_second_level_miss_skip_wdtlb: + rsr a3, excsave1 movi a0, 0 s32i a0, a3, EXC_TABLE_FIXUP @@ -1707,19 +1714,21 @@ ENTRY(fast_second_level_miss) esync rfde -9: l32i a0, a1, TASK_ACTIVE_MM # unlikely case mm == 0 - bnez a0, 8b +.Lfast_second_level_miss_no_mm: + l32i a0, a1, TASK_ACTIVE_MM # unlikely case mm == 0 + bnez a0, .Lfast_second_level_miss_continue /* Even more unlikely case active_mm == 0. * We can get here with NMI in the middle of context_switch that * touches vmalloc area. */ movi a0, init_mm - j 8b + j .Lfast_second_level_miss_continue +.Lfast_second_level_miss_no_pmd: #if (DCACHE_WAY_SIZE > PAGE_SIZE) -2: /* Special case for cache aliasing. + /* Special case for cache aliasing. * We (should) only get here if a clear_user_page, copy_user_page * or the aliased cache flush functions got preemptively interrupted * by another task. Re-establish temporary mapping to the @@ -1729,24 +1738,24 @@ ENTRY(fast_second_level_miss) /* We shouldn't be in a double exception */ l32i a0, a2, PT_DEPC - bgeui a0, VALID_DOUBLE_EXCEPTION_ADDRESS, 2f + bgeui a0, VALID_DOUBLE_EXCEPTION_ADDRESS, .Lfast_second_level_miss_slow /* Make sure the exception originated in the special functions */ movi a0, __tlbtemp_mapping_start rsr a3, epc1 - bltu a3, a0, 2f + bltu a3, a0, .Lfast_second_level_miss_slow movi a0, __tlbtemp_mapping_end - bgeu a3, a0, 2f + bgeu a3, a0, .Lfast_second_level_miss_slow /* Check if excvaddr was in one of the TLBTEMP_BASE areas. */ movi a3, TLBTEMP_BASE_1 rsr a0, excvaddr - bltu a0, a3, 2f + bltu a0, a3, .Lfast_second_level_miss_slow addi a1, a0, -TLBTEMP_SIZE - bgeu a1, a3, 2f + bgeu a1, a3, .Lfast_second_level_miss_slow /* Check if we have to restore an ITLB mapping. */ @@ -1772,19 +1781,19 @@ ENTRY(fast_second_level_miss) mov a0, a6 movnez a0, a7, a3 - j 3b + j .Lfast_second_level_miss_wdtlb /* ITLB entry. We only use dst in a6. */ 1: witlb a6, a1 isync - j 4b + j .Lfast_second_level_miss_skip_wdtlb #endif // DCACHE_WAY_SIZE > PAGE_SIZE - -2: /* Invalid PGD, default exception handling */ + /* Invalid PGD, default exception handling */ +.Lfast_second_level_miss_slow: rsr a1, depc s32i a1, a2, PT_AREG2 @@ -1824,12 +1833,13 @@ ENTRY(fast_store_prohibited) GET_CURRENT(a1,a2) l32i a0, a1, TASK_MM # tsk->mm - beqz a0, 9f + beqz a0, .Lfast_store_no_mm -8: rsr a1, excvaddr # fault address +.Lfast_store_continue: + rsr a1, excvaddr # fault address _PGD_OFFSET(a0, a1, a3) l32i a0, a0, 0 - beqz a0, 2f + beqz a0, .Lfast_store_slow /* * Note that we test _PAGE_WRITABLE_BIT only if PTE is present @@ -1839,8 +1849,8 @@ ENTRY(fast_store_prohibited) _PTE_OFFSET(a0, a1, a3) l32i a3, a0, 0 # read pteval movi a1, _PAGE_CA_INVALID - ball a3, a1, 2f - bbci.l a3, _PAGE_WRITABLE_BIT, 2f + ball a3, a1, .Lfast_store_slow + bbci.l a3, _PAGE_WRITABLE_BIT, .Lfast_store_slow movi a1, _PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_HW_WRITE or a3, a3, a1 @@ -1868,7 +1878,6 @@ ENTRY(fast_store_prohibited) l32i a2, a2, PT_DEPC bgeui a2, VALID_DOUBLE_EXCEPTION_ADDRESS, 1f - rsr a2, depc rfe @@ -1878,11 +1887,17 @@ ENTRY(fast_store_prohibited) esync rfde -9: l32i a0, a1, TASK_ACTIVE_MM # unlikely case mm == 0 - j 8b - -2: /* If there was a problem, handle fault in C */ +.Lfast_store_no_mm: + l32i a0, a1, TASK_ACTIVE_MM # unlikely case mm == 0 + j .Lfast_store_continue + /* If there was a problem, handle fault in C */ +.Lfast_store_slow: + rsr a1, excvaddr + pdtlb a0, a1 + bbci.l a0, DTLB_HIT_BIT, 1f + idtlb a0 +1: rsr a3, depc # still holds a2 s32i a3, a2, PT_AREG2 mov a1, a2 @@ -2071,8 +2086,16 @@ ENTRY(_switch_to) #if (XTENSA_HAVE_COPROCESSORS || XTENSA_HAVE_IO_PORTS) l32i a3, a5, THREAD_CPENABLE - xsr a3, cpenable - s32i a3, a4, THREAD_CPENABLE +#ifdef CONFIG_SMP + beqz a3, 1f + memw # pairs with memw (2) in fast_coprocessor + l32i a6, a5, THREAD_CP_OWNER_CPU + l32i a7, a5, THREAD_CPU + beq a6, a7, 1f # load 0 into CPENABLE if current CPU is not the owner + movi a3, 0 +1: +#endif + wsr a3, cpenable #endif #if XCHAL_HAVE_EXCLUSIVE @@ -2147,3 +2170,95 @@ ENTRY(ret_from_kernel_thread) j common_exception_return ENDPROC(ret_from_kernel_thread) + +#ifdef CONFIG_HIBERNATION + + .bss + .align 4 +.Lsaved_regs: +#if defined(__XTENSA_WINDOWED_ABI__) + .fill 2, 4 +#elif defined(__XTENSA_CALL0_ABI__) + .fill 6, 4 +#else +#error Unsupported Xtensa ABI +#endif + .align XCHAL_NCP_SA_ALIGN +.Lsaved_user_regs: + .fill XTREGS_USER_SIZE, 1 + + .previous + +ENTRY(swsusp_arch_suspend) + + abi_entry_default + + movi a2, .Lsaved_regs + movi a3, .Lsaved_user_regs + s32i a0, a2, 0 + s32i a1, a2, 4 + save_xtregs_user a3 a4 a5 a6 a7 a8 0 +#if defined(__XTENSA_WINDOWED_ABI__) + spill_registers_kernel +#elif defined(__XTENSA_CALL0_ABI__) + s32i a12, a2, 8 + s32i a13, a2, 12 + s32i a14, a2, 16 + s32i a15, a2, 20 +#else +#error Unsupported Xtensa ABI +#endif + abi_call swsusp_save + mov a2, abi_rv + abi_ret_default + +ENDPROC(swsusp_arch_suspend) + +ENTRY(swsusp_arch_resume) + + abi_entry_default + +#if defined(__XTENSA_WINDOWED_ABI__) + spill_registers_kernel +#endif + + movi a2, restore_pblist + l32i a2, a2, 0 + +.Lcopy_pbe: + l32i a3, a2, PBE_ADDRESS + l32i a4, a2, PBE_ORIG_ADDRESS + + __loopi a3, a9, PAGE_SIZE, 16 + l32i a5, a3, 0 + l32i a6, a3, 4 + l32i a7, a3, 8 + l32i a8, a3, 12 + addi a3, a3, 16 + s32i a5, a4, 0 + s32i a6, a4, 4 + s32i a7, a4, 8 + s32i a8, a4, 12 + addi a4, a4, 16 + __endl a3, a9 + + l32i a2, a2, PBE_NEXT + bnez a2, .Lcopy_pbe + + movi a2, .Lsaved_regs + movi a3, .Lsaved_user_regs + l32i a0, a2, 0 + l32i a1, a2, 4 + load_xtregs_user a3 a4 a5 a6 a7 a8 0 +#if defined(__XTENSA_CALL0_ABI__) + l32i a12, a2, 8 + l32i a13, a2, 12 + l32i a14, a2, 16 + l32i a15, a2, 20 +#endif + movi a2, 0 + abi_ret_default + +ENDPROC(swsusp_arch_resume) + +#endif diff --git a/arch/xtensa/kernel/hibernate.c b/arch/xtensa/kernel/hibernate.c new file mode 100644 index 000000000000..06984327d6e2 --- /dev/null +++ b/arch/xtensa/kernel/hibernate.c @@ -0,0 +1,25 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <linux/mm.h> +#include <linux/suspend.h> +#include <asm/coprocessor.h> + +int pfn_is_nosave(unsigned long pfn) +{ + unsigned long nosave_begin_pfn = PFN_DOWN(__pa(&__nosave_begin)); + unsigned long nosave_end_pfn = PFN_UP(__pa(&__nosave_end)); + + return (pfn >= nosave_begin_pfn) && (pfn < nosave_end_pfn); +} + +void notrace save_processor_state(void) +{ + WARN_ON(num_online_cpus() != 1); +#if XTENSA_HAVE_COPROCESSORS + local_coprocessors_flush_release_all(); +#endif +} + +void notrace restore_processor_state(void) +{ +} diff --git a/arch/xtensa/kernel/jump_label.c b/arch/xtensa/kernel/jump_label.c index 0dde21e0d3de..ad1841cecdfb 100644 --- a/arch/xtensa/kernel/jump_label.c +++ b/arch/xtensa/kernel/jump_label.c @@ -40,7 +40,7 @@ static int patch_text_stop_machine(void *data) { struct patch *patch = data; - if (atomic_inc_return(&patch->cpu_count) == 1) { + if (atomic_inc_return(&patch->cpu_count) == num_online_cpus()) { local_patch_text(patch->addr, patch->data, patch->sz); atomic_inc(&patch->cpu_count); } else { diff --git a/arch/xtensa/kernel/process.c b/arch/xtensa/kernel/process.c index e8bfbca5f001..7e38292dd07a 100644 --- a/arch/xtensa/kernel/process.c +++ b/arch/xtensa/kernel/process.c @@ -47,6 +47,7 @@ #include <asm/asm-offsets.h> #include <asm/regs.h> #include <asm/hw_breakpoint.h> +#include <asm/traps.h> extern void ret_from_fork(void); extern void ret_from_kernel_thread(void); @@ -63,52 +64,114 @@ EXPORT_SYMBOL(__stack_chk_guard); #if XTENSA_HAVE_COPROCESSORS -void coprocessor_release_all(struct thread_info *ti) +void local_coprocessors_flush_release_all(void) { - unsigned long cpenable; - int i; + struct thread_info **coprocessor_owner; + struct thread_info *unique_owner[XCHAL_CP_MAX]; + int n = 0; + int i, j; - /* Make sure we don't switch tasks during this operation. */ + coprocessor_owner = this_cpu_ptr(&exc_table)->coprocessor_owner; + xtensa_set_sr(XCHAL_CP_MASK, cpenable); - preempt_disable(); + for (i = 0; i < XCHAL_CP_MAX; i++) { + struct thread_info *ti = coprocessor_owner[i]; - /* Walk through all cp owners and release it for the requested one. */ + if (ti) { + coprocessor_flush(ti, i); - cpenable = ti->cpenable; + for (j = 0; j < n; j++) + if (unique_owner[j] == ti) + break; + if (j == n) + unique_owner[n++] = ti; - for (i = 0; i < XCHAL_CP_MAX; i++) { - if (coprocessor_owner[i] == ti) { - coprocessor_owner[i] = 0; - cpenable &= ~(1 << i); + coprocessor_owner[i] = NULL; } } + for (i = 0; i < n; i++) { + /* pairs with memw (1) in fast_coprocessor and memw in switch_to */ + smp_wmb(); + unique_owner[i]->cpenable = 0; + } + xtensa_set_sr(0, cpenable); +} - ti->cpenable = cpenable; +static void local_coprocessor_release_all(void *info) +{ + struct thread_info *ti = info; + struct thread_info **coprocessor_owner; + int i; + + coprocessor_owner = this_cpu_ptr(&exc_table)->coprocessor_owner; + + /* Walk through all cp owners and release it for the requested one. */ + + for (i = 0; i < XCHAL_CP_MAX; i++) { + if (coprocessor_owner[i] == ti) + coprocessor_owner[i] = NULL; + } + /* pairs with memw (1) in fast_coprocessor and memw in switch_to */ + smp_wmb(); + ti->cpenable = 0; if (ti == current_thread_info()) xtensa_set_sr(0, cpenable); +} - preempt_enable(); +void coprocessor_release_all(struct thread_info *ti) +{ + if (ti->cpenable) { + /* pairs with memw (2) in fast_coprocessor */ + smp_rmb(); + smp_call_function_single(ti->cp_owner_cpu, + local_coprocessor_release_all, + ti, true); + } } -void coprocessor_flush_all(struct thread_info *ti) +static void local_coprocessor_flush_all(void *info) { - unsigned long cpenable, old_cpenable; + struct thread_info *ti = info; + struct thread_info **coprocessor_owner; + unsigned long old_cpenable; int i; - preempt_disable(); - - old_cpenable = xtensa_get_sr(cpenable); - cpenable = ti->cpenable; - xtensa_set_sr(cpenable, cpenable); + coprocessor_owner = this_cpu_ptr(&exc_table)->coprocessor_owner; + old_cpenable = xtensa_xsr(ti->cpenable, cpenable); for (i = 0; i < XCHAL_CP_MAX; i++) { - if ((cpenable & 1) != 0 && coprocessor_owner[i] == ti) + if (coprocessor_owner[i] == ti) coprocessor_flush(ti, i); - cpenable >>= 1; } xtensa_set_sr(old_cpenable, cpenable); +} - preempt_enable(); +void coprocessor_flush_all(struct thread_info *ti) +{ + if (ti->cpenable) { + /* pairs with memw (2) in fast_coprocessor */ + smp_rmb(); + smp_call_function_single(ti->cp_owner_cpu, + local_coprocessor_flush_all, + ti, true); + } +} + +static void local_coprocessor_flush_release_all(void *info) +{ + local_coprocessor_flush_all(info); + local_coprocessor_release_all(info); +} + +void coprocessor_flush_release_all(struct thread_info *ti) +{ + if (ti->cpenable) { + /* pairs with memw (2) in fast_coprocessor */ + smp_rmb(); + smp_call_function_single(ti->cp_owner_cpu, + local_coprocessor_flush_release_all, + ti, true); + } } #endif @@ -140,8 +203,7 @@ void flush_thread(void) { #if XTENSA_HAVE_COPROCESSORS struct thread_info *ti = current_thread_info(); - coprocessor_flush_all(ti); - coprocessor_release_all(ti); + coprocessor_flush_release_all(ti); #endif flush_ptrace_hw_breakpoint(current); } diff --git a/arch/xtensa/kernel/ptrace.c b/arch/xtensa/kernel/ptrace.c index 323c678a691f..22cdaa6729d3 100644 --- a/arch/xtensa/kernel/ptrace.c +++ b/arch/xtensa/kernel/ptrace.c @@ -171,8 +171,7 @@ static int tie_set(struct task_struct *target, #if XTENSA_HAVE_COPROCESSORS /* Flush all coprocessors before we overwrite them. */ - coprocessor_flush_all(ti); - coprocessor_release_all(ti); + coprocessor_flush_release_all(ti); ti->xtregs_cp.cp0 = newregs->cp0; ti->xtregs_cp.cp1 = newregs->cp1; ti->xtregs_cp.cp2 = newregs->cp2; diff --git a/arch/xtensa/kernel/s32c1i_selftest.c b/arch/xtensa/kernel/s32c1i_selftest.c index 07e56e3a9a8b..8362388c8719 100644 --- a/arch/xtensa/kernel/s32c1i_selftest.c +++ b/arch/xtensa/kernel/s32c1i_selftest.c @@ -40,14 +40,13 @@ static inline int probed_compare_swap(int *v, int cmp, int set) /* Handle probed exception */ -static void __init do_probed_exception(struct pt_regs *regs, - unsigned long exccause) +static void __init do_probed_exception(struct pt_regs *regs) { if (regs->pc == rcw_probe_pc) { /* exception on s32c1i ? */ regs->pc += 3; /* skip the s32c1i instruction */ - rcw_exc = exccause; + rcw_exc = regs->exccause; } else { - do_unhandled(regs, exccause); + do_unhandled(regs); } } diff --git a/arch/xtensa/kernel/signal.c b/arch/xtensa/kernel/signal.c index 6f68649e86ba..c9ffd42db873 100644 --- a/arch/xtensa/kernel/signal.c +++ b/arch/xtensa/kernel/signal.c @@ -162,8 +162,7 @@ setup_sigcontext(struct rt_sigframe __user *frame, struct pt_regs *regs) return err; #if XTENSA_HAVE_COPROCESSORS - coprocessor_flush_all(ti); - coprocessor_release_all(ti); + coprocessor_flush_release_all(ti); err |= __copy_to_user(&frame->xtregs.cp, &ti->xtregs_cp, sizeof (frame->xtregs.cp)); #endif diff --git a/arch/xtensa/kernel/smp.c b/arch/xtensa/kernel/smp.c index 1254da07ead1..4dc109dd6214 100644 --- a/arch/xtensa/kernel/smp.c +++ b/arch/xtensa/kernel/smp.c @@ -30,6 +30,7 @@ #include <linux/thread_info.h> #include <asm/cacheflush.h> +#include <asm/coprocessor.h> #include <asm/kdebug.h> #include <asm/mmu_context.h> #include <asm/mxregs.h> @@ -272,6 +273,12 @@ int __cpu_disable(void) */ set_cpu_online(cpu, false); +#if XTENSA_HAVE_COPROCESSORS + /* + * Flush coprocessor contexts that are active on the current CPU. + */ + local_coprocessors_flush_release_all(); +#endif /* * OK - migrate IRQs away from this CPU */ diff --git a/arch/xtensa/kernel/traps.c b/arch/xtensa/kernel/traps.c index 9345007d474d..0c25e035ff10 100644 --- a/arch/xtensa/kernel/traps.c +++ b/arch/xtensa/kernel/traps.c @@ -48,25 +48,20 @@ * Machine specific interrupt handlers */ -extern void kernel_exception(void); -extern void user_exception(void); - -extern void fast_illegal_instruction_user(void); -extern void fast_syscall_user(void); -extern void fast_alloca(void); -extern void fast_unaligned(void); -extern void fast_second_level_miss(void); -extern void fast_store_prohibited(void); -extern void fast_coprocessor(void); - -extern void do_illegal_instruction (struct pt_regs*); -extern void do_interrupt (struct pt_regs*); -extern void do_nmi(struct pt_regs *); -extern void do_unaligned_user (struct pt_regs*); -extern void do_multihit (struct pt_regs*, unsigned long); -extern void do_page_fault (struct pt_regs*, unsigned long); -extern void do_debug (struct pt_regs*); -extern void system_call (struct pt_regs*); +static void do_illegal_instruction(struct pt_regs *regs); +static void do_div0(struct pt_regs *regs); +static void do_interrupt(struct pt_regs *regs); +#if XTENSA_FAKE_NMI +static void do_nmi(struct pt_regs *regs); +#endif +#if XCHAL_UNALIGNED_LOAD_EXCEPTION || XCHAL_UNALIGNED_STORE_EXCEPTION +static void do_unaligned_user(struct pt_regs *regs); +#endif +static void do_multihit(struct pt_regs *regs); +#if XTENSA_HAVE_COPROCESSORS +static void do_coprocessor(struct pt_regs *regs); +#endif +static void do_debug(struct pt_regs *regs); /* * The vector table must be preceded by a save area (which @@ -78,7 +73,8 @@ extern void system_call (struct pt_regs*); #define USER 0x02 #define COPROCESSOR(x) \ -{ EXCCAUSE_COPROCESSOR ## x ## _DISABLED, USER, fast_coprocessor } +{ EXCCAUSE_COPROCESSOR ## x ## _DISABLED, USER|KRNL, fast_coprocessor },\ +{ EXCCAUSE_COPROCESSOR ## x ## _DISABLED, 0, do_coprocessor } typedef struct { int cause; @@ -100,7 +96,7 @@ static dispatch_init_table_t __initdata dispatch_init_table[] = { #ifdef SUPPORT_WINDOWED { EXCCAUSE_ALLOCA, USER|KRNL, fast_alloca }, #endif -/* EXCCAUSE_INTEGER_DIVIDE_BY_ZERO unhandled */ +{ EXCCAUSE_INTEGER_DIVIDE_BY_ZERO, 0, do_div0 }, /* EXCCAUSE_PRIVILEGED unhandled */ #if XCHAL_UNALIGNED_LOAD_EXCEPTION || XCHAL_UNALIGNED_STORE_EXCEPTION #ifdef CONFIG_XTENSA_UNALIGNED_USER @@ -110,21 +106,21 @@ static dispatch_init_table_t __initdata dispatch_init_table[] = { { EXCCAUSE_UNALIGNED, KRNL, fast_unaligned }, #endif #ifdef CONFIG_MMU -{ EXCCAUSE_ITLB_MISS, 0, do_page_fault }, -{ EXCCAUSE_ITLB_MISS, USER|KRNL, fast_second_level_miss}, +{ EXCCAUSE_ITLB_MISS, 0, do_page_fault }, +{ EXCCAUSE_ITLB_MISS, USER|KRNL, fast_second_level_miss}, +{ EXCCAUSE_DTLB_MISS, USER|KRNL, fast_second_level_miss}, +{ EXCCAUSE_DTLB_MISS, 0, do_page_fault }, +{ EXCCAUSE_STORE_CACHE_ATTRIBUTE, USER|KRNL, fast_store_prohibited }, +#endif /* CONFIG_MMU */ +#ifdef CONFIG_PFAULT { EXCCAUSE_ITLB_MULTIHIT, 0, do_multihit }, -{ EXCCAUSE_ITLB_PRIVILEGE, 0, do_page_fault }, -/* EXCCAUSE_SIZE_RESTRICTION unhandled */ +{ EXCCAUSE_ITLB_PRIVILEGE, 0, do_page_fault }, { EXCCAUSE_FETCH_CACHE_ATTRIBUTE, 0, do_page_fault }, -{ EXCCAUSE_DTLB_MISS, USER|KRNL, fast_second_level_miss}, -{ EXCCAUSE_DTLB_MISS, 0, do_page_fault }, { EXCCAUSE_DTLB_MULTIHIT, 0, do_multihit }, -{ EXCCAUSE_DTLB_PRIVILEGE, 0, do_page_fault }, -/* EXCCAUSE_DTLB_SIZE_RESTRICTION unhandled */ -{ EXCCAUSE_STORE_CACHE_ATTRIBUTE, USER|KRNL, fast_store_prohibited }, +{ EXCCAUSE_DTLB_PRIVILEGE, 0, do_page_fault }, { EXCCAUSE_STORE_CACHE_ATTRIBUTE, 0, do_page_fault }, { EXCCAUSE_LOAD_CACHE_ATTRIBUTE, 0, do_page_fault }, -#endif /* CONFIG_MMU */ +#endif /* XCCHAL_EXCCAUSE_FLOATING_POINT unhandled */ #if XTENSA_HAVE_COPROCESSOR(0) COPROCESSOR(0), @@ -179,7 +175,7 @@ __die_if_kernel(const char *str, struct pt_regs *regs, long err) * Unhandled Exceptions. Kill user task or panic if in kernel space. */ -void do_unhandled(struct pt_regs *regs, unsigned long exccause) +void do_unhandled(struct pt_regs *regs) { __die_if_kernel("Caught unhandled exception - should not happen", regs, SIGKILL); @@ -189,7 +185,7 @@ void do_unhandled(struct pt_regs *regs, unsigned long exccause) "(pid = %d, pc = %#010lx) - should not happen\n" "\tEXCCAUSE is %ld\n", current->comm, task_pid_nr(current), regs->pc, - exccause); + regs->exccause); force_sig(SIGILL); } @@ -197,7 +193,7 @@ void do_unhandled(struct pt_regs *regs, unsigned long exccause) * Multi-hit exception. This if fatal! */ -void do_multihit(struct pt_regs *regs, unsigned long exccause) +static void do_multihit(struct pt_regs *regs) { die("Caught multihit exception", regs, SIGKILL); } @@ -206,8 +202,6 @@ void do_multihit(struct pt_regs *regs, unsigned long exccause) * IRQ handler. */ -extern void do_IRQ(int, struct pt_regs *); - #if XTENSA_FAKE_NMI #define IS_POW2(v) (((v) & ((v) - 1)) == 0) @@ -240,14 +234,10 @@ irqreturn_t xtensa_pmu_irq_handler(int irq, void *dev_id); DEFINE_PER_CPU(unsigned long, nmi_count); -void do_nmi(struct pt_regs *regs) +static void do_nmi(struct pt_regs *regs) { - struct pt_regs *old_regs; - - if ((regs->ps & PS_INTLEVEL_MASK) < LOCKLEVEL) - trace_hardirqs_off(); + struct pt_regs *old_regs = set_irq_regs(regs); - old_regs = set_irq_regs(regs); nmi_enter(); ++*this_cpu_ptr(&nmi_count); check_valid_nmi(); @@ -257,7 +247,7 @@ void do_nmi(struct pt_regs *regs) } #endif -void do_interrupt(struct pt_regs *regs) +static void do_interrupt(struct pt_regs *regs) { static const unsigned int_level_mask[] = { 0, @@ -269,12 +259,9 @@ void do_interrupt(struct pt_regs *regs) XCHAL_INTLEVEL6_MASK, XCHAL_INTLEVEL7_MASK, }; - struct pt_regs *old_regs; + struct pt_regs *old_regs = set_irq_regs(regs); unsigned unhandled = ~0u; - trace_hardirqs_off(); - - old_regs = set_irq_regs(regs); irq_enter(); for (;;) { @@ -306,13 +293,47 @@ void do_interrupt(struct pt_regs *regs) set_irq_regs(old_regs); } +static bool check_div0(struct pt_regs *regs) +{ + static const u8 pattern[] = {'D', 'I', 'V', '0'}; + const u8 *p; + u8 buf[5]; + + if (user_mode(regs)) { + if (copy_from_user(buf, (void __user *)regs->pc + 2, 5)) + return false; + p = buf; + } else { + p = (const u8 *)regs->pc + 2; + } + + return memcmp(p, pattern, sizeof(pattern)) == 0 || + memcmp(p + 1, pattern, sizeof(pattern)) == 0; +} + /* * Illegal instruction. Fatal if in kernel space. */ -void -do_illegal_instruction(struct pt_regs *regs) +static void do_illegal_instruction(struct pt_regs *regs) { +#ifdef CONFIG_USER_ABI_CALL0_PROBE + /* + * When call0 application encounters an illegal instruction fast + * exception handler will attempt to set PS.WOE and retry failing + * instruction. + * If we get here we know that that instruction is also illegal + * with PS.WOE set, so it's not related to the windowed option + * hence PS.WOE may be cleared. + */ + if (regs->pc == current_thread_info()->ps_woe_fix_addr) + regs->ps &= ~PS_WOE_MASK; +#endif + if (check_div0(regs)) { + do_div0(regs); + return; + } + __die_if_kernel("Illegal instruction in kernel", regs, SIGKILL); /* If in user mode, send SIGILL signal to current process. */ @@ -322,6 +343,11 @@ do_illegal_instruction(struct pt_regs *regs) force_sig(SIGILL); } +static void do_div0(struct pt_regs *regs) +{ + __die_if_kernel("Unhandled division by 0 in kernel", regs, SIGKILL); + force_sig_fault(SIGFPE, FPE_INTDIV, (void __user *)regs->pc); +} /* * Handle unaligned memory accesses from user space. Kill task. @@ -331,8 +357,7 @@ do_illegal_instruction(struct pt_regs *regs) */ #if XCHAL_UNALIGNED_LOAD_EXCEPTION || XCHAL_UNALIGNED_STORE_EXCEPTION -void -do_unaligned_user (struct pt_regs *regs) +static void do_unaligned_user(struct pt_regs *regs) { __die_if_kernel("Unhandled unaligned exception in kernel", regs, SIGKILL); @@ -347,14 +372,20 @@ do_unaligned_user (struct pt_regs *regs) } #endif +#if XTENSA_HAVE_COPROCESSORS +static void do_coprocessor(struct pt_regs *regs) +{ + coprocessor_flush_release_all(current_thread_info()); +} +#endif + /* Handle debug events. * When CONFIG_HAVE_HW_BREAKPOINT is on this handler is called with * preemption disabled to avoid rescheduling and keep mapping of hardware * breakpoint structures to debug registers intact, so that * DEBUGCAUSE.DBNUM could be used in case of data breakpoint hit. */ -void -do_debug(struct pt_regs *regs) +static void do_debug(struct pt_regs *regs) { #ifdef CONFIG_HAVE_HW_BREAKPOINT int ret = check_hw_breakpoint(regs); @@ -381,7 +412,8 @@ do_debug(struct pt_regs *regs) /* Set exception C handler - for temporary use when probing exceptions */ -void * __init trap_set_handler(int cause, void *handler) +xtensa_exception_handler * +__init trap_set_handler(int cause, xtensa_exception_handler *handler) { void *previous = per_cpu(exc_table, 0).default_handler[cause]; @@ -392,8 +424,7 @@ void * __init trap_set_handler(int cause, void *handler) static void trap_init_excsave(void) { - unsigned long excsave1 = (unsigned long)this_cpu_ptr(&exc_table); - __asm__ __volatile__("wsr %0, excsave1\n" : : "a" (excsave1)); + xtensa_set_sr(this_cpu_ptr(&exc_table), excsave1); } static void trap_init_debug(void) diff --git a/arch/xtensa/lib/Makefile b/arch/xtensa/lib/Makefile index 5848c133f7ea..d4e9c397e3fd 100644 --- a/arch/xtensa/lib/Makefile +++ b/arch/xtensa/lib/Makefile @@ -8,3 +8,5 @@ lib-y += memcopy.o memset.o checksum.o \ divsi3.o udivsi3.o modsi3.o umodsi3.o mulsi3.o \ usercopy.o strncpy_user.o strnlen_user.o lib-$(CONFIG_PCI) += pci-auto.o +lib-$(CONFIG_KCSAN) += kcsan-stubs.o +KCSAN_SANITIZE_kcsan-stubs.o := n diff --git a/arch/xtensa/lib/kcsan-stubs.c b/arch/xtensa/lib/kcsan-stubs.c new file mode 100644 index 000000000000..2b08faa62b86 --- /dev/null +++ b/arch/xtensa/lib/kcsan-stubs.c @@ -0,0 +1,54 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bug.h> +#include <linux/types.h> + +void __atomic_store_8(volatile void *p, u64 v, int i) +{ + BUG(); +} + +u64 __atomic_load_8(const volatile void *p, int i) +{ + BUG(); +} + +u64 __atomic_exchange_8(volatile void *p, u64 v, int i) +{ + BUG(); +} + +bool __atomic_compare_exchange_8(volatile void *p1, void *p2, u64 v, bool b, int i1, int i2) +{ + BUG(); +} + +u64 __atomic_fetch_add_8(volatile void *p, u64 v, int i) +{ + BUG(); +} + +u64 __atomic_fetch_sub_8(volatile void *p, u64 v, int i) +{ + BUG(); +} + +u64 __atomic_fetch_and_8(volatile void *p, u64 v, int i) +{ + BUG(); +} + +u64 __atomic_fetch_or_8(volatile void *p, u64 v, int i) +{ + BUG(); +} + +u64 __atomic_fetch_xor_8(volatile void *p, u64 v, int i) +{ + BUG(); +} + +u64 __atomic_fetch_nand_8(volatile void *p, u64 v, int i) +{ + BUG(); +} diff --git a/arch/xtensa/lib/memcopy.S b/arch/xtensa/lib/memcopy.S index 582d817979ed..b20d206bcb71 100644 --- a/arch/xtensa/lib/memcopy.S +++ b/arch/xtensa/lib/memcopy.S @@ -402,13 +402,13 @@ WEAK(memmove) */ # copy 16 bytes per iteration for word-aligned dst and word-aligned src #if XCHAL_HAVE_LOOPS - loopnez a7, .backLoop1done + loopnez a7, .LbackLoop1done #else /* !XCHAL_HAVE_LOOPS */ - beqz a7, .backLoop1done + beqz a7, .LbackLoop1done slli a8, a7, 4 sub a8, a3, a8 # a8 = start of first 16B source chunk #endif /* !XCHAL_HAVE_LOOPS */ -.backLoop1: +.LbackLoop1: addi a3, a3, -16 l32i a7, a3, 12 l32i a6, a3, 8 @@ -420,9 +420,9 @@ WEAK(memmove) s32i a7, a5, 4 s32i a6, a5, 0 #if !XCHAL_HAVE_LOOPS - bne a3, a8, .backLoop1 # continue loop if a3:src != a8:src_start + bne a3, a8, .LbackLoop1 # continue loop if a3:src != a8:src_start #endif /* !XCHAL_HAVE_LOOPS */ -.backLoop1done: +.LbackLoop1done: bbci.l a4, 3, .Lback2 # copy 8 bytes addi a3, a3, -8 @@ -479,13 +479,13 @@ WEAK(memmove) #endif l32i a6, a3, 0 # load first word #if XCHAL_HAVE_LOOPS - loopnez a7, .backLoop2done + loopnez a7, .LbackLoop2done #else /* !XCHAL_HAVE_LOOPS */ - beqz a7, .backLoop2done + beqz a7, .LbackLoop2done slli a10, a7, 4 sub a10, a3, a10 # a10 = start of first 16B source chunk #endif /* !XCHAL_HAVE_LOOPS */ -.backLoop2: +.LbackLoop2: addi a3, a3, -16 l32i a7, a3, 12 l32i a8, a3, 8 @@ -501,9 +501,9 @@ WEAK(memmove) __src_b a9, a6, a9 s32i a9, a5, 0 #if !XCHAL_HAVE_LOOPS - bne a3, a10, .backLoop2 # continue loop if a3:src != a10:src_start + bne a3, a10, .LbackLoop2 # continue loop if a3:src != a10:src_start #endif /* !XCHAL_HAVE_LOOPS */ -.backLoop2done: +.LbackLoop2done: bbci.l a4, 3, .Lback12 # copy 8 bytes addi a3, a3, -8 diff --git a/arch/xtensa/mm/Makefile b/arch/xtensa/mm/Makefile index f7fb08ae768f..44153a335951 100644 --- a/arch/xtensa/mm/Makefile +++ b/arch/xtensa/mm/Makefile @@ -4,7 +4,8 @@ # obj-y := init.o misc.o -obj-$(CONFIG_MMU) += cache.o fault.o ioremap.o mmu.o tlb.o +obj-$(CONFIG_PFAULT) += fault.o +obj-$(CONFIG_MMU) += cache.o ioremap.o mmu.o tlb.o obj-$(CONFIG_HIGHMEM) += highmem.o obj-$(CONFIG_KASAN) += kasan_init.o diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c index 06d0973a0d74..16f0a5ff5799 100644 --- a/arch/xtensa/mm/fault.c +++ b/arch/xtensa/mm/fault.c @@ -21,9 +21,61 @@ #include <asm/cacheflush.h> #include <asm/hardirq.h> -DEFINE_PER_CPU(unsigned long, asid_cache) = ASID_USER_FIRST; void bad_page_fault(struct pt_regs*, unsigned long, int); +static void vmalloc_fault(struct pt_regs *regs, unsigned int address) +{ +#ifdef CONFIG_MMU + /* Synchronize this task's top level page-table + * with the 'reference' page table. + */ + struct mm_struct *act_mm = current->active_mm; + int index = pgd_index(address); + pgd_t *pgd, *pgd_k; + p4d_t *p4d, *p4d_k; + pud_t *pud, *pud_k; + pmd_t *pmd, *pmd_k; + pte_t *pte_k; + + if (act_mm == NULL) + goto bad_page_fault; + + pgd = act_mm->pgd + index; + pgd_k = init_mm.pgd + index; + + if (!pgd_present(*pgd_k)) + goto bad_page_fault; + + pgd_val(*pgd) = pgd_val(*pgd_k); + + p4d = p4d_offset(pgd, address); + p4d_k = p4d_offset(pgd_k, address); + if (!p4d_present(*p4d) || !p4d_present(*p4d_k)) + goto bad_page_fault; + + pud = pud_offset(p4d, address); + pud_k = pud_offset(p4d_k, address); + if (!pud_present(*pud) || !pud_present(*pud_k)) + goto bad_page_fault; + + pmd = pmd_offset(pud, address); + pmd_k = pmd_offset(pud_k, address); + if (!pmd_present(*pmd) || !pmd_present(*pmd_k)) + goto bad_page_fault; + + pmd_val(*pmd) = pmd_val(*pmd_k); + pte_k = pte_offset_kernel(pmd_k, address); + + if (!pte_present(*pte_k)) + goto bad_page_fault; + return; + +bad_page_fault: + bad_page_fault(regs, address, SIGKILL); +#else + WARN_ONCE(1, "%s in noMMU configuration\n", __func__); +#endif +} /* * This routine handles page faults. It determines the address, * and the problem, and then passes it off to one of the appropriate @@ -49,8 +101,10 @@ void do_page_fault(struct pt_regs *regs) /* We fault-in kernel-space virtual memory on-demand. The * 'reference' page table is init_mm.pgd. */ - if (address >= TASK_SIZE && !user_mode(regs)) - goto vmalloc_fault; + if (address >= TASK_SIZE && !user_mode(regs)) { + vmalloc_fault(regs, address); + return; + } /* If we're in an interrupt or have no user * context, we must not take the fault.. @@ -114,7 +168,7 @@ good_area: if (fault_signal_pending(fault, regs)) { if (!user_mode(regs)) - goto bad_page_fault; + bad_page_fault(regs, address, SIGKILL); return; } @@ -181,56 +235,6 @@ do_sigbus: if (!user_mode(regs)) bad_page_fault(regs, address, SIGBUS); return; - -vmalloc_fault: - { - /* Synchronize this task's top level page-table - * with the 'reference' page table. - */ - struct mm_struct *act_mm = current->active_mm; - int index = pgd_index(address); - pgd_t *pgd, *pgd_k; - p4d_t *p4d, *p4d_k; - pud_t *pud, *pud_k; - pmd_t *pmd, *pmd_k; - pte_t *pte_k; - - if (act_mm == NULL) - goto bad_page_fault; - - pgd = act_mm->pgd + index; - pgd_k = init_mm.pgd + index; - - if (!pgd_present(*pgd_k)) - goto bad_page_fault; - - pgd_val(*pgd) = pgd_val(*pgd_k); - - p4d = p4d_offset(pgd, address); - p4d_k = p4d_offset(pgd_k, address); - if (!p4d_present(*p4d) || !p4d_present(*p4d_k)) - goto bad_page_fault; - - pud = pud_offset(p4d, address); - pud_k = pud_offset(p4d_k, address); - if (!pud_present(*pud) || !pud_present(*pud_k)) - goto bad_page_fault; - - pmd = pmd_offset(pud, address); - pmd_k = pmd_offset(pud_k, address); - if (!pmd_present(*pmd) || !pmd_present(*pmd_k)) - goto bad_page_fault; - - pmd_val(*pmd) = pmd_val(*pmd_k); - pte_k = pte_offset_kernel(pmd_k, address); - - if (!pte_present(*pte_k)) - goto bad_page_fault; - return; - } -bad_page_fault: - bad_page_fault(regs, address, SIGKILL); - return; } diff --git a/arch/xtensa/mm/mmu.c b/arch/xtensa/mm/mmu.c index 38acda4f04e8..92e158c69c10 100644 --- a/arch/xtensa/mm/mmu.c +++ b/arch/xtensa/mm/mmu.c @@ -18,6 +18,8 @@ #include <asm/initialize_mmu.h> #include <asm/io.h> +DEFINE_PER_CPU(unsigned long, asid_cache) = ASID_USER_FIRST; + #if defined(CONFIG_HIGHMEM) static void * __init init_pmd(unsigned long vaddr, unsigned long n_pages) { diff --git a/arch/xtensa/platforms/iss/console.c b/arch/xtensa/platforms/iss/console.c index 81d7c7e8f7e9..10b79d3c74e0 100644 --- a/arch/xtensa/platforms/iss/console.c +++ b/arch/xtensa/platforms/iss/console.c @@ -36,24 +36,19 @@ static void rs_poll(struct timer_list *); static struct tty_driver *serial_driver; static struct tty_port serial_port; static DEFINE_TIMER(serial_timer, rs_poll); -static DEFINE_SPINLOCK(timer_lock); static int rs_open(struct tty_struct *tty, struct file * filp) { - spin_lock_bh(&timer_lock); if (tty->count == 1) mod_timer(&serial_timer, jiffies + SERIAL_TIMER_VALUE); - spin_unlock_bh(&timer_lock); return 0; } static void rs_close(struct tty_struct *tty, struct file * filp) { - spin_lock_bh(&timer_lock); if (tty->count == 1) del_timer_sync(&serial_timer); - spin_unlock_bh(&timer_lock); } @@ -73,8 +68,6 @@ static void rs_poll(struct timer_list *unused) int rd = 1; unsigned char c; - spin_lock(&timer_lock); - while (simc_poll(0)) { rd = simc_read(0, &c, 1); if (rd <= 0) @@ -87,7 +80,6 @@ static void rs_poll(struct timer_list *unused) tty_flip_buffer_push(port); if (rd) mod_timer(&serial_timer, jiffies + SERIAL_TIMER_VALUE); - spin_unlock(&timer_lock); } diff --git a/arch/xtensa/platforms/iss/network.c b/arch/xtensa/platforms/iss/network.c index be3aaaad8bee..fd84d4891758 100644 --- a/arch/xtensa/platforms/iss/network.c +++ b/arch/xtensa/platforms/iss/network.c @@ -38,9 +38,6 @@ #define ISS_NET_TIMER_VALUE (HZ / 10) -static DEFINE_SPINLOCK(opened_lock); -static LIST_HEAD(opened); - static DEFINE_SPINLOCK(devices_lock); static LIST_HEAD(devices); @@ -59,17 +56,27 @@ struct tuntap_info { /* ------------------------------------------------------------------------- */ +struct iss_net_private; + +struct iss_net_ops { + int (*open)(struct iss_net_private *lp); + void (*close)(struct iss_net_private *lp); + int (*read)(struct iss_net_private *lp, struct sk_buff **skb); + int (*write)(struct iss_net_private *lp, struct sk_buff **skb); + unsigned short (*protocol)(struct sk_buff *skb); + int (*poll)(struct iss_net_private *lp); +}; + /* This structure contains out private information for the driver. */ struct iss_net_private { struct list_head device_list; - struct list_head opened_list; spinlock_t lock; struct net_device *dev; struct platform_device pdev; struct timer_list tl; - struct net_device_stats stats; + struct rtnl_link_stats64 stats; struct timer_list timer; unsigned int timer_val; @@ -82,12 +89,7 @@ struct iss_net_private { struct tuntap_info tuntap; } info; - int (*open)(struct iss_net_private *lp); - void (*close)(struct iss_net_private *lp); - int (*read)(struct iss_net_private *lp, struct sk_buff **skb); - int (*write)(struct iss_net_private *lp, struct sk_buff **skb); - unsigned short (*protocol)(struct sk_buff *skb); - int (*poll)(struct iss_net_private *lp); + const struct iss_net_ops *net_ops; } tp; }; @@ -215,6 +217,15 @@ static int tuntap_poll(struct iss_net_private *lp) return simc_poll(lp->tp.info.tuntap.fd); } +static const struct iss_net_ops tuntap_ops = { + .open = tuntap_open, + .close = tuntap_close, + .read = tuntap_read, + .write = tuntap_write, + .protocol = tuntap_protocol, + .poll = tuntap_poll, +}; + /* * ethX=tuntap,[mac address],device name */ @@ -257,13 +268,7 @@ static int tuntap_probe(struct iss_net_private *lp, int index, char *init) lp->mtu = TRANSPORT_TUNTAP_MTU; lp->tp.info.tuntap.fd = -1; - - lp->tp.open = tuntap_open; - lp->tp.close = tuntap_close; - lp->tp.read = tuntap_read; - lp->tp.write = tuntap_write; - lp->tp.protocol = tuntap_protocol; - lp->tp.poll = tuntap_poll; + lp->tp.net_ops = &tuntap_ops; return 1; } @@ -278,14 +283,16 @@ static int iss_net_rx(struct net_device *dev) /* Check if there is any new data. */ - if (lp->tp.poll(lp) == 0) + if (lp->tp.net_ops->poll(lp) == 0) return 0; /* Try to allocate memory, if it fails, try again next round. */ skb = dev_alloc_skb(dev->mtu + 2 + ETH_HEADER_OTHER); if (skb == NULL) { + spin_lock_bh(&lp->lock); lp->stats.rx_dropped++; + spin_unlock_bh(&lp->lock); return 0; } @@ -295,15 +302,17 @@ static int iss_net_rx(struct net_device *dev) skb->dev = dev; skb_reset_mac_header(skb); - pkt_len = lp->tp.read(lp, &skb); + pkt_len = lp->tp.net_ops->read(lp, &skb); skb_put(skb, pkt_len); if (pkt_len > 0) { skb_trim(skb, pkt_len); - skb->protocol = lp->tp.protocol(skb); + skb->protocol = lp->tp.net_ops->protocol(skb); + spin_lock_bh(&lp->lock); lp->stats.rx_bytes += skb->len; lp->stats.rx_packets++; + spin_unlock_bh(&lp->lock); netif_rx(skb); return pkt_len; } @@ -311,38 +320,24 @@ static int iss_net_rx(struct net_device *dev) return pkt_len; } -static int iss_net_poll(void) +static int iss_net_poll(struct iss_net_private *lp) { - struct list_head *ele; int err, ret = 0; - spin_lock(&opened_lock); - - list_for_each(ele, &opened) { - struct iss_net_private *lp; - - lp = list_entry(ele, struct iss_net_private, opened_list); - - if (!netif_running(lp->dev)) - break; - - spin_lock(&lp->lock); - - while ((err = iss_net_rx(lp->dev)) > 0) - ret++; + if (!netif_running(lp->dev)) + return 0; - spin_unlock(&lp->lock); + while ((err = iss_net_rx(lp->dev)) > 0) + ret++; - if (err < 0) { - pr_err("Device '%s' read returned %d, shutting it down\n", - lp->dev->name, err); - dev_close(lp->dev); - } else { - /* FIXME reactivate_fd(lp->fd, ISS_ETH_IRQ); */ - } + if (err < 0) { + pr_err("Device '%s' read returned %d, shutting it down\n", + lp->dev->name, err); + dev_close(lp->dev); + } else { + /* FIXME reactivate_fd(lp->fd, ISS_ETH_IRQ); */ } - spin_unlock(&opened_lock); return ret; } @@ -351,10 +346,8 @@ static void iss_net_timer(struct timer_list *t) { struct iss_net_private *lp = from_timer(lp, t, timer); - iss_net_poll(); - spin_lock(&lp->lock); + iss_net_poll(lp); mod_timer(&lp->timer, jiffies + lp->timer_val); - spin_unlock(&lp->lock); } @@ -363,11 +356,9 @@ static int iss_net_open(struct net_device *dev) struct iss_net_private *lp = netdev_priv(dev); int err; - spin_lock_bh(&lp->lock); - - err = lp->tp.open(lp); + err = lp->tp.net_ops->open(lp); if (err < 0) - goto out; + return err; netif_start_queue(dev); @@ -378,36 +369,21 @@ static int iss_net_open(struct net_device *dev) while ((err = iss_net_rx(dev)) > 0) ; - spin_unlock_bh(&lp->lock); - spin_lock_bh(&opened_lock); - list_add(&lp->opened_list, &opened); - spin_unlock_bh(&opened_lock); - spin_lock_bh(&lp->lock); - timer_setup(&lp->timer, iss_net_timer, 0); lp->timer_val = ISS_NET_TIMER_VALUE; mod_timer(&lp->timer, jiffies + lp->timer_val); -out: - spin_unlock_bh(&lp->lock); return err; } static int iss_net_close(struct net_device *dev) { struct iss_net_private *lp = netdev_priv(dev); - netif_stop_queue(dev); - spin_lock_bh(&lp->lock); - - spin_lock(&opened_lock); - list_del(&opened); - spin_unlock(&opened_lock); + netif_stop_queue(dev); del_timer_sync(&lp->timer); + lp->tp.net_ops->close(lp); - lp->tp.close(lp); - - spin_unlock_bh(&lp->lock); return 0; } @@ -417,13 +393,14 @@ static int iss_net_start_xmit(struct sk_buff *skb, struct net_device *dev) int len; netif_stop_queue(dev); - spin_lock_bh(&lp->lock); - len = lp->tp.write(lp, &skb); + len = lp->tp.net_ops->write(lp, &skb); if (len == skb->len) { + spin_lock_bh(&lp->lock); lp->stats.tx_packets++; lp->stats.tx_bytes += skb->len; + spin_unlock_bh(&lp->lock); netif_trans_update(dev); netif_start_queue(dev); @@ -432,24 +409,29 @@ static int iss_net_start_xmit(struct sk_buff *skb, struct net_device *dev) } else if (len == 0) { netif_start_queue(dev); + spin_lock_bh(&lp->lock); lp->stats.tx_dropped++; + spin_unlock_bh(&lp->lock); } else { netif_start_queue(dev); pr_err("%s: %s failed(%d)\n", dev->name, __func__, len); } - spin_unlock_bh(&lp->lock); dev_kfree_skb(skb); return NETDEV_TX_OK; } -static struct net_device_stats *iss_net_get_stats(struct net_device *dev) +static void iss_net_get_stats64(struct net_device *dev, + struct rtnl_link_stats64 *stats) { struct iss_net_private *lp = netdev_priv(dev); - return &lp->stats; + + spin_lock_bh(&lp->lock); + *stats = lp->stats; + spin_unlock_bh(&lp->lock); } static void iss_net_set_multicast_list(struct net_device *dev) @@ -460,19 +442,6 @@ static void iss_net_tx_timeout(struct net_device *dev, unsigned int txqueue) { } -static int iss_net_set_mac(struct net_device *dev, void *addr) -{ - struct iss_net_private *lp = netdev_priv(dev); - struct sockaddr *hwaddr = addr; - - if (!is_valid_ether_addr(hwaddr->sa_data)) - return -EADDRNOTAVAIL; - spin_lock_bh(&lp->lock); - eth_hw_addr_set(dev, hwaddr->sa_data); - spin_unlock_bh(&lp->lock); - return 0; -} - static int iss_net_change_mtu(struct net_device *dev, int new_mtu) { return -EINVAL; @@ -494,11 +463,11 @@ static int driver_registered; static const struct net_device_ops iss_netdev_ops = { .ndo_open = iss_net_open, .ndo_stop = iss_net_close, - .ndo_get_stats = iss_net_get_stats, + .ndo_get_stats64 = iss_net_get_stats64, .ndo_start_xmit = iss_net_start_xmit, .ndo_validate_addr = eth_validate_addr, .ndo_change_mtu = iss_net_change_mtu, - .ndo_set_mac_address = iss_net_set_mac, + .ndo_set_mac_address = eth_mac_addr, .ndo_tx_timeout = iss_net_tx_timeout, .ndo_set_rx_mode = iss_net_set_multicast_list, }; @@ -520,7 +489,6 @@ static int iss_net_configure(int index, char *init) lp = netdev_priv(dev); *lp = (struct iss_net_private) { .device_list = LIST_HEAD_INIT(lp->device_list), - .opened_list = LIST_HEAD_INIT(lp->opened_list), .dev = dev, .index = index, }; diff --git a/arch/xtensa/platforms/iss/simdisk.c b/arch/xtensa/platforms/iss/simdisk.c index 0f0e0724397f..4255b92fa3eb 100644 --- a/arch/xtensa/platforms/iss/simdisk.c +++ b/arch/xtensa/platforms/iss/simdisk.c @@ -211,12 +211,18 @@ static ssize_t proc_read_simdisk(struct file *file, char __user *buf, struct simdisk *dev = pde_data(file_inode(file)); const char *s = dev->filename; if (s) { - ssize_t n = simple_read_from_buffer(buf, size, ppos, - s, strlen(s)); - if (n < 0) - return n; - buf += n; - size -= n; + ssize_t len = strlen(s); + char *temp = kmalloc(len + 2, GFP_KERNEL); + + if (!temp) + return -ENOMEM; + + len = scnprintf(temp, len + 2, "%s\n", s); + len = simple_read_from_buffer(buf, size, ppos, + temp, len); + + kfree(temp); + return len; } return simple_read_from_buffer(buf, size, ppos, "\n", 1); } diff --git a/arch/xtensa/platforms/xt2000/setup.c b/arch/xtensa/platforms/xt2000/setup.c index 145d129be76f..0dc22c371614 100644 --- a/arch/xtensa/platforms/xt2000/setup.c +++ b/arch/xtensa/platforms/xt2000/setup.c @@ -78,7 +78,7 @@ void __init platform_init(bp_tag_t *first) void platform_heartbeat(void) { - static int i=0, t = 0; + static int i, t; if (--t < 0) { diff --git a/block/Makefile b/block/Makefile index 3950ecbc5c26..4e01bb71ad6e 100644 --- a/block/Makefile +++ b/block/Makefile @@ -16,6 +16,7 @@ obj-$(CONFIG_BLK_DEV_BSG_COMMON) += bsg.o obj-$(CONFIG_BLK_DEV_BSGLIB) += bsg-lib.o obj-$(CONFIG_BLK_CGROUP) += blk-cgroup.o obj-$(CONFIG_BLK_CGROUP_RWSTAT) += blk-cgroup-rwstat.o +obj-$(CONFIG_BLK_CGROUP_FC_APPID) += blk-cgroup-fc-appid.o obj-$(CONFIG_BLK_DEV_THROTTLING) += blk-throttle.o obj-$(CONFIG_BLK_CGROUP_IOPRIO) += blk-ioprio.o obj-$(CONFIG_BLK_CGROUP_IOLATENCY) += blk-iolatency.o diff --git a/block/badblocks.c b/block/badblocks.c index d39056630d9c..3afb550c0f7b 100644 --- a/block/badblocks.c +++ b/block/badblocks.c @@ -65,7 +65,6 @@ int badblocks_check(struct badblocks *bb, sector_t s, int sectors, s >>= bb->shift; target += (1<<bb->shift) - 1; target >>= bb->shift; - sectors = target - s; } /* 'target' is now the first block after the bad range */ @@ -345,7 +344,6 @@ int badblocks_clear(struct badblocks *bb, sector_t s, int sectors) s += (1<<bb->shift) - 1; s >>= bb->shift; target >>= bb->shift; - sectors = target - s; } write_seqlock_irq(&bb->lock); diff --git a/block/bdev.c b/block/bdev.c index 13de871fa816..5fe06c1f2def 100644 --- a/block/bdev.c +++ b/block/bdev.c @@ -200,6 +200,13 @@ int sync_blockdev(struct block_device *bdev) } EXPORT_SYMBOL(sync_blockdev); +int sync_blockdev_range(struct block_device *bdev, loff_t lstart, loff_t lend) +{ + return filemap_write_and_wait_range(bdev->bd_inode->i_mapping, + lstart, lend); +} +EXPORT_SYMBOL(sync_blockdev_range); + /* * Write out and wait upon all dirty data associated with this * device. Filesystem data as well as the underlying block @@ -673,17 +680,17 @@ static int blkdev_get_whole(struct block_device *bdev, fmode_t mode) } } - if (!bdev->bd_openers) + if (!atomic_read(&bdev->bd_openers)) set_init_blocksize(bdev); if (test_bit(GD_NEED_PART_SCAN, &disk->state)) bdev_disk_changed(disk, false); - bdev->bd_openers++; + atomic_inc(&bdev->bd_openers); return 0; } static void blkdev_put_whole(struct block_device *bdev, fmode_t mode) { - if (!--bdev->bd_openers) + if (atomic_dec_and_test(&bdev->bd_openers)) blkdev_flush_mapping(bdev); if (bdev->bd_disk->fops->release) bdev->bd_disk->fops->release(bdev->bd_disk, mode); @@ -694,7 +701,7 @@ static int blkdev_get_part(struct block_device *part, fmode_t mode) struct gendisk *disk = part->bd_disk; int ret; - if (part->bd_openers) + if (atomic_read(&part->bd_openers)) goto done; ret = blkdev_get_whole(bdev_whole(part), mode); @@ -708,7 +715,7 @@ static int blkdev_get_part(struct block_device *part, fmode_t mode) disk->open_partitions++; set_init_blocksize(part); done: - part->bd_openers++; + atomic_inc(&part->bd_openers); return 0; out_blkdev_put: @@ -720,7 +727,7 @@ static void blkdev_put_part(struct block_device *part, fmode_t mode) { struct block_device *whole = bdev_whole(part); - if (--part->bd_openers) + if (!atomic_dec_and_test(&part->bd_openers)) return; blkdev_flush_mapping(part); whole->bd_disk->open_partitions--; @@ -899,7 +906,7 @@ void blkdev_put(struct block_device *bdev, fmode_t mode) * of the world and we want to avoid long (could be several minute) * syncs while holding the mutex. */ - if (bdev->bd_openers == 1) + if (atomic_read(&bdev->bd_openers) == 1) sync_blockdev(bdev); mutex_lock(&disk->open_mutex); @@ -1044,7 +1051,7 @@ void sync_bdevs(bool wait) bdev = I_BDEV(inode); mutex_lock(&bdev->bd_disk->open_mutex); - if (!bdev->bd_openers) { + if (!atomic_read(&bdev->bd_openers)) { ; /* skip */ } else if (wait) { /* diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c index 420eda2589c0..09574af83566 100644 --- a/block/bfq-cgroup.c +++ b/block/bfq-cgroup.c @@ -557,6 +557,7 @@ static void bfq_pd_init(struct blkg_policy_data *pd) */ bfqg->bfqd = bfqd; bfqg->active_entities = 0; + bfqg->online = true; bfqg->rq_pos_tree = RB_ROOT; } @@ -585,28 +586,11 @@ static void bfq_group_set_parent(struct bfq_group *bfqg, entity->sched_data = &parent->sched_data; } -static struct bfq_group *bfq_lookup_bfqg(struct bfq_data *bfqd, - struct blkcg *blkcg) +static void bfq_link_bfqg(struct bfq_data *bfqd, struct bfq_group *bfqg) { - struct blkcg_gq *blkg; - - blkg = blkg_lookup(blkcg, bfqd->queue); - if (likely(blkg)) - return blkg_to_bfqg(blkg); - return NULL; -} - -struct bfq_group *bfq_find_set_group(struct bfq_data *bfqd, - struct blkcg *blkcg) -{ - struct bfq_group *bfqg, *parent; + struct bfq_group *parent; struct bfq_entity *entity; - bfqg = bfq_lookup_bfqg(bfqd, blkcg); - - if (unlikely(!bfqg)) - return NULL; - /* * Update chain of bfq_groups as we might be handling a leaf group * which, along with some of its relatives, has not been hooked yet @@ -623,8 +607,24 @@ struct bfq_group *bfq_find_set_group(struct bfq_data *bfqd, bfq_group_set_parent(curr_bfqg, parent); } } +} - return bfqg; +struct bfq_group *bfq_bio_bfqg(struct bfq_data *bfqd, struct bio *bio) +{ + struct blkcg_gq *blkg = bio->bi_blkg; + struct bfq_group *bfqg; + + while (blkg) { + bfqg = blkg_to_bfqg(blkg); + if (bfqg->online) { + bio_associate_blkg_from_css(bio, &blkg->blkcg->css); + return bfqg; + } + blkg = blkg->parent; + } + bio_associate_blkg_from_css(bio, + &bfqg_to_blkg(bfqd->root_group)->blkcg->css); + return bfqd->root_group; } /** @@ -714,25 +714,15 @@ void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq, * Move bic to blkcg, assuming that bfqd->lock is held; which makes * sure that the reference to cgroup is valid across the call (see * comments in bfq_bic_update_cgroup on this issue) - * - * NOTE: an alternative approach might have been to store the current - * cgroup in bfqq and getting a reference to it, reducing the lookup - * time here, at the price of slightly more complex code. */ -static struct bfq_group *__bfq_bic_change_cgroup(struct bfq_data *bfqd, - struct bfq_io_cq *bic, - struct blkcg *blkcg) +static void *__bfq_bic_change_cgroup(struct bfq_data *bfqd, + struct bfq_io_cq *bic, + struct bfq_group *bfqg) { struct bfq_queue *async_bfqq = bic_to_bfqq(bic, 0); struct bfq_queue *sync_bfqq = bic_to_bfqq(bic, 1); - struct bfq_group *bfqg; struct bfq_entity *entity; - bfqg = bfq_find_set_group(bfqd, blkcg); - - if (unlikely(!bfqg)) - bfqg = bfqd->root_group; - if (async_bfqq) { entity = &async_bfqq->entity; @@ -743,9 +733,39 @@ static struct bfq_group *__bfq_bic_change_cgroup(struct bfq_data *bfqd, } if (sync_bfqq) { - entity = &sync_bfqq->entity; - if (entity->sched_data != &bfqg->sched_data) - bfq_bfqq_move(bfqd, sync_bfqq, bfqg); + if (!sync_bfqq->new_bfqq && !bfq_bfqq_coop(sync_bfqq)) { + /* We are the only user of this bfqq, just move it */ + if (sync_bfqq->entity.sched_data != &bfqg->sched_data) + bfq_bfqq_move(bfqd, sync_bfqq, bfqg); + } else { + struct bfq_queue *bfqq; + + /* + * The queue was merged to a different queue. Check + * that the merge chain still belongs to the same + * cgroup. + */ + for (bfqq = sync_bfqq; bfqq; bfqq = bfqq->new_bfqq) + if (bfqq->entity.sched_data != + &bfqg->sched_data) + break; + if (bfqq) { + /* + * Some queue changed cgroup so the merge is + * not valid anymore. We cannot easily just + * cancel the merge (by clearing new_bfqq) as + * there may be other processes using this + * queue and holding refs to all queues below + * sync_bfqq->new_bfqq. Similarly if the merge + * already happened, we need to detach from + * bfqq now so that we cannot merge bio to a + * request from the old cgroup. + */ + bfq_put_cooperator(sync_bfqq); + bfq_release_process_ref(bfqd, sync_bfqq); + bic_set_bfqq(bic, NULL, 1); + } + } } return bfqg; @@ -754,20 +774,24 @@ static struct bfq_group *__bfq_bic_change_cgroup(struct bfq_data *bfqd, void bfq_bic_update_cgroup(struct bfq_io_cq *bic, struct bio *bio) { struct bfq_data *bfqd = bic_to_bfqd(bic); - struct bfq_group *bfqg = NULL; + struct bfq_group *bfqg = bfq_bio_bfqg(bfqd, bio); uint64_t serial_nr; - rcu_read_lock(); - serial_nr = __bio_blkcg(bio)->css.serial_nr; + serial_nr = bfqg_to_blkg(bfqg)->blkcg->css.serial_nr; /* * Check whether blkcg has changed. The condition may trigger * spuriously on a newly created cic but there's no harm. */ if (unlikely(!bfqd) || likely(bic->blkcg_serial_nr == serial_nr)) - goto out; + return; - bfqg = __bfq_bic_change_cgroup(bfqd, bic, __bio_blkcg(bio)); + /* + * New cgroup for this process. Make sure it is linked to bfq internal + * cgroup hierarchy. + */ + bfq_link_bfqg(bfqd, bfqg); + __bfq_bic_change_cgroup(bfqd, bic, bfqg); /* * Update blkg_path for bfq_log_* functions. We cache this * path, and update it here, for the following @@ -820,8 +844,6 @@ void bfq_bic_update_cgroup(struct bfq_io_cq *bic, struct bio *bio) */ blkg_path(bfqg_to_blkg(bfqg), bfqg->blkg_path, sizeof(bfqg->blkg_path)); bic->blkcg_serial_nr = serial_nr; -out: - rcu_read_unlock(); } /** @@ -949,6 +971,7 @@ static void bfq_pd_offline(struct blkg_policy_data *pd) put_async_queues: bfq_put_async_queues(bfqd, bfqg); + bfqg->online = false; spin_unlock_irqrestore(&bfqd->lock, flags); /* @@ -1438,7 +1461,7 @@ void bfq_end_wr_async(struct bfq_data *bfqd) bfq_end_wr_async_queues(bfqd, bfqd->root_group); } -struct bfq_group *bfq_find_set_group(struct bfq_data *bfqd, struct blkcg *blkcg) +struct bfq_group *bfq_bio_bfqg(struct bfq_data *bfqd, struct bio *bio) { return bfqd->root_group; } diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 2e0dd68a3cbe..0d46cb728bbf 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -374,7 +374,7 @@ static const unsigned long bfq_activation_stable_merging = 600; */ static const unsigned long bfq_late_stable_merging = 600; -#define RQ_BIC(rq) icq_to_bic((rq)->elv.priv[0]) +#define RQ_BIC(rq) ((struct bfq_io_cq *)((rq)->elv.priv[0])) #define RQ_BFQQ(rq) ((rq)->elv.priv[1]) struct bfq_queue *bic_to_bfqq(struct bfq_io_cq *bic, bool is_sync) @@ -456,6 +456,8 @@ static struct bfq_io_cq *bfq_bic_lookup(struct request_queue *q) */ void bfq_schedule_dispatch(struct bfq_data *bfqd) { + lockdep_assert_held(&bfqd->lock); + if (bfqd->queued != 0) { bfq_log(bfqd, "schedule dispatch"); blk_mq_run_hw_queues(bfqd->queue, true); @@ -569,7 +571,7 @@ static bool bfqq_request_over_limit(struct bfq_queue *bfqq, int limit) struct bfq_entity *entity = &bfqq->entity; struct bfq_entity *inline_entities[BFQ_LIMIT_INLINE_DEPTH]; struct bfq_entity **entities = inline_entities; - int depth, level; + int depth, level, alloc_depth = BFQ_LIMIT_INLINE_DEPTH; int class_idx = bfqq->ioprio_class - 1; struct bfq_sched_data *sched_data; unsigned long wsum; @@ -578,15 +580,21 @@ static bool bfqq_request_over_limit(struct bfq_queue *bfqq, int limit) if (!entity->on_st_or_in_serv) return false; +retry: + spin_lock_irq(&bfqd->lock); /* +1 for bfqq entity, root cgroup not included */ depth = bfqg_to_blkg(bfqq_group(bfqq))->blkcg->css.cgroup->level + 1; - if (depth > BFQ_LIMIT_INLINE_DEPTH) { + if (depth > alloc_depth) { + spin_unlock_irq(&bfqd->lock); + if (entities != inline_entities) + kfree(entities); entities = kmalloc_array(depth, sizeof(*entities), GFP_NOIO); if (!entities) return false; + alloc_depth = depth; + goto retry; } - spin_lock_irq(&bfqd->lock); sched_data = entity->sched_data; /* Gather our ancestors as we need to traverse them in reverse order */ level = 0; @@ -2127,9 +2135,7 @@ static void bfq_check_waker(struct bfq_data *bfqd, struct bfq_queue *bfqq, if (!bfqd->last_completed_rq_bfqq || bfqd->last_completed_rq_bfqq == bfqq || bfq_bfqq_has_short_ttime(bfqq) || - bfqq->dispatched > 0 || - now_ns - bfqd->last_completion >= 4 * NSEC_PER_MSEC || - bfqd->last_completed_rq_bfqq == bfqq->waker_bfqq) + now_ns - bfqd->last_completion >= 4 * NSEC_PER_MSEC) return; /* @@ -2202,9 +2208,13 @@ static void bfq_add_request(struct request *rq) bfq_log_bfqq(bfqd, bfqq, "add_request %d", rq_is_sync(rq)); bfqq->queued[rq_is_sync(rq)]++; - bfqd->queued++; + /* + * Updating of 'bfqd->queued' is protected by 'bfqd->lock', however, it + * may be read without holding the lock in bfq_has_work(). + */ + WRITE_ONCE(bfqd->queued, bfqd->queued + 1); - if (RB_EMPTY_ROOT(&bfqq->sort_list) && bfq_bfqq_sync(bfqq)) { + if (bfq_bfqq_sync(bfqq) && RQ_BIC(rq)->requests <= 1) { bfq_check_waker(bfqd, bfqq, now_ns); /* @@ -2394,7 +2404,11 @@ static void bfq_remove_request(struct request_queue *q, if (rq->queuelist.prev != &rq->queuelist) list_del_init(&rq->queuelist); bfqq->queued[sync]--; - bfqd->queued--; + /* + * Updating of 'bfqd->queued' is protected by 'bfqd->lock', however, it + * may be read without holding the lock in bfq_has_work(). + */ + WRITE_ONCE(bfqd->queued, bfqd->queued - 1); elv_rb_del(&bfqq->sort_list, rq); elv_rqhash_del(q, rq); @@ -2457,10 +2471,17 @@ static bool bfq_bio_merge(struct request_queue *q, struct bio *bio, spin_lock_irq(&bfqd->lock); - if (bic) + if (bic) { + /* + * Make sure cgroup info is uptodate for current process before + * considering the merge. + */ + bfq_bic_update_cgroup(bic, bio); + bfqd->bio_bfqq = bic_to_bfqq(bic, op_is_sync(bio->bi_opf)); - else + } else { bfqd->bio_bfqq = NULL; + } bfqd->bio_bic = bic; ret = blk_mq_sched_try_merge(q, bio, nr_segs, &free); @@ -2490,8 +2511,6 @@ static int bfq_request_merge(struct request_queue *q, struct request **req, return ELEVATOR_NO_MERGE; } -static struct bfq_queue *bfq_init_rq(struct request *rq); - static void bfq_request_merged(struct request_queue *q, struct request *req, enum elv_merge type) { @@ -2500,7 +2519,7 @@ static void bfq_request_merged(struct request_queue *q, struct request *req, blk_rq_pos(req) < blk_rq_pos(container_of(rb_prev(&req->rb_node), struct request, rb_node))) { - struct bfq_queue *bfqq = bfq_init_rq(req); + struct bfq_queue *bfqq = RQ_BFQQ(req); struct bfq_data *bfqd; struct request *prev, *next_rq; @@ -2552,8 +2571,8 @@ static void bfq_request_merged(struct request_queue *q, struct request *req, static void bfq_requests_merged(struct request_queue *q, struct request *rq, struct request *next) { - struct bfq_queue *bfqq = bfq_init_rq(rq), - *next_bfqq = bfq_init_rq(next); + struct bfq_queue *bfqq = RQ_BFQQ(rq), + *next_bfqq = RQ_BFQQ(next); if (!bfqq) goto remove; @@ -2758,6 +2777,14 @@ bfq_setup_merge(struct bfq_queue *bfqq, struct bfq_queue *new_bfqq) if (process_refs == 0 || new_process_refs == 0) return NULL; + /* + * Make sure merged queues belong to the same parent. Parents could + * have changed since the time we decided the two queues are suitable + * for merging. + */ + if (new_bfqq->entity.parent != bfqq->entity.parent) + return NULL; + bfq_log_bfqq(bfqq->bfqd, bfqq, "scheduling merge with queue %d", new_bfqq->pid); @@ -2895,9 +2922,12 @@ bfq_setup_cooperator(struct bfq_data *bfqd, struct bfq_queue *bfqq, struct bfq_queue *new_bfqq = bfq_setup_merge(bfqq, stable_merge_bfqq); - bic->stably_merged = true; - if (new_bfqq && new_bfqq->bic) - new_bfqq->bic->stably_merged = true; + if (new_bfqq) { + bic->stably_merged = true; + if (new_bfqq->bic) + new_bfqq->bic->stably_merged = + true; + } return new_bfqq; } else return NULL; @@ -5039,11 +5069,11 @@ static bool bfq_has_work(struct blk_mq_hw_ctx *hctx) struct bfq_data *bfqd = hctx->queue->elevator->elevator_data; /* - * Avoiding lock: a race on bfqd->busy_queues should cause at + * Avoiding lock: a race on bfqd->queued should cause at * most a call to dispatch for nothing */ return !list_empty_careful(&bfqd->dispatch) || - bfq_tot_busy_queues(bfqd) > 0; + READ_ONCE(bfqd->queued); } static struct request *__bfq_dispatch_request(struct blk_mq_hw_ctx *hctx) @@ -5304,7 +5334,7 @@ static void bfq_put_stable_ref(struct bfq_queue *bfqq) bfq_put_queue(bfqq); } -static void bfq_put_cooperator(struct bfq_queue *bfqq) +void bfq_put_cooperator(struct bfq_queue *bfqq) { struct bfq_queue *__bfqq, *next; @@ -5710,14 +5740,7 @@ static struct bfq_queue *bfq_get_queue(struct bfq_data *bfqd, struct bfq_queue *bfqq; struct bfq_group *bfqg; - rcu_read_lock(); - - bfqg = bfq_find_set_group(bfqd, __bio_blkcg(bio)); - if (!bfqg) { - bfqq = &bfqd->oom_bfqq; - goto out; - } - + bfqg = bfq_bio_bfqg(bfqd, bio); if (!is_sync) { async_bfqq = bfq_async_queue_prio(bfqd, bfqg, ioprio_class, ioprio); @@ -5763,8 +5786,6 @@ out: if (bfqq != &bfqd->oom_bfqq && is_sync && !respawn) bfqq = bfq_do_or_sched_stable_merge(bfqd, bfqq, bic); - - rcu_read_unlock(); return bfqq; } @@ -6111,6 +6132,8 @@ static inline void bfq_update_insert_stats(struct request_queue *q, unsigned int cmd_flags) {} #endif /* CONFIG_BFQ_CGROUP_DEBUG */ +static struct bfq_queue *bfq_init_rq(struct request *rq); + static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq, bool at_head) { @@ -6126,18 +6149,15 @@ static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq, bfqg_stats_update_legacy_io(q, rq); #endif spin_lock_irq(&bfqd->lock); + bfqq = bfq_init_rq(rq); if (blk_mq_sched_try_insert_merge(q, rq, &free)) { spin_unlock_irq(&bfqd->lock); blk_mq_free_requests(&free); return; } - spin_unlock_irq(&bfqd->lock); - trace_block_rq_insert(rq); - spin_lock_irq(&bfqd->lock); - bfqq = bfq_init_rq(rq); if (!bfqq || at_head) { if (at_head) list_add(&rq->queuelist, &bfqd->dispatch); @@ -6354,12 +6374,6 @@ static void bfq_completed_request(struct bfq_queue *bfqq, struct bfq_data *bfqd) bfq_schedule_dispatch(bfqd); } -static void bfq_finish_requeue_request_body(struct bfq_queue *bfqq) -{ - bfqq_request_freed(bfqq); - bfq_put_queue(bfqq); -} - /* * The processes associated with bfqq may happen to generate their * cumulative I/O at a lower rate than the rate at which the device @@ -6556,7 +6570,9 @@ static void bfq_finish_requeue_request(struct request *rq) bfq_completed_request(bfqq, bfqd); } - bfq_finish_requeue_request_body(bfqq); + bfqq_request_freed(bfqq); + bfq_put_queue(bfqq); + RQ_BIC(rq)->requests--; spin_unlock_irqrestore(&bfqd->lock, flags); /* @@ -6790,6 +6806,7 @@ static struct bfq_queue *bfq_init_rq(struct request *rq) bfqq_request_allocated(bfqq); bfqq->ref++; + bic->requests++; bfq_log_bfqq(bfqd, bfqq, "get_request %p: bfqq %p, %d", rq, bfqq, bfqq->ref); @@ -6886,8 +6903,8 @@ bfq_idle_slice_timer_body(struct bfq_data *bfqd, struct bfq_queue *bfqq) bfq_bfqq_expire(bfqd, bfqq, true, reason); schedule_dispatch: - spin_unlock_irqrestore(&bfqd->lock, flags); bfq_schedule_dispatch(bfqd); + spin_unlock_irqrestore(&bfqd->lock, flags); } /* diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h index 3b83e3d1c2e5..ca8177d7bf7c 100644 --- a/block/bfq-iosched.h +++ b/block/bfq-iosched.h @@ -468,6 +468,7 @@ struct bfq_io_cq { struct bfq_queue *stable_merge_bfqq; bool stably_merged; /* non splittable if true */ + unsigned int requests; /* Number of requests this process has in flight */ }; /** @@ -928,6 +929,8 @@ struct bfq_group { /* reference counter (see comments in bfq_bic_update_cgroup) */ int ref; + /* Is bfq_group still online? */ + bool online; struct bfq_entity entity; struct bfq_sched_data sched_data; @@ -979,6 +982,7 @@ void bfq_weights_tree_remove(struct bfq_data *bfqd, void bfq_bfqq_expire(struct bfq_data *bfqd, struct bfq_queue *bfqq, bool compensate, enum bfqq_expiration reason); void bfq_put_queue(struct bfq_queue *bfqq); +void bfq_put_cooperator(struct bfq_queue *bfqq); void bfq_end_wr_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg); void bfq_release_process_ref(struct bfq_data *bfqd, struct bfq_queue *bfqq); void bfq_schedule_dispatch(struct bfq_data *bfqd); @@ -1006,8 +1010,7 @@ void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq, void bfq_init_entity(struct bfq_entity *entity, struct bfq_group *bfqg); void bfq_bic_update_cgroup(struct bfq_io_cq *bic, struct bio *bio); void bfq_end_wr_async(struct bfq_data *bfqd); -struct bfq_group *bfq_find_set_group(struct bfq_data *bfqd, - struct blkcg *blkcg); +struct bfq_group *bfq_bio_bfqg(struct bfq_data *bfqd, struct bio *bio); struct blkcg_gq *bfqg_to_blkg(struct bfq_group *bfqg); struct bfq_group *bfqq_group(struct bfq_queue *bfqq); struct bfq_group *bfq_create_group_hierarchy(struct bfq_data *bfqd, int node); @@ -1100,13 +1103,13 @@ struct bfq_group *bfqq_group(struct bfq_queue *bfqq); break; \ bfq_bfqq_name((bfqq), pid_str, MAX_BFQQ_NAME_LENGTH); \ blk_add_cgroup_trace_msg((bfqd)->queue, \ - bfqg_to_blkg(bfqq_group(bfqq))->blkcg, \ + &bfqg_to_blkg(bfqq_group(bfqq))->blkcg->css, \ "%s " fmt, pid_str, ##args); \ } while (0) #define bfq_log_bfqg(bfqd, bfqg, fmt, args...) do { \ blk_add_cgroup_trace_msg((bfqd)->queue, \ - bfqg_to_blkg(bfqg)->blkcg, fmt, ##args); \ + &bfqg_to_blkg(bfqg)->blkcg->css, fmt, ##args); \ } while (0) #else /* CONFIG_BFQ_GROUP_IOSCHED */ diff --git a/block/bio.c b/block/bio.c index cdd7b2915c53..a3893d80dccc 100644 --- a/block/bio.c +++ b/block/bio.c @@ -224,24 +224,13 @@ EXPORT_SYMBOL(bio_uninit); static void bio_free(struct bio *bio) { struct bio_set *bs = bio->bi_pool; - void *p; - - bio_uninit(bio); + void *p = bio; - if (bs) { - bvec_free(&bs->bvec_pool, bio->bi_io_vec, bio->bi_max_vecs); + WARN_ON_ONCE(!bs); - /* - * If we have front padding, adjust the bio pointer before freeing - */ - p = bio; - p -= bs->front_pad; - - mempool_free(p, &bs->bio_pool); - } else { - /* Bio was allocated by bio_kmalloc() */ - kfree(bio); - } + bio_uninit(bio); + bvec_free(&bs->bvec_pool, bio->bi_io_vec, bio->bi_max_vecs); + mempool_free(p - bs->front_pad, &bs->bio_pool); } /* @@ -419,6 +408,28 @@ static void punt_bios_to_rescuer(struct bio_set *bs) queue_work(bs->rescue_workqueue, &bs->rescue_work); } +static struct bio *bio_alloc_percpu_cache(struct block_device *bdev, + unsigned short nr_vecs, unsigned int opf, gfp_t gfp, + struct bio_set *bs) +{ + struct bio_alloc_cache *cache; + struct bio *bio; + + cache = per_cpu_ptr(bs->cache, get_cpu()); + if (!cache->free_list) { + put_cpu(); + return NULL; + } + bio = cache->free_list; + cache->free_list = bio->bi_next; + cache->nr--; + put_cpu(); + + bio_init(bio, bdev, nr_vecs ? bio->bi_inline_vecs : NULL, nr_vecs, opf); + bio->bi_pool = bs; + return bio; +} + /** * bio_alloc_bioset - allocate a bio for I/O * @bdev: block device to allocate the bio for (can be %NULL) @@ -451,6 +462,9 @@ static void punt_bios_to_rescuer(struct bio_set *bs) * submit_bio_noacct() should be avoided - instead, use bio_set's front_pad * for per bio allocations. * + * If REQ_ALLOC_CACHE is set, the final put of the bio MUST be done from process + * context, not hard/soft IRQ. + * * Returns: Pointer to new bio on success, NULL on failure. */ struct bio *bio_alloc_bioset(struct block_device *bdev, unsigned short nr_vecs, @@ -465,6 +479,21 @@ struct bio *bio_alloc_bioset(struct block_device *bdev, unsigned short nr_vecs, if (WARN_ON_ONCE(!mempool_initialized(&bs->bvec_pool) && nr_vecs > 0)) return NULL; + if (opf & REQ_ALLOC_CACHE) { + if (bs->cache && nr_vecs <= BIO_INLINE_VECS) { + bio = bio_alloc_percpu_cache(bdev, nr_vecs, opf, + gfp_mask, bs); + if (bio) + return bio; + /* + * No cached bio available, bio returned below marked with + * REQ_ALLOC_CACHE to particpate in per-cpu alloc cache. + */ + } else { + opf &= ~REQ_ALLOC_CACHE; + } + } + /* * submit_bio_noacct() converts recursion to iteration; this means if * we're running beneath it, any bios we allocate and submit will not be @@ -528,28 +557,28 @@ err_free: EXPORT_SYMBOL(bio_alloc_bioset); /** - * bio_kmalloc - kmalloc a bio for I/O + * bio_kmalloc - kmalloc a bio + * @nr_vecs: number of bio_vecs to allocate * @gfp_mask: the GFP_* mask given to the slab allocator - * @nr_iovecs: number of iovecs to pre-allocate * - * Use kmalloc to allocate and initialize a bio. + * Use kmalloc to allocate a bio (including bvecs). The bio must be initialized + * using bio_init() before use. To free a bio returned from this function use + * kfree() after calling bio_uninit(). A bio returned from this function can + * be reused by calling bio_uninit() before calling bio_init() again. + * + * Note that unlike bio_alloc() or bio_alloc_bioset() allocations from this + * function are not backed by a mempool can can fail. Do not use this function + * for allocations in the file system I/O path. * * Returns: Pointer to new bio on success, NULL on failure. */ -struct bio *bio_kmalloc(gfp_t gfp_mask, unsigned short nr_iovecs) +struct bio *bio_kmalloc(unsigned short nr_vecs, gfp_t gfp_mask) { struct bio *bio; - if (nr_iovecs > UIO_MAXIOV) - return NULL; - - bio = kmalloc(struct_size(bio, bi_inline_vecs, nr_iovecs), gfp_mask); - if (unlikely(!bio)) + if (nr_vecs > UIO_MAXIOV) return NULL; - bio_init(bio, NULL, nr_iovecs ? bio->bi_inline_vecs : NULL, nr_iovecs, - 0); - bio->bi_pool = NULL; - return bio; + return kmalloc(struct_size(bio, bi_inline_vecs, nr_vecs), gfp_mask); } EXPORT_SYMBOL(bio_kmalloc); @@ -711,7 +740,7 @@ void bio_put(struct bio *bio) return; } - if (bio_flagged(bio, BIO_PERCPU_CACHE)) { + if (bio->bi_opf & REQ_ALLOC_CACHE) { struct bio_alloc_cache *cache; bio_uninit(bio); @@ -732,14 +761,15 @@ static int __bio_clone(struct bio *bio, struct bio *bio_src, gfp_t gfp) bio_set_flag(bio, BIO_CLONED); if (bio_flagged(bio_src, BIO_THROTTLED)) bio_set_flag(bio, BIO_THROTTLED); - if (bio->bi_bdev == bio_src->bi_bdev && - bio_flagged(bio_src, BIO_REMAPPED)) - bio_set_flag(bio, BIO_REMAPPED); bio->bi_ioprio = bio_src->bi_ioprio; bio->bi_iter = bio_src->bi_iter; - bio_clone_blkg_association(bio, bio_src); - blkcg_bio_issue_init(bio); + if (bio->bi_bdev) { + if (bio->bi_bdev == bio_src->bi_bdev && + bio_flagged(bio_src, BIO_REMAPPED)) + bio_set_flag(bio, BIO_REMAPPED); + bio_clone_blkg_association(bio, bio_src); + } if (bio_crypt_clone(bio, bio_src, gfp) < 0) return -ENOMEM; @@ -1598,7 +1628,7 @@ EXPORT_SYMBOL(bio_split); void bio_trim(struct bio *bio, sector_t offset, sector_t size) { if (WARN_ON_ONCE(offset > BIO_MAX_SECTORS || size > BIO_MAX_SECTORS || - offset + size > bio->bi_iter.bi_size)) + offset + size > bio_sectors(bio))) return; size <<= 9; @@ -1727,55 +1757,13 @@ int bioset_init_from_src(struct bio_set *bs, struct bio_set *src) flags |= BIOSET_NEED_BVECS; if (src->rescue_workqueue) flags |= BIOSET_NEED_RESCUER; + if (src->cache) + flags |= BIOSET_PERCPU_CACHE; return bioset_init(bs, src->bio_pool.min_nr, src->front_pad, flags); } EXPORT_SYMBOL(bioset_init_from_src); -/** - * bio_alloc_kiocb - Allocate a bio from bio_set based on kiocb - * @kiocb: kiocb describing the IO - * @bdev: block device to allocate the bio for (can be %NULL) - * @nr_vecs: number of iovecs to pre-allocate - * @opf: operation and flags for bio - * @bs: bio_set to allocate from - * - * Description: - * Like @bio_alloc_bioset, but pass in the kiocb. The kiocb is only - * used to check if we should dip into the per-cpu bio_set allocation - * cache. The allocation uses GFP_KERNEL internally. On return, the - * bio is marked BIO_PERCPU_CACHEABLE, and the final put of the bio - * MUST be done from process context, not hard/soft IRQ. - * - */ -struct bio *bio_alloc_kiocb(struct kiocb *kiocb, struct block_device *bdev, - unsigned short nr_vecs, unsigned int opf, struct bio_set *bs) -{ - struct bio_alloc_cache *cache; - struct bio *bio; - - if (!(kiocb->ki_flags & IOCB_ALLOC_CACHE) || nr_vecs > BIO_INLINE_VECS) - return bio_alloc_bioset(bdev, nr_vecs, opf, GFP_KERNEL, bs); - - cache = per_cpu_ptr(bs->cache, get_cpu()); - if (cache->free_list) { - bio = cache->free_list; - cache->free_list = bio->bi_next; - cache->nr--; - put_cpu(); - bio_init(bio, bdev, nr_vecs ? bio->bi_inline_vecs : NULL, - nr_vecs, opf); - bio->bi_pool = bs; - bio_set_flag(bio, BIO_PERCPU_CACHE); - return bio; - } - put_cpu(); - bio = bio_alloc_bioset(bdev, nr_vecs, opf, GFP_KERNEL, bs); - bio_set_flag(bio, BIO_PERCPU_CACHE); - return bio; -} -EXPORT_SYMBOL_GPL(bio_alloc_kiocb); - static int __init init_bio(void) { int i; diff --git a/block/blk-cgroup-fc-appid.c b/block/blk-cgroup-fc-appid.c new file mode 100644 index 000000000000..760a2e1878dd --- /dev/null +++ b/block/blk-cgroup-fc-appid.c @@ -0,0 +1,57 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "blk-cgroup.h" + +/** + * blkcg_set_fc_appid - set the fc_app_id field associted to blkcg + * @app_id: application identifier + * @cgrp_id: cgroup id + * @app_id_len: size of application identifier + */ +int blkcg_set_fc_appid(char *app_id, u64 cgrp_id, size_t app_id_len) +{ + struct cgroup *cgrp; + struct cgroup_subsys_state *css; + struct blkcg *blkcg; + int ret = 0; + + if (app_id_len > FC_APPID_LEN) + return -EINVAL; + + cgrp = cgroup_get_from_id(cgrp_id); + if (!cgrp) + return -ENOENT; + css = cgroup_get_e_css(cgrp, &io_cgrp_subsys); + if (!css) { + ret = -ENOENT; + goto out_cgrp_put; + } + blkcg = css_to_blkcg(css); + /* + * There is a slight race condition on setting the appid. + * Worst case an I/O may not find the right id. + * This is no different from the I/O we let pass while obtaining + * the vmid from the fabric. + * Adding the overhead of a lock is not necessary. + */ + strlcpy(blkcg->fc_app_id, app_id, app_id_len); + css_put(css); +out_cgrp_put: + cgroup_put(cgrp); + return ret; +} +EXPORT_SYMBOL_GPL(blkcg_set_fc_appid); + +/** + * blkcg_get_fc_appid - get the fc app identifier associated with a bio + * @bio: target bio + * + * On success return the fc_app_id, on failure return NULL + */ +char *blkcg_get_fc_appid(struct bio *bio) +{ + if (!bio->bi_blkg || bio->bi_blkg->blkcg->fc_app_id[0] == '\0') + return NULL; + return bio->bi_blkg->blkcg->fc_app_id; +} +EXPORT_SYMBOL_GPL(blkcg_get_fc_appid); diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 8dfe62786cd5..40161a3f68d0 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -59,6 +59,23 @@ static struct workqueue_struct *blkcg_punt_bio_wq; #define BLKG_DESTROY_BATCH_SIZE 64 +/** + * blkcg_css - find the current css + * + * Find the css associated with either the kthread or the current task. + * This may return a dying css, so it is up to the caller to use tryget logic + * to confirm it is alive and well. + */ +static struct cgroup_subsys_state *blkcg_css(void) +{ + struct cgroup_subsys_state *css; + + css = kthread_blkcg(); + if (css) + return css; + return task_css(current, io_cgrp_id); +} + static bool blkcg_policy_enabled(struct request_queue *q, const struct blkcg_policy *pol) { @@ -156,6 +173,33 @@ static void blkg_async_bio_workfn(struct work_struct *work) } /** + * bio_blkcg_css - return the blkcg CSS associated with a bio + * @bio: target bio + * + * This returns the CSS for the blkcg associated with a bio, or %NULL if not + * associated. Callers are expected to either handle %NULL or know association + * has been done prior to calling this. + */ +struct cgroup_subsys_state *bio_blkcg_css(struct bio *bio) +{ + if (!bio || !bio->bi_blkg) + return NULL; + return &bio->bi_blkg->blkcg->css; +} +EXPORT_SYMBOL_GPL(bio_blkcg_css); + +/** + * blkcg_parent - get the parent of a blkcg + * @blkcg: blkcg of interest + * + * Return the parent blkcg of @blkcg. Can be called anytime. + */ +static inline struct blkcg *blkcg_parent(struct blkcg *blkcg) +{ + return css_to_blkcg(blkcg->css.parent); +} + +/** * blkg_alloc - allocate a blkg * @blkcg: block cgroup the new blkg is associated with * @q: request_queue the new blkg is associated with @@ -254,7 +298,6 @@ static struct blkcg_gq *blkg_create(struct blkcg *blkcg, struct blkcg_gq *blkg; int i, ret; - WARN_ON_ONCE(!rcu_read_lock_held()); lockdep_assert_held(&q->queue_lock); /* request_queue is dying, do not create/recreate a blkg */ @@ -905,7 +948,6 @@ static void blkcg_print_one_stat(struct blkcg_gq *blkg, struct seq_file *s) { struct blkg_iostat_set *bis = &blkg->iostat; u64 rbytes, wbytes, rios, wios, dbytes, dios; - bool has_stats = false; const char *dname; unsigned seq; int i; @@ -931,14 +973,12 @@ static void blkcg_print_one_stat(struct blkcg_gq *blkg, struct seq_file *s) } while (u64_stats_fetch_retry(&bis->sync, seq)); if (rbytes || wbytes || rios || wios) { - has_stats = true; seq_printf(s, "rbytes=%llu wbytes=%llu rios=%llu wios=%llu dbytes=%llu dios=%llu", rbytes, wbytes, rios, wios, dbytes, dios); } if (blkcg_debug_stats && atomic_read(&blkg->use_delay)) { - has_stats = true; seq_printf(s, " use_delay=%d delay_nsec=%llu", atomic_read(&blkg->use_delay), atomic64_read(&blkg->delay_nsec)); @@ -950,12 +990,10 @@ static void blkcg_print_one_stat(struct blkcg_gq *blkg, struct seq_file *s) if (!blkg->pd[i] || !pol->pd_stat_fn) continue; - if (pol->pd_stat_fn(blkg->pd[i], s)) - has_stats = true; + pol->pd_stat_fn(blkg->pd[i], s); } - if (has_stats) - seq_printf(s, "\n"); + seq_puts(s, "\n"); } static int blkcg_print_stat(struct seq_file *sf, void *v) @@ -994,6 +1032,13 @@ static struct cftype blkcg_legacy_files[] = { { } /* terminate */ }; +#ifdef CONFIG_CGROUP_WRITEBACK +struct list_head *blkcg_get_cgwb_list(struct cgroup_subsys_state *css) +{ + return &css_to_blkcg(css)->cgwb_list; +} +#endif + /* * blkcg destruction is a three-stage process. * @@ -1016,25 +1061,6 @@ static struct cftype blkcg_legacy_files[] = { */ /** - * blkcg_css_offline - cgroup css_offline callback - * @css: css of interest - * - * This function is called when @css is about to go away. Here the cgwbs are - * offlined first and only once writeback associated with the blkcg has - * finished do we start step 2 (see above). - */ -static void blkcg_css_offline(struct cgroup_subsys_state *css) -{ - struct blkcg *blkcg = css_to_blkcg(css); - - /* this prevents anyone from attaching or migrating to this blkcg */ - wb_blkcg_offline(blkcg); - - /* put the base online pin allowing step 2 to be triggered */ - blkcg_unpin_online(blkcg); -} - -/** * blkcg_destroy_blkgs - responsible for shooting down blkgs * @blkcg: blkcg of interest * @@ -1045,7 +1071,7 @@ static void blkcg_css_offline(struct cgroup_subsys_state *css) * * This is the blkcg counterpart of ioc_release_fn(). */ -void blkcg_destroy_blkgs(struct blkcg *blkcg) +static void blkcg_destroy_blkgs(struct blkcg *blkcg) { might_sleep(); @@ -1075,6 +1101,57 @@ void blkcg_destroy_blkgs(struct blkcg *blkcg) spin_unlock_irq(&blkcg->lock); } +/** + * blkcg_pin_online - pin online state + * @blkcg_css: blkcg of interest + * + * While pinned, a blkcg is kept online. This is primarily used to + * impedance-match blkg and cgwb lifetimes so that blkg doesn't go offline + * while an associated cgwb is still active. + */ +void blkcg_pin_online(struct cgroup_subsys_state *blkcg_css) +{ + refcount_inc(&css_to_blkcg(blkcg_css)->online_pin); +} + +/** + * blkcg_unpin_online - unpin online state + * @blkcg_css: blkcg of interest + * + * This is primarily used to impedance-match blkg and cgwb lifetimes so + * that blkg doesn't go offline while an associated cgwb is still active. + * When this count goes to zero, all active cgwbs have finished so the + * blkcg can continue destruction by calling blkcg_destroy_blkgs(). + */ +void blkcg_unpin_online(struct cgroup_subsys_state *blkcg_css) +{ + struct blkcg *blkcg = css_to_blkcg(blkcg_css); + + do { + if (!refcount_dec_and_test(&blkcg->online_pin)) + break; + blkcg_destroy_blkgs(blkcg); + blkcg = blkcg_parent(blkcg); + } while (blkcg); +} + +/** + * blkcg_css_offline - cgroup css_offline callback + * @css: css of interest + * + * This function is called when @css is about to go away. Here the cgwbs are + * offlined first and only once writeback associated with the blkcg has + * finished do we start step 2 (see above). + */ +static void blkcg_css_offline(struct cgroup_subsys_state *css) +{ + /* this prevents anyone from attaching or migrating to this blkcg */ + wb_blkcg_offline(css); + + /* put the base online pin allowing step 2 to be triggered */ + blkcg_unpin_online(css); +} + static void blkcg_css_free(struct cgroup_subsys_state *css) { struct blkcg *blkcg = css_to_blkcg(css); @@ -1163,8 +1240,7 @@ unlock: static int blkcg_css_online(struct cgroup_subsys_state *css) { - struct blkcg *blkcg = css_to_blkcg(css); - struct blkcg *parent = blkcg_parent(blkcg); + struct blkcg *parent = blkcg_parent(css_to_blkcg(css)); /* * blkcg_pin_online() is used to delay blkcg offline so that blkgs @@ -1172,7 +1248,7 @@ static int blkcg_css_online(struct cgroup_subsys_state *css) * parent so that offline always happens towards the root. */ if (parent) - blkcg_pin_online(parent); + blkcg_pin_online(css); return 0; } @@ -1201,14 +1277,13 @@ int blkcg_init_queue(struct request_queue *q) preloaded = !radix_tree_preload(GFP_KERNEL); /* Make sure the root blkg exists. */ - rcu_read_lock(); + /* spin_lock_irq can serve as RCU read-side critical section. */ spin_lock_irq(&q->queue_lock); blkg = blkg_create(&blkcg_root, q, new_blkg); if (IS_ERR(blkg)) goto err_unlock; q->root_blkg = blkg; spin_unlock_irq(&q->queue_lock); - rcu_read_unlock(); if (preloaded) radix_tree_preload_end(); @@ -1234,7 +1309,6 @@ err_destroy_all: return ret; err_unlock: spin_unlock_irq(&q->queue_lock); - rcu_read_unlock(); if (preloaded) radix_tree_preload_end(); return PTR_ERR(blkg); @@ -1726,7 +1800,6 @@ static void blkcg_maybe_throttle_blkg(struct blkcg_gq *blkg, bool use_memdelay) void blkcg_maybe_throttle_current(void) { struct request_queue *q = current->throttle_queue; - struct cgroup_subsys_state *css; struct blkcg *blkcg; struct blkcg_gq *blkg; bool use_memdelay = current->use_memdelay; @@ -1738,12 +1811,7 @@ void blkcg_maybe_throttle_current(void) current->use_memdelay = false; rcu_read_lock(); - css = kthread_blkcg(); - if (css) - blkcg = css_to_blkcg(css); - else - blkcg = css_to_blkcg(task_css(current, io_cgrp_id)); - + blkcg = css_to_blkcg(blkcg_css()); if (!blkcg) goto out; blkg = blkg_lookup(blkcg, q); @@ -1889,7 +1957,7 @@ void bio_associate_blkg(struct bio *bio) rcu_read_lock(); if (bio->bi_blkg) - css = &bio_blkcg(bio)->css; + css = bio_blkcg_css(bio); else css = blkcg_css(); @@ -1950,6 +2018,22 @@ void blk_cgroup_bio_start(struct bio *bio) put_cpu(); } +bool blk_cgroup_congested(void) +{ + struct cgroup_subsys_state *css; + bool ret = false; + + rcu_read_lock(); + for (css = blkcg_css(); css; css = css->parent) { + if (atomic_read(&css->cgroup->congestion_count)) { + ret = true; + break; + } + } + rcu_read_unlock(); + return ret; +} + static int __init blkcg_init(void) { blkcg_punt_bio_wq = alloc_workqueue("blkcg_punt_bio", diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h index 47e1e38390c9..d4de0a35e066 100644 --- a/block/blk-cgroup.h +++ b/block/blk-cgroup.h @@ -15,13 +15,101 @@ */ #include <linux/blk-cgroup.h> +#include <linux/cgroup.h> +#include <linux/kthread.h> #include <linux/blk-mq.h> +struct blkcg_gq; +struct blkg_policy_data; + + /* percpu_counter batch for blkg_[rw]stats, per-cpu drift doesn't matter */ #define BLKG_STAT_CPU_BATCH (INT_MAX / 2) #ifdef CONFIG_BLK_CGROUP +enum blkg_iostat_type { + BLKG_IOSTAT_READ, + BLKG_IOSTAT_WRITE, + BLKG_IOSTAT_DISCARD, + + BLKG_IOSTAT_NR, +}; + +struct blkg_iostat { + u64 bytes[BLKG_IOSTAT_NR]; + u64 ios[BLKG_IOSTAT_NR]; +}; + +struct blkg_iostat_set { + struct u64_stats_sync sync; + struct blkg_iostat cur; + struct blkg_iostat last; +}; + +/* association between a blk cgroup and a request queue */ +struct blkcg_gq { + /* Pointer to the associated request_queue */ + struct request_queue *q; + struct list_head q_node; + struct hlist_node blkcg_node; + struct blkcg *blkcg; + + /* all non-root blkcg_gq's are guaranteed to have access to parent */ + struct blkcg_gq *parent; + + /* reference count */ + struct percpu_ref refcnt; + + /* is this blkg online? protected by both blkcg and q locks */ + bool online; + + struct blkg_iostat_set __percpu *iostat_cpu; + struct blkg_iostat_set iostat; + + struct blkg_policy_data *pd[BLKCG_MAX_POLS]; + + spinlock_t async_bio_lock; + struct bio_list async_bios; + union { + struct work_struct async_bio_work; + struct work_struct free_work; + }; + + atomic_t use_delay; + atomic64_t delay_nsec; + atomic64_t delay_start; + u64 last_delay; + int last_use; + + struct rcu_head rcu_head; +}; + +struct blkcg { + struct cgroup_subsys_state css; + spinlock_t lock; + refcount_t online_pin; + + struct radix_tree_root blkg_tree; + struct blkcg_gq __rcu *blkg_hint; + struct hlist_head blkg_list; + + struct blkcg_policy_data *cpd[BLKCG_MAX_POLS]; + + struct list_head all_blkcgs_node; +#ifdef CONFIG_BLK_CGROUP_FC_APPID + char fc_app_id[FC_APPID_LEN]; +#endif +#ifdef CONFIG_CGROUP_WRITEBACK + struct list_head cgwb_list; +#endif +}; + +static inline struct blkcg *css_to_blkcg(struct cgroup_subsys_state *css) +{ + return css ? container_of(css, struct blkcg, css) : NULL; +} + /* * A blkcg_gq (blkg) is association between a block cgroup (blkcg) and a * request_queue (q). This is used by blkcg policies which need to track @@ -63,7 +151,7 @@ typedef void (blkcg_pol_online_pd_fn)(struct blkg_policy_data *pd); typedef void (blkcg_pol_offline_pd_fn)(struct blkg_policy_data *pd); typedef void (blkcg_pol_free_pd_fn)(struct blkg_policy_data *pd); typedef void (blkcg_pol_reset_pd_stats_fn)(struct blkg_policy_data *pd); -typedef bool (blkcg_pol_stat_pd_fn)(struct blkg_policy_data *pd, +typedef void (blkcg_pol_stat_pd_fn)(struct blkg_policy_data *pd, struct seq_file *s); struct blkcg_policy { @@ -123,52 +211,14 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol, void blkg_conf_finish(struct blkg_conf_ctx *ctx); /** - * blkcg_css - find the current css - * - * Find the css associated with either the kthread or the current task. - * This may return a dying css, so it is up to the caller to use tryget logic - * to confirm it is alive and well. - */ -static inline struct cgroup_subsys_state *blkcg_css(void) -{ - struct cgroup_subsys_state *css; - - css = kthread_blkcg(); - if (css) - return css; - return task_css(current, io_cgrp_id); -} - -/** - * __bio_blkcg - internal, inconsistent version to get blkcg - * - * DO NOT USE. - * This function is inconsistent and consequently is dangerous to use. The - * first part of the function returns a blkcg where a reference is owned by the - * bio. This means it does not need to be rcu protected as it cannot go away - * with the bio owning a reference to it. However, the latter potentially gets - * it from task_css(). This can race against task migration and the cgroup - * dying. It is also semantically different as it must be called rcu protected - * and is susceptible to failure when trying to get a reference to it. - * Therefore, it is not ok to assume that *_get() will always succeed on the - * blkcg returned here. - */ -static inline struct blkcg *__bio_blkcg(struct bio *bio) -{ - if (bio && bio->bi_blkg) - return bio->bi_blkg->blkcg; - return css_to_blkcg(blkcg_css()); -} - -/** * bio_issue_as_root_blkg - see if this bio needs to be issued as root blkg * @return: true if this bio needs to be submitted with the root blkg context. * * In order to avoid priority inversions we sometimes need to issue a bio as if * it were attached to the root blkg, and then backcharge to the actual owning - * blkg. The idea is we do bio_blkcg() to look up the actual context for the - * bio and attach the appropriate blkg to the bio. Then we call this helper and - * if it is true run with the root blkg for that queue and then do any + * blkg. The idea is we do bio_blkcg_css() to look up the actual context for + * the bio and attach the appropriate blkg to the bio. Then we call this helper + * and if it is true run with the root blkg for that queue and then do any * backcharging to the originating cgroup once the io is complete. */ static inline bool bio_issue_as_root_blkg(struct bio *bio) @@ -457,7 +507,8 @@ struct blkcg_policy_data { struct blkcg_policy { }; -#ifdef CONFIG_BLOCK +struct blkcg { +}; static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, void *key) { return NULL; } static inline struct blkcg_gq *blk_queue_root_blkg(struct request_queue *q) @@ -471,8 +522,6 @@ static inline int blkcg_activate_policy(struct request_queue *q, static inline void blkcg_deactivate_policy(struct request_queue *q, const struct blkcg_policy *pol) { } -static inline struct blkcg *__bio_blkcg(struct bio *bio) { return NULL; } - static inline struct blkg_policy_data *blkg_to_pd(struct blkcg_gq *blkg, struct blkcg_policy *pol) { return NULL; } static inline struct blkcg_gq *pd_to_blkg(struct blkg_policy_data *pd) { return NULL; } @@ -488,7 +537,6 @@ static inline bool blk_cgroup_mergeable(struct request *rq, struct bio *bio) { r #define blk_queue_for_each_rl(rl, q) \ for ((rl) = &(q)->root_rl; (rl); (rl) = NULL) -#endif /* CONFIG_BLOCK */ #endif /* CONFIG_BLK_CGROUP */ #endif /* _BLK_CGROUP_PRIVATE_H */ diff --git a/block/blk-core.c b/block/blk-core.c index 937bb6b86331..80fa73c419a9 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -50,7 +50,6 @@ #include "blk-pm.h" #include "blk-cgroup.h" #include "blk-throttle.h" -#include "blk-rq-qos.h" struct dentry *blk_debugfs_root; @@ -315,9 +314,6 @@ void blk_cleanup_queue(struct request_queue *q) */ blk_freeze_queue(q); - /* cleanup rq qos structures for queue without disk */ - rq_qos_exit(q); - blk_queue_flag_set(QUEUE_FLAG_DEAD, q); blk_sync_queue(q); @@ -592,10 +588,9 @@ static inline int bio_check_eod(struct bio *bio) (nr_sectors > maxsector || bio->bi_iter.bi_sector > maxsector - nr_sectors)) { pr_info_ratelimited("%s: attempt to access beyond end of device\n" - "%pg: rw=%d, want=%llu, limit=%llu\n", - current->comm, - bio->bi_bdev, bio->bi_opf, - bio_end_sector(bio), maxsector); + "%pg: rw=%d, sector=%llu, nr_sectors = %u limit=%llu\n", + current->comm, bio->bi_bdev, bio->bi_opf, + bio->bi_iter.bi_sector, nr_sectors, maxsector); return -EIO; } return 0; @@ -820,11 +815,11 @@ void submit_bio_noacct(struct bio *bio) switch (bio_op(bio)) { case REQ_OP_DISCARD: - if (!blk_queue_discard(q)) + if (!bdev_max_discard_sectors(bdev)) goto not_supported; break; case REQ_OP_SECURE_ERASE: - if (!blk_queue_secure_erase(q)) + if (!bdev_max_secure_erase_sectors(bdev)) goto not_supported; break; case REQ_OP_ZONE_APPEND: @@ -893,19 +888,11 @@ void submit_bio(struct bio *bio) if (blkcg_punt_bio_submit(bio)) return; - /* - * If it's a regular read/write or a barrier with data attached, - * go through the normal accounting stuff before submission. - */ - if (bio_has_data(bio)) { - unsigned int count = bio_sectors(bio); - - if (op_is_write(bio_op(bio))) { - count_vm_events(PGPGOUT, count); - } else { - task_io_account_read(bio->bi_iter.bi_size); - count_vm_events(PGPGIN, count); - } + if (bio_op(bio) == REQ_OP_READ) { + task_io_account_read(bio->bi_iter.bi_size); + count_vm_events(PGPGIN, bio_sectors(bio)); + } else if (bio_op(bio) == REQ_OP_WRITE) { + count_vm_events(PGPGOUT, bio_sectors(bio)); } /* @@ -1022,21 +1009,22 @@ again: } } -static unsigned long __part_start_io_acct(struct block_device *part, - unsigned int sectors, unsigned int op, - unsigned long start_time) +unsigned long bdev_start_io_acct(struct block_device *bdev, + unsigned int sectors, unsigned int op, + unsigned long start_time) { const int sgrp = op_stat_group(op); part_stat_lock(); - update_io_ticks(part, start_time, false); - part_stat_inc(part, ios[sgrp]); - part_stat_add(part, sectors[sgrp], sectors); - part_stat_local_inc(part, in_flight[op_is_write(op)]); + update_io_ticks(bdev, start_time, false); + part_stat_inc(bdev, ios[sgrp]); + part_stat_add(bdev, sectors[sgrp], sectors); + part_stat_local_inc(bdev, in_flight[op_is_write(op)]); part_stat_unlock(); return start_time; } +EXPORT_SYMBOL(bdev_start_io_acct); /** * bio_start_io_acct_time - start I/O accounting for bio based drivers @@ -1045,8 +1033,8 @@ static unsigned long __part_start_io_acct(struct block_device *part, */ void bio_start_io_acct_time(struct bio *bio, unsigned long start_time) { - __part_start_io_acct(bio->bi_bdev, bio_sectors(bio), - bio_op(bio), start_time); + bdev_start_io_acct(bio->bi_bdev, bio_sectors(bio), + bio_op(bio), start_time); } EXPORT_SYMBOL_GPL(bio_start_io_acct_time); @@ -1058,46 +1046,33 @@ EXPORT_SYMBOL_GPL(bio_start_io_acct_time); */ unsigned long bio_start_io_acct(struct bio *bio) { - return __part_start_io_acct(bio->bi_bdev, bio_sectors(bio), - bio_op(bio), jiffies); + return bdev_start_io_acct(bio->bi_bdev, bio_sectors(bio), + bio_op(bio), jiffies); } EXPORT_SYMBOL_GPL(bio_start_io_acct); -unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors, - unsigned int op) -{ - return __part_start_io_acct(disk->part0, sectors, op, jiffies); -} -EXPORT_SYMBOL(disk_start_io_acct); - -static void __part_end_io_acct(struct block_device *part, unsigned int op, - unsigned long start_time) +void bdev_end_io_acct(struct block_device *bdev, unsigned int op, + unsigned long start_time) { const int sgrp = op_stat_group(op); unsigned long now = READ_ONCE(jiffies); unsigned long duration = now - start_time; part_stat_lock(); - update_io_ticks(part, now, true); - part_stat_add(part, nsecs[sgrp], jiffies_to_nsecs(duration)); - part_stat_local_dec(part, in_flight[op_is_write(op)]); + update_io_ticks(bdev, now, true); + part_stat_add(bdev, nsecs[sgrp], jiffies_to_nsecs(duration)); + part_stat_local_dec(bdev, in_flight[op_is_write(op)]); part_stat_unlock(); } +EXPORT_SYMBOL(bdev_end_io_acct); void bio_end_io_acct_remapped(struct bio *bio, unsigned long start_time, - struct block_device *orig_bdev) + struct block_device *orig_bdev) { - __part_end_io_acct(orig_bdev, bio_op(bio), start_time); + bdev_end_io_acct(orig_bdev, bio_op(bio), start_time); } EXPORT_SYMBOL_GPL(bio_end_io_acct_remapped); -void disk_end_io_acct(struct gendisk *disk, unsigned int op, - unsigned long start_time) -{ - __part_end_io_acct(disk->part0, op, start_time); -} -EXPORT_SYMBOL(disk_end_io_acct); - /** * blk_lld_busy - Check if underlying low-level drivers of a device are busy * @q : the queue of the device being checked diff --git a/block/blk-crypto-fallback.c b/block/blk-crypto-fallback.c index 7c854584b52b..621abd1b0e4d 100644 --- a/block/blk-crypto-fallback.c +++ b/block/blk-crypto-fallback.c @@ -152,23 +152,25 @@ static void blk_crypto_fallback_encrypt_endio(struct bio *enc_bio) src_bio->bi_status = enc_bio->bi_status; - bio_put(enc_bio); + bio_uninit(enc_bio); + kfree(enc_bio); bio_endio(src_bio); } static struct bio *blk_crypto_fallback_clone_bio(struct bio *bio_src) { + unsigned int nr_segs = bio_segments(bio_src); struct bvec_iter iter; struct bio_vec bv; struct bio *bio; - bio = bio_kmalloc(GFP_NOIO, bio_segments(bio_src)); + bio = bio_kmalloc(nr_segs, GFP_NOIO); if (!bio) return NULL; - bio->bi_bdev = bio_src->bi_bdev; + bio_init(bio, bio_src->bi_bdev, bio->bi_inline_vecs, nr_segs, + bio_src->bi_opf); if (bio_flagged(bio_src, BIO_REMAPPED)) bio_set_flag(bio, BIO_REMAPPED); - bio->bi_opf = bio_src->bi_opf; bio->bi_ioprio = bio_src->bi_ioprio; bio->bi_iter.bi_sector = bio_src->bi_iter.bi_sector; bio->bi_iter.bi_size = bio_src->bi_iter.bi_size; @@ -177,7 +179,6 @@ static struct bio *blk_crypto_fallback_clone_bio(struct bio *bio_src) bio->bi_io_vec[bio->bi_vcnt++] = bv; bio_clone_blkg_association(bio, bio_src); - blkcg_bio_issue_init(bio); return bio; } @@ -363,8 +364,8 @@ out_release_keyslot: blk_crypto_put_keyslot(slot); out_put_enc_bio: if (enc_bio) - bio_put(enc_bio); - + bio_uninit(enc_bio); + kfree(enc_bio); return ret; } diff --git a/block/blk-iocost.c b/block/blk-iocost.c index 70a0a3d680a3..33a11ba971ea 100644 --- a/block/blk-iocost.c +++ b/block/blk-iocost.c @@ -533,8 +533,7 @@ struct ioc_gq { /* statistics */ struct iocg_pcpu_stat __percpu *pcpu_stat; - struct iocg_stat local_stat; - struct iocg_stat desc_stat; + struct iocg_stat stat; struct iocg_stat last_stat; u64 last_stat_abs_vusage; u64 usage_delta_us; @@ -1371,7 +1370,7 @@ static bool iocg_kick_delay(struct ioc_gq *iocg, struct ioc_now *now) return true; } else { if (iocg->indelay_since) { - iocg->local_stat.indelay_us += now->now - iocg->indelay_since; + iocg->stat.indelay_us += now->now - iocg->indelay_since; iocg->indelay_since = 0; } iocg->delay = 0; @@ -1419,7 +1418,7 @@ static void iocg_pay_debt(struct ioc_gq *iocg, u64 abs_vpay, /* if debt is paid in full, restore inuse */ if (!iocg->abs_vdebt) { - iocg->local_stat.indebt_us += now->now - iocg->indebt_since; + iocg->stat.indebt_us += now->now - iocg->indebt_since; iocg->indebt_since = 0; propagate_weights(iocg, iocg->active, iocg->last_inuse, @@ -1513,7 +1512,7 @@ static void iocg_kick_waitq(struct ioc_gq *iocg, bool pay_debt, if (!waitqueue_active(&iocg->waitq)) { if (iocg->wait_since) { - iocg->local_stat.wait_us += now->now - iocg->wait_since; + iocg->stat.wait_us += now->now - iocg->wait_since; iocg->wait_since = 0; } return; @@ -1641,11 +1640,30 @@ static void iocg_build_inner_walk(struct ioc_gq *iocg, } } +/* propagate the deltas to the parent */ +static void iocg_flush_stat_upward(struct ioc_gq *iocg) +{ + if (iocg->level > 0) { + struct iocg_stat *parent_stat = + &iocg->ancestors[iocg->level - 1]->stat; + + parent_stat->usage_us += + iocg->stat.usage_us - iocg->last_stat.usage_us; + parent_stat->wait_us += + iocg->stat.wait_us - iocg->last_stat.wait_us; + parent_stat->indebt_us += + iocg->stat.indebt_us - iocg->last_stat.indebt_us; + parent_stat->indelay_us += + iocg->stat.indelay_us - iocg->last_stat.indelay_us; + } + + iocg->last_stat = iocg->stat; +} + /* collect per-cpu counters and propagate the deltas to the parent */ -static void iocg_flush_stat_one(struct ioc_gq *iocg, struct ioc_now *now) +static void iocg_flush_stat_leaf(struct ioc_gq *iocg, struct ioc_now *now) { struct ioc *ioc = iocg->ioc; - struct iocg_stat new_stat; u64 abs_vusage = 0; u64 vusage_delta; int cpu; @@ -1661,34 +1679,9 @@ static void iocg_flush_stat_one(struct ioc_gq *iocg, struct ioc_now *now) iocg->last_stat_abs_vusage = abs_vusage; iocg->usage_delta_us = div64_u64(vusage_delta, ioc->vtime_base_rate); - iocg->local_stat.usage_us += iocg->usage_delta_us; - - /* propagate upwards */ - new_stat.usage_us = - iocg->local_stat.usage_us + iocg->desc_stat.usage_us; - new_stat.wait_us = - iocg->local_stat.wait_us + iocg->desc_stat.wait_us; - new_stat.indebt_us = - iocg->local_stat.indebt_us + iocg->desc_stat.indebt_us; - new_stat.indelay_us = - iocg->local_stat.indelay_us + iocg->desc_stat.indelay_us; - - /* propagate the deltas to the parent */ - if (iocg->level > 0) { - struct iocg_stat *parent_stat = - &iocg->ancestors[iocg->level - 1]->desc_stat; + iocg->stat.usage_us += iocg->usage_delta_us; - parent_stat->usage_us += - new_stat.usage_us - iocg->last_stat.usage_us; - parent_stat->wait_us += - new_stat.wait_us - iocg->last_stat.wait_us; - parent_stat->indebt_us += - new_stat.indebt_us - iocg->last_stat.indebt_us; - parent_stat->indelay_us += - new_stat.indelay_us - iocg->last_stat.indelay_us; - } - - iocg->last_stat = new_stat; + iocg_flush_stat_upward(iocg); } /* get stat counters ready for reading on all active iocgs */ @@ -1699,13 +1692,13 @@ static void iocg_flush_stat(struct list_head *target_iocgs, struct ioc_now *now) /* flush leaves and build inner node walk list */ list_for_each_entry(iocg, target_iocgs, active_list) { - iocg_flush_stat_one(iocg, now); + iocg_flush_stat_leaf(iocg, now); iocg_build_inner_walk(iocg, &inner_walk); } /* keep flushing upwards by walking the inner list backwards */ list_for_each_entry_safe_reverse(iocg, tiocg, &inner_walk, walk_list) { - iocg_flush_stat_one(iocg, now); + iocg_flush_stat_upward(iocg); list_del_init(&iocg->walk_list); } } @@ -2152,16 +2145,16 @@ static int ioc_check_iocgs(struct ioc *ioc, struct ioc_now *now) /* flush wait and indebt stat deltas */ if (iocg->wait_since) { - iocg->local_stat.wait_us += now->now - iocg->wait_since; + iocg->stat.wait_us += now->now - iocg->wait_since; iocg->wait_since = now->now; } if (iocg->indebt_since) { - iocg->local_stat.indebt_us += + iocg->stat.indebt_us += now->now - iocg->indebt_since; iocg->indebt_since = now->now; } if (iocg->indelay_since) { - iocg->local_stat.indelay_us += + iocg->stat.indelay_us += now->now - iocg->indelay_since; iocg->indelay_since = now->now; } @@ -2322,7 +2315,17 @@ static void ioc_timer_fn(struct timer_list *timer) iocg->hweight_donating = hwa; iocg->hweight_after_donation = new_hwi; list_add(&iocg->surplus_list, &surpluses); - } else { + } else if (!iocg->abs_vdebt) { + /* + * @iocg doesn't have enough to donate. Reset + * its inuse to active. + * + * Don't reset debtors as their inuse's are + * owned by debt handling. This shouldn't affect + * donation calculuation in any meaningful way + * as @iocg doesn't have a meaningful amount of + * share anyway. + */ TRACE_IOCG_PATH(inuse_shortage, iocg, &now, iocg->inuse, iocg->active, iocg->hweight_inuse, new_hwi); @@ -2995,13 +2998,13 @@ static void ioc_pd_free(struct blkg_policy_data *pd) kfree(iocg); } -static bool ioc_pd_stat(struct blkg_policy_data *pd, struct seq_file *s) +static void ioc_pd_stat(struct blkg_policy_data *pd, struct seq_file *s) { struct ioc_gq *iocg = pd_to_iocg(pd); struct ioc *ioc = iocg->ioc; if (!ioc->enabled) - return false; + return; if (iocg->level == 0) { unsigned vp10k = DIV64_U64_ROUND_CLOSEST( @@ -3017,7 +3020,6 @@ static bool ioc_pd_stat(struct blkg_policy_data *pd, struct seq_file *s) iocg->last_stat.wait_us, iocg->last_stat.indebt_us, iocg->last_stat.indelay_us); - return true; } static u64 ioc_weight_prfill(struct seq_file *sf, struct blkg_policy_data *pd, diff --git a/block/blk-iolatency.c b/block/blk-iolatency.c index 2f33932e72e3..5b676c7cf2b6 100644 --- a/block/blk-iolatency.c +++ b/block/blk-iolatency.c @@ -891,7 +891,7 @@ static int iolatency_print_limit(struct seq_file *sf, void *v) return 0; } -static bool iolatency_ssd_stat(struct iolatency_grp *iolat, struct seq_file *s) +static void iolatency_ssd_stat(struct iolatency_grp *iolat, struct seq_file *s) { struct latency_stat stat; int cpu; @@ -914,17 +914,16 @@ static bool iolatency_ssd_stat(struct iolatency_grp *iolat, struct seq_file *s) (unsigned long long)stat.ps.missed, (unsigned long long)stat.ps.total, iolat->rq_depth.max_depth); - return true; } -static bool iolatency_pd_stat(struct blkg_policy_data *pd, struct seq_file *s) +static void iolatency_pd_stat(struct blkg_policy_data *pd, struct seq_file *s) { struct iolatency_grp *iolat = pd_to_lat(pd); unsigned long long avg_lat; unsigned long long cur_win; if (!blkcg_debug_stats) - return false; + return; if (iolat->ssd) return iolatency_ssd_stat(iolat, s); @@ -937,7 +936,6 @@ static bool iolatency_pd_stat(struct blkg_policy_data *pd, struct seq_file *s) else seq_printf(s, " depth=%u avg_lat=%llu win=%llu", iolat->rq_depth.max_depth, avg_lat, cur_win); - return true; } static struct blkg_policy_data *iolatency_pd_alloc(gfp_t gfp, diff --git a/block/blk-lib.c b/block/blk-lib.c index 237d60d8b585..09b7e1200c0f 100644 --- a/block/blk-lib.c +++ b/block/blk-lib.c @@ -10,30 +10,44 @@ #include "blk.h" +static sector_t bio_discard_limit(struct block_device *bdev, sector_t sector) +{ + unsigned int discard_granularity = bdev_discard_granularity(bdev); + sector_t granularity_aligned_sector; + + if (bdev_is_partition(bdev)) + sector += bdev->bd_start_sect; + + granularity_aligned_sector = + round_up(sector, discard_granularity >> SECTOR_SHIFT); + + /* + * Make sure subsequent bios start aligned to the discard granularity if + * it needs to be split. + */ + if (granularity_aligned_sector != sector) + return granularity_aligned_sector - sector; + + /* + * Align the bio size to the discard granularity to make splitting the bio + * at discard granularity boundaries easier in the driver if needed. + */ + return round_down(UINT_MAX, discard_granularity) >> SECTOR_SHIFT; +} + int __blkdev_issue_discard(struct block_device *bdev, sector_t sector, - sector_t nr_sects, gfp_t gfp_mask, int flags, - struct bio **biop) + sector_t nr_sects, gfp_t gfp_mask, struct bio **biop) { - struct request_queue *q = bdev_get_queue(bdev); struct bio *bio = *biop; - unsigned int op; - sector_t bs_mask, part_offset = 0; + sector_t bs_mask; if (bdev_read_only(bdev)) return -EPERM; - - if (flags & BLKDEV_DISCARD_SECURE) { - if (!blk_queue_secure_erase(q)) - return -EOPNOTSUPP; - op = REQ_OP_SECURE_ERASE; - } else { - if (!blk_queue_discard(q)) - return -EOPNOTSUPP; - op = REQ_OP_DISCARD; - } + if (!bdev_max_discard_sectors(bdev)) + return -EOPNOTSUPP; /* In case the discard granularity isn't set by buggy device driver */ - if (WARN_ON_ONCE(!q->limits.discard_granularity)) { + if (WARN_ON_ONCE(!bdev_discard_granularity(bdev))) { char dev_name[BDEVNAME_SIZE]; bdevname(bdev, dev_name); @@ -48,38 +62,11 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector, if (!nr_sects) return -EINVAL; - /* In case the discard request is in a partition */ - if (bdev_is_partition(bdev)) - part_offset = bdev->bd_start_sect; - while (nr_sects) { - sector_t granularity_aligned_lba, req_sects; - sector_t sector_mapped = sector + part_offset; - - granularity_aligned_lba = round_up(sector_mapped, - q->limits.discard_granularity >> SECTOR_SHIFT); - - /* - * Check whether the discard bio starts at a discard_granularity - * aligned LBA, - * - If no: set (granularity_aligned_lba - sector_mapped) to - * bi_size of the first split bio, then the second bio will - * start at a discard_granularity aligned LBA on the device. - * - If yes: use bio_aligned_discard_max_sectors() as the max - * possible bi_size of the first split bio. Then when this bio - * is split in device drive, the split ones are very probably - * to be aligned to discard_granularity of the device's queue. - */ - if (granularity_aligned_lba == sector_mapped) - req_sects = min_t(sector_t, nr_sects, - bio_aligned_discard_max_sectors(q)); - else - req_sects = min_t(sector_t, nr_sects, - granularity_aligned_lba - sector_mapped); - - WARN_ON_ONCE((req_sects << 9) > UINT_MAX); + sector_t req_sects = + min(nr_sects, bio_discard_limit(bdev, sector)); - bio = blk_next_bio(bio, bdev, 0, op, gfp_mask); + bio = blk_next_bio(bio, bdev, 0, REQ_OP_DISCARD, gfp_mask); bio->bi_iter.bi_sector = sector; bio->bi_iter.bi_size = req_sects << 9; sector += req_sects; @@ -105,21 +92,19 @@ EXPORT_SYMBOL(__blkdev_issue_discard); * @sector: start sector * @nr_sects: number of sectors to discard * @gfp_mask: memory allocation flags (for bio_alloc) - * @flags: BLKDEV_DISCARD_* flags to control behaviour * * Description: * Issue a discard request for the sectors in question. */ int blkdev_issue_discard(struct block_device *bdev, sector_t sector, - sector_t nr_sects, gfp_t gfp_mask, unsigned long flags) + sector_t nr_sects, gfp_t gfp_mask) { struct bio *bio = NULL; struct blk_plug plug; int ret; blk_start_plug(&plug); - ret = __blkdev_issue_discard(bdev, sector, nr_sects, gfp_mask, flags, - &bio); + ret = __blkdev_issue_discard(bdev, sector, nr_sects, gfp_mask, &bio); if (!ret && bio) { ret = submit_bio_wait(bio); if (ret == -EOPNOTSUPP) @@ -316,3 +301,42 @@ retry: return ret; } EXPORT_SYMBOL(blkdev_issue_zeroout); + +int blkdev_issue_secure_erase(struct block_device *bdev, sector_t sector, + sector_t nr_sects, gfp_t gfp) +{ + sector_t bs_mask = (bdev_logical_block_size(bdev) >> 9) - 1; + unsigned int max_sectors = bdev_max_secure_erase_sectors(bdev); + struct bio *bio = NULL; + struct blk_plug plug; + int ret = 0; + + if (max_sectors == 0) + return -EOPNOTSUPP; + if ((sector | nr_sects) & bs_mask) + return -EINVAL; + if (bdev_read_only(bdev)) + return -EPERM; + + blk_start_plug(&plug); + for (;;) { + unsigned int len = min_t(sector_t, nr_sects, max_sectors); + + bio = blk_next_bio(bio, bdev, 0, REQ_OP_SECURE_ERASE, gfp); + bio->bi_iter.bi_sector = sector; + bio->bi_iter.bi_size = len; + + sector += len << SECTOR_SHIFT; + nr_sects -= len << SECTOR_SHIFT; + if (!nr_sects) { + ret = submit_bio_wait(bio); + bio_put(bio); + break; + } + cond_resched(); + } + blk_finish_plug(&plug); + + return ret; +} +EXPORT_SYMBOL(blkdev_issue_secure_erase); diff --git a/block/blk-map.c b/block/blk-map.c index c7f71d83eff1..df8b066cd548 100644 --- a/block/blk-map.c +++ b/block/blk-map.c @@ -152,10 +152,10 @@ static int bio_copy_user_iov(struct request *rq, struct rq_map_data *map_data, nr_pages = bio_max_segs(DIV_ROUND_UP(offset + len, PAGE_SIZE)); ret = -ENOMEM; - bio = bio_kmalloc(gfp_mask, nr_pages); + bio = bio_kmalloc(nr_pages, gfp_mask); if (!bio) goto out_bmd; - bio->bi_opf |= req_op(rq); + bio_init(bio, NULL, bio->bi_inline_vecs, nr_pages, req_op(rq)); if (map_data) { nr_pages = 1 << map_data->page_order; @@ -224,7 +224,8 @@ static int bio_copy_user_iov(struct request *rq, struct rq_map_data *map_data, cleanup: if (!map_data) bio_free_pages(bio); - bio_put(bio); + bio_uninit(bio); + kfree(bio); out_bmd: kfree(bmd); return ret; @@ -234,6 +235,7 @@ static int bio_map_user_iov(struct request *rq, struct iov_iter *iter, gfp_t gfp_mask) { unsigned int max_sectors = queue_max_hw_sectors(rq->q); + unsigned int nr_vecs = iov_iter_npages(iter, BIO_MAX_VECS); struct bio *bio; int ret; int j; @@ -241,10 +243,10 @@ static int bio_map_user_iov(struct request *rq, struct iov_iter *iter, if (!iov_iter_count(iter)) return -EINVAL; - bio = bio_kmalloc(gfp_mask, iov_iter_npages(iter, BIO_MAX_VECS)); + bio = bio_kmalloc(nr_vecs, gfp_mask); if (!bio) return -ENOMEM; - bio->bi_opf |= req_op(rq); + bio_init(bio, NULL, bio->bi_inline_vecs, nr_vecs, req_op(rq)); while (iov_iter_count(iter)) { struct page **pages; @@ -260,10 +262,9 @@ static int bio_map_user_iov(struct request *rq, struct iov_iter *iter, npages = DIV_ROUND_UP(offs + bytes, PAGE_SIZE); - if (unlikely(offs & queue_dma_alignment(rq->q))) { - ret = -EINVAL; + if (unlikely(offs & queue_dma_alignment(rq->q))) j = 0; - } else { + else { for (j = 0; j < npages; j++) { struct page *page = pages[j]; unsigned int n = PAGE_SIZE - offs; @@ -303,7 +304,8 @@ static int bio_map_user_iov(struct request *rq, struct iov_iter *iter, out_unmap: bio_release_pages(bio, false); - bio_put(bio); + bio_uninit(bio); + kfree(bio); return ret; } @@ -323,7 +325,8 @@ static void bio_invalidate_vmalloc_pages(struct bio *bio) static void bio_map_kern_endio(struct bio *bio) { bio_invalidate_vmalloc_pages(bio); - bio_put(bio); + bio_uninit(bio); + kfree(bio); } /** @@ -348,9 +351,10 @@ static struct bio *bio_map_kern(struct request_queue *q, void *data, int offset, i; struct bio *bio; - bio = bio_kmalloc(gfp_mask, nr_pages); + bio = bio_kmalloc(nr_pages, gfp_mask); if (!bio) return ERR_PTR(-ENOMEM); + bio_init(bio, NULL, bio->bi_inline_vecs, nr_pages, 0); if (is_vmalloc) { flush_kernel_vmap_range(data, len); @@ -374,7 +378,8 @@ static struct bio *bio_map_kern(struct request_queue *q, void *data, if (bio_add_pc_page(q, bio, page, bytes, offset) < bytes) { /* we don't support partial mappings */ - bio_put(bio); + bio_uninit(bio); + kfree(bio); return ERR_PTR(-EINVAL); } @@ -390,7 +395,8 @@ static struct bio *bio_map_kern(struct request_queue *q, void *data, static void bio_copy_kern_endio(struct bio *bio) { bio_free_pages(bio); - bio_put(bio); + bio_uninit(bio); + kfree(bio); } static void bio_copy_kern_endio_read(struct bio *bio) @@ -435,9 +441,10 @@ static struct bio *bio_copy_kern(struct request_queue *q, void *data, return ERR_PTR(-EINVAL); nr_pages = end - start; - bio = bio_kmalloc(gfp_mask, nr_pages); + bio = bio_kmalloc(nr_pages, gfp_mask); if (!bio) return ERR_PTR(-ENOMEM); + bio_init(bio, NULL, bio->bi_inline_vecs, nr_pages, 0); while (len) { struct page *page; @@ -471,7 +478,8 @@ static struct bio *bio_copy_kern(struct request_queue *q, void *data, cleanup: bio_free_pages(bio); - bio_put(bio); + bio_uninit(bio); + kfree(bio); return ERR_PTR(-ENOMEM); } @@ -602,7 +610,8 @@ int blk_rq_unmap_user(struct bio *bio) next_bio = bio; bio = bio->bi_next; - bio_put(next_bio); + bio_uninit(next_bio); + kfree(next_bio); } return ret; @@ -648,8 +657,10 @@ int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf, bio->bi_opf |= req_op(rq); ret = blk_rq_append_bio(rq, bio); - if (unlikely(ret)) - bio_put(bio); + if (unlikely(ret)) { + bio_uninit(bio); + kfree(bio); + } return ret; } EXPORT_SYMBOL(blk_rq_map_kern); diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index aa0349e9f083..7e4136a60e1c 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -113,10 +113,8 @@ static const char *const blk_queue_flag_name[] = { QUEUE_FLAG_NAME(FAIL_IO), QUEUE_FLAG_NAME(NONROT), QUEUE_FLAG_NAME(IO_STAT), - QUEUE_FLAG_NAME(DISCARD), QUEUE_FLAG_NAME(NOXMERGES), QUEUE_FLAG_NAME(ADD_RANDOM), - QUEUE_FLAG_NAME(SECERASE), QUEUE_FLAG_NAME(SAME_FORCE), QUEUE_FLAG_NAME(DEAD), QUEUE_FLAG_NAME(INIT_DONE), diff --git a/block/blk-mq.c b/block/blk-mq.c index ed3ed86f7dd2..ae116b755648 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -794,7 +794,8 @@ bool blk_update_request(struct request *req, blk_status_t error, #endif if (unlikely(error && !blk_rq_is_passthrough(req) && - !(req->rq_flags & RQF_QUIET))) { + !(req->rq_flags & RQF_QUIET)) && + !test_bit(GD_DEAD, &req->q->disk->state)) { blk_print_req_error(req, error); trace_block_rq_error(req, error, nr_bytes); } @@ -1082,7 +1083,7 @@ bool blk_mq_complete_request_remote(struct request *rq) WRITE_ONCE(rq->state, MQ_RQ_COMPLETE); /* - * For a polled request, always complete locallly, it's pointless + * For a polled request, always complete locally, it's pointless * to redirect the completion. */ if (rq->cmd_flags & REQ_POLLED) @@ -1130,14 +1131,7 @@ void blk_mq_start_request(struct request *rq) trace_block_rq_issue(rq); if (test_bit(QUEUE_FLAG_STATS, &q->queue_flags)) { - u64 start_time; -#ifdef CONFIG_BLK_CGROUP - if (rq->bio) - start_time = bio_issue_time(&rq->bio->bi_issue); - else -#endif - start_time = ktime_get_ns(); - rq->io_start_time_ns = start_time; + rq->io_start_time_ns = ktime_get_ns(); rq->stats_sectors = blk_rq_sectors(rq); rq->rq_flags |= RQF_STATS; rq_qos_issue(q, rq); @@ -1175,6 +1169,62 @@ static void blk_end_sync_rq(struct request *rq, blk_status_t error) complete(waiting); } +/* + * Allow 2x BLK_MAX_REQUEST_COUNT requests on plug queue for multiple + * queues. This is important for md arrays to benefit from merging + * requests. + */ +static inline unsigned short blk_plug_max_rq_count(struct blk_plug *plug) +{ + if (plug->multiple_queues) + return BLK_MAX_REQUEST_COUNT * 2; + return BLK_MAX_REQUEST_COUNT; +} + +static void blk_add_rq_to_plug(struct blk_plug *plug, struct request *rq) +{ + struct request *last = rq_list_peek(&plug->mq_list); + + if (!plug->rq_count) { + trace_block_plug(rq->q); + } else if (plug->rq_count >= blk_plug_max_rq_count(plug) || + (!blk_queue_nomerges(rq->q) && + blk_rq_bytes(last) >= BLK_PLUG_FLUSH_SIZE)) { + blk_mq_flush_plug_list(plug, false); + trace_block_plug(rq->q); + } + + if (!plug->multiple_queues && last && last->q != rq->q) + plug->multiple_queues = true; + if (!plug->has_elevator && (rq->rq_flags & RQF_ELV)) + plug->has_elevator = true; + rq->rq_next = NULL; + rq_list_add(&plug->mq_list, rq); + plug->rq_count++; +} + +static void __blk_execute_rq_nowait(struct request *rq, bool at_head, + rq_end_io_fn *done, bool use_plug) +{ + WARN_ON(irqs_disabled()); + WARN_ON(!blk_rq_is_passthrough(rq)); + + rq->end_io = done; + + blk_account_io_start(rq); + + if (use_plug && current->plug) { + blk_add_rq_to_plug(current->plug, rq); + return; + } + /* + * don't check dying flag for MQ because the request won't + * be reused after dying flag is set + */ + blk_mq_sched_insert_request(rq, at_head, true, false); +} + + /** * blk_execute_rq_nowait - insert a request to I/O scheduler for execution * @rq: request to insert @@ -1190,18 +1240,8 @@ static void blk_end_sync_rq(struct request *rq, blk_status_t error) */ void blk_execute_rq_nowait(struct request *rq, bool at_head, rq_end_io_fn *done) { - WARN_ON(irqs_disabled()); - WARN_ON(!blk_rq_is_passthrough(rq)); - - rq->end_io = done; + __blk_execute_rq_nowait(rq, at_head, done, true); - blk_account_io_start(rq); - - /* - * don't check dying flag for MQ because the request won't - * be reused after dying flag is set - */ - blk_mq_sched_insert_request(rq, at_head, true, false); } EXPORT_SYMBOL_GPL(blk_execute_rq_nowait); @@ -1239,8 +1279,13 @@ blk_status_t blk_execute_rq(struct request *rq, bool at_head) DECLARE_COMPLETION_ONSTACK(wait); unsigned long hang_check; + /* + * iopoll requires request to be submitted to driver, so can't + * use plug + */ rq->end_io_data = &wait; - blk_execute_rq_nowait(rq, at_head, blk_end_sync_rq); + __blk_execute_rq_nowait(rq, at_head, blk_end_sync_rq, + !blk_rq_is_poll(rq)); /* Prevent hang_check timer from firing at us during very long I/O */ hang_check = sysctl_hung_task_timeout_secs; @@ -2682,40 +2727,6 @@ void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx, hctx->queue->mq_ops->commit_rqs(hctx); } -/* - * Allow 2x BLK_MAX_REQUEST_COUNT requests on plug queue for multiple - * queues. This is important for md arrays to benefit from merging - * requests. - */ -static inline unsigned short blk_plug_max_rq_count(struct blk_plug *plug) -{ - if (plug->multiple_queues) - return BLK_MAX_REQUEST_COUNT * 2; - return BLK_MAX_REQUEST_COUNT; -} - -static void blk_add_rq_to_plug(struct blk_plug *plug, struct request *rq) -{ - struct request *last = rq_list_peek(&plug->mq_list); - - if (!plug->rq_count) { - trace_block_plug(rq->q); - } else if (plug->rq_count >= blk_plug_max_rq_count(plug) || - (!blk_queue_nomerges(rq->q) && - blk_rq_bytes(last) >= BLK_PLUG_FLUSH_SIZE)) { - blk_mq_flush_plug_list(plug, false); - trace_block_plug(rq->q); - } - - if (!plug->multiple_queues && last && last->q != rq->q) - plug->multiple_queues = true; - if (!plug->has_elevator && (rq->rq_flags & RQF_ELV)) - plug->has_elevator = true; - rq->rq_next = NULL; - rq_list_add(&plug->mq_list, rq); - plug->rq_count++; -} - static bool blk_mq_attempt_bio_merge(struct request_queue *q, struct bio *bio, unsigned int nr_segs) { diff --git a/block/blk-settings.c b/block/blk-settings.c index b83df3d2eebc..6ccceb421ed2 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -46,6 +46,7 @@ void blk_set_default_limits(struct queue_limits *lim) lim->max_zone_append_sectors = 0; lim->max_discard_sectors = 0; lim->max_hw_discard_sectors = 0; + lim->max_secure_erase_sectors = 0; lim->discard_granularity = 0; lim->discard_alignment = 0; lim->discard_misaligned = 0; @@ -177,6 +178,18 @@ void blk_queue_max_discard_sectors(struct request_queue *q, EXPORT_SYMBOL(blk_queue_max_discard_sectors); /** + * blk_queue_max_secure_erase_sectors - set max sectors for a secure erase + * @q: the request queue for the device + * @max_sectors: maximum number of sectors to secure_erase + **/ +void blk_queue_max_secure_erase_sectors(struct request_queue *q, + unsigned int max_sectors) +{ + q->limits.max_secure_erase_sectors = max_sectors; +} +EXPORT_SYMBOL(blk_queue_max_secure_erase_sectors); + +/** * blk_queue_max_write_zeroes_sectors - set max sectors for a single * write zeroes * @q: the request queue for the device @@ -468,6 +481,40 @@ void blk_queue_io_opt(struct request_queue *q, unsigned int opt) } EXPORT_SYMBOL(blk_queue_io_opt); +static int queue_limit_alignment_offset(struct queue_limits *lim, + sector_t sector) +{ + unsigned int granularity = max(lim->physical_block_size, lim->io_min); + unsigned int alignment = sector_div(sector, granularity >> SECTOR_SHIFT) + << SECTOR_SHIFT; + + return (granularity + lim->alignment_offset - alignment) % granularity; +} + +static unsigned int queue_limit_discard_alignment(struct queue_limits *lim, + sector_t sector) +{ + unsigned int alignment, granularity, offset; + + if (!lim->max_discard_sectors) + return 0; + + /* Why are these in bytes, not sectors? */ + alignment = lim->discard_alignment >> SECTOR_SHIFT; + granularity = lim->discard_granularity >> SECTOR_SHIFT; + if (!granularity) + return 0; + + /* Offset of the partition start in 'granularity' sectors */ + offset = sector_div(sector, granularity); + + /* And why do we do this modulus *again* in blkdev_issue_discard()? */ + offset = (granularity + alignment - offset) % granularity; + + /* Turn it back into bytes, gaah */ + return offset << SECTOR_SHIFT; +} + static unsigned int blk_round_down_sectors(unsigned int sectors, unsigned int lbs) { sectors = round_down(sectors, lbs >> SECTOR_SHIFT); @@ -627,7 +674,8 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, t->discard_alignment = lcm_not_zero(t->discard_alignment, alignment) % t->discard_granularity; } - + t->max_secure_erase_sectors = min_not_zero(t->max_secure_erase_sectors, + b->max_secure_erase_sectors); t->zone_write_granularity = max(t->zone_write_granularity, b->zone_write_granularity); t->zoned = max(t->zoned, b->zoned); @@ -901,3 +949,27 @@ void blk_queue_set_zoned(struct gendisk *disk, enum blk_zoned_model model) } } EXPORT_SYMBOL_GPL(blk_queue_set_zoned); + +int bdev_alignment_offset(struct block_device *bdev) +{ + struct request_queue *q = bdev_get_queue(bdev); + + if (q->limits.misaligned) + return -1; + if (bdev_is_partition(bdev)) + return queue_limit_alignment_offset(&q->limits, + bdev->bd_start_sect); + return q->limits.alignment_offset; +} +EXPORT_SYMBOL_GPL(bdev_alignment_offset); + +unsigned int bdev_discard_alignment(struct block_device *bdev) +{ + struct request_queue *q = bdev_get_queue(bdev); + + if (bdev_is_partition(bdev)) + return queue_limit_discard_alignment(&q->limits, + bdev->bd_start_sect); + return q->limits.discard_alignment; +} +EXPORT_SYMBOL_GPL(bdev_discard_alignment); diff --git a/block/blk-throttle.c b/block/blk-throttle.c index 469c483719be..139b2d7a99e2 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -227,7 +227,7 @@ static unsigned int tg_iops_limit(struct throtl_grp *tg, int rw) break; \ if ((__tg)) { \ blk_add_cgroup_trace_msg(__td->queue, \ - tg_to_blkg(__tg)->blkcg, "throtl " fmt, ##args);\ + &tg_to_blkg(__tg)->blkcg->css, "throtl " fmt, ##args);\ } else { \ blk_add_trace_msg(__td->queue, "throtl " fmt, ##args); \ } \ @@ -2189,13 +2189,14 @@ again: } out_unlock: - spin_unlock_irq(&q->queue_lock); bio_set_flag(bio, BIO_THROTTLED); #ifdef CONFIG_BLK_DEV_THROTTLING_LOW if (throttled || !td->track_bio_latency) bio->bi_issue.value |= BIO_ISSUE_THROTL_SKIP_LATENCY; #endif + spin_unlock_irq(&q->queue_lock); + rcu_read_unlock(); return throttled; } diff --git a/block/blk.h b/block/blk.h index 8ccbc6e07636..434017701403 100644 --- a/block/blk.h +++ b/block/blk.h @@ -347,20 +347,6 @@ static inline unsigned int bio_allowed_max_sectors(struct request_queue *q) } /* - * The max bio size which is aligned to q->limits.discard_granularity. This - * is a hint to split large discard bio in generic block layer, then if device - * driver needs to split the discard bio into smaller ones, their bi_size can - * be very probably and easily aligned to discard_granularity of the device's - * queue. - */ -static inline unsigned int bio_aligned_discard_max_sectors( - struct request_queue *q) -{ - return round_down(UINT_MAX, q->limits.discard_granularity) >> - SECTOR_SHIFT; -} - -/* * Internal io_context interface */ struct io_cq *ioc_find_get_icq(struct request_queue *q); @@ -450,13 +436,6 @@ extern struct device_attribute dev_attr_events; extern struct device_attribute dev_attr_events_async; extern struct device_attribute dev_attr_events_poll_msecs; -static inline void bio_clear_polled(struct bio *bio) -{ - /* can't support alloc cache if we turn off polling */ - bio_clear_flag(bio, BIO_PERCPU_CACHE); - bio->bi_opf &= ~REQ_POLLED; -} - long blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg); long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg); diff --git a/block/bounce.c b/block/bounce.c index 467be46d0e65..8f7b6fe3b4db 100644 --- a/block/bounce.c +++ b/block/bounce.c @@ -191,7 +191,6 @@ static struct bio *bounce_clone_bio(struct bio *bio_src) goto err_put; bio_clone_blkg_association(bio, bio_src); - blkcg_bio_issue_init(bio); return bio; diff --git a/block/fops.c b/block/fops.c index 9f2ecec406b0..d6b3276a6c68 100644 --- a/block/fops.c +++ b/block/fops.c @@ -44,14 +44,6 @@ static unsigned int dio_bio_write_op(struct kiocb *iocb) #define DIO_INLINE_BIO_VECS 4 -static void blkdev_bio_end_io_simple(struct bio *bio) -{ - struct task_struct *waiter = bio->bi_private; - - WRITE_ONCE(bio->bi_private, NULL); - blk_wake_io_task(waiter); -} - static ssize_t __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter, unsigned int nr_pages) { @@ -83,8 +75,6 @@ static ssize_t __blkdev_direct_IO_simple(struct kiocb *iocb, bio_init(&bio, bdev, vecs, nr_pages, dio_bio_write_op(iocb)); } bio.bi_iter.bi_sector = pos >> SECTOR_SHIFT; - bio.bi_private = current; - bio.bi_end_io = blkdev_bio_end_io_simple; bio.bi_ioprio = iocb->ki_ioprio; ret = bio_iov_iter_get_pages(&bio, iter); @@ -97,18 +87,8 @@ static ssize_t __blkdev_direct_IO_simple(struct kiocb *iocb, if (iocb->ki_flags & IOCB_NOWAIT) bio.bi_opf |= REQ_NOWAIT; - if (iocb->ki_flags & IOCB_HIPRI) - bio_set_polled(&bio, iocb); - submit_bio(&bio); - for (;;) { - set_current_state(TASK_UNINTERRUPTIBLE); - if (!READ_ONCE(bio.bi_private)) - break; - if (!(iocb->ki_flags & IOCB_HIPRI) || !bio_poll(&bio, NULL, 0)) - blk_io_schedule(); - } - __set_current_state(TASK_RUNNING); + submit_bio_wait(&bio); bio_release_pages(&bio, should_dirty); if (unlikely(bio.bi_status)) @@ -197,8 +177,10 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, (bdev_logical_block_size(bdev) - 1)) return -EINVAL; - bio = bio_alloc_kiocb(iocb, bdev, nr_pages, opf, &blkdev_dio_pool); - + if (iocb->ki_flags & IOCB_ALLOC_CACHE) + opf |= REQ_ALLOC_CACHE; + bio = bio_alloc_bioset(bdev, nr_pages, opf, GFP_KERNEL, + &blkdev_dio_pool); dio = container_of(bio, struct blkdev_dio, bio); atomic_set(&dio->ref, 1); /* @@ -320,7 +302,10 @@ static ssize_t __blkdev_direct_IO_async(struct kiocb *iocb, (bdev_logical_block_size(bdev) - 1)) return -EINVAL; - bio = bio_alloc_kiocb(iocb, bdev, nr_pages, opf, &blkdev_dio_pool); + if (iocb->ki_flags & IOCB_ALLOC_CACHE) + opf |= REQ_ALLOC_CACHE; + bio = bio_alloc_bioset(bdev, nr_pages, opf, GFP_KERNEL, + &blkdev_dio_pool); dio = container_of(bio, struct blkdev_dio, bio); dio->flags = 0; dio->iocb = iocb; @@ -387,9 +372,9 @@ static int blkdev_writepage(struct page *page, struct writeback_control *wbc) return block_write_full_page(page, blkdev_get_block, wbc); } -static int blkdev_readpage(struct file * file, struct page * page) +static int blkdev_read_folio(struct file *file, struct folio *folio) { - return block_read_full_page(page, blkdev_get_block); + return block_read_full_folio(folio, blkdev_get_block); } static void blkdev_readahead(struct readahead_control *rac) @@ -398,11 +383,9 @@ static void blkdev_readahead(struct readahead_control *rac) } static int blkdev_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, struct page **pagep, - void **fsdata) + loff_t pos, unsigned len, struct page **pagep, void **fsdata) { - return block_write_begin(mapping, pos, len, flags, pagep, - blkdev_get_block); + return block_write_begin(mapping, pos, len, pagep, blkdev_get_block); } static int blkdev_write_end(struct file *file, struct address_space *mapping, @@ -427,7 +410,7 @@ static int blkdev_writepages(struct address_space *mapping, const struct address_space_operations def_blk_aops = { .dirty_folio = block_dirty_folio, .invalidate_folio = block_invalidate_folio, - .readpage = blkdev_readpage, + .read_folio = blkdev_read_folio, .readahead = blkdev_readahead, .writepage = blkdev_writepage, .write_begin = blkdev_write_begin, @@ -672,7 +655,7 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start, break; case FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE | FALLOC_FL_NO_HIDE_STALE: error = blkdev_issue_discard(bdev, start >> SECTOR_SHIFT, - len >> SECTOR_SHIFT, GFP_KERNEL, 0); + len >> SECTOR_SHIFT, GFP_KERNEL); break; default: error = -EOPNOTSUPP; diff --git a/block/genhd.c b/block/genhd.c index b8b6759d670f..36532b931841 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -1010,7 +1010,7 @@ static ssize_t disk_alignment_offset_show(struct device *dev, { struct gendisk *disk = dev_to_disk(dev); - return sprintf(buf, "%d\n", queue_alignment_offset(disk->queue)); + return sprintf(buf, "%d\n", bdev_alignment_offset(disk->part0)); } static ssize_t disk_discard_alignment_show(struct device *dev, @@ -1019,7 +1019,7 @@ static ssize_t disk_discard_alignment_show(struct device *dev, { struct gendisk *disk = dev_to_disk(dev); - return sprintf(buf, "%d\n", queue_discard_alignment(disk->queue)); + return sprintf(buf, "%d\n", bdev_alignment_offset(disk->part0)); } static ssize_t diskseq_show(struct device *dev, diff --git a/block/ioctl.c b/block/ioctl.c index 4a86340133e4..46949f1b0dba 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -83,18 +83,17 @@ static int compat_blkpg_ioctl(struct block_device *bdev, #endif static int blk_ioctl_discard(struct block_device *bdev, fmode_t mode, - unsigned long arg, unsigned long flags) + unsigned long arg) { uint64_t range[2]; uint64_t start, len; - struct request_queue *q = bdev_get_queue(bdev); struct inode *inode = bdev->bd_inode; int err; if (!(mode & FMODE_WRITE)) return -EBADF; - if (!blk_queue_discard(q)) + if (!bdev_max_discard_sectors(bdev)) return -EOPNOTSUPP; if (copy_from_user(range, (void __user *)arg, sizeof(range))) @@ -115,15 +114,43 @@ static int blk_ioctl_discard(struct block_device *bdev, fmode_t mode, err = truncate_bdev_range(bdev, mode, start, start + len - 1); if (err) goto fail; - - err = blkdev_issue_discard(bdev, start >> 9, len >> 9, - GFP_KERNEL, flags); - + err = blkdev_issue_discard(bdev, start >> 9, len >> 9, GFP_KERNEL); fail: filemap_invalidate_unlock(inode->i_mapping); return err; } +static int blk_ioctl_secure_erase(struct block_device *bdev, fmode_t mode, + void __user *argp) +{ + uint64_t start, len; + uint64_t range[2]; + int err; + + if (!(mode & FMODE_WRITE)) + return -EBADF; + if (!bdev_max_secure_erase_sectors(bdev)) + return -EOPNOTSUPP; + if (copy_from_user(range, argp, sizeof(range))) + return -EFAULT; + + start = range[0]; + len = range[1]; + if ((start & 511) || (len & 511)) + return -EINVAL; + if (start + len > bdev_nr_bytes(bdev)) + return -EINVAL; + + filemap_invalidate_lock(bdev->bd_inode->i_mapping); + err = truncate_bdev_range(bdev, mode, start, start + len - 1); + if (!err) + err = blkdev_issue_secure_erase(bdev, start >> 9, len >> 9, + GFP_KERNEL); + filemap_invalidate_unlock(bdev->bd_inode->i_mapping); + return err; +} + + static int blk_ioctl_zeroout(struct block_device *bdev, fmode_t mode, unsigned long arg) { @@ -451,10 +478,9 @@ static int blkdev_common_ioctl(struct block_device *bdev, fmode_t mode, case BLKROSET: return blkdev_roset(bdev, mode, cmd, arg); case BLKDISCARD: - return blk_ioctl_discard(bdev, mode, arg, 0); + return blk_ioctl_discard(bdev, mode, arg); case BLKSECDISCARD: - return blk_ioctl_discard(bdev, mode, arg, - BLKDEV_DISCARD_SECURE); + return blk_ioctl_secure_erase(bdev, mode, argp); case BLKZEROOUT: return blk_ioctl_zeroout(bdev, mode, arg); case BLKGETDISKSEQ: @@ -489,7 +515,7 @@ static int blkdev_common_ioctl(struct block_device *bdev, fmode_t mode, queue_max_sectors(bdev_get_queue(bdev))); return put_ushort(argp, max_sectors); case BLKROTATIONAL: - return put_ushort(argp, !blk_queue_nonrot(bdev_get_queue(bdev))); + return put_ushort(argp, !bdev_nonrot(bdev)); case BLKRASET: case BLKFRASET: if(!capable(CAP_SYS_ADMIN)) @@ -629,7 +655,7 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg) return compat_put_long(argp, (bdev->bd_disk->bdi->ra_pages * PAGE_SIZE) / 512); case BLKGETSIZE: - if (bdev_nr_sectors(bdev) > ~0UL) + if (bdev_nr_sectors(bdev) > ~(compat_ulong_t)0) return -EFBIG; return compat_put_ulong(argp, bdev_nr_sectors(bdev)); diff --git a/block/mq-deadline.c b/block/mq-deadline.c index 3ed5eaf3446a..6ed602b2f80a 100644 --- a/block/mq-deadline.c +++ b/block/mq-deadline.c @@ -742,6 +742,7 @@ static void dd_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq, if (at_head) { list_add(&rq->queuelist, &per_prio->dispatch); + rq->fifo_time = jiffies; } else { deadline_add_rq_rb(per_prio, rq); diff --git a/block/partitions/acorn.c b/block/partitions/acorn.c index 2c381c694c57..d2fc122d7426 100644 --- a/block/partitions/acorn.c +++ b/block/partitions/acorn.c @@ -282,13 +282,13 @@ int adfspart_check_ADFS(struct parsed_partitions *state) #ifdef CONFIG_ACORN_PARTITION_RISCIX case PARTITION_RISCIX_SCSI: case PARTITION_RISCIX_MFM: - slot = riscix_partition(state, start_sect, slot, + riscix_partition(state, start_sect, slot, nr_sects); break; #endif case PARTITION_LINUX: - slot = linux_partition(state, start_sect, slot, + linux_partition(state, start_sect, slot, nr_sects); break; } diff --git a/block/partitions/atari.c b/block/partitions/atari.c index da5994175416..9655c728262a 100644 --- a/block/partitions/atari.c +++ b/block/partitions/atari.c @@ -140,7 +140,6 @@ int atari_partition(struct parsed_partitions *state) /* accept only GEM,BGM,RAW,LNX,SWP partitions */ if (!((pi->flg & 1) && OK_id(pi->id))) continue; - part_fmt = 2; put_partition (state, slot, be32_to_cpu(pi->st), be32_to_cpu(pi->siz)); diff --git a/block/partitions/core.c b/block/partitions/core.c index 2ef8dfa1e5c8..8a0ec929023b 100644 --- a/block/partitions/core.c +++ b/block/partitions/core.c @@ -200,21 +200,13 @@ static ssize_t part_ro_show(struct device *dev, static ssize_t part_alignment_offset_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct block_device *bdev = dev_to_bdev(dev); - - return sprintf(buf, "%u\n", - queue_limit_alignment_offset(&bdev_get_queue(bdev)->limits, - bdev->bd_start_sect)); + return sprintf(buf, "%u\n", bdev_alignment_offset(dev_to_bdev(dev))); } static ssize_t part_discard_alignment_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct block_device *bdev = dev_to_bdev(dev); - - return sprintf(buf, "%u\n", - queue_limit_discard_alignment(&bdev_get_queue(bdev)->limits, - bdev->bd_start_sect)); + return sprintf(buf, "%u\n", bdev_discard_alignment(dev_to_bdev(dev))); } static DEVICE_ATTR(partition, 0444, part_partition_show, NULL); @@ -486,7 +478,7 @@ int bdev_del_partition(struct gendisk *disk, int partno) goto out_unlock; ret = -EBUSY; - if (part->bd_openers) + if (atomic_read(&part->bd_openers)) goto out_unlock; delete_partition(part); diff --git a/block/partitions/ldm.c b/block/partitions/ldm.c index 27f6c7d9c776..38e58960ae03 100644 --- a/block/partitions/ldm.c +++ b/block/partitions/ldm.c @@ -736,7 +736,6 @@ static bool ldm_parse_cmp3 (const u8 *buffer, int buflen, struct vblk *vb) len = r_cols; } else { r_stripe = 0; - r_cols = 0; len = r_parent; } if (len < 0) @@ -783,11 +782,8 @@ static int ldm_parse_dgr3 (const u8 *buffer, int buflen, struct vblk *vb) r_id1 = ldm_relative (buffer, buflen, 0x24, r_diskid); r_id2 = ldm_relative (buffer, buflen, 0x24, r_id1); len = r_id2; - } else { - r_id1 = 0; - r_id2 = 0; + } else len = r_diskid; - } if (len < 0) return false; @@ -826,11 +822,8 @@ static bool ldm_parse_dgr4 (const u8 *buffer, int buflen, struct vblk *vb) r_id1 = ldm_relative (buffer, buflen, 0x44, r_name); r_id2 = ldm_relative (buffer, buflen, 0x44, r_id1); len = r_id2; - } else { - r_id1 = 0; - r_id2 = 0; + } else len = r_name; - } if (len < 0) return false; @@ -963,10 +956,8 @@ static bool ldm_parse_prt3(const u8 *buffer, int buflen, struct vblk *vb) return false; } len = r_index; - } else { - r_index = 0; + } else len = r_diskid; - } if (len < 0) { ldm_error("len %d < 0", len); return false; diff --git a/certs/.gitignore b/certs/.gitignore index 9e42fe3e02f5..56637aceaf81 100644 --- a/certs/.gitignore +++ b/certs/.gitignore @@ -1,4 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only +/blacklist_hashes_checked /extract-cert /x509_certificate_list /x509_revocation_list diff --git a/certs/Kconfig b/certs/Kconfig index 73d1350c223a..476755703cf8 100644 --- a/certs/Kconfig +++ b/certs/Kconfig @@ -104,8 +104,11 @@ config SYSTEM_BLACKLIST_HASH_LIST help If set, this option should be the filename of a list of hashes in the form "<hash>", "<hash>", ... . This will be included into a C - wrapper to incorporate the list into the kernel. Each <hash> should - be a string of hex digits. + wrapper to incorporate the list into the kernel. Each <hash> must be a + string starting with a prefix ("tbs" or "bin"), then a colon (":"), and + finally an even number of hexadecimal lowercase characters (up to 128). + Certificate hashes can be generated with + tools/certs/print-cert-tbs-hash.sh . config SYSTEM_REVOCATION_LIST bool "Provide system-wide ring of revocation certificates" @@ -124,4 +127,14 @@ config SYSTEM_REVOCATION_KEYS containing X.509 certificates to be included in the default blacklist keyring. +config SYSTEM_BLACKLIST_AUTH_UPDATE + bool "Allow root to add signed blacklist keys" + depends on SYSTEM_BLACKLIST_KEYRING + depends on SYSTEM_DATA_VERIFICATION + help + If set, provide the ability to load new blacklist keys at run time if + they are signed and vouched by a certificate from the builtin trusted + keyring. The PKCS#7 signature of the description is set in the key + payload. Blacklist keys cannot be removed. + endmenu diff --git a/certs/Makefile b/certs/Makefile index d8443cfb1c40..1d26ae36af20 100644 --- a/certs/Makefile +++ b/certs/Makefile @@ -7,6 +7,18 @@ obj-$(CONFIG_SYSTEM_TRUSTED_KEYRING) += system_keyring.o system_certificates.o c obj-$(CONFIG_SYSTEM_BLACKLIST_KEYRING) += blacklist.o common.o obj-$(CONFIG_SYSTEM_REVOCATION_LIST) += revocation_certificates.o ifneq ($(CONFIG_SYSTEM_BLACKLIST_HASH_LIST),) +quiet_cmd_check_blacklist_hashes = CHECK $(patsubst "%",%,$(2)) + cmd_check_blacklist_hashes = $(AWK) -f $(srctree)/scripts/check-blacklist-hashes.awk $(2); touch $@ + +$(eval $(call config_filename,SYSTEM_BLACKLIST_HASH_LIST)) + +$(obj)/blacklist_hashes.o: $(obj)/blacklist_hashes_checked + +CFLAGS_blacklist_hashes.o += -I$(srctree) + +targets += blacklist_hashes_checked +$(obj)/blacklist_hashes_checked: $(SYSTEM_BLACKLIST_HASH_LIST_SRCPREFIX)$(SYSTEM_BLACKLIST_HASH_LIST_FILENAME) scripts/check-blacklist-hashes.awk FORCE + $(call if_changed,check_blacklist_hashes,$(SYSTEM_BLACKLIST_HASH_LIST_SRCPREFIX)$(CONFIG_SYSTEM_BLACKLIST_HASH_LIST)) obj-$(CONFIG_SYSTEM_BLACKLIST_KEYRING) += blacklist_hashes.o else obj-$(CONFIG_SYSTEM_BLACKLIST_KEYRING) += blacklist_nohashes.o @@ -21,7 +33,7 @@ $(obj)/system_certificates.o: $(obj)/x509_certificate_list $(obj)/x509_certificate_list: $(CONFIG_SYSTEM_TRUSTED_KEYS) $(obj)/extract-cert FORCE $(call if_changed,extract_certs) -targets += x509_certificate_list +targets += x509_certificate_list blacklist_hashes_checked # If module signing is requested, say by allyesconfig, but a key has not been # supplied, then one will need to be generated to make sure the build does not diff --git a/certs/blacklist.c b/certs/blacklist.c index c9a435b15af4..25094ea73600 100644 --- a/certs/blacklist.c +++ b/certs/blacklist.c @@ -15,10 +15,24 @@ #include <linux/err.h> #include <linux/seq_file.h> #include <linux/uidgid.h> +#include <linux/verification.h> #include <keys/system_keyring.h> #include "blacklist.h" #include "common.h" +/* + * According to crypto/asymmetric_keys/x509_cert_parser.c:x509_note_pkey_algo(), + * the size of the currently longest supported hash algorithm is 512 bits, + * which translates into 128 hex characters. + */ +#define MAX_HASH_LEN 128 + +#define BLACKLIST_KEY_PERM (KEY_POS_SEARCH | KEY_POS_VIEW | \ + KEY_USR_SEARCH | KEY_USR_VIEW) + +static const char tbs_prefix[] = "tbs"; +static const char bin_prefix[] = "bin"; + static struct key *blacklist_keyring; #ifdef CONFIG_SYSTEM_REVOCATION_LIST @@ -32,41 +46,89 @@ extern __initconst const unsigned long revocation_certificate_list_size; */ static int blacklist_vet_description(const char *desc) { - int n = 0; - - if (*desc == ':') - return -EINVAL; - for (; *desc; desc++) - if (*desc == ':') - goto found_colon; + int i, prefix_len, tbs_step = 0, bin_step = 0; + + /* The following algorithm only works if prefix lengths match. */ + BUILD_BUG_ON(sizeof(tbs_prefix) != sizeof(bin_prefix)); + prefix_len = sizeof(tbs_prefix) - 1; + for (i = 0; *desc; desc++, i++) { + if (*desc == ':') { + if (tbs_step == prefix_len) + goto found_colon; + if (bin_step == prefix_len) + goto found_colon; + return -EINVAL; + } + if (i >= prefix_len) + return -EINVAL; + if (*desc == tbs_prefix[i]) + tbs_step++; + if (*desc == bin_prefix[i]) + bin_step++; + } return -EINVAL; found_colon: desc++; - for (; *desc; desc++) { + for (i = 0; *desc && i < MAX_HASH_LEN; desc++, i++) { if (!isxdigit(*desc) || isupper(*desc)) return -EINVAL; - n++; } + if (*desc) + /* The hash is greater than MAX_HASH_LEN. */ + return -ENOPKG; - if (n == 0 || n & 1) + /* Checks for an even number of hexadecimal characters. */ + if (i == 0 || i & 1) return -EINVAL; return 0; } -/* - * The hash to be blacklisted is expected to be in the description. There will - * be no payload. - */ -static int blacklist_preparse(struct key_preparsed_payload *prep) +static int blacklist_key_instantiate(struct key *key, + struct key_preparsed_payload *prep) { - if (prep->datalen > 0) - return -EINVAL; - return 0; +#ifdef CONFIG_SYSTEM_BLACKLIST_AUTH_UPDATE + int err; +#endif + + /* Sets safe default permissions for keys loaded by user space. */ + key->perm = BLACKLIST_KEY_PERM; + + /* + * Skips the authentication step for builtin hashes, they are not + * signed but still trusted. + */ + if (key->flags & (1 << KEY_FLAG_BUILTIN)) + goto out; + +#ifdef CONFIG_SYSTEM_BLACKLIST_AUTH_UPDATE + /* + * Verifies the description's PKCS#7 signature against the builtin + * trusted keyring. + */ + err = verify_pkcs7_signature(key->description, + strlen(key->description), prep->data, prep->datalen, + NULL, VERIFYING_UNSPECIFIED_SIGNATURE, NULL, NULL); + if (err) + return err; +#else + /* + * It should not be possible to come here because the keyring doesn't + * have KEY_USR_WRITE and the only other way to call this function is + * for builtin hashes. + */ + WARN_ON_ONCE(1); + return -EPERM; +#endif + +out: + return generic_key_instantiate(key, prep); } -static void blacklist_free_preparse(struct key_preparsed_payload *prep) +static int blacklist_key_update(struct key *key, + struct key_preparsed_payload *prep) { + return -EPERM; } static void blacklist_describe(const struct key *key, struct seq_file *m) @@ -77,17 +139,48 @@ static void blacklist_describe(const struct key *key, struct seq_file *m) static struct key_type key_type_blacklist = { .name = "blacklist", .vet_description = blacklist_vet_description, - .preparse = blacklist_preparse, - .free_preparse = blacklist_free_preparse, - .instantiate = generic_key_instantiate, + .instantiate = blacklist_key_instantiate, + .update = blacklist_key_update, .describe = blacklist_describe, }; +static char *get_raw_hash(const u8 *hash, size_t hash_len, + enum blacklist_hash_type hash_type) +{ + size_t type_len; + const char *type_prefix; + char *buffer, *p; + + switch (hash_type) { + case BLACKLIST_HASH_X509_TBS: + type_len = sizeof(tbs_prefix) - 1; + type_prefix = tbs_prefix; + break; + case BLACKLIST_HASH_BINARY: + type_len = sizeof(bin_prefix) - 1; + type_prefix = bin_prefix; + break; + default: + WARN_ON_ONCE(1); + return ERR_PTR(-EINVAL); + } + buffer = kmalloc(type_len + 1 + hash_len * 2 + 1, GFP_KERNEL); + if (!buffer) + return ERR_PTR(-ENOMEM); + p = memcpy(buffer, type_prefix, type_len); + p += type_len; + *p++ = ':'; + bin2hex(p, hash, hash_len); + p += hash_len * 2; + *p = '\0'; + return buffer; +} + /** - * mark_hash_blacklisted - Add a hash to the system blacklist + * mark_raw_hash_blacklisted - Add a hash to the system blacklist * @hash: The hash as a hex string with a type prefix (eg. "tbs:23aa429783") */ -int mark_hash_blacklisted(const char *hash) +static int mark_raw_hash_blacklisted(const char *hash) { key_ref_t key; @@ -96,8 +189,7 @@ int mark_hash_blacklisted(const char *hash) hash, NULL, 0, - ((KEY_POS_ALL & ~KEY_POS_SETATTR) | - KEY_USR_VIEW), + BLACKLIST_KEY_PERM, KEY_ALLOC_NOT_IN_QUOTA | KEY_ALLOC_BUILT_IN); if (IS_ERR(key)) { @@ -107,29 +199,36 @@ int mark_hash_blacklisted(const char *hash) return 0; } +int mark_hash_blacklisted(const u8 *hash, size_t hash_len, + enum blacklist_hash_type hash_type) +{ + const char *buffer; + int err; + + buffer = get_raw_hash(hash, hash_len, hash_type); + if (IS_ERR(buffer)) + return PTR_ERR(buffer); + err = mark_raw_hash_blacklisted(buffer); + kfree(buffer); + return err; +} + /** * is_hash_blacklisted - Determine if a hash is blacklisted * @hash: The hash to be checked as a binary blob * @hash_len: The length of the binary hash - * @type: Type of hash + * @hash_type: Type of hash */ -int is_hash_blacklisted(const u8 *hash, size_t hash_len, const char *type) +int is_hash_blacklisted(const u8 *hash, size_t hash_len, + enum blacklist_hash_type hash_type) { key_ref_t kref; - size_t type_len = strlen(type); - char *buffer, *p; + const char *buffer; int ret = 0; - buffer = kmalloc(type_len + 1 + hash_len * 2 + 1, GFP_KERNEL); - if (!buffer) - return -ENOMEM; - p = memcpy(buffer, type, type_len); - p += type_len; - *p++ = ':'; - bin2hex(p, hash, hash_len); - p += hash_len * 2; - *p = 0; - + buffer = get_raw_hash(hash, hash_len, hash_type); + if (IS_ERR(buffer)) + return PTR_ERR(buffer); kref = keyring_search(make_key_ref(blacklist_keyring, true), &key_type_blacklist, buffer, false); if (!IS_ERR(kref)) { @@ -144,7 +243,8 @@ EXPORT_SYMBOL_GPL(is_hash_blacklisted); int is_binary_blacklisted(const u8 *hash, size_t hash_len) { - if (is_hash_blacklisted(hash, hash_len, "bin") == -EKEYREJECTED) + if (is_hash_blacklisted(hash, hash_len, BLACKLIST_HASH_BINARY) == + -EKEYREJECTED) return -EPERM; return 0; @@ -166,8 +266,10 @@ int add_key_to_revocation_list(const char *data, size_t size) NULL, data, size, - ((KEY_POS_ALL & ~KEY_POS_SETATTR) | KEY_USR_VIEW), - KEY_ALLOC_NOT_IN_QUOTA | KEY_ALLOC_BUILT_IN); + KEY_POS_VIEW | KEY_POS_READ | KEY_POS_SEARCH + | KEY_USR_VIEW, + KEY_ALLOC_NOT_IN_QUOTA | KEY_ALLOC_BUILT_IN + | KEY_ALLOC_BYPASS_RESTRICTION); if (IS_ERR(key)) { pr_err("Problem with revocation key (%ld)\n", PTR_ERR(key)); @@ -194,30 +296,57 @@ int is_key_on_revocation_list(struct pkcs7_message *pkcs7) } #endif +static int restrict_link_for_blacklist(struct key *dest_keyring, + const struct key_type *type, const union key_payload *payload, + struct key *restrict_key) +{ + if (type == &key_type_blacklist) + return 0; + return -EOPNOTSUPP; +} + /* * Initialise the blacklist + * + * The blacklist_init() function is registered as an initcall via + * device_initcall(). As a result if the blacklist_init() function fails for + * any reason the kernel continues to execute. While cleanly returning -ENODEV + * could be acceptable for some non-critical kernel parts, if the blacklist + * keyring fails to load it defeats the certificate/key based deny list for + * signed modules. If a critical piece of security functionality that users + * expect to be present fails to initialize, panic()ing is likely the right + * thing to do. */ static int __init blacklist_init(void) { const char *const *bl; + struct key_restriction *restriction; if (register_key_type(&key_type_blacklist) < 0) panic("Can't allocate system blacklist key type\n"); + restriction = kzalloc(sizeof(*restriction), GFP_KERNEL); + if (!restriction) + panic("Can't allocate blacklist keyring restriction\n"); + restriction->check = restrict_link_for_blacklist; + blacklist_keyring = keyring_alloc(".blacklist", GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, current_cred(), - (KEY_POS_ALL & ~KEY_POS_SETATTR) | - KEY_USR_VIEW | KEY_USR_READ | - KEY_USR_SEARCH, - KEY_ALLOC_NOT_IN_QUOTA | + KEY_POS_VIEW | KEY_POS_READ | KEY_POS_SEARCH | + KEY_POS_WRITE | + KEY_USR_VIEW | KEY_USR_READ | KEY_USR_SEARCH +#ifdef CONFIG_SYSTEM_BLACKLIST_AUTH_UPDATE + | KEY_USR_WRITE +#endif + , KEY_ALLOC_NOT_IN_QUOTA | KEY_ALLOC_SET_KEEP, - NULL, NULL); + restriction, NULL); if (IS_ERR(blacklist_keyring)) panic("Can't allocate system blacklist keyring\n"); for (bl = blacklist_hashes; *bl; bl++) - if (mark_hash_blacklisted(*bl) < 0) + if (mark_raw_hash_blacklisted(*bl) < 0) pr_err("- blacklisting failed\n"); return 0; } diff --git a/crypto/asymmetric_keys/x509_public_key.c b/crypto/asymmetric_keys/x509_public_key.c index 91a4ad50dea2..77ed4e93ad56 100644 --- a/crypto/asymmetric_keys/x509_public_key.c +++ b/crypto/asymmetric_keys/x509_public_key.c @@ -69,7 +69,8 @@ int x509_get_sig_params(struct x509_certificate *cert) if (ret < 0) goto error_2; - ret = is_hash_blacklisted(sig->digest, sig->digest_size, "tbs"); + ret = is_hash_blacklisted(sig->digest, sig->digest_size, + BLACKLIST_HASH_X509_TBS); if (ret == -EKEYREJECTED) { pr_err("Cert %*phN is blacklisted\n", sig->digest_size, sig->digest); diff --git a/drivers/acpi/acpi_pad.c b/drivers/acpi/acpi_pad.c index f45979aa2d64..ec0e22a1e25d 100644 --- a/drivers/acpi/acpi_pad.c +++ b/drivers/acpi/acpi_pad.c @@ -17,6 +17,7 @@ #include <linux/tick.h> #include <linux/slab.h> #include <linux/acpi.h> +#include <linux/perf_event.h> #include <asm/mwait.h> #include <xen/xen.h> @@ -164,6 +165,9 @@ static int power_saving_thread(void *data) tsc_marked_unstable = 1; } local_irq_disable(); + + perf_lopwr_cb(true); + tick_broadcast_enable(); tick_broadcast_enter(); stop_critical_timings(); @@ -172,6 +176,9 @@ static int power_saving_thread(void *data) start_critical_timings(); tick_broadcast_exit(); + + perf_lopwr_cb(false); + local_irq_enable(); if (time_before(expire_time, jiffies)) { diff --git a/drivers/acpi/acpica/acapps.h b/drivers/acpi/acpica/acapps.h index 725e2f65cdca..0a50b4912515 100644 --- a/drivers/acpi/acpica/acapps.h +++ b/drivers/acpi/acpica/acapps.h @@ -3,7 +3,7 @@ * * Module Name: acapps - common include for ACPI applications/tools * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ @@ -17,7 +17,7 @@ /* Common info for tool signons */ #define ACPICA_NAME "Intel ACPI Component Architecture" -#define ACPICA_COPYRIGHT "Copyright (c) 2000 - 2021 Intel Corporation" +#define ACPICA_COPYRIGHT "Copyright (c) 2000 - 2022 Intel Corporation" #if ACPI_MACHINE_WIDTH == 64 #define ACPI_WIDTH " (64-bit version)" diff --git a/drivers/acpi/acpica/accommon.h b/drivers/acpi/acpica/accommon.h index be3826f46f88..bb329e34ee7d 100644 --- a/drivers/acpi/acpica/accommon.h +++ b/drivers/acpi/acpica/accommon.h @@ -3,7 +3,7 @@ * * Name: accommon.h - Common include files for generation of ACPICA source * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/acconvert.h b/drivers/acpi/acpica/acconvert.h index 53b41c7a6119..476d21e67767 100644 --- a/drivers/acpi/acpica/acconvert.h +++ b/drivers/acpi/acpica/acconvert.h @@ -3,7 +3,7 @@ * * Module Name: acapps - common include for ACPI applications/tools * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/acdebug.h b/drivers/acpi/acpica/acdebug.h index 3ccc7b2a76f1..d629716aa5b2 100644 --- a/drivers/acpi/acpica/acdebug.h +++ b/drivers/acpi/acpica/acdebug.h @@ -3,7 +3,7 @@ * * Name: acdebug.h - ACPI/AML debugger * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/acdispat.h b/drivers/acpi/acpica/acdispat.h index 3170a24fe505..fe2c3630a38d 100644 --- a/drivers/acpi/acpica/acdispat.h +++ b/drivers/acpi/acpica/acdispat.h @@ -3,7 +3,7 @@ * * Name: acdispat.h - dispatcher (parser to interpreter interface) * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/acevents.h b/drivers/acpi/acpica/acevents.h index b29ba436944a..922f559a3e59 100644 --- a/drivers/acpi/acpica/acevents.h +++ b/drivers/acpi/acpica/acevents.h @@ -3,7 +3,7 @@ * * Name: acevents.h - Event subcomponent prototypes and defines * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/acglobal.h b/drivers/acpi/acpica/acglobal.h index 4366d36ef119..088d6a7d052c 100644 --- a/drivers/acpi/acpica/acglobal.h +++ b/drivers/acpi/acpica/acglobal.h @@ -3,7 +3,7 @@ * * Name: acglobal.h - Declarations for global variables * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/achware.h b/drivers/acpi/acpica/achware.h index 810de0b4c125..6f2787506b50 100644 --- a/drivers/acpi/acpica/achware.h +++ b/drivers/acpi/acpica/achware.h @@ -3,7 +3,7 @@ * * Name: achware.h -- hardware specific interfaces * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/acinterp.h b/drivers/acpi/acpica/acinterp.h index 816a16e1fc4c..6bdf133a2767 100644 --- a/drivers/acpi/acpica/acinterp.h +++ b/drivers/acpi/acpica/acinterp.h @@ -3,7 +3,7 @@ * * Name: acinterp.h - Interpreter subcomponent prototypes and defines * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/aclocal.h b/drivers/acpi/acpica/aclocal.h index be57436182a1..901b1543b869 100644 --- a/drivers/acpi/acpica/aclocal.h +++ b/drivers/acpi/acpica/aclocal.h @@ -3,7 +3,7 @@ * * Name: aclocal.h - Internal data types used across the ACPI subsystem * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/acmacros.h b/drivers/acpi/acpica/acmacros.h index 93bd2d19c156..2f3e609df47d 100644 --- a/drivers/acpi/acpica/acmacros.h +++ b/drivers/acpi/acpica/acmacros.h @@ -3,7 +3,7 @@ * * Name: acmacros.h - C macros for the entire subsystem. * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/acnamesp.h b/drivers/acpi/acpica/acnamesp.h index 199aabac3790..7b27b9cc5916 100644 --- a/drivers/acpi/acpica/acnamesp.h +++ b/drivers/acpi/acpica/acnamesp.h @@ -3,7 +3,7 @@ * * Name: acnamesp.h - Namespace subcomponent prototypes and defines * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/acobject.h b/drivers/acpi/acpica/acobject.h index 0aa0d847cb25..6af5dc995085 100644 --- a/drivers/acpi/acpica/acobject.h +++ b/drivers/acpi/acpica/acobject.h @@ -3,7 +3,7 @@ * * Name: acobject.h - Definition of union acpi_operand_object (Internal object only) * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/acopcode.h b/drivers/acpi/acpica/acopcode.h index c3f12ee9fc6f..a224926bd9c8 100644 --- a/drivers/acpi/acpica/acopcode.h +++ b/drivers/acpi/acpica/acopcode.h @@ -3,7 +3,7 @@ * * Name: acopcode.h - AML opcode information for the AML parser and interpreter * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/acparser.h b/drivers/acpi/acpica/acparser.h index 8e40e5909458..4511c2bd8bc3 100644 --- a/drivers/acpi/acpica/acparser.h +++ b/drivers/acpi/acpica/acparser.h @@ -3,7 +3,7 @@ * * Module Name: acparser.h - AML Parser subcomponent prototypes and defines * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/acpredef.h b/drivers/acpi/acpica/acpredef.h index 5951b433c304..f7d65a20026b 100644 --- a/drivers/acpi/acpica/acpredef.h +++ b/drivers/acpi/acpica/acpredef.h @@ -3,7 +3,7 @@ * * Name: acpredef - Information table for ACPI predefined methods and objects * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/acresrc.h b/drivers/acpi/acpica/acresrc.h index 37c47e185fd4..f7749c63d277 100644 --- a/drivers/acpi/acpica/acresrc.h +++ b/drivers/acpi/acpica/acresrc.h @@ -3,7 +3,7 @@ * * Name: acresrc.h - Resource Manager function prototypes * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/acstruct.h b/drivers/acpi/acpica/acstruct.h index e3beb096c46d..b859de96a1e4 100644 --- a/drivers/acpi/acpica/acstruct.h +++ b/drivers/acpi/acpica/acstruct.h @@ -3,7 +3,7 @@ * * Name: acstruct.h - Internal structs * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/actables.h b/drivers/acpi/acpica/actables.h index 533802fe73e9..f8d7bfd737df 100644 --- a/drivers/acpi/acpica/actables.h +++ b/drivers/acpi/acpica/actables.h @@ -3,7 +3,7 @@ * * Name: actables.h - ACPI table management * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/acutils.h b/drivers/acpi/acpica/acutils.h index 59d6ded01614..6e6270f96bfb 100644 --- a/drivers/acpi/acpica/acutils.h +++ b/drivers/acpi/acpica/acutils.h @@ -3,7 +3,7 @@ * * Name: acutils.h -- prototypes for the common (subsystem-wide) procedures * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/amlcode.h b/drivers/acpi/acpica/amlcode.h index d6b088c5001f..62a7ec277513 100644 --- a/drivers/acpi/acpica/amlcode.h +++ b/drivers/acpi/acpica/amlcode.h @@ -5,7 +5,7 @@ * Declarations and definitions contained herein are derived * directly from the ACPI specification. * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/amlresrc.h b/drivers/acpi/acpica/amlresrc.h index b98123210281..b31779ce204a 100644 --- a/drivers/acpi/acpica/amlresrc.h +++ b/drivers/acpi/acpica/amlresrc.h @@ -3,7 +3,7 @@ * * Module Name: amlresrc.h - AML resource descriptors * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/dbhistry.c b/drivers/acpi/acpica/dbhistry.c index fd813c5d3952..105e6ceaa887 100644 --- a/drivers/acpi/acpica/dbhistry.c +++ b/drivers/acpi/acpica/dbhistry.c @@ -3,7 +3,7 @@ * * Module Name: dbhistry - debugger HISTORY command * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/dsargs.c b/drivers/acpi/acpica/dsargs.c index 6630d6536fb0..2963d1579c05 100644 --- a/drivers/acpi/acpica/dsargs.c +++ b/drivers/acpi/acpica/dsargs.c @@ -4,7 +4,7 @@ * Module Name: dsargs - Support for execution of dynamic arguments for static * objects (regions, fields, buffer fields, etc.) * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/dscontrol.c b/drivers/acpi/acpica/dscontrol.c index a152f03135cd..8492619149d1 100644 --- a/drivers/acpi/acpica/dscontrol.c +++ b/drivers/acpi/acpica/dscontrol.c @@ -4,7 +4,7 @@ * Module Name: dscontrol - Support for execution control opcodes - * if/else/while/return * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/dsdebug.c b/drivers/acpi/acpica/dsdebug.c index b9b03d629930..2d99ccf5bde7 100644 --- a/drivers/acpi/acpica/dsdebug.c +++ b/drivers/acpi/acpica/dsdebug.c @@ -3,7 +3,7 @@ * * Module Name: dsdebug - Parser/Interpreter interface - debugging * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/dsfield.c b/drivers/acpi/acpica/dsfield.c index a16817767969..de175f1b4beb 100644 --- a/drivers/acpi/acpica/dsfield.c +++ b/drivers/acpi/acpica/dsfield.c @@ -3,7 +3,7 @@ * * Module Name: dsfield - Dispatcher field routines * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/dsinit.c b/drivers/acpi/acpica/dsinit.c index ba6f882e83bc..dffd54fdbd51 100644 --- a/drivers/acpi/acpica/dsinit.c +++ b/drivers/acpi/acpica/dsinit.c @@ -3,7 +3,7 @@ * * Module Name: dsinit - Object initialization namespace walk * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/dsmethod.c b/drivers/acpi/acpica/dsmethod.c index 8e011e59b9b4..ae2e768830bf 100644 --- a/drivers/acpi/acpica/dsmethod.c +++ b/drivers/acpi/acpica/dsmethod.c @@ -3,7 +3,7 @@ * * Module Name: dsmethod - Parser/Interpreter interface - control method parsing * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/dsobject.c b/drivers/acpi/acpica/dsobject.c index 3c0c31157e7e..e3dfc734ace9 100644 --- a/drivers/acpi/acpica/dsobject.c +++ b/drivers/acpi/acpica/dsobject.c @@ -3,7 +3,7 @@ * * Module Name: dsobject - Dispatcher object management routines * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/dsopcode.c b/drivers/acpi/acpica/dsopcode.c index 44c448269861..2b9b6a974ca9 100644 --- a/drivers/acpi/acpica/dsopcode.c +++ b/drivers/acpi/acpica/dsopcode.c @@ -3,7 +3,7 @@ * * Module Name: dsopcode - Dispatcher support for regions and fields * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/dspkginit.c b/drivers/acpi/acpica/dspkginit.c index e642d65bcc66..1624d6e7dc46 100644 --- a/drivers/acpi/acpica/dspkginit.c +++ b/drivers/acpi/acpica/dspkginit.c @@ -3,7 +3,7 @@ * * Module Name: dspkginit - Completion of deferred package initialization * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/dswexec.c b/drivers/acpi/acpica/dswexec.c index f2d2267054af..e8ad41387f84 100644 --- a/drivers/acpi/acpica/dswexec.c +++ b/drivers/acpi/acpica/dswexec.c @@ -4,7 +4,7 @@ * Module Name: dswexec - Dispatcher method execution callbacks; * dispatch to interpreter. * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ @@ -30,7 +30,7 @@ static acpi_execute_op acpi_gbl_op_type_dispatch[] = { acpi_ex_opcode_0A_0T_1R, acpi_ex_opcode_1A_0T_0R, acpi_ex_opcode_1A_0T_1R, - acpi_ex_opcode_1A_1T_0R, + NULL, /* Was: acpi_ex_opcode_1A_0T_0R (Was for Load operator) */ acpi_ex_opcode_1A_1T_1R, acpi_ex_opcode_2A_0T_0R, acpi_ex_opcode_2A_0T_1R, diff --git a/drivers/acpi/acpica/dswload.c b/drivers/acpi/acpica/dswload.c index a377638e44f9..9f6573646ab5 100644 --- a/drivers/acpi/acpica/dswload.c +++ b/drivers/acpi/acpica/dswload.c @@ -3,7 +3,7 @@ * * Module Name: dswload - Dispatcher first pass namespace load callbacks * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/dswload2.c b/drivers/acpi/acpica/dswload2.c index 3625952c3957..778df616aaa0 100644 --- a/drivers/acpi/acpica/dswload2.c +++ b/drivers/acpi/acpica/dswload2.c @@ -3,7 +3,7 @@ * * Module Name: dswload2 - Dispatcher second pass namespace load callbacks * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/dswscope.c b/drivers/acpi/acpica/dswscope.c index 9c123af08bc1..634b9100f674 100644 --- a/drivers/acpi/acpica/dswscope.c +++ b/drivers/acpi/acpica/dswscope.c @@ -3,7 +3,7 @@ * * Module Name: dswscope - Scope stack manipulation * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/dswstate.c b/drivers/acpi/acpica/dswstate.c index fbe2ba05c82a..0aa735d3b93c 100644 --- a/drivers/acpi/acpica/dswstate.c +++ b/drivers/acpi/acpica/dswstate.c @@ -3,7 +3,7 @@ * * Module Name: dswstate - Dispatcher parse tree walk management routines * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/evevent.c b/drivers/acpi/acpica/evevent.c index 35385148fedb..df596d46dd97 100644 --- a/drivers/acpi/acpica/evevent.c +++ b/drivers/acpi/acpica/evevent.c @@ -3,7 +3,7 @@ * * Module Name: evevent - Fixed Event handling and dispatch * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/evglock.c b/drivers/acpi/acpica/evglock.c index de4eea606ccd..9aab54797ded 100644 --- a/drivers/acpi/acpica/evglock.c +++ b/drivers/acpi/acpica/evglock.c @@ -3,7 +3,7 @@ * * Module Name: evglock - Global Lock support * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/evgpe.c b/drivers/acpi/acpica/evgpe.c index c5a06882bdf6..a6bb480d631c 100644 --- a/drivers/acpi/acpica/evgpe.c +++ b/drivers/acpi/acpica/evgpe.c @@ -3,7 +3,7 @@ * * Module Name: evgpe - General Purpose Event handling and dispatch * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/evgpeblk.c b/drivers/acpi/acpica/evgpeblk.c index e5f8245c2d93..39fe4566310b 100644 --- a/drivers/acpi/acpica/evgpeblk.c +++ b/drivers/acpi/acpica/evgpeblk.c @@ -3,7 +3,7 @@ * * Module Name: evgpeblk - GPE block creation and initialization. * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/evgpeinit.c b/drivers/acpi/acpica/evgpeinit.c index b0724d6e6e80..2f1a75fee61c 100644 --- a/drivers/acpi/acpica/evgpeinit.c +++ b/drivers/acpi/acpica/evgpeinit.c @@ -3,7 +3,7 @@ * * Module Name: evgpeinit - System GPE initialization and update * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/evgpeutil.c b/drivers/acpi/acpica/evgpeutil.c index 2e74308d7725..c32eb57aa21d 100644 --- a/drivers/acpi/acpica/evgpeutil.c +++ b/drivers/acpi/acpica/evgpeutil.c @@ -3,7 +3,7 @@ * * Module Name: evgpeutil - GPE utilities * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/evhandler.c b/drivers/acpi/acpica/evhandler.c index 8f43d38dc4ca..be9a05498adc 100644 --- a/drivers/acpi/acpica/evhandler.c +++ b/drivers/acpi/acpica/evhandler.c @@ -3,7 +3,7 @@ * * Module Name: evhandler - Support for Address Space handlers * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/evmisc.c b/drivers/acpi/acpica/evmisc.c index f14ebcd610ab..6172cddc1b39 100644 --- a/drivers/acpi/acpica/evmisc.c +++ b/drivers/acpi/acpica/evmisc.c @@ -3,7 +3,7 @@ * * Module Name: evmisc - Miscellaneous event manager support functions * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/evregion.c b/drivers/acpi/acpica/evregion.c index b9d77d327d38..b96b3a7e78e5 100644 --- a/drivers/acpi/acpica/evregion.c +++ b/drivers/acpi/acpica/evregion.c @@ -3,7 +3,7 @@ * * Module Name: evregion - Operation Region support * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/evrgnini.c b/drivers/acpi/acpica/evrgnini.c index d28dee929e61..ca4ba6b351fe 100644 --- a/drivers/acpi/acpica/evrgnini.c +++ b/drivers/acpi/acpica/evrgnini.c @@ -3,7 +3,7 @@ * * Module Name: evrgnini- ACPI address_space (op_region) init * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/evxface.c b/drivers/acpi/acpica/evxface.c index ff5cf5b0705a..18219abba108 100644 --- a/drivers/acpi/acpica/evxface.c +++ b/drivers/acpi/acpica/evxface.c @@ -3,7 +3,7 @@ * * Module Name: evxface - External interfaces for ACPI events * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/evxfevnt.c b/drivers/acpi/acpica/evxfevnt.c index 5445a361c621..8187b081e0a6 100644 --- a/drivers/acpi/acpica/evxfevnt.c +++ b/drivers/acpi/acpica/evxfevnt.c @@ -3,7 +3,7 @@ * * Module Name: evxfevnt - External Interfaces, ACPI event disable/enable * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/evxfgpe.c b/drivers/acpi/acpica/evxfgpe.c index a6d53cf86450..340947e412bb 100644 --- a/drivers/acpi/acpica/evxfgpe.c +++ b/drivers/acpi/acpica/evxfgpe.c @@ -3,7 +3,7 @@ * * Module Name: evxfgpe - External Interfaces for General Purpose Events (GPEs) * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/evxfregn.c b/drivers/acpi/acpica/evxfregn.c index b1ff0a8f9c14..0a8372bf6a77 100644 --- a/drivers/acpi/acpica/evxfregn.c +++ b/drivers/acpi/acpica/evxfregn.c @@ -4,7 +4,7 @@ * Module Name: evxfregn - External Interfaces, ACPI Operation Regions and * Address Spaces. * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exconcat.c b/drivers/acpi/acpica/exconcat.c index 2d220d470c60..66201742f499 100644 --- a/drivers/acpi/acpica/exconcat.c +++ b/drivers/acpi/acpica/exconcat.c @@ -3,7 +3,7 @@ * * Module Name: exconcat - Concatenate-type AML operators * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exconfig.c b/drivers/acpi/acpica/exconfig.c index 6c2685a6a4c1..d7d74ef87b18 100644 --- a/drivers/acpi/acpica/exconfig.c +++ b/drivers/acpi/acpica/exconfig.c @@ -3,7 +3,7 @@ * * Module Name: exconfig - Namespace reconfiguration (Load/Unload opcodes) * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ @@ -87,11 +87,21 @@ acpi_ex_load_table_op(struct acpi_walk_state *walk_state, struct acpi_namespace_node *parent_node; struct acpi_namespace_node *start_node; struct acpi_namespace_node *parameter_node = NULL; + union acpi_operand_object *return_obj; union acpi_operand_object *ddb_handle; u32 table_index; ACPI_FUNCTION_TRACE(ex_load_table_op); + /* Create the return object */ + + return_obj = acpi_ut_create_integer_object((u64)0); + if (!return_obj) { + return_ACPI_STATUS(AE_NO_MEMORY); + } + + *return_desc = return_obj; + /* Find the ACPI table in the RSDT/XSDT */ acpi_ex_exit_interpreter(); @@ -106,12 +116,6 @@ acpi_ex_load_table_op(struct acpi_walk_state *walk_state, /* Table not found, return an Integer=0 and AE_OK */ - ddb_handle = acpi_ut_create_integer_object((u64) 0); - if (!ddb_handle) { - return_ACPI_STATUS(AE_NO_MEMORY); - } - - *return_desc = ddb_handle; return_ACPI_STATUS(AE_OK); } @@ -198,7 +202,13 @@ acpi_ex_load_table_op(struct acpi_walk_state *walk_state, } } - *return_desc = ddb_handle; + /* Remove the reference to ddb_handle created by acpi_ex_add_table above */ + + acpi_ut_remove_reference(ddb_handle); + + /* Return -1 (non-zero) indicates success */ + + return_obj->integer.value = 0xFFFFFFFFFFFFFFFF; return_ACPI_STATUS(status); } @@ -249,7 +259,7 @@ acpi_ex_region_read(union acpi_operand_object *obj_desc, u32 length, u8 *buffer) * * PARAMETERS: obj_desc - Region or Buffer/Field where the table will be * obtained - * target - Where a handle to the table will be stored + * target - Where the status of the load will be stored * walk_state - Current state * * RETURN: Status @@ -278,6 +288,20 @@ acpi_ex_load_op(union acpi_operand_object *obj_desc, ACPI_FUNCTION_TRACE(ex_load_op); + if (target->common.descriptor_type == ACPI_DESC_TYPE_NAMED) { + target = + acpi_ns_get_attached_object(ACPI_CAST_PTR + (struct acpi_namespace_node, + target)); + } + if (target->common.type != ACPI_TYPE_INTEGER) { + ACPI_EXCEPTION((AE_INFO, AE_TYPE, + "Type not integer: %X\n", target->common.type)); + return_ACPI_STATUS(AE_AML_OPERAND_TYPE); + } + + target->integer.value = 0; + /* Source Object can be either an op_region or a Buffer/Field */ switch (obj_desc->common.type) { @@ -430,9 +454,6 @@ acpi_ex_load_op(union acpi_operand_object *obj_desc, */ status = acpi_ex_add_table(table_index, &ddb_handle); if (ACPI_FAILURE(status)) { - - /* On error, table_ptr was deallocated above */ - return_ACPI_STATUS(status); } @@ -442,21 +463,13 @@ acpi_ex_load_op(union acpi_operand_object *obj_desc, acpi_ns_initialize_objects(); acpi_ex_enter_interpreter(); - /* Store the ddb_handle into the Target operand */ + /* Remove the reference to ddb_handle created by acpi_ex_add_table above */ - status = acpi_ex_store(ddb_handle, target, walk_state); - if (ACPI_FAILURE(status)) { - (void)acpi_ex_unload_table(ddb_handle); - - /* table_ptr was deallocated above */ - - acpi_ut_remove_reference(ddb_handle); - return_ACPI_STATUS(status); - } + acpi_ut_remove_reference(ddb_handle); - /* Remove the reference by added by acpi_ex_store above */ + /* Return -1 (non-zero) indicates success */ - acpi_ut_remove_reference(ddb_handle); + target->integer.value = 0xFFFFFFFFFFFFFFFF; return_ACPI_STATUS(status); } diff --git a/drivers/acpi/acpica/exconvrt.c b/drivers/acpi/acpica/exconvrt.c index 6b7498371eb0..8de5d47ad485 100644 --- a/drivers/acpi/acpica/exconvrt.c +++ b/drivers/acpi/acpica/exconvrt.c @@ -3,7 +3,7 @@ * * Module Name: exconvrt - Object conversion routines * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/excreate.c b/drivers/acpi/acpica/excreate.c index deb3674ae726..fb2453fa9442 100644 --- a/drivers/acpi/acpica/excreate.c +++ b/drivers/acpi/acpica/excreate.c @@ -3,7 +3,7 @@ * * Module Name: excreate - Named object creation * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exdebug.c b/drivers/acpi/acpica/exdebug.c index 6a01e38b7d5a..8a99aadb9d15 100644 --- a/drivers/acpi/acpica/exdebug.c +++ b/drivers/acpi/acpica/exdebug.c @@ -3,7 +3,7 @@ * * Module Name: exdebug - Support for stores to the AML Debug Object * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exdump.c b/drivers/acpi/acpica/exdump.c index 2aea44ecc37d..24b3d041b3e5 100644 --- a/drivers/acpi/acpica/exdump.c +++ b/drivers/acpi/acpica/exdump.c @@ -3,7 +3,7 @@ * * Module Name: exdump - Interpreter debug output routines * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exfield.c b/drivers/acpi/acpica/exfield.c index 8618500f23b3..2b89a496de65 100644 --- a/drivers/acpi/acpica/exfield.c +++ b/drivers/acpi/acpica/exfield.c @@ -3,7 +3,7 @@ * * Module Name: exfield - AML execution - field_unit read/write * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exfldio.c b/drivers/acpi/acpica/exfldio.c index bdc7a30d1217..d769cea1468b 100644 --- a/drivers/acpi/acpica/exfldio.c +++ b/drivers/acpi/acpica/exfldio.c @@ -3,7 +3,7 @@ * * Module Name: exfldio - Aml Field I/O * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ @@ -104,7 +104,7 @@ acpi_ex_setup_region(union acpi_operand_object *obj_desc, #ifdef ACPI_UNDER_DEVELOPMENT /* * If the Field access is any_acc, we can now compute the optimal - * access (because we know know the length of the parent region) + * access (because we know the length of the parent region) */ if (!(obj_desc->common.flags & AOPOBJ_DATA_VALID)) { if (ACPI_FAILURE(status)) { diff --git a/drivers/acpi/acpica/exmisc.c b/drivers/acpi/acpica/exmisc.c index ad19f914641b..b4bac8c60a13 100644 --- a/drivers/acpi/acpica/exmisc.c +++ b/drivers/acpi/acpica/exmisc.c @@ -3,7 +3,7 @@ * * Module Name: exmisc - ACPI AML (p-code) execution - specific opcodes * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exmutex.c b/drivers/acpi/acpica/exmutex.c index 6237ae8284b1..e9dcfa1e93eb 100644 --- a/drivers/acpi/acpica/exmutex.c +++ b/drivers/acpi/acpica/exmutex.c @@ -3,7 +3,7 @@ * * Module Name: exmutex - ASL Mutex Acquire/Release functions * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exnames.c b/drivers/acpi/acpica/exnames.c index 5283603d078d..318eb769058d 100644 --- a/drivers/acpi/acpica/exnames.c +++ b/drivers/acpi/acpica/exnames.c @@ -3,7 +3,7 @@ * * Module Name: exnames - interpreter/scanner name load/execute * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exoparg1.c b/drivers/acpi/acpica/exoparg1.c index 44b7c350ed5c..d108a1a86f12 100644 --- a/drivers/acpi/acpica/exoparg1.c +++ b/drivers/acpi/acpica/exoparg1.c @@ -3,7 +3,7 @@ * * Module Name: exoparg1 - AML execution - opcodes with 1 argument * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ @@ -163,6 +163,7 @@ acpi_status acpi_ex_opcode_1A_0T_0R(struct acpi_walk_state *walk_state) return_ACPI_STATUS(status); } +#ifdef _OBSOLETE_CODE /* Was originally used for Load() operator */ /******************************************************************************* * * FUNCTION: acpi_ex_opcode_1A_1T_0R @@ -187,10 +188,12 @@ acpi_status acpi_ex_opcode_1A_1T_0R(struct acpi_walk_state *walk_state) /* Examine the AML opcode */ switch (walk_state->opcode) { +#ifdef _OBSOLETE_CODE case AML_LOAD_OP: status = acpi_ex_load_op(operand[0], operand[1], walk_state); break; +#endif default: /* Unknown opcode */ @@ -204,6 +207,7 @@ cleanup: return_ACPI_STATUS(status); } +#endif /******************************************************************************* * @@ -215,6 +219,8 @@ cleanup: * * DESCRIPTION: Execute opcode with one argument, one target, and a * return value. + * January 2022: Added Load operator, with new ACPI 6.4 + * semantics. * ******************************************************************************/ @@ -239,6 +245,7 @@ acpi_status acpi_ex_opcode_1A_1T_1R(struct acpi_walk_state *walk_state) case AML_FIND_SET_LEFT_BIT_OP: case AML_FIND_SET_RIGHT_BIT_OP: case AML_FROM_BCD_OP: + case AML_LOAD_OP: case AML_TO_BCD_OP: case AML_CONDITIONAL_REF_OF_OP: @@ -338,6 +345,20 @@ acpi_status acpi_ex_opcode_1A_1T_1R(struct acpi_walk_state *walk_state) } break; + case AML_LOAD_OP: /* Result1 = Load (Operand[0], Result1) */ + + return_desc->integer.value = 0; + status = + acpi_ex_load_op(operand[0], return_desc, + walk_state); + if (ACPI_SUCCESS(status)) { + + /* Return -1 (non-zero) indicates success */ + + return_desc->integer.value = 0xFFFFFFFFFFFFFFFF; + } + break; + case AML_TO_BCD_OP: /* to_bcd (Operand, Result) */ return_desc->integer.value = 0; diff --git a/drivers/acpi/acpica/exoparg2.c b/drivers/acpi/acpica/exoparg2.c index 10323ab186da..ebf7c89d52d9 100644 --- a/drivers/acpi/acpica/exoparg2.c +++ b/drivers/acpi/acpica/exoparg2.c @@ -3,7 +3,7 @@ * * Module Name: exoparg2 - AML execution - opcodes with 2 arguments * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exoparg3.c b/drivers/acpi/acpica/exoparg3.c index 140aae009690..4b069bd6bc71 100644 --- a/drivers/acpi/acpica/exoparg3.c +++ b/drivers/acpi/acpica/exoparg3.c @@ -3,7 +3,7 @@ * * Module Name: exoparg3 - AML execution - opcodes with 3 arguments * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exoparg6.c b/drivers/acpi/acpica/exoparg6.c index 2cf9f37a0ba8..2a506ef386cf 100644 --- a/drivers/acpi/acpica/exoparg6.c +++ b/drivers/acpi/acpica/exoparg6.c @@ -3,7 +3,7 @@ * * Module Name: exoparg6 - AML execution - opcodes with 6 arguments * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exprep.c b/drivers/acpi/acpica/exprep.c index d8c55dde191b..08f06797386a 100644 --- a/drivers/acpi/acpica/exprep.c +++ b/drivers/acpi/acpica/exprep.c @@ -3,7 +3,7 @@ * * Module Name: exprep - ACPI AML field prep utilities * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exregion.c b/drivers/acpi/acpica/exregion.c index 48c19908fa4e..4ff35852c0b3 100644 --- a/drivers/acpi/acpica/exregion.c +++ b/drivers/acpi/acpica/exregion.c @@ -3,7 +3,7 @@ * * Module Name: exregion - ACPI default op_region (address space) handlers * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exresnte.c b/drivers/acpi/acpica/exresnte.c index d80b76455c50..b81506d73447 100644 --- a/drivers/acpi/acpica/exresnte.c +++ b/drivers/acpi/acpica/exresnte.c @@ -3,7 +3,7 @@ * * Module Name: exresnte - AML Interpreter object resolution * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exresolv.c b/drivers/acpi/acpica/exresolv.c index fa6a96242835..61ee7fb46006 100644 --- a/drivers/acpi/acpica/exresolv.c +++ b/drivers/acpi/acpica/exresolv.c @@ -3,7 +3,7 @@ * * Module Name: exresolv - AML Interpreter object resolution * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exresop.c b/drivers/acpi/acpica/exresop.c index cbe2c88b1dc2..3342780230af 100644 --- a/drivers/acpi/acpica/exresop.c +++ b/drivers/acpi/acpica/exresop.c @@ -3,7 +3,7 @@ * * Module Name: exresop - AML Interpreter operand/object resolution * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exserial.c b/drivers/acpi/acpica/exserial.c index 10d68a5f76a3..4da20d7845df 100644 --- a/drivers/acpi/acpica/exserial.c +++ b/drivers/acpi/acpica/exserial.c @@ -3,7 +3,7 @@ * * Module Name: exserial - field_unit support for serial address spaces * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exstore.c b/drivers/acpi/acpica/exstore.c index 12f4210ea085..f99e8cf27a6c 100644 --- a/drivers/acpi/acpica/exstore.c +++ b/drivers/acpi/acpica/exstore.c @@ -3,7 +3,7 @@ * * Module Name: exstore - AML Interpreter object store support * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exstoren.c b/drivers/acpi/acpica/exstoren.c index 08469d37e73e..c848b328e760 100644 --- a/drivers/acpi/acpica/exstoren.c +++ b/drivers/acpi/acpica/exstoren.c @@ -4,7 +4,7 @@ * Module Name: exstoren - AML Interpreter object store support, * Store to Node (namespace object) * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exstorob.c b/drivers/acpi/acpica/exstorob.c index a82628683329..45c757bbf9a9 100644 --- a/drivers/acpi/acpica/exstorob.c +++ b/drivers/acpi/acpica/exstorob.c @@ -3,7 +3,7 @@ * * Module Name: exstorob - AML object store support, store to object * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exsystem.c b/drivers/acpi/acpica/exsystem.c index 1281c07112de..7b5470f404f3 100644 --- a/drivers/acpi/acpica/exsystem.c +++ b/drivers/acpi/acpica/exsystem.c @@ -3,7 +3,7 @@ * * Module Name: exsystem - Interface to OS services * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ @@ -107,7 +107,7 @@ acpi_status acpi_ex_system_wait_mutex(acpi_mutex mutex, u16 timeout) * * FUNCTION: acpi_ex_system_do_stall * - * PARAMETERS: how_long - The amount of time to stall, + * PARAMETERS: how_long_us - The amount of time to stall, * in microseconds * * RETURN: Status @@ -120,24 +120,29 @@ acpi_status acpi_ex_system_wait_mutex(acpi_mutex mutex, u16 timeout) * ******************************************************************************/ -acpi_status acpi_ex_system_do_stall(u32 how_long) +acpi_status acpi_ex_system_do_stall(u32 how_long_us) { acpi_status status = AE_OK; ACPI_FUNCTION_ENTRY(); - if (how_long > 255) { /* 255 microseconds */ + if (how_long_us > 255) { /* - * Longer than 255 usec, this is an error + * Longer than 255 microseconds, this is an error * * (ACPI specifies 100 usec as max, but this gives some slack in * order to support existing BIOSs) */ ACPI_ERROR((AE_INFO, - "Time parameter is too large (%u)", how_long)); + "Time parameter is too large (%u)", how_long_us)); status = AE_AML_OPERAND_VALUE; } else { - acpi_os_stall(how_long); + if (how_long_us > 100) { + ACPI_WARNING((AE_INFO, + "Time parameter %u us > 100 us violating ACPI spec, please fix the firmware.", + how_long_us)); + } + acpi_os_stall(how_long_us); } return (status); @@ -147,7 +152,7 @@ acpi_status acpi_ex_system_do_stall(u32 how_long) * * FUNCTION: acpi_ex_system_do_sleep * - * PARAMETERS: how_long - The amount of time to sleep, + * PARAMETERS: how_long_ms - The amount of time to sleep, * in milliseconds * * RETURN: None @@ -156,7 +161,7 @@ acpi_status acpi_ex_system_do_stall(u32 how_long) * ******************************************************************************/ -acpi_status acpi_ex_system_do_sleep(u64 how_long) +acpi_status acpi_ex_system_do_sleep(u64 how_long_ms) { ACPI_FUNCTION_ENTRY(); @@ -168,11 +173,11 @@ acpi_status acpi_ex_system_do_sleep(u64 how_long) * For compatibility with other ACPI implementations and to prevent * accidental deep sleeps, limit the sleep time to something reasonable. */ - if (how_long > ACPI_MAX_SLEEP) { - how_long = ACPI_MAX_SLEEP; + if (how_long_ms > ACPI_MAX_SLEEP) { + how_long_ms = ACPI_MAX_SLEEP; } - acpi_os_sleep(how_long); + acpi_os_sleep(how_long_ms); /* And now we must get the interpreter again */ diff --git a/drivers/acpi/acpica/extrace.c b/drivers/acpi/acpica/extrace.c index 8846f483fb02..b570d7a7e134 100644 --- a/drivers/acpi/acpica/extrace.c +++ b/drivers/acpi/acpica/extrace.c @@ -3,7 +3,7 @@ * * Module Name: extrace - Support for interpreter execution tracing * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exutils.c b/drivers/acpi/acpica/exutils.c index 4d41a866f633..87f01ce1c1aa 100644 --- a/drivers/acpi/acpica/exutils.c +++ b/drivers/acpi/acpica/exutils.c @@ -3,7 +3,7 @@ * * Module Name: exutils - interpreter/scanner utilities * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/hwacpi.c b/drivers/acpi/acpica/hwacpi.c index 96f55f079988..2f1c2fc8bd2a 100644 --- a/drivers/acpi/acpica/hwacpi.c +++ b/drivers/acpi/acpica/hwacpi.c @@ -3,7 +3,7 @@ * * Module Name: hwacpi - ACPI Hardware Initialization/Mode Interface * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/hwesleep.c b/drivers/acpi/acpica/hwesleep.c index 7ee2939c08cd..d8597e052912 100644 --- a/drivers/acpi/acpica/hwesleep.c +++ b/drivers/acpi/acpica/hwesleep.c @@ -4,7 +4,7 @@ * Name: hwesleep.c - ACPI Hardware Sleep/Wake Support functions for the * extended FADT-V5 sleep registers. * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/hwgpe.c b/drivers/acpi/acpica/hwgpe.c index 0770aa176cd5..13d54a48e6e9 100644 --- a/drivers/acpi/acpica/hwgpe.c +++ b/drivers/acpi/acpica/hwgpe.c @@ -3,7 +3,7 @@ * * Module Name: hwgpe - Low level GPE enable/disable/clear functions * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/hwregs.c b/drivers/acpi/acpica/hwregs.c index 69603ba52a3a..f62d5d024205 100644 --- a/drivers/acpi/acpica/hwregs.c +++ b/drivers/acpi/acpica/hwregs.c @@ -446,7 +446,7 @@ struct acpi_bit_register_info *acpi_hw_get_bit_register_info(u32 register_id) * RETURN: Status * * DESCRIPTION: Write the PM1 A/B control registers. These registers are - * different than than the PM1 A/B status and enable registers + * different than the PM1 A/B status and enable registers * in that different values can be written to the A/B registers. * Most notably, the SLP_TYP bits can be different, as per the * values returned from the _Sx predefined methods. diff --git a/drivers/acpi/acpica/hwsleep.c b/drivers/acpi/acpica/hwsleep.c index 5efa3d8e483e..bd936476dda9 100644 --- a/drivers/acpi/acpica/hwsleep.c +++ b/drivers/acpi/acpica/hwsleep.c @@ -4,7 +4,7 @@ * Name: hwsleep.c - ACPI Hardware Sleep/Wake Support functions for the * original/legacy sleep/PM registers. * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/hwtimer.c b/drivers/acpi/acpica/hwtimer.c index 63deadde9f48..46f3ae03ab99 100644 --- a/drivers/acpi/acpica/hwtimer.c +++ b/drivers/acpi/acpica/hwtimer.c @@ -3,7 +3,7 @@ * * Name: hwtimer.c - ACPI Power Management Timer Interface * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/hwvalid.c b/drivers/acpi/acpica/hwvalid.c index e15badf4077a..915b26448d2c 100644 --- a/drivers/acpi/acpica/hwvalid.c +++ b/drivers/acpi/acpica/hwvalid.c @@ -3,7 +3,7 @@ * * Module Name: hwvalid - I/O request validation * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/hwxface.c b/drivers/acpi/acpica/hwxface.c index fb27aaad0dee..55d9b897e70f 100644 --- a/drivers/acpi/acpica/hwxface.c +++ b/drivers/acpi/acpica/hwxface.c @@ -3,7 +3,7 @@ * * Module Name: hwxface - Public ACPICA hardware interfaces * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/hwxfsleep.c b/drivers/acpi/acpica/hwxfsleep.c index ba77598ee43e..aff51ceea02c 100644 --- a/drivers/acpi/acpica/hwxfsleep.c +++ b/drivers/acpi/acpica/hwxfsleep.c @@ -3,7 +3,7 @@ * * Name: hwxfsleep.c - ACPI Hardware Sleep/Wake External Interfaces * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/nsarguments.c b/drivers/acpi/acpica/nsarguments.c index c8a2747005c5..22586b90e532 100644 --- a/drivers/acpi/acpica/nsarguments.c +++ b/drivers/acpi/acpica/nsarguments.c @@ -3,7 +3,7 @@ * * Module Name: nsarguments - Validation of args for ACPI predefined methods * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/nsconvert.c b/drivers/acpi/acpica/nsconvert.c index 597d0eed23c1..b02555fe38f0 100644 --- a/drivers/acpi/acpica/nsconvert.c +++ b/drivers/acpi/acpica/nsconvert.c @@ -4,7 +4,7 @@ * Module Name: nsconvert - Object conversions for objects returned by * predefined methods * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/nsdump.c b/drivers/acpi/acpica/nsdump.c index 2f66f3ed1810..f154824d4eb6 100644 --- a/drivers/acpi/acpica/nsdump.c +++ b/drivers/acpi/acpica/nsdump.c @@ -3,7 +3,7 @@ * * Module Name: nsdump - table dumping routines for debug * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/nsdumpdv.c b/drivers/acpi/acpica/nsdumpdv.c index d3dc6761bcdd..b9a88b7b518b 100644 --- a/drivers/acpi/acpica/nsdumpdv.c +++ b/drivers/acpi/acpica/nsdumpdv.c @@ -3,7 +3,7 @@ * * Module Name: nsdump - table dumping routines for debug * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/nsinit.c b/drivers/acpi/acpica/nsinit.c index 4db81f8ba29b..3e6207ad18d8 100644 --- a/drivers/acpi/acpica/nsinit.c +++ b/drivers/acpi/acpica/nsinit.c @@ -3,7 +3,7 @@ * * Module Name: nsinit - namespace initialization * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/nsload.c b/drivers/acpi/acpica/nsload.c index 7d77956ed790..880260a30c0c 100644 --- a/drivers/acpi/acpica/nsload.c +++ b/drivers/acpi/acpica/nsload.c @@ -3,7 +3,7 @@ * * Module Name: nsload - namespace loading/expanding/contracting procedures * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/nsparse.c b/drivers/acpi/acpica/nsparse.c index 778f80e624be..4b893676ab5c 100644 --- a/drivers/acpi/acpica/nsparse.c +++ b/drivers/acpi/acpica/nsparse.c @@ -3,7 +3,7 @@ * * Module Name: nsparse - namespace interface to AML parser * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/nspredef.c b/drivers/acpi/acpica/nspredef.c index e4e5f32da7dc..c0db6690bb32 100644 --- a/drivers/acpi/acpica/nspredef.c +++ b/drivers/acpi/acpica/nspredef.c @@ -3,7 +3,7 @@ * * Module Name: nspredef - Validation of ACPI predefined methods and objects * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/nsprepkg.c b/drivers/acpi/acpica/nsprepkg.c index 6742b50836f7..82932c9a774b 100644 --- a/drivers/acpi/acpica/nsprepkg.c +++ b/drivers/acpi/acpica/nsprepkg.c @@ -3,7 +3,7 @@ * * Module Name: nsprepkg - Validation of package objects for predefined names * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/nsrepair.c b/drivers/acpi/acpica/nsrepair.c index 499067daa22c..367fcd201f96 100644 --- a/drivers/acpi/acpica/nsrepair.c +++ b/drivers/acpi/acpica/nsrepair.c @@ -3,7 +3,7 @@ * * Module Name: nsrepair - Repair for objects returned by predefined methods * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/nsrepair2.c b/drivers/acpi/acpica/nsrepair2.c index 14b71b41e845..dd533c887e3a 100644 --- a/drivers/acpi/acpica/nsrepair2.c +++ b/drivers/acpi/acpica/nsrepair2.c @@ -4,7 +4,7 @@ * Module Name: nsrepair2 - Repair for objects returned by specific * predefined methods * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/nsutils.c b/drivers/acpi/acpica/nsutils.c index 83d0f276da4d..ef531b145add 100644 --- a/drivers/acpi/acpica/nsutils.c +++ b/drivers/acpi/acpica/nsutils.c @@ -4,7 +4,7 @@ * Module Name: nsutils - Utilities for accessing ACPI namespace, accessing * parents and siblings and Scope manipulation * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/nswalk.c b/drivers/acpi/acpica/nswalk.c index e7c30ce06e18..82a0dae349e2 100644 --- a/drivers/acpi/acpica/nswalk.c +++ b/drivers/acpi/acpica/nswalk.c @@ -3,7 +3,7 @@ * * Module Name: nswalk - Functions for walking the ACPI namespace * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/nsxfname.c b/drivers/acpi/acpica/nsxfname.c index 03487546da5a..b2cfdfef3194 100644 --- a/drivers/acpi/acpica/nsxfname.c +++ b/drivers/acpi/acpica/nsxfname.c @@ -4,7 +4,7 @@ * Module Name: nsxfname - Public interfaces to the ACPI subsystem * ACPI Namespace oriented interfaces * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/psargs.c b/drivers/acpi/acpica/psargs.c index b9ff535aa02e..f7ec5606098c 100644 --- a/drivers/acpi/acpica/psargs.c +++ b/drivers/acpi/acpica/psargs.c @@ -3,7 +3,7 @@ * * Module Name: psargs - Parse AML opcode arguments * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/psloop.c b/drivers/acpi/acpica/psloop.c index 4b51dd939f29..840512fa9fc6 100644 --- a/drivers/acpi/acpica/psloop.c +++ b/drivers/acpi/acpica/psloop.c @@ -3,7 +3,7 @@ * * Module Name: psloop - Main AML parse loop * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/psobject.c b/drivers/acpi/acpica/psobject.c index e4420cd6d281..bca249e67c6b 100644 --- a/drivers/acpi/acpica/psobject.c +++ b/drivers/acpi/acpica/psobject.c @@ -3,7 +3,7 @@ * * Module Name: psobject - Support for parse objects * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/psopcode.c b/drivers/acpi/acpica/psopcode.c index 3e80eb1a5f35..bef69e87a0a2 100644 --- a/drivers/acpi/acpica/psopcode.c +++ b/drivers/acpi/acpica/psopcode.c @@ -3,7 +3,7 @@ * * Module Name: psopcode - Parser/Interpreter opcode information table * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ @@ -408,8 +408,8 @@ const struct acpi_opcode_info acpi_gbl_aml_op_info[AML_NUM_OPCODES] = { AML_HAS_ARGS | AML_NSOBJECT | AML_NSNODE | AML_DEFER | AML_FIELD | AML_CREATE), /* 4A */ ACPI_OP("Load", ARGP_LOAD_OP, ARGI_LOAD_OP, ACPI_TYPE_ANY, - AML_CLASS_EXECUTE, AML_TYPE_EXEC_1A_1T_0R, - AML_FLAGS_EXEC_1A_1T_0R), + AML_CLASS_EXECUTE, AML_TYPE_EXEC_1A_1T_1R, + AML_FLAGS_EXEC_1A_1T_1R), /* 4B */ ACPI_OP("Stall", ARGP_STALL_OP, ARGI_STALL_OP, ACPI_TYPE_ANY, AML_CLASS_EXECUTE, AML_TYPE_EXEC_1A_0T_0R, AML_FLAGS_EXEC_1A_0T_0R), diff --git a/drivers/acpi/acpica/psopinfo.c b/drivers/acpi/acpica/psopinfo.c index 476b00a121f3..f10afe699ad7 100644 --- a/drivers/acpi/acpica/psopinfo.c +++ b/drivers/acpi/acpica/psopinfo.c @@ -3,7 +3,7 @@ * * Module Name: psopinfo - AML opcode information functions and dispatch tables * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/psparse.c b/drivers/acpi/acpica/psparse.c index 7eb7a81619a3..ba93f359760a 100644 --- a/drivers/acpi/acpica/psparse.c +++ b/drivers/acpi/acpica/psparse.c @@ -3,7 +3,7 @@ * * Module Name: psparse - Parser top level AML parse routines * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/psscope.c b/drivers/acpi/acpica/psscope.c index 3f2eada44942..400f001631ea 100644 --- a/drivers/acpi/acpica/psscope.c +++ b/drivers/acpi/acpica/psscope.c @@ -3,7 +3,7 @@ * * Module Name: psscope - Parser scope stack management routines * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/pstree.c b/drivers/acpi/acpica/pstree.c index ffb2a7bfc6d7..3012a9342367 100644 --- a/drivers/acpi/acpica/pstree.c +++ b/drivers/acpi/acpica/pstree.c @@ -3,7 +3,7 @@ * * Module Name: pstree - Parser op tree manipulation/traversal/search * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/psutils.c b/drivers/acpi/acpica/psutils.c index e6596051d548..49b39aeded12 100644 --- a/drivers/acpi/acpica/psutils.c +++ b/drivers/acpi/acpica/psutils.c @@ -3,7 +3,7 @@ * * Module Name: psutils - Parser miscellaneous utilities (Parser only) * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/pswalk.c b/drivers/acpi/acpica/pswalk.c index 7018a789debc..7735a01dab90 100644 --- a/drivers/acpi/acpica/pswalk.c +++ b/drivers/acpi/acpica/pswalk.c @@ -3,7 +3,7 @@ * * Module Name: pswalk - Parser routines to walk parsed op tree(s) * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/psxface.c b/drivers/acpi/acpica/psxface.c index fd0f28c7af1e..a6509aeb2955 100644 --- a/drivers/acpi/acpica/psxface.c +++ b/drivers/acpi/acpica/psxface.c @@ -3,7 +3,7 @@ * * Module Name: psxface - Parser external interfaces * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/tbdata.c b/drivers/acpi/acpica/tbdata.c index 20360a9db482..a7642b34ce48 100644 --- a/drivers/acpi/acpica/tbdata.c +++ b/drivers/acpi/acpica/tbdata.c @@ -3,7 +3,7 @@ * * Module Name: tbdata - Table manager data structure functions * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/tbfadt.c b/drivers/acpi/acpica/tbfadt.c index 047bd094ba68..31d7ea84a360 100644 --- a/drivers/acpi/acpica/tbfadt.c +++ b/drivers/acpi/acpica/tbfadt.c @@ -3,7 +3,7 @@ * * Module Name: tbfadt - FADT table utilities * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/tbfind.c b/drivers/acpi/acpica/tbfind.c index 2c2c2b1f5a28..c31a5ddb0ffd 100644 --- a/drivers/acpi/acpica/tbfind.c +++ b/drivers/acpi/acpica/tbfind.c @@ -3,7 +3,7 @@ * * Module Name: tbfind - find table * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/tbinstal.c b/drivers/acpi/acpica/tbinstal.c index 5649f493a1ed..499efcaf798d 100644 --- a/drivers/acpi/acpica/tbinstal.c +++ b/drivers/acpi/acpica/tbinstal.c @@ -3,7 +3,7 @@ * * Module Name: tbinstal - ACPI table installation and removal * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/tbprint.c b/drivers/acpi/acpica/tbprint.c index 4dac16bd63d3..595547db28c0 100644 --- a/drivers/acpi/acpica/tbprint.c +++ b/drivers/acpi/acpica/tbprint.c @@ -3,7 +3,7 @@ * * Module Name: tbprint - Table output utilities * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/tbutils.c b/drivers/acpi/acpica/tbutils.c index 5e8d50a4b6a9..633a823be65f 100644 --- a/drivers/acpi/acpica/tbutils.c +++ b/drivers/acpi/acpica/tbutils.c @@ -3,7 +3,7 @@ * * Module Name: tbutils - ACPI Table utilities * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/tbxface.c b/drivers/acpi/acpica/tbxface.c index e6f51fedaf1a..37da09dca940 100644 --- a/drivers/acpi/acpica/tbxface.c +++ b/drivers/acpi/acpica/tbxface.c @@ -3,7 +3,7 @@ * * Module Name: tbxface - ACPI table-oriented external interfaces * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/tbxfload.c b/drivers/acpi/acpica/tbxfload.c index 87356d9ad613..258796e02be1 100644 --- a/drivers/acpi/acpica/tbxfload.c +++ b/drivers/acpi/acpica/tbxfload.c @@ -3,7 +3,7 @@ * * Module Name: tbxfload - Table load/unload external interfaces * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/tbxfroot.c b/drivers/acpi/acpica/tbxfroot.c index 9fec3df6c3ba..3d09e3f6bd43 100644 --- a/drivers/acpi/acpica/tbxfroot.c +++ b/drivers/acpi/acpica/tbxfroot.c @@ -3,7 +3,7 @@ * * Module Name: tbxfroot - Find the root ACPI table (RSDT) * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/utaddress.c b/drivers/acpi/acpica/utaddress.c index 7001f4b113f1..915321806cd7 100644 --- a/drivers/acpi/acpica/utaddress.c +++ b/drivers/acpi/acpica/utaddress.c @@ -3,7 +3,7 @@ * * Module Name: utaddress - op_region address range check * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/utalloc.c b/drivers/acpi/acpica/utalloc.c index 796fd9b33a7d..2bab6017d827 100644 --- a/drivers/acpi/acpica/utalloc.c +++ b/drivers/acpi/acpica/utalloc.c @@ -3,7 +3,7 @@ * * Module Name: utalloc - local memory allocation routines * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/utascii.c b/drivers/acpi/acpica/utascii.c index e1b55575d5fb..72fb7e9ec485 100644 --- a/drivers/acpi/acpica/utascii.c +++ b/drivers/acpi/acpica/utascii.c @@ -3,7 +3,7 @@ * * Module Name: utascii - Utility ascii functions * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/utbuffer.c b/drivers/acpi/acpica/utbuffer.c index 8ab90f78825b..59c4050b8e91 100644 --- a/drivers/acpi/acpica/utbuffer.c +++ b/drivers/acpi/acpica/utbuffer.c @@ -3,7 +3,7 @@ * * Module Name: utbuffer - Buffer dump routines * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/utcache.c b/drivers/acpi/acpica/utcache.c index 814145019f95..5425968dd2a8 100644 --- a/drivers/acpi/acpica/utcache.c +++ b/drivers/acpi/acpica/utcache.c @@ -3,7 +3,7 @@ * * Module Name: utcache - local cache allocation routines * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/utcopy.c b/drivers/acpi/acpica/utcopy.c index d9877153f400..400b9e15a709 100644 --- a/drivers/acpi/acpica/utcopy.c +++ b/drivers/acpi/acpica/utcopy.c @@ -3,7 +3,7 @@ * * Module Name: utcopy - Internal to external object translation utilities * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/utdebug.c b/drivers/acpi/acpica/utdebug.c index 09245945f319..64ed546cf19c 100644 --- a/drivers/acpi/acpica/utdebug.c +++ b/drivers/acpi/acpica/utdebug.c @@ -3,7 +3,7 @@ * * Module Name: utdebug - Debug print/trace routines * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/utdecode.c b/drivers/acpi/acpica/utdecode.c index bcd3871079d7..3176393a729d 100644 --- a/drivers/acpi/acpica/utdecode.c +++ b/drivers/acpi/acpica/utdecode.c @@ -3,7 +3,7 @@ * * Module Name: utdecode - Utility decoding routines (value-to-string) * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/uteval.c b/drivers/acpi/acpica/uteval.c index d2503920c620..df20d46ed8b7 100644 --- a/drivers/acpi/acpica/uteval.c +++ b/drivers/acpi/acpica/uteval.c @@ -3,7 +3,7 @@ * * Module Name: uteval - Object evaluation * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/utglobal.c b/drivers/acpi/acpica/utglobal.c index 59a48371a7bc..cda6e16dddf7 100644 --- a/drivers/acpi/acpica/utglobal.c +++ b/drivers/acpi/acpica/utglobal.c @@ -3,7 +3,7 @@ * * Module Name: utglobal - Global variables for the ACPI subsystem * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/uthex.c b/drivers/acpi/acpica/uthex.c index b1e94c094f9a..c811ee2a8160 100644 --- a/drivers/acpi/acpica/uthex.c +++ b/drivers/acpi/acpica/uthex.c @@ -3,7 +3,7 @@ * * Module Name: uthex -- Hex/ASCII support functions * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/utids.c b/drivers/acpi/acpica/utids.c index 08e9f316cbde..b6caab49f1bd 100644 --- a/drivers/acpi/acpica/utids.c +++ b/drivers/acpi/acpica/utids.c @@ -3,7 +3,7 @@ * * Module Name: utids - support for device Ids - HID, UID, CID, SUB, CLS * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/utinit.c b/drivers/acpi/acpica/utinit.c index 7b606a1e6986..18177e4f26f7 100644 --- a/drivers/acpi/acpica/utinit.c +++ b/drivers/acpi/acpica/utinit.c @@ -3,7 +3,7 @@ * * Module Name: utinit - Common ACPI subsystem initialization * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/utlock.c b/drivers/acpi/acpica/utlock.c index 923dd15e7a16..84abdbf5cfca 100644 --- a/drivers/acpi/acpica/utlock.c +++ b/drivers/acpi/acpica/utlock.c @@ -3,7 +3,7 @@ * * Module Name: utlock - Reader/Writer lock interfaces * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/utobject.c b/drivers/acpi/acpica/utobject.c index 84a210b49e3a..d3667bfff401 100644 --- a/drivers/acpi/acpica/utobject.c +++ b/drivers/acpi/acpica/utobject.c @@ -3,7 +3,7 @@ * * Module Name: utobject - ACPI object create/delete/size/cache routines * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/utosi.c b/drivers/acpi/acpica/utosi.c index 8afa1ccaf12e..b8ab0a3cb5b9 100644 --- a/drivers/acpi/acpica/utosi.c +++ b/drivers/acpi/acpica/utosi.c @@ -3,7 +3,7 @@ * * Module Name: utosi - Support for the _OSI predefined control method * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ @@ -74,6 +74,7 @@ static struct acpi_interface_info acpi_default_supported_interfaces[] = { {"Windows 2018.2", NULL, 0, ACPI_OSI_WIN_10_RS5}, /* Windows 10 version 1809 - Added 11/2018 */ {"Windows 2019", NULL, 0, ACPI_OSI_WIN_10_19H1}, /* Windows 10 version 1903 - Added 08/2019 */ {"Windows 2020", NULL, 0, ACPI_OSI_WIN_10_20H1}, /* Windows 10 version 2004 - Added 08/2021 */ + {"Windows 2021", NULL, 0, ACPI_OSI_WIN_11}, /* Windows 11 - Added 01/2022 */ /* Feature Group Strings */ diff --git a/drivers/acpi/acpica/utpredef.c b/drivers/acpi/acpica/utpredef.c index a6f87a88c30e..2524f013be7a 100644 --- a/drivers/acpi/acpica/utpredef.c +++ b/drivers/acpi/acpica/utpredef.c @@ -3,7 +3,7 @@ * * Module Name: utpredef - support functions for predefined names * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/utprint.c b/drivers/acpi/acpica/utprint.c index 05426596d1f4..d5aa2109847f 100644 --- a/drivers/acpi/acpica/utprint.c +++ b/drivers/acpi/acpica/utprint.c @@ -3,7 +3,7 @@ * * Module Name: utprint - Formatted printing routines * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/uttrack.c b/drivers/acpi/acpica/uttrack.c index 2ce85fcfeb5b..a06988ac409d 100644 --- a/drivers/acpi/acpica/uttrack.c +++ b/drivers/acpi/acpica/uttrack.c @@ -3,7 +3,7 @@ * * Module Name: uttrack - Memory allocation tracking routines (debug only) * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/utuuid.c b/drivers/acpi/acpica/utuuid.c index dca9061518ab..e24bc670b53e 100644 --- a/drivers/acpi/acpica/utuuid.c +++ b/drivers/acpi/acpica/utuuid.c @@ -3,7 +3,7 @@ * * Module Name: utuuid -- UUID support functions * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/utxface.c b/drivers/acpi/acpica/utxface.c index 3285c1a92e40..86e76b443da7 100644 --- a/drivers/acpi/acpica/utxface.c +++ b/drivers/acpi/acpica/utxface.c @@ -3,7 +3,7 @@ * * Module Name: utxface - External interfaces, miscellaneous utility functions * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/utxfinit.c b/drivers/acpi/acpica/utxfinit.c index 91016366de1d..f2acec3a0ee3 100644 --- a/drivers/acpi/acpica/utxfinit.c +++ b/drivers/acpi/acpica/utxfinit.c @@ -3,7 +3,7 @@ * * Module Name: utxfinit - External interfaces for ACPICA initialization * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/apei/einj.c b/drivers/acpi/apei/einj.c index 95cc2a9f3e05..d4326ec12d29 100644 --- a/drivers/acpi/apei/einj.c +++ b/drivers/acpi/apei/einj.c @@ -549,6 +549,9 @@ static int einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2, !arch_is_platform_page(base_addr))) return -EINVAL; + if (is_zero_pfn(base_addr >> PAGE_SHIFT)) + return -EADDRINUSE; + inject: mutex_lock(&einj_mutex); rc = __einj_error_inject(type, flags, param1, param2, param3, param4); diff --git a/drivers/acpi/apei/erst-dbg.c b/drivers/acpi/apei/erst-dbg.c index c740f0faad39..8bc71cdc2270 100644 --- a/drivers/acpi/apei/erst-dbg.c +++ b/drivers/acpi/apei/erst-dbg.c @@ -111,7 +111,8 @@ retry_next: goto out; } retry: - rc = len = erst_read(id, erst_dbg_buf, erst_dbg_buf_len); + rc = len = erst_read_record(id, erst_dbg_buf, erst_dbg_buf_len, + erst_dbg_buf_len, NULL); /* The record may be cleared by others, try read next record */ if (rc == -ENOENT) goto retry_next; diff --git a/drivers/acpi/apei/erst.c b/drivers/acpi/apei/erst.c index 698d67cee052..31b077eedb58 100644 --- a/drivers/acpi/apei/erst.c +++ b/drivers/acpi/apei/erst.c @@ -856,6 +856,74 @@ ssize_t erst_read(u64 record_id, struct cper_record_header *record, } EXPORT_SYMBOL_GPL(erst_read); +static void erst_clear_cache(u64 record_id) +{ + int i; + u64 *entries; + + mutex_lock(&erst_record_id_cache.lock); + + entries = erst_record_id_cache.entries; + for (i = 0; i < erst_record_id_cache.len; i++) { + if (entries[i] == record_id) + entries[i] = APEI_ERST_INVALID_RECORD_ID; + } + __erst_record_id_cache_compact(); + + mutex_unlock(&erst_record_id_cache.lock); +} + +ssize_t erst_read_record(u64 record_id, struct cper_record_header *record, + size_t buflen, size_t recordlen, const guid_t *creatorid) +{ + ssize_t len; + + /* + * if creatorid is NULL, read any record for erst-dbg module + */ + if (creatorid == NULL) { + len = erst_read(record_id, record, buflen); + if (len == -ENOENT) + erst_clear_cache(record_id); + + return len; + } + + len = erst_read(record_id, record, buflen); + /* + * if erst_read return value is -ENOENT skip to next record_id, + * and clear the record_id cache. + */ + if (len == -ENOENT) { + erst_clear_cache(record_id); + goto out; + } + + if (len < 0) + goto out; + + /* + * if erst_read return value is less than record head length, + * consider it as -EIO, and clear the record_id cache. + */ + if (len < recordlen) { + len = -EIO; + erst_clear_cache(record_id); + goto out; + } + + /* + * if creatorid is not wanted, consider it as not found, + * for skipping to next record_id. + */ + if (!guid_equal(&record->creator_id, creatorid)) + len = -ENOENT; + +out: + return len; +} +EXPORT_SYMBOL_GPL(erst_read_record); + int erst_clear(u64 record_id) { int rc, i; @@ -996,16 +1064,13 @@ skip: goto out; } - len = erst_read(record_id, &rcd->hdr, rcd_len); + len = erst_read_record(record_id, &rcd->hdr, rcd_len, sizeof(*rcd), + &CPER_CREATOR_PSTORE); /* The record may be cleared by others, try read next record */ if (len == -ENOENT) goto skip; - else if (len < 0 || len < sizeof(*rcd)) { - rc = -EIO; + else if (len < 0) goto out; - } - if (!guid_equal(&rcd->hdr.creator_id, &CPER_CREATOR_PSTORE)) - goto skip; record->buf = kmalloc(len, GFP_KERNEL); if (record->buf == NULL) { diff --git a/drivers/acpi/arm64/agdi.c b/drivers/acpi/arm64/agdi.c index 4df337d545b7..cf31abd0ed1b 100644 --- a/drivers/acpi/arm64/agdi.c +++ b/drivers/acpi/arm64/agdi.c @@ -9,6 +9,7 @@ #define pr_fmt(fmt) "ACPI: AGDI: " fmt #include <linux/acpi.h> +#include <linux/acpi_agdi.h> #include <linux/arm_sdei.h> #include <linux/io.h> #include <linux/kernel.h> diff --git a/drivers/acpi/bgrt.c b/drivers/acpi/bgrt.c index 02d208732f9a..e4fb9e225ddf 100644 --- a/drivers/acpi/bgrt.c +++ b/drivers/acpi/bgrt.c @@ -21,7 +21,7 @@ static struct kobject *bgrt_kobj; { \ return sysfs_emit(buf, "%d\n", bgrt_tab._member); \ } \ - struct kobj_attribute bgrt_attr_##_name = __ATTR_RO(_name) + static struct kobj_attribute bgrt_attr_##_name = __ATTR_RO(_name) BGRT_SHOW(version, version); BGRT_SHOW(status, status); diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c index 3e58b613a2c4..b67d2ee77cd1 100644 --- a/drivers/acpi/bus.c +++ b/drivers/acpi/bus.c @@ -279,6 +279,20 @@ bool osc_pc_lpi_support_confirmed; EXPORT_SYMBOL_GPL(osc_pc_lpi_support_confirmed); /* + * ACPI 6.2 Section 6.2.11.2 'Platform-Wide OSPM Capabilities': + * Starting with ACPI Specification 6.2, all _CPC registers can be in + * PCC, System Memory, System IO, or Functional Fixed Hardware address + * spaces. OSPM support for this more flexible register space scheme is + * indicated by the “Flexible Address Space for CPPC Registers” _OSC bit. + * + * Otherwise (cf ACPI 6.1, s8.4.7.1.1.X), _CPC registers must be in: + * - PCC or Functional Fixed Hardware address space if defined + * - SystemMemory address space (NULL register) if not defined + */ +bool osc_cpc_flexible_adr_space_confirmed; +EXPORT_SYMBOL_GPL(osc_cpc_flexible_adr_space_confirmed); + +/* * ACPI 6.4 Operating System Capabilities for USB. */ bool osc_sb_native_usb4_support_confirmed; @@ -315,12 +329,15 @@ static void acpi_bus_osc_negotiate_platform_control(void) #endif #ifdef CONFIG_X86 capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_GENERIC_INITIATOR_SUPPORT; - if (boot_cpu_has(X86_FEATURE_HWP)) { - capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_CPC_SUPPORT; - capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_CPCV2_SUPPORT; - } #endif +#ifdef CONFIG_ACPI_CPPC_LIB + capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_CPC_SUPPORT; + capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_CPCV2_SUPPORT; +#endif + + capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_CPC_FLEXIBLE_ADR_SPACE; + if (IS_ENABLED(CONFIG_SCHED_MC_PRIO)) capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_CPC_DIVERSE_HIGH_SUPPORT; @@ -341,10 +358,9 @@ static void acpi_bus_osc_negotiate_platform_control(void) return; } -#ifdef CONFIG_X86 - if (boot_cpu_has(X86_FEATURE_HWP)) - osc_sb_cppc_not_supported = !(capbuf_ret[OSC_SUPPORT_DWORD] & - (OSC_SB_CPC_SUPPORT | OSC_SB_CPCV2_SUPPORT)); +#ifdef CONFIG_ACPI_CPPC_LIB + osc_sb_cppc_not_supported = !(capbuf_ret[OSC_SUPPORT_DWORD] & + (OSC_SB_CPC_SUPPORT | OSC_SB_CPCV2_SUPPORT)); #endif /* @@ -366,6 +382,8 @@ static void acpi_bus_osc_negotiate_platform_control(void) capbuf_ret[OSC_SUPPORT_DWORD] & OSC_SB_PCLPI_SUPPORT; osc_sb_native_usb4_support_confirmed = capbuf_ret[OSC_SUPPORT_DWORD] & OSC_SB_NATIVE_USB4_SUPPORT; + osc_cpc_flexible_adr_space_confirmed = + capbuf_ret[OSC_SUPPORT_DWORD] & OSC_SB_CPC_FLEXIBLE_ADR_SPACE; } kfree(context.ret.pointer); @@ -1070,6 +1088,32 @@ int acpi_bus_for_each_dev(int (*fn)(struct device *, void *), void *data) } EXPORT_SYMBOL_GPL(acpi_bus_for_each_dev); +struct acpi_dev_walk_context { + int (*fn)(struct acpi_device *, void *); + void *data; +}; + +static int acpi_dev_for_one_check(struct device *dev, void *context) +{ + struct acpi_dev_walk_context *adwc = context; + + if (dev->bus != &acpi_bus_type) + return 0; + + return adwc->fn(to_acpi_device(dev), adwc->data); +} + +int acpi_dev_for_each_child(struct acpi_device *adev, + int (*fn)(struct acpi_device *, void *), void *data) +{ + struct acpi_dev_walk_context adwc = { + .fn = fn, + .data = data, + }; + + return device_for_each_child(&adev->dev, &adwc, acpi_dev_for_one_check); +} + /* -------------------------------------------------------------------------- Initialization/Cleanup -------------------------------------------------------------------------- */ diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c index bc1454789a06..3b299b28a8af 100644 --- a/drivers/acpi/cppc_acpi.c +++ b/drivers/acpi/cppc_acpi.c @@ -100,6 +100,16 @@ static DEFINE_PER_CPU(struct cpc_desc *, cpc_desc_ptr); (cpc)->cpc_entry.reg.space_id == \ ACPI_ADR_SPACE_PLATFORM_COMM) +/* Check if a CPC register is in SystemMemory */ +#define CPC_IN_SYSTEM_MEMORY(cpc) ((cpc)->type == ACPI_TYPE_BUFFER && \ + (cpc)->cpc_entry.reg.space_id == \ + ACPI_ADR_SPACE_SYSTEM_MEMORY) + +/* Check if a CPC register is in SystemIo */ +#define CPC_IN_SYSTEM_IO(cpc) ((cpc)->type == ACPI_TYPE_BUFFER && \ + (cpc)->cpc_entry.reg.space_id == \ + ACPI_ADR_SPACE_SYSTEM_IO) + /* Evaluates to True if reg is a NULL register descriptor */ #define IS_NULL_REG(reg) ((reg)->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY && \ (reg)->address == 0 && \ @@ -424,6 +434,24 @@ bool acpi_cpc_valid(void) } EXPORT_SYMBOL_GPL(acpi_cpc_valid); +bool cppc_allow_fast_switch(void) +{ + struct cpc_register_resource *desired_reg; + struct cpc_desc *cpc_ptr; + int cpu; + + for_each_possible_cpu(cpu) { + cpc_ptr = per_cpu(cpc_desc_ptr, cpu); + desired_reg = &cpc_ptr->cpc_regs[DESIRED_PERF]; + if (!CPC_IN_SYSTEM_MEMORY(desired_reg) && + !CPC_IN_SYSTEM_IO(desired_reg)) + return false; + } + + return true; +} +EXPORT_SYMBOL_GPL(cppc_allow_fast_switch); + /** * acpi_get_psd_map - Map the CPUs in the freq domain of a given cpu * @cpu: Find all CPUs that share a domain with cpu. @@ -736,6 +764,11 @@ int acpi_cppc_processor_probe(struct acpi_processor *pr) if (gas_t->address) { void __iomem *addr; + if (!osc_cpc_flexible_adr_space_confirmed) { + pr_debug("Flexible address space capability not supported\n"); + goto out_free; + } + addr = ioremap(gas_t->address, gas_t->bit_width/8); if (!addr) goto out_free; @@ -758,6 +791,10 @@ int acpi_cppc_processor_probe(struct acpi_processor *pr) gas_t->address); goto out_free; } + if (!osc_cpc_flexible_adr_space_confirmed) { + pr_debug("Flexible address space capability not supported\n"); + goto out_free; + } } else { if (gas_t->space_id != ACPI_ADR_SPACE_FIXED_HARDWARE || !cpc_ffh_supported()) { /* Support only PCC, SystemMemory, SystemIO, and FFH type regs. */ @@ -1447,6 +1484,9 @@ EXPORT_SYMBOL_GPL(cppc_set_perf); * transition latency for performance change requests. The closest we have * is the timing information from the PCCT tables which provides the info * on the number and frequency of PCC commands the platform can handle. + * + * If desired_reg is in the SystemMemory or SystemIo ACPI address space, + * then assume there is no latency. */ unsigned int cppc_get_transition_latency(int cpu_num) { @@ -1472,7 +1512,9 @@ unsigned int cppc_get_transition_latency(int cpu_num) return CPUFREQ_ETERNAL; desired_reg = &cpc_desc->cpc_regs[DESIRED_PERF]; - if (!CPC_IN_PCC(desired_reg)) + if (CPC_IN_SYSTEM_MEMORY(desired_reg) || CPC_IN_SYSTEM_IO(desired_reg)) + return 0; + else if (!CPC_IN_PCC(desired_reg)) return CPUFREQ_ETERNAL; if (pcc_ss_id < 0) diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c index cc6c97e7dcae..130b5f4a50a3 100644 --- a/drivers/acpi/device_pm.c +++ b/drivers/acpi/device_pm.c @@ -10,7 +10,7 @@ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ */ -#define pr_fmt(fmt) "ACPI: PM: " fmt +#define pr_fmt(fmt) "PM: " fmt #include <linux/acpi.h> #include <linux/export.h> @@ -130,8 +130,8 @@ int acpi_device_get_power(struct acpi_device *device, int *state) *state = result; out: - dev_dbg(&device->dev, "Device power state is %s\n", - acpi_power_state_string(*state)); + acpi_handle_debug(device->handle, "Power state: %s\n", + acpi_power_state_string(*state)); return 0; } @@ -173,11 +173,8 @@ int acpi_device_set_power(struct acpi_device *device, int state) /* Make sure this is a valid target state */ /* There is a special case for D0 addressed below. */ - if (state > ACPI_STATE_D0 && state == device->power.state) { - dev_dbg(&device->dev, "Device already in %s\n", - acpi_power_state_string(state)); - return 0; - } + if (state > ACPI_STATE_D0 && state == device->power.state) + goto no_change; if (state == ACPI_STATE_D3_COLD) { /* @@ -189,17 +186,17 @@ int acpi_device_set_power(struct acpi_device *device, int state) if (!device->power.states[ACPI_STATE_D3_COLD].flags.valid) target_state = state; } else if (!device->power.states[state].flags.valid) { - dev_warn(&device->dev, "Power state %s not supported\n", - acpi_power_state_string(state)); + acpi_handle_debug(device->handle, "Power state %s not supported\n", + acpi_power_state_string(state)); return -ENODEV; } - if (!device->power.flags.ignore_parent && - device->parent && (state < device->parent->power.state)) { - dev_warn(&device->dev, - "Cannot transition to power state %s for parent in %s\n", - acpi_power_state_string(state), - acpi_power_state_string(device->parent->power.state)); + if (!device->power.flags.ignore_parent && device->parent && + state < device->parent->power.state) { + acpi_handle_debug(device->handle, + "Cannot transition to %s for parent in %s\n", + acpi_power_state_string(state), + acpi_power_state_string(device->parent->power.state)); return -ENODEV; } @@ -216,9 +213,10 @@ int acpi_device_set_power(struct acpi_device *device, int state) * (deeper) states to higher-power (shallower) states. */ if (state < device->power.state) { - dev_warn(&device->dev, "Cannot transition from %s to %s\n", - acpi_power_state_string(device->power.state), - acpi_power_state_string(state)); + acpi_handle_debug(device->handle, + "Cannot transition from %s to %s\n", + acpi_power_state_string(device->power.state), + acpi_power_state_string(state)); return -ENODEV; } @@ -248,7 +246,7 @@ int acpi_device_set_power(struct acpi_device *device, int state) /* Nothing to do here if _PSC is not present. */ if (!device->power.flags.explicit_get) - return 0; + goto no_change; /* * The power state of the device was set to D0 last @@ -263,23 +261,29 @@ int acpi_device_set_power(struct acpi_device *device, int state) */ result = acpi_dev_pm_explicit_get(device, &psc); if (result || psc == ACPI_STATE_D0) - return 0; + goto no_change; } result = acpi_dev_pm_explicit_set(device, ACPI_STATE_D0); } - end: +end: if (result) { - dev_warn(&device->dev, "Failed to change power state to %s\n", - acpi_power_state_string(target_state)); + acpi_handle_debug(device->handle, + "Failed to change power state to %s\n", + acpi_power_state_string(target_state)); } else { device->power.state = target_state; - dev_dbg(&device->dev, "Power state changed to %s\n", - acpi_power_state_string(target_state)); + acpi_handle_debug(device->handle, "Power state changed to %s\n", + acpi_power_state_string(target_state)); } return result; + +no_change: + acpi_handle_debug(device->handle, "Already in %s\n", + acpi_power_state_string(state)); + return 0; } EXPORT_SYMBOL(acpi_device_set_power); @@ -425,6 +429,33 @@ bool acpi_bus_power_manageable(acpi_handle handle) } EXPORT_SYMBOL(acpi_bus_power_manageable); +static int acpi_power_up_if_adr_present(struct acpi_device *adev, void *not_used) +{ + if (!(adev->flags.power_manageable && adev->pnp.type.bus_address)) + return 0; + + acpi_handle_debug(adev->handle, "Power state: %s\n", + acpi_power_state_string(adev->power.state)); + + if (adev->power.state == ACPI_STATE_D3_COLD) + return acpi_device_set_power(adev, ACPI_STATE_D0); + + return 0; +} + +/** + * acpi_dev_power_up_children_with_adr - Power up childres with valid _ADR + * @adev: Parent ACPI device object. + * + * Change the power states of the direct children of @adev that are in D3cold + * and hold valid _ADR objects to D0 in order to allow bus (e.g. PCI) + * enumeration code to access them. + */ +void acpi_dev_power_up_children_with_adr(struct acpi_device *adev) +{ + acpi_dev_for_each_child(adev, acpi_power_up_if_adr_present, NULL); +} + #ifdef CONFIG_PM static DEFINE_MUTEX(acpi_pm_notifier_lock); static DEFINE_MUTEX(acpi_pm_notifier_install_lock); diff --git a/drivers/acpi/dptf/dptf_power.c b/drivers/acpi/dptf/dptf_power.c index dc1f52a5b3f4..407b89d8a2ce 100644 --- a/drivers/acpi/dptf/dptf_power.c +++ b/drivers/acpi/dptf/dptf_power.c @@ -12,14 +12,12 @@ /* * Presentation of attributes which are defined for INT3407 and INT3532. * They are: - * PMAX : Maximum platform powe + * PMAX : Maximum platform power * PSRC : Platform power source * ARTG : Adapter rating * CTYP : Charger type - * PBSS : Battery steady power * PROP : Rest of worst case platform Power * PBSS : Power Battery Steady State - * PBSS : Power Battery Steady State * RBHF : High Frequency Impedance * VBNL : Instantaneous No-Load Voltage * CMPP : Current Discharge Capability @@ -117,7 +115,7 @@ static const struct attribute_group dptf_battery_attribute_group = { #define POWER_STATE_CHANGED 0x81 #define STEADY_STATE_POWER_CHANGED 0x83 #define POWER_PROP_CHANGE_EVENT 0x84 -#define IMPEDANCED_CHNGED 0x85 +#define IMPEDANCE_CHANGED 0x85 #define VOLTAGE_CURRENT_CHANGED 0x86 static long long dptf_participant_type(acpi_handle handle) @@ -150,6 +148,9 @@ static void dptf_power_notify(acpi_handle handle, u32 event, void *data) case STEADY_STATE_POWER_CHANGED: attr = "max_steady_state_power_mw"; break; + case IMPEDANCE_CHANGED: + attr = "high_freq_impedance_mohm"; + break; case VOLTAGE_CURRENT_CHANGED: attr = "no_load_voltage_mv"; break; diff --git a/drivers/acpi/pci_root.c b/drivers/acpi/pci_root.c index 6f9e75d14808..b3b507f20e87 100644 --- a/drivers/acpi/pci_root.c +++ b/drivers/acpi/pci_root.c @@ -927,6 +927,8 @@ struct pci_bus *acpi_pci_root_create(struct acpi_pci_root *root, host_bridge->preserve_config = 1; ACPI_FREE(obj); + acpi_dev_power_up_children_with_adr(device); + pci_scan_child_bus(bus); pci_set_host_bridge_release(host_bridge, acpi_pci_root_release_info, info); diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c index 32b20efff5f8..e9c84d0ac55b 100644 --- a/drivers/acpi/processor_idle.c +++ b/drivers/acpi/processor_idle.c @@ -21,6 +21,7 @@ #include <linux/cpuidle.h> #include <linux/cpu.h> #include <linux/minmax.h> +#include <linux/perf_event.h> #include <acpi/processor.h> /* @@ -96,11 +97,6 @@ static const struct dmi_system_id processor_power_dmi_table[] = { DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK Computer Inc."), DMI_MATCH(DMI_PRODUCT_NAME,"L8400B series Notebook PC")}, (void *)1}, - /* T40 can not handle C3 idle state */ - { set_max_cstate, "IBM ThinkPad T40", { - DMI_MATCH(DMI_SYS_VENDOR, "IBM"), - DMI_MATCH(DMI_PRODUCT_NAME, "23737CU")}, - (void *)2}, {}, }; @@ -549,6 +545,8 @@ static void wait_for_freeze(void) */ static void __cpuidle acpi_idle_do_entry(struct acpi_processor_cx *cx) { + perf_lopwr_cb(true); + if (cx->entry_method == ACPI_CSTATE_FFH) { /* Call into architectural FFH based C-state */ acpi_processor_ffh_cstate_enter(cx); @@ -559,6 +557,8 @@ static void __cpuidle acpi_idle_do_entry(struct acpi_processor_cx *cx) inb(cx->address); wait_for_freeze(); } + + perf_lopwr_cb(false); } /** @@ -570,8 +570,7 @@ static int acpi_idle_play_dead(struct cpuidle_device *dev, int index) { struct acpi_processor_cx *cx = per_cpu(acpi_cstate[index], dev->cpu); - if (cx->type == ACPI_STATE_C3) - ACPI_FLUSH_CPU_CACHE(); + ACPI_FLUSH_CPU_CACHE(); while (1) { @@ -796,7 +795,8 @@ static int acpi_processor_setup_cstates(struct acpi_processor *pr) if (cx->type == ACPI_STATE_C1 || cx->type == ACPI_STATE_C2 || cx->type == ACPI_STATE_C3) { state->enter_dead = acpi_idle_play_dead; - drv->safe_state_index = count; + if (cx->type != ACPI_STATE_C3) + drv->safe_state_index = count; } /* * Halt-induced C1 is not good for ->enter_s2idle, because it diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c index 12bbfe833609..d3173811614e 100644 --- a/drivers/acpi/property.c +++ b/drivers/acpi/property.c @@ -433,6 +433,16 @@ void acpi_init_properties(struct acpi_device *adev) acpi_extract_apple_properties(adev); } +static void acpi_free_device_properties(struct list_head *list) +{ + struct acpi_device_properties *props, *tmp; + + list_for_each_entry_safe(props, tmp, list, list) { + list_del(&props->list); + kfree(props); + } +} + static void acpi_destroy_nondev_subnodes(struct list_head *list) { struct acpi_data_node *dn, *next; @@ -445,22 +455,18 @@ static void acpi_destroy_nondev_subnodes(struct list_head *list) wait_for_completion(&dn->kobj_done); list_del(&dn->sibling); ACPI_FREE((void *)dn->data.pointer); + acpi_free_device_properties(&dn->data.properties); kfree(dn); } } void acpi_free_properties(struct acpi_device *adev) { - struct acpi_device_properties *props, *tmp; - acpi_destroy_nondev_subnodes(&adev->data.subnodes); ACPI_FREE((void *)adev->data.pointer); adev->data.of_compatible = NULL; adev->data.pointer = NULL; - list_for_each_entry_safe(props, tmp, &adev->data.properties, list) { - list_del(&props->list); - kfree(props); - } + acpi_free_device_properties(&adev->data.properties); } /** @@ -1256,6 +1262,24 @@ static bool acpi_fwnode_device_is_available(const struct fwnode_handle *fwnode) return acpi_device_is_present(to_acpi_device_node(fwnode)); } +static const void * +acpi_fwnode_device_get_match_data(const struct fwnode_handle *fwnode, + const struct device *dev) +{ + return acpi_device_get_match_data(dev); +} + +static bool acpi_fwnode_device_dma_supported(const struct fwnode_handle *fwnode) +{ + return acpi_dma_supported(to_acpi_device_node(fwnode)); +} + +static enum dev_dma_attr +acpi_fwnode_device_get_dma_attr(const struct fwnode_handle *fwnode) +{ + return acpi_get_dma_attr(to_acpi_device_node(fwnode)); +} + static bool acpi_fwnode_property_present(const struct fwnode_handle *fwnode, const char *propname) { @@ -1376,17 +1400,26 @@ static int acpi_fwnode_graph_parse_endpoint(const struct fwnode_handle *fwnode, return 0; } -static const void * -acpi_fwnode_device_get_match_data(const struct fwnode_handle *fwnode, - const struct device *dev) +static int acpi_fwnode_irq_get(const struct fwnode_handle *fwnode, + unsigned int index) { - return acpi_device_get_match_data(dev); + struct resource res; + int ret; + + ret = acpi_irq_get(ACPI_HANDLE_FWNODE(fwnode), index, &res); + if (ret) + return ret; + + return res.start; } #define DECLARE_ACPI_FWNODE_OPS(ops) \ const struct fwnode_operations ops = { \ .device_is_available = acpi_fwnode_device_is_available, \ .device_get_match_data = acpi_fwnode_device_get_match_data, \ + .device_dma_supported = \ + acpi_fwnode_device_dma_supported, \ + .device_get_dma_attr = acpi_fwnode_device_get_dma_attr, \ .property_present = acpi_fwnode_property_present, \ .property_read_int_array = \ acpi_fwnode_property_read_int_array, \ @@ -1404,6 +1437,7 @@ acpi_fwnode_device_get_match_data(const struct fwnode_handle *fwnode, acpi_graph_get_remote_endpoint, \ .graph_get_port_parent = acpi_fwnode_get_parent, \ .graph_parse_endpoint = acpi_fwnode_graph_parse_endpoint, \ + .irq_get = acpi_fwnode_irq_get, \ }; \ EXPORT_SYMBOL_GPL(ops) diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index 9efbfe087de7..762b61f67e6c 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -588,19 +588,6 @@ static struct acpi_device *handle_to_device(acpi_handle handle, return adev; } -int acpi_bus_get_device(acpi_handle handle, struct acpi_device **device) -{ - if (!device) - return -EINVAL; - - *device = handle_to_device(handle, NULL); - if (!*device) - return -ENODEV; - - return 0; -} -EXPORT_SYMBOL(acpi_bus_get_device); - /** * acpi_fetch_acpi_dev - Retrieve ACPI device object. * @handle: ACPI handle associated with the requested ACPI device object. diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c index c992e57b2c79..3147702710af 100644 --- a/drivers/acpi/sleep.c +++ b/drivers/acpi/sleep.c @@ -373,6 +373,18 @@ static const struct dmi_system_id acpisleep_dmi_table[] __initconst = { DMI_MATCH(DMI_PRODUCT_NAME, "20GGA00L00"), }, }, + /* + * ASUS B1400CEAE hangs on resume from suspend (see + * https://bugzilla.kernel.org/show_bug.cgi?id=215742). + */ + { + .callback = init_default_s3, + .ident = "ASUS B1400CEAE", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "ASUS EXPERTBOOK B1400CEAE"), + }, + }, {}, }; diff --git a/drivers/acpi/spcr.c b/drivers/acpi/spcr.c index d589543875b8..1eabfcd122ee 100644 --- a/drivers/acpi/spcr.c +++ b/drivers/acpi/spcr.c @@ -142,6 +142,7 @@ int __init acpi_parse_spcr(bool enable_earlycon, bool enable_console) case ACPI_DBG2_16550_COMPATIBLE: case ACPI_DBG2_16550_SUBSET: case ACPI_DBG2_16550_WITH_GAS: + case ACPI_DBG2_16550_NVIDIA: uart = "uart"; break; default: diff --git a/drivers/acpi/sysfs.c b/drivers/acpi/sysfs.c index a4b638bea6f1..cc2fe0618178 100644 --- a/drivers/acpi/sysfs.c +++ b/drivers/acpi/sysfs.c @@ -415,19 +415,30 @@ static ssize_t acpi_data_show(struct file *filp, struct kobject *kobj, loff_t offset, size_t count) { struct acpi_data_attr *data_attr; - void *base; - ssize_t rc; + void __iomem *base; + ssize_t size; data_attr = container_of(bin_attr, struct acpi_data_attr, attr); + size = data_attr->attr.size; + + if (offset < 0) + return -EINVAL; + + if (offset >= size) + return 0; - base = acpi_os_map_memory(data_attr->addr, data_attr->attr.size); + if (count > size - offset) + count = size - offset; + + base = acpi_os_map_iomem(data_attr->addr, size); if (!base) return -ENOMEM; - rc = memory_read_from_buffer(buf, count, &offset, base, - data_attr->attr.size); - acpi_os_unmap_memory(base, data_attr->attr.size); - return rc; + memcpy_fromio(buf, base + offset, count); + + acpi_os_unmap_iomem(base, size); + + return count; } static int acpi_bert_data_init(void *th, struct acpi_data_attr *data_attr) diff --git a/drivers/acpi/utils.c b/drivers/acpi/utils.c index d5cedffeeff9..3a9773a09e19 100644 --- a/drivers/acpi/utils.c +++ b/drivers/acpi/utils.c @@ -681,7 +681,7 @@ acpi_evaluate_dsm(acpi_handle handle, const guid_t *guid, u64 rev, u64 func, if (ret != AE_NOT_FOUND) acpi_handle_warn(handle, - "failed to evaluate _DSM (0x%x)\n", ret); + "failed to evaluate _DSM %pUb (0x%x)\n", guid, ret); return NULL; } diff --git a/drivers/amba/bus.c b/drivers/amba/bus.c index d3bd14aaabf6..7e775ba6fdd9 100644 --- a/drivers/amba/bus.c +++ b/drivers/amba/bus.c @@ -395,107 +395,104 @@ static void amba_device_release(struct device *dev) kfree(d); } -static int amba_device_try_add(struct amba_device *dev, struct resource *parent) +static int amba_read_periphid(struct amba_device *dev) { - u32 size; + struct reset_control *rstc; + u32 size, pid, cid; void __iomem *tmp; int i, ret; - ret = request_resource(parent, &dev->res); + ret = dev_pm_domain_attach(&dev->dev, true); if (ret) goto err_out; - /* Hard-coded primecell ID instead of plug-n-play */ - if (dev->periphid != 0) - goto skip_probe; + ret = amba_get_enable_pclk(dev); + if (ret) + goto err_pm; /* - * Dynamically calculate the size of the resource - * and use this for iomap + * Find reset control(s) of the amba bus and de-assert them. */ + rstc = of_reset_control_array_get_optional_shared(dev->dev.of_node); + if (IS_ERR(rstc)) { + ret = PTR_ERR(rstc); + if (ret != -EPROBE_DEFER) + dev_err(&dev->dev, "can't get reset: %d\n", ret); + goto err_clk; + } + reset_control_deassert(rstc); + reset_control_put(rstc); + size = resource_size(&dev->res); tmp = ioremap(dev->res.start, size); if (!tmp) { ret = -ENOMEM; - goto err_release; + goto err_clk; } - ret = dev_pm_domain_attach(&dev->dev, true); - if (ret) { - iounmap(tmp); - goto err_release; - } - - ret = amba_get_enable_pclk(dev); - if (ret == 0) { - u32 pid, cid; - struct reset_control *rstc; - - /* - * Find reset control(s) of the amba bus and de-assert them. - */ - rstc = of_reset_control_array_get_optional_shared(dev->dev.of_node); - if (IS_ERR(rstc)) { - ret = PTR_ERR(rstc); - if (ret != -EPROBE_DEFER) - dev_err(&dev->dev, "can't get reset: %d\n", - ret); - goto err_reset; - } - reset_control_deassert(rstc); - reset_control_put(rstc); - - /* - * Read pid and cid based on size of resource - * they are located at end of region - */ - for (pid = 0, i = 0; i < 4; i++) - pid |= (readl(tmp + size - 0x20 + 4 * i) & 255) << - (i * 8); - for (cid = 0, i = 0; i < 4; i++) - cid |= (readl(tmp + size - 0x10 + 4 * i) & 255) << - (i * 8); - - if (cid == CORESIGHT_CID) { - /* set the base to the start of the last 4k block */ - void __iomem *csbase = tmp + size - 4096; - - dev->uci.devarch = - readl(csbase + UCI_REG_DEVARCH_OFFSET); - dev->uci.devtype = - readl(csbase + UCI_REG_DEVTYPE_OFFSET) & 0xff; - } + /* + * Read pid and cid based on size of resource + * they are located at end of region + */ + for (pid = 0, i = 0; i < 4; i++) + pid |= (readl(tmp + size - 0x20 + 4 * i) & 255) << (i * 8); + for (cid = 0, i = 0; i < 4; i++) + cid |= (readl(tmp + size - 0x10 + 4 * i) & 255) << (i * 8); - amba_put_disable_pclk(dev); + if (cid == CORESIGHT_CID) { + /* set the base to the start of the last 4k block */ + void __iomem *csbase = tmp + size - 4096; - if (cid == AMBA_CID || cid == CORESIGHT_CID) { - dev->periphid = pid; - dev->cid = cid; - } + dev->uci.devarch = readl(csbase + UCI_REG_DEVARCH_OFFSET); + dev->uci.devtype = readl(csbase + UCI_REG_DEVTYPE_OFFSET) & 0xff; + } - if (!dev->periphid) - ret = -ENODEV; + if (cid == AMBA_CID || cid == CORESIGHT_CID) { + dev->periphid = pid; + dev->cid = cid; } + if (!dev->periphid) + ret = -ENODEV; + iounmap(tmp); + +err_clk: + amba_put_disable_pclk(dev); +err_pm: dev_pm_domain_detach(&dev->dev, true); +err_out: + return ret; +} + +static int amba_device_try_add(struct amba_device *dev, struct resource *parent) +{ + int ret; + ret = request_resource(parent, &dev->res); if (ret) + goto err_out; + + /* Hard-coded primecell ID instead of plug-n-play */ + if (dev->periphid != 0) + goto skip_probe; + + ret = amba_read_periphid(dev); + if (ret) { + if (ret != -EPROBE_DEFER) { + amba_device_put(dev); + goto err_out; + } goto err_release; + } - skip_probe: +skip_probe: ret = device_add(&dev->dev); - err_release: +err_release: if (ret) release_resource(&dev->res); - err_out: +err_out: return ret; - - err_reset: - amba_put_disable_pclk(dev); - iounmap(tmp); - dev_pm_domain_detach(&dev->dev, true); - goto err_release; } /* diff --git a/drivers/android/binder.c b/drivers/android/binder.c index 8351c5638880..f3b639e89dd8 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -2295,6 +2295,7 @@ static int binder_do_deferred_txn_copies(struct binder_alloc *alloc, { int ret = 0; struct binder_sg_copy *sgc, *tmpsgc; + struct binder_ptr_fixup *tmppf; struct binder_ptr_fixup *pf = list_first_entry_or_null(pf_head, struct binder_ptr_fixup, node); @@ -2349,7 +2350,11 @@ static int binder_do_deferred_txn_copies(struct binder_alloc *alloc, list_del(&sgc->node); kfree(sgc); } - BUG_ON(!list_empty(pf_head)); + list_for_each_entry_safe(pf, tmppf, pf_head, node) { + BUG_ON(pf->skip_size == 0); + list_del(&pf->node); + kfree(pf); + } BUG_ON(!list_empty(sgc_head)); return ret > 0 ? -EINVAL : ret; @@ -2486,6 +2491,9 @@ static int binder_translate_fd_array(struct list_head *pf_head, struct binder_proc *proc = thread->proc; int ret; + if (fda->num_fds == 0) + return 0; + fd_buf_size = sizeof(u32) * fda->num_fds; if (fda->num_fds >= SIZE_MAX / sizeof(u32)) { binder_user_error("%d:%d got transaction with invalid number of fds (%lld)\n", diff --git a/drivers/ata/Kconfig b/drivers/ata/Kconfig index e5641e6c52ee..bb45a9c00514 100644 --- a/drivers/ata/Kconfig +++ b/drivers/ata/Kconfig @@ -115,14 +115,16 @@ config SATA_AHCI If unsure, say N. -config SATA_LPM_POLICY +config SATA_MOBILE_LPM_POLICY int "Default SATA Link Power Management policy for low power chipsets" range 0 4 default 0 depends on SATA_AHCI help Select the Default SATA Link Power Management (LPM) policy to use - for chipsets / "South Bridges" designated as supporting low power. + for chipsets / "South Bridges" supporting low-power modes. Such + chipsets are typically found on most laptops but desktops and + servers now also widely use chipsets supporting low power modes. The value set has the following meanings: 0 => Keep firmware settings diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index 84456c05e845..c1eca72b4575 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -324,7 +324,6 @@ static const struct pci_device_id ahci_pci_tbl[] = { { PCI_VDEVICE(INTEL, 0x1d02), board_ahci }, /* PBG AHCI */ { PCI_VDEVICE(INTEL, 0x1d04), board_ahci }, /* PBG RAID */ { PCI_VDEVICE(INTEL, 0x1d06), board_ahci }, /* PBG RAID */ - { PCI_VDEVICE(INTEL, 0x2826), board_ahci }, /* PBG/Lewisburg RAID*/ { PCI_VDEVICE(INTEL, 0x2323), board_ahci }, /* DH89xxCC AHCI */ { PCI_VDEVICE(INTEL, 0x1e02), board_ahci }, /* Panther Point AHCI */ { PCI_VDEVICE(INTEL, 0x1e03), board_ahci_low_power }, /* Panther M AHCI */ @@ -367,7 +366,9 @@ static const struct pci_device_id ahci_pci_tbl[] = { { PCI_VDEVICE(INTEL, 0x1f3e), board_ahci_avn }, /* Avoton RAID */ { PCI_VDEVICE(INTEL, 0x1f3f), board_ahci_avn }, /* Avoton RAID */ { PCI_VDEVICE(INTEL, 0x2823), board_ahci }, /* Wellsburg/Lewisburg AHCI*/ - { PCI_VDEVICE(INTEL, 0x2827), board_ahci }, /* Wellsburg/Lewisburg RAID*/ + { PCI_VDEVICE(INTEL, 0x2826), board_ahci }, /* *burg SATA0 'RAID' */ + { PCI_VDEVICE(INTEL, 0x2827), board_ahci }, /* *burg SATA1 'RAID' */ + { PCI_VDEVICE(INTEL, 0x282f), board_ahci }, /* *burg SATA2 'RAID' */ { PCI_VDEVICE(INTEL, 0x43d4), board_ahci }, /* Rocket Lake PCH-H RAID */ { PCI_VDEVICE(INTEL, 0x43d5), board_ahci }, /* Rocket Lake PCH-H RAID */ { PCI_VDEVICE(INTEL, 0x43d6), board_ahci }, /* Rocket Lake PCH-H RAID */ @@ -1595,7 +1596,7 @@ static int ahci_init_msi(struct pci_dev *pdev, unsigned int n_ports, static void ahci_update_initial_lpm_policy(struct ata_port *ap, struct ahci_host_priv *hpriv) { - int policy = CONFIG_SATA_LPM_POLICY; + int policy = CONFIG_SATA_MOBILE_LPM_POLICY; /* Ignore processing for chipsets that don't use policy */ diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h index 6ead58c1b6e5..ad11a4c52fbe 100644 --- a/drivers/ata/ahci.h +++ b/drivers/ata/ahci.h @@ -236,7 +236,7 @@ enum { AHCI_HFLAG_NO_WRITE_TO_RO = (1 << 24), /* don't write to read only registers */ AHCI_HFLAG_USE_LPM_POLICY = (1 << 25), /* chipset that should use - SATA_LPM_POLICY + SATA_MOBILE_LPM_POLICY as default lpm_policy */ AHCI_HFLAG_SUSPEND_PHYS = (1 << 26), /* handle PHYs during suspend/resume */ diff --git a/drivers/ata/ahci_brcm.c b/drivers/ata/ahci_brcm.c index ab8552b1ff2a..f61795c546cf 100644 --- a/drivers/ata/ahci_brcm.c +++ b/drivers/ata/ahci_brcm.c @@ -549,15 +549,10 @@ static int brcm_ahci_remove(struct platform_device *pdev) struct ata_host *host = dev_get_drvdata(&pdev->dev); struct ahci_host_priv *hpriv = host->private_data; struct brcm_ahci_priv *priv = hpriv->plat_data; - int ret; brcm_sata_phys_disable(priv); - ret = ata_platform_remove_one(pdev); - if (ret) - return ret; - - return 0; + return ata_platform_remove_one(pdev); } static void brcm_ahci_shutdown(struct platform_device *pdev) diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index cceedde51126..40e816419f48 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -96,7 +96,8 @@ struct ata_force_param { unsigned long xfer_mask; unsigned int horkage_on; unsigned int horkage_off; - u16 lflags; + u16 lflags_on; + u16 lflags_off; }; struct ata_force_ent { @@ -386,11 +387,17 @@ static void ata_force_link_limits(struct ata_link *link) } /* let lflags stack */ - if (fe->param.lflags) { - link->flags |= fe->param.lflags; + if (fe->param.lflags_on) { + link->flags |= fe->param.lflags_on; ata_link_notice(link, "FORCE: link flag 0x%x forced -> 0x%x\n", - fe->param.lflags, link->flags); + fe->param.lflags_on, link->flags); + } + if (fe->param.lflags_off) { + link->flags &= ~fe->param.lflags_off; + ata_link_notice(link, + "FORCE: link flag 0x%x cleared -> 0x%x\n", + fe->param.lflags_off, link->flags); } } } @@ -898,7 +905,7 @@ EXPORT_SYMBOL_GPL(ata_xfer_mode2mask); * RETURNS: * Matching xfer_shift, -1 if no match found. */ -int ata_xfer_mode2shift(unsigned long xfer_mode) +int ata_xfer_mode2shift(u8 xfer_mode) { const struct ata_xfer_ent *ent; @@ -1398,7 +1405,7 @@ unsigned long ata_id_xfermask(const u16 *id) /* But wait.. there's more. Design your standards by * committee and you too can get a free iordy field to - * process. However its the speeds not the modes that + * process. However it is the speeds not the modes that * are supported... Note drivers using the timing API * will get this right anyway */ @@ -3898,7 +3905,7 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { /* Devices where NCQ should be avoided */ /* NCQ is slow */ { "WDC WD740ADFD-00", NULL, ATA_HORKAGE_NONCQ }, - { "WDC WD740ADFD-00NLR1", NULL, ATA_HORKAGE_NONCQ, }, + { "WDC WD740ADFD-00NLR1", NULL, ATA_HORKAGE_NONCQ }, /* http://thread.gmane.org/gmane.linux.ide/14907 */ { "FUJITSU MHT2060BH", NULL, ATA_HORKAGE_NONCQ }, /* NCQ is broken */ @@ -3924,23 +3931,23 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { /* drives which fail FPDMA_AA activation (some may freeze afterwards) the ST disks also have LPM issues */ { "ST1000LM024 HN-M101MBB", NULL, ATA_HORKAGE_BROKEN_FPDMA_AA | - ATA_HORKAGE_NOLPM, }, + ATA_HORKAGE_NOLPM }, { "VB0250EAVER", "HPG7", ATA_HORKAGE_BROKEN_FPDMA_AA }, /* Blacklist entries taken from Silicon Image 3124/3132 Windows driver .inf file - also several Linux problem reports */ - { "HTS541060G9SA00", "MB3OC60D", ATA_HORKAGE_NONCQ, }, - { "HTS541080G9SA00", "MB4OC60D", ATA_HORKAGE_NONCQ, }, - { "HTS541010G9SA00", "MBZOC60D", ATA_HORKAGE_NONCQ, }, + { "HTS541060G9SA00", "MB3OC60D", ATA_HORKAGE_NONCQ }, + { "HTS541080G9SA00", "MB4OC60D", ATA_HORKAGE_NONCQ }, + { "HTS541010G9SA00", "MBZOC60D", ATA_HORKAGE_NONCQ }, /* https://bugzilla.kernel.org/show_bug.cgi?id=15573 */ - { "C300-CTFDDAC128MAG", "0001", ATA_HORKAGE_NONCQ, }, + { "C300-CTFDDAC128MAG", "0001", ATA_HORKAGE_NONCQ }, /* Sandisk SD7/8/9s lock up hard on large trims */ - { "SanDisk SD[789]*", NULL, ATA_HORKAGE_MAX_TRIM_128M, }, + { "SanDisk SD[789]*", NULL, ATA_HORKAGE_MAX_TRIM_128M }, /* devices which puke on READ_NATIVE_MAX */ - { "HDS724040KLSA80", "KFAOA20N", ATA_HORKAGE_BROKEN_HPA, }, + { "HDS724040KLSA80", "KFAOA20N", ATA_HORKAGE_BROKEN_HPA }, { "WDC WD3200JD-00KLB0", "WD-WCAMR1130137", ATA_HORKAGE_BROKEN_HPA }, { "WDC WD2500JD-00HBB0", "WD-WMAL71490727", ATA_HORKAGE_BROKEN_HPA }, { "MAXTOR 6L080L4", "A93.0500", ATA_HORKAGE_BROKEN_HPA }, @@ -3949,22 +3956,22 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { { "OCZ-VERTEX", "1.30", ATA_HORKAGE_BROKEN_HPA }, /* Devices which report 1 sector over size HPA */ - { "ST340823A", NULL, ATA_HORKAGE_HPA_SIZE, }, - { "ST320413A", NULL, ATA_HORKAGE_HPA_SIZE, }, - { "ST310211A", NULL, ATA_HORKAGE_HPA_SIZE, }, + { "ST340823A", NULL, ATA_HORKAGE_HPA_SIZE }, + { "ST320413A", NULL, ATA_HORKAGE_HPA_SIZE }, + { "ST310211A", NULL, ATA_HORKAGE_HPA_SIZE }, /* Devices which get the IVB wrong */ - { "QUANTUM FIREBALLlct10 05", "A03.0900", ATA_HORKAGE_IVB, }, + { "QUANTUM FIREBALLlct10 05", "A03.0900", ATA_HORKAGE_IVB }, /* Maybe we should just blacklist TSSTcorp... */ - { "TSSTcorp CDDVDW SH-S202[HJN]", "SB0[01]", ATA_HORKAGE_IVB, }, + { "TSSTcorp CDDVDW SH-S202[HJN]", "SB0[01]", ATA_HORKAGE_IVB }, /* Devices that do not need bridging limits applied */ - { "MTRON MSP-SATA*", NULL, ATA_HORKAGE_BRIDGE_OK, }, - { "BUFFALO HD-QSU2/R5", NULL, ATA_HORKAGE_BRIDGE_OK, }, + { "MTRON MSP-SATA*", NULL, ATA_HORKAGE_BRIDGE_OK }, + { "BUFFALO HD-QSU2/R5", NULL, ATA_HORKAGE_BRIDGE_OK }, /* Devices which aren't very happy with higher link speeds */ - { "WD My Book", NULL, ATA_HORKAGE_1_5_GBPS, }, - { "Seagate FreeAgent GoFlex", NULL, ATA_HORKAGE_1_5_GBPS, }, + { "WD My Book", NULL, ATA_HORKAGE_1_5_GBPS }, + { "Seagate FreeAgent GoFlex", NULL, ATA_HORKAGE_1_5_GBPS }, /* * Devices which choke on SETXFER. Applies only if both the @@ -3982,54 +3989,57 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { /* 512GB MX100 with MU01 firmware has both queued TRIM and LPM issues */ { "Crucial_CT512MX100*", "MU01", ATA_HORKAGE_NO_NCQ_TRIM | ATA_HORKAGE_ZERO_AFTER_TRIM | - ATA_HORKAGE_NOLPM, }, + ATA_HORKAGE_NOLPM }, /* 512GB MX100 with newer firmware has only LPM issues */ { "Crucial_CT512MX100*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM | - ATA_HORKAGE_NOLPM, }, + ATA_HORKAGE_NOLPM }, /* 480GB+ M500 SSDs have both queued TRIM and LPM issues */ { "Crucial_CT480M500*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | ATA_HORKAGE_ZERO_AFTER_TRIM | - ATA_HORKAGE_NOLPM, }, + ATA_HORKAGE_NOLPM }, { "Crucial_CT960M500*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | ATA_HORKAGE_ZERO_AFTER_TRIM | - ATA_HORKAGE_NOLPM, }, + ATA_HORKAGE_NOLPM }, /* These specific Samsung models/firmware-revs do not handle LPM well */ - { "SAMSUNG MZMPC128HBFU-000MV", "CXM14M1Q", ATA_HORKAGE_NOLPM, }, - { "SAMSUNG SSD PM830 mSATA *", "CXM13D1Q", ATA_HORKAGE_NOLPM, }, - { "SAMSUNG MZ7TD256HAFV-000L9", NULL, ATA_HORKAGE_NOLPM, }, - { "SAMSUNG MZ7TE512HMHP-000L1", "EXT06L0Q", ATA_HORKAGE_NOLPM, }, + { "SAMSUNG MZMPC128HBFU-000MV", "CXM14M1Q", ATA_HORKAGE_NOLPM }, + { "SAMSUNG SSD PM830 mSATA *", "CXM13D1Q", ATA_HORKAGE_NOLPM }, + { "SAMSUNG MZ7TD256HAFV-000L9", NULL, ATA_HORKAGE_NOLPM }, + { "SAMSUNG MZ7TE512HMHP-000L1", "EXT06L0Q", ATA_HORKAGE_NOLPM }, /* devices that don't properly handle queued TRIM commands */ { "Micron_M500IT_*", "MU01", ATA_HORKAGE_NO_NCQ_TRIM | - ATA_HORKAGE_ZERO_AFTER_TRIM, }, + ATA_HORKAGE_ZERO_AFTER_TRIM }, { "Micron_M500_*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | - ATA_HORKAGE_ZERO_AFTER_TRIM, }, + ATA_HORKAGE_ZERO_AFTER_TRIM }, { "Crucial_CT*M500*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | - ATA_HORKAGE_ZERO_AFTER_TRIM, }, + ATA_HORKAGE_ZERO_AFTER_TRIM }, { "Micron_M5[15]0_*", "MU01", ATA_HORKAGE_NO_NCQ_TRIM | - ATA_HORKAGE_ZERO_AFTER_TRIM, }, + ATA_HORKAGE_ZERO_AFTER_TRIM }, { "Crucial_CT*M550*", "MU01", ATA_HORKAGE_NO_NCQ_TRIM | - ATA_HORKAGE_ZERO_AFTER_TRIM, }, + ATA_HORKAGE_ZERO_AFTER_TRIM }, { "Crucial_CT*MX100*", "MU01", ATA_HORKAGE_NO_NCQ_TRIM | - ATA_HORKAGE_ZERO_AFTER_TRIM, }, + ATA_HORKAGE_ZERO_AFTER_TRIM }, + { "Samsung SSD 840 EVO*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | + ATA_HORKAGE_NO_DMA_LOG | + ATA_HORKAGE_ZERO_AFTER_TRIM }, { "Samsung SSD 840*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | - ATA_HORKAGE_ZERO_AFTER_TRIM, }, + ATA_HORKAGE_ZERO_AFTER_TRIM }, { "Samsung SSD 850*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | - ATA_HORKAGE_ZERO_AFTER_TRIM, }, + ATA_HORKAGE_ZERO_AFTER_TRIM }, { "Samsung SSD 860*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | ATA_HORKAGE_ZERO_AFTER_TRIM | - ATA_HORKAGE_NO_NCQ_ON_ATI, }, + ATA_HORKAGE_NO_NCQ_ON_ATI }, { "Samsung SSD 870*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | ATA_HORKAGE_ZERO_AFTER_TRIM | - ATA_HORKAGE_NO_NCQ_ON_ATI, }, + ATA_HORKAGE_NO_NCQ_ON_ATI }, { "FCCT*M500*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | - ATA_HORKAGE_ZERO_AFTER_TRIM, }, + ATA_HORKAGE_ZERO_AFTER_TRIM }, /* devices that don't properly handle TRIM commands */ - { "SuperSSpeed S238*", NULL, ATA_HORKAGE_NOTRIM, }, - { "M88V29*", NULL, ATA_HORKAGE_NOTRIM, }, + { "SuperSSpeed S238*", NULL, ATA_HORKAGE_NOTRIM }, + { "M88V29*", NULL, ATA_HORKAGE_NOTRIM }, /* * As defined, the DRAT (Deterministic Read After Trim) and RZAT @@ -4047,16 +4057,16 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { * The intel 510 drive has buggy DRAT/RZAT. Explicitly exclude * that model before whitelisting all other intel SSDs. */ - { "INTEL*SSDSC2MH*", NULL, 0, }, + { "INTEL*SSDSC2MH*", NULL, 0 }, - { "Micron*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM, }, - { "Crucial*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM, }, - { "INTEL*SSD*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM, }, - { "SSD*INTEL*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM, }, - { "Samsung*SSD*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM, }, - { "SAMSUNG*SSD*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM, }, - { "SAMSUNG*MZ7KM*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM, }, - { "ST[1248][0248]0[FH]*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM, }, + { "Micron*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM }, + { "Crucial*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM }, + { "INTEL*SSD*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM }, + { "SSD*INTEL*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM }, + { "Samsung*SSD*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM }, + { "SAMSUNG*SSD*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM }, + { "SAMSUNG*MZ7KM*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM }, + { "ST[1248][0248]0[FH]*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM }, /* * Some WD SATA-I drives spin up and down erratically when the link @@ -4564,42 +4574,6 @@ void swap_buf_le16(u16 *buf, unsigned int buf_words) } /** - * ata_qc_new_init - Request an available ATA command, and initialize it - * @dev: Device from whom we request an available command structure - * @tag: tag - * - * LOCKING: - * None. - */ - -struct ata_queued_cmd *ata_qc_new_init(struct ata_device *dev, int tag) -{ - struct ata_port *ap = dev->link->ap; - struct ata_queued_cmd *qc; - - /* no command while frozen */ - if (unlikely(ap->pflags & ATA_PFLAG_FROZEN)) - return NULL; - - /* libsas case */ - if (ap->flags & ATA_FLAG_SAS_HOST) { - tag = ata_sas_allocate_tag(ap); - if (tag < 0) - return NULL; - } - - qc = __ata_qc_from_tag(ap, tag); - qc->tag = qc->hw_tag = tag; - qc->scsicmd = NULL; - qc->ap = ap; - qc->dev = dev; - - ata_qc_reinit(qc); - - return qc; -} - -/** * ata_qc_free - free unused ata_queued_cmd * @qc: Command to complete * @@ -4611,19 +4585,9 @@ struct ata_queued_cmd *ata_qc_new_init(struct ata_device *dev, int tag) */ void ata_qc_free(struct ata_queued_cmd *qc) { - struct ata_port *ap; - unsigned int tag; - - WARN_ON_ONCE(qc == NULL); /* ata_qc_from_tag _might_ return NULL */ - ap = qc->ap; - qc->flags = 0; - tag = qc->tag; - if (ata_tag_valid(tag)) { + if (ata_tag_valid(qc->tag)) qc->tag = ATA_TAG_POISON; - if (ap->flags & ATA_FLAG_SAS_HOST) - ata_sas_free_tag(tag, ap); - } } void __ata_qc_complete(struct ata_queued_cmd *qc) @@ -5602,7 +5566,7 @@ static void ata_finalize_port_ops(struct ata_port_operations *ops) * Start and then freeze ports of @host. Started status is * recorded in host->flags, so this function can be called * multiple times. Ports are guaranteed to get started only - * once. If host->ops isn't initialized yet, its set to the + * once. If host->ops is not initialized yet, it is set to the * first non-dummy port ops. * * LOCKING: @@ -6143,67 +6107,113 @@ int ata_platform_remove_one(struct platform_device *pdev) EXPORT_SYMBOL_GPL(ata_platform_remove_one); #ifdef CONFIG_ATA_FORCE + +#define force_cbl(name, flag) \ + { #name, .cbl = (flag) } + +#define force_spd_limit(spd, val) \ + { #spd, .spd_limit = (val) } + +#define force_xfer(mode, shift) \ + { #mode, .xfer_mask = (1UL << (shift)) } + +#define force_lflag_on(name, flags) \ + { #name, .lflags_on = (flags) } + +#define force_lflag_onoff(name, flags) \ + { "no" #name, .lflags_on = (flags) }, \ + { #name, .lflags_off = (flags) } + +#define force_horkage_on(name, flag) \ + { #name, .horkage_on = (flag) } + +#define force_horkage_onoff(name, flag) \ + { "no" #name, .horkage_on = (flag) }, \ + { #name, .horkage_off = (flag) } + +static const struct ata_force_param force_tbl[] __initconst = { + force_cbl(40c, ATA_CBL_PATA40), + force_cbl(80c, ATA_CBL_PATA80), + force_cbl(short40c, ATA_CBL_PATA40_SHORT), + force_cbl(unk, ATA_CBL_PATA_UNK), + force_cbl(ign, ATA_CBL_PATA_IGN), + force_cbl(sata, ATA_CBL_SATA), + + force_spd_limit(1.5Gbps, 1), + force_spd_limit(3.0Gbps, 2), + + force_xfer(pio0, ATA_SHIFT_PIO + 0), + force_xfer(pio1, ATA_SHIFT_PIO + 1), + force_xfer(pio2, ATA_SHIFT_PIO + 2), + force_xfer(pio3, ATA_SHIFT_PIO + 3), + force_xfer(pio4, ATA_SHIFT_PIO + 4), + force_xfer(pio5, ATA_SHIFT_PIO + 5), + force_xfer(pio6, ATA_SHIFT_PIO + 6), + force_xfer(mwdma0, ATA_SHIFT_MWDMA + 0), + force_xfer(mwdma1, ATA_SHIFT_MWDMA + 1), + force_xfer(mwdma2, ATA_SHIFT_MWDMA + 2), + force_xfer(mwdma3, ATA_SHIFT_MWDMA + 3), + force_xfer(mwdma4, ATA_SHIFT_MWDMA + 4), + force_xfer(udma0, ATA_SHIFT_UDMA + 0), + force_xfer(udma16, ATA_SHIFT_UDMA + 0), + force_xfer(udma/16, ATA_SHIFT_UDMA + 0), + force_xfer(udma1, ATA_SHIFT_UDMA + 1), + force_xfer(udma25, ATA_SHIFT_UDMA + 1), + force_xfer(udma/25, ATA_SHIFT_UDMA + 1), + force_xfer(udma2, ATA_SHIFT_UDMA + 2), + force_xfer(udma33, ATA_SHIFT_UDMA + 2), + force_xfer(udma/33, ATA_SHIFT_UDMA + 2), + force_xfer(udma3, ATA_SHIFT_UDMA + 3), + force_xfer(udma44, ATA_SHIFT_UDMA + 3), + force_xfer(udma/44, ATA_SHIFT_UDMA + 3), + force_xfer(udma4, ATA_SHIFT_UDMA + 4), + force_xfer(udma66, ATA_SHIFT_UDMA + 4), + force_xfer(udma/66, ATA_SHIFT_UDMA + 4), + force_xfer(udma5, ATA_SHIFT_UDMA + 5), + force_xfer(udma100, ATA_SHIFT_UDMA + 5), + force_xfer(udma/100, ATA_SHIFT_UDMA + 5), + force_xfer(udma6, ATA_SHIFT_UDMA + 6), + force_xfer(udma133, ATA_SHIFT_UDMA + 6), + force_xfer(udma/133, ATA_SHIFT_UDMA + 6), + force_xfer(udma7, ATA_SHIFT_UDMA + 7), + + force_lflag_on(nohrst, ATA_LFLAG_NO_HRST), + force_lflag_on(nosrst, ATA_LFLAG_NO_SRST), + force_lflag_on(norst, ATA_LFLAG_NO_HRST | ATA_LFLAG_NO_SRST), + force_lflag_on(rstonce, ATA_LFLAG_RST_ONCE), + force_lflag_onoff(dbdelay, ATA_LFLAG_NO_DEBOUNCE_DELAY), + + force_horkage_onoff(ncq, ATA_HORKAGE_NONCQ), + force_horkage_onoff(ncqtrim, ATA_HORKAGE_NO_NCQ_TRIM), + force_horkage_onoff(ncqati, ATA_HORKAGE_NO_NCQ_ON_ATI), + + force_horkage_onoff(trim, ATA_HORKAGE_NOTRIM), + force_horkage_on(trim_zero, ATA_HORKAGE_ZERO_AFTER_TRIM), + force_horkage_on(max_trim_128m, ATA_HORKAGE_MAX_TRIM_128M), + + force_horkage_onoff(dma, ATA_HORKAGE_NODMA), + force_horkage_on(atapi_dmadir, ATA_HORKAGE_ATAPI_DMADIR), + force_horkage_on(atapi_mod16_dma, ATA_HORKAGE_ATAPI_MOD16_DMA), + + force_horkage_onoff(dmalog, ATA_HORKAGE_NO_DMA_LOG), + force_horkage_onoff(iddevlog, ATA_HORKAGE_NO_ID_DEV_LOG), + force_horkage_onoff(logdir, ATA_HORKAGE_NO_LOG_DIR), + + force_horkage_on(max_sec_128, ATA_HORKAGE_MAX_SEC_128), + force_horkage_on(max_sec_1024, ATA_HORKAGE_MAX_SEC_1024), + force_horkage_on(max_sec_lba48, ATA_HORKAGE_MAX_SEC_LBA48), + + force_horkage_onoff(lpm, ATA_HORKAGE_NOLPM), + force_horkage_onoff(setxfer, ATA_HORKAGE_NOSETXFER), + force_horkage_on(dump_id, ATA_HORKAGE_DUMP_ID), + + force_horkage_on(disable, ATA_HORKAGE_DISABLE), +}; + static int __init ata_parse_force_one(char **cur, struct ata_force_ent *force_ent, const char **reason) { - static const struct ata_force_param force_tbl[] __initconst = { - { "40c", .cbl = ATA_CBL_PATA40 }, - { "80c", .cbl = ATA_CBL_PATA80 }, - { "short40c", .cbl = ATA_CBL_PATA40_SHORT }, - { "unk", .cbl = ATA_CBL_PATA_UNK }, - { "ign", .cbl = ATA_CBL_PATA_IGN }, - { "sata", .cbl = ATA_CBL_SATA }, - { "1.5Gbps", .spd_limit = 1 }, - { "3.0Gbps", .spd_limit = 2 }, - { "noncq", .horkage_on = ATA_HORKAGE_NONCQ }, - { "ncq", .horkage_off = ATA_HORKAGE_NONCQ }, - { "noncqtrim", .horkage_on = ATA_HORKAGE_NO_NCQ_TRIM }, - { "ncqtrim", .horkage_off = ATA_HORKAGE_NO_NCQ_TRIM }, - { "noncqati", .horkage_on = ATA_HORKAGE_NO_NCQ_ON_ATI }, - { "ncqati", .horkage_off = ATA_HORKAGE_NO_NCQ_ON_ATI }, - { "dump_id", .horkage_on = ATA_HORKAGE_DUMP_ID }, - { "pio0", .xfer_mask = 1 << (ATA_SHIFT_PIO + 0) }, - { "pio1", .xfer_mask = 1 << (ATA_SHIFT_PIO + 1) }, - { "pio2", .xfer_mask = 1 << (ATA_SHIFT_PIO + 2) }, - { "pio3", .xfer_mask = 1 << (ATA_SHIFT_PIO + 3) }, - { "pio4", .xfer_mask = 1 << (ATA_SHIFT_PIO + 4) }, - { "pio5", .xfer_mask = 1 << (ATA_SHIFT_PIO + 5) }, - { "pio6", .xfer_mask = 1 << (ATA_SHIFT_PIO + 6) }, - { "mwdma0", .xfer_mask = 1 << (ATA_SHIFT_MWDMA + 0) }, - { "mwdma1", .xfer_mask = 1 << (ATA_SHIFT_MWDMA + 1) }, - { "mwdma2", .xfer_mask = 1 << (ATA_SHIFT_MWDMA + 2) }, - { "mwdma3", .xfer_mask = 1 << (ATA_SHIFT_MWDMA + 3) }, - { "mwdma4", .xfer_mask = 1 << (ATA_SHIFT_MWDMA + 4) }, - { "udma0", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 0) }, - { "udma16", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 0) }, - { "udma/16", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 0) }, - { "udma1", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 1) }, - { "udma25", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 1) }, - { "udma/25", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 1) }, - { "udma2", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 2) }, - { "udma33", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 2) }, - { "udma/33", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 2) }, - { "udma3", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 3) }, - { "udma44", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 3) }, - { "udma/44", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 3) }, - { "udma4", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 4) }, - { "udma66", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 4) }, - { "udma/66", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 4) }, - { "udma5", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 5) }, - { "udma100", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 5) }, - { "udma/100", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 5) }, - { "udma6", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 6) }, - { "udma133", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 6) }, - { "udma/133", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 6) }, - { "udma7", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 7) }, - { "nohrst", .lflags = ATA_LFLAG_NO_HRST }, - { "nosrst", .lflags = ATA_LFLAG_NO_SRST }, - { "norst", .lflags = ATA_LFLAG_NO_HRST | ATA_LFLAG_NO_SRST }, - { "rstonce", .lflags = ATA_LFLAG_RST_ONCE }, - { "atapi_dmadir", .horkage_on = ATA_HORKAGE_ATAPI_DMADIR }, - { "disable", .horkage_on = ATA_HORKAGE_DISABLE }, - }; char *start = *cur, *p = *cur; char *id, *val, *endp; const struct ata_force_param *match_fp = NULL; @@ -6285,7 +6295,7 @@ static void __init ata_parse_force_param(void) int last_port = -1, last_device = -1; char *p, *cur, *next; - /* calculate maximum number of params and allocate force_tbl */ + /* Calculate maximum number of params and allocate ata_force_tbl */ for (p = ata_force_param_buf; *p; p++) if (*p == ',') size++; diff --git a/drivers/ata/libata-sata.c b/drivers/ata/libata-sata.c index 044a16daa2d4..7a5fe41aa5ae 100644 --- a/drivers/ata/libata-sata.c +++ b/drivers/ata/libata-sata.c @@ -1268,31 +1268,6 @@ int ata_sas_queuecmd(struct scsi_cmnd *cmd, struct ata_port *ap) } EXPORT_SYMBOL_GPL(ata_sas_queuecmd); -int ata_sas_allocate_tag(struct ata_port *ap) -{ - unsigned int max_queue = ap->host->n_tags; - unsigned int i, tag; - - for (i = 0, tag = ap->sas_last_tag + 1; i < max_queue; i++, tag++) { - tag = tag < max_queue ? tag : 0; - - /* the last tag is reserved for internal command. */ - if (ata_tag_internal(tag)) - continue; - - if (!test_and_set_bit(tag, &ap->sas_tag_allocated)) { - ap->sas_last_tag = tag; - return tag; - } - } - return -1; -} - -void ata_sas_free_tag(unsigned int tag, struct ata_port *ap) -{ - clear_bit(tag, &ap->sas_tag_allocated); -} - /** * sata_async_notification - SATA async notification handler * @ap: ATA port where async notification is received diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 06c9d90238d9..42cecf95a4e5 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -638,24 +638,48 @@ EXPORT_SYMBOL_GPL(ata_scsi_ioctl); static struct ata_queued_cmd *ata_scsi_qc_new(struct ata_device *dev, struct scsi_cmnd *cmd) { + struct ata_port *ap = dev->link->ap; struct ata_queued_cmd *qc; + int tag; - qc = ata_qc_new_init(dev, scsi_cmd_to_rq(cmd)->tag); - if (qc) { - qc->scsicmd = cmd; - qc->scsidone = scsi_done; - - qc->sg = scsi_sglist(cmd); - qc->n_elem = scsi_sg_count(cmd); + if (unlikely(ap->pflags & ATA_PFLAG_FROZEN)) + goto fail; - if (scsi_cmd_to_rq(cmd)->rq_flags & RQF_QUIET) - qc->flags |= ATA_QCFLAG_QUIET; + if (ap->flags & ATA_FLAG_SAS_HOST) { + /* + * SAS hosts may queue > ATA_MAX_QUEUE commands so use + * unique per-device budget token as a tag. + */ + if (WARN_ON_ONCE(cmd->budget_token >= ATA_MAX_QUEUE)) + goto fail; + tag = cmd->budget_token; } else { - cmd->result = (DID_OK << 16) | SAM_STAT_TASK_SET_FULL; - scsi_done(cmd); + tag = scsi_cmd_to_rq(cmd)->tag; } + qc = __ata_qc_from_tag(ap, tag); + qc->tag = qc->hw_tag = tag; + qc->ap = ap; + qc->dev = dev; + + ata_qc_reinit(qc); + + qc->scsicmd = cmd; + qc->scsidone = scsi_done; + + qc->sg = scsi_sglist(cmd); + qc->n_elem = scsi_sg_count(cmd); + + if (scsi_cmd_to_rq(cmd)->rq_flags & RQF_QUIET) + qc->flags |= ATA_QCFLAG_QUIET; + return qc; + +fail: + set_host_byte(cmd, DID_OK); + set_status_byte(cmd, SAM_STAT_TASK_SET_FULL); + scsi_done(cmd); + return NULL; } static void ata_qc_set_pc_nbytes(struct ata_queued_cmd *qc) diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c index b3be7a8f5bea..b1666adc1c3a 100644 --- a/drivers/ata/libata-sff.c +++ b/drivers/ata/libata-sff.c @@ -1634,7 +1634,7 @@ EXPORT_SYMBOL_GPL(ata_sff_interrupt); void ata_sff_lost_interrupt(struct ata_port *ap) { - u8 status; + u8 status = 0; struct ata_queued_cmd *qc; /* Only one outstanding command per SFF channel */ diff --git a/drivers/ata/libata.h b/drivers/ata/libata.h index c9c2496d91ea..926a7f41303d 100644 --- a/drivers/ata/libata.h +++ b/drivers/ata/libata.h @@ -44,7 +44,6 @@ static inline void ata_force_cbl(struct ata_port *ap) { } #endif extern u64 ata_tf_to_lba(const struct ata_taskfile *tf); extern u64 ata_tf_to_lba48(const struct ata_taskfile *tf); -extern struct ata_queued_cmd *ata_qc_new_init(struct ata_device *dev, int tag); extern int ata_build_rw_tf(struct ata_taskfile *tf, struct ata_device *dev, u64 block, u32 n_block, unsigned int tf_flags, unsigned int tag, int class); @@ -91,18 +90,6 @@ extern unsigned int ata_read_log_page(struct ata_device *dev, u8 log, #define to_ata_port(d) container_of(d, struct ata_port, tdev) -/* libata-sata.c */ -#ifdef CONFIG_SATA_HOST -int ata_sas_allocate_tag(struct ata_port *ap); -void ata_sas_free_tag(unsigned int tag, struct ata_port *ap); -#else -static inline int ata_sas_allocate_tag(struct ata_port *ap) -{ - return -EOPNOTSUPP; -} -static inline void ata_sas_free_tag(unsigned int tag, struct ata_port *ap) { } -#endif - /* libata-acpi.c */ #ifdef CONFIG_ATA_ACPI extern unsigned int ata_acpi_gtf_filter; diff --git a/drivers/ata/pata_ftide010.c b/drivers/ata/pata_ftide010.c index 2e35505b683c..0117df0fe3c5 100644 --- a/drivers/ata/pata_ftide010.c +++ b/drivers/ata/pata_ftide010.c @@ -536,8 +536,8 @@ static int pata_ftide010_probe(struct platform_device *pdev) return 0; err_dis_clk: - if (!IS_ERR(ftide->pclk)) - clk_disable_unprepare(ftide->pclk); + clk_disable_unprepare(ftide->pclk); + return ret; } @@ -547,8 +547,7 @@ static int pata_ftide010_remove(struct platform_device *pdev) struct ftide010 *ftide = host->private_data; ata_host_detach(ftide->host); - if (!IS_ERR(ftide->pclk)) - clk_disable_unprepare(ftide->pclk); + clk_disable_unprepare(ftide->pclk); return 0; } diff --git a/drivers/ata/pata_marvell.c b/drivers/ata/pata_marvell.c index 0c5a51970fbf..014ccb0f45dc 100644 --- a/drivers/ata/pata_marvell.c +++ b/drivers/ata/pata_marvell.c @@ -77,6 +77,8 @@ static int marvell_cable_detect(struct ata_port *ap) switch(ap->port_no) { case 0: + if (!ap->ioaddr.bmdma_addr) + return ATA_CBL_PATA_UNK; if (ioread8(ap->ioaddr.bmdma_addr + 1) & 1) return ATA_CBL_PATA40; return ATA_CBL_PATA80; diff --git a/drivers/ata/pata_mpc52xx.c b/drivers/ata/pata_mpc52xx.c index 3250ef317df6..03b6ae37a578 100644 --- a/drivers/ata/pata_mpc52xx.c +++ b/drivers/ata/pata_mpc52xx.c @@ -19,11 +19,12 @@ #include <linux/gfp.h> #include <linux/delay.h> #include <linux/libata.h> +#include <linux/of_address.h> +#include <linux/of_irq.h> #include <linux/of_platform.h> #include <linux/types.h> #include <asm/cacheflush.h> -#include <asm/prom.h> #include <asm/mpc52xx.h> #include <linux/fsl/bestcomm/bestcomm.h> diff --git a/drivers/ata/pata_sil680.c b/drivers/ata/pata_sil680.c index 0da58ce20d82..67ef2e26d7df 100644 --- a/drivers/ata/pata_sil680.c +++ b/drivers/ata/pata_sil680.c @@ -47,11 +47,9 @@ * criticial. */ -static unsigned long sil680_selreg(struct ata_port *ap, int r) +static int sil680_selreg(struct ata_port *ap, int r) { - unsigned long base = 0xA0 + r; - base += (ap->port_no << 4); - return base; + return 0xA0 + (ap->port_no << 4) + r; } /** @@ -65,12 +63,9 @@ static unsigned long sil680_selreg(struct ata_port *ap, int r) * the unit shift. */ -static unsigned long sil680_seldev(struct ata_port *ap, struct ata_device *adev, int r) +static int sil680_seldev(struct ata_port *ap, struct ata_device *adev, int r) { - unsigned long base = 0xA0 + r; - base += (ap->port_no << 4); - base |= adev->devno ? 2 : 0; - return base; + return 0xA0 + (ap->port_no << 4) + r + (adev->devno << 1); } @@ -85,8 +80,9 @@ static unsigned long sil680_seldev(struct ata_port *ap, struct ata_device *adev, static int sil680_cable_detect(struct ata_port *ap) { struct pci_dev *pdev = to_pci_dev(ap->host->dev); - unsigned long addr = sil680_selreg(ap, 0); + int addr = sil680_selreg(ap, 0); u8 ata66; + pci_read_config_byte(pdev, addr, &ata66); if (ata66 & 1) return ATA_CBL_PATA80; @@ -113,9 +109,9 @@ static void sil680_set_piomode(struct ata_port *ap, struct ata_device *adev) 0x328A, 0x2283, 0x1281, 0x10C3, 0x10C1 }; - unsigned long tfaddr = sil680_selreg(ap, 0x02); - unsigned long addr = sil680_seldev(ap, adev, 0x04); - unsigned long addr_mask = 0x80 + 4 * ap->port_no; + int tfaddr = sil680_selreg(ap, 0x02); + int addr = sil680_seldev(ap, adev, 0x04); + int addr_mask = 0x80 + 4 * ap->port_no; struct pci_dev *pdev = to_pci_dev(ap->host->dev); int pio = adev->pio_mode - XFER_PIO_0; int lowest_pio = pio; @@ -165,9 +161,9 @@ static void sil680_set_dmamode(struct ata_port *ap, struct ata_device *adev) static const u16 dma_table[3] = { 0x2208, 0x10C2, 0x10C1 }; struct pci_dev *pdev = to_pci_dev(ap->host->dev); - unsigned long ma = sil680_seldev(ap, adev, 0x08); - unsigned long ua = sil680_seldev(ap, adev, 0x0C); - unsigned long addr_mask = 0x80 + 4 * ap->port_no; + int ma = sil680_seldev(ap, adev, 0x08); + int ua = sil680_seldev(ap, adev, 0x0C); + int addr_mask = 0x80 + 4 * ap->port_no; int port_shift = adev->devno * 4; u8 scsc, mode; u16 multi, ultra; @@ -219,7 +215,7 @@ static void sil680_sff_exec_command(struct ata_port *ap, static bool sil680_sff_irq_check(struct ata_port *ap) { struct pci_dev *pdev = to_pci_dev(ap->host->dev); - unsigned long addr = sil680_selreg(ap, 1); + int addr = sil680_selreg(ap, 1); u8 val; pci_read_config_byte(pdev, addr, &val); diff --git a/drivers/ata/pata_via.c b/drivers/ata/pata_via.c index 439ca882f73c..215c02d4056a 100644 --- a/drivers/ata/pata_via.c +++ b/drivers/ata/pata_via.c @@ -248,9 +248,9 @@ static void via_do_set_mode(struct ata_port *ap, struct ata_device *adev, struct pci_dev *pdev = to_pci_dev(ap->host->dev); struct ata_device *peer = ata_dev_pair(adev); struct ata_timing t, p; - static int via_clock = 33333; /* Bus clock in kHZ */ - unsigned long T = 1000000000 / via_clock; - unsigned long UT = T; + const int via_clock = 33333; /* Bus clock in kHz */ + const int T = 1000000000 / via_clock; + int UT = T; int ut; int offset = 3 - (2*ap->port_no) - adev->devno; diff --git a/drivers/ata/sata_dwc_460ex.c b/drivers/ata/sata_dwc_460ex.c index bec33d781ae0..e3263e961045 100644 --- a/drivers/ata/sata_dwc_460ex.c +++ b/drivers/ata/sata_dwc_460ex.c @@ -137,7 +137,11 @@ struct sata_dwc_device { #endif }; -#define SATA_DWC_QCMD_MAX 32 +/* + * Allow one extra special slot for commands and DMA management + * to account for libata internal commands. + */ +#define SATA_DWC_QCMD_MAX (ATA_MAX_QUEUE + 1) struct sata_dwc_device_port { struct sata_dwc_device *hsdev; diff --git a/drivers/ata/sata_gemini.c b/drivers/ata/sata_gemini.c index 00e1c7941d0e..b729e9919bb0 100644 --- a/drivers/ata/sata_gemini.c +++ b/drivers/ata/sata_gemini.c @@ -318,7 +318,6 @@ static int gemini_sata_probe(struct platform_device *pdev) struct device_node *np = dev->of_node; struct sata_gemini *sg; struct regmap *map; - struct resource *res; enum gemini_muxmode muxmode; u32 gmode; u32 gmask; @@ -329,11 +328,7 @@ static int gemini_sata_probe(struct platform_device *pdev) return -ENOMEM; sg->dev = dev; - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (!res) - return -ENODEV; - - sg->base = devm_ioremap_resource(dev, res); + sg->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(sg->base)) return PTR_ERR(sg->base); diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c index 1d6636ebaac5..f73b836047cf 100644 --- a/drivers/base/arch_topology.c +++ b/drivers/base/arch_topology.c @@ -667,6 +667,15 @@ const struct cpumask *cpu_coregroup_mask(int cpu) core_mask = &cpu_topology[cpu].llc_sibling; } + /* + * For systems with no shared cpu-side LLC but with clusters defined, + * extend core_mask to cluster_siblings. The sched domain builder will + * then remove MC as redundant with CLS if SCHED_CLUSTER is enabled. + */ + if (IS_ENABLED(CONFIG_SCHED_CLUSTER) && + cpumask_subset(core_mask, &cpu_topology[cpu].cluster_sibling)) + core_mask = &cpu_topology[cpu].cluster_sibling; + return core_mask; } @@ -684,7 +693,7 @@ void update_siblings_masks(unsigned int cpuid) for_each_online_cpu(cpu) { cpu_topo = &cpu_topology[cpu]; - if (cpuid_topo->llc_id == cpu_topo->llc_id) { + if (cpu_topo->llc_id != -1 && cpuid_topo->llc_id == cpu_topo->llc_id) { cpumask_set_cpu(cpu, &cpuid_topo->llc_sibling); cpumask_set_cpu(cpuid, &cpu_topo->llc_sibling); } diff --git a/drivers/base/dd.c b/drivers/base/dd.c index af6bea56f4e2..3fc3b5940bb3 100644 --- a/drivers/base/dd.c +++ b/drivers/base/dd.c @@ -296,6 +296,7 @@ int driver_deferred_probe_check_state(struct device *dev) return -EPROBE_DEFER; } +EXPORT_SYMBOL_GPL(driver_deferred_probe_check_state); static void deferred_probe_timeout_work_func(struct work_struct *work) { diff --git a/drivers/base/firmware_loader/main.c b/drivers/base/firmware_loader/main.c index 94d1789a233e..406a907a4cae 100644 --- a/drivers/base/firmware_loader/main.c +++ b/drivers/base/firmware_loader/main.c @@ -735,6 +735,8 @@ _request_firmware(const struct firmware **firmware_p, const char *name, size_t offset, u32 opt_flags) { struct firmware *fw = NULL; + struct cred *kern_cred = NULL; + const struct cred *old_cred; bool nondirect = false; int ret; @@ -751,6 +753,18 @@ _request_firmware(const struct firmware **firmware_p, const char *name, if (ret <= 0) /* error or already assigned */ goto out; + /* + * We are about to try to access the firmware file. Because we may have been + * called by a driver when serving an unrelated request from userland, we use + * the kernel credentials to read the file. + */ + kern_cred = prepare_kernel_cred(NULL); + if (!kern_cred) { + ret = -ENOMEM; + goto out; + } + old_cred = override_creds(kern_cred); + ret = fw_get_filesystem_firmware(device, fw->priv, "", NULL); /* Only full reads can support decompression, platform, and sysfs. */ @@ -776,6 +790,9 @@ _request_firmware(const struct firmware **firmware_p, const char *name, } else ret = assign_fw(fw, device); + revert_creds(old_cred); + put_cred(kern_cred); + out: if (ret < 0) { fw_abort_batch_reqs(fw); diff --git a/drivers/base/power/common.c b/drivers/base/power/common.c index bbddb267c2e6..72115917e0bd 100644 --- a/drivers/base/power/common.c +++ b/drivers/base/power/common.c @@ -172,10 +172,10 @@ EXPORT_SYMBOL_GPL(dev_pm_domain_attach_by_name); * @dev: Device to detach. * @power_off: Used to indicate whether we should power off the device. * - * This functions will reverse the actions from dev_pm_domain_attach() and - * dev_pm_domain_attach_by_id(), thus it detaches @dev from its PM domain. - * Typically it should be invoked during the remove phase, either from - * subsystem level code or from drivers. + * This functions will reverse the actions from dev_pm_domain_attach(), + * dev_pm_domain_attach_by_id() and dev_pm_domain_attach_by_name(), thus it + * detaches @dev from its PM domain. Typically it should be invoked during the + * remove phase, either from subsystem level code or from drivers. * * Callers must ensure proper synchronization of this function with power * management callbacks. diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c index 1ee878d126fd..739e52cd4aba 100644 --- a/drivers/base/power/domain.c +++ b/drivers/base/power/domain.c @@ -131,7 +131,7 @@ static const struct genpd_lock_ops genpd_spin_ops = { #define genpd_is_cpu_domain(genpd) (genpd->flags & GENPD_FLAG_CPU_DOMAIN) #define genpd_is_rpm_always_on(genpd) (genpd->flags & GENPD_FLAG_RPM_ALWAYS_ON) -static inline bool irq_safe_dev_in_no_sleep_domain(struct device *dev, +static inline bool irq_safe_dev_in_sleep_domain(struct device *dev, const struct generic_pm_domain *genpd) { bool ret; @@ -139,11 +139,14 @@ static inline bool irq_safe_dev_in_no_sleep_domain(struct device *dev, ret = pm_runtime_is_irq_safe(dev) && !genpd_is_irq_safe(genpd); /* - * Warn once if an IRQ safe device is attached to a no sleep domain, as - * to indicate a suboptimal configuration for PM. For an always on - * domain this isn't case, thus don't warn. + * Warn once if an IRQ safe device is attached to a domain, which + * callbacks are allowed to sleep. This indicates a suboptimal + * configuration for PM, but it doesn't matter for an always on domain. */ - if (ret && !genpd_is_always_on(genpd)) + if (genpd_is_always_on(genpd) || genpd_is_rpm_always_on(genpd)) + return ret; + + if (ret) dev_warn_once(dev, "PM domain %s will not be powered off\n", genpd->name); @@ -225,24 +228,23 @@ static void genpd_debug_remove(struct generic_pm_domain *genpd) static void genpd_update_accounting(struct generic_pm_domain *genpd) { - ktime_t delta, now; + u64 delta, now; - now = ktime_get(); - delta = ktime_sub(now, genpd->accounting_time); + now = ktime_get_mono_fast_ns(); + if (now <= genpd->accounting_time) + return; + + delta = now - genpd->accounting_time; /* * If genpd->status is active, it means we are just * out of off and so update the idle time and vice * versa. */ - if (genpd->status == GENPD_STATE_ON) { - int state_idx = genpd->state_idx; - - genpd->states[state_idx].idle_time = - ktime_add(genpd->states[state_idx].idle_time, delta); - } else { - genpd->on_time = ktime_add(genpd->on_time, delta); - } + if (genpd->status == GENPD_STATE_ON) + genpd->states[genpd->state_idx].idle_time += delta; + else + genpd->on_time += delta; genpd->accounting_time = now; } @@ -476,15 +478,16 @@ EXPORT_SYMBOL_GPL(dev_pm_genpd_set_performance_state); */ void dev_pm_genpd_set_next_wakeup(struct device *dev, ktime_t next) { - struct generic_pm_domain_data *gpd_data; struct generic_pm_domain *genpd; + struct gpd_timing_data *td; genpd = dev_to_genpd_safe(dev); if (!genpd) return; - gpd_data = to_gpd_data(dev->power.subsys_data->domain_data); - gpd_data->next_wakeup = next; + td = to_gpd_data(dev->power.subsys_data->domain_data)->td; + if (td) + td->next_wakeup = next; } EXPORT_SYMBOL_GPL(dev_pm_genpd_set_next_wakeup); @@ -506,6 +509,7 @@ static int _genpd_power_on(struct generic_pm_domain *genpd, bool timed) if (!genpd->power_on) goto out; + timed = timed && genpd->gd && !genpd->states[state_idx].fwnode; if (!timed) { ret = genpd->power_on(genpd); if (ret) @@ -524,7 +528,7 @@ static int _genpd_power_on(struct generic_pm_domain *genpd, bool timed) goto out; genpd->states[state_idx].power_on_latency_ns = elapsed_ns; - genpd->max_off_time_changed = true; + genpd->gd->max_off_time_changed = true; pr_debug("%s: Power-%s latency exceeded, new value %lld ns\n", genpd->name, "on", elapsed_ns); @@ -555,6 +559,7 @@ static int _genpd_power_off(struct generic_pm_domain *genpd, bool timed) if (!genpd->power_off) goto out; + timed = timed && genpd->gd && !genpd->states[state_idx].fwnode; if (!timed) { ret = genpd->power_off(genpd); if (ret) @@ -573,7 +578,7 @@ static int _genpd_power_off(struct generic_pm_domain *genpd, bool timed) goto out; genpd->states[state_idx].power_off_latency_ns = elapsed_ns; - genpd->max_off_time_changed = true; + genpd->gd->max_off_time_changed = true; pr_debug("%s: Power-%s latency exceeded, new value %lld ns\n", genpd->name, "off", elapsed_ns); @@ -649,18 +654,12 @@ static int genpd_power_off(struct generic_pm_domain *genpd, bool one_dev_on, } list_for_each_entry(pdd, &genpd->dev_list, list_node) { - enum pm_qos_flags_status stat; - - stat = dev_pm_qos_flags(pdd->dev, PM_QOS_FLAG_NO_POWER_OFF); - if (stat > PM_QOS_FLAGS_NONE) - return -EBUSY; - /* * Do not allow PM domain to be powered off, when an IRQ safe * device is part of a non-IRQ safe domain. */ if (!pm_runtime_suspended(pdd->dev) || - irq_safe_dev_in_no_sleep_domain(pdd->dev, genpd)) + irq_safe_dev_in_sleep_domain(pdd->dev, genpd)) not_suspended++; } @@ -775,25 +774,27 @@ static int genpd_dev_pm_qos_notifier(struct notifier_block *nb, dev = gpd_data->base.dev; for (;;) { - struct generic_pm_domain *genpd; + struct generic_pm_domain *genpd = ERR_PTR(-ENODATA); struct pm_domain_data *pdd; + struct gpd_timing_data *td; spin_lock_irq(&dev->power.lock); pdd = dev->power.subsys_data ? dev->power.subsys_data->domain_data : NULL; if (pdd) { - to_gpd_data(pdd)->td.constraint_changed = true; - genpd = dev_to_genpd(dev); - } else { - genpd = ERR_PTR(-ENODATA); + td = to_gpd_data(pdd)->td; + if (td) { + td->constraint_changed = true; + genpd = dev_to_genpd(dev); + } } spin_unlock_irq(&dev->power.lock); if (!IS_ERR(genpd)) { genpd_lock(genpd); - genpd->max_off_time_changed = true; + genpd->gd->max_off_time_changed = true; genpd_unlock(genpd); } @@ -879,9 +880,9 @@ static int genpd_runtime_suspend(struct device *dev) struct generic_pm_domain *genpd; bool (*suspend_ok)(struct device *__dev); struct generic_pm_domain_data *gpd_data = dev_gpd_data(dev); - struct gpd_timing_data *td = &gpd_data->td; + struct gpd_timing_data *td = gpd_data->td; bool runtime_pm = pm_runtime_enabled(dev); - ktime_t time_start; + ktime_t time_start = 0; s64 elapsed_ns; int ret; @@ -902,8 +903,7 @@ static int genpd_runtime_suspend(struct device *dev) return -EBUSY; /* Measure suspend latency. */ - time_start = 0; - if (runtime_pm) + if (td && runtime_pm) time_start = ktime_get(); ret = __genpd_runtime_suspend(dev); @@ -917,13 +917,13 @@ static int genpd_runtime_suspend(struct device *dev) } /* Update suspend latency value if the measured time exceeds it. */ - if (runtime_pm) { + if (td && runtime_pm) { elapsed_ns = ktime_to_ns(ktime_sub(ktime_get(), time_start)); if (elapsed_ns > td->suspend_latency_ns) { td->suspend_latency_ns = elapsed_ns; dev_dbg(dev, "suspend latency exceeded, %lld ns\n", elapsed_ns); - genpd->max_off_time_changed = true; + genpd->gd->max_off_time_changed = true; td->constraint_changed = true; } } @@ -932,7 +932,7 @@ static int genpd_runtime_suspend(struct device *dev) * If power.irq_safe is set, this routine may be run with * IRQs disabled, so suspend only if the PM domain also is irq_safe. */ - if (irq_safe_dev_in_no_sleep_domain(dev, genpd)) + if (irq_safe_dev_in_sleep_domain(dev, genpd)) return 0; genpd_lock(genpd); @@ -955,12 +955,11 @@ static int genpd_runtime_resume(struct device *dev) { struct generic_pm_domain *genpd; struct generic_pm_domain_data *gpd_data = dev_gpd_data(dev); - struct gpd_timing_data *td = &gpd_data->td; - bool runtime_pm = pm_runtime_enabled(dev); - ktime_t time_start; + struct gpd_timing_data *td = gpd_data->td; + bool timed = td && pm_runtime_enabled(dev); + ktime_t time_start = 0; s64 elapsed_ns; int ret; - bool timed = true; dev_dbg(dev, "%s()\n", __func__); @@ -972,10 +971,8 @@ static int genpd_runtime_resume(struct device *dev) * As we don't power off a non IRQ safe domain, which holds * an IRQ safe device, we don't need to restore power to it. */ - if (irq_safe_dev_in_no_sleep_domain(dev, genpd)) { - timed = false; + if (irq_safe_dev_in_sleep_domain(dev, genpd)) goto out; - } genpd_lock(genpd); ret = genpd_power_on(genpd, 0); @@ -988,8 +985,7 @@ static int genpd_runtime_resume(struct device *dev) out: /* Measure resume latency. */ - time_start = 0; - if (timed && runtime_pm) + if (timed) time_start = ktime_get(); ret = genpd_start_dev(genpd, dev); @@ -1001,13 +997,13 @@ static int genpd_runtime_resume(struct device *dev) goto err_stop; /* Update resume latency value if the measured time exceeds it. */ - if (timed && runtime_pm) { + if (timed) { elapsed_ns = ktime_to_ns(ktime_sub(ktime_get(), time_start)); if (elapsed_ns > td->resume_latency_ns) { td->resume_latency_ns = elapsed_ns; dev_dbg(dev, "resume latency exceeded, %lld ns\n", elapsed_ns); - genpd->max_off_time_changed = true; + genpd->gd->max_off_time_changed = true; td->constraint_changed = true; } } @@ -1500,9 +1496,11 @@ EXPORT_SYMBOL_GPL(dev_pm_genpd_resume); #endif /* CONFIG_PM_SLEEP */ -static struct generic_pm_domain_data *genpd_alloc_dev_data(struct device *dev) +static struct generic_pm_domain_data *genpd_alloc_dev_data(struct device *dev, + bool has_governor) { struct generic_pm_domain_data *gpd_data; + struct gpd_timing_data *td; int ret; ret = dev_pm_get_subsys_data(dev); @@ -1516,26 +1514,38 @@ static struct generic_pm_domain_data *genpd_alloc_dev_data(struct device *dev) } gpd_data->base.dev = dev; - gpd_data->td.constraint_changed = true; - gpd_data->td.effective_constraint_ns = PM_QOS_RESUME_LATENCY_NO_CONSTRAINT_NS; gpd_data->nb.notifier_call = genpd_dev_pm_qos_notifier; - gpd_data->next_wakeup = KTIME_MAX; - spin_lock_irq(&dev->power.lock); + /* Allocate data used by a governor. */ + if (has_governor) { + td = kzalloc(sizeof(*td), GFP_KERNEL); + if (!td) { + ret = -ENOMEM; + goto err_free; + } - if (dev->power.subsys_data->domain_data) { - ret = -EINVAL; - goto err_free; + td->constraint_changed = true; + td->effective_constraint_ns = PM_QOS_RESUME_LATENCY_NO_CONSTRAINT_NS; + td->next_wakeup = KTIME_MAX; + gpd_data->td = td; } - dev->power.subsys_data->domain_data = &gpd_data->base; + spin_lock_irq(&dev->power.lock); + + if (dev->power.subsys_data->domain_data) + ret = -EINVAL; + else + dev->power.subsys_data->domain_data = &gpd_data->base; spin_unlock_irq(&dev->power.lock); + if (ret) + goto err_free; + return gpd_data; err_free: - spin_unlock_irq(&dev->power.lock); + kfree(gpd_data->td); kfree(gpd_data); err_put: dev_pm_put_subsys_data(dev); @@ -1551,6 +1561,7 @@ static void genpd_free_dev_data(struct device *dev, spin_unlock_irq(&dev->power.lock); + kfree(gpd_data->td); kfree(gpd_data); dev_pm_put_subsys_data(dev); } @@ -1607,6 +1618,7 @@ static int genpd_get_cpu(struct generic_pm_domain *genpd, struct device *dev) static int genpd_add_device(struct generic_pm_domain *genpd, struct device *dev, struct device *base_dev) { + struct genpd_governor_data *gd = genpd->gd; struct generic_pm_domain_data *gpd_data; int ret; @@ -1615,7 +1627,7 @@ static int genpd_add_device(struct generic_pm_domain *genpd, struct device *dev, if (IS_ERR_OR_NULL(genpd) || IS_ERR_OR_NULL(dev)) return -EINVAL; - gpd_data = genpd_alloc_dev_data(dev); + gpd_data = genpd_alloc_dev_data(dev, gd); if (IS_ERR(gpd_data)) return PTR_ERR(gpd_data); @@ -1631,7 +1643,8 @@ static int genpd_add_device(struct generic_pm_domain *genpd, struct device *dev, dev_pm_domain_set(dev, &genpd->domain); genpd->device_count++; - genpd->max_off_time_changed = true; + if (gd) + gd->max_off_time_changed = true; list_add_tail(&gpd_data->base.list_node, &genpd->dev_list); @@ -1685,7 +1698,8 @@ static int genpd_remove_device(struct generic_pm_domain *genpd, } genpd->device_count--; - genpd->max_off_time_changed = true; + if (genpd->gd) + genpd->gd->max_off_time_changed = true; genpd_clear_cpumask(genpd, gpd_data->cpu); dev_pm_domain_set(dev, NULL); @@ -1958,6 +1972,53 @@ static int genpd_set_default_power_state(struct generic_pm_domain *genpd) return 0; } +static int genpd_alloc_data(struct generic_pm_domain *genpd) +{ + struct genpd_governor_data *gd = NULL; + int ret; + + if (genpd_is_cpu_domain(genpd) && + !zalloc_cpumask_var(&genpd->cpus, GFP_KERNEL)) + return -ENOMEM; + + if (genpd->gov) { + gd = kzalloc(sizeof(*gd), GFP_KERNEL); + if (!gd) { + ret = -ENOMEM; + goto free; + } + + gd->max_off_time_ns = -1; + gd->max_off_time_changed = true; + gd->next_wakeup = KTIME_MAX; + } + + /* Use only one "off" state if there were no states declared */ + if (genpd->state_count == 0) { + ret = genpd_set_default_power_state(genpd); + if (ret) + goto free; + } + + genpd->gd = gd; + return 0; + +free: + if (genpd_is_cpu_domain(genpd)) + free_cpumask_var(genpd->cpus); + kfree(gd); + return ret; +} + +static void genpd_free_data(struct generic_pm_domain *genpd) +{ + if (genpd_is_cpu_domain(genpd)) + free_cpumask_var(genpd->cpus); + if (genpd->free_states) + genpd->free_states(genpd->states, genpd->state_count); + kfree(genpd->gd); +} + static void genpd_lock_init(struct generic_pm_domain *genpd) { if (genpd->flags & GENPD_FLAG_IRQ_SAFE) { @@ -1995,11 +2056,9 @@ int pm_genpd_init(struct generic_pm_domain *genpd, atomic_set(&genpd->sd_count, 0); genpd->status = is_off ? GENPD_STATE_OFF : GENPD_STATE_ON; genpd->device_count = 0; - genpd->max_off_time_ns = -1; - genpd->max_off_time_changed = true; genpd->provider = NULL; genpd->has_provider = false; - genpd->accounting_time = ktime_get(); + genpd->accounting_time = ktime_get_mono_fast_ns(); genpd->domain.ops.runtime_suspend = genpd_runtime_suspend; genpd->domain.ops.runtime_resume = genpd_runtime_resume; genpd->domain.ops.prepare = genpd_prepare; @@ -2017,26 +2076,22 @@ int pm_genpd_init(struct generic_pm_domain *genpd, genpd->dev_ops.start = pm_clk_resume; } + /* The always-on governor works better with the corresponding flag. */ + if (gov == &pm_domain_always_on_gov) + genpd->flags |= GENPD_FLAG_RPM_ALWAYS_ON; + /* Always-on domains must be powered on at initialization. */ if ((genpd_is_always_on(genpd) || genpd_is_rpm_always_on(genpd)) && !genpd_status_on(genpd)) return -EINVAL; - if (genpd_is_cpu_domain(genpd) && - !zalloc_cpumask_var(&genpd->cpus, GFP_KERNEL)) - return -ENOMEM; - - /* Use only one "off" state if there were no states declared */ - if (genpd->state_count == 0) { - ret = genpd_set_default_power_state(genpd); - if (ret) { - if (genpd_is_cpu_domain(genpd)) - free_cpumask_var(genpd->cpus); - return ret; - } - } else if (!gov && genpd->state_count > 1) { + /* Multiple states but no governor doesn't make sense. */ + if (!gov && genpd->state_count > 1) pr_warn("%s: no governor for states\n", genpd->name); - } + + ret = genpd_alloc_data(genpd); + if (ret) + return ret; device_initialize(&genpd->dev); dev_set_name(&genpd->dev, "%s", genpd->name); @@ -2081,10 +2136,7 @@ static int genpd_remove(struct generic_pm_domain *genpd) genpd_unlock(genpd); genpd_debug_remove(genpd); cancel_work_sync(&genpd->power_off_work); - if (genpd_is_cpu_domain(genpd)) - free_cpumask_var(genpd->cpus); - if (genpd->free_states) - genpd->free_states(genpd->states, genpd->state_count); + genpd_free_data(genpd); pr_debug("%s: removed %s\n", __func__, genpd->name); @@ -3163,6 +3215,7 @@ static int sub_domains_show(struct seq_file *s, void *data) static int idle_states_show(struct seq_file *s, void *data) { struct generic_pm_domain *genpd = s->private; + u64 now, delta, idle_time = 0; unsigned int i; int ret = 0; @@ -3173,17 +3226,19 @@ static int idle_states_show(struct seq_file *s, void *data) seq_puts(s, "State Time Spent(ms) Usage Rejected\n"); for (i = 0; i < genpd->state_count; i++) { - ktime_t delta = 0; - s64 msecs; + idle_time += genpd->states[i].idle_time; - if ((genpd->status == GENPD_STATE_OFF) && - (genpd->state_idx == i)) - delta = ktime_sub(ktime_get(), genpd->accounting_time); + if (genpd->status == GENPD_STATE_OFF && genpd->state_idx == i) { + now = ktime_get_mono_fast_ns(); + if (now > genpd->accounting_time) { + delta = now - genpd->accounting_time; + idle_time += delta; + } + } - msecs = ktime_to_ms( - ktime_add(genpd->states[i].idle_time, delta)); - seq_printf(s, "S%-13i %-14lld %-14llu %llu\n", i, msecs, - genpd->states[i].usage, genpd->states[i].rejected); + do_div(idle_time, NSEC_PER_MSEC); + seq_printf(s, "S%-13i %-14llu %-14llu %llu\n", i, idle_time, + genpd->states[i].usage, genpd->states[i].rejected); } genpd_unlock(genpd); @@ -3193,18 +3248,22 @@ static int idle_states_show(struct seq_file *s, void *data) static int active_time_show(struct seq_file *s, void *data) { struct generic_pm_domain *genpd = s->private; - ktime_t delta = 0; + u64 now, on_time, delta = 0; int ret = 0; ret = genpd_lock_interruptible(genpd); if (ret) return -ERESTARTSYS; - if (genpd->status == GENPD_STATE_ON) - delta = ktime_sub(ktime_get(), genpd->accounting_time); + if (genpd->status == GENPD_STATE_ON) { + now = ktime_get_mono_fast_ns(); + if (now > genpd->accounting_time) + delta = now - genpd->accounting_time; + } - seq_printf(s, "%lld ms\n", ktime_to_ms( - ktime_add(genpd->on_time, delta))); + on_time = genpd->on_time + delta; + do_div(on_time, NSEC_PER_MSEC); + seq_printf(s, "%llu ms\n", on_time); genpd_unlock(genpd); return ret; @@ -3213,7 +3272,7 @@ static int active_time_show(struct seq_file *s, void *data) static int total_idle_time_show(struct seq_file *s, void *data) { struct generic_pm_domain *genpd = s->private; - ktime_t delta = 0, total = 0; + u64 now, delta, total = 0; unsigned int i; int ret = 0; @@ -3222,16 +3281,19 @@ static int total_idle_time_show(struct seq_file *s, void *data) return -ERESTARTSYS; for (i = 0; i < genpd->state_count; i++) { + total += genpd->states[i].idle_time; - if ((genpd->status == GENPD_STATE_OFF) && - (genpd->state_idx == i)) - delta = ktime_sub(ktime_get(), genpd->accounting_time); - - total = ktime_add(total, genpd->states[i].idle_time); + if (genpd->status == GENPD_STATE_OFF && genpd->state_idx == i) { + now = ktime_get_mono_fast_ns(); + if (now > genpd->accounting_time) { + delta = now - genpd->accounting_time; + total += delta; + } + } } - total = ktime_add(total, delta); - seq_printf(s, "%lld ms\n", ktime_to_ms(total)); + do_div(total, NSEC_PER_MSEC); + seq_printf(s, "%llu ms\n", total); genpd_unlock(genpd); return ret; diff --git a/drivers/base/power/domain_governor.c b/drivers/base/power/domain_governor.c index cd08c5885190..282a3a135827 100644 --- a/drivers/base/power/domain_governor.c +++ b/drivers/base/power/domain_governor.c @@ -18,6 +18,8 @@ static int dev_update_qos_constraint(struct device *dev, void *data) s64 constraint_ns; if (dev->power.subsys_data && dev->power.subsys_data->domain_data) { + struct gpd_timing_data *td = dev_gpd_data(dev)->td; + /* * Only take suspend-time QoS constraints of devices into * account, because constraints updated after the device has @@ -25,7 +27,8 @@ static int dev_update_qos_constraint(struct device *dev, void *data) * anyway. In order for them to take effect, the device has to * be resumed and suspended again. */ - constraint_ns = dev_gpd_data(dev)->td.effective_constraint_ns; + constraint_ns = td ? td->effective_constraint_ns : + PM_QOS_RESUME_LATENCY_NO_CONSTRAINT_NS; } else { /* * The child is not in a domain and there's no info on its @@ -49,7 +52,7 @@ static int dev_update_qos_constraint(struct device *dev, void *data) */ static bool default_suspend_ok(struct device *dev) { - struct gpd_timing_data *td = &dev_gpd_data(dev)->td; + struct gpd_timing_data *td = dev_gpd_data(dev)->td; unsigned long flags; s64 constraint_ns; @@ -136,26 +139,28 @@ static void update_domain_next_wakeup(struct generic_pm_domain *genpd, ktime_t n * is able to enter its optimal idle state. */ list_for_each_entry(pdd, &genpd->dev_list, list_node) { - next_wakeup = to_gpd_data(pdd)->next_wakeup; + next_wakeup = to_gpd_data(pdd)->td->next_wakeup; if (next_wakeup != KTIME_MAX && !ktime_before(next_wakeup, now)) if (ktime_before(next_wakeup, domain_wakeup)) domain_wakeup = next_wakeup; } list_for_each_entry(link, &genpd->parent_links, parent_node) { - next_wakeup = link->child->next_wakeup; + struct genpd_governor_data *cgd = link->child->gd; + + next_wakeup = cgd ? cgd->next_wakeup : KTIME_MAX; if (next_wakeup != KTIME_MAX && !ktime_before(next_wakeup, now)) if (ktime_before(next_wakeup, domain_wakeup)) domain_wakeup = next_wakeup; } - genpd->next_wakeup = domain_wakeup; + genpd->gd->next_wakeup = domain_wakeup; } static bool next_wakeup_allows_state(struct generic_pm_domain *genpd, unsigned int state, ktime_t now) { - ktime_t domain_wakeup = genpd->next_wakeup; + ktime_t domain_wakeup = genpd->gd->next_wakeup; s64 idle_time_ns, min_sleep_ns; min_sleep_ns = genpd->states[state].power_off_latency_ns + @@ -185,8 +190,9 @@ static bool __default_power_down_ok(struct dev_pm_domain *pd, * All subdomains have been powered off already at this point. */ list_for_each_entry(link, &genpd->parent_links, parent_node) { - struct generic_pm_domain *sd = link->child; - s64 sd_max_off_ns = sd->max_off_time_ns; + struct genpd_governor_data *cgd = link->child->gd; + + s64 sd_max_off_ns = cgd ? cgd->max_off_time_ns : -1; if (sd_max_off_ns < 0) continue; @@ -215,7 +221,7 @@ static bool __default_power_down_ok(struct dev_pm_domain *pd, * domain to turn off and on (that's how much time it will * have to wait worst case). */ - td = &to_gpd_data(pdd)->td; + td = to_gpd_data(pdd)->td; constraint_ns = td->effective_constraint_ns; /* * Zero means "no suspend at all" and this runs only when all @@ -244,7 +250,7 @@ static bool __default_power_down_ok(struct dev_pm_domain *pd, * time and the time needed to turn the domain on is the maximum * theoretical time this domain can spend in the "off" state. */ - genpd->max_off_time_ns = min_off_time_ns - + genpd->gd->max_off_time_ns = min_off_time_ns - genpd->states[state].power_on_latency_ns; return true; } @@ -259,6 +265,7 @@ static bool __default_power_down_ok(struct dev_pm_domain *pd, static bool _default_power_down_ok(struct dev_pm_domain *pd, ktime_t now) { struct generic_pm_domain *genpd = pd_to_genpd(pd); + struct genpd_governor_data *gd = genpd->gd; int state_idx = genpd->state_count - 1; struct gpd_link *link; @@ -269,11 +276,11 @@ static bool _default_power_down_ok(struct dev_pm_domain *pd, ktime_t now) * cannot be met. */ update_domain_next_wakeup(genpd, now); - if ((genpd->flags & GENPD_FLAG_MIN_RESIDENCY) && (genpd->next_wakeup != KTIME_MAX)) { + if ((genpd->flags & GENPD_FLAG_MIN_RESIDENCY) && (gd->next_wakeup != KTIME_MAX)) { /* Let's find out the deepest domain idle state, the devices prefer */ while (state_idx >= 0) { if (next_wakeup_allows_state(genpd, state_idx, now)) { - genpd->max_off_time_changed = true; + gd->max_off_time_changed = true; break; } state_idx--; @@ -281,14 +288,14 @@ static bool _default_power_down_ok(struct dev_pm_domain *pd, ktime_t now) if (state_idx < 0) { state_idx = 0; - genpd->cached_power_down_ok = false; + gd->cached_power_down_ok = false; goto done; } } - if (!genpd->max_off_time_changed) { - genpd->state_idx = genpd->cached_power_down_state_idx; - return genpd->cached_power_down_ok; + if (!gd->max_off_time_changed) { + genpd->state_idx = gd->cached_power_down_state_idx; + return gd->cached_power_down_ok; } /* @@ -297,12 +304,16 @@ static bool _default_power_down_ok(struct dev_pm_domain *pd, ktime_t now) * going to be called for any parent until this instance * returns. */ - list_for_each_entry(link, &genpd->child_links, child_node) - link->parent->max_off_time_changed = true; + list_for_each_entry(link, &genpd->child_links, child_node) { + struct genpd_governor_data *pgd = link->parent->gd; + + if (pgd) + pgd->max_off_time_changed = true; + } - genpd->max_off_time_ns = -1; - genpd->max_off_time_changed = false; - genpd->cached_power_down_ok = true; + gd->max_off_time_ns = -1; + gd->max_off_time_changed = false; + gd->cached_power_down_ok = true; /* * Find a state to power down to, starting from the state @@ -310,7 +321,7 @@ static bool _default_power_down_ok(struct dev_pm_domain *pd, ktime_t now) */ while (!__default_power_down_ok(pd, state_idx)) { if (state_idx == 0) { - genpd->cached_power_down_ok = false; + gd->cached_power_down_ok = false; break; } state_idx--; @@ -318,8 +329,8 @@ static bool _default_power_down_ok(struct dev_pm_domain *pd, ktime_t now) done: genpd->state_idx = state_idx; - genpd->cached_power_down_state_idx = genpd->state_idx; - return genpd->cached_power_down_ok; + gd->cached_power_down_state_idx = genpd->state_idx; + return gd->cached_power_down_ok; } static bool default_power_down_ok(struct dev_pm_domain *pd) @@ -327,11 +338,6 @@ static bool default_power_down_ok(struct dev_pm_domain *pd) return _default_power_down_ok(pd, ktime_get()); } -static bool always_on_power_down_ok(struct dev_pm_domain *domain) -{ - return false; -} - #ifdef CONFIG_CPU_IDLE static bool cpu_power_down_ok(struct dev_pm_domain *pd) { @@ -401,6 +407,5 @@ struct dev_power_governor simple_qos_governor = { * pm_genpd_gov_always_on - A governor implementing an always-on policy */ struct dev_power_governor pm_domain_always_on_gov = { - .power_down_ok = always_on_power_down_ok, .suspend_ok = default_suspend_ok, }; diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c index d4059e6ffeae..676dc72d912d 100644 --- a/drivers/base/power/runtime.c +++ b/drivers/base/power/runtime.c @@ -263,7 +263,7 @@ static int rpm_check_suspend_allowed(struct device *dev) retval = -EINVAL; else if (dev->power.disable_depth > 0) retval = -EACCES; - else if (atomic_read(&dev->power.usage_count) > 0) + else if (atomic_read(&dev->power.usage_count)) retval = -EAGAIN; else if (!dev->power.ignore_children && atomic_read(&dev->power.child_count)) @@ -1039,13 +1039,33 @@ int pm_schedule_suspend(struct device *dev, unsigned int delay) } EXPORT_SYMBOL_GPL(pm_schedule_suspend); +static int rpm_drop_usage_count(struct device *dev) +{ + int ret; + + ret = atomic_sub_return(1, &dev->power.usage_count); + if (ret >= 0) + return ret; + + /* + * Because rpm_resume() does not check the usage counter, it will resume + * the device even if the usage counter is 0 or negative, so it is + * sufficient to increment the usage counter here to reverse the change + * made above. + */ + atomic_inc(&dev->power.usage_count); + dev_warn(dev, "Runtime PM usage count underflow!\n"); + return -EINVAL; +} + /** * __pm_runtime_idle - Entry point for runtime idle operations. * @dev: Device to send idle notification for. * @rpmflags: Flag bits. * * If the RPM_GET_PUT flag is set, decrement the device's usage count and - * return immediately if it is larger than zero. Then carry out an idle + * return immediately if it is larger than zero (if it becomes negative, log a + * warning, increment it, and return an error). Then carry out an idle * notification, either synchronous or asynchronous. * * This routine may be called in atomic context if the RPM_ASYNC flag is set, @@ -1057,7 +1077,10 @@ int __pm_runtime_idle(struct device *dev, int rpmflags) int retval; if (rpmflags & RPM_GET_PUT) { - if (!atomic_dec_and_test(&dev->power.usage_count)) { + retval = rpm_drop_usage_count(dev); + if (retval < 0) { + return retval; + } else if (retval > 0) { trace_rpm_usage_rcuidle(dev, rpmflags); return 0; } @@ -1079,7 +1102,8 @@ EXPORT_SYMBOL_GPL(__pm_runtime_idle); * @rpmflags: Flag bits. * * If the RPM_GET_PUT flag is set, decrement the device's usage count and - * return immediately if it is larger than zero. Then carry out a suspend, + * return immediately if it is larger than zero (if it becomes negative, log a + * warning, increment it, and return an error). Then carry out a suspend, * either synchronous or asynchronous. * * This routine may be called in atomic context if the RPM_ASYNC flag is set, @@ -1091,7 +1115,10 @@ int __pm_runtime_suspend(struct device *dev, int rpmflags) int retval; if (rpmflags & RPM_GET_PUT) { - if (!atomic_dec_and_test(&dev->power.usage_count)) { + retval = rpm_drop_usage_count(dev); + if (retval < 0) { + return retval; + } else if (retval > 0) { trace_rpm_usage_rcuidle(dev, rpmflags); return 0; } @@ -1210,12 +1237,13 @@ int __pm_runtime_set_status(struct device *dev, unsigned int status) { struct device *parent = dev->parent; bool notify_parent = false; + unsigned long flags; int error = 0; if (status != RPM_ACTIVE && status != RPM_SUSPENDED) return -EINVAL; - spin_lock_irq(&dev->power.lock); + spin_lock_irqsave(&dev->power.lock, flags); /* * Prevent PM-runtime from being enabled for the device or return an @@ -1226,7 +1254,7 @@ int __pm_runtime_set_status(struct device *dev, unsigned int status) else error = -EAGAIN; - spin_unlock_irq(&dev->power.lock); + spin_unlock_irqrestore(&dev->power.lock, flags); if (error) return error; @@ -1247,7 +1275,7 @@ int __pm_runtime_set_status(struct device *dev, unsigned int status) device_links_read_unlock(idx); } - spin_lock_irq(&dev->power.lock); + spin_lock_irqsave(&dev->power.lock, flags); if (dev->power.runtime_status == status || !parent) goto out_set; @@ -1288,7 +1316,7 @@ int __pm_runtime_set_status(struct device *dev, unsigned int status) dev->power.runtime_error = 0; out: - spin_unlock_irq(&dev->power.lock); + spin_unlock_irqrestore(&dev->power.lock, flags); if (notify_parent) pm_request_idle(parent); @@ -1527,14 +1555,17 @@ EXPORT_SYMBOL_GPL(pm_runtime_forbid); */ void pm_runtime_allow(struct device *dev) { + int ret; + spin_lock_irq(&dev->power.lock); if (dev->power.runtime_auto) goto out; dev->power.runtime_auto = true; - if (atomic_dec_and_test(&dev->power.usage_count)) + ret = rpm_drop_usage_count(dev); + if (ret == 0) rpm_idle(dev, RPM_AUTO | RPM_ASYNC); - else + else if (ret > 0) trace_rpm_usage_rcuidle(dev, RPM_AUTO | RPM_ASYNC); out: diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c index a57d469676ca..11a4ffe91367 100644 --- a/drivers/base/power/wakeup.c +++ b/drivers/base/power/wakeup.c @@ -930,6 +930,7 @@ bool pm_wakeup_pending(void) return ret || atomic_read(&pm_abort_suspend) > 0; } +EXPORT_SYMBOL_GPL(pm_wakeup_pending); void pm_system_wakeup(void) { diff --git a/drivers/base/property.c b/drivers/base/property.c index c0e94cce9c29..3adcac2c78fa 100644 --- a/drivers/base/property.c +++ b/drivers/base/property.c @@ -47,12 +47,14 @@ bool fwnode_property_present(const struct fwnode_handle *fwnode, { bool ret; + if (IS_ERR_OR_NULL(fwnode)) + return false; + ret = fwnode_call_bool_op(fwnode, property_present, propname); - if (ret == false && !IS_ERR_OR_NULL(fwnode) && - !IS_ERR_OR_NULL(fwnode->secondary)) - ret = fwnode_call_bool_op(fwnode->secondary, property_present, - propname); - return ret; + if (ret) + return ret; + + return fwnode_call_bool_op(fwnode->secondary, property_present, propname); } EXPORT_SYMBOL_GPL(fwnode_property_present); @@ -66,6 +68,9 @@ EXPORT_SYMBOL_GPL(fwnode_property_present); * Function reads an array of u8 properties with @propname from the device * firmware description and stores them to @val if found. * + * It's recommended to call device_property_count_u8() instead of calling + * this function with @val equals %NULL and @nval equals 0. + * * Return: number of values if @val was %NULL, * %0 if the property was found (success), * %-EINVAL if given arguments are not valid, @@ -91,6 +96,9 @@ EXPORT_SYMBOL_GPL(device_property_read_u8_array); * Function reads an array of u16 properties with @propname from the device * firmware description and stores them to @val if found. * + * It's recommended to call device_property_count_u16() instead of calling + * this function with @val equals %NULL and @nval equals 0. + * * Return: number of values if @val was %NULL, * %0 if the property was found (success), * %-EINVAL if given arguments are not valid, @@ -116,6 +124,9 @@ EXPORT_SYMBOL_GPL(device_property_read_u16_array); * Function reads an array of u32 properties with @propname from the device * firmware description and stores them to @val if found. * + * It's recommended to call device_property_count_u32() instead of calling + * this function with @val equals %NULL and @nval equals 0. + * * Return: number of values if @val was %NULL, * %0 if the property was found (success), * %-EINVAL if given arguments are not valid, @@ -141,6 +152,9 @@ EXPORT_SYMBOL_GPL(device_property_read_u32_array); * Function reads an array of u64 properties with @propname from the device * firmware description and stores them to @val if found. * + * It's recommended to call device_property_count_u64() instead of calling + * this function with @val equals %NULL and @nval equals 0. + * * Return: number of values if @val was %NULL, * %0 if the property was found (success), * %-EINVAL if given arguments are not valid, @@ -166,6 +180,9 @@ EXPORT_SYMBOL_GPL(device_property_read_u64_array); * Function reads an array of string properties with @propname from the device * firmware description and stores them to @val if found. * + * It's recommended to call device_property_string_array_count() instead of calling + * this function with @val equals %NULL and @nval equals 0. + * * Return: number of values read on success if @val is non-NULL, * number of values available on success if @val is NULL, * %-EINVAL if given arguments are not valid, @@ -232,15 +249,16 @@ static int fwnode_property_read_int_array(const struct fwnode_handle *fwnode, { int ret; + if (IS_ERR_OR_NULL(fwnode)) + return -EINVAL; + ret = fwnode_call_int_op(fwnode, property_read_int_array, propname, elem_size, val, nval); - if (ret == -EINVAL && !IS_ERR_OR_NULL(fwnode) && - !IS_ERR_OR_NULL(fwnode->secondary)) - ret = fwnode_call_int_op( - fwnode->secondary, property_read_int_array, propname, - elem_size, val, nval); + if (ret != -EINVAL) + return ret; - return ret; + return fwnode_call_int_op(fwnode->secondary, property_read_int_array, propname, + elem_size, val, nval); } /** @@ -253,6 +271,9 @@ static int fwnode_property_read_int_array(const struct fwnode_handle *fwnode, * Read an array of u8 properties with @propname from @fwnode and stores them to * @val if found. * + * It's recommended to call fwnode_property_count_u8() instead of calling + * this function with @val equals %NULL and @nval equals 0. + * * Return: number of values if @val was %NULL, * %0 if the property was found (success), * %-EINVAL if given arguments are not valid, @@ -279,6 +300,9 @@ EXPORT_SYMBOL_GPL(fwnode_property_read_u8_array); * Read an array of u16 properties with @propname from @fwnode and store them to * @val if found. * + * It's recommended to call fwnode_property_count_u16() instead of calling + * this function with @val equals %NULL and @nval equals 0. + * * Return: number of values if @val was %NULL, * %0 if the property was found (success), * %-EINVAL if given arguments are not valid, @@ -305,6 +329,9 @@ EXPORT_SYMBOL_GPL(fwnode_property_read_u16_array); * Read an array of u32 properties with @propname from @fwnode store them to * @val if found. * + * It's recommended to call fwnode_property_count_u32() instead of calling + * this function with @val equals %NULL and @nval equals 0. + * * Return: number of values if @val was %NULL, * %0 if the property was found (success), * %-EINVAL if given arguments are not valid, @@ -331,6 +358,9 @@ EXPORT_SYMBOL_GPL(fwnode_property_read_u32_array); * Read an array of u64 properties with @propname from @fwnode and store them to * @val if found. * + * It's recommended to call fwnode_property_count_u64() instead of calling + * this function with @val equals %NULL and @nval equals 0. + * * Return: number of values if @val was %NULL, * %0 if the property was found (success), * %-EINVAL if given arguments are not valid, @@ -357,6 +387,9 @@ EXPORT_SYMBOL_GPL(fwnode_property_read_u64_array); * Read an string list property @propname from the given firmware node and store * them to @val if found. * + * It's recommended to call fwnode_property_string_array_count() instead of calling + * this function with @val equals %NULL and @nval equals 0. + * * Return: number of values read on success if @val is non-NULL, * number of values available on success if @val is NULL, * %-EINVAL if given arguments are not valid, @@ -371,14 +404,16 @@ int fwnode_property_read_string_array(const struct fwnode_handle *fwnode, { int ret; + if (IS_ERR_OR_NULL(fwnode)) + return -EINVAL; + ret = fwnode_call_int_op(fwnode, property_read_string_array, propname, val, nval); - if (ret == -EINVAL && !IS_ERR_OR_NULL(fwnode) && - !IS_ERR_OR_NULL(fwnode->secondary)) - ret = fwnode_call_int_op(fwnode->secondary, - property_read_string_array, propname, - val, nval); - return ret; + if (ret != -EINVAL) + return ret; + + return fwnode_call_int_op(fwnode->secondary, property_read_string_array, propname, + val, nval); } EXPORT_SYMBOL_GPL(fwnode_property_read_string_array); @@ -480,15 +515,19 @@ int fwnode_property_get_reference_args(const struct fwnode_handle *fwnode, { int ret; + if (IS_ERR_OR_NULL(fwnode)) + return -ENOENT; + ret = fwnode_call_int_op(fwnode, get_reference_args, prop, nargs_prop, nargs, index, args); + if (ret == 0) + return ret; - if (ret < 0 && !IS_ERR_OR_NULL(fwnode) && - !IS_ERR_OR_NULL(fwnode->secondary)) - ret = fwnode_call_int_op(fwnode->secondary, get_reference_args, - prop, nargs_prop, nargs, index, args); + if (IS_ERR_OR_NULL(fwnode->secondary)) + return ret; - return ret; + return fwnode_call_int_op(fwnode->secondary, get_reference_args, prop, nargs_prop, + nargs, index, args); } EXPORT_SYMBOL_GPL(fwnode_property_get_reference_args); @@ -587,17 +626,17 @@ EXPORT_SYMBOL_GPL(fwnode_get_next_parent); */ struct device *fwnode_get_next_parent_dev(struct fwnode_handle *fwnode) { + struct fwnode_handle *parent; struct device *dev; - fwnode_handle_get(fwnode); - do { - fwnode = fwnode_get_next_parent(fwnode); - if (!fwnode) - return NULL; - dev = get_dev_from_fwnode(fwnode); - } while (!dev); - fwnode_handle_put(fwnode); - return dev; + fwnode_for_each_parent_node(fwnode, parent) { + dev = get_dev_from_fwnode(parent); + if (dev) { + fwnode_handle_put(parent); + return dev; + } + } + return NULL; } /** @@ -608,13 +647,11 @@ struct device *fwnode_get_next_parent_dev(struct fwnode_handle *fwnode) */ unsigned int fwnode_count_parents(const struct fwnode_handle *fwnode) { - struct fwnode_handle *__fwnode; - unsigned int count; - - __fwnode = fwnode_get_parent(fwnode); + struct fwnode_handle *parent; + unsigned int count = 0; - for (count = 0; __fwnode; count++) - __fwnode = fwnode_get_next_parent(__fwnode); + fwnode_for_each_parent_node(fwnode, parent) + count++; return count; } @@ -635,40 +672,43 @@ EXPORT_SYMBOL_GPL(fwnode_count_parents); struct fwnode_handle *fwnode_get_nth_parent(struct fwnode_handle *fwnode, unsigned int depth) { - unsigned int i; + struct fwnode_handle *parent; - fwnode_handle_get(fwnode); + if (depth == 0) + return fwnode_handle_get(fwnode); - for (i = 0; i < depth && fwnode; i++) - fwnode = fwnode_get_next_parent(fwnode); - - return fwnode; + fwnode_for_each_parent_node(fwnode, parent) { + if (--depth == 0) + return parent; + } + return NULL; } EXPORT_SYMBOL_GPL(fwnode_get_nth_parent); /** - * fwnode_is_ancestor_of - Test if @test_ancestor is ancestor of @test_child - * @test_ancestor: Firmware which is tested for being an ancestor - * @test_child: Firmware which is tested for being the child + * fwnode_is_ancestor_of - Test if @ancestor is ancestor of @child + * @ancestor: Firmware which is tested for being an ancestor + * @child: Firmware which is tested for being the child * * A node is considered an ancestor of itself too. * - * Returns true if @test_ancestor is an ancestor of @test_child. - * Otherwise, returns false. + * Returns true if @ancestor is an ancestor of @child. Otherwise, returns false. */ -bool fwnode_is_ancestor_of(struct fwnode_handle *test_ancestor, - struct fwnode_handle *test_child) +bool fwnode_is_ancestor_of(struct fwnode_handle *ancestor, struct fwnode_handle *child) { - if (!test_ancestor) + struct fwnode_handle *parent; + + if (IS_ERR_OR_NULL(ancestor)) return false; - fwnode_handle_get(test_child); - while (test_child) { - if (test_child == test_ancestor) { - fwnode_handle_put(test_child); + if (child == ancestor) + return true; + + fwnode_for_each_parent_node(child, parent) { + if (parent == ancestor) { + fwnode_handle_put(parent); return true; } - test_child = fwnode_get_next_parent(test_child); } return false; } @@ -698,7 +738,7 @@ fwnode_get_next_available_child_node(const struct fwnode_handle *fwnode, { struct fwnode_handle *next_child = child; - if (!fwnode) + if (IS_ERR_OR_NULL(fwnode)) return NULL; do { @@ -722,16 +762,16 @@ struct fwnode_handle *device_get_next_child_node(struct device *dev, const struct fwnode_handle *fwnode = dev_fwnode(dev); struct fwnode_handle *next; + if (IS_ERR_OR_NULL(fwnode)) + return NULL; + /* Try to find a child in primary fwnode */ next = fwnode_get_next_child_node(fwnode, child); if (next) return next; /* When no more children in primary, continue with secondary */ - if (fwnode && !IS_ERR_OR_NULL(fwnode->secondary)) - next = fwnode_get_next_child_node(fwnode->secondary, child); - - return next; + return fwnode_get_next_child_node(fwnode->secondary, child); } EXPORT_SYMBOL_GPL(device_get_next_child_node); @@ -798,6 +838,9 @@ EXPORT_SYMBOL_GPL(fwnode_handle_put); */ bool fwnode_device_is_available(const struct fwnode_handle *fwnode) { + if (IS_ERR_OR_NULL(fwnode)) + return false; + if (!fwnode_has_op(fwnode, device_is_available)) return true; @@ -823,33 +866,16 @@ EXPORT_SYMBOL_GPL(device_get_child_node_count); bool device_dma_supported(struct device *dev) { - const struct fwnode_handle *fwnode = dev_fwnode(dev); - - /* For DT, this is always supported. - * For ACPI, this depends on CCA, which - * is determined by the acpi_dma_supported(). - */ - if (is_of_node(fwnode)) - return true; - - return acpi_dma_supported(to_acpi_device_node(fwnode)); + return fwnode_call_bool_op(dev_fwnode(dev), device_dma_supported); } EXPORT_SYMBOL_GPL(device_dma_supported); enum dev_dma_attr device_get_dma_attr(struct device *dev) { - const struct fwnode_handle *fwnode = dev_fwnode(dev); - enum dev_dma_attr attr = DEV_DMA_NOT_SUPPORTED; - - if (is_of_node(fwnode)) { - if (of_dma_is_coherent(to_of_node(fwnode))) - attr = DEV_DMA_COHERENT; - else - attr = DEV_DMA_NON_COHERENT; - } else - attr = acpi_get_dma_attr(to_acpi_device_node(fwnode)); + if (!fwnode_has_op(dev_fwnode(dev), device_get_dma_attr)) + return DEV_DMA_NOT_SUPPORTED; - return attr; + return fwnode_call_int_op(dev_fwnode(dev), device_get_dma_attr); } EXPORT_SYMBOL_GPL(device_get_dma_attr); @@ -904,10 +930,7 @@ EXPORT_SYMBOL_GPL(device_get_phy_mode); */ void __iomem *fwnode_iomap(struct fwnode_handle *fwnode, int index) { - if (IS_ENABLED(CONFIG_OF_ADDRESS) && is_of_node(fwnode)) - return of_iomap(to_of_node(fwnode), index); - - return NULL; + return fwnode_call_ptr_op(fwnode, iomap, index); } EXPORT_SYMBOL(fwnode_iomap); @@ -921,17 +944,7 @@ EXPORT_SYMBOL(fwnode_iomap); */ int fwnode_irq_get(const struct fwnode_handle *fwnode, unsigned int index) { - struct resource res; - int ret; - - if (is_of_node(fwnode)) - return of_irq_get(to_of_node(fwnode), index); - - ret = acpi_irq_get(ACPI_HANDLE_FWNODE(fwnode), index, &res); - if (ret) - return ret; - - return res.start; + return fwnode_call_int_op(fwnode, irq_get, index); } EXPORT_SYMBOL(fwnode_irq_get); @@ -988,14 +1001,14 @@ fwnode_graph_get_next_endpoint(const struct fwnode_handle *fwnode, parent = fwnode_graph_get_port_parent(prev); else parent = fwnode; + if (IS_ERR_OR_NULL(parent)) + return NULL; ep = fwnode_call_ptr_op(parent, graph_get_next_endpoint, prev); + if (ep) + return ep; - if (IS_ERR_OR_NULL(ep) && - !IS_ERR_OR_NULL(parent) && !IS_ERR_OR_NULL(parent->secondary)) - ep = fwnode_graph_get_next_endpoint(parent->secondary, NULL); - - return ep; + return fwnode_graph_get_next_endpoint(parent->secondary, NULL); } EXPORT_SYMBOL_GPL(fwnode_graph_get_next_endpoint); diff --git a/drivers/base/regmap/internal.h b/drivers/base/regmap/internal.h index b4df36c7b17d..da8996e7a1f1 100644 --- a/drivers/base/regmap/internal.h +++ b/drivers/base/regmap/internal.h @@ -110,6 +110,10 @@ struct regmap { int (*reg_write)(void *context, unsigned int reg, unsigned int val); int (*reg_update_bits)(void *context, unsigned int reg, unsigned int mask, unsigned int val); + /* Bulk read/write */ + int (*read)(void *context, const void *reg_buf, size_t reg_size, + void *val_buf, size_t val_size); + int (*write)(void *context, const void *data, size_t count); bool defer_caching; diff --git a/drivers/base/regmap/regcache.c b/drivers/base/regmap/regcache.c index f2469d3435ca..d0f5bc827978 100644 --- a/drivers/base/regmap/regcache.c +++ b/drivers/base/regmap/regcache.c @@ -183,8 +183,8 @@ int regcache_init(struct regmap *map, const struct regmap_config *config) return 0; } - if (!map->max_register) - map->max_register = map->num_reg_defaults_raw; + if (!map->max_register && map->num_reg_defaults_raw) + map->max_register = (map->num_reg_defaults_raw - 1) * map->reg_stride; if (map->cache_ops->init) { dev_dbg(map->dev, "Initializing %s cache\n", diff --git a/drivers/base/regmap/regmap-i3c.c b/drivers/base/regmap/regmap-i3c.c index 1578fb506683..0328b0b34284 100644 --- a/drivers/base/regmap/regmap-i3c.c +++ b/drivers/base/regmap/regmap-i3c.c @@ -40,7 +40,7 @@ static int regmap_i3c_read(void *context, return i3c_device_do_priv_xfers(i3c, xfers, 2); } -static struct regmap_bus regmap_i3c = { +static const struct regmap_bus regmap_i3c = { .write = regmap_i3c_write, .read = regmap_i3c_read, }; diff --git a/drivers/base/regmap/regmap-sccb.c b/drivers/base/regmap/regmap-sccb.c index 597042e2d009..986af26d88c2 100644 --- a/drivers/base/regmap/regmap-sccb.c +++ b/drivers/base/regmap/regmap-sccb.c @@ -80,7 +80,7 @@ static int regmap_sccb_write(void *context, unsigned int reg, unsigned int val) return i2c_smbus_write_byte_data(i2c, reg, val); } -static struct regmap_bus regmap_sccb_bus = { +static const struct regmap_bus regmap_sccb_bus = { .reg_write = regmap_sccb_write, .reg_read = regmap_sccb_read, }; diff --git a/drivers/base/regmap/regmap-sdw-mbq.c b/drivers/base/regmap/regmap-sdw-mbq.c index fe3ac26b66ad..388c3a087bd9 100644 --- a/drivers/base/regmap/regmap-sdw-mbq.c +++ b/drivers/base/regmap/regmap-sdw-mbq.c @@ -42,7 +42,7 @@ static int regmap_sdw_mbq_read(void *context, unsigned int reg, unsigned int *va return 0; } -static struct regmap_bus regmap_sdw_mbq = { +static const struct regmap_bus regmap_sdw_mbq = { .reg_read = regmap_sdw_mbq_read, .reg_write = regmap_sdw_mbq_write, .reg_format_endian_default = REGMAP_ENDIAN_LITTLE, diff --git a/drivers/base/regmap/regmap-sdw.c b/drivers/base/regmap/regmap-sdw.c index 966de8a136d9..81b0327f719d 100644 --- a/drivers/base/regmap/regmap-sdw.c +++ b/drivers/base/regmap/regmap-sdw.c @@ -30,7 +30,7 @@ static int regmap_sdw_read(void *context, unsigned int reg, unsigned int *val) return 0; } -static struct regmap_bus regmap_sdw = { +static const struct regmap_bus regmap_sdw = { .reg_read = regmap_sdw_read, .reg_write = regmap_sdw_write, .reg_format_endian_default = REGMAP_ENDIAN_LITTLE, diff --git a/drivers/base/regmap/regmap-slimbus.c b/drivers/base/regmap/regmap-slimbus.c index 0968059f1ef5..8075db788b39 100644 --- a/drivers/base/regmap/regmap-slimbus.c +++ b/drivers/base/regmap/regmap-slimbus.c @@ -22,7 +22,7 @@ static int regmap_slimbus_read(void *context, const void *reg, size_t reg_size, return slim_read(sdev, *(u16 *)reg, val_size, val); } -static struct regmap_bus regmap_slimbus_bus = { +static const struct regmap_bus regmap_slimbus_bus = { .write = regmap_slimbus_write, .read = regmap_slimbus_read, .reg_format_endian_default = REGMAP_ENDIAN_LITTLE, diff --git a/drivers/base/regmap/regmap-w1.c b/drivers/base/regmap/regmap-w1.c index 1fbaaad71ca5..3a8b402db852 100644 --- a/drivers/base/regmap/regmap-w1.c +++ b/drivers/base/regmap/regmap-w1.c @@ -172,17 +172,17 @@ static int w1_reg_a16_v16_write(void *context, unsigned int reg, * Various types of supported bus addressing */ -static struct regmap_bus regmap_w1_bus_a8_v8 = { +static const struct regmap_bus regmap_w1_bus_a8_v8 = { .reg_read = w1_reg_a8_v8_read, .reg_write = w1_reg_a8_v8_write, }; -static struct regmap_bus regmap_w1_bus_a8_v16 = { +static const struct regmap_bus regmap_w1_bus_a8_v16 = { .reg_read = w1_reg_a8_v16_read, .reg_write = w1_reg_a8_v16_write, }; -static struct regmap_bus regmap_w1_bus_a16_v16 = { +static const struct regmap_bus regmap_w1_bus_a16_v16 = { .reg_read = w1_reg_a16_v16_read, .reg_write = w1_reg_a16_v16_write, }; diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index 5e12f7cb5147..2221d9863831 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -838,12 +838,15 @@ struct regmap *__regmap_init(struct device *dev, map->reg_stride_order = ilog2(map->reg_stride); else map->reg_stride_order = -1; - map->use_single_read = config->use_single_read || !bus || !bus->read; - map->use_single_write = config->use_single_write || !bus || !bus->write; - map->can_multi_write = config->can_multi_write && bus && bus->write; + map->use_single_read = config->use_single_read || !(config->read || (bus && bus->read)); + map->use_single_write = config->use_single_write || !(config->write || (bus && bus->write)); + map->can_multi_write = config->can_multi_write && (config->write || (bus && bus->write)); if (bus) { map->max_raw_read = bus->max_raw_read; map->max_raw_write = bus->max_raw_write; + } else if (config->max_raw_read && config->max_raw_write) { + map->max_raw_read = config->max_raw_read; + map->max_raw_write = config->max_raw_write; } map->dev = dev; map->bus = bus; @@ -877,7 +880,16 @@ struct regmap *__regmap_init(struct device *dev, map->read_flag_mask = bus->read_flag_mask; } - if (!bus) { + if (config && config->read && config->write) { + map->reg_read = _regmap_bus_read; + + /* Bulk read/write */ + map->read = config->read; + map->write = config->write; + + reg_endian = REGMAP_ENDIAN_NATIVE; + val_endian = REGMAP_ENDIAN_NATIVE; + } else if (!bus) { map->reg_read = config->reg_read; map->reg_write = config->reg_write; map->reg_update_bits = config->reg_update_bits; @@ -894,10 +906,13 @@ struct regmap *__regmap_init(struct device *dev, } else { map->reg_read = _regmap_bus_read; map->reg_update_bits = bus->reg_update_bits; - } + /* Bulk read/write */ + map->read = bus->read; + map->write = bus->write; - reg_endian = regmap_get_reg_endian(bus, config); - val_endian = regmap_get_val_endian(dev, bus, config); + reg_endian = regmap_get_reg_endian(bus, config); + val_endian = regmap_get_val_endian(dev, bus, config); + } switch (config->reg_bits + map->reg_shift) { case 2: @@ -1671,8 +1686,6 @@ static int _regmap_raw_write_impl(struct regmap *map, unsigned int reg, size_t len; int i; - WARN_ON(!map->bus); - /* Check for unwritable or noinc registers in range * before we start */ @@ -1754,7 +1767,7 @@ static int _regmap_raw_write_impl(struct regmap *map, unsigned int reg, val = work_val; } - if (map->async && map->bus->async_write) { + if (map->async && map->bus && map->bus->async_write) { struct regmap_async *async; trace_regmap_async_write_start(map, reg, val_len); @@ -1822,11 +1835,11 @@ static int _regmap_raw_write_impl(struct regmap *map, unsigned int reg, * write. */ if (val == work_val) - ret = map->bus->write(map->bus_context, map->work_buf, - map->format.reg_bytes + - map->format.pad_bytes + - val_len); - else if (map->bus->gather_write) + ret = map->write(map->bus_context, map->work_buf, + map->format.reg_bytes + + map->format.pad_bytes + + val_len); + else if (map->bus && map->bus->gather_write) ret = map->bus->gather_write(map->bus_context, map->work_buf, map->format.reg_bytes + map->format.pad_bytes, @@ -1844,7 +1857,7 @@ static int _regmap_raw_write_impl(struct regmap *map, unsigned int reg, memcpy(buf, map->work_buf, map->format.reg_bytes); memcpy(buf + map->format.reg_bytes + map->format.pad_bytes, val, val_len); - ret = map->bus->write(map->bus_context, buf, len); + ret = map->write(map->bus_context, buf, len); kfree(buf); } else if (ret != 0 && !map->cache_bypass && map->format.parse_val) { @@ -1901,7 +1914,7 @@ static int _regmap_bus_formatted_write(void *context, unsigned int reg, struct regmap_range_node *range; struct regmap *map = context; - WARN_ON(!map->bus || !map->format.format_write); + WARN_ON(!map->format.format_write); range = _regmap_range_lookup(map, reg); if (range) { @@ -1916,8 +1929,7 @@ static int _regmap_bus_formatted_write(void *context, unsigned int reg, trace_regmap_hw_write_start(map, reg, 1); - ret = map->bus->write(map->bus_context, map->work_buf, - map->format.buf_size); + ret = map->write(map->bus_context, map->work_buf, map->format.buf_size); trace_regmap_hw_write_done(map, reg, 1); @@ -1937,7 +1949,7 @@ static int _regmap_bus_raw_write(void *context, unsigned int reg, { struct regmap *map = context; - WARN_ON(!map->bus || !map->format.format_val); + WARN_ON(!map->format.format_val); map->format.format_val(map->work_buf + map->format.reg_bytes + map->format.pad_bytes, val, 0); @@ -1951,7 +1963,7 @@ static int _regmap_bus_raw_write(void *context, unsigned int reg, static inline void *_regmap_map_get_context(struct regmap *map) { - return (map->bus) ? map : map->bus_context; + return (map->bus || (!map->bus && map->read)) ? map : map->bus_context; } int _regmap_write(struct regmap *map, unsigned int reg, @@ -2363,7 +2375,7 @@ static int _regmap_raw_multi_reg_write(struct regmap *map, u8 = buf; *u8 |= map->write_flag_mask; - ret = map->bus->write(map->bus_context, buf, len); + ret = map->write(map->bus_context, buf, len); kfree(buf); @@ -2669,9 +2681,7 @@ static int _regmap_raw_read(struct regmap *map, unsigned int reg, void *val, struct regmap_range_node *range; int ret; - WARN_ON(!map->bus); - - if (!map->bus || !map->bus->read) + if (!map->read) return -EINVAL; range = _regmap_range_lookup(map, reg); @@ -2689,9 +2699,9 @@ static int _regmap_raw_read(struct regmap *map, unsigned int reg, void *val, map->read_flag_mask); trace_regmap_hw_read_start(map, reg, val_len / map->format.val_bytes); - ret = map->bus->read(map->bus_context, map->work_buf, - map->format.reg_bytes + map->format.pad_bytes, - val, val_len); + ret = map->read(map->bus_context, map->work_buf, + map->format.reg_bytes + map->format.pad_bytes, + val, val_len); trace_regmap_hw_read_done(map, reg, val_len / map->format.val_bytes); @@ -2802,8 +2812,6 @@ int regmap_raw_read(struct regmap *map, unsigned int reg, void *val, unsigned int v; int ret, i; - if (!map->bus) - return -EINVAL; if (val_len % map->format.val_bytes) return -EINVAL; if (!IS_ALIGNED(reg, map->reg_stride)) @@ -2818,7 +2826,7 @@ int regmap_raw_read(struct regmap *map, unsigned int reg, void *val, size_t chunk_count, chunk_bytes; size_t chunk_regs = val_count; - if (!map->bus->read) { + if (!map->read) { ret = -ENOTSUPP; goto out; } @@ -2878,7 +2886,7 @@ EXPORT_SYMBOL_GPL(regmap_raw_read); * @val: Pointer to data buffer * @val_len: Length of output buffer in bytes. * - * The regmap API usually assumes that bulk bus read operations will read a + * The regmap API usually assumes that bulk read operations will read a * range of registers. Some devices have certain registers for which a read * operation read will read from an internal FIFO. * @@ -2896,10 +2904,6 @@ int regmap_noinc_read(struct regmap *map, unsigned int reg, size_t read_len; int ret; - if (!map->bus) - return -EINVAL; - if (!map->bus->read) - return -ENOTSUPP; if (val_len % map->format.val_bytes) return -EINVAL; if (!IS_ALIGNED(reg, map->reg_stride)) @@ -3013,7 +3017,7 @@ int regmap_bulk_read(struct regmap *map, unsigned int reg, void *val, if (val_count == 0) return -EINVAL; - if (map->bus && map->format.parse_inplace && (vol || map->cache_type == REGCACHE_NONE)) { + if (map->format.parse_inplace && (vol || map->cache_type == REGCACHE_NONE)) { ret = regmap_raw_read(map, reg, val, val_bytes * val_count); if (ret != 0) return ret; diff --git a/drivers/base/topology.c b/drivers/base/topology.c index e9d1efcda89b..ac6ad9ab67f9 100644 --- a/drivers/base/topology.c +++ b/drivers/base/topology.c @@ -152,9 +152,19 @@ static struct attribute *default_attrs[] = { NULL }; +static umode_t topology_is_visible(struct kobject *kobj, + struct attribute *attr, int unused) +{ + if (attr == &dev_attr_ppin.attr && !topology_ppin(kobj_to_dev(kobj)->id)) + return 0; + + return attr->mode; +} + static const struct attribute_group topology_attr_group = { .attrs = default_attrs, .bin_attrs = bin_attrs, + .is_visible = topology_is_visible, .name = "topology" }; diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig index 519b6d38d4df..fdb81f2794cd 100644 --- a/drivers/block/Kconfig +++ b/drivers/block/Kconfig @@ -33,6 +33,22 @@ config BLK_DEV_FD To compile this driver as a module, choose M here: the module will be called floppy. +config BLK_DEV_FD_RAWCMD + bool "Support for raw floppy disk commands (DEPRECATED)" + depends on BLK_DEV_FD + help + If you want to use actual physical floppies and expect to do + special low-level hardware accesses to them (access and use + non-standard formats, for example), then enable this. + + Note that the code enabled by this option is rarely used and + might be unstable or insecure, and distros should not enable it. + + Note: FDRAWCMD is deprecated and will be removed from the kernel + in the near future. + + If unsure, say N. + config AMIGA_FLOPPY tristate "Amiga floppy support" depends on AMIGA diff --git a/drivers/block/aoe/aoe.h b/drivers/block/aoe/aoe.h index 84d0fcebd6af..749ae1246f4c 100644 --- a/drivers/block/aoe/aoe.h +++ b/drivers/block/aoe/aoe.h @@ -244,3 +244,5 @@ void aoenet_exit(void); void aoenet_xmit(struct sk_buff_head *); int is_aoe_netif(struct net_device *ifp); int set_aoe_iflist(const char __user *str, size_t size); + +extern struct workqueue_struct *aoe_wq; diff --git a/drivers/block/aoe/aoeblk.c b/drivers/block/aoe/aoeblk.c index 8a91fcac6f82..348adf335217 100644 --- a/drivers/block/aoe/aoeblk.c +++ b/drivers/block/aoe/aoeblk.c @@ -435,7 +435,7 @@ err_mempool: err: spin_lock_irqsave(&d->lock, flags); d->flags &= ~DEVFL_GD_NOW; - schedule_work(&d->work); + queue_work(aoe_wq, &d->work); spin_unlock_irqrestore(&d->lock, flags); } diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c index 384073ef2323..d7317425be51 100644 --- a/drivers/block/aoe/aoecmd.c +++ b/drivers/block/aoe/aoecmd.c @@ -968,7 +968,7 @@ ataid_complete(struct aoedev *d, struct aoetgt *t, unsigned char *id) d->flags |= DEVFL_NEWSIZE; else d->flags |= DEVFL_GDALLOC; - schedule_work(&d->work); + queue_work(aoe_wq, &d->work); } static void diff --git a/drivers/block/aoe/aoedev.c b/drivers/block/aoe/aoedev.c index c5753c6bfe80..b381d1c3ef32 100644 --- a/drivers/block/aoe/aoedev.c +++ b/drivers/block/aoe/aoedev.c @@ -321,7 +321,7 @@ flush(const char __user *str, size_t cnt, int exiting) specified = 1; } - flush_scheduled_work(); + flush_workqueue(aoe_wq); /* pass one: do aoedev_downdev, which might sleep */ restart1: spin_lock_irqsave(&devlist_lock, flags); @@ -520,7 +520,7 @@ freetgt(struct aoedev *d, struct aoetgt *t) void aoedev_exit(void) { - flush_scheduled_work(); + flush_workqueue(aoe_wq); flush(NULL, 0, EXITING); } diff --git a/drivers/block/aoe/aoemain.c b/drivers/block/aoe/aoemain.c index 1e4e2971171c..6238c4c87cfc 100644 --- a/drivers/block/aoe/aoemain.c +++ b/drivers/block/aoe/aoemain.c @@ -16,6 +16,7 @@ MODULE_DESCRIPTION("AoE block/char driver for 2.6.2 and newer 2.6 kernels"); MODULE_VERSION(VERSION); static struct timer_list timer; +struct workqueue_struct *aoe_wq; static void discover_timer(struct timer_list *t) { @@ -35,6 +36,7 @@ aoe_exit(void) aoechr_exit(); aoedev_exit(); aoeblk_exit(); /* free cache after de-allocating bufs */ + destroy_workqueue(aoe_wq); } static int __init @@ -42,9 +44,13 @@ aoe_init(void) { int ret; + aoe_wq = alloc_workqueue("aoe_wq", 0, 0); + if (!aoe_wq) + return -ENOMEM; + ret = aoedev_init(); if (ret) - return ret; + goto dev_fail; ret = aoechr_init(); if (ret) goto chr_fail; @@ -77,6 +83,8 @@ aoe_init(void) aoechr_exit(); chr_fail: aoedev_exit(); + dev_fail: + destroy_workqueue(aoe_wq); printk(KERN_INFO "aoe: initialisation failure.\n"); return ret; diff --git a/drivers/block/ataflop.c b/drivers/block/ataflop.c index 5d819a466e2f..e232cc4fd444 100644 --- a/drivers/block/ataflop.c +++ b/drivers/block/ataflop.c @@ -303,6 +303,7 @@ static struct atari_floppy_struct { int ref; int type; struct blk_mq_tag_set tag_set; + int error_count; } unit[FD_MAX_UNITS]; #define UD unit[drive] @@ -705,14 +706,14 @@ static void fd_error( void ) if (!fd_request) return; - fd_request->error_count++; - if (fd_request->error_count >= MAX_ERRORS) { + unit[SelectedDrive].error_count++; + if (unit[SelectedDrive].error_count >= MAX_ERRORS) { printk(KERN_ERR "fd%d: too many errors.\n", SelectedDrive ); fd_end_request_cur(BLK_STS_IOERR); finish_fdc(); return; } - else if (fd_request->error_count == RECALIBRATE_ERRORS) { + else if (unit[SelectedDrive].error_count == RECALIBRATE_ERRORS) { printk(KERN_WARNING "fd%d: recalibrating\n", SelectedDrive ); if (SelectedDrive != -1) SUD.track = -1; @@ -1491,7 +1492,7 @@ static void setup_req_params( int drive ) ReqData = ReqBuffer + 512 * ReqCnt; if (UseTrackbuffer) - read_track = (ReqCmd == READ && fd_request->error_count == 0); + read_track = (ReqCmd == READ && unit[drive].error_count == 0); else read_track = 0; @@ -1520,6 +1521,7 @@ static blk_status_t ataflop_queue_rq(struct blk_mq_hw_ctx *hctx, return BLK_STS_RESOURCE; } fd_request = bd->rq; + unit[drive].error_count = 0; blk_mq_start_request(fd_request); atari_disable_irq( IRQ_MFP_FDC ); diff --git a/drivers/block/drbd/drbd_bitmap.c b/drivers/block/drbd/drbd_bitmap.c index df25eecf80af..9e060e49b3f8 100644 --- a/drivers/block/drbd/drbd_bitmap.c +++ b/drivers/block/drbd/drbd_bitmap.c @@ -683,7 +683,7 @@ int drbd_bm_resize(struct drbd_device *device, sector_t capacity, int set_new_bi } } - want = ALIGN(words*sizeof(long), PAGE_SIZE) >> PAGE_SHIFT; + want = PFN_UP(words*sizeof(long)); have = b->bm_number_of_pages; if (want == have) { D_ASSERT(device, b->bm_pages != NULL); diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h index 4b55e864a0a3..4d3efaa20b7b 100644 --- a/drivers/block/drbd/drbd_int.h +++ b/drivers/block/drbd/drbd_int.h @@ -1638,22 +1638,22 @@ struct sib_info { }; void drbd_bcast_event(struct drbd_device *device, const struct sib_info *sib); -extern void notify_resource_state(struct sk_buff *, +extern int notify_resource_state(struct sk_buff *, unsigned int, struct drbd_resource *, struct resource_info *, enum drbd_notification_type); -extern void notify_device_state(struct sk_buff *, +extern int notify_device_state(struct sk_buff *, unsigned int, struct drbd_device *, struct device_info *, enum drbd_notification_type); -extern void notify_connection_state(struct sk_buff *, +extern int notify_connection_state(struct sk_buff *, unsigned int, struct drbd_connection *, struct connection_info *, enum drbd_notification_type); -extern void notify_peer_device_state(struct sk_buff *, +extern int notify_peer_device_state(struct sk_buff *, unsigned int, struct drbd_peer_device *, struct peer_device_info *, diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c index 9676a1d214bc..2887350ae010 100644 --- a/drivers/block/drbd/drbd_main.c +++ b/drivers/block/drbd/drbd_main.c @@ -903,31 +903,6 @@ void drbd_gen_and_send_sync_uuid(struct drbd_peer_device *peer_device) } } -/* communicated if (agreed_features & DRBD_FF_WSAME) */ -static void -assign_p_sizes_qlim(struct drbd_device *device, struct p_sizes *p, - struct request_queue *q) -{ - if (q) { - p->qlim->physical_block_size = cpu_to_be32(queue_physical_block_size(q)); - p->qlim->logical_block_size = cpu_to_be32(queue_logical_block_size(q)); - p->qlim->alignment_offset = cpu_to_be32(queue_alignment_offset(q)); - p->qlim->io_min = cpu_to_be32(queue_io_min(q)); - p->qlim->io_opt = cpu_to_be32(queue_io_opt(q)); - p->qlim->discard_enabled = blk_queue_discard(q); - p->qlim->write_same_capable = 0; - } else { - q = device->rq_queue; - p->qlim->physical_block_size = cpu_to_be32(queue_physical_block_size(q)); - p->qlim->logical_block_size = cpu_to_be32(queue_logical_block_size(q)); - p->qlim->alignment_offset = 0; - p->qlim->io_min = cpu_to_be32(queue_io_min(q)); - p->qlim->io_opt = cpu_to_be32(queue_io_opt(q)); - p->qlim->discard_enabled = 0; - p->qlim->write_same_capable = 0; - } -} - int drbd_send_sizes(struct drbd_peer_device *peer_device, int trigger_reply, enum dds_flags flags) { struct drbd_device *device = peer_device->device; @@ -949,7 +924,9 @@ int drbd_send_sizes(struct drbd_peer_device *peer_device, int trigger_reply, enu memset(p, 0, packet_size); if (get_ldev_if_state(device, D_NEGOTIATING)) { - struct request_queue *q = bdev_get_queue(device->ldev->backing_bdev); + struct block_device *bdev = device->ldev->backing_bdev; + struct request_queue *q = bdev_get_queue(bdev); + d_size = drbd_get_max_capacity(device->ldev); rcu_read_lock(); u_size = rcu_dereference(device->ldev->disk_conf)->disk_size; @@ -957,14 +934,32 @@ int drbd_send_sizes(struct drbd_peer_device *peer_device, int trigger_reply, enu q_order_type = drbd_queue_order_type(device); max_bio_size = queue_max_hw_sectors(q) << 9; max_bio_size = min(max_bio_size, DRBD_MAX_BIO_SIZE); - assign_p_sizes_qlim(device, p, q); + p->qlim->physical_block_size = + cpu_to_be32(bdev_physical_block_size(bdev)); + p->qlim->logical_block_size = + cpu_to_be32(bdev_logical_block_size(bdev)); + p->qlim->alignment_offset = + cpu_to_be32(bdev_alignment_offset(bdev)); + p->qlim->io_min = cpu_to_be32(bdev_io_min(bdev)); + p->qlim->io_opt = cpu_to_be32(bdev_io_opt(bdev)); + p->qlim->discard_enabled = !!bdev_max_discard_sectors(bdev); put_ldev(device); } else { + struct request_queue *q = device->rq_queue; + + p->qlim->physical_block_size = + cpu_to_be32(queue_physical_block_size(q)); + p->qlim->logical_block_size = + cpu_to_be32(queue_logical_block_size(q)); + p->qlim->alignment_offset = 0; + p->qlim->io_min = cpu_to_be32(queue_io_min(q)); + p->qlim->io_opt = cpu_to_be32(queue_io_opt(q)); + p->qlim->discard_enabled = 0; + d_size = 0; u_size = 0; q_order_type = QUEUE_ORDERED_NONE; max_bio_size = DRBD_MAX_BIO_SIZE; /* ... multiple BIOs per peer_request */ - assign_p_sizes_qlim(device, p, NULL); } if (peer_device->connection->agreed_pro_version <= 94) @@ -2719,6 +2714,7 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig sprintf(disk->disk_name, "drbd%d", minor); disk->private_data = device; + blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, disk->queue); blk_queue_write_cache(disk->queue, true, true); /* Setting the max_hw_sectors to an odd value of 8kibyte here This triggers a max_bio_size message upon first attach or connect */ @@ -2773,12 +2769,12 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig if (init_submitter(device)) { err = ERR_NOMEM; - goto out_idr_remove_vol; + goto out_idr_remove_from_resource; } err = add_disk(disk); if (err) - goto out_idr_remove_vol; + goto out_idr_remove_from_resource; /* inherit the connection state */ device->state.conn = first_connection(resource)->cstate; @@ -2792,8 +2788,6 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig drbd_debugfs_device_add(device); return NO_ERROR; -out_idr_remove_vol: - idr_remove(&connection->peer_devices, vnr); out_idr_remove_from_resource: for_each_connection(connection, resource) { peer_device = idr_remove(&connection->peer_devices, vnr); @@ -3587,9 +3581,8 @@ const char *cmdname(enum drbd_packet cmd) * when we want to support more than * one PRO_VERSION */ static const char *cmdnames[] = { + [P_DATA] = "Data", - [P_WSAME] = "WriteSame", - [P_TRIM] = "Trim", [P_DATA_REPLY] = "DataReply", [P_RS_DATA_REPLY] = "RSDataReply", [P_BARRIER] = "Barrier", @@ -3600,7 +3593,6 @@ const char *cmdname(enum drbd_packet cmd) [P_DATA_REQUEST] = "DataRequest", [P_RS_DATA_REQUEST] = "RSDataRequest", [P_SYNC_PARAM] = "SyncParam", - [P_SYNC_PARAM89] = "SyncParam89", [P_PROTOCOL] = "ReportProtocol", [P_UUIDS] = "ReportUUIDs", [P_SIZES] = "ReportSizes", @@ -3608,6 +3600,7 @@ const char *cmdname(enum drbd_packet cmd) [P_SYNC_UUID] = "ReportSyncUUID", [P_AUTH_CHALLENGE] = "AuthChallenge", [P_AUTH_RESPONSE] = "AuthResponse", + [P_STATE_CHG_REQ] = "StateChgRequest", [P_PING] = "Ping", [P_PING_ACK] = "PingAck", [P_RECV_ACK] = "RecvAck", @@ -3618,23 +3611,25 @@ const char *cmdname(enum drbd_packet cmd) [P_NEG_DREPLY] = "NegDReply", [P_NEG_RS_DREPLY] = "NegRSDReply", [P_BARRIER_ACK] = "BarrierAck", - [P_STATE_CHG_REQ] = "StateChgRequest", [P_STATE_CHG_REPLY] = "StateChgReply", [P_OV_REQUEST] = "OVRequest", [P_OV_REPLY] = "OVReply", [P_OV_RESULT] = "OVResult", [P_CSUM_RS_REQUEST] = "CsumRSRequest", [P_RS_IS_IN_SYNC] = "CsumRSIsInSync", + [P_SYNC_PARAM89] = "SyncParam89", [P_COMPRESSED_BITMAP] = "CBitmap", [P_DELAY_PROBE] = "DelayProbe", [P_OUT_OF_SYNC] = "OutOfSync", - [P_RETRY_WRITE] = "RetryWrite", [P_RS_CANCEL] = "RSCancel", [P_CONN_ST_CHG_REQ] = "conn_st_chg_req", [P_CONN_ST_CHG_REPLY] = "conn_st_chg_reply", [P_PROTOCOL_UPDATE] = "protocol_update", + [P_TRIM] = "Trim", [P_RS_THIN_REQ] = "rs_thin_req", [P_RS_DEALLOCATED] = "rs_deallocated", + [P_WSAME] = "WriteSame", + [P_ZEROES] = "Zeroes", /* enum drbd_packet, but not commands - obsoleted flags: * P_MAY_IGNORE diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c index 02030c9c4d3b..013d355a2033 100644 --- a/drivers/block/drbd/drbd_nl.c +++ b/drivers/block/drbd/drbd_nl.c @@ -770,6 +770,7 @@ int drbd_adm_set_role(struct sk_buff *skb, struct genl_info *info) struct set_role_parms parms; int err; enum drbd_ret_code retcode; + enum drbd_state_rv rv; retcode = drbd_adm_prepare(&adm_ctx, skb, info, DRBD_ADM_NEED_MINOR); if (!adm_ctx.reply_skb) @@ -790,14 +791,14 @@ int drbd_adm_set_role(struct sk_buff *skb, struct genl_info *info) mutex_lock(&adm_ctx.resource->adm_mutex); if (info->genlhdr->cmd == DRBD_ADM_PRIMARY) - retcode = (enum drbd_ret_code)drbd_set_role(adm_ctx.device, - R_PRIMARY, parms.assume_uptodate); + rv = drbd_set_role(adm_ctx.device, R_PRIMARY, parms.assume_uptodate); else - retcode = (enum drbd_ret_code)drbd_set_role(adm_ctx.device, - R_SECONDARY, 0); + rv = drbd_set_role(adm_ctx.device, R_SECONDARY, 0); mutex_unlock(&adm_ctx.resource->adm_mutex); genl_lock(); + drbd_adm_finish(&adm_ctx, info, rv); + return 0; out: drbd_adm_finish(&adm_ctx, info, retcode); return 0; @@ -1204,50 +1205,40 @@ static unsigned int drbd_max_discard_sectors(struct drbd_connection *connection) } static void decide_on_discard_support(struct drbd_device *device, - struct request_queue *q, - struct request_queue *b, - bool discard_zeroes_if_aligned) + struct drbd_backing_dev *bdev) { - /* q = drbd device queue (device->rq_queue) - * b = backing device queue (device->ldev->backing_bdev->bd_disk->queue), - * or NULL if diskless - */ - struct drbd_connection *connection = first_peer_device(device)->connection; - bool can_do = b ? blk_queue_discard(b) : true; - - if (can_do && connection->cstate >= C_CONNECTED && !(connection->agreed_features & DRBD_FF_TRIM)) { - can_do = false; - drbd_info(connection, "peer DRBD too old, does not support TRIM: disabling discards\n"); - } - if (can_do) { - /* We don't care for the granularity, really. - * Stacking limits below should fix it for the local - * device. Whether or not it is a suitable granularity - * on the remote device is not our problem, really. If - * you care, you need to use devices with similar - * topology on all peers. */ - blk_queue_discard_granularity(q, 512); - q->limits.max_discard_sectors = drbd_max_discard_sectors(connection); - blk_queue_flag_set(QUEUE_FLAG_DISCARD, q); - q->limits.max_write_zeroes_sectors = drbd_max_discard_sectors(connection); - } else { - blk_queue_flag_clear(QUEUE_FLAG_DISCARD, q); - blk_queue_discard_granularity(q, 0); - q->limits.max_discard_sectors = 0; - q->limits.max_write_zeroes_sectors = 0; - } -} + struct drbd_connection *connection = + first_peer_device(device)->connection; + struct request_queue *q = device->rq_queue; -static void fixup_discard_if_not_supported(struct request_queue *q) -{ - /* To avoid confusion, if this queue does not support discard, clear - * max_discard_sectors, which is what lsblk -D reports to the user. - * Older kernels got this wrong in "stack limits". - * */ - if (!blk_queue_discard(q)) { - blk_queue_max_discard_sectors(q, 0); - blk_queue_discard_granularity(q, 0); + if (bdev && !bdev_max_discard_sectors(bdev->backing_bdev)) + goto not_supported; + + if (connection->cstate >= C_CONNECTED && + !(connection->agreed_features & DRBD_FF_TRIM)) { + drbd_info(connection, + "peer DRBD too old, does not support TRIM: disabling discards\n"); + goto not_supported; } + + /* + * We don't care for the granularity, really. + * + * Stacking limits below should fix it for the local device. Whether or + * not it is a suitable granularity on the remote device is not our + * problem, really. If you care, you need to use devices with similar + * topology on all peers. + */ + blk_queue_discard_granularity(q, 512); + q->limits.max_discard_sectors = drbd_max_discard_sectors(connection); + q->limits.max_write_zeroes_sectors = + drbd_max_discard_sectors(connection); + return; + +not_supported: + blk_queue_discard_granularity(q, 0); + q->limits.max_discard_sectors = 0; + q->limits.max_write_zeroes_sectors = 0; } static void fixup_write_zeroes(struct drbd_device *device, struct request_queue *q) @@ -1273,7 +1264,6 @@ static void drbd_setup_queue_param(struct drbd_device *device, struct drbd_backi unsigned int max_segments = 0; struct request_queue *b = NULL; struct disk_conf *dc; - bool discard_zeroes_if_aligned = true; if (bdev) { b = bdev->backing_bdev->bd_disk->queue; @@ -1282,7 +1272,6 @@ static void drbd_setup_queue_param(struct drbd_device *device, struct drbd_backi rcu_read_lock(); dc = rcu_dereference(device->ldev->disk_conf); max_segments = dc->max_bio_bvecs; - discard_zeroes_if_aligned = dc->discard_zeroes_if_aligned; rcu_read_unlock(); blk_set_stacking_limits(&q->limits); @@ -1292,13 +1281,12 @@ static void drbd_setup_queue_param(struct drbd_device *device, struct drbd_backi /* This is the workaround for "bio would need to, but cannot, be split" */ blk_queue_max_segments(q, max_segments ? max_segments : BLK_MAX_SEGMENTS); blk_queue_segment_boundary(q, PAGE_SIZE-1); - decide_on_discard_support(device, q, b, discard_zeroes_if_aligned); + decide_on_discard_support(device, bdev); if (b) { blk_stack_limits(&q->limits, &b->limits, 0); disk_update_readahead(device->vdisk); } - fixup_discard_if_not_supported(q); fixup_write_zeroes(device, q); } @@ -1437,14 +1425,14 @@ static bool write_ordering_changed(struct disk_conf *a, struct disk_conf *b) static void sanitize_disk_conf(struct drbd_device *device, struct disk_conf *disk_conf, struct drbd_backing_dev *nbc) { - struct request_queue * const q = nbc->backing_bdev->bd_disk->queue; + struct block_device *bdev = nbc->backing_bdev; if (disk_conf->al_extents < DRBD_AL_EXTENTS_MIN) disk_conf->al_extents = DRBD_AL_EXTENTS_MIN; if (disk_conf->al_extents > drbd_al_extents_max(nbc)) disk_conf->al_extents = drbd_al_extents_max(nbc); - if (!blk_queue_discard(q)) { + if (!bdev_max_discard_sectors(bdev)) { if (disk_conf->rs_discard_granularity) { disk_conf->rs_discard_granularity = 0; /* disable feature */ drbd_info(device, "rs_discard_granularity feature disabled\n"); @@ -1453,16 +1441,19 @@ static void sanitize_disk_conf(struct drbd_device *device, struct disk_conf *dis if (disk_conf->rs_discard_granularity) { int orig_value = disk_conf->rs_discard_granularity; + sector_t discard_size = bdev_max_discard_sectors(bdev) << 9; + unsigned int discard_granularity = bdev_discard_granularity(bdev); int remainder; - if (q->limits.discard_granularity > disk_conf->rs_discard_granularity) - disk_conf->rs_discard_granularity = q->limits.discard_granularity; + if (discard_granularity > disk_conf->rs_discard_granularity) + disk_conf->rs_discard_granularity = discard_granularity; - remainder = disk_conf->rs_discard_granularity % q->limits.discard_granularity; + remainder = disk_conf->rs_discard_granularity % + discard_granularity; disk_conf->rs_discard_granularity += remainder; - if (disk_conf->rs_discard_granularity > q->limits.max_discard_sectors << 9) - disk_conf->rs_discard_granularity = q->limits.max_discard_sectors << 9; + if (disk_conf->rs_discard_granularity > discard_size) + disk_conf->rs_discard_granularity = discard_size; if (disk_conf->rs_discard_granularity != orig_value) drbd_info(device, "rs_discard_granularity changed to %d\n", @@ -1611,8 +1602,7 @@ int drbd_adm_disk_opts(struct sk_buff *skb, struct genl_info *info) drbd_send_sync_param(peer_device); } - synchronize_rcu(); - kfree(old_disk_conf); + kvfree_rcu(old_disk_conf); kfree(old_plan); mod_timer(&device->request_timer, jiffies + HZ); goto success; @@ -2443,8 +2433,7 @@ int drbd_adm_net_opts(struct sk_buff *skb, struct genl_info *info) mutex_unlock(&connection->resource->conf_update); mutex_unlock(&connection->data.mutex); - synchronize_rcu(); - kfree(old_net_conf); + kvfree_rcu(old_net_conf); if (connection->cstate >= C_WF_REPORT_PARAMS) { struct drbd_peer_device *peer_device; @@ -2502,6 +2491,7 @@ int drbd_adm_connect(struct sk_buff *skb, struct genl_info *info) struct drbd_resource *resource; struct drbd_connection *connection; enum drbd_ret_code retcode; + enum drbd_state_rv rv; int i; int err; @@ -2621,12 +2611,11 @@ int drbd_adm_connect(struct sk_buff *skb, struct genl_info *info) } rcu_read_unlock(); - retcode = (enum drbd_ret_code)conn_request_state(connection, - NS(conn, C_UNCONNECTED), CS_VERBOSE); + rv = conn_request_state(connection, NS(conn, C_UNCONNECTED), CS_VERBOSE); conn_reconfig_done(connection); mutex_unlock(&adm_ctx.resource->adm_mutex); - drbd_adm_finish(&adm_ctx, info, retcode); + drbd_adm_finish(&adm_ctx, info, rv); return 0; fail: @@ -2734,11 +2723,12 @@ int drbd_adm_disconnect(struct sk_buff *skb, struct genl_info *info) mutex_lock(&adm_ctx.resource->adm_mutex); rv = conn_try_disconnect(connection, parms.force_disconnect); - if (rv < SS_SUCCESS) - retcode = (enum drbd_ret_code)rv; - else - retcode = NO_ERROR; mutex_unlock(&adm_ctx.resource->adm_mutex); + if (rv < SS_SUCCESS) { + drbd_adm_finish(&adm_ctx, info, rv); + return 0; + } + retcode = NO_ERROR; fail: drbd_adm_finish(&adm_ctx, info, retcode); return 0; @@ -2857,8 +2847,7 @@ int drbd_adm_resize(struct sk_buff *skb, struct genl_info *info) new_disk_conf->disk_size = (sector_t)rs.resize_size; rcu_assign_pointer(device->ldev->disk_conf, new_disk_conf); mutex_unlock(&device->resource->conf_update); - synchronize_rcu(); - kfree(old_disk_conf); + kvfree_rcu(old_disk_conf); new_disk_conf = NULL; } @@ -4549,7 +4538,7 @@ static int nla_put_notification_header(struct sk_buff *msg, return drbd_notification_header_to_skb(msg, &nh, true); } -void notify_resource_state(struct sk_buff *skb, +int notify_resource_state(struct sk_buff *skb, unsigned int seq, struct drbd_resource *resource, struct resource_info *resource_info, @@ -4591,16 +4580,17 @@ void notify_resource_state(struct sk_buff *skb, if (err && err != -ESRCH) goto failed; } - return; + return 0; nla_put_failure: nlmsg_free(skb); failed: drbd_err(resource, "Error %d while broadcasting event. Event seq:%u\n", err, seq); + return err; } -void notify_device_state(struct sk_buff *skb, +int notify_device_state(struct sk_buff *skb, unsigned int seq, struct drbd_device *device, struct device_info *device_info, @@ -4640,16 +4630,17 @@ void notify_device_state(struct sk_buff *skb, if (err && err != -ESRCH) goto failed; } - return; + return 0; nla_put_failure: nlmsg_free(skb); failed: drbd_err(device, "Error %d while broadcasting event. Event seq:%u\n", err, seq); + return err; } -void notify_connection_state(struct sk_buff *skb, +int notify_connection_state(struct sk_buff *skb, unsigned int seq, struct drbd_connection *connection, struct connection_info *connection_info, @@ -4689,16 +4680,17 @@ void notify_connection_state(struct sk_buff *skb, if (err && err != -ESRCH) goto failed; } - return; + return 0; nla_put_failure: nlmsg_free(skb); failed: drbd_err(connection, "Error %d while broadcasting event. Event seq:%u\n", err, seq); + return err; } -void notify_peer_device_state(struct sk_buff *skb, +int notify_peer_device_state(struct sk_buff *skb, unsigned int seq, struct drbd_peer_device *peer_device, struct peer_device_info *peer_device_info, @@ -4739,13 +4731,14 @@ void notify_peer_device_state(struct sk_buff *skb, if (err && err != -ESRCH) goto failed; } - return; + return 0; nla_put_failure: nlmsg_free(skb); failed: drbd_err(peer_device, "Error %d while broadcasting event. Event seq:%u\n", err, seq); + return err; } void notify_helper(enum drbd_notification_type type, @@ -4796,7 +4789,7 @@ fail: err, seq); } -static void notify_initial_state_done(struct sk_buff *skb, unsigned int seq) +static int notify_initial_state_done(struct sk_buff *skb, unsigned int seq) { struct drbd_genlmsghdr *dh; int err; @@ -4810,11 +4803,12 @@ static void notify_initial_state_done(struct sk_buff *skb, unsigned int seq) if (nla_put_notification_header(skb, NOTIFY_EXISTS)) goto nla_put_failure; genlmsg_end(skb, dh); - return; + return 0; nla_put_failure: nlmsg_free(skb); pr_err("Error %d sending event. Event seq:%u\n", err, seq); + return err; } static void free_state_changes(struct list_head *list) @@ -4841,6 +4835,7 @@ static int get_initial_state(struct sk_buff *skb, struct netlink_callback *cb) unsigned int seq = cb->args[2]; unsigned int n; enum drbd_notification_type flags = 0; + int err = 0; /* There is no need for taking notification_mutex here: it doesn't matter if the initial state events mix with later state chage @@ -4849,32 +4844,32 @@ static int get_initial_state(struct sk_buff *skb, struct netlink_callback *cb) cb->args[5]--; if (cb->args[5] == 1) { - notify_initial_state_done(skb, seq); + err = notify_initial_state_done(skb, seq); goto out; } n = cb->args[4]++; if (cb->args[4] < cb->args[3]) flags |= NOTIFY_CONTINUES; if (n < 1) { - notify_resource_state_change(skb, seq, state_change->resource, + err = notify_resource_state_change(skb, seq, state_change->resource, NOTIFY_EXISTS | flags); goto next; } n--; if (n < state_change->n_connections) { - notify_connection_state_change(skb, seq, &state_change->connections[n], + err = notify_connection_state_change(skb, seq, &state_change->connections[n], NOTIFY_EXISTS | flags); goto next; } n -= state_change->n_connections; if (n < state_change->n_devices) { - notify_device_state_change(skb, seq, &state_change->devices[n], + err = notify_device_state_change(skb, seq, &state_change->devices[n], NOTIFY_EXISTS | flags); goto next; } n -= state_change->n_devices; if (n < state_change->n_devices * state_change->n_connections) { - notify_peer_device_state_change(skb, seq, &state_change->peer_devices[n], + err = notify_peer_device_state_change(skb, seq, &state_change->peer_devices[n], NOTIFY_EXISTS | flags); goto next; } @@ -4889,7 +4884,10 @@ next: cb->args[4] = 0; } out: - return skb->len; + if (err) + return err; + else + return skb->len; } int drbd_adm_get_initial_state(struct sk_buff *skb, struct netlink_callback *cb) diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c index 08da922f81d1..6762be53f409 100644 --- a/drivers/block/drbd/drbd_receiver.c +++ b/drivers/block/drbd/drbd_receiver.c @@ -364,7 +364,7 @@ drbd_alloc_peer_req(struct drbd_peer_device *peer_device, u64 id, sector_t secto struct drbd_device *device = peer_device->device; struct drbd_peer_request *peer_req; struct page *page = NULL; - unsigned nr_pages = (payload_size + PAGE_SIZE -1) >> PAGE_SHIFT; + unsigned int nr_pages = PFN_UP(payload_size); if (drbd_insert_fault(device, DRBD_FAULT_AL_EE)) return NULL; @@ -1511,7 +1511,6 @@ void drbd_bump_write_ordering(struct drbd_resource *resource, struct drbd_backin int drbd_issue_discard_or_zero_out(struct drbd_device *device, sector_t start, unsigned int nr_sectors, int flags) { struct block_device *bdev = device->ldev->backing_bdev; - struct request_queue *q = bdev_get_queue(bdev); sector_t tmp, nr; unsigned int max_discard_sectors, granularity; int alignment; @@ -1521,10 +1520,10 @@ int drbd_issue_discard_or_zero_out(struct drbd_device *device, sector_t start, u goto zero_out; /* Zero-sector (unknown) and one-sector granularities are the same. */ - granularity = max(q->limits.discard_granularity >> 9, 1U); + granularity = max(bdev_discard_granularity(bdev) >> 9, 1U); alignment = (bdev_discard_alignment(bdev) >> 9) % granularity; - max_discard_sectors = min(q->limits.max_discard_sectors, (1U << 22)); + max_discard_sectors = min(bdev_max_discard_sectors(bdev), (1U << 22)); max_discard_sectors -= max_discard_sectors % granularity; if (unlikely(!max_discard_sectors)) goto zero_out; @@ -1548,7 +1547,8 @@ int drbd_issue_discard_or_zero_out(struct drbd_device *device, sector_t start, u start = tmp; } while (nr_sectors >= max_discard_sectors) { - err |= blkdev_issue_discard(bdev, start, max_discard_sectors, GFP_NOIO, 0); + err |= blkdev_issue_discard(bdev, start, max_discard_sectors, + GFP_NOIO); nr_sectors -= max_discard_sectors; start += max_discard_sectors; } @@ -1560,7 +1560,7 @@ int drbd_issue_discard_or_zero_out(struct drbd_device *device, sector_t start, u nr = nr_sectors; nr -= (unsigned int)nr % granularity; if (nr) { - err |= blkdev_issue_discard(bdev, start, nr, GFP_NOIO, 0); + err |= blkdev_issue_discard(bdev, start, nr, GFP_NOIO); nr_sectors -= nr; start += nr; } @@ -1575,11 +1575,10 @@ int drbd_issue_discard_or_zero_out(struct drbd_device *device, sector_t start, u static bool can_do_reliable_discards(struct drbd_device *device) { - struct request_queue *q = bdev_get_queue(device->ldev->backing_bdev); struct disk_conf *dc; bool can_do; - if (!blk_queue_discard(q)) + if (!bdev_max_discard_sectors(device->ldev->backing_bdev)) return false; rcu_read_lock(); @@ -1629,9 +1628,9 @@ int drbd_submit_peer_request(struct drbd_device *device, struct bio *bio; struct page *page = peer_req->pages; sector_t sector = peer_req->i.sector; - unsigned data_size = peer_req->i.size; - unsigned n_bios = 0; - unsigned nr_pages = (data_size + PAGE_SIZE -1) >> PAGE_SHIFT; + unsigned int data_size = peer_req->i.size; + unsigned int n_bios = 0; + unsigned int nr_pages = PFN_UP(data_size); /* TRIM/DISCARD: for now, always use the helper function * blkdev_issue_zeroout(..., discard=true). @@ -3751,8 +3750,7 @@ static int receive_protocol(struct drbd_connection *connection, struct packet_in drbd_info(connection, "peer data-integrity-alg: %s\n", integrity_alg[0] ? integrity_alg : "(none)"); - synchronize_rcu(); - kfree(old_net_conf); + kvfree_rcu(old_net_conf); return 0; disconnect_rcu_unlock: @@ -3903,7 +3901,6 @@ static int receive_SyncParam(struct drbd_connection *connection, struct packet_i drbd_err(device, "verify-alg of wrong size, " "peer wants %u, accepting only up to %u byte\n", data_size, SHARED_SECRET_MAX); - err = -EIO; goto reconnect; } @@ -4121,8 +4118,7 @@ static int receive_sizes(struct drbd_connection *connection, struct packet_info rcu_assign_pointer(device->ldev->disk_conf, new_disk_conf); mutex_unlock(&connection->resource->conf_update); - synchronize_rcu(); - kfree(old_disk_conf); + kvfree_rcu(old_disk_conf); drbd_info(device, "Peer sets u_size to %lu sectors (old: %lu)\n", (unsigned long)p_usize, (unsigned long)my_usize); diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c index 75be0e16770a..e64bcfba30ef 100644 --- a/drivers/block/drbd/drbd_req.c +++ b/drivers/block/drbd/drbd_req.c @@ -922,7 +922,7 @@ static bool remote_due_to_read_balancing(struct drbd_device *device, sector_t se switch (rbm) { case RB_CONGESTED_REMOTE: - return 0; + return false; case RB_LEAST_PENDING: return atomic_read(&device->local_cnt) > atomic_read(&device->ap_pending_cnt) + atomic_read(&device->rs_pending_cnt); diff --git a/drivers/block/drbd/drbd_state.c b/drivers/block/drbd/drbd_state.c index b8a27818ab3f..3f7bf9f2d874 100644 --- a/drivers/block/drbd/drbd_state.c +++ b/drivers/block/drbd/drbd_state.c @@ -1537,7 +1537,7 @@ int drbd_bitmap_io_from_worker(struct drbd_device *device, return rv; } -void notify_resource_state_change(struct sk_buff *skb, +int notify_resource_state_change(struct sk_buff *skb, unsigned int seq, struct drbd_resource_state_change *resource_state_change, enum drbd_notification_type type) @@ -1550,10 +1550,10 @@ void notify_resource_state_change(struct sk_buff *skb, .res_susp_fen = resource_state_change->susp_fen[NEW], }; - notify_resource_state(skb, seq, resource, &resource_info, type); + return notify_resource_state(skb, seq, resource, &resource_info, type); } -void notify_connection_state_change(struct sk_buff *skb, +int notify_connection_state_change(struct sk_buff *skb, unsigned int seq, struct drbd_connection_state_change *connection_state_change, enum drbd_notification_type type) @@ -1564,10 +1564,10 @@ void notify_connection_state_change(struct sk_buff *skb, .conn_role = connection_state_change->peer_role[NEW], }; - notify_connection_state(skb, seq, connection, &connection_info, type); + return notify_connection_state(skb, seq, connection, &connection_info, type); } -void notify_device_state_change(struct sk_buff *skb, +int notify_device_state_change(struct sk_buff *skb, unsigned int seq, struct drbd_device_state_change *device_state_change, enum drbd_notification_type type) @@ -1577,10 +1577,10 @@ void notify_device_state_change(struct sk_buff *skb, .dev_disk_state = device_state_change->disk_state[NEW], }; - notify_device_state(skb, seq, device, &device_info, type); + return notify_device_state(skb, seq, device, &device_info, type); } -void notify_peer_device_state_change(struct sk_buff *skb, +int notify_peer_device_state_change(struct sk_buff *skb, unsigned int seq, struct drbd_peer_device_state_change *p, enum drbd_notification_type type) @@ -1594,7 +1594,7 @@ void notify_peer_device_state_change(struct sk_buff *skb, .peer_resync_susp_dependency = p->resync_susp_dependency[NEW], }; - notify_peer_device_state(skb, seq, peer_device, &peer_device_info, type); + return notify_peer_device_state(skb, seq, peer_device, &peer_device_info, type); } static void broadcast_state_change(struct drbd_state_change *state_change) @@ -1602,7 +1602,7 @@ static void broadcast_state_change(struct drbd_state_change *state_change) struct drbd_resource_state_change *resource_state_change = &state_change->resource[0]; bool resource_state_has_changed; unsigned int n_device, n_connection, n_peer_device, n_peer_devices; - void (*last_func)(struct sk_buff *, unsigned int, void *, + int (*last_func)(struct sk_buff *, unsigned int, void *, enum drbd_notification_type) = NULL; void *last_arg = NULL; @@ -2071,8 +2071,7 @@ static int w_after_conn_state_ch(struct drbd_work *w, int unused) conn_free_crypto(connection); mutex_unlock(&connection->resource->conf_update); - synchronize_rcu(); - kfree(old_conf); + kvfree_rcu(old_conf); } if (ns_max.susp_fen) { diff --git a/drivers/block/drbd/drbd_state_change.h b/drivers/block/drbd/drbd_state_change.h index ba80f612d6ab..d5b0479bc9a6 100644 --- a/drivers/block/drbd/drbd_state_change.h +++ b/drivers/block/drbd/drbd_state_change.h @@ -44,19 +44,19 @@ extern struct drbd_state_change *remember_old_state(struct drbd_resource *, gfp_ extern void copy_old_to_new_state_change(struct drbd_state_change *); extern void forget_state_change(struct drbd_state_change *); -extern void notify_resource_state_change(struct sk_buff *, +extern int notify_resource_state_change(struct sk_buff *, unsigned int, struct drbd_resource_state_change *, enum drbd_notification_type type); -extern void notify_connection_state_change(struct sk_buff *, +extern int notify_connection_state_change(struct sk_buff *, unsigned int, struct drbd_connection_state_change *, enum drbd_notification_type type); -extern void notify_device_state_change(struct sk_buff *, +extern int notify_device_state_change(struct sk_buff *, unsigned int, struct drbd_device_state_change *, enum drbd_notification_type type); -extern void notify_peer_device_state_change(struct sk_buff *, +extern int notify_peer_device_state_change(struct sk_buff *, unsigned int, struct drbd_peer_device_state_change *, enum drbd_notification_type type); diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c index 0f9956f4e9c4..af3051dd8912 100644 --- a/drivers/block/drbd/drbd_worker.c +++ b/drivers/block/drbd/drbd_worker.c @@ -1030,7 +1030,7 @@ static void move_to_net_ee_or_free(struct drbd_device *device, struct drbd_peer_ { if (drbd_peer_req_has_active_page(peer_req)) { /* This might happen if sendpage() has not finished */ - int i = (peer_req->i.size + PAGE_SIZE -1) >> PAGE_SHIFT; + int i = PFN_UP(peer_req->i.size); atomic_add(i, &device->pp_in_use_by_net); atomic_sub(i, &device->pp_in_use); spin_lock_irq(&device->resource->req_lock); diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index 8c647532e3ce..015841f50f4e 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -509,8 +509,8 @@ static unsigned long fdc_busy; static DECLARE_WAIT_QUEUE_HEAD(fdc_wait); static DECLARE_WAIT_QUEUE_HEAD(command_done); -/* Errors during formatting are counted here. */ -static int format_errors; +/* errors encountered on the current (or last) request */ +static int floppy_errors; /* Format request descriptor. */ static struct format_descr format_req; @@ -530,7 +530,6 @@ static struct format_descr format_req; static char *floppy_track_buffer; static int max_buffer_sectors; -static int *errors; typedef void (*done_f)(int); static const struct cont_t { void (*interrupt)(void); @@ -1455,7 +1454,7 @@ static int interpret_errors(void) if (drive_params[current_drive].flags & FTD_MSG) DPRINT("Over/Underrun - retrying\n"); bad = 0; - } else if (*errors >= drive_params[current_drive].max_errors.reporting) { + } else if (floppy_errors >= drive_params[current_drive].max_errors.reporting) { print_errors(); } if (reply_buffer[ST2] & ST2_WC || reply_buffer[ST2] & ST2_BC) @@ -2095,7 +2094,7 @@ static void bad_flp_intr(void) if (!next_valid_format(current_drive)) return; } - err_count = ++(*errors); + err_count = ++floppy_errors; INFBOUND(write_errors[current_drive].badness, err_count); if (err_count > drive_params[current_drive].max_errors.abort) cont->done(0); @@ -2241,9 +2240,8 @@ static int do_format(int drive, struct format_descr *tmp_format_req) return -EINVAL; } format_req = *tmp_format_req; - format_errors = 0; cont = &format_cont; - errors = &format_errors; + floppy_errors = 0; ret = wait_til_done(redo_format, true); if (ret == -EINTR) return -EINTR; @@ -2759,10 +2757,11 @@ static int set_next_request(void) current_req = list_first_entry_or_null(&floppy_reqs, struct request, queuelist); if (current_req) { - current_req->error_count = 0; + floppy_errors = 0; list_del_init(¤t_req->queuelist); + return 1; } - return current_req != NULL; + return 0; } /* Starts or continues processing request. Will automatically unlock the @@ -2821,7 +2820,6 @@ do_request: _floppy = floppy_type + drive_params[current_drive].autodetect[drive_state[current_drive].probed_format]; } else probing = 0; - errors = &(current_req->error_count); tmp = make_raw_rw_request(); if (tmp < 2) { request_done(tmp); @@ -2982,6 +2980,8 @@ static const char *drive_name(int type, int drive) return "(null)"; } +#ifdef CONFIG_BLK_DEV_FD_RAWCMD + /* raw commands */ static void raw_cmd_done(int flag) { @@ -3181,6 +3181,35 @@ static int raw_cmd_ioctl(int cmd, void __user *param) return ret; } +static int floppy_raw_cmd_ioctl(int type, int drive, int cmd, + void __user *param) +{ + int ret; + + pr_warn_once("Note: FDRAWCMD is deprecated and will be removed from the kernel in the near future.\n"); + + if (type) + return -EINVAL; + if (lock_fdc(drive)) + return -EINTR; + set_floppy(drive); + ret = raw_cmd_ioctl(cmd, param); + if (ret == -EINTR) + return -EINTR; + process_fd_request(); + return ret; +} + +#else /* CONFIG_BLK_DEV_FD_RAWCMD */ + +static int floppy_raw_cmd_ioctl(int type, int drive, int cmd, + void __user *param) +{ + return -EOPNOTSUPP; +} + +#endif + static int invalidate_drive(struct block_device *bdev) { /* invalidate the buffer track to force a reread */ @@ -3369,7 +3398,6 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int { int drive = (long)bdev->bd_disk->private_data; int type = ITYPE(drive_state[drive].fd_device); - int i; int ret; int size; union inparam { @@ -3520,16 +3548,7 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int outparam = &write_errors[drive]; break; case FDRAWCMD: - if (type) - return -EINVAL; - if (lock_fdc(drive)) - return -EINTR; - set_floppy(drive); - i = raw_cmd_ioctl(cmd, (void __user *)param); - if (i == -EINTR) - return -EINTR; - process_fd_request(); - return i; + return floppy_raw_cmd_ioctl(type, drive, cmd, (void __user *)param); case FDTWADDLE: if (lock_fdc(drive)) return -EINTR; diff --git a/drivers/block/loop.c b/drivers/block/loop.c index a58595f5ee2c..e2cb51810e89 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -1,54 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-only /* - * linux/drivers/block/loop.c - * - * Written by Theodore Ts'o, 3/29/93 - * - * Copyright 1993 by Theodore Ts'o. Redistribution of this file is - * permitted under the GNU General Public License. - * - * DES encryption plus some minor changes by Werner Almesberger, 30-MAY-1993 - * more DES encryption plus IDEA encryption by Nicholas J. Leon, June 20, 1996 - * - * Modularized and updated for 1.1.16 kernel - Mitch Dsouza 28th May 1994 - * Adapted for 1.3.59 kernel - Andries Brouwer, 1 Feb 1996 - * - * Fixed do_loop_request() re-entrancy - Vincent.Renardias@waw.com Mar 20, 1997 - * - * Added devfs support - Richard Gooch <rgooch@atnf.csiro.au> 16-Jan-1998 - * - * Handle sparse backing files correctly - Kenn Humborg, Jun 28, 1998 - * - * Loadable modules and other fixes by AK, 1998 - * - * Make real block number available to downstream transfer functions, enables - * CBC (and relatives) mode encryption requiring unique IVs per data block. - * Reed H. Petty, rhp@draper.net - * - * Maximum number of loop devices now dynamic via max_loop module parameter. - * Russell Kroll <rkroll@exploits.org> 19990701 - * - * Maximum number of loop devices when compiled-in now selectable by passing - * max_loop=<1-255> to the kernel on boot. - * Erik I. Bolsø, <eriki@himolde.no>, Oct 31, 1999 - * - * Completely rewrite request handling to be make_request_fn style and - * non blocking, pushing work to a helper thread. Lots of fixes from - * Al Viro too. - * Jens Axboe <axboe@suse.de>, Nov 2000 - * - * Support up to 256 loop devices - * Heinz Mauelshagen <mge@sistina.com>, Feb 2002 - * - * Support for falling back on the write file operation when the address space - * operations write_begin is not available on the backing filesystem. - * Anton Altaparmakov, 16 Feb 2005 - * - * Still To Fix: - * - Advisory locking is ignored here. - * - Should use an own CAP_* category instead of CAP_SYS_ADMIN - * + * Copyright 1993 by Theodore Ts'o. */ - #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/sched.h> @@ -59,7 +12,6 @@ #include <linux/errno.h> #include <linux/major.h> #include <linux/wait.h> -#include <linux/blkdev.h> #include <linux/blkpg.h> #include <linux/init.h> #include <linux/swap.h> @@ -80,10 +32,62 @@ #include <linux/blk-cgroup.h> #include <linux/sched/mm.h> #include <linux/statfs.h> +#include <linux/uaccess.h> +#include <linux/blk-mq.h> +#include <linux/spinlock.h> +#include <uapi/linux/loop.h> + +/* Possible states of device */ +enum { + Lo_unbound, + Lo_bound, + Lo_rundown, + Lo_deleting, +}; -#include "loop.h" +struct loop_func_table; + +struct loop_device { + int lo_number; + loff_t lo_offset; + loff_t lo_sizelimit; + int lo_flags; + char lo_file_name[LO_NAME_SIZE]; + + struct file * lo_backing_file; + struct block_device *lo_device; + + gfp_t old_gfp_mask; + + spinlock_t lo_lock; + int lo_state; + spinlock_t lo_work_lock; + struct workqueue_struct *workqueue; + struct work_struct rootcg_work; + struct list_head rootcg_cmd_list; + struct list_head idle_worker_list; + struct rb_root worker_tree; + struct timer_list timer; + bool use_dio; + bool sysfs_inited; + + struct request_queue *lo_queue; + struct blk_mq_tag_set tag_set; + struct gendisk *lo_disk; + struct mutex lo_mutex; + bool idr_visible; +}; -#include <linux/uaccess.h> +struct loop_cmd { + struct list_head list_entry; + bool use_aio; /* use AIO interface to handle I/O */ + atomic_t ref; /* only for aio */ + long ret; + struct kiocb iocb; + struct bio_vec *bvec; + struct cgroup_subsys_state *blkcg_css; + struct cgroup_subsys_state *memcg_css; +}; #define LOOP_IDLE_WORKER_TIMEOUT (60 * HZ) #define LOOP_DEFAULT_HW_Q_DEPTH (128) @@ -314,15 +318,12 @@ static int lo_fallocate(struct loop_device *lo, struct request *rq, loff_t pos, mode |= FALLOC_FL_KEEP_SIZE; - if (!blk_queue_discard(lo->lo_queue)) { - ret = -EOPNOTSUPP; - goto out; - } + if (!bdev_max_discard_sectors(lo->lo_device)) + return -EOPNOTSUPP; ret = file->f_op->fallocate(file, mode, pos, blk_rq_bytes(rq)); if (unlikely(ret && ret != -EINVAL && ret != -EOPNOTSUPP)) - ret = -EIO; - out: + return -EIO; return ret; } @@ -572,6 +573,10 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev, if (!file) return -EBADF; + + /* suppress uevents while reconfiguring the device */ + dev_set_uevent_suppress(disk_to_dev(lo->lo_disk), 1); + is_loop = is_loop_device(file); error = loop_global_lock_killable(lo, is_loop); if (error) @@ -626,13 +631,18 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev, fput(old_file); if (partscan) loop_reread_partitions(lo); - return 0; + + error = 0; +done: + /* enable and uncork uevent now that we are done */ + dev_set_uevent_suppress(disk_to_dev(lo->lo_disk), 0); + return error; out_err: loop_global_unlock(lo, is_loop); out_putf: fput(file); - return error; + goto done; } /* loop sysfs attributes */ @@ -762,7 +772,7 @@ static void loop_config_discard(struct loop_device *lo) struct request_queue *backingq = bdev_get_queue(I_BDEV(inode)); max_discard_sectors = backingq->limits.max_write_zeroes_sectors; - granularity = backingq->limits.discard_granularity ?: + granularity = bdev_discard_granularity(I_BDEV(inode)) ?: queue_physical_block_size(backingq); /* @@ -787,14 +797,11 @@ static void loop_config_discard(struct loop_device *lo) q->limits.discard_granularity = granularity; blk_queue_max_discard_sectors(q, max_discard_sectors); blk_queue_max_write_zeroes_sectors(q, max_discard_sectors); - blk_queue_flag_set(QUEUE_FLAG_DISCARD, q); } else { q->limits.discard_granularity = 0; blk_queue_max_discard_sectors(q, 0); blk_queue_max_write_zeroes_sectors(q, 0); - blk_queue_flag_clear(QUEUE_FLAG_DISCARD, q); } - q->limits.discard_alignment = 0; } struct loop_worker { @@ -808,8 +815,6 @@ struct loop_worker { }; static void loop_workfn(struct work_struct *work); -static void loop_rootcg_workfn(struct work_struct *work); -static void loop_free_idle_workers(struct timer_list *timer); #ifdef CONFIG_BLK_CGROUP static inline int queue_on_root_worker(struct cgroup_subsys_state *css) @@ -893,6 +898,39 @@ queue_work: spin_unlock_irq(&lo->lo_work_lock); } +static void loop_set_timer(struct loop_device *lo) +{ + timer_reduce(&lo->timer, jiffies + LOOP_IDLE_WORKER_TIMEOUT); +} + +static void loop_free_idle_workers(struct loop_device *lo, bool delete_all) +{ + struct loop_worker *pos, *worker; + + spin_lock_irq(&lo->lo_work_lock); + list_for_each_entry_safe(worker, pos, &lo->idle_worker_list, + idle_list) { + if (!delete_all && + time_is_after_jiffies(worker->last_ran_at + + LOOP_IDLE_WORKER_TIMEOUT)) + break; + list_del(&worker->idle_list); + rb_erase(&worker->rb_node, &lo->worker_tree); + css_put(worker->blkcg_css); + kfree(worker); + } + if (!list_empty(&lo->idle_worker_list)) + loop_set_timer(lo); + spin_unlock_irq(&lo->lo_work_lock); +} + +static void loop_free_idle_workers_timer(struct timer_list *timer) +{ + struct loop_device *lo = container_of(timer, struct loop_device, timer); + + return loop_free_idle_workers(lo, false); +} + static void loop_update_rotational(struct loop_device *lo) { struct file *file = lo->lo_backing_file; @@ -903,7 +941,7 @@ static void loop_update_rotational(struct loop_device *lo) /* not all filesystems (e.g. tmpfs) have a sb->s_bdev */ if (file_bdev) - nonrot = blk_queue_nonrot(bdev_get_queue(file_bdev)); + nonrot = bdev_nonrot(file_bdev); if (nonrot) blk_queue_flag_set(QUEUE_FLAG_NONROT, q); @@ -967,6 +1005,9 @@ static int loop_configure(struct loop_device *lo, fmode_t mode, /* This is safe, since we have a reference from open(). */ __module_get(THIS_MODULE); + /* suppress uevents while reconfiguring the device */ + dev_set_uevent_suppress(disk_to_dev(lo->lo_disk), 1); + /* * If we don't hold exclusive handle for the device, upgrade to it * here to avoid changing device under exclusive owner. @@ -1011,24 +1052,19 @@ static int loop_configure(struct loop_device *lo, fmode_t mode, !file->f_op->write_iter) lo->lo_flags |= LO_FLAGS_READ_ONLY; - lo->workqueue = alloc_workqueue("loop%d", - WQ_UNBOUND | WQ_FREEZABLE, - 0, - lo->lo_number); if (!lo->workqueue) { - error = -ENOMEM; - goto out_unlock; + lo->workqueue = alloc_workqueue("loop%d", + WQ_UNBOUND | WQ_FREEZABLE, + 0, lo->lo_number); + if (!lo->workqueue) { + error = -ENOMEM; + goto out_unlock; + } } disk_force_media_change(lo->lo_disk, DISK_EVENT_MEDIA_CHANGE); set_disk_ro(lo->lo_disk, (lo->lo_flags & LO_FLAGS_READ_ONLY) != 0); - INIT_WORK(&lo->rootcg_work, loop_rootcg_workfn); - INIT_LIST_HEAD(&lo->rootcg_cmd_list); - INIT_LIST_HEAD(&lo->idle_worker_list); - lo->worker_tree = RB_ROOT; - timer_setup(&lo->timer, loop_free_idle_workers, - TIMER_DEFERRABLE); lo->use_dio = lo->lo_flags & LO_FLAGS_DIRECT_IO; lo->lo_device = bdev; lo->lo_backing_file = file; @@ -1073,7 +1109,12 @@ static int loop_configure(struct loop_device *lo, fmode_t mode, loop_reread_partitions(lo); if (!(mode & FMODE_EXCL)) bd_abort_claiming(bdev, loop_configure); - return 0; + + error = 0; +done: + /* enable and uncork uevent now that we are done */ + dev_set_uevent_suppress(disk_to_dev(lo->lo_disk), 0); + return error; out_unlock: loop_global_unlock(lo, is_loop); @@ -1084,53 +1125,24 @@ out_putf: fput(file); /* This is safe: open() is still holding a reference. */ module_put(THIS_MODULE); - return error; + goto done; } static void __loop_clr_fd(struct loop_device *lo, bool release) { struct file *filp; gfp_t gfp = lo->old_gfp_mask; - struct loop_worker *pos, *worker; - - /* - * Flush loop_configure() and loop_change_fd(). It is acceptable for - * loop_validate_file() to succeed, for actual clear operation has not - * started yet. - */ - mutex_lock(&loop_validate_mutex); - mutex_unlock(&loop_validate_mutex); - /* - * loop_validate_file() now fails because l->lo_state != Lo_bound - * became visible. - */ - - /* - * Since this function is called upon "ioctl(LOOP_CLR_FD)" xor "close() - * after ioctl(LOOP_CLR_FD)", it is a sign of something going wrong if - * lo->lo_state has changed while waiting for lo->lo_mutex. - */ - mutex_lock(&lo->lo_mutex); - BUG_ON(lo->lo_state != Lo_rundown); - mutex_unlock(&lo->lo_mutex); if (test_bit(QUEUE_FLAG_WC, &lo->lo_queue->queue_flags)) blk_queue_write_cache(lo->lo_queue, false, false); - /* freeze request queue during the transition */ - blk_mq_freeze_queue(lo->lo_queue); - - destroy_workqueue(lo->workqueue); - spin_lock_irq(&lo->lo_work_lock); - list_for_each_entry_safe(worker, pos, &lo->idle_worker_list, - idle_list) { - list_del(&worker->idle_list); - rb_erase(&worker->rb_node, &lo->worker_tree); - css_put(worker->blkcg_css); - kfree(worker); - } - spin_unlock_irq(&lo->lo_work_lock); - del_timer_sync(&lo->timer); + /* + * Freeze the request queue when unbinding on a live file descriptor and + * thus an open device. When called from ->release we are guaranteed + * that there is no I/O in progress already. + */ + if (!release) + blk_mq_freeze_queue(lo->lo_queue); spin_lock_irq(&lo->lo_lock); filp = lo->lo_backing_file; @@ -1151,7 +1163,8 @@ static void __loop_clr_fd(struct loop_device *lo, bool release) mapping_set_gfp_mask(filp->f_mapping, gfp); /* This is safe: open() is still holding a reference. */ module_put(THIS_MODULE); - blk_mq_unfreeze_queue(lo->lo_queue); + if (!release) + blk_mq_unfreeze_queue(lo->lo_queue); disk_force_media_change(lo->lo_disk, DISK_EVENT_MEDIA_CHANGE); @@ -1202,11 +1215,20 @@ static int loop_clr_fd(struct loop_device *lo) { int err; - err = mutex_lock_killable(&lo->lo_mutex); + /* + * Since lo_ioctl() is called without locks held, it is possible that + * loop_configure()/loop_change_fd() and loop_clr_fd() run in parallel. + * + * Therefore, use global lock when setting Lo_rundown state in order to + * make sure that loop_validate_file() will fail if the "struct file" + * which loop_configure()/loop_change_fd() found via fget() was this + * loop device. + */ + err = loop_global_lock_killable(lo, true); if (err) return err; if (lo->lo_state != Lo_bound) { - mutex_unlock(&lo->lo_mutex); + loop_global_unlock(lo, true); return -ENXIO; } /* @@ -1219,13 +1241,13 @@ static int loop_clr_fd(struct loop_device *lo) * <dev>/do something like mkfs/losetup -d <dev> causing the losetup -d * command to fail with EBUSY. */ - if (atomic_read(&lo->lo_refcnt) > 1) { + if (disk_openers(lo->lo_disk) > 1) { lo->lo_flags |= LO_FLAGS_AUTOCLEAR; - mutex_unlock(&lo->lo_mutex); + loop_global_unlock(lo, true); return 0; } lo->lo_state = Lo_rundown; - mutex_unlock(&lo->lo_mutex); + loop_global_unlock(lo, true); __loop_clr_fd(lo, false); return 0; @@ -1257,15 +1279,6 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info) /* I/O need to be drained during transfer transition */ blk_mq_freeze_queue(lo->lo_queue); - if (size_changed && lo->lo_device->bd_inode->i_mapping->nrpages) { - /* If any pages were dirtied after invalidate_bdev(), try again */ - err = -EAGAIN; - pr_warn("%s: loop%d (%s) still has dirty pages (nrpages=%lu)\n", - __func__, lo->lo_number, lo->lo_file_name, - lo->lo_device->bd_inode->i_mapping->nrpages); - goto out_unfreeze; - } - prev_lo_flags = lo->lo_flags; err = loop_set_status_from_info(lo, info); @@ -1476,21 +1489,10 @@ static int loop_set_block_size(struct loop_device *lo, unsigned long arg) invalidate_bdev(lo->lo_device); blk_mq_freeze_queue(lo->lo_queue); - - /* invalidate_bdev should have truncated all the pages */ - if (lo->lo_device->bd_inode->i_mapping->nrpages) { - err = -EAGAIN; - pr_warn("%s: loop%d (%s) still has dirty pages (nrpages=%lu)\n", - __func__, lo->lo_number, lo->lo_file_name, - lo->lo_device->bd_inode->i_mapping->nrpages); - goto out_unfreeze; - } - blk_queue_logical_block_size(lo->lo_queue, arg); blk_queue_physical_block_size(lo->lo_queue, arg); blk_queue_io_min(lo->lo_queue, arg); loop_update_dio(lo); -out_unfreeze: blk_mq_unfreeze_queue(lo->lo_queue); return err; @@ -1720,33 +1722,15 @@ static int lo_compat_ioctl(struct block_device *bdev, fmode_t mode, } #endif -static int lo_open(struct block_device *bdev, fmode_t mode) -{ - struct loop_device *lo = bdev->bd_disk->private_data; - int err; - - err = mutex_lock_killable(&lo->lo_mutex); - if (err) - return err; - if (lo->lo_state == Lo_deleting) - err = -ENXIO; - else - atomic_inc(&lo->lo_refcnt); - mutex_unlock(&lo->lo_mutex); - return err; -} - static void lo_release(struct gendisk *disk, fmode_t mode) { struct loop_device *lo = disk->private_data; - mutex_lock(&lo->lo_mutex); - if (atomic_dec_return(&lo->lo_refcnt)) - goto out_unlock; + if (disk_openers(disk) > 0) + return; - if (lo->lo_flags & LO_FLAGS_AUTOCLEAR) { - if (lo->lo_state != Lo_bound) - goto out_unlock; + mutex_lock(&lo->lo_mutex); + if (lo->lo_state == Lo_bound && (lo->lo_flags & LO_FLAGS_AUTOCLEAR)) { lo->lo_state = Lo_rundown; mutex_unlock(&lo->lo_mutex); /* @@ -1755,27 +1739,30 @@ static void lo_release(struct gendisk *disk, fmode_t mode) */ __loop_clr_fd(lo, true); return; - } else if (lo->lo_state == Lo_bound) { - /* - * Otherwise keep thread (if running) and config, - * but flush possible ongoing bios in thread. - */ - blk_mq_freeze_queue(lo->lo_queue); - blk_mq_unfreeze_queue(lo->lo_queue); } - -out_unlock: mutex_unlock(&lo->lo_mutex); } +static void lo_free_disk(struct gendisk *disk) +{ + struct loop_device *lo = disk->private_data; + + if (lo->workqueue) + destroy_workqueue(lo->workqueue); + loop_free_idle_workers(lo, true); + del_timer_sync(&lo->timer); + mutex_destroy(&lo->lo_mutex); + kfree(lo); +} + static const struct block_device_operations lo_fops = { .owner = THIS_MODULE, - .open = lo_open, .release = lo_release, .ioctl = lo_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = lo_compat_ioctl, #endif + .free_disk = lo_free_disk, }; /* @@ -1834,12 +1821,14 @@ static blk_status_t loop_queue_rq(struct blk_mq_hw_ctx *hctx, cmd->blkcg_css = NULL; cmd->memcg_css = NULL; #ifdef CONFIG_BLK_CGROUP - if (rq->bio && rq->bio->bi_blkg) { - cmd->blkcg_css = &bio_blkcg(rq->bio)->css; + if (rq->bio) { + cmd->blkcg_css = bio_blkcg_css(rq->bio); #ifdef CONFIG_MEMCG - cmd->memcg_css = - cgroup_get_e_css(cmd->blkcg_css->cgroup, - &memory_cgrp_subsys); + if (cmd->blkcg_css) { + cmd->memcg_css = + cgroup_get_e_css(cmd->blkcg_css->cgroup, + &memory_cgrp_subsys); + } #endif } #endif @@ -1888,11 +1877,6 @@ static void loop_handle_cmd(struct loop_cmd *cmd) } } -static void loop_set_timer(struct loop_device *lo) -{ - timer_reduce(&lo->timer, jiffies + LOOP_IDLE_WORKER_TIMEOUT); -} - static void loop_process_work(struct loop_worker *worker, struct list_head *cmd_list, struct loop_device *lo) { @@ -1941,27 +1925,6 @@ static void loop_rootcg_workfn(struct work_struct *work) loop_process_work(NULL, &lo->rootcg_cmd_list, lo); } -static void loop_free_idle_workers(struct timer_list *timer) -{ - struct loop_device *lo = container_of(timer, struct loop_device, timer); - struct loop_worker *pos, *worker; - - spin_lock_irq(&lo->lo_work_lock); - list_for_each_entry_safe(worker, pos, &lo->idle_worker_list, - idle_list) { - if (time_is_after_jiffies(worker->last_ran_at + - LOOP_IDLE_WORKER_TIMEOUT)) - break; - list_del(&worker->idle_list); - rb_erase(&worker->rb_node, &lo->worker_tree); - css_put(worker->blkcg_css); - kfree(worker); - } - if (!list_empty(&lo->idle_worker_list)) - loop_set_timer(lo); - spin_unlock_irq(&lo->lo_work_lock); -} - static const struct blk_mq_ops loop_mq_ops = { .queue_rq = loop_queue_rq, .complete = lo_complete_rq, @@ -1977,6 +1940,9 @@ static int loop_add(int i) lo = kzalloc(sizeof(*lo), GFP_KERNEL); if (!lo) goto out; + lo->worker_tree = RB_ROOT; + INIT_LIST_HEAD(&lo->idle_worker_list); + timer_setup(&lo->timer, loop_free_idle_workers_timer, TIMER_DEFERRABLE); lo->lo_state = Lo_unbound; err = mutex_lock_killable(&loop_ctl_mutex); @@ -2046,11 +2012,12 @@ static int loop_add(int i) */ if (!part_shift) disk->flags |= GENHD_FL_NO_PART; - atomic_set(&lo->lo_refcnt, 0); mutex_init(&lo->lo_mutex); lo->lo_number = i; spin_lock_init(&lo->lo_lock); spin_lock_init(&lo->lo_work_lock); + INIT_WORK(&lo->rootcg_work, loop_rootcg_workfn); + INIT_LIST_HEAD(&lo->rootcg_cmd_list); disk->major = LOOP_MAJOR; disk->first_minor = i << part_shift; disk->minors = 1 << part_shift; @@ -2090,15 +2057,14 @@ static void loop_remove(struct loop_device *lo) { /* Make this loop device unreachable from pathname. */ del_gendisk(lo->lo_disk); - blk_cleanup_disk(lo->lo_disk); + blk_cleanup_queue(lo->lo_disk->queue); blk_mq_free_tag_set(&lo->tag_set); mutex_lock(&loop_ctl_mutex); idr_remove(&loop_index_idr, lo->lo_number); mutex_unlock(&loop_ctl_mutex); - /* There is no route which can find this loop device. */ - mutex_destroy(&lo->lo_mutex); - kfree(lo); + + put_disk(lo->lo_disk); } static void loop_probe(dev_t dev) @@ -2137,13 +2103,12 @@ static int loop_control_remove(int idx) ret = mutex_lock_killable(&lo->lo_mutex); if (ret) goto mark_visible; - if (lo->lo_state != Lo_unbound || - atomic_read(&lo->lo_refcnt) > 0) { + if (lo->lo_state != Lo_unbound || disk_openers(lo->lo_disk) > 0) { mutex_unlock(&lo->lo_mutex); ret = -EBUSY; goto mark_visible; } - /* Mark this loop device no longer open()-able. */ + /* Mark this loop device as no more bound, but not quite unbound yet */ lo->lo_state = Lo_deleting; mutex_unlock(&lo->lo_mutex); diff --git a/drivers/block/loop.h b/drivers/block/loop.h deleted file mode 100644 index 082d4b6bfc6a..000000000000 --- a/drivers/block/loop.h +++ /dev/null @@ -1,72 +0,0 @@ -/* - * loop.h - * - * Written by Theodore Ts'o, 3/29/93. - * - * Copyright 1993 by Theodore Ts'o. Redistribution of this file is - * permitted under the GNU General Public License. - */ -#ifndef _LINUX_LOOP_H -#define _LINUX_LOOP_H - -#include <linux/bio.h> -#include <linux/blkdev.h> -#include <linux/blk-mq.h> -#include <linux/spinlock.h> -#include <linux/mutex.h> -#include <uapi/linux/loop.h> - -/* Possible states of device */ -enum { - Lo_unbound, - Lo_bound, - Lo_rundown, - Lo_deleting, -}; - -struct loop_func_table; - -struct loop_device { - int lo_number; - atomic_t lo_refcnt; - loff_t lo_offset; - loff_t lo_sizelimit; - int lo_flags; - char lo_file_name[LO_NAME_SIZE]; - - struct file * lo_backing_file; - struct block_device *lo_device; - - gfp_t old_gfp_mask; - - spinlock_t lo_lock; - int lo_state; - spinlock_t lo_work_lock; - struct workqueue_struct *workqueue; - struct work_struct rootcg_work; - struct list_head rootcg_cmd_list; - struct list_head idle_worker_list; - struct rb_root worker_tree; - struct timer_list timer; - bool use_dio; - bool sysfs_inited; - - struct request_queue *lo_queue; - struct blk_mq_tag_set tag_set; - struct gendisk *lo_disk; - struct mutex lo_mutex; - bool idr_visible; -}; - -struct loop_cmd { - struct list_head list_entry; - bool use_aio; /* use AIO interface to handle I/O */ - atomic_t ref; /* only for aio */ - long ret; - struct kiocb iocb; - struct bio_vec *bvec; - struct cgroup_subsys_state *blkcg_css; - struct cgroup_subsys_state *memcg_css; -}; - -#endif diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c index 4fbaf0b4958b..27386a572ba4 100644 --- a/drivers/block/mtip32xx/mtip32xx.c +++ b/drivers/block/mtip32xx/mtip32xx.c @@ -2729,7 +2729,7 @@ static int mtip_dma_alloc(struct driver_data *dd) { struct mtip_port *port = dd->port; - /* Allocate dma memory for RX Fis, Identify, and Sector Bufffer */ + /* Allocate dma memory for RX Fis, Identify, and Sector Buffer */ port->block1 = dma_alloc_coherent(&dd->pdev->dev, BLOCK_DMA_ALLOC_SZ, &port->block1_dma, GFP_KERNEL); diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 5a1f98494ddd..ac8b045c777c 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -333,7 +333,6 @@ static int nbd_set_size(struct nbd_device *nbd, loff_t bytesize, if (nbd->config->flags & NBD_FLAG_SEND_TRIM) { nbd->disk->queue->limits.discard_granularity = blksize; - nbd->disk->queue->limits.discard_alignment = blksize; blk_queue_max_discard_sectors(nbd->disk->queue, UINT_MAX); } blk_queue_logical_block_size(nbd->disk->queue, blksize); @@ -947,11 +946,15 @@ static int wait_for_reconnect(struct nbd_device *nbd) struct nbd_config *config = nbd->config; if (!config->dead_conn_timeout) return 0; - if (test_bit(NBD_RT_DISCONNECTED, &config->runtime_flags)) + + if (!wait_event_timeout(config->conn_wait, + test_bit(NBD_RT_DISCONNECTED, + &config->runtime_flags) || + atomic_read(&config->live_connections) > 0, + config->dead_conn_timeout)) return 0; - return wait_event_timeout(config->conn_wait, - atomic_read(&config->live_connections) > 0, - config->dead_conn_timeout) > 0; + + return !test_bit(NBD_RT_DISCONNECTED, &config->runtime_flags); } static int nbd_handle_cmd(struct nbd_cmd *cmd, int index) @@ -1217,11 +1220,11 @@ static int nbd_reconnect_socket(struct nbd_device *nbd, unsigned long arg) return -ENOSPC; } -static void nbd_bdev_reset(struct block_device *bdev) +static void nbd_bdev_reset(struct nbd_device *nbd) { - if (bdev->bd_openers > 1) + if (disk_openers(nbd->disk) > 1) return; - set_capacity(bdev->bd_disk, 0); + set_capacity(nbd->disk, 0); } static void nbd_parse_flags(struct nbd_device *nbd) @@ -1231,8 +1234,6 @@ static void nbd_parse_flags(struct nbd_device *nbd) set_disk_ro(nbd->disk, true); else set_disk_ro(nbd->disk, false); - if (config->flags & NBD_FLAG_SEND_TRIM) - blk_queue_flag_set(QUEUE_FLAG_DISCARD, nbd->disk->queue); if (config->flags & NBD_FLAG_SEND_FLUSH) { if (config->flags & NBD_FLAG_SEND_FUA) blk_queue_write_cache(nbd->disk->queue, true, true); @@ -1318,9 +1319,7 @@ static void nbd_config_put(struct nbd_device *nbd) nbd->tag_set.timeout = 0; nbd->disk->queue->limits.discard_granularity = 0; - nbd->disk->queue->limits.discard_alignment = 0; - blk_queue_max_discard_sectors(nbd->disk->queue, UINT_MAX); - blk_queue_flag_clear(QUEUE_FLAG_DISCARD, nbd->disk->queue); + blk_queue_max_discard_sectors(nbd->disk->queue, 0); mutex_unlock(&nbd->config_lock); nbd_put(nbd); @@ -1389,7 +1388,7 @@ static int nbd_start_device(struct nbd_device *nbd) return nbd_set_size(nbd, config->bytesize, nbd_blksize(config)); } -static int nbd_start_device_ioctl(struct nbd_device *nbd, struct block_device *bdev) +static int nbd_start_device_ioctl(struct nbd_device *nbd) { struct nbd_config *config = nbd->config; int ret; @@ -1408,7 +1407,7 @@ static int nbd_start_device_ioctl(struct nbd_device *nbd, struct block_device *b flush_workqueue(nbd->recv_workq); mutex_lock(&nbd->config_lock); - nbd_bdev_reset(bdev); + nbd_bdev_reset(nbd); /* user requested, ignore socket errors */ if (test_bit(NBD_RT_DISCONNECT_REQUESTED, &config->runtime_flags)) ret = 0; @@ -1422,7 +1421,7 @@ static void nbd_clear_sock_ioctl(struct nbd_device *nbd, { sock_shutdown(nbd); __invalidate_device(bdev, true); - nbd_bdev_reset(bdev); + nbd_bdev_reset(nbd); if (test_and_clear_bit(NBD_RT_HAS_CONFIG_REF, &nbd->config->runtime_flags)) nbd_config_put(nbd); @@ -1468,7 +1467,7 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd, config->flags = arg; return 0; case NBD_DO_IT: - return nbd_start_device_ioctl(nbd, bdev); + return nbd_start_device_ioctl(nbd); case NBD_CLEAR_QUE: /* * This is for compatibility only. The queue is always cleared @@ -1579,7 +1578,7 @@ static void nbd_release(struct gendisk *disk, fmode_t mode) struct nbd_device *nbd = disk->private_data; if (test_bit(NBD_RT_DISCONNECT_ON_CLOSE, &nbd->config->runtime_flags) && - disk->part0->bd_openers == 0) + disk_openers(disk) == 0) nbd_disconnect_and_put(nbd); nbd_config_put(nbd); @@ -1784,7 +1783,6 @@ static struct nbd_device *nbd_dev_add(int index, unsigned int refs) blk_queue_flag_set(QUEUE_FLAG_NONROT, disk->queue); blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, disk->queue); disk->queue->limits.discard_granularity = 0; - disk->queue->limits.discard_alignment = 0; blk_queue_max_discard_sectors(disk->queue, 0); blk_queue_max_segment_size(disk->queue, UINT_MAX); blk_queue_max_segments(disk->queue, USHRT_MAX); @@ -2082,6 +2080,7 @@ static void nbd_disconnect_and_put(struct nbd_device *nbd) mutex_lock(&nbd->config_lock); nbd_disconnect(nbd); sock_shutdown(nbd); + wake_up(&nbd->config->conn_wait); /* * Make sure recv thread has finished, we can safely call nbd_clear_que() * to cancel the inflight I/Os. diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c index 05b1120e6623..539cfeac263d 100644 --- a/drivers/block/null_blk/main.c +++ b/drivers/block/null_blk/main.c @@ -11,6 +11,9 @@ #include <linux/init.h> #include "null_blk.h" +#undef pr_fmt +#define pr_fmt(fmt) "null_blk: " fmt + #define FREE_BATCH 16 #define TICKS_PER_SEC 50ULL @@ -232,6 +235,7 @@ static struct nullb_device *null_alloc_dev(void); static void null_free_dev(struct nullb_device *dev); static void null_del_dev(struct nullb *nullb); static int null_add_dev(struct nullb_device *dev); +static struct nullb *null_find_dev_by_name(const char *name); static void null_free_device_storage(struct nullb_device *dev, bool is_cache); static inline struct nullb_device *to_nullb_device(struct config_item *item) @@ -560,6 +564,9 @@ config_item *nullb_group_make_item(struct config_group *group, const char *name) { struct nullb_device *dev; + if (null_find_dev_by_name(name)) + return ERR_PTR(-EEXIST); + dev = null_alloc_dev(); if (!dev) return ERR_PTR(-ENOMEM); @@ -1600,7 +1607,7 @@ static enum blk_eh_timer_return null_timeout_rq(struct request *rq, bool res) * Only fake timeouts need to execute blk_mq_complete_request() here. */ cmd->error = BLK_STS_TIMEOUT; - if (cmd->fake_timeout) + if (cmd->fake_timeout || hctx->type == HCTX_TYPE_POLL) blk_mq_complete_request(rq); return BLK_EH_DONE; } @@ -1765,9 +1772,7 @@ static void null_config_discard(struct nullb *nullb) } nullb->q->limits.discard_granularity = nullb->dev->blocksize; - nullb->q->limits.discard_alignment = nullb->dev->blocksize; blk_queue_max_discard_sectors(nullb->q, UINT_MAX >> 9); - blk_queue_flag_set(QUEUE_FLAG_DISCARD, nullb->q); } static const struct block_device_operations null_bio_ops = { @@ -2061,7 +2066,13 @@ static int null_add_dev(struct nullb_device *dev) null_config_discard(nullb); - sprintf(nullb->disk_name, "nullb%d", nullb->index); + if (config_item_name(&dev->item)) { + /* Use configfs dir name as the device name */ + snprintf(nullb->disk_name, sizeof(nullb->disk_name), + "%s", config_item_name(&dev->item)); + } else { + sprintf(nullb->disk_name, "nullb%d", nullb->index); + } rv = null_gendisk_register(nullb); if (rv) @@ -2071,6 +2082,8 @@ static int null_add_dev(struct nullb_device *dev) list_add_tail(&nullb->list, &nullb_list); mutex_unlock(&lock); + pr_info("disk %s created\n", nullb->disk_name); + return 0; out_cleanup_zone: null_free_zoned_dev(dev); @@ -2088,12 +2101,53 @@ out: return rv; } +static struct nullb *null_find_dev_by_name(const char *name) +{ + struct nullb *nullb = NULL, *nb; + + mutex_lock(&lock); + list_for_each_entry(nb, &nullb_list, list) { + if (strcmp(nb->disk_name, name) == 0) { + nullb = nb; + break; + } + } + mutex_unlock(&lock); + + return nullb; +} + +static int null_create_dev(void) +{ + struct nullb_device *dev; + int ret; + + dev = null_alloc_dev(); + if (!dev) + return -ENOMEM; + + ret = null_add_dev(dev); + if (ret) { + null_free_dev(dev); + return ret; + } + + return 0; +} + +static void null_destroy_dev(struct nullb *nullb) +{ + struct nullb_device *dev = nullb->dev; + + null_del_dev(nullb); + null_free_dev(dev); +} + static int __init null_init(void) { int ret = 0; unsigned int i; struct nullb *nullb; - struct nullb_device *dev; if (g_bs > PAGE_SIZE) { pr_warn("invalid block size\n"); @@ -2113,19 +2167,21 @@ static int __init null_init(void) } if (g_queue_mode == NULL_Q_RQ) { - pr_err("legacy IO path no longer available\n"); + pr_err("legacy IO path is no longer available\n"); return -EINVAL; } + if (g_queue_mode == NULL_Q_MQ && g_use_per_node_hctx) { if (g_submit_queues != nr_online_nodes) { pr_warn("submit_queues param is set to %u.\n", - nr_online_nodes); + nr_online_nodes); g_submit_queues = nr_online_nodes; } - } else if (g_submit_queues > nr_cpu_ids) + } else if (g_submit_queues > nr_cpu_ids) { g_submit_queues = nr_cpu_ids; - else if (g_submit_queues <= 0) + } else if (g_submit_queues <= 0) { g_submit_queues = 1; + } if (g_queue_mode == NULL_Q_MQ && shared_tags) { ret = null_init_tag_set(NULL, &tag_set); @@ -2149,16 +2205,9 @@ static int __init null_init(void) } for (i = 0; i < nr_devices; i++) { - dev = null_alloc_dev(); - if (!dev) { - ret = -ENOMEM; - goto err_dev; - } - ret = null_add_dev(dev); - if (ret) { - null_free_dev(dev); + ret = null_create_dev(); + if (ret) goto err_dev; - } } pr_info("module loaded\n"); @@ -2167,9 +2216,7 @@ static int __init null_init(void) err_dev: while (!list_empty(&nullb_list)) { nullb = list_entry(nullb_list.next, struct nullb, list); - dev = nullb->dev; - null_del_dev(nullb); - null_free_dev(dev); + null_destroy_dev(nullb); } unregister_blkdev(null_major, "nullb"); err_conf: @@ -2190,12 +2237,8 @@ static void __exit null_exit(void) mutex_lock(&lock); while (!list_empty(&nullb_list)) { - struct nullb_device *dev; - nullb = list_entry(nullb_list.next, struct nullb, list); - dev = nullb->dev; - null_del_dev(nullb); - null_free_dev(dev); + null_destroy_dev(nullb); } mutex_unlock(&lock); diff --git a/drivers/block/null_blk/null_blk.h b/drivers/block/null_blk/null_blk.h index 78eb56b0ca55..4525a65e1b23 100644 --- a/drivers/block/null_blk/null_blk.h +++ b/drivers/block/null_blk/null_blk.h @@ -16,13 +16,15 @@ #include <linux/mutex.h> struct nullb_cmd { - struct request *rq; - struct bio *bio; + union { + struct request *rq; + struct bio *bio; + }; unsigned int tag; blk_status_t error; + bool fake_timeout; struct nullb_queue *nq; struct hrtimer timer; - bool fake_timeout; }; struct nullb_queue { diff --git a/drivers/block/null_blk/zoned.c b/drivers/block/null_blk/zoned.c index dae54dd1aeac..ed158ea4fdd1 100644 --- a/drivers/block/null_blk/zoned.c +++ b/drivers/block/null_blk/zoned.c @@ -6,6 +6,9 @@ #define CREATE_TRACE_POINTS #include "trace.h" +#undef pr_fmt +#define pr_fmt(fmt) "null_blk: " fmt + static inline sector_t mb_to_sects(unsigned long mb) { return ((sector_t)mb * SZ_1M) >> SECTOR_SHIFT; @@ -75,8 +78,8 @@ int null_init_zoned_dev(struct nullb_device *dev, struct request_queue *q) dev->zone_capacity = dev->zone_size; if (dev->zone_capacity > dev->zone_size) { - pr_err("null_blk: zone capacity (%lu MB) larger than zone size (%lu MB)\n", - dev->zone_capacity, dev->zone_size); + pr_err("zone capacity (%lu MB) larger than zone size (%lu MB)\n", + dev->zone_capacity, dev->zone_size); return -EINVAL; } diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index 86c8794ede41..789093375344 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -12,7 +12,7 @@ * Theory of operation: * * At the lowest level, there is the standard driver for the CD/DVD device, - * typically ide-cd.c or sr.c. This driver can handle read and write requests, + * such as drivers/scsi/sr.c. This driver can handle read and write requests, * but it doesn't know anything about the special restrictions that apply to * packet writing. One restriction is that write requests must be aligned to * packet boundaries on the physical media, and the size of a write request @@ -522,7 +522,7 @@ static struct packet_data *pkt_alloc_packet_data(int frames) goto no_pkt; pkt->frames = frames; - pkt->w_bio = bio_kmalloc(GFP_KERNEL, frames); + pkt->w_bio = bio_kmalloc(frames, GFP_KERNEL); if (!pkt->w_bio) goto no_bio; @@ -536,27 +536,21 @@ static struct packet_data *pkt_alloc_packet_data(int frames) bio_list_init(&pkt->orig_bios); for (i = 0; i < frames; i++) { - struct bio *bio = bio_kmalloc(GFP_KERNEL, 1); - if (!bio) + pkt->r_bios[i] = bio_kmalloc(1, GFP_KERNEL); + if (!pkt->r_bios[i]) goto no_rd_bio; - - pkt->r_bios[i] = bio; } return pkt; no_rd_bio: - for (i = 0; i < frames; i++) { - struct bio *bio = pkt->r_bios[i]; - if (bio) - bio_put(bio); - } - + for (i = 0; i < frames; i++) + kfree(pkt->r_bios[i]); no_page: for (i = 0; i < frames / FRAMES_PER_PAGE; i++) if (pkt->pages[i]) __free_page(pkt->pages[i]); - bio_put(pkt->w_bio); + kfree(pkt->w_bio); no_bio: kfree(pkt); no_pkt: @@ -570,14 +564,11 @@ static void pkt_free_packet_data(struct packet_data *pkt) { int i; - for (i = 0; i < pkt->frames; i++) { - struct bio *bio = pkt->r_bios[i]; - if (bio) - bio_put(bio); - } + for (i = 0; i < pkt->frames; i++) + kfree(pkt->r_bios[i]); for (i = 0; i < pkt->frames / FRAMES_PER_PAGE; i++) __free_page(pkt->pages[i]); - bio_put(pkt->w_bio); + kfree(pkt->w_bio); kfree(pkt); } @@ -951,6 +942,7 @@ static void pkt_end_io_read(struct bio *bio) if (bio->bi_status) atomic_inc(&pkt->io_errors); + bio_uninit(bio); if (atomic_dec_and_test(&pkt->io_wait)) { atomic_inc(&pkt->run_sm); wake_up(&pd->wqueue); @@ -968,6 +960,7 @@ static void pkt_end_io_packet_write(struct bio *bio) pd->stats.pkt_ended++; + bio_uninit(bio); pkt_bio_finished(pd); atomic_dec(&pkt->io_wait); atomic_inc(&pkt->run_sm); @@ -1022,7 +1015,7 @@ static void pkt_gather_data(struct pktcdvd_device *pd, struct packet_data *pkt) continue; bio = pkt->r_bios[f]; - bio_reset(bio, pd->bdev, REQ_OP_READ); + bio_init(bio, pd->bdev, bio->bi_inline_vecs, 1, REQ_OP_READ); bio->bi_iter.bi_sector = pkt->sector + f * (CD_FRAMESIZE >> 9); bio->bi_end_io = pkt_end_io_read; bio->bi_private = pkt; @@ -1235,7 +1228,8 @@ static void pkt_start_write(struct pktcdvd_device *pd, struct packet_data *pkt) { int f; - bio_reset(pkt->w_bio, pd->bdev, REQ_OP_WRITE); + bio_init(pkt->w_bio, pd->bdev, pkt->w_bio->bi_inline_vecs, pkt->frames, + REQ_OP_WRITE); pkt->w_bio->bi_iter.bi_sector = pkt->sector; pkt->w_bio->bi_end_io = pkt_end_io_packet_write; pkt->w_bio->bi_private = pkt; diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index b844432bad20..2b21f717cce1 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -4942,7 +4942,6 @@ static int rbd_init_disk(struct rbd_device *rbd_dev) blk_queue_io_opt(q, rbd_dev->opts->alloc_size); if (rbd_dev->opts->trim) { - blk_queue_flag_set(QUEUE_FLAG_DISCARD, q); q->limits.discard_granularity = rbd_dev->opts->alloc_size; blk_queue_max_discard_sectors(q, objset_bytes >> SECTOR_SHIFT); blk_queue_max_write_zeroes_sectors(q, objset_bytes >> SECTOR_SHIFT); diff --git a/drivers/block/rnbd/rnbd-clt.c b/drivers/block/rnbd/rnbd-clt.c index b66e8840b94b..409c76b81aed 100644 --- a/drivers/block/rnbd/rnbd-clt.c +++ b/drivers/block/rnbd/rnbd-clt.c @@ -25,6 +25,7 @@ static int rnbd_client_major; static DEFINE_IDA(index_ida); static DEFINE_MUTEX(sess_lock); static LIST_HEAD(sess_list); +static struct workqueue_struct *rnbd_clt_wq; /* * Maximum number of partitions an instance can have. @@ -1364,11 +1365,9 @@ static void setup_request_queue(struct rnbd_clt_dev *dev) blk_queue_max_discard_sectors(dev->queue, dev->max_discard_sectors); dev->queue->limits.discard_granularity = dev->discard_granularity; dev->queue->limits.discard_alignment = dev->discard_alignment; - if (dev->max_discard_sectors) - blk_queue_flag_set(QUEUE_FLAG_DISCARD, dev->queue); if (dev->secure_discard) - blk_queue_flag_set(QUEUE_FLAG_SECERASE, dev->queue); - + blk_queue_max_secure_erase_sectors(dev->queue, + dev->max_discard_sectors); blk_queue_flag_set(QUEUE_FLAG_SAME_COMP, dev->queue); blk_queue_flag_set(QUEUE_FLAG_SAME_FORCE, dev->queue); blk_queue_max_segments(dev->queue, dev->max_segments); @@ -1761,12 +1760,12 @@ static void rnbd_destroy_sessions(void) * procedure takes minutes. */ INIT_WORK(&dev->unmap_on_rmmod_work, unmap_device_work); - queue_work(system_long_wq, &dev->unmap_on_rmmod_work); + queue_work(rnbd_clt_wq, &dev->unmap_on_rmmod_work); } rnbd_clt_put_sess(sess); } /* Wait for all scheduled unmap works */ - flush_workqueue(system_long_wq); + flush_workqueue(rnbd_clt_wq); WARN_ON(!list_empty(&sess_list)); } @@ -1791,6 +1790,14 @@ static int __init rnbd_client_init(void) pr_err("Failed to load module, creating sysfs device files failed, err: %d\n", err); unregister_blkdev(rnbd_client_major, "rnbd"); + return err; + } + rnbd_clt_wq = alloc_workqueue("rnbd_clt_wq", 0, 0); + if (!rnbd_clt_wq) { + pr_err("Failed to load module, alloc_workqueue failed.\n"); + rnbd_clt_destroy_sysfs_files(); + unregister_blkdev(rnbd_client_major, "rnbd"); + err = -ENOMEM; } return err; @@ -1801,6 +1808,7 @@ static void __exit rnbd_client_exit(void) rnbd_destroy_sessions(); unregister_blkdev(rnbd_client_major, "rnbd"); ida_destroy(&index_ida); + destroy_workqueue(rnbd_clt_wq); } module_init(rnbd_client_init); diff --git a/drivers/block/rnbd/rnbd-srv-dev.h b/drivers/block/rnbd/rnbd-srv-dev.h index 2c3df02b5e8e..4309e5252469 100644 --- a/drivers/block/rnbd/rnbd-srv-dev.h +++ b/drivers/block/rnbd/rnbd-srv-dev.h @@ -44,16 +44,12 @@ static inline int rnbd_dev_get_max_hw_sects(const struct rnbd_dev *dev) static inline int rnbd_dev_get_secure_discard(const struct rnbd_dev *dev) { - return blk_queue_secure_erase(bdev_get_queue(dev->bdev)); + return bdev_max_secure_erase_sectors(dev->bdev); } static inline int rnbd_dev_get_max_discard_sects(const struct rnbd_dev *dev) { - if (!blk_queue_discard(bdev_get_queue(dev->bdev))) - return 0; - - return blk_queue_get_max_sectors(bdev_get_queue(dev->bdev), - REQ_OP_DISCARD); + return bdev_max_discard_sectors(dev->bdev); } static inline int rnbd_dev_get_discard_granularity(const struct rnbd_dev *dev) @@ -63,7 +59,7 @@ static inline int rnbd_dev_get_discard_granularity(const struct rnbd_dev *dev) static inline int rnbd_dev_get_discard_alignment(const struct rnbd_dev *dev) { - return bdev_get_queue(dev->bdev)->limits.discard_alignment; + return bdev_discard_alignment(dev->bdev); } #endif /* RNBD_SRV_DEV_H */ diff --git a/drivers/block/rnbd/rnbd-srv.c b/drivers/block/rnbd/rnbd-srv.c index f04df6294650..beaef43a67b9 100644 --- a/drivers/block/rnbd/rnbd-srv.c +++ b/drivers/block/rnbd/rnbd-srv.c @@ -533,7 +533,6 @@ static void rnbd_srv_fill_msg_open_rsp(struct rnbd_msg_open_rsp *rsp, struct rnbd_srv_sess_dev *sess_dev) { struct rnbd_dev *rnbd_dev = sess_dev->rnbd_dev; - struct request_queue *q = bdev_get_queue(rnbd_dev->bdev); rsp->hdr.type = cpu_to_le16(RNBD_MSG_OPEN_RSP); rsp->device_id = @@ -558,9 +557,9 @@ static void rnbd_srv_fill_msg_open_rsp(struct rnbd_msg_open_rsp *rsp, rsp->secure_discard = cpu_to_le16(rnbd_dev_get_secure_discard(rnbd_dev)); rsp->cache_policy = 0; - if (test_bit(QUEUE_FLAG_WC, &q->queue_flags)) + if (bdev_write_cache(rnbd_dev->bdev)) rsp->cache_policy |= RNBD_WRITEBACK; - if (blk_queue_fua(q)) + if (bdev_fua(rnbd_dev->bdev)) rsp->cache_policy |= RNBD_FUA; } diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index a8bcf3f664af..d624cc8eddc3 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -867,11 +867,12 @@ static int virtblk_probe(struct virtio_device *vdev) blk_queue_io_opt(q, blk_size * opt_io_size); if (virtio_has_feature(vdev, VIRTIO_BLK_F_DISCARD)) { - q->limits.discard_granularity = blk_size; - virtio_cread(vdev, struct virtio_blk_config, discard_sector_alignment, &v); - q->limits.discard_alignment = v ? v << SECTOR_SHIFT : 0; + if (v) + q->limits.discard_granularity = v << SECTOR_SHIFT; + else + q->limits.discard_granularity = blk_size; virtio_cread(vdev, struct virtio_blk_config, max_discard_sectors, &v); @@ -888,8 +889,6 @@ static int virtblk_probe(struct virtio_device *vdev) v = sg_elems; blk_queue_max_discard_segments(q, min(v, MAX_DISCARD_SEGMENTS)); - - blk_queue_flag_set(QUEUE_FLAG_DISCARD, q); } if (virtio_has_feature(vdev, VIRTIO_BLK_F_WRITE_ZEROES)) { diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c index de42458195bc..a97f2bf5b01b 100644 --- a/drivers/block/xen-blkback/blkback.c +++ b/drivers/block/xen-blkback/blkback.c @@ -970,7 +970,6 @@ static int dispatch_discard_io(struct xen_blkif_ring *ring, int status = BLKIF_RSP_OKAY; struct xen_blkif *blkif = ring->blkif; struct block_device *bdev = blkif->vbd.bdev; - unsigned long secure; struct phys_req preq; xen_blkif_get(blkif); @@ -987,13 +986,15 @@ static int dispatch_discard_io(struct xen_blkif_ring *ring, } ring->st_ds_req++; - secure = (blkif->vbd.discard_secure && - (req->u.discard.flag & BLKIF_DISCARD_SECURE)) ? - BLKDEV_DISCARD_SECURE : 0; + if (blkif->vbd.discard_secure && + (req->u.discard.flag & BLKIF_DISCARD_SECURE)) + err = blkdev_issue_secure_erase(bdev, + req->u.discard.sector_number, + req->u.discard.nr_sectors, GFP_KERNEL); + else + err = blkdev_issue_discard(bdev, req->u.discard.sector_number, + req->u.discard.nr_sectors, GFP_KERNEL); - err = blkdev_issue_discard(bdev, req->u.discard.sector_number, - req->u.discard.nr_sectors, - GFP_KERNEL, secure); fail_response: if (err == -EOPNOTSUPP) { pr_debug("discard op failed, not supported\n"); diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c index f09040435e2e..97de13b14175 100644 --- a/drivers/block/xen-blkback/xenbus.c +++ b/drivers/block/xen-blkback/xenbus.c @@ -484,7 +484,6 @@ static int xen_vbd_create(struct xen_blkif *blkif, blkif_vdev_t handle, { struct xen_vbd *vbd; struct block_device *bdev; - struct request_queue *q; vbd = &blkif->vbd; vbd->handle = handle; @@ -516,11 +515,9 @@ static int xen_vbd_create(struct xen_blkif *blkif, blkif_vdev_t handle, if (vbd->bdev->bd_disk->flags & GENHD_FL_REMOVABLE) vbd->type |= VDISK_REMOVABLE; - q = bdev_get_queue(bdev); - if (q && test_bit(QUEUE_FLAG_WC, &q->queue_flags)) + if (bdev_write_cache(bdev)) vbd->flush_support = true; - - if (q && blk_queue_secure_erase(q)) + if (bdev_max_secure_erase_sectors(bdev)) vbd->discard_secure = true; vbd->feature_gnt_persistent = feature_persistent; @@ -578,22 +575,21 @@ static void xen_blkbk_discard(struct xenbus_transaction xbt, struct backend_info int err; int state = 0; struct block_device *bdev = be->blkif->vbd.bdev; - struct request_queue *q = bdev_get_queue(bdev); if (!xenbus_read_unsigned(dev->nodename, "discard-enable", 1)) return; - if (blk_queue_discard(q)) { + if (bdev_max_discard_sectors(bdev)) { err = xenbus_printf(xbt, dev->nodename, "discard-granularity", "%u", - q->limits.discard_granularity); + bdev_discard_granularity(bdev)); if (err) { dev_warn(&dev->dev, "writing discard-granularity (%d)", err); return; } err = xenbus_printf(xbt, dev->nodename, "discard-alignment", "%u", - q->limits.discard_alignment); + bdev_discard_alignment(bdev)); if (err) { dev_warn(&dev->dev, "writing discard-alignment (%d)", err); return; diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 003056d4f7f5..55e004d03ced 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -229,8 +229,6 @@ static unsigned int nr_minors; static unsigned long *minors; static DEFINE_SPINLOCK(minor_lock); -#define GRANT_INVALID_REF 0 - #define PARTS_PER_DISK 16 #define PARTS_PER_EXT_DISK 256 @@ -321,7 +319,7 @@ static int fill_grant_buffer(struct blkfront_ring_info *rinfo, int num) gnt_list_entry->page = granted_page; } - gnt_list_entry->gref = GRANT_INVALID_REF; + gnt_list_entry->gref = INVALID_GRANT_REF; list_add(&gnt_list_entry->node, &rinfo->grants); i++; } @@ -350,7 +348,7 @@ static struct grant *get_free_grant(struct blkfront_ring_info *rinfo) node); list_del(&gnt_list_entry->node); - if (gnt_list_entry->gref != GRANT_INVALID_REF) + if (gnt_list_entry->gref != INVALID_GRANT_REF) rinfo->persistent_gnts_c--; return gnt_list_entry; @@ -372,7 +370,7 @@ static struct grant *get_grant(grant_ref_t *gref_head, struct grant *gnt_list_entry = get_free_grant(rinfo); struct blkfront_info *info = rinfo->dev_info; - if (gnt_list_entry->gref != GRANT_INVALID_REF) + if (gnt_list_entry->gref != INVALID_GRANT_REF) return gnt_list_entry; /* Assign a gref to this page */ @@ -396,7 +394,7 @@ static struct grant *get_indirect_grant(grant_ref_t *gref_head, struct grant *gnt_list_entry = get_free_grant(rinfo); struct blkfront_info *info = rinfo->dev_info; - if (gnt_list_entry->gref != GRANT_INVALID_REF) + if (gnt_list_entry->gref != INVALID_GRANT_REF) return gnt_list_entry; /* Assign a gref to this page */ @@ -944,13 +942,13 @@ static void blkif_set_queue_limits(struct blkfront_info *info) blk_queue_flag_set(QUEUE_FLAG_VIRT, rq); if (info->feature_discard) { - blk_queue_flag_set(QUEUE_FLAG_DISCARD, rq); blk_queue_max_discard_sectors(rq, get_capacity(gd)); rq->limits.discard_granularity = info->discard_granularity ?: info->physical_sector_size; rq->limits.discard_alignment = info->discard_alignment; if (info->feature_secdiscard) - blk_queue_flag_set(QUEUE_FLAG_SECERASE, rq); + blk_queue_max_secure_erase_sectors(rq, + get_capacity(gd)); } /* Hard sector size and max sectors impersonate the equiv. hardware. */ @@ -1221,7 +1219,7 @@ static void blkif_free_ring(struct blkfront_ring_info *rinfo) list_for_each_entry_safe(persistent_gnt, n, &rinfo->grants, node) { list_del(&persistent_gnt->node); - if (persistent_gnt->gref != GRANT_INVALID_REF) { + if (persistent_gnt->gref != INVALID_GRANT_REF) { gnttab_end_foreign_access(persistent_gnt->gref, 0UL); rinfo->persistent_gnts_c--; @@ -1282,15 +1280,8 @@ free_shadow: flush_work(&rinfo->work); /* Free resources associated with old device channel. */ - for (i = 0; i < info->nr_ring_pages; i++) { - if (rinfo->ring_ref[i] != GRANT_INVALID_REF) { - gnttab_end_foreign_access(rinfo->ring_ref[i], 0); - rinfo->ring_ref[i] = GRANT_INVALID_REF; - } - } - free_pages_exact(rinfo->ring.sring, - info->nr_ring_pages * XEN_PAGE_SIZE); - rinfo->ring.sring = NULL; + xenbus_teardown_ring((void **)&rinfo->ring.sring, info->nr_ring_pages, + rinfo->ring_ref); if (rinfo->irq) unbind_from_irqhandler(rinfo->irq, rinfo); @@ -1475,7 +1466,7 @@ static int blkif_completion(unsigned long *id, * to the tail of the list, so it will not be picked * again unless we run out of persistent grants. */ - s->grants_used[i]->gref = GRANT_INVALID_REF; + s->grants_used[i]->gref = INVALID_GRANT_REF; list_add_tail(&s->grants_used[i]->node, &rinfo->grants); } } @@ -1500,7 +1491,7 @@ static int blkif_completion(unsigned long *id, indirect_page = s->indirect_grants[i]->page; list_add(&indirect_page->lru, &rinfo->indirect_pages); } - s->indirect_grants[i]->gref = GRANT_INVALID_REF; + s->indirect_grants[i]->gref = INVALID_GRANT_REF; list_add_tail(&s->indirect_grants[i]->node, &rinfo->grants); } } @@ -1606,8 +1597,8 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id) blkif_req(req)->error = BLK_STS_NOTSUPP; info->feature_discard = 0; info->feature_secdiscard = 0; - blk_queue_flag_clear(QUEUE_FLAG_DISCARD, rq); - blk_queue_flag_clear(QUEUE_FLAG_SECERASE, rq); + blk_queue_max_discard_sectors(rq, 0); + blk_queue_max_secure_erase_sectors(rq, 0); } break; case BLKIF_OP_FLUSH_DISKCACHE: @@ -1681,30 +1672,16 @@ static int setup_blkring(struct xenbus_device *dev, struct blkfront_ring_info *rinfo) { struct blkif_sring *sring; - int err, i; + int err; struct blkfront_info *info = rinfo->dev_info; unsigned long ring_size = info->nr_ring_pages * XEN_PAGE_SIZE; - grant_ref_t gref[XENBUS_MAX_RING_GRANTS]; - - for (i = 0; i < info->nr_ring_pages; i++) - rinfo->ring_ref[i] = GRANT_INVALID_REF; - sring = alloc_pages_exact(ring_size, GFP_NOIO); - if (!sring) { - xenbus_dev_fatal(dev, -ENOMEM, "allocating shared ring"); - return -ENOMEM; - } - SHARED_RING_INIT(sring); - FRONT_RING_INIT(&rinfo->ring, sring, ring_size); - - err = xenbus_grant_ring(dev, rinfo->ring.sring, info->nr_ring_pages, gref); - if (err < 0) { - free_pages_exact(sring, ring_size); - rinfo->ring.sring = NULL; + err = xenbus_setup_ring(dev, GFP_NOIO, (void **)&sring, + info->nr_ring_pages, rinfo->ring_ref); + if (err) goto fail; - } - for (i = 0; i < info->nr_ring_pages; i++) - rinfo->ring_ref[i] = gref[i]; + + XEN_FRONT_RING_INIT(&rinfo->ring, sring, ring_size); err = xenbus_alloc_evtchn(dev, &rinfo->evtchn); if (err) @@ -2544,13 +2521,13 @@ static void purge_persistent_grants(struct blkfront_info *info) list_for_each_entry_safe(gnt_list_entry, tmp, &rinfo->grants, node) { - if (gnt_list_entry->gref == GRANT_INVALID_REF || + if (gnt_list_entry->gref == INVALID_GRANT_REF || !gnttab_try_end_foreign_access(gnt_list_entry->gref)) continue; list_del(&gnt_list_entry->node); rinfo->persistent_gnts_c--; - gnt_list_entry->gref = GRANT_INVALID_REF; + gnt_list_entry->gref = INVALID_GRANT_REF; list_add_tail(&gnt_list_entry->node, &grants); } diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index e9474b02012d..6853dd3c7d3a 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -1675,9 +1675,10 @@ static int zram_rw_page(struct block_device *bdev, sector_t sector, bv.bv_len = PAGE_SIZE; bv.bv_offset = 0; - start_time = disk_start_io_acct(bdev->bd_disk, SECTORS_PER_PAGE, op); + start_time = bdev_start_io_acct(bdev->bd_disk->part0, + SECTORS_PER_PAGE, op, jiffies); ret = zram_bvec_rw(zram, &bv, index, offset, op, NULL); - disk_end_io_acct(bdev->bd_disk, op, start_time); + bdev_end_io_acct(bdev->bd_disk->part0, op, start_time); out: /* * If I/O fails, just return error(ie, non-zero) without @@ -1786,7 +1787,7 @@ static ssize_t reset_store(struct device *dev, int ret; unsigned short do_reset; struct zram *zram; - struct block_device *bdev; + struct gendisk *disk; ret = kstrtou16(buf, 10, &do_reset); if (ret) @@ -1796,26 +1797,26 @@ static ssize_t reset_store(struct device *dev, return -EINVAL; zram = dev_to_zram(dev); - bdev = zram->disk->part0; + disk = zram->disk; - mutex_lock(&bdev->bd_disk->open_mutex); + mutex_lock(&disk->open_mutex); /* Do not reset an active device or claimed device */ - if (bdev->bd_openers || zram->claim) { - mutex_unlock(&bdev->bd_disk->open_mutex); + if (disk_openers(disk) || zram->claim) { + mutex_unlock(&disk->open_mutex); return -EBUSY; } /* From now on, anyone can't open /dev/zram[0-9] */ zram->claim = true; - mutex_unlock(&bdev->bd_disk->open_mutex); + mutex_unlock(&disk->open_mutex); /* Make sure all the pending I/O are finished */ - sync_blockdev(bdev); + sync_blockdev(disk->part0); zram_reset_device(zram); - mutex_lock(&bdev->bd_disk->open_mutex); + mutex_lock(&disk->open_mutex); zram->claim = false; - mutex_unlock(&bdev->bd_disk->open_mutex); + mutex_unlock(&disk->open_mutex); return len; } @@ -1952,7 +1953,6 @@ static int zram_add(void) blk_queue_io_opt(zram->disk->queue, PAGE_SIZE); zram->disk->queue->limits.discard_granularity = PAGE_SIZE; blk_queue_max_discard_sectors(zram->disk->queue, UINT_MAX); - blk_queue_flag_set(QUEUE_FLAG_DISCARD, zram->disk->queue); /* * zram_bio_discard() will clear all logical blocks if logical block @@ -1987,19 +1987,18 @@ out_free_dev: static int zram_remove(struct zram *zram) { - struct block_device *bdev = zram->disk->part0; bool claimed; - mutex_lock(&bdev->bd_disk->open_mutex); - if (bdev->bd_openers) { - mutex_unlock(&bdev->bd_disk->open_mutex); + mutex_lock(&zram->disk->open_mutex); + if (disk_openers(zram->disk)) { + mutex_unlock(&zram->disk->open_mutex); return -EBUSY; } claimed = zram->claim; if (!claimed) zram->claim = true; - mutex_unlock(&bdev->bd_disk->open_mutex); + mutex_unlock(&zram->disk->open_mutex); zram_debugfs_unregister(zram); @@ -2011,7 +2010,7 @@ static int zram_remove(struct zram *zram) ; } else { /* Make sure all the pending I/O are finished */ - sync_blockdev(bdev); + sync_blockdev(zram->disk->part0); zram_reset_device(zram); } diff --git a/drivers/bus/fsl-mc/fsl-mc-msi.c b/drivers/bus/fsl-mc/fsl-mc-msi.c index 5e0e4393ce4d..0cfe859a4ac4 100644 --- a/drivers/bus/fsl-mc/fsl-mc-msi.c +++ b/drivers/bus/fsl-mc/fsl-mc-msi.c @@ -224,8 +224,12 @@ int fsl_mc_msi_domain_alloc_irqs(struct device *dev, unsigned int irq_count) if (error) return error; + msi_lock_descs(dev); if (msi_first_desc(dev, MSI_DESC_ALL)) - return -EINVAL; + error = -EINVAL; + msi_unlock_descs(dev); + if (error) + return error; /* * NOTE: Calling this function will trigger the invocation of the diff --git a/drivers/bus/imx-weim.c b/drivers/bus/imx-weim.c index 60fbd42041dd..828c66bbaa67 100644 --- a/drivers/bus/imx-weim.c +++ b/drivers/bus/imx-weim.c @@ -352,8 +352,7 @@ static int of_weim_notify(struct notifier_block *nb, unsigned long action, pdev = of_find_device_by_node(rd->dn); if (!pdev) { - dev_err(&pdev->dev, - "Could not find platform device for '%pOF'\n", + pr_err("Could not find platform device for '%pOF'\n", rd->dn); ret = notifier_from_errno(-EINVAL); @@ -370,7 +369,7 @@ static int of_weim_notify(struct notifier_block *nb, unsigned long action, return ret; } -struct notifier_block weim_of_notifier = { +static struct notifier_block weim_of_notifier = { .notifier_call = of_weim_notify, }; #endif /* IS_ENABLED(CONFIG_OF_DYNAMIC) */ diff --git a/drivers/bus/mhi/host/pci_generic.c b/drivers/bus/mhi/host/pci_generic.c index 9527b7d63840..541ced27d941 100644 --- a/drivers/bus/mhi/host/pci_generic.c +++ b/drivers/bus/mhi/host/pci_generic.c @@ -1060,6 +1060,7 @@ static int __maybe_unused mhi_pci_freeze(struct device *dev) * the intermediate restore kernel reinitializes MHI device with new * context. */ + flush_work(&mhi_pdev->recovery_work); if (test_and_clear_bit(MHI_PCI_DEV_STARTED, &mhi_pdev->status)) { mhi_power_down(mhi_cntrl, true); mhi_unprepare_after_power_down(mhi_cntrl); @@ -1085,6 +1086,7 @@ static const struct dev_pm_ops mhi_pci_pm_ops = { .resume = mhi_pci_resume, .freeze = mhi_pci_freeze, .thaw = mhi_pci_restore, + .poweroff = mhi_pci_freeze, .restore = mhi_pci_restore, #endif }; diff --git a/drivers/bus/sunxi-rsb.c b/drivers/bus/sunxi-rsb.c index 4566e730ef2b..60b082fe2ed0 100644 --- a/drivers/bus/sunxi-rsb.c +++ b/drivers/bus/sunxi-rsb.c @@ -227,6 +227,8 @@ static struct sunxi_rsb_device *sunxi_rsb_device_create(struct sunxi_rsb *rsb, dev_dbg(&rdev->dev, "device %s registered\n", dev_name(&rdev->dev)); + return rdev; + err_device_add: put_device(&rdev->dev); diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c index 54c0ee6dda30..7a1b1f9e4933 100644 --- a/drivers/bus/ti-sysc.c +++ b/drivers/bus/ti-sysc.c @@ -3232,13 +3232,27 @@ static int sysc_check_disabled_devices(struct sysc *ddata) */ static int sysc_check_active_timer(struct sysc *ddata) { + int error; + if (ddata->cap->type != TI_SYSC_OMAP2_TIMER && ddata->cap->type != TI_SYSC_OMAP4_TIMER) return 0; + /* + * Quirk for omap3 beagleboard revision A to B4 to use gpt12. + * Revision C and later are fixed with commit 23885389dbbb ("ARM: + * dts: Fix timer regression for beagleboard revision c"). This all + * can be dropped if we stop supporting old beagleboard revisions + * A to B4 at some point. + */ + if (sysc_soc->soc == SOC_3430) + error = -ENXIO; + else + error = -EBUSY; + if ((ddata->cfg.quirks & SYSC_QUIRK_NO_RESET_ON_INIT) && (ddata->cfg.quirks & SYSC_QUIRK_NO_IDLE)) - return -ENXIO; + return error; return 0; } diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c index 7bd10d63ddbe..416f723a2dbb 100644 --- a/drivers/cdrom/cdrom.c +++ b/drivers/cdrom/cdrom.c @@ -14,15 +14,6 @@ actually talk to the hardware. Suggestions are welcome. Patches that work are more welcome though. ;-) - To Do List: - ---------------------------------- - - -- Modify sysctl/proc interface. I plan on having one directory per - drive, with entries for outputing general drive information, and sysctl - based tunable parameters such as whether the tray should auto-close for - that drive. Suggestions (or patches) for this welcome! - - Revision History ---------------------------------- 1.00 Date Unknown -- David van Leeuwen <david@tm.tno.nl> @@ -648,6 +639,7 @@ int register_cdrom(struct gendisk *disk, struct cdrom_device_info *cdi) mutex_unlock(&cdrom_mutex); return 0; } +EXPORT_SYMBOL(register_cdrom); #undef ENSURE void unregister_cdrom(struct cdrom_device_info *cdi) @@ -663,6 +655,7 @@ void unregister_cdrom(struct cdrom_device_info *cdi) cd_dbg(CD_REG_UNREG, "drive \"/dev/%s\" unregistered\n", cdi->name); } +EXPORT_SYMBOL(unregister_cdrom); int cdrom_get_media_event(struct cdrom_device_info *cdi, struct media_event_desc *med) @@ -690,6 +683,7 @@ int cdrom_get_media_event(struct cdrom_device_info *cdi, memcpy(med, &buffer[sizeof(*eh)], sizeof(*med)); return 0; } +EXPORT_SYMBOL(cdrom_get_media_event); static int cdrom_get_random_writable(struct cdrom_device_info *cdi, struct rwrt_feature_desc *rfd) @@ -1206,6 +1200,7 @@ err: cdi->use_count--; return ret; } +EXPORT_SYMBOL(cdrom_open); /* This code is similar to that in open_for_data. The routine is called whenever an audio play operation is requested. @@ -1301,6 +1296,7 @@ void cdrom_release(struct cdrom_device_info *cdi, fmode_t mode) cdo->tray_move(cdi, 1); } } +EXPORT_SYMBOL(cdrom_release); static int cdrom_read_mech_status(struct cdrom_device_info *cdi, struct cdrom_changer_info *buf) @@ -1365,7 +1361,6 @@ out_free: */ int cdrom_number_of_slots(struct cdrom_device_info *cdi) { - int status; int nslots = 1; struct cdrom_changer_info *info; @@ -1377,12 +1372,13 @@ int cdrom_number_of_slots(struct cdrom_device_info *cdi) if (!info) return -ENOMEM; - if ((status = cdrom_read_mech_status(cdi, info)) == 0) + if (cdrom_read_mech_status(cdi, info) == 0) nslots = info->hdr.nslots; kfree(info); return nslots; } +EXPORT_SYMBOL(cdrom_number_of_slots); /* If SLOT < 0, unload the current slot. Otherwise, try to load SLOT. */ @@ -1582,6 +1578,7 @@ void init_cdrom_command(struct packet_command *cgc, void *buf, int len, cgc->data_direction = type; cgc->timeout = CDROM_DEF_TIMEOUT; } +EXPORT_SYMBOL(init_cdrom_command); /* DVD handling */ @@ -2000,6 +1997,7 @@ int cdrom_mode_sense(struct cdrom_device_info *cdi, cgc->data_direction = CGC_DATA_READ; return cdo->generic_packet(cdi, cgc); } +EXPORT_SYMBOL(cdrom_mode_sense); int cdrom_mode_select(struct cdrom_device_info *cdi, struct packet_command *cgc) @@ -2015,6 +2013,7 @@ int cdrom_mode_select(struct cdrom_device_info *cdi, cgc->data_direction = CGC_DATA_WRITE; return cdo->generic_packet(cdi, cgc); } +EXPORT_SYMBOL(cdrom_mode_select); static int cdrom_read_subchannel(struct cdrom_device_info *cdi, struct cdrom_subchnl *subchnl, int mcn) @@ -2444,14 +2443,6 @@ static int cdrom_ioctl_select_disc(struct cdrom_device_info *cdi, return -EINVAL; } - /* - * ->select_disc is a hook to allow a driver-specific way of - * seleting disc. However, since there is no equivalent hook for - * cdrom_slot_status this may not actually be useful... - */ - if (cdi->ops->select_disc) - return cdi->ops->select_disc(cdi, arg); - cd_dbg(CD_CHANGER, "Using generic cdrom_select_disc()\n"); return cdrom_select_disc(cdi, arg); } @@ -2893,6 +2884,7 @@ use_toc: *last_written = toc.cdte_addr.lba; return 0; } +EXPORT_SYMBOL(cdrom_get_last_written); /* return the next writable block. also for udf file system. */ static int cdrom_get_next_writable(struct cdrom_device_info *cdi, @@ -3430,18 +3422,7 @@ int cdrom_ioctl(struct cdrom_device_info *cdi, struct block_device *bdev, return -ENOSYS; } - -EXPORT_SYMBOL(cdrom_get_last_written); -EXPORT_SYMBOL(register_cdrom); -EXPORT_SYMBOL(unregister_cdrom); -EXPORT_SYMBOL(cdrom_open); -EXPORT_SYMBOL(cdrom_release); EXPORT_SYMBOL(cdrom_ioctl); -EXPORT_SYMBOL(cdrom_number_of_slots); -EXPORT_SYMBOL(cdrom_mode_select); -EXPORT_SYMBOL(cdrom_mode_sense); -EXPORT_SYMBOL(init_cdrom_command); -EXPORT_SYMBOL(cdrom_get_media_event); #ifdef CONFIG_SYSCTL diff --git a/drivers/char/agp/amd64-agp.c b/drivers/char/agp/amd64-agp.c index dc78a4fb879e..84a4aa9312cf 100644 --- a/drivers/char/agp/amd64-agp.c +++ b/drivers/char/agp/amd64-agp.c @@ -327,7 +327,7 @@ static int cache_nbs(struct pci_dev *pdev, u32 cap_ptr) { int i; - if (amd_cache_northbridges() < 0) + if (!amd_nb_num()) return -ENODEV; if (!amd_nb_has_feature(AMD_NB_GART)) diff --git a/drivers/char/ipmi/ipmb_dev_int.c b/drivers/char/ipmi/ipmb_dev_int.c index 49b8f22fdcf0..db40037eb347 100644 --- a/drivers/char/ipmi/ipmb_dev_int.c +++ b/drivers/char/ipmi/ipmb_dev_int.c @@ -299,8 +299,7 @@ static int ipmb_slave_cb(struct i2c_client *client, return 0; } -static int ipmb_probe(struct i2c_client *client, - const struct i2c_device_id *id) +static int ipmb_probe(struct i2c_client *client) { struct ipmb_dev *ipmb_dev; int ret; @@ -369,7 +368,7 @@ static struct i2c_driver ipmb_driver = { .name = "ipmb-dev", .acpi_match_table = ACPI_PTR(acpi_ipmb_id), }, - .probe = ipmb_probe, + .probe_new = ipmb_probe, .remove = ipmb_remove, .id_table = ipmb_id, }; diff --git a/drivers/char/ipmi/ipmi_ipmb.c b/drivers/char/ipmi/ipmi_ipmb.c index b81b862532fb..ab19b4b3317e 100644 --- a/drivers/char/ipmi/ipmi_ipmb.c +++ b/drivers/char/ipmi/ipmi_ipmb.c @@ -442,8 +442,7 @@ static int ipmi_ipmb_remove(struct i2c_client *client) return 0; } -static int ipmi_ipmb_probe(struct i2c_client *client, - const struct i2c_device_id *id) +static int ipmi_ipmb_probe(struct i2c_client *client) { struct device *dev = &client->dev; struct ipmi_ipmb_dev *iidev; @@ -476,6 +475,7 @@ static int ipmi_ipmb_probe(struct i2c_client *client, slave_np = of_parse_phandle(dev->of_node, "slave-dev", 0); if (slave_np) { slave_adap = of_get_i2c_adapter_by_node(slave_np); + of_node_put(slave_np); if (!slave_adap) { dev_notice(&client->dev, "Could not find slave adapter\n"); @@ -570,7 +570,7 @@ static struct i2c_driver ipmi_ipmb_driver = { .name = DEVICE_NAME, .of_match_table = of_ipmi_ipmb_match, }, - .probe = ipmi_ipmb_probe, + .probe_new = ipmi_ipmb_probe, .remove = ipmi_ipmb_remove, .id_table = ipmi_ipmb_id, }; diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c index c59265146e9c..703433493c85 100644 --- a/drivers/char/ipmi/ipmi_msghandler.c +++ b/drivers/char/ipmi/ipmi_msghandler.c @@ -11,8 +11,8 @@ * Copyright 2002 MontaVista Software Inc. */ -#define pr_fmt(fmt) "%s" fmt, "IPMI message handler: " -#define dev_fmt pr_fmt +#define pr_fmt(fmt) "IPMI message handler: " fmt +#define dev_fmt(fmt) pr_fmt(fmt) #include <linux/module.h> #include <linux/errno.h> @@ -145,6 +145,18 @@ module_param(default_max_retries, uint, 0644); MODULE_PARM_DESC(default_max_retries, "The time (milliseconds) between retry sends in maintenance mode"); +/* The default maximum number of users that may register. */ +static unsigned int max_users = 30; +module_param(max_users, uint, 0644); +MODULE_PARM_DESC(max_users, + "The most users that may use the IPMI stack at one time."); + +/* The default maximum number of message a user may have outstanding. */ +static unsigned int max_msgs_per_user = 100; +module_param(max_msgs_per_user, uint, 0644); +MODULE_PARM_DESC(max_msgs_per_user, + "The most message a user may have outstanding."); + /* Call every ~1000 ms. */ #define IPMI_TIMEOUT_TIME 1000 @@ -187,6 +199,8 @@ struct ipmi_user { /* Does this interface receive IPMI events? */ bool gets_events; + atomic_t nr_msgs; + /* Free must run in process context for RCU cleanup. */ struct work_struct remove_work; }; @@ -442,6 +456,10 @@ struct ipmi_smi { */ struct list_head users; struct srcu_struct users_srcu; + atomic_t nr_users; + struct device_attribute nr_users_devattr; + struct device_attribute nr_msgs_devattr; + /* Used for wake ups at startup. */ wait_queue_head_t waitq; @@ -927,11 +945,13 @@ static int deliver_response(struct ipmi_smi *intf, struct ipmi_recv_msg *msg) * risk. At this moment, simply skip it in that case. */ ipmi_free_recv_msg(msg); + atomic_dec(&msg->user->nr_msgs); } else { int index; struct ipmi_user *user = acquire_ipmi_user(msg->user, &index); if (user) { + atomic_dec(&user->nr_msgs); user->handler->ipmi_recv_hndl(msg, user->handler_data); release_ipmi_user(user, index); } else { @@ -1230,6 +1250,11 @@ int ipmi_create_user(unsigned int if_num, goto out_kfree; found: + if (atomic_add_return(1, &intf->nr_users) > max_users) { + rv = -EBUSY; + goto out_kfree; + } + INIT_WORK(&new_user->remove_work, free_user_work); rv = init_srcu_struct(&new_user->release_barrier); @@ -1244,6 +1269,7 @@ int ipmi_create_user(unsigned int if_num, /* Note that each existing user holds a refcount to the interface. */ kref_get(&intf->refcount); + atomic_set(&new_user->nr_msgs, 0); kref_init(&new_user->refcount); new_user->handler = handler; new_user->handler_data = handler_data; @@ -1262,6 +1288,7 @@ int ipmi_create_user(unsigned int if_num, return 0; out_kfree: + atomic_dec(&intf->nr_users); srcu_read_unlock(&ipmi_interfaces_srcu, index); vfree(new_user); return rv; @@ -1336,6 +1363,7 @@ static void _ipmi_destroy_user(struct ipmi_user *user) /* Remove the user from the interface's sequence table. */ spin_lock_irqsave(&intf->seq_lock, flags); list_del_rcu(&user->link); + atomic_dec(&intf->nr_users); for (i = 0; i < IPMI_IPMB_NUM_SEQ; i++) { if (intf->seq_table[i].inuse @@ -2284,6 +2312,14 @@ static int i_ipmi_request(struct ipmi_user *user, struct ipmi_recv_msg *recv_msg; int rv = 0; + if (user) { + if (atomic_add_return(1, &user->nr_msgs) > max_msgs_per_user) { + /* Decrement will happen at the end of the routine. */ + rv = -EBUSY; + goto out; + } + } + if (supplied_recv) recv_msg = supplied_recv; else { @@ -2296,7 +2332,7 @@ static int i_ipmi_request(struct ipmi_user *user, recv_msg->user_msg_data = user_msg_data; if (supplied_smi) - smi_msg = (struct ipmi_smi_msg *) supplied_smi; + smi_msg = supplied_smi; else { smi_msg = ipmi_alloc_smi_msg(); if (smi_msg == NULL) { @@ -2348,13 +2384,16 @@ out_err: ipmi_free_smi_msg(smi_msg); ipmi_free_recv_msg(recv_msg); } else { - pr_debug("Send: %*ph\n", smi_msg->data_size, smi_msg->data); + dev_dbg(intf->si_dev, "Send: %*ph\n", + smi_msg->data_size, smi_msg->data); smi_send(intf, intf->handlers, smi_msg, priority); } rcu_read_unlock(); out: + if (rv && user) + atomic_dec(&user->nr_msgs); return rv; } @@ -3471,6 +3510,36 @@ void ipmi_poll_interface(struct ipmi_user *user) } EXPORT_SYMBOL(ipmi_poll_interface); +static ssize_t nr_users_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct ipmi_smi *intf = container_of(attr, + struct ipmi_smi, nr_users_devattr); + + return sysfs_emit(buf, "%d\n", atomic_read(&intf->nr_users)); +} +static DEVICE_ATTR_RO(nr_users); + +static ssize_t nr_msgs_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct ipmi_smi *intf = container_of(attr, + struct ipmi_smi, nr_msgs_devattr); + struct ipmi_user *user; + int index; + unsigned int count = 0; + + index = srcu_read_lock(&intf->users_srcu); + list_for_each_entry_rcu(user, &intf->users, link) + count += atomic_read(&user->nr_msgs); + srcu_read_unlock(&intf->users_srcu, index); + + return sysfs_emit(buf, "%u\n", count); +} +static DEVICE_ATTR_RO(nr_msgs); + static void redo_bmc_reg(struct work_struct *work) { struct ipmi_smi *intf = container_of(work, struct ipmi_smi, @@ -3529,6 +3598,7 @@ int ipmi_add_smi(struct module *owner, if (slave_addr != 0) intf->addrinfo[0].address = slave_addr; INIT_LIST_HEAD(&intf->users); + atomic_set(&intf->nr_users, 0); intf->handlers = handlers; intf->send_info = send_info; spin_lock_init(&intf->seq_lock); @@ -3592,6 +3662,20 @@ int ipmi_add_smi(struct module *owner, if (rv) goto out_err_bmc_reg; + intf->nr_users_devattr = dev_attr_nr_users; + sysfs_attr_init(&intf->nr_users_devattr.attr); + rv = device_create_file(intf->si_dev, &intf->nr_users_devattr); + if (rv) + goto out_err_bmc_reg; + + intf->nr_msgs_devattr = dev_attr_nr_msgs; + sysfs_attr_init(&intf->nr_msgs_devattr.attr); + rv = device_create_file(intf->si_dev, &intf->nr_msgs_devattr); + if (rv) { + device_remove_file(intf->si_dev, &intf->nr_users_devattr); + goto out_err_bmc_reg; + } + /* * Keep memory order straight for RCU readers. Make * sure everything else is committed to memory before @@ -3677,8 +3761,11 @@ static void cleanup_smi_msgs(struct ipmi_smi *intf) void ipmi_unregister_smi(struct ipmi_smi *intf) { struct ipmi_smi_watcher *w; - int intf_num = intf->intf_num, index; + int intf_num, index; + if (!intf) + return; + intf_num = intf->intf_num; mutex_lock(&ipmi_interfaces_mutex); intf->intf_num = -1; intf->in_shutdown = true; @@ -3688,6 +3775,9 @@ void ipmi_unregister_smi(struct ipmi_smi *intf) /* At this point no users can be added to the interface. */ + device_remove_file(intf->si_dev, &intf->nr_msgs_devattr); + device_remove_file(intf->si_dev, &intf->nr_users_devattr); + /* * Call all the watcher interfaces to tell them that * an interface is going away. @@ -3836,7 +3926,8 @@ static int handle_ipmb_get_msg_cmd(struct ipmi_smi *intf, msg->data[10] = ipmb_checksum(&msg->data[6], 4); msg->data_size = 11; - pr_debug("Invalid command: %*ph\n", msg->data_size, msg->data); + dev_dbg(intf->si_dev, "Invalid command: %*ph\n", + msg->data_size, msg->data); rcu_read_lock(); if (!intf->in_shutdown) { @@ -3989,10 +4080,10 @@ static int handle_ipmb_direct_rcv_rsp(struct ipmi_smi *intf, struct ipmi_recv_msg *recv_msg; struct ipmi_ipmb_direct_addr *daddr; - recv_msg = (struct ipmi_recv_msg *) msg->user_data; + recv_msg = msg->user_data; if (recv_msg == NULL) { dev_warn(intf->si_dev, - "IPMI message received with no owner. This could be because of a malformed message, or because of a hardware error. Contact your hardware vendor for assistance.\n"); + "IPMI direct message received with no owner. This could be because of a malformed message, or because of a hardware error. Contact your hardware vendor for assistance.\n"); return 0; } @@ -4407,10 +4498,10 @@ static int handle_bmc_rsp(struct ipmi_smi *intf, struct ipmi_recv_msg *recv_msg; struct ipmi_system_interface_addr *smi_addr; - recv_msg = (struct ipmi_recv_msg *) msg->user_data; + recv_msg = msg->user_data; if (recv_msg == NULL) { dev_warn(intf->si_dev, - "IPMI message received with no owner. This could be because of a malformed message, or because of a hardware error. Contact your hardware vendor for assistance.\n"); + "IPMI SMI message received with no owner. This could be because of a malformed message, or because of a hardware error. Contact your hardware vendor for assistance.\n"); return 0; } @@ -4444,7 +4535,7 @@ static int handle_one_recv_msg(struct ipmi_smi *intf, unsigned char cc; bool is_cmd = !((msg->rsp[0] >> 2) & 1); - pr_debug("Recv: %*ph\n", msg->rsp_size, msg->rsp); + dev_dbg(intf->si_dev, "Recv: %*ph\n", msg->rsp_size, msg->rsp); if (msg->rsp_size < 2) { /* Message is too small to be correct. */ @@ -4518,6 +4609,8 @@ return_unspecified: } else /* The message was sent, start the timer. */ intf_start_seq_timer(intf, msg->msgid); + requeue = 0; + goto out; } else if (((msg->rsp[0] >> 2) != ((msg->data[0] >> 2) | 1)) || (msg->rsp[1] != msg->data[1])) { /* @@ -4826,7 +4919,8 @@ smi_from_recv_msg(struct ipmi_smi *intf, struct ipmi_recv_msg *recv_msg, smi_msg->data_size = recv_msg->msg.data_len; smi_msg->msgid = STORE_SEQ_IN_MSGID(seq, seqid); - pr_debug("Resend: %*ph\n", smi_msg->data_size, smi_msg->data); + dev_dbg(intf->si_dev, "Resend: %*ph\n", + smi_msg->data_size, smi_msg->data); return smi_msg; } diff --git a/drivers/char/ipmi/ipmi_poweroff.c b/drivers/char/ipmi/ipmi_poweroff.c index bc3a18daf97a..163ec9749e55 100644 --- a/drivers/char/ipmi/ipmi_poweroff.c +++ b/drivers/char/ipmi/ipmi_poweroff.c @@ -94,12 +94,8 @@ static void dummy_recv_free(struct ipmi_recv_msg *msg) { atomic_dec(&dummy_count); } -static struct ipmi_smi_msg halt_smi_msg = { - .done = dummy_smi_free -}; -static struct ipmi_recv_msg halt_recv_msg = { - .done = dummy_recv_free -}; +static struct ipmi_smi_msg halt_smi_msg = INIT_IPMI_SMI_MSG(dummy_smi_free); +static struct ipmi_recv_msg halt_recv_msg = INIT_IPMI_RECV_MSG(dummy_recv_free); /* diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c index 64dedb3ef8ec..6e357ad76f2e 100644 --- a/drivers/char/ipmi/ipmi_si_intf.c +++ b/drivers/char/ipmi/ipmi_si_intf.c @@ -264,15 +264,16 @@ static void cleanup_one_si(struct smi_info *smi_info); static void cleanup_ipmi_si(void); #ifdef DEBUG_TIMING -void debug_timestamp(char *msg) +void debug_timestamp(struct smi_info *smi_info, char *msg) { struct timespec64 t; ktime_get_ts64(&t); - pr_debug("**%s: %lld.%9.9ld\n", msg, t.tv_sec, t.tv_nsec); + dev_dbg(smi_info->io.dev, "**%s: %lld.%9.9ld\n", + msg, t.tv_sec, t.tv_nsec); } #else -#define debug_timestamp(x) +#define debug_timestamp(smi_info, x) #endif static ATOMIC_NOTIFIER_HEAD(xaction_notifier_list); @@ -318,7 +319,7 @@ static enum si_sm_result start_next_msg(struct smi_info *smi_info) smi_info->curr_msg = smi_info->waiting_msg; smi_info->waiting_msg = NULL; - debug_timestamp("Start2"); + debug_timestamp(smi_info, "Start2"); err = atomic_notifier_call_chain(&xaction_notifier_list, 0, smi_info); if (err & NOTIFY_STOP_MASK) { @@ -538,7 +539,7 @@ static void handle_transaction_done(struct smi_info *smi_info) { struct ipmi_smi_msg *msg; - debug_timestamp("Done"); + debug_timestamp(smi_info, "Done"); switch (smi_info->si_state) { case SI_NORMAL: if (!smi_info->curr_msg) @@ -901,7 +902,7 @@ static void sender(void *send_info, struct smi_info *smi_info = send_info; unsigned long flags; - debug_timestamp("Enqueue"); + debug_timestamp(smi_info, "Enqueue"); if (smi_info->run_to_completion) { /* @@ -1079,7 +1080,7 @@ static void smi_timeout(struct timer_list *t) long timeout; spin_lock_irqsave(&(smi_info->si_lock), flags); - debug_timestamp("Timer"); + debug_timestamp(smi_info, "Timer"); jiffies_now = jiffies; time_diff = (((long)jiffies_now - (long)smi_info->last_timeout_jiffies) @@ -1128,7 +1129,7 @@ irqreturn_t ipmi_si_irq_handler(int irq, void *data) smi_inc_stat(smi_info, interrupts); - debug_timestamp("Interrupt"); + debug_timestamp(smi_info, "Interrupt"); smi_event_handler(smi_info, 0); spin_unlock_irqrestore(&(smi_info->si_lock), flags); @@ -2220,10 +2221,7 @@ static void cleanup_one_si(struct smi_info *smi_info) return; list_del(&smi_info->link); - - if (smi_info->intf) - ipmi_unregister_smi(smi_info->intf); - + ipmi_unregister_smi(smi_info->intf); kfree(smi_info); } diff --git a/drivers/char/ipmi/ipmi_ssif.c b/drivers/char/ipmi/ipmi_ssif.c index f199cc194844..fc742ee9c046 100644 --- a/drivers/char/ipmi/ipmi_ssif.c +++ b/drivers/char/ipmi/ipmi_ssif.c @@ -814,6 +814,14 @@ static void msg_done_handler(struct ssif_info *ssif_info, int result, break; case SSIF_GETTING_EVENTS: + if (!msg) { + /* Should never happen, but just in case. */ + dev_warn(&ssif_info->client->dev, + "No message set while getting events\n"); + ipmi_ssif_unlock_cond(ssif_info, flags); + break; + } + if ((result < 0) || (len < 3) || (msg->rsp[2] != 0)) { /* Error getting event, probably done. */ msg->done(msg); @@ -838,6 +846,14 @@ static void msg_done_handler(struct ssif_info *ssif_info, int result, break; case SSIF_GETTING_MESSAGES: + if (!msg) { + /* Should never happen, but just in case. */ + dev_warn(&ssif_info->client->dev, + "No message set while getting messages\n"); + ipmi_ssif_unlock_cond(ssif_info, flags); + break; + } + if ((result < 0) || (len < 3) || (msg->rsp[2] != 0)) { /* Error getting event, probably done. */ msg->done(msg); @@ -861,6 +877,13 @@ static void msg_done_handler(struct ssif_info *ssif_info, int result, deliver_recv_msg(ssif_info, msg); } break; + + default: + /* Should never happen, but just in case. */ + dev_warn(&ssif_info->client->dev, + "Invalid state in message done handling: %d\n", + ssif_info->ssif_state); + ipmi_ssif_unlock_cond(ssif_info, flags); } flags = ipmi_ssif_lock_cond(ssif_info, &oflags); @@ -1053,7 +1076,7 @@ static void start_next_msg(struct ssif_info *ssif_info, unsigned long *flags) static void sender(void *send_info, struct ipmi_smi_msg *msg) { - struct ssif_info *ssif_info = (struct ssif_info *) send_info; + struct ssif_info *ssif_info = send_info; unsigned long oflags, *flags; BUG_ON(ssif_info->waiting_msg); @@ -1090,7 +1113,7 @@ static int get_smi_info(void *send_info, struct ipmi_smi_info *data) */ static void request_events(void *send_info) { - struct ssif_info *ssif_info = (struct ssif_info *) send_info; + struct ssif_info *ssif_info = send_info; unsigned long oflags, *flags; if (!ssif_info->has_event_buffer) @@ -1107,7 +1130,7 @@ static void request_events(void *send_info) */ static void ssif_set_need_watch(void *send_info, unsigned int watch_mask) { - struct ssif_info *ssif_info = (struct ssif_info *) send_info; + struct ssif_info *ssif_info = send_info; unsigned long oflags, *flags; long timeout = 0; @@ -1619,7 +1642,7 @@ static int ssif_check_and_remove(struct i2c_client *client, return 0; } -static int ssif_probe(struct i2c_client *client, const struct i2c_device_id *id) +static int ssif_probe(struct i2c_client *client) { unsigned char msg[3]; unsigned char *resp; @@ -2037,7 +2060,7 @@ static struct i2c_driver ssif_i2c_driver = { .driver = { .name = DEVICE_NAME }, - .probe = ssif_probe, + .probe_new = ssif_probe, .remove = ssif_remove, .alert = ssif_alert, .id_table = ssif_id, diff --git a/drivers/char/ipmi/ipmi_watchdog.c b/drivers/char/ipmi/ipmi_watchdog.c index 0604abdd249a..5b4e677929ca 100644 --- a/drivers/char/ipmi/ipmi_watchdog.c +++ b/drivers/char/ipmi/ipmi_watchdog.c @@ -354,12 +354,8 @@ static void msg_free_recv(struct ipmi_recv_msg *msg) complete(&msg_wait); } } -static struct ipmi_smi_msg smi_msg = { - .done = msg_free_smi -}; -static struct ipmi_recv_msg recv_msg = { - .done = msg_free_recv -}; +static struct ipmi_smi_msg smi_msg = INIT_IPMI_SMI_MSG(msg_free_smi); +static struct ipmi_recv_msg recv_msg = INIT_IPMI_RECV_MSG(msg_free_recv); static int __ipmi_set_timeout(struct ipmi_smi_msg *smi_msg, struct ipmi_recv_msg *recv_msg, @@ -475,12 +471,10 @@ static void panic_recv_free(struct ipmi_recv_msg *msg) atomic_dec(&panic_done_count); } -static struct ipmi_smi_msg panic_halt_heartbeat_smi_msg = { - .done = panic_smi_free -}; -static struct ipmi_recv_msg panic_halt_heartbeat_recv_msg = { - .done = panic_recv_free -}; +static struct ipmi_smi_msg panic_halt_heartbeat_smi_msg = + INIT_IPMI_SMI_MSG(panic_smi_free); +static struct ipmi_recv_msg panic_halt_heartbeat_recv_msg = + INIT_IPMI_RECV_MSG(panic_recv_free); static void panic_halt_ipmi_heartbeat(void) { @@ -516,12 +510,10 @@ static void panic_halt_ipmi_heartbeat(void) atomic_sub(2, &panic_done_count); } -static struct ipmi_smi_msg panic_halt_smi_msg = { - .done = panic_smi_free -}; -static struct ipmi_recv_msg panic_halt_recv_msg = { - .done = panic_recv_free -}; +static struct ipmi_smi_msg panic_halt_smi_msg = + INIT_IPMI_SMI_MSG(panic_smi_free); +static struct ipmi_recv_msg panic_halt_recv_msg = + INIT_IPMI_RECV_MSG(panic_recv_free); /* * Special call, doesn't claim any locks. This is only to be called diff --git a/drivers/char/random.c b/drivers/char/random.c index 1d8242969751..b691b9d59503 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -15,14 +15,12 @@ * - Sysctl interface. * * The high level overview is that there is one input pool, into which - * various pieces of data are hashed. Some of that data is then "credited" as - * having a certain number of bits of entropy. When enough bits of entropy are - * available, the hash is finalized and handed as a key to a stream cipher that - * expands it indefinitely for various consumers. This key is periodically - * refreshed as the various entropy collectors, described below, add data to the - * input pool and credit it. There is currently no Fortuna-like scheduler - * involved, which can lead to malicious entropy sources causing a premature - * reseed, and the entropy estimates are, at best, conservative guesses. + * various pieces of data are hashed. Prior to initialization, some of that + * data is then "credited" as having a certain number of bits of entropy. + * When enough bits of entropy are available, the hash is finalized and + * handed as a key to a stream cipher that expands it indefinitely for + * various consumers. This key is periodically refreshed as the various + * entropy collectors, described below, add data to the input pool. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt @@ -53,6 +51,8 @@ #include <linux/completion.h> #include <linux/uuid.h> #include <linux/uaccess.h> +#include <linux/suspend.h> +#include <linux/siphash.h> #include <crypto/chacha.h> #include <crypto/blake2s.h> #include <asm/processor.h> @@ -71,27 +71,25 @@ *********************************************************************/ /* - * crng_init = 0 --> Uninitialized - * 1 --> Initialized - * 2 --> Initialized from input_pool - * * crng_init is protected by base_crng->lock, and only increases - * its value (from 0->1->2). + * its value (from empty->early->ready). */ -static int crng_init = 0; -#define crng_ready() (likely(crng_init > 1)) -/* Various types of waiters for crng_init->2 transition. */ +static enum { + CRNG_EMPTY = 0, /* Little to no entropy collected */ + CRNG_EARLY = 1, /* At least POOL_EARLY_BITS collected */ + CRNG_READY = 2 /* Fully initialized with POOL_READY_BITS collected */ +} crng_init __read_mostly = CRNG_EMPTY; +static DEFINE_STATIC_KEY_FALSE(crng_is_ready); +#define crng_ready() (static_branch_likely(&crng_is_ready) || crng_init >= CRNG_READY) +/* Various types of waiters for crng_init->CRNG_READY transition. */ static DECLARE_WAIT_QUEUE_HEAD(crng_init_wait); static struct fasync_struct *fasync; -static DEFINE_SPINLOCK(random_ready_chain_lock); -static RAW_NOTIFIER_HEAD(random_ready_chain); /* Control how we warn userspace. */ -static struct ratelimit_state unseeded_warning = - RATELIMIT_STATE_INIT("warn_unseeded_randomness", HZ, 3); static struct ratelimit_state urandom_warning = RATELIMIT_STATE_INIT("warn_urandom_randomness", HZ, 3); -static int ratelimit_disable __read_mostly; +static int ratelimit_disable __read_mostly = + IS_ENABLED(CONFIG_WARN_ALL_UNSEEDED_RANDOM); module_param_named(ratelimit_disable, ratelimit_disable, int, 0644); MODULE_PARM_DESC(ratelimit_disable, "Disable random ratelimit suppression"); @@ -110,6 +108,11 @@ bool rng_is_initialized(void) } EXPORT_SYMBOL(rng_is_initialized); +static void __cold crng_set_ready(struct work_struct *work) +{ + static_branch_enable(&crng_is_ready); +} + /* Used by wait_for_random_bytes(), and considered an entropy collector, below. */ static void try_to_generate_entropy(void); @@ -137,73 +140,10 @@ int wait_for_random_bytes(void) } EXPORT_SYMBOL(wait_for_random_bytes); -/* - * Add a callback function that will be invoked when the input - * pool is initialised. - * - * returns: 0 if callback is successfully added - * -EALREADY if pool is already initialised (callback not called) - */ -int register_random_ready_notifier(struct notifier_block *nb) -{ - unsigned long flags; - int ret = -EALREADY; - - if (crng_ready()) - return ret; - - spin_lock_irqsave(&random_ready_chain_lock, flags); - if (!crng_ready()) - ret = raw_notifier_chain_register(&random_ready_chain, nb); - spin_unlock_irqrestore(&random_ready_chain_lock, flags); - return ret; -} - -/* - * Delete a previously registered readiness callback function. - */ -int unregister_random_ready_notifier(struct notifier_block *nb) -{ - unsigned long flags; - int ret; - - spin_lock_irqsave(&random_ready_chain_lock, flags); - ret = raw_notifier_chain_unregister(&random_ready_chain, nb); - spin_unlock_irqrestore(&random_ready_chain_lock, flags); - return ret; -} - -static void process_random_ready_list(void) -{ - unsigned long flags; - - spin_lock_irqsave(&random_ready_chain_lock, flags); - raw_notifier_call_chain(&random_ready_chain, 0, NULL); - spin_unlock_irqrestore(&random_ready_chain_lock, flags); -} - -#define warn_unseeded_randomness(previous) \ - _warn_unseeded_randomness(__func__, (void *)_RET_IP_, (previous)) - -static void _warn_unseeded_randomness(const char *func_name, void *caller, void **previous) -{ -#ifdef CONFIG_WARN_ALL_UNSEEDED_RANDOM - const bool print_once = false; -#else - static bool print_once __read_mostly; -#endif - - if (print_once || crng_ready() || - (previous && (caller == READ_ONCE(*previous)))) - return; - WRITE_ONCE(*previous, caller); -#ifndef CONFIG_WARN_ALL_UNSEEDED_RANDOM - print_once = true; -#endif - if (__ratelimit(&unseeded_warning)) - printk_deferred(KERN_NOTICE "random: %s called from %pS with crng_init=%d\n", - func_name, caller, crng_init); -} +#define warn_unseeded_randomness() \ + if (IS_ENABLED(CONFIG_WARN_ALL_UNSEEDED_RANDOM) && !crng_ready()) \ + printk_deferred(KERN_NOTICE "random: %s called from %pS with crng_init=%d\n", \ + __func__, (void *)_RET_IP_, crng_init) /********************************************************************* @@ -216,7 +156,7 @@ static void _warn_unseeded_randomness(const char *func_name, void *caller, void * * There are a few exported interfaces for use by other drivers: * - * void get_random_bytes(void *buf, size_t nbytes) + * void get_random_bytes(void *buf, size_t len) * u32 get_random_u32() * u64 get_random_u64() * unsigned int get_random_int() @@ -232,8 +172,8 @@ static void _warn_unseeded_randomness(const char *func_name, void *caller, void *********************************************************************/ enum { - CRNG_RESEED_INTERVAL = 300 * HZ, - CRNG_INIT_CNT_THRESH = 2 * CHACHA_KEY_SIZE + CRNG_RESEED_START_INTERVAL = HZ, + CRNG_RESEED_INTERVAL = 60 * HZ }; static struct { @@ -256,24 +196,17 @@ static DEFINE_PER_CPU(struct crng, crngs) = { .lock = INIT_LOCAL_LOCK(crngs.lock), }; -/* Used by crng_reseed() to extract a new seed from the input pool. */ -static bool drain_entropy(void *buf, size_t nbytes, bool force); +/* Used by crng_reseed() and crng_make_state() to extract a new seed from the input pool. */ +static void extract_entropy(void *buf, size_t len); -/* - * This extracts a new crng key from the input pool, but only if there is a - * sufficient amount of entropy available or force is true, in order to - * mitigate bruteforcing of newly added bits. - */ -static void crng_reseed(bool force) +/* This extracts a new crng key from the input pool. */ +static void crng_reseed(void) { unsigned long flags; unsigned long next_gen; u8 key[CHACHA_KEY_SIZE]; - bool finalize_init = false; - /* Only reseed if we can, to prevent brute forcing a small amount of new bits. */ - if (!drain_entropy(key, sizeof(key), force)) - return; + extract_entropy(key, sizeof(key)); /* * We copy the new key into the base_crng, overwriting the old one, @@ -288,28 +221,10 @@ static void crng_reseed(bool force) ++next_gen; WRITE_ONCE(base_crng.generation, next_gen); WRITE_ONCE(base_crng.birth, jiffies); - if (!crng_ready()) { - crng_init = 2; - finalize_init = true; - } + if (!static_branch_likely(&crng_is_ready)) + crng_init = CRNG_READY; spin_unlock_irqrestore(&base_crng.lock, flags); memzero_explicit(key, sizeof(key)); - if (finalize_init) { - process_random_ready_list(); - wake_up_interruptible(&crng_init_wait); - kill_fasync(&fasync, SIGIO, POLL_IN); - pr_notice("crng init done\n"); - if (unseeded_warning.missed) { - pr_notice("%d get_random_xx warning(s) missed due to ratelimiting\n", - unseeded_warning.missed); - unseeded_warning.missed = 0; - } - if (urandom_warning.missed) { - pr_notice("%d urandom warning(s) missed due to ratelimiting\n", - urandom_warning.missed); - urandom_warning.missed = 0; - } - } } /* @@ -318,6 +233,13 @@ static void crng_reseed(bool force) * the resultant ChaCha state to the user, along with the second * half of the block containing 32 bytes of random data that may * be used; random_data_len may not be greater than 32. + * + * The returned ChaCha state contains within it a copy of the old + * key value, at index 4, so the state should always be zeroed out + * immediately after using in order to maintain forward secrecy. + * If the state cannot be erased in a timely manner, then it is + * safer to set the random_data parameter to &chacha_state[4] so + * that this function overwrites it before returning. */ static void crng_fast_key_erasure(u8 key[CHACHA_KEY_SIZE], u32 chacha_state[CHACHA_STATE_WORDS], @@ -338,10 +260,10 @@ static void crng_fast_key_erasure(u8 key[CHACHA_KEY_SIZE], } /* - * Return whether the crng seed is considered to be sufficiently - * old that a reseeding might be attempted. This happens if the last - * reseeding was CRNG_RESEED_INTERVAL ago, or during early boot, at - * an interval proportional to the uptime. + * Return whether the crng seed is considered to be sufficiently old + * that a reseeding is needed. This happens if the last reseeding + * was CRNG_RESEED_INTERVAL ago, or during early boot, at an interval + * proportional to the uptime. */ static bool crng_has_old_seed(void) { @@ -353,10 +275,10 @@ static bool crng_has_old_seed(void) if (uptime >= CRNG_RESEED_INTERVAL / HZ * 2) WRITE_ONCE(early_boot, false); else - interval = max_t(unsigned int, 5 * HZ, + interval = max_t(unsigned int, CRNG_RESEED_START_INTERVAL, (unsigned int)uptime / 2 * HZ); } - return time_after(jiffies, READ_ONCE(base_crng.birth) + interval); + return time_is_before_jiffies(READ_ONCE(base_crng.birth) + interval); } /* @@ -375,28 +297,31 @@ static void crng_make_state(u32 chacha_state[CHACHA_STATE_WORDS], /* * For the fast path, we check whether we're ready, unlocked first, and * then re-check once locked later. In the case where we're really not - * ready, we do fast key erasure with the base_crng directly, because - * this is what crng_pre_init_inject() mutates during early init. + * ready, we do fast key erasure with the base_crng directly, extracting + * when crng_init is CRNG_EMPTY. */ if (!crng_ready()) { bool ready; spin_lock_irqsave(&base_crng.lock, flags); ready = crng_ready(); - if (!ready) + if (!ready) { + if (crng_init == CRNG_EMPTY) + extract_entropy(base_crng.key, sizeof(base_crng.key)); crng_fast_key_erasure(base_crng.key, chacha_state, random_data, random_data_len); + } spin_unlock_irqrestore(&base_crng.lock, flags); if (!ready) return; } /* - * If the base_crng is old enough, we try to reseed, which in turn - * bumps the generation counter that we check below. + * If the base_crng is old enough, we reseed, which in turn bumps the + * generation counter that we check below. */ if (unlikely(crng_has_old_seed())) - crng_reseed(false); + crng_reseed(); local_lock_irqsave(&crngs.lock, flags); crng = raw_cpu_ptr(&crngs); @@ -426,76 +351,24 @@ static void crng_make_state(u32 chacha_state[CHACHA_STATE_WORDS], local_unlock_irqrestore(&crngs.lock, flags); } -/* - * This function is for crng_init == 0 only. It loads entropy directly - * into the crng's key, without going through the input pool. It is, - * generally speaking, not very safe, but we use this only at early - * boot time when it's better to have something there rather than - * nothing. - * - * If account is set, then the crng_init_cnt counter is incremented. - * This shouldn't be set by functions like add_device_randomness(), - * where we can't trust the buffer passed to it is guaranteed to be - * unpredictable (so it might not have any entropy at all). - * - * Returns the number of bytes processed from input, which is bounded - * by CRNG_INIT_CNT_THRESH if account is true. - */ -static size_t crng_pre_init_inject(const void *input, size_t len, bool account) -{ - static int crng_init_cnt = 0; - struct blake2s_state hash; - unsigned long flags; - - blake2s_init(&hash, sizeof(base_crng.key)); - - spin_lock_irqsave(&base_crng.lock, flags); - if (crng_init != 0) { - spin_unlock_irqrestore(&base_crng.lock, flags); - return 0; - } - - if (account) - len = min_t(size_t, len, CRNG_INIT_CNT_THRESH - crng_init_cnt); - - blake2s_update(&hash, base_crng.key, sizeof(base_crng.key)); - blake2s_update(&hash, input, len); - blake2s_final(&hash, base_crng.key); - - if (account) { - crng_init_cnt += len; - if (crng_init_cnt >= CRNG_INIT_CNT_THRESH) { - ++base_crng.generation; - crng_init = 1; - } - } - - spin_unlock_irqrestore(&base_crng.lock, flags); - - if (crng_init == 1) - pr_notice("fast init done\n"); - - return len; -} - -static void _get_random_bytes(void *buf, size_t nbytes) +static void _get_random_bytes(void *buf, size_t len) { u32 chacha_state[CHACHA_STATE_WORDS]; u8 tmp[CHACHA_BLOCK_SIZE]; - size_t len; + size_t first_block_len; - if (!nbytes) + if (!len) return; - len = min_t(size_t, 32, nbytes); - crng_make_state(chacha_state, buf, len); - nbytes -= len; - buf += len; + first_block_len = min_t(size_t, 32, len); + crng_make_state(chacha_state, buf, first_block_len); + len -= first_block_len; + buf += first_block_len; - while (nbytes) { - if (nbytes < CHACHA_BLOCK_SIZE) { + while (len) { + if (len < CHACHA_BLOCK_SIZE) { chacha20_block(chacha_state, tmp); - memcpy(buf, tmp, nbytes); + memcpy(buf, tmp, len); memzero_explicit(tmp, sizeof(tmp)); break; } @@ -503,7 +376,7 @@ static void _get_random_bytes(void *buf, size_t nbytes) chacha20_block(chacha_state, buf); if (unlikely(chacha_state[12] == 0)) ++chacha_state[13]; - nbytes -= CHACHA_BLOCK_SIZE; + len -= CHACHA_BLOCK_SIZE; buf += CHACHA_BLOCK_SIZE; } @@ -513,67 +386,64 @@ static void _get_random_bytes(void *buf, size_t nbytes) /* * This function is the exported kernel interface. It returns some * number of good random numbers, suitable for key generation, seeding - * TCP sequence numbers, etc. It does not rely on the hardware random - * number generator. For random bytes direct from the hardware RNG - * (when available), use get_random_bytes_arch(). In order to ensure - * that the randomness provided by this function is okay, the function - * wait_for_random_bytes() should be called and return 0 at least once - * at any point prior. + * TCP sequence numbers, etc. In order to ensure that the randomness + * by this function is okay, the function wait_for_random_bytes() + * should be called and return 0 at least once at any point prior. */ -void get_random_bytes(void *buf, size_t nbytes) +void get_random_bytes(void *buf, size_t len) { - static void *previous; - - warn_unseeded_randomness(&previous); - _get_random_bytes(buf, nbytes); + warn_unseeded_randomness(); + _get_random_bytes(buf, len); } EXPORT_SYMBOL(get_random_bytes); -static ssize_t get_random_bytes_user(void __user *buf, size_t nbytes) +static ssize_t get_random_bytes_user(struct iov_iter *iter) { - bool large_request = nbytes > 256; - ssize_t ret = 0; - size_t len; u32 chacha_state[CHACHA_STATE_WORDS]; - u8 output[CHACHA_BLOCK_SIZE]; + u8 block[CHACHA_BLOCK_SIZE]; + size_t ret = 0, copied; - if (!nbytes) + if (unlikely(!iov_iter_count(iter))) return 0; - len = min_t(size_t, 32, nbytes); - crng_make_state(chacha_state, output, len); - - if (copy_to_user(buf, output, len)) - return -EFAULT; - nbytes -= len; - buf += len; - ret += len; - - while (nbytes) { - if (large_request && need_resched()) { - if (signal_pending(current)) - break; - schedule(); - } + /* + * Immediately overwrite the ChaCha key at index 4 with random + * bytes, in case userspace causes copy_to_user() below to sleep + * forever, so that we still retain forward secrecy in that case. + */ + crng_make_state(chacha_state, (u8 *)&chacha_state[4], CHACHA_KEY_SIZE); + /* + * However, if we're doing a read of len <= 32, we don't need to + * use chacha_state after, so we can simply return those bytes to + * the user directly. + */ + if (iov_iter_count(iter) <= CHACHA_KEY_SIZE) { + ret = copy_to_iter(&chacha_state[4], CHACHA_KEY_SIZE, iter); + goto out_zero_chacha; + } - chacha20_block(chacha_state, output); + for (;;) { + chacha20_block(chacha_state, block); if (unlikely(chacha_state[12] == 0)) ++chacha_state[13]; - len = min_t(size_t, nbytes, CHACHA_BLOCK_SIZE); - if (copy_to_user(buf, output, len)) { - ret = -EFAULT; + copied = copy_to_iter(block, sizeof(block), iter); + ret += copied; + if (!iov_iter_count(iter) || copied != sizeof(block)) break; - } - nbytes -= len; - buf += len; - ret += len; + BUILD_BUG_ON(PAGE_SIZE % sizeof(block) != 0); + if (ret % PAGE_SIZE == 0) { + if (signal_pending(current)) + break; + cond_resched(); + } } + memzero_explicit(block, sizeof(block)); +out_zero_chacha: memzero_explicit(chacha_state, sizeof(chacha_state)); - memzero_explicit(output, sizeof(output)); - return ret; + return ret ? ret : -EFAULT; } /* @@ -582,98 +452,69 @@ static ssize_t get_random_bytes_user(void __user *buf, size_t nbytes) * provided by this function is okay, the function wait_for_random_bytes() * should be called and return 0 at least once at any point prior. */ -struct batched_entropy { - union { - /* - * We make this 1.5x a ChaCha block, so that we get the - * remaining 32 bytes from fast key erasure, plus one full - * block from the detached ChaCha state. We can increase - * the size of this later if needed so long as we keep the - * formula of (integer_blocks + 0.5) * CHACHA_BLOCK_SIZE. - */ - u64 entropy_u64[CHACHA_BLOCK_SIZE * 3 / (2 * sizeof(u64))]; - u32 entropy_u32[CHACHA_BLOCK_SIZE * 3 / (2 * sizeof(u32))]; - }; - local_lock_t lock; - unsigned long generation; - unsigned int position; -}; - -static DEFINE_PER_CPU(struct batched_entropy, batched_entropy_u64) = { - .lock = INIT_LOCAL_LOCK(batched_entropy_u64.lock), - .position = UINT_MAX -}; - -u64 get_random_u64(void) -{ - u64 ret; - unsigned long flags; - struct batched_entropy *batch; - static void *previous; - unsigned long next_gen; - - warn_unseeded_randomness(&previous); - - local_lock_irqsave(&batched_entropy_u64.lock, flags); - batch = raw_cpu_ptr(&batched_entropy_u64); - - next_gen = READ_ONCE(base_crng.generation); - if (batch->position >= ARRAY_SIZE(batch->entropy_u64) || - next_gen != batch->generation) { - _get_random_bytes(batch->entropy_u64, sizeof(batch->entropy_u64)); - batch->position = 0; - batch->generation = next_gen; - } - - ret = batch->entropy_u64[batch->position]; - batch->entropy_u64[batch->position] = 0; - ++batch->position; - local_unlock_irqrestore(&batched_entropy_u64.lock, flags); - return ret; -} -EXPORT_SYMBOL(get_random_u64); - -static DEFINE_PER_CPU(struct batched_entropy, batched_entropy_u32) = { - .lock = INIT_LOCAL_LOCK(batched_entropy_u32.lock), - .position = UINT_MAX -}; - -u32 get_random_u32(void) -{ - u32 ret; - unsigned long flags; - struct batched_entropy *batch; - static void *previous; - unsigned long next_gen; - - warn_unseeded_randomness(&previous); - - local_lock_irqsave(&batched_entropy_u32.lock, flags); - batch = raw_cpu_ptr(&batched_entropy_u32); - - next_gen = READ_ONCE(base_crng.generation); - if (batch->position >= ARRAY_SIZE(batch->entropy_u32) || - next_gen != batch->generation) { - _get_random_bytes(batch->entropy_u32, sizeof(batch->entropy_u32)); - batch->position = 0; - batch->generation = next_gen; - } - - ret = batch->entropy_u32[batch->position]; - batch->entropy_u32[batch->position] = 0; - ++batch->position; - local_unlock_irqrestore(&batched_entropy_u32.lock, flags); - return ret; -} -EXPORT_SYMBOL(get_random_u32); +#define DEFINE_BATCHED_ENTROPY(type) \ +struct batch_ ##type { \ + /* \ + * We make this 1.5x a ChaCha block, so that we get the \ + * remaining 32 bytes from fast key erasure, plus one full \ + * block from the detached ChaCha state. We can increase \ + * the size of this later if needed so long as we keep the \ + * formula of (integer_blocks + 0.5) * CHACHA_BLOCK_SIZE. \ + */ \ + type entropy[CHACHA_BLOCK_SIZE * 3 / (2 * sizeof(type))]; \ + local_lock_t lock; \ + unsigned long generation; \ + unsigned int position; \ +}; \ + \ +static DEFINE_PER_CPU(struct batch_ ##type, batched_entropy_ ##type) = { \ + .lock = INIT_LOCAL_LOCK(batched_entropy_ ##type.lock), \ + .position = UINT_MAX \ +}; \ + \ +type get_random_ ##type(void) \ +{ \ + type ret; \ + unsigned long flags; \ + struct batch_ ##type *batch; \ + unsigned long next_gen; \ + \ + warn_unseeded_randomness(); \ + \ + if (!crng_ready()) { \ + _get_random_bytes(&ret, sizeof(ret)); \ + return ret; \ + } \ + \ + local_lock_irqsave(&batched_entropy_ ##type.lock, flags); \ + batch = raw_cpu_ptr(&batched_entropy_##type); \ + \ + next_gen = READ_ONCE(base_crng.generation); \ + if (batch->position >= ARRAY_SIZE(batch->entropy) || \ + next_gen != batch->generation) { \ + _get_random_bytes(batch->entropy, sizeof(batch->entropy)); \ + batch->position = 0; \ + batch->generation = next_gen; \ + } \ + \ + ret = batch->entropy[batch->position]; \ + batch->entropy[batch->position] = 0; \ + ++batch->position; \ + local_unlock_irqrestore(&batched_entropy_ ##type.lock, flags); \ + return ret; \ +} \ +EXPORT_SYMBOL(get_random_ ##type); + +DEFINE_BATCHED_ENTROPY(u64) +DEFINE_BATCHED_ENTROPY(u32) #ifdef CONFIG_SMP /* * This function is called when the CPU is coming up, with entry * CPUHP_RANDOM_PREPARE, which comes before CPUHP_WORKQUEUE_PREP. */ -int random_prepare_cpu(unsigned int cpu) +int __cold random_prepare_cpu(unsigned int cpu) { /* * When the cpu comes back online, immediately invalidate both @@ -687,65 +528,6 @@ int random_prepare_cpu(unsigned int cpu) } #endif -/** - * randomize_page - Generate a random, page aligned address - * @start: The smallest acceptable address the caller will take. - * @range: The size of the area, starting at @start, within which the - * random address must fall. - * - * If @start + @range would overflow, @range is capped. - * - * NOTE: Historical use of randomize_range, which this replaces, presumed that - * @start was already page aligned. We now align it regardless. - * - * Return: A page aligned address within [start, start + range). On error, - * @start is returned. - */ -unsigned long randomize_page(unsigned long start, unsigned long range) -{ - if (!PAGE_ALIGNED(start)) { - range -= PAGE_ALIGN(start) - start; - start = PAGE_ALIGN(start); - } - - if (start > ULONG_MAX - range) - range = ULONG_MAX - start; - - range >>= PAGE_SHIFT; - - if (range == 0) - return start; - - return start + (get_random_long() % range << PAGE_SHIFT); -} - -/* - * This function will use the architecture-specific hardware random - * number generator if it is available. It is not recommended for - * use. Use get_random_bytes() instead. It returns the number of - * bytes filled in. - */ -size_t __must_check get_random_bytes_arch(void *buf, size_t nbytes) -{ - size_t left = nbytes; - u8 *p = buf; - - while (left) { - unsigned long v; - size_t chunk = min_t(size_t, left, sizeof(unsigned long)); - - if (!arch_get_random_long(&v)) - break; - - memcpy(p, &v, chunk); - p += chunk; - left -= chunk; - } - - return nbytes - left; -} -EXPORT_SYMBOL(get_random_bytes_arch); - /********************************************************************** * @@ -753,33 +535,28 @@ EXPORT_SYMBOL(get_random_bytes_arch); * * Callers may add entropy via: * - * static void mix_pool_bytes(const void *in, size_t nbytes) + * static void mix_pool_bytes(const void *buf, size_t len) * * After which, if added entropy should be credited: * - * static void credit_entropy_bits(size_t nbits) + * static void credit_init_bits(size_t bits) * - * Finally, extract entropy via these two, with the latter one - * setting the entropy count to zero and extracting only if there - * is POOL_MIN_BITS entropy credited prior or force is true: + * Finally, extract entropy via: * - * static void extract_entropy(void *buf, size_t nbytes) - * static bool drain_entropy(void *buf, size_t nbytes, bool force) + * static void extract_entropy(void *buf, size_t len) * **********************************************************************/ enum { POOL_BITS = BLAKE2S_HASH_SIZE * 8, - POOL_MIN_BITS = POOL_BITS /* No point in settling for less. */ + POOL_READY_BITS = POOL_BITS, /* When crng_init->CRNG_READY */ + POOL_EARLY_BITS = POOL_READY_BITS / 2 /* When crng_init->CRNG_EARLY */ }; -/* For notifying userspace should write into /dev/random. */ -static DECLARE_WAIT_QUEUE_HEAD(random_write_wait); - static struct { struct blake2s_state hash; spinlock_t lock; - unsigned int entropy_count; + unsigned int init_bits; } input_pool = { .hash.h = { BLAKE2S_IV0 ^ (0x01010000 | BLAKE2S_HASH_SIZE), BLAKE2S_IV1, BLAKE2S_IV2, BLAKE2S_IV3, BLAKE2S_IV4, @@ -788,48 +565,30 @@ static struct { .lock = __SPIN_LOCK_UNLOCKED(input_pool.lock), }; -static void _mix_pool_bytes(const void *in, size_t nbytes) +static void _mix_pool_bytes(const void *buf, size_t len) { - blake2s_update(&input_pool.hash, in, nbytes); + blake2s_update(&input_pool.hash, buf, len); } /* - * This function adds bytes into the entropy "pool". It does not - * update the entropy estimate. The caller should call - * credit_entropy_bits if this is appropriate. + * This function adds bytes into the input pool. It does not + * update the initialization bit counter; the caller should call + * credit_init_bits if this is appropriate. */ -static void mix_pool_bytes(const void *in, size_t nbytes) +static void mix_pool_bytes(const void *buf, size_t len) { unsigned long flags; spin_lock_irqsave(&input_pool.lock, flags); - _mix_pool_bytes(in, nbytes); + _mix_pool_bytes(buf, len); spin_unlock_irqrestore(&input_pool.lock, flags); } -static void credit_entropy_bits(size_t nbits) -{ - unsigned int entropy_count, orig, add; - - if (!nbits) - return; - - add = min_t(size_t, nbits, POOL_BITS); - - do { - orig = READ_ONCE(input_pool.entropy_count); - entropy_count = min_t(unsigned int, POOL_BITS, orig + add); - } while (cmpxchg(&input_pool.entropy_count, orig, entropy_count) != orig); - - if (!crng_ready() && entropy_count >= POOL_MIN_BITS) - crng_reseed(false); -} - /* * This is an HKDF-like construction for using the hashed collected entropy * as a PRF key, that's then expanded block-by-block. */ -static void extract_entropy(void *buf, size_t nbytes) +static void extract_entropy(void *buf, size_t len) { unsigned long flags; u8 seed[BLAKE2S_HASH_SIZE], next_key[BLAKE2S_HASH_SIZE]; @@ -858,12 +617,12 @@ static void extract_entropy(void *buf, size_t nbytes) spin_unlock_irqrestore(&input_pool.lock, flags); memzero_explicit(next_key, sizeof(next_key)); - while (nbytes) { - i = min_t(size_t, nbytes, BLAKE2S_HASH_SIZE); + while (len) { + i = min_t(size_t, len, BLAKE2S_HASH_SIZE); /* output = HASHPRF(seed, RDSEED || ++counter) */ ++block.counter; blake2s(buf, (u8 *)&block, seed, i, sizeof(block), sizeof(seed)); - nbytes -= i; + len -= i; buf += i; } @@ -871,23 +630,42 @@ static void extract_entropy(void *buf, size_t nbytes) memzero_explicit(&block, sizeof(block)); } -/* - * First we make sure we have POOL_MIN_BITS of entropy in the pool unless force - * is true, and then we set the entropy count to zero (but don't actually touch - * any data). Only then can we extract a new key with extract_entropy(). - */ -static bool drain_entropy(void *buf, size_t nbytes, bool force) +#define credit_init_bits(bits) if (!crng_ready()) _credit_init_bits(bits) + +static void __cold _credit_init_bits(size_t bits) { - unsigned int entropy_count; + static struct execute_work set_ready; + unsigned int new, orig, add; + unsigned long flags; + + if (!bits) + return; + + add = min_t(size_t, bits, POOL_BITS); + do { - entropy_count = READ_ONCE(input_pool.entropy_count); - if (!force && entropy_count < POOL_MIN_BITS) - return false; - } while (cmpxchg(&input_pool.entropy_count, entropy_count, 0) != entropy_count); - extract_entropy(buf, nbytes); - wake_up_interruptible(&random_write_wait); - kill_fasync(&fasync, SIGIO, POLL_OUT); - return true; + orig = READ_ONCE(input_pool.init_bits); + new = min_t(unsigned int, POOL_BITS, orig + add); + } while (cmpxchg(&input_pool.init_bits, orig, new) != orig); + + if (orig < POOL_READY_BITS && new >= POOL_READY_BITS) { + crng_reseed(); /* Sets crng_init to CRNG_READY under base_crng.lock. */ + execute_in_process_context(crng_set_ready, &set_ready); + wake_up_interruptible(&crng_init_wait); + kill_fasync(&fasync, SIGIO, POLL_IN); + pr_notice("crng init done\n"); + if (urandom_warning.missed) + pr_notice("%d urandom warning(s) missed due to ratelimiting\n", + urandom_warning.missed); + } else if (orig < POOL_EARLY_BITS && new >= POOL_EARLY_BITS) { + spin_lock_irqsave(&base_crng.lock, flags); + /* Check if crng_init is CRNG_EMPTY, to avoid race with crng_reseed(). */ + if (crng_init == CRNG_EMPTY) { + extract_entropy(base_crng.key, sizeof(base_crng.key)); + crng_init = CRNG_EARLY; + } + spin_unlock_irqrestore(&base_crng.lock, flags); + } } @@ -898,15 +676,13 @@ static bool drain_entropy(void *buf, size_t nbytes, bool force) * The following exported functions are used for pushing entropy into * the above entropy accumulation routines: * - * void add_device_randomness(const void *buf, size_t size); - * void add_input_randomness(unsigned int type, unsigned int code, - * unsigned int value); - * void add_disk_randomness(struct gendisk *disk); - * void add_hwgenerator_randomness(const void *buffer, size_t count, - * size_t entropy); - * void add_bootloader_randomness(const void *buf, size_t size); - * void add_vmfork_randomness(const void *unique_vm_id, size_t size); + * void add_device_randomness(const void *buf, size_t len); + * void add_hwgenerator_randomness(const void *buf, size_t len, size_t entropy); + * void add_bootloader_randomness(const void *buf, size_t len); + * void add_vmfork_randomness(const void *unique_vm_id, size_t len); * void add_interrupt_randomness(int irq); + * void add_input_randomness(unsigned int type, unsigned int code, unsigned int value); + * void add_disk_randomness(struct gendisk *disk); * * add_device_randomness() adds data to the input pool that * is likely to differ between two devices (or possibly even per boot). @@ -916,26 +692,13 @@ static bool drain_entropy(void *buf, size_t nbytes, bool force) * that might otherwise be identical and have very little entropy * available to them (particularly common in the embedded world). * - * add_input_randomness() uses the input layer interrupt timing, as well - * as the event type information from the hardware. - * - * add_disk_randomness() uses what amounts to the seek time of block - * layer request events, on a per-disk_devt basis, as input to the - * entropy pool. Note that high-speed solid state drives with very low - * seek times do not make for good sources of entropy, as their seek - * times are usually fairly consistent. - * - * The above two routines try to estimate how many bits of entropy - * to credit. They do this by keeping track of the first and second - * order deltas of the event timings. - * * add_hwgenerator_randomness() is for true hardware RNGs, and will credit * entropy as specified by the caller. If the entropy pool is full it will * block until more entropy is needed. * - * add_bootloader_randomness() is the same as add_hwgenerator_randomness() or - * add_device_randomness(), depending on whether or not the configuration - * option CONFIG_RANDOM_TRUST_BOOTLOADER is set. + * add_bootloader_randomness() is called by bootloader drivers, such as EFI + * and device tree, and credits its input depending on whether or not the + * configuration option CONFIG_RANDOM_TRUST_BOOTLOADER is set. * * add_vmfork_randomness() adds a unique (but not necessarily secret) ID * representing the current instance of a VM to the pool, without crediting, @@ -946,8 +709,22 @@ static bool drain_entropy(void *buf, size_t nbytes, bool force) * as inputs, it feeds the input pool roughly once a second or after 64 * interrupts, crediting 1 bit of entropy for whichever comes first. * + * add_input_randomness() uses the input layer interrupt timing, as well + * as the event type information from the hardware. + * + * add_disk_randomness() uses what amounts to the seek time of block + * layer request events, on a per-disk_devt basis, as input to the + * entropy pool. Note that high-speed solid state drives with very low + * seek times do not make for good sources of entropy, as their seek + * times are usually fairly consistent. + * + * The last two routines try to estimate how many bits of entropy + * to credit. They do this by keeping track of the first and second + * order deltas of the event timings. + * **********************************************************************/ +static bool used_arch_random; static bool trust_cpu __ro_after_init = IS_ENABLED(CONFIG_RANDOM_TRUST_CPU); static bool trust_bootloader __ro_after_init = IS_ENABLED(CONFIG_RANDOM_TRUST_BOOTLOADER); static int __init parse_trust_cpu(char *arg) @@ -961,52 +738,91 @@ static int __init parse_trust_bootloader(char *arg) early_param("random.trust_cpu", parse_trust_cpu); early_param("random.trust_bootloader", parse_trust_bootloader); +static int random_pm_notification(struct notifier_block *nb, unsigned long action, void *data) +{ + unsigned long flags, entropy = random_get_entropy(); + + /* + * Encode a representation of how long the system has been suspended, + * in a way that is distinct from prior system suspends. + */ + ktime_t stamps[] = { ktime_get(), ktime_get_boottime(), ktime_get_real() }; + + spin_lock_irqsave(&input_pool.lock, flags); + _mix_pool_bytes(&action, sizeof(action)); + _mix_pool_bytes(stamps, sizeof(stamps)); + _mix_pool_bytes(&entropy, sizeof(entropy)); + spin_unlock_irqrestore(&input_pool.lock, flags); + + if (crng_ready() && (action == PM_RESTORE_PREPARE || + (action == PM_POST_SUSPEND && + !IS_ENABLED(CONFIG_PM_AUTOSLEEP) && !IS_ENABLED(CONFIG_ANDROID)))) { + crng_reseed(); + pr_notice("crng reseeded on system resumption\n"); + } + return 0; +} + +static struct notifier_block pm_notifier = { .notifier_call = random_pm_notification }; + /* * The first collection of entropy occurs at system boot while interrupts - * are still turned off. Here we push in RDSEED, a timestamp, and utsname(). - * Depending on the above configuration knob, RDSEED may be considered - * sufficient for initialization. Note that much earlier setup may already - * have pushed entropy into the input pool by the time we get here. + * are still turned off. Here we push in latent entropy, RDSEED, a timestamp, + * utsname(), and the command line. Depending on the above configuration knob, + * RDSEED may be considered sufficient for initialization. Note that much + * earlier setup may already have pushed entropy into the input pool by the + * time we get here. */ -int __init rand_initialize(void) +int __init random_init(const char *command_line) { - size_t i; ktime_t now = ktime_get_real(); - bool arch_init = true; - unsigned long rv; + unsigned int i, arch_bytes; + unsigned long entropy; #if defined(LATENT_ENTROPY_PLUGIN) static const u8 compiletime_seed[BLAKE2S_BLOCK_SIZE] __initconst __latent_entropy; _mix_pool_bytes(compiletime_seed, sizeof(compiletime_seed)); #endif - for (i = 0; i < BLAKE2S_BLOCK_SIZE; i += sizeof(rv)) { - if (!arch_get_random_seed_long_early(&rv) && - !arch_get_random_long_early(&rv)) { - rv = random_get_entropy(); - arch_init = false; + for (i = 0, arch_bytes = BLAKE2S_BLOCK_SIZE; + i < BLAKE2S_BLOCK_SIZE; i += sizeof(entropy)) { + if (!arch_get_random_seed_long_early(&entropy) && + !arch_get_random_long_early(&entropy)) { + entropy = random_get_entropy(); + arch_bytes -= sizeof(entropy); } - _mix_pool_bytes(&rv, sizeof(rv)); + _mix_pool_bytes(&entropy, sizeof(entropy)); } _mix_pool_bytes(&now, sizeof(now)); _mix_pool_bytes(utsname(), sizeof(*(utsname()))); + _mix_pool_bytes(command_line, strlen(command_line)); + add_latent_entropy(); - extract_entropy(base_crng.key, sizeof(base_crng.key)); - ++base_crng.generation; + if (crng_ready()) + crng_reseed(); + else if (trust_cpu) + credit_init_bits(arch_bytes * 8); + used_arch_random = arch_bytes * 8 >= POOL_READY_BITS; - if (arch_init && trust_cpu && !crng_ready()) { - crng_init = 2; - pr_notice("crng init done (trusting CPU's manufacturer)\n"); - } + WARN_ON(register_pm_notifier(&pm_notifier)); - if (ratelimit_disable) { - urandom_warning.interval = 0; - unseeded_warning.interval = 0; - } + WARN(!random_get_entropy(), "Missing cycle counter and fallback timer; RNG " + "entropy collection will consequently suffer."); return 0; } /* + * Returns whether arch randomness has been mixed into the initial + * state of the RNG, regardless of whether or not that randomness + * was credited. Knowing this is only good for a very limited set + * of uses, such as early init printk pointer obfuscation. + */ +bool rng_has_arch_random(void) +{ + return used_arch_random; +} + +/* * Add device- or boot-specific data to the input pool to help * initialize it. * @@ -1014,168 +830,46 @@ int __init rand_initialize(void) * the entropy pool having similar initial state across largely * identical devices. */ -void add_device_randomness(const void *buf, size_t size) +void add_device_randomness(const void *buf, size_t len) { - cycles_t cycles = random_get_entropy(); - unsigned long flags, now = jiffies; - - if (crng_init == 0 && size) - crng_pre_init_inject(buf, size, false); + unsigned long entropy = random_get_entropy(); + unsigned long flags; spin_lock_irqsave(&input_pool.lock, flags); - _mix_pool_bytes(&cycles, sizeof(cycles)); - _mix_pool_bytes(&now, sizeof(now)); - _mix_pool_bytes(buf, size); + _mix_pool_bytes(&entropy, sizeof(entropy)); + _mix_pool_bytes(buf, len); spin_unlock_irqrestore(&input_pool.lock, flags); } EXPORT_SYMBOL(add_device_randomness); -/* There is one of these per entropy source */ -struct timer_rand_state { - unsigned long last_time; - long last_delta, last_delta2; -}; - -/* - * This function adds entropy to the entropy "pool" by using timing - * delays. It uses the timer_rand_state structure to make an estimate - * of how many bits of entropy this call has added to the pool. - * - * The number "num" is also added to the pool - it should somehow describe - * the type of event which just happened. This is currently 0-255 for - * keyboard scan codes, and 256 upwards for interrupts. - */ -static void add_timer_randomness(struct timer_rand_state *state, unsigned int num) -{ - cycles_t cycles = random_get_entropy(); - unsigned long flags, now = jiffies; - long delta, delta2, delta3; - - spin_lock_irqsave(&input_pool.lock, flags); - _mix_pool_bytes(&cycles, sizeof(cycles)); - _mix_pool_bytes(&now, sizeof(now)); - _mix_pool_bytes(&num, sizeof(num)); - spin_unlock_irqrestore(&input_pool.lock, flags); - - /* - * Calculate number of bits of randomness we probably added. - * We take into account the first, second and third-order deltas - * in order to make our estimate. - */ - delta = now - READ_ONCE(state->last_time); - WRITE_ONCE(state->last_time, now); - - delta2 = delta - READ_ONCE(state->last_delta); - WRITE_ONCE(state->last_delta, delta); - - delta3 = delta2 - READ_ONCE(state->last_delta2); - WRITE_ONCE(state->last_delta2, delta2); - - if (delta < 0) - delta = -delta; - if (delta2 < 0) - delta2 = -delta2; - if (delta3 < 0) - delta3 = -delta3; - if (delta > delta2) - delta = delta2; - if (delta > delta3) - delta = delta3; - - /* - * delta is now minimum absolute delta. - * Round down by 1 bit on general principles, - * and limit entropy estimate to 12 bits. - */ - credit_entropy_bits(min_t(unsigned int, fls(delta >> 1), 11)); -} - -void add_input_randomness(unsigned int type, unsigned int code, - unsigned int value) -{ - static unsigned char last_value; - static struct timer_rand_state input_timer_state = { INITIAL_JIFFIES }; - - /* Ignore autorepeat and the like. */ - if (value == last_value) - return; - - last_value = value; - add_timer_randomness(&input_timer_state, - (type << 4) ^ code ^ (code >> 4) ^ value); -} -EXPORT_SYMBOL_GPL(add_input_randomness); - -#ifdef CONFIG_BLOCK -void add_disk_randomness(struct gendisk *disk) -{ - if (!disk || !disk->random) - return; - /* First major is 1, so we get >= 0x200 here. */ - add_timer_randomness(disk->random, 0x100 + disk_devt(disk)); -} -EXPORT_SYMBOL_GPL(add_disk_randomness); - -void rand_initialize_disk(struct gendisk *disk) -{ - struct timer_rand_state *state; - - /* - * If kzalloc returns null, we just won't use that entropy - * source. - */ - state = kzalloc(sizeof(struct timer_rand_state), GFP_KERNEL); - if (state) { - state->last_time = INITIAL_JIFFIES; - disk->random = state; - } -} -#endif - /* * Interface for in-kernel drivers of true hardware RNGs. * Those devices may produce endless random bits and will be throttled * when our pool is full. */ -void add_hwgenerator_randomness(const void *buffer, size_t count, - size_t entropy) +void add_hwgenerator_randomness(const void *buf, size_t len, size_t entropy) { - if (unlikely(crng_init == 0 && entropy < POOL_MIN_BITS)) { - size_t ret = crng_pre_init_inject(buffer, count, true); - mix_pool_bytes(buffer, ret); - count -= ret; - buffer += ret; - if (!count || crng_init == 0) - return; - } + mix_pool_bytes(buf, len); + credit_init_bits(entropy); /* - * Throttle writing if we're above the trickle threshold. - * We'll be woken up again once below POOL_MIN_BITS, when - * the calling thread is about to terminate, or once - * CRNG_RESEED_INTERVAL has elapsed. + * Throttle writing to once every CRNG_RESEED_INTERVAL, unless + * we're not yet initialized. */ - wait_event_interruptible_timeout(random_write_wait, - !system_wq || kthread_should_stop() || - input_pool.entropy_count < POOL_MIN_BITS, - CRNG_RESEED_INTERVAL); - mix_pool_bytes(buffer, count); - credit_entropy_bits(entropy); + if (!kthread_should_stop() && crng_ready()) + schedule_timeout_interruptible(CRNG_RESEED_INTERVAL); } EXPORT_SYMBOL_GPL(add_hwgenerator_randomness); /* - * Handle random seed passed by bootloader. - * If the seed is trustworthy, it would be regarded as hardware RNGs. Otherwise - * it would be regarded as device data. - * The decision is controlled by CONFIG_RANDOM_TRUST_BOOTLOADER. + * Handle random seed passed by bootloader, and credit it if + * CONFIG_RANDOM_TRUST_BOOTLOADER is set. */ -void add_bootloader_randomness(const void *buf, size_t size) +void __cold add_bootloader_randomness(const void *buf, size_t len) { + mix_pool_bytes(buf, len); if (trust_bootloader) - add_hwgenerator_randomness(buf, size, size * 8); - else - add_device_randomness(buf, size); + credit_init_bits(len * 8); } EXPORT_SYMBOL_GPL(add_bootloader_randomness); @@ -1187,11 +881,11 @@ static BLOCKING_NOTIFIER_HEAD(vmfork_chain); * don't credit it, but we do immediately force a reseed after so * that it's used by the crng posthaste. */ -void add_vmfork_randomness(const void *unique_vm_id, size_t size) +void __cold add_vmfork_randomness(const void *unique_vm_id, size_t len) { - add_device_randomness(unique_vm_id, size); + add_device_randomness(unique_vm_id, len); if (crng_ready()) { - crng_reseed(true); + crng_reseed(); pr_notice("crng reseeded due to virtual machine fork\n"); } blocking_notifier_call_chain(&vmfork_chain, 0, NULL); @@ -1200,13 +894,13 @@ void add_vmfork_randomness(const void *unique_vm_id, size_t size) EXPORT_SYMBOL_GPL(add_vmfork_randomness); #endif -int register_random_vmfork_notifier(struct notifier_block *nb) +int __cold register_random_vmfork_notifier(struct notifier_block *nb) { return blocking_notifier_chain_register(&vmfork_chain, nb); } EXPORT_SYMBOL_GPL(register_random_vmfork_notifier); -int unregister_random_vmfork_notifier(struct notifier_block *nb) +int __cold unregister_random_vmfork_notifier(struct notifier_block *nb) { return blocking_notifier_chain_unregister(&vmfork_chain, nb); } @@ -1218,17 +912,15 @@ struct fast_pool { unsigned long pool[4]; unsigned long last; unsigned int count; - u16 reg_idx; }; static DEFINE_PER_CPU(struct fast_pool, irq_randomness) = { #ifdef CONFIG_64BIT - /* SipHash constants */ - .pool = { 0x736f6d6570736575UL, 0x646f72616e646f6dUL, - 0x6c7967656e657261UL, 0x7465646279746573UL } +#define FASTMIX_PERM SIPHASH_PERMUTATION + .pool = { SIPHASH_CONST_0, SIPHASH_CONST_1, SIPHASH_CONST_2, SIPHASH_CONST_3 } #else - /* HalfSipHash constants */ - .pool = { 0, 0, 0x6c796765U, 0x74656462U } +#define FASTMIX_PERM HSIPHASH_PERMUTATION + .pool = { HSIPHASH_CONST_0, HSIPHASH_CONST_1, HSIPHASH_CONST_2, HSIPHASH_CONST_3 } #endif }; @@ -1236,27 +928,16 @@ static DEFINE_PER_CPU(struct fast_pool, irq_randomness) = { * This is [Half]SipHash-1-x, starting from an empty key. Because * the key is fixed, it assumes that its inputs are non-malicious, * and therefore this has no security on its own. s represents the - * 128 or 256-bit SipHash state, while v represents a 128-bit input. + * four-word SipHash state, while v represents a two-word input. */ -static void fast_mix(unsigned long s[4], const unsigned long *v) +static void fast_mix(unsigned long s[4], unsigned long v1, unsigned long v2) { - size_t i; - - for (i = 0; i < 16 / sizeof(long); ++i) { - s[3] ^= v[i]; -#ifdef CONFIG_64BIT - s[0] += s[1]; s[1] = rol64(s[1], 13); s[1] ^= s[0]; s[0] = rol64(s[0], 32); - s[2] += s[3]; s[3] = rol64(s[3], 16); s[3] ^= s[2]; - s[0] += s[3]; s[3] = rol64(s[3], 21); s[3] ^= s[0]; - s[2] += s[1]; s[1] = rol64(s[1], 17); s[1] ^= s[2]; s[2] = rol64(s[2], 32); -#else - s[0] += s[1]; s[1] = rol32(s[1], 5); s[1] ^= s[0]; s[0] = rol32(s[0], 16); - s[2] += s[3]; s[3] = rol32(s[3], 8); s[3] ^= s[2]; - s[0] += s[3]; s[3] = rol32(s[3], 7); s[3] ^= s[0]; - s[2] += s[1]; s[1] = rol32(s[1], 13); s[1] ^= s[2]; s[2] = rol32(s[2], 16); -#endif - s[0] ^= v[i]; - } + s[3] ^= v1; + FASTMIX_PERM(s[0], s[1], s[2], s[3]); + s[0] ^= v1; + s[3] ^= v2; + FASTMIX_PERM(s[0], s[1], s[2], s[3]); + s[0] ^= v2; } #ifdef CONFIG_SMP @@ -1264,7 +945,7 @@ static void fast_mix(unsigned long s[4], const unsigned long *v) * This function is called when the CPU has just come online, with * entry CPUHP_AP_RANDOM_ONLINE, just after CPUHP_AP_WORKQUEUE_ONLINE. */ -int random_online_cpu(unsigned int cpu) +int __cold random_online_cpu(unsigned int cpu) { /* * During CPU shutdown and before CPU onlining, add_interrupt_ @@ -1282,33 +963,18 @@ int random_online_cpu(unsigned int cpu) } #endif -static unsigned long get_reg(struct fast_pool *f, struct pt_regs *regs) -{ - unsigned long *ptr = (unsigned long *)regs; - unsigned int idx; - - if (regs == NULL) - return 0; - idx = READ_ONCE(f->reg_idx); - if (idx >= sizeof(struct pt_regs) / sizeof(unsigned long)) - idx = 0; - ptr += idx++; - WRITE_ONCE(f->reg_idx, idx); - return *ptr; -} - static void mix_interrupt_randomness(struct work_struct *work) { struct fast_pool *fast_pool = container_of(work, struct fast_pool, mix); /* - * The size of the copied stack pool is explicitly 16 bytes so that we - * tax mix_pool_byte()'s compression function the same amount on all - * platforms. This means on 64-bit we copy half the pool into this, - * while on 32-bit we copy all of it. The entropy is supposed to be - * sufficiently dispersed between bits that in the sponge-like - * half case, on average we don't wind up "losing" some. + * The size of the copied stack pool is explicitly 2 longs so that we + * only ever ingest half of the siphash output each time, retaining + * the other half as the next "key" that carries over. The entropy is + * supposed to be sufficiently dispersed between bits so on average + * we don't wind up "losing" some. */ - u8 pool[16]; + unsigned long pool[2]; + unsigned int count; /* Check to see if we're running on the wrong CPU due to hotplug. */ local_irq_disable(); @@ -1322,17 +988,13 @@ static void mix_interrupt_randomness(struct work_struct *work) * consistent view, before we reenable irqs again. */ memcpy(pool, fast_pool->pool, sizeof(pool)); + count = fast_pool->count; fast_pool->count = 0; fast_pool->last = jiffies; local_irq_enable(); - if (unlikely(crng_init == 0)) { - crng_pre_init_inject(pool, sizeof(pool), true); - mix_pool_bytes(pool, sizeof(pool)); - } else { - mix_pool_bytes(pool, sizeof(pool)); - credit_entropy_bits(1); - } + mix_pool_bytes(pool, sizeof(pool)); + credit_init_bits(max(1u, (count & U16_MAX) / 64)); memzero_explicit(pool, sizeof(pool)); } @@ -1340,42 +1002,19 @@ static void mix_interrupt_randomness(struct work_struct *work) void add_interrupt_randomness(int irq) { enum { MIX_INFLIGHT = 1U << 31 }; - cycles_t cycles = random_get_entropy(); - unsigned long now = jiffies; + unsigned long entropy = random_get_entropy(); struct fast_pool *fast_pool = this_cpu_ptr(&irq_randomness); struct pt_regs *regs = get_irq_regs(); unsigned int new_count; - union { - u32 u32[4]; - u64 u64[2]; - unsigned long longs[16 / sizeof(long)]; - } irq_data; - - if (cycles == 0) - cycles = get_reg(fast_pool, regs); - - if (sizeof(cycles) == 8) - irq_data.u64[0] = cycles ^ rol64(now, 32) ^ irq; - else { - irq_data.u32[0] = cycles ^ irq; - irq_data.u32[1] = now; - } - if (sizeof(unsigned long) == 8) - irq_data.u64[1] = regs ? instruction_pointer(regs) : _RET_IP_; - else { - irq_data.u32[2] = regs ? instruction_pointer(regs) : _RET_IP_; - irq_data.u32[3] = get_reg(fast_pool, regs); - } - - fast_mix(fast_pool->pool, irq_data.longs); + fast_mix(fast_pool->pool, entropy, + (regs ? instruction_pointer(regs) : _RET_IP_) ^ swab(irq)); new_count = ++fast_pool->count; if (new_count & MIX_INFLIGHT) return; - if (new_count < 64 && (!time_after(now, fast_pool->last + HZ) || - unlikely(crng_init == 0))) + if (new_count < 64 && !time_is_before_jiffies(fast_pool->last + HZ)) return; if (unlikely(!fast_pool->mix.func)) @@ -1385,6 +1024,132 @@ void add_interrupt_randomness(int irq) } EXPORT_SYMBOL_GPL(add_interrupt_randomness); +/* There is one of these per entropy source */ +struct timer_rand_state { + unsigned long last_time; + long last_delta, last_delta2; +}; + +/* + * This function adds entropy to the entropy "pool" by using timing + * delays. It uses the timer_rand_state structure to make an estimate + * of how many bits of entropy this call has added to the pool. The + * value "num" is also added to the pool; it should somehow describe + * the type of event that just happened. + */ +static void add_timer_randomness(struct timer_rand_state *state, unsigned int num) +{ + unsigned long entropy = random_get_entropy(), now = jiffies, flags; + long delta, delta2, delta3; + unsigned int bits; + + /* + * If we're in a hard IRQ, add_interrupt_randomness() will be called + * sometime after, so mix into the fast pool. + */ + if (in_hardirq()) { + fast_mix(this_cpu_ptr(&irq_randomness)->pool, entropy, num); + } else { + spin_lock_irqsave(&input_pool.lock, flags); + _mix_pool_bytes(&entropy, sizeof(entropy)); + _mix_pool_bytes(&num, sizeof(num)); + spin_unlock_irqrestore(&input_pool.lock, flags); + } + + if (crng_ready()) + return; + + /* + * Calculate number of bits of randomness we probably added. + * We take into account the first, second and third-order deltas + * in order to make our estimate. + */ + delta = now - READ_ONCE(state->last_time); + WRITE_ONCE(state->last_time, now); + + delta2 = delta - READ_ONCE(state->last_delta); + WRITE_ONCE(state->last_delta, delta); + + delta3 = delta2 - READ_ONCE(state->last_delta2); + WRITE_ONCE(state->last_delta2, delta2); + + if (delta < 0) + delta = -delta; + if (delta2 < 0) + delta2 = -delta2; + if (delta3 < 0) + delta3 = -delta3; + if (delta > delta2) + delta = delta2; + if (delta > delta3) + delta = delta3; + + /* + * delta is now minimum absolute delta. Round down by 1 bit + * on general principles, and limit entropy estimate to 11 bits. + */ + bits = min(fls(delta >> 1), 11); + + /* + * As mentioned above, if we're in a hard IRQ, add_interrupt_randomness() + * will run after this, which uses a different crediting scheme of 1 bit + * per every 64 interrupts. In order to let that function do accounting + * close to the one in this function, we credit a full 64/64 bit per bit, + * and then subtract one to account for the extra one added. + */ + if (in_hardirq()) + this_cpu_ptr(&irq_randomness)->count += max(1u, bits * 64) - 1; + else + _credit_init_bits(bits); +} + +void add_input_randomness(unsigned int type, unsigned int code, unsigned int value) +{ + static unsigned char last_value; + static struct timer_rand_state input_timer_state = { INITIAL_JIFFIES }; + + /* Ignore autorepeat and the like. */ + if (value == last_value) + return; + + last_value = value; + add_timer_randomness(&input_timer_state, + (type << 4) ^ code ^ (code >> 4) ^ value); +} +EXPORT_SYMBOL_GPL(add_input_randomness); + +#ifdef CONFIG_BLOCK +void add_disk_randomness(struct gendisk *disk) +{ + if (!disk || !disk->random) + return; + /* First major is 1, so we get >= 0x200 here. */ + add_timer_randomness(disk->random, 0x100 + disk_devt(disk)); +} +EXPORT_SYMBOL_GPL(add_disk_randomness); + +void __cold rand_initialize_disk(struct gendisk *disk) +{ + struct timer_rand_state *state; + + /* + * If kzalloc returns null, we just won't use that entropy + * source. + */ + state = kzalloc(sizeof(struct timer_rand_state), GFP_KERNEL); + if (state) { + state->last_time = INITIAL_JIFFIES; + disk->random = state; + } +} +#endif + +struct entropy_timer_state { + unsigned long entropy; + struct timer_list timer; + unsigned int samples, samples_per_bit; +}; + /* * Each time the timer fires, we expect that we got an unpredictable * jump in the cycle counter. Even if the timer is running on another @@ -1398,40 +1163,50 @@ EXPORT_SYMBOL_GPL(add_interrupt_randomness); * * So the re-arming always happens in the entropy loop itself. */ -static void entropy_timer(struct timer_list *t) +static void __cold entropy_timer(struct timer_list *timer) { - credit_entropy_bits(1); + struct entropy_timer_state *state = container_of(timer, struct entropy_timer_state, timer); + + if (++state->samples == state->samples_per_bit) { + credit_init_bits(1); + state->samples = 0; + } } /* * If we have an actual cycle counter, see if we can * generate enough entropy with timing noise */ -static void try_to_generate_entropy(void) +static void __cold try_to_generate_entropy(void) { - struct { - cycles_t cycles; - struct timer_list timer; - } stack; - - stack.cycles = random_get_entropy(); - - /* Slow counter - or none. Don't even bother */ - if (stack.cycles == random_get_entropy()) + enum { NUM_TRIAL_SAMPLES = 8192, MAX_SAMPLES_PER_BIT = 32 }; + struct entropy_timer_state stack; + unsigned int i, num_different = 0; + unsigned long last = random_get_entropy(); + + for (i = 0; i < NUM_TRIAL_SAMPLES - 1; ++i) { + stack.entropy = random_get_entropy(); + if (stack.entropy != last) + ++num_different; + last = stack.entropy; + } + stack.samples_per_bit = DIV_ROUND_UP(NUM_TRIAL_SAMPLES, num_different + 1); + if (stack.samples_per_bit > MAX_SAMPLES_PER_BIT) return; + stack.samples = 0; timer_setup_on_stack(&stack.timer, entropy_timer, 0); while (!crng_ready() && !signal_pending(current)) { if (!timer_pending(&stack.timer)) mod_timer(&stack.timer, jiffies + 1); - mix_pool_bytes(&stack.cycles, sizeof(stack.cycles)); + mix_pool_bytes(&stack.entropy, sizeof(stack.entropy)); schedule(); - stack.cycles = random_get_entropy(); + stack.entropy = random_get_entropy(); } del_timer_sync(&stack.timer); destroy_timer_on_stack(&stack.timer); - mix_pool_bytes(&stack.cycles, sizeof(stack.cycles)); + mix_pool_bytes(&stack.entropy, sizeof(stack.entropy)); } @@ -1463,9 +1238,12 @@ static void try_to_generate_entropy(void) * **********************************************************************/ -SYSCALL_DEFINE3(getrandom, char __user *, buf, size_t, count, unsigned int, - flags) +SYSCALL_DEFINE3(getrandom, char __user *, ubuf, size_t, len, unsigned int, flags) { + struct iov_iter iter; + struct iovec iov; + int ret; + if (flags & ~(GRND_NONBLOCK | GRND_RANDOM | GRND_INSECURE)) return -EINVAL; @@ -1476,106 +1254,102 @@ SYSCALL_DEFINE3(getrandom, char __user *, buf, size_t, count, unsigned int, if ((flags & (GRND_INSECURE | GRND_RANDOM)) == (GRND_INSECURE | GRND_RANDOM)) return -EINVAL; - if (count > INT_MAX) - count = INT_MAX; - - if (!(flags & GRND_INSECURE) && !crng_ready()) { - int ret; - + if (!crng_ready() && !(flags & GRND_INSECURE)) { if (flags & GRND_NONBLOCK) return -EAGAIN; ret = wait_for_random_bytes(); if (unlikely(ret)) return ret; } - return get_random_bytes_user(buf, count); + + ret = import_single_range(READ, ubuf, len, &iov, &iter); + if (unlikely(ret)) + return ret; + return get_random_bytes_user(&iter); } static __poll_t random_poll(struct file *file, poll_table *wait) { - __poll_t mask; - poll_wait(file, &crng_init_wait, wait); - poll_wait(file, &random_write_wait, wait); - mask = 0; - if (crng_ready()) - mask |= EPOLLIN | EPOLLRDNORM; - if (input_pool.entropy_count < POOL_MIN_BITS) - mask |= EPOLLOUT | EPOLLWRNORM; - return mask; + return crng_ready() ? EPOLLIN | EPOLLRDNORM : EPOLLOUT | EPOLLWRNORM; } -static int write_pool(const char __user *ubuf, size_t count) +static ssize_t write_pool_user(struct iov_iter *iter) { - size_t len; - int ret = 0; u8 block[BLAKE2S_BLOCK_SIZE]; + ssize_t ret = 0; + size_t copied; + + if (unlikely(!iov_iter_count(iter))) + return 0; - while (count) { - len = min(count, sizeof(block)); - if (copy_from_user(block, ubuf, len)) { - ret = -EFAULT; - goto out; + for (;;) { + copied = copy_from_iter(block, sizeof(block), iter); + ret += copied; + mix_pool_bytes(block, copied); + if (!iov_iter_count(iter) || copied != sizeof(block)) + break; + + BUILD_BUG_ON(PAGE_SIZE % sizeof(block) != 0); + if (ret % PAGE_SIZE == 0) { + if (signal_pending(current)) + break; + cond_resched(); } - count -= len; - ubuf += len; - mix_pool_bytes(block, len); - cond_resched(); } -out: memzero_explicit(block, sizeof(block)); - return ret; + return ret ? ret : -EFAULT; } -static ssize_t random_write(struct file *file, const char __user *buffer, - size_t count, loff_t *ppos) +static ssize_t random_write_iter(struct kiocb *kiocb, struct iov_iter *iter) { - int ret; - - ret = write_pool(buffer, count); - if (ret) - return ret; - - return (ssize_t)count; + return write_pool_user(iter); } -static ssize_t urandom_read(struct file *file, char __user *buf, size_t nbytes, - loff_t *ppos) +static ssize_t urandom_read_iter(struct kiocb *kiocb, struct iov_iter *iter) { static int maxwarn = 10; - if (!crng_ready() && maxwarn > 0) { - maxwarn--; - if (__ratelimit(&urandom_warning)) - pr_notice("%s: uninitialized urandom read (%zd bytes read)\n", - current->comm, nbytes); + /* + * Opportunistically attempt to initialize the RNG on platforms that + * have fast cycle counters, but don't (for now) require it to succeed. + */ + if (!crng_ready()) + try_to_generate_entropy(); + + if (!crng_ready()) { + if (!ratelimit_disable && maxwarn <= 0) + ++urandom_warning.missed; + else if (ratelimit_disable || __ratelimit(&urandom_warning)) { + --maxwarn; + pr_notice("%s: uninitialized urandom read (%zu bytes read)\n", + current->comm, iov_iter_count(iter)); + } } - return get_random_bytes_user(buf, nbytes); + return get_random_bytes_user(iter); } -static ssize_t random_read(struct file *file, char __user *buf, size_t nbytes, - loff_t *ppos) +static ssize_t random_read_iter(struct kiocb *kiocb, struct iov_iter *iter) { int ret; ret = wait_for_random_bytes(); if (ret != 0) return ret; - return get_random_bytes_user(buf, nbytes); + return get_random_bytes_user(iter); } static long random_ioctl(struct file *f, unsigned int cmd, unsigned long arg) { - int size, ent_count; int __user *p = (int __user *)arg; - int retval; + int ent_count; switch (cmd) { case RNDGETENTCNT: /* Inherently racy, no point locking. */ - if (put_user(input_pool.entropy_count, p)) + if (put_user(input_pool.init_bits, p)) return -EFAULT; return 0; case RNDADDTOENTCNT: @@ -1585,41 +1359,46 @@ static long random_ioctl(struct file *f, unsigned int cmd, unsigned long arg) return -EFAULT; if (ent_count < 0) return -EINVAL; - credit_entropy_bits(ent_count); + credit_init_bits(ent_count); return 0; - case RNDADDENTROPY: + case RNDADDENTROPY: { + struct iov_iter iter; + struct iovec iov; + ssize_t ret; + int len; + if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (get_user(ent_count, p++)) return -EFAULT; if (ent_count < 0) return -EINVAL; - if (get_user(size, p++)) + if (get_user(len, p++)) return -EFAULT; - retval = write_pool((const char __user *)p, size); - if (retval < 0) - return retval; - credit_entropy_bits(ent_count); + ret = import_single_range(WRITE, p, len, &iov, &iter); + if (unlikely(ret)) + return ret; + ret = write_pool_user(&iter); + if (unlikely(ret < 0)) + return ret; + /* Since we're crediting, enforce that it was all written into the pool. */ + if (unlikely(ret != len)) + return -EFAULT; + credit_init_bits(ent_count); return 0; + } case RNDZAPENTCNT: case RNDCLEARPOOL: - /* - * Clear the entropy pool counters. We no longer clear - * the entropy pool, as that's silly. - */ + /* No longer has any effect. */ if (!capable(CAP_SYS_ADMIN)) return -EPERM; - if (xchg(&input_pool.entropy_count, 0) >= POOL_MIN_BITS) { - wake_up_interruptible(&random_write_wait); - kill_fasync(&fasync, SIGIO, POLL_OUT); - } return 0; case RNDRESEEDCRNG: if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (!crng_ready()) return -ENODATA; - crng_reseed(false); + crng_reseed(); return 0; default: return -EINVAL; @@ -1632,22 +1411,26 @@ static int random_fasync(int fd, struct file *filp, int on) } const struct file_operations random_fops = { - .read = random_read, - .write = random_write, + .read_iter = random_read_iter, + .write_iter = random_write_iter, .poll = random_poll, .unlocked_ioctl = random_ioctl, .compat_ioctl = compat_ptr_ioctl, .fasync = random_fasync, .llseek = noop_llseek, + .splice_read = generic_file_splice_read, + .splice_write = iter_file_splice_write, }; const struct file_operations urandom_fops = { - .read = urandom_read, - .write = random_write, + .read_iter = urandom_read_iter, + .write_iter = random_write_iter, .unlocked_ioctl = random_ioctl, .compat_ioctl = compat_ptr_ioctl, .fasync = random_fasync, .llseek = noop_llseek, + .splice_read = generic_file_splice_read, + .splice_write = iter_file_splice_write, }; @@ -1671,7 +1454,7 @@ const struct file_operations urandom_fops = { * * - write_wakeup_threshold - the amount of entropy in the input pool * below which write polls to /dev/random will unblock, requesting - * more entropy, tied to the POOL_MIN_BITS constant. It is writable + * more entropy, tied to the POOL_READY_BITS constant. It is writable * to avoid breaking old userspaces, but writing to it does not * change any behavior of the RNG. * @@ -1686,7 +1469,7 @@ const struct file_operations urandom_fops = { #include <linux/sysctl.h> static int sysctl_random_min_urandom_seed = CRNG_RESEED_INTERVAL / HZ; -static int sysctl_random_write_wakeup_bits = POOL_MIN_BITS; +static int sysctl_random_write_wakeup_bits = POOL_READY_BITS; static int sysctl_poolsize = POOL_BITS; static u8 sysctl_bootid[UUID_SIZE]; @@ -1695,7 +1478,7 @@ static u8 sysctl_bootid[UUID_SIZE]; * UUID. The difference is in whether table->data is NULL; if it is, * then a new UUID is generated and returned to the user. */ -static int proc_do_uuid(struct ctl_table *table, int write, void *buffer, +static int proc_do_uuid(struct ctl_table *table, int write, void *buf, size_t *lenp, loff_t *ppos) { u8 tmp_uuid[UUID_SIZE], *uuid; @@ -1722,14 +1505,14 @@ static int proc_do_uuid(struct ctl_table *table, int write, void *buffer, } snprintf(uuid_string, sizeof(uuid_string), "%pU", uuid); - return proc_dostring(&fake_table, 0, buffer, lenp, ppos); + return proc_dostring(&fake_table, 0, buf, lenp, ppos); } /* The same as proc_dointvec, but writes don't change anything. */ -static int proc_do_rointvec(struct ctl_table *table, int write, void *buffer, +static int proc_do_rointvec(struct ctl_table *table, int write, void *buf, size_t *lenp, loff_t *ppos) { - return write ? 0 : proc_dointvec(table, 0, buffer, lenp, ppos); + return write ? 0 : proc_dointvec(table, 0, buf, lenp, ppos); } static struct ctl_table random_table[] = { @@ -1742,7 +1525,7 @@ static struct ctl_table random_table[] = { }, { .procname = "entropy_avail", - .data = &input_pool.entropy_count, + .data = &input_pool.init_bits, .maxlen = sizeof(int), .mode = 0444, .proc_handler = proc_dointvec, @@ -1776,8 +1559,8 @@ static struct ctl_table random_table[] = { }; /* - * rand_initialize() is called before sysctl_init(), - * so we cannot call register_sysctl_init() in rand_initialize() + * random_init() is called before sysctl_init(), + * so we cannot call register_sysctl_init() in random_init() */ static int __init random_sysctls_init(void) { diff --git a/drivers/char/tpm/tpm2-cmd.c b/drivers/char/tpm/tpm2-cmd.c index 4704fa553098..c1eb5d223839 100644 --- a/drivers/char/tpm/tpm2-cmd.c +++ b/drivers/char/tpm/tpm2-cmd.c @@ -400,7 +400,16 @@ ssize_t tpm2_get_tpm_pt(struct tpm_chip *chip, u32 property_id, u32 *value, if (!rc) { out = (struct tpm2_get_cap_out *) &buf.data[TPM_HEADER_SIZE]; - *value = be32_to_cpu(out->value); + /* + * To prevent failing boot up of some systems, Infineon TPM2.0 + * returns SUCCESS on TPM2_Startup in field upgrade mode. Also + * the TPM2_Getcapability command returns a zero length list + * in field upgrade mode. + */ + if (be32_to_cpu(out->property_cnt) > 0) + *value = be32_to_cpu(out->value); + else + rc = -ENODATA; } tpm_buf_destroy(&buf); return rc; @@ -745,7 +754,11 @@ int tpm2_auto_startup(struct tpm_chip *chip) rc = tpm2_get_cc_attrs_tbl(chip); out: - if (rc == TPM2_RC_UPGRADE) { + /* + * Infineon TPM in field upgrade mode will return no data for the number + * of supported commands. + */ + if (rc == TPM2_RC_UPGRADE || rc == -ENODATA) { dev_info(&chip->dev, "TPM in field upgrade mode, requires firmware upgrade\n"); chip->flags |= TPM_CHIP_FLAG_FIRMWARE_UPGRADE; rc = 0; diff --git a/drivers/char/tpm/tpm_ftpm_tee.c b/drivers/char/tpm/tpm_ftpm_tee.c index 6e3235565a4d..5c233423c56f 100644 --- a/drivers/char/tpm/tpm_ftpm_tee.c +++ b/drivers/char/tpm/tpm_ftpm_tee.c @@ -177,7 +177,7 @@ static u8 ftpm_tee_tpm_op_status(struct tpm_chip *chip) static bool ftpm_tee_tpm_req_canceled(struct tpm_chip *chip, u8 status) { - return 0; + return false; } static const struct tpm_class_ops ftpm_tee_tpm_ops = { diff --git a/drivers/char/tpm/tpm_ibmvtpm.c b/drivers/char/tpm/tpm_ibmvtpm.c index 3af4c07a9342..d3989b257f42 100644 --- a/drivers/char/tpm/tpm_ibmvtpm.c +++ b/drivers/char/tpm/tpm_ibmvtpm.c @@ -681,6 +681,7 @@ static int tpm_ibmvtpm_probe(struct vio_dev *vio_dev, if (!wait_event_timeout(ibmvtpm->crq_queue.wq, ibmvtpm->rtce_buf != NULL, HZ)) { + rc = -ENODEV; dev_err(dev, "CRQ response timed out\n"); goto init_irq_cleanup; } diff --git a/drivers/char/tpm/tpm_tis.c b/drivers/char/tpm/tpm_tis.c index d3f2e5364c27..bcff6429e0b4 100644 --- a/drivers/char/tpm/tpm_tis.c +++ b/drivers/char/tpm/tpm_tis.c @@ -153,50 +153,46 @@ static int check_acpi_tpm2(struct device *dev) #endif static int tpm_tcg_read_bytes(struct tpm_tis_data *data, u32 addr, u16 len, - u8 *result) + u8 *result, enum tpm_tis_io_mode io_mode) { struct tpm_tis_tcg_phy *phy = to_tpm_tis_tcg_phy(data); - - while (len--) - *result++ = ioread8(phy->iobase + addr); + __le16 result_le16; + __le32 result_le32; + + switch (io_mode) { + case TPM_TIS_PHYS_8: + while (len--) + *result++ = ioread8(phy->iobase + addr); + break; + case TPM_TIS_PHYS_16: + result_le16 = cpu_to_le16(ioread16(phy->iobase + addr)); + memcpy(result, &result_le16, sizeof(u16)); + break; + case TPM_TIS_PHYS_32: + result_le32 = cpu_to_le32(ioread32(phy->iobase + addr)); + memcpy(result, &result_le32, sizeof(u32)); + break; + } return 0; } static int tpm_tcg_write_bytes(struct tpm_tis_data *data, u32 addr, u16 len, - const u8 *value) + const u8 *value, enum tpm_tis_io_mode io_mode) { struct tpm_tis_tcg_phy *phy = to_tpm_tis_tcg_phy(data); - while (len--) - iowrite8(*value++, phy->iobase + addr); - - return 0; -} - -static int tpm_tcg_read16(struct tpm_tis_data *data, u32 addr, u16 *result) -{ - struct tpm_tis_tcg_phy *phy = to_tpm_tis_tcg_phy(data); - - *result = ioread16(phy->iobase + addr); - - return 0; -} - -static int tpm_tcg_read32(struct tpm_tis_data *data, u32 addr, u32 *result) -{ - struct tpm_tis_tcg_phy *phy = to_tpm_tis_tcg_phy(data); - - *result = ioread32(phy->iobase + addr); - - return 0; -} - -static int tpm_tcg_write32(struct tpm_tis_data *data, u32 addr, u32 value) -{ - struct tpm_tis_tcg_phy *phy = to_tpm_tis_tcg_phy(data); - - iowrite32(value, phy->iobase + addr); + switch (io_mode) { + case TPM_TIS_PHYS_8: + while (len--) + iowrite8(*value++, phy->iobase + addr); + break; + case TPM_TIS_PHYS_16: + return -EINVAL; + case TPM_TIS_PHYS_32: + iowrite32(le32_to_cpu(*((__le32 *)value)), phy->iobase + addr); + break; + } return 0; } @@ -204,9 +200,6 @@ static int tpm_tcg_write32(struct tpm_tis_data *data, u32 addr, u32 value) static const struct tpm_tis_phy_ops tpm_tcg = { .read_bytes = tpm_tcg_read_bytes, .write_bytes = tpm_tcg_write_bytes, - .read16 = tpm_tcg_read16, - .read32 = tpm_tcg_read32, - .write32 = tpm_tcg_write32, }; static int tpm_tis_init(struct device *dev, struct tpm_info *tpm_info) diff --git a/drivers/char/tpm/tpm_tis_core.h b/drivers/char/tpm/tpm_tis_core.h index 3be24f221e32..6c203f36b8a1 100644 --- a/drivers/char/tpm/tpm_tis_core.h +++ b/drivers/char/tpm/tpm_tis_core.h @@ -104,54 +104,88 @@ struct tpm_tis_data { unsigned int timeout_max; /* usecs */ }; +/* + * IO modes to indicate how many bytes should be read/written at once in the + * tpm_tis_phy_ops read_bytes/write_bytes calls. Use TPM_TIS_PHYS_8 to + * receive/transmit byte-wise, TPM_TIS_PHYS_16 for two bytes etc. + */ +enum tpm_tis_io_mode { + TPM_TIS_PHYS_8, + TPM_TIS_PHYS_16, + TPM_TIS_PHYS_32, +}; + struct tpm_tis_phy_ops { + /* data is passed in little endian */ int (*read_bytes)(struct tpm_tis_data *data, u32 addr, u16 len, - u8 *result); + u8 *result, enum tpm_tis_io_mode mode); int (*write_bytes)(struct tpm_tis_data *data, u32 addr, u16 len, - const u8 *value); - int (*read16)(struct tpm_tis_data *data, u32 addr, u16 *result); - int (*read32)(struct tpm_tis_data *data, u32 addr, u32 *result); - int (*write32)(struct tpm_tis_data *data, u32 addr, u32 src); + const u8 *value, enum tpm_tis_io_mode mode); }; static inline int tpm_tis_read_bytes(struct tpm_tis_data *data, u32 addr, u16 len, u8 *result) { - return data->phy_ops->read_bytes(data, addr, len, result); + return data->phy_ops->read_bytes(data, addr, len, result, + TPM_TIS_PHYS_8); } static inline int tpm_tis_read8(struct tpm_tis_data *data, u32 addr, u8 *result) { - return data->phy_ops->read_bytes(data, addr, 1, result); + return data->phy_ops->read_bytes(data, addr, 1, result, TPM_TIS_PHYS_8); } static inline int tpm_tis_read16(struct tpm_tis_data *data, u32 addr, u16 *result) { - return data->phy_ops->read16(data, addr, result); + __le16 result_le; + int rc; + + rc = data->phy_ops->read_bytes(data, addr, sizeof(u16), + (u8 *)&result_le, TPM_TIS_PHYS_16); + if (!rc) + *result = le16_to_cpu(result_le); + + return rc; } static inline int tpm_tis_read32(struct tpm_tis_data *data, u32 addr, u32 *result) { - return data->phy_ops->read32(data, addr, result); + __le32 result_le; + int rc; + + rc = data->phy_ops->read_bytes(data, addr, sizeof(u32), + (u8 *)&result_le, TPM_TIS_PHYS_32); + if (!rc) + *result = le32_to_cpu(result_le); + + return rc; } static inline int tpm_tis_write_bytes(struct tpm_tis_data *data, u32 addr, u16 len, const u8 *value) { - return data->phy_ops->write_bytes(data, addr, len, value); + return data->phy_ops->write_bytes(data, addr, len, value, + TPM_TIS_PHYS_8); } static inline int tpm_tis_write8(struct tpm_tis_data *data, u32 addr, u8 value) { - return data->phy_ops->write_bytes(data, addr, 1, &value); + return data->phy_ops->write_bytes(data, addr, 1, &value, + TPM_TIS_PHYS_8); } static inline int tpm_tis_write32(struct tpm_tis_data *data, u32 addr, u32 value) { - return data->phy_ops->write32(data, addr, value); + __le32 value_le; + int rc; + + value_le = cpu_to_le32(value); + rc = data->phy_ops->write_bytes(data, addr, sizeof(u32), + (u8 *)&value_le, TPM_TIS_PHYS_32); + return rc; } static inline bool is_bsw(void) diff --git a/drivers/char/tpm/tpm_tis_i2c_cr50.c b/drivers/char/tpm/tpm_tis_i2c_cr50.c index f6c0affbb456..974479a1ec5a 100644 --- a/drivers/char/tpm/tpm_tis_i2c_cr50.c +++ b/drivers/char/tpm/tpm_tis_i2c_cr50.c @@ -31,6 +31,7 @@ #define TPM_CR50_TIMEOUT_SHORT_MS 2 /* Short timeout during transactions */ #define TPM_CR50_TIMEOUT_NOIRQ_MS 20 /* Timeout for TPM ready without IRQ */ #define TPM_CR50_I2C_DID_VID 0x00281ae0L /* Device and vendor ID reg value */ +#define TPM_TI50_I2C_DID_VID 0x504a6666L /* Device and vendor ID reg value */ #define TPM_CR50_I2C_MAX_RETRIES 3 /* Max retries due to I2C errors */ #define TPM_CR50_I2C_RETRY_DELAY_LO 55 /* Min usecs between retries on I2C */ #define TPM_CR50_I2C_RETRY_DELAY_HI 65 /* Max usecs between retries on I2C */ @@ -742,15 +743,15 @@ static int tpm_cr50_i2c_probe(struct i2c_client *client) } vendor = le32_to_cpup((__le32 *)buf); - if (vendor != TPM_CR50_I2C_DID_VID) { + if (vendor != TPM_CR50_I2C_DID_VID && vendor != TPM_TI50_I2C_DID_VID) { dev_err(dev, "Vendor ID did not match! ID was %08x\n", vendor); tpm_cr50_release_locality(chip, true); return -ENODEV; } - dev_info(dev, "cr50 TPM 2.0 (i2c 0x%02x irq %d id 0x%x)\n", + dev_info(dev, "%s TPM 2.0 (i2c 0x%02x irq %d id 0x%x)\n", + vendor == TPM_TI50_I2C_DID_VID ? "ti50" : "cr50", client->addr, client->irq, vendor >> 16); - return tpm_chip_register(chip); } @@ -768,8 +769,8 @@ static int tpm_cr50_i2c_remove(struct i2c_client *client) struct device *dev = &client->dev; if (!chip) { - dev_err(dev, "Could not get client data at remove\n"); - return -ENODEV; + dev_crit(dev, "Could not get client data at remove, memory corruption ahead\n"); + return 0; } tpm_chip_unregister(chip); diff --git a/drivers/char/tpm/tpm_tis_spi.h b/drivers/char/tpm/tpm_tis_spi.h index bba73979c368..d0f66f6f1931 100644 --- a/drivers/char/tpm/tpm_tis_spi.h +++ b/drivers/char/tpm/tpm_tis_spi.h @@ -31,10 +31,6 @@ extern int tpm_tis_spi_init(struct spi_device *spi, struct tpm_tis_spi_phy *phy, extern int tpm_tis_spi_transfer(struct tpm_tis_data *data, u32 addr, u16 len, u8 *in, const u8 *out); -extern int tpm_tis_spi_read16(struct tpm_tis_data *data, u32 addr, u16 *result); -extern int tpm_tis_spi_read32(struct tpm_tis_data *data, u32 addr, u32 *result); -extern int tpm_tis_spi_write32(struct tpm_tis_data *data, u32 addr, u32 value); - #ifdef CONFIG_TCG_TIS_SPI_CR50 extern int cr50_spi_probe(struct spi_device *spi); #else diff --git a/drivers/char/tpm/tpm_tis_spi_cr50.c b/drivers/char/tpm/tpm_tis_spi_cr50.c index 7bf123d3c537..f4937280e940 100644 --- a/drivers/char/tpm/tpm_tis_spi_cr50.c +++ b/drivers/char/tpm/tpm_tis_spi_cr50.c @@ -222,13 +222,13 @@ static int tpm_tis_spi_cr50_transfer(struct tpm_tis_data *data, u32 addr, u16 le } static int tpm_tis_spi_cr50_read_bytes(struct tpm_tis_data *data, u32 addr, - u16 len, u8 *result) + u16 len, u8 *result, enum tpm_tis_io_mode io_mode) { return tpm_tis_spi_cr50_transfer(data, addr, len, result, NULL); } static int tpm_tis_spi_cr50_write_bytes(struct tpm_tis_data *data, u32 addr, - u16 len, const u8 *value) + u16 len, const u8 *value, enum tpm_tis_io_mode io_mode) { return tpm_tis_spi_cr50_transfer(data, addr, len, NULL, value); } @@ -236,9 +236,6 @@ static int tpm_tis_spi_cr50_write_bytes(struct tpm_tis_data *data, u32 addr, static const struct tpm_tis_phy_ops tpm_spi_cr50_phy_ops = { .read_bytes = tpm_tis_spi_cr50_read_bytes, .write_bytes = tpm_tis_spi_cr50_write_bytes, - .read16 = tpm_tis_spi_read16, - .read32 = tpm_tis_spi_read32, - .write32 = tpm_tis_spi_write32, }; static void cr50_print_fw_version(struct tpm_tis_data *data) diff --git a/drivers/char/tpm/tpm_tis_spi_main.c b/drivers/char/tpm/tpm_tis_spi_main.c index 184396b3af50..a0963a3e92bd 100644 --- a/drivers/char/tpm/tpm_tis_spi_main.c +++ b/drivers/char/tpm/tpm_tis_spi_main.c @@ -141,55 +141,17 @@ exit: } static int tpm_tis_spi_read_bytes(struct tpm_tis_data *data, u32 addr, - u16 len, u8 *result) + u16 len, u8 *result, enum tpm_tis_io_mode io_mode) { return tpm_tis_spi_transfer(data, addr, len, result, NULL); } static int tpm_tis_spi_write_bytes(struct tpm_tis_data *data, u32 addr, - u16 len, const u8 *value) + u16 len, const u8 *value, enum tpm_tis_io_mode io_mode) { return tpm_tis_spi_transfer(data, addr, len, NULL, value); } -int tpm_tis_spi_read16(struct tpm_tis_data *data, u32 addr, u16 *result) -{ - __le16 result_le; - int rc; - - rc = data->phy_ops->read_bytes(data, addr, sizeof(u16), - (u8 *)&result_le); - if (!rc) - *result = le16_to_cpu(result_le); - - return rc; -} - -int tpm_tis_spi_read32(struct tpm_tis_data *data, u32 addr, u32 *result) -{ - __le32 result_le; - int rc; - - rc = data->phy_ops->read_bytes(data, addr, sizeof(u32), - (u8 *)&result_le); - if (!rc) - *result = le32_to_cpu(result_le); - - return rc; -} - -int tpm_tis_spi_write32(struct tpm_tis_data *data, u32 addr, u32 value) -{ - __le32 value_le; - int rc; - - value_le = cpu_to_le32(value); - rc = data->phy_ops->write_bytes(data, addr, sizeof(u32), - (u8 *)&value_le); - - return rc; -} - int tpm_tis_spi_init(struct spi_device *spi, struct tpm_tis_spi_phy *phy, int irq, const struct tpm_tis_phy_ops *phy_ops) { @@ -205,9 +167,6 @@ int tpm_tis_spi_init(struct spi_device *spi, struct tpm_tis_spi_phy *phy, static const struct tpm_tis_phy_ops tpm_spi_phy_ops = { .read_bytes = tpm_tis_spi_read_bytes, .write_bytes = tpm_tis_spi_write_bytes, - .read16 = tpm_tis_spi_read16, - .read32 = tpm_tis_spi_read32, - .write32 = tpm_tis_spi_write32, }; static int tpm_tis_spi_probe(struct spi_device *dev) diff --git a/drivers/char/tpm/tpm_tis_synquacer.c b/drivers/char/tpm/tpm_tis_synquacer.c index e47bdd272704..679196c61401 100644 --- a/drivers/char/tpm/tpm_tis_synquacer.c +++ b/drivers/char/tpm/tpm_tis_synquacer.c @@ -35,72 +35,53 @@ static inline struct tpm_tis_synquacer_phy *to_tpm_tis_tcg_phy(struct tpm_tis_da } static int tpm_tis_synquacer_read_bytes(struct tpm_tis_data *data, u32 addr, - u16 len, u8 *result) + u16 len, u8 *result, + enum tpm_tis_io_mode io_mode) { struct tpm_tis_synquacer_phy *phy = to_tpm_tis_tcg_phy(data); - - while (len--) - *result++ = ioread8(phy->iobase + addr); + switch (io_mode) { + case TPM_TIS_PHYS_8: + while (len--) + *result++ = ioread8(phy->iobase + addr); + break; + case TPM_TIS_PHYS_16: + result[1] = ioread8(phy->iobase + addr + 1); + result[0] = ioread8(phy->iobase + addr); + break; + case TPM_TIS_PHYS_32: + result[3] = ioread8(phy->iobase + addr + 3); + result[2] = ioread8(phy->iobase + addr + 2); + result[1] = ioread8(phy->iobase + addr + 1); + result[0] = ioread8(phy->iobase + addr); + break; + } return 0; } static int tpm_tis_synquacer_write_bytes(struct tpm_tis_data *data, u32 addr, - u16 len, const u8 *value) + u16 len, const u8 *value, + enum tpm_tis_io_mode io_mode) { struct tpm_tis_synquacer_phy *phy = to_tpm_tis_tcg_phy(data); - - while (len--) - iowrite8(*value++, phy->iobase + addr); - - return 0; -} - -static int tpm_tis_synquacer_read16_bw(struct tpm_tis_data *data, - u32 addr, u16 *result) -{ - struct tpm_tis_synquacer_phy *phy = to_tpm_tis_tcg_phy(data); - - /* - * Due to the limitation of SPI controller on SynQuacer, - * 16/32 bits access must be done in byte-wise and descending order. - */ - *result = (ioread8(phy->iobase + addr + 1) << 8) | - (ioread8(phy->iobase + addr)); - - return 0; -} - -static int tpm_tis_synquacer_read32_bw(struct tpm_tis_data *data, - u32 addr, u32 *result) -{ - struct tpm_tis_synquacer_phy *phy = to_tpm_tis_tcg_phy(data); - - /* - * Due to the limitation of SPI controller on SynQuacer, - * 16/32 bits access must be done in byte-wise and descending order. - */ - *result = (ioread8(phy->iobase + addr + 3) << 24) | - (ioread8(phy->iobase + addr + 2) << 16) | - (ioread8(phy->iobase + addr + 1) << 8) | - (ioread8(phy->iobase + addr)); - - return 0; -} - -static int tpm_tis_synquacer_write32_bw(struct tpm_tis_data *data, - u32 addr, u32 value) -{ - struct tpm_tis_synquacer_phy *phy = to_tpm_tis_tcg_phy(data); - - /* - * Due to the limitation of SPI controller on SynQuacer, - * 16/32 bits access must be done in byte-wise and descending order. - */ - iowrite8(value >> 24, phy->iobase + addr + 3); - iowrite8(value >> 16, phy->iobase + addr + 2); - iowrite8(value >> 8, phy->iobase + addr + 1); - iowrite8(value, phy->iobase + addr); + switch (io_mode) { + case TPM_TIS_PHYS_8: + while (len--) + iowrite8(*value++, phy->iobase + addr); + break; + case TPM_TIS_PHYS_16: + return -EINVAL; + case TPM_TIS_PHYS_32: + /* + * Due to the limitation of SPI controller on SynQuacer, + * 16/32 bits access must be done in byte-wise and descending order. + */ + iowrite8(value[3], phy->iobase + addr + 3); + iowrite8(value[2], phy->iobase + addr + 2); + iowrite8(value[1], phy->iobase + addr + 1); + iowrite8(value[0], phy->iobase + addr); + break; + } return 0; } @@ -108,9 +89,6 @@ static int tpm_tis_synquacer_write32_bw(struct tpm_tis_data *data, static const struct tpm_tis_phy_ops tpm_tcg_bw = { .read_bytes = tpm_tis_synquacer_read_bytes, .write_bytes = tpm_tis_synquacer_write_bytes, - .read16 = tpm_tis_synquacer_read16_bw, - .read32 = tpm_tis_synquacer_read32_bw, - .write32 = tpm_tis_synquacer_write32_bw, }; static int tpm_tis_synquacer_init(struct device *dev, diff --git a/drivers/char/tpm/xen-tpmfront.c b/drivers/char/tpm/xen-tpmfront.c index 69df04ae2401..379291826261 100644 --- a/drivers/char/tpm/xen-tpmfront.c +++ b/drivers/char/tpm/xen-tpmfront.c @@ -253,20 +253,12 @@ static int setup_ring(struct xenbus_device *dev, struct tpm_private *priv) struct xenbus_transaction xbt; const char *message = NULL; int rv; - grant_ref_t gref; - priv->shr = (void *)__get_free_page(GFP_KERNEL|__GFP_ZERO); - if (!priv->shr) { - xenbus_dev_fatal(dev, -ENOMEM, "allocating shared ring"); - return -ENOMEM; - } - - rv = xenbus_grant_ring(dev, priv->shr, 1, &gref); + rv = xenbus_setup_ring(dev, GFP_KERNEL, (void **)&priv->shr, 1, + &priv->ring_ref); if (rv < 0) return rv; - priv->ring_ref = gref; - rv = xenbus_alloc_evtchn(dev, &priv->evtchn); if (rv) return rv; @@ -331,11 +323,7 @@ static void ring_free(struct tpm_private *priv) if (!priv) return; - if (priv->ring_ref) - gnttab_end_foreign_access(priv->ring_ref, - (unsigned long)priv->shr); - else - free_page((unsigned long)priv->shr); + xenbus_teardown_ring((void **)&priv->shr, 1, &priv->ring_ref); if (priv->irq) unbind_from_irqhandler(priv->irq, priv); diff --git a/drivers/clk/at91/clk-generated.c b/drivers/clk/at91/clk-generated.c index 23cc8297ec4c..d429ba52a719 100644 --- a/drivers/clk/at91/clk-generated.c +++ b/drivers/clk/at91/clk-generated.c @@ -117,6 +117,10 @@ static void clk_generated_best_diff(struct clk_rate_request *req, tmp_rate = parent_rate; else tmp_rate = parent_rate / div; + + if (tmp_rate < req->min_rate || tmp_rate > req->max_rate) + return; + tmp_diff = abs(req->rate - tmp_rate); if (*best_diff < 0 || *best_diff >= tmp_diff) { diff --git a/drivers/clk/bcm/clk-bcm2835.c b/drivers/clk/bcm/clk-bcm2835.c index 3ad20e75fd23..48a1eb9f2d55 100644 --- a/drivers/clk/bcm/clk-bcm2835.c +++ b/drivers/clk/bcm/clk-bcm2835.c @@ -941,6 +941,7 @@ static u32 bcm2835_clock_choose_div(struct clk_hw *hw, u64 temp = (u64)parent_rate << CM_DIV_FRAC_BITS; u32 div, mindiv, maxdiv; + do_div(temp, rate); div = temp; div &= ~unused_frac_mask; diff --git a/drivers/clk/microchip/clk-mpfs.c b/drivers/clk/microchip/clk-mpfs.c index aa1561b773d6..070c3b896559 100644 --- a/drivers/clk/microchip/clk-mpfs.c +++ b/drivers/clk/microchip/clk-mpfs.c @@ -11,20 +11,48 @@ #include <dt-bindings/clock/microchip,mpfs-clock.h> /* address offset of control registers */ +#define REG_MSSPLL_REF_CR 0x08u +#define REG_MSSPLL_POSTDIV_CR 0x10u +#define REG_MSSPLL_SSCG_2_CR 0x2Cu #define REG_CLOCK_CONFIG_CR 0x08u +#define REG_RTC_CLOCK_CR 0x0Cu #define REG_SUBBLK_CLOCK_CR 0x84u #define REG_SUBBLK_RESET_CR 0x88u +#define MSSPLL_FBDIV_SHIFT 0x00u +#define MSSPLL_FBDIV_WIDTH 0x0Cu +#define MSSPLL_REFDIV_SHIFT 0x08u +#define MSSPLL_REFDIV_WIDTH 0x06u +#define MSSPLL_POSTDIV_SHIFT 0x08u +#define MSSPLL_POSTDIV_WIDTH 0x07u +#define MSSPLL_FIXED_DIV 4u + struct mpfs_clock_data { void __iomem *base; + void __iomem *msspll_base; struct clk_hw_onecell_data hw_data; }; +struct mpfs_msspll_hw_clock { + void __iomem *base; + unsigned int id; + u32 reg_offset; + u32 shift; + u32 width; + u32 flags; + struct clk_hw hw; + struct clk_init_data init; +}; + +#define to_mpfs_msspll_clk(_hw) container_of(_hw, struct mpfs_msspll_hw_clock, hw) + struct mpfs_cfg_clock { const struct clk_div_table *table; unsigned int id; + u32 reg_offset; u8 shift; u8 width; + u8 flags; }; struct mpfs_cfg_hw_clock { @@ -55,7 +83,7 @@ struct mpfs_periph_hw_clock { */ static DEFINE_SPINLOCK(mpfs_clk_lock); -static const struct clk_parent_data mpfs_cfg_parent[] = { +static const struct clk_parent_data mpfs_ext_ref[] = { { .index = 0 }, }; @@ -69,6 +97,86 @@ static const struct clk_div_table mpfs_div_ahb_table[] = { { 0, 0 } }; +/* + * The only two supported reference clock frequencies for the PolarFire SoC are + * 100 and 125 MHz, as the rtc reference is required to be 1 MHz. + * It therefore only needs to have divider table entries corresponding to + * divide by 100 and 125. + */ +static const struct clk_div_table mpfs_div_rtcref_table[] = { + { 100, 100 }, { 125, 125 }, + { 0, 0 } +}; + +static unsigned long mpfs_clk_msspll_recalc_rate(struct clk_hw *hw, unsigned long prate) +{ + struct mpfs_msspll_hw_clock *msspll_hw = to_mpfs_msspll_clk(hw); + void __iomem *mult_addr = msspll_hw->base + msspll_hw->reg_offset; + void __iomem *ref_div_addr = msspll_hw->base + REG_MSSPLL_REF_CR; + void __iomem *postdiv_addr = msspll_hw->base + REG_MSSPLL_POSTDIV_CR; + u32 mult, ref_div, postdiv; + + mult = readl_relaxed(mult_addr) >> MSSPLL_FBDIV_SHIFT; + mult &= clk_div_mask(MSSPLL_FBDIV_WIDTH); + ref_div = readl_relaxed(ref_div_addr) >> MSSPLL_REFDIV_SHIFT; + ref_div &= clk_div_mask(MSSPLL_REFDIV_WIDTH); + postdiv = readl_relaxed(postdiv_addr) >> MSSPLL_POSTDIV_SHIFT; + postdiv &= clk_div_mask(MSSPLL_POSTDIV_WIDTH); + + return prate * mult / (ref_div * MSSPLL_FIXED_DIV * postdiv); +} + +static const struct clk_ops mpfs_clk_msspll_ops = { + .recalc_rate = mpfs_clk_msspll_recalc_rate, +}; + +#define CLK_PLL(_id, _name, _parent, _shift, _width, _flags, _offset) { \ + .id = _id, \ + .shift = _shift, \ + .width = _width, \ + .reg_offset = _offset, \ + .flags = _flags, \ + .hw.init = CLK_HW_INIT_PARENTS_DATA(_name, _parent, &mpfs_clk_msspll_ops, 0), \ +} + +static struct mpfs_msspll_hw_clock mpfs_msspll_clks[] = { + CLK_PLL(CLK_MSSPLL, "clk_msspll", mpfs_ext_ref, MSSPLL_FBDIV_SHIFT, + MSSPLL_FBDIV_WIDTH, 0, REG_MSSPLL_SSCG_2_CR), +}; + +static int mpfs_clk_register_msspll(struct device *dev, struct mpfs_msspll_hw_clock *msspll_hw, + void __iomem *base) +{ + msspll_hw->base = base; + + return devm_clk_hw_register(dev, &msspll_hw->hw); +} + +static int mpfs_clk_register_mssplls(struct device *dev, struct mpfs_msspll_hw_clock *msspll_hws, + unsigned int num_clks, struct mpfs_clock_data *data) +{ + void __iomem *base = data->msspll_base; + unsigned int i; + int ret; + + for (i = 0; i < num_clks; i++) { + struct mpfs_msspll_hw_clock *msspll_hw = &msspll_hws[i]; + + ret = mpfs_clk_register_msspll(dev, msspll_hw, base); + if (ret) + return dev_err_probe(dev, ret, "failed to register msspll id: %d\n", + CLK_MSSPLL); + + data->hw_data.hws[msspll_hw->id] = &msspll_hw->hw; + } + + return 0; +} + +/* + * "CFG" clocks + */ + static unsigned long mpfs_cfg_clk_recalc_rate(struct clk_hw *hw, unsigned long prate) { struct mpfs_cfg_hw_clock *cfg_hw = to_mpfs_cfg_clk(hw); @@ -76,10 +184,10 @@ static unsigned long mpfs_cfg_clk_recalc_rate(struct clk_hw *hw, unsigned long p void __iomem *base_addr = cfg_hw->sys_base; u32 val; - val = readl_relaxed(base_addr + REG_CLOCK_CONFIG_CR) >> cfg->shift; + val = readl_relaxed(base_addr + cfg->reg_offset) >> cfg->shift; val &= clk_div_mask(cfg->width); - return prate / (1u << val); + return divider_recalc_rate(hw, prate, val, cfg->table, cfg->flags, cfg->width); } static long mpfs_cfg_clk_round_rate(struct clk_hw *hw, unsigned long rate, unsigned long *prate) @@ -105,11 +213,10 @@ static int mpfs_cfg_clk_set_rate(struct clk_hw *hw, unsigned long rate, unsigned return divider_setting; spin_lock_irqsave(&mpfs_clk_lock, flags); - - val = readl_relaxed(base_addr + REG_CLOCK_CONFIG_CR); + val = readl_relaxed(base_addr + cfg->reg_offset); val &= ~(clk_div_mask(cfg->width) << cfg_hw->cfg.shift); val |= divider_setting << cfg->shift; - writel_relaxed(val, base_addr + REG_CLOCK_CONFIG_CR); + writel_relaxed(val, base_addr + cfg->reg_offset); spin_unlock_irqrestore(&mpfs_clk_lock, flags); @@ -122,19 +229,33 @@ static const struct clk_ops mpfs_clk_cfg_ops = { .set_rate = mpfs_cfg_clk_set_rate, }; -#define CLK_CFG(_id, _name, _parent, _shift, _width, _table, _flags) { \ - .cfg.id = _id, \ - .cfg.shift = _shift, \ - .cfg.width = _width, \ - .cfg.table = _table, \ - .hw.init = CLK_HW_INIT_PARENTS_DATA(_name, _parent, &mpfs_clk_cfg_ops, \ - _flags), \ +#define CLK_CFG(_id, _name, _parent, _shift, _width, _table, _flags, _offset) { \ + .cfg.id = _id, \ + .cfg.shift = _shift, \ + .cfg.width = _width, \ + .cfg.table = _table, \ + .cfg.reg_offset = _offset, \ + .cfg.flags = _flags, \ + .hw.init = CLK_HW_INIT(_name, _parent, &mpfs_clk_cfg_ops, 0), \ } static struct mpfs_cfg_hw_clock mpfs_cfg_clks[] = { - CLK_CFG(CLK_CPU, "clk_cpu", mpfs_cfg_parent, 0, 2, mpfs_div_cpu_axi_table, 0), - CLK_CFG(CLK_AXI, "clk_axi", mpfs_cfg_parent, 2, 2, mpfs_div_cpu_axi_table, 0), - CLK_CFG(CLK_AHB, "clk_ahb", mpfs_cfg_parent, 4, 2, mpfs_div_ahb_table, 0), + CLK_CFG(CLK_CPU, "clk_cpu", "clk_msspll", 0, 2, mpfs_div_cpu_axi_table, 0, + REG_CLOCK_CONFIG_CR), + CLK_CFG(CLK_AXI, "clk_axi", "clk_msspll", 2, 2, mpfs_div_cpu_axi_table, 0, + REG_CLOCK_CONFIG_CR), + CLK_CFG(CLK_AHB, "clk_ahb", "clk_msspll", 4, 2, mpfs_div_ahb_table, 0, + REG_CLOCK_CONFIG_CR), + { + .cfg.id = CLK_RTCREF, + .cfg.shift = 0, + .cfg.width = 12, + .cfg.table = mpfs_div_rtcref_table, + .cfg.reg_offset = REG_RTC_CLOCK_CR, + .cfg.flags = CLK_DIVIDER_ONE_BASED, + .hw.init = + CLK_HW_INIT_PARENTS_DATA("clk_rtcref", mpfs_ext_ref, &mpfs_clk_cfg_ops, 0), + } }; static int mpfs_clk_register_cfg(struct device *dev, struct mpfs_cfg_hw_clock *cfg_hw, @@ -160,13 +281,17 @@ static int mpfs_clk_register_cfgs(struct device *dev, struct mpfs_cfg_hw_clock * return dev_err_probe(dev, ret, "failed to register clock id: %d\n", cfg_hw->cfg.id); - id = cfg_hws[i].cfg.id; + id = cfg_hw->cfg.id; data->hw_data.hws[id] = &cfg_hw->hw; } return 0; } +/* + * peripheral clocks - devices connected to axi or ahb buses. + */ + static int mpfs_periph_clk_enable(struct clk_hw *hw) { struct mpfs_periph_hw_clock *periph_hw = to_mpfs_periph_clk(hw); @@ -200,10 +325,6 @@ static void mpfs_periph_clk_disable(struct clk_hw *hw) spin_lock_irqsave(&mpfs_clk_lock, flags); - reg = readl_relaxed(base_addr + REG_SUBBLK_RESET_CR); - val = reg | (1u << periph->shift); - writel_relaxed(val, base_addr + REG_SUBBLK_RESET_CR); - reg = readl_relaxed(base_addr + REG_SUBBLK_CLOCK_CR); val = reg & ~(1u << periph->shift); writel_relaxed(val, base_addr + REG_SUBBLK_CLOCK_CR); @@ -249,8 +370,10 @@ static const struct clk_ops mpfs_periph_clk_ops = { * trap handler * - CLK_MMUART0: reserved by the hss * - CLK_DDRC: provides clock to the ddr subsystem - * - CLK_FICx: these provide clocks for sections of the fpga fabric, disabling them would - * cause the fabric to go into reset + * - CLK_FICx: these provide the processor side clocks to the "FIC" (Fabric InterConnect) + * clock domain crossers which provide the interface to the FPGA fabric. Disabling them + * causes the FPGA fabric to go into reset. + * - CLK_ATHENA: The athena clock is FIC4, which is reserved for the Athena TeraFire. */ static struct mpfs_periph_hw_clock mpfs_periph_clks[] = { @@ -258,7 +381,7 @@ static struct mpfs_periph_hw_clock mpfs_periph_clks[] = { CLK_PERIPH(CLK_MAC0, "clk_periph_mac0", PARENT_CLK(AHB), 1, 0), CLK_PERIPH(CLK_MAC1, "clk_periph_mac1", PARENT_CLK(AHB), 2, 0), CLK_PERIPH(CLK_MMC, "clk_periph_mmc", PARENT_CLK(AHB), 3, 0), - CLK_PERIPH(CLK_TIMER, "clk_periph_timer", PARENT_CLK(AHB), 4, 0), + CLK_PERIPH(CLK_TIMER, "clk_periph_timer", PARENT_CLK(RTCREF), 4, 0), CLK_PERIPH(CLK_MMUART0, "clk_periph_mmuart0", PARENT_CLK(AHB), 5, CLK_IS_CRITICAL), CLK_PERIPH(CLK_MMUART1, "clk_periph_mmuart1", PARENT_CLK(AHB), 6, 0), CLK_PERIPH(CLK_MMUART2, "clk_periph_mmuart2", PARENT_CLK(AHB), 7, 0), @@ -277,11 +400,11 @@ static struct mpfs_periph_hw_clock mpfs_periph_clks[] = { CLK_PERIPH(CLK_GPIO1, "clk_periph_gpio1", PARENT_CLK(AHB), 21, 0), CLK_PERIPH(CLK_GPIO2, "clk_periph_gpio2", PARENT_CLK(AHB), 22, 0), CLK_PERIPH(CLK_DDRC, "clk_periph_ddrc", PARENT_CLK(AHB), 23, CLK_IS_CRITICAL), - CLK_PERIPH(CLK_FIC0, "clk_periph_fic0", PARENT_CLK(AHB), 24, CLK_IS_CRITICAL), - CLK_PERIPH(CLK_FIC1, "clk_periph_fic1", PARENT_CLK(AHB), 25, CLK_IS_CRITICAL), - CLK_PERIPH(CLK_FIC2, "clk_periph_fic2", PARENT_CLK(AHB), 26, CLK_IS_CRITICAL), - CLK_PERIPH(CLK_FIC3, "clk_periph_fic3", PARENT_CLK(AHB), 27, CLK_IS_CRITICAL), - CLK_PERIPH(CLK_ATHENA, "clk_periph_athena", PARENT_CLK(AHB), 28, 0), + CLK_PERIPH(CLK_FIC0, "clk_periph_fic0", PARENT_CLK(AXI), 24, CLK_IS_CRITICAL), + CLK_PERIPH(CLK_FIC1, "clk_periph_fic1", PARENT_CLK(AXI), 25, CLK_IS_CRITICAL), + CLK_PERIPH(CLK_FIC2, "clk_periph_fic2", PARENT_CLK(AXI), 26, CLK_IS_CRITICAL), + CLK_PERIPH(CLK_FIC3, "clk_periph_fic3", PARENT_CLK(AXI), 27, CLK_IS_CRITICAL), + CLK_PERIPH(CLK_ATHENA, "clk_periph_athena", PARENT_CLK(AXI), 28, CLK_IS_CRITICAL), CLK_PERIPH(CLK_CFM, "clk_periph_cfm", PARENT_CLK(AHB), 29, 0), }; @@ -322,8 +445,9 @@ static int mpfs_clk_probe(struct platform_device *pdev) unsigned int num_clks; int ret; - /* CLK_RESERVED is not part of cfg_clks nor periph_clks, so add 1 */ - num_clks = ARRAY_SIZE(mpfs_cfg_clks) + ARRAY_SIZE(mpfs_periph_clks) + 1; + /* CLK_RESERVED is not part of clock arrays, so add 1 */ + num_clks = ARRAY_SIZE(mpfs_msspll_clks) + ARRAY_SIZE(mpfs_cfg_clks) + + ARRAY_SIZE(mpfs_periph_clks) + 1; clk_data = devm_kzalloc(dev, struct_size(clk_data, hw_data.hws, num_clks), GFP_KERNEL); if (!clk_data) @@ -333,8 +457,17 @@ static int mpfs_clk_probe(struct platform_device *pdev) if (IS_ERR(clk_data->base)) return PTR_ERR(clk_data->base); + clk_data->msspll_base = devm_platform_ioremap_resource(pdev, 1); + if (IS_ERR(clk_data->msspll_base)) + return PTR_ERR(clk_data->msspll_base); + clk_data->hw_data.num = num_clks; + ret = mpfs_clk_register_mssplls(dev, mpfs_msspll_clks, ARRAY_SIZE(mpfs_msspll_clks), + clk_data); + if (ret) + return ret; + ret = mpfs_clk_register_cfgs(dev, mpfs_cfg_clks, ARRAY_SIZE(mpfs_cfg_clks), clk_data); if (ret) return ret; diff --git a/drivers/clk/qcom/clk-rcg2.c b/drivers/clk/qcom/clk-rcg2.c index f675fd969c4d..e9c357309fd9 100644 --- a/drivers/clk/qcom/clk-rcg2.c +++ b/drivers/clk/qcom/clk-rcg2.c @@ -818,7 +818,7 @@ EXPORT_SYMBOL_GPL(clk_pixel_ops); static int clk_gfx3d_determine_rate(struct clk_hw *hw, struct clk_rate_request *req) { - struct clk_rate_request parent_req = { }; + struct clk_rate_request parent_req = { .min_rate = 0, .max_rate = ULONG_MAX }; struct clk_rcg2_gfx3d *cgfx = to_clk_rcg2_gfx3d(hw); struct clk_hw *xo, *p0, *p1, *p2; unsigned long p0_rate; diff --git a/drivers/clk/sunxi-ng/ccu-sun6i-rtc.c b/drivers/clk/sunxi-ng/ccu-sun6i-rtc.c index 8a10bade7e0d..d65398497d5f 100644 --- a/drivers/clk/sunxi-ng/ccu-sun6i-rtc.c +++ b/drivers/clk/sunxi-ng/ccu-sun6i-rtc.c @@ -241,6 +241,7 @@ static struct clk_init_data rtc_32k_init_data = { .ops = &ccu_mux_ops, .parent_hws = rtc_32k_parents, .num_parents = ARRAY_SIZE(rtc_32k_parents), /* updated during probe */ + .flags = CLK_IS_CRITICAL, }; static struct ccu_mux rtc_32k_clk = { @@ -297,10 +298,6 @@ static const struct sunxi_ccu_desc sun6i_rtc_ccu_desc = { .hw_clks = &sun6i_rtc_ccu_hw_clks, }; -static const struct clk_parent_data sun50i_h6_osc32k_fanout_parents[] = { - { .hw = &osc32k_clk.common.hw }, -}; - static const struct clk_parent_data sun50i_h616_osc32k_fanout_parents[] = { { .hw = &osc32k_clk.common.hw }, { .fw_name = "pll-32k" }, @@ -313,13 +310,6 @@ static const struct clk_parent_data sun50i_r329_osc32k_fanout_parents[] = { { .hw = &osc24M_32k_clk.common.hw } }; -static const struct sun6i_rtc_match_data sun50i_h6_rtc_ccu_data = { - .have_ext_osc32k = true, - .have_iosc_calibration = true, - .osc32k_fanout_parents = sun50i_h6_osc32k_fanout_parents, - .osc32k_fanout_nparents = ARRAY_SIZE(sun50i_h6_osc32k_fanout_parents), -}; - static const struct sun6i_rtc_match_data sun50i_h616_rtc_ccu_data = { .have_iosc_calibration = true, .rtc_32k_single_parent = true, @@ -335,10 +325,6 @@ static const struct sun6i_rtc_match_data sun50i_r329_rtc_ccu_data = { static const struct of_device_id sun6i_rtc_ccu_match[] = { { - .compatible = "allwinner,sun50i-h6-rtc", - .data = &sun50i_h6_rtc_ccu_data, - }, - { .compatible = "allwinner,sun50i-h616-rtc", .data = &sun50i_h616_rtc_ccu_data, }, @@ -346,6 +332,7 @@ static const struct of_device_id sun6i_rtc_ccu_match[] = { .compatible = "allwinner,sun50i-r329-rtc", .data = &sun50i_r329_rtc_ccu_data, }, + {}, }; int sun6i_rtc_ccu_probe(struct device *dev, void __iomem *reg) diff --git a/drivers/clk/sunxi/clk-sun9i-mmc.c b/drivers/clk/sunxi/clk-sun9i-mmc.c index 542b31d6e96d..636bcf2439ef 100644 --- a/drivers/clk/sunxi/clk-sun9i-mmc.c +++ b/drivers/clk/sunxi/clk-sun9i-mmc.c @@ -109,6 +109,8 @@ static int sun9i_a80_mmc_config_clk_probe(struct platform_device *pdev) spin_lock_init(&data->lock); r = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (!r) + return -EINVAL; /* one clock/reset pair per word */ count = DIV_ROUND_UP((resource_size(r)), SUN9I_MMC_WIDTH); data->membase = devm_ioremap_resource(&pdev->dev, r); diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig index 1589ae7d5abb..06866bfa1826 100644 --- a/drivers/clocksource/Kconfig +++ b/drivers/clocksource/Kconfig @@ -711,4 +711,11 @@ config MICROCHIP_PIT64B modes and high resolution. It is used as a clocksource and a clockevent. +config GOLDFISH_TIMER + bool "Clocksource using goldfish-rtc" + depends on M68K || COMPILE_TEST + depends on RTC_DRV_GOLDFISH + help + Support for the timer/counter of goldfish-rtc + endmenu diff --git a/drivers/clocksource/Makefile b/drivers/clocksource/Makefile index 9c85ee2bb373..b839beb6ea53 100644 --- a/drivers/clocksource/Makefile +++ b/drivers/clocksource/Makefile @@ -88,3 +88,4 @@ obj-$(CONFIG_GX6605S_TIMER) += timer-gx6605s.o obj-$(CONFIG_HYPERV_TIMER) += hyperv_timer.o obj-$(CONFIG_MICROCHIP_PIT64B) += timer-microchip-pit64b.o obj-$(CONFIG_MSC313E_TIMER) += timer-msc313e.o +obj-$(CONFIG_GOLDFISH_TIMER) += timer-goldfish.o diff --git a/drivers/clocksource/timer-goldfish.c b/drivers/clocksource/timer-goldfish.c new file mode 100644 index 000000000000..0512d5eabc82 --- /dev/null +++ b/drivers/clocksource/timer-goldfish.c @@ -0,0 +1,153 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/interrupt.h> +#include <linux/ioport.h> +#include <linux/clocksource.h> +#include <linux/clockchips.h> +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/goldfish.h> +#include <clocksource/timer-goldfish.h> + +struct goldfish_timer { + struct clocksource cs; + struct clock_event_device ced; + struct resource res; + void __iomem *base; +}; + +static struct goldfish_timer *ced_to_gf(struct clock_event_device *ced) +{ + return container_of(ced, struct goldfish_timer, ced); +} + +static struct goldfish_timer *cs_to_gf(struct clocksource *cs) +{ + return container_of(cs, struct goldfish_timer, cs); +} + +static u64 goldfish_timer_read(struct clocksource *cs) +{ + struct goldfish_timer *timerdrv = cs_to_gf(cs); + void __iomem *base = timerdrv->base; + u32 time_low, time_high; + u64 ticks; + + /* + * time_low: get low bits of current time and update time_high + * time_high: get high bits of time at last time_low read + */ + time_low = gf_ioread32(base + TIMER_TIME_LOW); + time_high = gf_ioread32(base + TIMER_TIME_HIGH); + + ticks = ((u64)time_high << 32) | time_low; + + return ticks; +} + +static int goldfish_timer_set_oneshot(struct clock_event_device *evt) +{ + struct goldfish_timer *timerdrv = ced_to_gf(evt); + void __iomem *base = timerdrv->base; + + gf_iowrite32(0, base + TIMER_ALARM_HIGH); + gf_iowrite32(0, base + TIMER_ALARM_LOW); + gf_iowrite32(1, base + TIMER_IRQ_ENABLED); + + return 0; +} + +static int goldfish_timer_shutdown(struct clock_event_device *evt) +{ + struct goldfish_timer *timerdrv = ced_to_gf(evt); + void __iomem *base = timerdrv->base; + + gf_iowrite32(0, base + TIMER_IRQ_ENABLED); + + return 0; +} + +static int goldfish_timer_next_event(unsigned long delta, + struct clock_event_device *evt) +{ + struct goldfish_timer *timerdrv = ced_to_gf(evt); + void __iomem *base = timerdrv->base; + u64 now; + + now = goldfish_timer_read(&timerdrv->cs); + + now += delta; + + gf_iowrite32(upper_32_bits(now), base + TIMER_ALARM_HIGH); + gf_iowrite32(lower_32_bits(now), base + TIMER_ALARM_LOW); + + return 0; +} + +static irqreturn_t goldfish_timer_irq(int irq, void *dev_id) +{ + struct goldfish_timer *timerdrv = dev_id; + struct clock_event_device *evt = &timerdrv->ced; + void __iomem *base = timerdrv->base; + + gf_iowrite32(1, base + TIMER_CLEAR_INTERRUPT); + + evt->event_handler(evt); + + return IRQ_HANDLED; +} + +int __init goldfish_timer_init(int irq, void __iomem *base) +{ + struct goldfish_timer *timerdrv; + int ret; + + timerdrv = kzalloc(sizeof(*timerdrv), GFP_KERNEL); + if (!timerdrv) + return -ENOMEM; + + timerdrv->base = base; + + timerdrv->ced = (struct clock_event_device){ + .name = "goldfish_timer", + .features = CLOCK_EVT_FEAT_ONESHOT, + .set_state_shutdown = goldfish_timer_shutdown, + .set_state_oneshot = goldfish_timer_set_oneshot, + .set_next_event = goldfish_timer_next_event, + }; + + timerdrv->res = (struct resource){ + .name = "goldfish_timer", + .start = (unsigned long)base, + .end = (unsigned long)base + 0xfff, + }; + + ret = request_resource(&iomem_resource, &timerdrv->res); + if (ret) { + pr_err("Cannot allocate '%s' resource\n", timerdrv->res.name); + return ret; + } + + timerdrv->cs = (struct clocksource){ + .name = "goldfish_timer", + .rating = 400, + .read = goldfish_timer_read, + .mask = CLOCKSOURCE_MASK(64), + .flags = 0, + .max_idle_ns = LONG_MAX, + }; + + clocksource_register_hz(&timerdrv->cs, NSEC_PER_SEC); + + ret = request_irq(irq, goldfish_timer_irq, IRQF_TIMER, + "goldfish_timer", timerdrv); + if (ret) { + pr_err("Couldn't register goldfish-timer interrupt\n"); + return ret; + } + + clockevents_config_and_register(&timerdrv->ced, NSEC_PER_SEC, + 1, 0xffffffff); + + return 0; +} diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c index 82d370ae6a4a..d092c9bb4ba3 100644 --- a/drivers/cpufreq/cppc_cpufreq.c +++ b/drivers/cpufreq/cppc_cpufreq.c @@ -389,6 +389,27 @@ static int cppc_cpufreq_set_target(struct cpufreq_policy *policy, return ret; } +static unsigned int cppc_cpufreq_fast_switch(struct cpufreq_policy *policy, + unsigned int target_freq) +{ + struct cppc_cpudata *cpu_data = policy->driver_data; + unsigned int cpu = policy->cpu; + u32 desired_perf; + int ret; + + desired_perf = cppc_cpufreq_khz_to_perf(cpu_data, target_freq); + cpu_data->perf_ctrls.desired_perf = desired_perf; + ret = cppc_set_perf(cpu, &cpu_data->perf_ctrls); + + if (ret) { + pr_debug("Failed to set target on CPU:%d. ret:%d\n", + cpu, ret); + return 0; + } + + return target_freq; +} + static int cppc_verify_policy(struct cpufreq_policy_data *policy) { cpufreq_verify_within_cpu_limits(policy); @@ -420,12 +441,197 @@ static unsigned int cppc_cpufreq_get_transition_delay_us(unsigned int cpu) return cppc_get_transition_latency(cpu) / NSEC_PER_USEC; } +static DEFINE_PER_CPU(unsigned int, efficiency_class); +static void cppc_cpufreq_register_em(struct cpufreq_policy *policy); + +/* Create an artificial performance state every CPPC_EM_CAP_STEP capacity unit. */ +#define CPPC_EM_CAP_STEP (20) +/* Increase the cost value by CPPC_EM_COST_STEP every performance state. */ +#define CPPC_EM_COST_STEP (1) +/* Add a cost gap correspnding to the energy of 4 CPUs. */ +#define CPPC_EM_COST_GAP (4 * SCHED_CAPACITY_SCALE * CPPC_EM_COST_STEP \ + / CPPC_EM_CAP_STEP) + +static unsigned int get_perf_level_count(struct cpufreq_policy *policy) +{ + struct cppc_perf_caps *perf_caps; + unsigned int min_cap, max_cap; + struct cppc_cpudata *cpu_data; + int cpu = policy->cpu; + + cpu_data = policy->driver_data; + perf_caps = &cpu_data->perf_caps; + max_cap = arch_scale_cpu_capacity(cpu); + min_cap = div_u64(max_cap * perf_caps->lowest_perf, perf_caps->highest_perf); + if ((min_cap == 0) || (max_cap < min_cap)) + return 0; + return 1 + max_cap / CPPC_EM_CAP_STEP - min_cap / CPPC_EM_CAP_STEP; +} + +/* + * The cost is defined as: + * cost = power * max_frequency / frequency + */ +static inline unsigned long compute_cost(int cpu, int step) +{ + return CPPC_EM_COST_GAP * per_cpu(efficiency_class, cpu) + + step * CPPC_EM_COST_STEP; +} + +static int cppc_get_cpu_power(struct device *cpu_dev, + unsigned long *power, unsigned long *KHz) +{ + unsigned long perf_step, perf_prev, perf, perf_check; + unsigned int min_step, max_step, step, step_check; + unsigned long prev_freq = *KHz; + unsigned int min_cap, max_cap; + struct cpufreq_policy *policy; + + struct cppc_perf_caps *perf_caps; + struct cppc_cpudata *cpu_data; + + policy = cpufreq_cpu_get_raw(cpu_dev->id); + cpu_data = policy->driver_data; + perf_caps = &cpu_data->perf_caps; + max_cap = arch_scale_cpu_capacity(cpu_dev->id); + min_cap = div_u64(max_cap * perf_caps->lowest_perf, + perf_caps->highest_perf); + + perf_step = CPPC_EM_CAP_STEP * perf_caps->highest_perf / max_cap; + min_step = min_cap / CPPC_EM_CAP_STEP; + max_step = max_cap / CPPC_EM_CAP_STEP; + + perf_prev = cppc_cpufreq_khz_to_perf(cpu_data, *KHz); + step = perf_prev / perf_step; + + if (step > max_step) + return -EINVAL; + + if (min_step == max_step) { + step = max_step; + perf = perf_caps->highest_perf; + } else if (step < min_step) { + step = min_step; + perf = perf_caps->lowest_perf; + } else { + step++; + if (step == max_step) + perf = perf_caps->highest_perf; + else + perf = step * perf_step; + } + + *KHz = cppc_cpufreq_perf_to_khz(cpu_data, perf); + perf_check = cppc_cpufreq_khz_to_perf(cpu_data, *KHz); + step_check = perf_check / perf_step; + + /* + * To avoid bad integer approximation, check that new frequency value + * increased and that the new frequency will be converted to the + * desired step value. + */ + while ((*KHz == prev_freq) || (step_check != step)) { + perf++; + *KHz = cppc_cpufreq_perf_to_khz(cpu_data, perf); + perf_check = cppc_cpufreq_khz_to_perf(cpu_data, *KHz); + step_check = perf_check / perf_step; + } + + /* + * With an artificial EM, only the cost value is used. Still the power + * is populated such as 0 < power < EM_MAX_POWER. This allows to add + * more sense to the artificial performance states. + */ + *power = compute_cost(cpu_dev->id, step); + + return 0; +} + +static int cppc_get_cpu_cost(struct device *cpu_dev, unsigned long KHz, + unsigned long *cost) +{ + unsigned long perf_step, perf_prev; + struct cppc_perf_caps *perf_caps; + struct cpufreq_policy *policy; + struct cppc_cpudata *cpu_data; + unsigned int max_cap; + int step; + + policy = cpufreq_cpu_get_raw(cpu_dev->id); + cpu_data = policy->driver_data; + perf_caps = &cpu_data->perf_caps; + max_cap = arch_scale_cpu_capacity(cpu_dev->id); + + perf_prev = cppc_cpufreq_khz_to_perf(cpu_data, KHz); + perf_step = CPPC_EM_CAP_STEP * perf_caps->highest_perf / max_cap; + step = perf_prev / perf_step; + + *cost = compute_cost(cpu_dev->id, step); + + return 0; +} + +static int populate_efficiency_class(void) +{ + struct acpi_madt_generic_interrupt *gicc; + DECLARE_BITMAP(used_classes, 256) = {}; + int class, cpu, index; + + for_each_possible_cpu(cpu) { + gicc = acpi_cpu_get_madt_gicc(cpu); + class = gicc->efficiency_class; + bitmap_set(used_classes, class, 1); + } + + if (bitmap_weight(used_classes, 256) <= 1) { + pr_debug("Efficiency classes are all equal (=%d). " + "No EM registered", class); + return -EINVAL; + } + + /* + * Squeeze efficiency class values on [0:#efficiency_class-1]. + * Values are per spec in [0:255]. + */ + index = 0; + for_each_set_bit(class, used_classes, 256) { + for_each_possible_cpu(cpu) { + gicc = acpi_cpu_get_madt_gicc(cpu); + if (gicc->efficiency_class == class) + per_cpu(efficiency_class, cpu) = index; + } + index++; + } + cppc_cpufreq_driver.register_em = cppc_cpufreq_register_em; + + return 0; +} + +static void cppc_cpufreq_register_em(struct cpufreq_policy *policy) +{ + struct cppc_cpudata *cpu_data; + struct em_data_callback em_cb = + EM_ADV_DATA_CB(cppc_get_cpu_power, cppc_get_cpu_cost); + + cpu_data = policy->driver_data; + em_dev_register_perf_domain(get_cpu_device(policy->cpu), + get_perf_level_count(policy), &em_cb, + cpu_data->shared_cpu_map, 0); +} + #else static unsigned int cppc_cpufreq_get_transition_delay_us(unsigned int cpu) { return cppc_get_transition_latency(cpu) / NSEC_PER_USEC; } +static int populate_efficiency_class(void) +{ + return 0; +} +static void cppc_cpufreq_register_em(struct cpufreq_policy *policy) +{ +} #endif @@ -536,6 +742,9 @@ static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy) goto out; } + policy->fast_switch_possible = cppc_allow_fast_switch(); + policy->dvfs_possible_from_any_cpu = true; + /* * If 'highest_perf' is greater than 'nominal_perf', we assume CPU Boost * is supported. @@ -681,6 +890,7 @@ static struct cpufreq_driver cppc_cpufreq_driver = { .verify = cppc_verify_policy, .target = cppc_cpufreq_set_target, .get = cppc_cpufreq_get_rate, + .fast_switch = cppc_cpufreq_fast_switch, .init = cppc_cpufreq_cpu_init, .exit = cppc_cpufreq_cpu_exit, .set_boost = cppc_cpufreq_set_boost, @@ -742,6 +952,7 @@ static int __init cppc_cpufreq_init(void) cppc_check_hisi_workaround(); cppc_freq_invariance_init(); + populate_efficiency_class(); ret = cpufreq_register_driver(&cppc_cpufreq_driver); if (ret) diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 80f535cc8a75..2cad42774164 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -28,6 +28,7 @@ #include <linux/suspend.h> #include <linux/syscore_ops.h> #include <linux/tick.h> +#include <linux/units.h> #include <trace/events/power.h> static LIST_HEAD(cpufreq_policy_list); @@ -947,13 +948,14 @@ static ssize_t show(struct kobject *kobj, struct attribute *attr, char *buf) { struct cpufreq_policy *policy = to_policy(kobj); struct freq_attr *fattr = to_attr(attr); - ssize_t ret; + ssize_t ret = -EBUSY; if (!fattr->show) return -EIO; down_read(&policy->rwsem); - ret = fattr->show(policy, buf); + if (likely(!policy_is_inactive(policy))) + ret = fattr->show(policy, buf); up_read(&policy->rwsem); return ret; @@ -964,7 +966,7 @@ static ssize_t store(struct kobject *kobj, struct attribute *attr, { struct cpufreq_policy *policy = to_policy(kobj); struct freq_attr *fattr = to_attr(attr); - ssize_t ret = -EINVAL; + ssize_t ret = -EBUSY; if (!fattr->store) return -EIO; @@ -978,7 +980,8 @@ static ssize_t store(struct kobject *kobj, struct attribute *attr, if (cpu_online(policy->cpu)) { down_write(&policy->rwsem); - ret = fattr->store(policy, buf, count); + if (likely(!policy_is_inactive(policy))) + ret = fattr->store(policy, buf, count); up_write(&policy->rwsem); } @@ -1019,11 +1022,12 @@ static void add_cpu_dev_symlink(struct cpufreq_policy *policy, unsigned int cpu, dev_err(dev, "cpufreq symlink creation failed\n"); } -static void remove_cpu_dev_symlink(struct cpufreq_policy *policy, +static void remove_cpu_dev_symlink(struct cpufreq_policy *policy, int cpu, struct device *dev) { dev_dbg(dev, "%s: Removing symlink\n", __func__); sysfs_remove_link(&dev->kobj, "cpufreq"); + cpumask_clear_cpu(cpu, policy->real_cpus); } static int cpufreq_add_dev_interface(struct cpufreq_policy *policy) @@ -1337,12 +1341,12 @@ static int cpufreq_online(unsigned int cpu) down_write(&policy->rwsem); policy->cpu = cpu; policy->governor = NULL; - up_write(&policy->rwsem); } else { new_policy = true; policy = cpufreq_policy_alloc(cpu); if (!policy) return -ENOMEM; + down_write(&policy->rwsem); } if (!new_policy && cpufreq_driver->online) { @@ -1382,7 +1386,6 @@ static int cpufreq_online(unsigned int cpu) cpumask_copy(policy->related_cpus, policy->cpus); } - down_write(&policy->rwsem); /* * affected cpus must always be the one, which are online. We aren't * managing offline cpus here. @@ -1531,9 +1534,9 @@ static int cpufreq_online(unsigned int cpu) out_destroy_policy: for_each_cpu(j, policy->real_cpus) - remove_cpu_dev_symlink(policy, get_cpu_device(j)); + remove_cpu_dev_symlink(policy, j, get_cpu_device(j)); - up_write(&policy->rwsem); + cpumask_clear(policy->cpus); out_offline_policy: if (cpufreq_driver->offline) @@ -1544,6 +1547,8 @@ out_exit_policy: cpufreq_driver->exit(policy); out_free_policy: + up_write(&policy->rwsem); + cpufreq_policy_free(policy); return ret; } @@ -1575,47 +1580,36 @@ static int cpufreq_add_dev(struct device *dev, struct subsys_interface *sif) return 0; } -static int cpufreq_offline(unsigned int cpu) +static void __cpufreq_offline(unsigned int cpu, struct cpufreq_policy *policy) { - struct cpufreq_policy *policy; int ret; - pr_debug("%s: unregistering CPU %u\n", __func__, cpu); - - policy = cpufreq_cpu_get_raw(cpu); - if (!policy) { - pr_debug("%s: No cpu_data found\n", __func__); - return 0; - } - - down_write(&policy->rwsem); if (has_target()) cpufreq_stop_governor(policy); cpumask_clear_cpu(cpu, policy->cpus); - if (policy_is_inactive(policy)) { - if (has_target()) - strncpy(policy->last_governor, policy->governor->name, - CPUFREQ_NAME_LEN); - else - policy->last_policy = policy->policy; - } else if (cpu == policy->cpu) { - /* Nominate new CPU */ - policy->cpu = cpumask_any(policy->cpus); - } - - /* Start governor again for active policy */ if (!policy_is_inactive(policy)) { + /* Nominate a new CPU if necessary. */ + if (cpu == policy->cpu) + policy->cpu = cpumask_any(policy->cpus); + + /* Start the governor again for the active policy. */ if (has_target()) { ret = cpufreq_start_governor(policy); if (ret) pr_err("%s: Failed to start governor\n", __func__); } - goto unlock; + return; } + if (has_target()) + strncpy(policy->last_governor, policy->governor->name, + CPUFREQ_NAME_LEN); + else + policy->last_policy = policy->policy; + if (cpufreq_thermal_control_enabled(cpufreq_driver)) { cpufreq_cooling_unregister(policy->cdev); policy->cdev = NULL; @@ -1634,8 +1628,24 @@ static int cpufreq_offline(unsigned int cpu) cpufreq_driver->exit(policy); policy->freq_table = NULL; } +} + +static int cpufreq_offline(unsigned int cpu) +{ + struct cpufreq_policy *policy; + + pr_debug("%s: unregistering CPU %u\n", __func__, cpu); + + policy = cpufreq_cpu_get_raw(cpu); + if (!policy) { + pr_debug("%s: No cpu_data found\n", __func__); + return 0; + } + + down_write(&policy->rwsem); + + __cpufreq_offline(cpu, policy); -unlock: up_write(&policy->rwsem); return 0; } @@ -1653,19 +1663,25 @@ static void cpufreq_remove_dev(struct device *dev, struct subsys_interface *sif) if (!policy) return; - if (cpu_online(cpu)) - cpufreq_offline(cpu); + down_write(&policy->rwsem); - cpumask_clear_cpu(cpu, policy->real_cpus); - remove_cpu_dev_symlink(policy, dev); + if (cpu_online(cpu)) + __cpufreq_offline(cpu, policy); - if (cpumask_empty(policy->real_cpus)) { - /* We did light-weight exit earlier, do full tear down now */ - if (cpufreq_driver->offline) - cpufreq_driver->exit(policy); + remove_cpu_dev_symlink(policy, cpu, dev); - cpufreq_policy_free(policy); + if (!cpumask_empty(policy->real_cpus)) { + up_write(&policy->rwsem); + return; } + + /* We did light-weight exit earlier, do full tear down now */ + if (cpufreq_driver->offline) + cpufreq_driver->exit(policy); + + up_write(&policy->rwsem); + + cpufreq_policy_free(policy); } /** @@ -1707,6 +1723,16 @@ static unsigned int cpufreq_verify_current_freq(struct cpufreq_policy *policy, b return new_freq; if (policy->cur != new_freq) { + /* + * For some platforms, the frequency returned by hardware may be + * slightly different from what is provided in the frequency + * table, for example hardware may return 499 MHz instead of 500 + * MHz. In such cases it is better to avoid getting into + * unnecessary frequency updates. + */ + if (abs(policy->cur - new_freq) < HZ_PER_MHZ) + return policy->cur; + cpufreq_out_of_sync(policy, new_freq); if (update) schedule_work(&policy->update); diff --git a/drivers/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c index 0d42cf8b88d8..85da677c43d6 100644 --- a/drivers/cpufreq/cpufreq_governor.c +++ b/drivers/cpufreq/cpufreq_governor.c @@ -388,6 +388,15 @@ static void free_policy_dbs_info(struct policy_dbs_info *policy_dbs, gov->free(policy_dbs); } +static void cpufreq_dbs_data_release(struct kobject *kobj) +{ + struct dbs_data *dbs_data = to_dbs_data(to_gov_attr_set(kobj)); + struct dbs_governor *gov = dbs_data->gov; + + gov->exit(dbs_data); + kfree(dbs_data); +} + int cpufreq_dbs_governor_init(struct cpufreq_policy *policy) { struct dbs_governor *gov = dbs_governor_of(policy); @@ -425,6 +434,7 @@ int cpufreq_dbs_governor_init(struct cpufreq_policy *policy) goto free_policy_dbs_info; } + dbs_data->gov = gov; gov_attr_set_init(&dbs_data->attr_set, &policy_dbs->list); ret = gov->init(dbs_data); @@ -447,6 +457,7 @@ int cpufreq_dbs_governor_init(struct cpufreq_policy *policy) policy->governor_data = policy_dbs; gov->kobj_type.sysfs_ops = &governor_sysfs_ops; + gov->kobj_type.release = cpufreq_dbs_data_release; ret = kobject_init_and_add(&dbs_data->attr_set.kobj, &gov->kobj_type, get_governor_parent_kobj(policy), "%s", gov->gov.name); @@ -488,13 +499,8 @@ void cpufreq_dbs_governor_exit(struct cpufreq_policy *policy) policy->governor_data = NULL; - if (!count) { - if (!have_governor_per_policy()) - gov->gdbs_data = NULL; - - gov->exit(dbs_data); - kfree(dbs_data); - } + if (!count && !have_governor_per_policy()) + gov->gdbs_data = NULL; free_policy_dbs_info(policy_dbs, gov); diff --git a/drivers/cpufreq/cpufreq_governor.h b/drivers/cpufreq/cpufreq_governor.h index a5a0bc3cc23e..168c23fd7fca 100644 --- a/drivers/cpufreq/cpufreq_governor.h +++ b/drivers/cpufreq/cpufreq_governor.h @@ -37,6 +37,7 @@ enum {OD_NORMAL_SAMPLE, OD_SUB_SAMPLE}; /* Governor demand based switching data (per-policy or global). */ struct dbs_data { struct gov_attr_set attr_set; + struct dbs_governor *gov; void *tuners; unsigned int ignore_nice_load; unsigned int sampling_rate; diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 846bb3a78788..57cdb3679885 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -1322,6 +1322,7 @@ static ssize_t store_no_turbo(struct kobject *a, struct kobj_attribute *b, mutex_unlock(&intel_pstate_limits_lock); intel_pstate_update_policies(); + arch_set_max_freq_ratio(global.no_turbo); mutex_unlock(&intel_pstate_driver_lock); @@ -2424,6 +2425,7 @@ static const struct x86_cpu_id intel_pstate_cpu_oob_ids[] __initconst = { X86_MATCH(BROADWELL_X, core_funcs), X86_MATCH(SKYLAKE_X, core_funcs), X86_MATCH(ICELAKE_X, core_funcs), + X86_MATCH(SAPPHIRERAPIDS_X, core_funcs), {} }; diff --git a/drivers/cpufreq/mediatek-cpufreq-hw.c b/drivers/cpufreq/mediatek-cpufreq-hw.c index 0a94c56ddad2..813cccbfe934 100644 --- a/drivers/cpufreq/mediatek-cpufreq-hw.c +++ b/drivers/cpufreq/mediatek-cpufreq-hw.c @@ -51,8 +51,8 @@ static const u16 cpufreq_mtk_offsets[REG_ARRAY_SIZE] = { }; static int __maybe_unused -mtk_cpufreq_get_cpu_power(unsigned long *mW, - unsigned long *KHz, struct device *cpu_dev) +mtk_cpufreq_get_cpu_power(struct device *cpu_dev, unsigned long *mW, + unsigned long *KHz) { struct mtk_cpufreq_data *data; struct cpufreq_policy *policy; diff --git a/drivers/cpufreq/pasemi-cpufreq.c b/drivers/cpufreq/pasemi-cpufreq.c index 815645170c4d..039a66bbe1be 100644 --- a/drivers/cpufreq/pasemi-cpufreq.c +++ b/drivers/cpufreq/pasemi-cpufreq.c @@ -18,7 +18,6 @@ #include <asm/hw_irq.h> #include <asm/io.h> -#include <asm/prom.h> #include <asm/time.h> #include <asm/smp.h> diff --git a/drivers/cpufreq/pmac32-cpufreq.c b/drivers/cpufreq/pmac32-cpufreq.c index 4f20c6a9108d..20f64a8b0a35 100644 --- a/drivers/cpufreq/pmac32-cpufreq.c +++ b/drivers/cpufreq/pmac32-cpufreq.c @@ -24,7 +24,7 @@ #include <linux/device.h> #include <linux/hardirq.h> #include <linux/of_device.h> -#include <asm/prom.h> + #include <asm/machdep.h> #include <asm/irq.h> #include <asm/pmac_feature.h> diff --git a/drivers/cpufreq/pmac64-cpufreq.c b/drivers/cpufreq/pmac64-cpufreq.c index d7542a106e6b..ba9c31d98bd6 100644 --- a/drivers/cpufreq/pmac64-cpufreq.c +++ b/drivers/cpufreq/pmac64-cpufreq.c @@ -22,7 +22,7 @@ #include <linux/completion.h> #include <linux/mutex.h> #include <linux/of_device.h> -#include <asm/prom.h> + #include <asm/machdep.h> #include <asm/irq.h> #include <asm/sections.h> diff --git a/drivers/cpufreq/ppc_cbe_cpufreq.c b/drivers/cpufreq/ppc_cbe_cpufreq.c index c58abb4cca3a..e3313ce63b38 100644 --- a/drivers/cpufreq/ppc_cbe_cpufreq.c +++ b/drivers/cpufreq/ppc_cbe_cpufreq.c @@ -12,7 +12,6 @@ #include <linux/of_platform.h> #include <asm/machdep.h> -#include <asm/prom.h> #include <asm/cell-regs.h> #include "ppc_cbe_cpufreq.h" diff --git a/drivers/cpufreq/ppc_cbe_cpufreq_pmi.c b/drivers/cpufreq/ppc_cbe_cpufreq_pmi.c index 037fe23bc6ed..4fba3637b115 100644 --- a/drivers/cpufreq/ppc_cbe_cpufreq_pmi.c +++ b/drivers/cpufreq/ppc_cbe_cpufreq_pmi.c @@ -13,9 +13,9 @@ #include <linux/init.h> #include <linux/of_platform.h> #include <linux/pm_qos.h> +#include <linux/slab.h> #include <asm/processor.h> -#include <asm/prom.h> #include <asm/pmi.h> #include <asm/cell-regs.h> diff --git a/drivers/cpufreq/qcom-cpufreq-hw.c b/drivers/cpufreq/qcom-cpufreq-hw.c index f9d593ff4718..0253731d6d25 100644 --- a/drivers/cpufreq/qcom-cpufreq-hw.c +++ b/drivers/cpufreq/qcom-cpufreq-hw.c @@ -24,13 +24,17 @@ #define CLK_HW_DIV 2 #define LUT_TURBO_IND 1 +#define GT_IRQ_STATUS BIT(2) + #define HZ_PER_KHZ 1000 struct qcom_cpufreq_soc_data { u32 reg_enable; + u32 reg_domain_state; u32 reg_dcvs_ctrl; u32 reg_freq_lut; u32 reg_volt_lut; + u32 reg_intr_clr; u32 reg_current_vote; u32 reg_perf_state; u8 lut_row_size; @@ -280,37 +284,46 @@ static void qcom_get_related_cpus(int index, struct cpumask *m) } } -static unsigned int qcom_lmh_get_throttle_freq(struct qcom_cpufreq_data *data) +static unsigned long qcom_lmh_get_throttle_freq(struct qcom_cpufreq_data *data) { - unsigned int val = readl_relaxed(data->base + data->soc_data->reg_current_vote); + unsigned int lval; + + if (data->soc_data->reg_current_vote) + lval = readl_relaxed(data->base + data->soc_data->reg_current_vote) & 0x3ff; + else + lval = readl_relaxed(data->base + data->soc_data->reg_domain_state) & 0xff; - return (val & 0x3FF) * 19200; + return lval * xo_rate; } static void qcom_lmh_dcvs_notify(struct qcom_cpufreq_data *data) { struct cpufreq_policy *policy = data->policy; - int cpu = cpumask_first(policy->cpus); + int cpu = cpumask_first(policy->related_cpus); struct device *dev = get_cpu_device(cpu); unsigned long freq_hz, throttled_freq; struct dev_pm_opp *opp; - unsigned int freq; /* * Get the h/w throttled frequency, normalize it using the * registered opp table and use it to calculate thermal pressure. */ - freq = qcom_lmh_get_throttle_freq(data); - freq_hz = freq * HZ_PER_KHZ; + freq_hz = qcom_lmh_get_throttle_freq(data); opp = dev_pm_opp_find_freq_floor(dev, &freq_hz); if (IS_ERR(opp) && PTR_ERR(opp) == -ERANGE) - dev_pm_opp_find_freq_ceil(dev, &freq_hz); + opp = dev_pm_opp_find_freq_ceil(dev, &freq_hz); + + if (IS_ERR(opp)) { + dev_warn(dev, "Can't find the OPP for throttling: %pe!\n", opp); + } else { + throttled_freq = freq_hz / HZ_PER_KHZ; - throttled_freq = freq_hz / HZ_PER_KHZ; + /* Update thermal pressure (the boost frequencies are accepted) */ + arch_update_thermal_pressure(policy->related_cpus, throttled_freq); - /* Update thermal pressure (the boost frequencies are accepted) */ - arch_update_thermal_pressure(policy->related_cpus, throttled_freq); + dev_pm_opp_put(opp); + } /* * In the unlikely case policy is unregistered do not enable @@ -350,6 +363,10 @@ static irqreturn_t qcom_lmh_dcvs_handle_irq(int irq, void *data) disable_irq_nosync(c_data->throttle_irq); schedule_delayed_work(&c_data->throttle_work, 0); + if (c_data->soc_data->reg_intr_clr) + writel_relaxed(GT_IRQ_STATUS, + c_data->base + c_data->soc_data->reg_intr_clr); + return IRQ_HANDLED; } @@ -365,9 +382,11 @@ static const struct qcom_cpufreq_soc_data qcom_soc_data = { static const struct qcom_cpufreq_soc_data epss_soc_data = { .reg_enable = 0x0, + .reg_domain_state = 0x20, .reg_dcvs_ctrl = 0xb0, .reg_freq_lut = 0x100, .reg_volt_lut = 0x200, + .reg_intr_clr = 0x308, .reg_perf_state = 0x320, .lut_row_size = 4, }; @@ -417,16 +436,39 @@ static int qcom_cpufreq_hw_lmh_init(struct cpufreq_policy *policy, int index) return 0; } -static void qcom_cpufreq_hw_lmh_exit(struct qcom_cpufreq_data *data) +static int qcom_cpufreq_hw_cpu_online(struct cpufreq_policy *policy) +{ + struct qcom_cpufreq_data *data = policy->driver_data; + struct platform_device *pdev = cpufreq_get_driver_data(); + int ret; + + ret = irq_set_affinity_hint(data->throttle_irq, policy->cpus); + if (ret) + dev_err(&pdev->dev, "Failed to set CPU affinity of %s[%d]\n", + data->irq_name, data->throttle_irq); + + return ret; +} + +static int qcom_cpufreq_hw_cpu_offline(struct cpufreq_policy *policy) { + struct qcom_cpufreq_data *data = policy->driver_data; + if (data->throttle_irq <= 0) - return; + return 0; mutex_lock(&data->throttle_lock); data->cancel_throttle = true; mutex_unlock(&data->throttle_lock); cancel_delayed_work_sync(&data->throttle_work); + irq_set_affinity_hint(data->throttle_irq, NULL); + + return 0; +} + +static void qcom_cpufreq_hw_lmh_exit(struct qcom_cpufreq_data *data) +{ free_irq(data->throttle_irq, data); } @@ -583,6 +625,8 @@ static struct cpufreq_driver cpufreq_qcom_hw_driver = { .get = qcom_cpufreq_hw_get, .init = qcom_cpufreq_hw_cpu_init, .exit = qcom_cpufreq_hw_cpu_exit, + .online = qcom_cpufreq_hw_cpu_online, + .offline = qcom_cpufreq_hw_cpu_offline, .register_em = cpufreq_register_em_with_opp, .fast_switch = qcom_cpufreq_hw_fast_switch, .name = "qcom-cpufreq-hw", diff --git a/drivers/cpufreq/scmi-cpufreq.c b/drivers/cpufreq/scmi-cpufreq.c index 919fa6e3f462..6d2a4cf46db7 100644 --- a/drivers/cpufreq/scmi-cpufreq.c +++ b/drivers/cpufreq/scmi-cpufreq.c @@ -96,8 +96,8 @@ scmi_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpumask) } static int __maybe_unused -scmi_get_cpu_power(unsigned long *power, unsigned long *KHz, - struct device *cpu_dev) +scmi_get_cpu_power(struct device *cpu_dev, unsigned long *power, + unsigned long *KHz) { unsigned long Hz; int ret, domain; diff --git a/drivers/cpufreq/sun50i-cpufreq-nvmem.c b/drivers/cpufreq/sun50i-cpufreq-nvmem.c index 2deed8d8773f..75e1bf3a08f7 100644 --- a/drivers/cpufreq/sun50i-cpufreq-nvmem.c +++ b/drivers/cpufreq/sun50i-cpufreq-nvmem.c @@ -98,8 +98,10 @@ static int sun50i_cpufreq_nvmem_probe(struct platform_device *pdev) return -ENOMEM; ret = sun50i_cpufreq_get_efuse(&speed); - if (ret) + if (ret) { + kfree(opp_tables); return ret; + } snprintf(name, MAX_NAME_LEN, "speed%d", speed); diff --git a/drivers/cpuidle/cpuidle-psci-domain.c b/drivers/cpuidle/cpuidle-psci-domain.c index 755bbdfc5b82..3db4fca1172b 100644 --- a/drivers/cpuidle/cpuidle-psci-domain.c +++ b/drivers/cpuidle/cpuidle-psci-domain.c @@ -52,7 +52,7 @@ static int psci_pd_init(struct device_node *np, bool use_osi) struct generic_pm_domain *pd; struct psci_pd_provider *pd_provider; struct dev_power_governor *pd_gov; - int ret = -ENOMEM, state_count = 0; + int ret = -ENOMEM; pd = dt_idle_pd_alloc(np, psci_dt_parse_state_node); if (!pd) @@ -71,7 +71,7 @@ static int psci_pd_init(struct device_node *np, bool use_osi) pd->flags |= GENPD_FLAG_ALWAYS_ON; /* Use governor for CPU PM domains if it has some states to manage. */ - pd_gov = state_count > 0 ? &pm_domain_cpu_gov : NULL; + pd_gov = pd->states ? &pm_domain_cpu_gov : NULL; ret = pm_genpd_init(pd, pd_gov, false); if (ret) diff --git a/drivers/cpuidle/cpuidle-psci.c b/drivers/cpuidle/cpuidle-psci.c index b51b5df08450..540105ca0781 100644 --- a/drivers/cpuidle/cpuidle-psci.c +++ b/drivers/cpuidle/cpuidle-psci.c @@ -23,6 +23,7 @@ #include <linux/pm_runtime.h> #include <linux/slab.h> #include <linux/string.h> +#include <linux/syscore_ops.h> #include <asm/cpuidle.h> @@ -131,6 +132,49 @@ static int psci_idle_cpuhp_down(unsigned int cpu) return 0; } +static void psci_idle_syscore_switch(bool suspend) +{ + bool cleared = false; + struct device *dev; + int cpu; + + for_each_possible_cpu(cpu) { + dev = per_cpu_ptr(&psci_cpuidle_data, cpu)->dev; + + if (dev && suspend) { + dev_pm_genpd_suspend(dev); + } else if (dev) { + dev_pm_genpd_resume(dev); + + /* Account for userspace having offlined a CPU. */ + if (pm_runtime_status_suspended(dev)) + pm_runtime_set_active(dev); + + /* Clear domain state to re-start fresh. */ + if (!cleared) { + psci_set_domain_state(0); + cleared = true; + } + } + } +} + +static int psci_idle_syscore_suspend(void) +{ + psci_idle_syscore_switch(true); + return 0; +} + +static void psci_idle_syscore_resume(void) +{ + psci_idle_syscore_switch(false); +} + +static struct syscore_ops psci_idle_syscore_ops = { + .suspend = psci_idle_syscore_suspend, + .resume = psci_idle_syscore_resume, +}; + static void psci_idle_init_cpuhp(void) { int err; @@ -138,6 +182,8 @@ static void psci_idle_init_cpuhp(void) if (!psci_cpuidle_use_cpuhp) return; + register_syscore_ops(&psci_idle_syscore_ops); + err = cpuhp_setup_state_nocalls(CPUHP_AP_CPU_PM_STARTING, "cpuidle/psci:online", psci_idle_cpuhp_up, diff --git a/drivers/cpuidle/cpuidle-riscv-sbi.c b/drivers/cpuidle/cpuidle-riscv-sbi.c index b459eda2cd37..1151e5e2ba82 100644 --- a/drivers/cpuidle/cpuidle-riscv-sbi.c +++ b/drivers/cpuidle/cpuidle-riscv-sbi.c @@ -22,6 +22,7 @@ #include <linux/pm_runtime.h> #include <asm/cpuidle.h> #include <asm/sbi.h> +#include <asm/smp.h> #include <asm/suspend.h> #include "dt_idle_states.h" @@ -413,7 +414,7 @@ static int sbi_pd_init(struct device_node *np) struct generic_pm_domain *pd; struct sbi_pd_provider *pd_provider; struct dev_power_governor *pd_gov; - int ret = -ENOMEM, state_count = 0; + int ret = -ENOMEM; pd = dt_idle_pd_alloc(np, sbi_dt_parse_state_node); if (!pd) @@ -432,7 +433,7 @@ static int sbi_pd_init(struct device_node *np) pd->flags |= GENPD_FLAG_ALWAYS_ON; /* Use governor for CPU PM domains if it has some states to manage. */ - pd_gov = state_count > 0 ? &pm_domain_cpu_gov : NULL; + pd_gov = pd->states ? &pm_domain_cpu_gov : NULL; ret = pm_genpd_init(pd, pd_gov, false); if (ret) diff --git a/drivers/crypto/caam/Kconfig b/drivers/crypto/caam/Kconfig index 84ea7cba5ee5..ea9f8b1ae981 100644 --- a/drivers/crypto/caam/Kconfig +++ b/drivers/crypto/caam/Kconfig @@ -151,6 +151,9 @@ config CRYPTO_DEV_FSL_CAAM_RNG_API Selecting this will register the SEC4 hardware rng to the hw_random API for supplying the kernel entropy pool. +config CRYPTO_DEV_FSL_CAAM_BLOB_GEN + bool + endif # CRYPTO_DEV_FSL_CAAM_JR endif # CRYPTO_DEV_FSL_CAAM diff --git a/drivers/crypto/caam/Makefile b/drivers/crypto/caam/Makefile index 3570286eb9ce..25f7ae5a4642 100644 --- a/drivers/crypto/caam/Makefile +++ b/drivers/crypto/caam/Makefile @@ -21,6 +21,7 @@ caam_jr-$(CONFIG_CRYPTO_DEV_FSL_CAAM_CRYPTO_API_QI) += caamalg_qi.o caam_jr-$(CONFIG_CRYPTO_DEV_FSL_CAAM_AHASH_API) += caamhash.o caam_jr-$(CONFIG_CRYPTO_DEV_FSL_CAAM_RNG_API) += caamrng.o caam_jr-$(CONFIG_CRYPTO_DEV_FSL_CAAM_PKC_API) += caampkc.o pkc_desc.o +caam_jr-$(CONFIG_CRYPTO_DEV_FSL_CAAM_BLOB_GEN) += blob_gen.o caam-$(CONFIG_CRYPTO_DEV_FSL_CAAM_CRYPTO_API_QI) += qi.o ifneq ($(CONFIG_CRYPTO_DEV_FSL_CAAM_CRYPTO_API_QI),) diff --git a/drivers/crypto/caam/blob_gen.c b/drivers/crypto/caam/blob_gen.c new file mode 100644 index 000000000000..6345c7269eb0 --- /dev/null +++ b/drivers/crypto/caam/blob_gen.c @@ -0,0 +1,182 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2015 Pengutronix, Steffen Trumtrar <kernel@pengutronix.de> + * Copyright (C) 2021 Pengutronix, Ahmad Fatoum <kernel@pengutronix.de> + */ + +#define pr_fmt(fmt) "caam blob_gen: " fmt + +#include <linux/device.h> +#include <soc/fsl/caam-blob.h> + +#include "compat.h" +#include "desc_constr.h" +#include "desc.h" +#include "error.h" +#include "intern.h" +#include "jr.h" +#include "regs.h" + +#define CAAM_BLOB_DESC_BYTES_MAX \ + /* Command to initialize & stating length of descriptor */ \ + (CAAM_CMD_SZ + \ + /* Command to append the key-modifier + key-modifier data */ \ + CAAM_CMD_SZ + CAAM_BLOB_KEYMOD_LENGTH + \ + /* Command to include input key + pointer to the input key */ \ + CAAM_CMD_SZ + CAAM_PTR_SZ_MAX + \ + /* Command to include output key + pointer to the output key */ \ + CAAM_CMD_SZ + CAAM_PTR_SZ_MAX + \ + /* Command describing the operation to perform */ \ + CAAM_CMD_SZ) + +struct caam_blob_priv { + struct device jrdev; +}; + +struct caam_blob_job_result { + int err; + struct completion completion; +}; + +static void caam_blob_job_done(struct device *dev, u32 *desc, u32 err, void *context) +{ + struct caam_blob_job_result *res = context; + int ecode = 0; + + dev_dbg(dev, "%s %d: err 0x%x\n", __func__, __LINE__, err); + + if (err) + ecode = caam_jr_strstatus(dev, err); + + res->err = ecode; + + /* + * Upon completion, desc points to a buffer containing a CAAM job + * descriptor which encapsulates data into an externally-storable + * blob. + */ + complete(&res->completion); +} + +int caam_process_blob(struct caam_blob_priv *priv, + struct caam_blob_info *info, bool encap) +{ + struct caam_blob_job_result testres; + struct device *jrdev = &priv->jrdev; + dma_addr_t dma_in, dma_out; + int op = OP_PCLID_BLOB; + size_t output_len; + u32 *desc; + int ret; + + if (info->key_mod_len > CAAM_BLOB_KEYMOD_LENGTH) + return -EINVAL; + + if (encap) { + op |= OP_TYPE_ENCAP_PROTOCOL; + output_len = info->input_len + CAAM_BLOB_OVERHEAD; + } else { + op |= OP_TYPE_DECAP_PROTOCOL; + output_len = info->input_len - CAAM_BLOB_OVERHEAD; + } + + desc = kzalloc(CAAM_BLOB_DESC_BYTES_MAX, GFP_KERNEL | GFP_DMA); + if (!desc) + return -ENOMEM; + + dma_in = dma_map_single(jrdev, info->input, info->input_len, + DMA_TO_DEVICE); + if (dma_mapping_error(jrdev, dma_in)) { + dev_err(jrdev, "unable to map input DMA buffer\n"); + ret = -ENOMEM; + goto out_free; + } + + dma_out = dma_map_single(jrdev, info->output, output_len, + DMA_FROM_DEVICE); + if (dma_mapping_error(jrdev, dma_out)) { + dev_err(jrdev, "unable to map output DMA buffer\n"); + ret = -ENOMEM; + goto out_unmap_in; + } + + /* + * A data blob is encrypted using a blob key (BK); a random number. + * The BK is used as an AES-CCM key. The initial block (B0) and the + * initial counter (Ctr0) are generated automatically and stored in + * Class 1 Context DWords 0+1+2+3. The random BK is stored in the + * Class 1 Key Register. Operation Mode is set to AES-CCM. + */ + + init_job_desc(desc, 0); + append_key_as_imm(desc, info->key_mod, info->key_mod_len, + info->key_mod_len, CLASS_2 | KEY_DEST_CLASS_REG); + append_seq_in_ptr_intlen(desc, dma_in, info->input_len, 0); + append_seq_out_ptr_intlen(desc, dma_out, output_len, 0); + append_operation(desc, op); + + print_hex_dump_debug("data@"__stringify(__LINE__)": ", + DUMP_PREFIX_ADDRESS, 16, 1, info->input, + info->input_len, false); + print_hex_dump_debug("jobdesc@"__stringify(__LINE__)": ", + DUMP_PREFIX_ADDRESS, 16, 1, desc, + desc_bytes(desc), false); + + testres.err = 0; + init_completion(&testres.completion); + + ret = caam_jr_enqueue(jrdev, desc, caam_blob_job_done, &testres); + if (ret == -EINPROGRESS) { + wait_for_completion(&testres.completion); + ret = testres.err; + print_hex_dump_debug("output@"__stringify(__LINE__)": ", + DUMP_PREFIX_ADDRESS, 16, 1, info->output, + output_len, false); + } + + if (ret == 0) + info->output_len = output_len; + + dma_unmap_single(jrdev, dma_out, output_len, DMA_FROM_DEVICE); +out_unmap_in: + dma_unmap_single(jrdev, dma_in, info->input_len, DMA_TO_DEVICE); +out_free: + kfree(desc); + + return ret; +} +EXPORT_SYMBOL(caam_process_blob); + +struct caam_blob_priv *caam_blob_gen_init(void) +{ + struct caam_drv_private *ctrlpriv; + struct device *jrdev; + + /* + * caam_blob_gen_init() may expectedly fail with -ENODEV, e.g. when + * CAAM driver didn't probe or when SoC lacks BLOB support. An + * error would be harsh in this case, so we stick to info level. + */ + + jrdev = caam_jr_alloc(); + if (IS_ERR(jrdev)) { + pr_info("job ring requested, but none currently available\n"); + return ERR_PTR(-ENODEV); + } + + ctrlpriv = dev_get_drvdata(jrdev->parent); + if (!ctrlpriv->blob_present) { + dev_info(jrdev, "no hardware blob generation support\n"); + caam_jr_free(jrdev); + return ERR_PTR(-ENODEV); + } + + return container_of(jrdev, struct caam_blob_priv, jrdev); +} +EXPORT_SYMBOL(caam_blob_gen_init); + +void caam_blob_gen_exit(struct caam_blob_priv *priv) +{ + caam_jr_free(&priv->jrdev); +} +EXPORT_SYMBOL(caam_blob_gen_exit); diff --git a/drivers/crypto/caam/ctrl.c b/drivers/crypto/caam/ctrl.c index ca0361b2dbb0..38c4d88a9d03 100644 --- a/drivers/crypto/caam/ctrl.c +++ b/drivers/crypto/caam/ctrl.c @@ -820,12 +820,25 @@ static int caam_probe(struct platform_device *pdev) return -ENOMEM; } - if (ctrlpriv->era < 10) + comp_params = rd_reg32(&ctrl->perfmon.comp_parms_ls); + ctrlpriv->blob_present = !!(comp_params & CTPR_LS_BLOB); + + /* + * Some SoCs like the LS1028A (non-E) indicate CTPR_LS_BLOB support, + * but fail when actually using it due to missing AES support, so + * check both here. + */ + if (ctrlpriv->era < 10) { rng_vid = (rd_reg32(&ctrl->perfmon.cha_id_ls) & CHA_ID_LS_RNG_MASK) >> CHA_ID_LS_RNG_SHIFT; - else + ctrlpriv->blob_present = ctrlpriv->blob_present && + (rd_reg32(&ctrl->perfmon.cha_num_ls) & CHA_ID_LS_AES_MASK); + } else { rng_vid = (rd_reg32(&ctrl->vreg.rng) & CHA_VER_VID_MASK) >> CHA_VER_VID_SHIFT; + ctrlpriv->blob_present = ctrlpriv->blob_present && + (rd_reg32(&ctrl->vreg.aesa) & CHA_VER_MISC_AES_NUM_MASK); + } /* * If SEC has RNG version >= 4 and RNG state handle has not been diff --git a/drivers/crypto/caam/intern.h b/drivers/crypto/caam/intern.h index 7d45b21bd55a..e92210e2ab76 100644 --- a/drivers/crypto/caam/intern.h +++ b/drivers/crypto/caam/intern.h @@ -92,6 +92,7 @@ struct caam_drv_private { */ u8 total_jobrs; /* Total Job Rings in device */ u8 qi_present; /* Nonzero if QI present in device */ + u8 blob_present; /* Nonzero if BLOB support present in device */ u8 mc_en; /* Nonzero if MC f/w is active */ int secvio_irq; /* Security violation interrupt number */ int virt_en; /* Virtualization enabled in CAAM */ diff --git a/drivers/crypto/caam/regs.h b/drivers/crypto/caam/regs.h index 3738625c0250..66d6dad841bb 100644 --- a/drivers/crypto/caam/regs.h +++ b/drivers/crypto/caam/regs.h @@ -320,7 +320,8 @@ struct version_regs { #define CHA_VER_VID_MASK (0xffull << CHA_VER_VID_SHIFT) /* CHA Miscellaneous Information - AESA_MISC specific */ -#define CHA_VER_MISC_AES_GCM BIT(1 + CHA_VER_MISC_SHIFT) +#define CHA_VER_MISC_AES_NUM_MASK GENMASK(7, 0) +#define CHA_VER_MISC_AES_GCM BIT(1 + CHA_VER_MISC_SHIFT) /* CHA Miscellaneous Information - PKHA_MISC specific */ #define CHA_VER_MISC_PKHA_NO_CRYPT BIT(7 + CHA_VER_MISC_SHIFT) @@ -414,6 +415,7 @@ struct caam_perfmon { #define CTPR_MS_PG_SZ_MASK 0x10 #define CTPR_MS_PG_SZ_SHIFT 4 u32 comp_parms_ms; /* CTPR - Compile Parameters Register */ +#define CTPR_LS_BLOB BIT(1) u32 comp_parms_ls; /* CTPR - Compile Parameters Register */ u64 rsvd1[2]; diff --git a/drivers/crypto/qcom-rng.c b/drivers/crypto/qcom-rng.c index 11f30fd48c14..031b5f701a0a 100644 --- a/drivers/crypto/qcom-rng.c +++ b/drivers/crypto/qcom-rng.c @@ -65,6 +65,7 @@ static int qcom_rng_read(struct qcom_rng *rng, u8 *data, unsigned int max) } else { /* copy only remaining bytes */ memcpy(data, &val, max - currsize); + break; } } while (currsize < max); diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c index 8a7267d116b7..3f2182d66829 100644 --- a/drivers/cxl/pci.c +++ b/drivers/cxl/pci.c @@ -436,7 +436,6 @@ static int wait_for_media_ready(struct cxl_dev_state *cxlds) for (i = mbox_ready_timeout; i; i--) { u32 temp; - int rc; rc = pci_read_config_dword( pdev, d + CXL_DVSEC_RANGE_SIZE_LOW(0), &temp); diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c index a525a609dfc6..01474daf4548 100644 --- a/drivers/devfreq/devfreq.c +++ b/drivers/devfreq/devfreq.c @@ -112,16 +112,16 @@ static unsigned long find_available_max_freq(struct devfreq *devfreq) } /** - * get_freq_range() - Get the current freq range + * devfreq_get_freq_range() - Get the current freq range * @devfreq: the devfreq instance * @min_freq: the min frequency * @max_freq: the max frequency * * This takes into consideration all constraints. */ -static void get_freq_range(struct devfreq *devfreq, - unsigned long *min_freq, - unsigned long *max_freq) +void devfreq_get_freq_range(struct devfreq *devfreq, + unsigned long *min_freq, + unsigned long *max_freq) { unsigned long *freq_table = devfreq->profile->freq_table; s32 qos_min_freq, qos_max_freq; @@ -158,6 +158,7 @@ static void get_freq_range(struct devfreq *devfreq, if (*min_freq > *max_freq) *min_freq = *max_freq; } +EXPORT_SYMBOL(devfreq_get_freq_range); /** * devfreq_get_freq_level() - Lookup freq_table for the frequency @@ -418,7 +419,7 @@ int devfreq_update_target(struct devfreq *devfreq, unsigned long freq) err = devfreq->governor->get_target_freq(devfreq, &freq); if (err) return err; - get_freq_range(devfreq, &min_freq, &max_freq); + devfreq_get_freq_range(devfreq, &min_freq, &max_freq); if (freq < min_freq) { freq = min_freq; @@ -785,6 +786,7 @@ struct devfreq *devfreq_add_device(struct device *dev, { struct devfreq *devfreq; struct devfreq_governor *governor; + unsigned long min_freq, max_freq; int err = 0; if (!dev || !profile || !governor_name) { @@ -849,6 +851,8 @@ struct devfreq *devfreq_add_device(struct device *dev, goto err_dev; } + devfreq_get_freq_range(devfreq, &min_freq, &max_freq); + devfreq->suspend_freq = dev_pm_opp_get_suspend_opp_freq(dev); devfreq->opp_table = dev_pm_opp_get_opp_table(dev); if (IS_ERR(devfreq->opp_table)) @@ -1587,7 +1591,7 @@ static ssize_t min_freq_show(struct device *dev, struct device_attribute *attr, unsigned long min_freq, max_freq; mutex_lock(&df->lock); - get_freq_range(df, &min_freq, &max_freq); + devfreq_get_freq_range(df, &min_freq, &max_freq); mutex_unlock(&df->lock); return sprintf(buf, "%lu\n", min_freq); @@ -1641,7 +1645,7 @@ static ssize_t max_freq_show(struct device *dev, struct device_attribute *attr, unsigned long min_freq, max_freq; mutex_lock(&df->lock); - get_freq_range(df, &min_freq, &max_freq); + devfreq_get_freq_range(df, &min_freq, &max_freq); mutex_unlock(&df->lock); return sprintf(buf, "%lu\n", max_freq); @@ -1955,7 +1959,7 @@ static int devfreq_summary_show(struct seq_file *s, void *data) mutex_lock(&devfreq->lock); cur_freq = devfreq->previous_freq; - get_freq_range(devfreq, &min_freq, &max_freq); + devfreq_get_freq_range(devfreq, &min_freq, &max_freq); timer = devfreq->profile->timer; if (IS_SUPPORTED_ATTR(devfreq->governor->attrs, POLLING_INTERVAL)) diff --git a/drivers/devfreq/governor.h b/drivers/devfreq/governor.h index 002a7d67e39d..0adfebc0467a 100644 --- a/drivers/devfreq/governor.h +++ b/drivers/devfreq/governor.h @@ -48,6 +48,31 @@ #define DEVFREQ_GOV_ATTR_TIMER BIT(1) /** + * struct devfreq_cpu_data - Hold the per-cpu data + * @node: list node + * @dev: reference to cpu device. + * @first_cpu: the cpumask of the first cpu of a policy. + * @opp_table: reference to cpu opp table. + * @cur_freq: the current frequency of the cpu. + * @min_freq: the min frequency of the cpu. + * @max_freq: the max frequency of the cpu. + * + * This structure stores the required cpu_data of a cpu. + * This is auto-populated by the governor. + */ +struct devfreq_cpu_data { + struct list_head node; + + struct device *dev; + unsigned int first_cpu; + + struct opp_table *opp_table; + unsigned int cur_freq; + unsigned int min_freq; + unsigned int max_freq; +}; + +/** * struct devfreq_governor - Devfreq policy governor * @node: list node - contains registered devfreq governors * @name: Governor's name @@ -89,6 +114,8 @@ int devm_devfreq_add_governor(struct device *dev, int devfreq_update_status(struct devfreq *devfreq, unsigned long freq); int devfreq_update_target(struct devfreq *devfreq, unsigned long freq); +void devfreq_get_freq_range(struct devfreq *devfreq, unsigned long *min_freq, + unsigned long *max_freq); static inline int devfreq_update_stats(struct devfreq *df) { diff --git a/drivers/devfreq/governor_passive.c b/drivers/devfreq/governor_passive.c index fc09324a03e0..72c67979ebe1 100644 --- a/drivers/devfreq/governor_passive.c +++ b/drivers/devfreq/governor_passive.c @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0-only + // SPDX-License-Identifier: GPL-2.0-only /* * linux/drivers/devfreq/governor_passive.c * @@ -8,76 +8,129 @@ */ #include <linux/module.h> +#include <linux/cpu.h> +#include <linux/cpufreq.h> +#include <linux/cpumask.h> +#include <linux/slab.h> #include <linux/device.h> #include <linux/devfreq.h> #include "governor.h" -static int devfreq_passive_get_target_freq(struct devfreq *devfreq, - unsigned long *freq) +#define HZ_PER_KHZ 1000 + +static struct devfreq_cpu_data * +get_parent_cpu_data(struct devfreq_passive_data *p_data, + struct cpufreq_policy *policy) { - struct devfreq_passive_data *p_data - = (struct devfreq_passive_data *)devfreq->data; - struct devfreq *parent_devfreq = (struct devfreq *)p_data->parent; - unsigned long child_freq = ULONG_MAX; - struct dev_pm_opp *opp, *p_opp; - int i, count; + struct devfreq_cpu_data *parent_cpu_data; - /* - * If the devfreq device with passive governor has the specific method - * to determine the next frequency, should use the get_target_freq() - * of struct devfreq_passive_data. - */ - if (p_data->get_target_freq) - return p_data->get_target_freq(devfreq, freq); + if (!p_data || !policy) + return NULL; - /* - * If the parent and passive devfreq device uses the OPP table, - * get the next frequency by using the OPP table. - */ + list_for_each_entry(parent_cpu_data, &p_data->cpu_data_list, node) + if (parent_cpu_data->first_cpu == cpumask_first(policy->related_cpus)) + return parent_cpu_data; - /* - * - parent devfreq device uses the governors except for passive. - * - passive devfreq device uses the passive governor. - * - * Each devfreq has the OPP table. After deciding the new frequency - * from the governor of parent devfreq device, the passive governor - * need to get the index of new frequency on OPP table of parent - * device. And then the index is used for getting the suitable - * new frequency for passive devfreq device. - */ - if (!devfreq->profile || !devfreq->profile->freq_table - || devfreq->profile->max_state <= 0) - return -EINVAL; + return NULL; +} - /* - * The passive governor have to get the correct frequency from OPP - * list of parent device. Because in this case, *freq is temporary - * value which is decided by ondemand governor. - */ - if (devfreq->opp_table && parent_devfreq->opp_table) { - p_opp = devfreq_recommended_opp(parent_devfreq->dev.parent, - freq, 0); - if (IS_ERR(p_opp)) - return PTR_ERR(p_opp); +static unsigned long get_target_freq_by_required_opp(struct device *p_dev, + struct opp_table *p_opp_table, + struct opp_table *opp_table, + unsigned long *freq) +{ + struct dev_pm_opp *opp = NULL, *p_opp = NULL; + unsigned long target_freq; - opp = dev_pm_opp_xlate_required_opp(parent_devfreq->opp_table, - devfreq->opp_table, p_opp); - dev_pm_opp_put(p_opp); + if (!p_dev || !p_opp_table || !opp_table || !freq) + return 0; - if (IS_ERR(opp)) - goto no_required_opp; + p_opp = devfreq_recommended_opp(p_dev, freq, 0); + if (IS_ERR(p_opp)) + return 0; - *freq = dev_pm_opp_get_freq(opp); - dev_pm_opp_put(opp); + opp = dev_pm_opp_xlate_required_opp(p_opp_table, opp_table, p_opp); + dev_pm_opp_put(p_opp); + if (IS_ERR(opp)) return 0; + + target_freq = dev_pm_opp_get_freq(opp); + dev_pm_opp_put(opp); + + return target_freq; +} + +static int get_target_freq_with_cpufreq(struct devfreq *devfreq, + unsigned long *target_freq) +{ + struct devfreq_passive_data *p_data = + (struct devfreq_passive_data *)devfreq->data; + struct devfreq_cpu_data *parent_cpu_data; + struct cpufreq_policy *policy; + unsigned long cpu, cpu_cur, cpu_min, cpu_max, cpu_percent; + unsigned long dev_min, dev_max; + unsigned long freq = 0; + int ret = 0; + + for_each_online_cpu(cpu) { + policy = cpufreq_cpu_get(cpu); + if (!policy) { + ret = -EINVAL; + continue; + } + + parent_cpu_data = get_parent_cpu_data(p_data, policy); + if (!parent_cpu_data) { + cpufreq_cpu_put(policy); + continue; + } + + /* Get target freq via required opps */ + cpu_cur = parent_cpu_data->cur_freq * HZ_PER_KHZ; + freq = get_target_freq_by_required_opp(parent_cpu_data->dev, + parent_cpu_data->opp_table, + devfreq->opp_table, &cpu_cur); + if (freq) { + *target_freq = max(freq, *target_freq); + cpufreq_cpu_put(policy); + continue; + } + + /* Use interpolation if required opps is not available */ + devfreq_get_freq_range(devfreq, &dev_min, &dev_max); + + cpu_min = parent_cpu_data->min_freq; + cpu_max = parent_cpu_data->max_freq; + cpu_cur = parent_cpu_data->cur_freq; + + cpu_percent = ((cpu_cur - cpu_min) * 100) / (cpu_max - cpu_min); + freq = dev_min + mult_frac(dev_max - dev_min, cpu_percent, 100); + + *target_freq = max(freq, *target_freq); + cpufreq_cpu_put(policy); } -no_required_opp: - /* - * Get the OPP table's index of decided frequency by governor - * of parent device. - */ + return ret; +} + +static int get_target_freq_with_devfreq(struct devfreq *devfreq, + unsigned long *freq) +{ + struct devfreq_passive_data *p_data + = (struct devfreq_passive_data *)devfreq->data; + struct devfreq *parent_devfreq = (struct devfreq *)p_data->parent; + unsigned long child_freq = ULONG_MAX; + int i, count; + + /* Get target freq via required opps */ + child_freq = get_target_freq_by_required_opp(parent_devfreq->dev.parent, + parent_devfreq->opp_table, + devfreq->opp_table, freq); + if (child_freq) + goto out; + + /* Use interpolation if required opps is not available */ for (i = 0; i < parent_devfreq->profile->max_state; i++) if (parent_devfreq->profile->freq_table[i] == *freq) break; @@ -85,7 +138,6 @@ no_required_opp: if (i == parent_devfreq->profile->max_state) return -EINVAL; - /* Get the suitable frequency by using index of parent device. */ if (i < devfreq->profile->max_state) { child_freq = devfreq->profile->freq_table[i]; } else { @@ -93,12 +145,202 @@ no_required_opp: child_freq = devfreq->profile->freq_table[count - 1]; } - /* Return the suitable frequency for passive device. */ +out: *freq = child_freq; return 0; } +static int devfreq_passive_get_target_freq(struct devfreq *devfreq, + unsigned long *freq) +{ + struct devfreq_passive_data *p_data = + (struct devfreq_passive_data *)devfreq->data; + int ret; + + if (!p_data) + return -EINVAL; + + /* + * If the devfreq device with passive governor has the specific method + * to determine the next frequency, should use the get_target_freq() + * of struct devfreq_passive_data. + */ + if (p_data->get_target_freq) + return p_data->get_target_freq(devfreq, freq); + + switch (p_data->parent_type) { + case DEVFREQ_PARENT_DEV: + ret = get_target_freq_with_devfreq(devfreq, freq); + break; + case CPUFREQ_PARENT_DEV: + ret = get_target_freq_with_cpufreq(devfreq, freq); + break; + default: + ret = -EINVAL; + dev_err(&devfreq->dev, "Invalid parent type\n"); + break; + } + + return ret; +} + +static int cpufreq_passive_notifier_call(struct notifier_block *nb, + unsigned long event, void *ptr) +{ + struct devfreq_passive_data *p_data = + container_of(nb, struct devfreq_passive_data, nb); + struct devfreq *devfreq = (struct devfreq *)p_data->this; + struct devfreq_cpu_data *parent_cpu_data; + struct cpufreq_freqs *freqs = ptr; + unsigned int cur_freq; + int ret; + + if (event != CPUFREQ_POSTCHANGE || !freqs) + return 0; + + parent_cpu_data = get_parent_cpu_data(p_data, freqs->policy); + if (!parent_cpu_data || parent_cpu_data->cur_freq == freqs->new) + return 0; + + cur_freq = parent_cpu_data->cur_freq; + parent_cpu_data->cur_freq = freqs->new; + + mutex_lock(&devfreq->lock); + ret = devfreq_update_target(devfreq, freqs->new); + mutex_unlock(&devfreq->lock); + if (ret) { + parent_cpu_data->cur_freq = cur_freq; + dev_err(&devfreq->dev, "failed to update the frequency.\n"); + return ret; + } + + return 0; +} + +static int cpufreq_passive_unregister_notifier(struct devfreq *devfreq) +{ + struct devfreq_passive_data *p_data + = (struct devfreq_passive_data *)devfreq->data; + struct devfreq_cpu_data *parent_cpu_data; + int cpu, ret = 0; + + if (p_data->nb.notifier_call) { + ret = cpufreq_unregister_notifier(&p_data->nb, + CPUFREQ_TRANSITION_NOTIFIER); + if (ret < 0) + return ret; + } + + for_each_possible_cpu(cpu) { + struct cpufreq_policy *policy = cpufreq_cpu_get(cpu); + if (!policy) { + ret = -EINVAL; + continue; + } + + parent_cpu_data = get_parent_cpu_data(p_data, policy); + if (!parent_cpu_data) { + cpufreq_cpu_put(policy); + continue; + } + + list_del(&parent_cpu_data->node); + if (parent_cpu_data->opp_table) + dev_pm_opp_put_opp_table(parent_cpu_data->opp_table); + kfree(parent_cpu_data); + cpufreq_cpu_put(policy); + } + + return ret; +} + +static int cpufreq_passive_register_notifier(struct devfreq *devfreq) +{ + struct devfreq_passive_data *p_data + = (struct devfreq_passive_data *)devfreq->data; + struct device *dev = devfreq->dev.parent; + struct opp_table *opp_table = NULL; + struct devfreq_cpu_data *parent_cpu_data; + struct cpufreq_policy *policy; + struct device *cpu_dev; + unsigned int cpu; + int ret; + + p_data->cpu_data_list + = (struct list_head)LIST_HEAD_INIT(p_data->cpu_data_list); + + p_data->nb.notifier_call = cpufreq_passive_notifier_call; + ret = cpufreq_register_notifier(&p_data->nb, CPUFREQ_TRANSITION_NOTIFIER); + if (ret) { + dev_err(dev, "failed to register cpufreq notifier\n"); + p_data->nb.notifier_call = NULL; + goto err; + } + + for_each_possible_cpu(cpu) { + policy = cpufreq_cpu_get(cpu); + if (!policy) { + ret = -EPROBE_DEFER; + goto err; + } + + parent_cpu_data = get_parent_cpu_data(p_data, policy); + if (parent_cpu_data) { + cpufreq_cpu_put(policy); + continue; + } + + parent_cpu_data = kzalloc(sizeof(*parent_cpu_data), + GFP_KERNEL); + if (!parent_cpu_data) { + ret = -ENOMEM; + goto err_put_policy; + } + + cpu_dev = get_cpu_device(cpu); + if (!cpu_dev) { + dev_err(dev, "failed to get cpu device\n"); + ret = -ENODEV; + goto err_free_cpu_data; + } + + opp_table = dev_pm_opp_get_opp_table(cpu_dev); + if (IS_ERR(opp_table)) { + dev_err(dev, "failed to get opp_table of cpu%d\n", cpu); + ret = PTR_ERR(opp_table); + goto err_free_cpu_data; + } + + parent_cpu_data->dev = cpu_dev; + parent_cpu_data->opp_table = opp_table; + parent_cpu_data->first_cpu = cpumask_first(policy->related_cpus); + parent_cpu_data->cur_freq = policy->cur; + parent_cpu_data->min_freq = policy->cpuinfo.min_freq; + parent_cpu_data->max_freq = policy->cpuinfo.max_freq; + + list_add_tail(&parent_cpu_data->node, &p_data->cpu_data_list); + cpufreq_cpu_put(policy); + } + + mutex_lock(&devfreq->lock); + ret = devfreq_update_target(devfreq, 0L); + mutex_unlock(&devfreq->lock); + if (ret) + dev_err(dev, "failed to update the frequency\n"); + + return ret; + +err_free_cpu_data: + kfree(parent_cpu_data); +err_put_policy: + cpufreq_cpu_put(policy); +err: + WARN_ON(cpufreq_passive_unregister_notifier(devfreq)); + + return ret; +} + static int devfreq_passive_notifier_call(struct notifier_block *nb, unsigned long event, void *ptr) { @@ -131,30 +373,55 @@ static int devfreq_passive_notifier_call(struct notifier_block *nb, return NOTIFY_DONE; } -static int devfreq_passive_event_handler(struct devfreq *devfreq, - unsigned int event, void *data) +static int devfreq_passive_unregister_notifier(struct devfreq *devfreq) +{ + struct devfreq_passive_data *p_data + = (struct devfreq_passive_data *)devfreq->data; + struct devfreq *parent = (struct devfreq *)p_data->parent; + struct notifier_block *nb = &p_data->nb; + + return devfreq_unregister_notifier(parent, nb, DEVFREQ_TRANSITION_NOTIFIER); +} + +static int devfreq_passive_register_notifier(struct devfreq *devfreq) { struct devfreq_passive_data *p_data = (struct devfreq_passive_data *)devfreq->data; struct devfreq *parent = (struct devfreq *)p_data->parent; struct notifier_block *nb = &p_data->nb; - int ret = 0; if (!parent) return -EPROBE_DEFER; + nb->notifier_call = devfreq_passive_notifier_call; + return devfreq_register_notifier(parent, nb, DEVFREQ_TRANSITION_NOTIFIER); +} + +static int devfreq_passive_event_handler(struct devfreq *devfreq, + unsigned int event, void *data) +{ + struct devfreq_passive_data *p_data + = (struct devfreq_passive_data *)devfreq->data; + int ret = 0; + + if (!p_data) + return -EINVAL; + + if (!p_data->this) + p_data->this = devfreq; + switch (event) { case DEVFREQ_GOV_START: - if (!p_data->this) - p_data->this = devfreq; - - nb->notifier_call = devfreq_passive_notifier_call; - ret = devfreq_register_notifier(parent, nb, - DEVFREQ_TRANSITION_NOTIFIER); + if (p_data->parent_type == DEVFREQ_PARENT_DEV) + ret = devfreq_passive_register_notifier(devfreq); + else if (p_data->parent_type == CPUFREQ_PARENT_DEV) + ret = cpufreq_passive_register_notifier(devfreq); break; case DEVFREQ_GOV_STOP: - WARN_ON(devfreq_unregister_notifier(parent, nb, - DEVFREQ_TRANSITION_NOTIFIER)); + if (p_data->parent_type == DEVFREQ_PARENT_DEV) + WARN_ON(devfreq_passive_unregister_notifier(devfreq)); + else if (p_data->parent_type == CPUFREQ_PARENT_DEV) + WARN_ON(cpufreq_passive_unregister_notifier(devfreq)); break; default: break; diff --git a/drivers/devfreq/rk3399_dmc.c b/drivers/devfreq/rk3399_dmc.c index 293857ebfd75..daff40702615 100644 --- a/drivers/devfreq/rk3399_dmc.c +++ b/drivers/devfreq/rk3399_dmc.c @@ -5,6 +5,7 @@ */ #include <linux/arm-smccc.h> +#include <linux/bitfield.h> #include <linux/clk.h> #include <linux/delay.h> #include <linux/devfreq.h> @@ -20,55 +21,49 @@ #include <linux/rwsem.h> #include <linux/suspend.h> +#include <soc/rockchip/pm_domains.h> #include <soc/rockchip/rk3399_grf.h> #include <soc/rockchip/rockchip_sip.h> -struct dram_timing { - unsigned int ddr3_speed_bin; - unsigned int pd_idle; - unsigned int sr_idle; - unsigned int sr_mc_gate_idle; - unsigned int srpd_lite_idle; - unsigned int standby_idle; - unsigned int auto_pd_dis_freq; - unsigned int dram_dll_dis_freq; - unsigned int phy_dll_dis_freq; - unsigned int ddr3_odt_dis_freq; - unsigned int ddr3_drv; - unsigned int ddr3_odt; - unsigned int phy_ddr3_ca_drv; - unsigned int phy_ddr3_dq_drv; - unsigned int phy_ddr3_odt; - unsigned int lpddr3_odt_dis_freq; - unsigned int lpddr3_drv; - unsigned int lpddr3_odt; - unsigned int phy_lpddr3_ca_drv; - unsigned int phy_lpddr3_dq_drv; - unsigned int phy_lpddr3_odt; - unsigned int lpddr4_odt_dis_freq; - unsigned int lpddr4_drv; - unsigned int lpddr4_dq_odt; - unsigned int lpddr4_ca_odt; - unsigned int phy_lpddr4_ca_drv; - unsigned int phy_lpddr4_ck_cs_drv; - unsigned int phy_lpddr4_dq_drv; - unsigned int phy_lpddr4_odt; -}; +#define NS_TO_CYCLE(NS, MHz) (((NS) * (MHz)) / NSEC_PER_USEC) + +#define RK3399_SET_ODT_PD_0_SR_IDLE GENMASK(7, 0) +#define RK3399_SET_ODT_PD_0_SR_MC_GATE_IDLE GENMASK(15, 8) +#define RK3399_SET_ODT_PD_0_STANDBY_IDLE GENMASK(31, 16) + +#define RK3399_SET_ODT_PD_1_PD_IDLE GENMASK(11, 0) +#define RK3399_SET_ODT_PD_1_SRPD_LITE_IDLE GENMASK(27, 16) + +#define RK3399_SET_ODT_PD_2_ODT_ENABLE BIT(0) struct rk3399_dmcfreq { struct device *dev; struct devfreq *devfreq; + struct devfreq_dev_profile profile; struct devfreq_simple_ondemand_data ondemand_data; struct clk *dmc_clk; struct devfreq_event_dev *edev; struct mutex lock; - struct dram_timing timing; struct regulator *vdd_center; struct regmap *regmap_pmu; unsigned long rate, target_rate; unsigned long volt, target_volt; unsigned int odt_dis_freq; - int odt_pd_arg0, odt_pd_arg1; + + unsigned int pd_idle_ns; + unsigned int sr_idle_ns; + unsigned int sr_mc_gate_idle_ns; + unsigned int srpd_lite_idle_ns; + unsigned int standby_idle_ns; + unsigned int ddr3_odt_dis_freq; + unsigned int lpddr3_odt_dis_freq; + unsigned int lpddr4_odt_dis_freq; + + unsigned int pd_idle_dis_freq; + unsigned int sr_idle_dis_freq; + unsigned int sr_mc_gate_idle_dis_freq; + unsigned int srpd_lite_idle_dis_freq; + unsigned int standby_idle_dis_freq; }; static int rk3399_dmcfreq_target(struct device *dev, unsigned long *freq, @@ -78,10 +73,14 @@ static int rk3399_dmcfreq_target(struct device *dev, unsigned long *freq, struct dev_pm_opp *opp; unsigned long old_clk_rate = dmcfreq->rate; unsigned long target_volt, target_rate; + unsigned int ddrcon_mhz; struct arm_smccc_res res; - bool odt_enable = false; int err; + u32 odt_pd_arg0 = 0; + u32 odt_pd_arg1 = 0; + u32 odt_pd_arg2 = 0; + opp = devfreq_recommended_opp(dev, freq, flags); if (IS_ERR(opp)) return PTR_ERR(opp); @@ -95,19 +94,71 @@ static int rk3399_dmcfreq_target(struct device *dev, unsigned long *freq, mutex_lock(&dmcfreq->lock); + /* + * Ensure power-domain transitions don't interfere with ARM Trusted + * Firmware power-domain idling. + */ + err = rockchip_pmu_block(); + if (err) { + dev_err(dev, "Failed to block PMU: %d\n", err); + goto out_unlock; + } + + /* + * Some idle parameters may be based on the DDR controller clock, which + * is half of the DDR frequency. + * pd_idle and standby_idle are based on the controller clock cycle. + * sr_idle_cycle, sr_mc_gate_idle_cycle, and srpd_lite_idle_cycle + * are based on the 1024 controller clock cycle + */ + ddrcon_mhz = target_rate / USEC_PER_SEC / 2; + + u32p_replace_bits(&odt_pd_arg1, + NS_TO_CYCLE(dmcfreq->pd_idle_ns, ddrcon_mhz), + RK3399_SET_ODT_PD_1_PD_IDLE); + u32p_replace_bits(&odt_pd_arg0, + NS_TO_CYCLE(dmcfreq->standby_idle_ns, ddrcon_mhz), + RK3399_SET_ODT_PD_0_STANDBY_IDLE); + u32p_replace_bits(&odt_pd_arg0, + DIV_ROUND_UP(NS_TO_CYCLE(dmcfreq->sr_idle_ns, + ddrcon_mhz), 1024), + RK3399_SET_ODT_PD_0_SR_IDLE); + u32p_replace_bits(&odt_pd_arg0, + DIV_ROUND_UP(NS_TO_CYCLE(dmcfreq->sr_mc_gate_idle_ns, + ddrcon_mhz), 1024), + RK3399_SET_ODT_PD_0_SR_MC_GATE_IDLE); + u32p_replace_bits(&odt_pd_arg1, + DIV_ROUND_UP(NS_TO_CYCLE(dmcfreq->srpd_lite_idle_ns, + ddrcon_mhz), 1024), + RK3399_SET_ODT_PD_1_SRPD_LITE_IDLE); + if (dmcfreq->regmap_pmu) { + if (target_rate >= dmcfreq->sr_idle_dis_freq) + odt_pd_arg0 &= ~RK3399_SET_ODT_PD_0_SR_IDLE; + + if (target_rate >= dmcfreq->sr_mc_gate_idle_dis_freq) + odt_pd_arg0 &= ~RK3399_SET_ODT_PD_0_SR_MC_GATE_IDLE; + + if (target_rate >= dmcfreq->standby_idle_dis_freq) + odt_pd_arg0 &= ~RK3399_SET_ODT_PD_0_STANDBY_IDLE; + + if (target_rate >= dmcfreq->pd_idle_dis_freq) + odt_pd_arg1 &= ~RK3399_SET_ODT_PD_1_PD_IDLE; + + if (target_rate >= dmcfreq->srpd_lite_idle_dis_freq) + odt_pd_arg1 &= ~RK3399_SET_ODT_PD_1_SRPD_LITE_IDLE; + if (target_rate >= dmcfreq->odt_dis_freq) - odt_enable = true; + odt_pd_arg2 |= RK3399_SET_ODT_PD_2_ODT_ENABLE; /* * This makes a SMC call to the TF-A to set the DDR PD * (power-down) timings and to enable or disable the * ODT (on-die termination) resistors. */ - arm_smccc_smc(ROCKCHIP_SIP_DRAM_FREQ, dmcfreq->odt_pd_arg0, - dmcfreq->odt_pd_arg1, - ROCKCHIP_SIP_CONFIG_DRAM_SET_ODT_PD, - odt_enable, 0, 0, 0, &res); + arm_smccc_smc(ROCKCHIP_SIP_DRAM_FREQ, odt_pd_arg0, odt_pd_arg1, + ROCKCHIP_SIP_CONFIG_DRAM_SET_ODT_PD, odt_pd_arg2, + 0, 0, 0, &res); } /* @@ -158,6 +209,8 @@ static int rk3399_dmcfreq_target(struct device *dev, unsigned long *freq, dmcfreq->volt = target_volt; out: + rockchip_pmu_unblock(); +out_unlock: mutex_unlock(&dmcfreq->lock); return err; } @@ -189,13 +242,6 @@ static int rk3399_dmcfreq_get_cur_freq(struct device *dev, unsigned long *freq) return 0; } -static struct devfreq_dev_profile rk3399_devfreq_dmc_profile = { - .polling_ms = 200, - .target = rk3399_dmcfreq_target, - .get_dev_status = rk3399_dmcfreq_get_dev_status, - .get_cur_freq = rk3399_dmcfreq_get_cur_freq, -}; - static __maybe_unused int rk3399_dmcfreq_suspend(struct device *dev) { struct rk3399_dmcfreq *dmcfreq = dev_get_drvdata(dev); @@ -238,69 +284,48 @@ static __maybe_unused int rk3399_dmcfreq_resume(struct device *dev) static SIMPLE_DEV_PM_OPS(rk3399_dmcfreq_pm, rk3399_dmcfreq_suspend, rk3399_dmcfreq_resume); -static int of_get_ddr_timings(struct dram_timing *timing, - struct device_node *np) +static int rk3399_dmcfreq_of_props(struct rk3399_dmcfreq *data, + struct device_node *np) { int ret = 0; - ret = of_property_read_u32(np, "rockchip,ddr3_speed_bin", - &timing->ddr3_speed_bin); - ret |= of_property_read_u32(np, "rockchip,pd_idle", - &timing->pd_idle); - ret |= of_property_read_u32(np, "rockchip,sr_idle", - &timing->sr_idle); - ret |= of_property_read_u32(np, "rockchip,sr_mc_gate_idle", - &timing->sr_mc_gate_idle); - ret |= of_property_read_u32(np, "rockchip,srpd_lite_idle", - &timing->srpd_lite_idle); - ret |= of_property_read_u32(np, "rockchip,standby_idle", - &timing->standby_idle); - ret |= of_property_read_u32(np, "rockchip,auto_pd_dis_freq", - &timing->auto_pd_dis_freq); - ret |= of_property_read_u32(np, "rockchip,dram_dll_dis_freq", - &timing->dram_dll_dis_freq); - ret |= of_property_read_u32(np, "rockchip,phy_dll_dis_freq", - &timing->phy_dll_dis_freq); + /* + * These are all optional, and serve as minimum bounds. Give them large + * (i.e., never "disabled") values if the DT doesn't specify one. + */ + data->pd_idle_dis_freq = + data->sr_idle_dis_freq = + data->sr_mc_gate_idle_dis_freq = + data->srpd_lite_idle_dis_freq = + data->standby_idle_dis_freq = UINT_MAX; + + ret |= of_property_read_u32(np, "rockchip,pd-idle-ns", + &data->pd_idle_ns); + ret |= of_property_read_u32(np, "rockchip,sr-idle-ns", + &data->sr_idle_ns); + ret |= of_property_read_u32(np, "rockchip,sr-mc-gate-idle-ns", + &data->sr_mc_gate_idle_ns); + ret |= of_property_read_u32(np, "rockchip,srpd-lite-idle-ns", + &data->srpd_lite_idle_ns); + ret |= of_property_read_u32(np, "rockchip,standby-idle-ns", + &data->standby_idle_ns); ret |= of_property_read_u32(np, "rockchip,ddr3_odt_dis_freq", - &timing->ddr3_odt_dis_freq); - ret |= of_property_read_u32(np, "rockchip,ddr3_drv", - &timing->ddr3_drv); - ret |= of_property_read_u32(np, "rockchip,ddr3_odt", - &timing->ddr3_odt); - ret |= of_property_read_u32(np, "rockchip,phy_ddr3_ca_drv", - &timing->phy_ddr3_ca_drv); - ret |= of_property_read_u32(np, "rockchip,phy_ddr3_dq_drv", - &timing->phy_ddr3_dq_drv); - ret |= of_property_read_u32(np, "rockchip,phy_ddr3_odt", - &timing->phy_ddr3_odt); + &data->ddr3_odt_dis_freq); ret |= of_property_read_u32(np, "rockchip,lpddr3_odt_dis_freq", - &timing->lpddr3_odt_dis_freq); - ret |= of_property_read_u32(np, "rockchip,lpddr3_drv", - &timing->lpddr3_drv); - ret |= of_property_read_u32(np, "rockchip,lpddr3_odt", - &timing->lpddr3_odt); - ret |= of_property_read_u32(np, "rockchip,phy_lpddr3_ca_drv", - &timing->phy_lpddr3_ca_drv); - ret |= of_property_read_u32(np, "rockchip,phy_lpddr3_dq_drv", - &timing->phy_lpddr3_dq_drv); - ret |= of_property_read_u32(np, "rockchip,phy_lpddr3_odt", - &timing->phy_lpddr3_odt); + &data->lpddr3_odt_dis_freq); ret |= of_property_read_u32(np, "rockchip,lpddr4_odt_dis_freq", - &timing->lpddr4_odt_dis_freq); - ret |= of_property_read_u32(np, "rockchip,lpddr4_drv", - &timing->lpddr4_drv); - ret |= of_property_read_u32(np, "rockchip,lpddr4_dq_odt", - &timing->lpddr4_dq_odt); - ret |= of_property_read_u32(np, "rockchip,lpddr4_ca_odt", - &timing->lpddr4_ca_odt); - ret |= of_property_read_u32(np, "rockchip,phy_lpddr4_ca_drv", - &timing->phy_lpddr4_ca_drv); - ret |= of_property_read_u32(np, "rockchip,phy_lpddr4_ck_cs_drv", - &timing->phy_lpddr4_ck_cs_drv); - ret |= of_property_read_u32(np, "rockchip,phy_lpddr4_dq_drv", - &timing->phy_lpddr4_dq_drv); - ret |= of_property_read_u32(np, "rockchip,phy_lpddr4_odt", - &timing->phy_lpddr4_odt); + &data->lpddr4_odt_dis_freq); + + ret |= of_property_read_u32(np, "rockchip,pd-idle-dis-freq-hz", + &data->pd_idle_dis_freq); + ret |= of_property_read_u32(np, "rockchip,sr-idle-dis-freq-hz", + &data->sr_idle_dis_freq); + ret |= of_property_read_u32(np, "rockchip,sr-mc-gate-idle-dis-freq-hz", + &data->sr_mc_gate_idle_dis_freq); + ret |= of_property_read_u32(np, "rockchip,srpd-lite-idle-dis-freq-hz", + &data->srpd_lite_idle_dis_freq); + ret |= of_property_read_u32(np, "rockchip,standby-idle-dis-freq-hz", + &data->standby_idle_dis_freq); return ret; } @@ -311,8 +336,7 @@ static int rk3399_dmcfreq_probe(struct platform_device *pdev) struct device *dev = &pdev->dev; struct device_node *np = pdev->dev.of_node, *node; struct rk3399_dmcfreq *data; - int ret, index, size; - uint32_t *timing; + int ret; struct dev_pm_opp *opp; u32 ddr_type; u32 val; @@ -343,26 +367,7 @@ static int rk3399_dmcfreq_probe(struct platform_device *pdev) return ret; } - /* - * Get dram timing and pass it to arm trust firmware, - * the dram driver in arm trust firmware will get these - * timing and to do dram initial. - */ - if (!of_get_ddr_timings(&data->timing, np)) { - timing = &data->timing.ddr3_speed_bin; - size = sizeof(struct dram_timing) / 4; - for (index = 0; index < size; index++) { - arm_smccc_smc(ROCKCHIP_SIP_DRAM_FREQ, *timing++, index, - ROCKCHIP_SIP_CONFIG_DRAM_SET_PARAM, - 0, 0, 0, 0, &res); - if (res.a0) { - dev_err(dev, "Failed to set dram param: %ld\n", - res.a0); - ret = -EINVAL; - goto err_edev; - } - } - } + rk3399_dmcfreq_of_props(data, np); node = of_parse_phandle(np, "rockchip,pmu", 0); if (!node) @@ -381,13 +386,13 @@ static int rk3399_dmcfreq_probe(struct platform_device *pdev) switch (ddr_type) { case RK3399_PMUGRF_DDRTYPE_DDR3: - data->odt_dis_freq = data->timing.ddr3_odt_dis_freq; + data->odt_dis_freq = data->ddr3_odt_dis_freq; break; case RK3399_PMUGRF_DDRTYPE_LPDDR3: - data->odt_dis_freq = data->timing.lpddr3_odt_dis_freq; + data->odt_dis_freq = data->lpddr3_odt_dis_freq; break; case RK3399_PMUGRF_DDRTYPE_LPDDR4: - data->odt_dis_freq = data->timing.lpddr4_odt_dis_freq; + data->odt_dis_freq = data->lpddr4_odt_dis_freq; break; default: ret = -EINVAL; @@ -400,62 +405,45 @@ no_pmu: 0, 0, 0, 0, &res); /* - * In TF-A there is a platform SIP call to set the PD (power-down) - * timings and to enable or disable the ODT (on-die termination). - * This call needs three arguments as follows: - * - * arg0: - * bit[0-7] : sr_idle - * bit[8-15] : sr_mc_gate_idle - * bit[16-31] : standby idle - * arg1: - * bit[0-11] : pd_idle - * bit[16-27] : srpd_lite_idle - * arg2: - * bit[0] : odt enable - */ - data->odt_pd_arg0 = (data->timing.sr_idle & 0xff) | - ((data->timing.sr_mc_gate_idle & 0xff) << 8) | - ((data->timing.standby_idle & 0xffff) << 16); - data->odt_pd_arg1 = (data->timing.pd_idle & 0xfff) | - ((data->timing.srpd_lite_idle & 0xfff) << 16); - - /* * We add a devfreq driver to our parent since it has a device tree node * with operating points. */ - if (dev_pm_opp_of_add_table(dev)) { + if (devm_pm_opp_of_add_table(dev)) { dev_err(dev, "Invalid operating-points in device tree.\n"); ret = -EINVAL; goto err_edev; } - of_property_read_u32(np, "upthreshold", - &data->ondemand_data.upthreshold); - of_property_read_u32(np, "downdifferential", - &data->ondemand_data.downdifferential); + data->ondemand_data.upthreshold = 25; + data->ondemand_data.downdifferential = 15; data->rate = clk_get_rate(data->dmc_clk); opp = devfreq_recommended_opp(dev, &data->rate, 0); if (IS_ERR(opp)) { ret = PTR_ERR(opp); - goto err_free_opp; + goto err_edev; } data->rate = dev_pm_opp_get_freq(opp); data->volt = dev_pm_opp_get_voltage(opp); dev_pm_opp_put(opp); - rk3399_devfreq_dmc_profile.initial_freq = data->rate; + data->profile = (struct devfreq_dev_profile) { + .polling_ms = 200, + .target = rk3399_dmcfreq_target, + .get_dev_status = rk3399_dmcfreq_get_dev_status, + .get_cur_freq = rk3399_dmcfreq_get_cur_freq, + .initial_freq = data->rate, + }; data->devfreq = devm_devfreq_add_device(dev, - &rk3399_devfreq_dmc_profile, + &data->profile, DEVFREQ_GOV_SIMPLE_ONDEMAND, &data->ondemand_data); if (IS_ERR(data->devfreq)) { ret = PTR_ERR(data->devfreq); - goto err_free_opp; + goto err_edev; } devm_devfreq_register_opp_notifier(dev, data->devfreq); @@ -465,8 +453,6 @@ no_pmu: return 0; -err_free_opp: - dev_pm_opp_of_remove_table(&pdev->dev); err_edev: devfreq_event_disable_edev(data->edev); @@ -477,11 +463,7 @@ static int rk3399_dmcfreq_remove(struct platform_device *pdev) { struct rk3399_dmcfreq *dmcfreq = dev_get_drvdata(&pdev->dev); - /* - * Before remove the opp table we need to unregister the opp notifier. - */ - devm_devfreq_unregister_opp_notifier(dmcfreq->dev, dmcfreq->devfreq); - dev_pm_opp_of_remove_table(dmcfreq->dev); + devfreq_event_disable_edev(dmcfreq->edev); return 0; } diff --git a/drivers/dma-buf/Makefile b/drivers/dma-buf/Makefile index 511805dbeb75..4c9eb53ba3f8 100644 --- a/drivers/dma-buf/Makefile +++ b/drivers/dma-buf/Makefile @@ -12,6 +12,7 @@ dmabuf_selftests-y := \ selftest.o \ st-dma-fence.o \ st-dma-fence-chain.o \ + st-dma-fence-unwrap.o \ st-dma-resv.o obj-$(CONFIG_DMABUF_SELFTESTS) += dmabuf_selftests.o diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index df23239b04fc..53297a0d9c57 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -407,6 +407,7 @@ static inline int is_dma_buf_file(struct file *file) static struct file *dma_buf_getfile(struct dma_buf *dmabuf, int flags) { + static atomic64_t dmabuf_inode = ATOMIC64_INIT(0); struct file *file; struct inode *inode = alloc_anon_inode(dma_buf_mnt->mnt_sb); @@ -416,6 +417,13 @@ static struct file *dma_buf_getfile(struct dma_buf *dmabuf, int flags) inode->i_size = dmabuf->size; inode_set_bytes(inode, dmabuf->size); + /* + * The ->i_ino acquired from get_next_ino() is not unique thus + * not suitable for using it as dentry name by dmabuf stats. + * Override ->i_ino with the unique and dmabuffs specific + * value. + */ + inode->i_ino = atomic64_add_return(1, &dmabuf_inode); file = alloc_file_pseudo(inode, dma_buf_mnt, "dmabuf", flags, &dma_buf_fops); if (IS_ERR(file)) @@ -543,10 +551,6 @@ struct dma_buf *dma_buf_export(const struct dma_buf_export_info *exp_info) file->f_mode |= FMODE_LSEEK; dmabuf->file = file; - ret = dma_buf_stats_setup(dmabuf); - if (ret) - goto err_sysfs; - mutex_init(&dmabuf->lock); INIT_LIST_HEAD(&dmabuf->attachments); @@ -554,6 +558,10 @@ struct dma_buf *dma_buf_export(const struct dma_buf_export_info *exp_info) list_add(&dmabuf->list_node, &db_list.head); mutex_unlock(&db_list.lock); + ret = dma_buf_stats_setup(dmabuf); + if (ret) + goto err_sysfs; + return dmabuf; err_sysfs: diff --git a/drivers/dma-buf/dma-fence-array.c b/drivers/dma-buf/dma-fence-array.c index cb1bacb5a42b..5c8a7084577b 100644 --- a/drivers/dma-buf/dma-fence-array.c +++ b/drivers/dma-buf/dma-fence-array.c @@ -159,6 +159,8 @@ struct dma_fence_array *dma_fence_array_create(int num_fences, struct dma_fence_array *array; size_t size = sizeof(*array); + WARN_ON(!num_fences || !fences); + /* Allocate the callback structures behind the array. */ size += num_fences * sizeof(struct dma_fence_array_cb); array = kzalloc(size, GFP_KERNEL); @@ -219,3 +221,33 @@ bool dma_fence_match_context(struct dma_fence *fence, u64 context) return true; } EXPORT_SYMBOL(dma_fence_match_context); + +struct dma_fence *dma_fence_array_first(struct dma_fence *head) +{ + struct dma_fence_array *array; + + if (!head) + return NULL; + + array = to_dma_fence_array(head); + if (!array) + return head; + + if (!array->num_fences) + return NULL; + + return array->fences[0]; +} +EXPORT_SYMBOL(dma_fence_array_first); + +struct dma_fence *dma_fence_array_next(struct dma_fence *head, + unsigned int index) +{ + struct dma_fence_array *array = to_dma_fence_array(head); + + if (!array || index >= array->num_fences) + return NULL; + + return array->fences[index]; +} +EXPORT_SYMBOL(dma_fence_array_next); diff --git a/drivers/dma-buf/selftests.h b/drivers/dma-buf/selftests.h index 97d73aaa31da..851965867d9c 100644 --- a/drivers/dma-buf/selftests.h +++ b/drivers/dma-buf/selftests.h @@ -12,4 +12,5 @@ selftest(sanitycheck, __sanitycheck__) /* keep first (igt selfcheck) */ selftest(dma_fence, dma_fence) selftest(dma_fence_chain, dma_fence_chain) +selftest(dma_fence_unwrap, dma_fence_unwrap) selftest(dma_resv, dma_resv) diff --git a/drivers/dma-buf/st-dma-fence-unwrap.c b/drivers/dma-buf/st-dma-fence-unwrap.c new file mode 100644 index 000000000000..039f016b57be --- /dev/null +++ b/drivers/dma-buf/st-dma-fence-unwrap.c @@ -0,0 +1,261 @@ +// SPDX-License-Identifier: MIT + +/* + * Copyright (C) 2022 Advanced Micro Devices, Inc. + */ + +#include <linux/dma-fence-unwrap.h> +#if 0 +#include <linux/kernel.h> +#include <linux/kthread.h> +#include <linux/mm.h> +#include <linux/sched/signal.h> +#include <linux/slab.h> +#include <linux/spinlock.h> +#include <linux/random.h> +#endif + +#include "selftest.h" + +#define CHAIN_SZ (4 << 10) + +static inline struct mock_fence { + struct dma_fence base; + spinlock_t lock; +} *to_mock_fence(struct dma_fence *f) { + return container_of(f, struct mock_fence, base); +} + +static const char *mock_name(struct dma_fence *f) +{ + return "mock"; +} + +static const struct dma_fence_ops mock_ops = { + .get_driver_name = mock_name, + .get_timeline_name = mock_name, +}; + +static struct dma_fence *mock_fence(void) +{ + struct mock_fence *f; + + f = kmalloc(sizeof(*f), GFP_KERNEL); + if (!f) + return NULL; + + spin_lock_init(&f->lock); + dma_fence_init(&f->base, &mock_ops, &f->lock, 0, 0); + + return &f->base; +} + +static struct dma_fence *mock_array(unsigned int num_fences, ...) +{ + struct dma_fence_array *array; + struct dma_fence **fences; + va_list valist; + int i; + + fences = kcalloc(num_fences, sizeof(*fences), GFP_KERNEL); + if (!fences) + return NULL; + + va_start(valist, num_fences); + for (i = 0; i < num_fences; ++i) + fences[i] = va_arg(valist, typeof(*fences)); + va_end(valist); + + array = dma_fence_array_create(num_fences, fences, + dma_fence_context_alloc(1), + 1, false); + if (!array) + goto cleanup; + return &array->base; + +cleanup: + for (i = 0; i < num_fences; ++i) + dma_fence_put(fences[i]); + kfree(fences); + return NULL; +} + +static struct dma_fence *mock_chain(struct dma_fence *prev, + struct dma_fence *fence) +{ + struct dma_fence_chain *f; + + f = dma_fence_chain_alloc(); + if (!f) { + dma_fence_put(prev); + dma_fence_put(fence); + return NULL; + } + + dma_fence_chain_init(f, prev, fence, 1); + return &f->base; +} + +static int sanitycheck(void *arg) +{ + struct dma_fence *f, *chain, *array; + int err = 0; + + f = mock_fence(); + if (!f) + return -ENOMEM; + + array = mock_array(1, f); + if (!array) + return -ENOMEM; + + chain = mock_chain(NULL, array); + if (!chain) + return -ENOMEM; + + dma_fence_signal(f); + dma_fence_put(chain); + return err; +} + +static int unwrap_array(void *arg) +{ + struct dma_fence *fence, *f1, *f2, *array; + struct dma_fence_unwrap iter; + int err = 0; + + f1 = mock_fence(); + if (!f1) + return -ENOMEM; + + f2 = mock_fence(); + if (!f2) { + dma_fence_put(f1); + return -ENOMEM; + } + + array = mock_array(2, f1, f2); + if (!array) + return -ENOMEM; + + dma_fence_unwrap_for_each(fence, &iter, array) { + if (fence == f1) { + f1 = NULL; + } else if (fence == f2) { + f2 = NULL; + } else { + pr_err("Unexpected fence!\n"); + err = -EINVAL; + } + } + + if (f1 || f2) { + pr_err("Not all fences seen!\n"); + err = -EINVAL; + } + + dma_fence_signal(f1); + dma_fence_signal(f2); + dma_fence_put(array); + return 0; +} + +static int unwrap_chain(void *arg) +{ + struct dma_fence *fence, *f1, *f2, *chain; + struct dma_fence_unwrap iter; + int err = 0; + + f1 = mock_fence(); + if (!f1) + return -ENOMEM; + + f2 = mock_fence(); + if (!f2) { + dma_fence_put(f1); + return -ENOMEM; + } + + chain = mock_chain(f1, f2); + if (!chain) + return -ENOMEM; + + dma_fence_unwrap_for_each(fence, &iter, chain) { + if (fence == f1) { + f1 = NULL; + } else if (fence == f2) { + f2 = NULL; + } else { + pr_err("Unexpected fence!\n"); + err = -EINVAL; + } + } + + if (f1 || f2) { + pr_err("Not all fences seen!\n"); + err = -EINVAL; + } + + dma_fence_signal(f1); + dma_fence_signal(f2); + dma_fence_put(chain); + return 0; +} + +static int unwrap_chain_array(void *arg) +{ + struct dma_fence *fence, *f1, *f2, *array, *chain; + struct dma_fence_unwrap iter; + int err = 0; + + f1 = mock_fence(); + if (!f1) + return -ENOMEM; + + f2 = mock_fence(); + if (!f2) { + dma_fence_put(f1); + return -ENOMEM; + } + + array = mock_array(2, f1, f2); + if (!array) + return -ENOMEM; + + chain = mock_chain(NULL, array); + if (!chain) + return -ENOMEM; + + dma_fence_unwrap_for_each(fence, &iter, chain) { + if (fence == f1) { + f1 = NULL; + } else if (fence == f2) { + f2 = NULL; + } else { + pr_err("Unexpected fence!\n"); + err = -EINVAL; + } + } + + if (f1 || f2) { + pr_err("Not all fences seen!\n"); + err = -EINVAL; + } + + dma_fence_signal(f1); + dma_fence_signal(f2); + dma_fence_put(chain); + return 0; +} + +int dma_fence_unwrap(void) +{ + static const struct subtest tests[] = { + SUBTEST(sanitycheck), + SUBTEST(unwrap_array), + SUBTEST(unwrap_chain), + SUBTEST(unwrap_chain_array), + }; + + return subtests(tests, NULL); +} diff --git a/drivers/dma-buf/sync_file.c b/drivers/dma-buf/sync_file.c index 394e6e1e9686..514d213261df 100644 --- a/drivers/dma-buf/sync_file.c +++ b/drivers/dma-buf/sync_file.c @@ -5,6 +5,7 @@ * Copyright (C) 2012 Google, Inc. */ +#include <linux/dma-fence-unwrap.h> #include <linux/export.h> #include <linux/file.h> #include <linux/fs.h> @@ -172,20 +173,6 @@ static int sync_file_set_fence(struct sync_file *sync_file, return 0; } -static struct dma_fence **get_fences(struct sync_file *sync_file, - int *num_fences) -{ - if (dma_fence_is_array(sync_file->fence)) { - struct dma_fence_array *array = to_dma_fence_array(sync_file->fence); - - *num_fences = array->num_fences; - return array->fences; - } - - *num_fences = 1; - return &sync_file->fence; -} - static void add_fence(struct dma_fence **fences, int *i, struct dma_fence *fence) { @@ -210,86 +197,97 @@ static void add_fence(struct dma_fence **fences, static struct sync_file *sync_file_merge(const char *name, struct sync_file *a, struct sync_file *b) { + struct dma_fence *a_fence, *b_fence, **fences; + struct dma_fence_unwrap a_iter, b_iter; + unsigned int index, num_fences; struct sync_file *sync_file; - struct dma_fence **fences = NULL, **nfences, **a_fences, **b_fences; - int i = 0, i_a, i_b, num_fences, a_num_fences, b_num_fences; sync_file = sync_file_alloc(); if (!sync_file) return NULL; - a_fences = get_fences(a, &a_num_fences); - b_fences = get_fences(b, &b_num_fences); - if (a_num_fences > INT_MAX - b_num_fences) - goto err; + num_fences = 0; + dma_fence_unwrap_for_each(a_fence, &a_iter, a->fence) + ++num_fences; + dma_fence_unwrap_for_each(b_fence, &b_iter, b->fence) + ++num_fences; - num_fences = a_num_fences + b_num_fences; + if (num_fences > INT_MAX) + goto err_free_sync_file; fences = kcalloc(num_fences, sizeof(*fences), GFP_KERNEL); if (!fences) - goto err; + goto err_free_sync_file; /* - * Assume sync_file a and b are both ordered and have no - * duplicates with the same context. + * We can't guarantee that fences in both a and b are ordered, but it is + * still quite likely. * - * If a sync_file can only be created with sync_file_merge - * and sync_file_create, this is a reasonable assumption. + * So attempt to order the fences as we pass over them and merge fences + * with the same context. */ - for (i_a = i_b = 0; i_a < a_num_fences && i_b < b_num_fences; ) { - struct dma_fence *pt_a = a_fences[i_a]; - struct dma_fence *pt_b = b_fences[i_b]; - if (pt_a->context < pt_b->context) { - add_fence(fences, &i, pt_a); + index = 0; + for (a_fence = dma_fence_unwrap_first(a->fence, &a_iter), + b_fence = dma_fence_unwrap_first(b->fence, &b_iter); + a_fence || b_fence; ) { + + if (!b_fence) { + add_fence(fences, &index, a_fence); + a_fence = dma_fence_unwrap_next(&a_iter); + + } else if (!a_fence) { + add_fence(fences, &index, b_fence); + b_fence = dma_fence_unwrap_next(&b_iter); + + } else if (a_fence->context < b_fence->context) { + add_fence(fences, &index, a_fence); + a_fence = dma_fence_unwrap_next(&a_iter); - i_a++; - } else if (pt_a->context > pt_b->context) { - add_fence(fences, &i, pt_b); + } else if (b_fence->context < a_fence->context) { + add_fence(fences, &index, b_fence); + b_fence = dma_fence_unwrap_next(&b_iter); + + } else if (__dma_fence_is_later(a_fence->seqno, b_fence->seqno, + a_fence->ops)) { + add_fence(fences, &index, a_fence); + a_fence = dma_fence_unwrap_next(&a_iter); + b_fence = dma_fence_unwrap_next(&b_iter); - i_b++; } else { - if (__dma_fence_is_later(pt_a->seqno, pt_b->seqno, - pt_a->ops)) - add_fence(fences, &i, pt_a); - else - add_fence(fences, &i, pt_b); - - i_a++; - i_b++; + add_fence(fences, &index, b_fence); + a_fence = dma_fence_unwrap_next(&a_iter); + b_fence = dma_fence_unwrap_next(&b_iter); } } - for (; i_a < a_num_fences; i_a++) - add_fence(fences, &i, a_fences[i_a]); - - for (; i_b < b_num_fences; i_b++) - add_fence(fences, &i, b_fences[i_b]); - - if (i == 0) - fences[i++] = dma_fence_get(a_fences[0]); + if (index == 0) + fences[index++] = dma_fence_get_stub(); - if (num_fences > i) { - nfences = krealloc_array(fences, i, sizeof(*fences), GFP_KERNEL); - if (!nfences) - goto err; + if (num_fences > index) { + struct dma_fence **tmp; - fences = nfences; + /* Keep going even when reducing the size failed */ + tmp = krealloc_array(fences, index, sizeof(*fences), + GFP_KERNEL); + if (tmp) + fences = tmp; } - if (sync_file_set_fence(sync_file, fences, i) < 0) - goto err; + if (sync_file_set_fence(sync_file, fences, index) < 0) + goto err_put_fences; strlcpy(sync_file->user_name, name, sizeof(sync_file->user_name)); return sync_file; -err: - while (i) - dma_fence_put(fences[--i]); +err_put_fences: + while (index) + dma_fence_put(fences[--index]); kfree(fences); + +err_free_sync_file: fput(sync_file->file); return NULL; - } static int sync_file_release(struct inode *inode, struct file *file) @@ -398,11 +396,13 @@ static int sync_fill_fence_info(struct dma_fence *fence, static long sync_file_ioctl_fence_info(struct sync_file *sync_file, unsigned long arg) { - struct sync_file_info info; struct sync_fence_info *fence_info = NULL; - struct dma_fence **fences; + struct dma_fence_unwrap iter; + struct sync_file_info info; + unsigned int num_fences; + struct dma_fence *fence; + int ret; __u32 size; - int num_fences, ret, i; if (copy_from_user(&info, (void __user *)arg, sizeof(info))) return -EFAULT; @@ -410,7 +410,9 @@ static long sync_file_ioctl_fence_info(struct sync_file *sync_file, if (info.flags || info.pad) return -EINVAL; - fences = get_fences(sync_file, &num_fences); + num_fences = 0; + dma_fence_unwrap_for_each(fence, &iter, sync_file->fence) + ++num_fences; /* * Passing num_fences = 0 means that userspace doesn't want to @@ -433,8 +435,11 @@ static long sync_file_ioctl_fence_info(struct sync_file *sync_file, if (!fence_info) return -ENOMEM; - for (i = 0; i < num_fences; i++) { - int status = sync_fill_fence_info(fences[i], &fence_info[i]); + num_fences = 0; + dma_fence_unwrap_for_each(fence, &iter, sync_file->fence) { + int status; + + status = sync_fill_fence_info(fence, &fence_info[num_fences++]); info.status = info.status <= 0 ? info.status : status; } diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c index 1476156af74b..def564d1e8fa 100644 --- a/drivers/dma/at_xdmac.c +++ b/drivers/dma/at_xdmac.c @@ -1453,7 +1453,7 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie, { struct at_xdmac_chan *atchan = to_at_xdmac_chan(chan); struct at_xdmac *atxdmac = to_at_xdmac(atchan->chan.device); - struct at_xdmac_desc *desc, *_desc; + struct at_xdmac_desc *desc, *_desc, *iter; struct list_head *descs_list; enum dma_status ret; int residue, retry; @@ -1568,11 +1568,13 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie, * microblock. */ descs_list = &desc->descs_list; - list_for_each_entry_safe(desc, _desc, descs_list, desc_node) { - dwidth = at_xdmac_get_dwidth(desc->lld.mbr_cfg); - residue -= (desc->lld.mbr_ubc & 0xffffff) << dwidth; - if ((desc->lld.mbr_nda & 0xfffffffc) == cur_nda) + list_for_each_entry_safe(iter, _desc, descs_list, desc_node) { + dwidth = at_xdmac_get_dwidth(iter->lld.mbr_cfg); + residue -= (iter->lld.mbr_ubc & 0xffffff) << dwidth; + if ((iter->lld.mbr_nda & 0xfffffffc) == cur_nda) { + desc = iter; break; + } } residue += cur_ubc << dwidth; diff --git a/drivers/dma/dw-edma/dw-edma-v0-core.c b/drivers/dma/dw-edma/dw-edma-v0-core.c index 329fc2e57b70..33bc1e6c4cf2 100644 --- a/drivers/dma/dw-edma/dw-edma-v0-core.c +++ b/drivers/dma/dw-edma/dw-edma-v0-core.c @@ -414,14 +414,18 @@ void dw_edma_v0_core_start(struct dw_edma_chunk *chunk, bool first) SET_CH_32(dw, chan->dir, chan->id, ch_control1, (DW_EDMA_V0_CCS | DW_EDMA_V0_LLE)); /* Linked list */ + #ifdef CONFIG_64BIT - SET_CH_64(dw, chan->dir, chan->id, llp.reg, - chunk->ll_region.paddr); + /* llp is not aligned on 64bit -> keep 32bit accesses */ + SET_CH_32(dw, chan->dir, chan->id, llp.lsb, + lower_32_bits(chunk->ll_region.paddr)); + SET_CH_32(dw, chan->dir, chan->id, llp.msb, + upper_32_bits(chunk->ll_region.paddr)); #else /* CONFIG_64BIT */ - SET_CH_32(dw, chan->dir, chan->id, llp.lsb, - lower_32_bits(chunk->ll_region.paddr)); - SET_CH_32(dw, chan->dir, chan->id, llp.msb, - upper_32_bits(chunk->ll_region.paddr)); + SET_CH_32(dw, chan->dir, chan->id, llp.lsb, + lower_32_bits(chunk->ll_region.paddr)); + SET_CH_32(dw, chan->dir, chan->id, llp.msb, + upper_32_bits(chunk->ll_region.paddr)); #endif /* CONFIG_64BIT */ } /* Doorbell */ diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c index 3061fe857d69..f652da6ab47d 100644 --- a/drivers/dma/idxd/device.c +++ b/drivers/dma/idxd/device.c @@ -373,7 +373,6 @@ static void idxd_wq_device_reset_cleanup(struct idxd_wq *wq) { lockdep_assert_held(&wq->wq_lock); - idxd_wq_disable_cleanup(wq); wq->size = 0; wq->group = NULL; } @@ -701,14 +700,17 @@ static void idxd_device_wqs_clear_state(struct idxd_device *idxd) if (wq->state == IDXD_WQ_ENABLED) { idxd_wq_disable_cleanup(wq); - idxd_wq_device_reset_cleanup(wq); wq->state = IDXD_WQ_DISABLED; } + idxd_wq_device_reset_cleanup(wq); } } void idxd_device_clear_state(struct idxd_device *idxd) { + if (!test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags)) + return; + idxd_groups_clear_state(idxd); idxd_engines_clear_state(idxd); idxd_device_wqs_clear_state(idxd); diff --git a/drivers/dma/idxd/submit.c b/drivers/dma/idxd/submit.c index e289fd48711a..c01db23e3333 100644 --- a/drivers/dma/idxd/submit.c +++ b/drivers/dma/idxd/submit.c @@ -150,14 +150,15 @@ static void llist_abort_desc(struct idxd_wq *wq, struct idxd_irq_entry *ie, */ int idxd_enqcmds(struct idxd_wq *wq, void __iomem *portal, const void *desc) { - int rc, retries = 0; + unsigned int retries = wq->enqcmds_retries; + int rc; do { rc = enqcmds(portal, desc); if (rc == 0) break; cpu_relax(); - } while (retries++ < wq->enqcmds_retries); + } while (retries--); return rc; } diff --git a/drivers/dma/idxd/sysfs.c b/drivers/dma/idxd/sysfs.c index 7e19ab92b61a..dfd549685c46 100644 --- a/drivers/dma/idxd/sysfs.c +++ b/drivers/dma/idxd/sysfs.c @@ -905,6 +905,9 @@ static ssize_t wq_max_transfer_size_store(struct device *dev, struct device_attr u64 xfer_size; int rc; + if (!test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags)) + return -EPERM; + if (wq->state != IDXD_WQ_DISABLED) return -EPERM; @@ -939,6 +942,9 @@ static ssize_t wq_max_batch_size_store(struct device *dev, struct device_attribu u64 batch_size; int rc; + if (!test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags)) + return -EPERM; + if (wq->state != IDXD_WQ_DISABLED) return -EPERM; diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c index 70c0aa931ddf..6196a7b3956b 100644 --- a/drivers/dma/imx-sdma.c +++ b/drivers/dma/imx-sdma.c @@ -198,12 +198,12 @@ struct sdma_script_start_addrs { s32 per_2_firi_addr; s32 mcu_2_firi_addr; s32 uart_2_per_addr; - s32 uart_2_mcu_ram_addr; + s32 uart_2_mcu_addr; s32 per_2_app_addr; s32 mcu_2_app_addr; s32 per_2_per_addr; s32 uartsh_2_per_addr; - s32 uartsh_2_mcu_ram_addr; + s32 uartsh_2_mcu_addr; s32 per_2_shp_addr; s32 mcu_2_shp_addr; s32 ata_2_mcu_addr; @@ -232,8 +232,8 @@ struct sdma_script_start_addrs { s32 mcu_2_ecspi_addr; s32 mcu_2_sai_addr; s32 sai_2_mcu_addr; - s32 uart_2_mcu_addr; - s32 uartsh_2_mcu_addr; + s32 uart_2_mcu_rom_addr; + s32 uartsh_2_mcu_rom_addr; /* End of v3 array */ s32 mcu_2_zqspi_addr; /* End of v4 array */ @@ -1796,17 +1796,17 @@ static void sdma_add_scripts(struct sdma_engine *sdma, saddr_arr[i] = addr_arr[i]; /* - * get uart_2_mcu_addr/uartsh_2_mcu_addr rom script specially because - * they are now replaced by uart_2_mcu_ram_addr/uartsh_2_mcu_ram_addr - * to be compatible with legacy freescale/nxp sdma firmware, and they - * are located in the bottom part of sdma_script_start_addrs which are - * beyond the SDMA_SCRIPT_ADDRS_ARRAY_SIZE_V1. + * For compatibility with NXP internal legacy kernel before 4.19 which + * is based on uart ram script and mainline kernel based on uart rom + * script, both uart ram/rom scripts are present in newer sdma + * firmware. Use the rom versions if they are present (V3 or newer). */ - if (addr->uart_2_mcu_addr) - sdma->script_addrs->uart_2_mcu_addr = addr->uart_2_mcu_addr; - if (addr->uartsh_2_mcu_addr) - sdma->script_addrs->uartsh_2_mcu_addr = addr->uartsh_2_mcu_addr; - + if (sdma->script_number >= SDMA_SCRIPT_ADDRS_ARRAY_SIZE_V3) { + if (addr->uart_2_mcu_rom_addr) + sdma->script_addrs->uart_2_mcu_addr = addr->uart_2_mcu_rom_addr; + if (addr->uartsh_2_mcu_rom_addr) + sdma->script_addrs->uartsh_2_mcu_addr = addr->uartsh_2_mcu_rom_addr; + } } static void sdma_load_firmware(const struct firmware *fw, void *context) @@ -1885,7 +1885,7 @@ static int sdma_event_remap(struct sdma_engine *sdma) u32 reg, val, shift, num_map, i; int ret = 0; - if (IS_ERR(np) || IS_ERR(gpr_np)) + if (IS_ERR(np) || !gpr_np) goto out; event_remap = of_find_property(np, propname, NULL); @@ -1933,7 +1933,7 @@ static int sdma_event_remap(struct sdma_engine *sdma) } out: - if (!IS_ERR(gpr_np)) + if (gpr_np) of_node_put(gpr_np); return ret; diff --git a/drivers/dma/mediatek/mtk-uart-apdma.c b/drivers/dma/mediatek/mtk-uart-apdma.c index 375e7e647df6..a1517ef1f4a0 100644 --- a/drivers/dma/mediatek/mtk-uart-apdma.c +++ b/drivers/dma/mediatek/mtk-uart-apdma.c @@ -274,7 +274,7 @@ static int mtk_uart_apdma_alloc_chan_resources(struct dma_chan *chan) unsigned int status; int ret; - ret = pm_runtime_get_sync(mtkd->ddev.dev); + ret = pm_runtime_resume_and_get(mtkd->ddev.dev); if (ret < 0) { pm_runtime_put_noidle(chan->device->dev); return ret; @@ -288,18 +288,21 @@ static int mtk_uart_apdma_alloc_chan_resources(struct dma_chan *chan) ret = readx_poll_timeout(readl, c->base + VFF_EN, status, !status, 10, 100); if (ret) - return ret; + goto err_pm; ret = request_irq(c->irq, mtk_uart_apdma_irq_handler, IRQF_TRIGGER_NONE, KBUILD_MODNAME, chan); if (ret < 0) { dev_err(chan->device->dev, "Can't request dma IRQ\n"); - return -EINVAL; + ret = -EINVAL; + goto err_pm; } if (mtkd->support_33bits) mtk_uart_apdma_write(c, VFF_4G_SUPPORT, VFF_4G_SUPPORT_CLR_B); +err_pm: + pm_runtime_put_noidle(mtkd->ddev.dev); return ret; } diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig index 58ab63642e72..d3e2477948c8 100644 --- a/drivers/edac/Kconfig +++ b/drivers/edac/Kconfig @@ -55,6 +55,7 @@ config EDAC_DECODE_MCE config EDAC_GHES bool "Output ACPI APEI/GHES BIOS detected errors via EDAC" depends on ACPI_APEI_GHES && (EDAC=y) + select UEFI_CPER help Not all machines support hardware-driven error report. Some of those provide a BIOS-driven error report mechanism via ACPI, using the @@ -484,7 +485,7 @@ config EDAC_ARMADA_XP config EDAC_SYNOPSYS tristate "Synopsys DDR Memory Controller" - depends on ARCH_ZYNQ || ARCH_ZYNQMP || ARCH_INTEL_SOCFPGA + depends on ARCH_ZYNQ || ARCH_ZYNQMP || ARCH_INTEL_SOCFPGA || ARCH_MXC help Support for error detection and correction on the Synopsys DDR memory controller. diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c index 812baa48b290..2f854feeeb23 100644 --- a/drivers/edac/amd64_edac.c +++ b/drivers/edac/amd64_edac.c @@ -4336,7 +4336,7 @@ static int __init amd64_edac_init(void) if (!x86_match_cpu(amd64_cpuids)) return -ENODEV; - if (amd_cache_northbridges() < 0) + if (!amd_nb_num()) return -ENODEV; opstate_init(); diff --git a/drivers/edac/armada_xp_edac.c b/drivers/edac/armada_xp_edac.c index b1f46a974b9e..038abbb83f4b 100644 --- a/drivers/edac/armada_xp_edac.c +++ b/drivers/edac/armada_xp_edac.c @@ -286,17 +286,10 @@ static int axp_mc_probe(struct platform_device *pdev) struct edac_mc_layer layers[1]; const struct of_device_id *id; struct mem_ctl_info *mci; - struct resource *r; void __iomem *base; uint32_t config; - r = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (!r) { - dev_err(&pdev->dev, "Unable to get mem resource\n"); - return -ENODEV; - } - - base = devm_ioremap_resource(&pdev->dev, r); + base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(base)) { dev_err(&pdev->dev, "Unable to map regs\n"); return PTR_ERR(base); @@ -516,15 +509,8 @@ static int aurora_l2_probe(struct platform_device *pdev) const struct of_device_id *id; uint32_t l2x0_aux_ctrl; void __iomem *base; - struct resource *r; - - r = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (!r) { - dev_err(&pdev->dev, "Unable to get mem resource\n"); - return -ENODEV; - } - base = devm_ioremap_resource(&pdev->dev, r); + base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(base)) { dev_err(&pdev->dev, "Unable to map regs\n"); return PTR_ERR(base); diff --git a/drivers/edac/dmc520_edac.c b/drivers/edac/dmc520_edac.c index b8a7d9594afd..1fa5ca57e9ec 100644 --- a/drivers/edac/dmc520_edac.c +++ b/drivers/edac/dmc520_edac.c @@ -489,7 +489,7 @@ static int dmc520_edac_probe(struct platform_device *pdev) dev = &pdev->dev; for (idx = 0; idx < NUMBER_OF_IRQS; idx++) { - irq = platform_get_irq_byname(pdev, dmc520_irq_configs[idx].name); + irq = platform_get_irq_byname_optional(pdev, dmc520_irq_configs[idx].name); irqs[idx] = irq; masks[idx] = dmc520_irq_configs[idx].mask; if (irq >= 0) { diff --git a/drivers/edac/edac_device.c b/drivers/edac/edac_device.c index 8c4d947fb848..19522c568aa5 100644 --- a/drivers/edac/edac_device.c +++ b/drivers/edac/edac_device.c @@ -47,99 +47,67 @@ static void edac_device_dump_device(struct edac_device_ctl_info *edac_dev) } #endif /* CONFIG_EDAC_DEBUG */ -struct edac_device_ctl_info *edac_device_alloc_ctl_info( - unsigned sz_private, - char *edac_device_name, unsigned nr_instances, - char *edac_block_name, unsigned nr_blocks, - unsigned offset_value, /* zero, 1, or other based offset */ - struct edac_dev_sysfs_block_attribute *attrib_spec, unsigned nr_attrib, - int device_index) +/* + * @off_val: zero, 1, or other based offset + */ +struct edac_device_ctl_info * +edac_device_alloc_ctl_info(unsigned pvt_sz, char *dev_name, unsigned nr_instances, + char *blk_name, unsigned nr_blocks, unsigned off_val, + struct edac_dev_sysfs_block_attribute *attrib_spec, + unsigned nr_attrib, int device_index) { - struct edac_device_ctl_info *dev_ctl; - struct edac_device_instance *dev_inst, *inst; - struct edac_device_block *dev_blk, *blk_p, *blk; struct edac_dev_sysfs_block_attribute *dev_attrib, *attrib_p, *attrib; - unsigned total_size; - unsigned count; + struct edac_device_block *dev_blk, *blk_p, *blk; + struct edac_device_instance *dev_inst, *inst; + struct edac_device_ctl_info *dev_ctl; unsigned instance, block, attr; - void *pvt, *p; + void *pvt; int err; edac_dbg(4, "instances=%d blocks=%d\n", nr_instances, nr_blocks); - /* Calculate the size of memory we need to allocate AND - * determine the offsets of the various item arrays - * (instance,block,attrib) from the start of an allocated structure. - * We want the alignment of each item (instance,block,attrib) - * to be at least as stringent as what the compiler would - * provide if we could simply hardcode everything into a single struct. - */ - p = NULL; - dev_ctl = edac_align_ptr(&p, sizeof(*dev_ctl), 1); + dev_ctl = kzalloc(sizeof(struct edac_device_ctl_info), GFP_KERNEL); + if (!dev_ctl) + return NULL; - /* Calc the 'end' offset past end of ONE ctl_info structure - * which will become the start of the 'instance' array - */ - dev_inst = edac_align_ptr(&p, sizeof(*dev_inst), nr_instances); + dev_inst = kcalloc(nr_instances, sizeof(struct edac_device_instance), GFP_KERNEL); + if (!dev_inst) + goto free; - /* Calc the 'end' offset past the instance array within the ctl_info - * which will become the start of the block array - */ - count = nr_instances * nr_blocks; - dev_blk = edac_align_ptr(&p, sizeof(*dev_blk), count); + dev_ctl->instances = dev_inst; - /* Calc the 'end' offset past the dev_blk array - * which will become the start of the attrib array, if any. - */ - /* calc how many nr_attrib we need */ - if (nr_attrib > 0) - count *= nr_attrib; - dev_attrib = edac_align_ptr(&p, sizeof(*dev_attrib), count); + dev_blk = kcalloc(nr_instances * nr_blocks, sizeof(struct edac_device_block), GFP_KERNEL); + if (!dev_blk) + goto free; - /* Calc the 'end' offset past the attributes array */ - pvt = edac_align_ptr(&p, sz_private, 1); + dev_ctl->blocks = dev_blk; - /* 'pvt' now points to where the private data area is. - * At this point 'pvt' (like dev_inst,dev_blk and dev_attrib) - * is baselined at ZERO - */ - total_size = ((unsigned long)pvt) + sz_private; + if (nr_attrib) { + dev_attrib = kcalloc(nr_attrib, sizeof(struct edac_dev_sysfs_block_attribute), + GFP_KERNEL); + if (!dev_attrib) + goto free; - /* Allocate the amount of memory for the set of control structures */ - dev_ctl = kzalloc(total_size, GFP_KERNEL); - if (dev_ctl == NULL) - return NULL; + dev_ctl->attribs = dev_attrib; + } - /* Adjust pointers so they point within the actual memory we - * just allocated rather than an imaginary chunk of memory - * located at address 0. - * 'dev_ctl' points to REAL memory, while the others are - * ZERO based and thus need to be adjusted to point within - * the allocated memory. - */ - dev_inst = (struct edac_device_instance *) - (((char *)dev_ctl) + ((unsigned long)dev_inst)); - dev_blk = (struct edac_device_block *) - (((char *)dev_ctl) + ((unsigned long)dev_blk)); - dev_attrib = (struct edac_dev_sysfs_block_attribute *) - (((char *)dev_ctl) + ((unsigned long)dev_attrib)); - pvt = sz_private ? (((char *)dev_ctl) + ((unsigned long)pvt)) : NULL; - - /* Begin storing the information into the control info structure */ - dev_ctl->dev_idx = device_index; - dev_ctl->nr_instances = nr_instances; - dev_ctl->instances = dev_inst; - dev_ctl->pvt_info = pvt; + if (pvt_sz) { + pvt = kzalloc(pvt_sz, GFP_KERNEL); + if (!pvt) + goto free; + + dev_ctl->pvt_info = pvt; + } + + dev_ctl->dev_idx = device_index; + dev_ctl->nr_instances = nr_instances; /* Default logging of CEs and UEs */ dev_ctl->log_ce = 1; dev_ctl->log_ue = 1; /* Name of this edac device */ - snprintf(dev_ctl->name,sizeof(dev_ctl->name),"%s",edac_device_name); - - edac_dbg(4, "edac_dev=%p next after end=%p\n", - dev_ctl, pvt + sz_private); + snprintf(dev_ctl->name, sizeof(dev_ctl->name),"%s", dev_name); /* Initialize every Instance */ for (instance = 0; instance < nr_instances; instance++) { @@ -150,15 +118,14 @@ struct edac_device_ctl_info *edac_device_alloc_ctl_info( inst->blocks = blk_p; /* name of this instance */ - snprintf(inst->name, sizeof(inst->name), - "%s%u", edac_device_name, instance); + snprintf(inst->name, sizeof(inst->name), "%s%u", dev_name, instance); /* Initialize every block in each instance */ for (block = 0; block < nr_blocks; block++) { blk = &blk_p[block]; blk->instance = inst; snprintf(blk->name, sizeof(blk->name), - "%s%d", edac_block_name, block+offset_value); + "%s%d", blk_name, block + off_val); edac_dbg(4, "instance=%d inst_p=%p block=#%d block_p=%p name='%s'\n", instance, inst, block, blk, blk->name); @@ -210,10 +177,8 @@ struct edac_device_ctl_info *edac_device_alloc_ctl_info( * Initialize the 'root' kobj for the edac_device controller */ err = edac_device_register_sysfs_main_kobj(dev_ctl); - if (err) { - kfree(dev_ctl); - return NULL; - } + if (err) + goto free; /* at this point, the root kobj is valid, and in order to * 'free' the object, then the function: @@ -223,6 +188,11 @@ struct edac_device_ctl_info *edac_device_alloc_ctl_info( */ return dev_ctl; + +free: + __edac_device_free_ctl_info(dev_ctl); + + return NULL; } EXPORT_SYMBOL_GPL(edac_device_alloc_ctl_info); diff --git a/drivers/edac/edac_device.h b/drivers/edac/edac_device.h index fc2d2c218064..3f44e6b9d387 100644 --- a/drivers/edac/edac_device.h +++ b/drivers/edac/edac_device.h @@ -216,6 +216,8 @@ struct edac_device_ctl_info { */ u32 nr_instances; struct edac_device_instance *instances; + struct edac_device_block *blocks; + struct edac_dev_sysfs_block_attribute *attribs; /* Event counters for the this whole EDAC Device */ struct edac_device_counter counters; @@ -348,4 +350,16 @@ edac_device_handle_ue(struct edac_device_ctl_info *edac_dev, int inst_nr, */ extern int edac_device_alloc_index(void); extern const char *edac_layer_name[]; + +/* Free the actual struct */ +static inline void __edac_device_free_ctl_info(struct edac_device_ctl_info *ci) +{ + if (ci) { + kfree(ci->pvt_info); + kfree(ci->attribs); + kfree(ci->blocks); + kfree(ci->instances); + kfree(ci); + } +} #endif diff --git a/drivers/edac/edac_device_sysfs.c b/drivers/edac/edac_device_sysfs.c index 9a61d92bdf42..ac678b4a21fc 100644 --- a/drivers/edac/edac_device_sysfs.c +++ b/drivers/edac/edac_device_sysfs.c @@ -208,10 +208,7 @@ static void edac_device_ctrl_master_release(struct kobject *kobj) /* decrement the EDAC CORE module ref count */ module_put(edac_dev->owner); - /* free the control struct containing the 'main' kobj - * passed in to this routine - */ - kfree(edac_dev); + __edac_device_free_ctl_info(edac_dev); } /* ktype for the main (master) kobject */ diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c index d2715774af6f..eb58644bb019 100644 --- a/drivers/edac/edac_mc.c +++ b/drivers/edac/edac_mc.c @@ -170,61 +170,6 @@ const char * const edac_mem_types[] = { }; EXPORT_SYMBOL_GPL(edac_mem_types); -/** - * edac_align_ptr - Prepares the pointer offsets for a single-shot allocation - * @p: pointer to a pointer with the memory offset to be used. At - * return, this will be incremented to point to the next offset - * @size: Size of the data structure to be reserved - * @n_elems: Number of elements that should be reserved - * - * If 'size' is a constant, the compiler will optimize this whole function - * down to either a no-op or the addition of a constant to the value of '*p'. - * - * The 'p' pointer is absolutely needed to keep the proper advancing - * further in memory to the proper offsets when allocating the struct along - * with its embedded structs, as edac_device_alloc_ctl_info() does it - * above, for example. - * - * At return, the pointer 'p' will be incremented to be used on a next call - * to this function. - */ -void *edac_align_ptr(void **p, unsigned int size, int n_elems) -{ - unsigned int align, r; - void *ptr = *p; - - *p += size * n_elems; - - /* - * 'p' can possibly be an unaligned item X such that sizeof(X) is - * 'size'. Adjust 'p' so that its alignment is at least as - * stringent as what the compiler would provide for X and return - * the aligned result. - * Here we assume that the alignment of a "long long" is the most - * stringent alignment that the compiler will ever provide by default. - * As far as I know, this is a reasonable assumption. - */ - if (size > sizeof(long)) - align = sizeof(long long); - else if (size > sizeof(int)) - align = sizeof(long); - else if (size > sizeof(short)) - align = sizeof(int); - else if (size > sizeof(char)) - align = sizeof(short); - else - return ptr; - - r = (unsigned long)ptr % align; - - if (r == 0) - return ptr; - - *p += align - r; - - return (void *)(((unsigned long)ptr) + align - r); -} - static void _edac_mc_free(struct mem_ctl_info *mci) { put_device(&mci->dev); @@ -257,6 +202,8 @@ static void mci_release(struct device *dev) } kfree(mci->csrows); } + kfree(mci->pvt_info); + kfree(mci->layers); kfree(mci); } @@ -392,9 +339,8 @@ struct mem_ctl_info *edac_mc_alloc(unsigned int mc_num, { struct mem_ctl_info *mci; struct edac_mc_layer *layer; - unsigned int idx, size, tot_dimms = 1; + unsigned int idx, tot_dimms = 1; unsigned int tot_csrows = 1, tot_channels = 1; - void *pvt, *ptr = NULL; bool per_rank = false; if (WARN_ON(n_layers > EDAC_MAX_LAYERS || n_layers == 0)) @@ -416,41 +362,25 @@ struct mem_ctl_info *edac_mc_alloc(unsigned int mc_num, per_rank = true; } - /* Figure out the offsets of the various items from the start of an mc - * structure. We want the alignment of each item to be at least as - * stringent as what the compiler would provide if we could simply - * hardcode everything into a single struct. - */ - mci = edac_align_ptr(&ptr, sizeof(*mci), 1); - layer = edac_align_ptr(&ptr, sizeof(*layer), n_layers); - pvt = edac_align_ptr(&ptr, sz_pvt, 1); - size = ((unsigned long)pvt) + sz_pvt; - - edac_dbg(1, "allocating %u bytes for mci data (%d %s, %d csrows/channels)\n", - size, - tot_dimms, - per_rank ? "ranks" : "dimms", - tot_csrows * tot_channels); - - mci = kzalloc(size, GFP_KERNEL); - if (mci == NULL) + mci = kzalloc(sizeof(struct mem_ctl_info), GFP_KERNEL); + if (!mci) return NULL; + mci->layers = kcalloc(n_layers, sizeof(struct edac_mc_layer), GFP_KERNEL); + if (!mci->layers) + goto error; + + mci->pvt_info = kzalloc(sz_pvt, GFP_KERNEL); + if (!mci->pvt_info) + goto error; + mci->dev.release = mci_release; device_initialize(&mci->dev); - /* Adjust pointers so they point within the memory we just allocated - * rather than an imaginary chunk of memory located at address 0. - */ - layer = (struct edac_mc_layer *)(((char *)mci) + ((unsigned long)layer)); - pvt = sz_pvt ? (((char *)mci) + ((unsigned long)pvt)) : NULL; - /* setup index and various internal pointers */ mci->mc_idx = mc_num; mci->tot_dimms = tot_dimms; - mci->pvt_info = pvt; mci->n_layers = n_layers; - mci->layers = layer; memcpy(mci->layers, layers, sizeof(*layer) * n_layers); mci->nr_csrows = tot_csrows; mci->num_cschannel = tot_channels; diff --git a/drivers/edac/edac_module.h b/drivers/edac/edac_module.h index aa1f91688eb8..96f6de0c8ff6 100644 --- a/drivers/edac/edac_module.h +++ b/drivers/edac/edac_module.h @@ -59,8 +59,6 @@ extern void edac_device_reset_delay_period(struct edac_device_ctl_info *edac_dev, unsigned long value); extern void edac_mc_reset_delay_period(unsigned long value); -extern void *edac_align_ptr(void **p, unsigned size, int n_elems); - /* * EDAC debugfs functions */ diff --git a/drivers/edac/edac_pci.c b/drivers/edac/edac_pci.c index 48c844a72a27..2205d7e731db 100644 --- a/drivers/edac/edac_pci.c +++ b/drivers/edac/edac_pci.c @@ -29,32 +29,31 @@ static LIST_HEAD(edac_pci_list); static atomic_t pci_indexes = ATOMIC_INIT(0); struct edac_pci_ctl_info *edac_pci_alloc_ctl_info(unsigned int sz_pvt, - const char *edac_pci_name) + const char *edac_pci_name) { struct edac_pci_ctl_info *pci; - void *p = NULL, *pvt; - unsigned int size; edac_dbg(1, "\n"); - pci = edac_align_ptr(&p, sizeof(*pci), 1); - pvt = edac_align_ptr(&p, 1, sz_pvt); - size = ((unsigned long)pvt) + sz_pvt; - - /* Alloc the needed control struct memory */ - pci = kzalloc(size, GFP_KERNEL); - if (pci == NULL) + pci = kzalloc(sizeof(struct edac_pci_ctl_info), GFP_KERNEL); + if (!pci) return NULL; - /* Now much private space */ - pvt = sz_pvt ? ((char *)pci) + ((unsigned long)pvt) : NULL; + if (sz_pvt) { + pci->pvt_info = kzalloc(sz_pvt, GFP_KERNEL); + if (!pci->pvt_info) + goto free; + } - pci->pvt_info = pvt; pci->op_state = OP_ALLOC; snprintf(pci->name, strlen(edac_pci_name) + 1, "%s", edac_pci_name); return pci; + +free: + kfree(pci); + return NULL; } EXPORT_SYMBOL_GPL(edac_pci_alloc_ctl_info); diff --git a/drivers/edac/ghes_edac.c b/drivers/edac/ghes_edac.c index 6d1ddecbf0da..59b0bedc9c24 100644 --- a/drivers/edac/ghes_edac.c +++ b/drivers/edac/ghes_edac.c @@ -15,11 +15,13 @@ #include "edac_module.h" #include <ras/ras_event.h> +#define OTHER_DETAIL_LEN 400 + struct ghes_pvt { struct mem_ctl_info *mci; /* Buffers for the error handling routine */ - char other_detail[400]; + char other_detail[OTHER_DETAIL_LEN]; char msg[80]; }; @@ -36,7 +38,7 @@ static struct ghes_pvt *ghes_pvt; * This driver's representation of the system hardware, as collected * from DMI. */ -struct ghes_hw_desc { +static struct ghes_hw_desc { int num_dimms; struct dimm_info *dimms; } ghes_hw; @@ -235,8 +237,34 @@ static void ghes_scan_system(void) system_scanned = true; } +static int print_mem_error_other_detail(const struct cper_sec_mem_err *mem, char *msg, + const char *location, unsigned int len) +{ + u32 n; + + if (!msg) + return 0; + + n = 0; + len -= 1; + + n += scnprintf(msg + n, len - n, "APEI location: %s ", location); + + if (!(mem->validation_bits & CPER_MEM_VALID_ERROR_STATUS)) + goto out; + + n += scnprintf(msg + n, len - n, "status(0x%016llx): ", mem->error_status); + n += scnprintf(msg + n, len - n, "%s ", cper_mem_err_status_str(mem->error_status)); + +out: + msg[n] = '\0'; + + return n; +} + void ghes_edac_report_mem_error(int sev, struct cper_sec_mem_err *mem_err) { + struct cper_mem_err_compact cmem; struct edac_raw_error_desc *e; struct mem_ctl_info *mci; struct ghes_pvt *pvt; @@ -292,60 +320,10 @@ void ghes_edac_report_mem_error(int sev, struct cper_sec_mem_err *mem_err) /* Error type, mapped on e->msg */ if (mem_err->validation_bits & CPER_MEM_VALID_ERROR_TYPE) { + u8 etype = mem_err->error_type; + p = pvt->msg; - switch (mem_err->error_type) { - case 0: - p += sprintf(p, "Unknown"); - break; - case 1: - p += sprintf(p, "No error"); - break; - case 2: - p += sprintf(p, "Single-bit ECC"); - break; - case 3: - p += sprintf(p, "Multi-bit ECC"); - break; - case 4: - p += sprintf(p, "Single-symbol ChipKill ECC"); - break; - case 5: - p += sprintf(p, "Multi-symbol ChipKill ECC"); - break; - case 6: - p += sprintf(p, "Master abort"); - break; - case 7: - p += sprintf(p, "Target abort"); - break; - case 8: - p += sprintf(p, "Parity Error"); - break; - case 9: - p += sprintf(p, "Watchdog timeout"); - break; - case 10: - p += sprintf(p, "Invalid address"); - break; - case 11: - p += sprintf(p, "Mirror Broken"); - break; - case 12: - p += sprintf(p, "Memory Sparing"); - break; - case 13: - p += sprintf(p, "Scrub corrected error"); - break; - case 14: - p += sprintf(p, "Scrub uncorrected error"); - break; - case 15: - p += sprintf(p, "Physical Memory Map-out event"); - break; - default: - p += sprintf(p, "reserved error (%d)", - mem_err->error_type); - } + p += snprintf(p, sizeof(pvt->msg), "%s", cper_mem_err_type_str(etype)); } else { strcpy(pvt->msg, "unknown error"); } @@ -362,52 +340,19 @@ void ghes_edac_report_mem_error(int sev, struct cper_sec_mem_err *mem_err) /* Memory error location, mapped on e->location */ p = e->location; - if (mem_err->validation_bits & CPER_MEM_VALID_NODE) - p += sprintf(p, "node:%d ", mem_err->node); - if (mem_err->validation_bits & CPER_MEM_VALID_CARD) - p += sprintf(p, "card:%d ", mem_err->card); - if (mem_err->validation_bits & CPER_MEM_VALID_MODULE) - p += sprintf(p, "module:%d ", mem_err->module); - if (mem_err->validation_bits & CPER_MEM_VALID_RANK_NUMBER) - p += sprintf(p, "rank:%d ", mem_err->rank); - if (mem_err->validation_bits & CPER_MEM_VALID_BANK) - p += sprintf(p, "bank:%d ", mem_err->bank); - if (mem_err->validation_bits & CPER_MEM_VALID_BANK_GROUP) - p += sprintf(p, "bank_group:%d ", - mem_err->bank >> CPER_MEM_BANK_GROUP_SHIFT); - if (mem_err->validation_bits & CPER_MEM_VALID_BANK_ADDRESS) - p += sprintf(p, "bank_address:%d ", - mem_err->bank & CPER_MEM_BANK_ADDRESS_MASK); - if (mem_err->validation_bits & (CPER_MEM_VALID_ROW | CPER_MEM_VALID_ROW_EXT)) { - u32 row = mem_err->row; - - row |= cper_get_mem_extension(mem_err->validation_bits, mem_err->extended); - p += sprintf(p, "row:%d ", row); - } - if (mem_err->validation_bits & CPER_MEM_VALID_COLUMN) - p += sprintf(p, "col:%d ", mem_err->column); - if (mem_err->validation_bits & CPER_MEM_VALID_BIT_POSITION) - p += sprintf(p, "bit_pos:%d ", mem_err->bit_pos); + cper_mem_err_pack(mem_err, &cmem); + p += cper_mem_err_location(&cmem, p); + if (mem_err->validation_bits & CPER_MEM_VALID_MODULE_HANDLE) { - const char *bank = NULL, *device = NULL; struct dimm_info *dimm; - dmi_memdev_name(mem_err->mem_dev_handle, &bank, &device); - if (bank != NULL && device != NULL) - p += sprintf(p, "DIMM location:%s %s ", bank, device); - else - p += sprintf(p, "DIMM DMI handle: 0x%.4x ", - mem_err->mem_dev_handle); - + p += cper_dimm_err_location(&cmem, p); dimm = find_dimm_by_handle(mci, mem_err->mem_dev_handle); if (dimm) { e->top_layer = dimm->idx; strcpy(e->label, dimm->label); } } - if (mem_err->validation_bits & CPER_MEM_VALID_CHIP_ID) - p += sprintf(p, "chipID: %d ", - mem_err->extended >> CPER_MEM_CHIP_ID_SHIFT); if (p > e->location) *(p - 1) = '\0'; @@ -416,78 +361,7 @@ void ghes_edac_report_mem_error(int sev, struct cper_sec_mem_err *mem_err) /* All other fields are mapped on e->other_detail */ p = pvt->other_detail; - p += snprintf(p, sizeof(pvt->other_detail), - "APEI location: %s ", e->location); - if (mem_err->validation_bits & CPER_MEM_VALID_ERROR_STATUS) { - u64 status = mem_err->error_status; - - p += sprintf(p, "status(0x%016llx): ", (long long)status); - switch ((status >> 8) & 0xff) { - case 1: - p += sprintf(p, "Error detected internal to the component "); - break; - case 16: - p += sprintf(p, "Error detected in the bus "); - break; - case 4: - p += sprintf(p, "Storage error in DRAM memory "); - break; - case 5: - p += sprintf(p, "Storage error in TLB "); - break; - case 6: - p += sprintf(p, "Storage error in cache "); - break; - case 7: - p += sprintf(p, "Error in one or more functional units "); - break; - case 8: - p += sprintf(p, "component failed self test "); - break; - case 9: - p += sprintf(p, "Overflow or undervalue of internal queue "); - break; - case 17: - p += sprintf(p, "Virtual address not found on IO-TLB or IO-PDIR "); - break; - case 18: - p += sprintf(p, "Improper access error "); - break; - case 19: - p += sprintf(p, "Access to a memory address which is not mapped to any component "); - break; - case 20: - p += sprintf(p, "Loss of Lockstep "); - break; - case 21: - p += sprintf(p, "Response not associated with a request "); - break; - case 22: - p += sprintf(p, "Bus parity error - must also set the A, C, or D Bits "); - break; - case 23: - p += sprintf(p, "Detection of a PATH_ERROR "); - break; - case 25: - p += sprintf(p, "Bus operation timeout "); - break; - case 26: - p += sprintf(p, "A read was issued to data that has been poisoned "); - break; - default: - p += sprintf(p, "reserved "); - break; - } - } - if (mem_err->validation_bits & CPER_MEM_VALID_REQUESTOR_ID) - p += sprintf(p, "requestorID: 0x%016llx ", - (long long)mem_err->requestor_id); - if (mem_err->validation_bits & CPER_MEM_VALID_RESPONDER_ID) - p += sprintf(p, "responderID: 0x%016llx ", - (long long)mem_err->responder_id); - if (mem_err->validation_bits & CPER_MEM_VALID_TARGET_ID) - p += sprintf(p, "targetID: 0x%016llx ", - (long long)mem_err->responder_id); + p += print_mem_error_other_detail(mem_err, p, e->location, OTHER_DETAIL_LEN); if (p > pvt->other_detail) *(p - 1) = '\0'; diff --git a/drivers/edac/i5100_edac.c b/drivers/edac/i5100_edac.c index 324a46b8479b..f5d82518c15e 100644 --- a/drivers/edac/i5100_edac.c +++ b/drivers/edac/i5100_edac.c @@ -244,11 +244,6 @@ static inline u32 i5100_nrecmema_rank(u32 a) return a >> 8 & ((1 << 3) - 1); } -static inline u32 i5100_nrecmema_dm_buf_id(u32 a) -{ - return a & ((1 << 8) - 1); -} - static inline u32 i5100_nrecmemb_cas(u32 a) { return a >> 16 & ((1 << 13) - 1); diff --git a/drivers/edac/mpc85xx_edac.c b/drivers/edac/mpc85xx_edac.c index 67f7bc3fe5b3..5bf92298554d 100644 --- a/drivers/edac/mpc85xx_edac.c +++ b/drivers/edac/mpc85xx_edac.c @@ -609,13 +609,6 @@ static int mpc85xx_l2_err_remove(struct platform_device *op) } static const struct of_device_id mpc85xx_l2_err_of_match[] = { -/* deprecate the fsl,85.. forms in the future, 2.6.30? */ - { .compatible = "fsl,8540-l2-cache-controller", }, - { .compatible = "fsl,8541-l2-cache-controller", }, - { .compatible = "fsl,8544-l2-cache-controller", }, - { .compatible = "fsl,8548-l2-cache-controller", }, - { .compatible = "fsl,8555-l2-cache-controller", }, - { .compatible = "fsl,8568-l2-cache-controller", }, { .compatible = "fsl,mpc8536-l2-cache-controller", }, { .compatible = "fsl,mpc8540-l2-cache-controller", }, { .compatible = "fsl,mpc8541-l2-cache-controller", }, @@ -644,13 +637,6 @@ static struct platform_driver mpc85xx_l2_err_driver = { }; static const struct of_device_id mpc85xx_mc_err_of_match[] = { -/* deprecate the fsl,85.. forms in the future, 2.6.30? */ - { .compatible = "fsl,8540-memory-controller", }, - { .compatible = "fsl,8541-memory-controller", }, - { .compatible = "fsl,8544-memory-controller", }, - { .compatible = "fsl,8548-memory-controller", }, - { .compatible = "fsl,8555-memory-controller", }, - { .compatible = "fsl,8568-memory-controller", }, { .compatible = "fsl,mpc8536-memory-controller", }, { .compatible = "fsl,mpc8540-memory-controller", }, { .compatible = "fsl,mpc8541-memory-controller", }, diff --git a/drivers/edac/synopsys_edac.c b/drivers/edac/synopsys_edac.c index f05ff02c0656..1cee64b80a7e 100644 --- a/drivers/edac/synopsys_edac.c +++ b/drivers/edac/synopsys_edac.c @@ -1,22 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Synopsys DDR ECC Driver * This driver is based on ppc4xx_edac.c drivers * * Copyright (C) 2012 - 2014 Xilinx, Inc. - * - * This program is free software: you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation, either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details */ #include <linux/edac.h> @@ -164,6 +151,11 @@ #define ECC_STAT_CECNT_SHIFT 8 #define ECC_STAT_BITNUM_MASK 0x7F +/* ECC error count register definitions */ +#define ECC_ERRCNT_UECNT_MASK 0xFFFF0000 +#define ECC_ERRCNT_UECNT_SHIFT 16 +#define ECC_ERRCNT_CECNT_MASK 0xFFFF + /* DDR QOS Interrupt register definitions */ #define DDR_QOS_IRQ_STAT_OFST 0x20200 #define DDR_QOSUE_MASK 0x4 @@ -423,15 +415,16 @@ static int zynqmp_get_error_info(struct synps_edac_priv *priv) base = priv->baseaddr; p = &priv->stat; + regval = readl(base + ECC_ERRCNT_OFST); + p->ce_cnt = regval & ECC_ERRCNT_CECNT_MASK; + p->ue_cnt = (regval & ECC_ERRCNT_UECNT_MASK) >> ECC_ERRCNT_UECNT_SHIFT; + if (!p->ce_cnt) + goto ue_err; + regval = readl(base + ECC_STAT_OFST); if (!regval) return 1; - p->ce_cnt = (regval & ECC_STAT_CECNT_MASK) >> ECC_STAT_CECNT_SHIFT; - p->ue_cnt = (regval & ECC_STAT_UECNT_MASK) >> ECC_STAT_UECNT_SHIFT; - if (!p->ce_cnt) - goto ue_err; - p->ceinfo.bitpos = (regval & ECC_STAT_BITNUM_MASK); regval = readl(base + ECC_CEADDR0_OFST); diff --git a/drivers/edac/xgene_edac.c b/drivers/edac/xgene_edac.c index 7197f9fa0245..54081403db4f 100644 --- a/drivers/edac/xgene_edac.c +++ b/drivers/edac/xgene_edac.c @@ -501,7 +501,7 @@ static int xgene_edac_mc_remove(struct xgene_edac_mc_ctx *mcu) #define MEMERR_L2C_L2ESRA_PAGE_OFFSET 0x0804 /* - * Processor Module Domain (PMD) context - Context for a pair of processsors. + * Processor Module Domain (PMD) context - Context for a pair of processors. * Each PMD consists of 2 CPUs and a shared L2 cache. Each CPU consists of * its own L1 cache. */ diff --git a/drivers/firewire/core-card.c b/drivers/firewire/core-card.c index 54be88167c60..f3b3953cac83 100644 --- a/drivers/firewire/core-card.c +++ b/drivers/firewire/core-card.c @@ -668,6 +668,7 @@ EXPORT_SYMBOL_GPL(fw_card_release); void fw_core_remove_card(struct fw_card *card) { struct fw_card_driver dummy_driver = dummy_driver_template; + unsigned long flags; card->driver->update_phy_reg(card, 4, PHY_LINK_ACTIVE | PHY_CONTENDER, 0); @@ -682,7 +683,9 @@ void fw_core_remove_card(struct fw_card *card) dummy_driver.stop_iso = card->driver->stop_iso; card->driver = &dummy_driver; + spin_lock_irqsave(&card->lock, flags); fw_destroy_nodes(card); + spin_unlock_irqrestore(&card->lock, flags); /* Wait for all users, especially device workqueue jobs, to finish. */ fw_card_put(card); diff --git a/drivers/firewire/core-cdev.c b/drivers/firewire/core-cdev.c index 9f89c17730b1..708e417200f4 100644 --- a/drivers/firewire/core-cdev.c +++ b/drivers/firewire/core-cdev.c @@ -1500,6 +1500,7 @@ static void outbound_phy_packet_callback(struct fw_packet *packet, { struct outbound_phy_packet_event *e = container_of(packet, struct outbound_phy_packet_event, p); + struct client *e_client; switch (status) { /* expected: */ @@ -1516,9 +1517,10 @@ static void outbound_phy_packet_callback(struct fw_packet *packet, } e->phy_packet.data[0] = packet->timestamp; + e_client = e->client; queue_event(e->client, &e->event, &e->phy_packet, sizeof(e->phy_packet) + e->phy_packet.length, NULL, 0); - client_put(e->client); + client_put(e_client); } static int ioctl_send_phy_packet(struct client *client, union ioctl_arg *arg) diff --git a/drivers/firewire/core-topology.c b/drivers/firewire/core-topology.c index b63d55f5ebd3..f40c81534381 100644 --- a/drivers/firewire/core-topology.c +++ b/drivers/firewire/core-topology.c @@ -375,16 +375,13 @@ static void report_found_node(struct fw_card *card, card->bm_retries = 0; } +/* Must be called with card->lock held */ void fw_destroy_nodes(struct fw_card *card) { - unsigned long flags; - - spin_lock_irqsave(&card->lock, flags); card->color++; if (card->local_node != NULL) for_each_fw_node(card, card->local_node, report_lost_node); card->local_node = NULL; - spin_unlock_irqrestore(&card->lock, flags); } static void move_tree(struct fw_node *node0, struct fw_node *node1, int port) @@ -510,6 +507,8 @@ void fw_core_handle_bus_reset(struct fw_card *card, int node_id, int generation, struct fw_node *local_node; unsigned long flags; + spin_lock_irqsave(&card->lock, flags); + /* * If the selfID buffer is not the immediate successor of the * previously processed one, we cannot reliably compare the @@ -521,8 +520,6 @@ void fw_core_handle_bus_reset(struct fw_card *card, int node_id, int generation, card->bm_retries = 0; } - spin_lock_irqsave(&card->lock, flags); - card->broadcast_channel_allocated = card->broadcast_channel_auto_allocated; card->node_id = node_id; /* diff --git a/drivers/firewire/core-transaction.c b/drivers/firewire/core-transaction.c index ac487c96bb71..6c20815cc8d1 100644 --- a/drivers/firewire/core-transaction.c +++ b/drivers/firewire/core-transaction.c @@ -73,24 +73,25 @@ static int try_cancel_split_timeout(struct fw_transaction *t) static int close_transaction(struct fw_transaction *transaction, struct fw_card *card, int rcode) { - struct fw_transaction *t; + struct fw_transaction *t = NULL, *iter; unsigned long flags; spin_lock_irqsave(&card->lock, flags); - list_for_each_entry(t, &card->transaction_list, link) { - if (t == transaction) { - if (!try_cancel_split_timeout(t)) { + list_for_each_entry(iter, &card->transaction_list, link) { + if (iter == transaction) { + if (!try_cancel_split_timeout(iter)) { spin_unlock_irqrestore(&card->lock, flags); goto timed_out; } - list_del_init(&t->link); - card->tlabel_mask &= ~(1ULL << t->tlabel); + list_del_init(&iter->link); + card->tlabel_mask &= ~(1ULL << iter->tlabel); + t = iter; break; } } spin_unlock_irqrestore(&card->lock, flags); - if (&t->link != &card->transaction_list) { + if (t) { t->callback(card, rcode, NULL, 0, t->callback_data); return 0; } @@ -935,7 +936,7 @@ EXPORT_SYMBOL(fw_core_handle_request); void fw_core_handle_response(struct fw_card *card, struct fw_packet *p) { - struct fw_transaction *t; + struct fw_transaction *t = NULL, *iter; unsigned long flags; u32 *data; size_t data_length; @@ -947,20 +948,21 @@ void fw_core_handle_response(struct fw_card *card, struct fw_packet *p) rcode = HEADER_GET_RCODE(p->header[1]); spin_lock_irqsave(&card->lock, flags); - list_for_each_entry(t, &card->transaction_list, link) { - if (t->node_id == source && t->tlabel == tlabel) { - if (!try_cancel_split_timeout(t)) { + list_for_each_entry(iter, &card->transaction_list, link) { + if (iter->node_id == source && iter->tlabel == tlabel) { + if (!try_cancel_split_timeout(iter)) { spin_unlock_irqrestore(&card->lock, flags); goto timed_out; } - list_del_init(&t->link); - card->tlabel_mask &= ~(1ULL << t->tlabel); + list_del_init(&iter->link); + card->tlabel_mask &= ~(1ULL << iter->tlabel); + t = iter; break; } } spin_unlock_irqrestore(&card->lock, flags); - if (&t->link == &card->transaction_list) { + if (!t) { timed_out: fw_notice(card, "unsolicited response (source %x, tlabel %x)\n", source, tlabel); diff --git a/drivers/firewire/sbp2.c b/drivers/firewire/sbp2.c index 85cd379fd383..60051c0cabea 100644 --- a/drivers/firewire/sbp2.c +++ b/drivers/firewire/sbp2.c @@ -408,7 +408,7 @@ static void sbp2_status_write(struct fw_card *card, struct fw_request *request, void *payload, size_t length, void *callback_data) { struct sbp2_logical_unit *lu = callback_data; - struct sbp2_orb *orb; + struct sbp2_orb *orb = NULL, *iter; struct sbp2_status status; unsigned long flags; @@ -433,17 +433,18 @@ static void sbp2_status_write(struct fw_card *card, struct fw_request *request, /* Lookup the orb corresponding to this status write. */ spin_lock_irqsave(&lu->tgt->lock, flags); - list_for_each_entry(orb, &lu->orb_list, link) { + list_for_each_entry(iter, &lu->orb_list, link) { if (STATUS_GET_ORB_HIGH(status) == 0 && - STATUS_GET_ORB_LOW(status) == orb->request_bus) { - orb->rcode = RCODE_COMPLETE; - list_del(&orb->link); + STATUS_GET_ORB_LOW(status) == iter->request_bus) { + iter->rcode = RCODE_COMPLETE; + list_del(&iter->link); + orb = iter; break; } } spin_unlock_irqrestore(&lu->tgt->lock, flags); - if (&orb->link != &lu->orb_list) { + if (orb) { orb->callback(orb, &status); kref_put(&orb->kref, free_orb); /* orb callback reference */ } else { diff --git a/drivers/firmware/arm_scmi/clock.c b/drivers/firmware/arm_scmi/clock.c index cf6fed6dec77..45600acc0f45 100644 --- a/drivers/firmware/arm_scmi/clock.c +++ b/drivers/firmware/arm_scmi/clock.c @@ -49,7 +49,7 @@ struct scmi_msg_resp_clock_describe_rates { struct { __le32 value_low; __le32 value_high; - } rate[0]; + } rate[]; #define RATE_TO_U64(X) \ ({ \ typeof(X) x = (X); \ @@ -210,7 +210,8 @@ scmi_clock_describe_rates_get(const struct scmi_protocol_handle *ph, u32 clk_id, if (rate_discrete && rate) { clk->list.num_rates = tot_rate_cnt; - sort(rate, tot_rate_cnt, sizeof(*rate), rate_cmp_func, NULL); + sort(clk->list.rates, tot_rate_cnt, sizeof(*rate), + rate_cmp_func, NULL); } clk->rate_discrete = rate_discrete; diff --git a/drivers/firmware/arm_scmi/driver.c b/drivers/firmware/arm_scmi/driver.c index 46118300a4d1..e17c6568344d 100644 --- a/drivers/firmware/arm_scmi/driver.c +++ b/drivers/firmware/arm_scmi/driver.c @@ -679,7 +679,8 @@ static void scmi_handle_response(struct scmi_chan_info *cinfo, xfer = scmi_xfer_command_acquire(cinfo, msg_hdr); if (IS_ERR(xfer)) { - scmi_clear_channel(info, cinfo); + if (MSG_XTRACT_TYPE(msg_hdr) == MSG_TYPE_DELAYED_RESP) + scmi_clear_channel(info, cinfo); return; } diff --git a/drivers/firmware/arm_scmi/optee.c b/drivers/firmware/arm_scmi/optee.c index 734f1eeee161..8302a2b4aeeb 100644 --- a/drivers/firmware/arm_scmi/optee.c +++ b/drivers/firmware/arm_scmi/optee.c @@ -405,8 +405,8 @@ static int scmi_optee_chan_free(int id, void *p, void *data) return 0; } -static struct scmi_shared_mem *get_channel_shm(struct scmi_optee_channel *chan, - struct scmi_xfer *xfer) +static struct scmi_shared_mem __iomem * +get_channel_shm(struct scmi_optee_channel *chan, struct scmi_xfer *xfer) { if (!chan) return NULL; @@ -419,7 +419,7 @@ static int scmi_optee_send_message(struct scmi_chan_info *cinfo, struct scmi_xfer *xfer) { struct scmi_optee_channel *channel = cinfo->transport_info; - struct scmi_shared_mem *shmem = get_channel_shm(channel, xfer); + struct scmi_shared_mem __iomem *shmem = get_channel_shm(channel, xfer); int ret; mutex_lock(&channel->mu); @@ -436,7 +436,7 @@ static void scmi_optee_fetch_response(struct scmi_chan_info *cinfo, struct scmi_xfer *xfer) { struct scmi_optee_channel *channel = cinfo->transport_info; - struct scmi_shared_mem *shmem = get_channel_shm(channel, xfer); + struct scmi_shared_mem __iomem *shmem = get_channel_shm(channel, xfer); shmem_fetch_response(shmem, xfer); } diff --git a/drivers/firmware/cirrus/cs_dsp.c b/drivers/firmware/cirrus/cs_dsp.c index e48108e694f8..7dad6f57d970 100644 --- a/drivers/firmware/cirrus/cs_dsp.c +++ b/drivers/firmware/cirrus/cs_dsp.c @@ -955,8 +955,7 @@ static int cs_dsp_create_control(struct cs_dsp *dsp, ctl->alg_region = *alg_region; if (subname && dsp->fw_ver >= 2) { ctl->subname_len = subname_len; - ctl->subname = kmemdup(subname, - strlen(subname) + 1, GFP_KERNEL); + ctl->subname = kasprintf(GFP_KERNEL, "%.*s", subname_len, subname); if (!ctl->subname) { ret = -ENOMEM; goto err_ctl; diff --git a/drivers/firmware/efi/Kconfig b/drivers/firmware/efi/Kconfig index 2c3dac5ecb36..4720ba98cec3 100644 --- a/drivers/firmware/efi/Kconfig +++ b/drivers/firmware/efi/Kconfig @@ -91,6 +91,18 @@ config EFI_SOFT_RESERVE If unsure, say Y. +config EFI_DXE_MEM_ATTRIBUTES + bool "Adjust memory attributes in EFISTUB" + depends on EFI && EFI_STUB && X86 + default y + help + UEFI specification does not guarantee all memory to be + accessible for both write and execute as the kernel expects + it to be. + Use DXE services to check and alter memory protection + attributes during boot via EFISTUB to ensure that memory + ranges used by the kernel are writable and executable. + config EFI_PARAMS_FROM_FDT bool help @@ -284,3 +296,34 @@ config EFI_CUSTOM_SSDT_OVERLAYS See Documentation/admin-guide/acpi/ssdt-overlays.rst for more information. + +config EFI_DISABLE_RUNTIME + bool "Disable EFI runtime services support by default" + default y if PREEMPT_RT + help + Allow to disable the EFI runtime services support by default. This can + already be achieved by using the efi=noruntime option, but it could be + useful to have this default without any kernel command line parameter. + + The EFI runtime services are disabled by default when PREEMPT_RT is + enabled, because measurements have shown that some EFI functions calls + might take too much time to complete, causing large latencies which is + an issue for Real-Time kernels. + + This default can be overridden by using the efi=runtime option. + +config EFI_COCO_SECRET + bool "EFI Confidential Computing Secret Area Support" + depends on EFI + help + Confidential Computing platforms (such as AMD SEV) allow the + Guest Owner to securely inject secrets during guest VM launch. + The secrets are placed in a designated EFI reserved memory area. + + In order to use the secrets in the kernel, the location of the secret + area (as published in the EFI config table) must be kept. + + If you say Y here, the address of the EFI secret area will be kept + for usage inside the kernel. This will allow the + virt/coco/efi_secret module to access the secrets, which in turn + allows userspace programs to access the injected secrets. diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c index 6ec8edec6329..e4e5ea7ce910 100644 --- a/drivers/firmware/efi/cper.c +++ b/drivers/firmware/efi/cper.c @@ -211,7 +211,33 @@ const char *cper_mem_err_type_str(unsigned int etype) } EXPORT_SYMBOL_GPL(cper_mem_err_type_str); -static int cper_mem_err_location(struct cper_mem_err_compact *mem, char *msg) +const char *cper_mem_err_status_str(u64 status) +{ + switch ((status >> 8) & 0xff) { + case 1: return "Error detected internal to the component"; + case 4: return "Storage error in DRAM memory"; + case 5: return "Storage error in TLB"; + case 6: return "Storage error in cache"; + case 7: return "Error in one or more functional units"; + case 8: return "Component failed self test"; + case 9: return "Overflow or undervalue of internal queue"; + case 16: return "Error detected in the bus"; + case 17: return "Virtual address not found on IO-TLB or IO-PDIR"; + case 18: return "Improper access error"; + case 19: return "Access to a memory address which is not mapped to any component"; + case 20: return "Loss of Lockstep"; + case 21: return "Response not associated with a request"; + case 22: return "Bus parity error - must also set the A, C, or D Bits"; + case 23: return "Detection of a protocol error"; + case 24: return "Detection of a PATH_ERROR"; + case 25: return "Bus operation timeout"; + case 26: return "A read was issued to data that has been poisoned"; + default: return "Reserved"; + } +} +EXPORT_SYMBOL_GPL(cper_mem_err_status_str); + +int cper_mem_err_location(struct cper_mem_err_compact *mem, char *msg) { u32 len, n; @@ -221,51 +247,51 @@ static int cper_mem_err_location(struct cper_mem_err_compact *mem, char *msg) n = 0; len = CPER_REC_LEN; if (mem->validation_bits & CPER_MEM_VALID_NODE) - n += scnprintf(msg + n, len - n, "node: %d ", mem->node); + n += scnprintf(msg + n, len - n, "node:%d ", mem->node); if (mem->validation_bits & CPER_MEM_VALID_CARD) - n += scnprintf(msg + n, len - n, "card: %d ", mem->card); + n += scnprintf(msg + n, len - n, "card:%d ", mem->card); if (mem->validation_bits & CPER_MEM_VALID_MODULE) - n += scnprintf(msg + n, len - n, "module: %d ", mem->module); + n += scnprintf(msg + n, len - n, "module:%d ", mem->module); if (mem->validation_bits & CPER_MEM_VALID_RANK_NUMBER) - n += scnprintf(msg + n, len - n, "rank: %d ", mem->rank); + n += scnprintf(msg + n, len - n, "rank:%d ", mem->rank); if (mem->validation_bits & CPER_MEM_VALID_BANK) - n += scnprintf(msg + n, len - n, "bank: %d ", mem->bank); + n += scnprintf(msg + n, len - n, "bank:%d ", mem->bank); if (mem->validation_bits & CPER_MEM_VALID_BANK_GROUP) - n += scnprintf(msg + n, len - n, "bank_group: %d ", + n += scnprintf(msg + n, len - n, "bank_group:%d ", mem->bank >> CPER_MEM_BANK_GROUP_SHIFT); if (mem->validation_bits & CPER_MEM_VALID_BANK_ADDRESS) - n += scnprintf(msg + n, len - n, "bank_address: %d ", + n += scnprintf(msg + n, len - n, "bank_address:%d ", mem->bank & CPER_MEM_BANK_ADDRESS_MASK); if (mem->validation_bits & CPER_MEM_VALID_DEVICE) - n += scnprintf(msg + n, len - n, "device: %d ", mem->device); + n += scnprintf(msg + n, len - n, "device:%d ", mem->device); if (mem->validation_bits & (CPER_MEM_VALID_ROW | CPER_MEM_VALID_ROW_EXT)) { u32 row = mem->row; row |= cper_get_mem_extension(mem->validation_bits, mem->extended); - n += scnprintf(msg + n, len - n, "row: %d ", row); + n += scnprintf(msg + n, len - n, "row:%d ", row); } if (mem->validation_bits & CPER_MEM_VALID_COLUMN) - n += scnprintf(msg + n, len - n, "column: %d ", mem->column); + n += scnprintf(msg + n, len - n, "column:%d ", mem->column); if (mem->validation_bits & CPER_MEM_VALID_BIT_POSITION) - n += scnprintf(msg + n, len - n, "bit_position: %d ", + n += scnprintf(msg + n, len - n, "bit_position:%d ", mem->bit_pos); if (mem->validation_bits & CPER_MEM_VALID_REQUESTOR_ID) - n += scnprintf(msg + n, len - n, "requestor_id: 0x%016llx ", + n += scnprintf(msg + n, len - n, "requestor_id:0x%016llx ", mem->requestor_id); if (mem->validation_bits & CPER_MEM_VALID_RESPONDER_ID) - n += scnprintf(msg + n, len - n, "responder_id: 0x%016llx ", + n += scnprintf(msg + n, len - n, "responder_id:0x%016llx ", mem->responder_id); if (mem->validation_bits & CPER_MEM_VALID_TARGET_ID) - n += scnprintf(msg + n, len - n, "target_id: 0x%016llx ", + n += scnprintf(msg + n, len - n, "target_id:0x%016llx ", mem->target_id); if (mem->validation_bits & CPER_MEM_VALID_CHIP_ID) - n += scnprintf(msg + n, len - n, "chip_id: %d ", + n += scnprintf(msg + n, len - n, "chip_id:%d ", mem->extended >> CPER_MEM_CHIP_ID_SHIFT); return n; } -static int cper_dimm_err_location(struct cper_mem_err_compact *mem, char *msg) +int cper_dimm_err_location(struct cper_mem_err_compact *mem, char *msg) { u32 len, n; const char *bank = NULL, *device = NULL; @@ -334,7 +360,9 @@ static void cper_print_mem(const char *pfx, const struct cper_sec_mem_err *mem, return; } if (mem->validation_bits & CPER_MEM_VALID_ERROR_STATUS) - printk("%s""error_status: 0x%016llx\n", pfx, mem->error_status); + printk("%s error_status: %s (0x%016llx)\n", + pfx, cper_mem_err_status_str(mem->error_status), + mem->error_status); if (mem->validation_bits & CPER_MEM_VALID_PA) printk("%s""physical_address: 0x%016llx\n", pfx, mem->physical_addr); diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index 5502e176d51b..860534bcfdac 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -46,6 +46,9 @@ struct efi __read_mostly efi = { #ifdef CONFIG_LOAD_UEFI_KEYS .mokvar_table = EFI_INVALID_TABLE_ADDR, #endif +#ifdef CONFIG_EFI_COCO_SECRET + .coco_secret = EFI_INVALID_TABLE_ADDR, +#endif }; EXPORT_SYMBOL(efi); @@ -66,7 +69,7 @@ struct mm_struct efi_mm = { struct workqueue_struct *efi_rts_wq; -static bool disable_runtime = IS_ENABLED(CONFIG_PREEMPT_RT); +static bool disable_runtime = IS_ENABLED(CONFIG_EFI_DISABLE_RUNTIME); static int __init setup_noefi(char *arg) { disable_runtime = true; @@ -422,6 +425,11 @@ static int __init efisubsys_init(void) if (efi_enabled(EFI_DBG) && efi_enabled(EFI_PRESERVE_BS_REGIONS)) efi_debugfs_init(); +#ifdef CONFIG_EFI_COCO_SECRET + if (efi.coco_secret != EFI_INVALID_TABLE_ADDR) + platform_device_register_simple("efi_secret", 0, NULL, 0); +#endif + return 0; err_remove_group: @@ -529,6 +537,9 @@ static const efi_config_table_type_t common_tables[] __initconst = { #ifdef CONFIG_LOAD_UEFI_KEYS {LINUX_EFI_MOK_VARIABLE_TABLE_GUID, &efi.mokvar_table, "MOKvar" }, #endif +#ifdef CONFIG_EFI_COCO_SECRET + {LINUX_EFI_COCO_SECRET_AREA_GUID, &efi.coco_secret, "CocoSecret" }, +#endif {}, }; diff --git a/drivers/firmware/efi/libstub/arm32-stub.c b/drivers/firmware/efi/libstub/arm32-stub.c index 4b5b2403b3a0..0131e3aaa605 100644 --- a/drivers/firmware/efi/libstub/arm32-stub.c +++ b/drivers/firmware/efi/libstub/arm32-stub.c @@ -117,7 +117,8 @@ efi_status_t handle_kernel_image(unsigned long *image_addr, unsigned long *image_size, unsigned long *reserve_addr, unsigned long *reserve_size, - efi_loaded_image_t *image) + efi_loaded_image_t *image, + efi_handle_t image_handle) { const int slack = TEXT_OFFSET - 5 * PAGE_SIZE; int alloc_size = MAX_UNCOMP_KERNEL_SIZE + EFI_PHYS_ALIGN; diff --git a/drivers/firmware/efi/libstub/arm64-stub.c b/drivers/firmware/efi/libstub/arm64-stub.c index 9cc556013d08..577173ee1f83 100644 --- a/drivers/firmware/efi/libstub/arm64-stub.c +++ b/drivers/firmware/efi/libstub/arm64-stub.c @@ -83,7 +83,8 @@ efi_status_t handle_kernel_image(unsigned long *image_addr, unsigned long *image_size, unsigned long *reserve_addr, unsigned long *reserve_size, - efi_loaded_image_t *image) + efi_loaded_image_t *image, + efi_handle_t image_handle) { efi_status_t status; unsigned long kernel_size, kernel_memsize = 0; @@ -100,7 +101,15 @@ efi_status_t handle_kernel_image(unsigned long *image_addr, u64 min_kimg_align = efi_nokaslr ? MIN_KIMG_ALIGN : EFI_KIMG_ALIGN; if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) { - if (!efi_nokaslr) { + efi_guid_t li_fixed_proto = LINUX_EFI_LOADED_IMAGE_FIXED_GUID; + void *p; + + if (efi_nokaslr) { + efi_info("KASLR disabled on kernel command line\n"); + } else if (efi_bs_call(handle_protocol, image_handle, + &li_fixed_proto, &p) == EFI_SUCCESS) { + efi_info("Image placement fixed by loader\n"); + } else { status = efi_get_random_bytes(sizeof(phys_seed), (u8 *)&phys_seed); if (status == EFI_NOT_FOUND) { @@ -111,8 +120,6 @@ efi_status_t handle_kernel_image(unsigned long *image_addr, status); efi_nokaslr = true; } - } else { - efi_info("KASLR disabled on kernel command line\n"); } } diff --git a/drivers/firmware/efi/libstub/efi-stub.c b/drivers/firmware/efi/libstub/efi-stub.c index da93864d7abc..f515394cce6e 100644 --- a/drivers/firmware/efi/libstub/efi-stub.c +++ b/drivers/firmware/efi/libstub/efi-stub.c @@ -198,7 +198,7 @@ efi_status_t __efiapi efi_pe_entry(efi_handle_t handle, status = handle_kernel_image(&image_addr, &image_size, &reserve_addr, &reserve_size, - image); + image, handle); if (status != EFI_SUCCESS) { efi_err("Failed to relocate kernel\n"); goto fail_free_screeninfo; diff --git a/drivers/firmware/efi/libstub/efistub.h b/drivers/firmware/efi/libstub/efistub.h index edb77b0621ea..b0ae0a454404 100644 --- a/drivers/firmware/efi/libstub/efistub.h +++ b/drivers/firmware/efi/libstub/efistub.h @@ -36,6 +36,9 @@ extern bool efi_novamap; extern const efi_system_table_t *efi_system_table; +typedef union efi_dxe_services_table efi_dxe_services_table_t; +extern const efi_dxe_services_table_t *efi_dxe_table; + efi_status_t __efiapi efi_pe_entry(efi_handle_t handle, efi_system_table_t *sys_table_arg); @@ -44,6 +47,7 @@ efi_status_t __efiapi efi_pe_entry(efi_handle_t handle, #define efi_is_native() (true) #define efi_bs_call(func, ...) efi_system_table->boottime->func(__VA_ARGS__) #define efi_rt_call(func, ...) efi_system_table->runtime->func(__VA_ARGS__) +#define efi_dxe_call(func, ...) efi_dxe_table->func(__VA_ARGS__) #define efi_table_attr(inst, attr) (inst->attr) #define efi_call_proto(inst, func, ...) inst->func(inst, ##__VA_ARGS__) @@ -329,6 +333,76 @@ union efi_boot_services { } mixed_mode; }; +typedef enum { + EfiGcdMemoryTypeNonExistent, + EfiGcdMemoryTypeReserved, + EfiGcdMemoryTypeSystemMemory, + EfiGcdMemoryTypeMemoryMappedIo, + EfiGcdMemoryTypePersistent, + EfiGcdMemoryTypeMoreReliable, + EfiGcdMemoryTypeMaximum +} efi_gcd_memory_type_t; + +typedef struct { + efi_physical_addr_t base_address; + u64 length; + u64 capabilities; + u64 attributes; + efi_gcd_memory_type_t gcd_memory_type; + void *image_handle; + void *device_handle; +} efi_gcd_memory_space_desc_t; + +/* + * EFI DXE Services table + */ +union efi_dxe_services_table { + struct { + efi_table_hdr_t hdr; + void *add_memory_space; + void *allocate_memory_space; + void *free_memory_space; + void *remove_memory_space; + efi_status_t (__efiapi *get_memory_space_descriptor)(efi_physical_addr_t, + efi_gcd_memory_space_desc_t *); + efi_status_t (__efiapi *set_memory_space_attributes)(efi_physical_addr_t, + u64, u64); + void *get_memory_space_map; + void *add_io_space; + void *allocate_io_space; + void *free_io_space; + void *remove_io_space; + void *get_io_space_descriptor; + void *get_io_space_map; + void *dispatch; + void *schedule; + void *trust; + void *process_firmware_volume; + void *set_memory_space_capabilities; + }; + struct { + efi_table_hdr_t hdr; + u32 add_memory_space; + u32 allocate_memory_space; + u32 free_memory_space; + u32 remove_memory_space; + u32 get_memory_space_descriptor; + u32 set_memory_space_attributes; + u32 get_memory_space_map; + u32 add_io_space; + u32 allocate_io_space; + u32 free_io_space; + u32 remove_io_space; + u32 get_io_space_descriptor; + u32 get_io_space_map; + u32 dispatch; + u32 schedule; + u32 trust; + u32 process_firmware_volume; + u32 set_memory_space_capabilities; + } mixed_mode; +}; + typedef union efi_uga_draw_protocol efi_uga_draw_protocol_t; union efi_uga_draw_protocol { @@ -720,6 +794,13 @@ union efi_tcg2_protocol { } mixed_mode; }; +struct riscv_efi_boot_protocol { + u64 revision; + + efi_status_t (__efiapi *get_boot_hartid)(struct riscv_efi_boot_protocol *, + unsigned long *boot_hartid); +}; + typedef union efi_load_file_protocol efi_load_file_protocol_t; typedef union efi_load_file_protocol efi_load_file2_protocol_t; @@ -865,7 +946,8 @@ efi_status_t handle_kernel_image(unsigned long *image_addr, unsigned long *image_size, unsigned long *reserve_addr, unsigned long *reserve_size, - efi_loaded_image_t *image); + efi_loaded_image_t *image, + efi_handle_t image_handle); asmlinkage void __noreturn efi_enter_kernel(unsigned long entrypoint, unsigned long fdt_addr, diff --git a/drivers/firmware/efi/libstub/randomalloc.c b/drivers/firmware/efi/libstub/randomalloc.c index 724155b9e10d..715f37479154 100644 --- a/drivers/firmware/efi/libstub/randomalloc.c +++ b/drivers/firmware/efi/libstub/randomalloc.c @@ -56,6 +56,7 @@ efi_status_t efi_random_alloc(unsigned long size, unsigned long random_seed) { unsigned long map_size, desc_size, total_slots = 0, target_slot; + unsigned long total_mirrored_slots = 0; unsigned long buff_size; efi_status_t status; efi_memory_desc_t *memory_map; @@ -86,8 +87,14 @@ efi_status_t efi_random_alloc(unsigned long size, slots = get_entry_num_slots(md, size, ilog2(align)); MD_NUM_SLOTS(md) = slots; total_slots += slots; + if (md->attribute & EFI_MEMORY_MORE_RELIABLE) + total_mirrored_slots += slots; } + /* consider only mirrored slots for randomization if any exist */ + if (total_mirrored_slots > 0) + total_slots = total_mirrored_slots; + /* find a random number between 0 and total_slots */ target_slot = (total_slots * (u64)(random_seed & U32_MAX)) >> 32; @@ -107,6 +114,10 @@ efi_status_t efi_random_alloc(unsigned long size, efi_physical_addr_t target; unsigned long pages; + if (total_mirrored_slots > 0 && + !(md->attribute & EFI_MEMORY_MORE_RELIABLE)) + continue; + if (target_slot >= MD_NUM_SLOTS(md)) { target_slot -= MD_NUM_SLOTS(md); continue; diff --git a/drivers/firmware/efi/libstub/riscv-stub.c b/drivers/firmware/efi/libstub/riscv-stub.c index 9c460843442f..9e85e58d1f27 100644 --- a/drivers/firmware/efi/libstub/riscv-stub.c +++ b/drivers/firmware/efi/libstub/riscv-stub.c @@ -21,9 +21,9 @@ #define MIN_KIMG_ALIGN SZ_4M #endif -typedef void __noreturn (*jump_kernel_func)(unsigned int, unsigned long); +typedef void __noreturn (*jump_kernel_func)(unsigned long, unsigned long); -static u32 hartid; +static unsigned long hartid; static int get_boot_hartid_from_fdt(void) { @@ -47,14 +47,31 @@ static int get_boot_hartid_from_fdt(void) return 0; } +static efi_status_t get_boot_hartid_from_efi(void) +{ + efi_guid_t boot_protocol_guid = RISCV_EFI_BOOT_PROTOCOL_GUID; + struct riscv_efi_boot_protocol *boot_protocol; + efi_status_t status; + + status = efi_bs_call(locate_protocol, &boot_protocol_guid, NULL, + (void **)&boot_protocol); + if (status != EFI_SUCCESS) + return status; + return efi_call_proto(boot_protocol, get_boot_hartid, &hartid); +} + efi_status_t check_platform_features(void) { + efi_status_t status; int ret; - ret = get_boot_hartid_from_fdt(); - if (ret) { - efi_err("/chosen/boot-hartid missing or invalid!\n"); - return EFI_UNSUPPORTED; + status = get_boot_hartid_from_efi(); + if (status != EFI_SUCCESS) { + ret = get_boot_hartid_from_fdt(); + if (ret) { + efi_err("Failed to get boot hartid!\n"); + return EFI_UNSUPPORTED; + } } return EFI_SUCCESS; } @@ -80,7 +97,8 @@ efi_status_t handle_kernel_image(unsigned long *image_addr, unsigned long *image_size, unsigned long *reserve_addr, unsigned long *reserve_size, - efi_loaded_image_t *image) + efi_loaded_image_t *image, + efi_handle_t image_handle) { unsigned long kernel_size = 0; unsigned long preferred_addr; diff --git a/drivers/firmware/efi/libstub/x86-stub.c b/drivers/firmware/efi/libstub/x86-stub.c index 01ddd4502e28..b14e88ccefca 100644 --- a/drivers/firmware/efi/libstub/x86-stub.c +++ b/drivers/firmware/efi/libstub/x86-stub.c @@ -22,6 +22,7 @@ #define MAXMEM_X86_64_4LEVEL (1ull << 46) const efi_system_table_t *efi_system_table; +const efi_dxe_services_table_t *efi_dxe_table; extern u32 image_offset; static efi_loaded_image_t *image = NULL; @@ -211,9 +212,110 @@ static void retrieve_apple_device_properties(struct boot_params *boot_params) } } +static void +adjust_memory_range_protection(unsigned long start, unsigned long size) +{ + efi_status_t status; + efi_gcd_memory_space_desc_t desc; + unsigned long end, next; + unsigned long rounded_start, rounded_end; + unsigned long unprotect_start, unprotect_size; + int has_system_memory = 0; + + if (efi_dxe_table == NULL) + return; + + rounded_start = rounddown(start, EFI_PAGE_SIZE); + rounded_end = roundup(start + size, EFI_PAGE_SIZE); + + /* + * Don't modify memory region attributes, they are + * already suitable, to lower the possibility to + * encounter firmware bugs. + */ + + for (end = start + size; start < end; start = next) { + + status = efi_dxe_call(get_memory_space_descriptor, start, &desc); + + if (status != EFI_SUCCESS) + return; + + next = desc.base_address + desc.length; + + /* + * Only system memory is suitable for trampoline/kernel image placement, + * so only this type of memory needs its attributes to be modified. + */ + + if (desc.gcd_memory_type != EfiGcdMemoryTypeSystemMemory || + (desc.attributes & (EFI_MEMORY_RO | EFI_MEMORY_XP)) == 0) + continue; + + unprotect_start = max(rounded_start, (unsigned long)desc.base_address); + unprotect_size = min(rounded_end, next) - unprotect_start; + + status = efi_dxe_call(set_memory_space_attributes, + unprotect_start, unprotect_size, + EFI_MEMORY_WB); + + if (status != EFI_SUCCESS) { + efi_warn("Unable to unprotect memory range [%08lx,%08lx]: %d\n", + unprotect_start, + unprotect_start + unprotect_size, + (int)status); + } + } +} + +/* + * Trampoline takes 2 pages and can be loaded in first megabyte of memory + * with its end placed between 128k and 640k where BIOS might start. + * (see arch/x86/boot/compressed/pgtable_64.c) + * + * We cannot find exact trampoline placement since memory map + * can be modified by UEFI, and it can alter the computed address. + */ + +#define TRAMPOLINE_PLACEMENT_BASE ((128 - 8)*1024) +#define TRAMPOLINE_PLACEMENT_SIZE (640*1024 - (128 - 8)*1024) + +void startup_32(struct boot_params *boot_params); + +static void +setup_memory_protection(unsigned long image_base, unsigned long image_size) +{ + /* + * Allow execution of possible trampoline used + * for switching between 4- and 5-level page tables + * and relocated kernel image. + */ + + adjust_memory_range_protection(TRAMPOLINE_PLACEMENT_BASE, + TRAMPOLINE_PLACEMENT_SIZE); + +#ifdef CONFIG_64BIT + if (image_base != (unsigned long)startup_32) + adjust_memory_range_protection(image_base, image_size); +#else + /* + * Clear protection flags on a whole range of possible + * addresses used for KASLR. We don't need to do that + * on x86_64, since KASLR/extraction is performed after + * dedicated identity page tables are built and we only + * need to remove possible protection on relocated image + * itself disregarding further relocations. + */ + adjust_memory_range_protection(LOAD_PHYSICAL_ADDR, + KERNEL_IMAGE_SIZE - LOAD_PHYSICAL_ADDR); +#endif +} + static const efi_char16_t apple[] = L"Apple"; -static void setup_quirks(struct boot_params *boot_params) +static void setup_quirks(struct boot_params *boot_params, + unsigned long image_base, + unsigned long image_size) { efi_char16_t *fw_vendor = (efi_char16_t *)(unsigned long) efi_table_attr(efi_system_table, fw_vendor); @@ -222,6 +324,9 @@ static void setup_quirks(struct boot_params *boot_params) if (IS_ENABLED(CONFIG_APPLE_PROPERTIES)) retrieve_apple_device_properties(boot_params); } + + if (IS_ENABLED(CONFIG_EFI_DXE_MEM_ATTRIBUTES)) + setup_memory_protection(image_base, image_size); } /* @@ -341,8 +446,6 @@ static void __noreturn efi_exit(efi_handle_t handle, efi_status_t status) asm("hlt"); } -void startup_32(struct boot_params *boot_params); - void __noreturn efi_stub_entry(efi_handle_t handle, efi_system_table_t *sys_table_arg, struct boot_params *boot_params); @@ -677,11 +780,17 @@ unsigned long efi_main(efi_handle_t handle, efi_status_t status; efi_system_table = sys_table_arg; - /* Check if we were booted by the EFI firmware */ if (efi_system_table->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE) efi_exit(handle, EFI_INVALID_PARAMETER); + efi_dxe_table = get_efi_config_table(EFI_DXE_SERVICES_TABLE_GUID); + if (efi_dxe_table && + efi_dxe_table->hdr.signature != EFI_DXE_SERVICES_TABLE_SIGNATURE) { + efi_warn("Ignoring DXE services table: invalid signature\n"); + efi_dxe_table = NULL; + } + /* * If the kernel isn't already loaded at a suitable address, * relocate it. @@ -791,7 +900,7 @@ unsigned long efi_main(efi_handle_t handle, setup_efi_pci(boot_params); - setup_quirks(boot_params); + setup_quirks(boot_params, bzimage_addr, buffer_end - buffer_start); status = exit_boot(boot_params, handle); if (status != EFI_SUCCESS) { diff --git a/drivers/gpio/TODO b/drivers/gpio/TODO index b8b1473a5b1e..f87ff3fa8a53 100644 --- a/drivers/gpio/TODO +++ b/drivers/gpio/TODO @@ -178,3 +178,22 @@ discussed but the idea is to provide a low-level access point for debugging and hacking and to expose all lines without the need of any exporting. Also provide ample ammunition to shoot oneself in the foot, because this is debugfs after all. + + +Moving over to immutable irq_chip structures + +Most of the gpio chips implementing interrupt support rely on gpiolib +intercepting some of the irq_chip callbacks, preventing the structures +from being made read-only and forcing duplication of structures that +should otherwise be unique. + +The solution is to call into the gpiolib code when needed (resource +management, enable/disable or unmask/mask callbacks), and to let the +core code know about that by exposing a flag (IRQCHIP_IMMUTABLE) in +the irq_chip structure. The irq_chip structure can then be made unique +and const. + +A small number of drivers have been converted (pl061, tegra186, msm, +amd, apple), and can be used as examples of how to proceed with this +conversion. Note that drivers using the generic irqchip framework +cannot be converted yet, but watch this space! diff --git a/drivers/gpio/gpio-mvebu.c b/drivers/gpio/gpio-mvebu.c index 4c1f9e1091b7..2db19cd640a4 100644 --- a/drivers/gpio/gpio-mvebu.c +++ b/drivers/gpio/gpio-mvebu.c @@ -707,6 +707,9 @@ static int mvebu_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm, unsigned long flags; unsigned int on, off; + if (state->polarity != PWM_POLARITY_NORMAL) + return -EINVAL; + val = (unsigned long long) mvpwm->clk_rate * state->duty_cycle; do_div(val, NSEC_PER_SEC); if (val > UINT_MAX + 1ULL) @@ -871,13 +874,6 @@ static int mvebu_pwm_probe(struct platform_device *pdev, mvpwm->chip.dev = dev; mvpwm->chip.ops = &mvebu_pwm_ops; mvpwm->chip.npwm = mvchip->chip.ngpio; - /* - * There may already be some PWM allocated, so we can't force - * mvpwm->chip.base to a fixed point like mvchip->chip.base. - * So, we let pwmchip_add() do the numbering and take the next free - * region. - */ - mvpwm->chip.base = -1; spin_lock_init(&mvpwm->lock); diff --git a/drivers/gpio/gpio-pca953x.c b/drivers/gpio/gpio-pca953x.c index d2fe76f3f34f..8726921a1129 100644 --- a/drivers/gpio/gpio-pca953x.c +++ b/drivers/gpio/gpio-pca953x.c @@ -762,11 +762,11 @@ static bool pca953x_irq_pending(struct pca953x_chip *chip, unsigned long *pendin bitmap_xor(cur_stat, new_stat, old_stat, gc->ngpio); bitmap_and(trigger, cur_stat, chip->irq_mask, gc->ngpio); + bitmap_copy(chip->irq_stat, new_stat, gc->ngpio); + if (bitmap_empty(trigger, gc->ngpio)) return false; - bitmap_copy(chip->irq_stat, new_stat, gc->ngpio); - bitmap_and(cur_stat, chip->irq_trig_fall, old_stat, gc->ngpio); bitmap_and(old_stat, chip->irq_trig_raise, new_stat, gc->ngpio); bitmap_or(new_stat, old_stat, cur_stat, gc->ngpio); diff --git a/drivers/gpio/gpio-pl061.c b/drivers/gpio/gpio-pl061.c index 4ecab700f23f..6464056cb6ae 100644 --- a/drivers/gpio/gpio-pl061.c +++ b/drivers/gpio/gpio-pl061.c @@ -52,7 +52,6 @@ struct pl061 { void __iomem *base; struct gpio_chip gc; - struct irq_chip irq_chip; int parent_irq; #ifdef CONFIG_PM @@ -241,6 +240,8 @@ static void pl061_irq_mask(struct irq_data *d) gpioie = readb(pl061->base + GPIOIE) & ~mask; writeb(gpioie, pl061->base + GPIOIE); raw_spin_unlock(&pl061->lock); + + gpiochip_disable_irq(gc, d->hwirq); } static void pl061_irq_unmask(struct irq_data *d) @@ -250,6 +251,8 @@ static void pl061_irq_unmask(struct irq_data *d) u8 mask = BIT(irqd_to_hwirq(d) % PL061_GPIO_NR); u8 gpioie; + gpiochip_enable_irq(gc, d->hwirq); + raw_spin_lock(&pl061->lock); gpioie = readb(pl061->base + GPIOIE) | mask; writeb(gpioie, pl061->base + GPIOIE); @@ -283,6 +286,24 @@ static int pl061_irq_set_wake(struct irq_data *d, unsigned int state) return irq_set_irq_wake(pl061->parent_irq, state); } +static void pl061_irq_print_chip(struct irq_data *data, struct seq_file *p) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(data); + + seq_printf(p, dev_name(gc->parent)); +} + +static const struct irq_chip pl061_irq_chip = { + .irq_ack = pl061_irq_ack, + .irq_mask = pl061_irq_mask, + .irq_unmask = pl061_irq_unmask, + .irq_set_type = pl061_irq_type, + .irq_set_wake = pl061_irq_set_wake, + .irq_print_chip = pl061_irq_print_chip, + .flags = IRQCHIP_IMMUTABLE, + GPIOCHIP_IRQ_RESOURCE_HELPERS, +}; + static int pl061_probe(struct amba_device *adev, const struct amba_id *id) { struct device *dev = &adev->dev; @@ -315,13 +336,6 @@ static int pl061_probe(struct amba_device *adev, const struct amba_id *id) /* * irq_chip support */ - pl061->irq_chip.name = dev_name(dev); - pl061->irq_chip.irq_ack = pl061_irq_ack; - pl061->irq_chip.irq_mask = pl061_irq_mask; - pl061->irq_chip.irq_unmask = pl061_irq_unmask; - pl061->irq_chip.irq_set_type = pl061_irq_type; - pl061->irq_chip.irq_set_wake = pl061_irq_set_wake; - writeb(0, pl061->base + GPIOIE); /* disable irqs */ irq = adev->irq[0]; if (!irq) @@ -329,7 +343,7 @@ static int pl061_probe(struct amba_device *adev, const struct amba_id *id) pl061->parent_irq = irq; girq = &pl061->gc.irq; - girq->chip = &pl061->irq_chip; + gpio_irq_chip_set_chip(girq, &pl061_irq_chip); girq->parent_handler = pl061_irq_handler; girq->num_parents = 1; girq->parents = devm_kcalloc(dev, 1, sizeof(*girq->parents), diff --git a/drivers/gpio/gpio-sim.c b/drivers/gpio/gpio-sim.c index 8e5d87984a48..41c31b10ae84 100644 --- a/drivers/gpio/gpio-sim.c +++ b/drivers/gpio/gpio-sim.c @@ -134,7 +134,7 @@ static int gpio_sim_get_multiple(struct gpio_chip *gc, struct gpio_sim_chip *chip = gpiochip_get_data(gc); mutex_lock(&chip->lock); - bitmap_copy(bits, chip->value_map, gc->ngpio); + bitmap_replace(bits, bits, chip->value_map, mask, gc->ngpio); mutex_unlock(&chip->lock); return 0; @@ -146,7 +146,7 @@ static void gpio_sim_set_multiple(struct gpio_chip *gc, struct gpio_sim_chip *chip = gpiochip_get_data(gc); mutex_lock(&chip->lock); - bitmap_copy(chip->value_map, bits, gc->ngpio); + bitmap_replace(chip->value_map, chip->value_map, bits, mask, gc->ngpio); mutex_unlock(&chip->lock); } diff --git a/drivers/gpio/gpio-tegra186.c b/drivers/gpio/gpio-tegra186.c index 031fe105b58e..84c4f1e9fb0c 100644 --- a/drivers/gpio/gpio-tegra186.c +++ b/drivers/gpio/gpio-tegra186.c @@ -80,7 +80,6 @@ struct tegra_gpio_soc { struct tegra_gpio { struct gpio_chip gpio; - struct irq_chip intc; unsigned int num_irq; unsigned int *irq; @@ -372,6 +371,8 @@ static void tegra186_irq_mask(struct irq_data *data) value = readl(base + TEGRA186_GPIO_ENABLE_CONFIG); value &= ~TEGRA186_GPIO_ENABLE_CONFIG_INTERRUPT; writel(value, base + TEGRA186_GPIO_ENABLE_CONFIG); + + gpiochip_disable_irq(&gpio->gpio, data->hwirq); } static void tegra186_irq_unmask(struct irq_data *data) @@ -385,6 +386,8 @@ static void tegra186_irq_unmask(struct irq_data *data) if (WARN_ON(base == NULL)) return; + gpiochip_enable_irq(&gpio->gpio, data->hwirq); + value = readl(base + TEGRA186_GPIO_ENABLE_CONFIG); value |= TEGRA186_GPIO_ENABLE_CONFIG_INTERRUPT; writel(value, base + TEGRA186_GPIO_ENABLE_CONFIG); @@ -456,6 +459,24 @@ static int tegra186_irq_set_wake(struct irq_data *data, unsigned int on) return 0; } +static void tegra186_irq_print_chip(struct irq_data *data, struct seq_file *p) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(data); + + seq_printf(p, dev_name(gc->parent)); +} + +static const struct irq_chip tegra186_gpio_irq_chip = { + .irq_ack = tegra186_irq_ack, + .irq_mask = tegra186_irq_mask, + .irq_unmask = tegra186_irq_unmask, + .irq_set_type = tegra186_irq_set_type, + .irq_set_wake = tegra186_irq_set_wake, + .irq_print_chip = tegra186_irq_print_chip, + .flags = IRQCHIP_IMMUTABLE, + GPIOCHIP_IRQ_RESOURCE_HELPERS, +}; + static void tegra186_gpio_irq(struct irq_desc *desc) { struct tegra_gpio *gpio = irq_desc_get_handler_data(desc); @@ -760,15 +781,8 @@ static int tegra186_gpio_probe(struct platform_device *pdev) gpio->gpio.of_xlate = tegra186_gpio_of_xlate; #endif /* CONFIG_OF_GPIO */ - gpio->intc.name = dev_name(&pdev->dev); - gpio->intc.irq_ack = tegra186_irq_ack; - gpio->intc.irq_mask = tegra186_irq_mask; - gpio->intc.irq_unmask = tegra186_irq_unmask; - gpio->intc.irq_set_type = tegra186_irq_set_type; - gpio->intc.irq_set_wake = tegra186_irq_set_wake; - irq = &gpio->gpio.irq; - irq->chip = &gpio->intc; + gpio_irq_chip_set_chip(irq, &tegra186_gpio_irq_chip); irq->fwnode = of_node_to_fwnode(pdev->dev.of_node); irq->child_to_parent_hwirq = tegra186_gpio_child_to_parent_hwirq; irq->populate_parent_alloc_arg = tegra186_gpio_populate_parent_fwspec; diff --git a/drivers/gpio/gpio-vf610.c b/drivers/gpio/gpio-vf610.c index 20780c35da1b..23cddb265a0d 100644 --- a/drivers/gpio/gpio-vf610.c +++ b/drivers/gpio/gpio-vf610.c @@ -125,9 +125,13 @@ static int vf610_gpio_direction_output(struct gpio_chip *chip, unsigned gpio, { struct vf610_gpio_port *port = gpiochip_get_data(chip); unsigned long mask = BIT(gpio); + u32 val; - if (port->sdata && port->sdata->have_paddr) - vf610_gpio_writel(mask, port->gpio_base + GPIO_PDDR); + if (port->sdata && port->sdata->have_paddr) { + val = vf610_gpio_readl(port->gpio_base + GPIO_PDDR); + val |= mask; + vf610_gpio_writel(val, port->gpio_base + GPIO_PDDR); + } vf610_gpio_set(chip, gpio, value); diff --git a/drivers/gpio/gpio-visconti.c b/drivers/gpio/gpio-visconti.c index 47455810bdb9..e6534ea1eaa7 100644 --- a/drivers/gpio/gpio-visconti.c +++ b/drivers/gpio/gpio-visconti.c @@ -130,7 +130,6 @@ static int visconti_gpio_probe(struct platform_device *pdev) struct gpio_irq_chip *girq; struct irq_domain *parent; struct device_node *irq_parent; - struct fwnode_handle *fwnode; int ret; priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); @@ -150,14 +149,12 @@ static int visconti_gpio_probe(struct platform_device *pdev) } parent = irq_find_host(irq_parent); + of_node_put(irq_parent); if (!parent) { dev_err(dev, "No IRQ parent domain\n"); return -ENODEV; } - fwnode = of_node_to_fwnode(irq_parent); - of_node_put(irq_parent); - ret = bgpio_init(&priv->gpio_chip, dev, 4, priv->base + GPIO_IDATA, priv->base + GPIO_OSET, @@ -180,7 +177,7 @@ static int visconti_gpio_probe(struct platform_device *pdev) girq = &priv->gpio_chip.irq; girq->chip = irq_chip; - girq->fwnode = fwnode; + girq->fwnode = of_node_to_fwnode(dev->of_node); girq->parent_domain = parent; girq->child_to_parent_hwirq = visconti_gpio_child_to_parent_hwirq; girq->populate_parent_alloc_arg = visconti_gpio_populate_parent_fwspec; diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c index a5495ad31c9c..c2523ac26fac 100644 --- a/drivers/gpio/gpiolib-acpi.c +++ b/drivers/gpio/gpiolib-acpi.c @@ -108,7 +108,7 @@ static int acpi_gpiochip_find(struct gpio_chip *gc, void *data) * controller does not have GPIO chip registered at the moment. This is to * support probe deferral. */ -static struct gpio_desc *acpi_get_gpiod(char *path, int pin) +static struct gpio_desc *acpi_get_gpiod(char *path, unsigned int pin) { struct gpio_chip *chip; acpi_handle handle; @@ -136,7 +136,7 @@ static struct gpio_desc *acpi_get_gpiod(char *path, int pin) * as it is intended for use outside of the GPIO layer (in a similar fashion to * gpiod_get_index() for example) it also holds a reference to the GPIO device. */ -struct gpio_desc *acpi_get_and_request_gpiod(char *path, int pin, char *label) +struct gpio_desc *acpi_get_and_request_gpiod(char *path, unsigned int pin, char *label) { struct gpio_desc *gpio; int ret; @@ -317,11 +317,12 @@ static struct gpio_desc *acpi_request_own_gpiod(struct gpio_chip *chip, return desc; } -static bool acpi_gpio_in_ignore_list(const char *controller_in, int pin_in) +static bool acpi_gpio_in_ignore_list(const char *controller_in, unsigned int pin_in) { const char *controller, *pin_str; - int len, pin; + unsigned int pin; char *endp; + int len; controller = ignore_wake; while (controller) { @@ -354,13 +355,13 @@ err: static bool acpi_gpio_irq_is_wake(struct device *parent, struct acpi_resource_gpio *agpio) { - int pin = agpio->pin_table[0]; + unsigned int pin = agpio->pin_table[0]; if (agpio->wake_capable != ACPI_WAKE_CAPABLE) return false; if (acpi_gpio_in_ignore_list(dev_name(parent), pin)) { - dev_info(parent, "Ignoring wakeup on pin %d\n", pin); + dev_info(parent, "Ignoring wakeup on pin %u\n", pin); return false; } @@ -378,7 +379,8 @@ static acpi_status acpi_gpiochip_alloc_event(struct acpi_resource *ares, struct acpi_gpio_event *event; irq_handler_t handler = NULL; struct gpio_desc *desc; - int ret, pin, irq; + unsigned int pin; + int ret, irq; if (!acpi_gpio_get_irq_resource(ares, &agpio)) return AE_OK; @@ -387,8 +389,8 @@ static acpi_status acpi_gpiochip_alloc_event(struct acpi_resource *ares, pin = agpio->pin_table[0]; if (pin <= 255) { - char ev_name[5]; - sprintf(ev_name, "_%c%02hhX", + char ev_name[8]; + sprintf(ev_name, "_%c%02X", agpio->triggering == ACPI_EDGE_SENSITIVE ? 'E' : 'L', pin); if (ACPI_SUCCESS(acpi_get_handle(handle, ev_name, &evt_handle))) @@ -1098,7 +1100,7 @@ acpi_gpio_adr_space_handler(u32 function, acpi_physical_address address, length = min_t(u16, agpio->pin_table_length, pin_index + bits); for (i = pin_index; i < length; ++i) { - int pin = agpio->pin_table[i]; + unsigned int pin = agpio->pin_table[i]; struct acpi_gpio_connection *conn; struct gpio_desc *desc; bool found; diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c index ae1ce319cd78..7e5e51d49d09 100644 --- a/drivers/gpio/gpiolib-of.c +++ b/drivers/gpio/gpiolib-of.c @@ -910,7 +910,7 @@ static void of_gpiochip_init_valid_mask(struct gpio_chip *chip) i, &start); of_property_read_u32_index(np, "gpio-reserved-ranges", i + 1, &count); - if (start >= chip->ngpio || start + count >= chip->ngpio) + if (start >= chip->ngpio || start + count > chip->ngpio) continue; bitmap_clear(chip->valid_mask, start, count); diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index e59884cc12a7..690035124faa 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -1404,6 +1404,16 @@ static int gpiochip_to_irq(struct gpio_chip *gc, unsigned int offset) { struct irq_domain *domain = gc->irq.domain; +#ifdef CONFIG_GPIOLIB_IRQCHIP + /* + * Avoid race condition with other code, which tries to lookup + * an IRQ before the irqchip has been properly registered, + * i.e. while gpiochip is still being brought up. + */ + if (!gc->irq.initialized) + return -EPROBE_DEFER; +#endif + if (!gpiochip_irqchip_irq_valid(gc, offset)) return -ENXIO; @@ -1423,19 +1433,21 @@ static int gpiochip_to_irq(struct gpio_chip *gc, unsigned int offset) return irq_create_mapping(domain, offset); } -static int gpiochip_irq_reqres(struct irq_data *d) +int gpiochip_irq_reqres(struct irq_data *d) { struct gpio_chip *gc = irq_data_get_irq_chip_data(d); return gpiochip_reqres_irq(gc, d->hwirq); } +EXPORT_SYMBOL(gpiochip_irq_reqres); -static void gpiochip_irq_relres(struct irq_data *d) +void gpiochip_irq_relres(struct irq_data *d) { struct gpio_chip *gc = irq_data_get_irq_chip_data(d); gpiochip_relres_irq(gc, d->hwirq); } +EXPORT_SYMBOL(gpiochip_irq_relres); static void gpiochip_irq_mask(struct irq_data *d) { @@ -1475,6 +1487,11 @@ static void gpiochip_set_irq_hooks(struct gpio_chip *gc) { struct irq_chip *irqchip = gc->irq.chip; + if (irqchip->flags & IRQCHIP_IMMUTABLE) + return; + + chip_warn(gc, "not an immutable chip, please consider fixing it!\n"); + if (!irqchip->irq_request_resources && !irqchip->irq_release_resources) { irqchip->irq_request_resources = gpiochip_irq_reqres; @@ -1591,6 +1608,15 @@ static int gpiochip_add_irqchip(struct gpio_chip *gc, gpiochip_set_irq_hooks(gc); + /* + * Using barrier() here to prevent compiler from reordering + * gc->irq.initialized before initialization of above + * GPIO chip irq members. + */ + barrier(); + + gc->irq.initialized = true; + acpi_gpiochip_request_interrupts(gc); return 0; @@ -1633,7 +1659,7 @@ static void gpiochip_irqchip_remove(struct gpio_chip *gc) irq_domain_remove(gc->irq.domain); } - if (irqchip) { + if (irqchip && !(irqchip->flags & IRQCHIP_IMMUTABLE)) { if (irqchip->irq_request_resources == gpiochip_irq_reqres) { irqchip->irq_request_resources = NULL; irqchip->irq_release_resources = NULL; diff --git a/drivers/gpu/drm/amd/amdgpu/ObjectID.h b/drivers/gpu/drm/amd/amdgpu/ObjectID.h index 5b393622f592..a0f0a17e224f 100644 --- a/drivers/gpu/drm/amd/amdgpu/ObjectID.h +++ b/drivers/gpu/drm/amd/amdgpu/ObjectID.h @@ -119,6 +119,7 @@ #define CONNECTOR_OBJECT_ID_eDP 0x14 #define CONNECTOR_OBJECT_ID_MXM 0x15 #define CONNECTOR_OBJECT_ID_LVDS_eDP 0x16 +#define CONNECTOR_OBJECT_ID_USBC 0x17 /* deleted */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index cdf0818088b3..7606e3b6361e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -1342,9 +1342,11 @@ static inline int amdgpu_acpi_smart_shift_update(struct drm_device *dev, #if defined(CONFIG_ACPI) && defined(CONFIG_SUSPEND) bool amdgpu_acpi_is_s3_active(struct amdgpu_device *adev); +bool amdgpu_acpi_should_gpu_reset(struct amdgpu_device *adev); bool amdgpu_acpi_is_s0ix_active(struct amdgpu_device *adev); #else static inline bool amdgpu_acpi_is_s0ix_active(struct amdgpu_device *adev) { return false; } +static inline bool amdgpu_acpi_should_gpu_reset(struct amdgpu_device *adev) { return false; } static inline bool amdgpu_acpi_is_s3_active(struct amdgpu_device *adev) { return false; } #endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c index 0e12315fa0cb..98ac53ee6bb5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c @@ -1046,6 +1046,20 @@ bool amdgpu_acpi_is_s3_active(struct amdgpu_device *adev) } /** + * amdgpu_acpi_should_gpu_reset + * + * @adev: amdgpu_device_pointer + * + * returns true if should reset GPU, false if not + */ +bool amdgpu_acpi_should_gpu_reset(struct amdgpu_device *adev) +{ + if (adev->flags & AMD_IS_APU) + return false; + return pm_suspend_target_state != PM_SUSPEND_TO_IDLE; +} + +/** * amdgpu_acpi_is_s0ix_active * * @adev: amdgpu_device_pointer diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index 970b065e9a6b..d0d0ea565e3d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -128,6 +128,8 @@ static int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, union drm_amdgpu_cs goto free_chunk; } + mutex_lock(&p->ctx->lock); + /* skip guilty context job */ if (atomic_read(&p->ctx->guilty) == 1) { ret = -ECANCELED; @@ -709,6 +711,7 @@ static void amdgpu_cs_parser_fini(struct amdgpu_cs_parser *parser, int error, dma_fence_put(parser->fence); if (parser->ctx) { + mutex_unlock(&parser->ctx->lock); amdgpu_ctx_put(parser->ctx); } if (parser->bo_list) @@ -1157,6 +1160,9 @@ static int amdgpu_cs_dependencies(struct amdgpu_device *adev, { int i, r; + /* TODO: Investigate why we still need the context lock */ + mutex_unlock(&p->ctx->lock); + for (i = 0; i < p->nchunks; ++i) { struct amdgpu_cs_chunk *chunk; @@ -1167,32 +1173,34 @@ static int amdgpu_cs_dependencies(struct amdgpu_device *adev, case AMDGPU_CHUNK_ID_SCHEDULED_DEPENDENCIES: r = amdgpu_cs_process_fence_dep(p, chunk); if (r) - return r; + goto out; break; case AMDGPU_CHUNK_ID_SYNCOBJ_IN: r = amdgpu_cs_process_syncobj_in_dep(p, chunk); if (r) - return r; + goto out; break; case AMDGPU_CHUNK_ID_SYNCOBJ_OUT: r = amdgpu_cs_process_syncobj_out_dep(p, chunk); if (r) - return r; + goto out; break; case AMDGPU_CHUNK_ID_SYNCOBJ_TIMELINE_WAIT: r = amdgpu_cs_process_syncobj_timeline_in_dep(p, chunk); if (r) - return r; + goto out; break; case AMDGPU_CHUNK_ID_SYNCOBJ_TIMELINE_SIGNAL: r = amdgpu_cs_process_syncobj_timeline_out_dep(p, chunk); if (r) - return r; + goto out; break; } } - return 0; +out: + mutex_lock(&p->ctx->lock); + return r; } static void amdgpu_cs_post_dependencies(struct amdgpu_cs_parser *p) @@ -1368,6 +1376,7 @@ int amdgpu_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) goto out; r = amdgpu_cs_submit(&parser, cs); + out: amdgpu_cs_parser_fini(&parser, r, reserved_buffers); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c index 5981c7d9bd48..c317078d1afd 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c @@ -237,6 +237,7 @@ static int amdgpu_ctx_init(struct amdgpu_device *adev, kref_init(&ctx->refcount); spin_lock_init(&ctx->ring_lock); + mutex_init(&ctx->lock); ctx->reset_counter = atomic_read(&adev->gpu_reset_counter); ctx->reset_counter_query = ctx->reset_counter; @@ -295,6 +296,7 @@ static int amdgpu_ctx_set_stable_pstate(struct amdgpu_ctx *ctx, { struct amdgpu_device *adev = ctx->adev; enum amd_dpm_forced_level level; + u32 current_stable_pstate; int r; mutex_lock(&adev->pm.stable_pstate_ctx_lock); @@ -303,6 +305,10 @@ static int amdgpu_ctx_set_stable_pstate(struct amdgpu_ctx *ctx, goto done; } + r = amdgpu_ctx_get_stable_pstate(ctx, ¤t_stable_pstate); + if (r || (stable_pstate == current_stable_pstate)) + goto done; + switch (stable_pstate) { case AMDGPU_CTX_STABLE_PSTATE_NONE: level = AMD_DPM_FORCED_LEVEL_AUTO; @@ -357,6 +363,7 @@ static void amdgpu_ctx_fini(struct kref *ref) drm_dev_exit(idx); } + mutex_destroy(&ctx->lock); kfree(ctx); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.h index d0cbfcea90f7..142f2f87d44c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.h @@ -49,6 +49,7 @@ struct amdgpu_ctx { bool preamble_presented; int32_t init_priority; int32_t override_priority; + struct mutex lock; atomic_t guilty; unsigned long ras_counter_ce; unsigned long ras_counter_ue; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 3987ecb24ef4..49f734137f15 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -5733,7 +5733,7 @@ void amdgpu_device_flush_hdp(struct amdgpu_device *adev, struct amdgpu_ring *ring) { #ifdef CONFIG_X86_64 - if (adev->flags & AMD_IS_APU) + if ((adev->flags & AMD_IS_APU) && !amdgpu_passthrough(adev)) return; #endif if (adev->gmc.xgmi.connected_to_cpu) @@ -5749,7 +5749,7 @@ void amdgpu_device_invalidate_hdp(struct amdgpu_device *adev, struct amdgpu_ring *ring) { #ifdef CONFIG_X86_64 - if (adev->flags & AMD_IS_APU) + if ((adev->flags & AMD_IS_APU) && !amdgpu_passthrough(adev)) return; #endif if (adev->gmc.xgmi.connected_to_cpu) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index bb1c025d9001..46ef57b07c15 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -680,7 +680,7 @@ MODULE_PARM_DESC(sched_policy, * Maximum number of processes that HWS can schedule concurrently. The maximum is the * number of VMIDs assigned to the HWS, which is also the default. */ -int hws_max_conc_proc = 8; +int hws_max_conc_proc = -1; module_param(hws_max_conc_proc, int, 0444); MODULE_PARM_DESC(hws_max_conc_proc, "Max # processes HWS can execute concurrently when sched_policy=0 (0 = no concurrency, #VMIDs for KFD = Maximum(default))"); @@ -2323,18 +2323,23 @@ static int amdgpu_pmops_suspend(struct device *dev) { struct drm_device *drm_dev = dev_get_drvdata(dev); struct amdgpu_device *adev = drm_to_adev(drm_dev); - int r; if (amdgpu_acpi_is_s0ix_active(adev)) adev->in_s0ix = true; else adev->in_s3 = true; - r = amdgpu_device_suspend(drm_dev, true); - if (r) - return r; - if (!adev->in_s0ix) - r = amdgpu_asic_reset(adev); - return r; + return amdgpu_device_suspend(drm_dev, true); +} + +static int amdgpu_pmops_suspend_noirq(struct device *dev) +{ + struct drm_device *drm_dev = dev_get_drvdata(dev); + struct amdgpu_device *adev = drm_to_adev(drm_dev); + + if (amdgpu_acpi_should_gpu_reset(adev)) + return amdgpu_asic_reset(adev); + + return 0; } static int amdgpu_pmops_resume(struct device *dev) @@ -2390,6 +2395,71 @@ static int amdgpu_pmops_restore(struct device *dev) return amdgpu_device_resume(drm_dev, true); } +static int amdgpu_runtime_idle_check_display(struct device *dev) +{ + struct pci_dev *pdev = to_pci_dev(dev); + struct drm_device *drm_dev = pci_get_drvdata(pdev); + struct amdgpu_device *adev = drm_to_adev(drm_dev); + + if (adev->mode_info.num_crtc) { + struct drm_connector *list_connector; + struct drm_connector_list_iter iter; + int ret = 0; + + /* XXX: Return busy if any displays are connected to avoid + * possible display wakeups after runtime resume due to + * hotplug events in case any displays were connected while + * the GPU was in suspend. Remove this once that is fixed. + */ + mutex_lock(&drm_dev->mode_config.mutex); + drm_connector_list_iter_begin(drm_dev, &iter); + drm_for_each_connector_iter(list_connector, &iter) { + if (list_connector->status == connector_status_connected) { + ret = -EBUSY; + break; + } + } + drm_connector_list_iter_end(&iter); + mutex_unlock(&drm_dev->mode_config.mutex); + + if (ret) + return ret; + + if (amdgpu_device_has_dc_support(adev)) { + struct drm_crtc *crtc; + + drm_for_each_crtc(crtc, drm_dev) { + drm_modeset_lock(&crtc->mutex, NULL); + if (crtc->state->active) + ret = -EBUSY; + drm_modeset_unlock(&crtc->mutex); + if (ret < 0) + break; + } + } else { + mutex_lock(&drm_dev->mode_config.mutex); + drm_modeset_lock(&drm_dev->mode_config.connection_mutex, NULL); + + drm_connector_list_iter_begin(drm_dev, &iter); + drm_for_each_connector_iter(list_connector, &iter) { + if (list_connector->dpms == DRM_MODE_DPMS_ON) { + ret = -EBUSY; + break; + } + } + + drm_connector_list_iter_end(&iter); + + drm_modeset_unlock(&drm_dev->mode_config.connection_mutex); + mutex_unlock(&drm_dev->mode_config.mutex); + } + if (ret) + return ret; + } + + return 0; +} + static int amdgpu_pmops_runtime_suspend(struct device *dev) { struct pci_dev *pdev = to_pci_dev(dev); @@ -2402,6 +2472,10 @@ static int amdgpu_pmops_runtime_suspend(struct device *dev) return -EBUSY; } + ret = amdgpu_runtime_idle_check_display(dev); + if (ret) + return ret; + /* wait for all rings to drain before suspending */ for (i = 0; i < AMDGPU_MAX_RINGS; i++) { struct amdgpu_ring *ring = adev->rings[i]; @@ -2511,41 +2585,7 @@ static int amdgpu_pmops_runtime_idle(struct device *dev) return -EBUSY; } - if (amdgpu_device_has_dc_support(adev)) { - struct drm_crtc *crtc; - - drm_for_each_crtc(crtc, drm_dev) { - drm_modeset_lock(&crtc->mutex, NULL); - if (crtc->state->active) - ret = -EBUSY; - drm_modeset_unlock(&crtc->mutex); - if (ret < 0) - break; - } - - } else { - struct drm_connector *list_connector; - struct drm_connector_list_iter iter; - - mutex_lock(&drm_dev->mode_config.mutex); - drm_modeset_lock(&drm_dev->mode_config.connection_mutex, NULL); - - drm_connector_list_iter_begin(drm_dev, &iter); - drm_for_each_connector_iter(list_connector, &iter) { - if (list_connector->dpms == DRM_MODE_DPMS_ON) { - ret = -EBUSY; - break; - } - } - - drm_connector_list_iter_end(&iter); - - drm_modeset_unlock(&drm_dev->mode_config.connection_mutex); - mutex_unlock(&drm_dev->mode_config.mutex); - } - - if (ret == -EBUSY) - DRM_DEBUG_DRIVER("failing to power off - crtc active\n"); + ret = amdgpu_runtime_idle_check_display(dev); pm_runtime_mark_last_busy(dev); pm_runtime_autosuspend(dev); @@ -2575,6 +2615,7 @@ static const struct dev_pm_ops amdgpu_pm_ops = { .prepare = amdgpu_pmops_prepare, .complete = amdgpu_pmops_complete, .suspend = amdgpu_pmops_suspend, + .suspend_noirq = amdgpu_pmops_suspend_noirq, .resume = amdgpu_pmops_resume, .freeze = amdgpu_pmops_freeze, .thaw = amdgpu_pmops_thaw, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c index 8fe939976224..28a736c507bb 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c @@ -266,7 +266,7 @@ static int amdgpu_gfx_kiq_acquire(struct amdgpu_device *adev, * adev->gfx.mec.num_pipe_per_mec * adev->gfx.mec.num_queue_per_pipe; - while (queue_bit-- >= 0) { + while (--queue_bit >= 0) { if (test_bit(queue_bit, adev->gfx.mec.queue_bitmap)) continue; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c index ca2cfb65f976..a66a0881a934 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c @@ -561,9 +561,15 @@ void amdgpu_gmc_noretry_set(struct amdgpu_device *adev) switch (adev->ip_versions[GC_HWIP][0]) { case IP_VERSION(9, 0, 1): + case IP_VERSION(9, 3, 0): case IP_VERSION(9, 4, 0): case IP_VERSION(9, 4, 1): case IP_VERSION(9, 4, 2): + case IP_VERSION(10, 3, 3): + case IP_VERSION(10, 3, 4): + case IP_VERSION(10, 3, 5): + case IP_VERSION(10, 3, 6): + case IP_VERSION(10, 3, 7): /* * noretry = 0 will cause kfd page fault tests fail * for some ASICs, so set default to 1 for these ASICs. diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index 25731719c627..940752488330 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -1284,6 +1284,7 @@ void amdgpu_bo_get_memory(struct amdgpu_bo *bo, uint64_t *vram_mem, */ void amdgpu_bo_release_notify(struct ttm_buffer_object *bo) { + struct amdgpu_device *adev = amdgpu_ttm_adev(bo->bdev); struct dma_fence *fence = NULL; struct amdgpu_bo *abo; int r; @@ -1303,7 +1304,8 @@ void amdgpu_bo_release_notify(struct ttm_buffer_object *bo) amdgpu_amdkfd_remove_fence_on_pt_pd_bos(abo); if (bo->resource->mem_type != TTM_PL_VRAM || - !(abo->flags & AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE)) + !(abo->flags & AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE) || + adev->in_suspend || adev->shutdown) return; if (WARN_ON_ONCE(!dma_resv_trylock(bo->base.resv))) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h index 5320bb0883d8..317d80209e95 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h @@ -300,8 +300,8 @@ void amdgpu_ring_generic_pad_ib(struct amdgpu_ring *ring, struct amdgpu_ib *ib); void amdgpu_ring_commit(struct amdgpu_ring *ring); void amdgpu_ring_undo(struct amdgpu_ring *ring); int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring, - unsigned int ring_size, struct amdgpu_irq_src *irq_src, - unsigned int irq_type, unsigned int prio, + unsigned int max_dw, struct amdgpu_irq_src *irq_src, + unsigned int irq_type, unsigned int hw_prio, atomic_t *sched_score); void amdgpu_ring_fini(struct amdgpu_ring *ring); void amdgpu_ring_emit_reg_write_reg_wait_helper(struct amdgpu_ring *ring, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c index f99093f2ebc7..a0ee828a4a97 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c @@ -52,7 +52,7 @@ #define FIRMWARE_ALDEBARAN "amdgpu/aldebaran_vcn.bin" #define FIRMWARE_BEIGE_GOBY "amdgpu/beige_goby_vcn.bin" #define FIRMWARE_YELLOW_CARP "amdgpu/yellow_carp_vcn.bin" -#define FIRMWARE_VCN_3_1_2 "amdgpu/vcn_3_1_2_vcn.bin" +#define FIRMWARE_VCN_3_1_2 "amdgpu/vcn_3_1_2.bin" MODULE_FIRMWARE(FIRMWARE_RAVEN); MODULE_FIRMWARE(FIRMWARE_PICASSO); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h index e2fde88aaf5e..f06fb7f882e2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h @@ -159,6 +159,7 @@ #define AMDGPU_VCN_MULTI_QUEUE_FLAG (1 << 8) #define AMDGPU_VCN_SW_RING_FLAG (1 << 9) #define AMDGPU_VCN_FW_LOGGING_FLAG (1 << 10) +#define AMDGPU_VCN_SMU_VERSION_INFO_FLAG (1 << 11) #define AMDGPU_VCN_IB_FLAG_DECODE_BUFFER 0x00000001 #define AMDGPU_VCN_CMD_FLAG_MSG_BUFFER 0x00000001 @@ -279,6 +280,11 @@ struct amdgpu_fw_shared_fw_logging { uint32_t size; }; +struct amdgpu_fw_shared_smu_interface_info { + uint8_t smu_interface_type; + uint8_t padding[3]; +}; + struct amdgpu_fw_shared { uint32_t present_flag_0; uint8_t pad[44]; @@ -287,6 +293,7 @@ struct amdgpu_fw_shared { struct amdgpu_fw_shared_multi_queue multi_queue; struct amdgpu_fw_shared_sw_ring sw_ring; struct amdgpu_fw_shared_fw_logging fw_log; + struct amdgpu_fw_shared_smu_interface_info smu_interface_info; }; struct amdgpu_vcn_fwlog { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c index a025f080aa6a..5e3756643da3 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c @@ -24,6 +24,7 @@ #include <linux/module.h> #include <drm/drm_drv.h> +#include <xen/xen.h> #include "amdgpu.h" #include "amdgpu_ras.h" @@ -710,7 +711,8 @@ void amdgpu_detect_virtualization(struct amdgpu_device *adev) adev->virt.caps |= AMDGPU_SRIOV_CAPS_ENABLE_IOV; if (!reg) { - if (is_virtual_machine()) /* passthrough mode exclus sriov mod */ + /* passthrough mode exclus sriov mod */ + if (is_virtual_machine() && !xen_initial_domain()) adev->virt.caps |= AMDGPU_PASSTHROUGH_MODE; } diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index f4c6accd3226..9426e252d8aa 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -3293,7 +3293,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_3_3[] = SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG3, 0xffffffff, 0x00000280), SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG4, 0xffffffff, 0x00800000), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGB_ADDR_CONFIG, 0x0c1807ff, 0x00000242), - SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL, 0x1ff1ffff, 0x00000500), + SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL_Vangogh, 0x1ff1ffff, 0x00000500), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL1_PIPE_STEER, 0x000000ff, 0x000000e4), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2_PIPE_STEER_0, 0x77777777, 0x32103210), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2_PIPE_STEER_1, 0x77777777, 0x32103210), @@ -3429,7 +3429,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_3_6[] = SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG3, 0xffffffff, 0x00000280), SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG4, 0xffffffff, 0x00800000), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGB_ADDR_CONFIG, 0x0c1807ff, 0x00000042), - SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL, 0x1ff1ffff, 0x00000500), + SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL_Vangogh, 0x1ff1ffff, 0x00000500), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL1_PIPE_STEER, 0x000000ff, 0x00000044), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2_PIPE_STEER_0, 0x77777777, 0x32103210), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2_PIPE_STEER_1, 0x77777777, 0x32103210), @@ -3454,7 +3454,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_3_7[] = { SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG3, 0xffffffff, 0x00000280), SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG4, 0xffffffff, 0x00800000), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGB_ADDR_CONFIG, 0x0c1807ff, 0x00000041), - SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL, 0x1ff1ffff, 0x00000500), + SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL_Vangogh, 0x1ff1ffff, 0x00000500), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL1_PIPE_STEER, 0x000000ff, 0x000000e4), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2_PIPE_STEER_0, 0x77777777, 0x32103210), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2_PIPE_STEER_1, 0x77777777, 0x32103210), @@ -7689,6 +7689,7 @@ static uint64_t gfx_v10_0_get_gpu_clock_counter(struct amdgpu_device *adev) switch (adev->ip_versions[GC_HWIP][0]) { case IP_VERSION(10, 3, 1): case IP_VERSION(10, 3, 3): + case IP_VERSION(10, 3, 7): preempt_disable(); clock_hi = RREG32_SOC15_NO_KIQ(SMUIO, 0, mmGOLDEN_TSC_COUNT_UPPER_Vangogh); clock_lo = RREG32_SOC15_NO_KIQ(SMUIO, 0, mmGOLDEN_TSC_COUNT_LOWER_Vangogh); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index 46d4bf27ebbb..b8cfcc6b1125 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -1205,6 +1205,8 @@ static const struct amdgpu_gfxoff_quirk amdgpu_gfxoff_quirk_list[] = { { 0x1002, 0x15dd, 0x103c, 0x83e7, 0xd3 }, /* GFXOFF is unstable on C6 parts with a VBIOS 113-RAVEN-114 */ { 0x1002, 0x15dd, 0x1002, 0x15dd, 0xc6 }, + /* Apple MacBook Pro (15-inch, 2019) Radeon Pro Vega 20 4 GB */ + { 0x1002, 0x69af, 0x106b, 0x019a, 0xc0 }, { 0, 0, 0, 0, 0 }, }; diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c index 3c1d440824a7..7c956cf21bc7 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c @@ -814,7 +814,7 @@ static int gmc_v10_0_mc_init(struct amdgpu_device *adev) adev->gmc.aper_size = pci_resource_len(adev->pdev, 0); #ifdef CONFIG_X86_64 - if (adev->flags & AMD_IS_APU) { + if ((adev->flags & AMD_IS_APU) && !amdgpu_passthrough(adev)) { adev->gmc.aper_base = adev->gfxhub.funcs->get_mc_fb_offset(adev); adev->gmc.aper_size = adev->gmc.real_vram_size; } @@ -1151,6 +1151,16 @@ static int gmc_v10_0_set_clockgating_state(void *handle, int r; struct amdgpu_device *adev = (struct amdgpu_device *)handle; + /* + * The issue mmhub can't disconnect from DF with MMHUB clock gating being disabled + * is a new problem observed at DF 3.0.3, however with the same suspend sequence not + * seen any issue on the DF 3.0.2 series platform. + */ + if (adev->in_s0ix && adev->ip_versions[DF_HWIP][0] > IP_VERSION(3, 0, 2)) { + dev_dbg(adev->dev, "keep mmhub clock gating being enabled for s0ix\n"); + return 0; + } + r = adev->mmhub.funcs->set_clockgating(adev, state); if (r) return r; diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c index 344d819b4c1b..979da6f510e8 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c @@ -381,8 +381,9 @@ static int gmc_v7_0_mc_init(struct amdgpu_device *adev) adev->gmc.aper_size = pci_resource_len(adev->pdev, 0); #ifdef CONFIG_X86_64 - if (adev->flags & AMD_IS_APU && - adev->gmc.real_vram_size > adev->gmc.aper_size) { + if ((adev->flags & AMD_IS_APU) && + adev->gmc.real_vram_size > adev->gmc.aper_size && + !amdgpu_passthrough(adev)) { adev->gmc.aper_base = ((u64)RREG32(mmMC_VM_FB_OFFSET)) << 22; adev->gmc.aper_size = adev->gmc.real_vram_size; } diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c index ca9841d5669f..1932a3e4af7e 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c @@ -581,7 +581,7 @@ static int gmc_v8_0_mc_init(struct amdgpu_device *adev) adev->gmc.aper_size = pci_resource_len(adev->pdev, 0); #ifdef CONFIG_X86_64 - if (adev->flags & AMD_IS_APU) { + if ((adev->flags & AMD_IS_APU) && !amdgpu_passthrough(adev)) { adev->gmc.aper_base = ((u64)RREG32(mmMC_VM_FB_OFFSET)) << 22; adev->gmc.aper_size = adev->gmc.real_vram_size; } diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c index 431742eb7811..6009fbfdcc19 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c @@ -1456,7 +1456,7 @@ static int gmc_v9_0_mc_init(struct amdgpu_device *adev) */ /* check whether both host-gpu and gpu-gpu xgmi links exist */ - if ((adev->flags & AMD_IS_APU) || + if (((adev->flags & AMD_IS_APU) && !amdgpu_passthrough(adev)) || (adev->gmc.xgmi.supported && adev->gmc.xgmi.connected_to_cpu)) { adev->gmc.aper_base = @@ -1721,7 +1721,7 @@ static int gmc_v9_0_sw_fini(void *handle) amdgpu_gem_force_release(adev); amdgpu_vm_manager_fini(adev); amdgpu_gart_table_vram_free(adev); - amdgpu_bo_unref(&adev->gmc.pdb0_bo); + amdgpu_bo_free_kernel(&adev->gmc.pdb0_bo, NULL, &adev->gmc.ptr_pdb0); amdgpu_bo_fini(adev); return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c index dff54190b96c..f0fbcda76f5e 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c @@ -24,6 +24,7 @@ #include <linux/firmware.h> #include "amdgpu.h" +#include "amdgpu_cs.h" #include "amdgpu_vcn.h" #include "amdgpu_pm.h" #include "soc15.h" @@ -1900,6 +1901,75 @@ static const struct amd_ip_funcs vcn_v1_0_ip_funcs = { .set_powergating_state = vcn_v1_0_set_powergating_state, }; +/* + * It is a hardware issue that VCN can't handle a GTT TMZ buffer on + * CHIP_RAVEN series ASIC. Move such a GTT TMZ buffer to VRAM domain + * before command submission as a workaround. + */ +static int vcn_v1_0_validate_bo(struct amdgpu_cs_parser *parser, + struct amdgpu_job *job, + uint64_t addr) +{ + struct ttm_operation_ctx ctx = { false, false }; + struct amdgpu_fpriv *fpriv = parser->filp->driver_priv; + struct amdgpu_vm *vm = &fpriv->vm; + struct amdgpu_bo_va_mapping *mapping; + struct amdgpu_bo *bo; + int r; + + addr &= AMDGPU_GMC_HOLE_MASK; + if (addr & 0x7) { + DRM_ERROR("VCN messages must be 8 byte aligned!\n"); + return -EINVAL; + } + + mapping = amdgpu_vm_bo_lookup_mapping(vm, addr/AMDGPU_GPU_PAGE_SIZE); + if (!mapping || !mapping->bo_va || !mapping->bo_va->base.bo) + return -EINVAL; + + bo = mapping->bo_va->base.bo; + if (!(bo->flags & AMDGPU_GEM_CREATE_ENCRYPTED)) + return 0; + + amdgpu_bo_placement_from_domain(bo, AMDGPU_GEM_DOMAIN_VRAM); + r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx); + if (r) { + DRM_ERROR("Failed to validate the VCN message BO (%d)!\n", r); + return r; + } + + return r; +} + +static int vcn_v1_0_ring_patch_cs_in_place(struct amdgpu_cs_parser *p, + struct amdgpu_job *job, + struct amdgpu_ib *ib) +{ + uint32_t msg_lo = 0, msg_hi = 0; + int i, r; + + if (!(ib->flags & AMDGPU_IB_FLAGS_SECURE)) + return 0; + + for (i = 0; i < ib->length_dw; i += 2) { + uint32_t reg = amdgpu_ib_get_value(ib, i); + uint32_t val = amdgpu_ib_get_value(ib, i + 1); + + if (reg == PACKET0(p->adev->vcn.internal.data0, 0)) { + msg_lo = val; + } else if (reg == PACKET0(p->adev->vcn.internal.data1, 0)) { + msg_hi = val; + } else if (reg == PACKET0(p->adev->vcn.internal.cmd, 0)) { + r = vcn_v1_0_validate_bo(p, job, + ((u64)msg_hi) << 32 | msg_lo); + if (r) + return r; + } + } + + return 0; +} + static const struct amdgpu_ring_funcs vcn_v1_0_dec_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_DEC, .align_mask = 0xf, @@ -1910,6 +1980,7 @@ static const struct amdgpu_ring_funcs vcn_v1_0_dec_ring_vm_funcs = { .get_rptr = vcn_v1_0_dec_ring_get_rptr, .get_wptr = vcn_v1_0_dec_ring_get_wptr, .set_wptr = vcn_v1_0_dec_ring_set_wptr, + .patch_cs_in_place = vcn_v1_0_ring_patch_cs_in_place, .emit_frame_size = 6 + 6 + /* hdp invalidate / flush */ SOC15_FLUSH_GPU_TLB_NUM_WREG * 6 + diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c index c87263ed20ec..cb5f0a12333f 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c @@ -219,6 +219,11 @@ static int vcn_v3_0_sw_init(void *handle) cpu_to_le32(AMDGPU_VCN_MULTI_QUEUE_FLAG) | cpu_to_le32(AMDGPU_VCN_FW_SHARED_FLAG_0_RB); fw_shared->sw_ring.is_enabled = cpu_to_le32(DEC_SW_RING_ENABLED); + fw_shared->present_flag_0 |= AMDGPU_VCN_SMU_VERSION_INFO_FLAG; + if (adev->ip_versions[UVD_HWIP][0] == IP_VERSION(3, 1, 2)) + fw_shared->smu_interface_info.smu_interface_type = 2; + else if (adev->ip_versions[UVD_HWIP][0] == IP_VERSION(3, 1, 1)) + fw_shared->smu_interface_info.smu_interface_type = 1; if (amdgpu_vcnfw_log) amdgpu_vcn_fwlog_init(&adev->vcn.inst[i]); @@ -575,8 +580,8 @@ static void vcn_v3_0_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_idx AMDGPU_GPU_PAGE_ALIGN(sizeof(struct amdgpu_fw_shared)), 0, indirect); /* VCN global tiling registers */ - WREG32_SOC15_DPG_MODE(0, SOC15_DPG_MODE_OFFSET( - UVD, 0, mmUVD_GFX10_ADDR_CONFIG), adev->gfx.config.gb_addr_config, 0, indirect); + WREG32_SOC15_DPG_MODE(inst_idx, SOC15_DPG_MODE_OFFSET( + UVD, inst_idx, mmUVD_GFX10_ADDR_CONFIG), adev->gfx.config.gb_addr_config, 0, indirect); } static void vcn_v3_0_disable_static_power_gating(struct amdgpu_device *adev, int inst) @@ -1480,8 +1485,11 @@ static int vcn_v3_0_start_sriov(struct amdgpu_device *adev) static int vcn_v3_0_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx) { + struct dpg_pause_state state = {.fw_based = VCN_DPG_STATE__UNPAUSE}; uint32_t tmp; + vcn_v3_0_pause_dpg_mode(adev, inst_idx, &state); + /* Wait for power status to be 1 */ SOC15_WAIT_ON_RREG(VCN, inst_idx, mmUVD_POWER_STATUS, 1, UVD_POWER_STATUS__UVD_POWER_STATUS_MASK); diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c index 039b90cdc3bc..45f0188c4273 100644 --- a/drivers/gpu/drm/amd/amdgpu/vi.c +++ b/drivers/gpu/drm/amd/amdgpu/vi.c @@ -81,6 +81,10 @@ #include "mxgpu_vi.h" #include "amdgpu_dm.h" +#if IS_ENABLED(CONFIG_X86) +#include <asm/intel-family.h> +#endif + #define ixPCIE_LC_L1_PM_SUBSTATE 0x100100C6 #define PCIE_LC_L1_PM_SUBSTATE__LC_L1_SUBSTATES_OVERRIDE_EN_MASK 0x00000001L #define PCIE_LC_L1_PM_SUBSTATE__LC_PCI_PM_L1_2_OVERRIDE_MASK 0x00000002L @@ -1134,13 +1138,24 @@ static void vi_enable_aspm(struct amdgpu_device *adev) WREG32_PCIE(ixPCIE_LC_CNTL, data); } +static bool aspm_support_quirk_check(void) +{ +#if IS_ENABLED(CONFIG_X86) + struct cpuinfo_x86 *c = &cpu_data(0); + + return !(c->x86 == 6 && c->x86_model == INTEL_FAM6_ALDERLAKE); +#else + return true; +#endif +} + static void vi_program_aspm(struct amdgpu_device *adev) { u32 data, data1, orig; bool bL1SS = false; bool bClkReqSupport = true; - if (!amdgpu_device_should_use_aspm(adev)) + if (!amdgpu_device_should_use_aspm(adev) || !aspm_support_quirk_check()) return; if (adev->flags & AMD_IS_APU || diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c index 339e12c94cff..62aa6c9d5123 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c @@ -483,15 +483,10 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd, } /* Verify module parameters regarding mapped process number*/ - if ((hws_max_conc_proc < 0) - || (hws_max_conc_proc > kfd->vm_info.vmid_num_kfd)) { - dev_err(kfd_device, - "hws_max_conc_proc %d must be between 0 and %d, use %d instead\n", - hws_max_conc_proc, kfd->vm_info.vmid_num_kfd, - kfd->vm_info.vmid_num_kfd); + if (hws_max_conc_proc >= 0) + kfd->max_proc_per_quantum = min((u32)hws_max_conc_proc, kfd->vm_info.vmid_num_kfd); + else kfd->max_proc_per_quantum = kfd->vm_info.vmid_num_kfd; - } else - kfd->max_proc_per_quantum = hws_max_conc_proc; /* calculate max size of mqds needed for queues */ size = max_num_of_queues_per_device * @@ -536,7 +531,8 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd, goto kfd_doorbell_error; } - kfd->hive_id = kfd->adev->gmc.xgmi.hive_id; + if (amdgpu_use_xgmi_p2p) + kfd->hive_id = kfd->adev->gmc.xgmi.hive_id; kfd->noretry = kfd->adev->gmc.noretry; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c index acf4f7975850..198672264492 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -130,19 +130,33 @@ void program_sh_mem_settings(struct device_queue_manager *dqm, } static void increment_queue_count(struct device_queue_manager *dqm, - enum kfd_queue_type type) + struct qcm_process_device *qpd, + struct queue *q) { dqm->active_queue_count++; - if (type == KFD_QUEUE_TYPE_COMPUTE || type == KFD_QUEUE_TYPE_DIQ) + if (q->properties.type == KFD_QUEUE_TYPE_COMPUTE || + q->properties.type == KFD_QUEUE_TYPE_DIQ) dqm->active_cp_queue_count++; + + if (q->properties.is_gws) { + dqm->gws_queue_count++; + qpd->mapped_gws_queue = true; + } } static void decrement_queue_count(struct device_queue_manager *dqm, - enum kfd_queue_type type) + struct qcm_process_device *qpd, + struct queue *q) { dqm->active_queue_count--; - if (type == KFD_QUEUE_TYPE_COMPUTE || type == KFD_QUEUE_TYPE_DIQ) + if (q->properties.type == KFD_QUEUE_TYPE_COMPUTE || + q->properties.type == KFD_QUEUE_TYPE_DIQ) dqm->active_cp_queue_count--; + + if (q->properties.is_gws) { + dqm->gws_queue_count--; + qpd->mapped_gws_queue = false; + } } /* @@ -412,7 +426,7 @@ add_queue_to_list: list_add(&q->list, &qpd->queues_list); qpd->queue_count++; if (q->properties.is_active) - increment_queue_count(dqm, q->properties.type); + increment_queue_count(dqm, qpd, q); /* * Unconditionally increment this counter, regardless of the queue's @@ -601,13 +615,8 @@ static int destroy_queue_nocpsch_locked(struct device_queue_manager *dqm, deallocate_vmid(dqm, qpd, q); } qpd->queue_count--; - if (q->properties.is_active) { - decrement_queue_count(dqm, q->properties.type); - if (q->properties.is_gws) { - dqm->gws_queue_count--; - qpd->mapped_gws_queue = false; - } - } + if (q->properties.is_active) + decrement_queue_count(dqm, qpd, q); return retval; } @@ -700,12 +709,11 @@ static int update_queue(struct device_queue_manager *dqm, struct queue *q, * dqm->active_queue_count to determine whether a new runlist must be * uploaded. */ - if (q->properties.is_active && !prev_active) - increment_queue_count(dqm, q->properties.type); - else if (!q->properties.is_active && prev_active) - decrement_queue_count(dqm, q->properties.type); - - if (q->gws && !q->properties.is_gws) { + if (q->properties.is_active && !prev_active) { + increment_queue_count(dqm, &pdd->qpd, q); + } else if (!q->properties.is_active && prev_active) { + decrement_queue_count(dqm, &pdd->qpd, q); + } else if (q->gws && !q->properties.is_gws) { if (q->properties.is_active) { dqm->gws_queue_count++; pdd->qpd.mapped_gws_queue = true; @@ -767,11 +775,7 @@ static int evict_process_queues_nocpsch(struct device_queue_manager *dqm, mqd_mgr = dqm->mqd_mgrs[get_mqd_type_from_queue_type( q->properties.type)]; q->properties.is_active = false; - decrement_queue_count(dqm, q->properties.type); - if (q->properties.is_gws) { - dqm->gws_queue_count--; - qpd->mapped_gws_queue = false; - } + decrement_queue_count(dqm, qpd, q); if (WARN_ONCE(!dqm->sched_running, "Evict when stopped\n")) continue; @@ -817,7 +821,7 @@ static int evict_process_queues_cpsch(struct device_queue_manager *dqm, continue; q->properties.is_active = false; - decrement_queue_count(dqm, q->properties.type); + decrement_queue_count(dqm, qpd, q); } pdd->last_evict_timestamp = get_jiffies_64(); retval = execute_queues_cpsch(dqm, @@ -888,11 +892,7 @@ static int restore_process_queues_nocpsch(struct device_queue_manager *dqm, mqd_mgr = dqm->mqd_mgrs[get_mqd_type_from_queue_type( q->properties.type)]; q->properties.is_active = true; - increment_queue_count(dqm, q->properties.type); - if (q->properties.is_gws) { - dqm->gws_queue_count++; - qpd->mapped_gws_queue = true; - } + increment_queue_count(dqm, qpd, q); if (WARN_ONCE(!dqm->sched_running, "Restore when stopped\n")) continue; @@ -950,7 +950,7 @@ static int restore_process_queues_cpsch(struct device_queue_manager *dqm, continue; q->properties.is_active = true; - increment_queue_count(dqm, q->properties.type); + increment_queue_count(dqm, &pdd->qpd, q); } retval = execute_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0); @@ -1378,7 +1378,7 @@ static int create_kernel_queue_cpsch(struct device_queue_manager *dqm, dqm->total_queue_count); list_add(&kq->list, &qpd->priv_queue_list); - increment_queue_count(dqm, kq->queue->properties.type); + increment_queue_count(dqm, qpd, kq->queue); qpd->is_debug = true; execute_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0); dqm_unlock(dqm); @@ -1392,7 +1392,7 @@ static void destroy_kernel_queue_cpsch(struct device_queue_manager *dqm, { dqm_lock(dqm); list_del(&kq->list); - decrement_queue_count(dqm, kq->queue->properties.type); + decrement_queue_count(dqm, qpd, kq->queue); qpd->is_debug = false; execute_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES, 0); /* @@ -1467,7 +1467,7 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q, qpd->queue_count++; if (q->properties.is_active) { - increment_queue_count(dqm, q->properties.type); + increment_queue_count(dqm, qpd, q); execute_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0); @@ -1683,15 +1683,11 @@ static int destroy_queue_cpsch(struct device_queue_manager *dqm, list_del(&q->list); qpd->queue_count--; if (q->properties.is_active) { - decrement_queue_count(dqm, q->properties.type); + decrement_queue_count(dqm, qpd, q); retval = execute_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0); if (retval == -ETIME) qpd->reset_wavefronts = true; - if (q->properties.is_gws) { - dqm->gws_queue_count--; - qpd->mapped_gws_queue = false; - } } /* @@ -1932,7 +1928,7 @@ static int process_termination_cpsch(struct device_queue_manager *dqm, /* Clean all kernel queues */ list_for_each_entry_safe(kq, kq_next, &qpd->priv_queue_list, list) { list_del(&kq->list); - decrement_queue_count(dqm, kq->queue->properties.type); + decrement_queue_count(dqm, qpd, kq->queue); qpd->is_debug = false; dqm->total_queue_count--; filter = KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES; @@ -1945,13 +1941,8 @@ static int process_termination_cpsch(struct device_queue_manager *dqm, else if (q->properties.type == KFD_QUEUE_TYPE_SDMA_XGMI) deallocate_sdma_queue(dqm, q); - if (q->properties.is_active) { - decrement_queue_count(dqm, q->properties.type); - if (q->properties.is_gws) { - dqm->gws_queue_count--; - qpd->mapped_gws_queue = false; - } - } + if (q->properties.is_active) + decrement_queue_count(dqm, qpd, q); dqm->total_queue_count--; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_events.c index deecccebe5b6..64f4a51cc880 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_events.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.c @@ -749,6 +749,8 @@ static struct kfd_event_waiter *alloc_event_waiters(uint32_t num_events) event_waiters = kmalloc_array(num_events, sizeof(struct kfd_event_waiter), GFP_KERNEL); + if (!event_waiters) + return NULL; for (i = 0; (event_waiters) && (i < num_events) ; i++) { init_wait(&event_waiters[i].wait); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h index 9967a73d5b0f..8f58fc491b28 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h @@ -1103,7 +1103,7 @@ struct kfd_criu_queue_priv_data { uint32_t priority; uint32_t q_percent; uint32_t doorbell_id; - uint32_t is_gws; + uint32_t gws; uint32_t sdma_id; uint32_t eop_ring_buffer_size; uint32_t ctx_save_restore_area_size; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c index 6eca9509f2e3..4f58e671d39b 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c @@ -636,6 +636,8 @@ static int criu_checkpoint_queue(struct kfd_process_device *pdd, q_data->ctx_save_restore_area_size = q->properties.ctx_save_restore_area_size; + q_data->gws = !!q->gws; + ret = pqm_checkpoint_mqd(&pdd->process->pqm, q->properties.queue_id, mqd, ctl_stack); if (ret) { pr_err("Failed checkpoint queue_mqd (%d)\n", ret); @@ -743,7 +745,6 @@ static void set_queue_properties_from_criu(struct queue_properties *qp, struct kfd_criu_queue_priv_data *q_data) { qp->is_interop = false; - qp->is_gws = q_data->is_gws; qp->queue_percent = q_data->q_percent; qp->priority = q_data->priority; qp->queue_address = q_data->q_address; @@ -826,12 +827,15 @@ int kfd_criu_restore_queue(struct kfd_process *p, NULL); if (ret) { pr_err("Failed to create new queue err:%d\n", ret); - ret = -EINVAL; + goto exit; } + if (q_data->gws) + ret = pqm_set_gws(&p->pqm, q_data->q_id, pdd->dev->gws); + exit: if (ret) - pr_err("Failed to create queue (%d)\n", ret); + pr_err("Failed to restore queue (%d)\n", ret); else pr_debug("Queue id %d was restored successfully\n", queue_id); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c index e4beebb1c80a..f2e1d506ba21 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c @@ -247,15 +247,6 @@ int kfd_smi_event_open(struct kfd_dev *dev, uint32_t *fd) return ret; } - ret = anon_inode_getfd(kfd_smi_name, &kfd_smi_ev_fops, (void *)client, - O_RDWR); - if (ret < 0) { - kfifo_free(&client->fifo); - kfree(client); - return ret; - } - *fd = ret; - init_waitqueue_head(&client->wait_queue); spin_lock_init(&client->lock); client->events = 0; @@ -265,5 +256,20 @@ int kfd_smi_event_open(struct kfd_dev *dev, uint32_t *fd) list_add_rcu(&client->list, &dev->smi_clients); spin_unlock(&dev->smi_lock); + ret = anon_inode_getfd(kfd_smi_name, &kfd_smi_ev_fops, (void *)client, + O_RDWR); + if (ret < 0) { + spin_lock(&dev->smi_lock); + list_del_rcu(&client->list); + spin_unlock(&dev->smi_lock); + + synchronize_rcu(); + + kfifo_free(&client->fifo); + kfree(client); + return ret; + } + *fd = ret; + return 0; } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index b30656959fd8..62139ff35476 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -2714,7 +2714,8 @@ static int dm_resume(void *handle) * this is the case when traversing through already created * MST connectors, should be skipped */ - if (aconnector->mst_port) + if (aconnector->dc_link && + aconnector->dc_link->type == dc_connection_mst_branch) continue; mutex_lock(&aconnector->hpd_lock); @@ -3972,7 +3973,7 @@ static u32 convert_brightness_to_user(const struct amdgpu_dm_backlight_caps *cap max - min); } -static int amdgpu_dm_backlight_set_level(struct amdgpu_display_manager *dm, +static void amdgpu_dm_backlight_set_level(struct amdgpu_display_manager *dm, int bl_idx, u32 user_brightness) { @@ -4003,7 +4004,8 @@ static int amdgpu_dm_backlight_set_level(struct amdgpu_display_manager *dm, DRM_DEBUG("DM: Failed to update backlight on eDP[%d]\n", bl_idx); } - return rc ? 0 : 1; + if (rc) + dm->actual_brightness[bl_idx] = user_brightness; } static int amdgpu_dm_backlight_update_status(struct backlight_device *bd) @@ -9947,7 +9949,7 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state) /* restore the backlight level */ for (i = 0; i < dm->num_of_edps; i++) { if (dm->backlight_dev[i] && - (amdgpu_dm_backlight_get_level(dm, i) != dm->brightness[i])) + (dm->actual_brightness[i] != dm->brightness[i])) amdgpu_dm_backlight_set_level(dm, i, dm->brightness[i]); } #endif diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h index 6a908d736d6a..7e44b0429448 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h @@ -540,6 +540,12 @@ struct amdgpu_display_manager { * cached backlight values. */ u32 brightness[AMDGPU_DM_MAX_NUM_EDP]; + /** + * @actual_brightness: + * + * last successfully applied backlight values. + */ + u32 actual_brightness[AMDGPU_DM_MAX_NUM_EDP]; }; enum dsc_clock_force_state { diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce100/dce_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce100/dce_clk_mgr.c index dfba6138f538..26feefbb8990 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce100/dce_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce100/dce_clk_mgr.c @@ -374,7 +374,7 @@ void dce_clock_read_ss_info(struct clk_mgr_internal *clk_mgr_dce) clk_mgr_dce->dprefclk_ss_percentage = info.spread_spectrum_percentage; } - if (clk_mgr_dce->base.ctx->dc->debug.ignore_dpref_ss) + if (clk_mgr_dce->base.ctx->dc->config.ignore_dpref_ss) clk_mgr_dce->dprefclk_ss_percentage = 0; } } diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c index edda572dc570..8be4c1970628 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c @@ -436,57 +436,84 @@ static void dcn315_clk_mgr_helper_populate_bw_params( struct integrated_info *bios_info, const DpmClocks_315_t *clock_table) { - int i, j; + int i; struct clk_bw_params *bw_params = clk_mgr->base.bw_params; - uint32_t max_dispclk = 0, max_dppclk = 0; - - j = -1; - - ASSERT(NUM_DF_PSTATE_LEVELS <= MAX_NUM_DPM_LVL); - - /* Find lowest DPM, FCLK is filled in reverse order*/ - - for (i = NUM_DF_PSTATE_LEVELS - 1; i >= 0; i--) { - if (clock_table->DfPstateTable[i].FClk != 0) { - j = i; - break; + uint32_t max_dispclk, max_dppclk, max_pstate, max_socclk, max_fclk = 0, min_pstate = 0; + struct clk_limit_table_entry def_max = bw_params->clk_table.entries[bw_params->clk_table.num_entries - 1]; + + max_dispclk = find_max_clk_value(clock_table->DispClocks, clock_table->NumDispClkLevelsEnabled); + max_dppclk = find_max_clk_value(clock_table->DppClocks, clock_table->NumDispClkLevelsEnabled); + max_socclk = find_max_clk_value(clock_table->SocClocks, clock_table->NumSocClkLevelsEnabled); + + /* Find highest fclk pstate */ + for (i = 0; i < clock_table->NumDfPstatesEnabled; i++) { + if (clock_table->DfPstateTable[i].FClk > max_fclk) { + max_fclk = clock_table->DfPstateTable[i].FClk; + max_pstate = i; } } - if (j == -1) { - /* clock table is all 0s, just use our own hardcode */ - ASSERT(0); - return; - } - - bw_params->clk_table.num_entries = j + 1; - - /* dispclk and dppclk can be max at any voltage, same number of levels for both */ - if (clock_table->NumDispClkLevelsEnabled <= NUM_DISPCLK_DPM_LEVELS && - clock_table->NumDispClkLevelsEnabled <= NUM_DPPCLK_DPM_LEVELS) { - max_dispclk = find_max_clk_value(clock_table->DispClocks, clock_table->NumDispClkLevelsEnabled); - max_dppclk = find_max_clk_value(clock_table->DppClocks, clock_table->NumDispClkLevelsEnabled); - } else { - ASSERT(0); - } + /* For 315 we want to base clock table on dcfclk, need at least one entry regardless of pmfw table */ + for (i = 0; i < clock_table->NumDcfClkLevelsEnabled; i++) { + int j; + uint32_t min_fclk = clock_table->DfPstateTable[0].FClk; - for (i = 0; i < bw_params->clk_table.num_entries; i++, j--) { - int temp; + for (j = 1; j < clock_table->NumDfPstatesEnabled; j++) { + if (clock_table->DfPstateTable[j].Voltage <= clock_table->SocVoltage[i] + && clock_table->DfPstateTable[j].FClk < min_fclk) { + min_fclk = clock_table->DfPstateTable[j].FClk; + min_pstate = j; + } + } - bw_params->clk_table.entries[i].fclk_mhz = clock_table->DfPstateTable[j].FClk; - bw_params->clk_table.entries[i].memclk_mhz = clock_table->DfPstateTable[j].MemClk; - bw_params->clk_table.entries[i].voltage = clock_table->DfPstateTable[j].Voltage; + bw_params->clk_table.entries[i].fclk_mhz = min_fclk; + bw_params->clk_table.entries[i].memclk_mhz = clock_table->DfPstateTable[min_pstate].MemClk; + bw_params->clk_table.entries[i].voltage = clock_table->DfPstateTable[min_pstate].Voltage; + bw_params->clk_table.entries[i].dcfclk_mhz = clock_table->DcfClocks[i]; + bw_params->clk_table.entries[i].socclk_mhz = clock_table->SocClocks[i]; + bw_params->clk_table.entries[i].dispclk_mhz = max_dispclk; + bw_params->clk_table.entries[i].dppclk_mhz = max_dppclk; bw_params->clk_table.entries[i].wck_ratio = 1; - temp = find_clk_for_voltage(clock_table, clock_table->DcfClocks, clock_table->DfPstateTable[j].Voltage); - if (temp) - bw_params->clk_table.entries[i].dcfclk_mhz = temp; - temp = find_clk_for_voltage(clock_table, clock_table->SocClocks, clock_table->DfPstateTable[j].Voltage); - if (temp) - bw_params->clk_table.entries[i].socclk_mhz = temp; + }; + + /* Make sure to include at least one entry and highest pstate */ + if (max_pstate != min_pstate) { + bw_params->clk_table.entries[i].fclk_mhz = max_fclk; + bw_params->clk_table.entries[i].memclk_mhz = clock_table->DfPstateTable[max_pstate].MemClk; + bw_params->clk_table.entries[i].voltage = clock_table->DfPstateTable[max_pstate].Voltage; + bw_params->clk_table.entries[i].dcfclk_mhz = find_clk_for_voltage( + clock_table, clock_table->DcfClocks, clock_table->DfPstateTable[max_pstate].Voltage); + bw_params->clk_table.entries[i].socclk_mhz = find_clk_for_voltage( + clock_table, clock_table->SocClocks, clock_table->DfPstateTable[max_pstate].Voltage); bw_params->clk_table.entries[i].dispclk_mhz = max_dispclk; bw_params->clk_table.entries[i].dppclk_mhz = max_dppclk; + bw_params->clk_table.entries[i].wck_ratio = 1; + i++; } + bw_params->clk_table.num_entries = i; + + /* Include highest socclk */ + if (bw_params->clk_table.entries[i-1].socclk_mhz < max_socclk) + bw_params->clk_table.entries[i-1].socclk_mhz = max_socclk; + /* Set any 0 clocks to max default setting. Not an issue for + * power since we aren't doing switching in such case anyway + */ + for (i = 0; i < bw_params->clk_table.num_entries; i++) { + if (!bw_params->clk_table.entries[i].fclk_mhz) { + bw_params->clk_table.entries[i].fclk_mhz = def_max.fclk_mhz; + bw_params->clk_table.entries[i].memclk_mhz = def_max.memclk_mhz; + bw_params->clk_table.entries[i].voltage = def_max.voltage; + } + if (!bw_params->clk_table.entries[i].dcfclk_mhz) + bw_params->clk_table.entries[i].dcfclk_mhz = def_max.dcfclk_mhz; + if (!bw_params->clk_table.entries[i].socclk_mhz) + bw_params->clk_table.entries[i].socclk_mhz = def_max.socclk_mhz; + if (!bw_params->clk_table.entries[i].dispclk_mhz) + bw_params->clk_table.entries[i].dispclk_mhz = def_max.dispclk_mhz; + if (!bw_params->clk_table.entries[i].dppclk_mhz) + bw_params->clk_table.entries[i].dppclk_mhz = def_max.dppclk_mhz; + } bw_params->vram_type = bios_info->memory_type; bw_params->num_channels = bios_info->ma_channel_number; diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.c index 880ffea2afc6..2600313fea57 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.c @@ -80,8 +80,8 @@ static const struct IP_BASE NBIO_BASE = { { { { 0x00000000, 0x00000014, 0x00000D #define VBIOSSMC_MSG_SetDppclkFreq 0x06 ///< Set DPP clock frequency in MHZ #define VBIOSSMC_MSG_SetHardMinDcfclkByFreq 0x07 ///< Set DCF clock frequency hard min in MHZ #define VBIOSSMC_MSG_SetMinDeepSleepDcfclk 0x08 ///< Set DCF clock minimum frequency in deep sleep in MHZ -#define VBIOSSMC_MSG_SetPhyclkVoltageByFreq 0x09 ///< Set display phy clock frequency in MHZ in case VMIN does not support phy frequency -#define VBIOSSMC_MSG_GetFclkFrequency 0x0A ///< Get FCLK frequency, return frequemcy in MHZ +#define VBIOSSMC_MSG_GetDtbclkFreq 0x09 ///< Get display dtb clock frequency in MHZ in case VMIN does not support phy frequency +#define VBIOSSMC_MSG_SetDtbClk 0x0A ///< Set dtb clock frequency, return frequemcy in MHZ #define VBIOSSMC_MSG_SetDisplayCount 0x0B ///< Inform PMFW of number of display connected #define VBIOSSMC_MSG_EnableTmdp48MHzRefclkPwrDown 0x0C ///< To ask PMFW turn off TMDP 48MHz refclk during display off to save power #define VBIOSSMC_MSG_UpdatePmeRestore 0x0D ///< To ask PMFW to write into Azalia for PME wake up event @@ -324,15 +324,26 @@ int dcn315_smu_get_dpref_clk(struct clk_mgr_internal *clk_mgr) return (dprefclk_get_mhz * 1000); } -int dcn315_smu_get_smu_fclk(struct clk_mgr_internal *clk_mgr) +int dcn315_smu_get_dtbclk(struct clk_mgr_internal *clk_mgr) { int fclk_get_mhz = -1; if (clk_mgr->smu_present) { fclk_get_mhz = dcn315_smu_send_msg_with_param( clk_mgr, - VBIOSSMC_MSG_GetFclkFrequency, + VBIOSSMC_MSG_GetDtbclkFreq, 0); } return (fclk_get_mhz * 1000); } + +void dcn315_smu_set_dtbclk(struct clk_mgr_internal *clk_mgr, bool enable) +{ + if (!clk_mgr->smu_present) + return; + + dcn315_smu_send_msg_with_param( + clk_mgr, + VBIOSSMC_MSG_SetDtbClk, + enable); +} diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.h b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.h index 66fa42f8dd18..5aa3275ac7d8 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.h +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.h @@ -37,6 +37,7 @@ #define NUM_SOC_VOLTAGE_LEVELS 4 #define NUM_DF_PSTATE_LEVELS 4 + typedef struct { uint16_t MinClock; // This is either DCFCLK or SOCCLK (in MHz) uint16_t MaxClock; // This is either DCFCLK or SOCCLK (in MHz) @@ -124,5 +125,6 @@ void dcn315_smu_transfer_wm_table_dram_2_smu(struct clk_mgr_internal *clk_mgr); void dcn315_smu_request_voltage_via_phyclk(struct clk_mgr_internal *clk_mgr, int requested_phyclk_khz); void dcn315_smu_enable_pme_wa(struct clk_mgr_internal *clk_mgr); int dcn315_smu_get_dpref_clk(struct clk_mgr_internal *clk_mgr); -int dcn315_smu_get_smu_fclk(struct clk_mgr_internal *clk_mgr); +int dcn315_smu_get_dtbclk(struct clk_mgr_internal *clk_mgr); +void dcn315_smu_set_dtbclk(struct clk_mgr_internal *clk_mgr, bool enable); #endif /* DAL_DC_315_SMU_H_ */ diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c index 702d00ce7da4..3121dd2d2a91 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c @@ -686,8 +686,8 @@ void dcn316_clk_mgr_construct( clk_mgr->base.base.dprefclk_khz = dcn316_smu_get_dpref_clk(&clk_mgr->base); clk_mgr->base.dccg->ref_dtbclk_khz = clk_mgr->base.base.dprefclk_khz; dce_clock_read_ss_info(&clk_mgr->base); - clk_mgr->base.dccg->ref_dtbclk_khz = - dce_adjust_dp_ref_freq_for_ss(&clk_mgr->base, clk_mgr->base.base.dprefclk_khz); + /*clk_mgr->base.dccg->ref_dtbclk_khz = + dce_adjust_dp_ref_freq_for_ss(&clk_mgr->base, clk_mgr->base.base.dprefclk_khz);*/ clk_mgr->base.base.bw_params = &dcn316_bw_params; diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index f6e19efea756..c436db416708 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -2389,6 +2389,8 @@ static enum surface_update_type check_update_surfaces_for_stream( if (stream_update->mst_bw_update) su_flags->bits.mst_bw = 1; + if (stream_update->crtc_timing_adjust && dc_extended_blank_supported(dc)) + su_flags->bits.crtc_timing_adjust = 1; if (su_flags->raw != 0) overall_type = UPDATE_TYPE_FULL; @@ -2650,6 +2652,9 @@ static void copy_stream_update_to_stream(struct dc *dc, if (update->vrr_infopacket) stream->vrr_infopacket = *update->vrr_infopacket; + if (update->crtc_timing_adjust) + stream->adjust = *update->crtc_timing_adjust; + if (update->dpms_off) stream->dpms_off = *update->dpms_off; @@ -4051,3 +4056,17 @@ void dc_notify_vsync_int_state(struct dc *dc, struct dc_stream_state *stream, bo if (pipe->stream_res.abm && pipe->stream_res.abm->funcs->set_abm_pause) pipe->stream_res.abm->funcs->set_abm_pause(pipe->stream_res.abm, !enable, i, pipe->stream_res.tg->inst); } +/* + * dc_extended_blank_supported: Decide whether extended blank is supported + * + * Extended blank is a freesync optimization feature to be enabled in the future. + * During the extra vblank period gained from freesync, we have the ability to enter z9/z10. + * + * @param [in] dc: Current DC state + * @return: Indicate whether extended blank is supported (true or false) + */ +bool dc_extended_blank_supported(struct dc *dc) +{ + return dc->debug.extended_blank_optimization && !dc->debug.disable_z10 + && dc->caps.zstate_support && dc->caps.is_apu; +} diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c index cb87dd643180..bbaa5abdf888 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -983,8 +983,7 @@ static bool should_verify_link_capability_destructively(struct dc_link *link, destrictive = false; } } - } else if (dc_is_hdmi_signal(link->local_sink->sink_signal)) - destrictive = true; + } return destrictive; } diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c index 351081f574cb..95b5b5bfa1ff 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c @@ -4440,7 +4440,7 @@ static void dp_test_get_audio_test_data(struct dc_link *link, bool disable_video &dpcd_pattern_type.value, sizeof(dpcd_pattern_type)); - channel_count = dpcd_test_mode.bits.channel_count + 1; + channel_count = min(dpcd_test_mode.bits.channel_count + 1, AUDIO_CHANNELS_COUNT); // read pattern periods for requested channels when sawTooth pattern is requested if (dpcd_pattern_type.value == AUDIO_TEST_PATTERN_SAWTOOTH || @@ -5216,6 +5216,62 @@ static void retrieve_cable_id(struct dc_link *link) &link->dpcd_caps.cable_id, &usbc_cable_id); } +/* DPRX may take some time to respond to AUX messages after HPD asserted. + * If AUX read unsuccessful, try to wake unresponsive DPRX by toggling DPCD SET_POWER (0x600). + */ +static enum dc_status wa_try_to_wake_dprx(struct dc_link *link, uint64_t timeout_ms) +{ + enum dc_status status = DC_ERROR_UNEXPECTED; + uint8_t dpcd_data = 0; + uint64_t start_ts = 0; + uint64_t current_ts = 0; + uint64_t time_taken_ms = 0; + enum dc_connection_type type = dc_connection_none; + + status = core_link_read_dpcd( + link, + DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV, + &dpcd_data, + sizeof(dpcd_data)); + + if (status != DC_OK) { + DC_LOG_WARNING("%s: Read DPCD LTTPR_CAP failed - try to toggle DPCD SET_POWER for %lld ms.", + __func__, + timeout_ms); + start_ts = dm_get_timestamp(link->ctx); + + do { + if (!dc_link_detect_sink(link, &type) || type == dc_connection_none) + break; + + dpcd_data = DP_SET_POWER_D3; + status = core_link_write_dpcd( + link, + DP_SET_POWER, + &dpcd_data, + sizeof(dpcd_data)); + + dpcd_data = DP_SET_POWER_D0; + status = core_link_write_dpcd( + link, + DP_SET_POWER, + &dpcd_data, + sizeof(dpcd_data)); + + current_ts = dm_get_timestamp(link->ctx); + time_taken_ms = div_u64(dm_get_elapse_time_in_ns(link->ctx, current_ts, start_ts), 1000000); + } while (status != DC_OK && time_taken_ms < timeout_ms); + + DC_LOG_WARNING("%s: DPCD SET_POWER %s after %lld ms%s", + __func__, + (status == DC_OK) ? "succeeded" : "failed", + time_taken_ms, + (type == dc_connection_none) ? ". Unplugged." : "."); + } + + return status; +} + static bool retrieve_link_cap(struct dc_link *link) { /* DP_ADAPTER_CAP - DP_DPCD_REV + 1 == 16 and also DP_DSC_BITS_PER_PIXEL_INC - DP_DSC_SUPPORT + 1 == 16, @@ -5251,6 +5307,15 @@ static bool retrieve_link_cap(struct dc_link *link) dc_link_aux_try_to_configure_timeout(link->ddc, LINK_AUX_DEFAULT_LTTPR_TIMEOUT_PERIOD); + /* Try to ensure AUX channel active before proceeding. */ + if (link->dc->debug.aux_wake_wa.bits.enable_wa) { + uint64_t timeout_ms = link->dc->debug.aux_wake_wa.bits.timeout_ms; + + if (link->dc->debug.aux_wake_wa.bits.use_default_timeout) + timeout_ms = LINK_AUX_WAKE_TIMEOUT_MS; + status = wa_try_to_wake_dprx(link, timeout_ms); + } + is_lttpr_present = dp_retrieve_lttpr_cap(link); /* Read DP tunneling information. */ status = dpcd_get_tunneling_device_data(link); diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c index 7af153434e9e..d251c3f3a714 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c @@ -1685,8 +1685,8 @@ bool dc_is_stream_unchanged( if (old_stream->ignore_msa_timing_param != stream->ignore_msa_timing_param) return false; - // Only Have Audio left to check whether it is same or not. This is a corner case for Tiled sinks - if (old_stream->audio_info.mode_count != stream->audio_info.mode_count) + /*compare audio info*/ + if (memcmp(&old_stream->audio_info, &stream->audio_info, sizeof(stream->audio_info)) != 0) return false; return true; diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index 4ffab7bb1098..9e79f60e6129 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -188,6 +188,7 @@ struct dc_caps { bool psp_setup_panel_mode; bool extended_aux_timeout_support; bool dmcub_support; + bool zstate_support; uint32_t num_of_internal_disp; enum dp_protocol_version max_dp_protocol_version; unsigned int mall_size_per_mem_channel; @@ -339,6 +340,7 @@ struct dc_config { bool is_asymmetric_memory; bool is_single_rank_dimm; bool use_pipe_ctx_sync_logic; + bool ignore_dpref_ss; }; enum visual_confirm { @@ -525,6 +527,22 @@ union dpia_debug_options { uint32_t raw; }; +/* AUX wake work around options + * 0: enable/disable work around + * 1: use default timeout LINK_AUX_WAKE_TIMEOUT_MS + * 15-2: reserved + * 31-16: timeout in ms + */ +union aux_wake_wa_options { + struct { + uint32_t enable_wa : 1; + uint32_t use_default_timeout : 1; + uint32_t rsvd: 14; + uint32_t timeout_ms : 16; + } bits; + uint32_t raw; +}; + struct dc_debug_data { uint32_t ltFailCount; uint32_t i2cErrorCount; @@ -703,14 +721,15 @@ struct dc_debug_options { bool enable_driver_sequence_debug; enum det_size crb_alloc_policy; int crb_alloc_policy_min_disp_count; -#if defined(CONFIG_DRM_AMD_DC_DCN) bool disable_z10; +#if defined(CONFIG_DRM_AMD_DC_DCN) bool enable_z9_disable_interface; bool enable_sw_cntl_psr; union dpia_debug_options dpia_debug; #endif bool apply_vendor_specific_lttpr_wa; - bool ignore_dpref_ss; + bool extended_blank_optimization; + union aux_wake_wa_options aux_wake_wa; uint8_t psr_power_use_phy_fsm; }; @@ -1369,6 +1388,8 @@ struct dc_sink_init_data { bool converter_disable_audio; }; +bool dc_extended_blank_supported(struct dc *dc); + struct dc_sink *dc_sink_create(const struct dc_sink_init_data *init_params); /* Newer interfaces */ diff --git a/drivers/gpu/drm/amd/display/dc/dc_stream.h b/drivers/gpu/drm/amd/display/dc/dc_stream.h index 99a750f561f8..c4168c11257c 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_stream.h +++ b/drivers/gpu/drm/amd/display/dc/dc_stream.h @@ -131,6 +131,7 @@ union stream_update_flags { uint32_t wb_update:1; uint32_t dsc_changed : 1; uint32_t mst_bw : 1; + uint32_t crtc_timing_adjust : 1; } bits; uint32_t raw; @@ -289,6 +290,7 @@ struct dc_stream_update { struct dc_3dlut *lut3d_func; struct test_pattern *pending_test_pattern; + struct dc_crtc_timing_adjust *crtc_timing_adjust; }; bool dc_is_stream_unchanged( diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c index c3e141c19a77..83fbea2df410 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c @@ -1497,16 +1497,12 @@ void dcn10_init_hw(struct dc *dc) link->link_status.link_active = true; } - /* Power gate DSCs */ - if (!is_optimized_init_done) { - for (i = 0; i < res_pool->res_cap->num_dsc; i++) - if (hws->funcs.dsc_pg_control != NULL) - hws->funcs.dsc_pg_control(hws, res_pool->dscs[i]->inst, false); - } - /* we want to turn off all dp displays before doing detection */ dc_link_blank_all_dp_displays(dc); + if (hws->funcs.enable_power_gating_plane) + hws->funcs.enable_power_gating_plane(dc->hwseq, true); + /* If taking control over from VBIOS, we may want to optimize our first * mode set, so we need to skip powering down pipes until we know which * pipes we want to use. @@ -1559,8 +1555,6 @@ void dcn10_init_hw(struct dc *dc) REG_UPDATE(DCFCLK_CNTL, DCFCLK_GATE_DIS, 0); } - if (hws->funcs.enable_power_gating_plane) - hws->funcs.enable_power_gating_plane(dc->hwseq, true); if (dc->clk_mgr->funcs->notify_wm_ranges) dc->clk_mgr->funcs->notify_wm_ranges(dc->clk_mgr); @@ -2056,7 +2050,7 @@ static int dcn10_align_pixel_clocks(struct dc *dc, int group_size, { struct dc_context *dc_ctx = dc->ctx; int i, master = -1, embedded = -1; - struct dc_crtc_timing hw_crtc_timing[MAX_PIPES] = {0}; + struct dc_crtc_timing *hw_crtc_timing; uint64_t phase[MAX_PIPES]; uint64_t modulo[MAX_PIPES]; unsigned int pclk; @@ -2067,6 +2061,10 @@ static int dcn10_align_pixel_clocks(struct dc *dc, int group_size, uint32_t dp_ref_clk_100hz = dc->res_pool->dp_clock_source->ctx->dc->clk_mgr->dprefclk_khz*10; + hw_crtc_timing = kcalloc(MAX_PIPES, sizeof(*hw_crtc_timing), GFP_KERNEL); + if (!hw_crtc_timing) + return master; + if (dc->config.vblank_alignment_dto_params && dc->res_pool->dp_clock_source->funcs->override_dp_pix_clk) { embedded_h_total = @@ -2130,6 +2128,8 @@ static int dcn10_align_pixel_clocks(struct dc *dc, int group_size, } } + + kfree(hw_crtc_timing); return master; } @@ -2522,14 +2522,18 @@ void dcn10_update_mpcc(struct dc *dc, struct pipe_ctx *pipe_ctx) struct mpc *mpc = dc->res_pool->mpc; struct mpc_tree *mpc_tree_params = &(pipe_ctx->stream_res.opp->mpc_tree_params); - if (per_pixel_alpha) - blnd_cfg.alpha_mode = MPCC_ALPHA_BLEND_MODE_PER_PIXEL_ALPHA; - else - blnd_cfg.alpha_mode = MPCC_ALPHA_BLEND_MODE_GLOBAL_ALPHA; - blnd_cfg.overlap_only = false; blnd_cfg.global_gain = 0xff; + if (per_pixel_alpha && pipe_ctx->plane_state->global_alpha) { + blnd_cfg.alpha_mode = MPCC_ALPHA_BLEND_MODE_PER_PIXEL_ALPHA_COMBINED_GLOBAL_GAIN; + blnd_cfg.global_gain = pipe_ctx->plane_state->global_alpha_value; + } else if (per_pixel_alpha) { + blnd_cfg.alpha_mode = MPCC_ALPHA_BLEND_MODE_PER_PIXEL_ALPHA; + } else { + blnd_cfg.alpha_mode = MPCC_ALPHA_BLEND_MODE_GLOBAL_ALPHA; + } + if (pipe_ctx->plane_state->global_alpha) blnd_cfg.global_alpha = pipe_ctx->plane_state->global_alpha_value; else diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c index ab910deed481..b627c41713cc 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c @@ -1857,6 +1857,7 @@ void dcn20_optimize_bandwidth( struct dc_state *context) { struct hubbub *hubbub = dc->res_pool->hubbub; + int i; /* program dchubbub watermarks */ hubbub->funcs->program_watermarks(hubbub, @@ -1873,6 +1874,17 @@ void dcn20_optimize_bandwidth( dc->clk_mgr, context, true); + if (dc_extended_blank_supported(dc) && context->bw_ctx.bw.dcn.clk.zstate_support == DCN_ZSTATE_SUPPORT_ALLOW) { + for (i = 0; i < dc->res_pool->pipe_count; ++i) { + struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i]; + + if (pipe_ctx->stream && pipe_ctx->plane_res.hubp->funcs->program_extended_blank + && pipe_ctx->stream->adjust.v_total_min == pipe_ctx->stream->adjust.v_total_max + && pipe_ctx->stream->adjust.v_total_max > pipe_ctx->stream->timing.v_total) + pipe_ctx->plane_res.hubp->funcs->program_extended_blank(pipe_ctx->plane_res.hubp, + pipe_ctx->dlg_regs.optimized_min_dst_y_next_start); + } + } /* increase compbuf size */ if (hubbub->funcs->program_compbuf_size) hubbub->funcs->program_compbuf_size(hubbub, context->bw_ctx.bw.dcn.compbuf_size_kb, true); @@ -2332,14 +2344,18 @@ void dcn20_update_mpcc(struct dc *dc, struct pipe_ctx *pipe_ctx) struct mpc *mpc = dc->res_pool->mpc; struct mpc_tree *mpc_tree_params = &(pipe_ctx->stream_res.opp->mpc_tree_params); - if (per_pixel_alpha) - blnd_cfg.alpha_mode = MPCC_ALPHA_BLEND_MODE_PER_PIXEL_ALPHA; - else - blnd_cfg.alpha_mode = MPCC_ALPHA_BLEND_MODE_GLOBAL_ALPHA; - blnd_cfg.overlap_only = false; blnd_cfg.global_gain = 0xff; + if (per_pixel_alpha && pipe_ctx->plane_state->global_alpha) { + blnd_cfg.alpha_mode = MPCC_ALPHA_BLEND_MODE_PER_PIXEL_ALPHA_COMBINED_GLOBAL_GAIN; + blnd_cfg.global_gain = pipe_ctx->plane_state->global_alpha_value; + } else if (per_pixel_alpha) { + blnd_cfg.alpha_mode = MPCC_ALPHA_BLEND_MODE_PER_PIXEL_ALPHA; + } else { + blnd_cfg.alpha_mode = MPCC_ALPHA_BLEND_MODE_GLOBAL_ALPHA; + } + if (pipe_ctx->plane_state->global_alpha) blnd_cfg.global_alpha = pipe_ctx->plane_state->global_alpha_value; else diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c index d473708d5399..7802d603f796 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c @@ -1976,7 +1976,6 @@ int dcn20_validate_apply_pipe_split_flags( /*If need split for odm but 4 way split already*/ if (split[i] == 2 && ((pipe->prev_odm_pipe && !pipe->prev_odm_pipe->prev_odm_pipe) || !pipe->next_odm_pipe)) { - ASSERT(0); /* NOT expected yet */ merge[i] = true; /* 4 -> 2 ODM */ } else if (split[i] == 0 && pipe->prev_odm_pipe) { ASSERT(0); /* NOT expected yet */ diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c index 612732656772..faab59508d82 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c @@ -644,7 +644,7 @@ static const struct dc_debug_options debug_defaults_drv = { .clock_trace = true, .disable_pplib_clock_request = true, .min_disp_clk_khz = 100000, - .pipe_split_policy = MPC_SPLIT_DYNAMIC, + .pipe_split_policy = MPC_SPLIT_AVOID_MULT_DISP, .force_single_disp_pipe_split = false, .disable_dcc = DCC_ENABLE, .vsr_support = true, @@ -997,6 +997,7 @@ static struct clock_source *dcn21_clock_source_create( return &clk_src->base; } + kfree(clk_src); BREAK_TO_DEBUGGER(); return NULL; } diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c index ed0a0e5fd805..f61ec8763844 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c @@ -547,6 +547,9 @@ void dcn30_init_hw(struct dc *dc) /* we want to turn off all dp displays before doing detection */ dc_link_blank_all_dp_displays(dc); + if (hws->funcs.enable_power_gating_plane) + hws->funcs.enable_power_gating_plane(dc->hwseq, true); + /* If taking control over from VBIOS, we may want to optimize our first * mode set, so we need to skip powering down pipes until we know which * pipes we want to use. @@ -624,8 +627,6 @@ void dcn30_init_hw(struct dc *dc) REG_UPDATE(DCFCLK_CNTL, DCFCLK_GATE_DIS, 0); } - if (hws->funcs.enable_power_gating_plane) - hws->funcs.enable_power_gating_plane(dc->hwseq, true); if (!dcb->funcs->is_accelerated_mode(dcb) && dc->res_pool->hubbub->funcs->init_watermarks) dc->res_pool->hubbub->funcs->init_watermarks(dc->res_pool->hubbub); diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubbub.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubbub.c index 3e6d6ebd199e..51c5f3685470 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubbub.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubbub.c @@ -1042,5 +1042,7 @@ void hubbub31_construct(struct dcn20_hubbub *hubbub31, hubbub31->detile_buf_size = det_size_kb * 1024; hubbub31->pixel_chunk_size = pixel_chunk_size_kb * 1024; hubbub31->crb_size_segs = config_return_buffer_size_kb / DCN31_CRB_SEGMENT_SIZE_KB; + + hubbub31->debug_test_index_pstate = 0x6; } diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubp.c index 53b792b997b7..8ae6117953ca 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubp.c @@ -54,6 +54,13 @@ void hubp31_soft_reset(struct hubp *hubp, bool reset) REG_UPDATE(DCHUBP_CNTL, HUBP_SOFT_RESET, reset); } +void hubp31_program_extended_blank(struct hubp *hubp, unsigned int min_dst_y_next_start_optimized) +{ + struct dcn20_hubp *hubp2 = TO_DCN20_HUBP(hubp); + + REG_SET(BLANK_OFFSET_1, 0, MIN_DST_Y_NEXT_START, min_dst_y_next_start_optimized); +} + static struct hubp_funcs dcn31_hubp_funcs = { .hubp_enable_tripleBuffer = hubp2_enable_triplebuffer, .hubp_is_triplebuffer_enabled = hubp2_is_triplebuffer_enabled, @@ -80,6 +87,7 @@ static struct hubp_funcs dcn31_hubp_funcs = { .set_unbounded_requesting = hubp31_set_unbounded_requesting, .hubp_soft_reset = hubp31_soft_reset, .hubp_in_blank = hubp1_in_blank, + .program_extended_blank = hubp31_program_extended_blank, }; bool hubp31_construct( diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c index 4be228680909..631d8ac63aa4 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c @@ -199,6 +199,9 @@ void dcn31_init_hw(struct dc *dc) /* we want to turn off all dp displays before doing detection */ dc_link_blank_all_dp_displays(dc); + if (hws->funcs.enable_power_gating_plane) + hws->funcs.enable_power_gating_plane(dc->hwseq, true); + /* If taking control over from VBIOS, we may want to optimize our first * mode set, so we need to skip powering down pipes until we know which * pipes we want to use. @@ -248,8 +251,6 @@ void dcn31_init_hw(struct dc *dc) REG_UPDATE(DCFCLK_CNTL, DCFCLK_GATE_DIS, 0); } - if (hws->funcs.enable_power_gating_plane) - hws->funcs.enable_power_gating_plane(dc->hwseq, true); if (!dcb->funcs->is_accelerated_mode(dcb) && dc->res_pool->hubbub->funcs->init_watermarks) dc->res_pool->hubbub->funcs->init_watermarks(dc->res_pool->hubbub); @@ -338,20 +339,20 @@ void dcn31_enable_power_gating_plane( bool enable) { bool force_on = true; /* disable power gating */ + uint32_t org_ip_request_cntl = 0; if (enable && !hws->ctx->dc->debug.disable_hubp_power_gate) force_on = false; + REG_GET(DC_IP_REQUEST_CNTL, IP_REQUEST_EN, &org_ip_request_cntl); + if (org_ip_request_cntl == 0) + REG_SET(DC_IP_REQUEST_CNTL, 0, IP_REQUEST_EN, 1); /* DCHUBP0/1/2/3/4/5 */ REG_UPDATE(DOMAIN0_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - REG_WAIT(DOMAIN0_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, force_on, 1, 1000); REG_UPDATE(DOMAIN2_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - REG_WAIT(DOMAIN2_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, force_on, 1, 1000); /* DPP0/1/2/3/4/5 */ REG_UPDATE(DOMAIN1_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - REG_WAIT(DOMAIN1_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, force_on, 1, 1000); REG_UPDATE(DOMAIN3_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - REG_WAIT(DOMAIN3_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, force_on, 1, 1000); force_on = true; /* disable power gating */ if (enable && !hws->ctx->dc->debug.disable_dsc_power_gate) @@ -359,11 +360,11 @@ void dcn31_enable_power_gating_plane( /* DCS0/1/2/3/4/5 */ REG_UPDATE(DOMAIN16_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - REG_WAIT(DOMAIN16_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, force_on, 1, 1000); REG_UPDATE(DOMAIN17_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - REG_WAIT(DOMAIN17_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, force_on, 1, 1000); REG_UPDATE(DOMAIN18_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - REG_WAIT(DOMAIN18_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, force_on, 1, 1000); + + if (org_ip_request_cntl == 0) + REG_SET(DC_IP_REQUEST_CNTL, 0, IP_REQUEST_EN, 0); } void dcn31_update_info_frame(struct pipe_ctx *pipe_ctx) diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c index d7559e5a99ce..e708f07fe75a 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c @@ -153,9 +153,4 @@ void dcn31_hw_sequencer_construct(struct dc *dc) dc->hwss.init_hw = dcn20_fpga_init_hw; dc->hwseq->funcs.init_pipes = NULL; } - if (dc->debug.disable_z10) { - /*hw not support z10 or sw disable it*/ - dc->hwss.z10_restore = NULL; - dc->hwss.z10_save_init = NULL; - } } diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_optc.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_optc.c index 8afe2130d7c5..e05527a3a8ba 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_optc.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_optc.c @@ -124,7 +124,6 @@ static bool optc31_enable_crtc(struct timing_generator *optc) static bool optc31_disable_crtc(struct timing_generator *optc) { struct optc *optc1 = DCN10TG_FROM_TG(optc); - /* disable otg request until end of the first line * in the vertical blank region */ @@ -138,6 +137,7 @@ static bool optc31_disable_crtc(struct timing_generator *optc) REG_WAIT(OTG_CLOCK_CONTROL, OTG_BUSY, 0, 1, 100000); + optc1_clear_optc_underflow(optc); return true; } @@ -158,6 +158,9 @@ static bool optc31_immediate_disable_crtc(struct timing_generator *optc) OTG_BUSY, 0, 1, 100000); + /* clear the false state */ + optc1_clear_optc_underflow(optc); + return true; } diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c index 89b7b6b7254a..63934ecf6be8 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c @@ -2032,7 +2032,9 @@ bool dcn31_validate_bandwidth(struct dc *dc, BW_VAL_TRACE_COUNT(); + DC_FP_START(); out = dcn30_internal_validate_bw(dc, context, pipes, &pipe_cnt, &vlevel, fast_validate); + DC_FP_END(); // Disable fast_validate to set min dcfclk in alculate_wm_and_dlg if (pipe_cnt == 0) @@ -2232,6 +2234,7 @@ static bool dcn31_resource_construct( dc->caps.extended_aux_timeout_support = true; dc->caps.dmcub_support = true; dc->caps.is_apu = true; + dc->caps.zstate_support = true; /* Color pipeline capabilities */ dc->caps.color.dpp.dcn_arch = 1; diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c index 2f6122153bdb..f93af45aeab4 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c @@ -722,8 +722,10 @@ static enum dcn_zstate_support_state decide_zstate_support(struct dc *dc, struc { int plane_count; int i; + unsigned int optimized_min_dst_y_next_start_us; plane_count = 0; + optimized_min_dst_y_next_start_us = 0; for (i = 0; i < dc->res_pool->pipe_count; i++) { if (context->res_ctx.pipe_ctx[i].plane_state) plane_count++; @@ -744,11 +746,22 @@ static enum dcn_zstate_support_state decide_zstate_support(struct dc *dc, struc struct dc_link *link = context->streams[0]->sink->link; struct dc_stream_status *stream_status = &context->stream_status[0]; + if (dc_extended_blank_supported(dc)) { + for (i = 0; i < dc->res_pool->pipe_count; i++) { + if (context->res_ctx.pipe_ctx[i].stream == context->streams[0] + && context->res_ctx.pipe_ctx[i].stream->adjust.v_total_min == context->res_ctx.pipe_ctx[i].stream->adjust.v_total_max + && context->res_ctx.pipe_ctx[i].stream->adjust.v_total_min > context->res_ctx.pipe_ctx[i].stream->timing.v_total) { + optimized_min_dst_y_next_start_us = + context->res_ctx.pipe_ctx[i].dlg_regs.optimized_min_dst_y_next_start_us; + break; + } + } + } /* zstate only supported on PWRSEQ0 and when there's <2 planes*/ if (link->link_index != 0 || stream_status->plane_count > 1) return DCN_ZSTATE_SUPPORT_DISALLOW; - if (context->bw_ctx.dml.vba.StutterPeriod > 5000.0) + if (context->bw_ctx.dml.vba.StutterPeriod > 5000.0 || optimized_min_dst_y_next_start_us > 5000) return DCN_ZSTATE_SUPPORT_ALLOW; else if (link->psr_settings.psr_version == DC_PSR_VERSION_1 && !dc->debug.disable_psr) return DCN_ZSTATE_SUPPORT_ALLOW_Z10_ONLY; @@ -786,8 +799,6 @@ void dcn20_calculate_dlg_params( != dm_dram_clock_change_unsupported; context->bw_ctx.bw.dcn.clk.dppclk_khz = 0; - context->bw_ctx.bw.dcn.clk.zstate_support = decide_zstate_support(dc, context); - context->bw_ctx.bw.dcn.clk.dtbclk_en = is_dtbclk_required(dc, context); if (context->bw_ctx.bw.dcn.clk.dispclk_khz < dc->debug.min_disp_clk_khz) @@ -843,6 +854,7 @@ void dcn20_calculate_dlg_params( &pipes[pipe_idx].pipe); pipe_idx++; } + context->bw_ctx.bw.dcn.clk.zstate_support = decide_zstate_support(dc, context); } static void swizzle_to_dml_params( diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_rq_dlg_calc_31.c b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_rq_dlg_calc_31.c index e0fecf127bd5..53d760e169e6 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_rq_dlg_calc_31.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_rq_dlg_calc_31.c @@ -1055,6 +1055,7 @@ static void dml_rq_dlg_get_dlg_params( float vba__refcyc_per_req_delivery_pre_l = get_refcyc_per_req_delivery_pre_l_in_us(mode_lib, e2e_pipe_param, num_pipes, pipe_idx) * refclk_freq_in_mhz; // From VBA float vba__refcyc_per_req_delivery_l = get_refcyc_per_req_delivery_l_in_us(mode_lib, e2e_pipe_param, num_pipes, pipe_idx) * refclk_freq_in_mhz; // From VBA + int blank_lines; memset(disp_dlg_regs, 0, sizeof(*disp_dlg_regs)); memset(disp_ttu_regs, 0, sizeof(*disp_ttu_regs)); @@ -1080,6 +1081,18 @@ static void dml_rq_dlg_get_dlg_params( dlg_vblank_start = interlaced ? (vblank_start / 2) : vblank_start; disp_dlg_regs->min_dst_y_next_start = (unsigned int) (((double) dlg_vblank_start) * dml_pow(2, 2)); + blank_lines = (dst->vblank_end + dst->vtotal_min - dst->vblank_start - dst->vstartup_start - 1); + if (blank_lines < 0) + blank_lines = 0; + if (blank_lines != 0) { + disp_dlg_regs->optimized_min_dst_y_next_start_us = + ((unsigned int) blank_lines * dst->hactive) / (unsigned int) dst->pixel_rate_mhz; + disp_dlg_regs->optimized_min_dst_y_next_start = + (unsigned int)(((double) (dlg_vblank_start + blank_lines)) * dml_pow(2, 2)); + } else { + // use unoptimized value + disp_dlg_regs->optimized_min_dst_y_next_start = disp_dlg_regs->min_dst_y_next_start; + } ASSERT(disp_dlg_regs->min_dst_y_next_start < (unsigned int)dml_pow(2, 18)); dml_print("DML_DLG: %s: min_ttu_vblank (us) = %3.2f\n", __func__, min_ttu_vblank); diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h b/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h index 59f0a61c33cf..2df660cd8801 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h +++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h @@ -446,6 +446,8 @@ struct _vcs_dpi_display_dlg_regs_st { unsigned int refcyc_h_blank_end; unsigned int dlg_vblank_end; unsigned int min_dst_y_next_start; + unsigned int optimized_min_dst_y_next_start; + unsigned int optimized_min_dst_y_next_start_us; unsigned int refcyc_per_htotal; unsigned int refcyc_x_after_scaler; unsigned int dst_y_after_scaler; diff --git a/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c b/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c index efc2339f1fa0..4385d19bc489 100644 --- a/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c +++ b/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c @@ -864,11 +864,11 @@ static bool setup_dsc_config( min_slices_h = inc_num_slices(dsc_common_caps.slice_caps, min_slices_h); } + is_dsc_possible = (min_slices_h <= max_slices_h); + if (pic_width % min_slices_h != 0) min_slices_h = 0; // DSC TODO: Maybe try increasing the number of slices first? - is_dsc_possible = (min_slices_h <= max_slices_h); - if (min_slices_h == 0 && max_slices_h == 0) is_dsc_possible = false; diff --git a/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h b/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h index ab9939db8cea..44f167d2584f 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h +++ b/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h @@ -33,6 +33,7 @@ #define MAX_MTP_SLOT_COUNT 64 #define DP_REPEATER_CONFIGURATION_AND_STATUS_SIZE 0x50 #define TRAINING_AUX_RD_INTERVAL 100 //us +#define LINK_AUX_WAKE_TIMEOUT_MS 1500 // Timeout when trying to wake unresponsive DPRX. struct dc_link; struct dc_stream_state; diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h b/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h index e45b7993c5c5..ad69d78c4ac3 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h @@ -195,6 +195,9 @@ struct hubp_funcs { void (*hubp_set_flip_int)(struct hubp *hubp); + void (*program_extended_blank)(struct hubp *hubp, + unsigned int min_dst_y_next_start_optimized); + void (*hubp_wait_pipe_read_start)(struct hubp *hubp); }; diff --git a/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c b/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c index b691aa45e84f..79bc207415bc 100644 --- a/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c +++ b/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c @@ -100,7 +100,8 @@ enum vsc_packet_revision { //PB7 = MD0 #define MASK_VTEM_MD0__VRR_EN 0x01 #define MASK_VTEM_MD0__M_CONST 0x02 -#define MASK_VTEM_MD0__RESERVED2 0x0C +#define MASK_VTEM_MD0__QMS_EN 0x04 +#define MASK_VTEM_MD0__RESERVED2 0x08 #define MASK_VTEM_MD0__FVA_FACTOR_M1 0xF0 //MD1 @@ -109,7 +110,7 @@ enum vsc_packet_revision { //MD2 #define MASK_VTEM_MD2__BASE_REFRESH_RATE_98 0x03 #define MASK_VTEM_MD2__RB 0x04 -#define MASK_VTEM_MD2__RESERVED3 0xF8 +#define MASK_VTEM_MD2__NEXT_TFR 0xF8 //MD3 #define MASK_VTEM_MD3__BASE_REFRESH_RATE_07 0xFF diff --git a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c index 89fbee568be4..72e7b5d40af6 100644 --- a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c +++ b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c @@ -173,6 +173,17 @@ bool amdgpu_dpm_is_baco_supported(struct amdgpu_device *adev) if (!pp_funcs || !pp_funcs->get_asic_baco_capability) return false; + /* Don't use baco for reset in S3. + * This is a workaround for some platforms + * where entering BACO during suspend + * seems to cause reboots or hangs. + * This might be related to the fact that BACO controls + * power to the whole GPU including devices like audio and USB. + * Powering down/up everything may adversely affect these other + * devices. Needs more investigation. + */ + if (adev->in_s3) + return false; mutex_lock(&adev->pm.mutex); @@ -416,6 +427,7 @@ int amdgpu_dpm_read_sensor(struct amdgpu_device *adev, enum amd_pp_sensors senso void amdgpu_dpm_compute_clocks(struct amdgpu_device *adev) { const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs; + int i; if (!adev->pm.dpm_enabled) return; @@ -423,6 +435,15 @@ void amdgpu_dpm_compute_clocks(struct amdgpu_device *adev) if (!pp_funcs->pm_compute_clocks) return; + if (adev->mode_info.num_crtc) + amdgpu_display_bandwidth_update(adev); + + for (i = 0; i < AMDGPU_MAX_RINGS; i++) { + struct amdgpu_ring *ring = adev->rings[i]; + if (ring && ring->sched.ready) + amdgpu_fence_wait_empty(ring); + } + mutex_lock(&adev->pm.mutex); pp_funcs->pm_compute_clocks(adev->powerplay.pp_handle); mutex_unlock(&adev->pm.mutex); @@ -432,6 +453,20 @@ void amdgpu_dpm_enable_uvd(struct amdgpu_device *adev, bool enable) { int ret = 0; + if (adev->family == AMDGPU_FAMILY_SI) { + mutex_lock(&adev->pm.mutex); + if (enable) { + adev->pm.dpm.uvd_active = true; + adev->pm.dpm.state = POWER_STATE_TYPE_INTERNAL_UVD; + } else { + adev->pm.dpm.uvd_active = false; + } + mutex_unlock(&adev->pm.mutex); + + amdgpu_dpm_compute_clocks(adev); + return; + } + ret = amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_UVD, !enable); if (ret) DRM_ERROR("Dpm %s uvd failed, ret = %d. \n", @@ -442,6 +477,21 @@ void amdgpu_dpm_enable_vce(struct amdgpu_device *adev, bool enable) { int ret = 0; + if (adev->family == AMDGPU_FAMILY_SI) { + mutex_lock(&adev->pm.mutex); + if (enable) { + adev->pm.dpm.vce_active = true; + /* XXX select vce level based on ring/task */ + adev->pm.dpm.vce_level = AMD_VCE_LEVEL_AC_ALL; + } else { + adev->pm.dpm.vce_active = false; + } + mutex_unlock(&adev->pm.mutex); + + amdgpu_dpm_compute_clocks(adev); + return; + } + ret = amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_VCE, !enable); if (ret) DRM_ERROR("Dpm %s vce failed, ret = %d. \n", @@ -500,6 +550,9 @@ int amdgpu_dpm_send_hbm_bad_pages_num(struct amdgpu_device *adev, uint32_t size) struct smu_context *smu = adev->powerplay.pp_handle; int ret = 0; + if (!is_support_sw_smu(adev)) + return -EOPNOTSUPP; + mutex_lock(&adev->pm.mutex); ret = smu_send_hbm_bad_pages_num(smu, size); mutex_unlock(&adev->pm.mutex); @@ -512,6 +565,9 @@ int amdgpu_dpm_send_hbm_bad_channel_flag(struct amdgpu_device *adev, uint32_t si struct smu_context *smu = adev->powerplay.pp_handle; int ret = 0; + if (!is_support_sw_smu(adev)) + return -EOPNOTSUPP; + mutex_lock(&adev->pm.mutex); ret = smu_send_hbm_bad_channel_flag(smu, size); mutex_unlock(&adev->pm.mutex); diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c index 9613c6181c17..d3fe149d8476 100644 --- a/drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c +++ b/drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c @@ -1028,16 +1028,6 @@ static int amdgpu_dpm_change_power_state_locked(struct amdgpu_device *adev) void amdgpu_legacy_dpm_compute_clocks(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; - int i = 0; - - if (adev->mode_info.num_crtc) - amdgpu_display_bandwidth_update(adev); - - for (i = 0; i < AMDGPU_MAX_RINGS; i++) { - struct amdgpu_ring *ring = adev->rings[i]; - if (ring && ring->sched.ready) - amdgpu_fence_wait_empty(ring); - } amdgpu_dpm_get_active_displays(adev); diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c index caae54487f9c..633dab14f51c 100644 --- a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c +++ b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c @@ -3892,40 +3892,6 @@ static int si_set_boot_state(struct amdgpu_device *adev) } #endif -static int si_set_powergating_by_smu(void *handle, - uint32_t block_type, - bool gate) -{ - struct amdgpu_device *adev = (struct amdgpu_device *)handle; - - switch (block_type) { - case AMD_IP_BLOCK_TYPE_UVD: - if (!gate) { - adev->pm.dpm.uvd_active = true; - adev->pm.dpm.state = POWER_STATE_TYPE_INTERNAL_UVD; - } else { - adev->pm.dpm.uvd_active = false; - } - - amdgpu_legacy_dpm_compute_clocks(handle); - break; - case AMD_IP_BLOCK_TYPE_VCE: - if (!gate) { - adev->pm.dpm.vce_active = true; - /* XXX select vce level based on ring/task */ - adev->pm.dpm.vce_level = AMD_VCE_LEVEL_AC_ALL; - } else { - adev->pm.dpm.vce_active = false; - } - - amdgpu_legacy_dpm_compute_clocks(handle); - break; - default: - break; - } - return 0; -} - static int si_set_sw_state(struct amdgpu_device *adev) { return (amdgpu_si_send_msg_to_smc(adev, PPSMC_MSG_SwitchToSwState) == PPSMC_Result_OK) ? @@ -8125,7 +8091,6 @@ static const struct amd_pm_funcs si_dpm_funcs = { .print_power_state = &si_dpm_print_power_state, .debugfs_print_current_performance_level = &si_dpm_debugfs_print_current_performance_level, .force_performance_level = &si_dpm_force_performance_level, - .set_powergating_by_smu = &si_set_powergating_by_smu, .vblank_too_short = &si_dpm_vblank_too_short, .set_fan_control_mode = &si_dpm_set_fan_control_mode, .get_fan_control_mode = &si_dpm_get_fan_control_mode, diff --git a/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c index a2da46bf3985..71e9c6ce6b1a 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c +++ b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c @@ -1487,16 +1487,6 @@ static void pp_pm_compute_clocks(void *handle) { struct pp_hwmgr *hwmgr = handle; struct amdgpu_device *adev = hwmgr->adev; - int i = 0; - - if (adev->mode_info.num_crtc) - amdgpu_display_bandwidth_update(adev); - - for (i = 0; i < AMDGPU_MAX_RINGS; i++) { - struct amdgpu_ring *ring = adev->rings[i]; - if (ring && ring->sched.ready) - amdgpu_fence_wait_empty(ring); - } if (!amdgpu_device_has_dc_support(adev)) { amdgpu_dpm_get_active_displays(adev); diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c index 9ddd8491ff00..ede71de2343d 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c @@ -773,13 +773,13 @@ static int smu10_dpm_force_dpm_level(struct pp_hwmgr *hwmgr, smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetHardMinFclkByFreq, hwmgr->display_config->num_display > 3 ? - data->clock_vol_info.vdd_dep_on_fclk->entries[0].clk : + (data->clock_vol_info.vdd_dep_on_fclk->entries[0].clk / 100) : min_mclk, NULL); smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetHardMinSocclkByFreq, - data->clock_vol_info.vdd_dep_on_socclk->entries[0].clk, + data->clock_vol_info.vdd_dep_on_socclk->entries[0].clk / 100, NULL); smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetHardMinVcn, @@ -792,11 +792,11 @@ static int smu10_dpm_force_dpm_level(struct pp_hwmgr *hwmgr, NULL); smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetSoftMaxFclkByFreq, - data->clock_vol_info.vdd_dep_on_fclk->entries[index_fclk].clk, + data->clock_vol_info.vdd_dep_on_fclk->entries[index_fclk].clk / 100, NULL); smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetSoftMaxSocclkByFreq, - data->clock_vol_info.vdd_dep_on_socclk->entries[index_socclk].clk, + data->clock_vol_info.vdd_dep_on_socclk->entries[index_socclk].clk / 100, NULL); smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetSoftMaxVcn, diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c index f1544755d8b4..f10a0256413e 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c @@ -1351,14 +1351,8 @@ static int smu_disable_dpms(struct smu_context *smu) { struct amdgpu_device *adev = smu->adev; int ret = 0; - /* - * TODO: (adev->in_suspend && !adev->in_s0ix) is added to pair - * the workaround which always reset the asic in suspend. - * It's likely that workaround will be dropped in the future. - * Then the change here should be dropped together. - */ bool use_baco = !smu->is_apu && - (((amdgpu_in_reset(adev) || (adev->in_suspend && !adev->in_s0ix)) && + ((amdgpu_in_reset(adev) && (amdgpu_asic_reset_method(adev) == AMD_RESET_METHOD_BACO)) || ((adev->in_runpm || adev->in_s4) && amdgpu_asic_supports_baco(adev))); diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_5_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_5_ppt.c index 7bfac029e513..b81711c4ff33 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_5_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_5_ppt.c @@ -991,7 +991,7 @@ static int smu_v13_0_5_set_performance_level(struct smu_context *smu, return -EINVAL; } - if (sclk_min && sclk_max) { + if (sclk_min && sclk_max && smu_v13_0_5_clk_dpm_is_enabled(smu, SMU_SCLK)) { ret = smu_v13_0_5_set_soft_freq_limited_range(smu, SMU_SCLK, sclk_min, diff --git a/drivers/gpu/drm/bridge/Kconfig b/drivers/gpu/drm/bridge/Kconfig index 007e5a282f67..2145b08f9534 100644 --- a/drivers/gpu/drm/bridge/Kconfig +++ b/drivers/gpu/drm/bridge/Kconfig @@ -78,6 +78,7 @@ config DRM_ITE_IT6505 tristate "ITE IT6505 DisplayPort bridge" depends on OF select DRM_KMS_HELPER + select DRM_DP_HELPER select EXTCON help ITE IT6505 DisplayPort bridge chip driver. diff --git a/drivers/gpu/drm/dp/drm_dp_mst_topology.c b/drivers/gpu/drm/dp/drm_dp_mst_topology.c index 11300b53d24f..7a7cc44686f9 100644 --- a/drivers/gpu/drm/dp/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/dp/drm_dp_mst_topology.c @@ -4852,6 +4852,7 @@ static void fetch_monitor_name(struct drm_dp_mst_topology_mgr *mgr, mst_edid = drm_dp_mst_get_edid(port->connector, mgr, port); drm_edid_get_monitor_name(mst_edid, name, namelen); + kfree(mst_edid); } /** diff --git a/drivers/gpu/drm/drm_of.c b/drivers/gpu/drm/drm_of.c index 026e4e29a0f3..9a2cfab3a177 100644 --- a/drivers/gpu/drm/drm_of.c +++ b/drivers/gpu/drm/drm_of.c @@ -244,21 +244,6 @@ int drm_of_find_panel_or_bridge(const struct device_node *np, if (panel) *panel = NULL; - /** - * Devices can also be child nodes when we also control that device - * through the upstream device (ie, MIPI-DCS for a MIPI-DSI device). - * - * Lookup for a child node of the given parent that isn't either port - * or ports. - */ - for_each_available_child_of_node(np, remote) { - if (of_node_name_eq(remote, "port") || - of_node_name_eq(remote, "ports")) - continue; - - goto of_find_panel_or_bridge; - } - /* * of_graph_get_remote_node() produces a noisy error message if port * node isn't found and the absence of the port is a legit case here, @@ -269,8 +254,6 @@ int drm_of_find_panel_or_bridge(const struct device_node *np, return -ENODEV; remote = of_graph_get_remote_node(np, port, endpoint); - -of_find_panel_or_bridge: if (!remote) return -ENODEV; diff --git a/drivers/gpu/drm/i915/display/intel_dmc.c b/drivers/gpu/drm/i915/display/intel_dmc.c index 7616a3906b9e..1b774dcfb281 100644 --- a/drivers/gpu/drm/i915/display/intel_dmc.c +++ b/drivers/gpu/drm/i915/display/intel_dmc.c @@ -367,6 +367,44 @@ static void dmc_set_fw_offset(struct intel_dmc *dmc, } } +static bool dmc_mmio_addr_sanity_check(struct intel_dmc *dmc, + const u32 *mmioaddr, u32 mmio_count, + int header_ver, u8 dmc_id) +{ + struct drm_i915_private *i915 = container_of(dmc, typeof(*i915), dmc); + u32 start_range, end_range; + int i; + + if (dmc_id >= DMC_FW_MAX) { + drm_warn(&i915->drm, "Unsupported firmware id %u\n", dmc_id); + return false; + } + + if (header_ver == 1) { + start_range = DMC_MMIO_START_RANGE; + end_range = DMC_MMIO_END_RANGE; + } else if (dmc_id == DMC_FW_MAIN) { + start_range = TGL_MAIN_MMIO_START; + end_range = TGL_MAIN_MMIO_END; + } else if (DISPLAY_VER(i915) >= 13) { + start_range = ADLP_PIPE_MMIO_START; + end_range = ADLP_PIPE_MMIO_END; + } else if (DISPLAY_VER(i915) >= 12) { + start_range = TGL_PIPE_MMIO_START(dmc_id); + end_range = TGL_PIPE_MMIO_END(dmc_id); + } else { + drm_warn(&i915->drm, "Unknown mmio range for sanity check"); + return false; + } + + for (i = 0; i < mmio_count; i++) { + if (mmioaddr[i] < start_range || mmioaddr[i] > end_range) + return false; + } + + return true; +} + static u32 parse_dmc_fw_header(struct intel_dmc *dmc, const struct intel_dmc_header_base *dmc_header, size_t rem_size, u8 dmc_id) @@ -436,6 +474,12 @@ static u32 parse_dmc_fw_header(struct intel_dmc *dmc, return 0; } + if (!dmc_mmio_addr_sanity_check(dmc, mmioaddr, mmio_count, + dmc_header->header_ver, dmc_id)) { + drm_err(&i915->drm, "DMC firmware has Wrong MMIO Addresses\n"); + return 0; + } + for (i = 0; i < mmio_count; i++) { dmc_info->mmioaddr[i] = _MMIO(mmioaddr[i]); dmc_info->mmiodata[i] = mmiodata[i]; diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index d667657e3606..f868db8be02a 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -4383,13 +4383,20 @@ intel_dp_update_420(struct intel_dp *intel_dp) static void intel_dp_set_edid(struct intel_dp *intel_dp) { + struct drm_i915_private *i915 = dp_to_i915(intel_dp); struct intel_connector *connector = intel_dp->attached_connector; struct edid *edid; + bool vrr_capable; intel_dp_unset_edid(intel_dp); edid = intel_dp_get_edid(intel_dp); connector->detect_edid = edid; + vrr_capable = intel_vrr_is_capable(&connector->base); + drm_dbg_kms(&i915->drm, "[CONNECTOR:%d:%s] VRR capable: %s\n", + connector->base.base.id, connector->base.name, str_yes_no(vrr_capable)); + drm_connector_set_vrr_capable_property(&connector->base, vrr_capable); + intel_dp_update_dfp(intel_dp, edid); intel_dp_update_420(intel_dp); @@ -4422,6 +4429,9 @@ intel_dp_unset_edid(struct intel_dp *intel_dp) intel_dp->dfp.ycbcr_444_to_420 = false; connector->base.ycbcr_420_allowed = false; + + drm_connector_set_vrr_capable_property(&connector->base, + false); } static int @@ -4572,14 +4582,9 @@ static int intel_dp_get_modes(struct drm_connector *connector) int num_modes = 0; edid = intel_connector->detect_edid; - if (edid) { + if (edid) num_modes = intel_connector_update_modes(connector, edid); - if (intel_vrr_is_capable(connector)) - drm_connector_set_vrr_capable_property(connector, - true); - } - /* Also add fixed mode, which may or may not be present in EDID */ if (intel_dp_is_edp(intel_attached_dp(intel_connector)) && intel_connector->panel.fixed_mode) { diff --git a/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c b/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c index 97cf3cac0105..fb6cf30ee628 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c +++ b/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c @@ -97,6 +97,14 @@ #define INTEL_EDP_BRIGHTNESS_OPTIMIZATION_1 0x359 +enum intel_dp_aux_backlight_modparam { + INTEL_DP_AUX_BACKLIGHT_AUTO = -1, + INTEL_DP_AUX_BACKLIGHT_OFF = 0, + INTEL_DP_AUX_BACKLIGHT_ON = 1, + INTEL_DP_AUX_BACKLIGHT_FORCE_VESA = 2, + INTEL_DP_AUX_BACKLIGHT_FORCE_INTEL = 3, +}; + /* Intel EDP backlight callbacks */ static bool intel_dp_aux_supports_hdr_backlight(struct intel_connector *connector) @@ -126,6 +134,24 @@ intel_dp_aux_supports_hdr_backlight(struct intel_connector *connector) return false; } + /* + * If we don't have HDR static metadata there is no way to + * runtime detect used range for nits based control. For now + * do not use Intel proprietary eDP backlight control if we + * don't have this data in panel EDID. In case we find panel + * which supports only nits based control, but doesn't provide + * HDR static metadata we need to start maintaining table of + * ranges for such panels. + */ + if (i915->params.enable_dpcd_backlight != INTEL_DP_AUX_BACKLIGHT_FORCE_INTEL && + !(connector->base.hdr_sink_metadata.hdmi_type1.metadata_type & + BIT(HDMI_STATIC_METADATA_TYPE1))) { + drm_info(&i915->drm, + "Panel is missing HDR static metadata. Possible support for Intel HDR backlight interface is not used. If your backlight controls don't work try booting with i915.enable_dpcd_backlight=%d. needs this, please file a _new_ bug report on drm/i915, see " FDO_BUG_URL " for details.\n", + INTEL_DP_AUX_BACKLIGHT_FORCE_INTEL); + return false; + } + panel->backlight.edp.intel.sdr_uses_aux = tcon_cap[2] & INTEL_EDP_SDR_TCON_BRIGHTNESS_AUX_CAP; @@ -413,14 +439,6 @@ static const struct intel_panel_bl_funcs intel_dp_vesa_bl_funcs = { .get = intel_dp_aux_vesa_get_backlight, }; -enum intel_dp_aux_backlight_modparam { - INTEL_DP_AUX_BACKLIGHT_AUTO = -1, - INTEL_DP_AUX_BACKLIGHT_OFF = 0, - INTEL_DP_AUX_BACKLIGHT_ON = 1, - INTEL_DP_AUX_BACKLIGHT_FORCE_VESA = 2, - INTEL_DP_AUX_BACKLIGHT_FORCE_INTEL = 3, -}; - int intel_dp_aux_init_backlight_funcs(struct intel_connector *connector) { struct drm_device *dev = connector->base.dev; diff --git a/drivers/gpu/drm/i915/display/intel_fbc.c b/drivers/gpu/drm/i915/display/intel_fbc.c index 87f4af3fd523..3e61a8936245 100644 --- a/drivers/gpu/drm/i915/display/intel_fbc.c +++ b/drivers/gpu/drm/i915/display/intel_fbc.c @@ -1037,7 +1037,7 @@ static int intel_fbc_check_plane(struct intel_atomic_state *state, struct intel_plane_state *plane_state = intel_atomic_get_new_plane_state(state, plane); const struct drm_framebuffer *fb = plane_state->hw.fb; - struct intel_crtc *crtc = to_intel_crtc(plane_state->uapi.crtc); + struct intel_crtc *crtc = to_intel_crtc(plane_state->hw.crtc); const struct intel_crtc_state *crtc_state; struct intel_fbc *fbc = plane->fbc; diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c index bff8c2d73cdf..6c9e6e7f0afd 100644 --- a/drivers/gpu/drm/i915/display/intel_psr.c +++ b/drivers/gpu/drm/i915/display/intel_psr.c @@ -887,6 +887,20 @@ static bool intel_psr2_config_valid(struct intel_dp *intel_dp, return false; } + /* Wa_16011303918:adl-p */ + if (crtc_state->vrr.enable && + IS_ADLP_DISPLAY_STEP(dev_priv, STEP_A0, STEP_B0)) { + drm_dbg_kms(&dev_priv->drm, + "PSR2 not enabled, not compatible with HW stepping + VRR\n"); + return false; + } + + if (!_compute_psr2_sdp_prior_scanline_indication(intel_dp, crtc_state)) { + drm_dbg_kms(&dev_priv->drm, + "PSR2 not enabled, PSR2 SDP indication do not fit in hblank\n"); + return false; + } + if (HAS_PSR2_SEL_FETCH(dev_priv)) { if (!intel_psr2_sel_fetch_config_valid(intel_dp, crtc_state) && !HAS_PSR_HW_TRACKING(dev_priv)) { @@ -900,12 +914,12 @@ static bool intel_psr2_config_valid(struct intel_dp *intel_dp, if (!crtc_state->enable_psr2_sel_fetch && IS_TGL_DISPLAY_STEP(dev_priv, STEP_A0, STEP_C0)) { drm_dbg_kms(&dev_priv->drm, "PSR2 HW tracking is not supported this Display stepping\n"); - return false; + goto unsupported; } if (!psr2_granularity_check(intel_dp, crtc_state)) { drm_dbg_kms(&dev_priv->drm, "PSR2 not enabled, SU granularity not compatible\n"); - return false; + goto unsupported; } if (!crtc_state->enable_psr2_sel_fetch && @@ -914,25 +928,15 @@ static bool intel_psr2_config_valid(struct intel_dp *intel_dp, "PSR2 not enabled, resolution %dx%d > max supported %dx%d\n", crtc_hdisplay, crtc_vdisplay, psr_max_h, psr_max_v); - return false; - } - - if (!_compute_psr2_sdp_prior_scanline_indication(intel_dp, crtc_state)) { - drm_dbg_kms(&dev_priv->drm, - "PSR2 not enabled, PSR2 SDP indication do not fit in hblank\n"); - return false; - } - - /* Wa_16011303918:adl-p */ - if (crtc_state->vrr.enable && - IS_ADLP_DISPLAY_STEP(dev_priv, STEP_A0, STEP_B0)) { - drm_dbg_kms(&dev_priv->drm, - "PSR2 not enabled, not compatible with HW stepping + VRR\n"); - return false; + goto unsupported; } tgl_dc3co_exitline_compute_config(intel_dp, crtc_state); return true; + +unsupported: + crtc_state->enable_psr2_sel_fetch = false; + return false; } void intel_psr_compute_config(struct intel_dp *intel_dp, diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c index d42f437149c9..6ca8929cf6e1 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c @@ -1252,14 +1252,12 @@ static void *reloc_iomap(struct i915_vma *batch, * Only attempt to pin the batch buffer to ggtt if the current batch * is not inside ggtt, or the batch buffer is not misplaced. */ - if (!i915_is_ggtt(batch->vm)) { + if (!i915_is_ggtt(batch->vm) || + !i915_vma_misplaced(batch, 0, 0, PIN_MAPPABLE)) { vma = i915_gem_object_ggtt_pin_ww(obj, &eb->ww, NULL, 0, 0, PIN_MAPPABLE | PIN_NONBLOCK /* NOWARN */ | PIN_NOEVICT); - } else if (i915_vma_is_map_and_fenceable(batch)) { - __i915_vma_pin(batch); - vma = batch; } if (vma == ERR_PTR(-EDEADLK)) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c index c3ea243d414d..0c5c43852e24 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c @@ -70,7 +70,7 @@ i915_gem_mmap_ioctl(struct drm_device *dev, void *data, * mmap ioctl is disallowed for all discrete platforms, * and for all platforms with GRAPHICS_VER > 12. */ - if (IS_DGFX(i915) || GRAPHICS_VER(i915) > 12) + if (IS_DGFX(i915) || GRAPHICS_VER_FULL(i915) > IP_VER(12, 0)) return -EOPNOTSUPP; if (args->flags & ~(I915_MMAP_WC)) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c index 3a1c782ed791..e92cc9d7257c 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c @@ -408,6 +408,7 @@ shmem_pwrite(struct drm_i915_gem_object *obj, const struct drm_i915_gem_pwrite *arg) { struct address_space *mapping = obj->base.filp->f_mapping; + const struct address_space_operations *aops = mapping->a_ops; char __user *user_data = u64_to_user_ptr(arg->data_ptr); u64 remain, offset; unsigned int pg; @@ -465,9 +466,8 @@ shmem_pwrite(struct drm_i915_gem_object *obj, if (err) return err; - err = pagecache_write_begin(obj->base.filp, mapping, - offset, len, 0, - &page, &data); + err = aops->write_begin(obj->base.filp, mapping, offset, len, + &page, &data); if (err < 0) return err; @@ -477,9 +477,8 @@ shmem_pwrite(struct drm_i915_gem_object *obj, len); kunmap_atomic(vaddr); - err = pagecache_write_end(obj->base.filp, mapping, - offset, len, len - unwritten, - page, data); + err = aops->write_end(obj->base.filp, mapping, offset, len, + len - unwritten, page, data); if (err < 0) return err; @@ -622,6 +621,7 @@ i915_gem_object_create_shmem_from_data(struct drm_i915_private *dev_priv, { struct drm_i915_gem_object *obj; struct file *file; + const struct address_space_operations *aops; resource_size_t offset; int err; @@ -633,15 +633,15 @@ i915_gem_object_create_shmem_from_data(struct drm_i915_private *dev_priv, GEM_BUG_ON(obj->write_domain != I915_GEM_DOMAIN_CPU); file = obj->base.filp; + aops = file->f_mapping->a_ops; offset = 0; do { unsigned int len = min_t(typeof(size), size, PAGE_SIZE); struct page *page; void *pgdata, *vaddr; - err = pagecache_write_begin(file, file->f_mapping, - offset, len, 0, - &page, &pgdata); + err = aops->write_begin(file, file->f_mapping, offset, len, + &page, &pgdata); if (err < 0) goto fail; @@ -649,9 +649,8 @@ i915_gem_object_create_shmem_from_data(struct drm_i915_private *dev_priv, memcpy(vaddr, data, len); kunmap(page); - err = pagecache_write_end(file, file->f_mapping, - offset, len, len, - page, pgdata); + err = aops->write_end(file, file->f_mapping, offset, len, len, + page, pgdata); if (err < 0) goto fail; diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c index 82713264b96c..b7c6d4462ec5 100644 --- a/drivers/gpu/drm/i915/gt/intel_reset.c +++ b/drivers/gpu/drm/i915/gt/intel_reset.c @@ -806,7 +806,7 @@ static int gt_reset(struct intel_gt *gt, intel_engine_mask_t stalled_mask) __intel_engine_reset(engine, stalled_mask & engine->mask); local_bh_enable(); - intel_uc_reset(>->uc, true); + intel_uc_reset(>->uc, ALL_ENGINES); intel_ggtt_restore_fences(gt->ggtt); diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.h b/drivers/gpu/drm/i915/gt/uc/intel_guc.h index bf7079480d47..2488d1197f3e 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.h @@ -438,7 +438,7 @@ int intel_guc_global_policies_update(struct intel_guc *guc); void intel_guc_context_ban(struct intel_context *ce, struct i915_request *rq); void intel_guc_submission_reset_prepare(struct intel_guc *guc); -void intel_guc_submission_reset(struct intel_guc *guc, bool stalled); +void intel_guc_submission_reset(struct intel_guc *guc, intel_engine_mask_t stalled); void intel_guc_submission_reset_finish(struct intel_guc *guc); void intel_guc_submission_cancel_requests(struct intel_guc *guc); diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c index 1ce7e04aa837..28f9aac0201d 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -1590,9 +1590,9 @@ __unwind_incomplete_requests(struct intel_context *ce) spin_unlock_irqrestore(&sched_engine->lock, flags); } -static void __guc_reset_context(struct intel_context *ce, bool stalled) +static void __guc_reset_context(struct intel_context *ce, intel_engine_mask_t stalled) { - bool local_stalled; + bool guilty; struct i915_request *rq; unsigned long flags; u32 head; @@ -1620,7 +1620,7 @@ static void __guc_reset_context(struct intel_context *ce, bool stalled) if (!intel_context_is_pinned(ce)) goto next_context; - local_stalled = false; + guilty = false; rq = intel_context_find_active_request(ce); if (!rq) { head = ce->ring->tail; @@ -1628,14 +1628,14 @@ static void __guc_reset_context(struct intel_context *ce, bool stalled) } if (i915_request_started(rq)) - local_stalled = true; + guilty = stalled & ce->engine->mask; GEM_BUG_ON(i915_active_is_idle(&ce->active)); head = intel_ring_wrap(ce->ring, rq->head); - __i915_request_reset(rq, local_stalled && stalled); + __i915_request_reset(rq, guilty); out_replay: - guc_reset_state(ce, head, local_stalled && stalled); + guc_reset_state(ce, head, guilty); next_context: if (i != number_children) ce = list_next_entry(ce, parallel.child_link); @@ -1645,7 +1645,7 @@ next_context: intel_context_put(parent); } -void intel_guc_submission_reset(struct intel_guc *guc, bool stalled) +void intel_guc_submission_reset(struct intel_guc *guc, intel_engine_mask_t stalled) { struct intel_context *ce; unsigned long index; @@ -4013,7 +4013,7 @@ static void guc_context_replay(struct intel_context *ce) { struct i915_sched_engine *sched_engine = ce->engine->sched_engine; - __guc_reset_context(ce, true); + __guc_reset_context(ce, ce->engine->mask); tasklet_hi_schedule(&sched_engine->tasklet); } diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc.c b/drivers/gpu/drm/i915/gt/uc/intel_uc.c index da199aa6989f..8eb34de2f20c 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_uc.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_uc.c @@ -593,7 +593,7 @@ sanitize: __uc_sanitize(uc); } -void intel_uc_reset(struct intel_uc *uc, bool stalled) +void intel_uc_reset(struct intel_uc *uc, intel_engine_mask_t stalled) { struct intel_guc *guc = &uc->guc; diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc.h b/drivers/gpu/drm/i915/gt/uc/intel_uc.h index 866b462821c0..a8f38c2c60e2 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_uc.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_uc.h @@ -42,7 +42,7 @@ void intel_uc_driver_late_release(struct intel_uc *uc); void intel_uc_driver_remove(struct intel_uc *uc); void intel_uc_init_mmio(struct intel_uc *uc); void intel_uc_reset_prepare(struct intel_uc *uc); -void intel_uc_reset(struct intel_uc *uc, bool stalled); +void intel_uc_reset(struct intel_uc *uc, intel_engine_mask_t stalled); void intel_uc_reset_finish(struct intel_uc *uc); void intel_uc_cancel_requests(struct intel_uc *uc); void intel_uc_suspend(struct intel_uc *uc); diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 3c87d77d2cf6..fe960c204362 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -4345,12 +4345,12 @@ #define _DSPAADDR 0x70184 #define _DSPASTRIDE 0x70188 #define _DSPAPOS 0x7018C /* reserved */ -#define DISP_POS_Y_MASK REG_GENMASK(31, 0) +#define DISP_POS_Y_MASK REG_GENMASK(31, 16) #define DISP_POS_Y(y) REG_FIELD_PREP(DISP_POS_Y_MASK, (y)) #define DISP_POS_X_MASK REG_GENMASK(15, 0) #define DISP_POS_X(x) REG_FIELD_PREP(DISP_POS_X_MASK, (x)) #define _DSPASIZE 0x70190 -#define DISP_HEIGHT_MASK REG_GENMASK(31, 0) +#define DISP_HEIGHT_MASK REG_GENMASK(31, 16) #define DISP_HEIGHT(h) REG_FIELD_PREP(DISP_HEIGHT_MASK, (h)) #define DISP_WIDTH_MASK REG_GENMASK(15, 0) #define DISP_WIDTH(w) REG_FIELD_PREP(DISP_WIDTH_MASK, (w)) @@ -5152,7 +5152,7 @@ #define _SEL_FETCH_PLANE_BASE_6_A 0x70940 #define _SEL_FETCH_PLANE_BASE_7_A 0x70960 #define _SEL_FETCH_PLANE_BASE_CUR_A 0x70880 -#define _SEL_FETCH_PLANE_BASE_1_B 0x70990 +#define _SEL_FETCH_PLANE_BASE_1_B 0x71890 #define _SEL_FETCH_PLANE_BASE_A(plane) _PICK(plane, \ _SEL_FETCH_PLANE_BASE_1_A, \ @@ -5501,6 +5501,22 @@ /* MMIO address range for DMC program (0x80000 - 0x82FFF) */ #define DMC_MMIO_START_RANGE 0x80000 #define DMC_MMIO_END_RANGE 0x8FFFF +#define DMC_V1_MMIO_START_RANGE 0x80000 +#define TGL_MAIN_MMIO_START 0x8F000 +#define TGL_MAIN_MMIO_END 0x8FFFF +#define _TGL_PIPEA_MMIO_START 0x92000 +#define _TGL_PIPEA_MMIO_END 0x93FFF +#define _TGL_PIPEB_MMIO_START 0x96000 +#define _TGL_PIPEB_MMIO_END 0x97FFF +#define ADLP_PIPE_MMIO_START 0x5F000 +#define ADLP_PIPE_MMIO_END 0x5FFFF + +#define TGL_PIPE_MMIO_START(dmc_id) _PICK_EVEN(((dmc_id) - 1), _TGL_PIPEA_MMIO_START,\ + _TGL_PIPEB_MMIO_START) + +#define TGL_PIPE_MMIO_END(dmc_id) _PICK_EVEN(((dmc_id) - 1), _TGL_PIPEA_MMIO_END,\ + _TGL_PIPEB_MMIO_END) + #define SKL_DMC_DC3_DC5_COUNT _MMIO(0x80030) #define SKL_DMC_DC5_DC6_COUNT _MMIO(0x8002C) #define BXT_DMC_DC3_DC5_COUNT _MMIO(0x80038) diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c index 94fcdb7bd21d..eeaa8d0d0407 100644 --- a/drivers/gpu/drm/i915/i915_vma.c +++ b/drivers/gpu/drm/i915/i915_vma.c @@ -1605,17 +1605,17 @@ void i915_vma_close(struct i915_vma *vma) static void __i915_vma_remove_closed(struct i915_vma *vma) { - struct intel_gt *gt = vma->vm->gt; - - spin_lock_irq(>->closed_lock); list_del_init(&vma->closed_link); - spin_unlock_irq(>->closed_lock); } void i915_vma_reopen(struct i915_vma *vma) { + struct intel_gt *gt = vma->vm->gt; + + spin_lock_irq(>->closed_lock); if (i915_vma_is_closed(vma)) __i915_vma_remove_closed(vma); + spin_unlock_irq(>->closed_lock); } void i915_vma_release(struct kref *ref) @@ -1641,6 +1641,7 @@ static void force_unbind(struct i915_vma *vma) static void release_references(struct i915_vma *vma) { struct drm_i915_gem_object *obj = vma->obj; + struct intel_gt *gt = vma->vm->gt; GEM_BUG_ON(i915_vma_is_active(vma)); @@ -1650,7 +1651,9 @@ static void release_references(struct i915_vma *vma) rb_erase(&vma->obj_node, &obj->vma.tree); spin_unlock(&obj->vma.lock); + spin_lock_irq(>->closed_lock); __i915_vma_remove_closed(vma); + spin_unlock_irq(>->closed_lock); __i915_vma_put(vma); } diff --git a/drivers/gpu/drm/imx/dw_hdmi-imx.c b/drivers/gpu/drm/imx/dw_hdmi-imx.c index 87428fb23d9f..a2277a0d6d06 100644 --- a/drivers/gpu/drm/imx/dw_hdmi-imx.c +++ b/drivers/gpu/drm/imx/dw_hdmi-imx.c @@ -222,6 +222,7 @@ static int dw_hdmi_imx_probe(struct platform_device *pdev) struct device_node *np = pdev->dev.of_node; const struct of_device_id *match = of_match_node(dw_hdmi_imx_dt_ids, np); struct imx_hdmi *hdmi; + int ret; hdmi = devm_kzalloc(&pdev->dev, sizeof(*hdmi), GFP_KERNEL); if (!hdmi) @@ -243,10 +244,15 @@ static int dw_hdmi_imx_probe(struct platform_device *pdev) hdmi->bridge = of_drm_find_bridge(np); if (!hdmi->bridge) { dev_err(hdmi->dev, "Unable to find bridge\n"); + dw_hdmi_remove(hdmi->hdmi); return -ENODEV; } - return component_add(&pdev->dev, &dw_hdmi_imx_ops); + ret = component_add(&pdev->dev, &dw_hdmi_imx_ops); + if (ret) + dw_hdmi_remove(hdmi->hdmi); + + return ret; } static int dw_hdmi_imx_remove(struct platform_device *pdev) diff --git a/drivers/gpu/drm/imx/imx-ldb.c b/drivers/gpu/drm/imx/imx-ldb.c index e5078d03020d..fb0e951248f6 100644 --- a/drivers/gpu/drm/imx/imx-ldb.c +++ b/drivers/gpu/drm/imx/imx-ldb.c @@ -572,6 +572,8 @@ static int imx_ldb_panel_ddc(struct device *dev, edidp = of_get_property(child, "edid", &edid_len); if (edidp) { channel->edid = kmemdup(edidp, edid_len, GFP_KERNEL); + if (!channel->edid) + return -ENOMEM; } else if (!channel->panel) { /* fallback to display-timings node */ ret = of_get_drm_display_mode(child, diff --git a/drivers/gpu/drm/imx/parallel-display.c b/drivers/gpu/drm/imx/parallel-display.c index 06cb1a59b9bc..63ba2ad84679 100644 --- a/drivers/gpu/drm/imx/parallel-display.c +++ b/drivers/gpu/drm/imx/parallel-display.c @@ -75,8 +75,10 @@ static int imx_pd_connector_get_modes(struct drm_connector *connector) ret = of_get_drm_display_mode(np, &imxpd->mode, &imxpd->bus_flags, OF_USE_NATIVE_MODE); - if (ret) + if (ret) { + drm_mode_destroy(connector->dev, mode); return ret; + } drm_mode_copy(mode, &imxpd->mode); mode->type |= DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED; diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c index 83c31b2ad865..ccc4fcf7a630 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c @@ -1742,7 +1742,7 @@ a6xx_create_private_address_space(struct msm_gpu *gpu) return ERR_CAST(mmu); return msm_gem_address_space_create(mmu, - "gpu", 0x100000000ULL, 0x1ffffffffULL); + "gpu", 0x100000000ULL, SZ_4G); } static uint32_t a6xx_get_rptr(struct msm_gpu *gpu, struct msm_ringbuffer *ring) diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c index 89cfd84760d7..8706bcdd1472 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_device.c +++ b/drivers/gpu/drm/msm/adreno/adreno_device.c @@ -599,43 +599,91 @@ static const struct of_device_id dt_match[] = { {} }; -#ifdef CONFIG_PM -static int adreno_resume(struct device *dev) +static int adreno_runtime_resume(struct device *dev) { struct msm_gpu *gpu = dev_to_gpu(dev); return gpu->funcs->pm_resume(gpu); } -static int active_submits(struct msm_gpu *gpu) +static int adreno_runtime_suspend(struct device *dev) { - int active_submits; - mutex_lock(&gpu->active_lock); - active_submits = gpu->active_submits; - mutex_unlock(&gpu->active_lock); - return active_submits; + struct msm_gpu *gpu = dev_to_gpu(dev); + + /* + * We should be holding a runpm ref, which will prevent + * runtime suspend. In the system suspend path, we've + * already waited for active jobs to complete. + */ + WARN_ON_ONCE(gpu->active_submits); + + return gpu->funcs->pm_suspend(gpu); +} + +static void suspend_scheduler(struct msm_gpu *gpu) +{ + int i; + + /* + * Shut down the scheduler before we force suspend, so that + * suspend isn't racing with scheduler kthread feeding us + * more work. + * + * Note, we just want to park the thread, and let any jobs + * that are already on the hw queue complete normally, as + * opposed to the drm_sched_stop() path used for handling + * faulting/timed-out jobs. We can't really cancel any jobs + * already on the hw queue without racing with the GPU. + */ + for (i = 0; i < gpu->nr_rings; i++) { + struct drm_gpu_scheduler *sched = &gpu->rb[i]->sched; + kthread_park(sched->thread); + } } -static int adreno_suspend(struct device *dev) +static void resume_scheduler(struct msm_gpu *gpu) +{ + int i; + + for (i = 0; i < gpu->nr_rings; i++) { + struct drm_gpu_scheduler *sched = &gpu->rb[i]->sched; + kthread_unpark(sched->thread); + } +} + +static int adreno_system_suspend(struct device *dev) { struct msm_gpu *gpu = dev_to_gpu(dev); - int remaining; + int remaining, ret; + + suspend_scheduler(gpu); remaining = wait_event_timeout(gpu->retire_event, - active_submits(gpu) == 0, + gpu->active_submits == 0, msecs_to_jiffies(1000)); if (remaining == 0) { dev_err(dev, "Timeout waiting for GPU to suspend\n"); - return -EBUSY; + ret = -EBUSY; + goto out; } - return gpu->funcs->pm_suspend(gpu); + ret = pm_runtime_force_suspend(dev); +out: + if (ret) + resume_scheduler(gpu); + + return ret; +} + +static int adreno_system_resume(struct device *dev) +{ + resume_scheduler(dev_to_gpu(dev)); + return pm_runtime_force_resume(dev); } -#endif static const struct dev_pm_ops adreno_pm_ops = { - SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, pm_runtime_force_resume) - SET_RUNTIME_PM_OPS(adreno_suspend, adreno_resume, NULL) + SYSTEM_SLEEP_PM_OPS(adreno_system_suspend, adreno_system_resume) + RUNTIME_PM_OPS(adreno_runtime_suspend, adreno_runtime_resume, NULL) }; static struct platform_driver adreno_driver = { diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c index c515b7cf922c..c61b5b283f08 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c @@ -54,87 +54,87 @@ struct dpu_intr_reg { * When making changes be sure to sync with dpu_hw_intr_reg */ static const struct dpu_intr_reg dpu_intr_set[] = { - { + [MDP_SSPP_TOP0_INTR] = { MDP_SSPP_TOP0_OFF+INTR_CLEAR, MDP_SSPP_TOP0_OFF+INTR_EN, MDP_SSPP_TOP0_OFF+INTR_STATUS }, - { + [MDP_SSPP_TOP0_INTR2] = { MDP_SSPP_TOP0_OFF+INTR2_CLEAR, MDP_SSPP_TOP0_OFF+INTR2_EN, MDP_SSPP_TOP0_OFF+INTR2_STATUS }, - { + [MDP_SSPP_TOP0_HIST_INTR] = { MDP_SSPP_TOP0_OFF+HIST_INTR_CLEAR, MDP_SSPP_TOP0_OFF+HIST_INTR_EN, MDP_SSPP_TOP0_OFF+HIST_INTR_STATUS }, - { + [MDP_INTF0_INTR] = { MDP_INTF_0_OFF+INTF_INTR_CLEAR, MDP_INTF_0_OFF+INTF_INTR_EN, MDP_INTF_0_OFF+INTF_INTR_STATUS }, - { + [MDP_INTF1_INTR] = { MDP_INTF_1_OFF+INTF_INTR_CLEAR, MDP_INTF_1_OFF+INTF_INTR_EN, MDP_INTF_1_OFF+INTF_INTR_STATUS }, - { + [MDP_INTF2_INTR] = { MDP_INTF_2_OFF+INTF_INTR_CLEAR, MDP_INTF_2_OFF+INTF_INTR_EN, MDP_INTF_2_OFF+INTF_INTR_STATUS }, - { + [MDP_INTF3_INTR] = { MDP_INTF_3_OFF+INTF_INTR_CLEAR, MDP_INTF_3_OFF+INTF_INTR_EN, MDP_INTF_3_OFF+INTF_INTR_STATUS }, - { + [MDP_INTF4_INTR] = { MDP_INTF_4_OFF+INTF_INTR_CLEAR, MDP_INTF_4_OFF+INTF_INTR_EN, MDP_INTF_4_OFF+INTF_INTR_STATUS }, - { + [MDP_INTF5_INTR] = { MDP_INTF_5_OFF+INTF_INTR_CLEAR, MDP_INTF_5_OFF+INTF_INTR_EN, MDP_INTF_5_OFF+INTF_INTR_STATUS }, - { + [MDP_AD4_0_INTR] = { MDP_AD4_0_OFF + MDP_AD4_INTR_CLEAR_OFF, MDP_AD4_0_OFF + MDP_AD4_INTR_EN_OFF, MDP_AD4_0_OFF + MDP_AD4_INTR_STATUS_OFF, }, - { + [MDP_AD4_1_INTR] = { MDP_AD4_1_OFF + MDP_AD4_INTR_CLEAR_OFF, MDP_AD4_1_OFF + MDP_AD4_INTR_EN_OFF, MDP_AD4_1_OFF + MDP_AD4_INTR_STATUS_OFF, }, - { + [MDP_INTF0_7xxx_INTR] = { MDP_INTF_0_OFF_REV_7xxx+INTF_INTR_CLEAR, MDP_INTF_0_OFF_REV_7xxx+INTF_INTR_EN, MDP_INTF_0_OFF_REV_7xxx+INTF_INTR_STATUS }, - { + [MDP_INTF1_7xxx_INTR] = { MDP_INTF_1_OFF_REV_7xxx+INTF_INTR_CLEAR, MDP_INTF_1_OFF_REV_7xxx+INTF_INTR_EN, MDP_INTF_1_OFF_REV_7xxx+INTF_INTR_STATUS }, - { + [MDP_INTF2_7xxx_INTR] = { MDP_INTF_2_OFF_REV_7xxx+INTF_INTR_CLEAR, MDP_INTF_2_OFF_REV_7xxx+INTF_INTR_EN, MDP_INTF_2_OFF_REV_7xxx+INTF_INTR_STATUS }, - { + [MDP_INTF3_7xxx_INTR] = { MDP_INTF_3_OFF_REV_7xxx+INTF_INTR_CLEAR, MDP_INTF_3_OFF_REV_7xxx+INTF_INTR_EN, MDP_INTF_3_OFF_REV_7xxx+INTF_INTR_STATUS }, - { + [MDP_INTF4_7xxx_INTR] = { MDP_INTF_4_OFF_REV_7xxx+INTF_INTR_CLEAR, MDP_INTF_4_OFF_REV_7xxx+INTF_INTR_EN, MDP_INTF_4_OFF_REV_7xxx+INTF_INTR_STATUS }, - { + [MDP_INTF5_7xxx_INTR] = { MDP_INTF_5_OFF_REV_7xxx+INTF_INTR_CLEAR, MDP_INTF_5_OFF_REV_7xxx+INTF_INTR_EN, MDP_INTF_5_OFF_REV_7xxx+INTF_INTR_STATUS diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c index 1ee824600995..c478d25f7825 100644 --- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c +++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c @@ -98,7 +98,10 @@ static void mdp5_plane_reset(struct drm_plane *plane) __drm_atomic_helper_plane_destroy_state(plane->state); kfree(to_mdp5_plane_state(plane->state)); + plane->state = NULL; mdp5_state = kzalloc(sizeof(*mdp5_state), GFP_KERNEL); + if (!mdp5_state) + return; __drm_atomic_helper_plane_reset(plane, &mdp5_state->base); } diff --git a/drivers/gpu/drm/msm/disp/msm_disp_snapshot_util.c b/drivers/gpu/drm/msm/disp/msm_disp_snapshot_util.c index 5d2ff6791058..acfe1b31e079 100644 --- a/drivers/gpu/drm/msm/disp/msm_disp_snapshot_util.c +++ b/drivers/gpu/drm/msm/disp/msm_disp_snapshot_util.c @@ -176,6 +176,8 @@ void msm_disp_snapshot_add_block(struct msm_disp_state *disp_state, u32 len, va_list va; new_blk = kzalloc(sizeof(struct msm_disp_state_block), GFP_KERNEL); + if (!new_blk) + return; va_start(va, fmt); diff --git a/drivers/gpu/drm/msm/dp/dp_panel.c b/drivers/gpu/drm/msm/dp/dp_panel.c index f1418722c549..26f4b6959c31 100644 --- a/drivers/gpu/drm/msm/dp/dp_panel.c +++ b/drivers/gpu/drm/msm/dp/dp_panel.c @@ -206,17 +206,6 @@ int dp_panel_read_sink_caps(struct dp_panel *dp_panel, rc = -ETIMEDOUT; goto end; } - - /* fail safe edid */ - mutex_lock(&connector->dev->mode_config.mutex); - if (drm_add_modes_noedid(connector, 640, 480)) - drm_set_preferred_mode(connector, 640, 480); - mutex_unlock(&connector->dev->mode_config.mutex); - } else { - /* always add fail-safe mode as backup mode */ - mutex_lock(&connector->dev->mode_config.mutex); - drm_add_modes_noedid(connector, 640, 480); - mutex_unlock(&connector->dev->mode_config.mutex); } if (panel->aux_cfg_update_done) { diff --git a/drivers/gpu/drm/msm/dsi/dsi_manager.c b/drivers/gpu/drm/msm/dsi/dsi_manager.c index 0c1b7dde377c..9f6af0f0fe00 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_manager.c +++ b/drivers/gpu/drm/msm/dsi/dsi_manager.c @@ -638,7 +638,7 @@ struct drm_connector *msm_dsi_manager_connector_init(u8 id) return connector; fail: - connector->funcs->destroy(msm_dsi->connector); + connector->funcs->destroy(connector); return ERR_PTR(ret); } diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c index 02b9ae65a96a..a4f61972667b 100644 --- a/drivers/gpu/drm/msm/msm_gem.c +++ b/drivers/gpu/drm/msm/msm_gem.c @@ -926,6 +926,7 @@ void msm_gem_describe(struct drm_gem_object *obj, struct seq_file *m, get_pid_task(aspace->pid, PIDTYPE_PID); if (task) { comm = kstrdup(task->comm, GFP_KERNEL); + put_task_struct(task); } else { comm = NULL; } diff --git a/drivers/gpu/drm/nouveau/nouveau_backlight.c b/drivers/gpu/drm/nouveau/nouveau_backlight.c index daf9f87477ba..a2141d3d9b1d 100644 --- a/drivers/gpu/drm/nouveau/nouveau_backlight.c +++ b/drivers/gpu/drm/nouveau/nouveau_backlight.c @@ -46,8 +46,9 @@ static bool nouveau_get_backlight_name(char backlight_name[BL_NAME_SIZE], struct nouveau_backlight *bl) { - const int nb = ida_simple_get(&bl_ida, 0, 0, GFP_KERNEL); - if (nb < 0 || nb >= 100) + const int nb = ida_alloc_max(&bl_ida, 99, GFP_KERNEL); + + if (nb < 0) return false; if (nb > 0) snprintf(backlight_name, BL_NAME_SIZE, "nv_backlight%d", nb); @@ -414,7 +415,7 @@ nouveau_backlight_init(struct drm_connector *connector) nv_encoder, ops, &props); if (IS_ERR(bl->dev)) { if (bl->id >= 0) - ida_simple_remove(&bl_ida, bl->id); + ida_free(&bl_ida, bl->id); ret = PTR_ERR(bl->dev); goto fail_alloc; } @@ -442,7 +443,7 @@ nouveau_backlight_fini(struct drm_connector *connector) return; if (bl->id >= 0) - ida_simple_remove(&bl_ida, bl->id); + ida_free(&bl_ida, bl->id); backlight_device_unregister(bl->dev); nv_conn->backlight = NULL; diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c index 992cc285f2fe..2ed528c065fa 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c @@ -123,7 +123,7 @@ nvkm_device_tegra_probe_iommu(struct nvkm_device_tegra *tdev) mutex_init(&tdev->iommu.mutex); - if (iommu_present(&platform_bus_type)) { + if (device_iommu_mapped(dev)) { tdev->iommu.domain = iommu_domain_alloc(&platform_bus_type); if (!tdev->iommu.domain) goto error; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gm20b.c b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gm20b.c index e1772211b0a4..612310d5d481 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gm20b.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gm20b.c @@ -216,6 +216,7 @@ gm20b_pmu = { .intr = gt215_pmu_intr, .recv = gm20b_pmu_recv, .initmsg = gm20b_pmu_initmsg, + .reset = gf100_pmu_reset, }; #if IS_ENABLED(CONFIG_ARCH_TEGRA_210_SOC) diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp102.c index 6bf7fc1bd1e3..1a6f9c3af5ec 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp102.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp102.c @@ -23,7 +23,7 @@ */ #include "priv.h" -static void +void gp102_pmu_reset(struct nvkm_pmu *pmu) { struct nvkm_device *device = pmu->subdev.device; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp10b.c b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp10b.c index ba1583bb618b..94cfb1791af6 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp10b.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp10b.c @@ -83,6 +83,7 @@ gp10b_pmu = { .intr = gt215_pmu_intr, .recv = gm20b_pmu_recv, .initmsg = gm20b_pmu_initmsg, + .reset = gp102_pmu_reset, }; #if IS_ENABLED(CONFIG_ARCH_TEGRA_210_SOC) diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/priv.h b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/priv.h index bcaade758ff7..21abf31f4442 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/priv.h +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/priv.h @@ -41,6 +41,7 @@ int gt215_pmu_send(struct nvkm_pmu *, u32[2], u32, u32, u32, u32); bool gf100_pmu_enabled(struct nvkm_pmu *); void gf100_pmu_reset(struct nvkm_pmu *); +void gp102_pmu_reset(struct nvkm_pmu *pmu); void gk110_pmu_pgob(struct nvkm_pmu *, bool); diff --git a/drivers/gpu/drm/panel/panel-ilitek-ili9341.c b/drivers/gpu/drm/panel/panel-ilitek-ili9341.c index a07ef26234e5..6826f4d4826a 100644 --- a/drivers/gpu/drm/panel/panel-ilitek-ili9341.c +++ b/drivers/gpu/drm/panel/panel-ilitek-ili9341.c @@ -612,8 +612,10 @@ static int ili9341_dbi_probe(struct spi_device *spi, struct gpio_desc *dc, int ret; vcc = devm_regulator_get_optional(dev, "vcc"); - if (IS_ERR(vcc)) + if (IS_ERR(vcc)) { dev_err(dev, "get optional vcc failed\n"); + vcc = NULL; + } dbidev = devm_drm_dev_alloc(dev, &ili9341_dbi_driver, struct mipi_dbi_dev, drm); diff --git a/drivers/gpu/drm/panel/panel-raspberrypi-touchscreen.c b/drivers/gpu/drm/panel/panel-raspberrypi-touchscreen.c index 46029c5610c8..145047e19394 100644 --- a/drivers/gpu/drm/panel/panel-raspberrypi-touchscreen.c +++ b/drivers/gpu/drm/panel/panel-raspberrypi-touchscreen.c @@ -229,7 +229,7 @@ static void rpi_touchscreen_i2c_write(struct rpi_touchscreen *ts, ret = i2c_smbus_write_byte_data(ts->i2c, reg, val); if (ret) - dev_err(&ts->dsi->dev, "I2C write failed: %d\n", ret); + dev_err(&ts->i2c->dev, "I2C write failed: %d\n", ret); } static int rpi_touchscreen_write(struct rpi_touchscreen *ts, u16 reg, u32 val) @@ -265,7 +265,7 @@ static int rpi_touchscreen_noop(struct drm_panel *panel) return 0; } -static int rpi_touchscreen_enable(struct drm_panel *panel) +static int rpi_touchscreen_prepare(struct drm_panel *panel) { struct rpi_touchscreen *ts = panel_to_ts(panel); int i; @@ -295,6 +295,13 @@ static int rpi_touchscreen_enable(struct drm_panel *panel) rpi_touchscreen_write(ts, DSI_STARTDSI, 0x01); msleep(100); + return 0; +} + +static int rpi_touchscreen_enable(struct drm_panel *panel) +{ + struct rpi_touchscreen *ts = panel_to_ts(panel); + /* Turn on the backlight. */ rpi_touchscreen_i2c_write(ts, REG_PWM, 255); @@ -349,7 +356,7 @@ static int rpi_touchscreen_get_modes(struct drm_panel *panel, static const struct drm_panel_funcs rpi_touchscreen_funcs = { .disable = rpi_touchscreen_disable, .unprepare = rpi_touchscreen_noop, - .prepare = rpi_touchscreen_noop, + .prepare = rpi_touchscreen_prepare, .enable = rpi_touchscreen_enable, .get_modes = rpi_touchscreen_get_modes, }; diff --git a/drivers/gpu/drm/radeon/radeon_sync.c b/drivers/gpu/drm/radeon/radeon_sync.c index b991ba1bcd51..f63efd8d5e52 100644 --- a/drivers/gpu/drm/radeon/radeon_sync.c +++ b/drivers/gpu/drm/radeon/radeon_sync.c @@ -96,7 +96,7 @@ int radeon_sync_resv(struct radeon_device *rdev, struct dma_fence *f; int r = 0; - dma_resv_for_each_fence(&cursor, resv, shared, f) { + dma_resv_for_each_fence(&cursor, resv, !shared, f) { fence = to_radeon_fence(f); if (fence && fence->rdev == rdev) radeon_sync_fence(sync, fence); diff --git a/drivers/gpu/drm/sun4i/sun4i_frontend.c b/drivers/gpu/drm/sun4i/sun4i_frontend.c index 56ae38389db0..462fae73eae9 100644 --- a/drivers/gpu/drm/sun4i/sun4i_frontend.c +++ b/drivers/gpu/drm/sun4i/sun4i_frontend.c @@ -222,13 +222,11 @@ void sun4i_frontend_update_buffer(struct sun4i_frontend *frontend, /* Set the physical address of the buffer in memory */ paddr = drm_fb_cma_get_gem_addr(fb, state, 0); - paddr -= PHYS_OFFSET; DRM_DEBUG_DRIVER("Setting buffer #0 address to %pad\n", &paddr); regmap_write(frontend->regs, SUN4I_FRONTEND_BUF_ADDR0_REG, paddr); if (fb->format->num_planes > 1) { paddr = drm_fb_cma_get_gem_addr(fb, state, swap ? 2 : 1); - paddr -= PHYS_OFFSET; DRM_DEBUG_DRIVER("Setting buffer #1 address to %pad\n", &paddr); regmap_write(frontend->regs, SUN4I_FRONTEND_BUF_ADDR1_REG, paddr); @@ -236,7 +234,6 @@ void sun4i_frontend_update_buffer(struct sun4i_frontend *frontend, if (fb->format->num_planes > 2) { paddr = drm_fb_cma_get_gem_addr(fb, state, swap ? 1 : 2); - paddr -= PHYS_OFFSET; DRM_DEBUG_DRIVER("Setting buffer #2 address to %pad\n", &paddr); regmap_write(frontend->regs, SUN4I_FRONTEND_BUF_ADDR2_REG, paddr); diff --git a/drivers/gpu/drm/vc4/Kconfig b/drivers/gpu/drm/vc4/Kconfig index de3424fed2fc..6cf2621786e6 100644 --- a/drivers/gpu/drm/vc4/Kconfig +++ b/drivers/gpu/drm/vc4/Kconfig @@ -2,6 +2,9 @@ config DRM_VC4 tristate "Broadcom VC4 Graphics" depends on ARCH_BCM || ARCH_BCM2835 || COMPILE_TEST + # Make sure not 'y' when RASPBERRYPI_FIRMWARE is 'm'. This can only + # happen when COMPILE_TEST=y, hence the added !RASPBERRYPI_FIRMWARE. + depends on RASPBERRYPI_FIRMWARE || (COMPILE_TEST && !RASPBERRYPI_FIRMWARE) depends on DRM depends on SND && SND_SOC depends on COMMON_CLK diff --git a/drivers/gpu/drm/vc4/vc4_dsi.c b/drivers/gpu/drm/vc4/vc4_dsi.c index 752f921735c6..98308a17e4ed 100644 --- a/drivers/gpu/drm/vc4/vc4_dsi.c +++ b/drivers/gpu/drm/vc4/vc4_dsi.c @@ -846,7 +846,7 @@ static void vc4_dsi_encoder_enable(struct drm_encoder *encoder) unsigned long phy_clock; int ret; - ret = pm_runtime_get_sync(dev); + ret = pm_runtime_resume_and_get(dev); if (ret) { DRM_ERROR("Failed to runtime PM enable on DSI%d\n", dsi->variant->port); return; diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c index 6c58b0fd13fb..98b78ec6b37d 100644 --- a/drivers/gpu/drm/vc4/vc4_hdmi.c +++ b/drivers/gpu/drm/vc4/vc4_hdmi.c @@ -38,6 +38,7 @@ #include <drm/drm_scdc_helper.h> #include <linux/clk.h> #include <linux/component.h> +#include <linux/gpio/consumer.h> #include <linux/i2c.h> #include <linux/of_address.h> #include <linux/of_gpio.h> diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c index 31aecc46624b..04c8a378aeed 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c @@ -46,6 +46,21 @@ vmw_buffer_object(struct ttm_buffer_object *bo) return container_of(bo, struct vmw_buffer_object, base); } +/** + * bo_is_vmw - check if the buffer object is a &vmw_buffer_object + * @bo: ttm buffer object to be checked + * + * Uses destroy function associated with the object to determine if this is + * a &vmw_buffer_object. + * + * Returns: + * true if the object is of &vmw_buffer_object type, false if not. + */ +static bool bo_is_vmw(struct ttm_buffer_object *bo) +{ + return bo->destroy == &vmw_bo_bo_free || + bo->destroy == &vmw_gem_destroy; +} /** * vmw_bo_pin_in_placement - Validate a buffer to placement. @@ -615,8 +630,9 @@ int vmw_user_bo_synccpu_ioctl(struct drm_device *dev, void *data, ret = vmw_user_bo_synccpu_grab(vbo, arg->flags); vmw_bo_unreference(&vbo); - if (unlikely(ret != 0 && ret != -ERESTARTSYS && - ret != -EBUSY)) { + if (unlikely(ret != 0)) { + if (ret == -ERESTARTSYS || ret == -EBUSY) + return -EBUSY; DRM_ERROR("Failed synccpu grab on handle 0x%08x.\n", (unsigned int) arg->handle); return ret; @@ -798,7 +814,7 @@ int vmw_dumb_create(struct drm_file *file_priv, void vmw_bo_swap_notify(struct ttm_buffer_object *bo) { /* Is @bo embedded in a struct vmw_buffer_object? */ - if (vmw_bo_is_vmw_bo(bo)) + if (!bo_is_vmw(bo)) return; /* Kill any cached kernel maps before swapout */ @@ -822,7 +838,7 @@ void vmw_bo_move_notify(struct ttm_buffer_object *bo, struct vmw_buffer_object *vbo; /* Make sure @bo is embedded in a struct vmw_buffer_object? */ - if (vmw_bo_is_vmw_bo(bo)) + if (!bo_is_vmw(bo)) return; vbo = container_of(bo, struct vmw_buffer_object, base); @@ -843,22 +859,3 @@ void vmw_bo_move_notify(struct ttm_buffer_object *bo, if (mem->mem_type != VMW_PL_MOB && bo->resource->mem_type == VMW_PL_MOB) vmw_resource_unbind_list(vbo); } - -/** - * vmw_bo_is_vmw_bo - check if the buffer object is a &vmw_buffer_object - * @bo: buffer object to be checked - * - * Uses destroy function associated with the object to determine if this is - * a &vmw_buffer_object. - * - * Returns: - * true if the object is of &vmw_buffer_object type, false if not. - */ -bool vmw_bo_is_vmw_bo(struct ttm_buffer_object *bo) -{ - if (bo->destroy == &vmw_bo_bo_free || - bo->destroy == &vmw_gem_destroy) - return true; - - return false; -} diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cmd.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cmd.c index a3bfbb6c3e14..162dfeb1cc5a 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_cmd.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cmd.c @@ -528,7 +528,7 @@ int vmw_cmd_send_fence(struct vmw_private *dev_priv, uint32_t *seqno) *seqno = atomic_add_return(1, &dev_priv->marker_seq); } while (*seqno == 0); - if (!(vmw_fifo_caps(dev_priv) & SVGA_FIFO_CAP_FENCE)) { + if (!vmw_has_fences(dev_priv)) { /* * Don't request hardware to send a fence. The @@ -675,11 +675,14 @@ int vmw_cmd_emit_dummy_query(struct vmw_private *dev_priv, */ bool vmw_cmd_supported(struct vmw_private *vmw) { - if ((vmw->capabilities & (SVGA_CAP_COMMAND_BUFFERS | - SVGA_CAP_CMD_BUFFERS_2)) != 0) - return true; + bool has_cmdbufs = + (vmw->capabilities & (SVGA_CAP_COMMAND_BUFFERS | + SVGA_CAP_CMD_BUFFERS_2)) != 0; + if (vmw_is_svga_v3(vmw)) + return (has_cmdbufs && + (vmw->capabilities & SVGA_CAP_GBOBJECTS) != 0); /* * We have FIFO cmd's */ - return vmw->fifo_mem != NULL; + return has_cmdbufs || vmw->fifo_mem != NULL; } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index 26eb5478394a..163c00793eb1 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -998,13 +998,10 @@ static int vmw_driver_load(struct vmw_private *dev_priv, u32 pci_id) goto out_no_fman; } - drm_vma_offset_manager_init(&dev_priv->vma_manager, - DRM_FILE_PAGE_OFFSET_START, - DRM_FILE_PAGE_OFFSET_SIZE); ret = ttm_device_init(&dev_priv->bdev, &vmw_bo_driver, dev_priv->drm.dev, dev_priv->drm.anon_inode->i_mapping, - &dev_priv->vma_manager, + dev_priv->drm.vma_offset_manager, dev_priv->map_mode == vmw_dma_alloc_coherent, false); if (unlikely(ret != 0)) { @@ -1174,7 +1171,6 @@ static void vmw_driver_unload(struct drm_device *dev) vmw_devcaps_destroy(dev_priv); vmw_vram_manager_fini(dev_priv); ttm_device_fini(&dev_priv->bdev); - drm_vma_offset_manager_destroy(&dev_priv->vma_manager); vmw_release_device_late(dev_priv); vmw_fence_manager_takedown(dev_priv->fman); if (dev_priv->capabilities & SVGA_CAP_IRQMASK) @@ -1398,7 +1394,7 @@ vmw_get_unmapped_area(struct file *file, unsigned long uaddr, struct vmw_private *dev_priv = vmw_priv(file_priv->minor->dev); return drm_get_unmapped_area(file, uaddr, len, pgoff, flags, - &dev_priv->vma_manager); + dev_priv->drm.vma_offset_manager); } static int vmwgfx_pm_notifier(struct notifier_block *nb, unsigned long val, diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h index ea3ecdda561d..6de0b9ef5c77 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h @@ -1679,4 +1679,12 @@ static inline void vmw_irq_status_write(struct vmw_private *vmw, outl(status, vmw->io_start + SVGA_IRQSTATUS_PORT); } +static inline bool vmw_has_fences(struct vmw_private *vmw) +{ + if ((vmw->capabilities & (SVGA_CAP_COMMAND_BUFFERS | + SVGA_CAP_CMD_BUFFERS_2)) != 0) + return true; + return (vmw_fifo_caps(vmw) & SVGA_FIFO_CAP_FENCE) != 0; +} + #endif diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c index 8ee34576c7d0..adf17c740656 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c @@ -483,7 +483,7 @@ static int vmw_fb_kms_detach(struct vmw_fb_par *par, static int vmw_fb_kms_framebuffer(struct fb_info *info) { - struct drm_mode_fb_cmd2 mode_cmd; + struct drm_mode_fb_cmd2 mode_cmd = {0}; struct vmw_fb_par *par = info->par; struct fb_var_screeninfo *var = &info->var; struct drm_framebuffer *cur_fb; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c index 59d6a2dd4c2e..66cc35dc223e 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c @@ -82,6 +82,22 @@ fman_from_fence(struct vmw_fence_obj *fence) return container_of(fence->base.lock, struct vmw_fence_manager, lock); } +static u32 vmw_fence_goal_read(struct vmw_private *vmw) +{ + if ((vmw->capabilities2 & SVGA_CAP2_EXTRA_REGS) != 0) + return vmw_read(vmw, SVGA_REG_FENCE_GOAL); + else + return vmw_fifo_mem_read(vmw, SVGA_FIFO_FENCE_GOAL); +} + +static void vmw_fence_goal_write(struct vmw_private *vmw, u32 value) +{ + if ((vmw->capabilities2 & SVGA_CAP2_EXTRA_REGS) != 0) + vmw_write(vmw, SVGA_REG_FENCE_GOAL, value); + else + vmw_fifo_mem_write(vmw, SVGA_FIFO_FENCE_GOAL, value); +} + /* * Note on fencing subsystem usage of irqs: * Typically the vmw_fences_update function is called @@ -392,7 +408,7 @@ static bool vmw_fence_goal_new_locked(struct vmw_fence_manager *fman, if (likely(!fman->seqno_valid)) return false; - goal_seqno = vmw_fifo_mem_read(fman->dev_priv, SVGA_FIFO_FENCE_GOAL); + goal_seqno = vmw_fence_goal_read(fman->dev_priv); if (likely(passed_seqno - goal_seqno >= VMW_FENCE_WRAP)) return false; @@ -400,9 +416,8 @@ static bool vmw_fence_goal_new_locked(struct vmw_fence_manager *fman, list_for_each_entry(fence, &fman->fence_list, head) { if (!list_empty(&fence->seq_passed_actions)) { fman->seqno_valid = true; - vmw_fifo_mem_write(fman->dev_priv, - SVGA_FIFO_FENCE_GOAL, - fence->base.seqno); + vmw_fence_goal_write(fman->dev_priv, + fence->base.seqno); break; } } @@ -434,13 +449,12 @@ static bool vmw_fence_goal_check_locked(struct vmw_fence_obj *fence) if (dma_fence_is_signaled_locked(&fence->base)) return false; - goal_seqno = vmw_fifo_mem_read(fman->dev_priv, SVGA_FIFO_FENCE_GOAL); + goal_seqno = vmw_fence_goal_read(fman->dev_priv); if (likely(fman->seqno_valid && goal_seqno - fence->base.seqno < VMW_FENCE_WRAP)) return false; - vmw_fifo_mem_write(fman->dev_priv, SVGA_FIFO_FENCE_GOAL, - fence->base.seqno); + vmw_fence_goal_write(fman->dev_priv, fence->base.seqno); fman->seqno_valid = true; return true; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_irq.c b/drivers/gpu/drm/vmwgfx/vmwgfx_irq.c index c5191de365ca..fe4732bf2c9d 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_irq.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_irq.c @@ -32,6 +32,14 @@ #define VMW_FENCE_WRAP (1 << 24) +static u32 vmw_irqflag_fence_goal(struct vmw_private *vmw) +{ + if ((vmw->capabilities2 & SVGA_CAP2_EXTRA_REGS) != 0) + return SVGA_IRQFLAG_REG_FENCE_GOAL; + else + return SVGA_IRQFLAG_FENCE_GOAL; +} + /** * vmw_thread_fn - Deferred (process context) irq handler * @@ -96,7 +104,7 @@ static irqreturn_t vmw_irq_handler(int irq, void *arg) wake_up_all(&dev_priv->fifo_queue); if ((masked_status & (SVGA_IRQFLAG_ANY_FENCE | - SVGA_IRQFLAG_FENCE_GOAL)) && + vmw_irqflag_fence_goal(dev_priv))) && !test_and_set_bit(VMW_IRQTHREAD_FENCE, dev_priv->irqthread_pending)) ret = IRQ_WAKE_THREAD; @@ -137,8 +145,7 @@ bool vmw_seqno_passed(struct vmw_private *dev_priv, if (likely(dev_priv->last_read_seqno - seqno < VMW_FENCE_WRAP)) return true; - if (!(vmw_fifo_caps(dev_priv) & SVGA_FIFO_CAP_FENCE) && - vmw_fifo_idle(dev_priv, seqno)) + if (!vmw_has_fences(dev_priv) && vmw_fifo_idle(dev_priv, seqno)) return true; /** @@ -160,6 +167,7 @@ int vmw_fallback_wait(struct vmw_private *dev_priv, unsigned long timeout) { struct vmw_fifo_state *fifo_state = dev_priv->fifo; + bool fifo_down = false; uint32_t count = 0; uint32_t signal_seq; @@ -176,12 +184,14 @@ int vmw_fallback_wait(struct vmw_private *dev_priv, */ if (fifo_idle) { - down_read(&fifo_state->rwsem); if (dev_priv->cman) { ret = vmw_cmdbuf_idle(dev_priv->cman, interruptible, 10*HZ); if (ret) goto out_err; + } else if (fifo_state) { + down_read(&fifo_state->rwsem); + fifo_down = true; } } @@ -218,12 +228,12 @@ int vmw_fallback_wait(struct vmw_private *dev_priv, } } finish_wait(&dev_priv->fence_queue, &__wait); - if (ret == 0 && fifo_idle) + if (ret == 0 && fifo_idle && fifo_state) vmw_fence_write(dev_priv, signal_seq); wake_up_all(&dev_priv->fence_queue); out_err: - if (fifo_idle) + if (fifo_down) up_read(&fifo_state->rwsem); return ret; @@ -266,13 +276,13 @@ void vmw_seqno_waiter_remove(struct vmw_private *dev_priv) void vmw_goal_waiter_add(struct vmw_private *dev_priv) { - vmw_generic_waiter_add(dev_priv, SVGA_IRQFLAG_FENCE_GOAL, + vmw_generic_waiter_add(dev_priv, vmw_irqflag_fence_goal(dev_priv), &dev_priv->goal_queue_waiters); } void vmw_goal_waiter_remove(struct vmw_private *dev_priv) { - vmw_generic_waiter_remove(dev_priv, SVGA_IRQFLAG_FENCE_GOAL, + vmw_generic_waiter_remove(dev_priv, vmw_irqflag_fence_goal(dev_priv), &dev_priv->goal_queue_waiters); } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c index bbd2f4ec08ec..93431e8f6606 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c @@ -1344,7 +1344,6 @@ vmw_kms_new_framebuffer(struct vmw_private *dev_priv, ret = vmw_kms_new_framebuffer_surface(dev_priv, surface, &vfb, mode_cmd, is_bo_proxy); - /* * vmw_create_bo_proxy() adds a reference that is no longer * needed @@ -1385,13 +1384,16 @@ static struct drm_framebuffer *vmw_kms_fb_create(struct drm_device *dev, ret = vmw_user_lookup_handle(dev_priv, file_priv, mode_cmd->handles[0], &surface, &bo); - if (ret) + if (ret) { + DRM_ERROR("Invalid buffer object handle %u (0x%x).\n", + mode_cmd->handles[0], mode_cmd->handles[0]); goto err_out; + } if (!bo && !vmw_kms_srf_ok(dev_priv, mode_cmd->width, mode_cmd->height)) { - DRM_ERROR("Surface size cannot exceed %dx%d", + DRM_ERROR("Surface size cannot exceed %dx%d\n", dev_priv->texture_max_width, dev_priv->texture_max_height); goto err_out; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c index 00e8e27e4884..ace7ca150b03 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c @@ -683,6 +683,9 @@ static void vmw_user_surface_base_release(struct ttm_base_object **p_base) container_of(base, struct vmw_user_surface, prime.base); struct vmw_resource *res = &user_srf->srf.res; + if (base->shareable && res && res->backup) + drm_gem_object_put(&res->backup->base.base); + *p_base = NULL; vmw_resource_unreference(&res); } @@ -857,6 +860,7 @@ int vmw_surface_define_ioctl(struct drm_device *dev, void *data, goto out_unlock; } vmw_bo_reference(res->backup); + drm_gem_object_get(&res->backup->base.base); } tmp = vmw_resource_reference(&srf->res); @@ -1513,7 +1517,6 @@ vmw_gb_surface_define_internal(struct drm_device *dev, &res->backup); if (ret == 0) vmw_bo_reference(res->backup); - } if (unlikely(ret != 0)) { @@ -1561,6 +1564,8 @@ vmw_gb_surface_define_internal(struct drm_device *dev, drm_vma_node_offset_addr(&res->backup->base.base.vma_node); rep->buffer_size = res->backup->base.base.size; rep->buffer_handle = backup_handle; + if (user_srf->prime.base.shareable) + drm_gem_object_get(&res->backup->base.base); } else { rep->buffer_map_handle = 0; rep->buffer_size = 0; diff --git a/drivers/gpu/drm/xen/xen_drm_front.h b/drivers/gpu/drm/xen/xen_drm_front.h index cefafe859aba..a987c78abe41 100644 --- a/drivers/gpu/drm/xen/xen_drm_front.h +++ b/drivers/gpu/drm/xen/xen_drm_front.h @@ -80,15 +80,6 @@ struct drm_pending_vblank_event; /* timeout in ms to wait for backend to respond */ #define XEN_DRM_FRONT_WAIT_BACK_MS 3000 -#ifndef GRANT_INVALID_REF -/* - * Note on usage of grant reference 0 as invalid grant reference: - * grant reference 0 is valid, but never exposed to a PV driver, - * because of the fact it is already in use/reserved by the PV console. - */ -#define GRANT_INVALID_REF 0 -#endif - struct xen_drm_front_info { struct xenbus_device *xb_dev; struct xen_drm_front_drm_info *drm_info; diff --git a/drivers/gpu/drm/xen/xen_drm_front_evtchnl.c b/drivers/gpu/drm/xen/xen_drm_front_evtchnl.c index 08b526eeec16..e52afd792346 100644 --- a/drivers/gpu/drm/xen/xen_drm_front_evtchnl.c +++ b/drivers/gpu/drm/xen/xen_drm_front_evtchnl.c @@ -123,12 +123,12 @@ out: static void evtchnl_free(struct xen_drm_front_info *front_info, struct xen_drm_front_evtchnl *evtchnl) { - unsigned long page = 0; + void *page = NULL; if (evtchnl->type == EVTCHNL_TYPE_REQ) - page = (unsigned long)evtchnl->u.req.ring.sring; + page = evtchnl->u.req.ring.sring; else if (evtchnl->type == EVTCHNL_TYPE_EVT) - page = (unsigned long)evtchnl->u.evt.page; + page = evtchnl->u.evt.page; if (!page) return; @@ -147,8 +147,7 @@ static void evtchnl_free(struct xen_drm_front_info *front_info, xenbus_free_evtchn(front_info->xb_dev, evtchnl->port); /* end access and free the page */ - if (evtchnl->gref != GRANT_INVALID_REF) - gnttab_end_foreign_access(evtchnl->gref, page); + xenbus_teardown_ring(&page, 1, &evtchnl->gref); memset(evtchnl, 0, sizeof(*evtchnl)); } @@ -158,8 +157,7 @@ static int evtchnl_alloc(struct xen_drm_front_info *front_info, int index, enum xen_drm_front_evtchnl_type type) { struct xenbus_device *xb_dev = front_info->xb_dev; - unsigned long page; - grant_ref_t gref; + void *page; irq_handler_t handler; int ret; @@ -168,44 +166,25 @@ static int evtchnl_alloc(struct xen_drm_front_info *front_info, int index, evtchnl->index = index; evtchnl->front_info = front_info; evtchnl->state = EVTCHNL_STATE_DISCONNECTED; - evtchnl->gref = GRANT_INVALID_REF; - page = get_zeroed_page(GFP_NOIO | __GFP_HIGH); - if (!page) { - ret = -ENOMEM; + ret = xenbus_setup_ring(xb_dev, GFP_NOIO | __GFP_HIGH, &page, + 1, &evtchnl->gref); + if (ret) goto fail; - } if (type == EVTCHNL_TYPE_REQ) { struct xen_displif_sring *sring; init_completion(&evtchnl->u.req.completion); mutex_init(&evtchnl->u.req.req_io_lock); - sring = (struct xen_displif_sring *)page; - SHARED_RING_INIT(sring); - FRONT_RING_INIT(&evtchnl->u.req.ring, sring, XEN_PAGE_SIZE); - - ret = xenbus_grant_ring(xb_dev, sring, 1, &gref); - if (ret < 0) { - evtchnl->u.req.ring.sring = NULL; - free_page(page); - goto fail; - } + sring = page; + XEN_FRONT_RING_INIT(&evtchnl->u.req.ring, sring, XEN_PAGE_SIZE); handler = evtchnl_interrupt_ctrl; } else { - ret = gnttab_grant_foreign_access(xb_dev->otherend_id, - virt_to_gfn((void *)page), 0); - if (ret < 0) { - free_page(page); - goto fail; - } - - evtchnl->u.evt.page = (struct xendispl_event_page *)page; - gref = ret; + evtchnl->u.evt.page = page; handler = evtchnl_interrupt_evt; } - evtchnl->gref = gref; ret = xenbus_alloc_evtchn(xb_dev, &evtchnl->port); if (ret < 0) diff --git a/drivers/gpu/ipu-v3/ipu-di.c b/drivers/gpu/ipu-v3/ipu-di.c index 666223c6bec4..0a34e0ab4fe6 100644 --- a/drivers/gpu/ipu-v3/ipu-di.c +++ b/drivers/gpu/ipu-v3/ipu-di.c @@ -447,8 +447,9 @@ static void ipu_di_config_clock(struct ipu_di *di, error = rate / (sig->mode.pixelclock / 1000); - dev_dbg(di->ipu->dev, " IPU clock can give %lu with divider %u, error %d.%u%%\n", - rate, div, (signed)(error - 1000) / 10, error % 10); + dev_dbg(di->ipu->dev, " IPU clock can give %lu with divider %u, error %c%d.%d%%\n", + rate, div, error < 1000 ? '-' : '+', + abs(error - 1000) / 10, abs(error - 1000) % 10); /* Allow a 1% error */ if (error < 1010 && error >= 990) { diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig index a95a7cbc4a59..70da5931082f 100644 --- a/drivers/hid/Kconfig +++ b/drivers/hid/Kconfig @@ -697,6 +697,14 @@ config HID_MAYFLASH Say Y here if you have HJZ Mayflash PS3 game controller adapters and want to enable force feedback support. +config HID_MEGAWORLD_FF + tristate "Mega World based game controller force feedback support" + depends on USB_HID + select INPUT_FF_MEMLESS + help + Say Y here if you have a Mega World based game controller and want + to have force feedback support for it. + config HID_REDRAGON tristate "Redragon keyboards" depends on HID diff --git a/drivers/hid/Makefile b/drivers/hid/Makefile index 345ac5581bd8..cac2cbe26d11 100644 --- a/drivers/hid/Makefile +++ b/drivers/hid/Makefile @@ -77,6 +77,7 @@ obj-$(CONFIG_HID_MAGICMOUSE) += hid-magicmouse.o obj-$(CONFIG_HID_MALTRON) += hid-maltron.o obj-$(CONFIG_HID_MCP2221) += hid-mcp2221.o obj-$(CONFIG_HID_MAYFLASH) += hid-mf.o +obj-$(CONFIG_HID_MEGAWORLD_FF) += hid-megaworld.o obj-$(CONFIG_HID_MICROSOFT) += hid-microsoft.o obj-$(CONFIG_HID_MONTEREY) += hid-monterey.o obj-$(CONFIG_HID_MULTITOUCH) += hid-multitouch.o diff --git a/drivers/hid/amd-sfh-hid/amd_sfh_client.c b/drivers/hid/amd-sfh-hid/amd_sfh_client.c index c5de0ec4f9d0..0f770a2b47ff 100644 --- a/drivers/hid/amd-sfh-hid/amd_sfh_client.c +++ b/drivers/hid/amd-sfh-hid/amd_sfh_client.c @@ -141,6 +141,24 @@ u32 amd_sfh_wait_for_response(struct amd_mp2_dev *mp2, u8 sid, u32 sensor_sts) return sensor_sts; } +const char *get_sensor_name(int idx) +{ + switch (idx) { + case accel_idx: + return "accelerometer"; + case gyro_idx: + return "gyroscope"; + case mag_idx: + return "magnetometer"; + case als_idx: + return "ALS"; + case HPD_IDX: + return "HPD"; + default: + return "unknown sensor type"; + } +} + int amd_sfh_hid_client_init(struct amd_mp2_dev *privdata) { struct amd_input_data *in_data = &privdata->in_data; @@ -219,13 +237,27 @@ int amd_sfh_hid_client_init(struct amd_mp2_dev *privdata) (privdata, cl_data->sensor_idx[i], SENSOR_DISABLED); if (status != SENSOR_ENABLED) cl_data->sensor_sts[i] = SENSOR_DISABLED; - dev_dbg(dev, "sid 0x%x status 0x%x\n", - cl_data->sensor_idx[i], cl_data->sensor_sts[i]); + dev_dbg(dev, "sid 0x%x (%s) status 0x%x\n", + cl_data->sensor_idx[i], + get_sensor_name(cl_data->sensor_idx[i]), + cl_data->sensor_sts[i]); goto cleanup; } } - dev_dbg(dev, "sid 0x%x status 0x%x\n", - cl_data->sensor_idx[i], cl_data->sensor_sts[i]); + dev_dbg(dev, "sid 0x%x (%s) status 0x%x\n", + cl_data->sensor_idx[i], get_sensor_name(cl_data->sensor_idx[i]), + cl_data->sensor_sts[i]); + } + if (privdata->mp2_ops->discovery_status && + privdata->mp2_ops->discovery_status(privdata) == 0) { + amd_sfh_hid_client_deinit(privdata); + for (i = 0; i < cl_data->num_hid_devices; i++) { + devm_kfree(dev, cl_data->feature_report[i]); + devm_kfree(dev, in_data->input_report[i]); + devm_kfree(dev, cl_data->report_descr[i]); + } + dev_warn(dev, "Failed to discover, sensors not enabled\n"); + return -EOPNOTSUPP; } schedule_delayed_work(&cl_data->work_buffer, msecs_to_jiffies(AMD_SFH_IDLE_LOOP)); return 0; @@ -257,8 +289,9 @@ int amd_sfh_hid_client_deinit(struct amd_mp2_dev *privdata) (privdata, cl_data->sensor_idx[i], SENSOR_DISABLED); if (status != SENSOR_ENABLED) cl_data->sensor_sts[i] = SENSOR_DISABLED; - dev_dbg(&privdata->pdev->dev, "stopping sid 0x%x status 0x%x\n", - cl_data->sensor_idx[i], cl_data->sensor_sts[i]); + dev_dbg(&privdata->pdev->dev, "stopping sid 0x%x (%s) status 0x%x\n", + cl_data->sensor_idx[i], get_sensor_name(cl_data->sensor_idx[i]), + cl_data->sensor_sts[i]); } } diff --git a/drivers/hid/amd-sfh-hid/amd_sfh_hid.c b/drivers/hid/amd-sfh-hid/amd_sfh_hid.c index 2bf97b6ac973..1089134030b0 100644 --- a/drivers/hid/amd-sfh-hid/amd_sfh_hid.c +++ b/drivers/hid/amd-sfh-hid/amd_sfh_hid.c @@ -12,6 +12,7 @@ #include <linux/sched.h> #include "amd_sfh_hid.h" +#include "amd_sfh_pcie.h" #define AMD_SFH_RESPONSE_TIMEOUT 1500 @@ -120,6 +121,8 @@ static struct hid_ll_driver amdtp_hid_ll_driver = { int amdtp_hid_probe(u32 cur_hid_dev, struct amdtp_cl_data *cli_data) { + struct amd_mp2_dev *mp2 = container_of(cli_data->in_data, struct amd_mp2_dev, in_data); + struct device *dev = &mp2->pdev->dev; struct hid_device *hid; struct amdtp_hid_data *hid_data; int rc; @@ -141,10 +144,12 @@ int amdtp_hid_probe(u32 cur_hid_dev, struct amdtp_cl_data *cli_data) hid->driver_data = hid_data; cli_data->hid_sensor_hubs[cur_hid_dev] = hid; - hid->bus = BUS_AMD_AMDTP; + strscpy(hid->phys, dev->driver ? dev->driver->name : dev_name(dev), + sizeof(hid->phys)); + hid->bus = BUS_AMD_SFH; hid->vendor = AMD_SFH_HID_VENDOR; hid->product = AMD_SFH_HID_PRODUCT; - snprintf(hid->name, sizeof(hid->name), "%s %04X:%04X", "hid-amdtp", + snprintf(hid->name, sizeof(hid->name), "%s %04X:%04X", "hid-amdsfh", hid->vendor, hid->product); rc = hid_add_device(hid); diff --git a/drivers/hid/amd-sfh-hid/amd_sfh_hid.h b/drivers/hid/amd-sfh-hid/amd_sfh_hid.h index c60abd38054c..ad264db63180 100644 --- a/drivers/hid/amd-sfh-hid/amd_sfh_hid.h +++ b/drivers/hid/amd-sfh-hid/amd_sfh_hid.h @@ -12,7 +12,6 @@ #define AMDSFH_HID_H #define MAX_HID_DEVICES 5 -#define BUS_AMD_AMDTP 0x20 #define AMD_SFH_HID_VENDOR 0x1022 #define AMD_SFH_HID_PRODUCT 0x0001 diff --git a/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c b/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c index 6b5fd90b0bd1..dadc491bbf6b 100644 --- a/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c +++ b/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c @@ -130,6 +130,12 @@ static int amd_sfh_irq_init_v2(struct amd_mp2_dev *privdata) return 0; } +static int amd_sfh_dis_sts_v2(struct amd_mp2_dev *privdata) +{ + return (readl(privdata->mmio + AMD_P2C_MSG(1)) & + SENSOR_DISCOVERY_STATUS_MASK) >> SENSOR_DISCOVERY_STATUS_SHIFT; +} + void amd_start_sensor(struct amd_mp2_dev *privdata, struct amd_mp2_sensor_info info) { union sfh_cmd_param cmd_param; @@ -245,6 +251,7 @@ static const struct amd_mp2_ops amd_sfh_ops_v2 = { .response = amd_sfh_wait_response_v2, .clear_intr = amd_sfh_clear_intr_v2, .init_intr = amd_sfh_irq_init_v2, + .discovery_status = amd_sfh_dis_sts_v2, }; static const struct amd_mp2_ops amd_sfh_ops = { @@ -346,8 +353,9 @@ static int __maybe_unused amd_mp2_pci_resume(struct device *dev) (mp2, cl_data->sensor_idx[i], SENSOR_ENABLED); if (status == SENSOR_ENABLED) cl_data->sensor_sts[i] = SENSOR_ENABLED; - dev_dbg(dev, "resume sid 0x%x status 0x%x\n", - cl_data->sensor_idx[i], cl_data->sensor_sts[i]); + dev_dbg(dev, "suspend sid 0x%x (%s) status 0x%x\n", + cl_data->sensor_idx[i], get_sensor_name(cl_data->sensor_idx[i]), + cl_data->sensor_sts[i]); } } @@ -371,8 +379,9 @@ static int __maybe_unused amd_mp2_pci_suspend(struct device *dev) (mp2, cl_data->sensor_idx[i], SENSOR_DISABLED); if (status != SENSOR_ENABLED) cl_data->sensor_sts[i] = SENSOR_DISABLED; - dev_dbg(dev, "suspend sid 0x%x status 0x%x\n", - cl_data->sensor_idx[i], cl_data->sensor_sts[i]); + dev_dbg(dev, "suspend sid 0x%x (%s) status 0x%x\n", + cl_data->sensor_idx[i], get_sensor_name(cl_data->sensor_idx[i]), + cl_data->sensor_sts[i]); } } diff --git a/drivers/hid/amd-sfh-hid/amd_sfh_pcie.h b/drivers/hid/amd-sfh-hid/amd_sfh_pcie.h index 97b99861fae2..8c760526132a 100644 --- a/drivers/hid/amd-sfh-hid/amd_sfh_pcie.h +++ b/drivers/hid/amd-sfh-hid/amd_sfh_pcie.h @@ -39,6 +39,9 @@ #define AMD_SFH_IDLE_LOOP 200 +#define SENSOR_DISCOVERY_STATUS_MASK GENMASK(5, 3) +#define SENSOR_DISCOVERY_STATUS_SHIFT 3 + /* SFH Command register */ union sfh_cmd_base { u32 ul; @@ -135,6 +138,7 @@ int amd_sfh_hid_client_deinit(struct amd_mp2_dev *privdata); u32 amd_sfh_wait_for_response(struct amd_mp2_dev *mp2, u8 sid, u32 sensor_sts); void amd_mp2_suspend(struct amd_mp2_dev *mp2); void amd_mp2_resume(struct amd_mp2_dev *mp2); +const char *get_sensor_name(int idx); struct amd_mp2_ops { void (*start)(struct amd_mp2_dev *privdata, struct amd_mp2_sensor_info info); @@ -143,5 +147,6 @@ struct amd_mp2_ops { int (*response)(struct amd_mp2_dev *mp2, u8 sid, u32 sensor_sts); void (*clear_intr)(struct amd_mp2_dev *privdata); int (*init_intr)(struct amd_mp2_dev *privdata); + int (*discovery_status)(struct amd_mp2_dev *privdata); }; #endif diff --git a/drivers/hid/amd-sfh-hid/hid_descriptor/amd_sfh_hid_report_desc.h b/drivers/hid/amd-sfh-hid/hid_descriptor/amd_sfh_hid_report_desc.h index 8d97ca0f9b52..697f2791ea9c 100644 --- a/drivers/hid/amd-sfh-hid/hid_descriptor/amd_sfh_hid_report_desc.h +++ b/drivers/hid/amd-sfh-hid/hid_descriptor/amd_sfh_hid_report_desc.h @@ -179,7 +179,7 @@ static const u8 accel3_report_descriptor[] = { 0xC0 /* HID end collection */ }; -const u8 gyro3_report_descriptor[] = { +static const u8 gyro3_report_descriptor[] = { 0x05, 0x20, /* Usage page */ 0x09, 0x76, /* Motion type Gyro3D */ 0xA1, 0x00, /* HID Collection (Physical) */ @@ -340,7 +340,7 @@ const u8 gyro3_report_descriptor[] = { 0xC0, /* HID end collection */ }; -const u8 comp3_report_descriptor[] = { +static const u8 comp3_report_descriptor[] = { 0x05, 0x20, /* Usage page */ 0x09, 0x83, /* Motion type Orientation compass 3D */ 0xA1, 0x00, /* HID Collection (Physical) */ @@ -512,7 +512,7 @@ const u8 comp3_report_descriptor[] = { 0xC0 /* HID end collection */ }; -const u8 als_report_descriptor[] = { +static const u8 als_report_descriptor[] = { 0x05, 0x20, /* HID usage page sensor */ 0x09, 0x41, /* HID usage sensor type Ambientlight */ 0xA1, 0x00, /* HID Collection (Physical) */ diff --git a/drivers/hid/hid-apple.c b/drivers/hid/hid-apple.c index 0cf35caee9fa..42a568902f49 100644 --- a/drivers/hid/hid-apple.c +++ b/drivers/hid/hid-apple.c @@ -21,6 +21,7 @@ #include <linux/module.h> #include <linux/slab.h> #include <linux/timer.h> +#include <linux/string.h> #include "hid-ids.h" @@ -35,16 +36,17 @@ #define APPLE_NUMLOCK_EMULATION BIT(8) #define APPLE_RDESC_BATTERY BIT(9) #define APPLE_BACKLIGHT_CTL BIT(10) +#define APPLE_IS_KEYCHRON BIT(11) #define APPLE_FLAG_FKEY 0x01 #define HID_COUNTRY_INTERNATIONAL_ISO 13 #define APPLE_BATTERY_TIMEOUT_MS 60000 -static unsigned int fnmode = 1; +static unsigned int fnmode = 3; module_param(fnmode, uint, 0644); MODULE_PARM_DESC(fnmode, "Mode of fn key on Apple keyboards (0 = disabled, " - "[1] = fkeyslast, 2 = fkeysfirst)"); + "1 = fkeyslast, 2 = fkeysfirst, [3] = auto)"); static int iso_layout = -1; module_param(iso_layout, int, 0644); @@ -349,6 +351,7 @@ static int hidinput_apple_event(struct hid_device *hid, struct input_dev *input, const struct apple_key_translation *trans, *table; bool do_translate; u16 code = 0; + unsigned int real_fnmode; u16 fn_keycode = (swap_fn_leftctrl) ? (KEY_LEFTCTRL) : (KEY_FN); @@ -359,7 +362,13 @@ static int hidinput_apple_event(struct hid_device *hid, struct input_dev *input, return 1; } - if (fnmode) { + if (fnmode == 3) { + real_fnmode = (asc->quirks & APPLE_IS_KEYCHRON) ? 2 : 1; + } else { + real_fnmode = fnmode; + } + + if (real_fnmode) { if (hid->product == USB_DEVICE_ID_APPLE_ALU_WIRELESS_ANSI || hid->product == USB_DEVICE_ID_APPLE_ALU_WIRELESS_ISO || hid->product == USB_DEVICE_ID_APPLE_ALU_WIRELESS_JIS || @@ -406,7 +415,7 @@ static int hidinput_apple_event(struct hid_device *hid, struct input_dev *input, if (!code) { if (trans->flags & APPLE_FLAG_FKEY) { - switch (fnmode) { + switch (real_fnmode) { case 1: do_translate = !asc->fn_on; break; @@ -660,6 +669,11 @@ static int apple_input_configured(struct hid_device *hdev, asc->quirks &= ~APPLE_HAS_FN; } + if (strncmp(hdev->name, "Keychron", 8) == 0) { + hid_info(hdev, "Keychron keyboard detected; function keys will default to fnmode=2 behavior\n"); + asc->quirks |= APPLE_IS_KEYCHRON; + } + return 0; } diff --git a/drivers/hid/hid-bigbenff.c b/drivers/hid/hid-bigbenff.c index 74ad8bf98bfd..e8c5e3ac9fff 100644 --- a/drivers/hid/hid-bigbenff.c +++ b/drivers/hid/hid-bigbenff.c @@ -347,6 +347,12 @@ static int bigben_probe(struct hid_device *hid, bigben->report = list_entry(report_list->next, struct hid_report, list); + if (list_empty(&hid->inputs)) { + hid_err(hid, "no inputs found\n"); + error = -ENODEV; + goto error_hw_stop; + } + hidinput = list_first_entry(&hid->inputs, struct hid_input, list); set_bit(FF_RUMBLE, hidinput->input->ffbit); diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index db925794fbe6..00154a1cd2d8 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -2222,6 +2222,10 @@ int hid_connect(struct hid_device *hdev, unsigned int connect_mask) case BUS_VIRTUAL: bus = "VIRTUAL"; break; + case BUS_INTEL_ISHTP: + case BUS_AMD_SFH: + bus = "SENSOR HUB"; + break; default: bus = "<UNKNOWN>"; } diff --git a/drivers/hid/hid-elan.c b/drivers/hid/hid-elan.c index 3091355d48df..8e4a5528e25d 100644 --- a/drivers/hid/hid-elan.c +++ b/drivers/hid/hid-elan.c @@ -188,7 +188,6 @@ static int elan_input_configured(struct hid_device *hdev, struct hid_input *hi) ret = input_mt_init_slots(input, ELAN_MAX_FINGERS, INPUT_MT_POINTER); if (ret) { hid_err(hdev, "Failed to init elan MT slots: %d\n", ret); - input_free_device(input); return ret; } @@ -200,7 +199,6 @@ static int elan_input_configured(struct hid_device *hdev, struct hid_input *hi) hid_err(hdev, "Failed to register elan input device: %d\n", ret); input_mt_destroy_slots(input); - input_free_device(input); return ret; } diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 053853a891c5..d9eb676abe96 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -761,13 +761,16 @@ #define USB_VENDOR_ID_LENOVO 0x17ef #define USB_DEVICE_ID_LENOVO_TPKBD 0x6009 #define USB_DEVICE_ID_LENOVO_CUSBKBD 0x6047 +#define USB_DEVICE_ID_LENOVO_TPIIUSBKBD 0x60ee #define USB_DEVICE_ID_LENOVO_CBTKBD 0x6048 +#define USB_DEVICE_ID_LENOVO_TPIIBTKBD 0x60e1 #define USB_DEVICE_ID_LENOVO_SCROLLPOINT_OPTICAL 0x6049 #define USB_DEVICE_ID_LENOVO_TP10UBKBD 0x6062 #define USB_DEVICE_ID_LENOVO_TPPRODOCK 0x6067 #define USB_DEVICE_ID_LENOVO_X1_COVER 0x6085 #define USB_DEVICE_ID_LENOVO_X1_TAB 0x60a3 #define USB_DEVICE_ID_LENOVO_X1_TAB3 0x60b5 +#define USB_DEVICE_ID_LENOVO_X12_TAB 0x60fe #define USB_DEVICE_ID_LENOVO_OPTICAL_USB_MOUSE_600E 0x600e #define USB_DEVICE_ID_LENOVO_PIXART_USB_MOUSE_608D 0x608d #define USB_DEVICE_ID_LENOVO_PIXART_USB_MOUSE_6019 0x6019 @@ -868,6 +871,9 @@ #define USB_VENDOR_ID_MCS 0x16d0 #define USB_DEVICE_ID_MCS_GAMEPADBLOCK 0x0bcc +#define USB_VENDOR_MEGAWORLD 0x07b5 +#define USB_DEVICE_ID_MEGAWORLD_GAMEPAD 0x0312 + #define USB_VENDOR_ID_MGE 0x0463 #define USB_DEVICE_ID_MGE_UPS 0xffff #define USB_DEVICE_ID_MGE_UPS1 0x0001 @@ -1272,6 +1278,7 @@ #define USB_DEVICE_ID_UGEE_XPPEN_TABLET_G540 0x0075 #define USB_DEVICE_ID_UGEE_XPPEN_TABLET_G640 0x0094 #define USB_DEVICE_ID_UGEE_XPPEN_TABLET_DECO01 0x0042 +#define USB_DEVICE_ID_UGEE_XPPEN_TABLET_STAR06 0x0078 #define USB_DEVICE_ID_UGEE_TABLET_G5 0x0074 #define USB_DEVICE_ID_UGEE_TABLET_EX07S 0x0071 #define USB_DEVICE_ID_UGEE_TABLET_RAINBOW_CV720 0x0055 diff --git a/drivers/hid/hid-kye.c b/drivers/hid/hid-kye.c index f46616390a98..da903138eee4 100644 --- a/drivers/hid/hid-kye.c +++ b/drivers/hid/hid-kye.c @@ -33,7 +33,7 @@ static __u8 easypen_i405x_rdesc_fixed[] = { 0xB1, 0x02, /* Feature (Variable), */ 0xC0, /* End Collection, */ 0x05, 0x0D, /* Usage Page (Digitizer), */ - 0x09, 0x02, /* Usage (Pen), */ + 0x09, 0x01, /* Usage (Digitizer), */ 0xA1, 0x01, /* Collection (Application), */ 0x85, 0x10, /* Report ID (16), */ 0x09, 0x20, /* Usage (Stylus), */ @@ -91,7 +91,7 @@ static __u8 mousepen_i608x_rdesc_fixed[] = { 0xB1, 0x02, /* Feature (Variable), */ 0xC0, /* End Collection, */ 0x05, 0x0D, /* Usage Page (Digitizer), */ - 0x09, 0x02, /* Usage (Pen), */ + 0x09, 0x01, /* Usage (Digitizer), */ 0xA1, 0x01, /* Collection (Application), */ 0x85, 0x10, /* Report ID (16), */ 0x09, 0x20, /* Usage (Stylus), */ @@ -190,7 +190,7 @@ static __u8 mousepen_i608x_v2_rdesc_fixed[] = { 0xB1, 0x02, /* Feature (Variable), */ 0xC0, /* End Collection, */ 0x05, 0x0D, /* Usage Page (Digitizer), */ - 0x09, 0x02, /* Usage (Pen), */ + 0x09, 0x01, /* Usage (Digitizer), */ 0xA1, 0x01, /* Collection (Application), */ 0x85, 0x10, /* Report ID (16), */ 0x09, 0x20, /* Usage (Stylus), */ @@ -289,7 +289,7 @@ static __u8 easypen_m610x_rdesc_fixed[] = { 0xB1, 0x02, /* Feature (Variable), */ 0xC0, /* End Collection, */ 0x05, 0x0D, /* Usage Page (Digitizer), */ - 0x09, 0x02, /* Usage (Pen), */ + 0x09, 0x01, /* Usage (Digitizer), */ 0xA1, 0x01, /* Collection (Application), */ 0x85, 0x10, /* Report ID (16), */ 0x09, 0x20, /* Usage (Stylus), */ @@ -368,7 +368,7 @@ static __u8 pensketch_m912_rdesc_fixed[] = { 0xB1, 0x02, /* Feature (Variable), */ 0xC0, /* End Collection, */ 0x05, 0x0D, /* Usage Page (Digitizer), */ - 0x09, 0x02, /* Usage (Pen), */ + 0x09, 0x01, /* Usage (Digitizer), */ 0xA1, 0x01, /* Collection (Application), */ 0x85, 0x10, /* Report ID (16), */ 0x09, 0x20, /* Usage (Stylus), */ @@ -497,7 +497,7 @@ static __u8 easypen_m406xe_rdesc_fixed[] = { 0xB1, 0x02, /* Feature (Variable), */ 0xC0, /* End Collection, */ 0x05, 0x0D, /* Usage Page (Digitizer), */ - 0x09, 0x02, /* Usage (Pen), */ + 0x09, 0x01, /* Usage (Digitizer), */ 0xA1, 0x01, /* Collection (Application), */ 0x85, 0x10, /* Report ID (16), */ 0x09, 0x20, /* Usage (Stylus), */ diff --git a/drivers/hid/hid-led.c b/drivers/hid/hid-led.c index c2c66ceca132..7d82f8d426bb 100644 --- a/drivers/hid/hid-led.c +++ b/drivers/hid/hid-led.c @@ -366,7 +366,7 @@ static const struct hidled_config hidled_configs[] = { .type = DREAM_CHEEKY, .name = "Dream Cheeky Webmail Notifier", .short_name = "dream_cheeky", - .max_brightness = 31, + .max_brightness = 63, .num_leds = 1, .report_size = 9, .report_type = RAW_REQUEST, diff --git a/drivers/hid/hid-lenovo.c b/drivers/hid/hid-lenovo.c index 93b1f935e526..9dabd6323234 100644 --- a/drivers/hid/hid-lenovo.c +++ b/drivers/hid/hid-lenovo.c @@ -4,6 +4,7 @@ * - ThinkPad USB Keyboard with TrackPoint (tpkbd) * - ThinkPad Compact Bluetooth Keyboard with TrackPoint (cptkbd) * - ThinkPad Compact USB Keyboard with TrackPoint (cptkbd) + * - ThinkPad TrackPoint Keyboard II USB/Bluetooth (cptkbd/tpIIkbd) * * Copyright (c) 2012 Bernhard Seibold * Copyright (c) 2014 Jamie Lentin <jm@lentin.co.uk> @@ -110,6 +111,23 @@ static const __u8 lenovo_pro_dock_need_fixup_collection[] = { 0x2a, 0xff, 0xff, /* Usage Maximum (65535) */ }; +/* Broken ThinkPad TrackPoint II collection (Bluetooth mode) */ +static const __u8 lenovo_tpIIbtkbd_need_fixup_collection[] = { + 0x06, 0x00, 0xFF, /* Usage Page (Vendor Defined 0xFF00) */ + 0x09, 0x01, /* Usage (0x01) */ + 0xA1, 0x01, /* Collection (Application) */ + 0x85, 0x05, /* Report ID (5) */ + 0x1A, 0xF1, 0x00, /* Usage Minimum (0xF1) */ + 0x2A, 0xFC, 0x00, /* Usage Maximum (0xFC) */ + 0x15, 0x00, /* Logical Minimum (0) */ + 0x25, 0x01, /* Logical Maximum (1) */ + 0x75, 0x01, /* Report Size (1) */ + 0x95, 0x0D, /* Report Count (13) */ + 0x81, 0x02, /* Input (Data,Var,Abs,No Wrap,Linear,Preferred State,No Null Position) */ + 0x95, 0x03, /* Report Count (3) */ + 0x81, 0x01, /* Input (Const,Array,Abs,No Wrap,Linear,Preferred State,No Null Position) */ +}; + static __u8 *lenovo_report_fixup(struct hid_device *hdev, __u8 *rdesc, unsigned int *rsize) { @@ -126,6 +144,19 @@ static __u8 *lenovo_report_fixup(struct hid_device *hdev, __u8 *rdesc, rdesc[152] = 0x00; } break; + case USB_DEVICE_ID_LENOVO_TPIIBTKBD: + if (*rsize >= 263 && + memcmp(&rdesc[234], lenovo_tpIIbtkbd_need_fixup_collection, + sizeof(lenovo_tpIIbtkbd_need_fixup_collection)) == 0) { + rdesc[244] = 0x00; /* usage minimum = 0x00 */ + rdesc[247] = 0xff; /* usage maximum = 0xff */ + rdesc[252] = 0xff; /* logical maximum = 0xff */ + rdesc[254] = 0x08; /* report size = 0x08 */ + rdesc[256] = 0x01; /* report count = 0x01 */ + rdesc[258] = 0x00; /* input = 0x00 */ + rdesc[260] = 0x01; /* report count (2) = 0x01 */ + } + break; } return rdesc; } @@ -217,6 +248,101 @@ static int lenovo_input_mapping_cptkbd(struct hid_device *hdev, return 0; } +static int lenovo_input_mapping_tpIIkbd(struct hid_device *hdev, + struct hid_input *hi, struct hid_field *field, + struct hid_usage *usage, unsigned long **bit, int *max) +{ + /* + * 0xff0a0000 = USB, HID_UP_MSVENDOR = BT. + * + * In BT mode, there are two HID_UP_MSVENDOR pages. + * Use only the page that contains report ID == 5. + */ + if (((usage->hid & HID_USAGE_PAGE) == 0xff0a0000 || + (usage->hid & HID_USAGE_PAGE) == HID_UP_MSVENDOR) && + field->report->id == 5) { + switch (usage->hid & HID_USAGE) { + case 0x00bb: /* Fn-F4: Mic mute */ + map_key_clear(LENOVO_KEY_MICMUTE); + return 1; + case 0x00c3: /* Fn-F5: Brightness down */ + map_key_clear(KEY_BRIGHTNESSDOWN); + return 1; + case 0x00c4: /* Fn-F6: Brightness up */ + map_key_clear(KEY_BRIGHTNESSUP); + return 1; + case 0x00c1: /* Fn-F8: Notification center */ + map_key_clear(KEY_NOTIFICATION_CENTER); + return 1; + case 0x00bc: /* Fn-F9: Control panel */ + map_key_clear(KEY_CONFIG); + return 1; + case 0x00b6: /* Fn-F10: Bluetooth */ + map_key_clear(KEY_BLUETOOTH); + return 1; + case 0x00b7: /* Fn-F11: Keyboard config */ + map_key_clear(KEY_KEYBOARD); + return 1; + case 0x00b8: /* Fn-F12: User function */ + map_key_clear(KEY_PROG1); + return 1; + case 0x00b9: /* Fn-PrtSc: Snipping tool */ + map_key_clear(KEY_SELECTIVE_SCREENSHOT); + return 1; + case 0x00b5: /* Fn-Esc: Fn-lock toggle */ + map_key_clear(KEY_FN_ESC); + return 1; + } + } + + if ((usage->hid & HID_USAGE_PAGE) == 0xffa00000) { + switch (usage->hid & HID_USAGE) { + case 0x00fb: /* Middle mouse (in native USB mode) */ + map_key_clear(BTN_MIDDLE); + return 1; + } + } + + if ((usage->hid & HID_USAGE_PAGE) == HID_UP_MSVENDOR && + field->report->id == 21) { + switch (usage->hid & HID_USAGE) { + case 0x0004: /* Middle mouse (in native Bluetooth mode) */ + map_key_clear(BTN_MIDDLE); + return 1; + } + } + + /* Compatibility middle/wheel mappings should be ignored */ + if (usage->hid == HID_GD_WHEEL) + return -1; + if ((usage->hid & HID_USAGE_PAGE) == HID_UP_BUTTON && + (usage->hid & HID_USAGE) == 0x003) + return -1; + if ((usage->hid & HID_USAGE_PAGE) == HID_UP_CONSUMER && + (usage->hid & HID_USAGE) == 0x238) + return -1; + + /* Map wheel emulation reports: 0xff10 */ + if ((usage->hid & HID_USAGE_PAGE) == 0xff100000) { + field->flags |= HID_MAIN_ITEM_RELATIVE | HID_MAIN_ITEM_VARIABLE; + field->logical_minimum = -127; + field->logical_maximum = 127; + + switch (usage->hid & HID_USAGE) { + case 0x0000: + hid_map_usage(hi, usage, bit, max, EV_REL, REL_HWHEEL); + return 1; + case 0x0001: + hid_map_usage(hi, usage, bit, max, EV_REL, REL_WHEEL); + return 1; + default: + return -1; + } + } + + return 0; +} + static int lenovo_input_mapping_scrollpoint(struct hid_device *hdev, struct hid_input *hi, struct hid_field *field, struct hid_usage *usage, unsigned long **bit, int *max) @@ -326,6 +452,10 @@ static int lenovo_input_mapping(struct hid_device *hdev, case USB_DEVICE_ID_LENOVO_CBTKBD: return lenovo_input_mapping_cptkbd(hdev, hi, field, usage, bit, max); + case USB_DEVICE_ID_LENOVO_TPIIUSBKBD: + case USB_DEVICE_ID_LENOVO_TPIIBTKBD: + return lenovo_input_mapping_tpIIkbd(hdev, hi, field, + usage, bit, max); case USB_DEVICE_ID_IBM_SCROLLPOINT_III: case USB_DEVICE_ID_IBM_SCROLLPOINT_PRO: case USB_DEVICE_ID_IBM_SCROLLPOINT_OPTICAL: @@ -357,16 +487,23 @@ static int lenovo_send_cmd_cptkbd(struct hid_device *hdev, if (!buf) return -ENOMEM; + /* + * Feature report 0x13 is used for USB, + * output report 0x18 is used for Bluetooth. + * buf[0] is ignored by hid_hw_raw_request. + */ buf[0] = 0x18; buf[1] = byte2; buf[2] = byte3; switch (hdev->product) { case USB_DEVICE_ID_LENOVO_CUSBKBD: + case USB_DEVICE_ID_LENOVO_TPIIUSBKBD: ret = hid_hw_raw_request(hdev, 0x13, buf, 3, HID_FEATURE_REPORT, HID_REQ_SET_REPORT); break; case USB_DEVICE_ID_LENOVO_CBTKBD: + case USB_DEVICE_ID_LENOVO_TPIIBTKBD: ret = hid_hw_output_report(hdev, buf, 3); break; default: @@ -422,6 +559,8 @@ static ssize_t attr_fn_lock_store(struct device *dev, switch (hdev->product) { case USB_DEVICE_ID_LENOVO_CUSBKBD: case USB_DEVICE_ID_LENOVO_CBTKBD: + case USB_DEVICE_ID_LENOVO_TPIIUSBKBD: + case USB_DEVICE_ID_LENOVO_TPIIBTKBD: lenovo_features_set_cptkbd(hdev); break; case USB_DEVICE_ID_LENOVO_TP10UBKBD: @@ -556,6 +695,15 @@ static int lenovo_event_cptkbd(struct hid_device *hdev, return 1; } + if (usage->type == EV_KEY && usage->code == KEY_FN_ESC && value == 1) { + /* + * The user has toggled the Fn-lock state. Toggle our own + * cached value of it and sync our value to the keyboard to + * ensure things are in sync (the syncing should be a no-op). + */ + cptkbd_data->fn_lock = !cptkbd_data->fn_lock; + } + return 0; } @@ -568,6 +716,8 @@ static int lenovo_event(struct hid_device *hdev, struct hid_field *field, switch (hdev->product) { case USB_DEVICE_ID_LENOVO_CUSBKBD: case USB_DEVICE_ID_LENOVO_CBTKBD: + case USB_DEVICE_ID_LENOVO_TPIIUSBKBD: + case USB_DEVICE_ID_LENOVO_TPIIBTKBD: return lenovo_event_cptkbd(hdev, field, usage, value); case USB_DEVICE_ID_LENOVO_TP10UBKBD: case USB_DEVICE_ID_LENOVO_X1_TAB: @@ -960,8 +1110,9 @@ static int lenovo_probe_cptkbd(struct hid_device *hdev) struct lenovo_drvdata *cptkbd_data; /* All the custom action happens on the USBMOUSE device for USB */ - if (hdev->product == USB_DEVICE_ID_LENOVO_CUSBKBD - && hdev->type != HID_TYPE_USBMOUSE) { + if (((hdev->product == USB_DEVICE_ID_LENOVO_CUSBKBD) || + (hdev->product == USB_DEVICE_ID_LENOVO_TPIIUSBKBD)) && + hdev->type != HID_TYPE_USBMOUSE) { hid_dbg(hdev, "Ignoring keyboard half of device\n"); return 0; } @@ -977,11 +1128,14 @@ static int lenovo_probe_cptkbd(struct hid_device *hdev) /* * Tell the keyboard a driver understands it, and turn F7, F9, F11 into - * regular keys + * regular keys (Compact only) */ - ret = lenovo_send_cmd_cptkbd(hdev, 0x01, 0x03); - if (ret) - hid_warn(hdev, "Failed to switch F7/9/11 mode: %d\n", ret); + if (hdev->product == USB_DEVICE_ID_LENOVO_CUSBKBD || + hdev->product == USB_DEVICE_ID_LENOVO_CBTKBD) { + ret = lenovo_send_cmd_cptkbd(hdev, 0x01, 0x03); + if (ret) + hid_warn(hdev, "Failed to switch F7/9/11 mode: %d\n", ret); + } /* Switch middle button to native mode */ ret = lenovo_send_cmd_cptkbd(hdev, 0x09, 0x01); @@ -1088,6 +1242,8 @@ static int lenovo_probe(struct hid_device *hdev, break; case USB_DEVICE_ID_LENOVO_CUSBKBD: case USB_DEVICE_ID_LENOVO_CBTKBD: + case USB_DEVICE_ID_LENOVO_TPIIUSBKBD: + case USB_DEVICE_ID_LENOVO_TPIIBTKBD: ret = lenovo_probe_cptkbd(hdev); break; case USB_DEVICE_ID_LENOVO_TP10UBKBD: @@ -1154,6 +1310,8 @@ static void lenovo_remove(struct hid_device *hdev) break; case USB_DEVICE_ID_LENOVO_CUSBKBD: case USB_DEVICE_ID_LENOVO_CBTKBD: + case USB_DEVICE_ID_LENOVO_TPIIUSBKBD: + case USB_DEVICE_ID_LENOVO_TPIIBTKBD: lenovo_remove_cptkbd(hdev); break; case USB_DEVICE_ID_LENOVO_TP10UBKBD: @@ -1172,6 +1330,8 @@ static int lenovo_input_configured(struct hid_device *hdev, case USB_DEVICE_ID_LENOVO_TPKBD: case USB_DEVICE_ID_LENOVO_CUSBKBD: case USB_DEVICE_ID_LENOVO_CBTKBD: + case USB_DEVICE_ID_LENOVO_TPIIUSBKBD: + case USB_DEVICE_ID_LENOVO_TPIIBTKBD: if (test_bit(EV_REL, hi->input->evbit)) { /* set only for trackpoint device */ __set_bit(INPUT_PROP_POINTER, hi->input->propbit); @@ -1188,7 +1348,9 @@ static int lenovo_input_configured(struct hid_device *hdev, static const struct hid_device_id lenovo_devices[] = { { HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_TPKBD) }, { HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_CUSBKBD) }, + { HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_TPIIUSBKBD) }, { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_CBTKBD) }, + { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_TPIIBTKBD) }, { HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_TPPRODOCK) }, { HID_USB_DEVICE(USB_VENDOR_ID_IBM, USB_DEVICE_ID_IBM_SCROLLPOINT_III) }, { HID_USB_DEVICE(USB_VENDOR_ID_IBM, USB_DEVICE_ID_IBM_SCROLLPOINT_PRO) }, diff --git a/drivers/hid/hid-megaworld.c b/drivers/hid/hid-megaworld.c new file mode 100644 index 000000000000..599657863cb9 --- /dev/null +++ b/drivers/hid/hid-megaworld.c @@ -0,0 +1,125 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Vibration support for Mega World controllers + * + * Copyright 2022 Frank Zago + * + * Derived from hid-zpff.c: + * Copyright (c) 2005, 2006 Anssi Hannula <anssi.hannula@gmail.com> + */ + +#include <linux/hid.h> +#include <linux/input.h> +#include <linux/module.h> +#include <linux/slab.h> + +#include "hid-ids.h" + +struct mwctrl_device { + struct hid_report *report; + s32 *weak; + s32 *strong; +}; + +static int mwctrl_play(struct input_dev *dev, void *data, + struct ff_effect *effect) +{ + struct hid_device *hid = input_get_drvdata(dev); + struct mwctrl_device *mwctrl = data; + + *mwctrl->strong = effect->u.rumble.strong_magnitude >> 8; + *mwctrl->weak = effect->u.rumble.weak_magnitude >> 8; + + hid_hw_request(hid, mwctrl->report, HID_REQ_SET_REPORT); + + return 0; +} + +static int mwctrl_init(struct hid_device *hid) +{ + struct mwctrl_device *mwctrl; + struct hid_report *report; + struct hid_input *hidinput; + struct input_dev *dev; + int error; + int i; + + if (list_empty(&hid->inputs)) { + hid_err(hid, "no inputs found\n"); + return -ENODEV; + } + hidinput = list_entry(hid->inputs.next, struct hid_input, list); + dev = hidinput->input; + + for (i = 0; i < 4; i++) { + report = hid_validate_values(hid, HID_OUTPUT_REPORT, 0, i, 1); + if (!report) + return -ENODEV; + } + + mwctrl = kzalloc(sizeof(struct mwctrl_device), GFP_KERNEL); + if (!mwctrl) + return -ENOMEM; + + set_bit(FF_RUMBLE, dev->ffbit); + + error = input_ff_create_memless(dev, mwctrl, mwctrl_play); + if (error) { + kfree(mwctrl); + return error; + } + + mwctrl->report = report; + + /* Field 0 is always 2, and field 1 is always 0. The original + * windows driver has a 5 bytes command, where the 5th byte is + * a repeat of the 3rd byte, however the device has only 4 + * fields. It could be a bug in the driver, or there is a + * different device that needs it. + */ + report->field[0]->value[0] = 0x02; + + mwctrl->strong = &report->field[2]->value[0]; + mwctrl->weak = &report->field[3]->value[0]; + + return 0; +} + +static int mwctrl_probe(struct hid_device *hdev, const struct hid_device_id *id) +{ + int ret; + + ret = hid_parse(hdev); + if (ret) { + hid_err(hdev, "parse failed\n"); + return ret; + } + + ret = hid_hw_start(hdev, HID_CONNECT_DEFAULT & ~HID_CONNECT_FF); + if (ret) { + hid_err(hdev, "hw start failed\n"); + return ret; + } + + ret = mwctrl_init(hdev); + if (ret) + hid_hw_stop(hdev); + + return ret; +} + +static const struct hid_device_id mwctrl_devices[] = { + { HID_USB_DEVICE(USB_VENDOR_MEGAWORLD, + USB_DEVICE_ID_MEGAWORLD_GAMEPAD) }, + { } +}; +MODULE_DEVICE_TABLE(hid, mwctrl_devices); + +static struct hid_driver mwctrl_driver = { + .name = "megaworld", + .id_table = mwctrl_devices, + .probe = mwctrl_probe, +}; +module_hid_driver(mwctrl_driver); + +MODULE_LICENSE("GPL"); diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c index 99eabfb4145b..6bb3890b0f2c 100644 --- a/drivers/hid/hid-multitouch.c +++ b/drivers/hid/hid-multitouch.c @@ -2034,6 +2034,12 @@ static const struct hid_device_id mt_devices[] = { USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_X1_TAB3) }, + /* Lenovo X12 TAB Gen 1 */ + { .driver_data = MT_CLS_WIN_8_FORCE_MULTI_INPUT, + HID_DEVICE(BUS_USB, HID_GROUP_MULTITOUCH_WIN_8, + USB_VENDOR_ID_LENOVO, + USB_DEVICE_ID_LENOVO_X12_TAB) }, + /* MosArt panels */ { .driver_data = MT_CLS_CONFIDENCE_MINUS_ONE, MT_USB_DEVICE(USB_VENDOR_ID_ASUS, @@ -2178,6 +2184,9 @@ static const struct hid_device_id mt_devices[] = { { .driver_data = MT_CLS_GOOGLE, HID_DEVICE(HID_BUS_ANY, HID_GROUP_ANY, USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_TOUCH_ROSE) }, + { .driver_data = MT_CLS_GOOGLE, + HID_DEVICE(BUS_USB, HID_GROUP_MULTITOUCH_WIN_8, USB_VENDOR_ID_GOOGLE, + USB_DEVICE_ID_GOOGLE_WHISKERS) }, /* Generic MT device */ { HID_DEVICE(HID_BUS_ANY, HID_GROUP_MULTITOUCH, HID_ANY_ID, HID_ANY_ID) }, diff --git a/drivers/hid/hid-uclogic-core.c b/drivers/hid/hid-uclogic-core.c index 05147f2d7564..c0fe66e50c58 100644 --- a/drivers/hid/hid-uclogic-core.c +++ b/drivers/hid/hid-uclogic-core.c @@ -81,6 +81,24 @@ static __u8 *uclogic_report_fixup(struct hid_device *hdev, __u8 *rdesc, return rdesc; } +static int uclogic_input_mapping(struct hid_device *hdev, + struct hid_input *hi, + struct hid_field *field, + struct hid_usage *usage, + unsigned long **bit, + int *max) +{ + struct uclogic_drvdata *drvdata = hid_get_drvdata(hdev); + struct uclogic_params *params = &drvdata->params; + + /* Discard invalid pen usages */ + if (params->pen.usage_invalid && (field->application == HID_DG_PEN)) + return -1; + + /* Let hid-core decide what to do */ + return 0; +} + static int uclogic_input_configured(struct hid_device *hdev, struct hid_input *hi) { @@ -90,6 +108,8 @@ static int uclogic_input_configured(struct hid_device *hdev, const char *suffix = NULL; struct hid_field *field; size_t len; + size_t i; + const struct uclogic_params_frame *frame; /* no report associated (HID_QUIRK_MULTI_INPUT not set) */ if (!hi->report) @@ -104,27 +124,44 @@ static int uclogic_input_configured(struct hid_device *hdev, drvdata->pen_input = hi->input; } - field = hi->report->field[0]; + /* If it's one of the frame devices */ + for (i = 0; i < ARRAY_SIZE(params->frame_list); i++) { + frame = ¶ms->frame_list[i]; + if (hi->report->id == frame->id) { + /* Assign custom suffix, if any */ + suffix = frame->suffix; + /* + * Disable EV_MSC reports for touch ring interfaces to + * make the Wacom driver pickup touch ring extents + */ + if (frame->touch_byte > 0) + __clear_bit(EV_MSC, hi->input->evbit); + } + } - switch (field->application) { - case HID_GD_KEYBOARD: - suffix = "Keyboard"; - break; - case HID_GD_MOUSE: - suffix = "Mouse"; - break; - case HID_GD_KEYPAD: - suffix = "Pad"; - break; - case HID_DG_PEN: - suffix = "Pen"; - break; - case HID_CP_CONSUMER_CONTROL: - suffix = "Consumer Control"; - break; - case HID_GD_SYSTEM_CONTROL: - suffix = "System Control"; - break; + if (!suffix) { + field = hi->report->field[0]; + + switch (field->application) { + case HID_GD_KEYBOARD: + suffix = "Keyboard"; + break; + case HID_GD_MOUSE: + suffix = "Mouse"; + break; + case HID_GD_KEYPAD: + suffix = "Pad"; + break; + case HID_DG_PEN: + suffix = "Pen"; + break; + case HID_CP_CONSUMER_CONTROL: + suffix = "Consumer Control"; + break; + case HID_GD_SYSTEM_CONTROL: + suffix = "System Control"; + break; + } } if (suffix) { @@ -172,8 +209,8 @@ static int uclogic_probe(struct hid_device *hdev, goto failure; } params_initialized = true; - hid_dbg(hdev, "parameters:\n" UCLOGIC_PARAMS_FMT_STR, - UCLOGIC_PARAMS_FMT_ARGS(&drvdata->params)); + hid_dbg(hdev, "parameters:\n"); + uclogic_params_hid_dbg(hdev, &drvdata->params); if (drvdata->params.invalid) { hid_info(hdev, "interface is invalid, ignoring\n"); rc = -ENODEV; @@ -313,8 +350,15 @@ static int uclogic_raw_event_frame( /* If need to, and can, set pad device ID for Wacom drivers */ if (frame->dev_id_byte > 0 && frame->dev_id_byte < size) { - data[frame->dev_id_byte] = 0xf; + /* If we also have a touch ring and the finger left it */ + if (frame->touch_byte > 0 && frame->touch_byte < size && + data[frame->touch_byte] == 0) { + data[frame->dev_id_byte] = 0; + } else { + data[frame->dev_id_byte] = 0xf; + } } + /* If need to, and can, read rotary encoder state change */ if (frame->re_lsb > 0 && frame->re_lsb / 8 < size) { unsigned int byte = frame->re_lsb / 8; @@ -341,6 +385,26 @@ static int uclogic_raw_event_frame( drvdata->re_state = state; } + /* If need to, and can, transform the touch ring reports */ + if (frame->touch_byte > 0 && frame->touch_byte < size) { + __s8 value = data[frame->touch_byte]; + + if (value != 0) { + if (frame->touch_flip_at != 0) { + value = frame->touch_flip_at - value; + if (value <= 0) + value = frame->touch_max + value; + } + data[frame->touch_byte] = value - 1; + } + } + + /* If need to, and can, transform the bitmap dial reports */ + if (frame->bitmap_dial_byte > 0 && frame->bitmap_dial_byte < size) { + if (data[frame->bitmap_dial_byte] == 2) + data[frame->bitmap_dial_byte] = -1; + } + return 0; } @@ -457,6 +521,8 @@ static const struct hid_device_id uclogic_devices[] = { USB_DEVICE_ID_UGEE_XPPEN_TABLET_G640) }, { HID_USB_DEVICE(USB_VENDOR_ID_UGEE, USB_DEVICE_ID_UGEE_XPPEN_TABLET_DECO01) }, + { HID_USB_DEVICE(USB_VENDOR_ID_UGEE, + USB_DEVICE_ID_UGEE_XPPEN_TABLET_STAR06) }, { } }; MODULE_DEVICE_TABLE(hid, uclogic_devices); @@ -468,6 +534,7 @@ static struct hid_driver uclogic_driver = { .remove = uclogic_remove, .report_fixup = uclogic_report_fixup, .raw_event = uclogic_raw_event, + .input_mapping = uclogic_input_mapping, .input_configured = uclogic_input_configured, #ifdef CONFIG_PM .resume = uclogic_resume, diff --git a/drivers/hid/hid-uclogic-params.c b/drivers/hid/hid-uclogic-params.c index 5f50ceb875d6..db838f16282d 100644 --- a/drivers/hid/hid-uclogic-params.c +++ b/drivers/hid/hid-uclogic-params.c @@ -29,8 +29,8 @@ * Returns: * The string representing the type, or NULL if the type is unknown. */ -const char *uclogic_params_pen_inrange_to_str( - enum uclogic_params_pen_inrange inrange) +static const char *uclogic_params_pen_inrange_to_str( + enum uclogic_params_pen_inrange inrange) { switch (inrange) { case UCLOGIC_PARAMS_PEN_INRANGE_NORMAL: @@ -45,6 +45,91 @@ const char *uclogic_params_pen_inrange_to_str( } /** + * Dump tablet interface pen parameters with hid_dbg(), indented with one tab. + * + * @hdev: The HID device the pen parameters describe. + * @pen: The pen parameters to dump. + */ +static void uclogic_params_pen_hid_dbg(const struct hid_device *hdev, + const struct uclogic_params_pen *pen) +{ + size_t i; + + hid_dbg(hdev, "\t.usage_invalid = %s\n", + (pen->usage_invalid ? "true" : "false")); + hid_dbg(hdev, "\t.desc_ptr = %p\n", pen->desc_ptr); + hid_dbg(hdev, "\t.desc_size = %u\n", pen->desc_size); + hid_dbg(hdev, "\t.id = %u\n", pen->id); + hid_dbg(hdev, "\t.subreport_list = {\n"); + for (i = 0; i < ARRAY_SIZE(pen->subreport_list); i++) { + hid_dbg(hdev, "\t\t{0x%02hhx, %hhu}%s\n", + pen->subreport_list[i].value, + pen->subreport_list[i].id, + i < (ARRAY_SIZE(pen->subreport_list) - 1) ? "," : ""); + } + hid_dbg(hdev, "\t}\n"); + hid_dbg(hdev, "\t.inrange = %s\n", + uclogic_params_pen_inrange_to_str(pen->inrange)); + hid_dbg(hdev, "\t.fragmented_hires = %s\n", + (pen->fragmented_hires ? "true" : "false")); + hid_dbg(hdev, "\t.tilt_y_flipped = %s\n", + (pen->tilt_y_flipped ? "true" : "false")); +} + +/** + * Dump tablet interface frame parameters with hid_dbg(), indented with two + * tabs. + * + * @hdev: The HID device the pen parameters describe. + * @frame: The frame parameters to dump. + */ +static void uclogic_params_frame_hid_dbg( + const struct hid_device *hdev, + const struct uclogic_params_frame *frame) +{ + hid_dbg(hdev, "\t\t.desc_ptr = %p\n", frame->desc_ptr); + hid_dbg(hdev, "\t\t.desc_size = %u\n", frame->desc_size); + hid_dbg(hdev, "\t\t.id = %u\n", frame->id); + hid_dbg(hdev, "\t\t.suffix = %s\n", frame->suffix); + hid_dbg(hdev, "\t\t.re_lsb = %u\n", frame->re_lsb); + hid_dbg(hdev, "\t\t.dev_id_byte = %u\n", frame->dev_id_byte); + hid_dbg(hdev, "\t\t.touch_byte = %u\n", frame->touch_byte); + hid_dbg(hdev, "\t\t.touch_max = %hhd\n", frame->touch_max); + hid_dbg(hdev, "\t\t.touch_flip_at = %hhd\n", + frame->touch_flip_at); + hid_dbg(hdev, "\t\t.bitmap_dial_byte = %u\n", + frame->bitmap_dial_byte); +} + +/** + * Dump tablet interface parameters with hid_dbg(). + * + * @hdev: The HID device the parameters describe. + * @params: The parameters to dump. + */ +void uclogic_params_hid_dbg(const struct hid_device *hdev, + const struct uclogic_params *params) +{ + size_t i; + + hid_dbg(hdev, ".invalid = %s\n", + params->invalid ? "true" : "false"); + hid_dbg(hdev, ".desc_ptr = %p\n", params->desc_ptr); + hid_dbg(hdev, ".desc_size = %u\n", params->desc_size); + hid_dbg(hdev, ".pen = {\n"); + uclogic_params_pen_hid_dbg(hdev, ¶ms->pen); + hid_dbg(hdev, "\t}\n"); + hid_dbg(hdev, ".frame_list = {\n"); + for (i = 0; i < ARRAY_SIZE(params->frame_list); i++) { + hid_dbg(hdev, "\t{\n"); + uclogic_params_frame_hid_dbg(hdev, ¶ms->frame_list[i]); + hid_dbg(hdev, "\t}%s\n", + i < (ARRAY_SIZE(params->frame_list) - 1) ? "," : ""); + } + hid_dbg(hdev, "}\n"); +} + +/** * uclogic_params_get_str_desc - retrieve a string descriptor from a HID * device interface, putting it into a kmalloc-allocated buffer as is, without * character encoding conversion. @@ -253,28 +338,45 @@ static s32 uclogic_params_get_le24(const void *p) * uclogic_params_pen_init_v2() - initialize tablet interface pen * input and retrieve its parameters from the device, using v2 protocol. * - * @pen: Pointer to the pen parameters to initialize (to be - * cleaned up with uclogic_params_pen_cleanup()). Not modified in - * case of error, or if parameters are not found. Cannot be NULL. - * @pfound: Location for a flag which is set to true if the parameters - * were found, and to false if not (e.g. device was - * incompatible). Not modified in case of error. Cannot be NULL. - * @hdev: The HID device of the tablet interface to initialize and get - * parameters from. Cannot be NULL. + * @pen: Pointer to the pen parameters to initialize (to be + * cleaned up with uclogic_params_pen_cleanup()). Not + * modified in case of error, or if parameters are not + * found. Cannot be NULL. + * @pfound: Location for a flag which is set to true if the + * parameters were found, and to false if not (e.g. + * device was incompatible). Not modified in case of + * error. Cannot be NULL. + * @pparams_ptr: Location for a kmalloc'ed pointer to the retrieved raw + * parameters, which could be used to identify the tablet + * to some extent. Should be freed with kfree after use. + * NULL, if not needed. Not modified in case of error. + * Only set if *pfound is set to true. + * @pparams_len: Location for the length of the retrieved raw + * parameters. NULL, if not needed. Not modified in case + * of error. Only set if *pfound is set to true. + * @hdev: The HID device of the tablet interface to initialize + * and get parameters from. Cannot be NULL. * * Returns: * Zero, if successful. A negative errno code on error. */ static int uclogic_params_pen_init_v2(struct uclogic_params_pen *pen, bool *pfound, + __u8 **pparams_ptr, + size_t *pparams_len, struct hid_device *hdev) { int rc; bool found = false; - /* Buffer for (part of) the string descriptor */ + /* Buffer for (part of) the parameter string descriptor */ __u8 *buf = NULL; - /* Descriptor length required */ - const int len = 18; + /* Parameter string descriptor required length */ + const int params_len_min = 18; + /* Parameter string descriptor accepted length */ + const int params_len_max = 32; + /* Parameter string descriptor received length */ + int params_len; + size_t i; s32 resolution; /* Pen report descriptor template parameters */ s32 desc_params[UCLOGIC_RDESC_PEN_PH_ID_NUM]; @@ -292,7 +394,7 @@ static int uclogic_params_pen_init_v2(struct uclogic_params_pen *pen, * the Windows driver traffic. * NOTE: This enables fully-functional tablet mode. */ - rc = uclogic_params_get_str_desc(&buf, hdev, 200, len); + rc = uclogic_params_get_str_desc(&buf, hdev, 200, params_len_max); if (rc == -EPIPE) { hid_dbg(hdev, "string descriptor with pen parameters not found, assuming not compatible\n"); @@ -300,27 +402,28 @@ static int uclogic_params_pen_init_v2(struct uclogic_params_pen *pen, } else if (rc < 0) { hid_err(hdev, "failed retrieving pen parameters: %d\n", rc); goto cleanup; - } else if (rc != len) { + } else if (rc < params_len_min) { hid_dbg(hdev, - "string descriptor with pen parameters has invalid length (got %d, expected %d), assuming not compatible\n", - rc, len); + "string descriptor with pen parameters is too short (got %d, expected at least %d), assuming not compatible\n", + rc, params_len_min); + goto finish; + } + + params_len = rc; + + /* + * Check it's not just a catch-all UTF-16LE-encoded ASCII + * string (such as the model name) some tablets put into all + * unknown string descriptors. + */ + for (i = 2; + i < params_len && + (buf[i] >= 0x20 && buf[i] < 0x7f && buf[i + 1] == 0); + i += 2); + if (i >= params_len) { + hid_dbg(hdev, + "string descriptor with pen parameters seems to contain only text, assuming not compatible\n"); goto finish; - } else { - size_t i; - /* - * Check it's not just a catch-all UTF-16LE-encoded ASCII - * string (such as the model name) some tablets put into all - * unknown string descriptors. - */ - for (i = 2; - i < len && - (buf[i] >= 0x20 && buf[i] < 0x7f && buf[i + 1] == 0); - i += 2); - if (i >= len) { - hid_dbg(hdev, - "string descriptor with pen parameters seems to contain only text, assuming not compatible\n"); - goto finish; - } } /* @@ -344,8 +447,6 @@ static int uclogic_params_pen_init_v2(struct uclogic_params_pen *pen, desc_params[UCLOGIC_RDESC_PEN_PH_ID_Y_LM] * 1000 / resolution; } - kfree(buf); - buf = NULL; /* * Generate pen report descriptor @@ -371,6 +472,13 @@ static int uclogic_params_pen_init_v2(struct uclogic_params_pen *pen, pen->fragmented_hires = true; pen->tilt_y_flipped = true; found = true; + if (pparams_ptr != NULL) { + *pparams_ptr = buf; + buf = NULL; + } + if (pparams_len != NULL) + *pparams_len = params_len; + finish: *pfound = found; rc = 0; @@ -700,6 +808,14 @@ static int uclogic_params_huion_init(struct uclogic_params *params, static const char transition_ver[] = "HUION_T153_160607"; char *ver_ptr = NULL; const size_t ver_len = sizeof(transition_ver) + 1; + __u8 *params_ptr = NULL; + size_t params_len = 0; + /* Parameters string descriptor of a model with touch ring (HS610) */ + const __u8 touch_ring_model_params_buf[] = { + 0x13, 0x03, 0x70, 0xC6, 0x00, 0x06, 0x7C, 0x00, + 0xFF, 0x1F, 0xD8, 0x13, 0x03, 0x0D, 0x10, 0x01, + 0x04, 0x3C, 0x3E + }; /* Check arguments */ if (params == NULL || hdev == NULL) { @@ -711,8 +827,13 @@ static int uclogic_params_huion_init(struct uclogic_params *params, iface = to_usb_interface(hdev->dev.parent); bInterfaceNumber = iface->cur_altsetting->desc.bInterfaceNumber; - /* If it's not a pen interface */ - if (bInterfaceNumber != 0) { + /* If it's a custom keyboard interface */ + if (bInterfaceNumber == 1) { + /* Keep everything intact, but mark pen usage invalid */ + p.pen.usage_invalid = true; + goto output; + /* Else, if it's not a pen interface */ + } else if (bInterfaceNumber != 0) { uclogic_params_init_invalid(&p); goto output; } @@ -738,29 +859,103 @@ static int uclogic_params_huion_init(struct uclogic_params *params, "transition firmware detected, not probing pen v2 parameters\n"); } else { /* Try to probe v2 pen parameters */ - rc = uclogic_params_pen_init_v2(&p.pen, &found, hdev); + rc = uclogic_params_pen_init_v2(&p.pen, &found, + ¶ms_ptr, ¶ms_len, + hdev); if (rc != 0) { hid_err(hdev, "failed probing pen v2 parameters: %d\n", rc); goto cleanup; } else if (found) { hid_dbg(hdev, "pen v2 parameters found\n"); - /* Create v2 frame parameters */ + /* Create v2 frame button parameters */ rc = uclogic_params_frame_init_with_desc( &p.frame_list[0], - uclogic_rdesc_v2_frame_arr, - uclogic_rdesc_v2_frame_size, - UCLOGIC_RDESC_V2_FRAME_ID); + uclogic_rdesc_v2_frame_buttons_arr, + uclogic_rdesc_v2_frame_buttons_size, + UCLOGIC_RDESC_V2_FRAME_BUTTONS_ID); if (rc != 0) { hid_err(hdev, - "failed creating v2 frame parameters: %d\n", + "failed creating v2 frame button parameters: %d\n", rc); goto cleanup; } - /* Link frame button subreports from pen reports */ + + /* Link from pen sub-report */ p.pen.subreport_list[0].value = 0xe0; p.pen.subreport_list[0].id = - UCLOGIC_RDESC_V2_FRAME_ID; + UCLOGIC_RDESC_V2_FRAME_BUTTONS_ID; + + /* If this is the model with touch ring */ + if (params_ptr != NULL && + params_len == sizeof(touch_ring_model_params_buf) && + memcmp(params_ptr, touch_ring_model_params_buf, + params_len) == 0) { + /* Create touch ring parameters */ + rc = uclogic_params_frame_init_with_desc( + &p.frame_list[1], + uclogic_rdesc_v2_frame_touch_ring_arr, + uclogic_rdesc_v2_frame_touch_ring_size, + UCLOGIC_RDESC_V2_FRAME_TOUCH_ID); + if (rc != 0) { + hid_err(hdev, + "failed creating v2 frame touch ring parameters: %d\n", + rc); + goto cleanup; + } + p.frame_list[1].suffix = "Touch Ring"; + p.frame_list[1].dev_id_byte = + UCLOGIC_RDESC_V2_FRAME_TOUCH_DEV_ID_BYTE; + p.frame_list[1].touch_byte = 5; + p.frame_list[1].touch_max = 12; + p.frame_list[1].touch_flip_at = 7; + } else { + /* Create touch strip parameters */ + rc = uclogic_params_frame_init_with_desc( + &p.frame_list[1], + uclogic_rdesc_v2_frame_touch_strip_arr, + uclogic_rdesc_v2_frame_touch_strip_size, + UCLOGIC_RDESC_V2_FRAME_TOUCH_ID); + if (rc != 0) { + hid_err(hdev, + "failed creating v2 frame touch strip parameters: %d\n", + rc); + goto cleanup; + } + p.frame_list[1].suffix = "Touch Strip"; + p.frame_list[1].dev_id_byte = + UCLOGIC_RDESC_V2_FRAME_TOUCH_DEV_ID_BYTE; + p.frame_list[1].touch_byte = 5; + p.frame_list[1].touch_max = 8; + } + + /* Link from pen sub-report */ + p.pen.subreport_list[1].value = 0xf0; + p.pen.subreport_list[1].id = + UCLOGIC_RDESC_V2_FRAME_TOUCH_ID; + + /* Create v2 frame dial parameters */ + rc = uclogic_params_frame_init_with_desc( + &p.frame_list[2], + uclogic_rdesc_v2_frame_dial_arr, + uclogic_rdesc_v2_frame_dial_size, + UCLOGIC_RDESC_V2_FRAME_DIAL_ID); + if (rc != 0) { + hid_err(hdev, + "failed creating v2 frame dial parameters: %d\n", + rc); + goto cleanup; + } + p.frame_list[2].suffix = "Dial"; + p.frame_list[2].dev_id_byte = + UCLOGIC_RDESC_V2_FRAME_DIAL_DEV_ID_BYTE; + p.frame_list[2].bitmap_dial_byte = 5; + + /* Link from pen sub-report */ + p.pen.subreport_list[2].value = 0xf1; + p.pen.subreport_list[2].id = + UCLOGIC_RDESC_V2_FRAME_DIAL_ID; + goto output; } hid_dbg(hdev, "pen v2 parameters not found\n"); @@ -801,6 +996,7 @@ output: memset(&p, 0, sizeof(p)); rc = 0; cleanup: + kfree(params_ptr); kfree(ver_ptr); uclogic_params_cleanup(&p); return rc; @@ -1000,6 +1196,8 @@ int uclogic_params_init(struct uclogic_params *params, case VID_PID(USB_VENDOR_ID_UGEE, USB_DEVICE_ID_UGEE_XPPEN_TABLET_G640): case VID_PID(USB_VENDOR_ID_UGEE, + USB_DEVICE_ID_UGEE_XPPEN_TABLET_STAR06): + case VID_PID(USB_VENDOR_ID_UGEE, USB_DEVICE_ID_UGEE_TABLET_RAINBOW_CV720): /* If this is the pen interface */ if (bInterfaceNumber == 1) { diff --git a/drivers/hid/hid-uclogic-params.h b/drivers/hid/hid-uclogic-params.h index 86f616dfbb53..5bef8daaa607 100644 --- a/drivers/hid/hid-uclogic-params.h +++ b/drivers/hid/hid-uclogic-params.h @@ -29,11 +29,6 @@ enum uclogic_params_pen_inrange { UCLOGIC_PARAMS_PEN_INRANGE_NONE, }; -/* Convert a pen in-range reporting type to a string */ -extern const char *uclogic_params_pen_inrange_to_str( - enum uclogic_params_pen_inrange inrange); - - /* * Pen report's subreport data. */ @@ -62,8 +57,13 @@ struct uclogic_params_pen_subreport { */ struct uclogic_params_pen { /* - * Pointer to report descriptor describing the inputs. - * Allocated with kmalloc. + * True if pen usage is invalid for this interface and should be + * ignored, false otherwise. + */ + bool usage_invalid; + /* + * Pointer to report descriptor part describing the pen inputs. + * Allocated with kmalloc. NULL if the part is not specified. */ __u8 *desc_ptr; /* @@ -73,8 +73,8 @@ struct uclogic_params_pen { unsigned int desc_size; /* Report ID, if reports should be tweaked, zero if not */ unsigned int id; - /* The list of subreports */ - struct uclogic_params_pen_subreport subreport_list[1]; + /* The list of subreports, only valid if "id" is not zero */ + struct uclogic_params_pen_subreport subreport_list[3]; /* Type of in-range reporting, only valid if "id" is not zero */ enum uclogic_params_pen_inrange inrange; /* @@ -101,8 +101,8 @@ struct uclogic_params_pen { */ struct uclogic_params_frame { /* - * Pointer to report descriptor describing the inputs. - * Allocated with kmalloc. + * Pointer to report descriptor part describing the frame inputs. + * Allocated with kmalloc. NULL if the part is not specified. */ __u8 *desc_ptr; /* @@ -115,6 +115,10 @@ struct uclogic_params_frame { */ unsigned int id; /* + * The suffix to add to the input device name, if not NULL. + */ + const char *suffix; + /* * Number of the least-significant bit of the 2-bit state of a rotary * encoder, in the report. Cannot point to a 2-bit field crossing a * byte boundary. Zero if not present. Only valid if "id" is not zero. @@ -123,10 +127,40 @@ struct uclogic_params_frame { /* * Offset of the Wacom-style device ID byte in the report, to be set * to pad device ID (0xf), for compatibility with Wacom drivers. Zero - * if no changes to the report should be made. Only valid if "id" is - * not zero. + * if no changes to the report should be made. The ID byte will be set + * to zero whenever the byte pointed by "touch_byte" is zero, if + * the latter is valid. Only valid if "id" is not zero. */ unsigned int dev_id_byte; + /* + * Offset of the touch ring/strip state byte, in the report. + * Zero if not present. If dev_id_byte is also valid and non-zero, + * then the device ID byte will be cleared when the byte pointed to by + * this offset is zero. Only valid if "id" is not zero. + */ + unsigned int touch_byte; + /* + * The value to anchor the reversed touch ring/strip reports at. + * I.e. one, if the reports should be flipped without offset. + * Zero if no reversal should be done. + * Only valid if "touch_byte" is valid and not zero. + */ + __s8 touch_flip_at; + /* + * Maximum value of the touch ring/strip report around which the value + * should be wrapped when flipping according to "touch_flip_at". + * The minimum valid value is considered to be one, with zero being + * out-of-proximity (finger lift) value. + * Only valid if "touch_flip_at" is valid and not zero. + */ + __s8 touch_max; + /* + * Offset of the bitmap dial byte, in the report. Zero if not present. + * Only valid if "id" is not zero. A bitmap dial sends reports with a + * dedicated bit per direction: 1 means clockwise rotation, 2 means + * counterclockwise, as opposed to the normal 1 and -1. + */ + unsigned int bitmap_dial_byte; }; /* @@ -156,7 +190,7 @@ struct uclogic_params { __u8 *desc_ptr; /* * Size of the common part of the replacement report descriptor. - * Only valid, if "desc_ptr" is not NULL. + * Only valid, if "desc_ptr" is valid and not NULL. */ unsigned int desc_size; /* @@ -168,50 +202,13 @@ struct uclogic_params { * The list of frame control parameters and optional report descriptor * parts. Only valid, if "invalid" is false. */ - struct uclogic_params_frame frame_list[1]; + struct uclogic_params_frame frame_list[3]; }; /* Initialize a tablet interface and discover its parameters */ extern int uclogic_params_init(struct uclogic_params *params, struct hid_device *hdev); -/* Tablet interface parameters *printf format string */ -#define UCLOGIC_PARAMS_FMT_STR \ - ".invalid = %s\n" \ - ".desc_ptr = %p\n" \ - ".desc_size = %u\n" \ - ".pen.desc_ptr = %p\n" \ - ".pen.desc_size = %u\n" \ - ".pen.id = %u\n" \ - ".pen.subreport_list[0] = {0x%02hhx, %hhu}\n" \ - ".pen.inrange = %s\n" \ - ".pen.fragmented_hires = %s\n" \ - ".pen.tilt_y_flipped = %s\n" \ - ".frame_list[0].desc_ptr = %p\n" \ - ".frame_list[0].desc_size = %u\n" \ - ".frame_list[0].id = %u\n" \ - ".frame_list[0].re_lsb = %u\n" \ - ".frame_list[0].dev_id_byte = %u\n" - -/* Tablet interface parameters *printf format arguments */ -#define UCLOGIC_PARAMS_FMT_ARGS(_params) \ - ((_params)->invalid ? "true" : "false"), \ - (_params)->desc_ptr, \ - (_params)->desc_size, \ - (_params)->pen.desc_ptr, \ - (_params)->pen.desc_size, \ - (_params)->pen.id, \ - (_params)->pen.subreport_list[0].value, \ - (_params)->pen.subreport_list[0].id, \ - uclogic_params_pen_inrange_to_str((_params)->pen.inrange), \ - ((_params)->pen.fragmented_hires ? "true" : "false"), \ - ((_params)->pen.tilt_y_flipped ? "true" : "false"), \ - (_params)->frame_list[0].desc_ptr, \ - (_params)->frame_list[0].desc_size, \ - (_params)->frame_list[0].id, \ - (_params)->frame_list[0].re_lsb, \ - (_params)->frame_list[0].dev_id_byte - /* Get a replacement report descriptor for a tablet's interface. */ extern int uclogic_params_get_desc(const struct uclogic_params *params, __u8 **pdesc, @@ -220,4 +217,8 @@ extern int uclogic_params_get_desc(const struct uclogic_params *params, /* Free resources used by tablet interface's parameters */ extern void uclogic_params_cleanup(struct uclogic_params *params); +/* Dump tablet interface parameters with hid_dbg() */ +extern void uclogic_params_hid_dbg(const struct hid_device *hdev, + const struct uclogic_params *params); + #endif /* _HID_UCLOGIC_PARAMS_H */ diff --git a/drivers/hid/hid-uclogic-rdesc.c b/drivers/hid/hid-uclogic-rdesc.c index 04644d93bd11..13f9ce73f1b1 100644 --- a/drivers/hid/hid-uclogic-rdesc.c +++ b/drivers/hid/hid-uclogic-rdesc.c @@ -21,7 +21,7 @@ /* Fixed WP4030U report descriptor */ __u8 uclogic_rdesc_wp4030u_fixed_arr[] = { 0x05, 0x0D, /* Usage Page (Digitizer), */ - 0x09, 0x02, /* Usage (Pen), */ + 0x09, 0x01, /* Usage (Digitizer), */ 0xA1, 0x01, /* Collection (Application), */ 0x85, 0x09, /* Report ID (9), */ 0x09, 0x20, /* Usage (Stylus), */ @@ -66,7 +66,7 @@ const size_t uclogic_rdesc_wp4030u_fixed_size = /* Fixed WP5540U report descriptor */ __u8 uclogic_rdesc_wp5540u_fixed_arr[] = { 0x05, 0x0D, /* Usage Page (Digitizer), */ - 0x09, 0x02, /* Usage (Pen), */ + 0x09, 0x01, /* Usage (Digitizer), */ 0xA1, 0x01, /* Collection (Application), */ 0x85, 0x09, /* Report ID (9), */ 0x09, 0x20, /* Usage (Stylus), */ @@ -143,7 +143,7 @@ const size_t uclogic_rdesc_wp5540u_fixed_size = /* Fixed WP8060U report descriptor */ __u8 uclogic_rdesc_wp8060u_fixed_arr[] = { 0x05, 0x0D, /* Usage Page (Digitizer), */ - 0x09, 0x02, /* Usage (Pen), */ + 0x09, 0x01, /* Usage (Digitizer), */ 0xA1, 0x01, /* Collection (Application), */ 0x85, 0x09, /* Report ID (9), */ 0x09, 0x20, /* Usage (Stylus), */ @@ -220,7 +220,7 @@ const size_t uclogic_rdesc_wp8060u_fixed_size = /* Fixed WP1062 report descriptor */ __u8 uclogic_rdesc_wp1062_fixed_arr[] = { 0x05, 0x0D, /* Usage Page (Digitizer), */ - 0x09, 0x02, /* Usage (Pen), */ + 0x09, 0x01, /* Usage (Digitizer), */ 0xA1, 0x01, /* Collection (Application), */ 0x85, 0x09, /* Report ID (9), */ 0x09, 0x20, /* Usage (Stylus), */ @@ -268,7 +268,7 @@ const size_t uclogic_rdesc_wp1062_fixed_size = /* Fixed PF1209 report descriptor */ __u8 uclogic_rdesc_pf1209_fixed_arr[] = { 0x05, 0x0D, /* Usage Page (Digitizer), */ - 0x09, 0x02, /* Usage (Pen), */ + 0x09, 0x01, /* Usage (Digitizer), */ 0xA1, 0x01, /* Collection (Application), */ 0x85, 0x09, /* Report ID (9), */ 0x09, 0x20, /* Usage (Stylus), */ @@ -345,7 +345,7 @@ const size_t uclogic_rdesc_pf1209_fixed_size = /* Fixed PID 0522 tablet report descriptor, interface 0 (stylus) */ __u8 uclogic_rdesc_twhl850_fixed0_arr[] = { 0x05, 0x0D, /* Usage Page (Digitizer), */ - 0x09, 0x02, /* Usage (Pen), */ + 0x09, 0x01, /* Usage (Digitizer), */ 0xA1, 0x01, /* Collection (Application), */ 0x85, 0x09, /* Report ID (9), */ 0x09, 0x20, /* Usage (Stylus), */ @@ -457,7 +457,7 @@ const size_t uclogic_rdesc_twhl850_fixed2_size = /* Fixed TWHA60 report descriptor, interface 0 (stylus) */ __u8 uclogic_rdesc_twha60_fixed0_arr[] = { 0x05, 0x0D, /* Usage Page (Digitizer), */ - 0x09, 0x02, /* Usage (Pen), */ + 0x09, 0x01, /* Usage (Digitizer), */ 0xA1, 0x01, /* Collection (Application), */ 0x85, 0x09, /* Report ID (9), */ 0x09, 0x20, /* Usage (Stylus), */ @@ -534,7 +534,7 @@ const size_t uclogic_rdesc_twha60_fixed1_size = /* Fixed report descriptor template for (tweaked) v1 pen reports */ const __u8 uclogic_rdesc_v1_pen_template_arr[] = { 0x05, 0x0D, /* Usage Page (Digitizer), */ - 0x09, 0x02, /* Usage (Pen), */ + 0x09, 0x01, /* Usage (Digitizer), */ 0xA1, 0x01, /* Collection (Application), */ 0x85, 0x07, /* Report ID (7), */ 0x09, 0x20, /* Usage (Stylus), */ @@ -588,7 +588,7 @@ const size_t uclogic_rdesc_v1_pen_template_size = /* Fixed report descriptor template for (tweaked) v2 pen reports */ const __u8 uclogic_rdesc_v2_pen_template_arr[] = { 0x05, 0x0D, /* Usage Page (Digitizer), */ - 0x09, 0x02, /* Usage (Pen), */ + 0x09, 0x01, /* Usage (Digitizer), */ 0xA1, 0x01, /* Collection (Application), */ 0x85, 0x08, /* Report ID (8), */ 0x09, 0x20, /* Usage (Stylus), */ @@ -652,12 +652,12 @@ const size_t uclogic_rdesc_v2_pen_template_size = sizeof(uclogic_rdesc_v2_pen_template_arr); /* - * Expand to the contents of a generic frame report descriptor. + * Expand to the contents of a generic frame buttons report descriptor. * * @_id: The report ID to use. * @_size: Size of the report to pad to, including report ID, bytes. */ -#define UCLOGIC_RDESC_FRAME_BYTES(_id, _size) \ +#define UCLOGIC_RDESC_FRAME_BUTTONS_BYTES(_id, _size) \ 0x05, 0x01, /* Usage Page (Desktop), */ \ 0x09, 0x07, /* Usage (Keypad), */ \ 0xA1, 0x01, /* Collection (Application), */ \ @@ -700,17 +700,164 @@ const size_t uclogic_rdesc_v2_pen_template_size = /* Fixed report descriptor for (tweaked) v1 frame reports */ const __u8 uclogic_rdesc_v1_frame_arr[] = { - UCLOGIC_RDESC_FRAME_BYTES(UCLOGIC_RDESC_V1_FRAME_ID, 8) + UCLOGIC_RDESC_FRAME_BUTTONS_BYTES(UCLOGIC_RDESC_V1_FRAME_ID, 8) }; const size_t uclogic_rdesc_v1_frame_size = sizeof(uclogic_rdesc_v1_frame_arr); -/* Fixed report descriptor for (tweaked) v2 frame reports */ -const __u8 uclogic_rdesc_v2_frame_arr[] = { - UCLOGIC_RDESC_FRAME_BYTES(UCLOGIC_RDESC_V2_FRAME_ID, 12) +/* Fixed report descriptor for (tweaked) v2 frame button reports */ +const __u8 uclogic_rdesc_v2_frame_buttons_arr[] = { + UCLOGIC_RDESC_FRAME_BUTTONS_BYTES(UCLOGIC_RDESC_V2_FRAME_BUTTONS_ID, + 12) }; -const size_t uclogic_rdesc_v2_frame_size = - sizeof(uclogic_rdesc_v2_frame_arr); +const size_t uclogic_rdesc_v2_frame_buttons_size = + sizeof(uclogic_rdesc_v2_frame_buttons_arr); + +/* Fixed report descriptor for (tweaked) v2 frame touch ring reports */ +const __u8 uclogic_rdesc_v2_frame_touch_ring_arr[] = { + 0x05, 0x01, /* Usage Page (Desktop), */ + 0x09, 0x07, /* Usage (Keypad), */ + 0xA1, 0x01, /* Collection (Application), */ + 0x85, UCLOGIC_RDESC_V2_FRAME_TOUCH_ID, + /* Report ID (TOUCH_ID), */ + 0x14, /* Logical Minimum (0), */ + 0x05, 0x0D, /* Usage Page (Digitizer), */ + 0x09, 0x39, /* Usage (Tablet Function Keys), */ + 0xA0, /* Collection (Physical), */ + 0x25, 0x01, /* Logical Maximum (1), */ + 0x75, 0x01, /* Report Size (1), */ + 0x05, 0x09, /* Usage Page (Button), */ + 0x09, 0x01, /* Usage (01h), */ + 0x95, 0x01, /* Report Count (1), */ + 0x81, 0x02, /* Input (Variable), */ + 0x95, 0x07, /* Report Count (7), */ + 0x81, 0x01, /* Input (Constant), */ + 0x75, 0x08, /* Report Size (8), */ + 0x95, 0x02, /* Report Count (2), */ + 0x81, 0x01, /* Input (Constant), */ + 0x05, 0x0D, /* Usage Page (Digitizer), */ + 0x0A, 0xFF, 0xFF, /* Usage (FFFFh), */ + 0x26, 0xFF, 0x00, /* Logical Maximum (255), */ + 0x95, 0x01, /* Report Count (1), */ + 0x81, 0x02, /* Input (Variable), */ + 0x05, 0x01, /* Usage Page (Desktop), */ + 0x09, 0x38, /* Usage (Wheel), */ + 0x95, 0x01, /* Report Count (1), */ + 0x15, 0x00, /* Logical Minimum (0), */ + 0x25, 0x0B, /* Logical Maximum (11), */ + 0x81, 0x02, /* Input (Variable), */ + 0x09, 0x30, /* Usage (X), */ + 0x09, 0x31, /* Usage (Y), */ + 0x14, /* Logical Minimum (0), */ + 0x25, 0x01, /* Logical Maximum (1), */ + 0x75, 0x01, /* Report Size (1), */ + 0x95, 0x02, /* Report Count (2), */ + 0x81, 0x02, /* Input (Variable), */ + 0x95, 0x2E, /* Report Count (46), */ + 0x81, 0x01, /* Input (Constant), */ + 0xC0, /* End Collection, */ + 0xC0 /* End Collection */ +}; +const size_t uclogic_rdesc_v2_frame_touch_ring_size = + sizeof(uclogic_rdesc_v2_frame_touch_ring_arr); + +/* Fixed report descriptor for (tweaked) v2 frame touch strip reports */ +const __u8 uclogic_rdesc_v2_frame_touch_strip_arr[] = { + 0x05, 0x01, /* Usage Page (Desktop), */ + 0x09, 0x07, /* Usage (Keypad), */ + 0xA1, 0x01, /* Collection (Application), */ + 0x85, UCLOGIC_RDESC_V2_FRAME_TOUCH_ID, + /* Report ID (TOUCH_ID), */ + 0x14, /* Logical Minimum (0), */ + 0x05, 0x0D, /* Usage Page (Digitizer), */ + 0x09, 0x39, /* Usage (Tablet Function Keys), */ + 0xA0, /* Collection (Physical), */ + 0x25, 0x01, /* Logical Maximum (1), */ + 0x75, 0x01, /* Report Size (1), */ + 0x05, 0x09, /* Usage Page (Button), */ + 0x09, 0x01, /* Usage (01h), */ + 0x95, 0x01, /* Report Count (1), */ + 0x81, 0x02, /* Input (Variable), */ + 0x95, 0x07, /* Report Count (7), */ + 0x81, 0x01, /* Input (Constant), */ + 0x75, 0x08, /* Report Size (8), */ + 0x95, 0x02, /* Report Count (2), */ + 0x81, 0x01, /* Input (Constant), */ + 0x05, 0x0D, /* Usage Page (Digitizer), */ + 0x0A, 0xFF, 0xFF, /* Usage (FFFFh), */ + 0x26, 0xFF, 0x00, /* Logical Maximum (255), */ + 0x95, 0x01, /* Report Count (1), */ + 0x81, 0x02, /* Input (Variable), */ + 0x05, 0x01, /* Usage Page (Desktop), */ + 0x09, 0x38, /* Usage (Wheel), */ + 0x95, 0x01, /* Report Count (1), */ + 0x15, 0x00, /* Logical Minimum (0), */ + 0x25, 0x07, /* Logical Maximum (7), */ + 0x81, 0x02, /* Input (Variable), */ + 0x09, 0x30, /* Usage (X), */ + 0x09, 0x31, /* Usage (Y), */ + 0x14, /* Logical Minimum (0), */ + 0x25, 0x01, /* Logical Maximum (1), */ + 0x75, 0x01, /* Report Size (1), */ + 0x95, 0x02, /* Report Count (2), */ + 0x81, 0x02, /* Input (Variable), */ + 0x95, 0x2E, /* Report Count (46), */ + 0x81, 0x01, /* Input (Constant), */ + 0xC0, /* End Collection, */ + 0xC0 /* End Collection */ +}; +const size_t uclogic_rdesc_v2_frame_touch_strip_size = + sizeof(uclogic_rdesc_v2_frame_touch_strip_arr); + +/* Fixed report descriptor for (tweaked) v2 frame dial reports */ +const __u8 uclogic_rdesc_v2_frame_dial_arr[] = { + 0x05, 0x01, /* Usage Page (Desktop), */ + 0x09, 0x07, /* Usage (Keypad), */ + 0xA1, 0x01, /* Collection (Application), */ + 0x85, UCLOGIC_RDESC_V2_FRAME_DIAL_ID, + /* Report ID (DIAL_ID), */ + 0x14, /* Logical Minimum (0), */ + 0x05, 0x0D, /* Usage Page (Digitizer), */ + 0x09, 0x39, /* Usage (Tablet Function Keys), */ + 0xA0, /* Collection (Physical), */ + 0x25, 0x01, /* Logical Maximum (1), */ + 0x75, 0x01, /* Report Size (1), */ + 0x95, 0x01, /* Report Count (1), */ + 0x81, 0x01, /* Input (Constant), */ + 0x05, 0x09, /* Usage Page (Button), */ + 0x09, 0x01, /* Usage (01h), */ + 0x95, 0x01, /* Report Count (1), */ + 0x81, 0x02, /* Input (Variable), */ + 0x95, 0x06, /* Report Count (6), */ + 0x81, 0x01, /* Input (Constant), */ + 0x75, 0x08, /* Report Size (8), */ + 0x95, 0x02, /* Report Count (2), */ + 0x81, 0x01, /* Input (Constant), */ + 0x05, 0x0D, /* Usage Page (Digitizer), */ + 0x0A, 0xFF, 0xFF, /* Usage (FFFFh), */ + 0x26, 0xFF, 0x00, /* Logical Maximum (255), */ + 0x95, 0x01, /* Report Count (1), */ + 0x81, 0x02, /* Input (Variable), */ + 0x05, 0x01, /* Usage Page (Desktop), */ + 0x09, 0x38, /* Usage (Wheel), */ + 0x95, 0x01, /* Report Count (1), */ + 0x15, 0xFF, /* Logical Minimum (-1), */ + 0x25, 0x01, /* Logical Maximum (1), */ + 0x81, 0x06, /* Input (Variable, Relative), */ + 0x09, 0x30, /* Usage (X), */ + 0x09, 0x31, /* Usage (Y), */ + 0x14, /* Logical Minimum (0), */ + 0x25, 0x01, /* Logical Maximum (1), */ + 0x75, 0x01, /* Report Size (1), */ + 0x95, 0x02, /* Report Count (2), */ + 0x81, 0x02, /* Input (Variable), */ + 0x95, 0x2E, /* Report Count (46), */ + 0x81, 0x01, /* Input (Constant), */ + 0xC0, /* End Collection, */ + 0xC0 /* End Collection */ +}; +const size_t uclogic_rdesc_v2_frame_dial_size = + sizeof(uclogic_rdesc_v2_frame_dial_arr); /* Fixed report descriptor for Ugee EX07 frame */ const __u8 uclogic_rdesc_ugee_ex07_frame_arr[] = { diff --git a/drivers/hid/hid-uclogic-rdesc.h b/drivers/hid/hid-uclogic-rdesc.h index 3d904c27b86a..0c6e95e8bde7 100644 --- a/drivers/hid/hid-uclogic-rdesc.h +++ b/drivers/hid/hid-uclogic-rdesc.h @@ -124,12 +124,36 @@ extern const size_t uclogic_rdesc_v2_pen_template_size; extern const __u8 uclogic_rdesc_v1_frame_arr[]; extern const size_t uclogic_rdesc_v1_frame_size; -/* Report ID for tweaked v2 frame reports */ -#define UCLOGIC_RDESC_V2_FRAME_ID 0xf7 +/* Report ID for tweaked v2 frame button reports */ +#define UCLOGIC_RDESC_V2_FRAME_BUTTONS_ID 0xf7 -/* Fixed report descriptor for (tweaked) v2 frame reports */ -extern const __u8 uclogic_rdesc_v2_frame_arr[]; -extern const size_t uclogic_rdesc_v2_frame_size; +/* Fixed report descriptor for (tweaked) v2 frame button reports */ +extern const __u8 uclogic_rdesc_v2_frame_buttons_arr[]; +extern const size_t uclogic_rdesc_v2_frame_buttons_size; + +/* Report ID for tweaked v2 frame touch ring/strip reports */ +#define UCLOGIC_RDESC_V2_FRAME_TOUCH_ID 0xf8 + +/* Fixed report descriptor for (tweaked) v2 frame touch ring reports */ +extern const __u8 uclogic_rdesc_v2_frame_touch_ring_arr[]; +extern const size_t uclogic_rdesc_v2_frame_touch_ring_size; + +/* Fixed report descriptor for (tweaked) v2 frame touch strip reports */ +extern const __u8 uclogic_rdesc_v2_frame_touch_strip_arr[]; +extern const size_t uclogic_rdesc_v2_frame_touch_strip_size; + +/* Device ID byte offset in v2 frame touch ring/strip reports */ +#define UCLOGIC_RDESC_V2_FRAME_TOUCH_DEV_ID_BYTE 0x4 + +/* Report ID for tweaked v2 frame dial reports */ +#define UCLOGIC_RDESC_V2_FRAME_DIAL_ID 0xf9 + +/* Fixed report descriptor for (tweaked) v2 frame dial reports */ +extern const __u8 uclogic_rdesc_v2_frame_dial_arr[]; +extern const size_t uclogic_rdesc_v2_frame_dial_size; + +/* Device ID byte offset in v2 frame dial reports */ +#define UCLOGIC_RDESC_V2_FRAME_DIAL_DEV_ID_BYTE 0x4 /* Fixed report descriptor for Ugee EX07 frame */ extern const __u8 uclogic_rdesc_ugee_ex07_frame_arr[]; diff --git a/drivers/hid/hid-viewsonic.c b/drivers/hid/hid-viewsonic.c index df60c8fc2efd..8024b1d370e2 100644 --- a/drivers/hid/hid-viewsonic.c +++ b/drivers/hid/hid-viewsonic.c @@ -24,7 +24,7 @@ /* Fixed report descriptor of PD1011 signature pad */ static __u8 pd1011_rdesc_fixed[] = { 0x05, 0x0D, /* Usage Page (Digitizer), */ - 0x09, 0x02, /* Usage (Pen), */ + 0x09, 0x01, /* Usage (Digitizer), */ 0xA1, 0x01, /* Collection (Application), */ 0x85, 0x02, /* Report ID (2), */ 0x09, 0x20, /* Usage (Stylus), */ diff --git a/drivers/hid/intel-ish-hid/ipc/hw-ish.h b/drivers/hid/intel-ish-hid/ipc/hw-ish.h index 07e3cbc86bef..e600dbf04dfc 100644 --- a/drivers/hid/intel-ish-hid/ipc/hw-ish.h +++ b/drivers/hid/intel-ish-hid/ipc/hw-ish.h @@ -30,6 +30,8 @@ #define TGL_H_DEVICE_ID 0x43FC #define ADL_S_DEVICE_ID 0x7AF8 #define ADL_P_DEVICE_ID 0x51FC +#define ADL_N_DEVICE_ID 0x54FC +#define RPL_S_DEVICE_ID 0x7A78 #define REVISION_ID_CHT_A0 0x6 #define REVISION_ID_CHT_Ax_SI 0x0 diff --git a/drivers/hid/intel-ish-hid/ipc/pci-ish.c b/drivers/hid/intel-ish-hid/ipc/pci-ish.c index 8e9d9450cb83..2c67ec17bec6 100644 --- a/drivers/hid/intel-ish-hid/ipc/pci-ish.c +++ b/drivers/hid/intel-ish-hid/ipc/pci-ish.c @@ -41,6 +41,8 @@ static const struct pci_device_id ish_pci_tbl[] = { {PCI_DEVICE(PCI_VENDOR_ID_INTEL, TGL_H_DEVICE_ID)}, {PCI_DEVICE(PCI_VENDOR_ID_INTEL, ADL_S_DEVICE_ID)}, {PCI_DEVICE(PCI_VENDOR_ID_INTEL, ADL_P_DEVICE_ID)}, + {PCI_DEVICE(PCI_VENDOR_ID_INTEL, ADL_N_DEVICE_ID)}, + {PCI_DEVICE(PCI_VENDOR_ID_INTEL, RPL_S_DEVICE_ID)}, {0, } }; MODULE_DEVICE_TABLE(pci, ish_pci_tbl); diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c index 066c567dbaa2..620fe74f5676 100644 --- a/drivers/hid/wacom_sys.c +++ b/drivers/hid/wacom_sys.c @@ -1777,7 +1777,7 @@ static int __wacom_initialize_battery(struct wacom *wacom, bat_desc->get_property = wacom_battery_get_property; sprintf(battery->bat_name, "wacom_battery_%ld", n); bat_desc->name = battery->bat_name; - bat_desc->type = POWER_SUPPLY_TYPE_USB; + bat_desc->type = POWER_SUPPLY_TYPE_BATTERY; bat_desc->use_for_apm = 0; ps_bat = devm_power_supply_register(dev, bat_desc, &psy_cfg); diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index a7176fc0635d..9470c2b0b529 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -1811,7 +1811,9 @@ int wacom_equivalent_usage(int usage) usage == WACOM_HID_WD_TOUCHSTRIP2 || usage == WACOM_HID_WD_TOUCHRING || usage == WACOM_HID_WD_TOUCHRINGSTATUS || - usage == WACOM_HID_WD_REPORT_VALID) { + usage == WACOM_HID_WD_REPORT_VALID || + usage == WACOM_HID_WD_BARRELSWITCH3 || + usage == WACOM_HID_WD_SEQUENCENUMBER) { return usage; } @@ -2196,8 +2198,11 @@ static void wacom_set_barrel_switch3_usage(struct wacom_wac *wacom_wac) if (!(features->quirks & WACOM_QUIRK_AESPEN) && wacom_wac->hid_data.barrelswitch && wacom_wac->hid_data.barrelswitch2 && - wacom_wac->hid_data.serialhi) + wacom_wac->hid_data.serialhi && + !wacom_wac->hid_data.barrelswitch3) { input_set_capability(input, EV_KEY, BTN_STYLUS3); + features->quirks |= WACOM_QUIRK_PEN_BUTTON3; + } } static void wacom_wac_pen_usage_mapping(struct hid_device *hdev, @@ -2261,6 +2266,9 @@ static void wacom_wac_pen_usage_mapping(struct hid_device *hdev, features->quirks |= WACOM_QUIRK_TOOLSERIAL; wacom_map_usage(input, usage, field, EV_MSC, MSC_SERIAL, 0); break; + case HID_DG_SCANTIME: + wacom_map_usage(input, usage, field, EV_MSC, MSC_TIMESTAMP, 0); + break; case WACOM_HID_WD_SENSE: features->quirks |= WACOM_QUIRK_SENSE; wacom_map_usage(input, usage, field, EV_KEY, BTN_TOOL_PEN, 0); @@ -2274,6 +2282,11 @@ static void wacom_wac_pen_usage_mapping(struct hid_device *hdev, input_set_capability(input, EV_KEY, BTN_TOOL_AIRBRUSH); wacom_map_usage(input, usage, field, EV_ABS, ABS_WHEEL, 0); break; + case WACOM_HID_WD_BARRELSWITCH3: + wacom_wac->hid_data.barrelswitch3 = true; + wacom_map_usage(input, usage, field, EV_KEY, BTN_STYLUS3, 0); + features->quirks &= ~WACOM_QUIRK_PEN_BUTTON3; + break; } } @@ -2390,6 +2403,14 @@ static void wacom_wac_pen_event(struct hid_device *hdev, struct hid_field *field case WACOM_HID_WD_REPORT_VALID: wacom_wac->is_invalid_bt_frame = !value; return; + case WACOM_HID_WD_BARRELSWITCH3: + wacom_wac->hid_data.barrelswitch3 = value; + return; + case WACOM_HID_WD_SEQUENCENUMBER: + if (wacom_wac->hid_data.sequence_number != value) + hid_warn(hdev, "Dropped %hu packets", (unsigned short)(value - wacom_wac->hid_data.sequence_number)); + wacom_wac->hid_data.sequence_number = value + 1; + return; } /* send pen events only when touch is up or forced out @@ -2442,12 +2463,15 @@ static void wacom_wac_pen_report(struct hid_device *hdev, if (!delay_pen_events(wacom_wac) && wacom_wac->tool[0]) { int id = wacom_wac->id[0]; - int sw_state = wacom_wac->hid_data.barrelswitch | - (wacom_wac->hid_data.barrelswitch2 << 1); - - input_report_key(input, BTN_STYLUS, sw_state == 1); - input_report_key(input, BTN_STYLUS2, sw_state == 2); - input_report_key(input, BTN_STYLUS3, sw_state == 3); + if (wacom_wac->features.quirks & WACOM_QUIRK_PEN_BUTTON3 && + wacom_wac->hid_data.barrelswitch & wacom_wac->hid_data.barrelswitch2) { + wacom_wac->hid_data.barrelswitch = 0; + wacom_wac->hid_data.barrelswitch2 = 0; + wacom_wac->hid_data.barrelswitch3 = 1; + } + input_report_key(input, BTN_STYLUS, wacom_wac->hid_data.barrelswitch); + input_report_key(input, BTN_STYLUS2, wacom_wac->hid_data.barrelswitch2); + input_report_key(input, BTN_STYLUS3, wacom_wac->hid_data.barrelswitch3); /* * Non-USI EMR tools should have their IDs mangled to @@ -2529,6 +2553,9 @@ static void wacom_wac_finger_usage_mapping(struct hid_device *hdev, field->logical_maximum = 255; } break; + case HID_DG_SCANTIME: + wacom_map_usage(input, usage, field, EV_MSC, MSC_TIMESTAMP, 0); + break; } } diff --git a/drivers/hid/wacom_wac.h b/drivers/hid/wacom_wac.h index 466b62cc16dc..fef1538005b5 100644 --- a/drivers/hid/wacom_wac.h +++ b/drivers/hid/wacom_wac.h @@ -86,6 +86,7 @@ #define WACOM_QUIRK_AESPEN 0x0004 #define WACOM_QUIRK_BATTERY 0x0008 #define WACOM_QUIRK_TOOLSERIAL 0x0010 +#define WACOM_QUIRK_PEN_BUTTON3 0x0020 /* device types */ #define WACOM_DEVICETYPE_NONE 0x0000 @@ -108,6 +109,7 @@ #define WACOM_HID_WD_DIGITIZERFNKEYS (WACOM_HID_UP_WACOMDIGITIZER | 0x39) #define WACOM_HID_WD_SERIALNUMBER (WACOM_HID_UP_WACOMDIGITIZER | 0x5b) #define WACOM_HID_WD_SERIALHI (WACOM_HID_UP_WACOMDIGITIZER | 0x5c) +#define WACOM_HID_WD_BARRELSWITCH3 (WACOM_HID_UP_WACOMDIGITIZER | 0x5d) #define WACOM_HID_WD_TOOLTYPE (WACOM_HID_UP_WACOMDIGITIZER | 0x77) #define WACOM_HID_WD_DISTANCE (WACOM_HID_UP_WACOMDIGITIZER | 0x0132) #define WACOM_HID_WD_TOUCHSTRIP (WACOM_HID_UP_WACOMDIGITIZER | 0x0136) @@ -115,6 +117,7 @@ #define WACOM_HID_WD_TOUCHRING (WACOM_HID_UP_WACOMDIGITIZER | 0x0138) #define WACOM_HID_WD_TOUCHRINGSTATUS (WACOM_HID_UP_WACOMDIGITIZER | 0x0139) #define WACOM_HID_WD_REPORT_VALID (WACOM_HID_UP_WACOMDIGITIZER | 0x01d0) +#define WACOM_HID_WD_SEQUENCENUMBER (WACOM_HID_UP_WACOMDIGITIZER | 0x0220) #define WACOM_HID_WD_ACCELEROMETER_X (WACOM_HID_UP_WACOMDIGITIZER | 0x0401) #define WACOM_HID_WD_ACCELEROMETER_Y (WACOM_HID_UP_WACOMDIGITIZER | 0x0402) #define WACOM_HID_WD_ACCELEROMETER_Z (WACOM_HID_UP_WACOMDIGITIZER | 0x0403) @@ -300,6 +303,7 @@ struct hid_data { bool tipswitch; bool barrelswitch; bool barrelswitch2; + bool barrelswitch3; bool serialhi; bool confidence; int x; @@ -320,6 +324,7 @@ struct hid_data { int bat_connected; int ps_connected; bool pad_input_event_flag; + unsigned short sequence_number; }; struct wacom_remote_data { diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c index 26d269ba947c..85a2142c9384 100644 --- a/drivers/hv/channel_mgmt.c +++ b/drivers/hv/channel_mgmt.c @@ -380,7 +380,7 @@ void vmbus_channel_map_relid(struct vmbus_channel *channel) * execute: * * (a) In the "normal (i.e., not resuming from hibernation)" path, - * the full barrier in smp_store_mb() guarantees that the store + * the full barrier in virt_store_mb() guarantees that the store * is propagated to all CPUs before the add_channel_work work * is queued. In turn, add_channel_work is queued before the * channel's ring buffer is allocated/initialized and the @@ -392,14 +392,14 @@ void vmbus_channel_map_relid(struct vmbus_channel *channel) * recv_int_page before retrieving the channel pointer from the * array of channels. * - * (b) In the "resuming from hibernation" path, the smp_store_mb() + * (b) In the "resuming from hibernation" path, the virt_store_mb() * guarantees that the store is propagated to all CPUs before * the VMBus connection is marked as ready for the resume event * (cf. check_ready_for_resume_event()). The interrupt handler * of the VMBus driver and vmbus_chan_sched() can not run before * vmbus_bus_resume() has completed execution (cf. resume_noirq). */ - smp_store_mb( + virt_store_mb( vmbus_connection.channels[channel->offermsg.child_relid], channel); } diff --git a/drivers/hv/hv_balloon.c b/drivers/hv/hv_balloon.c index 439f99b8b5de..3248b48f37f6 100644 --- a/drivers/hv/hv_balloon.c +++ b/drivers/hv/hv_balloon.c @@ -17,6 +17,7 @@ #include <linux/slab.h> #include <linux/kthread.h> #include <linux/completion.h> +#include <linux/count_zeros.h> #include <linux/memory_hotplug.h> #include <linux/memory.h> #include <linux/notifier.h> @@ -1130,6 +1131,7 @@ static void post_status(struct hv_dynmem_device *dm) struct dm_status status; unsigned long now = jiffies; unsigned long last_post = last_post_time; + unsigned long num_pages_avail, num_pages_committed; if (pressure_report_delay > 0) { --pressure_report_delay; @@ -1154,16 +1156,21 @@ static void post_status(struct hv_dynmem_device *dm) * num_pages_onlined) as committed to the host, otherwise it can try * asking us to balloon them out. */ - status.num_avail = si_mem_available(); - status.num_committed = vm_memory_committed() + + num_pages_avail = si_mem_available(); + num_pages_committed = vm_memory_committed() + dm->num_pages_ballooned + (dm->num_pages_added > dm->num_pages_onlined ? dm->num_pages_added - dm->num_pages_onlined : 0) + compute_balloon_floor(); - trace_balloon_status(status.num_avail, status.num_committed, + trace_balloon_status(num_pages_avail, num_pages_committed, vm_memory_committed(), dm->num_pages_ballooned, dm->num_pages_added, dm->num_pages_onlined); + + /* Convert numbers of pages into numbers of HV_HYP_PAGEs. */ + status.num_avail = num_pages_avail * NR_HV_HYP_PAGES_IN_PAGE; + status.num_committed = num_pages_committed * NR_HV_HYP_PAGES_IN_PAGE; + /* * If our transaction ID is no longer current, just don't * send the status. This can happen if we were interrupted @@ -1653,6 +1660,38 @@ static void disable_page_reporting(void) } } +static int ballooning_enabled(void) +{ + /* + * Disable ballooning if the page size is not 4k (HV_HYP_PAGE_SIZE), + * since currently it's unclear to us whether an unballoon request can + * make sure all page ranges are guest page size aligned. + */ + if (PAGE_SIZE != HV_HYP_PAGE_SIZE) { + pr_info("Ballooning disabled because page size is not 4096 bytes\n"); + return 0; + } + + return 1; +} + +static int hot_add_enabled(void) +{ + /* + * Disable hot add on ARM64, because we currently rely on + * memory_add_physaddr_to_nid() to get a node id of a hot add range, + * however ARM64's memory_add_physaddr_to_nid() always return 0 and + * DM_MEM_HOT_ADD_REQUEST doesn't have the NUMA node information for + * add_memory(). + */ + if (IS_ENABLED(CONFIG_ARM64)) { + pr_info("Memory hot add disabled on ARM64\n"); + return 0; + } + + return 1; +} + static int balloon_connect_vsp(struct hv_device *dev) { struct dm_version_request version_req; @@ -1724,8 +1763,8 @@ static int balloon_connect_vsp(struct hv_device *dev) * currently still requires the bits to be set, so we have to add code * to fail the host's hot-add and balloon up/down requests, if any. */ - cap_msg.caps.cap_bits.balloon = 1; - cap_msg.caps.cap_bits.hot_add = 1; + cap_msg.caps.cap_bits.balloon = ballooning_enabled(); + cap_msg.caps.cap_bits.hot_add = hot_add_enabled(); /* * Specify our alignment requirements as it relates diff --git a/drivers/hv/hv_common.c b/drivers/hv/hv_common.c index c1dd21d0d7ef..ae68298c0dca 100644 --- a/drivers/hv/hv_common.c +++ b/drivers/hv/hv_common.c @@ -20,6 +20,7 @@ #include <linux/panic_notifier.h> #include <linux/ptrace.h> #include <linux/slab.h> +#include <linux/dma-map-ops.h> #include <asm/hyperv-tlfs.h> #include <asm/mshyperv.h> @@ -218,6 +219,16 @@ bool hv_query_ext_cap(u64 cap_query) } EXPORT_SYMBOL_GPL(hv_query_ext_cap); +void hv_setup_dma_ops(struct device *dev, bool coherent) +{ + /* + * Hyper-V does not offer a vIOMMU in the guest + * VM, so pass 0/NULL for the IOMMU settings + */ + arch_setup_dma_ops(dev, 0, 0, NULL, coherent); +} +EXPORT_SYMBOL_GPL(hv_setup_dma_ops); + bool hv_is_hibernation_supported(void) { return !hv_root_partition && acpi_sleep_state_supported(ACPI_STATE_S4); diff --git a/drivers/hv/ring_buffer.c b/drivers/hv/ring_buffer.c index 71efacb90965..3d215d9dec43 100644 --- a/drivers/hv/ring_buffer.c +++ b/drivers/hv/ring_buffer.c @@ -439,7 +439,16 @@ int hv_ringbuffer_read(struct vmbus_channel *channel, static u32 hv_pkt_iter_avail(const struct hv_ring_buffer_info *rbi) { u32 priv_read_loc = rbi->priv_read_index; - u32 write_loc = READ_ONCE(rbi->ring_buffer->write_index); + u32 write_loc; + + /* + * The Hyper-V host writes the packet data, then uses + * store_release() to update the write_index. Use load_acquire() + * here to prevent loads of the packet data from being re-ordered + * before the read of the write_index and potentially getting + * stale data. + */ + write_loc = virt_load_acquire(&rbi->ring_buffer->write_index); if (write_loc >= priv_read_loc) return write_loc - priv_read_loc; diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index 60ee8b329f9e..14de17087864 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -77,8 +77,8 @@ static int hyperv_panic_event(struct notifier_block *nb, unsigned long val, /* * Hyper-V should be notified only once about a panic. If we will be - * doing hyperv_report_panic_msg() later with kmsg data, don't do - * the notification here. + * doing hv_kmsg_dump() with kmsg data later, don't do the notification + * here. */ if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE && hyperv_report_reg()) { @@ -100,8 +100,8 @@ static int hyperv_die_event(struct notifier_block *nb, unsigned long val, /* * Hyper-V should be notified only once about a panic. If we will be - * doing hyperv_report_panic_msg() later with kmsg data, don't do - * the notification here. + * doing hv_kmsg_dump() with kmsg data later, don't do the notification + * here. */ if (hyperv_report_reg()) hyperv_report_panic(regs, val, true); @@ -921,6 +921,21 @@ static int vmbus_probe(struct device *child_device) } /* + * vmbus_dma_configure -- Configure DMA coherence for VMbus device + */ +static int vmbus_dma_configure(struct device *child_device) +{ + /* + * On ARM64, propagate the DMA coherence setting from the top level + * VMbus ACPI device to the child VMbus device being added here. + * On x86/x64 coherence is assumed and these calls have no effect. + */ + hv_setup_dma_ops(child_device, + device_get_dma_attr(&hv_acpi_dev->dev) == DEV_DMA_COHERENT); + return 0; +} + +/* * vmbus_remove - Remove a vmbus device */ static void vmbus_remove(struct device *child_device) @@ -1040,6 +1055,7 @@ static struct bus_type hv_bus = { .remove = vmbus_remove, .probe = vmbus_probe, .uevent = vmbus_uevent, + .dma_configure = vmbus_dma_configure, .dev_groups = vmbus_dev_groups, .drv_groups = vmbus_drv_groups, .bus_groups = vmbus_bus_groups, @@ -1546,14 +1562,20 @@ static int vmbus_bus_init(void) if (ret) goto err_connect; + if (hv_is_isolation_supported()) + sysctl_record_panic_msg = 0; + /* * Only register if the crash MSRs are available */ if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE) { u64 hyperv_crash_ctl; /* - * Sysctl registration is not fatal, since by default - * reporting is enabled. + * Panic message recording (sysctl_record_panic_msg) + * is enabled by default in non-isolated guests and + * disabled by default in isolated guests; the panic + * message recording won't be available in isolated + * guests should the following registration fail. */ hv_ctl_table_hdr = register_sysctl_table(hv_root_table); if (!hv_ctl_table_hdr) @@ -2097,6 +2119,10 @@ int vmbus_device_register(struct hv_device *child_device_obj) child_device_obj->device.parent = &hv_acpi_dev->dev; child_device_obj->device.release = vmbus_device_release; + child_device_obj->device.dma_parms = &child_device_obj->dma_parms; + child_device_obj->device.dma_mask = &child_device_obj->dma_mask; + dma_set_mask(&child_device_obj->device, DMA_BIT_MASK(64)); + /* * Register with the LDM. This will kick off the driver/device * binding...which will eventually call vmbus_match() and vmbus_probe() @@ -2122,9 +2148,6 @@ int vmbus_device_register(struct hv_device *child_device_obj) } hv_debug_add_dev_dir(child_device_obj); - child_device_obj->device.dma_parms = &child_device_obj->dma_parms; - child_device_obj->device.dma_mask = &child_device_obj->dma_mask; - dma_set_mask(&child_device_obj->device, DMA_BIT_MASK(64)); return 0; err_kset_unregister: @@ -2428,6 +2451,21 @@ static int vmbus_acpi_add(struct acpi_device *device) hv_acpi_dev = device; + /* + * Older versions of Hyper-V for ARM64 fail to include the _CCA + * method on the top level VMbus device in the DSDT. But devices + * are hardware coherent in all current Hyper-V use cases, so fix + * up the ACPI device to behave as if _CCA is present and indicates + * hardware coherence. + */ + ACPI_COMPANION_SET(&device->dev, device); + if (IS_ENABLED(CONFIG_ACPI_CCA_REQUIRED) && + device_get_dma_attr(&device->dev) == DEV_DMA_NOT_SUPPORTED) { + pr_info("No ACPI _CCA found; assuming coherent device I/O\n"); + device->flags.cca_seen = true; + device->flags.coherent_dma = true; + } + result = acpi_walk_resources(device->handle, METHOD_NAME__CRS, vmbus_walk_resources, NULL); @@ -2780,10 +2818,15 @@ static void __exit vmbus_exit(void) if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE) { kmsg_dump_unregister(&hv_kmsg_dumper); unregister_die_notifier(&hyperv_die_block); - atomic_notifier_chain_unregister(&panic_notifier_list, - &hyperv_panic_block); } + /* + * The panic notifier is always registered, hence we should + * also unconditionally unregister it here as well. + */ + atomic_notifier_chain_unregister(&panic_notifier_list, + &hyperv_panic_block); + free_page((unsigned long)hv_panic_page); unregister_sysctl_table(hv_ctl_table_hdr); hv_ctl_table_hdr = NULL; diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig index 68a8a27ab3b7..590d3d550acb 100644 --- a/drivers/hwmon/Kconfig +++ b/drivers/hwmon/Kconfig @@ -256,11 +256,14 @@ config SENSORS_AHT10 will be called aht10. config SENSORS_AQUACOMPUTER_D5NEXT - tristate "Aquacomputer D5 Next watercooling pump" + tristate "Aquacomputer D5 Next, Octo, Farbwerk, and Farbwerk 360" depends on USB_HID + select CRC16 help - If you say yes here you get support for the Aquacomputer D5 Next - watercooling pump sensors. + If you say yes here you get support for sensors and fans of + the Aquacomputer D5 Next watercooling pump, Octo fan + controller, Farbwerk and Farbwerk 360 RGB controllers, where + available. This driver can also be built as a module. If so, the module will be called aquacomputer_d5next. @@ -415,6 +418,7 @@ config SENSORS_ATXP1 config SENSORS_BT1_PVT tristate "Baikal-T1 Process, Voltage, Temperature sensor driver" depends on MIPS_BAIKAL_T1 || COMPILE_TEST + select POLYNOMIAL help If you say yes here you get support for Baikal-T1 PVT sensor embedded into the SoC. @@ -498,6 +502,7 @@ config SENSORS_DS1621 config SENSORS_DELL_SMM tristate "Dell laptop SMM BIOS hwmon driver" depends on X86 + imply THERMAL help This hwmon driver adds support for reporting temperature of different sensors and controls the fans on Dell laptops via System Management @@ -814,6 +819,18 @@ config SENSORS_POWR1220 This driver can also be built as a module. If so, the module will be called powr1220. +config SENSORS_LAN966X + tristate "Microchip LAN966x Hardware Monitoring" + depends on SOC_LAN966 || COMPILE_TEST + select REGMAP + select POLYNOMIAL + help + If you say yes here you get support for temperature monitoring + on the Microchip LAN966x SoC. + + This driver can also be built as a module. If so, the module + will be called lan966x-hwmon. + config SENSORS_LINEAGE tristate "Lineage Compact Power Line Power Entry Module" depends on I2C @@ -960,7 +977,7 @@ config SENSORS_LTC4261 config SENSORS_LTQ_CPUTEMP bool "Lantiq cpu temperature sensor driver" - depends on LANTIQ + depends on SOC_XWAY help If you say yes here you get support for the temperature sensor inside your CPU. @@ -1248,6 +1265,7 @@ config SENSORS_LM75 temperature sensor chip, with models including: - Analog Devices ADT75 + - Atmel (now Microchip) AT30TS74 - Dallas Semiconductor DS75, DS1775 and DS7505 - Global Mixed-mode Technology (GMT) G751 - Maxim MAX6625 and MAX6626 @@ -1457,11 +1475,23 @@ config SENSORS_NCT6683 This driver can also be built as a module. If so, the module will be called nct6683. +config SENSORS_NCT6775_CORE + tristate + select REGMAP + help + This module contains common code shared by the platform and + i2c versions of the nct6775 driver; it is not useful on its + own. + + If built as a module, the module will be called + nct6775-core. + config SENSORS_NCT6775 - tristate "Nuvoton NCT6775F and compatibles" + tristate "Platform driver for Nuvoton NCT6775F and compatibles" depends on !PPC depends on ACPI_WMI || ACPI_WMI=n select HWMON_VID + select SENSORS_NCT6775_CORE help If you say yes here you get support for the hardware monitoring functionality of the Nuvoton NCT6106D, NCT6775F, NCT6776F, NCT6779D, @@ -1472,6 +1502,23 @@ config SENSORS_NCT6775 This driver can also be built as a module. If so, the module will be called nct6775. +config SENSORS_NCT6775_I2C + tristate "I2C driver for Nuvoton NCT6775F and compatibles" + depends on I2C + select REGMAP_I2C + select SENSORS_NCT6775_CORE + help + If you say yes here you get support for the hardware monitoring + functionality of the Nuvoton NCT6106D, NCT6775F, NCT6776F, NCT6779D, + NCT6791D, NCT6792D, NCT6793D, NCT6795D, NCT6796D, and compatible + Super-I/O chips via their I2C interface. + + If you're not building a kernel for a BMC, this is probably + not the driver you want (see CONFIG_SENSORS_NCT6775). + + This driver can also be built as a module. If so, the module + will be called nct6775-i2c. + config SENSORS_NCT7802 tristate "Nuvoton NCT7802Y" depends on I2C diff --git a/drivers/hwmon/Makefile b/drivers/hwmon/Makefile index 8a03289e2aa4..007e829d1d0d 100644 --- a/drivers/hwmon/Makefile +++ b/drivers/hwmon/Makefile @@ -100,6 +100,7 @@ obj-$(CONFIG_SENSORS_IT87) += it87.o obj-$(CONFIG_SENSORS_JC42) += jc42.o obj-$(CONFIG_SENSORS_K8TEMP) += k8temp.o obj-$(CONFIG_SENSORS_K10TEMP) += k10temp.o +obj-$(CONFIG_SENSORS_LAN966X) += lan966x-hwmon.o obj-$(CONFIG_SENSORS_LINEAGE) += lineage-pem.o obj-$(CONFIG_SENSORS_LOCHNAGAR) += lochnagar-hwmon.o obj-$(CONFIG_SENSORS_LM63) += lm63.o @@ -154,7 +155,10 @@ obj-$(CONFIG_SENSORS_MLXREG_FAN) += mlxreg-fan.o obj-$(CONFIG_SENSORS_MENF21BMC_HWMON) += menf21bmc_hwmon.o obj-$(CONFIG_SENSORS_MR75203) += mr75203.o obj-$(CONFIG_SENSORS_NCT6683) += nct6683.o +obj-$(CONFIG_SENSORS_NCT6775_CORE) += nct6775-core.o +nct6775-objs := nct6775-platform.o obj-$(CONFIG_SENSORS_NCT6775) += nct6775.o +obj-$(CONFIG_SENSORS_NCT6775_I2C) += nct6775-i2c.o obj-$(CONFIG_SENSORS_NCT7802) += nct7802.o obj-$(CONFIG_SENSORS_NCT7904) += nct7904.o obj-$(CONFIG_SENSORS_NPCM7XX) += npcm750-pwm-fan.o diff --git a/drivers/hwmon/acpi_power_meter.c b/drivers/hwmon/acpi_power_meter.c index c405a5869581..d2545a1be9fc 100644 --- a/drivers/hwmon/acpi_power_meter.c +++ b/drivers/hwmon/acpi_power_meter.c @@ -481,7 +481,7 @@ static struct sensor_template meter_attrs[] = { RO_SENSOR_TEMPLATE("power1_average_interval_max", show_val, 1), RO_SENSOR_TEMPLATE("power1_is_battery", show_val, 5), RW_SENSOR_TEMPLATE(POWER_AVG_INTERVAL_NAME, show_avg_interval, - set_avg_interval, 0), + set_avg_interval, 0), {}, }; @@ -530,6 +530,7 @@ static void remove_domain_devices(struct acpi_power_meter_resource *resource) for (i = 0; i < resource->num_domain_devices; i++) { struct acpi_device *obj = resource->domain_devices[i]; + if (!obj) continue; @@ -580,7 +581,7 @@ static int read_domain_devices(struct acpi_power_meter_resource *resource) } resource->holders_dir = kobject_create_and_add("measures", - &resource->acpi_dev->dev.kobj); + &resource->acpi_dev->dev.kobj); if (!resource->holders_dir) { res = -ENOMEM; goto exit_free; @@ -590,7 +591,7 @@ static int read_domain_devices(struct acpi_power_meter_resource *resource) for (i = 0; i < pss->package.count; i++) { struct acpi_device *obj; - union acpi_object *element = &(pss->package.elements[i]); + union acpi_object *element = &pss->package.elements[i]; /* Refuse non-references */ if (element->type != ACPI_TYPE_LOCAL_REFERENCE) @@ -603,7 +604,7 @@ static int read_domain_devices(struct acpi_power_meter_resource *resource) continue; res = sysfs_create_link(resource->holders_dir, &obj->dev.kobj, - kobject_name(&obj->dev.kobj)); + kobject_name(&obj->dev.kobj)); if (res) { acpi_dev_put(obj); resource->domain_devices[i] = NULL; @@ -788,7 +789,7 @@ static int read_capabilities(struct acpi_power_meter_resource *resource) str = &resource->model_number; for (i = 11; i < 14; i++) { - union acpi_object *element = &(pss->package.elements[i]); + union acpi_object *element = &pss->package.elements[i]; if (element->type != ACPI_TYPE_STRING) { res = -EINVAL; @@ -868,8 +869,7 @@ static int acpi_power_meter_add(struct acpi_device *device) if (!device) return -EINVAL; - resource = kzalloc(sizeof(struct acpi_power_meter_resource), - GFP_KERNEL); + resource = kzalloc(sizeof(*resource), GFP_KERNEL); if (!resource) return -ENOMEM; @@ -884,7 +884,8 @@ static int acpi_power_meter_add(struct acpi_device *device) if (res) goto exit_free; - resource->trip[0] = resource->trip[1] = -1; + resource->trip[0] = -1; + resource->trip[1] = -1; res = setup_attrs(resource); if (res) diff --git a/drivers/hwmon/adt7470.c b/drivers/hwmon/adt7470.c index fb6d14d213a1..c67cd037a93f 100644 --- a/drivers/hwmon/adt7470.c +++ b/drivers/hwmon/adt7470.c @@ -19,6 +19,7 @@ #include <linux/log2.h> #include <linux/kthread.h> #include <linux/regmap.h> +#include <linux/sched.h> #include <linux/slab.h> #include <linux/util_macros.h> @@ -294,11 +295,10 @@ static int adt7470_update_thread(void *p) adt7470_read_temperatures(data); mutex_unlock(&data->lock); - set_current_state(TASK_INTERRUPTIBLE); if (kthread_should_stop()) break; - schedule_timeout(msecs_to_jiffies(data->auto_update_interval)); + schedule_timeout_interruptible(msecs_to_jiffies(data->auto_update_interval)); } return 0; diff --git a/drivers/hwmon/adt7475.c b/drivers/hwmon/adt7475.c index 9d5b019651f2..ac480e6e4818 100644 --- a/drivers/hwmon/adt7475.c +++ b/drivers/hwmon/adt7475.c @@ -112,6 +112,8 @@ #define CONFIG3_THERM 0x02 #define CONFIG4_PINFUNC 0x03 +#define CONFIG4_THERM 0x01 +#define CONFIG4_SMBALERT 0x02 #define CONFIG4_MAXDUTY 0x08 #define CONFIG4_ATTN_IN10 0x30 #define CONFIG4_ATTN_IN43 0xC0 @@ -1460,6 +1462,96 @@ static int adt7475_update_limits(struct i2c_client *client) return 0; } +static int load_config3(const struct i2c_client *client, const char *propname) +{ + const char *function; + u8 config3; + int ret; + + ret = of_property_read_string(client->dev.of_node, propname, &function); + if (!ret) { + ret = adt7475_read(REG_CONFIG3); + if (ret < 0) + return ret; + + config3 = ret & ~CONFIG3_SMBALERT; + if (!strcmp("pwm2", function)) + ; + else if (!strcmp("smbalert#", function)) + config3 |= CONFIG3_SMBALERT; + else + return -EINVAL; + + return i2c_smbus_write_byte_data(client, REG_CONFIG3, config3); + } + + return 0; +} + +static int load_config4(const struct i2c_client *client, const char *propname) +{ + const char *function; + u8 config4; + int ret; + + ret = of_property_read_string(client->dev.of_node, propname, &function); + if (!ret) { + ret = adt7475_read(REG_CONFIG4); + if (ret < 0) + return ret; + + config4 = ret & ~CONFIG4_PINFUNC; + + if (!strcmp("tach4", function)) + ; + else if (!strcmp("therm#", function)) + config4 |= CONFIG4_THERM; + else if (!strcmp("smbalert#", function)) + config4 |= CONFIG4_SMBALERT; + else if (!strcmp("gpio", function)) + config4 |= CONFIG4_PINFUNC; + else + return -EINVAL; + + return i2c_smbus_write_byte_data(client, REG_CONFIG4, config4); + } + + return 0; +} + +static int load_config(const struct i2c_client *client, enum chips chip) +{ + int err; + const char *prop1, *prop2; + + switch (chip) { + case adt7473: + case adt7475: + prop1 = "adi,pin5-function"; + prop2 = "adi,pin9-function"; + break; + case adt7476: + case adt7490: + prop1 = "adi,pin10-function"; + prop2 = "adi,pin14-function"; + break; + } + + err = load_config3(client, prop1); + if (err) { + dev_err(&client->dev, "failed to configure %s\n", prop1); + return err; + } + + err = load_config4(client, prop2); + if (err) { + dev_err(&client->dev, "failed to configure %s\n", prop2); + return err; + } + + return 0; +} + static int set_property_bit(const struct i2c_client *client, char *property, u8 *config, u8 bit_index) { @@ -1477,12 +1569,12 @@ static int set_property_bit(const struct i2c_client *client, char *property, return ret; } -static int load_attenuators(const struct i2c_client *client, int chip, +static int load_attenuators(const struct i2c_client *client, enum chips chip, struct adt7475_data *data) { - int ret; - - if (chip == adt7476 || chip == adt7490) { + switch (chip) { + case adt7476: + case adt7490: set_property_bit(client, "adi,bypass-attenuator-in0", &data->config4, 4); set_property_bit(client, "adi,bypass-attenuator-in1", @@ -1492,18 +1584,15 @@ static int load_attenuators(const struct i2c_client *client, int chip, set_property_bit(client, "adi,bypass-attenuator-in4", &data->config4, 7); - ret = i2c_smbus_write_byte_data(client, REG_CONFIG4, - data->config4); - if (ret < 0) - return ret; - } else if (chip == adt7473 || chip == adt7475) { + return i2c_smbus_write_byte_data(client, REG_CONFIG4, + data->config4); + case adt7473: + case adt7475: set_property_bit(client, "adi,bypass-attenuator-in1", &data->config2, 5); - ret = i2c_smbus_write_byte_data(client, REG_CONFIG2, - data->config2); - if (ret < 0) - return ret; + return i2c_smbus_write_byte_data(client, REG_CONFIG2, + data->config2); } return 0; @@ -1585,6 +1674,10 @@ static int adt7475_probe(struct i2c_client *client) revision = adt7475_read(REG_DEVID2) & 0x07; } + ret = load_config(client, chip); + if (ret) + return ret; + config3 = adt7475_read(REG_CONFIG3); /* Pin PWM2 may alternatively be used for ALERT output */ if (!(config3 & CONFIG3_SMBALERT)) diff --git a/drivers/hwmon/aquacomputer_d5next.c b/drivers/hwmon/aquacomputer_d5next.c index 525809cf7c95..a0e69f7ece36 100644 --- a/drivers/hwmon/aquacomputer_d5next.c +++ b/drivers/hwmon/aquacomputer_d5next.c @@ -1,30 +1,37 @@ // SPDX-License-Identifier: GPL-2.0+ /* - * hwmon driver for Aquacomputer devices (D5 Next, Farbwerk 360) + * hwmon driver for Aquacomputer devices (D5 Next, Farbwerk, Farbwerk 360, Octo) * * Aquacomputer devices send HID reports (with ID 0x01) every second to report * sensor values. * * Copyright 2021 Aleksa Savic <savicaleksa83@gmail.com> + * Copyright 2022 Jack Doan <me@jackdoan.com> */ +#include <linux/crc16.h> #include <linux/debugfs.h> #include <linux/hid.h> #include <linux/hwmon.h> #include <linux/jiffies.h> #include <linux/module.h> +#include <linux/mutex.h> #include <linux/seq_file.h> #include <asm/unaligned.h> #define USB_VENDOR_ID_AQUACOMPUTER 0x0c70 +#define USB_PRODUCT_ID_FARBWERK 0xf00a #define USB_PRODUCT_ID_D5NEXT 0xf00e #define USB_PRODUCT_ID_FARBWERK360 0xf010 +#define USB_PRODUCT_ID_OCTO 0xf011 -enum kinds { d5next, farbwerk360 }; +enum kinds { d5next, farbwerk, farbwerk360, octo }; static const char *const aqc_device_names[] = { [d5next] = "d5next", - [farbwerk360] = "farbwerk360" + [farbwerk] = "farbwerk", + [farbwerk360] = "farbwerk360", + [octo] = "octo" }; #define DRIVER_NAME "aquacomputer_d5next" @@ -35,6 +42,18 @@ static const char *const aqc_device_names[] = { #define SERIAL_SECOND_PART 5 #define FIRMWARE_VERSION 13 +#define CTRL_REPORT_ID 0x03 + +/* The HID report that the official software always sends + * after writing values, currently same for all devices + */ +#define SECONDARY_CTRL_REPORT_ID 0x02 +#define SECONDARY_CTRL_REPORT_SIZE 0x0B + +static u8 secondary_ctrl_report[] = { + 0x02, 0x00, 0x00, 0x00, 0x02, 0x00, 0x00, 0x00, 0x00, 0x34, 0xC6 +}; + /* Register offsets for the D5 Next pump */ #define D5NEXT_POWER_CYCLES 24 @@ -53,14 +72,46 @@ static const char *const aqc_device_names[] = { #define D5NEXT_PUMP_CURRENT 112 #define D5NEXT_FAN_CURRENT 99 +/* Register offsets for the Farbwerk RGB controller */ +#define FARBWERK_NUM_SENSORS 4 +#define FARBWERK_SENSOR_START 0x2f +#define FARBWERK_SENSOR_SIZE 0x02 +#define FARBWERK_SENSOR_DISCONNECTED 0x7FFF + /* Register offsets for the Farbwerk 360 RGB controller */ #define FARBWERK360_NUM_SENSORS 4 -#define FARBWERK360_SENSOR_START 0x32 +#define FARBWERK360_SENSOR_START 0x32 #define FARBWERK360_SENSOR_SIZE 0x02 #define FARBWERK360_SENSOR_DISCONNECTED 0x7FFF +/* Register offsets for the Octo fan controller */ +#define OCTO_POWER_CYCLES 0x18 +#define OCTO_NUM_FANS 8 +#define OCTO_FAN_PERCENT_OFFSET 0x00 +#define OCTO_FAN_VOLTAGE_OFFSET 0x02 +#define OCTO_FAN_CURRENT_OFFSET 0x04 +#define OCTO_FAN_POWER_OFFSET 0x06 +#define OCTO_FAN_SPEED_OFFSET 0x08 + +static u8 octo_sensor_fan_offsets[] = { 0x7D, 0x8A, 0x97, 0xA4, 0xB1, 0xBE, 0xCB, 0xD8 }; + +#define OCTO_NUM_SENSORS 4 +#define OCTO_SENSOR_START 0x3D +#define OCTO_SENSOR_SIZE 0x02 +#define OCTO_SENSOR_DISCONNECTED 0x7FFF + +#define OCTO_CTRL_REPORT_SIZE 0x65F +#define OCTO_CTRL_REPORT_CHECKSUM_OFFSET 0x65D +#define OCTO_CTRL_REPORT_CHECKSUM_START 0x01 +#define OCTO_CTRL_REPORT_CHECKSUM_LENGTH 0x65C + +/* Fan speed registers in Octo control report (from 0-100%) */ +static u16 octo_ctrl_fan_offsets[] = { 0x5B, 0xB0, 0x105, 0x15A, 0x1AF, 0x204, 0x259, 0x2AE }; + /* Labels for D5 Next */ -#define L_D5NEXT_COOLANT_TEMP "Coolant temp" +static const char *const label_d5next_temp[] = { + "Coolant temp" +}; static const char *const label_d5next_speeds[] = { "Pump speed", @@ -83,7 +134,7 @@ static const char *const label_d5next_current[] = { "Fan current" }; -/* Labels for Farbwerk 360 temperature sensors */ +/* Labels for Farbwerk, Farbwerk 360 and Octo temperature sensors */ static const char *const label_temp_sensors[] = { "Sensor 1", "Sensor 2", @@ -91,32 +142,182 @@ static const char *const label_temp_sensors[] = { "Sensor 4" }; +/* Labels for Octo */ +static const char *const label_fan_speed[] = { + "Fan 1 speed", + "Fan 2 speed", + "Fan 3 speed", + "Fan 4 speed", + "Fan 5 speed", + "Fan 6 speed", + "Fan 7 speed", + "Fan 8 speed" +}; + +static const char *const label_fan_power[] = { + "Fan 1 power", + "Fan 2 power", + "Fan 3 power", + "Fan 4 power", + "Fan 5 power", + "Fan 6 power", + "Fan 7 power", + "Fan 8 power" +}; + +static const char *const label_fan_voltage[] = { + "Fan 1 voltage", + "Fan 2 voltage", + "Fan 3 voltage", + "Fan 4 voltage", + "Fan 5 voltage", + "Fan 6 voltage", + "Fan 7 voltage", + "Fan 8 voltage" +}; + +static const char *const label_fan_current[] = { + "Fan 1 current", + "Fan 2 current", + "Fan 3 current", + "Fan 4 current", + "Fan 5 current", + "Fan 6 current", + "Fan 7 current", + "Fan 8 current" +}; + struct aqc_data { struct hid_device *hdev; struct device *hwmon_dev; struct dentry *debugfs; + struct mutex mutex; /* Used for locking access when reading and writing PWM values */ enum kinds kind; const char *name; + int buffer_size; + u8 *buffer; + int checksum_start; + int checksum_length; + int checksum_offset; + /* General info, same across all devices */ u32 serial_number[2]; u16 firmware_version; - /* D5 Next specific - how many times the device was powered on */ + /* How many times the device was powered on */ u32 power_cycles; /* Sensor values */ s32 temp_input[4]; - u16 speed_input[2]; - u32 power_input[2]; - u16 voltage_input[3]; - u16 current_input[2]; + u16 speed_input[8]; + u32 power_input[8]; + u16 voltage_input[8]; + u16 current_input[8]; + + /* Label values */ + const char *const *temp_label; + const char *const *speed_label; + const char *const *power_label; + const char *const *voltage_label; + const char *const *current_label; unsigned long updated; }; -static umode_t aqc_is_visible(const void *data, enum hwmon_sensor_types type, u32 attr, - int channel) +/* Converts from centi-percent */ +static int aqc_percent_to_pwm(u16 val) +{ + return DIV_ROUND_CLOSEST(val * 255, 100 * 100); +} + +/* Converts to centi-percent */ +static int aqc_pwm_to_percent(long val) +{ + if (val < 0 || val > 255) + return -EINVAL; + + return DIV_ROUND_CLOSEST(val * 100 * 100, 255); +} + +/* Expects the mutex to be locked */ +static int aqc_get_ctrl_data(struct aqc_data *priv) +{ + int ret; + + memset(priv->buffer, 0x00, priv->buffer_size); + ret = hid_hw_raw_request(priv->hdev, CTRL_REPORT_ID, priv->buffer, priv->buffer_size, + HID_FEATURE_REPORT, HID_REQ_GET_REPORT); + if (ret < 0) + ret = -ENODATA; + + return ret; +} + +/* Expects the mutex to be locked */ +static int aqc_send_ctrl_data(struct aqc_data *priv) +{ + int ret; + u16 checksum; + + /* Init and xorout value for CRC-16/USB is 0xffff */ + checksum = crc16(0xffff, priv->buffer + priv->checksum_start, priv->checksum_length); + checksum ^= 0xffff; + + /* Place the new checksum at the end of the report */ + put_unaligned_be16(checksum, priv->buffer + priv->checksum_offset); + + /* Send the patched up report back to the device */ + ret = hid_hw_raw_request(priv->hdev, CTRL_REPORT_ID, priv->buffer, priv->buffer_size, + HID_FEATURE_REPORT, HID_REQ_SET_REPORT); + if (ret < 0) + return ret; + + /* The official software sends this report after every change, so do it here as well */ + ret = hid_hw_raw_request(priv->hdev, SECONDARY_CTRL_REPORT_ID, secondary_ctrl_report, + SECONDARY_CTRL_REPORT_SIZE, HID_FEATURE_REPORT, + HID_REQ_SET_REPORT); + return ret; +} + +/* Refreshes the control buffer and returns value at offset */ +static int aqc_get_ctrl_val(struct aqc_data *priv, int offset) +{ + int ret; + + mutex_lock(&priv->mutex); + + ret = aqc_get_ctrl_data(priv); + if (ret < 0) + goto unlock_and_return; + + ret = get_unaligned_be16(priv->buffer + offset); + +unlock_and_return: + mutex_unlock(&priv->mutex); + return ret; +} + +static int aqc_set_ctrl_val(struct aqc_data *priv, int offset, long val) +{ + int ret; + + mutex_lock(&priv->mutex); + + ret = aqc_get_ctrl_data(priv); + if (ret < 0) + goto unlock_and_return; + + put_unaligned_be16((u16)val, priv->buffer + offset); + + ret = aqc_send_ctrl_data(priv); + +unlock_and_return: + mutex_unlock(&priv->mutex); + return ret; +} + +static umode_t aqc_is_visible(const void *data, enum hwmon_sensor_types type, u32 attr, int channel) { const struct aqc_data *priv = data; @@ -127,18 +328,49 @@ static umode_t aqc_is_visible(const void *data, enum hwmon_sensor_types type, u3 if (channel == 0) return 0444; break; + case farbwerk: case farbwerk360: + case octo: return 0444; default: break; } break; + case hwmon_pwm: + switch (priv->kind) { + case octo: + switch (attr) { + case hwmon_pwm_input: + return 0644; + default: + break; + } + break; + default: + break; + } + break; case hwmon_fan: case hwmon_power: - case hwmon_in: case hwmon_curr: switch (priv->kind) { case d5next: + if (channel < 2) + return 0444; + break; + case octo: + return 0444; + default: + break; + } + break; + case hwmon_in: + switch (priv->kind) { + case d5next: + if (channel < 3) + return 0444; + break; + case octo: return 0444; default: break; @@ -154,6 +386,7 @@ static umode_t aqc_is_visible(const void *data, enum hwmon_sensor_types type, u3 static int aqc_read(struct device *dev, enum hwmon_sensor_types type, u32 attr, int channel, long *val) { + int ret; struct aqc_data *priv = dev_get_drvdata(dev); if (time_after(jiffies, priv->updated + STATUS_UPDATE_INTERVAL)) @@ -172,6 +405,19 @@ static int aqc_read(struct device *dev, enum hwmon_sensor_types type, u32 attr, case hwmon_power: *val = priv->power_input[channel]; break; + case hwmon_pwm: + switch (priv->kind) { + case octo: + ret = aqc_get_ctrl_val(priv, octo_ctrl_fan_offsets[channel]); + if (ret < 0) + return ret; + + *val = aqc_percent_to_pwm(ret); + break; + default: + break; + } + break; case hwmon_in: *val = priv->voltage_input[channel]; break; @@ -192,48 +438,51 @@ static int aqc_read_string(struct device *dev, enum hwmon_sensor_types type, u32 switch (type) { case hwmon_temp: - switch (priv->kind) { - case d5next: - *str = L_D5NEXT_COOLANT_TEMP; - break; - case farbwerk360: - *str = label_temp_sensors[channel]; - break; - default: - break; - } + *str = priv->temp_label[channel]; break; case hwmon_fan: - switch (priv->kind) { - case d5next: - *str = label_d5next_speeds[channel]; - break; - default: - break; - } + *str = priv->speed_label[channel]; break; case hwmon_power: - switch (priv->kind) { - case d5next: - *str = label_d5next_power[channel]; - break; - default: - break; - } + *str = priv->power_label[channel]; break; case hwmon_in: - switch (priv->kind) { - case d5next: - *str = label_d5next_voltages[channel]; - break; - default: - break; - } + *str = priv->voltage_label[channel]; break; case hwmon_curr: - switch (priv->kind) { - case d5next: - *str = label_d5next_current[channel]; + *str = priv->current_label[channel]; + break; + default: + return -EOPNOTSUPP; + } + + return 0; +} + +static int aqc_write(struct device *dev, enum hwmon_sensor_types type, u32 attr, int channel, + long val) +{ + int ret, pwm_value; + struct aqc_data *priv = dev_get_drvdata(dev); + + switch (type) { + case hwmon_pwm: + switch (attr) { + case hwmon_pwm_input: + switch (priv->kind) { + case octo: + pwm_value = aqc_pwm_to_percent(val); + if (pwm_value < 0) + return pwm_value; + + ret = aqc_set_ctrl_val(priv, octo_ctrl_fan_offsets[channel], + pwm_value); + if (ret < 0) + return ret; + break; + default: + break; + } break; default: break; @@ -250,6 +499,7 @@ static const struct hwmon_ops aqc_hwmon_ops = { .is_visible = aqc_is_visible, .read = aqc_read, .read_string = aqc_read_string, + .write = aqc_write }; static const struct hwmon_channel_info *aqc_info[] = { @@ -260,16 +510,48 @@ static const struct hwmon_channel_info *aqc_info[] = { HWMON_T_INPUT | HWMON_T_LABEL), HWMON_CHANNEL_INFO(fan, HWMON_F_INPUT | HWMON_F_LABEL, + HWMON_F_INPUT | HWMON_F_LABEL, + HWMON_F_INPUT | HWMON_F_LABEL, + HWMON_F_INPUT | HWMON_F_LABEL, + HWMON_F_INPUT | HWMON_F_LABEL, + HWMON_F_INPUT | HWMON_F_LABEL, + HWMON_F_INPUT | HWMON_F_LABEL, HWMON_F_INPUT | HWMON_F_LABEL), HWMON_CHANNEL_INFO(power, HWMON_P_INPUT | HWMON_P_LABEL, + HWMON_P_INPUT | HWMON_P_LABEL, + HWMON_P_INPUT | HWMON_P_LABEL, + HWMON_P_INPUT | HWMON_P_LABEL, + HWMON_P_INPUT | HWMON_P_LABEL, + HWMON_P_INPUT | HWMON_P_LABEL, + HWMON_P_INPUT | HWMON_P_LABEL, HWMON_P_INPUT | HWMON_P_LABEL), + HWMON_CHANNEL_INFO(pwm, + HWMON_PWM_INPUT, + HWMON_PWM_INPUT, + HWMON_PWM_INPUT, + HWMON_PWM_INPUT, + HWMON_PWM_INPUT, + HWMON_PWM_INPUT, + HWMON_PWM_INPUT, + HWMON_PWM_INPUT), HWMON_CHANNEL_INFO(in, HWMON_I_INPUT | HWMON_I_LABEL, HWMON_I_INPUT | HWMON_I_LABEL, + HWMON_I_INPUT | HWMON_I_LABEL, + HWMON_I_INPUT | HWMON_I_LABEL, + HWMON_I_INPUT | HWMON_I_LABEL, + HWMON_I_INPUT | HWMON_I_LABEL, + HWMON_I_INPUT | HWMON_I_LABEL, HWMON_I_INPUT | HWMON_I_LABEL), HWMON_CHANNEL_INFO(curr, HWMON_C_INPUT | HWMON_C_LABEL, + HWMON_C_INPUT | HWMON_C_LABEL, + HWMON_C_INPUT | HWMON_C_LABEL, + HWMON_C_INPUT | HWMON_C_LABEL, + HWMON_C_INPUT | HWMON_C_LABEL, + HWMON_C_INPUT | HWMON_C_LABEL, + HWMON_C_INPUT | HWMON_C_LABEL, HWMON_C_INPUT | HWMON_C_LABEL), NULL }; @@ -279,8 +561,7 @@ static const struct hwmon_chip_info aqc_chip_info = { .info = aqc_info, }; -static int aqc_raw_event(struct hid_device *hdev, struct hid_report *report, u8 *data, - int size) +static int aqc_raw_event(struct hid_device *hdev, struct hid_report *report, u8 *data, int size) { int i, sensor_value; struct aqc_data *priv; @@ -315,6 +596,17 @@ static int aqc_raw_event(struct hid_device *hdev, struct hid_report *report, u8 priv->current_input[0] = get_unaligned_be16(data + D5NEXT_PUMP_CURRENT); priv->current_input[1] = get_unaligned_be16(data + D5NEXT_FAN_CURRENT); break; + case farbwerk: + /* Temperature sensor readings */ + for (i = 0; i < FARBWERK_NUM_SENSORS; i++) { + sensor_value = get_unaligned_be16(data + FARBWERK_SENSOR_START + + i * FARBWERK_SENSOR_SIZE); + if (sensor_value == FARBWERK_SENSOR_DISCONNECTED) + priv->temp_input[i] = -ENODATA; + else + priv->temp_input[i] = sensor_value * 10; + } + break; case farbwerk360: /* Temperature sensor readings */ for (i = 0; i < FARBWERK360_NUM_SENSORS; i++) { @@ -326,6 +618,35 @@ static int aqc_raw_event(struct hid_device *hdev, struct hid_report *report, u8 priv->temp_input[i] = sensor_value * 10; } break; + case octo: + priv->power_cycles = get_unaligned_be32(data + OCTO_POWER_CYCLES); + + /* Fan speed and related readings */ + for (i = 0; i < OCTO_NUM_FANS; i++) { + priv->speed_input[i] = + get_unaligned_be16(data + octo_sensor_fan_offsets[i] + + OCTO_FAN_SPEED_OFFSET); + priv->power_input[i] = + get_unaligned_be16(data + octo_sensor_fan_offsets[i] + + OCTO_FAN_POWER_OFFSET) * 10000; + priv->voltage_input[i] = + get_unaligned_be16(data + octo_sensor_fan_offsets[i] + + OCTO_FAN_VOLTAGE_OFFSET) * 10; + priv->current_input[i] = + get_unaligned_be16(data + octo_sensor_fan_offsets[i] + + OCTO_FAN_CURRENT_OFFSET); + } + + /* Temperature sensor readings */ + for (i = 0; i < OCTO_NUM_SENSORS; i++) { + sensor_value = get_unaligned_be16(data + OCTO_SENSOR_START + + i * OCTO_SENSOR_SIZE); + if (sensor_value == OCTO_SENSOR_DISCONNECTED) + priv->temp_input[i] = -ENODATA; + else + priv->temp_input[i] = sensor_value * 10; + } + break; default: break; } @@ -378,8 +699,14 @@ static void aqc_debugfs_init(struct aqc_data *priv) debugfs_create_file("serial_number", 0444, priv->debugfs, priv, &serial_number_fops); debugfs_create_file("firmware_version", 0444, priv->debugfs, priv, &firmware_version_fops); - if (priv->kind == d5next) + switch (priv->kind) { + case d5next: + case octo: debugfs_create_file("power_cycles", 0444, priv->debugfs, priv, &power_cycles_fops); + break; + default: + break; + } } #else @@ -419,9 +746,35 @@ static int aqc_probe(struct hid_device *hdev, const struct hid_device_id *id) switch (hdev->product) { case USB_PRODUCT_ID_D5NEXT: priv->kind = d5next; + + priv->temp_label = label_d5next_temp; + priv->speed_label = label_d5next_speeds; + priv->power_label = label_d5next_power; + priv->voltage_label = label_d5next_voltages; + priv->current_label = label_d5next_current; + break; + case USB_PRODUCT_ID_FARBWERK: + priv->kind = farbwerk; + + priv->temp_label = label_temp_sensors; break; case USB_PRODUCT_ID_FARBWERK360: priv->kind = farbwerk360; + + priv->temp_label = label_temp_sensors; + break; + case USB_PRODUCT_ID_OCTO: + priv->kind = octo; + priv->buffer_size = OCTO_CTRL_REPORT_SIZE; + priv->checksum_start = OCTO_CTRL_REPORT_CHECKSUM_START; + priv->checksum_length = OCTO_CTRL_REPORT_CHECKSUM_LENGTH; + priv->checksum_offset = OCTO_CTRL_REPORT_CHECKSUM_OFFSET; + + priv->temp_label = label_temp_sensors; + priv->speed_label = label_fan_speed; + priv->power_label = label_fan_power; + priv->voltage_label = label_fan_voltage; + priv->current_label = label_fan_current; break; default: break; @@ -429,6 +782,14 @@ static int aqc_probe(struct hid_device *hdev, const struct hid_device_id *id) priv->name = aqc_device_names[priv->kind]; + priv->buffer = devm_kzalloc(&hdev->dev, priv->buffer_size, GFP_KERNEL); + if (!priv->buffer) { + ret = -ENOMEM; + goto fail_and_close; + } + + mutex_init(&priv->mutex); + priv->hwmon_dev = hwmon_device_register_with_info(&hdev->dev, priv->name, priv, &aqc_chip_info, NULL); @@ -461,7 +822,9 @@ static void aqc_remove(struct hid_device *hdev) static const struct hid_device_id aqc_table[] = { { HID_USB_DEVICE(USB_VENDOR_ID_AQUACOMPUTER, USB_PRODUCT_ID_D5NEXT) }, + { HID_USB_DEVICE(USB_VENDOR_ID_AQUACOMPUTER, USB_PRODUCT_ID_FARBWERK) }, { HID_USB_DEVICE(USB_VENDOR_ID_AQUACOMPUTER, USB_PRODUCT_ID_FARBWERK360) }, + { HID_USB_DEVICE(USB_VENDOR_ID_AQUACOMPUTER, USB_PRODUCT_ID_OCTO) }, { } }; @@ -491,4 +854,5 @@ module_exit(aqc_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Aleksa Savic <savicaleksa83@gmail.com>"); +MODULE_AUTHOR("Jack Doan <me@jackdoan.com>"); MODULE_DESCRIPTION("Hwmon driver for Aquacomputer devices"); diff --git a/drivers/hwmon/as370-hwmon.c b/drivers/hwmon/as370-hwmon.c index 464244ba8d58..63b5b2d6e593 100644 --- a/drivers/hwmon/as370-hwmon.c +++ b/drivers/hwmon/as370-hwmon.c @@ -76,18 +76,8 @@ as370_hwmon_is_visible(const void *data, enum hwmon_sensor_types type, } } -static const u32 as370_hwmon_temp_config[] = { - HWMON_T_INPUT, - 0 -}; - -static const struct hwmon_channel_info as370_hwmon_temp = { - .type = hwmon_temp, - .config = as370_hwmon_temp_config, -}; - static const struct hwmon_channel_info *as370_hwmon_info[] = { - &as370_hwmon_temp, + HWMON_CHANNEL_INFO(temp, HWMON_T_INPUT), NULL }; diff --git a/drivers/hwmon/asus-ec-sensors.c b/drivers/hwmon/asus-ec-sensors.c index b5cf0136360c..57e11b2bab74 100644 --- a/drivers/hwmon/asus-ec-sensors.c +++ b/drivers/hwmon/asus-ec-sensors.c @@ -54,8 +54,10 @@ static char *mutex_path_override; /* ACPI mutex for locking access to the EC for the firmware */ #define ASUS_HW_ACCESS_MUTEX_ASMX "\\AMW0.ASMX" -/* There are two variants of the vendor spelling */ -#define VENDOR_ASUS_UPPER_CASE "ASUSTeK COMPUTER INC." +#define MAX_IDENTICAL_BOARD_VARIATIONS 3 + +/* Moniker for the ACPI global lock (':' is not allowed in ASL identifiers) */ +#define ACPI_GLOBAL_LOCK_PSEUDO_PATH ":GLOBAL_LOCK" typedef union { u32 value; @@ -133,8 +135,44 @@ enum ec_sensors { #define SENSOR_TEMP_WATER_IN BIT(ec_sensor_temp_water_in) #define SENSOR_TEMP_WATER_OUT BIT(ec_sensor_temp_water_out) +enum board_family { + family_unknown, + family_amd_400_series, + family_amd_500_series, +}; + /* All the known sensors for ASUS EC controllers */ -static const struct ec_sensor_info known_ec_sensors[] = { +static const struct ec_sensor_info sensors_family_amd_400[] = { + [ec_sensor_temp_chipset] = + EC_SENSOR("Chipset", hwmon_temp, 1, 0x00, 0x3a), + [ec_sensor_temp_cpu] = + EC_SENSOR("CPU", hwmon_temp, 1, 0x00, 0x3b), + [ec_sensor_temp_mb] = + EC_SENSOR("Motherboard", hwmon_temp, 1, 0x00, 0x3c), + [ec_sensor_temp_t_sensor] = + EC_SENSOR("T_Sensor", hwmon_temp, 1, 0x00, 0x3d), + [ec_sensor_temp_vrm] = + EC_SENSOR("VRM", hwmon_temp, 1, 0x00, 0x3e), + [ec_sensor_in_cpu_core] = + EC_SENSOR("CPU Core", hwmon_in, 2, 0x00, 0xa2), + [ec_sensor_fan_cpu_opt] = + EC_SENSOR("CPU_Opt", hwmon_fan, 2, 0x00, 0xbc), + [ec_sensor_fan_vrm_hs] = + EC_SENSOR("VRM HS", hwmon_fan, 2, 0x00, 0xb2), + [ec_sensor_fan_chipset] = + /* no chipset fans in this generation */ + EC_SENSOR("Chipset", hwmon_fan, 0, 0x00, 0x00), + [ec_sensor_fan_water_flow] = + EC_SENSOR("Water_Flow", hwmon_fan, 2, 0x00, 0xb4), + [ec_sensor_curr_cpu] = + EC_SENSOR("CPU", hwmon_curr, 1, 0x00, 0xf4), + [ec_sensor_temp_water_in] = + EC_SENSOR("Water_In", hwmon_temp, 1, 0x01, 0x0d), + [ec_sensor_temp_water_out] = + EC_SENSOR("Water_Out", hwmon_temp, 1, 0x01, 0x0b), +}; + +static const struct ec_sensor_info sensors_family_amd_500[] = { [ec_sensor_temp_chipset] = EC_SENSOR("Chipset", hwmon_temp, 1, 0x00, 0x3a), [ec_sensor_temp_cpu] = EC_SENSOR("CPU", hwmon_temp, 1, 0x00, 0x3b), @@ -164,68 +202,134 @@ static const struct ec_sensor_info known_ec_sensors[] = { (SENSOR_TEMP_CHIPSET | SENSOR_TEMP_CPU | SENSOR_TEMP_MB) #define SENSOR_SET_TEMP_WATER (SENSOR_TEMP_WATER_IN | SENSOR_TEMP_WATER_OUT) -#define DMI_EXACT_MATCH_BOARD(vendor, name, sensors) { \ - .matches = { \ - DMI_EXACT_MATCH(DMI_BOARD_VENDOR, vendor), \ - DMI_EXACT_MATCH(DMI_BOARD_NAME, name), \ - }, \ - .driver_data = (void *)(sensors), \ -} +struct ec_board_info { + const char *board_names[MAX_IDENTICAL_BOARD_VARIATIONS]; + unsigned long sensors; + /* + * Defines which mutex to use for guarding access to the state and the + * hardware. Can be either a full path to an AML mutex or the + * pseudo-path ACPI_GLOBAL_LOCK_PSEUDO_PATH to use the global ACPI lock, + * or left empty to use a regular mutex object, in which case access to + * the hardware is not guarded. + */ + const char *mutex_path; + enum board_family family; +}; -static const struct dmi_system_id asus_ec_dmi_table[] __initconst = { - DMI_EXACT_MATCH_BOARD(VENDOR_ASUS_UPPER_CASE, "PRIME X570-PRO", - SENSOR_SET_TEMP_CHIPSET_CPU_MB | SENSOR_TEMP_VRM | - SENSOR_TEMP_T_SENSOR | SENSOR_FAN_CHIPSET), - DMI_EXACT_MATCH_BOARD(VENDOR_ASUS_UPPER_CASE, "Pro WS X570-ACE", - SENSOR_SET_TEMP_CHIPSET_CPU_MB | SENSOR_TEMP_VRM | - SENSOR_FAN_CHIPSET | SENSOR_CURR_CPU | SENSOR_IN_CPU_CORE), - DMI_EXACT_MATCH_BOARD(VENDOR_ASUS_UPPER_CASE, - "ROG CROSSHAIR VIII DARK HERO", - SENSOR_SET_TEMP_CHIPSET_CPU_MB | SENSOR_TEMP_T_SENSOR | - SENSOR_TEMP_VRM | SENSOR_SET_TEMP_WATER | - SENSOR_FAN_CPU_OPT | SENSOR_FAN_WATER_FLOW | - SENSOR_CURR_CPU | SENSOR_IN_CPU_CORE), - DMI_EXACT_MATCH_BOARD(VENDOR_ASUS_UPPER_CASE, - "ROG CROSSHAIR VIII FORMULA", - SENSOR_SET_TEMP_CHIPSET_CPU_MB | SENSOR_TEMP_T_SENSOR | - SENSOR_TEMP_VRM | SENSOR_FAN_CPU_OPT | SENSOR_FAN_CHIPSET | - SENSOR_CURR_CPU | SENSOR_IN_CPU_CORE), - DMI_EXACT_MATCH_BOARD(VENDOR_ASUS_UPPER_CASE, "ROG CROSSHAIR VIII HERO", - SENSOR_SET_TEMP_CHIPSET_CPU_MB | SENSOR_TEMP_T_SENSOR | - SENSOR_TEMP_VRM | SENSOR_SET_TEMP_WATER | - SENSOR_FAN_CPU_OPT | SENSOR_FAN_CHIPSET | - SENSOR_FAN_WATER_FLOW | SENSOR_CURR_CPU | SENSOR_IN_CPU_CORE), - DMI_EXACT_MATCH_BOARD(VENDOR_ASUS_UPPER_CASE, - "ROG CROSSHAIR VIII HERO (WI-FI)", - SENSOR_SET_TEMP_CHIPSET_CPU_MB | SENSOR_TEMP_T_SENSOR | - SENSOR_TEMP_VRM | SENSOR_SET_TEMP_WATER | - SENSOR_FAN_CPU_OPT | SENSOR_FAN_CHIPSET | - SENSOR_FAN_WATER_FLOW | SENSOR_CURR_CPU | SENSOR_IN_CPU_CORE), - DMI_EXACT_MATCH_BOARD(VENDOR_ASUS_UPPER_CASE, - "ROG CROSSHAIR VIII IMPACT", - SENSOR_SET_TEMP_CHIPSET_CPU_MB | SENSOR_TEMP_T_SENSOR | - SENSOR_TEMP_VRM | SENSOR_FAN_CHIPSET | - SENSOR_CURR_CPU | SENSOR_IN_CPU_CORE), - DMI_EXACT_MATCH_BOARD(VENDOR_ASUS_UPPER_CASE, "ROG STRIX B550-E GAMING", - SENSOR_SET_TEMP_CHIPSET_CPU_MB | - SENSOR_TEMP_T_SENSOR | - SENSOR_TEMP_VRM | SENSOR_FAN_CPU_OPT), - DMI_EXACT_MATCH_BOARD(VENDOR_ASUS_UPPER_CASE, "ROG STRIX B550-I GAMING", - SENSOR_SET_TEMP_CHIPSET_CPU_MB | - SENSOR_TEMP_T_SENSOR | - SENSOR_TEMP_VRM | SENSOR_FAN_VRM_HS | - SENSOR_CURR_CPU | SENSOR_IN_CPU_CORE), - DMI_EXACT_MATCH_BOARD(VENDOR_ASUS_UPPER_CASE, "ROG STRIX X570-E GAMING", - SENSOR_SET_TEMP_CHIPSET_CPU_MB | - SENSOR_TEMP_T_SENSOR | - SENSOR_TEMP_VRM | SENSOR_FAN_CHIPSET | - SENSOR_CURR_CPU | SENSOR_IN_CPU_CORE), - DMI_EXACT_MATCH_BOARD(VENDOR_ASUS_UPPER_CASE, "ROG STRIX X570-F GAMING", - SENSOR_SET_TEMP_CHIPSET_CPU_MB | - SENSOR_TEMP_T_SENSOR | SENSOR_FAN_CHIPSET), - DMI_EXACT_MATCH_BOARD(VENDOR_ASUS_UPPER_CASE, "ROG STRIX X570-I GAMING", - SENSOR_TEMP_T_SENSOR | SENSOR_FAN_VRM_HS | - SENSOR_FAN_CHIPSET | SENSOR_CURR_CPU | SENSOR_IN_CPU_CORE), +static const struct ec_board_info board_info[] = { + { + .board_names = {"PRIME X470-PRO"}, + .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | + SENSOR_TEMP_T_SENSOR | SENSOR_TEMP_VRM | + SENSOR_FAN_CPU_OPT | + SENSOR_CURR_CPU | SENSOR_IN_CPU_CORE, + .mutex_path = ACPI_GLOBAL_LOCK_PSEUDO_PATH, + .family = family_amd_400_series, + }, + { + .board_names = {"PRIME X570-PRO"}, + .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | SENSOR_TEMP_VRM | + SENSOR_TEMP_T_SENSOR | SENSOR_FAN_CHIPSET, + .mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX, + .family = family_amd_500_series, + }, + { + .board_names = {"ProArt X570-CREATOR WIFI"}, + .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | SENSOR_TEMP_VRM | + SENSOR_TEMP_T_SENSOR | SENSOR_FAN_CPU_OPT | + SENSOR_CURR_CPU | SENSOR_IN_CPU_CORE, + }, + { + .board_names = {"Pro WS X570-ACE"}, + .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | SENSOR_TEMP_VRM | + SENSOR_TEMP_T_SENSOR | SENSOR_FAN_CHIPSET | + SENSOR_CURR_CPU | SENSOR_IN_CPU_CORE, + .mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX, + .family = family_amd_500_series, + }, + { + .board_names = {"ROG CROSSHAIR VIII DARK HERO"}, + .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | + SENSOR_TEMP_T_SENSOR | + SENSOR_TEMP_VRM | SENSOR_SET_TEMP_WATER | + SENSOR_FAN_CPU_OPT | SENSOR_FAN_WATER_FLOW | + SENSOR_CURR_CPU | SENSOR_IN_CPU_CORE, + .mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX, + .family = family_amd_500_series, + }, + { + .board_names = { + "ROG CROSSHAIR VIII FORMULA" + "ROG CROSSHAIR VIII HERO", + "ROG CROSSHAIR VIII HERO (WI-FI)", + }, + .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | + SENSOR_TEMP_T_SENSOR | + SENSOR_TEMP_VRM | SENSOR_SET_TEMP_WATER | + SENSOR_FAN_CPU_OPT | SENSOR_FAN_CHIPSET | + SENSOR_FAN_WATER_FLOW | SENSOR_CURR_CPU | + SENSOR_IN_CPU_CORE, + .mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX, + .family = family_amd_500_series, + }, + { + .board_names = {"ROG CROSSHAIR VIII IMPACT"}, + .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | + SENSOR_TEMP_T_SENSOR | SENSOR_TEMP_VRM | + SENSOR_FAN_CHIPSET | SENSOR_CURR_CPU | + SENSOR_IN_CPU_CORE, + .mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX, + .family = family_amd_500_series, + }, + { + .board_names = {"ROG STRIX B550-E GAMING"}, + .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | + SENSOR_TEMP_T_SENSOR | SENSOR_TEMP_VRM | + SENSOR_FAN_CPU_OPT, + .mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX, + .family = family_amd_500_series, + }, + { + .board_names = {"ROG STRIX B550-I GAMING"}, + .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | + SENSOR_TEMP_T_SENSOR | SENSOR_TEMP_VRM | + SENSOR_FAN_VRM_HS | SENSOR_CURR_CPU | + SENSOR_IN_CPU_CORE, + .mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX, + .family = family_amd_500_series, + }, + { + .board_names = {"ROG STRIX X570-E GAMING"}, + .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | + SENSOR_TEMP_T_SENSOR | SENSOR_TEMP_VRM | + SENSOR_FAN_CHIPSET | SENSOR_CURR_CPU | + SENSOR_IN_CPU_CORE, + .mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX, + .family = family_amd_500_series, + }, + { + .board_names = {"ROG STRIX X570-E GAMING WIFI II"}, + .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | + SENSOR_TEMP_T_SENSOR | SENSOR_CURR_CPU | + SENSOR_IN_CPU_CORE, + .mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX, + .family = family_amd_500_series, + }, + { + .board_names = {"ROG STRIX X570-F GAMING"}, + .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | + SENSOR_TEMP_T_SENSOR | SENSOR_FAN_CHIPSET, + .mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX, + .family = family_amd_500_series, + }, + { + .board_names = {"ROG STRIX X570-I GAMING"}, + .sensors = SENSOR_TEMP_T_SENSOR | SENSOR_FAN_VRM_HS | + SENSOR_FAN_CHIPSET | SENSOR_CURR_CPU | + SENSOR_IN_CPU_CORE, + .mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX, + .family = family_amd_500_series, + }, {} }; @@ -234,8 +338,49 @@ struct ec_sensor { s32 cached_value; }; +struct lock_data { + union { + acpi_handle aml; + /* global lock handle */ + u32 glk; + } mutex; + bool (*lock)(struct lock_data *data); + bool (*unlock)(struct lock_data *data); +}; + +/* + * The next function pairs implement options for locking access to the + * state and the EC + */ +static bool lock_via_acpi_mutex(struct lock_data *data) +{ + /* + * ASUS DSDT does not specify that access to the EC has to be guarded, + * but firmware does access it via ACPI + */ + return ACPI_SUCCESS(acpi_acquire_mutex(data->mutex.aml, + NULL, ACPI_LOCK_DELAY_MS)); +} + +static bool unlock_acpi_mutex(struct lock_data *data) +{ + return ACPI_SUCCESS(acpi_release_mutex(data->mutex.aml, NULL)); +} + +static bool lock_via_global_acpi_lock(struct lock_data *data) +{ + return ACPI_SUCCESS(acpi_acquire_global_lock(ACPI_LOCK_DELAY_MS, + &data->mutex.glk)); +} + +static bool unlock_global_acpi_lock(struct lock_data *data) +{ + return ACPI_SUCCESS(acpi_release_global_lock(data->mutex.glk)); +} + struct ec_sensors_data { - unsigned long board_sensors; + const struct ec_board_info *board_info; + const struct ec_sensor_info *sensors_info; struct ec_sensor *sensors; /* EC registers to read from */ u16 *registers; @@ -244,7 +389,7 @@ struct ec_sensors_data { u8 banks[ASUS_EC_MAX_BANK + 1]; /* in jiffies */ unsigned long last_updated; - acpi_handle aml_mutex; + struct lock_data lock_data; /* number of board EC sensors */ u8 nr_sensors; /* @@ -278,7 +423,7 @@ static bool is_sensor_data_signed(const struct ec_sensor_info *si) static const struct ec_sensor_info * get_sensor_info(const struct ec_sensors_data *state, int index) { - return &known_ec_sensors[state->sensors[index].info_index]; + return state->sensors_info + state->sensors[index].info_index; } static int find_ec_sensor_index(const struct ec_sensors_data *ec, @@ -301,11 +446,6 @@ static int __init bank_compare(const void *a, const void *b) return *((const s8 *)a) - *((const s8 *)b); } -static int __init board_sensors_count(unsigned long sensors) -{ - return hweight_long(sensors); -} - static void __init setup_sensor_data(struct ec_sensors_data *ec) { struct ec_sensor *s = ec->sensors; @@ -316,14 +456,14 @@ static void __init setup_sensor_data(struct ec_sensors_data *ec) ec->nr_banks = 0; ec->nr_registers = 0; - for_each_set_bit(i, &ec->board_sensors, - BITS_PER_TYPE(ec->board_sensors)) { + for_each_set_bit(i, &ec->board_info->sensors, + BITS_PER_TYPE(ec->board_info->sensors)) { s->info_index = i; s->cached_value = 0; ec->nr_registers += - known_ec_sensors[s->info_index].addr.components.size; + ec->sensors_info[s->info_index].addr.components.size; bank_found = false; - bank = known_ec_sensors[s->info_index].addr.components.bank; + bank = ec->sensors_info[s->info_index].addr.components.bank; for (j = 0; j < ec->nr_banks; j++) { if (ec->banks[j] == bank) { bank_found = true; @@ -353,23 +493,36 @@ static void __init fill_ec_registers(struct ec_sensors_data *ec) } } -static acpi_handle __init asus_hw_access_mutex(struct device *dev) +static int __init setup_lock_data(struct device *dev) { const char *mutex_path; - acpi_handle res; int status; + struct ec_sensors_data *state = dev_get_drvdata(dev); mutex_path = mutex_path_override ? - mutex_path_override : ASUS_HW_ACCESS_MUTEX_ASMX; + mutex_path_override : state->board_info->mutex_path; - status = acpi_get_handle(NULL, (acpi_string)mutex_path, &res); - if (ACPI_FAILURE(status)) { - dev_err(dev, - "Could not get hardware access guard mutex '%s': error %d", - mutex_path, status); - return NULL; + if (!mutex_path || !strlen(mutex_path)) { + dev_err(dev, "Hardware access guard mutex name is empty"); + return -EINVAL; } - return res; + if (!strcmp(mutex_path, ACPI_GLOBAL_LOCK_PSEUDO_PATH)) { + state->lock_data.mutex.glk = 0; + state->lock_data.lock = lock_via_global_acpi_lock; + state->lock_data.unlock = unlock_global_acpi_lock; + } else { + status = acpi_get_handle(NULL, (acpi_string)mutex_path, + &state->lock_data.mutex.aml); + if (ACPI_FAILURE(status)) { + dev_err(dev, + "Failed to get hardware access guard AML mutex '%s': error %d", + mutex_path, status); + return -ENOENT; + } + state->lock_data.lock = lock_via_acpi_mutex; + state->lock_data.unlock = unlock_acpi_mutex; + } + return 0; } static int asus_ec_bank_switch(u8 bank, u8 *old) @@ -457,10 +610,11 @@ static inline s32 get_sensor_value(const struct ec_sensor_info *si, u8 *data) static void update_sensor_values(struct ec_sensors_data *ec, u8 *data) { const struct ec_sensor_info *si; - struct ec_sensor *s; + struct ec_sensor *s, *sensor_end; - for (s = ec->sensors; s != ec->sensors + ec->nr_sensors; s++) { - si = &known_ec_sensors[s->info_index]; + sensor_end = ec->sensors + ec->nr_sensors; + for (s = ec->sensors; s != sensor_end; s++) { + si = ec->sensors_info + s->info_index; s->cached_value = get_sensor_value(si, data); data += si->addr.components.size; } @@ -471,15 +625,9 @@ static int update_ec_sensors(const struct device *dev, { int status; - /* - * ASUS DSDT does not specify that access to the EC has to be guarded, - * but firmware does access it via ACPI - */ - if (ACPI_FAILURE(acpi_acquire_mutex(ec->aml_mutex, NULL, - ACPI_LOCK_DELAY_MS))) { - dev_err(dev, "Failed to acquire AML mutex"); - status = -EBUSY; - goto cleanup; + if (!ec->lock_data.lock(&ec->lock_data)) { + dev_warn(dev, "Failed to acquire mutex"); + return -EBUSY; } status = asus_ec_block_read(dev, ec); @@ -487,10 +635,10 @@ static int update_ec_sensors(const struct device *dev, if (!status) { update_sensor_values(ec, ec->read_buffer); } - if (ACPI_FAILURE(acpi_release_mutex(ec->aml_mutex, NULL))) { - dev_err(dev, "Failed to release AML mutex"); - } -cleanup: + + if (!ec->lock_data.unlock(&ec->lock_data)) + dev_err(dev, "Failed to release mutex"); + return status; } @@ -597,12 +745,24 @@ static struct hwmon_chip_info asus_ec_chip_info = { .ops = &asus_ec_hwmon_ops, }; -static unsigned long __init get_board_sensors(void) +static const struct ec_board_info * __init get_board_info(void) { - const struct dmi_system_id *dmi_entry = - dmi_first_match(asus_ec_dmi_table); + const char *dmi_board_vendor = dmi_get_system_info(DMI_BOARD_VENDOR); + const char *dmi_board_name = dmi_get_system_info(DMI_BOARD_NAME); + const struct ec_board_info *board; - return dmi_entry ? (unsigned long)dmi_entry->driver_data : 0; + if (!dmi_board_vendor || !dmi_board_name || + strcasecmp(dmi_board_vendor, "ASUSTeK COMPUTER INC.")) + return NULL; + + for (board = board_info; board->sensors; board++) { + if (match_string(board->board_names, + MAX_IDENTICAL_BOARD_VARIATIONS, + dmi_board_name) >= 0) + return board; + } + + return NULL; } static int __init asus_ec_probe(struct platform_device *pdev) @@ -610,17 +770,18 @@ static int __init asus_ec_probe(struct platform_device *pdev) const struct hwmon_channel_info **ptr_asus_ec_ci; int nr_count[hwmon_max] = { 0 }, nr_types = 0; struct hwmon_channel_info *asus_ec_hwmon_chan; + const struct ec_board_info *pboard_info; const struct hwmon_chip_info *chip_info; struct device *dev = &pdev->dev; struct ec_sensors_data *ec_data; const struct ec_sensor_info *si; enum hwmon_sensor_types type; - unsigned long board_sensors; struct device *hwdev; unsigned int i; + int status; - board_sensors = get_board_sensors(); - if (!board_sensors) + pboard_info = get_board_info(); + if (!pboard_info) return -ENODEV; ec_data = devm_kzalloc(dev, sizeof(struct ec_sensors_data), @@ -629,11 +790,31 @@ static int __init asus_ec_probe(struct platform_device *pdev) return -ENOMEM; dev_set_drvdata(dev, ec_data); - ec_data->board_sensors = board_sensors; - ec_data->nr_sensors = board_sensors_count(ec_data->board_sensors); + ec_data->board_info = pboard_info; + + switch (ec_data->board_info->family) { + case family_amd_400_series: + ec_data->sensors_info = sensors_family_amd_400; + break; + case family_amd_500_series: + ec_data->sensors_info = sensors_family_amd_500; + break; + default: + dev_err(dev, "Unknown board family: %d", + ec_data->board_info->family); + return -EINVAL; + } + + ec_data->nr_sensors = hweight_long(ec_data->board_info->sensors); ec_data->sensors = devm_kcalloc(dev, ec_data->nr_sensors, sizeof(struct ec_sensor), GFP_KERNEL); + status = setup_lock_data(dev); + if (status) { + dev_err(dev, "Failed to setup state/EC locking: %d", status); + return status; + } + setup_sensor_data(ec_data); ec_data->registers = devm_kcalloc(dev, ec_data->nr_registers, sizeof(u16), GFP_KERNEL); @@ -645,8 +826,6 @@ static int __init asus_ec_probe(struct platform_device *pdev) fill_ec_registers(ec_data); - ec_data->aml_mutex = asus_hw_access_mutex(dev); - for (i = 0; i < ec_data->nr_sensors; ++i) { si = get_sensor_info(ec_data, i); if (!nr_count[si->type]) @@ -703,7 +882,14 @@ static struct platform_driver asus_ec_sensors_platform_driver = { }, }; -MODULE_DEVICE_TABLE(dmi, asus_ec_dmi_table); +MODULE_DEVICE_TABLE(acpi, acpi_ec_ids); +/* + * we use module_platform_driver_probe() rather than module_platform_driver() + * because the probe function (and its dependants) are marked with __init, which + * means we can't put it into the .probe member of the platform_driver struct + * above, and we can't mark the asus_ec_sensors_platform_driver object as __init + * because the object is referenced from the module exit code. + */ module_platform_driver_probe(asus_ec_sensors_platform_driver, asus_ec_probe); module_param_named(mutex_path, mutex_path_override, charp, 0); diff --git a/drivers/hwmon/asus_wmi_sensors.c b/drivers/hwmon/asus_wmi_sensors.c index 8fdcb62ae52d..9e935e34c998 100644 --- a/drivers/hwmon/asus_wmi_sensors.c +++ b/drivers/hwmon/asus_wmi_sensors.c @@ -71,7 +71,7 @@ static const struct dmi_system_id asus_wmi_dmi_table[] = { DMI_EXACT_MATCH_ASUS_BOARD_NAME("PRIME X399-A"), DMI_EXACT_MATCH_ASUS_BOARD_NAME("PRIME X470-PRO"), DMI_EXACT_MATCH_ASUS_BOARD_NAME("ROG CROSSHAIR VI EXTREME"), - DMI_EXACT_MATCH_ASUS_BOARD_NAME("ROG CROSSHAIR VI HERO"), + DMI_EXACT_MATCH_ASUS_BOARD_NAME("CROSSHAIR VI HERO"), DMI_EXACT_MATCH_ASUS_BOARD_NAME("ROG CROSSHAIR VI HERO (WI-FI AC)"), DMI_EXACT_MATCH_ASUS_BOARD_NAME("ROG CROSSHAIR VII HERO"), DMI_EXACT_MATCH_ASUS_BOARD_NAME("ROG CROSSHAIR VII HERO (WI-FI)"), diff --git a/drivers/hwmon/bt1-pvt.c b/drivers/hwmon/bt1-pvt.c index 74ce5211eb75..21ab172774ec 100644 --- a/drivers/hwmon/bt1-pvt.c +++ b/drivers/hwmon/bt1-pvt.c @@ -26,6 +26,7 @@ #include <linux/mutex.h> #include <linux/of.h> #include <linux/platform_device.h> +#include <linux/polynomial.h> #include <linux/seqlock.h> #include <linux/sysfs.h> #include <linux/types.h> @@ -65,7 +66,7 @@ static const struct pvt_sensor_info pvt_info[] = { * 48380, * where T = [-48380, 147438] mC and N = [0, 1023]. */ -static const struct pvt_poly __maybe_unused poly_temp_to_N = { +static const struct polynomial __maybe_unused poly_temp_to_N = { .total_divider = 10000, .terms = { {4, 18322, 10000, 10000}, @@ -76,7 +77,7 @@ static const struct pvt_poly __maybe_unused poly_temp_to_N = { } }; -static const struct pvt_poly poly_N_to_temp = { +static const struct polynomial poly_N_to_temp = { .total_divider = 1, .terms = { {4, -16743, 1000, 1}, @@ -97,7 +98,7 @@ static const struct pvt_poly poly_N_to_temp = { * N = (18658e-3*V - 11572) / 10, * V = N * 10^5 / 18658 + 11572 * 10^4 / 18658. */ -static const struct pvt_poly __maybe_unused poly_volt_to_N = { +static const struct polynomial __maybe_unused poly_volt_to_N = { .total_divider = 10, .terms = { {1, 18658, 1000, 1}, @@ -105,7 +106,7 @@ static const struct pvt_poly __maybe_unused poly_volt_to_N = { } }; -static const struct pvt_poly poly_N_to_volt = { +static const struct polynomial poly_N_to_volt = { .total_divider = 10, .terms = { {1, 100000, 18658, 1}, @@ -113,31 +114,6 @@ static const struct pvt_poly poly_N_to_volt = { } }; -/* - * Here is the polynomial calculation function, which performs the - * redistributed terms calculations. It's pretty straightforward. We walk - * over each degree term up to the free one, and perform the redistributed - * multiplication of the term coefficient, its divider (as for the rationale - * fraction representation), data power and the rational fraction divider - * leftover. Then all of this is collected in a total sum variable, which - * value is normalized by the total divider before being returned. - */ -static long pvt_calc_poly(const struct pvt_poly *poly, long data) -{ - const struct pvt_poly_term *term = poly->terms; - long tmp, ret = 0; - int deg; - - do { - tmp = term->coef; - for (deg = 0; deg < term->deg; ++deg) - tmp = mult_frac(tmp, data, term->divider); - ret += tmp / term->divider_leftover; - } while ((term++)->deg); - - return ret / poly->total_divider; -} - static inline u32 pvt_update(void __iomem *reg, u32 mask, u32 data) { u32 old; @@ -324,9 +300,9 @@ static int pvt_read_data(struct pvt_hwmon *pvt, enum pvt_sensor_type type, } while (read_seqretry(&cache->data_seqlock, seq)); if (type == PVT_TEMP) - *val = pvt_calc_poly(&poly_N_to_temp, data); + *val = polynomial_calc(&poly_N_to_temp, data); else - *val = pvt_calc_poly(&poly_N_to_volt, data); + *val = polynomial_calc(&poly_N_to_volt, data); return 0; } @@ -345,9 +321,9 @@ static int pvt_read_limit(struct pvt_hwmon *pvt, enum pvt_sensor_type type, data = FIELD_GET(PVT_THRES_HI_MASK, data); if (type == PVT_TEMP) - *val = pvt_calc_poly(&poly_N_to_temp, data); + *val = polynomial_calc(&poly_N_to_temp, data); else - *val = pvt_calc_poly(&poly_N_to_volt, data); + *val = polynomial_calc(&poly_N_to_volt, data); return 0; } @@ -360,10 +336,10 @@ static int pvt_write_limit(struct pvt_hwmon *pvt, enum pvt_sensor_type type, if (type == PVT_TEMP) { val = clamp(val, PVT_TEMP_MIN, PVT_TEMP_MAX); - data = pvt_calc_poly(&poly_temp_to_N, val); + data = polynomial_calc(&poly_temp_to_N, val); } else { val = clamp(val, PVT_VOLT_MIN, PVT_VOLT_MAX); - data = pvt_calc_poly(&poly_volt_to_N, val); + data = polynomial_calc(&poly_volt_to_N, val); } /* Serialize limit update, since a part of the register is changed. */ @@ -522,9 +498,9 @@ static int pvt_read_data(struct pvt_hwmon *pvt, enum pvt_sensor_type type, return -ETIMEDOUT; if (type == PVT_TEMP) - *val = pvt_calc_poly(&poly_N_to_temp, data); + *val = polynomial_calc(&poly_N_to_temp, data); else - *val = pvt_calc_poly(&poly_N_to_volt, data); + *val = polynomial_calc(&poly_N_to_volt, data); return 0; } diff --git a/drivers/hwmon/dell-smm-hwmon.c b/drivers/hwmon/dell-smm-hwmon.c index 84cb1ede7bc0..071aa6f4e109 100644 --- a/drivers/hwmon/dell-smm-hwmon.c +++ b/drivers/hwmon/dell-smm-hwmon.c @@ -21,14 +21,17 @@ #include <linux/errno.h> #include <linux/hwmon.h> #include <linux/init.h> +#include <linux/kconfig.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/platform_device.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> -#include <linux/string.h> +#include <linux/slab.h> #include <linux/smp.h> +#include <linux/string.h> +#include <linux/thermal.h> #include <linux/types.h> #include <linux/uaccess.h> @@ -46,8 +49,11 @@ #define I8K_SMM_GET_DELL_SIG1 0xfea3 #define I8K_SMM_GET_DELL_SIG2 0xffa3 +/* in usecs */ +#define DELL_SMM_MAX_DURATION 250000 + #define I8K_FAN_MULT 30 -#define I8K_FAN_MAX_RPM 30000 +#define I8K_FAN_RPM_THRESHOLD 1000 #define I8K_MAX_TEMP 127 #define I8K_FN_NONE 0x00 @@ -80,6 +86,11 @@ struct dell_smm_data { int *fan_nominal_speed[DELL_SMM_NO_FANS]; }; +struct dell_smm_cooling_data { + u8 fan_num; + struct dell_smm_data *data; +}; + MODULE_AUTHOR("Massimo Dal Zotto (dz@debian.org)"); MODULE_AUTHOR("Pali Rohár <pali@kernel.org>"); MODULE_DESCRIPTION("Dell laptop SMM BIOS hwmon driver"); @@ -231,6 +242,9 @@ static int i8k_smm_func(void *par) pr_debug("smm(0x%.4x 0x%.4x) = 0x%.4x (took %7lld usecs)\n", eax, ebx, (rc ? 0xffff : regs->eax & 0xffff), duration); + if (duration > DELL_SMM_MAX_DURATION) + pr_warn_once("SMM call took %lld usecs!\n", duration); + return rc; } @@ -318,7 +332,7 @@ static int __init i8k_get_fan_nominal_speed(const struct dell_smm_data *data, u8 if (data->disallow_fan_support) return -EINVAL; - return i8k_smm(®s) ? : (regs.eax & 0xffff) * data->i8k_fan_mult; + return i8k_smm(®s) ? : (regs.eax & 0xffff); } /* @@ -638,9 +652,50 @@ static void __init i8k_init_procfs(struct device *dev) #endif -/* - * Hwmon interface - */ +static int dell_smm_get_max_state(struct thermal_cooling_device *dev, unsigned long *state) +{ + struct dell_smm_cooling_data *cdata = dev->devdata; + + *state = cdata->data->i8k_fan_max; + + return 0; +} + +static int dell_smm_get_cur_state(struct thermal_cooling_device *dev, unsigned long *state) +{ + struct dell_smm_cooling_data *cdata = dev->devdata; + int ret; + + ret = i8k_get_fan_status(cdata->data, cdata->fan_num); + if (ret < 0) + return ret; + + *state = ret; + + return 0; +} + +static int dell_smm_set_cur_state(struct thermal_cooling_device *dev, unsigned long state) +{ + struct dell_smm_cooling_data *cdata = dev->devdata; + struct dell_smm_data *data = cdata->data; + int ret; + + if (state > data->i8k_fan_max) + return -EINVAL; + + mutex_lock(&data->i8k_mutex); + ret = i8k_set_fan(data, cdata->fan_num, (int)state); + mutex_unlock(&data->i8k_mutex); + + return ret; +} + +static const struct thermal_cooling_device_ops dell_smm_cooling_ops = { + .get_max_state = dell_smm_get_max_state, + .get_cur_state = dell_smm_get_cur_state, + .set_cur_state = dell_smm_set_cur_state, +}; static umode_t dell_smm_is_visible(const void *drvdata, enum hwmon_sensor_types type, u32 attr, int channel) @@ -727,6 +782,7 @@ static int dell_smm_read(struct device *dev, enum hwmon_sensor_types type, u32 a long *val) { struct dell_smm_data *data = dev_get_drvdata(dev); + int mult = data->i8k_fan_mult; int ret; switch (type) { @@ -755,11 +811,11 @@ static int dell_smm_read(struct device *dev, enum hwmon_sensor_types type, u32 a return 0; case hwmon_fan_min: - *val = data->fan_nominal_speed[channel][0]; + *val = data->fan_nominal_speed[channel][0] * mult; return 0; case hwmon_fan_max: - *val = data->fan_nominal_speed[channel][data->i8k_fan_max]; + *val = data->fan_nominal_speed[channel][data->i8k_fan_max] * mult; return 0; case hwmon_fan_target: @@ -770,7 +826,7 @@ static int dell_smm_read(struct device *dev, enum hwmon_sensor_types type, u32 a if (ret > data->i8k_fan_max) ret = data->i8k_fan_max; - *val = data->fan_nominal_speed[channel][ret]; + *val = data->fan_nominal_speed[channel][ret] * mult; return 0; default: @@ -941,6 +997,37 @@ static const struct hwmon_chip_info dell_smm_chip_info = { .info = dell_smm_info, }; +static int __init dell_smm_init_cdev(struct device *dev, u8 fan_num) +{ + struct dell_smm_data *data = dev_get_drvdata(dev); + struct thermal_cooling_device *cdev; + struct dell_smm_cooling_data *cdata; + int ret = 0; + char *name; + + name = kasprintf(GFP_KERNEL, "dell-smm-fan%u", fan_num + 1); + if (!name) + return -ENOMEM; + + cdata = devm_kmalloc(dev, sizeof(*cdata), GFP_KERNEL); + if (cdata) { + cdata->fan_num = fan_num; + cdata->data = data; + cdev = devm_thermal_of_cooling_device_register(dev, NULL, name, cdata, + &dell_smm_cooling_ops); + if (IS_ERR(cdev)) { + devm_kfree(dev, cdata); + ret = PTR_ERR(cdev); + } + } else { + ret = -ENOMEM; + } + + kfree(name); + + return ret; +} + static int __init dell_smm_init_hwmon(struct device *dev) { struct dell_smm_data *data = dev_get_drvdata(dev); @@ -967,6 +1054,15 @@ static int __init dell_smm_init_hwmon(struct device *dev) continue; data->fan[i] = true; + + /* the cooling device is not critical, ignore failures */ + if (IS_REACHABLE(CONFIG_THERMAL)) { + err = dell_smm_init_cdev(dev, i); + if (err < 0) + dev_warn(dev, "Failed to register cooling device for fan %u\n", + i + 1); + } + data->fan_nominal_speed[i] = devm_kmalloc_array(dev, data->i8k_fan_max + 1, sizeof(*data->fan_nominal_speed[i]), GFP_KERNEL); @@ -982,6 +1078,13 @@ static int __init dell_smm_init_hwmon(struct device *dev) break; } data->fan_nominal_speed[i][state] = err; + /* + * Autodetect fan multiplier based on nominal rpm if multiplier + * was not specified as module param or in DMI. If fan reports + * rpm value too high then set multiplier to 1. + */ + if (!fan_mult && err > I8K_FAN_RPM_THRESHOLD) + data->i8k_fan_mult = 1; } } @@ -1270,15 +1373,12 @@ static int __init dell_smm_probe(struct platform_device *pdev) struct dell_smm_data *data; const struct dmi_system_id *id, *fan_control; int ret; - u8 fan; data = devm_kzalloc(&pdev->dev, sizeof(struct dell_smm_data), GFP_KERNEL); if (!data) return -ENOMEM; mutex_init(&data->i8k_mutex); - data->i8k_fan_mult = I8K_FAN_MULT; - data->i8k_fan_max = I8K_FAN_HIGH; platform_set_drvdata(pdev, data); if (dmi_check_system(i8k_blacklist_fan_support_dmi_table)) { @@ -1313,7 +1413,9 @@ static int __init dell_smm_probe(struct platform_device *pdev) fan_max = conf->fan_max; } - data->i8k_fan_max = fan_max ? : I8K_FAN_HIGH; /* Must not be 0 */ + /* All options must not be 0 */ + data->i8k_fan_mult = fan_mult ? : I8K_FAN_MULT; + data->i8k_fan_max = fan_max ? : I8K_FAN_HIGH; data->i8k_pwm_mult = DIV_ROUND_UP(255, data->i8k_fan_max); fan_control = dmi_first_match(i8k_whitelist_fan_control); @@ -1325,25 +1427,6 @@ static int __init dell_smm_probe(struct platform_device *pdev) dev_info(&pdev->dev, "enabling support for setting automatic/manual fan control\n"); } - if (!fan_mult) { - /* - * Autodetect fan multiplier based on nominal rpm - * If fan reports rpm value too high then set multiplier to 1 - */ - for (fan = 0; fan < DELL_SMM_NO_FANS; ++fan) { - ret = i8k_get_fan_nominal_speed(data, fan, data->i8k_fan_max); - if (ret < 0) - continue; - - if (ret > I8K_FAN_MAX_RPM) - data->i8k_fan_mult = 1; - break; - } - } else { - /* Fan multiplier was specified in module param or in dmi */ - data->i8k_fan_mult = fan_mult; - } - ret = dell_smm_init_hwmon(&pdev->dev); if (ret) return ret; diff --git a/drivers/hwmon/f71882fg.c b/drivers/hwmon/f71882fg.c index 938a8b9ec70d..6830e029995d 100644 --- a/drivers/hwmon/f71882fg.c +++ b/drivers/hwmon/f71882fg.c @@ -1578,8 +1578,9 @@ static ssize_t show_temp(struct device *dev, struct device_attribute *devattr, temp *= 125; if (sign) temp -= 128000; - } else - temp = data->temp[nr] * 1000; + } else { + temp = ((s8)data->temp[nr]) * 1000; + } return sprintf(buf, "%d\n", temp); } diff --git a/drivers/hwmon/hwmon.c b/drivers/hwmon/hwmon.c index 989e2c8496dd..2e2cd79d89eb 100644 --- a/drivers/hwmon/hwmon.c +++ b/drivers/hwmon/hwmon.c @@ -764,7 +764,7 @@ __hwmon_device_register(struct device *dev, const char *name, void *drvdata, "hwmon: '%s' is not a valid name attribute, please fix\n", name); - id = ida_simple_get(&hwmon_ida, 0, 0, GFP_KERNEL); + id = ida_alloc(&hwmon_ida, GFP_KERNEL); if (id < 0) return ERR_PTR(id); @@ -856,7 +856,7 @@ __hwmon_device_register(struct device *dev, const char *name, void *drvdata, free_hwmon: hwmon_dev_release(hdev); ida_remove: - ida_simple_remove(&hwmon_ida, id); + ida_free(&hwmon_ida, id); return ERR_PTR(err); } @@ -886,11 +886,12 @@ EXPORT_SYMBOL_GPL(hwmon_device_register_with_groups); /** * hwmon_device_register_with_info - register w/ hwmon - * @dev: the parent device - * @name: hwmon name attribute - * @drvdata: driver data to attach to created device - * @chip: pointer to hwmon chip information + * @dev: the parent device (mandatory) + * @name: hwmon name attribute (mandatory) + * @drvdata: driver data to attach to created device (optional) + * @chip: pointer to hwmon chip information (mandatory) * @extra_groups: pointer to list of additional non-standard attribute groups + * (optional) * * hwmon_device_unregister() must be called when the device is no * longer needed. @@ -903,13 +904,10 @@ hwmon_device_register_with_info(struct device *dev, const char *name, const struct hwmon_chip_info *chip, const struct attribute_group **extra_groups) { - if (!name) - return ERR_PTR(-EINVAL); - - if (chip && (!chip->ops || !chip->ops->is_visible || !chip->info)) + if (!dev || !name || !chip) return ERR_PTR(-EINVAL); - if (chip && !dev) + if (!chip->ops || !chip->ops->is_visible || !chip->info) return ERR_PTR(-EINVAL); return __hwmon_device_register(dev, name, drvdata, chip, extra_groups); @@ -917,6 +915,31 @@ hwmon_device_register_with_info(struct device *dev, const char *name, EXPORT_SYMBOL_GPL(hwmon_device_register_with_info); /** + * hwmon_device_register_for_thermal - register hwmon device for thermal subsystem + * @dev: the parent device + * @name: hwmon name attribute + * @drvdata: driver data to attach to created device + * + * The use of this function is restricted. It is provided for legacy reasons + * and must only be called from the thermal subsystem. + * + * hwmon_device_unregister() must be called when the device is no + * longer needed. + * + * Returns the pointer to the new device. + */ +struct device * +hwmon_device_register_for_thermal(struct device *dev, const char *name, + void *drvdata) +{ + if (!name || !dev) + return ERR_PTR(-EINVAL); + + return __hwmon_device_register(dev, name, drvdata, NULL, NULL); +} +EXPORT_SYMBOL_NS_GPL(hwmon_device_register_for_thermal, HWMON_THERMAL); + +/** * hwmon_device_register - register w/ hwmon * @dev: the device to register * @@ -945,7 +968,7 @@ void hwmon_device_unregister(struct device *dev) if (likely(sscanf(dev_name(dev), HWMON_ID_FORMAT, &id) == 1)) { device_unregister(dev); - ida_simple_remove(&hwmon_ida, id); + ida_free(&hwmon_ida, id); } else dev_dbg(dev->parent, "hwmon_device_unregister() failed: bad class ID!\n"); @@ -1057,6 +1080,59 @@ void devm_hwmon_device_unregister(struct device *dev) } EXPORT_SYMBOL_GPL(devm_hwmon_device_unregister); +static char *__hwmon_sanitize_name(struct device *dev, const char *old_name) +{ + char *name, *p; + + if (dev) + name = devm_kstrdup(dev, old_name, GFP_KERNEL); + else + name = kstrdup(old_name, GFP_KERNEL); + if (!name) + return ERR_PTR(-ENOMEM); + + for (p = name; *p; p++) + if (hwmon_is_bad_char(*p)) + *p = '_'; + + return name; +} + +/** + * hwmon_sanitize_name - Replaces invalid characters in a hwmon name + * @name: NUL-terminated name + * + * Allocates a new string where any invalid characters will be replaced + * by an underscore. It is the responsibility of the caller to release + * the memory. + * + * Returns newly allocated name, or ERR_PTR on error. + */ +char *hwmon_sanitize_name(const char *name) +{ + return __hwmon_sanitize_name(NULL, name); +} +EXPORT_SYMBOL_GPL(hwmon_sanitize_name); + +/** + * devm_hwmon_sanitize_name - resource managed hwmon_sanitize_name() + * @dev: device to allocate memory for + * @name: NUL-terminated name + * + * Allocates a new string where any invalid characters will be replaced + * by an underscore. + * + * Returns newly allocated name, or ERR_PTR on error. + */ +char *devm_hwmon_sanitize_name(struct device *dev, const char *name) +{ + if (!dev) + return ERR_PTR(-EINVAL); + + return __hwmon_sanitize_name(dev, name); +} +EXPORT_SYMBOL_GPL(devm_hwmon_sanitize_name); + static void __init hwmon_pci_quirks(void) { #if defined CONFIG_X86 && defined CONFIG_PCI diff --git a/drivers/hwmon/ibmaem.c b/drivers/hwmon/ibmaem.c index de6baf6ca3d1..5c4cf742f5ae 100644 --- a/drivers/hwmon/ibmaem.c +++ b/drivers/hwmon/ibmaem.c @@ -482,7 +482,7 @@ static void aem_delete(struct aem_data *data) ipmi_destroy_user(data->ipmi.user); platform_set_drvdata(data->pdev, NULL); platform_device_unregister(data->pdev); - ida_simple_remove(&aem_ida, data->id); + ida_free(&aem_ida, data->id); kfree(data); } @@ -539,7 +539,7 @@ static int aem_init_aem1_inst(struct aem_ipmi_data *probe, u8 module_handle) data->power_period[i] = AEM_DEFAULT_POWER_INTERVAL; /* Create sub-device for this fw instance */ - data->id = ida_simple_get(&aem_ida, 0, 0, GFP_KERNEL); + data->id = ida_alloc(&aem_ida, GFP_KERNEL); if (data->id < 0) goto id_err; @@ -600,7 +600,7 @@ ipmi_err: platform_set_drvdata(data->pdev, NULL); platform_device_unregister(data->pdev); dev_err: - ida_simple_remove(&aem_ida, data->id); + ida_free(&aem_ida, data->id); id_err: kfree(data); @@ -679,7 +679,7 @@ static int aem_init_aem2_inst(struct aem_ipmi_data *probe, data->power_period[i] = AEM_DEFAULT_POWER_INTERVAL; /* Create sub-device for this fw instance */ - data->id = ida_simple_get(&aem_ida, 0, 0, GFP_KERNEL); + data->id = ida_alloc(&aem_ida, GFP_KERNEL); if (data->id < 0) goto id_err; @@ -740,7 +740,7 @@ ipmi_err: platform_set_drvdata(data->pdev, NULL); platform_device_unregister(data->pdev); dev_err: - ida_simple_remove(&aem_ida, data->id); + ida_free(&aem_ida, data->id); id_err: kfree(data); diff --git a/drivers/hwmon/intel-m10-bmc-hwmon.c b/drivers/hwmon/intel-m10-bmc-hwmon.c index 7a08e4c44a4b..6e82f7200d1c 100644 --- a/drivers/hwmon/intel-m10-bmc-hwmon.c +++ b/drivers/hwmon/intel-m10-bmc-hwmon.c @@ -515,7 +515,6 @@ static int m10bmc_hwmon_probe(struct platform_device *pdev) struct intel_m10bmc *m10bmc = dev_get_drvdata(pdev->dev.parent); struct device *hwmon_dev, *dev = &pdev->dev; struct m10bmc_hwmon *hw; - int i; hw = devm_kzalloc(dev, sizeof(*hw), GFP_KERNEL); if (!hw) @@ -528,13 +527,9 @@ static int m10bmc_hwmon_probe(struct platform_device *pdev) hw->chip.info = hw->bdata->hinfo; hw->chip.ops = &m10bmc_hwmon_ops; - hw->hw_name = devm_kstrdup(dev, id->name, GFP_KERNEL); - if (!hw->hw_name) - return -ENOMEM; - - for (i = 0; hw->hw_name[i]; i++) - if (hwmon_is_bad_char(hw->hw_name[i])) - hw->hw_name[i] = '_'; + hw->hw_name = devm_hwmon_sanitize_name(dev, id->name); + if (IS_ERR(hw->hw_name)) + return PTR_ERR(hw->hw_name); hwmon_dev = devm_hwmon_device_register_with_info(dev, hw->hw_name, hw, &hw->chip, NULL); diff --git a/drivers/hwmon/jc42.c b/drivers/hwmon/jc42.c index cb347a6bd8d9..07f7f8b5b73d 100644 --- a/drivers/hwmon/jc42.c +++ b/drivers/hwmon/jc42.c @@ -63,6 +63,7 @@ static const unsigned short normal_i2c[] = { #define STM_MANID 0x104a /* ST Microelectronics */ #define GT_MANID 0x1c68 /* Giantec */ #define GT_MANID2 0x132d /* Giantec, 2nd mfg ID */ +#define SI_MANID 0x1c85 /* Seiko Instruments */ /* SMBUS register */ #define SMBUS_STMOUT BIT(7) /* SMBus time-out, active low */ @@ -156,6 +157,10 @@ static const unsigned short normal_i2c[] = { #define STTS3000_DEVID 0x0200 #define STTS3000_DEVID_MASK 0xffff +/* Seiko Instruments */ +#define S34TS04A_DEVID 0x2221 +#define S34TS04A_DEVID_MASK 0xffff + static u16 jc42_hysteresis[] = { 0, 1500, 3000, 6000 }; struct jc42_chips { @@ -186,6 +191,7 @@ static struct jc42_chips jc42_chips[] = { { ONS_MANID, CAT34TS04_DEVID, CAT34TS04_DEVID_MASK }, { ONS_MANID, N34TS04_DEVID, N34TS04_DEVID_MASK }, { NXP_MANID, SE98_DEVID, SE98_DEVID_MASK }, + { SI_MANID, S34TS04A_DEVID, S34TS04A_DEVID_MASK }, { STM_MANID, STTS424_DEVID, STTS424_DEVID_MASK }, { STM_MANID, STTS424E_DEVID, STTS424E_DEVID_MASK }, { STM_MANID, STTS2002_DEVID, STTS2002_DEVID_MASK }, @@ -443,6 +449,8 @@ static int jc42_detect(struct i2c_client *client, struct i2c_board_info *info) } static const struct hwmon_channel_info *jc42_info[] = { + HWMON_CHANNEL_INFO(chip, + HWMON_C_REGISTER_TZ | HWMON_C_UPDATE_INTERVAL), HWMON_CHANNEL_INFO(temp, HWMON_T_INPUT | HWMON_T_MIN | HWMON_T_MAX | HWMON_T_CRIT | HWMON_T_MAX_HYST | diff --git a/drivers/hwmon/lan966x-hwmon.c b/drivers/hwmon/lan966x-hwmon.c new file mode 100644 index 000000000000..f41df053ac31 --- /dev/null +++ b/drivers/hwmon/lan966x-hwmon.c @@ -0,0 +1,418 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <linux/bitfield.h> +#include <linux/clk.h> +#include <linux/hwmon.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/mod_devicetable.h> +#include <linux/platform_device.h> +#include <linux/polynomial.h> +#include <linux/regmap.h> + +/* + * The original translation formulae of the temperature (in degrees of Celsius) + * are as follows: + * + * T = -3.4627e-11*(N^4) + 1.1023e-7*(N^3) + -1.9165e-4*(N^2) + + * 3.0604e-1*(N^1) + -5.6197e1 + * + * where [-56.197, 136.402]C and N = [0, 1023]. + * + * They must be accordingly altered to be suitable for the integer arithmetics. + * The technique is called 'factor redistribution', which just makes sure the + * multiplications and divisions are made so to have a result of the operations + * within the integer numbers limit. In addition we need to translate the + * formulae to accept millidegrees of Celsius. Here what it looks like after + * the alterations: + * + * T = -34627e-12*(N^4) + 110230e-9*(N^3) + -191650e-6*(N^2) + + * 306040e-3*(N^1) + -56197 + * + * where T = [-56197, 136402]mC and N = [0, 1023]. + */ + +static const struct polynomial poly_N_to_temp = { + .terms = { + {4, -34627, 1000, 1}, + {3, 110230, 1000, 1}, + {2, -191650, 1000, 1}, + {1, 306040, 1000, 1}, + {0, -56197, 1, 1} + } +}; + +#define PVT_SENSOR_CTRL 0x0 /* unused */ +#define PVT_SENSOR_CFG 0x4 +#define SENSOR_CFG_CLK_CFG GENMASK(27, 20) +#define SENSOR_CFG_TRIM_VAL GENMASK(13, 9) +#define SENSOR_CFG_SAMPLE_ENA BIT(8) +#define SENSOR_CFG_START_CAPTURE BIT(7) +#define SENSOR_CFG_CONTINIOUS_MODE BIT(6) +#define SENSOR_CFG_PSAMPLE_ENA GENMASK(1, 0) +#define PVT_SENSOR_STAT 0x8 +#define SENSOR_STAT_DATA_VALID BIT(10) +#define SENSOR_STAT_DATA GENMASK(9, 0) + +#define FAN_CFG 0x0 +#define FAN_CFG_DUTY_CYCLE GENMASK(23, 16) +#define INV_POL BIT(3) +#define GATE_ENA BIT(2) +#define PWM_OPEN_COL_ENA BIT(1) +#define FAN_STAT_CFG BIT(0) +#define FAN_PWM_FREQ 0x4 +#define FAN_PWM_CYC_10US GENMASK(25, 15) +#define FAN_PWM_FREQ_FREQ GENMASK(14, 0) +#define FAN_CNT 0xc +#define FAN_CNT_DATA GENMASK(15, 0) + +#define LAN966X_PVT_CLK 1200000 /* 1.2 MHz */ + +struct lan966x_hwmon { + struct regmap *regmap_pvt; + struct regmap *regmap_fan; + struct clk *clk; + unsigned long clk_rate; +}; + +static int lan966x_hwmon_read_temp(struct device *dev, long *val) +{ + struct lan966x_hwmon *hwmon = dev_get_drvdata(dev); + unsigned int data; + int ret; + + ret = regmap_read(hwmon->regmap_pvt, PVT_SENSOR_STAT, &data); + if (ret < 0) + return ret; + + if (!(data & SENSOR_STAT_DATA_VALID)) + return -ENODATA; + + *val = polynomial_calc(&poly_N_to_temp, + FIELD_GET(SENSOR_STAT_DATA, data)); + + return 0; +} + +static int lan966x_hwmon_read_fan(struct device *dev, long *val) +{ + struct lan966x_hwmon *hwmon = dev_get_drvdata(dev); + unsigned int data; + int ret; + + ret = regmap_read(hwmon->regmap_fan, FAN_CNT, &data); + if (ret < 0) + return ret; + + /* + * Data is given in pulses per second. Assume two pulses + * per revolution. + */ + *val = FIELD_GET(FAN_CNT_DATA, data) * 60 / 2; + + return 0; +} + +static int lan966x_hwmon_read_pwm(struct device *dev, long *val) +{ + struct lan966x_hwmon *hwmon = dev_get_drvdata(dev); + unsigned int data; + int ret; + + ret = regmap_read(hwmon->regmap_fan, FAN_CFG, &data); + if (ret < 0) + return ret; + + *val = FIELD_GET(FAN_CFG_DUTY_CYCLE, data); + + return 0; +} + +static int lan966x_hwmon_read_pwm_freq(struct device *dev, long *val) +{ + struct lan966x_hwmon *hwmon = dev_get_drvdata(dev); + unsigned long tmp; + unsigned int data; + int ret; + + ret = regmap_read(hwmon->regmap_fan, FAN_PWM_FREQ, &data); + if (ret < 0) + return ret; + + /* + * Datasheet says it is sys_clk / 256 / pwm_freq. But in reality + * it is sys_clk / 256 / (pwm_freq + 1). + */ + data = FIELD_GET(FAN_PWM_FREQ_FREQ, data) + 1; + tmp = DIV_ROUND_CLOSEST(hwmon->clk_rate, 256); + *val = DIV_ROUND_CLOSEST(tmp, data); + + return 0; +} + +static int lan966x_hwmon_read(struct device *dev, enum hwmon_sensor_types type, + u32 attr, int channel, long *val) +{ + switch (type) { + case hwmon_temp: + return lan966x_hwmon_read_temp(dev, val); + case hwmon_fan: + return lan966x_hwmon_read_fan(dev, val); + case hwmon_pwm: + switch (attr) { + case hwmon_pwm_input: + return lan966x_hwmon_read_pwm(dev, val); + case hwmon_pwm_freq: + return lan966x_hwmon_read_pwm_freq(dev, val); + default: + return -EOPNOTSUPP; + } + default: + return -EOPNOTSUPP; + } +} + +static int lan966x_hwmon_write_pwm(struct device *dev, long val) +{ + struct lan966x_hwmon *hwmon = dev_get_drvdata(dev); + + if (val < 0 || val > 255) + return -EINVAL; + + return regmap_update_bits(hwmon->regmap_fan, FAN_CFG, + FAN_CFG_DUTY_CYCLE, + FIELD_PREP(FAN_CFG_DUTY_CYCLE, val)); +} + +static int lan966x_hwmon_write_pwm_freq(struct device *dev, long val) +{ + struct lan966x_hwmon *hwmon = dev_get_drvdata(dev); + + if (val <= 0) + return -EINVAL; + + val = DIV_ROUND_CLOSEST(hwmon->clk_rate, val); + val = DIV_ROUND_CLOSEST(val, 256) - 1; + val = clamp_val(val, 0, FAN_PWM_FREQ_FREQ); + + return regmap_update_bits(hwmon->regmap_fan, FAN_PWM_FREQ, + FAN_PWM_FREQ_FREQ, + FIELD_PREP(FAN_PWM_FREQ_FREQ, val)); +} + +static int lan966x_hwmon_write(struct device *dev, enum hwmon_sensor_types type, + u32 attr, int channel, long val) +{ + switch (type) { + case hwmon_pwm: + switch (attr) { + case hwmon_pwm_input: + return lan966x_hwmon_write_pwm(dev, val); + case hwmon_pwm_freq: + return lan966x_hwmon_write_pwm_freq(dev, val); + default: + return -EOPNOTSUPP; + } + default: + return -EOPNOTSUPP; + } +} + +static umode_t lan966x_hwmon_is_visible(const void *data, + enum hwmon_sensor_types type, + u32 attr, int channel) +{ + umode_t mode = 0; + + switch (type) { + case hwmon_temp: + switch (attr) { + case hwmon_temp_input: + mode = 0444; + break; + default: + break; + } + break; + case hwmon_fan: + switch (attr) { + case hwmon_fan_input: + mode = 0444; + break; + default: + break; + } + break; + case hwmon_pwm: + switch (attr) { + case hwmon_pwm_input: + case hwmon_pwm_freq: + mode = 0644; + break; + default: + break; + } + break; + default: + break; + } + + return mode; +} + +static const struct hwmon_channel_info *lan966x_hwmon_info[] = { + HWMON_CHANNEL_INFO(chip, HWMON_C_REGISTER_TZ), + HWMON_CHANNEL_INFO(temp, HWMON_T_INPUT), + HWMON_CHANNEL_INFO(fan, HWMON_F_INPUT), + HWMON_CHANNEL_INFO(pwm, HWMON_PWM_INPUT | HWMON_PWM_FREQ), + NULL +}; + +static const struct hwmon_ops lan966x_hwmon_ops = { + .is_visible = lan966x_hwmon_is_visible, + .read = lan966x_hwmon_read, + .write = lan966x_hwmon_write, +}; + +static const struct hwmon_chip_info lan966x_hwmon_chip_info = { + .ops = &lan966x_hwmon_ops, + .info = lan966x_hwmon_info, +}; + +static void lan966x_hwmon_disable(void *data) +{ + struct lan966x_hwmon *hwmon = data; + + regmap_update_bits(hwmon->regmap_pvt, PVT_SENSOR_CFG, + SENSOR_CFG_SAMPLE_ENA | SENSOR_CFG_CONTINIOUS_MODE, + 0); +} + +static int lan966x_hwmon_enable(struct device *dev, + struct lan966x_hwmon *hwmon) +{ + unsigned int mask = SENSOR_CFG_CLK_CFG | + SENSOR_CFG_SAMPLE_ENA | + SENSOR_CFG_START_CAPTURE | + SENSOR_CFG_CONTINIOUS_MODE | + SENSOR_CFG_PSAMPLE_ENA; + unsigned int val; + unsigned int div; + int ret; + + /* enable continuous mode */ + val = SENSOR_CFG_SAMPLE_ENA | SENSOR_CFG_CONTINIOUS_MODE; + + /* set PVT clock to be between 1.15 and 1.25 MHz */ + div = DIV_ROUND_CLOSEST(hwmon->clk_rate, LAN966X_PVT_CLK); + val |= FIELD_PREP(SENSOR_CFG_CLK_CFG, div); + + ret = regmap_update_bits(hwmon->regmap_pvt, PVT_SENSOR_CFG, + mask, val); + if (ret) + return ret; + + return devm_add_action_or_reset(dev, lan966x_hwmon_disable, hwmon); +} + +static struct regmap *lan966x_init_regmap(struct platform_device *pdev, + const char *name) +{ + struct regmap_config regmap_config = { + .reg_bits = 32, + .reg_stride = 4, + .val_bits = 32, + }; + void __iomem *base; + + base = devm_platform_ioremap_resource_byname(pdev, name); + if (IS_ERR(base)) + return ERR_CAST(base); + + regmap_config.name = name; + + return devm_regmap_init_mmio(&pdev->dev, base, ®map_config); +} + +static void lan966x_clk_disable(void *data) +{ + struct lan966x_hwmon *hwmon = data; + + clk_disable_unprepare(hwmon->clk); +} + +static int lan966x_clk_enable(struct device *dev, struct lan966x_hwmon *hwmon) +{ + int ret; + + ret = clk_prepare_enable(hwmon->clk); + if (ret) + return ret; + + return devm_add_action_or_reset(dev, lan966x_clk_disable, hwmon); +} + +static int lan966x_hwmon_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct lan966x_hwmon *hwmon; + struct device *hwmon_dev; + int ret; + + hwmon = devm_kzalloc(dev, sizeof(*hwmon), GFP_KERNEL); + if (!hwmon) + return -ENOMEM; + + hwmon->clk = devm_clk_get(dev, NULL); + if (IS_ERR(hwmon->clk)) + return dev_err_probe(dev, PTR_ERR(hwmon->clk), + "failed to get clock\n"); + + ret = lan966x_clk_enable(dev, hwmon); + if (ret) + return dev_err_probe(dev, ret, "failed to enable clock\n"); + + hwmon->clk_rate = clk_get_rate(hwmon->clk); + + hwmon->regmap_pvt = lan966x_init_regmap(pdev, "pvt"); + if (IS_ERR(hwmon->regmap_pvt)) + return dev_err_probe(dev, PTR_ERR(hwmon->regmap_pvt), + "failed to get regmap for PVT registers\n"); + + hwmon->regmap_fan = lan966x_init_regmap(pdev, "fan"); + if (IS_ERR(hwmon->regmap_fan)) + return dev_err_probe(dev, PTR_ERR(hwmon->regmap_fan), + "failed to get regmap for fan registers\n"); + + ret = lan966x_hwmon_enable(dev, hwmon); + if (ret) + return dev_err_probe(dev, ret, "failed to enable sensor\n"); + + hwmon_dev = devm_hwmon_device_register_with_info(&pdev->dev, + "lan966x_hwmon", hwmon, + &lan966x_hwmon_chip_info, NULL); + if (IS_ERR(hwmon_dev)) + return dev_err_probe(dev, PTR_ERR(hwmon_dev), + "failed to register hwmon device\n"); + + return 0; +} + +static const struct of_device_id lan966x_hwmon_of_match[] = { + { .compatible = "microchip,lan9668-hwmon" }, + {} +}; +MODULE_DEVICE_TABLE(of, lan966x_hwmon_of_match); + +static struct platform_driver lan966x_hwmon_driver = { + .probe = lan966x_hwmon_probe, + .driver = { + .name = "lan966x-hwmon", + .of_match_table = lan966x_hwmon_of_match, + }, +}; +module_platform_driver(lan966x_hwmon_driver); + +MODULE_DESCRIPTION("LAN966x Hardware Monitoring Driver"); +MODULE_AUTHOR("Michael Walle <michael@walle.cc>"); +MODULE_LICENSE("GPL"); diff --git a/drivers/hwmon/lm75.c b/drivers/hwmon/lm75.c index afdbb63237b9..66dc826f7962 100644 --- a/drivers/hwmon/lm75.c +++ b/drivers/hwmon/lm75.c @@ -26,6 +26,7 @@ enum lm75_type { /* keep sorted in alphabetical order */ adt75, + at30ts74, ds1775, ds75, ds7505, @@ -128,6 +129,14 @@ static const struct lm75_params device_params[] = { .default_resolution = 12, .default_sample_time = MSEC_PER_SEC / 10, }, + [at30ts74] = { + .set_mask = 3 << 5, /* 12-bit mode*/ + .default_resolution = 12, + .default_sample_time = 200, + .num_sample_times = 4, + .sample_times = (unsigned int []){ 25, 50, 100, 200 }, + .resolutions = (u8 []) {9, 10, 11, 12 }, + }, [ds1775] = { .clr_mask = 3 << 5, .set_mask = 2 << 5, /* 11-bit mode */ @@ -645,6 +654,7 @@ static int lm75_probe(struct i2c_client *client) static const struct i2c_device_id lm75_ids[] = { { "adt75", adt75, }, + { "at30ts74", at30ts74, }, { "ds1775", ds1775, }, { "ds75", ds75, }, { "ds7505", ds7505, }, @@ -681,6 +691,10 @@ static const struct of_device_id __maybe_unused lm75_of_match[] = { .data = (void *)adt75 }, { + .compatible = "atmel,at30ts74", + .data = (void *)at30ts74 + }, + { .compatible = "dallas,ds1775", .data = (void *)ds1775 }, diff --git a/drivers/hwmon/lm83.c b/drivers/hwmon/lm83.c index 12370dcefa6a..905f5689f907 100644 --- a/drivers/hwmon/lm83.c +++ b/drivers/hwmon/lm83.c @@ -24,10 +24,8 @@ #include <linux/init.h> #include <linux/hwmon.h> #include <linux/module.h> -#include <linux/mutex.h> #include <linux/regmap.h> #include <linux/slab.h> -#include <linux/sysfs.h> /* * Addresses to scan diff --git a/drivers/hwmon/lm90.c b/drivers/hwmon/lm90.c index 1c9493c70813..3820f0e61510 100644 --- a/drivers/hwmon/lm90.c +++ b/drivers/hwmon/lm90.c @@ -1707,6 +1707,7 @@ static void lm90_restore_conf(void *_data) static int lm90_init_client(struct i2c_client *client, struct lm90_data *data) { + struct device_node *np = client->dev.of_node; int config, convrate; convrate = lm90_read_reg(client, LM90_REG_R_CONVRATE); @@ -1727,6 +1728,9 @@ static int lm90_init_client(struct i2c_client *client, struct lm90_data *data) /* Check Temperature Range Select */ if (data->flags & LM90_HAVE_EXTENDED_TEMP) { + if (of_property_read_bool(np, "ti,extended-range-enable")) + config |= 0x04; + if (config & 0x04) data->flags |= LM90_FLAG_ADT7461_EXT; } diff --git a/drivers/hwmon/ltc2992.c b/drivers/hwmon/ltc2992.c index 7352d2b3c756..72489d5d7eaf 100644 --- a/drivers/hwmon/ltc2992.c +++ b/drivers/hwmon/ltc2992.c @@ -811,68 +811,32 @@ static const struct hwmon_ops ltc2992_hwmon_ops = { .write = ltc2992_write, }; -static const u32 ltc2992_chip_config[] = { - HWMON_C_IN_RESET_HISTORY, - 0 -}; - -static const struct hwmon_channel_info ltc2992_chip = { - .type = hwmon_chip, - .config = ltc2992_chip_config, -}; - -static const u32 ltc2992_in_config[] = { - HWMON_I_INPUT | HWMON_I_LOWEST | HWMON_I_HIGHEST | HWMON_I_MIN | HWMON_I_MAX | - HWMON_I_MIN_ALARM | HWMON_I_MAX_ALARM, - HWMON_I_INPUT | HWMON_I_LOWEST | HWMON_I_HIGHEST | HWMON_I_MIN | HWMON_I_MAX | - HWMON_I_MIN_ALARM | HWMON_I_MAX_ALARM, - HWMON_I_INPUT | HWMON_I_LOWEST | HWMON_I_HIGHEST | HWMON_I_MIN | HWMON_I_MAX | - HWMON_I_MIN_ALARM | HWMON_I_MAX_ALARM, - HWMON_I_INPUT | HWMON_I_LOWEST | HWMON_I_HIGHEST | HWMON_I_MIN | HWMON_I_MAX | - HWMON_I_MIN_ALARM | HWMON_I_MAX_ALARM, - HWMON_I_INPUT | HWMON_I_LOWEST | HWMON_I_HIGHEST | HWMON_I_MIN | HWMON_I_MAX | - HWMON_I_MIN_ALARM | HWMON_I_MAX_ALARM, - HWMON_I_INPUT | HWMON_I_LOWEST | HWMON_I_HIGHEST | HWMON_I_MIN | HWMON_I_MAX | - HWMON_I_MIN_ALARM | HWMON_I_MAX_ALARM, - 0 -}; - -static const struct hwmon_channel_info ltc2992_in = { - .type = hwmon_in, - .config = ltc2992_in_config, -}; - -static const u32 ltc2992_curr_config[] = { - HWMON_C_INPUT | HWMON_C_LOWEST | HWMON_C_HIGHEST | HWMON_C_MIN | HWMON_C_MAX | - HWMON_C_MIN_ALARM | HWMON_C_MAX_ALARM, - HWMON_C_INPUT | HWMON_C_LOWEST | HWMON_C_HIGHEST | HWMON_C_MIN | HWMON_C_MAX | - HWMON_C_MIN_ALARM | HWMON_C_MAX_ALARM, - 0 -}; - -static const struct hwmon_channel_info ltc2992_curr = { - .type = hwmon_curr, - .config = ltc2992_curr_config, -}; - -static const u32 ltc2992_power_config[] = { - HWMON_P_INPUT | HWMON_P_INPUT_LOWEST | HWMON_P_INPUT_HIGHEST | HWMON_P_MIN | HWMON_P_MAX | - HWMON_P_MIN_ALARM | HWMON_P_MAX_ALARM, - HWMON_P_INPUT | HWMON_P_INPUT_LOWEST | HWMON_P_INPUT_HIGHEST | HWMON_P_MIN | HWMON_P_MAX | - HWMON_P_MIN_ALARM | HWMON_P_MAX_ALARM, - 0 -}; - -static const struct hwmon_channel_info ltc2992_power = { - .type = hwmon_power, - .config = ltc2992_power_config, -}; - static const struct hwmon_channel_info *ltc2992_info[] = { - <c2992_chip, - <c2992_in, - <c2992_curr, - <c2992_power, + HWMON_CHANNEL_INFO(chip, + HWMON_C_IN_RESET_HISTORY), + HWMON_CHANNEL_INFO(in, + HWMON_I_INPUT | HWMON_I_LOWEST | HWMON_I_HIGHEST | HWMON_I_MIN | + HWMON_I_MAX | HWMON_I_MIN_ALARM | HWMON_I_MAX_ALARM, + HWMON_I_INPUT | HWMON_I_LOWEST | HWMON_I_HIGHEST | HWMON_I_MIN | + HWMON_I_MAX | HWMON_I_MIN_ALARM | HWMON_I_MAX_ALARM, + HWMON_I_INPUT | HWMON_I_LOWEST | HWMON_I_HIGHEST | HWMON_I_MIN | + HWMON_I_MAX | HWMON_I_MIN_ALARM | HWMON_I_MAX_ALARM, + HWMON_I_INPUT | HWMON_I_LOWEST | HWMON_I_HIGHEST | HWMON_I_MIN | + HWMON_I_MAX | HWMON_I_MIN_ALARM | HWMON_I_MAX_ALARM, + HWMON_I_INPUT | HWMON_I_LOWEST | HWMON_I_HIGHEST | HWMON_I_MIN | + HWMON_I_MAX | HWMON_I_MIN_ALARM | HWMON_I_MAX_ALARM, + HWMON_I_INPUT | HWMON_I_LOWEST | HWMON_I_HIGHEST | HWMON_I_MIN | + HWMON_I_MAX | HWMON_I_MIN_ALARM | HWMON_I_MAX_ALARM), + HWMON_CHANNEL_INFO(curr, + HWMON_C_INPUT | HWMON_C_LOWEST | HWMON_C_HIGHEST | HWMON_C_MIN | + HWMON_C_MAX | HWMON_C_MIN_ALARM | HWMON_C_MAX_ALARM, + HWMON_C_INPUT | HWMON_C_LOWEST | HWMON_C_HIGHEST | HWMON_C_MIN | + HWMON_C_MAX | HWMON_C_MIN_ALARM | HWMON_C_MAX_ALARM), + HWMON_CHANNEL_INFO(power, + HWMON_P_INPUT | HWMON_P_INPUT_LOWEST | HWMON_P_INPUT_HIGHEST | + HWMON_P_MIN | HWMON_P_MAX | HWMON_P_MIN_ALARM | HWMON_P_MAX_ALARM, + HWMON_P_INPUT | HWMON_P_INPUT_LOWEST | HWMON_P_INPUT_HIGHEST | + HWMON_P_MIN | HWMON_P_MAX | HWMON_P_MIN_ALARM | HWMON_P_MAX_ALARM), NULL }; diff --git a/drivers/hwmon/mr75203.c b/drivers/hwmon/mr75203.c index 1ba1e3145969..26278b0f17a9 100644 --- a/drivers/hwmon/mr75203.c +++ b/drivers/hwmon/mr75203.c @@ -223,16 +223,6 @@ static int pvt_read(struct device *dev, enum hwmon_sensor_types type, } } -static const u32 pvt_chip_config[] = { - HWMON_C_REGISTER_TZ, - 0 -}; - -static const struct hwmon_channel_info pvt_chip = { - .type = hwmon_chip, - .config = pvt_chip_config, -}; - static struct hwmon_channel_info pvt_temp = { .type = hwmon_temp, }; @@ -555,7 +545,7 @@ static int mr75203_probe(struct platform_device *pdev) pvt_info = devm_kcalloc(dev, val + 2, sizeof(*pvt_info), GFP_KERNEL); if (!pvt_info) return -ENOMEM; - pvt_info[0] = &pvt_chip; + pvt_info[0] = HWMON_CHANNEL_INFO(chip, HWMON_C_REGISTER_TZ); index = 1; if (ts_num) { diff --git a/drivers/hwmon/nct6775.c b/drivers/hwmon/nct6775-core.c index 2b91f7e05126..446964cbae4c 100644 --- a/drivers/hwmon/nct6775.c +++ b/drivers/hwmon/nct6775-core.c @@ -44,24 +44,20 @@ #include <linux/init.h> #include <linux/slab.h> #include <linux/jiffies.h> -#include <linux/platform_device.h> #include <linux/hwmon.h> #include <linux/hwmon-sysfs.h> -#include <linux/hwmon-vid.h> #include <linux/err.h> #include <linux/mutex.h> -#include <linux/acpi.h> #include <linux/bitops.h> -#include <linux/dmi.h> -#include <linux/io.h> #include <linux/nospec.h> -#include <linux/wmi.h> +#include <linux/regmap.h> #include "lm75.h" +#include "nct6775.h" -#define USE_ALTERNATE +#undef DEFAULT_SYMBOL_NAMESPACE +#define DEFAULT_SYMBOL_NAMESPACE HWMON_NCT6775 -enum kinds { nct6106, nct6116, nct6775, nct6776, nct6779, nct6791, nct6792, - nct6793, nct6795, nct6796, nct6797, nct6798 }; +#define USE_ALTERNATE /* used to set data->name = nct6775_device_names[data->sio_kind] */ static const char * const nct6775_device_names[] = { @@ -79,242 +75,6 @@ static const char * const nct6775_device_names[] = { "nct6798", }; -static const char * const nct6775_sio_names[] __initconst = { - "NCT6106D", - "NCT6116D", - "NCT6775F", - "NCT6776D/F", - "NCT6779D", - "NCT6791D", - "NCT6792D", - "NCT6793D", - "NCT6795D", - "NCT6796D", - "NCT6797D", - "NCT6798D", -}; - -static unsigned short force_id; -module_param(force_id, ushort, 0); -MODULE_PARM_DESC(force_id, "Override the detected device ID"); - -static unsigned short fan_debounce; -module_param(fan_debounce, ushort, 0); -MODULE_PARM_DESC(fan_debounce, "Enable debouncing for fan RPM signal"); - -#define DRVNAME "nct6775" - -/* - * Super-I/O constants and functions - */ - -#define NCT6775_LD_ACPI 0x0a -#define NCT6775_LD_HWM 0x0b -#define NCT6775_LD_VID 0x0d -#define NCT6775_LD_12 0x12 - -#define SIO_REG_LDSEL 0x07 /* Logical device select */ -#define SIO_REG_DEVID 0x20 /* Device ID (2 bytes) */ -#define SIO_REG_ENABLE 0x30 /* Logical device enable */ -#define SIO_REG_ADDR 0x60 /* Logical device address (2 bytes) */ - -#define SIO_NCT6106_ID 0xc450 -#define SIO_NCT6116_ID 0xd280 -#define SIO_NCT6775_ID 0xb470 -#define SIO_NCT6776_ID 0xc330 -#define SIO_NCT6779_ID 0xc560 -#define SIO_NCT6791_ID 0xc800 -#define SIO_NCT6792_ID 0xc910 -#define SIO_NCT6793_ID 0xd120 -#define SIO_NCT6795_ID 0xd350 -#define SIO_NCT6796_ID 0xd420 -#define SIO_NCT6797_ID 0xd450 -#define SIO_NCT6798_ID 0xd428 -#define SIO_ID_MASK 0xFFF8 - -enum pwm_enable { off, manual, thermal_cruise, speed_cruise, sf3, sf4 }; -enum sensor_access { access_direct, access_asuswmi }; - -struct nct6775_sio_data { - int sioreg; - int ld; - enum kinds kind; - enum sensor_access access; - - /* superio_() callbacks */ - void (*sio_outb)(struct nct6775_sio_data *sio_data, int reg, int val); - int (*sio_inb)(struct nct6775_sio_data *sio_data, int reg); - void (*sio_select)(struct nct6775_sio_data *sio_data, int ld); - int (*sio_enter)(struct nct6775_sio_data *sio_data); - void (*sio_exit)(struct nct6775_sio_data *sio_data); -}; - -#define ASUSWMI_MONITORING_GUID "466747A0-70EC-11DE-8A39-0800200C9A66" -#define ASUSWMI_METHODID_RSIO 0x5253494F -#define ASUSWMI_METHODID_WSIO 0x5753494F -#define ASUSWMI_METHODID_RHWM 0x5248574D -#define ASUSWMI_METHODID_WHWM 0x5748574D -#define ASUSWMI_UNSUPPORTED_METHOD 0xFFFFFFFE - -static int nct6775_asuswmi_evaluate_method(u32 method_id, u8 bank, u8 reg, u8 val, u32 *retval) -{ -#if IS_ENABLED(CONFIG_ACPI_WMI) - u32 args = bank | (reg << 8) | (val << 16); - struct acpi_buffer input = { (acpi_size) sizeof(args), &args }; - struct acpi_buffer output = { ACPI_ALLOCATE_BUFFER, NULL }; - acpi_status status; - union acpi_object *obj; - u32 tmp = ASUSWMI_UNSUPPORTED_METHOD; - - status = wmi_evaluate_method(ASUSWMI_MONITORING_GUID, 0, - method_id, &input, &output); - - if (ACPI_FAILURE(status)) - return -EIO; - - obj = output.pointer; - if (obj && obj->type == ACPI_TYPE_INTEGER) - tmp = obj->integer.value; - - if (retval) - *retval = tmp; - - kfree(obj); - - if (tmp == ASUSWMI_UNSUPPORTED_METHOD) - return -ENODEV; - return 0; -#else - return -EOPNOTSUPP; -#endif -} - -static inline int nct6775_asuswmi_write(u8 bank, u8 reg, u8 val) -{ - return nct6775_asuswmi_evaluate_method(ASUSWMI_METHODID_WHWM, bank, - reg, val, NULL); -} - -static inline int nct6775_asuswmi_read(u8 bank, u8 reg, u8 *val) -{ - u32 ret, tmp = 0; - - ret = nct6775_asuswmi_evaluate_method(ASUSWMI_METHODID_RHWM, bank, - reg, 0, &tmp); - *val = tmp; - return ret; -} - -static int superio_wmi_inb(struct nct6775_sio_data *sio_data, int reg) -{ - int tmp = 0; - - nct6775_asuswmi_evaluate_method(ASUSWMI_METHODID_RSIO, sio_data->ld, - reg, 0, &tmp); - return tmp; -} - -static void superio_wmi_outb(struct nct6775_sio_data *sio_data, int reg, int val) -{ - nct6775_asuswmi_evaluate_method(ASUSWMI_METHODID_WSIO, sio_data->ld, - reg, val, NULL); -} - -static void superio_wmi_select(struct nct6775_sio_data *sio_data, int ld) -{ - sio_data->ld = ld; -} - -static int superio_wmi_enter(struct nct6775_sio_data *sio_data) -{ - return 0; -} - -static void superio_wmi_exit(struct nct6775_sio_data *sio_data) -{ -} - -static void superio_outb(struct nct6775_sio_data *sio_data, int reg, int val) -{ - int ioreg = sio_data->sioreg; - - outb(reg, ioreg); - outb(val, ioreg + 1); -} - -static int superio_inb(struct nct6775_sio_data *sio_data, int reg) -{ - int ioreg = sio_data->sioreg; - - outb(reg, ioreg); - return inb(ioreg + 1); -} - -static void superio_select(struct nct6775_sio_data *sio_data, int ld) -{ - int ioreg = sio_data->sioreg; - - outb(SIO_REG_LDSEL, ioreg); - outb(ld, ioreg + 1); -} - -static int superio_enter(struct nct6775_sio_data *sio_data) -{ - int ioreg = sio_data->sioreg; - - /* - * Try to reserve <ioreg> and <ioreg + 1> for exclusive access. - */ - if (!request_muxed_region(ioreg, 2, DRVNAME)) - return -EBUSY; - - outb(0x87, ioreg); - outb(0x87, ioreg); - - return 0; -} - -static void superio_exit(struct nct6775_sio_data *sio_data) -{ - int ioreg = sio_data->sioreg; - - outb(0xaa, ioreg); - outb(0x02, ioreg); - outb(0x02, ioreg + 1); - release_region(ioreg, 2); -} - -/* - * ISA constants - */ - -#define IOREGION_ALIGNMENT (~7) -#define IOREGION_OFFSET 5 -#define IOREGION_LENGTH 2 -#define ADDR_REG_OFFSET 0 -#define DATA_REG_OFFSET 1 - -#define NCT6775_REG_BANK 0x4E -#define NCT6775_REG_CONFIG 0x40 -#define NCT6775_PORT_CHIPID 0x58 - -/* - * Not currently used: - * REG_MAN_ID has the value 0x5ca3 for all supported chips. - * REG_CHIP_ID == 0x88/0xa1/0xc1 depending on chip model. - * REG_MAN_ID is at port 0x4f - * REG_CHIP_ID is at port 0x58 - */ - -#define NUM_TEMP 10 /* Max number of temp attribute sets w/ limits*/ -#define NUM_TEMP_FIXED 6 /* Max number of fixed temp attribute sets */ -#define NUM_TSI_TEMP 8 /* Max number of TSI temp register pairs */ - -#define NUM_REG_ALARM 7 /* Max number of alarm registers */ -#define NUM_REG_BEEP 5 /* Max number of beep registers */ - -#define NUM_FAN 7 - /* Common and NCT6775 specific data */ /* Voltage min/max registers for nr=7..14 are in bank 5 */ @@ -333,11 +93,6 @@ static const u16 NCT6775_REG_IN[] = { #define NCT6775_REG_DIODE 0x5E #define NCT6775_DIODE_MASK 0x02 -#define NCT6775_REG_FANDIV1 0x506 -#define NCT6775_REG_FANDIV2 0x507 - -#define NCT6775_REG_CR_FAN_DEBOUNCE 0xf0 - static const u16 NCT6775_REG_ALARM[NUM_REG_ALARM] = { 0x459, 0x45A, 0x45B }; /* 0..15 voltages, 16..23 fans, 24..29 temperatures, 30..31 intrusion */ @@ -351,10 +106,6 @@ static const s8 NCT6775_ALARM_BITS[] = { 4, 5, 13, -1, -1, -1, /* temp1..temp6 */ 12, -1 }; /* intrusion0, intrusion1 */ -#define FAN_ALARM_BASE 16 -#define TEMP_ALARM_BASE 24 -#define INTRUSION_ALARM_BASE 30 - static const u16 NCT6775_REG_BEEP[NUM_REG_BEEP] = { 0x56, 0x57, 0x453, 0x4e }; /* @@ -370,11 +121,6 @@ static const s8 NCT6775_BEEP_BITS[] = { 4, 5, 13, -1, -1, -1, /* temp1..temp6 */ 12, -1 }; /* intrusion0, intrusion1 */ -#define BEEP_ENABLE_BASE 15 - -static const u8 NCT6775_REG_CR_CASEOPEN_CLR[] = { 0xe6, 0xee }; -static const u8 NCT6775_CR_CASEOPEN_CLR_MASK[] = { 0x20, 0x01 }; - /* DC or PWM output fan configuration */ static const u8 NCT6775_REG_PWM_MODE[] = { 0x04, 0x04, 0x12 }; static const u8 NCT6775_PWM_MODE_MASK[] = { 0x01, 0x02, 0x01 }; @@ -690,8 +436,6 @@ static const u16 NCT6779_REG_TEMP_CRIT[32] = { /* NCT6791 specific data */ -#define NCT6791_REG_HM_IO_SPACE_LOCK_ENABLE 0x28 - static const u16 NCT6791_REG_WEIGHT_TEMP_SEL[NUM_FAN] = { 0, 0x239 }; static const u16 NCT6791_REG_WEIGHT_TEMP_STEP[NUM_FAN] = { 0, 0x23a }; static const u16 NCT6791_REG_WEIGHT_TEMP_STEP_TOL[NUM_FAN] = { 0, 0x23b }; @@ -1191,165 +935,6 @@ static inline unsigned int tsi_temp_from_reg(unsigned int reg) * Data structures and manipulation thereof */ -struct nct6775_data { - int addr; /* IO base of hw monitor block */ - struct nct6775_sio_data *sio_data; - enum kinds kind; - const char *name; - - const struct attribute_group *groups[7]; - - u16 reg_temp[5][NUM_TEMP]; /* 0=temp, 1=temp_over, 2=temp_hyst, - * 3=temp_crit, 4=temp_lcrit - */ - u8 temp_src[NUM_TEMP]; - u16 reg_temp_config[NUM_TEMP]; - const char * const *temp_label; - u32 temp_mask; - u32 virt_temp_mask; - - u16 REG_CONFIG; - u16 REG_VBAT; - u16 REG_DIODE; - u8 DIODE_MASK; - - const s8 *ALARM_BITS; - const s8 *BEEP_BITS; - - const u16 *REG_VIN; - const u16 *REG_IN_MINMAX[2]; - - const u16 *REG_TARGET; - const u16 *REG_FAN; - const u16 *REG_FAN_MODE; - const u16 *REG_FAN_MIN; - const u16 *REG_FAN_PULSES; - const u16 *FAN_PULSE_SHIFT; - const u16 *REG_FAN_TIME[3]; - - const u16 *REG_TOLERANCE_H; - - const u8 *REG_PWM_MODE; - const u8 *PWM_MODE_MASK; - - const u16 *REG_PWM[7]; /* [0]=pwm, [1]=pwm_start, [2]=pwm_floor, - * [3]=pwm_max, [4]=pwm_step, - * [5]=weight_duty_step, [6]=weight_duty_base - */ - const u16 *REG_PWM_READ; - - const u16 *REG_CRITICAL_PWM_ENABLE; - u8 CRITICAL_PWM_ENABLE_MASK; - const u16 *REG_CRITICAL_PWM; - - const u16 *REG_AUTO_TEMP; - const u16 *REG_AUTO_PWM; - - const u16 *REG_CRITICAL_TEMP; - const u16 *REG_CRITICAL_TEMP_TOLERANCE; - - const u16 *REG_TEMP_SOURCE; /* temp register sources */ - const u16 *REG_TEMP_SEL; - const u16 *REG_WEIGHT_TEMP_SEL; - const u16 *REG_WEIGHT_TEMP[3]; /* 0=base, 1=tolerance, 2=step */ - - const u16 *REG_TEMP_OFFSET; - - const u16 *REG_ALARM; - const u16 *REG_BEEP; - - const u16 *REG_TSI_TEMP; - - unsigned int (*fan_from_reg)(u16 reg, unsigned int divreg); - unsigned int (*fan_from_reg_min)(u16 reg, unsigned int divreg); - - struct mutex update_lock; - bool valid; /* true if following fields are valid */ - unsigned long last_updated; /* In jiffies */ - - /* Register values */ - u8 bank; /* current register bank */ - u8 in_num; /* number of in inputs we have */ - u8 in[15][3]; /* [0]=in, [1]=in_max, [2]=in_min */ - unsigned int rpm[NUM_FAN]; - u16 fan_min[NUM_FAN]; - u8 fan_pulses[NUM_FAN]; - u8 fan_div[NUM_FAN]; - u8 has_pwm; - u8 has_fan; /* some fan inputs can be disabled */ - u8 has_fan_min; /* some fans don't have min register */ - bool has_fan_div; - - u8 num_temp_alarms; /* 2, 3, or 6 */ - u8 num_temp_beeps; /* 2, 3, or 6 */ - u8 temp_fixed_num; /* 3 or 6 */ - u8 temp_type[NUM_TEMP_FIXED]; - s8 temp_offset[NUM_TEMP_FIXED]; - s16 temp[5][NUM_TEMP]; /* 0=temp, 1=temp_over, 2=temp_hyst, - * 3=temp_crit, 4=temp_lcrit */ - s16 tsi_temp[NUM_TSI_TEMP]; - u64 alarms; - u64 beeps; - - u8 pwm_num; /* number of pwm */ - u8 pwm_mode[NUM_FAN]; /* 0->DC variable voltage, - * 1->PWM variable duty cycle - */ - enum pwm_enable pwm_enable[NUM_FAN]; - /* 0->off - * 1->manual - * 2->thermal cruise mode (also called SmartFan I) - * 3->fan speed cruise mode - * 4->SmartFan III - * 5->enhanced variable thermal cruise (SmartFan IV) - */ - u8 pwm[7][NUM_FAN]; /* [0]=pwm, [1]=pwm_start, [2]=pwm_floor, - * [3]=pwm_max, [4]=pwm_step, - * [5]=weight_duty_step, [6]=weight_duty_base - */ - - u8 target_temp[NUM_FAN]; - u8 target_temp_mask; - u32 target_speed[NUM_FAN]; - u32 target_speed_tolerance[NUM_FAN]; - u8 speed_tolerance_limit; - - u8 temp_tolerance[2][NUM_FAN]; - u8 tolerance_mask; - - u8 fan_time[3][NUM_FAN]; /* 0 = stop_time, 1 = step_up, 2 = step_down */ - - /* Automatic fan speed control registers */ - int auto_pwm_num; - u8 auto_pwm[NUM_FAN][7]; - u8 auto_temp[NUM_FAN][7]; - u8 pwm_temp_sel[NUM_FAN]; - u8 pwm_weight_temp_sel[NUM_FAN]; - u8 weight_temp[3][NUM_FAN]; /* 0->temp_step, 1->temp_step_tol, - * 2->temp_base - */ - - u8 vid; - u8 vrm; - - bool have_vid; - - u16 have_temp; - u16 have_temp_fixed; - u16 have_tsi_temp; - u16 have_in; - - /* Remember extra register values over suspend/resume */ - u8 vbat; - u8 fandiv1; - u8 fandiv2; - u8 sio_reg_enable; - - /* nct6775_*() callbacks */ - u16 (*read_value)(struct nct6775_data *data, u16 reg); - int (*write_value)(struct nct6775_data *data, u16 reg, u16 value); -}; - struct sensor_device_template { struct device_attribute dev_attr; union { @@ -1405,10 +990,8 @@ struct sensor_template_group { int base; }; -static struct attribute_group * -nct6775_create_attr_group(struct device *dev, - const struct sensor_template_group *tg, - int repeat) +static int nct6775_add_template_attr_group(struct device *dev, struct nct6775_data *data, + const struct sensor_template_group *tg, int repeat) { struct attribute_group *group; struct sensor_device_attr_u *su; @@ -1419,28 +1002,28 @@ nct6775_create_attr_group(struct device *dev, int i, count; if (repeat <= 0) - return ERR_PTR(-EINVAL); + return -EINVAL; t = tg->templates; for (count = 0; *t; t++, count++) ; if (count == 0) - return ERR_PTR(-EINVAL); + return -EINVAL; group = devm_kzalloc(dev, sizeof(*group), GFP_KERNEL); if (group == NULL) - return ERR_PTR(-ENOMEM); + return -ENOMEM; attrs = devm_kcalloc(dev, repeat * count + 1, sizeof(*attrs), GFP_KERNEL); if (attrs == NULL) - return ERR_PTR(-ENOMEM); + return -ENOMEM; su = devm_kzalloc(dev, array3_size(repeat, count, sizeof(*su)), GFP_KERNEL); if (su == NULL) - return ERR_PTR(-ENOMEM); + return -ENOMEM; group->attrs = attrs; group->is_visible = tg->is_visible; @@ -1478,10 +1061,10 @@ nct6775_create_attr_group(struct device *dev, } } - return group; + return nct6775_add_attr_group(data, group); } -static bool is_word_sized(struct nct6775_data *data, u16 reg) +bool nct6775_reg_is_word_sized(struct nct6775_data *data, u16 reg) { switch (data->kind) { case nct6106: @@ -1538,180 +1121,81 @@ static bool is_word_sized(struct nct6775_data *data, u16 reg) } return false; } +EXPORT_SYMBOL_GPL(nct6775_reg_is_word_sized); -static inline void nct6775_wmi_set_bank(struct nct6775_data *data, u16 reg) -{ - u8 bank = reg >> 8; - - data->bank = bank; -} - -static u16 nct6775_wmi_read_value(struct nct6775_data *data, u16 reg) +/* We left-align 8-bit temperature values to make the code simpler */ +static int nct6775_read_temp(struct nct6775_data *data, u16 reg, u16 *val) { - int res, err, word_sized = is_word_sized(data, reg); - u8 tmp = 0; - - nct6775_wmi_set_bank(data, reg); + int err; - err = nct6775_asuswmi_read(data->bank, reg & 0xff, &tmp); + err = nct6775_read_value(data, reg, val); if (err) - return 0; - - res = tmp; - if (word_sized) { - err = nct6775_asuswmi_read(data->bank, (reg & 0xff) + 1, &tmp); - if (err) - return 0; - - res = (res << 8) + tmp; - } - return res; -} - -static int nct6775_wmi_write_value(struct nct6775_data *data, u16 reg, u16 value) -{ - int res, word_sized = is_word_sized(data, reg); - - nct6775_wmi_set_bank(data, reg); - - if (word_sized) { - res = nct6775_asuswmi_write(data->bank, reg & 0xff, value >> 8); - if (res) - return res; - - res = nct6775_asuswmi_write(data->bank, (reg & 0xff) + 1, value); - } else { - res = nct6775_asuswmi_write(data->bank, reg & 0xff, value); - } - - return res; -} - -/* - * On older chips, only registers 0x50-0x5f are banked. - * On more recent chips, all registers are banked. - * Assume that is the case and set the bank number for each access. - * Cache the bank number so it only needs to be set if it changes. - */ -static inline void nct6775_set_bank(struct nct6775_data *data, u16 reg) -{ - u8 bank = reg >> 8; - - if (data->bank != bank) { - outb_p(NCT6775_REG_BANK, data->addr + ADDR_REG_OFFSET); - outb_p(bank, data->addr + DATA_REG_OFFSET); - data->bank = bank; - } -} + return err; -static u16 nct6775_read_value(struct nct6775_data *data, u16 reg) -{ - int res, word_sized = is_word_sized(data, reg); - - nct6775_set_bank(data, reg); - outb_p(reg & 0xff, data->addr + ADDR_REG_OFFSET); - res = inb_p(data->addr + DATA_REG_OFFSET); - if (word_sized) { - outb_p((reg & 0xff) + 1, - data->addr + ADDR_REG_OFFSET); - res = (res << 8) + inb_p(data->addr + DATA_REG_OFFSET); - } - return res; -} + if (!nct6775_reg_is_word_sized(data, reg)) + *val <<= 8; -static int nct6775_write_value(struct nct6775_data *data, u16 reg, u16 value) -{ - int word_sized = is_word_sized(data, reg); - - nct6775_set_bank(data, reg); - outb_p(reg & 0xff, data->addr + ADDR_REG_OFFSET); - if (word_sized) { - outb_p(value >> 8, data->addr + DATA_REG_OFFSET); - outb_p((reg & 0xff) + 1, - data->addr + ADDR_REG_OFFSET); - } - outb_p(value & 0xff, data->addr + DATA_REG_OFFSET); return 0; } -/* We left-align 8-bit temperature values to make the code simpler */ -static u16 nct6775_read_temp(struct nct6775_data *data, u16 reg) -{ - u16 res; - - res = data->read_value(data, reg); - if (!is_word_sized(data, reg)) - res <<= 8; - - return res; -} - -static int nct6775_write_temp(struct nct6775_data *data, u16 reg, u16 value) -{ - if (!is_word_sized(data, reg)) - value >>= 8; - return data->write_value(data, reg, value); -} - /* This function assumes that the caller holds data->update_lock */ -static void nct6775_write_fan_div(struct nct6775_data *data, int nr) +static int nct6775_write_fan_div(struct nct6775_data *data, int nr) { - u8 reg; + u16 reg; + int err; + u16 fandiv_reg = nr < 2 ? NCT6775_REG_FANDIV1 : NCT6775_REG_FANDIV2; + unsigned int oddshift = (nr & 1) * 4; /* masks shift by four if nr is odd */ - switch (nr) { - case 0: - reg = (data->read_value(data, NCT6775_REG_FANDIV1) & 0x70) - | (data->fan_div[0] & 0x7); - data->write_value(data, NCT6775_REG_FANDIV1, reg); - break; - case 1: - reg = (data->read_value(data, NCT6775_REG_FANDIV1) & 0x7) - | ((data->fan_div[1] << 4) & 0x70); - data->write_value(data, NCT6775_REG_FANDIV1, reg); - break; - case 2: - reg = (data->read_value(data, NCT6775_REG_FANDIV2) & 0x70) - | (data->fan_div[2] & 0x7); - data->write_value(data, NCT6775_REG_FANDIV2, reg); - break; - case 3: - reg = (data->read_value(data, NCT6775_REG_FANDIV2) & 0x7) - | ((data->fan_div[3] << 4) & 0x70); - data->write_value(data, NCT6775_REG_FANDIV2, reg); - break; - } + err = nct6775_read_value(data, fandiv_reg, ®); + if (err) + return err; + reg &= 0x70 >> oddshift; + reg |= data->fan_div[nr] & (0x7 << oddshift); + return nct6775_write_value(data, fandiv_reg, reg); } -static void nct6775_write_fan_div_common(struct nct6775_data *data, int nr) +static int nct6775_write_fan_div_common(struct nct6775_data *data, int nr) { if (data->kind == nct6775) - nct6775_write_fan_div(data, nr); + return nct6775_write_fan_div(data, nr); + return 0; } -static void nct6775_update_fan_div(struct nct6775_data *data) +static int nct6775_update_fan_div(struct nct6775_data *data) { - u8 i; + int err; + u16 i; - i = data->read_value(data, NCT6775_REG_FANDIV1); + err = nct6775_read_value(data, NCT6775_REG_FANDIV1, &i); + if (err) + return err; data->fan_div[0] = i & 0x7; data->fan_div[1] = (i & 0x70) >> 4; - i = data->read_value(data, NCT6775_REG_FANDIV2); + err = nct6775_read_value(data, NCT6775_REG_FANDIV2, &i); + if (err) + return err; data->fan_div[2] = i & 0x7; if (data->has_fan & BIT(3)) data->fan_div[3] = (i & 0x70) >> 4; + + return 0; } -static void nct6775_update_fan_div_common(struct nct6775_data *data) +static int nct6775_update_fan_div_common(struct nct6775_data *data) { if (data->kind == nct6775) - nct6775_update_fan_div(data); + return nct6775_update_fan_div(data); + return 0; } -static void nct6775_init_fan_div(struct nct6775_data *data) +static int nct6775_init_fan_div(struct nct6775_data *data) { - int i; + int i, err; + + err = nct6775_update_fan_div_common(data); + if (err) + return err; - nct6775_update_fan_div_common(data); /* * For all fans, start with highest divider value if the divider * register is not initialized. This ensures that we get a @@ -1723,19 +1207,26 @@ static void nct6775_init_fan_div(struct nct6775_data *data) continue; if (data->fan_div[i] == 0) { data->fan_div[i] = 7; - nct6775_write_fan_div_common(data, i); + err = nct6775_write_fan_div_common(data, i); + if (err) + return err; } } + + return 0; } -static void nct6775_init_fan_common(struct device *dev, - struct nct6775_data *data) +static int nct6775_init_fan_common(struct device *dev, + struct nct6775_data *data) { - int i; - u8 reg; + int i, err; + u16 reg; - if (data->has_fan_div) - nct6775_init_fan_div(data); + if (data->has_fan_div) { + err = nct6775_init_fan_div(data); + if (err) + return err; + } /* * If fan_min is not set (0), set it to 0xff to disable it. This @@ -1743,23 +1234,30 @@ static void nct6775_init_fan_common(struct device *dev, */ for (i = 0; i < ARRAY_SIZE(data->fan_min); i++) { if (data->has_fan_min & BIT(i)) { - reg = data->read_value(data, data->REG_FAN_MIN[i]); - if (!reg) - data->write_value(data, data->REG_FAN_MIN[i], - data->has_fan_div ? 0xff - : 0xff1f); + err = nct6775_read_value(data, data->REG_FAN_MIN[i], ®); + if (err) + return err; + if (!reg) { + err = nct6775_write_value(data, data->REG_FAN_MIN[i], + data->has_fan_div ? 0xff : 0xff1f); + if (err) + return err; + } } } + + return 0; } -static void nct6775_select_fan_div(struct device *dev, - struct nct6775_data *data, int nr, u16 reg) +static int nct6775_select_fan_div(struct device *dev, + struct nct6775_data *data, int nr, u16 reg) { + int err; u8 fan_div = data->fan_div[nr]; u16 fan_min; if (!data->has_fan_div) - return; + return 0; /* * If we failed to measure the fan speed, or the reported value is not @@ -1791,36 +1289,46 @@ static void nct6775_select_fan_div(struct device *dev, } if (fan_min != data->fan_min[nr]) { data->fan_min[nr] = fan_min; - data->write_value(data, data->REG_FAN_MIN[nr], - fan_min); + err = nct6775_write_value(data, data->REG_FAN_MIN[nr], fan_min); + if (err) + return err; } } data->fan_div[nr] = fan_div; - nct6775_write_fan_div_common(data, nr); + err = nct6775_write_fan_div_common(data, nr); + if (err) + return err; } + + return 0; } -static void nct6775_update_pwm(struct device *dev) +static int nct6775_update_pwm(struct device *dev) { struct nct6775_data *data = dev_get_drvdata(dev); - int i, j; - int fanmodecfg, reg; + int i, j, err; + u16 fanmodecfg, reg; bool duty_is_dc; for (i = 0; i < data->pwm_num; i++) { if (!(data->has_pwm & BIT(i))) continue; - duty_is_dc = data->REG_PWM_MODE[i] && - (data->read_value(data, data->REG_PWM_MODE[i]) - & data->PWM_MODE_MASK[i]); + err = nct6775_read_value(data, data->REG_PWM_MODE[i], ®); + if (err) + return err; + duty_is_dc = data->REG_PWM_MODE[i] && (reg & data->PWM_MODE_MASK[i]); data->pwm_mode[i] = !duty_is_dc; - fanmodecfg = data->read_value(data, data->REG_FAN_MODE[i]); + err = nct6775_read_value(data, data->REG_FAN_MODE[i], &fanmodecfg); + if (err) + return err; for (j = 0; j < ARRAY_SIZE(data->REG_PWM); j++) { if (data->REG_PWM[j] && data->REG_PWM[j][i]) { - data->pwm[j][i] = data->read_value(data, - data->REG_PWM[j][i]); + err = nct6775_read_value(data, data->REG_PWM[j][i], ®); + if (err) + return err; + data->pwm[j][i] = reg; } } @@ -1835,17 +1343,22 @@ static void nct6775_update_pwm(struct device *dev) u8 t = fanmodecfg & 0x0f; if (data->REG_TOLERANCE_H) { - t |= (data->read_value(data, - data->REG_TOLERANCE_H[i]) & 0x70) >> 1; + err = nct6775_read_value(data, data->REG_TOLERANCE_H[i], ®); + if (err) + return err; + t |= (reg & 0x70) >> 1; } data->target_speed_tolerance[i] = t; } - data->temp_tolerance[1][i] = - data->read_value(data, - data->REG_CRITICAL_TEMP_TOLERANCE[i]); + err = nct6775_read_value(data, data->REG_CRITICAL_TEMP_TOLERANCE[i], ®); + if (err) + return err; + data->temp_tolerance[1][i] = reg; - reg = data->read_value(data, data->REG_TEMP_SEL[i]); + err = nct6775_read_value(data, data->REG_TEMP_SEL[i], ®); + if (err) + return err; data->pwm_temp_sel[i] = reg & 0x1f; /* If fan can stop, report floor as 0 */ if (reg & 0x80) @@ -1854,7 +1367,9 @@ static void nct6775_update_pwm(struct device *dev) if (!data->REG_WEIGHT_TEMP_SEL[i]) continue; - reg = data->read_value(data, data->REG_WEIGHT_TEMP_SEL[i]); + err = nct6775_read_value(data, data->REG_WEIGHT_TEMP_SEL[i], ®); + if (err) + return err; data->pwm_weight_temp_sel[i] = reg & 0x1f; /* If weight is disabled, report weight source as 0 */ if (!(reg & 0x80)) @@ -1862,29 +1377,37 @@ static void nct6775_update_pwm(struct device *dev) /* Weight temp data */ for (j = 0; j < ARRAY_SIZE(data->weight_temp); j++) { - data->weight_temp[j][i] = data->read_value(data, - data->REG_WEIGHT_TEMP[j][i]); + err = nct6775_read_value(data, data->REG_WEIGHT_TEMP[j][i], ®); + if (err) + return err; + data->weight_temp[j][i] = reg; } } + + return 0; } -static void nct6775_update_pwm_limits(struct device *dev) +static int nct6775_update_pwm_limits(struct device *dev) { struct nct6775_data *data = dev_get_drvdata(dev); - int i, j; - u8 reg; - u16 reg_t; + int i, j, err; + u16 reg, reg_t; for (i = 0; i < data->pwm_num; i++) { if (!(data->has_pwm & BIT(i))) continue; for (j = 0; j < ARRAY_SIZE(data->fan_time); j++) { - data->fan_time[j][i] = - data->read_value(data, data->REG_FAN_TIME[j][i]); + err = nct6775_read_value(data, data->REG_FAN_TIME[j][i], ®); + if (err) + return err; + data->fan_time[j][i] = reg; } - reg_t = data->read_value(data, data->REG_TARGET[i]); + err = nct6775_read_value(data, data->REG_TARGET[i], ®_t); + if (err) + return err; + /* Update only in matching mode or if never updated */ if (!data->target_temp[i] || data->pwm_enable[i] == thermal_cruise) @@ -1892,29 +1415,37 @@ static void nct6775_update_pwm_limits(struct device *dev) if (!data->target_speed[i] || data->pwm_enable[i] == speed_cruise) { if (data->REG_TOLERANCE_H) { - reg_t |= (data->read_value(data, - data->REG_TOLERANCE_H[i]) & 0x0f) << 8; + err = nct6775_read_value(data, data->REG_TOLERANCE_H[i], ®); + if (err) + return err; + reg_t |= (reg & 0x0f) << 8; } data->target_speed[i] = reg_t; } for (j = 0; j < data->auto_pwm_num; j++) { - data->auto_pwm[i][j] = - data->read_value(data, - NCT6775_AUTO_PWM(data, i, j)); - data->auto_temp[i][j] = - data->read_value(data, - NCT6775_AUTO_TEMP(data, i, j)); + err = nct6775_read_value(data, NCT6775_AUTO_PWM(data, i, j), ®); + if (err) + return err; + data->auto_pwm[i][j] = reg; + + err = nct6775_read_value(data, NCT6775_AUTO_TEMP(data, i, j), ®); + if (err) + return err; + data->auto_temp[i][j] = reg; } /* critical auto_pwm temperature data */ - data->auto_temp[i][data->auto_pwm_num] = - data->read_value(data, data->REG_CRITICAL_TEMP[i]); + err = nct6775_read_value(data, data->REG_CRITICAL_TEMP[i], ®); + if (err) + return err; + data->auto_temp[i][data->auto_pwm_num] = reg; switch (data->kind) { case nct6775: - reg = data->read_value(data, - NCT6775_REG_CRITICAL_ENAB[i]); + err = nct6775_read_value(data, NCT6775_REG_CRITICAL_ENAB[i], ®); + if (err) + return err; data->auto_pwm[i][data->auto_pwm_num] = (reg & 0x02) ? 0xff : 0x00; break; @@ -1931,120 +1462,158 @@ static void nct6775_update_pwm_limits(struct device *dev) case nct6796: case nct6797: case nct6798: - reg = data->read_value(data, - data->REG_CRITICAL_PWM_ENABLE[i]); - if (reg & data->CRITICAL_PWM_ENABLE_MASK) - reg = data->read_value(data, - data->REG_CRITICAL_PWM[i]); - else + err = nct6775_read_value(data, data->REG_CRITICAL_PWM_ENABLE[i], ®); + if (err) + return err; + if (reg & data->CRITICAL_PWM_ENABLE_MASK) { + err = nct6775_read_value(data, data->REG_CRITICAL_PWM[i], ®); + if (err) + return err; + } else { reg = 0xff; + } data->auto_pwm[i][data->auto_pwm_num] = reg; break; } } + + return 0; } static struct nct6775_data *nct6775_update_device(struct device *dev) { struct nct6775_data *data = dev_get_drvdata(dev); - int i, j; + int i, j, err = 0; + u16 reg; mutex_lock(&data->update_lock); if (time_after(jiffies, data->last_updated + HZ + HZ / 2) || !data->valid) { /* Fan clock dividers */ - nct6775_update_fan_div_common(data); + err = nct6775_update_fan_div_common(data); + if (err) + goto out; /* Measured voltages and limits */ for (i = 0; i < data->in_num; i++) { if (!(data->have_in & BIT(i))) continue; - data->in[i][0] = data->read_value(data, - data->REG_VIN[i]); - data->in[i][1] = data->read_value(data, - data->REG_IN_MINMAX[0][i]); - data->in[i][2] = data->read_value(data, - data->REG_IN_MINMAX[1][i]); + err = nct6775_read_value(data, data->REG_VIN[i], ®); + if (err) + goto out; + data->in[i][0] = reg; + + err = nct6775_read_value(data, data->REG_IN_MINMAX[0][i], ®); + if (err) + goto out; + data->in[i][1] = reg; + + err = nct6775_read_value(data, data->REG_IN_MINMAX[1][i], ®); + if (err) + goto out; + data->in[i][2] = reg; } /* Measured fan speeds and limits */ for (i = 0; i < ARRAY_SIZE(data->rpm); i++) { - u16 reg; - if (!(data->has_fan & BIT(i))) continue; - reg = data->read_value(data, data->REG_FAN[i]); + err = nct6775_read_value(data, data->REG_FAN[i], ®); + if (err) + goto out; data->rpm[i] = data->fan_from_reg(reg, data->fan_div[i]); - if (data->has_fan_min & BIT(i)) - data->fan_min[i] = data->read_value(data, - data->REG_FAN_MIN[i]); + if (data->has_fan_min & BIT(i)) { + err = nct6775_read_value(data, data->REG_FAN_MIN[i], ®); + if (err) + goto out; + data->fan_min[i] = reg; + } if (data->REG_FAN_PULSES[i]) { - data->fan_pulses[i] = - (data->read_value(data, - data->REG_FAN_PULSES[i]) - >> data->FAN_PULSE_SHIFT[i]) & 0x03; + err = nct6775_read_value(data, data->REG_FAN_PULSES[i], ®); + if (err) + goto out; + data->fan_pulses[i] = (reg >> data->FAN_PULSE_SHIFT[i]) & 0x03; } - nct6775_select_fan_div(dev, data, i, reg); + err = nct6775_select_fan_div(dev, data, i, reg); + if (err) + goto out; } - nct6775_update_pwm(dev); - nct6775_update_pwm_limits(dev); + err = nct6775_update_pwm(dev); + if (err) + goto out; + + err = nct6775_update_pwm_limits(dev); + if (err) + goto out; /* Measured temperatures and limits */ for (i = 0; i < NUM_TEMP; i++) { if (!(data->have_temp & BIT(i))) continue; for (j = 0; j < ARRAY_SIZE(data->reg_temp); j++) { - if (data->reg_temp[j][i]) - data->temp[j][i] = nct6775_read_temp(data, - data->reg_temp[j][i]); + if (data->reg_temp[j][i]) { + err = nct6775_read_temp(data, data->reg_temp[j][i], ®); + if (err) + goto out; + data->temp[j][i] = reg; + } } if (i >= NUM_TEMP_FIXED || !(data->have_temp_fixed & BIT(i))) continue; - data->temp_offset[i] = data->read_value(data, - data->REG_TEMP_OFFSET[i]); + err = nct6775_read_value(data, data->REG_TEMP_OFFSET[i], ®); + if (err) + goto out; + data->temp_offset[i] = reg; } for (i = 0; i < NUM_TSI_TEMP; i++) { if (!(data->have_tsi_temp & BIT(i))) continue; - data->tsi_temp[i] = data->read_value(data, data->REG_TSI_TEMP[i]); + err = nct6775_read_value(data, data->REG_TSI_TEMP[i], ®); + if (err) + goto out; + data->tsi_temp[i] = reg; } data->alarms = 0; for (i = 0; i < NUM_REG_ALARM; i++) { - u8 alarm; + u16 alarm; if (!data->REG_ALARM[i]) continue; - alarm = data->read_value(data, data->REG_ALARM[i]); + err = nct6775_read_value(data, data->REG_ALARM[i], &alarm); + if (err) + goto out; data->alarms |= ((u64)alarm) << (i << 3); } data->beeps = 0; for (i = 0; i < NUM_REG_BEEP; i++) { - u8 beep; + u16 beep; if (!data->REG_BEEP[i]) continue; - beep = data->read_value(data, data->REG_BEEP[i]); + err = nct6775_read_value(data, data->REG_BEEP[i], &beep); + if (err) + goto out; data->beeps |= ((u64)beep) << (i << 3); } data->last_updated = jiffies; data->valid = true; } - +out: mutex_unlock(&data->update_lock); - return data; + return err ? ERR_PTR(err) : data; } /* @@ -2058,6 +1627,9 @@ show_in_reg(struct device *dev, struct device_attribute *attr, char *buf) int index = sattr->index; int nr = sattr->nr; + if (IS_ERR(data)) + return PTR_ERR(data); + return sprintf(buf, "%ld\n", in_from_reg(data->in[nr][index], nr)); } @@ -2077,34 +1649,39 @@ store_in_reg(struct device *dev, struct device_attribute *attr, const char *buf, return err; mutex_lock(&data->update_lock); data->in[nr][index] = in_to_reg(val, nr); - data->write_value(data, data->REG_IN_MINMAX[index - 1][nr], - data->in[nr][index]); + err = nct6775_write_value(data, data->REG_IN_MINMAX[index - 1][nr], data->in[nr][index]); mutex_unlock(&data->update_lock); - return count; + return err ? : count; } -static ssize_t -show_alarm(struct device *dev, struct device_attribute *attr, char *buf) +ssize_t +nct6775_show_alarm(struct device *dev, struct device_attribute *attr, char *buf) { struct nct6775_data *data = nct6775_update_device(dev); struct sensor_device_attribute *sattr = to_sensor_dev_attr(attr); - int nr = data->ALARM_BITS[sattr->index]; + int nr; + if (IS_ERR(data)) + return PTR_ERR(data); + + nr = data->ALARM_BITS[sattr->index]; return sprintf(buf, "%u\n", (unsigned int)((data->alarms >> nr) & 0x01)); } +EXPORT_SYMBOL_GPL(nct6775_show_alarm); static int find_temp_source(struct nct6775_data *data, int index, int count) { int source = data->temp_src[index]; - int nr; + int nr, err; for (nr = 0; nr < count; nr++) { - int src; + u16 src; - src = data->read_value(data, - data->REG_TEMP_SOURCE[nr]) & 0x1f; - if (src == source) + err = nct6775_read_value(data, data->REG_TEMP_SOURCE[nr], &src); + if (err) + return err; + if ((src & 0x1f) == source) return nr; } return -ENODEV; @@ -2118,6 +1695,9 @@ show_temp_alarm(struct device *dev, struct device_attribute *attr, char *buf) unsigned int alarm = 0; int nr; + if (IS_ERR(data)) + return PTR_ERR(data); + /* * For temperatures, there is no fixed mapping from registers to alarm * bits. Alarm bits are determined by the temperature source mapping. @@ -2131,20 +1711,25 @@ show_temp_alarm(struct device *dev, struct device_attribute *attr, char *buf) return sprintf(buf, "%u\n", alarm); } -static ssize_t -show_beep(struct device *dev, struct device_attribute *attr, char *buf) +ssize_t +nct6775_show_beep(struct device *dev, struct device_attribute *attr, char *buf) { struct sensor_device_attribute *sattr = to_sensor_dev_attr(attr); struct nct6775_data *data = nct6775_update_device(dev); - int nr = data->BEEP_BITS[sattr->index]; + int nr; + + if (IS_ERR(data)) + return PTR_ERR(data); + + nr = data->BEEP_BITS[sattr->index]; return sprintf(buf, "%u\n", (unsigned int)((data->beeps >> nr) & 0x01)); } +EXPORT_SYMBOL_GPL(nct6775_show_beep); -static ssize_t -store_beep(struct device *dev, struct device_attribute *attr, const char *buf, - size_t count) +ssize_t +nct6775_store_beep(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct sensor_device_attribute_2 *sattr = to_sensor_dev_attr_2(attr); struct nct6775_data *data = dev_get_drvdata(dev); @@ -2164,11 +1749,12 @@ store_beep(struct device *dev, struct device_attribute *attr, const char *buf, data->beeps |= (1ULL << nr); else data->beeps &= ~(1ULL << nr); - data->write_value(data, data->REG_BEEP[regindex], - (data->beeps >> (regindex << 3)) & 0xff); + err = nct6775_write_value(data, data->REG_BEEP[regindex], + (data->beeps >> (regindex << 3)) & 0xff); mutex_unlock(&data->update_lock); - return count; + return err ? : count; } +EXPORT_SYMBOL_GPL(nct6775_store_beep); static ssize_t show_temp_beep(struct device *dev, struct device_attribute *attr, char *buf) @@ -2178,6 +1764,9 @@ show_temp_beep(struct device *dev, struct device_attribute *attr, char *buf) unsigned int beep = 0; int nr; + if (IS_ERR(data)) + return PTR_ERR(data); + /* * For temperatures, there is no fixed mapping from registers to beep * enable bits. Beep enable bits are determined by the temperature @@ -2220,11 +1809,11 @@ store_temp_beep(struct device *dev, struct device_attribute *attr, data->beeps |= (1ULL << bit); else data->beeps &= ~(1ULL << bit); - data->write_value(data, data->REG_BEEP[regindex], - (data->beeps >> (regindex << 3)) & 0xff); + err = nct6775_write_value(data, data->REG_BEEP[regindex], + (data->beeps >> (regindex << 3)) & 0xff); mutex_unlock(&data->update_lock); - return count; + return err ? : count; } static umode_t nct6775_in_is_visible(struct kobject *kobj, @@ -2237,17 +1826,14 @@ static umode_t nct6775_in_is_visible(struct kobject *kobj, if (!(data->have_in & BIT(in))) return 0; - return attr->mode; + return nct6775_attr_mode(data, attr); } -SENSOR_TEMPLATE_2(in_input, "in%d_input", S_IRUGO, show_in_reg, NULL, 0, 0); -SENSOR_TEMPLATE(in_alarm, "in%d_alarm", S_IRUGO, show_alarm, NULL, 0); -SENSOR_TEMPLATE(in_beep, "in%d_beep", S_IWUSR | S_IRUGO, show_beep, store_beep, - 0); -SENSOR_TEMPLATE_2(in_min, "in%d_min", S_IWUSR | S_IRUGO, show_in_reg, - store_in_reg, 0, 1); -SENSOR_TEMPLATE_2(in_max, "in%d_max", S_IWUSR | S_IRUGO, show_in_reg, - store_in_reg, 0, 2); +SENSOR_TEMPLATE_2(in_input, "in%d_input", 0444, show_in_reg, NULL, 0, 0); +SENSOR_TEMPLATE(in_alarm, "in%d_alarm", 0444, nct6775_show_alarm, NULL, 0); +SENSOR_TEMPLATE(in_beep, "in%d_beep", 0644, nct6775_show_beep, nct6775_store_beep, 0); +SENSOR_TEMPLATE_2(in_min, "in%d_min", 0644, show_in_reg, store_in_reg, 0, 1); +SENSOR_TEMPLATE_2(in_max, "in%d_max", 0644, show_in_reg, store_in_reg, 0, 2); /* * nct6775_in_is_visible uses the index into the following array @@ -2275,6 +1861,9 @@ show_fan(struct device *dev, struct device_attribute *attr, char *buf) struct sensor_device_attribute *sattr = to_sensor_dev_attr(attr); int nr = sattr->index; + if (IS_ERR(data)) + return PTR_ERR(data); + return sprintf(buf, "%d\n", data->rpm[nr]); } @@ -2285,6 +1874,9 @@ show_fan_min(struct device *dev, struct device_attribute *attr, char *buf) struct sensor_device_attribute *sattr = to_sensor_dev_attr(attr); int nr = sattr->index; + if (IS_ERR(data)) + return PTR_ERR(data); + return sprintf(buf, "%d\n", data->fan_from_reg_min(data->fan_min[nr], data->fan_div[nr])); @@ -2297,6 +1889,9 @@ show_fan_div(struct device *dev, struct device_attribute *attr, char *buf) struct sensor_device_attribute *sattr = to_sensor_dev_attr(attr); int nr = sattr->index; + if (IS_ERR(data)) + return PTR_ERR(data); + return sprintf(buf, "%u\n", div_from_reg(data->fan_div[nr])); } @@ -2382,16 +1977,18 @@ write_div: nr + 1, div_from_reg(data->fan_div[nr]), div_from_reg(new_div)); data->fan_div[nr] = new_div; - nct6775_write_fan_div_common(data, nr); + err = nct6775_write_fan_div_common(data, nr); + if (err) + goto write_min; /* Give the chip time to sample a new speed value */ data->last_updated = jiffies; } write_min: - data->write_value(data, data->REG_FAN_MIN[nr], data->fan_min[nr]); + err = nct6775_write_value(data, data->REG_FAN_MIN[nr], data->fan_min[nr]); mutex_unlock(&data->update_lock); - return count; + return err ? : count; } static ssize_t @@ -2399,8 +1996,12 @@ show_fan_pulses(struct device *dev, struct device_attribute *attr, char *buf) { struct nct6775_data *data = nct6775_update_device(dev); struct sensor_device_attribute *sattr = to_sensor_dev_attr(attr); - int p = data->fan_pulses[sattr->index]; + int p; + + if (IS_ERR(data)) + return PTR_ERR(data); + p = data->fan_pulses[sattr->index]; return sprintf(buf, "%d\n", p ? : 4); } @@ -2413,7 +2014,7 @@ store_fan_pulses(struct device *dev, struct device_attribute *attr, int nr = sattr->index; unsigned long val; int err; - u8 reg; + u16 reg; err = kstrtoul(buf, 10, &val); if (err < 0) @@ -2424,13 +2025,16 @@ store_fan_pulses(struct device *dev, struct device_attribute *attr, mutex_lock(&data->update_lock); data->fan_pulses[nr] = val & 3; - reg = data->read_value(data, data->REG_FAN_PULSES[nr]); + err = nct6775_read_value(data, data->REG_FAN_PULSES[nr], ®); + if (err) + goto out; reg &= ~(0x03 << data->FAN_PULSE_SHIFT[nr]); reg |= (val & 3) << data->FAN_PULSE_SHIFT[nr]; - data->write_value(data, data->REG_FAN_PULSES[nr], reg); + err = nct6775_write_value(data, data->REG_FAN_PULSES[nr], reg); +out: mutex_unlock(&data->update_lock); - return count; + return err ? : count; } static umode_t nct6775_fan_is_visible(struct kobject *kobj, @@ -2455,19 +2059,16 @@ static umode_t nct6775_fan_is_visible(struct kobject *kobj, if (nr == 5 && data->kind != nct6775) return 0; - return attr->mode; + return nct6775_attr_mode(data, attr); } -SENSOR_TEMPLATE(fan_input, "fan%d_input", S_IRUGO, show_fan, NULL, 0); -SENSOR_TEMPLATE(fan_alarm, "fan%d_alarm", S_IRUGO, show_alarm, NULL, - FAN_ALARM_BASE); -SENSOR_TEMPLATE(fan_beep, "fan%d_beep", S_IWUSR | S_IRUGO, show_beep, - store_beep, FAN_ALARM_BASE); -SENSOR_TEMPLATE(fan_pulses, "fan%d_pulses", S_IWUSR | S_IRUGO, show_fan_pulses, - store_fan_pulses, 0); -SENSOR_TEMPLATE(fan_min, "fan%d_min", S_IWUSR | S_IRUGO, show_fan_min, - store_fan_min, 0); -SENSOR_TEMPLATE(fan_div, "fan%d_div", S_IRUGO, show_fan_div, NULL, 0); +SENSOR_TEMPLATE(fan_input, "fan%d_input", 0444, show_fan, NULL, 0); +SENSOR_TEMPLATE(fan_alarm, "fan%d_alarm", 0444, nct6775_show_alarm, NULL, FAN_ALARM_BASE); +SENSOR_TEMPLATE(fan_beep, "fan%d_beep", 0644, nct6775_show_beep, + nct6775_store_beep, FAN_ALARM_BASE); +SENSOR_TEMPLATE(fan_pulses, "fan%d_pulses", 0644, show_fan_pulses, store_fan_pulses, 0); +SENSOR_TEMPLATE(fan_min, "fan%d_min", 0644, show_fan_min, store_fan_min, 0); +SENSOR_TEMPLATE(fan_div, "fan%d_div", 0444, show_fan_div, NULL, 0); /* * nct6775_fan_is_visible uses the index into the following array @@ -2497,6 +2098,9 @@ show_temp_label(struct device *dev, struct device_attribute *attr, char *buf) struct sensor_device_attribute *sattr = to_sensor_dev_attr(attr); int nr = sattr->index; + if (IS_ERR(data)) + return PTR_ERR(data); + return sprintf(buf, "%s\n", data->temp_label[data->temp_src[nr]]); } @@ -2508,6 +2112,9 @@ show_temp(struct device *dev, struct device_attribute *attr, char *buf) int nr = sattr->nr; int index = sattr->index; + if (IS_ERR(data)) + return PTR_ERR(data); + return sprintf(buf, "%d\n", LM75_TEMP_FROM_REG(data->temp[index][nr])); } @@ -2528,10 +2135,9 @@ store_temp(struct device *dev, struct device_attribute *attr, const char *buf, mutex_lock(&data->update_lock); data->temp[index][nr] = LM75_TEMP_TO_REG(val); - nct6775_write_temp(data, data->reg_temp[index][nr], - data->temp[index][nr]); + err = nct6775_write_temp(data, data->reg_temp[index][nr], data->temp[index][nr]); mutex_unlock(&data->update_lock); - return count; + return err ? : count; } static ssize_t @@ -2540,6 +2146,9 @@ show_temp_offset(struct device *dev, struct device_attribute *attr, char *buf) struct nct6775_data *data = nct6775_update_device(dev); struct sensor_device_attribute *sattr = to_sensor_dev_attr(attr); + if (IS_ERR(data)) + return PTR_ERR(data); + return sprintf(buf, "%d\n", data->temp_offset[sattr->index] * 1000); } @@ -2561,10 +2170,10 @@ store_temp_offset(struct device *dev, struct device_attribute *attr, mutex_lock(&data->update_lock); data->temp_offset[nr] = val; - data->write_value(data, data->REG_TEMP_OFFSET[nr], val); + err = nct6775_write_value(data, data->REG_TEMP_OFFSET[nr], val); mutex_unlock(&data->update_lock); - return count; + return err ? : count; } static ssize_t @@ -2574,6 +2183,9 @@ show_temp_type(struct device *dev, struct device_attribute *attr, char *buf) struct sensor_device_attribute *sattr = to_sensor_dev_attr(attr); int nr = sattr->index; + if (IS_ERR(data)) + return PTR_ERR(data); + return sprintf(buf, "%d\n", (int)data->temp_type[nr]); } @@ -2586,7 +2198,11 @@ store_temp_type(struct device *dev, struct device_attribute *attr, int nr = sattr->index; unsigned long val; int err; - u8 vbat, diode, vbit, dbit; + u8 vbit, dbit; + u16 vbat, diode; + + if (IS_ERR(data)) + return PTR_ERR(data); err = kstrtoul(buf, 10, &val); if (err < 0) @@ -2600,8 +2216,17 @@ store_temp_type(struct device *dev, struct device_attribute *attr, data->temp_type[nr] = val; vbit = 0x02 << nr; dbit = data->DIODE_MASK << nr; - vbat = data->read_value(data, data->REG_VBAT) & ~vbit; - diode = data->read_value(data, data->REG_DIODE) & ~dbit; + + err = nct6775_read_value(data, data->REG_VBAT, &vbat); + if (err) + goto out; + vbat &= ~vbit; + + err = nct6775_read_value(data, data->REG_DIODE, &diode); + if (err) + goto out; + diode &= ~dbit; + switch (val) { case 1: /* CPU diode (diode, current mode) */ vbat |= vbit; @@ -2613,11 +2238,13 @@ store_temp_type(struct device *dev, struct device_attribute *attr, case 4: /* thermistor */ break; } - data->write_value(data, data->REG_VBAT, vbat); - data->write_value(data, data->REG_DIODE, diode); - + err = nct6775_write_value(data, data->REG_VBAT, vbat); + if (err) + goto out; + err = nct6775_write_value(data, data->REG_DIODE, diode); +out: mutex_unlock(&data->update_lock); - return count; + return err ? : count; } static umode_t nct6775_temp_is_visible(struct kobject *kobj, @@ -2656,26 +2283,19 @@ static umode_t nct6775_temp_is_visible(struct kobject *kobj, if (nr > 7 && !(data->have_temp_fixed & BIT(temp))) return 0; - return attr->mode; + return nct6775_attr_mode(data, attr); } -SENSOR_TEMPLATE_2(temp_input, "temp%d_input", S_IRUGO, show_temp, NULL, 0, 0); -SENSOR_TEMPLATE(temp_label, "temp%d_label", S_IRUGO, show_temp_label, NULL, 0); -SENSOR_TEMPLATE_2(temp_max, "temp%d_max", S_IRUGO | S_IWUSR, show_temp, - store_temp, 0, 1); -SENSOR_TEMPLATE_2(temp_max_hyst, "temp%d_max_hyst", S_IRUGO | S_IWUSR, - show_temp, store_temp, 0, 2); -SENSOR_TEMPLATE_2(temp_crit, "temp%d_crit", S_IRUGO | S_IWUSR, show_temp, - store_temp, 0, 3); -SENSOR_TEMPLATE_2(temp_lcrit, "temp%d_lcrit", S_IRUGO | S_IWUSR, show_temp, - store_temp, 0, 4); -SENSOR_TEMPLATE(temp_offset, "temp%d_offset", S_IRUGO | S_IWUSR, - show_temp_offset, store_temp_offset, 0); -SENSOR_TEMPLATE(temp_type, "temp%d_type", S_IRUGO | S_IWUSR, show_temp_type, - store_temp_type, 0); -SENSOR_TEMPLATE(temp_alarm, "temp%d_alarm", S_IRUGO, show_temp_alarm, NULL, 0); -SENSOR_TEMPLATE(temp_beep, "temp%d_beep", S_IRUGO | S_IWUSR, show_temp_beep, - store_temp_beep, 0); +SENSOR_TEMPLATE_2(temp_input, "temp%d_input", 0444, show_temp, NULL, 0, 0); +SENSOR_TEMPLATE(temp_label, "temp%d_label", 0444, show_temp_label, NULL, 0); +SENSOR_TEMPLATE_2(temp_max, "temp%d_max", 0644, show_temp, store_temp, 0, 1); +SENSOR_TEMPLATE_2(temp_max_hyst, "temp%d_max_hyst", 0644, show_temp, store_temp, 0, 2); +SENSOR_TEMPLATE_2(temp_crit, "temp%d_crit", 0644, show_temp, store_temp, 0, 3); +SENSOR_TEMPLATE_2(temp_lcrit, "temp%d_lcrit", 0644, show_temp, store_temp, 0, 4); +SENSOR_TEMPLATE(temp_offset, "temp%d_offset", 0644, show_temp_offset, store_temp_offset, 0); +SENSOR_TEMPLATE(temp_type, "temp%d_type", 0644, show_temp_type, store_temp_type, 0); +SENSOR_TEMPLATE(temp_alarm, "temp%d_alarm", 0444, show_temp_alarm, NULL, 0); +SENSOR_TEMPLATE(temp_beep, "temp%d_beep", 0644, show_temp_beep, store_temp_beep, 0); /* * nct6775_temp_is_visible uses the index into the following array @@ -2707,6 +2327,9 @@ static ssize_t show_tsi_temp(struct device *dev, struct device_attribute *attr, struct nct6775_data *data = nct6775_update_device(dev); struct sensor_device_attribute *sattr = to_sensor_dev_attr(attr); + if (IS_ERR(data)) + return PTR_ERR(data); + return sysfs_emit(buf, "%u\n", tsi_temp_from_reg(data->tsi_temp[sattr->index])); } @@ -2727,7 +2350,7 @@ static umode_t nct6775_tsi_temp_is_visible(struct kobject *kobj, struct attribut struct nct6775_data *data = dev_get_drvdata(dev); int temp = index / 2; - return (data->have_tsi_temp & BIT(temp)) ? attr->mode : 0; + return (data->have_tsi_temp & BIT(temp)) ? nct6775_attr_mode(data, attr) : 0; } /* @@ -2746,6 +2369,9 @@ show_pwm_mode(struct device *dev, struct device_attribute *attr, char *buf) struct nct6775_data *data = nct6775_update_device(dev); struct sensor_device_attribute *sattr = to_sensor_dev_attr(attr); + if (IS_ERR(data)) + return PTR_ERR(data); + return sprintf(buf, "%d\n", data->pwm_mode[sattr->index]); } @@ -2758,7 +2384,7 @@ store_pwm_mode(struct device *dev, struct device_attribute *attr, int nr = sattr->index; unsigned long val; int err; - u8 reg; + u16 reg; err = kstrtoul(buf, 10, &val); if (err < 0) @@ -2776,13 +2402,16 @@ store_pwm_mode(struct device *dev, struct device_attribute *attr, mutex_lock(&data->update_lock); data->pwm_mode[nr] = val; - reg = data->read_value(data, data->REG_PWM_MODE[nr]); + err = nct6775_read_value(data, data->REG_PWM_MODE[nr], ®); + if (err) + goto out; reg &= ~data->PWM_MODE_MASK[nr]; if (!val) reg |= data->PWM_MODE_MASK[nr]; - data->write_value(data, data->REG_PWM_MODE[nr], reg); + err = nct6775_write_value(data, data->REG_PWM_MODE[nr], reg); +out: mutex_unlock(&data->update_lock); - return count; + return err ? : count; } static ssize_t @@ -2792,16 +2421,23 @@ show_pwm(struct device *dev, struct device_attribute *attr, char *buf) struct sensor_device_attribute_2 *sattr = to_sensor_dev_attr_2(attr); int nr = sattr->nr; int index = sattr->index; - int pwm; + int err; + u16 pwm; + + if (IS_ERR(data)) + return PTR_ERR(data); /* * For automatic fan control modes, show current pwm readings. * Otherwise, show the configured value. */ - if (index == 0 && data->pwm_enable[nr] > manual) - pwm = data->read_value(data, data->REG_PWM_READ[nr]); - else + if (index == 0 && data->pwm_enable[nr] > manual) { + err = nct6775_read_value(data, data->REG_PWM_READ[nr], &pwm); + if (err) + return err; + } else { pwm = data->pwm[index][nr]; + } return sprintf(buf, "%d\n", pwm); } @@ -2819,7 +2455,7 @@ store_pwm(struct device *dev, struct device_attribute *attr, const char *buf, int maxval[7] = { 255, 255, data->pwm[3][nr] ? : 255, 255, 255, 255, 255 }; int err; - u8 reg; + u16 reg; err = kstrtoul(buf, 10, &val); if (err < 0) @@ -2828,16 +2464,21 @@ store_pwm(struct device *dev, struct device_attribute *attr, const char *buf, mutex_lock(&data->update_lock); data->pwm[index][nr] = val; - data->write_value(data, data->REG_PWM[index][nr], val); + err = nct6775_write_value(data, data->REG_PWM[index][nr], val); + if (err) + goto out; if (index == 2) { /* floor: disable if val == 0 */ - reg = data->read_value(data, data->REG_TEMP_SEL[nr]); + err = nct6775_read_value(data, data->REG_TEMP_SEL[nr], ®); + if (err) + goto out; reg &= 0x7f; if (val) reg |= 0x80; - data->write_value(data, data->REG_TEMP_SEL[nr], reg); + err = nct6775_write_value(data, data->REG_TEMP_SEL[nr], reg); } +out: mutex_unlock(&data->update_lock); - return count; + return err ? : count; } /* Returns 0 if OK, -EINVAL otherwise */ @@ -2864,40 +2505,54 @@ static int check_trip_points(struct nct6775_data *data, int nr) return 0; } -static void pwm_update_registers(struct nct6775_data *data, int nr) +static int pwm_update_registers(struct nct6775_data *data, int nr) { - u8 reg; + u16 reg; + int err; switch (data->pwm_enable[nr]) { case off: case manual: break; case speed_cruise: - reg = data->read_value(data, data->REG_FAN_MODE[nr]); + err = nct6775_read_value(data, data->REG_FAN_MODE[nr], ®); + if (err) + return err; reg = (reg & ~data->tolerance_mask) | (data->target_speed_tolerance[nr] & data->tolerance_mask); - data->write_value(data, data->REG_FAN_MODE[nr], reg); - data->write_value(data, data->REG_TARGET[nr], - data->target_speed[nr] & 0xff); + err = nct6775_write_value(data, data->REG_FAN_MODE[nr], reg); + if (err) + return err; + err = nct6775_write_value(data, data->REG_TARGET[nr], + data->target_speed[nr] & 0xff); + if (err) + return err; if (data->REG_TOLERANCE_H) { reg = (data->target_speed[nr] >> 8) & 0x0f; reg |= (data->target_speed_tolerance[nr] & 0x38) << 1; - data->write_value(data, - data->REG_TOLERANCE_H[nr], - reg); + err = nct6775_write_value(data, data->REG_TOLERANCE_H[nr], reg); + if (err) + return err; } break; case thermal_cruise: - data->write_value(data, data->REG_TARGET[nr], - data->target_temp[nr]); + err = nct6775_write_value(data, data->REG_TARGET[nr], data->target_temp[nr]); + if (err) + return err; fallthrough; default: - reg = data->read_value(data, data->REG_FAN_MODE[nr]); + err = nct6775_read_value(data, data->REG_FAN_MODE[nr], ®); + if (err) + return err; reg = (reg & ~data->tolerance_mask) | data->temp_tolerance[0][nr]; - data->write_value(data, data->REG_FAN_MODE[nr], reg); + err = nct6775_write_value(data, data->REG_FAN_MODE[nr], reg); + if (err) + return err; break; } + + return 0; } static ssize_t @@ -2906,6 +2561,9 @@ show_pwm_enable(struct device *dev, struct device_attribute *attr, char *buf) struct nct6775_data *data = nct6775_update_device(dev); struct sensor_device_attribute *sattr = to_sensor_dev_attr(attr); + if (IS_ERR(data)) + return PTR_ERR(data); + return sprintf(buf, "%d\n", data->pwm_enable[sattr->index]); } @@ -2943,15 +2601,22 @@ store_pwm_enable(struct device *dev, struct device_attribute *attr, * turn off pwm control: select manual mode, set pwm to maximum */ data->pwm[0][nr] = 255; - data->write_value(data, data->REG_PWM[0][nr], 255); + err = nct6775_write_value(data, data->REG_PWM[0][nr], 255); + if (err) + goto out; } - pwm_update_registers(data, nr); - reg = data->read_value(data, data->REG_FAN_MODE[nr]); + err = pwm_update_registers(data, nr); + if (err) + goto out; + err = nct6775_read_value(data, data->REG_FAN_MODE[nr], ®); + if (err) + goto out; reg &= 0x0f; reg |= pwm_enable_to_reg(val) << 4; - data->write_value(data, data->REG_FAN_MODE[nr], reg); + err = nct6775_write_value(data, data->REG_FAN_MODE[nr], reg); +out: mutex_unlock(&data->update_lock); - return count; + return err ? : count; } static ssize_t @@ -2978,6 +2643,9 @@ show_pwm_temp_sel(struct device *dev, struct device_attribute *attr, char *buf) struct sensor_device_attribute *sattr = to_sensor_dev_attr(attr); int index = sattr->index; + if (IS_ERR(data)) + return PTR_ERR(data); + return show_pwm_temp_sel_common(data, buf, data->pwm_temp_sel[index]); } @@ -2989,7 +2657,11 @@ store_pwm_temp_sel(struct device *dev, struct device_attribute *attr, struct sensor_device_attribute *sattr = to_sensor_dev_attr(attr); int nr = sattr->index; unsigned long val; - int err, reg, src; + int err, src; + u16 reg; + + if (IS_ERR(data)) + return PTR_ERR(data); err = kstrtoul(buf, 10, &val); if (err < 0) @@ -3002,13 +2674,16 @@ store_pwm_temp_sel(struct device *dev, struct device_attribute *attr, mutex_lock(&data->update_lock); src = data->temp_src[val - 1]; data->pwm_temp_sel[nr] = src; - reg = data->read_value(data, data->REG_TEMP_SEL[nr]); + err = nct6775_read_value(data, data->REG_TEMP_SEL[nr], ®); + if (err) + goto out; reg &= 0xe0; reg |= src; - data->write_value(data, data->REG_TEMP_SEL[nr], reg); + err = nct6775_write_value(data, data->REG_TEMP_SEL[nr], reg); +out: mutex_unlock(&data->update_lock); - return count; + return err ? : count; } static ssize_t @@ -3019,6 +2694,9 @@ show_pwm_weight_temp_sel(struct device *dev, struct device_attribute *attr, struct sensor_device_attribute *sattr = to_sensor_dev_attr(attr); int index = sattr->index; + if (IS_ERR(data)) + return PTR_ERR(data); + return show_pwm_temp_sel_common(data, buf, data->pwm_weight_temp_sel[index]); } @@ -3031,7 +2709,11 @@ store_pwm_weight_temp_sel(struct device *dev, struct device_attribute *attr, struct sensor_device_attribute *sattr = to_sensor_dev_attr(attr); int nr = sattr->index; unsigned long val; - int err, reg, src; + int err, src; + u16 reg; + + if (IS_ERR(data)) + return PTR_ERR(data); err = kstrtoul(buf, 10, &val); if (err < 0) @@ -3047,19 +2729,24 @@ store_pwm_weight_temp_sel(struct device *dev, struct device_attribute *attr, if (val) { src = data->temp_src[val - 1]; data->pwm_weight_temp_sel[nr] = src; - reg = data->read_value(data, data->REG_WEIGHT_TEMP_SEL[nr]); + err = nct6775_read_value(data, data->REG_WEIGHT_TEMP_SEL[nr], ®); + if (err) + goto out; reg &= 0xe0; reg |= (src | 0x80); - data->write_value(data, data->REG_WEIGHT_TEMP_SEL[nr], reg); + err = nct6775_write_value(data, data->REG_WEIGHT_TEMP_SEL[nr], reg); } else { data->pwm_weight_temp_sel[nr] = 0; - reg = data->read_value(data, data->REG_WEIGHT_TEMP_SEL[nr]); + err = nct6775_read_value(data, data->REG_WEIGHT_TEMP_SEL[nr], ®); + if (err) + goto out; reg &= 0x7f; - data->write_value(data, data->REG_WEIGHT_TEMP_SEL[nr], reg); + err = nct6775_write_value(data, data->REG_WEIGHT_TEMP_SEL[nr], reg); } +out: mutex_unlock(&data->update_lock); - return count; + return err ? : count; } static ssize_t @@ -3068,6 +2755,9 @@ show_target_temp(struct device *dev, struct device_attribute *attr, char *buf) struct nct6775_data *data = nct6775_update_device(dev); struct sensor_device_attribute *sattr = to_sensor_dev_attr(attr); + if (IS_ERR(data)) + return PTR_ERR(data); + return sprintf(buf, "%d\n", data->target_temp[sattr->index] * 1000); } @@ -3090,9 +2780,9 @@ store_target_temp(struct device *dev, struct device_attribute *attr, mutex_lock(&data->update_lock); data->target_temp[nr] = val; - pwm_update_registers(data, nr); + err = pwm_update_registers(data, nr); mutex_unlock(&data->update_lock); - return count; + return err ? : count; } static ssize_t @@ -3102,6 +2792,9 @@ show_target_speed(struct device *dev, struct device_attribute *attr, char *buf) struct sensor_device_attribute *sattr = to_sensor_dev_attr(attr); int nr = sattr->index; + if (IS_ERR(data)) + return PTR_ERR(data); + return sprintf(buf, "%d\n", fan_from_reg16(data->target_speed[nr], data->fan_div[nr])); @@ -3127,9 +2820,9 @@ store_target_speed(struct device *dev, struct device_attribute *attr, mutex_lock(&data->update_lock); data->target_speed[nr] = speed; - pwm_update_registers(data, nr); + err = pwm_update_registers(data, nr); mutex_unlock(&data->update_lock); - return count; + return err ? : count; } static ssize_t @@ -3141,6 +2834,9 @@ show_temp_tolerance(struct device *dev, struct device_attribute *attr, int nr = sattr->nr; int index = sattr->index; + if (IS_ERR(data)) + return PTR_ERR(data); + return sprintf(buf, "%d\n", data->temp_tolerance[index][nr] * 1000); } @@ -3165,13 +2861,11 @@ store_temp_tolerance(struct device *dev, struct device_attribute *attr, mutex_lock(&data->update_lock); data->temp_tolerance[index][nr] = val; if (index) - pwm_update_registers(data, nr); + err = pwm_update_registers(data, nr); else - data->write_value(data, - data->REG_CRITICAL_TEMP_TOLERANCE[nr], - val); + err = nct6775_write_value(data, data->REG_CRITICAL_TEMP_TOLERANCE[nr], val); mutex_unlock(&data->update_lock); - return count; + return err ? : count; } /* @@ -3188,8 +2882,12 @@ show_speed_tolerance(struct device *dev, struct device_attribute *attr, struct nct6775_data *data = nct6775_update_device(dev); struct sensor_device_attribute *sattr = to_sensor_dev_attr(attr); int nr = sattr->index; - int target = data->target_speed[nr]; - int tolerance = 0; + int target, tolerance = 0; + + if (IS_ERR(data)) + return PTR_ERR(data); + + target = data->target_speed[nr]; if (target) { int low = target - data->target_speed_tolerance[nr]; @@ -3239,24 +2937,19 @@ store_speed_tolerance(struct device *dev, struct device_attribute *attr, mutex_lock(&data->update_lock); data->target_speed_tolerance[nr] = val; - pwm_update_registers(data, nr); + err = pwm_update_registers(data, nr); mutex_unlock(&data->update_lock); - return count; + return err ? : count; } -SENSOR_TEMPLATE_2(pwm, "pwm%d", S_IWUSR | S_IRUGO, show_pwm, store_pwm, 0, 0); -SENSOR_TEMPLATE(pwm_mode, "pwm%d_mode", S_IWUSR | S_IRUGO, show_pwm_mode, - store_pwm_mode, 0); -SENSOR_TEMPLATE(pwm_enable, "pwm%d_enable", S_IWUSR | S_IRUGO, show_pwm_enable, - store_pwm_enable, 0); -SENSOR_TEMPLATE(pwm_temp_sel, "pwm%d_temp_sel", S_IWUSR | S_IRUGO, - show_pwm_temp_sel, store_pwm_temp_sel, 0); -SENSOR_TEMPLATE(pwm_target_temp, "pwm%d_target_temp", S_IWUSR | S_IRUGO, - show_target_temp, store_target_temp, 0); -SENSOR_TEMPLATE(fan_target, "fan%d_target", S_IWUSR | S_IRUGO, - show_target_speed, store_target_speed, 0); -SENSOR_TEMPLATE(fan_tolerance, "fan%d_tolerance", S_IWUSR | S_IRUGO, - show_speed_tolerance, store_speed_tolerance, 0); +SENSOR_TEMPLATE_2(pwm, "pwm%d", 0644, show_pwm, store_pwm, 0, 0); +SENSOR_TEMPLATE(pwm_mode, "pwm%d_mode", 0644, show_pwm_mode, store_pwm_mode, 0); +SENSOR_TEMPLATE(pwm_enable, "pwm%d_enable", 0644, show_pwm_enable, store_pwm_enable, 0); +SENSOR_TEMPLATE(pwm_temp_sel, "pwm%d_temp_sel", 0644, show_pwm_temp_sel, store_pwm_temp_sel, 0); +SENSOR_TEMPLATE(pwm_target_temp, "pwm%d_target_temp", 0644, show_target_temp, store_target_temp, 0); +SENSOR_TEMPLATE(fan_target, "fan%d_target", 0644, show_target_speed, store_target_speed, 0); +SENSOR_TEMPLATE(fan_tolerance, "fan%d_tolerance", 0644, show_speed_tolerance, + store_speed_tolerance, 0); /* Smart Fan registers */ @@ -3268,6 +2961,9 @@ show_weight_temp(struct device *dev, struct device_attribute *attr, char *buf) int nr = sattr->nr; int index = sattr->index; + if (IS_ERR(data)) + return PTR_ERR(data); + return sprintf(buf, "%d\n", data->weight_temp[index][nr] * 1000); } @@ -3290,23 +2986,21 @@ store_weight_temp(struct device *dev, struct device_attribute *attr, mutex_lock(&data->update_lock); data->weight_temp[index][nr] = val; - data->write_value(data, data->REG_WEIGHT_TEMP[index][nr], val); + err = nct6775_write_value(data, data->REG_WEIGHT_TEMP[index][nr], val); mutex_unlock(&data->update_lock); - return count; + return err ? : count; } -SENSOR_TEMPLATE(pwm_weight_temp_sel, "pwm%d_weight_temp_sel", S_IWUSR | S_IRUGO, - show_pwm_weight_temp_sel, store_pwm_weight_temp_sel, 0); +SENSOR_TEMPLATE(pwm_weight_temp_sel, "pwm%d_weight_temp_sel", 0644, + show_pwm_weight_temp_sel, store_pwm_weight_temp_sel, 0); SENSOR_TEMPLATE_2(pwm_weight_temp_step, "pwm%d_weight_temp_step", - S_IWUSR | S_IRUGO, show_weight_temp, store_weight_temp, 0, 0); + 0644, show_weight_temp, store_weight_temp, 0, 0); SENSOR_TEMPLATE_2(pwm_weight_temp_step_tol, "pwm%d_weight_temp_step_tol", - S_IWUSR | S_IRUGO, show_weight_temp, store_weight_temp, 0, 1); + 0644, show_weight_temp, store_weight_temp, 0, 1); SENSOR_TEMPLATE_2(pwm_weight_temp_step_base, "pwm%d_weight_temp_step_base", - S_IWUSR | S_IRUGO, show_weight_temp, store_weight_temp, 0, 2); -SENSOR_TEMPLATE_2(pwm_weight_duty_step, "pwm%d_weight_duty_step", - S_IWUSR | S_IRUGO, show_pwm, store_pwm, 0, 5); -SENSOR_TEMPLATE_2(pwm_weight_duty_base, "pwm%d_weight_duty_base", - S_IWUSR | S_IRUGO, show_pwm, store_pwm, 0, 6); + 0644, show_weight_temp, store_weight_temp, 0, 2); +SENSOR_TEMPLATE_2(pwm_weight_duty_step, "pwm%d_weight_duty_step", 0644, show_pwm, store_pwm, 0, 5); +SENSOR_TEMPLATE_2(pwm_weight_duty_base, "pwm%d_weight_duty_base", 0644, show_pwm, store_pwm, 0, 6); static ssize_t show_fan_time(struct device *dev, struct device_attribute *attr, char *buf) @@ -3316,6 +3010,9 @@ show_fan_time(struct device *dev, struct device_attribute *attr, char *buf) int nr = sattr->nr; int index = sattr->index; + if (IS_ERR(data)) + return PTR_ERR(data); + return sprintf(buf, "%d\n", step_time_from_reg(data->fan_time[index][nr], data->pwm_mode[nr])); @@ -3339,9 +3036,9 @@ store_fan_time(struct device *dev, struct device_attribute *attr, val = step_time_to_reg(val, data->pwm_mode[nr]); mutex_lock(&data->update_lock); data->fan_time[index][nr] = val; - data->write_value(data, data->REG_FAN_TIME[index][nr], val); + err = nct6775_write_value(data, data->REG_FAN_TIME[index][nr], val); mutex_unlock(&data->update_lock); - return count; + return err ? : count; } static ssize_t @@ -3350,6 +3047,9 @@ show_auto_pwm(struct device *dev, struct device_attribute *attr, char *buf) struct nct6775_data *data = nct6775_update_device(dev); struct sensor_device_attribute_2 *sattr = to_sensor_dev_attr_2(attr); + if (IS_ERR(data)) + return PTR_ERR(data); + return sprintf(buf, "%d\n", data->auto_pwm[sattr->nr][sattr->index]); } @@ -3363,7 +3063,7 @@ store_auto_pwm(struct device *dev, struct device_attribute *attr, int point = sattr->index; unsigned long val; int err; - u8 reg; + u16 reg; err = kstrtoul(buf, 10, &val); if (err < 0) @@ -3381,21 +3081,20 @@ store_auto_pwm(struct device *dev, struct device_attribute *attr, mutex_lock(&data->update_lock); data->auto_pwm[nr][point] = val; if (point < data->auto_pwm_num) { - data->write_value(data, - NCT6775_AUTO_PWM(data, nr, point), - data->auto_pwm[nr][point]); + err = nct6775_write_value(data, NCT6775_AUTO_PWM(data, nr, point), + data->auto_pwm[nr][point]); } else { switch (data->kind) { case nct6775: /* disable if needed (pwm == 0) */ - reg = data->read_value(data, - NCT6775_REG_CRITICAL_ENAB[nr]); + err = nct6775_read_value(data, NCT6775_REG_CRITICAL_ENAB[nr], ®); + if (err) + break; if (val) reg |= 0x02; else reg &= ~0x02; - data->write_value(data, NCT6775_REG_CRITICAL_ENAB[nr], - reg); + err = nct6775_write_value(data, NCT6775_REG_CRITICAL_ENAB[nr], reg); break; case nct6776: break; /* always enabled, nothing to do */ @@ -3409,22 +3108,22 @@ store_auto_pwm(struct device *dev, struct device_attribute *attr, case nct6796: case nct6797: case nct6798: - data->write_value(data, data->REG_CRITICAL_PWM[nr], - val); - reg = data->read_value(data, - data->REG_CRITICAL_PWM_ENABLE[nr]); + err = nct6775_write_value(data, data->REG_CRITICAL_PWM[nr], val); + if (err) + break; + err = nct6775_read_value(data, data->REG_CRITICAL_PWM_ENABLE[nr], ®); + if (err) + break; if (val == 255) reg &= ~data->CRITICAL_PWM_ENABLE_MASK; else reg |= data->CRITICAL_PWM_ENABLE_MASK; - data->write_value(data, - data->REG_CRITICAL_PWM_ENABLE[nr], - reg); + err = nct6775_write_value(data, data->REG_CRITICAL_PWM_ENABLE[nr], reg); break; } } mutex_unlock(&data->update_lock); - return count; + return err ? : count; } static ssize_t @@ -3435,6 +3134,9 @@ show_auto_temp(struct device *dev, struct device_attribute *attr, char *buf) int nr = sattr->nr; int point = sattr->index; + if (IS_ERR(data)) + return PTR_ERR(data); + /* * We don't know for sure if the temperature is signed or unsigned. * Assume it is unsigned. @@ -3462,15 +3164,14 @@ store_auto_temp(struct device *dev, struct device_attribute *attr, mutex_lock(&data->update_lock); data->auto_temp[nr][point] = DIV_ROUND_CLOSEST(val, 1000); if (point < data->auto_pwm_num) { - data->write_value(data, - NCT6775_AUTO_TEMP(data, nr, point), - data->auto_temp[nr][point]); + err = nct6775_write_value(data, NCT6775_AUTO_TEMP(data, nr, point), + data->auto_temp[nr][point]); } else { - data->write_value(data, data->REG_CRITICAL_TEMP[nr], - data->auto_temp[nr][point]); + err = nct6775_write_value(data, data->REG_CRITICAL_TEMP[nr], + data->auto_temp[nr][point]); } mutex_unlock(&data->update_lock); - return count; + return err ? : count; } static umode_t nct6775_pwm_is_visible(struct kobject *kobj, @@ -3500,65 +3201,59 @@ static umode_t nct6775_pwm_is_visible(struct kobject *kobj, if (api > data->auto_pwm_num) return 0; } - return attr->mode; + return nct6775_attr_mode(data, attr); } -SENSOR_TEMPLATE_2(pwm_stop_time, "pwm%d_stop_time", S_IWUSR | S_IRUGO, - show_fan_time, store_fan_time, 0, 0); -SENSOR_TEMPLATE_2(pwm_step_up_time, "pwm%d_step_up_time", S_IWUSR | S_IRUGO, +SENSOR_TEMPLATE_2(pwm_stop_time, "pwm%d_stop_time", 0644, show_fan_time, store_fan_time, 0, 0); +SENSOR_TEMPLATE_2(pwm_step_up_time, "pwm%d_step_up_time", 0644, show_fan_time, store_fan_time, 0, 1); -SENSOR_TEMPLATE_2(pwm_step_down_time, "pwm%d_step_down_time", S_IWUSR | S_IRUGO, +SENSOR_TEMPLATE_2(pwm_step_down_time, "pwm%d_step_down_time", 0644, show_fan_time, store_fan_time, 0, 2); -SENSOR_TEMPLATE_2(pwm_start, "pwm%d_start", S_IWUSR | S_IRUGO, show_pwm, - store_pwm, 0, 1); -SENSOR_TEMPLATE_2(pwm_floor, "pwm%d_floor", S_IWUSR | S_IRUGO, show_pwm, - store_pwm, 0, 2); -SENSOR_TEMPLATE_2(pwm_temp_tolerance, "pwm%d_temp_tolerance", S_IWUSR | S_IRUGO, +SENSOR_TEMPLATE_2(pwm_start, "pwm%d_start", 0644, show_pwm, store_pwm, 0, 1); +SENSOR_TEMPLATE_2(pwm_floor, "pwm%d_floor", 0644, show_pwm, store_pwm, 0, 2); +SENSOR_TEMPLATE_2(pwm_temp_tolerance, "pwm%d_temp_tolerance", 0644, show_temp_tolerance, store_temp_tolerance, 0, 0); SENSOR_TEMPLATE_2(pwm_crit_temp_tolerance, "pwm%d_crit_temp_tolerance", - S_IWUSR | S_IRUGO, show_temp_tolerance, store_temp_tolerance, - 0, 1); + 0644, show_temp_tolerance, store_temp_tolerance, 0, 1); -SENSOR_TEMPLATE_2(pwm_max, "pwm%d_max", S_IWUSR | S_IRUGO, show_pwm, store_pwm, - 0, 3); +SENSOR_TEMPLATE_2(pwm_max, "pwm%d_max", 0644, show_pwm, store_pwm, 0, 3); -SENSOR_TEMPLATE_2(pwm_step, "pwm%d_step", S_IWUSR | S_IRUGO, show_pwm, - store_pwm, 0, 4); +SENSOR_TEMPLATE_2(pwm_step, "pwm%d_step", 0644, show_pwm, store_pwm, 0, 4); SENSOR_TEMPLATE_2(pwm_auto_point1_pwm, "pwm%d_auto_point1_pwm", - S_IWUSR | S_IRUGO, show_auto_pwm, store_auto_pwm, 0, 0); + 0644, show_auto_pwm, store_auto_pwm, 0, 0); SENSOR_TEMPLATE_2(pwm_auto_point1_temp, "pwm%d_auto_point1_temp", - S_IWUSR | S_IRUGO, show_auto_temp, store_auto_temp, 0, 0); + 0644, show_auto_temp, store_auto_temp, 0, 0); SENSOR_TEMPLATE_2(pwm_auto_point2_pwm, "pwm%d_auto_point2_pwm", - S_IWUSR | S_IRUGO, show_auto_pwm, store_auto_pwm, 0, 1); + 0644, show_auto_pwm, store_auto_pwm, 0, 1); SENSOR_TEMPLATE_2(pwm_auto_point2_temp, "pwm%d_auto_point2_temp", - S_IWUSR | S_IRUGO, show_auto_temp, store_auto_temp, 0, 1); + 0644, show_auto_temp, store_auto_temp, 0, 1); SENSOR_TEMPLATE_2(pwm_auto_point3_pwm, "pwm%d_auto_point3_pwm", - S_IWUSR | S_IRUGO, show_auto_pwm, store_auto_pwm, 0, 2); + 0644, show_auto_pwm, store_auto_pwm, 0, 2); SENSOR_TEMPLATE_2(pwm_auto_point3_temp, "pwm%d_auto_point3_temp", - S_IWUSR | S_IRUGO, show_auto_temp, store_auto_temp, 0, 2); + 0644, show_auto_temp, store_auto_temp, 0, 2); SENSOR_TEMPLATE_2(pwm_auto_point4_pwm, "pwm%d_auto_point4_pwm", - S_IWUSR | S_IRUGO, show_auto_pwm, store_auto_pwm, 0, 3); + 0644, show_auto_pwm, store_auto_pwm, 0, 3); SENSOR_TEMPLATE_2(pwm_auto_point4_temp, "pwm%d_auto_point4_temp", - S_IWUSR | S_IRUGO, show_auto_temp, store_auto_temp, 0, 3); + 0644, show_auto_temp, store_auto_temp, 0, 3); SENSOR_TEMPLATE_2(pwm_auto_point5_pwm, "pwm%d_auto_point5_pwm", - S_IWUSR | S_IRUGO, show_auto_pwm, store_auto_pwm, 0, 4); + 0644, show_auto_pwm, store_auto_pwm, 0, 4); SENSOR_TEMPLATE_2(pwm_auto_point5_temp, "pwm%d_auto_point5_temp", - S_IWUSR | S_IRUGO, show_auto_temp, store_auto_temp, 0, 4); + 0644, show_auto_temp, store_auto_temp, 0, 4); SENSOR_TEMPLATE_2(pwm_auto_point6_pwm, "pwm%d_auto_point6_pwm", - S_IWUSR | S_IRUGO, show_auto_pwm, store_auto_pwm, 0, 5); + 0644, show_auto_pwm, store_auto_pwm, 0, 5); SENSOR_TEMPLATE_2(pwm_auto_point6_temp, "pwm%d_auto_point6_temp", - S_IWUSR | S_IRUGO, show_auto_temp, store_auto_temp, 0, 5); + 0644, show_auto_temp, store_auto_temp, 0, 5); SENSOR_TEMPLATE_2(pwm_auto_point7_pwm, "pwm%d_auto_point7_pwm", - S_IWUSR | S_IRUGO, show_auto_pwm, store_auto_pwm, 0, 6); + 0644, show_auto_pwm, store_auto_pwm, 0, 6); SENSOR_TEMPLATE_2(pwm_auto_point7_temp, "pwm%d_auto_point7_temp", - S_IWUSR | S_IRUGO, show_auto_temp, store_auto_temp, 0, 6); + 0644, show_auto_temp, store_auto_temp, 0, 6); /* * nct6775_pwm_is_visible uses the index into the following array @@ -3612,123 +3307,21 @@ static const struct sensor_template_group nct6775_pwm_template_group = { .base = 1, }; -static ssize_t -cpu0_vid_show(struct device *dev, struct device_attribute *attr, char *buf) -{ - struct nct6775_data *data = dev_get_drvdata(dev); - - return sprintf(buf, "%d\n", vid_from_reg(data->vid, data->vrm)); -} - -static DEVICE_ATTR_RO(cpu0_vid); - -/* Case open detection */ - -static ssize_t -clear_caseopen(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count) +static inline int nct6775_init_device(struct nct6775_data *data) { - struct nct6775_data *data = dev_get_drvdata(dev); - struct nct6775_sio_data *sio_data = data->sio_data; - int nr = to_sensor_dev_attr(attr)->index - INTRUSION_ALARM_BASE; - unsigned long val; - u8 reg; - int ret; - - if (kstrtoul(buf, 10, &val) || val != 0) - return -EINVAL; - - mutex_lock(&data->update_lock); - - /* - * Use CR registers to clear caseopen status. - * The CR registers are the same for all chips, and not all chips - * support clearing the caseopen status through "regular" registers. - */ - ret = sio_data->sio_enter(sio_data); - if (ret) { - count = ret; - goto error; - } - - sio_data->sio_select(sio_data, NCT6775_LD_ACPI); - reg = sio_data->sio_inb(sio_data, NCT6775_REG_CR_CASEOPEN_CLR[nr]); - reg |= NCT6775_CR_CASEOPEN_CLR_MASK[nr]; - sio_data->sio_outb(sio_data, NCT6775_REG_CR_CASEOPEN_CLR[nr], reg); - reg &= ~NCT6775_CR_CASEOPEN_CLR_MASK[nr]; - sio_data->sio_outb(sio_data, NCT6775_REG_CR_CASEOPEN_CLR[nr], reg); - sio_data->sio_exit(sio_data); - - data->valid = false; /* Force cache refresh */ -error: - mutex_unlock(&data->update_lock); - return count; -} - -static SENSOR_DEVICE_ATTR(intrusion0_alarm, S_IWUSR | S_IRUGO, show_alarm, - clear_caseopen, INTRUSION_ALARM_BASE); -static SENSOR_DEVICE_ATTR(intrusion1_alarm, S_IWUSR | S_IRUGO, show_alarm, - clear_caseopen, INTRUSION_ALARM_BASE + 1); -static SENSOR_DEVICE_ATTR(intrusion0_beep, S_IWUSR | S_IRUGO, show_beep, - store_beep, INTRUSION_ALARM_BASE); -static SENSOR_DEVICE_ATTR(intrusion1_beep, S_IWUSR | S_IRUGO, show_beep, - store_beep, INTRUSION_ALARM_BASE + 1); -static SENSOR_DEVICE_ATTR(beep_enable, S_IWUSR | S_IRUGO, show_beep, - store_beep, BEEP_ENABLE_BASE); - -static umode_t nct6775_other_is_visible(struct kobject *kobj, - struct attribute *attr, int index) -{ - struct device *dev = kobj_to_dev(kobj); - struct nct6775_data *data = dev_get_drvdata(dev); - - if (index == 0 && !data->have_vid) - return 0; - - if (index == 1 || index == 2) { - if (data->ALARM_BITS[INTRUSION_ALARM_BASE + index - 1] < 0) - return 0; - } - - if (index == 3 || index == 4) { - if (data->BEEP_BITS[INTRUSION_ALARM_BASE + index - 3] < 0) - return 0; - } - - return attr->mode; -} - -/* - * nct6775_other_is_visible uses the index into the following array - * to determine if attributes should be created or not. - * Any change in order or content must be matched. - */ -static struct attribute *nct6775_attributes_other[] = { - &dev_attr_cpu0_vid.attr, /* 0 */ - &sensor_dev_attr_intrusion0_alarm.dev_attr.attr, /* 1 */ - &sensor_dev_attr_intrusion1_alarm.dev_attr.attr, /* 2 */ - &sensor_dev_attr_intrusion0_beep.dev_attr.attr, /* 3 */ - &sensor_dev_attr_intrusion1_beep.dev_attr.attr, /* 4 */ - &sensor_dev_attr_beep_enable.dev_attr.attr, /* 5 */ - - NULL -}; - -static const struct attribute_group nct6775_group_other = { - .attrs = nct6775_attributes_other, - .is_visible = nct6775_other_is_visible, -}; - -static inline void nct6775_init_device(struct nct6775_data *data) -{ - int i; - u8 tmp, diode; + int i, err; + u16 tmp, diode; /* Start monitoring if needed */ if (data->REG_CONFIG) { - tmp = data->read_value(data, data->REG_CONFIG); - if (!(tmp & 0x01)) - data->write_value(data, data->REG_CONFIG, tmp | 0x01); + err = nct6775_read_value(data, data->REG_CONFIG, &tmp); + if (err) + return err; + if (!(tmp & 0x01)) { + err = nct6775_write_value(data, data->REG_CONFIG, tmp | 0x01); + if (err) + return err; + } } /* Enable temperature sensors if needed */ @@ -3737,18 +3330,29 @@ static inline void nct6775_init_device(struct nct6775_data *data) continue; if (!data->reg_temp_config[i]) continue; - tmp = data->read_value(data, data->reg_temp_config[i]); - if (tmp & 0x01) - data->write_value(data, data->reg_temp_config[i], - tmp & 0xfe); + err = nct6775_read_value(data, data->reg_temp_config[i], &tmp); + if (err) + return err; + if (tmp & 0x01) { + err = nct6775_write_value(data, data->reg_temp_config[i], tmp & 0xfe); + if (err) + return err; + } } /* Enable VBAT monitoring if needed */ - tmp = data->read_value(data, data->REG_VBAT); - if (!(tmp & 0x01)) - data->write_value(data, data->REG_VBAT, tmp | 0x01); + err = nct6775_read_value(data, data->REG_VBAT, &tmp); + if (err) + return err; + if (!(tmp & 0x01)) { + err = nct6775_write_value(data, data->REG_VBAT, tmp | 0x01); + if (err) + return err; + } - diode = data->read_value(data, data->REG_DIODE); + err = nct6775_read_value(data, data->REG_DIODE, &diode); + if (err) + return err; for (i = 0; i < data->temp_fixed_num; i++) { if (!(data->have_temp_fixed & BIT(i))) @@ -3759,241 +3363,24 @@ static inline void nct6775_init_device(struct nct6775_data *data) else /* thermistor */ data->temp_type[i] = 4; } -} - -static void -nct6775_check_fan_inputs(struct nct6775_data *data, struct nct6775_sio_data *sio_data) -{ - bool fan3pin = false, fan4pin = false, fan4min = false; - bool fan5pin = false, fan6pin = false, fan7pin = false; - bool pwm3pin = false, pwm4pin = false, pwm5pin = false; - bool pwm6pin = false, pwm7pin = false; - - /* Store SIO_REG_ENABLE for use during resume */ - sio_data->sio_select(sio_data, NCT6775_LD_HWM); - data->sio_reg_enable = sio_data->sio_inb(sio_data, SIO_REG_ENABLE); - - /* fan4 and fan5 share some pins with the GPIO and serial flash */ - if (data->kind == nct6775) { - int cr2c = sio_data->sio_inb(sio_data, 0x2c); - - fan3pin = cr2c & BIT(6); - pwm3pin = cr2c & BIT(7); - - /* On NCT6775, fan4 shares pins with the fdc interface */ - fan4pin = !(sio_data->sio_inb(sio_data, 0x2A) & 0x80); - } else if (data->kind == nct6776) { - bool gpok = sio_data->sio_inb(sio_data, 0x27) & 0x80; - const char *board_vendor, *board_name; - - board_vendor = dmi_get_system_info(DMI_BOARD_VENDOR); - board_name = dmi_get_system_info(DMI_BOARD_NAME); - - if (board_name && board_vendor && - !strcmp(board_vendor, "ASRock")) { - /* - * Auxiliary fan monitoring is not enabled on ASRock - * Z77 Pro4-M if booted in UEFI Ultra-FastBoot mode. - * Observed with BIOS version 2.00. - */ - if (!strcmp(board_name, "Z77 Pro4-M")) { - if ((data->sio_reg_enable & 0xe0) != 0xe0) { - data->sio_reg_enable |= 0xe0; - sio_data->sio_outb(sio_data, SIO_REG_ENABLE, - data->sio_reg_enable); - } - } - } - - if (data->sio_reg_enable & 0x80) - fan3pin = gpok; - else - fan3pin = !(sio_data->sio_inb(sio_data, 0x24) & 0x40); - - if (data->sio_reg_enable & 0x40) - fan4pin = gpok; - else - fan4pin = sio_data->sio_inb(sio_data, 0x1C) & 0x01; - - if (data->sio_reg_enable & 0x20) - fan5pin = gpok; - else - fan5pin = sio_data->sio_inb(sio_data, 0x1C) & 0x02; - - fan4min = fan4pin; - pwm3pin = fan3pin; - } else if (data->kind == nct6106) { - int cr24 = sio_data->sio_inb(sio_data, 0x24); - - fan3pin = !(cr24 & 0x80); - pwm3pin = cr24 & 0x08; - } else if (data->kind == nct6116) { - int cr1a = sio_data->sio_inb(sio_data, 0x1a); - int cr1b = sio_data->sio_inb(sio_data, 0x1b); - int cr24 = sio_data->sio_inb(sio_data, 0x24); - int cr2a = sio_data->sio_inb(sio_data, 0x2a); - int cr2b = sio_data->sio_inb(sio_data, 0x2b); - int cr2f = sio_data->sio_inb(sio_data, 0x2f); - - fan3pin = !(cr2b & 0x10); - fan4pin = (cr2b & 0x80) || // pin 1(2) - (!(cr2f & 0x10) && (cr1a & 0x04)); // pin 65(66) - fan5pin = (cr2b & 0x80) || // pin 126(127) - (!(cr1b & 0x03) && (cr2a & 0x02)); // pin 94(96) - - pwm3pin = fan3pin && (cr24 & 0x08); - pwm4pin = fan4pin; - pwm5pin = fan5pin; - } else { - /* - * NCT6779D, NCT6791D, NCT6792D, NCT6793D, NCT6795D, NCT6796D, - * NCT6797D, NCT6798D - */ - int cr1a = sio_data->sio_inb(sio_data, 0x1a); - int cr1b = sio_data->sio_inb(sio_data, 0x1b); - int cr1c = sio_data->sio_inb(sio_data, 0x1c); - int cr1d = sio_data->sio_inb(sio_data, 0x1d); - int cr2a = sio_data->sio_inb(sio_data, 0x2a); - int cr2b = sio_data->sio_inb(sio_data, 0x2b); - int cr2d = sio_data->sio_inb(sio_data, 0x2d); - int cr2f = sio_data->sio_inb(sio_data, 0x2f); - bool dsw_en = cr2f & BIT(3); - bool ddr4_en = cr2f & BIT(4); - int cre0; - int creb; - int cred; - - sio_data->sio_select(sio_data, NCT6775_LD_12); - cre0 = sio_data->sio_inb(sio_data, 0xe0); - creb = sio_data->sio_inb(sio_data, 0xeb); - cred = sio_data->sio_inb(sio_data, 0xed); - - fan3pin = !(cr1c & BIT(5)); - fan4pin = !(cr1c & BIT(6)); - fan5pin = !(cr1c & BIT(7)); - - pwm3pin = !(cr1c & BIT(0)); - pwm4pin = !(cr1c & BIT(1)); - pwm5pin = !(cr1c & BIT(2)); - - switch (data->kind) { - case nct6791: - fan6pin = cr2d & BIT(1); - pwm6pin = cr2d & BIT(0); - break; - case nct6792: - fan6pin = !dsw_en && (cr2d & BIT(1)); - pwm6pin = !dsw_en && (cr2d & BIT(0)); - break; - case nct6793: - fan5pin |= cr1b & BIT(5); - fan5pin |= creb & BIT(5); - - fan6pin = !dsw_en && (cr2d & BIT(1)); - fan6pin |= creb & BIT(3); - - pwm5pin |= cr2d & BIT(7); - pwm5pin |= (creb & BIT(4)) && !(cr2a & BIT(0)); - - pwm6pin = !dsw_en && (cr2d & BIT(0)); - pwm6pin |= creb & BIT(2); - break; - case nct6795: - fan5pin |= cr1b & BIT(5); - fan5pin |= creb & BIT(5); - - fan6pin = (cr2a & BIT(4)) && - (!dsw_en || (cred & BIT(4))); - fan6pin |= creb & BIT(3); - - pwm5pin |= cr2d & BIT(7); - pwm5pin |= (creb & BIT(4)) && !(cr2a & BIT(0)); - - pwm6pin = (cr2a & BIT(3)) && (cred & BIT(2)); - pwm6pin |= creb & BIT(2); - break; - case nct6796: - fan5pin |= cr1b & BIT(5); - fan5pin |= (cre0 & BIT(3)) && !(cr1b & BIT(0)); - fan5pin |= creb & BIT(5); - - fan6pin = (cr2a & BIT(4)) && - (!dsw_en || (cred & BIT(4))); - fan6pin |= creb & BIT(3); - - fan7pin = !(cr2b & BIT(2)); - - pwm5pin |= cr2d & BIT(7); - pwm5pin |= (cre0 & BIT(4)) && !(cr1b & BIT(0)); - pwm5pin |= (creb & BIT(4)) && !(cr2a & BIT(0)); - - pwm6pin = (cr2a & BIT(3)) && (cred & BIT(2)); - pwm6pin |= creb & BIT(2); - - pwm7pin = !(cr1d & (BIT(2) | BIT(3))); - break; - case nct6797: - fan5pin |= !ddr4_en && (cr1b & BIT(5)); - fan5pin |= creb & BIT(5); - - fan6pin = cr2a & BIT(4); - fan6pin |= creb & BIT(3); - - fan7pin = cr1a & BIT(1); - - pwm5pin |= (creb & BIT(4)) && !(cr2a & BIT(0)); - pwm5pin |= !ddr4_en && (cr2d & BIT(7)); - - pwm6pin = creb & BIT(2); - pwm6pin |= cred & BIT(2); - - pwm7pin = cr1d & BIT(4); - break; - case nct6798: - fan6pin = !(cr1b & BIT(0)) && (cre0 & BIT(3)); - fan6pin |= cr2a & BIT(4); - fan6pin |= creb & BIT(5); - - fan7pin = cr1b & BIT(5); - fan7pin |= !(cr2b & BIT(2)); - fan7pin |= creb & BIT(3); - - pwm6pin = !(cr1b & BIT(0)) && (cre0 & BIT(4)); - pwm6pin |= !(cred & BIT(2)) && (cr2a & BIT(3)); - pwm6pin |= (creb & BIT(4)) && !(cr2a & BIT(0)); - - pwm7pin = !(cr1d & (BIT(2) | BIT(3))); - pwm7pin |= cr2d & BIT(7); - pwm7pin |= creb & BIT(2); - break; - default: /* NCT6779D */ - break; - } - - fan4min = fan4pin; - } - /* fan 1 and 2 (0x03) are always present */ - data->has_fan = 0x03 | (fan3pin << 2) | (fan4pin << 3) | - (fan5pin << 4) | (fan6pin << 5) | (fan7pin << 6); - data->has_fan_min = 0x03 | (fan3pin << 2) | (fan4min << 3) | - (fan5pin << 4) | (fan6pin << 5) | (fan7pin << 6); - data->has_pwm = 0x03 | (pwm3pin << 2) | (pwm4pin << 3) | - (pwm5pin << 4) | (pwm6pin << 5) | (pwm7pin << 6); + return 0; } -static void add_temp_sensors(struct nct6775_data *data, const u16 *regp, - int *available, int *mask) +static int add_temp_sensors(struct nct6775_data *data, const u16 *regp, + int *available, int *mask) { - int i; - u8 src; + int i, err; + u16 src; for (i = 0; i < data->pwm_num && *available; i++) { int index; if (!regp[i]) continue; - src = data->read_value(data, regp[i]); + err = nct6775_read_value(data, regp[i], &src); + if (err) + return err; src &= 0x1f; if (!src || (*mask & BIT(src))) continue; @@ -4001,58 +3388,36 @@ static void add_temp_sensors(struct nct6775_data *data, const u16 *regp, continue; index = __ffs(*available); - data->write_value(data, data->REG_TEMP_SOURCE[index], src); + err = nct6775_write_value(data, data->REG_TEMP_SOURCE[index], src); + if (err) + return err; *available &= ~BIT(index); *mask |= BIT(src); } + + return 0; } -static int nct6775_probe(struct platform_device *pdev) +int nct6775_probe(struct device *dev, struct nct6775_data *data, + const struct regmap_config *regmapcfg) { - struct device *dev = &pdev->dev; - struct nct6775_sio_data *sio_data = dev_get_platdata(dev); - struct nct6775_data *data; - struct resource *res; int i, s, err = 0; - int src, mask, available; + int mask, available; + u16 src; const u16 *reg_temp, *reg_temp_over, *reg_temp_hyst, *reg_temp_config; const u16 *reg_temp_mon, *reg_temp_alternate, *reg_temp_crit; const u16 *reg_temp_crit_l = NULL, *reg_temp_crit_h = NULL; int num_reg_temp, num_reg_temp_mon, num_reg_tsi_temp; - u8 cr2a; - struct attribute_group *group; struct device *hwmon_dev; struct sensor_template_group tsi_temp_tg; - int num_attr_groups = 0; - - if (sio_data->access == access_direct) { - res = platform_get_resource(pdev, IORESOURCE_IO, 0); - if (!devm_request_region(&pdev->dev, res->start, IOREGION_LENGTH, - DRVNAME)) - return -EBUSY; - } - - data = devm_kzalloc(&pdev->dev, sizeof(struct nct6775_data), - GFP_KERNEL); - if (!data) - return -ENOMEM; - data->kind = sio_data->kind; - data->sio_data = sio_data; - - if (sio_data->access == access_direct) { - data->addr = res->start; - data->read_value = nct6775_read_value; - data->write_value = nct6775_write_value; - } else { - data->read_value = nct6775_wmi_read_value; - data->write_value = nct6775_wmi_write_value; - } + data->regmap = devm_regmap_init(dev, NULL, data, regmapcfg); + if (IS_ERR(data->regmap)) + return PTR_ERR(data->regmap); mutex_init(&data->update_lock); data->name = nct6775_device_names[data->kind]; data->bank = 0xff; /* Force initial bank selection */ - platform_set_drvdata(pdev, data); switch (data->kind) { case nct6106: @@ -4596,7 +3961,10 @@ static int nct6775_probe(struct platform_device *pdev) if (reg_temp[i] == 0) continue; - src = data->read_value(data, data->REG_TEMP_SOURCE[i]) & 0x1f; + err = nct6775_read_value(data, data->REG_TEMP_SOURCE[i], &src); + if (err) + return err; + src &= 0x1f; if (!src || (mask & BIT(src))) available |= BIT(i); @@ -4607,8 +3975,12 @@ static int nct6775_probe(struct platform_device *pdev) * Now find unmonitored temperature registers and enable monitoring * if additional monitoring registers are available. */ - add_temp_sensors(data, data->REG_TEMP_SEL, &available, &mask); - add_temp_sensors(data, data->REG_WEIGHT_TEMP_SEL, &available, &mask); + err = add_temp_sensors(data, data->REG_TEMP_SEL, &available, &mask); + if (err) + return err; + err = add_temp_sensors(data, data->REG_WEIGHT_TEMP_SEL, &available, &mask); + if (err) + return err; mask = 0; s = NUM_TEMP_FIXED; /* First dynamic temperature attribute */ @@ -4616,7 +3988,10 @@ static int nct6775_probe(struct platform_device *pdev) if (reg_temp[i] == 0) continue; - src = data->read_value(data, data->REG_TEMP_SOURCE[i]) & 0x1f; + err = nct6775_read_value(data, data->REG_TEMP_SOURCE[i], &src); + if (err) + return err; + src &= 0x1f; if (!src || (mask & BIT(src))) continue; @@ -4676,7 +4051,10 @@ static int nct6775_probe(struct platform_device *pdev) if (reg_temp_mon[i] == 0) continue; - src = data->read_value(data, data->REG_TEMP_SEL[i]) & 0x1f; + err = nct6775_read_value(data, data->REG_TEMP_SEL[i], &src); + if (err) + return err; + src &= 0x1f; if (!src) continue; @@ -4760,525 +4138,68 @@ static int nct6775_probe(struct platform_device *pdev) /* Check which TSIx_TEMP registers are active */ for (i = 0; i < num_reg_tsi_temp; i++) { - if (data->read_value(data, data->REG_TSI_TEMP[i])) + u16 tmp; + + err = nct6775_read_value(data, data->REG_TSI_TEMP[i], &tmp); + if (err) + return err; + if (tmp) data->have_tsi_temp |= BIT(i); } /* Initialize the chip */ - nct6775_init_device(data); - - err = sio_data->sio_enter(sio_data); + err = nct6775_init_device(data); if (err) return err; - cr2a = sio_data->sio_inb(sio_data, 0x2a); - switch (data->kind) { - case nct6775: - data->have_vid = (cr2a & 0x40); - break; - case nct6776: - data->have_vid = (cr2a & 0x60) == 0x40; - break; - case nct6106: - case nct6116: - case nct6779: - case nct6791: - case nct6792: - case nct6793: - case nct6795: - case nct6796: - case nct6797: - case nct6798: - break; - } - - /* - * Read VID value - * We can get the VID input values directly at logical device D 0xe3. - */ - if (data->have_vid) { - sio_data->sio_select(sio_data, NCT6775_LD_VID); - data->vid = sio_data->sio_inb(sio_data, 0xe3); - data->vrm = vid_which_vrm(); - } - - if (fan_debounce) { - u8 tmp; - - sio_data->sio_select(sio_data, NCT6775_LD_HWM); - tmp = sio_data->sio_inb(sio_data, - NCT6775_REG_CR_FAN_DEBOUNCE); - switch (data->kind) { - case nct6106: - case nct6116: - tmp |= 0xe0; - break; - case nct6775: - tmp |= 0x1e; - break; - case nct6776: - case nct6779: - tmp |= 0x3e; - break; - case nct6791: - case nct6792: - case nct6793: - case nct6795: - case nct6796: - case nct6797: - case nct6798: - tmp |= 0x7e; - break; - } - sio_data->sio_outb(sio_data, NCT6775_REG_CR_FAN_DEBOUNCE, - tmp); - dev_info(&pdev->dev, "Enabled fan debounce for chip %s\n", - data->name); + if (data->driver_init) { + err = data->driver_init(data); + if (err) + return err; } - nct6775_check_fan_inputs(data, sio_data); - - sio_data->sio_exit(sio_data); - /* Read fan clock dividers immediately */ - nct6775_init_fan_common(dev, data); + err = nct6775_init_fan_common(dev, data); + if (err) + return err; /* Register sysfs hooks */ - group = nct6775_create_attr_group(dev, &nct6775_pwm_template_group, - data->pwm_num); - if (IS_ERR(group)) - return PTR_ERR(group); - - data->groups[num_attr_groups++] = group; - - group = nct6775_create_attr_group(dev, &nct6775_in_template_group, - fls(data->have_in)); - if (IS_ERR(group)) - return PTR_ERR(group); - - data->groups[num_attr_groups++] = group; - - group = nct6775_create_attr_group(dev, &nct6775_fan_template_group, - fls(data->has_fan)); - if (IS_ERR(group)) - return PTR_ERR(group); + err = nct6775_add_template_attr_group(dev, data, &nct6775_pwm_template_group, + data->pwm_num); + if (err) + return err; - data->groups[num_attr_groups++] = group; + err = nct6775_add_template_attr_group(dev, data, &nct6775_in_template_group, + fls(data->have_in)); + if (err) + return err; - group = nct6775_create_attr_group(dev, &nct6775_temp_template_group, - fls(data->have_temp)); - if (IS_ERR(group)) - return PTR_ERR(group); + err = nct6775_add_template_attr_group(dev, data, &nct6775_fan_template_group, + fls(data->has_fan)); + if (err) + return err; - data->groups[num_attr_groups++] = group; + err = nct6775_add_template_attr_group(dev, data, &nct6775_temp_template_group, + fls(data->have_temp)); + if (err) + return err; if (data->have_tsi_temp) { tsi_temp_tg.templates = nct6775_tsi_temp_template; tsi_temp_tg.is_visible = nct6775_tsi_temp_is_visible; tsi_temp_tg.base = fls(data->have_temp) + 1; - group = nct6775_create_attr_group(dev, &tsi_temp_tg, fls(data->have_tsi_temp)); - if (IS_ERR(group)) - return PTR_ERR(group); - - data->groups[num_attr_groups++] = group; + err = nct6775_add_template_attr_group(dev, data, &tsi_temp_tg, + fls(data->have_tsi_temp)); + if (err) + return err; } - data->groups[num_attr_groups++] = &nct6775_group_other; - hwmon_dev = devm_hwmon_device_register_with_groups(dev, data->name, data, data->groups); return PTR_ERR_OR_ZERO(hwmon_dev); } - -static void nct6791_enable_io_mapping(struct nct6775_sio_data *sio_data) -{ - int val; - - val = sio_data->sio_inb(sio_data, NCT6791_REG_HM_IO_SPACE_LOCK_ENABLE); - if (val & 0x10) { - pr_info("Enabling hardware monitor logical device mappings.\n"); - sio_data->sio_outb(sio_data, NCT6791_REG_HM_IO_SPACE_LOCK_ENABLE, - val & ~0x10); - } -} - -static int __maybe_unused nct6775_suspend(struct device *dev) -{ - struct nct6775_data *data = nct6775_update_device(dev); - - mutex_lock(&data->update_lock); - data->vbat = data->read_value(data, data->REG_VBAT); - if (data->kind == nct6775) { - data->fandiv1 = data->read_value(data, NCT6775_REG_FANDIV1); - data->fandiv2 = data->read_value(data, NCT6775_REG_FANDIV2); - } - mutex_unlock(&data->update_lock); - - return 0; -} - -static int __maybe_unused nct6775_resume(struct device *dev) -{ - struct nct6775_data *data = dev_get_drvdata(dev); - struct nct6775_sio_data *sio_data = dev_get_platdata(dev); - int i, j, err = 0; - u8 reg; - - mutex_lock(&data->update_lock); - data->bank = 0xff; /* Force initial bank selection */ - - err = sio_data->sio_enter(sio_data); - if (err) - goto abort; - - sio_data->sio_select(sio_data, NCT6775_LD_HWM); - reg = sio_data->sio_inb(sio_data, SIO_REG_ENABLE); - if (reg != data->sio_reg_enable) - sio_data->sio_outb(sio_data, SIO_REG_ENABLE, data->sio_reg_enable); - - if (data->kind == nct6791 || data->kind == nct6792 || - data->kind == nct6793 || data->kind == nct6795 || - data->kind == nct6796 || data->kind == nct6797 || - data->kind == nct6798) - nct6791_enable_io_mapping(sio_data); - - sio_data->sio_exit(sio_data); - - /* Restore limits */ - for (i = 0; i < data->in_num; i++) { - if (!(data->have_in & BIT(i))) - continue; - - data->write_value(data, data->REG_IN_MINMAX[0][i], - data->in[i][1]); - data->write_value(data, data->REG_IN_MINMAX[1][i], - data->in[i][2]); - } - - for (i = 0; i < ARRAY_SIZE(data->fan_min); i++) { - if (!(data->has_fan_min & BIT(i))) - continue; - - data->write_value(data, data->REG_FAN_MIN[i], - data->fan_min[i]); - } - - for (i = 0; i < NUM_TEMP; i++) { - if (!(data->have_temp & BIT(i))) - continue; - - for (j = 1; j < ARRAY_SIZE(data->reg_temp); j++) - if (data->reg_temp[j][i]) - nct6775_write_temp(data, data->reg_temp[j][i], - data->temp[j][i]); - } - - /* Restore other settings */ - data->write_value(data, data->REG_VBAT, data->vbat); - if (data->kind == nct6775) { - data->write_value(data, NCT6775_REG_FANDIV1, data->fandiv1); - data->write_value(data, NCT6775_REG_FANDIV2, data->fandiv2); - } - -abort: - /* Force re-reading all values */ - data->valid = false; - mutex_unlock(&data->update_lock); - - return err; -} - -static SIMPLE_DEV_PM_OPS(nct6775_dev_pm_ops, nct6775_suspend, nct6775_resume); - -static struct platform_driver nct6775_driver = { - .driver = { - .name = DRVNAME, - .pm = &nct6775_dev_pm_ops, - }, - .probe = nct6775_probe, -}; - -/* nct6775_find() looks for a '627 in the Super-I/O config space */ -static int __init nct6775_find(int sioaddr, struct nct6775_sio_data *sio_data) -{ - u16 val; - int err; - int addr; - - sio_data->access = access_direct; - sio_data->sioreg = sioaddr; - - err = sio_data->sio_enter(sio_data); - if (err) - return err; - - val = (sio_data->sio_inb(sio_data, SIO_REG_DEVID) << 8) | - sio_data->sio_inb(sio_data, SIO_REG_DEVID + 1); - if (force_id && val != 0xffff) - val = force_id; - - switch (val & SIO_ID_MASK) { - case SIO_NCT6106_ID: - sio_data->kind = nct6106; - break; - case SIO_NCT6116_ID: - sio_data->kind = nct6116; - break; - case SIO_NCT6775_ID: - sio_data->kind = nct6775; - break; - case SIO_NCT6776_ID: - sio_data->kind = nct6776; - break; - case SIO_NCT6779_ID: - sio_data->kind = nct6779; - break; - case SIO_NCT6791_ID: - sio_data->kind = nct6791; - break; - case SIO_NCT6792_ID: - sio_data->kind = nct6792; - break; - case SIO_NCT6793_ID: - sio_data->kind = nct6793; - break; - case SIO_NCT6795_ID: - sio_data->kind = nct6795; - break; - case SIO_NCT6796_ID: - sio_data->kind = nct6796; - break; - case SIO_NCT6797_ID: - sio_data->kind = nct6797; - break; - case SIO_NCT6798_ID: - sio_data->kind = nct6798; - break; - default: - if (val != 0xffff) - pr_debug("unsupported chip ID: 0x%04x\n", val); - sio_data->sio_exit(sio_data); - return -ENODEV; - } - - /* We have a known chip, find the HWM I/O address */ - sio_data->sio_select(sio_data, NCT6775_LD_HWM); - val = (sio_data->sio_inb(sio_data, SIO_REG_ADDR) << 8) - | sio_data->sio_inb(sio_data, SIO_REG_ADDR + 1); - addr = val & IOREGION_ALIGNMENT; - if (addr == 0) { - pr_err("Refusing to enable a Super-I/O device with a base I/O port 0\n"); - sio_data->sio_exit(sio_data); - return -ENODEV; - } - - /* Activate logical device if needed */ - val = sio_data->sio_inb(sio_data, SIO_REG_ENABLE); - if (!(val & 0x01)) { - pr_warn("Forcibly enabling Super-I/O. Sensor is probably unusable.\n"); - sio_data->sio_outb(sio_data, SIO_REG_ENABLE, val | 0x01); - } - - if (sio_data->kind == nct6791 || sio_data->kind == nct6792 || - sio_data->kind == nct6793 || sio_data->kind == nct6795 || - sio_data->kind == nct6796 || sio_data->kind == nct6797 || - sio_data->kind == nct6798) - nct6791_enable_io_mapping(sio_data); - - sio_data->sio_exit(sio_data); - pr_info("Found %s or compatible chip at %#x:%#x\n", - nct6775_sio_names[sio_data->kind], sioaddr, addr); - - return addr; -} - -/* - * when Super-I/O functions move to a separate file, the Super-I/O - * bus will manage the lifetime of the device and this module will only keep - * track of the nct6775 driver. But since we use platform_device_alloc(), we - * must keep track of the device - */ -static struct platform_device *pdev[2]; - -static const char * const asus_wmi_boards[] = { - "ProArt X570-CREATOR WIFI", - "Pro B550M-C", - "Pro WS X570-ACE", - "PRIME B360-PLUS", - "PRIME B460-PLUS", - "PRIME B550-PLUS", - "PRIME B550M-A", - "PRIME B550M-A (WI-FI)", - "PRIME X570-P", - "PRIME X570-PRO", - "ROG CROSSHAIR VIII DARK HERO", - "ROG CROSSHAIR VIII FORMULA", - "ROG CROSSHAIR VIII HERO", - "ROG CROSSHAIR VIII IMPACT", - "ROG STRIX B550-A GAMING", - "ROG STRIX B550-E GAMING", - "ROG STRIX B550-F GAMING", - "ROG STRIX B550-F GAMING (WI-FI)", - "ROG STRIX B550-F GAMING WIFI II", - "ROG STRIX B550-I GAMING", - "ROG STRIX B550-XE GAMING (WI-FI)", - "ROG STRIX X570-E GAMING", - "ROG STRIX X570-F GAMING", - "ROG STRIX X570-I GAMING", - "ROG STRIX Z390-E GAMING", - "ROG STRIX Z390-F GAMING", - "ROG STRIX Z390-H GAMING", - "ROG STRIX Z390-I GAMING", - "ROG STRIX Z490-A GAMING", - "ROG STRIX Z490-E GAMING", - "ROG STRIX Z490-F GAMING", - "ROG STRIX Z490-G GAMING", - "ROG STRIX Z490-G GAMING (WI-FI)", - "ROG STRIX Z490-H GAMING", - "ROG STRIX Z490-I GAMING", - "TUF GAMING B550M-PLUS", - "TUF GAMING B550M-PLUS (WI-FI)", - "TUF GAMING B550-PLUS", - "TUF GAMING B550-PRO", - "TUF GAMING X570-PLUS", - "TUF GAMING X570-PLUS (WI-FI)", - "TUF GAMING X570-PRO (WI-FI)", - "TUF GAMING Z490-PLUS", - "TUF GAMING Z490-PLUS (WI-FI)", -}; - -static int __init sensors_nct6775_init(void) -{ - int i, err; - bool found = false; - int address; - struct resource res; - struct nct6775_sio_data sio_data; - int sioaddr[2] = { 0x2e, 0x4e }; - enum sensor_access access = access_direct; - const char *board_vendor, *board_name; - u8 tmp; - - err = platform_driver_register(&nct6775_driver); - if (err) - return err; - - board_vendor = dmi_get_system_info(DMI_BOARD_VENDOR); - board_name = dmi_get_system_info(DMI_BOARD_NAME); - - if (board_name && board_vendor && - !strcmp(board_vendor, "ASUSTeK COMPUTER INC.")) { - err = match_string(asus_wmi_boards, ARRAY_SIZE(asus_wmi_boards), - board_name); - if (err >= 0) { - /* if reading chip id via WMI succeeds, use WMI */ - if (!nct6775_asuswmi_read(0, NCT6775_PORT_CHIPID, &tmp) && tmp) { - pr_info("Using Asus WMI to access %#x chip.\n", tmp); - access = access_asuswmi; - } else { - pr_err("Can't read ChipID by Asus WMI.\n"); - } - } - } - - /* - * initialize sio_data->kind and sio_data->sioreg. - * - * when Super-I/O functions move to a separate file, the Super-I/O - * driver will probe 0x2e and 0x4e and auto-detect the presence of a - * nct6775 hardware monitor, and call probe() - */ - for (i = 0; i < ARRAY_SIZE(pdev); i++) { - sio_data.sio_outb = superio_outb; - sio_data.sio_inb = superio_inb; - sio_data.sio_select = superio_select; - sio_data.sio_enter = superio_enter; - sio_data.sio_exit = superio_exit; - - address = nct6775_find(sioaddr[i], &sio_data); - if (address <= 0) - continue; - - found = true; - - sio_data.access = access; - - if (access == access_asuswmi) { - sio_data.sio_outb = superio_wmi_outb; - sio_data.sio_inb = superio_wmi_inb; - sio_data.sio_select = superio_wmi_select; - sio_data.sio_enter = superio_wmi_enter; - sio_data.sio_exit = superio_wmi_exit; - } - - pdev[i] = platform_device_alloc(DRVNAME, address); - if (!pdev[i]) { - err = -ENOMEM; - goto exit_device_unregister; - } - - err = platform_device_add_data(pdev[i], &sio_data, - sizeof(struct nct6775_sio_data)); - if (err) - goto exit_device_put; - - if (sio_data.access == access_direct) { - memset(&res, 0, sizeof(res)); - res.name = DRVNAME; - res.start = address + IOREGION_OFFSET; - res.end = address + IOREGION_OFFSET + IOREGION_LENGTH - 1; - res.flags = IORESOURCE_IO; - - err = acpi_check_resource_conflict(&res); - if (err) { - platform_device_put(pdev[i]); - pdev[i] = NULL; - continue; - } - - err = platform_device_add_resources(pdev[i], &res, 1); - if (err) - goto exit_device_put; - } - - /* platform_device_add calls probe() */ - err = platform_device_add(pdev[i]); - if (err) - goto exit_device_put; - } - if (!found) { - err = -ENODEV; - goto exit_unregister; - } - - return 0; - -exit_device_put: - platform_device_put(pdev[i]); -exit_device_unregister: - while (--i >= 0) { - if (pdev[i]) - platform_device_unregister(pdev[i]); - } -exit_unregister: - platform_driver_unregister(&nct6775_driver); - return err; -} - -static void __exit sensors_nct6775_exit(void) -{ - int i; - - for (i = 0; i < ARRAY_SIZE(pdev); i++) { - if (pdev[i]) - platform_device_unregister(pdev[i]); - } - platform_driver_unregister(&nct6775_driver); -} +EXPORT_SYMBOL_GPL(nct6775_probe); MODULE_AUTHOR("Guenter Roeck <linux@roeck-us.net>"); -MODULE_DESCRIPTION("Driver for NCT6775F and compatible chips"); +MODULE_DESCRIPTION("Core driver for NCT6775F and compatible chips"); MODULE_LICENSE("GPL"); - -module_init(sensors_nct6775_init); -module_exit(sensors_nct6775_exit); diff --git a/drivers/hwmon/nct6775-i2c.c b/drivers/hwmon/nct6775-i2c.c new file mode 100644 index 000000000000..e1bcd1146191 --- /dev/null +++ b/drivers/hwmon/nct6775-i2c.c @@ -0,0 +1,195 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * nct6775-i2c - I2C driver for the hardware monitoring functionality of + * Nuvoton NCT677x Super-I/O chips + * + * Copyright (C) 2022 Zev Weiss <zev@bewilderbeest.net> + * + * This driver interacts with the chip via it's "back door" i2c interface, as + * is often exposed to a BMC. Because the host may still be operating the + * chip via the ("front door") LPC interface, this driver cannot assume that + * it actually has full control of the chip, and in particular must avoid + * making any changes that could confuse the host's LPC usage of it. It thus + * operates in a strictly read-only fashion, with the only exception being the + * bank-select register (which seems, thankfully, to be replicated for the i2c + * interface so it doesn't affect the LPC interface). + */ + +#include <linux/module.h> +#include <linux/init.h> +#include <linux/i2c.h> +#include <linux/hwmon.h> +#include <linux/hwmon-sysfs.h> +#include <linux/err.h> +#include <linux/of_device.h> +#include <linux/regmap.h> +#include "nct6775.h" + +static int nct6775_i2c_read(void *ctx, unsigned int reg, unsigned int *val) +{ + int ret; + u32 tmp; + u8 bank = reg >> 8; + struct nct6775_data *data = ctx; + struct i2c_client *client = data->driver_data; + + if (bank != data->bank) { + ret = i2c_smbus_write_byte_data(client, NCT6775_REG_BANK, bank); + if (ret) + return ret; + data->bank = bank; + } + + ret = i2c_smbus_read_byte_data(client, reg & 0xff); + if (ret < 0) + return ret; + tmp = ret; + + if (nct6775_reg_is_word_sized(data, reg)) { + ret = i2c_smbus_read_byte_data(client, (reg & 0xff) + 1); + if (ret < 0) + return ret; + tmp = (tmp << 8) | ret; + } + + *val = tmp; + return 0; +} + +/* + * The write operation is a dummy so as not to disturb anything being done + * with the chip via LPC. + */ +static int nct6775_i2c_write(void *ctx, unsigned int reg, unsigned int value) +{ + struct nct6775_data *data = ctx; + struct i2c_client *client = data->driver_data; + + dev_dbg(&client->dev, "skipping attempted write: %02x -> %03x\n", value, reg); + + /* + * This is a lie, but writing anything but the bank-select register is + * something this driver shouldn't be doing. + */ + return 0; +} + +static const struct of_device_id __maybe_unused nct6775_i2c_of_match[] = { + { .compatible = "nuvoton,nct6106", .data = (void *)nct6106, }, + { .compatible = "nuvoton,nct6116", .data = (void *)nct6116, }, + { .compatible = "nuvoton,nct6775", .data = (void *)nct6775, }, + { .compatible = "nuvoton,nct6776", .data = (void *)nct6776, }, + { .compatible = "nuvoton,nct6779", .data = (void *)nct6779, }, + { .compatible = "nuvoton,nct6791", .data = (void *)nct6791, }, + { .compatible = "nuvoton,nct6792", .data = (void *)nct6792, }, + { .compatible = "nuvoton,nct6793", .data = (void *)nct6793, }, + { .compatible = "nuvoton,nct6795", .data = (void *)nct6795, }, + { .compatible = "nuvoton,nct6796", .data = (void *)nct6796, }, + { .compatible = "nuvoton,nct6797", .data = (void *)nct6797, }, + { .compatible = "nuvoton,nct6798", .data = (void *)nct6798, }, + { }, +}; +MODULE_DEVICE_TABLE(of, nct6775_i2c_of_match); + +static const struct i2c_device_id nct6775_i2c_id[] = { + { "nct6106", nct6106 }, + { "nct6116", nct6116 }, + { "nct6775", nct6775 }, + { "nct6776", nct6776 }, + { "nct6779", nct6779 }, + { "nct6791", nct6791 }, + { "nct6792", nct6792 }, + { "nct6793", nct6793 }, + { "nct6795", nct6795 }, + { "nct6796", nct6796 }, + { "nct6797", nct6797 }, + { "nct6798", nct6798 }, + { } +}; +MODULE_DEVICE_TABLE(i2c, nct6775_i2c_id); + +static int nct6775_i2c_probe_init(struct nct6775_data *data) +{ + u32 tsi_channel_mask; + struct i2c_client *client = data->driver_data; + + /* + * The i2c interface doesn't provide access to the control registers + * needed to determine the presence of other fans, but fans 1 and 2 + * are (in principle) always there. + * + * In practice this is perhaps a little silly, because the system + * using this driver is mostly likely a BMC, and hence probably has + * totally separate fan tachs & pwms of its own that are actually + * controlling/monitoring the fans -- these are thus unlikely to be + * doing anything actually useful. + */ + data->has_fan = 0x03; + data->has_fan_min = 0x03; + data->has_pwm = 0x03; + + /* + * Because on a BMC this driver may be bound very shortly after power + * is first applied to the device, the automatic TSI channel detection + * in nct6775_probe() (which has already been run at this point) may + * not find anything if a channel hasn't yet produced a temperature + * reading. Augment whatever was found via autodetection (if + * anything) with the channels DT says should be active. + */ + if (!of_property_read_u32(client->dev.of_node, "nuvoton,tsi-channel-mask", + &tsi_channel_mask)) + data->have_tsi_temp |= tsi_channel_mask & GENMASK(NUM_TSI_TEMP - 1, 0); + + return 0; +} + +static const struct regmap_config nct6775_i2c_regmap_config = { + .reg_bits = 16, + .val_bits = 16, + .reg_read = nct6775_i2c_read, + .reg_write = nct6775_i2c_write, +}; + +static int nct6775_i2c_probe(struct i2c_client *client) +{ + struct nct6775_data *data; + const struct of_device_id *of_id; + const struct i2c_device_id *i2c_id; + struct device *dev = &client->dev; + + of_id = of_match_device(nct6775_i2c_of_match, dev); + i2c_id = i2c_match_id(nct6775_i2c_id, client); + + if (of_id && (unsigned long)of_id->data != i2c_id->driver_data) + dev_notice(dev, "Device mismatch: %s in device tree, %s detected\n", + of_id->name, i2c_id->name); + + data = devm_kzalloc(&client->dev, sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; + + data->kind = i2c_id->driver_data; + + data->read_only = true; + data->driver_data = client; + data->driver_init = nct6775_i2c_probe_init; + + return nct6775_probe(dev, data, &nct6775_i2c_regmap_config); +} + +static struct i2c_driver nct6775_i2c_driver = { + .class = I2C_CLASS_HWMON, + .driver = { + .name = "nct6775-i2c", + .of_match_table = of_match_ptr(nct6775_i2c_of_match), + }, + .probe_new = nct6775_i2c_probe, + .id_table = nct6775_i2c_id, +}; + +module_i2c_driver(nct6775_i2c_driver); + +MODULE_AUTHOR("Zev Weiss <zev@bewilderbeest.net>"); +MODULE_DESCRIPTION("I2C driver for NCT6775F and compatible chips"); +MODULE_LICENSE("GPL"); +MODULE_IMPORT_NS(HWMON_NCT6775); diff --git a/drivers/hwmon/nct6775-platform.c b/drivers/hwmon/nct6775-platform.c new file mode 100644 index 000000000000..6d46c9401898 --- /dev/null +++ b/drivers/hwmon/nct6775-platform.c @@ -0,0 +1,1229 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * nct6775 - Platform driver for the hardware monitoring + * functionality of Nuvoton NCT677x Super-I/O chips + * + * Copyright (C) 2012 Guenter Roeck <linux@roeck-us.net> + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/acpi.h> +#include <linux/dmi.h> +#include <linux/hwmon-sysfs.h> +#include <linux/hwmon-vid.h> +#include <linux/init.h> +#include <linux/io.h> +#include <linux/module.h> +#include <linux/platform_device.h> +#include <linux/regmap.h> +#include <linux/wmi.h> + +#include "nct6775.h" + +enum sensor_access { access_direct, access_asuswmi }; + +static const char * const nct6775_sio_names[] __initconst = { + "NCT6106D", + "NCT6116D", + "NCT6775F", + "NCT6776D/F", + "NCT6779D", + "NCT6791D", + "NCT6792D", + "NCT6793D", + "NCT6795D", + "NCT6796D", + "NCT6797D", + "NCT6798D", +}; + +static unsigned short force_id; +module_param(force_id, ushort, 0); +MODULE_PARM_DESC(force_id, "Override the detected device ID"); + +static unsigned short fan_debounce; +module_param(fan_debounce, ushort, 0); +MODULE_PARM_DESC(fan_debounce, "Enable debouncing for fan RPM signal"); + +#define DRVNAME "nct6775" + +#define NCT6775_PORT_CHIPID 0x58 + +/* + * ISA constants + */ + +#define IOREGION_ALIGNMENT (~7) +#define IOREGION_OFFSET 5 +#define IOREGION_LENGTH 2 +#define ADDR_REG_OFFSET 0 +#define DATA_REG_OFFSET 1 + +/* + * Super-I/O constants and functions + */ + +#define NCT6775_LD_ACPI 0x0a +#define NCT6775_LD_HWM 0x0b +#define NCT6775_LD_VID 0x0d +#define NCT6775_LD_12 0x12 + +#define SIO_REG_LDSEL 0x07 /* Logical device select */ +#define SIO_REG_DEVID 0x20 /* Device ID (2 bytes) */ +#define SIO_REG_ENABLE 0x30 /* Logical device enable */ +#define SIO_REG_ADDR 0x60 /* Logical device address (2 bytes) */ + +#define SIO_NCT6106_ID 0xc450 +#define SIO_NCT6116_ID 0xd280 +#define SIO_NCT6775_ID 0xb470 +#define SIO_NCT6776_ID 0xc330 +#define SIO_NCT6779_ID 0xc560 +#define SIO_NCT6791_ID 0xc800 +#define SIO_NCT6792_ID 0xc910 +#define SIO_NCT6793_ID 0xd120 +#define SIO_NCT6795_ID 0xd350 +#define SIO_NCT6796_ID 0xd420 +#define SIO_NCT6797_ID 0xd450 +#define SIO_NCT6798_ID 0xd428 +#define SIO_ID_MASK 0xFFF8 + +/* + * Control registers + */ +#define NCT6775_REG_CR_FAN_DEBOUNCE 0xf0 + +struct nct6775_sio_data { + int sioreg; + int ld; + enum kinds kind; + enum sensor_access access; + + /* superio_() callbacks */ + void (*sio_outb)(struct nct6775_sio_data *sio_data, int reg, int val); + int (*sio_inb)(struct nct6775_sio_data *sio_data, int reg); + void (*sio_select)(struct nct6775_sio_data *sio_data, int ld); + int (*sio_enter)(struct nct6775_sio_data *sio_data); + void (*sio_exit)(struct nct6775_sio_data *sio_data); +}; + +#define ASUSWMI_MONITORING_GUID "466747A0-70EC-11DE-8A39-0800200C9A66" +#define ASUSWMI_METHODID_RSIO 0x5253494F +#define ASUSWMI_METHODID_WSIO 0x5753494F +#define ASUSWMI_METHODID_RHWM 0x5248574D +#define ASUSWMI_METHODID_WHWM 0x5748574D +#define ASUSWMI_UNSUPPORTED_METHOD 0xFFFFFFFE + +static int nct6775_asuswmi_evaluate_method(u32 method_id, u8 bank, u8 reg, u8 val, u32 *retval) +{ +#if IS_ENABLED(CONFIG_ACPI_WMI) + u32 args = bank | (reg << 8) | (val << 16); + struct acpi_buffer input = { (acpi_size) sizeof(args), &args }; + struct acpi_buffer output = { ACPI_ALLOCATE_BUFFER, NULL }; + acpi_status status; + union acpi_object *obj; + u32 tmp = ASUSWMI_UNSUPPORTED_METHOD; + + status = wmi_evaluate_method(ASUSWMI_MONITORING_GUID, 0, + method_id, &input, &output); + + if (ACPI_FAILURE(status)) + return -EIO; + + obj = output.pointer; + if (obj && obj->type == ACPI_TYPE_INTEGER) + tmp = obj->integer.value; + + if (retval) + *retval = tmp; + + kfree(obj); + + if (tmp == ASUSWMI_UNSUPPORTED_METHOD) + return -ENODEV; + return 0; +#else + return -EOPNOTSUPP; +#endif +} + +static inline int nct6775_asuswmi_write(u8 bank, u8 reg, u8 val) +{ + return nct6775_asuswmi_evaluate_method(ASUSWMI_METHODID_WHWM, bank, + reg, val, NULL); +} + +static inline int nct6775_asuswmi_read(u8 bank, u8 reg, u8 *val) +{ + u32 ret, tmp = 0; + + ret = nct6775_asuswmi_evaluate_method(ASUSWMI_METHODID_RHWM, bank, + reg, 0, &tmp); + *val = tmp; + return ret; +} + +static int superio_wmi_inb(struct nct6775_sio_data *sio_data, int reg) +{ + int tmp = 0; + + nct6775_asuswmi_evaluate_method(ASUSWMI_METHODID_RSIO, sio_data->ld, + reg, 0, &tmp); + return tmp; +} + +static void superio_wmi_outb(struct nct6775_sio_data *sio_data, int reg, int val) +{ + nct6775_asuswmi_evaluate_method(ASUSWMI_METHODID_WSIO, sio_data->ld, + reg, val, NULL); +} + +static void superio_wmi_select(struct nct6775_sio_data *sio_data, int ld) +{ + sio_data->ld = ld; +} + +static int superio_wmi_enter(struct nct6775_sio_data *sio_data) +{ + return 0; +} + +static void superio_wmi_exit(struct nct6775_sio_data *sio_data) +{ +} + +static void superio_outb(struct nct6775_sio_data *sio_data, int reg, int val) +{ + int ioreg = sio_data->sioreg; + + outb(reg, ioreg); + outb(val, ioreg + 1); +} + +static int superio_inb(struct nct6775_sio_data *sio_data, int reg) +{ + int ioreg = sio_data->sioreg; + + outb(reg, ioreg); + return inb(ioreg + 1); +} + +static void superio_select(struct nct6775_sio_data *sio_data, int ld) +{ + int ioreg = sio_data->sioreg; + + outb(SIO_REG_LDSEL, ioreg); + outb(ld, ioreg + 1); +} + +static int superio_enter(struct nct6775_sio_data *sio_data) +{ + int ioreg = sio_data->sioreg; + + /* + * Try to reserve <ioreg> and <ioreg + 1> for exclusive access. + */ + if (!request_muxed_region(ioreg, 2, DRVNAME)) + return -EBUSY; + + outb(0x87, ioreg); + outb(0x87, ioreg); + + return 0; +} + +static void superio_exit(struct nct6775_sio_data *sio_data) +{ + int ioreg = sio_data->sioreg; + + outb(0xaa, ioreg); + outb(0x02, ioreg); + outb(0x02, ioreg + 1); + release_region(ioreg, 2); +} + +static inline void nct6775_wmi_set_bank(struct nct6775_data *data, u16 reg) +{ + u8 bank = reg >> 8; + + data->bank = bank; +} + +static int nct6775_wmi_reg_read(void *ctx, unsigned int reg, unsigned int *val) +{ + struct nct6775_data *data = ctx; + int err, word_sized = nct6775_reg_is_word_sized(data, reg); + u8 tmp = 0; + u16 res; + + nct6775_wmi_set_bank(data, reg); + + err = nct6775_asuswmi_read(data->bank, reg & 0xff, &tmp); + if (err) + return err; + + res = tmp; + if (word_sized) { + err = nct6775_asuswmi_read(data->bank, (reg & 0xff) + 1, &tmp); + if (err) + return err; + + res = (res << 8) + tmp; + } + *val = res; + return 0; +} + +static int nct6775_wmi_reg_write(void *ctx, unsigned int reg, unsigned int value) +{ + struct nct6775_data *data = ctx; + int res, word_sized = nct6775_reg_is_word_sized(data, reg); + + nct6775_wmi_set_bank(data, reg); + + if (word_sized) { + res = nct6775_asuswmi_write(data->bank, reg & 0xff, value >> 8); + if (res) + return res; + + res = nct6775_asuswmi_write(data->bank, (reg & 0xff) + 1, value); + } else { + res = nct6775_asuswmi_write(data->bank, reg & 0xff, value); + } + + return res; +} + +/* + * On older chips, only registers 0x50-0x5f are banked. + * On more recent chips, all registers are banked. + * Assume that is the case and set the bank number for each access. + * Cache the bank number so it only needs to be set if it changes. + */ +static inline void nct6775_set_bank(struct nct6775_data *data, u16 reg) +{ + u8 bank = reg >> 8; + + if (data->bank != bank) { + outb_p(NCT6775_REG_BANK, data->addr + ADDR_REG_OFFSET); + outb_p(bank, data->addr + DATA_REG_OFFSET); + data->bank = bank; + } +} + +static int nct6775_reg_read(void *ctx, unsigned int reg, unsigned int *val) +{ + struct nct6775_data *data = ctx; + int word_sized = nct6775_reg_is_word_sized(data, reg); + + nct6775_set_bank(data, reg); + outb_p(reg & 0xff, data->addr + ADDR_REG_OFFSET); + *val = inb_p(data->addr + DATA_REG_OFFSET); + if (word_sized) { + outb_p((reg & 0xff) + 1, + data->addr + ADDR_REG_OFFSET); + *val = (*val << 8) + inb_p(data->addr + DATA_REG_OFFSET); + } + return 0; +} + +static int nct6775_reg_write(void *ctx, unsigned int reg, unsigned int value) +{ + struct nct6775_data *data = ctx; + int word_sized = nct6775_reg_is_word_sized(data, reg); + + nct6775_set_bank(data, reg); + outb_p(reg & 0xff, data->addr + ADDR_REG_OFFSET); + if (word_sized) { + outb_p(value >> 8, data->addr + DATA_REG_OFFSET); + outb_p((reg & 0xff) + 1, + data->addr + ADDR_REG_OFFSET); + } + outb_p(value & 0xff, data->addr + DATA_REG_OFFSET); + return 0; +} + +static void nct6791_enable_io_mapping(struct nct6775_sio_data *sio_data) +{ + int val; + + val = sio_data->sio_inb(sio_data, NCT6791_REG_HM_IO_SPACE_LOCK_ENABLE); + if (val & 0x10) { + pr_info("Enabling hardware monitor logical device mappings.\n"); + sio_data->sio_outb(sio_data, NCT6791_REG_HM_IO_SPACE_LOCK_ENABLE, + val & ~0x10); + } +} + +static int __maybe_unused nct6775_suspend(struct device *dev) +{ + int err; + u16 tmp; + struct nct6775_data *data = dev_get_drvdata(dev); + + if (IS_ERR(data)) + return PTR_ERR(data); + + mutex_lock(&data->update_lock); + err = nct6775_read_value(data, data->REG_VBAT, &tmp); + if (err) + goto out; + data->vbat = tmp; + if (data->kind == nct6775) { + err = nct6775_read_value(data, NCT6775_REG_FANDIV1, &tmp); + if (err) + goto out; + data->fandiv1 = tmp; + + err = nct6775_read_value(data, NCT6775_REG_FANDIV2, &tmp); + if (err) + goto out; + data->fandiv2 = tmp; + } +out: + mutex_unlock(&data->update_lock); + + return err; +} + +static int __maybe_unused nct6775_resume(struct device *dev) +{ + struct nct6775_data *data = dev_get_drvdata(dev); + struct nct6775_sio_data *sio_data = dev_get_platdata(dev); + int i, j, err = 0; + u8 reg; + + mutex_lock(&data->update_lock); + data->bank = 0xff; /* Force initial bank selection */ + + err = sio_data->sio_enter(sio_data); + if (err) + goto abort; + + sio_data->sio_select(sio_data, NCT6775_LD_HWM); + reg = sio_data->sio_inb(sio_data, SIO_REG_ENABLE); + if (reg != data->sio_reg_enable) + sio_data->sio_outb(sio_data, SIO_REG_ENABLE, data->sio_reg_enable); + + if (data->kind == nct6791 || data->kind == nct6792 || + data->kind == nct6793 || data->kind == nct6795 || + data->kind == nct6796 || data->kind == nct6797 || + data->kind == nct6798) + nct6791_enable_io_mapping(sio_data); + + sio_data->sio_exit(sio_data); + + /* Restore limits */ + for (i = 0; i < data->in_num; i++) { + if (!(data->have_in & BIT(i))) + continue; + + err = nct6775_write_value(data, data->REG_IN_MINMAX[0][i], data->in[i][1]); + if (err) + goto abort; + err = nct6775_write_value(data, data->REG_IN_MINMAX[1][i], data->in[i][2]); + if (err) + goto abort; + } + + for (i = 0; i < ARRAY_SIZE(data->fan_min); i++) { + if (!(data->has_fan_min & BIT(i))) + continue; + + err = nct6775_write_value(data, data->REG_FAN_MIN[i], data->fan_min[i]); + if (err) + goto abort; + } + + for (i = 0; i < NUM_TEMP; i++) { + if (!(data->have_temp & BIT(i))) + continue; + + for (j = 1; j < ARRAY_SIZE(data->reg_temp); j++) + if (data->reg_temp[j][i]) { + err = nct6775_write_temp(data, data->reg_temp[j][i], + data->temp[j][i]); + if (err) + goto abort; + } + } + + /* Restore other settings */ + err = nct6775_write_value(data, data->REG_VBAT, data->vbat); + if (err) + goto abort; + if (data->kind == nct6775) { + err = nct6775_write_value(data, NCT6775_REG_FANDIV1, data->fandiv1); + if (err) + goto abort; + err = nct6775_write_value(data, NCT6775_REG_FANDIV2, data->fandiv2); + } + +abort: + /* Force re-reading all values */ + data->valid = false; + mutex_unlock(&data->update_lock); + + return err; +} + +static SIMPLE_DEV_PM_OPS(nct6775_dev_pm_ops, nct6775_suspend, nct6775_resume); + +static void +nct6775_check_fan_inputs(struct nct6775_data *data, struct nct6775_sio_data *sio_data) +{ + bool fan3pin = false, fan4pin = false, fan4min = false; + bool fan5pin = false, fan6pin = false, fan7pin = false; + bool pwm3pin = false, pwm4pin = false, pwm5pin = false; + bool pwm6pin = false, pwm7pin = false; + + /* Store SIO_REG_ENABLE for use during resume */ + sio_data->sio_select(sio_data, NCT6775_LD_HWM); + data->sio_reg_enable = sio_data->sio_inb(sio_data, SIO_REG_ENABLE); + + /* fan4 and fan5 share some pins with the GPIO and serial flash */ + if (data->kind == nct6775) { + int cr2c = sio_data->sio_inb(sio_data, 0x2c); + + fan3pin = cr2c & BIT(6); + pwm3pin = cr2c & BIT(7); + + /* On NCT6775, fan4 shares pins with the fdc interface */ + fan4pin = !(sio_data->sio_inb(sio_data, 0x2A) & 0x80); + } else if (data->kind == nct6776) { + bool gpok = sio_data->sio_inb(sio_data, 0x27) & 0x80; + const char *board_vendor, *board_name; + + board_vendor = dmi_get_system_info(DMI_BOARD_VENDOR); + board_name = dmi_get_system_info(DMI_BOARD_NAME); + + if (board_name && board_vendor && + !strcmp(board_vendor, "ASRock")) { + /* + * Auxiliary fan monitoring is not enabled on ASRock + * Z77 Pro4-M if booted in UEFI Ultra-FastBoot mode. + * Observed with BIOS version 2.00. + */ + if (!strcmp(board_name, "Z77 Pro4-M")) { + if ((data->sio_reg_enable & 0xe0) != 0xe0) { + data->sio_reg_enable |= 0xe0; + sio_data->sio_outb(sio_data, SIO_REG_ENABLE, + data->sio_reg_enable); + } + } + } + + if (data->sio_reg_enable & 0x80) + fan3pin = gpok; + else + fan3pin = !(sio_data->sio_inb(sio_data, 0x24) & 0x40); + + if (data->sio_reg_enable & 0x40) + fan4pin = gpok; + else + fan4pin = sio_data->sio_inb(sio_data, 0x1C) & 0x01; + + if (data->sio_reg_enable & 0x20) + fan5pin = gpok; + else + fan5pin = sio_data->sio_inb(sio_data, 0x1C) & 0x02; + + fan4min = fan4pin; + pwm3pin = fan3pin; + } else if (data->kind == nct6106) { + int cr24 = sio_data->sio_inb(sio_data, 0x24); + + fan3pin = !(cr24 & 0x80); + pwm3pin = cr24 & 0x08; + } else if (data->kind == nct6116) { + int cr1a = sio_data->sio_inb(sio_data, 0x1a); + int cr1b = sio_data->sio_inb(sio_data, 0x1b); + int cr24 = sio_data->sio_inb(sio_data, 0x24); + int cr2a = sio_data->sio_inb(sio_data, 0x2a); + int cr2b = sio_data->sio_inb(sio_data, 0x2b); + int cr2f = sio_data->sio_inb(sio_data, 0x2f); + + fan3pin = !(cr2b & 0x10); + fan4pin = (cr2b & 0x80) || // pin 1(2) + (!(cr2f & 0x10) && (cr1a & 0x04)); // pin 65(66) + fan5pin = (cr2b & 0x80) || // pin 126(127) + (!(cr1b & 0x03) && (cr2a & 0x02)); // pin 94(96) + + pwm3pin = fan3pin && (cr24 & 0x08); + pwm4pin = fan4pin; + pwm5pin = fan5pin; + } else { + /* + * NCT6779D, NCT6791D, NCT6792D, NCT6793D, NCT6795D, NCT6796D, + * NCT6797D, NCT6798D + */ + int cr1a = sio_data->sio_inb(sio_data, 0x1a); + int cr1b = sio_data->sio_inb(sio_data, 0x1b); + int cr1c = sio_data->sio_inb(sio_data, 0x1c); + int cr1d = sio_data->sio_inb(sio_data, 0x1d); + int cr2a = sio_data->sio_inb(sio_data, 0x2a); + int cr2b = sio_data->sio_inb(sio_data, 0x2b); + int cr2d = sio_data->sio_inb(sio_data, 0x2d); + int cr2f = sio_data->sio_inb(sio_data, 0x2f); + bool dsw_en = cr2f & BIT(3); + bool ddr4_en = cr2f & BIT(4); + int cre0; + int creb; + int cred; + + sio_data->sio_select(sio_data, NCT6775_LD_12); + cre0 = sio_data->sio_inb(sio_data, 0xe0); + creb = sio_data->sio_inb(sio_data, 0xeb); + cred = sio_data->sio_inb(sio_data, 0xed); + + fan3pin = !(cr1c & BIT(5)); + fan4pin = !(cr1c & BIT(6)); + fan5pin = !(cr1c & BIT(7)); + + pwm3pin = !(cr1c & BIT(0)); + pwm4pin = !(cr1c & BIT(1)); + pwm5pin = !(cr1c & BIT(2)); + + switch (data->kind) { + case nct6791: + fan6pin = cr2d & BIT(1); + pwm6pin = cr2d & BIT(0); + break; + case nct6792: + fan6pin = !dsw_en && (cr2d & BIT(1)); + pwm6pin = !dsw_en && (cr2d & BIT(0)); + break; + case nct6793: + fan5pin |= cr1b & BIT(5); + fan5pin |= creb & BIT(5); + + fan6pin = !dsw_en && (cr2d & BIT(1)); + fan6pin |= creb & BIT(3); + + pwm5pin |= cr2d & BIT(7); + pwm5pin |= (creb & BIT(4)) && !(cr2a & BIT(0)); + + pwm6pin = !dsw_en && (cr2d & BIT(0)); + pwm6pin |= creb & BIT(2); + break; + case nct6795: + fan5pin |= cr1b & BIT(5); + fan5pin |= creb & BIT(5); + + fan6pin = (cr2a & BIT(4)) && + (!dsw_en || (cred & BIT(4))); + fan6pin |= creb & BIT(3); + + pwm5pin |= cr2d & BIT(7); + pwm5pin |= (creb & BIT(4)) && !(cr2a & BIT(0)); + + pwm6pin = (cr2a & BIT(3)) && (cred & BIT(2)); + pwm6pin |= creb & BIT(2); + break; + case nct6796: + fan5pin |= cr1b & BIT(5); + fan5pin |= (cre0 & BIT(3)) && !(cr1b & BIT(0)); + fan5pin |= creb & BIT(5); + + fan6pin = (cr2a & BIT(4)) && + (!dsw_en || (cred & BIT(4))); + fan6pin |= creb & BIT(3); + + fan7pin = !(cr2b & BIT(2)); + + pwm5pin |= cr2d & BIT(7); + pwm5pin |= (cre0 & BIT(4)) && !(cr1b & BIT(0)); + pwm5pin |= (creb & BIT(4)) && !(cr2a & BIT(0)); + + pwm6pin = (cr2a & BIT(3)) && (cred & BIT(2)); + pwm6pin |= creb & BIT(2); + + pwm7pin = !(cr1d & (BIT(2) | BIT(3))); + break; + case nct6797: + fan5pin |= !ddr4_en && (cr1b & BIT(5)); + fan5pin |= creb & BIT(5); + + fan6pin = cr2a & BIT(4); + fan6pin |= creb & BIT(3); + + fan7pin = cr1a & BIT(1); + + pwm5pin |= (creb & BIT(4)) && !(cr2a & BIT(0)); + pwm5pin |= !ddr4_en && (cr2d & BIT(7)); + + pwm6pin = creb & BIT(2); + pwm6pin |= cred & BIT(2); + + pwm7pin = cr1d & BIT(4); + break; + case nct6798: + fan6pin = !(cr1b & BIT(0)) && (cre0 & BIT(3)); + fan6pin |= cr2a & BIT(4); + fan6pin |= creb & BIT(5); + + fan7pin = cr1b & BIT(5); + fan7pin |= !(cr2b & BIT(2)); + fan7pin |= creb & BIT(3); + + pwm6pin = !(cr1b & BIT(0)) && (cre0 & BIT(4)); + pwm6pin |= !(cred & BIT(2)) && (cr2a & BIT(3)); + pwm6pin |= (creb & BIT(4)) && !(cr2a & BIT(0)); + + pwm7pin = !(cr1d & (BIT(2) | BIT(3))); + pwm7pin |= cr2d & BIT(7); + pwm7pin |= creb & BIT(2); + break; + default: /* NCT6779D */ + break; + } + + fan4min = fan4pin; + } + + /* fan 1 and 2 (0x03) are always present */ + data->has_fan = 0x03 | (fan3pin << 2) | (fan4pin << 3) | + (fan5pin << 4) | (fan6pin << 5) | (fan7pin << 6); + data->has_fan_min = 0x03 | (fan3pin << 2) | (fan4min << 3) | + (fan5pin << 4) | (fan6pin << 5) | (fan7pin << 6); + data->has_pwm = 0x03 | (pwm3pin << 2) | (pwm4pin << 3) | + (pwm5pin << 4) | (pwm6pin << 5) | (pwm7pin << 6); +} + +static ssize_t +cpu0_vid_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct nct6775_data *data = dev_get_drvdata(dev); + + return sprintf(buf, "%d\n", vid_from_reg(data->vid, data->vrm)); +} + +static DEVICE_ATTR_RO(cpu0_vid); + +/* Case open detection */ + +static const u8 NCT6775_REG_CR_CASEOPEN_CLR[] = { 0xe6, 0xee }; +static const u8 NCT6775_CR_CASEOPEN_CLR_MASK[] = { 0x20, 0x01 }; + +static ssize_t +clear_caseopen(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + struct nct6775_data *data = dev_get_drvdata(dev); + struct nct6775_sio_data *sio_data = data->driver_data; + int nr = to_sensor_dev_attr(attr)->index - INTRUSION_ALARM_BASE; + unsigned long val; + u8 reg; + int ret; + + if (kstrtoul(buf, 10, &val) || val != 0) + return -EINVAL; + + mutex_lock(&data->update_lock); + + /* + * Use CR registers to clear caseopen status. + * The CR registers are the same for all chips, and not all chips + * support clearing the caseopen status through "regular" registers. + */ + ret = sio_data->sio_enter(sio_data); + if (ret) { + count = ret; + goto error; + } + + sio_data->sio_select(sio_data, NCT6775_LD_ACPI); + reg = sio_data->sio_inb(sio_data, NCT6775_REG_CR_CASEOPEN_CLR[nr]); + reg |= NCT6775_CR_CASEOPEN_CLR_MASK[nr]; + sio_data->sio_outb(sio_data, NCT6775_REG_CR_CASEOPEN_CLR[nr], reg); + reg &= ~NCT6775_CR_CASEOPEN_CLR_MASK[nr]; + sio_data->sio_outb(sio_data, NCT6775_REG_CR_CASEOPEN_CLR[nr], reg); + sio_data->sio_exit(sio_data); + + data->valid = false; /* Force cache refresh */ +error: + mutex_unlock(&data->update_lock); + return count; +} + +static SENSOR_DEVICE_ATTR(intrusion0_alarm, 0644, nct6775_show_alarm, + clear_caseopen, INTRUSION_ALARM_BASE); +static SENSOR_DEVICE_ATTR(intrusion1_alarm, 0644, nct6775_show_alarm, + clear_caseopen, INTRUSION_ALARM_BASE + 1); +static SENSOR_DEVICE_ATTR(intrusion0_beep, 0644, nct6775_show_beep, + nct6775_store_beep, INTRUSION_ALARM_BASE); +static SENSOR_DEVICE_ATTR(intrusion1_beep, 0644, nct6775_show_beep, + nct6775_store_beep, INTRUSION_ALARM_BASE + 1); +static SENSOR_DEVICE_ATTR(beep_enable, 0644, nct6775_show_beep, + nct6775_store_beep, BEEP_ENABLE_BASE); + +static umode_t nct6775_other_is_visible(struct kobject *kobj, + struct attribute *attr, int index) +{ + struct device *dev = kobj_to_dev(kobj); + struct nct6775_data *data = dev_get_drvdata(dev); + + if (index == 0 && !data->have_vid) + return 0; + + if (index == 1 || index == 2) { + if (data->ALARM_BITS[INTRUSION_ALARM_BASE + index - 1] < 0) + return 0; + } + + if (index == 3 || index == 4) { + if (data->BEEP_BITS[INTRUSION_ALARM_BASE + index - 3] < 0) + return 0; + } + + return nct6775_attr_mode(data, attr); +} + +/* + * nct6775_other_is_visible uses the index into the following array + * to determine if attributes should be created or not. + * Any change in order or content must be matched. + */ +static struct attribute *nct6775_attributes_other[] = { + &dev_attr_cpu0_vid.attr, /* 0 */ + &sensor_dev_attr_intrusion0_alarm.dev_attr.attr, /* 1 */ + &sensor_dev_attr_intrusion1_alarm.dev_attr.attr, /* 2 */ + &sensor_dev_attr_intrusion0_beep.dev_attr.attr, /* 3 */ + &sensor_dev_attr_intrusion1_beep.dev_attr.attr, /* 4 */ + &sensor_dev_attr_beep_enable.dev_attr.attr, /* 5 */ + + NULL +}; + +static const struct attribute_group nct6775_group_other = { + .attrs = nct6775_attributes_other, + .is_visible = nct6775_other_is_visible, +}; + +static int nct6775_platform_probe_init(struct nct6775_data *data) +{ + int err; + u8 cr2a; + struct nct6775_sio_data *sio_data = data->driver_data; + + err = sio_data->sio_enter(sio_data); + if (err) + return err; + + cr2a = sio_data->sio_inb(sio_data, 0x2a); + switch (data->kind) { + case nct6775: + data->have_vid = (cr2a & 0x40); + break; + case nct6776: + data->have_vid = (cr2a & 0x60) == 0x40; + break; + case nct6106: + case nct6116: + case nct6779: + case nct6791: + case nct6792: + case nct6793: + case nct6795: + case nct6796: + case nct6797: + case nct6798: + break; + } + + /* + * Read VID value + * We can get the VID input values directly at logical device D 0xe3. + */ + if (data->have_vid) { + sio_data->sio_select(sio_data, NCT6775_LD_VID); + data->vid = sio_data->sio_inb(sio_data, 0xe3); + data->vrm = vid_which_vrm(); + } + + if (fan_debounce) { + u8 tmp; + + sio_data->sio_select(sio_data, NCT6775_LD_HWM); + tmp = sio_data->sio_inb(sio_data, + NCT6775_REG_CR_FAN_DEBOUNCE); + switch (data->kind) { + case nct6106: + case nct6116: + tmp |= 0xe0; + break; + case nct6775: + tmp |= 0x1e; + break; + case nct6776: + case nct6779: + tmp |= 0x3e; + break; + case nct6791: + case nct6792: + case nct6793: + case nct6795: + case nct6796: + case nct6797: + case nct6798: + tmp |= 0x7e; + break; + } + sio_data->sio_outb(sio_data, NCT6775_REG_CR_FAN_DEBOUNCE, + tmp); + pr_info("Enabled fan debounce for chip %s\n", data->name); + } + + nct6775_check_fan_inputs(data, sio_data); + + sio_data->sio_exit(sio_data); + + return nct6775_add_attr_group(data, &nct6775_group_other); +} + +static const struct regmap_config nct6775_regmap_config = { + .reg_bits = 16, + .val_bits = 16, + .reg_read = nct6775_reg_read, + .reg_write = nct6775_reg_write, +}; + +static const struct regmap_config nct6775_wmi_regmap_config = { + .reg_bits = 16, + .val_bits = 16, + .reg_read = nct6775_wmi_reg_read, + .reg_write = nct6775_wmi_reg_write, +}; + +static int nct6775_platform_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct nct6775_sio_data *sio_data = dev_get_platdata(dev); + struct nct6775_data *data; + struct resource *res; + const struct regmap_config *regmapcfg; + + if (sio_data->access == access_direct) { + res = platform_get_resource(pdev, IORESOURCE_IO, 0); + if (!devm_request_region(&pdev->dev, res->start, IOREGION_LENGTH, DRVNAME)) + return -EBUSY; + } + + data = devm_kzalloc(&pdev->dev, sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; + + data->kind = sio_data->kind; + data->sioreg = sio_data->sioreg; + + if (sio_data->access == access_direct) { + data->addr = res->start; + regmapcfg = &nct6775_regmap_config; + } else { + regmapcfg = &nct6775_wmi_regmap_config; + } + + platform_set_drvdata(pdev, data); + + data->driver_data = sio_data; + data->driver_init = nct6775_platform_probe_init; + + return nct6775_probe(&pdev->dev, data, regmapcfg); +} + +static struct platform_driver nct6775_driver = { + .driver = { + .name = DRVNAME, + .pm = &nct6775_dev_pm_ops, + }, + .probe = nct6775_platform_probe, +}; + +/* nct6775_find() looks for a '627 in the Super-I/O config space */ +static int __init nct6775_find(int sioaddr, struct nct6775_sio_data *sio_data) +{ + u16 val; + int err; + int addr; + + sio_data->access = access_direct; + sio_data->sioreg = sioaddr; + + err = sio_data->sio_enter(sio_data); + if (err) + return err; + + val = (sio_data->sio_inb(sio_data, SIO_REG_DEVID) << 8) | + sio_data->sio_inb(sio_data, SIO_REG_DEVID + 1); + if (force_id && val != 0xffff) + val = force_id; + + switch (val & SIO_ID_MASK) { + case SIO_NCT6106_ID: + sio_data->kind = nct6106; + break; + case SIO_NCT6116_ID: + sio_data->kind = nct6116; + break; + case SIO_NCT6775_ID: + sio_data->kind = nct6775; + break; + case SIO_NCT6776_ID: + sio_data->kind = nct6776; + break; + case SIO_NCT6779_ID: + sio_data->kind = nct6779; + break; + case SIO_NCT6791_ID: + sio_data->kind = nct6791; + break; + case SIO_NCT6792_ID: + sio_data->kind = nct6792; + break; + case SIO_NCT6793_ID: + sio_data->kind = nct6793; + break; + case SIO_NCT6795_ID: + sio_data->kind = nct6795; + break; + case SIO_NCT6796_ID: + sio_data->kind = nct6796; + break; + case SIO_NCT6797_ID: + sio_data->kind = nct6797; + break; + case SIO_NCT6798_ID: + sio_data->kind = nct6798; + break; + default: + if (val != 0xffff) + pr_debug("unsupported chip ID: 0x%04x\n", val); + sio_data->sio_exit(sio_data); + return -ENODEV; + } + + /* We have a known chip, find the HWM I/O address */ + sio_data->sio_select(sio_data, NCT6775_LD_HWM); + val = (sio_data->sio_inb(sio_data, SIO_REG_ADDR) << 8) + | sio_data->sio_inb(sio_data, SIO_REG_ADDR + 1); + addr = val & IOREGION_ALIGNMENT; + if (addr == 0) { + pr_err("Refusing to enable a Super-I/O device with a base I/O port 0\n"); + sio_data->sio_exit(sio_data); + return -ENODEV; + } + + /* Activate logical device if needed */ + val = sio_data->sio_inb(sio_data, SIO_REG_ENABLE); + if (!(val & 0x01)) { + pr_warn("Forcibly enabling Super-I/O. Sensor is probably unusable.\n"); + sio_data->sio_outb(sio_data, SIO_REG_ENABLE, val | 0x01); + } + + if (sio_data->kind == nct6791 || sio_data->kind == nct6792 || + sio_data->kind == nct6793 || sio_data->kind == nct6795 || + sio_data->kind == nct6796 || sio_data->kind == nct6797 || + sio_data->kind == nct6798) + nct6791_enable_io_mapping(sio_data); + + sio_data->sio_exit(sio_data); + pr_info("Found %s or compatible chip at %#x:%#x\n", + nct6775_sio_names[sio_data->kind], sioaddr, addr); + + return addr; +} + +/* + * when Super-I/O functions move to a separate file, the Super-I/O + * bus will manage the lifetime of the device and this module will only keep + * track of the nct6775 driver. But since we use platform_device_alloc(), we + * must keep track of the device + */ +static struct platform_device *pdev[2]; + +static const char * const asus_wmi_boards[] = { + "PRO H410T", + "ProArt X570-CREATOR WIFI", + "Pro B550M-C", + "Pro WS X570-ACE", + "PRIME B360-PLUS", + "PRIME B460-PLUS", + "PRIME B550-PLUS", + "PRIME B550M-A", + "PRIME B550M-A (WI-FI)", + "PRIME H410M-R", + "PRIME X570-P", + "PRIME X570-PRO", + "ROG CROSSHAIR VIII DARK HERO", + "ROG CROSSHAIR VIII FORMULA", + "ROG CROSSHAIR VIII HERO", + "ROG CROSSHAIR VIII IMPACT", + "ROG STRIX B550-A GAMING", + "ROG STRIX B550-E GAMING", + "ROG STRIX B550-F GAMING", + "ROG STRIX B550-F GAMING (WI-FI)", + "ROG STRIX B550-F GAMING WIFI II", + "ROG STRIX B550-I GAMING", + "ROG STRIX B550-XE GAMING (WI-FI)", + "ROG STRIX X570-E GAMING", + "ROG STRIX X570-E GAMING WIFI II", + "ROG STRIX X570-F GAMING", + "ROG STRIX X570-I GAMING", + "ROG STRIX Z390-E GAMING", + "ROG STRIX Z390-F GAMING", + "ROG STRIX Z390-H GAMING", + "ROG STRIX Z390-I GAMING", + "ROG STRIX Z490-A GAMING", + "ROG STRIX Z490-E GAMING", + "ROG STRIX Z490-F GAMING", + "ROG STRIX Z490-G GAMING", + "ROG STRIX Z490-G GAMING (WI-FI)", + "ROG STRIX Z490-H GAMING", + "ROG STRIX Z490-I GAMING", + "TUF GAMING B550M-PLUS", + "TUF GAMING B550M-PLUS (WI-FI)", + "TUF GAMING B550-PLUS", + "TUF GAMING B550-PRO", + "TUF GAMING X570-PLUS", + "TUF GAMING X570-PLUS (WI-FI)", + "TUF GAMING X570-PRO (WI-FI)", + "TUF GAMING Z490-PLUS", + "TUF GAMING Z490-PLUS (WI-FI)", +}; + +static int __init sensors_nct6775_platform_init(void) +{ + int i, err; + bool found = false; + int address; + struct resource res; + struct nct6775_sio_data sio_data; + int sioaddr[2] = { 0x2e, 0x4e }; + enum sensor_access access = access_direct; + const char *board_vendor, *board_name; + u8 tmp; + + err = platform_driver_register(&nct6775_driver); + if (err) + return err; + + board_vendor = dmi_get_system_info(DMI_BOARD_VENDOR); + board_name = dmi_get_system_info(DMI_BOARD_NAME); + + if (board_name && board_vendor && + !strcmp(board_vendor, "ASUSTeK COMPUTER INC.")) { + err = match_string(asus_wmi_boards, ARRAY_SIZE(asus_wmi_boards), + board_name); + if (err >= 0) { + /* if reading chip id via WMI succeeds, use WMI */ + if (!nct6775_asuswmi_read(0, NCT6775_PORT_CHIPID, &tmp) && tmp) { + pr_info("Using Asus WMI to access %#x chip.\n", tmp); + access = access_asuswmi; + } else { + pr_err("Can't read ChipID by Asus WMI.\n"); + } + } + } + + /* + * initialize sio_data->kind and sio_data->sioreg. + * + * when Super-I/O functions move to a separate file, the Super-I/O + * driver will probe 0x2e and 0x4e and auto-detect the presence of a + * nct6775 hardware monitor, and call probe() + */ + for (i = 0; i < ARRAY_SIZE(pdev); i++) { + sio_data.sio_outb = superio_outb; + sio_data.sio_inb = superio_inb; + sio_data.sio_select = superio_select; + sio_data.sio_enter = superio_enter; + sio_data.sio_exit = superio_exit; + + address = nct6775_find(sioaddr[i], &sio_data); + if (address <= 0) + continue; + + found = true; + + sio_data.access = access; + + if (access == access_asuswmi) { + sio_data.sio_outb = superio_wmi_outb; + sio_data.sio_inb = superio_wmi_inb; + sio_data.sio_select = superio_wmi_select; + sio_data.sio_enter = superio_wmi_enter; + sio_data.sio_exit = superio_wmi_exit; + } + + pdev[i] = platform_device_alloc(DRVNAME, address); + if (!pdev[i]) { + err = -ENOMEM; + goto exit_device_unregister; + } + + err = platform_device_add_data(pdev[i], &sio_data, + sizeof(struct nct6775_sio_data)); + if (err) + goto exit_device_put; + + if (sio_data.access == access_direct) { + memset(&res, 0, sizeof(res)); + res.name = DRVNAME; + res.start = address + IOREGION_OFFSET; + res.end = address + IOREGION_OFFSET + IOREGION_LENGTH - 1; + res.flags = IORESOURCE_IO; + + err = acpi_check_resource_conflict(&res); + if (err) { + platform_device_put(pdev[i]); + pdev[i] = NULL; + continue; + } + + err = platform_device_add_resources(pdev[i], &res, 1); + if (err) + goto exit_device_put; + } + + /* platform_device_add calls probe() */ + err = platform_device_add(pdev[i]); + if (err) + goto exit_device_put; + } + if (!found) { + err = -ENODEV; + goto exit_unregister; + } + + return 0; + +exit_device_put: + platform_device_put(pdev[i]); +exit_device_unregister: + while (--i >= 0) { + if (pdev[i]) + platform_device_unregister(pdev[i]); + } +exit_unregister: + platform_driver_unregister(&nct6775_driver); + return err; +} + +static void __exit sensors_nct6775_platform_exit(void) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(pdev); i++) { + if (pdev[i]) + platform_device_unregister(pdev[i]); + } + platform_driver_unregister(&nct6775_driver); +} + +MODULE_AUTHOR("Guenter Roeck <linux@roeck-us.net>"); +MODULE_DESCRIPTION("Platform driver for NCT6775F and compatible chips"); +MODULE_LICENSE("GPL"); +MODULE_IMPORT_NS(HWMON_NCT6775); + +module_init(sensors_nct6775_platform_init); +module_exit(sensors_nct6775_platform_exit); diff --git a/drivers/hwmon/nct6775.h b/drivers/hwmon/nct6775.h new file mode 100644 index 000000000000..93f708148e65 --- /dev/null +++ b/drivers/hwmon/nct6775.h @@ -0,0 +1,252 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef __HWMON_NCT6775_H__ +#define __HWMON_NCT6775_H__ + +#include <linux/types.h> + +enum kinds { nct6106, nct6116, nct6775, nct6776, nct6779, nct6791, nct6792, + nct6793, nct6795, nct6796, nct6797, nct6798 }; +enum pwm_enable { off, manual, thermal_cruise, speed_cruise, sf3, sf4 }; + +#define NUM_TEMP 10 /* Max number of temp attribute sets w/ limits*/ +#define NUM_TEMP_FIXED 6 /* Max number of fixed temp attribute sets */ +#define NUM_TSI_TEMP 8 /* Max number of TSI temp register pairs */ + +#define NUM_REG_ALARM 7 /* Max number of alarm registers */ +#define NUM_REG_BEEP 5 /* Max number of beep registers */ + +#define NUM_FAN 7 + +struct nct6775_data { + int addr; /* IO base of hw monitor block */ + int sioreg; /* SIO register address */ + enum kinds kind; + const char *name; + + const struct attribute_group *groups[7]; + u8 num_groups; + + u16 reg_temp[5][NUM_TEMP]; /* 0=temp, 1=temp_over, 2=temp_hyst, + * 3=temp_crit, 4=temp_lcrit + */ + u8 temp_src[NUM_TEMP]; + u16 reg_temp_config[NUM_TEMP]; + const char * const *temp_label; + u32 temp_mask; + u32 virt_temp_mask; + + u16 REG_CONFIG; + u16 REG_VBAT; + u16 REG_DIODE; + u8 DIODE_MASK; + + const s8 *ALARM_BITS; + const s8 *BEEP_BITS; + + const u16 *REG_VIN; + const u16 *REG_IN_MINMAX[2]; + + const u16 *REG_TARGET; + const u16 *REG_FAN; + const u16 *REG_FAN_MODE; + const u16 *REG_FAN_MIN; + const u16 *REG_FAN_PULSES; + const u16 *FAN_PULSE_SHIFT; + const u16 *REG_FAN_TIME[3]; + + const u16 *REG_TOLERANCE_H; + + const u8 *REG_PWM_MODE; + const u8 *PWM_MODE_MASK; + + const u16 *REG_PWM[7]; /* [0]=pwm, [1]=pwm_start, [2]=pwm_floor, + * [3]=pwm_max, [4]=pwm_step, + * [5]=weight_duty_step, [6]=weight_duty_base + */ + const u16 *REG_PWM_READ; + + const u16 *REG_CRITICAL_PWM_ENABLE; + u8 CRITICAL_PWM_ENABLE_MASK; + const u16 *REG_CRITICAL_PWM; + + const u16 *REG_AUTO_TEMP; + const u16 *REG_AUTO_PWM; + + const u16 *REG_CRITICAL_TEMP; + const u16 *REG_CRITICAL_TEMP_TOLERANCE; + + const u16 *REG_TEMP_SOURCE; /* temp register sources */ + const u16 *REG_TEMP_SEL; + const u16 *REG_WEIGHT_TEMP_SEL; + const u16 *REG_WEIGHT_TEMP[3]; /* 0=base, 1=tolerance, 2=step */ + + const u16 *REG_TEMP_OFFSET; + + const u16 *REG_ALARM; + const u16 *REG_BEEP; + + const u16 *REG_TSI_TEMP; + + unsigned int (*fan_from_reg)(u16 reg, unsigned int divreg); + unsigned int (*fan_from_reg_min)(u16 reg, unsigned int divreg); + + struct mutex update_lock; + bool valid; /* true if following fields are valid */ + unsigned long last_updated; /* In jiffies */ + + /* Register values */ + u8 bank; /* current register bank */ + u8 in_num; /* number of in inputs we have */ + u8 in[15][3]; /* [0]=in, [1]=in_max, [2]=in_min */ + unsigned int rpm[NUM_FAN]; + u16 fan_min[NUM_FAN]; + u8 fan_pulses[NUM_FAN]; + u8 fan_div[NUM_FAN]; + u8 has_pwm; + u8 has_fan; /* some fan inputs can be disabled */ + u8 has_fan_min; /* some fans don't have min register */ + bool has_fan_div; + + u8 num_temp_alarms; /* 2, 3, or 6 */ + u8 num_temp_beeps; /* 2, 3, or 6 */ + u8 temp_fixed_num; /* 3 or 6 */ + u8 temp_type[NUM_TEMP_FIXED]; + s8 temp_offset[NUM_TEMP_FIXED]; + s16 temp[5][NUM_TEMP]; /* 0=temp, 1=temp_over, 2=temp_hyst, + * 3=temp_crit, 4=temp_lcrit + */ + s16 tsi_temp[NUM_TSI_TEMP]; + u64 alarms; + u64 beeps; + + u8 pwm_num; /* number of pwm */ + u8 pwm_mode[NUM_FAN]; /* 0->DC variable voltage, + * 1->PWM variable duty cycle + */ + enum pwm_enable pwm_enable[NUM_FAN]; + /* 0->off + * 1->manual + * 2->thermal cruise mode (also called SmartFan I) + * 3->fan speed cruise mode + * 4->SmartFan III + * 5->enhanced variable thermal cruise (SmartFan IV) + */ + u8 pwm[7][NUM_FAN]; /* [0]=pwm, [1]=pwm_start, [2]=pwm_floor, + * [3]=pwm_max, [4]=pwm_step, + * [5]=weight_duty_step, [6]=weight_duty_base + */ + + u8 target_temp[NUM_FAN]; + u8 target_temp_mask; + u32 target_speed[NUM_FAN]; + u32 target_speed_tolerance[NUM_FAN]; + u8 speed_tolerance_limit; + + u8 temp_tolerance[2][NUM_FAN]; + u8 tolerance_mask; + + u8 fan_time[3][NUM_FAN]; /* 0 = stop_time, 1 = step_up, 2 = step_down */ + + /* Automatic fan speed control registers */ + int auto_pwm_num; + u8 auto_pwm[NUM_FAN][7]; + u8 auto_temp[NUM_FAN][7]; + u8 pwm_temp_sel[NUM_FAN]; + u8 pwm_weight_temp_sel[NUM_FAN]; + u8 weight_temp[3][NUM_FAN]; /* 0->temp_step, 1->temp_step_tol, + * 2->temp_base + */ + + u8 vid; + u8 vrm; + + bool have_vid; + + u16 have_temp; + u16 have_temp_fixed; + u16 have_tsi_temp; + u16 have_in; + + /* Remember extra register values over suspend/resume */ + u8 vbat; + u8 fandiv1; + u8 fandiv2; + u8 sio_reg_enable; + + struct regmap *regmap; + bool read_only; + + /* driver-specific (platform, i2c) initialization hook and data */ + int (*driver_init)(struct nct6775_data *data); + void *driver_data; +}; + +static inline int nct6775_read_value(struct nct6775_data *data, u16 reg, u16 *value) +{ + unsigned int tmp; + int ret = regmap_read(data->regmap, reg, &tmp); + + if (!ret) + *value = tmp; + return ret; +} + +static inline int nct6775_write_value(struct nct6775_data *data, u16 reg, u16 value) +{ + return regmap_write(data->regmap, reg, value); +} + +bool nct6775_reg_is_word_sized(struct nct6775_data *data, u16 reg); +int nct6775_probe(struct device *dev, struct nct6775_data *data, + const struct regmap_config *regmapcfg); + +ssize_t nct6775_show_alarm(struct device *dev, struct device_attribute *attr, char *buf); +ssize_t nct6775_show_beep(struct device *dev, struct device_attribute *attr, char *buf); +ssize_t nct6775_store_beep(struct device *dev, struct device_attribute *attr, const char *buf, + size_t count); + +static inline int nct6775_write_temp(struct nct6775_data *data, u16 reg, u16 value) +{ + if (!nct6775_reg_is_word_sized(data, reg)) + value >>= 8; + return nct6775_write_value(data, reg, value); +} + +static inline umode_t nct6775_attr_mode(struct nct6775_data *data, struct attribute *attr) +{ + return data->read_only ? (attr->mode & ~0222) : attr->mode; +} + +static inline int +nct6775_add_attr_group(struct nct6775_data *data, const struct attribute_group *group) +{ + /* Need to leave a NULL terminator at the end of data->groups */ + if (data->num_groups == ARRAY_SIZE(data->groups) - 1) + return -ENOBUFS; + + data->groups[data->num_groups++] = group; + return 0; +} + +#define NCT6775_REG_BANK 0x4E +#define NCT6775_REG_CONFIG 0x40 + +#define NCT6775_REG_FANDIV1 0x506 +#define NCT6775_REG_FANDIV2 0x507 + +#define NCT6791_REG_HM_IO_SPACE_LOCK_ENABLE 0x28 + +#define FAN_ALARM_BASE 16 +#define TEMP_ALARM_BASE 24 +#define INTRUSION_ALARM_BASE 30 +#define BEEP_ENABLE_BASE 15 + +/* + * Not currently used: + * REG_MAN_ID has the value 0x5ca3 for all supported chips. + * REG_CHIP_ID == 0x88/0xa1/0xc1 depending on chip model. + * REG_MAN_ID is at port 0x4f + * REG_CHIP_ID is at port 0x58 + */ + +#endif /* __HWMON_NCT6775_H__ */ diff --git a/drivers/hwmon/occ/common.c b/drivers/hwmon/occ/common.c index f00cd59f1d19..d78f4bebc718 100644 --- a/drivers/hwmon/occ/common.c +++ b/drivers/hwmon/occ/common.c @@ -1149,44 +1149,75 @@ static void occ_parse_poll_response(struct occ *occ) sizeof(*header), size + sizeof(*header)); } -int occ_setup(struct occ *occ, const char *name) +int occ_active(struct occ *occ, bool active) { - int rc; - - mutex_init(&occ->lock); - occ->groups[0] = &occ->group; + int rc = mutex_lock_interruptible(&occ->lock); - /* no need to lock */ - rc = occ_poll(occ); - if (rc == -ESHUTDOWN) { - dev_info(occ->bus_dev, "host is not ready\n"); - return rc; - } else if (rc < 0) { - dev_err(occ->bus_dev, - "failed to get OCC poll response=%02x: %d\n", - occ->resp.return_status, rc); + if (rc) return rc; - } - occ->next_update = jiffies + OCC_UPDATE_FREQUENCY; - occ_parse_poll_response(occ); + if (active) { + if (occ->active) { + rc = -EALREADY; + goto unlock; + } - rc = occ_setup_sensor_attrs(occ); - if (rc) { - dev_err(occ->bus_dev, "failed to setup sensor attrs: %d\n", - rc); - return rc; - } + occ->error_count = 0; + occ->last_safe = 0; - occ->hwmon = devm_hwmon_device_register_with_groups(occ->bus_dev, name, - occ, occ->groups); - if (IS_ERR(occ->hwmon)) { - rc = PTR_ERR(occ->hwmon); - dev_err(occ->bus_dev, "failed to register hwmon device: %d\n", - rc); - return rc; + rc = occ_poll(occ); + if (rc < 0) { + dev_err(occ->bus_dev, + "failed to get OCC poll response=%02x: %d\n", + occ->resp.return_status, rc); + goto unlock; + } + + occ->active = true; + occ->next_update = jiffies + OCC_UPDATE_FREQUENCY; + occ_parse_poll_response(occ); + + rc = occ_setup_sensor_attrs(occ); + if (rc) { + dev_err(occ->bus_dev, + "failed to setup sensor attrs: %d\n", rc); + goto unlock; + } + + occ->hwmon = hwmon_device_register_with_groups(occ->bus_dev, + "occ", occ, + occ->groups); + if (IS_ERR(occ->hwmon)) { + rc = PTR_ERR(occ->hwmon); + occ->hwmon = NULL; + dev_err(occ->bus_dev, + "failed to register hwmon device: %d\n", rc); + goto unlock; + } + } else { + if (!occ->active) { + rc = -EALREADY; + goto unlock; + } + + if (occ->hwmon) + hwmon_device_unregister(occ->hwmon); + occ->active = false; + occ->hwmon = NULL; } +unlock: + mutex_unlock(&occ->lock); + return rc; +} + +int occ_setup(struct occ *occ) +{ + int rc; + + mutex_init(&occ->lock); + occ->groups[0] = &occ->group; + rc = occ_setup_sysfs(occ); if (rc) dev_err(occ->bus_dev, "failed to setup sysfs: %d\n", rc); @@ -1195,6 +1226,15 @@ int occ_setup(struct occ *occ, const char *name) } EXPORT_SYMBOL_GPL(occ_setup); +void occ_shutdown(struct occ *occ) +{ + occ_shutdown_sysfs(occ); + + if (occ->hwmon) + hwmon_device_unregister(occ->hwmon); +} +EXPORT_SYMBOL_GPL(occ_shutdown); + MODULE_AUTHOR("Eddie James <eajames@linux.ibm.com>"); MODULE_DESCRIPTION("Common OCC hwmon code"); MODULE_LICENSE("GPL"); diff --git a/drivers/hwmon/occ/common.h b/drivers/hwmon/occ/common.h index 2dd4a4d240c0..64d5ec7e169b 100644 --- a/drivers/hwmon/occ/common.h +++ b/drivers/hwmon/occ/common.h @@ -106,6 +106,7 @@ struct occ { struct attribute_group group; const struct attribute_group *groups[2]; + bool active; int error; /* final transfer error after retry */ int last_error; /* latest transfer error */ unsigned int error_count; /* number of xfr errors observed */ @@ -123,9 +124,11 @@ struct occ { u8 prev_mode; }; -int occ_setup(struct occ *occ, const char *name); +int occ_active(struct occ *occ, bool active); +int occ_setup(struct occ *occ); int occ_setup_sysfs(struct occ *occ); void occ_shutdown(struct occ *occ); +void occ_shutdown_sysfs(struct occ *occ); void occ_sysfs_poll_done(struct occ *occ); int occ_update_response(struct occ *occ); diff --git a/drivers/hwmon/occ/p8_i2c.c b/drivers/hwmon/occ/p8_i2c.c index 9e61e1fb5142..da39ea28df31 100644 --- a/drivers/hwmon/occ/p8_i2c.c +++ b/drivers/hwmon/occ/p8_i2c.c @@ -223,7 +223,7 @@ static int p8_i2c_occ_probe(struct i2c_client *client) occ->poll_cmd_data = 0x10; /* P8 OCC poll data */ occ->send_cmd = p8_i2c_occ_send_cmd; - return occ_setup(occ, "p8_occ"); + return occ_setup(occ); } static int p8_i2c_occ_remove(struct i2c_client *client) diff --git a/drivers/hwmon/occ/p9_sbe.c b/drivers/hwmon/occ/p9_sbe.c index 49b13cc01073..42fc7b97bb34 100644 --- a/drivers/hwmon/occ/p9_sbe.c +++ b/drivers/hwmon/occ/p9_sbe.c @@ -145,7 +145,7 @@ static int p9_sbe_occ_probe(struct platform_device *pdev) occ->poll_cmd_data = 0x20; /* P9 OCC poll data */ occ->send_cmd = p9_sbe_occ_send_cmd; - rc = occ_setup(occ, "p9_occ"); + rc = occ_setup(occ); if (rc == -ESHUTDOWN) rc = -ENODEV; /* Host is shutdown, don't spew errors */ diff --git a/drivers/hwmon/occ/sysfs.c b/drivers/hwmon/occ/sysfs.c index b2f788a77746..2317301fc1e9 100644 --- a/drivers/hwmon/occ/sysfs.c +++ b/drivers/hwmon/occ/sysfs.c @@ -6,13 +6,13 @@ #include <linux/export.h> #include <linux/hwmon-sysfs.h> #include <linux/kernel.h> +#include <linux/kstrtox.h> #include <linux/sysfs.h> #include "common.h" /* OCC status register */ #define OCC_STAT_MASTER BIT(7) -#define OCC_STAT_ACTIVE BIT(0) /* OCC extended status register */ #define OCC_EXT_STAT_DVFS_OT BIT(7) @@ -22,6 +22,25 @@ #define OCC_EXT_STAT_DVFS_VDD BIT(3) #define OCC_EXT_STAT_GPU_THROTTLE GENMASK(2, 0) +static ssize_t occ_active_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + int rc; + bool active; + struct occ *occ = dev_get_drvdata(dev); + + rc = kstrtobool(buf, &active); + if (rc) + return rc; + + rc = occ_active(occ, active); + if (rc) + return rc; + + return count; +} + static ssize_t occ_sysfs_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -31,54 +50,64 @@ static ssize_t occ_sysfs_show(struct device *dev, struct occ_poll_response_header *header; struct sensor_device_attribute *sattr = to_sensor_dev_attr(attr); - rc = occ_update_response(occ); - if (rc) - return rc; + if (occ->active) { + rc = occ_update_response(occ); + if (rc) + return rc; - header = (struct occ_poll_response_header *)occ->resp.data; - - switch (sattr->index) { - case 0: - val = !!(header->status & OCC_STAT_MASTER); - break; - case 1: - val = !!(header->status & OCC_STAT_ACTIVE); - break; - case 2: - val = !!(header->ext_status & OCC_EXT_STAT_DVFS_OT); - break; - case 3: - val = !!(header->ext_status & OCC_EXT_STAT_DVFS_POWER); - break; - case 4: - val = !!(header->ext_status & OCC_EXT_STAT_MEM_THROTTLE); - break; - case 5: - val = !!(header->ext_status & OCC_EXT_STAT_QUICK_DROP); - break; - case 6: - val = header->occ_state; - break; - case 7: - if (header->status & OCC_STAT_MASTER) - val = hweight8(header->occs_present); - else + header = (struct occ_poll_response_header *)occ->resp.data; + + switch (sattr->index) { + case 0: + val = !!(header->status & OCC_STAT_MASTER); + break; + case 1: val = 1; - break; - case 8: - val = header->ips_status; - break; - case 9: - val = header->mode; - break; - case 10: - val = !!(header->ext_status & OCC_EXT_STAT_DVFS_VDD); - break; - case 11: - val = header->ext_status & OCC_EXT_STAT_GPU_THROTTLE; - break; - default: - return -EINVAL; + break; + case 2: + val = !!(header->ext_status & OCC_EXT_STAT_DVFS_OT); + break; + case 3: + val = !!(header->ext_status & OCC_EXT_STAT_DVFS_POWER); + break; + case 4: + val = !!(header->ext_status & + OCC_EXT_STAT_MEM_THROTTLE); + break; + case 5: + val = !!(header->ext_status & OCC_EXT_STAT_QUICK_DROP); + break; + case 6: + val = header->occ_state; + break; + case 7: + if (header->status & OCC_STAT_MASTER) + val = hweight8(header->occs_present); + else + val = 1; + break; + case 8: + val = header->ips_status; + break; + case 9: + val = header->mode; + break; + case 10: + val = !!(header->ext_status & OCC_EXT_STAT_DVFS_VDD); + break; + case 11: + val = header->ext_status & OCC_EXT_STAT_GPU_THROTTLE; + break; + default: + return -EINVAL; + } + } else { + if (sattr->index == 1) + val = 0; + else if (sattr->index <= 11) + val = -ENODATA; + else + return -EINVAL; } return sysfs_emit(buf, "%d\n", val); @@ -95,7 +124,8 @@ static ssize_t occ_error_show(struct device *dev, } static SENSOR_DEVICE_ATTR(occ_master, 0444, occ_sysfs_show, NULL, 0); -static SENSOR_DEVICE_ATTR(occ_active, 0444, occ_sysfs_show, NULL, 1); +static SENSOR_DEVICE_ATTR(occ_active, 0644, occ_sysfs_show, occ_active_store, + 1); static SENSOR_DEVICE_ATTR(occ_dvfs_overtemp, 0444, occ_sysfs_show, NULL, 2); static SENSOR_DEVICE_ATTR(occ_dvfs_power, 0444, occ_sysfs_show, NULL, 3); static SENSOR_DEVICE_ATTR(occ_mem_throttle, 0444, occ_sysfs_show, NULL, 4); @@ -139,7 +169,7 @@ void occ_sysfs_poll_done(struct occ *occ) * On the first poll response, we haven't yet created the sysfs * attributes, so don't make any notify calls. */ - if (!occ->hwmon) + if (!occ->active) goto done; if ((header->status & OCC_STAT_MASTER) != @@ -148,12 +178,6 @@ void occ_sysfs_poll_done(struct occ *occ) sysfs_notify(&occ->bus_dev->kobj, NULL, name); } - if ((header->status & OCC_STAT_ACTIVE) != - (occ->prev_stat & OCC_STAT_ACTIVE)) { - name = sensor_dev_attr_occ_active.dev_attr.attr.name; - sysfs_notify(&occ->bus_dev->kobj, NULL, name); - } - if ((header->ext_status & OCC_EXT_STAT_DVFS_OT) != (occ->prev_ext_stat & OCC_EXT_STAT_DVFS_OT)) { name = sensor_dev_attr_occ_dvfs_overtemp.dev_attr.attr.name; @@ -227,8 +251,7 @@ int occ_setup_sysfs(struct occ *occ) return sysfs_create_group(&occ->bus_dev->kobj, &occ_sysfs); } -void occ_shutdown(struct occ *occ) +void occ_shutdown_sysfs(struct occ *occ) { sysfs_remove_group(&occ->bus_dev->kobj, &occ_sysfs); } -EXPORT_SYMBOL_GPL(occ_shutdown); diff --git a/drivers/hwmon/peci/cputemp.c b/drivers/hwmon/peci/cputemp.c index 12156328f5cf..57470fda5f6c 100644 --- a/drivers/hwmon/peci/cputemp.c +++ b/drivers/hwmon/peci/cputemp.c @@ -447,29 +447,23 @@ static const struct hwmon_ops peci_cputemp_ops = { .read = cputemp_read, }; -static const u32 peci_cputemp_temp_channel_config[] = { - /* Die temperature */ - HWMON_T_LABEL | HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_CRIT | HWMON_T_CRIT_HYST, - /* DTS margin */ - HWMON_T_LABEL | HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_CRIT | HWMON_T_CRIT_HYST, - /* Tcontrol temperature */ - HWMON_T_LABEL | HWMON_T_INPUT | HWMON_T_CRIT, - /* Tthrottle temperature */ - HWMON_T_LABEL | HWMON_T_INPUT, - /* Tjmax temperature */ - HWMON_T_LABEL | HWMON_T_INPUT, - /* Core temperature - for all core channels */ - [channel_core ... CPUTEMP_CHANNEL_NUMS - 1] = HWMON_T_LABEL | HWMON_T_INPUT, - 0 -}; - -static const struct hwmon_channel_info peci_cputemp_temp_channel = { - .type = hwmon_temp, - .config = peci_cputemp_temp_channel_config, -}; - static const struct hwmon_channel_info *peci_cputemp_info[] = { - &peci_cputemp_temp_channel, + HWMON_CHANNEL_INFO(temp, + /* Die temperature */ + HWMON_T_LABEL | HWMON_T_INPUT | HWMON_T_MAX | + HWMON_T_CRIT | HWMON_T_CRIT_HYST, + /* DTS margin */ + HWMON_T_LABEL | HWMON_T_INPUT | HWMON_T_MAX | + HWMON_T_CRIT | HWMON_T_CRIT_HYST, + /* Tcontrol temperature */ + HWMON_T_LABEL | HWMON_T_INPUT | HWMON_T_CRIT, + /* Tthrottle temperature */ + HWMON_T_LABEL | HWMON_T_INPUT, + /* Tjmax temperature */ + HWMON_T_LABEL | HWMON_T_INPUT, + /* Core temperature - for all core channels */ + [channel_core ... CPUTEMP_CHANNEL_NUMS - 1] = + HWMON_T_LABEL | HWMON_T_INPUT), NULL }; diff --git a/drivers/hwmon/peci/dimmtemp.c b/drivers/hwmon/peci/dimmtemp.c index c8222354c005..0a633bda3668 100644 --- a/drivers/hwmon/peci/dimmtemp.c +++ b/drivers/hwmon/peci/dimmtemp.c @@ -4,6 +4,7 @@ #include <linux/auxiliary_bus.h> #include <linux/bitfield.h> #include <linux/bitops.h> +#include <linux/devm-helpers.h> #include <linux/hwmon.h> #include <linux/jiffies.h> #include <linux/module.h> @@ -219,7 +220,7 @@ static int check_populated_dimms(struct peci_dimmtemp *priv) int chan_rank_max = priv->gen_info->chan_rank_max; int dimm_idx_max = priv->gen_info->dimm_idx_max; u32 chan_rank_empty = 0; - u64 dimm_mask = 0; + u32 dimm_mask = 0; int chan_rank, dimm_idx, ret; u32 pcs; @@ -278,9 +279,9 @@ static int check_populated_dimms(struct peci_dimmtemp *priv) return -EAGAIN; } - dev_dbg(priv->dev, "Scanned populated DIMMs: %#llx\n", dimm_mask); + dev_dbg(priv->dev, "Scanned populated DIMMs: %#x\n", dimm_mask); - bitmap_from_u64(priv->dimm_mask, dimm_mask); + bitmap_from_arr32(priv->dimm_mask, &dimm_mask, DIMM_NUMS_MAX); return 0; } @@ -299,18 +300,10 @@ static int create_dimm_temp_label(struct peci_dimmtemp *priv, int chan) return 0; } -static const u32 peci_dimmtemp_temp_channel_config[] = { - [0 ... DIMM_NUMS_MAX - 1] = HWMON_T_LABEL | HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_CRIT, - 0 -}; - -static const struct hwmon_channel_info peci_dimmtemp_temp_channel = { - .type = hwmon_temp, - .config = peci_dimmtemp_temp_channel_config, -}; - static const struct hwmon_channel_info *peci_dimmtemp_temp_info[] = { - &peci_dimmtemp_temp_channel, + HWMON_CHANNEL_INFO(temp, + [0 ... DIMM_NUMS_MAX - 1] = HWMON_T_LABEL | + HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_CRIT), NULL }; @@ -378,13 +371,6 @@ static void create_dimm_temp_info_delayed(struct work_struct *work) dev_err(priv->dev, "Failed to populate DIMM temp info\n"); } -static void remove_delayed_work(void *_priv) -{ - struct peci_dimmtemp *priv = _priv; - - cancel_delayed_work_sync(&priv->detect_work); -} - static int peci_dimmtemp_probe(struct auxiliary_device *adev, const struct auxiliary_device_id *id) { struct device *dev = &adev->dev; @@ -415,9 +401,8 @@ static int peci_dimmtemp_probe(struct auxiliary_device *adev, const struct auxil "Unexpected PECI revision %#x, some features may be unavailable\n", peci_dev->info.peci_revision); - INIT_DELAYED_WORK(&priv->detect_work, create_dimm_temp_info_delayed); - - ret = devm_add_action_or_reset(priv->dev, remove_delayed_work, priv); + ret = devm_delayed_work_autocancel(priv->dev, &priv->detect_work, + create_dimm_temp_info_delayed); if (ret) return ret; diff --git a/drivers/hwmon/pmbus/Kconfig b/drivers/hwmon/pmbus/Kconfig index a2ea1d5a8765..dfae76db65ae 100644 --- a/drivers/hwmon/pmbus/Kconfig +++ b/drivers/hwmon/pmbus/Kconfig @@ -228,10 +228,10 @@ config SENSORS_MAX16064 be called max16064. config SENSORS_MAX16601 - tristate "Maxim MAX16508, MAX16601" + tristate "Maxim MAX16508, MAX16601, MAX16602" help If you say yes here you get hardware monitoring support for Maxim - MAX16508 and MAX16601. + MAX16508, MAX16601 and MAX16602. This driver can also be built as a module. If so, the module will be called max16601. @@ -408,6 +408,15 @@ config SENSORS_UCD9200 This driver can also be built as a module. If so, the module will be called ucd9200. +config SENSORS_XDPE152 + tristate "Infineon XDPE152 family" + help + If you say yes here you get hardware monitoring support for Infineon + XDPE15284, XDPE152C4, device. + + This driver can also be built as a module. If so, the module will + be called xdpe152c4. + config SENSORS_XDPE122 tristate "Infineon XDPE122 family" help diff --git a/drivers/hwmon/pmbus/Makefile b/drivers/hwmon/pmbus/Makefile index a4a96ac71de7..4678fba5012c 100644 --- a/drivers/hwmon/pmbus/Makefile +++ b/drivers/hwmon/pmbus/Makefile @@ -43,5 +43,6 @@ obj-$(CONFIG_SENSORS_TPS53679) += tps53679.o obj-$(CONFIG_SENSORS_UCD9000) += ucd9000.o obj-$(CONFIG_SENSORS_UCD9200) += ucd9200.o obj-$(CONFIG_SENSORS_XDPE122) += xdpe12284.o +obj-$(CONFIG_SENSORS_XDPE152) += xdpe152c4.o obj-$(CONFIG_SENSORS_ZL6100) += zl6100.o obj-$(CONFIG_SENSORS_PIM4328) += pim4328.o diff --git a/drivers/hwmon/pmbus/delta-ahe50dc-fan.c b/drivers/hwmon/pmbus/delta-ahe50dc-fan.c index 40dffd9c4cbf..f546f0c12497 100644 --- a/drivers/hwmon/pmbus/delta-ahe50dc-fan.c +++ b/drivers/hwmon/pmbus/delta-ahe50dc-fan.c @@ -14,6 +14,21 @@ #define AHE50DC_PMBUS_READ_TEMP4 0xd0 +static int ahe50dc_fan_write_byte(struct i2c_client *client, int page, u8 value) +{ + /* + * The CLEAR_FAULTS operation seems to sometimes (unpredictably, perhaps + * 5% of the time or so) trigger a problematic phenomenon in which the + * fan speeds surge momentarily and at least some (perhaps all?) of the + * system's power outputs experience a glitch. + * + * However, according to Delta it should be OK to simply not send any + * CLEAR_FAULTS commands (the device doesn't seem to be capable of + * reporting any faults anyway), so just blackhole them unconditionally. + */ + return value == PMBUS_CLEAR_FAULTS ? -EOPNOTSUPP : -ENODATA; +} + static int ahe50dc_fan_read_word_data(struct i2c_client *client, int page, int phase, int reg) { /* temp1 in (virtual) page 1 is remapped to mfr-specific temp4 */ @@ -68,6 +83,7 @@ static struct pmbus_driver_info ahe50dc_fan_info = { PMBUS_HAVE_VIN | PMBUS_HAVE_FAN12 | PMBUS_HAVE_FAN34 | PMBUS_HAVE_STATUS_FAN12 | PMBUS_HAVE_STATUS_FAN34 | PMBUS_PAGE_VIRTUAL, .func[1] = PMBUS_HAVE_TEMP | PMBUS_PAGE_VIRTUAL, + .write_byte = ahe50dc_fan_write_byte, .read_word_data = ahe50dc_fan_read_word_data, }; diff --git a/drivers/hwmon/pmbus/ltc2978.c b/drivers/hwmon/pmbus/ltc2978.c index 0127273883f0..531aa674a928 100644 --- a/drivers/hwmon/pmbus/ltc2978.c +++ b/drivers/hwmon/pmbus/ltc2978.c @@ -196,6 +196,17 @@ static int ltc_read_byte_data(struct i2c_client *client, int page, int reg) return pmbus_read_byte_data(client, page, reg); } +static int ltc_write_byte_data(struct i2c_client *client, int page, int reg, u8 value) +{ + int ret; + + ret = ltc_wait_ready(client); + if (ret < 0) + return ret; + + return pmbus_write_byte_data(client, page, reg, value); +} + static int ltc_write_byte(struct i2c_client *client, int page, u8 byte) { int ret; @@ -681,6 +692,7 @@ static int ltc2978_probe(struct i2c_client *client) info = &data->info; info->write_word_data = ltc2978_write_word_data; info->write_byte = ltc_write_byte; + info->write_byte_data = ltc_write_byte_data; info->read_word_data = ltc_read_word_data; info->read_byte_data = ltc_read_byte_data; diff --git a/drivers/hwmon/pmbus/max16601.c b/drivers/hwmon/pmbus/max16601.c index 5a226a564776..b628405e6586 100644 --- a/drivers/hwmon/pmbus/max16601.c +++ b/drivers/hwmon/pmbus/max16601.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* - * Hardware monitoring driver for Maxim MAX16508 and MAX16601. + * Hardware monitoring driver for Maxim MAX16508, MAX16601 and MAX16602. * * Implementation notes: * @@ -31,7 +31,7 @@ #include "pmbus.h" -enum chips { max16508, max16601 }; +enum chips { max16508, max16601, max16602 }; #define REG_DEFAULT_NUM_POP 0xc4 #define REG_SETPT_DVID 0xd1 @@ -202,7 +202,7 @@ static int max16601_identify(struct i2c_client *client, else info->vrm_version[0] = vr12; - if (data->id != max16601) + if (data->id != max16601 && data->id != max16602) return 0; reg = i2c_smbus_read_byte_data(client, REG_DEFAULT_NUM_POP); @@ -264,6 +264,7 @@ static void max16601_remove(void *_data) static const struct i2c_device_id max16601_id[] = { {"max16508", max16508}, {"max16601", max16601}, + {"max16602", max16602}, {} }; MODULE_DEVICE_TABLE(i2c, max16601_id); @@ -280,13 +281,15 @@ static int max16601_get_id(struct i2c_client *client) return -ENODEV; /* - * PMBUS_IC_DEVICE_ID is expected to return "MAX16601y.xx" - * or "MAX16500y.xx". + * PMBUS_IC_DEVICE_ID is expected to return "MAX16601y.xx" or + * MAX16602y.xx or "MAX16500y.xx".cdxxcccccccccc */ if (!strncmp(buf, "MAX16500", 8)) { id = max16508; } else if (!strncmp(buf, "MAX16601", 8)) { id = max16601; + } else if (!strncmp(buf, "MAX16602", 8)) { + id = max16602; } else { buf[ret] = '\0'; dev_err(dev, "Unsupported chip '%s'\n", buf); diff --git a/drivers/hwmon/pmbus/pmbus.h b/drivers/hwmon/pmbus/pmbus.h index e74b6ef070f3..c031a9700ace 100644 --- a/drivers/hwmon/pmbus/pmbus.h +++ b/drivers/hwmon/pmbus/pmbus.h @@ -438,6 +438,8 @@ struct pmbus_driver_info { int (*read_byte_data)(struct i2c_client *client, int page, int reg); int (*read_word_data)(struct i2c_client *client, int page, int phase, int reg); + int (*write_byte_data)(struct i2c_client *client, int page, int reg, + u8 byte); int (*write_word_data)(struct i2c_client *client, int page, int reg, u16 word); int (*write_byte)(struct i2c_client *client, int page, u8 value); diff --git a/drivers/hwmon/pmbus/pmbus_core.c b/drivers/hwmon/pmbus/pmbus_core.c index b2618b1d529e..02912022853d 100644 --- a/drivers/hwmon/pmbus/pmbus_core.c +++ b/drivers/hwmon/pmbus/pmbus_core.c @@ -19,6 +19,8 @@ #include <linux/pmbus.h> #include <linux/regulator/driver.h> #include <linux/regulator/machine.h> +#include <linux/of.h> +#include <linux/thermal.h> #include "pmbus.h" /* @@ -276,6 +278,42 @@ static int _pmbus_write_word_data(struct i2c_client *client, int page, int reg, return pmbus_write_word_data(client, page, reg, word); } +/* + * _pmbus_write_byte_data() is similar to pmbus_write_byte_data(), but checks if + * a device specific mapping function exists and calls it if necessary. + */ +static int _pmbus_write_byte_data(struct i2c_client *client, int page, int reg, u8 value) +{ + struct pmbus_data *data = i2c_get_clientdata(client); + const struct pmbus_driver_info *info = data->info; + int status; + + if (info->write_byte_data) { + status = info->write_byte_data(client, page, reg, value); + if (status != -ENODATA) + return status; + } + return pmbus_write_byte_data(client, page, reg, value); +} + +/* + * _pmbus_read_byte_data() is similar to pmbus_read_byte_data(), but checks if + * a device specific mapping function exists and calls it if necessary. + */ +static int _pmbus_read_byte_data(struct i2c_client *client, int page, int reg) +{ + struct pmbus_data *data = i2c_get_clientdata(client); + const struct pmbus_driver_info *info = data->info; + int status; + + if (info->read_byte_data) { + status = info->read_byte_data(client, page, reg); + if (status != -ENODATA) + return status; + } + return pmbus_read_byte_data(client, page, reg); +} + int pmbus_update_fan(struct i2c_client *client, int page, int id, u8 config, u8 mask, u16 command) { @@ -283,14 +321,14 @@ int pmbus_update_fan(struct i2c_client *client, int page, int id, int rv; u8 to; - from = pmbus_read_byte_data(client, page, + from = _pmbus_read_byte_data(client, page, pmbus_fan_config_registers[id]); if (from < 0) return from; to = (from & ~mask) | (config & mask); if (to != from) { - rv = pmbus_write_byte_data(client, page, + rv = _pmbus_write_byte_data(client, page, pmbus_fan_config_registers[id], to); if (rv < 0) return rv; @@ -390,37 +428,19 @@ int pmbus_update_byte_data(struct i2c_client *client, int page, u8 reg, unsigned int tmp; int rv; - rv = pmbus_read_byte_data(client, page, reg); + rv = _pmbus_read_byte_data(client, page, reg); if (rv < 0) return rv; tmp = (rv & ~mask) | (value & mask); if (tmp != rv) - rv = pmbus_write_byte_data(client, page, reg, tmp); + rv = _pmbus_write_byte_data(client, page, reg, tmp); return rv; } EXPORT_SYMBOL_NS_GPL(pmbus_update_byte_data, PMBUS); -/* - * _pmbus_read_byte_data() is similar to pmbus_read_byte_data(), but checks if - * a device specific mapping function exists and calls it if necessary. - */ -static int _pmbus_read_byte_data(struct i2c_client *client, int page, int reg) -{ - struct pmbus_data *data = i2c_get_clientdata(client); - const struct pmbus_driver_info *info = data->info; - int status; - - if (info->read_byte_data) { - status = info->read_byte_data(client, page, reg); - if (status != -ENODATA) - return status; - } - return pmbus_read_byte_data(client, page, reg); -} - static struct pmbus_sensor *pmbus_find_sensor(struct pmbus_data *data, int page, int reg) { @@ -455,7 +475,7 @@ static int pmbus_get_fan_rate(struct i2c_client *client, int page, int id, return s->data; } - config = pmbus_read_byte_data(client, page, + config = _pmbus_read_byte_data(client, page, pmbus_fan_config_registers[id]); if (config < 0) return config; @@ -912,7 +932,7 @@ static int pmbus_get_boolean(struct i2c_client *client, struct pmbus_boolean *b, regval = status & mask; if (regval) { - ret = pmbus_write_byte_data(client, page, reg, regval); + ret = _pmbus_write_byte_data(client, page, reg, regval); if (ret) goto unlock; } @@ -1083,6 +1103,68 @@ static int pmbus_add_boolean(struct pmbus_data *data, return pmbus_add_attribute(data, &a->dev_attr.attr); } +/* of thermal for pmbus temperature sensors */ +struct pmbus_thermal_data { + struct pmbus_data *pmbus_data; + struct pmbus_sensor *sensor; +}; + +static int pmbus_thermal_get_temp(void *data, int *temp) +{ + struct pmbus_thermal_data *tdata = data; + struct pmbus_sensor *sensor = tdata->sensor; + struct pmbus_data *pmbus_data = tdata->pmbus_data; + struct i2c_client *client = to_i2c_client(pmbus_data->dev); + struct device *dev = pmbus_data->hwmon_dev; + int ret = 0; + + if (!dev) { + /* May not even get to hwmon yet */ + *temp = 0; + return 0; + } + + mutex_lock(&pmbus_data->update_lock); + pmbus_update_sensor_data(client, sensor); + if (sensor->data < 0) + ret = sensor->data; + else + *temp = (int)pmbus_reg2data(pmbus_data, sensor); + mutex_unlock(&pmbus_data->update_lock); + + return ret; +} + +static const struct thermal_zone_of_device_ops pmbus_thermal_ops = { + .get_temp = pmbus_thermal_get_temp, +}; + +static int pmbus_thermal_add_sensor(struct pmbus_data *pmbus_data, + struct pmbus_sensor *sensor, int index) +{ + struct device *dev = pmbus_data->dev; + struct pmbus_thermal_data *tdata; + struct thermal_zone_device *tzd; + + tdata = devm_kzalloc(dev, sizeof(*tdata), GFP_KERNEL); + if (!tdata) + return -ENOMEM; + + tdata->sensor = sensor; + tdata->pmbus_data = pmbus_data; + + tzd = devm_thermal_zone_of_sensor_register(dev, index, tdata, + &pmbus_thermal_ops); + /* + * If CONFIG_THERMAL_OF is disabled, this returns -ENODEV, + * so ignore that error but forward any other error. + */ + if (IS_ERR(tzd) && (PTR_ERR(tzd) != -ENODEV)) + return PTR_ERR(tzd); + + return 0; +} + static struct pmbus_sensor *pmbus_add_sensor(struct pmbus_data *data, const char *name, const char *type, int seq, int page, int phase, @@ -1126,6 +1208,10 @@ static struct pmbus_sensor *pmbus_add_sensor(struct pmbus_data *data, sensor->next = data->sensors; data->sensors = sensor; + /* temperature sensors with _input values are registered with thermal */ + if (class == PSC_TEMPERATURE && strcmp(type, "input") == 0) + pmbus_thermal_add_sensor(data, sensor, seq); + return sensor; } @@ -2309,6 +2395,21 @@ static int pmbus_init_common(struct i2c_client *client, struct pmbus_data *data, int page, ret; /* + * Figure out if PEC is enabled before accessing any other register. + * Make sure PEC is disabled, will be enabled later if needed. + */ + client->flags &= ~I2C_CLIENT_PEC; + + /* Enable PEC if the controller and bus supports it */ + if (!(data->flags & PMBUS_NO_CAPABILITY)) { + ret = i2c_smbus_read_byte_data(client, PMBUS_CAPABILITY); + if (ret >= 0 && (ret & PB_CAPABILITY_ERROR_CHECK)) { + if (i2c_check_functionality(client->adapter, I2C_FUNC_SMBUS_PEC)) + client->flags |= I2C_CLIENT_PEC; + } + } + + /* * Some PMBus chips don't support PMBUS_STATUS_WORD, so try * to use PMBUS_STATUS_BYTE instead if that is the case. * Bail out if both registers are not supported. @@ -2326,16 +2427,6 @@ static int pmbus_init_common(struct i2c_client *client, struct pmbus_data *data, data->has_status_word = true; } - /* Enable PEC if the controller and bus supports it */ - if (!(data->flags & PMBUS_NO_CAPABILITY)) { - ret = i2c_smbus_read_byte_data(client, PMBUS_CAPABILITY); - if (ret >= 0 && (ret & PB_CAPABILITY_ERROR_CHECK)) { - if (i2c_check_functionality(client->adapter, I2C_FUNC_SMBUS_PEC)) { - client->flags |= I2C_CLIENT_PEC; - } - } - } - /* * Check if the chip is write protected. If it is, we can not clear * faults, and we should not try it. Also, in that case, writes into @@ -2396,7 +2487,7 @@ static int pmbus_regulator_is_enabled(struct regulator_dev *rdev) int ret; mutex_lock(&data->update_lock); - ret = pmbus_read_byte_data(client, page, PMBUS_OPERATION); + ret = _pmbus_read_byte_data(client, page, PMBUS_OPERATION); mutex_unlock(&data->update_lock); if (ret < 0) @@ -2495,7 +2586,7 @@ static int pmbus_regulator_get_error_flags(struct regulator_dev *rdev, unsigned if (!(func & cat->func)) continue; - status = pmbus_read_byte_data(client, page, cat->reg); + status = _pmbus_read_byte_data(client, page, cat->reg); if (status < 0) { mutex_unlock(&data->update_lock); return status; @@ -2545,11 +2636,78 @@ static int pmbus_regulator_get_error_flags(struct regulator_dev *rdev, unsigned return 0; } +static int pmbus_regulator_get_voltage(struct regulator_dev *rdev) +{ + struct device *dev = rdev_get_dev(rdev); + struct i2c_client *client = to_i2c_client(dev->parent); + struct pmbus_data *data = i2c_get_clientdata(client); + struct pmbus_sensor s = { + .page = rdev_get_id(rdev), + .class = PSC_VOLTAGE_OUT, + .convert = true, + }; + + s.data = _pmbus_read_word_data(client, s.page, 0xff, PMBUS_READ_VOUT); + if (s.data < 0) + return s.data; + + return (int)pmbus_reg2data(data, &s) * 1000; /* unit is uV */ +} + +static int pmbus_regulator_set_voltage(struct regulator_dev *rdev, int min_uv, + int max_uv, unsigned int *selector) +{ + struct device *dev = rdev_get_dev(rdev); + struct i2c_client *client = to_i2c_client(dev->parent); + struct pmbus_data *data = i2c_get_clientdata(client); + struct pmbus_sensor s = { + .page = rdev_get_id(rdev), + .class = PSC_VOLTAGE_OUT, + .convert = true, + .data = -1, + }; + int val = DIV_ROUND_CLOSEST(min_uv, 1000); /* convert to mV */ + int low, high; + + *selector = 0; + + if (pmbus_check_word_register(client, s.page, PMBUS_MFR_VOUT_MIN)) + s.data = _pmbus_read_word_data(client, s.page, 0xff, PMBUS_MFR_VOUT_MIN); + if (s.data < 0) { + s.data = _pmbus_read_word_data(client, s.page, 0xff, PMBUS_VOUT_MARGIN_LOW); + if (s.data < 0) + return s.data; + } + low = pmbus_reg2data(data, &s); + + s.data = -1; + if (pmbus_check_word_register(client, s.page, PMBUS_MFR_VOUT_MAX)) + s.data = _pmbus_read_word_data(client, s.page, 0xff, PMBUS_MFR_VOUT_MAX); + if (s.data < 0) { + s.data = _pmbus_read_word_data(client, s.page, 0xff, PMBUS_VOUT_MARGIN_HIGH); + if (s.data < 0) + return s.data; + } + high = pmbus_reg2data(data, &s); + + /* Make sure we are within margins */ + if (low > val) + val = low; + if (high < val) + val = high; + + val = pmbus_data2reg(data, &s, val); + + return _pmbus_write_word_data(client, s.page, PMBUS_VOUT_COMMAND, (u16)val); +} + const struct regulator_ops pmbus_regulator_ops = { .enable = pmbus_regulator_enable, .disable = pmbus_regulator_disable, .is_enabled = pmbus_regulator_is_enabled, .get_error_flags = pmbus_regulator_get_error_flags, + .get_voltage = pmbus_regulator_get_voltage, + .set_voltage = pmbus_regulator_set_voltage, }; EXPORT_SYMBOL_NS_GPL(pmbus_regulator_ops, PMBUS); diff --git a/drivers/hwmon/pmbus/xdpe12284.c b/drivers/hwmon/pmbus/xdpe12284.c index 18fffc5d749b..32bc7736d609 100644 --- a/drivers/hwmon/pmbus/xdpe12284.c +++ b/drivers/hwmon/pmbus/xdpe12284.c @@ -124,7 +124,7 @@ static int xdpe122_identify(struct i2c_client *client, return 0; } -static const struct regulator_desc xdpe122_reg_desc[] = { +static const struct regulator_desc __maybe_unused xdpe122_reg_desc[] = { PMBUS_REGULATOR("vout", 0), PMBUS_REGULATOR("vout", 1), }; diff --git a/drivers/hwmon/pmbus/xdpe152c4.c b/drivers/hwmon/pmbus/xdpe152c4.c new file mode 100644 index 000000000000..b8a36ef73e45 --- /dev/null +++ b/drivers/hwmon/pmbus/xdpe152c4.c @@ -0,0 +1,75 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Hardware monitoring driver for Infineon Multi-phase Digital VR Controllers + * + * Copyright (c) 2022 Infineon Technologies. All rights reserved. + */ + +#include <linux/err.h> +#include <linux/i2c.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include "pmbus.h" + +#define XDPE152_PAGE_NUM 2 + +static struct pmbus_driver_info xdpe152_info = { + .pages = XDPE152_PAGE_NUM, + .format[PSC_VOLTAGE_IN] = linear, + .format[PSC_VOLTAGE_OUT] = linear, + .format[PSC_TEMPERATURE] = linear, + .format[PSC_CURRENT_IN] = linear, + .format[PSC_CURRENT_OUT] = linear, + .format[PSC_POWER] = linear, + .func[0] = PMBUS_HAVE_VIN | PMBUS_HAVE_VOUT | PMBUS_HAVE_STATUS_VOUT | + PMBUS_HAVE_IIN | PMBUS_HAVE_IOUT | PMBUS_HAVE_STATUS_IOUT | + PMBUS_HAVE_TEMP | PMBUS_HAVE_TEMP2 | PMBUS_HAVE_STATUS_TEMP | + PMBUS_HAVE_POUT | PMBUS_HAVE_PIN | PMBUS_HAVE_STATUS_INPUT, + .func[1] = PMBUS_HAVE_VIN | PMBUS_HAVE_VOUT | PMBUS_HAVE_STATUS_VOUT | + PMBUS_HAVE_IIN | PMBUS_HAVE_IOUT | PMBUS_HAVE_STATUS_IOUT | + PMBUS_HAVE_POUT | PMBUS_HAVE_PIN | PMBUS_HAVE_STATUS_INPUT, +}; + +static int xdpe152_probe(struct i2c_client *client) +{ + struct pmbus_driver_info *info; + + info = devm_kmemdup(&client->dev, &xdpe152_info, sizeof(*info), + GFP_KERNEL); + if (!info) + return -ENOMEM; + + return pmbus_do_probe(client, info); +} + +static const struct i2c_device_id xdpe152_id[] = { + {"xdpe152c4", 0}, + {"xdpe15284", 0}, + {} +}; + +MODULE_DEVICE_TABLE(i2c, xdpe152_id); + +static const struct of_device_id __maybe_unused xdpe152_of_match[] = { + {.compatible = "infineon,xdpe152c4"}, + {.compatible = "infineon,xdpe15284"}, + {} +}; +MODULE_DEVICE_TABLE(of, xdpe152_of_match); + +static struct i2c_driver xdpe152_driver = { + .driver = { + .name = "xdpe152c4", + .of_match_table = of_match_ptr(xdpe152_of_match), + }, + .probe_new = xdpe152_probe, + .id_table = xdpe152_id, +}; + +module_i2c_driver(xdpe152_driver); + +MODULE_AUTHOR("Greg Schwendimann <greg.schwendimann@infineon.com>"); +MODULE_DESCRIPTION("PMBus driver for Infineon XDPE152 family"); +MODULE_LICENSE("GPL"); +MODULE_IMPORT_NS(PMBUS); diff --git a/drivers/hwmon/pwm-fan.c b/drivers/hwmon/pwm-fan.c index f12b9a28a232..6c08551d8d14 100644 --- a/drivers/hwmon/pwm-fan.c +++ b/drivers/hwmon/pwm-fan.c @@ -49,16 +49,6 @@ struct pwm_fan_ctx { struct hwmon_channel_info fan_channel; }; -static const u32 pwm_fan_channel_config_pwm[] = { - HWMON_PWM_INPUT, - 0 -}; - -static const struct hwmon_channel_info pwm_fan_channel_pwm = { - .type = hwmon_pwm, - .config = pwm_fan_channel_config_pwm, -}; - /* This handler assumes self resetting edge triggered interrupt. */ static irqreturn_t pulse_handler(int irq, void *dev_id) { @@ -387,7 +377,7 @@ static int pwm_fan_probe(struct platform_device *pdev) if (!channels) return -ENOMEM; - channels[0] = &pwm_fan_channel_pwm; + channels[0] = HWMON_CHANNEL_INFO(pwm, HWMON_PWM_INPUT); for (i = 0; i < ctx->tach_count; i++) { struct pwm_fan_tach *tach = &ctx->tachs[i]; diff --git a/drivers/hwmon/sl28cpld-hwmon.c b/drivers/hwmon/sl28cpld-hwmon.c index e48f58ec5b9c..9ce4899a81a5 100644 --- a/drivers/hwmon/sl28cpld-hwmon.c +++ b/drivers/hwmon/sl28cpld-hwmon.c @@ -54,7 +54,7 @@ static int sl28cpld_hwmon_read(struct device *dev, /* * The counter period is 1000ms and the sysfs specification - * says we should asssume 2 pulses per revolution. + * says we should assume 2 pulses per revolution. */ value *= 60 / 2; @@ -67,18 +67,8 @@ static int sl28cpld_hwmon_read(struct device *dev, return 0; } -static const u32 sl28cpld_hwmon_fan_config[] = { - HWMON_F_INPUT, - 0 -}; - -static const struct hwmon_channel_info sl28cpld_hwmon_fan = { - .type = hwmon_fan, - .config = sl28cpld_hwmon_fan_config, -}; - static const struct hwmon_channel_info *sl28cpld_hwmon_info[] = { - &sl28cpld_hwmon_fan, + HWMON_CHANNEL_INFO(fan, HWMON_F_INPUT), NULL }; diff --git a/drivers/hwmon/tmp401.c b/drivers/hwmon/tmp401.c index b86d9df7105d..cc0a1c219b1f 100644 --- a/drivers/hwmon/tmp401.c +++ b/drivers/hwmon/tmp401.c @@ -41,6 +41,8 @@ enum chips { tmp401, tmp411, tmp431, tmp432, tmp435 }; #define TMP401_STATUS 0x02 #define TMP401_CONFIG 0x03 #define TMP401_CONVERSION_RATE 0x04 +#define TMP4XX_N_FACTOR_REG 0x18 +#define TMP43X_BETA_RANGE 0x25 #define TMP401_TEMP_CRIT_HYST 0x21 #define TMP401_MANUFACTURER_ID_REG 0xFE #define TMP401_DEVICE_ID_REG 0xFF @@ -543,6 +545,8 @@ static int tmp401_init_client(struct tmp401_data *data) struct regmap *regmap = data->regmap; u32 config, config_orig; int ret; + u32 val = 0; + s32 nfactor = 0; /* Set conversion rate to 2 Hz */ ret = regmap_write(regmap, TMP401_CONVERSION_RATE, 5); @@ -557,12 +561,50 @@ static int tmp401_init_client(struct tmp401_data *data) config_orig = config; config &= ~TMP401_CONFIG_SHUTDOWN; + if (of_property_read_bool(data->client->dev.of_node, "ti,extended-range-enable")) { + /* Enable measurement over extended temperature range */ + config |= TMP401_CONFIG_RANGE; + } + data->extended_range = !!(config & TMP401_CONFIG_RANGE); - if (config != config_orig) + if (config != config_orig) { ret = regmap_write(regmap, TMP401_CONFIG, config); + if (ret < 0) + return ret; + } - return ret; + ret = of_property_read_u32(data->client->dev.of_node, "ti,n-factor", &nfactor); + if (!ret) { + if (data->kind == tmp401) { + dev_err(&data->client->dev, "ti,tmp401 does not support n-factor correction\n"); + return -EINVAL; + } + if (nfactor < -128 || nfactor > 127) { + dev_err(&data->client->dev, "n-factor is invalid (%d)\n", nfactor); + return -EINVAL; + } + ret = regmap_write(regmap, TMP4XX_N_FACTOR_REG, (unsigned int)nfactor); + if (ret < 0) + return ret; + } + + ret = of_property_read_u32(data->client->dev.of_node, "ti,beta-compensation", &val); + if (!ret) { + if (data->kind == tmp401 || data->kind == tmp411) { + dev_err(&data->client->dev, "ti,tmp401 or ti,tmp411 does not support beta compensation\n"); + return -EINVAL; + } + if (val > 15) { + dev_err(&data->client->dev, "beta-compensation is invalid (%u)\n", val); + return -EINVAL; + } + ret = regmap_write(regmap, TMP43X_BETA_RANGE, val); + if (ret < 0) + return ret; + } + + return 0; } static int tmp401_detect(struct i2c_client *client, @@ -708,10 +750,21 @@ static int tmp401_probe(struct i2c_client *client) return 0; } +static const struct of_device_id __maybe_unused tmp4xx_of_match[] = { + { .compatible = "ti,tmp401", }, + { .compatible = "ti,tmp411", }, + { .compatible = "ti,tmp431", }, + { .compatible = "ti,tmp432", }, + { .compatible = "ti,tmp435", }, + { }, +}; +MODULE_DEVICE_TABLE(of, tmp4xx_of_match); + static struct i2c_driver tmp401_driver = { .class = I2C_CLASS_HWMON, .driver = { .name = "tmp401", + .of_match_table = of_match_ptr(tmp4xx_of_match), }, .probe_new = tmp401_probe, .id_table = tmp401_id, diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c index 27f969b3dc07..e9e2db68b9fb 100644 --- a/drivers/i2c/busses/i2c-imx.c +++ b/drivers/i2c/busses/i2c-imx.c @@ -179,6 +179,12 @@ struct imx_i2c_hwdata { unsigned int ndivs; unsigned int i2sr_clr_opcode; unsigned int i2cr_ien_opcode; + /* + * Errata ERR007805 or e7805: + * I2C: When the I2C clock speed is configured for 400 kHz, + * the SCL low period violates the I2C spec of 1.3 uS min. + */ + bool has_err007805; }; struct imx_i2c_dma { @@ -240,6 +246,16 @@ static const struct imx_i2c_hwdata imx21_i2c_hwdata = { }; +static const struct imx_i2c_hwdata imx6_i2c_hwdata = { + .devtype = IMX21_I2C, + .regshift = IMX_I2C_REGSHIFT, + .clk_div = imx_i2c_clk_div, + .ndivs = ARRAY_SIZE(imx_i2c_clk_div), + .i2sr_clr_opcode = I2SR_CLR_OPCODE_W0C, + .i2cr_ien_opcode = I2CR_IEN_OPCODE_1, + .has_err007805 = true, +}; + static struct imx_i2c_hwdata vf610_i2c_hwdata = { .devtype = VF610_I2C, .regshift = VF610_I2C_REGSHIFT, @@ -266,6 +282,16 @@ MODULE_DEVICE_TABLE(platform, imx_i2c_devtype); static const struct of_device_id i2c_imx_dt_ids[] = { { .compatible = "fsl,imx1-i2c", .data = &imx1_i2c_hwdata, }, { .compatible = "fsl,imx21-i2c", .data = &imx21_i2c_hwdata, }, + { .compatible = "fsl,imx6q-i2c", .data = &imx6_i2c_hwdata, }, + { .compatible = "fsl,imx6sl-i2c", .data = &imx6_i2c_hwdata, }, + { .compatible = "fsl,imx6sll-i2c", .data = &imx6_i2c_hwdata, }, + { .compatible = "fsl,imx6sx-i2c", .data = &imx6_i2c_hwdata, }, + { .compatible = "fsl,imx6ul-i2c", .data = &imx6_i2c_hwdata, }, + { .compatible = "fsl,imx7s-i2c", .data = &imx6_i2c_hwdata, }, + { .compatible = "fsl,imx8mm-i2c", .data = &imx6_i2c_hwdata, }, + { .compatible = "fsl,imx8mn-i2c", .data = &imx6_i2c_hwdata, }, + { .compatible = "fsl,imx8mp-i2c", .data = &imx6_i2c_hwdata, }, + { .compatible = "fsl,imx8mq-i2c", .data = &imx6_i2c_hwdata, }, { .compatible = "fsl,vf610-i2c", .data = &vf610_i2c_hwdata, }, { /* sentinel */ } }; @@ -551,6 +577,13 @@ static void i2c_imx_set_clk(struct imx_i2c_struct *i2c_imx, unsigned int div; int i; + if (i2c_imx->hwdata->has_err007805 && i2c_imx->bitrate > 384000) { + dev_dbg(&i2c_imx->adapter.dev, + "SoC errata ERR007805 or e7805 applies, bus frequency limited from %d Hz to 384000 Hz.\n", + i2c_imx->bitrate); + i2c_imx->bitrate = 384000; + } + /* Divider value calculation */ if (i2c_imx->cur_clk == i2c_clk_rate) return; diff --git a/drivers/i2c/busses/i2c-ismt.c b/drivers/i2c/busses/i2c-ismt.c index f4820fd3dc13..c16157ee8c52 100644 --- a/drivers/i2c/busses/i2c-ismt.c +++ b/drivers/i2c/busses/i2c-ismt.c @@ -82,6 +82,7 @@ #define ISMT_DESC_ENTRIES 2 /* number of descriptor entries */ #define ISMT_MAX_RETRIES 3 /* number of SMBus retries to attempt */ +#define ISMT_LOG_ENTRIES 3 /* number of interrupt cause log entries */ /* Hardware Descriptor Constants - Control Field */ #define ISMT_DESC_CWRL 0x01 /* Command/Write Length */ @@ -145,8 +146,8 @@ #define ISMT_SPGT_SPD_MASK 0xc0000000 /* SMBus Speed mask */ #define ISMT_SPGT_SPD_80K 0x00 /* 80 kHz */ #define ISMT_SPGT_SPD_100K (0x1 << 30) /* 100 kHz */ -#define ISMT_SPGT_SPD_400K (0x2 << 30) /* 400 kHz */ -#define ISMT_SPGT_SPD_1M (0x3 << 30) /* 1 MHz */ +#define ISMT_SPGT_SPD_400K (0x2U << 30) /* 400 kHz */ +#define ISMT_SPGT_SPD_1M (0x3U << 30) /* 1 MHz */ /* MSI Control Register (MSICTL) bit definitions */ @@ -175,6 +176,8 @@ struct ismt_priv { u8 head; /* ring buffer head pointer */ struct completion cmp; /* interrupt completion */ u8 buffer[I2C_SMBUS_BLOCK_MAX + 16]; /* temp R/W data buffer */ + dma_addr_t log_dma; + u32 *log; }; static const struct pci_device_id ismt_ids[] = { @@ -411,6 +414,9 @@ static int ismt_access(struct i2c_adapter *adap, u16 addr, memset(desc, 0, sizeof(struct ismt_desc)); desc->tgtaddr_rw = ISMT_DESC_ADDR_RW(addr, read_write); + /* Always clear the log entries */ + memset(priv->log, 0, ISMT_LOG_ENTRIES * sizeof(u32)); + /* Initialize common control bits */ if (likely(pci_dev_msi_enabled(priv->pci_dev))) desc->control = ISMT_DESC_INT | ISMT_DESC_FAIR; @@ -708,6 +714,8 @@ static void ismt_hw_init(struct ismt_priv *priv) /* initialize the Master Descriptor Base Address (MDBA) */ writeq(priv->io_rng_dma, priv->smba + ISMT_MSTR_MDBA); + writeq(priv->log_dma, priv->smba + ISMT_GR_SMTICL); + /* initialize the Master Control Register (MCTRL) */ writel(ISMT_MCTRL_MEIE, priv->smba + ISMT_MSTR_MCTRL); @@ -795,6 +803,12 @@ static int ismt_dev_init(struct ismt_priv *priv) priv->head = 0; init_completion(&priv->cmp); + priv->log = dmam_alloc_coherent(&priv->pci_dev->dev, + ISMT_LOG_ENTRIES * sizeof(u32), + &priv->log_dma, GFP_KERNEL); + if (!priv->log) + return -ENOMEM; + return 0; } diff --git a/drivers/i2c/busses/i2c-mt7621.c b/drivers/i2c/busses/i2c-mt7621.c index 45fe4a7fe0c0..901f0fb04fee 100644 --- a/drivers/i2c/busses/i2c-mt7621.c +++ b/drivers/i2c/busses/i2c-mt7621.c @@ -304,7 +304,8 @@ static int mtk_i2c_probe(struct platform_device *pdev) if (i2c->bus_freq == 0) { dev_warn(i2c->dev, "clock-frequency 0 not supported\n"); - return -EINVAL; + ret = -EINVAL; + goto err_disable_clk; } adap = &i2c->adap; @@ -322,10 +323,15 @@ static int mtk_i2c_probe(struct platform_device *pdev) ret = i2c_add_adapter(adap); if (ret < 0) - return ret; + goto err_disable_clk; dev_info(&pdev->dev, "clock %u kHz\n", i2c->bus_freq / 1000); + return 0; + +err_disable_clk: + clk_disable_unprepare(i2c->clk); + return ret; } diff --git a/drivers/i2c/busses/i2c-pasemi-core.c b/drivers/i2c/busses/i2c-pasemi-core.c index 7728c8460dc0..9028ffb58cc0 100644 --- a/drivers/i2c/busses/i2c-pasemi-core.c +++ b/drivers/i2c/busses/i2c-pasemi-core.c @@ -137,6 +137,12 @@ static int pasemi_i2c_xfer_msg(struct i2c_adapter *adapter, TXFIFO_WR(smbus, msg->buf[msg->len-1] | (stop ? MTXFIFO_STOP : 0)); + + if (stop) { + err = pasemi_smb_waitready(smbus); + if (err) + goto reset_out; + } } return 0; diff --git a/drivers/i2c/busses/i2c-qcom-geni.c b/drivers/i2c/busses/i2c-qcom-geni.c index fc1dcc19f2a1..5b920f0fc7dd 100644 --- a/drivers/i2c/busses/i2c-qcom-geni.c +++ b/drivers/i2c/busses/i2c-qcom-geni.c @@ -843,10 +843,8 @@ static int geni_i2c_probe(struct platform_device *pdev) /* FIFO is disabled, so we can only use GPI DMA */ gi2c->gpi_mode = true; ret = setup_gpi_dma(gi2c); - if (ret) { - dev_err(dev, "Failed to setup GPI DMA mode:%d ret\n", ret); - return ret; - } + if (ret) + return dev_err_probe(dev, ret, "Failed to setup GPI DMA mode\n"); dev_dbg(dev, "Using GPI DMA mode for I2C\n"); } else { diff --git a/drivers/i2c/busses/i2c-thunderx-pcidrv.c b/drivers/i2c/busses/i2c-thunderx-pcidrv.c index 12c90aa0900e..a77cd86fe75e 100644 --- a/drivers/i2c/busses/i2c-thunderx-pcidrv.c +++ b/drivers/i2c/busses/i2c-thunderx-pcidrv.c @@ -213,6 +213,7 @@ static int thunder_i2c_probe_pci(struct pci_dev *pdev, i2c->adap.bus_recovery_info = &octeon_i2c_recovery_info; i2c->adap.dev.parent = dev; i2c->adap.dev.of_node = pdev->dev.of_node; + i2c->adap.dev.fwnode = dev->fwnode; snprintf(i2c->adap.name, sizeof(i2c->adap.name), "Cavium ThunderX i2c adapter at %s", dev_name(dev)); i2c_set_adapdata(&i2c->adap, i2c); diff --git a/drivers/i2c/i2c-dev.c b/drivers/i2c/i2c-dev.c index cf5d049342ea..ab0adaa130da 100644 --- a/drivers/i2c/i2c-dev.c +++ b/drivers/i2c/i2c-dev.c @@ -557,7 +557,7 @@ static long compat_i2cdev_ioctl(struct file *file, unsigned int cmd, unsigned lo .addr = umsg.addr, .flags = umsg.flags, .len = umsg.len, - .buf = compat_ptr(umsg.buf) + .buf = (__force __u8 *)compat_ptr(umsg.buf), }; } @@ -668,16 +668,21 @@ static int i2cdev_attach_adapter(struct device *dev, void *dummy) i2c_dev->dev.class = i2c_dev_class; i2c_dev->dev.parent = &adap->dev; i2c_dev->dev.release = i2cdev_dev_release; - dev_set_name(&i2c_dev->dev, "i2c-%d", adap->nr); + + res = dev_set_name(&i2c_dev->dev, "i2c-%d", adap->nr); + if (res) + goto err_put_i2c_dev; res = cdev_device_add(&i2c_dev->cdev, &i2c_dev->dev); - if (res) { - put_i2c_dev(i2c_dev, false); - return res; - } + if (res) + goto err_put_i2c_dev; pr_debug("adapter [%s] registered as minor %d\n", adap->name, adap->nr); return 0; + +err_put_i2c_dev: + put_i2c_dev(i2c_dev, false); + return res; } static int i2cdev_detach_adapter(struct device *dev, void *dummy) diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c index b7640cfe0020..b9bb94bd0f67 100644 --- a/drivers/idle/intel_idle.c +++ b/drivers/idle/intel_idle.c @@ -69,7 +69,12 @@ static unsigned int preferred_states_mask; static struct cpuidle_device __percpu *intel_idle_cpuidle_devices; static unsigned long auto_demotion_disable_flags; -static bool disable_promotion_to_c1e; + +static enum { + C1E_PROMOTION_PRESERVE, + C1E_PROMOTION_ENABLE, + C1E_PROMOTION_DISABLE +} c1e_promotion = C1E_PROMOTION_PRESERVE; struct idle_cpu { struct cpuidle_state *state_table; @@ -760,6 +765,106 @@ static struct cpuidle_state icx_cstates[] __initdata = { }; /* + * On AlderLake C1 has to be disabled if C1E is enabled, and vice versa. + * C1E is enabled only if "C1E promotion" bit is set in MSR_IA32_POWER_CTL. + * But in this case there is effectively no C1, because C1 requests are + * promoted to C1E. If the "C1E promotion" bit is cleared, then both C1 + * and C1E requests end up with C1, so there is effectively no C1E. + * + * By default we enable C1E and disable C1 by marking it with + * 'CPUIDLE_FLAG_UNUSABLE'. + */ +static struct cpuidle_state adl_cstates[] __initdata = { + { + .name = "C1", + .desc = "MWAIT 0x00", + .flags = MWAIT2flg(0x00) | CPUIDLE_FLAG_UNUSABLE, + .exit_latency = 1, + .target_residency = 1, + .enter = &intel_idle, + .enter_s2idle = intel_idle_s2idle, }, + { + .name = "C1E", + .desc = "MWAIT 0x01", + .flags = MWAIT2flg(0x01) | CPUIDLE_FLAG_ALWAYS_ENABLE, + .exit_latency = 2, + .target_residency = 4, + .enter = &intel_idle, + .enter_s2idle = intel_idle_s2idle, }, + { + .name = "C6", + .desc = "MWAIT 0x20", + .flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED, + .exit_latency = 220, + .target_residency = 600, + .enter = &intel_idle, + .enter_s2idle = intel_idle_s2idle, }, + { + .name = "C8", + .desc = "MWAIT 0x40", + .flags = MWAIT2flg(0x40) | CPUIDLE_FLAG_TLB_FLUSHED, + .exit_latency = 280, + .target_residency = 800, + .enter = &intel_idle, + .enter_s2idle = intel_idle_s2idle, }, + { + .name = "C10", + .desc = "MWAIT 0x60", + .flags = MWAIT2flg(0x60) | CPUIDLE_FLAG_TLB_FLUSHED, + .exit_latency = 680, + .target_residency = 2000, + .enter = &intel_idle, + .enter_s2idle = intel_idle_s2idle, }, + { + .enter = NULL } +}; + +static struct cpuidle_state adl_l_cstates[] __initdata = { + { + .name = "C1", + .desc = "MWAIT 0x00", + .flags = MWAIT2flg(0x00) | CPUIDLE_FLAG_UNUSABLE, + .exit_latency = 1, + .target_residency = 1, + .enter = &intel_idle, + .enter_s2idle = intel_idle_s2idle, }, + { + .name = "C1E", + .desc = "MWAIT 0x01", + .flags = MWAIT2flg(0x01) | CPUIDLE_FLAG_ALWAYS_ENABLE, + .exit_latency = 2, + .target_residency = 4, + .enter = &intel_idle, + .enter_s2idle = intel_idle_s2idle, }, + { + .name = "C6", + .desc = "MWAIT 0x20", + .flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED, + .exit_latency = 170, + .target_residency = 500, + .enter = &intel_idle, + .enter_s2idle = intel_idle_s2idle, }, + { + .name = "C8", + .desc = "MWAIT 0x40", + .flags = MWAIT2flg(0x40) | CPUIDLE_FLAG_TLB_FLUSHED, + .exit_latency = 200, + .target_residency = 600, + .enter = &intel_idle, + .enter_s2idle = intel_idle_s2idle, }, + { + .name = "C10", + .desc = "MWAIT 0x60", + .flags = MWAIT2flg(0x60) | CPUIDLE_FLAG_TLB_FLUSHED, + .exit_latency = 230, + .target_residency = 700, + .enter = &intel_idle, + .enter_s2idle = intel_idle_s2idle, }, + { + .enter = NULL } +}; + +/* * On Sapphire Rapids Xeon C1 has to be disabled if C1E is enabled, and vice * versa. On SPR C1E is enabled only if "C1E promotion" bit is set in * MSR_IA32_POWER_CTL. But in this case there effectively no C1, because C1 @@ -1142,6 +1247,14 @@ static const struct idle_cpu idle_cpu_icx __initconst = { .use_acpi = true, }; +static const struct idle_cpu idle_cpu_adl __initconst = { + .state_table = adl_cstates, +}; + +static const struct idle_cpu idle_cpu_adl_l __initconst = { + .state_table = adl_l_cstates, +}; + static const struct idle_cpu idle_cpu_spr __initconst = { .state_table = spr_cstates, .disable_promotion_to_c1e = true, @@ -1210,6 +1323,8 @@ static const struct x86_cpu_id intel_idle_ids[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_X, &idle_cpu_skx), X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X, &idle_cpu_icx), X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_D, &idle_cpu_icx), + X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE, &idle_cpu_adl), + X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, &idle_cpu_adl_l), X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &idle_cpu_spr), X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNL, &idle_cpu_knl), X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNM, &idle_cpu_knl), @@ -1398,8 +1513,6 @@ static inline void intel_idle_init_cstates_acpi(struct cpuidle_driver *drv) { } static inline bool intel_idle_off_by_default(u32 mwait_hint) { return false; } #endif /* !CONFIG_ACPI_PROCESSOR_CSTATE */ -static void c1e_promotion_enable(void); - /** * ivt_idle_state_table_update - Tune the idle states table for Ivy Town. * @@ -1571,6 +1684,25 @@ static void __init skx_idle_state_table_update(void) } /** + * adl_idle_state_table_update - Adjust AlderLake idle states table. + */ +static void __init adl_idle_state_table_update(void) +{ + /* Check if user prefers C1 over C1E. */ + if (preferred_states_mask & BIT(1) && !(preferred_states_mask & BIT(2))) { + cpuidle_state_table[0].flags &= ~CPUIDLE_FLAG_UNUSABLE; + cpuidle_state_table[1].flags |= CPUIDLE_FLAG_UNUSABLE; + + /* Disable C1E by clearing the "C1E promotion" bit. */ + c1e_promotion = C1E_PROMOTION_DISABLE; + return; + } + + /* Make sure C1E is enabled by default */ + c1e_promotion = C1E_PROMOTION_ENABLE; +} + +/** * spr_idle_state_table_update - Adjust Sapphire Rapids idle states table. */ static void __init spr_idle_state_table_update(void) @@ -1578,17 +1710,14 @@ static void __init spr_idle_state_table_update(void) unsigned long long msr; /* Check if user prefers C1E over C1. */ - if (preferred_states_mask & BIT(2)) { - if (preferred_states_mask & BIT(1)) - /* Both can't be enabled, stick to the defaults. */ - return; - + if ((preferred_states_mask & BIT(2)) && + !(preferred_states_mask & BIT(1))) { + /* Disable C1 and enable C1E. */ spr_cstates[0].flags |= CPUIDLE_FLAG_UNUSABLE; spr_cstates[1].flags &= ~CPUIDLE_FLAG_UNUSABLE; /* Enable C1E using the "C1E promotion" bit. */ - c1e_promotion_enable(); - disable_promotion_to_c1e = false; + c1e_promotion = C1E_PROMOTION_ENABLE; } /* @@ -1642,6 +1771,10 @@ static void __init intel_idle_init_cstates_icpu(struct cpuidle_driver *drv) case INTEL_FAM6_SAPPHIRERAPIDS_X: spr_idle_state_table_update(); break; + case INTEL_FAM6_ALDERLAKE: + case INTEL_FAM6_ALDERLAKE_L: + adl_idle_state_table_update(); + break; } for (cstate = 0; cstate < CPUIDLE_STATE_MAX; ++cstate) { @@ -1754,7 +1887,9 @@ static int intel_idle_cpu_init(unsigned int cpu) if (auto_demotion_disable_flags) auto_demotion_disable(); - if (disable_promotion_to_c1e) + if (c1e_promotion == C1E_PROMOTION_ENABLE) + c1e_promotion_enable(); + else if (c1e_promotion == C1E_PROMOTION_DISABLE) c1e_promotion_disable(); return 0; @@ -1833,7 +1968,8 @@ static int __init intel_idle_init(void) if (icpu) { cpuidle_state_table = icpu->state_table; auto_demotion_disable_flags = icpu->auto_demotion_disable_flags; - disable_promotion_to_c1e = icpu->disable_promotion_to_c1e; + if (icpu->disable_promotion_to_c1e) + c1e_promotion = C1E_PROMOTION_DISABLE; if (icpu->use_acpi || force_use_acpi) intel_idle_acpi_cst_extract(); } else if (!intel_idle_acpi_cst_extract()) { diff --git a/drivers/iio/adc/ad7280a.c b/drivers/iio/adc/ad7280a.c index ef9d27759961..ec9acbf12b9a 100644 --- a/drivers/iio/adc/ad7280a.c +++ b/drivers/iio/adc/ad7280a.c @@ -745,7 +745,7 @@ static int ad7280a_write_thresh(struct iio_dev *indio_dev, case IIO_EV_DIR_RISING: addr = AD7280A_CELL_OVERVOLTAGE_REG; ret = ad7280_write(st, AD7280A_DEVADDR_MASTER, addr, - 1, val); + 1, value); if (ret) break; st->cell_threshhigh = value; @@ -753,7 +753,7 @@ static int ad7280a_write_thresh(struct iio_dev *indio_dev, case IIO_EV_DIR_FALLING: addr = AD7280A_CELL_UNDERVOLTAGE_REG; ret = ad7280_write(st, AD7280A_DEVADDR_MASTER, addr, - 1, val); + 1, value); if (ret) break; st->cell_threshlow = value; @@ -770,18 +770,18 @@ static int ad7280a_write_thresh(struct iio_dev *indio_dev, case IIO_EV_DIR_RISING: addr = AD7280A_AUX_ADC_OVERVOLTAGE_REG; ret = ad7280_write(st, AD7280A_DEVADDR_MASTER, addr, - 1, val); + 1, value); if (ret) break; - st->aux_threshhigh = val; + st->aux_threshhigh = value; break; case IIO_EV_DIR_FALLING: addr = AD7280A_AUX_ADC_UNDERVOLTAGE_REG; ret = ad7280_write(st, AD7280A_DEVADDR_MASTER, addr, - 1, val); + 1, value); if (ret) break; - st->aux_threshlow = val; + st->aux_threshlow = value; break; default: ret = -EINVAL; diff --git a/drivers/iio/adc/qcom-vadc-common.c b/drivers/iio/adc/qcom-vadc-common.c index 6c6aec848f98..d5209f32adb3 100644 --- a/drivers/iio/adc/qcom-vadc-common.c +++ b/drivers/iio/adc/qcom-vadc-common.c @@ -677,6 +677,17 @@ u16 qcom_adc_tm5_temp_volt_scale(unsigned int prescale_ratio, } EXPORT_SYMBOL(qcom_adc_tm5_temp_volt_scale); +u16 qcom_adc_tm5_gen2_temp_res_scale(int temp) +{ + int64_t resistance; + + resistance = qcom_vadc_map_temp_voltage(adcmap7_100k, + ARRAY_SIZE(adcmap7_100k), temp); + + return div64_s64(resistance * RATIO_MAX_ADC7, resistance + R_PU_100K); +} +EXPORT_SYMBOL(qcom_adc_tm5_gen2_temp_res_scale); + int qcom_adc5_hw_scale(enum vadc_scale_fn_type scaletype, unsigned int prescale_ratio, const struct adc5_data *data, diff --git a/drivers/iio/chemical/scd30.h b/drivers/iio/chemical/scd30.h index f60127bfe0f4..1ac9f3f79271 100644 --- a/drivers/iio/chemical/scd30.h +++ b/drivers/iio/chemical/scd30.h @@ -68,10 +68,7 @@ struct scd30_state { scd30_command_t command; }; -int scd30_suspend(struct device *dev); -int scd30_resume(struct device *dev); - -static __maybe_unused SIMPLE_DEV_PM_OPS(scd30_pm_ops, scd30_suspend, scd30_resume); +extern const struct dev_pm_ops scd30_pm_ops; int scd30_probe(struct device *dev, int irq, const char *name, void *priv, scd30_command_t command); diff --git a/drivers/iio/chemical/scd30_core.c b/drivers/iio/chemical/scd30_core.c index 9fe6bbe9ee04..682fca39d14d 100644 --- a/drivers/iio/chemical/scd30_core.c +++ b/drivers/iio/chemical/scd30_core.c @@ -517,7 +517,7 @@ static const struct iio_chan_spec scd30_channels[] = { IIO_CHAN_SOFT_TIMESTAMP(3), }; -int __maybe_unused scd30_suspend(struct device *dev) +static int scd30_suspend(struct device *dev) { struct iio_dev *indio_dev = dev_get_drvdata(dev); struct scd30_state *state = iio_priv(indio_dev); @@ -529,9 +529,8 @@ int __maybe_unused scd30_suspend(struct device *dev) return regulator_disable(state->vdd); } -EXPORT_SYMBOL(scd30_suspend); -int __maybe_unused scd30_resume(struct device *dev) +static int scd30_resume(struct device *dev) { struct iio_dev *indio_dev = dev_get_drvdata(dev); struct scd30_state *state = iio_priv(indio_dev); @@ -543,7 +542,8 @@ int __maybe_unused scd30_resume(struct device *dev) return scd30_command_write(state, CMD_START_MEAS, state->pressure_comp); } -EXPORT_SYMBOL(scd30_resume); + +EXPORT_NS_SIMPLE_DEV_PM_OPS(scd30_pm_ops, scd30_suspend, scd30_resume, IIO_SCD30); static void scd30_stop_meas(void *data) { @@ -759,7 +759,7 @@ int scd30_probe(struct device *dev, int irq, const char *name, void *priv, return devm_iio_device_register(dev, indio_dev); } -EXPORT_SYMBOL(scd30_probe); +EXPORT_SYMBOL_NS(scd30_probe, IIO_SCD30); MODULE_AUTHOR("Tomasz Duszynski <tomasz.duszynski@octakon.com>"); MODULE_DESCRIPTION("Sensirion SCD30 carbon dioxide sensor core driver"); diff --git a/drivers/iio/chemical/scd30_i2c.c b/drivers/iio/chemical/scd30_i2c.c index 875892a070ee..bae479a4721f 100644 --- a/drivers/iio/chemical/scd30_i2c.c +++ b/drivers/iio/chemical/scd30_i2c.c @@ -128,7 +128,7 @@ static struct i2c_driver scd30_i2c_driver = { .driver = { .name = KBUILD_MODNAME, .of_match_table = scd30_i2c_of_match, - .pm = &scd30_pm_ops, + .pm = pm_sleep_ptr(&scd30_pm_ops), }, .probe_new = scd30_i2c_probe, }; @@ -137,3 +137,4 @@ module_i2c_driver(scd30_i2c_driver); MODULE_AUTHOR("Tomasz Duszynski <tomasz.duszynski@octakon.com>"); MODULE_DESCRIPTION("Sensirion SCD30 carbon dioxide sensor i2c driver"); MODULE_LICENSE("GPL v2"); +MODULE_IMPORT_NS(IIO_SCD30); diff --git a/drivers/iio/chemical/scd30_serial.c b/drivers/iio/chemical/scd30_serial.c index 568b34486c44..3c519103d30b 100644 --- a/drivers/iio/chemical/scd30_serial.c +++ b/drivers/iio/chemical/scd30_serial.c @@ -252,7 +252,7 @@ static struct serdev_device_driver scd30_serdev_driver = { .driver = { .name = KBUILD_MODNAME, .of_match_table = scd30_serdev_of_match, - .pm = &scd30_pm_ops, + .pm = pm_sleep_ptr(&scd30_pm_ops), }, .probe = scd30_serdev_probe, }; @@ -261,3 +261,4 @@ module_serdev_device_driver(scd30_serdev_driver); MODULE_AUTHOR("Tomasz Duszynski <tomasz.duszynski@octakon.com>"); MODULE_DESCRIPTION("Sensirion SCD30 carbon dioxide sensor serial driver"); MODULE_LICENSE("GPL v2"); +MODULE_IMPORT_NS(IIO_SCD30); diff --git a/drivers/iio/chemical/scd4x.c b/drivers/iio/chemical/scd4x.c index 20d4e7584e92..37143b5526ee 100644 --- a/drivers/iio/chemical/scd4x.c +++ b/drivers/iio/chemical/scd4x.c @@ -471,12 +471,15 @@ static ssize_t calibration_forced_value_store(struct device *dev, ret = scd4x_write_and_fetch(state, CMD_FRC, arg, &val, sizeof(val)); mutex_unlock(&state->lock); + if (ret) + return ret; + if (val == 0xff) { dev_err(dev, "forced calibration has failed"); return -EINVAL; } - return ret ?: len; + return len; } static IIO_DEVICE_ATTR_RW(calibration_auto_enable, 0); diff --git a/drivers/iio/dac/ad3552r.c b/drivers/iio/dac/ad3552r.c index 97f13c0b9631..d5ea1a1be122 100644 --- a/drivers/iio/dac/ad3552r.c +++ b/drivers/iio/dac/ad3552r.c @@ -656,7 +656,7 @@ static int ad3552r_reset(struct ad3552r_desc *dac) { struct reg_addr_pool addr; int ret; - u16 val; + int val; dac->gpio_reset = devm_gpiod_get_optional(&dac->spi->dev, "reset", GPIOD_OUT_LOW); @@ -809,10 +809,10 @@ static int ad3552r_configure_custom_gain(struct ad3552r_desc *dac, gain_child = fwnode_get_named_child_node(child, "custom-output-range-config"); - if (IS_ERR(gain_child)) { + if (!gain_child) { dev_err(dev, "mandatory custom-output-range-config property missing\n"); - return PTR_ERR(gain_child); + return -EINVAL; } dac->ch_data[ch].range_override = 1; diff --git a/drivers/iio/dac/ad5446.c b/drivers/iio/dac/ad5446.c index 14cfabacbea5..fdf824041497 100644 --- a/drivers/iio/dac/ad5446.c +++ b/drivers/iio/dac/ad5446.c @@ -178,7 +178,7 @@ static int ad5446_read_raw(struct iio_dev *indio_dev, switch (m) { case IIO_CHAN_INFO_RAW: - *val = st->cached_val; + *val = st->cached_val >> chan->scan_type.shift; return IIO_VAL_INT; case IIO_CHAN_INFO_SCALE: *val = st->vref_mv; diff --git a/drivers/iio/dac/ad5592r-base.c b/drivers/iio/dac/ad5592r-base.c index a424b7220b61..4434c1b2a322 100644 --- a/drivers/iio/dac/ad5592r-base.c +++ b/drivers/iio/dac/ad5592r-base.c @@ -522,7 +522,7 @@ static int ad5592r_alloc_channels(struct iio_dev *iio_dev) if (!ret) st->channel_modes[reg] = tmp; - fwnode_property_read_u32(child, "adi,off-state", &tmp); + ret = fwnode_property_read_u32(child, "adi,off-state", &tmp); if (!ret) st->channel_offstate[reg] = tmp; } diff --git a/drivers/iio/dac/ltc2688.c b/drivers/iio/dac/ltc2688.c index e41861d29767..2f9c384885f4 100644 --- a/drivers/iio/dac/ltc2688.c +++ b/drivers/iio/dac/ltc2688.c @@ -298,7 +298,7 @@ static int ltc2688_read_raw(struct iio_dev *indio_dev, if (ret) return ret; - *val = 16; + *val2 = 16; return IIO_VAL_FRACTIONAL_LOG2; case IIO_CHAN_INFO_CALIBBIAS: ret = regmap_read(st->regmap, diff --git a/drivers/iio/dac/ti-dac5571.c b/drivers/iio/dac/ti-dac5571.c index 4a3b8d875518..0b775f943db3 100644 --- a/drivers/iio/dac/ti-dac5571.c +++ b/drivers/iio/dac/ti-dac5571.c @@ -19,6 +19,7 @@ #include <linux/i2c.h> #include <linux/module.h> #include <linux/mod_devicetable.h> +#include <linux/property.h> #include <linux/regulator/consumer.h> enum chip_id { @@ -311,6 +312,7 @@ static int dac5571_probe(struct i2c_client *client, const struct dac5571_spec *spec; struct dac5571_data *data; struct iio_dev *indio_dev; + enum chip_id chip_id; int ret, i; indio_dev = devm_iio_device_alloc(dev, sizeof(*data)); @@ -326,7 +328,13 @@ static int dac5571_probe(struct i2c_client *client, indio_dev->modes = INDIO_DIRECT_MODE; indio_dev->channels = dac5571_channels; - spec = &dac5571_spec[id->driver_data]; + if (dev_fwnode(dev)) + chip_id = (uintptr_t)device_get_match_data(dev); + else + chip_id = id->driver_data; + + spec = &dac5571_spec[chip_id]; + indio_dev->num_channels = spec->num_channels; data->spec = spec; @@ -385,15 +393,15 @@ static int dac5571_remove(struct i2c_client *i2c) } static const struct of_device_id dac5571_of_id[] = { - {.compatible = "ti,dac5571"}, - {.compatible = "ti,dac6571"}, - {.compatible = "ti,dac7571"}, - {.compatible = "ti,dac5574"}, - {.compatible = "ti,dac6574"}, - {.compatible = "ti,dac7574"}, - {.compatible = "ti,dac5573"}, - {.compatible = "ti,dac6573"}, - {.compatible = "ti,dac7573"}, + {.compatible = "ti,dac5571", .data = (void *)single_8bit}, + {.compatible = "ti,dac6571", .data = (void *)single_10bit}, + {.compatible = "ti,dac7571", .data = (void *)single_12bit}, + {.compatible = "ti,dac5574", .data = (void *)quad_8bit}, + {.compatible = "ti,dac6574", .data = (void *)quad_10bit}, + {.compatible = "ti,dac7574", .data = (void *)quad_12bit}, + {.compatible = "ti,dac5573", .data = (void *)quad_8bit}, + {.compatible = "ti,dac6573", .data = (void *)quad_10bit}, + {.compatible = "ti,dac7573", .data = (void *)quad_12bit}, {} }; MODULE_DEVICE_TABLE(of, dac5571_of_id); diff --git a/drivers/iio/filter/Kconfig b/drivers/iio/filter/Kconfig index 3ae35817ad82..a85b345ea14e 100644 --- a/drivers/iio/filter/Kconfig +++ b/drivers/iio/filter/Kconfig @@ -8,6 +8,7 @@ menu "Filters" config ADMV8818 tristate "Analog Devices ADMV8818 High-Pass and Low-Pass Filter" depends on SPI && COMMON_CLK && 64BIT + select REGMAP_SPI help Say yes here to build support for Analog Devices ADMV8818 2 GHz to 18 GHz, Digitally Tunable, High-Pass and Low-Pass Filter. diff --git a/drivers/iio/imu/bmi160/bmi160_core.c b/drivers/iio/imu/bmi160/bmi160_core.c index 824b5124a5f5..01336105792e 100644 --- a/drivers/iio/imu/bmi160/bmi160_core.c +++ b/drivers/iio/imu/bmi160/bmi160_core.c @@ -730,7 +730,7 @@ static int bmi160_chip_init(struct bmi160_data *data, bool use_spi) ret = regmap_write(data->regmap, BMI160_REG_CMD, BMI160_CMD_SOFTRESET); if (ret) - return ret; + goto disable_regulator; usleep_range(BMI160_SOFTRESET_USLEEP, BMI160_SOFTRESET_USLEEP + 1); @@ -741,29 +741,37 @@ static int bmi160_chip_init(struct bmi160_data *data, bool use_spi) if (use_spi) { ret = regmap_read(data->regmap, BMI160_REG_DUMMY, &val); if (ret) - return ret; + goto disable_regulator; } ret = regmap_read(data->regmap, BMI160_REG_CHIP_ID, &val); if (ret) { dev_err(dev, "Error reading chip id\n"); - return ret; + goto disable_regulator; } if (val != BMI160_CHIP_ID_VAL) { dev_err(dev, "Wrong chip id, got %x expected %x\n", val, BMI160_CHIP_ID_VAL); - return -ENODEV; + ret = -ENODEV; + goto disable_regulator; } ret = bmi160_set_mode(data, BMI160_ACCEL, true); if (ret) - return ret; + goto disable_regulator; ret = bmi160_set_mode(data, BMI160_GYRO, true); if (ret) - return ret; + goto disable_accel; return 0; + +disable_accel: + bmi160_set_mode(data, BMI160_ACCEL, false); + +disable_regulator: + regulator_bulk_disable(ARRAY_SIZE(data->supplies), data->supplies); + return ret; } static int bmi160_data_rdy_trigger_set_state(struct iio_trigger *trig, diff --git a/drivers/iio/imu/inv_icm42600/inv_icm42600_i2c.c b/drivers/iio/imu/inv_icm42600/inv_icm42600_i2c.c index 33d9afb1ba91..d4a692b838d0 100644 --- a/drivers/iio/imu/inv_icm42600/inv_icm42600_i2c.c +++ b/drivers/iio/imu/inv_icm42600/inv_icm42600_i2c.c @@ -18,12 +18,15 @@ static int inv_icm42600_i2c_bus_setup(struct inv_icm42600_state *st) unsigned int mask, val; int ret; - /* setup interface registers */ - ret = regmap_update_bits(st->map, INV_ICM42600_REG_INTF_CONFIG6, - INV_ICM42600_INTF_CONFIG6_MASK, - INV_ICM42600_INTF_CONFIG6_I3C_EN); - if (ret) - return ret; + /* + * setup interface registers + * This register write to REG_INTF_CONFIG6 enables a spike filter that + * is impacting the line and can prevent the I2C ACK to be seen by the + * controller. So we don't test the return value. + */ + regmap_update_bits(st->map, INV_ICM42600_REG_INTF_CONFIG6, + INV_ICM42600_INTF_CONFIG6_MASK, + INV_ICM42600_INTF_CONFIG6_I3C_EN); ret = regmap_update_bits(st->map, INV_ICM42600_REG_INTF_CONFIG4, INV_ICM42600_INTF_CONFIG4_I3C_BUS_ONLY, 0); diff --git a/drivers/iio/magnetometer/ak8975.c b/drivers/iio/magnetometer/ak8975.c index 088f748b683e..2432e697150c 100644 --- a/drivers/iio/magnetometer/ak8975.c +++ b/drivers/iio/magnetometer/ak8975.c @@ -416,6 +416,7 @@ static int ak8975_power_on(const struct ak8975_data *data) if (ret) { dev_warn(&data->client->dev, "Failed to enable specified Vid supply\n"); + regulator_disable(data->vdd); return ret; } diff --git a/drivers/iio/proximity/sx9324.c b/drivers/iio/proximity/sx9324.c index 0d9bbbb50cb4..70c37f664f6d 100644 --- a/drivers/iio/proximity/sx9324.c +++ b/drivers/iio/proximity/sx9324.c @@ -70,13 +70,17 @@ #define SX9324_REG_AFE_PH2 0x2a #define SX9324_REG_AFE_PH3 0x2b #define SX9324_REG_AFE_CTRL8 0x2c -#define SX9324_REG_AFE_CTRL8_RESFILTN_4KOHM 0x02 +#define SX9324_REG_AFE_CTRL8_RESERVED 0x10 +#define SX9324_REG_AFE_CTRL8_RESFILTIN_4KOHM 0x02 #define SX9324_REG_AFE_CTRL9 0x2d #define SX9324_REG_AFE_CTRL9_AGAIN_1 0x08 #define SX9324_REG_PROX_CTRL0 0x30 #define SX9324_REG_PROX_CTRL0_GAIN_MASK GENMASK(5, 3) -#define SX9324_REG_PROX_CTRL0_GAIN_1 0x80 +#define SX9324_REG_PROX_CTRL0_GAIN_SHIFT 3 +#define SX9324_REG_PROX_CTRL0_GAIN_RSVD 0x0 +#define SX9324_REG_PROX_CTRL0_GAIN_1 0x1 +#define SX9324_REG_PROX_CTRL0_GAIN_8 0x4 #define SX9324_REG_PROX_CTRL0_RAWFILT_MASK GENMASK(2, 0) #define SX9324_REG_PROX_CTRL0_RAWFILT_1P50 0x01 #define SX9324_REG_PROX_CTRL1 0x31 @@ -379,7 +383,14 @@ static int sx9324_read_gain(struct sx_common_data *data, if (ret) return ret; - *val = 1 << FIELD_GET(SX9324_REG_PROX_CTRL0_GAIN_MASK, regval); + regval = FIELD_GET(SX9324_REG_PROX_CTRL0_GAIN_MASK, regval); + if (regval) + regval--; + else if (regval == SX9324_REG_PROX_CTRL0_GAIN_RSVD || + regval > SX9324_REG_PROX_CTRL0_GAIN_8) + return -EINVAL; + + *val = 1 << regval; return IIO_VAL_INT; } @@ -725,8 +736,12 @@ static int sx9324_write_gain(struct sx_common_data *data, unsigned int gain, reg; int ret; - gain = ilog2(val); reg = SX9324_REG_PROX_CTRL0 + chan->channel / 2; + + gain = ilog2(val) + 1; + if (val <= 0 || gain > SX9324_REG_PROX_CTRL0_GAIN_8) + return -EINVAL; + gain = FIELD_PREP(SX9324_REG_PROX_CTRL0_GAIN_MASK, gain); mutex_lock(&data->mutex); @@ -781,12 +796,15 @@ static const struct sx_common_reg_default sx9324_default_regs[] = { { SX9324_REG_AFE_PH2, 0x1a }, { SX9324_REG_AFE_PH3, 0x16 }, - { SX9324_REG_AFE_CTRL8, SX9324_REG_AFE_CTRL8_RESFILTN_4KOHM }, + { SX9324_REG_AFE_CTRL8, SX9324_REG_AFE_CTRL8_RESERVED | + SX9324_REG_AFE_CTRL8_RESFILTIN_4KOHM }, { SX9324_REG_AFE_CTRL9, SX9324_REG_AFE_CTRL9_AGAIN_1 }, - { SX9324_REG_PROX_CTRL0, SX9324_REG_PROX_CTRL0_GAIN_1 | + { SX9324_REG_PROX_CTRL0, + SX9324_REG_PROX_CTRL0_GAIN_1 << SX9324_REG_PROX_CTRL0_GAIN_SHIFT | SX9324_REG_PROX_CTRL0_RAWFILT_1P50 }, - { SX9324_REG_PROX_CTRL1, SX9324_REG_PROX_CTRL0_GAIN_1 | + { SX9324_REG_PROX_CTRL1, + SX9324_REG_PROX_CTRL0_GAIN_1 << SX9324_REG_PROX_CTRL0_GAIN_SHIFT | SX9324_REG_PROX_CTRL0_RAWFILT_1P50 }, { SX9324_REG_PROX_CTRL2, SX9324_REG_PROX_CTRL2_AVGNEG_THRESH_16K }, { SX9324_REG_PROX_CTRL3, SX9324_REG_PROX_CTRL3_AVGDEB_2SAMPLES | diff --git a/drivers/iio/proximity/sx_common.c b/drivers/iio/proximity/sx_common.c index a7c07316a0a9..8ad814d96b7e 100644 --- a/drivers/iio/proximity/sx_common.c +++ b/drivers/iio/proximity/sx_common.c @@ -521,6 +521,7 @@ int sx_common_probe(struct i2c_client *client, return dev_err_probe(dev, ret, "error reading WHOAMI\n"); ACPI_COMPANION_SET(&indio_dev->dev, ACPI_COMPANION(dev)); + indio_dev->dev.of_node = client->dev.of_node; indio_dev->modes = INDIO_DIRECT_MODE; indio_dev->channels = data->chip_info->iio_channels; diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c index 35f0d5e7533d..1c107d6d03b9 100644 --- a/drivers/infiniband/core/cm.c +++ b/drivers/infiniband/core/cm.c @@ -2824,6 +2824,7 @@ static int cm_dreq_handler(struct cm_work *work) switch (cm_id_priv->id.state) { case IB_CM_REP_SENT: case IB_CM_DREQ_SENT: + case IB_CM_MRA_REP_RCVD: ib_cancel_mad(cm_id_priv->msg); break; case IB_CM_ESTABLISHED: @@ -2831,8 +2832,6 @@ static int cm_dreq_handler(struct cm_work *work) cm_id_priv->id.lap_state == IB_CM_MRA_LAP_RCVD) ib_cancel_mad(cm_id_priv->msg); break; - case IB_CM_MRA_REP_RCVD: - break; case IB_CM_TIMEWAIT: atomic_long_inc(&work->port->counters[CM_RECV_DUPLICATES] [CM_DREQ_COUNTER]); diff --git a/drivers/infiniband/hw/hfi1/mmu_rb.c b/drivers/infiniband/hw/hfi1/mmu_rb.c index 876cc78a22cc..7333646021bb 100644 --- a/drivers/infiniband/hw/hfi1/mmu_rb.c +++ b/drivers/infiniband/hw/hfi1/mmu_rb.c @@ -80,6 +80,9 @@ void hfi1_mmu_rb_unregister(struct mmu_rb_handler *handler) unsigned long flags; struct list_head del_list; + /* Prevent freeing of mm until we are completely finished. */ + mmgrab(handler->mn.mm); + /* Unregister first so we don't get any more notifications. */ mmu_notifier_unregister(&handler->mn, handler->mn.mm); @@ -102,6 +105,9 @@ void hfi1_mmu_rb_unregister(struct mmu_rb_handler *handler) do_remove(handler, &del_list); + /* Now the mm may be freed. */ + mmdrop(handler->mn.mm); + kfree(handler); } diff --git a/drivers/infiniband/hw/irdma/cm.c b/drivers/infiniband/hw/irdma/cm.c index dedb3b7edd8d..638bf4a1ed94 100644 --- a/drivers/infiniband/hw/irdma/cm.c +++ b/drivers/infiniband/hw/irdma/cm.c @@ -2308,10 +2308,8 @@ err: return NULL; } -static void irdma_cm_node_free_cb(struct rcu_head *rcu_head) +static void irdma_destroy_connection(struct irdma_cm_node *cm_node) { - struct irdma_cm_node *cm_node = - container_of(rcu_head, struct irdma_cm_node, rcu_head); struct irdma_cm_core *cm_core = cm_node->cm_core; struct irdma_qp *iwqp; struct irdma_cm_info nfo; @@ -2359,7 +2357,6 @@ static void irdma_cm_node_free_cb(struct rcu_head *rcu_head) } cm_core->cm_free_ah(cm_node); - kfree(cm_node); } /** @@ -2387,8 +2384,9 @@ void irdma_rem_ref_cm_node(struct irdma_cm_node *cm_node) spin_unlock_irqrestore(&cm_core->ht_lock, flags); - /* wait for all list walkers to exit their grace period */ - call_rcu(&cm_node->rcu_head, irdma_cm_node_free_cb); + irdma_destroy_connection(cm_node); + + kfree_rcu(cm_node, rcu_head); } /** @@ -3246,15 +3244,10 @@ int irdma_setup_cm_core(struct irdma_device *iwdev, u8 rdma_ver) */ void irdma_cleanup_cm_core(struct irdma_cm_core *cm_core) { - unsigned long flags; - if (!cm_core) return; - spin_lock_irqsave(&cm_core->ht_lock, flags); - if (timer_pending(&cm_core->tcp_timer)) - del_timer_sync(&cm_core->tcp_timer); - spin_unlock_irqrestore(&cm_core->ht_lock, flags); + del_timer_sync(&cm_core->tcp_timer); destroy_workqueue(cm_core->event_wq); cm_core->dev->ws_reset(&cm_core->iwdev->vsi); @@ -3467,12 +3460,6 @@ static void irdma_cm_disconn_true(struct irdma_qp *iwqp) } cm_id = iwqp->cm_id; - /* make sure we havent already closed this connection */ - if (!cm_id) { - spin_unlock_irqrestore(&iwqp->lock, flags); - return; - } - original_hw_tcp_state = iwqp->hw_tcp_state; original_ibqp_state = iwqp->ibqp_state; last_ae = iwqp->last_aeq; @@ -3494,11 +3481,11 @@ static void irdma_cm_disconn_true(struct irdma_qp *iwqp) disconn_status = -ECONNRESET; } - if ((original_hw_tcp_state == IRDMA_TCP_STATE_CLOSED || - original_hw_tcp_state == IRDMA_TCP_STATE_TIME_WAIT || - last_ae == IRDMA_AE_RDMAP_ROE_BAD_LLP_CLOSE || - last_ae == IRDMA_AE_BAD_CLOSE || - last_ae == IRDMA_AE_LLP_CONNECTION_RESET || iwdev->rf->reset)) { + if (original_hw_tcp_state == IRDMA_TCP_STATE_CLOSED || + original_hw_tcp_state == IRDMA_TCP_STATE_TIME_WAIT || + last_ae == IRDMA_AE_RDMAP_ROE_BAD_LLP_CLOSE || + last_ae == IRDMA_AE_BAD_CLOSE || + last_ae == IRDMA_AE_LLP_CONNECTION_RESET || iwdev->rf->reset || !cm_id) { issue_close = 1; iwqp->cm_id = NULL; qp->term_flags = 0; diff --git a/drivers/infiniband/hw/irdma/utils.c b/drivers/infiniband/hw/irdma/utils.c index 346c2c5dabdf..81760415d66c 100644 --- a/drivers/infiniband/hw/irdma/utils.c +++ b/drivers/infiniband/hw/irdma/utils.c @@ -258,18 +258,16 @@ int irdma_net_event(struct notifier_block *notifier, unsigned long event, u32 local_ipaddr[4] = {}; bool ipv4 = true; - real_dev = rdma_vlan_dev_real_dev(netdev); - if (!real_dev) - real_dev = netdev; - - ibdev = ib_device_get_by_netdev(real_dev, RDMA_DRIVER_IRDMA); - if (!ibdev) - return NOTIFY_DONE; - - iwdev = to_iwdev(ibdev); - switch (event) { case NETEVENT_NEIGH_UPDATE: + real_dev = rdma_vlan_dev_real_dev(netdev); + if (!real_dev) + real_dev = netdev; + ibdev = ib_device_get_by_netdev(real_dev, RDMA_DRIVER_IRDMA); + if (!ibdev) + return NOTIFY_DONE; + + iwdev = to_iwdev(ibdev); p = (__be32 *)neigh->primary_key; if (neigh->tbl->family == AF_INET6) { ipv4 = false; @@ -290,13 +288,12 @@ int irdma_net_event(struct notifier_block *notifier, unsigned long event, irdma_manage_arp_cache(iwdev->rf, neigh->ha, local_ipaddr, ipv4, IRDMA_ARP_DELETE); + ib_device_put(ibdev); break; default: break; } - ib_device_put(ibdev); - return NOTIFY_DONE; } diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c index 46f475394af5..52f3e88f8569 100644 --- a/drivers/infiniband/hw/irdma/verbs.c +++ b/drivers/infiniband/hw/irdma/verbs.c @@ -1618,13 +1618,13 @@ int irdma_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, int attr_mask, if (issue_modify_qp && iwqp->ibqp_state > IB_QPS_RTS) { if (dont_wait) { - if (iwqp->cm_id && iwqp->hw_tcp_state) { + if (iwqp->hw_tcp_state) { spin_lock_irqsave(&iwqp->lock, flags); iwqp->hw_tcp_state = IRDMA_TCP_STATE_CLOSED; iwqp->last_aeq = IRDMA_AE_RESET_SENT; spin_unlock_irqrestore(&iwqp->lock, flags); - irdma_cm_disconn(iwqp); } + irdma_cm_disconn(iwqp); } else { int close_timer_started; diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index 956f8e875daa..32ef67e9a6a7 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -574,8 +574,10 @@ static void __cache_work_func(struct mlx5_cache_ent *ent) spin_lock_irq(&ent->lock); if (ent->disabled) goto out; - if (need_delay) + if (need_delay) { queue_delayed_work(cache->wq, &ent->dwork, 300 * HZ); + goto out; + } remove_cache_mr_locked(ent); queue_adjust_cache_locked(ent); } @@ -625,6 +627,7 @@ static void mlx5_mr_cache_free(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr) { struct mlx5_cache_ent *ent = mr->cache_ent; + WRITE_ONCE(dev->cache.last_add, jiffies); spin_lock_irq(&ent->lock); list_add_tail(&mr->list, &ent->head); ent->available_mrs++; diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c index ae50b56e8913..8ef112f883a7 100644 --- a/drivers/infiniband/sw/rdmavt/qp.c +++ b/drivers/infiniband/sw/rdmavt/qp.c @@ -3190,7 +3190,11 @@ serr_no_r_lock: spin_lock_irqsave(&sqp->s_lock, flags); rvt_send_complete(sqp, wqe, send_status); if (sqp->ibqp.qp_type == IB_QPT_RC) { - int lastwqe = rvt_error_qp(sqp, IB_WC_WR_FLUSH_ERR); + int lastwqe; + + spin_lock(&sqp->r_lock); + lastwqe = rvt_error_qp(sqp, IB_WC_WR_FLUSH_ERR); + spin_unlock(&sqp->r_lock); sqp->s_flags &= ~RVT_S_BUSY; spin_unlock_irqrestore(&sqp->s_lock, flags); diff --git a/drivers/infiniband/sw/rxe/rxe_mcast.c b/drivers/infiniband/sw/rxe/rxe_mcast.c index ae8f11cb704a..873a9b10307c 100644 --- a/drivers/infiniband/sw/rxe/rxe_mcast.c +++ b/drivers/infiniband/sw/rxe/rxe_mcast.c @@ -38,13 +38,13 @@ static int rxe_mcast_add(struct rxe_dev *rxe, union ib_gid *mgid) } /** - * rxe_mcast_delete - delete multicast address from rxe device + * rxe_mcast_del - delete multicast address from rxe device * @rxe: rxe device object * @mgid: multicast address as a gid * * Returns 0 on success else an error */ -static int rxe_mcast_delete(struct rxe_dev *rxe, union ib_gid *mgid) +static int rxe_mcast_del(struct rxe_dev *rxe, union ib_gid *mgid) { unsigned char ll_addr[ETH_ALEN]; @@ -143,11 +143,10 @@ static struct rxe_mcg *__rxe_lookup_mcg(struct rxe_dev *rxe, struct rxe_mcg *rxe_lookup_mcg(struct rxe_dev *rxe, union ib_gid *mgid) { struct rxe_mcg *mcg; - unsigned long flags; - spin_lock_irqsave(&rxe->mcg_lock, flags); + spin_lock_bh(&rxe->mcg_lock); mcg = __rxe_lookup_mcg(rxe, mgid); - spin_unlock_irqrestore(&rxe->mcg_lock, flags); + spin_unlock_bh(&rxe->mcg_lock); return mcg; } @@ -159,17 +158,10 @@ struct rxe_mcg *rxe_lookup_mcg(struct rxe_dev *rxe, union ib_gid *mgid) * @mcg: new mcg object * * Context: caller should hold rxe->mcg lock - * Returns: 0 on success else an error */ -static int __rxe_init_mcg(struct rxe_dev *rxe, union ib_gid *mgid, - struct rxe_mcg *mcg) +static void __rxe_init_mcg(struct rxe_dev *rxe, union ib_gid *mgid, + struct rxe_mcg *mcg) { - int err; - - err = rxe_mcast_add(rxe, mgid); - if (unlikely(err)) - return err; - kref_init(&mcg->ref_cnt); memcpy(&mcg->mgid, mgid, sizeof(mcg->mgid)); INIT_LIST_HEAD(&mcg->qp_list); @@ -184,8 +176,6 @@ static int __rxe_init_mcg(struct rxe_dev *rxe, union ib_gid *mgid, */ kref_get(&mcg->ref_cnt); __rxe_insert_mcg(mcg); - - return 0; } /** @@ -198,7 +188,6 @@ static int __rxe_init_mcg(struct rxe_dev *rxe, union ib_gid *mgid, static struct rxe_mcg *rxe_get_mcg(struct rxe_dev *rxe, union ib_gid *mgid) { struct rxe_mcg *mcg, *tmp; - unsigned long flags; int err; if (rxe->attr.max_mcast_grp == 0) @@ -209,36 +198,38 @@ static struct rxe_mcg *rxe_get_mcg(struct rxe_dev *rxe, union ib_gid *mgid) if (mcg) return mcg; + /* check to see if we have reached limit */ + if (atomic_inc_return(&rxe->mcg_num) > rxe->attr.max_mcast_grp) { + err = -ENOMEM; + goto err_dec; + } + /* speculative alloc of new mcg */ mcg = kzalloc(sizeof(*mcg), GFP_KERNEL); if (!mcg) return ERR_PTR(-ENOMEM); - spin_lock_irqsave(&rxe->mcg_lock, flags); + spin_lock_bh(&rxe->mcg_lock); /* re-check to see if someone else just added it */ tmp = __rxe_lookup_mcg(rxe, mgid); if (tmp) { + spin_unlock_bh(&rxe->mcg_lock); + atomic_dec(&rxe->mcg_num); kfree(mcg); - mcg = tmp; - goto out; + return tmp; } - if (atomic_inc_return(&rxe->mcg_num) > rxe->attr.max_mcast_grp) { - err = -ENOMEM; - goto err_dec; - } + __rxe_init_mcg(rxe, mgid, mcg); + spin_unlock_bh(&rxe->mcg_lock); - err = __rxe_init_mcg(rxe, mgid, mcg); - if (err) - goto err_dec; -out: - spin_unlock_irqrestore(&rxe->mcg_lock, flags); - return mcg; + /* add mcast address outside of lock */ + err = rxe_mcast_add(rxe, mgid); + if (!err) + return mcg; + kfree(mcg); err_dec: atomic_dec(&rxe->mcg_num); - spin_unlock_irqrestore(&rxe->mcg_lock, flags); - kfree(mcg); return ERR_PTR(err); } @@ -268,7 +259,6 @@ static void __rxe_destroy_mcg(struct rxe_mcg *mcg) __rxe_remove_mcg(mcg); kref_put(&mcg->ref_cnt, rxe_cleanup_mcg); - rxe_mcast_delete(mcg->rxe, &mcg->mgid); atomic_dec(&rxe->mcg_num); } @@ -280,11 +270,12 @@ static void __rxe_destroy_mcg(struct rxe_mcg *mcg) */ static void rxe_destroy_mcg(struct rxe_mcg *mcg) { - unsigned long flags; + /* delete mcast address outside of lock */ + rxe_mcast_del(mcg->rxe, &mcg->mgid); - spin_lock_irqsave(&mcg->rxe->mcg_lock, flags); + spin_lock_bh(&mcg->rxe->mcg_lock); __rxe_destroy_mcg(mcg); - spin_unlock_irqrestore(&mcg->rxe->mcg_lock, flags); + spin_unlock_bh(&mcg->rxe->mcg_lock); } /** @@ -339,25 +330,24 @@ static int rxe_attach_mcg(struct rxe_mcg *mcg, struct rxe_qp *qp) { struct rxe_dev *rxe = mcg->rxe; struct rxe_mca *mca, *tmp; - unsigned long flags; int err; /* check to see if the qp is already a member of the group */ - spin_lock_irqsave(&rxe->mcg_lock, flags); + spin_lock_bh(&rxe->mcg_lock); list_for_each_entry(mca, &mcg->qp_list, qp_list) { if (mca->qp == qp) { - spin_unlock_irqrestore(&rxe->mcg_lock, flags); + spin_unlock_bh(&rxe->mcg_lock); return 0; } } - spin_unlock_irqrestore(&rxe->mcg_lock, flags); + spin_unlock_bh(&rxe->mcg_lock); /* speculative alloc new mca without using GFP_ATOMIC */ mca = kzalloc(sizeof(*mca), GFP_KERNEL); if (!mca) return -ENOMEM; - spin_lock_irqsave(&rxe->mcg_lock, flags); + spin_lock_bh(&rxe->mcg_lock); /* re-check to see if someone else just attached qp */ list_for_each_entry(tmp, &mcg->qp_list, qp_list) { if (tmp->qp == qp) { @@ -371,7 +361,7 @@ static int rxe_attach_mcg(struct rxe_mcg *mcg, struct rxe_qp *qp) if (err) kfree(mca); out: - spin_unlock_irqrestore(&rxe->mcg_lock, flags); + spin_unlock_bh(&rxe->mcg_lock); return err; } @@ -405,9 +395,8 @@ static int rxe_detach_mcg(struct rxe_mcg *mcg, struct rxe_qp *qp) { struct rxe_dev *rxe = mcg->rxe; struct rxe_mca *mca, *tmp; - unsigned long flags; - spin_lock_irqsave(&rxe->mcg_lock, flags); + spin_lock_bh(&rxe->mcg_lock); list_for_each_entry_safe(mca, tmp, &mcg->qp_list, qp_list) { if (mca->qp == qp) { __rxe_cleanup_mca(mca, mcg); @@ -421,13 +410,13 @@ static int rxe_detach_mcg(struct rxe_mcg *mcg, struct rxe_qp *qp) if (atomic_read(&mcg->qp_num) <= 0) __rxe_destroy_mcg(mcg); - spin_unlock_irqrestore(&rxe->mcg_lock, flags); + spin_unlock_bh(&rxe->mcg_lock); return 0; } } /* we didn't find the qp on the list */ - spin_unlock_irqrestore(&rxe->mcg_lock, flags); + spin_unlock_bh(&rxe->mcg_lock); return -EINVAL; } diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c index 16fc7ea1298d..9cd0eaff98de 100644 --- a/drivers/infiniband/sw/rxe/rxe_resp.c +++ b/drivers/infiniband/sw/rxe/rxe_resp.c @@ -680,6 +680,11 @@ static struct resp_res *rxe_prepare_read_res(struct rxe_qp *qp, * It is assumed that the access permissions if originally good * are OK and the mappings to be unchanged. * + * TODO: If someone reregisters an MR to change its size or + * access permissions during the processing of an RDMA read + * we should kill the responder resource and complete the + * operation with an error. + * * Return: mr on success else NULL */ static struct rxe_mr *rxe_recheck_mr(struct rxe_qp *qp, u32 rkey) @@ -690,23 +695,27 @@ static struct rxe_mr *rxe_recheck_mr(struct rxe_qp *qp, u32 rkey) if (rkey_is_mw(rkey)) { mw = rxe_pool_get_index(&rxe->mw_pool, rkey >> 8); - if (!mw || mw->rkey != rkey) + if (!mw) return NULL; - if (mw->state != RXE_MW_STATE_VALID) { + mr = mw->mr; + if (mw->rkey != rkey || mw->state != RXE_MW_STATE_VALID || + !mr || mr->state != RXE_MR_STATE_VALID) { rxe_put(mw); return NULL; } - mr = mw->mr; + rxe_get(mr); rxe_put(mw); - } else { - mr = rxe_pool_get_index(&rxe->mr_pool, rkey >> 8); - if (!mr || mr->rkey != rkey) - return NULL; + + return mr; } - if (mr->state != RXE_MR_STATE_VALID) { + mr = rxe_pool_get_index(&rxe->mr_pool, rkey >> 8); + if (!mr) + return NULL; + + if (mr->rkey != rkey || mr->state != RXE_MR_STATE_VALID) { rxe_put(mr); return NULL; } @@ -736,8 +745,14 @@ static enum resp_states read_reply(struct rxe_qp *qp, } if (res->state == rdatm_res_state_new) { - mr = qp->resp.mr; - qp->resp.mr = NULL; + if (!res->replay) { + mr = qp->resp.mr; + qp->resp.mr = NULL; + } else { + mr = rxe_recheck_mr(qp, res->read.rkey); + if (!mr) + return RESPST_ERR_RKEY_VIOLATION; + } if (res->read.resid <= mtu) opcode = IB_OPCODE_RC_RDMA_READ_RESPONSE_ONLY; diff --git a/drivers/infiniband/sw/siw/siw_cm.c b/drivers/infiniband/sw/siw/siw_cm.c index 7acdd3c3a599..17f34d584cd9 100644 --- a/drivers/infiniband/sw/siw/siw_cm.c +++ b/drivers/infiniband/sw/siw/siw_cm.c @@ -968,14 +968,15 @@ static void siw_accept_newconn(struct siw_cep *cep) siw_cep_set_inuse(new_cep); rv = siw_proc_mpareq(new_cep); - siw_cep_set_free(new_cep); - if (rv != -EAGAIN) { siw_cep_put(cep); new_cep->listen_cep = NULL; - if (rv) + if (rv) { + siw_cep_set_free(new_cep); goto error; + } } + siw_cep_set_free(new_cep); } return; diff --git a/drivers/input/keyboard/cypress-sf.c b/drivers/input/keyboard/cypress-sf.c index c28996028e80..9a23eed6a4f4 100644 --- a/drivers/input/keyboard/cypress-sf.c +++ b/drivers/input/keyboard/cypress-sf.c @@ -61,6 +61,14 @@ static irqreturn_t cypress_sf_irq_handler(int irq, void *devid) return IRQ_HANDLED; } +static void cypress_sf_disable_regulators(void *arg) +{ + struct cypress_sf_data *touchkey = arg; + + regulator_bulk_disable(ARRAY_SIZE(touchkey->regulators), + touchkey->regulators); +} + static int cypress_sf_probe(struct i2c_client *client) { struct cypress_sf_data *touchkey; @@ -121,6 +129,12 @@ static int cypress_sf_probe(struct i2c_client *client) return error; } + error = devm_add_action_or_reset(&client->dev, + cypress_sf_disable_regulators, + touchkey); + if (error) + return error; + touchkey->input_dev = devm_input_allocate_device(&client->dev); if (!touchkey->input_dev) { dev_err(&client->dev, "Failed to allocate input device\n"); diff --git a/drivers/input/keyboard/omap4-keypad.c b/drivers/input/keyboard/omap4-keypad.c index 43375b38ee59..8a7ce41b8c56 100644 --- a/drivers/input/keyboard/omap4-keypad.c +++ b/drivers/input/keyboard/omap4-keypad.c @@ -393,7 +393,7 @@ static int omap4_keypad_probe(struct platform_device *pdev) * revision register. */ error = pm_runtime_get_sync(dev); - if (error) { + if (error < 0) { dev_err(dev, "pm_runtime_get_sync() failed\n"); pm_runtime_put_noidle(dev); return error; diff --git a/drivers/input/touchscreen/ili210x.c b/drivers/input/touchscreen/ili210x.c index 2bd407d86bae..e9bd36adbe47 100644 --- a/drivers/input/touchscreen/ili210x.c +++ b/drivers/input/touchscreen/ili210x.c @@ -756,15 +756,12 @@ static int ili251x_firmware_reset(struct i2c_client *client) return ili251x_firmware_busy(client); } -static void ili251x_hardware_reset(struct device *dev) +static void ili210x_hardware_reset(struct gpio_desc *reset_gpio) { - struct i2c_client *client = to_i2c_client(dev); - struct ili210x *priv = i2c_get_clientdata(client); - /* Reset the controller */ - gpiod_set_value_cansleep(priv->reset_gpio, 1); - usleep_range(10000, 15000); - gpiod_set_value_cansleep(priv->reset_gpio, 0); + gpiod_set_value_cansleep(reset_gpio, 1); + usleep_range(12000, 15000); + gpiod_set_value_cansleep(reset_gpio, 0); msleep(300); } @@ -773,6 +770,7 @@ static ssize_t ili210x_firmware_update_store(struct device *dev, const char *buf, size_t count) { struct i2c_client *client = to_i2c_client(dev); + struct ili210x *priv = i2c_get_clientdata(client); const char *fwname = ILI251X_FW_FILENAME; const struct firmware *fw; u16 ac_end, df_end; @@ -803,7 +801,7 @@ static ssize_t ili210x_firmware_update_store(struct device *dev, dev_dbg(dev, "Firmware update started, firmware=%s\n", fwname); - ili251x_hardware_reset(dev); + ili210x_hardware_reset(priv->reset_gpio); error = ili251x_firmware_reset(client); if (error) @@ -858,7 +856,7 @@ static ssize_t ili210x_firmware_update_store(struct device *dev, error = count; exit: - ili251x_hardware_reset(dev); + ili210x_hardware_reset(priv->reset_gpio); dev_dbg(dev, "Firmware update ended, error=%i\n", error); enable_irq(client->irq); kfree(fwbuf); @@ -951,9 +949,7 @@ static int ili210x_i2c_probe(struct i2c_client *client, if (error) return error; - usleep_range(50, 100); - gpiod_set_value_cansleep(reset_gpio, 0); - msleep(100); + ili210x_hardware_reset(reset_gpio); } priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); diff --git a/drivers/interconnect/core.c b/drivers/interconnect/core.c index 9050ca1f4285..808f6e7a8048 100644 --- a/drivers/interconnect/core.c +++ b/drivers/interconnect/core.c @@ -1087,9 +1087,15 @@ static int of_count_icc_providers(struct device_node *np) { struct device_node *child; int count = 0; + const struct of_device_id __maybe_unused ignore_list[] = { + { .compatible = "qcom,sc7180-ipa-virt" }, + { .compatible = "qcom,sdx55-ipa-virt" }, + {} + }; for_each_available_child_of_node(np, child) { - if (of_property_read_bool(child, "#interconnect-cells")) + if (of_property_read_bool(child, "#interconnect-cells") && + likely(!of_match_node(ignore_list, child))) count++; count += of_count_icc_providers(child); } diff --git a/drivers/interconnect/qcom/sc7180.c b/drivers/interconnect/qcom/sc7180.c index 12d59c36df53..5f7c0f85fa8e 100644 --- a/drivers/interconnect/qcom/sc7180.c +++ b/drivers/interconnect/qcom/sc7180.c @@ -47,7 +47,6 @@ DEFINE_QNODE(qnm_mnoc_sf, SC7180_MASTER_MNOC_SF_MEM_NOC, 1, 32, SC7180_SLAVE_GEM DEFINE_QNODE(qnm_snoc_gc, SC7180_MASTER_SNOC_GC_MEM_NOC, 1, 8, SC7180_SLAVE_LLCC); DEFINE_QNODE(qnm_snoc_sf, SC7180_MASTER_SNOC_SF_MEM_NOC, 1, 16, SC7180_SLAVE_LLCC); DEFINE_QNODE(qxm_gpu, SC7180_MASTER_GFX3D, 2, 32, SC7180_SLAVE_GEM_NOC_SNOC, SC7180_SLAVE_LLCC); -DEFINE_QNODE(ipa_core_master, SC7180_MASTER_IPA_CORE, 1, 8, SC7180_SLAVE_IPA_CORE); DEFINE_QNODE(llcc_mc, SC7180_MASTER_LLCC, 2, 4, SC7180_SLAVE_EBI1); DEFINE_QNODE(qhm_mnoc_cfg, SC7180_MASTER_CNOC_MNOC_CFG, 1, 4, SC7180_SLAVE_SERVICE_MNOC); DEFINE_QNODE(qxm_camnoc_hf0, SC7180_MASTER_CAMNOC_HF0, 2, 32, SC7180_SLAVE_MNOC_HF_MEM_NOC); @@ -129,7 +128,6 @@ DEFINE_QNODE(qhs_mdsp_ms_mpu_cfg, SC7180_SLAVE_MSS_PROC_MS_MPU_CFG, 1, 4); DEFINE_QNODE(qns_gem_noc_snoc, SC7180_SLAVE_GEM_NOC_SNOC, 1, 8, SC7180_MASTER_GEM_NOC_SNOC); DEFINE_QNODE(qns_llcc, SC7180_SLAVE_LLCC, 1, 16, SC7180_MASTER_LLCC); DEFINE_QNODE(srvc_gemnoc, SC7180_SLAVE_SERVICE_GEM_NOC, 1, 4); -DEFINE_QNODE(ipa_core_slave, SC7180_SLAVE_IPA_CORE, 1, 8); DEFINE_QNODE(ebi, SC7180_SLAVE_EBI1, 2, 4); DEFINE_QNODE(qns_mem_noc_hf, SC7180_SLAVE_MNOC_HF_MEM_NOC, 1, 32, SC7180_MASTER_MNOC_HF_MEM_NOC); DEFINE_QNODE(qns_mem_noc_sf, SC7180_SLAVE_MNOC_SF_MEM_NOC, 1, 32, SC7180_MASTER_MNOC_SF_MEM_NOC); @@ -160,7 +158,6 @@ DEFINE_QBCM(bcm_mc0, "MC0", true, &ebi); DEFINE_QBCM(bcm_sh0, "SH0", true, &qns_llcc); DEFINE_QBCM(bcm_mm0, "MM0", false, &qns_mem_noc_hf); DEFINE_QBCM(bcm_ce0, "CE0", false, &qxm_crypto); -DEFINE_QBCM(bcm_ip0, "IP0", false, &ipa_core_slave); DEFINE_QBCM(bcm_cn0, "CN0", true, &qnm_snoc, &xm_qdss_dap, &qhs_a1_noc_cfg, &qhs_a2_noc_cfg, &qhs_ahb2phy0, &qhs_aop, &qhs_aoss, &qhs_boot_rom, &qhs_camera_cfg, &qhs_camera_nrt_throttle_cfg, &qhs_camera_rt_throttle_cfg, &qhs_clk_ctl, &qhs_cpr_cx, &qhs_cpr_mx, &qhs_crypto0_cfg, &qhs_dcc_cfg, &qhs_ddrss_cfg, &qhs_display_cfg, &qhs_display_rt_throttle_cfg, &qhs_display_throttle_cfg, &qhs_glm, &qhs_gpuss_cfg, &qhs_imem_cfg, &qhs_ipa, &qhs_mnoc_cfg, &qhs_mss_cfg, &qhs_npu_cfg, &qhs_npu_dma_throttle_cfg, &qhs_npu_dsp_throttle_cfg, &qhs_pimem_cfg, &qhs_prng, &qhs_qdss_cfg, &qhs_qm_cfg, &qhs_qm_mpu_cfg, &qhs_qup0, &qhs_qup1, &qhs_security, &qhs_snoc_cfg, &qhs_tcsr, &qhs_tlmm_1, &qhs_tlmm_2, &qhs_tlmm_3, &qhs_ufs_mem_cfg, &qhs_usb3, &qhs_venus_cfg, &qhs_venus_throttle_cfg, &qhs_vsense_ctrl_cfg, &srvc_cnoc); DEFINE_QBCM(bcm_mm1, "MM1", false, &qxm_camnoc_hf0_uncomp, &qxm_camnoc_hf1_uncomp, &qxm_camnoc_sf_uncomp, &qhm_mnoc_cfg, &qxm_mdp0, &qxm_rot, &qxm_venus0, &qxm_venus_arm9); DEFINE_QBCM(bcm_sh2, "SH2", false, &acm_sys_tcu); @@ -372,22 +369,6 @@ static struct qcom_icc_desc sc7180_gem_noc = { .num_bcms = ARRAY_SIZE(gem_noc_bcms), }; -static struct qcom_icc_bcm *ipa_virt_bcms[] = { - &bcm_ip0, -}; - -static struct qcom_icc_node *ipa_virt_nodes[] = { - [MASTER_IPA_CORE] = &ipa_core_master, - [SLAVE_IPA_CORE] = &ipa_core_slave, -}; - -static struct qcom_icc_desc sc7180_ipa_virt = { - .nodes = ipa_virt_nodes, - .num_nodes = ARRAY_SIZE(ipa_virt_nodes), - .bcms = ipa_virt_bcms, - .num_bcms = ARRAY_SIZE(ipa_virt_bcms), -}; - static struct qcom_icc_bcm *mc_virt_bcms[] = { &bcm_acv, &bcm_mc0, @@ -519,8 +500,6 @@ static const struct of_device_id qnoc_of_match[] = { .data = &sc7180_dc_noc}, { .compatible = "qcom,sc7180-gem-noc", .data = &sc7180_gem_noc}, - { .compatible = "qcom,sc7180-ipa-virt", - .data = &sc7180_ipa_virt}, { .compatible = "qcom,sc7180-mc-virt", .data = &sc7180_mc_virt}, { .compatible = "qcom,sc7180-mmss-noc", diff --git a/drivers/interconnect/qcom/sdx55.c b/drivers/interconnect/qcom/sdx55.c index 03d604f84cc5..e3ac25a997b7 100644 --- a/drivers/interconnect/qcom/sdx55.c +++ b/drivers/interconnect/qcom/sdx55.c @@ -18,7 +18,6 @@ #include "icc-rpmh.h" #include "sdx55.h" -DEFINE_QNODE(ipa_core_master, SDX55_MASTER_IPA_CORE, 1, 8, SDX55_SLAVE_IPA_CORE); DEFINE_QNODE(llcc_mc, SDX55_MASTER_LLCC, 4, 4, SDX55_SLAVE_EBI_CH0); DEFINE_QNODE(acm_tcu, SDX55_MASTER_TCU_0, 1, 8, SDX55_SLAVE_LLCC, SDX55_SLAVE_MEM_NOC_SNOC, SDX55_SLAVE_MEM_NOC_PCIE_SNOC); DEFINE_QNODE(qnm_snoc_gc, SDX55_MASTER_SNOC_GC_MEM_NOC, 1, 8, SDX55_SLAVE_LLCC); @@ -40,7 +39,6 @@ DEFINE_QNODE(xm_pcie, SDX55_MASTER_PCIE, 1, 8, SDX55_SLAVE_ANOC_SNOC); DEFINE_QNODE(xm_qdss_etr, SDX55_MASTER_QDSS_ETR, 1, 8, SDX55_SLAVE_SNOC_CFG, SDX55_SLAVE_EMAC_CFG, SDX55_SLAVE_USB3, SDX55_SLAVE_AOSS, SDX55_SLAVE_SPMI_FETCHER, SDX55_SLAVE_QDSS_CFG, SDX55_SLAVE_PDM, SDX55_SLAVE_SNOC_MEM_NOC_GC, SDX55_SLAVE_TCSR, SDX55_SLAVE_CNOC_DDRSS, SDX55_SLAVE_SPMI_VGI_COEX, SDX55_SLAVE_QPIC, SDX55_SLAVE_OCIMEM, SDX55_SLAVE_IPA_CFG, SDX55_SLAVE_USB3_PHY_CFG, SDX55_SLAVE_AOP, SDX55_SLAVE_BLSP_1, SDX55_SLAVE_SDCC_1, SDX55_SLAVE_CNOC_MSS, SDX55_SLAVE_PCIE_PARF, SDX55_SLAVE_ECC_CFG, SDX55_SLAVE_AUDIO, SDX55_SLAVE_AOSS, SDX55_SLAVE_PRNG, SDX55_SLAVE_CRYPTO_0_CFG, SDX55_SLAVE_TCU, SDX55_SLAVE_CLK_CTL, SDX55_SLAVE_IMEM_CFG); DEFINE_QNODE(xm_sdc1, SDX55_MASTER_SDCC_1, 1, 8, SDX55_SLAVE_AOSS, SDX55_SLAVE_IPA_CFG, SDX55_SLAVE_ANOC_SNOC, SDX55_SLAVE_AOP, SDX55_SLAVE_AUDIO); DEFINE_QNODE(xm_usb3, SDX55_MASTER_USB3, 1, 8, SDX55_SLAVE_ANOC_SNOC); -DEFINE_QNODE(ipa_core_slave, SDX55_SLAVE_IPA_CORE, 1, 8); DEFINE_QNODE(ebi, SDX55_SLAVE_EBI_CH0, 1, 4); DEFINE_QNODE(qns_llcc, SDX55_SLAVE_LLCC, 1, 16, SDX55_SLAVE_EBI_CH0); DEFINE_QNODE(qns_memnoc_snoc, SDX55_SLAVE_MEM_NOC_SNOC, 1, 8, SDX55_MASTER_MEM_NOC_SNOC); @@ -82,7 +80,6 @@ DEFINE_QNODE(xs_sys_tcu_cfg, SDX55_SLAVE_TCU, 1, 8); DEFINE_QBCM(bcm_mc0, "MC0", true, &ebi); DEFINE_QBCM(bcm_sh0, "SH0", true, &qns_llcc); DEFINE_QBCM(bcm_ce0, "CE0", false, &qxm_crypto); -DEFINE_QBCM(bcm_ip0, "IP0", false, &ipa_core_slave); DEFINE_QBCM(bcm_pn0, "PN0", false, &qhm_snoc_cfg); DEFINE_QBCM(bcm_sh3, "SH3", false, &xm_apps_rdwr); DEFINE_QBCM(bcm_sh4, "SH4", false, &qns_memnoc_snoc, &qns_sys_pcie); @@ -219,22 +216,6 @@ static const struct qcom_icc_desc sdx55_system_noc = { .num_bcms = ARRAY_SIZE(system_noc_bcms), }; -static struct qcom_icc_bcm *ipa_virt_bcms[] = { - &bcm_ip0, -}; - -static struct qcom_icc_node *ipa_virt_nodes[] = { - [MASTER_IPA_CORE] = &ipa_core_master, - [SLAVE_IPA_CORE] = &ipa_core_slave, -}; - -static const struct qcom_icc_desc sdx55_ipa_virt = { - .nodes = ipa_virt_nodes, - .num_nodes = ARRAY_SIZE(ipa_virt_nodes), - .bcms = ipa_virt_bcms, - .num_bcms = ARRAY_SIZE(ipa_virt_bcms), -}; - static const struct of_device_id qnoc_of_match[] = { { .compatible = "qcom,sdx55-mc-virt", .data = &sdx55_mc_virt}, @@ -242,8 +223,6 @@ static const struct of_device_id qnoc_of_match[] = { .data = &sdx55_mem_noc}, { .compatible = "qcom,sdx55-system-noc", .data = &sdx55_system_noc}, - { .compatible = "qcom,sdx55-ipa-virt", - .data = &sdx55_ipa_virt}, { } }; MODULE_DEVICE_TABLE(of, qnoc_of_match); diff --git a/drivers/iommu/apple-dart.c b/drivers/iommu/apple-dart.c index decafb07ad08..8af0242a90d9 100644 --- a/drivers/iommu/apple-dart.c +++ b/drivers/iommu/apple-dart.c @@ -773,6 +773,7 @@ static const struct iommu_ops apple_dart_iommu_ops = { .get_resv_regions = apple_dart_get_resv_regions, .put_resv_regions = generic_iommu_put_resv_regions, .pgsize_bitmap = -1UL, /* Restricted during dart probe */ + .owner = THIS_MODULE, .default_domain_ops = &(const struct iommu_domain_ops) { .attach_dev = apple_dart_attach_dev, .detach_dev = apple_dart_detach_dev, @@ -859,16 +860,15 @@ static int apple_dart_probe(struct platform_device *pdev) dart->dev = dev; spin_lock_init(&dart->lock); - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + dart->regs = devm_platform_get_and_ioremap_resource(pdev, 0, &res); + if (IS_ERR(dart->regs)) + return PTR_ERR(dart->regs); + if (resource_size(res) < 0x4000) { dev_err(dev, "MMIO region too small (%pr)\n", res); return -EINVAL; } - dart->regs = devm_ioremap_resource(dev, res); - if (IS_ERR(dart->regs)) - return PTR_ERR(dart->regs); - dart->irq = platform_get_irq(pdev, 0); if (dart->irq < 0) return -ENODEV; diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c index 22ddd05bbdcd..c623dae1e115 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c @@ -183,7 +183,14 @@ static void arm_smmu_mm_invalidate_range(struct mmu_notifier *mn, { struct arm_smmu_mmu_notifier *smmu_mn = mn_to_smmu(mn); struct arm_smmu_domain *smmu_domain = smmu_mn->domain; - size_t size = end - start + 1; + size_t size; + + /* + * The mm_types defines vm_end as the first byte after the end address, + * different from IOMMU subsystem using the last address of an address + * range. So do a simple translation here by calculating size correctly. + */ + size = end - start; if (!(smmu_domain->smmu->features & ARM_SMMU_FEAT_BTM)) arm_smmu_tlb_inv_range_asid(start, size, smmu_mn->cd->asid, diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-nvidia.c b/drivers/iommu/arm/arm-smmu/arm-smmu-nvidia.c index 01e9b50b10a1..87bf522b9d2e 100644 --- a/drivers/iommu/arm/arm-smmu/arm-smmu-nvidia.c +++ b/drivers/iommu/arm/arm-smmu/arm-smmu-nvidia.c @@ -258,6 +258,34 @@ static void nvidia_smmu_probe_finalize(struct arm_smmu_device *smmu, struct devi dev_name(dev), err); } +static int nvidia_smmu_init_context(struct arm_smmu_domain *smmu_domain, + struct io_pgtable_cfg *pgtbl_cfg, + struct device *dev) +{ + struct arm_smmu_device *smmu = smmu_domain->smmu; + const struct device_node *np = smmu->dev->of_node; + + /* + * Tegra194 and Tegra234 SoCs have the erratum that causes walk cache + * entries to not be invalidated correctly. The problem is that the walk + * cache index generated for IOVA is not same across translation and + * invalidation requests. This is leading to page faults when PMD entry + * is released during unmap and populated with new PTE table during + * subsequent map request. Disabling large page mappings avoids the + * release of PMD entry and avoid translations seeing stale PMD entry in + * walk cache. + * Fix this by limiting the page mappings to PAGE_SIZE on Tegra194 and + * Tegra234. + */ + if (of_device_is_compatible(np, "nvidia,tegra234-smmu") || + of_device_is_compatible(np, "nvidia,tegra194-smmu")) { + smmu->pgsize_bitmap = PAGE_SIZE; + pgtbl_cfg->pgsize_bitmap = smmu->pgsize_bitmap; + } + + return 0; +} + static const struct arm_smmu_impl nvidia_smmu_impl = { .read_reg = nvidia_smmu_read_reg, .write_reg = nvidia_smmu_write_reg, @@ -268,10 +296,12 @@ static const struct arm_smmu_impl nvidia_smmu_impl = { .global_fault = nvidia_smmu_global_fault, .context_fault = nvidia_smmu_context_fault, .probe_finalize = nvidia_smmu_probe_finalize, + .init_context = nvidia_smmu_init_context, }; static const struct arm_smmu_impl nvidia_smmu_single_impl = { .probe_finalize = nvidia_smmu_probe_finalize, + .init_context = nvidia_smmu_init_context, }; struct arm_smmu_device *nvidia_smmu_impl_init(struct arm_smmu_device *smmu) diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index df5c62ecf942..0ea47e17b379 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -1588,7 +1588,8 @@ static void iommu_flush_iotlb_psi(struct intel_iommu *iommu, unsigned long pfn, unsigned int pages, int ih, int map) { - unsigned int mask = ilog2(__roundup_pow_of_two(pages)); + unsigned int aligned_pages = __roundup_pow_of_two(pages); + unsigned int mask = ilog2(aligned_pages); uint64_t addr = (uint64_t)pfn << VTD_PAGE_SHIFT; u16 did = domain->iommu_did[iommu->seq_id]; @@ -1600,10 +1601,30 @@ static void iommu_flush_iotlb_psi(struct intel_iommu *iommu, if (domain_use_first_level(domain)) { qi_flush_piotlb(iommu, did, PASID_RID2PASID, addr, pages, ih); } else { + unsigned long bitmask = aligned_pages - 1; + + /* + * PSI masks the low order bits of the base address. If the + * address isn't aligned to the mask, then compute a mask value + * needed to ensure the target range is flushed. + */ + if (unlikely(bitmask & pfn)) { + unsigned long end_pfn = pfn + pages - 1, shared_bits; + + /* + * Since end_pfn <= pfn + bitmask, the only way bits + * higher than bitmask can differ in pfn and end_pfn is + * by carrying. This means after masking out bitmask, + * high bits starting with the first set bit in + * shared_bits are all equal in both pfn and end_pfn. + */ + shared_bits = ~(pfn ^ end_pfn) & ~bitmask; + mask = shared_bits ? __ffs(shared_bits) : BITS_PER_LONG; + } + /* * Fallback to domain selective flush if no PSI support or - * the size is too big. PSI requires page size to be 2 ^ x, - * and the base address is naturally aligned to the size. + * the size is too big. */ if (!cap_pgsel_inv(iommu->cap) || mask > cap_max_amask_val(iommu->cap)) diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c index 23a38763c1d1..7ee37d996e15 100644 --- a/drivers/iommu/intel/svm.c +++ b/drivers/iommu/intel/svm.c @@ -757,6 +757,10 @@ bad_req: goto bad_req; } + /* Drop Stop Marker message. No need for a response. */ + if (unlikely(req->lpig && !req->rd_req && !req->wr_req)) + goto prq_advance; + if (!svm || svm->pasid != req->pasid) { /* * It can't go away, because the driver is not permitted diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index f2c45b85b9fc..857d4c2fd1a2 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -506,6 +506,13 @@ int iommu_get_group_resv_regions(struct iommu_group *group, list_for_each_entry(device, &group->devices, list) { struct list_head dev_resv_regions; + /* + * Non-API groups still expose reserved_regions in sysfs, + * so filter out calls that get here that way. + */ + if (!device->dev->iommu) + break; + INIT_LIST_HEAD(&dev_resv_regions); iommu_get_resv_regions(device->dev, &dev_resv_regions); ret = iommu_insert_device_resv_regions(&dev_resv_regions, head); @@ -3019,7 +3026,7 @@ static ssize_t iommu_group_store_type(struct iommu_group *group, if (!capable(CAP_SYS_ADMIN) || !capable(CAP_SYS_RAWIO)) return -EACCES; - if (WARN_ON(!group)) + if (WARN_ON(!group) || !group->default_domain) return -EINVAL; if (sysfs_streq(buf, "identity")) diff --git a/drivers/iommu/omap-iommu.c b/drivers/iommu/omap-iommu.c index 4aab631ef517..d9cf2820c02e 100644 --- a/drivers/iommu/omap-iommu.c +++ b/drivers/iommu/omap-iommu.c @@ -1661,7 +1661,7 @@ static struct iommu_device *omap_iommu_probe_device(struct device *dev) num_iommus = of_property_count_elems_of_size(dev->of_node, "iommus", sizeof(phandle)); if (num_iommus < 0) - return 0; + return ERR_PTR(-ENODEV); arch_data = kcalloc(num_iommus + 1, sizeof(*arch_data), GFP_KERNEL); if (!arch_data) diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig index 680d2fcf2686..135c156673a7 100644 --- a/drivers/irqchip/Kconfig +++ b/drivers/irqchip/Kconfig @@ -257,6 +257,18 @@ config ST_IRQCHIP help Enables SysCfg Controlled IRQs on STi based platforms. +config SUN4I_INTC + bool + +config SUN6I_R_INTC + bool + select IRQ_DOMAIN_HIERARCHY + select IRQ_FASTEOI_HIERARCHY_HANDLERS + +config SUNXI_NMI_INTC + bool + select GENERIC_IRQ_CHIP + config TB10X_IRQC bool select IRQ_DOMAIN @@ -433,6 +445,7 @@ config QCOM_PDC config QCOM_MPM tristate "QCOM MPM" depends on ARCH_QCOM + depends on MAILBOX select IRQ_DOMAIN_HIERARCHY help MSM Power Manager driver to manage and configure wakeup diff --git a/drivers/irqchip/Makefile b/drivers/irqchip/Makefile index 160a1d8ceaa9..9b1ffb0f98cc 100644 --- a/drivers/irqchip/Makefile +++ b/drivers/irqchip/Makefile @@ -23,9 +23,9 @@ obj-$(CONFIG_OMPIC) += irq-ompic.o obj-$(CONFIG_OR1K_PIC) += irq-or1k-pic.o obj-$(CONFIG_ORION_IRQCHIP) += irq-orion.o obj-$(CONFIG_OMAP_IRQCHIP) += irq-omap-intc.o -obj-$(CONFIG_ARCH_SUNXI) += irq-sun4i.o -obj-$(CONFIG_ARCH_SUNXI) += irq-sun6i-r.o -obj-$(CONFIG_ARCH_SUNXI) += irq-sunxi-nmi.o +obj-$(CONFIG_SUN4I_INTC) += irq-sun4i.o +obj-$(CONFIG_SUN6I_R_INTC) += irq-sun6i-r.o +obj-$(CONFIG_SUNXI_NMI_INTC) += irq-sunxi-nmi.o obj-$(CONFIG_ARCH_SPEAR3XX) += spear-shirq.o obj-$(CONFIG_ARM_GIC) += irq-gic.o irq-gic-common.o obj-$(CONFIG_ARM_GIC_PM) += irq-gic-pm.o diff --git a/drivers/irqchip/irq-armada-370-xp.c b/drivers/irqchip/irq-armada-370-xp.c index 5b8d571c041d..ee18eb3e72b7 100644 --- a/drivers/irqchip/irq-armada-370-xp.c +++ b/drivers/irqchip/irq-armada-370-xp.c @@ -209,15 +209,29 @@ static struct msi_domain_info armada_370_xp_msi_domain_info = { static void armada_370_xp_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) { + unsigned int cpu = cpumask_first(irq_data_get_effective_affinity_mask(data)); + msg->address_lo = lower_32_bits(msi_doorbell_addr); msg->address_hi = upper_32_bits(msi_doorbell_addr); - msg->data = 0xf00 | (data->hwirq + PCI_MSI_DOORBELL_START); + msg->data = BIT(cpu + 8) | (data->hwirq + PCI_MSI_DOORBELL_START); } static int armada_370_xp_msi_set_affinity(struct irq_data *irq_data, const struct cpumask *mask, bool force) { - return -EINVAL; + unsigned int cpu; + + if (!force) + cpu = cpumask_any_and(mask, cpu_online_mask); + else + cpu = cpumask_first(mask); + + if (cpu >= nr_cpu_ids) + return -EINVAL; + + irq_data_update_effective_affinity(irq_data, cpumask_of(cpu)); + + return IRQ_SET_MASK_OK; } static struct irq_chip armada_370_xp_msi_bottom_irq_chip = { @@ -264,11 +278,21 @@ static const struct irq_domain_ops armada_370_xp_msi_domain_ops = { .free = armada_370_xp_msi_free, }; -static int armada_370_xp_msi_init(struct device_node *node, - phys_addr_t main_int_phys_base) +static void armada_370_xp_msi_reenable_percpu(void) { u32 reg; + /* Enable MSI doorbell mask and combined cpu local interrupt */ + reg = readl(per_cpu_int_base + ARMADA_370_XP_IN_DRBEL_MSK_OFFS) + | PCI_MSI_DOORBELL_MASK; + writel(reg, per_cpu_int_base + ARMADA_370_XP_IN_DRBEL_MSK_OFFS); + /* Unmask local doorbell interrupt */ + writel(1, per_cpu_int_base + ARMADA_370_XP_INT_CLEAR_MASK_OFFS); +} + +static int armada_370_xp_msi_init(struct device_node *node, + phys_addr_t main_int_phys_base) +{ msi_doorbell_addr = main_int_phys_base + ARMADA_370_XP_SW_TRIG_INT_OFFS; @@ -287,18 +311,13 @@ static int armada_370_xp_msi_init(struct device_node *node, return -ENOMEM; } - reg = readl(per_cpu_int_base + ARMADA_370_XP_IN_DRBEL_MSK_OFFS) - | PCI_MSI_DOORBELL_MASK; - - writel(reg, per_cpu_int_base + - ARMADA_370_XP_IN_DRBEL_MSK_OFFS); - - /* Unmask IPI interrupt */ - writel(1, per_cpu_int_base + ARMADA_370_XP_INT_CLEAR_MASK_OFFS); + armada_370_xp_msi_reenable_percpu(); return 0; } #else +static void armada_370_xp_msi_reenable_percpu(void) {} + static inline int armada_370_xp_msi_init(struct device_node *node, phys_addr_t main_int_phys_base) { @@ -308,7 +327,16 @@ static inline int armada_370_xp_msi_init(struct device_node *node, static void armada_xp_mpic_perf_init(void) { - unsigned long cpuid = cpu_logical_map(smp_processor_id()); + unsigned long cpuid; + + /* + * This Performance Counter Overflow interrupt is specific for + * Armada 370 and XP. It is not available on Armada 375, 38x and 39x. + */ + if (!of_machine_is_compatible("marvell,armada-370-xp")) + return; + + cpuid = cpu_logical_map(smp_processor_id()); /* Enable Performance Counter Overflow interrupts */ writel(ARMADA_370_XP_INT_CAUSE_PERF(cpuid), @@ -501,6 +529,8 @@ static void armada_xp_mpic_reenable_percpu(void) } ipi_resume(); + + armada_370_xp_msi_reenable_percpu(); } static int armada_xp_mpic_starting_cpu(unsigned int cpu) diff --git a/drivers/irqchip/irq-aspeed-i2c-ic.c b/drivers/irqchip/irq-aspeed-i2c-ic.c index a47db16ff960..9c9fc3e2967e 100644 --- a/drivers/irqchip/irq-aspeed-i2c-ic.c +++ b/drivers/irqchip/irq-aspeed-i2c-ic.c @@ -77,8 +77,8 @@ static int __init aspeed_i2c_ic_of_init(struct device_node *node, } i2c_ic->parent_irq = irq_of_parse_and_map(node, 0); - if (i2c_ic->parent_irq < 0) { - ret = i2c_ic->parent_irq; + if (!i2c_ic->parent_irq) { + ret = -EINVAL; goto err_iounmap; } diff --git a/drivers/irqchip/irq-aspeed-scu-ic.c b/drivers/irqchip/irq-aspeed-scu-ic.c index 18b77c3e6db4..279e92cf0b16 100644 --- a/drivers/irqchip/irq-aspeed-scu-ic.c +++ b/drivers/irqchip/irq-aspeed-scu-ic.c @@ -157,8 +157,8 @@ static int aspeed_scu_ic_of_init_common(struct aspeed_scu_ic *scu_ic, } irq = irq_of_parse_and_map(node, 0); - if (irq < 0) { - rc = irq; + if (!irq) { + rc = -EINVAL; goto err; } diff --git a/drivers/irqchip/irq-bcm6345-l1.c b/drivers/irqchip/irq-bcm6345-l1.c index fd079215c17f..142a7431745f 100644 --- a/drivers/irqchip/irq-bcm6345-l1.c +++ b/drivers/irqchip/irq-bcm6345-l1.c @@ -315,7 +315,7 @@ static int __init bcm6345_l1_of_init(struct device_node *dn, cpumask_set_cpu(idx, &intc->cpumask); } - if (!cpumask_weight(&intc->cpumask)) { + if (cpumask_empty(&intc->cpumask)) { ret = -ENODEV; goto out_free; } diff --git a/drivers/irqchip/irq-csky-apb-intc.c b/drivers/irqchip/irq-csky-apb-intc.c index d36f536506ba..42d8a2438ebc 100644 --- a/drivers/irqchip/irq-csky-apb-intc.c +++ b/drivers/irqchip/irq-csky-apb-intc.c @@ -136,11 +136,11 @@ static inline bool handle_irq_perbit(struct pt_regs *regs, u32 hwirq, u32 irq_base) { if (hwirq == 0) - return 0; + return false; generic_handle_domain_irq(root_domain, irq_base + __fls(hwirq)); - return 1; + return true; } /* gx6605s 64 irqs interrupt controller */ diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index cd772973114a..5ff09de6c48f 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -1624,7 +1624,7 @@ static int its_select_cpu(struct irq_data *d, cpu = cpumask_pick_least_loaded(d, tmpmask); } else { - cpumask_and(tmpmask, irq_data_get_affinity_mask(d), cpu_online_mask); + cpumask_copy(tmpmask, aff_mask); /* If we cannot cross sockets, limit the search to that node */ if ((its_dev->its->flags & ITS_FLAGS_WORKAROUND_CAVIUM_23144) && @@ -3011,18 +3011,12 @@ static int __init allocate_lpi_tables(void) return 0; } -static u64 its_clear_vpend_valid(void __iomem *vlpi_base, u64 clr, u64 set) +static u64 read_vpend_dirty_clear(void __iomem *vlpi_base) { u32 count = 1000000; /* 1s! */ bool clean; u64 val; - val = gicr_read_vpendbaser(vlpi_base + GICR_VPENDBASER); - val &= ~GICR_VPENDBASER_Valid; - val &= ~clr; - val |= set; - gicr_write_vpendbaser(val, vlpi_base + GICR_VPENDBASER); - do { val = gicr_read_vpendbaser(vlpi_base + GICR_VPENDBASER); clean = !(val & GICR_VPENDBASER_Dirty); @@ -3033,10 +3027,26 @@ static u64 its_clear_vpend_valid(void __iomem *vlpi_base, u64 clr, u64 set) } } while (!clean && count); - if (unlikely(val & GICR_VPENDBASER_Dirty)) { + if (unlikely(!clean)) pr_err_ratelimited("ITS virtual pending table not cleaning\n"); + + return val; +} + +static u64 its_clear_vpend_valid(void __iomem *vlpi_base, u64 clr, u64 set) +{ + u64 val; + + /* Make sure we wait until the RD is done with the initial scan */ + val = read_vpend_dirty_clear(vlpi_base); + val &= ~GICR_VPENDBASER_Valid; + val &= ~clr; + val |= set; + gicr_write_vpendbaser(val, vlpi_base + GICR_VPENDBASER); + + val = read_vpend_dirty_clear(vlpi_base); + if (unlikely(val & GICR_VPENDBASER_Dirty)) val |= GICR_VPENDBASER_PendingLast; - } return val; } diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c index 0efe1a9a9f3b..2be8dea6b6b0 100644 --- a/drivers/irqchip/irq-gic-v3.c +++ b/drivers/irqchip/irq-gic-v3.c @@ -206,11 +206,11 @@ static inline void __iomem *gic_dist_base(struct irq_data *d) } } -static void gic_do_wait_for_rwp(void __iomem *base) +static void gic_do_wait_for_rwp(void __iomem *base, u32 bit) { u32 count = 1000000; /* 1s! */ - while (readl_relaxed(base + GICD_CTLR) & GICD_CTLR_RWP) { + while (readl_relaxed(base + GICD_CTLR) & bit) { count--; if (!count) { pr_err_ratelimited("RWP timeout, gone fishing\n"); @@ -224,13 +224,13 @@ static void gic_do_wait_for_rwp(void __iomem *base) /* Wait for completion of a distributor change */ static void gic_dist_wait_for_rwp(void) { - gic_do_wait_for_rwp(gic_data.dist_base); + gic_do_wait_for_rwp(gic_data.dist_base, GICD_CTLR_RWP); } /* Wait for completion of a redistributor change */ static void gic_redist_wait_for_rwp(void) { - gic_do_wait_for_rwp(gic_data_rdist_rd_base()); + gic_do_wait_for_rwp(gic_data_rdist_rd_base(), GICR_CTLR_RWP); } #ifdef CONFIG_ARM64 @@ -352,28 +352,27 @@ static int gic_peek_irq(struct irq_data *d, u32 offset) static void gic_poke_irq(struct irq_data *d, u32 offset) { - void (*rwp_wait)(void); void __iomem *base; u32 index, mask; offset = convert_offset_index(d, offset, &index); mask = 1 << (index % 32); - if (gic_irq_in_rdist(d)) { + if (gic_irq_in_rdist(d)) base = gic_data_rdist_sgi_base(); - rwp_wait = gic_redist_wait_for_rwp; - } else { + else base = gic_data.dist_base; - rwp_wait = gic_dist_wait_for_rwp; - } writel_relaxed(mask, base + offset + (index / 32) * 4); - rwp_wait(); } static void gic_mask_irq(struct irq_data *d) { gic_poke_irq(d, GICD_ICENABLER); + if (gic_irq_in_rdist(d)) + gic_redist_wait_for_rwp(); + else + gic_dist_wait_for_rwp(); } static void gic_eoimode1_mask_irq(struct irq_data *d) @@ -420,7 +419,11 @@ static int gic_irq_set_irqchip_state(struct irq_data *d, break; case IRQCHIP_STATE_MASKED: - reg = val ? GICD_ICENABLER : GICD_ISENABLER; + if (val) { + gic_mask_irq(d); + return 0; + } + reg = GICD_ISENABLER; break; default: @@ -556,7 +559,8 @@ static void gic_irq_nmi_teardown(struct irq_data *d) static void gic_eoi_irq(struct irq_data *d) { - gic_write_eoir(gic_irq(d)); + write_gicreg(gic_irq(d), ICC_EOIR1_EL1); + isb(); } static void gic_eoimode1_eoi_irq(struct irq_data *d) @@ -574,7 +578,6 @@ static int gic_set_type(struct irq_data *d, unsigned int type) { enum gic_intid_range range; unsigned int irq = gic_irq(d); - void (*rwp_wait)(void); void __iomem *base; u32 offset, index; int ret; @@ -590,17 +593,14 @@ static int gic_set_type(struct irq_data *d, unsigned int type) type != IRQ_TYPE_LEVEL_HIGH && type != IRQ_TYPE_EDGE_RISING) return -EINVAL; - if (gic_irq_in_rdist(d)) { + if (gic_irq_in_rdist(d)) base = gic_data_rdist_sgi_base(); - rwp_wait = gic_redist_wait_for_rwp; - } else { + else base = gic_data.dist_base; - rwp_wait = gic_dist_wait_for_rwp; - } offset = convert_offset_index(d, GICD_ICFGR, &index); - ret = gic_configure_irq(index, type, base + offset, rwp_wait); + ret = gic_configure_irq(index, type, base + offset, NULL); if (ret && (range == PPI_RANGE || range == EPPI_RANGE)) { /* Misconfigured PPIs are usually not fatal */ pr_warn("GIC: PPI INTID%d is secure or misconfigured\n", irq); @@ -640,82 +640,101 @@ static void gic_deactivate_unhandled(u32 irqnr) if (irqnr < 8192) gic_write_dir(irqnr); } else { - gic_write_eoir(irqnr); + write_gicreg(irqnr, ICC_EOIR1_EL1); + isb(); } } -static inline void gic_handle_nmi(u32 irqnr, struct pt_regs *regs) +/* + * Follow a read of the IAR with any HW maintenance that needs to happen prior + * to invoking the relevant IRQ handler. We must do two things: + * + * (1) Ensure instruction ordering between a read of IAR and subsequent + * instructions in the IRQ handler using an ISB. + * + * It is possible for the IAR to report an IRQ which was signalled *after* + * the CPU took an IRQ exception as multiple interrupts can race to be + * recognized by the GIC, earlier interrupts could be withdrawn, and/or + * later interrupts could be prioritized by the GIC. + * + * For devices which are tightly coupled to the CPU, such as PMUs, a + * context synchronization event is necessary to ensure that system + * register state is not stale, as these may have been indirectly written + * *after* exception entry. + * + * (2) Deactivate the interrupt when EOI mode 1 is in use. + */ +static inline void gic_complete_ack(u32 irqnr) { - bool irqs_enabled = interrupts_enabled(regs); - int err; - - if (irqs_enabled) - nmi_enter(); - if (static_branch_likely(&supports_deactivate_key)) - gic_write_eoir(irqnr); - /* - * Leave the PSR.I bit set to prevent other NMIs to be - * received while handling this one. - * PSR.I will be restored when we ERET to the - * interrupted context. - */ - err = generic_handle_domain_nmi(gic_data.domain, irqnr); - if (err) - gic_deactivate_unhandled(irqnr); + write_gicreg(irqnr, ICC_EOIR1_EL1); - if (irqs_enabled) - nmi_exit(); + isb(); } -static u32 do_read_iar(struct pt_regs *regs) +static bool gic_rpr_is_nmi_prio(void) { - u32 iar; + if (!gic_supports_nmi()) + return false; - if (gic_supports_nmi() && unlikely(!interrupts_enabled(regs))) { - u64 pmr; + return unlikely(gic_read_rpr() == GICD_INT_RPR_PRI(GICD_INT_NMI_PRI)); +} - /* - * We were in a context with IRQs disabled. However, the - * entry code has set PMR to a value that allows any - * interrupt to be acknowledged, and not just NMIs. This can - * lead to surprising effects if the NMI has been retired in - * the meantime, and that there is an IRQ pending. The IRQ - * would then be taken in NMI context, something that nobody - * wants to debug twice. - * - * Until we sort this, drop PMR again to a level that will - * actually only allow NMIs before reading IAR, and then - * restore it to what it was. - */ - pmr = gic_read_pmr(); - gic_pmr_mask_irqs(); - isb(); +static bool gic_irqnr_is_special(u32 irqnr) +{ + return irqnr >= 1020 && irqnr <= 1023; +} + +static void __gic_handle_irq(u32 irqnr, struct pt_regs *regs) +{ + if (gic_irqnr_is_special(irqnr)) + return; - iar = gic_read_iar(); + gic_complete_ack(irqnr); - gic_write_pmr(pmr); - } else { - iar = gic_read_iar(); + if (generic_handle_domain_irq(gic_data.domain, irqnr)) { + WARN_ONCE(true, "Unexpected interrupt (irqnr %u)\n", irqnr); + gic_deactivate_unhandled(irqnr); } +} - return iar; +static void __gic_handle_nmi(u32 irqnr, struct pt_regs *regs) +{ + if (gic_irqnr_is_special(irqnr)) + return; + + gic_complete_ack(irqnr); + + if (generic_handle_domain_nmi(gic_data.domain, irqnr)) { + WARN_ONCE(true, "Unexpected pseudo-NMI (irqnr %u)\n", irqnr); + gic_deactivate_unhandled(irqnr); + } } -static asmlinkage void __exception_irq_entry gic_handle_irq(struct pt_regs *regs) +/* + * An exception has been taken from a context with IRQs enabled, and this could + * be an IRQ or an NMI. + * + * The entry code called us with DAIF.IF set to keep NMIs masked. We must clear + * DAIF.IF (and update ICC_PMR_EL1 to mask regular IRQs) prior to returning, + * after handling any NMI but before handling any IRQ. + * + * The entry code has performed IRQ entry, and if an NMI is detected we must + * perform NMI entry/exit around invoking the handler. + */ +static void __gic_handle_irq_from_irqson(struct pt_regs *regs) { + bool is_nmi; u32 irqnr; - irqnr = do_read_iar(regs); + irqnr = gic_read_iar(); - /* Check for special IDs first */ - if ((irqnr >= 1020 && irqnr <= 1023)) - return; + is_nmi = gic_rpr_is_nmi_prio(); - if (gic_supports_nmi() && - unlikely(gic_read_rpr() == GICD_INT_RPR_PRI(GICD_INT_NMI_PRI))) { - gic_handle_nmi(irqnr, regs); - return; + if (is_nmi) { + nmi_enter(); + __gic_handle_nmi(irqnr, regs); + nmi_exit(); } if (gic_prio_masking_enabled()) { @@ -723,15 +742,52 @@ static asmlinkage void __exception_irq_entry gic_handle_irq(struct pt_regs *regs gic_arch_enable_irqs(); } - if (static_branch_likely(&supports_deactivate_key)) - gic_write_eoir(irqnr); - else - isb(); + if (!is_nmi) + __gic_handle_irq(irqnr, regs); +} - if (generic_handle_domain_irq(gic_data.domain, irqnr)) { - WARN_ONCE(true, "Unexpected interrupt received!\n"); - gic_deactivate_unhandled(irqnr); - } +/* + * An exception has been taken from a context with IRQs disabled, which can only + * be an NMI. + * + * The entry code called us with DAIF.IF set to keep NMIs masked. We must leave + * DAIF.IF (and ICC_PMR_EL1) unchanged. + * + * The entry code has performed NMI entry. + */ +static void __gic_handle_irq_from_irqsoff(struct pt_regs *regs) +{ + u64 pmr; + u32 irqnr; + + /* + * We were in a context with IRQs disabled. However, the + * entry code has set PMR to a value that allows any + * interrupt to be acknowledged, and not just NMIs. This can + * lead to surprising effects if the NMI has been retired in + * the meantime, and that there is an IRQ pending. The IRQ + * would then be taken in NMI context, something that nobody + * wants to debug twice. + * + * Until we sort this, drop PMR again to a level that will + * actually only allow NMIs before reading IAR, and then + * restore it to what it was. + */ + pmr = gic_read_pmr(); + gic_pmr_mask_irqs(); + isb(); + irqnr = gic_read_iar(); + gic_write_pmr(pmr); + + __gic_handle_nmi(irqnr, regs); +} + +static asmlinkage void __exception_irq_entry gic_handle_irq(struct pt_regs *regs) +{ + if (unlikely(gic_supports_nmi() && !interrupts_enabled(regs))) + __gic_handle_irq_from_irqsoff(regs); + else + __gic_handle_irq_from_irqson(regs); } static u32 gic_get_pribits(void) @@ -807,8 +863,8 @@ static void __init gic_dist_init(void) for (i = 0; i < GIC_ESPI_NR; i += 4) writel_relaxed(GICD_INT_DEF_PRI_X4, base + GICD_IPRIORITYRnE + i); - /* Now do the common stuff, and wait for the distributor to drain */ - gic_dist_config(base, GIC_LINE_NR, gic_dist_wait_for_rwp); + /* Now do the common stuff */ + gic_dist_config(base, GIC_LINE_NR, NULL); val = GICD_CTLR_ARE_NS | GICD_CTLR_ENABLE_G1A | GICD_CTLR_ENABLE_G1; if (gic_data.rdists.gicd_typer2 & GICD_TYPER2_nASSGIcap) { @@ -816,8 +872,9 @@ static void __init gic_dist_init(void) val |= GICD_CTLR_nASSGIreq; } - /* Enable distributor with ARE, Group1 */ + /* Enable distributor with ARE, Group1, and wait for it to drain */ writel_relaxed(val, base + GICD_CTLR); + gic_dist_wait_for_rwp(); /* * Set all global interrupts to the boot CPU only. ARE must be @@ -919,6 +976,7 @@ static int __gic_update_rdist_properties(struct redist_region *region, void __iomem *ptr) { u64 typer = gic_read_typer(ptr + GICR_TYPER); + u32 ctlr = readl_relaxed(ptr + GICR_CTLR); /* Boot-time cleanip */ if ((typer & GICR_TYPER_VLPIS) && (typer & GICR_TYPER_RVPEID)) { @@ -938,9 +996,18 @@ static int __gic_update_rdist_properties(struct redist_region *region, gic_data.rdists.has_vlpis &= !!(typer & GICR_TYPER_VLPIS); - /* RVPEID implies some form of DirectLPI, no matter what the doc says... :-/ */ + /* + * TYPER.RVPEID implies some form of DirectLPI, no matter what the + * doc says... :-/ And CTLR.IR implies another subset of DirectLPI + * that the ITS driver can make use of for LPIs (and not VLPIs). + * + * These are 3 different ways to express the same thing, depending + * on the revision of the architecture and its relaxations over + * time. Just group them under the 'direct_lpi' banner. + */ gic_data.rdists.has_rvpeid &= !!(typer & GICR_TYPER_RVPEID); gic_data.rdists.has_direct_lpi &= (!!(typer & GICR_TYPER_DirectLPIS) | + !!(ctlr & GICR_CTLR_IR) | gic_data.rdists.has_rvpeid); gic_data.rdists.has_vpend_valid_dirty &= !!(typer & GICR_TYPER_DIRTY); @@ -962,7 +1029,11 @@ static void gic_update_rdist_properties(void) gic_iterate_rdists(__gic_update_rdist_properties); if (WARN_ON(gic_data.ppi_nr == UINT_MAX)) gic_data.ppi_nr = 0; - pr_info("%d PPIs implemented\n", gic_data.ppi_nr); + pr_info("GICv3 features: %d PPIs%s%s\n", + gic_data.ppi_nr, + gic_data.has_rss ? ", RSS" : "", + gic_data.rdists.has_direct_lpi ? ", DirectLPI" : ""); + if (gic_data.rdists.has_vlpis) pr_info("GICv4 features: %s%s%s\n", gic_data.rdists.has_direct_lpi ? "DirectLPI " : "", @@ -1284,8 +1355,6 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val, */ if (enabled) gic_unmask_irq(d); - else - gic_dist_wait_for_rwp(); irq_data_update_effective_affinity(d, cpumask_of(cpu)); @@ -1466,6 +1535,12 @@ static int gic_irq_domain_translate(struct irq_domain *d, if(fwspec->param_count != 2) return -EINVAL; + if (fwspec->param[0] < 16) { + pr_err(FW_BUG "Illegal GSI%d translation request\n", + fwspec->param[0]); + return -EINVAL; + } + *hwirq = fwspec->param[0]; *type = fwspec->param[1]; @@ -1797,8 +1872,6 @@ static int __init gic_init_bases(void __iomem *dist_base, irq_domain_update_bus_token(gic_data.domain, DOMAIN_BUS_WIRED); gic_data.has_rss = !!(typer & GICD_TYPER_RSS); - pr_info("Distributor has %sRange Selector support\n", - gic_data.has_rss ? "" : "no "); if (typer & GICD_TYPER_MBIS) { err = mbi_init(handle, gic_data.domain); @@ -1974,10 +2047,10 @@ static int __init gic_of_init(struct device_node *node, struct device_node *pare u32 nr_redist_regions; int err, i; - dist_base = of_iomap(node, 0); - if (!dist_base) { + dist_base = of_io_request_and_map(node, 0, "GICD"); + if (IS_ERR(dist_base)) { pr_err("%pOF: unable to map gic dist registers\n", node); - return -ENXIO; + return PTR_ERR(dist_base); } err = gic_validate_dist_version(dist_base); @@ -2001,8 +2074,8 @@ static int __init gic_of_init(struct device_node *node, struct device_node *pare int ret; ret = of_address_to_resource(node, 1 + i, &res); - rdist_regs[i].redist_base = of_iomap(node, 1 + i); - if (ret || !rdist_regs[i].redist_base) { + rdist_regs[i].redist_base = of_io_request_and_map(node, 1 + i, "GICR"); + if (ret || IS_ERR(rdist_regs[i].redist_base)) { pr_err("%pOF: couldn't map region %d\n", node, i); err = -ENODEV; goto out_unmap_rdist; @@ -2028,7 +2101,7 @@ static int __init gic_of_init(struct device_node *node, struct device_node *pare out_unmap_rdist: for (i = 0; i < nr_redist_regions; i++) - if (rdist_regs[i].redist_base) + if (rdist_regs[i].redist_base && !IS_ERR(rdist_regs[i].redist_base)) iounmap(rdist_regs[i].redist_base); kfree(rdist_regs); out_unmap_dist: @@ -2075,6 +2148,7 @@ gic_acpi_parse_madt_redist(union acpi_subtable_headers *header, pr_err("Couldn't map GICR region @%llx\n", redist->base_address); return -ENOMEM; } + request_mem_region(redist->base_address, redist->length, "GICR"); gic_acpi_register_redist(redist->base_address, redist_base); return 0; @@ -2097,6 +2171,7 @@ gic_acpi_parse_madt_gicc(union acpi_subtable_headers *header, redist_base = ioremap(gicc->gicr_base_address, size); if (!redist_base) return -ENOMEM; + request_mem_region(gicc->gicr_base_address, size, "GICR"); gic_acpi_register_redist(gicc->gicr_base_address, redist_base); return 0; @@ -2298,6 +2373,7 @@ gic_acpi_init(union acpi_subtable_headers *header, const unsigned long end) pr_err("Unable to map GICD registers\n"); return -ENOMEM; } + request_mem_region(dist->base_address, ACPI_GICV3_DIST_MEM_SIZE, "GICD"); err = gic_validate_dist_version(acpi_data.dist_base); if (err) { diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c index 58ba835bee1f..820404cb56bc 100644 --- a/drivers/irqchip/irq-gic.c +++ b/drivers/irqchip/irq-gic.c @@ -1115,7 +1115,8 @@ static int gic_irq_domain_translate(struct irq_domain *d, *type = fwspec->param[2] & IRQ_TYPE_SENSE_MASK; /* Make it clear that broken DTs are... broken */ - WARN_ON(*type == IRQ_TYPE_NONE); + WARN(*type == IRQ_TYPE_NONE, + "HW irq %ld has invalid type\n", *hwirq); return 0; } @@ -1123,10 +1124,17 @@ static int gic_irq_domain_translate(struct irq_domain *d, if(fwspec->param_count != 2) return -EINVAL; + if (fwspec->param[0] < 16) { + pr_err(FW_BUG "Illegal GSI%d translation request\n", + fwspec->param[0]); + return -EINVAL; + } + *hwirq = fwspec->param[0]; *type = fwspec->param[1]; - WARN_ON(*type == IRQ_TYPE_NONE); + WARN(*type == IRQ_TYPE_NONE, + "HW irq %ld has invalid type\n", *hwirq); return 0; } diff --git a/drivers/irqchip/irq-imx-irqsteer.c b/drivers/irqchip/irq-imx-irqsteer.c index 8d91a02593fc..96230a04ec23 100644 --- a/drivers/irqchip/irq-imx-irqsteer.c +++ b/drivers/irqchip/irq-imx-irqsteer.c @@ -12,6 +12,7 @@ #include <linux/kernel.h> #include <linux/of_irq.h> #include <linux/of_platform.h> +#include <linux/pm_runtime.h> #include <linux/spinlock.h> #define CTRL_STRIDE_OFF(_t, _r) (_t * 4 * _r) @@ -70,7 +71,7 @@ static void imx_irqsteer_irq_mask(struct irq_data *d) raw_spin_unlock_irqrestore(&data->lock, flags); } -static struct irq_chip imx_irqsteer_irq_chip = { +static const struct irq_chip imx_irqsteer_irq_chip = { .name = "irqsteer", .irq_mask = imx_irqsteer_irq_mask, .irq_unmask = imx_irqsteer_irq_unmask, @@ -175,7 +176,7 @@ static int imx_irqsteer_probe(struct platform_device *pdev) data->irq_count = DIV_ROUND_UP(irqs_num, 64); data->reg_num = irqs_num / 32; - if (IS_ENABLED(CONFIG_PM_SLEEP)) { + if (IS_ENABLED(CONFIG_PM)) { data->saved_reg = devm_kzalloc(&pdev->dev, sizeof(u32) * data->reg_num, GFP_KERNEL); @@ -199,6 +200,7 @@ static int imx_irqsteer_probe(struct platform_device *pdev) ret = -ENOMEM; goto out; } + irq_domain_set_pm_device(data->domain, &pdev->dev); if (!data->irq_count || data->irq_count > CHAN_MAX_OUTPUT_INT) { ret = -EINVAL; @@ -219,6 +221,9 @@ static int imx_irqsteer_probe(struct platform_device *pdev) platform_set_drvdata(pdev, data); + pm_runtime_set_active(&pdev->dev); + pm_runtime_enable(&pdev->dev); + return 0; out: clk_disable_unprepare(data->ipg_clk); @@ -241,7 +246,7 @@ static int imx_irqsteer_remove(struct platform_device *pdev) return 0; } -#ifdef CONFIG_PM_SLEEP +#ifdef CONFIG_PM static void imx_irqsteer_save_regs(struct irqsteer_data *data) { int i; @@ -288,7 +293,10 @@ static int imx_irqsteer_resume(struct device *dev) #endif static const struct dev_pm_ops imx_irqsteer_pm_ops = { - SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(imx_irqsteer_suspend, imx_irqsteer_resume) + SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, + pm_runtime_force_resume) + SET_RUNTIME_PM_OPS(imx_irqsteer_suspend, + imx_irqsteer_resume, NULL) }; static const struct of_device_id imx_irqsteer_dt_ids[] = { diff --git a/drivers/irqchip/irq-qcom-mpm.c b/drivers/irqchip/irq-qcom-mpm.c index eea5a753618c..d30614661eea 100644 --- a/drivers/irqchip/irq-qcom-mpm.c +++ b/drivers/irqchip/irq-qcom-mpm.c @@ -375,7 +375,7 @@ static int qcom_mpm_init(struct device_node *np, struct device_node *parent) raw_spin_lock_init(&priv->lock); priv->base = devm_platform_ioremap_resource(pdev, 0); - if (!priv->base) + if (IS_ERR(priv->base)) return PTR_ERR(priv->base); for (i = 0; i < priv->reg_stride; i++) { diff --git a/drivers/irqchip/irq-sni-exiu.c b/drivers/irqchip/irq-sni-exiu.c index abd011fcecf4..c7db617e1a2f 100644 --- a/drivers/irqchip/irq-sni-exiu.c +++ b/drivers/irqchip/irq-sni-exiu.c @@ -37,11 +37,26 @@ struct exiu_irq_data { u32 spi_base; }; -static void exiu_irq_eoi(struct irq_data *d) +static void exiu_irq_ack(struct irq_data *d) { struct exiu_irq_data *data = irq_data_get_irq_chip_data(d); writel(BIT(d->hwirq), data->base + EIREQCLR); +} + +static void exiu_irq_eoi(struct irq_data *d) +{ + struct exiu_irq_data *data = irq_data_get_irq_chip_data(d); + + /* + * Level triggered interrupts are latched and must be cleared during + * EOI or the interrupt will be jammed on. Of course if a level + * triggered interrupt is still asserted then the write will not clear + * the interrupt. + */ + if (irqd_is_level_type(d)) + writel(BIT(d->hwirq), data->base + EIREQCLR); + irq_chip_eoi_parent(d); } @@ -91,10 +106,13 @@ static int exiu_irq_set_type(struct irq_data *d, unsigned int type) writel_relaxed(val, data->base + EILVL); val = readl_relaxed(data->base + EIEDG); - if (type == IRQ_TYPE_LEVEL_LOW || type == IRQ_TYPE_LEVEL_HIGH) + if (type == IRQ_TYPE_LEVEL_LOW || type == IRQ_TYPE_LEVEL_HIGH) { val &= ~BIT(d->hwirq); - else + irq_set_handler_locked(d, handle_fasteoi_irq); + } else { val |= BIT(d->hwirq); + irq_set_handler_locked(d, handle_fasteoi_ack_irq); + } writel_relaxed(val, data->base + EIEDG); writel_relaxed(BIT(d->hwirq), data->base + EIREQCLR); @@ -104,6 +122,7 @@ static int exiu_irq_set_type(struct irq_data *d, unsigned int type) static struct irq_chip exiu_irq_chip = { .name = "EXIU", + .irq_ack = exiu_irq_ack, .irq_eoi = exiu_irq_eoi, .irq_enable = exiu_irq_enable, .irq_mask = exiu_irq_mask, diff --git a/drivers/irqchip/irq-sun6i-r.c b/drivers/irqchip/irq-sun6i-r.c index 4cd3e533740b..a01e44049415 100644 --- a/drivers/irqchip/irq-sun6i-r.c +++ b/drivers/irqchip/irq-sun6i-r.c @@ -249,11 +249,13 @@ static int sun6i_r_intc_domain_alloc(struct irq_domain *domain, for (i = 0; i < nr_irqs; ++i, ++hwirq, ++virq) { if (hwirq == nmi_hwirq) { irq_domain_set_hwirq_and_chip(domain, virq, hwirq, - &sun6i_r_intc_nmi_chip, 0); + &sun6i_r_intc_nmi_chip, + NULL); irq_set_handler(virq, handle_fasteoi_ack_irq); } else { irq_domain_set_hwirq_and_chip(domain, virq, hwirq, - &sun6i_r_intc_wakeup_chip, 0); + &sun6i_r_intc_wakeup_chip, + NULL); } } diff --git a/drivers/irqchip/irq-xtensa-mx.c b/drivers/irqchip/irq-xtensa-mx.c index 27933338f7b3..8c581c985aa7 100644 --- a/drivers/irqchip/irq-xtensa-mx.c +++ b/drivers/irqchip/irq-xtensa-mx.c @@ -151,14 +151,25 @@ static struct irq_chip xtensa_mx_irq_chip = { .irq_set_affinity = xtensa_mx_irq_set_affinity, }; +static void __init xtensa_mx_init_common(struct irq_domain *root_domain) +{ + unsigned int i; + + irq_set_default_host(root_domain); + secondary_init_irq(); + + /* Initialize default IRQ routing to CPU 0 */ + for (i = 0; i < XCHAL_NUM_EXTINTERRUPTS; ++i) + set_er(1, MIROUT(i)); +} + int __init xtensa_mx_init_legacy(struct device_node *interrupt_parent) { struct irq_domain *root_domain = irq_domain_add_legacy(NULL, NR_IRQS - 1, 1, 0, &xtensa_mx_irq_domain_ops, &xtensa_mx_irq_chip); - irq_set_default_host(root_domain); - secondary_init_irq(); + xtensa_mx_init_common(root_domain); return 0; } @@ -168,8 +179,7 @@ static int __init xtensa_mx_init(struct device_node *np, struct irq_domain *root_domain = irq_domain_add_linear(np, NR_IRQS, &xtensa_mx_irq_domain_ops, &xtensa_mx_irq_chip); - irq_set_default_host(root_domain); - secondary_init_irq(); + xtensa_mx_init_common(root_domain); return 0; } IRQCHIP_DECLARE(xtensa_mx_irq_chip, "cdns,xtensa-mx", xtensa_mx_init); diff --git a/drivers/md/bcache/alloc.c b/drivers/md/bcache/alloc.c index 097577ae3c47..ce13c272c387 100644 --- a/drivers/md/bcache/alloc.c +++ b/drivers/md/bcache/alloc.c @@ -336,7 +336,7 @@ static int bch_allocator_thread(void *arg) mutex_unlock(&ca->set->bucket_lock); blkdev_issue_discard(ca->bdev, bucket_to_sector(ca->set, bucket), - ca->sb.bucket_size, GFP_KERNEL, 0); + ca->sb.bucket_size, GFP_KERNEL); mutex_lock(&ca->set->bucket_lock); } diff --git a/drivers/md/bcache/debug.c b/drivers/md/bcache/debug.c index 6230dfdd9286..7510d1c983a5 100644 --- a/drivers/md/bcache/debug.c +++ b/drivers/md/bcache/debug.c @@ -107,15 +107,16 @@ void bch_btree_verify(struct btree *b) void bch_data_verify(struct cached_dev *dc, struct bio *bio) { + unsigned int nr_segs = bio_segments(bio); struct bio *check; struct bio_vec bv, cbv; struct bvec_iter iter, citer = { 0 }; - check = bio_kmalloc(GFP_NOIO, bio_segments(bio)); + check = bio_kmalloc(nr_segs, GFP_NOIO); if (!check) return; - bio_set_dev(check, bio->bi_bdev); - check->bi_opf = REQ_OP_READ; + bio_init(check, bio->bi_bdev, check->bi_inline_vecs, nr_segs, + REQ_OP_READ); check->bi_iter.bi_sector = bio->bi_iter.bi_sector; check->bi_iter.bi_size = bio->bi_iter.bi_size; @@ -146,7 +147,8 @@ void bch_data_verify(struct cached_dev *dc, struct bio *bio) bio_free_pages(check); out_put: - bio_put(check); + bio_uninit(check); + kfree(check); } #endif diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c index 7c2ca52ca3e4..df5347ea450b 100644 --- a/drivers/md/bcache/journal.c +++ b/drivers/md/bcache/journal.c @@ -771,12 +771,12 @@ static void journal_write_unlocked(struct closure *cl) bio_reset(bio, ca->bdev, REQ_OP_WRITE | REQ_SYNC | REQ_META | REQ_PREFLUSH | REQ_FUA); - bch_bio_map(bio, w->data); bio->bi_iter.bi_sector = PTR_OFFSET(k, i); bio->bi_iter.bi_size = sectors << 9; bio->bi_end_io = journal_write_endio; bio->bi_private = w; + bch_bio_map(bio, w->data); trace_bcache_journal_write(bio, w->data->keys); bio_list_add(&list, bio); diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c index fdd0194f84dd..9c5dde73da88 100644 --- a/drivers/md/bcache/request.c +++ b/drivers/md/bcache/request.c @@ -685,7 +685,7 @@ static void do_bio_hook(struct search *s, { struct bio *bio = &s->bio.bio; - bio_init_clone(bio->bi_bdev, bio, orig_bio, GFP_NOIO); + bio_init_clone(orig_bio->bi_bdev, bio, orig_bio, GFP_NOIO); /* * bi_end_io can be set separately somewhere else, e.g. the * variants in, @@ -1005,7 +1005,7 @@ static void cached_dev_write(struct cached_dev *dc, struct search *s) bio_get(s->iop.bio); if (bio_op(bio) == REQ_OP_DISCARD && - !blk_queue_discard(bdev_get_queue(dc->bdev))) + !bdev_max_discard_sectors(dc->bdev)) goto insert_data; /* I/O request sent to backing device */ @@ -1115,7 +1115,7 @@ static void detached_dev_do_request(struct bcache_device *d, struct bio *bio, bio->bi_private = ddip; if ((bio_op(bio) == REQ_OP_DISCARD) && - !blk_queue_discard(bdev_get_queue(dc->bdev))) + !bdev_max_discard_sectors(dc->bdev)) bio->bi_end_io(bio); else submit_bio_noacct(bio); diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index bf3de149d3c9..2f49e31142f6 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -973,7 +973,6 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size, blk_queue_flag_set(QUEUE_FLAG_NONROT, d->disk->queue); blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, d->disk->queue); - blk_queue_flag_set(QUEUE_FLAG_DISCARD, d->disk->queue); blk_queue_write_cache(q, true, true); @@ -2350,7 +2349,7 @@ static int register_cache(struct cache_sb *sb, struct cache_sb_disk *sb_disk, ca->bdev->bd_holder = ca; ca->sb_disk = sb_disk; - if (blk_queue_discard(bdev_get_queue(bdev))) + if (bdev_max_discard_sectors((bdev))) ca->discard = CACHE_DISCARD(&ca->sb); ret = cache_alloc(ca); diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c index d1029d71ff3b..c6f677059214 100644 --- a/drivers/md/bcache/sysfs.c +++ b/drivers/md/bcache/sysfs.c @@ -1151,7 +1151,7 @@ STORE(__bch_cache) if (attr == &sysfs_discard) { bool v = strtoul_or_return(buf); - if (blk_queue_discard(bdev_get_queue(ca->bdev))) + if (bdev_max_discard_sectors(ca->bdev)) ca->discard = v; if (v != CACHE_DISCARD(&ca->sb)) { diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index e9cbc70d5a0e..5ffa1dcf84cf 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -611,7 +611,8 @@ static void bio_complete(struct bio *bio) { struct dm_buffer *b = bio->bi_private; blk_status_t status = bio->bi_status; - bio_put(bio); + bio_uninit(bio); + kfree(bio); b->end_io(b, status); } @@ -626,16 +627,14 @@ static void use_bio(struct dm_buffer *b, int rw, sector_t sector, if (unlikely(b->c->sectors_per_block_bits < PAGE_SHIFT - SECTOR_SHIFT)) vec_size += 2; - bio = bio_kmalloc(GFP_NOWAIT | __GFP_NORETRY | __GFP_NOWARN, vec_size); + bio = bio_kmalloc(vec_size, GFP_NOWAIT | __GFP_NORETRY | __GFP_NOWARN); if (!bio) { dmio: use_dmio(b, rw, sector, n_sectors, offset); return; } - + bio_init(bio, b->c->bdev, bio->bi_inline_vecs, vec_size, rw); bio->bi_iter.bi_sector = sector; - bio_set_dev(bio, b->c->bdev); - bio_set_op_attrs(bio, rw, 0); bio->bi_end_io = bio_complete; bio->bi_private = b; diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index 780a61bc6cc0..28c5de8eca4a 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -3329,13 +3329,6 @@ static int cache_iterate_devices(struct dm_target *ti, return r; } -static bool origin_dev_supports_discard(struct block_device *origin_bdev) -{ - struct request_queue *q = bdev_get_queue(origin_bdev); - - return blk_queue_discard(q); -} - /* * If discard_passdown was enabled verify that the origin device * supports discards. Disable discard_passdown if not. @@ -3349,7 +3342,7 @@ static void disable_passdown_if_not_supported(struct cache *cache) if (!cache->features.discard_passdown) return; - if (!origin_dev_supports_discard(origin_bdev)) + if (!bdev_max_discard_sectors(origin_bdev)) reason = "discard unsupported"; else if (origin_limits->max_discard_sectors < cache->sectors_per_block) diff --git a/drivers/md/dm-clone-target.c b/drivers/md/dm-clone-target.c index 128316a73d01..811b0a5379d0 100644 --- a/drivers/md/dm-clone-target.c +++ b/drivers/md/dm-clone-target.c @@ -2016,13 +2016,6 @@ static void clone_resume(struct dm_target *ti) do_waker(&clone->waker.work); } -static bool bdev_supports_discards(struct block_device *bdev) -{ - struct request_queue *q = bdev_get_queue(bdev); - - return (q && blk_queue_discard(q)); -} - /* * If discard_passdown was enabled verify that the destination device supports * discards. Disable discard_passdown if not. @@ -2036,7 +2029,7 @@ static void disable_passdown_if_not_supported(struct clone *clone) if (!test_bit(DM_CLONE_DISCARD_PASSDOWN, &clone->flags)) return; - if (!bdev_supports_discards(dest_dev)) + if (!bdev_max_discard_sectors(dest_dev)) reason = "discard unsupported"; else if (dest_limits->max_discard_sectors < clone->region_size) reason = "max discard sectors smaller than a region"; diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index ad2d5faa2ebb..36ae30b73a6e 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -4399,6 +4399,7 @@ try_smaller_buffer: } if (ic->internal_hash) { + size_t recalc_tags_size; ic->recalc_wq = alloc_workqueue("dm-integrity-recalc", WQ_MEM_RECLAIM, 1); if (!ic->recalc_wq ) { ti->error = "Cannot allocate workqueue"; @@ -4412,8 +4413,10 @@ try_smaller_buffer: r = -ENOMEM; goto bad; } - ic->recalc_tags = kvmalloc_array(RECALC_SECTORS >> ic->sb->log2_sectors_per_block, - ic->tag_size, GFP_KERNEL); + recalc_tags_size = (RECALC_SECTORS >> ic->sb->log2_sectors_per_block) * ic->tag_size; + if (crypto_shash_digestsize(ic->internal_hash) > ic->tag_size) + recalc_tags_size += crypto_shash_digestsize(ic->internal_hash) - ic->tag_size; + ic->recalc_tags = kvmalloc(recalc_tags_size, GFP_KERNEL); if (!ic->recalc_tags) { ti->error = "Cannot allocate tags for recalculating"; r = -ENOMEM; diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c index 5762366333a2..e4b95eaeec8c 100644 --- a/drivers/md/dm-io.c +++ b/drivers/md/dm-io.c @@ -311,7 +311,7 @@ static void do_region(int op, int op_flags, unsigned region, * Reject unsupported discard and write same requests. */ if (op == REQ_OP_DISCARD) - special_cmd_max_sectors = q->limits.max_discard_sectors; + special_cmd_max_sectors = bdev_max_discard_sectors(where->bdev); else if (op == REQ_OP_WRITE_ZEROES) special_cmd_max_sectors = q->limits.max_write_zeroes_sectors; if ((op == REQ_OP_DISCARD || op == REQ_OP_WRITE_ZEROES) && diff --git a/drivers/md/dm-log-writes.c b/drivers/md/dm-log-writes.c index c9d036d6bb2e..e194226c89e5 100644 --- a/drivers/md/dm-log-writes.c +++ b/drivers/md/dm-log-writes.c @@ -866,9 +866,8 @@ static int log_writes_message(struct dm_target *ti, unsigned argc, char **argv, static void log_writes_io_hints(struct dm_target *ti, struct queue_limits *limits) { struct log_writes_c *lc = ti->private; - struct request_queue *q = bdev_get_queue(lc->dev->bdev); - if (!q || !blk_queue_discard(q)) { + if (!bdev_max_discard_sectors(lc->dev->bdev)) { lc->device_supports_discard = false; limits->discard_granularity = lc->sectorsize; limits->max_discard_sectors = (UINT_MAX >> SECTOR_SHIFT); diff --git a/drivers/md/dm-ps-historical-service-time.c b/drivers/md/dm-ps-historical-service-time.c index 875bca30a0dd..82f2a06153dc 100644 --- a/drivers/md/dm-ps-historical-service-time.c +++ b/drivers/md/dm-ps-historical-service-time.c @@ -27,7 +27,6 @@ #include <linux/blkdev.h> #include <linux/slab.h> #include <linux/module.h> -#include <linux/sched/clock.h> #define DM_MSG_PREFIX "multipath historical-service-time" @@ -433,7 +432,7 @@ static struct dm_path *hst_select_path(struct path_selector *ps, { struct selector *s = ps->context; struct path_info *pi = NULL, *best = NULL; - u64 time_now = sched_clock(); + u64 time_now = ktime_get_ns(); struct dm_path *ret = NULL; unsigned long flags; @@ -474,7 +473,7 @@ static int hst_start_io(struct path_selector *ps, struct dm_path *path, static u64 path_service_time(struct path_info *pi, u64 start_time) { - u64 sched_now = ktime_get_ns(); + u64 now = ktime_get_ns(); /* if a previous disk request has finished after this IO was * sent to the hardware, pretend the submission happened @@ -483,11 +482,11 @@ static u64 path_service_time(struct path_info *pi, u64 start_time) if (time_after64(pi->last_finish, start_time)) start_time = pi->last_finish; - pi->last_finish = sched_now; - if (time_before64(sched_now, start_time)) + pi->last_finish = now; + if (time_before64(now, start_time)) return 0; - return sched_now - start_time; + return now - start_time; } static int hst_end_io(struct path_selector *ps, struct dm_path *path, diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index 2b26435a6946..9526ccbedafb 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -2963,13 +2963,8 @@ static void configure_discard_support(struct raid_set *rs) raid456 = rs_is_raid456(rs); for (i = 0; i < rs->raid_disks; i++) { - struct request_queue *q; - - if (!rs->dev[i].rdev.bdev) - continue; - - q = bdev_get_queue(rs->dev[i].rdev.bdev); - if (!q || !blk_queue_discard(q)) + if (!rs->dev[i].rdev.bdev || + !bdev_max_discard_sectors(rs->dev[i].rdev.bdev)) return; if (raid456) { diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 03541cfc2317..e7d42f6335a2 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -1820,9 +1820,7 @@ static int device_dax_write_cache_enabled(struct dm_target *ti, static int device_is_rotational(struct dm_target *ti, struct dm_dev *dev, sector_t start, sector_t len, void *data) { - struct request_queue *q = bdev_get_queue(dev->bdev); - - return !blk_queue_nonrot(q); + return !bdev_nonrot(dev->bdev); } static int device_is_not_random(struct dm_target *ti, struct dm_dev *dev, @@ -1890,9 +1888,7 @@ static bool dm_table_supports_nowait(struct dm_table *t) static int device_not_discard_capable(struct dm_target *ti, struct dm_dev *dev, sector_t start, sector_t len, void *data) { - struct request_queue *q = bdev_get_queue(dev->bdev); - - return !blk_queue_discard(q); + return !bdev_max_discard_sectors(dev->bdev); } static bool dm_table_supports_discards(struct dm_table *t) @@ -1924,9 +1920,7 @@ static int device_not_secure_erase_capable(struct dm_target *ti, struct dm_dev *dev, sector_t start, sector_t len, void *data) { - struct request_queue *q = bdev_get_queue(dev->bdev); - - return !blk_queue_secure_erase(q); + return !bdev_max_secure_erase_sectors(dev->bdev); } static bool dm_table_supports_secure_erase(struct dm_table *t) @@ -1952,9 +1946,7 @@ static int device_requires_stable_pages(struct dm_target *ti, struct dm_dev *dev, sector_t start, sector_t len, void *data) { - struct request_queue *q = bdev_get_queue(dev->bdev); - - return blk_queue_stable_writes(q); + return bdev_stable_writes(dev->bdev); } int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, @@ -1974,18 +1966,15 @@ int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, blk_queue_flag_clear(QUEUE_FLAG_NOWAIT, q); if (!dm_table_supports_discards(t)) { - blk_queue_flag_clear(QUEUE_FLAG_DISCARD, q); - /* Must also clear discard limits... */ q->limits.max_discard_sectors = 0; q->limits.max_hw_discard_sectors = 0; q->limits.discard_granularity = 0; q->limits.discard_alignment = 0; q->limits.discard_misaligned = 0; - } else - blk_queue_flag_set(QUEUE_FLAG_DISCARD, q); + } - if (dm_table_supports_secure_erase(t)) - blk_queue_flag_set(QUEUE_FLAG_SECERASE, q); + if (!dm_table_supports_secure_erase(t)) + q->limits.max_secure_erase_sectors = 0; if (dm_table_supports_flush(t, (1UL << QUEUE_FLAG_WC))) { wc = true; diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index 4d25d0e27031..84c083f76673 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -398,8 +398,8 @@ static int issue_discard(struct discard_op *op, dm_block_t data_b, dm_block_t da sector_t s = block_to_sectors(tc->pool, data_b); sector_t len = block_to_sectors(tc->pool, data_e - data_b); - return __blkdev_issue_discard(tc->pool_dev->bdev, s, len, - GFP_NOWAIT, 0, &op->bio); + return __blkdev_issue_discard(tc->pool_dev->bdev, s, len, GFP_NOWAIT, + &op->bio); } static void end_discard(struct discard_op *op, int r) @@ -2802,13 +2802,6 @@ static void requeue_bios(struct pool *pool) /*---------------------------------------------------------------- * Binding of control targets to a pool object *--------------------------------------------------------------*/ -static bool data_dev_supports_discard(struct pool_c *pt) -{ - struct request_queue *q = bdev_get_queue(pt->data_dev->bdev); - - return blk_queue_discard(q); -} - static bool is_factor(sector_t block_size, uint32_t n) { return !sector_div(block_size, n); @@ -2828,7 +2821,7 @@ static void disable_passdown_if_not_supported(struct pool_c *pt) if (!pt->adjusted_pf.discard_passdown) return; - if (!data_dev_supports_discard(pt)) + if (!bdev_max_discard_sectors(pt->data_dev->bdev)) reason = "discard unsupported"; else if (data_limits->max_discard_sectors < pool->sectors_per_block) @@ -4057,8 +4050,6 @@ static void pool_io_hints(struct dm_target *ti, struct queue_limits *limits) /* * Must explicitly disallow stacking discard limits otherwise the * block layer will stack them if pool's data device has support. - * QUEUE_FLAG_DISCARD wouldn't be set but there is no way for the - * user to see that, so make sure to set all discard limits to 0. */ limits->discard_granularity = 0; return; diff --git a/drivers/md/dm-zone.c b/drivers/md/dm-zone.c index c1ca9be4b79e..57daa86c19cf 100644 --- a/drivers/md/dm-zone.c +++ b/drivers/md/dm-zone.c @@ -360,16 +360,20 @@ static int dm_update_zone_wp_offset(struct mapped_device *md, unsigned int zno, return 0; } +struct orig_bio_details { + unsigned int op; + unsigned int nr_sectors; +}; + /* * First phase of BIO mapping for targets with zone append emulation: * check all BIO that change a zone writer pointer and change zone * append operations into regular write operations. */ static bool dm_zone_map_bio_begin(struct mapped_device *md, - struct bio *orig_bio, struct bio *clone) + unsigned int zno, struct bio *clone) { sector_t zsectors = blk_queue_zone_sectors(md->queue); - unsigned int zno = bio_zone_no(orig_bio); unsigned int zwp_offset = READ_ONCE(md->zwp_offset[zno]); /* @@ -384,7 +388,7 @@ static bool dm_zone_map_bio_begin(struct mapped_device *md, WRITE_ONCE(md->zwp_offset[zno], zwp_offset); } - switch (bio_op(orig_bio)) { + switch (bio_op(clone)) { case REQ_OP_ZONE_RESET: case REQ_OP_ZONE_FINISH: return true; @@ -401,9 +405,8 @@ static bool dm_zone_map_bio_begin(struct mapped_device *md, * target zone. */ clone->bi_opf = REQ_OP_WRITE | REQ_NOMERGE | - (orig_bio->bi_opf & (~REQ_OP_MASK)); - clone->bi_iter.bi_sector = - orig_bio->bi_iter.bi_sector + zwp_offset; + (clone->bi_opf & (~REQ_OP_MASK)); + clone->bi_iter.bi_sector += zwp_offset; break; default: DMWARN_LIMIT("Invalid BIO operation"); @@ -423,11 +426,10 @@ static bool dm_zone_map_bio_begin(struct mapped_device *md, * data written to a zone. Note that at this point, the remapped clone BIO * may already have completed, so we do not touch it. */ -static blk_status_t dm_zone_map_bio_end(struct mapped_device *md, - struct bio *orig_bio, +static blk_status_t dm_zone_map_bio_end(struct mapped_device *md, unsigned int zno, + struct orig_bio_details *orig_bio_details, unsigned int nr_sectors) { - unsigned int zno = bio_zone_no(orig_bio); unsigned int zwp_offset = READ_ONCE(md->zwp_offset[zno]); /* The clone BIO may already have been completed and failed */ @@ -435,7 +437,7 @@ static blk_status_t dm_zone_map_bio_end(struct mapped_device *md, return BLK_STS_IOERR; /* Update the zone wp offset */ - switch (bio_op(orig_bio)) { + switch (orig_bio_details->op) { case REQ_OP_ZONE_RESET: WRITE_ONCE(md->zwp_offset[zno], 0); return BLK_STS_OK; @@ -452,7 +454,7 @@ static blk_status_t dm_zone_map_bio_end(struct mapped_device *md, * Check that the target did not truncate the write operation * emulating a zone append. */ - if (nr_sectors != bio_sectors(orig_bio)) { + if (nr_sectors != orig_bio_details->nr_sectors) { DMWARN_LIMIT("Truncated write for zone append"); return BLK_STS_IOERR; } @@ -488,7 +490,7 @@ static inline void dm_zone_unlock(struct request_queue *q, bio_clear_flag(clone, BIO_ZONE_WRITE_LOCKED); } -static bool dm_need_zone_wp_tracking(struct bio *orig_bio) +static bool dm_need_zone_wp_tracking(struct bio *bio) { /* * Special processing is not needed for operations that do not need the @@ -496,15 +498,15 @@ static bool dm_need_zone_wp_tracking(struct bio *orig_bio) * zones and all operations that do not modify directly a sequential * zone write pointer. */ - if (op_is_flush(orig_bio->bi_opf) && !bio_sectors(orig_bio)) + if (op_is_flush(bio->bi_opf) && !bio_sectors(bio)) return false; - switch (bio_op(orig_bio)) { + switch (bio_op(bio)) { case REQ_OP_WRITE_ZEROES: case REQ_OP_WRITE: case REQ_OP_ZONE_RESET: case REQ_OP_ZONE_FINISH: case REQ_OP_ZONE_APPEND: - return bio_zone_is_seq(orig_bio); + return bio_zone_is_seq(bio); default: return false; } @@ -519,8 +521,8 @@ int dm_zone_map_bio(struct dm_target_io *tio) struct dm_target *ti = tio->ti; struct mapped_device *md = io->md; struct request_queue *q = md->queue; - struct bio *orig_bio = io->orig_bio; struct bio *clone = &tio->clone; + struct orig_bio_details orig_bio_details; unsigned int zno; blk_status_t sts; int r; @@ -529,18 +531,21 @@ int dm_zone_map_bio(struct dm_target_io *tio) * IOs that do not change a zone write pointer do not need * any additional special processing. */ - if (!dm_need_zone_wp_tracking(orig_bio)) + if (!dm_need_zone_wp_tracking(clone)) return ti->type->map(ti, clone); /* Lock the target zone */ - zno = bio_zone_no(orig_bio); + zno = bio_zone_no(clone); dm_zone_lock(q, zno, clone); + orig_bio_details.nr_sectors = bio_sectors(clone); + orig_bio_details.op = bio_op(clone); + /* * Check that the bio and the target zone write pointer offset are * both valid, and if the bio is a zone append, remap it to a write. */ - if (!dm_zone_map_bio_begin(md, orig_bio, clone)) { + if (!dm_zone_map_bio_begin(md, zno, clone)) { dm_zone_unlock(q, zno, clone); return DM_MAPIO_KILL; } @@ -560,7 +565,8 @@ int dm_zone_map_bio(struct dm_target_io *tio) * The target submitted the clone BIO. The target zone will * be unlocked on completion of the clone. */ - sts = dm_zone_map_bio_end(md, orig_bio, *tio->len_ptr); + sts = dm_zone_map_bio_end(md, zno, &orig_bio_details, + *tio->len_ptr); break; case DM_MAPIO_REMAPPED: /* @@ -568,7 +574,8 @@ int dm_zone_map_bio(struct dm_target_io *tio) * unlock the target zone here as the clone will not be * submitted. */ - sts = dm_zone_map_bio_end(md, orig_bio, *tio->len_ptr); + sts = dm_zone_map_bio_end(md, zno, &orig_bio_details, + *tio->len_ptr); if (sts != BLK_STS_OK) dm_zone_unlock(q, zno, clone); break; diff --git a/drivers/md/dm-zoned-target.c b/drivers/md/dm-zoned-target.c index cac295cc8840..0ec5d8b9b1a4 100644 --- a/drivers/md/dm-zoned-target.c +++ b/drivers/md/dm-zoned-target.c @@ -1001,7 +1001,7 @@ static void dmz_io_hints(struct dm_target *ti, struct queue_limits *limits) blk_limits_io_min(limits, DMZ_BLOCK_SIZE); blk_limits_io_opt(limits, DMZ_BLOCK_SIZE); - limits->discard_alignment = DMZ_BLOCK_SIZE; + limits->discard_alignment = 0; limits->discard_granularity = DMZ_BLOCK_SIZE; limits->max_discard_sectors = chunk_sectors; limits->max_hw_discard_sectors = chunk_sectors; diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 3c5fad7c4ee6..39081338ca61 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -955,7 +955,6 @@ void disable_discard(struct mapped_device *md) /* device doesn't really support DISCARD, disable it */ limits->max_discard_sectors = 0; - blk_queue_flag_clear(QUEUE_FLAG_DISCARD, md->queue); } void disable_write_zeroes(struct mapped_device *md) @@ -982,7 +981,7 @@ static void clone_endio(struct bio *bio) if (unlikely(error == BLK_STS_TARGET)) { if (bio_op(bio) == REQ_OP_DISCARD && - !q->limits.max_discard_sectors) + !bdev_max_discard_sectors(bio->bi_bdev)) disable_discard(md); else if (bio_op(bio) == REQ_OP_WRITE_ZEROES && !q->limits.max_write_zeroes_sectors) @@ -1323,8 +1322,7 @@ static void __map_bio(struct bio *clone) } static void alloc_multiple_bios(struct bio_list *blist, struct clone_info *ci, - struct dm_target *ti, unsigned num_bios, - unsigned *len) + struct dm_target *ti, unsigned num_bios) { struct bio *bio; int try; @@ -1335,7 +1333,7 @@ static void alloc_multiple_bios(struct bio_list *blist, struct clone_info *ci, if (try) mutex_lock(&ci->io->md->table_devices_lock); for (bio_nr = 0; bio_nr < num_bios; bio_nr++) { - bio = alloc_tio(ci, ti, bio_nr, len, + bio = alloc_tio(ci, ti, bio_nr, NULL, try ? GFP_NOIO : GFP_NOWAIT); if (!bio) break; @@ -1363,11 +1361,11 @@ static void __send_duplicate_bios(struct clone_info *ci, struct dm_target *ti, break; case 1: clone = alloc_tio(ci, ti, 0, len, GFP_NOIO); - dm_tio_set_flag(clone_to_tio(clone), DM_TIO_IS_DUPLICATE_BIO); __map_bio(clone); break; default: - alloc_multiple_bios(&blist, ci, ti, num_bios, len); + /* dm_accept_partial_bio() is not supported with shared tio->len_ptr */ + alloc_multiple_bios(&blist, ci, ti, num_bios); while ((clone = bio_list_pop(&blist))) { dm_tio_set_flag(clone_to_tio(clone), DM_TIO_IS_DUPLICATE_BIO); __map_bio(clone); @@ -1392,6 +1390,7 @@ static void __send_empty_flush(struct clone_info *ci) ci->bio = &flush_bio; ci->sector_count = 0; + ci->io->tio.clone.bi_iter.bi_size = 0; while ((ti = dm_table_get_target(ci->map, target_nr++))) __send_duplicate_bios(ci, ti, ti->num_flush_bios, NULL); @@ -1407,14 +1406,10 @@ static void __send_changing_extent_only(struct clone_info *ci, struct dm_target len = min_t(sector_t, ci->sector_count, max_io_len_target_boundary(ti, dm_target_offset(ti, ci->sector))); - /* - * dm_accept_partial_bio cannot be used with duplicate bios, - * so update clone_info cursor before __send_duplicate_bios(). - */ + __send_duplicate_bios(ci, ti, num_bios, &len); + ci->sector += len; ci->sector_count -= len; - - __send_duplicate_bios(ci, ti, num_bios, &len); } static bool is_abnormal_io(struct bio *bio) diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c index bfd6026d7809..d87f674ab762 100644 --- a/drivers/md/md-bitmap.c +++ b/drivers/md/md-bitmap.c @@ -639,14 +639,6 @@ re_read: daemon_sleep = le32_to_cpu(sb->daemon_sleep) * HZ; write_behind = le32_to_cpu(sb->write_behind); sectors_reserved = le32_to_cpu(sb->sectors_reserved); - /* Setup nodes/clustername only if bitmap version is - * cluster-compatible - */ - if (sb->version == cpu_to_le32(BITMAP_MAJOR_CLUSTERED)) { - nodes = le32_to_cpu(sb->nodes); - strlcpy(bitmap->mddev->bitmap_info.cluster_name, - sb->cluster_name, 64); - } /* verify that the bitmap-specific fields are valid */ if (sb->magic != cpu_to_le32(BITMAP_MAGIC)) @@ -668,6 +660,16 @@ re_read: goto out; } + /* + * Setup nodes/clustername only if bitmap version is + * cluster-compatible + */ + if (sb->version == cpu_to_le32(BITMAP_MAJOR_CLUSTERED)) { + nodes = le32_to_cpu(sb->nodes); + strscpy(bitmap->mddev->bitmap_info.cluster_name, + sb->cluster_name, 64); + } + /* keep the array size field of the bitmap superblock up to date */ sb->sync_size = cpu_to_le64(bitmap->mddev->resync_max_sectors); @@ -695,14 +697,13 @@ re_read: if (le32_to_cpu(sb->version) == BITMAP_MAJOR_HOSTENDIAN) set_bit(BITMAP_HOSTENDIAN, &bitmap->flags); bitmap->events_cleared = le64_to_cpu(sb->events_cleared); - strlcpy(bitmap->mddev->bitmap_info.cluster_name, sb->cluster_name, 64); err = 0; out: kunmap_atomic(sb); - /* Assigning chunksize is required for "re_read" */ - bitmap->mddev->bitmap_info.chunksize = chunksize; if (err == 0 && nodes && (bitmap->cluster_slot < 0)) { + /* Assigning chunksize is required for "re_read" */ + bitmap->mddev->bitmap_info.chunksize = chunksize; err = md_setup_cluster(bitmap->mddev, nodes); if (err) { pr_warn("%s: Could not setup cluster service (%d)\n", @@ -713,18 +714,18 @@ out: goto re_read; } - out_no_sb: - if (test_bit(BITMAP_STALE, &bitmap->flags)) - bitmap->events_cleared = bitmap->mddev->events; - bitmap->mddev->bitmap_info.chunksize = chunksize; - bitmap->mddev->bitmap_info.daemon_sleep = daemon_sleep; - bitmap->mddev->bitmap_info.max_write_behind = write_behind; - bitmap->mddev->bitmap_info.nodes = nodes; - if (bitmap->mddev->bitmap_info.space == 0 || - bitmap->mddev->bitmap_info.space > sectors_reserved) - bitmap->mddev->bitmap_info.space = sectors_reserved; - if (err) { + if (err == 0) { + if (test_bit(BITMAP_STALE, &bitmap->flags)) + bitmap->events_cleared = bitmap->mddev->events; + bitmap->mddev->bitmap_info.chunksize = chunksize; + bitmap->mddev->bitmap_info.daemon_sleep = daemon_sleep; + bitmap->mddev->bitmap_info.max_write_behind = write_behind; + bitmap->mddev->bitmap_info.nodes = nodes; + if (bitmap->mddev->bitmap_info.space == 0 || + bitmap->mddev->bitmap_info.space > sectors_reserved) + bitmap->mddev->bitmap_info.space = sectors_reserved; + } else { md_bitmap_print_sb(bitmap); if (bitmap->cluster_slot < 0) md_cluster_stop(bitmap->mddev); diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c index 1c8a06b77c85..37cbcce3cc66 100644 --- a/drivers/md/md-cluster.c +++ b/drivers/md/md-cluster.c @@ -201,7 +201,7 @@ static struct dlm_lock_resource *lockres_init(struct mddev *mddev, pr_err("md-cluster: Unable to allocate resource name for resource %s\n", name); goto out_err; } - strlcpy(res->name, name, namelen + 1); + strscpy(res->name, name, namelen + 1); if (with_lvb) { res->lksb.sb_lvbptr = kzalloc(LVB_SIZE, GFP_KERNEL); if (!res->lksb.sb_lvbptr) { diff --git a/drivers/md/md-linear.c b/drivers/md/md-linear.c index 0f55b079371b..138a3b25c5c8 100644 --- a/drivers/md/md-linear.c +++ b/drivers/md/md-linear.c @@ -64,7 +64,6 @@ static struct linear_conf *linear_conf(struct mddev *mddev, int raid_disks) struct linear_conf *conf; struct md_rdev *rdev; int i, cnt; - bool discard_supported = false; conf = kzalloc(struct_size(conf, disks, raid_disks), GFP_KERNEL); if (!conf) @@ -96,9 +95,6 @@ static struct linear_conf *linear_conf(struct mddev *mddev, int raid_disks) conf->array_sectors += rdev->sectors; cnt++; - - if (blk_queue_discard(bdev_get_queue(rdev->bdev))) - discard_supported = true; } if (cnt != raid_disks) { pr_warn("md/linear:%s: not enough drives present. Aborting!\n", @@ -106,11 +102,6 @@ static struct linear_conf *linear_conf(struct mddev *mddev, int raid_disks) goto out; } - if (!discard_supported) - blk_queue_flag_clear(QUEUE_FLAG_DISCARD, mddev->queue); - else - blk_queue_flag_set(QUEUE_FLAG_DISCARD, mddev->queue); - /* * Here we calculate the device offsets. */ @@ -252,7 +243,7 @@ static bool linear_make_request(struct mddev *mddev, struct bio *bio) start_sector + data_offset; if (unlikely((bio_op(bio) == REQ_OP_DISCARD) && - !blk_queue_discard(bio->bi_bdev->bd_disk->queue))) { + !bdev_max_discard_sectors(bio->bi_bdev))) { /* Just ignore it */ bio_endio(bio); } else { diff --git a/drivers/md/md.c b/drivers/md/md.c index 309b3af906ad..707e802d0082 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -2627,14 +2627,16 @@ static void sync_sbs(struct mddev *mddev, int nospares) static bool does_sb_need_changing(struct mddev *mddev) { - struct md_rdev *rdev; + struct md_rdev *rdev = NULL, *iter; struct mdp_superblock_1 *sb; int role; /* Find a good rdev */ - rdev_for_each(rdev, mddev) - if ((rdev->raid_disk >= 0) && !test_bit(Faulty, &rdev->flags)) + rdev_for_each(iter, mddev) + if ((iter->raid_disk >= 0) && !test_bit(Faulty, &iter->flags)) { + rdev = iter; break; + } /* No good device found. */ if (!rdev) @@ -2645,11 +2647,11 @@ static bool does_sb_need_changing(struct mddev *mddev) rdev_for_each(rdev, mddev) { role = le16_to_cpu(sb->dev_roles[rdev->desc_nr]); /* Device activated? */ - if (role == 0xffff && rdev->raid_disk >=0 && + if (role == MD_DISK_ROLE_SPARE && rdev->raid_disk >= 0 && !test_bit(Faulty, &rdev->flags)) return true; /* Device turned faulty? */ - if (test_bit(Faulty, &rdev->flags) && (role < 0xfffd)) + if (test_bit(Faulty, &rdev->flags) && (role < MD_DISK_ROLE_MAX)) return true; } @@ -2984,10 +2986,11 @@ state_store(struct md_rdev *rdev, const char *buf, size_t len) if (cmd_match(buf, "faulty") && rdev->mddev->pers) { md_error(rdev->mddev, rdev); - if (test_bit(Faulty, &rdev->flags)) - err = 0; - else + + if (test_bit(MD_BROKEN, &rdev->mddev->flags)) err = -EBUSY; + else + err = 0; } else if (cmd_match(buf, "remove")) { if (rdev->mddev->pers) { clear_bit(Blocked, &rdev->flags); @@ -4028,7 +4031,7 @@ level_store(struct mddev *mddev, const char *buf, size_t len) oldpriv = mddev->private; mddev->pers = pers; mddev->private = priv; - strlcpy(mddev->clevel, pers->name, sizeof(mddev->clevel)); + strscpy(mddev->clevel, pers->name, sizeof(mddev->clevel)); mddev->level = mddev->new_level; mddev->layout = mddev->new_layout; mddev->chunk_sectors = mddev->new_chunk_sectors; @@ -4353,10 +4356,9 @@ __ATTR_PREALLOC(resync_start, S_IRUGO|S_IWUSR, * like active, but no writes have been seen for a while (100msec). * * broken - * RAID0/LINEAR-only: same as clean, but array is missing a member. - * It's useful because RAID0/LINEAR mounted-arrays aren't stopped - * when a member is gone, so this state will at least alert the - * user that something is wrong. +* Array is failed. It's useful because mounted-arrays aren't stopped +* when array is failed, so this state will at least alert the user that +* something is wrong. */ enum array_state { clear, inactive, suspended, readonly, read_auto, clean, active, write_pending, active_idle, broken, bad_word}; @@ -5763,7 +5765,7 @@ static int add_named_array(const char *val, const struct kernel_param *kp) len--; if (len >= DISK_NAME_LEN) return -E2BIG; - strlcpy(buf, val, len+1); + strscpy(buf, val, len+1); if (strncmp(buf, "md_", 3) == 0) return md_alloc(0, buf); if (strncmp(buf, "md", 2) == 0 && @@ -5896,7 +5898,7 @@ int md_run(struct mddev *mddev) mddev->level = pers->level; mddev->new_level = pers->level; } - strlcpy(mddev->clevel, pers->name, sizeof(mddev->clevel)); + strscpy(mddev->clevel, pers->name, sizeof(mddev->clevel)); if (mddev->reshape_position != MaxSector && pers->start_reshape == NULL) { @@ -5991,8 +5993,7 @@ int md_run(struct mddev *mddev) bool nonrot = true; rdev_for_each(rdev, mddev) { - if (rdev->raid_disk >= 0 && - !blk_queue_nonrot(bdev_get_queue(rdev->bdev))) { + if (rdev->raid_disk >= 0 && !bdev_nonrot(rdev->bdev)) { nonrot = false; break; } @@ -7444,7 +7445,7 @@ static int set_disk_faulty(struct mddev *mddev, dev_t dev) err = -ENODEV; else { md_error(mddev, rdev); - if (!test_bit(Faulty, &rdev->flags)) + if (test_bit(MD_BROKEN, &mddev->flags)) err = -EBUSY; } rcu_read_unlock(); @@ -7985,13 +7986,16 @@ void md_error(struct mddev *mddev, struct md_rdev *rdev) if (!mddev->pers || !mddev->pers->error_handler) return; - mddev->pers->error_handler(mddev,rdev); - if (mddev->degraded) + mddev->pers->error_handler(mddev, rdev); + + if (mddev->degraded && !test_bit(MD_BROKEN, &mddev->flags)) set_bit(MD_RECOVERY_RECOVER, &mddev->recovery); sysfs_notify_dirent_safe(rdev->sysfs_state); set_bit(MD_RECOVERY_INTR, &mddev->recovery); - set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); - md_wakeup_thread(mddev->thread); + if (!test_bit(MD_BROKEN, &mddev->flags)) { + set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); + md_wakeup_thread(mddev->thread); + } if (mddev->event_work.func) queue_work(md_misc_wq, &mddev->event_work); md_new_event(); @@ -8585,7 +8589,7 @@ void md_submit_discard_bio(struct mddev *mddev, struct md_rdev *rdev, { struct bio *discard_bio = NULL; - if (__blkdev_issue_discard(rdev->bdev, start, size, GFP_NOIO, 0, + if (__blkdev_issue_discard(rdev->bdev, start, size, GFP_NOIO, &discard_bio) || !discard_bio) return; @@ -9671,7 +9675,7 @@ static void check_sb_changes(struct mddev *mddev, struct md_rdev *rdev) role = le16_to_cpu(sb->dev_roles[rdev2->desc_nr]); if (test_bit(Candidate, &rdev2->flags)) { - if (role == 0xfffe) { + if (role == MD_DISK_ROLE_FAULTY) { pr_info("md: Removing Candidate device %s because add failed\n", bdevname(rdev2->bdev,b)); md_kick_rdev_from_array(rdev2); continue; @@ -9684,7 +9688,7 @@ static void check_sb_changes(struct mddev *mddev, struct md_rdev *rdev) /* * got activated except reshape is happening. */ - if (rdev2->raid_disk == -1 && role != 0xffff && + if (rdev2->raid_disk == -1 && role != MD_DISK_ROLE_SPARE && !(le32_to_cpu(sb->feature_map) & MD_FEATURE_RESHAPE_ACTIVE)) { rdev2->saved_raid_disk = role; @@ -9701,7 +9705,8 @@ static void check_sb_changes(struct mddev *mddev, struct md_rdev *rdev) * as faulty. The recovery is performed by the * one who initiated the error. */ - if ((role == 0xfffe) || (role == 0xfffd)) { + if (role == MD_DISK_ROLE_FAULTY || + role == MD_DISK_ROLE_JOURNAL) { md_error(mddev, rdev2); clear_bit(Blocked, &rdev2->flags); } @@ -9791,16 +9796,18 @@ static int read_rdev(struct mddev *mddev, struct md_rdev *rdev) void md_reload_sb(struct mddev *mddev, int nr) { - struct md_rdev *rdev; + struct md_rdev *rdev = NULL, *iter; int err; /* Find the rdev */ - rdev_for_each_rcu(rdev, mddev) { - if (rdev->desc_nr == nr) + rdev_for_each_rcu(iter, mddev) { + if (iter->desc_nr == nr) { + rdev = iter; break; + } } - if (!rdev || rdev->desc_nr != nr) { + if (!rdev) { pr_warn("%s: %d Could not find rdev with nr %d\n", __func__, __LINE__, nr); return; } diff --git a/drivers/md/md.h b/drivers/md/md.h index 6ac283864533..cf2cbb17acbd 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -234,34 +234,42 @@ extern int rdev_clear_badblocks(struct md_rdev *rdev, sector_t s, int sectors, int is_new); struct md_cluster_info; -/* change UNSUPPORTED_MDDEV_FLAGS for each array type if new flag is added */ +/** + * enum mddev_flags - md device flags. + * @MD_ARRAY_FIRST_USE: First use of array, needs initialization. + * @MD_CLOSING: If set, we are closing the array, do not open it then. + * @MD_JOURNAL_CLEAN: A raid with journal is already clean. + * @MD_HAS_JOURNAL: The raid array has journal feature set. + * @MD_CLUSTER_RESYNC_LOCKED: cluster raid only, which means node, already took + * resync lock, need to release the lock. + * @MD_FAILFAST_SUPPORTED: Using MD_FAILFAST on metadata writes is supported as + * calls to md_error() will never cause the array to + * become failed. + * @MD_HAS_PPL: The raid array has PPL feature set. + * @MD_HAS_MULTIPLE_PPLS: The raid array has multiple PPLs feature set. + * @MD_ALLOW_SB_UPDATE: md_check_recovery is allowed to update the metadata + * without taking reconfig_mutex. + * @MD_UPDATING_SB: md_check_recovery is updating the metadata without + * explicitly holding reconfig_mutex. + * @MD_NOT_READY: do_md_run() is active, so 'array_state', ust not report that + * array is ready yet. + * @MD_BROKEN: This is used to stop writes and mark array as failed. + * + * change UNSUPPORTED_MDDEV_FLAGS for each array type if new flag is added + */ enum mddev_flags { - MD_ARRAY_FIRST_USE, /* First use of array, needs initialization */ - MD_CLOSING, /* If set, we are closing the array, do not open - * it then */ - MD_JOURNAL_CLEAN, /* A raid with journal is already clean */ - MD_HAS_JOURNAL, /* The raid array has journal feature set */ - MD_CLUSTER_RESYNC_LOCKED, /* cluster raid only, which means node - * already took resync lock, need to - * release the lock */ - MD_FAILFAST_SUPPORTED, /* Using MD_FAILFAST on metadata writes is - * supported as calls to md_error() will - * never cause the array to become failed. - */ - MD_HAS_PPL, /* The raid array has PPL feature set */ - MD_HAS_MULTIPLE_PPLS, /* The raid array has multiple PPLs feature set */ - MD_ALLOW_SB_UPDATE, /* md_check_recovery is allowed to update - * the metadata without taking reconfig_mutex. - */ - MD_UPDATING_SB, /* md_check_recovery is updating the metadata - * without explicitly holding reconfig_mutex. - */ - MD_NOT_READY, /* do_md_run() is active, so 'array_state' - * must not report that array is ready yet - */ - MD_BROKEN, /* This is used in RAID-0/LINEAR only, to stop - * I/O in case an array member is gone/failed. - */ + MD_ARRAY_FIRST_USE, + MD_CLOSING, + MD_JOURNAL_CLEAN, + MD_HAS_JOURNAL, + MD_CLUSTER_RESYNC_LOCKED, + MD_FAILFAST_SUPPORTED, + MD_HAS_PPL, + MD_HAS_MULTIPLE_PPLS, + MD_ALLOW_SB_UPDATE, + MD_UPDATING_SB, + MD_NOT_READY, + MD_BROKEN, }; enum mddev_sb_flags { diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index b21e101183f4..e11701e394ca 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -128,21 +128,6 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf) pr_debug("md/raid0:%s: FINAL %d zones\n", mdname(mddev), conf->nr_strip_zones); - if (conf->nr_strip_zones == 1) { - conf->layout = RAID0_ORIG_LAYOUT; - } else if (mddev->layout == RAID0_ORIG_LAYOUT || - mddev->layout == RAID0_ALT_MULTIZONE_LAYOUT) { - conf->layout = mddev->layout; - } else if (default_layout == RAID0_ORIG_LAYOUT || - default_layout == RAID0_ALT_MULTIZONE_LAYOUT) { - conf->layout = default_layout; - } else { - pr_err("md/raid0:%s: cannot assemble multi-zone RAID0 with default_layout setting\n", - mdname(mddev)); - pr_err("md/raid0: please set raid0.default_layout to 1 or 2\n"); - err = -ENOTSUPP; - goto abort; - } /* * now since we have the hard sector sizes, we can make sure * chunk size is a multiple of that sector size @@ -273,6 +258,22 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf) (unsigned long long)smallest->sectors); } + if (conf->nr_strip_zones == 1 || conf->strip_zone[1].nb_dev == 1) { + conf->layout = RAID0_ORIG_LAYOUT; + } else if (mddev->layout == RAID0_ORIG_LAYOUT || + mddev->layout == RAID0_ALT_MULTIZONE_LAYOUT) { + conf->layout = mddev->layout; + } else if (default_layout == RAID0_ORIG_LAYOUT || + default_layout == RAID0_ALT_MULTIZONE_LAYOUT) { + conf->layout = default_layout; + } else { + pr_err("md/raid0:%s: cannot assemble multi-zone RAID0 with default_layout setting\n", + mdname(mddev)); + pr_err("md/raid0: please set raid0.default_layout to 1 or 2\n"); + err = -EOPNOTSUPP; + goto abort; + } + pr_debug("md/raid0:%s: done.\n", mdname(mddev)); *private_conf = conf; @@ -399,7 +400,6 @@ static int raid0_run(struct mddev *mddev) conf = mddev->private; if (mddev->queue) { struct md_rdev *rdev; - bool discard_supported = false; blk_queue_max_hw_sectors(mddev->queue, mddev->chunk_sectors); blk_queue_max_write_zeroes_sectors(mddev->queue, mddev->chunk_sectors); @@ -412,13 +412,7 @@ static int raid0_run(struct mddev *mddev) rdev_for_each(rdev, mddev) { disk_stack_limits(mddev->gendisk, rdev->bdev, rdev->data_offset << 9); - if (blk_queue_discard(bdev_get_queue(rdev->bdev))) - discard_supported = true; } - if (!discard_supported) - blk_queue_flag_clear(QUEUE_FLAG_DISCARD, mddev->queue); - else - blk_queue_flag_set(QUEUE_FLAG_DISCARD, mddev->queue); } /* calculate array device size */ diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 99d5464a51f8..99d5af1362d7 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -165,9 +165,10 @@ static void * r1buf_pool_alloc(gfp_t gfp_flags, void *data) * Allocate bios : 1 for reading, n-1 for writing */ for (j = pi->raid_disks ; j-- ; ) { - bio = bio_kmalloc(gfp_flags, RESYNC_PAGES); + bio = bio_kmalloc(RESYNC_PAGES, gfp_flags); if (!bio) goto out_free_bio; + bio_init(bio, NULL, bio->bi_inline_vecs, RESYNC_PAGES, 0); r1_bio->bios[j] = bio; } /* @@ -206,8 +207,10 @@ out_free_pages: resync_free_pages(&rps[j]); out_free_bio: - while (++j < pi->raid_disks) - bio_put(r1_bio->bios[j]); + while (++j < pi->raid_disks) { + bio_uninit(r1_bio->bios[j]); + kfree(r1_bio->bios[j]); + } kfree(rps); out_free_r1bio: @@ -225,7 +228,8 @@ static void r1buf_pool_free(void *__r1_bio, void *data) for (i = pi->raid_disks; i--; ) { rp = get_resync_pages(r1bio->bios[i]); resync_free_pages(rp); - bio_put(r1bio->bios[i]); + bio_uninit(r1bio->bios[i]); + kfree(r1bio->bios[i]); } /* resync pages array stored in the 1st bio's .bi_private */ @@ -704,7 +708,7 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect /* At least two disks to choose from so failfast is OK */ set_bit(R1BIO_FailFast, &r1_bio->state); - nonrot = blk_queue_nonrot(bdev_get_queue(rdev->bdev)); + nonrot = bdev_nonrot(rdev->bdev); has_nonrot_disk |= nonrot; pending = atomic_read(&rdev->nr_pending); dist = abs(this_sector - conf->mirrors[disk].head_position); @@ -802,7 +806,7 @@ static void flush_bio_list(struct r1conf *conf, struct bio *bio) if (test_bit(Faulty, &rdev->flags)) { bio_io_error(bio); } else if (unlikely((bio_op(bio) == REQ_OP_DISCARD) && - !blk_queue_discard(bio->bi_bdev->bd_disk->queue))) + !bdev_max_discard_sectors(bio->bi_bdev))) /* Just ignore it */ bio_endio(bio); else @@ -1637,30 +1641,39 @@ static void raid1_status(struct seq_file *seq, struct mddev *mddev) seq_printf(seq, "]"); } +/** + * raid1_error() - RAID1 error handler. + * @mddev: affected md device. + * @rdev: member device to fail. + * + * The routine acknowledges &rdev failure and determines new @mddev state. + * If it failed, then: + * - &MD_BROKEN flag is set in &mddev->flags. + * - recovery is disabled. + * Otherwise, it must be degraded: + * - recovery is interrupted. + * - &mddev->degraded is bumped. + * + * @rdev is marked as &Faulty excluding case when array is failed and + * &mddev->fail_last_dev is off. + */ static void raid1_error(struct mddev *mddev, struct md_rdev *rdev) { char b[BDEVNAME_SIZE]; struct r1conf *conf = mddev->private; unsigned long flags; - /* - * If it is not operational, then we have already marked it as dead - * else if it is the last working disks with "fail_last_dev == false", - * ignore the error, let the next level up know. - * else mark the drive as failed - */ spin_lock_irqsave(&conf->device_lock, flags); - if (test_bit(In_sync, &rdev->flags) && !mddev->fail_last_dev - && (conf->raid_disks - mddev->degraded) == 1) { - /* - * Don't fail the drive, act as though we were just a - * normal single drive. - * However don't try a recovery from this drive as - * it is very likely to fail. - */ - conf->recovery_disabled = mddev->recovery_disabled; - spin_unlock_irqrestore(&conf->device_lock, flags); - return; + + if (test_bit(In_sync, &rdev->flags) && + (conf->raid_disks - mddev->degraded) == 1) { + set_bit(MD_BROKEN, &mddev->flags); + + if (!mddev->fail_last_dev) { + conf->recovery_disabled = mddev->recovery_disabled; + spin_unlock_irqrestore(&conf->device_lock, flags); + return; + } } set_bit(Blocked, &rdev->flags); if (test_and_clear_bit(In_sync, &rdev->flags)) @@ -1826,8 +1839,6 @@ static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev) break; } } - if (mddev->queue && blk_queue_discard(bdev_get_queue(rdev->bdev))) - blk_queue_flag_set(QUEUE_FLAG_DISCARD, mddev->queue); print_conf(conf); return err; } @@ -3106,7 +3117,6 @@ static int raid1_run(struct mddev *mddev) int i; struct md_rdev *rdev; int ret; - bool discard_supported = false; if (mddev->level != 1) { pr_warn("md/raid1:%s: raid level not set to mirroring (%d)\n", @@ -3141,8 +3151,6 @@ static int raid1_run(struct mddev *mddev) continue; disk_stack_limits(mddev->gendisk, rdev->bdev, rdev->data_offset << 9); - if (blk_queue_discard(bdev_get_queue(rdev->bdev))) - discard_supported = true; } mddev->degraded = 0; @@ -3179,15 +3187,6 @@ static int raid1_run(struct mddev *mddev) md_set_array_sectors(mddev, raid1_size(mddev, 0, 0)); - if (mddev->queue) { - if (discard_supported) - blk_queue_flag_set(QUEUE_FLAG_DISCARD, - mddev->queue); - else - blk_queue_flag_clear(QUEUE_FLAG_DISCARD, - mddev->queue); - } - ret = md_integrity_register(mddev); if (ret) { md_unregister_thread(&mddev->thread); diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index dfe7d62d3fbd..dfa576cdf11c 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -145,15 +145,17 @@ static void * r10buf_pool_alloc(gfp_t gfp_flags, void *data) * Allocate bios. */ for (j = nalloc ; j-- ; ) { - bio = bio_kmalloc(gfp_flags, RESYNC_PAGES); + bio = bio_kmalloc(RESYNC_PAGES, gfp_flags); if (!bio) goto out_free_bio; + bio_init(bio, NULL, bio->bi_inline_vecs, RESYNC_PAGES, 0); r10_bio->devs[j].bio = bio; if (!conf->have_replacement) continue; - bio = bio_kmalloc(gfp_flags, RESYNC_PAGES); + bio = bio_kmalloc(RESYNC_PAGES, gfp_flags); if (!bio) goto out_free_bio; + bio_init(bio, NULL, bio->bi_inline_vecs, RESYNC_PAGES, 0); r10_bio->devs[j].repl_bio = bio; } /* @@ -197,9 +199,11 @@ out_free_pages: out_free_bio: for ( ; j < nalloc; j++) { if (r10_bio->devs[j].bio) - bio_put(r10_bio->devs[j].bio); + bio_uninit(r10_bio->devs[j].bio); + kfree(r10_bio->devs[j].bio); if (r10_bio->devs[j].repl_bio) - bio_put(r10_bio->devs[j].repl_bio); + bio_uninit(r10_bio->devs[j].repl_bio); + kfree(r10_bio->devs[j].repl_bio); } kfree(rps); out_free_r10bio: @@ -220,12 +224,15 @@ static void r10buf_pool_free(void *__r10_bio, void *data) if (bio) { rp = get_resync_pages(bio); resync_free_pages(rp); - bio_put(bio); + bio_uninit(bio); + kfree(bio); } bio = r10bio->devs[j].repl_bio; - if (bio) - bio_put(bio); + if (bio) { + bio_uninit(bio); + kfree(bio); + } } /* resync pages array stored in the 1st bio's .bi_private */ @@ -796,7 +803,7 @@ static struct md_rdev *read_balance(struct r10conf *conf, if (!do_balance) break; - nonrot = blk_queue_nonrot(bdev_get_queue(rdev->bdev)); + nonrot = bdev_nonrot(rdev->bdev); has_nonrot_disk |= nonrot; pending = atomic_read(&rdev->nr_pending); if (min_pending > pending && nonrot) { @@ -888,7 +895,7 @@ static void flush_pending_writes(struct r10conf *conf) if (test_bit(Faulty, &rdev->flags)) { bio_io_error(bio); } else if (unlikely((bio_op(bio) == REQ_OP_DISCARD) && - !blk_queue_discard(bio->bi_bdev->bd_disk->queue))) + !bdev_max_discard_sectors(bio->bi_bdev))) /* Just ignore it */ bio_endio(bio); else @@ -1083,7 +1090,7 @@ static void raid10_unplug(struct blk_plug_cb *cb, bool from_schedule) if (test_bit(Faulty, &rdev->flags)) { bio_io_error(bio); } else if (unlikely((bio_op(bio) == REQ_OP_DISCARD) && - !blk_queue_discard(bio->bi_bdev->bd_disk->queue))) + !bdev_max_discard_sectors(bio->bi_bdev))) /* Just ignore it */ bio_endio(bio); else @@ -1963,32 +1970,40 @@ static int enough(struct r10conf *conf, int ignore) _enough(conf, 1, ignore); } +/** + * raid10_error() - RAID10 error handler. + * @mddev: affected md device. + * @rdev: member device to fail. + * + * The routine acknowledges &rdev failure and determines new @mddev state. + * If it failed, then: + * - &MD_BROKEN flag is set in &mddev->flags. + * Otherwise, it must be degraded: + * - recovery is interrupted. + * - &mddev->degraded is bumped. + + * @rdev is marked as &Faulty excluding case when array is failed and + * &mddev->fail_last_dev is off. + */ static void raid10_error(struct mddev *mddev, struct md_rdev *rdev) { char b[BDEVNAME_SIZE]; struct r10conf *conf = mddev->private; unsigned long flags; - /* - * If it is not operational, then we have already marked it as dead - * else if it is the last working disks with "fail_last_dev == false", - * ignore the error, let the next level up know. - * else mark the drive as failed - */ spin_lock_irqsave(&conf->device_lock, flags); - if (test_bit(In_sync, &rdev->flags) && !mddev->fail_last_dev - && !enough(conf, rdev->raid_disk)) { - /* - * Don't fail the drive, just return an IO error. - */ - spin_unlock_irqrestore(&conf->device_lock, flags); - return; + + if (test_bit(In_sync, &rdev->flags) && !enough(conf, rdev->raid_disk)) { + set_bit(MD_BROKEN, &mddev->flags); + + if (!mddev->fail_last_dev) { + spin_unlock_irqrestore(&conf->device_lock, flags); + return; + } } if (test_and_clear_bit(In_sync, &rdev->flags)) mddev->degraded++; - /* - * If recovery is running, make sure it aborts. - */ + set_bit(MD_RECOVERY_INTR, &mddev->recovery); set_bit(Blocked, &rdev->flags); set_bit(Faulty, &rdev->flags); @@ -2144,8 +2159,6 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev) rcu_assign_pointer(p->rdev, rdev); break; } - if (mddev->queue && blk_queue_discard(bdev_get_queue(rdev->bdev))) - blk_queue_flag_set(QUEUE_FLAG_DISCARD, mddev->queue); print_conf(conf); return err; @@ -4069,7 +4082,6 @@ static int raid10_run(struct mddev *mddev) sector_t size; sector_t min_offset_diff = 0; int first = 1; - bool discard_supported = false; if (mddev_init_writes_pending(mddev) < 0) return -ENOMEM; @@ -4140,20 +4152,9 @@ static int raid10_run(struct mddev *mddev) rdev->data_offset << 9); disk->head_position = 0; - - if (blk_queue_discard(bdev_get_queue(rdev->bdev))) - discard_supported = true; first = 0; } - if (mddev->queue) { - if (discard_supported) - blk_queue_flag_set(QUEUE_FLAG_DISCARD, - mddev->queue); - else - blk_queue_flag_clear(QUEUE_FLAG_DISCARD, - mddev->queue); - } /* need to check that every block has at least one working mirror */ if (!enough(conf, -1)) { pr_err("md/raid10:%s: not enough operational mirrors.\n", diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c index a7d50ff9020a..094a4042589e 100644 --- a/drivers/md/raid5-cache.c +++ b/drivers/md/raid5-cache.c @@ -1318,7 +1318,7 @@ static void r5l_write_super_and_discard_space(struct r5l_log *log, r5l_write_super(log, end); - if (!blk_queue_discard(bdev_get_queue(bdev))) + if (!bdev_max_discard_sectors(bdev)) return; mddev = log->rdev->mddev; @@ -1344,14 +1344,14 @@ static void r5l_write_super_and_discard_space(struct r5l_log *log, if (log->last_checkpoint < end) { blkdev_issue_discard(bdev, log->last_checkpoint + log->rdev->data_offset, - end - log->last_checkpoint, GFP_NOIO, 0); + end - log->last_checkpoint, GFP_NOIO); } else { blkdev_issue_discard(bdev, log->last_checkpoint + log->rdev->data_offset, log->device_size - log->last_checkpoint, - GFP_NOIO, 0); + GFP_NOIO); blkdev_issue_discard(bdev, log->rdev->data_offset, end, - GFP_NOIO, 0); + GFP_NOIO); } } diff --git a/drivers/md/raid5-ppl.c b/drivers/md/raid5-ppl.c index d3962d92df18..55d065a87b89 100644 --- a/drivers/md/raid5-ppl.c +++ b/drivers/md/raid5-ppl.c @@ -883,7 +883,9 @@ static int ppl_recover_entry(struct ppl_log *log, struct ppl_header_entry *e, (unsigned long long)r_sector, dd_idx, (unsigned long long)sector); - rdev = conf->disks[dd_idx].rdev; + /* Array has not started so rcu dereference is safe */ + rdev = rcu_dereference_protected( + conf->disks[dd_idx].rdev, 1); if (!rdev || (!test_bit(In_sync, &rdev->flags) && sector >= rdev->recovery_offset)) { pr_debug("%s:%*s data member disk %d missing\n", @@ -934,7 +936,10 @@ static int ppl_recover_entry(struct ppl_log *log, struct ppl_header_entry *e, parity_sector = raid5_compute_sector(conf, r_sector_first + i, 0, &disk, &sh); BUG_ON(sh.pd_idx != le32_to_cpu(e->parity_disk)); - parity_rdev = conf->disks[sh.pd_idx].rdev; + + /* Array has not started so rcu dereference is safe */ + parity_rdev = rcu_dereference_protected( + conf->disks[sh.pd_idx].rdev, 1); BUG_ON(parity_rdev->bdev->bd_dev != log->rdev->bdev->bd_dev); pr_debug("%s:%*s write parity at sector %llu, disk %s\n", @@ -1404,7 +1409,9 @@ int ppl_init_log(struct r5conf *conf) for (i = 0; i < ppl_conf->count; i++) { struct ppl_log *log = &ppl_conf->child_logs[i]; - struct md_rdev *rdev = conf->disks[i].rdev; + /* Array has not started so rcu dereference is safe */ + struct md_rdev *rdev = + rcu_dereference_protected(conf->disks[i].rdev, 1); mutex_init(&log->io_mutex); spin_lock_init(&log->io_list_lock); diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 351d341a1ffa..39038fa8b1c8 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -79,18 +79,21 @@ static inline int stripe_hash_locks_hash(struct r5conf *conf, sector_t sect) } static inline void lock_device_hash_lock(struct r5conf *conf, int hash) + __acquires(&conf->device_lock) { spin_lock_irq(conf->hash_locks + hash); spin_lock(&conf->device_lock); } static inline void unlock_device_hash_lock(struct r5conf *conf, int hash) + __releases(&conf->device_lock) { spin_unlock(&conf->device_lock); spin_unlock_irq(conf->hash_locks + hash); } static inline void lock_all_device_hash_locks_irq(struct r5conf *conf) + __acquires(&conf->device_lock) { int i; spin_lock_irq(conf->hash_locks); @@ -100,6 +103,7 @@ static inline void lock_all_device_hash_locks_irq(struct r5conf *conf) } static inline void unlock_all_device_hash_locks_irq(struct r5conf *conf) + __releases(&conf->device_lock) { int i; spin_unlock(&conf->device_lock); @@ -164,6 +168,7 @@ static bool stripe_is_lowprio(struct stripe_head *sh) } static void raid5_wakeup_stripe_thread(struct stripe_head *sh) + __must_hold(&sh->raid_conf->device_lock) { struct r5conf *conf = sh->raid_conf; struct r5worker_group *group; @@ -211,6 +216,7 @@ static void raid5_wakeup_stripe_thread(struct stripe_head *sh) static void do_release_stripe(struct r5conf *conf, struct stripe_head *sh, struct list_head *temp_inactive_list) + __must_hold(&conf->device_lock) { int i; int injournal = 0; /* number of date pages with R5_InJournal */ @@ -296,6 +302,7 @@ static void do_release_stripe(struct r5conf *conf, struct stripe_head *sh, static void __release_stripe(struct r5conf *conf, struct stripe_head *sh, struct list_head *temp_inactive_list) + __must_hold(&conf->device_lock) { if (atomic_dec_and_test(&sh->count)) do_release_stripe(conf, sh, temp_inactive_list); @@ -350,9 +357,9 @@ static void release_inactive_stripe_list(struct r5conf *conf, } } -/* should hold conf->device_lock already */ static int release_stripe_list(struct r5conf *conf, struct list_head *temp_inactive_list) + __must_hold(&conf->device_lock) { struct stripe_head *sh, *t; int count = 0; @@ -629,6 +636,10 @@ static struct stripe_head *__find_stripe(struct r5conf *conf, sector_t sector, * This is because some failed devices may only affect one * of the two sections, and some non-in_sync devices may * be insync in the section most affected by failed devices. + * + * Most calls to this function hold &conf->device_lock. Calls + * in raid5_run() do not require the lock as no other threads + * have been started yet. */ int raid5_calc_degraded(struct r5conf *conf) { @@ -686,17 +697,17 @@ int raid5_calc_degraded(struct r5conf *conf) return degraded; } -static int has_failed(struct r5conf *conf) +static bool has_failed(struct r5conf *conf) { - int degraded; + int degraded = conf->mddev->degraded; - if (conf->mddev->reshape_position == MaxSector) - return conf->mddev->degraded > conf->max_degraded; + if (test_bit(MD_BROKEN, &conf->mddev->flags)) + return true; - degraded = raid5_calc_degraded(conf); - if (degraded > conf->max_degraded) - return 1; - return 0; + if (conf->mddev->reshape_position != MaxSector) + degraded = raid5_calc_degraded(conf); + + return degraded > conf->max_degraded; } struct stripe_head * @@ -2648,6 +2659,28 @@ static void shrink_stripes(struct r5conf *conf) conf->slab_cache = NULL; } +/* + * This helper wraps rcu_dereference_protected() and can be used when + * it is known that the nr_pending of the rdev is elevated. + */ +static struct md_rdev *rdev_pend_deref(struct md_rdev __rcu *rdev) +{ + return rcu_dereference_protected(rdev, + atomic_read(&rcu_access_pointer(rdev)->nr_pending)); +} + +/* + * This helper wraps rcu_dereference_protected() and should be used + * when it is known that the mddev_lock() is held. This is safe + * seeing raid5_remove_disk() has the same lock held. + */ +static struct md_rdev *rdev_mdlock_deref(struct mddev *mddev, + struct md_rdev __rcu *rdev) +{ + return rcu_dereference_protected(rdev, + lockdep_is_held(&mddev->reconfig_mutex)); +} + static void raid5_end_read_request(struct bio * bi) { struct stripe_head *sh = bi->bi_private; @@ -2674,9 +2707,9 @@ static void raid5_end_read_request(struct bio * bi) * In that case it moved down to 'rdev'. * rdev is not removed until all requests are finished. */ - rdev = conf->disks[i].replacement; + rdev = rdev_pend_deref(conf->disks[i].replacement); if (!rdev) - rdev = conf->disks[i].rdev; + rdev = rdev_pend_deref(conf->disks[i].rdev); if (use_new_offset(conf, sh)) s = sh->sector + rdev->new_data_offset; @@ -2790,11 +2823,11 @@ static void raid5_end_write_request(struct bio *bi) for (i = 0 ; i < disks; i++) { if (bi == &sh->dev[i].req) { - rdev = conf->disks[i].rdev; + rdev = rdev_pend_deref(conf->disks[i].rdev); break; } if (bi == &sh->dev[i].rreq) { - rdev = conf->disks[i].replacement; + rdev = rdev_pend_deref(conf->disks[i].replacement); if (rdev) replacement = 1; else @@ -2802,7 +2835,7 @@ static void raid5_end_write_request(struct bio *bi) * replaced it. rdev is not removed * until all requests are finished. */ - rdev = conf->disks[i].rdev; + rdev = rdev_pend_deref(conf->disks[i].rdev); break; } } @@ -2863,34 +2896,31 @@ static void raid5_error(struct mddev *mddev, struct md_rdev *rdev) unsigned long flags; pr_debug("raid456: error called\n"); + pr_crit("md/raid:%s: Disk failure on %s, disabling device.\n", + mdname(mddev), bdevname(rdev->bdev, b)); + spin_lock_irqsave(&conf->device_lock, flags); + set_bit(Faulty, &rdev->flags); + clear_bit(In_sync, &rdev->flags); + mddev->degraded = raid5_calc_degraded(conf); - if (test_bit(In_sync, &rdev->flags) && - mddev->degraded == conf->max_degraded) { - /* - * Don't allow to achieve failed state - * Don't try to recover this device - */ + if (has_failed(conf)) { + set_bit(MD_BROKEN, &conf->mddev->flags); conf->recovery_disabled = mddev->recovery_disabled; - spin_unlock_irqrestore(&conf->device_lock, flags); - return; + + pr_crit("md/raid:%s: Cannot continue operation (%d/%d failed).\n", + mdname(mddev), mddev->degraded, conf->raid_disks); + } else { + pr_crit("md/raid:%s: Operation continuing on %d devices.\n", + mdname(mddev), conf->raid_disks - mddev->degraded); } - set_bit(Faulty, &rdev->flags); - clear_bit(In_sync, &rdev->flags); - mddev->degraded = raid5_calc_degraded(conf); spin_unlock_irqrestore(&conf->device_lock, flags); set_bit(MD_RECOVERY_INTR, &mddev->recovery); set_bit(Blocked, &rdev->flags); set_mask_bits(&mddev->sb_flags, 0, BIT(MD_SB_CHANGE_DEVS) | BIT(MD_SB_CHANGE_PENDING)); - pr_crit("md/raid:%s: Disk failure on %s, disabling device.\n" - "md/raid:%s: Operation continuing on %d devices.\n", - mdname(mddev), - bdevname(rdev->bdev, b), - mdname(mddev), - conf->raid_disks - mddev->degraded); r5c_update_on_rdev_error(mddev, rdev); } @@ -5213,23 +5243,23 @@ finish: struct r5dev *dev = &sh->dev[i]; if (test_and_clear_bit(R5_WriteError, &dev->flags)) { /* We own a safe reference to the rdev */ - rdev = conf->disks[i].rdev; + rdev = rdev_pend_deref(conf->disks[i].rdev); if (!rdev_set_badblocks(rdev, sh->sector, RAID5_STRIPE_SECTORS(conf), 0)) md_error(conf->mddev, rdev); rdev_dec_pending(rdev, conf->mddev); } if (test_and_clear_bit(R5_MadeGood, &dev->flags)) { - rdev = conf->disks[i].rdev; + rdev = rdev_pend_deref(conf->disks[i].rdev); rdev_clear_badblocks(rdev, sh->sector, RAID5_STRIPE_SECTORS(conf), 0); rdev_dec_pending(rdev, conf->mddev); } if (test_and_clear_bit(R5_MadeGoodRepl, &dev->flags)) { - rdev = conf->disks[i].replacement; + rdev = rdev_pend_deref(conf->disks[i].replacement); if (!rdev) /* rdev have been moved down */ - rdev = conf->disks[i].rdev; + rdev = rdev_pend_deref(conf->disks[i].rdev); rdev_clear_badblocks(rdev, sh->sector, RAID5_STRIPE_SECTORS(conf), 0); rdev_dec_pending(rdev, conf->mddev); @@ -5256,6 +5286,7 @@ finish: } static void raid5_activate_delayed(struct r5conf *conf) + __must_hold(&conf->device_lock) { if (atomic_read(&conf->preread_active_stripes) < IO_THRESHOLD) { while (!list_empty(&conf->delayed_list)) { @@ -5273,9 +5304,9 @@ static void raid5_activate_delayed(struct r5conf *conf) } static void activate_bit_delay(struct r5conf *conf, - struct list_head *temp_inactive_list) + struct list_head *temp_inactive_list) + __must_hold(&conf->device_lock) { - /* device_lock is held */ struct list_head head; list_add(&head, &conf->bitmap_list); list_del_init(&conf->bitmap_list); @@ -5500,6 +5531,7 @@ static struct bio *chunk_aligned_read(struct mddev *mddev, struct bio *raid_bio) * handle_list. */ static struct stripe_head *__get_priority_stripe(struct r5conf *conf, int group) + __must_hold(&conf->device_lock) { struct stripe_head *sh, *tmp; struct list_head *handle_list = NULL; @@ -6288,7 +6320,7 @@ static inline sector_t raid5_sync_request(struct mddev *mddev, sector_t sector_n */ rcu_read_lock(); for (i = 0; i < conf->raid_disks; i++) { - struct md_rdev *rdev = READ_ONCE(conf->disks[i].rdev); + struct md_rdev *rdev = rcu_dereference(conf->disks[i].rdev); if (rdev == NULL || test_bit(Faulty, &rdev->flags)) still_degraded = 1; @@ -6371,8 +6403,7 @@ static int retry_aligned_read(struct r5conf *conf, struct bio *raid_bio, static int handle_active_stripes(struct r5conf *conf, int group, struct r5worker *worker, struct list_head *temp_inactive_list) - __releases(&conf->device_lock) - __acquires(&conf->device_lock) + __must_hold(&conf->device_lock) { struct stripe_head *batch[MAX_STRIPE_BATCH], *sh; int i, batch_size = 0, hash; @@ -7166,7 +7197,7 @@ static struct r5conf *setup_conf(struct mddev *mddev) int i; int group_cnt; struct r5worker_group *new_group; - int ret; + int ret = -ENOMEM; if (mddev->new_level != 5 && mddev->new_level != 4 @@ -7225,6 +7256,7 @@ static struct r5conf *setup_conf(struct mddev *mddev) spin_lock_init(&conf->device_lock); seqcount_spinlock_init(&conf->gen_lock, &conf->device_lock); mutex_init(&conf->cache_size_mutex); + init_waitqueue_head(&conf->wait_for_quiescent); init_waitqueue_head(&conf->wait_for_stripe); init_waitqueue_head(&conf->wait_for_overlap); @@ -7242,7 +7274,7 @@ static struct r5conf *setup_conf(struct mddev *mddev) rdev_for_each(rdev, mddev) { if (test_bit(Journal, &rdev->flags)) continue; - if (blk_queue_nonrot(bdev_get_queue(rdev->bdev))) { + if (bdev_nonrot(rdev->bdev)) { conf->batch_bio_dispatch = false; break; } @@ -7302,11 +7334,13 @@ static struct r5conf *setup_conf(struct mddev *mddev) conf->level = mddev->new_level; conf->chunk_sectors = mddev->new_chunk_sectors; - if (raid5_alloc_percpu(conf) != 0) + ret = raid5_alloc_percpu(conf); + if (ret) goto abort; pr_debug("raid456: run(%s) called.\n", mdname(mddev)); + ret = -EIO; rdev_for_each(rdev, mddev) { raid_disk = rdev->raid_disk; if (raid_disk >= max_disks @@ -7317,11 +7351,11 @@ static struct r5conf *setup_conf(struct mddev *mddev) if (test_bit(Replacement, &rdev->flags)) { if (disk->replacement) goto abort; - disk->replacement = rdev; + RCU_INIT_POINTER(disk->replacement, rdev); } else { if (disk->rdev) goto abort; - disk->rdev = rdev; + RCU_INIT_POINTER(disk->rdev, rdev); } if (test_bit(In_sync, &rdev->flags)) { @@ -7370,6 +7404,7 @@ static struct r5conf *setup_conf(struct mddev *mddev) if (grow_stripes(conf, conf->min_nr_stripes)) { pr_warn("md/raid:%s: couldn't allocate %dkB for buffers\n", mdname(mddev), memory); + ret = -ENOMEM; goto abort; } else pr_debug("md/raid:%s: allocated %dkB\n", mdname(mddev), memory); @@ -7383,7 +7418,8 @@ static struct r5conf *setup_conf(struct mddev *mddev) conf->shrinker.count_objects = raid5_cache_count; conf->shrinker.batch = 128; conf->shrinker.flags = 0; - if (register_shrinker(&conf->shrinker)) { + ret = register_shrinker(&conf->shrinker); + if (ret) { pr_warn("md/raid:%s: couldn't register shrinker.\n", mdname(mddev)); goto abort; @@ -7394,17 +7430,16 @@ static struct r5conf *setup_conf(struct mddev *mddev) if (!conf->thread) { pr_warn("md/raid:%s: couldn't allocate thread.\n", mdname(mddev)); + ret = -ENOMEM; goto abort; } return conf; abort: - if (conf) { + if (conf) free_conf(conf); - return ERR_PTR(-EIO); - } else - return ERR_PTR(-ENOMEM); + return ERR_PTR(ret); } static int only_parity(int raid_disk, int algo, int raid_disks, int max_degraded) @@ -7621,17 +7656,18 @@ static int raid5_run(struct mddev *mddev) for (i = 0; i < conf->raid_disks && conf->previous_raid_disks; i++) { - rdev = conf->disks[i].rdev; + rdev = rdev_mdlock_deref(mddev, conf->disks[i].rdev); if (!rdev && conf->disks[i].replacement) { /* The replacement is all we have yet */ - rdev = conf->disks[i].replacement; + rdev = rdev_mdlock_deref(mddev, + conf->disks[i].replacement); conf->disks[i].replacement = NULL; clear_bit(Replacement, &rdev->flags); - conf->disks[i].rdev = rdev; + rcu_assign_pointer(conf->disks[i].rdev, rdev); } if (!rdev) continue; - if (conf->disks[i].replacement && + if (rcu_access_pointer(conf->disks[i].replacement) && conf->reshape_progress != MaxSector) { /* replacements and reshape simply do not mix. */ pr_warn("md: cannot handle concurrent replacement and reshape.\n"); @@ -7749,7 +7785,6 @@ static int raid5_run(struct mddev *mddev) */ stripe = stripe * PAGE_SIZE; stripe = roundup_pow_of_two(stripe); - mddev->queue->limits.discard_alignment = stripe; mddev->queue->limits.discard_granularity = stripe; blk_queue_max_write_zeroes_sectors(mddev->queue, 0); @@ -7776,14 +7811,10 @@ static int raid5_run(struct mddev *mddev) * A better idea might be to turn DISCARD into WRITE_ZEROES * requests, as that is required to be safe. */ - if (devices_handle_discard_safely && - mddev->queue->limits.max_discard_sectors >= (stripe >> 9) && - mddev->queue->limits.discard_granularity >= stripe) - blk_queue_flag_set(QUEUE_FLAG_DISCARD, - mddev->queue); - else - blk_queue_flag_clear(QUEUE_FLAG_DISCARD, - mddev->queue); + if (!devices_handle_discard_safely || + mddev->queue->limits.max_discard_sectors < (stripe >> 9) || + mddev->queue->limits.discard_granularity < stripe) + blk_queue_max_discard_sectors(mddev->queue, 0); blk_queue_max_hw_sectors(mddev->queue, UINT_MAX); } @@ -7832,8 +7863,8 @@ static void raid5_status(struct seq_file *seq, struct mddev *mddev) static void print_raid5_conf (struct r5conf *conf) { + struct md_rdev *rdev; int i; - struct disk_info *tmp; pr_debug("RAID conf printout:\n"); if (!conf) { @@ -7844,50 +7875,54 @@ static void print_raid5_conf (struct r5conf *conf) conf->raid_disks, conf->raid_disks - conf->mddev->degraded); + rcu_read_lock(); for (i = 0; i < conf->raid_disks; i++) { char b[BDEVNAME_SIZE]; - tmp = conf->disks + i; - if (tmp->rdev) + rdev = rcu_dereference(conf->disks[i].rdev); + if (rdev) pr_debug(" disk %d, o:%d, dev:%s\n", - i, !test_bit(Faulty, &tmp->rdev->flags), - bdevname(tmp->rdev->bdev, b)); + i, !test_bit(Faulty, &rdev->flags), + bdevname(rdev->bdev, b)); } + rcu_read_unlock(); } static int raid5_spare_active(struct mddev *mddev) { int i; struct r5conf *conf = mddev->private; - struct disk_info *tmp; + struct md_rdev *rdev, *replacement; int count = 0; unsigned long flags; for (i = 0; i < conf->raid_disks; i++) { - tmp = conf->disks + i; - if (tmp->replacement - && tmp->replacement->recovery_offset == MaxSector - && !test_bit(Faulty, &tmp->replacement->flags) - && !test_and_set_bit(In_sync, &tmp->replacement->flags)) { + rdev = rdev_mdlock_deref(mddev, conf->disks[i].rdev); + replacement = rdev_mdlock_deref(mddev, + conf->disks[i].replacement); + if (replacement + && replacement->recovery_offset == MaxSector + && !test_bit(Faulty, &replacement->flags) + && !test_and_set_bit(In_sync, &replacement->flags)) { /* Replacement has just become active. */ - if (!tmp->rdev - || !test_and_clear_bit(In_sync, &tmp->rdev->flags)) + if (!rdev + || !test_and_clear_bit(In_sync, &rdev->flags)) count++; - if (tmp->rdev) { + if (rdev) { /* Replaced device not technically faulty, * but we need to be sure it gets removed * and never re-added. */ - set_bit(Faulty, &tmp->rdev->flags); + set_bit(Faulty, &rdev->flags); sysfs_notify_dirent_safe( - tmp->rdev->sysfs_state); + rdev->sysfs_state); } - sysfs_notify_dirent_safe(tmp->replacement->sysfs_state); - } else if (tmp->rdev - && tmp->rdev->recovery_offset == MaxSector - && !test_bit(Faulty, &tmp->rdev->flags) - && !test_and_set_bit(In_sync, &tmp->rdev->flags)) { + sysfs_notify_dirent_safe(replacement->sysfs_state); + } else if (rdev + && rdev->recovery_offset == MaxSector + && !test_bit(Faulty, &rdev->flags) + && !test_and_set_bit(In_sync, &rdev->flags)) { count++; - sysfs_notify_dirent_safe(tmp->rdev->sysfs_state); + sysfs_notify_dirent_safe(rdev->sysfs_state); } } spin_lock_irqsave(&conf->device_lock, flags); @@ -7902,8 +7937,9 @@ static int raid5_remove_disk(struct mddev *mddev, struct md_rdev *rdev) struct r5conf *conf = mddev->private; int err = 0; int number = rdev->raid_disk; - struct md_rdev **rdevp; + struct md_rdev __rcu **rdevp; struct disk_info *p = conf->disks + number; + struct md_rdev *tmp; print_raid5_conf(conf); if (test_bit(Journal, &rdev->flags) && conf->log) { @@ -7921,9 +7957,9 @@ static int raid5_remove_disk(struct mddev *mddev, struct md_rdev *rdev) log_exit(conf); return 0; } - if (rdev == p->rdev) + if (rdev == rcu_access_pointer(p->rdev)) rdevp = &p->rdev; - else if (rdev == p->replacement) + else if (rdev == rcu_access_pointer(p->replacement)) rdevp = &p->replacement; else return 0; @@ -7943,18 +7979,20 @@ static int raid5_remove_disk(struct mddev *mddev, struct md_rdev *rdev) if (!test_bit(Faulty, &rdev->flags) && mddev->recovery_disabled != conf->recovery_disabled && !has_failed(conf) && - (!p->replacement || p->replacement == rdev) && + (!rcu_access_pointer(p->replacement) || + rcu_access_pointer(p->replacement) == rdev) && number < conf->raid_disks) { err = -EBUSY; goto abort; } *rdevp = NULL; if (!test_bit(RemoveSynchronized, &rdev->flags)) { + lockdep_assert_held(&mddev->reconfig_mutex); synchronize_rcu(); if (atomic_read(&rdev->nr_pending)) { /* lost the race, try later */ err = -EBUSY; - *rdevp = rdev; + rcu_assign_pointer(*rdevp, rdev); } } if (!err) { @@ -7962,17 +8000,19 @@ static int raid5_remove_disk(struct mddev *mddev, struct md_rdev *rdev) if (err) goto abort; } - if (p->replacement) { + + tmp = rcu_access_pointer(p->replacement); + if (tmp) { /* We must have just cleared 'rdev' */ - p->rdev = p->replacement; - clear_bit(Replacement, &p->replacement->flags); + rcu_assign_pointer(p->rdev, tmp); + clear_bit(Replacement, &tmp->flags); smp_mb(); /* Make sure other CPUs may see both as identical * but will never see neither - if they are careful */ - p->replacement = NULL; + rcu_assign_pointer(p->replacement, NULL); if (!err) - err = log_modify(conf, p->rdev, true); + err = log_modify(conf, tmp, true); } clear_bit(WantReplacement, &rdev->flags); @@ -7988,6 +8028,7 @@ static int raid5_add_disk(struct mddev *mddev, struct md_rdev *rdev) int ret, err = -EEXIST; int disk; struct disk_info *p; + struct md_rdev *tmp; int first = 0; int last = conf->raid_disks - 1; @@ -8045,7 +8086,8 @@ static int raid5_add_disk(struct mddev *mddev, struct md_rdev *rdev) } for (disk = first; disk <= last; disk++) { p = conf->disks + disk; - if (test_bit(WantReplacement, &p->rdev->flags) && + tmp = rdev_mdlock_deref(mddev, p->rdev); + if (test_bit(WantReplacement, &tmp->flags) && p->replacement == NULL) { clear_bit(In_sync, &rdev->flags); set_bit(Replacement, &rdev->flags); @@ -8336,6 +8378,7 @@ static void end_reshape(struct r5conf *conf) static void raid5_finish_reshape(struct mddev *mddev) { struct r5conf *conf = mddev->private; + struct md_rdev *rdev; if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery)) { @@ -8347,10 +8390,12 @@ static void raid5_finish_reshape(struct mddev *mddev) for (d = conf->raid_disks ; d < conf->raid_disks - mddev->delta_disks; d++) { - struct md_rdev *rdev = conf->disks[d].rdev; + rdev = rdev_mdlock_deref(mddev, + conf->disks[d].rdev); if (rdev) clear_bit(In_sync, &rdev->flags); - rdev = conf->disks[d].replacement; + rdev = rdev_mdlock_deref(mddev, + conf->disks[d].replacement); if (rdev) clear_bit(In_sync, &rdev->flags); } diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h index 9e8486a9e445..638d29863503 100644 --- a/drivers/md/raid5.h +++ b/drivers/md/raid5.h @@ -473,7 +473,8 @@ enum { */ struct disk_info { - struct md_rdev *rdev, *replacement; + struct md_rdev __rcu *rdev; + struct md_rdev __rcu *replacement; struct page *extra_page; /* extra page to use in prexor */ }; @@ -560,6 +561,16 @@ struct r5pending_data { struct bio_list bios; }; +struct raid5_percpu { + struct page *spare_page; /* Used when checking P/Q in raid6 */ + void *scribble; /* space for constructing buffer + * lists and performing address + * conversions + */ + int scribble_obj_size; + local_lock_t lock; +}; + struct r5conf { struct hlist_head *stripe_hashtbl; /* only protect corresponding hash list and inactive_list */ @@ -635,15 +646,7 @@ struct r5conf { */ int recovery_disabled; /* per cpu variables */ - struct raid5_percpu { - struct page *spare_page; /* Used when checking P/Q in raid6 */ - void *scribble; /* space for constructing buffer - * lists and performing address - * conversions - */ - int scribble_obj_size; - local_lock_t lock; - } __percpu *percpu; + struct raid5_percpu __percpu *percpu; int scribble_disks; int scribble_sectors; struct hlist_node node; diff --git a/drivers/media/cec/core/cec-adap.c b/drivers/media/cec/core/cec-adap.c index 2e12331c12a9..8bf91b5a7d0e 100644 --- a/drivers/media/cec/core/cec-adap.c +++ b/drivers/media/cec/core/cec-adap.c @@ -27,27 +27,6 @@ static void cec_fill_msg_report_features(struct cec_adapter *adap, struct cec_msg *msg, unsigned int la_idx); -/* - * 400 ms is the time it takes for one 16 byte message to be - * transferred and 5 is the maximum number of retries. Add - * another 100 ms as a margin. So if the transmit doesn't - * finish before that time something is really wrong and we - * have to time out. - * - * This is a sign that something it really wrong and a warning - * will be issued. - */ -#define CEC_XFER_TIMEOUT_MS (5 * 400 + 100) - -#define call_op(adap, op, arg...) \ - (adap->ops->op ? adap->ops->op(adap, ## arg) : 0) - -#define call_void_op(adap, op, arg...) \ - do { \ - if (adap->ops->op) \ - adap->ops->op(adap, ## arg); \ - } while (0) - static int cec_log_addr2idx(const struct cec_adapter *adap, u8 log_addr) { int i; @@ -366,38 +345,48 @@ static void cec_data_completed(struct cec_data *data) /* * A pending CEC transmit needs to be cancelled, either because the CEC * adapter is disabled or the transmit takes an impossibly long time to - * finish. + * finish, or the reply timed out. * * This function is called with adap->lock held. */ -static void cec_data_cancel(struct cec_data *data, u8 tx_status) +static void cec_data_cancel(struct cec_data *data, u8 tx_status, u8 rx_status) { + struct cec_adapter *adap = data->adap; + /* * It's either the current transmit, or it is a pending * transmit. Take the appropriate action to clear it. */ - if (data->adap->transmitting == data) { - data->adap->transmitting = NULL; + if (adap->transmitting == data) { + adap->transmitting = NULL; } else { list_del_init(&data->list); if (!(data->msg.tx_status & CEC_TX_STATUS_OK)) - if (!WARN_ON(!data->adap->transmit_queue_sz)) - data->adap->transmit_queue_sz--; + if (!WARN_ON(!adap->transmit_queue_sz)) + adap->transmit_queue_sz--; } if (data->msg.tx_status & CEC_TX_STATUS_OK) { data->msg.rx_ts = ktime_get_ns(); - data->msg.rx_status = CEC_RX_STATUS_ABORTED; + data->msg.rx_status = rx_status; + if (!data->blocking) + data->msg.tx_status = 0; } else { data->msg.tx_ts = ktime_get_ns(); data->msg.tx_status |= tx_status | CEC_TX_STATUS_MAX_RETRIES; data->msg.tx_error_cnt++; data->attempts = 0; + if (!data->blocking) + data->msg.rx_status = 0; } /* Queue transmitted message for monitoring purposes */ - cec_queue_msg_monitor(data->adap, &data->msg, 1); + cec_queue_msg_monitor(adap, &data->msg, 1); + + if (!data->blocking && data->msg.sequence) + /* Allow drivers to process the message first */ + call_op(adap, received, &data->msg); cec_data_completed(data); } @@ -418,15 +407,15 @@ static void cec_flush(struct cec_adapter *adap) while (!list_empty(&adap->transmit_queue)) { data = list_first_entry(&adap->transmit_queue, struct cec_data, list); - cec_data_cancel(data, CEC_TX_STATUS_ABORTED); + cec_data_cancel(data, CEC_TX_STATUS_ABORTED, 0); } if (adap->transmitting) - cec_data_cancel(adap->transmitting, CEC_TX_STATUS_ABORTED); + adap->transmit_in_progress_aborted = true; /* Cancel the pending timeout work. */ list_for_each_entry_safe(data, n, &adap->wait_queue, list) { if (cancel_delayed_work(&data->work)) - cec_data_cancel(data, CEC_TX_STATUS_OK); + cec_data_cancel(data, CEC_TX_STATUS_OK, CEC_RX_STATUS_ABORTED); /* * If cancel_delayed_work returned false, then * the cec_wait_timeout function is running, @@ -482,7 +471,7 @@ int cec_thread_func(void *_adap) kthread_should_stop() || (!adap->transmit_in_progress && !list_empty(&adap->transmit_queue)), - msecs_to_jiffies(CEC_XFER_TIMEOUT_MS)); + msecs_to_jiffies(adap->xfer_timeout_ms)); timeout = err == 0; } else { /* Otherwise we just wait for something to happen. */ @@ -508,7 +497,8 @@ int cec_thread_func(void *_adap) * adapter driver, or the CEC bus is in some weird * state. On rare occasions it can happen if there is * so much traffic on the bus that the adapter was - * unable to transmit for CEC_XFER_TIMEOUT_MS (2.1s). + * unable to transmit for xfer_timeout_ms (2.1s by + * default). */ if (adap->transmitting) { pr_warn("cec-%s: message %*ph timed out\n", adap->name, @@ -516,7 +506,7 @@ int cec_thread_func(void *_adap) adap->transmitting->msg.msg); /* Just give up on this. */ cec_data_cancel(adap->transmitting, - CEC_TX_STATUS_TIMEOUT); + CEC_TX_STATUS_TIMEOUT, 0); } else { pr_warn("cec-%s: transmit timed out\n", adap->name); } @@ -572,10 +562,11 @@ int cec_thread_func(void *_adap) if (data->attempts == 0) data->attempts = attempts; + adap->transmit_in_progress_aborted = false; /* Tell the adapter to transmit, cancel on error */ - if (adap->ops->adap_transmit(adap, data->attempts, - signal_free_time, &data->msg)) - cec_data_cancel(data, CEC_TX_STATUS_ABORTED); + if (call_op(adap, adap_transmit, data->attempts, + signal_free_time, &data->msg)) + cec_data_cancel(data, CEC_TX_STATUS_ABORTED, 0); else adap->transmit_in_progress = true; @@ -599,6 +590,8 @@ void cec_transmit_done_ts(struct cec_adapter *adap, u8 status, struct cec_msg *msg; unsigned int attempts_made = arb_lost_cnt + nack_cnt + low_drive_cnt + error_cnt; + bool done = status & (CEC_TX_STATUS_MAX_RETRIES | CEC_TX_STATUS_OK); + bool aborted = adap->transmit_in_progress_aborted; dprintk(2, "%s: status 0x%02x\n", __func__, status); if (attempts_made < 1) @@ -619,6 +612,7 @@ void cec_transmit_done_ts(struct cec_adapter *adap, u8 status, goto wake_thread; } adap->transmit_in_progress = false; + adap->transmit_in_progress_aborted = false; msg = &data->msg; @@ -639,8 +633,7 @@ void cec_transmit_done_ts(struct cec_adapter *adap, u8 status, * the hardware didn't signal that it retried itself (by setting * CEC_TX_STATUS_MAX_RETRIES), then we will retry ourselves. */ - if (data->attempts > attempts_made && - !(status & (CEC_TX_STATUS_MAX_RETRIES | CEC_TX_STATUS_OK))) { + if (!aborted && data->attempts > attempts_made && !done) { /* Retry this message */ data->attempts -= attempts_made; if (msg->timeout) @@ -655,6 +648,8 @@ void cec_transmit_done_ts(struct cec_adapter *adap, u8 status, goto wake_thread; } + if (aborted && !done) + status |= CEC_TX_STATUS_ABORTED; data->attempts = 0; /* Always set CEC_TX_STATUS_MAX_RETRIES on error */ @@ -733,9 +728,7 @@ static void cec_wait_timeout(struct work_struct *work) /* Mark the message as timed out */ list_del_init(&data->list); - data->msg.rx_ts = ktime_get_ns(); - data->msg.rx_status = CEC_RX_STATUS_TIMEOUT; - cec_data_completed(data); + cec_data_cancel(data, CEC_TX_STATUS_OK, CEC_RX_STATUS_TIMEOUT); unlock: mutex_unlock(&adap->lock); } @@ -921,8 +914,12 @@ int cec_transmit_msg_fh(struct cec_adapter *adap, struct cec_msg *msg, mutex_lock(&adap->lock); /* Cancel the transmit if it was interrupted */ - if (!data->completed) - cec_data_cancel(data, CEC_TX_STATUS_ABORTED); + if (!data->completed) { + if (data->msg.tx_status & CEC_TX_STATUS_OK) + cec_data_cancel(data, CEC_TX_STATUS_OK, CEC_RX_STATUS_ABORTED); + else + cec_data_cancel(data, CEC_TX_STATUS_ABORTED, 0); + } /* The transmit completed (possibly with an error) */ *msg = data->msg; @@ -1278,17 +1275,22 @@ static int cec_config_log_addr(struct cec_adapter *adap, * While trying to poll the physical address was reset * and the adapter was unconfigured, so bail out. */ - if (!adap->is_configuring) + if (adap->phys_addr == CEC_PHYS_ADDR_INVALID) + return -EINTR; + + /* Also bail out if the PA changed while configuring. */ + if (adap->must_reconfigure) return -EINTR; if (err) return err; /* - * The message was aborted due to a disconnect or + * The message was aborted or timed out due to a disconnect or * unconfigure, just bail out. */ - if (msg.tx_status & CEC_TX_STATUS_ABORTED) + if (msg.tx_status & + (CEC_TX_STATUS_ABORTED | CEC_TX_STATUS_TIMEOUT)) return -EINTR; if (msg.tx_status & CEC_TX_STATUS_OK) return 0; @@ -1314,7 +1316,7 @@ static int cec_config_log_addr(struct cec_adapter *adap, * Message not acknowledged, so this logical * address is free to use. */ - err = adap->ops->adap_log_addr(adap, log_addr); + err = call_op(adap, adap_log_addr, log_addr); if (err) return err; @@ -1331,15 +1333,14 @@ static int cec_config_log_addr(struct cec_adapter *adap, */ static void cec_adap_unconfigure(struct cec_adapter *adap) { - if (!adap->needs_hpd || - adap->phys_addr != CEC_PHYS_ADDR_INVALID) - WARN_ON(adap->ops->adap_log_addr(adap, CEC_LOG_ADDR_INVALID)); + if (!adap->needs_hpd || adap->phys_addr != CEC_PHYS_ADDR_INVALID) + WARN_ON(call_op(adap, adap_log_addr, CEC_LOG_ADDR_INVALID)); adap->log_addrs.log_addr_mask = 0; - adap->is_configuring = false; adap->is_configured = false; cec_flush(adap); wake_up_interruptible(&adap->kthread_waitq); cec_post_state_event(adap); + call_void_op(adap, adap_configured, false); } /* @@ -1408,6 +1409,7 @@ static int cec_config_thread_func(void *arg) if (las->log_addr_type[0] == CEC_LOG_ADDR_TYPE_UNREGISTERED) goto configured; +reconfigure: for (i = 0; i < las->num_log_addrs; i++) { unsigned int type = las->log_addr_type[i]; const u8 *la_list; @@ -1430,6 +1432,13 @@ static int cec_config_thread_func(void *arg) last_la = la_list[0]; err = cec_config_log_addr(adap, i, last_la); + + if (adap->must_reconfigure) { + adap->must_reconfigure = false; + las->log_addr_mask = 0; + goto reconfigure; + } + if (err > 0) /* Reused last LA */ continue; @@ -1475,6 +1484,7 @@ configured: las->log_addr[i] = CEC_LOG_ADDR_INVALID; adap->is_configured = true; adap->is_configuring = false; + adap->must_reconfigure = false; cec_post_state_event(adap); /* @@ -1521,15 +1531,18 @@ configured: adap->kthread_config = NULL; complete(&adap->config_completion); mutex_unlock(&adap->lock); + call_void_op(adap, adap_configured, true); return 0; unconfigure: for (i = 0; i < las->num_log_addrs; i++) las->log_addr[i] = CEC_LOG_ADDR_INVALID; cec_adap_unconfigure(adap); + adap->is_configuring = false; + adap->must_reconfigure = false; adap->kthread_config = NULL; - mutex_unlock(&adap->lock); complete(&adap->config_completion); + mutex_unlock(&adap->lock); return 0; } @@ -1552,6 +1565,7 @@ static void cec_claim_log_addrs(struct cec_adapter *adap, bool block) "ceccfg-%s", adap->name); if (IS_ERR(adap->kthread_config)) { adap->kthread_config = NULL; + adap->is_configuring = false; } else if (block) { mutex_unlock(&adap->lock); wait_for_completion(&adap->config_completion); @@ -1559,63 +1573,96 @@ static void cec_claim_log_addrs(struct cec_adapter *adap, bool block) } } +/* + * Helper function to enable/disable the CEC adapter. + * + * This function is called with adap->lock held. + */ +static int cec_adap_enable(struct cec_adapter *adap) +{ + bool enable; + int ret = 0; + + enable = adap->monitor_all_cnt || adap->monitor_pin_cnt || + adap->log_addrs.num_log_addrs; + if (adap->needs_hpd) + enable = enable && adap->phys_addr != CEC_PHYS_ADDR_INVALID; + + if (enable == adap->is_enabled) + return 0; + + /* serialize adap_enable */ + mutex_lock(&adap->devnode.lock); + if (enable) { + adap->last_initiator = 0xff; + adap->transmit_in_progress = false; + ret = adap->ops->adap_enable(adap, true); + if (!ret) { + /* + * Enable monitor-all/pin modes if needed. We warn, but + * continue if this fails as this is not a critical error. + */ + if (adap->monitor_all_cnt) + WARN_ON(call_op(adap, adap_monitor_all_enable, true)); + if (adap->monitor_pin_cnt) + WARN_ON(call_op(adap, adap_monitor_pin_enable, true)); + } + } else { + /* Disable monitor-all/pin modes if needed (needs_hpd == 1) */ + if (adap->monitor_all_cnt) + WARN_ON(call_op(adap, adap_monitor_all_enable, false)); + if (adap->monitor_pin_cnt) + WARN_ON(call_op(adap, adap_monitor_pin_enable, false)); + WARN_ON(adap->ops->adap_enable(adap, false)); + adap->last_initiator = 0xff; + adap->transmit_in_progress = false; + adap->transmit_in_progress_aborted = false; + if (adap->transmitting) + cec_data_cancel(adap->transmitting, CEC_TX_STATUS_ABORTED, 0); + } + if (!ret) + adap->is_enabled = enable; + wake_up_interruptible(&adap->kthread_waitq); + mutex_unlock(&adap->devnode.lock); + return ret; +} + /* Set a new physical address and send an event notifying userspace of this. * * This function is called with adap->lock held. */ void __cec_s_phys_addr(struct cec_adapter *adap, u16 phys_addr, bool block) { + bool becomes_invalid = phys_addr == CEC_PHYS_ADDR_INVALID; + bool is_invalid = adap->phys_addr == CEC_PHYS_ADDR_INVALID; + if (phys_addr == adap->phys_addr) return; - if (phys_addr != CEC_PHYS_ADDR_INVALID && adap->devnode.unregistered) + if (!becomes_invalid && adap->devnode.unregistered) return; dprintk(1, "new physical address %x.%x.%x.%x\n", cec_phys_addr_exp(phys_addr)); - if (phys_addr == CEC_PHYS_ADDR_INVALID || - adap->phys_addr != CEC_PHYS_ADDR_INVALID) { + if (becomes_invalid || !is_invalid) { adap->phys_addr = CEC_PHYS_ADDR_INVALID; cec_post_state_event(adap); cec_adap_unconfigure(adap); - /* Disabling monitor all mode should always succeed */ - if (adap->monitor_all_cnt) - WARN_ON(call_op(adap, adap_monitor_all_enable, false)); - /* serialize adap_enable */ - mutex_lock(&adap->devnode.lock); - if (adap->needs_hpd || list_empty(&adap->devnode.fhs)) { - WARN_ON(adap->ops->adap_enable(adap, false)); - adap->transmit_in_progress = false; - wake_up_interruptible(&adap->kthread_waitq); - } - mutex_unlock(&adap->devnode.lock); - if (phys_addr == CEC_PHYS_ADDR_INVALID) - return; - } - - /* serialize adap_enable */ - mutex_lock(&adap->devnode.lock); - adap->last_initiator = 0xff; - adap->transmit_in_progress = false; - - if (adap->needs_hpd || list_empty(&adap->devnode.fhs)) { - if (adap->ops->adap_enable(adap, true)) { - mutex_unlock(&adap->devnode.lock); + if (becomes_invalid) { + cec_adap_enable(adap); return; } } - if (adap->monitor_all_cnt && - call_op(adap, adap_monitor_all_enable, true)) { - if (adap->needs_hpd || list_empty(&adap->devnode.fhs)) - WARN_ON(adap->ops->adap_enable(adap, false)); - mutex_unlock(&adap->devnode.lock); - return; - } - mutex_unlock(&adap->devnode.lock); - adap->phys_addr = phys_addr; + if (is_invalid) + cec_adap_enable(adap); + cec_post_state_event(adap); - if (adap->log_addrs.num_log_addrs) + if (!adap->log_addrs.num_log_addrs) + return; + if (adap->is_configuring) + adap->must_reconfigure = true; + else cec_claim_log_addrs(adap, block); } @@ -1670,19 +1717,24 @@ int __cec_s_log_addrs(struct cec_adapter *adap, struct cec_log_addrs *log_addrs, bool block) { u16 type_mask = 0; + int err; int i; if (adap->devnode.unregistered) return -ENODEV; if (!log_addrs || log_addrs->num_log_addrs == 0) { - cec_adap_unconfigure(adap); + if (!adap->log_addrs.num_log_addrs) + return 0; + if (adap->is_configuring || adap->is_configured) + cec_adap_unconfigure(adap); adap->log_addrs.num_log_addrs = 0; for (i = 0; i < CEC_MAX_LOG_ADDRS; i++) adap->log_addrs.log_addr[i] = CEC_LOG_ADDR_INVALID; adap->log_addrs.osd_name[0] = '\0'; adap->log_addrs.vendor_id = CEC_VENDOR_ID_NONE; adap->log_addrs.cec_version = CEC_OP_CEC_VERSION_2_0; + cec_adap_enable(adap); return 0; } @@ -1818,9 +1870,10 @@ int __cec_s_log_addrs(struct cec_adapter *adap, log_addrs->log_addr_mask = adap->log_addrs.log_addr_mask; adap->log_addrs = *log_addrs; - if (adap->phys_addr != CEC_PHYS_ADDR_INVALID) + err = cec_adap_enable(adap); + if (!err && adap->phys_addr != CEC_PHYS_ADDR_INVALID) cec_claim_log_addrs(adap, block); - return 0; + return err; } int cec_s_log_addrs(struct cec_adapter *adap, @@ -1922,11 +1975,10 @@ static int cec_receive_notify(struct cec_adapter *adap, struct cec_msg *msg, msg->msg[1] != CEC_MSG_CDC_MESSAGE) return 0; - if (adap->ops->received) { - /* Allow drivers to process the message first */ - if (adap->ops->received(adap, msg) != -ENOMSG) - return 0; - } + /* Allow drivers to process the message first */ + if (adap->ops->received && !adap->devnode.unregistered && + adap->ops->received(adap, msg) != -ENOMSG) + return 0; /* * REPORT_PHYSICAL_ADDR, CEC_MSG_USER_CONTROL_PRESSED and @@ -2119,20 +2171,25 @@ skip_processing: */ int cec_monitor_all_cnt_inc(struct cec_adapter *adap) { - int ret = 0; + int ret; + + if (adap->monitor_all_cnt++) + return 0; - if (adap->monitor_all_cnt == 0) - ret = call_op(adap, adap_monitor_all_enable, 1); - if (ret == 0) - adap->monitor_all_cnt++; + ret = cec_adap_enable(adap); + if (ret) + adap->monitor_all_cnt--; return ret; } void cec_monitor_all_cnt_dec(struct cec_adapter *adap) { - adap->monitor_all_cnt--; - if (adap->monitor_all_cnt == 0) - WARN_ON(call_op(adap, adap_monitor_all_enable, 0)); + if (WARN_ON(!adap->monitor_all_cnt)) + return; + if (--adap->monitor_all_cnt) + return; + WARN_ON(call_op(adap, adap_monitor_all_enable, false)); + cec_adap_enable(adap); } /* @@ -2142,20 +2199,25 @@ void cec_monitor_all_cnt_dec(struct cec_adapter *adap) */ int cec_monitor_pin_cnt_inc(struct cec_adapter *adap) { - int ret = 0; + int ret; + + if (adap->monitor_pin_cnt++) + return 0; - if (adap->monitor_pin_cnt == 0) - ret = call_op(adap, adap_monitor_pin_enable, 1); - if (ret == 0) - adap->monitor_pin_cnt++; + ret = cec_adap_enable(adap); + if (ret) + adap->monitor_pin_cnt--; return ret; } void cec_monitor_pin_cnt_dec(struct cec_adapter *adap) { - adap->monitor_pin_cnt--; - if (adap->monitor_pin_cnt == 0) - WARN_ON(call_op(adap, adap_monitor_pin_enable, 0)); + if (WARN_ON(!adap->monitor_pin_cnt)) + return; + if (--adap->monitor_pin_cnt) + return; + WARN_ON(call_op(adap, adap_monitor_pin_enable, false)); + cec_adap_enable(adap); } #ifdef CONFIG_DEBUG_FS @@ -2169,6 +2231,7 @@ int cec_adap_status(struct seq_file *file, void *priv) struct cec_data *data; mutex_lock(&adap->lock); + seq_printf(file, "enabled: %d\n", adap->is_enabled); seq_printf(file, "configured: %d\n", adap->is_configured); seq_printf(file, "configuring: %d\n", adap->is_configuring); seq_printf(file, "phys_addr: %x.%x.%x.%x\n", @@ -2183,6 +2246,9 @@ int cec_adap_status(struct seq_file *file, void *priv) if (adap->monitor_all_cnt) seq_printf(file, "file handles in Monitor All mode: %u\n", adap->monitor_all_cnt); + if (adap->monitor_pin_cnt) + seq_printf(file, "file handles in Monitor Pin mode: %u\n", + adap->monitor_pin_cnt); if (adap->tx_timeouts) { seq_printf(file, "transmit timeouts: %u\n", adap->tx_timeouts); diff --git a/drivers/media/cec/core/cec-api.c b/drivers/media/cec/core/cec-api.c index d72ad48c9898..67dc79ef1705 100644 --- a/drivers/media/cec/core/cec-api.c +++ b/drivers/media/cec/core/cec-api.c @@ -586,18 +586,6 @@ static int cec_open(struct inode *inode, struct file *filp) return err; } - /* serialize adap_enable */ - mutex_lock(&devnode->lock); - if (list_empty(&devnode->fhs) && - !adap->needs_hpd && - adap->phys_addr == CEC_PHYS_ADDR_INVALID) { - err = adap->ops->adap_enable(adap, true); - if (err) { - mutex_unlock(&devnode->lock); - kfree(fh); - return err; - } - } filp->private_data = fh; /* Queue up initial state events */ @@ -607,7 +595,8 @@ static int cec_open(struct inode *inode, struct file *filp) adap->conn_info.type != CEC_CONNECTOR_TYPE_NO_CONNECTOR; cec_queue_event_fh(fh, &ev, 0); #ifdef CONFIG_CEC_PIN - if (adap->pin && adap->pin->ops->read_hpd) { + if (adap->pin && adap->pin->ops->read_hpd && + !adap->devnode.unregistered) { err = adap->pin->ops->read_hpd(adap); if (err >= 0) { ev.event = err ? CEC_EVENT_PIN_HPD_HIGH : @@ -615,7 +604,8 @@ static int cec_open(struct inode *inode, struct file *filp) cec_queue_event_fh(fh, &ev, 0); } } - if (adap->pin && adap->pin->ops->read_5v) { + if (adap->pin && adap->pin->ops->read_5v && + !adap->devnode.unregistered) { err = adap->pin->ops->read_5v(adap); if (err >= 0) { ev.event = err ? CEC_EVENT_PIN_5V_HIGH : @@ -625,6 +615,7 @@ static int cec_open(struct inode *inode, struct file *filp) } #endif + mutex_lock(&devnode->lock); mutex_lock(&devnode->lock_fhs); list_add(&fh->list, &devnode->fhs); mutex_unlock(&devnode->lock_fhs); @@ -656,15 +647,10 @@ static int cec_release(struct inode *inode, struct file *filp) cec_monitor_all_cnt_dec(adap); mutex_unlock(&adap->lock); - /* serialize adap_enable */ mutex_lock(&devnode->lock); mutex_lock(&devnode->lock_fhs); list_del(&fh->list); mutex_unlock(&devnode->lock_fhs); - if (cec_is_registered(adap) && list_empty(&devnode->fhs) && - !adap->needs_hpd && adap->phys_addr == CEC_PHYS_ADDR_INVALID) { - WARN_ON(adap->ops->adap_enable(adap, false)); - } mutex_unlock(&devnode->lock); /* Unhook pending transmits from this filehandle. */ diff --git a/drivers/media/cec/core/cec-core.c b/drivers/media/cec/core/cec-core.c index a3ab6a43fb14..af358e901b5f 100644 --- a/drivers/media/cec/core/cec-core.c +++ b/drivers/media/cec/core/cec-core.c @@ -20,6 +20,18 @@ #define CEC_NUM_DEVICES 256 #define CEC_NAME "cec" +/* + * 400 ms is the time it takes for one 16 byte message to be + * transferred and 5 is the maximum number of retries. Add + * another 100 ms as a margin. So if the transmit doesn't + * finish before that time something is really wrong and we + * have to time out. + * + * This is a sign that something it really wrong and a warning + * will be issued. + */ +#define CEC_XFER_TIMEOUT_MS (5 * 400 + 100) + int cec_debug; module_param_named(debug, cec_debug, int, 0644); MODULE_PARM_DESC(debug, "debug level (0-2)"); @@ -204,7 +216,7 @@ static ssize_t cec_error_inj_write(struct file *file, line = strsep(&p, "\n"); if (!*line || *line == '#') continue; - if (!adap->ops->error_inj_parse_line(adap, line)) { + if (!call_op(adap, error_inj_parse_line, line)) { kfree(buf); return -EINVAL; } @@ -217,7 +229,7 @@ static int cec_error_inj_show(struct seq_file *sf, void *unused) { struct cec_adapter *adap = sf->private; - return adap->ops->error_inj_show(adap, sf); + return call_op(adap, error_inj_show, sf); } static int cec_error_inj_open(struct inode *inode, struct file *file) @@ -331,6 +343,8 @@ int cec_register_adapter(struct cec_adapter *adap, adap->owner = parent->driver->owner; adap->devnode.dev.parent = parent; + if (!adap->xfer_timeout_ms) + adap->xfer_timeout_ms = CEC_XFER_TIMEOUT_MS; #ifdef CONFIG_MEDIA_CEC_RC if (adap->capabilities & CEC_CAP_RC) { diff --git a/drivers/media/cec/core/cec-pin-priv.h b/drivers/media/cec/core/cec-pin-priv.h index 7bad5a0b7cb7..8eb5819e6ccb 100644 --- a/drivers/media/cec/core/cec-pin-priv.h +++ b/drivers/media/cec/core/cec-pin-priv.h @@ -12,6 +12,17 @@ #include <linux/atomic.h> #include <media/cec-pin.h> +#define call_pin_op(pin, op, arg...) \ + ((pin && pin->ops->op && !pin->adap->devnode.unregistered) ? \ + pin->ops->op(pin->adap, ## arg) : 0) + +#define call_void_pin_op(pin, op, arg...) \ + do { \ + if (pin && pin->ops->op && \ + !pin->adap->devnode.unregistered) \ + pin->ops->op(pin->adap, ## arg); \ + } while (0) + enum cec_pin_state { /* CEC is off */ CEC_ST_OFF, diff --git a/drivers/media/cec/core/cec-pin.c b/drivers/media/cec/core/cec-pin.c index 21f0f749713e..68353c5dc501 100644 --- a/drivers/media/cec/core/cec-pin.c +++ b/drivers/media/cec/core/cec-pin.c @@ -135,7 +135,7 @@ static void cec_pin_update(struct cec_pin *pin, bool v, bool force) static bool cec_pin_read(struct cec_pin *pin) { - bool v = pin->ops->read(pin->adap); + bool v = call_pin_op(pin, read); cec_pin_update(pin, v, false); return v; @@ -143,13 +143,13 @@ static bool cec_pin_read(struct cec_pin *pin) static void cec_pin_low(struct cec_pin *pin) { - pin->ops->low(pin->adap); + call_void_pin_op(pin, low); cec_pin_update(pin, false, false); } static bool cec_pin_high(struct cec_pin *pin) { - pin->ops->high(pin->adap); + call_void_pin_op(pin, high); return cec_pin_read(pin); } @@ -1037,11 +1037,14 @@ static int cec_pin_thread_func(void *_adap) for (;;) { wait_event_interruptible(pin->kthread_waitq, - kthread_should_stop() || - pin->work_rx_msg.len || - pin->work_tx_status || - atomic_read(&pin->work_irq_change) || - atomic_read(&pin->work_pin_num_events)); + kthread_should_stop() || + pin->work_rx_msg.len || + pin->work_tx_status || + atomic_read(&pin->work_irq_change) || + atomic_read(&pin->work_pin_num_events)); + + if (kthread_should_stop()) + break; if (pin->work_rx_msg.len) { struct cec_msg *msg = &pin->work_rx_msg; @@ -1086,10 +1089,12 @@ static int cec_pin_thread_func(void *_adap) CEC_PIN_IRQ_UNCHANGED)) { case CEC_PIN_IRQ_DISABLE: if (irq_enabled) { - pin->ops->disable_irq(adap); + call_void_pin_op(pin, disable_irq); irq_enabled = false; } cec_pin_high(pin); + if (pin->state == CEC_ST_OFF) + break; cec_pin_to_idle(pin); hrtimer_start(&pin->timer, ns_to_ktime(0), HRTIMER_MODE_REL); @@ -1097,7 +1102,7 @@ static int cec_pin_thread_func(void *_adap) case CEC_PIN_IRQ_ENABLE: if (irq_enabled) break; - pin->enable_irq_failed = !pin->ops->enable_irq(adap); + pin->enable_irq_failed = !call_pin_op(pin, enable_irq); if (pin->enable_irq_failed) { cec_pin_to_idle(pin); hrtimer_start(&pin->timer, ns_to_ktime(0), @@ -1109,15 +1114,7 @@ static int cec_pin_thread_func(void *_adap) default: break; } - if (kthread_should_stop()) - break; } - if (pin->ops->disable_irq && irq_enabled) - pin->ops->disable_irq(adap); - hrtimer_cancel(&pin->timer); - cec_pin_read(pin); - cec_pin_to_idle(pin); - pin->state = CEC_ST_OFF; return 0; } @@ -1126,24 +1123,32 @@ static int cec_pin_adap_enable(struct cec_adapter *adap, bool enable) struct cec_pin *pin = adap->pin; if (enable) { - atomic_set(&pin->work_pin_num_events, 0); - pin->work_pin_events_rd = pin->work_pin_events_wr = 0; - pin->work_pin_events_dropped = false; cec_pin_read(pin); cec_pin_to_idle(pin); pin->tx_msg.len = 0; pin->timer_ts = ns_to_ktime(0); atomic_set(&pin->work_irq_change, CEC_PIN_IRQ_UNCHANGED); - pin->kthread = kthread_run(cec_pin_thread_func, adap, - "cec-pin"); - if (IS_ERR(pin->kthread)) { - pr_err("cec-pin: kernel_thread() failed\n"); - return PTR_ERR(pin->kthread); + if (!pin->kthread) { + pin->kthread = kthread_run(cec_pin_thread_func, adap, + "cec-pin"); + if (IS_ERR(pin->kthread)) { + int err = PTR_ERR(pin->kthread); + + pr_err("cec-pin: kernel_thread() failed\n"); + pin->kthread = NULL; + return err; + } } hrtimer_start(&pin->timer, ns_to_ktime(0), HRTIMER_MODE_REL); - } else { - kthread_stop(pin->kthread); + } else if (pin->kthread) { + hrtimer_cancel(&pin->timer); + cec_pin_high(pin); + cec_pin_to_idle(pin); + pin->state = CEC_ST_OFF; + pin->work_tx_status = 0; + atomic_set(&pin->work_irq_change, CEC_PIN_IRQ_DISABLE); + wake_up_interruptible(&pin->kthread_waitq); } return 0; } @@ -1207,7 +1212,7 @@ static void cec_pin_adap_status(struct cec_adapter *adap, seq_printf(file, "state: %s\n", states[pin->state].name); seq_printf(file, "tx_bit: %d\n", pin->tx_bit); seq_printf(file, "rx_bit: %d\n", pin->rx_bit); - seq_printf(file, "cec pin: %d\n", pin->ops->read(adap)); + seq_printf(file, "cec pin: %d\n", call_pin_op(pin, read)); seq_printf(file, "cec pin events dropped: %u\n", pin->work_pin_events_dropped_cnt); seq_printf(file, "irq failed: %d\n", pin->enable_irq_failed); @@ -1260,8 +1265,7 @@ static void cec_pin_adap_status(struct cec_adapter *adap, pin->rx_data_bit_too_long_cnt = 0; pin->rx_low_drive_cnt = 0; pin->tx_low_drive_cnt = 0; - if (pin->ops->status) - pin->ops->status(adap, file); + call_void_pin_op(pin, status, file); } static int cec_pin_adap_monitor_all_enable(struct cec_adapter *adap, @@ -1277,6 +1281,9 @@ static void cec_pin_adap_free(struct cec_adapter *adap) { struct cec_pin *pin = adap->pin; + if (pin->kthread) + kthread_stop(pin->kthread); + pin->kthread = NULL; if (pin->ops->free) pin->ops->free(adap); adap->pin = NULL; @@ -1287,7 +1294,7 @@ static int cec_pin_received(struct cec_adapter *adap, struct cec_msg *msg) { struct cec_pin *pin = adap->pin; - if (pin->ops->received) + if (pin->ops->received && !adap->devnode.unregistered) return pin->ops->received(adap, msg); return -ENOMSG; } @@ -1327,6 +1334,7 @@ struct cec_adapter *cec_pin_allocate_adapter(const struct cec_pin_ops *pin_ops, return ERR_PTR(-ENOMEM); pin->ops = pin_ops; hrtimer_init(&pin->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + atomic_set(&pin->work_pin_num_events, 0); pin->timer.function = cec_pin_timer; init_waitqueue_head(&pin->kthread_waitq); pin->tx_custom_low_usecs = CEC_TIM_CUSTOM_DEFAULT; diff --git a/drivers/media/cec/core/cec-priv.h b/drivers/media/cec/core/cec-priv.h index 9bbd05053d42..b78df931aa74 100644 --- a/drivers/media/cec/core/cec-priv.h +++ b/drivers/media/cec/core/cec-priv.h @@ -17,6 +17,16 @@ pr_info("cec-%s: " fmt, adap->name, ## arg); \ } while (0) +#define call_op(adap, op, arg...) \ + ((adap->ops->op && !adap->devnode.unregistered) ? \ + adap->ops->op(adap, ## arg) : 0) + +#define call_void_op(adap, op, arg...) \ + do { \ + if (adap->ops->op && !adap->devnode.unregistered) \ + adap->ops->op(adap, ## arg); \ + } while (0) + /* devnode to cec_adapter */ #define to_cec_adapter(node) container_of(node, struct cec_adapter, devnode) diff --git a/drivers/media/cec/platform/seco/seco-cec.c b/drivers/media/cec/platform/seco/seco-cec.c index 51a6fcfd077d..580905e3d066 100644 --- a/drivers/media/cec/platform/seco/seco-cec.c +++ b/drivers/media/cec/platform/seco/seco-cec.c @@ -31,29 +31,17 @@ struct secocec_data { int irq; }; -#define smb_wr16(cmd, data) smb_word_op(CMD_WORD_DATA, SECOCEC_MICRO_ADDRESS, \ - cmd, data, SMBUS_WRITE, NULL) -#define smb_rd16(cmd, res) smb_word_op(CMD_WORD_DATA, SECOCEC_MICRO_ADDRESS, \ +#define smb_wr16(cmd, data) smb_word_op(SECOCEC_MICRO_ADDRESS, \ + cmd, data, SMBUS_WRITE, NULL) +#define smb_rd16(cmd, res) smb_word_op(SECOCEC_MICRO_ADDRESS, \ cmd, 0, SMBUS_READ, res) -static int smb_word_op(short data_format, u16 slave_addr, u8 cmd, u16 data, +static int smb_word_op(u16 slave_addr, u8 cmd, u16 data, u8 operation, u16 *result) { unsigned int count; - short _data_format; int status = 0; - switch (data_format) { - case CMD_BYTE_DATA: - _data_format = BRA_SMB_CMD_BYTE_DATA; - break; - case CMD_WORD_DATA: - _data_format = BRA_SMB_CMD_WORD_DATA; - break; - default: - return -EINVAL; - } - /* Active wait until ready */ for (count = 0; count <= SMBTIMEOUT; ++count) { if (!(inb(HSTS) & BRA_INUSE_STS)) @@ -75,7 +63,7 @@ static int smb_word_op(short data_format, u16 slave_addr, u8 cmd, u16 data, outb((u8)(data >> 8), HDAT1); } - outb(BRA_START + _data_format, HCNT); + outb(BRA_START + BRA_SMB_CMD_WORD_DATA, HCNT); for (count = 0; count <= SMBTIMEOUT; count++) { if (!(inb(HSTS) & BRA_HOST_BUSY)) diff --git a/drivers/media/common/saa7146/saa7146_video.c b/drivers/media/common/saa7146/saa7146_video.c index 66215d9106a4..2296765079a4 100644 --- a/drivers/media/common/saa7146/saa7146_video.c +++ b/drivers/media/common/saa7146/saa7146_video.c @@ -443,7 +443,6 @@ static int vidioc_querycap(struct file *file, void *fh, struct v4l2_capability * strscpy((char *)cap->driver, "saa7146 v4l2", sizeof(cap->driver)); strscpy((char *)cap->card, dev->ext->name, sizeof(cap->card)); - sprintf((char *)cap->bus_info, "PCI:%s", pci_name(dev->pci)); cap->capabilities = V4L2_CAP_VIDEO_CAPTURE | V4L2_CAP_VIDEO_OVERLAY | V4L2_CAP_READWRITE | V4L2_CAP_STREAMING | V4L2_CAP_DEVICE_CAPS; diff --git a/drivers/media/common/videobuf2/videobuf2-dma-sg.c b/drivers/media/common/videobuf2/videobuf2-dma-sg.c index f8a21c560ad2..fa69158a65b1 100644 --- a/drivers/media/common/videobuf2/videobuf2-dma-sg.c +++ b/drivers/media/common/videobuf2/videobuf2-dma-sg.c @@ -126,8 +126,7 @@ static void *vb2_dma_sg_alloc(struct vb2_buffer *vb, struct device *dev, * there is no memory consistency guarantee, hence dma-sg ignores DMA * attributes passed from the upper layer. */ - buf->pages = kvmalloc_array(buf->num_pages, sizeof(struct page *), - GFP_KERNEL | __GFP_ZERO); + buf->pages = kvcalloc(buf->num_pages, sizeof(struct page *), GFP_KERNEL); if (!buf->pages) goto fail_pages_array_alloc; diff --git a/drivers/media/common/videobuf2/videobuf2-v4l2.c b/drivers/media/common/videobuf2/videobuf2-v4l2.c index 6edf4508c636..075d24ebf44c 100644 --- a/drivers/media/common/videobuf2/videobuf2-v4l2.c +++ b/drivers/media/common/videobuf2/videobuf2-v4l2.c @@ -977,12 +977,6 @@ EXPORT_SYMBOL_GPL(vb2_poll); * and so they simplify the driver code. */ -/* The queue is busy if there is a owner and you are not that owner. */ -static inline bool vb2_queue_is_busy(struct video_device *vdev, struct file *file) -{ - return vdev->queue->owner && vdev->queue->owner != file->private_data; -} - /* vb2 ioctl helpers */ int vb2_ioctl_reqbufs(struct file *file, void *priv, @@ -997,7 +991,7 @@ int vb2_ioctl_reqbufs(struct file *file, void *priv, p->flags = flags; if (res) return res; - if (vb2_queue_is_busy(vdev, file)) + if (vb2_queue_is_busy(vdev->queue, file)) return -EBUSY; res = vb2_core_reqbufs(vdev->queue, p->memory, p->flags, &p->count); /* If count == 0, then the owner has released all buffers and he @@ -1026,7 +1020,7 @@ int vb2_ioctl_create_bufs(struct file *file, void *priv, return res != -EBUSY ? res : 0; if (res) return res; - if (vb2_queue_is_busy(vdev, file)) + if (vb2_queue_is_busy(vdev->queue, file)) return -EBUSY; res = vb2_create_bufs(vdev->queue, p); @@ -1041,7 +1035,7 @@ int vb2_ioctl_prepare_buf(struct file *file, void *priv, { struct video_device *vdev = video_devdata(file); - if (vb2_queue_is_busy(vdev, file)) + if (vb2_queue_is_busy(vdev->queue, file)) return -EBUSY; return vb2_prepare_buf(vdev->queue, vdev->v4l2_dev->mdev, p); } @@ -1060,7 +1054,7 @@ int vb2_ioctl_qbuf(struct file *file, void *priv, struct v4l2_buffer *p) { struct video_device *vdev = video_devdata(file); - if (vb2_queue_is_busy(vdev, file)) + if (vb2_queue_is_busy(vdev->queue, file)) return -EBUSY; return vb2_qbuf(vdev->queue, vdev->v4l2_dev->mdev, p); } @@ -1070,7 +1064,7 @@ int vb2_ioctl_dqbuf(struct file *file, void *priv, struct v4l2_buffer *p) { struct video_device *vdev = video_devdata(file); - if (vb2_queue_is_busy(vdev, file)) + if (vb2_queue_is_busy(vdev->queue, file)) return -EBUSY; return vb2_dqbuf(vdev->queue, p, file->f_flags & O_NONBLOCK); } @@ -1080,7 +1074,7 @@ int vb2_ioctl_streamon(struct file *file, void *priv, enum v4l2_buf_type i) { struct video_device *vdev = video_devdata(file); - if (vb2_queue_is_busy(vdev, file)) + if (vb2_queue_is_busy(vdev->queue, file)) return -EBUSY; return vb2_streamon(vdev->queue, i); } @@ -1090,7 +1084,7 @@ int vb2_ioctl_streamoff(struct file *file, void *priv, enum v4l2_buf_type i) { struct video_device *vdev = video_devdata(file); - if (vb2_queue_is_busy(vdev, file)) + if (vb2_queue_is_busy(vdev->queue, file)) return -EBUSY; return vb2_streamoff(vdev->queue, i); } @@ -1100,7 +1094,7 @@ int vb2_ioctl_expbuf(struct file *file, void *priv, struct v4l2_exportbuffer *p) { struct video_device *vdev = video_devdata(file); - if (vb2_queue_is_busy(vdev, file)) + if (vb2_queue_is_busy(vdev->queue, file)) return -EBUSY; return vb2_expbuf(vdev->queue, p); } @@ -1152,7 +1146,7 @@ ssize_t vb2_fop_write(struct file *file, const char __user *buf, return -EINVAL; if (lock && mutex_lock_interruptible(lock)) return -ERESTARTSYS; - if (vb2_queue_is_busy(vdev, file)) + if (vb2_queue_is_busy(vdev->queue, file)) goto exit; err = vb2_write(vdev->queue, buf, count, ppos, file->f_flags & O_NONBLOCK); @@ -1176,7 +1170,7 @@ ssize_t vb2_fop_read(struct file *file, char __user *buf, return -EINVAL; if (lock && mutex_lock_interruptible(lock)) return -ERESTARTSYS; - if (vb2_queue_is_busy(vdev, file)) + if (vb2_queue_is_busy(vdev->queue, file)) goto exit; err = vb2_read(vdev->queue, buf, count, ppos, file->f_flags & O_NONBLOCK); diff --git a/drivers/media/i2c/Kconfig b/drivers/media/i2c/Kconfig index fae2baabb773..2b20aa6c37b1 100644 --- a/drivers/media/i2c/Kconfig +++ b/drivers/media/i2c/Kconfig @@ -372,6 +372,7 @@ config VIDEO_OV13B10 config VIDEO_OV2640 tristate "OmniVision OV2640 sensor support" depends on VIDEO_DEV && I2C + select V4L2_ASYNC help This is a Video4Linux2 sensor driver for the OmniVision OV2640 camera. diff --git a/drivers/media/i2c/adv7180.c b/drivers/media/i2c/adv7180.c index 4f5db195e66d..e3a57c178c6b 100644 --- a/drivers/media/i2c/adv7180.c +++ b/drivers/media/i2c/adv7180.c @@ -66,6 +66,9 @@ #define ADV7180_HUE_DEF 0 #define ADV7180_HUE_MAX 128 +#define ADV7180_REG_DEF_VALUE_Y 0x000c +#define ADV7180_DEF_VAL_EN 0x1 +#define ADV7180_DEF_VAL_AUTO_EN 0x2 #define ADV7180_REG_CTRL 0x000e #define ADV7180_CTRL_IRQ_SPACE 0x20 @@ -549,6 +552,40 @@ static int adv7180_s_power(struct v4l2_subdev *sd, int on) return ret; } +static const char * const test_pattern_menu[] = { + "Single color", + "Color bars", + "Luma ramp", + "Boundary box", + "Disable", +}; + +static int adv7180_test_pattern(struct adv7180_state *state, int value) +{ + unsigned int reg = 0; + + /* Map menu value into register value */ + if (value < 3) + reg = value; + if (value == 3) + reg = 5; + + adv7180_write(state, ADV7180_REG_ANALOG_CLAMP_CTL, reg); + + if (value == ARRAY_SIZE(test_pattern_menu) - 1) { + reg = adv7180_read(state, ADV7180_REG_DEF_VALUE_Y); + reg &= ~ADV7180_DEF_VAL_EN; + adv7180_write(state, ADV7180_REG_DEF_VALUE_Y, reg); + return 0; + } + + reg = adv7180_read(state, ADV7180_REG_DEF_VALUE_Y); + reg |= ADV7180_DEF_VAL_EN | ADV7180_DEF_VAL_AUTO_EN; + adv7180_write(state, ADV7180_REG_DEF_VALUE_Y, reg); + + return 0; +} + static int adv7180_s_ctrl(struct v4l2_ctrl *ctrl) { struct v4l2_subdev *sd = to_adv7180_sd(ctrl); @@ -592,6 +629,9 @@ static int adv7180_s_ctrl(struct v4l2_ctrl *ctrl) adv7180_write(state, ADV7180_REG_FLCONTROL, 0x00); } break; + case V4L2_CID_TEST_PATTERN: + ret = adv7180_test_pattern(state, val); + break; default: ret = -EINVAL; } @@ -632,6 +672,12 @@ static int adv7180_init_controls(struct adv7180_state *state) ADV7180_HUE_MAX, 1, ADV7180_HUE_DEF); v4l2_ctrl_new_custom(&state->ctrl_hdl, &adv7180_ctrl_fast_switch, NULL); + v4l2_ctrl_new_std_menu_items(&state->ctrl_hdl, &adv7180_ctrl_ops, + V4L2_CID_TEST_PATTERN, + ARRAY_SIZE(test_pattern_menu) - 1, + 0, ARRAY_SIZE(test_pattern_menu) - 1, + test_pattern_menu); + state->sd.ctrl_handler = &state->ctrl_hdl; if (state->ctrl_hdl.error) { int err = state->ctrl_hdl.error; diff --git a/drivers/media/i2c/ccs/ccs-core.c b/drivers/media/i2c/ccs/ccs-core.c index 03e841b8443f..7609add2aff4 100644 --- a/drivers/media/i2c/ccs/ccs-core.c +++ b/drivers/media/i2c/ccs/ccs-core.c @@ -121,7 +121,7 @@ void ccs_replace_limit(struct ccs_sensor *sensor, linfo = &ccs_limits[ccs_limit_offsets[limit].info]; - dev_dbg(&client->dev, "quirk: 0x%8.8x \"%s\" %u = %d, 0x%x\n", + dev_dbg(&client->dev, "quirk: 0x%8.8x \"%s\" %u = %u, 0x%x\n", linfo->reg, linfo->name, offset, val, val); ccs_assign_limit(ptr, ccs_reg_width(linfo->reg), val); @@ -288,7 +288,7 @@ static int ccs_read_frame_fmt(struct ccs_sensor *sensor) CCS_FRAME_FORMAT_DESCRIPTOR_4_PIXELS_MASK; } else { dev_dbg(&client->dev, - "invalid frame format model type %d\n", + "invalid frame format model type %u\n", fmt_model_type); return -EINVAL; } @@ -320,7 +320,7 @@ static int ccs_read_frame_fmt(struct ccs_sensor *sensor) } dev_dbg(&client->dev, - "%s pixels: %d %s (pixelcode %u)\n", + "%s pixels: %u %s (pixelcode %u)\n", what, pixels, which, pixelcode); if (i < ncol_desc) { @@ -353,9 +353,9 @@ static int ccs_read_frame_fmt(struct ccs_sensor *sensor) sensor->image_start = sensor->embedded_end; } - dev_dbg(&client->dev, "embedded data from lines %d to %d\n", + dev_dbg(&client->dev, "embedded data from lines %u to %u\n", sensor->embedded_start, sensor->embedded_end); - dev_dbg(&client->dev, "image data starts at line %d\n", + dev_dbg(&client->dev, "image data starts at line %u\n", sensor->image_start); return 0; @@ -571,7 +571,7 @@ static u32 ccs_pixel_order(struct ccs_sensor *sensor) flip ^= sensor->hvflip_inv_mask; - dev_dbg(&client->dev, "flip %d\n", flip); + dev_dbg(&client->dev, "flip %u\n", flip); return sensor->default_pixel_order ^ flip; } @@ -1056,18 +1056,18 @@ static int ccs_get_mbus_formats(struct ccs_sensor *sensor) type = CCS_LIM(sensor, DATA_FORMAT_MODEL_TYPE); - dev_dbg(&client->dev, "data_format_model_type %d\n", type); + dev_dbg(&client->dev, "data_format_model_type %u\n", type); rval = ccs_read(sensor, PIXEL_ORDER, &pixel_order); if (rval) return rval; if (pixel_order >= ARRAY_SIZE(pixel_order_str)) { - dev_dbg(&client->dev, "bad pixel order %d\n", pixel_order); + dev_dbg(&client->dev, "bad pixel order %u\n", pixel_order); return -EINVAL; } - dev_dbg(&client->dev, "pixel order %d (%s)\n", pixel_order, + dev_dbg(&client->dev, "pixel order %u (%s)\n", pixel_order, pixel_order_str[pixel_order]); switch (type) { @@ -1105,7 +1105,7 @@ static int ccs_get_mbus_formats(struct ccs_sensor *sensor) (fmt & CCS_DATA_FORMAT_DESCRIPTOR_COMPRESSED_MASK)) continue; - dev_dbg(&client->dev, "jolly good! %d\n", j); + dev_dbg(&client->dev, "jolly good! %u\n", j); sensor->default_mbus_frame_fmts |= 1 << j; } @@ -1602,8 +1602,11 @@ static int ccs_power_on(struct device *dev) usleep_range(1000, 2000); } while (--retry); - if (!reset) - return -EIO; + if (!reset) { + dev_err(dev, "software reset failed\n"); + rval = -EIO; + goto out_cci_addr_fail; + } } if (sensor->hwcfg.i2c_addr_alt) { @@ -1999,7 +2002,7 @@ static int ccs_enum_mbus_code(struct v4l2_subdev *subdev, mutex_lock(&sensor->mutex); - dev_err(&client->dev, "subdev %s, pad %d, index %d\n", + dev_err(&client->dev, "subdev %s, pad %u, index %u\n", subdev->name, code->pad, code->index); if (subdev != &sensor->src->sd || code->pad != CCS_PAD_SRC) { @@ -2017,7 +2020,7 @@ static int ccs_enum_mbus_code(struct v4l2_subdev *subdev, if (idx == code->index) { code->code = ccs_csi_data_formats[i].code; - dev_err(&client->dev, "found index %d, i %d, code %x\n", + dev_err(&client->dev, "found index %u, i %u, code %x\n", code->index, i, code->code); rval = 0; break; @@ -2386,7 +2389,7 @@ static void ccs_set_compose_scaler(struct v4l2_subdev *subdev, max_m = clamp(max_m, CCS_LIM(sensor, SCALER_M_MIN), CCS_LIM(sensor, SCALER_M_MAX)); - dev_dbg(&client->dev, "scaling: a %d b %d max_m %d\n", a, b, max_m); + dev_dbg(&client->dev, "scaling: a %u b %u max_m %u\n", a, b, max_m); min = min(max_m, min(a, b)); max = min(max_m, max(a, b)); @@ -2416,7 +2419,7 @@ static void ccs_set_compose_scaler(struct v4l2_subdev *subdev, sel->r.height, sel->flags); - dev_dbg(&client->dev, "trying factor %d (%d)\n", try[i], i); + dev_dbg(&client->dev, "trying factor %u (%u)\n", try[i], i); if (this > best) { scale_m = try[i]; @@ -3183,7 +3186,7 @@ static int ccs_get_hwconfig(struct ccs_sensor *sensor, struct device *dev) struct fwnode_handle *ep; struct fwnode_handle *fwnode = dev_fwnode(dev); u32 rotation; - int i; + unsigned int i; int rval; ep = fwnode_graph_get_endpoint_by_id(fwnode, 0, 0, @@ -3221,8 +3224,6 @@ static int ccs_get_hwconfig(struct ccs_sensor *sensor, struct device *dev) goto out_err; } - dev_dbg(dev, "lanes %u\n", hwcfg->lanes); - rval = fwnode_property_read_u32(fwnode, "rotation", &rotation); if (!rval) { switch (rotation) { @@ -3244,7 +3245,7 @@ static int ccs_get_hwconfig(struct ccs_sensor *sensor, struct device *dev) if (rval) dev_info(dev, "can't get clock-frequency\n"); - dev_dbg(dev, "clk %d, mode %d\n", hwcfg->ext_clk, + dev_dbg(dev, "clk %u, mode %u\n", hwcfg->ext_clk, hwcfg->csi_signalling_mode); if (!bus_cfg.nr_of_link_frequencies) { @@ -3263,7 +3264,7 @@ static int ccs_get_hwconfig(struct ccs_sensor *sensor, struct device *dev) for (i = 0; i < bus_cfg.nr_of_link_frequencies; i++) { hwcfg->op_sys_clock[i] = bus_cfg.link_frequencies[i]; - dev_dbg(dev, "freq %d: %lld\n", i, hwcfg->op_sys_clock[i]); + dev_dbg(dev, "freq %u: %lld\n", i, hwcfg->op_sys_clock[i]); } v4l2_fwnode_endpoint_free(&bus_cfg); diff --git a/drivers/media/i2c/dw9714.c b/drivers/media/i2c/dw9714.c index cd7008ad8f2f..206d74338b9c 100644 --- a/drivers/media/i2c/dw9714.c +++ b/drivers/media/i2c/dw9714.c @@ -183,6 +183,7 @@ static int dw9714_probe(struct i2c_client *client) return 0; err_cleanup: + regulator_disable(dw9714_dev->vcc); v4l2_ctrl_handler_free(&dw9714_dev->ctrls_vcm); media_entity_cleanup(&dw9714_dev->sd.entity); @@ -201,7 +202,6 @@ static int dw9714_remove(struct i2c_client *client) if (ret) { dev_err(&client->dev, "Failed to disable vcc: %d\n", ret); - return ret; } } pm_runtime_set_suspended(&client->dev); diff --git a/drivers/media/i2c/dw9768.c b/drivers/media/i2c/dw9768.c index 65c6acf3ced9..c086580efac7 100644 --- a/drivers/media/i2c/dw9768.c +++ b/drivers/media/i2c/dw9768.c @@ -469,11 +469,6 @@ static int dw9768_probe(struct i2c_client *client) dw9768->sd.entity.function = MEDIA_ENT_F_LENS; - /* - * Device is already turned on by i2c-core with ACPI domain PM. - * Attempt to turn off the device to satisfy the privacy LED concerns. - */ - pm_runtime_set_active(dev); pm_runtime_enable(dev); if (!pm_runtime_enabled(dev)) { ret = dw9768_runtime_resume(dev); @@ -488,7 +483,6 @@ static int dw9768_probe(struct i2c_client *client) dev_err(dev, "failed to register V4L2 subdev: %d", ret); goto err_power_off; } - pm_runtime_idle(dev); return 0; diff --git a/drivers/media/i2c/dw9807-vcm.c b/drivers/media/i2c/dw9807-vcm.c index 95e06f13bc9e..01c372925a80 100644 --- a/drivers/media/i2c/dw9807-vcm.c +++ b/drivers/media/i2c/dw9807-vcm.c @@ -295,6 +295,8 @@ static int __maybe_unused dw9807_vcm_resume(struct device *dev) static const struct of_device_id dw9807_of_table[] = { { .compatible = "dongwoon,dw9807-vcm" }, + /* Compatibility for older firmware, NEVER USE THIS IN FIRMWARE! */ + { .compatible = "dongwoon,dw9807" }, { /* sentinel */ } }; MODULE_DEVICE_TABLE(of, dw9807_of_table); diff --git a/drivers/media/i2c/imx412.c b/drivers/media/i2c/imx412.c index be3f6ea55559..a1394d6c1432 100644 --- a/drivers/media/i2c/imx412.c +++ b/drivers/media/i2c/imx412.c @@ -11,6 +11,7 @@ #include <linux/i2c.h> #include <linux/module.h> #include <linux/pm_runtime.h> +#include <linux/regulator/consumer.h> #include <media/v4l2-ctrls.h> #include <media/v4l2-fwnode.h> @@ -101,6 +102,12 @@ struct imx412_mode { struct imx412_reg_list reg_list; }; +static const char * const imx412_supply_names[] = { + "dovdd", /* Digital I/O power */ + "avdd", /* Analog power */ + "dvdd", /* Digital core power */ +}; + /** * struct imx412 - imx412 sensor device structure * @dev: Pointer to generic device @@ -109,6 +116,7 @@ struct imx412_mode { * @pad: Media pad. Only one pad supported * @reset_gpio: Sensor reset gpio * @inclk: Sensor input clock + * @supplies: Regulator supplies * @ctrl_handler: V4L2 control handler * @link_freq_ctrl: Pointer to link frequency control * @pclk_ctrl: Pointer to pixel clock control @@ -128,6 +136,7 @@ struct imx412 { struct media_pad pad; struct gpio_desc *reset_gpio; struct clk *inclk; + struct regulator_bulk_data supplies[ARRAY_SIZE(imx412_supply_names)]; struct v4l2_ctrl_handler ctrl_handler; struct v4l2_ctrl *link_freq_ctrl; struct v4l2_ctrl *pclk_ctrl; @@ -946,6 +955,16 @@ static int imx412_parse_hw_config(struct imx412 *imx412) return -EINVAL; } + /* Get optional DT defined regulators */ + for (i = 0; i < ARRAY_SIZE(imx412_supply_names); i++) + imx412->supplies[i].supply = imx412_supply_names[i]; + + ret = devm_regulator_bulk_get(imx412->dev, + ARRAY_SIZE(imx412_supply_names), + imx412->supplies); + if (ret) + return ret; + ep = fwnode_graph_get_next_endpoint(fwnode, NULL); if (!ep) return -ENXIO; @@ -1011,7 +1030,14 @@ static int imx412_power_on(struct device *dev) struct imx412 *imx412 = to_imx412(sd); int ret; - gpiod_set_value_cansleep(imx412->reset_gpio, 1); + ret = regulator_bulk_enable(ARRAY_SIZE(imx412_supply_names), + imx412->supplies); + if (ret < 0) { + dev_err(dev, "failed to enable regulators\n"); + return ret; + } + + gpiod_set_value_cansleep(imx412->reset_gpio, 0); ret = clk_prepare_enable(imx412->inclk); if (ret) { @@ -1024,7 +1050,9 @@ static int imx412_power_on(struct device *dev) return 0; error_reset: - gpiod_set_value_cansleep(imx412->reset_gpio, 0); + gpiod_set_value_cansleep(imx412->reset_gpio, 1); + regulator_bulk_disable(ARRAY_SIZE(imx412_supply_names), + imx412->supplies); return ret; } @@ -1040,10 +1068,13 @@ static int imx412_power_off(struct device *dev) struct v4l2_subdev *sd = dev_get_drvdata(dev); struct imx412 *imx412 = to_imx412(sd); - gpiod_set_value_cansleep(imx412->reset_gpio, 0); - clk_disable_unprepare(imx412->inclk); + gpiod_set_value_cansleep(imx412->reset_gpio, 1); + + regulator_bulk_disable(ARRAY_SIZE(imx412_supply_names), + imx412->supplies); + return 0; } diff --git a/drivers/media/i2c/max9286.c b/drivers/media/i2c/max9286.c index d2a4915ed9f7..3684faa72253 100644 --- a/drivers/media/i2c/max9286.c +++ b/drivers/media/i2c/max9286.c @@ -1147,22 +1147,18 @@ static int max9286_poc_enable(struct max9286_priv *priv, bool enable) return ret; } -static int max9286_init(struct device *dev) +static int max9286_init(struct max9286_priv *priv) { - struct max9286_priv *priv; - struct i2c_client *client; + struct i2c_client *client = priv->client; int ret; - client = to_i2c_client(dev); - priv = i2c_get_clientdata(client); - ret = max9286_poc_enable(priv, true); if (ret) return ret; ret = max9286_setup(priv); if (ret) { - dev_err(dev, "Unable to setup max9286\n"); + dev_err(&client->dev, "Unable to setup max9286\n"); goto err_poc_disable; } @@ -1172,13 +1168,13 @@ static int max9286_init(struct device *dev) */ ret = max9286_v4l2_register(priv); if (ret) { - dev_err(dev, "Failed to register with V4L2\n"); + dev_err(&client->dev, "Failed to register with V4L2\n"); goto err_poc_disable; } ret = max9286_i2c_mux_init(priv); if (ret) { - dev_err(dev, "Unable to initialize I2C multiplexer\n"); + dev_err(&client->dev, "Unable to initialize I2C multiplexer\n"); goto err_v4l2_register; } @@ -1333,7 +1329,6 @@ static int max9286_probe(struct i2c_client *client) mutex_init(&priv->mutex); priv->client = client; - i2c_set_clientdata(client, priv); priv->gpiod_pwdn = devm_gpiod_get_optional(&client->dev, "enable", GPIOD_OUT_HIGH); @@ -1369,7 +1364,7 @@ static int max9286_probe(struct i2c_client *client) if (ret) goto err_powerdown; - ret = max9286_init(&client->dev); + ret = max9286_init(priv); if (ret < 0) goto err_cleanup_dt; @@ -1385,7 +1380,7 @@ err_powerdown: static int max9286_remove(struct i2c_client *client) { - struct max9286_priv *priv = i2c_get_clientdata(client); + struct max9286_priv *priv = sd_to_max9286(i2c_get_clientdata(client)); i2c_mux_del_adapters(priv->mux); diff --git a/drivers/media/i2c/ov5645.c b/drivers/media/i2c/ov5645.c index 368fa21e675e..562c62f192c4 100644 --- a/drivers/media/i2c/ov5645.c +++ b/drivers/media/i2c/ov5645.c @@ -843,7 +843,7 @@ static int ov5645_enum_mbus_code(struct v4l2_subdev *sd, if (code->index > 0) return -EINVAL; - code->code = MEDIA_BUS_FMT_UYVY8_2X8; + code->code = MEDIA_BUS_FMT_UYVY8_1X16; return 0; } @@ -852,7 +852,7 @@ static int ov5645_enum_frame_size(struct v4l2_subdev *subdev, struct v4l2_subdev_state *sd_state, struct v4l2_subdev_frame_size_enum *fse) { - if (fse->code != MEDIA_BUS_FMT_UYVY8_2X8) + if (fse->code != MEDIA_BUS_FMT_UYVY8_1X16) return -EINVAL; if (fse->index >= ARRAY_SIZE(ov5645_mode_info_data)) @@ -948,7 +948,7 @@ static int ov5645_set_format(struct v4l2_subdev *sd, format->which); __format->width = __crop->width; __format->height = __crop->height; - __format->code = MEDIA_BUS_FMT_UYVY8_2X8; + __format->code = MEDIA_BUS_FMT_UYVY8_1X16; __format->field = V4L2_FIELD_NONE; __format->colorspace = V4L2_COLORSPACE_SRGB; @@ -1283,7 +1283,7 @@ MODULE_DEVICE_TABLE(of, ov5645_of_match); static struct i2c_driver ov5645_i2c_driver = { .driver = { - .of_match_table = of_match_ptr(ov5645_of_match), + .of_match_table = ov5645_of_match, .name = "ov5645", }, .probe_new = ov5645_probe, diff --git a/drivers/media/i2c/ov5648.c b/drivers/media/i2c/ov5648.c index 930ff6897044..dfcd33e9ee13 100644 --- a/drivers/media/i2c/ov5648.c +++ b/drivers/media/i2c/ov5648.c @@ -2498,9 +2498,9 @@ static int ov5648_probe(struct i2c_client *client) /* DOVDD: digital I/O */ sensor->dovdd = devm_regulator_get(dev, "dovdd"); - if (IS_ERR(sensor->dvdd)) { + if (IS_ERR(sensor->dovdd)) { dev_err(dev, "cannot get DOVDD (digital I/O) regulator\n"); - ret = PTR_ERR(sensor->dvdd); + ret = PTR_ERR(sensor->dovdd); goto error_endpoint; } diff --git a/drivers/media/i2c/ov5695.c b/drivers/media/i2c/ov5695.c index 439385938a51..910309783885 100644 --- a/drivers/media/i2c/ov5695.c +++ b/drivers/media/i2c/ov5695.c @@ -1122,7 +1122,7 @@ static int ov5695_set_ctrl(struct v4l2_ctrl *ctrl) switch (ctrl->id) { case V4L2_CID_EXPOSURE: - /* 4 least significant bits of expsoure are fractional part */ + /* 4 least significant bits of exposure are fractional part */ ret = ov5695_write_reg(ov5695->client, OV5695_REG_EXPOSURE, OV5695_REG_VALUE_24BIT, ctrl->val << 4); break; diff --git a/drivers/media/i2c/ov7251.c b/drivers/media/i2c/ov7251.c index ebb299f207e5..0e7be15bc20a 100644 --- a/drivers/media/i2c/ov7251.c +++ b/drivers/media/i2c/ov7251.c @@ -14,6 +14,8 @@ #include <linux/i2c.h> #include <linux/init.h> #include <linux/module.h> +#include <linux/mod_devicetable.h> +#include <linux/pm_runtime.h> #include <linux/regulator/consumer.h> #include <linux/slab.h> #include <linux/types.h> @@ -41,6 +43,29 @@ #define OV7251_TIMING_FORMAT2_MIRROR BIT(2) #define OV7251_PRE_ISP_00 0x5e00 #define OV7251_PRE_ISP_00_TEST_PATTERN BIT(7) +#define OV7251_PLL1_PRE_DIV_REG 0x30b4 +#define OV7251_PLL1_MULT_REG 0x30b3 +#define OV7251_PLL1_DIVIDER_REG 0x30b1 +#define OV7251_PLL1_PIX_DIV_REG 0x30b0 +#define OV7251_PLL1_MIPI_DIV_REG 0x30b5 +#define OV7251_PLL2_PRE_DIV_REG 0x3098 +#define OV7251_PLL2_MULT_REG 0x3099 +#define OV7251_PLL2_DIVIDER_REG 0x309d +#define OV7251_PLL2_SYS_DIV_REG 0x309a +#define OV7251_PLL2_ADC_DIV_REG 0x309b + +#define OV7251_NATIVE_WIDTH 656 +#define OV7251_NATIVE_HEIGHT 496 +#define OV7251_ACTIVE_START_LEFT 4 +#define OV7251_ACTIVE_START_TOP 4 +#define OV7251_ACTIVE_WIDTH 648 +#define OV7251_ACTIVE_HEIGHT 488 + +#define OV7251_FIXED_PPL 928 +#define OV7251_TIMING_VTS_REG 0x380e +#define OV7251_TIMING_MIN_VTS 1 +#define OV7251_TIMING_MAX_VTS 0xffff +#define OV7251_INTEGRATION_MARGIN 20 struct reg_value { u16 reg; @@ -50,6 +75,7 @@ struct reg_value { struct ov7251_mode_info { u32 width; u32 height; + u32 vts; const struct reg_value *data; u32 data_size; u32 pixel_clock; @@ -59,6 +85,43 @@ struct ov7251_mode_info { struct v4l2_fract timeperframe; }; +struct ov7251_pll1_cfg { + unsigned int pre_div; + unsigned int mult; + unsigned int div; + unsigned int pix_div; + unsigned int mipi_div; +}; + +struct ov7251_pll2_cfg { + unsigned int pre_div; + unsigned int mult; + unsigned int div; + unsigned int sys_div; + unsigned int adc_div; +}; + +/* + * Rubbish ordering, but only PLL1 needs to have a separate configuration per + * link frequency and the array member needs to be last. + */ +struct ov7251_pll_cfgs { + const struct ov7251_pll2_cfg *pll2; + const struct ov7251_pll1_cfg *pll1[]; +}; + +enum xclk_rate { + OV7251_19_2_MHZ, + OV7251_24_MHZ, + OV7251_NUM_SUPPORTED_RATES +}; + +enum supported_link_freqs { + OV7251_LINK_FREQ_240_MHZ, + OV7251_LINK_FREQ_319_2_MHZ, + OV7251_NUM_SUPPORTED_LINK_FREQS +}; + struct ov7251 { struct i2c_client *i2c_client; struct device *dev; @@ -74,6 +137,8 @@ struct ov7251 { struct regulator *core_regulator; struct regulator *analog_regulator; + const struct ov7251_pll_cfgs *pll_cfgs; + enum supported_link_freqs link_freq_idx; const struct ov7251_mode_info *current_mode; struct v4l2_ctrl_handler ctrls; @@ -81,6 +146,8 @@ struct ov7251 { struct v4l2_ctrl *link_freq; struct v4l2_ctrl *exposure; struct v4l2_ctrl *gain; + struct v4l2_ctrl *hblank; + struct v4l2_ctrl *vblank; /* Cached register values */ u8 aec_pk_manual; @@ -99,6 +166,75 @@ static inline struct ov7251 *to_ov7251(struct v4l2_subdev *sd) return container_of(sd, struct ov7251, sd); } +static const struct ov7251_pll1_cfg ov7251_pll1_cfg_19_2_mhz_240_mhz = { + .pre_div = 0x03, + .mult = 0x4b, + .div = 0x01, + .pix_div = 0x0a, + .mipi_div = 0x05, +}; + +static const struct ov7251_pll1_cfg ov7251_pll1_cfg_19_2_mhz_319_2_mhz = { + .pre_div = 0x01, + .mult = 0x85, + .div = 0x04, + .pix_div = 0x0a, + .mipi_div = 0x05, +}; + +static const struct ov7251_pll1_cfg ov7251_pll1_cfg_24_mhz_240_mhz = { + .pre_div = 0x03, + .mult = 0x64, + .div = 0x01, + .pix_div = 0x0a, + .mipi_div = 0x05, +}; + +static const struct ov7251_pll1_cfg ov7251_pll1_cfg_24_mhz_319_2_mhz = { + .pre_div = 0x05, + .mult = 0x85, + .div = 0x02, + .pix_div = 0x0a, + .mipi_div = 0x05, +}; + +static const struct ov7251_pll2_cfg ov7251_pll2_cfg_19_2_mhz = { + .pre_div = 0x04, + .mult = 0x32, + .div = 0x00, + .sys_div = 0x05, + .adc_div = 0x04, +}; + +static const struct ov7251_pll2_cfg ov7251_pll2_cfg_24_mhz = { + .pre_div = 0x04, + .mult = 0x28, + .div = 0x00, + .sys_div = 0x05, + .adc_div = 0x04, +}; + +static const struct ov7251_pll_cfgs ov7251_pll_cfgs_19_2_mhz = { + .pll2 = &ov7251_pll2_cfg_19_2_mhz, + .pll1 = { + [OV7251_LINK_FREQ_240_MHZ] = &ov7251_pll1_cfg_19_2_mhz_240_mhz, + [OV7251_LINK_FREQ_319_2_MHZ] = &ov7251_pll1_cfg_19_2_mhz_319_2_mhz, + }, +}; + +static const struct ov7251_pll_cfgs ov7251_pll_cfgs_24_mhz = { + .pll2 = &ov7251_pll2_cfg_24_mhz, + .pll1 = { + [OV7251_LINK_FREQ_240_MHZ] = &ov7251_pll1_cfg_24_mhz_240_mhz, + [OV7251_LINK_FREQ_319_2_MHZ] = &ov7251_pll1_cfg_24_mhz_319_2_mhz, + }, +}; + +static const struct ov7251_pll_cfgs *ov7251_pll_cfgs[] = { + [OV7251_19_2_MHZ] = &ov7251_pll_cfgs_19_2_mhz, + [OV7251_24_MHZ] = &ov7251_pll_cfgs_24_mhz, +}; + static const struct reg_value ov7251_global_init_setting[] = { { 0x0103, 0x01 }, { 0x303b, 0x02 }, @@ -117,16 +253,6 @@ static const struct reg_value ov7251_setting_vga_30fps[] = { { 0x301c, 0xf0 }, { 0x3023, 0x05 }, { 0x3037, 0xf0 }, - { 0x3098, 0x04 }, /* pll2 pre divider */ - { 0x3099, 0x28 }, /* pll2 multiplier */ - { 0x309a, 0x05 }, /* pll2 sys divider */ - { 0x309b, 0x04 }, /* pll2 adc divider */ - { 0x309d, 0x00 }, /* pll2 divider */ - { 0x30b0, 0x0a }, /* pll1 pix divider */ - { 0x30b1, 0x01 }, /* pll1 divider */ - { 0x30b3, 0x64 }, /* pll1 multiplier */ - { 0x30b4, 0x03 }, /* pll1 pre divider */ - { 0x30b5, 0x05 }, /* pll1 mipi divider */ { 0x3106, 0xda }, { 0x3503, 0x07 }, { 0x3509, 0x10 }, @@ -255,16 +381,6 @@ static const struct reg_value ov7251_setting_vga_60fps[] = { { 0x301c, 0x00 }, { 0x3023, 0x05 }, { 0x3037, 0xf0 }, - { 0x3098, 0x04 }, /* pll2 pre divider */ - { 0x3099, 0x28 }, /* pll2 multiplier */ - { 0x309a, 0x05 }, /* pll2 sys divider */ - { 0x309b, 0x04 }, /* pll2 adc divider */ - { 0x309d, 0x00 }, /* pll2 divider */ - { 0x30b0, 0x0a }, /* pll1 pix divider */ - { 0x30b1, 0x01 }, /* pll1 divider */ - { 0x30b3, 0x64 }, /* pll1 multiplier */ - { 0x30b4, 0x03 }, /* pll1 pre divider */ - { 0x30b5, 0x05 }, /* pll1 mipi divider */ { 0x3106, 0xda }, { 0x3503, 0x07 }, { 0x3509, 0x10 }, @@ -393,16 +509,6 @@ static const struct reg_value ov7251_setting_vga_90fps[] = { { 0x301c, 0x00 }, { 0x3023, 0x05 }, { 0x3037, 0xf0 }, - { 0x3098, 0x04 }, /* pll2 pre divider */ - { 0x3099, 0x28 }, /* pll2 multiplier */ - { 0x309a, 0x05 }, /* pll2 sys divider */ - { 0x309b, 0x04 }, /* pll2 adc divider */ - { 0x309d, 0x00 }, /* pll2 divider */ - { 0x30b0, 0x0a }, /* pll1 pix divider */ - { 0x30b1, 0x01 }, /* pll1 divider */ - { 0x30b3, 0x64 }, /* pll1 multiplier */ - { 0x30b4, 0x03 }, /* pll1 pre divider */ - { 0x30b5, 0x05 }, /* pll1 mipi divider */ { 0x3106, 0xda }, { 0x3503, 0x07 }, { 0x3509, 0x10 }, @@ -518,18 +624,28 @@ static const struct reg_value ov7251_setting_vga_90fps[] = { { 0x5001, 0x80 }, }; +static const unsigned long supported_xclk_rates[] = { + [OV7251_19_2_MHZ] = 19200000, + [OV7251_24_MHZ] = 24000000, +}; + static const s64 link_freq[] = { - 240000000, + [OV7251_LINK_FREQ_240_MHZ] = 240000000, + [OV7251_LINK_FREQ_319_2_MHZ] = 319200000, +}; + +static const s64 pixel_rates[] = { + [OV7251_LINK_FREQ_240_MHZ] = 48000000, + [OV7251_LINK_FREQ_319_2_MHZ] = 63840000, }; static const struct ov7251_mode_info ov7251_mode_info_data[] = { { .width = 640, .height = 480, + .vts = 1724, .data = ov7251_setting_vga_30fps, .data_size = ARRAY_SIZE(ov7251_setting_vga_30fps), - .pixel_clock = 48000000, - .link_freq = 0, /* an index in link_freq[] */ .exposure_max = 1704, .exposure_def = 504, .timeperframe = { @@ -540,10 +656,9 @@ static const struct ov7251_mode_info ov7251_mode_info_data[] = { { .width = 640, .height = 480, + .vts = 860, .data = ov7251_setting_vga_60fps, .data_size = ARRAY_SIZE(ov7251_setting_vga_60fps), - .pixel_clock = 48000000, - .link_freq = 0, /* an index in link_freq[] */ .exposure_max = 840, .exposure_def = 504, .timeperframe = { @@ -554,10 +669,9 @@ static const struct ov7251_mode_info ov7251_mode_info_data[] = { { .width = 640, .height = 480, + .vts = 572, .data = ov7251_setting_vga_90fps, .data_size = ARRAY_SIZE(ov7251_setting_vga_90fps), - .pixel_clock = 48000000, - .link_freq = 0, /* an index in link_freq[] */ .exposure_max = 552, .exposure_def = 504, .timeperframe = { @@ -691,6 +805,63 @@ static int ov7251_read_reg(struct ov7251 *ov7251, u16 reg, u8 *val) return 0; } +static int ov7251_pll_configure(struct ov7251 *ov7251) +{ + const struct ov7251_pll_cfgs *configs; + int ret; + + configs = ov7251->pll_cfgs; + + ret = ov7251_write_reg(ov7251, OV7251_PLL1_PRE_DIV_REG, + configs->pll1[ov7251->link_freq_idx]->pre_div); + if (ret < 0) + return ret; + + ret = ov7251_write_reg(ov7251, OV7251_PLL1_MULT_REG, + configs->pll1[ov7251->link_freq_idx]->mult); + if (ret < 0) + return ret; + ret = ov7251_write_reg(ov7251, OV7251_PLL1_DIVIDER_REG, + configs->pll1[ov7251->link_freq_idx]->div); + if (ret < 0) + return ret; + + ret = ov7251_write_reg(ov7251, OV7251_PLL1_PIX_DIV_REG, + configs->pll1[ov7251->link_freq_idx]->pix_div); + if (ret < 0) + return ret; + + ret = ov7251_write_reg(ov7251, OV7251_PLL1_MIPI_DIV_REG, + configs->pll1[ov7251->link_freq_idx]->mipi_div); + if (ret < 0) + return ret; + + ret = ov7251_write_reg(ov7251, OV7251_PLL2_PRE_DIV_REG, + configs->pll2->pre_div); + if (ret < 0) + return ret; + + ret = ov7251_write_reg(ov7251, OV7251_PLL2_MULT_REG, + configs->pll2->mult); + if (ret < 0) + return ret; + + ret = ov7251_write_reg(ov7251, OV7251_PLL2_DIVIDER_REG, + configs->pll2->div); + if (ret < 0) + return ret; + + ret = ov7251_write_reg(ov7251, OV7251_PLL2_SYS_DIV_REG, + configs->pll2->sys_div); + if (ret < 0) + return ret; + + ret = ov7251_write_reg(ov7251, OV7251_PLL2_ADC_DIV_REG, + configs->pll2->adc_div); + + return ret; +} + static int ov7251_set_exposure(struct ov7251 *ov7251, s32 exposure) { u16 reg; @@ -732,8 +903,11 @@ static int ov7251_set_register_array(struct ov7251 *ov7251, return 0; } -static int ov7251_set_power_on(struct ov7251 *ov7251) +static int ov7251_set_power_on(struct device *dev) { + struct i2c_client *client = container_of(dev, struct i2c_client, dev); + struct v4l2_subdev *sd = i2c_get_clientdata(client); + struct ov7251 *ov7251 = to_ov7251(sd); int ret; u32 wait_us; @@ -755,51 +929,29 @@ static int ov7251_set_power_on(struct ov7251 *ov7251) DIV_ROUND_UP(ov7251->xclk_freq, 1000)); usleep_range(wait_us, wait_us + 1000); - return 0; -} + ret = ov7251_set_register_array(ov7251, + ov7251_global_init_setting, + ARRAY_SIZE(ov7251_global_init_setting)); + if (ret < 0) { + dev_err(ov7251->dev, "error during global init\n"); + ov7251_regulators_disable(ov7251); + return ret; + } -static void ov7251_set_power_off(struct ov7251 *ov7251) -{ - clk_disable_unprepare(ov7251->xclk); - gpiod_set_value_cansleep(ov7251->enable_gpio, 0); - ov7251_regulators_disable(ov7251); + return ret; } -static int ov7251_s_power(struct v4l2_subdev *sd, int on) +static int ov7251_set_power_off(struct device *dev) { + struct i2c_client *client = container_of(dev, struct i2c_client, dev); + struct v4l2_subdev *sd = i2c_get_clientdata(client); struct ov7251 *ov7251 = to_ov7251(sd); - int ret = 0; - - mutex_lock(&ov7251->lock); - - /* If the power state is not modified - no work to do. */ - if (ov7251->power_on == !!on) - goto exit; - - if (on) { - ret = ov7251_set_power_on(ov7251); - if (ret < 0) - goto exit; - ret = ov7251_set_register_array(ov7251, - ov7251_global_init_setting, - ARRAY_SIZE(ov7251_global_init_setting)); - if (ret < 0) { - dev_err(ov7251->dev, "could not set init registers\n"); - ov7251_set_power_off(ov7251); - goto exit; - } - - ov7251->power_on = true; - } else { - ov7251_set_power_off(ov7251); - ov7251->power_on = false; - } - -exit: - mutex_unlock(&ov7251->lock); + clk_disable_unprepare(ov7251->xclk); + gpiod_set_value_cansleep(ov7251->enable_gpio, 0); + ov7251_regulators_disable(ov7251); - return ret; + return 0; } static int ov7251_set_hflip(struct ov7251 *ov7251, s32 value) @@ -858,15 +1010,39 @@ static const char * const ov7251_test_pattern_menu[] = { "Vertical Pattern Bars", }; +static int ov7251_vts_configure(struct ov7251 *ov7251, s32 vblank) +{ + u8 vts[2]; + + vts[0] = ((ov7251->current_mode->height + vblank) & 0xff00) >> 8; + vts[1] = ((ov7251->current_mode->height + vblank) & 0x00ff); + + return ov7251_write_seq_regs(ov7251, OV7251_TIMING_VTS_REG, vts, 2); +} + static int ov7251_s_ctrl(struct v4l2_ctrl *ctrl) { struct ov7251 *ov7251 = container_of(ctrl->handler, struct ov7251, ctrls); int ret; + /* If VBLANK is altered we need to update exposure to compensate */ + if (ctrl->id == V4L2_CID_VBLANK) { + int exposure_max; + + exposure_max = ov7251->current_mode->height + ctrl->val - + OV7251_INTEGRATION_MARGIN; + __v4l2_ctrl_modify_range(ov7251->exposure, + ov7251->exposure->minimum, + exposure_max, + ov7251->exposure->step, + min(ov7251->exposure->val, + exposure_max)); + } + /* v4l2_ctrl_lock() locks our mutex */ - if (!ov7251->power_on) + if (!pm_runtime_get_if_in_use(ov7251->dev)) return 0; switch (ctrl->id) { @@ -885,11 +1061,16 @@ static int ov7251_s_ctrl(struct v4l2_ctrl *ctrl) case V4L2_CID_VFLIP: ret = ov7251_set_vflip(ov7251, ctrl->val); break; + case V4L2_CID_VBLANK: + ret = ov7251_vts_configure(ov7251, ctrl->val); + break; default: ret = -EINVAL; break; } + pm_runtime_put(ov7251->dev); + return ret; } @@ -1034,6 +1215,7 @@ static int ov7251_set_format(struct v4l2_subdev *sd, { struct ov7251 *ov7251 = to_ov7251(sd); struct v4l2_mbus_framefmt *__format; + int vblank_max, vblank_def; struct v4l2_rect *__crop; const struct ov7251_mode_info *new_mode; int ret = 0; @@ -1052,16 +1234,6 @@ static int ov7251_set_format(struct v4l2_subdev *sd, __crop->height = new_mode->height; if (format->which == V4L2_SUBDEV_FORMAT_ACTIVE) { - ret = __v4l2_ctrl_s_ctrl_int64(ov7251->pixel_clock, - new_mode->pixel_clock); - if (ret < 0) - goto exit; - - ret = __v4l2_ctrl_s_ctrl(ov7251->link_freq, - new_mode->link_freq); - if (ret < 0) - goto exit; - ret = __v4l2_ctrl_modify_range(ov7251->exposure, 1, new_mode->exposure_max, 1, new_mode->exposure_def); @@ -1077,6 +1249,14 @@ static int ov7251_set_format(struct v4l2_subdev *sd, if (ret < 0) goto exit; + vblank_max = OV7251_TIMING_MAX_VTS - new_mode->height; + vblank_def = new_mode->vts - new_mode->height; + ret = __v4l2_ctrl_modify_range(ov7251->vblank, + OV7251_TIMING_MIN_VTS, + vblank_max, 1, vblank_def); + if (ret < 0) + goto exit; + ov7251->current_mode = new_mode; } @@ -1123,13 +1303,29 @@ static int ov7251_get_selection(struct v4l2_subdev *sd, { struct ov7251 *ov7251 = to_ov7251(sd); - if (sel->target != V4L2_SEL_TGT_CROP) - return -EINVAL; - + switch (sel->target) { + case V4L2_SEL_TGT_CROP_DEFAULT: + case V4L2_SEL_TGT_CROP: mutex_lock(&ov7251->lock); - sel->r = *__ov7251_get_pad_crop(ov7251, sd_state, sel->pad, - sel->which); - mutex_unlock(&ov7251->lock); + sel->r = *__ov7251_get_pad_crop(ov7251, sd_state, sel->pad, + sel->which); + mutex_unlock(&ov7251->lock); + break; + case V4L2_SEL_TGT_NATIVE_SIZE: + sel->r.top = 0; + sel->r.left = 0; + sel->r.width = OV7251_NATIVE_WIDTH; + sel->r.height = OV7251_NATIVE_HEIGHT; + break; + case V4L2_SEL_TGT_CROP_BOUNDS: + sel->r.top = OV7251_ACTIVE_START_TOP; + sel->r.left = OV7251_ACTIVE_START_LEFT; + sel->r.width = OV7251_ACTIVE_WIDTH; + sel->r.height = OV7251_ACTIVE_HEIGHT; + break; + default: + return -EINVAL; + } return 0; } @@ -1142,6 +1338,16 @@ static int ov7251_s_stream(struct v4l2_subdev *subdev, int enable) mutex_lock(&ov7251->lock); if (enable) { + ret = pm_runtime_get_sync(ov7251->dev); + if (ret < 0) + goto unlock_out; + + ret = ov7251_pll_configure(ov7251); + if (ret) { + dev_err(ov7251->dev, "error configuring PLLs\n"); + goto err_power_down; + } + ret = ov7251_set_register_array(ov7251, ov7251->current_mode->data, ov7251->current_mode->data_size); @@ -1149,23 +1355,30 @@ static int ov7251_s_stream(struct v4l2_subdev *subdev, int enable) dev_err(ov7251->dev, "could not set mode %dx%d\n", ov7251->current_mode->width, ov7251->current_mode->height); - goto exit; + goto err_power_down; } ret = __v4l2_ctrl_handler_setup(&ov7251->ctrls); if (ret < 0) { dev_err(ov7251->dev, "could not sync v4l2 controls\n"); - goto exit; + goto err_power_down; } ret = ov7251_write_reg(ov7251, OV7251_SC_MODE_SELECT, OV7251_SC_MODE_SELECT_STREAMING); + if (ret) + goto err_power_down; } else { ret = ov7251_write_reg(ov7251, OV7251_SC_MODE_SELECT, OV7251_SC_MODE_SELECT_SW_STANDBY); + pm_runtime_put(ov7251->dev); } -exit: +unlock_out: mutex_unlock(&ov7251->lock); + return ret; +err_power_down: + pm_runtime_put_noidle(ov7251->dev); + mutex_unlock(&ov7251->lock); return ret; } @@ -1192,16 +1405,6 @@ static int ov7251_set_frame_interval(struct v4l2_subdev *subdev, new_mode = ov7251_find_mode_by_ival(ov7251, &fi->interval); if (new_mode != ov7251->current_mode) { - ret = __v4l2_ctrl_s_ctrl_int64(ov7251->pixel_clock, - new_mode->pixel_clock); - if (ret < 0) - goto exit; - - ret = __v4l2_ctrl_s_ctrl(ov7251->link_freq, - new_mode->link_freq); - if (ret < 0) - goto exit; - ret = __v4l2_ctrl_modify_range(ov7251->exposure, 1, new_mode->exposure_max, 1, new_mode->exposure_def); @@ -1228,10 +1431,6 @@ exit: return ret; } -static const struct v4l2_subdev_core_ops ov7251_core_ops = { - .s_power = ov7251_s_power, -}; - static const struct v4l2_subdev_video_ops ov7251_video_ops = { .s_stream = ov7251_s_stream, .g_frame_interval = ov7251_get_frame_interval, @@ -1249,97 +1448,97 @@ static const struct v4l2_subdev_pad_ops ov7251_subdev_pad_ops = { }; static const struct v4l2_subdev_ops ov7251_subdev_ops = { - .core = &ov7251_core_ops, .video = &ov7251_video_ops, .pad = &ov7251_subdev_pad_ops, }; -static int ov7251_probe(struct i2c_client *client) +static int ov7251_check_hwcfg(struct ov7251 *ov7251) { - struct device *dev = &client->dev; + struct fwnode_handle *fwnode = dev_fwnode(ov7251->dev); + struct v4l2_fwnode_endpoint bus_cfg = { + .bus_type = V4L2_MBUS_CSI2_DPHY, + }; struct fwnode_handle *endpoint; - struct ov7251 *ov7251; - u8 chip_id_high, chip_id_low, chip_rev; + unsigned int i, j; int ret; - ov7251 = devm_kzalloc(dev, sizeof(struct ov7251), GFP_KERNEL); - if (!ov7251) - return -ENOMEM; - - ov7251->i2c_client = client; - ov7251->dev = dev; - - endpoint = fwnode_graph_get_next_endpoint(dev_fwnode(dev), NULL); - if (!endpoint) { - dev_err(dev, "endpoint node not found\n"); - return -EINVAL; - } + endpoint = fwnode_graph_get_next_endpoint(fwnode, NULL); + if (!endpoint) + return -EPROBE_DEFER; /* could be provided by cio2-bridge */ - ret = v4l2_fwnode_endpoint_parse(endpoint, &ov7251->ep); + ret = v4l2_fwnode_endpoint_alloc_parse(endpoint, &bus_cfg); fwnode_handle_put(endpoint); - if (ret < 0) { - dev_err(dev, "parsing endpoint node failed\n"); - return ret; + if (ret) + return dev_err_probe(ov7251->dev, ret, + "parsing endpoint node failed\n"); + + if (!bus_cfg.nr_of_link_frequencies) { + ret = dev_err_probe(ov7251->dev, -EINVAL, + "no link frequencies defined\n"); + goto out_free_bus_cfg; } - if (ov7251->ep.bus_type != V4L2_MBUS_CSI2_DPHY) { - dev_err(dev, "invalid bus type (%u), must be CSI2 (%u)\n", - ov7251->ep.bus_type, V4L2_MBUS_CSI2_DPHY); - return -EINVAL; - } + for (i = 0; i < bus_cfg.nr_of_link_frequencies; i++) { + for (j = 0; j < ARRAY_SIZE(link_freq); j++) + if (bus_cfg.link_frequencies[i] == link_freq[j]) + break; - /* get system clock (xclk) */ - ov7251->xclk = devm_clk_get(dev, "xclk"); - if (IS_ERR(ov7251->xclk)) { - dev_err(dev, "could not get xclk"); - return PTR_ERR(ov7251->xclk); + if (j < ARRAY_SIZE(link_freq)) + break; } - ret = fwnode_property_read_u32(dev_fwnode(dev), "clock-frequency", - &ov7251->xclk_freq); - if (ret) { - dev_err(dev, "could not get xclk frequency\n"); - return ret; + if (i == bus_cfg.nr_of_link_frequencies) { + ret = dev_err_probe(ov7251->dev, -EINVAL, + "no supported link freq found\n"); + goto out_free_bus_cfg; } - /* external clock must be 24MHz, allow 1% tolerance */ - if (ov7251->xclk_freq < 23760000 || ov7251->xclk_freq > 24240000) { - dev_err(dev, "external clock frequency %u is not supported\n", - ov7251->xclk_freq); - return -EINVAL; - } + ov7251->link_freq_idx = i; - ret = clk_set_rate(ov7251->xclk, ov7251->xclk_freq); - if (ret) { - dev_err(dev, "could not set xclk frequency\n"); - return ret; - } +out_free_bus_cfg: + v4l2_fwnode_endpoint_free(&bus_cfg); - ov7251->io_regulator = devm_regulator_get(dev, "vdddo"); - if (IS_ERR(ov7251->io_regulator)) { - dev_err(dev, "cannot get io regulator\n"); - return PTR_ERR(ov7251->io_regulator); - } + return ret; +} - ov7251->core_regulator = devm_regulator_get(dev, "vddd"); - if (IS_ERR(ov7251->core_regulator)) { - dev_err(dev, "cannot get core regulator\n"); - return PTR_ERR(ov7251->core_regulator); - } +static int ov7251_detect_chip(struct ov7251 *ov7251) +{ + u8 chip_id_high, chip_id_low, chip_rev; + int ret; - ov7251->analog_regulator = devm_regulator_get(dev, "vdda"); - if (IS_ERR(ov7251->analog_regulator)) { - dev_err(dev, "cannot get analog regulator\n"); - return PTR_ERR(ov7251->analog_regulator); - } + ret = ov7251_read_reg(ov7251, OV7251_CHIP_ID_HIGH, &chip_id_high); + if (ret < 0 || chip_id_high != OV7251_CHIP_ID_HIGH_BYTE) + return dev_err_probe(ov7251->dev, -ENODEV, + "could not read ID high\n"); - ov7251->enable_gpio = devm_gpiod_get(dev, "enable", GPIOD_OUT_HIGH); - if (IS_ERR(ov7251->enable_gpio)) { - dev_err(dev, "cannot get enable gpio\n"); - return PTR_ERR(ov7251->enable_gpio); - } + ret = ov7251_read_reg(ov7251, OV7251_CHIP_ID_LOW, &chip_id_low); + if (ret < 0 || chip_id_low != OV7251_CHIP_ID_LOW_BYTE) + return dev_err_probe(ov7251->dev, -ENODEV, + "could not read ID low\n"); - mutex_init(&ov7251->lock); + ret = ov7251_read_reg(ov7251, OV7251_SC_GP_IO_IN1, &chip_rev); + if (ret < 0) + return dev_err_probe(ov7251->dev, -ENODEV, + "could not read revision\n"); + chip_rev >>= 4; + + dev_info(ov7251->dev, + "OV7251 revision %x (%s) detected at address 0x%02x\n", + chip_rev, + chip_rev == 0x4 ? "1A / 1B" : + chip_rev == 0x5 ? "1C / 1D" : + chip_rev == 0x6 ? "1E" : + chip_rev == 0x7 ? "1F" : "unknown", + ov7251->i2c_client->addr); + + return 0; +} + +static int ov7251_init_ctrls(struct ov7251 *ov7251) +{ + int vblank_max, vblank_def; + s64 pixel_rate; + int hblank; v4l2_ctrl_handler_init(&ov7251->ctrls, 7); ov7251->ctrls.lock = &ov7251->lock; @@ -1356,25 +1555,138 @@ static int ov7251_probe(struct i2c_client *client) V4L2_CID_TEST_PATTERN, ARRAY_SIZE(ov7251_test_pattern_menu) - 1, 0, 0, ov7251_test_pattern_menu); + + pixel_rate = pixel_rates[ov7251->link_freq_idx]; ov7251->pixel_clock = v4l2_ctrl_new_std(&ov7251->ctrls, &ov7251_ctrl_ops, V4L2_CID_PIXEL_RATE, - 1, INT_MAX, 1, 1); + pixel_rate, INT_MAX, + pixel_rate, pixel_rate); ov7251->link_freq = v4l2_ctrl_new_int_menu(&ov7251->ctrls, &ov7251_ctrl_ops, V4L2_CID_LINK_FREQ, ARRAY_SIZE(link_freq) - 1, - 0, link_freq); + ov7251->link_freq_idx, + link_freq); if (ov7251->link_freq) ov7251->link_freq->flags |= V4L2_CTRL_FLAG_READ_ONLY; + if (ov7251->pixel_clock) + ov7251->pixel_clock->flags |= V4L2_CTRL_FLAG_READ_ONLY; + + hblank = OV7251_FIXED_PPL - ov7251->current_mode->width; + ov7251->hblank = v4l2_ctrl_new_std(&ov7251->ctrls, &ov7251_ctrl_ops, + V4L2_CID_HBLANK, hblank, hblank, 1, + hblank); + if (ov7251->hblank) + ov7251->hblank->flags |= V4L2_CTRL_FLAG_READ_ONLY; + + vblank_max = OV7251_TIMING_MAX_VTS - ov7251->current_mode->height; + vblank_def = ov7251->current_mode->vts - ov7251->current_mode->height; + ov7251->vblank = v4l2_ctrl_new_std(&ov7251->ctrls, &ov7251_ctrl_ops, + V4L2_CID_VBLANK, + OV7251_TIMING_MIN_VTS, vblank_max, 1, + vblank_def); ov7251->sd.ctrl_handler = &ov7251->ctrls; if (ov7251->ctrls.error) { - dev_err(dev, "%s: control initialization error %d\n", - __func__, ov7251->ctrls.error); - ret = ov7251->ctrls.error; - goto free_ctrl; + v4l2_ctrl_handler_free(&ov7251->ctrls); + return ov7251->ctrls.error; + } + + return 0; +} + +static int ov7251_probe(struct i2c_client *client) +{ + struct device *dev = &client->dev; + struct ov7251 *ov7251; + unsigned int rate = 0, clk_rate = 0; + int ret; + int i; + + ov7251 = devm_kzalloc(dev, sizeof(struct ov7251), GFP_KERNEL); + if (!ov7251) + return -ENOMEM; + + ov7251->i2c_client = client; + ov7251->dev = dev; + + ret = ov7251_check_hwcfg(ov7251); + if (ret) + return ret; + + /* get system clock (xclk) */ + ov7251->xclk = devm_clk_get_optional(dev, NULL); + if (IS_ERR(ov7251->xclk)) + return dev_err_probe(dev, PTR_ERR(ov7251->xclk), + "could not get xclk"); + + /* + * We could have either a 24MHz or 19.2MHz clock rate from either DT or + * ACPI. We also need to support the IPU3 case which will have both an + * external clock AND a clock-frequency property. + */ + ret = fwnode_property_read_u32(dev_fwnode(dev), "clock-frequency", + &rate); + if (ret && !ov7251->xclk) + return dev_err_probe(dev, ret, "invalid clock config\n"); + + clk_rate = clk_get_rate(ov7251->xclk); + ov7251->xclk_freq = clk_rate ? clk_rate : rate; + + if (ov7251->xclk_freq == 0) + return dev_err_probe(dev, -EINVAL, "invalid clock frequency\n"); + + if (!ret && ov7251->xclk) { + ret = clk_set_rate(ov7251->xclk, rate); + if (ret) + return dev_err_probe(dev, ret, + "failed to set clock rate\n"); + } + + for (i = 0; i < ARRAY_SIZE(supported_xclk_rates); i++) + if (ov7251->xclk_freq == supported_xclk_rates[i]) + break; + + if (i == ARRAY_SIZE(supported_xclk_rates)) + return dev_err_probe(dev, -EINVAL, + "clock rate %u Hz is unsupported\n", + ov7251->xclk_freq); + + ov7251->pll_cfgs = ov7251_pll_cfgs[i]; + + ov7251->io_regulator = devm_regulator_get(dev, "vdddo"); + if (IS_ERR(ov7251->io_regulator)) { + dev_err(dev, "cannot get io regulator\n"); + return PTR_ERR(ov7251->io_regulator); + } + + ov7251->core_regulator = devm_regulator_get(dev, "vddd"); + if (IS_ERR(ov7251->core_regulator)) { + dev_err(dev, "cannot get core regulator\n"); + return PTR_ERR(ov7251->core_regulator); + } + + ov7251->analog_regulator = devm_regulator_get(dev, "vdda"); + if (IS_ERR(ov7251->analog_regulator)) { + dev_err(dev, "cannot get analog regulator\n"); + return PTR_ERR(ov7251->analog_regulator); + } + + ov7251->enable_gpio = devm_gpiod_get(dev, "enable", GPIOD_OUT_HIGH); + if (IS_ERR(ov7251->enable_gpio)) { + dev_err(dev, "cannot get enable gpio\n"); + return PTR_ERR(ov7251->enable_gpio); + } + + mutex_init(&ov7251->lock); + + ov7251->current_mode = &ov7251_mode_info_data[0]; + ret = ov7251_init_ctrls(ov7251); + if (ret) { + dev_err_probe(dev, ret, "error during v4l2 ctrl init\n"); + goto destroy_mutex; } v4l2_i2c_subdev_init(&ov7251->sd, client, &ov7251_subdev_ops); @@ -1389,47 +1701,24 @@ static int ov7251_probe(struct i2c_client *client) goto free_ctrl; } - ret = ov7251_s_power(&ov7251->sd, true); - if (ret < 0) { - dev_err(dev, "could not power up OV7251\n"); + ret = ov7251_set_power_on(ov7251->dev); + if (ret) goto free_entity; - } - ret = ov7251_read_reg(ov7251, OV7251_CHIP_ID_HIGH, &chip_id_high); - if (ret < 0 || chip_id_high != OV7251_CHIP_ID_HIGH_BYTE) { - dev_err(dev, "could not read ID high\n"); - ret = -ENODEV; - goto power_down; - } - ret = ov7251_read_reg(ov7251, OV7251_CHIP_ID_LOW, &chip_id_low); - if (ret < 0 || chip_id_low != OV7251_CHIP_ID_LOW_BYTE) { - dev_err(dev, "could not read ID low\n"); - ret = -ENODEV; + ret = ov7251_detect_chip(ov7251); + if (ret) goto power_down; - } - ret = ov7251_read_reg(ov7251, OV7251_SC_GP_IO_IN1, &chip_rev); - if (ret < 0) { - dev_err(dev, "could not read revision\n"); - ret = -ENODEV; - goto power_down; - } - chip_rev >>= 4; - - dev_info(dev, "OV7251 revision %x (%s) detected at address 0x%02x\n", - chip_rev, - chip_rev == 0x4 ? "1A / 1B" : - chip_rev == 0x5 ? "1C / 1D" : - chip_rev == 0x6 ? "1E" : - chip_rev == 0x7 ? "1F" : "unknown", - client->addr); + pm_runtime_set_active(&client->dev); + pm_runtime_get_noresume(&client->dev); + pm_runtime_enable(&client->dev); ret = ov7251_read_reg(ov7251, OV7251_PRE_ISP_00, &ov7251->pre_isp_00); if (ret < 0) { dev_err(dev, "could not read test pattern value\n"); ret = -ENODEV; - goto power_down; + goto err_pm_runtime; } ret = ov7251_read_reg(ov7251, OV7251_TIMING_FORMAT1, @@ -1437,7 +1726,7 @@ static int ov7251_probe(struct i2c_client *client) if (ret < 0) { dev_err(dev, "could not read vflip value\n"); ret = -ENODEV; - goto power_down; + goto err_pm_runtime; } ret = ov7251_read_reg(ov7251, OV7251_TIMING_FORMAT2, @@ -1445,10 +1734,12 @@ static int ov7251_probe(struct i2c_client *client) if (ret < 0) { dev_err(dev, "could not read hflip value\n"); ret = -ENODEV; - goto power_down; + goto err_pm_runtime; } - ov7251_s_power(&ov7251->sd, false); + pm_runtime_set_autosuspend_delay(&client->dev, 1000); + pm_runtime_use_autosuspend(&client->dev); + pm_runtime_put_autosuspend(&client->dev); ret = v4l2_async_register_subdev(&ov7251->sd); if (ret < 0) { @@ -1460,12 +1751,16 @@ static int ov7251_probe(struct i2c_client *client) return 0; +err_pm_runtime: + pm_runtime_disable(ov7251->dev); + pm_runtime_put_noidle(ov7251->dev); power_down: - ov7251_s_power(&ov7251->sd, false); + ov7251_set_power_off(ov7251->dev); free_entity: media_entity_cleanup(&ov7251->sd.entity); free_ctrl: v4l2_ctrl_handler_free(&ov7251->ctrls); +destroy_mutex: mutex_destroy(&ov7251->lock); return ret; @@ -1481,19 +1776,36 @@ static int ov7251_remove(struct i2c_client *client) v4l2_ctrl_handler_free(&ov7251->ctrls); mutex_destroy(&ov7251->lock); + pm_runtime_disable(ov7251->dev); + if (!pm_runtime_status_suspended(ov7251->dev)) + ov7251_set_power_off(ov7251->dev); + pm_runtime_set_suspended(ov7251->dev); + return 0; } +static const struct dev_pm_ops ov7251_pm_ops = { + SET_RUNTIME_PM_OPS(ov7251_set_power_off, ov7251_set_power_on, NULL) +}; + static const struct of_device_id ov7251_of_match[] = { { .compatible = "ovti,ov7251" }, { /* sentinel */ } }; MODULE_DEVICE_TABLE(of, ov7251_of_match); +static const struct acpi_device_id ov7251_acpi_match[] = { + { "INT347E" }, + { } +}; +MODULE_DEVICE_TABLE(acpi, ov7251_acpi_match); + static struct i2c_driver ov7251_i2c_driver = { .driver = { .of_match_table = ov7251_of_match, + .acpi_match_table = ov7251_acpi_match, .name = "ov7251", + .pm = &ov7251_pm_ops, }, .probe_new = ov7251_probe, .remove = ov7251_remove, diff --git a/drivers/media/i2c/ov7640.c b/drivers/media/i2c/ov7640.c index 010803d58ce8..977cd2d8ad33 100644 --- a/drivers/media/i2c/ov7640.c +++ b/drivers/media/i2c/ov7640.c @@ -13,23 +13,28 @@ MODULE_DESCRIPTION("OmniVision ov7640 sensor driver"); MODULE_LICENSE("GPL v2"); -static const u8 initial_registers[] = { - 0x12, 0x80, - 0x12, 0x54, - 0x14, 0x24, - 0x15, 0x01, - 0x28, 0x20, - 0x75, 0x82, - 0xFF, 0xFF, /* Terminator (reg 0xFF is unused) */ +struct reg_val { + u8 reg; + u8 val; }; -static int write_regs(struct i2c_client *client, const u8 *regs) -{ - int i; +static const struct reg_val regval_init[] = { + {0x12, 0x80}, + {0x12, 0x54}, + {0x14, 0x24}, + {0x15, 0x01}, + {0x28, 0x20}, + {0x75, 0x82}, +}; - for (i = 0; regs[i] != 0xFF; i += 2) - if (i2c_smbus_write_byte_data(client, regs[i], regs[i + 1]) < 0) +static int write_regs(struct i2c_client *client, + const struct reg_val *rv, int len) +{ + while (--len >= 0) { + if (i2c_smbus_write_byte_data(client, rv->reg, rv->val) < 0) return -1; + rv++; + } return 0; } @@ -56,7 +61,7 @@ static int ov7640_probe(struct i2c_client *client, v4l_info(client, "chip found @ 0x%02x (%s)\n", client->addr << 1, client->adapter->name); - if (write_regs(client, initial_registers) < 0) { + if (write_regs(client, regval_init, ARRAY_SIZE(regval_init)) < 0) { v4l_err(client, "error initializing OV7640\n"); return -ENODEV; } diff --git a/drivers/media/i2c/ov7670.c b/drivers/media/i2c/ov7670.c index 196746423116..1be2c0e5bdc1 100644 --- a/drivers/media/i2c/ov7670.c +++ b/drivers/media/i2c/ov7670.c @@ -2017,7 +2017,6 @@ static int ov7670_remove(struct i2c_client *client) v4l2_async_unregister_subdev(sd); v4l2_ctrl_handler_free(&info->hdl); media_entity_cleanup(&info->sd.entity); - ov7670_power_off(sd); return 0; } diff --git a/drivers/media/i2c/ov8856.c b/drivers/media/i2c/ov8856.c index 8785764b7a74..a9728afc81d4 100644 --- a/drivers/media/i2c/ov8856.c +++ b/drivers/media/i2c/ov8856.c @@ -63,6 +63,7 @@ #define OV8856_ANAL_GAIN_STEP 1 /* Digital gain controls from sensor */ +#define OV8856_REG_DIGITAL_GAIN 0x350a #define OV8856_REG_MWB_R_GAIN 0x5019 #define OV8856_REG_MWB_G_GAIN 0x501b #define OV8856_REG_MWB_B_GAIN 0x501d @@ -351,7 +352,7 @@ static const struct ov8856_reg lane_2_mode_3280x2464[] = { {0x484b, 0x05}, {0x5000, 0x57}, {0x5001, 0x0a}, - {0x5004, 0x04}, + {0x5004, 0x06}, {0x502e, 0x03}, {0x5030, 0x41}, {0x5795, 0x02}, @@ -543,7 +544,7 @@ static const struct ov8856_reg lane_2_mode_1640x1232[] = { {0x484b, 0x05}, {0x5000, 0x57}, {0x5001, 0x0a}, - {0x5004, 0x04}, + {0x5004, 0x06}, {0x502e, 0x03}, {0x5030, 0x41}, {0x5795, 0x00}, @@ -734,7 +735,7 @@ static const struct ov8856_reg lane_4_mode_3280x2464[] = { {0x484b, 0x05}, {0x5000, 0x57}, {0x5001, 0x0a}, - {0x5004, 0x04}, + {0x5004, 0x06}, {0x502e, 0x03}, {0x5030, 0x41}, {0x5780, 0x14}, @@ -925,7 +926,7 @@ static const struct ov8856_reg lane_4_mode_1640x1232[] = { {0x484b, 0x05}, {0x5000, 0x57}, {0x5001, 0x0a}, - {0x5004, 0x04}, + {0x5004, 0x06}, {0x502e, 0x03}, {0x5030, 0x41}, {0x5780, 0x14}, @@ -1755,19 +1756,7 @@ static int ov8856_identify_module(struct ov8856 *ov8856) static int ov8856_update_digital_gain(struct ov8856 *ov8856, u32 d_gain) { - int ret; - - ret = ov8856_write_reg(ov8856, OV8856_REG_MWB_R_GAIN, - OV8856_REG_VALUE_16BIT, d_gain); - if (ret) - return ret; - - ret = ov8856_write_reg(ov8856, OV8856_REG_MWB_G_GAIN, - OV8856_REG_VALUE_16BIT, d_gain); - if (ret) - return ret; - - return ov8856_write_reg(ov8856, OV8856_REG_MWB_B_GAIN, + return ov8856_write_reg(ov8856, OV8856_REG_DIGITAL_GAIN, OV8856_REG_VALUE_16BIT, d_gain); } diff --git a/drivers/media/i2c/rdacm20.c b/drivers/media/i2c/rdacm20.c index 025a610de893..2615ad154f49 100644 --- a/drivers/media/i2c/rdacm20.c +++ b/drivers/media/i2c/rdacm20.c @@ -47,11 +47,11 @@ #define OV10635_VTS 933 /* - * As the drivers supports a single MEDIA_BUS_FMT_UYVY8_2X8 format we + * As the drivers supports a single MEDIA_BUS_FMT_UYVY8_1X16 format we * can harcode the pixel rate. * * PCLK is fed through the system clock, programmed @88MHz. - * MEDIA_BUS_FMT_UYVY8_2X8 format = 2 samples per pixel. + * MEDIA_BUS_FMT_UYVY8_1X16 format = 2 samples per pixel. * * Pixelrate = PCLK / 2 * FPS = (OV10635_VTS * OV10635_HTS) / PixelRate @@ -409,7 +409,7 @@ static int rdacm20_enum_mbus_code(struct v4l2_subdev *sd, if (code->pad || code->index > 0) return -EINVAL; - code->code = MEDIA_BUS_FMT_UYVY8_2X8; + code->code = MEDIA_BUS_FMT_UYVY8_1X16; return 0; } @@ -425,7 +425,7 @@ static int rdacm20_get_fmt(struct v4l2_subdev *sd, mf->width = OV10635_WIDTH; mf->height = OV10635_HEIGHT; - mf->code = MEDIA_BUS_FMT_UYVY8_2X8; + mf->code = MEDIA_BUS_FMT_UYVY8_1X16; mf->colorspace = V4L2_COLORSPACE_RAW; mf->field = V4L2_FIELD_NONE; mf->ycbcr_enc = V4L2_YCBCR_ENC_601; @@ -611,7 +611,7 @@ static int rdacm20_probe(struct i2c_client *client) goto error_free_ctrls; dev->pad.flags = MEDIA_PAD_FL_SOURCE; - dev->sd.entity.flags |= MEDIA_ENT_F_CAM_SENSOR; + dev->sd.entity.function = MEDIA_ENT_F_CAM_SENSOR; ret = media_entity_pads_init(&dev->sd.entity, 1, &dev->pad); if (ret < 0) goto error_free_ctrls; diff --git a/drivers/media/i2c/rdacm21.c b/drivers/media/i2c/rdacm21.c index 12ec5467ed1e..ef31cf5f23ca 100644 --- a/drivers/media/i2c/rdacm21.c +++ b/drivers/media/i2c/rdacm21.c @@ -583,7 +583,7 @@ static int rdacm21_probe(struct i2c_client *client) goto error_free_ctrls; dev->pad.flags = MEDIA_PAD_FL_SOURCE; - dev->sd.entity.flags |= MEDIA_ENT_F_CAM_SENSOR; + dev->sd.entity.function = MEDIA_ENT_F_CAM_SENSOR; ret = media_entity_pads_init(&dev->sd.entity, 1, &dev->pad); if (ret < 0) goto error_free_ctrls; diff --git a/drivers/media/i2c/s5k6a3.c b/drivers/media/i2c/s5k6a3.c index b97dd6149e90..f6ecf6f92bb2 100644 --- a/drivers/media/i2c/s5k6a3.c +++ b/drivers/media/i2c/s5k6a3.c @@ -213,7 +213,7 @@ static int __s5k6a3_power_on(struct s5k6a3 *sensor) for (i++; i < S5K6A3_NUM_SUPPLIES; i++) { ret = regulator_enable(sensor->supplies[i].consumer); if (ret < 0) - goto error_reg_dis; + goto error_clk; } gpio_set_value(sensor->gpio_reset, 1); @@ -226,6 +226,8 @@ static int __s5k6a3_power_on(struct s5k6a3 *sensor) msleep(20); return 0; +error_clk: + clk_disable_unprepare(sensor->clock); error_reg_dis: for (--i; i >= 0; --i) regulator_disable(sensor->supplies[i].consumer); diff --git a/drivers/media/i2c/video-i2c.c b/drivers/media/i2c/video-i2c.c index cb660b4bfd4b..e08e3579c0a1 100644 --- a/drivers/media/i2c/video-i2c.c +++ b/drivers/media/i2c/video-i2c.c @@ -9,6 +9,7 @@ * - Melexis MLX90640 Thermal Cameras */ +#include <linux/bits.h> #include <linux/delay.h> #include <linux/freezer.h> #include <linux/hwmon.h> @@ -34,6 +35,37 @@ #define VIDEO_I2C_DRIVER "video-i2c" +/* Power control register */ +#define AMG88XX_REG_PCTL 0x00 +#define AMG88XX_PCTL_NORMAL 0x00 +#define AMG88XX_PCTL_SLEEP 0x10 + +/* Reset register */ +#define AMG88XX_REG_RST 0x01 +#define AMG88XX_RST_FLAG 0x30 +#define AMG88XX_RST_INIT 0x3f + +/* Frame rate register */ +#define AMG88XX_REG_FPSC 0x02 +#define AMG88XX_FPSC_1FPS BIT(0) + +/* Thermistor register */ +#define AMG88XX_REG_TTHL 0x0e + +/* Temperature register */ +#define AMG88XX_REG_T01L 0x80 + +/* RAM */ +#define MLX90640_RAM_START_ADDR 0x0400 + +/* EEPROM */ +#define MLX90640_EEPROM_START_ADDR 0x2400 + +/* Control register */ +#define MLX90640_REG_CTL1 0x800d +#define MLX90640_REG_CTL1_MASK GENMASK(9, 7) +#define MLX90640_REG_CTL1_MASK_SHIFT 7 + struct video_i2c_chip; struct video_i2c_buffer { @@ -124,7 +156,7 @@ static int mlx90640_nvram_read(void *priv, unsigned int offset, void *val, { struct video_i2c_data *data = priv; - return regmap_bulk_read(data->regmap, 0x2400 + offset, val, bytes); + return regmap_bulk_read(data->regmap, MLX90640_EEPROM_START_ADDR + offset, val, bytes); } static struct nvmem_config mlx90640_nvram_config = { @@ -135,31 +167,6 @@ static struct nvmem_config mlx90640_nvram_config = { .reg_read = mlx90640_nvram_read, }; -/* Power control register */ -#define AMG88XX_REG_PCTL 0x00 -#define AMG88XX_PCTL_NORMAL 0x00 -#define AMG88XX_PCTL_SLEEP 0x10 - -/* Reset register */ -#define AMG88XX_REG_RST 0x01 -#define AMG88XX_RST_FLAG 0x30 -#define AMG88XX_RST_INIT 0x3f - -/* Frame rate register */ -#define AMG88XX_REG_FPSC 0x02 -#define AMG88XX_FPSC_1FPS BIT(0) - -/* Thermistor register */ -#define AMG88XX_REG_TTHL 0x0e - -/* Temperature register */ -#define AMG88XX_REG_T01L 0x80 - -/* Control register */ -#define MLX90640_REG_CTL1 0x800d -#define MLX90640_REG_CTL1_MASK 0x0380 -#define MLX90640_REG_CTL1_MASK_SHIFT 7 - static int amg88xx_xfer(struct video_i2c_data *data, char *buf) { return regmap_bulk_read(data->regmap, AMG88XX_REG_T01L, buf, @@ -168,7 +175,7 @@ static int amg88xx_xfer(struct video_i2c_data *data, char *buf) static int mlx90640_xfer(struct video_i2c_data *data, char *buf) { - return regmap_bulk_read(data->regmap, 0x400, buf, + return regmap_bulk_read(data->regmap, MLX90640_RAM_START_ADDR, buf, data->chip->buffer_size); } diff --git a/drivers/media/mc/mc-device.c b/drivers/media/mc/mc-device.c index cf5e459b1d96..b8176a3b76d3 100644 --- a/drivers/media/mc/mc-device.c +++ b/drivers/media/mc/mc-device.c @@ -604,15 +604,8 @@ static void __media_device_unregister_entity(struct media_entity *entity) media_gobj_destroy(&entity->graph_obj); /* invoke entity_notify callbacks to handle entity removal?? */ - - entity->graph_obj.mdev = NULL; } -/** - * media_device_register_entity - Register an entity with a media device - * @mdev: The media device - * @entity: The entity - */ int __must_check media_device_register_entity(struct media_device *mdev, struct media_entity *entity) { @@ -691,16 +684,6 @@ void media_device_unregister_entity(struct media_entity *entity) } EXPORT_SYMBOL_GPL(media_device_unregister_entity); -/** - * media_device_init() - initialize a media device - * @mdev: The media device - * - * The caller is responsible for initializing the media device before - * registration. The following fields must be set: - * - * - dev must point to the parent device - * - model must be filled with the device model name - */ void media_device_init(struct media_device *mdev) { INIT_LIST_HEAD(&mdev->entities); @@ -715,6 +698,10 @@ void media_device_init(struct media_device *mdev) atomic_set(&mdev->request_id, 0); + if (!*mdev->bus_info) + media_set_bus_info(mdev->bus_info, sizeof(mdev->bus_info), + mdev->dev); + dev_dbg(mdev->dev, "Media device initialized\n"); } EXPORT_SYMBOL_GPL(media_device_init); diff --git a/drivers/media/mc/mc-entity.c b/drivers/media/mc/mc-entity.c index 8ab0913d8d82..11f5207f73aa 100644 --- a/drivers/media/mc/mc-entity.c +++ b/drivers/media/mc/mc-entity.c @@ -44,6 +44,20 @@ static inline const char *intf_type(struct media_interface *intf) } }; +static inline const char *link_type_name(struct media_link *link) +{ + switch (link->flags & MEDIA_LNK_FL_LINK_TYPE) { + case MEDIA_LNK_FL_DATA_LINK: + return "data"; + case MEDIA_LNK_FL_INTERFACE_LINK: + return "interface"; + case MEDIA_LNK_FL_ANCILLARY_LINK: + return "ancillary"; + default: + return "unknown"; + } +} + __must_check int __media_entity_enum_init(struct media_entity_enum *ent_enum, int idx_max) { @@ -89,9 +103,7 @@ static void dev_dbg_obj(const char *event_name, struct media_gobj *gobj) dev_dbg(gobj->mdev->dev, "%s id %u: %s link id %u ==> id %u\n", - event_name, media_id(gobj), - media_type(link->gobj0) == MEDIA_GRAPH_PAD ? - "data" : "interface", + event_name, media_id(gobj), link_type_name(link), media_id(link->gobj0), media_id(link->gobj1)); break; @@ -295,6 +307,12 @@ static void media_graph_walk_iter(struct media_graph *graph) link = list_entry(link_top(graph), typeof(*link), list); + /* If the link is not a data link, don't follow it */ + if ((link->flags & MEDIA_LNK_FL_LINK_TYPE) != MEDIA_LNK_FL_DATA_LINK) { + link_top(graph) = link_top(graph)->next; + return; + } + /* The link is not enabled so we do not follow. */ if (!(link->flags & MEDIA_LNK_FL_ENABLED)) { link_top(graph) = link_top(graph)->next; @@ -579,26 +597,30 @@ static void __media_entity_remove_link(struct media_entity *entity, struct media_link *rlink, *tmp; struct media_entity *remote; - if (link->source->entity == entity) - remote = link->sink->entity; - else - remote = link->source->entity; + /* Remove the reverse links for a data link. */ + if ((link->flags & MEDIA_LNK_FL_LINK_TYPE) == MEDIA_LNK_FL_DATA_LINK) { + if (link->source->entity == entity) + remote = link->sink->entity; + else + remote = link->source->entity; - list_for_each_entry_safe(rlink, tmp, &remote->links, list) { - if (rlink != link->reverse) - continue; + list_for_each_entry_safe(rlink, tmp, &remote->links, list) { + if (rlink != link->reverse) + continue; - if (link->source->entity == entity) - remote->num_backlinks--; + if (link->source->entity == entity) + remote->num_backlinks--; - /* Remove the remote link */ - list_del(&rlink->list); - media_gobj_destroy(&rlink->graph_obj); - kfree(rlink); + /* Remove the remote link */ + list_del(&rlink->list); + media_gobj_destroy(&rlink->graph_obj); + kfree(rlink); - if (--remote->num_links == 0) - break; + if (--remote->num_links == 0) + break; + } } + list_del(&link->list); media_gobj_destroy(&link->graph_obj); kfree(link); @@ -1007,3 +1029,25 @@ void media_remove_intf_links(struct media_interface *intf) mutex_unlock(&mdev->graph_mutex); } EXPORT_SYMBOL_GPL(media_remove_intf_links); + +struct media_link *media_create_ancillary_link(struct media_entity *primary, + struct media_entity *ancillary) +{ + struct media_link *link; + + link = media_add_link(&primary->links); + if (!link) + return ERR_PTR(-ENOMEM); + + link->gobj0 = &primary->graph_obj; + link->gobj1 = &ancillary->graph_obj; + link->flags = MEDIA_LNK_FL_IMMUTABLE | MEDIA_LNK_FL_ENABLED | + MEDIA_LNK_FL_ANCILLARY_LINK; + + /* Initialize graph object embedded in the new link */ + media_gobj_create(primary->graph_obj.mdev, MEDIA_GRAPH_LINK, + &link->graph_obj); + + return link; +} +EXPORT_SYMBOL_GPL(media_create_ancillary_link); diff --git a/drivers/media/pci/bt8xx/bttv-driver.c b/drivers/media/pci/bt8xx/bttv-driver.c index 5ca3d0cc653a..d40b537f4e98 100644 --- a/drivers/media/pci/bt8xx/bttv-driver.c +++ b/drivers/media/pci/bt8xx/bttv-driver.c @@ -2435,8 +2435,6 @@ static int bttv_querycap(struct file *file, void *priv, strscpy(cap->driver, "bttv", sizeof(cap->driver)); strscpy(cap->card, btv->video_dev.name, sizeof(cap->card)); - snprintf(cap->bus_info, sizeof(cap->bus_info), - "PCI:%s", pci_name(btv->c.pci)); cap->capabilities = V4L2_CAP_VIDEO_CAPTURE | V4L2_CAP_READWRITE | V4L2_CAP_STREAMING | V4L2_CAP_DEVICE_CAPS; if (no_overlay <= 0) diff --git a/drivers/media/pci/cx18/cx18-ioctl.c b/drivers/media/pci/cx18/cx18-ioctl.c index ce3f0141f94e..c8ba7841c720 100644 --- a/drivers/media/pci/cx18/cx18-ioctl.c +++ b/drivers/media/pci/cx18/cx18-ioctl.c @@ -389,8 +389,6 @@ static int cx18_querycap(struct file *file, void *fh, strscpy(vcap->driver, CX18_DRIVER_NAME, sizeof(vcap->driver)); strscpy(vcap->card, cx->card_name, sizeof(vcap->card)); - snprintf(vcap->bus_info, sizeof(vcap->bus_info), - "PCI:%s", pci_name(cx->pci_dev)); vcap->capabilities = cx->v4l2_cap | V4L2_CAP_DEVICE_CAPS; return 0; } diff --git a/drivers/media/pci/cx23885/cx23885-core.c b/drivers/media/pci/cx23885/cx23885-core.c index f8f2ff3b00c3..a07b18f2034e 100644 --- a/drivers/media/pci/cx23885/cx23885-core.c +++ b/drivers/media/pci/cx23885/cx23885-core.c @@ -2165,7 +2165,7 @@ static int cx23885_initdev(struct pci_dev *pci_dev, err = dma_set_mask(&pci_dev->dev, 0xffffffff); if (err) { pr_err("%s/0: Oops: no 32bit PCI DMA ???\n", dev->name); - goto fail_ctrl; + goto fail_dma_set_mask; } err = request_irq(pci_dev->irq, cx23885_irq, @@ -2173,7 +2173,7 @@ static int cx23885_initdev(struct pci_dev *pci_dev, if (err < 0) { pr_err("%s: can't get IRQ %d\n", dev->name, pci_dev->irq); - goto fail_irq; + goto fail_dma_set_mask; } switch (dev->board) { @@ -2195,7 +2195,7 @@ static int cx23885_initdev(struct pci_dev *pci_dev, return 0; -fail_irq: +fail_dma_set_mask: cx23885_dev_unregister(dev); fail_ctrl: v4l2_ctrl_handler_free(hdl); diff --git a/drivers/media/pci/cx25821/cx25821-alsa.c b/drivers/media/pci/cx25821/cx25821-alsa.c index 438fdcec6eac..a42f0c03a7ca 100644 --- a/drivers/media/pci/cx25821/cx25821-alsa.c +++ b/drivers/media/pci/cx25821/cx25821-alsa.c @@ -728,8 +728,8 @@ static int cx25821_audio_initdev(struct cx25821_dev *dev) chip->irq = dev->pci->irq; - err = request_irq(dev->pci->irq, cx25821_irq, - IRQF_SHARED, chip->dev->name, chip); + err = devm_request_irq(&dev->pci->dev, dev->pci->irq, cx25821_irq, + IRQF_SHARED, chip->dev->name, chip); if (err < 0) { pr_err("ERROR %s: can't get IRQ %d for ALSA\n", chip->dev->name, diff --git a/drivers/media/pci/cx25821/cx25821-core.c b/drivers/media/pci/cx25821/cx25821-core.c index 3078a39f0b95..6627fa9166d3 100644 --- a/drivers/media/pci/cx25821/cx25821-core.c +++ b/drivers/media/pci/cx25821/cx25821-core.c @@ -1332,11 +1332,11 @@ static void cx25821_finidev(struct pci_dev *pci_dev) struct cx25821_dev *dev = get_cx25821(v4l2_dev); cx25821_shutdown(dev); - pci_disable_device(pci_dev); /* unregister stuff */ if (pci_dev->irq) free_irq(pci_dev->irq, dev); + pci_disable_device(pci_dev); cx25821_dev_unregister(dev); v4l2_device_unregister(v4l2_dev); diff --git a/drivers/media/pci/cx88/cx88-blackbird.c b/drivers/media/pci/cx88/cx88-blackbird.c index d5da3bd5695d..c1b41a9283c1 100644 --- a/drivers/media/pci/cx88/cx88-blackbird.c +++ b/drivers/media/pci/cx88/cx88-blackbird.c @@ -796,7 +796,6 @@ static int vidioc_querycap(struct file *file, void *priv, struct cx88_core *core = dev->core; strscpy(cap->driver, "cx88_blackbird", sizeof(cap->driver)); - sprintf(cap->bus_info, "PCI:%s", pci_name(dev->pci)); return cx88_querycap(file, core, cap); } diff --git a/drivers/media/pci/cx88/cx88-video.c b/drivers/media/pci/cx88/cx88-video.c index c17ad9f7d822..d3729be89252 100644 --- a/drivers/media/pci/cx88/cx88-video.c +++ b/drivers/media/pci/cx88/cx88-video.c @@ -808,7 +808,6 @@ static int vidioc_querycap(struct file *file, void *priv, struct cx88_core *core = dev->core; strscpy(cap->driver, "cx8800", sizeof(cap->driver)); - sprintf(cap->bus_info, "PCI:%s", pci_name(dev->pci)); return cx88_querycap(file, core, cap); } diff --git a/drivers/media/pci/dt3155/dt3155.c b/drivers/media/pci/dt3155/dt3155.c index 961f844de99c..548156b199cc 100644 --- a/drivers/media/pci/dt3155/dt3155.c +++ b/drivers/media/pci/dt3155/dt3155.c @@ -292,11 +292,8 @@ static const struct v4l2_file_operations dt3155_fops = { static int dt3155_querycap(struct file *filp, void *p, struct v4l2_capability *cap) { - struct dt3155_priv *pd = video_drvdata(filp); - strscpy(cap->driver, DT3155_NAME, sizeof(cap->driver)); strscpy(cap->card, DT3155_NAME " frame grabber", sizeof(cap->card)); - sprintf(cap->bus_info, "PCI:%s", pci_name(pd->pdev)); return 0; } diff --git a/drivers/media/pci/intel/ipu3/cio2-bridge.c b/drivers/media/pci/intel/ipu3/cio2-bridge.c index 7ccb7b6eaa82..df6c94da2f6a 100644 --- a/drivers/media/pci/intel/ipu3/cio2-bridge.c +++ b/drivers/media/pci/intel/ipu3/cio2-bridge.c @@ -25,6 +25,8 @@ static const struct cio2_sensor_config cio2_supported_sensors[] = { CIO2_SENSOR_CONFIG("INT33BE", 1, 419200000), /* Omnivision OV8865 */ CIO2_SENSOR_CONFIG("INT347A", 1, 360000000), + /* Omnivision OV7251 */ + CIO2_SENSOR_CONFIG("INT347E", 1, 319200000), /* Omnivision OV2680 */ CIO2_SENSOR_CONFIG("OVTI2680", 0), }; diff --git a/drivers/media/pci/intel/ipu3/ipu3-cio2-main.c b/drivers/media/pci/intel/ipu3/ipu3-cio2-main.c index 0e9b0503b62a..dbdbdb648a0d 100644 --- a/drivers/media/pci/intel/ipu3/ipu3-cio2-main.c +++ b/drivers/media/pci/intel/ipu3/ipu3-cio2-main.c @@ -65,6 +65,11 @@ static const struct ipu3_cio2_fmt formats[] = { .fourcc = V4L2_PIX_FMT_IPU3_SRGGB10, .mipicode = 0x2b, .bpp = 10, + }, { + .mbus_code = MEDIA_BUS_FMT_Y10_1X10, + .fourcc = V4L2_PIX_FMT_IPU3_Y10, + .mipicode = 0x2b, + .bpp = 10, }, }; @@ -1046,12 +1051,8 @@ static const struct vb2_ops cio2_vb2_ops = { static int cio2_v4l2_querycap(struct file *file, void *fh, struct v4l2_capability *cap) { - struct cio2_device *cio2 = video_drvdata(file); - strscpy(cap->driver, CIO2_NAME, sizeof(cap->driver)); strscpy(cap->card, CIO2_DEVICE_NAME, sizeof(cap->card)); - snprintf(cap->bus_info, sizeof(cap->bus_info), - "PCI:%s", pci_name(cio2->pci_dev)); return 0; } @@ -1777,8 +1778,6 @@ static int cio2_pci_probe(struct pci_dev *pci_dev, cio2->media_dev.dev = dev; strscpy(cio2->media_dev.model, CIO2_DEVICE_NAME, sizeof(cio2->media_dev.model)); - snprintf(cio2->media_dev.bus_info, sizeof(cio2->media_dev.bus_info), - "PCI:%s", pci_name(cio2->pci_dev)); cio2->media_dev.hw_revision = 0; media_device_init(&cio2->media_dev); diff --git a/drivers/media/pci/ivtv/ivtv-ioctl.c b/drivers/media/pci/ivtv/ivtv-ioctl.c index fee460e2ca86..7947dcd615e8 100644 --- a/drivers/media/pci/ivtv/ivtv-ioctl.c +++ b/drivers/media/pci/ivtv/ivtv-ioctl.c @@ -732,7 +732,6 @@ static int ivtv_querycap(struct file *file, void *fh, struct v4l2_capability *vc strscpy(vcap->driver, IVTV_DRIVER_NAME, sizeof(vcap->driver)); strscpy(vcap->card, itv->card_name, sizeof(vcap->card)); - snprintf(vcap->bus_info, sizeof(vcap->bus_info), "PCI:%s", pci_name(itv->pdev)); vcap->capabilities = itv->v4l2_cap | V4L2_CAP_DEVICE_CAPS; return 0; } diff --git a/drivers/media/pci/meye/meye.c b/drivers/media/pci/meye/meye.c index 8944e4bd4638..5d87efd9b95c 100644 --- a/drivers/media/pci/meye/meye.c +++ b/drivers/media/pci/meye/meye.c @@ -1012,7 +1012,6 @@ static int vidioc_querycap(struct file *file, void *fh, { strscpy(cap->driver, "meye", sizeof(cap->driver)); strscpy(cap->card, "meye", sizeof(cap->card)); - sprintf(cap->bus_info, "PCI:%s", pci_name(meye.mchip_dev)); return 0; } diff --git a/drivers/media/pci/saa7134/saa7134-video.c b/drivers/media/pci/saa7134/saa7134-video.c index 48543ad3d595..4d8974c9fcc9 100644 --- a/drivers/media/pci/saa7134/saa7134-video.c +++ b/drivers/media/pci/saa7134/saa7134-video.c @@ -1475,7 +1475,6 @@ int saa7134_querycap(struct file *file, void *priv, strscpy(cap->driver, "saa7134", sizeof(cap->driver)); strscpy(cap->card, saa7134_boards[dev->board].name, sizeof(cap->card)); - sprintf(cap->bus_info, "PCI:%s", pci_name(dev->pci)); cap->capabilities = V4L2_CAP_READWRITE | V4L2_CAP_STREAMING | V4L2_CAP_RADIO | V4L2_CAP_VIDEO_CAPTURE | V4L2_CAP_VBI_CAPTURE | V4L2_CAP_DEVICE_CAPS; @@ -1833,8 +1832,7 @@ static int saa7134_overlay(struct file *file, void *priv, unsigned int on) spin_lock_irqsave(&dev->slock, flags); start_preview(dev); spin_unlock_irqrestore(&dev->slock, flags); - } - if (!on) { + } else { if (priv != dev->overlay_owner) return -EINVAL; spin_lock_irqsave(&dev->slock, flags); diff --git a/drivers/media/pci/saa7164/saa7164-encoder.c b/drivers/media/pci/saa7164/saa7164-encoder.c index 1d1d32e043f1..c1b6a0596801 100644 --- a/drivers/media/pci/saa7164/saa7164-encoder.c +++ b/drivers/media/pci/saa7164/saa7164-encoder.c @@ -490,7 +490,6 @@ static int vidioc_querycap(struct file *file, void *priv, strscpy(cap->driver, dev->name, sizeof(cap->driver)); strscpy(cap->card, saa7164_boards[dev->board].name, sizeof(cap->card)); - sprintf(cap->bus_info, "PCI:%s", pci_name(dev->pci)); cap->capabilities = V4L2_CAP_VIDEO_CAPTURE | V4L2_CAP_READWRITE | V4L2_CAP_TUNER | V4L2_CAP_VBI_CAPTURE | V4L2_CAP_DEVICE_CAPS; diff --git a/drivers/media/pci/saa7164/saa7164-vbi.c b/drivers/media/pci/saa7164/saa7164-vbi.c index cb2e09f0841d..a6738baab688 100644 --- a/drivers/media/pci/saa7164/saa7164-vbi.c +++ b/drivers/media/pci/saa7164/saa7164-vbi.c @@ -201,7 +201,6 @@ static int vidioc_querycap(struct file *file, void *priv, strscpy(cap->driver, dev->name, sizeof(cap->driver)); strscpy(cap->card, saa7164_boards[dev->board].name, sizeof(cap->card)); - sprintf(cap->bus_info, "PCI:%s", pci_name(dev->pci)); cap->capabilities = V4L2_CAP_VIDEO_CAPTURE | V4L2_CAP_READWRITE | V4L2_CAP_TUNER | V4L2_CAP_VBI_CAPTURE | V4L2_CAP_DEVICE_CAPS; diff --git a/drivers/media/pci/solo6x10/solo6x10-v4l2-enc.c b/drivers/media/pci/solo6x10/solo6x10-v4l2-enc.c index 7766cadb73ea..80d20e2a2099 100644 --- a/drivers/media/pci/solo6x10/solo6x10-v4l2-enc.c +++ b/drivers/media/pci/solo6x10/solo6x10-v4l2-enc.c @@ -764,13 +764,10 @@ static int solo_enc_querycap(struct file *file, void *priv, struct v4l2_capability *cap) { struct solo_enc_dev *solo_enc = video_drvdata(file); - struct solo_dev *solo_dev = solo_enc->solo_dev; strscpy(cap->driver, SOLO6X10_NAME, sizeof(cap->driver)); snprintf(cap->card, sizeof(cap->card), "Softlogic 6x10 Enc %d", solo_enc->ch); - snprintf(cap->bus_info, sizeof(cap->bus_info), "PCI:%s", - pci_name(solo_dev->pdev)); return 0; } diff --git a/drivers/media/pci/solo6x10/solo6x10-v4l2.c b/drivers/media/pci/solo6x10/solo6x10-v4l2.c index 24ef0c446bef..e18cc41fca83 100644 --- a/drivers/media/pci/solo6x10/solo6x10-v4l2.c +++ b/drivers/media/pci/solo6x10/solo6x10-v4l2.c @@ -372,12 +372,8 @@ static const struct vb2_ops solo_video_qops = { static int solo_querycap(struct file *file, void *priv, struct v4l2_capability *cap) { - struct solo_dev *solo_dev = video_drvdata(file); - strscpy(cap->driver, SOLO6X10_NAME, sizeof(cap->driver)); strscpy(cap->card, "Softlogic 6x10", sizeof(cap->card)); - snprintf(cap->bus_info, sizeof(cap->bus_info), "PCI:%s", - pci_name(solo_dev->pdev)); return 0; } diff --git a/drivers/media/pci/sta2x11/sta2x11_vip.c b/drivers/media/pci/sta2x11/sta2x11_vip.c index 524912f20d9f..8535e49a4c4f 100644 --- a/drivers/media/pci/sta2x11/sta2x11_vip.c +++ b/drivers/media/pci/sta2x11/sta2x11_vip.c @@ -401,12 +401,8 @@ static const struct v4l2_file_operations vip_fops = { static int vidioc_querycap(struct file *file, void *priv, struct v4l2_capability *cap) { - struct sta2x11_vip *vip = video_drvdata(file); - strscpy(cap->driver, KBUILD_MODNAME, sizeof(cap->driver)); strscpy(cap->card, KBUILD_MODNAME, sizeof(cap->card)); - snprintf(cap->bus_info, sizeof(cap->bus_info), "PCI:%s", - pci_name(vip->pdev)); return 0; } diff --git a/drivers/media/pci/tw5864/tw5864-video.c b/drivers/media/pci/tw5864/tw5864-video.c index 9131265c2b87..197ed8978102 100644 --- a/drivers/media/pci/tw5864/tw5864-video.c +++ b/drivers/media/pci/tw5864/tw5864-video.c @@ -604,7 +604,6 @@ static int tw5864_querycap(struct file *file, void *priv, strscpy(cap->driver, "tw5864", sizeof(cap->driver)); snprintf(cap->card, sizeof(cap->card), "TW5864 Encoder %d", input->nr); - sprintf(cap->bus_info, "PCI:%s", pci_name(input->root->pci)); return 0; } diff --git a/drivers/media/pci/tw68/tw68-video.c b/drivers/media/pci/tw68/tw68-video.c index fe94944d0531..0cbc5b038073 100644 --- a/drivers/media/pci/tw68/tw68-video.c +++ b/drivers/media/pci/tw68/tw68-video.c @@ -712,12 +712,9 @@ static int tw68_s_input(struct file *file, void *priv, unsigned int i) static int tw68_querycap(struct file *file, void *priv, struct v4l2_capability *cap) { - struct tw68_dev *dev = video_drvdata(file); - strscpy(cap->driver, "tw68", sizeof(cap->driver)); strscpy(cap->card, "Techwell Capture Card", sizeof(cap->card)); - sprintf(cap->bus_info, "PCI:%s", pci_name(dev->pci)); return 0; } diff --git a/drivers/media/pci/tw686x/tw686x-video.c b/drivers/media/pci/tw686x/tw686x-video.c index b227e9e78ebd..6344a479119f 100644 --- a/drivers/media/pci/tw686x/tw686x-video.c +++ b/drivers/media/pci/tw686x/tw686x-video.c @@ -762,8 +762,6 @@ static int tw686x_querycap(struct file *file, void *priv, strscpy(cap->driver, "tw686x", sizeof(cap->driver)); strscpy(cap->card, dev->name, sizeof(cap->card)); - snprintf(cap->bus_info, sizeof(cap->bus_info), - "PCI:%s", pci_name(dev->pci_dev)); return 0; } diff --git a/drivers/media/platform/allegro-dvt/allegro-core.c b/drivers/media/platform/allegro-dvt/allegro-core.c index 4a3d06c70e34..2423714afcb9 100644 --- a/drivers/media/platform/allegro-dvt/allegro-core.c +++ b/drivers/media/platform/allegro-dvt/allegro-core.c @@ -3249,13 +3249,8 @@ static int allegro_release(struct file *file) static int allegro_querycap(struct file *file, void *fh, struct v4l2_capability *cap) { - struct video_device *vdev = video_devdata(file); - struct allegro_dev *dev = video_get_drvdata(vdev); - strscpy(cap->driver, KBUILD_MODNAME, sizeof(cap->driver)); strscpy(cap->card, "Allegro DVT Video Encoder", sizeof(cap->card)); - snprintf(cap->bus_info, sizeof(cap->bus_info), "platform:%s", - dev_name(&dev->plat_dev->dev)); return 0; } diff --git a/drivers/media/platform/amphion/vdec.c b/drivers/media/platform/amphion/vdec.c index 8f8dfd6ce2c6..3c02aa2a54aa 100644 --- a/drivers/media/platform/amphion/vdec.c +++ b/drivers/media/platform/amphion/vdec.c @@ -26,8 +26,8 @@ #include "vpu_cmds.h" #include "vpu_rpc.h" -#define VDEC_FRAME_DEPTH 256 #define VDEC_MIN_BUFFER_CAP 8 +#define VDEC_MIN_BUFFER_OUT 8 struct vdec_fs_info { char name[8]; @@ -63,8 +63,6 @@ struct vdec_t { bool is_source_changed; u32 source_change; u32 drain; - u32 ts_pre_count; - u32 frame_depth; }; static const struct vpu_format vdec_formats[] = { @@ -164,6 +162,12 @@ static int vdec_ctrl_init(struct vpu_inst *inst) if (ctrl) ctrl->flags |= V4L2_CTRL_FLAG_VOLATILE; + if (inst->ctrl_handler.error) { + ret = inst->ctrl_handler.error; + v4l2_ctrl_handler_free(&inst->ctrl_handler); + return ret; + } + ret = v4l2_ctrl_handler_setup(&inst->ctrl_handler); if (ret) { dev_err(inst->dev, "[%d] setup ctrls fail, ret = %d\n", inst->id, ret); @@ -470,7 +474,7 @@ static int vdec_drain(struct vpu_inst *inst) if (!vdec->drain) return 0; - if (v4l2_m2m_num_src_bufs_ready(inst->fh.m2m_ctx)) + if (!vpu_is_source_empty(inst)) return 0; if (!vdec->params.frame_count) { @@ -589,11 +593,8 @@ static bool vdec_check_ready(struct vpu_inst *inst, unsigned int type) { struct vdec_t *vdec = inst->priv; - if (V4L2_TYPE_IS_OUTPUT(type)) { - if (vdec->ts_pre_count >= vdec->frame_depth) - return false; + if (V4L2_TYPE_IS_OUTPUT(type)) return true; - } if (vdec->req_frame_count) return true; @@ -601,12 +602,21 @@ static bool vdec_check_ready(struct vpu_inst *inst, unsigned int type) return false; } +static struct vb2_v4l2_buffer *vdec_get_src_buffer(struct vpu_inst *inst, u32 count) +{ + if (count > 1) + vpu_skip_frame(inst, count - 1); + + return vpu_next_src_buf(inst); +} + static int vdec_frame_decoded(struct vpu_inst *inst, void *arg) { struct vdec_t *vdec = inst->priv; struct vpu_dec_pic_info *info = arg; struct vpu_vb2_buffer *vpu_buf; struct vb2_v4l2_buffer *vbuf; + struct vb2_v4l2_buffer *src_buf; int ret = 0; if (!info || info->id >= ARRAY_SIZE(vdec->slots)) @@ -620,14 +630,21 @@ static int vdec_frame_decoded(struct vpu_inst *inst, void *arg) goto exit; } vbuf = &vpu_buf->m2m_buf.vb; + src_buf = vdec_get_src_buffer(inst, info->consumed_count); + if (src_buf) { + v4l2_m2m_buf_copy_metadata(src_buf, vbuf, true); + if (info->consumed_count) { + v4l2_m2m_src_buf_remove(inst->fh.m2m_ctx); + vpu_set_buffer_state(src_buf, VPU_BUF_STATE_IDLE); + v4l2_m2m_buf_done(src_buf, VB2_BUF_STATE_DONE); + } else { + vpu_set_buffer_state(src_buf, VPU_BUF_STATE_DECODED); + } + } if (vpu_get_buffer_state(vbuf) == VPU_BUF_STATE_DECODED) dev_info(inst->dev, "[%d] buf[%d] has been decoded\n", inst->id, info->id); vpu_set_buffer_state(vbuf, VPU_BUF_STATE_DECODED); vdec->decoded_frame_count++; - if (vdec->ts_pre_count >= info->consumed_count) - vdec->ts_pre_count -= info->consumed_count; - else - vdec->ts_pre_count = 0; exit: vpu_inst_unlock(inst); @@ -683,10 +700,9 @@ static void vdec_buf_done(struct vpu_inst *inst, struct vpu_frame_info *frame) vpu_set_buffer_state(vbuf, VPU_BUF_STATE_READY); vb2_set_plane_payload(&vbuf->vb2_buf, 0, inst->cap_format.sizeimage[0]); vb2_set_plane_payload(&vbuf->vb2_buf, 1, inst->cap_format.sizeimage[1]); - vbuf->vb2_buf.timestamp = frame->timestamp; vbuf->field = inst->cap_format.field; vbuf->sequence = sequence; - dev_dbg(inst->dev, "[%d][OUTPUT TS]%32lld\n", inst->id, frame->timestamp); + dev_dbg(inst->dev, "[%d][OUTPUT TS]%32lld\n", inst->id, vbuf->vb2_buf.timestamp); v4l2_m2m_buf_done(vbuf, VB2_BUF_STATE_DONE); vpu_inst_lock(inst); @@ -708,7 +724,6 @@ static void vdec_stop_done(struct vpu_inst *inst) vdec->fixed_fmt = false; vdec->params.end_flag = 0; vdec->drain = 0; - vdec->ts_pre_count = 0; vdec->params.frame_count = 0; vdec->decoded_frame_count = 0; vdec->display_frame_count = 0; @@ -782,7 +797,7 @@ static void vdec_init_fmt(struct vpu_inst *inst) if (vdec->codec_info.progressive) inst->cap_format.field = V4L2_FIELD_NONE; else - inst->cap_format.field = V4L2_FIELD_SEQ_BT; + inst->cap_format.field = V4L2_FIELD_SEQ_TB; if (vdec->codec_info.color_primaries == V4L2_COLORSPACE_DEFAULT) vdec->codec_info.color_primaries = V4L2_COLORSPACE_REC709; if (vdec->codec_info.transfer_chars == V4L2_XFER_FUNC_DEFAULT) @@ -1244,18 +1259,14 @@ static int vdec_process_output(struct vpu_inst *inst, struct vb2_buffer *vb) if (free_space < vb2_get_plane_payload(vb, 0) + 0x40000) return -ENOMEM; + vpu_set_buffer_state(vbuf, VPU_BUF_STATE_INUSE); ret = vpu_iface_input_frame(inst, vb); if (ret < 0) return -ENOMEM; dev_dbg(inst->dev, "[%d][INPUT TS]%32lld\n", inst->id, vb->timestamp); - vdec->ts_pre_count++; vdec->params.frame_count++; - v4l2_m2m_src_buf_remove_by_buf(inst->fh.m2m_ctx, vbuf); - vpu_set_buffer_state(vbuf, VPU_BUF_STATE_IDLE); - v4l2_m2m_buf_done(vbuf, VB2_BUF_STATE_DONE); - if (vdec->drain) vdec_drain(inst); @@ -1318,7 +1329,6 @@ static void vdec_abort(struct vpu_inst *inst) vdec->sequence); vdec->params.end_flag = 0; vdec->drain = 0; - vdec->ts_pre_count = 0; vdec->params.frame_count = 0; vdec->decoded_frame_count = 0; vdec->display_frame_count = 0; @@ -1525,10 +1535,6 @@ static int vdec_get_debug_info(struct vpu_inst *inst, char *str, u32 size, u32 i vdec->drain, vdec->eos_received, vdec->source_change); break; case 8: - num = scnprintf(str, size, "ts_pre_count = %d, frame_depth = %d\n", - vdec->ts_pre_count, vdec->frame_depth); - break; - case 9: num = scnprintf(str, size, "fps = %d/%d\n", vdec->codec_info.frame_rate.numerator, vdec->codec_info.frame_rate.denominator); @@ -1562,12 +1568,8 @@ static struct vpu_inst_ops vdec_inst_ops = { static void vdec_init(struct file *file) { struct vpu_inst *inst = to_inst(file); - struct vdec_t *vdec; struct v4l2_format f; - vdec = inst->priv; - vdec->frame_depth = VDEC_FRAME_DEPTH; - memset(&f, 0, sizeof(f)); f.type = V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE; f.fmt.pix_mp.pixelformat = V4L2_PIX_FMT_H264; @@ -1612,36 +1614,18 @@ static int vdec_open(struct file *file) vdec->fixed_fmt = false; inst->min_buffer_cap = VDEC_MIN_BUFFER_CAP; + inst->min_buffer_out = VDEC_MIN_BUFFER_OUT; vdec_init(file); return 0; } -static __poll_t vdec_poll(struct file *file, poll_table *wait) -{ - struct vpu_inst *inst = to_inst(file); - struct vb2_queue *src_q, *dst_q; - __poll_t ret; - - ret = v4l2_m2m_fop_poll(file, wait); - src_q = v4l2_m2m_get_src_vq(inst->fh.m2m_ctx); - dst_q = v4l2_m2m_get_dst_vq(inst->fh.m2m_ctx); - if (vb2_is_streaming(src_q) && !vb2_is_streaming(dst_q)) - ret &= (~EPOLLERR); - if (!src_q->error && !dst_q->error && - (vb2_is_streaming(src_q) && list_empty(&src_q->queued_list)) && - (vb2_is_streaming(dst_q) && list_empty(&dst_q->queued_list))) - ret &= (~EPOLLERR); - - return ret; -} - static const struct v4l2_file_operations vdec_fops = { .owner = THIS_MODULE, .open = vdec_open, .release = vpu_v4l2_close, .unlocked_ioctl = video_ioctl2, - .poll = vdec_poll, + .poll = v4l2_m2m_fop_poll, .mmap = v4l2_m2m_fop_mmap, }; diff --git a/drivers/media/platform/amphion/venc.c b/drivers/media/platform/amphion/venc.c index d33c2748e4b7..43d61d82f58c 100644 --- a/drivers/media/platform/amphion/venc.c +++ b/drivers/media/platform/amphion/venc.c @@ -33,6 +33,8 @@ #define VENC_CAPTURE_ENABLE BIT(1) #define VENC_ENABLE_MASK (VENC_OUTPUT_ENABLE | VENC_CAPTURE_ENABLE) #define VENC_MAX_BUF_CNT 8 +#define VENC_MIN_BUFFER_OUT 6 +#define VENC_MIN_BUFFER_CAP 6 struct venc_t { struct vpu_encode_params params; @@ -281,6 +283,9 @@ static int venc_g_parm(struct file *file, void *fh, struct v4l2_streamparm *parm if (!parm) return -EINVAL; + if (!V4L2_TYPE_IS_OUTPUT(parm->type)) + return -EINVAL; + if (!vpu_helper_check_type(inst, parm->type)) return -EINVAL; @@ -302,6 +307,9 @@ static int venc_s_parm(struct file *file, void *fh, struct v4l2_streamparm *parm if (!parm) return -EINVAL; + if (!V4L2_TYPE_IS_OUTPUT(parm->type)) + return -EINVAL; + if (!vpu_helper_check_type(inst, parm->type)) return -EINVAL; @@ -423,7 +431,7 @@ static int venc_drain(struct vpu_inst *inst) if (inst->state != VPU_CODEC_STATE_DRAIN) return 0; - if (v4l2_m2m_num_src_bufs_ready(inst->fh.m2m_ctx)) + if (!vpu_is_source_empty(inst)) return 0; if (!venc->input_ready) @@ -680,6 +688,12 @@ static int venc_ctrl_init(struct vpu_inst *inst) ~(1 << V4L2_MPEG_VIDEO_HEADER_MODE_JOINED_WITH_1ST_FRAME), V4L2_MPEG_VIDEO_HEADER_MODE_JOINED_WITH_1ST_FRAME); + if (inst->ctrl_handler.error) { + ret = inst->ctrl_handler.error; + v4l2_ctrl_handler_free(&inst->ctrl_handler); + return ret; + } + ret = v4l2_ctrl_handler_setup(&inst->ctrl_handler); if (ret) { dev_err(inst->dev, "[%d] setup ctrls fail, ret = %d\n", inst->id, ret); @@ -775,10 +789,20 @@ static int venc_get_one_encoded_frame(struct vpu_inst *inst, struct vb2_v4l2_buffer *vbuf) { struct venc_t *venc = inst->priv; + struct vb2_v4l2_buffer *src_buf; if (!vbuf) return -EAGAIN; + src_buf = vpu_find_buf_by_sequence(inst, inst->out_format.type, frame->info.frame_id); + if (src_buf) { + v4l2_m2m_buf_copy_metadata(src_buf, vbuf, true); + vpu_set_buffer_state(src_buf, VPU_BUF_STATE_IDLE); + v4l2_m2m_src_buf_remove_by_buf(inst->fh.m2m_ctx, src_buf); + v4l2_m2m_buf_done(src_buf, VB2_BUF_STATE_DONE); + } else { + vbuf->vb2_buf.timestamp = frame->info.timestamp; + } if (!venc_get_enable(inst->priv, vbuf->vb2_buf.type)) { v4l2_m2m_buf_done(vbuf, VB2_BUF_STATE_ERROR); return 0; @@ -800,11 +824,10 @@ static int venc_get_one_encoded_frame(struct vpu_inst *inst, } vb2_set_plane_payload(&vbuf->vb2_buf, 0, frame->bytesused); vbuf->sequence = frame->info.frame_id; - vbuf->vb2_buf.timestamp = frame->info.timestamp; vbuf->field = inst->cap_format.field; vbuf->flags |= frame->info.pic_type; vpu_set_buffer_state(vbuf, VPU_BUF_STATE_IDLE); - dev_dbg(inst->dev, "[%d][OUTPUT TS]%32lld\n", inst->id, frame->info.timestamp); + dev_dbg(inst->dev, "[%d][OUTPUT TS]%32lld\n", inst->id, vbuf->vb2_buf.timestamp); v4l2_m2m_buf_done(vbuf, VB2_BUF_STATE_DONE); venc->ready_count++; @@ -860,33 +883,6 @@ static int venc_frame_encoded(struct vpu_inst *inst, void *arg) return ret; } -static void venc_buf_done(struct vpu_inst *inst, struct vpu_frame_info *frame) -{ - struct vb2_v4l2_buffer *vbuf; - - if (!inst->fh.m2m_ctx) - return; - - vpu_inst_lock(inst); - if (!venc_get_enable(inst->priv, frame->type)) - goto exit; - vbuf = vpu_find_buf_by_sequence(inst, frame->type, frame->sequence); - if (!vbuf) { - dev_err(inst->dev, "[%d] can't find buf: type %d, sequence %d\n", - inst->id, frame->type, frame->sequence); - goto exit; - } - - vpu_set_buffer_state(vbuf, VPU_BUF_STATE_IDLE); - if (V4L2_TYPE_IS_OUTPUT(frame->type)) - v4l2_m2m_src_buf_remove_by_buf(inst->fh.m2m_ctx, vbuf); - else - v4l2_m2m_dst_buf_remove_by_buf(inst->fh.m2m_ctx, vbuf); - v4l2_m2m_buf_done(vbuf, VB2_BUF_STATE_DONE); -exit: - vpu_inst_unlock(inst); -} - static void venc_set_last_buffer_dequeued(struct vpu_inst *inst) { struct venc_t *venc = inst->priv; @@ -1252,7 +1248,6 @@ static struct vpu_inst_ops venc_inst_ops = { .check_ready = venc_check_ready, .input_done = venc_input_done, .get_one_frame = venc_frame_encoded, - .buf_done = venc_buf_done, .stop_done = venc_stop_done, .event_notify = venc_event_notify, .release = venc_release, @@ -1333,6 +1328,8 @@ static int venc_open(struct file *file) if (ret) return ret; + inst->min_buffer_out = VENC_MIN_BUFFER_OUT; + inst->min_buffer_cap = VENC_MIN_BUFFER_CAP; venc_init(file); return 0; diff --git a/drivers/media/platform/amphion/vpu_dbg.c b/drivers/media/platform/amphion/vpu_dbg.c index 376196bea178..da62bd718fb8 100644 --- a/drivers/media/platform/amphion/vpu_dbg.c +++ b/drivers/media/platform/amphion/vpu_dbg.c @@ -413,10 +413,6 @@ int vpu_inst_create_dbgfs_file(struct vpu_inst *inst) vpu->debugfs, inst, &vpu_dbg_inst_fops); - if (!inst->debugfs) { - dev_err(inst->dev, "vpu create debugfs %s fail\n", name); - return -EINVAL; - } return 0; } @@ -451,10 +447,6 @@ int vpu_core_create_dbgfs_file(struct vpu_core *core) vpu->debugfs, core, &vpu_dbg_core_fops); - if (!core->debugfs) { - dev_err(core->dev, "vpu create debugfs %s fail\n", name); - return -EINVAL; - } } if (!core->debugfs_fwlog) { scnprintf(name, sizeof(name), "fwlog.%d", core->id); @@ -463,10 +455,6 @@ int vpu_core_create_dbgfs_file(struct vpu_core *core) vpu->debugfs, core, &vpu_dbg_fwlog_fops); - if (!core->debugfs_fwlog) { - dev_err(core->dev, "vpu create debugfs %s fail\n", name); - return -EINVAL; - } } return 0; diff --git a/drivers/media/platform/amphion/vpu_defs.h b/drivers/media/platform/amphion/vpu_defs.h index 282664202dcf..667637eedb5d 100644 --- a/drivers/media/platform/amphion/vpu_defs.h +++ b/drivers/media/platform/amphion/vpu_defs.h @@ -69,8 +69,8 @@ enum { VPU_MSG_ID_BS_ERROR, VPU_MSG_ID_UNSUPPORTED, VPU_MSG_ID_TIMESTAMP_INFO, - VPU_MSG_ID_FIRMWARE_XCPT, + VPU_MSG_ID_PIC_SKIPPED, }; enum VPU_ENC_MEMORY_RESOURSE { diff --git a/drivers/media/platform/amphion/vpu_malone.c b/drivers/media/platform/amphion/vpu_malone.c index 446a9de0cc11..f29c223eefce 100644 --- a/drivers/media/platform/amphion/vpu_malone.c +++ b/drivers/media/platform/amphion/vpu_malone.c @@ -170,6 +170,7 @@ enum { VID_API_EVENT_DEC_CHECK_RES = 0x24, VID_API_EVENT_DEC_CFG_INFO = 0x25, VID_API_EVENT_UNSUPPORTED_STREAM = 0x26, + VID_API_EVENT_PIC_SKIPPED = 0x27, VID_API_EVENT_STR_SUSPENDED = 0x30, VID_API_EVENT_SNAPSHOT_DONE = 0x40, VID_API_EVENT_FW_STATUS = 0xF0, @@ -703,6 +704,7 @@ static struct vpu_pair malone_msgs[] = { {VPU_MSG_ID_BS_ERROR, VID_API_EVENT_BS_ERROR}, {VPU_MSG_ID_UNSUPPORTED, VID_API_EVENT_UNSUPPORTED_STREAM}, {VPU_MSG_ID_FIRMWARE_XCPT, VID_API_EVENT_FIRMWARE_XCPT}, + {VPU_MSG_ID_PIC_SKIPPED, VID_API_EVENT_PIC_SKIPPED}, }; static void vpu_malone_pack_fs_alloc(struct vpu_rpc_event *pkt, @@ -1556,7 +1558,7 @@ int vpu_malone_input_frame(struct vpu_shared_addr *shared, * merge the data to next frame */ vbuf = to_vb2_v4l2_buffer(vb); - if (vpu_vb_is_codecconfig(vbuf) && (s64)vb->timestamp < 0) { + if (vpu_vb_is_codecconfig(vbuf)) { inst->extra_size += size; return 0; } diff --git a/drivers/media/platform/amphion/vpu_msgs.c b/drivers/media/platform/amphion/vpu_msgs.c index 58502c51ddb3..d5850df8f1d5 100644 --- a/drivers/media/platform/amphion/vpu_msgs.c +++ b/drivers/media/platform/amphion/vpu_msgs.c @@ -166,6 +166,13 @@ static void vpu_session_handle_firmware_xcpt(struct vpu_inst *inst, struct vpu_r vpu_v4l2_set_error(inst); } +static void vpu_session_handle_pic_skipped(struct vpu_inst *inst, struct vpu_rpc_event *pkt) +{ + vpu_inst_lock(inst); + vpu_skip_frame(inst, 1); + vpu_inst_unlock(inst); +} + static struct vpu_msg_handler handlers[] = { {VPU_MSG_ID_START_DONE, vpu_session_handle_start_done}, {VPU_MSG_ID_STOP_DONE, vpu_session_handle_stop_done}, @@ -181,6 +188,7 @@ static struct vpu_msg_handler handlers[] = { {VPU_MSG_ID_PIC_EOS, vpu_session_handle_eos}, {VPU_MSG_ID_UNSUPPORTED, vpu_session_handle_error}, {VPU_MSG_ID_FIRMWARE_XCPT, vpu_session_handle_firmware_xcpt}, + {VPU_MSG_ID_PIC_SKIPPED, vpu_session_handle_pic_skipped}, }; static int vpu_session_handle_msg(struct vpu_inst *inst, struct vpu_rpc_event *msg) diff --git a/drivers/media/platform/amphion/vpu_v4l2.c b/drivers/media/platform/amphion/vpu_v4l2.c index 9c0704cd5766..446f07d09d0b 100644 --- a/drivers/media/platform/amphion/vpu_v4l2.c +++ b/drivers/media/platform/amphion/vpu_v4l2.c @@ -73,10 +73,10 @@ void vpu_v4l2_set_error(struct vpu_inst *inst) if (inst->fh.m2m_ctx) { src_q = v4l2_m2m_get_src_vq(inst->fh.m2m_ctx); dst_q = v4l2_m2m_get_dst_vq(inst->fh.m2m_ctx); - if (src_q) - src_q->error = 1; - if (dst_q) - dst_q->error = 1; + src_q->error = 1; + dst_q->error = 1; + wake_up(&src_q->done_wq); + wake_up(&dst_q->done_wq); } vpu_inst_unlock(inst); } @@ -127,6 +127,19 @@ int vpu_set_last_buffer_dequeued(struct vpu_inst *inst) return 0; } +bool vpu_is_source_empty(struct vpu_inst *inst) +{ + struct v4l2_m2m_buffer *buf = NULL; + + if (!inst->fh.m2m_ctx) + return true; + v4l2_m2m_for_each_src_buf(inst->fh.m2m_ctx, buf) { + if (vpu_get_buffer_state(&buf->vb) == VPU_BUF_STATE_IDLE) + return false; + } + return true; +} + const struct vpu_format *vpu_try_fmt_common(struct vpu_inst *inst, struct v4l2_format *f) { struct v4l2_pix_format_mplane *pixmp = &f->fmt.pix_mp; @@ -234,6 +247,49 @@ int vpu_process_capture_buffer(struct vpu_inst *inst) return call_vop(inst, process_capture, &vbuf->vb2_buf); } +struct vb2_v4l2_buffer *vpu_next_src_buf(struct vpu_inst *inst) +{ + struct vb2_v4l2_buffer *src_buf = v4l2_m2m_next_src_buf(inst->fh.m2m_ctx); + + if (!src_buf || vpu_get_buffer_state(src_buf) == VPU_BUF_STATE_IDLE) + return NULL; + + while (vpu_vb_is_codecconfig(src_buf)) { + v4l2_m2m_src_buf_remove(inst->fh.m2m_ctx); + vpu_set_buffer_state(src_buf, VPU_BUF_STATE_IDLE); + v4l2_m2m_buf_done(src_buf, VB2_BUF_STATE_DONE); + + src_buf = v4l2_m2m_next_src_buf(inst->fh.m2m_ctx); + if (!src_buf || vpu_get_buffer_state(src_buf) == VPU_BUF_STATE_IDLE) + return NULL; + } + + return src_buf; +} + +void vpu_skip_frame(struct vpu_inst *inst, int count) +{ + struct vb2_v4l2_buffer *src_buf; + enum vb2_buffer_state state; + int i = 0; + + if (count <= 0) + return; + + while (i < count) { + src_buf = v4l2_m2m_src_buf_remove(inst->fh.m2m_ctx); + if (!src_buf || vpu_get_buffer_state(src_buf) == VPU_BUF_STATE_IDLE) + return; + if (vpu_get_buffer_state(src_buf) == VPU_BUF_STATE_DECODED) + state = VB2_BUF_STATE_DONE; + else + state = VB2_BUF_STATE_ERROR; + i++; + vpu_set_buffer_state(src_buf, VPU_BUF_STATE_IDLE); + v4l2_m2m_buf_done(src_buf, state); + } +} + struct vb2_v4l2_buffer *vpu_find_buf_by_sequence(struct vpu_inst *inst, u32 type, u32 sequence) { struct v4l2_m2m_buffer *buf = NULL; @@ -342,6 +398,10 @@ static int vpu_vb2_queue_setup(struct vb2_queue *vq, return 0; } + if (V4L2_TYPE_IS_OUTPUT(vq->type)) + *buf_count = max_t(unsigned int, *buf_count, inst->min_buffer_out); + else + *buf_count = max_t(unsigned int, *buf_count, inst->min_buffer_cap); *plane_count = cur_fmt->num_planes; for (i = 0; i < cur_fmt->num_planes; i++) psize[i] = cur_fmt->sizeimage[i]; diff --git a/drivers/media/platform/amphion/vpu_v4l2.h b/drivers/media/platform/amphion/vpu_v4l2.h index 90fa7ea67495..795ca33a6a50 100644 --- a/drivers/media/platform/amphion/vpu_v4l2.h +++ b/drivers/media/platform/amphion/vpu_v4l2.h @@ -19,6 +19,8 @@ int vpu_v4l2_close(struct file *file); const struct vpu_format *vpu_try_fmt_common(struct vpu_inst *inst, struct v4l2_format *f); int vpu_process_output_buffer(struct vpu_inst *inst); int vpu_process_capture_buffer(struct vpu_inst *inst); +struct vb2_v4l2_buffer *vpu_next_src_buf(struct vpu_inst *inst); +void vpu_skip_frame(struct vpu_inst *inst, int count); struct vb2_v4l2_buffer *vpu_find_buf_by_sequence(struct vpu_inst *inst, u32 type, u32 sequence); struct vb2_v4l2_buffer *vpu_find_buf_by_idx(struct vpu_inst *inst, u32 type, u32 idx); void vpu_v4l2_set_error(struct vpu_inst *inst); @@ -27,6 +29,7 @@ int vpu_notify_source_change(struct vpu_inst *inst); int vpu_set_last_buffer_dequeued(struct vpu_inst *inst); void vpu_vb2_buffers_return(struct vpu_inst *inst, unsigned int type, enum vb2_buffer_state state); int vpu_get_num_buffers(struct vpu_inst *inst, u32 type); +bool vpu_is_source_empty(struct vpu_inst *inst); dma_addr_t vpu_get_vb_phy_addr(struct vb2_buffer *vb, u32 plane_no); unsigned int vpu_get_vb_length(struct vb2_buffer *vb, u32 plane_no); diff --git a/drivers/media/platform/aspeed/aspeed-video.c b/drivers/media/platform/aspeed/aspeed-video.c index b937dbcbe9e0..20f795ccc11b 100644 --- a/drivers/media/platform/aspeed/aspeed-video.c +++ b/drivers/media/platform/aspeed/aspeed-video.c @@ -1993,6 +1993,7 @@ static int aspeed_video_probe(struct platform_device *pdev) rc = aspeed_video_setup_video(video); if (rc) { + aspeed_video_free_buf(video, &video->jpeg); clk_unprepare(video->vclk); clk_unprepare(video->eclk); return rc; @@ -2024,8 +2025,7 @@ static int aspeed_video_remove(struct platform_device *pdev) v4l2_device_unregister(v4l2_dev); - dma_free_coherent(video->dev, VE_JPEG_HEADER_SIZE, video->jpeg.virt, - video->jpeg.dma); + aspeed_video_free_buf(video, &video->jpeg); of_reserved_mem_device_release(dev); diff --git a/drivers/media/platform/atmel/atmel-isc-base.c b/drivers/media/platform/atmel/atmel-isc-base.c index db15770d5b88..2f07a50035c8 100644 --- a/drivers/media/platform/atmel/atmel-isc-base.c +++ b/drivers/media/platform/atmel/atmel-isc-base.c @@ -401,6 +401,7 @@ static void isc_stop_streaming(struct vb2_queue *vq) struct isc_buffer *buf; int ret; + mutex_lock(&isc->awb_mutex); v4l2_ctrl_activate(isc->do_wb_ctrl, false); isc->stop = true; @@ -410,6 +411,8 @@ static void isc_stop_streaming(struct vb2_queue *vq) v4l2_err(&isc->v4l2_dev, "Timeout waiting for end of the capture\n"); + mutex_unlock(&isc->awb_mutex); + /* Disable DMA interrupt */ regmap_write(isc->regmap, ISC_INTDIS, ISC_INT_DDONE); @@ -442,7 +445,7 @@ static void isc_buffer_queue(struct vb2_buffer *vb) spin_lock_irqsave(&isc->dma_queue_lock, flags); if (!isc->cur_frm && list_empty(&isc->dma_queue) && - vb2_is_streaming(vb->vb2_queue)) { + vb2_start_streaming_called(vb->vb2_queue)) { isc->cur_frm = buf; isc_start_dma(isc); } else @@ -1029,7 +1032,7 @@ static int isc_s_fmt_vid_cap(struct file *file, void *priv, { struct isc_device *isc = video_drvdata(file); - if (vb2_is_streaming(&isc->vb2_vidq)) + if (vb2_is_busy(&isc->vb2_vidq)) return -EBUSY; return isc_set_fmt(isc, f); @@ -1397,10 +1400,6 @@ static void isc_awb_work(struct work_struct *w) u32 min, max; int ret; - /* streaming is not active anymore */ - if (isc->stop) - return; - if (ctrls->hist_stat != HIST_ENABLED) return; @@ -1455,7 +1454,24 @@ static void isc_awb_work(struct work_struct *w) } regmap_write(regmap, ISC_HIS_CFG + isc->offsets.his, hist_id | baysel | ISC_HIS_CFG_RAR); + + /* + * We have to make sure the streaming has not stopped meanwhile. + * ISC requires a frame to clock the internal profile update. + * To avoid issues, lock the sequence with a mutex + */ + mutex_lock(&isc->awb_mutex); + + /* streaming is not active anymore */ + if (isc->stop) { + mutex_unlock(&isc->awb_mutex); + return; + }; + isc_update_profile(isc); + + mutex_unlock(&isc->awb_mutex); + /* if awb has been disabled, we don't need to start another histogram */ if (ctrls->awb) regmap_write(regmap, ISC_CTRLEN, ISC_CTRL_HISREQ); @@ -1534,6 +1550,7 @@ static int isc_s_awb_ctrl(struct v4l2_ctrl *ctrl) isc_update_awb_ctrls(isc); + mutex_lock(&isc->awb_mutex); if (vb2_is_streaming(&isc->vb2_vidq)) { /* * If we are streaming, we can update profile to @@ -1548,6 +1565,7 @@ static int isc_s_awb_ctrl(struct v4l2_ctrl *ctrl) */ v4l2_ctrl_activate(isc->do_wb_ctrl, false); } + mutex_unlock(&isc->awb_mutex); /* if we have autowhitebalance on, start histogram procedure */ if (ctrls->awb == ISC_WB_AUTO && @@ -1729,6 +1747,7 @@ static void isc_async_unbind(struct v4l2_async_notifier *notifier, { struct isc_device *isc = container_of(notifier->v4l2_dev, struct isc_device, v4l2_dev); + mutex_destroy(&isc->awb_mutex); cancel_work_sync(&isc->awb_work); video_unregister_device(&isc->video_dev); v4l2_ctrl_handler_free(&isc->ctrls.handler); @@ -1838,6 +1857,8 @@ static int isc_async_complete(struct v4l2_async_notifier *notifier) isc->current_subdev = container_of(notifier, struct isc_subdev_entity, notifier); mutex_init(&isc->lock); + mutex_init(&isc->awb_mutex); + init_completion(&isc->comp); /* Initialize videobuf2 queue */ @@ -1906,6 +1927,7 @@ static int isc_async_complete(struct v4l2_async_notifier *notifier) return 0; isc_async_complete_err: + mutex_destroy(&isc->awb_mutex); mutex_destroy(&isc->lock); return ret; } diff --git a/drivers/media/platform/atmel/atmel-isc.h b/drivers/media/platform/atmel/atmel-isc.h index 07fa6dbf8460..ff60ba020cb9 100644 --- a/drivers/media/platform/atmel/atmel-isc.h +++ b/drivers/media/platform/atmel/atmel-isc.h @@ -218,6 +218,7 @@ struct isc_reg_offsets { * * @lock: lock for serializing userspace file operations * with ISC operations + * @awb_mutex: serialize access to streaming status from awb work queue * @awb_lock: lock for serializing awb work queue operations * with DMA/buffer operations * @@ -272,7 +273,7 @@ struct isc_device { struct video_device video_dev; struct vb2_queue vb2_vidq; - spinlock_t dma_queue_lock; /* serialize access to dma queue */ + spinlock_t dma_queue_lock; struct list_head dma_queue; struct isc_buffer *cur_frm; unsigned int sequence; @@ -289,8 +290,9 @@ struct isc_device { struct isc_ctrls ctrls; struct work_struct awb_work; - struct mutex lock; /* serialize access to file operations */ - spinlock_t awb_lock; /* serialize access to DMA buffers from awb work queue */ + struct mutex lock; + struct mutex awb_mutex; + spinlock_t awb_lock; struct regmap_field *pipeline[ISC_PIPE_LINE_NODE_NUM]; diff --git a/drivers/media/platform/atmel/atmel-sama5d2-isc.c b/drivers/media/platform/atmel/atmel-sama5d2-isc.c index c5b9563e36cb..9881d89a645b 100644 --- a/drivers/media/platform/atmel/atmel-sama5d2-isc.c +++ b/drivers/media/platform/atmel/atmel-sama5d2-isc.c @@ -60,56 +60,39 @@ static const struct isc_format sama5d2_controller_formats[] = { { .fourcc = V4L2_PIX_FMT_ARGB444, - }, - { + }, { .fourcc = V4L2_PIX_FMT_ARGB555, - }, - { + }, { .fourcc = V4L2_PIX_FMT_RGB565, - }, - { + }, { .fourcc = V4L2_PIX_FMT_ABGR32, - }, - { + }, { .fourcc = V4L2_PIX_FMT_XBGR32, - }, - { + }, { .fourcc = V4L2_PIX_FMT_YUV420, - }, - { + }, { .fourcc = V4L2_PIX_FMT_YUYV, - }, - { + }, { .fourcc = V4L2_PIX_FMT_YUV422P, - }, - { + }, { .fourcc = V4L2_PIX_FMT_GREY, - }, - { + }, { .fourcc = V4L2_PIX_FMT_Y10, - }, - { + }, { .fourcc = V4L2_PIX_FMT_SBGGR8, - }, - { + }, { .fourcc = V4L2_PIX_FMT_SGBRG8, - }, - { + }, { .fourcc = V4L2_PIX_FMT_SGRBG8, - }, - { + }, { .fourcc = V4L2_PIX_FMT_SRGGB8, - }, - { + }, { .fourcc = V4L2_PIX_FMT_SBGGR10, - }, - { + }, { .fourcc = V4L2_PIX_FMT_SGBRG10, - }, - { + }, { .fourcc = V4L2_PIX_FMT_SGRBG10, - }, - { + }, { .fourcc = V4L2_PIX_FMT_SRGGB10, }, }; @@ -291,7 +274,7 @@ static void isc_sama5d2_config_rlp(struct isc_device *isc) * Thus, if the YCYC mode is selected, replace it with the * sama5d2-compliant mode which is YYCC . */ - if ((rlp_mode & ISC_RLP_CFG_MODE_YCYC) == ISC_RLP_CFG_MODE_YCYC) { + if ((rlp_mode & ISC_RLP_CFG_MODE_MASK) == ISC_RLP_CFG_MODE_YCYC) { rlp_mode &= ~ISC_RLP_CFG_MODE_MASK; rlp_mode |= ISC_RLP_CFG_MODE_YYCC; } @@ -562,7 +545,7 @@ static int atmel_isc_probe(struct platform_device *pdev) ret = clk_prepare_enable(isc->ispck); if (ret) { dev_err(dev, "failed to enable ispck: %d\n", ret); - goto cleanup_subdev; + goto disable_pm; } /* ispck should be greater or equal to hclock */ @@ -580,6 +563,9 @@ static int atmel_isc_probe(struct platform_device *pdev) unprepare_clk: clk_disable_unprepare(isc->ispck); +disable_pm: + pm_runtime_disable(dev); + cleanup_subdev: isc_subdev_cleanup(isc); diff --git a/drivers/media/platform/atmel/atmel-sama7g5-isc.c b/drivers/media/platform/atmel/atmel-sama7g5-isc.c index 07a80b08bc54..83b175070c06 100644 --- a/drivers/media/platform/atmel/atmel-sama7g5-isc.c +++ b/drivers/media/platform/atmel/atmel-sama7g5-isc.c @@ -63,65 +63,45 @@ static const struct isc_format sama7g5_controller_formats[] = { { .fourcc = V4L2_PIX_FMT_ARGB444, - }, - { + }, { .fourcc = V4L2_PIX_FMT_ARGB555, - }, - { + }, { .fourcc = V4L2_PIX_FMT_RGB565, - }, - { + }, { .fourcc = V4L2_PIX_FMT_ABGR32, - }, - { + }, { .fourcc = V4L2_PIX_FMT_XBGR32, - }, - { + }, { .fourcc = V4L2_PIX_FMT_YUV420, - }, - { + }, { .fourcc = V4L2_PIX_FMT_UYVY, - }, - { + }, { .fourcc = V4L2_PIX_FMT_VYUY, - }, - { + }, { .fourcc = V4L2_PIX_FMT_YUYV, - }, - { + }, { .fourcc = V4L2_PIX_FMT_YUV422P, - }, - { + }, { .fourcc = V4L2_PIX_FMT_GREY, - }, - { + }, { .fourcc = V4L2_PIX_FMT_Y10, - }, - { + }, { .fourcc = V4L2_PIX_FMT_Y16, - }, - { + }, { .fourcc = V4L2_PIX_FMT_SBGGR8, - }, - { + }, { .fourcc = V4L2_PIX_FMT_SGBRG8, - }, - { + }, { .fourcc = V4L2_PIX_FMT_SGRBG8, - }, - { + }, { .fourcc = V4L2_PIX_FMT_SRGGB8, - }, - { + }, { .fourcc = V4L2_PIX_FMT_SBGGR10, - }, - { + }, { .fourcc = V4L2_PIX_FMT_SGBRG10, - }, - { + }, { .fourcc = V4L2_PIX_FMT_SGRBG10, - }, - { + }, { .fourcc = V4L2_PIX_FMT_SRGGB10, }, }; @@ -225,7 +205,6 @@ static struct isc_format sama7g5_formats_list[] = { .mbus_code = MEDIA_BUS_FMT_Y10_1X10, .pfe_cfg0_bps = ISC_PFG_CFG0_BPS_TEN, }, - }; static void isc_sama7g5_config_csc(struct isc_device *isc) diff --git a/drivers/media/platform/atmel/microchip-csi2dc.c b/drivers/media/platform/atmel/microchip-csi2dc.c index 2487978db1f1..d5b359f607ae 100644 --- a/drivers/media/platform/atmel/microchip-csi2dc.c +++ b/drivers/media/platform/atmel/microchip-csi2dc.c @@ -454,6 +454,10 @@ static int csi2dc_init_cfg(struct v4l2_subdev *csi2dc_sd, return 0; } +static const struct media_entity_operations csi2dc_entity_ops = { + .link_validate = v4l2_subdev_link_validate, +}; + static const struct v4l2_subdev_pad_ops csi2dc_pad_ops = { .enum_mbus_code = csi2dc_enum_mbus_code, .set_fmt = csi2dc_set_fmt, @@ -683,6 +687,7 @@ static int csi2dc_probe(struct platform_device *pdev) csi2dc->csi2dc_sd.flags |= V4L2_SUBDEV_FL_HAS_DEVNODE; csi2dc->csi2dc_sd.entity.function = MEDIA_ENT_F_VID_IF_BRIDGE; + csi2dc->csi2dc_sd.entity.ops = &csi2dc_entity_ops; platform_set_drvdata(pdev, csi2dc); diff --git a/drivers/media/platform/cadence/cdns-csi2tx.c b/drivers/media/platform/cadence/cdns-csi2tx.c index 8f8c36056354..58e405b69f67 100644 --- a/drivers/media/platform/cadence/cdns-csi2tx.c +++ b/drivers/media/platform/cadence/cdns-csi2tx.c @@ -15,6 +15,7 @@ #include <linux/platform_device.h> #include <linux/slab.h> +#include <media/mipi-csi2.h> #include <media/v4l2-ctrls.h> #include <media/v4l2-device.h> #include <media/v4l2-fwnode.h> @@ -121,12 +122,12 @@ static const struct csi2tx_fmt csi2tx_formats[] = { { .mbus = MEDIA_BUS_FMT_UYVY8_1X16, .bpp = 2, - .dt = 0x1e, + .dt = MIPI_CSI2_DT_YUV422_8B, }, { .mbus = MEDIA_BUS_FMT_RGB888_1X24, .bpp = 3, - .dt = 0x24, + .dt = MIPI_CSI2_DT_RGB888, }, }; diff --git a/drivers/media/platform/chips-media/coda-bit.c b/drivers/media/platform/chips-media/coda-bit.c index c484c008ab02..2736a902e3df 100644 --- a/drivers/media/platform/chips-media/coda-bit.c +++ b/drivers/media/platform/chips-media/coda-bit.c @@ -326,6 +326,8 @@ void coda_fill_bitstream(struct coda_ctx *ctx, struct list_head *buffer_list) struct coda_buffer_meta *meta; u32 start; + lockdep_assert_held(&ctx->bitstream_mutex); + if (ctx->bit_stream_param & CODA_BIT_STREAM_END_FLAG) return; @@ -2174,7 +2176,6 @@ static int coda_prepare_decode(struct coda_ctx *ctx) (!(ctx->bit_stream_param & CODA_BIT_STREAM_END_FLAG))) { coda_dbg(1, ctx, "bitstream payload: %d, skipping\n", coda_get_bitstream_payload(ctx)); - v4l2_m2m_job_finish(ctx->dev->m2m_dev, ctx->fh.m2m_ctx); return -EAGAIN; } @@ -2184,7 +2185,6 @@ static int coda_prepare_decode(struct coda_ctx *ctx) if (ret < 0) { v4l2_err(&dev->v4l2_dev, "failed to start decoding\n"); - v4l2_m2m_job_finish(ctx->dev->m2m_dev, ctx->fh.m2m_ctx); return -EAGAIN; } else { ctx->initialized = 1; diff --git a/drivers/media/platform/chips-media/coda-common.c b/drivers/media/platform/chips-media/coda-common.c index a57822b05070..af71eea04dbd 100644 --- a/drivers/media/platform/chips-media/coda-common.c +++ b/drivers/media/platform/chips-media/coda-common.c @@ -657,6 +657,8 @@ static int coda_try_fmt_vid_cap(struct file *file, void *priv, const struct coda_q_data *q_data_src; const struct coda_codec *codec; struct vb2_queue *src_vq; + int hscale = 0; + int vscale = 0; int ret; bool use_vdoa; @@ -673,8 +675,13 @@ static int coda_try_fmt_vid_cap(struct file *file, void *priv, */ src_vq = v4l2_m2m_get_vq(ctx->fh.m2m_ctx, V4L2_BUF_TYPE_VIDEO_OUTPUT); if (vb2_is_streaming(src_vq)) { - f->fmt.pix.width = q_data_src->width; - f->fmt.pix.height = q_data_src->height; + if (q_data_src->fourcc == V4L2_PIX_FMT_JPEG && + ctx->dev->devtype->product == CODA_960) { + hscale = coda_jpeg_scale(q_data_src->width, f->fmt.pix.width); + vscale = coda_jpeg_scale(q_data_src->height, f->fmt.pix.height); + } + f->fmt.pix.width = q_data_src->width >> hscale; + f->fmt.pix.height = q_data_src->height >> vscale; if (q_data_src->fourcc == V4L2_PIX_FMT_JPEG) { if (ctx->params.jpeg_chroma_subsampling == @@ -704,8 +711,8 @@ static int coda_try_fmt_vid_cap(struct file *file, void *priv, /* The decoders always write complete macroblocks or MCUs */ if (ctx->inst_type == CODA_INST_DECODER) { - f->fmt.pix.bytesperline = round_up(f->fmt.pix.width, 16); - f->fmt.pix.height = round_up(f->fmt.pix.height, 16); + f->fmt.pix.bytesperline = round_up(f->fmt.pix.width, 16 >> hscale); + f->fmt.pix.height = round_up(f->fmt.pix.height, 16 >> vscale); if (codec->src_fourcc == V4L2_PIX_FMT_JPEG && f->fmt.pix.pixelformat == V4L2_PIX_FMT_YUV422P) { f->fmt.pix.sizeimage = f->fmt.pix.bytesperline * @@ -850,17 +857,26 @@ static int coda_s_fmt_vid_cap(struct file *file, void *priv, struct coda_q_data *q_data_src; const struct coda_codec *codec; struct v4l2_rect r; + int hscale = 0; + int vscale = 0; int ret; + q_data_src = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_OUTPUT); + + if (q_data_src->fourcc == V4L2_PIX_FMT_JPEG && + ctx->dev->devtype->product == CODA_960) { + hscale = coda_jpeg_scale(q_data_src->width, f->fmt.pix.width); + vscale = coda_jpeg_scale(q_data_src->height, f->fmt.pix.height); + } + ret = coda_try_fmt_vid_cap(file, priv, f); if (ret) return ret; - q_data_src = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_OUTPUT); r.left = 0; r.top = 0; - r.width = q_data_src->width; - r.height = q_data_src->height; + r.width = q_data_src->width >> hscale; + r.height = q_data_src->height >> vscale; ret = coda_s_fmt(ctx, f, &r); if (ret) @@ -1091,17 +1107,6 @@ static int coda_s_selection(struct file *file, void *fh, } } -static int coda_try_encoder_cmd(struct file *file, void *fh, - struct v4l2_encoder_cmd *ec) -{ - struct coda_ctx *ctx = fh_to_ctx(fh); - - if (ctx->inst_type != CODA_INST_ENCODER) - return -ENOTTY; - - return v4l2_m2m_ioctl_try_encoder_cmd(file, fh, ec); -} - static void coda_wake_up_capture_queue(struct coda_ctx *ctx) { struct vb2_queue *dst_vq; @@ -1120,7 +1125,7 @@ static int coda_encoder_cmd(struct file *file, void *fh, struct vb2_v4l2_buffer *buf; int ret; - ret = coda_try_encoder_cmd(file, fh, ec); + ret = v4l2_m2m_ioctl_try_encoder_cmd(file, fh, ec); if (ret < 0) return ret; @@ -1149,17 +1154,6 @@ static int coda_encoder_cmd(struct file *file, void *fh, return 0; } -static int coda_try_decoder_cmd(struct file *file, void *fh, - struct v4l2_decoder_cmd *dc) -{ - struct coda_ctx *ctx = fh_to_ctx(fh); - - if (ctx->inst_type != CODA_INST_DECODER) - return -ENOTTY; - - return v4l2_m2m_ioctl_try_decoder_cmd(file, fh, dc); -} - static bool coda_mark_last_meta(struct coda_ctx *ctx) { struct coda_buffer_meta *meta; @@ -1216,7 +1210,7 @@ static int coda_decoder_cmd(struct file *file, void *fh, bool wakeup; int ret; - ret = coda_try_decoder_cmd(file, fh, dc); + ret = v4l2_m2m_ioctl_try_decoder_cmd(file, fh, dc); if (ret < 0) return ret; @@ -1291,9 +1285,6 @@ static int coda_enum_framesizes(struct file *file, void *fh, struct coda_q_data *q_data_dst; const struct coda_codec *codec; - if (ctx->inst_type != CODA_INST_ENCODER) - return -ENOTTY; - if (fsize->index) return -EINVAL; @@ -1324,7 +1315,8 @@ static int coda_enum_frameintervals(struct file *file, void *fh, struct v4l2_frmivalenum *f) { struct coda_ctx *ctx = fh_to_ctx(fh); - int i; + struct coda_q_data *q_data; + const struct coda_codec *codec; if (f->index) return -EINVAL; @@ -1333,12 +1325,19 @@ static int coda_enum_frameintervals(struct file *file, void *fh, if (!ctx->vdoa && f->pixel_format == V4L2_PIX_FMT_YUYV) return -EINVAL; - for (i = 0; i < CODA_MAX_FORMATS; i++) { - if (f->pixel_format == ctx->cvd->src_formats[i] || - f->pixel_format == ctx->cvd->dst_formats[i]) - break; + if (coda_format_normalize_yuv(f->pixel_format) == V4L2_PIX_FMT_YUV420) { + q_data = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_CAPTURE); + codec = coda_find_codec(ctx->dev, f->pixel_format, + q_data->fourcc); + } else { + codec = coda_find_codec(ctx->dev, V4L2_PIX_FMT_YUV420, + f->pixel_format); } - if (i == CODA_MAX_FORMATS) + if (!codec) + return -EINVAL; + + if (f->width < MIN_W || f->width > codec->max_w || + f->height < MIN_H || f->height > codec->max_h) return -EINVAL; f->type = V4L2_FRMIVAL_TYPE_CONTINUOUS; @@ -1498,9 +1497,9 @@ static const struct v4l2_ioctl_ops coda_ioctl_ops = { .vidioc_g_selection = coda_g_selection, .vidioc_s_selection = coda_s_selection, - .vidioc_try_encoder_cmd = coda_try_encoder_cmd, + .vidioc_try_encoder_cmd = v4l2_m2m_ioctl_try_encoder_cmd, .vidioc_encoder_cmd = coda_encoder_cmd, - .vidioc_try_decoder_cmd = coda_try_decoder_cmd, + .vidioc_try_decoder_cmd = v4l2_m2m_ioctl_try_decoder_cmd, .vidioc_decoder_cmd = coda_decoder_cmd, .vidioc_g_parm = coda_g_parm, @@ -1535,12 +1534,8 @@ static void coda_pic_run_work(struct work_struct *work) mutex_lock(&dev->coda_mutex); ret = ctx->ops->prepare_run(ctx); - if (ret < 0 && ctx->inst_type == CODA_INST_DECODER) { - mutex_unlock(&dev->coda_mutex); - mutex_unlock(&ctx->buffer_mutex); - /* job_finish scheduled by prepare_decode */ - return; - } + if (ret < 0 && ctx->inst_type == CODA_INST_DECODER) + goto out; if (!wait_for_completion_timeout(&ctx->completion, msecs_to_jiffies(1000))) { @@ -1562,6 +1557,7 @@ static void coda_pic_run_work(struct work_struct *work) ctx->ops->seq_end_work) queue_work(dev->workqueue, &ctx->seq_end_work); +out: mutex_unlock(&dev->coda_mutex); mutex_unlock(&ctx->buffer_mutex); @@ -1665,13 +1661,18 @@ static void set_default_params(struct coda_ctx *ctx) csize = coda_estimate_sizeimage(ctx, usize, max_w, max_h); ctx->params.codec_mode = ctx->codec->mode; - if (ctx->cvd->src_formats[0] == V4L2_PIX_FMT_JPEG) - ctx->colorspace = V4L2_COLORSPACE_JPEG; - else + if (ctx->cvd->src_formats[0] == V4L2_PIX_FMT_JPEG || + ctx->cvd->dst_formats[0] == V4L2_PIX_FMT_JPEG) { + ctx->colorspace = V4L2_COLORSPACE_SRGB; + ctx->xfer_func = V4L2_XFER_FUNC_SRGB; + ctx->ycbcr_enc = V4L2_YCBCR_ENC_601; + ctx->quantization = V4L2_QUANTIZATION_FULL_RANGE; + } else { ctx->colorspace = V4L2_COLORSPACE_REC709; - ctx->xfer_func = V4L2_XFER_FUNC_DEFAULT; - ctx->ycbcr_enc = V4L2_YCBCR_ENC_DEFAULT; - ctx->quantization = V4L2_QUANTIZATION_DEFAULT; + ctx->xfer_func = V4L2_XFER_FUNC_DEFAULT; + ctx->ycbcr_enc = V4L2_YCBCR_ENC_DEFAULT; + ctx->quantization = V4L2_QUANTIZATION_DEFAULT; + } ctx->params.framerate = 30; /* Default formats for output and input queues */ @@ -2011,13 +2012,13 @@ static int coda_start_streaming(struct vb2_queue *q, unsigned int count) */ if (q_data_src->fourcc == V4L2_PIX_FMT_JPEG) { buf = v4l2_m2m_next_src_buf(ctx->fh.m2m_ctx); - ret = coda_jpeg_decode_header(ctx, &buf->vb2_buf); - if (ret < 0) { - v4l2_err(v4l2_dev, - "failed to decode JPEG header: %d\n", - ret); - goto err; - } + coda_jpeg_decode_header(ctx, &buf->vb2_buf); + /* + * We have to start streaming even if the first buffer + * does not contain a valid JPEG image. The error will + * be caught during device run and will be signalled + * via the capture buffer error flag. + */ q_data_dst = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_CAPTURE); q_data_dst->width = round_up(q_data_src->width, 16); @@ -2344,8 +2345,8 @@ static void coda_encode_ctrls(struct coda_ctx *ctx) V4L2_CID_MPEG_VIDEO_H264_CHROMA_QP_INDEX_OFFSET, -12, 12, 1, 0); v4l2_ctrl_new_std_menu(&ctx->ctrls, &coda_ctrl_ops, V4L2_CID_MPEG_VIDEO_H264_PROFILE, - V4L2_MPEG_VIDEO_H264_PROFILE_BASELINE, 0x0, - V4L2_MPEG_VIDEO_H264_PROFILE_BASELINE); + V4L2_MPEG_VIDEO_H264_PROFILE_CONSTRAINED_BASELINE, 0x0, + V4L2_MPEG_VIDEO_H264_PROFILE_CONSTRAINED_BASELINE); if (ctx->dev->devtype->product == CODA_HX4 || ctx->dev->devtype->product == CODA_7541) { v4l2_ctrl_new_std_menu(&ctx->ctrls, &coda_ctrl_ops, @@ -2359,12 +2360,15 @@ static void coda_encode_ctrls(struct coda_ctx *ctx) if (ctx->dev->devtype->product == CODA_960) { v4l2_ctrl_new_std_menu(&ctx->ctrls, &coda_ctrl_ops, V4L2_CID_MPEG_VIDEO_H264_LEVEL, - V4L2_MPEG_VIDEO_H264_LEVEL_4_0, - ~((1 << V4L2_MPEG_VIDEO_H264_LEVEL_2_0) | + V4L2_MPEG_VIDEO_H264_LEVEL_4_2, + ~((1 << V4L2_MPEG_VIDEO_H264_LEVEL_1_0) | + (1 << V4L2_MPEG_VIDEO_H264_LEVEL_2_0) | (1 << V4L2_MPEG_VIDEO_H264_LEVEL_3_0) | (1 << V4L2_MPEG_VIDEO_H264_LEVEL_3_1) | (1 << V4L2_MPEG_VIDEO_H264_LEVEL_3_2) | - (1 << V4L2_MPEG_VIDEO_H264_LEVEL_4_0)), + (1 << V4L2_MPEG_VIDEO_H264_LEVEL_4_0) | + (1 << V4L2_MPEG_VIDEO_H264_LEVEL_4_1) | + (1 << V4L2_MPEG_VIDEO_H264_LEVEL_4_2)), V4L2_MPEG_VIDEO_H264_LEVEL_4_0); } v4l2_ctrl_new_std(&ctx->ctrls, &coda_ctrl_ops, @@ -2426,7 +2430,7 @@ static void coda_decode_ctrls(struct coda_ctx *ctx) ctx->h264_profile_ctrl = v4l2_ctrl_new_std_menu(&ctx->ctrls, &coda_ctrl_ops, V4L2_CID_MPEG_VIDEO_H264_PROFILE, V4L2_MPEG_VIDEO_H264_PROFILE_HIGH, - ~((1 << V4L2_MPEG_VIDEO_H264_PROFILE_BASELINE) | + ~((1 << V4L2_MPEG_VIDEO_H264_PROFILE_CONSTRAINED_BASELINE) | (1 << V4L2_MPEG_VIDEO_H264_PROFILE_MAIN) | (1 << V4L2_MPEG_VIDEO_H264_PROFILE_HIGH)), V4L2_MPEG_VIDEO_H264_PROFILE_HIGH); @@ -2901,6 +2905,23 @@ static int coda_register_device(struct coda_dev *dev, int i) v4l2_disable_ioctl(vfd, VIDIOC_G_CROP); v4l2_disable_ioctl(vfd, VIDIOC_S_CROP); + if (dev->devtype->vdevs[i]->type == CODA_INST_ENCODER) { + v4l2_disable_ioctl(vfd, VIDIOC_DECODER_CMD); + v4l2_disable_ioctl(vfd, VIDIOC_TRY_DECODER_CMD); + if (dev->devtype->vdevs[i]->dst_formats[0] == V4L2_PIX_FMT_JPEG) { + v4l2_disable_ioctl(vfd, VIDIOC_ENUM_FRAMEINTERVALS); + v4l2_disable_ioctl(vfd, VIDIOC_G_PARM); + v4l2_disable_ioctl(vfd, VIDIOC_S_PARM); + } + } else { + v4l2_disable_ioctl(vfd, VIDIOC_ENCODER_CMD); + v4l2_disable_ioctl(vfd, VIDIOC_TRY_ENCODER_CMD); + v4l2_disable_ioctl(vfd, VIDIOC_ENUM_FRAMESIZES); + v4l2_disable_ioctl(vfd, VIDIOC_ENUM_FRAMEINTERVALS); + v4l2_disable_ioctl(vfd, VIDIOC_G_PARM); + v4l2_disable_ioctl(vfd, VIDIOC_S_PARM); + } + ret = video_register_device(vfd, VFL_TYPE_VIDEO, 0); if (!ret) v4l2_info(&dev->v4l2_dev, "%s registered as %s\n", diff --git a/drivers/media/platform/chips-media/coda-jpeg.c b/drivers/media/platform/chips-media/coda-jpeg.c index a72f4655e5ad..a0b22b07f69a 100644 --- a/drivers/media/platform/chips-media/coda-jpeg.c +++ b/drivers/media/platform/chips-media/coda-jpeg.c @@ -283,7 +283,8 @@ int coda_jpeg_decode_header(struct coda_ctx *ctx, struct vb2_buffer *vb) ret = v4l2_jpeg_parse_header(buf, len, &header); if (ret < 0) { - v4l2_err(&dev->v4l2_dev, "failed to parse header\n"); + v4l2_err(&dev->v4l2_dev, "failed to parse JPEG header: %pe\n", + ERR_PTR(ret)); return ret; } @@ -1328,6 +1329,7 @@ static int coda9_jpeg_prepare_decode(struct coda_ctx *ctx) struct coda_q_data *q_data_src, *q_data_dst; struct vb2_v4l2_buffer *src_buf, *dst_buf; int chroma_interleave; + int scl_hor_mode, scl_ver_mode; src_buf = v4l2_m2m_next_src_buf(ctx->fh.m2m_ctx); dst_buf = v4l2_m2m_next_dst_buf(ctx->fh.m2m_ctx); @@ -1335,27 +1337,24 @@ static int coda9_jpeg_prepare_decode(struct coda_ctx *ctx) q_data_dst = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_CAPTURE); dst_fourcc = q_data_dst->fourcc; + scl_hor_mode = coda_jpeg_scale(q_data_src->width, q_data_dst->width); + scl_ver_mode = coda_jpeg_scale(q_data_src->height, q_data_dst->height); + if (vb2_get_plane_payload(&src_buf->vb2_buf, 0) == 0) vb2_set_plane_payload(&src_buf->vb2_buf, 0, vb2_plane_size(&src_buf->vb2_buf, 0)); chroma_format = coda9_jpeg_chroma_format(q_data_dst->fourcc); - if (chroma_format < 0) { - v4l2_m2m_job_finish(ctx->dev->m2m_dev, ctx->fh.m2m_ctx); + if (chroma_format < 0) return chroma_format; - } ret = coda_jpeg_decode_header(ctx, &src_buf->vb2_buf); if (ret < 0) { - v4l2_err(&dev->v4l2_dev, "failed to decode JPEG header: %d\n", - ret); - src_buf = v4l2_m2m_src_buf_remove(ctx->fh.m2m_ctx); dst_buf = v4l2_m2m_dst_buf_remove(ctx->fh.m2m_ctx); v4l2_m2m_buf_done(src_buf, VB2_BUF_STATE_DONE); - v4l2_m2m_buf_done(dst_buf, VB2_BUF_STATE_DONE); + v4l2_m2m_buf_done(dst_buf, VB2_BUF_STATE_ERROR); - v4l2_m2m_job_finish(ctx->dev->m2m_dev, ctx->fh.m2m_ctx); return ret; } @@ -1386,7 +1385,11 @@ static int coda9_jpeg_prepare_decode(struct coda_ctx *ctx) coda_write(dev, 0, CODA9_REG_JPEG_ROT_INFO); coda_write(dev, bus_req_num[chroma_format], CODA9_REG_JPEG_OP_INFO); coda_write(dev, mcu_info[chroma_format], CODA9_REG_JPEG_MCU_INFO); - coda_write(dev, 0, CODA9_REG_JPEG_SCL_INFO); + if (scl_hor_mode || scl_ver_mode) + val = CODA9_JPEG_SCL_ENABLE | (scl_hor_mode << 2) | scl_ver_mode; + else + val = 0; + coda_write(dev, val, CODA9_REG_JPEG_SCL_INFO); coda_write(dev, chroma_interleave, CODA9_REG_JPEG_DPB_CONFIG); coda_write(dev, ctx->params.jpeg_restart_interval, CODA9_REG_JPEG_RST_INTVAL); @@ -1396,7 +1399,6 @@ static int coda9_jpeg_prepare_decode(struct coda_ctx *ctx) if (ret < 0) { v4l2_err(&dev->v4l2_dev, "failed to set up Huffman tables: %d\n", ret); - v4l2_m2m_job_finish(ctx->dev->m2m_dev, ctx->fh.m2m_ctx); return ret; } } diff --git a/drivers/media/platform/chips-media/coda.h b/drivers/media/platform/chips-media/coda.h index dcf35641c603..ddfd0a32c653 100644 --- a/drivers/media/platform/chips-media/coda.h +++ b/drivers/media/platform/chips-media/coda.h @@ -380,6 +380,13 @@ u32 coda_mpeg4_parse_headers(struct coda_ctx *ctx, u8 *buf, u32 size); void coda_update_profile_level_ctrls(struct coda_ctx *ctx, u8 profile_idc, u8 level_idc); +static inline int coda_jpeg_scale(int src, int dst) +{ + return (dst <= src / 8) ? 3 : + (dst <= src / 4) ? 2 : + (dst <= src / 2) ? 1 : 0; +} + bool coda_jpeg_check_buffer(struct coda_ctx *ctx, struct vb2_buffer *vb); int coda_jpeg_decode_header(struct coda_ctx *ctx, struct vb2_buffer *vb); int coda_jpeg_write_tables(struct coda_ctx *ctx); diff --git a/drivers/media/platform/marvell/cafe-driver.c b/drivers/media/platform/marvell/cafe-driver.c index 03dcf8bf705e..ae97ce4ead98 100644 --- a/drivers/media/platform/marvell/cafe-driver.c +++ b/drivers/media/platform/marvell/cafe-driver.c @@ -497,7 +497,6 @@ static int cafe_pci_probe(struct pci_dev *pdev, mcam->plat_power_up = cafe_ctlr_power_up; mcam->plat_power_down = cafe_ctlr_power_down; mcam->dev = &pdev->dev; - snprintf(mcam->bus_info, sizeof(mcam->bus_info), "PCI:%s", pci_name(pdev)); /* * Vmalloc mode for buffers is traditional with this driver. * We *might* be able to run DMA_contig, especially on a system diff --git a/drivers/media/platform/mediatek/jpeg/mtk_jpeg_core.c b/drivers/media/platform/mediatek/jpeg/mtk_jpeg_core.c index ab5485dfc20c..bc5b0a0168ec 100644 --- a/drivers/media/platform/mediatek/jpeg/mtk_jpeg_core.c +++ b/drivers/media/platform/mediatek/jpeg/mtk_jpeg_core.c @@ -137,8 +137,6 @@ static int mtk_jpeg_querycap(struct file *file, void *priv, strscpy(cap->driver, jpeg->variant->dev_name, sizeof(cap->driver)); strscpy(cap->card, jpeg->variant->dev_name, sizeof(cap->card)); - snprintf(cap->bus_info, sizeof(cap->bus_info), "platform:%s", - dev_name(jpeg->dev)); return 0; } diff --git a/drivers/media/platform/mediatek/vcodec/Kconfig b/drivers/media/platform/mediatek/vcodec/Kconfig index c5c76753c626..74b00eb1bc97 100644 --- a/drivers/media/platform/mediatek/vcodec/Kconfig +++ b/drivers/media/platform/mediatek/vcodec/Kconfig @@ -22,6 +22,7 @@ config VIDEO_MEDIATEK_VCODEC select VIDEO_MEDIATEK_VCODEC_VPU if VIDEO_MEDIATEK_VPU select VIDEO_MEDIATEK_VCODEC_SCP if MTK_SCP select V4L2_H264 + select V4L2_VP9 select MEDIA_CONTROLLER select MEDIA_CONTROLLER_REQUEST_API help diff --git a/drivers/media/platform/mediatek/vcodec/Makefile b/drivers/media/platform/mediatek/vcodec/Makefile index 359619653a0e..93e7a343b5b0 100644 --- a/drivers/media/platform/mediatek/vcodec/Makefile +++ b/drivers/media/platform/mediatek/vcodec/Makefile @@ -7,8 +7,12 @@ obj-$(CONFIG_VIDEO_MEDIATEK_VCODEC) += mtk-vcodec-dec.o \ mtk-vcodec-dec-y := vdec/vdec_h264_if.o \ vdec/vdec_vp8_if.o \ + vdec/vdec_vp8_req_if.o \ vdec/vdec_vp9_if.o \ + vdec/vdec_vp9_req_lat_if.o \ vdec/vdec_h264_req_if.o \ + vdec/vdec_h264_req_common.o \ + vdec/vdec_h264_req_multi_if.o \ mtk_vcodec_dec_drv.o \ vdec_drv_if.o \ vdec_vpu_if.o \ diff --git a/drivers/media/platform/mediatek/vcodec/mtk_vcodec_dec.c b/drivers/media/platform/mediatek/vcodec/mtk_vcodec_dec.c index 130ecef2e766..52e5d36aa912 100644 --- a/drivers/media/platform/mediatek/vcodec/mtk_vcodec_dec.c +++ b/drivers/media/platform/mediatek/vcodec/mtk_vcodec_dec.c @@ -26,7 +26,7 @@ mtk_vdec_find_format(struct v4l2_format *f, const struct mtk_video_fmt *fmt; unsigned int k; - for (k = 0; k < dec_pdata->num_formats; k++) { + for (k = 0; k < *dec_pdata->num_formats; k++) { fmt = &dec_pdata->vdec_formats[k]; if (fmt->fourcc == f->fmt.pix_mp.pixelformat) return fmt; @@ -47,14 +47,7 @@ static struct mtk_q_data *mtk_vdec_get_q_data(struct mtk_vcodec_ctx *ctx, static int vidioc_try_decoder_cmd(struct file *file, void *priv, struct v4l2_decoder_cmd *cmd) { - struct mtk_vcodec_ctx *ctx = fh_to_ctx(priv); - - /* Use M2M stateless helper if relevant */ - if (ctx->dev->vdec_pdata->uses_stateless_api) - return v4l2_m2m_ioctl_stateless_try_decoder_cmd(file, priv, - cmd); - else - return v4l2_m2m_ioctl_try_decoder_cmd(file, priv, cmd); + return v4l2_m2m_ioctl_try_decoder_cmd(file, priv, cmd); } @@ -69,10 +62,6 @@ static int vidioc_decoder_cmd(struct file *file, void *priv, if (ret) return ret; - /* Use M2M stateless helper if relevant */ - if (ctx->dev->vdec_pdata->uses_stateless_api) - return v4l2_m2m_ioctl_stateless_decoder_cmd(file, priv, cmd); - mtk_v4l2_debug(1, "decoder cmd=%u", cmd->cmd); dst_vq = v4l2_m2m_get_vq(ctx->m2m_ctx, V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE); @@ -152,13 +141,15 @@ void mtk_vcodec_dec_set_default_params(struct mtk_vcodec_ctx *ctx) q_data->coded_height = DFT_CFG_HEIGHT; q_data->fmt = ctx->dev->vdec_pdata->default_cap_fmt; q_data->field = V4L2_FIELD_NONE; + ctx->max_width = MTK_VDEC_MAX_W; + ctx->max_height = MTK_VDEC_MAX_H; v4l_bound_align_image(&q_data->coded_width, MTK_VDEC_MIN_W, - MTK_VDEC_MAX_W, 4, + ctx->max_width, 4, &q_data->coded_height, MTK_VDEC_MIN_H, - MTK_VDEC_MAX_H, 5, 6); + ctx->max_height, 5, 6); q_data->sizeimage[0] = q_data->coded_width * q_data->coded_height; q_data->bytesperline[0] = q_data->coded_width; @@ -217,7 +208,7 @@ static int vidioc_vdec_subscribe_evt(struct v4l2_fh *fh, } } -static int vidioc_try_fmt(struct v4l2_format *f, +static int vidioc_try_fmt(struct mtk_vcodec_ctx *ctx, struct v4l2_format *f, const struct mtk_video_fmt *fmt) { struct v4l2_pix_format_mplane *pix_fmt_mp = &f->fmt.pix_mp; @@ -225,9 +216,9 @@ static int vidioc_try_fmt(struct v4l2_format *f, pix_fmt_mp->field = V4L2_FIELD_NONE; pix_fmt_mp->width = - clamp(pix_fmt_mp->width, MTK_VDEC_MIN_W, MTK_VDEC_MAX_W); + clamp(pix_fmt_mp->width, MTK_VDEC_MIN_W, ctx->max_width); pix_fmt_mp->height = - clamp(pix_fmt_mp->height, MTK_VDEC_MIN_H, MTK_VDEC_MAX_H); + clamp(pix_fmt_mp->height, MTK_VDEC_MIN_H, ctx->max_height); if (f->type == V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE) { pix_fmt_mp->num_planes = 1; @@ -245,16 +236,16 @@ static int vidioc_try_fmt(struct v4l2_format *f, tmp_h = pix_fmt_mp->height; v4l_bound_align_image(&pix_fmt_mp->width, MTK_VDEC_MIN_W, - MTK_VDEC_MAX_W, 6, + ctx->max_width, 6, &pix_fmt_mp->height, MTK_VDEC_MIN_H, - MTK_VDEC_MAX_H, 6, 9); + ctx->max_height, 6, 9); if (pix_fmt_mp->width < tmp_w && - (pix_fmt_mp->width + 64) <= MTK_VDEC_MAX_W) + (pix_fmt_mp->width + 64) <= ctx->max_width) pix_fmt_mp->width += 64; if (pix_fmt_mp->height < tmp_h && - (pix_fmt_mp->height + 64) <= MTK_VDEC_MAX_H) + (pix_fmt_mp->height + 64) <= ctx->max_height) pix_fmt_mp->height += 64; mtk_v4l2_debug(0, @@ -294,7 +285,7 @@ static int vidioc_try_fmt_vid_cap_mplane(struct file *file, void *priv, fmt = mtk_vdec_find_format(f, dec_pdata); } - return vidioc_try_fmt(f, fmt); + return vidioc_try_fmt(ctx, f, fmt); } static int vidioc_try_fmt_vid_out_mplane(struct file *file, void *priv, @@ -317,7 +308,7 @@ static int vidioc_try_fmt_vid_out_mplane(struct file *file, void *priv, return -EINVAL; } - return vidioc_try_fmt(f, fmt); + return vidioc_try_fmt(ctx, f, fmt); } static int vidioc_vdec_g_selection(struct file *file, void *priv, @@ -444,8 +435,15 @@ static int vidioc_vdec_s_fmt(struct file *file, void *priv, if (fmt == NULL) return -EINVAL; + if (!(ctx->dev->dec_capability & VCODEC_CAPABILITY_4K_DISABLED) && + fmt->fourcc != V4L2_PIX_FMT_VP8_FRAME) { + mtk_v4l2_debug(3, "4K is enabled"); + ctx->max_width = VCODEC_DEC_4K_CODED_WIDTH; + ctx->max_height = VCODEC_DEC_4K_CODED_HEIGHT; + } + q_data->fmt = fmt; - vidioc_try_fmt(f, q_data->fmt); + vidioc_try_fmt(ctx, f, q_data->fmt); if (f->type == V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE) { q_data->sizeimage[0] = pix_mp->plane_fmt[0].sizeimage; q_data->coded_width = pix_mp->width; @@ -466,6 +464,8 @@ static int vidioc_vdec_s_fmt(struct file *file, void *priv, } ctx->state = MTK_STATE_INIT; } + } else { + ctx->capture_fourcc = fmt->fourcc; } /* @@ -476,11 +476,14 @@ static int vidioc_vdec_s_fmt(struct file *file, void *priv, ctx->picinfo.pic_w = pix_mp->width; ctx->picinfo.pic_h = pix_mp->height; + /* + * If get pic info fail, need to use the default pic info params, or + * v4l2-compliance will fail + */ ret = vdec_if_get_param(ctx, GET_PARAM_PIC_INFO, &ctx->picinfo); if (ret) { mtk_v4l2_err("[%d]Error!! Get GET_PARAM_PICTURE_INFO Fail", ctx->id); - return -EINVAL; } ctx->last_decoded_picinfo = ctx->picinfo; @@ -523,20 +526,15 @@ static int vidioc_enum_framesizes(struct file *file, void *priv, if (fsize->index != 0) return -EINVAL; - for (i = 0; i < dec_pdata->num_framesizes; ++i) { + for (i = 0; i < *dec_pdata->num_framesizes; ++i) { if (fsize->pixel_format != dec_pdata->vdec_framesizes[i].fourcc) continue; fsize->type = V4L2_FRMSIZE_TYPE_STEPWISE; fsize->stepwise = dec_pdata->vdec_framesizes[i].stepwise; - if (!(ctx->dev->dec_capability & - VCODEC_CAPABILITY_4K_DISABLED)) { - mtk_v4l2_debug(3, "4K is enabled"); - fsize->stepwise.max_width = - VCODEC_DEC_4K_CODED_WIDTH; - fsize->stepwise.max_height = - VCODEC_DEC_4K_CODED_HEIGHT; - } + + fsize->stepwise.max_width = ctx->max_width; + fsize->stepwise.max_height = ctx->max_height; mtk_v4l2_debug(1, "%x, %d %d %d %d %d %d", ctx->dev->dec_capability, fsize->stepwise.min_width, @@ -545,6 +543,7 @@ static int vidioc_enum_framesizes(struct file *file, void *priv, fsize->stepwise.min_height, fsize->stepwise.max_height, fsize->stepwise.step_height); + return 0; } @@ -559,7 +558,7 @@ static int vidioc_enum_fmt(struct v4l2_fmtdesc *f, void *priv, const struct mtk_video_fmt *fmt; int i, j = 0; - for (i = 0; i < dec_pdata->num_formats; i++) { + for (i = 0; i < *dec_pdata->num_formats; i++) { if (output_queue && dec_pdata->vdec_formats[i].type != MTK_FMT_DEC) continue; @@ -572,7 +571,7 @@ static int vidioc_enum_fmt(struct v4l2_fmtdesc *f, void *priv, ++j; } - if (i == dec_pdata->num_formats) + if (i == *dec_pdata->num_formats) return -EINVAL; fmt = &dec_pdata->vdec_formats[i]; @@ -737,6 +736,8 @@ int vb2ops_vdec_buf_prepare(struct vb2_buffer *vb) i, vb2_plane_size(vb, i), q_data->sizeimage[i]); } + if (!V4L2_TYPE_IS_OUTPUT(vb->type)) + vb2_set_plane_payload(vb, i, q_data->sizeimage[i]); } return 0; diff --git a/drivers/media/platform/mediatek/vcodec/mtk_vcodec_dec.h b/drivers/media/platform/mediatek/vcodec/mtk_vcodec_dec.h index 66cd6d2242c3..4572f92826f2 100644 --- a/drivers/media/platform/mediatek/vcodec/mtk_vcodec_dec.h +++ b/drivers/media/platform/mediatek/vcodec/mtk_vcodec_dec.h @@ -69,6 +69,7 @@ extern const struct media_device_ops mtk_vcodec_media_ops; extern const struct mtk_vcodec_dec_pdata mtk_vdec_8173_pdata; extern const struct mtk_vcodec_dec_pdata mtk_vdec_8183_pdata; extern const struct mtk_vcodec_dec_pdata mtk_lat_sig_core_pdata; +extern const struct mtk_vcodec_dec_pdata mtk_vdec_single_core_pdata; /* diff --git a/drivers/media/platform/mediatek/vcodec/mtk_vcodec_dec_drv.c b/drivers/media/platform/mediatek/vcodec/mtk_vcodec_dec_drv.c index df7b25e9cbc8..995e6e2fb1ab 100644 --- a/drivers/media/platform/mediatek/vcodec/mtk_vcodec_dec_drv.c +++ b/drivers/media/platform/mediatek/vcodec/mtk_vcodec_dec_drv.c @@ -193,9 +193,6 @@ static int fops_vcodec_open(struct file *file) mtk_vcodec_dec_set_default_params(ctx); if (v4l2_fh_is_singular(&ctx->fh)) { - ret = mtk_vcodec_dec_pw_on(dev, MTK_VDEC_LAT0); - if (ret < 0) - goto err_load_fw; /* * Does nothing if firmware was already loaded. */ @@ -252,8 +249,6 @@ static int fops_vcodec_release(struct file *file) v4l2_m2m_ctx_release(ctx->m2m_ctx); mtk_vcodec_dec_release(ctx); - if (v4l2_fh_is_singular(&ctx->fh)) - mtk_vcodec_dec_pw_off(dev, MTK_VDEC_LAT0); v4l2_fh_del(&ctx->fh); v4l2_fh_exit(&ctx->fh); v4l2_ctrl_handler_free(&ctx->ctrl_hdl); @@ -400,6 +395,9 @@ static int mtk_vcodec_probe(struct platform_device *pdev) } if (dev->vdec_pdata->uses_stateless_api) { + v4l2_disable_ioctl(vfd_dec, VIDIOC_DECODER_CMD); + v4l2_disable_ioctl(vfd_dec, VIDIOC_TRY_DECODER_CMD); + dev->mdev_dec.dev = &pdev->dev; strscpy(dev->mdev_dec.model, MTK_VCODEC_DEC_NAME, sizeof(dev->mdev_dec.model)); @@ -463,6 +461,10 @@ static const struct of_device_id mtk_vcodec_match[] = { .compatible = "mediatek,mt8192-vcodec-dec", .data = &mtk_lat_sig_core_pdata, }, + { + .compatible = "mediatek,mt8186-vcodec-dec", + .data = &mtk_vdec_single_core_pdata, + }, {}, }; @@ -487,7 +489,8 @@ static int mtk_vcodec_dec_remove(struct platform_device *pdev) video_unregister_device(dev->vfd_dec); v4l2_device_unregister(&dev->v4l2_dev); - pm_runtime_disable(dev->pm.dev); + if (!dev->vdec_pdata->is_subdev_supported) + pm_runtime_disable(dev->pm.dev); mtk_vcodec_fw_release(dev->fw_handler); return 0; } diff --git a/drivers/media/platform/mediatek/vcodec/mtk_vcodec_dec_pm.c b/drivers/media/platform/mediatek/vcodec/mtk_vcodec_dec_pm.c index 7e0c2644bf7b..0fb7e5ba635b 100644 --- a/drivers/media/platform/mediatek/vcodec/mtk_vcodec_dec_pm.c +++ b/drivers/media/platform/mediatek/vcodec/mtk_vcodec_dec_pm.c @@ -57,74 +57,31 @@ int mtk_vcodec_init_dec_clk(struct platform_device *pdev, struct mtk_vcodec_pm * } EXPORT_SYMBOL_GPL(mtk_vcodec_init_dec_clk); -int mtk_vcodec_dec_pw_on(struct mtk_vcodec_dev *vdec_dev, int hw_idx) +static int mtk_vcodec_dec_pw_on(struct mtk_vcodec_pm *pm) { - struct mtk_vdec_hw_dev *subdev_dev; - struct mtk_vcodec_pm *pm; int ret; - if (vdec_dev->vdec_pdata->is_subdev_supported) { - subdev_dev = mtk_vcodec_get_hw_dev(vdec_dev, hw_idx); - if (!subdev_dev) { - mtk_v4l2_err("Failed to get hw dev\n"); - return -EINVAL; - } - pm = &subdev_dev->pm; - } else { - pm = &vdec_dev->pm; - } - ret = pm_runtime_resume_and_get(pm->dev); if (ret) mtk_v4l2_err("pm_runtime_resume_and_get fail %d", ret); return ret; } -EXPORT_SYMBOL_GPL(mtk_vcodec_dec_pw_on); -void mtk_vcodec_dec_pw_off(struct mtk_vcodec_dev *vdec_dev, int hw_idx) +static void mtk_vcodec_dec_pw_off(struct mtk_vcodec_pm *pm) { - struct mtk_vdec_hw_dev *subdev_dev; - struct mtk_vcodec_pm *pm; int ret; - if (vdec_dev->vdec_pdata->is_subdev_supported) { - subdev_dev = mtk_vcodec_get_hw_dev(vdec_dev, hw_idx); - if (!subdev_dev) { - mtk_v4l2_err("Failed to get hw dev\n"); - return; - } - pm = &subdev_dev->pm; - } else { - pm = &vdec_dev->pm; - } - ret = pm_runtime_put_sync(pm->dev); if (ret) mtk_v4l2_err("pm_runtime_put_sync fail %d", ret); } -EXPORT_SYMBOL_GPL(mtk_vcodec_dec_pw_off); -void mtk_vcodec_dec_clock_on(struct mtk_vcodec_dev *vdec_dev, int hw_idx) +static void mtk_vcodec_dec_clock_on(struct mtk_vcodec_pm *pm) { - struct mtk_vdec_hw_dev *subdev_dev; - struct mtk_vcodec_pm *pm; struct mtk_vcodec_clk *dec_clk; int ret, i; - if (vdec_dev->vdec_pdata->is_subdev_supported) { - subdev_dev = mtk_vcodec_get_hw_dev(vdec_dev, hw_idx); - if (!subdev_dev) { - mtk_v4l2_err("Failed to get hw dev\n"); - return; - } - pm = &subdev_dev->pm; - enable_irq(subdev_dev->dec_irq); - } else { - pm = &vdec_dev->pm; - enable_irq(vdec_dev->dec_irq); - } - dec_clk = &pm->vdec_clk; for (i = 0; i < dec_clk->clk_num; i++) { ret = clk_prepare_enable(dec_clk->clk_info[i].vcodec_clk); @@ -140,30 +97,119 @@ error: for (i -= 1; i >= 0; i--) clk_disable_unprepare(dec_clk->clk_info[i].vcodec_clk); } -EXPORT_SYMBOL_GPL(mtk_vcodec_dec_clock_on); -void mtk_vcodec_dec_clock_off(struct mtk_vcodec_dev *vdec_dev, int hw_idx) +static void mtk_vcodec_dec_clock_off(struct mtk_vcodec_pm *pm) { - struct mtk_vdec_hw_dev *subdev_dev; - struct mtk_vcodec_pm *pm; struct mtk_vcodec_clk *dec_clk; int i; + dec_clk = &pm->vdec_clk; + for (i = dec_clk->clk_num - 1; i >= 0; i--) + clk_disable_unprepare(dec_clk->clk_info[i].vcodec_clk); +} + +static void mtk_vcodec_dec_enable_irq(struct mtk_vcodec_dev *vdec_dev, int hw_idx) +{ + struct mtk_vdec_hw_dev *subdev_dev; + + if (!test_bit(hw_idx, vdec_dev->subdev_bitmap)) + return; + if (vdec_dev->vdec_pdata->is_subdev_supported) { subdev_dev = mtk_vcodec_get_hw_dev(vdec_dev, hw_idx); - if (!subdev_dev) { + if (subdev_dev) + enable_irq(subdev_dev->dec_irq); + else + mtk_v4l2_err("Failed to get hw dev\n"); + } else { + enable_irq(vdec_dev->dec_irq); + } +} + +static void mtk_vcodec_dec_disable_irq(struct mtk_vcodec_dev *vdec_dev, int hw_idx) +{ + struct mtk_vdec_hw_dev *subdev_dev; + + if (!test_bit(hw_idx, vdec_dev->subdev_bitmap)) + return; + + if (vdec_dev->vdec_pdata->is_subdev_supported) { + subdev_dev = mtk_vcodec_get_hw_dev(vdec_dev, hw_idx); + if (subdev_dev) + disable_irq(subdev_dev->dec_irq); + else mtk_v4l2_err("Failed to get hw dev\n"); - return; - } - pm = &subdev_dev->pm; - disable_irq(subdev_dev->dec_irq); } else { - pm = &vdec_dev->pm; disable_irq(vdec_dev->dec_irq); } +} - dec_clk = &pm->vdec_clk; - for (i = dec_clk->clk_num - 1; i >= 0; i--) - clk_disable_unprepare(dec_clk->clk_info[i].vcodec_clk); +static struct mtk_vcodec_pm *mtk_vcodec_dec_get_pm(struct mtk_vcodec_dev *vdec_dev, + int hw_idx) +{ + struct mtk_vdec_hw_dev *subdev_dev; + + if (!test_bit(hw_idx, vdec_dev->subdev_bitmap)) + return NULL; + + if (vdec_dev->vdec_pdata->is_subdev_supported) { + subdev_dev = mtk_vcodec_get_hw_dev(vdec_dev, hw_idx); + if (subdev_dev) + return &subdev_dev->pm; + + mtk_v4l2_err("Failed to get hw dev\n"); + return NULL; + } + + return &vdec_dev->pm; +} + +static void mtk_vcodec_dec_child_dev_on(struct mtk_vcodec_dev *vdec_dev, + int hw_idx) +{ + struct mtk_vcodec_pm *pm; + + pm = mtk_vcodec_dec_get_pm(vdec_dev, hw_idx); + if (pm) { + mtk_vcodec_dec_pw_on(pm); + mtk_vcodec_dec_clock_on(pm); + } +} + +static void mtk_vcodec_dec_child_dev_off(struct mtk_vcodec_dev *vdec_dev, + int hw_idx) +{ + struct mtk_vcodec_pm *pm; + + pm = mtk_vcodec_dec_get_pm(vdec_dev, hw_idx); + if (pm) { + mtk_vcodec_dec_clock_off(pm); + mtk_vcodec_dec_pw_off(pm); + } +} + +void mtk_vcodec_dec_enable_hardware(struct mtk_vcodec_ctx *ctx, int hw_idx) +{ + mutex_lock(&ctx->dev->dec_mutex[hw_idx]); + + if (IS_VDEC_LAT_ARCH(ctx->dev->vdec_pdata->hw_arch) && + hw_idx == MTK_VDEC_CORE) + mtk_vcodec_dec_child_dev_on(ctx->dev, MTK_VDEC_LAT0); + mtk_vcodec_dec_child_dev_on(ctx->dev, hw_idx); + + mtk_vcodec_dec_enable_irq(ctx->dev, hw_idx); +} +EXPORT_SYMBOL_GPL(mtk_vcodec_dec_enable_hardware); + +void mtk_vcodec_dec_disable_hardware(struct mtk_vcodec_ctx *ctx, int hw_idx) +{ + mtk_vcodec_dec_disable_irq(ctx->dev, hw_idx); + + mtk_vcodec_dec_child_dev_off(ctx->dev, hw_idx); + if (IS_VDEC_LAT_ARCH(ctx->dev->vdec_pdata->hw_arch) && + hw_idx == MTK_VDEC_CORE) + mtk_vcodec_dec_child_dev_off(ctx->dev, MTK_VDEC_LAT0); + + mutex_unlock(&ctx->dev->dec_mutex[hw_idx]); } -EXPORT_SYMBOL_GPL(mtk_vcodec_dec_clock_off); +EXPORT_SYMBOL_GPL(mtk_vcodec_dec_disable_hardware); diff --git a/drivers/media/platform/mediatek/vcodec/mtk_vcodec_dec_pm.h b/drivers/media/platform/mediatek/vcodec/mtk_vcodec_dec_pm.h index 3cc721bbfaf6..dbcf3cabe6f3 100644 --- a/drivers/media/platform/mediatek/vcodec/mtk_vcodec_dec_pm.h +++ b/drivers/media/platform/mediatek/vcodec/mtk_vcodec_dec_pm.h @@ -11,9 +11,7 @@ int mtk_vcodec_init_dec_clk(struct platform_device *pdev, struct mtk_vcodec_pm *pm); -int mtk_vcodec_dec_pw_on(struct mtk_vcodec_dev *vdec_dev, int hw_idx); -void mtk_vcodec_dec_pw_off(struct mtk_vcodec_dev *vdec_dev, int hw_idx); -void mtk_vcodec_dec_clock_on(struct mtk_vcodec_dev *vdec_dev, int hw_idx); -void mtk_vcodec_dec_clock_off(struct mtk_vcodec_dev *vdec_dev, int hw_idx); +void mtk_vcodec_dec_enable_hardware(struct mtk_vcodec_ctx *ctx, int hw_idx); +void mtk_vcodec_dec_disable_hardware(struct mtk_vcodec_ctx *ctx, int hw_idx); #endif /* _MTK_VCODEC_DEC_PM_H_ */ diff --git a/drivers/media/platform/mediatek/vcodec/mtk_vcodec_dec_stateful.c b/drivers/media/platform/mediatek/vcodec/mtk_vcodec_dec_stateful.c index 04ca43c77e5f..9c7e6145cebb 100644 --- a/drivers/media/platform/mediatek/vcodec/mtk_vcodec_dec_stateful.c +++ b/drivers/media/platform/mediatek/vcodec/mtk_vcodec_dec_stateful.c @@ -37,7 +37,9 @@ static const struct mtk_video_fmt mtk_video_formats[] = { }, }; -#define NUM_FORMATS ARRAY_SIZE(mtk_video_formats) +static const unsigned int num_supported_formats = + ARRAY_SIZE(mtk_video_formats); + #define DEFAULT_OUT_FMT_IDX 0 #define DEFAULT_CAP_FMT_IDX 3 @@ -59,7 +61,8 @@ static const struct mtk_codec_framesizes mtk_vdec_framesizes[] = { }, }; -#define NUM_SUPPORTED_FRAMESIZE ARRAY_SIZE(mtk_vdec_framesizes) +static const unsigned int num_supported_framesize = + ARRAY_SIZE(mtk_vdec_framesizes); /* * This function tries to clean all display buffers, the buffers will return @@ -90,11 +93,6 @@ static struct vb2_buffer *get_display_buffer(struct mtk_vcodec_ctx *ctx) vb = &dstbuf->m2m_buf.vb; mutex_lock(&ctx->lock); if (dstbuf->used) { - vb2_set_plane_payload(&vb->vb2_buf, 0, ctx->picinfo.fb_sz[0]); - if (ctx->q_data[MTK_Q_DATA_DST].fmt->num_planes == 2) - vb2_set_plane_payload(&vb->vb2_buf, 1, - ctx->picinfo.fb_sz[1]); - mtk_v4l2_debug(2, "[%d]status=%x queue id=%d to done_list %d", ctx->id, disp_frame_buffer->status, vb->vb2_buf.index, dstbuf->queued_in_vb2); @@ -235,7 +233,7 @@ static void mtk_vdec_update_fmt(struct mtk_vcodec_ctx *ctx, unsigned int k; dst_q_data = &ctx->q_data[MTK_Q_DATA_DST]; - for (k = 0; k < NUM_FORMATS; k++) { + for (k = 0; k < num_supported_formats; k++) { fmt = &mtk_video_formats[k]; if (fmt->fourcc == pixelformat) { mtk_v4l2_debug(1, "Update cap fourcc(%d -> %d)", @@ -613,16 +611,15 @@ static struct vb2_ops mtk_vdec_frame_vb2_ops = { }; const struct mtk_vcodec_dec_pdata mtk_vdec_8173_pdata = { - .chip = MTK_MT8173, .init_vdec_params = mtk_init_vdec_params, .ctrls_setup = mtk_vcodec_dec_ctrls_setup, .vdec_vb2_ops = &mtk_vdec_frame_vb2_ops, .vdec_formats = mtk_video_formats, - .num_formats = NUM_FORMATS, + .num_formats = &num_supported_formats, .default_out_fmt = &mtk_video_formats[DEFAULT_OUT_FMT_IDX], .default_cap_fmt = &mtk_video_formats[DEFAULT_CAP_FMT_IDX], .vdec_framesizes = mtk_vdec_framesizes, - .num_framesizes = NUM_SUPPORTED_FRAMESIZE, + .num_framesizes = &num_supported_framesize, .worker = mtk_vdec_worker, .flush_decoder = mtk_vdec_flush_decoder, .is_subdev_supported = false, diff --git a/drivers/media/platform/mediatek/vcodec/mtk_vcodec_dec_stateless.c b/drivers/media/platform/mediatek/vcodec/mtk_vcodec_dec_stateless.c index 23d997ac114d..16d55785d84b 100644 --- a/drivers/media/platform/mediatek/vcodec/mtk_vcodec_dec_stateless.c +++ b/drivers/media/platform/mediatek/vcodec/mtk_vcodec_dec_stateless.c @@ -76,69 +76,102 @@ static const struct mtk_stateless_control mtk_stateless_controls[] = { .max = V4L2_STATELESS_H264_START_CODE_ANNEX_B, }, .codec_type = V4L2_PIX_FMT_H264_SLICE, - } -}; - -#define NUM_CTRLS ARRAY_SIZE(mtk_stateless_controls) - -static const struct mtk_video_fmt mtk_video_formats[] = { + }, + { + .cfg = { + .id = V4L2_CID_STATELESS_VP8_FRAME, + }, + .codec_type = V4L2_PIX_FMT_VP8_FRAME, + }, { - .fourcc = V4L2_PIX_FMT_H264_SLICE, - .type = MTK_FMT_DEC, - .num_planes = 1, + .cfg = { + .id = V4L2_CID_MPEG_VIDEO_VP8_PROFILE, + .min = V4L2_MPEG_VIDEO_VP8_PROFILE_0, + .def = V4L2_MPEG_VIDEO_VP8_PROFILE_0, + .max = V4L2_MPEG_VIDEO_VP8_PROFILE_3, + }, + .codec_type = V4L2_PIX_FMT_VP8_FRAME, }, { - .fourcc = V4L2_PIX_FMT_MM21, - .type = MTK_FMT_FRAME, - .num_planes = 2, + .cfg = { + .id = V4L2_CID_STATELESS_VP9_FRAME, + }, + .codec_type = V4L2_PIX_FMT_VP9_FRAME, }, -}; - -#define NUM_FORMATS ARRAY_SIZE(mtk_video_formats) -#define DEFAULT_OUT_FMT_IDX 0 -#define DEFAULT_CAP_FMT_IDX 1 - -static const struct mtk_codec_framesizes mtk_vdec_framesizes[] = { { - .fourcc = V4L2_PIX_FMT_H264_SLICE, - .stepwise = { MTK_VDEC_MIN_W, MTK_VDEC_MAX_W, 16, - MTK_VDEC_MIN_H, MTK_VDEC_MAX_H, 16 }, + .cfg = { + .id = V4L2_CID_MPEG_VIDEO_VP9_PROFILE, + .min = V4L2_MPEG_VIDEO_VP9_PROFILE_0, + .def = V4L2_MPEG_VIDEO_VP9_PROFILE_0, + .max = V4L2_MPEG_VIDEO_VP9_PROFILE_3, + }, + .codec_type = V4L2_PIX_FMT_VP9_FRAME, }, }; -#define NUM_SUPPORTED_FRAMESIZE ARRAY_SIZE(mtk_vdec_framesizes) +#define NUM_CTRLS ARRAY_SIZE(mtk_stateless_controls) -static void mtk_vdec_stateless_set_dst_payload(struct mtk_vcodec_ctx *ctx, - struct vdec_fb *fb) +static struct mtk_video_fmt mtk_video_formats[5]; +static struct mtk_codec_framesizes mtk_vdec_framesizes[3]; + +static struct mtk_video_fmt default_out_format; +static struct mtk_video_fmt default_cap_format; +static unsigned int num_formats; +static unsigned int num_framesizes; + +static struct v4l2_frmsize_stepwise stepwise_fhd = { + .min_width = MTK_VDEC_MIN_W, + .max_width = MTK_VDEC_MAX_W, + .step_width = 16, + .min_height = MTK_VDEC_MIN_H, + .max_height = MTK_VDEC_MAX_H, + .step_height = 16 +}; + +static void mtk_vdec_stateless_cap_to_disp(struct mtk_vcodec_ctx *ctx, int error, + struct media_request *src_buf_req) { - struct mtk_video_dec_buf *vdec_frame_buf = - container_of(fb, struct mtk_video_dec_buf, frame_buffer); - struct vb2_v4l2_buffer *vb = &vdec_frame_buf->m2m_buf.vb; - unsigned int cap_y_size = ctx->q_data[MTK_Q_DATA_DST].sizeimage[0]; + struct vb2_v4l2_buffer *vb2_dst; + enum vb2_buffer_state state; - vb2_set_plane_payload(&vb->vb2_buf, 0, cap_y_size); - if (ctx->q_data[MTK_Q_DATA_DST].fmt->num_planes == 2) { - unsigned int cap_c_size = - ctx->q_data[MTK_Q_DATA_DST].sizeimage[1]; + if (error) + state = VB2_BUF_STATE_ERROR; + else + state = VB2_BUF_STATE_DONE; - vb2_set_plane_payload(&vb->vb2_buf, 1, cap_c_size); - } + vb2_dst = v4l2_m2m_dst_buf_remove(ctx->m2m_ctx); + v4l2_m2m_buf_done(vb2_dst, state); + + mtk_v4l2_debug(2, "free frame buffer id:%d to done list", + vb2_dst->vb2_buf.index); + + if (src_buf_req) + v4l2_ctrl_request_complete(src_buf_req, &ctx->ctrl_hdl); } -static struct vdec_fb *vdec_get_cap_buffer(struct mtk_vcodec_ctx *ctx, - struct vb2_v4l2_buffer *vb2_v4l2) +static struct vdec_fb *vdec_get_cap_buffer(struct mtk_vcodec_ctx *ctx) { - struct mtk_video_dec_buf *framebuf = - container_of(vb2_v4l2, struct mtk_video_dec_buf, m2m_buf.vb); - struct vdec_fb *pfb = &framebuf->frame_buffer; - struct vb2_buffer *dst_buf = &vb2_v4l2->vb2_buf; + struct mtk_video_dec_buf *framebuf; + struct vb2_v4l2_buffer *vb2_v4l2; + struct vb2_buffer *dst_buf; + struct vdec_fb *pfb; + + vb2_v4l2 = v4l2_m2m_next_dst_buf(ctx->m2m_ctx); + if (!vb2_v4l2) { + mtk_v4l2_debug(1, "[%d] dst_buf empty!!", ctx->id); + return NULL; + } + + dst_buf = &vb2_v4l2->vb2_buf; + framebuf = container_of(vb2_v4l2, struct mtk_video_dec_buf, m2m_buf.vb); - pfb->base_y.va = NULL; + pfb = &framebuf->frame_buffer; + pfb->base_y.va = vb2_plane_vaddr(dst_buf, 0); pfb->base_y.dma_addr = vb2_dma_contig_plane_dma_addr(dst_buf, 0); pfb->base_y.size = ctx->q_data[MTK_Q_DATA_DST].sizeimage[0]; if (ctx->q_data[MTK_Q_DATA_DST].fmt->num_planes == 2) { - pfb->base_c.va = NULL; + pfb->base_c.va = vb2_plane_vaddr(dst_buf, 1); pfb->base_c.dma_addr = vb2_dma_contig_plane_dma_addr(dst_buf, 1); pfb->base_c.size = ctx->q_data[MTK_Q_DATA_DST].sizeimage[1]; @@ -162,12 +195,12 @@ static void mtk_vdec_worker(struct work_struct *work) struct mtk_vcodec_ctx *ctx = container_of(work, struct mtk_vcodec_ctx, decode_work); struct mtk_vcodec_dev *dev = ctx->dev; - struct vb2_v4l2_buffer *vb2_v4l2_src, *vb2_v4l2_dst; + struct vb2_v4l2_buffer *vb2_v4l2_src; struct vb2_buffer *vb2_src; struct mtk_vcodec_mem *bs_src; struct mtk_video_dec_buf *dec_buf_src; struct media_request *src_buf_req; - struct vdec_fb *dst_buf; + enum vb2_buffer_state state; bool res_chg = false; int ret; @@ -178,13 +211,6 @@ static void mtk_vdec_worker(struct work_struct *work) return; } - vb2_v4l2_dst = v4l2_m2m_next_dst_buf(ctx->m2m_ctx); - if (!vb2_v4l2_dst) { - v4l2_m2m_job_finish(dev->m2m_dev_dec, ctx->m2m_ctx); - mtk_v4l2_debug(1, "[%d] no available destination buffer", ctx->id); - return; - } - vb2_src = &vb2_v4l2_src->vb2_buf; dec_buf_src = container_of(vb2_v4l2_src, struct mtk_video_dec_buf, m2m_buf.vb); @@ -193,9 +219,15 @@ static void mtk_vdec_worker(struct work_struct *work) mtk_v4l2_debug(3, "[%d] (%d) id=%d, vb=%p", ctx->id, vb2_src->vb2_queue->type, vb2_src->index, vb2_src); - bs_src->va = NULL; + bs_src->va = vb2_plane_vaddr(vb2_src, 0); bs_src->dma_addr = vb2_dma_contig_plane_dma_addr(vb2_src, 0); bs_src->size = (size_t)vb2_src->planes[0].bytesused; + if (!bs_src->va) { + v4l2_m2m_job_finish(dev->m2m_dev_dec, ctx->m2m_ctx); + mtk_v4l2_err("[%d] id=%d source buffer is NULL", ctx->id, + vb2_src->index); + return; + } mtk_v4l2_debug(3, "[%d] Bitstream VA=%p DMA=%pad Size=%zx vb=%p", ctx->id, bs_src->va, &bs_src->dma_addr, bs_src->size, vb2_src); @@ -206,9 +238,7 @@ static void mtk_vdec_worker(struct work_struct *work) else mtk_v4l2_err("vb2 buffer media request is NULL"); - dst_buf = vdec_get_cap_buffer(ctx, vb2_v4l2_dst); - v4l2_m2m_buf_copy_metadata(vb2_v4l2_src, vb2_v4l2_dst, true); - ret = vdec_if_decode(ctx, bs_src, dst_buf, &res_chg); + ret = vdec_if_decode(ctx, bs_src, NULL, &res_chg); if (ret) { mtk_v4l2_err(" <===[%d], src_buf[%d] sz=0x%zx pts=%llu vdec_if_decode() ret=%d res_chg=%d===>", ctx->id, vb2_src->index, bs_src->size, @@ -220,12 +250,17 @@ static void mtk_vdec_worker(struct work_struct *work) } } - mtk_vdec_stateless_set_dst_payload(ctx, dst_buf); - - v4l2_m2m_buf_done_and_job_finish(dev->m2m_dev_dec, ctx->m2m_ctx, - ret ? VB2_BUF_STATE_ERROR : VB2_BUF_STATE_DONE); - - v4l2_ctrl_request_complete(src_buf_req, &ctx->ctrl_hdl); + state = ret ? VB2_BUF_STATE_ERROR : VB2_BUF_STATE_DONE; + if (!IS_VDEC_LAT_ARCH(dev->vdec_pdata->hw_arch) || + ctx->current_codec == V4L2_PIX_FMT_VP8_FRAME || ret) { + v4l2_m2m_buf_done_and_job_finish(dev->m2m_dev_dec, ctx->m2m_ctx, state); + if (src_buf_req) + v4l2_ctrl_request_complete(src_buf_req, &ctx->ctrl_hdl); + } else { + v4l2_m2m_src_buf_remove(ctx->m2m_ctx); + v4l2_m2m_buf_done(vb2_v4l2_src, state); + v4l2_m2m_job_finish(dev->m2m_dev_dec, ctx->m2m_ctx); + } } static void vb2ops_vdec_stateless_buf_queue(struct vb2_buffer *vb) @@ -307,6 +342,77 @@ const struct media_device_ops mtk_vcodec_media_ops = { .req_queue = v4l2_m2m_request_queue, }; +static void mtk_vcodec_add_formats(unsigned int fourcc, + struct mtk_vcodec_ctx *ctx) +{ + struct mtk_vcodec_dev *dev = ctx->dev; + const struct mtk_vcodec_dec_pdata *pdata = dev->vdec_pdata; + int count_formats = *pdata->num_formats; + int count_framesizes = *pdata->num_framesizes; + + switch (fourcc) { + case V4L2_PIX_FMT_H264_SLICE: + case V4L2_PIX_FMT_VP8_FRAME: + case V4L2_PIX_FMT_VP9_FRAME: + mtk_video_formats[count_formats].fourcc = fourcc; + mtk_video_formats[count_formats].type = MTK_FMT_DEC; + mtk_video_formats[count_formats].num_planes = 1; + + mtk_vdec_framesizes[count_framesizes].fourcc = fourcc; + mtk_vdec_framesizes[count_framesizes].stepwise = stepwise_fhd; + num_framesizes++; + break; + case V4L2_PIX_FMT_MM21: + case V4L2_PIX_FMT_MT21C: + mtk_video_formats[count_formats].fourcc = fourcc; + mtk_video_formats[count_formats].type = MTK_FMT_FRAME; + mtk_video_formats[count_formats].num_planes = 2; + break; + default: + mtk_v4l2_err("Can not add unsupported format type"); + return; + } + + num_formats++; + mtk_v4l2_debug(3, "num_formats: %d num_frames:%d dec_capability: 0x%x", + count_formats, count_framesizes, ctx->dev->dec_capability); +} + +static void mtk_vcodec_get_supported_formats(struct mtk_vcodec_ctx *ctx) +{ + int cap_format_count = 0, out_format_count = 0; + + if (num_formats && num_framesizes) + return; + + if (ctx->dev->dec_capability & MTK_VDEC_FORMAT_MM21) { + mtk_vcodec_add_formats(V4L2_PIX_FMT_MM21, ctx); + cap_format_count++; + } + if (ctx->dev->dec_capability & MTK_VDEC_FORMAT_MT21C) { + mtk_vcodec_add_formats(V4L2_PIX_FMT_MT21C, ctx); + cap_format_count++; + } + if (ctx->dev->dec_capability & MTK_VDEC_FORMAT_H264_SLICE) { + mtk_vcodec_add_formats(V4L2_PIX_FMT_H264_SLICE, ctx); + out_format_count++; + } + if (ctx->dev->dec_capability & MTK_VDEC_FORMAT_VP8_FRAME) { + mtk_vcodec_add_formats(V4L2_PIX_FMT_VP8_FRAME, ctx); + out_format_count++; + } + if (ctx->dev->dec_capability & MTK_VDEC_FORMAT_VP9_FRAME) { + mtk_vcodec_add_formats(V4L2_PIX_FMT_VP9_FRAME, ctx); + out_format_count++; + } + + if (cap_format_count) + default_cap_format = mtk_video_formats[cap_format_count - 1]; + if (out_format_count) + default_out_format = + mtk_video_formats[cap_format_count + out_format_count - 1]; +} + static void mtk_init_vdec_params(struct mtk_vcodec_ctx *ctx) { struct vb2_queue *src_vq; @@ -314,6 +420,11 @@ static void mtk_init_vdec_params(struct mtk_vcodec_ctx *ctx) src_vq = v4l2_m2m_get_vq(ctx->m2m_ctx, V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE); + if (!ctx->dev->vdec_pdata->is_subdev_supported) + ctx->dev->dec_capability |= + MTK_VDEC_FORMAT_H264_SLICE | MTK_VDEC_FORMAT_MM21; + mtk_vcodec_get_supported_formats(ctx); + /* Support request api for output plane */ src_vq->supports_requests = true; src_vq->requires_requests = true; @@ -343,38 +454,59 @@ static struct vb2_ops mtk_vdec_request_vb2_ops = { }; const struct mtk_vcodec_dec_pdata mtk_vdec_8183_pdata = { - .chip = MTK_MT8183, .init_vdec_params = mtk_init_vdec_params, .ctrls_setup = mtk_vcodec_dec_ctrls_setup, .vdec_vb2_ops = &mtk_vdec_request_vb2_ops, .vdec_formats = mtk_video_formats, - .num_formats = NUM_FORMATS, - .default_out_fmt = &mtk_video_formats[DEFAULT_OUT_FMT_IDX], - .default_cap_fmt = &mtk_video_formats[DEFAULT_CAP_FMT_IDX], + .num_formats = &num_formats, + .default_out_fmt = &default_out_format, + .default_cap_fmt = &default_cap_format, .vdec_framesizes = mtk_vdec_framesizes, - .num_framesizes = NUM_SUPPORTED_FRAMESIZE, + .num_framesizes = &num_framesizes, .uses_stateless_api = true, .worker = mtk_vdec_worker, .flush_decoder = mtk_vdec_flush_decoder, + .cap_to_disp = mtk_vdec_stateless_cap_to_disp, + .get_cap_buffer = vdec_get_cap_buffer, .is_subdev_supported = false, .hw_arch = MTK_VDEC_PURE_SINGLE_CORE, }; /* This platform data is used for one lat and one core architecture. */ const struct mtk_vcodec_dec_pdata mtk_lat_sig_core_pdata = { - .chip = MTK_MT8192, .init_vdec_params = mtk_init_vdec_params, .ctrls_setup = mtk_vcodec_dec_ctrls_setup, .vdec_vb2_ops = &mtk_vdec_request_vb2_ops, .vdec_formats = mtk_video_formats, - .num_formats = NUM_FORMATS, - .default_out_fmt = &mtk_video_formats[DEFAULT_OUT_FMT_IDX], - .default_cap_fmt = &mtk_video_formats[DEFAULT_CAP_FMT_IDX], + .num_formats = &num_formats, + .default_out_fmt = &default_out_format, + .default_cap_fmt = &default_cap_format, .vdec_framesizes = mtk_vdec_framesizes, - .num_framesizes = NUM_SUPPORTED_FRAMESIZE, + .num_framesizes = &num_framesizes, .uses_stateless_api = true, .worker = mtk_vdec_worker, .flush_decoder = mtk_vdec_flush_decoder, + .cap_to_disp = mtk_vdec_stateless_cap_to_disp, + .get_cap_buffer = vdec_get_cap_buffer, .is_subdev_supported = true, .hw_arch = MTK_VDEC_LAT_SINGLE_CORE, }; + +const struct mtk_vcodec_dec_pdata mtk_vdec_single_core_pdata = { + .init_vdec_params = mtk_init_vdec_params, + .ctrls_setup = mtk_vcodec_dec_ctrls_setup, + .vdec_vb2_ops = &mtk_vdec_request_vb2_ops, + .vdec_formats = mtk_video_formats, + .num_formats = &num_formats, + .default_out_fmt = &default_out_format, + .default_cap_fmt = &default_cap_format, + .vdec_framesizes = mtk_vdec_framesizes, + .num_framesizes = &num_framesizes, + .uses_stateless_api = true, + .worker = mtk_vdec_worker, + .flush_decoder = mtk_vdec_flush_decoder, + .cap_to_disp = mtk_vdec_stateless_cap_to_disp, + .get_cap_buffer = vdec_get_cap_buffer, + .is_subdev_supported = true, + .hw_arch = MTK_VDEC_PURE_SINGLE_CORE, +}; diff --git a/drivers/media/platform/mediatek/vcodec/mtk_vcodec_drv.h b/drivers/media/platform/mediatek/vcodec/mtk_vcodec_drv.h index 813901c4be5e..a29041a0b7e0 100644 --- a/drivers/media/platform/mediatek/vcodec/mtk_vcodec_drv.h +++ b/drivers/media/platform/mediatek/vcodec/mtk_vcodec_drv.h @@ -274,6 +274,7 @@ struct vdec_pic_info { * to be used with encoder and stateful decoder. * @is_flushing: set to true if flushing is in progress. * @current_codec: current set input codec, in V4L2 pixel format + * @capture_fourcc: capture queue type in V4L2 pixel format * * @colorspace: enum v4l2_colorspace; supplemental to pixelformat * @ycbcr_enc: enum v4l2_ycbcr_encoding, Y'CbCr encoding @@ -284,6 +285,8 @@ struct vdec_pic_info { * mtk_video_dec_buf. * @hw_id: hardware index used to identify different hardware. * + * @max_width: hardware supported max width + * @max_height: hardware supported max height * @msg_queue: msg queue used to store lat buffer information. */ struct mtk_vcodec_ctx { @@ -319,6 +322,7 @@ struct mtk_vcodec_ctx { bool is_flushing; u32 current_codec; + u32 capture_fourcc; enum v4l2_colorspace colorspace; enum v4l2_ycbcr_encoding ycbcr_enc; @@ -329,16 +333,11 @@ struct mtk_vcodec_ctx { struct mutex lock; int hw_id; + unsigned int max_width; + unsigned int max_height; struct vdec_msg_queue msg_queue; }; -enum mtk_chip { - MTK_MT8173, - MTK_MT8183, - MTK_MT8192, - MTK_MT8195, -}; - /* * enum mtk_vdec_hw_arch - Used to separate different hardware architecture */ @@ -347,13 +346,26 @@ enum mtk_vdec_hw_arch { MTK_VDEC_LAT_SINGLE_CORE, }; +/* + * struct mtk_vdec_format_types - Structure used to get supported + * format types according to decoder capability + */ +enum mtk_vdec_format_types { + MTK_VDEC_FORMAT_MM21 = 0x20, + MTK_VDEC_FORMAT_MT21C = 0x40, + MTK_VDEC_FORMAT_H264_SLICE = 0x100, + MTK_VDEC_FORMAT_VP8_FRAME = 0x200, + MTK_VDEC_FORMAT_VP9_FRAME = 0x400, +}; + /** * struct mtk_vcodec_dec_pdata - compatible data for each IC * @init_vdec_params: init vdec params * @ctrls_setup: init vcodec dec ctrls * @worker: worker to start a decode job * @flush_decoder: function that flushes the decoder - * + * @get_cap_buffer: get capture buffer from capture queue + * @cap_to_disp: put capture buffer to disp list for lat and core arch * @vdec_vb2_ops: struct vb2_ops * * @vdec_formats: supported video decoder formats @@ -364,7 +376,6 @@ enum mtk_vdec_hw_arch { * @vdec_framesizes: supported video decoder frame sizes * @num_framesizes: count of video decoder frame sizes * - * @chip: chip this decoder is compatible with * @hw_arch: hardware arch is used to separate pure_sin_core and lat_sin_core * * @is_subdev_supported: whether support parent-node architecture(subdev) @@ -376,18 +387,20 @@ struct mtk_vcodec_dec_pdata { int (*ctrls_setup)(struct mtk_vcodec_ctx *ctx); void (*worker)(struct work_struct *work); int (*flush_decoder)(struct mtk_vcodec_ctx *ctx); + struct vdec_fb *(*get_cap_buffer)(struct mtk_vcodec_ctx *ctx); + void (*cap_to_disp)(struct mtk_vcodec_ctx *ctx, int error, + struct media_request *src_buf_req); struct vb2_ops *vdec_vb2_ops; const struct mtk_video_fmt *vdec_formats; - const int num_formats; + const int *num_formats; const struct mtk_video_fmt *default_out_fmt; const struct mtk_video_fmt *default_cap_fmt; const struct mtk_codec_framesizes *vdec_framesizes; - const int num_framesizes; + const int *num_framesizes; - enum mtk_chip chip; enum mtk_vdec_hw_arch hw_arch; bool is_subdev_supported; @@ -397,8 +410,6 @@ struct mtk_vcodec_dec_pdata { /** * struct mtk_vcodec_enc_pdata - compatible data for each IC * - * @chip: chip this encoder is compatible with - * * @uses_ext: whether the encoder uses the extended firmware messaging format * @min_bitrate: minimum supported encoding bitrate * @max_bitrate: maximum supported encoding bitrate @@ -409,8 +420,6 @@ struct mtk_vcodec_dec_pdata { * @core_id: stand for h264 or vp8 encode index */ struct mtk_vcodec_enc_pdata { - enum mtk_chip chip; - bool uses_ext; unsigned long min_bitrate; unsigned long max_bitrate; diff --git a/drivers/media/platform/mediatek/vcodec/mtk_vcodec_enc_drv.c b/drivers/media/platform/mediatek/vcodec/mtk_vcodec_enc_drv.c index 5172cfe0db4a..95e8c29ccc65 100644 --- a/drivers/media/platform/mediatek/vcodec/mtk_vcodec_enc_drv.c +++ b/drivers/media/platform/mediatek/vcodec/mtk_vcodec_enc_drv.c @@ -376,7 +376,6 @@ err_enc_pm: } static const struct mtk_vcodec_enc_pdata mt8173_avc_pdata = { - .chip = MTK_MT8173, .capture_formats = mtk_video_formats_capture_h264, .num_capture_formats = ARRAY_SIZE(mtk_video_formats_capture_h264), .output_formats = mtk_video_formats_output, @@ -387,7 +386,6 @@ static const struct mtk_vcodec_enc_pdata mt8173_avc_pdata = { }; static const struct mtk_vcodec_enc_pdata mt8173_vp8_pdata = { - .chip = MTK_MT8173, .capture_formats = mtk_video_formats_capture_vp8, .num_capture_formats = ARRAY_SIZE(mtk_video_formats_capture_vp8), .output_formats = mtk_video_formats_output, @@ -398,7 +396,6 @@ static const struct mtk_vcodec_enc_pdata mt8173_vp8_pdata = { }; static const struct mtk_vcodec_enc_pdata mt8183_pdata = { - .chip = MTK_MT8183, .uses_ext = true, .capture_formats = mtk_video_formats_capture_h264, .num_capture_formats = ARRAY_SIZE(mtk_video_formats_capture_h264), @@ -410,7 +407,6 @@ static const struct mtk_vcodec_enc_pdata mt8183_pdata = { }; static const struct mtk_vcodec_enc_pdata mt8192_pdata = { - .chip = MTK_MT8192, .uses_ext = true, .capture_formats = mtk_video_formats_capture_h264, .num_capture_formats = ARRAY_SIZE(mtk_video_formats_capture_h264), @@ -422,7 +418,6 @@ static const struct mtk_vcodec_enc_pdata mt8192_pdata = { }; static const struct mtk_vcodec_enc_pdata mt8195_pdata = { - .chip = MTK_MT8195, .uses_ext = true, .capture_formats = mtk_video_formats_capture_h264, .num_capture_formats = ARRAY_SIZE(mtk_video_formats_capture_h264), diff --git a/drivers/media/platform/mediatek/vcodec/mtk_vcodec_fw.c b/drivers/media/platform/mediatek/vcodec/mtk_vcodec_fw.c index 94b39ae5c2e1..556e54aadac9 100644 --- a/drivers/media/platform/mediatek/vcodec/mtk_vcodec_fw.c +++ b/drivers/media/platform/mediatek/vcodec/mtk_vcodec_fw.c @@ -65,3 +65,9 @@ int mtk_vcodec_fw_ipi_send(struct mtk_vcodec_fw *fw, int id, void *buf, return fw->ops->ipi_send(fw, id, buf, len, wait); } EXPORT_SYMBOL_GPL(mtk_vcodec_fw_ipi_send); + +int mtk_vcodec_fw_get_type(struct mtk_vcodec_fw *fw) +{ + return fw->type; +} +EXPORT_SYMBOL_GPL(mtk_vcodec_fw_get_type); diff --git a/drivers/media/platform/mediatek/vcodec/mtk_vcodec_fw.h b/drivers/media/platform/mediatek/vcodec/mtk_vcodec_fw.h index 15ab6b8e3ae2..16824114657f 100644 --- a/drivers/media/platform/mediatek/vcodec/mtk_vcodec_fw.h +++ b/drivers/media/platform/mediatek/vcodec/mtk_vcodec_fw.h @@ -39,5 +39,6 @@ int mtk_vcodec_fw_ipi_register(struct mtk_vcodec_fw *fw, int id, const char *name, void *priv); int mtk_vcodec_fw_ipi_send(struct mtk_vcodec_fw *fw, int id, void *buf, unsigned int len, unsigned int wait); +int mtk_vcodec_fw_get_type(struct mtk_vcodec_fw *fw); #endif /* _MTK_VCODEC_FW_H_ */ diff --git a/drivers/media/platform/mediatek/vcodec/vdec/vdec_h264_req_common.c b/drivers/media/platform/mediatek/vcodec/vdec/vdec_h264_req_common.c new file mode 100644 index 000000000000..ca628321d272 --- /dev/null +++ b/drivers/media/platform/mediatek/vcodec/vdec/vdec_h264_req_common.c @@ -0,0 +1,323 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2022 MediaTek Inc. + * Author: Yunfei Dong <yunfei.dong@mediatek.com> + */ + +#include "vdec_h264_req_common.h" + +/* get used parameters for sps/pps */ +#define GET_MTK_VDEC_FLAG(cond, flag) \ + { dst_param->cond = ((src_param->flags & flag) ? (1) : (0)); } +#define GET_MTK_VDEC_PARAM(param) \ + { dst_param->param = src_param->param; } + +void mtk_vdec_h264_get_ref_list(u8 *ref_list, + const struct v4l2_h264_reference *v4l2_ref_list, + int num_valid) +{ + u32 i; + + /* + * TODO The firmware does not support field decoding. Future + * implementation must use v4l2_ref_list[i].fields to obtain + * the reference field parity. + */ + + for (i = 0; i < num_valid; i++) + ref_list[i] = v4l2_ref_list[i].index; + + /* + * The firmware expects unused reflist entries to have the value 0x20. + */ + memset(&ref_list[num_valid], 0x20, 32 - num_valid); +} + +void *mtk_vdec_h264_get_ctrl_ptr(struct mtk_vcodec_ctx *ctx, int id) +{ + struct v4l2_ctrl *ctrl = v4l2_ctrl_find(&ctx->ctrl_hdl, id); + + if (!ctrl) + return ERR_PTR(-EINVAL); + + return ctrl->p_cur.p; +} + +void mtk_vdec_h264_fill_dpb_info(struct mtk_vcodec_ctx *ctx, + struct slice_api_h264_decode_param *decode_params, + struct mtk_h264_dpb_info *h264_dpb_info) +{ + const struct slice_h264_dpb_entry *dpb; + struct vb2_queue *vq; + struct vb2_buffer *vb; + struct vb2_v4l2_buffer *vb2_v4l2; + int index, vb2_index; + + vq = v4l2_m2m_get_vq(ctx->m2m_ctx, V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE); + + for (index = 0; index < V4L2_H264_NUM_DPB_ENTRIES; index++) { + dpb = &decode_params->dpb[index]; + if (!(dpb->flags & V4L2_H264_DPB_ENTRY_FLAG_ACTIVE)) { + h264_dpb_info[index].reference_flag = 0; + continue; + } + + vb2_index = vb2_find_timestamp(vq, dpb->reference_ts, 0); + if (vb2_index < 0) { + dev_err(&ctx->dev->plat_dev->dev, + "Reference invalid: dpb_index(%d) reference_ts(%lld)", + index, dpb->reference_ts); + continue; + } + + /* 1 for short term reference, 2 for long term reference */ + if (!(dpb->flags & V4L2_H264_DPB_ENTRY_FLAG_LONG_TERM)) + h264_dpb_info[index].reference_flag = 1; + else + h264_dpb_info[index].reference_flag = 2; + + vb = vq->bufs[vb2_index]; + vb2_v4l2 = container_of(vb, struct vb2_v4l2_buffer, vb2_buf); + h264_dpb_info[index].field = vb2_v4l2->field; + + h264_dpb_info[index].y_dma_addr = + vb2_dma_contig_plane_dma_addr(vb, 0); + if (ctx->q_data[MTK_Q_DATA_DST].fmt->num_planes == 2) + h264_dpb_info[index].c_dma_addr = + vb2_dma_contig_plane_dma_addr(vb, 1); + else + h264_dpb_info[index].c_dma_addr = + h264_dpb_info[index].y_dma_addr + + ctx->picinfo.fb_sz[0]; + } +} + +void mtk_vdec_h264_copy_sps_params(struct mtk_h264_sps_param *dst_param, + const struct v4l2_ctrl_h264_sps *src_param) +{ + GET_MTK_VDEC_PARAM(chroma_format_idc); + GET_MTK_VDEC_PARAM(bit_depth_luma_minus8); + GET_MTK_VDEC_PARAM(bit_depth_chroma_minus8); + GET_MTK_VDEC_PARAM(log2_max_frame_num_minus4); + GET_MTK_VDEC_PARAM(pic_order_cnt_type); + GET_MTK_VDEC_PARAM(log2_max_pic_order_cnt_lsb_minus4); + GET_MTK_VDEC_PARAM(max_num_ref_frames); + GET_MTK_VDEC_PARAM(pic_width_in_mbs_minus1); + GET_MTK_VDEC_PARAM(pic_height_in_map_units_minus1); + + GET_MTK_VDEC_FLAG(separate_colour_plane_flag, + V4L2_H264_SPS_FLAG_SEPARATE_COLOUR_PLANE); + GET_MTK_VDEC_FLAG(qpprime_y_zero_transform_bypass_flag, + V4L2_H264_SPS_FLAG_QPPRIME_Y_ZERO_TRANSFORM_BYPASS); + GET_MTK_VDEC_FLAG(delta_pic_order_always_zero_flag, + V4L2_H264_SPS_FLAG_DELTA_PIC_ORDER_ALWAYS_ZERO); + GET_MTK_VDEC_FLAG(frame_mbs_only_flag, + V4L2_H264_SPS_FLAG_FRAME_MBS_ONLY); + GET_MTK_VDEC_FLAG(mb_adaptive_frame_field_flag, + V4L2_H264_SPS_FLAG_MB_ADAPTIVE_FRAME_FIELD); + GET_MTK_VDEC_FLAG(direct_8x8_inference_flag, + V4L2_H264_SPS_FLAG_DIRECT_8X8_INFERENCE); +} + +void mtk_vdec_h264_copy_pps_params(struct mtk_h264_pps_param *dst_param, + const struct v4l2_ctrl_h264_pps *src_param) +{ + GET_MTK_VDEC_PARAM(num_ref_idx_l0_default_active_minus1); + GET_MTK_VDEC_PARAM(num_ref_idx_l1_default_active_minus1); + GET_MTK_VDEC_PARAM(weighted_bipred_idc); + GET_MTK_VDEC_PARAM(pic_init_qp_minus26); + GET_MTK_VDEC_PARAM(chroma_qp_index_offset); + GET_MTK_VDEC_PARAM(second_chroma_qp_index_offset); + + GET_MTK_VDEC_FLAG(entropy_coding_mode_flag, + V4L2_H264_PPS_FLAG_ENTROPY_CODING_MODE); + GET_MTK_VDEC_FLAG(pic_order_present_flag, + V4L2_H264_PPS_FLAG_BOTTOM_FIELD_PIC_ORDER_IN_FRAME_PRESENT); + GET_MTK_VDEC_FLAG(weighted_pred_flag, + V4L2_H264_PPS_FLAG_WEIGHTED_PRED); + GET_MTK_VDEC_FLAG(deblocking_filter_control_present_flag, + V4L2_H264_PPS_FLAG_DEBLOCKING_FILTER_CONTROL_PRESENT); + GET_MTK_VDEC_FLAG(constrained_intra_pred_flag, + V4L2_H264_PPS_FLAG_CONSTRAINED_INTRA_PRED); + GET_MTK_VDEC_FLAG(redundant_pic_cnt_present_flag, + V4L2_H264_PPS_FLAG_REDUNDANT_PIC_CNT_PRESENT); + GET_MTK_VDEC_FLAG(transform_8x8_mode_flag, + V4L2_H264_PPS_FLAG_TRANSFORM_8X8_MODE); + GET_MTK_VDEC_FLAG(scaling_matrix_present_flag, + V4L2_H264_PPS_FLAG_SCALING_MATRIX_PRESENT); +} + +void mtk_vdec_h264_copy_slice_hd_params(struct mtk_h264_slice_hd_param *dst_param, + const struct v4l2_ctrl_h264_slice_params *src_param, + const struct v4l2_ctrl_h264_decode_params *dec_param) +{ + int temp; + + GET_MTK_VDEC_PARAM(first_mb_in_slice); + GET_MTK_VDEC_PARAM(slice_type); + GET_MTK_VDEC_PARAM(cabac_init_idc); + GET_MTK_VDEC_PARAM(slice_qp_delta); + GET_MTK_VDEC_PARAM(disable_deblocking_filter_idc); + GET_MTK_VDEC_PARAM(slice_alpha_c0_offset_div2); + GET_MTK_VDEC_PARAM(slice_beta_offset_div2); + GET_MTK_VDEC_PARAM(num_ref_idx_l0_active_minus1); + GET_MTK_VDEC_PARAM(num_ref_idx_l1_active_minus1); + + dst_param->frame_num = dec_param->frame_num; + dst_param->pic_order_cnt_lsb = dec_param->pic_order_cnt_lsb; + + dst_param->delta_pic_order_cnt_bottom = + dec_param->delta_pic_order_cnt_bottom; + dst_param->delta_pic_order_cnt0 = + dec_param->delta_pic_order_cnt0; + dst_param->delta_pic_order_cnt1 = + dec_param->delta_pic_order_cnt1; + + temp = dec_param->flags & V4L2_H264_DECODE_PARAM_FLAG_FIELD_PIC; + dst_param->field_pic_flag = temp ? 1 : 0; + + temp = dec_param->flags & V4L2_H264_DECODE_PARAM_FLAG_BOTTOM_FIELD; + dst_param->bottom_field_flag = temp ? 1 : 0; + + GET_MTK_VDEC_FLAG(direct_spatial_mv_pred_flag, + V4L2_H264_SLICE_FLAG_DIRECT_SPATIAL_MV_PRED); +} + +void mtk_vdec_h264_copy_scaling_matrix(struct slice_api_h264_scaling_matrix *dst_matrix, + const struct v4l2_ctrl_h264_scaling_matrix *src_matrix) +{ + memcpy(dst_matrix->scaling_list_4x4, src_matrix->scaling_list_4x4, + sizeof(dst_matrix->scaling_list_4x4)); + + memcpy(dst_matrix->scaling_list_8x8, src_matrix->scaling_list_8x8, + sizeof(dst_matrix->scaling_list_8x8)); +} + +void +mtk_vdec_h264_copy_decode_params(struct slice_api_h264_decode_param *dst_params, + const struct v4l2_ctrl_h264_decode_params *src_params, + const struct v4l2_h264_dpb_entry dpb[V4L2_H264_NUM_DPB_ENTRIES]) +{ + struct slice_h264_dpb_entry *dst_entry; + const struct v4l2_h264_dpb_entry *src_entry; + int i; + + for (i = 0; i < ARRAY_SIZE(dst_params->dpb); i++) { + dst_entry = &dst_params->dpb[i]; + src_entry = &dpb[i]; + + dst_entry->reference_ts = src_entry->reference_ts; + dst_entry->frame_num = src_entry->frame_num; + dst_entry->pic_num = src_entry->pic_num; + dst_entry->top_field_order_cnt = src_entry->top_field_order_cnt; + dst_entry->bottom_field_order_cnt = + src_entry->bottom_field_order_cnt; + dst_entry->flags = src_entry->flags; + } + + /* num_slices is a leftover from the old H.264 support and is ignored + * by the firmware. + */ + dst_params->num_slices = 0; + dst_params->nal_ref_idc = src_params->nal_ref_idc; + dst_params->top_field_order_cnt = src_params->top_field_order_cnt; + dst_params->bottom_field_order_cnt = src_params->bottom_field_order_cnt; + dst_params->flags = src_params->flags; +} + +static bool mtk_vdec_h264_dpb_entry_match(const struct v4l2_h264_dpb_entry *a, + const struct v4l2_h264_dpb_entry *b) +{ + return a->top_field_order_cnt == b->top_field_order_cnt && + a->bottom_field_order_cnt == b->bottom_field_order_cnt; +} + +/* + * Move DPB entries of dec_param that refer to a frame already existing in dpb + * into the already existing slot in dpb, and move other entries into new slots. + * + * This function is an adaptation of the similarly-named function in + * hantro_h264.c. + */ +void mtk_vdec_h264_update_dpb(const struct v4l2_ctrl_h264_decode_params *dec_param, + struct v4l2_h264_dpb_entry *dpb) +{ + DECLARE_BITMAP(new, ARRAY_SIZE(dec_param->dpb)) = { 0, }; + DECLARE_BITMAP(in_use, ARRAY_SIZE(dec_param->dpb)) = { 0, }; + DECLARE_BITMAP(used, ARRAY_SIZE(dec_param->dpb)) = { 0, }; + unsigned int i, j; + + /* Disable all entries by default, and mark the ones in use. */ + for (i = 0; i < ARRAY_SIZE(dec_param->dpb); i++) { + if (dpb[i].flags & V4L2_H264_DPB_ENTRY_FLAG_ACTIVE) + set_bit(i, in_use); + dpb[i].flags &= ~V4L2_H264_DPB_ENTRY_FLAG_ACTIVE; + } + + /* Try to match new DPB entries with existing ones by their POCs. */ + for (i = 0; i < ARRAY_SIZE(dec_param->dpb); i++) { + const struct v4l2_h264_dpb_entry *ndpb = &dec_param->dpb[i]; + + if (!(ndpb->flags & V4L2_H264_DPB_ENTRY_FLAG_ACTIVE)) + continue; + + /* + * To cut off some comparisons, iterate only on target DPB + * entries were already used. + */ + for_each_set_bit(j, in_use, ARRAY_SIZE(dec_param->dpb)) { + struct v4l2_h264_dpb_entry *cdpb; + + cdpb = &dpb[j]; + if (!mtk_vdec_h264_dpb_entry_match(cdpb, ndpb)) + continue; + + *cdpb = *ndpb; + set_bit(j, used); + /* Don't reiterate on this one. */ + clear_bit(j, in_use); + break; + } + + if (j == ARRAY_SIZE(dec_param->dpb)) + set_bit(i, new); + } + + /* For entries that could not be matched, use remaining free slots. */ + for_each_set_bit(i, new, ARRAY_SIZE(dec_param->dpb)) { + const struct v4l2_h264_dpb_entry *ndpb = &dec_param->dpb[i]; + struct v4l2_h264_dpb_entry *cdpb; + + /* + * Both arrays are of the same sizes, so there is no way + * we can end up with no space in target array, unless + * something is buggy. + */ + j = find_first_zero_bit(used, ARRAY_SIZE(dec_param->dpb)); + if (WARN_ON(j >= ARRAY_SIZE(dec_param->dpb))) + return; + + cdpb = &dpb[j]; + *cdpb = *ndpb; + set_bit(j, used); + } +} + +unsigned int mtk_vdec_h264_get_mv_buf_size(unsigned int width, unsigned int height) +{ + int unit_size = (width / MB_UNIT_LEN) * (height / MB_UNIT_LEN) + 8; + + return HW_MB_STORE_SZ * unit_size; +} + +int mtk_vdec_h264_find_start_code(unsigned char *data, unsigned int data_sz) +{ + if (data_sz > 3 && data[0] == 0 && data[1] == 0 && data[2] == 1) + return 3; + + if (data_sz > 4 && data[0] == 0 && data[1] == 0 && data[2] == 0 && + data[3] == 1) + return 4; + + return -1; +} diff --git a/drivers/media/platform/mediatek/vcodec/vdec/vdec_h264_req_common.h b/drivers/media/platform/mediatek/vcodec/vdec/vdec_h264_req_common.h new file mode 100644 index 000000000000..53d0a7c962a9 --- /dev/null +++ b/drivers/media/platform/mediatek/vcodec/vdec/vdec_h264_req_common.h @@ -0,0 +1,277 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2022 MediaTek Inc. + * Author: Yunfei Dong <yunfei.dong@mediatek.com> + */ + +#ifndef _VDEC_H264_REQ_COMMON_H_ +#define _VDEC_H264_REQ_COMMON_H_ + +#include <linux/module.h> +#include <linux/slab.h> +#include <media/v4l2-h264.h> +#include <media/v4l2-mem2mem.h> +#include <media/videobuf2-dma-contig.h> + +#include "../mtk_vcodec_drv.h" + +#define NAL_NON_IDR_SLICE 0x01 +#define NAL_IDR_SLICE 0x05 +#define NAL_TYPE(value) ((value) & 0x1F) + +#define BUF_PREDICTION_SZ (64 * 4096) +#define MB_UNIT_LEN 16 + +/* motion vector size (bytes) for every macro block */ +#define HW_MB_STORE_SZ 64 + +#define H264_MAX_MV_NUM 32 + +/** + * struct mtk_h264_dpb_info - h264 dpb information + * + * @y_dma_addr: Y bitstream physical address + * @c_dma_addr: CbCr bitstream physical address + * @reference_flag: reference picture flag (short/long term reference picture) + * @field: field picture flag + */ +struct mtk_h264_dpb_info { + dma_addr_t y_dma_addr; + dma_addr_t c_dma_addr; + int reference_flag; + int field; +}; + +/* + * struct mtk_h264_sps_param - parameters for sps + */ +struct mtk_h264_sps_param { + unsigned char chroma_format_idc; + unsigned char bit_depth_luma_minus8; + unsigned char bit_depth_chroma_minus8; + unsigned char log2_max_frame_num_minus4; + unsigned char pic_order_cnt_type; + unsigned char log2_max_pic_order_cnt_lsb_minus4; + unsigned char max_num_ref_frames; + unsigned char separate_colour_plane_flag; + unsigned short pic_width_in_mbs_minus1; + unsigned short pic_height_in_map_units_minus1; + unsigned int max_frame_nums; + unsigned char qpprime_y_zero_transform_bypass_flag; + unsigned char delta_pic_order_always_zero_flag; + unsigned char frame_mbs_only_flag; + unsigned char mb_adaptive_frame_field_flag; + unsigned char direct_8x8_inference_flag; + unsigned char reserved[3]; +}; + +/* + * struct mtk_h264_pps_param - parameters for pps + */ +struct mtk_h264_pps_param { + unsigned char num_ref_idx_l0_default_active_minus1; + unsigned char num_ref_idx_l1_default_active_minus1; + unsigned char weighted_bipred_idc; + char pic_init_qp_minus26; + char chroma_qp_index_offset; + char second_chroma_qp_index_offset; + unsigned char entropy_coding_mode_flag; + unsigned char pic_order_present_flag; + unsigned char deblocking_filter_control_present_flag; + unsigned char constrained_intra_pred_flag; + unsigned char weighted_pred_flag; + unsigned char redundant_pic_cnt_present_flag; + unsigned char transform_8x8_mode_flag; + unsigned char scaling_matrix_present_flag; + unsigned char reserved[2]; +}; + +/* + * struct mtk_h264_slice_hd_param - parameters for slice header + */ +struct mtk_h264_slice_hd_param { + unsigned int first_mb_in_slice; + unsigned int field_pic_flag; + unsigned int slice_type; + unsigned int frame_num; + int pic_order_cnt_lsb; + int delta_pic_order_cnt_bottom; + unsigned int bottom_field_flag; + unsigned int direct_spatial_mv_pred_flag; + int delta_pic_order_cnt0; + int delta_pic_order_cnt1; + unsigned int cabac_init_idc; + int slice_qp_delta; + unsigned int disable_deblocking_filter_idc; + int slice_alpha_c0_offset_div2; + int slice_beta_offset_div2; + unsigned int num_ref_idx_l0_active_minus1; + unsigned int num_ref_idx_l1_active_minus1; + unsigned int reserved; +}; + +/* + * struct slice_api_h264_scaling_matrix - parameters for scaling list + */ +struct slice_api_h264_scaling_matrix { + unsigned char scaling_list_4x4[6][16]; + unsigned char scaling_list_8x8[6][64]; +}; + +/* + * struct slice_h264_dpb_entry - each dpb information + */ +struct slice_h264_dpb_entry { + unsigned long long reference_ts; + unsigned short frame_num; + unsigned short pic_num; + /* Note that field is indicated by v4l2_buffer.field */ + int top_field_order_cnt; + int bottom_field_order_cnt; + unsigned int flags; +}; + +/* + * struct slice_api_h264_decode_param - parameters for decode. + */ +struct slice_api_h264_decode_param { + struct slice_h264_dpb_entry dpb[V4L2_H264_NUM_DPB_ENTRIES]; + unsigned short num_slices; + unsigned short nal_ref_idc; + unsigned char ref_pic_list_p0[32]; + unsigned char ref_pic_list_b0[32]; + unsigned char ref_pic_list_b1[32]; + int top_field_order_cnt; + int bottom_field_order_cnt; + unsigned int flags; +}; + +/** + * struct h264_fb - h264 decode frame buffer information + * + * @vdec_fb_va: virtual address of struct vdec_fb + * @y_fb_dma: dma address of Y frame buffer (luma) + * @c_fb_dma: dma address of C frame buffer (chroma) + * @poc: picture order count of frame buffer + * @reserved: for 8 bytes alignment + */ +struct h264_fb { + u64 vdec_fb_va; + u64 y_fb_dma; + u64 c_fb_dma; + s32 poc; + u32 reserved; +}; + +/** + * mtk_vdec_h264_get_ref_list - translate V4L2 reference list + * + * @ref_list: Mediatek reference picture list + * @v4l2_ref_list: V4L2 reference picture list + * @num_valid: used reference number + */ +void mtk_vdec_h264_get_ref_list(u8 *ref_list, + const struct v4l2_h264_reference *v4l2_ref_list, + int num_valid); + +/** + * mtk_vdec_h264_get_ctrl_ptr - get each CID contrl address. + * + * @ctx: v4l2 ctx + * @id: CID control ID + * + * Return: returns CID ctrl address. + */ +void *mtk_vdec_h264_get_ctrl_ptr(struct mtk_vcodec_ctx *ctx, int id); + +/** + * mtk_vdec_h264_fill_dpb_info - get each CID contrl address. + * + * @ctx: v4l2 ctx + * @decode_params: slice decode params + * @h264_dpb_info: dpb buffer information + */ +void mtk_vdec_h264_fill_dpb_info(struct mtk_vcodec_ctx *ctx, + struct slice_api_h264_decode_param *decode_params, + struct mtk_h264_dpb_info *h264_dpb_info); + +/** + * mtk_vdec_h264_copy_sps_params - get sps params. + * + * @dst_param: sps params for hw decoder + * @src_param: sps params from user driver + */ +void mtk_vdec_h264_copy_sps_params(struct mtk_h264_sps_param *dst_param, + const struct v4l2_ctrl_h264_sps *src_param); + +/** + * mtk_vdec_h264_copy_pps_params - get pps params. + * + * @dst_param: pps params for hw decoder + * @src_param: pps params from user driver + */ +void mtk_vdec_h264_copy_pps_params(struct mtk_h264_pps_param *dst_param, + const struct v4l2_ctrl_h264_pps *src_param); + +/** + * mtk_vdec_h264_copy_slice_hd_params - get slice header params. + * + * @dst_param: slice params for hw decoder + * @src_param: slice params from user driver + * @dec_param: decode params from user driver + */ +void mtk_vdec_h264_copy_slice_hd_params(struct mtk_h264_slice_hd_param *dst_param, + const struct v4l2_ctrl_h264_slice_params *src_param, + const struct v4l2_ctrl_h264_decode_params *dec_param); + +/** + * mtk_vdec_h264_copy_scaling_matrix - get each CID contrl address. + * + * @dst_matrix: scaling list params for hw decoder + * @src_matrix: scaling list params from user driver + */ +void mtk_vdec_h264_copy_scaling_matrix(struct slice_api_h264_scaling_matrix *dst_matrix, + const struct v4l2_ctrl_h264_scaling_matrix *src_matrix); + +/** + * mtk_vdec_h264_copy_decode_params - get decode params. + * + * @dst_params: dst params for hw decoder + * @src_params: decode params from user driver + * @dpb: dpb information + */ +void +mtk_vdec_h264_copy_decode_params(struct slice_api_h264_decode_param *dst_params, + const struct v4l2_ctrl_h264_decode_params *src_params, + const struct v4l2_h264_dpb_entry dpb[V4L2_H264_NUM_DPB_ENTRIES]); + +/** + * mtk_vdec_h264_update_dpb - updata dpb list. + * + * @dec_param: v4l2 control decode params + * @dpb: dpb entry informaton + */ +void mtk_vdec_h264_update_dpb(const struct v4l2_ctrl_h264_decode_params *dec_param, + struct v4l2_h264_dpb_entry *dpb); + +/** + * mtk_vdec_h264_find_start_code - find h264 start code using sofeware. + * + * @data: input buffer address + * @data_sz: input buffer size + * + * Return: returns start code position. + */ +int mtk_vdec_h264_find_start_code(unsigned char *data, unsigned int data_sz); + +/** + * mtk_vdec_h264_get_mv_buf_size - get mv buffer size. + * + * @width: picture width + * @height: picture height + * + * Return: returns mv buffer size. + */ +unsigned int mtk_vdec_h264_get_mv_buf_size(unsigned int width, unsigned int height); + +#endif diff --git a/drivers/media/platform/mediatek/vcodec/vdec/vdec_h264_req_if.c b/drivers/media/platform/mediatek/vcodec/vdec/vdec_h264_req_if.c index 43542de11e9c..4bc05ab5afea 100644 --- a/drivers/media/platform/mediatek/vcodec/vdec/vdec_h264_req_if.c +++ b/drivers/media/platform/mediatek/vcodec/vdec/vdec_h264_req_if.c @@ -12,109 +12,7 @@ #include "../vdec_drv_base.h" #include "../vdec_drv_if.h" #include "../vdec_vpu_if.h" - -#define BUF_PREDICTION_SZ (64 * 4096) -#define MB_UNIT_LEN 16 - -/* get used parameters for sps/pps */ -#define GET_MTK_VDEC_FLAG(cond, flag) \ - { dst_param->cond = ((src_param->flags & (flag)) ? (1) : (0)); } -#define GET_MTK_VDEC_PARAM(param) \ - { dst_param->param = src_param->param; } -/* motion vector size (bytes) for every macro block */ -#define HW_MB_STORE_SZ 64 - -#define H264_MAX_FB_NUM 17 -#define H264_MAX_MV_NUM 32 -#define HDR_PARSING_BUF_SZ 1024 - -/** - * struct mtk_h264_dpb_info - h264 dpb information - * @y_dma_addr: Y bitstream physical address - * @c_dma_addr: CbCr bitstream physical address - * @reference_flag: reference picture flag (short/long term reference picture) - * @field: field picture flag - */ -struct mtk_h264_dpb_info { - dma_addr_t y_dma_addr; - dma_addr_t c_dma_addr; - int reference_flag; - int field; -}; - -/* - * struct mtk_h264_sps_param - parameters for sps - */ -struct mtk_h264_sps_param { - unsigned char chroma_format_idc; - unsigned char bit_depth_luma_minus8; - unsigned char bit_depth_chroma_minus8; - unsigned char log2_max_frame_num_minus4; - unsigned char pic_order_cnt_type; - unsigned char log2_max_pic_order_cnt_lsb_minus4; - unsigned char max_num_ref_frames; - unsigned char separate_colour_plane_flag; - unsigned short pic_width_in_mbs_minus1; - unsigned short pic_height_in_map_units_minus1; - unsigned int max_frame_nums; - unsigned char qpprime_y_zero_transform_bypass_flag; - unsigned char delta_pic_order_always_zero_flag; - unsigned char frame_mbs_only_flag; - unsigned char mb_adaptive_frame_field_flag; - unsigned char direct_8x8_inference_flag; - unsigned char reserved[3]; -}; - -/* - * struct mtk_h264_pps_param - parameters for pps - */ -struct mtk_h264_pps_param { - unsigned char num_ref_idx_l0_default_active_minus1; - unsigned char num_ref_idx_l1_default_active_minus1; - unsigned char weighted_bipred_idc; - char pic_init_qp_minus26; - char chroma_qp_index_offset; - char second_chroma_qp_index_offset; - unsigned char entropy_coding_mode_flag; - unsigned char pic_order_present_flag; - unsigned char deblocking_filter_control_present_flag; - unsigned char constrained_intra_pred_flag; - unsigned char weighted_pred_flag; - unsigned char redundant_pic_cnt_present_flag; - unsigned char transform_8x8_mode_flag; - unsigned char scaling_matrix_present_flag; - unsigned char reserved[2]; -}; - -struct slice_api_h264_scaling_matrix { - unsigned char scaling_list_4x4[6][16]; - unsigned char scaling_list_8x8[6][64]; -}; - -struct slice_h264_dpb_entry { - unsigned long long reference_ts; - unsigned short frame_num; - unsigned short pic_num; - /* Note that field is indicated by v4l2_buffer.field */ - int top_field_order_cnt; - int bottom_field_order_cnt; - unsigned int flags; /* V4L2_H264_DPB_ENTRY_FLAG_* */ -}; - -/* - * struct slice_api_h264_decode_param - parameters for decode. - */ -struct slice_api_h264_decode_param { - struct slice_h264_dpb_entry dpb[16]; - unsigned short num_slices; - unsigned short nal_ref_idc; - unsigned char ref_pic_list_p0[32]; - unsigned char ref_pic_list_b0[32]; - unsigned char ref_pic_list_b1[32]; - int top_field_order_cnt; - int bottom_field_order_cnt; - unsigned int flags; /* V4L2_H264_DECODE_PARAM_FLAG_* */ -}; +#include "vdec_h264_req_common.h" /* * struct mtk_h264_dec_slice_param - parameters for decode current frame @@ -128,22 +26,6 @@ struct mtk_h264_dec_slice_param { }; /** - * struct h264_fb - h264 decode frame buffer information - * @vdec_fb_va : virtual address of struct vdec_fb - * @y_fb_dma : dma address of Y frame buffer (luma) - * @c_fb_dma : dma address of C frame buffer (chroma) - * @poc : picture order count of frame buffer - * @reserved : for 8 bytes alignment - */ -struct h264_fb { - u64 vdec_fb_va; - u64 y_fb_dma; - u64 c_fb_dma; - s32 poc; - u32 reserved; -}; - -/** * struct vdec_h264_dec_info - decode information * @dpb_sz : decoding picture buffer size * @resolution_changed : resoltion change happen @@ -212,285 +94,65 @@ struct vdec_h264_slice_inst { struct v4l2_h264_dpb_entry dpb[16]; }; -static void *get_ctrl_ptr(struct mtk_vcodec_ctx *ctx, int id) -{ - struct v4l2_ctrl *ctrl = v4l2_ctrl_find(&ctx->ctrl_hdl, id); - - return ctrl->p_cur.p; -} - -static void get_h264_dpb_list(struct vdec_h264_slice_inst *inst, - struct mtk_h264_dec_slice_param *slice_param) -{ - struct vb2_queue *vq; - struct vb2_buffer *vb; - struct vb2_v4l2_buffer *vb2_v4l2; - u64 index; - - vq = v4l2_m2m_get_vq(inst->ctx->m2m_ctx, V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE); - - for (index = 0; index < ARRAY_SIZE(slice_param->decode_params.dpb); index++) { - const struct slice_h264_dpb_entry *dpb; - int vb2_index; - - dpb = &slice_param->decode_params.dpb[index]; - if (!(dpb->flags & V4L2_H264_DPB_ENTRY_FLAG_ACTIVE)) { - slice_param->h264_dpb_info[index].reference_flag = 0; - continue; - } - - vb2_index = vb2_find_timestamp(vq, dpb->reference_ts, 0); - if (vb2_index < 0) { - mtk_vcodec_err(inst, "Reference invalid: dpb_index(%lld) reference_ts(%lld)", - index, dpb->reference_ts); - continue; - } - /* 1 for short term reference, 2 for long term reference */ - if (!(dpb->flags & V4L2_H264_DPB_ENTRY_FLAG_LONG_TERM)) - slice_param->h264_dpb_info[index].reference_flag = 1; - else - slice_param->h264_dpb_info[index].reference_flag = 2; - - vb = vq->bufs[vb2_index]; - vb2_v4l2 = container_of(vb, struct vb2_v4l2_buffer, vb2_buf); - slice_param->h264_dpb_info[index].field = vb2_v4l2->field; - - slice_param->h264_dpb_info[index].y_dma_addr = - vb2_dma_contig_plane_dma_addr(vb, 0); - if (inst->ctx->q_data[MTK_Q_DATA_DST].fmt->num_planes == 2) { - slice_param->h264_dpb_info[index].c_dma_addr = - vb2_dma_contig_plane_dma_addr(vb, 1); - } - } -} - -static void get_h264_sps_parameters(struct mtk_h264_sps_param *dst_param, - const struct v4l2_ctrl_h264_sps *src_param) -{ - GET_MTK_VDEC_PARAM(chroma_format_idc); - GET_MTK_VDEC_PARAM(bit_depth_luma_minus8); - GET_MTK_VDEC_PARAM(bit_depth_chroma_minus8); - GET_MTK_VDEC_PARAM(log2_max_frame_num_minus4); - GET_MTK_VDEC_PARAM(pic_order_cnt_type); - GET_MTK_VDEC_PARAM(log2_max_pic_order_cnt_lsb_minus4); - GET_MTK_VDEC_PARAM(max_num_ref_frames); - GET_MTK_VDEC_PARAM(pic_width_in_mbs_minus1); - GET_MTK_VDEC_PARAM(pic_height_in_map_units_minus1); - - GET_MTK_VDEC_FLAG(separate_colour_plane_flag, - V4L2_H264_SPS_FLAG_SEPARATE_COLOUR_PLANE); - GET_MTK_VDEC_FLAG(qpprime_y_zero_transform_bypass_flag, - V4L2_H264_SPS_FLAG_QPPRIME_Y_ZERO_TRANSFORM_BYPASS); - GET_MTK_VDEC_FLAG(delta_pic_order_always_zero_flag, - V4L2_H264_SPS_FLAG_DELTA_PIC_ORDER_ALWAYS_ZERO); - GET_MTK_VDEC_FLAG(frame_mbs_only_flag, - V4L2_H264_SPS_FLAG_FRAME_MBS_ONLY); - GET_MTK_VDEC_FLAG(mb_adaptive_frame_field_flag, - V4L2_H264_SPS_FLAG_MB_ADAPTIVE_FRAME_FIELD); - GET_MTK_VDEC_FLAG(direct_8x8_inference_flag, - V4L2_H264_SPS_FLAG_DIRECT_8X8_INFERENCE); -} - -static void get_h264_pps_parameters(struct mtk_h264_pps_param *dst_param, - const struct v4l2_ctrl_h264_pps *src_param) -{ - GET_MTK_VDEC_PARAM(num_ref_idx_l0_default_active_minus1); - GET_MTK_VDEC_PARAM(num_ref_idx_l1_default_active_minus1); - GET_MTK_VDEC_PARAM(weighted_bipred_idc); - GET_MTK_VDEC_PARAM(pic_init_qp_minus26); - GET_MTK_VDEC_PARAM(chroma_qp_index_offset); - GET_MTK_VDEC_PARAM(second_chroma_qp_index_offset); - - GET_MTK_VDEC_FLAG(entropy_coding_mode_flag, - V4L2_H264_PPS_FLAG_ENTROPY_CODING_MODE); - GET_MTK_VDEC_FLAG(pic_order_present_flag, - V4L2_H264_PPS_FLAG_BOTTOM_FIELD_PIC_ORDER_IN_FRAME_PRESENT); - GET_MTK_VDEC_FLAG(weighted_pred_flag, - V4L2_H264_PPS_FLAG_WEIGHTED_PRED); - GET_MTK_VDEC_FLAG(deblocking_filter_control_present_flag, - V4L2_H264_PPS_FLAG_DEBLOCKING_FILTER_CONTROL_PRESENT); - GET_MTK_VDEC_FLAG(constrained_intra_pred_flag, - V4L2_H264_PPS_FLAG_CONSTRAINED_INTRA_PRED); - GET_MTK_VDEC_FLAG(redundant_pic_cnt_present_flag, - V4L2_H264_PPS_FLAG_REDUNDANT_PIC_CNT_PRESENT); - GET_MTK_VDEC_FLAG(transform_8x8_mode_flag, - V4L2_H264_PPS_FLAG_TRANSFORM_8X8_MODE); - GET_MTK_VDEC_FLAG(scaling_matrix_present_flag, - V4L2_H264_PPS_FLAG_SCALING_MATRIX_PRESENT); -} - -static void -get_h264_scaling_matrix(struct slice_api_h264_scaling_matrix *dst_matrix, - const struct v4l2_ctrl_h264_scaling_matrix *src_matrix) +static int get_vdec_decode_parameters(struct vdec_h264_slice_inst *inst) { - memcpy(dst_matrix->scaling_list_4x4, src_matrix->scaling_list_4x4, - sizeof(dst_matrix->scaling_list_4x4)); - - memcpy(dst_matrix->scaling_list_8x8, src_matrix->scaling_list_8x8, - sizeof(dst_matrix->scaling_list_8x8)); -} - -static void -get_h264_decode_parameters(struct slice_api_h264_decode_param *dst_params, - const struct v4l2_ctrl_h264_decode_params *src_params, - const struct v4l2_h264_dpb_entry dpb[V4L2_H264_NUM_DPB_ENTRIES]) -{ - int i; - - for (i = 0; i < ARRAY_SIZE(dst_params->dpb); i++) { - struct slice_h264_dpb_entry *dst_entry = &dst_params->dpb[i]; - const struct v4l2_h264_dpb_entry *src_entry = &dpb[i]; - - dst_entry->reference_ts = src_entry->reference_ts; - dst_entry->frame_num = src_entry->frame_num; - dst_entry->pic_num = src_entry->pic_num; - dst_entry->top_field_order_cnt = src_entry->top_field_order_cnt; - dst_entry->bottom_field_order_cnt = - src_entry->bottom_field_order_cnt; - dst_entry->flags = src_entry->flags; - } - - /* - * num_slices is a leftover from the old H.264 support and is ignored - * by the firmware. - */ - dst_params->num_slices = 0; - dst_params->nal_ref_idc = src_params->nal_ref_idc; - dst_params->top_field_order_cnt = src_params->top_field_order_cnt; - dst_params->bottom_field_order_cnt = src_params->bottom_field_order_cnt; - dst_params->flags = src_params->flags; -} - -static bool dpb_entry_match(const struct v4l2_h264_dpb_entry *a, - const struct v4l2_h264_dpb_entry *b) -{ - return a->top_field_order_cnt == b->top_field_order_cnt && - a->bottom_field_order_cnt == b->bottom_field_order_cnt; -} - -/* - * Move DPB entries of dec_param that refer to a frame already existing in dpb - * into the already existing slot in dpb, and move other entries into new slots. - * - * This function is an adaptation of the similarly-named function in - * hantro_h264.c. - */ -static void update_dpb(const struct v4l2_ctrl_h264_decode_params *dec_param, - struct v4l2_h264_dpb_entry *dpb) -{ - DECLARE_BITMAP(new, ARRAY_SIZE(dec_param->dpb)) = { 0, }; - DECLARE_BITMAP(in_use, ARRAY_SIZE(dec_param->dpb)) = { 0, }; - DECLARE_BITMAP(used, ARRAY_SIZE(dec_param->dpb)) = { 0, }; - unsigned int i, j; - - /* Disable all entries by default, and mark the ones in use. */ - for (i = 0; i < ARRAY_SIZE(dec_param->dpb); i++) { - if (dpb[i].flags & V4L2_H264_DPB_ENTRY_FLAG_ACTIVE) - set_bit(i, in_use); - dpb[i].flags &= ~V4L2_H264_DPB_ENTRY_FLAG_ACTIVE; - } - - /* Try to match new DPB entries with existing ones by their POCs. */ - for (i = 0; i < ARRAY_SIZE(dec_param->dpb); i++) { - const struct v4l2_h264_dpb_entry *ndpb = &dec_param->dpb[i]; - - if (!(ndpb->flags & V4L2_H264_DPB_ENTRY_FLAG_ACTIVE)) - continue; - - /* - * To cut off some comparisons, iterate only on target DPB - * entries were already used. - */ - for_each_set_bit(j, in_use, ARRAY_SIZE(dec_param->dpb)) { - struct v4l2_h264_dpb_entry *cdpb; - - cdpb = &dpb[j]; - if (!dpb_entry_match(cdpb, ndpb)) - continue; - - *cdpb = *ndpb; - set_bit(j, used); - /* Don't reiterate on this one. */ - clear_bit(j, in_use); - break; - } - - if (j == ARRAY_SIZE(dec_param->dpb)) - set_bit(i, new); - } - - /* For entries that could not be matched, use remaining free slots. */ - for_each_set_bit(i, new, ARRAY_SIZE(dec_param->dpb)) { - const struct v4l2_h264_dpb_entry *ndpb = &dec_param->dpb[i]; - struct v4l2_h264_dpb_entry *cdpb; - - /* - * Both arrays are of the same sizes, so there is no way - * we can end up with no space in target array, unless - * something is buggy. - */ - j = find_first_zero_bit(used, ARRAY_SIZE(dec_param->dpb)); - if (WARN_ON(j >= ARRAY_SIZE(dec_param->dpb))) - return; - - cdpb = &dpb[j]; - *cdpb = *ndpb; - set_bit(j, used); - } -} - -/* - * The firmware expects unused reflist entries to have the value 0x20. - */ -static void fixup_ref_list(u8 *ref_list, size_t num_valid) -{ - memset(&ref_list[num_valid], 0x20, 32 - num_valid); -} - -static void get_vdec_decode_parameters(struct vdec_h264_slice_inst *inst) -{ - const struct v4l2_ctrl_h264_decode_params *dec_params = - get_ctrl_ptr(inst->ctx, V4L2_CID_STATELESS_H264_DECODE_PARAMS); - const struct v4l2_ctrl_h264_sps *sps = - get_ctrl_ptr(inst->ctx, V4L2_CID_STATELESS_H264_SPS); - const struct v4l2_ctrl_h264_pps *pps = - get_ctrl_ptr(inst->ctx, V4L2_CID_STATELESS_H264_PPS); - const struct v4l2_ctrl_h264_scaling_matrix *scaling_matrix = - get_ctrl_ptr(inst->ctx, V4L2_CID_STATELESS_H264_SCALING_MATRIX); + const struct v4l2_ctrl_h264_decode_params *dec_params; + const struct v4l2_ctrl_h264_sps *sps; + const struct v4l2_ctrl_h264_pps *pps; + const struct v4l2_ctrl_h264_scaling_matrix *scaling_matrix; struct mtk_h264_dec_slice_param *slice_param = &inst->h264_slice_param; struct v4l2_h264_reflist_builder reflist_builder; + struct v4l2_h264_reference v4l2_p0_reflist[V4L2_H264_REF_LIST_LEN]; + struct v4l2_h264_reference v4l2_b0_reflist[V4L2_H264_REF_LIST_LEN]; + struct v4l2_h264_reference v4l2_b1_reflist[V4L2_H264_REF_LIST_LEN]; u8 *p0_reflist = slice_param->decode_params.ref_pic_list_p0; u8 *b0_reflist = slice_param->decode_params.ref_pic_list_b0; u8 *b1_reflist = slice_param->decode_params.ref_pic_list_b1; - update_dpb(dec_params, inst->dpb); + dec_params = + mtk_vdec_h264_get_ctrl_ptr(inst->ctx, V4L2_CID_STATELESS_H264_DECODE_PARAMS); + if (IS_ERR(dec_params)) + return PTR_ERR(dec_params); + + sps = mtk_vdec_h264_get_ctrl_ptr(inst->ctx, V4L2_CID_STATELESS_H264_SPS); + if (IS_ERR(sps)) + return PTR_ERR(sps); - get_h264_sps_parameters(&slice_param->sps, sps); - get_h264_pps_parameters(&slice_param->pps, pps); - get_h264_scaling_matrix(&slice_param->scaling_matrix, scaling_matrix); - get_h264_decode_parameters(&slice_param->decode_params, dec_params, - inst->dpb); - get_h264_dpb_list(inst, slice_param); + pps = mtk_vdec_h264_get_ctrl_ptr(inst->ctx, V4L2_CID_STATELESS_H264_PPS); + if (IS_ERR(pps)) + return PTR_ERR(pps); + + scaling_matrix = + mtk_vdec_h264_get_ctrl_ptr(inst->ctx, V4L2_CID_STATELESS_H264_SCALING_MATRIX); + if (IS_ERR(scaling_matrix)) + return PTR_ERR(scaling_matrix); + + mtk_vdec_h264_update_dpb(dec_params, inst->dpb); + + mtk_vdec_h264_copy_sps_params(&slice_param->sps, sps); + mtk_vdec_h264_copy_pps_params(&slice_param->pps, pps); + mtk_vdec_h264_copy_scaling_matrix(&slice_param->scaling_matrix, scaling_matrix); + mtk_vdec_h264_copy_decode_params(&slice_param->decode_params, + dec_params, inst->dpb); + mtk_vdec_h264_fill_dpb_info(inst->ctx, &slice_param->decode_params, + slice_param->h264_dpb_info); /* Build the reference lists */ v4l2_h264_init_reflist_builder(&reflist_builder, dec_params, sps, inst->dpb); - v4l2_h264_build_p_ref_list(&reflist_builder, p0_reflist); - v4l2_h264_build_b_ref_lists(&reflist_builder, b0_reflist, b1_reflist); + v4l2_h264_build_p_ref_list(&reflist_builder, v4l2_p0_reflist); + v4l2_h264_build_b_ref_lists(&reflist_builder, v4l2_b0_reflist, + v4l2_b1_reflist); + /* Adapt the built lists to the firmware's expectations */ - fixup_ref_list(p0_reflist, reflist_builder.num_valid); - fixup_ref_list(b0_reflist, reflist_builder.num_valid); - fixup_ref_list(b1_reflist, reflist_builder.num_valid); + mtk_vdec_h264_get_ref_list(p0_reflist, v4l2_p0_reflist, reflist_builder.num_valid); + mtk_vdec_h264_get_ref_list(b0_reflist, v4l2_b0_reflist, reflist_builder.num_valid); + mtk_vdec_h264_get_ref_list(b1_reflist, v4l2_b1_reflist, reflist_builder.num_valid); memcpy(&inst->vsi_ctx.h264_slice_params, slice_param, sizeof(inst->vsi_ctx.h264_slice_params)); -} - -static unsigned int get_mv_buf_size(unsigned int width, unsigned int height) -{ - int unit_size = (width / MB_UNIT_LEN) * (height / MB_UNIT_LEN) + 8; - return HW_MB_STORE_SZ * unit_size; + return 0; } static int allocate_predication_buf(struct vdec_h264_slice_inst *inst) @@ -525,7 +187,7 @@ static int alloc_mv_buf(struct vdec_h264_slice_inst *inst, int i; int err; struct mtk_vcodec_mem *mem = NULL; - unsigned int buf_sz = get_mv_buf_size(pic->buf_w, pic->buf_h); + unsigned int buf_sz = mtk_vdec_h264_get_mv_buf_size(pic->buf_w, pic->buf_h); mtk_v4l2_debug(3, "size = 0x%x", buf_sz); for (i = 0; i < H264_MAX_MV_NUM; i++) { @@ -670,33 +332,46 @@ static void vdec_h264_slice_deinit(void *h_vdec) } static int vdec_h264_slice_decode(void *h_vdec, struct mtk_vcodec_mem *bs, - struct vdec_fb *fb, bool *res_chg) + struct vdec_fb *unused, bool *res_chg) { struct vdec_h264_slice_inst *inst = h_vdec; const struct v4l2_ctrl_h264_decode_params *dec_params = - get_ctrl_ptr(inst->ctx, V4L2_CID_STATELESS_H264_DECODE_PARAMS); + mtk_vdec_h264_get_ctrl_ptr(inst->ctx, V4L2_CID_STATELESS_H264_DECODE_PARAMS); struct vdec_vpu_inst *vpu = &inst->vpu; + struct mtk_video_dec_buf *src_buf_info; + struct mtk_video_dec_buf *dst_buf_info; + struct vdec_fb *fb; u32 data[2]; u64 y_fb_dma; u64 c_fb_dma; int err; + inst->num_nalu++; /* bs NULL means flush decoder */ if (!bs) return vpu_dec_reset(vpu); + fb = inst->ctx->dev->vdec_pdata->get_cap_buffer(inst->ctx); + src_buf_info = container_of(bs, struct mtk_video_dec_buf, bs_buffer); + dst_buf_info = container_of(fb, struct mtk_video_dec_buf, frame_buffer); + y_fb_dma = fb ? (u64)fb->base_y.dma_addr : 0; c_fb_dma = fb ? (u64)fb->base_c.dma_addr : 0; mtk_vcodec_debug(inst, "+ [%d] FB y_dma=%llx c_dma=%llx va=%p", - ++inst->num_nalu, y_fb_dma, c_fb_dma, fb); + inst->num_nalu, y_fb_dma, c_fb_dma, fb); inst->vsi_ctx.dec.bs_dma = (uint64_t)bs->dma_addr; inst->vsi_ctx.dec.y_fb_dma = y_fb_dma; inst->vsi_ctx.dec.c_fb_dma = c_fb_dma; inst->vsi_ctx.dec.vdec_fb_va = (u64)(uintptr_t)fb; - get_vdec_decode_parameters(inst); + v4l2_m2m_buf_copy_metadata(&src_buf_info->m2m_buf.vb, + &dst_buf_info->m2m_buf.vb, true); + err = get_vdec_decode_parameters(inst); + if (err) + goto err_free_fb_out; + data[0] = bs->size; /* * Reconstruct the first byte of the NAL unit, as the firmware requests diff --git a/drivers/media/platform/mediatek/vcodec/vdec/vdec_h264_req_multi_if.c b/drivers/media/platform/mediatek/vcodec/vdec/vdec_h264_req_multi_if.c new file mode 100644 index 000000000000..784d01f8bd50 --- /dev/null +++ b/drivers/media/platform/mediatek/vcodec/vdec/vdec_h264_req_multi_if.c @@ -0,0 +1,808 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2022 MediaTek Inc. + * Author: Yunfei Dong <yunfei.dong@mediatek.com> + */ + +#include <linux/module.h> +#include <linux/slab.h> +#include <media/v4l2-h264.h> +#include <media/v4l2-mem2mem.h> +#include <media/videobuf2-dma-contig.h> + +#include "../mtk_vcodec_util.h" +#include "../mtk_vcodec_dec.h" +#include "../mtk_vcodec_intr.h" +#include "../vdec_drv_base.h" +#include "../vdec_drv_if.h" +#include "../vdec_vpu_if.h" +#include "vdec_h264_req_common.h" + +/** + * enum vdec_h264_core_dec_err_type - core decode error type + * + * @TRANS_BUFFER_FULL: trans buffer is full + * @SLICE_HEADER_FULL: slice header buffer is full + */ +enum vdec_h264_core_dec_err_type { + TRANS_BUFFER_FULL = 1, + SLICE_HEADER_FULL, +}; + +/** + * struct vdec_h264_slice_lat_dec_param - parameters for decode current frame + * + * @sps: h264 sps syntax parameters + * @pps: h264 pps syntax parameters + * @slice_header: h264 slice header syntax parameters + * @scaling_matrix: h264 scaling list parameters + * @decode_params: decoder parameters of each frame used for hardware decode + * @h264_dpb_info: dpb reference list + */ +struct vdec_h264_slice_lat_dec_param { + struct mtk_h264_sps_param sps; + struct mtk_h264_pps_param pps; + struct mtk_h264_slice_hd_param slice_header; + struct slice_api_h264_scaling_matrix scaling_matrix; + struct slice_api_h264_decode_param decode_params; + struct mtk_h264_dpb_info h264_dpb_info[V4L2_H264_NUM_DPB_ENTRIES]; +}; + +/** + * struct vdec_h264_slice_info - decode information + * + * @nal_info: nal info of current picture + * @timeout: Decode timeout: 1 timeout, 0 no timeount + * @bs_buf_size: bitstream size + * @bs_buf_addr: bitstream buffer dma address + * @y_fb_dma: Y frame buffer dma address + * @c_fb_dma: C frame buffer dma address + * @vdec_fb_va: VDEC frame buffer struct virtual address + * @crc: Used to check whether hardware's status is right + */ +struct vdec_h264_slice_info { + u16 nal_info; + u16 timeout; + u32 bs_buf_size; + u64 bs_buf_addr; + u64 y_fb_dma; + u64 c_fb_dma; + u64 vdec_fb_va; + u32 crc[8]; +}; + +/** + * struct vdec_h264_slice_vsi - shared memory for decode information exchange + * between SCP and Host. + * + * @wdma_err_addr: wdma error dma address + * @wdma_start_addr: wdma start dma address + * @wdma_end_addr: wdma end dma address + * @slice_bc_start_addr: slice bc start dma address + * @slice_bc_end_addr: slice bc end dma address + * @row_info_start_addr: row info start dma address + * @row_info_end_addr: row info end dma address + * @trans_start: trans start dma address + * @trans_end: trans end dma address + * @wdma_end_addr_offset: wdma end address offset + * + * @mv_buf_dma: HW working motion vector buffer + * dma address (AP-W, VPU-R) + * @dec: decode information (AP-R, VPU-W) + * @h264_slice_params: decode parameters for hw used + */ +struct vdec_h264_slice_vsi { + /* LAT dec addr */ + u64 wdma_err_addr; + u64 wdma_start_addr; + u64 wdma_end_addr; + u64 slice_bc_start_addr; + u64 slice_bc_end_addr; + u64 row_info_start_addr; + u64 row_info_end_addr; + u64 trans_start; + u64 trans_end; + u64 wdma_end_addr_offset; + + u64 mv_buf_dma[H264_MAX_MV_NUM]; + struct vdec_h264_slice_info dec; + struct vdec_h264_slice_lat_dec_param h264_slice_params; +}; + +/** + * struct vdec_h264_slice_share_info - shared information used to exchange + * message between lat and core + * + * @sps: sequence header information from user space + * @dec_params: decoder params from user space + * @h264_slice_params: decoder params used for hardware + * @trans_start: trans start dma address + * @trans_end: trans end dma address + * @nal_info: nal info of current picture + */ +struct vdec_h264_slice_share_info { + struct v4l2_ctrl_h264_sps sps; + struct v4l2_ctrl_h264_decode_params dec_params; + struct vdec_h264_slice_lat_dec_param h264_slice_params; + u64 trans_start; + u64 trans_end; + u16 nal_info; +}; + +/** + * struct vdec_h264_slice_inst - h264 decoder instance + * + * @slice_dec_num: how many picture be decoded + * @ctx: point to mtk_vcodec_ctx + * @pred_buf: HW working predication buffer + * @mv_buf: HW working motion vector buffer + * @vpu: VPU instance + * @vsi: vsi used for lat + * @vsi_core: vsi used for core + * + * @vsi_ctx: Local VSI data for this decoding context + * @h264_slice_param: the parameters that hardware use to decode + * + * @resolution_changed:resolution changed + * @realloc_mv_buf: reallocate mv buffer + * @cap_num_planes: number of capture queue plane + * + * @dpb: decoded picture buffer used to store reference + * buffer information + *@is_field_bitstream: is field bitstream + */ +struct vdec_h264_slice_inst { + unsigned int slice_dec_num; + struct mtk_vcodec_ctx *ctx; + struct mtk_vcodec_mem pred_buf; + struct mtk_vcodec_mem mv_buf[H264_MAX_MV_NUM]; + struct vdec_vpu_inst vpu; + struct vdec_h264_slice_vsi *vsi; + struct vdec_h264_slice_vsi *vsi_core; + + struct vdec_h264_slice_vsi vsi_ctx; + struct vdec_h264_slice_lat_dec_param h264_slice_param; + + unsigned int resolution_changed; + unsigned int realloc_mv_buf; + unsigned int cap_num_planes; + + struct v4l2_h264_dpb_entry dpb[16]; + bool is_field_bitstream; +}; + +static int vdec_h264_slice_fill_decode_parameters(struct vdec_h264_slice_inst *inst, + struct vdec_h264_slice_share_info *share_info) +{ + struct vdec_h264_slice_lat_dec_param *slice_param = &inst->vsi->h264_slice_params; + const struct v4l2_ctrl_h264_decode_params *dec_params; + const struct v4l2_ctrl_h264_scaling_matrix *src_matrix; + const struct v4l2_ctrl_h264_sps *sps; + const struct v4l2_ctrl_h264_pps *pps; + + dec_params = + mtk_vdec_h264_get_ctrl_ptr(inst->ctx, V4L2_CID_STATELESS_H264_DECODE_PARAMS); + if (IS_ERR(dec_params)) + return PTR_ERR(dec_params); + + src_matrix = + mtk_vdec_h264_get_ctrl_ptr(inst->ctx, V4L2_CID_STATELESS_H264_SCALING_MATRIX); + if (IS_ERR(src_matrix)) + return PTR_ERR(src_matrix); + + sps = mtk_vdec_h264_get_ctrl_ptr(inst->ctx, V4L2_CID_STATELESS_H264_SPS); + if (IS_ERR(sps)) + return PTR_ERR(sps); + + pps = mtk_vdec_h264_get_ctrl_ptr(inst->ctx, V4L2_CID_STATELESS_H264_PPS); + if (IS_ERR(pps)) + return PTR_ERR(pps); + + if (dec_params->flags & V4L2_H264_DECODE_PARAM_FLAG_FIELD_PIC) { + mtk_vcodec_err(inst, "No support for H.264 field decoding."); + inst->is_field_bitstream = true; + return -EINVAL; + } + + mtk_vdec_h264_copy_sps_params(&slice_param->sps, sps); + mtk_vdec_h264_copy_pps_params(&slice_param->pps, pps); + mtk_vdec_h264_copy_scaling_matrix(&slice_param->scaling_matrix, src_matrix); + + memcpy(&share_info->sps, sps, sizeof(*sps)); + memcpy(&share_info->dec_params, dec_params, sizeof(*dec_params)); + + return 0; +} + +static int get_vdec_sig_decode_parameters(struct vdec_h264_slice_inst *inst) +{ + const struct v4l2_ctrl_h264_decode_params *dec_params; + const struct v4l2_ctrl_h264_sps *sps; + const struct v4l2_ctrl_h264_pps *pps; + const struct v4l2_ctrl_h264_scaling_matrix *scaling_matrix; + struct vdec_h264_slice_lat_dec_param *slice_param = &inst->h264_slice_param; + struct v4l2_h264_reflist_builder reflist_builder; + struct v4l2_h264_reference v4l2_p0_reflist[V4L2_H264_REF_LIST_LEN]; + struct v4l2_h264_reference v4l2_b0_reflist[V4L2_H264_REF_LIST_LEN]; + struct v4l2_h264_reference v4l2_b1_reflist[V4L2_H264_REF_LIST_LEN]; + u8 *p0_reflist = slice_param->decode_params.ref_pic_list_p0; + u8 *b0_reflist = slice_param->decode_params.ref_pic_list_b0; + u8 *b1_reflist = slice_param->decode_params.ref_pic_list_b1; + + dec_params = + mtk_vdec_h264_get_ctrl_ptr(inst->ctx, V4L2_CID_STATELESS_H264_DECODE_PARAMS); + if (IS_ERR(dec_params)) + return PTR_ERR(dec_params); + + sps = mtk_vdec_h264_get_ctrl_ptr(inst->ctx, V4L2_CID_STATELESS_H264_SPS); + if (IS_ERR(sps)) + return PTR_ERR(sps); + + pps = mtk_vdec_h264_get_ctrl_ptr(inst->ctx, V4L2_CID_STATELESS_H264_PPS); + if (IS_ERR(pps)) + return PTR_ERR(pps); + + scaling_matrix = + mtk_vdec_h264_get_ctrl_ptr(inst->ctx, V4L2_CID_STATELESS_H264_SCALING_MATRIX); + if (IS_ERR(scaling_matrix)) + return PTR_ERR(scaling_matrix); + + mtk_vdec_h264_update_dpb(dec_params, inst->dpb); + + mtk_vdec_h264_copy_sps_params(&slice_param->sps, sps); + mtk_vdec_h264_copy_pps_params(&slice_param->pps, pps); + mtk_vdec_h264_copy_scaling_matrix(&slice_param->scaling_matrix, scaling_matrix); + + mtk_vdec_h264_copy_decode_params(&slice_param->decode_params, dec_params, inst->dpb); + mtk_vdec_h264_fill_dpb_info(inst->ctx, &slice_param->decode_params, + slice_param->h264_dpb_info); + + /* Build the reference lists */ + v4l2_h264_init_reflist_builder(&reflist_builder, dec_params, sps, inst->dpb); + v4l2_h264_build_p_ref_list(&reflist_builder, v4l2_p0_reflist); + v4l2_h264_build_b_ref_lists(&reflist_builder, v4l2_b0_reflist, v4l2_b1_reflist); + + /* Adapt the built lists to the firmware's expectations */ + mtk_vdec_h264_get_ref_list(p0_reflist, v4l2_p0_reflist, reflist_builder.num_valid); + mtk_vdec_h264_get_ref_list(b0_reflist, v4l2_b0_reflist, reflist_builder.num_valid); + mtk_vdec_h264_get_ref_list(b1_reflist, v4l2_b1_reflist, reflist_builder.num_valid); + + memcpy(&inst->vsi_ctx.h264_slice_params, slice_param, + sizeof(inst->vsi_ctx.h264_slice_params)); + + return 0; +} + +static void vdec_h264_slice_fill_decode_reflist(struct vdec_h264_slice_inst *inst, + struct vdec_h264_slice_lat_dec_param *slice_param, + struct vdec_h264_slice_share_info *share_info) +{ + struct v4l2_ctrl_h264_decode_params *dec_params = &share_info->dec_params; + struct v4l2_ctrl_h264_sps *sps = &share_info->sps; + struct v4l2_h264_reflist_builder reflist_builder; + struct v4l2_h264_reference v4l2_p0_reflist[V4L2_H264_REF_LIST_LEN]; + struct v4l2_h264_reference v4l2_b0_reflist[V4L2_H264_REF_LIST_LEN]; + struct v4l2_h264_reference v4l2_b1_reflist[V4L2_H264_REF_LIST_LEN]; + u8 *p0_reflist = slice_param->decode_params.ref_pic_list_p0; + u8 *b0_reflist = slice_param->decode_params.ref_pic_list_b0; + u8 *b1_reflist = slice_param->decode_params.ref_pic_list_b1; + + mtk_vdec_h264_update_dpb(dec_params, inst->dpb); + + mtk_vdec_h264_copy_decode_params(&slice_param->decode_params, dec_params, + inst->dpb); + mtk_vdec_h264_fill_dpb_info(inst->ctx, &slice_param->decode_params, + slice_param->h264_dpb_info); + + mtk_v4l2_debug(3, "cur poc = %d\n", dec_params->bottom_field_order_cnt); + /* Build the reference lists */ + v4l2_h264_init_reflist_builder(&reflist_builder, dec_params, sps, + inst->dpb); + v4l2_h264_build_p_ref_list(&reflist_builder, v4l2_p0_reflist); + v4l2_h264_build_b_ref_lists(&reflist_builder, v4l2_b0_reflist, v4l2_b1_reflist); + + /* Adapt the built lists to the firmware's expectations */ + mtk_vdec_h264_get_ref_list(p0_reflist, v4l2_p0_reflist, reflist_builder.num_valid); + mtk_vdec_h264_get_ref_list(b0_reflist, v4l2_b0_reflist, reflist_builder.num_valid); + mtk_vdec_h264_get_ref_list(b1_reflist, v4l2_b1_reflist, reflist_builder.num_valid); +} + +static int vdec_h264_slice_alloc_mv_buf(struct vdec_h264_slice_inst *inst, + struct vdec_pic_info *pic) +{ + unsigned int buf_sz = mtk_vdec_h264_get_mv_buf_size(pic->buf_w, pic->buf_h); + struct mtk_vcodec_mem *mem; + int i, err; + + mtk_v4l2_debug(3, "size = 0x%x", buf_sz); + for (i = 0; i < H264_MAX_MV_NUM; i++) { + mem = &inst->mv_buf[i]; + if (mem->va) + mtk_vcodec_mem_free(inst->ctx, mem); + mem->size = buf_sz; + err = mtk_vcodec_mem_alloc(inst->ctx, mem); + if (err) { + mtk_vcodec_err(inst, "failed to allocate mv buf"); + return err; + } + } + + return 0; +} + +static void vdec_h264_slice_free_mv_buf(struct vdec_h264_slice_inst *inst) +{ + int i; + struct mtk_vcodec_mem *mem; + + for (i = 0; i < H264_MAX_MV_NUM; i++) { + mem = &inst->mv_buf[i]; + if (mem->va) + mtk_vcodec_mem_free(inst->ctx, mem); + } +} + +static void vdec_h264_slice_get_pic_info(struct vdec_h264_slice_inst *inst) +{ + struct mtk_vcodec_ctx *ctx = inst->ctx; + u32 data[3]; + + data[0] = ctx->picinfo.pic_w; + data[1] = ctx->picinfo.pic_h; + data[2] = ctx->capture_fourcc; + vpu_dec_get_param(&inst->vpu, data, 3, GET_PARAM_PIC_INFO); + + ctx->picinfo.buf_w = ALIGN(ctx->picinfo.pic_w, VCODEC_DEC_ALIGNED_64); + ctx->picinfo.buf_h = ALIGN(ctx->picinfo.pic_h, VCODEC_DEC_ALIGNED_64); + ctx->picinfo.fb_sz[0] = inst->vpu.fb_sz[0]; + ctx->picinfo.fb_sz[1] = inst->vpu.fb_sz[1]; + inst->cap_num_planes = + ctx->q_data[MTK_Q_DATA_DST].fmt->num_planes; + + mtk_vcodec_debug(inst, "pic(%d, %d), buf(%d, %d)", + ctx->picinfo.pic_w, ctx->picinfo.pic_h, + ctx->picinfo.buf_w, ctx->picinfo.buf_h); + mtk_vcodec_debug(inst, "Y/C(%d, %d)", ctx->picinfo.fb_sz[0], + ctx->picinfo.fb_sz[1]); + + if (ctx->last_decoded_picinfo.pic_w != ctx->picinfo.pic_w || + ctx->last_decoded_picinfo.pic_h != ctx->picinfo.pic_h) { + inst->resolution_changed = true; + if (ctx->last_decoded_picinfo.buf_w != ctx->picinfo.buf_w || + ctx->last_decoded_picinfo.buf_h != ctx->picinfo.buf_h) + inst->realloc_mv_buf = true; + + mtk_v4l2_debug(1, "resChg: (%d %d) : old(%d, %d) -> new(%d, %d)", + inst->resolution_changed, + inst->realloc_mv_buf, + ctx->last_decoded_picinfo.pic_w, + ctx->last_decoded_picinfo.pic_h, + ctx->picinfo.pic_w, ctx->picinfo.pic_h); + } +} + +static void vdec_h264_slice_get_crop_info(struct vdec_h264_slice_inst *inst, + struct v4l2_rect *cr) +{ + cr->left = 0; + cr->top = 0; + cr->width = inst->ctx->picinfo.pic_w; + cr->height = inst->ctx->picinfo.pic_h; + + mtk_vcodec_debug(inst, "l=%d, t=%d, w=%d, h=%d", + cr->left, cr->top, cr->width, cr->height); +} + +static int vdec_h264_slice_init(struct mtk_vcodec_ctx *ctx) +{ + struct vdec_h264_slice_inst *inst; + int err, vsi_size; + + inst = kzalloc(sizeof(*inst), GFP_KERNEL); + if (!inst) + return -ENOMEM; + + inst->ctx = ctx; + + inst->vpu.id = SCP_IPI_VDEC_LAT; + inst->vpu.core_id = SCP_IPI_VDEC_CORE; + inst->vpu.ctx = ctx; + inst->vpu.codec_type = ctx->current_codec; + inst->vpu.capture_type = ctx->capture_fourcc; + + err = vpu_dec_init(&inst->vpu); + if (err) { + mtk_vcodec_err(inst, "vdec_h264 init err=%d", err); + goto error_free_inst; + } + + vsi_size = round_up(sizeof(struct vdec_h264_slice_vsi), VCODEC_DEC_ALIGNED_64); + inst->vsi = inst->vpu.vsi; + inst->vsi_core = + (struct vdec_h264_slice_vsi *)(((char *)inst->vpu.vsi) + vsi_size); + inst->resolution_changed = true; + inst->realloc_mv_buf = true; + + mtk_vcodec_debug(inst, "lat struct size = %d,%d,%d,%d vsi: %d\n", + (int)sizeof(struct mtk_h264_sps_param), + (int)sizeof(struct mtk_h264_pps_param), + (int)sizeof(struct vdec_h264_slice_lat_dec_param), + (int)sizeof(struct mtk_h264_dpb_info), + vsi_size); + mtk_vcodec_debug(inst, "lat H264 instance >> %p, codec_type = 0x%x", + inst, inst->vpu.codec_type); + + ctx->drv_handle = inst; + return 0; + +error_free_inst: + kfree(inst); + return err; +} + +static void vdec_h264_slice_deinit(void *h_vdec) +{ + struct vdec_h264_slice_inst *inst = h_vdec; + + mtk_vcodec_debug_enter(inst); + + vpu_dec_deinit(&inst->vpu); + vdec_h264_slice_free_mv_buf(inst); + vdec_msg_queue_deinit(&inst->ctx->msg_queue, inst->ctx); + + kfree(inst); +} + +static int vdec_h264_slice_core_decode(struct vdec_lat_buf *lat_buf) +{ + struct vdec_fb *fb; + u64 vdec_fb_va; + u64 y_fb_dma, c_fb_dma; + int err, timeout, i; + struct mtk_vcodec_ctx *ctx = lat_buf->ctx; + struct vdec_h264_slice_inst *inst = ctx->drv_handle; + struct vb2_v4l2_buffer *vb2_v4l2; + struct vdec_h264_slice_share_info *share_info = lat_buf->private_data; + struct mtk_vcodec_mem *mem; + struct vdec_vpu_inst *vpu = &inst->vpu; + + mtk_vcodec_debug(inst, "[h264-core] vdec_h264 core decode"); + memcpy(&inst->vsi_core->h264_slice_params, &share_info->h264_slice_params, + sizeof(share_info->h264_slice_params)); + + fb = ctx->dev->vdec_pdata->get_cap_buffer(ctx); + y_fb_dma = fb ? (u64)fb->base_y.dma_addr : 0; + vdec_fb_va = (unsigned long)fb; + + if (ctx->q_data[MTK_Q_DATA_DST].fmt->num_planes == 1) + c_fb_dma = + y_fb_dma + inst->ctx->picinfo.buf_w * inst->ctx->picinfo.buf_h; + else + c_fb_dma = fb ? (u64)fb->base_c.dma_addr : 0; + + mtk_vcodec_debug(inst, "[h264-core] y/c addr = 0x%llx 0x%llx", y_fb_dma, + c_fb_dma); + + inst->vsi_core->dec.y_fb_dma = y_fb_dma; + inst->vsi_core->dec.c_fb_dma = c_fb_dma; + inst->vsi_core->dec.vdec_fb_va = vdec_fb_va; + inst->vsi_core->dec.nal_info = share_info->nal_info; + inst->vsi_core->wdma_start_addr = + lat_buf->ctx->msg_queue.wdma_addr.dma_addr; + inst->vsi_core->wdma_end_addr = + lat_buf->ctx->msg_queue.wdma_addr.dma_addr + + lat_buf->ctx->msg_queue.wdma_addr.size; + inst->vsi_core->wdma_err_addr = lat_buf->wdma_err_addr.dma_addr; + inst->vsi_core->slice_bc_start_addr = lat_buf->slice_bc_addr.dma_addr; + inst->vsi_core->slice_bc_end_addr = lat_buf->slice_bc_addr.dma_addr + + lat_buf->slice_bc_addr.size; + inst->vsi_core->trans_start = share_info->trans_start; + inst->vsi_core->trans_end = share_info->trans_end; + for (i = 0; i < H264_MAX_MV_NUM; i++) { + mem = &inst->mv_buf[i]; + inst->vsi_core->mv_buf_dma[i] = mem->dma_addr; + } + + vb2_v4l2 = v4l2_m2m_next_dst_buf(ctx->m2m_ctx); + v4l2_m2m_buf_copy_metadata(&lat_buf->ts_info, vb2_v4l2, true); + + vdec_h264_slice_fill_decode_reflist(inst, &inst->vsi_core->h264_slice_params, + share_info); + + err = vpu_dec_core(vpu); + if (err) { + mtk_vcodec_err(inst, "core decode err=%d", err); + goto vdec_dec_end; + } + + /* wait decoder done interrupt */ + timeout = mtk_vcodec_wait_for_done_ctx(inst->ctx, MTK_INST_IRQ_RECEIVED, + WAIT_INTR_TIMEOUT_MS, MTK_VDEC_CORE); + if (timeout) + mtk_vcodec_err(inst, "core decode timeout: pic_%d", + ctx->decoded_frame_cnt); + inst->vsi_core->dec.timeout = !!timeout; + + vpu_dec_core_end(vpu); + mtk_vcodec_debug(inst, "pic[%d] crc: 0x%x 0x%x 0x%x 0x%x 0x%x 0x%x 0x%x 0x%x", + ctx->decoded_frame_cnt, + inst->vsi_core->dec.crc[0], inst->vsi_core->dec.crc[1], + inst->vsi_core->dec.crc[2], inst->vsi_core->dec.crc[3], + inst->vsi_core->dec.crc[4], inst->vsi_core->dec.crc[5], + inst->vsi_core->dec.crc[6], inst->vsi_core->dec.crc[7]); + +vdec_dec_end: + vdec_msg_queue_update_ube_rptr(&lat_buf->ctx->msg_queue, share_info->trans_end); + ctx->dev->vdec_pdata->cap_to_disp(ctx, !!err, lat_buf->src_buf_req); + mtk_vcodec_debug(inst, "core decode done err=%d", err); + ctx->decoded_frame_cnt++; + return 0; +} + +static int vdec_h264_slice_lat_decode(void *h_vdec, struct mtk_vcodec_mem *bs, + struct vdec_fb *fb, bool *res_chg) +{ + struct vdec_h264_slice_inst *inst = h_vdec; + struct vdec_vpu_inst *vpu = &inst->vpu; + struct mtk_video_dec_buf *src_buf_info; + int nal_start_idx, err, timeout = 0, i; + unsigned int data[2]; + struct vdec_lat_buf *lat_buf; + struct vdec_h264_slice_share_info *share_info; + unsigned char *buf; + struct mtk_vcodec_mem *mem; + + if (vdec_msg_queue_init(&inst->ctx->msg_queue, inst->ctx, + vdec_h264_slice_core_decode, + sizeof(*share_info))) + return -ENOMEM; + + /* bs NULL means flush decoder */ + if (!bs) { + vdec_msg_queue_wait_lat_buf_full(&inst->ctx->msg_queue); + return vpu_dec_reset(vpu); + } + + if (inst->is_field_bitstream) + return -EINVAL; + + lat_buf = vdec_msg_queue_dqbuf(&inst->ctx->msg_queue.lat_ctx); + if (!lat_buf) { + mtk_vcodec_err(inst, "failed to get lat buffer"); + return -EINVAL; + } + share_info = lat_buf->private_data; + src_buf_info = container_of(bs, struct mtk_video_dec_buf, bs_buffer); + + buf = (unsigned char *)bs->va; + nal_start_idx = mtk_vdec_h264_find_start_code(buf, bs->size); + if (nal_start_idx < 0) { + err = -EINVAL; + goto err_free_fb_out; + } + + inst->vsi->dec.nal_info = buf[nal_start_idx]; + inst->vsi->dec.bs_buf_addr = (u64)bs->dma_addr; + inst->vsi->dec.bs_buf_size = bs->size; + + lat_buf->src_buf_req = src_buf_info->m2m_buf.vb.vb2_buf.req_obj.req; + v4l2_m2m_buf_copy_metadata(&src_buf_info->m2m_buf.vb, &lat_buf->ts_info, true); + + err = vdec_h264_slice_fill_decode_parameters(inst, share_info); + if (err) + goto err_free_fb_out; + + *res_chg = inst->resolution_changed; + if (inst->resolution_changed) { + mtk_vcodec_debug(inst, "- resolution changed -"); + if (inst->realloc_mv_buf) { + err = vdec_h264_slice_alloc_mv_buf(inst, &inst->ctx->picinfo); + inst->realloc_mv_buf = false; + if (err) + goto err_free_fb_out; + } + inst->resolution_changed = false; + } + for (i = 0; i < H264_MAX_MV_NUM; i++) { + mem = &inst->mv_buf[i]; + inst->vsi->mv_buf_dma[i] = mem->dma_addr; + } + inst->vsi->wdma_start_addr = lat_buf->ctx->msg_queue.wdma_addr.dma_addr; + inst->vsi->wdma_end_addr = lat_buf->ctx->msg_queue.wdma_addr.dma_addr + + lat_buf->ctx->msg_queue.wdma_addr.size; + inst->vsi->wdma_err_addr = lat_buf->wdma_err_addr.dma_addr; + inst->vsi->slice_bc_start_addr = lat_buf->slice_bc_addr.dma_addr; + inst->vsi->slice_bc_end_addr = lat_buf->slice_bc_addr.dma_addr + + lat_buf->slice_bc_addr.size; + + inst->vsi->trans_end = inst->ctx->msg_queue.wdma_rptr_addr; + inst->vsi->trans_start = inst->ctx->msg_queue.wdma_wptr_addr; + mtk_vcodec_debug(inst, "lat:trans(0x%llx 0x%llx) err:0x%llx", + inst->vsi->wdma_start_addr, + inst->vsi->wdma_end_addr, + inst->vsi->wdma_err_addr); + + mtk_vcodec_debug(inst, "slice(0x%llx 0x%llx) rprt((0x%llx 0x%llx))", + inst->vsi->slice_bc_start_addr, + inst->vsi->slice_bc_end_addr, + inst->vsi->trans_start, + inst->vsi->trans_end); + err = vpu_dec_start(vpu, data, 2); + if (err) { + mtk_vcodec_debug(inst, "lat decode err: %d", err); + goto err_scp_decode; + } + + /* wait decoder done interrupt */ + timeout = mtk_vcodec_wait_for_done_ctx(inst->ctx, MTK_INST_IRQ_RECEIVED, + WAIT_INTR_TIMEOUT_MS, MTK_VDEC_LAT0); + inst->vsi->dec.timeout = !!timeout; + + err = vpu_dec_end(vpu); + if (err == SLICE_HEADER_FULL || timeout || err == TRANS_BUFFER_FULL) { + err = -EINVAL; + goto err_scp_decode; + } + + share_info->trans_end = inst->ctx->msg_queue.wdma_addr.dma_addr + + inst->vsi->wdma_end_addr_offset; + share_info->trans_start = inst->ctx->msg_queue.wdma_wptr_addr; + share_info->nal_info = inst->vsi->dec.nal_info; + vdec_msg_queue_update_ube_wptr(&lat_buf->ctx->msg_queue, share_info->trans_end); + + memcpy(&share_info->h264_slice_params, &inst->vsi->h264_slice_params, + sizeof(share_info->h264_slice_params)); + vdec_msg_queue_qbuf(&inst->ctx->dev->msg_queue_core_ctx, lat_buf); + + inst->slice_dec_num++; + return 0; + +err_scp_decode: +err_free_fb_out: + vdec_msg_queue_qbuf(&inst->ctx->msg_queue.lat_ctx, lat_buf); + mtk_vcodec_err(inst, "slice dec number: %d err: %d", inst->slice_dec_num, err); + return err; +} + +static int vdec_h264_slice_single_decode(void *h_vdec, struct mtk_vcodec_mem *bs, + struct vdec_fb *unused, bool *res_chg) +{ + struct vdec_h264_slice_inst *inst = h_vdec; + struct vdec_vpu_inst *vpu = &inst->vpu; + struct mtk_video_dec_buf *src_buf_info, *dst_buf_info; + struct vdec_fb *fb; + unsigned char *buf; + unsigned int data[2], i; + u64 y_fb_dma, c_fb_dma; + struct mtk_vcodec_mem *mem; + int err, nal_start_idx; + + /* bs NULL means flush decoder */ + if (!bs) + return vpu_dec_reset(vpu); + + fb = inst->ctx->dev->vdec_pdata->get_cap_buffer(inst->ctx); + src_buf_info = container_of(bs, struct mtk_video_dec_buf, bs_buffer); + dst_buf_info = container_of(fb, struct mtk_video_dec_buf, frame_buffer); + + y_fb_dma = fb ? (u64)fb->base_y.dma_addr : 0; + c_fb_dma = fb ? (u64)fb->base_c.dma_addr : 0; + mtk_vcodec_debug(inst, "[h264-dec] [%d] y_dma=%llx c_dma=%llx", + inst->ctx->decoded_frame_cnt, y_fb_dma, c_fb_dma); + + inst->vsi_ctx.dec.bs_buf_addr = (u64)bs->dma_addr; + inst->vsi_ctx.dec.bs_buf_size = bs->size; + inst->vsi_ctx.dec.y_fb_dma = y_fb_dma; + inst->vsi_ctx.dec.c_fb_dma = c_fb_dma; + inst->vsi_ctx.dec.vdec_fb_va = (u64)(uintptr_t)fb; + + v4l2_m2m_buf_copy_metadata(&src_buf_info->m2m_buf.vb, + &dst_buf_info->m2m_buf.vb, true); + err = get_vdec_sig_decode_parameters(inst); + if (err) + goto err_free_fb_out; + + buf = (unsigned char *)bs->va; + nal_start_idx = mtk_vdec_h264_find_start_code(buf, bs->size); + if (nal_start_idx < 0) { + err = -EINVAL; + goto err_free_fb_out; + } + inst->vsi_ctx.dec.nal_info = buf[nal_start_idx]; + + *res_chg = inst->resolution_changed; + if (inst->resolution_changed) { + mtk_vcodec_debug(inst, "- resolution changed -"); + if (inst->realloc_mv_buf) { + err = vdec_h264_slice_alloc_mv_buf(inst, &inst->ctx->picinfo); + inst->realloc_mv_buf = false; + if (err) + goto err_free_fb_out; + } + inst->resolution_changed = false; + + for (i = 0; i < H264_MAX_MV_NUM; i++) { + mem = &inst->mv_buf[i]; + inst->vsi_ctx.mv_buf_dma[i] = mem->dma_addr; + } + } + + memcpy(inst->vpu.vsi, &inst->vsi_ctx, sizeof(inst->vsi_ctx)); + err = vpu_dec_start(vpu, data, 2); + if (err) + goto err_free_fb_out; + + /* wait decoder done interrupt */ + err = mtk_vcodec_wait_for_done_ctx(inst->ctx, MTK_INST_IRQ_RECEIVED, + WAIT_INTR_TIMEOUT_MS, MTK_VDEC_CORE); + if (err) + mtk_vcodec_err(inst, "decode timeout: pic_%d", + inst->ctx->decoded_frame_cnt); + + inst->vsi->dec.timeout = !!err; + err = vpu_dec_end(vpu); + if (err) + goto err_free_fb_out; + + memcpy(&inst->vsi_ctx, inst->vpu.vsi, sizeof(inst->vsi_ctx)); + mtk_vcodec_debug(inst, "pic[%d] crc: 0x%x 0x%x 0x%x 0x%x 0x%x 0x%x 0x%x 0x%x", + inst->ctx->decoded_frame_cnt, + inst->vsi_ctx.dec.crc[0], inst->vsi_ctx.dec.crc[1], + inst->vsi_ctx.dec.crc[2], inst->vsi_ctx.dec.crc[3], + inst->vsi_ctx.dec.crc[4], inst->vsi_ctx.dec.crc[5], + inst->vsi_ctx.dec.crc[6], inst->vsi_ctx.dec.crc[7]); + + inst->ctx->decoded_frame_cnt++; + return 0; + +err_free_fb_out: + mtk_vcodec_err(inst, "dec frame number: %d err: %d", + inst->ctx->decoded_frame_cnt, err); + return err; +} + +static int vdec_h264_slice_decode(void *h_vdec, struct mtk_vcodec_mem *bs, + struct vdec_fb *unused, bool *res_chg) +{ + struct vdec_h264_slice_inst *inst = h_vdec; + int ret; + + if (!h_vdec) + return -EINVAL; + + if (inst->ctx->dev->vdec_pdata->hw_arch == MTK_VDEC_PURE_SINGLE_CORE) + ret = vdec_h264_slice_single_decode(h_vdec, bs, unused, res_chg); + else + ret = vdec_h264_slice_lat_decode(h_vdec, bs, unused, res_chg); + + return ret; +} + +static int vdec_h264_slice_get_param(void *h_vdec, enum vdec_get_param_type type, + void *out) +{ + struct vdec_h264_slice_inst *inst = h_vdec; + + switch (type) { + case GET_PARAM_PIC_INFO: + vdec_h264_slice_get_pic_info(inst); + break; + case GET_PARAM_DPB_SIZE: + *(unsigned int *)out = 6; + break; + case GET_PARAM_CROP_INFO: + vdec_h264_slice_get_crop_info(inst, out); + break; + default: + mtk_vcodec_err(inst, "invalid get parameter type=%d", type); + return -EINVAL; + } + return 0; +} + +const struct vdec_common_if vdec_h264_slice_multi_if = { + .init = vdec_h264_slice_init, + .decode = vdec_h264_slice_decode, + .get_param = vdec_h264_slice_get_param, + .deinit = vdec_h264_slice_deinit, +}; diff --git a/drivers/media/platform/mediatek/vcodec/vdec/vdec_vp8_req_if.c b/drivers/media/platform/mediatek/vcodec/vdec/vdec_vp8_req_if.c new file mode 100644 index 000000000000..eef102f3f4f3 --- /dev/null +++ b/drivers/media/platform/mediatek/vcodec/vdec/vdec_vp8_req_if.c @@ -0,0 +1,437 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2021 MediaTek Inc. + * Author: Yunfei Dong <yunfei.dong@mediatek.com> + */ + +#include <linux/slab.h> +#include <media/v4l2-mem2mem.h> +#include <media/videobuf2-dma-contig.h> +#include <uapi/linux/v4l2-controls.h> + +#include "../mtk_vcodec_util.h" +#include "../mtk_vcodec_dec.h" +#include "../mtk_vcodec_intr.h" +#include "../vdec_drv_base.h" +#include "../vdec_drv_if.h" +#include "../vdec_vpu_if.h" + +/* Decoding picture buffer size (3 reference frames plus current frame) */ +#define VP8_DPB_SIZE 4 + +/* HW working buffer size (bytes) */ +#define VP8_SEG_ID_SZ SZ_256K +#define VP8_PP_WRAPY_SZ SZ_64K +#define VP8_PP_WRAPC_SZ SZ_64K +#define VP8_VLD_PRED_SZ SZ_64K + +/** + * struct vdec_vp8_slice_info - decode misc information + * + * @vld_wrapper_dma: vld wrapper dma address + * @seg_id_buf_dma: seg id dma address + * @wrap_y_dma: wrap y dma address + * @wrap_c_dma: wrap y dma address + * @cur_y_fb_dma: current plane Y frame buffer dma address + * @cur_c_fb_dma: current plane C frame buffer dma address + * @bs_dma: bitstream dma address + * @bs_sz: bitstream size + * @resolution_changed:resolution change flag 1 - changed, 0 - not change + * @frame_header_type: current frame header type + * @wait_key_frame: wait key frame coming + * @crc: used to check whether hardware's status is right + * @reserved: reserved, currently unused + */ +struct vdec_vp8_slice_info { + u64 vld_wrapper_dma; + u64 seg_id_buf_dma; + u64 wrap_y_dma; + u64 wrap_c_dma; + u64 cur_y_fb_dma; + u64 cur_c_fb_dma; + u64 bs_dma; + u32 bs_sz; + u32 resolution_changed; + u32 frame_header_type; + u32 crc[8]; + u32 reserved; +}; + +/** + * struct vdec_vp8_slice_dpb_info - vp8 reference information + * + * @y_dma_addr: Y bitstream physical address + * @c_dma_addr: CbCr bitstream physical address + * @reference_flag: reference picture flag + * @reserved: 64bit align + */ +struct vdec_vp8_slice_dpb_info { + dma_addr_t y_dma_addr; + dma_addr_t c_dma_addr; + int reference_flag; + int reserved; +}; + +/** + * struct vdec_vp8_slice_vsi - VPU shared information + * + * @dec: decoding information + * @pic: picture information + * @vp8_dpb_info: reference buffer information + */ +struct vdec_vp8_slice_vsi { + struct vdec_vp8_slice_info dec; + struct vdec_pic_info pic; + struct vdec_vp8_slice_dpb_info vp8_dpb_info[3]; +}; + +/** + * struct vdec_vp8_slice_inst - VP8 decoder instance + * + * @seg_id_buf: seg buffer + * @wrap_y_buf: wrapper y buffer + * @wrap_c_buf: wrapper c buffer + * @vld_wrapper_buf: vld wrapper buffer + * @ctx: V4L2 context + * @vpu: VPU instance for decoder + * @vsi: VPU share information + */ +struct vdec_vp8_slice_inst { + struct mtk_vcodec_mem seg_id_buf; + struct mtk_vcodec_mem wrap_y_buf; + struct mtk_vcodec_mem wrap_c_buf; + struct mtk_vcodec_mem vld_wrapper_buf; + struct mtk_vcodec_ctx *ctx; + struct vdec_vpu_inst vpu; + struct vdec_vp8_slice_vsi *vsi; +}; + +static void *vdec_vp8_slice_get_ctrl_ptr(struct mtk_vcodec_ctx *ctx, int id) +{ + struct v4l2_ctrl *ctrl = v4l2_ctrl_find(&ctx->ctrl_hdl, id); + + if (!ctrl) + return ERR_PTR(-EINVAL); + + return ctrl->p_cur.p; +} + +static void vdec_vp8_slice_get_pic_info(struct vdec_vp8_slice_inst *inst) +{ + struct mtk_vcodec_ctx *ctx = inst->ctx; + unsigned int data[3]; + + data[0] = ctx->picinfo.pic_w; + data[1] = ctx->picinfo.pic_h; + data[2] = ctx->capture_fourcc; + vpu_dec_get_param(&inst->vpu, data, 3, GET_PARAM_PIC_INFO); + + ctx->picinfo.buf_w = ALIGN(ctx->picinfo.pic_w, 64); + ctx->picinfo.buf_h = ALIGN(ctx->picinfo.pic_h, 64); + ctx->picinfo.fb_sz[0] = inst->vpu.fb_sz[0]; + ctx->picinfo.fb_sz[1] = inst->vpu.fb_sz[1]; + + inst->vsi->pic.pic_w = ctx->picinfo.pic_w; + inst->vsi->pic.pic_h = ctx->picinfo.pic_h; + inst->vsi->pic.buf_w = ctx->picinfo.buf_w; + inst->vsi->pic.buf_h = ctx->picinfo.buf_h; + inst->vsi->pic.fb_sz[0] = ctx->picinfo.fb_sz[0]; + inst->vsi->pic.fb_sz[1] = ctx->picinfo.fb_sz[1]; + mtk_vcodec_debug(inst, "pic(%d, %d), buf(%d, %d)", + ctx->picinfo.pic_w, ctx->picinfo.pic_h, + ctx->picinfo.buf_w, ctx->picinfo.buf_h); + mtk_vcodec_debug(inst, "fb size: Y(%d), C(%d)", + ctx->picinfo.fb_sz[0], ctx->picinfo.fb_sz[1]); +} + +static int vdec_vp8_slice_alloc_working_buf(struct vdec_vp8_slice_inst *inst) +{ + int err; + struct mtk_vcodec_mem *mem; + + mem = &inst->seg_id_buf; + mem->size = VP8_SEG_ID_SZ; + err = mtk_vcodec_mem_alloc(inst->ctx, mem); + if (err) { + mtk_vcodec_err(inst, "Cannot allocate working buffer"); + return err; + } + inst->vsi->dec.seg_id_buf_dma = (u64)mem->dma_addr; + + mem = &inst->wrap_y_buf; + mem->size = VP8_PP_WRAPY_SZ; + err = mtk_vcodec_mem_alloc(inst->ctx, mem); + if (err) { + mtk_vcodec_err(inst, "cannot allocate WRAP Y buffer"); + return err; + } + inst->vsi->dec.wrap_y_dma = (u64)mem->dma_addr; + + mem = &inst->wrap_c_buf; + mem->size = VP8_PP_WRAPC_SZ; + err = mtk_vcodec_mem_alloc(inst->ctx, mem); + if (err) { + mtk_vcodec_err(inst, "cannot allocate WRAP C buffer"); + return err; + } + inst->vsi->dec.wrap_c_dma = (u64)mem->dma_addr; + + mem = &inst->vld_wrapper_buf; + mem->size = VP8_VLD_PRED_SZ; + err = mtk_vcodec_mem_alloc(inst->ctx, mem); + if (err) { + mtk_vcodec_err(inst, "cannot allocate vld wrapper buffer"); + return err; + } + inst->vsi->dec.vld_wrapper_dma = (u64)mem->dma_addr; + + return 0; +} + +static void vdec_vp8_slice_free_working_buf(struct vdec_vp8_slice_inst *inst) +{ + struct mtk_vcodec_mem *mem; + + mem = &inst->seg_id_buf; + if (mem->va) + mtk_vcodec_mem_free(inst->ctx, mem); + inst->vsi->dec.seg_id_buf_dma = 0; + + mem = &inst->wrap_y_buf; + if (mem->va) + mtk_vcodec_mem_free(inst->ctx, mem); + inst->vsi->dec.wrap_y_dma = 0; + + mem = &inst->wrap_c_buf; + if (mem->va) + mtk_vcodec_mem_free(inst->ctx, mem); + inst->vsi->dec.wrap_c_dma = 0; + + mem = &inst->vld_wrapper_buf; + if (mem->va) + mtk_vcodec_mem_free(inst->ctx, mem); + inst->vsi->dec.vld_wrapper_dma = 0; +} + +static u64 vdec_vp8_slice_get_ref_by_ts(const struct v4l2_ctrl_vp8_frame *frame_header, + int index) +{ + switch (index) { + case 0: + return frame_header->last_frame_ts; + case 1: + return frame_header->golden_frame_ts; + case 2: + return frame_header->alt_frame_ts; + default: + break; + } + + return -1; +} + +static int vdec_vp8_slice_get_decode_parameters(struct vdec_vp8_slice_inst *inst) +{ + const struct v4l2_ctrl_vp8_frame *frame_header; + struct mtk_vcodec_ctx *ctx = inst->ctx; + struct vb2_queue *vq; + struct vb2_buffer *vb; + u64 referenct_ts; + int index, vb2_index; + + frame_header = vdec_vp8_slice_get_ctrl_ptr(inst->ctx, V4L2_CID_STATELESS_VP8_FRAME); + if (IS_ERR(frame_header)) + return PTR_ERR(frame_header); + + vq = v4l2_m2m_get_vq(ctx->m2m_ctx, V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE); + for (index = 0; index < 3; index++) { + referenct_ts = vdec_vp8_slice_get_ref_by_ts(frame_header, index); + vb2_index = vb2_find_timestamp(vq, referenct_ts, 0); + if (vb2_index < 0) { + if (!V4L2_VP8_FRAME_IS_KEY_FRAME(frame_header)) + mtk_vcodec_err(inst, "reference invalid: index(%d) ts(%lld)", + index, referenct_ts); + inst->vsi->vp8_dpb_info[index].reference_flag = 0; + continue; + } + inst->vsi->vp8_dpb_info[index].reference_flag = 1; + + vb = vq->bufs[vb2_index]; + inst->vsi->vp8_dpb_info[index].y_dma_addr = + vb2_dma_contig_plane_dma_addr(vb, 0); + if (ctx->q_data[MTK_Q_DATA_DST].fmt->num_planes == 2) + inst->vsi->vp8_dpb_info[index].c_dma_addr = + vb2_dma_contig_plane_dma_addr(vb, 1); + else + inst->vsi->vp8_dpb_info[index].c_dma_addr = + inst->vsi->vp8_dpb_info[index].y_dma_addr + + ctx->picinfo.fb_sz[0]; + } + + inst->vsi->dec.frame_header_type = frame_header->flags >> 1; + + return 0; +} + +static int vdec_vp8_slice_init(struct mtk_vcodec_ctx *ctx) +{ + struct vdec_vp8_slice_inst *inst; + int err; + + inst = kzalloc(sizeof(*inst), GFP_KERNEL); + if (!inst) + return -ENOMEM; + + inst->ctx = ctx; + + inst->vpu.id = SCP_IPI_VDEC_LAT; + inst->vpu.core_id = SCP_IPI_VDEC_CORE; + inst->vpu.ctx = ctx; + inst->vpu.codec_type = ctx->current_codec; + inst->vpu.capture_type = ctx->capture_fourcc; + + err = vpu_dec_init(&inst->vpu); + if (err) { + mtk_vcodec_err(inst, "vdec_vp8 init err=%d", err); + goto error_free_inst; + } + + inst->vsi = inst->vpu.vsi; + err = vdec_vp8_slice_alloc_working_buf(inst); + if (err) + goto error_deinit; + + mtk_vcodec_debug(inst, "vp8 struct size = %d vsi: %d\n", + (int)sizeof(struct v4l2_ctrl_vp8_frame), + (int)sizeof(struct vdec_vp8_slice_vsi)); + mtk_vcodec_debug(inst, "vp8:%p, codec_type = 0x%x vsi: 0x%p", + inst, inst->vpu.codec_type, inst->vpu.vsi); + + ctx->drv_handle = inst; + return 0; + +error_deinit: + vpu_dec_deinit(&inst->vpu); +error_free_inst: + kfree(inst); + return err; +} + +static int vdec_vp8_slice_decode(void *h_vdec, struct mtk_vcodec_mem *bs, + struct vdec_fb *fb, bool *res_chg) +{ + struct vdec_vp8_slice_inst *inst = h_vdec; + struct vdec_vpu_inst *vpu = &inst->vpu; + struct mtk_video_dec_buf *src_buf_info, *dst_buf_info; + unsigned int data; + u64 y_fb_dma, c_fb_dma; + int err, timeout; + + /* Resolution changes are never initiated by us */ + *res_chg = false; + + /* bs NULL means flush decoder */ + if (!bs) + return vpu_dec_reset(vpu); + + src_buf_info = container_of(bs, struct mtk_video_dec_buf, bs_buffer); + + fb = inst->ctx->dev->vdec_pdata->get_cap_buffer(inst->ctx); + dst_buf_info = container_of(fb, struct mtk_video_dec_buf, frame_buffer); + + y_fb_dma = fb ? (u64)fb->base_y.dma_addr : 0; + if (inst->ctx->q_data[MTK_Q_DATA_DST].fmt->num_planes == 1) + c_fb_dma = y_fb_dma + + inst->ctx->picinfo.buf_w * inst->ctx->picinfo.buf_h; + else + c_fb_dma = fb ? (u64)fb->base_c.dma_addr : 0; + + inst->vsi->dec.bs_dma = (u64)bs->dma_addr; + inst->vsi->dec.bs_sz = bs->size; + inst->vsi->dec.cur_y_fb_dma = y_fb_dma; + inst->vsi->dec.cur_c_fb_dma = c_fb_dma; + + mtk_vcodec_debug(inst, "frame[%d] bs(%zu 0x%llx) y/c(0x%llx 0x%llx)", + inst->ctx->decoded_frame_cnt, + bs->size, (u64)bs->dma_addr, + y_fb_dma, c_fb_dma); + + v4l2_m2m_buf_copy_metadata(&src_buf_info->m2m_buf.vb, + &dst_buf_info->m2m_buf.vb, true); + + err = vdec_vp8_slice_get_decode_parameters(inst); + if (err) + goto error; + + err = vpu_dec_start(vpu, &data, 1); + if (err) { + mtk_vcodec_debug(inst, "vp8 dec start err!"); + goto error; + } + + if (inst->vsi->dec.resolution_changed) { + mtk_vcodec_debug(inst, "- resolution_changed -"); + *res_chg = true; + return 0; + } + + /* wait decode done interrupt */ + timeout = mtk_vcodec_wait_for_done_ctx(inst->ctx, MTK_INST_IRQ_RECEIVED, + 50, MTK_VDEC_CORE); + + err = vpu_dec_end(vpu); + if (err || timeout) + mtk_vcodec_debug(inst, "vp8 dec error timeout:%d err: %d pic_%d", + timeout, err, inst->ctx->decoded_frame_cnt); + + mtk_vcodec_debug(inst, "pic[%d] crc: 0x%x 0x%x 0x%x 0x%x 0x%x 0x%x 0x%x 0x%x", + inst->ctx->decoded_frame_cnt, + inst->vsi->dec.crc[0], inst->vsi->dec.crc[1], + inst->vsi->dec.crc[2], inst->vsi->dec.crc[3], + inst->vsi->dec.crc[4], inst->vsi->dec.crc[5], + inst->vsi->dec.crc[6], inst->vsi->dec.crc[7]); + + inst->ctx->decoded_frame_cnt++; +error: + return err; +} + +static int vdec_vp8_slice_get_param(void *h_vdec, enum vdec_get_param_type type, void *out) +{ + struct vdec_vp8_slice_inst *inst = h_vdec; + + switch (type) { + case GET_PARAM_PIC_INFO: + vdec_vp8_slice_get_pic_info(inst); + break; + case GET_PARAM_CROP_INFO: + mtk_vcodec_debug(inst, "No need to get vp8 crop information."); + break; + case GET_PARAM_DPB_SIZE: + *((unsigned int *)out) = VP8_DPB_SIZE; + break; + default: + mtk_vcodec_err(inst, "invalid get parameter type=%d", type); + return -EINVAL; + } + + return 0; +} + +static void vdec_vp8_slice_deinit(void *h_vdec) +{ + struct vdec_vp8_slice_inst *inst = h_vdec; + + mtk_vcodec_debug_enter(inst); + + vpu_dec_deinit(&inst->vpu); + vdec_vp8_slice_free_working_buf(inst); + kfree(inst); +} + +const struct vdec_common_if vdec_vp8_slice_if = { + .init = vdec_vp8_slice_init, + .decode = vdec_vp8_slice_decode, + .get_param = vdec_vp8_slice_get_param, + .deinit = vdec_vp8_slice_deinit, +}; diff --git a/drivers/media/platform/mediatek/vcodec/vdec/vdec_vp9_req_lat_if.c b/drivers/media/platform/mediatek/vcodec/vdec/vdec_vp9_req_lat_if.c new file mode 100644 index 000000000000..023aba4ec2c4 --- /dev/null +++ b/drivers/media/platform/mediatek/vcodec/vdec/vdec_vp9_req_lat_if.c @@ -0,0 +1,2030 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2021 MediaTek Inc. + * Author: George Sun <george.sun@mediatek.com> + */ + +#include <linux/module.h> +#include <linux/slab.h> +#include <media/videobuf2-dma-contig.h> +#include <media/v4l2-vp9.h> + +#include "../mtk_vcodec_util.h" +#include "../mtk_vcodec_dec.h" +#include "../mtk_vcodec_intr.h" +#include "../vdec_drv_base.h" +#include "../vdec_drv_if.h" +#include "../vdec_vpu_if.h" + +/* reset_frame_context defined in VP9 spec */ +#define VP9_RESET_FRAME_CONTEXT_NONE0 0 +#define VP9_RESET_FRAME_CONTEXT_NONE1 1 +#define VP9_RESET_FRAME_CONTEXT_SPEC 2 +#define VP9_RESET_FRAME_CONTEXT_ALL 3 + +#define VP9_TILE_BUF_SIZE 4096 +#define VP9_PROB_BUF_SIZE 2560 +#define VP9_COUNTS_BUF_SIZE 16384 + +#define HDR_FLAG(x) (!!((hdr)->flags & V4L2_VP9_FRAME_FLAG_##x)) +#define LF_FLAG(x) (!!((lf)->flags & V4L2_VP9_LOOP_FILTER_FLAG_##x)) +#define SEG_FLAG(x) (!!((seg)->flags & V4L2_VP9_SEGMENTATION_FLAG_##x)) +#define VP9_BAND_6(band) ((band) == 0 ? 3 : 6) + +/* + * struct vdec_vp9_slice_frame_ctx - vp9 prob tables footprint + */ +struct vdec_vp9_slice_frame_ctx { + struct { + u8 probs[6][3]; + u8 padding[2]; + } coef_probs[4][2][2][6]; + + u8 y_mode_prob[4][16]; + u8 switch_interp_prob[4][16]; + u8 seg[32]; /* ignore */ + u8 comp_inter_prob[16]; + u8 comp_ref_prob[16]; + u8 single_ref_prob[5][2]; + u8 single_ref_prob_padding[6]; + + u8 joint[3]; + u8 joint_padding[13]; + struct { + u8 sign; + u8 classes[10]; + u8 padding[5]; + } sign_classes[2]; + struct { + u8 class0[1]; + u8 bits[10]; + u8 padding[5]; + } class0_bits[2]; + struct { + u8 class0_fp[2][3]; + u8 fp[3]; + u8 class0_hp; + u8 hp; + u8 padding[5]; + } class0_fp_hp[2]; + + u8 uv_mode_prob[10][16]; + u8 uv_mode_prob_padding[2][16]; + + u8 partition_prob[16][4]; + + u8 inter_mode_probs[7][4]; + u8 skip_probs[4]; + + u8 tx_p8x8[2][4]; + u8 tx_p16x16[2][4]; + u8 tx_p32x32[2][4]; + u8 intra_inter_prob[8]; +}; + +/* + * struct vdec_vp9_slice_frame_counts - vp9 counts tables footprint + */ +struct vdec_vp9_slice_frame_counts { + union { + struct { + u32 band_0[3]; + u32 padding0[1]; + u32 band_1_5[5][6]; + u32 padding1[2]; + } eob_branch[4][2][2]; + u32 eob_branch_space[256 * 4]; + }; + + struct { + u32 band_0[3][4]; + u32 band_1_5[5][6][4]; + } coef_probs[4][2][2]; + + u32 intra_inter[4][2]; + u32 comp_inter[5][2]; + u32 comp_inter_padding[2]; + u32 comp_ref[5][2]; + u32 comp_ref_padding[2]; + u32 single_ref[5][2][2]; + u32 inter_mode[7][4]; + u32 y_mode[4][12]; + u32 uv_mode[10][10]; + u32 partition[16][4]; + u32 switchable_interp[4][4]; + + u32 tx_p8x8[2][2]; + u32 tx_p16x16[2][4]; + u32 tx_p32x32[2][4]; + + u32 skip[3][4]; + + u32 joint[4]; + + struct { + u32 sign[2]; + u32 class0[2]; + u32 classes[12]; + u32 bits[10][2]; + u32 padding[4]; + u32 class0_fp[2][4]; + u32 fp[4]; + u32 class0_hp[2]; + u32 hp[2]; + } mvcomp[2]; + + u32 reserved[126][4]; +}; + +/** + * struct vdec_vp9_slice_counts_map - vp9 counts tables to map + * v4l2_vp9_frame_symbol_counts + * @skip: skip counts. + * @y_mode: Y prediction mode counts. + * @filter: interpolation filter counts. + * @mv_joint: motion vector joint counts. + * @sign: motion vector sign counts. + * @classes: motion vector class counts. + * @class0: motion vector class0 bit counts. + * @bits: motion vector bits counts. + * @class0_fp: motion vector class0 fractional bit counts. + * @fp: motion vector fractional bit counts. + * @class0_hp: motion vector class0 high precision fractional bit counts. + * @hp: motion vector high precision fractional bit counts. + */ +struct vdec_vp9_slice_counts_map { + u32 skip[3][2]; + u32 y_mode[4][10]; + u32 filter[4][3]; + u32 sign[2][2]; + u32 classes[2][11]; + u32 class0[2][2]; + u32 bits[2][10][2]; + u32 class0_fp[2][2][4]; + u32 fp[2][4]; + u32 class0_hp[2][2]; + u32 hp[2][2]; +}; + +/* + * struct vdec_vp9_slice_uncompressed_header - vp9 uncompressed header syntax + * used for decoding + */ +struct vdec_vp9_slice_uncompressed_header { + u8 profile; + u8 last_frame_type; + u8 frame_type; + + u8 last_show_frame; + u8 show_frame; + u8 error_resilient_mode; + + u8 bit_depth; + u8 padding0[1]; + u16 last_frame_width; + u16 last_frame_height; + u16 frame_width; + u16 frame_height; + + u8 intra_only; + u8 reset_frame_context; + u8 ref_frame_sign_bias[4]; + u8 allow_high_precision_mv; + u8 interpolation_filter; + + u8 refresh_frame_context; + u8 frame_parallel_decoding_mode; + u8 frame_context_idx; + + /* loop_filter_params */ + u8 loop_filter_level; + u8 loop_filter_sharpness; + u8 loop_filter_delta_enabled; + s8 loop_filter_ref_deltas[4]; + s8 loop_filter_mode_deltas[2]; + + /* quantization_params */ + u8 base_q_idx; + s8 delta_q_y_dc; + s8 delta_q_uv_dc; + s8 delta_q_uv_ac; + + /* segmentation_params */ + u8 segmentation_enabled; + u8 segmentation_update_map; + u8 segmentation_tree_probs[7]; + u8 padding1[1]; + u8 segmentation_temporal_udpate; + u8 segmentation_pred_prob[3]; + u8 segmentation_update_data; + u8 segmentation_abs_or_delta_update; + u8 feature_enabled[8]; + s16 feature_value[8][4]; + + /* tile_info */ + u8 tile_cols_log2; + u8 tile_rows_log2; + u8 padding2[2]; + + u16 uncompressed_header_size; + u16 header_size_in_bytes; + + /* LAT OUT, CORE IN */ + u32 dequant[8][4]; +}; + +/* + * struct vdec_vp9_slice_compressed_header - vp9 compressed header syntax + * used for decoding. + */ +struct vdec_vp9_slice_compressed_header { + u8 tx_mode; + u8 ref_mode; + u8 comp_fixed_ref; + u8 comp_var_ref[2]; + u8 padding[3]; +}; + +/* + * struct vdec_vp9_slice_tiles - vp9 tile syntax + */ +struct vdec_vp9_slice_tiles { + u32 size[4][64]; + u32 mi_rows[4]; + u32 mi_cols[64]; + u8 actual_rows; + u8 padding[7]; +}; + +/* + * struct vdec_vp9_slice_reference - vp9 reference frame information + */ +struct vdec_vp9_slice_reference { + u16 frame_width; + u16 frame_height; + u8 bit_depth; + u8 subsampling_x; + u8 subsampling_y; + u8 padding; +}; + +/* + * struct vdec_vp9_slice_frame - vp9 syntax used for decoding + */ +struct vdec_vp9_slice_frame { + struct vdec_vp9_slice_uncompressed_header uh; + struct vdec_vp9_slice_compressed_header ch; + struct vdec_vp9_slice_tiles tiles; + struct vdec_vp9_slice_reference ref[3]; +}; + +/* + * struct vdec_vp9_slice_init_vsi - VSI used to initialize instance + */ +struct vdec_vp9_slice_init_vsi { + unsigned int architecture; + unsigned int reserved; + u64 core_vsi; + /* default frame context's position in MicroP */ + u64 default_frame_ctx; +}; + +/* + * struct vdec_vp9_slice_mem - memory address and size + */ +struct vdec_vp9_slice_mem { + union { + u64 buf; + dma_addr_t dma_addr; + }; + union { + size_t size; + dma_addr_t dma_addr_end; + u64 padding; + }; +}; + +/* + * struct vdec_vp9_slice_bs - input buffer for decoding + */ +struct vdec_vp9_slice_bs { + struct vdec_vp9_slice_mem buf; + struct vdec_vp9_slice_mem frame; +}; + +/* + * struct vdec_vp9_slice_fb - frame buffer for decoding + */ +struct vdec_vp9_slice_fb { + struct vdec_vp9_slice_mem y; + struct vdec_vp9_slice_mem c; +}; + +/* + * struct vdec_vp9_slice_state - decoding state + */ +struct vdec_vp9_slice_state { + int err; + unsigned int full; + unsigned int timeout; + unsigned int perf; + + unsigned int crc[12]; +}; + +/** + * struct vdec_vp9_slice_vsi - exchange decoding information + * between Main CPU and MicroP + * + * @bs: input buffer + * @fb: output buffer + * @ref: 3 reference buffers + * @mv: mv working buffer + * @seg: segmentation working buffer + * @tile: tile buffer + * @prob: prob table buffer, used to set/update prob table + * @counts: counts table buffer, used to update prob table + * @ube: general buffer + * @trans: trans buffer position in general buffer + * @err_map: error buffer + * @row_info: row info buffer + * @frame: decoding syntax + * @state: decoding state + */ +struct vdec_vp9_slice_vsi { + /* used in LAT stage */ + struct vdec_vp9_slice_bs bs; + /* used in Core stage */ + struct vdec_vp9_slice_fb fb; + struct vdec_vp9_slice_fb ref[3]; + + struct vdec_vp9_slice_mem mv[2]; + struct vdec_vp9_slice_mem seg[2]; + struct vdec_vp9_slice_mem tile; + struct vdec_vp9_slice_mem prob; + struct vdec_vp9_slice_mem counts; + + /* LAT stage's output, Core stage's input */ + struct vdec_vp9_slice_mem ube; + struct vdec_vp9_slice_mem trans; + struct vdec_vp9_slice_mem err_map; + struct vdec_vp9_slice_mem row_info; + + /* decoding parameters */ + struct vdec_vp9_slice_frame frame; + + struct vdec_vp9_slice_state state; +}; + +/** + * struct vdec_vp9_slice_pfc - per-frame context that contains a local vsi. + * pass it from lat to core + * + * @vsi: local vsi. copy to/from remote vsi before/after decoding + * @ref_idx: reference buffer index + * @seq: picture sequence + * @state: decoding state + */ +struct vdec_vp9_slice_pfc { + struct vdec_vp9_slice_vsi vsi; + + u64 ref_idx[3]; + + int seq; + + /* LAT/Core CRC */ + struct vdec_vp9_slice_state state[2]; +}; + +/* + * enum vdec_vp9_slice_resolution_level + */ +enum vdec_vp9_slice_resolution_level { + VP9_RES_NONE, + VP9_RES_FHD, + VP9_RES_4K, + VP9_RES_8K, +}; + +/* + * struct vdec_vp9_slice_ref - picture's width & height should kept + * for later decoding as reference picture + */ +struct vdec_vp9_slice_ref { + unsigned int width; + unsigned int height; +}; + +/** + * struct vdec_vp9_slice_instance - represent one vp9 instance + * + * @ctx: pointer to codec's context + * @vpu: VPU instance + * @seq: global picture sequence + * @level: level of current resolution + * @width: width of last picture + * @height: height of last picture + * @frame_type: frame_type of last picture + * @irq: irq to Main CPU or MicroP + * @show_frame: show_frame of last picture + * @dpb: picture information (width/height) for reference + * @mv: mv working buffer + * @seg: segmentation working buffer + * @tile: tile buffer + * @prob: prob table buffer, used to set/update prob table + * @counts: counts table buffer, used to update prob table + * @frame_ctx: 4 frame context according to VP9 Spec + * @frame_ctx_helper: 4 frame context according to newest kernel spec + * @dirty: state of each frame context + * @init_vsi: vsi used for initialized VP9 instance + * @vsi: vsi used for decoding/flush ... + * @core_vsi: vsi used for Core stage + * @counts_map: used map to counts_helper + * @counts_helper: counts table according to newest kernel spec + */ +struct vdec_vp9_slice_instance { + struct mtk_vcodec_ctx *ctx; + struct vdec_vpu_inst vpu; + + int seq; + + enum vdec_vp9_slice_resolution_level level; + + /* for resolution change and get_pic_info */ + unsigned int width; + unsigned int height; + + /* for last_frame_type */ + unsigned int frame_type; + unsigned int irq; + + unsigned int show_frame; + + /* maintain vp9 reference frame state */ + struct vdec_vp9_slice_ref dpb[VB2_MAX_FRAME]; + + /* + * normal working buffers + * mv[0]/seg[0]/tile/prob/counts is used for LAT + * mv[1]/seg[1] is used for CORE + */ + struct mtk_vcodec_mem mv[2]; + struct mtk_vcodec_mem seg[2]; + struct mtk_vcodec_mem tile; + struct mtk_vcodec_mem prob; + struct mtk_vcodec_mem counts; + + /* 4 prob tables */ + struct vdec_vp9_slice_frame_ctx frame_ctx[4]; + /*4 helper tables */ + struct v4l2_vp9_frame_context frame_ctx_helper; + unsigned char dirty[4]; + + /* MicroP vsi */ + union { + struct vdec_vp9_slice_init_vsi *init_vsi; + struct vdec_vp9_slice_vsi *vsi; + }; + struct vdec_vp9_slice_vsi *core_vsi; + + struct vdec_vp9_slice_counts_map counts_map; + struct v4l2_vp9_frame_symbol_counts counts_helper; +}; + +/* + * all VP9 instances could share this default frame context. + */ +static struct vdec_vp9_slice_frame_ctx *vdec_vp9_slice_default_frame_ctx; +static DEFINE_MUTEX(vdec_vp9_slice_frame_ctx_lock); + +static int vdec_vp9_slice_core_decode(struct vdec_lat_buf *lat_buf); + +static int vdec_vp9_slice_init_default_frame_ctx(struct vdec_vp9_slice_instance *instance) +{ + struct vdec_vp9_slice_frame_ctx *remote_frame_ctx; + struct vdec_vp9_slice_frame_ctx *frame_ctx; + struct mtk_vcodec_ctx *ctx; + struct vdec_vp9_slice_init_vsi *vsi; + int ret = 0; + + ctx = instance->ctx; + vsi = instance->vpu.vsi; + if (!ctx || !vsi) + return -EINVAL; + + remote_frame_ctx = mtk_vcodec_fw_map_dm_addr(ctx->dev->fw_handler, + (u32)vsi->default_frame_ctx); + if (!remote_frame_ctx) { + mtk_vcodec_err(instance, "failed to map default frame ctx\n"); + return -EINVAL; + } + + mutex_lock(&vdec_vp9_slice_frame_ctx_lock); + if (vdec_vp9_slice_default_frame_ctx) + goto out; + + frame_ctx = kmalloc(sizeof(*frame_ctx), GFP_KERNEL); + if (!frame_ctx) { + ret = -ENOMEM; + goto out; + } + + memcpy(frame_ctx, remote_frame_ctx, sizeof(*frame_ctx)); + vdec_vp9_slice_default_frame_ctx = frame_ctx; + +out: + mutex_unlock(&vdec_vp9_slice_frame_ctx_lock); + + return ret; +} + +static int vdec_vp9_slice_alloc_working_buffer(struct vdec_vp9_slice_instance *instance, + struct vdec_vp9_slice_vsi *vsi) +{ + struct mtk_vcodec_ctx *ctx = instance->ctx; + enum vdec_vp9_slice_resolution_level level; + /* super blocks */ + unsigned int max_sb_w; + unsigned int max_sb_h; + unsigned int max_w; + unsigned int max_h; + unsigned int w; + unsigned int h; + size_t size; + int ret; + int i; + + w = vsi->frame.uh.frame_width; + h = vsi->frame.uh.frame_height; + + if (w > VCODEC_DEC_4K_CODED_WIDTH || + h > VCODEC_DEC_4K_CODED_HEIGHT) { + return -EINVAL; + } else if (w > MTK_VDEC_MAX_W || h > MTK_VDEC_MAX_H) { + /* 4K */ + level = VP9_RES_4K; + max_w = VCODEC_DEC_4K_CODED_WIDTH; + max_h = VCODEC_DEC_4K_CODED_HEIGHT; + } else { + /* FHD */ + level = VP9_RES_FHD; + max_w = MTK_VDEC_MAX_W; + max_h = MTK_VDEC_MAX_H; + } + + if (level == instance->level) + return 0; + + mtk_vcodec_debug(instance, "resolution level changed, from %u to %u, %ux%u", + instance->level, level, w, h); + + max_sb_w = DIV_ROUND_UP(max_w, 64); + max_sb_h = DIV_ROUND_UP(max_h, 64); + ret = -ENOMEM; + + /* + * Lat-flush must wait core idle, otherwise core will + * use released buffers + */ + + size = (max_sb_w * max_sb_h + 2) * 576; + for (i = 0; i < 2; i++) { + if (instance->mv[i].va) + mtk_vcodec_mem_free(ctx, &instance->mv[i]); + instance->mv[i].size = size; + if (mtk_vcodec_mem_alloc(ctx, &instance->mv[i])) + goto err; + } + + size = (max_sb_w * max_sb_h * 32) + 256; + for (i = 0; i < 2; i++) { + if (instance->seg[i].va) + mtk_vcodec_mem_free(ctx, &instance->seg[i]); + instance->seg[i].size = size; + if (mtk_vcodec_mem_alloc(ctx, &instance->seg[i])) + goto err; + } + + if (!instance->tile.va) { + instance->tile.size = VP9_TILE_BUF_SIZE; + if (mtk_vcodec_mem_alloc(ctx, &instance->tile)) + goto err; + } + + if (!instance->prob.va) { + instance->prob.size = VP9_PROB_BUF_SIZE; + if (mtk_vcodec_mem_alloc(ctx, &instance->prob)) + goto err; + } + + if (!instance->counts.va) { + instance->counts.size = VP9_COUNTS_BUF_SIZE; + if (mtk_vcodec_mem_alloc(ctx, &instance->counts)) + goto err; + } + + instance->level = level; + return 0; + +err: + instance->level = VP9_RES_NONE; + return ret; +} + +static void vdec_vp9_slice_free_working_buffer(struct vdec_vp9_slice_instance *instance) +{ + struct mtk_vcodec_ctx *ctx = instance->ctx; + int i; + + for (i = 0; i < ARRAY_SIZE(instance->mv); i++) { + if (instance->mv[i].va) + mtk_vcodec_mem_free(ctx, &instance->mv[i]); + } + for (i = 0; i < ARRAY_SIZE(instance->seg); i++) { + if (instance->seg[i].va) + mtk_vcodec_mem_free(ctx, &instance->seg[i]); + } + if (instance->tile.va) + mtk_vcodec_mem_free(ctx, &instance->tile); + if (instance->prob.va) + mtk_vcodec_mem_free(ctx, &instance->prob); + if (instance->counts.va) + mtk_vcodec_mem_free(ctx, &instance->counts); + + instance->level = VP9_RES_NONE; +} + +static void vdec_vp9_slice_vsi_from_remote(struct vdec_vp9_slice_vsi *vsi, + struct vdec_vp9_slice_vsi *remote_vsi, + int skip) +{ + struct vdec_vp9_slice_frame *rf; + struct vdec_vp9_slice_frame *f; + + /* + * compressed header + * dequant + * buffer position + * decode state + */ + if (!skip) { + rf = &remote_vsi->frame; + f = &vsi->frame; + memcpy(&f->ch, &rf->ch, sizeof(f->ch)); + memcpy(&f->uh.dequant, &rf->uh.dequant, sizeof(f->uh.dequant)); + memcpy(&vsi->trans, &remote_vsi->trans, sizeof(vsi->trans)); + } + + memcpy(&vsi->state, &remote_vsi->state, sizeof(vsi->state)); +} + +static void vdec_vp9_slice_vsi_to_remote(struct vdec_vp9_slice_vsi *vsi, + struct vdec_vp9_slice_vsi *remote_vsi) +{ + memcpy(remote_vsi, vsi, sizeof(*vsi)); +} + +static int vdec_vp9_slice_tile_offset(int idx, int mi_num, int tile_log2) +{ + int sbs = (mi_num + 7) >> 3; + int offset = ((idx * sbs) >> tile_log2) << 3; + + return offset < mi_num ? offset : mi_num; +} + +static int vdec_vp9_slice_setup_lat_from_src_buf(struct vdec_vp9_slice_instance *instance, + struct vdec_lat_buf *lat_buf) +{ + struct vb2_v4l2_buffer *src; + struct vb2_v4l2_buffer *dst; + + src = v4l2_m2m_next_src_buf(instance->ctx->m2m_ctx); + if (!src) + return -EINVAL; + + lat_buf->src_buf_req = src->vb2_buf.req_obj.req; + + dst = &lat_buf->ts_info; + v4l2_m2m_buf_copy_metadata(src, dst, true); + return 0; +} + +static void vdec_vp9_slice_setup_hdr(struct vdec_vp9_slice_instance *instance, + struct vdec_vp9_slice_uncompressed_header *uh, + struct v4l2_ctrl_vp9_frame *hdr) +{ + int i; + + uh->profile = hdr->profile; + uh->last_frame_type = instance->frame_type; + uh->frame_type = !HDR_FLAG(KEY_FRAME); + uh->last_show_frame = instance->show_frame; + uh->show_frame = HDR_FLAG(SHOW_FRAME); + uh->error_resilient_mode = HDR_FLAG(ERROR_RESILIENT); + uh->bit_depth = hdr->bit_depth; + uh->last_frame_width = instance->width; + uh->last_frame_height = instance->height; + uh->frame_width = hdr->frame_width_minus_1 + 1; + uh->frame_height = hdr->frame_height_minus_1 + 1; + uh->intra_only = HDR_FLAG(INTRA_ONLY); + /* map v4l2 enum to values defined in VP9 spec for firmware */ + switch (hdr->reset_frame_context) { + case V4L2_VP9_RESET_FRAME_CTX_NONE: + uh->reset_frame_context = VP9_RESET_FRAME_CONTEXT_NONE0; + break; + case V4L2_VP9_RESET_FRAME_CTX_SPEC: + uh->reset_frame_context = VP9_RESET_FRAME_CONTEXT_SPEC; + break; + case V4L2_VP9_RESET_FRAME_CTX_ALL: + uh->reset_frame_context = VP9_RESET_FRAME_CONTEXT_ALL; + break; + default: + uh->reset_frame_context = VP9_RESET_FRAME_CONTEXT_NONE0; + break; + } + /* + * ref_frame_sign_bias specifies the intended direction + * of the motion vector in time for each reference frame. + * - INTRA_FRAME = 0, + * - LAST_FRAME = 1, + * - GOLDEN_FRAME = 2, + * - ALTREF_FRAME = 3, + * ref_frame_sign_bias[INTRA_FRAME] is always 0 + * and VDA only passes another 3 directions + */ + uh->ref_frame_sign_bias[0] = 0; + for (i = 0; i < 3; i++) + uh->ref_frame_sign_bias[i + 1] = + !!(hdr->ref_frame_sign_bias & (1 << i)); + uh->allow_high_precision_mv = HDR_FLAG(ALLOW_HIGH_PREC_MV); + uh->interpolation_filter = hdr->interpolation_filter; + uh->refresh_frame_context = HDR_FLAG(REFRESH_FRAME_CTX); + uh->frame_parallel_decoding_mode = HDR_FLAG(PARALLEL_DEC_MODE); + uh->frame_context_idx = hdr->frame_context_idx; + + /* tile info */ + uh->tile_cols_log2 = hdr->tile_cols_log2; + uh->tile_rows_log2 = hdr->tile_rows_log2; + + uh->uncompressed_header_size = hdr->uncompressed_header_size; + uh->header_size_in_bytes = hdr->compressed_header_size; +} + +static void vdec_vp9_slice_setup_frame_ctx(struct vdec_vp9_slice_instance *instance, + struct vdec_vp9_slice_uncompressed_header *uh, + struct v4l2_ctrl_vp9_frame *hdr) +{ + int error_resilient_mode; + int reset_frame_context; + int key_frame; + int intra_only; + int i; + + key_frame = HDR_FLAG(KEY_FRAME); + intra_only = HDR_FLAG(INTRA_ONLY); + error_resilient_mode = HDR_FLAG(ERROR_RESILIENT); + reset_frame_context = uh->reset_frame_context; + + /* + * according to "6.2 Uncompressed header syntax" in + * "VP9 Bitstream & Decoding Process Specification", + * reset @frame_context_idx when (FrameIsIntra || error_resilient_mode) + */ + if (key_frame || intra_only || error_resilient_mode) { + /* + * @reset_frame_context specifies + * whether the frame context should be + * reset to default values: + * 0 or 1 means do not reset any frame context + * 2 resets just the context specified in the frame header + * 3 resets all contexts + */ + if (key_frame || error_resilient_mode || + reset_frame_context == 3) { + /* use default table */ + for (i = 0; i < 4; i++) + instance->dirty[i] = 0; + } else if (reset_frame_context == 2) { + instance->dirty[uh->frame_context_idx] = 0; + } + uh->frame_context_idx = 0; + } +} + +static void vdec_vp9_slice_setup_loop_filter(struct vdec_vp9_slice_uncompressed_header *uh, + struct v4l2_vp9_loop_filter *lf) +{ + int i; + + uh->loop_filter_level = lf->level; + uh->loop_filter_sharpness = lf->sharpness; + uh->loop_filter_delta_enabled = LF_FLAG(DELTA_ENABLED); + for (i = 0; i < 4; i++) + uh->loop_filter_ref_deltas[i] = lf->ref_deltas[i]; + for (i = 0; i < 2; i++) + uh->loop_filter_mode_deltas[i] = lf->mode_deltas[i]; +} + +static void vdec_vp9_slice_setup_quantization(struct vdec_vp9_slice_uncompressed_header *uh, + struct v4l2_vp9_quantization *quant) +{ + uh->base_q_idx = quant->base_q_idx; + uh->delta_q_y_dc = quant->delta_q_y_dc; + uh->delta_q_uv_dc = quant->delta_q_uv_dc; + uh->delta_q_uv_ac = quant->delta_q_uv_ac; +} + +static void vdec_vp9_slice_setup_segmentation(struct vdec_vp9_slice_uncompressed_header *uh, + struct v4l2_vp9_segmentation *seg) +{ + int i; + int j; + + uh->segmentation_enabled = SEG_FLAG(ENABLED); + uh->segmentation_update_map = SEG_FLAG(UPDATE_MAP); + for (i = 0; i < 7; i++) + uh->segmentation_tree_probs[i] = seg->tree_probs[i]; + uh->segmentation_temporal_udpate = SEG_FLAG(TEMPORAL_UPDATE); + for (i = 0; i < 3; i++) + uh->segmentation_pred_prob[i] = seg->pred_probs[i]; + uh->segmentation_update_data = SEG_FLAG(UPDATE_DATA); + uh->segmentation_abs_or_delta_update = SEG_FLAG(ABS_OR_DELTA_UPDATE); + for (i = 0; i < 8; i++) { + uh->feature_enabled[i] = seg->feature_enabled[i]; + for (j = 0; j < 4; j++) + uh->feature_value[i][j] = seg->feature_data[i][j]; + } +} + +static int vdec_vp9_slice_setup_tile(struct vdec_vp9_slice_vsi *vsi, + struct v4l2_ctrl_vp9_frame *hdr) +{ + unsigned int rows_log2; + unsigned int cols_log2; + unsigned int rows; + unsigned int cols; + unsigned int mi_rows; + unsigned int mi_cols; + struct vdec_vp9_slice_tiles *tiles; + int offset; + int start; + int end; + int i; + + rows_log2 = hdr->tile_rows_log2; + cols_log2 = hdr->tile_cols_log2; + rows = 1 << rows_log2; + cols = 1 << cols_log2; + tiles = &vsi->frame.tiles; + tiles->actual_rows = 0; + + if (rows > 4 || cols > 64) + return -EINVAL; + + /* setup mi rows/cols information */ + mi_rows = (hdr->frame_height_minus_1 + 1 + 7) >> 3; + mi_cols = (hdr->frame_width_minus_1 + 1 + 7) >> 3; + + for (i = 0; i < rows; i++) { + start = vdec_vp9_slice_tile_offset(i, mi_rows, rows_log2); + end = vdec_vp9_slice_tile_offset(i + 1, mi_rows, rows_log2); + offset = end - start; + tiles->mi_rows[i] = (offset + 7) >> 3; + if (tiles->mi_rows[i]) + tiles->actual_rows++; + } + + for (i = 0; i < cols; i++) { + start = vdec_vp9_slice_tile_offset(i, mi_cols, cols_log2); + end = vdec_vp9_slice_tile_offset(i + 1, mi_cols, cols_log2); + offset = end - start; + tiles->mi_cols[i] = (offset + 7) >> 3; + } + + return 0; +} + +static void vdec_vp9_slice_setup_state(struct vdec_vp9_slice_vsi *vsi) +{ + memset(&vsi->state, 0, sizeof(vsi->state)); +} + +static void vdec_vp9_slice_setup_ref_idx(struct vdec_vp9_slice_pfc *pfc, + struct v4l2_ctrl_vp9_frame *hdr) +{ + pfc->ref_idx[0] = hdr->last_frame_ts; + pfc->ref_idx[1] = hdr->golden_frame_ts; + pfc->ref_idx[2] = hdr->alt_frame_ts; +} + +static int vdec_vp9_slice_setup_pfc(struct vdec_vp9_slice_instance *instance, + struct vdec_vp9_slice_pfc *pfc) +{ + struct v4l2_ctrl_vp9_frame *hdr; + struct vdec_vp9_slice_uncompressed_header *uh; + struct v4l2_ctrl *hdr_ctrl; + struct vdec_vp9_slice_vsi *vsi; + int ret; + + /* frame header */ + hdr_ctrl = v4l2_ctrl_find(&instance->ctx->ctrl_hdl, V4L2_CID_STATELESS_VP9_FRAME); + if (!hdr_ctrl || !hdr_ctrl->p_cur.p) + return -EINVAL; + + hdr = hdr_ctrl->p_cur.p; + vsi = &pfc->vsi; + uh = &vsi->frame.uh; + + /* setup vsi information */ + vdec_vp9_slice_setup_hdr(instance, uh, hdr); + vdec_vp9_slice_setup_frame_ctx(instance, uh, hdr); + vdec_vp9_slice_setup_loop_filter(uh, &hdr->lf); + vdec_vp9_slice_setup_quantization(uh, &hdr->quant); + vdec_vp9_slice_setup_segmentation(uh, &hdr->seg); + ret = vdec_vp9_slice_setup_tile(vsi, hdr); + if (ret) + return ret; + vdec_vp9_slice_setup_state(vsi); + + /* core stage needs buffer index to get ref y/c ... */ + vdec_vp9_slice_setup_ref_idx(pfc, hdr); + + pfc->seq = instance->seq; + instance->seq++; + + return 0; +} + +static int vdec_vp9_slice_setup_lat_buffer(struct vdec_vp9_slice_instance *instance, + struct vdec_vp9_slice_vsi *vsi, + struct mtk_vcodec_mem *bs, + struct vdec_lat_buf *lat_buf) +{ + int i; + + vsi->bs.buf.dma_addr = bs->dma_addr; + vsi->bs.buf.size = bs->size; + vsi->bs.frame.dma_addr = bs->dma_addr; + vsi->bs.frame.size = bs->size; + + for (i = 0; i < 2; i++) { + vsi->mv[i].dma_addr = instance->mv[i].dma_addr; + vsi->mv[i].size = instance->mv[i].size; + } + for (i = 0; i < 2; i++) { + vsi->seg[i].dma_addr = instance->seg[i].dma_addr; + vsi->seg[i].size = instance->seg[i].size; + } + vsi->tile.dma_addr = instance->tile.dma_addr; + vsi->tile.size = instance->tile.size; + vsi->prob.dma_addr = instance->prob.dma_addr; + vsi->prob.size = instance->prob.size; + vsi->counts.dma_addr = instance->counts.dma_addr; + vsi->counts.size = instance->counts.size; + + vsi->ube.dma_addr = lat_buf->ctx->msg_queue.wdma_addr.dma_addr; + vsi->ube.size = lat_buf->ctx->msg_queue.wdma_addr.size; + vsi->trans.dma_addr = lat_buf->ctx->msg_queue.wdma_wptr_addr; + /* used to store trans end */ + vsi->trans.dma_addr_end = lat_buf->ctx->msg_queue.wdma_rptr_addr; + vsi->err_map.dma_addr = lat_buf->wdma_err_addr.dma_addr; + vsi->err_map.size = lat_buf->wdma_err_addr.size; + + vsi->row_info.buf = 0; + vsi->row_info.size = 0; + + return 0; +} + +static int vdec_vp9_slice_setup_prob_buffer(struct vdec_vp9_slice_instance *instance, + struct vdec_vp9_slice_vsi *vsi) +{ + struct vdec_vp9_slice_frame_ctx *frame_ctx; + struct vdec_vp9_slice_uncompressed_header *uh; + + uh = &vsi->frame.uh; + + mtk_vcodec_debug(instance, "ctx dirty %u idx %d\n", + instance->dirty[uh->frame_context_idx], + uh->frame_context_idx); + + if (instance->dirty[uh->frame_context_idx]) + frame_ctx = &instance->frame_ctx[uh->frame_context_idx]; + else + frame_ctx = vdec_vp9_slice_default_frame_ctx; + memcpy(instance->prob.va, frame_ctx, sizeof(*frame_ctx)); + + return 0; +} + +static void vdec_vp9_slice_setup_seg_buffer(struct vdec_vp9_slice_instance *instance, + struct vdec_vp9_slice_vsi *vsi, + struct mtk_vcodec_mem *buf) +{ + struct vdec_vp9_slice_uncompressed_header *uh; + + /* reset segment buffer */ + uh = &vsi->frame.uh; + if (uh->frame_type == 0 || + uh->intra_only || + uh->error_resilient_mode || + uh->frame_width != instance->width || + uh->frame_height != instance->height) { + mtk_vcodec_debug(instance, "reset seg\n"); + memset(buf->va, 0, buf->size); + } +} + +/* + * parse tiles according to `6.4 Decode tiles syntax` + * in "vp9-bitstream-specification" + * + * frame contains uncompress header, compressed header and several tiles. + * this function parses tiles' position and size, stores them to tile buffer + * for decoding. + */ +static int vdec_vp9_slice_setup_tile_buffer(struct vdec_vp9_slice_instance *instance, + struct vdec_vp9_slice_vsi *vsi, + struct mtk_vcodec_mem *bs) +{ + struct vdec_vp9_slice_uncompressed_header *uh; + unsigned int rows_log2; + unsigned int cols_log2; + unsigned int rows; + unsigned int cols; + unsigned int mi_row; + unsigned int mi_col; + unsigned int offset; + unsigned int pa; + unsigned int size; + struct vdec_vp9_slice_tiles *tiles; + unsigned char *pos; + unsigned char *end; + unsigned char *va; + unsigned int *tb; + int i; + int j; + + uh = &vsi->frame.uh; + rows_log2 = uh->tile_rows_log2; + cols_log2 = uh->tile_cols_log2; + rows = 1 << rows_log2; + cols = 1 << cols_log2; + + if (rows > 4 || cols > 64) { + mtk_vcodec_err(instance, "tile_rows %u tile_cols %u\n", + rows, cols); + return -EINVAL; + } + + offset = uh->uncompressed_header_size + + uh->header_size_in_bytes; + if (bs->size <= offset) { + mtk_vcodec_err(instance, "bs size %zu tile offset %u\n", + bs->size, offset); + return -EINVAL; + } + + tiles = &vsi->frame.tiles; + /* setup tile buffer */ + + va = (unsigned char *)bs->va; + pos = va + offset; + end = va + bs->size; + /* truncated */ + pa = (unsigned int)bs->dma_addr + offset; + tb = instance->tile.va; + for (i = 0; i < rows; i++) { + for (j = 0; j < cols; j++) { + if (i == rows - 1 && + j == cols - 1) { + size = (unsigned int)(end - pos); + } else { + if (end - pos < 4) + return -EINVAL; + + size = (pos[0] << 24) | (pos[1] << 16) | + (pos[2] << 8) | pos[3]; + pos += 4; + pa += 4; + offset += 4; + if (end - pos < size) + return -EINVAL; + } + tiles->size[i][j] = size; + if (tiles->mi_rows[i]) { + *tb++ = (size << 3) + ((offset << 3) & 0x7f); + *tb++ = pa & ~0xf; + *tb++ = (pa << 3) & 0x7f; + mi_row = (tiles->mi_rows[i] - 1) & 0x1ff; + mi_col = (tiles->mi_cols[j] - 1) & 0x3f; + *tb++ = (mi_row << 6) + mi_col; + } + pos += size; + pa += size; + offset += size; + } + } + + return 0; +} + +static int vdec_vp9_slice_setup_lat(struct vdec_vp9_slice_instance *instance, + struct mtk_vcodec_mem *bs, + struct vdec_lat_buf *lat_buf, + struct vdec_vp9_slice_pfc *pfc) +{ + struct vdec_vp9_slice_vsi *vsi = &pfc->vsi; + int ret; + + ret = vdec_vp9_slice_setup_lat_from_src_buf(instance, lat_buf); + if (ret) + goto err; + + ret = vdec_vp9_slice_setup_pfc(instance, pfc); + if (ret) + goto err; + + ret = vdec_vp9_slice_alloc_working_buffer(instance, vsi); + if (ret) + goto err; + + ret = vdec_vp9_slice_setup_lat_buffer(instance, vsi, bs, lat_buf); + if (ret) + goto err; + + vdec_vp9_slice_setup_seg_buffer(instance, vsi, &instance->seg[0]); + + /* setup prob/tile buffers for LAT */ + + ret = vdec_vp9_slice_setup_prob_buffer(instance, vsi); + if (ret) + goto err; + + ret = vdec_vp9_slice_setup_tile_buffer(instance, vsi, bs); + if (ret) + goto err; + + return 0; + +err: + return ret; +} + +static +void vdec_vp9_slice_map_counts_eob_coef(unsigned int i, unsigned int j, unsigned int k, + struct vdec_vp9_slice_frame_counts *counts, + struct v4l2_vp9_frame_symbol_counts *counts_helper) +{ + u32 l = 0, m; + + /* + * helper eo -> mtk eo + * helpre e1 -> mtk c3 + * helper c0 -> c0 + * helper c1 -> c1 + * helper c2 -> c2 + */ + for (m = 0; m < 3; m++) { + counts_helper->coeff[i][j][k][l][m] = + (u32 (*)[3]) & counts->coef_probs[i][j][k].band_0[m]; + counts_helper->eob[i][j][k][l][m][0] = + &counts->eob_branch[i][j][k].band_0[m]; + counts_helper->eob[i][j][k][l][m][1] = + &counts->coef_probs[i][j][k].band_0[m][3]; + } + + for (l = 1; l < 6; l++) { + for (m = 0; m < 6; m++) { + counts_helper->coeff[i][j][k][l][m] = + (u32 (*)[3]) & counts->coef_probs[i][j][k].band_1_5[l - 1][m]; + counts_helper->eob[i][j][k][l][m][0] = + &counts->eob_branch[i][j][k].band_1_5[l - 1][m]; + counts_helper->eob[i][j][k][l][m][1] = + &counts->coef_probs[i][j][k].band_1_5[l - 1][m][3]; + } + } +} + +static void vdec_vp9_slice_counts_map_helper(struct vdec_vp9_slice_counts_map *counts_map, + struct vdec_vp9_slice_frame_counts *counts, + struct v4l2_vp9_frame_symbol_counts *counts_helper) +{ + int i, j, k; + + counts_helper->partition = &counts->partition; + counts_helper->intra_inter = &counts->intra_inter; + counts_helper->tx32p = &counts->tx_p32x32; + counts_helper->tx16p = &counts->tx_p16x16; + counts_helper->tx8p = &counts->tx_p8x8; + counts_helper->uv_mode = &counts->uv_mode; + + counts_helper->comp = &counts->comp_inter; + counts_helper->comp_ref = &counts->comp_ref; + counts_helper->single_ref = &counts->single_ref; + counts_helper->mv_mode = &counts->inter_mode; + counts_helper->mv_joint = &counts->joint; + + for (i = 0; i < ARRAY_SIZE(counts_map->skip); i++) + memcpy(counts_map->skip[i], counts->skip[i], + sizeof(counts_map->skip[0])); + counts_helper->skip = &counts_map->skip; + + for (i = 0; i < ARRAY_SIZE(counts_map->y_mode); i++) + memcpy(counts_map->y_mode[i], counts->y_mode[i], + sizeof(counts_map->y_mode[0])); + counts_helper->y_mode = &counts_map->y_mode; + + for (i = 0; i < ARRAY_SIZE(counts_map->filter); i++) + memcpy(counts_map->filter[i], counts->switchable_interp[i], + sizeof(counts_map->filter[0])); + counts_helper->filter = &counts_map->filter; + + for (i = 0; i < ARRAY_SIZE(counts_map->sign); i++) + memcpy(counts_map->sign[i], counts->mvcomp[i].sign, + sizeof(counts_map->sign[0])); + counts_helper->sign = &counts_map->sign; + + for (i = 0; i < ARRAY_SIZE(counts_map->classes); i++) + memcpy(counts_map->classes[i], counts->mvcomp[i].classes, + sizeof(counts_map->classes[0])); + counts_helper->classes = &counts_map->classes; + + for (i = 0; i < ARRAY_SIZE(counts_map->class0); i++) + memcpy(counts_map->class0[i], counts->mvcomp[i].class0, + sizeof(counts_map->class0[0])); + counts_helper->class0 = &counts_map->class0; + + for (i = 0; i < ARRAY_SIZE(counts_map->bits); i++) + for (j = 0; j < ARRAY_SIZE(counts_map->bits[0]); j++) + memcpy(counts_map->bits[i][j], counts->mvcomp[i].bits[j], + sizeof(counts_map->bits[0][0])); + counts_helper->bits = &counts_map->bits; + + for (i = 0; i < ARRAY_SIZE(counts_map->class0_fp); i++) + for (j = 0; j < ARRAY_SIZE(counts_map->class0_fp[0]); j++) + memcpy(counts_map->class0_fp[i][j], counts->mvcomp[i].class0_fp[j], + sizeof(counts_map->class0_fp[0][0])); + counts_helper->class0_fp = &counts_map->class0_fp; + + for (i = 0; i < ARRAY_SIZE(counts_map->fp); i++) + memcpy(counts_map->fp[i], counts->mvcomp[i].fp, + sizeof(counts_map->fp[0])); + counts_helper->fp = &counts_map->fp; + + for (i = 0; i < ARRAY_SIZE(counts_map->class0_hp); i++) + memcpy(counts_map->class0_hp[i], counts->mvcomp[i].class0_hp, + sizeof(counts_map->class0_hp[0])); + counts_helper->class0_hp = &counts_map->class0_hp; + + for (i = 0; i < ARRAY_SIZE(counts_map->hp); i++) + memcpy(counts_map->hp[i], counts->mvcomp[i].hp, sizeof(counts_map->hp[0])); + + counts_helper->hp = &counts_map->hp; + + for (i = 0; i < 4; i++) + for (j = 0; j < 2; j++) + for (k = 0; k < 2; k++) + vdec_vp9_slice_map_counts_eob_coef(i, j, k, counts, counts_helper); +} + +static void vdec_vp9_slice_map_to_coef(unsigned int i, unsigned int j, unsigned int k, + struct vdec_vp9_slice_frame_ctx *frame_ctx, + struct v4l2_vp9_frame_context *frame_ctx_helper) +{ + u32 l, m; + + for (l = 0; l < ARRAY_SIZE(frame_ctx_helper->coef[0][0][0]); l++) { + for (m = 0; m < VP9_BAND_6(l); m++) { + memcpy(frame_ctx_helper->coef[i][j][k][l][m], + frame_ctx->coef_probs[i][j][k][l].probs[m], + sizeof(frame_ctx_helper->coef[i][j][k][l][0])); + } + } +} + +static void vdec_vp9_slice_map_from_coef(unsigned int i, unsigned int j, unsigned int k, + struct vdec_vp9_slice_frame_ctx *frame_ctx, + struct v4l2_vp9_frame_context *frame_ctx_helper) +{ + u32 l, m; + + for (l = 0; l < ARRAY_SIZE(frame_ctx_helper->coef[0][0][0]); l++) { + for (m = 0; m < VP9_BAND_6(l); m++) { + memcpy(frame_ctx->coef_probs[i][j][k][l].probs[m], + frame_ctx_helper->coef[i][j][k][l][m], + sizeof(frame_ctx_helper->coef[i][j][k][l][0])); + } + } +} + +static +void vdec_vp9_slice_framectx_map_helper(bool frame_is_intra, + struct vdec_vp9_slice_frame_ctx *pre_frame_ctx, + struct vdec_vp9_slice_frame_ctx *frame_ctx, + struct v4l2_vp9_frame_context *frame_ctx_helper) +{ + struct v4l2_vp9_frame_mv_context *mv = &frame_ctx_helper->mv; + u32 i, j, k; + + for (i = 0; i < ARRAY_SIZE(frame_ctx_helper->coef); i++) + for (j = 0; j < ARRAY_SIZE(frame_ctx_helper->coef[0]); j++) + for (k = 0; k < ARRAY_SIZE(frame_ctx_helper->coef[0][0]); k++) + vdec_vp9_slice_map_to_coef(i, j, k, pre_frame_ctx, + frame_ctx_helper); + + /* + * use previous prob when frame is not intra or + * we should use the prob updated by the compressed header parse + */ + if (!frame_is_intra) + frame_ctx = pre_frame_ctx; + + for (i = 0; i < ARRAY_SIZE(frame_ctx_helper->tx8); i++) + memcpy(frame_ctx_helper->tx8[i], frame_ctx->tx_p8x8[i], + sizeof(frame_ctx_helper->tx8[0])); + + for (i = 0; i < ARRAY_SIZE(frame_ctx_helper->tx16); i++) + memcpy(frame_ctx_helper->tx16[i], frame_ctx->tx_p16x16[i], + sizeof(frame_ctx_helper->tx16[0])); + + for (i = 0; i < ARRAY_SIZE(frame_ctx_helper->tx32); i++) + memcpy(frame_ctx_helper->tx32[i], frame_ctx->tx_p32x32[i], + sizeof(frame_ctx_helper->tx32[0])); + + memcpy(frame_ctx_helper->skip, frame_ctx->skip_probs, sizeof(frame_ctx_helper->skip)); + + for (i = 0; i < ARRAY_SIZE(frame_ctx_helper->inter_mode); i++) + memcpy(frame_ctx_helper->inter_mode[i], frame_ctx->inter_mode_probs[i], + sizeof(frame_ctx_helper->inter_mode[0])); + + for (i = 0; i < ARRAY_SIZE(frame_ctx_helper->interp_filter); i++) + memcpy(frame_ctx_helper->interp_filter[i], frame_ctx->switch_interp_prob[i], + sizeof(frame_ctx_helper->interp_filter[0])); + + memcpy(frame_ctx_helper->is_inter, frame_ctx->intra_inter_prob, + sizeof(frame_ctx_helper->is_inter)); + + memcpy(frame_ctx_helper->comp_mode, frame_ctx->comp_inter_prob, + sizeof(frame_ctx_helper->comp_mode)); + + for (i = 0; i < ARRAY_SIZE(frame_ctx_helper->single_ref); i++) + memcpy(frame_ctx_helper->single_ref[i], frame_ctx->single_ref_prob[i], + sizeof(frame_ctx_helper->single_ref[0])); + + memcpy(frame_ctx_helper->comp_ref, frame_ctx->comp_ref_prob, + sizeof(frame_ctx_helper->comp_ref)); + + for (i = 0; i < ARRAY_SIZE(frame_ctx_helper->y_mode); i++) + memcpy(frame_ctx_helper->y_mode[i], frame_ctx->y_mode_prob[i], + sizeof(frame_ctx_helper->y_mode[0])); + + for (i = 0; i < ARRAY_SIZE(frame_ctx_helper->uv_mode); i++) + memcpy(frame_ctx_helper->uv_mode[i], frame_ctx->uv_mode_prob[i], + sizeof(frame_ctx_helper->uv_mode[0])); + + for (i = 0; i < ARRAY_SIZE(frame_ctx_helper->partition); i++) + memcpy(frame_ctx_helper->partition[i], frame_ctx->partition_prob[i], + sizeof(frame_ctx_helper->partition[0])); + + memcpy(mv->joint, frame_ctx->joint, sizeof(mv->joint)); + + for (i = 0; i < ARRAY_SIZE(mv->sign); i++) + mv->sign[i] = frame_ctx->sign_classes[i].sign; + + for (i = 0; i < ARRAY_SIZE(mv->classes); i++) + memcpy(mv->classes[i], frame_ctx->sign_classes[i].classes, + sizeof(mv->classes[i])); + + for (i = 0; i < ARRAY_SIZE(mv->class0_bit); i++) + mv->class0_bit[i] = frame_ctx->class0_bits[i].class0[0]; + + for (i = 0; i < ARRAY_SIZE(mv->bits); i++) + memcpy(mv->bits[i], frame_ctx->class0_bits[i].bits, sizeof(mv->bits[0])); + + for (i = 0; i < ARRAY_SIZE(mv->class0_fr); i++) + for (j = 0; j < ARRAY_SIZE(mv->class0_fr[0]); j++) + memcpy(mv->class0_fr[i][j], frame_ctx->class0_fp_hp[i].class0_fp[j], + sizeof(mv->class0_fr[0][0])); + + for (i = 0; i < ARRAY_SIZE(mv->fr); i++) + memcpy(mv->fr[i], frame_ctx->class0_fp_hp[i].fp, sizeof(mv->fr[0])); + + for (i = 0; i < ARRAY_SIZE(mv->class0_hp); i++) + mv->class0_hp[i] = frame_ctx->class0_fp_hp[i].class0_hp; + + for (i = 0; i < ARRAY_SIZE(mv->hp); i++) + mv->hp[i] = frame_ctx->class0_fp_hp[i].hp; +} + +static void vdec_vp9_slice_helper_map_framectx(struct v4l2_vp9_frame_context *frame_ctx_helper, + struct vdec_vp9_slice_frame_ctx *frame_ctx) +{ + struct v4l2_vp9_frame_mv_context *mv = &frame_ctx_helper->mv; + u32 i, j, k; + + for (i = 0; i < ARRAY_SIZE(frame_ctx_helper->tx8); i++) + memcpy(frame_ctx->tx_p8x8[i], frame_ctx_helper->tx8[i], + sizeof(frame_ctx_helper->tx8[0])); + + for (i = 0; i < ARRAY_SIZE(frame_ctx_helper->tx16); i++) + memcpy(frame_ctx->tx_p16x16[i], frame_ctx_helper->tx16[i], + sizeof(frame_ctx_helper->tx16[0])); + + for (i = 0; i < ARRAY_SIZE(frame_ctx_helper->tx32); i++) + memcpy(frame_ctx->tx_p32x32[i], frame_ctx_helper->tx32[i], + sizeof(frame_ctx_helper->tx32[0])); + + for (i = 0; i < ARRAY_SIZE(frame_ctx_helper->coef); i++) + for (j = 0; j < ARRAY_SIZE(frame_ctx_helper->coef[0]); j++) + for (k = 0; k < ARRAY_SIZE(frame_ctx_helper->coef[0][0]); k++) + vdec_vp9_slice_map_from_coef(i, j, k, frame_ctx, + frame_ctx_helper); + + memcpy(frame_ctx->skip_probs, frame_ctx_helper->skip, sizeof(frame_ctx_helper->skip)); + + for (i = 0; i < ARRAY_SIZE(frame_ctx_helper->inter_mode); i++) + memcpy(frame_ctx->inter_mode_probs[i], frame_ctx_helper->inter_mode[i], + sizeof(frame_ctx_helper->inter_mode[0])); + + for (i = 0; i < ARRAY_SIZE(frame_ctx_helper->interp_filter); i++) + memcpy(frame_ctx->switch_interp_prob[i], frame_ctx_helper->interp_filter[i], + sizeof(frame_ctx_helper->interp_filter[0])); + + memcpy(frame_ctx->intra_inter_prob, frame_ctx_helper->is_inter, + sizeof(frame_ctx_helper->is_inter)); + + memcpy(frame_ctx->comp_inter_prob, frame_ctx_helper->comp_mode, + sizeof(frame_ctx_helper->comp_mode)); + + for (i = 0; i < ARRAY_SIZE(frame_ctx_helper->single_ref); i++) + memcpy(frame_ctx->single_ref_prob[i], frame_ctx_helper->single_ref[i], + sizeof(frame_ctx_helper->single_ref[0])); + + memcpy(frame_ctx->comp_ref_prob, frame_ctx_helper->comp_ref, + sizeof(frame_ctx_helper->comp_ref)); + + for (i = 0; i < ARRAY_SIZE(frame_ctx_helper->y_mode); i++) + memcpy(frame_ctx->y_mode_prob[i], frame_ctx_helper->y_mode[i], + sizeof(frame_ctx_helper->y_mode[0])); + + for (i = 0; i < ARRAY_SIZE(frame_ctx_helper->uv_mode); i++) + memcpy(frame_ctx->uv_mode_prob[i], frame_ctx_helper->uv_mode[i], + sizeof(frame_ctx_helper->uv_mode[0])); + + for (i = 0; i < ARRAY_SIZE(frame_ctx_helper->partition); i++) + memcpy(frame_ctx->partition_prob[i], frame_ctx_helper->partition[i], + sizeof(frame_ctx_helper->partition[0])); + + memcpy(frame_ctx->joint, mv->joint, sizeof(mv->joint)); + + for (i = 0; i < ARRAY_SIZE(mv->sign); i++) + frame_ctx->sign_classes[i].sign = mv->sign[i]; + + for (i = 0; i < ARRAY_SIZE(mv->classes); i++) + memcpy(frame_ctx->sign_classes[i].classes, mv->classes[i], + sizeof(mv->classes[i])); + + for (i = 0; i < ARRAY_SIZE(mv->class0_bit); i++) + frame_ctx->class0_bits[i].class0[0] = mv->class0_bit[i]; + + for (i = 0; i < ARRAY_SIZE(mv->bits); i++) + memcpy(frame_ctx->class0_bits[i].bits, mv->bits[i], sizeof(mv->bits[0])); + + for (i = 0; i < ARRAY_SIZE(mv->class0_fr); i++) + for (j = 0; j < ARRAY_SIZE(mv->class0_fr[0]); j++) + memcpy(frame_ctx->class0_fp_hp[i].class0_fp[j], mv->class0_fr[i][j], + sizeof(mv->class0_fr[0][0])); + + for (i = 0; i < ARRAY_SIZE(mv->fr); i++) + memcpy(frame_ctx->class0_fp_hp[i].fp, mv->fr[i], sizeof(mv->fr[0])); + + for (i = 0; i < ARRAY_SIZE(mv->class0_hp); i++) + frame_ctx->class0_fp_hp[i].class0_hp = mv->class0_hp[i]; + + for (i = 0; i < ARRAY_SIZE(mv->hp); i++) + frame_ctx->class0_fp_hp[i].hp = mv->hp[i]; +} + +static int vdec_vp9_slice_update_prob(struct vdec_vp9_slice_instance *instance, + struct vdec_vp9_slice_vsi *vsi) +{ + struct vdec_vp9_slice_frame_ctx *pre_frame_ctx; + struct v4l2_vp9_frame_context *pre_frame_ctx_helper; + struct vdec_vp9_slice_frame_ctx *frame_ctx; + struct vdec_vp9_slice_frame_counts *counts; + struct v4l2_vp9_frame_symbol_counts *counts_helper; + struct vdec_vp9_slice_uncompressed_header *uh; + bool frame_is_intra; + bool use_128; + + uh = &vsi->frame.uh; + pre_frame_ctx = &instance->frame_ctx[uh->frame_context_idx]; + pre_frame_ctx_helper = &instance->frame_ctx_helper; + frame_ctx = (struct vdec_vp9_slice_frame_ctx *)instance->prob.va; + counts = (struct vdec_vp9_slice_frame_counts *)instance->counts.va; + counts_helper = &instance->counts_helper; + + if (!uh->refresh_frame_context) + return 0; + + if (!uh->frame_parallel_decoding_mode) { + vdec_vp9_slice_counts_map_helper(&instance->counts_map, counts, counts_helper); + + frame_is_intra = !vsi->frame.uh.frame_type || vsi->frame.uh.intra_only; + /* check default prob */ + if (!instance->dirty[uh->frame_context_idx]) + vdec_vp9_slice_framectx_map_helper(frame_is_intra, + vdec_vp9_slice_default_frame_ctx, + frame_ctx, + pre_frame_ctx_helper); + else + vdec_vp9_slice_framectx_map_helper(frame_is_intra, + pre_frame_ctx, + frame_ctx, + pre_frame_ctx_helper); + + use_128 = !frame_is_intra && !vsi->frame.uh.last_frame_type; + v4l2_vp9_adapt_coef_probs(pre_frame_ctx_helper, + counts_helper, + use_128, + frame_is_intra); + if (!frame_is_intra) + v4l2_vp9_adapt_noncoef_probs(pre_frame_ctx_helper, + counts_helper, + V4L2_VP9_REFERENCE_MODE_SINGLE_REFERENCE, + vsi->frame.uh.interpolation_filter, + vsi->frame.ch.tx_mode, + vsi->frame.uh.allow_high_precision_mv ? + V4L2_VP9_FRAME_FLAG_ALLOW_HIGH_PREC_MV : 0); + vdec_vp9_slice_helper_map_framectx(pre_frame_ctx_helper, pre_frame_ctx); + } else { + memcpy(pre_frame_ctx, frame_ctx, sizeof(*frame_ctx)); + } + + instance->dirty[uh->frame_context_idx] = 1; + + return 0; +} + +static int vdec_vp9_slice_update_lat(struct vdec_vp9_slice_instance *instance, + struct vdec_lat_buf *lat_buf, + struct vdec_vp9_slice_pfc *pfc) +{ + struct vdec_vp9_slice_vsi *vsi; + + vsi = &pfc->vsi; + memcpy(&pfc->state[0], &vsi->state, sizeof(vsi->state)); + + mtk_vcodec_debug(instance, "Frame %u LAT CRC 0x%08x %lx %lx\n", + pfc->seq, vsi->state.crc[0], + (unsigned long)vsi->trans.dma_addr, + (unsigned long)vsi->trans.dma_addr_end); + + /* buffer full, need to re-decode */ + if (vsi->state.full) { + /* buffer not enough */ + if (vsi->trans.dma_addr_end - vsi->trans.dma_addr == + vsi->ube.size) + return -ENOMEM; + return -EAGAIN; + } + + vdec_vp9_slice_update_prob(instance, vsi); + + instance->width = vsi->frame.uh.frame_width; + instance->height = vsi->frame.uh.frame_height; + instance->frame_type = vsi->frame.uh.frame_type; + instance->show_frame = vsi->frame.uh.show_frame; + + return 0; +} + +static int vdec_vp9_slice_setup_core_to_dst_buf(struct vdec_vp9_slice_instance *instance, + struct vdec_lat_buf *lat_buf) +{ + struct vb2_v4l2_buffer *dst; + + dst = v4l2_m2m_next_dst_buf(instance->ctx->m2m_ctx); + if (!dst) + return -EINVAL; + + v4l2_m2m_buf_copy_metadata(&lat_buf->ts_info, dst, true); + return 0; +} + +static int vdec_vp9_slice_setup_core_buffer(struct vdec_vp9_slice_instance *instance, + struct vdec_vp9_slice_pfc *pfc, + struct vdec_vp9_slice_vsi *vsi, + struct vdec_fb *fb, + struct vdec_lat_buf *lat_buf) +{ + struct vb2_buffer *vb; + struct vb2_queue *vq; + struct vdec_vp9_slice_reference *ref; + int plane; + int size; + int idx; + int w; + int h; + int i; + + plane = instance->ctx->q_data[MTK_Q_DATA_DST].fmt->num_planes; + w = vsi->frame.uh.frame_width; + h = vsi->frame.uh.frame_height; + size = ALIGN(w, 64) * ALIGN(h, 64); + + /* frame buffer */ + vsi->fb.y.dma_addr = fb->base_y.dma_addr; + if (plane == 1) + vsi->fb.c.dma_addr = fb->base_y.dma_addr + size; + else + vsi->fb.c.dma_addr = fb->base_c.dma_addr; + + /* reference buffers */ + vq = v4l2_m2m_get_vq(instance->ctx->m2m_ctx, + V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE); + if (!vq) + return -EINVAL; + + /* get current output buffer */ + vb = &v4l2_m2m_next_dst_buf(instance->ctx->m2m_ctx)->vb2_buf; + if (!vb) + return -EINVAL; + + /* update internal buffer's width/height */ + for (i = 0; i < vq->num_buffers; i++) { + if (vb == vq->bufs[i]) { + instance->dpb[i].width = w; + instance->dpb[i].height = h; + break; + } + } + + /* + * get buffer's width/height from instance + * get buffer address from vb2buf + */ + for (i = 0; i < 3; i++) { + ref = &vsi->frame.ref[i]; + idx = vb2_find_timestamp(vq, pfc->ref_idx[i], 0); + if (idx < 0) { + ref->frame_width = w; + ref->frame_height = h; + memset(&vsi->ref[i], 0, sizeof(vsi->ref[i])); + } else { + ref->frame_width = instance->dpb[idx].width; + ref->frame_height = instance->dpb[idx].height; + vb = vq->bufs[idx]; + vsi->ref[i].y.dma_addr = + vb2_dma_contig_plane_dma_addr(vb, 0); + if (plane == 1) + vsi->ref[i].c.dma_addr = + vsi->ref[i].y.dma_addr + size; + else + vsi->ref[i].c.dma_addr = + vb2_dma_contig_plane_dma_addr(vb, 1); + } + } + + return 0; +} + +static int vdec_vp9_slice_setup_core(struct vdec_vp9_slice_instance *instance, + struct vdec_fb *fb, + struct vdec_lat_buf *lat_buf, + struct vdec_vp9_slice_pfc *pfc) +{ + struct vdec_vp9_slice_vsi *vsi = &pfc->vsi; + int ret; + + vdec_vp9_slice_setup_state(vsi); + + ret = vdec_vp9_slice_setup_core_to_dst_buf(instance, lat_buf); + if (ret) + goto err; + + ret = vdec_vp9_slice_setup_core_buffer(instance, pfc, vsi, fb, lat_buf); + if (ret) + goto err; + + vdec_vp9_slice_setup_seg_buffer(instance, vsi, &instance->seg[1]); + + return 0; + +err: + return ret; +} + +static int vdec_vp9_slice_update_core(struct vdec_vp9_slice_instance *instance, + struct vdec_lat_buf *lat_buf, + struct vdec_vp9_slice_pfc *pfc) +{ + struct vdec_vp9_slice_vsi *vsi; + + vsi = &pfc->vsi; + memcpy(&pfc->state[1], &vsi->state, sizeof(vsi->state)); + + mtk_vcodec_debug(instance, "Frame %u Y_CRC %08x %08x %08x %08x\n", + pfc->seq, + vsi->state.crc[0], vsi->state.crc[1], + vsi->state.crc[2], vsi->state.crc[3]); + mtk_vcodec_debug(instance, "Frame %u C_CRC %08x %08x %08x %08x\n", + pfc->seq, + vsi->state.crc[4], vsi->state.crc[5], + vsi->state.crc[6], vsi->state.crc[7]); + + return 0; +} + +static int vdec_vp9_slice_init(struct mtk_vcodec_ctx *ctx) +{ + struct vdec_vp9_slice_instance *instance; + struct vdec_vp9_slice_init_vsi *vsi; + int ret; + + instance = kzalloc(sizeof(*instance), GFP_KERNEL); + if (!instance) + return -ENOMEM; + + instance->ctx = ctx; + instance->vpu.id = SCP_IPI_VDEC_LAT; + instance->vpu.core_id = SCP_IPI_VDEC_CORE; + instance->vpu.ctx = ctx; + instance->vpu.codec_type = ctx->current_codec; + + ret = vpu_dec_init(&instance->vpu); + if (ret) { + mtk_vcodec_err(instance, "failed to init vpu dec, ret %d\n", ret); + goto error_vpu_init; + } + + /* init vsi and global flags */ + + vsi = instance->vpu.vsi; + if (!vsi) { + mtk_vcodec_err(instance, "failed to get VP9 vsi\n"); + ret = -EINVAL; + goto error_vsi; + } + instance->init_vsi = vsi; + instance->core_vsi = mtk_vcodec_fw_map_dm_addr(ctx->dev->fw_handler, + (u32)vsi->core_vsi); + if (!instance->core_vsi) { + mtk_vcodec_err(instance, "failed to get VP9 core vsi\n"); + ret = -EINVAL; + goto error_vsi; + } + + instance->irq = 1; + + ret = vdec_vp9_slice_init_default_frame_ctx(instance); + if (ret) + goto error_default_frame_ctx; + + ctx->drv_handle = instance; + + return 0; + +error_default_frame_ctx: +error_vsi: + vpu_dec_deinit(&instance->vpu); +error_vpu_init: + kfree(instance); + return ret; +} + +static void vdec_vp9_slice_deinit(void *h_vdec) +{ + struct vdec_vp9_slice_instance *instance = h_vdec; + + if (!instance) + return; + + vpu_dec_deinit(&instance->vpu); + vdec_vp9_slice_free_working_buffer(instance); + vdec_msg_queue_deinit(&instance->ctx->msg_queue, instance->ctx); + kfree(instance); +} + +static int vdec_vp9_slice_flush(void *h_vdec, struct mtk_vcodec_mem *bs, + struct vdec_fb *fb, bool *res_chg) +{ + struct vdec_vp9_slice_instance *instance = h_vdec; + + mtk_vcodec_debug(instance, "flush ...\n"); + + vdec_msg_queue_wait_lat_buf_full(&instance->ctx->msg_queue); + return vpu_dec_reset(&instance->vpu); +} + +static void vdec_vp9_slice_get_pic_info(struct vdec_vp9_slice_instance *instance) +{ + struct mtk_vcodec_ctx *ctx = instance->ctx; + unsigned int data[3]; + + mtk_vcodec_debug(instance, "w %u h %u\n", + ctx->picinfo.pic_w, ctx->picinfo.pic_h); + + data[0] = ctx->picinfo.pic_w; + data[1] = ctx->picinfo.pic_h; + data[2] = ctx->capture_fourcc; + vpu_dec_get_param(&instance->vpu, data, 3, GET_PARAM_PIC_INFO); + + ctx->picinfo.buf_w = ALIGN(ctx->picinfo.pic_w, 64); + ctx->picinfo.buf_h = ALIGN(ctx->picinfo.pic_h, 64); + ctx->picinfo.fb_sz[0] = instance->vpu.fb_sz[0]; + ctx->picinfo.fb_sz[1] = instance->vpu.fb_sz[1]; +} + +static void vdec_vp9_slice_get_dpb_size(struct vdec_vp9_slice_instance *instance, + unsigned int *dpb_sz) +{ + /* refer VP9 specification */ + *dpb_sz = 9; +} + +static int vdec_vp9_slice_get_param(void *h_vdec, enum vdec_get_param_type type, void *out) +{ + struct vdec_vp9_slice_instance *instance = h_vdec; + + switch (type) { + case GET_PARAM_PIC_INFO: + vdec_vp9_slice_get_pic_info(instance); + break; + case GET_PARAM_DPB_SIZE: + vdec_vp9_slice_get_dpb_size(instance, out); + break; + case GET_PARAM_CROP_INFO: + mtk_vcodec_debug(instance, "No need to get vp9 crop information."); + break; + default: + mtk_vcodec_err(instance, "invalid get parameter type=%d\n", + type); + return -EINVAL; + } + + return 0; +} + +static int vdec_vp9_slice_lat_decode(void *h_vdec, struct mtk_vcodec_mem *bs, + struct vdec_fb *fb, bool *res_chg) +{ + struct vdec_vp9_slice_instance *instance = h_vdec; + struct vdec_lat_buf *lat_buf; + struct vdec_vp9_slice_pfc *pfc; + struct vdec_vp9_slice_vsi *vsi; + struct mtk_vcodec_ctx *ctx; + int ret; + + if (!instance || !instance->ctx) + return -EINVAL; + ctx = instance->ctx; + + /* init msgQ for the first time */ + if (vdec_msg_queue_init(&ctx->msg_queue, ctx, + vdec_vp9_slice_core_decode, + sizeof(*pfc))) + return -ENOMEM; + + /* bs NULL means flush decoder */ + if (!bs) + return vdec_vp9_slice_flush(h_vdec, bs, fb, res_chg); + + lat_buf = vdec_msg_queue_dqbuf(&instance->ctx->msg_queue.lat_ctx); + if (!lat_buf) { + mtk_vcodec_err(instance, "Failed to get VP9 lat buf\n"); + return -EBUSY; + } + pfc = (struct vdec_vp9_slice_pfc *)lat_buf->private_data; + if (!pfc) + return -EINVAL; + vsi = &pfc->vsi; + + ret = vdec_vp9_slice_setup_lat(instance, bs, lat_buf, pfc); + if (ret) { + mtk_vcodec_err(instance, "Failed to setup VP9 lat ret %d\n", ret); + return ret; + } + vdec_vp9_slice_vsi_to_remote(vsi, instance->vsi); + + ret = vpu_dec_start(&instance->vpu, NULL, 0); + if (ret) { + mtk_vcodec_err(instance, "Failed to dec VP9 ret %d\n", ret); + return ret; + } + + if (instance->irq) { + ret = mtk_vcodec_wait_for_done_ctx(ctx, MTK_INST_IRQ_RECEIVED, + WAIT_INTR_TIMEOUT_MS, MTK_VDEC_LAT0); + /* update remote vsi if decode timeout */ + if (ret) { + mtk_vcodec_err(instance, "VP9 decode timeout %d pic %d\n", ret, pfc->seq); + WRITE_ONCE(instance->vsi->state.timeout, 1); + } + vpu_dec_end(&instance->vpu); + } + + vdec_vp9_slice_vsi_from_remote(vsi, instance->vsi, 0); + ret = vdec_vp9_slice_update_lat(instance, lat_buf, pfc); + + /* LAT trans full, no more UBE or decode timeout */ + if (ret) { + mtk_vcodec_err(instance, "VP9 decode error: %d\n", ret); + return ret; + } + + mtk_vcodec_debug(instance, "lat dma addr: 0x%lx 0x%lx\n", + (unsigned long)pfc->vsi.trans.dma_addr, + (unsigned long)pfc->vsi.trans.dma_addr_end); + + vdec_msg_queue_update_ube_wptr(&ctx->msg_queue, + vsi->trans.dma_addr_end + + ctx->msg_queue.wdma_addr.dma_addr); + vdec_msg_queue_qbuf(&ctx->dev->msg_queue_core_ctx, lat_buf); + + return 0; +} + +static int vdec_vp9_slice_core_decode(struct vdec_lat_buf *lat_buf) +{ + struct vdec_vp9_slice_instance *instance; + struct vdec_vp9_slice_pfc *pfc; + struct mtk_vcodec_ctx *ctx = NULL; + struct vdec_fb *fb = NULL; + int ret = -EINVAL; + + if (!lat_buf) + goto err; + + pfc = lat_buf->private_data; + ctx = lat_buf->ctx; + if (!pfc || !ctx) + goto err; + + instance = ctx->drv_handle; + if (!instance) + goto err; + + fb = ctx->dev->vdec_pdata->get_cap_buffer(ctx); + if (!fb) { + ret = -EBUSY; + goto err; + } + + ret = vdec_vp9_slice_setup_core(instance, fb, lat_buf, pfc); + if (ret) { + mtk_vcodec_err(instance, "vdec_vp9_slice_setup_core\n"); + goto err; + } + vdec_vp9_slice_vsi_to_remote(&pfc->vsi, instance->core_vsi); + + ret = vpu_dec_core(&instance->vpu); + if (ret) { + mtk_vcodec_err(instance, "vpu_dec_core\n"); + goto err; + } + + if (instance->irq) { + ret = mtk_vcodec_wait_for_done_ctx(ctx, MTK_INST_IRQ_RECEIVED, + WAIT_INTR_TIMEOUT_MS, MTK_VDEC_CORE); + /* update remote vsi if decode timeout */ + if (ret) { + mtk_vcodec_err(instance, "VP9 core timeout pic %d\n", pfc->seq); + WRITE_ONCE(instance->core_vsi->state.timeout, 1); + } + vpu_dec_core_end(&instance->vpu); + } + + vdec_vp9_slice_vsi_from_remote(&pfc->vsi, instance->core_vsi, 1); + ret = vdec_vp9_slice_update_core(instance, lat_buf, pfc); + if (ret) { + mtk_vcodec_err(instance, "vdec_vp9_slice_update_core\n"); + goto err; + } + + pfc->vsi.trans.dma_addr_end += ctx->msg_queue.wdma_addr.dma_addr; + mtk_vcodec_debug(instance, "core dma_addr_end 0x%lx\n", + (unsigned long)pfc->vsi.trans.dma_addr_end); + vdec_msg_queue_update_ube_rptr(&ctx->msg_queue, pfc->vsi.trans.dma_addr_end); + ctx->dev->vdec_pdata->cap_to_disp(ctx, 0, lat_buf->src_buf_req); + + return 0; + +err: + if (ctx && pfc) { + /* always update read pointer */ + vdec_msg_queue_update_ube_rptr(&ctx->msg_queue, pfc->vsi.trans.dma_addr_end); + + if (fb) + ctx->dev->vdec_pdata->cap_to_disp(ctx, 1, lat_buf->src_buf_req); + } + return ret; +} + +const struct vdec_common_if vdec_vp9_slice_lat_if = { + .init = vdec_vp9_slice_init, + .decode = vdec_vp9_slice_lat_decode, + .get_param = vdec_vp9_slice_get_param, + .deinit = vdec_vp9_slice_deinit, +}; diff --git a/drivers/media/platform/mediatek/vcodec/vdec_drv_if.c b/drivers/media/platform/mediatek/vcodec/vdec_drv_if.c index 05a5b240e906..27b4b35039cf 100644 --- a/drivers/media/platform/mediatek/vcodec/vdec_drv_if.c +++ b/drivers/media/platform/mediatek/vcodec/vdec_drv_if.c @@ -16,16 +16,27 @@ int vdec_if_init(struct mtk_vcodec_ctx *ctx, unsigned int fourcc) { + enum mtk_vdec_hw_arch hw_arch = ctx->dev->vdec_pdata->hw_arch; int ret = 0; switch (fourcc) { case V4L2_PIX_FMT_H264_SLICE: - ctx->dec_if = &vdec_h264_slice_if; + if (!ctx->dev->vdec_pdata->is_subdev_supported) { + ctx->dec_if = &vdec_h264_slice_if; + ctx->hw_id = MTK_VDEC_CORE; + } else { + ctx->dec_if = &vdec_h264_slice_multi_if; + ctx->hw_id = IS_VDEC_LAT_ARCH(hw_arch) ? MTK_VDEC_LAT0 : MTK_VDEC_CORE; + } break; case V4L2_PIX_FMT_H264: ctx->dec_if = &vdec_h264_if; ctx->hw_id = MTK_VDEC_CORE; break; + case V4L2_PIX_FMT_VP8_FRAME: + ctx->dec_if = &vdec_vp8_slice_if; + ctx->hw_id = MTK_VDEC_CORE; + break; case V4L2_PIX_FMT_VP8: ctx->dec_if = &vdec_vp8_if; ctx->hw_id = MTK_VDEC_CORE; @@ -34,15 +45,17 @@ int vdec_if_init(struct mtk_vcodec_ctx *ctx, unsigned int fourcc) ctx->dec_if = &vdec_vp9_if; ctx->hw_id = MTK_VDEC_CORE; break; + case V4L2_PIX_FMT_VP9_FRAME: + ctx->dec_if = &vdec_vp9_slice_lat_if; + ctx->hw_id = MTK_VDEC_LAT0; + break; default: return -EINVAL; } - mtk_vdec_lock(ctx); - mtk_vcodec_dec_clock_on(ctx->dev, ctx->hw_id); + mtk_vcodec_dec_enable_hardware(ctx, ctx->hw_id); ret = ctx->dec_if->init(ctx); - mtk_vcodec_dec_clock_off(ctx->dev, ctx->hw_id); - mtk_vdec_unlock(ctx); + mtk_vcodec_dec_disable_hardware(ctx, ctx->hw_id); return ret; } @@ -70,15 +83,11 @@ int vdec_if_decode(struct mtk_vcodec_ctx *ctx, struct mtk_vcodec_mem *bs, if (!ctx->drv_handle) return -EIO; - mtk_vdec_lock(ctx); - + mtk_vcodec_dec_enable_hardware(ctx, ctx->hw_id); mtk_vcodec_set_curr_ctx(ctx->dev, ctx, ctx->hw_id); - mtk_vcodec_dec_clock_on(ctx->dev, ctx->hw_id); ret = ctx->dec_if->decode(ctx->drv_handle, bs, fb, res_chg); - mtk_vcodec_dec_clock_off(ctx->dev, ctx->hw_id); mtk_vcodec_set_curr_ctx(ctx->dev, NULL, ctx->hw_id); - - mtk_vdec_unlock(ctx); + mtk_vcodec_dec_disable_hardware(ctx, ctx->hw_id); return ret; } @@ -103,11 +112,9 @@ void vdec_if_deinit(struct mtk_vcodec_ctx *ctx) if (!ctx->drv_handle) return; - mtk_vdec_lock(ctx); - mtk_vcodec_dec_clock_on(ctx->dev, ctx->hw_id); + mtk_vcodec_dec_enable_hardware(ctx, ctx->hw_id); ctx->dec_if->deinit(ctx->drv_handle); - mtk_vcodec_dec_clock_off(ctx->dev, ctx->hw_id); - mtk_vdec_unlock(ctx); + mtk_vcodec_dec_disable_hardware(ctx, ctx->hw_id); ctx->drv_handle = NULL; } diff --git a/drivers/media/platform/mediatek/vcodec/vdec_drv_if.h b/drivers/media/platform/mediatek/vcodec/vdec_drv_if.h index d467e8af4a84..076306ff2dd4 100644 --- a/drivers/media/platform/mediatek/vcodec/vdec_drv_if.h +++ b/drivers/media/platform/mediatek/vcodec/vdec_drv_if.h @@ -56,8 +56,11 @@ struct vdec_fb_node { extern const struct vdec_common_if vdec_h264_if; extern const struct vdec_common_if vdec_h264_slice_if; +extern const struct vdec_common_if vdec_h264_slice_multi_if; extern const struct vdec_common_if vdec_vp8_if; +extern const struct vdec_common_if vdec_vp8_slice_if; extern const struct vdec_common_if vdec_vp9_if; +extern const struct vdec_common_if vdec_vp9_slice_lat_if; /** * vdec_if_init() - initialize decode driver diff --git a/drivers/media/platform/mediatek/vcodec/vdec_ipi_msg.h b/drivers/media/platform/mediatek/vcodec/vdec_ipi_msg.h index bf54d6d9a857..47070be2a991 100644 --- a/drivers/media/platform/mediatek/vcodec/vdec_ipi_msg.h +++ b/drivers/media/platform/mediatek/vcodec/vdec_ipi_msg.h @@ -20,6 +20,7 @@ enum vdec_ipi_msgid { AP_IPIMSG_DEC_RESET = 0xA004, AP_IPIMSG_DEC_CORE = 0xA005, AP_IPIMSG_DEC_CORE_END = 0xA006, + AP_IPIMSG_DEC_GET_PARAM = 0xA007, VPU_IPIMSG_DEC_INIT_ACK = 0xB000, VPU_IPIMSG_DEC_START_ACK = 0xB001, @@ -28,6 +29,7 @@ enum vdec_ipi_msgid { VPU_IPIMSG_DEC_RESET_ACK = 0xB004, VPU_IPIMSG_DEC_CORE_ACK = 0xB005, VPU_IPIMSG_DEC_CORE_END_ACK = 0xB006, + VPU_IPIMSG_DEC_GET_PARAM_ACK = 0xB007, }; /** @@ -114,4 +116,38 @@ struct vdec_vpu_ipi_init_ack { uint32_t inst_id; }; +/** + * struct vdec_ap_ipi_get_param - for AP_IPIMSG_DEC_GET_PARAM + * @msg_id : AP_IPIMSG_DEC_GET_PARAM + * @inst_id : instance ID. Used if the ABI version >= 2. + * @data : picture information + * @param_type : get param type + * @codec_type : Codec fourcc + */ +struct vdec_ap_ipi_get_param { + u32 msg_id; + u32 inst_id; + u32 data[4]; + u32 param_type; + u32 codec_type; +}; + +/** + * struct vdec_vpu_ipi_get_param_ack - for VPU_IPIMSG_DEC_GET_PARAM_ACK + * @msg_id : VPU_IPIMSG_DEC_GET_PARAM_ACK + * @status : VPU execution result + * @ap_inst_addr : AP vcodec_vpu_inst instance address + * @data : picture information from SCP. + * @param_type : get param type + * @reserved : reserved param + */ +struct vdec_vpu_ipi_get_param_ack { + u32 msg_id; + s32 status; + u64 ap_inst_addr; + u32 data[4]; + u32 param_type; + u32 reserved; +}; + #endif diff --git a/drivers/media/platform/mediatek/vcodec/vdec_msg_queue.c b/drivers/media/platform/mediatek/vcodec/vdec_msg_queue.c index 4b062a8128b4..ae500980ad45 100644 --- a/drivers/media/platform/mediatek/vcodec/vdec_msg_queue.c +++ b/drivers/media/platform/mediatek/vcodec/vdec_msg_queue.c @@ -212,11 +212,13 @@ static void vdec_msg_queue_core_work(struct work_struct *work) return; ctx = lat_buf->ctx; + mtk_vcodec_dec_enable_hardware(ctx, MTK_VDEC_CORE); mtk_vcodec_set_curr_ctx(dev, ctx, MTK_VDEC_CORE); lat_buf->core_decode(lat_buf); mtk_vcodec_set_curr_ctx(dev, NULL, MTK_VDEC_CORE); + mtk_vcodec_dec_disable_hardware(ctx, MTK_VDEC_CORE); vdec_msg_queue_qbuf(&ctx->msg_queue.lat_ctx, lat_buf); if (!list_empty(&ctx->msg_queue.lat_ctx.ready_queue)) { diff --git a/drivers/media/platform/mediatek/vcodec/vdec_msg_queue.h b/drivers/media/platform/mediatek/vcodec/vdec_msg_queue.h index b6ba66d3e026..c43d427f5f54 100644 --- a/drivers/media/platform/mediatek/vcodec/vdec_msg_queue.h +++ b/drivers/media/platform/mediatek/vcodec/vdec_msg_queue.h @@ -43,6 +43,7 @@ struct vdec_msg_queue_ctx { * @wdma_err_addr: wdma error address used for lat hardware * @slice_bc_addr: slice bc address used for lat hardware * @ts_info: need to set timestamp from output to capture + * @src_buf_req: output buffer media request object * * @private_data: shared information used to lat and core hardware * @ctx: mtk vcodec context information @@ -54,6 +55,7 @@ struct vdec_lat_buf { struct mtk_vcodec_mem wdma_err_addr; struct mtk_vcodec_mem slice_bc_addr; struct vb2_v4l2_buffer ts_info; + struct media_request *src_buf_req; void *private_data; struct mtk_vcodec_ctx *ctx; diff --git a/drivers/media/platform/mediatek/vcodec/vdec_vpu_if.c b/drivers/media/platform/mediatek/vcodec/vdec_vpu_if.c index dd35d2c5f920..35f4d5583084 100644 --- a/drivers/media/platform/mediatek/vcodec/vdec_vpu_if.c +++ b/drivers/media/platform/mediatek/vcodec/vdec_vpu_if.c @@ -6,6 +6,7 @@ #include "mtk_vcodec_drv.h" #include "mtk_vcodec_util.h" +#include "vdec_drv_if.h" #include "vdec_ipi_msg.h" #include "vdec_vpu_if.h" #include "mtk_vcodec_fw.h" @@ -33,8 +34,8 @@ static void handle_init_ack_msg(const struct vdec_vpu_ipi_init_ack *msg) */ vpu->inst_id = 0xdeadbeef; - /* Firmware version field does not exist on MT8173. */ - if (vpu->ctx->dev->vdec_pdata->chip == MTK_MT8173) + /* VPU firmware does not contain a version field. */ + if (mtk_vcodec_fw_get_type(vpu->ctx->dev->fw_handler) == VPU) return; /* Check firmware version. */ @@ -54,6 +55,26 @@ static void handle_init_ack_msg(const struct vdec_vpu_ipi_init_ack *msg) } } +static void handle_get_param_msg_ack(const struct vdec_vpu_ipi_get_param_ack *msg) +{ + struct vdec_vpu_inst *vpu = (struct vdec_vpu_inst *) + (unsigned long)msg->ap_inst_addr; + + mtk_vcodec_debug(vpu, "+ ap_inst_addr = 0x%llx", msg->ap_inst_addr); + + /* param_type is enum vdec_get_param_type */ + switch (msg->param_type) { + case GET_PARAM_PIC_INFO: + vpu->fb_sz[0] = msg->data[0]; + vpu->fb_sz[1] = msg->data[1]; + break; + default: + mtk_vcodec_err(vpu, "invalid get param type=%d", msg->param_type); + vpu->failure = 1; + break; + } +} + /* * vpu_dec_ipi_handler - Handler for VPU ipi message. * @@ -89,6 +110,9 @@ static void vpu_dec_ipi_handler(void *data, unsigned int len, void *priv) case VPU_IPIMSG_DEC_CORE_END_ACK: break; + case VPU_IPIMSG_DEC_GET_PARAM_ACK: + handle_get_param_msg_ack(data); + break; default: mtk_vcodec_err(vpu, "invalid msg=%X", msg->msg_id); break; @@ -217,6 +241,31 @@ int vpu_dec_start(struct vdec_vpu_inst *vpu, uint32_t *data, unsigned int len) return err; } +int vpu_dec_get_param(struct vdec_vpu_inst *vpu, uint32_t *data, + unsigned int len, unsigned int param_type) +{ + struct vdec_ap_ipi_get_param msg; + int err; + + mtk_vcodec_debug_enter(vpu); + + if (len > ARRAY_SIZE(msg.data)) { + mtk_vcodec_err(vpu, "invalid len = %d\n", len); + return -EINVAL; + } + + memset(&msg, 0, sizeof(msg)); + msg.msg_id = AP_IPIMSG_DEC_GET_PARAM; + msg.inst_id = vpu->inst_id; + memcpy(msg.data, data, sizeof(unsigned int) * len); + msg.param_type = param_type; + msg.codec_type = vpu->codec_type; + + err = vcodec_vpu_send_msg(vpu, (void *)&msg, sizeof(msg)); + mtk_vcodec_debug(vpu, "- ret=%d", err); + return err; +} + int vpu_dec_core(struct vdec_vpu_inst *vpu) { return vcodec_send_ap_ipi(vpu, AP_IPIMSG_DEC_CORE); diff --git a/drivers/media/platform/mediatek/vcodec/vdec_vpu_if.h b/drivers/media/platform/mediatek/vcodec/vdec_vpu_if.h index 4cb3c7f5a3ad..0436bba91457 100644 --- a/drivers/media/platform/mediatek/vcodec/vdec_vpu_if.h +++ b/drivers/media/platform/mediatek/vcodec/vdec_vpu_if.h @@ -28,6 +28,8 @@ struct mtk_vcodec_ctx; * @wq : wait queue to wait VPU message ack * @handler : ipi handler for each decoder * @codec_type : use codec type to separate different codecs + * @capture_type: used capture type to separate different capture format + * @fb_sz : frame buffer size of each plane */ struct vdec_vpu_inst { int id; @@ -42,6 +44,8 @@ struct vdec_vpu_inst { wait_queue_head_t wq; mtk_vcodec_ipi_handler handler; unsigned int codec_type; + unsigned int capture_type; + unsigned int fb_sz[2]; }; /** @@ -104,4 +108,15 @@ int vpu_dec_core(struct vdec_vpu_inst *vpu); */ int vpu_dec_core_end(struct vdec_vpu_inst *vpu); +/** + * vpu_dec_get_param - get param from scp + * + * @vpu : instance for vdec_vpu_inst + * @data: meta data to pass bitstream info to VPU decoder + * @len : meta data length + * @param_type : get param type + */ +int vpu_dec_get_param(struct vdec_vpu_inst *vpu, uint32_t *data, + unsigned int len, unsigned int param_type); + #endif diff --git a/drivers/media/platform/mediatek/vcodec/venc_vpu_if.c b/drivers/media/platform/mediatek/vcodec/venc_vpu_if.c index e7899d8a3e4e..d3570c4c177d 100644 --- a/drivers/media/platform/mediatek/vcodec/venc_vpu_if.c +++ b/drivers/media/platform/mediatek/vcodec/venc_vpu_if.c @@ -18,7 +18,7 @@ static void handle_enc_init_msg(struct venc_vpu_inst *vpu, const void *data) msg->vpu_inst_addr); /* Firmware version field value is unspecified on MT8173. */ - if (vpu->ctx->dev->venc_pdata->chip == MTK_MT8173) + if (mtk_vcodec_fw_get_type(vpu->ctx->dev->fw_handler) == VPU) return; /* Check firmware version. */ diff --git a/drivers/media/platform/nvidia/tegra-vde/h264.c b/drivers/media/platform/nvidia/tegra-vde/h264.c index d8e5534e80c8..88f81a134ba0 100644 --- a/drivers/media/platform/nvidia/tegra-vde/h264.c +++ b/drivers/media/platform/nvidia/tegra-vde/h264.c @@ -45,9 +45,9 @@ struct tegra_vde_h264_decoder_ctx { }; struct h264_reflists { - u8 p[V4L2_H264_NUM_DPB_ENTRIES]; - u8 b0[V4L2_H264_NUM_DPB_ENTRIES]; - u8 b1[V4L2_H264_NUM_DPB_ENTRIES]; + struct v4l2_h264_reference p[V4L2_H264_NUM_DPB_ENTRIES]; + struct v4l2_h264_reference b0[V4L2_H264_NUM_DPB_ENTRIES]; + struct v4l2_h264_reference b1[V4L2_H264_NUM_DPB_ENTRIES]; }; static int tegra_vde_wait_mbe(struct tegra_vde *vde) @@ -765,10 +765,10 @@ static int tegra_vde_h264_setup_frames(struct tegra_ctx *ctx, struct tegra_m2m_buffer *tb = vb_to_tegra_buf(&dst->vb2_buf); struct tegra_ctx_h264 *h = &ctx->h264; struct v4l2_h264_reflist_builder b; + struct v4l2_h264_reference *dpb_id; struct h264_reflists reflists; struct vb2_buffer *ref; unsigned int i; - u8 *dpb_id; int err; /* @@ -811,14 +811,16 @@ static int tegra_vde_h264_setup_frames(struct tegra_ctx *ctx, } for (i = 0; i < b.num_valid; i++) { - ref = get_ref_buf(ctx, dst, dpb_id[i]); + int dpb_idx = dpb_id[i].index; - err = tegra_vde_h264_setup_frame(ctx, h264, &b, ref, dpb_id[i], + ref = get_ref_buf(ctx, dst, dpb_idx); + + err = tegra_vde_h264_setup_frame(ctx, h264, &b, ref, dpb_idx, h264->dpb_frames_nb++); if (err) return err; - if (b.refs[dpb_id[i]].pic_order_count < b.cur_pic_order_count) + if (b.refs[dpb_idx].top_field_order_cnt < b.cur_pic_order_count) h264->dpb_ref_frames_with_earlier_poc_nb++; } @@ -880,6 +882,9 @@ static int tegra_vde_h264_setup_context(struct tegra_ctx *ctx, if (h->pps->flags & V4L2_H264_PPS_FLAG_ENTROPY_CODING_MODE) return -EOPNOTSUPP; + if (h->decode_params->flags & V4L2_H264_DECODE_PARAM_FLAG_FIELD_PIC) + return -EOPNOTSUPP; + if (h->sps->profile_idc == 66) h264->baseline_profile = 1; diff --git a/drivers/media/platform/nxp/Kconfig b/drivers/media/platform/nxp/Kconfig index 28f2bafc14d2..1ac0a6e91111 100644 --- a/drivers/media/platform/nxp/Kconfig +++ b/drivers/media/platform/nxp/Kconfig @@ -7,10 +7,10 @@ comment "NXP media platform drivers" config VIDEO_IMX_MIPI_CSIS tristate "NXP MIPI CSI-2 CSIS receiver found on i.MX7 and i.MX8 models" depends on ARCH_MXC || COMPILE_TEST + depends on VIDEO_DEV select MEDIA_CONTROLLER select V4L2_FWNODE select VIDEO_V4L2_SUBDEV_API - default n help Video4Linux2 sub-device driver for the MIPI CSI-2 CSIS receiver v3.3/v3.6.3 found on some i.MX7 and i.MX8 SoCs. @@ -20,7 +20,6 @@ config VIDEO_VIU depends on V4L_PLATFORM_DRIVERS depends on VIDEO_DEV && (PPC_MPC512x || COMPILE_TEST) && I2C select VIDEOBUF_DMA_CONTIG - default y help Support for Freescale VIU video driver. This device captures video data, or overlays video on DIU frame buffer. diff --git a/drivers/media/platform/nxp/imx-jpeg/mxc-jpeg-hw.h b/drivers/media/platform/nxp/imx-jpeg/mxc-jpeg-hw.h index ae70d3a0dc24..d838e875616c 100644 --- a/drivers/media/platform/nxp/imx-jpeg/mxc-jpeg-hw.h +++ b/drivers/media/platform/nxp/imx-jpeg/mxc-jpeg-hw.h @@ -102,11 +102,11 @@ enum mxc_jpeg_image_format { MXC_JPEG_INVALID = -1, MXC_JPEG_YUV420 = 0x0, /* 2 Plannar, Y=1st plane UV=2nd plane */ MXC_JPEG_YUV422 = 0x1, /* 1 Plannar, YUYV sequence */ - MXC_JPEG_RGB = 0x2, /* RGBRGB packed format */ + MXC_JPEG_BGR = 0x2, /* BGR packed format */ MXC_JPEG_YUV444 = 0x3, /* 1 Plannar, YUVYUV sequence */ MXC_JPEG_GRAY = 0x4, /* Y8 or Y12 or Single Component */ MXC_JPEG_RESERVED = 0x5, - MXC_JPEG_ARGB = 0x6, + MXC_JPEG_ABGR = 0x6, }; #include "mxc-jpeg.h" diff --git a/drivers/media/platform/nxp/imx-jpeg/mxc-jpeg.c b/drivers/media/platform/nxp/imx-jpeg/mxc-jpeg.c index d1ec1f4b506b..f36b512bae51 100644 --- a/drivers/media/platform/nxp/imx-jpeg/mxc-jpeg.c +++ b/drivers/media/platform/nxp/imx-jpeg/mxc-jpeg.c @@ -8,7 +8,7 @@ * Baseline and extended sequential jpeg decoding is supported. * Progressive jpeg decoding is not supported by the IP. * Supports encode and decode of various formats: - * YUV444, YUV422, YUV420, RGB, ARGB, Gray + * YUV444, YUV422, YUV420, BGR, ABGR, Gray * YUV420 is the only multi-planar format supported. * Minimum resolution is 64 x 64, maximum 8192 x 8192. * To achieve 8192 x 8192, modify in defconfig: CONFIG_CMA_SIZE_MBYTES=320 @@ -73,8 +73,8 @@ static const struct mxc_jpeg_fmt mxc_formats[] = { .flags = MXC_JPEG_FMT_TYPE_ENC, }, { - .name = "RGB", /*RGBRGB packed format*/ - .fourcc = V4L2_PIX_FMT_RGB24, + .name = "BGR", /*BGR packed format*/ + .fourcc = V4L2_PIX_FMT_BGR24, .subsampling = V4L2_JPEG_CHROMA_SUBSAMPLING_444, .nc = 3, .depth = 24, @@ -82,10 +82,11 @@ static const struct mxc_jpeg_fmt mxc_formats[] = { .h_align = 3, .v_align = 3, .flags = MXC_JPEG_FMT_TYPE_RAW, + .precision = 8, }, { - .name = "ARGB", /* ARGBARGB packed format */ - .fourcc = V4L2_PIX_FMT_ARGB32, + .name = "ABGR", /* ABGR packed format */ + .fourcc = V4L2_PIX_FMT_ABGR32, .subsampling = V4L2_JPEG_CHROMA_SUBSAMPLING_444, .nc = 4, .depth = 32, @@ -93,6 +94,7 @@ static const struct mxc_jpeg_fmt mxc_formats[] = { .h_align = 3, .v_align = 3, .flags = MXC_JPEG_FMT_TYPE_RAW, + .precision = 8, }, { .name = "YUV420", /* 1st plane = Y, 2nd plane = UV */ @@ -104,6 +106,7 @@ static const struct mxc_jpeg_fmt mxc_formats[] = { .h_align = 4, .v_align = 4, .flags = MXC_JPEG_FMT_TYPE_RAW, + .precision = 8, }, { .name = "YUV422", /* YUYV */ @@ -115,6 +118,7 @@ static const struct mxc_jpeg_fmt mxc_formats[] = { .h_align = 4, .v_align = 3, .flags = MXC_JPEG_FMT_TYPE_RAW, + .precision = 8, }, { .name = "YUV444", /* YUVYUV */ @@ -126,6 +130,7 @@ static const struct mxc_jpeg_fmt mxc_formats[] = { .h_align = 3, .v_align = 3, .flags = MXC_JPEG_FMT_TYPE_RAW, + .precision = 8, }, { .name = "Gray", /* Gray (Y8/Y12) or Single Comp */ @@ -137,6 +142,7 @@ static const struct mxc_jpeg_fmt mxc_formats[] = { .h_align = 3, .v_align = 3, .flags = MXC_JPEG_FMT_TYPE_RAW, + .precision = 8, }, }; @@ -309,6 +315,9 @@ struct mxc_jpeg_src_buf { /* mxc-jpeg specific */ bool dht_needed; bool jpeg_parse_error; + const struct mxc_jpeg_fmt *fmt; + int w; + int h; }; static inline struct mxc_jpeg_src_buf *vb2_to_mxc_buf(struct vb2_buffer *vb) @@ -321,6 +330,9 @@ static unsigned int debug; module_param(debug, int, 0644); MODULE_PARM_DESC(debug, "Debug level (0-3)"); +static void mxc_jpeg_bytesperline(struct mxc_jpeg_q_data *q, u32 precision); +static void mxc_jpeg_sizeimage(struct mxc_jpeg_q_data *q); + static void _bswap16(u16 *a) { *a = ((*a & 0x00FF) << 8) | ((*a & 0xFF00) >> 8); @@ -408,10 +420,10 @@ static enum mxc_jpeg_image_format mxc_jpeg_fourcc_to_imgfmt(u32 fourcc) return MXC_JPEG_YUV420; case V4L2_PIX_FMT_YUV24: return MXC_JPEG_YUV444; - case V4L2_PIX_FMT_RGB24: - return MXC_JPEG_RGB; - case V4L2_PIX_FMT_ARGB32: - return MXC_JPEG_ARGB; + case V4L2_PIX_FMT_BGR24: + return MXC_JPEG_BGR; + case V4L2_PIX_FMT_ABGR32: + return MXC_JPEG_ABGR; default: return MXC_JPEG_INVALID; } @@ -684,11 +696,11 @@ static int mxc_jpeg_fixup_sof(struct mxc_jpeg_sof *sof, sof->comp[0].h = 0x2; break; case V4L2_PIX_FMT_YUV24: - case V4L2_PIX_FMT_RGB24: + case V4L2_PIX_FMT_BGR24: default: sof->components_no = 3; break; - case V4L2_PIX_FMT_ARGB32: + case V4L2_PIX_FMT_ABGR32: sof->components_no = 4; break; case V4L2_PIX_FMT_GREY: @@ -716,11 +728,11 @@ static int mxc_jpeg_fixup_sos(struct mxc_jpeg_sos *sos, sos->components_no = 3; break; case V4L2_PIX_FMT_YUV24: - case V4L2_PIX_FMT_RGB24: + case V4L2_PIX_FMT_BGR24: default: sos->components_no = 3; break; - case V4L2_PIX_FMT_ARGB32: + case V4L2_PIX_FMT_ABGR32: sos->components_no = 4; break; case V4L2_PIX_FMT_GREY: @@ -751,8 +763,8 @@ static unsigned int mxc_jpeg_setup_cfg_stream(void *cfg_stream_vaddr, memcpy(cfg + offset, jpeg_soi, ARRAY_SIZE(jpeg_soi)); offset += ARRAY_SIZE(jpeg_soi); - if (fourcc == V4L2_PIX_FMT_RGB24 || - fourcc == V4L2_PIX_FMT_ARGB32) { + if (fourcc == V4L2_PIX_FMT_BGR24 || + fourcc == V4L2_PIX_FMT_ABGR32) { memcpy(cfg + offset, jpeg_app14, sizeof(jpeg_app14)); offset += sizeof(jpeg_app14); } else { @@ -916,6 +928,67 @@ static void mxc_jpeg_config_enc_desc(struct vb2_buffer *out_buf, mxc_jpeg_set_desc(cfg_desc_handle, reg, slot); } +static bool mxc_jpeg_source_change(struct mxc_jpeg_ctx *ctx, + struct mxc_jpeg_src_buf *jpeg_src_buf) +{ + struct device *dev = ctx->mxc_jpeg->dev; + struct mxc_jpeg_q_data *q_data_cap; + + if (!jpeg_src_buf->fmt) + return false; + + q_data_cap = mxc_jpeg_get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_CAPTURE); + if (q_data_cap->fmt != jpeg_src_buf->fmt || + q_data_cap->w != jpeg_src_buf->w || + q_data_cap->h != jpeg_src_buf->h) { + dev_dbg(dev, "Detected jpeg res=(%dx%d)->(%dx%d), pixfmt=%c%c%c%c\n", + q_data_cap->w, q_data_cap->h, + jpeg_src_buf->w, jpeg_src_buf->h, + (jpeg_src_buf->fmt->fourcc & 0xff), + (jpeg_src_buf->fmt->fourcc >> 8) & 0xff, + (jpeg_src_buf->fmt->fourcc >> 16) & 0xff, + (jpeg_src_buf->fmt->fourcc >> 24) & 0xff); + + /* + * set-up the capture queue with the pixelformat and resolution + * detected from the jpeg output stream + */ + q_data_cap->w = jpeg_src_buf->w; + q_data_cap->h = jpeg_src_buf->h; + q_data_cap->fmt = jpeg_src_buf->fmt; + q_data_cap->w_adjusted = q_data_cap->w; + q_data_cap->h_adjusted = q_data_cap->h; + + /* + * align up the resolution for CAST IP, + * but leave the buffer resolution unchanged + */ + v4l_bound_align_image(&q_data_cap->w_adjusted, + q_data_cap->w_adjusted, /* adjust up */ + MXC_JPEG_MAX_WIDTH, + q_data_cap->fmt->h_align, + &q_data_cap->h_adjusted, + q_data_cap->h_adjusted, /* adjust up */ + MXC_JPEG_MAX_HEIGHT, + q_data_cap->fmt->v_align, + 0); + + /* setup bytesperline/sizeimage for capture queue */ + mxc_jpeg_bytesperline(q_data_cap, jpeg_src_buf->fmt->precision); + mxc_jpeg_sizeimage(q_data_cap); + notify_src_chg(ctx); + ctx->source_change = 1; + } + return ctx->source_change ? true : false; +} + +static int mxc_jpeg_job_ready(void *priv) +{ + struct mxc_jpeg_ctx *ctx = priv; + + return ctx->source_change ? 0 : 1; +} + static void mxc_jpeg_device_run(void *priv) { struct mxc_jpeg_ctx *ctx = priv; @@ -963,6 +1036,13 @@ static void mxc_jpeg_device_run(void *priv) return; } + if (ctx->mxc_jpeg->mode == MXC_JPEG_DECODE) { + if (ctx->source_change || mxc_jpeg_source_change(ctx, jpeg_src_buf)) { + spin_unlock_irqrestore(&ctx->mxc_jpeg->hw_lock, flags); + v4l2_m2m_job_finish(jpeg->m2m_dev, ctx->fh.m2m_ctx); + return; + } + } mxc_jpeg_enable(reg); mxc_jpeg_set_l_endian(reg, 1); @@ -1009,6 +1089,7 @@ static void mxc_jpeg_set_last_buffer_dequeued(struct mxc_jpeg_ctx *ctx) q->last_buffer_dequeued = true; wake_up(&q->done_wq); ctx->stopped = 0; + ctx->header_parsed = false; } static int mxc_jpeg_decoder_cmd(struct file *file, void *priv, @@ -1081,6 +1162,8 @@ static int mxc_jpeg_queue_setup(struct vb2_queue *q, /* Handle CREATE_BUFS situation - *nplanes != 0 */ if (*nplanes) { + if (*nplanes != q_data->fmt->colplanes) + return -EINVAL; for (i = 0; i < *nplanes; i++) { if (sizes[i] < q_data->sizeimage[i]) return -EINVAL; @@ -1102,6 +1185,8 @@ static int mxc_jpeg_start_streaming(struct vb2_queue *q, unsigned int count) struct mxc_jpeg_q_data *q_data = mxc_jpeg_get_q_data(ctx, q->type); int ret; + if (ctx->mxc_jpeg->mode == MXC_JPEG_DECODE && V4L2_TYPE_IS_CAPTURE(q->type)) + ctx->source_change = 0; dev_dbg(ctx->mxc_jpeg->dev, "Start streaming ctx=%p", ctx); q_data->sequence = 0; @@ -1175,14 +1260,17 @@ static u32 mxc_jpeg_get_image_format(struct device *dev, for (i = 0; i < MXC_JPEG_NUM_FORMATS; i++) if (mxc_formats[i].subsampling == header->frame.subsampling && - mxc_formats[i].nc == header->frame.num_components) { + mxc_formats[i].nc == header->frame.num_components && + mxc_formats[i].precision == header->frame.precision) { fourcc = mxc_formats[i].fourcc; break; } if (fourcc == 0) { - dev_err(dev, "Could not identify image format nc=%d, subsampling=%d\n", + dev_err(dev, + "Could not identify image format nc=%d, subsampling=%d, precision=%d\n", header->frame.num_components, - header->frame.subsampling); + header->frame.subsampling, + header->frame.precision); return fourcc; } /* @@ -1190,9 +1278,9 @@ static u32 mxc_jpeg_get_image_format(struct device *dev, * encoded with 3 components have RGB colorspace, see Recommendation * ITU-T T.872 chapter 6.5.3 APP14 marker segment for colour encoding */ - if (fourcc == V4L2_PIX_FMT_YUV24 || fourcc == V4L2_PIX_FMT_RGB24) { + if (fourcc == V4L2_PIX_FMT_YUV24 || fourcc == V4L2_PIX_FMT_BGR24) { if (header->app14_tf == V4L2_JPEG_APP14_TF_CMYK_RGB) - fourcc = V4L2_PIX_FMT_RGB24; + fourcc = V4L2_PIX_FMT_BGR24; else fourcc = V4L2_PIX_FMT_YUV24; } @@ -1200,26 +1288,29 @@ static u32 mxc_jpeg_get_image_format(struct device *dev, return fourcc; } -static void mxc_jpeg_bytesperline(struct mxc_jpeg_q_data *q, - u32 precision) +static void mxc_jpeg_bytesperline(struct mxc_jpeg_q_data *q, u32 precision) { /* Bytes distance between the leftmost pixels in two adjacent lines */ if (q->fmt->fourcc == V4L2_PIX_FMT_JPEG) { /* bytesperline unused for compressed formats */ q->bytesperline[0] = 0; q->bytesperline[1] = 0; - } else if (q->fmt->fourcc == V4L2_PIX_FMT_NV12M) { + } else if (q->fmt->subsampling == V4L2_JPEG_CHROMA_SUBSAMPLING_420) { /* When the image format is planar the bytesperline value * applies to the first plane and is divided by the same factor * as the width field for the other planes */ - q->bytesperline[0] = q->w * (precision / 8) * - (q->fmt->depth / 8); + q->bytesperline[0] = q->w * DIV_ROUND_UP(precision, 8); q->bytesperline[1] = q->bytesperline[0]; + } else if (q->fmt->subsampling == V4L2_JPEG_CHROMA_SUBSAMPLING_422) { + q->bytesperline[0] = q->w * DIV_ROUND_UP(precision, 8) * 2; + q->bytesperline[1] = 0; + } else if (q->fmt->subsampling == V4L2_JPEG_CHROMA_SUBSAMPLING_444) { + q->bytesperline[0] = q->w * DIV_ROUND_UP(precision, 8) * q->fmt->nc; + q->bytesperline[1] = 0; } else { - /* single plane formats */ - q->bytesperline[0] = q->w * (precision / 8) * - (q->fmt->depth / 8); + /* grayscale */ + q->bytesperline[0] = q->w * DIV_ROUND_UP(precision, 8); q->bytesperline[1] = 0; } } @@ -1245,17 +1336,17 @@ static void mxc_jpeg_sizeimage(struct mxc_jpeg_q_data *q) } } -static int mxc_jpeg_parse(struct mxc_jpeg_ctx *ctx, - u8 *src_addr, u32 size, bool *dht_needed) +static int mxc_jpeg_parse(struct mxc_jpeg_ctx *ctx, struct vb2_buffer *vb) { struct device *dev = ctx->mxc_jpeg->dev; - struct mxc_jpeg_q_data *q_data_out, *q_data_cap; - enum v4l2_buf_type cap_type = V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE; - bool src_chg = false; + struct mxc_jpeg_q_data *q_data_out; u32 fourcc; struct v4l2_jpeg_header header; struct mxc_jpeg_sof *psof = NULL; struct mxc_jpeg_sos *psos = NULL; + struct mxc_jpeg_src_buf *jpeg_src_buf = vb2_to_mxc_buf(vb); + u8 *src_addr = (u8 *)vb2_plane_vaddr(vb, 0); + u32 size = vb2_get_plane_payload(vb, 0); int ret; memset(&header, 0, sizeof(header)); @@ -1266,7 +1357,7 @@ static int mxc_jpeg_parse(struct mxc_jpeg_ctx *ctx, } /* if DHT marker present, no need to inject default one */ - *dht_needed = (header.num_dht == 0); + jpeg_src_buf->dht_needed = (header.num_dht == 0); q_data_out = mxc_jpeg_get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE); @@ -1274,16 +1365,15 @@ static int mxc_jpeg_parse(struct mxc_jpeg_ctx *ctx, dev_warn(dev, "Invalid user resolution 0x0"); dev_warn(dev, "Keeping resolution from JPEG: %dx%d", header.frame.width, header.frame.height); - q_data_out->w = header.frame.width; - q_data_out->h = header.frame.height; } else if (header.frame.width != q_data_out->w || header.frame.height != q_data_out->h) { dev_err(dev, "Resolution mismatch: %dx%d (JPEG) versus %dx%d(user)", header.frame.width, header.frame.height, q_data_out->w, q_data_out->h); - return -EINVAL; } + q_data_out->w = header.frame.width; + q_data_out->h = header.frame.height; if (header.frame.width % 8 != 0 || header.frame.height % 8 != 0) { dev_err(dev, "JPEG width or height not multiple of 8: %dx%d\n", header.frame.width, header.frame.height); @@ -1316,51 +1406,13 @@ static int mxc_jpeg_parse(struct mxc_jpeg_ctx *ctx, if (fourcc == 0) return -EINVAL; - /* - * set-up the capture queue with the pixelformat and resolution - * detected from the jpeg output stream - */ - q_data_cap = mxc_jpeg_get_q_data(ctx, cap_type); - if (q_data_cap->w != header.frame.width || - q_data_cap->h != header.frame.height) - src_chg = true; - q_data_cap->w = header.frame.width; - q_data_cap->h = header.frame.height; - q_data_cap->fmt = mxc_jpeg_find_format(ctx, fourcc); - q_data_cap->w_adjusted = q_data_cap->w; - q_data_cap->h_adjusted = q_data_cap->h; - /* - * align up the resolution for CAST IP, - * but leave the buffer resolution unchanged - */ - v4l_bound_align_image(&q_data_cap->w_adjusted, - q_data_cap->w_adjusted, /* adjust up */ - MXC_JPEG_MAX_WIDTH, - q_data_cap->fmt->h_align, - &q_data_cap->h_adjusted, - q_data_cap->h_adjusted, /* adjust up */ - MXC_JPEG_MAX_HEIGHT, - q_data_cap->fmt->v_align, - 0); - dev_dbg(dev, "Detected jpeg res=(%dx%d)->(%dx%d), pixfmt=%c%c%c%c\n", - q_data_cap->w, q_data_cap->h, - q_data_cap->w_adjusted, q_data_cap->h_adjusted, - (fourcc & 0xff), - (fourcc >> 8) & 0xff, - (fourcc >> 16) & 0xff, - (fourcc >> 24) & 0xff); - - /* setup bytesperline/sizeimage for capture queue */ - mxc_jpeg_bytesperline(q_data_cap, header.frame.precision); - mxc_jpeg_sizeimage(q_data_cap); + jpeg_src_buf->fmt = mxc_jpeg_find_format(ctx, fourcc); + jpeg_src_buf->w = header.frame.width; + jpeg_src_buf->h = header.frame.height; + ctx->header_parsed = true; - /* - * if the CAPTURE format was updated with new values, regardless of - * whether they match the values set by the client or not, signal - * a source change event - */ - if (src_chg) - notify_src_chg(ctx); + if (!v4l2_m2m_num_src_bufs_ready(ctx->fh.m2m_ctx)) + mxc_jpeg_source_change(ctx, jpeg_src_buf); return 0; } @@ -1381,10 +1433,7 @@ static void mxc_jpeg_buf_queue(struct vb2_buffer *vb) jpeg_src_buf = vb2_to_mxc_buf(vb); jpeg_src_buf->jpeg_parse_error = false; - ret = mxc_jpeg_parse(ctx, - (u8 *)vb2_plane_vaddr(vb, 0), - vb2_get_plane_payload(vb, 0), - &jpeg_src_buf->dht_needed); + ret = mxc_jpeg_parse(ctx, vb); if (ret) jpeg_src_buf->jpeg_parse_error = true; @@ -1422,7 +1471,6 @@ static int mxc_jpeg_buf_prepare(struct vb2_buffer *vb) i, vb2_plane_size(vb, i), sizeimage); return -EINVAL; } - vb2_set_plane_payload(vb, i, sizeimage); } return 0; } @@ -1440,6 +1488,7 @@ static void mxc_jpeg_buf_finish(struct vb2_buffer *vb) if (list_empty(&q->done_list)) { vbuf->flags |= V4L2_BUF_FLAG_LAST; ctx->stopped = 0; + ctx->header_parsed = false; } } @@ -1470,7 +1519,6 @@ static int mxc_jpeg_queue_init(void *priv, struct vb2_queue *src_vq, src_vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_COPY; src_vq->lock = &ctx->mxc_jpeg->lock; src_vq->dev = ctx->mxc_jpeg->dev; - src_vq->allow_zero_bytesused = 1; /* keep old userspace apps working */ ret = vb2_queue_init(src_vq); if (ret) @@ -1510,7 +1558,7 @@ static void mxc_jpeg_set_default_params(struct mxc_jpeg_ctx *ctx) q[i]->h = MXC_JPEG_DEFAULT_HEIGHT; q[i]->w_adjusted = MXC_JPEG_DEFAULT_WIDTH; q[i]->h_adjusted = MXC_JPEG_DEFAULT_HEIGHT; - mxc_jpeg_bytesperline(q[i], 8); + mxc_jpeg_bytesperline(q[i], q[i]->fmt->precision); mxc_jpeg_sizeimage(q[i]); } } @@ -1569,12 +1617,8 @@ free: static int mxc_jpeg_querycap(struct file *file, void *priv, struct v4l2_capability *cap) { - struct mxc_jpeg_dev *mxc_jpeg = video_drvdata(file); - strscpy(cap->driver, MXC_JPEG_NAME " codec", sizeof(cap->driver)); strscpy(cap->card, MXC_JPEG_NAME " codec", sizeof(cap->card)); - snprintf(cap->bus_info, sizeof(cap->bus_info), "platform:%s", - dev_name(mxc_jpeg->dev)); cap->device_caps = V4L2_CAP_STREAMING | V4L2_CAP_VIDEO_M2M_MPLANE; cap->capabilities = cap->device_caps | V4L2_CAP_DEVICE_CAPS; @@ -1585,26 +1629,42 @@ static int mxc_jpeg_enum_fmt_vid_cap(struct file *file, void *priv, struct v4l2_fmtdesc *f) { struct mxc_jpeg_ctx *ctx = mxc_jpeg_fh_to_ctx(priv); + struct mxc_jpeg_q_data *q_data = mxc_jpeg_get_q_data(ctx, f->type); - if (ctx->mxc_jpeg->mode == MXC_JPEG_ENCODE) + if (ctx->mxc_jpeg->mode == MXC_JPEG_ENCODE) { return enum_fmt(mxc_formats, MXC_JPEG_NUM_FORMATS, f, MXC_JPEG_FMT_TYPE_ENC); - else + } else if (!ctx->header_parsed) { return enum_fmt(mxc_formats, MXC_JPEG_NUM_FORMATS, f, MXC_JPEG_FMT_TYPE_RAW); + } else { + /* For the decoder CAPTURE queue, only enumerate the raw formats + * supported for the format currently active on OUTPUT + * (more precisely what was propagated on capture queue + * after jpeg parse on the output buffer) + */ + if (f->index) + return -EINVAL; + f->pixelformat = q_data->fmt->fourcc; + strscpy(f->description, q_data->fmt->name, sizeof(f->description)); + return 0; + } } static int mxc_jpeg_enum_fmt_vid_out(struct file *file, void *priv, struct v4l2_fmtdesc *f) { struct mxc_jpeg_ctx *ctx = mxc_jpeg_fh_to_ctx(priv); + u32 type = ctx->mxc_jpeg->mode == MXC_JPEG_DECODE ? MXC_JPEG_FMT_TYPE_ENC : + MXC_JPEG_FMT_TYPE_RAW; + int ret; + ret = enum_fmt(mxc_formats, MXC_JPEG_NUM_FORMATS, f, type); + if (ret) + return ret; if (ctx->mxc_jpeg->mode == MXC_JPEG_DECODE) - return enum_fmt(mxc_formats, MXC_JPEG_NUM_FORMATS, f, - MXC_JPEG_FMT_TYPE_ENC); - else - return enum_fmt(mxc_formats, MXC_JPEG_NUM_FORMATS, f, - MXC_JPEG_FMT_TYPE_RAW); + f->flags = V4L2_FMT_FLAG_DYN_RESOLUTION; + return 0; } static int mxc_jpeg_try_fmt(struct v4l2_format *f, const struct mxc_jpeg_fmt *fmt, @@ -1652,7 +1712,7 @@ static int mxc_jpeg_try_fmt(struct v4l2_format *f, const struct mxc_jpeg_fmt *fm } /* calculate bytesperline & sizeimage into the tmp_q */ - mxc_jpeg_bytesperline(&tmp_q, 8); + mxc_jpeg_bytesperline(&tmp_q, fmt->precision); mxc_jpeg_sizeimage(&tmp_q); /* adjust user format according to our calculations */ @@ -1819,12 +1879,40 @@ static int mxc_jpeg_s_fmt_vid_out(struct file *file, void *priv, struct v4l2_format *f) { int ret; + struct mxc_jpeg_ctx *ctx = mxc_jpeg_fh_to_ctx(priv); + struct vb2_queue *dst_vq; + struct mxc_jpeg_q_data *q_data_cap; + enum v4l2_buf_type cap_type = V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE; + struct v4l2_format fc; ret = mxc_jpeg_try_fmt_vid_out(file, priv, f); if (ret) return ret; - return mxc_jpeg_s_fmt(mxc_jpeg_fh_to_ctx(priv), f); + ret = mxc_jpeg_s_fmt(mxc_jpeg_fh_to_ctx(priv), f); + if (ret) + return ret; + + if (ctx->mxc_jpeg->mode != MXC_JPEG_DECODE) + return 0; + + dst_vq = v4l2_m2m_get_vq(ctx->fh.m2m_ctx, cap_type); + if (!dst_vq) + return -EINVAL; + + if (vb2_is_busy(dst_vq)) + return 0; + + q_data_cap = mxc_jpeg_get_q_data(ctx, cap_type); + if (q_data_cap->w == f->fmt.pix_mp.width && q_data_cap->h == f->fmt.pix_mp.height) + return 0; + memset(&fc, 0, sizeof(fc)); + fc.type = cap_type; + fc.fmt.pix_mp.pixelformat = q_data_cap->fmt->fourcc; + fc.fmt.pix_mp.width = f->fmt.pix_mp.width; + fc.fmt.pix_mp.height = f->fmt.pix_mp.height; + + return mxc_jpeg_s_fmt_vid_cap(file, priv, &fc); } static int mxc_jpeg_g_fmt_vid(struct file *file, void *priv, @@ -1962,6 +2050,7 @@ static const struct v4l2_file_operations mxc_jpeg_fops = { }; static const struct v4l2_m2m_ops mxc_jpeg_m2m_ops = { + .job_ready = mxc_jpeg_job_ready, .device_run = mxc_jpeg_device_run, }; @@ -2213,9 +2302,33 @@ static int mxc_jpeg_runtime_suspend(struct device *dev) } #endif +#ifdef CONFIG_PM_SLEEP +static int mxc_jpeg_suspend(struct device *dev) +{ + struct mxc_jpeg_dev *jpeg = dev_get_drvdata(dev); + + v4l2_m2m_suspend(jpeg->m2m_dev); + return pm_runtime_force_suspend(dev); +} + +static int mxc_jpeg_resume(struct device *dev) +{ + struct mxc_jpeg_dev *jpeg = dev_get_drvdata(dev); + int ret; + + ret = pm_runtime_force_resume(dev); + if (ret < 0) + return ret; + + v4l2_m2m_resume(jpeg->m2m_dev); + return ret; +} +#endif + static const struct dev_pm_ops mxc_jpeg_pm_ops = { SET_RUNTIME_PM_OPS(mxc_jpeg_runtime_suspend, mxc_jpeg_runtime_resume, NULL) + SET_SYSTEM_SLEEP_PM_OPS(mxc_jpeg_suspend, mxc_jpeg_resume) }; static int mxc_jpeg_remove(struct platform_device *pdev) diff --git a/drivers/media/platform/nxp/imx-jpeg/mxc-jpeg.h b/drivers/media/platform/nxp/imx-jpeg/mxc-jpeg.h index f53f004ba851..760eaf5387a1 100644 --- a/drivers/media/platform/nxp/imx-jpeg/mxc-jpeg.h +++ b/drivers/media/platform/nxp/imx-jpeg/mxc-jpeg.h @@ -17,7 +17,7 @@ #define MXC_JPEG_FMT_TYPE_RAW 1 #define MXC_JPEG_DEFAULT_WIDTH 1280 #define MXC_JPEG_DEFAULT_HEIGHT 720 -#define MXC_JPEG_DEFAULT_PFMT V4L2_PIX_FMT_RGB24 +#define MXC_JPEG_DEFAULT_PFMT V4L2_PIX_FMT_BGR24 #define MXC_JPEG_MIN_WIDTH 64 #define MXC_JPEG_MIN_HEIGHT 64 #define MXC_JPEG_MAX_WIDTH 0x2000 @@ -49,6 +49,7 @@ enum mxc_jpeg_mode { * @h_align: horizontal alignment order (align to 2^h_align) * @v_align: vertical alignment order (align to 2^v_align) * @flags: flags describing format applicability + * @precision: jpeg sample precision */ struct mxc_jpeg_fmt { const char *name; @@ -60,6 +61,7 @@ struct mxc_jpeg_fmt { int h_align; int v_align; u32 flags; + u8 precision; }; struct mxc_jpeg_desc { @@ -93,6 +95,8 @@ struct mxc_jpeg_ctx { unsigned int stopping; unsigned int stopped; unsigned int slot; + unsigned int source_change; + bool header_parsed; }; struct mxc_jpeg_slot_data { diff --git a/drivers/media/platform/nxp/imx-mipi-csis.c b/drivers/media/platform/nxp/imx-mipi-csis.c index 0a72734db55e..80b1c021d14a 100644 --- a/drivers/media/platform/nxp/imx-mipi-csis.c +++ b/drivers/media/platform/nxp/imx-mipi-csis.c @@ -243,12 +243,6 @@ #define MIPI_CSI2_DATA_TYPE_RAW14 0x2d #define MIPI_CSI2_DATA_TYPE_USER(x) (0x30 + (x)) -enum { - ST_POWERED = 1, - ST_STREAMING = 2, - ST_SUSPENDED = 4, -}; - struct mipi_csis_event { bool debug; u32 mask; @@ -310,7 +304,7 @@ struct mipi_csis_info { unsigned int num_clocks; }; -struct csi_state { +struct mipi_csis_device { struct device *dev; void __iomem *regs; struct clk_bulk_data *clks; @@ -328,10 +322,9 @@ struct csi_state { u32 hs_settle; u32 clk_settle; - struct mutex lock; /* Protect csis_fmt, format_mbus and state */ + struct mutex lock; /* Protect csis_fmt and format_mbus */ const struct csis_pix_format *csis_fmt; struct v4l2_mbus_framefmt format_mbus[CSIS_PADS_NUM]; - u32 state; spinlock_t slock; /* Protect events */ struct mipi_csis_event events[MIPI_CSIS_NUM_EVENTS]; @@ -470,6 +463,34 @@ static const struct csis_pix_format mipi_csis_formats[] = { .output = MEDIA_BUS_FMT_SRGGB14_1X14, .data_type = MIPI_CSI2_DATA_TYPE_RAW14, .width = 14, + }, + /* JPEG */ + { + .code = MEDIA_BUS_FMT_JPEG_1X8, + .output = MEDIA_BUS_FMT_JPEG_1X8, + /* + * Map JPEG_1X8 to the RAW8 datatype. + * + * The CSI-2 specification suggests in Annex A "JPEG8 Data + * Format (informative)" to transmit JPEG data using one of the + * Data Types aimed to represent arbitrary data, such as the + * "User Defined Data Type 1" (0x30). + * + * However, when configured with a User Defined Data Type, the + * CSIS outputs data in quad pixel mode regardless of the mode + * selected in the MIPI_CSIS_ISP_CONFIG_CH register. Neither of + * the IP cores connected to the CSIS in i.MX SoCs (CSI bridge + * or ISI) support quad pixel mode, so this will never work in + * practice. + * + * Some sensors (such as the OV5640) send JPEG data using the + * RAW8 data type. This is usable and works, so map the JPEG + * format to RAW8. If the CSIS ends up being integrated in an + * SoC that can support quad pixel mode, this will have to be + * revisited. + */ + .data_type = MIPI_CSI2_DATA_TYPE_RAW8, + .width = 8, } }; @@ -487,59 +508,60 @@ static const struct csis_pix_format *find_csis_format(u32 code) * Hardware configuration */ -static inline u32 mipi_csis_read(struct csi_state *state, u32 reg) +static inline u32 mipi_csis_read(struct mipi_csis_device *csis, u32 reg) { - return readl(state->regs + reg); + return readl(csis->regs + reg); } -static inline void mipi_csis_write(struct csi_state *state, u32 reg, u32 val) +static inline void mipi_csis_write(struct mipi_csis_device *csis, u32 reg, + u32 val) { - writel(val, state->regs + reg); + writel(val, csis->regs + reg); } -static void mipi_csis_enable_interrupts(struct csi_state *state, bool on) +static void mipi_csis_enable_interrupts(struct mipi_csis_device *csis, bool on) { - mipi_csis_write(state, MIPI_CSIS_INT_MSK, on ? 0xffffffff : 0); - mipi_csis_write(state, MIPI_CSIS_DBG_INTR_MSK, on ? 0xffffffff : 0); + mipi_csis_write(csis, MIPI_CSIS_INT_MSK, on ? 0xffffffff : 0); + mipi_csis_write(csis, MIPI_CSIS_DBG_INTR_MSK, on ? 0xffffffff : 0); } -static void mipi_csis_sw_reset(struct csi_state *state) +static void mipi_csis_sw_reset(struct mipi_csis_device *csis) { - u32 val = mipi_csis_read(state, MIPI_CSIS_CMN_CTRL); + u32 val = mipi_csis_read(csis, MIPI_CSIS_CMN_CTRL); - mipi_csis_write(state, MIPI_CSIS_CMN_CTRL, + mipi_csis_write(csis, MIPI_CSIS_CMN_CTRL, val | MIPI_CSIS_CMN_CTRL_RESET); usleep_range(10, 20); } -static void mipi_csis_system_enable(struct csi_state *state, int on) +static void mipi_csis_system_enable(struct mipi_csis_device *csis, int on) { u32 val, mask; - val = mipi_csis_read(state, MIPI_CSIS_CMN_CTRL); + val = mipi_csis_read(csis, MIPI_CSIS_CMN_CTRL); if (on) val |= MIPI_CSIS_CMN_CTRL_ENABLE; else val &= ~MIPI_CSIS_CMN_CTRL_ENABLE; - mipi_csis_write(state, MIPI_CSIS_CMN_CTRL, val); + mipi_csis_write(csis, MIPI_CSIS_CMN_CTRL, val); - val = mipi_csis_read(state, MIPI_CSIS_DPHY_CMN_CTRL); + val = mipi_csis_read(csis, MIPI_CSIS_DPHY_CMN_CTRL); val &= ~MIPI_CSIS_DPHY_CMN_CTRL_ENABLE; if (on) { - mask = (1 << (state->bus.num_data_lanes + 1)) - 1; + mask = (1 << (csis->bus.num_data_lanes + 1)) - 1; val |= (mask & MIPI_CSIS_DPHY_CMN_CTRL_ENABLE); } - mipi_csis_write(state, MIPI_CSIS_DPHY_CMN_CTRL, val); + mipi_csis_write(csis, MIPI_CSIS_DPHY_CMN_CTRL, val); } -/* Called with the state.lock mutex held */ -static void __mipi_csis_set_format(struct csi_state *state) +/* Called with the csis.lock mutex held */ +static void __mipi_csis_set_format(struct mipi_csis_device *csis) { - struct v4l2_mbus_framefmt *mf = &state->format_mbus[CSIS_PAD_SINK]; + struct v4l2_mbus_framefmt *mf = &csis->format_mbus[CSIS_PAD_SINK]; u32 val; /* Color format */ - val = mipi_csis_read(state, MIPI_CSIS_ISP_CONFIG_CH(0)); + val = mipi_csis_read(csis, MIPI_CSIS_ISP_CONFIG_CH(0)); val &= ~(MIPI_CSIS_ISPCFG_ALIGN_32BIT | MIPI_CSIS_ISPCFG_FMT_MASK | MIPI_CSIS_ISPCFG_PIXEL_MASK); @@ -556,28 +578,28 @@ static void __mipi_csis_set_format(struct csi_state *state) * * TODO: Verify which other formats require DUAL (or QUAD) modes. */ - if (state->csis_fmt->data_type == MIPI_CSI2_DATA_TYPE_YUV422_8) + if (csis->csis_fmt->data_type == MIPI_CSI2_DATA_TYPE_YUV422_8) val |= MIPI_CSIS_ISPCFG_PIXEL_MODE_DUAL; - val |= MIPI_CSIS_ISPCFG_FMT(state->csis_fmt->data_type); - mipi_csis_write(state, MIPI_CSIS_ISP_CONFIG_CH(0), val); + val |= MIPI_CSIS_ISPCFG_FMT(csis->csis_fmt->data_type); + mipi_csis_write(csis, MIPI_CSIS_ISP_CONFIG_CH(0), val); /* Pixel resolution */ val = mf->width | (mf->height << 16); - mipi_csis_write(state, MIPI_CSIS_ISP_RESOL_CH(0), val); + mipi_csis_write(csis, MIPI_CSIS_ISP_RESOL_CH(0), val); } -static int mipi_csis_calculate_params(struct csi_state *state) +static int mipi_csis_calculate_params(struct mipi_csis_device *csis) { s64 link_freq; u32 lane_rate; /* Calculate the line rate from the pixel rate. */ - link_freq = v4l2_get_link_freq(state->src_sd->ctrl_handler, - state->csis_fmt->width, - state->bus.num_data_lanes * 2); + link_freq = v4l2_get_link_freq(csis->src_sd->ctrl_handler, + csis->csis_fmt->width, + csis->bus.num_data_lanes * 2); if (link_freq < 0) { - dev_err(state->dev, "Unable to obtain link frequency: %d\n", + dev_err(csis->dev, "Unable to obtain link frequency: %d\n", (int)link_freq); return link_freq; } @@ -585,7 +607,7 @@ static int mipi_csis_calculate_params(struct csi_state *state) lane_rate = link_freq * 2; if (lane_rate < 80000000 || lane_rate > 1500000000) { - dev_dbg(state->dev, "Out-of-bound lane rate %u\n", lane_rate); + dev_dbg(csis->dev, "Out-of-bound lane rate %u\n", lane_rate); return -EINVAL; } @@ -595,57 +617,57 @@ static int mipi_csis_calculate_params(struct csi_state *state) * (which is documented as corresponding to CSI-2 v0.87 to v1.00) until * we figure out how to compute it correctly. */ - state->hs_settle = (lane_rate - 5000000) / 45000000; - state->clk_settle = 0; + csis->hs_settle = (lane_rate - 5000000) / 45000000; + csis->clk_settle = 0; - dev_dbg(state->dev, "lane rate %u, Tclk_settle %u, Ths_settle %u\n", - lane_rate, state->clk_settle, state->hs_settle); + dev_dbg(csis->dev, "lane rate %u, Tclk_settle %u, Ths_settle %u\n", + lane_rate, csis->clk_settle, csis->hs_settle); - if (state->debug.hs_settle < 0xff) { - dev_dbg(state->dev, "overriding Ths_settle with %u\n", - state->debug.hs_settle); - state->hs_settle = state->debug.hs_settle; + if (csis->debug.hs_settle < 0xff) { + dev_dbg(csis->dev, "overriding Ths_settle with %u\n", + csis->debug.hs_settle); + csis->hs_settle = csis->debug.hs_settle; } - if (state->debug.clk_settle < 4) { - dev_dbg(state->dev, "overriding Tclk_settle with %u\n", - state->debug.clk_settle); - state->clk_settle = state->debug.clk_settle; + if (csis->debug.clk_settle < 4) { + dev_dbg(csis->dev, "overriding Tclk_settle with %u\n", + csis->debug.clk_settle); + csis->clk_settle = csis->debug.clk_settle; } return 0; } -static void mipi_csis_set_params(struct csi_state *state) +static void mipi_csis_set_params(struct mipi_csis_device *csis) { - int lanes = state->bus.num_data_lanes; + int lanes = csis->bus.num_data_lanes; u32 val; - val = mipi_csis_read(state, MIPI_CSIS_CMN_CTRL); + val = mipi_csis_read(csis, MIPI_CSIS_CMN_CTRL); val &= ~MIPI_CSIS_CMN_CTRL_LANE_NR_MASK; val |= (lanes - 1) << MIPI_CSIS_CMN_CTRL_LANE_NR_OFFSET; - if (state->info->version == MIPI_CSIS_V3_3) + if (csis->info->version == MIPI_CSIS_V3_3) val |= MIPI_CSIS_CMN_CTRL_INTER_MODE; - mipi_csis_write(state, MIPI_CSIS_CMN_CTRL, val); + mipi_csis_write(csis, MIPI_CSIS_CMN_CTRL, val); - __mipi_csis_set_format(state); + __mipi_csis_set_format(csis); - mipi_csis_write(state, MIPI_CSIS_DPHY_CMN_CTRL, - MIPI_CSIS_DPHY_CMN_CTRL_HSSETTLE(state->hs_settle) | - MIPI_CSIS_DPHY_CMN_CTRL_CLKSETTLE(state->clk_settle)); + mipi_csis_write(csis, MIPI_CSIS_DPHY_CMN_CTRL, + MIPI_CSIS_DPHY_CMN_CTRL_HSSETTLE(csis->hs_settle) | + MIPI_CSIS_DPHY_CMN_CTRL_CLKSETTLE(csis->clk_settle)); val = (0 << MIPI_CSIS_ISP_SYNC_HSYNC_LINTV_OFFSET) | (0 << MIPI_CSIS_ISP_SYNC_VSYNC_SINTV_OFFSET) | (0 << MIPI_CSIS_ISP_SYNC_VSYNC_EINTV_OFFSET); - mipi_csis_write(state, MIPI_CSIS_ISP_SYNC_CH(0), val); + mipi_csis_write(csis, MIPI_CSIS_ISP_SYNC_CH(0), val); - val = mipi_csis_read(state, MIPI_CSIS_CLK_CTRL); + val = mipi_csis_read(csis, MIPI_CSIS_CLK_CTRL); val |= MIPI_CSIS_CLK_CTRL_WCLK_SRC; val |= MIPI_CSIS_CLK_CTRL_CLKGATE_TRAIL_CH0(15); val &= ~MIPI_CSIS_CLK_CTRL_CLKGATE_EN_MSK; - mipi_csis_write(state, MIPI_CSIS_CLK_CTRL, val); + mipi_csis_write(csis, MIPI_CSIS_CLK_CTRL, val); - mipi_csis_write(state, MIPI_CSIS_DPHY_BCTRL_L, + mipi_csis_write(csis, MIPI_CSIS_DPHY_BCTRL_L, MIPI_CSIS_DPHY_BCTRL_L_BIAS_REF_VOLT_715MV | MIPI_CSIS_DPHY_BCTRL_L_BGR_CHOPPER_FREQ_3MHZ | MIPI_CSIS_DPHY_BCTRL_L_REG_12P_LVL_CTL_1_2V | @@ -653,95 +675,95 @@ static void mipi_csis_set_params(struct csi_state *state) MIPI_CSIS_DPHY_BCTRL_L_LP_RX_VREF_LVL_715MV | MIPI_CSIS_DPHY_BCTRL_L_LP_CD_HYS_60MV | MIPI_CSIS_DPHY_BCTRL_L_B_DPHYCTRL(20000000)); - mipi_csis_write(state, MIPI_CSIS_DPHY_BCTRL_H, 0); + mipi_csis_write(csis, MIPI_CSIS_DPHY_BCTRL_H, 0); /* Update the shadow register. */ - val = mipi_csis_read(state, MIPI_CSIS_CMN_CTRL); - mipi_csis_write(state, MIPI_CSIS_CMN_CTRL, + val = mipi_csis_read(csis, MIPI_CSIS_CMN_CTRL); + mipi_csis_write(csis, MIPI_CSIS_CMN_CTRL, val | MIPI_CSIS_CMN_CTRL_UPDATE_SHADOW | MIPI_CSIS_CMN_CTRL_UPDATE_SHADOW_CTRL); } -static int mipi_csis_clk_enable(struct csi_state *state) +static int mipi_csis_clk_enable(struct mipi_csis_device *csis) { - return clk_bulk_prepare_enable(state->info->num_clocks, state->clks); + return clk_bulk_prepare_enable(csis->info->num_clocks, csis->clks); } -static void mipi_csis_clk_disable(struct csi_state *state) +static void mipi_csis_clk_disable(struct mipi_csis_device *csis) { - clk_bulk_disable_unprepare(state->info->num_clocks, state->clks); + clk_bulk_disable_unprepare(csis->info->num_clocks, csis->clks); } -static int mipi_csis_clk_get(struct csi_state *state) +static int mipi_csis_clk_get(struct mipi_csis_device *csis) { unsigned int i; int ret; - state->clks = devm_kcalloc(state->dev, state->info->num_clocks, - sizeof(*state->clks), GFP_KERNEL); + csis->clks = devm_kcalloc(csis->dev, csis->info->num_clocks, + sizeof(*csis->clks), GFP_KERNEL); - if (!state->clks) + if (!csis->clks) return -ENOMEM; - for (i = 0; i < state->info->num_clocks; i++) - state->clks[i].id = mipi_csis_clk_id[i]; + for (i = 0; i < csis->info->num_clocks; i++) + csis->clks[i].id = mipi_csis_clk_id[i]; - ret = devm_clk_bulk_get(state->dev, state->info->num_clocks, - state->clks); + ret = devm_clk_bulk_get(csis->dev, csis->info->num_clocks, + csis->clks); if (ret < 0) return ret; /* Set clock rate */ - ret = clk_set_rate(state->clks[MIPI_CSIS_CLK_WRAP].clk, - state->clk_frequency); + ret = clk_set_rate(csis->clks[MIPI_CSIS_CLK_WRAP].clk, + csis->clk_frequency); if (ret < 0) - dev_err(state->dev, "set rate=%d failed: %d\n", - state->clk_frequency, ret); + dev_err(csis->dev, "set rate=%d failed: %d\n", + csis->clk_frequency, ret); return ret; } -static void mipi_csis_start_stream(struct csi_state *state) +static void mipi_csis_start_stream(struct mipi_csis_device *csis) { - mipi_csis_sw_reset(state); - mipi_csis_set_params(state); - mipi_csis_system_enable(state, true); - mipi_csis_enable_interrupts(state, true); + mipi_csis_sw_reset(csis); + mipi_csis_set_params(csis); + mipi_csis_system_enable(csis, true); + mipi_csis_enable_interrupts(csis, true); } -static void mipi_csis_stop_stream(struct csi_state *state) +static void mipi_csis_stop_stream(struct mipi_csis_device *csis) { - mipi_csis_enable_interrupts(state, false); - mipi_csis_system_enable(state, false); + mipi_csis_enable_interrupts(csis, false); + mipi_csis_system_enable(csis, false); } static irqreturn_t mipi_csis_irq_handler(int irq, void *dev_id) { - struct csi_state *state = dev_id; + struct mipi_csis_device *csis = dev_id; unsigned long flags; unsigned int i; u32 status; u32 dbg_status; - status = mipi_csis_read(state, MIPI_CSIS_INT_SRC); - dbg_status = mipi_csis_read(state, MIPI_CSIS_DBG_INTR_SRC); + status = mipi_csis_read(csis, MIPI_CSIS_INT_SRC); + dbg_status = mipi_csis_read(csis, MIPI_CSIS_DBG_INTR_SRC); - spin_lock_irqsave(&state->slock, flags); + spin_lock_irqsave(&csis->slock, flags); /* Update the event/error counters */ - if ((status & MIPI_CSIS_INT_SRC_ERRORS) || state->debug.enable) { + if ((status & MIPI_CSIS_INT_SRC_ERRORS) || csis->debug.enable) { for (i = 0; i < MIPI_CSIS_NUM_EVENTS; i++) { - struct mipi_csis_event *event = &state->events[i]; + struct mipi_csis_event *event = &csis->events[i]; if ((!event->debug && (status & event->mask)) || (event->debug && (dbg_status & event->mask))) event->counter++; } } - spin_unlock_irqrestore(&state->slock, flags); + spin_unlock_irqrestore(&csis->slock, flags); - mipi_csis_write(state, MIPI_CSIS_INT_SRC, status); - mipi_csis_write(state, MIPI_CSIS_DBG_INTR_SRC, dbg_status); + mipi_csis_write(csis, MIPI_CSIS_INT_SRC, status); + mipi_csis_write(csis, MIPI_CSIS_DBG_INTR_SRC, dbg_status); return IRQ_HANDLED; } @@ -750,47 +772,47 @@ static irqreturn_t mipi_csis_irq_handler(int irq, void *dev_id) * PHY regulator and reset */ -static int mipi_csis_phy_enable(struct csi_state *state) +static int mipi_csis_phy_enable(struct mipi_csis_device *csis) { - if (state->info->version != MIPI_CSIS_V3_3) + if (csis->info->version != MIPI_CSIS_V3_3) return 0; - return regulator_enable(state->mipi_phy_regulator); + return regulator_enable(csis->mipi_phy_regulator); } -static int mipi_csis_phy_disable(struct csi_state *state) +static int mipi_csis_phy_disable(struct mipi_csis_device *csis) { - if (state->info->version != MIPI_CSIS_V3_3) + if (csis->info->version != MIPI_CSIS_V3_3) return 0; - return regulator_disable(state->mipi_phy_regulator); + return regulator_disable(csis->mipi_phy_regulator); } -static void mipi_csis_phy_reset(struct csi_state *state) +static void mipi_csis_phy_reset(struct mipi_csis_device *csis) { - if (state->info->version != MIPI_CSIS_V3_3) + if (csis->info->version != MIPI_CSIS_V3_3) return; - reset_control_assert(state->mrst); + reset_control_assert(csis->mrst); msleep(20); - reset_control_deassert(state->mrst); + reset_control_deassert(csis->mrst); } -static int mipi_csis_phy_init(struct csi_state *state) +static int mipi_csis_phy_init(struct mipi_csis_device *csis) { - if (state->info->version != MIPI_CSIS_V3_3) + if (csis->info->version != MIPI_CSIS_V3_3) return 0; /* Get MIPI PHY reset and regulator. */ - state->mrst = devm_reset_control_get_exclusive(state->dev, NULL); - if (IS_ERR(state->mrst)) - return PTR_ERR(state->mrst); + csis->mrst = devm_reset_control_get_exclusive(csis->dev, NULL); + if (IS_ERR(csis->mrst)) + return PTR_ERR(csis->mrst); - state->mipi_phy_regulator = devm_regulator_get(state->dev, "phy"); - if (IS_ERR(state->mipi_phy_regulator)) - return PTR_ERR(state->mipi_phy_regulator); + csis->mipi_phy_regulator = devm_regulator_get(csis->dev, "phy"); + if (IS_ERR(csis->mipi_phy_regulator)) + return PTR_ERR(csis->mipi_phy_regulator); - return regulator_set_voltage(state->mipi_phy_regulator, 1000000, + return regulator_set_voltage(csis->mipi_phy_regulator, 1000000, 1000000); } @@ -798,36 +820,36 @@ static int mipi_csis_phy_init(struct csi_state *state) * Debug */ -static void mipi_csis_clear_counters(struct csi_state *state) +static void mipi_csis_clear_counters(struct mipi_csis_device *csis) { unsigned long flags; unsigned int i; - spin_lock_irqsave(&state->slock, flags); + spin_lock_irqsave(&csis->slock, flags); for (i = 0; i < MIPI_CSIS_NUM_EVENTS; i++) - state->events[i].counter = 0; - spin_unlock_irqrestore(&state->slock, flags); + csis->events[i].counter = 0; + spin_unlock_irqrestore(&csis->slock, flags); } -static void mipi_csis_log_counters(struct csi_state *state, bool non_errors) +static void mipi_csis_log_counters(struct mipi_csis_device *csis, bool non_errors) { unsigned int num_events = non_errors ? MIPI_CSIS_NUM_EVENTS : MIPI_CSIS_NUM_EVENTS - 8; unsigned long flags; unsigned int i; - spin_lock_irqsave(&state->slock, flags); + spin_lock_irqsave(&csis->slock, flags); for (i = 0; i < num_events; ++i) { - if (state->events[i].counter > 0 || state->debug.enable) - dev_info(state->dev, "%s events: %d\n", - state->events[i].name, - state->events[i].counter); + if (csis->events[i].counter > 0 || csis->debug.enable) + dev_info(csis->dev, "%s events: %d\n", + csis->events[i].name, + csis->events[i].counter); } - spin_unlock_irqrestore(&state->slock, flags); + spin_unlock_irqrestore(&csis->slock, flags); } -static int mipi_csis_dump_regs(struct csi_state *state) +static int mipi_csis_dump_regs(struct mipi_csis_device *csis) { static const struct { u32 offset; @@ -851,135 +873,134 @@ static int mipi_csis_dump_regs(struct csi_state *state) unsigned int i; u32 cfg; - dev_info(state->dev, "--- REGISTERS ---\n"); + if (!pm_runtime_get_if_in_use(csis->dev)) + return 0; + + dev_info(csis->dev, "--- REGISTERS ---\n"); for (i = 0; i < ARRAY_SIZE(registers); i++) { - cfg = mipi_csis_read(state, registers[i].offset); - dev_info(state->dev, "%14s: 0x%08x\n", registers[i].name, cfg); + cfg = mipi_csis_read(csis, registers[i].offset); + dev_info(csis->dev, "%14s: 0x%08x\n", registers[i].name, cfg); } + pm_runtime_put(csis->dev); + return 0; } static int mipi_csis_dump_regs_show(struct seq_file *m, void *private) { - struct csi_state *state = m->private; + struct mipi_csis_device *csis = m->private; - return mipi_csis_dump_regs(state); + return mipi_csis_dump_regs(csis); } DEFINE_SHOW_ATTRIBUTE(mipi_csis_dump_regs); -static void mipi_csis_debugfs_init(struct csi_state *state) +static void mipi_csis_debugfs_init(struct mipi_csis_device *csis) { - state->debug.hs_settle = UINT_MAX; - state->debug.clk_settle = UINT_MAX; + csis->debug.hs_settle = UINT_MAX; + csis->debug.clk_settle = UINT_MAX; - state->debugfs_root = debugfs_create_dir(dev_name(state->dev), NULL); + csis->debugfs_root = debugfs_create_dir(dev_name(csis->dev), NULL); - debugfs_create_bool("debug_enable", 0600, state->debugfs_root, - &state->debug.enable); - debugfs_create_file("dump_regs", 0600, state->debugfs_root, state, + debugfs_create_bool("debug_enable", 0600, csis->debugfs_root, + &csis->debug.enable); + debugfs_create_file("dump_regs", 0600, csis->debugfs_root, csis, &mipi_csis_dump_regs_fops); - debugfs_create_u32("tclk_settle", 0600, state->debugfs_root, - &state->debug.clk_settle); - debugfs_create_u32("ths_settle", 0600, state->debugfs_root, - &state->debug.hs_settle); + debugfs_create_u32("tclk_settle", 0600, csis->debugfs_root, + &csis->debug.clk_settle); + debugfs_create_u32("ths_settle", 0600, csis->debugfs_root, + &csis->debug.hs_settle); } -static void mipi_csis_debugfs_exit(struct csi_state *state) +static void mipi_csis_debugfs_exit(struct mipi_csis_device *csis) { - debugfs_remove_recursive(state->debugfs_root); + debugfs_remove_recursive(csis->debugfs_root); } /* ----------------------------------------------------------------------------- * V4L2 subdev operations */ -static struct csi_state *mipi_sd_to_csis_state(struct v4l2_subdev *sdev) +static struct mipi_csis_device *sd_to_mipi_csis_device(struct v4l2_subdev *sdev) { - return container_of(sdev, struct csi_state, sd); + return container_of(sdev, struct mipi_csis_device, sd); } static int mipi_csis_s_stream(struct v4l2_subdev *sd, int enable) { - struct csi_state *state = mipi_sd_to_csis_state(sd); + struct mipi_csis_device *csis = sd_to_mipi_csis_device(sd); int ret; - if (enable) { - ret = mipi_csis_calculate_params(state); - if (ret < 0) - return ret; + if (!enable) { + mutex_lock(&csis->lock); - mipi_csis_clear_counters(state); + v4l2_subdev_call(csis->src_sd, video, s_stream, 0); - ret = pm_runtime_resume_and_get(state->dev); - if (ret < 0) - return ret; + mipi_csis_stop_stream(csis); + if (csis->debug.enable) + mipi_csis_log_counters(csis, true); + + mutex_unlock(&csis->lock); - ret = v4l2_subdev_call(state->src_sd, core, s_power, 1); - if (ret < 0 && ret != -ENOIOCTLCMD) - goto done; + pm_runtime_put(csis->dev); + + return 0; } - mutex_lock(&state->lock); + ret = mipi_csis_calculate_params(csis); + if (ret < 0) + return ret; - if (enable) { - if (state->state & ST_SUSPENDED) { - ret = -EBUSY; - goto unlock; - } + mipi_csis_clear_counters(csis); - mipi_csis_start_stream(state); - ret = v4l2_subdev_call(state->src_sd, video, s_stream, 1); - if (ret < 0) - goto unlock; + ret = pm_runtime_resume_and_get(csis->dev); + if (ret < 0) + return ret; - mipi_csis_log_counters(state, true); + mutex_lock(&csis->lock); - state->state |= ST_STREAMING; - } else { - v4l2_subdev_call(state->src_sd, video, s_stream, 0); - ret = v4l2_subdev_call(state->src_sd, core, s_power, 0); - if (ret == -ENOIOCTLCMD) - ret = 0; - mipi_csis_stop_stream(state); - state->state &= ~ST_STREAMING; - if (state->debug.enable) - mipi_csis_log_counters(state, true); - } + mipi_csis_start_stream(csis); + ret = v4l2_subdev_call(csis->src_sd, video, s_stream, 1); + if (ret < 0) + goto error; -unlock: - mutex_unlock(&state->lock); + mipi_csis_log_counters(csis, true); -done: - if (!enable || ret < 0) - pm_runtime_put(state->dev); + mutex_unlock(&csis->lock); + + return 0; + +error: + mipi_csis_stop_stream(csis); + mutex_unlock(&csis->lock); + pm_runtime_put(csis->dev); return ret; } static struct v4l2_mbus_framefmt * -mipi_csis_get_format(struct csi_state *state, +mipi_csis_get_format(struct mipi_csis_device *csis, struct v4l2_subdev_state *sd_state, enum v4l2_subdev_format_whence which, unsigned int pad) { if (which == V4L2_SUBDEV_FORMAT_TRY) - return v4l2_subdev_get_try_format(&state->sd, sd_state, pad); + return v4l2_subdev_get_try_format(&csis->sd, sd_state, pad); - return &state->format_mbus[pad]; + return &csis->format_mbus[pad]; } static int mipi_csis_init_cfg(struct v4l2_subdev *sd, struct v4l2_subdev_state *sd_state) { - struct csi_state *state = mipi_sd_to_csis_state(sd); + struct mipi_csis_device *csis = sd_to_mipi_csis_device(sd); struct v4l2_mbus_framefmt *fmt_sink; struct v4l2_mbus_framefmt *fmt_source; enum v4l2_subdev_format_whence which; which = sd_state ? V4L2_SUBDEV_FORMAT_TRY : V4L2_SUBDEV_FORMAT_ACTIVE; - fmt_sink = mipi_csis_get_format(state, sd_state, which, CSIS_PAD_SINK); + fmt_sink = mipi_csis_get_format(csis, sd_state, which, CSIS_PAD_SINK); fmt_sink->code = MEDIA_BUS_FMT_UYVY8_1X16; fmt_sink->width = MIPI_CSIS_DEF_PIX_WIDTH; @@ -993,15 +1014,7 @@ static int mipi_csis_init_cfg(struct v4l2_subdev *sd, V4L2_MAP_QUANTIZATION_DEFAULT(false, fmt_sink->colorspace, fmt_sink->ycbcr_enc); - /* - * When called from mipi_csis_subdev_init() to initialize the active - * configuration, cfg is NULL, which indicates there's no source pad - * configuration to set. - */ - if (!sd_state) - return 0; - - fmt_source = mipi_csis_get_format(state, sd_state, which, + fmt_source = mipi_csis_get_format(csis, sd_state, which, CSIS_PAD_SOURCE); *fmt_source = *fmt_sink; @@ -1012,15 +1025,15 @@ static int mipi_csis_get_fmt(struct v4l2_subdev *sd, struct v4l2_subdev_state *sd_state, struct v4l2_subdev_format *sdformat) { - struct csi_state *state = mipi_sd_to_csis_state(sd); + struct mipi_csis_device *csis = sd_to_mipi_csis_device(sd); struct v4l2_mbus_framefmt *fmt; - fmt = mipi_csis_get_format(state, sd_state, sdformat->which, + fmt = mipi_csis_get_format(csis, sd_state, sdformat->which, sdformat->pad); - mutex_lock(&state->lock); + mutex_lock(&csis->lock); sdformat->format = *fmt; - mutex_unlock(&state->lock); + mutex_unlock(&csis->lock); return 0; } @@ -1029,7 +1042,7 @@ static int mipi_csis_enum_mbus_code(struct v4l2_subdev *sd, struct v4l2_subdev_state *sd_state, struct v4l2_subdev_mbus_code_enum *code) { - struct csi_state *state = mipi_sd_to_csis_state(sd); + struct mipi_csis_device *csis = sd_to_mipi_csis_device(sd); /* * The CSIS can't transcode in any way, the source format is identical @@ -1041,7 +1054,7 @@ static int mipi_csis_enum_mbus_code(struct v4l2_subdev *sd, if (code->index > 0) return -EINVAL; - fmt = mipi_csis_get_format(state, sd_state, code->which, + fmt = mipi_csis_get_format(csis, sd_state, code->which, code->pad); code->code = fmt->code; return 0; @@ -1062,7 +1075,7 @@ static int mipi_csis_set_fmt(struct v4l2_subdev *sd, struct v4l2_subdev_state *sd_state, struct v4l2_subdev_format *sdformat) { - struct csi_state *state = mipi_sd_to_csis_state(sd); + struct mipi_csis_device *csis = sd_to_mipi_csis_device(sd); struct csis_pix_format const *csis_fmt; struct v4l2_mbus_framefmt *fmt; unsigned int align; @@ -1110,10 +1123,10 @@ static int mipi_csis_set_fmt(struct v4l2_subdev *sd, &sdformat->format.height, 1, CSIS_MAX_PIX_HEIGHT, 0, 0); - fmt = mipi_csis_get_format(state, sd_state, sdformat->which, + fmt = mipi_csis_get_format(csis, sd_state, sdformat->which, sdformat->pad); - mutex_lock(&state->lock); + mutex_lock(&csis->lock); fmt->code = csis_fmt->code; fmt->width = sdformat->format.width; @@ -1126,7 +1139,7 @@ static int mipi_csis_set_fmt(struct v4l2_subdev *sd, sdformat->format = *fmt; /* Propagate the format from sink to source. */ - fmt = mipi_csis_get_format(state, sd_state, sdformat->which, + fmt = mipi_csis_get_format(csis, sd_state, sdformat->which, CSIS_PAD_SOURCE); *fmt = sdformat->format; @@ -1135,22 +1148,20 @@ static int mipi_csis_set_fmt(struct v4l2_subdev *sd, /* Store the CSIS format descriptor for active formats. */ if (sdformat->which == V4L2_SUBDEV_FORMAT_ACTIVE) - state->csis_fmt = csis_fmt; + csis->csis_fmt = csis_fmt; - mutex_unlock(&state->lock); + mutex_unlock(&csis->lock); return 0; } static int mipi_csis_log_status(struct v4l2_subdev *sd) { - struct csi_state *state = mipi_sd_to_csis_state(sd); + struct mipi_csis_device *csis = sd_to_mipi_csis_device(sd); - mutex_lock(&state->lock); - mipi_csis_log_counters(state, true); - if (state->debug.enable && (state->state & ST_POWERED)) - mipi_csis_dump_regs(state); - mutex_unlock(&state->lock); + mipi_csis_log_counters(csis, true); + if (csis->debug.enable) + mipi_csis_dump_regs(csis); return 0; } @@ -1185,10 +1196,10 @@ static int mipi_csis_link_setup(struct media_entity *entity, const struct media_pad *remote_pad, u32 flags) { struct v4l2_subdev *sd = media_entity_to_v4l2_subdev(entity); - struct csi_state *state = mipi_sd_to_csis_state(sd); + struct mipi_csis_device *csis = sd_to_mipi_csis_device(sd); struct v4l2_subdev *remote_sd; - dev_dbg(state->dev, "link setup %s -> %s", remote_pad->entity->name, + dev_dbg(csis->dev, "link setup %s -> %s", remote_pad->entity->name, local_pad->entity->name); /* We only care about the link to the source. */ @@ -1198,12 +1209,12 @@ static int mipi_csis_link_setup(struct media_entity *entity, remote_sd = media_entity_to_v4l2_subdev(remote_pad->entity); if (flags & MEDIA_LNK_FL_ENABLED) { - if (state->src_sd) + if (csis->src_sd) return -EBUSY; - state->src_sd = remote_sd; + csis->src_sd = remote_sd; } else { - state->src_sd = NULL; + csis->src_sd = NULL; } return 0; @@ -1219,18 +1230,18 @@ static const struct media_entity_operations mipi_csis_entity_ops = { * Async subdev notifier */ -static struct csi_state * +static struct mipi_csis_device * mipi_notifier_to_csis_state(struct v4l2_async_notifier *n) { - return container_of(n, struct csi_state, notifier); + return container_of(n, struct mipi_csis_device, notifier); } static int mipi_csis_notify_bound(struct v4l2_async_notifier *notifier, struct v4l2_subdev *sd, struct v4l2_async_subdev *asd) { - struct csi_state *state = mipi_notifier_to_csis_state(notifier); - struct media_pad *sink = &state->sd.entity.pads[CSIS_PAD_SINK]; + struct mipi_csis_device *csis = mipi_notifier_to_csis_state(notifier); + struct media_pad *sink = &csis->sd.entity.pads[CSIS_PAD_SINK]; return v4l2_create_fwnode_links_to_pad(sd, sink, 0); } @@ -1239,7 +1250,7 @@ static const struct v4l2_async_notifier_operations mipi_csis_notify_ops = { .bound = mipi_csis_notify_bound, }; -static int mipi_csis_async_register(struct csi_state *state) +static int mipi_csis_async_register(struct mipi_csis_device *csis) { struct v4l2_fwnode_endpoint vep = { .bus_type = V4L2_MBUS_CSI2_DPHY, @@ -1249,9 +1260,9 @@ static int mipi_csis_async_register(struct csi_state *state) unsigned int i; int ret; - v4l2_async_nf_init(&state->notifier); + v4l2_async_nf_init(&csis->notifier); - ep = fwnode_graph_get_endpoint_by_id(dev_fwnode(state->dev), 0, 0, + ep = fwnode_graph_get_endpoint_by_id(dev_fwnode(csis->dev), 0, 0, FWNODE_GRAPH_ENDPOINT_NEXT); if (!ep) return -ENOTCONN; @@ -1262,19 +1273,19 @@ static int mipi_csis_async_register(struct csi_state *state) for (i = 0; i < vep.bus.mipi_csi2.num_data_lanes; ++i) { if (vep.bus.mipi_csi2.data_lanes[i] != i + 1) { - dev_err(state->dev, + dev_err(csis->dev, "data lanes reordering is not supported"); ret = -EINVAL; goto err_parse; } } - state->bus = vep.bus.mipi_csi2; + csis->bus = vep.bus.mipi_csi2; - dev_dbg(state->dev, "data lanes: %d\n", state->bus.num_data_lanes); - dev_dbg(state->dev, "flags: 0x%08x\n", state->bus.flags); + dev_dbg(csis->dev, "data lanes: %d\n", csis->bus.num_data_lanes); + dev_dbg(csis->dev, "flags: 0x%08x\n", csis->bus.flags); - asd = v4l2_async_nf_add_fwnode_remote(&state->notifier, ep, + asd = v4l2_async_nf_add_fwnode_remote(&csis->notifier, ep, struct v4l2_async_subdev); if (IS_ERR(asd)) { ret = PTR_ERR(asd); @@ -1283,13 +1294,13 @@ static int mipi_csis_async_register(struct csi_state *state) fwnode_handle_put(ep); - state->notifier.ops = &mipi_csis_notify_ops; + csis->notifier.ops = &mipi_csis_notify_ops; - ret = v4l2_async_subdev_nf_register(&state->sd, &state->notifier); + ret = v4l2_async_subdev_nf_register(&csis->sd, &csis->notifier); if (ret) return ret; - return v4l2_async_register_subdev(&state->sd); + return v4l2_async_register_subdev(&csis->sd); err_parse: fwnode_handle_put(ep); @@ -1301,97 +1312,63 @@ err_parse: * Suspend/resume */ -static int mipi_csis_pm_suspend(struct device *dev, bool runtime) +static int __maybe_unused mipi_csis_runtime_suspend(struct device *dev) { struct v4l2_subdev *sd = dev_get_drvdata(dev); - struct csi_state *state = mipi_sd_to_csis_state(sd); + struct mipi_csis_device *csis = sd_to_mipi_csis_device(sd); int ret = 0; - mutex_lock(&state->lock); - if (state->state & ST_POWERED) { - mipi_csis_stop_stream(state); - ret = mipi_csis_phy_disable(state); - if (ret) - goto unlock; - mipi_csis_clk_disable(state); - state->state &= ~ST_POWERED; - if (!runtime) - state->state |= ST_SUSPENDED; - } + mutex_lock(&csis->lock); + + ret = mipi_csis_phy_disable(csis); + if (ret) + goto unlock; + + mipi_csis_clk_disable(csis); unlock: - mutex_unlock(&state->lock); + mutex_unlock(&csis->lock); return ret ? -EAGAIN : 0; } -static int mipi_csis_pm_resume(struct device *dev, bool runtime) +static int __maybe_unused mipi_csis_runtime_resume(struct device *dev) { struct v4l2_subdev *sd = dev_get_drvdata(dev); - struct csi_state *state = mipi_sd_to_csis_state(sd); + struct mipi_csis_device *csis = sd_to_mipi_csis_device(sd); int ret = 0; - mutex_lock(&state->lock); - if (!runtime && !(state->state & ST_SUSPENDED)) - goto unlock; - - if (!(state->state & ST_POWERED)) { - ret = mipi_csis_phy_enable(state); - if (ret) - goto unlock; + mutex_lock(&csis->lock); - state->state |= ST_POWERED; - mipi_csis_clk_enable(state); - } - if (state->state & ST_STREAMING) - mipi_csis_start_stream(state); + ret = mipi_csis_phy_enable(csis); + if (ret) + goto unlock; - state->state &= ~ST_SUSPENDED; + mipi_csis_clk_enable(csis); unlock: - mutex_unlock(&state->lock); + mutex_unlock(&csis->lock); return ret ? -EAGAIN : 0; } -static int __maybe_unused mipi_csis_suspend(struct device *dev) -{ - return mipi_csis_pm_suspend(dev, false); -} - -static int __maybe_unused mipi_csis_resume(struct device *dev) -{ - return mipi_csis_pm_resume(dev, false); -} - -static int __maybe_unused mipi_csis_runtime_suspend(struct device *dev) -{ - return mipi_csis_pm_suspend(dev, true); -} - -static int __maybe_unused mipi_csis_runtime_resume(struct device *dev) -{ - return mipi_csis_pm_resume(dev, true); -} - static const struct dev_pm_ops mipi_csis_pm_ops = { SET_RUNTIME_PM_OPS(mipi_csis_runtime_suspend, mipi_csis_runtime_resume, NULL) - SET_SYSTEM_SLEEP_PM_OPS(mipi_csis_suspend, mipi_csis_resume) }; /* ----------------------------------------------------------------------------- * Probe/remove & platform driver */ -static int mipi_csis_subdev_init(struct csi_state *state) +static int mipi_csis_subdev_init(struct mipi_csis_device *csis) { - struct v4l2_subdev *sd = &state->sd; + struct v4l2_subdev *sd = &csis->sd; v4l2_subdev_init(sd, &mipi_csis_subdev_ops); sd->owner = THIS_MODULE; snprintf(sd->name, sizeof(sd->name), "csis-%s", - dev_name(state->dev)); + dev_name(csis->dev)); sd->flags |= V4L2_SUBDEV_FL_HAS_DEVNODE; sd->ctrl_handler = NULL; @@ -1399,26 +1376,26 @@ static int mipi_csis_subdev_init(struct csi_state *state) sd->entity.function = MEDIA_ENT_F_VID_IF_BRIDGE; sd->entity.ops = &mipi_csis_entity_ops; - sd->dev = state->dev; + sd->dev = csis->dev; - state->csis_fmt = &mipi_csis_formats[0]; + csis->csis_fmt = &mipi_csis_formats[0]; mipi_csis_init_cfg(sd, NULL); - state->pads[CSIS_PAD_SINK].flags = MEDIA_PAD_FL_SINK + csis->pads[CSIS_PAD_SINK].flags = MEDIA_PAD_FL_SINK | MEDIA_PAD_FL_MUST_CONNECT; - state->pads[CSIS_PAD_SOURCE].flags = MEDIA_PAD_FL_SOURCE + csis->pads[CSIS_PAD_SOURCE].flags = MEDIA_PAD_FL_SOURCE | MEDIA_PAD_FL_MUST_CONNECT; return media_entity_pads_init(&sd->entity, CSIS_PADS_NUM, - state->pads); + csis->pads); } -static int mipi_csis_parse_dt(struct csi_state *state) +static int mipi_csis_parse_dt(struct mipi_csis_device *csis) { - struct device_node *node = state->dev->of_node; + struct device_node *node = csis->dev->of_node; if (of_property_read_u32(node, "clock-frequency", - &state->clk_frequency)) - state->clk_frequency = DEFAULT_SCLK_CSIS_FREQ; + &csis->clk_frequency)) + csis->clk_frequency = DEFAULT_SCLK_CSIS_FREQ; return 0; } @@ -1426,102 +1403,102 @@ static int mipi_csis_parse_dt(struct csi_state *state) static int mipi_csis_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; - struct csi_state *state; + struct mipi_csis_device *csis; int irq; int ret; - state = devm_kzalloc(dev, sizeof(*state), GFP_KERNEL); - if (!state) + csis = devm_kzalloc(dev, sizeof(*csis), GFP_KERNEL); + if (!csis) return -ENOMEM; - mutex_init(&state->lock); - spin_lock_init(&state->slock); + mutex_init(&csis->lock); + spin_lock_init(&csis->slock); - state->dev = dev; - state->info = of_device_get_match_data(dev); + csis->dev = dev; + csis->info = of_device_get_match_data(dev); - memcpy(state->events, mipi_csis_events, sizeof(state->events)); + memcpy(csis->events, mipi_csis_events, sizeof(csis->events)); /* Parse DT properties. */ - ret = mipi_csis_parse_dt(state); + ret = mipi_csis_parse_dt(csis); if (ret < 0) { dev_err(dev, "Failed to parse device tree: %d\n", ret); return ret; } /* Acquire resources. */ - state->regs = devm_platform_ioremap_resource(pdev, 0); - if (IS_ERR(state->regs)) - return PTR_ERR(state->regs); + csis->regs = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(csis->regs)) + return PTR_ERR(csis->regs); irq = platform_get_irq(pdev, 0); if (irq < 0) return irq; - ret = mipi_csis_phy_init(state); + ret = mipi_csis_phy_init(csis); if (ret < 0) return ret; - ret = mipi_csis_clk_get(state); + ret = mipi_csis_clk_get(csis); if (ret < 0) return ret; /* Reset PHY and enable the clocks. */ - mipi_csis_phy_reset(state); + mipi_csis_phy_reset(csis); - ret = mipi_csis_clk_enable(state); + ret = mipi_csis_clk_enable(csis); if (ret < 0) { - dev_err(state->dev, "failed to enable clocks: %d\n", ret); + dev_err(csis->dev, "failed to enable clocks: %d\n", ret); return ret; } /* Now that the hardware is initialized, request the interrupt. */ ret = devm_request_irq(dev, irq, mipi_csis_irq_handler, 0, - dev_name(dev), state); + dev_name(dev), csis); if (ret) { dev_err(dev, "Interrupt request failed\n"); goto disable_clock; } /* Initialize and register the subdev. */ - ret = mipi_csis_subdev_init(state); + ret = mipi_csis_subdev_init(csis); if (ret < 0) goto disable_clock; - platform_set_drvdata(pdev, &state->sd); + platform_set_drvdata(pdev, &csis->sd); - ret = mipi_csis_async_register(state); + ret = mipi_csis_async_register(csis); if (ret < 0) { dev_err(dev, "async register failed: %d\n", ret); goto cleanup; } /* Initialize debugfs. */ - mipi_csis_debugfs_init(state); + mipi_csis_debugfs_init(csis); /* Enable runtime PM. */ pm_runtime_enable(dev); if (!pm_runtime_enabled(dev)) { - ret = mipi_csis_pm_resume(dev, true); + ret = mipi_csis_runtime_resume(dev); if (ret < 0) goto unregister_all; } dev_info(dev, "lanes: %d, freq: %u\n", - state->bus.num_data_lanes, state->clk_frequency); + csis->bus.num_data_lanes, csis->clk_frequency); return 0; unregister_all: - mipi_csis_debugfs_exit(state); + mipi_csis_debugfs_exit(csis); cleanup: - media_entity_cleanup(&state->sd.entity); - v4l2_async_nf_unregister(&state->notifier); - v4l2_async_nf_cleanup(&state->notifier); - v4l2_async_unregister_subdev(&state->sd); + media_entity_cleanup(&csis->sd.entity); + v4l2_async_nf_unregister(&csis->notifier); + v4l2_async_nf_cleanup(&csis->notifier); + v4l2_async_unregister_subdev(&csis->sd); disable_clock: - mipi_csis_clk_disable(state); - mutex_destroy(&state->lock); + mipi_csis_clk_disable(csis); + mutex_destroy(&csis->lock); return ret; } @@ -1529,18 +1506,18 @@ disable_clock: static int mipi_csis_remove(struct platform_device *pdev) { struct v4l2_subdev *sd = platform_get_drvdata(pdev); - struct csi_state *state = mipi_sd_to_csis_state(sd); + struct mipi_csis_device *csis = sd_to_mipi_csis_device(sd); - mipi_csis_debugfs_exit(state); - v4l2_async_nf_unregister(&state->notifier); - v4l2_async_nf_cleanup(&state->notifier); - v4l2_async_unregister_subdev(&state->sd); + mipi_csis_debugfs_exit(csis); + v4l2_async_nf_unregister(&csis->notifier); + v4l2_async_nf_cleanup(&csis->notifier); + v4l2_async_unregister_subdev(&csis->sd); pm_runtime_disable(&pdev->dev); - mipi_csis_pm_suspend(&pdev->dev, true); - mipi_csis_clk_disable(state); - media_entity_cleanup(&state->sd.entity); - mutex_destroy(&state->lock); + mipi_csis_runtime_suspend(&pdev->dev); + mipi_csis_clk_disable(csis); + media_entity_cleanup(&csis->sd.entity); + mutex_destroy(&csis->lock); pm_runtime_set_suspended(&pdev->dev); return 0; diff --git a/drivers/media/platform/qcom/camss/camss-video.c b/drivers/media/platform/qcom/camss/camss-video.c index 5dc1ddbe6d65..307bb1dc4589 100644 --- a/drivers/media/platform/qcom/camss/camss-video.c +++ b/drivers/media/platform/qcom/camss/camss-video.c @@ -576,12 +576,8 @@ static const struct vb2_ops msm_video_vb2_q_ops = { static int video_querycap(struct file *file, void *fh, struct v4l2_capability *cap) { - struct camss_video *video = video_drvdata(file); - strscpy(cap->driver, "qcom-camss", sizeof(cap->driver)); strscpy(cap->card, "Qualcomm Camera Subsystem", sizeof(cap->card)); - snprintf(cap->bus_info, sizeof(cap->bus_info), "platform:%s", - dev_name(video->camss->dev)); return 0; } diff --git a/drivers/media/platform/qcom/venus/core.h b/drivers/media/platform/qcom/venus/core.h index c3023340d95c..d33825553edc 100644 --- a/drivers/media/platform/qcom/venus/core.h +++ b/drivers/media/platform/qcom/venus/core.h @@ -261,6 +261,7 @@ struct venc_controls { u32 header_mode; bool aud_enable; + u32 intra_refresh_type; u32 intra_refresh_period; struct { diff --git a/drivers/media/platform/qcom/venus/helpers.c b/drivers/media/platform/qcom/venus/helpers.c index 0bca95d01650..5c1104379c49 100644 --- a/drivers/media/platform/qcom/venus/helpers.c +++ b/drivers/media/platform/qcom/venus/helpers.c @@ -90,12 +90,28 @@ bool venus_helper_check_codec(struct venus_inst *inst, u32 v4l2_pixfmt) } EXPORT_SYMBOL_GPL(venus_helper_check_codec); +static void free_dpb_buf(struct venus_inst *inst, struct intbuf *buf) +{ + ida_free(&inst->dpb_ids, buf->dpb_out_tag); + + list_del_init(&buf->list); + dma_free_attrs(inst->core->dev, buf->size, buf->va, buf->da, + buf->attrs); + kfree(buf); +} + int venus_helper_queue_dpb_bufs(struct venus_inst *inst) { - struct intbuf *buf; + struct intbuf *buf, *next; + unsigned int dpb_size = 0; int ret = 0; - list_for_each_entry(buf, &inst->dpbbufs, list) { + if (inst->dpb_buftype == HFI_BUFFER_OUTPUT) + dpb_size = inst->output_buf_size; + else if (inst->dpb_buftype == HFI_BUFFER_OUTPUT2) + dpb_size = inst->output2_buf_size; + + list_for_each_entry_safe(buf, next, &inst->dpbbufs, list) { struct hfi_frame_data fdata; memset(&fdata, 0, sizeof(fdata)); @@ -106,6 +122,12 @@ int venus_helper_queue_dpb_bufs(struct venus_inst *inst) if (buf->owned_by == FIRMWARE) continue; + /* free buffer from previous sequence which was released later */ + if (dpb_size > buf->size) { + free_dpb_buf(inst, buf); + continue; + } + fdata.clnt_data = buf->dpb_out_tag; ret = hfi_session_process_buf(inst, &fdata); @@ -127,13 +149,7 @@ int venus_helper_free_dpb_bufs(struct venus_inst *inst) list_for_each_entry_safe(buf, n, &inst->dpbbufs, list) { if (buf->owned_by == FIRMWARE) continue; - - ida_free(&inst->dpb_ids, buf->dpb_out_tag); - - list_del_init(&buf->list); - dma_free_attrs(inst->core->dev, buf->size, buf->va, buf->da, - buf->attrs); - kfree(buf); + free_dpb_buf(inst, buf); } if (list_empty(&inst->dpbbufs)) @@ -592,6 +608,10 @@ static u32 to_hfi_raw_fmt(u32 v4l2_fmt) return HFI_COLOR_FORMAT_NV12; case V4L2_PIX_FMT_NV21: return HFI_COLOR_FORMAT_NV21; + case V4L2_PIX_FMT_QC08C: + return HFI_COLOR_FORMAT_NV12_UBWC; + case V4L2_PIX_FMT_QC10C: + return HFI_COLOR_FORMAT_YUV420_TP10_UBWC; default: break; } @@ -1174,7 +1194,8 @@ int venus_helper_set_format_constraints(struct venus_inst *inst) if (!IS_V6(inst->core)) return 0; - if (inst->opb_fmt == HFI_COLOR_FORMAT_NV12_UBWC) + if (inst->opb_fmt == HFI_COLOR_FORMAT_NV12_UBWC || + inst->opb_fmt == HFI_COLOR_FORMAT_YUV420_TP10_UBWC) return 0; pconstraint.buffer_type = HFI_BUFFER_OUTPUT2; @@ -1745,27 +1766,6 @@ int venus_helper_get_out_fmts(struct venus_inst *inst, u32 v4l2_fmt, if (!caps) return -EINVAL; - if (inst->bit_depth == VIDC_BITDEPTH_10 && - inst->session_type == VIDC_SESSION_TYPE_DEC) { - found_ubwc = - find_fmt_from_caps(caps, HFI_BUFFER_OUTPUT, - HFI_COLOR_FORMAT_YUV420_TP10_UBWC); - found = find_fmt_from_caps(caps, HFI_BUFFER_OUTPUT2, - HFI_COLOR_FORMAT_NV12); - if (found_ubwc && found) { - /* - * Hard-code DPB buffers to be 10bit UBWC and decoder - * output buffers in 8bit NV12 until V4L2 is able to - * expose compressed/tiled formats to applications. - */ - *out_fmt = HFI_COLOR_FORMAT_YUV420_TP10_UBWC; - *out2_fmt = HFI_COLOR_FORMAT_NV12; - return 0; - } - - return -EINVAL; - } - if (ubwc) { ubwc_fmt = fmt | HFI_COLOR_FORMAT_UBWC_BASE; found_ubwc = find_fmt_from_caps(caps, HFI_BUFFER_OUTPUT, @@ -1797,6 +1797,29 @@ int venus_helper_get_out_fmts(struct venus_inst *inst, u32 v4l2_fmt, } EXPORT_SYMBOL_GPL(venus_helper_get_out_fmts); +bool venus_helper_check_format(struct venus_inst *inst, u32 v4l2_pixfmt) +{ + struct venus_core *core = inst->core; + u32 fmt = to_hfi_raw_fmt(v4l2_pixfmt); + struct hfi_plat_caps *caps; + u32 buftype; + + if (!fmt) + return false; + + caps = venus_caps_by_codec(core, inst->hfi_codec, inst->session_type); + if (!caps) + return false; + + if (inst->session_type == VIDC_SESSION_TYPE_DEC) + buftype = HFI_BUFFER_OUTPUT2; + else + buftype = HFI_BUFFER_OUTPUT; + + return find_fmt_from_caps(caps, buftype, fmt); +} +EXPORT_SYMBOL_GPL(venus_helper_check_format); + int venus_helper_set_stride(struct venus_inst *inst, unsigned int width, unsigned int height) { diff --git a/drivers/media/platform/qcom/venus/helpers.h b/drivers/media/platform/qcom/venus/helpers.h index 32619c3e8c97..358e4f39c9c0 100644 --- a/drivers/media/platform/qcom/venus/helpers.h +++ b/drivers/media/platform/qcom/venus/helpers.h @@ -55,6 +55,7 @@ void venus_helper_init_instance(struct venus_inst *inst); int venus_helper_session_init(struct venus_inst *inst); int venus_helper_get_out_fmts(struct venus_inst *inst, u32 fmt, u32 *out_fmt, u32 *out2_fmt, bool ubwc); +bool venus_helper_check_format(struct venus_inst *inst, u32 v4l2_pixfmt); int venus_helper_alloc_dpb_bufs(struct venus_inst *inst); int venus_helper_free_dpb_bufs(struct venus_inst *inst); int venus_helper_intbufs_alloc(struct venus_inst *inst); diff --git a/drivers/media/platform/qcom/venus/hfi.c b/drivers/media/platform/qcom/venus/hfi.c index 4e2151fb47f0..1968f09ad177 100644 --- a/drivers/media/platform/qcom/venus/hfi.c +++ b/drivers/media/platform/qcom/venus/hfi.c @@ -104,6 +104,9 @@ int hfi_core_deinit(struct venus_core *core, bool blocking) mutex_lock(&core->lock); } + if (!core->ops) + goto unlock; + ret = core->ops->core_deinit(core); if (!ret) diff --git a/drivers/media/platform/qcom/venus/hfi_platform_v4.c b/drivers/media/platform/qcom/venus/hfi_platform_v4.c index 3f7f5277a50e..e3f0a90a567b 100644 --- a/drivers/media/platform/qcom/venus/hfi_platform_v4.c +++ b/drivers/media/platform/qcom/venus/hfi_platform_v4.c @@ -55,7 +55,7 @@ static const struct hfi_plat_caps caps[] = { .fmts[3] = {HFI_BUFFER_OUTPUT2, HFI_COLOR_FORMAT_NV12}, .fmts[4] = {HFI_BUFFER_OUTPUT2, HFI_COLOR_FORMAT_NV21}, .fmts[5] = {HFI_BUFFER_OUTPUT2, HFI_COLOR_FORMAT_P010}, - .fmts[6] = {HFI_BUFFER_OUTPUT2, HFI_COLOR_FORMAT_YUV420_TP10}, + .fmts[6] = {HFI_BUFFER_OUTPUT2, HFI_COLOR_FORMAT_YUV420_TP10_UBWC}, .num_fmts = 7, }, { .codec = HFI_VIDEO_CODEC_VP8, @@ -106,7 +106,7 @@ static const struct hfi_plat_caps caps[] = { .fmts[3] = {HFI_BUFFER_OUTPUT2, HFI_COLOR_FORMAT_NV12}, .fmts[4] = {HFI_BUFFER_OUTPUT2, HFI_COLOR_FORMAT_NV21}, .fmts[5] = {HFI_BUFFER_OUTPUT2, HFI_COLOR_FORMAT_P010}, - .fmts[6] = {HFI_BUFFER_OUTPUT2, HFI_COLOR_FORMAT_YUV420_TP10}, + .fmts[6] = {HFI_BUFFER_OUTPUT2, HFI_COLOR_FORMAT_YUV420_TP10_UBWC}, .num_fmts = 7, }, { .codec = HFI_VIDEO_CODEC_MPEG2, diff --git a/drivers/media/platform/qcom/venus/hfi_platform_v6.c b/drivers/media/platform/qcom/venus/hfi_platform_v6.c index c10618e44f5d..4e8af645f8b9 100644 --- a/drivers/media/platform/qcom/venus/hfi_platform_v6.c +++ b/drivers/media/platform/qcom/venus/hfi_platform_v6.c @@ -55,7 +55,7 @@ static const struct hfi_plat_caps caps[] = { .fmts[3] = {HFI_BUFFER_OUTPUT2, HFI_COLOR_FORMAT_NV12}, .fmts[4] = {HFI_BUFFER_OUTPUT2, HFI_COLOR_FORMAT_NV21}, .fmts[5] = {HFI_BUFFER_OUTPUT2, HFI_COLOR_FORMAT_P010}, - .fmts[6] = {HFI_BUFFER_OUTPUT2, HFI_COLOR_FORMAT_YUV420_TP10}, + .fmts[6] = {HFI_BUFFER_OUTPUT2, HFI_COLOR_FORMAT_YUV420_TP10_UBWC}, .num_fmts = 7, }, { .codec = HFI_VIDEO_CODEC_VP8, @@ -106,7 +106,7 @@ static const struct hfi_plat_caps caps[] = { .fmts[3] = {HFI_BUFFER_OUTPUT2, HFI_COLOR_FORMAT_NV12}, .fmts[4] = {HFI_BUFFER_OUTPUT2, HFI_COLOR_FORMAT_NV21}, .fmts[5] = {HFI_BUFFER_OUTPUT2, HFI_COLOR_FORMAT_P010}, - .fmts[6] = {HFI_BUFFER_OUTPUT2, HFI_COLOR_FORMAT_YUV420_TP10}, + .fmts[6] = {HFI_BUFFER_OUTPUT2, HFI_COLOR_FORMAT_YUV420_TP10_UBWC}, .num_fmts = 7, }, { .codec = HFI_VIDEO_CODEC_MPEG2, diff --git a/drivers/media/platform/qcom/venus/hfi_venus.c b/drivers/media/platform/qcom/venus/hfi_venus.c index 3a75a27632fb..9a34662fea38 100644 --- a/drivers/media/platform/qcom/venus/hfi_venus.c +++ b/drivers/media/platform/qcom/venus/hfi_venus.c @@ -1583,8 +1583,10 @@ static int venus_suspend_3xx(struct venus_core *core) */ ret = readx_poll_timeout(venus_cpu_and_video_core_idle, hdev, val, val, 1500, 100 * 1500); - if (ret) + if (ret) { + dev_err(dev, "wait for cpu and video core idle fail (%d)\n", ret); return ret; + } ret = venus_prepare_power_collapse(hdev, false); if (ret) { diff --git a/drivers/media/platform/qcom/venus/vdec.c b/drivers/media/platform/qcom/venus/vdec.c index 91da3f509724..ac0bb45d07f4 100644 --- a/drivers/media/platform/qcom/venus/vdec.c +++ b/drivers/media/platform/qcom/venus/vdec.c @@ -31,6 +31,14 @@ */ static const struct venus_format vdec_formats[] = { { + .pixfmt = V4L2_PIX_FMT_QC08C, + .num_planes = 1, + .type = V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE, + }, { + .pixfmt = V4L2_PIX_FMT_QC10C, + .num_planes = 1, + .type = V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE, + },{ .pixfmt = V4L2_PIX_FMT_NV12, .num_planes = 1, .type = V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE, @@ -106,6 +114,14 @@ find_format(struct venus_inst *inst, u32 pixfmt, u32 type) !venus_helper_check_codec(inst, fmt[i].pixfmt)) return NULL; + if (V4L2_TYPE_IS_CAPTURE(type) && + !venus_helper_check_format(inst, fmt[i].pixfmt)) + return NULL; + + if (V4L2_TYPE_IS_CAPTURE(type) && fmt[i].pixfmt == V4L2_PIX_FMT_QC10C && + !(inst->bit_depth == VIDC_BITDEPTH_10)) + return NULL; + return &fmt[i]; } @@ -124,8 +140,17 @@ find_format_by_index(struct venus_inst *inst, unsigned int index, u32 type) if (fmt[i].type != type) continue; - valid = type != V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE || - venus_helper_check_codec(inst, fmt[i].pixfmt); + + if (V4L2_TYPE_IS_OUTPUT(type)) { + valid = venus_helper_check_codec(inst, fmt[i].pixfmt); + } else if (V4L2_TYPE_IS_CAPTURE(type)) { + valid = venus_helper_check_format(inst, fmt[i].pixfmt); + + if (fmt[i].pixfmt == V4L2_PIX_FMT_QC10C && + !(inst->bit_depth == VIDC_BITDEPTH_10)) + valid = false; + } + if (k == index && valid) break; if (valid) @@ -676,8 +701,8 @@ static int vdec_output_conf(struct venus_inst *inst) struct venus_core *core = inst->core; struct hfi_enable en = { .enable = 1 }; struct hfi_buffer_requirements bufreq; - u32 width = inst->out_width; - u32 height = inst->out_height; + u32 width = inst->width; + u32 height = inst->height; u32 out_fmt, out2_fmt; bool ubwc = false; u32 ptype; @@ -1200,6 +1225,8 @@ static void vdec_stop_streaming(struct vb2_queue *q) struct venus_inst *inst = vb2_get_drv_priv(q); int ret = -EINVAL; + vdec_pm_get_put(inst); + mutex_lock(&inst->lock); if (q->type == V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE) @@ -1525,7 +1552,7 @@ static const struct hfi_inst_ops vdec_hfi_ops = { static void vdec_inst_init(struct venus_inst *inst) { inst->hfi_codec = HFI_VIDEO_CODEC_H264; - inst->fmt_out = &vdec_formats[6]; + inst->fmt_out = &vdec_formats[8]; inst->fmt_cap = &vdec_formats[0]; inst->width = frame_width_min(inst); inst->height = ALIGN(frame_height_min(inst), 32); diff --git a/drivers/media/platform/qcom/venus/venc.c b/drivers/media/platform/qcom/venus/venc.c index adea4c3b8c20..86918aea1d24 100644 --- a/drivers/media/platform/qcom/venus/venc.c +++ b/drivers/media/platform/qcom/venus/venc.c @@ -893,8 +893,12 @@ static int venc_set_properties(struct venus_inst *inst) mbs++; mbs /= ctr->intra_refresh_period; - intra_refresh.mode = HFI_INTRA_REFRESH_RANDOM; intra_refresh.cir_mbs = mbs; + if (ctr->intra_refresh_type == + V4L2_CID_MPEG_VIDEO_INTRA_REFRESH_PERIOD_TYPE_CYCLIC) + intra_refresh.mode = HFI_INTRA_REFRESH_CYCLIC; + else + intra_refresh.mode = HFI_INTRA_REFRESH_RANDOM; } ptype = HFI_PROPERTY_PARAM_VENC_INTRA_REFRESH; diff --git a/drivers/media/platform/qcom/venus/venc_ctrls.c b/drivers/media/platform/qcom/venus/venc_ctrls.c index ea5805e71c14..ed44e5800759 100644 --- a/drivers/media/platform/qcom/venus/venc_ctrls.c +++ b/drivers/media/platform/qcom/venus/venc_ctrls.c @@ -316,6 +316,9 @@ static int venc_op_s_ctrl(struct v4l2_ctrl *ctrl) case V4L2_CID_COLORIMETRY_HDR10_MASTERING_DISPLAY: ctr->mastering = *ctrl->p_new.p_hdr10_mastering; break; + case V4L2_CID_MPEG_VIDEO_INTRA_REFRESH_PERIOD_TYPE: + ctr->intra_refresh_type = ctrl->val; + break; case V4L2_CID_MPEG_VIDEO_INTRA_REFRESH_PERIOD: ctr->intra_refresh_period = ctrl->val; break; @@ -582,6 +585,11 @@ int venc_ctrl_init(struct venus_inst *inst) V4L2_CID_COLORIMETRY_HDR10_MASTERING_DISPLAY, v4l2_ctrl_ptr_create(NULL)); + v4l2_ctrl_new_std_menu(&inst->ctrl_handler, &venc_ctrl_ops, + V4L2_CID_MPEG_VIDEO_INTRA_REFRESH_PERIOD_TYPE, + V4L2_CID_MPEG_VIDEO_INTRA_REFRESH_PERIOD_TYPE_CYCLIC, + 0, V4L2_CID_MPEG_VIDEO_INTRA_REFRESH_PERIOD_TYPE_RANDOM); + v4l2_ctrl_new_std(&inst->ctrl_handler, &venc_ctrl_ops, V4L2_CID_MPEG_VIDEO_INTRA_REFRESH_PERIOD, 0, ((4096 * 2304) >> 8), 1, 0); diff --git a/drivers/media/platform/renesas/rcar-vin/rcar-core.c b/drivers/media/platform/renesas/rcar-vin/rcar-core.c index 64cb05b3907c..49bdcfba010b 100644 --- a/drivers/media/platform/renesas/rcar-vin/rcar-core.c +++ b/drivers/media/platform/renesas/rcar-vin/rcar-core.c @@ -94,8 +94,6 @@ static int rvin_group_init(struct rvin_group *group, struct rvin_dev *vin, strscpy(mdev->driver_name, KBUILD_MODNAME, sizeof(mdev->driver_name)); strscpy(mdev->model, match->compatible, sizeof(mdev->model)); - snprintf(mdev->bus_info, sizeof(mdev->bus_info), "platform:%s", - dev_name(mdev->dev)); media_device_init(mdev); @@ -891,7 +889,6 @@ static const struct media_device_ops rvin_csi2_media_ops = { static int rvin_csi2_create_link(struct rvin_group *group, unsigned int id, const struct rvin_group_route *route) - { struct media_entity *source = &group->remotes[route->csi].subdev->entity; struct media_entity *sink = &group->vin[id]->vdev.entity; diff --git a/drivers/media/platform/renesas/rcar-vin/rcar-dma.c b/drivers/media/platform/renesas/rcar-vin/rcar-dma.c index 2272f1c96aaf..6644b498929d 100644 --- a/drivers/media/platform/renesas/rcar-vin/rcar-dma.c +++ b/drivers/media/platform/renesas/rcar-vin/rcar-dma.c @@ -77,6 +77,7 @@ /* Register bit fields for R-Car VIN */ /* Video n Main Control Register bits */ +#define VNMC_INF_MASK (7 << 16) #define VNMC_DPINE (1 << 27) /* Gen3 specific */ #define VNMC_SCLE (1 << 26) /* Gen3 specific */ #define VNMC_FOC (1 << 21) @@ -88,6 +89,7 @@ #define VNMC_INF_RAW8 (4 << 16) #define VNMC_INF_YUV16 (5 << 16) #define VNMC_INF_RGB888 (6 << 16) +#define VNMC_INF_RGB666 (7 << 16) #define VNMC_VUP (1 << 10) #define VNMC_IM_ODD (0 << 3) #define VNMC_IM_ODD_EVEN (1 << 3) @@ -707,6 +709,29 @@ static int rvin_setup(struct rvin_dev *vin) break; } + /* Make sure input interface and input format is valid. */ + if (vin->info->model == RCAR_GEN3) { + switch (vnmc & VNMC_INF_MASK) { + case VNMC_INF_YUV8_BT656: + case VNMC_INF_YUV10_BT656: + case VNMC_INF_YUV16: + case VNMC_INF_RGB666: + if (vin->is_csi) { + vin_err(vin, "Invalid setting in MIPI CSI2\n"); + return -EINVAL; + } + break; + case VNMC_INF_RAW8: + if (!vin->is_csi) { + vin_err(vin, "Invalid setting in Digital Pins\n"); + return -EINVAL; + } + break; + default: + break; + } + } + /* Enable VSYNC Field Toggle mode after one VSYNC input */ if (vin->info->model == RCAR_GEN3) dmr2 = VNDMR2_FTEV; diff --git a/drivers/media/platform/renesas/rcar-vin/rcar-v4l2.c b/drivers/media/platform/renesas/rcar-vin/rcar-v4l2.c index 2e60b9fce03b..2e2aa9d746ee 100644 --- a/drivers/media/platform/renesas/rcar-vin/rcar-v4l2.c +++ b/drivers/media/platform/renesas/rcar-vin/rcar-v4l2.c @@ -255,6 +255,7 @@ static int rvin_try_format(struct rvin_dev *vin, u32 which, { struct v4l2_subdev *sd = vin_to_source(vin); struct v4l2_subdev_state *sd_state; + static struct lock_class_key key; struct v4l2_subdev_format format = { .which = which, .pad = vin->parallel.source_pad, @@ -263,7 +264,11 @@ static int rvin_try_format(struct rvin_dev *vin, u32 which, u32 width, height; int ret; - sd_state = v4l2_subdev_alloc_state(sd); + /* + * FIXME: Drop this call, drivers are not supposed to use + * __v4l2_subdev_state_alloc(). + */ + sd_state = __v4l2_subdev_state_alloc(sd, "rvin:state->lock", &key); if (IS_ERR(sd_state)) return PTR_ERR(sd_state); @@ -299,7 +304,7 @@ static int rvin_try_format(struct rvin_dev *vin, u32 which, rvin_format_align(vin, pix); done: - v4l2_subdev_free_state(sd_state); + __v4l2_subdev_state_free(sd_state); return ret; } @@ -307,12 +312,8 @@ done: static int rvin_querycap(struct file *file, void *priv, struct v4l2_capability *cap) { - struct rvin_dev *vin = video_drvdata(file); - strscpy(cap->driver, KBUILD_MODNAME, sizeof(cap->driver)); strscpy(cap->card, "R_Car_VIN", sizeof(cap->card)); - snprintf(cap->bus_info, sizeof(cap->bus_info), "platform:%s", - dev_name(vin->dev)); return 0; } diff --git a/drivers/media/platform/renesas/rcar_jpu.c b/drivers/media/platform/renesas/rcar_jpu.c index 293beba131e2..2f4377cfbb42 100644 --- a/drivers/media/platform/renesas/rcar_jpu.c +++ b/drivers/media/platform/renesas/rcar_jpu.c @@ -670,8 +670,6 @@ static int jpu_querycap(struct file *file, void *priv, strscpy(cap->card, DRV_NAME " decoder", sizeof(cap->card)); strscpy(cap->driver, DRV_NAME, sizeof(cap->driver)); - snprintf(cap->bus_info, sizeof(cap->bus_info), "platform:%s", - dev_name(ctx->jpu->dev)); memset(cap->reserved, 0, sizeof(cap->reserved)); return 0; diff --git a/drivers/media/platform/renesas/renesas-ceu.c b/drivers/media/platform/renesas/renesas-ceu.c index 2e8dbacc414e..f70f91b006b7 100644 --- a/drivers/media/platform/renesas/renesas-ceu.c +++ b/drivers/media/platform/renesas/renesas-ceu.c @@ -1606,15 +1606,15 @@ struct ceu_data { u32 irq_mask; }; -static const struct ceu_data ceu_data_rz = { - .irq_mask = CEU_CETCR_ALL_IRQS_RZ, -}; - static const struct ceu_data ceu_data_sh4 = { .irq_mask = CEU_CETCR_ALL_IRQS_SH4, }; #if IS_ENABLED(CONFIG_OF) +static const struct ceu_data ceu_data_rz = { + .irq_mask = CEU_CETCR_ALL_IRQS_RZ, +}; + static const struct of_device_id ceu_of_match[] = { { .compatible = "renesas,r7s72100-ceu", .data = &ceu_data_rz }, { .compatible = "renesas,r8a7740-ceu", .data = &ceu_data_rz }, diff --git a/drivers/media/platform/renesas/vsp1/vsp1_drv.c b/drivers/media/platform/renesas/vsp1/vsp1_drv.c index 502c7d9d6890..1f73c48eb738 100644 --- a/drivers/media/platform/renesas/vsp1/vsp1_drv.c +++ b/drivers/media/platform/renesas/vsp1/vsp1_drv.c @@ -243,8 +243,6 @@ static int vsp1_create_entities(struct vsp1_device *vsp1) mdev->dev = vsp1->dev; mdev->hw_revision = vsp1->version; strscpy(mdev->model, vsp1->info->model, sizeof(mdev->model)); - snprintf(mdev->bus_info, sizeof(mdev->bus_info), "platform:%s", - dev_name(mdev->dev)); media_device_init(mdev); vsp1->media_ops.link_setup = vsp1_entity_link_setup; diff --git a/drivers/media/platform/renesas/vsp1/vsp1_entity.c b/drivers/media/platform/renesas/vsp1/vsp1_entity.c index 823c15facd1b..a116a3362f9e 100644 --- a/drivers/media/platform/renesas/vsp1/vsp1_entity.c +++ b/drivers/media/platform/renesas/vsp1/vsp1_entity.c @@ -613,6 +613,7 @@ int vsp1_entity_init(struct vsp1_device *vsp1, struct vsp1_entity *entity, const char *name, unsigned int num_pads, const struct v4l2_subdev_ops *ops, u32 function) { + static struct lock_class_key key; struct v4l2_subdev *subdev; unsigned int i; int ret; @@ -675,7 +676,12 @@ int vsp1_entity_init(struct vsp1_device *vsp1, struct vsp1_entity *entity, * Allocate the pad configuration to store formats and selection * rectangles. */ - entity->config = v4l2_subdev_alloc_state(&entity->subdev); + /* + * FIXME: Drop this call, drivers are not supposed to use + * __v4l2_subdev_state_alloc(). + */ + entity->config = __v4l2_subdev_state_alloc(&entity->subdev, + "vsp1:config->lock", &key); if (IS_ERR(entity->config)) { media_entity_cleanup(&entity->subdev.entity); return PTR_ERR(entity->config); @@ -690,6 +696,6 @@ void vsp1_entity_destroy(struct vsp1_entity *entity) entity->ops->destroy(entity); if (entity->subdev.ctrl_handler) v4l2_ctrl_handler_free(entity->subdev.ctrl_handler); - v4l2_subdev_free_state(entity->config); + __v4l2_subdev_state_free(entity->config); media_entity_cleanup(&entity->subdev.entity); } diff --git a/drivers/media/platform/renesas/vsp1/vsp1_histo.c b/drivers/media/platform/renesas/vsp1/vsp1_histo.c index 5e5013d2cd2a..f22449dd654c 100644 --- a/drivers/media/platform/renesas/vsp1/vsp1_histo.c +++ b/drivers/media/platform/renesas/vsp1/vsp1_histo.c @@ -434,8 +434,6 @@ static int histo_v4l2_querycap(struct file *file, void *fh, strscpy(cap->driver, "vsp1", sizeof(cap->driver)); strscpy(cap->card, histo->video.name, sizeof(cap->card)); - snprintf(cap->bus_info, sizeof(cap->bus_info), "platform:%s", - dev_name(histo->entity.vsp1->dev)); return 0; } diff --git a/drivers/media/platform/renesas/vsp1/vsp1_rpf.c b/drivers/media/platform/renesas/vsp1/vsp1_rpf.c index 85587c1b6a37..75083cb234fe 100644 --- a/drivers/media/platform/renesas/vsp1/vsp1_rpf.c +++ b/drivers/media/platform/renesas/vsp1/vsp1_rpf.c @@ -291,11 +291,11 @@ static void rpf_configure_partition(struct vsp1_entity *entity, + crop.left * fmtinfo->bpp[0] / 8; if (format->num_planes > 1) { + unsigned int bpl = format->plane_fmt[1].bytesperline; unsigned int offset; - offset = crop.top * format->plane_fmt[1].bytesperline - + crop.left / fmtinfo->hsub - * fmtinfo->bpp[1] / 8; + offset = crop.top / fmtinfo->vsub * bpl + + crop.left / fmtinfo->hsub * fmtinfo->bpp[1] / 8; mem.addr[1] += offset; mem.addr[2] += offset; } diff --git a/drivers/media/platform/renesas/vsp1/vsp1_video.c b/drivers/media/platform/renesas/vsp1/vsp1_video.c index 044eb5778820..51219b1b6ea9 100644 --- a/drivers/media/platform/renesas/vsp1/vsp1_video.c +++ b/drivers/media/platform/renesas/vsp1/vsp1_video.c @@ -959,8 +959,6 @@ vsp1_video_querycap(struct file *file, void *fh, struct v4l2_capability *cap) strscpy(cap->driver, "vsp1", sizeof(cap->driver)); strscpy(cap->card, video->video.name, sizeof(cap->card)); - snprintf(cap->bus_info, sizeof(cap->bus_info), "platform:%s", - dev_name(video->vsp1->dev)); return 0; } @@ -1032,7 +1030,7 @@ vsp1_video_streamon(struct file *file, void *fh, enum v4l2_buf_type type) struct vsp1_pipeline *pipe; int ret; - if (video->queue.owner && video->queue.owner != file->private_data) + if (vb2_queue_is_busy(&video->queue, file)) return -EBUSY; /* @@ -1129,21 +1127,11 @@ static int vsp1_video_open(struct file *file) static int vsp1_video_release(struct file *file) { struct vsp1_video *video = video_drvdata(file); - struct v4l2_fh *vfh = file->private_data; - mutex_lock(&video->lock); - if (video->queue.owner == vfh) { - vb2_queue_release(&video->queue); - video->queue.owner = NULL; - } - mutex_unlock(&video->lock); + vb2_fop_release(file); vsp1_device_put(video->vsp1); - v4l2_fh_release(file); - - file->private_data = NULL; - return 0; } diff --git a/drivers/media/platform/rockchip/rga/rga.c b/drivers/media/platform/rockchip/rga/rga.c index 4de5e8d2b261..2f8df74ad0fd 100644 --- a/drivers/media/platform/rockchip/rga/rga.c +++ b/drivers/media/platform/rockchip/rga/rga.c @@ -865,7 +865,7 @@ static int rga_probe(struct platform_device *pdev) ret = pm_runtime_resume_and_get(rga->dev); if (ret < 0) - goto rel_vdev; + goto rel_m2m; rga->version.major = (rga_read(rga, RGA_VERSION_INFO) >> 24) & 0xFF; rga->version.minor = (rga_read(rga, RGA_VERSION_INFO) >> 20) & 0x0F; @@ -881,7 +881,7 @@ static int rga_probe(struct platform_device *pdev) DMA_ATTR_WRITE_COMBINE); if (!rga->cmdbuf_virt) { ret = -ENOMEM; - goto rel_vdev; + goto rel_m2m; } rga->src_mmu_pages = @@ -892,7 +892,7 @@ static int rga_probe(struct platform_device *pdev) } rga->dst_mmu_pages = (unsigned int *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, 3); - if (rga->dst_mmu_pages) { + if (!rga->dst_mmu_pages) { ret = -ENOMEM; goto free_src_pages; } @@ -918,6 +918,8 @@ free_src_pages: free_dma: dma_free_attrs(rga->dev, RGA_CMDBUF_SIZE, rga->cmdbuf_virt, rga->cmdbuf_phy, DMA_ATTR_WRITE_COMBINE); +rel_m2m: + v4l2_m2m_release(rga->m2m_dev); rel_vdev: video_device_release(vfd); unreg_v4l2_dev: diff --git a/drivers/media/platform/rockchip/rkisp1/rkisp1-isp.c b/drivers/media/platform/rockchip/rkisp1/rkisp1-isp.c index 2a35bf24e54e..4415c7248c2f 100644 --- a/drivers/media/platform/rockchip/rkisp1/rkisp1-isp.c +++ b/drivers/media/platform/rockchip/rkisp1/rkisp1-isp.c @@ -14,6 +14,8 @@ #include <linux/pm_runtime.h> #include <linux/videodev2.h> #include <linux/vmalloc.h> + +#include <media/mipi-csi2.h> #include <media/v4l2-event.h> #include "rkisp1-common.h" @@ -62,112 +64,112 @@ static const struct rkisp1_isp_mbus_info rkisp1_isp_formats[] = { }, { .mbus_code = MEDIA_BUS_FMT_SRGGB10_1X10, .pixel_enc = V4L2_PIXEL_ENC_BAYER, - .mipi_dt = RKISP1_CIF_CSI2_DT_RAW10, + .mipi_dt = MIPI_CSI2_DT_RAW10, .bayer_pat = RKISP1_RAW_RGGB, .bus_width = 10, .direction = RKISP1_ISP_SD_SINK | RKISP1_ISP_SD_SRC, }, { .mbus_code = MEDIA_BUS_FMT_SBGGR10_1X10, .pixel_enc = V4L2_PIXEL_ENC_BAYER, - .mipi_dt = RKISP1_CIF_CSI2_DT_RAW10, + .mipi_dt = MIPI_CSI2_DT_RAW10, .bayer_pat = RKISP1_RAW_BGGR, .bus_width = 10, .direction = RKISP1_ISP_SD_SINK | RKISP1_ISP_SD_SRC, }, { .mbus_code = MEDIA_BUS_FMT_SGBRG10_1X10, .pixel_enc = V4L2_PIXEL_ENC_BAYER, - .mipi_dt = RKISP1_CIF_CSI2_DT_RAW10, + .mipi_dt = MIPI_CSI2_DT_RAW10, .bayer_pat = RKISP1_RAW_GBRG, .bus_width = 10, .direction = RKISP1_ISP_SD_SINK | RKISP1_ISP_SD_SRC, }, { .mbus_code = MEDIA_BUS_FMT_SGRBG10_1X10, .pixel_enc = V4L2_PIXEL_ENC_BAYER, - .mipi_dt = RKISP1_CIF_CSI2_DT_RAW10, + .mipi_dt = MIPI_CSI2_DT_RAW10, .bayer_pat = RKISP1_RAW_GRBG, .bus_width = 10, .direction = RKISP1_ISP_SD_SINK | RKISP1_ISP_SD_SRC, }, { .mbus_code = MEDIA_BUS_FMT_SRGGB12_1X12, .pixel_enc = V4L2_PIXEL_ENC_BAYER, - .mipi_dt = RKISP1_CIF_CSI2_DT_RAW12, + .mipi_dt = MIPI_CSI2_DT_RAW12, .bayer_pat = RKISP1_RAW_RGGB, .bus_width = 12, .direction = RKISP1_ISP_SD_SINK | RKISP1_ISP_SD_SRC, }, { .mbus_code = MEDIA_BUS_FMT_SBGGR12_1X12, .pixel_enc = V4L2_PIXEL_ENC_BAYER, - .mipi_dt = RKISP1_CIF_CSI2_DT_RAW12, + .mipi_dt = MIPI_CSI2_DT_RAW12, .bayer_pat = RKISP1_RAW_BGGR, .bus_width = 12, .direction = RKISP1_ISP_SD_SINK | RKISP1_ISP_SD_SRC, }, { .mbus_code = MEDIA_BUS_FMT_SGBRG12_1X12, .pixel_enc = V4L2_PIXEL_ENC_BAYER, - .mipi_dt = RKISP1_CIF_CSI2_DT_RAW12, + .mipi_dt = MIPI_CSI2_DT_RAW12, .bayer_pat = RKISP1_RAW_GBRG, .bus_width = 12, .direction = RKISP1_ISP_SD_SINK | RKISP1_ISP_SD_SRC, }, { .mbus_code = MEDIA_BUS_FMT_SGRBG12_1X12, .pixel_enc = V4L2_PIXEL_ENC_BAYER, - .mipi_dt = RKISP1_CIF_CSI2_DT_RAW12, + .mipi_dt = MIPI_CSI2_DT_RAW12, .bayer_pat = RKISP1_RAW_GRBG, .bus_width = 12, .direction = RKISP1_ISP_SD_SINK | RKISP1_ISP_SD_SRC, }, { .mbus_code = MEDIA_BUS_FMT_SRGGB8_1X8, .pixel_enc = V4L2_PIXEL_ENC_BAYER, - .mipi_dt = RKISP1_CIF_CSI2_DT_RAW8, + .mipi_dt = MIPI_CSI2_DT_RAW8, .bayer_pat = RKISP1_RAW_RGGB, .bus_width = 8, .direction = RKISP1_ISP_SD_SINK | RKISP1_ISP_SD_SRC, }, { .mbus_code = MEDIA_BUS_FMT_SBGGR8_1X8, .pixel_enc = V4L2_PIXEL_ENC_BAYER, - .mipi_dt = RKISP1_CIF_CSI2_DT_RAW8, + .mipi_dt = MIPI_CSI2_DT_RAW8, .bayer_pat = RKISP1_RAW_BGGR, .bus_width = 8, .direction = RKISP1_ISP_SD_SINK | RKISP1_ISP_SD_SRC, }, { .mbus_code = MEDIA_BUS_FMT_SGBRG8_1X8, .pixel_enc = V4L2_PIXEL_ENC_BAYER, - .mipi_dt = RKISP1_CIF_CSI2_DT_RAW8, + .mipi_dt = MIPI_CSI2_DT_RAW8, .bayer_pat = RKISP1_RAW_GBRG, .bus_width = 8, .direction = RKISP1_ISP_SD_SINK | RKISP1_ISP_SD_SRC, }, { .mbus_code = MEDIA_BUS_FMT_SGRBG8_1X8, .pixel_enc = V4L2_PIXEL_ENC_BAYER, - .mipi_dt = RKISP1_CIF_CSI2_DT_RAW8, + .mipi_dt = MIPI_CSI2_DT_RAW8, .bayer_pat = RKISP1_RAW_GRBG, .bus_width = 8, .direction = RKISP1_ISP_SD_SINK | RKISP1_ISP_SD_SRC, }, { .mbus_code = MEDIA_BUS_FMT_YUYV8_1X16, .pixel_enc = V4L2_PIXEL_ENC_YUV, - .mipi_dt = RKISP1_CIF_CSI2_DT_YUV422_8b, + .mipi_dt = MIPI_CSI2_DT_YUV422_8B, .yuv_seq = RKISP1_CIF_ISP_ACQ_PROP_YCBYCR, .bus_width = 16, .direction = RKISP1_ISP_SD_SINK, }, { .mbus_code = MEDIA_BUS_FMT_YVYU8_1X16, .pixel_enc = V4L2_PIXEL_ENC_YUV, - .mipi_dt = RKISP1_CIF_CSI2_DT_YUV422_8b, + .mipi_dt = MIPI_CSI2_DT_YUV422_8B, .yuv_seq = RKISP1_CIF_ISP_ACQ_PROP_YCRYCB, .bus_width = 16, .direction = RKISP1_ISP_SD_SINK, }, { .mbus_code = MEDIA_BUS_FMT_UYVY8_1X16, .pixel_enc = V4L2_PIXEL_ENC_YUV, - .mipi_dt = RKISP1_CIF_CSI2_DT_YUV422_8b, + .mipi_dt = MIPI_CSI2_DT_YUV422_8B, .yuv_seq = RKISP1_CIF_ISP_ACQ_PROP_CBYCRY, .bus_width = 16, .direction = RKISP1_ISP_SD_SINK, }, { .mbus_code = MEDIA_BUS_FMT_VYUY8_1X16, .pixel_enc = V4L2_PIXEL_ENC_YUV, - .mipi_dt = RKISP1_CIF_CSI2_DT_YUV422_8b, + .mipi_dt = MIPI_CSI2_DT_YUV422_8B, .yuv_seq = RKISP1_CIF_ISP_ACQ_PROP_CRYCBY, .bus_width = 16, .direction = RKISP1_ISP_SD_SINK, diff --git a/drivers/media/platform/rockchip/rkisp1/rkisp1-regs.h b/drivers/media/platform/rockchip/rkisp1/rkisp1-regs.h index d326214c7e07..82f8d33d98b3 100644 --- a/drivers/media/platform/rockchip/rkisp1/rkisp1-regs.h +++ b/drivers/media/platform/rockchip/rkisp1/rkisp1-regs.h @@ -333,17 +333,6 @@ /* MIPI_DATA_SEL */ #define RKISP1_CIF_MIPI_DATA_SEL_VC(a) (((a) & 0x3) << 6) #define RKISP1_CIF_MIPI_DATA_SEL_DT(a) (((a) & 0x3F) << 0) -/* MIPI DATA_TYPE */ -#define RKISP1_CIF_CSI2_DT_YUV420_8b 0x18 -#define RKISP1_CIF_CSI2_DT_YUV420_10b 0x19 -#define RKISP1_CIF_CSI2_DT_YUV422_8b 0x1E -#define RKISP1_CIF_CSI2_DT_YUV422_10b 0x1F -#define RKISP1_CIF_CSI2_DT_RGB565 0x22 -#define RKISP1_CIF_CSI2_DT_RGB666 0x23 -#define RKISP1_CIF_CSI2_DT_RGB888 0x24 -#define RKISP1_CIF_CSI2_DT_RAW8 0x2A -#define RKISP1_CIF_CSI2_DT_RAW10 0x2B -#define RKISP1_CIF_CSI2_DT_RAW12 0x2C /* MIPI_IMSC, MIPI_RIS, MIPI_MIS, MIPI_ICR, MIPI_ISR */ #define RKISP1_CIF_MIPI_SYNC_FIFO_OVFLW(a) (((a) & 0xF) << 0) diff --git a/drivers/media/platform/samsung/exynos-gsc/gsc-m2m.c b/drivers/media/platform/samsung/exynos-gsc/gsc-m2m.c index f1cf847d1cc2..b7854ce5fb8e 100644 --- a/drivers/media/platform/samsung/exynos-gsc/gsc-m2m.c +++ b/drivers/media/platform/samsung/exynos-gsc/gsc-m2m.c @@ -285,13 +285,8 @@ static const struct vb2_ops gsc_m2m_qops = { static int gsc_m2m_querycap(struct file *file, void *fh, struct v4l2_capability *cap) { - struct gsc_ctx *ctx = fh_to_ctx(fh); - struct gsc_dev *gsc = ctx->gsc_dev; - strscpy(cap->driver, GSC_MODULE_NAME, sizeof(cap->driver)); strscpy(cap->card, GSC_MODULE_NAME " gscaler", sizeof(cap->card)); - snprintf(cap->bus_info, sizeof(cap->bus_info), "platform:%s", - dev_name(&gsc->pdev->dev)); return 0; } diff --git a/drivers/media/platform/samsung/exynos4-is/common.c b/drivers/media/platform/samsung/exynos4-is/common.c index 023f624d29d5..26ee2388edfd 100644 --- a/drivers/media/platform/samsung/exynos4-is/common.c +++ b/drivers/media/platform/samsung/exynos4-is/common.c @@ -41,8 +41,6 @@ void __fimc_vidioc_querycap(struct device *dev, struct v4l2_capability *cap) { strscpy(cap->driver, dev->driver->name, sizeof(cap->driver)); strscpy(cap->card, dev->driver->name, sizeof(cap->card)); - snprintf(cap->bus_info, sizeof(cap->bus_info), - "platform:%s", dev_name(dev)); } EXPORT_SYMBOL(__fimc_vidioc_querycap); diff --git a/drivers/media/platform/samsung/exynos4-is/fimc-is.c b/drivers/media/platform/samsung/exynos4-is/fimc-is.c index e55e411038f4..e3072d69c49f 100644 --- a/drivers/media/platform/samsung/exynos4-is/fimc-is.c +++ b/drivers/media/platform/samsung/exynos4-is/fimc-is.c @@ -140,7 +140,7 @@ static int fimc_is_enable_clocks(struct fimc_is *is) dev_err(&is->pdev->dev, "clock %s enable failed\n", fimc_is_clocks[i]); for (--i; i >= 0; i--) - clk_disable(is->clocks[i]); + clk_disable_unprepare(is->clocks[i]); return ret; } pr_debug("enabled clock: %s\n", fimc_is_clocks[i]); @@ -830,7 +830,7 @@ static int fimc_is_probe(struct platform_device *pdev) ret = pm_runtime_resume_and_get(dev); if (ret < 0) - goto err_irq; + goto err_pm_disable; vb2_dma_contig_set_max_seg_size(dev, DMA_BIT_MASK(32)); @@ -864,6 +864,8 @@ err_pm: pm_runtime_put_noidle(dev); if (!pm_runtime_enabled(dev)) fimc_is_runtime_suspend(dev); +err_pm_disable: + pm_runtime_disable(dev); err_irq: free_irq(is->irq, is); err_clk: diff --git a/drivers/media/platform/samsung/exynos4-is/fimc-isp-video.h b/drivers/media/platform/samsung/exynos4-is/fimc-isp-video.h index edcb3a5e3cb9..2dd4ddbc748a 100644 --- a/drivers/media/platform/samsung/exynos4-is/fimc-isp-video.h +++ b/drivers/media/platform/samsung/exynos4-is/fimc-isp-video.h @@ -32,7 +32,7 @@ static inline int fimc_isp_video_device_register(struct fimc_isp *isp, return 0; } -void fimc_isp_video_device_unregister(struct fimc_isp *isp, +static inline void fimc_isp_video_device_unregister(struct fimc_isp *isp, enum v4l2_buf_type type) { } diff --git a/drivers/media/platform/samsung/exynos4-is/fimc-lite.c b/drivers/media/platform/samsung/exynos4-is/fimc-lite.c index 2e8f476efc5c..1a396b7cd9a9 100644 --- a/drivers/media/platform/samsung/exynos4-is/fimc-lite.c +++ b/drivers/media/platform/samsung/exynos4-is/fimc-lite.c @@ -646,12 +646,8 @@ static void fimc_lite_try_compose(struct fimc_lite *fimc, struct v4l2_rect *r) static int fimc_lite_querycap(struct file *file, void *priv, struct v4l2_capability *cap) { - struct fimc_lite *fimc = video_drvdata(file); - strscpy(cap->driver, FIMC_LITE_DRV_NAME, sizeof(cap->driver)); strscpy(cap->card, FIMC_LITE_DRV_NAME, sizeof(cap->card)); - snprintf(cap->bus_info, sizeof(cap->bus_info), "platform:%s", - dev_name(&fimc->pdev->dev)); return 0; } diff --git a/drivers/media/platform/samsung/s5p-jpeg/jpeg-core.c b/drivers/media/platform/samsung/s5p-jpeg/jpeg-core.c index 5479bc8d474d..456287186ad8 100644 --- a/drivers/media/platform/samsung/s5p-jpeg/jpeg-core.c +++ b/drivers/media/platform/samsung/s5p-jpeg/jpeg-core.c @@ -1257,8 +1257,6 @@ static int s5p_jpeg_querycap(struct file *file, void *priv, strscpy(cap->card, S5P_JPEG_M2M_NAME " decoder", sizeof(cap->card)); } - snprintf(cap->bus_info, sizeof(cap->bus_info), "platform:%s", - dev_name(ctx->jpeg->dev)); return 0; } diff --git a/drivers/media/platform/samsung/s5p-jpeg/jpeg-hw-s5p.c b/drivers/media/platform/samsung/s5p-jpeg/jpeg-hw-s5p.c index 01b47b3df1e7..33e6e85dfd78 100644 --- a/drivers/media/platform/samsung/s5p-jpeg/jpeg-hw-s5p.c +++ b/drivers/media/platform/samsung/s5p-jpeg/jpeg-hw-s5p.c @@ -52,7 +52,6 @@ void s5p_jpeg_proc_mode(void __iomem *regs, unsigned long mode) { unsigned long reg, m; - m = S5P_PROC_MODE_DECOMPR; if (mode == S5P_JPEG_ENCODE) m = S5P_PROC_MODE_COMPR; else diff --git a/drivers/media/platform/samsung/s5p-mfc/s5p_mfc_dec.c b/drivers/media/platform/samsung/s5p-mfc/s5p_mfc_dec.c index 4b89df8bfd18..268ffe4da53c 100644 --- a/drivers/media/platform/samsung/s5p-mfc/s5p_mfc_dec.c +++ b/drivers/media/platform/samsung/s5p-mfc/s5p_mfc_dec.c @@ -288,8 +288,6 @@ static int vidioc_querycap(struct file *file, void *priv, strscpy(cap->driver, S5P_MFC_NAME, sizeof(cap->driver)); strscpy(cap->card, dev->vfd_dec->name, sizeof(cap->card)); - snprintf(cap->bus_info, sizeof(cap->bus_info), "platform:%s", - dev_name(&dev->plat_dev->dev)); return 0; } diff --git a/drivers/media/platform/samsung/s5p-mfc/s5p_mfc_enc.c b/drivers/media/platform/samsung/s5p-mfc/s5p_mfc_enc.c index a8877d805b29..b65e506665af 100644 --- a/drivers/media/platform/samsung/s5p-mfc/s5p_mfc_enc.c +++ b/drivers/media/platform/samsung/s5p-mfc/s5p_mfc_enc.c @@ -1309,8 +1309,6 @@ static int vidioc_querycap(struct file *file, void *priv, strscpy(cap->driver, S5P_MFC_NAME, sizeof(cap->driver)); strscpy(cap->card, dev->vfd_enc->name, sizeof(cap->card)); - snprintf(cap->bus_info, sizeof(cap->bus_info), "platform:%s", - dev_name(&dev->plat_dev->dev)); return 0; } diff --git a/drivers/media/platform/st/sti/bdisp/bdisp-v4l2.c b/drivers/media/platform/st/sti/bdisp/bdisp-v4l2.c index 5aa79d9277c8..dd74cc43920d 100644 --- a/drivers/media/platform/st/sti/bdisp/bdisp-v4l2.c +++ b/drivers/media/platform/st/sti/bdisp/bdisp-v4l2.c @@ -1394,8 +1394,7 @@ err_remove: bdisp_debugfs_remove(bdisp); v4l2_device_unregister(&bdisp->v4l2_dev); err_clk: - if (!IS_ERR(bdisp->clock)) - clk_unprepare(bdisp->clock); + clk_unprepare(bdisp->clock); err_wq: destroy_workqueue(bdisp->work_queue); return ret; diff --git a/drivers/media/platform/st/sti/c8sectpfe/c8sectpfe-common.h b/drivers/media/platform/st/sti/c8sectpfe/c8sectpfe-common.h index 5ab7ca448cf9..f8d97841f366 100644 --- a/drivers/media/platform/st/sti/c8sectpfe/c8sectpfe-common.h +++ b/drivers/media/platform/st/sti/c8sectpfe/c8sectpfe-common.h @@ -13,7 +13,6 @@ #include <linux/dvb/dmx.h> #include <linux/dvb/frontend.h> #include <linux/gpio.h> -#include <linux/version.h> #include <media/dmxdev.h> #include <media/dvb_demux.h> diff --git a/drivers/media/platform/st/sti/delta/delta-v4l2.c b/drivers/media/platform/st/sti/delta/delta-v4l2.c index c887a31ebb54..420ad4d8df5d 100644 --- a/drivers/media/platform/st/sti/delta/delta-v4l2.c +++ b/drivers/media/platform/st/sti/delta/delta-v4l2.c @@ -1859,7 +1859,7 @@ static int delta_probe(struct platform_device *pdev) if (ret) { dev_err(delta->dev, "%s failed to initialize firmware ipc channel\n", DELTA_PREFIX); - goto err; + goto err_pm_disable; } /* register all available decoders */ @@ -1873,7 +1873,7 @@ static int delta_probe(struct platform_device *pdev) if (ret) { dev_err(delta->dev, "%s failed to register V4L2 device\n", DELTA_PREFIX); - goto err; + goto err_pm_disable; } delta->work_queue = create_workqueue(DELTA_NAME); @@ -1898,6 +1898,8 @@ err_work_queue: destroy_workqueue(delta->work_queue); err_v4l2: v4l2_device_unregister(&delta->v4l2_dev); +err_pm_disable: + pm_runtime_disable(dev); err: return ret; } diff --git a/drivers/media/platform/st/stm32/stm32-dcmi.c b/drivers/media/platform/st/stm32/stm32-dcmi.c index c4c65d852525..09a743cd7004 100644 --- a/drivers/media/platform/st/stm32/stm32-dcmi.c +++ b/drivers/media/platform/st/stm32/stm32-dcmi.c @@ -1997,8 +1997,6 @@ static int dcmi_probe(struct platform_device *pdev) /* Initialize media device */ strscpy(dcmi->mdev.model, DRV_NAME, sizeof(dcmi->mdev.model)); - snprintf(dcmi->mdev.bus_info, sizeof(dcmi->mdev.bus_info), - "platform:%s", DRV_NAME); dcmi->mdev.dev = &pdev->dev; media_device_init(&dcmi->mdev); diff --git a/drivers/media/platform/sunxi/sun4i-csi/sun4i_csi.c b/drivers/media/platform/sunxi/sun4i-csi/sun4i_csi.c index 80a10f238bbe..18e6c65f4737 100644 --- a/drivers/media/platform/sunxi/sun4i-csi/sun4i_csi.c +++ b/drivers/media/platform/sunxi/sun4i-csi/sun4i_csi.c @@ -173,8 +173,6 @@ static int sun4i_csi_probe(struct platform_device *pdev) strscpy(csi->mdev.model, "Allwinner Video Capture Device", sizeof(csi->mdev.model)); csi->mdev.hw_revision = 0; - snprintf(csi->mdev.bus_info, sizeof(csi->mdev.bus_info), "platform:%s", - dev_name(csi->dev)); media_device_init(&csi->mdev); csi->v4l.mdev = &csi->mdev; diff --git a/drivers/media/platform/sunxi/sun4i-csi/sun4i_v4l2.c b/drivers/media/platform/sunxi/sun4i-csi/sun4i_v4l2.c index 3872027ed2fa..48702134ccc5 100644 --- a/drivers/media/platform/sunxi/sun4i-csi/sun4i_v4l2.c +++ b/drivers/media/platform/sunxi/sun4i-csi/sun4i_v4l2.c @@ -53,12 +53,8 @@ const struct sun4i_csi_format *sun4i_csi_find_format(const u32 *fourcc, static int sun4i_csi_querycap(struct file *file, void *priv, struct v4l2_capability *cap) { - struct sun4i_csi *csi = video_drvdata(file); - strscpy(cap->driver, KBUILD_MODNAME, sizeof(cap->driver)); strscpy(cap->card, "sun4i-csi", sizeof(cap->card)); - snprintf(cap->bus_info, sizeof(cap->bus_info), "platform:%s", - dev_name(csi->dev)); return 0; } diff --git a/drivers/media/platform/sunxi/sun6i-csi/sun6i_csi.c b/drivers/media/platform/sunxi/sun6i-csi/sun6i_csi.c index fc96921b0583..a971587dbbd1 100644 --- a/drivers/media/platform/sunxi/sun6i-csi/sun6i_csi.c +++ b/drivers/media/platform/sunxi/sun6i-csi/sun6i_csi.c @@ -733,8 +733,6 @@ static int sun6i_csi_v4l2_init(struct sun6i_csi *csi) strscpy(csi->media_dev.model, "Allwinner Video Capture Device", sizeof(csi->media_dev.model)); csi->media_dev.hw_revision = 0; - snprintf(csi->media_dev.bus_info, sizeof(csi->media_dev.bus_info), - "platform:%s", dev_name(csi->dev)); media_device_init(&csi->media_dev); v4l2_async_nf_init(&csi->notifier); diff --git a/drivers/media/platform/ti/cal/cal-camerarx.c b/drivers/media/platform/ti/cal/cal-camerarx.c index 6b43a1525b45..e69fed117fea 100644 --- a/drivers/media/platform/ti/cal/cal-camerarx.c +++ b/drivers/media/platform/ti/cal/cal-camerarx.c @@ -583,6 +583,33 @@ done: return ret; } +int cal_camerarx_get_remote_frame_desc(struct cal_camerarx *phy, + struct v4l2_mbus_frame_desc *desc) +{ + struct media_pad *pad; + int ret; + + if (!phy->source) + return -EPIPE; + + pad = media_entity_remote_pad(&phy->pads[CAL_CAMERARX_PAD_SINK]); + if (!pad) + return -EPIPE; + + ret = v4l2_subdev_call(phy->source, pad, get_frame_desc, pad->index, + desc); + if (ret) + return ret; + + if (desc->type != V4L2_MBUS_FRAME_DESC_TYPE_CSI2) { + dev_err(phy->cal->dev, + "Frame descriptor does not describe CSI-2 link"); + return -EINVAL; + } + + return 0; +} + /* ------------------------------------------------------------------ * V4L2 Subdev Operations * ------------------------------------------------------------------ diff --git a/drivers/media/platform/ti/cal/cal-video.c b/drivers/media/platform/ti/cal/cal-video.c index 3e936a2ca36c..07ae1a34e6b0 100644 --- a/drivers/media/platform/ti/cal/cal-video.c +++ b/drivers/media/platform/ti/cal/cal-video.c @@ -47,13 +47,9 @@ static char *fourcc_to_str(u32 fmt) static int cal_querycap(struct file *file, void *priv, struct v4l2_capability *cap) { - struct cal_ctx *ctx = video_drvdata(file); - strscpy(cap->driver, CAL_MODULE_NAME, sizeof(cap->driver)); strscpy(cap->card, CAL_MODULE_NAME, sizeof(cap->card)); - snprintf(cap->bus_info, sizeof(cap->bus_info), - "platform:%s", dev_name(ctx->cal->dev)); return 0; } diff --git a/drivers/media/platform/ti/cal/cal.c b/drivers/media/platform/ti/cal/cal.c index 4a4a6c5983f7..425b4f4b7ed7 100644 --- a/drivers/media/platform/ti/cal/cal.c +++ b/drivers/media/platform/ti/cal/cal.c @@ -469,10 +469,57 @@ static bool cal_ctx_wr_dma_stopped(struct cal_ctx *ctx) return stopped; } +static int +cal_get_remote_frame_desc_entry(struct cal_camerarx *phy, + struct v4l2_mbus_frame_desc_entry *entry) +{ + struct v4l2_mbus_frame_desc fd; + int ret; + + ret = cal_camerarx_get_remote_frame_desc(phy, &fd); + if (ret) { + if (ret != -ENOIOCTLCMD) + dev_err(phy->cal->dev, + "Failed to get remote frame desc: %d\n", ret); + return ret; + } + + if (fd.num_entries == 0) { + dev_err(phy->cal->dev, + "No streams found in the remote frame descriptor\n"); + + return -ENODEV; + } + + if (fd.num_entries > 1) + dev_dbg(phy->cal->dev, + "Multiple streams not supported in remote frame descriptor, using the first one\n"); + + *entry = fd.entry[0]; + + return 0; +} + int cal_ctx_prepare(struct cal_ctx *ctx) { + struct v4l2_mbus_frame_desc_entry entry; int ret; + ret = cal_get_remote_frame_desc_entry(ctx->phy, &entry); + + if (ret == -ENOIOCTLCMD) { + ctx->vc = 0; + ctx->datatype = CAL_CSI2_CTX_DT_ANY; + } else if (!ret) { + ctx_dbg(2, ctx, "Framedesc: len %u, vc %u, dt %#x\n", + entry.length, entry.bus.csi2.vc, entry.bus.csi2.dt); + + ctx->vc = entry.bus.csi2.vc; + ctx->datatype = entry.bus.csi2.dt; + } else { + return ret; + } + ctx->use_pix_proc = !ctx->fmtinfo->meta; if (ctx->use_pix_proc) { @@ -884,8 +931,6 @@ static int cal_media_init(struct cal_dev *cal) mdev->dev = cal->dev; mdev->hw_revision = cal->revision; strscpy(mdev->model, "CAL", sizeof(mdev->model)); - snprintf(mdev->bus_info, sizeof(mdev->bus_info), "platform:%s", - dev_name(mdev->dev)); media_device_init(mdev); /* @@ -936,8 +981,6 @@ static struct cal_ctx *cal_ctx_create(struct cal_dev *cal, int inst) ctx->dma_ctx = inst; ctx->csi2_ctx = inst; ctx->cport = inst; - ctx->vc = 0; - ctx->datatype = CAL_CSI2_CTX_DT_ANY; ret = cal_ctx_v4l2_init(ctx); if (ret) diff --git a/drivers/media/platform/ti/cal/cal.h b/drivers/media/platform/ti/cal/cal.h index 527e22d022f3..61409ddced98 100644 --- a/drivers/media/platform/ti/cal/cal.h +++ b/drivers/media/platform/ti/cal/cal.h @@ -323,6 +323,8 @@ const struct cal_format_info *cal_format_by_code(u32 code); void cal_quickdump_regs(struct cal_dev *cal); +int cal_camerarx_get_remote_frame_desc(struct cal_camerarx *phy, + struct v4l2_mbus_frame_desc *desc); void cal_camerarx_disable(struct cal_camerarx *phy); void cal_camerarx_i913_errata(struct cal_camerarx *phy); struct cal_camerarx *cal_camerarx_create(struct cal_dev *cal, diff --git a/drivers/media/platform/ti/davinci/dm355_ccdc.c b/drivers/media/platform/ti/davinci/dm355_ccdc.c index e06d113dfe96..8fe55d1b972c 100644 --- a/drivers/media/platform/ti/davinci/dm355_ccdc.c +++ b/drivers/media/platform/ti/davinci/dm355_ccdc.c @@ -918,8 +918,7 @@ static int dm355_ccdc_remove(struct platform_device *pdev) iounmap(ccdc_cfg.base_addr); res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (res) - release_mem_region(res->start, resource_size(res)); + release_mem_region(res->start, resource_size(res)); vpfe_unregister_ccdc_device(&ccdc_hw_dev); return 0; } diff --git a/drivers/media/platform/ti/davinci/dm644x_ccdc.c b/drivers/media/platform/ti/davinci/dm644x_ccdc.c index c6378c4e0074..e4073e99914c 100644 --- a/drivers/media/platform/ti/davinci/dm644x_ccdc.c +++ b/drivers/media/platform/ti/davinci/dm644x_ccdc.c @@ -839,8 +839,7 @@ static int dm644x_ccdc_remove(struct platform_device *pdev) iounmap(ccdc_cfg.base_addr); res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (res) - release_mem_region(res->start, resource_size(res)); + release_mem_region(res->start, resource_size(res)); vpfe_unregister_ccdc_device(&ccdc_hw_dev); return 0; } diff --git a/drivers/media/platform/ti/davinci/isif.c b/drivers/media/platform/ti/davinci/isif.c index c53cecd072b1..69e862de014f 100644 --- a/drivers/media/platform/ti/davinci/isif.c +++ b/drivers/media/platform/ti/davinci/isif.c @@ -1107,8 +1107,7 @@ static int isif_remove(struct platform_device *pdev) isif_cfg.linear_tbl1_addr = NULL; while (i < 3) { res = platform_get_resource(pdev, IORESOURCE_MEM, i); - if (res) - release_mem_region(res->start, resource_size(res)); + release_mem_region(res->start, resource_size(res)); i++; } vpfe_unregister_ccdc_device(&isif_hw_dev); diff --git a/drivers/media/platform/ti/davinci/vpbe_display.c b/drivers/media/platform/ti/davinci/vpbe_display.c index bf3c3e76b921..9ea70817538e 100644 --- a/drivers/media/platform/ti/davinci/vpbe_display.c +++ b/drivers/media/platform/ti/davinci/vpbe_display.c @@ -630,8 +630,6 @@ static int vpbe_display_querycap(struct file *file, void *priv, snprintf(cap->driver, sizeof(cap->driver), "%s", dev_name(vpbe_dev->pdev)); - snprintf(cap->bus_info, sizeof(cap->bus_info), "platform:%s", - dev_name(vpbe_dev->pdev)); strscpy(cap->card, vpbe_dev->cfg->module_name, sizeof(cap->card)); return 0; diff --git a/drivers/media/platform/ti/davinci/vpif_capture.c b/drivers/media/platform/ti/davinci/vpif_capture.c index bf76c5c83743..b91eec899eb5 100644 --- a/drivers/media/platform/ti/davinci/vpif_capture.c +++ b/drivers/media/platform/ti/davinci/vpif_capture.c @@ -1067,8 +1067,6 @@ static int vpif_querycap(struct file *file, void *priv, struct vpif_capture_config *config = vpif_dev->platform_data; strscpy(cap->driver, VPIF_DRIVER_NAME, sizeof(cap->driver)); - snprintf(cap->bus_info, sizeof(cap->bus_info), "platform:%s", - dev_name(vpif_dev)); strscpy(cap->card, config->card_name, sizeof(cap->card)); return 0; diff --git a/drivers/media/platform/ti/davinci/vpif_display.c b/drivers/media/platform/ti/davinci/vpif_display.c index fca148b66471..5d524acc995d 100644 --- a/drivers/media/platform/ti/davinci/vpif_display.c +++ b/drivers/media/platform/ti/davinci/vpif_display.c @@ -585,8 +585,6 @@ static int vpif_querycap(struct file *file, void *priv, struct vpif_display_config *config = vpif_dev->platform_data; strscpy(cap->driver, VPIF_DRIVER_NAME, sizeof(cap->driver)); - snprintf(cap->bus_info, sizeof(cap->bus_info), "platform:%s", - dev_name(vpif_dev)); strscpy(cap->card, config->card_name, sizeof(cap->card)); return 0; @@ -1286,8 +1284,7 @@ static __init int vpif_probe(struct platform_device *pdev) goto probe_subdev_out; } - if (vpif_obj.sd[i]) - vpif_obj.sd[i]->grp_id = 1 << i; + vpif_obj.sd[i]->grp_id = 1 << i; } err = vpif_probe_complete(); if (err) diff --git a/drivers/media/platform/ti/omap3isp/ispcsiphy.c b/drivers/media/platform/ti/omap3isp/ispcsiphy.c index 6dc7359c5131..1bde76c0adbe 100644 --- a/drivers/media/platform/ti/omap3isp/ispcsiphy.c +++ b/drivers/media/platform/ti/omap3isp/ispcsiphy.c @@ -31,7 +31,8 @@ static void csiphy_routing_cfg_3630(struct isp_csiphy *phy, switch (iface) { default: - /* Should not happen in practice, but let's keep the compiler happy. */ + /* Should not happen in practice, but let's keep the compiler happy. */ + return; case ISP_INTERFACE_CCP2B_PHY1: reg &= ~OMAP3630_CONTROL_CAMERA_PHY_CTRL_CSI1_RX_SEL_PHY2; shift = OMAP3630_CONTROL_CAMERA_PHY_CTRL_CAMMODE_PHY1_SHIFT; diff --git a/drivers/media/platform/video-mux.c b/drivers/media/platform/video-mux.c index fda8fc0e4814..b31e5913a4cd 100644 --- a/drivers/media/platform/video-mux.c +++ b/drivers/media/platform/video-mux.c @@ -442,9 +442,7 @@ static int video_mux_probe(struct platform_device *pdev) vmux->mux = devm_mux_control_get(dev, NULL); if (IS_ERR(vmux->mux)) { ret = PTR_ERR(vmux->mux); - if (ret != -EPROBE_DEFER) - dev_err(dev, "Failed to get mux: %d\n", ret); - return ret; + return dev_err_probe(dev, ret, "Failed to get mux\n"); } mutex_init(&vmux->lock); diff --git a/drivers/media/radio/Kconfig b/drivers/media/radio/Kconfig index cca03bd2cc42..616a38feb641 100644 --- a/drivers/media/radio/Kconfig +++ b/drivers/media/radio/Kconfig @@ -4,10 +4,10 @@ # menuconfig RADIO_ADAPTERS - bool "Radio Adapters" + tristate "Radio Adapters" depends on VIDEO_DEV depends on MEDIA_RADIO_SUPPORT - default y + default VIDEO_DEV help Say Y here to enable selecting AM/FM radio adapters. diff --git a/drivers/media/radio/radio-maxiradio.c b/drivers/media/radio/radio-maxiradio.c index de107e2cbcd6..1a5dbae24ef4 100644 --- a/drivers/media/radio/radio-maxiradio.c +++ b/drivers/media/radio/radio-maxiradio.c @@ -144,8 +144,6 @@ static int maxiradio_probe(struct pci_dev *pdev, dev->tea.v4l2_dev = v4l2_dev; dev->tea.radio_nr = radio_nr; strscpy(dev->tea.card, "Maxi Radio FM2000", sizeof(dev->tea.card)); - snprintf(dev->tea.bus_info, sizeof(dev->tea.bus_info), - "PCI:%s", pci_name(pdev)); retval = -ENODEV; diff --git a/drivers/media/rc/gpio-ir-tx.c b/drivers/media/rc/gpio-ir-tx.c index a50701cfbbd7..d3063ddb472e 100644 --- a/drivers/media/rc/gpio-ir-tx.c +++ b/drivers/media/rc/gpio-ir-tx.c @@ -62,8 +62,13 @@ static void delay_until(ktime_t until) return; /* udelay more than 1ms may not work */ - delta = min(delta, 1000); + if (delta >= 1000) { + mdelay(delta / 1000); + continue; + } + udelay(delta); + break; } } diff --git a/drivers/media/rc/imon.c b/drivers/media/rc/imon.c index 54da6f60079b..735b925da998 100644 --- a/drivers/media/rc/imon.c +++ b/drivers/media/rc/imon.c @@ -153,6 +153,24 @@ struct imon_context { const struct imon_usb_dev_descr *dev_descr; /* device description with key */ /* table for front panels */ + /* + * Fields for deferring free_imon_context(). + * + * Since reference to "struct imon_context" is stored into + * "struct file"->private_data, we need to remember + * how many file descriptors might access this "struct imon_context". + */ + refcount_t users; + /* + * Use a flag for telling display_open()/vfd_write()/lcd_write() that + * imon_disconnect() was already called. + */ + bool disconnected; + /* + * We need to wait for RCU grace period in order to allow + * display_open() to safely check ->disconnected and increment ->users. + */ + struct rcu_head rcu; }; #define TOUCH_TIMEOUT (HZ/30) @@ -160,18 +178,18 @@ struct imon_context { /* vfd character device file operations */ static const struct file_operations vfd_fops = { .owner = THIS_MODULE, - .open = &display_open, - .write = &vfd_write, - .release = &display_close, + .open = display_open, + .write = vfd_write, + .release = display_close, .llseek = noop_llseek, }; /* lcd character device file operations */ static const struct file_operations lcd_fops = { .owner = THIS_MODULE, - .open = &display_open, - .write = &lcd_write, - .release = &display_close, + .open = display_open, + .write = lcd_write, + .release = display_close, .llseek = noop_llseek, }; @@ -439,9 +457,6 @@ static struct usb_driver imon_driver = { .id_table = imon_usb_id_table, }; -/* to prevent races between open() and disconnect(), probing, etc */ -static DEFINE_MUTEX(driver_lock); - /* Module bookkeeping bits */ MODULE_AUTHOR(MOD_AUTHOR); MODULE_DESCRIPTION(MOD_DESC); @@ -481,9 +496,11 @@ static void free_imon_context(struct imon_context *ictx) struct device *dev = ictx->dev; usb_free_urb(ictx->tx_urb); + WARN_ON(ictx->dev_present_intf0); usb_free_urb(ictx->rx_urb_intf0); + WARN_ON(ictx->dev_present_intf1); usb_free_urb(ictx->rx_urb_intf1); - kfree(ictx); + kfree_rcu(ictx, rcu); dev_dbg(dev, "%s: iMON context freed\n", __func__); } @@ -499,9 +516,6 @@ static int display_open(struct inode *inode, struct file *file) int subminor; int retval = 0; - /* prevent races with disconnect */ - mutex_lock(&driver_lock); - subminor = iminor(inode); interface = usb_find_interface(&imon_driver, subminor); if (!interface) { @@ -509,13 +523,16 @@ static int display_open(struct inode *inode, struct file *file) retval = -ENODEV; goto exit; } - ictx = usb_get_intfdata(interface); - if (!ictx) { + rcu_read_lock(); + ictx = usb_get_intfdata(interface); + if (!ictx || ictx->disconnected || !refcount_inc_not_zero(&ictx->users)) { + rcu_read_unlock(); pr_err("no context found for minor %d\n", subminor); retval = -ENODEV; goto exit; } + rcu_read_unlock(); mutex_lock(&ictx->lock); @@ -533,8 +550,10 @@ static int display_open(struct inode *inode, struct file *file) mutex_unlock(&ictx->lock); + if (retval && refcount_dec_and_test(&ictx->users)) + free_imon_context(ictx); + exit: - mutex_unlock(&driver_lock); return retval; } @@ -544,16 +563,9 @@ exit: */ static int display_close(struct inode *inode, struct file *file) { - struct imon_context *ictx = NULL; + struct imon_context *ictx = file->private_data; int retval = 0; - ictx = file->private_data; - - if (!ictx) { - pr_err("no context for device\n"); - return -ENODEV; - } - mutex_lock(&ictx->lock); if (!ictx->display_supported) { @@ -568,6 +580,8 @@ static int display_close(struct inode *inode, struct file *file) } mutex_unlock(&ictx->lock); + if (refcount_dec_and_test(&ictx->users)) + free_imon_context(ictx); return retval; } @@ -934,15 +948,12 @@ static ssize_t vfd_write(struct file *file, const char __user *buf, int offset; int seq; int retval = 0; - struct imon_context *ictx; + struct imon_context *ictx = file->private_data; static const unsigned char vfd_packet6[] = { 0x01, 0x00, 0x00, 0x00, 0x00, 0xFF, 0xFF }; - ictx = file->private_data; - if (!ictx) { - pr_err_ratelimited("no context for device\n"); + if (ictx->disconnected) return -ENODEV; - } mutex_lock(&ictx->lock); @@ -1018,13 +1029,10 @@ static ssize_t lcd_write(struct file *file, const char __user *buf, size_t n_bytes, loff_t *pos) { int retval = 0; - struct imon_context *ictx; + struct imon_context *ictx = file->private_data; - ictx = file->private_data; - if (!ictx) { - pr_err_ratelimited("no context for device\n"); + if (ictx->disconnected) return -ENODEV; - } mutex_lock(&ictx->lock); @@ -2404,7 +2412,6 @@ static int imon_probe(struct usb_interface *interface, int ifnum, sysfs_err; int ret = 0; struct imon_context *ictx = NULL; - struct imon_context *first_if_ctx = NULL; u16 vendor, product; usbdev = usb_get_dev(interface_to_usbdev(interface)); @@ -2416,17 +2423,12 @@ static int imon_probe(struct usb_interface *interface, dev_dbg(dev, "%s: found iMON device (%04x:%04x, intf%d)\n", __func__, vendor, product, ifnum); - /* prevent races probing devices w/multiple interfaces */ - mutex_lock(&driver_lock); - first_if = usb_ifnum_to_if(usbdev, 0); if (!first_if) { ret = -ENODEV; goto fail; } - first_if_ctx = usb_get_intfdata(first_if); - if (ifnum == 0) { ictx = imon_init_intf0(interface, id); if (!ictx) { @@ -2434,9 +2436,11 @@ static int imon_probe(struct usb_interface *interface, ret = -ENODEV; goto fail; } + refcount_set(&ictx->users, 1); } else { /* this is the secondary interface on the device */ + struct imon_context *first_if_ctx = usb_get_intfdata(first_if); /* fail early if first intf failed to register */ if (!first_if_ctx) { @@ -2450,14 +2454,13 @@ static int imon_probe(struct usb_interface *interface, ret = -ENODEV; goto fail; } + refcount_inc(&ictx->users); } usb_set_intfdata(interface, ictx); if (ifnum == 0) { - mutex_lock(&ictx->lock); - if (product == 0xffdc && ictx->rf_device) { sysfs_err = sysfs_create_group(&interface->dev.kobj, &imon_rf_attr_group); @@ -2468,21 +2471,17 @@ static int imon_probe(struct usb_interface *interface, if (ictx->display_supported) imon_init_display(ictx, interface); - - mutex_unlock(&ictx->lock); } dev_info(dev, "iMON device (%04x:%04x, intf%d) on usb<%d:%d> initialized\n", vendor, product, ifnum, usbdev->bus->busnum, usbdev->devnum); - mutex_unlock(&driver_lock); usb_put_dev(usbdev); return 0; fail: - mutex_unlock(&driver_lock); usb_put_dev(usbdev); dev_err(dev, "unable to register, err %d\n", ret); @@ -2498,10 +2497,8 @@ static void imon_disconnect(struct usb_interface *interface) struct device *dev; int ifnum; - /* prevent races with multi-interface device probing and display_open */ - mutex_lock(&driver_lock); - ictx = usb_get_intfdata(interface); + ictx->disconnected = true; dev = ictx->dev; ifnum = interface->cur_altsetting->desc.bInterfaceNumber; @@ -2523,7 +2520,6 @@ static void imon_disconnect(struct usb_interface *interface) if (ifnum == 0) { ictx->dev_present_intf0 = false; usb_kill_urb(ictx->rx_urb_intf0); - usb_put_dev(ictx->usbdev_intf0); input_unregister_device(ictx->idev); rc_unregister_device(ictx->rdev); if (ictx->display_supported) { @@ -2532,21 +2528,20 @@ static void imon_disconnect(struct usb_interface *interface) else if (ictx->display_type == IMON_DISPLAY_TYPE_VFD) usb_deregister_dev(interface, &imon_vfd_class); } + usb_put_dev(ictx->usbdev_intf0); } else { ictx->dev_present_intf1 = false; usb_kill_urb(ictx->rx_urb_intf1); - usb_put_dev(ictx->usbdev_intf1); if (ictx->display_type == IMON_DISPLAY_TYPE_VGA) { - input_unregister_device(ictx->touch); del_timer_sync(&ictx->ttimer); + input_unregister_device(ictx->touch); } + usb_put_dev(ictx->usbdev_intf1); } - if (!ictx->dev_present_intf0 && !ictx->dev_present_intf1) + if (refcount_dec_and_test(&ictx->users)) free_imon_context(ictx); - mutex_unlock(&driver_lock); - dev_dbg(dev, "%s: iMON device (intf%d) disconnected\n", __func__, ifnum); } @@ -2578,7 +2573,7 @@ static int imon_resume(struct usb_interface *intf) usb_rx_callback_intf0, ictx, ictx->rx_endpoint_intf0->bInterval); - rc = usb_submit_urb(ictx->rx_urb_intf0, GFP_ATOMIC); + rc = usb_submit_urb(ictx->rx_urb_intf0, GFP_NOIO); } else { usb_fill_int_urb(ictx->rx_urb_intf1, ictx->usbdev_intf1, @@ -2588,7 +2583,7 @@ static int imon_resume(struct usb_interface *intf) usb_rx_callback_intf1, ictx, ictx->rx_endpoint_intf1->bInterval); - rc = usb_submit_urb(ictx->rx_urb_intf1, GFP_ATOMIC); + rc = usb_submit_urb(ictx->rx_urb_intf1, GFP_NOIO); } return rc; diff --git a/drivers/media/rc/meson-ir-tx.c b/drivers/media/rc/meson-ir-tx.c index 63e1dbf0a4e9..abdb62b16e98 100644 --- a/drivers/media/rc/meson-ir-tx.c +++ b/drivers/media/rc/meson-ir-tx.c @@ -323,10 +323,8 @@ static int __init meson_irtx_probe(struct platform_device *pdev) return PTR_ERR(ir->reg_base); irq = platform_get_irq(pdev, 0); - if (irq < 0) { - dev_err(dev, "no irq resource found\n"); + if (irq < 0) return -ENODEV; - } ir->dev = dev; ir->carrier = MIRTX_DEFAULT_CARRIER; diff --git a/drivers/media/tuners/si2157.c b/drivers/media/tuners/si2157.c index 47029746b89e..0de587b412d4 100644 --- a/drivers/media/tuners/si2157.c +++ b/drivers/media/tuners/si2157.c @@ -77,16 +77,16 @@ err_mutex_unlock: } static const struct si2157_tuner_info si2157_tuners[] = { - { SI2141, false, 0x60, SI2141_60_FIRMWARE, SI2141_A10_FIRMWARE }, - { SI2141, false, 0x61, SI2141_61_FIRMWARE, SI2141_A10_FIRMWARE }, - { SI2146, false, 0x11, SI2146_11_FIRMWARE, NULL }, - { SI2147, false, 0x50, SI2147_50_FIRMWARE, NULL }, - { SI2148, true, 0x32, SI2148_32_FIRMWARE, SI2158_A20_FIRMWARE }, - { SI2148, true, 0x33, SI2148_33_FIRMWARE, SI2158_A20_FIRMWARE }, - { SI2157, false, 0x50, SI2157_50_FIRMWARE, SI2157_A30_FIRMWARE }, - { SI2158, false, 0x50, SI2158_50_FIRMWARE, SI2158_A20_FIRMWARE }, - { SI2158, false, 0x51, SI2158_51_FIRMWARE, SI2158_A20_FIRMWARE }, - { SI2177, false, 0x50, SI2177_50_FIRMWARE, SI2157_A30_FIRMWARE }, + { SI2141, 0x60, false, SI2141_60_FIRMWARE, SI2141_A10_FIRMWARE }, + { SI2141, 0x61, false, SI2141_61_FIRMWARE, SI2141_A10_FIRMWARE }, + { SI2146, 0x11, false, SI2146_11_FIRMWARE, NULL }, + { SI2147, 0x50, false, SI2147_50_FIRMWARE, NULL }, + { SI2148, 0x32, true, SI2148_32_FIRMWARE, SI2158_A20_FIRMWARE }, + { SI2148, 0x33, true, SI2148_33_FIRMWARE, SI2158_A20_FIRMWARE }, + { SI2157, 0x50, false, SI2157_50_FIRMWARE, SI2157_A30_FIRMWARE }, + { SI2158, 0x50, false, SI2158_50_FIRMWARE, SI2158_A20_FIRMWARE }, + { SI2158, 0x51, false, SI2158_51_FIRMWARE, SI2158_A20_FIRMWARE }, + { SI2177, 0x50, false, SI2177_50_FIRMWARE, SI2157_A30_FIRMWARE }, }; static int si2157_load_firmware(struct dvb_frontend *fe, @@ -178,7 +178,7 @@ static int si2157_find_and_load_firmware(struct dvb_frontend *fe) } } - if (!fw_name && !fw_alt_name) { + if (required && !fw_name && !fw_alt_name) { dev_err(&client->dev, "unknown chip version Si21%d-%c%c%c ROM 0x%02x\n", part_id, cmd.args[1], cmd.args[3], cmd.args[4], rom_id); diff --git a/drivers/media/usb/dvb-usb/a800.c b/drivers/media/usb/dvb-usb/a800.c index 36b5b6227412..5f294784923c 100644 --- a/drivers/media/usb/dvb-usb/a800.c +++ b/drivers/media/usb/dvb-usb/a800.c @@ -72,11 +72,17 @@ static int a800_probe(struct usb_interface *intf, } /* do not change the order of the ID table */ -static struct usb_device_id a800_table [] = { -/* 00 */ { USB_DEVICE(USB_VID_AVERMEDIA, USB_PID_AVERMEDIA_DVBT_USB2_COLD) }, -/* 01 */ { USB_DEVICE(USB_VID_AVERMEDIA, USB_PID_AVERMEDIA_DVBT_USB2_WARM) }, - { } /* Terminating entry */ +enum { + AVERMEDIA_DVBT_USB2_COLD, + AVERMEDIA_DVBT_USB2_WARM, }; + +static struct usb_device_id a800_table[] = { + DVB_USB_DEV(AVERMEDIA, AVERMEDIA_DVBT_USB2_COLD), + DVB_USB_DEV(AVERMEDIA, AVERMEDIA_DVBT_USB2_WARM), + { } +}; + MODULE_DEVICE_TABLE (usb, a800_table); static struct dvb_usb_device_properties a800_properties = { @@ -132,8 +138,8 @@ static struct dvb_usb_device_properties a800_properties = { .num_device_descs = 1, .devices = { { "AVerMedia AverTV DVB-T USB 2.0 (A800)", - { &a800_table[0], NULL }, - { &a800_table[1], NULL }, + { &a800_table[AVERMEDIA_DVBT_USB2_COLD], NULL }, + { &a800_table[AVERMEDIA_DVBT_USB2_WARM], NULL }, }, } }; diff --git a/drivers/media/usb/dvb-usb/af9005.c b/drivers/media/usb/dvb-usb/af9005.c index b6a2436d16e9..0827bf3d4e8c 100644 --- a/drivers/media/usb/dvb-usb/af9005.c +++ b/drivers/media/usb/dvb-usb/af9005.c @@ -994,19 +994,16 @@ static int af9005_usb_probe(struct usb_interface *intf, THIS_MODULE, NULL, adapter_nr); } -enum af9005_usb_table_entry { +enum { AFATECH_AF9005, - TERRATEC_AF9005, - ANSONIC_AF9005, + TERRATEC_CINERGY_T_USB_XE, + ANSONIC_DVBT_USB, }; static struct usb_device_id af9005_usb_table[] = { - [AFATECH_AF9005] = {USB_DEVICE(USB_VID_AFATECH, - USB_PID_AFATECH_AF9005)}, - [TERRATEC_AF9005] = {USB_DEVICE(USB_VID_TERRATEC, - USB_PID_TERRATEC_CINERGY_T_USB_XE)}, - [ANSONIC_AF9005] = {USB_DEVICE(USB_VID_ANSONIC, - USB_PID_ANSONIC_DVBT_USB)}, + DVB_USB_DEV(AFATECH, AFATECH_AF9005), + DVB_USB_DEV(TERRATEC, TERRATEC_CINERGY_T_USB_XE), + DVB_USB_DEV(ANSONIC, ANSONIC_DVBT_USB), { } }; @@ -1071,11 +1068,11 @@ static struct dvb_usb_device_properties af9005_properties = { .warm_ids = {NULL}, }, {.name = "TerraTec Cinergy T USB XE", - .cold_ids = {&af9005_usb_table[TERRATEC_AF9005], NULL}, + .cold_ids = {&af9005_usb_table[TERRATEC_CINERGY_T_USB_XE], NULL}, .warm_ids = {NULL}, }, {.name = "Ansonic DVB-T USB1.1 stick", - .cold_ids = {&af9005_usb_table[ANSONIC_AF9005], NULL}, + .cold_ids = {&af9005_usb_table[ANSONIC_DVBT_USB], NULL}, .warm_ids = {NULL}, }, {NULL}, diff --git a/drivers/media/usb/dvb-usb/az6027.c b/drivers/media/usb/dvb-usb/az6027.c index 86788771175b..cf15988dfb51 100644 --- a/drivers/media/usb/dvb-usb/az6027.c +++ b/drivers/media/usb/dvb-usb/az6027.c @@ -1080,16 +1080,27 @@ static int az6027_identify_state(struct usb_device *udev, } +enum { + AZUREWAVE_AZ6027, + TERRATEC_DVBS2CI_V1, + TERRATEC_DVBS2CI_V2, + TECHNISAT_USB2_HDCI_V1, + TECHNISAT_USB2_HDCI_V2, + ELGATO_EYETV_SAT, + ELGATO_EYETV_SAT_V2, + ELGATO_EYETV_SAT_V3, +}; + static struct usb_device_id az6027_usb_table[] = { - { USB_DEVICE(USB_VID_AZUREWAVE, USB_PID_AZUREWAVE_AZ6027) }, - { USB_DEVICE(USB_VID_TERRATEC, USB_PID_TERRATEC_DVBS2CI_V1) }, - { USB_DEVICE(USB_VID_TERRATEC, USB_PID_TERRATEC_DVBS2CI_V2) }, - { USB_DEVICE(USB_VID_TECHNISAT, USB_PID_TECHNISAT_USB2_HDCI_V1) }, - { USB_DEVICE(USB_VID_TECHNISAT, USB_PID_TECHNISAT_USB2_HDCI_V2) }, - { USB_DEVICE(USB_VID_ELGATO, USB_PID_ELGATO_EYETV_SAT) }, - { USB_DEVICE(USB_VID_ELGATO, USB_PID_ELGATO_EYETV_SAT_V2) }, - { USB_DEVICE(USB_VID_ELGATO, USB_PID_ELGATO_EYETV_SAT_V3) }, - { }, + DVB_USB_DEV(AZUREWAVE, AZUREWAVE_AZ6027), + DVB_USB_DEV(TERRATEC, TERRATEC_DVBS2CI_V1), + DVB_USB_DEV(TERRATEC, TERRATEC_DVBS2CI_V2), + DVB_USB_DEV(TECHNISAT, TECHNISAT_USB2_HDCI_V1), + DVB_USB_DEV(TECHNISAT, TECHNISAT_USB2_HDCI_V2), + DVB_USB_DEV(ELGATO, ELGATO_EYETV_SAT), + DVB_USB_DEV(ELGATO, ELGATO_EYETV_SAT_V2), + DVB_USB_DEV(ELGATO, ELGATO_EYETV_SAT_V3), + { } }; MODULE_DEVICE_TABLE(usb, az6027_usb_table); @@ -1141,35 +1152,35 @@ static struct dvb_usb_device_properties az6027_properties = { .devices = { { .name = "AZUREWAVE DVB-S/S2 USB2.0 (AZ6027)", - .cold_ids = { &az6027_usb_table[0], NULL }, + .cold_ids = { &az6027_usb_table[AZUREWAVE_AZ6027], NULL }, .warm_ids = { NULL }, }, { .name = "TERRATEC S7", - .cold_ids = { &az6027_usb_table[1], NULL }, + .cold_ids = { &az6027_usb_table[TERRATEC_DVBS2CI_V1], NULL }, .warm_ids = { NULL }, }, { .name = "TERRATEC S7 MKII", - .cold_ids = { &az6027_usb_table[2], NULL }, + .cold_ids = { &az6027_usb_table[TERRATEC_DVBS2CI_V2], NULL }, .warm_ids = { NULL }, }, { .name = "Technisat SkyStar USB 2 HD CI", - .cold_ids = { &az6027_usb_table[3], NULL }, + .cold_ids = { &az6027_usb_table[TECHNISAT_USB2_HDCI_V1], NULL }, .warm_ids = { NULL }, }, { .name = "Technisat SkyStar USB 2 HD CI", - .cold_ids = { &az6027_usb_table[4], NULL }, + .cold_ids = { &az6027_usb_table[TECHNISAT_USB2_HDCI_V2], NULL }, .warm_ids = { NULL }, }, { .name = "Elgato EyeTV Sat", - .cold_ids = { &az6027_usb_table[5], NULL }, + .cold_ids = { &az6027_usb_table[ELGATO_EYETV_SAT], NULL }, .warm_ids = { NULL }, }, { .name = "Elgato EyeTV Sat", - .cold_ids = { &az6027_usb_table[6], NULL }, + .cold_ids = { &az6027_usb_table[ELGATO_EYETV_SAT_V2], NULL }, .warm_ids = { NULL }, }, { .name = "Elgato EyeTV Sat", - .cold_ids = { &az6027_usb_table[7], NULL }, + .cold_ids = { &az6027_usb_table[ELGATO_EYETV_SAT_V3], NULL }, .warm_ids = { NULL }, }, { NULL }, diff --git a/drivers/media/usb/dvb-usb/cinergyT2-core.c b/drivers/media/usb/dvb-usb/cinergyT2-core.c index 23f1093d28f8..4926c954e29a 100644 --- a/drivers/media/usb/dvb-usb/cinergyT2-core.c +++ b/drivers/media/usb/dvb-usb/cinergyT2-core.c @@ -193,9 +193,13 @@ static int cinergyt2_usb_probe(struct usb_interface *intf, THIS_MODULE, NULL, adapter_nr); } +enum { + TERRATEC_CINERGY_T2, +}; + static struct usb_device_id cinergyt2_usb_table[] = { - { USB_DEVICE(USB_VID_TERRATEC, 0x0038) }, - { 0 } + DVB_USB_DEV(TERRATEC, TERRATEC_CINERGY_T2), + { } }; MODULE_DEVICE_TABLE(usb, cinergyt2_usb_table); @@ -240,7 +244,7 @@ static const struct dvb_usb_device_properties cinergyt2_properties = { .devices = { { .name = "TerraTec/qanu USB2.0 Highspeed DVB-T Receiver", .cold_ids = {NULL}, - .warm_ids = { &cinergyt2_usb_table[0], NULL }, + .warm_ids = { &cinergyt2_usb_table[TERRATEC_CINERGY_T2], NULL }, }, { NULL }, } diff --git a/drivers/media/usb/dvb-usb/cxusb.c b/drivers/media/usb/dvb-usb/cxusb.c index 265b960db499..1d98d3465e28 100644 --- a/drivers/media/usb/dvb-usb/cxusb.c +++ b/drivers/media/usb/dvb-usb/cxusb.c @@ -1692,72 +1692,30 @@ static void cxusb_disconnect(struct usb_interface *intf) dvb_usb_device_exit(intf); } -static struct usb_device_id cxusb_table[NR__cxusb_table_index + 1] = { - [MEDION_MD95700] = { - USB_DEVICE(USB_VID_MEDION, USB_PID_MEDION_MD95700) - }, - [DVICO_BLUEBIRD_LG064F_COLD] = { - USB_DEVICE(USB_VID_DVICO, USB_PID_DVICO_BLUEBIRD_LG064F_COLD) - }, - [DVICO_BLUEBIRD_LG064F_WARM] = { - USB_DEVICE(USB_VID_DVICO, USB_PID_DVICO_BLUEBIRD_LG064F_WARM) - }, - [DVICO_BLUEBIRD_DUAL_1_COLD] = { - USB_DEVICE(USB_VID_DVICO, USB_PID_DVICO_BLUEBIRD_DUAL_1_COLD) - }, - [DVICO_BLUEBIRD_DUAL_1_WARM] = { - USB_DEVICE(USB_VID_DVICO, USB_PID_DVICO_BLUEBIRD_DUAL_1_WARM) - }, - [DVICO_BLUEBIRD_LGZ201_COLD] = { - USB_DEVICE(USB_VID_DVICO, USB_PID_DVICO_BLUEBIRD_LGZ201_COLD) - }, - [DVICO_BLUEBIRD_LGZ201_WARM] = { - USB_DEVICE(USB_VID_DVICO, USB_PID_DVICO_BLUEBIRD_LGZ201_WARM) - }, - [DVICO_BLUEBIRD_TH7579_COLD] = { - USB_DEVICE(USB_VID_DVICO, USB_PID_DVICO_BLUEBIRD_TH7579_COLD) - }, - [DVICO_BLUEBIRD_TH7579_WARM] = { - USB_DEVICE(USB_VID_DVICO, USB_PID_DVICO_BLUEBIRD_TH7579_WARM) - }, - [DIGITALNOW_BLUEBIRD_DUAL_1_COLD] = { - USB_DEVICE(USB_VID_DVICO, - USB_PID_DIGITALNOW_BLUEBIRD_DUAL_1_COLD) - }, - [DIGITALNOW_BLUEBIRD_DUAL_1_WARM] = { - USB_DEVICE(USB_VID_DVICO, - USB_PID_DIGITALNOW_BLUEBIRD_DUAL_1_WARM) - }, - [DVICO_BLUEBIRD_DUAL_2_COLD] = { - USB_DEVICE(USB_VID_DVICO, USB_PID_DVICO_BLUEBIRD_DUAL_2_COLD) - }, - [DVICO_BLUEBIRD_DUAL_2_WARM] = { - USB_DEVICE(USB_VID_DVICO, USB_PID_DVICO_BLUEBIRD_DUAL_2_WARM) - }, - [DVICO_BLUEBIRD_DUAL_4] = { - USB_DEVICE(USB_VID_DVICO, USB_PID_DVICO_BLUEBIRD_DUAL_4) - }, - [DVICO_BLUEBIRD_DVB_T_NANO_2] = { - USB_DEVICE(USB_VID_DVICO, USB_PID_DVICO_BLUEBIRD_DVB_T_NANO_2) - }, - [DVICO_BLUEBIRD_DVB_T_NANO_2_NFW_WARM] = { - USB_DEVICE(USB_VID_DVICO, - USB_PID_DVICO_BLUEBIRD_DVB_T_NANO_2_NFW_WARM) - }, - [AVERMEDIA_VOLAR_A868R] = { - USB_DEVICE(USB_VID_AVERMEDIA, USB_PID_AVERMEDIA_VOLAR_A868R) - }, - [DVICO_BLUEBIRD_DUAL_4_REV_2] = { - USB_DEVICE(USB_VID_DVICO, USB_PID_DVICO_BLUEBIRD_DUAL_4_REV_2) - }, - [CONEXANT_D680_DMB] = { - USB_DEVICE(USB_VID_CONEXANT, USB_PID_CONEXANT_D680_DMB) - }, - [MYGICA_D689] = { - USB_DEVICE(USB_VID_CONEXANT, USB_PID_MYGICA_D689) - }, - {} /* Terminating entry */ +static struct usb_device_id cxusb_table[] = { + DVB_USB_DEV(MEDION, MEDION_MD95700), + DVB_USB_DEV(DVICO, DVICO_BLUEBIRD_LG064F_COLD), + DVB_USB_DEV(DVICO, DVICO_BLUEBIRD_LG064F_WARM), + DVB_USB_DEV(DVICO, DVICO_BLUEBIRD_DUAL_1_COLD), + DVB_USB_DEV(DVICO, DVICO_BLUEBIRD_DUAL_1_WARM), + DVB_USB_DEV(DVICO, DVICO_BLUEBIRD_LGZ201_COLD), + DVB_USB_DEV(DVICO, DVICO_BLUEBIRD_LGZ201_WARM), + DVB_USB_DEV(DVICO, DVICO_BLUEBIRD_TH7579_COLD), + DVB_USB_DEV(DVICO, DVICO_BLUEBIRD_TH7579_WARM), + DVB_USB_DEV(DVICO, DIGITALNOW_BLUEBIRD_DUAL_1_COLD), + DVB_USB_DEV(DVICO, DIGITALNOW_BLUEBIRD_DUAL_1_WARM), + DVB_USB_DEV(DVICO, DVICO_BLUEBIRD_DUAL_2_COLD), + DVB_USB_DEV(DVICO, DVICO_BLUEBIRD_DUAL_2_WARM), + DVB_USB_DEV(DVICO, DVICO_BLUEBIRD_DUAL_4), + DVB_USB_DEV(DVICO, DVICO_BLUEBIRD_DVB_T_NANO_2), + DVB_USB_DEV(DVICO, DVICO_BLUEBIRD_DVB_T_NANO_2_NFW_WARM), + DVB_USB_DEV(AVERMEDIA, AVERMEDIA_VOLAR_A868R), + DVB_USB_DEV(DVICO, DVICO_BLUEBIRD_DUAL_4_REV_2), + DVB_USB_DEV(CONEXANT, CONEXANT_D680_DMB), + DVB_USB_DEV(CONEXANT, MYGICA_D689), + { } }; + MODULE_DEVICE_TABLE(usb, cxusb_table); static struct dvb_usb_device_properties cxusb_medion_properties = { diff --git a/drivers/media/usb/dvb-usb/dib0700_devices.c b/drivers/media/usb/dvb-usb/dib0700_devices.c index 08fcf120daf1..7f8bebfa3e8e 100644 --- a/drivers/media/usb/dvb-usb/dib0700_devices.c +++ b/drivers/media/usb/dvb-usb/dib0700_devices.c @@ -3816,99 +3816,187 @@ fail_demod_device: /* DVB-USB and USB stuff follows */ +enum { + DIBCOM_STK7700P, + DIBCOM_STK7700P_PC, + HAUPPAUGE_NOVA_T_500, + HAUPPAUGE_NOVA_T_500_2, + HAUPPAUGE_NOVA_T_STICK, + AVERMEDIA_VOLAR, + COMPRO_VIDEOMATE_U500, + UNIWILL_STK7700P, + LEADTEK_WINFAST_DTV_DONGLE_STK7700P, + HAUPPAUGE_NOVA_T_STICK_2, + AVERMEDIA_VOLAR_2, + PINNACLE_PCTV2000E, + TERRATEC_CINERGY_DT_XS_DIVERSITY, + HAUPPAUGE_NOVA_TD_STICK, + DIBCOM_STK7700D, + DIBCOM_STK7070P, + PINNACLE_PCTV_DVB_T_FLASH, + DIBCOM_STK7070PD, + PINNACLE_PCTV_DUAL_DIVERSITY_DVB_T, + COMPRO_VIDEOMATE_U500_PC, + AVERMEDIA_EXPRESS, + GIGABYTE_U7000, + ULTIMA_ARTEC_T14BR, + ASUS_U3000, + ASUS_U3100, + HAUPPAUGE_NOVA_T_STICK_3, + HAUPPAUGE_MYTV_T, + TERRATEC_CINERGY_HT_USB_XE, + PINNACLE_EXPRESSCARD_320CX, + PINNACLE_PCTV72E, + PINNACLE_PCTV73E, + YUAN_EC372S, + TERRATEC_CINERGY_HT_EXPRESS, + TERRATEC_CINERGY_T_XXS, + LEADTEK_WINFAST_DTV_DONGLE_STK7700P_2, + HAUPPAUGE_NOVA_TD_STICK_52009, + HAUPPAUGE_NOVA_T_500_3, + GIGABYTE_U8000, + YUAN_STK7700PH, + ASUS_U3000H, + PINNACLE_PCTV801E, + PINNACLE_PCTV801E_SE, + TERRATEC_CINERGY_T_EXPRESS, + TERRATEC_CINERGY_DT_XS_DIVERSITY_2, + SONY_PLAYTV, + YUAN_PD378S, + HAUPPAUGE_TIGER_ATSC, + HAUPPAUGE_TIGER_ATSC_B210, + YUAN_MC770, + ELGATO_EYETV_DTT, + ELGATO_EYETV_DTT_Dlx, + LEADTEK_WINFAST_DTV_DONGLE_H, + TERRATEC_T3, + TERRATEC_T5, + YUAN_STK7700D, + YUAN_STK7700D_2, + PINNACLE_PCTV73A, + PCTV_PINNACLE_PCTV73ESE, + PCTV_PINNACLE_PCTV282E, + DIBCOM_STK7770P, + TERRATEC_CINERGY_T_XXS_2, + DIBCOM_STK807XPVR, + DIBCOM_STK807XP, + PIXELVIEW_SBTVD, + EVOLUTEPC_TVWAY_PLUS, + PINNACLE_PCTV73ESE, + PINNACLE_PCTV282E, + DIBCOM_STK8096GP, + ELGATO_EYETV_DIVERSITY, + DIBCOM_NIM9090M, + DIBCOM_NIM8096MD, + DIBCOM_NIM9090MD, + DIBCOM_NIM7090, + DIBCOM_TFE7090PVR, + TECHNISAT_AIRSTAR_TELESTICK_2, + MEDION_CREATIX_CTX1921, + PINNACLE_PCTV340E, + PINNACLE_PCTV340E_SE, + DIBCOM_TFE7790P, + DIBCOM_TFE8096P, + ELGATO_EYETV_DTT_2, + PCTV_2002E, + PCTV_2002E_SE, + PCTV_DIBCOM_STK8096PVR, + DIBCOM_STK8096PVR, + HAMA_DVBT_HYBRID, + MICROSOFT_XBOX_ONE_TUNER, +}; + struct usb_device_id dib0700_usb_id_table[] = { -/* 0 */ { USB_DEVICE(USB_VID_DIBCOM, USB_PID_DIBCOM_STK7700P) }, - { USB_DEVICE(USB_VID_DIBCOM, USB_PID_DIBCOM_STK7700P_PC) }, - { USB_DEVICE(USB_VID_HAUPPAUGE, USB_PID_HAUPPAUGE_NOVA_T_500) }, - { USB_DEVICE(USB_VID_HAUPPAUGE, USB_PID_HAUPPAUGE_NOVA_T_500_2) }, - { USB_DEVICE(USB_VID_HAUPPAUGE, USB_PID_HAUPPAUGE_NOVA_T_STICK) }, -/* 5 */ { USB_DEVICE(USB_VID_AVERMEDIA, USB_PID_AVERMEDIA_VOLAR) }, - { USB_DEVICE(USB_VID_COMPRO, USB_PID_COMPRO_VIDEOMATE_U500) }, - { USB_DEVICE(USB_VID_UNIWILL, USB_PID_UNIWILL_STK7700P) }, - { USB_DEVICE(USB_VID_LEADTEK, USB_PID_WINFAST_DTV_DONGLE_STK7700P) }, - { USB_DEVICE(USB_VID_HAUPPAUGE, USB_PID_HAUPPAUGE_NOVA_T_STICK_2) }, -/* 10 */{ USB_DEVICE(USB_VID_AVERMEDIA, USB_PID_AVERMEDIA_VOLAR_2) }, - { USB_DEVICE(USB_VID_PINNACLE, USB_PID_PINNACLE_PCTV2000E) }, - { USB_DEVICE(USB_VID_TERRATEC, - USB_PID_TERRATEC_CINERGY_DT_XS_DIVERSITY) }, - { USB_DEVICE(USB_VID_HAUPPAUGE, USB_PID_HAUPPAUGE_NOVA_TD_STICK) }, - { USB_DEVICE(USB_VID_DIBCOM, USB_PID_DIBCOM_STK7700D) }, -/* 15 */{ USB_DEVICE(USB_VID_DIBCOM, USB_PID_DIBCOM_STK7070P) }, - { USB_DEVICE(USB_VID_PINNACLE, USB_PID_PINNACLE_PCTV_DVB_T_FLASH) }, - { USB_DEVICE(USB_VID_DIBCOM, USB_PID_DIBCOM_STK7070PD) }, - { USB_DEVICE(USB_VID_PINNACLE, - USB_PID_PINNACLE_PCTV_DUAL_DIVERSITY_DVB_T) }, - { USB_DEVICE(USB_VID_COMPRO, USB_PID_COMPRO_VIDEOMATE_U500_PC) }, -/* 20 */{ USB_DEVICE(USB_VID_AVERMEDIA, USB_PID_AVERMEDIA_EXPRESS) }, - { USB_DEVICE(USB_VID_GIGABYTE, USB_PID_GIGABYTE_U7000) }, - { USB_DEVICE(USB_VID_ULTIMA_ELECTRONIC, USB_PID_ARTEC_T14BR) }, - { USB_DEVICE(USB_VID_ASUS, USB_PID_ASUS_U3000) }, - { USB_DEVICE(USB_VID_ASUS, USB_PID_ASUS_U3100) }, -/* 25 */{ USB_DEVICE(USB_VID_HAUPPAUGE, USB_PID_HAUPPAUGE_NOVA_T_STICK_3) }, - { USB_DEVICE(USB_VID_HAUPPAUGE, USB_PID_HAUPPAUGE_MYTV_T) }, - { USB_DEVICE(USB_VID_TERRATEC, USB_PID_TERRATEC_CINERGY_HT_USB_XE) }, - { USB_DEVICE(USB_VID_PINNACLE, USB_PID_PINNACLE_EXPRESSCARD_320CX) }, - { USB_DEVICE(USB_VID_PINNACLE, USB_PID_PINNACLE_PCTV72E) }, -/* 30 */{ USB_DEVICE(USB_VID_PINNACLE, USB_PID_PINNACLE_PCTV73E) }, - { USB_DEVICE(USB_VID_YUAN, USB_PID_YUAN_EC372S) }, - { USB_DEVICE(USB_VID_TERRATEC, USB_PID_TERRATEC_CINERGY_HT_EXPRESS) }, - { USB_DEVICE(USB_VID_TERRATEC, USB_PID_TERRATEC_CINERGY_T_XXS) }, - { USB_DEVICE(USB_VID_LEADTEK, USB_PID_WINFAST_DTV_DONGLE_STK7700P_2) }, -/* 35 */{ USB_DEVICE(USB_VID_HAUPPAUGE, USB_PID_HAUPPAUGE_NOVA_TD_STICK_52009) }, - { USB_DEVICE(USB_VID_HAUPPAUGE, USB_PID_HAUPPAUGE_NOVA_T_500_3) }, - { USB_DEVICE(USB_VID_GIGABYTE, USB_PID_GIGABYTE_U8000) }, - { USB_DEVICE(USB_VID_YUAN, USB_PID_YUAN_STK7700PH) }, - { USB_DEVICE(USB_VID_ASUS, USB_PID_ASUS_U3000H) }, -/* 40 */{ USB_DEVICE(USB_VID_PINNACLE, USB_PID_PINNACLE_PCTV801E) }, - { USB_DEVICE(USB_VID_PINNACLE, USB_PID_PINNACLE_PCTV801E_SE) }, - { USB_DEVICE(USB_VID_TERRATEC, USB_PID_TERRATEC_CINERGY_T_EXPRESS) }, - { USB_DEVICE(USB_VID_TERRATEC, - USB_PID_TERRATEC_CINERGY_DT_XS_DIVERSITY_2) }, - { USB_DEVICE(USB_VID_SONY, USB_PID_SONY_PLAYTV) }, -/* 45 */{ USB_DEVICE(USB_VID_YUAN, USB_PID_YUAN_PD378S) }, - { USB_DEVICE(USB_VID_HAUPPAUGE, USB_PID_HAUPPAUGE_TIGER_ATSC) }, - { USB_DEVICE(USB_VID_HAUPPAUGE, USB_PID_HAUPPAUGE_TIGER_ATSC_B210) }, - { USB_DEVICE(USB_VID_YUAN, USB_PID_YUAN_MC770) }, - { USB_DEVICE(USB_VID_ELGATO, USB_PID_ELGATO_EYETV_DTT) }, -/* 50 */{ USB_DEVICE(USB_VID_ELGATO, USB_PID_ELGATO_EYETV_DTT_Dlx) }, - { USB_DEVICE(USB_VID_LEADTEK, USB_PID_WINFAST_DTV_DONGLE_H) }, - { USB_DEVICE(USB_VID_TERRATEC, USB_PID_TERRATEC_T3) }, - { USB_DEVICE(USB_VID_TERRATEC, USB_PID_TERRATEC_T5) }, - { USB_DEVICE(USB_VID_YUAN, USB_PID_YUAN_STK7700D) }, -/* 55 */{ USB_DEVICE(USB_VID_YUAN, USB_PID_YUAN_STK7700D_2) }, - { USB_DEVICE(USB_VID_PINNACLE, USB_PID_PINNACLE_PCTV73A) }, - { USB_DEVICE(USB_VID_PCTV, USB_PID_PINNACLE_PCTV73ESE) }, - { USB_DEVICE(USB_VID_PCTV, USB_PID_PINNACLE_PCTV282E) }, - { USB_DEVICE(USB_VID_DIBCOM, USB_PID_DIBCOM_STK7770P) }, -/* 60 */{ USB_DEVICE(USB_VID_TERRATEC, USB_PID_TERRATEC_CINERGY_T_XXS_2) }, - { USB_DEVICE(USB_VID_DIBCOM, USB_PID_DIBCOM_STK807XPVR) }, - { USB_DEVICE(USB_VID_DIBCOM, USB_PID_DIBCOM_STK807XP) }, - { USB_DEVICE_VER(USB_VID_PIXELVIEW, USB_PID_PIXELVIEW_SBTVD, 0x000, 0x3f00) }, - { USB_DEVICE(USB_VID_EVOLUTEPC, USB_PID_TVWAY_PLUS) }, -/* 65 */{ USB_DEVICE(USB_VID_PINNACLE, USB_PID_PINNACLE_PCTV73ESE) }, - { USB_DEVICE(USB_VID_PINNACLE, USB_PID_PINNACLE_PCTV282E) }, - { USB_DEVICE(USB_VID_DIBCOM, USB_PID_DIBCOM_STK8096GP) }, - { USB_DEVICE(USB_VID_ELGATO, USB_PID_ELGATO_EYETV_DIVERSITY) }, - { USB_DEVICE(USB_VID_DIBCOM, USB_PID_DIBCOM_NIM9090M) }, -/* 70 */{ USB_DEVICE(USB_VID_DIBCOM, USB_PID_DIBCOM_NIM8096MD) }, - { USB_DEVICE(USB_VID_DIBCOM, USB_PID_DIBCOM_NIM9090MD) }, - { USB_DEVICE(USB_VID_DIBCOM, USB_PID_DIBCOM_NIM7090) }, - { USB_DEVICE(USB_VID_DIBCOM, USB_PID_DIBCOM_TFE7090PVR) }, - { USB_DEVICE(USB_VID_TECHNISAT, USB_PID_TECHNISAT_AIRSTAR_TELESTICK_2) }, -/* 75 */{ USB_DEVICE(USB_VID_MEDION, USB_PID_CREATIX_CTX1921) }, - { USB_DEVICE(USB_VID_PINNACLE, USB_PID_PINNACLE_PCTV340E) }, - { USB_DEVICE(USB_VID_PINNACLE, USB_PID_PINNACLE_PCTV340E_SE) }, - { USB_DEVICE(USB_VID_DIBCOM, USB_PID_DIBCOM_TFE7790P) }, - { USB_DEVICE(USB_VID_DIBCOM, USB_PID_DIBCOM_TFE8096P) }, -/* 80 */{ USB_DEVICE(USB_VID_ELGATO, USB_PID_ELGATO_EYETV_DTT_2) }, - { USB_DEVICE(USB_VID_PCTV, USB_PID_PCTV_2002E) }, - { USB_DEVICE(USB_VID_PCTV, USB_PID_PCTV_2002E_SE) }, - { USB_DEVICE(USB_VID_PCTV, USB_PID_DIBCOM_STK8096PVR) }, - { USB_DEVICE(USB_VID_DIBCOM, USB_PID_DIBCOM_STK8096PVR) }, -/* 85 */{ USB_DEVICE(USB_VID_HAMA, USB_PID_HAMA_DVBT_HYBRID) }, - { USB_DEVICE(USB_VID_MICROSOFT, USB_PID_XBOX_ONE_TUNER) }, - { 0 } /* Terminating entry */ + DVB_USB_DEV(DIBCOM, DIBCOM_STK7700P), + DVB_USB_DEV(DIBCOM, DIBCOM_STK7700P_PC), + DVB_USB_DEV(HAUPPAUGE, HAUPPAUGE_NOVA_T_500), + DVB_USB_DEV(HAUPPAUGE, HAUPPAUGE_NOVA_T_500_2), + DVB_USB_DEV(HAUPPAUGE, HAUPPAUGE_NOVA_T_STICK), + DVB_USB_DEV(AVERMEDIA, AVERMEDIA_VOLAR), + DVB_USB_DEV(COMPRO, COMPRO_VIDEOMATE_U500), + DVB_USB_DEV(UNIWILL, UNIWILL_STK7700P), + DVB_USB_DEV(LEADTEK, LEADTEK_WINFAST_DTV_DONGLE_STK7700P), + DVB_USB_DEV(HAUPPAUGE, HAUPPAUGE_NOVA_T_STICK_2), + DVB_USB_DEV(AVERMEDIA, AVERMEDIA_VOLAR_2), + DVB_USB_DEV(PINNACLE, PINNACLE_PCTV2000E), + DVB_USB_DEV(TERRATEC, TERRATEC_CINERGY_DT_XS_DIVERSITY), + DVB_USB_DEV(HAUPPAUGE, HAUPPAUGE_NOVA_TD_STICK), + DVB_USB_DEV(DIBCOM, DIBCOM_STK7700D), + DVB_USB_DEV(DIBCOM, DIBCOM_STK7070P), + DVB_USB_DEV(PINNACLE, PINNACLE_PCTV_DVB_T_FLASH), + DVB_USB_DEV(DIBCOM, DIBCOM_STK7070PD), + DVB_USB_DEV(PINNACLE, PINNACLE_PCTV_DUAL_DIVERSITY_DVB_T), + DVB_USB_DEV(COMPRO, COMPRO_VIDEOMATE_U500_PC), + DVB_USB_DEV(AVERMEDIA, AVERMEDIA_EXPRESS), + DVB_USB_DEV(GIGABYTE, GIGABYTE_U7000), + DVB_USB_DEV(ULTIMA_ELECTRONIC, ULTIMA_ARTEC_T14BR), + DVB_USB_DEV(ASUS, ASUS_U3000), + DVB_USB_DEV(ASUS, ASUS_U3100), + DVB_USB_DEV(HAUPPAUGE, HAUPPAUGE_NOVA_T_STICK_3), + DVB_USB_DEV(HAUPPAUGE, HAUPPAUGE_MYTV_T), + DVB_USB_DEV(TERRATEC, TERRATEC_CINERGY_HT_USB_XE), + DVB_USB_DEV(PINNACLE, PINNACLE_EXPRESSCARD_320CX), + DVB_USB_DEV(PINNACLE, PINNACLE_PCTV72E), + DVB_USB_DEV(PINNACLE, PINNACLE_PCTV73E), + DVB_USB_DEV(YUAN, YUAN_EC372S), + DVB_USB_DEV(TERRATEC, TERRATEC_CINERGY_HT_EXPRESS), + DVB_USB_DEV(TERRATEC, TERRATEC_CINERGY_T_XXS), + DVB_USB_DEV(LEADTEK, LEADTEK_WINFAST_DTV_DONGLE_STK7700P_2), + DVB_USB_DEV(HAUPPAUGE, HAUPPAUGE_NOVA_TD_STICK_52009), + DVB_USB_DEV(HAUPPAUGE, HAUPPAUGE_NOVA_T_500_3), + DVB_USB_DEV(GIGABYTE, GIGABYTE_U8000), + DVB_USB_DEV(YUAN, YUAN_STK7700PH), + DVB_USB_DEV(ASUS, ASUS_U3000H), + DVB_USB_DEV(PINNACLE, PINNACLE_PCTV801E), + DVB_USB_DEV(PINNACLE, PINNACLE_PCTV801E_SE), + DVB_USB_DEV(TERRATEC, TERRATEC_CINERGY_T_EXPRESS), + DVB_USB_DEV(TERRATEC, TERRATEC_CINERGY_DT_XS_DIVERSITY_2), + DVB_USB_DEV(SONY, SONY_PLAYTV), + DVB_USB_DEV(YUAN, YUAN_PD378S), + DVB_USB_DEV(HAUPPAUGE, HAUPPAUGE_TIGER_ATSC), + DVB_USB_DEV(HAUPPAUGE, HAUPPAUGE_TIGER_ATSC_B210), + DVB_USB_DEV(YUAN, YUAN_MC770), + DVB_USB_DEV(ELGATO, ELGATO_EYETV_DTT), + DVB_USB_DEV(ELGATO, ELGATO_EYETV_DTT_Dlx), + DVB_USB_DEV(LEADTEK, LEADTEK_WINFAST_DTV_DONGLE_H), + DVB_USB_DEV(TERRATEC, TERRATEC_T3), + DVB_USB_DEV(TERRATEC, TERRATEC_T5), + DVB_USB_DEV(YUAN, YUAN_STK7700D), + DVB_USB_DEV(YUAN, YUAN_STK7700D_2), + DVB_USB_DEV(PINNACLE, PINNACLE_PCTV73A), + DVB_USB_DEV(PCTV, PCTV_PINNACLE_PCTV73ESE), + DVB_USB_DEV(PCTV, PCTV_PINNACLE_PCTV282E), + DVB_USB_DEV(DIBCOM, DIBCOM_STK7770P), + DVB_USB_DEV(TERRATEC, TERRATEC_CINERGY_T_XXS_2), + DVB_USB_DEV(DIBCOM, DIBCOM_STK807XPVR), + DVB_USB_DEV(DIBCOM, DIBCOM_STK807XP), + DVB_USB_DEV_VER(PIXELVIEW, PIXELVIEW_SBTVD, 0x000, 0x3f00), + DVB_USB_DEV(EVOLUTEPC, EVOLUTEPC_TVWAY_PLUS), + DVB_USB_DEV(PINNACLE, PINNACLE_PCTV73ESE), + DVB_USB_DEV(PINNACLE, PINNACLE_PCTV282E), + DVB_USB_DEV(DIBCOM, DIBCOM_STK8096GP), + DVB_USB_DEV(ELGATO, ELGATO_EYETV_DIVERSITY), + DVB_USB_DEV(DIBCOM, DIBCOM_NIM9090M), + DVB_USB_DEV(DIBCOM, DIBCOM_NIM8096MD), + DVB_USB_DEV(DIBCOM, DIBCOM_NIM9090MD), + DVB_USB_DEV(DIBCOM, DIBCOM_NIM7090), + DVB_USB_DEV(DIBCOM, DIBCOM_TFE7090PVR), + DVB_USB_DEV(TECHNISAT, TECHNISAT_AIRSTAR_TELESTICK_2), + DVB_USB_DEV(MEDION, MEDION_CREATIX_CTX1921), + DVB_USB_DEV(PINNACLE, PINNACLE_PCTV340E), + DVB_USB_DEV(PINNACLE, PINNACLE_PCTV340E_SE), + DVB_USB_DEV(DIBCOM, DIBCOM_TFE7790P), + DVB_USB_DEV(DIBCOM, DIBCOM_TFE8096P), + DVB_USB_DEV(ELGATO, ELGATO_EYETV_DTT_2), + DVB_USB_DEV(PCTV, PCTV_2002E), + DVB_USB_DEV(PCTV, PCTV_2002E_SE), + DVB_USB_DEV(PCTV, PCTV_DIBCOM_STK8096PVR), + DVB_USB_DEV(DIBCOM, DIBCOM_STK8096PVR), + DVB_USB_DEV(HAMA, HAMA_DVBT_HYBRID), + DVB_USB_DEV(MICROSOFT, MICROSOFT_XBOX_ONE_TUNER), + { } }; + MODULE_DEVICE_TABLE(usb, dib0700_usb_id_table); #define DIB0700_DEFAULT_DEVICE_PROPERTIES \ @@ -3962,35 +4050,35 @@ struct dvb_usb_device_properties dib0700_devices[] = { .num_device_descs = 8, .devices = { { "DiBcom STK7700P reference design", - { &dib0700_usb_id_table[0], &dib0700_usb_id_table[1] }, + { &dib0700_usb_id_table[DIBCOM_STK7700P], &dib0700_usb_id_table[DIBCOM_STK7700P_PC] }, { NULL }, }, { "Hauppauge Nova-T Stick", - { &dib0700_usb_id_table[4], &dib0700_usb_id_table[9], NULL }, + { &dib0700_usb_id_table[HAUPPAUGE_NOVA_T_STICK], &dib0700_usb_id_table[HAUPPAUGE_NOVA_T_STICK_2], NULL }, { NULL }, }, { "AVerMedia AVerTV DVB-T Volar", - { &dib0700_usb_id_table[5], &dib0700_usb_id_table[10] }, + { &dib0700_usb_id_table[AVERMEDIA_VOLAR], &dib0700_usb_id_table[AVERMEDIA_VOLAR_2] }, { NULL }, }, { "Compro Videomate U500", - { &dib0700_usb_id_table[6], &dib0700_usb_id_table[19] }, + { &dib0700_usb_id_table[COMPRO_VIDEOMATE_U500], &dib0700_usb_id_table[COMPRO_VIDEOMATE_U500_PC] }, { NULL }, }, { "Uniwill STK7700P based (Hama and others)", - { &dib0700_usb_id_table[7], NULL }, + { &dib0700_usb_id_table[UNIWILL_STK7700P], NULL }, { NULL }, }, { "Leadtek Winfast DTV Dongle (STK7700P based)", - { &dib0700_usb_id_table[8], &dib0700_usb_id_table[34] }, + { &dib0700_usb_id_table[LEADTEK_WINFAST_DTV_DONGLE_STK7700P], &dib0700_usb_id_table[LEADTEK_WINFAST_DTV_DONGLE_STK7700P_2] }, { NULL }, }, { "AVerMedia AVerTV DVB-T Express", - { &dib0700_usb_id_table[20] }, + { &dib0700_usb_id_table[AVERMEDIA_EXPRESS] }, { NULL }, }, { "Gigabyte U7000", - { &dib0700_usb_id_table[21], NULL }, + { &dib0700_usb_id_table[GIGABYTE_U7000], NULL }, { NULL }, } }, @@ -4030,7 +4118,7 @@ struct dvb_usb_device_properties dib0700_devices[] = { .num_device_descs = 1, .devices = { { "Hauppauge Nova-T 500 Dual DVB-T", - { &dib0700_usb_id_table[2], &dib0700_usb_id_table[3], NULL }, + { &dib0700_usb_id_table[HAUPPAUGE_NOVA_T_500], &dib0700_usb_id_table[HAUPPAUGE_NOVA_T_500_2], NULL }, { NULL }, }, }, @@ -4078,23 +4166,23 @@ struct dvb_usb_device_properties dib0700_devices[] = { .num_device_descs = 5, .devices = { { "Pinnacle PCTV 2000e", - { &dib0700_usb_id_table[11], NULL }, + { &dib0700_usb_id_table[PINNACLE_PCTV2000E], NULL }, { NULL }, }, { "Terratec Cinergy DT XS Diversity", - { &dib0700_usb_id_table[12], NULL }, + { &dib0700_usb_id_table[TERRATEC_CINERGY_DT_XS_DIVERSITY], NULL }, { NULL }, }, { "Hauppauge Nova-TD Stick/Elgato Eye-TV Diversity", - { &dib0700_usb_id_table[13], NULL }, + { &dib0700_usb_id_table[HAUPPAUGE_NOVA_TD_STICK], NULL }, { NULL }, }, { "DiBcom STK7700D reference design", - { &dib0700_usb_id_table[14], NULL }, + { &dib0700_usb_id_table[DIBCOM_STK7700D], NULL }, { NULL }, }, { "YUAN High-Tech DiBcom STK7700D", - { &dib0700_usb_id_table[55], NULL }, + { &dib0700_usb_id_table[YUAN_STK7700D_2], NULL }, { NULL }, }, @@ -4131,15 +4219,15 @@ struct dvb_usb_device_properties dib0700_devices[] = { .num_device_descs = 3, .devices = { { "ASUS My Cinema U3000 Mini DVBT Tuner", - { &dib0700_usb_id_table[23], NULL }, + { &dib0700_usb_id_table[ASUS_U3000], NULL }, { NULL }, }, { "Yuan EC372S", - { &dib0700_usb_id_table[31], NULL }, + { &dib0700_usb_id_table[YUAN_EC372S], NULL }, { NULL }, }, { "Terratec Cinergy T Express", - { &dib0700_usb_id_table[42], NULL }, + { &dib0700_usb_id_table[TERRATEC_CINERGY_T_EXPRESS], NULL }, { NULL }, } }, @@ -4176,51 +4264,51 @@ struct dvb_usb_device_properties dib0700_devices[] = { .num_device_descs = 12, .devices = { { "DiBcom STK7070P reference design", - { &dib0700_usb_id_table[15], NULL }, + { &dib0700_usb_id_table[DIBCOM_STK7070P], NULL }, { NULL }, }, { "Pinnacle PCTV DVB-T Flash Stick", - { &dib0700_usb_id_table[16], NULL }, + { &dib0700_usb_id_table[PINNACLE_PCTV_DVB_T_FLASH], NULL }, { NULL }, }, { "Artec T14BR DVB-T", - { &dib0700_usb_id_table[22], NULL }, + { &dib0700_usb_id_table[ULTIMA_ARTEC_T14BR], NULL }, { NULL }, }, { "ASUS My Cinema U3100 Mini DVBT Tuner", - { &dib0700_usb_id_table[24], NULL }, + { &dib0700_usb_id_table[ASUS_U3100], NULL }, { NULL }, }, { "Hauppauge Nova-T Stick", - { &dib0700_usb_id_table[25], NULL }, + { &dib0700_usb_id_table[HAUPPAUGE_NOVA_T_STICK_3], NULL }, { NULL }, }, { "Hauppauge Nova-T MyTV.t", - { &dib0700_usb_id_table[26], NULL }, + { &dib0700_usb_id_table[HAUPPAUGE_MYTV_T], NULL }, { NULL }, }, { "Pinnacle PCTV 72e", - { &dib0700_usb_id_table[29], NULL }, + { &dib0700_usb_id_table[PINNACLE_PCTV72E], NULL }, { NULL }, }, { "Pinnacle PCTV 73e", - { &dib0700_usb_id_table[30], NULL }, + { &dib0700_usb_id_table[PINNACLE_PCTV73E], NULL }, { NULL }, }, { "Elgato EyeTV DTT", - { &dib0700_usb_id_table[49], NULL }, + { &dib0700_usb_id_table[ELGATO_EYETV_DTT], NULL }, { NULL }, }, { "Yuan PD378S", - { &dib0700_usb_id_table[45], NULL }, + { &dib0700_usb_id_table[YUAN_PD378S], NULL }, { NULL }, }, { "Elgato EyeTV Dtt Dlx PD378S", - { &dib0700_usb_id_table[50], NULL }, + { &dib0700_usb_id_table[ELGATO_EYETV_DTT_Dlx], NULL }, { NULL }, }, { "Elgato EyeTV DTT rev. 2", - { &dib0700_usb_id_table[80], NULL }, + { &dib0700_usb_id_table[ELGATO_EYETV_DTT_2], NULL }, { NULL }, }, }, @@ -4257,15 +4345,15 @@ struct dvb_usb_device_properties dib0700_devices[] = { .num_device_descs = 3, .devices = { { "Pinnacle PCTV 73A", - { &dib0700_usb_id_table[56], NULL }, + { &dib0700_usb_id_table[PINNACLE_PCTV73A], NULL }, { NULL }, }, { "Pinnacle PCTV 73e SE", - { &dib0700_usb_id_table[57], &dib0700_usb_id_table[65], NULL }, + { &dib0700_usb_id_table[PCTV_PINNACLE_PCTV73ESE], &dib0700_usb_id_table[PINNACLE_PCTV73ESE], NULL }, { NULL }, }, { "Pinnacle PCTV 282e", - { &dib0700_usb_id_table[58], &dib0700_usb_id_table[66], NULL }, + { &dib0700_usb_id_table[PCTV_PINNACLE_PCTV282E], &dib0700_usb_id_table[PINNACLE_PCTV282E], NULL }, { NULL }, }, }, @@ -4314,15 +4402,15 @@ struct dvb_usb_device_properties dib0700_devices[] = { .num_device_descs = 3, .devices = { { "Hauppauge Nova-TD Stick (52009)", - { &dib0700_usb_id_table[35], NULL }, + { &dib0700_usb_id_table[HAUPPAUGE_NOVA_TD_STICK_52009], NULL }, { NULL }, }, { "PCTV 2002e", - { &dib0700_usb_id_table[81], NULL }, + { &dib0700_usb_id_table[PCTV_2002E], NULL }, { NULL }, }, { "PCTV 2002e SE", - { &dib0700_usb_id_table[82], NULL }, + { &dib0700_usb_id_table[PCTV_2002E_SE], NULL }, { NULL }, }, }, @@ -4371,24 +4459,24 @@ struct dvb_usb_device_properties dib0700_devices[] = { .num_device_descs = 5, .devices = { { "DiBcom STK7070PD reference design", - { &dib0700_usb_id_table[17], NULL }, + { &dib0700_usb_id_table[DIBCOM_STK7070PD], NULL }, { NULL }, }, { "Pinnacle PCTV Dual DVB-T Diversity Stick", - { &dib0700_usb_id_table[18], NULL }, + { &dib0700_usb_id_table[PINNACLE_PCTV_DUAL_DIVERSITY_DVB_T], NULL }, { NULL }, }, { "Hauppauge Nova-TD-500 (84xxx)", - { &dib0700_usb_id_table[36], NULL }, + { &dib0700_usb_id_table[HAUPPAUGE_NOVA_T_500_3], NULL }, { NULL }, }, { "Terratec Cinergy DT USB XS Diversity/ T5", - { &dib0700_usb_id_table[43], - &dib0700_usb_id_table[53], NULL}, + { &dib0700_usb_id_table[TERRATEC_CINERGY_DT_XS_DIVERSITY_2], + &dib0700_usb_id_table[TERRATEC_T5], NULL}, { NULL }, }, { "Sony PlayTV", - { &dib0700_usb_id_table[44], NULL }, + { &dib0700_usb_id_table[SONY_PLAYTV], NULL }, { NULL }, }, }, @@ -4437,7 +4525,7 @@ struct dvb_usb_device_properties dib0700_devices[] = { .num_device_descs = 1, .devices = { { "Elgato EyeTV Diversity", - { &dib0700_usb_id_table[68], NULL }, + { &dib0700_usb_id_table[ELGATO_EYETV_DIVERSITY], NULL }, { NULL }, }, }, @@ -4474,43 +4562,43 @@ struct dvb_usb_device_properties dib0700_devices[] = { .num_device_descs = 10, .devices = { { "Terratec Cinergy HT USB XE", - { &dib0700_usb_id_table[27], NULL }, + { &dib0700_usb_id_table[TERRATEC_CINERGY_HT_USB_XE], NULL }, { NULL }, }, { "Pinnacle Expresscard 320cx", - { &dib0700_usb_id_table[28], NULL }, + { &dib0700_usb_id_table[PINNACLE_EXPRESSCARD_320CX], NULL }, { NULL }, }, { "Terratec Cinergy HT Express", - { &dib0700_usb_id_table[32], NULL }, + { &dib0700_usb_id_table[TERRATEC_CINERGY_HT_EXPRESS], NULL }, { NULL }, }, { "Gigabyte U8000-RH", - { &dib0700_usb_id_table[37], NULL }, + { &dib0700_usb_id_table[GIGABYTE_U8000], NULL }, { NULL }, }, { "YUAN High-Tech STK7700PH", - { &dib0700_usb_id_table[38], NULL }, + { &dib0700_usb_id_table[YUAN_STK7700PH], NULL }, { NULL }, }, { "Asus My Cinema-U3000Hybrid", - { &dib0700_usb_id_table[39], NULL }, + { &dib0700_usb_id_table[ASUS_U3000H], NULL }, { NULL }, }, { "YUAN High-Tech MC770", - { &dib0700_usb_id_table[48], NULL }, + { &dib0700_usb_id_table[YUAN_MC770], NULL }, { NULL }, }, { "Leadtek WinFast DTV Dongle H", - { &dib0700_usb_id_table[51], NULL }, + { &dib0700_usb_id_table[LEADTEK_WINFAST_DTV_DONGLE_H], NULL }, { NULL }, }, { "YUAN High-Tech STK7700D", - { &dib0700_usb_id_table[54], NULL }, + { &dib0700_usb_id_table[YUAN_STK7700D], NULL }, { NULL }, }, { "Hama DVB=T Hybrid USB Stick", - { &dib0700_usb_id_table[85], NULL }, + { &dib0700_usb_id_table[HAMA_DVBT_HYBRID], NULL }, { NULL }, }, }, @@ -4542,11 +4630,11 @@ struct dvb_usb_device_properties dib0700_devices[] = { .num_device_descs = 2, .devices = { { "Pinnacle PCTV HD Pro USB Stick", - { &dib0700_usb_id_table[40], NULL }, + { &dib0700_usb_id_table[PINNACLE_PCTV801E], NULL }, { NULL }, }, { "Pinnacle PCTV HD USB Stick", - { &dib0700_usb_id_table[41], NULL }, + { &dib0700_usb_id_table[PINNACLE_PCTV801E_SE], NULL }, { NULL }, }, }, @@ -4578,11 +4666,11 @@ struct dvb_usb_device_properties dib0700_devices[] = { .num_device_descs = 2, .devices = { { "Hauppauge ATSC MiniCard (B200)", - { &dib0700_usb_id_table[46], NULL }, + { &dib0700_usb_id_table[HAUPPAUGE_TIGER_ATSC], NULL }, { NULL }, }, { "Hauppauge ATSC MiniCard (B210)", - { &dib0700_usb_id_table[47], NULL }, + { &dib0700_usb_id_table[HAUPPAUGE_TIGER_ATSC_B210], NULL }, { NULL }, }, }, @@ -4608,21 +4696,21 @@ struct dvb_usb_device_properties dib0700_devices[] = { .num_device_descs = 4, .devices = { { "DiBcom STK7770P reference design", - { &dib0700_usb_id_table[59], NULL }, + { &dib0700_usb_id_table[DIBCOM_STK7770P], NULL }, { NULL }, }, { "Terratec Cinergy T USB XXS (HD)/ T3", - { &dib0700_usb_id_table[33], - &dib0700_usb_id_table[52], - &dib0700_usb_id_table[60], NULL}, + { &dib0700_usb_id_table[TERRATEC_CINERGY_T_XXS], + &dib0700_usb_id_table[TERRATEC_T3], + &dib0700_usb_id_table[TERRATEC_CINERGY_T_XXS_2], NULL}, { NULL }, }, { "TechniSat AirStar TeleStick 2", - { &dib0700_usb_id_table[74], NULL }, + { &dib0700_usb_id_table[TECHNISAT_AIRSTAR_TELESTICK_2], NULL }, { NULL }, }, { "Medion CTX1921 DVB-T USB", - { &dib0700_usb_id_table[75], NULL }, + { &dib0700_usb_id_table[MEDION_CREATIX_CTX1921], NULL }, { NULL }, }, }, @@ -4658,15 +4746,15 @@ struct dvb_usb_device_properties dib0700_devices[] = { .num_device_descs = 3, .devices = { { "DiBcom STK807xP reference design", - { &dib0700_usb_id_table[62], NULL }, + { &dib0700_usb_id_table[DIBCOM_STK807XP], NULL }, { NULL }, }, { "Prolink Pixelview SBTVD", - { &dib0700_usb_id_table[63], NULL }, + { &dib0700_usb_id_table[PIXELVIEW_SBTVD], NULL }, { NULL }, }, { "EvolutePC TVWay+", - { &dib0700_usb_id_table[64], NULL }, + { &dib0700_usb_id_table[EVOLUTEPC_TVWAY_PLUS], NULL }, { NULL }, }, }, @@ -4715,7 +4803,7 @@ struct dvb_usb_device_properties dib0700_devices[] = { .num_device_descs = 1, .devices = { { "DiBcom STK807xPVR reference design", - { &dib0700_usb_id_table[61], NULL }, + { &dib0700_usb_id_table[DIBCOM_STK807XPVR], NULL }, { NULL }, }, }, @@ -4752,7 +4840,7 @@ struct dvb_usb_device_properties dib0700_devices[] = { .num_device_descs = 1, .devices = { { "DiBcom STK8096GP reference design", - { &dib0700_usb_id_table[67], NULL }, + { &dib0700_usb_id_table[DIBCOM_STK8096GP], NULL }, { NULL }, }, }, @@ -4789,7 +4877,7 @@ struct dvb_usb_device_properties dib0700_devices[] = { .num_device_descs = 1, .devices = { { "DiBcom STK9090M reference design", - { &dib0700_usb_id_table[69], NULL }, + { &dib0700_usb_id_table[DIBCOM_NIM9090M], NULL }, { NULL }, }, }, @@ -4826,7 +4914,7 @@ struct dvb_usb_device_properties dib0700_devices[] = { .num_device_descs = 1, .devices = { { "DiBcom NIM8096MD reference design", - { &dib0700_usb_id_table[70], NULL }, + { &dib0700_usb_id_table[DIBCOM_NIM8096MD], NULL }, { NULL }, }, }, @@ -4863,7 +4951,7 @@ struct dvb_usb_device_properties dib0700_devices[] = { .num_device_descs = 1, .devices = { { "DiBcom NIM9090MD reference design", - { &dib0700_usb_id_table[71], NULL }, + { &dib0700_usb_id_table[DIBCOM_NIM9090MD], NULL }, { NULL }, }, }, @@ -4900,7 +4988,7 @@ struct dvb_usb_device_properties dib0700_devices[] = { .num_device_descs = 1, .devices = { { "DiBcom NIM7090 reference design", - { &dib0700_usb_id_table[72], NULL }, + { &dib0700_usb_id_table[DIBCOM_NIM7090], NULL }, { NULL }, }, }, @@ -4951,7 +5039,7 @@ struct dvb_usb_device_properties dib0700_devices[] = { .num_device_descs = 1, .devices = { { "DiBcom TFE7090PVR reference design", - { &dib0700_usb_id_table[73], NULL }, + { &dib0700_usb_id_table[DIBCOM_TFE7090PVR], NULL }, { NULL }, }, }, @@ -4983,11 +5071,11 @@ struct dvb_usb_device_properties dib0700_devices[] = { .num_device_descs = 2, .devices = { { "Pinnacle PCTV 340e HD Pro USB Stick", - { &dib0700_usb_id_table[76], NULL }, + { &dib0700_usb_id_table[PINNACLE_PCTV340E], NULL }, { NULL }, }, { "Pinnacle PCTV Hybrid Stick Solo", - { &dib0700_usb_id_table[77], NULL }, + { &dib0700_usb_id_table[PINNACLE_PCTV340E_SE], NULL }, { NULL }, }, }, @@ -5023,7 +5111,7 @@ struct dvb_usb_device_properties dib0700_devices[] = { .num_device_descs = 1, .devices = { { "DiBcom TFE7790P reference design", - { &dib0700_usb_id_table[78], NULL }, + { &dib0700_usb_id_table[DIBCOM_TFE7790P], NULL }, { NULL }, }, }, @@ -5061,7 +5149,7 @@ struct dvb_usb_device_properties dib0700_devices[] = { .num_device_descs = 1, .devices = { { "DiBcom TFE8096P reference design", - { &dib0700_usb_id_table[79], NULL }, + { &dib0700_usb_id_table[DIBCOM_TFE8096P], NULL }, { NULL }, }, }, @@ -5114,8 +5202,8 @@ struct dvb_usb_device_properties dib0700_devices[] = { .num_device_descs = 1, .devices = { { "DiBcom STK8096-PVR reference design", - { &dib0700_usb_id_table[83], - &dib0700_usb_id_table[84], NULL}, + { &dib0700_usb_id_table[PCTV_DIBCOM_STK8096PVR], + &dib0700_usb_id_table[DIBCOM_STK8096PVR], NULL}, { NULL }, }, }, @@ -5145,7 +5233,7 @@ struct dvb_usb_device_properties dib0700_devices[] = { .num_device_descs = 1, .devices = { { "Microsoft Xbox One Digital TV Tuner", - { &dib0700_usb_id_table[86], NULL }, + { &dib0700_usb_id_table[MICROSOFT_XBOX_ONE_TUNER], NULL }, { NULL }, }, }, diff --git a/drivers/media/usb/dvb-usb/dibusb-mb.c b/drivers/media/usb/dvb-usb/dibusb-mb.c index e9dc27f73970..2cd88cab4c98 100644 --- a/drivers/media/usb/dvb-usb/dibusb-mb.c +++ b/drivers/media/usb/dvb-usb/dibusb-mb.c @@ -121,56 +121,77 @@ static int dibusb_probe(struct usb_interface *intf, } /* do not change the order of the ID table */ -static struct usb_device_id dibusb_dib3000mb_table [] = { -/* 00 */ { USB_DEVICE(USB_VID_WIDEVIEW, USB_PID_AVERMEDIA_DVBT_USB_COLD) }, -/* 01 */ { USB_DEVICE(USB_VID_WIDEVIEW, USB_PID_AVERMEDIA_DVBT_USB_WARM) }, -/* 02 */ { USB_DEVICE(USB_VID_COMPRO, USB_PID_COMPRO_DVBU2000_COLD) }, -/* 03 */ { USB_DEVICE(USB_VID_COMPRO, USB_PID_COMPRO_DVBU2000_WARM) }, -/* 04 */ { USB_DEVICE(USB_VID_COMPRO_UNK, USB_PID_COMPRO_DVBU2000_UNK_COLD) }, -/* 05 */ { USB_DEVICE(USB_VID_DIBCOM, USB_PID_DIBCOM_MOD3000_COLD) }, -/* 06 */ { USB_DEVICE(USB_VID_DIBCOM, USB_PID_DIBCOM_MOD3000_WARM) }, -/* 07 */ { USB_DEVICE(USB_VID_EMPIA, USB_PID_KWORLD_VSTREAM_COLD) }, -/* 08 */ { USB_DEVICE(USB_VID_EMPIA, USB_PID_KWORLD_VSTREAM_WARM) }, -/* 09 */ { USB_DEVICE(USB_VID_GRANDTEC, USB_PID_GRANDTEC_DVBT_USB_COLD) }, -/* 10 */ { USB_DEVICE(USB_VID_GRANDTEC, USB_PID_GRANDTEC_DVBT_USB_WARM) }, -/* 11 */ { USB_DEVICE(USB_VID_GRANDTEC, USB_PID_DIBCOM_MOD3000_COLD) }, -/* 12 */ { USB_DEVICE(USB_VID_GRANDTEC, USB_PID_DIBCOM_MOD3000_WARM) }, -/* 13 */ { USB_DEVICE(USB_VID_HYPER_PALTEK, USB_PID_UNK_HYPER_PALTEK_COLD) }, -/* 14 */ { USB_DEVICE(USB_VID_HYPER_PALTEK, USB_PID_UNK_HYPER_PALTEK_WARM) }, -/* 15 */ { USB_DEVICE(USB_VID_VISIONPLUS, USB_PID_TWINHAN_VP7041_COLD) }, -/* 16 */ { USB_DEVICE(USB_VID_VISIONPLUS, USB_PID_TWINHAN_VP7041_WARM) }, -/* 17 */ { USB_DEVICE(USB_VID_TWINHAN, USB_PID_TWINHAN_VP7041_COLD) }, -/* 18 */ { USB_DEVICE(USB_VID_TWINHAN, USB_PID_TWINHAN_VP7041_WARM) }, -/* 19 */ { USB_DEVICE(USB_VID_ULTIMA_ELECTRONIC, USB_PID_ULTIMA_TVBOX_COLD) }, -/* 20 */ { USB_DEVICE(USB_VID_ULTIMA_ELECTRONIC, USB_PID_ULTIMA_TVBOX_WARM) }, -/* 21 */ { USB_DEVICE(USB_VID_ULTIMA_ELECTRONIC, USB_PID_ULTIMA_TVBOX_AN2235_COLD) }, -/* 22 */ { USB_DEVICE(USB_VID_ULTIMA_ELECTRONIC, USB_PID_ULTIMA_TVBOX_AN2235_WARM) }, -/* 23 */ { USB_DEVICE(USB_VID_ADSTECH, USB_PID_ADSTECH_USB2_COLD) }, - -/* device ID with default DIBUSB2_0-firmware and with the hacked firmware */ -/* 24 */ { USB_DEVICE(USB_VID_ADSTECH, USB_PID_ADSTECH_USB2_WARM) }, -/* 25 */ { USB_DEVICE(USB_VID_KYE, USB_PID_KYE_DVB_T_COLD) }, -/* 26 */ { USB_DEVICE(USB_VID_KYE, USB_PID_KYE_DVB_T_WARM) }, - -/* 27 */ { USB_DEVICE(USB_VID_KWORLD, USB_PID_KWORLD_VSTREAM_COLD) }, - -/* 28 */ { USB_DEVICE(USB_VID_ULTIMA_ELECTRONIC, USB_PID_ULTIMA_TVBOX_USB2_COLD) }, -/* 29 */ { USB_DEVICE(USB_VID_ULTIMA_ELECTRONIC, USB_PID_ULTIMA_TVBOX_USB2_WARM) }, - -/* - * XXX: As Artec just 'forgot' to program the EEPROM on some Artec T1 devices - * we don't catch these faulty IDs (namely 'Cypress FX1 USB controller') that - * have been left on the device. If you don't have such a device but an Artec - * device that's supposed to work with this driver but is not detected by it, - * free to enable CONFIG_DVB_USB_DIBUSB_MB_FAULTY via your kernel config. - */ +enum { + WIDEVIEW_DVBT_USB_COLD, + WIDEVIEW_DVBT_USB_WARM, + COMPRO_DVBU2000_COLD, + COMPRO_DVBU2000_WARM, + COMPRO_DVBU2000_UNK_COLD, + DIBCOM_MOD3000_COLD, + DIBCOM_MOD3000_WARM, + EMPIA_VSTREAM_COLD, + EMPIA_VSTREAM_WARM, + GRANDTEC_DVBT_USB_COLD, + GRANDTEC_DVBT_USB_WARM, + GRANDTEC_MOD3000_COLD, + GRANDTEC_MOD3000_WARM, + UNK_HYPER_PALTEK_COLD, + UNK_HYPER_PALTEK_WARM, + VISIONPLUS_VP7041_COLD, + VISIONPLUS_VP7041_WARM, + TWINHAN_VP7041_COLD, + TWINHAN_VP7041_WARM, + ULTIMA_TVBOX_COLD, + ULTIMA_TVBOX_WARM, + ULTIMA_TVBOX_AN2235_COLD, + ULTIMA_TVBOX_AN2235_WARM, + ADSTECH_USB2_COLD, + ADSTECH_USB2_WARM, + KYE_DVB_T_COLD, + KYE_DVB_T_WARM, + KWORLD_VSTREAM_COLD, + ULTIMA_TVBOX_USB2_COLD, + ULTIMA_TVBOX_USB2_WARM, + ULTIMA_TVBOX_ANCHOR_COLD, +}; +static struct usb_device_id dibusb_dib3000mb_table[] = { + DVB_USB_DEV(WIDEVIEW, WIDEVIEW_DVBT_USB_COLD), + DVB_USB_DEV(WIDEVIEW, WIDEVIEW_DVBT_USB_WARM), + DVB_USB_DEV(COMPRO, COMPRO_DVBU2000_COLD), + DVB_USB_DEV(COMPRO, COMPRO_DVBU2000_WARM), + DVB_USB_DEV(COMPRO_UNK, COMPRO_DVBU2000_UNK_COLD), + DVB_USB_DEV(DIBCOM, DIBCOM_MOD3000_COLD), + DVB_USB_DEV(DIBCOM, DIBCOM_MOD3000_WARM), + DVB_USB_DEV(EMPIA, EMPIA_VSTREAM_COLD), + DVB_USB_DEV(EMPIA, EMPIA_VSTREAM_WARM), + DVB_USB_DEV(GRANDTEC, GRANDTEC_DVBT_USB_COLD), + DVB_USB_DEV(GRANDTEC, GRANDTEC_DVBT_USB_WARM), + DVB_USB_DEV(GRANDTEC, GRANDTEC_MOD3000_COLD), + DVB_USB_DEV(GRANDTEC, GRANDTEC_MOD3000_WARM), + DVB_USB_DEV(HYPER_PALTEK, UNK_HYPER_PALTEK_COLD), + DVB_USB_DEV(HYPER_PALTEK, UNK_HYPER_PALTEK_WARM), + DVB_USB_DEV(VISIONPLUS, VISIONPLUS_VP7041_COLD), + DVB_USB_DEV(VISIONPLUS, VISIONPLUS_VP7041_WARM), + DVB_USB_DEV(TWINHAN, TWINHAN_VP7041_COLD), + DVB_USB_DEV(TWINHAN, TWINHAN_VP7041_WARM), + DVB_USB_DEV(ULTIMA_ELECTRONIC, ULTIMA_TVBOX_COLD), + DVB_USB_DEV(ULTIMA_ELECTRONIC, ULTIMA_TVBOX_WARM), + DVB_USB_DEV(ULTIMA_ELECTRONIC, ULTIMA_TVBOX_AN2235_COLD), + DVB_USB_DEV(ULTIMA_ELECTRONIC, ULTIMA_TVBOX_AN2235_WARM), + DVB_USB_DEV(ADSTECH, ADSTECH_USB2_COLD), + DVB_USB_DEV(ADSTECH, ADSTECH_USB2_WARM), + DVB_USB_DEV(KYE, KYE_DVB_T_COLD), + DVB_USB_DEV(KYE, KYE_DVB_T_WARM), + DVB_USB_DEV(KWORLD, KWORLD_VSTREAM_COLD), + DVB_USB_DEV(ULTIMA_ELECTRONIC, ULTIMA_TVBOX_USB2_COLD), + DVB_USB_DEV(ULTIMA_ELECTRONIC, ULTIMA_TVBOX_USB2_WARM), #ifdef CONFIG_DVB_USB_DIBUSB_MB_FAULTY -/* 30 */ { USB_DEVICE(USB_VID_ANCHOR, USB_PID_ULTIMA_TVBOX_ANCHOR_COLD) }, + DVB_USB_DEV(ANCHOR, ULTIMA_TVBOX_ANCHOR_COLD), #endif - - { } /* Terminating entry */ + { } }; + MODULE_DEVICE_TABLE (usb, dibusb_dib3000mb_table); static struct dvb_usb_device_properties dibusb1_1_properties = { @@ -226,40 +247,40 @@ static struct dvb_usb_device_properties dibusb1_1_properties = { .num_device_descs = 9, .devices = { { "AVerMedia AverTV DVBT USB1.1", - { &dibusb_dib3000mb_table[0], NULL }, - { &dibusb_dib3000mb_table[1], NULL }, + { &dibusb_dib3000mb_table[WIDEVIEW_DVBT_USB_COLD], NULL }, + { &dibusb_dib3000mb_table[WIDEVIEW_DVBT_USB_WARM], NULL }, }, { "Compro Videomate DVB-U2000 - DVB-T USB1.1 (please confirm to linux-dvb)", - { &dibusb_dib3000mb_table[2], &dibusb_dib3000mb_table[4], NULL}, - { &dibusb_dib3000mb_table[3], NULL }, + { &dibusb_dib3000mb_table[COMPRO_DVBU2000_COLD], &dibusb_dib3000mb_table[COMPRO_DVBU2000_UNK_COLD], NULL}, + { &dibusb_dib3000mb_table[COMPRO_DVBU2000_WARM], NULL }, }, { "DiBcom USB1.1 DVB-T reference design (MOD3000)", - { &dibusb_dib3000mb_table[5], NULL }, - { &dibusb_dib3000mb_table[6], NULL }, + { &dibusb_dib3000mb_table[DIBCOM_MOD3000_COLD], NULL }, + { &dibusb_dib3000mb_table[DIBCOM_MOD3000_WARM], NULL }, }, { "KWorld V-Stream XPERT DTV - DVB-T USB1.1", - { &dibusb_dib3000mb_table[7], NULL }, - { &dibusb_dib3000mb_table[8], NULL }, + { &dibusb_dib3000mb_table[EMPIA_VSTREAM_COLD], NULL }, + { &dibusb_dib3000mb_table[EMPIA_VSTREAM_WARM], NULL }, }, { "Grandtec USB1.1 DVB-T", - { &dibusb_dib3000mb_table[9], &dibusb_dib3000mb_table[11], NULL }, - { &dibusb_dib3000mb_table[10], &dibusb_dib3000mb_table[12], NULL }, + { &dibusb_dib3000mb_table[GRANDTEC_DVBT_USB_COLD], &dibusb_dib3000mb_table[GRANDTEC_MOD3000_COLD], NULL }, + { &dibusb_dib3000mb_table[GRANDTEC_DVBT_USB_WARM], &dibusb_dib3000mb_table[GRANDTEC_MOD3000_WARM], NULL }, }, { "Unknown USB1.1 DVB-T device ???? please report the name to the author", - { &dibusb_dib3000mb_table[13], NULL }, - { &dibusb_dib3000mb_table[14], NULL }, + { &dibusb_dib3000mb_table[UNK_HYPER_PALTEK_COLD], NULL }, + { &dibusb_dib3000mb_table[UNK_HYPER_PALTEK_WARM], NULL }, }, { "TwinhanDTV USB-Ter USB1.1 / Magic Box I / HAMA USB1.1 DVB-T device", - { &dibusb_dib3000mb_table[15], &dibusb_dib3000mb_table[17], NULL}, - { &dibusb_dib3000mb_table[16], &dibusb_dib3000mb_table[18], NULL}, + { &dibusb_dib3000mb_table[VISIONPLUS_VP7041_COLD], &dibusb_dib3000mb_table[TWINHAN_VP7041_COLD], NULL}, + { &dibusb_dib3000mb_table[VISIONPLUS_VP7041_WARM], &dibusb_dib3000mb_table[TWINHAN_VP7041_WARM], NULL}, }, { "Artec T1 USB1.1 TVBOX with AN2135", - { &dibusb_dib3000mb_table[19], NULL }, - { &dibusb_dib3000mb_table[20], NULL }, + { &dibusb_dib3000mb_table[ULTIMA_TVBOX_COLD], NULL }, + { &dibusb_dib3000mb_table[ULTIMA_TVBOX_WARM], NULL }, }, { "VideoWalker DVB-T USB", - { &dibusb_dib3000mb_table[25], NULL }, - { &dibusb_dib3000mb_table[26], NULL }, + { &dibusb_dib3000mb_table[KYE_DVB_T_COLD], NULL }, + { &dibusb_dib3000mb_table[KYE_DVB_T_WARM], NULL }, }, } }; @@ -319,12 +340,12 @@ static struct dvb_usb_device_properties dibusb1_1_an2235_properties = { #endif .devices = { { "Artec T1 USB1.1 TVBOX with AN2235", - { &dibusb_dib3000mb_table[21], NULL }, - { &dibusb_dib3000mb_table[22], NULL }, + { &dibusb_dib3000mb_table[ULTIMA_TVBOX_AN2235_COLD], NULL }, + { &dibusb_dib3000mb_table[ULTIMA_TVBOX_AN2235_WARM], NULL }, }, #ifdef CONFIG_DVB_USB_DIBUSB_MB_FAULTY { "Artec T1 USB1.1 TVBOX with AN2235 (faulty USB IDs)", - { &dibusb_dib3000mb_table[30], NULL }, + { &dibusb_dib3000mb_table[ULTIMA_TVBOX_ANCHOR_COLD], NULL }, { NULL }, }, { NULL }, @@ -384,11 +405,11 @@ static struct dvb_usb_device_properties dibusb2_0b_properties = { .num_device_descs = 2, .devices = { { "KWorld/ADSTech Instant DVB-T USB2.0", - { &dibusb_dib3000mb_table[23], NULL }, - { &dibusb_dib3000mb_table[24], NULL }, + { &dibusb_dib3000mb_table[ADSTECH_USB2_COLD], NULL }, + { &dibusb_dib3000mb_table[ADSTECH_USB2_WARM], NULL }, }, { "KWorld Xpert DVB-T USB2.0", - { &dibusb_dib3000mb_table[27], NULL }, + { &dibusb_dib3000mb_table[KWORLD_VSTREAM_COLD], NULL }, { NULL } }, { NULL }, @@ -446,8 +467,8 @@ static struct dvb_usb_device_properties artec_t1_usb2_properties = { .num_device_descs = 1, .devices = { { "Artec T1 USB2.0", - { &dibusb_dib3000mb_table[28], NULL }, - { &dibusb_dib3000mb_table[29], NULL }, + { &dibusb_dib3000mb_table[ULTIMA_TVBOX_USB2_COLD], NULL }, + { &dibusb_dib3000mb_table[ULTIMA_TVBOX_USB2_WARM], NULL }, }, { NULL }, } diff --git a/drivers/media/usb/dvb-usb/dibusb-mc.c b/drivers/media/usb/dvb-usb/dibusb-mc.c index e2689977c8c8..00cb016f6266 100644 --- a/drivers/media/usb/dvb-usb/dibusb-mc.c +++ b/drivers/media/usb/dvb-usb/dibusb-mc.c @@ -24,25 +24,45 @@ static int dibusb_mc_probe(struct usb_interface *intf, } /* do not change the order of the ID table */ -static struct usb_device_id dibusb_dib3000mc_table [] = { -/* 00 */ { USB_DEVICE(USB_VID_DIBCOM, USB_PID_DIBCOM_MOD3001_COLD) }, -/* 01 */ { USB_DEVICE(USB_VID_DIBCOM, USB_PID_DIBCOM_MOD3001_WARM) }, -/* 02 */ { USB_DEVICE(USB_VID_ULTIMA_ELECTRONIC, USB_PID_ULTIMA_TVBOX_USB2_COLD) }, -/* 03 */ { USB_DEVICE(USB_VID_ULTIMA_ELECTRONIC, USB_PID_ULTIMA_TVBOX_USB2_WARM) }, // ( ? ) -/* 04 */ { USB_DEVICE(USB_VID_LITEON, USB_PID_LITEON_DVB_T_COLD) }, -/* 05 */ { USB_DEVICE(USB_VID_LITEON, USB_PID_LITEON_DVB_T_WARM) }, -/* 06 */ { USB_DEVICE(USB_VID_EMPIA, USB_PID_DIGIVOX_MINI_SL_COLD) }, -/* 07 */ { USB_DEVICE(USB_VID_EMPIA, USB_PID_DIGIVOX_MINI_SL_WARM) }, -/* 08 */ { USB_DEVICE(USB_VID_GRANDTEC, USB_PID_GRANDTEC_DVBT_USB2_COLD) }, -/* 09 */ { USB_DEVICE(USB_VID_GRANDTEC, USB_PID_GRANDTEC_DVBT_USB2_WARM) }, -/* 10 */ { USB_DEVICE(USB_VID_ULTIMA_ELECTRONIC, USB_PID_ARTEC_T14_COLD) }, -/* 11 */ { USB_DEVICE(USB_VID_ULTIMA_ELECTRONIC, USB_PID_ARTEC_T14_WARM) }, -/* 12 */ { USB_DEVICE(USB_VID_LEADTEK, USB_PID_WINFAST_DTV_DONGLE_COLD) }, -/* 13 */ { USB_DEVICE(USB_VID_LEADTEK, USB_PID_WINFAST_DTV_DONGLE_WARM) }, -/* 14 */ { USB_DEVICE(USB_VID_HUMAX_COEX, USB_PID_DVB_T_USB_STICK_HIGH_SPEED_COLD) }, -/* 15 */ { USB_DEVICE(USB_VID_HUMAX_COEX, USB_PID_DVB_T_USB_STICK_HIGH_SPEED_WARM) }, - { } /* Terminating entry */ +enum { + DIBCOM_MOD3001_COLD, + DIBCOM_MOD3001_WARM, + ULTIMA_TVBOX_USB2_COLD, + ULTIMA_TVBOX_USB2_WARM, + LITEON_DVB_T_COLD, + LITEON_DVB_T_WARM, + EMPIA_DIGIVOX_MINI_SL_COLD, + EMPIA_DIGIVOX_MINI_SL_WARM, + GRANDTEC_DVBT_USB2_COLD, + GRANDTEC_DVBT_USB2_WARM, + ULTIMA_ARTEC_T14_COLD, + ULTIMA_ARTEC_T14_WARM, + LEADTEK_WINFAST_DTV_DONGLE_COLD, + LEADTEK_WINFAST_DTV_DONGLE_WARM, + HUMAX_DVB_T_STICK_HIGH_SPEED_COLD, + HUMAX_DVB_T_STICK_HIGH_SPEED_WARM, }; + +static struct usb_device_id dibusb_dib3000mc_table[] = { + DVB_USB_DEV(DIBCOM, DIBCOM_MOD3001_COLD), + DVB_USB_DEV(DIBCOM, DIBCOM_MOD3001_WARM), + DVB_USB_DEV(ULTIMA_ELECTRONIC, ULTIMA_TVBOX_USB2_COLD), + DVB_USB_DEV(ULTIMA_ELECTRONIC, ULTIMA_TVBOX_USB2_WARM), + DVB_USB_DEV(LITEON, LITEON_DVB_T_COLD), + DVB_USB_DEV(LITEON, LITEON_DVB_T_WARM), + DVB_USB_DEV(EMPIA, EMPIA_DIGIVOX_MINI_SL_COLD), + DVB_USB_DEV(EMPIA, EMPIA_DIGIVOX_MINI_SL_WARM), + DVB_USB_DEV(GRANDTEC, GRANDTEC_DVBT_USB2_COLD), + DVB_USB_DEV(GRANDTEC, GRANDTEC_DVBT_USB2_WARM), + DVB_USB_DEV(ULTIMA_ELECTRONIC, ULTIMA_ARTEC_T14_COLD), + DVB_USB_DEV(ULTIMA_ELECTRONIC, ULTIMA_ARTEC_T14_WARM), + DVB_USB_DEV(LEADTEK, LEADTEK_WINFAST_DTV_DONGLE_COLD), + DVB_USB_DEV(LEADTEK, LEADTEK_WINFAST_DTV_DONGLE_WARM), + DVB_USB_DEV(HUMAX_COEX, HUMAX_DVB_T_STICK_HIGH_SPEED_COLD), + DVB_USB_DEV(HUMAX_COEX, HUMAX_DVB_T_STICK_HIGH_SPEED_WARM), + { } +}; + MODULE_DEVICE_TABLE (usb, dibusb_dib3000mc_table); static struct dvb_usb_device_properties dibusb_mc_properties = { @@ -95,37 +115,37 @@ static struct dvb_usb_device_properties dibusb_mc_properties = { .num_device_descs = 8, .devices = { { "DiBcom USB2.0 DVB-T reference design (MOD3000P)", - { &dibusb_dib3000mc_table[0], NULL }, - { &dibusb_dib3000mc_table[1], NULL }, + { &dibusb_dib3000mc_table[DIBCOM_MOD3001_COLD], NULL }, + { &dibusb_dib3000mc_table[DIBCOM_MOD3001_WARM], NULL }, }, { "Artec T1 USB2.0 TVBOX (please check the warm ID)", - { &dibusb_dib3000mc_table[2], NULL }, - { &dibusb_dib3000mc_table[3], NULL }, + { &dibusb_dib3000mc_table[ULTIMA_TVBOX_USB2_COLD], NULL }, + { &dibusb_dib3000mc_table[ULTIMA_TVBOX_USB2_WARM], NULL }, }, { "LITE-ON USB2.0 DVB-T Tuner", /* Also rebranded as Intuix S800, Toshiba */ - { &dibusb_dib3000mc_table[4], NULL }, - { &dibusb_dib3000mc_table[5], NULL }, + { &dibusb_dib3000mc_table[LITEON_DVB_T_COLD], NULL }, + { &dibusb_dib3000mc_table[LITEON_DVB_T_WARM], NULL }, }, { "MSI Digivox Mini SL", - { &dibusb_dib3000mc_table[6], NULL }, - { &dibusb_dib3000mc_table[7], NULL }, + { &dibusb_dib3000mc_table[EMPIA_DIGIVOX_MINI_SL_COLD], NULL }, + { &dibusb_dib3000mc_table[EMPIA_DIGIVOX_MINI_SL_WARM], NULL }, }, { "GRAND - USB2.0 DVB-T adapter", - { &dibusb_dib3000mc_table[8], NULL }, - { &dibusb_dib3000mc_table[9], NULL }, + { &dibusb_dib3000mc_table[GRANDTEC_DVBT_USB2_COLD], NULL }, + { &dibusb_dib3000mc_table[GRANDTEC_DVBT_USB2_WARM], NULL }, }, { "Artec T14 - USB2.0 DVB-T", - { &dibusb_dib3000mc_table[10], NULL }, - { &dibusb_dib3000mc_table[11], NULL }, + { &dibusb_dib3000mc_table[ULTIMA_ARTEC_T14_COLD], NULL }, + { &dibusb_dib3000mc_table[ULTIMA_ARTEC_T14_WARM], NULL }, }, { "Leadtek - USB2.0 Winfast DTV dongle", - { &dibusb_dib3000mc_table[12], NULL }, - { &dibusb_dib3000mc_table[13], NULL }, + { &dibusb_dib3000mc_table[LEADTEK_WINFAST_DTV_DONGLE_COLD], NULL }, + { &dibusb_dib3000mc_table[LEADTEK_WINFAST_DTV_DONGLE_WARM], NULL }, }, { "Humax/Coex DVB-T USB Stick 2.0 High Speed", - { &dibusb_dib3000mc_table[14], NULL }, - { &dibusb_dib3000mc_table[15], NULL }, + { &dibusb_dib3000mc_table[HUMAX_DVB_T_STICK_HIGH_SPEED_COLD], NULL }, + { &dibusb_dib3000mc_table[HUMAX_DVB_T_STICK_HIGH_SPEED_WARM], NULL }, }, { NULL }, } diff --git a/drivers/media/usb/dvb-usb/digitv.c b/drivers/media/usb/dvb-usb/digitv.c index 4e3b3c064bcf..2756815a780b 100644 --- a/drivers/media/usb/dvb-usb/digitv.c +++ b/drivers/media/usb/dvb-usb/digitv.c @@ -291,10 +291,15 @@ static int digitv_probe(struct usb_interface *intf, return ret; } -static struct usb_device_id digitv_table [] = { - { USB_DEVICE(USB_VID_ANCHOR, USB_PID_NEBULA_DIGITV) }, - { } /* Terminating entry */ +enum { + ANCHOR_NEBULA_DIGITV, }; + +static struct usb_device_id digitv_table[] = { + DVB_USB_DEV(ANCHOR, ANCHOR_NEBULA_DIGITV), + { } +}; + MODULE_DEVICE_TABLE (usb, digitv_table); static struct dvb_usb_device_properties digitv_properties = { @@ -343,7 +348,7 @@ static struct dvb_usb_device_properties digitv_properties = { .num_device_descs = 1, .devices = { { "Nebula Electronics uDigiTV DVB-T USB2.0)", - { &digitv_table[0], NULL }, + { &digitv_table[ANCHOR_NEBULA_DIGITV], NULL }, { NULL }, }, { NULL }, diff --git a/drivers/media/usb/dvb-usb/dtt200u.c b/drivers/media/usb/dvb-usb/dtt200u.c index 24efa023d827..e6ee56b3a9dd 100644 --- a/drivers/media/usb/dvb-usb/dtt200u.c +++ b/drivers/media/usb/dvb-usb/dtt200u.c @@ -158,19 +158,33 @@ static int dtt200u_usb_probe(struct usb_interface *intf, return -ENODEV; } -static struct usb_device_id dtt200u_usb_table [] = { - { USB_DEVICE(USB_VID_WIDEVIEW, USB_PID_DTT200U_COLD) }, - { USB_DEVICE(USB_VID_WIDEVIEW, USB_PID_DTT200U_WARM) }, - { USB_DEVICE(USB_VID_WIDEVIEW, USB_PID_WT220U_COLD) }, - { USB_DEVICE(USB_VID_WIDEVIEW, USB_PID_WT220U_WARM) }, - { USB_DEVICE(USB_VID_WIDEVIEW, USB_PID_WT220U_ZL0353_COLD) }, - { USB_DEVICE(USB_VID_WIDEVIEW, USB_PID_WT220U_ZL0353_WARM) }, - { USB_DEVICE(USB_VID_WIDEVIEW, USB_PID_WT220U_FC_COLD) }, - { USB_DEVICE(USB_VID_WIDEVIEW, USB_PID_WT220U_FC_WARM) }, - { USB_DEVICE(USB_VID_WIDEVIEW, USB_PID_WT220U_ZAP250_COLD) }, - { USB_DEVICE(USB_VID_MIGLIA, USB_PID_WT220U_ZAP250_COLD) }, - { 0 }, +enum { + WIDEVIEW_DTT200U_COLD, + WIDEVIEW_DTT200U_WARM, + WIDEVIEW_WT220U_COLD, + WIDEVIEW_WT220U_WARM, + WIDEVIEW_WT220U_ZL0353_COLD, + WIDEVIEW_WT220U_ZL0353_WARM, + WIDEVIEW_WT220U_FC_COLD, + WIDEVIEW_WT220U_FC_WARM, + WIDEVIEW_WT220U_ZAP250_COLD, + MIGLIA_WT220U_ZAP250_COLD, }; + +static struct usb_device_id dtt200u_usb_table[] = { + DVB_USB_DEV(WIDEVIEW, WIDEVIEW_DTT200U_COLD), + DVB_USB_DEV(WIDEVIEW, WIDEVIEW_DTT200U_WARM), + DVB_USB_DEV(WIDEVIEW, WIDEVIEW_WT220U_COLD), + DVB_USB_DEV(WIDEVIEW, WIDEVIEW_WT220U_WARM), + DVB_USB_DEV(WIDEVIEW, WIDEVIEW_WT220U_ZL0353_COLD), + DVB_USB_DEV(WIDEVIEW, WIDEVIEW_WT220U_ZL0353_WARM), + DVB_USB_DEV(WIDEVIEW, WIDEVIEW_WT220U_FC_COLD), + DVB_USB_DEV(WIDEVIEW, WIDEVIEW_WT220U_FC_WARM), + DVB_USB_DEV(WIDEVIEW, WIDEVIEW_WT220U_ZAP250_COLD), + DVB_USB_DEV(MIGLIA, MIGLIA_WT220U_ZAP250_COLD), + { } +}; + MODULE_DEVICE_TABLE(usb, dtt200u_usb_table); static struct dvb_usb_device_properties dtt200u_properties = { @@ -218,8 +232,8 @@ static struct dvb_usb_device_properties dtt200u_properties = { .num_device_descs = 1, .devices = { { .name = "WideView/Yuan/Yakumo/Hama/Typhoon DVB-T USB2.0 (WT-200U)", - .cold_ids = { &dtt200u_usb_table[0], NULL }, - .warm_ids = { &dtt200u_usb_table[1], NULL }, + .cold_ids = { &dtt200u_usb_table[WIDEVIEW_DTT200U_COLD], NULL }, + .warm_ids = { &dtt200u_usb_table[WIDEVIEW_DTT200U_WARM], NULL }, }, { NULL }, } @@ -270,8 +284,8 @@ static struct dvb_usb_device_properties wt220u_properties = { .num_device_descs = 1, .devices = { { .name = "WideView WT-220U PenType Receiver (Typhoon/Freecom)", - .cold_ids = { &dtt200u_usb_table[2], &dtt200u_usb_table[8], NULL }, - .warm_ids = { &dtt200u_usb_table[3], NULL }, + .cold_ids = { &dtt200u_usb_table[WIDEVIEW_WT220U_COLD], &dtt200u_usb_table[WIDEVIEW_WT220U_ZAP250_COLD], NULL }, + .warm_ids = { &dtt200u_usb_table[WIDEVIEW_WT220U_WARM], NULL }, }, { NULL }, } @@ -322,8 +336,8 @@ static struct dvb_usb_device_properties wt220u_fc_properties = { .num_device_descs = 1, .devices = { { .name = "WideView WT-220U PenType Receiver (Typhoon/Freecom)", - .cold_ids = { &dtt200u_usb_table[6], NULL }, - .warm_ids = { &dtt200u_usb_table[7], NULL }, + .cold_ids = { &dtt200u_usb_table[WIDEVIEW_WT220U_FC_COLD], NULL }, + .warm_ids = { &dtt200u_usb_table[WIDEVIEW_WT220U_FC_WARM], NULL }, }, { NULL }, } @@ -374,8 +388,8 @@ static struct dvb_usb_device_properties wt220u_zl0353_properties = { .num_device_descs = 1, .devices = { { .name = "WideView WT-220U PenType Receiver (based on ZL353)", - .cold_ids = { &dtt200u_usb_table[4], NULL }, - .warm_ids = { &dtt200u_usb_table[5], NULL }, + .cold_ids = { &dtt200u_usb_table[WIDEVIEW_WT220U_ZL0353_COLD], NULL }, + .warm_ids = { &dtt200u_usb_table[WIDEVIEW_WT220U_ZL0353_WARM], NULL }, }, { NULL }, } @@ -393,7 +407,7 @@ static struct dvb_usb_device_properties wt220u_miglia_properties = { .num_device_descs = 1, .devices = { { .name = "WideView WT-220U PenType Receiver (Miglia)", - .cold_ids = { &dtt200u_usb_table[9], NULL }, + .cold_ids = { &dtt200u_usb_table[MIGLIA_WT220U_ZAP250_COLD], NULL }, /* This device turns into WT220U_ZL0353_WARM when fw has been uploaded */ .warm_ids = { NULL }, diff --git a/drivers/media/usb/dvb-usb/dtv5100.c b/drivers/media/usb/dvb-usb/dtv5100.c index 1c13e493322c..56c9d521a34a 100644 --- a/drivers/media/usb/dvb-usb/dtv5100.c +++ b/drivers/media/usb/dvb-usb/dtv5100.c @@ -162,10 +162,15 @@ static int dtv5100_probe(struct usb_interface *intf, return 0; } +enum { + AME_DTV5100, +}; + static struct usb_device_id dtv5100_table[] = { - { USB_DEVICE(0x06be, 0xa232) }, - { } /* Terminating entry */ + DVB_USB_DEV(AME, AME_DTV5100), + { } }; + MODULE_DEVICE_TABLE(usb, dtv5100_table); static struct dvb_usb_device_properties dtv5100_properties = { @@ -201,7 +206,7 @@ static struct dvb_usb_device_properties dtv5100_properties = { { .name = "AME DTV-5100 USB2.0 DVB-T", .cold_ids = { NULL }, - .warm_ids = { &dtv5100_table[0], NULL }, + .warm_ids = { &dtv5100_table[AME_DTV5100], NULL }, }, } }; diff --git a/drivers/media/usb/dvb-usb/dw2102.c b/drivers/media/usb/dvb-usb/dw2102.c index ca75ebdc10b3..0ca764282c76 100644 --- a/drivers/media/usb/dvb-usb/dw2102.c +++ b/drivers/media/usb/dvb-usb/dw2102.c @@ -1771,10 +1771,10 @@ enum dw2102_table_entry { PROF_7500, GENIATECH_SU3000, HAUPPAUGE_MAX_S2, - TERRATEC_CINERGY_S2, + TERRATEC_CINERGY_S2_R1, TEVII_S480_1, TEVII_S480_2, - X3M_SPC1400HD, + GENIATECH_X3M_SPC1400HD, TEVII_S421, TEVII_S632, TERRATEC_CINERGY_S2_R2, @@ -1784,7 +1784,7 @@ enum dw2102_table_entry { TERRATEC_CINERGY_S2_2, GOTVIEW_SAT_HD, GENIATECH_T220, - TECHNOTREND_S2_4600, + TECHNOTREND_CONNECT_S2_4600, TEVII_S482_1, TEVII_S482_2, TERRATEC_CINERGY_S2_BOX, @@ -1792,42 +1792,36 @@ enum dw2102_table_entry { }; static struct usb_device_id dw2102_table[] = { - [CYPRESS_DW2102] = {USB_DEVICE(USB_VID_CYPRESS, USB_PID_DW2102)}, - [CYPRESS_DW2101] = {USB_DEVICE(USB_VID_CYPRESS, 0x2101)}, - [CYPRESS_DW2104] = {USB_DEVICE(USB_VID_CYPRESS, USB_PID_DW2104)}, - [TEVII_S650] = {USB_DEVICE(0x9022, USB_PID_TEVII_S650)}, - [TERRATEC_CINERGY_S] = {USB_DEVICE(USB_VID_TERRATEC, USB_PID_TERRATEC_CINERGY_S)}, - [CYPRESS_DW3101] = {USB_DEVICE(USB_VID_CYPRESS, USB_PID_DW3101)}, - [TEVII_S630] = {USB_DEVICE(0x9022, USB_PID_TEVII_S630)}, - [PROF_1100] = {USB_DEVICE(0x3011, USB_PID_PROF_1100)}, - [TEVII_S660] = {USB_DEVICE(0x9022, USB_PID_TEVII_S660)}, - [PROF_7500] = {USB_DEVICE(0x3034, 0x7500)}, - [GENIATECH_SU3000] = {USB_DEVICE(0x1f4d, 0x3000)}, - [HAUPPAUGE_MAX_S2] = {USB_DEVICE(0x2040, 0xd900)}, - [TERRATEC_CINERGY_S2] = {USB_DEVICE(USB_VID_TERRATEC, USB_PID_TERRATEC_CINERGY_S2_R1)}, - [TEVII_S480_1] = {USB_DEVICE(0x9022, USB_PID_TEVII_S480_1)}, - [TEVII_S480_2] = {USB_DEVICE(0x9022, USB_PID_TEVII_S480_2)}, - [X3M_SPC1400HD] = {USB_DEVICE(0x1f4d, 0x3100)}, - [TEVII_S421] = {USB_DEVICE(0x9022, USB_PID_TEVII_S421)}, - [TEVII_S632] = {USB_DEVICE(0x9022, USB_PID_TEVII_S632)}, - [TERRATEC_CINERGY_S2_R2] = {USB_DEVICE(USB_VID_TERRATEC, - USB_PID_TERRATEC_CINERGY_S2_R2)}, - [TERRATEC_CINERGY_S2_R3] = {USB_DEVICE(USB_VID_TERRATEC, - USB_PID_TERRATEC_CINERGY_S2_R3)}, - [TERRATEC_CINERGY_S2_R4] = {USB_DEVICE(USB_VID_TERRATEC, - USB_PID_TERRATEC_CINERGY_S2_R4)}, - [TERRATEC_CINERGY_S2_1] = {USB_DEVICE(USB_VID_TERRATEC_2, - USB_PID_TERRATEC_CINERGY_S2_1)}, - [TERRATEC_CINERGY_S2_2] = {USB_DEVICE(USB_VID_TERRATEC_2, - USB_PID_TERRATEC_CINERGY_S2_2)}, - [GOTVIEW_SAT_HD] = {USB_DEVICE(0x1FE1, USB_PID_GOTVIEW_SAT_HD)}, - [GENIATECH_T220] = {USB_DEVICE(0x1f4d, 0xD220)}, - [TECHNOTREND_S2_4600] = {USB_DEVICE(USB_VID_TECHNOTREND, - USB_PID_TECHNOTREND_CONNECT_S2_4600)}, - [TEVII_S482_1] = {USB_DEVICE(0x9022, 0xd483)}, - [TEVII_S482_2] = {USB_DEVICE(0x9022, 0xd484)}, - [TERRATEC_CINERGY_S2_BOX] = {USB_DEVICE(USB_VID_TERRATEC, 0x0105)}, - [TEVII_S662] = {USB_DEVICE(0x9022, USB_PID_TEVII_S662)}, + DVB_USB_DEV(CYPRESS, CYPRESS_DW2102), + DVB_USB_DEV(CYPRESS, CYPRESS_DW2101), + DVB_USB_DEV(CYPRESS, CYPRESS_DW2104), + DVB_USB_DEV(TEVII, TEVII_S650), + DVB_USB_DEV(TERRATEC, TERRATEC_CINERGY_S), + DVB_USB_DEV(CYPRESS, CYPRESS_DW3101), + DVB_USB_DEV(TEVII, TEVII_S630), + DVB_USB_DEV(PROF_1, PROF_1100), + DVB_USB_DEV(TEVII, TEVII_S660), + DVB_USB_DEV(PROF_2, PROF_7500), + DVB_USB_DEV(GTEK, GENIATECH_SU3000), + DVB_USB_DEV(HAUPPAUGE, HAUPPAUGE_MAX_S2), + DVB_USB_DEV(TERRATEC, TERRATEC_CINERGY_S2_R1), + DVB_USB_DEV(TEVII, TEVII_S480_1), + DVB_USB_DEV(TEVII, TEVII_S480_2), + DVB_USB_DEV(GTEK, GENIATECH_X3M_SPC1400HD), + DVB_USB_DEV(TEVII, TEVII_S421), + DVB_USB_DEV(TEVII, TEVII_S632), + DVB_USB_DEV(TERRATEC, TERRATEC_CINERGY_S2_R2), + DVB_USB_DEV(TERRATEC, TERRATEC_CINERGY_S2_R3), + DVB_USB_DEV(TERRATEC, TERRATEC_CINERGY_S2_R4), + DVB_USB_DEV(TERRATEC_2, TERRATEC_CINERGY_S2_1), + DVB_USB_DEV(TERRATEC_2, TERRATEC_CINERGY_S2_2), + DVB_USB_DEV(GOTVIEW, GOTVIEW_SAT_HD), + DVB_USB_DEV(GTEK, GENIATECH_T220), + DVB_USB_DEV(TECHNOTREND, TECHNOTREND_CONNECT_S2_4600), + DVB_USB_DEV(TEVII, TEVII_S482_1), + DVB_USB_DEV(TEVII, TEVII_S482_2), + DVB_USB_DEV(TERRATEC, TERRATEC_CINERGY_S2_BOX), + DVB_USB_DEV(TEVII, TEVII_S662), { } }; @@ -1889,18 +1883,18 @@ static int dw2102_load_firmware(struct usb_device *dev, case USB_PID_TEVII_S650: dw2104_properties.rc.core.rc_codes = RC_MAP_TEVII_NEC; fallthrough; - case USB_PID_DW2104: + case USB_PID_CYPRESS_DW2104: reset = 1; dw210x_op_rw(dev, 0xc4, 0x0000, 0, &reset, 1, DW210X_WRITE_MSG); fallthrough; - case USB_PID_DW3101: + case USB_PID_CYPRESS_DW3101: reset = 0; dw210x_op_rw(dev, 0xbf, 0x0040, 0, &reset, 0, DW210X_WRITE_MSG); break; case USB_PID_TERRATEC_CINERGY_S: - case USB_PID_DW2102: + case USB_PID_CYPRESS_DW2102: dw210x_op_rw(dev, 0xbf, 0x0040, 0, &reset, 0, DW210X_WRITE_MSG); dw210x_op_rw(dev, 0xb9, 0x0000, 0, &reset16[0], 2, @@ -2350,11 +2344,11 @@ static struct dvb_usb_device_properties su3000_properties = { { NULL }, }, { "Terratec Cinergy S2 USB HD", - { &dw2102_table[TERRATEC_CINERGY_S2], NULL }, + { &dw2102_table[TERRATEC_CINERGY_S2_R1], NULL }, { NULL }, }, { "X3M TV SPC1400HD PCI", - { &dw2102_table[X3M_SPC1400HD], NULL }, + { &dw2102_table[GENIATECH_X3M_SPC1400HD], NULL }, { NULL }, }, { "Terratec Cinergy S2 USB HD Rev.2", @@ -2525,7 +2519,7 @@ static struct dvb_usb_device_properties tt_s2_4600_properties = { .num_device_descs = 5, .devices = { { "TechnoTrend TT-connect S2-4600", - { &dw2102_table[TECHNOTREND_S2_4600], NULL }, + { &dw2102_table[TECHNOTREND_CONNECT_S2_4600], NULL }, { NULL }, }, { "TeVii S482 (tuner 1)", diff --git a/drivers/media/usb/dvb-usb/gp8psk.c b/drivers/media/usb/dvb-usb/gp8psk.c index b4f661bb5648..b2b27a86dfe5 100644 --- a/drivers/media/usb/dvb-usb/gp8psk.c +++ b/drivers/media/usb/dvb-usb/gp8psk.c @@ -310,15 +310,25 @@ static int gp8psk_usb_probe(struct usb_interface *intf, return ret; } -static struct usb_device_id gp8psk_usb_table [] = { - { USB_DEVICE(USB_VID_GENPIX, USB_PID_GENPIX_8PSK_REV_1_COLD) }, - { USB_DEVICE(USB_VID_GENPIX, USB_PID_GENPIX_8PSK_REV_1_WARM) }, - { USB_DEVICE(USB_VID_GENPIX, USB_PID_GENPIX_8PSK_REV_2) }, - { USB_DEVICE(USB_VID_GENPIX, USB_PID_GENPIX_SKYWALKER_1) }, - { USB_DEVICE(USB_VID_GENPIX, USB_PID_GENPIX_SKYWALKER_2) }, -/* { USB_DEVICE(USB_VID_GENPIX, USB_PID_GENPIX_SKYWALKER_CW3K) }, */ - { 0 }, +enum { + GENPIX_8PSK_REV_1_COLD, + GENPIX_8PSK_REV_1_WARM, + GENPIX_8PSK_REV_2, + GENPIX_SKYWALKER_1, + GENPIX_SKYWALKER_2, + GENPIX_SKYWALKER_CW3K, }; + +static struct usb_device_id gp8psk_usb_table[] = { + DVB_USB_DEV(GENPIX, GENPIX_8PSK_REV_1_COLD), + DVB_USB_DEV(GENPIX, GENPIX_8PSK_REV_1_WARM), + DVB_USB_DEV(GENPIX, GENPIX_8PSK_REV_2), + DVB_USB_DEV(GENPIX, GENPIX_SKYWALKER_1), + DVB_USB_DEV(GENPIX, GENPIX_SKYWALKER_2), + DVB_USB_DEV(GENPIX, GENPIX_SKYWALKER_CW3K), + { } +}; + MODULE_DEVICE_TABLE(usb, gp8psk_usb_table); static struct dvb_usb_device_properties gp8psk_properties = { @@ -355,20 +365,20 @@ static struct dvb_usb_device_properties gp8psk_properties = { .num_device_descs = 4, .devices = { { .name = "Genpix 8PSK-to-USB2 Rev.1 DVB-S receiver", - .cold_ids = { &gp8psk_usb_table[0], NULL }, - .warm_ids = { &gp8psk_usb_table[1], NULL }, + .cold_ids = { &gp8psk_usb_table[GENPIX_8PSK_REV_1_COLD], NULL }, + .warm_ids = { &gp8psk_usb_table[GENPIX_8PSK_REV_1_WARM], NULL }, }, { .name = "Genpix 8PSK-to-USB2 Rev.2 DVB-S receiver", .cold_ids = { NULL }, - .warm_ids = { &gp8psk_usb_table[2], NULL }, + .warm_ids = { &gp8psk_usb_table[GENPIX_8PSK_REV_2], NULL }, }, { .name = "Genpix SkyWalker-1 DVB-S receiver", .cold_ids = { NULL }, - .warm_ids = { &gp8psk_usb_table[3], NULL }, + .warm_ids = { &gp8psk_usb_table[GENPIX_SKYWALKER_1], NULL }, }, { .name = "Genpix SkyWalker-2 DVB-S receiver", .cold_ids = { NULL }, - .warm_ids = { &gp8psk_usb_table[4], NULL }, + .warm_ids = { &gp8psk_usb_table[GENPIX_SKYWALKER_2], NULL }, }, { NULL }, } diff --git a/drivers/media/usb/dvb-usb/m920x.c b/drivers/media/usb/dvb-usb/m920x.c index 691e05833db1..548199cd86f6 100644 --- a/drivers/media/usb/dvb-usb/m920x.c +++ b/drivers/media/usb/dvb-usb/m920x.c @@ -897,20 +897,29 @@ static int m920x_probe(struct usb_interface *intf, return ret; } -static struct usb_device_id m920x_table [] = { - { USB_DEVICE(USB_VID_MSI, USB_PID_MSI_MEGASKY580) }, - { USB_DEVICE(USB_VID_ANUBIS_ELECTRONIC, - USB_PID_MSI_DIGI_VOX_MINI_II) }, - { USB_DEVICE(USB_VID_ANUBIS_ELECTRONIC, - USB_PID_LIFEVIEW_TV_WALKER_TWIN_COLD) }, - { USB_DEVICE(USB_VID_ANUBIS_ELECTRONIC, - USB_PID_LIFEVIEW_TV_WALKER_TWIN_WARM) }, - { USB_DEVICE(USB_VID_DPOSH, USB_PID_DPOSH_M9206_COLD) }, - { USB_DEVICE(USB_VID_DPOSH, USB_PID_DPOSH_M9206_WARM) }, - { USB_DEVICE(USB_VID_VISIONPLUS, USB_PID_PINNACLE_PCTV310E) }, - { USB_DEVICE(USB_VID_AZUREWAVE, USB_PID_TWINHAN_VP7049) }, - { } /* Terminating entry */ +enum { + MSI_MEGASKY580, + ANUBIS_MSI_DIGI_VOX_MINI_II, + ANUBIS_LIFEVIEW_TV_WALKER_TWIN_COLD, + ANUBIS_LIFEVIEW_TV_WALKER_TWIN_WARM, + DPOSH_M9206_COLD, + DPOSH_M9206_WARM, + VISIONPLUS_PINNACLE_PCTV310E, + AZUREWAVE_TWINHAN_VP7049, }; + +static struct usb_device_id m920x_table[] = { + DVB_USB_DEV(MSI, MSI_MEGASKY580), + DVB_USB_DEV(ANUBIS_ELECTRONIC, ANUBIS_MSI_DIGI_VOX_MINI_II), + DVB_USB_DEV(ANUBIS_ELECTRONIC, ANUBIS_LIFEVIEW_TV_WALKER_TWIN_COLD), + DVB_USB_DEV(ANUBIS_ELECTRONIC, ANUBIS_LIFEVIEW_TV_WALKER_TWIN_WARM), + DVB_USB_DEV(DPOSH, DPOSH_M9206_COLD), + DVB_USB_DEV(DPOSH, DPOSH_M9206_WARM), + DVB_USB_DEV(VISIONPLUS, VISIONPLUS_PINNACLE_PCTV310E), + DVB_USB_DEV(AZUREWAVE, AZUREWAVE_TWINHAN_VP7049), + { } +}; + MODULE_DEVICE_TABLE (usb, m920x_table); static struct dvb_usb_device_properties megasky_properties = { @@ -962,7 +971,7 @@ static struct dvb_usb_device_properties megasky_properties = { .num_device_descs = 1, .devices = { { "MSI Mega Sky 580 DVB-T USB2.0", - { &m920x_table[0], NULL }, + { &m920x_table[MSI_MEGASKY580], NULL }, { NULL }, } } @@ -1010,7 +1019,7 @@ static struct dvb_usb_device_properties digivox_mini_ii_properties = { .num_device_descs = 1, .devices = { { "MSI DIGI VOX mini II DVB-T USB2.0", - { &m920x_table[1], NULL }, + { &m920x_table[ANUBIS_MSI_DIGI_VOX_MINI_II], NULL }, { NULL }, }, } @@ -1097,8 +1106,8 @@ static struct dvb_usb_device_properties tvwalkertwin_properties = { .num_device_descs = 1, .devices = { { .name = "LifeView TV Walker Twin DVB-T USB2.0", - .cold_ids = { &m920x_table[2], NULL }, - .warm_ids = { &m920x_table[3], NULL }, + .cold_ids = { &m920x_table[ANUBIS_LIFEVIEW_TV_WALKER_TWIN_COLD], NULL }, + .warm_ids = { &m920x_table[ANUBIS_LIFEVIEW_TV_WALKER_TWIN_WARM], NULL }, }, } }; @@ -1139,8 +1148,8 @@ static struct dvb_usb_device_properties dposh_properties = { .num_device_descs = 1, .devices = { { .name = "Dposh DVB-T USB2.0", - .cold_ids = { &m920x_table[4], NULL }, - .warm_ids = { &m920x_table[5], NULL }, + .cold_ids = { &m920x_table[DPOSH_M9206_COLD], NULL }, + .warm_ids = { &m920x_table[DPOSH_M9206_WARM], NULL }, }, } }; @@ -1195,7 +1204,7 @@ static struct dvb_usb_device_properties pinnacle_pctv310e_properties = { .num_device_descs = 1, .devices = { { "Pinnacle PCTV 310e", - { &m920x_table[6], NULL }, + { &m920x_table[VISIONPLUS_PINNACLE_PCTV310E], NULL }, { NULL }, } } @@ -1250,7 +1259,7 @@ static struct dvb_usb_device_properties vp7049_properties = { .num_device_descs = 1, .devices = { { "DTV-DVB UDTT7049", - { &m920x_table[7], NULL }, + { &m920x_table[AZUREWAVE_TWINHAN_VP7049], NULL }, { NULL }, } } diff --git a/drivers/media/usb/dvb-usb/nova-t-usb2.c b/drivers/media/usb/dvb-usb/nova-t-usb2.c index 9c0eb0d40822..4782d0780913 100644 --- a/drivers/media/usb/dvb-usb/nova-t-usb2.c +++ b/drivers/media/usb/dvb-usb/nova-t-usb2.c @@ -160,11 +160,17 @@ static int nova_t_probe(struct usb_interface *intf, } /* do not change the order of the ID table */ -static struct usb_device_id nova_t_table [] = { -/* 00 */ { USB_DEVICE(USB_VID_HAUPPAUGE, USB_PID_WINTV_NOVA_T_USB2_COLD) }, -/* 01 */ { USB_DEVICE(USB_VID_HAUPPAUGE, USB_PID_WINTV_NOVA_T_USB2_WARM) }, - { } /* Terminating entry */ +enum { + HAUPPAUGE_WINTV_NOVA_T_USB2_COLD, + HAUPPAUGE_WINTV_NOVA_T_USB2_WARM, }; + +static struct usb_device_id nova_t_table[] = { + DVB_USB_DEV(HAUPPAUGE, HAUPPAUGE_WINTV_NOVA_T_USB2_COLD), + DVB_USB_DEV(HAUPPAUGE, HAUPPAUGE_WINTV_NOVA_T_USB2_WARM), + { } +}; + MODULE_DEVICE_TABLE(usb, nova_t_table); static struct dvb_usb_device_properties nova_t_properties = { @@ -221,8 +227,8 @@ static struct dvb_usb_device_properties nova_t_properties = { .num_device_descs = 1, .devices = { { "Hauppauge WinTV-NOVA-T usb2", - { &nova_t_table[0], NULL }, - { &nova_t_table[1], NULL }, + { &nova_t_table[HAUPPAUGE_WINTV_NOVA_T_USB2_COLD], NULL }, + { &nova_t_table[HAUPPAUGE_WINTV_NOVA_T_USB2_WARM], NULL }, }, { NULL }, } diff --git a/drivers/media/usb/dvb-usb/opera1.c b/drivers/media/usb/dvb-usb/opera1.c index e8d784b9d119..0da86f58aff6 100644 --- a/drivers/media/usb/dvb-usb/opera1.c +++ b/drivers/media/usb/dvb-usb/opera1.c @@ -425,10 +425,15 @@ static int opera1_rc_query(struct dvb_usb_device *dev, u32 * event, int *state) return 0; } +enum { + CYPRESS_OPERA1_COLD, + OPERA1_WARM, +}; + static struct usb_device_id opera1_table[] = { - {USB_DEVICE(USB_VID_CYPRESS, USB_PID_OPERA1_COLD)}, - {USB_DEVICE(USB_VID_OPERA1, USB_PID_OPERA1_WARM)}, - {} + DVB_USB_DEV(CYPRESS, CYPRESS_OPERA1_COLD), + DVB_USB_DEV(OPERA1, OPERA1_WARM), + { } }; MODULE_DEVICE_TABLE(usb, opera1_table); @@ -540,8 +545,8 @@ static struct dvb_usb_device_properties opera1_properties = { .num_device_descs = 1, .devices = { {"Opera1 DVB-S USB2.0", - {&opera1_table[0], NULL}, - {&opera1_table[1], NULL}, + {&opera1_table[CYPRESS_OPERA1_COLD], NULL}, + {&opera1_table[OPERA1_WARM], NULL}, }, } }; diff --git a/drivers/media/usb/dvb-usb/pctv452e.c b/drivers/media/usb/dvb-usb/pctv452e.c index 9b78b40abc6d..f0794c68c622 100644 --- a/drivers/media/usb/dvb-usb/pctv452e.c +++ b/drivers/media/usb/dvb-usb/pctv452e.c @@ -951,13 +951,19 @@ static int pctv452e_tuner_attach(struct dvb_usb_adapter *a) return 0; } +enum { + PINNACLE_PCTV_452E, + TECHNOTREND_CONNECT_S2_3600, + TECHNOTREND_CONNECT_S2_3650_CI, +}; + static struct usb_device_id pctv452e_usb_table[] = { - {USB_DEVICE(USB_VID_PINNACLE, USB_PID_PCTV_452E)}, - {USB_DEVICE(USB_VID_TECHNOTREND, USB_PID_TECHNOTREND_CONNECT_S2_3600)}, - {USB_DEVICE(USB_VID_TECHNOTREND, - USB_PID_TECHNOTREND_CONNECT_S2_3650_CI)}, - {} + DVB_USB_DEV(PINNACLE, PINNACLE_PCTV_452E), + DVB_USB_DEV(TECHNOTREND, TECHNOTREND_CONNECT_S2_3600), + DVB_USB_DEV(TECHNOTREND, TECHNOTREND_CONNECT_S2_3650_CI), + { } }; + MODULE_DEVICE_TABLE(usb, pctv452e_usb_table); static struct dvb_usb_device_properties pctv452e_properties = { @@ -1006,7 +1012,7 @@ static struct dvb_usb_device_properties pctv452e_properties = { .devices = { { .name = "PCTV HDTV USB", .cold_ids = { NULL, NULL }, /* this is a warm only device */ - .warm_ids = { &pctv452e_usb_table[0], NULL } + .warm_ids = { &pctv452e_usb_table[PINNACLE_PCTV_452E], NULL } }, { NULL }, } @@ -1060,11 +1066,11 @@ static struct dvb_usb_device_properties tt_connect_s2_3600_properties = { .devices = { { .name = "Technotrend TT Connect S2-3600", .cold_ids = { NULL, NULL }, /* this is a warm only device */ - .warm_ids = { &pctv452e_usb_table[1], NULL } + .warm_ids = { &pctv452e_usb_table[TECHNOTREND_CONNECT_S2_3600], NULL } }, { .name = "Technotrend TT Connect S2-3650-CI", .cold_ids = { NULL, NULL }, - .warm_ids = { &pctv452e_usb_table[2], NULL } + .warm_ids = { &pctv452e_usb_table[TECHNOTREND_CONNECT_S2_3650_CI], NULL } }, { NULL }, } diff --git a/drivers/media/usb/dvb-usb/technisat-usb2.c b/drivers/media/usb/dvb-usb/technisat-usb2.c index a9ed26ce1be6..9c77911fcad4 100644 --- a/drivers/media/usb/dvb-usb/technisat-usb2.c +++ b/drivers/media/usb/dvb-usb/technisat-usb2.c @@ -689,10 +689,15 @@ static int technisat_usb2_rc_query(struct dvb_usb_device *d) } /* DVB-USB and USB stuff follows */ +enum { + TECHNISAT_USB2_DVB_S2, +}; + static struct usb_device_id technisat_usb2_id_table[] = { - { USB_DEVICE(USB_VID_TECHNISAT, USB_PID_TECHNISAT_USB2_DVB_S2) }, - { 0 } /* Terminating entry */ + DVB_USB_DEV(TECHNISAT, TECHNISAT_USB2_DVB_S2), + { } }; + MODULE_DEVICE_TABLE(usb, technisat_usb2_id_table); /* device description */ @@ -738,7 +743,7 @@ static struct dvb_usb_device_properties technisat_usb2_devices = { .num_device_descs = 1, .devices = { { "Technisat SkyStar USB HD (DVB-S/S2)", - { &technisat_usb2_id_table[0], NULL }, + { &technisat_usb2_id_table[TECHNISAT_USB2_DVB_S2], NULL }, { NULL }, }, }, diff --git a/drivers/media/usb/dvb-usb/ttusb2.c b/drivers/media/usb/dvb-usb/ttusb2.c index 294274fd8f55..373ffa7f641e 100644 --- a/drivers/media/usb/dvb-usb/ttusb2.c +++ b/drivers/media/usb/dvb-usb/ttusb2.c @@ -630,17 +630,23 @@ static int ttusb2_probe(struct usb_interface *intf, return -ENODEV; } -static struct usb_device_id ttusb2_table [] = { - { USB_DEVICE(USB_VID_PINNACLE, USB_PID_PCTV_400E) }, - { USB_DEVICE(USB_VID_PINNACLE, USB_PID_PCTV_450E) }, - { USB_DEVICE(USB_VID_TECHNOTREND, - USB_PID_TECHNOTREND_CONNECT_S2400) }, - { USB_DEVICE(USB_VID_TECHNOTREND, - USB_PID_TECHNOTREND_CONNECT_CT3650) }, - { USB_DEVICE(USB_VID_TECHNOTREND, - USB_PID_TECHNOTREND_CONNECT_S2400_8KEEPROM) }, - {} /* Terminating entry */ +enum { + PINNACLE_PCTV_400E, + PINNACLE_PCTV_450E, + TECHNOTREND_CONNECT_S2400, + TECHNOTREND_CONNECT_CT3650, + TECHNOTREND_CONNECT_S2400_8KEEPROM, +}; + +static struct usb_device_id ttusb2_table[] = { + DVB_USB_DEV(PINNACLE, PINNACLE_PCTV_400E), + DVB_USB_DEV(PINNACLE, PINNACLE_PCTV_450E), + DVB_USB_DEV(TECHNOTREND, TECHNOTREND_CONNECT_S2400), + DVB_USB_DEV(TECHNOTREND, TECHNOTREND_CONNECT_CT3650), + DVB_USB_DEV(TECHNOTREND, TECHNOTREND_CONNECT_S2400_8KEEPROM), + { } }; + MODULE_DEVICE_TABLE (usb, ttusb2_table); static struct dvb_usb_device_properties ttusb2_properties = { @@ -688,11 +694,11 @@ static struct dvb_usb_device_properties ttusb2_properties = { .num_device_descs = 2, .devices = { { "Pinnacle 400e DVB-S USB2.0", - { &ttusb2_table[0], NULL }, + { &ttusb2_table[PINNACLE_PCTV_400E], NULL }, { NULL }, }, { "Pinnacle 450e DVB-S USB2.0", - { &ttusb2_table[1], NULL }, + { &ttusb2_table[PINNACLE_PCTV_450E], NULL }, { NULL }, }, } @@ -743,11 +749,11 @@ static struct dvb_usb_device_properties ttusb2_properties_s2400 = { .num_device_descs = 2, .devices = { { "Technotrend TT-connect S-2400", - { &ttusb2_table[2], NULL }, + { &ttusb2_table[TECHNOTREND_CONNECT_S2400], NULL }, { NULL }, }, { "Technotrend TT-connect S-2400 (8kB EEPROM)", - { &ttusb2_table[4], NULL }, + { &ttusb2_table[TECHNOTREND_CONNECT_S2400_8KEEPROM], NULL }, { NULL }, }, } @@ -823,7 +829,7 @@ static struct dvb_usb_device_properties ttusb2_properties_ct3650 = { .num_device_descs = 1, .devices = { { "Technotrend TT-connect CT-3650", - .warm_ids = { &ttusb2_table[3], NULL }, + .warm_ids = { &ttusb2_table[TECHNOTREND_CONNECT_CT3650], NULL }, }, } }; diff --git a/drivers/media/usb/dvb-usb/umt-010.c b/drivers/media/usb/dvb-usb/umt-010.c index 2181993771ae..464699b0b75b 100644 --- a/drivers/media/usb/dvb-usb/umt-010.c +++ b/drivers/media/usb/dvb-usb/umt-010.c @@ -81,11 +81,17 @@ static int umt_probe(struct usb_interface *intf, } /* do not change the order of the ID table */ -static struct usb_device_id umt_table [] = { -/* 00 */ { USB_DEVICE(USB_VID_HANFTEK, USB_PID_HANFTEK_UMT_010_COLD) }, -/* 01 */ { USB_DEVICE(USB_VID_HANFTEK, USB_PID_HANFTEK_UMT_010_WARM) }, - { } /* Terminating entry */ +enum { + HANFTEK_UMT_010_COLD, + HANFTEK_UMT_010_WARM, }; + +static struct usb_device_id umt_table[] = { + DVB_USB_DEV(HANFTEK, HANFTEK_UMT_010_COLD), + DVB_USB_DEV(HANFTEK, HANFTEK_UMT_010_WARM), + { } +}; + MODULE_DEVICE_TABLE (usb, umt_table); static struct dvb_usb_device_properties umt_properties = { @@ -127,8 +133,8 @@ static struct dvb_usb_device_properties umt_properties = { .num_device_descs = 1, .devices = { { "Hanftek UMT-010 DVB-T USB2.0", - { &umt_table[0], NULL }, - { &umt_table[1], NULL }, + { &umt_table[HANFTEK_UMT_010_COLD], NULL }, + { &umt_table[HANFTEK_UMT_010_WARM], NULL }, }, } }; diff --git a/drivers/media/usb/dvb-usb/vp702x.c b/drivers/media/usb/dvb-usb/vp702x.c index a1d9e4801a2b..5b6740cbd1d1 100644 --- a/drivers/media/usb/dvb-usb/vp702x.c +++ b/drivers/media/usb/dvb-usb/vp702x.c @@ -369,12 +369,19 @@ static void vp702x_usb_disconnect(struct usb_interface *intf) dvb_usb_device_exit(intf); } -static struct usb_device_id vp702x_usb_table [] = { - { USB_DEVICE(USB_VID_VISIONPLUS, USB_PID_TWINHAN_VP7021_COLD) }, -// { USB_DEVICE(USB_VID_VISIONPLUS, USB_PID_TWINHAN_VP7020_COLD) }, -// { USB_DEVICE(USB_VID_VISIONPLUS, USB_PID_TWINHAN_VP7020_WARM) }, - { 0 }, +enum { + VISIONPLUS_VP7021_COLD, + VISIONPLUS_VP7020_COLD, + VISIONPLUS_VP7020_WARM, }; + +static struct usb_device_id vp702x_usb_table[] = { + DVB_USB_DEV(VISIONPLUS, VISIONPLUS_VP7021_COLD), +// DVB_USB_DEV(VISIONPLUS, VISIONPLUS_VP7020_COLD), +// DVB_USB_DEV(VISIONPLUS, VISIONPLUS_VP7020_WARM), + { } +}; + MODULE_DEVICE_TABLE(usb, vp702x_usb_table); static struct dvb_usb_device_properties vp702x_properties = { @@ -421,12 +428,12 @@ static struct dvb_usb_device_properties vp702x_properties = { .num_device_descs = 1, .devices = { { .name = "TwinhanDTV StarBox DVB-S USB2.0 (VP7021)", - .cold_ids = { &vp702x_usb_table[0], NULL }, + .cold_ids = { &vp702x_usb_table[VISIONPLUS_VP7021_COLD], NULL }, .warm_ids = { NULL }, }, /* { .name = "TwinhanDTV StarBox DVB-S USB2.0 (VP7020)", - .cold_ids = { &vp702x_usb_table[2], NULL }, - .warm_ids = { &vp702x_usb_table[3], NULL }, + .cold_ids = { &vp702x_usb_table[VISIONPLUS_VP7020_COLD], NULL }, + .warm_ids = { &vp702x_usb_table[VISIONPLUS_VP7020_WARM], NULL }, }, */ { NULL }, } diff --git a/drivers/media/usb/dvb-usb/vp7045.c b/drivers/media/usb/dvb-usb/vp7045.c index 23e3a90af1f4..1dc2b18d44d8 100644 --- a/drivers/media/usb/dvb-usb/vp7045.c +++ b/drivers/media/usb/dvb-usb/vp7045.c @@ -172,13 +172,21 @@ static int vp7045_usb_probe(struct usb_interface *intf, THIS_MODULE, NULL, adapter_nr); } -static struct usb_device_id vp7045_usb_table [] = { - { USB_DEVICE(USB_VID_VISIONPLUS, USB_PID_TWINHAN_VP7045_COLD) }, - { USB_DEVICE(USB_VID_VISIONPLUS, USB_PID_TWINHAN_VP7045_WARM) }, - { USB_DEVICE(USB_VID_VISIONPLUS, USB_PID_DNTV_TINYUSB2_COLD) }, - { USB_DEVICE(USB_VID_VISIONPLUS, USB_PID_DNTV_TINYUSB2_WARM) }, - { 0 }, +enum { + VISIONPLUS_VP7045_COLD, + VISIONPLUS_VP7045_WARM, + VISIONPLUS_TINYUSB2_COLD, + VISIONPLUS_TINYUSB2_WARM, }; + +static struct usb_device_id vp7045_usb_table[] = { + DVB_USB_DEV(VISIONPLUS, VISIONPLUS_VP7045_COLD), + DVB_USB_DEV(VISIONPLUS, VISIONPLUS_VP7045_WARM), + DVB_USB_DEV(VISIONPLUS, VISIONPLUS_TINYUSB2_COLD), + DVB_USB_DEV(VISIONPLUS, VISIONPLUS_TINYUSB2_WARM), + { } +}; + MODULE_DEVICE_TABLE(usb, vp7045_usb_table); static struct dvb_usb_device_properties vp7045_properties = { @@ -221,12 +229,12 @@ static struct dvb_usb_device_properties vp7045_properties = { .num_device_descs = 2, .devices = { { .name = "Twinhan USB2.0 DVB-T receiver (TwinhanDTV Alpha/MagicBox II)", - .cold_ids = { &vp7045_usb_table[0], NULL }, - .warm_ids = { &vp7045_usb_table[1], NULL }, + .cold_ids = { &vp7045_usb_table[VISIONPLUS_VP7045_COLD], NULL }, + .warm_ids = { &vp7045_usb_table[VISIONPLUS_VP7045_WARM], NULL }, }, { .name = "DigitalNow TinyUSB 2 DVB-t Receiver", - .cold_ids = { &vp7045_usb_table[2], NULL }, - .warm_ids = { &vp7045_usb_table[3], NULL }, + .cold_ids = { &vp7045_usb_table[VISIONPLUS_TINYUSB2_COLD], NULL }, + .warm_ids = { &vp7045_usb_table[VISIONPLUS_TINYUSB2_WARM], NULL }, }, { NULL }, } diff --git a/drivers/media/usb/gspca/spca561.c b/drivers/media/usb/gspca/spca561.c index d608a518c141..431527ed602b 100644 --- a/drivers/media/usb/gspca/spca561.c +++ b/drivers/media/usb/gspca/spca561.c @@ -510,7 +510,7 @@ static void setexposure(struct gspca_dev *gspca_dev, s32 val) /* We choose to use the high bits setting the fixed framerate divisor asap, as setting high basic exposure setting without the fixed divider in combination with high gains makes the cam stop */ - int table[] = { 0, 450, 550, 625, EXPOSURE_MAX }; + static const int table[] = { 0, 450, 550, 625, EXPOSURE_MAX }; for (i = 0; i < ARRAY_SIZE(table) - 1; i++) { if (val <= table[i + 1]) { diff --git a/drivers/media/usb/pvrusb2/pvrusb2-hdw.c b/drivers/media/usb/pvrusb2/pvrusb2-hdw.c index cd7b118d5929..a9666373af6b 100644 --- a/drivers/media/usb/pvrusb2/pvrusb2-hdw.c +++ b/drivers/media/usb/pvrusb2/pvrusb2-hdw.c @@ -2569,6 +2569,11 @@ struct pvr2_hdw *pvr2_hdw_create(struct usb_interface *intf, } while (0); mutex_unlock(&pvr2_unit_mtx); + INIT_WORK(&hdw->workpoll, pvr2_hdw_worker_poll); + + if (hdw->unit_number == -1) + goto fail; + cnt1 = 0; cnt2 = scnprintf(hdw->name+cnt1,sizeof(hdw->name)-cnt1,"pvrusb2"); cnt1 += cnt2; @@ -2580,8 +2585,6 @@ struct pvr2_hdw *pvr2_hdw_create(struct usb_interface *intf, if (cnt1 >= sizeof(hdw->name)) cnt1 = sizeof(hdw->name)-1; hdw->name[cnt1] = 0; - INIT_WORK(&hdw->workpoll,pvr2_hdw_worker_poll); - pvr2_trace(PVR2_TRACE_INIT,"Driver unit number is %d, name is %s", hdw->unit_number,hdw->name); diff --git a/drivers/media/usb/stkwebcam/stk-webcam.c b/drivers/media/usb/stkwebcam/stk-webcam.c index 5b822214ccc5..787edb3d47c2 100644 --- a/drivers/media/usb/stkwebcam/stk-webcam.c +++ b/drivers/media/usb/stkwebcam/stk-webcam.c @@ -150,25 +150,18 @@ int stk_camera_write_reg(struct stk_camera *dev, u16 index, u8 value) int stk_camera_read_reg(struct stk_camera *dev, u16 index, u8 *value) { struct usb_device *udev = dev->udev; - unsigned char *buf; int ret; - buf = kmalloc(sizeof(u8), GFP_KERNEL); - if (!buf) - return -ENOMEM; - ret = usb_control_msg(udev, usb_rcvctrlpipe(udev, 0), 0x00, USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_DEVICE, 0x00, index, - buf, + &dev->read_reg_scratch, sizeof(u8), 500); if (ret >= 0) - *value = *buf; - - kfree(buf); + *value = dev->read_reg_scratch; if (ret < 0) return ret; diff --git a/drivers/media/usb/stkwebcam/stk-webcam.h b/drivers/media/usb/stkwebcam/stk-webcam.h index 14519e5308b1..136decffe9ce 100644 --- a/drivers/media/usb/stkwebcam/stk-webcam.h +++ b/drivers/media/usb/stkwebcam/stk-webcam.h @@ -105,6 +105,8 @@ struct stk_camera { struct list_head sio_avail; struct list_head sio_full; unsigned sequence; + + u8 read_reg_scratch; }; #define vdev_to_camera(d) container_of(d, struct stk_camera, vdev) diff --git a/drivers/media/usb/uvc/uvc_ctrl.c b/drivers/media/usb/uvc/uvc_ctrl.c index b4f6edf968bc..0e78233fc8a0 100644 --- a/drivers/media/usb/uvc/uvc_ctrl.c +++ b/drivers/media/usb/uvc/uvc_ctrl.c @@ -2188,11 +2188,21 @@ static int __uvc_ctrl_add_mapping(struct uvc_video_chain *chain, if (map == NULL) return -ENOMEM; + /* For UVCIOC_CTRL_MAP custom control */ + if (mapping->name) { + map->name = kstrdup(mapping->name, GFP_KERNEL); + if (!map->name) { + kfree(map); + return -ENOMEM; + } + } + INIT_LIST_HEAD(&map->ev_subs); size = sizeof(*mapping->menu_info) * mapping->menu_count; map->menu_info = kmemdup(mapping->menu_info, size, GFP_KERNEL); if (map->menu_info == NULL) { + kfree(map->name); kfree(map); return -ENOMEM; } diff --git a/drivers/media/usb/uvc/uvc_driver.c b/drivers/media/usb/uvc/uvc_driver.c index dda0f0aa78b8..6c86faecbea2 100644 --- a/drivers/media/usb/uvc/uvc_driver.c +++ b/drivers/media/usb/uvc/uvc_driver.c @@ -155,6 +155,11 @@ static struct uvc_format_desc uvc_fmts[] = { .fcc = V4L2_PIX_FMT_H264, }, { + .name = "H.265", + .guid = UVC_GUID_FORMAT_H265, + .fcc = V4L2_PIX_FMT_HEVC, + }, + { .name = "Greyscale 8 L/R (Y8I)", .guid = UVC_GUID_FORMAT_Y8I, .fcc = V4L2_PIX_FMT_Y8I, @@ -1009,9 +1014,7 @@ static int uvc_parse_streaming(struct uvc_device *dev, streaming->header.bEndpointAddress); if (ep == NULL) continue; - - psize = le16_to_cpu(ep->desc.wMaxPacketSize); - psize = (psize & 0x07ff) * (1 + ((psize >> 11) & 3)); + psize = uvc_endpoint_max_bpi(dev->udev, ep); if (psize > streaming->maxpsize) streaming->maxpsize = psize; } @@ -2443,7 +2446,7 @@ static int uvc_probe(struct usb_interface *intf, "Forcing device quirks to 0x%x by module parameter for testing purpose.\n", dev->quirks); dev_info(&dev->udev->dev, - "Please report required quirks to the linux-uvc-devel mailing list.\n"); + "Please report required quirks to the linux-media mailing list.\n"); } if (dev->info->uvc_version) { diff --git a/drivers/media/usb/uvc/uvc_v4l2.c b/drivers/media/usb/uvc/uvc_v4l2.c index 711556d13d03..648dcd579e81 100644 --- a/drivers/media/usb/uvc/uvc_v4l2.c +++ b/drivers/media/usb/uvc/uvc_v4l2.c @@ -42,12 +42,12 @@ static int uvc_ioctl_ctrl_map(struct uvc_video_chain *chain, map->id = xmap->id; /* Non standard control id. */ if (v4l2_ctrl_get_name(map->id) == NULL) { - map->name = kmemdup(xmap->name, sizeof(xmap->name), - GFP_KERNEL); - if (!map->name) { - ret = -ENOMEM; + if (xmap->name[0] == '\0') { + ret = -EINVAL; goto free_map; } + xmap->name[sizeof(xmap->name) - 1] = '\0'; + map->name = xmap->name; } memcpy(map->entity, xmap->entity, sizeof(map->entity)); map->selector = xmap->selector; @@ -871,29 +871,31 @@ static int uvc_ioctl_enum_input(struct file *file, void *fh, struct uvc_video_chain *chain = handle->chain; const struct uvc_entity *selector = chain->selector; struct uvc_entity *iterm = NULL; + struct uvc_entity *it; u32 index = input->index; - int pin = 0; if (selector == NULL || (chain->dev->quirks & UVC_QUIRK_IGNORE_SELECTOR_UNIT)) { if (index != 0) return -EINVAL; - list_for_each_entry(iterm, &chain->entities, chain) { - if (UVC_ENTITY_IS_ITERM(iterm)) + list_for_each_entry(it, &chain->entities, chain) { + if (UVC_ENTITY_IS_ITERM(it)) { + iterm = it; break; + } } - pin = iterm->id; } else if (index < selector->bNrInPins) { - pin = selector->baSourceID[index]; - list_for_each_entry(iterm, &chain->entities, chain) { - if (!UVC_ENTITY_IS_ITERM(iterm)) + list_for_each_entry(it, &chain->entities, chain) { + if (!UVC_ENTITY_IS_ITERM(it)) continue; - if (iterm->id == pin) + if (it->id == selector->baSourceID[index]) { + iterm = it; break; + } } } - if (iterm == NULL || iterm->id != pin) + if (iterm == NULL) return -EINVAL; memset(input, 0, sizeof(*input)); diff --git a/drivers/media/usb/uvc/uvc_video.c b/drivers/media/usb/uvc/uvc_video.c index 1b4cc934109e..6d3dfa4e0bb2 100644 --- a/drivers/media/usb/uvc/uvc_video.c +++ b/drivers/media/usb/uvc/uvc_video.c @@ -383,7 +383,6 @@ int uvc_probe_video(struct uvc_streaming *stream, struct uvc_streaming_control *probe) { struct uvc_streaming_control probe_min, probe_max; - u16 bandwidth; unsigned int i; int ret; @@ -421,8 +420,7 @@ int uvc_probe_video(struct uvc_streaming *stream, if (stream->intf->num_altsetting == 1) break; - bandwidth = probe->dwMaxPayloadTransferSize; - if (bandwidth <= stream->maxpsize) + if (probe->dwMaxPayloadTransferSize <= stream->maxpsize) break; if (stream->dev->quirks & UVC_QUIRK_PROBE_MINMAX) { @@ -1756,25 +1754,17 @@ static void uvc_video_stop_transfer(struct uvc_streaming *stream, /* * Compute the maximum number of bytes per interval for an endpoint. */ -static unsigned int uvc_endpoint_max_bpi(struct usb_device *dev, - struct usb_host_endpoint *ep) +u16 uvc_endpoint_max_bpi(struct usb_device *dev, struct usb_host_endpoint *ep) { u16 psize; - u16 mult; switch (dev->speed) { case USB_SPEED_SUPER: case USB_SPEED_SUPER_PLUS: return le16_to_cpu(ep->ss_ep_comp.wBytesPerInterval); - case USB_SPEED_HIGH: - psize = usb_endpoint_maxp(&ep->desc); - mult = usb_endpoint_maxp_mult(&ep->desc); - return psize * mult; - case USB_SPEED_WIRELESS: - psize = usb_endpoint_maxp(&ep->desc); - return psize; default: psize = usb_endpoint_maxp(&ep->desc); + psize *= usb_endpoint_maxp_mult(&ep->desc); return psize; } } diff --git a/drivers/media/usb/uvc/uvcvideo.h b/drivers/media/usb/uvc/uvcvideo.h index 143230b3275b..c5b4febd2d94 100644 --- a/drivers/media/usb/uvc/uvcvideo.h +++ b/drivers/media/usb/uvc/uvcvideo.h @@ -139,6 +139,9 @@ #define UVC_GUID_FORMAT_H264 \ { 'H', '2', '6', '4', 0x00, 0x00, 0x10, 0x00, \ 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} +#define UVC_GUID_FORMAT_H265 \ + { 'H', '2', '6', '5', 0x00, 0x00, 0x10, 0x00, \ + 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} #define UVC_GUID_FORMAT_Y8I \ { 'Y', '8', 'I', ' ', 0x00, 0x00, 0x10, 0x00, \ 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} @@ -911,6 +914,7 @@ void uvc_simplify_fraction(u32 *numerator, u32 *denominator, u32 uvc_fraction_to_interval(u32 numerator, u32 denominator); struct usb_host_endpoint *uvc_find_endpoint(struct usb_host_interface *alts, u8 epaddr); +u16 uvc_endpoint_max_bpi(struct usb_device *dev, struct usb_host_endpoint *ep); /* Quirks support */ void uvc_video_decode_isight(struct uvc_urb *uvc_urb, diff --git a/drivers/media/v4l2-core/tuner-core.c b/drivers/media/v4l2-core/tuner-core.c index ad9224a18853..2d47c10de062 100644 --- a/drivers/media/v4l2-core/tuner-core.c +++ b/drivers/media/v4l2-core/tuner-core.c @@ -1118,7 +1118,7 @@ static void tuner_status(struct dvb_frontend *fe) if (t->mode != V4L2_TUNER_RADIO) return; if (fe_tuner_ops->get_status) { - u32 tuner_status; + u32 tuner_status = 0; fe_tuner_ops->get_status(&t->fe, &tuner_status); if (tuner_status & TUNER_STATUS_LOCKED) @@ -1258,7 +1258,7 @@ static int tuner_g_tuner(struct v4l2_subdev *sd, struct v4l2_tuner *vt) if (vt->type == t->mode) { vt->rxsubchans = V4L2_TUNER_SUB_MONO | V4L2_TUNER_SUB_STEREO; if (fe_tuner_ops->get_status) { - u32 tuner_status; + u32 tuner_status = 0; fe_tuner_ops->get_status(&t->fe, &tuner_status); vt->rxsubchans = diff --git a/drivers/media/v4l2-core/v4l2-async.c b/drivers/media/v4l2-core/v4l2-async.c index 0404267f1ae4..c6995718237a 100644 --- a/drivers/media/v4l2-core/v4l2-async.c +++ b/drivers/media/v4l2-core/v4l2-async.c @@ -275,6 +275,24 @@ v4l2_async_nf_try_complete(struct v4l2_async_notifier *notifier) static int v4l2_async_nf_try_all_subdevs(struct v4l2_async_notifier *notifier); +static int v4l2_async_create_ancillary_links(struct v4l2_async_notifier *n, + struct v4l2_subdev *sd) +{ + struct media_link *link = NULL; + +#if IS_ENABLED(CONFIG_MEDIA_CONTROLLER) + + if (sd->entity.function != MEDIA_ENT_F_LENS && + sd->entity.function != MEDIA_ENT_F_FLASH) + return 0; + + link = media_create_ancillary_link(&n->sd->entity, &sd->entity); + +#endif + + return IS_ERR(link) ? PTR_ERR(link) : 0; +} + static int v4l2_async_match_notify(struct v4l2_async_notifier *notifier, struct v4l2_device *v4l2_dev, struct v4l2_subdev *sd, @@ -293,6 +311,19 @@ static int v4l2_async_match_notify(struct v4l2_async_notifier *notifier, return ret; } + /* + * Depending of the function of the entities involved, we may want to + * create links between them (for example between a sensor and its lens + * or between a sensor's source pad and the connected device's sink + * pad). + */ + ret = v4l2_async_create_ancillary_links(notifier, sd); + if (ret) { + v4l2_async_nf_call_unbind(notifier, sd, asd); + v4l2_device_unregister_subdev(sd); + return ret; + } + /* Remove from the waiting list */ list_del(&asd->list); sd->asd = asd; @@ -662,7 +693,7 @@ __v4l2_async_nf_add_fwnode_remote(struct v4l2_async_notifier *notif, struct v4l2_async_subdev *asd; struct fwnode_handle *remote; - remote = fwnode_graph_get_remote_port_parent(endpoint); + remote = fwnode_graph_get_remote_endpoint(endpoint); if (!remote) return ERR_PTR(-ENOTCONN); diff --git a/drivers/media/v4l2-core/v4l2-ctrls-core.c b/drivers/media/v4l2-core/v4l2-ctrls-core.c index 8968cec8454e..949c1884d9c1 100644 --- a/drivers/media/v4l2-core/v4l2-ctrls-core.c +++ b/drivers/media/v4l2-core/v4l2-ctrls-core.c @@ -1140,9 +1140,8 @@ int v4l2_ctrl_handler_init_class(struct v4l2_ctrl_handler *hdl, INIT_LIST_HEAD(&hdl->ctrls); INIT_LIST_HEAD(&hdl->ctrl_refs); hdl->nr_of_buckets = 1 + nr_of_controls_hint / 8; - hdl->buckets = kvmalloc_array(hdl->nr_of_buckets, - sizeof(hdl->buckets[0]), - GFP_KERNEL | __GFP_ZERO); + hdl->buckets = kvcalloc(hdl->nr_of_buckets, sizeof(hdl->buckets[0]), + GFP_KERNEL); hdl->error = hdl->buckets ? 0 : -ENOMEM; v4l2_ctrl_handler_init_request(hdl); return hdl->error; diff --git a/drivers/media/v4l2-core/v4l2-ctrls-defs.c b/drivers/media/v4l2-core/v4l2-ctrls-defs.c index 54ca4e6b820b..16f42d2fd359 100644 --- a/drivers/media/v4l2-core/v4l2-ctrls-defs.c +++ b/drivers/media/v4l2-core/v4l2-ctrls-defs.c @@ -572,6 +572,11 @@ const char * const *v4l2_ctrl_get_menu(u32 id) "VBV/CPB Limit", NULL, }; + static const char * const intra_refresh_period_type[] = { + "Random", + "Cyclic", + NULL, + }; switch (id) { case V4L2_CID_MPEG_AUDIO_SAMPLING_FREQ: @@ -705,6 +710,8 @@ const char * const *v4l2_ctrl_get_menu(u32 id) return hevc_start_code; case V4L2_CID_CAMERA_ORIENTATION: return camera_orientation; + case V4L2_CID_MPEG_VIDEO_INTRA_REFRESH_PERIOD_TYPE: + return intra_refresh_period_type; default: return NULL; } @@ -834,6 +841,7 @@ const char *v4l2_ctrl_get_name(u32 id) case V4L2_CID_MPEG_VIDEO_DECODER_SLICE_INTERFACE: return "Decoder Slice Interface"; case V4L2_CID_MPEG_VIDEO_DECODER_MPEG4_DEBLOCK_FILTER: return "MPEG4 Loop Filter Enable"; case V4L2_CID_MPEG_VIDEO_CYCLIC_INTRA_REFRESH_MB: return "Number of Intra Refresh MBs"; + case V4L2_CID_MPEG_VIDEO_INTRA_REFRESH_PERIOD_TYPE: return "Intra Refresh Period Type"; case V4L2_CID_MPEG_VIDEO_INTRA_REFRESH_PERIOD: return "Intra Refresh Period"; case V4L2_CID_MPEG_VIDEO_FRAME_RC_ENABLE: return "Frame Level Rate Control Enable"; case V4L2_CID_MPEG_VIDEO_MB_RC_ENABLE: return "H264 MB Level Rate Control"; @@ -1360,6 +1368,7 @@ void v4l2_ctrl_fill(u32 id, const char **name, enum v4l2_ctrl_type *type, case V4L2_CID_STATELESS_H264_DECODE_MODE: case V4L2_CID_STATELESS_H264_START_CODE: case V4L2_CID_CAMERA_ORIENTATION: + case V4L2_CID_MPEG_VIDEO_INTRA_REFRESH_PERIOD_TYPE: *type = V4L2_CTRL_TYPE_MENU; break; case V4L2_CID_LINK_FREQ: diff --git a/drivers/media/v4l2-core/v4l2-fwnode.c b/drivers/media/v4l2-core/v4l2-fwnode.c index afceb35e500c..3d85a8600f57 100644 --- a/drivers/media/v4l2-core/v4l2-fwnode.c +++ b/drivers/media/v4l2-core/v4l2-fwnode.c @@ -61,6 +61,10 @@ static const struct v4l2_fwnode_bus_conv { V4L2_FWNODE_BUS_TYPE_BT656, V4L2_MBUS_BT656, "Bt.656", + }, { + V4L2_FWNODE_BUS_TYPE_DPI, + V4L2_MBUS_DPI, + "DPI", } }; diff --git a/drivers/media/v4l2-core/v4l2-h264.c b/drivers/media/v4l2-core/v4l2-h264.c index 5633a242520a..72bd64f65198 100644 --- a/drivers/media/v4l2-core/v4l2-h264.c +++ b/drivers/media/v4l2-core/v4l2-h264.c @@ -12,6 +12,12 @@ #include <media/v4l2-h264.h> +/* + * Size of the tempory buffer allocated when printing reference lists. The + * output will be truncated if the size is too small. + */ +static const int tmp_str_size = 1024; + /** * v4l2_h264_init_reflist_builder() - Initialize a P/B0/B1 reference list * builder @@ -34,62 +40,96 @@ v4l2_h264_init_reflist_builder(struct v4l2_h264_reflist_builder *b, cur_frame_num = dec_params->frame_num; memset(b, 0, sizeof(*b)); - if (!(dec_params->flags & V4L2_H264_DECODE_PARAM_FLAG_FIELD_PIC)) + if (!(dec_params->flags & V4L2_H264_DECODE_PARAM_FLAG_FIELD_PIC)) { b->cur_pic_order_count = min(dec_params->bottom_field_order_cnt, dec_params->top_field_order_cnt); - else if (dec_params->flags & V4L2_H264_DECODE_PARAM_FLAG_BOTTOM_FIELD) + b->cur_pic_fields = V4L2_H264_FRAME_REF; + } else if (dec_params->flags & V4L2_H264_DECODE_PARAM_FLAG_BOTTOM_FIELD) { b->cur_pic_order_count = dec_params->bottom_field_order_cnt; - else + b->cur_pic_fields = V4L2_H264_BOTTOM_FIELD_REF; + } else { b->cur_pic_order_count = dec_params->top_field_order_cnt; + b->cur_pic_fields = V4L2_H264_TOP_FIELD_REF; + } for (i = 0; i < V4L2_H264_NUM_DPB_ENTRIES; i++) { - u32 pic_order_count; - if (!(dpb[i].flags & V4L2_H264_DPB_ENTRY_FLAG_ACTIVE)) continue; - b->refs[i].pic_num = dpb[i].pic_num; if (dpb[i].flags & V4L2_H264_DPB_ENTRY_FLAG_LONG_TERM) b->refs[i].longterm = true; /* * Handle frame_num wraparound as described in section * '8.2.4.1 Decoding process for picture numbers' of the spec. - * TODO: This logic will have to be adjusted when we start - * supporting interlaced content. + * For long term references, frame_num is set to + * long_term_frame_idx which requires no wrapping. */ - if (dpb[i].frame_num > cur_frame_num) + if (!b->refs[i].longterm && dpb[i].frame_num > cur_frame_num) b->refs[i].frame_num = (int)dpb[i].frame_num - max_frame_num; else b->refs[i].frame_num = dpb[i].frame_num; - if (dpb[i].fields == V4L2_H264_FRAME_REF) - pic_order_count = min(dpb[i].top_field_order_cnt, - dpb[i].bottom_field_order_cnt); - else if (dpb[i].fields & V4L2_H264_BOTTOM_FIELD_REF) - pic_order_count = dpb[i].bottom_field_order_cnt; - else - pic_order_count = dpb[i].top_field_order_cnt; + b->refs[i].top_field_order_cnt = dpb[i].top_field_order_cnt; + b->refs[i].bottom_field_order_cnt = dpb[i].bottom_field_order_cnt; + + if (b->cur_pic_fields == V4L2_H264_FRAME_REF) { + u8 fields = V4L2_H264_FRAME_REF; + + b->unordered_reflist[b->num_valid].index = i; + b->unordered_reflist[b->num_valid].fields = fields; + b->num_valid++; + continue; + } + + if (dpb[i].fields & V4L2_H264_TOP_FIELD_REF) { + u8 fields = V4L2_H264_TOP_FIELD_REF; + + b->unordered_reflist[b->num_valid].index = i; + b->unordered_reflist[b->num_valid].fields = fields; + b->num_valid++; + } + + if (dpb[i].fields & V4L2_H264_BOTTOM_FIELD_REF) { + u8 fields = V4L2_H264_BOTTOM_FIELD_REF; - b->refs[i].pic_order_count = pic_order_count; - b->unordered_reflist[b->num_valid] = i; - b->num_valid++; + b->unordered_reflist[b->num_valid].index = i; + b->unordered_reflist[b->num_valid].fields = fields; + b->num_valid++; + } } for (i = b->num_valid; i < ARRAY_SIZE(b->unordered_reflist); i++) - b->unordered_reflist[i] = i; + b->unordered_reflist[i].index = i; } EXPORT_SYMBOL_GPL(v4l2_h264_init_reflist_builder); +static s32 v4l2_h264_get_poc(const struct v4l2_h264_reflist_builder *b, + const struct v4l2_h264_reference *ref) +{ + switch (ref->fields) { + case V4L2_H264_FRAME_REF: + return min(b->refs[ref->index].top_field_order_cnt, + b->refs[ref->index].bottom_field_order_cnt); + case V4L2_H264_TOP_FIELD_REF: + return b->refs[ref->index].top_field_order_cnt; + case V4L2_H264_BOTTOM_FIELD_REF: + return b->refs[ref->index].bottom_field_order_cnt; + } + + /* not reached */ + return 0; +} + static int v4l2_h264_p_ref_list_cmp(const void *ptra, const void *ptrb, const void *data) { const struct v4l2_h264_reflist_builder *builder = data; u8 idxa, idxb; - idxa = *((u8 *)ptra); - idxb = *((u8 *)ptrb); + idxa = ((struct v4l2_h264_reference *)ptra)->index; + idxb = ((struct v4l2_h264_reference *)ptrb)->index; if (WARN_ON(idxa >= V4L2_H264_NUM_DPB_ENTRIES || idxb >= V4L2_H264_NUM_DPB_ENTRIES)) @@ -104,15 +144,19 @@ static int v4l2_h264_p_ref_list_cmp(const void *ptra, const void *ptrb, } /* - * Short term pics in descending pic num order, long term ones in - * ascending order. + * For frames, short term pics are in descending pic num order and long + * term ones in ascending order. For fields, the same direction is used + * but with frame_num (wrapped). For frames, the value of pic_num and + * frame_num are the same (see formula (8-28) and (8-29)). For this + * reason we can use frame_num only and share this function between + * frames and fields reflist. */ if (!builder->refs[idxa].longterm) return builder->refs[idxb].frame_num < builder->refs[idxa].frame_num ? -1 : 1; - return builder->refs[idxa].pic_num < builder->refs[idxb].pic_num ? + return builder->refs[idxa].frame_num < builder->refs[idxb].frame_num ? -1 : 1; } @@ -123,8 +167,8 @@ static int v4l2_h264_b0_ref_list_cmp(const void *ptra, const void *ptrb, s32 poca, pocb; u8 idxa, idxb; - idxa = *((u8 *)ptra); - idxb = *((u8 *)ptrb); + idxa = ((struct v4l2_h264_reference *)ptra)->index; + idxb = ((struct v4l2_h264_reference *)ptrb)->index; if (WARN_ON(idxa >= V4L2_H264_NUM_DPB_ENTRIES || idxb >= V4L2_H264_NUM_DPB_ENTRIES)) @@ -138,14 +182,14 @@ static int v4l2_h264_b0_ref_list_cmp(const void *ptra, const void *ptrb, return 1; } - /* Long term pics in ascending pic num order. */ + /* Long term pics in ascending frame num order. */ if (builder->refs[idxa].longterm) - return builder->refs[idxa].pic_num < - builder->refs[idxb].pic_num ? + return builder->refs[idxa].frame_num < + builder->refs[idxb].frame_num ? -1 : 1; - poca = builder->refs[idxa].pic_order_count; - pocb = builder->refs[idxb].pic_order_count; + poca = v4l2_h264_get_poc(builder, ptra); + pocb = v4l2_h264_get_poc(builder, ptrb); /* * Short term pics with POC < cur POC first in POC descending order @@ -168,8 +212,8 @@ static int v4l2_h264_b1_ref_list_cmp(const void *ptra, const void *ptrb, s32 poca, pocb; u8 idxa, idxb; - idxa = *((u8 *)ptra); - idxb = *((u8 *)ptrb); + idxa = ((struct v4l2_h264_reference *)ptra)->index; + idxb = ((struct v4l2_h264_reference *)ptrb)->index; if (WARN_ON(idxa >= V4L2_H264_NUM_DPB_ENTRIES || idxb >= V4L2_H264_NUM_DPB_ENTRIES)) @@ -183,14 +227,14 @@ static int v4l2_h264_b1_ref_list_cmp(const void *ptra, const void *ptrb, return 1; } - /* Long term pics in ascending pic num order. */ + /* Long term pics in ascending frame num order. */ if (builder->refs[idxa].longterm) - return builder->refs[idxa].pic_num < - builder->refs[idxb].pic_num ? + return builder->refs[idxa].frame_num < + builder->refs[idxb].frame_num ? -1 : 1; - poca = builder->refs[idxa].pic_order_count; - pocb = builder->refs[idxb].pic_order_count; + poca = v4l2_h264_get_poc(builder, ptra); + pocb = v4l2_h264_get_poc(builder, ptrb); /* * Short term pics with POC > cur POC first in POC ascending order @@ -206,12 +250,135 @@ static int v4l2_h264_b1_ref_list_cmp(const void *ptra, const void *ptrb, return poca < pocb ? -1 : 1; } +/* + * The references need to be reordered so that references are alternating + * between top and bottom field references starting with the current picture + * parity. This has to be done for short term and long term references + * separately. + */ +static void reorder_field_reflist(const struct v4l2_h264_reflist_builder *b, + struct v4l2_h264_reference *reflist) +{ + struct v4l2_h264_reference tmplist[V4L2_H264_REF_LIST_LEN]; + u8 lt, i = 0, j = 0, k = 0; + + memcpy(tmplist, reflist, sizeof(tmplist[0]) * b->num_valid); + + for (lt = 0; lt <= 1; lt++) { + do { + for (; i < b->num_valid && b->refs[tmplist[i].index].longterm == lt; i++) { + if (tmplist[i].fields == b->cur_pic_fields) { + reflist[k++] = tmplist[i++]; + break; + } + } + + for (; j < b->num_valid && b->refs[tmplist[j].index].longterm == lt; j++) { + if (tmplist[j].fields != b->cur_pic_fields) { + reflist[k++] = tmplist[j++]; + break; + } + } + } while ((i < b->num_valid && b->refs[tmplist[i].index].longterm == lt) || + (j < b->num_valid && b->refs[tmplist[j].index].longterm == lt)); + } +} + +static char ref_type_to_char(u8 ref_type) +{ + switch (ref_type) { + case V4L2_H264_FRAME_REF: + return 'f'; + case V4L2_H264_TOP_FIELD_REF: + return 't'; + case V4L2_H264_BOTTOM_FIELD_REF: + return 'b'; + } + + return '?'; +} + +static const char *format_ref_list_p(const struct v4l2_h264_reflist_builder *builder, + struct v4l2_h264_reference *reflist, + char **out_str) +{ + int n = 0, i; + + *out_str = kmalloc(tmp_str_size, GFP_KERNEL); + + n += snprintf(*out_str + n, tmp_str_size - n, "|"); + + for (i = 0; i < builder->num_valid; i++) { + /* this is pic_num for frame and frame_num (wrapped) for field, + * but for frame pic_num is equal to frame_num (wrapped). + */ + int frame_num = builder->refs[reflist[i].index].frame_num; + bool longterm = builder->refs[reflist[i].index].longterm; + + n += scnprintf(*out_str + n, tmp_str_size - n, "%i%c%c|", + frame_num, longterm ? 'l' : 's', + ref_type_to_char(reflist[i].fields)); + } + + return *out_str; +} + +static void print_ref_list_p(const struct v4l2_h264_reflist_builder *builder, + struct v4l2_h264_reference *reflist) +{ + char *buf = NULL; + + pr_debug("ref_pic_list_p (cur_poc %u%c) %s\n", + builder->cur_pic_order_count, + ref_type_to_char(builder->cur_pic_fields), + format_ref_list_p(builder, reflist, &buf)); + + kfree(buf); +} + +static const char *format_ref_list_b(const struct v4l2_h264_reflist_builder *builder, + struct v4l2_h264_reference *reflist, + char **out_str) +{ + int n = 0, i; + + *out_str = kmalloc(tmp_str_size, GFP_KERNEL); + + n += snprintf(*out_str + n, tmp_str_size - n, "|"); + + for (i = 0; i < builder->num_valid; i++) { + int frame_num = builder->refs[reflist[i].index].frame_num; + u32 poc = v4l2_h264_get_poc(builder, reflist + i); + bool longterm = builder->refs[reflist[i].index].longterm; + + n += scnprintf(*out_str + n, tmp_str_size - n, "%i%c%c|", + longterm ? frame_num : poc, + longterm ? 'l' : 's', + ref_type_to_char(reflist[i].fields)); + } + + return *out_str; +} + +static void print_ref_list_b(const struct v4l2_h264_reflist_builder *builder, + struct v4l2_h264_reference *reflist, u8 list_num) +{ + char *buf = NULL; + + pr_debug("ref_pic_list_b%u (cur_poc %u%c) %s", + list_num, builder->cur_pic_order_count, + ref_type_to_char(builder->cur_pic_fields), + format_ref_list_b(builder, reflist, &buf)); + + kfree(buf); +} + /** * v4l2_h264_build_p_ref_list() - Build the P reference list * * @builder: reference list builder context - * @reflist: 16-bytes array used to store the P reference list. Each entry - * is an index in the DPB + * @reflist: 32 sized array used to store the P reference list. Each entry + * is a v4l2_h264_reference structure * * This functions builds the P reference lists. This procedure is describe in * section '8.2.4 Decoding process for reference picture lists construction' @@ -220,12 +387,17 @@ static int v4l2_h264_b1_ref_list_cmp(const void *ptra, const void *ptrb, */ void v4l2_h264_build_p_ref_list(const struct v4l2_h264_reflist_builder *builder, - u8 *reflist) + struct v4l2_h264_reference *reflist) { memcpy(reflist, builder->unordered_reflist, sizeof(builder->unordered_reflist[0]) * builder->num_valid); sort_r(reflist, builder->num_valid, sizeof(*reflist), v4l2_h264_p_ref_list_cmp, NULL, builder); + + if (builder->cur_pic_fields != V4L2_H264_FRAME_REF) + reorder_field_reflist(builder, reflist); + + print_ref_list_p(builder, reflist); } EXPORT_SYMBOL_GPL(v4l2_h264_build_p_ref_list); @@ -233,10 +405,10 @@ EXPORT_SYMBOL_GPL(v4l2_h264_build_p_ref_list); * v4l2_h264_build_b_ref_lists() - Build the B0/B1 reference lists * * @builder: reference list builder context - * @b0_reflist: 16-bytes array used to store the B0 reference list. Each entry - * is an index in the DPB - * @b1_reflist: 16-bytes array used to store the B1 reference list. Each entry - * is an index in the DPB + * @b0_reflist: 32 sized array used to store the B0 reference list. Each entry + * is a v4l2_h264_reference structure + * @b1_reflist: 32 sized array used to store the B1 reference list. Each entry + * is a v4l2_h264_reference structure * * This functions builds the B0/B1 reference lists. This procedure is described * in section '8.2.4 Decoding process for reference picture lists construction' @@ -245,7 +417,8 @@ EXPORT_SYMBOL_GPL(v4l2_h264_build_p_ref_list); */ void v4l2_h264_build_b_ref_lists(const struct v4l2_h264_reflist_builder *builder, - u8 *b0_reflist, u8 *b1_reflist) + struct v4l2_h264_reference *b0_reflist, + struct v4l2_h264_reference *b1_reflist) { memcpy(b0_reflist, builder->unordered_reflist, sizeof(builder->unordered_reflist[0]) * builder->num_valid); @@ -257,9 +430,17 @@ v4l2_h264_build_b_ref_lists(const struct v4l2_h264_reflist_builder *builder, sort_r(b1_reflist, builder->num_valid, sizeof(*b1_reflist), v4l2_h264_b1_ref_list_cmp, NULL, builder); + if (builder->cur_pic_fields != V4L2_H264_FRAME_REF) { + reorder_field_reflist(builder, b0_reflist); + reorder_field_reflist(builder, b1_reflist); + } + if (builder->num_valid > 1 && !memcmp(b1_reflist, b0_reflist, builder->num_valid)) swap(b1_reflist[0], b1_reflist[1]); + + print_ref_list_b(builder, b0_reflist, 0); + print_ref_list_b(builder, b1_reflist, 1); } EXPORT_SYMBOL_GPL(v4l2_h264_build_b_ref_lists); diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index 96e307fe3aab..21470de62d72 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -18,6 +18,7 @@ #include <linux/videodev2.h> +#include <media/media-device.h> /* for media_set_bus_info() */ #include <media/v4l2-common.h> #include <media/v4l2-ioctl.h> #include <media/v4l2-ctrls.h> @@ -1052,6 +1053,9 @@ static int v4l_querycap(const struct v4l2_ioctl_ops *ops, cap->device_caps = vfd->device_caps; cap->capabilities = vfd->device_caps | V4L2_CAP_DEVICE_CAPS; + media_set_bus_info(cap->bus_info, sizeof(cap->bus_info), + vfd->dev_parent); + ret = ops->vidioc_querycap(file, fh, cap); /* @@ -1265,6 +1269,7 @@ static void v4l_fill_fmtdesc(struct v4l2_fmtdesc *fmt) case V4L2_PIX_FMT_Y16_BE: descr = "16-bit Greyscale BE"; break; case V4L2_PIX_FMT_Y10BPACK: descr = "10-bit Greyscale (Packed)"; break; case V4L2_PIX_FMT_Y10P: descr = "10-bit Greyscale (MIPI Packed)"; break; + case V4L2_PIX_FMT_IPU3_Y10: descr = "10-bit greyscale (IPU3 Packed)"; break; case V4L2_PIX_FMT_Y8I: descr = "Interleaved 8-bit Greyscale"; break; case V4L2_PIX_FMT_Y12I: descr = "Interleaved 12-bit Greyscale"; break; case V4L2_PIX_FMT_Z16: descr = "16-bit Depth"; break; @@ -1441,6 +1446,8 @@ static void v4l_fill_fmtdesc(struct v4l2_fmtdesc *fmt) case V4L2_PIX_FMT_SE401: descr = "GSPCA SE401"; break; case V4L2_PIX_FMT_S5C_UYVY_JPG: descr = "S5C73MX interleaved UYVY/JPEG"; break; case V4L2_PIX_FMT_MT21C: descr = "Mediatek Compressed Format"; break; + case V4L2_PIX_FMT_QC08C: descr = "QCOM Compressed 8-bit Format"; break; + case V4L2_PIX_FMT_QC10C: descr = "QCOM Compressed 10-bit Format"; break; default: if (fmt->description[0]) return; diff --git a/drivers/media/v4l2-core/v4l2-mem2mem.c b/drivers/media/v4l2-core/v4l2-mem2mem.c index 675e22895ebe..6469f9a25a4e 100644 --- a/drivers/media/v4l2-core/v4l2-mem2mem.c +++ b/drivers/media/v4l2-core/v4l2-mem2mem.c @@ -68,16 +68,16 @@ static const char * const m2m_entity_name[] = { * struct v4l2_m2m_dev - per-device context * @source: &struct media_entity pointer with the source entity * Used only when the M2M device is registered via - * v4l2_m2m_unregister_media_controller(). + * v4l2_m2m_register_media_controller(). * @source_pad: &struct media_pad with the source pad. * Used only when the M2M device is registered via - * v4l2_m2m_unregister_media_controller(). + * v4l2_m2m_register_media_controller(). * @sink: &struct media_entity pointer with the sink entity * Used only when the M2M device is registered via - * v4l2_m2m_unregister_media_controller(). + * v4l2_m2m_register_media_controller(). * @sink_pad: &struct media_pad with the sink pad. * Used only when the M2M device is registered via - * v4l2_m2m_unregister_media_controller(). + * v4l2_m2m_register_media_controller(). * @proc: &struct media_entity pointer with the M2M device itself. * @proc_pads: &struct media_pad with the @proc pads. * Used only when the M2M device is registered via @@ -336,6 +336,7 @@ static void __v4l2_m2m_try_queue(struct v4l2_m2m_dev *m2m_dev, if (src && dst && dst->is_held && dst->vb2_buf.copied_timestamp && dst->vb2_buf.timestamp != src->vb2_buf.timestamp) { + dprintk("Timestamp mismatch, returning held capture buffer\n"); dst->is_held = false; v4l2_m2m_dst_buf_remove(m2m_ctx); v4l2_m2m_buf_done(dst, VB2_BUF_STATE_DONE); diff --git a/drivers/media/v4l2-core/v4l2-subdev.c b/drivers/media/v4l2-core/v4l2-subdev.c index 30eb50407db5..5c27bac772ea 100644 --- a/drivers/media/v4l2-core/v4l2-subdev.c +++ b/drivers/media/v4l2-core/v4l2-subdev.c @@ -27,8 +27,9 @@ static int subdev_fh_init(struct v4l2_subdev_fh *fh, struct v4l2_subdev *sd) { struct v4l2_subdev_state *state; + static struct lock_class_key key; - state = v4l2_subdev_alloc_state(sd); + state = __v4l2_subdev_state_alloc(sd, "fh->state->lock", &key); if (IS_ERR(state)) return PTR_ERR(state); @@ -39,7 +40,7 @@ static int subdev_fh_init(struct v4l2_subdev_fh *fh, struct v4l2_subdev *sd) static void subdev_fh_free(struct v4l2_subdev_fh *fh) { - v4l2_subdev_free_state(fh->state); + __v4l2_subdev_state_free(fh->state); fh->state = NULL; } @@ -63,7 +64,7 @@ static int subdev_open(struct file *file) v4l2_fh_init(&subdev_fh->vfh, vdev); v4l2_fh_add(&subdev_fh->vfh); file->private_data = &subdev_fh->vfh; -#if defined(CONFIG_MEDIA_CONTROLLER) + if (sd->v4l2_dev->mdev && sd->entity.graph_obj.mdev->dev) { struct module *owner; @@ -74,7 +75,6 @@ static int subdev_open(struct file *file) } subdev_fh->owner = owner; } -#endif if (sd->internal_ops && sd->internal_ops->open) { ret = sd->internal_ops->open(sd, subdev_fh); @@ -318,14 +318,55 @@ static int call_get_mbus_config(struct v4l2_subdev *sd, unsigned int pad, sd->ops->pad->get_mbus_config(sd, pad, config); } +#ifdef CONFIG_MEDIA_CONTROLLER +/* + * Create state-management wrapper for pad ops dealing with subdev state. The + * wrapper handles the case where the caller does not provide the called + * subdev's state. This should be removed when all the callers are fixed. + */ +#define DEFINE_STATE_WRAPPER(f, arg_type) \ + static int call_##f##_state(struct v4l2_subdev *sd, \ + struct v4l2_subdev_state *_state, \ + arg_type *arg) \ + { \ + struct v4l2_subdev_state *state = _state; \ + int ret; \ + if (!_state) \ + state = v4l2_subdev_lock_and_get_active_state(sd); \ + ret = call_##f(sd, state, arg); \ + if (!_state && state) \ + v4l2_subdev_unlock_state(state); \ + return ret; \ + } + +#else /* CONFIG_MEDIA_CONTROLLER */ + +#define DEFINE_STATE_WRAPPER(f, arg_type) \ + static int call_##f##_state(struct v4l2_subdev *sd, \ + struct v4l2_subdev_state *state, \ + arg_type *arg) \ + { \ + return call_##f(sd, state, arg); \ + } + +#endif /* CONFIG_MEDIA_CONTROLLER */ + +DEFINE_STATE_WRAPPER(get_fmt, struct v4l2_subdev_format); +DEFINE_STATE_WRAPPER(set_fmt, struct v4l2_subdev_format); +DEFINE_STATE_WRAPPER(enum_mbus_code, struct v4l2_subdev_mbus_code_enum); +DEFINE_STATE_WRAPPER(enum_frame_size, struct v4l2_subdev_frame_size_enum); +DEFINE_STATE_WRAPPER(enum_frame_interval, struct v4l2_subdev_frame_interval_enum); +DEFINE_STATE_WRAPPER(get_selection, struct v4l2_subdev_selection); +DEFINE_STATE_WRAPPER(set_selection, struct v4l2_subdev_selection); + static const struct v4l2_subdev_pad_ops v4l2_subdev_call_pad_wrappers = { - .get_fmt = call_get_fmt, - .set_fmt = call_set_fmt, - .enum_mbus_code = call_enum_mbus_code, - .enum_frame_size = call_enum_frame_size, - .enum_frame_interval = call_enum_frame_interval, - .get_selection = call_get_selection, - .set_selection = call_set_selection, + .get_fmt = call_get_fmt_state, + .set_fmt = call_set_fmt_state, + .enum_mbus_code = call_enum_mbus_code_state, + .enum_frame_size = call_enum_frame_size_state, + .enum_frame_interval = call_enum_frame_interval_state, + .get_selection = call_get_selection_state, + .set_selection = call_set_selection_state, .get_edid = call_get_edid, .set_edid = call_set_edid, .dv_timings_cap = call_dv_timings_cap, @@ -345,12 +386,50 @@ const struct v4l2_subdev_ops v4l2_subdev_call_wrappers = { EXPORT_SYMBOL(v4l2_subdev_call_wrappers); #if defined(CONFIG_VIDEO_V4L2_SUBDEV_API) -static long subdev_do_ioctl(struct file *file, unsigned int cmd, void *arg) + +static struct v4l2_subdev_state * +subdev_ioctl_get_state(struct v4l2_subdev *sd, struct v4l2_subdev_fh *subdev_fh, + unsigned int cmd, void *arg) +{ + u32 which; + + switch (cmd) { + default: + return NULL; + case VIDIOC_SUBDEV_G_FMT: + case VIDIOC_SUBDEV_S_FMT: + which = ((struct v4l2_subdev_format *)arg)->which; + break; + case VIDIOC_SUBDEV_G_CROP: + case VIDIOC_SUBDEV_S_CROP: + which = ((struct v4l2_subdev_crop *)arg)->which; + break; + case VIDIOC_SUBDEV_ENUM_MBUS_CODE: + which = ((struct v4l2_subdev_mbus_code_enum *)arg)->which; + break; + case VIDIOC_SUBDEV_ENUM_FRAME_SIZE: + which = ((struct v4l2_subdev_frame_size_enum *)arg)->which; + break; + case VIDIOC_SUBDEV_ENUM_FRAME_INTERVAL: + which = ((struct v4l2_subdev_frame_interval_enum *)arg)->which; + break; + case VIDIOC_SUBDEV_G_SELECTION: + case VIDIOC_SUBDEV_S_SELECTION: + which = ((struct v4l2_subdev_selection *)arg)->which; + break; + } + + return which == V4L2_SUBDEV_FORMAT_TRY ? + subdev_fh->state : + v4l2_subdev_get_unlocked_active_state(sd); +} + +static long subdev_do_ioctl(struct file *file, unsigned int cmd, void *arg, + struct v4l2_subdev_state *state) { struct video_device *vdev = video_devdata(file); struct v4l2_subdev *sd = vdev_to_v4l2_subdev(vdev); struct v4l2_fh *vfh = file->private_data; - struct v4l2_subdev_fh *subdev_fh = to_v4l2_subdev_fh(vfh); bool ro_subdev = test_bit(V4L2_FL_SUBDEV_RO_DEVNODE, &vdev->flags); int rval; @@ -476,7 +555,7 @@ static long subdev_do_ioctl(struct file *file, unsigned int cmd, void *arg) memset(format->reserved, 0, sizeof(format->reserved)); memset(format->format.reserved, 0, sizeof(format->format.reserved)); - return v4l2_subdev_call(sd, pad, get_fmt, subdev_fh->state, format); + return v4l2_subdev_call(sd, pad, get_fmt, state, format); } case VIDIOC_SUBDEV_S_FMT: { @@ -487,7 +566,7 @@ static long subdev_do_ioctl(struct file *file, unsigned int cmd, void *arg) memset(format->reserved, 0, sizeof(format->reserved)); memset(format->format.reserved, 0, sizeof(format->format.reserved)); - return v4l2_subdev_call(sd, pad, set_fmt, subdev_fh->state, format); + return v4l2_subdev_call(sd, pad, set_fmt, state, format); } case VIDIOC_SUBDEV_G_CROP: { @@ -501,7 +580,7 @@ static long subdev_do_ioctl(struct file *file, unsigned int cmd, void *arg) sel.target = V4L2_SEL_TGT_CROP; rval = v4l2_subdev_call( - sd, pad, get_selection, subdev_fh->state, &sel); + sd, pad, get_selection, state, &sel); crop->rect = sel.r; @@ -523,7 +602,7 @@ static long subdev_do_ioctl(struct file *file, unsigned int cmd, void *arg) sel.r = crop->rect; rval = v4l2_subdev_call( - sd, pad, set_selection, subdev_fh->state, &sel); + sd, pad, set_selection, state, &sel); crop->rect = sel.r; @@ -534,7 +613,7 @@ static long subdev_do_ioctl(struct file *file, unsigned int cmd, void *arg) struct v4l2_subdev_mbus_code_enum *code = arg; memset(code->reserved, 0, sizeof(code->reserved)); - return v4l2_subdev_call(sd, pad, enum_mbus_code, subdev_fh->state, + return v4l2_subdev_call(sd, pad, enum_mbus_code, state, code); } @@ -542,7 +621,7 @@ static long subdev_do_ioctl(struct file *file, unsigned int cmd, void *arg) struct v4l2_subdev_frame_size_enum *fse = arg; memset(fse->reserved, 0, sizeof(fse->reserved)); - return v4l2_subdev_call(sd, pad, enum_frame_size, subdev_fh->state, + return v4l2_subdev_call(sd, pad, enum_frame_size, state, fse); } @@ -567,7 +646,7 @@ static long subdev_do_ioctl(struct file *file, unsigned int cmd, void *arg) struct v4l2_subdev_frame_interval_enum *fie = arg; memset(fie->reserved, 0, sizeof(fie->reserved)); - return v4l2_subdev_call(sd, pad, enum_frame_interval, subdev_fh->state, + return v4l2_subdev_call(sd, pad, enum_frame_interval, state, fie); } @@ -576,7 +655,7 @@ static long subdev_do_ioctl(struct file *file, unsigned int cmd, void *arg) memset(sel->reserved, 0, sizeof(sel->reserved)); return v4l2_subdev_call( - sd, pad, get_selection, subdev_fh->state, sel); + sd, pad, get_selection, state, sel); } case VIDIOC_SUBDEV_S_SELECTION: { @@ -587,7 +666,7 @@ static long subdev_do_ioctl(struct file *file, unsigned int cmd, void *arg) memset(sel->reserved, 0, sizeof(sel->reserved)); return v4l2_subdev_call( - sd, pad, set_selection, subdev_fh->state, sel); + sd, pad, set_selection, state, sel); } case VIDIOC_G_EDID: { @@ -666,8 +745,24 @@ static long subdev_do_ioctl_lock(struct file *file, unsigned int cmd, void *arg) if (lock && mutex_lock_interruptible(lock)) return -ERESTARTSYS; - if (video_is_registered(vdev)) - ret = subdev_do_ioctl(file, cmd, arg); + + if (video_is_registered(vdev)) { + struct v4l2_subdev *sd = vdev_to_v4l2_subdev(vdev); + struct v4l2_fh *vfh = file->private_data; + struct v4l2_subdev_fh *subdev_fh = to_v4l2_subdev_fh(vfh); + struct v4l2_subdev_state *state; + + state = subdev_ioctl_get_state(sd, subdev_fh, cmd, arg); + + if (state) + v4l2_subdev_lock_state(state); + + ret = subdev_do_ioctl(file, cmd, arg, state); + + if (state) + v4l2_subdev_unlock_state(state); + } + if (lock) mutex_unlock(lock); return ret; @@ -824,7 +919,7 @@ v4l2_subdev_link_validate_get_format(struct media_pad *pad, fmt->which = V4L2_SUBDEV_FORMAT_ACTIVE; fmt->pad = pad->index; - return v4l2_subdev_call(sd, pad, get_fmt, NULL, fmt); + return v4l2_subdev_call_state_active(sd, pad, get_fmt, fmt); } WARN(pad->entity->function != MEDIA_ENT_F_IO_V4L, @@ -862,7 +957,9 @@ int v4l2_subdev_link_validate(struct media_link *link) } EXPORT_SYMBOL_GPL(v4l2_subdev_link_validate); -struct v4l2_subdev_state *v4l2_subdev_alloc_state(struct v4l2_subdev *sd) +struct v4l2_subdev_state * +__v4l2_subdev_state_alloc(struct v4l2_subdev *sd, const char *lock_name, + struct lock_class_key *lock_key) { struct v4l2_subdev_state *state; int ret; @@ -871,17 +968,29 @@ struct v4l2_subdev_state *v4l2_subdev_alloc_state(struct v4l2_subdev *sd) if (!state) return ERR_PTR(-ENOMEM); + __mutex_init(&state->_lock, lock_name, lock_key); + if (sd->state_lock) + state->lock = sd->state_lock; + else + state->lock = &state->_lock; + if (sd->entity.num_pads) { - state->pads = kvmalloc_array(sd->entity.num_pads, - sizeof(*state->pads), - GFP_KERNEL | __GFP_ZERO); + state->pads = kvcalloc(sd->entity.num_pads, + sizeof(*state->pads), GFP_KERNEL); if (!state->pads) { ret = -ENOMEM; goto err; } } + /* + * There can be no race at this point, but we lock the state anyway to + * satisfy lockdep checks. + */ + v4l2_subdev_lock_state(state); ret = v4l2_subdev_call(sd, pad, init_cfg, state); + v4l2_subdev_unlock_state(state); + if (ret < 0 && ret != -ENOIOCTLCMD) goto err; @@ -895,17 +1004,63 @@ err: return ERR_PTR(ret); } -EXPORT_SYMBOL_GPL(v4l2_subdev_alloc_state); +EXPORT_SYMBOL_GPL(__v4l2_subdev_state_alloc); -void v4l2_subdev_free_state(struct v4l2_subdev_state *state) +void __v4l2_subdev_state_free(struct v4l2_subdev_state *state) { if (!state) return; + mutex_destroy(&state->_lock); + kvfree(state->pads); kfree(state); } -EXPORT_SYMBOL_GPL(v4l2_subdev_free_state); +EXPORT_SYMBOL_GPL(__v4l2_subdev_state_free); + +int __v4l2_subdev_init_finalize(struct v4l2_subdev *sd, const char *name, + struct lock_class_key *key) +{ + struct v4l2_subdev_state *state; + + state = __v4l2_subdev_state_alloc(sd, name, key); + if (IS_ERR(state)) + return PTR_ERR(state); + + sd->active_state = state; + + return 0; +} +EXPORT_SYMBOL_GPL(__v4l2_subdev_init_finalize); + +void v4l2_subdev_cleanup(struct v4l2_subdev *sd) +{ + __v4l2_subdev_state_free(sd->active_state); + sd->active_state = NULL; +} +EXPORT_SYMBOL_GPL(v4l2_subdev_cleanup); + +#if defined(CONFIG_VIDEO_V4L2_SUBDEV_API) + +int v4l2_subdev_get_fmt(struct v4l2_subdev *sd, struct v4l2_subdev_state *state, + struct v4l2_subdev_format *format) +{ + struct v4l2_mbus_framefmt *fmt; + + if (format->pad >= sd->entity.num_pads) + return -EINVAL; + + fmt = v4l2_subdev_get_pad_format(sd, state, format->pad); + if (!fmt) + return -EINVAL; + + format->format = *fmt; + + return 0; +} +EXPORT_SYMBOL_GPL(v4l2_subdev_get_fmt); + +#endif /* CONFIG_VIDEO_V4L2_SUBDEV_API */ #endif /* CONFIG_MEDIA_CONTROLLER */ diff --git a/drivers/memory/atmel-ebi.c b/drivers/memory/atmel-ebi.c index c267283b01fd..e749dcb3ddea 100644 --- a/drivers/memory/atmel-ebi.c +++ b/drivers/memory/atmel-ebi.c @@ -544,20 +544,27 @@ static int atmel_ebi_probe(struct platform_device *pdev) smc_np = of_parse_phandle(dev->of_node, "atmel,smc", 0); ebi->smc.regmap = syscon_node_to_regmap(smc_np); - if (IS_ERR(ebi->smc.regmap)) - return PTR_ERR(ebi->smc.regmap); + if (IS_ERR(ebi->smc.regmap)) { + ret = PTR_ERR(ebi->smc.regmap); + goto put_node; + } ebi->smc.layout = atmel_hsmc_get_reg_layout(smc_np); - if (IS_ERR(ebi->smc.layout)) - return PTR_ERR(ebi->smc.layout); + if (IS_ERR(ebi->smc.layout)) { + ret = PTR_ERR(ebi->smc.layout); + goto put_node; + } ebi->smc.clk = of_clk_get(smc_np, 0); if (IS_ERR(ebi->smc.clk)) { - if (PTR_ERR(ebi->smc.clk) != -ENOENT) - return PTR_ERR(ebi->smc.clk); + if (PTR_ERR(ebi->smc.clk) != -ENOENT) { + ret = PTR_ERR(ebi->smc.clk); + goto put_node; + } ebi->smc.clk = NULL; } + of_node_put(smc_np); ret = clk_prepare_enable(ebi->smc.clk); if (ret) return ret; @@ -608,6 +615,10 @@ static int atmel_ebi_probe(struct platform_device *pdev) } return of_platform_populate(np, NULL, NULL, dev); + +put_node: + of_node_put(smc_np); + return ret; } static __maybe_unused int atmel_ebi_resume(struct device *dev) diff --git a/drivers/memory/fsl_ifc.c b/drivers/memory/fsl_ifc.c index 2f6939da21cd..e83b61c925a4 100644 --- a/drivers/memory/fsl_ifc.c +++ b/drivers/memory/fsl_ifc.c @@ -287,8 +287,7 @@ static int fsl_ifc_ctrl_probe(struct platform_device *dev) } /* legacy dts may still use "simple-bus" compatible */ - ret = of_platform_populate(dev->dev.of_node, NULL, NULL, - &dev->dev); + ret = of_platform_default_populate(dev->dev.of_node, NULL, &dev->dev); if (ret) goto err_free_nandirq; diff --git a/drivers/memory/renesas-rpc-if.c b/drivers/memory/renesas-rpc-if.c index e4cc64f56019..019a0822bde0 100644 --- a/drivers/memory/renesas-rpc-if.c +++ b/drivers/memory/renesas-rpc-if.c @@ -164,25 +164,39 @@ static const struct regmap_access_table rpcif_volatile_table = { /* - * Custom accessor functions to ensure SMRDR0 and SMWDR0 are always accessed - * with proper width. Requires SMENR_SPIDE to be correctly set before! + * Custom accessor functions to ensure SM[RW]DR[01] are always accessed with + * proper width. Requires rpcif.xfer_size to be correctly set before! */ static int rpcif_reg_read(void *context, unsigned int reg, unsigned int *val) { struct rpcif *rpc = context; - if (reg == RPCIF_SMRDR0 || reg == RPCIF_SMWDR0) { - u32 spide = readl(rpc->base + RPCIF_SMENR) & RPCIF_SMENR_SPIDE(0xF); - - if (spide == 0x8) { + switch (reg) { + case RPCIF_SMRDR0: + case RPCIF_SMWDR0: + switch (rpc->xfer_size) { + case 1: *val = readb(rpc->base + reg); return 0; - } else if (spide == 0xC) { + + case 2: *val = readw(rpc->base + reg); return 0; - } else if (spide != 0xF) { + + case 4: + case 8: + *val = readl(rpc->base + reg); + return 0; + + default: return -EILSEQ; } + + case RPCIF_SMRDR1: + case RPCIF_SMWDR1: + if (rpc->xfer_size != 8) + return -EILSEQ; + break; } *val = readl(rpc->base + reg); @@ -193,18 +207,34 @@ static int rpcif_reg_write(void *context, unsigned int reg, unsigned int val) { struct rpcif *rpc = context; - if (reg == RPCIF_SMRDR0 || reg == RPCIF_SMWDR0) { - u32 spide = readl(rpc->base + RPCIF_SMENR) & RPCIF_SMENR_SPIDE(0xF); - - if (spide == 0x8) { + switch (reg) { + case RPCIF_SMWDR0: + switch (rpc->xfer_size) { + case 1: writeb(val, rpc->base + reg); return 0; - } else if (spide == 0xC) { + + case 2: writew(val, rpc->base + reg); return 0; - } else if (spide != 0xF) { + + case 4: + case 8: + writel(val, rpc->base + reg); + return 0; + + default: return -EILSEQ; } + + case RPCIF_SMWDR1: + if (rpc->xfer_size != 8) + return -EILSEQ; + break; + + case RPCIF_SMRDR0: + case RPCIF_SMRDR1: + return -EPERM; } writel(val, rpc->base + reg); @@ -469,6 +499,7 @@ int rpcif_manual_xfer(struct rpcif *rpc) smenr |= RPCIF_SMENR_SPIDE(rpcif_bits_set(rpc, nbytes)); regmap_write(rpc->regmap, RPCIF_SMENR, smenr); + rpc->xfer_size = nbytes; memcpy(data, rpc->buffer + pos, nbytes); if (nbytes == 8) { @@ -533,6 +564,7 @@ int rpcif_manual_xfer(struct rpcif *rpc) regmap_write(rpc->regmap, RPCIF_SMENR, smenr); regmap_write(rpc->regmap, RPCIF_SMCR, rpc->smcr | RPCIF_SMCR_SPIE); + rpc->xfer_size = nbytes; ret = wait_msg_xfer_end(rpc); if (ret) goto err_out; @@ -651,6 +683,7 @@ static int rpcif_probe(struct platform_device *pdev) struct platform_device *vdev; struct device_node *flash; const char *name; + int ret; flash = of_get_next_child(pdev->dev.of_node, NULL); if (!flash) { @@ -674,7 +707,14 @@ static int rpcif_probe(struct platform_device *pdev) return -ENOMEM; vdev->dev.parent = &pdev->dev; platform_set_drvdata(pdev, vdev); - return platform_device_add(vdev); + + ret = platform_device_add(vdev); + if (ret) { + platform_device_put(vdev); + return ret; + } + + return 0; } static int rpcif_remove(struct platform_device *pdev) diff --git a/drivers/message/fusion/mptbase.c b/drivers/message/fusion/mptbase.c index e90adfa57950..9b3ba2df71c7 100644 --- a/drivers/message/fusion/mptbase.c +++ b/drivers/message/fusion/mptbase.c @@ -6658,13 +6658,13 @@ static int mpt_summary_proc_show(struct seq_file *m, void *v) static int mpt_version_proc_show(struct seq_file *m, void *v) { u8 cb_idx; - int scsi, fc, sas, lan, ctl, targ, dmp; + int scsi, fc, sas, lan, ctl, targ; char *drvname; seq_printf(m, "%s-%s\n", "mptlinux", MPT_LINUX_VERSION_COMMON); seq_printf(m, " Fusion MPT base driver\n"); - scsi = fc = sas = lan = ctl = targ = dmp = 0; + scsi = fc = sas = lan = ctl = targ = 0; for (cb_idx = MPT_MAX_PROTOCOL_DRIVERS-1; cb_idx; cb_idx--) { drvname = NULL; if (MptCallbacks[cb_idx]) { diff --git a/drivers/misc/eeprom/at25.c b/drivers/misc/eeprom/at25.c index 91f96abbb3f9..8d169a35cf13 100644 --- a/drivers/misc/eeprom/at25.c +++ b/drivers/misc/eeprom/at25.c @@ -31,6 +31,8 @@ */ #define FM25_SN_LEN 8 /* serial number length */ +#define EE_MAXADDRLEN 3 /* 24 bit addresses, up to 2 MBytes */ + struct at25_data { struct spi_eeprom chip; struct spi_device *spi; @@ -39,6 +41,7 @@ struct at25_data { struct nvmem_config nvmem_config; struct nvmem_device *nvmem; u8 sernum[FM25_SN_LEN]; + u8 command[EE_MAXADDRLEN + 1]; }; #define AT25_WREN 0x06 /* latch the write enable */ @@ -61,8 +64,6 @@ struct at25_data { #define FM25_ID_LEN 9 /* ID length */ -#define EE_MAXADDRLEN 3 /* 24 bit addresses, up to 2 MBytes */ - /* * Specs often allow 5ms for a page write, sometimes 20ms; * it's important to recover from write timeouts. @@ -78,7 +79,6 @@ static int at25_ee_read(void *priv, unsigned int offset, { struct at25_data *at25 = priv; char *buf = val; - u8 command[EE_MAXADDRLEN + 1]; u8 *cp; ssize_t status; struct spi_transfer t[2]; @@ -92,12 +92,15 @@ static int at25_ee_read(void *priv, unsigned int offset, if (unlikely(!count)) return -EINVAL; - cp = command; + cp = at25->command; instr = AT25_READ; if (at25->chip.flags & EE_INSTR_BIT3_IS_ADDR) if (offset >= BIT(at25->addrlen * 8)) instr |= AT25_INSTR_BIT3; + + mutex_lock(&at25->lock); + *cp++ = instr; /* 8/16/24-bit address is written MSB first */ @@ -116,7 +119,7 @@ static int at25_ee_read(void *priv, unsigned int offset, spi_message_init(&m); memset(t, 0, sizeof(t)); - t[0].tx_buf = command; + t[0].tx_buf = at25->command; t[0].len = at25->addrlen + 1; spi_message_add_tail(&t[0], &m); @@ -124,8 +127,6 @@ static int at25_ee_read(void *priv, unsigned int offset, t[1].len = count; spi_message_add_tail(&t[1], &m); - mutex_lock(&at25->lock); - /* * Read it all at once. * @@ -152,7 +153,7 @@ static int fm25_aux_read(struct at25_data *at25, u8 *buf, uint8_t command, spi_message_init(&m); memset(t, 0, sizeof(t)); - t[0].tx_buf = &command; + t[0].tx_buf = at25->command; t[0].len = 1; spi_message_add_tail(&t[0], &m); @@ -162,6 +163,8 @@ static int fm25_aux_read(struct at25_data *at25, u8 *buf, uint8_t command, mutex_lock(&at25->lock); + at25->command[0] = command; + status = spi_sync(at25->spi, &m); dev_dbg(&at25->spi->dev, "read %d aux bytes --> %d\n", len, status); diff --git a/drivers/misc/habanalabs/common/memory.c b/drivers/misc/habanalabs/common/memory.c index e008d82e4ba3..a13506dd8119 100644 --- a/drivers/misc/habanalabs/common/memory.c +++ b/drivers/misc/habanalabs/common/memory.c @@ -111,10 +111,10 @@ static int alloc_device_memory(struct hl_ctx *ctx, struct hl_mem_in *args, if (contiguous) { if (is_power_of_2(page_size)) - paddr = (u64) (uintptr_t) gen_pool_dma_alloc_align(vm->dram_pg_pool, - total_size, NULL, page_size); + paddr = (uintptr_t) gen_pool_dma_alloc_align(vm->dram_pg_pool, + total_size, NULL, page_size); else - paddr = (u64) (uintptr_t) gen_pool_alloc(vm->dram_pg_pool, total_size); + paddr = gen_pool_alloc(vm->dram_pg_pool, total_size); if (!paddr) { dev_err(hdev->dev, "failed to allocate %llu contiguous pages with total size of %llu\n", @@ -150,12 +150,12 @@ static int alloc_device_memory(struct hl_ctx *ctx, struct hl_mem_in *args, for (i = 0 ; i < num_pgs ; i++) { if (is_power_of_2(page_size)) phys_pg_pack->pages[i] = - (u64) gen_pool_dma_alloc_align(vm->dram_pg_pool, - page_size, NULL, - page_size); + (uintptr_t)gen_pool_dma_alloc_align(vm->dram_pg_pool, + page_size, NULL, + page_size); else - phys_pg_pack->pages[i] = (u64) gen_pool_alloc(vm->dram_pg_pool, - page_size); + phys_pg_pack->pages[i] = gen_pool_alloc(vm->dram_pg_pool, + page_size); if (!phys_pg_pack->pages[i]) { dev_err(hdev->dev, "Failed to allocate device memory (out of memory)\n"); diff --git a/drivers/misc/lkdtm/stackleak.c b/drivers/misc/lkdtm/stackleak.c index 00db21ff115e..82369c6f889e 100644 --- a/drivers/misc/lkdtm/stackleak.c +++ b/drivers/misc/lkdtm/stackleak.c @@ -11,72 +11,125 @@ #include "lkdtm.h" #include <linux/stackleak.h> -void lkdtm_STACKLEAK_ERASING(void) +#if defined(CONFIG_GCC_PLUGIN_STACKLEAK) +/* + * Check that stackleak tracks the lowest stack pointer and erases the stack + * below this as expected. + * + * To prevent the lowest stack pointer changing during the test, IRQs are + * masked and instrumentation of this function is disabled. We assume that the + * compiler will create a fixed-size stack frame for this function. + * + * Any non-inlined function may make further use of the stack, altering the + * lowest stack pointer and/or clobbering poison values. To avoid spurious + * failures we must avoid printing until the end of the test or have already + * encountered a failure condition. + */ +static void noinstr check_stackleak_irqoff(void) { - unsigned long *sp, left, found, i; - const unsigned long check_depth = - STACKLEAK_SEARCH_DEPTH / sizeof(unsigned long); + const unsigned long task_stack_base = (unsigned long)task_stack_page(current); + const unsigned long task_stack_low = stackleak_task_low_bound(current); + const unsigned long task_stack_high = stackleak_task_high_bound(current); + const unsigned long current_sp = current_stack_pointer; + const unsigned long lowest_sp = current->lowest_stack; + unsigned long untracked_high; + unsigned long poison_high, poison_low; bool test_failed = false; /* - * For the details about the alignment of the poison values, see - * the comment in stackleak_track_stack(). + * Check that the current and lowest recorded stack pointer values fall + * within the expected task stack boundaries. These tests should never + * fail unless the boundaries are incorrect or we're clobbering the + * STACK_END_MAGIC, and in either casee something is seriously wrong. */ - sp = PTR_ALIGN(&i, sizeof(unsigned long)); - - left = ((unsigned long)sp & (THREAD_SIZE - 1)) / sizeof(unsigned long); - sp--; + if (current_sp < task_stack_low || current_sp >= task_stack_high) { + pr_err("FAIL: current_stack_pointer (0x%lx) outside of task stack bounds [0x%lx..0x%lx]\n", + current_sp, task_stack_low, task_stack_high - 1); + test_failed = true; + goto out; + } + if (lowest_sp < task_stack_low || lowest_sp >= task_stack_high) { + pr_err("FAIL: current->lowest_stack (0x%lx) outside of task stack bounds [0x%lx..0x%lx]\n", + lowest_sp, task_stack_low, task_stack_high - 1); + test_failed = true; + goto out; + } /* - * One 'long int' at the bottom of the thread stack is reserved - * and not poisoned. + * Depending on what has run prior to this test, the lowest recorded + * stack pointer could be above or below the current stack pointer. + * Start from the lowest of the two. + * + * Poison values are naturally-aligned unsigned longs. As the current + * stack pointer might not be sufficiently aligned, we must align + * downwards to find the lowest known stack pointer value. This is the + * high boundary for a portion of the stack which may have been used + * without being tracked, and has to be scanned for poison. */ - if (left > 1) { - left--; - } else { - pr_err("FAIL: not enough stack space for the test\n"); - test_failed = true; - goto end; - } + untracked_high = min(current_sp, lowest_sp); + untracked_high = ALIGN_DOWN(untracked_high, sizeof(unsigned long)); - pr_info("checking unused part of the thread stack (%lu bytes)...\n", - left * sizeof(unsigned long)); + /* + * Find the top of the poison in the same way as the erasing code. + */ + poison_high = stackleak_find_top_of_poison(task_stack_low, untracked_high); /* - * Search for 'check_depth' poison values in a row (just like - * stackleak_erase() does). + * Check whether the poisoned portion of the stack (if any) consists + * entirely of poison. This verifies the entries that + * stackleak_find_top_of_poison() should have checked. */ - for (i = 0, found = 0; i < left && found <= check_depth; i++) { - if (*(sp - i) == STACKLEAK_POISON) - found++; - else - found = 0; - } + poison_low = poison_high; + while (poison_low > task_stack_low) { + poison_low -= sizeof(unsigned long); + + if (*(unsigned long *)poison_low == STACKLEAK_POISON) + continue; - if (found <= check_depth) { - pr_err("FAIL: the erased part is not found (checked %lu bytes)\n", - i * sizeof(unsigned long)); + pr_err("FAIL: non-poison value %lu bytes below poison boundary: 0x%lx\n", + poison_high - poison_low, *(unsigned long *)poison_low); test_failed = true; - goto end; } - pr_info("the erased part begins after %lu not poisoned bytes\n", - (i - found) * sizeof(unsigned long)); - - /* The rest of thread stack should be erased */ - for (; i < left; i++) { - if (*(sp - i) != STACKLEAK_POISON) { - pr_err("FAIL: bad value number %lu in the erased part: 0x%lx\n", - i, *(sp - i)); - test_failed = true; - } - } + pr_info("stackleak stack usage:\n" + " high offset: %lu bytes\n" + " current: %lu bytes\n" + " lowest: %lu bytes\n" + " tracked: %lu bytes\n" + " untracked: %lu bytes\n" + " poisoned: %lu bytes\n" + " low offset: %lu bytes\n", + task_stack_base + THREAD_SIZE - task_stack_high, + task_stack_high - current_sp, + task_stack_high - lowest_sp, + task_stack_high - untracked_high, + untracked_high - poison_high, + poison_high - task_stack_low, + task_stack_low - task_stack_base); -end: +out: if (test_failed) { pr_err("FAIL: the thread stack is NOT properly erased!\n"); - pr_expected_config(CONFIG_GCC_PLUGIN_STACKLEAK); } else { pr_info("OK: the rest of the thread stack is properly erased\n"); } } + +void lkdtm_STACKLEAK_ERASING(void) +{ + unsigned long flags; + + local_irq_save(flags); + check_stackleak_irqoff(); + local_irq_restore(flags); +} +#else /* defined(CONFIG_GCC_PLUGIN_STACKLEAK) */ +void lkdtm_STACKLEAK_ERASING(void) +{ + if (IS_ENABLED(CONFIG_HAVE_ARCH_STACKLEAK)) { + pr_err("XFAIL: stackleak is not enabled (CONFIG_GCC_PLUGIN_STACKLEAK=n)\n"); + } else { + pr_err("XFAIL: stackleak is not supported on this arch (HAVE_ARCH_STACKLEAK=n)\n"); + } +} +#endif /* defined(CONFIG_GCC_PLUGIN_STACKLEAK) */ diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index 4e67c1403cc9..1259ca22d625 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -126,6 +126,7 @@ struct mmc_blk_data { #define MMC_BLK_DISCARD BIT(2) #define MMC_BLK_SECDISCARD BIT(3) #define MMC_BLK_CQE_RECOVERY BIT(4) +#define MMC_BLK_TRIM BIT(5) /* * Only set in main mmc_blk_data associated @@ -330,7 +331,7 @@ static struct attribute *mmc_disk_attrs[] = { static umode_t mmc_disk_attrs_is_visible(struct kobject *kobj, struct attribute *a, int n) { - struct device *dev = container_of(kobj, struct device, kobj); + struct device *dev = kobj_to_dev(kobj); struct mmc_blk_data *md = mmc_blk_get(dev_to_disk(dev)); umode_t mode = a->mode; @@ -609,11 +610,11 @@ static int __mmc_blk_ioctl_cmd(struct mmc_card *card, struct mmc_blk_data *md, if (idata->rpmb || (cmd.flags & MMC_RSP_R1B) == MMC_RSP_R1B) { /* - * Ensure RPMB/R1B command has completed by polling CMD13 - * "Send Status". + * Ensure RPMB/R1B command has completed by polling CMD13 "Send Status". Here we + * allow to override the default timeout value if a custom timeout is specified. */ - err = mmc_poll_for_busy(card, MMC_BLK_TIMEOUT_MS, false, - MMC_BUSY_IO); + err = mmc_poll_for_busy(card, idata->ic.cmd_timeout_ms ? : MMC_BLK_TIMEOUT_MS, + false, MMC_BUSY_IO); } return err; @@ -676,8 +677,9 @@ static int mmc_blk_ioctl_multi_cmd(struct mmc_blk_data *md, struct mmc_ioc_cmd __user *cmds = user->cmds; struct mmc_card *card; struct mmc_queue *mq; - int i, err = 0, ioc_err = 0; + int err = 0, ioc_err = 0; __u64 num_of_cmds; + unsigned int i, n; struct request *req; if (copy_from_user(&num_of_cmds, &user->num_of_cmds, @@ -690,15 +692,16 @@ static int mmc_blk_ioctl_multi_cmd(struct mmc_blk_data *md, if (num_of_cmds > MMC_IOC_MAX_CMDS) return -EINVAL; - idata = kcalloc(num_of_cmds, sizeof(*idata), GFP_KERNEL); + n = num_of_cmds; + idata = kcalloc(n, sizeof(*idata), GFP_KERNEL); if (!idata) return -ENOMEM; - for (i = 0; i < num_of_cmds; i++) { + for (i = 0; i < n; i++) { idata[i] = mmc_blk_ioctl_copy_from_user(&cmds[i]); if (IS_ERR(idata[i])) { err = PTR_ERR(idata[i]); - num_of_cmds = i; + n = i; goto cmd_err; } /* This will be NULL on non-RPMB ioctl():s */ @@ -725,18 +728,18 @@ static int mmc_blk_ioctl_multi_cmd(struct mmc_blk_data *md, req_to_mmc_queue_req(req)->drv_op = rpmb ? MMC_DRV_OP_IOCTL_RPMB : MMC_DRV_OP_IOCTL; req_to_mmc_queue_req(req)->drv_op_data = idata; - req_to_mmc_queue_req(req)->ioc_count = num_of_cmds; + req_to_mmc_queue_req(req)->ioc_count = n; blk_execute_rq(req, false); ioc_err = req_to_mmc_queue_req(req)->drv_op_result; /* copy to user if data and response */ - for (i = 0; i < num_of_cmds && !err; i++) + for (i = 0; i < n && !err; i++) err = mmc_blk_ioctl_copy_to_user(&cmds[i], idata[i]); blk_mq_free_request(req); cmd_err: - for (i = 0; i < num_of_cmds; i++) { + for (i = 0; i < n; i++) { kfree(idata[i]->buf); kfree(idata[i]); } @@ -993,7 +996,7 @@ static int mmc_blk_reset(struct mmc_blk_data *md, struct mmc_host *host, return -EEXIST; md->reset_done |= type; - err = mmc_hw_reset(host); + err = mmc_hw_reset(host->card); /* Ensure we switch back to the correct partition */ if (err) { struct mmc_blk_data *main_md = @@ -1090,12 +1093,13 @@ static void mmc_blk_issue_drv_op(struct mmc_queue *mq, struct request *req) blk_mq_end_request(req, ret ? BLK_STS_IOERR : BLK_STS_OK); } -static void mmc_blk_issue_discard_rq(struct mmc_queue *mq, struct request *req) +static void mmc_blk_issue_erase_rq(struct mmc_queue *mq, struct request *req, + int type, unsigned int erase_arg) { struct mmc_blk_data *md = mq->blkdata; struct mmc_card *card = md->queue.card; unsigned int from, nr; - int err = 0, type = MMC_BLK_DISCARD; + int err = 0; blk_status_t status = BLK_STS_OK; if (!mmc_can_erase(card)) { @@ -1111,13 +1115,13 @@ static void mmc_blk_issue_discard_rq(struct mmc_queue *mq, struct request *req) if (card->quirks & MMC_QUIRK_INAND_CMD38) { err = mmc_switch(card, EXT_CSD_CMD_SET_NORMAL, INAND_CMD38_ARG_EXT_CSD, - card->erase_arg == MMC_TRIM_ARG ? + erase_arg == MMC_TRIM_ARG ? INAND_CMD38_ARG_TRIM : INAND_CMD38_ARG_ERASE, card->ext_csd.generic_cmd6_time); } if (!err) - err = mmc_erase(card, from, nr, card->erase_arg); + err = mmc_erase(card, from, nr, erase_arg); } while (err == -EIO && !mmc_blk_reset(md, card->host, type)); if (err) status = BLK_STS_IOERR; @@ -1127,6 +1131,19 @@ fail: blk_mq_end_request(req, status); } +static void mmc_blk_issue_trim_rq(struct mmc_queue *mq, struct request *req) +{ + mmc_blk_issue_erase_rq(mq, req, MMC_BLK_TRIM, MMC_TRIM_ARG); +} + +static void mmc_blk_issue_discard_rq(struct mmc_queue *mq, struct request *req) +{ + struct mmc_blk_data *md = mq->blkdata; + struct mmc_card *card = md->queue.card; + + mmc_blk_issue_erase_rq(mq, req, MMC_BLK_DISCARD, card->erase_arg); +} + static void mmc_blk_issue_secdiscard_rq(struct mmc_queue *mq, struct request *req) { @@ -1880,6 +1897,31 @@ static inline bool mmc_blk_rq_error(struct mmc_blk_request *brq) brq->data.error || brq->cmd.resp[0] & CMD_ERRORS; } +static int mmc_spi_err_check(struct mmc_card *card) +{ + u32 status = 0; + int err; + + /* + * SPI does not have a TRAN state we have to wait on, instead the + * card is ready again when it no longer holds the line LOW. + * We still have to ensure two things here before we know the write + * was successful: + * 1. The card has not disconnected during busy and we actually read our + * own pull-up, thinking it was still connected, so ensure it + * still responds. + * 2. Check for any error bits, in particular R1_SPI_IDLE to catch a + * just reconnected card after being disconnected during busy. + */ + err = __mmc_send_status(card, &status, 0); + if (err) + return err; + /* All R1 and R2 bits of SPI are errors in our case */ + if (status) + return -EIO; + return 0; +} + static int mmc_blk_busy_cb(void *cb_data, bool *busy) { struct mmc_blk_busy_data *data = cb_data; @@ -1903,9 +1945,16 @@ static int mmc_blk_card_busy(struct mmc_card *card, struct request *req) struct mmc_blk_busy_data cb_data; int err; - if (mmc_host_is_spi(card->host) || rq_data_dir(req) == READ) + if (rq_data_dir(req) == READ) return 0; + if (mmc_host_is_spi(card->host)) { + err = mmc_spi_err_check(card); + if (err) + mqrq->brq.data.bytes_xfered = 0; + return err; + } + cb_data.card = card; cb_data.status = 0; err = __mmc_poll_for_busy(card->host, 0, MMC_BLK_TIMEOUT_MS, @@ -2295,6 +2344,9 @@ enum mmc_issued mmc_blk_mq_issue_rq(struct mmc_queue *mq, struct request *req) case REQ_OP_SECURE_ERASE: mmc_blk_issue_secdiscard_rq(mq, req); break; + case REQ_OP_WRITE_ZEROES: + mmc_blk_issue_trim_rq(mq, req); + break; case REQ_OP_FLUSH: mmc_blk_issue_flush(mq, req); break; @@ -2350,6 +2402,8 @@ static struct mmc_blk_data *mmc_blk_alloc_req(struct mmc_card *card, struct mmc_blk_data *md; int devidx, ret; char cap_str[10]; + bool cache_enabled = false; + bool fua_enabled = false; devidx = ida_simple_get(&mmc_blk_ida, 0, max_devices, GFP_KERNEL); if (devidx < 0) { @@ -2429,13 +2483,17 @@ static struct mmc_blk_data *mmc_blk_alloc_req(struct mmc_card *card, md->flags |= MMC_BLK_CMD23; } - if (mmc_card_mmc(card) && - md->flags & MMC_BLK_CMD23 && + if (md->flags & MMC_BLK_CMD23 && ((card->ext_csd.rel_param & EXT_CSD_WR_REL_PARAM_EN) || card->ext_csd.rel_sectors)) { md->flags |= MMC_BLK_REL_WR; - blk_queue_write_cache(md->queue.queue, true, true); + fua_enabled = true; + cache_enabled = true; } + if (mmc_cache_enabled(card->host)) + cache_enabled = true; + + blk_queue_write_cache(md->queue.queue, cache_enabled, fua_enabled); string_get_size((u64)size, 512, STRING_UNITS_2, cap_str, sizeof(cap_str)); diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c index 368f10405e13..4b70cbfc6d5d 100644 --- a/drivers/mmc/core/core.c +++ b/drivers/mmc/core/core.c @@ -1988,14 +1988,14 @@ static void mmc_hw_reset_for_init(struct mmc_host *host) { mmc_pwrseq_reset(host); - if (!(host->caps & MMC_CAP_HW_RESET) || !host->ops->hw_reset) + if (!(host->caps & MMC_CAP_HW_RESET) || !host->ops->card_hw_reset) return; - host->ops->hw_reset(host); + host->ops->card_hw_reset(host); } /** * mmc_hw_reset - reset the card in hardware - * @host: MMC host to which the card is attached + * @card: card to be reset * * Hard reset the card. This function is only for upper layers, like the * block layer or card drivers. You cannot use it in host drivers (struct @@ -2003,8 +2003,9 @@ static void mmc_hw_reset_for_init(struct mmc_host *host) * * Return: 0 on success, -errno on failure */ -int mmc_hw_reset(struct mmc_host *host) +int mmc_hw_reset(struct mmc_card *card) { + struct mmc_host *host = card->host; int ret; ret = host->bus_ops->hw_reset(host); @@ -2016,8 +2017,9 @@ int mmc_hw_reset(struct mmc_host *host) } EXPORT_SYMBOL(mmc_hw_reset); -int mmc_sw_reset(struct mmc_host *host) +int mmc_sw_reset(struct mmc_card *card) { + struct mmc_host *host = card->host; int ret; if (!host->bus_ops->sw_reset) diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c index e7ea45386c22..89cd48fcec79 100644 --- a/drivers/mmc/core/mmc.c +++ b/drivers/mmc/core/mmc.c @@ -12,6 +12,7 @@ #include <linux/slab.h> #include <linux/stat.h> #include <linux/pm_runtime.h> +#include <linux/random.h> #include <linux/sysfs.h> #include <linux/mmc/host.h> @@ -72,6 +73,12 @@ static int mmc_decode_cid(struct mmc_card *card) u32 *resp = card->raw_cid; /* + * Add the raw card ID (cid) data to the entropy pool. It doesn't + * matter that not all of it is unique, it's just bonus entropy. + */ + add_device_randomness(&card->raw_cid, sizeof(card->raw_cid)); + + /* * The selection of the format here is based upon published * specs from sandisk and from what people have reported. */ @@ -1384,13 +1391,17 @@ static int mmc_select_hs400es(struct mmc_card *card) goto out_err; } + /* + * Bump to HS timing and frequency. Some cards don't handle + * SEND_STATUS reliably at the initial frequency. + */ mmc_set_timing(host, MMC_TIMING_MMC_HS); + mmc_set_bus_speed(card); + err = mmc_switch_status(card, true); if (err) goto out_err; - mmc_set_clock(host, card->ext_csd.hs_max_dtr); - /* Switch card to DDR with strobe bit */ val = EXT_CSD_DDR_BUS_WIDTH_8 | EXT_CSD_BUS_WIDTH_STROBE; err = mmc_switch(card, EXT_CSD_CMD_SET_NORMAL, @@ -1448,7 +1459,7 @@ out_err: static int mmc_select_hs200(struct mmc_card *card) { struct mmc_host *host = card->host; - unsigned int old_timing, old_signal_voltage; + unsigned int old_timing, old_signal_voltage, old_clock; int err = -EINVAL; u8 val; @@ -1479,8 +1490,17 @@ static int mmc_select_hs200(struct mmc_card *card) false, true, MMC_CMD_RETRIES); if (err) goto err; + + /* + * Bump to HS timing and frequency. Some cards don't handle + * SEND_STATUS reliably at the initial frequency. + * NB: We can't move to full (HS200) speeds until after we've + * successfully switched over. + */ old_timing = host->ios.timing; + old_clock = host->ios.clock; mmc_set_timing(host, MMC_TIMING_MMC_HS200); + mmc_set_clock(card->host, card->ext_csd.hs_max_dtr); /* * For HS200, CRC errors are not a reliable way to know the @@ -1493,8 +1513,10 @@ static int mmc_select_hs200(struct mmc_card *card) * mmc_select_timing() assumes timing has not changed if * it is a switch error. */ - if (err == -EBADMSG) + if (err == -EBADMSG) { + mmc_set_clock(host, old_clock); mmc_set_timing(host, old_timing); + } } err: if (err) { @@ -2225,11 +2247,11 @@ static int _mmc_hw_reset(struct mmc_host *host) */ _mmc_flush_cache(host); - if ((host->caps & MMC_CAP_HW_RESET) && host->ops->hw_reset && + if ((host->caps & MMC_CAP_HW_RESET) && host->ops->card_hw_reset && mmc_can_reset(card)) { /* If the card accept RST_n signal, send it. */ mmc_set_clock(host, host->f_init); - host->ops->hw_reset(host); + host->ops->card_hw_reset(host); /* Set initial state and call mmc_set_ios */ mmc_set_initial_state(host); } else { diff --git a/drivers/mmc/core/mmc_ops.c b/drivers/mmc/core/mmc_ops.c index 180d7e9d3400..81c55bfd6e0c 100644 --- a/drivers/mmc/core/mmc_ops.c +++ b/drivers/mmc/core/mmc_ops.c @@ -21,7 +21,7 @@ #define MMC_BKOPS_TIMEOUT_MS (120 * 1000) /* 120s */ #define MMC_SANITIZE_TIMEOUT_MS (240 * 1000) /* 240s */ -#define MMC_OP_COND_PERIOD_US (1 * 1000) /* 1ms */ +#define MMC_OP_COND_PERIOD_US (4 * 1000) /* 4ms */ #define MMC_OP_COND_TIMEOUT_MS 1000 /* 1s */ static const u8 tuning_blk_pattern_4bit[] = { diff --git a/drivers/mmc/core/mmc_test.c b/drivers/mmc/core/mmc_test.c index e6a2fd2c6d5c..8d9bceeff986 100644 --- a/drivers/mmc/core/mmc_test.c +++ b/drivers/mmc/core/mmc_test.c @@ -2325,10 +2325,9 @@ static int mmc_test_profile_sglen_r_nonblock_perf(struct mmc_test_card *test) static int mmc_test_reset(struct mmc_test_card *test) { struct mmc_card *card = test->card; - struct mmc_host *host = card->host; int err; - err = mmc_hw_reset(host); + err = mmc_hw_reset(card); if (!err) { /* * Reset will re-enable the card's command queue, but tests diff --git a/drivers/mmc/core/queue.c b/drivers/mmc/core/queue.c index c69b2d9df6f1..fa5324ceeebe 100644 --- a/drivers/mmc/core/queue.c +++ b/drivers/mmc/core/queue.c @@ -183,14 +183,15 @@ static void mmc_queue_setup_discard(struct request_queue *q, if (!max_discard) return; - blk_queue_flag_set(QUEUE_FLAG_DISCARD, q); blk_queue_max_discard_sectors(q, max_discard); q->limits.discard_granularity = card->pref_erase << 9; /* granularity must not be greater than max. discard */ if (card->pref_erase > max_discard) q->limits.discard_granularity = SECTOR_SIZE; if (mmc_can_secure_erase_trim(card)) - blk_queue_flag_set(QUEUE_FLAG_SECERASE, q); + blk_queue_max_secure_erase_sectors(q, max_discard); + if (mmc_can_trim(card) && card->erased_byte == 0) + blk_queue_max_write_zeroes_sectors(q, max_discard); } static unsigned short mmc_get_max_segments(struct mmc_host *host) diff --git a/drivers/mmc/core/sd.c b/drivers/mmc/core/sd.c index 68df6b2f49cc..c5f1df6ce4c0 100644 --- a/drivers/mmc/core/sd.c +++ b/drivers/mmc/core/sd.c @@ -12,6 +12,7 @@ #include <linux/slab.h> #include <linux/stat.h> #include <linux/pm_runtime.h> +#include <linux/random.h> #include <linux/scatterlist.h> #include <linux/sysfs.h> @@ -84,6 +85,12 @@ void mmc_decode_cid(struct mmc_card *card) u32 *resp = card->raw_cid; /* + * Add the raw card ID (cid) data to the entropy pool. It doesn't + * matter that not all of it is unique, it's just bonus entropy. + */ + add_device_randomness(&card->raw_cid, sizeof(card->raw_cid)); + + /* * SD doesn't currently have a version field so we will * have to assume we can parse this. */ diff --git a/drivers/mmc/host/atmel-mci.c b/drivers/mmc/host/atmel-mci.c index 807177c953f3..91d52ba7a39f 100644 --- a/drivers/mmc/host/atmel-mci.c +++ b/drivers/mmc/host/atmel-mci.c @@ -1122,13 +1122,12 @@ atmci_prepare_data_dma(struct atmel_mci *host, struct mmc_data *data) } /* If we don't have a channel, we can't do DMA */ - chan = host->dma.chan; - if (chan) - host->data_chan = chan; - - if (!chan) + if (!host->dma.chan) return -ENODEV; + chan = host->dma.chan; + host->data_chan = chan; + if (data->flags & MMC_DATA_READ) { host->dma_conf.direction = slave_dirn = DMA_DEV_TO_MEM; maxburst = atmci_convert_chksize(host, diff --git a/drivers/mmc/host/bcm2835.c b/drivers/mmc/host/bcm2835.c index 463b707d9e99..641ab4f42125 100644 --- a/drivers/mmc/host/bcm2835.c +++ b/drivers/mmc/host/bcm2835.c @@ -1259,7 +1259,7 @@ static void bcm2835_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) static const struct mmc_host_ops bcm2835_ops = { .request = bcm2835_request, .set_ios = bcm2835_set_ios, - .hw_reset = bcm2835_reset, + .card_hw_reset = bcm2835_reset, }; static int bcm2835_add_host(struct bcm2835_host *host) diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c index 06dc56cbada8..581614196a84 100644 --- a/drivers/mmc/host/dw_mmc.c +++ b/drivers/mmc/host/dw_mmc.c @@ -1812,7 +1812,7 @@ static const struct mmc_host_ops dw_mci_ops = { .set_ios = dw_mci_set_ios, .get_ro = dw_mci_get_ro, .get_cd = dw_mci_get_cd, - .hw_reset = dw_mci_hw_reset, + .card_hw_reset = dw_mci_hw_reset, .enable_sdio_irq = dw_mci_enable_sdio_irq, .ack_sdio_irq = dw_mci_ack_sdio_irq, .execute_tuning = dw_mci_execute_tuning, diff --git a/drivers/mmc/host/jz4740_mmc.c b/drivers/mmc/host/jz4740_mmc.c index 7ab1b38a7be5..b1d563b2ed1b 100644 --- a/drivers/mmc/host/jz4740_mmc.c +++ b/drivers/mmc/host/jz4740_mmc.c @@ -247,6 +247,26 @@ static int jz4740_mmc_acquire_dma_channels(struct jz4740_mmc_host *host) return PTR_ERR(host->dma_rx); } + /* + * Limit the maximum segment size in any SG entry according to + * the parameters of the DMA engine device. + */ + if (host->dma_tx) { + struct device *dev = host->dma_tx->device->dev; + unsigned int max_seg_size = dma_get_max_seg_size(dev); + + if (max_seg_size < host->mmc->max_seg_size) + host->mmc->max_seg_size = max_seg_size; + } + + if (host->dma_rx) { + struct device *dev = host->dma_rx->device->dev; + unsigned int max_seg_size = dma_get_max_seg_size(dev); + + if (max_seg_size < host->mmc->max_seg_size) + host->mmc->max_seg_size = max_seg_size; + } + return 0; } diff --git a/drivers/mmc/host/meson-gx-mmc.c b/drivers/mmc/host/meson-gx-mmc.c index 58ab9d90bc8b..2f08d442e557 100644 --- a/drivers/mmc/host/meson-gx-mmc.c +++ b/drivers/mmc/host/meson-gx-mmc.c @@ -1271,8 +1271,8 @@ static int meson_mmc_probe(struct platform_device *pdev) /* data bounce buffer */ host->bounce_buf_size = mmc->max_req_size; host->bounce_buf = - dma_alloc_coherent(host->dev, host->bounce_buf_size, - &host->bounce_dma_addr, GFP_KERNEL); + dmam_alloc_coherent(host->dev, host->bounce_buf_size, + &host->bounce_dma_addr, GFP_KERNEL); if (host->bounce_buf == NULL) { dev_err(host->dev, "Unable to map allocate DMA bounce buffer.\n"); ret = -ENOMEM; @@ -1280,12 +1280,12 @@ static int meson_mmc_probe(struct platform_device *pdev) } } - host->descs = dma_alloc_coherent(host->dev, SD_EMMC_DESC_BUF_LEN, - &host->descs_dma_addr, GFP_KERNEL); + host->descs = dmam_alloc_coherent(host->dev, SD_EMMC_DESC_BUF_LEN, + &host->descs_dma_addr, GFP_KERNEL); if (!host->descs) { dev_err(host->dev, "Allocating descriptor DMA buffer failed\n"); ret = -ENOMEM; - goto err_bounce_buf; + goto err_free_irq; } mmc->ops = &meson_mmc_ops; @@ -1293,10 +1293,6 @@ static int meson_mmc_probe(struct platform_device *pdev) return 0; -err_bounce_buf: - if (!host->dram_access_quirk) - dma_free_coherent(host->dev, host->bounce_buf_size, - host->bounce_buf, host->bounce_dma_addr); err_free_irq: free_irq(host->irq, host); err_init_clk: @@ -1318,13 +1314,6 @@ static int meson_mmc_remove(struct platform_device *pdev) writel(0, host->regs + SD_EMMC_IRQ_EN); free_irq(host->irq, host); - dma_free_coherent(host->dev, SD_EMMC_DESC_BUF_LEN, - host->descs, host->descs_dma_addr); - - if (!host->dram_access_quirk) - dma_free_coherent(host->dev, host->bounce_buf_size, - host->bounce_buf, host->bounce_dma_addr); - clk_disable_unprepare(host->mmc_clk); clk_disable_unprepare(host->core_clk); diff --git a/drivers/mmc/host/meson-mx-sdhc-mmc.c b/drivers/mmc/host/meson-mx-sdhc-mmc.c index 28aa78aa08f3..e92e63cb5641 100644 --- a/drivers/mmc/host/meson-mx-sdhc-mmc.c +++ b/drivers/mmc/host/meson-mx-sdhc-mmc.c @@ -511,7 +511,7 @@ static int meson_mx_sdhc_execute_tuning(struct mmc_host *mmc, u32 opcode) } static const struct mmc_host_ops meson_mx_sdhc_ops = { - .hw_reset = meson_mx_sdhc_hw_reset, + .card_hw_reset = meson_mx_sdhc_hw_reset, .request = meson_mx_sdhc_request, .set_ios = meson_mx_sdhc_set_ios, .card_busy = meson_mx_sdhc_card_busy, diff --git a/drivers/mmc/host/mmci.c b/drivers/mmc/host/mmci.c index 45b8608c935c..01159eaf8694 100644 --- a/drivers/mmc/host/mmci.c +++ b/drivers/mmc/host/mmci.c @@ -1619,6 +1619,8 @@ static irqreturn_t mmci_irq(int irq, void *dev_id) do { status = readl(host->base + MMCISTATUS); + if (!status) + break; if (host->singleirq) { if (status & host->mask1_reg) @@ -1746,10 +1748,6 @@ static void mmci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) unsigned long flags; int ret; - if (host->plat->ios_handler && - host->plat->ios_handler(mmc_dev(mmc), ios)) - dev_err(mmc_dev(mmc), "platform ios_handler failed\n"); - switch (ios->power_mode) { case MMC_POWER_OFF: if (!IS_ERR(mmc->supply.vmmc)) diff --git a/drivers/mmc/host/mmci_stm32_sdmmc.c b/drivers/mmc/host/mmci_stm32_sdmmc.c index 9c13f2c31365..60bca78a72b1 100644 --- a/drivers/mmc/host/mmci_stm32_sdmmc.c +++ b/drivers/mmc/host/mmci_stm32_sdmmc.c @@ -43,6 +43,9 @@ struct sdmmc_lli_desc { struct sdmmc_idma { dma_addr_t sg_dma; void *sg_cpu; + dma_addr_t bounce_dma_addr; + void *bounce_buf; + bool use_bounce_buffer; }; struct sdmmc_dlyb { @@ -54,6 +57,8 @@ struct sdmmc_dlyb { static int sdmmc_idma_validate_data(struct mmci_host *host, struct mmc_data *data) { + struct sdmmc_idma *idma = host->dma_priv; + struct device *dev = mmc_dev(host->mmc); struct scatterlist *sg; int i; @@ -61,41 +66,69 @@ static int sdmmc_idma_validate_data(struct mmci_host *host, * idma has constraints on idmabase & idmasize for each element * excepted the last element which has no constraint on idmasize */ + idma->use_bounce_buffer = false; for_each_sg(data->sg, sg, data->sg_len - 1, i) { - if (!IS_ALIGNED(data->sg->offset, sizeof(u32)) || - !IS_ALIGNED(data->sg->length, SDMMC_IDMA_BURST)) { - dev_err(mmc_dev(host->mmc), + if (!IS_ALIGNED(sg->offset, sizeof(u32)) || + !IS_ALIGNED(sg->length, SDMMC_IDMA_BURST)) { + dev_dbg(mmc_dev(host->mmc), "unaligned scatterlist: ofst:%x length:%d\n", data->sg->offset, data->sg->length); - return -EINVAL; + goto use_bounce_buffer; } } - if (!IS_ALIGNED(data->sg->offset, sizeof(u32))) { - dev_err(mmc_dev(host->mmc), + if (!IS_ALIGNED(sg->offset, sizeof(u32))) { + dev_dbg(mmc_dev(host->mmc), "unaligned last scatterlist: ofst:%x length:%d\n", data->sg->offset, data->sg->length); - return -EINVAL; + goto use_bounce_buffer; } return 0; + +use_bounce_buffer: + if (!idma->bounce_buf) { + idma->bounce_buf = dmam_alloc_coherent(dev, + host->mmc->max_req_size, + &idma->bounce_dma_addr, + GFP_KERNEL); + if (!idma->bounce_buf) { + dev_err(dev, "Unable to map allocate DMA bounce buffer.\n"); + return -ENOMEM; + } + } + + idma->use_bounce_buffer = true; + + return 0; } static int _sdmmc_idma_prep_data(struct mmci_host *host, struct mmc_data *data) { - int n_elem; + struct sdmmc_idma *idma = host->dma_priv; - n_elem = dma_map_sg(mmc_dev(host->mmc), - data->sg, - data->sg_len, - mmc_get_dma_dir(data)); + if (idma->use_bounce_buffer) { + if (data->flags & MMC_DATA_WRITE) { + unsigned int xfer_bytes = data->blksz * data->blocks; - if (!n_elem) { - dev_err(mmc_dev(host->mmc), "dma_map_sg failed\n"); - return -EINVAL; - } + sg_copy_to_buffer(data->sg, data->sg_len, + idma->bounce_buf, xfer_bytes); + dma_wmb(); + } + } else { + int n_elem; + + n_elem = dma_map_sg(mmc_dev(host->mmc), + data->sg, + data->sg_len, + mmc_get_dma_dir(data)); + if (!n_elem) { + dev_err(mmc_dev(host->mmc), "dma_map_sg failed\n"); + return -EINVAL; + } + } return 0; } @@ -112,8 +145,19 @@ static int sdmmc_idma_prep_data(struct mmci_host *host, static void sdmmc_idma_unprep_data(struct mmci_host *host, struct mmc_data *data, int err) { - dma_unmap_sg(mmc_dev(host->mmc), data->sg, data->sg_len, - mmc_get_dma_dir(data)); + struct sdmmc_idma *idma = host->dma_priv; + + if (idma->use_bounce_buffer) { + if (data->flags & MMC_DATA_READ) { + unsigned int xfer_bytes = data->blksz * data->blocks; + + sg_copy_from_buffer(data->sg, data->sg_len, + idma->bounce_buf, xfer_bytes); + } + } else { + dma_unmap_sg(mmc_dev(host->mmc), data->sg, data->sg_len, + mmc_get_dma_dir(data)); + } } static int sdmmc_idma_setup(struct mmci_host *host) @@ -137,6 +181,8 @@ static int sdmmc_idma_setup(struct mmci_host *host) host->mmc->max_segs = SDMMC_LLI_BUF_LEN / sizeof(struct sdmmc_lli_desc); host->mmc->max_seg_size = host->variant->stm32_idmabsize_mask; + + host->mmc->max_req_size = SZ_1M; } else { host->mmc->max_segs = 1; host->mmc->max_seg_size = host->mmc->max_req_size; @@ -154,8 +200,16 @@ static int sdmmc_idma_start(struct mmci_host *host, unsigned int *datactrl) struct scatterlist *sg; int i; - if (!host->variant->dma_lli || data->sg_len == 1) { - writel_relaxed(sg_dma_address(data->sg), + if (!host->variant->dma_lli || data->sg_len == 1 || + idma->use_bounce_buffer) { + u32 dma_addr; + + if (idma->use_bounce_buffer) + dma_addr = idma->bounce_dma_addr; + else + dma_addr = sg_dma_address(data->sg); + + writel_relaxed(dma_addr, host->base + MMCI_STM32_IDMABASE0R); writel_relaxed(MMCI_STM32_IDMAEN, host->base + MMCI_STM32_IDMACTRLR); diff --git a/drivers/mmc/host/mtk-sd.c b/drivers/mmc/host/mtk-sd.c index e61b0b98065a..195dc897188b 100644 --- a/drivers/mmc/host/mtk-sd.c +++ b/drivers/mmc/host/mtk-sd.c @@ -2458,7 +2458,7 @@ static const struct mmc_host_ops mt_msdc_ops = { .execute_tuning = msdc_execute_tuning, .prepare_hs400_tuning = msdc_prepare_hs400_tuning, .execute_hs400_tuning = msdc_execute_hs400_tuning, - .hw_reset = msdc_hw_reset, + .card_hw_reset = msdc_hw_reset, }; static const struct cqhci_host_ops msdc_cmdq_ops = { diff --git a/drivers/mmc/host/of_mmc_spi.c b/drivers/mmc/host/of_mmc_spi.c index 3629550528b6..bf54776fb26c 100644 --- a/drivers/mmc/host/of_mmc_spi.c +++ b/drivers/mmc/host/of_mmc_spi.c @@ -70,6 +70,10 @@ struct mmc_spi_platform_data *mmc_spi_get_pdata(struct spi_device *spi) } else { oms->pdata.caps |= MMC_CAP_NEEDS_POLL; } + if (device_property_read_bool(dev, "cap-sd-highspeed")) + oms->pdata.caps |= MMC_CAP_SD_HIGHSPEED; + if (device_property_read_bool(dev, "cap-mmc-highspeed")) + oms->pdata.caps |= MMC_CAP_MMC_HIGHSPEED; dev->platform_data = &oms->pdata; return dev->platform_data; diff --git a/drivers/mmc/host/omap.c b/drivers/mmc/host/omap.c index 5e5af34090f1..57d39283924d 100644 --- a/drivers/mmc/host/omap.c +++ b/drivers/mmc/host/omap.c @@ -1374,7 +1374,7 @@ static int mmc_omap_probe(struct platform_device *pdev) host->iclk = clk_get(&pdev->dev, "ick"); if (IS_ERR(host->iclk)) return PTR_ERR(host->iclk); - clk_enable(host->iclk); + clk_prepare_enable(host->iclk); host->fclk = clk_get(&pdev->dev, "fck"); if (IS_ERR(host->fclk)) { @@ -1382,16 +1382,18 @@ static int mmc_omap_probe(struct platform_device *pdev) goto err_free_iclk; } + ret = clk_prepare(host->fclk); + if (ret) + goto err_put_fclk; + host->dma_tx_burst = -1; host->dma_rx_burst = -1; host->dma_tx = dma_request_chan(&pdev->dev, "tx"); if (IS_ERR(host->dma_tx)) { ret = PTR_ERR(host->dma_tx); - if (ret == -EPROBE_DEFER) { - clk_put(host->fclk); - goto err_free_iclk; - } + if (ret == -EPROBE_DEFER) + goto err_free_fclk; host->dma_tx = NULL; dev_warn(host->dev, "TX DMA channel request failed\n"); @@ -1403,8 +1405,7 @@ static int mmc_omap_probe(struct platform_device *pdev) if (ret == -EPROBE_DEFER) { if (host->dma_tx) dma_release_channel(host->dma_tx); - clk_put(host->fclk); - goto err_free_iclk; + goto err_free_fclk; } host->dma_rx = NULL; @@ -1454,9 +1455,12 @@ err_free_dma: dma_release_channel(host->dma_tx); if (host->dma_rx) dma_release_channel(host->dma_rx); +err_free_fclk: + clk_unprepare(host->fclk); +err_put_fclk: clk_put(host->fclk); err_free_iclk: - clk_disable(host->iclk); + clk_disable_unprepare(host->iclk); clk_put(host->iclk); return ret; } @@ -1476,8 +1480,9 @@ static int mmc_omap_remove(struct platform_device *pdev) mmc_omap_fclk_enable(host, 0); free_irq(host->irq, host); + clk_unprepare(host->fclk); clk_put(host->fclk); - clk_disable(host->iclk); + clk_disable_unprepare(host->iclk); clk_put(host->iclk); if (host->dma_tx) diff --git a/drivers/mmc/host/renesas_sdhi.h b/drivers/mmc/host/renesas_sdhi.h index 66d308e73e17..1a1e3e020a8c 100644 --- a/drivers/mmc/host/renesas_sdhi.h +++ b/drivers/mmc/host/renesas_sdhi.h @@ -41,6 +41,8 @@ struct renesas_sdhi_of_data { struct renesas_sdhi_quirks { bool hs400_disabled; bool hs400_4taps; + bool fixed_addr_mode; + bool dma_one_rx_only; u32 hs400_bad_taps; const u8 (*hs400_calib_table)[SDHI_CALIB_TABLE_MAX]; }; diff --git a/drivers/mmc/host/renesas_sdhi_core.c b/drivers/mmc/host/renesas_sdhi_core.c index 2797a9c0f17d..4404ca1f98d8 100644 --- a/drivers/mmc/host/renesas_sdhi_core.c +++ b/drivers/mmc/host/renesas_sdhi_core.c @@ -27,7 +27,6 @@ #include <linux/mmc/mmc.h> #include <linux/mmc/slot-gpio.h> #include <linux/module.h> -#include <linux/of_device.h> #include <linux/pinctrl/consumer.h> #include <linux/pinctrl/pinctrl-state.h> #include <linux/platform_device.h> @@ -36,7 +35,6 @@ #include <linux/reset.h> #include <linux/sh_dma.h> #include <linux/slab.h> -#include <linux/sys_soc.h> #include "renesas_sdhi.h" #include "tmio_mmc.h" @@ -144,9 +142,9 @@ static unsigned int renesas_sdhi_clk_update(struct tmio_mmc_host *host, return clk_get_rate(priv->clk); if (priv->clkh) { + /* HS400 with 4TAP needs different clock settings */ bool use_4tap = priv->quirks && priv->quirks->hs400_4taps; - bool need_slow_clkh = (host->mmc->ios.timing == MMC_TIMING_UHS_SDR104) || - (host->mmc->ios.timing == MMC_TIMING_MMC_HS400); + bool need_slow_clkh = host->mmc->ios.timing == MMC_TIMING_MMC_HS400; clkh_shift = use_4tap && need_slow_clkh ? 1 : 2; ref_clk = priv->clkh; } @@ -396,10 +394,10 @@ static void renesas_sdhi_hs400_complete(struct mmc_host *mmc) SH_MOBILE_SDHI_SCC_TMPPORT2_HS400OSEL) | sd_scc_read32(host, priv, SH_MOBILE_SDHI_SCC_TMPPORT2)); - /* Set the sampling clock selection range of HS400 mode */ sd_scc_write32(host, priv, SH_MOBILE_SDHI_SCC_DTCNTL, SH_MOBILE_SDHI_SCC_DTCNTL_TAPEN | - 0x4 << SH_MOBILE_SDHI_SCC_DTCNTL_TAPNUM_SHIFT); + sd_scc_read32(host, priv, + SH_MOBILE_SDHI_SCC_DTCNTL)); /* Avoid bad TAP */ if (bad_taps & BIT(priv->tap_set)) { diff --git a/drivers/mmc/host/renesas_sdhi_internal_dmac.c b/drivers/mmc/host/renesas_sdhi_internal_dmac.c index 1685df00863b..3084b15ae2cb 100644 --- a/drivers/mmc/host/renesas_sdhi_internal_dmac.c +++ b/drivers/mmc/host/renesas_sdhi_internal_dmac.c @@ -78,11 +78,7 @@ static unsigned long global_flags; * stored into the system memory even if the DMAC interrupt happened. * So, this driver then uses one RX DMAC channel only. */ -#define SDHI_INTERNAL_DMAC_ONE_RX_ONLY 0 -#define SDHI_INTERNAL_DMAC_RX_IN_USE 1 - -/* RZ/A2 does not have the ADRR_MODE bit */ -#define SDHI_INTERNAL_DMAC_ADDR_MODE_FIXED_ONLY 2 +#define SDHI_INTERNAL_DMAC_RX_IN_USE 0 /* Definitions for sampling clocks */ static struct renesas_sdhi_scc rcar_gen3_scc_taps[] = { @@ -108,10 +104,6 @@ static const struct renesas_sdhi_of_data of_data_rza2 = { .max_segs = 1, }; -static const struct renesas_sdhi_of_data_with_quirks of_rza2_compatible = { - .of_data = &of_data_rza2, -}; - static const struct renesas_sdhi_of_data of_data_rcar_gen3 = { .tmio_flags = TMIO_MMC_HAS_IDLE_WAIT | TMIO_MMC_CLK_ACTUAL | TMIO_MMC_HAVE_CBSY | TMIO_MMC_MIN_RCAR2, @@ -128,7 +120,7 @@ static const struct renesas_sdhi_of_data of_data_rcar_gen3 = { .sdhi_flags = SDHI_FLAG_NEED_CLKH_FALLBACK, }; -static const struct renesas_sdhi_of_data of_data_rcar_gen3_no_fallback = { +static const struct renesas_sdhi_of_data of_data_rcar_gen3_no_sdh_fallback = { .tmio_flags = TMIO_MMC_HAS_IDLE_WAIT | TMIO_MMC_CLK_ACTUAL | TMIO_MMC_HAVE_CBSY | TMIO_MMC_MIN_RCAR2, .capabilities = MMC_CAP_SD_HIGHSPEED | MMC_CAP_SDIO_IRQ | @@ -169,6 +161,12 @@ static const struct renesas_sdhi_quirks sdhi_quirks_4tap_nohs400 = { .hs400_4taps = true, }; +static const struct renesas_sdhi_quirks sdhi_quirks_4tap_nohs400_one_rx = { + .hs400_disabled = true, + .hs400_4taps = true, + .dma_one_rx_only = true, +}; + static const struct renesas_sdhi_quirks sdhi_quirks_4tap = { .hs400_4taps = true, .hs400_bad_taps = BIT(2) | BIT(3) | BIT(6) | BIT(7), @@ -178,6 +176,10 @@ static const struct renesas_sdhi_quirks sdhi_quirks_nohs400 = { .hs400_disabled = true, }; +static const struct renesas_sdhi_quirks sdhi_quirks_fixed_addr = { + .fixed_addr_mode = true, +}; + static const struct renesas_sdhi_quirks sdhi_quirks_bad_taps1357 = { .hs400_bad_taps = BIT(1) | BIT(3) | BIT(5) | BIT(7), }; @@ -208,10 +210,12 @@ static const struct renesas_sdhi_quirks sdhi_quirks_r8a77990 = { */ static const struct soc_device_attribute sdhi_quirks_match[] = { { .soc_id = "r8a774a1", .revision = "ES1.[012]", .data = &sdhi_quirks_4tap_nohs400 }, - { .soc_id = "r8a7795", .revision = "ES1.*", .data = &sdhi_quirks_4tap_nohs400 }, + { .soc_id = "r8a7795", .revision = "ES1.*", .data = &sdhi_quirks_4tap_nohs400_one_rx }, { .soc_id = "r8a7795", .revision = "ES2.0", .data = &sdhi_quirks_4tap }, - { .soc_id = "r8a7796", .revision = "ES1.[012]", .data = &sdhi_quirks_4tap_nohs400 }, + { .soc_id = "r8a7796", .revision = "ES1.0", .data = &sdhi_quirks_4tap_nohs400_one_rx }, + { .soc_id = "r8a7796", .revision = "ES1.[12]", .data = &sdhi_quirks_4tap_nohs400 }, { .soc_id = "r8a7796", .revision = "ES1.*", .data = &sdhi_quirks_r8a7796_es13 }, + { .soc_id = "r8a77980", .revision = "ES1.*", .data = &sdhi_quirks_nohs400 }, { /* Sentinel. */ } }; @@ -231,11 +235,7 @@ static const struct renesas_sdhi_of_data_with_quirks of_r8a77965_compatible = { }; static const struct renesas_sdhi_of_data_with_quirks of_r8a77970_compatible = { - .of_data = &of_data_rcar_gen3_no_fallback, -}; - -static const struct renesas_sdhi_of_data_with_quirks of_r8a77980_compatible = { - .of_data = &of_data_rcar_gen3, + .of_data = &of_data_rcar_gen3_no_sdh_fallback, .quirks = &sdhi_quirks_nohs400, }; @@ -248,16 +248,25 @@ static const struct renesas_sdhi_of_data_with_quirks of_rcar_gen3_compatible = { .of_data = &of_data_rcar_gen3, }; +static const struct renesas_sdhi_of_data_with_quirks of_rcar_gen3_nohs400_compatible = { + .of_data = &of_data_rcar_gen3, + .quirks = &sdhi_quirks_nohs400, +}; + +static const struct renesas_sdhi_of_data_with_quirks of_rza2_compatible = { + .of_data = &of_data_rza2, + .quirks = &sdhi_quirks_fixed_addr, +}; + static const struct of_device_id renesas_sdhi_internal_dmac_of_match[] = { { .compatible = "renesas,sdhi-r7s9210", .data = &of_rza2_compatible, }, { .compatible = "renesas,sdhi-mmc-r8a77470", .data = &of_rcar_gen3_compatible, }, { .compatible = "renesas,sdhi-r8a7795", .data = &of_r8a7795_compatible, }, - { .compatible = "renesas,sdhi-r8a7796", .data = &of_rcar_gen3_compatible, }, { .compatible = "renesas,sdhi-r8a77961", .data = &of_r8a77961_compatible, }, { .compatible = "renesas,sdhi-r8a77965", .data = &of_r8a77965_compatible, }, { .compatible = "renesas,sdhi-r8a77970", .data = &of_r8a77970_compatible, }, - { .compatible = "renesas,sdhi-r8a77980", .data = &of_r8a77980_compatible, }, { .compatible = "renesas,sdhi-r8a77990", .data = &of_r8a77990_compatible, }, + { .compatible = "renesas,sdhi-r8a77995", .data = &of_rcar_gen3_nohs400_compatible, }, { .compatible = "renesas,rcar-gen3-sdhi", .data = &of_rcar_gen3_compatible, }, {}, }; @@ -287,7 +296,8 @@ renesas_sdhi_internal_dmac_enable_dma(struct tmio_mmc_host *host, bool enable) } static void -renesas_sdhi_internal_dmac_abort_dma(struct tmio_mmc_host *host) { +renesas_sdhi_internal_dmac_abort_dma(struct tmio_mmc_host *host) +{ u64 val = RST_DTRANRST1 | RST_DTRANRST0; renesas_sdhi_internal_dmac_enable_dma(host, false); @@ -303,7 +313,8 @@ renesas_sdhi_internal_dmac_abort_dma(struct tmio_mmc_host *host) { } static void -renesas_sdhi_internal_dmac_dataend_dma(struct tmio_mmc_host *host) { +renesas_sdhi_internal_dmac_dataend_dma(struct tmio_mmc_host *host) +{ struct renesas_sdhi *priv = host_to_priv(host); tasklet_schedule(&priv->dma_priv.dma_complete); @@ -357,10 +368,11 @@ static void renesas_sdhi_internal_dmac_start_dma(struct tmio_mmc_host *host, struct mmc_data *data) { + struct renesas_sdhi *priv = host_to_priv(host); struct scatterlist *sg = host->sg_ptr; u32 dtran_mode = DTRAN_MODE_BUS_WIDTH; - if (!test_bit(SDHI_INTERNAL_DMAC_ADDR_MODE_FIXED_ONLY, &global_flags)) + if (!(priv->quirks && priv->quirks->fixed_addr_mode)) dtran_mode |= DTRAN_MODE_ADDR_MODE; if (!renesas_sdhi_internal_dmac_map(host, data, COOKIE_MAPPED)) @@ -368,7 +380,7 @@ renesas_sdhi_internal_dmac_start_dma(struct tmio_mmc_host *host, if (data->flags & MMC_DATA_READ) { dtran_mode |= DTRAN_MODE_CH_NUM_CH1; - if (test_bit(SDHI_INTERNAL_DMAC_ONE_RX_ONLY, &global_flags) && + if (priv->quirks && priv->quirks->dma_one_rx_only && test_and_set_bit(SDHI_INTERNAL_DMAC_RX_IN_USE, &global_flags)) goto force_pio_with_unmap; } else { @@ -520,20 +532,6 @@ static const struct tmio_mmc_dma_ops renesas_sdhi_internal_dmac_dma_ops = { .end = renesas_sdhi_internal_dmac_end_dma, }; -/* - * Whitelist of specific R-Car Gen3 SoC ES versions to use this DMAC - * implementation as others may use a different implementation. - */ -static const struct soc_device_attribute soc_dma_quirks[] = { - { .soc_id = "r7s9210", - .data = (void *)BIT(SDHI_INTERNAL_DMAC_ADDR_MODE_FIXED_ONLY) }, - { .soc_id = "r8a7795", .revision = "ES1.*", - .data = (void *)BIT(SDHI_INTERNAL_DMAC_ONE_RX_ONLY) }, - { .soc_id = "r8a7796", .revision = "ES1.0", - .data = (void *)BIT(SDHI_INTERNAL_DMAC_ONE_RX_ONLY) }, - { /* sentinel */ } -}; - static int renesas_sdhi_internal_dmac_probe(struct platform_device *pdev) { const struct soc_device_attribute *attr; @@ -544,10 +542,6 @@ static int renesas_sdhi_internal_dmac_probe(struct platform_device *pdev) of_data_quirks = of_device_get_match_data(&pdev->dev); quirks = of_data_quirks->quirks; - attr = soc_device_match(soc_dma_quirks); - if (attr) - global_flags |= (unsigned long)attr->data; - attr = soc_device_match(sdhi_quirks_match); if (attr) quirks = attr->data; diff --git a/drivers/mmc/host/sdhci-brcmstb.c b/drivers/mmc/host/sdhci-brcmstb.c index f24623aac2db..8eb57de48e0c 100644 --- a/drivers/mmc/host/sdhci-brcmstb.c +++ b/drivers/mmc/host/sdhci-brcmstb.c @@ -17,23 +17,49 @@ #define SDHCI_VENDOR 0x78 #define SDHCI_VENDOR_ENHANCED_STRB 0x1 +#define SDHCI_VENDOR_GATE_SDCLK_EN 0x2 -#define BRCMSTB_PRIV_FLAGS_NO_64BIT BIT(0) -#define BRCMSTB_PRIV_FLAGS_BROKEN_TIMEOUT BIT(1) +#define BRCMSTB_MATCH_FLAGS_NO_64BIT BIT(0) +#define BRCMSTB_MATCH_FLAGS_BROKEN_TIMEOUT BIT(1) +#define BRCMSTB_MATCH_FLAGS_HAS_CLOCK_GATE BIT(2) + +#define BRCMSTB_PRIV_FLAGS_HAS_CQE BIT(0) +#define BRCMSTB_PRIV_FLAGS_GATE_CLOCK BIT(1) #define SDHCI_ARASAN_CQE_BASE_ADDR 0x200 struct sdhci_brcmstb_priv { void __iomem *cfg_regs; - bool has_cqe; + unsigned int flags; }; struct brcmstb_match_priv { void (*hs400es)(struct mmc_host *mmc, struct mmc_ios *ios); struct sdhci_ops *ops; - unsigned int flags; + const unsigned int flags; }; +static inline void enable_clock_gating(struct sdhci_host *host) +{ + u32 reg; + + reg = sdhci_readl(host, SDHCI_VENDOR); + reg |= SDHCI_VENDOR_GATE_SDCLK_EN; + sdhci_writel(host, reg, SDHCI_VENDOR); +} + +static void brcmstb_reset(struct sdhci_host *host, u8 mask) +{ + struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host); + struct sdhci_brcmstb_priv *priv = sdhci_pltfm_priv(pltfm_host); + + sdhci_reset(host, mask); + + /* Reset will clear this, so re-enable it */ + if (priv->flags & BRCMSTB_PRIV_FLAGS_GATE_CLOCK) + enable_clock_gating(host); +} + static void sdhci_brcmstb_hs400es(struct mmc_host *mmc, struct mmc_ios *ios) { struct sdhci_host *host = mmc_priv(mmc); @@ -129,22 +155,23 @@ static struct sdhci_ops sdhci_brcmstb_ops = { static struct sdhci_ops sdhci_brcmstb_ops_7216 = { .set_clock = sdhci_brcmstb_set_clock, .set_bus_width = sdhci_set_bus_width, - .reset = sdhci_reset, + .reset = brcmstb_reset, .set_uhs_signaling = sdhci_brcmstb_set_uhs_signaling, }; static struct brcmstb_match_priv match_priv_7425 = { - .flags = BRCMSTB_PRIV_FLAGS_NO_64BIT | - BRCMSTB_PRIV_FLAGS_BROKEN_TIMEOUT, + .flags = BRCMSTB_MATCH_FLAGS_NO_64BIT | + BRCMSTB_MATCH_FLAGS_BROKEN_TIMEOUT, .ops = &sdhci_brcmstb_ops, }; static struct brcmstb_match_priv match_priv_7445 = { - .flags = BRCMSTB_PRIV_FLAGS_BROKEN_TIMEOUT, + .flags = BRCMSTB_MATCH_FLAGS_BROKEN_TIMEOUT, .ops = &sdhci_brcmstb_ops, }; static const struct brcmstb_match_priv match_priv_7216 = { + .flags = BRCMSTB_MATCH_FLAGS_HAS_CLOCK_GATE, .hs400es = sdhci_brcmstb_hs400es, .ops = &sdhci_brcmstb_ops_7216, }; @@ -176,7 +203,7 @@ static int sdhci_brcmstb_add_host(struct sdhci_host *host, bool dma64; int ret; - if (!priv->has_cqe) + if ((priv->flags & BRCMSTB_PRIV_FLAGS_HAS_CQE) == 0) return sdhci_add_host(host); dev_dbg(mmc_dev(host->mmc), "CQE is enabled\n"); @@ -225,7 +252,6 @@ static int sdhci_brcmstb_probe(struct platform_device *pdev) struct sdhci_brcmstb_priv *priv; struct sdhci_host *host; struct resource *iomem; - bool has_cqe = false; struct clk *clk; int res; @@ -244,10 +270,6 @@ static int sdhci_brcmstb_probe(struct platform_device *pdev) return res; memset(&brcmstb_pdata, 0, sizeof(brcmstb_pdata)); - if (device_property_read_bool(&pdev->dev, "supports-cqe")) { - has_cqe = true; - match_priv->ops->irq = sdhci_brcmstb_cqhci_irq; - } brcmstb_pdata.ops = match_priv->ops; host = sdhci_pltfm_init(pdev, &brcmstb_pdata, sizeof(struct sdhci_brcmstb_priv)); @@ -258,7 +280,10 @@ static int sdhci_brcmstb_probe(struct platform_device *pdev) pltfm_host = sdhci_priv(host); priv = sdhci_pltfm_priv(pltfm_host); - priv->has_cqe = has_cqe; + if (device_property_read_bool(&pdev->dev, "supports-cqe")) { + priv->flags |= BRCMSTB_PRIV_FLAGS_HAS_CQE; + match_priv->ops->irq = sdhci_brcmstb_cqhci_irq; + } /* Map in the non-standard CFG registers */ iomem = platform_get_resource(pdev, IORESOURCE_MEM, 1); @@ -274,6 +299,14 @@ static int sdhci_brcmstb_probe(struct platform_device *pdev) goto err; /* + * Automatic clock gating does not work for SD cards that may + * voltage switch so only enable it for non-removable devices. + */ + if ((match_priv->flags & BRCMSTB_MATCH_FLAGS_HAS_CLOCK_GATE) && + (host->mmc->caps & MMC_CAP_NONREMOVABLE)) + priv->flags |= BRCMSTB_PRIV_FLAGS_GATE_CLOCK; + + /* * If the chip has enhanced strobe and it's enabled, add * callback */ @@ -287,14 +320,14 @@ static int sdhci_brcmstb_probe(struct platform_device *pdev) * properties through mmc_of_parse(). */ host->caps = sdhci_readl(host, SDHCI_CAPABILITIES); - if (match_priv->flags & BRCMSTB_PRIV_FLAGS_NO_64BIT) + if (match_priv->flags & BRCMSTB_MATCH_FLAGS_NO_64BIT) host->caps &= ~SDHCI_CAN_64BIT; host->caps1 = sdhci_readl(host, SDHCI_CAPABILITIES_1); host->caps1 &= ~(SDHCI_SUPPORT_SDR50 | SDHCI_SUPPORT_SDR104 | SDHCI_SUPPORT_DDR50); host->quirks |= SDHCI_QUIRK_MISSING_CAPS; - if (match_priv->flags & BRCMSTB_PRIV_FLAGS_BROKEN_TIMEOUT) + if (match_priv->flags & BRCMSTB_MATCH_FLAGS_BROKEN_TIMEOUT) host->quirks |= SDHCI_QUIRK_BROKEN_TIMEOUT_VAL; res = sdhci_brcmstb_add_host(host, priv); diff --git a/drivers/mmc/host/sdhci-msm.c b/drivers/mmc/host/sdhci-msm.c index 50c71e0ba5e4..e395411fb6fd 100644 --- a/drivers/mmc/host/sdhci-msm.c +++ b/drivers/mmc/host/sdhci-msm.c @@ -17,6 +17,7 @@ #include <linux/regulator/consumer.h> #include <linux/interconnect.h> #include <linux/pinctrl/consumer.h> +#include <linux/reset.h> #include "sdhci-pltfm.h" #include "cqhci.h" @@ -2434,8 +2435,33 @@ static const struct sdhci_msm_variant_info sdm845_sdhci_var = { }; static const struct of_device_id sdhci_msm_dt_match[] = { + /* Following two entries are deprecated (kept only for backward compatibility) */ {.compatible = "qcom,sdhci-msm-v4", .data = &sdhci_msm_mci_var}, {.compatible = "qcom,sdhci-msm-v5", .data = &sdhci_msm_v5_var}, + /* Add entries for sdcc versions less than 5.0 here */ + {.compatible = "qcom,apq8084-sdhci", .data = &sdhci_msm_mci_var}, + {.compatible = "qcom,msm8226-sdhci", .data = &sdhci_msm_mci_var}, + {.compatible = "qcom,msm8916-sdhci", .data = &sdhci_msm_mci_var}, + {.compatible = "qcom,msm8953-sdhci", .data = &sdhci_msm_mci_var}, + {.compatible = "qcom,msm8974-sdhci", .data = &sdhci_msm_mci_var}, + {.compatible = "qcom,msm8992-sdhci", .data = &sdhci_msm_mci_var}, + {.compatible = "qcom,msm8994-sdhci", .data = &sdhci_msm_mci_var}, + {.compatible = "qcom,msm8996-sdhci", .data = &sdhci_msm_mci_var}, + /* + * Add entries for sdcc version 5.0 here. For SDCC version 5.0.0, + * MCI registers are removed from SDCC interface and some registers + * are moved to HC. + */ + {.compatible = "qcom,qcs404-sdhci", .data = &sdhci_msm_v5_var}, + {.compatible = "qcom,sdx55-sdhci", .data = &sdhci_msm_v5_var}, + {.compatible = "qcom,sdx65-sdhci", .data = &sdhci_msm_v5_var}, + {.compatible = "qcom,sdm630-sdhci", .data = &sdhci_msm_v5_var}, + {.compatible = "qcom,sm6125-sdhci", .data = &sdhci_msm_v5_var}, + {.compatible = "qcom,sm6350-sdhci", .data = &sdhci_msm_v5_var}, + {.compatible = "qcom,sm8150-sdhci", .data = &sdhci_msm_v5_var}, + {.compatible = "qcom,sm8250-sdhci", .data = &sdhci_msm_v5_var}, + {.compatible = "qcom,sc7280-sdhci", .data = &sdhci_msm_v5_var}, + /* Add entries where soc specific handling is required, here */ {.compatible = "qcom,sdm845-sdhci", .data = &sdm845_sdhci_var}, {.compatible = "qcom,sc7180-sdhci", .data = &sdm845_sdhci_var}, {}, @@ -2482,6 +2508,43 @@ static inline void sdhci_msm_get_of_property(struct platform_device *pdev, of_property_read_u32(node, "qcom,dll-config", &msm_host->dll_config); } +static int sdhci_msm_gcc_reset(struct device *dev, struct sdhci_host *host) +{ + struct reset_control *reset; + int ret = 0; + + reset = reset_control_get_optional_exclusive(dev, NULL); + if (IS_ERR(reset)) + return dev_err_probe(dev, PTR_ERR(reset), + "unable to acquire core_reset\n"); + + if (!reset) + return ret; + + ret = reset_control_assert(reset); + if (ret) { + reset_control_put(reset); + return dev_err_probe(dev, ret, "core_reset assert failed\n"); + } + + /* + * The hardware requirement for delay between assert/deassert + * is at least 3-4 sleep clock (32.7KHz) cycles, which comes to + * ~125us (4/32768). To be on the safe side add 200us delay. + */ + usleep_range(200, 210); + + ret = reset_control_deassert(reset); + if (ret) { + reset_control_put(reset); + return dev_err_probe(dev, ret, "core_reset deassert failed\n"); + } + + usleep_range(200, 210); + reset_control_put(reset); + + return ret; +} static int sdhci_msm_probe(struct platform_device *pdev) { @@ -2529,6 +2592,10 @@ static int sdhci_msm_probe(struct platform_device *pdev) msm_host->saved_tuning_phase = INVALID_TUNING_PHASE; + ret = sdhci_msm_gcc_reset(&pdev->dev, host); + if (ret) + goto pltfm_free; + /* Setup SDCC bus voter clock. */ msm_host->bus_clk = devm_clk_get(&pdev->dev, "bus"); if (!IS_ERR(msm_host->bus_clk)) { diff --git a/drivers/mmc/host/sdhci-of-arasan.c b/drivers/mmc/host/sdhci-of-arasan.c index 6a2e5a468424..757801dfc308 100644 --- a/drivers/mmc/host/sdhci-of-arasan.c +++ b/drivers/mmc/host/sdhci-of-arasan.c @@ -1577,6 +1577,9 @@ static int sdhci_arasan_probe(struct platform_device *pdev) const struct sdhci_arasan_of_data *data; data = of_device_get_match_data(dev); + if (!data) + return -EINVAL; + host = sdhci_pltfm_init(pdev, data->pdata, sizeof(*sdhci_arasan)); if (IS_ERR(host)) diff --git a/drivers/mmc/host/sdhci-omap.c b/drivers/mmc/host/sdhci-omap.c index 64e27c2821f9..86e867ffbb10 100644 --- a/drivers/mmc/host/sdhci-omap.c +++ b/drivers/mmc/host/sdhci-omap.c @@ -1219,16 +1219,11 @@ static int sdhci_omap_probe(struct platform_device *pdev) struct sdhci_pltfm_host *pltfm_host; struct sdhci_omap_host *omap_host; struct mmc_host *mmc; - const struct of_device_id *match; - struct sdhci_omap_data *data; + const struct sdhci_omap_data *data; const struct soc_device_attribute *soc; struct resource *regs; - match = of_match_device(omap_sdhci_match, dev); - if (!match) - return -EINVAL; - - data = (struct sdhci_omap_data *)match->data; + data = of_device_get_match_data(&pdev->dev); if (!data) { dev_err(dev, "no sdhci omap data\n"); return -EINVAL; diff --git a/drivers/mmc/host/sdhci-pci-gli.c b/drivers/mmc/host/sdhci-pci-gli.c index d09728c37d03..1499a64ec3aa 100644 --- a/drivers/mmc/host/sdhci-pci-gli.c +++ b/drivers/mmc/host/sdhci-pci-gli.c @@ -142,6 +142,9 @@ #define PCI_GLI_9755_MISC 0x78 #define PCI_GLI_9755_MISC_SSC_OFF BIT(26) +#define PCI_GLI_9755_PM_CTRL 0xFC +#define PCI_GLI_9755_PM_STATE GENMASK(1, 0) + #define GLI_MAX_TUNING_LOOP 40 /* Genesys Logic chipset */ @@ -676,6 +679,13 @@ static void gl9755_hw_setting(struct sdhci_pci_slot *slot) GLI_9755_CFG2_L1DLY_VALUE); pci_write_config_dword(pdev, PCI_GLI_9755_CFG2, value); + /* toggle PM state to allow GL9755 to enter ASPM L1.2 */ + pci_read_config_dword(pdev, PCI_GLI_9755_PM_CTRL, &value); + value |= PCI_GLI_9755_PM_STATE; + pci_write_config_dword(pdev, PCI_GLI_9755_PM_CTRL, value); + value &= ~PCI_GLI_9755_PM_STATE; + pci_write_config_dword(pdev, PCI_GLI_9755_PM_CTRL, value); + gl9755_wt_off(pdev); } diff --git a/drivers/mmc/host/sdhci-xenon.c b/drivers/mmc/host/sdhci-xenon.c index 666cee4c7f7c..08e838400b52 100644 --- a/drivers/mmc/host/sdhci-xenon.c +++ b/drivers/mmc/host/sdhci-xenon.c @@ -241,16 +241,6 @@ static void xenon_voltage_switch(struct sdhci_host *host) { /* Wait for 5ms after set 1.8V signal enable bit */ usleep_range(5000, 5500); - - /* - * For some reason the controller's Host Control2 register reports - * the bit representing 1.8V signaling as 0 when read after it was - * written as 1. Subsequent read reports 1. - * - * Since this may cause some issues, do an empty read of the Host - * Control2 register here to circumvent this. - */ - sdhci_readw(host, SDHCI_HOST_CONTROL2); } static unsigned int xenon_get_max_clock(struct sdhci_host *host) diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c index 07c6da1f2f0f..22152029e14c 100644 --- a/drivers/mmc/host/sdhci.c +++ b/drivers/mmc/host/sdhci.c @@ -2999,7 +2999,7 @@ static const struct mmc_host_ops sdhci_ops = { .set_ios = sdhci_set_ios, .get_cd = sdhci_get_cd, .get_ro = sdhci_get_ro, - .hw_reset = sdhci_hw_reset, + .card_hw_reset = sdhci_hw_reset, .enable_sdio_irq = sdhci_enable_sdio_irq, .ack_sdio_irq = sdhci_ack_sdio_irq, .start_signal_voltage_switch = sdhci_start_signal_voltage_switch, diff --git a/drivers/mmc/host/sdhci_am654.c b/drivers/mmc/host/sdhci_am654.c index e54fe24d47e7..e7ced1496a07 100644 --- a/drivers/mmc/host/sdhci_am654.c +++ b/drivers/mmc/host/sdhci_am654.c @@ -147,6 +147,9 @@ struct sdhci_am654_data { int drv_strength; int strb_sel; u32 flags; + u32 quirks; + +#define SDHCI_AM654_QUIRK_FORCE_CDTEST BIT(0) }; struct sdhci_am654_driver_data { @@ -369,6 +372,21 @@ static void sdhci_am654_write_b(struct sdhci_host *host, u8 val, int reg) } } +static void sdhci_am654_reset(struct sdhci_host *host, u8 mask) +{ + u8 ctrl; + struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host); + struct sdhci_am654_data *sdhci_am654 = sdhci_pltfm_priv(pltfm_host); + + sdhci_reset(host, mask); + + if (sdhci_am654->quirks & SDHCI_AM654_QUIRK_FORCE_CDTEST) { + ctrl = sdhci_readb(host, SDHCI_HOST_CONTROL); + ctrl |= SDHCI_CTRL_CDTEST_INS | SDHCI_CTRL_CDTEST_EN; + sdhci_writeb(host, ctrl, SDHCI_HOST_CONTROL); + } +} + static int sdhci_am654_execute_tuning(struct mmc_host *mmc, u32 opcode) { struct sdhci_host *host = mmc_priv(mmc); @@ -500,7 +518,7 @@ static struct sdhci_ops sdhci_j721e_4bit_ops = { .set_clock = sdhci_j721e_4bit_set_clock, .write_b = sdhci_am654_write_b, .irq = sdhci_am654_cqhci_irq, - .reset = sdhci_reset, + .reset = sdhci_am654_reset, }; static const struct sdhci_pltfm_data sdhci_j721e_4bit_pdata = { @@ -719,6 +737,9 @@ static int sdhci_am654_get_of_property(struct platform_device *pdev, device_property_read_u32(dev, "ti,clkbuf-sel", &sdhci_am654->clkbuf_sel); + if (device_property_read_bool(dev, "ti,fails-without-test-cd")) + sdhci_am654->quirks |= SDHCI_AM654_QUIRK_FORCE_CDTEST; + sdhci_get_of_property(pdev); return 0; diff --git a/drivers/mmc/host/sh_mmcif.c b/drivers/mmc/host/sh_mmcif.c index 5f9ebf045b1c..0fd4c9d644dd 100644 --- a/drivers/mmc/host/sh_mmcif.c +++ b/drivers/mmc/host/sh_mmcif.c @@ -43,12 +43,12 @@ #include <linux/mmc/host.h> #include <linux/mmc/mmc.h> #include <linux/mmc/sdio.h> -#include <linux/mmc/sh_mmcif.h> #include <linux/mmc/slot-gpio.h> #include <linux/mod_devicetable.h> #include <linux/mutex.h> #include <linux/of_device.h> #include <linux/pagemap.h> +#include <linux/platform_data/sh_mmcif.h> #include <linux/platform_device.h> #include <linux/pm_qos.h> #include <linux/pm_runtime.h> diff --git a/drivers/mmc/host/sunxi-mmc.c b/drivers/mmc/host/sunxi-mmc.c index c62afd212692..b16e12e62e72 100644 --- a/drivers/mmc/host/sunxi-mmc.c +++ b/drivers/mmc/host/sunxi-mmc.c @@ -377,8 +377,9 @@ static void sunxi_mmc_init_idma_des(struct sunxi_mmc_host *host, pdes[i].buf_addr_ptr1 = cpu_to_le32(sg_dma_address(&data->sg[i]) >> host->cfg->idma_des_shift); - pdes[i].buf_addr_ptr2 = cpu_to_le32((u32)next_desc >> - host->cfg->idma_des_shift); + pdes[i].buf_addr_ptr2 = + cpu_to_le32(next_desc >> + host->cfg->idma_des_shift); } pdes[0].config |= cpu_to_le32(SDXC_IDMAC_DES0_FD); @@ -1115,7 +1116,7 @@ static const struct mmc_host_ops sunxi_mmc_ops = { .get_cd = mmc_gpio_get_cd, .enable_sdio_irq = sunxi_mmc_enable_sdio_irq, .start_signal_voltage_switch = sunxi_mmc_volt_switch, - .hw_reset = sunxi_mmc_hw_reset, + .card_hw_reset = sunxi_mmc_hw_reset, .card_busy = sunxi_mmc_card_busy, }; diff --git a/drivers/mmc/host/uniphier-sd.c b/drivers/mmc/host/uniphier-sd.c index ccbf9885a52b..3a8defdcca77 100644 --- a/drivers/mmc/host/uniphier-sd.c +++ b/drivers/mmc/host/uniphier-sd.c @@ -597,7 +597,7 @@ static int uniphier_sd_probe(struct platform_device *pdev) ret = PTR_ERR(priv->rst_hw); goto free_host; } - host->ops.hw_reset = uniphier_sd_hw_reset; + host->ops.card_hw_reset = uniphier_sd_hw_reset; } if (host->mmc->caps & MMC_CAP_UHS) { diff --git a/drivers/mtd/chips/cfi_cmdset_0002.c b/drivers/mtd/chips/cfi_cmdset_0002.c index a761134fd3be..67453f59c69c 100644 --- a/drivers/mtd/chips/cfi_cmdset_0002.c +++ b/drivers/mtd/chips/cfi_cmdset_0002.c @@ -48,6 +48,7 @@ #define SST49LF040B 0x0050 #define SST49LF008A 0x005a #define AT49BV6416 0x00d6 +#define S29GL064N_MN12 0x0c01 /* * Status Register bit description. Used by flash devices that don't @@ -59,6 +60,10 @@ #define CFI_SR_WBASB BIT(3) #define CFI_SR_SLSB BIT(1) +enum cfi_quirks { + CFI_QUIRK_DQ_TRUE_DATA = BIT(0), +}; + static int cfi_amdstd_read (struct mtd_info *, loff_t, size_t, size_t *, u_char *); static int cfi_amdstd_write_words(struct mtd_info *, loff_t, size_t, size_t *, const u_char *); #if !FORCE_WORD_WRITE @@ -436,6 +441,15 @@ static void fixup_s29ns512p_sectors(struct mtd_info *mtd) mtd->name); } +static void fixup_quirks(struct mtd_info *mtd) +{ + struct map_info *map = mtd->priv; + struct cfi_private *cfi = map->fldrv_priv; + + if (cfi->mfr == CFI_MFR_AMD && cfi->id == S29GL064N_MN12) + cfi->quirks |= CFI_QUIRK_DQ_TRUE_DATA; +} + /* Used to fix CFI-Tables of chips without Extended Query Tables */ static struct cfi_fixup cfi_nopri_fixup_table[] = { { CFI_MFR_SST, 0x234a, fixup_sst39vf }, /* SST39VF1602 */ @@ -462,7 +476,7 @@ static struct cfi_fixup cfi_fixup_table[] = { { CFI_MFR_AMD, 0x0056, fixup_use_secsi }, { CFI_MFR_AMD, 0x005C, fixup_use_secsi }, { CFI_MFR_AMD, 0x005F, fixup_use_secsi }, - { CFI_MFR_AMD, 0x0c01, fixup_s29gl064n_sectors }, + { CFI_MFR_AMD, S29GL064N_MN12, fixup_s29gl064n_sectors }, { CFI_MFR_AMD, 0x1301, fixup_s29gl064n_sectors }, { CFI_MFR_AMD, 0x1a00, fixup_s29gl032n_sectors }, { CFI_MFR_AMD, 0x1a01, fixup_s29gl032n_sectors }, @@ -474,6 +488,7 @@ static struct cfi_fixup cfi_fixup_table[] = { #if !FORCE_WORD_WRITE { CFI_MFR_ANY, CFI_ID_ANY, fixup_use_write_buffers }, #endif + { CFI_MFR_ANY, CFI_ID_ANY, fixup_quirks }, { 0, 0, NULL } }; static struct cfi_fixup jedec_fixup_table[] = { @@ -802,46 +817,10 @@ static struct mtd_info *cfi_amdstd_setup(struct mtd_info *mtd) } /* - * Return true if the chip is ready. - * - * Ready is one of: read mode, query mode, erase-suspend-read mode (in any - * non-suspended sector) and is indicated by no toggle bits toggling. - * - * Note that anything more complicated than checking if no bits are toggling - * (including checking DQ5 for an error status) is tricky to get working - * correctly and is therefore not done (particularly with interleaved chips - * as each chip must be checked independently of the others). - */ -static int __xipram chip_ready(struct map_info *map, struct flchip *chip, - unsigned long addr) -{ - struct cfi_private *cfi = map->fldrv_priv; - map_word d, t; - - if (cfi_use_status_reg(cfi)) { - map_word ready = CMD(CFI_SR_DRB); - /* - * For chips that support status register, check device - * ready bit - */ - cfi_send_gen_cmd(0x70, cfi->addr_unlock1, chip->start, map, cfi, - cfi->device_type, NULL); - d = map_read(map, addr); - - return map_word_andequal(map, d, ready, ready); - } - - d = map_read(map, addr); - t = map_read(map, addr); - - return map_word_equal(map, d, t); -} - -/* * Return true if the chip is ready and has the correct value. * * Ready is one of: read mode, query mode, erase-suspend-read mode (in any - * non-suspended sector) and it is indicated by no bits toggling. + * non-suspended sector) and is indicated by no toggle bits toggling. * * Error are indicated by toggling bits or bits held with the wrong value, * or with bits toggling. @@ -850,17 +829,16 @@ static int __xipram chip_ready(struct map_info *map, struct flchip *chip, * (including checking DQ5 for an error status) is tricky to get working * correctly and is therefore not done (particularly with interleaved chips * as each chip must be checked independently of the others). - * */ -static int __xipram chip_good(struct map_info *map, struct flchip *chip, - unsigned long addr, map_word expected) +static int __xipram chip_ready(struct map_info *map, struct flchip *chip, + unsigned long addr, map_word *expected) { struct cfi_private *cfi = map->fldrv_priv; map_word oldd, curd; + int ret; if (cfi_use_status_reg(cfi)) { map_word ready = CMD(CFI_SR_DRB); - /* * For chips that support status register, check device * ready bit @@ -875,8 +853,24 @@ static int __xipram chip_good(struct map_info *map, struct flchip *chip, oldd = map_read(map, addr); curd = map_read(map, addr); - return map_word_equal(map, oldd, curd) && - map_word_equal(map, curd, expected); + ret = map_word_equal(map, oldd, curd); + + if (!ret || !expected) + return ret; + + return map_word_equal(map, curd, *expected); +} + +static int __xipram chip_good(struct map_info *map, struct flchip *chip, + unsigned long addr, map_word *expected) +{ + struct cfi_private *cfi = map->fldrv_priv; + map_word *datum = expected; + + if (cfi->quirks & CFI_QUIRK_DQ_TRUE_DATA) + datum = NULL; + + return chip_ready(map, chip, addr, datum); } static int get_chip(struct map_info *map, struct flchip *chip, unsigned long adr, int mode) @@ -893,7 +887,7 @@ static int get_chip(struct map_info *map, struct flchip *chip, unsigned long adr case FL_STATUS: for (;;) { - if (chip_ready(map, chip, adr)) + if (chip_ready(map, chip, adr, NULL)) break; if (time_after(jiffies, timeo)) { @@ -932,7 +926,7 @@ static int get_chip(struct map_info *map, struct flchip *chip, unsigned long adr chip->state = FL_ERASE_SUSPENDING; chip->erase_suspended = 1; for (;;) { - if (chip_ready(map, chip, adr)) + if (chip_ready(map, chip, adr, NULL)) break; if (time_after(jiffies, timeo)) { @@ -1463,7 +1457,7 @@ static int do_otp_lock(struct map_info *map, struct flchip *chip, loff_t adr, /* wait for chip to become ready */ timeo = jiffies + msecs_to_jiffies(2); for (;;) { - if (chip_ready(map, chip, adr)) + if (chip_ready(map, chip, adr, NULL)) break; if (time_after(jiffies, timeo)) { @@ -1699,7 +1693,7 @@ static int __xipram do_write_oneword_once(struct map_info *map, * "chip_good" to avoid the failure due to scheduling. */ if (time_after(jiffies, timeo) && - !chip_good(map, chip, adr, datum)) { + !chip_good(map, chip, adr, &datum)) { xip_enable(map, chip, adr); printk(KERN_WARNING "MTD %s(): software timeout\n", __func__); xip_disable(map, chip, adr); @@ -1707,7 +1701,7 @@ static int __xipram do_write_oneword_once(struct map_info *map, break; } - if (chip_good(map, chip, adr, datum)) { + if (chip_good(map, chip, adr, &datum)) { if (cfi_check_err_status(map, chip, adr)) ret = -EIO; break; @@ -1979,14 +1973,14 @@ static int __xipram do_write_buffer_wait(struct map_info *map, * "chip_good" to avoid the failure due to scheduling. */ if (time_after(jiffies, timeo) && - !chip_good(map, chip, adr, datum)) { + !chip_good(map, chip, adr, &datum)) { pr_err("MTD %s(): software timeout, address:0x%.8lx.\n", __func__, adr); ret = -EIO; break; } - if (chip_good(map, chip, adr, datum)) { + if (chip_good(map, chip, adr, &datum)) { if (cfi_check_err_status(map, chip, adr)) ret = -EIO; break; @@ -2195,7 +2189,7 @@ static int cfi_amdstd_panic_wait(struct map_info *map, struct flchip *chip, * If the driver thinks the chip is idle, and no toggle bits * are changing, then the chip is actually idle for sure. */ - if (chip->state == FL_READY && chip_ready(map, chip, adr)) + if (chip->state == FL_READY && chip_ready(map, chip, adr, NULL)) return 0; /* @@ -2212,7 +2206,7 @@ static int cfi_amdstd_panic_wait(struct map_info *map, struct flchip *chip, /* wait for the chip to become ready */ for (i = 0; i < jiffies_to_usecs(timeo); i++) { - if (chip_ready(map, chip, adr)) + if (chip_ready(map, chip, adr, NULL)) return 0; udelay(1); @@ -2276,13 +2270,13 @@ retry: map_write(map, datum, adr); for (i = 0; i < jiffies_to_usecs(uWriteTimeout); i++) { - if (chip_ready(map, chip, adr)) + if (chip_ready(map, chip, adr, NULL)) break; udelay(1); } - if (!chip_good(map, chip, adr, datum) || + if (!chip_ready(map, chip, adr, &datum) || cfi_check_err_status(map, chip, adr)) { /* reset on all failures. */ map_write(map, CMD(0xF0), chip->start); @@ -2424,6 +2418,7 @@ static int __xipram do_erase_chip(struct map_info *map, struct flchip *chip) DECLARE_WAITQUEUE(wait, current); int ret; int retry_cnt = 0; + map_word datum = map_word_ff(map); adr = cfi->addr_unlock1; @@ -2478,7 +2473,7 @@ static int __xipram do_erase_chip(struct map_info *map, struct flchip *chip) chip->erase_suspended = 0; } - if (chip_good(map, chip, adr, map_word_ff(map))) { + if (chip_ready(map, chip, adr, &datum)) { if (cfi_check_err_status(map, chip, adr)) ret = -EIO; break; @@ -2523,6 +2518,7 @@ static int __xipram do_erase_oneblock(struct map_info *map, struct flchip *chip, DECLARE_WAITQUEUE(wait, current); int ret; int retry_cnt = 0; + map_word datum = map_word_ff(map); adr += chip->start; @@ -2577,7 +2573,7 @@ static int __xipram do_erase_oneblock(struct map_info *map, struct flchip *chip, chip->erase_suspended = 0; } - if (chip_good(map, chip, adr, map_word_ff(map))) { + if (chip_ready(map, chip, adr, &datum)) { if (cfi_check_err_status(map, chip, adr)) ret = -EIO; break; @@ -2771,7 +2767,7 @@ static int __maybe_unused do_ppb_xxlock(struct map_info *map, */ timeo = jiffies + msecs_to_jiffies(2000); /* 2s max (un)locking */ for (;;) { - if (chip_ready(map, chip, adr)) + if (chip_ready(map, chip, adr, NULL)) break; if (time_after(jiffies, timeo)) { diff --git a/drivers/mtd/devices/phram.c b/drivers/mtd/devices/phram.c index d503821a3e60..208bd4d871f4 100644 --- a/drivers/mtd/devices/phram.c +++ b/drivers/mtd/devices/phram.c @@ -27,10 +27,14 @@ #include <linux/slab.h> #include <linux/mtd/mtd.h> #include <asm/div64.h> +#include <linux/platform_device.h> +#include <linux/of_address.h> +#include <linux/of.h> struct phram_mtd_list { struct mtd_info mtd; struct list_head list; + bool cached; }; static LIST_HEAD(phram_list); @@ -77,20 +81,51 @@ static int phram_write(struct mtd_info *mtd, loff_t to, size_t len, return 0; } +static int phram_map(struct phram_mtd_list *phram, phys_addr_t start, size_t len) +{ + void *addr = NULL; + + if (phram->cached) + addr = memremap(start, len, MEMREMAP_WB); + else + addr = (void __force *)ioremap(start, len); + if (!addr) + return -EIO; + + phram->mtd.priv = addr; + + return 0; +} + +static void phram_unmap(struct phram_mtd_list *phram) +{ + void *addr = phram->mtd.priv; + + if (phram->cached) { + memunmap(addr); + return; + } + + iounmap((void __iomem *)addr); +} + static void unregister_devices(void) { struct phram_mtd_list *this, *safe; list_for_each_entry_safe(this, safe, &phram_list, list) { mtd_device_unregister(&this->mtd); - iounmap(this->mtd.priv); + phram_unmap(this); kfree(this->mtd.name); kfree(this); } } -static int register_device(char *name, phys_addr_t start, size_t len, uint32_t erasesize) +static int register_device(struct platform_device *pdev, const char *name, + phys_addr_t start, size_t len, uint32_t erasesize) { + struct device_node *np = pdev ? pdev->dev.of_node : NULL; + bool cached = np ? !of_property_read_bool(np, "no-map") : false; struct phram_mtd_list *new; int ret = -ENOMEM; @@ -98,9 +133,10 @@ static int register_device(char *name, phys_addr_t start, size_t len, uint32_t e if (!new) goto out0; - ret = -EIO; - new->mtd.priv = ioremap(start, len); - if (!new->mtd.priv) { + new->cached = cached; + + ret = phram_map(new, start, len); + if (ret) { pr_err("ioremap failed\n"); goto out1; } @@ -119,17 +155,23 @@ static int register_device(char *name, phys_addr_t start, size_t len, uint32_t e new->mtd.erasesize = erasesize; new->mtd.writesize = 1; + mtd_set_of_node(&new->mtd, np); + ret = -EAGAIN; if (mtd_device_register(&new->mtd, NULL, 0)) { pr_err("Failed to register new device\n"); goto out2; } - list_add_tail(&new->list, &phram_list); + if (pdev) + platform_set_drvdata(pdev, new); + else + list_add_tail(&new->list, &phram_list); + return 0; out2: - iounmap(new->mtd.priv); + phram_unmap(new); out1: kfree(new); out0: @@ -278,7 +320,7 @@ static int phram_setup(const char *val) goto error; } - ret = register_device(name, start, len, (uint32_t)erasesize); + ret = register_device(NULL, name, start, len, (uint32_t)erasesize); if (ret) goto error; @@ -325,10 +367,54 @@ static int phram_param_call(const char *val, const struct kernel_param *kp) module_param_call(phram, phram_param_call, NULL, NULL, 0200); MODULE_PARM_DESC(phram, "Memory region to map. \"phram=<name>,<start>,<length>[,<erasesize>]\""); +#ifdef CONFIG_OF +static const struct of_device_id phram_of_match[] = { + { .compatible = "phram" }, + {} +}; +MODULE_DEVICE_TABLE(of, phram_of_match); +#endif + +static int phram_probe(struct platform_device *pdev) +{ + struct resource *res; + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (!res) + return -ENOMEM; + + /* mtd_set_of_node() reads name from "label" */ + return register_device(pdev, NULL, res->start, resource_size(res), + PAGE_SIZE); +} + +static int phram_remove(struct platform_device *pdev) +{ + struct phram_mtd_list *phram = platform_get_drvdata(pdev); + + mtd_device_unregister(&phram->mtd); + phram_unmap(phram); + kfree(phram); + + return 0; +} + +static struct platform_driver phram_driver = { + .probe = phram_probe, + .remove = phram_remove, + .driver = { + .name = "phram", + .of_match_table = of_match_ptr(phram_of_match), + }, +}; static int __init init_phram(void) { - int ret = 0; + int ret; + + ret = platform_driver_register(&phram_driver); + if (ret) + return ret; #ifndef MODULE if (phram_paramline[0]) @@ -336,12 +422,16 @@ static int __init init_phram(void) phram_init_called = 1; #endif + if (ret) + platform_driver_unregister(&phram_driver); + return ret; } static void __exit cleanup_phram(void) { unregister_devices(); + platform_driver_unregister(&phram_driver); } module_init(init_phram); diff --git a/drivers/mtd/devices/st_spi_fsm.c b/drivers/mtd/devices/st_spi_fsm.c index 983999c020d6..d3377b10fc0f 100644 --- a/drivers/mtd/devices/st_spi_fsm.c +++ b/drivers/mtd/devices/st_spi_fsm.c @@ -2126,6 +2126,8 @@ static int stfsm_remove(struct platform_device *pdev) { struct stfsm *fsm = platform_get_drvdata(pdev); + clk_disable_unprepare(fsm->clk); + return mtd_device_unregister(&fsm->mtd); } diff --git a/drivers/mtd/maps/Kconfig b/drivers/mtd/maps/Kconfig index 6a099bbcd8be..e098ae937ce8 100644 --- a/drivers/mtd/maps/Kconfig +++ b/drivers/mtd/maps/Kconfig @@ -300,15 +300,6 @@ config MTD_DC21285 21285 bridge used with Intel's StrongARM processors. More info at <https://www.intel.com/design/bridge/docs/21285_documentation.htm>. -config MTD_IXP4XX - tristate "CFI Flash device mapped on Intel IXP4xx based systems" - depends on MTD_CFI && MTD_COMPLEX_MAPPINGS && ARCH_IXP4XX && MTD_CFI_ADV_OPTIONS - help - This enables MTD access to flash devices on platforms based - on Intel's IXP4xx family of network processors such as the - IXDP425 and Coyote. If you have an IXP4xx based board and - would like to use the flash chips on it, say 'Y'. - config MTD_IMPA7 tristate "JEDEC Flash device mapped on impA7" depends on ARM && MTD_JEDECPROBE diff --git a/drivers/mtd/maps/Makefile b/drivers/mtd/maps/Makefile index 2240b100f66a..094cfb244086 100644 --- a/drivers/mtd/maps/Makefile +++ b/drivers/mtd/maps/Makefile @@ -39,7 +39,6 @@ obj-$(CONFIG_MTD_IMPA7) += impa7.o obj-$(CONFIG_MTD_UCLINUX) += uclinux.o obj-$(CONFIG_MTD_NETtel) += nettel.o obj-$(CONFIG_MTD_SCB2_FLASH) += scb2_flash.o -obj-$(CONFIG_MTD_IXP4XX) += ixp4xx.o obj-$(CONFIG_MTD_PLATRAM) += plat-ram.o obj-$(CONFIG_MTD_INTEL_VR_NOR) += intel_vr_nor.o obj-$(CONFIG_MTD_VMU) += vmu-flash.o diff --git a/drivers/mtd/maps/ixp4xx.c b/drivers/mtd/maps/ixp4xx.c deleted file mode 100644 index d8543201ab94..000000000000 --- a/drivers/mtd/maps/ixp4xx.c +++ /dev/null @@ -1,262 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * drivers/mtd/maps/ixp4xx.c - * - * MTD Map file for IXP4XX based systems. Please do not make per-board - * changes in here. If your board needs special setup, do it in your - * platform level code in arch/arm/mach-ixp4xx/board-setup.c - * - * Original Author: Intel Corporation - * Maintainer: Deepak Saxena <dsaxena@mvista.com> - * - * Copyright (C) 2002 Intel Corporation - * Copyright (C) 2003-2004 MontaVista Software, Inc. - * - */ - -#include <linux/err.h> -#include <linux/module.h> -#include <linux/types.h> -#include <linux/kernel.h> -#include <linux/string.h> -#include <linux/slab.h> -#include <linux/ioport.h> -#include <linux/device.h> -#include <linux/platform_device.h> - -#include <linux/mtd/mtd.h> -#include <linux/mtd/map.h> -#include <linux/mtd/partitions.h> - -#include <asm/io.h> -#include <asm/mach/flash.h> - -#include <linux/reboot.h> - -/* - * Read/write a 16 bit word from flash address 'addr'. - * - * When the cpu is in little-endian mode it swizzles the address lines - * ('address coherency') so we need to undo the swizzling to ensure commands - * and the like end up on the correct flash address. - * - * To further complicate matters, due to the way the expansion bus controller - * handles 32 bit reads, the byte stream ABCD is stored on the flash as: - * D15 D0 - * +---+---+ - * | A | B | 0 - * +---+---+ - * | C | D | 2 - * +---+---+ - * This means that on LE systems each 16 bit word must be swapped. Note that - * this requires CONFIG_MTD_CFI_BE_BYTE_SWAP to be enabled to 'unswap' the CFI - * data and other flash commands which are always in D7-D0. - */ -#ifndef __ARMEB__ -#ifndef CONFIG_MTD_CFI_BE_BYTE_SWAP -# error CONFIG_MTD_CFI_BE_BYTE_SWAP required -#endif - -static inline u16 flash_read16(void __iomem *addr) -{ - return be16_to_cpu(__raw_readw((void __iomem *)((unsigned long)addr ^ 0x2))); -} - -static inline void flash_write16(u16 d, void __iomem *addr) -{ - __raw_writew(cpu_to_be16(d), (void __iomem *)((unsigned long)addr ^ 0x2)); -} - -#define BYTE0(h) ((h) & 0xFF) -#define BYTE1(h) (((h) >> 8) & 0xFF) - -#else - -static inline u16 flash_read16(const void __iomem *addr) -{ - return __raw_readw(addr); -} - -static inline void flash_write16(u16 d, void __iomem *addr) -{ - __raw_writew(d, addr); -} - -#define BYTE0(h) (((h) >> 8) & 0xFF) -#define BYTE1(h) ((h) & 0xFF) -#endif - -static map_word ixp4xx_read16(struct map_info *map, unsigned long ofs) -{ - map_word val; - val.x[0] = flash_read16(map->virt + ofs); - return val; -} - -/* - * The IXP4xx expansion bus only allows 16-bit wide acceses - * when attached to a 16-bit wide device (such as the 28F128J3A), - * so we can't just memcpy_fromio(). - */ -static void ixp4xx_copy_from(struct map_info *map, void *to, - unsigned long from, ssize_t len) -{ - u8 *dest = (u8 *) to; - void __iomem *src = map->virt + from; - - if (len <= 0) - return; - - if (from & 1) { - *dest++ = BYTE1(flash_read16(src-1)); - src++; - --len; - } - - while (len >= 2) { - u16 data = flash_read16(src); - *dest++ = BYTE0(data); - *dest++ = BYTE1(data); - src += 2; - len -= 2; - } - - if (len > 0) - *dest++ = BYTE0(flash_read16(src)); -} - -/* - * Unaligned writes are ignored, causing the 8-bit - * probe to fail and proceed to the 16-bit probe (which succeeds). - */ -static void ixp4xx_probe_write16(struct map_info *map, map_word d, unsigned long adr) -{ - if (!(adr & 1)) - flash_write16(d.x[0], map->virt + adr); -} - -/* - * Fast write16 function without the probing check above - */ -static void ixp4xx_write16(struct map_info *map, map_word d, unsigned long adr) -{ - flash_write16(d.x[0], map->virt + adr); -} - -struct ixp4xx_flash_info { - struct mtd_info *mtd; - struct map_info map; - struct resource *res; -}; - -static const char * const probes[] = { "RedBoot", "cmdlinepart", NULL }; - -static int ixp4xx_flash_remove(struct platform_device *dev) -{ - struct flash_platform_data *plat = dev_get_platdata(&dev->dev); - struct ixp4xx_flash_info *info = platform_get_drvdata(dev); - - if(!info) - return 0; - - if (info->mtd) { - mtd_device_unregister(info->mtd); - map_destroy(info->mtd); - } - - if (plat->exit) - plat->exit(); - - return 0; -} - -static int ixp4xx_flash_probe(struct platform_device *dev) -{ - struct flash_platform_data *plat = dev_get_platdata(&dev->dev); - struct ixp4xx_flash_info *info; - struct mtd_part_parser_data ppdata = { - .origin = dev->resource->start, - }; - int err = -1; - - if (!plat) - return -ENODEV; - - if (plat->init) { - err = plat->init(); - if (err) - return err; - } - - info = devm_kzalloc(&dev->dev, sizeof(struct ixp4xx_flash_info), - GFP_KERNEL); - if(!info) { - err = -ENOMEM; - goto Error; - } - - platform_set_drvdata(dev, info); - - /* - * Tell the MTD layer we're not 1:1 mapped so that it does - * not attempt to do a direct access on us. - */ - info->map.phys = NO_XIP; - info->map.size = resource_size(dev->resource); - - /* - * We only support 16-bit accesses for now. If and when - * any board use 8-bit access, we'll fixup the driver to - * handle that. - */ - info->map.bankwidth = 2; - info->map.name = dev_name(&dev->dev); - info->map.read = ixp4xx_read16; - info->map.write = ixp4xx_probe_write16; - info->map.copy_from = ixp4xx_copy_from; - - info->map.virt = devm_ioremap_resource(&dev->dev, dev->resource); - if (IS_ERR(info->map.virt)) { - err = PTR_ERR(info->map.virt); - goto Error; - } - - info->mtd = do_map_probe(plat->map_name, &info->map); - if (!info->mtd) { - printk(KERN_ERR "IXP4XXFlash: map_probe failed\n"); - err = -ENXIO; - goto Error; - } - info->mtd->dev.parent = &dev->dev; - - /* Use the fast version */ - info->map.write = ixp4xx_write16; - - err = mtd_device_parse_register(info->mtd, probes, &ppdata, - plat->parts, plat->nr_parts); - if (err) { - printk(KERN_ERR "Could not parse partitions\n"); - goto Error; - } - - return 0; - -Error: - ixp4xx_flash_remove(dev); - return err; -} - -static struct platform_driver ixp4xx_flash_driver = { - .probe = ixp4xx_flash_probe, - .remove = ixp4xx_flash_remove, - .driver = { - .name = "IXP4XX-Flash", - }, -}; - -module_platform_driver(ixp4xx_flash_driver); - -MODULE_LICENSE("GPL"); -MODULE_DESCRIPTION("MTD map driver for Intel IXP4xx systems"); -MODULE_AUTHOR("Deepak Saxena"); -MODULE_ALIAS("platform:IXP4XX-Flash"); diff --git a/drivers/mtd/mtd_blkdevs.c b/drivers/mtd/mtd_blkdevs.c index 64d2b093f114..f73172111465 100644 --- a/drivers/mtd/mtd_blkdevs.c +++ b/drivers/mtd/mtd_blkdevs.c @@ -377,7 +377,6 @@ int add_mtd_blktrans_dev(struct mtd_blktrans_dev *new) blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, new->rq); if (tr->discard) { - blk_queue_flag_set(QUEUE_FLAG_DISCARD, new->rq); blk_queue_max_discard_sectors(new->rq, UINT_MAX); new->rq->limits.discard_granularity = tr->blksize; } diff --git a/drivers/mtd/mtdblock.c b/drivers/mtd/mtdblock.c index 03e3de3a5d79..1e94e7d10b8b 100644 --- a/drivers/mtd/mtdblock.c +++ b/drivers/mtd/mtdblock.c @@ -257,6 +257,10 @@ static int mtdblock_open(struct mtd_blktrans_dev *mbd) return 0; } + if (mtd_type_is_nand(mbd->mtd)) + pr_warn("%s: MTD device '%s' is NAND, please consider using UBI block devices instead.\n", + mbd->tr->name, mbd->mtd->name); + /* OK, it's not open. Create cache info for it */ mtdblk->count = 1; mutex_init(&mtdblk->cache_mutex); @@ -322,10 +326,6 @@ static void mtdblock_add_mtd(struct mtd_blktrans_ops *tr, struct mtd_info *mtd) if (!(mtd->flags & MTD_WRITEABLE)) dev->mbd.readonly = 1; - if (mtd_type_is_nand(mtd)) - pr_warn("%s: MTD device '%s' is NAND, please consider using UBI block devices instead.\n", - tr->name, mtd->name); - if (add_mtd_blktrans_dev(&dev->mbd)) kfree(dev); } diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c index 7731796024e0..9eb0680db312 100644 --- a/drivers/mtd/mtdcore.c +++ b/drivers/mtd/mtdcore.c @@ -557,9 +557,10 @@ static int mtd_nvmem_add(struct mtd_info *mtd) int add_mtd_device(struct mtd_info *mtd) { + struct device_node *np = mtd_get_of_node(mtd); struct mtd_info *master = mtd_get_master(mtd); struct mtd_notifier *not; - int i, error; + int i, error, ofidx; /* * May occur, for instance, on buggy drivers which call @@ -598,7 +599,13 @@ int add_mtd_device(struct mtd_info *mtd) mutex_lock(&mtd_table_mutex); - i = idr_alloc(&mtd_idr, mtd, 0, 0, GFP_KERNEL); + ofidx = -1; + if (np) + ofidx = of_alias_get_id(np, "mtd"); + if (ofidx >= 0) + i = idr_alloc(&mtd_idr, mtd, ofidx, ofidx + 1, GFP_KERNEL); + else + i = idr_alloc(&mtd_idr, mtd, 0, 0, GFP_KERNEL); if (i < 0) { error = i; goto fail_locked; diff --git a/drivers/mtd/mtdoops.c b/drivers/mtd/mtdoops.c index 227df24387df..3d4a2ffb5b01 100644 --- a/drivers/mtd/mtdoops.c +++ b/drivers/mtd/mtdoops.c @@ -16,15 +16,13 @@ #include <linux/wait.h> #include <linux/delay.h> #include <linux/interrupt.h> +#include <linux/timekeeping.h> #include <linux/mtd/mtd.h> #include <linux/kmsg_dump.h> /* Maximum MTD partition size */ #define MTDOOPS_MAX_MTD_SIZE (8 * 1024 * 1024) -#define MTDOOPS_KERNMSG_MAGIC 0x5d005d00 -#define MTDOOPS_HEADER_SIZE 8 - static unsigned long record_size = 4096; module_param(record_size, ulong, 0400); MODULE_PARM_DESC(record_size, @@ -40,6 +38,15 @@ module_param(dump_oops, int, 0600); MODULE_PARM_DESC(dump_oops, "set to 1 to dump oopses, 0 to only dump panics (default 1)"); +#define MTDOOPS_KERNMSG_MAGIC_v1 0x5d005d00 /* Original */ +#define MTDOOPS_KERNMSG_MAGIC_v2 0x5d005e00 /* Adds the timestamp */ + +struct mtdoops_hdr { + u32 seq; + u32 magic; + ktime_t timestamp; +} __packed; + static struct mtdoops_context { struct kmsg_dumper dump; @@ -178,16 +185,17 @@ static void mtdoops_write(struct mtdoops_context *cxt, int panic) { struct mtd_info *mtd = cxt->mtd; size_t retlen; - u32 *hdr; + struct mtdoops_hdr *hdr; int ret; if (test_and_set_bit(0, &cxt->oops_buf_busy)) return; /* Add mtdoops header to the buffer */ - hdr = cxt->oops_buf; - hdr[0] = cxt->nextcount; - hdr[1] = MTDOOPS_KERNMSG_MAGIC; + hdr = (struct mtdoops_hdr *)cxt->oops_buf; + hdr->seq = cxt->nextcount; + hdr->magic = MTDOOPS_KERNMSG_MAGIC_v2; + hdr->timestamp = ktime_get_real(); if (panic) { ret = mtd_panic_write(mtd, cxt->nextpage * record_size, @@ -222,8 +230,9 @@ static void mtdoops_workfunc_write(struct work_struct *work) static void find_next_position(struct mtdoops_context *cxt) { struct mtd_info *mtd = cxt->mtd; + struct mtdoops_hdr hdr; int ret, page, maxpos = 0; - u32 count[2], maxcount = 0xffffffff; + u32 maxcount = 0xffffffff; size_t retlen; for (page = 0; page < cxt->oops_pages; page++) { @@ -231,32 +240,33 @@ static void find_next_position(struct mtdoops_context *cxt) continue; /* Assume the page is used */ mark_page_used(cxt, page); - ret = mtd_read(mtd, page * record_size, MTDOOPS_HEADER_SIZE, - &retlen, (u_char *)&count[0]); - if (retlen != MTDOOPS_HEADER_SIZE || + ret = mtd_read(mtd, page * record_size, sizeof(hdr), + &retlen, (u_char *)&hdr); + if (retlen != sizeof(hdr) || (ret < 0 && !mtd_is_bitflip(ret))) { - printk(KERN_ERR "mtdoops: read failure at %ld (%td of %d read), err %d\n", - page * record_size, retlen, - MTDOOPS_HEADER_SIZE, ret); + printk(KERN_ERR "mtdoops: read failure at %ld (%zu of %zu read), err %d\n", + page * record_size, retlen, sizeof(hdr), ret); continue; } - if (count[0] == 0xffffffff && count[1] == 0xffffffff) + if (hdr.seq == 0xffffffff && hdr.magic == 0xffffffff) mark_page_unused(cxt, page); - if (count[0] == 0xffffffff || count[1] != MTDOOPS_KERNMSG_MAGIC) + if (hdr.seq == 0xffffffff || + (hdr.magic != MTDOOPS_KERNMSG_MAGIC_v1 && + hdr.magic != MTDOOPS_KERNMSG_MAGIC_v2)) continue; if (maxcount == 0xffffffff) { - maxcount = count[0]; + maxcount = hdr.seq; maxpos = page; - } else if (count[0] < 0x40000000 && maxcount > 0xc0000000) { - maxcount = count[0]; + } else if (hdr.seq < 0x40000000 && maxcount > 0xc0000000) { + maxcount = hdr.seq; maxpos = page; - } else if (count[0] > maxcount && count[0] < 0xc0000000) { - maxcount = count[0]; + } else if (hdr.seq > maxcount && hdr.seq < 0xc0000000) { + maxcount = hdr.seq; maxpos = page; - } else if (count[0] > maxcount && count[0] > 0xc0000000 + } else if (hdr.seq > maxcount && hdr.seq > 0xc0000000 && maxcount > 0x80000000) { - maxcount = count[0]; + maxcount = hdr.seq; maxpos = page; } } @@ -287,8 +297,9 @@ static void mtdoops_do_dump(struct kmsg_dumper *dumper, if (test_and_set_bit(0, &cxt->oops_buf_busy)) return; - kmsg_dump_get_buffer(&iter, true, cxt->oops_buf + MTDOOPS_HEADER_SIZE, - record_size - MTDOOPS_HEADER_SIZE, NULL); + kmsg_dump_get_buffer(&iter, true, + cxt->oops_buf + sizeof(struct mtdoops_hdr), + record_size - sizeof(struct mtdoops_hdr), NULL); clear_bit(0, &cxt->oops_buf_busy); if (reason != KMSG_DUMP_OOPS) { diff --git a/drivers/mtd/mtdpart.c b/drivers/mtd/mtdpart.c index 357661b62c94..d442fa94c872 100644 --- a/drivers/mtd/mtdpart.c +++ b/drivers/mtd/mtdpart.c @@ -17,6 +17,7 @@ #include <linux/mtd/partitions.h> #include <linux/err.h> #include <linux/of.h> +#include <linux/of_platform.h> #include "mtdcore.h" @@ -577,10 +578,16 @@ static int mtd_part_of_parse(struct mtd_info *master, struct mtd_part_parser *parser; struct device_node *np; struct property *prop; + struct device *dev; const char *compat; const char *fixed = "fixed-partitions"; int ret, err = 0; + dev = &master->dev; + /* Use parent device (controller) if the top level MTD is not registered */ + if (!IS_ENABLED(CONFIG_MTD_PARTITIONED_MASTER) && !mtd_is_partition(master)) + dev = master->dev.parent; + np = mtd_get_of_node(master); if (mtd_is_partition(master)) of_node_get(np); @@ -593,6 +600,7 @@ static int mtd_part_of_parse(struct mtd_info *master, continue; ret = mtd_part_do_parse(parser, master, pparts, NULL); if (ret > 0) { + of_platform_populate(np, NULL, NULL, dev); of_node_put(np); return ret; } @@ -600,6 +608,7 @@ static int mtd_part_of_parse(struct mtd_info *master, if (ret < 0 && !err) err = ret; } + of_platform_populate(np, NULL, NULL, dev); of_node_put(np); /* diff --git a/drivers/mtd/nand/Kconfig b/drivers/mtd/nand/Kconfig index 9b249826ef93..5b0c2c95f10c 100644 --- a/drivers/mtd/nand/Kconfig +++ b/drivers/mtd/nand/Kconfig @@ -53,6 +53,14 @@ config MTD_NAND_ECC_MXIC help This enables support for the hardware ECC engine from Macronix. +config MTD_NAND_ECC_MEDIATEK + tristate "Mediatek hardware ECC engine" + depends on HAS_IOMEM + depends on ARCH_MEDIATEK || COMPILE_TEST + select MTD_NAND_ECC + help + This enables support for the hardware ECC engine from Mediatek. + endmenu endmenu diff --git a/drivers/mtd/nand/Makefile b/drivers/mtd/nand/Makefile index a4e6b7ae0614..19e1291ac4d5 100644 --- a/drivers/mtd/nand/Makefile +++ b/drivers/mtd/nand/Makefile @@ -2,6 +2,7 @@ nandcore-objs := core.o bbt.o obj-$(CONFIG_MTD_NAND_CORE) += nandcore.o +obj-$(CONFIG_MTD_NAND_ECC_MEDIATEK) += ecc-mtk.o obj-y += onenand/ obj-y += raw/ diff --git a/drivers/mtd/nand/raw/mtk_ecc.c b/drivers/mtd/nand/ecc-mtk.c index e7df3dac705e..9f9b201fe706 100644 --- a/drivers/mtd/nand/raw/mtk_ecc.c +++ b/drivers/mtd/nand/ecc-mtk.c @@ -15,8 +15,7 @@ #include <linux/of.h> #include <linux/of_platform.h> #include <linux/mutex.h> - -#include "mtk_ecc.h" +#include <linux/mtd/nand-ecc-mtk.h> #define ECC_IDLE_MASK BIT(0) #define ECC_IRQ_EN BIT(0) @@ -43,6 +42,7 @@ struct mtk_ecc_caps { u32 err_mask; + u32 err_shift; const u8 *ecc_strength; const u32 *ecc_regs; u8 num_ecc_strength; @@ -76,7 +76,7 @@ static const u8 ecc_strength_mt2712[] = { }; static const u8 ecc_strength_mt7622[] = { - 4, 6, 8, 10, 12, 14, 16 + 4, 6, 8, 10, 12 }; enum mtk_ecc_regs { @@ -221,7 +221,7 @@ void mtk_ecc_get_stats(struct mtk_ecc *ecc, struct mtk_ecc_stats *stats, for (i = 0; i < sectors; i++) { offset = (i >> 2) << 2; err = readl(ecc->regs + ECC_DECENUM0 + offset); - err = err >> ((i % 4) * 8); + err = err >> ((i % 4) * ecc->caps->err_shift); err &= ecc->caps->err_mask; if (err == ecc->caps->err_mask) { /* uncorrectable errors */ @@ -279,7 +279,10 @@ struct mtk_ecc *of_mtk_ecc_get(struct device_node *of_node) struct mtk_ecc *ecc = NULL; struct device_node *np; - np = of_parse_phandle(of_node, "ecc-engine", 0); + np = of_parse_phandle(of_node, "nand-ecc-engine", 0); + /* for backward compatibility */ + if (!np) + np = of_parse_phandle(of_node, "ecc-engine", 0); if (np) { ecc = mtk_ecc_get(np); of_node_put(np); @@ -449,6 +452,7 @@ EXPORT_SYMBOL(mtk_ecc_get_parity_bits); static const struct mtk_ecc_caps mtk_ecc_caps_mt2701 = { .err_mask = 0x3f, + .err_shift = 8, .ecc_strength = ecc_strength_mt2701, .ecc_regs = mt2701_ecc_regs, .num_ecc_strength = 20, @@ -459,6 +463,7 @@ static const struct mtk_ecc_caps mtk_ecc_caps_mt2701 = { static const struct mtk_ecc_caps mtk_ecc_caps_mt2712 = { .err_mask = 0x7f, + .err_shift = 8, .ecc_strength = ecc_strength_mt2712, .ecc_regs = mt2712_ecc_regs, .num_ecc_strength = 23, @@ -468,10 +473,11 @@ static const struct mtk_ecc_caps mtk_ecc_caps_mt2712 = { }; static const struct mtk_ecc_caps mtk_ecc_caps_mt7622 = { - .err_mask = 0x3f, + .err_mask = 0x1f, + .err_shift = 5, .ecc_strength = ecc_strength_mt7622, .ecc_regs = mt7622_ecc_regs, - .num_ecc_strength = 7, + .num_ecc_strength = 5, .ecc_mode_shift = 4, .parity_bits = 13, .pg_irq_sel = 0, diff --git a/drivers/mtd/nand/raw/Kconfig b/drivers/mtd/nand/raw/Kconfig index 9b078e78f3fa..8b6d7a515445 100644 --- a/drivers/mtd/nand/raw/Kconfig +++ b/drivers/mtd/nand/raw/Kconfig @@ -374,6 +374,7 @@ config MTD_NAND_QCOM config MTD_NAND_MTK tristate "MTK NAND controller" + depends on MTD_NAND_ECC_MEDIATEK depends on ARCH_MEDIATEK || COMPILE_TEST depends on HAS_IOMEM help diff --git a/drivers/mtd/nand/raw/Makefile b/drivers/mtd/nand/raw/Makefile index 88a566513c56..fa1d00120310 100644 --- a/drivers/mtd/nand/raw/Makefile +++ b/drivers/mtd/nand/raw/Makefile @@ -48,7 +48,7 @@ obj-$(CONFIG_MTD_NAND_SUNXI) += sunxi_nand.o obj-$(CONFIG_MTD_NAND_HISI504) += hisi504_nand.o obj-$(CONFIG_MTD_NAND_BRCMNAND) += brcmnand/ obj-$(CONFIG_MTD_NAND_QCOM) += qcom_nandc.o -obj-$(CONFIG_MTD_NAND_MTK) += mtk_ecc.o mtk_nand.o +obj-$(CONFIG_MTD_NAND_MTK) += mtk_nand.o obj-$(CONFIG_MTD_NAND_MXIC) += mxic_nand.o obj-$(CONFIG_MTD_NAND_TEGRA) += tegra_nand.o obj-$(CONFIG_MTD_NAND_STM32_FMC2) += stm32_fmc2_nand.o diff --git a/drivers/mtd/nand/raw/cadence-nand-controller.c b/drivers/mtd/nand/raw/cadence-nand-controller.c index 7eec60ea9056..0d72672f8b64 100644 --- a/drivers/mtd/nand/raw/cadence-nand-controller.c +++ b/drivers/mtd/nand/raw/cadence-nand-controller.c @@ -2983,11 +2983,10 @@ static int cadence_nand_dt_probe(struct platform_device *ofdev) if (IS_ERR(cdns_ctrl->reg)) return PTR_ERR(cdns_ctrl->reg); - res = platform_get_resource(ofdev, IORESOURCE_MEM, 1); - cdns_ctrl->io.dma = res->start; - cdns_ctrl->io.virt = devm_ioremap_resource(&ofdev->dev, res); + cdns_ctrl->io.virt = devm_platform_get_and_ioremap_resource(ofdev, 1, &res); if (IS_ERR(cdns_ctrl->io.virt)) return PTR_ERR(cdns_ctrl->io.virt); + cdns_ctrl->io.dma = res->start; dt->clk = devm_clk_get(cdns_ctrl->dev, "nf_clk"); if (IS_ERR(dt->clk)) diff --git a/drivers/mtd/nand/raw/cs553x_nand.c b/drivers/mtd/nand/raw/cs553x_nand.c index 6edf78c16fc8..f0a15717cf05 100644 --- a/drivers/mtd/nand/raw/cs553x_nand.c +++ b/drivers/mtd/nand/raw/cs553x_nand.c @@ -104,17 +104,12 @@ static int cs553x_write_ctrl_byte(struct cs553x_nand_controller *cs553x, u32 ctl, u8 data) { u8 status; - int ret; writeb(ctl, cs553x->mmio + MM_NAND_CTL); writeb(data, cs553x->mmio + MM_NAND_IO); - ret = readb_poll_timeout_atomic(cs553x->mmio + MM_NAND_STS, status, + return readb_poll_timeout_atomic(cs553x->mmio + MM_NAND_STS, status, !(status & CS_NAND_CTLR_BUSY), 1, 100000); - if (ret) - return ret; - - return 0; } static void cs553x_data_in(struct cs553x_nand_controller *cs553x, void *buf, diff --git a/drivers/mtd/nand/raw/davinci_nand.c b/drivers/mtd/nand/raw/davinci_nand.c index 45fec8c192ab..3e98e3c255bf 100644 --- a/drivers/mtd/nand/raw/davinci_nand.c +++ b/drivers/mtd/nand/raw/davinci_nand.c @@ -727,7 +727,7 @@ static int nand_davinci_probe(struct platform_device *pdev) return -ENODEV; /* which external chipselect will we be managing? */ - if (pdata->core_chipsel < 0 || pdata->core_chipsel > 3) + if (pdata->core_chipsel > 3) return -ENODEV; info = devm_kzalloc(&pdev->dev, sizeof(*info), GFP_KERNEL); diff --git a/drivers/mtd/nand/raw/denali_pci.c b/drivers/mtd/nand/raw/denali_pci.c index 20c085a30adc..de7e722d3826 100644 --- a/drivers/mtd/nand/raw/denali_pci.c +++ b/drivers/mtd/nand/raw/denali_pci.c @@ -74,22 +74,21 @@ static int denali_pci_probe(struct pci_dev *dev, const struct pci_device_id *id) return ret; } - denali->reg = ioremap(csr_base, csr_len); + denali->reg = devm_ioremap(denali->dev, csr_base, csr_len); if (!denali->reg) { dev_err(&dev->dev, "Spectra: Unable to remap memory region\n"); return -ENOMEM; } - denali->host = ioremap(mem_base, mem_len); + denali->host = devm_ioremap(denali->dev, mem_base, mem_len); if (!denali->host) { dev_err(&dev->dev, "Spectra: ioremap failed!"); - ret = -ENOMEM; - goto out_unmap_reg; + return -ENOMEM; } ret = denali_init(denali); if (ret) - goto out_unmap_host; + return ret; nsels = denali->nbanks; @@ -117,10 +116,6 @@ static int denali_pci_probe(struct pci_dev *dev, const struct pci_device_id *id) out_remove_denali: denali_remove(denali); -out_unmap_host: - iounmap(denali->host); -out_unmap_reg: - iounmap(denali->reg); return ret; } @@ -129,8 +124,6 @@ static void denali_pci_remove(struct pci_dev *dev) struct denali_controller *denali = pci_get_drvdata(dev); denali_remove(denali); - iounmap(denali->reg); - iounmap(denali->host); } static struct pci_driver denali_pci_driver = { diff --git a/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c b/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c index 44b14c9dc9a7..0b68d05846e1 100644 --- a/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c +++ b/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c @@ -218,7 +218,8 @@ static void gpmi_dump_info(struct gpmi_nand_data *this) "ECC Strength : %u\n" "Page Size in Bytes : %u\n" "Metadata Size in Bytes : %u\n" - "ECC Chunk Size in Bytes: %u\n" + "ECC0 Chunk Size in Bytes: %u\n" + "ECCn Chunk Size in Bytes: %u\n" "ECC Chunk Count : %u\n" "Payload Size in Bytes : %u\n" "Auxiliary Size in Bytes: %u\n" @@ -229,7 +230,8 @@ static void gpmi_dump_info(struct gpmi_nand_data *this) geo->ecc_strength, geo->page_size, geo->metadata_size, - geo->ecc_chunk_size, + geo->ecc0_chunk_size, + geo->eccn_chunk_size, geo->ecc_chunk_count, geo->payload_size, geo->auxiliary_size, @@ -238,9 +240,15 @@ static void gpmi_dump_info(struct gpmi_nand_data *this) geo->block_mark_bit_offset); } -static inline bool gpmi_check_ecc(struct gpmi_nand_data *this) +static bool gpmi_check_ecc(struct gpmi_nand_data *this) { + struct nand_chip *chip = &this->nand; struct bch_geometry *geo = &this->bch_geometry; + struct nand_device *nand = &chip->base; + struct nand_ecc_props *conf = &nand->ecc.ctx.conf; + + conf->step_size = geo->eccn_chunk_size; + conf->strength = geo->ecc_strength; /* Do the sanity check. */ if (GPMI_IS_MXS(this)) { @@ -248,7 +256,47 @@ static inline bool gpmi_check_ecc(struct gpmi_nand_data *this) if (geo->gf_len == 14) return false; } - return geo->ecc_strength <= this->devdata->bch_max_ecc_strength; + + if (geo->ecc_strength > this->devdata->bch_max_ecc_strength) + return false; + + if (!nand_ecc_is_strong_enough(nand)) + return false; + + return true; +} + +/* check if bbm locates in data chunk rather than ecc chunk */ +static bool bbm_in_data_chunk(struct gpmi_nand_data *this, + unsigned int *chunk_num) +{ + struct bch_geometry *geo = &this->bch_geometry; + struct nand_chip *chip = &this->nand; + struct mtd_info *mtd = nand_to_mtd(chip); + unsigned int i, j; + + if (geo->ecc0_chunk_size != geo->eccn_chunk_size) { + dev_err(this->dev, + "The size of ecc0_chunk must equal to eccn_chunk\n"); + return false; + } + + i = (mtd->writesize * 8 - geo->metadata_size * 8) / + (geo->gf_len * geo->ecc_strength + + geo->eccn_chunk_size * 8); + + j = (mtd->writesize * 8 - geo->metadata_size * 8) - + (geo->gf_len * geo->ecc_strength + + geo->eccn_chunk_size * 8) * i; + + if (j < geo->eccn_chunk_size * 8) { + *chunk_num = i+1; + dev_dbg(this->dev, "Set ecc to %d and bbm in chunk %d\n", + geo->ecc_strength, *chunk_num); + return true; + } + + return false; } /* @@ -280,13 +328,14 @@ static int set_geometry_by_ecc_info(struct gpmi_nand_data *this, nanddev_get_ecc_requirements(&chip->base)->step_size); return -EINVAL; } - geo->ecc_chunk_size = ecc_step; + geo->ecc0_chunk_size = ecc_step; + geo->eccn_chunk_size = ecc_step; geo->ecc_strength = round_up(ecc_strength, 2); if (!gpmi_check_ecc(this)) return -EINVAL; /* Keep the C >= O */ - if (geo->ecc_chunk_size < mtd->oobsize) { + if (geo->eccn_chunk_size < mtd->oobsize) { dev_err(this->dev, "unsupported nand chip. ecc size: %d, oob size : %d\n", ecc_step, mtd->oobsize); @@ -296,7 +345,7 @@ static int set_geometry_by_ecc_info(struct gpmi_nand_data *this, /* The default value, see comment in the legacy_set_geometry(). */ geo->metadata_size = 10; - geo->ecc_chunk_count = mtd->writesize / geo->ecc_chunk_size; + geo->ecc_chunk_count = mtd->writesize / geo->eccn_chunk_size; /* * Now, the NAND chip with 2K page(data chunk is 512byte) shows below: @@ -399,6 +448,134 @@ static inline int get_ecc_strength(struct gpmi_nand_data *this) return round_down(ecc_strength, 2); } +static int set_geometry_for_large_oob(struct gpmi_nand_data *this) +{ + struct bch_geometry *geo = &this->bch_geometry; + struct nand_chip *chip = &this->nand; + struct mtd_info *mtd = nand_to_mtd(chip); + const struct nand_ecc_props *requirements = + nanddev_get_ecc_requirements(&chip->base); + unsigned int block_mark_bit_offset; + unsigned int max_ecc; + unsigned int bbm_chunk; + unsigned int i; + + /* sanity check for the minimum ecc nand required */ + if (!(requirements->strength > 0 && + requirements->step_size > 0)) + return -EINVAL; + geo->ecc_strength = requirements->strength; + + /* check if platform can support this nand */ + if (!gpmi_check_ecc(this)) { + dev_err(this->dev, + "unsupported NAND chip, minimum ecc required %d\n", + geo->ecc_strength); + return -EINVAL; + } + + /* calculate the maximum ecc platform can support*/ + geo->metadata_size = 10; + geo->gf_len = 14; + geo->ecc0_chunk_size = 1024; + geo->eccn_chunk_size = 1024; + geo->ecc_chunk_count = mtd->writesize / geo->eccn_chunk_size; + max_ecc = min(get_ecc_strength(this), + this->devdata->bch_max_ecc_strength); + + /* + * search a supported ecc strength that makes bbm + * located in data chunk + */ + geo->ecc_strength = max_ecc; + while (!(geo->ecc_strength < requirements->strength)) { + if (bbm_in_data_chunk(this, &bbm_chunk)) + goto geo_setting; + geo->ecc_strength -= 2; + } + + /* if none of them works, keep using the minimum ecc */ + /* nand required but changing ecc page layout */ + geo->ecc_strength = requirements->strength; + /* add extra ecc for meta data */ + geo->ecc0_chunk_size = 0; + geo->ecc_chunk_count = (mtd->writesize / geo->eccn_chunk_size) + 1; + geo->ecc_for_meta = 1; + /* check if oob can afford this extra ecc chunk */ + if (mtd->oobsize * 8 < geo->metadata_size * 8 + + geo->gf_len * geo->ecc_strength * geo->ecc_chunk_count) { + dev_err(this->dev, "unsupported NAND chip with new layout\n"); + return -EINVAL; + } + + /* calculate in which chunk bbm located */ + bbm_chunk = (mtd->writesize * 8 - geo->metadata_size * 8 - + geo->gf_len * geo->ecc_strength) / + (geo->gf_len * geo->ecc_strength + + geo->eccn_chunk_size * 8) + 1; + +geo_setting: + + geo->page_size = mtd->writesize + geo->metadata_size + + (geo->gf_len * geo->ecc_strength * geo->ecc_chunk_count) / 8; + geo->payload_size = mtd->writesize; + + /* + * The auxiliary buffer contains the metadata and the ECC status. The + * metadata is padded to the nearest 32-bit boundary. The ECC status + * contains one byte for every ECC chunk, and is also padded to the + * nearest 32-bit boundary. + */ + geo->auxiliary_status_offset = ALIGN(geo->metadata_size, 4); + geo->auxiliary_size = ALIGN(geo->metadata_size, 4) + + ALIGN(geo->ecc_chunk_count, 4); + + if (!this->swap_block_mark) + return 0; + + /* calculate the number of ecc chunk behind the bbm */ + i = (mtd->writesize / geo->eccn_chunk_size) - bbm_chunk + 1; + + block_mark_bit_offset = mtd->writesize * 8 - + (geo->ecc_strength * geo->gf_len * (geo->ecc_chunk_count - i) + + geo->metadata_size * 8); + + geo->block_mark_byte_offset = block_mark_bit_offset / 8; + geo->block_mark_bit_offset = block_mark_bit_offset % 8; + + dev_dbg(this->dev, "BCH Geometry :\n" + "GF length : %u\n" + "ECC Strength : %u\n" + "Page Size in Bytes : %u\n" + "Metadata Size in Bytes : %u\n" + "ECC0 Chunk Size in Bytes: %u\n" + "ECCn Chunk Size in Bytes: %u\n" + "ECC Chunk Count : %u\n" + "Payload Size in Bytes : %u\n" + "Auxiliary Size in Bytes: %u\n" + "Auxiliary Status Offset: %u\n" + "Block Mark Byte Offset : %u\n" + "Block Mark Bit Offset : %u\n" + "Block Mark in chunk : %u\n" + "Ecc for Meta data : %u\n", + geo->gf_len, + geo->ecc_strength, + geo->page_size, + geo->metadata_size, + geo->ecc0_chunk_size, + geo->eccn_chunk_size, + geo->ecc_chunk_count, + geo->payload_size, + geo->auxiliary_size, + geo->auxiliary_status_offset, + geo->block_mark_byte_offset, + geo->block_mark_bit_offset, + bbm_chunk, + geo->ecc_for_meta); + + return 0; +} + static int legacy_set_geometry(struct gpmi_nand_data *this) { struct bch_geometry *geo = &this->bch_geometry; @@ -418,13 +595,15 @@ static int legacy_set_geometry(struct gpmi_nand_data *this) geo->gf_len = 13; /* The default for chunk size. */ - geo->ecc_chunk_size = 512; - while (geo->ecc_chunk_size < mtd->oobsize) { - geo->ecc_chunk_size *= 2; /* keep C >= O */ + geo->ecc0_chunk_size = 512; + geo->eccn_chunk_size = 512; + while (geo->eccn_chunk_size < mtd->oobsize) { + geo->ecc0_chunk_size *= 2; /* keep C >= O */ + geo->eccn_chunk_size *= 2; /* keep C >= O */ geo->gf_len = 14; } - geo->ecc_chunk_count = mtd->writesize / geo->ecc_chunk_size; + geo->ecc_chunk_count = mtd->writesize / geo->eccn_chunk_size; /* We use the same ECC strength for all chunks. */ geo->ecc_strength = get_ecc_strength(this); @@ -514,24 +693,40 @@ static int legacy_set_geometry(struct gpmi_nand_data *this) static int common_nfc_set_geometry(struct gpmi_nand_data *this) { struct nand_chip *chip = &this->nand; + struct mtd_info *mtd = nand_to_mtd(&this->nand); const struct nand_ecc_props *requirements = nanddev_get_ecc_requirements(&chip->base); + bool use_minimun_ecc; + int err; - if (chip->ecc.strength > 0 && chip->ecc.size > 0) - return set_geometry_by_ecc_info(this, chip->ecc.strength, - chip->ecc.size); + use_minimun_ecc = of_property_read_bool(this->dev->of_node, + "fsl,use-minimum-ecc"); - if ((of_property_read_bool(this->dev->of_node, "fsl,use-minimum-ecc")) - || legacy_set_geometry(this)) { - if (!(requirements->strength > 0 && requirements->step_size > 0)) - return -EINVAL; + /* use legacy bch geometry settings by default*/ + if ((!use_minimun_ecc && mtd->oobsize < 1024) || + !(requirements->strength > 0 && requirements->step_size > 0)) { + dev_dbg(this->dev, "use legacy bch geometry\n"); + err = legacy_set_geometry(this); + if (!err) + return 0; + } - return set_geometry_by_ecc_info(this, - requirements->strength, - requirements->step_size); + /* for large oob nand */ + if (mtd->oobsize > 1024) { + dev_dbg(this->dev, "use large oob bch geometry\n"); + err = set_geometry_for_large_oob(this); + if (!err) + return 0; } - return 0; + /* otherwise use the minimum ecc nand chip required */ + dev_dbg(this->dev, "use minimum ecc bch geometry\n"); + err = set_geometry_by_ecc_info(this, requirements->strength, + requirements->step_size); + if (err) + dev_err(this->dev, "none of the bch geometry setting works\n"); + + return err; } /* Configures the geometry for BCH. */ @@ -843,7 +1038,7 @@ static int gpmi_raw_len_to_len(struct gpmi_nand_data *this, int raw_len) * we are passed in exec_op. Calculate the data length from it. */ if (this->bch) - return ALIGN_DOWN(raw_len, this->bch_geometry.ecc_chunk_size); + return ALIGN_DOWN(raw_len, this->bch_geometry.eccn_chunk_size); else return raw_len; } @@ -1235,7 +1430,7 @@ static int gpmi_count_bitflips(struct nand_chip *chip, void *buf, int first, /* Read ECC bytes into our internal raw_buffer */ offset = nfc_geo->metadata_size * 8; - offset += ((8 * nfc_geo->ecc_chunk_size) + eccbits) * (i + 1); + offset += ((8 * nfc_geo->eccn_chunk_size) + eccbits) * (i + 1); offset -= eccbits; bitoffset = offset % 8; eccbytes = DIV_ROUND_UP(offset + eccbits, 8); @@ -1272,16 +1467,16 @@ static int gpmi_count_bitflips(struct nand_chip *chip, void *buf, int first, if (i == 0) { /* The first block includes metadata */ flips = nand_check_erased_ecc_chunk( - buf + i * nfc_geo->ecc_chunk_size, - nfc_geo->ecc_chunk_size, + buf + i * nfc_geo->eccn_chunk_size, + nfc_geo->eccn_chunk_size, eccbuf, eccbytes, this->auxiliary_virt, nfc_geo->metadata_size, nfc_geo->ecc_strength); } else { flips = nand_check_erased_ecc_chunk( - buf + i * nfc_geo->ecc_chunk_size, - nfc_geo->ecc_chunk_size, + buf + i * nfc_geo->eccn_chunk_size, + nfc_geo->eccn_chunk_size, eccbuf, eccbytes, NULL, 0, nfc_geo->ecc_strength); @@ -1310,20 +1505,21 @@ static void gpmi_bch_layout_std(struct gpmi_nand_data *this) struct bch_geometry *geo = &this->bch_geometry; unsigned int ecc_strength = geo->ecc_strength >> 1; unsigned int gf_len = geo->gf_len; - unsigned int block_size = geo->ecc_chunk_size; + unsigned int block0_size = geo->ecc0_chunk_size; + unsigned int blockn_size = geo->eccn_chunk_size; this->bch_flashlayout0 = BF_BCH_FLASH0LAYOUT0_NBLOCKS(geo->ecc_chunk_count - 1) | BF_BCH_FLASH0LAYOUT0_META_SIZE(geo->metadata_size) | BF_BCH_FLASH0LAYOUT0_ECC0(ecc_strength, this) | BF_BCH_FLASH0LAYOUT0_GF(gf_len, this) | - BF_BCH_FLASH0LAYOUT0_DATA0_SIZE(block_size, this); + BF_BCH_FLASH0LAYOUT0_DATA0_SIZE(block0_size, this); this->bch_flashlayout1 = BF_BCH_FLASH0LAYOUT1_PAGE_SIZE(geo->page_size) | BF_BCH_FLASH0LAYOUT1_ECCN(ecc_strength, this) | BF_BCH_FLASH0LAYOUT1_GF(gf_len, this) | - BF_BCH_FLASH0LAYOUT1_DATAN_SIZE(block_size, this); + BF_BCH_FLASH0LAYOUT1_DATAN_SIZE(blockn_size, this); } static int gpmi_ecc_read_page(struct nand_chip *chip, uint8_t *buf, @@ -1406,29 +1602,49 @@ static int gpmi_ecc_read_subpage(struct nand_chip *chip, uint32_t offs, } } + /* + * if there is an ECC dedicate for meta: + * - need to add an extra ECC size when calculating col and page_size, + * if the meta size is NOT zero. + * - ecc0_chunk size need to set to the same size as other chunks, + * if the meta size is zero. + */ + meta = geo->metadata_size; if (first) { - col = meta + (size + ecc_parity_size) * first; + if (geo->ecc_for_meta) + col = meta + ecc_parity_size + + (size + ecc_parity_size) * first; + else + col = meta + (size + ecc_parity_size) * first; + meta = 0; buf = buf + first * size; } ecc_parity_size = geo->gf_len * geo->ecc_strength / 8; - n = last - first + 1; - page_size = meta + (size + ecc_parity_size) * n; + + if (geo->ecc_for_meta && meta) + page_size = meta + ecc_parity_size + + (size + ecc_parity_size) * n; + else + page_size = meta + (size + ecc_parity_size) * n; + ecc_strength = geo->ecc_strength >> 1; - this->bch_flashlayout0 = BF_BCH_FLASH0LAYOUT0_NBLOCKS(n - 1) | + this->bch_flashlayout0 = BF_BCH_FLASH0LAYOUT0_NBLOCKS( + (geo->ecc_for_meta ? n : n - 1)) | BF_BCH_FLASH0LAYOUT0_META_SIZE(meta) | BF_BCH_FLASH0LAYOUT0_ECC0(ecc_strength, this) | BF_BCH_FLASH0LAYOUT0_GF(geo->gf_len, this) | - BF_BCH_FLASH0LAYOUT0_DATA0_SIZE(geo->ecc_chunk_size, this); + BF_BCH_FLASH0LAYOUT0_DATA0_SIZE((geo->ecc_for_meta ? + 0 : geo->ecc0_chunk_size), this); this->bch_flashlayout1 = BF_BCH_FLASH0LAYOUT1_PAGE_SIZE(page_size) | BF_BCH_FLASH0LAYOUT1_ECCN(ecc_strength, this) | BF_BCH_FLASH0LAYOUT1_GF(geo->gf_len, this) | - BF_BCH_FLASH0LAYOUT1_DATAN_SIZE(geo->ecc_chunk_size, this); + BF_BCH_FLASH0LAYOUT1_DATAN_SIZE(geo->eccn_chunk_size, this); this->bch = true; @@ -1597,7 +1813,7 @@ static int gpmi_ecc_read_page_raw(struct nand_chip *chip, uint8_t *buf, struct mtd_info *mtd = nand_to_mtd(chip); struct gpmi_nand_data *this = nand_get_controller_data(chip); struct bch_geometry *nfc_geo = &this->bch_geometry; - int eccsize = nfc_geo->ecc_chunk_size; + int eccsize = nfc_geo->eccn_chunk_size; int eccbits = nfc_geo->ecc_strength * nfc_geo->gf_len; u8 *tmp_buf = this->raw_buffer; size_t src_bit_off; @@ -1682,7 +1898,7 @@ static int gpmi_ecc_write_page_raw(struct nand_chip *chip, const uint8_t *buf, struct mtd_info *mtd = nand_to_mtd(chip); struct gpmi_nand_data *this = nand_get_controller_data(chip); struct bch_geometry *nfc_geo = &this->bch_geometry; - int eccsize = nfc_geo->ecc_chunk_size; + int eccsize = nfc_geo->eccn_chunk_size; int eccbits = nfc_geo->ecc_strength * nfc_geo->gf_len; u8 *tmp_buf = this->raw_buffer; uint8_t *oob = chip->oob_poi; @@ -2056,7 +2272,7 @@ static int gpmi_init_last(struct gpmi_nand_data *this) ecc->read_oob_raw = gpmi_ecc_read_oob_raw; ecc->write_oob_raw = gpmi_ecc_write_oob_raw; ecc->engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST; - ecc->size = bch_geo->ecc_chunk_size; + ecc->size = bch_geo->eccn_chunk_size; ecc->strength = bch_geo->ecc_strength; mtd_set_ooblayout(mtd, &gpmi_ooblayout_ops); diff --git a/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.h b/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.h index 5e1c3ddae5f8..c3ff56ac62a7 100644 --- a/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.h +++ b/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.h @@ -30,9 +30,9 @@ struct resources { * @page_size: The size, in bytes, of a physical page, including * both data and OOB. * @metadata_size: The size, in bytes, of the metadata. - * @ecc_chunk_size: The size, in bytes, of a single ECC chunk. Note - * the first chunk in the page includes both data and - * metadata, so it's a bit larger than this value. + * @ecc0_chunk_size: The size, in bytes, of a first ECC chunk. + * @eccn_chunk_size: The size, in bytes, of a single ECC chunk after + * the first chunk in the page. * @ecc_chunk_count: The number of ECC chunks in the page, * @payload_size: The size, in bytes, of the payload buffer. * @auxiliary_size: The size, in bytes, of the auxiliary buffer. @@ -42,19 +42,23 @@ struct resources { * which the underlying physical block mark appears. * @block_mark_bit_offset: The bit offset into the ECC-based page view at * which the underlying physical block mark appears. + * @ecc_for_meta: The flag to indicate if there is a dedicate ecc + * for meta. */ struct bch_geometry { unsigned int gf_len; unsigned int ecc_strength; unsigned int page_size; unsigned int metadata_size; - unsigned int ecc_chunk_size; + unsigned int ecc0_chunk_size; + unsigned int eccn_chunk_size; unsigned int ecc_chunk_count; unsigned int payload_size; unsigned int auxiliary_size; unsigned int auxiliary_status_offset; unsigned int block_mark_byte_offset; unsigned int block_mark_bit_offset; + unsigned int ecc_for_meta; /* ECC for meta data */ }; /** diff --git a/drivers/mtd/nand/raw/intel-nand-controller.c b/drivers/mtd/nand/raw/intel-nand-controller.c index 7c1c80dae826..e91b879b32bd 100644 --- a/drivers/mtd/nand/raw/intel-nand-controller.c +++ b/drivers/mtd/nand/raw/intel-nand-controller.c @@ -619,9 +619,9 @@ static int ebu_nand_probe(struct platform_device *pdev) resname = devm_kasprintf(dev, GFP_KERNEL, "nand_cs%d", cs); res = platform_get_resource_byname(pdev, IORESOURCE_MEM, resname); ebu_host->cs[cs].chipaddr = devm_ioremap_resource(dev, res); - ebu_host->cs[cs].nand_pa = res->start; if (IS_ERR(ebu_host->cs[cs].chipaddr)) return PTR_ERR(ebu_host->cs[cs].chipaddr); + ebu_host->cs[cs].nand_pa = res->start; ebu_host->clk = devm_clk_get(dev, NULL); if (IS_ERR(ebu_host->clk)) diff --git a/drivers/mtd/nand/raw/mpc5121_nfc.c b/drivers/mtd/nand/raw/mpc5121_nfc.c index 5b9271b9c326..800d774aed8e 100644 --- a/drivers/mtd/nand/raw/mpc5121_nfc.c +++ b/drivers/mtd/nand/raw/mpc5121_nfc.c @@ -595,8 +595,7 @@ static void mpc5121_nfc_free(struct device *dev, struct mtd_info *mtd) struct nand_chip *chip = mtd_to_nand(mtd); struct mpc5121_nfc_prv *prv = nand_get_controller_data(chip); - if (prv->clk) - clk_disable_unprepare(prv->clk); + clk_disable_unprepare(prv->clk); if (prv->csreg) iounmap(prv->csreg); diff --git a/drivers/mtd/nand/raw/mtk_nand.c b/drivers/mtd/nand/raw/mtk_nand.c index 66f04c693c87..d540454cbbdf 100644 --- a/drivers/mtd/nand/raw/mtk_nand.c +++ b/drivers/mtd/nand/raw/mtk_nand.c @@ -17,7 +17,7 @@ #include <linux/iopoll.h> #include <linux/of.h> #include <linux/of_device.h> -#include "mtk_ecc.h" +#include <linux/mtd/nand-ecc-mtk.h> /* NAND controller register definition */ #define NFI_CNFG (0x00) diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c index 284fff62ac49..6b67b7dfe7ce 100644 --- a/drivers/mtd/nand/raw/nand_base.c +++ b/drivers/mtd/nand/raw/nand_base.c @@ -4502,11 +4502,13 @@ int nand_erase_nand(struct nand_chip *chip, struct erase_info *instr, len = instr->len; while (len) { + loff_t ofs = (loff_t)page << chip->page_shift; + /* Check if we have a bad block, we do not erase bad blocks! */ if (nand_block_checkbad(chip, ((loff_t) page) << chip->page_shift, allowbbt)) { - pr_warn("%s: attempt to erase a bad block at page 0x%08x\n", - __func__, page); + pr_warn("%s: attempt to erase a bad block at 0x%08llx\n", + __func__, (unsigned long long)ofs); ret = -EIO; goto erase_exit; } @@ -4524,8 +4526,7 @@ int nand_erase_nand(struct nand_chip *chip, struct erase_info *instr, if (ret) { pr_debug("%s: failed erase, page 0x%08x\n", __func__, page); - instr->fail_addr = - ((loff_t)page << chip->page_shift); + instr->fail_addr = ofs; goto erase_exit; } diff --git a/drivers/mtd/nand/raw/nand_ids.c b/drivers/mtd/nand/raw/nand_ids.c index 6e41902be35f..88c2440b47d8 100644 --- a/drivers/mtd/nand/raw/nand_ids.c +++ b/drivers/mtd/nand/raw/nand_ids.c @@ -29,6 +29,9 @@ struct nand_flash_dev nand_flash_ids[] = { {"TC58NVG0S3E 1G 3.3V 8-bit", { .id = {0x98, 0xd1, 0x90, 0x15, 0x76, 0x14, 0x01, 0x00} }, SZ_2K, SZ_128, SZ_128K, 0, 8, 64, NAND_ECC_INFO(1, SZ_512), }, + {"TC58NVG0S3HTA00 1G 3.3V 8-bit", + { .id = {0x98, 0xf1, 0x80, 0x15} }, + SZ_2K, SZ_128, SZ_128K, 0, 4, 128, NAND_ECC_INFO(8, SZ_512), }, {"TC58NVG2S0F 4G 3.3V 8-bit", { .id = {0x98, 0xdc, 0x90, 0x26, 0x76, 0x15, 0x01, 0x08} }, SZ_4K, SZ_512, SZ_256K, 0, 8, 224, NAND_ECC_INFO(4, SZ_512) }, @@ -58,6 +61,9 @@ struct nand_flash_dev nand_flash_ids[] = { {"TH58NVG2S3HBAI4 4G 3.3V 8-bit", { .id = {0x98, 0xdc, 0x91, 0x15, 0x76} }, SZ_2K, SZ_512, SZ_128K, 0, 5, 128, NAND_ECC_INFO(8, SZ_512) }, + {"TH58NVG3S0HBAI4 8G 3.3V 8-bit", + { .id = {0x98, 0xd3, 0x91, 0x26, 0x76} }, + SZ_4K, SZ_1K, SZ_256K, 0, 5, 256, NAND_ECC_INFO(8, SZ_512)}, LEGACY_ID_NAND("NAND 4MiB 5V 8-bit", 0x6B, 4, SZ_8K, SP_OPTIONS), LEGACY_ID_NAND("NAND 4MiB 3,3V 8-bit", 0xE3, 4, SZ_8K, SP_OPTIONS), diff --git a/drivers/mtd/nand/raw/nand_toshiba.c b/drivers/mtd/nand/raw/nand_toshiba.c index cf4f37959421..d3d34d71921f 100644 --- a/drivers/mtd/nand/raw/nand_toshiba.c +++ b/drivers/mtd/nand/raw/nand_toshiba.c @@ -287,8 +287,10 @@ static int toshiba_nand_init(struct nand_chip *chip) if (!strncmp("TC58NVG0S3E", chip->parameters.model, sizeof("TC58NVG0S3E") - 1)) tc58nvg0s3e_init(chip); - if (!strncmp("TH58NVG2S3HBAI4", chip->parameters.model, - sizeof("TH58NVG2S3HBAI4") - 1)) + if ((!strncmp("TH58NVG2S3HBAI4", chip->parameters.model, + sizeof("TH58NVG2S3HBAI4") - 1)) || + (!strncmp("TH58NVG3S0HBAI4", chip->parameters.model, + sizeof("TH58NVG3S0HBAI4") - 1))) th58nvg2s3hbai4_init(chip); return 0; diff --git a/drivers/mtd/nand/raw/omap_elm.c b/drivers/mtd/nand/raw/omap_elm.c index 893e9979c4a2..4796a48e1012 100644 --- a/drivers/mtd/nand/raw/omap_elm.c +++ b/drivers/mtd/nand/raw/omap_elm.c @@ -548,6 +548,7 @@ static SIMPLE_DEV_PM_OPS(elm_pm_ops, elm_suspend, elm_resume); #ifdef CONFIG_OF static const struct of_device_id elm_of_match[] = { { .compatible = "ti,am3352-elm" }, + { .compatible = "ti,am64-elm" }, {}, }; MODULE_DEVICE_TABLE(of, elm_of_match); diff --git a/drivers/mtd/nand/raw/qcom_nandc.c b/drivers/mtd/nand/raw/qcom_nandc.c index 1a77542c6d67..048b255faa76 100644 --- a/drivers/mtd/nand/raw/qcom_nandc.c +++ b/drivers/mtd/nand/raw/qcom_nandc.c @@ -2651,10 +2651,23 @@ static int qcom_nand_attach_chip(struct nand_chip *chip) ecc->engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST; mtd_set_ooblayout(mtd, &qcom_nand_ooblayout_ops); + /* Free the initially allocated BAM transaction for reading the ONFI params */ + if (nandc->props->is_bam) + free_bam_transaction(nandc); nandc->max_cwperpage = max_t(unsigned int, nandc->max_cwperpage, cwperpage); + /* Now allocate the BAM transaction based on updated max_cwperpage */ + if (nandc->props->is_bam) { + nandc->bam_txn = alloc_bam_transaction(nandc); + if (!nandc->bam_txn) { + dev_err(nandc->dev, + "failed to allocate bam transaction\n"); + return -ENOMEM; + } + } + /* * DATA_UD_BYTES varies based on whether the read/write command protects * spare data with ECC too. We protect spare data by default, so we set @@ -2955,17 +2968,6 @@ static int qcom_nand_host_init_and_register(struct qcom_nand_controller *nandc, if (ret) return ret; - if (nandc->props->is_bam) { - free_bam_transaction(nandc); - nandc->bam_txn = alloc_bam_transaction(nandc); - if (!nandc->bam_txn) { - dev_err(nandc->dev, - "failed to allocate bam transaction\n"); - nand_cleanup(chip); - return -ENOMEM; - } - } - ret = mtd_device_parse_register(mtd, probes, NULL, NULL, 0); if (ret) nand_cleanup(chip); diff --git a/drivers/mtd/nand/raw/renesas-nand-controller.c b/drivers/mtd/nand/raw/renesas-nand-controller.c index 6db063b230a9..1620e25a1147 100644 --- a/drivers/mtd/nand/raw/renesas-nand-controller.c +++ b/drivers/mtd/nand/raw/renesas-nand-controller.c @@ -16,6 +16,7 @@ #include <linux/mtd/rawnand.h> #include <linux/of.h> #include <linux/platform_device.h> +#include <linux/pm_runtime.h> #include <linux/slab.h> #define COMMAND_REG 0x00 @@ -216,8 +217,7 @@ struct rnandc { struct nand_controller controller; struct device *dev; void __iomem *regs; - struct clk *hclk; - struct clk *eclk; + unsigned long ext_clk_rate; unsigned long assigned_cs; struct list_head chips; struct nand_chip *selected_chip; @@ -891,7 +891,7 @@ static int rnandc_setup_interface(struct nand_chip *chip, int chipnr, { struct rnand_chip *rnand = to_rnand(chip); struct rnandc *rnandc = to_rnandc(chip->controller); - unsigned int period_ns = 1000000000 / clk_get_rate(rnandc->eclk); + unsigned int period_ns = 1000000000 / rnandc->ext_clk_rate; const struct nand_sdr_timings *sdr; unsigned int cyc, cle, ale, bef_dly, ca_to_data; @@ -1319,6 +1319,7 @@ cleanup_chips: static int rnandc_probe(struct platform_device *pdev) { struct rnandc *rnandc; + struct clk *eclk; int irq, ret; rnandc = devm_kzalloc(&pdev->dev, sizeof(*rnandc), GFP_KERNEL); @@ -1335,29 +1336,26 @@ static int rnandc_probe(struct platform_device *pdev) if (IS_ERR(rnandc->regs)) return PTR_ERR(rnandc->regs); - /* APB clock */ - rnandc->hclk = devm_clk_get(&pdev->dev, "hclk"); - if (IS_ERR(rnandc->hclk)) - return PTR_ERR(rnandc->hclk); - - /* External NAND bus clock */ - rnandc->eclk = devm_clk_get(&pdev->dev, "eclk"); - if (IS_ERR(rnandc->eclk)) - return PTR_ERR(rnandc->eclk); - - ret = clk_prepare_enable(rnandc->hclk); - if (ret) + devm_pm_runtime_enable(&pdev->dev); + ret = pm_runtime_resume_and_get(&pdev->dev); + if (ret < 0) return ret; - ret = clk_prepare_enable(rnandc->eclk); - if (ret) - goto disable_hclk; + /* The external NAND bus clock rate is needed for computing timings */ + eclk = clk_get(&pdev->dev, "eclk"); + if (IS_ERR(eclk)) { + ret = PTR_ERR(eclk); + goto dis_runtime_pm; + } + + rnandc->ext_clk_rate = clk_get_rate(eclk); + clk_put(eclk); rnandc_dis_interrupts(rnandc); irq = platform_get_irq_optional(pdev, 0); if (irq == -EPROBE_DEFER) { ret = irq; - goto disable_eclk; + goto dis_runtime_pm; } else if (irq < 0) { dev_info(&pdev->dev, "No IRQ found, fallback to polling\n"); rnandc->use_polling = true; @@ -1365,12 +1363,12 @@ static int rnandc_probe(struct platform_device *pdev) ret = devm_request_irq(&pdev->dev, irq, rnandc_irq_handler, 0, "renesas-nand-controller", rnandc); if (ret < 0) - goto disable_eclk; + goto dis_runtime_pm; } ret = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32)); if (ret) - goto disable_eclk; + goto dis_runtime_pm; rnandc_clear_fifo(rnandc); @@ -1378,14 +1376,12 @@ static int rnandc_probe(struct platform_device *pdev) ret = rnandc_chips_init(rnandc); if (ret) - goto disable_eclk; + goto dis_runtime_pm; return 0; -disable_eclk: - clk_disable_unprepare(rnandc->eclk); -disable_hclk: - clk_disable_unprepare(rnandc->hclk); +dis_runtime_pm: + pm_runtime_put(&pdev->dev); return ret; } @@ -1396,8 +1392,7 @@ static int rnandc_remove(struct platform_device *pdev) rnandc_chips_cleanup(rnandc); - clk_disable_unprepare(rnandc->eclk); - clk_disable_unprepare(rnandc->hclk); + pm_runtime_put(&pdev->dev); return 0; } diff --git a/drivers/mtd/nand/raw/rockchip-nand-controller.c b/drivers/mtd/nand/raw/rockchip-nand-controller.c index cbaa4f1c83da..f133985cc053 100644 --- a/drivers/mtd/nand/raw/rockchip-nand-controller.c +++ b/drivers/mtd/nand/raw/rockchip-nand-controller.c @@ -911,8 +911,7 @@ static int rk_nfc_enable_clks(struct device *dev, struct rk_nfc *nfc) ret = clk_prepare_enable(nfc->ahb_clk); if (ret) { dev_err(dev, "failed to enable ahb clk\n"); - if (!IS_ERR(nfc->nfc_clk)) - clk_disable_unprepare(nfc->nfc_clk); + clk_disable_unprepare(nfc->nfc_clk); return ret; } @@ -921,8 +920,7 @@ static int rk_nfc_enable_clks(struct device *dev, struct rk_nfc *nfc) static void rk_nfc_disable_clks(struct rk_nfc *nfc) { - if (!IS_ERR(nfc->nfc_clk)) - clk_disable_unprepare(nfc->nfc_clk); + clk_disable_unprepare(nfc->nfc_clk); clk_disable_unprepare(nfc->ahb_clk); } diff --git a/drivers/mtd/nand/raw/sh_flctl.c b/drivers/mtd/nand/raw/sh_flctl.c index b85b9c6fcc42..a278829469d6 100644 --- a/drivers/mtd/nand/raw/sh_flctl.c +++ b/drivers/mtd/nand/raw/sh_flctl.c @@ -384,7 +384,8 @@ static int flctl_dma_fifo0_transfer(struct sh_flctl *flctl, unsigned long *buf, dma_addr_t dma_addr; dma_cookie_t cookie; uint32_t reg; - int ret; + int ret = 0; + unsigned long time_left; if (dir == DMA_FROM_DEVICE) { chan = flctl->chan_fifo0_rx; @@ -425,13 +426,14 @@ static int flctl_dma_fifo0_transfer(struct sh_flctl *flctl, unsigned long *buf, goto out; } - ret = + time_left = wait_for_completion_timeout(&flctl->dma_complete, msecs_to_jiffies(3000)); - if (ret <= 0) { + if (time_left == 0) { dmaengine_terminate_all(chan); dev_err(&flctl->pdev->dev, "wait_for_completion_timeout\n"); + ret = -ETIMEDOUT; } out: @@ -441,7 +443,7 @@ out: dma_unmap_single(chan->device->dev, dma_addr, len, dir); - /* ret > 0 is success */ + /* ret == 0 is success */ return ret; } @@ -465,7 +467,7 @@ static void read_fiforeg(struct sh_flctl *flctl, int rlen, int offset) /* initiate DMA transfer */ if (flctl->chan_fifo0_rx && rlen >= 32 && - flctl_dma_fifo0_transfer(flctl, buf, rlen, DMA_FROM_DEVICE) > 0) + !flctl_dma_fifo0_transfer(flctl, buf, rlen, DMA_FROM_DEVICE)) goto convert; /* DMA success */ /* do polling transfer */ @@ -524,7 +526,7 @@ static void write_ec_fiforeg(struct sh_flctl *flctl, int rlen, /* initiate DMA transfer */ if (flctl->chan_fifo0_tx && rlen >= 32 && - flctl_dma_fifo0_transfer(flctl, buf, rlen, DMA_TO_DEVICE) > 0) + !flctl_dma_fifo0_transfer(flctl, buf, rlen, DMA_TO_DEVICE)) return; /* DMA success */ /* do polling transfer */ diff --git a/drivers/mtd/nand/raw/tmio_nand.c b/drivers/mtd/nand/raw/tmio_nand.c index de8e919d0ebe..8f1a42bf199c 100644 --- a/drivers/mtd/nand/raw/tmio_nand.c +++ b/drivers/mtd/nand/raw/tmio_nand.c @@ -390,6 +390,9 @@ static int tmio_probe(struct platform_device *dev) if (data == NULL) dev_warn(&dev->dev, "NULL platform data!\n"); + if (!ccr || !fcr) + return -EINVAL; + tmio = devm_kzalloc(&dev->dev, sizeof(*tmio), GFP_KERNEL); if (!tmio) return -ENOMEM; diff --git a/drivers/mtd/nand/spi/Makefile b/drivers/mtd/nand/spi/Makefile index 9662b9c1d5a9..80dabe6ff0f3 100644 --- a/drivers/mtd/nand/spi/Makefile +++ b/drivers/mtd/nand/spi/Makefile @@ -1,3 +1,3 @@ # SPDX-License-Identifier: GPL-2.0 -spinand-objs := core.o gigadevice.o macronix.o micron.o paragon.o toshiba.o winbond.o +spinand-objs := core.o gigadevice.o macronix.o micron.o paragon.o toshiba.o winbond.o xtx.o obj-$(CONFIG_MTD_SPI_NAND) += spinand.o diff --git a/drivers/mtd/nand/spi/core.c b/drivers/mtd/nand/spi/core.c index ff8336870bc0..d5b685d1605e 100644 --- a/drivers/mtd/nand/spi/core.c +++ b/drivers/mtd/nand/spi/core.c @@ -933,6 +933,7 @@ static const struct spinand_manufacturer *spinand_manufacturers[] = { ¶gon_spinand_manufacturer, &toshiba_spinand_manufacturer, &winbond_spinand_manufacturer, + &xtx_spinand_manufacturer, }; static int spinand_manufacturer_match(struct spinand_device *spinand, diff --git a/drivers/mtd/nand/spi/gigadevice.c b/drivers/mtd/nand/spi/gigadevice.c index 1dd1c5898093..6b043e24855f 100644 --- a/drivers/mtd/nand/spi/gigadevice.c +++ b/drivers/mtd/nand/spi/gigadevice.c @@ -39,6 +39,22 @@ static SPINAND_OP_VARIANTS(read_cache_variants_f, SPINAND_PAGE_READ_FROM_CACHE_OP_3A(true, 0, 1, NULL, 0), SPINAND_PAGE_READ_FROM_CACHE_OP_3A(false, 0, 0, NULL, 0)); +static SPINAND_OP_VARIANTS(read_cache_variants_1gq5, + SPINAND_PAGE_READ_FROM_CACHE_QUADIO_OP(0, 2, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_X4_OP(0, 1, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_DUALIO_OP(0, 1, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_X2_OP(0, 1, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_OP(true, 0, 1, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_OP(false, 0, 1, NULL, 0)); + +static SPINAND_OP_VARIANTS(read_cache_variants_2gq5, + SPINAND_PAGE_READ_FROM_CACHE_QUADIO_OP(0, 4, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_X4_OP(0, 1, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_DUALIO_OP(0, 2, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_X2_OP(0, 1, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_OP(true, 0, 1, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_OP(false, 0, 1, NULL, 0)); + static SPINAND_OP_VARIANTS(write_cache_variants, SPINAND_PROG_LOAD_X4(true, 0, NULL, 0), SPINAND_PROG_LOAD(true, 0, NULL, 0)); @@ -325,6 +341,36 @@ static const struct spinand_info gigadevice_spinand_table[] = { SPINAND_HAS_QE_BIT, SPINAND_ECCINFO(&gd5fxgqx_variant2_ooblayout, gd5fxgq4uexxg_ecc_get_status)), + SPINAND_INFO("GD5F1GQ4RExxG", + SPINAND_ID(SPINAND_READID_METHOD_OPCODE_ADDR, 0xc1), + NAND_MEMORG(1, 2048, 128, 64, 1024, 20, 1, 1, 1), + NAND_ECCREQ(8, 512), + SPINAND_INFO_OP_VARIANTS(&read_cache_variants, + &write_cache_variants, + &update_cache_variants), + SPINAND_HAS_QE_BIT, + SPINAND_ECCINFO(&gd5fxgqx_variant2_ooblayout, + gd5fxgq4uexxg_ecc_get_status)), + SPINAND_INFO("GD5F2GQ4UExxG", + SPINAND_ID(SPINAND_READID_METHOD_OPCODE_ADDR, 0xd2), + NAND_MEMORG(1, 2048, 128, 64, 2048, 40, 1, 1, 1), + NAND_ECCREQ(8, 512), + SPINAND_INFO_OP_VARIANTS(&read_cache_variants, + &write_cache_variants, + &update_cache_variants), + SPINAND_HAS_QE_BIT, + SPINAND_ECCINFO(&gd5fxgqx_variant2_ooblayout, + gd5fxgq4uexxg_ecc_get_status)), + SPINAND_INFO("GD5F2GQ4RExxG", + SPINAND_ID(SPINAND_READID_METHOD_OPCODE_ADDR, 0xc2), + NAND_MEMORG(1, 2048, 128, 64, 2048, 40, 1, 1, 1), + NAND_ECCREQ(8, 512), + SPINAND_INFO_OP_VARIANTS(&read_cache_variants, + &write_cache_variants, + &update_cache_variants), + SPINAND_HAS_QE_BIT, + SPINAND_ECCINFO(&gd5fxgqx_variant2_ooblayout, + gd5fxgq4uexxg_ecc_get_status)), SPINAND_INFO("GD5F1GQ4UFxxG", SPINAND_ID(SPINAND_READID_METHOD_OPCODE, 0xb1, 0x48), NAND_MEMORG(1, 2048, 128, 64, 1024, 20, 1, 1, 1), @@ -339,12 +385,122 @@ static const struct spinand_info gigadevice_spinand_table[] = { SPINAND_ID(SPINAND_READID_METHOD_OPCODE_DUMMY, 0x51), NAND_MEMORG(1, 2048, 128, 64, 1024, 20, 1, 1, 1), NAND_ECCREQ(4, 512), - SPINAND_INFO_OP_VARIANTS(&read_cache_variants, + SPINAND_INFO_OP_VARIANTS(&read_cache_variants_1gq5, + &write_cache_variants, + &update_cache_variants), + SPINAND_HAS_QE_BIT, + SPINAND_ECCINFO(&gd5fxgqx_variant2_ooblayout, + gd5fxgq5xexxg_ecc_get_status)), + SPINAND_INFO("GD5F1GQ5RExxG", + SPINAND_ID(SPINAND_READID_METHOD_OPCODE_DUMMY, 0x41), + NAND_MEMORG(1, 2048, 128, 64, 1024, 20, 1, 1, 1), + NAND_ECCREQ(4, 512), + SPINAND_INFO_OP_VARIANTS(&read_cache_variants_1gq5, &write_cache_variants, &update_cache_variants), SPINAND_HAS_QE_BIT, SPINAND_ECCINFO(&gd5fxgqx_variant2_ooblayout, gd5fxgq5xexxg_ecc_get_status)), + SPINAND_INFO("GD5F2GQ5UExxG", + SPINAND_ID(SPINAND_READID_METHOD_OPCODE_DUMMY, 0x52), + NAND_MEMORG(1, 2048, 128, 64, 2048, 40, 1, 1, 1), + NAND_ECCREQ(4, 512), + SPINAND_INFO_OP_VARIANTS(&read_cache_variants_2gq5, + &write_cache_variants, + &update_cache_variants), + SPINAND_HAS_QE_BIT, + SPINAND_ECCINFO(&gd5fxgqx_variant2_ooblayout, + gd5fxgq5xexxg_ecc_get_status)), + SPINAND_INFO("GD5F2GQ5RExxG", + SPINAND_ID(SPINAND_READID_METHOD_OPCODE_DUMMY, 0x42), + NAND_MEMORG(1, 2048, 128, 64, 2048, 40, 1, 1, 1), + NAND_ECCREQ(4, 512), + SPINAND_INFO_OP_VARIANTS(&read_cache_variants_2gq5, + &write_cache_variants, + &update_cache_variants), + SPINAND_HAS_QE_BIT, + SPINAND_ECCINFO(&gd5fxgqx_variant2_ooblayout, + gd5fxgq5xexxg_ecc_get_status)), + SPINAND_INFO("GD5F4GQ6UExxG", + SPINAND_ID(SPINAND_READID_METHOD_OPCODE_DUMMY, 0x55), + NAND_MEMORG(1, 2048, 128, 64, 2048, 40, 1, 2, 1), + NAND_ECCREQ(4, 512), + SPINAND_INFO_OP_VARIANTS(&read_cache_variants_2gq5, + &write_cache_variants, + &update_cache_variants), + SPINAND_HAS_QE_BIT, + SPINAND_ECCINFO(&gd5fxgqx_variant2_ooblayout, + gd5fxgq5xexxg_ecc_get_status)), + SPINAND_INFO("GD5F4GQ6RExxG", + SPINAND_ID(SPINAND_READID_METHOD_OPCODE_DUMMY, 0x45), + NAND_MEMORG(1, 2048, 128, 64, 2048, 40, 1, 2, 1), + NAND_ECCREQ(4, 512), + SPINAND_INFO_OP_VARIANTS(&read_cache_variants_2gq5, + &write_cache_variants, + &update_cache_variants), + SPINAND_HAS_QE_BIT, + SPINAND_ECCINFO(&gd5fxgqx_variant2_ooblayout, + gd5fxgq5xexxg_ecc_get_status)), + SPINAND_INFO("GD5F1GM7UExxG", + SPINAND_ID(SPINAND_READID_METHOD_OPCODE_DUMMY, 0x91), + NAND_MEMORG(1, 2048, 128, 64, 1024, 20, 1, 1, 1), + NAND_ECCREQ(8, 512), + SPINAND_INFO_OP_VARIANTS(&read_cache_variants_1gq5, + &write_cache_variants, + &update_cache_variants), + SPINAND_HAS_QE_BIT, + SPINAND_ECCINFO(&gd5fxgqx_variant2_ooblayout, + gd5fxgq4uexxg_ecc_get_status)), + SPINAND_INFO("GD5F1GM7RExxG", + SPINAND_ID(SPINAND_READID_METHOD_OPCODE_DUMMY, 0x81), + NAND_MEMORG(1, 2048, 128, 64, 1024, 20, 1, 1, 1), + NAND_ECCREQ(8, 512), + SPINAND_INFO_OP_VARIANTS(&read_cache_variants_1gq5, + &write_cache_variants, + &update_cache_variants), + SPINAND_HAS_QE_BIT, + SPINAND_ECCINFO(&gd5fxgqx_variant2_ooblayout, + gd5fxgq4uexxg_ecc_get_status)), + SPINAND_INFO("GD5F2GM7UExxG", + SPINAND_ID(SPINAND_READID_METHOD_OPCODE_DUMMY, 0x92), + NAND_MEMORG(1, 2048, 128, 64, 2048, 40, 1, 1, 1), + NAND_ECCREQ(8, 512), + SPINAND_INFO_OP_VARIANTS(&read_cache_variants_1gq5, + &write_cache_variants, + &update_cache_variants), + SPINAND_HAS_QE_BIT, + SPINAND_ECCINFO(&gd5fxgqx_variant2_ooblayout, + gd5fxgq4uexxg_ecc_get_status)), + SPINAND_INFO("GD5F2GM7RExxG", + SPINAND_ID(SPINAND_READID_METHOD_OPCODE_DUMMY, 0x82), + NAND_MEMORG(1, 2048, 128, 64, 2048, 40, 1, 1, 1), + NAND_ECCREQ(8, 512), + SPINAND_INFO_OP_VARIANTS(&read_cache_variants_1gq5, + &write_cache_variants, + &update_cache_variants), + SPINAND_HAS_QE_BIT, + SPINAND_ECCINFO(&gd5fxgqx_variant2_ooblayout, + gd5fxgq4uexxg_ecc_get_status)), + SPINAND_INFO("GD5F4GM8UExxG", + SPINAND_ID(SPINAND_READID_METHOD_OPCODE_DUMMY, 0x95), + NAND_MEMORG(1, 2048, 128, 64, 4096, 80, 1, 1, 1), + NAND_ECCREQ(8, 512), + SPINAND_INFO_OP_VARIANTS(&read_cache_variants_1gq5, + &write_cache_variants, + &update_cache_variants), + SPINAND_HAS_QE_BIT, + SPINAND_ECCINFO(&gd5fxgqx_variant2_ooblayout, + gd5fxgq4uexxg_ecc_get_status)), + SPINAND_INFO("GD5F4GM8RExxG", + SPINAND_ID(SPINAND_READID_METHOD_OPCODE_DUMMY, 0x85), + NAND_MEMORG(1, 2048, 128, 64, 4096, 80, 1, 1, 1), + NAND_ECCREQ(8, 512), + SPINAND_INFO_OP_VARIANTS(&read_cache_variants_1gq5, + &write_cache_variants, + &update_cache_variants), + SPINAND_HAS_QE_BIT, + SPINAND_ECCINFO(&gd5fxgqx_variant2_ooblayout, + gd5fxgq4uexxg_ecc_get_status)), }; static const struct spinand_manufacturer_ops gigadevice_spinand_manuf_ops = { diff --git a/drivers/mtd/nand/spi/xtx.c b/drivers/mtd/nand/spi/xtx.c new file mode 100644 index 000000000000..3911520f718c --- /dev/null +++ b/drivers/mtd/nand/spi/xtx.c @@ -0,0 +1,129 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Author: + * Felix Matouschek <felix@matouschek.org> + */ + +#include <linux/device.h> +#include <linux/kernel.h> +#include <linux/mtd/spinand.h> + +#define SPINAND_MFR_XTX 0x0B + +#define XT26G0XA_STATUS_ECC_MASK GENMASK(5, 2) +#define XT26G0XA_STATUS_ECC_NO_DETECTED (0 << 2) +#define XT26G0XA_STATUS_ECC_8_CORRECTED (3 << 4) +#define XT26G0XA_STATUS_ECC_UNCOR_ERROR (2 << 4) + +static SPINAND_OP_VARIANTS(read_cache_variants, + SPINAND_PAGE_READ_FROM_CACHE_QUADIO_OP(0, 1, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_X4_OP(0, 1, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_DUALIO_OP(0, 1, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_X2_OP(0, 1, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_OP(true, 0, 1, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_OP(false, 0, 1, NULL, 0)); + +static SPINAND_OP_VARIANTS(write_cache_variants, + SPINAND_PROG_LOAD_X4(true, 0, NULL, 0), + SPINAND_PROG_LOAD(true, 0, NULL, 0)); + +static SPINAND_OP_VARIANTS(update_cache_variants, + SPINAND_PROG_LOAD_X4(false, 0, NULL, 0), + SPINAND_PROG_LOAD(false, 0, NULL, 0)); + +static int xt26g0xa_ooblayout_ecc(struct mtd_info *mtd, int section, + struct mtd_oob_region *region) +{ + if (section) + return -ERANGE; + + region->offset = 48; + region->length = 16; + + return 0; +} + +static int xt26g0xa_ooblayout_free(struct mtd_info *mtd, int section, + struct mtd_oob_region *region) +{ + if (section) + return -ERANGE; + + region->offset = 1; + region->length = 47; + + return 0; +} + +static const struct mtd_ooblayout_ops xt26g0xa_ooblayout = { + .ecc = xt26g0xa_ooblayout_ecc, + .free = xt26g0xa_ooblayout_free, +}; + +static int xt26g0xa_ecc_get_status(struct spinand_device *spinand, + u8 status) +{ + status = status & XT26G0XA_STATUS_ECC_MASK; + + switch (status) { + case XT26G0XA_STATUS_ECC_NO_DETECTED: + return 0; + case XT26G0XA_STATUS_ECC_8_CORRECTED: + return 8; + case XT26G0XA_STATUS_ECC_UNCOR_ERROR: + return -EBADMSG; + default: + break; + } + + /* At this point values greater than (2 << 4) are invalid */ + if (status > XT26G0XA_STATUS_ECC_UNCOR_ERROR) + return -EINVAL; + + /* (1 << 2) through (7 << 2) are 1-7 corrected errors */ + return status >> 2; +} + +static const struct spinand_info xtx_spinand_table[] = { + SPINAND_INFO("XT26G01A", + SPINAND_ID(SPINAND_READID_METHOD_OPCODE_ADDR, 0xE1), + NAND_MEMORG(1, 2048, 64, 64, 1024, 20, 1, 1, 1), + NAND_ECCREQ(8, 512), + SPINAND_INFO_OP_VARIANTS(&read_cache_variants, + &write_cache_variants, + &update_cache_variants), + SPINAND_HAS_QE_BIT, + SPINAND_ECCINFO(&xt26g0xa_ooblayout, + xt26g0xa_ecc_get_status)), + SPINAND_INFO("XT26G02A", + SPINAND_ID(SPINAND_READID_METHOD_OPCODE_ADDR, 0xE2), + NAND_MEMORG(1, 2048, 64, 64, 2048, 40, 1, 1, 1), + NAND_ECCREQ(8, 512), + SPINAND_INFO_OP_VARIANTS(&read_cache_variants, + &write_cache_variants, + &update_cache_variants), + SPINAND_HAS_QE_BIT, + SPINAND_ECCINFO(&xt26g0xa_ooblayout, + xt26g0xa_ecc_get_status)), + SPINAND_INFO("XT26G04A", + SPINAND_ID(SPINAND_READID_METHOD_OPCODE_ADDR, 0xE3), + NAND_MEMORG(1, 2048, 64, 128, 2048, 40, 1, 1, 1), + NAND_ECCREQ(8, 512), + SPINAND_INFO_OP_VARIANTS(&read_cache_variants, + &write_cache_variants, + &update_cache_variants), + SPINAND_HAS_QE_BIT, + SPINAND_ECCINFO(&xt26g0xa_ooblayout, + xt26g0xa_ecc_get_status)), +}; + +static const struct spinand_manufacturer_ops xtx_spinand_manuf_ops = { +}; + +const struct spinand_manufacturer xtx_spinand_manufacturer = { + .id = SPINAND_MFR_XTX, + .name = "XTX", + .chips = xtx_spinand_table, + .nchips = ARRAY_SIZE(xtx_spinand_table), + .ops = &xtx_spinand_manuf_ops, +}; diff --git a/drivers/mtd/parsers/bcm47xxpart.c b/drivers/mtd/parsers/bcm47xxpart.c index 6012a10f10c8..50fcf4c2174b 100644 --- a/drivers/mtd/parsers/bcm47xxpart.c +++ b/drivers/mtd/parsers/bcm47xxpart.c @@ -237,7 +237,7 @@ static int bcm47xxpart_parse(struct mtd_info *master, (uint8_t *)buf); if (err && !mtd_is_bitflip(err)) { pr_err("mtd_read error while parsing (offset: 0x%X): %d\n", - offset, err); + offset + 0x8000, err); continue; } diff --git a/drivers/mtd/spi-nor/Makefile b/drivers/mtd/spi-nor/Makefile index 6b904e439372..e347b435a038 100644 --- a/drivers/mtd/spi-nor/Makefile +++ b/drivers/mtd/spi-nor/Makefile @@ -17,6 +17,7 @@ spi-nor-objs += sst.o spi-nor-objs += winbond.o spi-nor-objs += xilinx.o spi-nor-objs += xmc.o +spi-nor-$(CONFIG_DEBUG_FS) += debugfs.o obj-$(CONFIG_MTD_SPI_NOR) += spi-nor.o obj-$(CONFIG_MTD_SPI_NOR) += controllers/ diff --git a/drivers/mtd/spi-nor/controllers/Kconfig b/drivers/mtd/spi-nor/controllers/Kconfig index 50f4f3484d42..ca45dcd3ffe8 100644 --- a/drivers/mtd/spi-nor/controllers/Kconfig +++ b/drivers/mtd/spi-nor/controllers/Kconfig @@ -1,14 +1,4 @@ # SPDX-License-Identifier: GPL-2.0-only -config SPI_ASPEED_SMC - tristate "Aspeed flash controllers in SPI mode" - depends on ARCH_ASPEED || COMPILE_TEST - depends on HAS_IOMEM && OF - help - This enables support for the Firmware Memory controller (FMC) - in the Aspeed AST2500/AST2400 SoCs when attached to SPI NOR chips, - and support for the SPI flash memory controller (SPI) for - the host firmware. The implementation only supports SPI NOR. - config SPI_HISI_SFC tristate "Hisilicon FMC SPI NOR Flash Controller(SFC)" depends on ARCH_HISI || COMPILE_TEST diff --git a/drivers/mtd/spi-nor/controllers/Makefile b/drivers/mtd/spi-nor/controllers/Makefile index 6e2a1dc68466..0b8e1d530913 100644 --- a/drivers/mtd/spi-nor/controllers/Makefile +++ b/drivers/mtd/spi-nor/controllers/Makefile @@ -1,4 +1,3 @@ # SPDX-License-Identifier: GPL-2.0 -obj-$(CONFIG_SPI_ASPEED_SMC) += aspeed-smc.o obj-$(CONFIG_SPI_HISI_SFC) += hisi-sfc.o obj-$(CONFIG_SPI_NXP_SPIFI) += nxp-spifi.o diff --git a/drivers/mtd/spi-nor/controllers/aspeed-smc.c b/drivers/mtd/spi-nor/controllers/aspeed-smc.c deleted file mode 100644 index acfe010f9dd7..000000000000 --- a/drivers/mtd/spi-nor/controllers/aspeed-smc.c +++ /dev/null @@ -1,921 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * ASPEED Static Memory Controller driver - * - * Copyright (c) 2015-2016, IBM Corporation. - */ - -#include <linux/bug.h> -#include <linux/device.h> -#include <linux/io.h> -#include <linux/module.h> -#include <linux/mutex.h> -#include <linux/mtd/mtd.h> -#include <linux/mtd/partitions.h> -#include <linux/mtd/spi-nor.h> -#include <linux/of.h> -#include <linux/of_platform.h> -#include <linux/sizes.h> -#include <linux/sysfs.h> - -#define DEVICE_NAME "aspeed-smc" - -/* - * The driver only support SPI flash - */ -enum aspeed_smc_flash_type { - smc_type_nor = 0, - smc_type_nand = 1, - smc_type_spi = 2, -}; - -struct aspeed_smc_chip; - -struct aspeed_smc_info { - u32 maxsize; /* maximum size of chip window */ - u8 nce; /* number of chip enables */ - bool hastype; /* flash type field exists in config reg */ - u8 we0; /* shift for write enable bit for CE0 */ - u8 ctl0; /* offset in regs of ctl for CE0 */ - - void (*set_4b)(struct aspeed_smc_chip *chip); -}; - -static void aspeed_smc_chip_set_4b_spi_2400(struct aspeed_smc_chip *chip); -static void aspeed_smc_chip_set_4b(struct aspeed_smc_chip *chip); - -static const struct aspeed_smc_info fmc_2400_info = { - .maxsize = 64 * 1024 * 1024, - .nce = 5, - .hastype = true, - .we0 = 16, - .ctl0 = 0x10, - .set_4b = aspeed_smc_chip_set_4b, -}; - -static const struct aspeed_smc_info spi_2400_info = { - .maxsize = 64 * 1024 * 1024, - .nce = 1, - .hastype = false, - .we0 = 0, - .ctl0 = 0x04, - .set_4b = aspeed_smc_chip_set_4b_spi_2400, -}; - -static const struct aspeed_smc_info fmc_2500_info = { - .maxsize = 256 * 1024 * 1024, - .nce = 3, - .hastype = true, - .we0 = 16, - .ctl0 = 0x10, - .set_4b = aspeed_smc_chip_set_4b, -}; - -static const struct aspeed_smc_info spi_2500_info = { - .maxsize = 128 * 1024 * 1024, - .nce = 2, - .hastype = false, - .we0 = 16, - .ctl0 = 0x10, - .set_4b = aspeed_smc_chip_set_4b, -}; - -enum aspeed_smc_ctl_reg_value { - smc_base, /* base value without mode for other commands */ - smc_read, /* command reg for (maybe fast) reads */ - smc_write, /* command reg for writes */ - smc_max, -}; - -struct aspeed_smc_controller; - -struct aspeed_smc_chip { - int cs; - struct aspeed_smc_controller *controller; - void __iomem *ctl; /* control register */ - void __iomem *ahb_base; /* base of chip window */ - u32 ahb_window_size; /* chip mapping window size */ - u32 ctl_val[smc_max]; /* control settings */ - enum aspeed_smc_flash_type type; /* what type of flash */ - struct spi_nor nor; -}; - -struct aspeed_smc_controller { - struct device *dev; - - struct mutex mutex; /* controller access mutex */ - const struct aspeed_smc_info *info; /* type info of controller */ - void __iomem *regs; /* controller registers */ - void __iomem *ahb_base; /* per-chip windows resource */ - u32 ahb_window_size; /* full mapping window size */ - - struct aspeed_smc_chip *chips[]; /* pointers to attached chips */ -}; - -/* - * SPI Flash Configuration Register (AST2500 SPI) - * or - * Type setting Register (AST2500 FMC). - * CE0 and CE1 can only be of type SPI. CE2 can be of type NOR but the - * driver does not support it. - */ -#define CONFIG_REG 0x0 -#define CONFIG_DISABLE_LEGACY BIT(31) /* 1 */ - -#define CONFIG_CE2_WRITE BIT(18) -#define CONFIG_CE1_WRITE BIT(17) -#define CONFIG_CE0_WRITE BIT(16) - -#define CONFIG_CE2_TYPE BIT(4) /* AST2500 FMC only */ -#define CONFIG_CE1_TYPE BIT(2) /* AST2500 FMC only */ -#define CONFIG_CE0_TYPE BIT(0) /* AST2500 FMC only */ - -/* - * CE Control Register - */ -#define CE_CONTROL_REG 0x4 - -/* - * CEx Control Register - */ -#define CONTROL_AAF_MODE BIT(31) -#define CONTROL_IO_MODE_MASK GENMASK(30, 28) -#define CONTROL_IO_DUAL_DATA BIT(29) -#define CONTROL_IO_DUAL_ADDR_DATA (BIT(29) | BIT(28)) -#define CONTROL_IO_QUAD_DATA BIT(30) -#define CONTROL_IO_QUAD_ADDR_DATA (BIT(30) | BIT(28)) -#define CONTROL_CE_INACTIVE_SHIFT 24 -#define CONTROL_CE_INACTIVE_MASK GENMASK(27, \ - CONTROL_CE_INACTIVE_SHIFT) -/* 0 = 16T ... 15 = 1T T=HCLK */ -#define CONTROL_COMMAND_SHIFT 16 -#define CONTROL_DUMMY_COMMAND_OUT BIT(15) -#define CONTROL_IO_DUMMY_HI BIT(14) -#define CONTROL_IO_DUMMY_HI_SHIFT 14 -#define CONTROL_CLK_DIV4 BIT(13) /* others */ -#define CONTROL_IO_ADDRESS_4B BIT(13) /* AST2400 SPI */ -#define CONTROL_RW_MERGE BIT(12) -#define CONTROL_IO_DUMMY_LO_SHIFT 6 -#define CONTROL_IO_DUMMY_LO GENMASK(7, \ - CONTROL_IO_DUMMY_LO_SHIFT) -#define CONTROL_IO_DUMMY_MASK (CONTROL_IO_DUMMY_HI | \ - CONTROL_IO_DUMMY_LO) -#define CONTROL_IO_DUMMY_SET(dummy) \ - (((((dummy) >> 2) & 0x1) << CONTROL_IO_DUMMY_HI_SHIFT) | \ - (((dummy) & 0x3) << CONTROL_IO_DUMMY_LO_SHIFT)) - -#define CONTROL_CLOCK_FREQ_SEL_SHIFT 8 -#define CONTROL_CLOCK_FREQ_SEL_MASK GENMASK(11, \ - CONTROL_CLOCK_FREQ_SEL_SHIFT) -#define CONTROL_LSB_FIRST BIT(5) -#define CONTROL_CLOCK_MODE_3 BIT(4) -#define CONTROL_IN_DUAL_DATA BIT(3) -#define CONTROL_CE_STOP_ACTIVE_CONTROL BIT(2) -#define CONTROL_COMMAND_MODE_MASK GENMASK(1, 0) -#define CONTROL_COMMAND_MODE_NORMAL 0 -#define CONTROL_COMMAND_MODE_FREAD 1 -#define CONTROL_COMMAND_MODE_WRITE 2 -#define CONTROL_COMMAND_MODE_USER 3 - -#define CONTROL_KEEP_MASK \ - (CONTROL_AAF_MODE | CONTROL_CE_INACTIVE_MASK | CONTROL_CLK_DIV4 | \ - CONTROL_CLOCK_FREQ_SEL_MASK | CONTROL_LSB_FIRST | CONTROL_CLOCK_MODE_3) - -/* - * The Segment Register uses a 8MB unit to encode the start address - * and the end address of the mapping window of a flash SPI slave : - * - * | byte 1 | byte 2 | byte 3 | byte 4 | - * +--------+--------+--------+--------+ - * | end | start | 0 | 0 | - */ -#define SEGMENT_ADDR_REG0 0x30 -#define SEGMENT_ADDR_START(_r) ((((_r) >> 16) & 0xFF) << 23) -#define SEGMENT_ADDR_END(_r) ((((_r) >> 24) & 0xFF) << 23) -#define SEGMENT_ADDR_VALUE(start, end) \ - (((((start) >> 23) & 0xFF) << 16) | ((((end) >> 23) & 0xFF) << 24)) -#define SEGMENT_ADDR_REG(controller, cs) \ - ((controller)->regs + SEGMENT_ADDR_REG0 + (cs) * 4) - -/* - * In user mode all data bytes read or written to the chip decode address - * range are transferred to or from the SPI bus. The range is treated as a - * fifo of arbitratry 1, 2, or 4 byte width but each write has to be aligned - * to its size. The address within the multiple 8kB range is ignored when - * sending bytes to the SPI bus. - * - * On the arm architecture, as of Linux version 4.3, memcpy_fromio and - * memcpy_toio on little endian targets use the optimized memcpy routines - * that were designed for well behavied memory storage. These routines - * have a stutter if the source and destination are not both word aligned, - * once with a duplicate access to the source after aligning to the - * destination to a word boundary, and again with a duplicate access to - * the source when the final byte count is not word aligned. - * - * When writing or reading the fifo this stutter discards data or sends - * too much data to the fifo and can not be used by this driver. - * - * While the low level io string routines that implement the insl family do - * the desired accesses and memory increments, the cross architecture io - * macros make them essentially impossible to use on a memory mapped address - * instead of a a token from the call to iomap of an io port. - * - * These fifo routines use readl and friends to a constant io port and update - * the memory buffer pointer and count via explicit code. The final updates - * to len are optimistically suppressed. - */ -static int aspeed_smc_read_from_ahb(void *buf, void __iomem *src, size_t len) -{ - size_t offset = 0; - - if (IS_ALIGNED((uintptr_t)src, sizeof(uintptr_t)) && - IS_ALIGNED((uintptr_t)buf, sizeof(uintptr_t))) { - ioread32_rep(src, buf, len >> 2); - offset = len & ~0x3; - len -= offset; - } - ioread8_rep(src, (u8 *)buf + offset, len); - return 0; -} - -static int aspeed_smc_write_to_ahb(void __iomem *dst, const void *buf, - size_t len) -{ - size_t offset = 0; - - if (IS_ALIGNED((uintptr_t)dst, sizeof(uintptr_t)) && - IS_ALIGNED((uintptr_t)buf, sizeof(uintptr_t))) { - iowrite32_rep(dst, buf, len >> 2); - offset = len & ~0x3; - len -= offset; - } - iowrite8_rep(dst, (const u8 *)buf + offset, len); - return 0; -} - -static inline u32 aspeed_smc_chip_write_bit(struct aspeed_smc_chip *chip) -{ - return BIT(chip->controller->info->we0 + chip->cs); -} - -static void aspeed_smc_chip_check_config(struct aspeed_smc_chip *chip) -{ - struct aspeed_smc_controller *controller = chip->controller; - u32 reg; - - reg = readl(controller->regs + CONFIG_REG); - - if (reg & aspeed_smc_chip_write_bit(chip)) - return; - - dev_dbg(controller->dev, "config write is not set ! @%p: 0x%08x\n", - controller->regs + CONFIG_REG, reg); - reg |= aspeed_smc_chip_write_bit(chip); - writel(reg, controller->regs + CONFIG_REG); -} - -static void aspeed_smc_start_user(struct spi_nor *nor) -{ - struct aspeed_smc_chip *chip = nor->priv; - u32 ctl = chip->ctl_val[smc_base]; - - /* - * When the chip is controlled in user mode, we need write - * access to send the opcodes to it. So check the config. - */ - aspeed_smc_chip_check_config(chip); - - ctl |= CONTROL_COMMAND_MODE_USER | - CONTROL_CE_STOP_ACTIVE_CONTROL; - writel(ctl, chip->ctl); - - ctl &= ~CONTROL_CE_STOP_ACTIVE_CONTROL; - writel(ctl, chip->ctl); -} - -static void aspeed_smc_stop_user(struct spi_nor *nor) -{ - struct aspeed_smc_chip *chip = nor->priv; - - u32 ctl = chip->ctl_val[smc_read]; - u32 ctl2 = ctl | CONTROL_COMMAND_MODE_USER | - CONTROL_CE_STOP_ACTIVE_CONTROL; - - writel(ctl2, chip->ctl); /* stop user CE control */ - writel(ctl, chip->ctl); /* default to fread or read mode */ -} - -static int aspeed_smc_prep(struct spi_nor *nor) -{ - struct aspeed_smc_chip *chip = nor->priv; - - mutex_lock(&chip->controller->mutex); - return 0; -} - -static void aspeed_smc_unprep(struct spi_nor *nor) -{ - struct aspeed_smc_chip *chip = nor->priv; - - mutex_unlock(&chip->controller->mutex); -} - -static int aspeed_smc_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, - size_t len) -{ - struct aspeed_smc_chip *chip = nor->priv; - - aspeed_smc_start_user(nor); - aspeed_smc_write_to_ahb(chip->ahb_base, &opcode, 1); - aspeed_smc_read_from_ahb(buf, chip->ahb_base, len); - aspeed_smc_stop_user(nor); - return 0; -} - -static int aspeed_smc_write_reg(struct spi_nor *nor, u8 opcode, const u8 *buf, - size_t len) -{ - struct aspeed_smc_chip *chip = nor->priv; - - aspeed_smc_start_user(nor); - aspeed_smc_write_to_ahb(chip->ahb_base, &opcode, 1); - aspeed_smc_write_to_ahb(chip->ahb_base, buf, len); - aspeed_smc_stop_user(nor); - return 0; -} - -static void aspeed_smc_send_cmd_addr(struct spi_nor *nor, u8 cmd, u32 addr) -{ - struct aspeed_smc_chip *chip = nor->priv; - __be32 temp; - u32 cmdaddr; - - switch (nor->addr_width) { - default: - WARN_ONCE(1, "Unexpected address width %u, defaulting to 3\n", - nor->addr_width); - fallthrough; - case 3: - cmdaddr = addr & 0xFFFFFF; - cmdaddr |= cmd << 24; - - temp = cpu_to_be32(cmdaddr); - aspeed_smc_write_to_ahb(chip->ahb_base, &temp, 4); - break; - case 4: - temp = cpu_to_be32(addr); - aspeed_smc_write_to_ahb(chip->ahb_base, &cmd, 1); - aspeed_smc_write_to_ahb(chip->ahb_base, &temp, 4); - break; - } -} - -static ssize_t aspeed_smc_read_user(struct spi_nor *nor, loff_t from, - size_t len, u_char *read_buf) -{ - struct aspeed_smc_chip *chip = nor->priv; - int i; - u8 dummy = 0xFF; - - aspeed_smc_start_user(nor); - aspeed_smc_send_cmd_addr(nor, nor->read_opcode, from); - for (i = 0; i < chip->nor.read_dummy / 8; i++) - aspeed_smc_write_to_ahb(chip->ahb_base, &dummy, sizeof(dummy)); - - aspeed_smc_read_from_ahb(read_buf, chip->ahb_base, len); - aspeed_smc_stop_user(nor); - return len; -} - -static ssize_t aspeed_smc_write_user(struct spi_nor *nor, loff_t to, - size_t len, const u_char *write_buf) -{ - struct aspeed_smc_chip *chip = nor->priv; - - aspeed_smc_start_user(nor); - aspeed_smc_send_cmd_addr(nor, nor->program_opcode, to); - aspeed_smc_write_to_ahb(chip->ahb_base, write_buf, len); - aspeed_smc_stop_user(nor); - return len; -} - -static int aspeed_smc_unregister(struct aspeed_smc_controller *controller) -{ - struct aspeed_smc_chip *chip; - int n; - - for (n = 0; n < controller->info->nce; n++) { - chip = controller->chips[n]; - if (chip) - mtd_device_unregister(&chip->nor.mtd); - } - - return 0; -} - -static int aspeed_smc_remove(struct platform_device *dev) -{ - return aspeed_smc_unregister(platform_get_drvdata(dev)); -} - -static const struct of_device_id aspeed_smc_matches[] = { - { .compatible = "aspeed,ast2400-fmc", .data = &fmc_2400_info }, - { .compatible = "aspeed,ast2400-spi", .data = &spi_2400_info }, - { .compatible = "aspeed,ast2500-fmc", .data = &fmc_2500_info }, - { .compatible = "aspeed,ast2500-spi", .data = &spi_2500_info }, - { } -}; -MODULE_DEVICE_TABLE(of, aspeed_smc_matches); - -/* - * Each chip has a mapping window defined by a segment address - * register defining a start and an end address on the AHB bus. These - * addresses can be configured to fit the chip size and offer a - * contiguous memory region across chips. For the moment, we only - * check that each chip segment is valid. - */ -static void __iomem *aspeed_smc_chip_base(struct aspeed_smc_chip *chip, - struct resource *res) -{ - struct aspeed_smc_controller *controller = chip->controller; - u32 offset = 0; - u32 reg; - - if (controller->info->nce > 1) { - reg = readl(SEGMENT_ADDR_REG(controller, chip->cs)); - - if (SEGMENT_ADDR_START(reg) >= SEGMENT_ADDR_END(reg)) - return NULL; - - offset = SEGMENT_ADDR_START(reg) - res->start; - } - - return controller->ahb_base + offset; -} - -static u32 aspeed_smc_ahb_base_phy(struct aspeed_smc_controller *controller) -{ - u32 seg0_val = readl(SEGMENT_ADDR_REG(controller, 0)); - - return SEGMENT_ADDR_START(seg0_val); -} - -static u32 chip_set_segment(struct aspeed_smc_chip *chip, u32 cs, u32 start, - u32 size) -{ - struct aspeed_smc_controller *controller = chip->controller; - void __iomem *seg_reg; - u32 seg_oldval, seg_newval, ahb_base_phy, end; - - ahb_base_phy = aspeed_smc_ahb_base_phy(controller); - - seg_reg = SEGMENT_ADDR_REG(controller, cs); - seg_oldval = readl(seg_reg); - - /* - * If the chip size is not specified, use the default segment - * size, but take into account the possible overlap with the - * previous segment - */ - if (!size) - size = SEGMENT_ADDR_END(seg_oldval) - start; - - /* - * The segment cannot exceed the maximum window size of the - * controller. - */ - if (start + size > ahb_base_phy + controller->ahb_window_size) { - size = ahb_base_phy + controller->ahb_window_size - start; - dev_warn(chip->nor.dev, "CE%d window resized to %dMB", - cs, size >> 20); - } - - end = start + size; - seg_newval = SEGMENT_ADDR_VALUE(start, end); - writel(seg_newval, seg_reg); - - /* - * Restore default value if something goes wrong. The chip - * might have set some bogus value and we would loose access - * to the chip. - */ - if (seg_newval != readl(seg_reg)) { - dev_err(chip->nor.dev, "CE%d window invalid", cs); - writel(seg_oldval, seg_reg); - start = SEGMENT_ADDR_START(seg_oldval); - end = SEGMENT_ADDR_END(seg_oldval); - size = end - start; - } - - dev_info(chip->nor.dev, "CE%d window [ 0x%.8x - 0x%.8x ] %dMB", - cs, start, end, size >> 20); - - return size; -} - -/* - * The segment register defines the mapping window on the AHB bus and - * it needs to be configured depending on the chip size. The segment - * register of the following CE also needs to be tuned in order to - * provide a contiguous window across multiple chips. - * - * This is expected to be called in increasing CE order - */ -static u32 aspeed_smc_chip_set_segment(struct aspeed_smc_chip *chip) -{ - struct aspeed_smc_controller *controller = chip->controller; - u32 ahb_base_phy, start; - u32 size = chip->nor.mtd.size; - - /* - * Each controller has a chip size limit for direct memory - * access - */ - if (size > controller->info->maxsize) - size = controller->info->maxsize; - - /* - * The AST2400 SPI controller only handles one chip and does - * not have segment registers. Let's use the chip size for the - * AHB window. - */ - if (controller->info == &spi_2400_info) - goto out; - - /* - * The AST2500 SPI controller has a HW bug when the CE0 chip - * size reaches 128MB. Enforce a size limit of 120MB to - * prevent the controller from using bogus settings in the - * segment register. - */ - if (chip->cs == 0 && controller->info == &spi_2500_info && - size == SZ_128M) { - size = 120 << 20; - dev_info(chip->nor.dev, - "CE%d window resized to %dMB (AST2500 HW quirk)", - chip->cs, size >> 20); - } - - ahb_base_phy = aspeed_smc_ahb_base_phy(controller); - - /* - * As a start address for the current segment, use the default - * start address if we are handling CE0 or use the previous - * segment ending address - */ - if (chip->cs) { - u32 prev = readl(SEGMENT_ADDR_REG(controller, chip->cs - 1)); - - start = SEGMENT_ADDR_END(prev); - } else { - start = ahb_base_phy; - } - - size = chip_set_segment(chip, chip->cs, start, size); - - /* Update chip base address on the AHB bus */ - chip->ahb_base = controller->ahb_base + (start - ahb_base_phy); - - /* - * Now, make sure the next segment does not overlap with the - * current one we just configured, even if there is no - * available chip. That could break access in Command Mode. - */ - if (chip->cs < controller->info->nce - 1) - chip_set_segment(chip, chip->cs + 1, start + size, 0); - -out: - if (size < chip->nor.mtd.size) - dev_warn(chip->nor.dev, - "CE%d window too small for chip %dMB", - chip->cs, (u32)chip->nor.mtd.size >> 20); - - return size; -} - -static void aspeed_smc_chip_enable_write(struct aspeed_smc_chip *chip) -{ - struct aspeed_smc_controller *controller = chip->controller; - u32 reg; - - reg = readl(controller->regs + CONFIG_REG); - - reg |= aspeed_smc_chip_write_bit(chip); - writel(reg, controller->regs + CONFIG_REG); -} - -static void aspeed_smc_chip_set_type(struct aspeed_smc_chip *chip, int type) -{ - struct aspeed_smc_controller *controller = chip->controller; - u32 reg; - - chip->type = type; - - reg = readl(controller->regs + CONFIG_REG); - reg &= ~(3 << (chip->cs * 2)); - reg |= chip->type << (chip->cs * 2); - writel(reg, controller->regs + CONFIG_REG); -} - -/* - * The first chip of the AST2500 FMC flash controller is strapped by - * hardware, or autodetected, but other chips need to be set. Enforce - * the 4B setting for all chips. - */ -static void aspeed_smc_chip_set_4b(struct aspeed_smc_chip *chip) -{ - struct aspeed_smc_controller *controller = chip->controller; - u32 reg; - - reg = readl(controller->regs + CE_CONTROL_REG); - reg |= 1 << chip->cs; - writel(reg, controller->regs + CE_CONTROL_REG); -} - -/* - * The AST2400 SPI flash controller does not have a CE Control - * register. It uses the CE0 control register to set 4Byte mode at the - * controller level. - */ -static void aspeed_smc_chip_set_4b_spi_2400(struct aspeed_smc_chip *chip) -{ - chip->ctl_val[smc_base] |= CONTROL_IO_ADDRESS_4B; - chip->ctl_val[smc_read] |= CONTROL_IO_ADDRESS_4B; -} - -static int aspeed_smc_chip_setup_init(struct aspeed_smc_chip *chip, - struct resource *res) -{ - struct aspeed_smc_controller *controller = chip->controller; - const struct aspeed_smc_info *info = controller->info; - u32 reg, base_reg; - - /* - * Always turn on the write enable bit to allow opcodes to be - * sent in user mode. - */ - aspeed_smc_chip_enable_write(chip); - - /* The driver only supports SPI type flash */ - if (info->hastype) - aspeed_smc_chip_set_type(chip, smc_type_spi); - - /* - * Configure chip base address in memory - */ - chip->ahb_base = aspeed_smc_chip_base(chip, res); - if (!chip->ahb_base) { - dev_warn(chip->nor.dev, "CE%d window closed", chip->cs); - return -EINVAL; - } - - /* - * Get value of the inherited control register. U-Boot usually - * does some timing calibration on the FMC chip, so it's good - * to keep them. In the future, we should handle calibration - * from Linux. - */ - reg = readl(chip->ctl); - dev_dbg(controller->dev, "control register: %08x\n", reg); - - base_reg = reg & CONTROL_KEEP_MASK; - if (base_reg != reg) { - dev_dbg(controller->dev, - "control register changed to: %08x\n", - base_reg); - } - chip->ctl_val[smc_base] = base_reg; - - /* - * Retain the prior value of the control register as the - * default if it was normal access mode. Otherwise start with - * the sanitized base value set to read mode. - */ - if ((reg & CONTROL_COMMAND_MODE_MASK) == - CONTROL_COMMAND_MODE_NORMAL) - chip->ctl_val[smc_read] = reg; - else - chip->ctl_val[smc_read] = chip->ctl_val[smc_base] | - CONTROL_COMMAND_MODE_NORMAL; - - dev_dbg(controller->dev, "default control register: %08x\n", - chip->ctl_val[smc_read]); - return 0; -} - -static int aspeed_smc_chip_setup_finish(struct aspeed_smc_chip *chip) -{ - struct aspeed_smc_controller *controller = chip->controller; - const struct aspeed_smc_info *info = controller->info; - u32 cmd; - - if (chip->nor.addr_width == 4 && info->set_4b) - info->set_4b(chip); - - /* This is for direct AHB access when using Command Mode. */ - chip->ahb_window_size = aspeed_smc_chip_set_segment(chip); - - /* - * base mode has not been optimized yet. use it for writes. - */ - chip->ctl_val[smc_write] = chip->ctl_val[smc_base] | - chip->nor.program_opcode << CONTROL_COMMAND_SHIFT | - CONTROL_COMMAND_MODE_WRITE; - - dev_dbg(controller->dev, "write control register: %08x\n", - chip->ctl_val[smc_write]); - - /* - * TODO: Adjust clocks if fast read is supported and interpret - * SPI NOR flags to adjust controller settings. - */ - if (chip->nor.read_proto == SNOR_PROTO_1_1_1) { - if (chip->nor.read_dummy == 0) - cmd = CONTROL_COMMAND_MODE_NORMAL; - else - cmd = CONTROL_COMMAND_MODE_FREAD; - } else { - dev_err(chip->nor.dev, "unsupported SPI read mode\n"); - return -EINVAL; - } - - chip->ctl_val[smc_read] |= cmd | - CONTROL_IO_DUMMY_SET(chip->nor.read_dummy / 8); - - dev_dbg(controller->dev, "base control register: %08x\n", - chip->ctl_val[smc_read]); - return 0; -} - -static const struct spi_nor_controller_ops aspeed_smc_controller_ops = { - .prepare = aspeed_smc_prep, - .unprepare = aspeed_smc_unprep, - .read_reg = aspeed_smc_read_reg, - .write_reg = aspeed_smc_write_reg, - .read = aspeed_smc_read_user, - .write = aspeed_smc_write_user, -}; - -static int aspeed_smc_setup_flash(struct aspeed_smc_controller *controller, - struct device_node *np, struct resource *r) -{ - const struct spi_nor_hwcaps hwcaps = { - .mask = SNOR_HWCAPS_READ | - SNOR_HWCAPS_READ_FAST | - SNOR_HWCAPS_PP, - }; - const struct aspeed_smc_info *info = controller->info; - struct device *dev = controller->dev; - struct device_node *child; - unsigned int cs; - int ret = -ENODEV; - bool found_one = false; - - for_each_available_child_of_node(np, child) { - struct aspeed_smc_chip *chip; - struct spi_nor *nor; - struct mtd_info *mtd; - - /* This driver does not support NAND or NOR flash devices. */ - if (!of_device_is_compatible(child, "jedec,spi-nor")) - continue; - - ret = of_property_read_u32(child, "reg", &cs); - if (ret) { - dev_err(dev, "Couldn't not read chip select.\n"); - break; - } - - if (cs >= info->nce) { - dev_err(dev, "Chip select %d out of range.\n", - cs); - ret = -ERANGE; - break; - } - - if (controller->chips[cs]) { - dev_err(dev, "Chip select %d already in use by %s\n", - cs, dev_name(controller->chips[cs]->nor.dev)); - ret = -EBUSY; - break; - } - - chip = devm_kzalloc(controller->dev, sizeof(*chip), GFP_KERNEL); - if (!chip) { - ret = -ENOMEM; - break; - } - - chip->controller = controller; - chip->ctl = controller->regs + info->ctl0 + cs * 4; - chip->cs = cs; - - nor = &chip->nor; - mtd = &nor->mtd; - - nor->dev = dev; - nor->priv = chip; - spi_nor_set_flash_node(nor, child); - nor->controller_ops = &aspeed_smc_controller_ops; - - ret = aspeed_smc_chip_setup_init(chip, r); - if (ret) - break; - - /* - * TODO: Add support for Dual and Quad SPI protocols - * attach when board support is present as determined - * by of property. - */ - ret = spi_nor_scan(nor, NULL, &hwcaps); - /* - * If we fail to scan the device it might not be present or - * broken. Don't fail the whole controller if others work. - */ - if (ret) { - if (found_one) - ret = 0; - - devm_kfree(controller->dev, chip); - continue; - } - - ret = aspeed_smc_chip_setup_finish(chip); - if (ret) - break; - - ret = mtd_device_register(mtd, NULL, 0); - if (ret) - break; - - controller->chips[cs] = chip; - found_one = true; - } - - if (ret) { - of_node_put(child); - aspeed_smc_unregister(controller); - } - - return ret; -} - -static int aspeed_smc_probe(struct platform_device *pdev) -{ - struct device_node *np = pdev->dev.of_node; - struct device *dev = &pdev->dev; - struct aspeed_smc_controller *controller; - const struct of_device_id *match; - const struct aspeed_smc_info *info; - struct resource *res; - int ret; - - match = of_match_device(aspeed_smc_matches, &pdev->dev); - if (!match || !match->data) - return -ENODEV; - info = match->data; - - controller = devm_kzalloc(&pdev->dev, - struct_size(controller, chips, info->nce), - GFP_KERNEL); - if (!controller) - return -ENOMEM; - controller->info = info; - controller->dev = dev; - - mutex_init(&controller->mutex); - platform_set_drvdata(pdev, controller); - - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - controller->regs = devm_ioremap_resource(dev, res); - if (IS_ERR(controller->regs)) - return PTR_ERR(controller->regs); - - res = platform_get_resource(pdev, IORESOURCE_MEM, 1); - controller->ahb_base = devm_ioremap_resource(dev, res); - if (IS_ERR(controller->ahb_base)) - return PTR_ERR(controller->ahb_base); - - controller->ahb_window_size = resource_size(res); - - ret = aspeed_smc_setup_flash(controller, np, res); - if (ret) - dev_err(dev, "Aspeed SMC probe failed %d\n", ret); - - return ret; -} - -static struct platform_driver aspeed_smc_driver = { - .probe = aspeed_smc_probe, - .remove = aspeed_smc_remove, - .driver = { - .name = DEVICE_NAME, - .of_match_table = aspeed_smc_matches, - } -}; - -module_platform_driver(aspeed_smc_driver); - -MODULE_DESCRIPTION("ASPEED Static Memory Controller Driver"); -MODULE_AUTHOR("Cedric Le Goater <clg@kaod.org>"); -MODULE_LICENSE("GPL v2"); diff --git a/drivers/mtd/spi-nor/core.c b/drivers/mtd/spi-nor/core.c index b4f141ad9c9c..502967c76c5f 100644 --- a/drivers/mtd/spi-nor/core.c +++ b/drivers/mtd/spi-nor/core.c @@ -308,6 +308,52 @@ ssize_t spi_nor_write_data(struct spi_nor *nor, loff_t to, size_t len, } /** + * spi_nor_read_any_reg() - read any register from flash memory, nonvolatile or + * volatile. + * @nor: pointer to 'struct spi_nor'. + * @op: SPI memory operation. op->data.buf must be DMA-able. + * @proto: SPI protocol to use for the register operation. + * + * Return: zero on success, -errno otherwise + */ +int spi_nor_read_any_reg(struct spi_nor *nor, struct spi_mem_op *op, + enum spi_nor_protocol proto) +{ + if (!nor->spimem) + return -EOPNOTSUPP; + + spi_nor_spimem_setup_op(nor, op, proto); + return spi_nor_spimem_exec_op(nor, op); +} + +/** + * spi_nor_write_any_volatile_reg() - write any volatile register to flash + * memory. + * @nor: pointer to 'struct spi_nor' + * @op: SPI memory operation. op->data.buf must be DMA-able. + * @proto: SPI protocol to use for the register operation. + * + * Writing volatile registers are instant according to some manufacturers + * (Cypress, Micron) and do not need any status polling. + * + * Return: zero on success, -errno otherwise + */ +int spi_nor_write_any_volatile_reg(struct spi_nor *nor, struct spi_mem_op *op, + enum spi_nor_protocol proto) +{ + int ret; + + if (!nor->spimem) + return -EOPNOTSUPP; + + ret = spi_nor_write_enable(nor); + if (ret) + return ret; + spi_nor_spimem_setup_op(nor, op, proto); + return spi_nor_spimem_exec_op(nor, op); +} + +/** * spi_nor_write_enable() - Set write enable latch with Write Enable command. * @nor: pointer to 'struct spi_nor'. * @@ -318,11 +364,7 @@ int spi_nor_write_enable(struct spi_nor *nor) int ret; if (nor->spimem) { - struct spi_mem_op op = - SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_WREN, 0), - SPI_MEM_OP_NO_ADDR, - SPI_MEM_OP_NO_DUMMY, - SPI_MEM_OP_NO_DATA); + struct spi_mem_op op = SPI_NOR_WREN_OP; spi_nor_spimem_setup_op(nor, &op, nor->reg_proto); @@ -349,11 +391,7 @@ int spi_nor_write_disable(struct spi_nor *nor) int ret; if (nor->spimem) { - struct spi_mem_op op = - SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_WRDI, 0), - SPI_MEM_OP_NO_ADDR, - SPI_MEM_OP_NO_DUMMY, - SPI_MEM_OP_NO_DATA); + struct spi_mem_op op = SPI_NOR_WRDI_OP; spi_nor_spimem_setup_op(nor, &op, nor->reg_proto); @@ -370,6 +408,37 @@ int spi_nor_write_disable(struct spi_nor *nor) } /** + * spi_nor_read_id() - Read the JEDEC ID. + * @nor: pointer to 'struct spi_nor'. + * @naddr: number of address bytes to send. Can be zero if the operation + * does not need to send an address. + * @ndummy: number of dummy bytes to send after an opcode or address. Can + * be zero if the operation does not require dummy bytes. + * @id: pointer to a DMA-able buffer where the value of the JEDEC ID + * will be written. + * @proto: the SPI protocol for register operation. + * + * Return: 0 on success, -errno otherwise. + */ +int spi_nor_read_id(struct spi_nor *nor, u8 naddr, u8 ndummy, u8 *id, + enum spi_nor_protocol proto) +{ + int ret; + + if (nor->spimem) { + struct spi_mem_op op = + SPI_NOR_READID_OP(naddr, ndummy, id, SPI_NOR_MAX_ID_LEN); + + spi_nor_spimem_setup_op(nor, &op, proto); + ret = spi_mem_exec_op(nor->spimem, &op); + } else { + ret = nor->controller_ops->read_reg(nor, SPINOR_OP_RDID, id, + SPI_NOR_MAX_ID_LEN); + } + return ret; +} + +/** * spi_nor_read_sr() - Read the Status Register. * @nor: pointer to 'struct spi_nor'. * @sr: pointer to a DMA-able buffer where the value of the @@ -382,11 +451,7 @@ int spi_nor_read_sr(struct spi_nor *nor, u8 *sr) int ret; if (nor->spimem) { - struct spi_mem_op op = - SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_RDSR, 0), - SPI_MEM_OP_NO_ADDR, - SPI_MEM_OP_NO_DUMMY, - SPI_MEM_OP_DATA_IN(1, sr, 0)); + struct spi_mem_op op = SPI_NOR_RDSR_OP(sr); if (nor->reg_proto == SNOR_PROTO_8_8_8_DTR) { op.addr.nbytes = nor->params->rdsr_addr_nbytes; @@ -426,11 +491,7 @@ int spi_nor_read_cr(struct spi_nor *nor, u8 *cr) int ret; if (nor->spimem) { - struct spi_mem_op op = - SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_RDCR, 0), - SPI_MEM_OP_NO_ADDR, - SPI_MEM_OP_NO_DUMMY, - SPI_MEM_OP_DATA_IN(1, cr, 0)); + struct spi_mem_op op = SPI_NOR_RDCR_OP(cr); spi_nor_spimem_setup_op(nor, &op, nor->reg_proto); @@ -459,14 +520,7 @@ int spi_nor_set_4byte_addr_mode(struct spi_nor *nor, bool enable) int ret; if (nor->spimem) { - struct spi_mem_op op = - SPI_MEM_OP(SPI_MEM_OP_CMD(enable ? - SPINOR_OP_EN4B : - SPINOR_OP_EX4B, - 0), - SPI_MEM_OP_NO_ADDR, - SPI_MEM_OP_NO_DUMMY, - SPI_MEM_OP_NO_DATA); + struct spi_mem_op op = SPI_NOR_EN4B_EX4B_OP(enable); spi_nor_spimem_setup_op(nor, &op, nor->reg_proto); @@ -500,11 +554,7 @@ static int spansion_set_4byte_addr_mode(struct spi_nor *nor, bool enable) nor->bouncebuf[0] = enable << 7; if (nor->spimem) { - struct spi_mem_op op = - SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_BRWR, 0), - SPI_MEM_OP_NO_ADDR, - SPI_MEM_OP_NO_DUMMY, - SPI_MEM_OP_DATA_OUT(1, nor->bouncebuf, 0)); + struct spi_mem_op op = SPI_NOR_BRWR_OP(nor->bouncebuf); spi_nor_spimem_setup_op(nor, &op, nor->reg_proto); @@ -521,40 +571,6 @@ static int spansion_set_4byte_addr_mode(struct spi_nor *nor, bool enable) } /** - * spi_nor_write_ear() - Write Extended Address Register. - * @nor: pointer to 'struct spi_nor'. - * @ear: value to write to the Extended Address Register. - * - * Return: 0 on success, -errno otherwise. - */ -int spi_nor_write_ear(struct spi_nor *nor, u8 ear) -{ - int ret; - - nor->bouncebuf[0] = ear; - - if (nor->spimem) { - struct spi_mem_op op = - SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_WREAR, 0), - SPI_MEM_OP_NO_ADDR, - SPI_MEM_OP_NO_DUMMY, - SPI_MEM_OP_DATA_OUT(1, nor->bouncebuf, 0)); - - spi_nor_spimem_setup_op(nor, &op, nor->reg_proto); - - ret = spi_mem_exec_op(nor->spimem, &op); - } else { - ret = spi_nor_controller_ops_write_reg(nor, SPINOR_OP_WREAR, - nor->bouncebuf, 1); - } - - if (ret) - dev_dbg(nor->dev, "error %d writing EAR\n", ret); - - return ret; -} - -/** * spi_nor_sr_ready() - Query the Status Register to see if the flash is ready * for new commands. * @nor: pointer to 'struct spi_nor'. @@ -649,11 +665,7 @@ int spi_nor_global_block_unlock(struct spi_nor *nor) return ret; if (nor->spimem) { - struct spi_mem_op op = - SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_GBULK, 0), - SPI_MEM_OP_NO_ADDR, - SPI_MEM_OP_NO_DUMMY, - SPI_MEM_OP_NO_DATA); + struct spi_mem_op op = SPI_NOR_GBULK_OP; spi_nor_spimem_setup_op(nor, &op, nor->reg_proto); @@ -688,11 +700,7 @@ int spi_nor_write_sr(struct spi_nor *nor, const u8 *sr, size_t len) return ret; if (nor->spimem) { - struct spi_mem_op op = - SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_WRSR, 0), - SPI_MEM_OP_NO_ADDR, - SPI_MEM_OP_NO_DUMMY, - SPI_MEM_OP_DATA_OUT(len, sr, 0)); + struct spi_mem_op op = SPI_NOR_WRSR_OP(sr, len); spi_nor_spimem_setup_op(nor, &op, nor->reg_proto); @@ -788,6 +796,15 @@ static int spi_nor_write_16bit_sr_and_check(struct spi_nor *nor, u8 sr1) if (ret) return ret; + ret = spi_nor_read_sr(nor, sr_cr); + if (ret) + return ret; + + if (sr1 != sr_cr[0]) { + dev_dbg(nor->dev, "SR: Read back test failed\n"); + return -EIO; + } + if (nor->flags & SNOR_F_NO_READ_CR) return 0; @@ -892,11 +909,7 @@ static int spi_nor_write_sr2(struct spi_nor *nor, const u8 *sr2) return ret; if (nor->spimem) { - struct spi_mem_op op = - SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_WRSR2, 0), - SPI_MEM_OP_NO_ADDR, - SPI_MEM_OP_NO_DUMMY, - SPI_MEM_OP_DATA_OUT(1, sr2, 0)); + struct spi_mem_op op = SPI_NOR_WRSR2_OP(sr2); spi_nor_spimem_setup_op(nor, &op, nor->reg_proto); @@ -928,11 +941,7 @@ static int spi_nor_read_sr2(struct spi_nor *nor, u8 *sr2) int ret; if (nor->spimem) { - struct spi_mem_op op = - SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_RDSR2, 0), - SPI_MEM_OP_NO_ADDR, - SPI_MEM_OP_NO_DUMMY, - SPI_MEM_OP_DATA_IN(1, sr2, 0)); + struct spi_mem_op op = SPI_NOR_RDSR2_OP(sr2); spi_nor_spimem_setup_op(nor, &op, nor->reg_proto); @@ -961,11 +970,7 @@ static int spi_nor_erase_chip(struct spi_nor *nor) dev_dbg(nor->dev, " %lldKiB\n", (long long)(nor->mtd.size >> 10)); if (nor->spimem) { - struct spi_mem_op op = - SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_CHIP_ERASE, 0), - SPI_MEM_OP_NO_ADDR, - SPI_MEM_OP_NO_DUMMY, - SPI_MEM_OP_NO_DATA); + struct spi_mem_op op = SPI_NOR_CHIP_ERASE_OP; spi_nor_spimem_setup_op(nor, &op, nor->write_proto); @@ -1107,10 +1112,8 @@ int spi_nor_erase_sector(struct spi_nor *nor, u32 addr) if (nor->spimem) { struct spi_mem_op op = - SPI_MEM_OP(SPI_MEM_OP_CMD(nor->erase_opcode, 0), - SPI_MEM_OP_ADDR(nor->addr_width, addr, 0), - SPI_MEM_OP_NO_DUMMY, - SPI_MEM_OP_NO_DATA); + SPI_NOR_SECTOR_ERASE_OP(nor->erase_opcode, + nor->addr_width, addr); spi_nor_spimem_setup_op(nor, &op, nor->write_proto); @@ -1629,58 +1632,45 @@ static const struct spi_nor_manufacturer *manufacturers[] = { &spi_nor_xmc, }; -static const struct flash_info * -spi_nor_search_part_by_id(const struct flash_info *parts, unsigned int nparts, - const u8 *id) +static const struct flash_info *spi_nor_match_id(struct spi_nor *nor, + const u8 *id) { - unsigned int i; + const struct flash_info *part; + unsigned int i, j; - for (i = 0; i < nparts; i++) { - if (parts[i].id_len && - !memcmp(parts[i].id, id, parts[i].id_len)) - return &parts[i]; + for (i = 0; i < ARRAY_SIZE(manufacturers); i++) { + for (j = 0; j < manufacturers[i]->nparts; j++) { + part = &manufacturers[i]->parts[j]; + if (part->id_len && + !memcmp(part->id, id, part->id_len)) { + nor->manufacturer = manufacturers[i]; + return part; + } + } } return NULL; } -static const struct flash_info *spi_nor_read_id(struct spi_nor *nor) +static const struct flash_info *spi_nor_detect(struct spi_nor *nor) { const struct flash_info *info; u8 *id = nor->bouncebuf; - unsigned int i; int ret; - if (nor->spimem) { - struct spi_mem_op op = - SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_RDID, 1), - SPI_MEM_OP_NO_ADDR, - SPI_MEM_OP_NO_DUMMY, - SPI_MEM_OP_DATA_IN(SPI_NOR_MAX_ID_LEN, id, 1)); - - ret = spi_mem_exec_op(nor->spimem, &op); - } else { - ret = nor->controller_ops->read_reg(nor, SPINOR_OP_RDID, id, - SPI_NOR_MAX_ID_LEN); - } + ret = spi_nor_read_id(nor, 0, 0, id, nor->reg_proto); if (ret) { dev_dbg(nor->dev, "error %d reading JEDEC ID\n", ret); return ERR_PTR(ret); } - for (i = 0; i < ARRAY_SIZE(manufacturers); i++) { - info = spi_nor_search_part_by_id(manufacturers[i]->parts, - manufacturers[i]->nparts, - id); - if (info) { - nor->manufacturer = manufacturers[i]; - return info; - } + info = spi_nor_match_id(nor, id); + if (!info) { + dev_err(nor->dev, "unrecognized JEDEC id bytes: %*ph\n", + SPI_NOR_MAX_ID_LEN, id); + return ERR_PTR(-ENODEV); } - - dev_err(nor->dev, "unrecognized JEDEC id bytes: %*ph\n", - SPI_NOR_MAX_ID_LEN, id); - return ERR_PTR(-ENODEV); + return info; } static int spi_nor_read(struct mtd_info *mtd, loff_t from, size_t len, @@ -1860,7 +1850,7 @@ int spi_nor_hwcaps_read2cmd(u32 hwcaps) ARRAY_SIZE(hwcaps_read2cmd)); } -static int spi_nor_hwcaps_pp2cmd(u32 hwcaps) +int spi_nor_hwcaps_pp2cmd(u32 hwcaps) { static const int hwcaps_pp2cmd[][2] = { { SNOR_HWCAPS_PP, SNOR_CMD_PP }, @@ -1919,10 +1909,7 @@ static int spi_nor_spimem_check_op(struct spi_nor *nor, static int spi_nor_spimem_check_readop(struct spi_nor *nor, const struct spi_nor_read_command *read) { - struct spi_mem_op op = SPI_MEM_OP(SPI_MEM_OP_CMD(read->opcode, 0), - SPI_MEM_OP_ADDR(3, 0, 0), - SPI_MEM_OP_DUMMY(1, 0), - SPI_MEM_OP_DATA_IN(2, NULL, 0)); + struct spi_mem_op op = SPI_NOR_READ_OP(read->opcode); spi_nor_spimem_setup_op(nor, &op, read->proto); @@ -1945,10 +1932,7 @@ static int spi_nor_spimem_check_readop(struct spi_nor *nor, static int spi_nor_spimem_check_pp(struct spi_nor *nor, const struct spi_nor_pp_command *pp) { - struct spi_mem_op op = SPI_MEM_OP(SPI_MEM_OP_CMD(pp->opcode, 0), - SPI_MEM_OP_ADDR(3, 0, 0), - SPI_MEM_OP_NO_DUMMY, - SPI_MEM_OP_DATA_OUT(2, NULL, 0)); + struct spi_mem_op op = SPI_NOR_PP_OP(pp->opcode); spi_nor_spimem_setup_op(nor, &op, pp->proto); @@ -2772,10 +2756,7 @@ static void spi_nor_soft_reset(struct spi_nor *nor) struct spi_mem_op op; int ret; - op = (struct spi_mem_op)SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_SRSTEN, 0), - SPI_MEM_OP_NO_DUMMY, - SPI_MEM_OP_NO_ADDR, - SPI_MEM_OP_NO_DATA); + op = (struct spi_mem_op)SPINOR_SRSTEN_OP; spi_nor_spimem_setup_op(nor, &op, nor->reg_proto); @@ -2785,10 +2766,7 @@ static void spi_nor_soft_reset(struct spi_nor *nor) return; } - op = (struct spi_mem_op)SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_SRST, 0), - SPI_MEM_OP_NO_DUMMY, - SPI_MEM_OP_NO_ADDR, - SPI_MEM_OP_NO_DATA); + op = (struct spi_mem_op)SPINOR_SRST_OP; spi_nor_spimem_setup_op(nor, &op, nor->reg_proto); @@ -2876,8 +2854,8 @@ void spi_nor_restore(struct spi_nor *nor) } EXPORT_SYMBOL_GPL(spi_nor_restore); -static const struct flash_info *spi_nor_match_id(struct spi_nor *nor, - const char *name) +static const struct flash_info *spi_nor_match_name(struct spi_nor *nor, + const char *name) { unsigned int i, j; @@ -2899,12 +2877,10 @@ static const struct flash_info *spi_nor_get_flash_info(struct spi_nor *nor, const struct flash_info *info = NULL; if (name) - info = spi_nor_match_id(nor, name); + info = spi_nor_match_name(nor, name); /* Try to auto-detect if chip name wasn't specified or not found */ if (!info) - info = spi_nor_read_id(nor); - if (IS_ERR_OR_NULL(info)) - return ERR_PTR(-ENOENT); + return spi_nor_detect(nor); /* * If caller has specified name of flash model that can normally be @@ -2913,7 +2889,7 @@ static const struct flash_info *spi_nor_get_flash_info(struct spi_nor *nor, if (name && info->id_len) { const struct flash_info *jinfo; - jinfo = spi_nor_read_id(nor); + jinfo = spi_nor_detect(nor); if (IS_ERR(jinfo)) { return jinfo; } else if (jinfo != info) { @@ -3156,6 +3132,8 @@ static int spi_nor_probe(struct spi_mem *spimem) if (ret) return ret; + spi_nor_debugfs_register(nor); + /* * None of the existing parts have > 512B pages, but let's play safe * and add this logic so that if anyone ever adds support for such diff --git a/drivers/mtd/spi-nor/core.h b/drivers/mtd/spi-nor/core.h index b7fd760e3b47..3f841ec36e56 100644 --- a/drivers/mtd/spi-nor/core.h +++ b/drivers/mtd/spi-nor/core.h @@ -11,6 +11,110 @@ #define SPI_NOR_MAX_ID_LEN 6 +/* Standard SPI NOR flash operations. */ +#define SPI_NOR_READID_OP(naddr, ndummy, buf, len) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_RDID, 0), \ + SPI_MEM_OP_ADDR(naddr, 0, 0), \ + SPI_MEM_OP_DUMMY(ndummy, 0), \ + SPI_MEM_OP_DATA_IN(len, buf, 0)) + +#define SPI_NOR_WREN_OP \ + SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_WREN, 0), \ + SPI_MEM_OP_NO_ADDR, \ + SPI_MEM_OP_NO_DUMMY, \ + SPI_MEM_OP_NO_DATA) + +#define SPI_NOR_WRDI_OP \ + SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_WRDI, 0), \ + SPI_MEM_OP_NO_ADDR, \ + SPI_MEM_OP_NO_DUMMY, \ + SPI_MEM_OP_NO_DATA) + +#define SPI_NOR_RDSR_OP(buf) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_RDSR, 0), \ + SPI_MEM_OP_NO_ADDR, \ + SPI_MEM_OP_NO_DUMMY, \ + SPI_MEM_OP_DATA_IN(1, buf, 0)) + +#define SPI_NOR_WRSR_OP(buf, len) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_WRSR, 0), \ + SPI_MEM_OP_NO_ADDR, \ + SPI_MEM_OP_NO_DUMMY, \ + SPI_MEM_OP_DATA_OUT(len, buf, 0)) + +#define SPI_NOR_RDSR2_OP(buf) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_RDSR2, 0), \ + SPI_MEM_OP_NO_ADDR, \ + SPI_MEM_OP_NO_DUMMY, \ + SPI_MEM_OP_DATA_OUT(1, buf, 0)) + +#define SPI_NOR_WRSR2_OP(buf) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_WRSR2, 0), \ + SPI_MEM_OP_NO_ADDR, \ + SPI_MEM_OP_NO_DUMMY, \ + SPI_MEM_OP_DATA_OUT(1, buf, 0)) + +#define SPI_NOR_RDCR_OP(buf) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_RDCR, 0), \ + SPI_MEM_OP_NO_ADDR, \ + SPI_MEM_OP_NO_DUMMY, \ + SPI_MEM_OP_DATA_IN(1, buf, 0)) + +#define SPI_NOR_EN4B_EX4B_OP(enable) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(enable ? SPINOR_OP_EN4B : SPINOR_OP_EX4B, 0), \ + SPI_MEM_OP_NO_ADDR, \ + SPI_MEM_OP_NO_DUMMY, \ + SPI_MEM_OP_NO_DATA) + +#define SPI_NOR_BRWR_OP(buf) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_BRWR, 0), \ + SPI_MEM_OP_NO_ADDR, \ + SPI_MEM_OP_NO_DUMMY, \ + SPI_MEM_OP_DATA_OUT(1, buf, 0)) + +#define SPI_NOR_GBULK_OP \ + SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_GBULK, 0), \ + SPI_MEM_OP_NO_ADDR, \ + SPI_MEM_OP_NO_DUMMY, \ + SPI_MEM_OP_NO_DATA) + +#define SPI_NOR_CHIP_ERASE_OP \ + SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_CHIP_ERASE, 0), \ + SPI_MEM_OP_NO_ADDR, \ + SPI_MEM_OP_NO_DUMMY, \ + SPI_MEM_OP_NO_DATA) + +#define SPI_NOR_SECTOR_ERASE_OP(opcode, addr_width, addr) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(opcode, 0), \ + SPI_MEM_OP_ADDR(addr_width, addr, 0), \ + SPI_MEM_OP_NO_DUMMY, \ + SPI_MEM_OP_NO_DATA) + +#define SPI_NOR_READ_OP(opcode) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(opcode, 0), \ + SPI_MEM_OP_ADDR(3, 0, 0), \ + SPI_MEM_OP_DUMMY(1, 0), \ + SPI_MEM_OP_DATA_IN(2, NULL, 0)) + +#define SPI_NOR_PP_OP(opcode) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(opcode, 0), \ + SPI_MEM_OP_ADDR(3, 0, 0), \ + SPI_MEM_OP_NO_DUMMY, \ + SPI_MEM_OP_DATA_OUT(2, NULL, 0)) + +#define SPINOR_SRSTEN_OP \ + SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_SRSTEN, 0), \ + SPI_MEM_OP_NO_DUMMY, \ + SPI_MEM_OP_NO_ADDR, \ + SPI_MEM_OP_NO_DATA) + +#define SPINOR_SRST_OP \ + SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_SRST, 0), \ + SPI_MEM_OP_NO_DUMMY, \ + SPI_MEM_OP_NO_ADDR, \ + SPI_MEM_OP_NO_DATA) + +/* Keep these in sync with the list in debugfs.c */ enum spi_nor_option_flags { SNOR_F_HAS_SR_TB = BIT(0), SNOR_F_NO_OP_CHIP_ERASE = BIT(1), @@ -236,9 +340,10 @@ struct spi_nor_otp { * @writesize Minimal writable flash unit size. Defaults to 1. Set to * ECC unit size for ECC-ed flashes. * @page_size: the page size of the SPI NOR flash memory. - * @rdsr_dummy: dummy cycles needed for Read Status Register command. + * @rdsr_dummy: dummy cycles needed for Read Status Register command + * in octal DTR mode. * @rdsr_addr_nbytes: dummy address bytes needed for Read Status Register - * command. + * command in octal DTR mode. * @hwcaps: describes the read and page program hardware * capabilities. * @reads: read capabilities ordered by priority: the higher index @@ -526,7 +631,6 @@ void spi_nor_spimem_setup_op(const struct spi_nor *nor, int spi_nor_write_enable(struct spi_nor *nor); int spi_nor_write_disable(struct spi_nor *nor); int spi_nor_set_4byte_addr_mode(struct spi_nor *nor, bool enable); -int spi_nor_write_ear(struct spi_nor *nor, u8 ear); int spi_nor_wait_till_ready(struct spi_nor *nor); int spi_nor_global_block_unlock(struct spi_nor *nor); int spi_nor_lock_and_prep(struct spi_nor *nor); @@ -534,6 +638,8 @@ void spi_nor_unlock_and_unprep(struct spi_nor *nor); int spi_nor_sr1_bit6_quad_enable(struct spi_nor *nor); int spi_nor_sr2_bit1_quad_enable(struct spi_nor *nor); int spi_nor_sr2_bit7_quad_enable(struct spi_nor *nor); +int spi_nor_read_id(struct spi_nor *nor, u8 naddr, u8 ndummy, u8 *id, + enum spi_nor_protocol reg_proto); int spi_nor_read_sr(struct spi_nor *nor, u8 *sr); int spi_nor_sr_ready(struct spi_nor *nor); int spi_nor_read_cr(struct spi_nor *nor, u8 *cr); @@ -545,6 +651,10 @@ ssize_t spi_nor_read_data(struct spi_nor *nor, loff_t from, size_t len, u8 *buf); ssize_t spi_nor_write_data(struct spi_nor *nor, loff_t to, size_t len, const u8 *buf); +int spi_nor_read_any_reg(struct spi_nor *nor, struct spi_mem_op *op, + enum spi_nor_protocol proto); +int spi_nor_write_any_volatile_reg(struct spi_nor *nor, struct spi_mem_op *op, + enum spi_nor_protocol proto); int spi_nor_erase_sector(struct spi_nor *nor, u32 addr); int spi_nor_otp_read_secr(struct spi_nor *nor, loff_t addr, size_t len, u8 *buf); @@ -555,6 +665,7 @@ int spi_nor_otp_lock_sr2(struct spi_nor *nor, unsigned int region); int spi_nor_otp_is_locked_sr2(struct spi_nor *nor, unsigned int region); int spi_nor_hwcaps_read2cmd(u32 hwcaps); +int spi_nor_hwcaps_pp2cmd(u32 hwcaps); u8 spi_nor_convert_3to4_read(u8 opcode); void spi_nor_set_read_settings(struct spi_nor_read_command *read, u8 num_mode_clocks, @@ -590,4 +701,10 @@ static inline struct spi_nor *mtd_to_spi_nor(struct mtd_info *mtd) return container_of(mtd, struct spi_nor, mtd); } +#ifdef CONFIG_DEBUG_FS +void spi_nor_debugfs_register(struct spi_nor *nor); +#else +static inline void spi_nor_debugfs_register(struct spi_nor *nor) {} +#endif + #endif /* __LINUX_MTD_SPI_NOR_INTERNAL_H */ diff --git a/drivers/mtd/spi-nor/debugfs.c b/drivers/mtd/spi-nor/debugfs.c new file mode 100644 index 000000000000..eaf84f7a0676 --- /dev/null +++ b/drivers/mtd/spi-nor/debugfs.c @@ -0,0 +1,249 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/mtd/spi-nor.h> +#include <linux/spi/spi.h> +#include <linux/spi/spi-mem.h> +#include <linux/debugfs.h> + +#include "core.h" + +#define SPI_NOR_DEBUGFS_ROOT "spi-nor" + +#define SNOR_F_NAME(name) [ilog2(SNOR_F_##name)] = #name +static const char *const snor_f_names[] = { + SNOR_F_NAME(HAS_SR_TB), + SNOR_F_NAME(NO_OP_CHIP_ERASE), + SNOR_F_NAME(BROKEN_RESET), + SNOR_F_NAME(4B_OPCODES), + SNOR_F_NAME(HAS_4BAIT), + SNOR_F_NAME(HAS_LOCK), + SNOR_F_NAME(HAS_16BIT_SR), + SNOR_F_NAME(NO_READ_CR), + SNOR_F_NAME(HAS_SR_TB_BIT6), + SNOR_F_NAME(HAS_4BIT_BP), + SNOR_F_NAME(HAS_SR_BP3_BIT6), + SNOR_F_NAME(IO_MODE_EN_VOLATILE), + SNOR_F_NAME(SOFT_RESET), + SNOR_F_NAME(SWP_IS_VOLATILE), +}; +#undef SNOR_F_NAME + +static const char *spi_nor_protocol_name(enum spi_nor_protocol proto) +{ + switch (proto) { + case SNOR_PROTO_1_1_1: return "1S-1S-1S"; + case SNOR_PROTO_1_1_2: return "1S-1S-2S"; + case SNOR_PROTO_1_1_4: return "1S-1S-4S"; + case SNOR_PROTO_1_1_8: return "1S-1S-8S"; + case SNOR_PROTO_1_2_2: return "1S-2S-2S"; + case SNOR_PROTO_1_4_4: return "1S-4S-4S"; + case SNOR_PROTO_1_8_8: return "1S-8S-8S"; + case SNOR_PROTO_2_2_2: return "2S-2S-2S"; + case SNOR_PROTO_4_4_4: return "4S-4S-4S"; + case SNOR_PROTO_8_8_8: return "8S-8S-8S"; + case SNOR_PROTO_1_1_1_DTR: return "1D-1D-1D"; + case SNOR_PROTO_1_2_2_DTR: return "1D-2D-2D"; + case SNOR_PROTO_1_4_4_DTR: return "1D-4D-4D"; + case SNOR_PROTO_1_8_8_DTR: return "1D-8D-8D"; + case SNOR_PROTO_8_8_8_DTR: return "8D-8D-8D"; + } + + return "<unknown>"; +} + +static void spi_nor_print_flags(struct seq_file *s, unsigned long flags, + const char *const *names, int names_len) +{ + bool sep = false; + int i; + + for (i = 0; i < sizeof(flags) * BITS_PER_BYTE; i++) { + if (!(flags & BIT(i))) + continue; + if (sep) + seq_puts(s, " | "); + sep = true; + if (i < names_len && names[i]) + seq_puts(s, names[i]); + else + seq_printf(s, "1<<%d", i); + } +} + +static int spi_nor_params_show(struct seq_file *s, void *data) +{ + struct spi_nor *nor = s->private; + struct spi_nor_flash_parameter *params = nor->params; + struct spi_nor_erase_map *erase_map = ¶ms->erase_map; + struct spi_nor_erase_region *region; + const struct flash_info *info = nor->info; + char buf[16], *str; + int i; + + seq_printf(s, "name\t\t%s\n", info->name); + seq_printf(s, "id\t\t%*ph\n", info->id_len, info->id); + string_get_size(params->size, 1, STRING_UNITS_2, buf, sizeof(buf)); + seq_printf(s, "size\t\t%s\n", buf); + seq_printf(s, "write size\t%u\n", params->writesize); + seq_printf(s, "page size\t%u\n", params->page_size); + seq_printf(s, "address width\t%u\n", nor->addr_width); + + seq_puts(s, "flags\t\t"); + spi_nor_print_flags(s, nor->flags, snor_f_names, sizeof(snor_f_names)); + seq_puts(s, "\n"); + + seq_puts(s, "\nopcodes\n"); + seq_printf(s, " read\t\t0x%02x\n", nor->read_opcode); + seq_printf(s, " dummy cycles\t%u\n", nor->read_dummy); + seq_printf(s, " erase\t\t0x%02x\n", nor->erase_opcode); + seq_printf(s, " program\t0x%02x\n", nor->program_opcode); + + switch (nor->cmd_ext_type) { + case SPI_NOR_EXT_NONE: + str = "none"; + break; + case SPI_NOR_EXT_REPEAT: + str = "repeat"; + break; + case SPI_NOR_EXT_INVERT: + str = "invert"; + break; + default: + str = "<unknown>"; + break; + } + seq_printf(s, " 8D extension\t%s\n", str); + + seq_puts(s, "\nprotocols\n"); + seq_printf(s, " read\t\t%s\n", + spi_nor_protocol_name(nor->read_proto)); + seq_printf(s, " write\t\t%s\n", + spi_nor_protocol_name(nor->write_proto)); + seq_printf(s, " register\t%s\n", + spi_nor_protocol_name(nor->reg_proto)); + + seq_puts(s, "\nerase commands\n"); + for (i = 0; i < SNOR_ERASE_TYPE_MAX; i++) { + struct spi_nor_erase_type *et = &erase_map->erase_type[i]; + + if (et->size) { + string_get_size(et->size, 1, STRING_UNITS_2, buf, + sizeof(buf)); + seq_printf(s, " %02x (%s) [%d]\n", et->opcode, buf, i); + } + } + + if (!(nor->flags & SNOR_F_NO_OP_CHIP_ERASE)) { + string_get_size(params->size, 1, STRING_UNITS_2, buf, sizeof(buf)); + seq_printf(s, " %02x (%s)\n", SPINOR_OP_CHIP_ERASE, buf); + } + + seq_puts(s, "\nsector map\n"); + seq_puts(s, " region (in hex) | erase mask | flags\n"); + seq_puts(s, " ------------------+------------+----------\n"); + for (region = erase_map->regions; + region; + region = spi_nor_region_next(region)) { + u64 start = region->offset & ~SNOR_ERASE_FLAGS_MASK; + u64 flags = region->offset & SNOR_ERASE_FLAGS_MASK; + u64 end = start + region->size - 1; + + seq_printf(s, " %08llx-%08llx | [%c%c%c%c] | %s\n", + start, end, + flags & BIT(0) ? '0' : ' ', + flags & BIT(1) ? '1' : ' ', + flags & BIT(2) ? '2' : ' ', + flags & BIT(3) ? '3' : ' ', + flags & SNOR_OVERLAID_REGION ? "overlaid" : ""); + } + + return 0; +} +DEFINE_SHOW_ATTRIBUTE(spi_nor_params); + +static void spi_nor_print_read_cmd(struct seq_file *s, u32 cap, + struct spi_nor_read_command *cmd) +{ + seq_printf(s, " %s%s\n", spi_nor_protocol_name(cmd->proto), + cap == SNOR_HWCAPS_READ_FAST ? " (fast read)" : ""); + seq_printf(s, " opcode\t0x%02x\n", cmd->opcode); + seq_printf(s, " mode cycles\t%u\n", cmd->num_mode_clocks); + seq_printf(s, " dummy cycles\t%u\n", cmd->num_wait_states); +} + +static void spi_nor_print_pp_cmd(struct seq_file *s, + struct spi_nor_pp_command *cmd) +{ + seq_printf(s, " %s\n", spi_nor_protocol_name(cmd->proto)); + seq_printf(s, " opcode\t0x%02x\n", cmd->opcode); +} + +static int spi_nor_capabilities_show(struct seq_file *s, void *data) +{ + struct spi_nor *nor = s->private; + struct spi_nor_flash_parameter *params = nor->params; + u32 hwcaps = params->hwcaps.mask; + int i, cmd; + + seq_puts(s, "Supported read modes by the flash\n"); + for (i = 0; i < sizeof(hwcaps) * BITS_PER_BYTE; i++) { + if (!(hwcaps & BIT(i))) + continue; + + cmd = spi_nor_hwcaps_read2cmd(BIT(i)); + if (cmd < 0) + continue; + + spi_nor_print_read_cmd(s, BIT(i), ¶ms->reads[cmd]); + hwcaps &= ~BIT(i); + } + + seq_puts(s, "\nSupported page program modes by the flash\n"); + for (i = 0; i < sizeof(hwcaps) * BITS_PER_BYTE; i++) { + if (!(hwcaps & BIT(i))) + continue; + + cmd = spi_nor_hwcaps_pp2cmd(BIT(i)); + if (cmd < 0) + continue; + + spi_nor_print_pp_cmd(s, ¶ms->page_programs[cmd]); + hwcaps &= ~BIT(i); + } + + if (hwcaps) + seq_printf(s, "\nunknown hwcaps 0x%x\n", hwcaps); + + return 0; +} +DEFINE_SHOW_ATTRIBUTE(spi_nor_capabilities); + +static void spi_nor_debugfs_unregister(void *data) +{ + struct spi_nor *nor = data; + + debugfs_remove(nor->debugfs_root); + nor->debugfs_root = NULL; +} + +void spi_nor_debugfs_register(struct spi_nor *nor) +{ + struct dentry *rootdir, *d; + int ret; + + /* Create rootdir once. Will never be deleted again. */ + rootdir = debugfs_lookup(SPI_NOR_DEBUGFS_ROOT, NULL); + if (!rootdir) + rootdir = debugfs_create_dir(SPI_NOR_DEBUGFS_ROOT, NULL); + + ret = devm_add_action(nor->dev, spi_nor_debugfs_unregister, nor); + if (ret) + return; + + d = debugfs_create_dir(dev_name(nor->dev), rootdir); + nor->debugfs_root = d; + + debugfs_create_file("params", 0444, d, nor, &spi_nor_params_fops); + debugfs_create_file("capabilities", 0444, d, nor, + &spi_nor_capabilities_fops); +} diff --git a/drivers/mtd/spi-nor/eon.c b/drivers/mtd/spi-nor/eon.c index 8c1c57530281..50a11053711f 100644 --- a/drivers/mtd/spi-nor/eon.c +++ b/drivers/mtd/spi-nor/eon.c @@ -25,7 +25,8 @@ static const struct flash_info eon_nor_parts[] = { { "en25qh64", INFO(0x1c7017, 0, 64 * 1024, 128) NO_SFDP_FLAGS(SECT_4K | SPI_NOR_DUAL_READ) }, { "en25qh128", INFO(0x1c7018, 0, 64 * 1024, 256) }, - { "en25qh256", INFO(0x1c7019, 0, 64 * 1024, 512) }, + { "en25qh256", INFO(0x1c7019, 0, 64 * 1024, 512) + PARSE_SFDP }, { "en25s64", INFO(0x1c3817, 0, 64 * 1024, 128) NO_SFDP_FLAGS(SECT_4K) }, }; diff --git a/drivers/mtd/spi-nor/micron-st.c b/drivers/mtd/spi-nor/micron-st.c index 8a20475ce77a..a96f74e0f568 100644 --- a/drivers/mtd/spi-nor/micron-st.c +++ b/drivers/mtd/spi-nor/micron-st.c @@ -28,82 +28,87 @@ #define FSR_P_ERR BIT(4) /* Program operation status */ #define FSR_PT_ERR BIT(1) /* Protection error bit */ -static int micron_st_nor_octal_dtr_enable(struct spi_nor *nor, bool enable) +/* Micron ST SPI NOR flash operations. */ +#define MICRON_ST_NOR_WR_ANY_REG_OP(naddr, addr, ndata, buf) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_MT_WR_ANY_REG, 0), \ + SPI_MEM_OP_ADDR(naddr, addr, 0), \ + SPI_MEM_OP_NO_DUMMY, \ + SPI_MEM_OP_DATA_OUT(ndata, buf, 0)) + +#define MICRON_ST_RDFSR_OP(buf) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_RDFSR, 0), \ + SPI_MEM_OP_NO_ADDR, \ + SPI_MEM_OP_NO_DUMMY, \ + SPI_MEM_OP_DATA_IN(1, buf, 0)) + +#define MICRON_ST_CLFSR_OP \ + SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_CLFSR, 0), \ + SPI_MEM_OP_NO_ADDR, \ + SPI_MEM_OP_NO_DUMMY, \ + SPI_MEM_OP_NO_DATA) + +static int micron_st_nor_octal_dtr_en(struct spi_nor *nor) { struct spi_mem_op op; u8 *buf = nor->bouncebuf; int ret; - if (enable) { - /* Use 20 dummy cycles for memory array reads. */ - ret = spi_nor_write_enable(nor); - if (ret) - return ret; - - *buf = 20; - op = (struct spi_mem_op) - SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_MT_WR_ANY_REG, 1), - SPI_MEM_OP_ADDR(3, SPINOR_REG_MT_CFR1V, 1), - SPI_MEM_OP_NO_DUMMY, - SPI_MEM_OP_DATA_OUT(1, buf, 1)); - - ret = spi_mem_exec_op(nor->spimem, &op); - if (ret) - return ret; - - ret = spi_nor_wait_till_ready(nor); - if (ret) - return ret; - } + /* Use 20 dummy cycles for memory array reads. */ + *buf = 20; + op = (struct spi_mem_op) + MICRON_ST_NOR_WR_ANY_REG_OP(3, SPINOR_REG_MT_CFR1V, 1, buf); + ret = spi_nor_write_any_volatile_reg(nor, &op, nor->reg_proto); + if (ret) + return ret; - ret = spi_nor_write_enable(nor); + buf[0] = SPINOR_MT_OCT_DTR; + op = (struct spi_mem_op) + MICRON_ST_NOR_WR_ANY_REG_OP(3, SPINOR_REG_MT_CFR0V, 1, buf); + ret = spi_nor_write_any_volatile_reg(nor, &op, nor->reg_proto); if (ret) return ret; - if (enable) { - buf[0] = SPINOR_MT_OCT_DTR; - } else { - /* - * The register is 1-byte wide, but 1-byte transactions are not - * allowed in 8D-8D-8D mode. The next register is the dummy - * cycle configuration register. Since the transaction needs to - * be at least 2 bytes wide, set the next register to its - * default value. This also makes sense because the value was - * changed when enabling 8D-8D-8D mode, it should be reset when - * disabling. - */ - buf[0] = SPINOR_MT_EXSPI; - buf[1] = SPINOR_REG_MT_CFR1V_DEF; + /* Read flash ID to make sure the switch was successful. */ + ret = spi_nor_read_id(nor, 0, 8, buf, SNOR_PROTO_8_8_8_DTR); + if (ret) { + dev_dbg(nor->dev, "error %d reading JEDEC ID after enabling 8D-8D-8D mode\n", ret); + return ret; } - op = (struct spi_mem_op) - SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_MT_WR_ANY_REG, 1), - SPI_MEM_OP_ADDR(enable ? 3 : 4, - SPINOR_REG_MT_CFR0V, 1), - SPI_MEM_OP_NO_DUMMY, - SPI_MEM_OP_DATA_OUT(enable ? 1 : 2, buf, 1)); + if (memcmp(buf, nor->info->id, nor->info->id_len)) + return -EINVAL; - if (!enable) - spi_nor_spimem_setup_op(nor, &op, SNOR_PROTO_8_8_8_DTR); + return 0; +} - ret = spi_mem_exec_op(nor->spimem, &op); +static int micron_st_nor_octal_dtr_dis(struct spi_nor *nor) +{ + struct spi_mem_op op; + u8 *buf = nor->bouncebuf; + int ret; + + /* + * The register is 1-byte wide, but 1-byte transactions are not allowed + * in 8D-8D-8D mode. The next register is the dummy cycle configuration + * register. Since the transaction needs to be at least 2 bytes wide, + * set the next register to its default value. This also makes sense + * because the value was changed when enabling 8D-8D-8D mode, it should + * be reset when disabling. + */ + buf[0] = SPINOR_MT_EXSPI; + buf[1] = SPINOR_REG_MT_CFR1V_DEF; + op = (struct spi_mem_op) + MICRON_ST_NOR_WR_ANY_REG_OP(4, SPINOR_REG_MT_CFR0V, 2, buf); + ret = spi_nor_write_any_volatile_reg(nor, &op, SNOR_PROTO_8_8_8_DTR); if (ret) return ret; /* Read flash ID to make sure the switch was successful. */ - op = (struct spi_mem_op) - SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_RDID, 1), - SPI_MEM_OP_NO_ADDR, - SPI_MEM_OP_DUMMY(enable ? 8 : 0, 1), - SPI_MEM_OP_DATA_IN(round_up(nor->info->id_len, 2), - buf, 1)); - - if (enable) - spi_nor_spimem_setup_op(nor, &op, SNOR_PROTO_8_8_8_DTR); - - ret = spi_mem_exec_op(nor->spimem, &op); - if (ret) + ret = spi_nor_read_id(nor, 0, 0, buf, SNOR_PROTO_1_1_1); + if (ret) { + dev_dbg(nor->dev, "error %d reading JEDEC ID after disabling 8D-8D-8D mode\n", ret); return ret; + } if (memcmp(buf, nor->info->id, nor->info->id_len)) return -EINVAL; @@ -111,6 +116,12 @@ static int micron_st_nor_octal_dtr_enable(struct spi_nor *nor, bool enable) return 0; } +static int micron_st_nor_octal_dtr_enable(struct spi_nor *nor, bool enable) +{ + return enable ? micron_st_nor_octal_dtr_en(nor) : + micron_st_nor_octal_dtr_dis(nor); +} + static void mt35xu512aba_default_init(struct spi_nor *nor) { nor->params->octal_dtr_enable = micron_st_nor_octal_dtr_enable; @@ -322,11 +333,7 @@ static int micron_st_nor_read_fsr(struct spi_nor *nor, u8 *fsr) int ret; if (nor->spimem) { - struct spi_mem_op op = - SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_RDFSR, 0), - SPI_MEM_OP_NO_ADDR, - SPI_MEM_OP_NO_DUMMY, - SPI_MEM_OP_DATA_IN(1, fsr, 0)); + struct spi_mem_op op = MICRON_ST_RDFSR_OP(fsr); if (nor->reg_proto == SNOR_PROTO_8_8_8_DTR) { op.addr.nbytes = nor->params->rdsr_addr_nbytes; @@ -361,11 +368,7 @@ static void micron_st_nor_clear_fsr(struct spi_nor *nor) int ret; if (nor->spimem) { - struct spi_mem_op op = - SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_CLFSR, 0), - SPI_MEM_OP_NO_ADDR, - SPI_MEM_OP_NO_DUMMY, - SPI_MEM_OP_NO_DATA); + struct spi_mem_op op = MICRON_ST_CLFSR_OP; spi_nor_spimem_setup_op(nor, &op, nor->reg_proto); diff --git a/drivers/mtd/spi-nor/spansion.c b/drivers/mtd/spi-nor/spansion.c index f24e546e04a5..43cd6cd92537 100644 --- a/drivers/mtd/spi-nor/spansion.c +++ b/drivers/mtd/spi-nor/spansion.c @@ -23,94 +23,89 @@ #define SPINOR_REG_CYPRESS_CFR5V_OCT_DTR_DS 0 #define SPINOR_OP_CYPRESS_RD_FAST 0xee -/** - * cypress_nor_octal_dtr_enable() - Enable octal DTR on Cypress flashes. - * @nor: pointer to a 'struct spi_nor' - * @enable: whether to enable or disable Octal DTR - * - * This also sets the memory access latency cycles to 24 to allow the flash to - * run at up to 200MHz. - * - * Return: 0 on success, -errno otherwise. - */ -static int cypress_nor_octal_dtr_enable(struct spi_nor *nor, bool enable) +/* Cypress SPI NOR flash operations. */ +#define CYPRESS_NOR_WR_ANY_REG_OP(naddr, addr, ndata, buf) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_WR_ANY_REG, 0), \ + SPI_MEM_OP_ADDR(naddr, addr, 0), \ + SPI_MEM_OP_NO_DUMMY, \ + SPI_MEM_OP_DATA_OUT(ndata, buf, 0)) + +#define CYPRESS_NOR_RD_ANY_REG_OP(naddr, addr, buf) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_RD_ANY_REG, 0), \ + SPI_MEM_OP_ADDR(naddr, addr, 0), \ + SPI_MEM_OP_NO_DUMMY, \ + SPI_MEM_OP_DATA_IN(1, buf, 0)) + +#define SPANSION_CLSR_OP \ + SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_CLSR, 0), \ + SPI_MEM_OP_NO_ADDR, \ + SPI_MEM_OP_NO_DUMMY, \ + SPI_MEM_OP_NO_DATA) + +static int cypress_nor_octal_dtr_en(struct spi_nor *nor) { struct spi_mem_op op; u8 *buf = nor->bouncebuf; int ret; - if (enable) { - /* Use 24 dummy cycles for memory array reads. */ - ret = spi_nor_write_enable(nor); - if (ret) - return ret; - - *buf = SPINOR_REG_CYPRESS_CFR2V_MEMLAT_11_24; - op = (struct spi_mem_op) - SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_WR_ANY_REG, 1), - SPI_MEM_OP_ADDR(3, SPINOR_REG_CYPRESS_CFR2V, - 1), - SPI_MEM_OP_NO_DUMMY, - SPI_MEM_OP_DATA_OUT(1, buf, 1)); + /* Use 24 dummy cycles for memory array reads. */ + *buf = SPINOR_REG_CYPRESS_CFR2V_MEMLAT_11_24; + op = (struct spi_mem_op) + CYPRESS_NOR_WR_ANY_REG_OP(3, SPINOR_REG_CYPRESS_CFR2V, 1, buf); - ret = spi_mem_exec_op(nor->spimem, &op); - if (ret) - return ret; + ret = spi_nor_write_any_volatile_reg(nor, &op, nor->reg_proto); + if (ret) + return ret; - ret = spi_nor_wait_till_ready(nor); - if (ret) - return ret; + nor->read_dummy = 24; - nor->read_dummy = 24; - } + /* Set the octal and DTR enable bits. */ + buf[0] = SPINOR_REG_CYPRESS_CFR5V_OCT_DTR_EN; + op = (struct spi_mem_op) + CYPRESS_NOR_WR_ANY_REG_OP(3, SPINOR_REG_CYPRESS_CFR5V, 1, buf); - /* Set/unset the octal and DTR enable bits. */ - ret = spi_nor_write_enable(nor); + ret = spi_nor_write_any_volatile_reg(nor, &op, nor->reg_proto); if (ret) return ret; - if (enable) { - buf[0] = SPINOR_REG_CYPRESS_CFR5V_OCT_DTR_EN; - } else { - /* - * The register is 1-byte wide, but 1-byte transactions are not - * allowed in 8D-8D-8D mode. Since there is no register at the - * next location, just initialize the value to 0 and let the - * transaction go on. - */ - buf[0] = SPINOR_REG_CYPRESS_CFR5V_OCT_DTR_DS; - buf[1] = 0; + /* Read flash ID to make sure the switch was successful. */ + ret = spi_nor_read_id(nor, 4, 3, buf, SNOR_PROTO_8_8_8_DTR); + if (ret) { + dev_dbg(nor->dev, "error %d reading JEDEC ID after enabling 8D-8D-8D mode\n", ret); + return ret; } - op = (struct spi_mem_op) - SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_WR_ANY_REG, 1), - SPI_MEM_OP_ADDR(enable ? 3 : 4, - SPINOR_REG_CYPRESS_CFR5V, - 1), - SPI_MEM_OP_NO_DUMMY, - SPI_MEM_OP_DATA_OUT(enable ? 1 : 2, buf, 1)); + if (memcmp(buf, nor->info->id, nor->info->id_len)) + return -EINVAL; - if (!enable) - spi_nor_spimem_setup_op(nor, &op, SNOR_PROTO_8_8_8_DTR); + return 0; +} - ret = spi_mem_exec_op(nor->spimem, &op); +static int cypress_nor_octal_dtr_dis(struct spi_nor *nor) +{ + struct spi_mem_op op; + u8 *buf = nor->bouncebuf; + int ret; + + /* + * The register is 1-byte wide, but 1-byte transactions are not allowed + * in 8D-8D-8D mode. Since there is no register at the next location, + * just initialize the value to 0 and let the transaction go on. + */ + buf[0] = SPINOR_REG_CYPRESS_CFR5V_OCT_DTR_DS; + buf[1] = 0; + op = (struct spi_mem_op) + CYPRESS_NOR_WR_ANY_REG_OP(4, SPINOR_REG_CYPRESS_CFR5V, 2, buf); + ret = spi_nor_write_any_volatile_reg(nor, &op, SNOR_PROTO_8_8_8_DTR); if (ret) return ret; /* Read flash ID to make sure the switch was successful. */ - op = (struct spi_mem_op) - SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_RDID, 1), - SPI_MEM_OP_ADDR(enable ? 4 : 0, 0, 1), - SPI_MEM_OP_DUMMY(enable ? 3 : 0, 1), - SPI_MEM_OP_DATA_IN(round_up(nor->info->id_len, 2), - buf, 1)); - - if (enable) - spi_nor_spimem_setup_op(nor, &op, SNOR_PROTO_8_8_8_DTR); - - ret = spi_mem_exec_op(nor->spimem, &op); - if (ret) + ret = spi_nor_read_id(nor, 0, 0, buf, SNOR_PROTO_1_1_1); + if (ret) { + dev_dbg(nor->dev, "error %d reading JEDEC ID after disabling 8D-8D-8D mode\n", ret); return ret; + } if (memcmp(buf, nor->info->id, nor->info->id_len)) return -EINVAL; @@ -118,6 +113,22 @@ static int cypress_nor_octal_dtr_enable(struct spi_nor *nor, bool enable) return 0; } +/** + * cypress_nor_octal_dtr_enable() - Enable octal DTR on Cypress flashes. + * @nor: pointer to a 'struct spi_nor' + * @enable: whether to enable or disable Octal DTR + * + * This also sets the memory access latency cycles to 24 to allow the flash to + * run at up to 200MHz. + * + * Return: 0 on success, -errno otherwise. + */ +static int cypress_nor_octal_dtr_enable(struct spi_nor *nor, bool enable) +{ + return enable ? cypress_nor_octal_dtr_en(nor) : + cypress_nor_octal_dtr_dis(nor); +} + static void s28hs512t_default_init(struct spi_nor *nor) { nor->params->octal_dtr_enable = cypress_nor_octal_dtr_enable; @@ -162,12 +173,12 @@ static int s28hs512t_post_bfpt_fixup(struct spi_nor *nor, * CFR3V[4] and set the correct size. */ struct spi_mem_op op = - SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_RD_ANY_REG, 1), - SPI_MEM_OP_ADDR(3, SPINOR_REG_CYPRESS_CFR3V, 1), - SPI_MEM_OP_NO_DUMMY, - SPI_MEM_OP_DATA_IN(1, nor->bouncebuf, 1)); + CYPRESS_NOR_RD_ANY_REG_OP(3, SPINOR_REG_CYPRESS_CFR3V, + nor->bouncebuf); int ret; + spi_nor_spimem_setup_op(nor, &op, nor->reg_proto); + ret = spi_mem_exec_op(nor->spimem, &op); if (ret) return ret; @@ -317,11 +328,7 @@ static void spansion_nor_clear_sr(struct spi_nor *nor) int ret; if (nor->spimem) { - struct spi_mem_op op = - SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_CLSR, 0), - SPI_MEM_OP_NO_ADDR, - SPI_MEM_OP_NO_DUMMY, - SPI_MEM_OP_NO_DATA); + struct spi_mem_op op = SPANSION_CLSR_OP; spi_nor_spimem_setup_op(nor, &op, nor->reg_proto); diff --git a/drivers/mtd/spi-nor/winbond.c b/drivers/mtd/spi-nor/winbond.c index fe80dffc2e70..ffaa24055259 100644 --- a/drivers/mtd/spi-nor/winbond.c +++ b/drivers/mtd/spi-nor/winbond.c @@ -8,6 +8,15 @@ #include "core.h" +#define WINBOND_NOR_OP_RDEAR 0xc8 /* Read Extended Address Register */ +#define WINBOND_NOR_OP_WREAR 0xc5 /* Write Extended Address Register */ + +#define WINBOND_NOR_WREAR_OP(buf) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(WINBOND_NOR_OP_WREAR, 0), \ + SPI_MEM_OP_NO_ADDR, \ + SPI_MEM_OP_NO_DUMMY, \ + SPI_MEM_OP_DATA_OUT(1, buf, 0)) + static int w25q256_post_bfpt_fixups(struct spi_nor *nor, const struct sfdp_parameter_header *bfpt_header, @@ -124,12 +133,46 @@ static const struct flash_info winbond_nor_parts[] = { { "w25m512jv", INFO(0xef7119, 0, 64 * 1024, 1024) NO_SFDP_FLAGS(SECT_4K | SPI_NOR_QUAD_READ | SPI_NOR_DUAL_READ) }, + { "w25q512nwm", INFO(0xef8020, 0, 64 * 1024, 1024) + PARSE_SFDP + OTP_INFO(256, 3, 0x1000, 0x1000) }, { "w25q512jvq", INFO(0xef4020, 0, 64 * 1024, 1024) NO_SFDP_FLAGS(SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ) }, }; /** + * winbond_nor_write_ear() - Write Extended Address Register. + * @nor: pointer to 'struct spi_nor'. + * @ear: value to write to the Extended Address Register. + * + * Return: 0 on success, -errno otherwise. + */ +static int winbond_nor_write_ear(struct spi_nor *nor, u8 ear) +{ + int ret; + + nor->bouncebuf[0] = ear; + + if (nor->spimem) { + struct spi_mem_op op = WINBOND_NOR_WREAR_OP(nor->bouncebuf); + + spi_nor_spimem_setup_op(nor, &op, nor->reg_proto); + + ret = spi_mem_exec_op(nor->spimem, &op); + } else { + ret = spi_nor_controller_ops_write_reg(nor, + WINBOND_NOR_OP_WREAR, + nor->bouncebuf, 1); + } + + if (ret) + dev_dbg(nor->dev, "error %d writing EAR\n", ret); + + return ret; +} + +/** * winbond_nor_set_4byte_addr_mode() - Set 4-byte address mode for Winbond * flashes. * @nor: pointer to 'struct spi_nor'. @@ -155,7 +198,7 @@ static int winbond_nor_set_4byte_addr_mode(struct spi_nor *nor, bool enable) if (ret) return ret; - ret = spi_nor_write_ear(nor, 0); + ret = winbond_nor_write_ear(nor, 0); if (ret) return ret; diff --git a/drivers/mtd/spi-nor/xilinx.c b/drivers/mtd/spi-nor/xilinx.c index 9459ac2609dc..1d2f5db047bd 100644 --- a/drivers/mtd/spi-nor/xilinx.c +++ b/drivers/mtd/spi-nor/xilinx.c @@ -15,6 +15,12 @@ #define XSR_PAGESIZE BIT(0) /* Page size in Po2 or Linear */ #define XSR_RDY BIT(7) /* Ready */ +#define XILINX_RDSR_OP(buf) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(XILINX_OP_RDSR, 0), \ + SPI_MEM_OP_NO_ADDR, \ + SPI_MEM_OP_NO_DUMMY, \ + SPI_MEM_OP_DATA_IN(1, buf, 0)) + #define S3AN_INFO(_jedec_id, _n_sectors, _page_size) \ .id = { \ ((_jedec_id) >> 16) & 0xff, \ @@ -72,11 +78,7 @@ static int xilinx_nor_read_sr(struct spi_nor *nor, u8 *sr) int ret; if (nor->spimem) { - struct spi_mem_op op = - SPI_MEM_OP(SPI_MEM_OP_CMD(XILINX_OP_RDSR, 0), - SPI_MEM_OP_NO_ADDR, - SPI_MEM_OP_NO_DUMMY, - SPI_MEM_OP_DATA_IN(1, sr, 0)); + struct spi_mem_op op = XILINX_RDSR_OP(sr); spi_nor_spimem_setup_op(nor, &op, nor->reg_proto); diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 15eddca7b4b6..38e152548126 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -4027,14 +4027,19 @@ static bool bond_flow_dissect(struct bonding *bond, struct sk_buff *skb, const v return true; } -static u32 bond_ip_hash(u32 hash, struct flow_keys *flow) +static u32 bond_ip_hash(u32 hash, struct flow_keys *flow, int xmit_policy) { hash ^= (__force u32)flow_get_u32_dst(flow) ^ (__force u32)flow_get_u32_src(flow); hash ^= (hash >> 16); hash ^= (hash >> 8); + /* discard lowest hash bit to deal with the common even ports pattern */ - return hash >> 1; + if (xmit_policy == BOND_XMIT_POLICY_LAYER34 || + xmit_policy == BOND_XMIT_POLICY_ENCAP34) + return hash >> 1; + + return hash; } /* Generate hash based on xmit policy. If @skb is given it is used to linearize @@ -4064,7 +4069,7 @@ static u32 __bond_xmit_hash(struct bonding *bond, struct sk_buff *skb, const voi memcpy(&hash, &flow.ports.ports, sizeof(hash)); } - return bond_ip_hash(hash, &flow); + return bond_ip_hash(hash, &flow, bond->params.xmit_policy); } /** @@ -5259,7 +5264,7 @@ static u32 bond_sk_hash_l34(struct sock *sk) /* L4 */ memcpy(&hash, &flow.ports.ports, sizeof(hash)); /* L3 */ - return bond_ip_hash(hash, &flow); + return bond_ip_hash(hash, &flow, BOND_XMIT_POLICY_LAYER34); } static struct net_device *__bond_sk_get_lower_dev(struct bonding *bond, diff --git a/drivers/net/can/grcan.c b/drivers/net/can/grcan.c index d0c5a7a60daf..5215bd9b2c80 100644 --- a/drivers/net/can/grcan.c +++ b/drivers/net/can/grcan.c @@ -241,13 +241,14 @@ struct grcan_device_config { .rxsize = GRCAN_DEFAULT_BUFFER_SIZE, \ } -#define GRCAN_TXBUG_SAFE_GRLIB_VERSION 0x4100 +#define GRCAN_TXBUG_SAFE_GRLIB_VERSION 4100 #define GRLIB_VERSION_MASK 0xffff /* GRCAN private data structure */ struct grcan_priv { struct can_priv can; /* must be the first member */ struct net_device *dev; + struct device *ofdev_dev; struct napi_struct napi; struct grcan_registers __iomem *regs; /* ioremap'ed registers */ @@ -921,7 +922,7 @@ static void grcan_free_dma_buffers(struct net_device *dev) struct grcan_priv *priv = netdev_priv(dev); struct grcan_dma *dma = &priv->dma; - dma_free_coherent(&dev->dev, dma->base_size, dma->base_buf, + dma_free_coherent(priv->ofdev_dev, dma->base_size, dma->base_buf, dma->base_handle); memset(dma, 0, sizeof(*dma)); } @@ -946,7 +947,7 @@ static int grcan_allocate_dma_buffers(struct net_device *dev, /* Extra GRCAN_BUFFER_ALIGNMENT to allow for alignment */ dma->base_size = lsize + ssize + GRCAN_BUFFER_ALIGNMENT; - dma->base_buf = dma_alloc_coherent(&dev->dev, + dma->base_buf = dma_alloc_coherent(priv->ofdev_dev, dma->base_size, &dma->base_handle, GFP_KERNEL); @@ -1102,8 +1103,10 @@ static int grcan_close(struct net_device *dev) priv->closing = true; if (priv->need_txbug_workaround) { + spin_unlock_irqrestore(&priv->lock, flags); del_timer_sync(&priv->hang_timer); del_timer_sync(&priv->rr_timer); + spin_lock_irqsave(&priv->lock, flags); } netif_stop_queue(dev); grcan_stop_hardware(dev); @@ -1122,7 +1125,7 @@ static int grcan_close(struct net_device *dev) return 0; } -static int grcan_transmit_catch_up(struct net_device *dev, int budget) +static void grcan_transmit_catch_up(struct net_device *dev) { struct grcan_priv *priv = netdev_priv(dev); unsigned long flags; @@ -1130,7 +1133,7 @@ static int grcan_transmit_catch_up(struct net_device *dev, int budget) spin_lock_irqsave(&priv->lock, flags); - work_done = catch_up_echo_skb(dev, budget, true); + work_done = catch_up_echo_skb(dev, -1, true); if (work_done) { if (!priv->resetting && !priv->closing && !(priv->can.ctrlmode & CAN_CTRLMODE_LISTENONLY)) @@ -1144,8 +1147,6 @@ static int grcan_transmit_catch_up(struct net_device *dev, int budget) } spin_unlock_irqrestore(&priv->lock, flags); - - return work_done; } static int grcan_receive(struct net_device *dev, int budget) @@ -1227,19 +1228,13 @@ static int grcan_poll(struct napi_struct *napi, int budget) struct net_device *dev = priv->dev; struct grcan_registers __iomem *regs = priv->regs; unsigned long flags; - int tx_work_done, rx_work_done; - int rx_budget = budget / 2; - int tx_budget = budget - rx_budget; + int work_done; - /* Half of the budget for receiving messages */ - rx_work_done = grcan_receive(dev, rx_budget); + work_done = grcan_receive(dev, budget); - /* Half of the budget for transmitting messages as that can trigger echo - * frames being received - */ - tx_work_done = grcan_transmit_catch_up(dev, tx_budget); + grcan_transmit_catch_up(dev); - if (rx_work_done < rx_budget && tx_work_done < tx_budget) { + if (work_done < budget) { napi_complete(napi); /* Guarantee no interference with a running reset that otherwise @@ -1256,7 +1251,7 @@ static int grcan_poll(struct napi_struct *napi, int budget) spin_unlock_irqrestore(&priv->lock, flags); } - return rx_work_done + tx_work_done; + return work_done; } /* Work tx bug by waiting while for the risky situation to clear. If that fails, @@ -1587,6 +1582,7 @@ static int grcan_setup_netdev(struct platform_device *ofdev, memcpy(&priv->config, &grcan_module_config, sizeof(struct grcan_device_config)); priv->dev = dev; + priv->ofdev_dev = &ofdev->dev; priv->regs = base; priv->can.bittiming_const = &grcan_bittiming_const; priv->can.do_set_bittiming = grcan_set_bittiming; @@ -1639,6 +1635,7 @@ exit_free_candev: static int grcan_probe(struct platform_device *ofdev) { struct device_node *np = ofdev->dev.of_node; + struct device_node *sysid_parent; u32 sysid, ambafreq; int irq, err; void __iomem *base; @@ -1647,10 +1644,15 @@ static int grcan_probe(struct platform_device *ofdev) /* Compare GRLIB version number with the first that does not * have the tx bug (see start_xmit) */ - err = of_property_read_u32(np, "systemid", &sysid); - if (!err && ((sysid & GRLIB_VERSION_MASK) - >= GRCAN_TXBUG_SAFE_GRLIB_VERSION)) - txbug = false; + sysid_parent = of_find_node_by_path("/ambapp0"); + if (sysid_parent) { + of_node_get(sysid_parent); + err = of_property_read_u32(sysid_parent, "systemid", &sysid); + if (!err && ((sysid & GRLIB_VERSION_MASK) >= + GRCAN_TXBUG_SAFE_GRLIB_VERSION)) + txbug = false; + of_node_put(sysid_parent); + } err = of_property_read_u32(np, "freq", &ambafreq); if (err) { diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c index b3b5bc1c803b..088bb1bcf1ef 100644 --- a/drivers/net/can/m_can/m_can.c +++ b/drivers/net/can/m_can/m_can.c @@ -1495,34 +1495,22 @@ static int m_can_dev_setup(struct m_can_classdev *cdev) err = can_set_static_ctrlmode(dev, CAN_CTRLMODE_FD_NON_ISO); if (err) return err; - cdev->can.bittiming_const = cdev->bit_timing ? - cdev->bit_timing : &m_can_bittiming_const_30X; - - cdev->can.data_bittiming_const = cdev->data_timing ? - cdev->data_timing : - &m_can_data_bittiming_const_30X; + cdev->can.bittiming_const = &m_can_bittiming_const_30X; + cdev->can.data_bittiming_const = &m_can_data_bittiming_const_30X; break; case 31: /* CAN_CTRLMODE_FD_NON_ISO is fixed with M_CAN IP v3.1.x */ err = can_set_static_ctrlmode(dev, CAN_CTRLMODE_FD_NON_ISO); if (err) return err; - cdev->can.bittiming_const = cdev->bit_timing ? - cdev->bit_timing : &m_can_bittiming_const_31X; - - cdev->can.data_bittiming_const = cdev->data_timing ? - cdev->data_timing : - &m_can_data_bittiming_const_31X; + cdev->can.bittiming_const = &m_can_bittiming_const_31X; + cdev->can.data_bittiming_const = &m_can_data_bittiming_const_31X; break; case 32: case 33: /* Support both MCAN version v3.2.x and v3.3.0 */ - cdev->can.bittiming_const = cdev->bit_timing ? - cdev->bit_timing : &m_can_bittiming_const_31X; - - cdev->can.data_bittiming_const = cdev->data_timing ? - cdev->data_timing : - &m_can_data_bittiming_const_31X; + cdev->can.bittiming_const = &m_can_bittiming_const_31X; + cdev->can.data_bittiming_const = &m_can_data_bittiming_const_31X; cdev->can.ctrlmode_supported |= (m_can_niso_supported(cdev) ? diff --git a/drivers/net/can/m_can/m_can.h b/drivers/net/can/m_can/m_can.h index 2c5d40997168..d18b515e6ccc 100644 --- a/drivers/net/can/m_can/m_can.h +++ b/drivers/net/can/m_can/m_can.h @@ -85,9 +85,6 @@ struct m_can_classdev { struct sk_buff *tx_skb; struct phy *transceiver; - const struct can_bittiming_const *bit_timing; - const struct can_bittiming_const *data_timing; - struct m_can_ops *ops; int version; diff --git a/drivers/net/can/m_can/m_can_pci.c b/drivers/net/can/m_can/m_can_pci.c index b56a54d6c5a9..8f184a852a0a 100644 --- a/drivers/net/can/m_can/m_can_pci.c +++ b/drivers/net/can/m_can/m_can_pci.c @@ -18,14 +18,9 @@ #define M_CAN_PCI_MMIO_BAR 0 +#define M_CAN_CLOCK_FREQ_EHL 200000000 #define CTL_CSR_INT_CTL_OFFSET 0x508 -struct m_can_pci_config { - const struct can_bittiming_const *bit_timing; - const struct can_bittiming_const *data_timing; - unsigned int clock_freq; -}; - struct m_can_pci_priv { struct m_can_classdev cdev; @@ -89,40 +84,9 @@ static struct m_can_ops m_can_pci_ops = { .read_fifo = iomap_read_fifo, }; -static const struct can_bittiming_const m_can_bittiming_const_ehl = { - .name = KBUILD_MODNAME, - .tseg1_min = 2, /* Time segment 1 = prop_seg + phase_seg1 */ - .tseg1_max = 64, - .tseg2_min = 1, /* Time segment 2 = phase_seg2 */ - .tseg2_max = 128, - .sjw_max = 128, - .brp_min = 1, - .brp_max = 512, - .brp_inc = 1, -}; - -static const struct can_bittiming_const m_can_data_bittiming_const_ehl = { - .name = KBUILD_MODNAME, - .tseg1_min = 2, /* Time segment 1 = prop_seg + phase_seg1 */ - .tseg1_max = 16, - .tseg2_min = 1, /* Time segment 2 = phase_seg2 */ - .tseg2_max = 8, - .sjw_max = 4, - .brp_min = 1, - .brp_max = 32, - .brp_inc = 1, -}; - -static const struct m_can_pci_config m_can_pci_ehl = { - .bit_timing = &m_can_bittiming_const_ehl, - .data_timing = &m_can_data_bittiming_const_ehl, - .clock_freq = 200000000, -}; - static int m_can_pci_probe(struct pci_dev *pci, const struct pci_device_id *id) { struct device *dev = &pci->dev; - const struct m_can_pci_config *cfg; struct m_can_classdev *mcan_class; struct m_can_pci_priv *priv; void __iomem *base; @@ -150,8 +114,6 @@ static int m_can_pci_probe(struct pci_dev *pci, const struct pci_device_id *id) if (!mcan_class) return -ENOMEM; - cfg = (const struct m_can_pci_config *)id->driver_data; - priv = cdev_to_priv(mcan_class); priv->base = base; @@ -163,9 +125,7 @@ static int m_can_pci_probe(struct pci_dev *pci, const struct pci_device_id *id) mcan_class->dev = &pci->dev; mcan_class->net->irq = pci_irq_vector(pci, 0); mcan_class->pm_clock_support = 1; - mcan_class->bit_timing = cfg->bit_timing; - mcan_class->data_timing = cfg->data_timing; - mcan_class->can.clock.freq = cfg->clock_freq; + mcan_class->can.clock.freq = id->driver_data; mcan_class->ops = &m_can_pci_ops; pci_set_drvdata(pci, mcan_class); @@ -218,8 +178,8 @@ static SIMPLE_DEV_PM_OPS(m_can_pci_pm_ops, m_can_pci_suspend, m_can_pci_resume); static const struct pci_device_id m_can_pci_id_table[] = { - { PCI_VDEVICE(INTEL, 0x4bc1), (kernel_ulong_t)&m_can_pci_ehl, }, - { PCI_VDEVICE(INTEL, 0x4bc2), (kernel_ulong_t)&m_can_pci_ehl, }, + { PCI_VDEVICE(INTEL, 0x4bc1), M_CAN_CLOCK_FREQ_EHL, }, + { PCI_VDEVICE(INTEL, 0x4bc2), M_CAN_CLOCK_FREQ_EHL, }, { } /* Terminating Entry */ }; MODULE_DEVICE_TABLE(pci, m_can_pci_id_table); diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index 77501f9c5915..fbb32aa49b24 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -1354,46 +1354,25 @@ static void b53_phylink_get_caps(struct dsa_switch *ds, int port, config->legacy_pre_march2020 = false; } -int b53_phylink_mac_link_state(struct dsa_switch *ds, int port, - struct phylink_link_state *state) +static struct phylink_pcs *b53_phylink_mac_select_pcs(struct dsa_switch *ds, + int port, + phy_interface_t interface) { struct b53_device *dev = ds->priv; - int ret = -EOPNOTSUPP; - if ((phy_interface_mode_is_8023z(state->interface) || - state->interface == PHY_INTERFACE_MODE_SGMII) && - dev->ops->serdes_link_state) - ret = dev->ops->serdes_link_state(dev, port, state); + if (!dev->ops->phylink_mac_select_pcs) + return NULL; - return ret; + return dev->ops->phylink_mac_select_pcs(dev, port, interface); } -EXPORT_SYMBOL(b53_phylink_mac_link_state); void b53_phylink_mac_config(struct dsa_switch *ds, int port, unsigned int mode, const struct phylink_link_state *state) { - struct b53_device *dev = ds->priv; - - if (mode == MLO_AN_PHY || mode == MLO_AN_FIXED) - return; - - if ((phy_interface_mode_is_8023z(state->interface) || - state->interface == PHY_INTERFACE_MODE_SGMII) && - dev->ops->serdes_config) - dev->ops->serdes_config(dev, port, mode, state); } EXPORT_SYMBOL(b53_phylink_mac_config); -void b53_phylink_mac_an_restart(struct dsa_switch *ds, int port) -{ - struct b53_device *dev = ds->priv; - - if (dev->ops->serdes_an_restart) - dev->ops->serdes_an_restart(dev, port); -} -EXPORT_SYMBOL(b53_phylink_mac_an_restart); - void b53_phylink_mac_link_down(struct dsa_switch *ds, int port, unsigned int mode, phy_interface_t interface) @@ -2269,9 +2248,8 @@ static const struct dsa_switch_ops b53_switch_ops = { .phy_write = b53_phy_write16, .adjust_link = b53_adjust_link, .phylink_get_caps = b53_phylink_get_caps, - .phylink_mac_link_state = b53_phylink_mac_link_state, + .phylink_mac_select_pcs = b53_phylink_mac_select_pcs, .phylink_mac_config = b53_phylink_mac_config, - .phylink_mac_an_restart = b53_phylink_mac_an_restart, .phylink_mac_link_down = b53_phylink_mac_link_down, .phylink_mac_link_up = b53_phylink_mac_link_up, .port_enable = b53_enable_port, diff --git a/drivers/net/dsa/b53/b53_priv.h b/drivers/net/dsa/b53/b53_priv.h index 3085b6cc7d40..795cbffd5c2b 100644 --- a/drivers/net/dsa/b53/b53_priv.h +++ b/drivers/net/dsa/b53/b53_priv.h @@ -21,7 +21,7 @@ #include <linux/kernel.h> #include <linux/mutex.h> -#include <linux/phy.h> +#include <linux/phylink.h> #include <linux/etherdevice.h> #include <net/dsa.h> @@ -29,7 +29,6 @@ struct b53_device; struct net_device; -struct phylink_link_state; struct b53_io_ops { int (*read8)(struct b53_device *dev, u8 page, u8 reg, u8 *value); @@ -48,13 +47,10 @@ struct b53_io_ops { void (*irq_disable)(struct b53_device *dev, int port); void (*phylink_get_caps)(struct b53_device *dev, int port, struct phylink_config *config); + struct phylink_pcs *(*phylink_mac_select_pcs)(struct b53_device *dev, + int port, + phy_interface_t interface); u8 (*serdes_map_lane)(struct b53_device *dev, int port); - int (*serdes_link_state)(struct b53_device *dev, int port, - struct phylink_link_state *state); - void (*serdes_config)(struct b53_device *dev, int port, - unsigned int mode, - const struct phylink_link_state *state); - void (*serdes_an_restart)(struct b53_device *dev, int port); void (*serdes_link_set)(struct b53_device *dev, int port, unsigned int mode, phy_interface_t interface, bool link_up); @@ -85,8 +81,15 @@ enum { BCM7278_DEVICE_ID = 0x7278, }; +struct b53_pcs { + struct phylink_pcs pcs; + struct b53_device *dev; + u8 lane; +}; + #define B53_N_PORTS 9 #define B53_N_PORTS_25 6 +#define B53_N_PCS 2 struct b53_port { u16 vlan_ctl_mask; @@ -143,6 +146,8 @@ struct b53_device { bool vlan_enabled; unsigned int num_ports; struct b53_port *ports; + + struct b53_pcs pcs[B53_N_PCS]; }; #define b53_for_each_port(dev, i) \ @@ -336,12 +341,9 @@ int b53_br_flags(struct dsa_switch *ds, int port, struct netlink_ext_ack *extack); int b53_setup_devlink_resources(struct dsa_switch *ds); void b53_port_event(struct dsa_switch *ds, int port); -int b53_phylink_mac_link_state(struct dsa_switch *ds, int port, - struct phylink_link_state *state); void b53_phylink_mac_config(struct dsa_switch *ds, int port, unsigned int mode, const struct phylink_link_state *state); -void b53_phylink_mac_an_restart(struct dsa_switch *ds, int port); void b53_phylink_mac_link_down(struct dsa_switch *ds, int port, unsigned int mode, phy_interface_t interface); diff --git a/drivers/net/dsa/b53/b53_serdes.c b/drivers/net/dsa/b53/b53_serdes.c index 555e5b372321..0690210770ff 100644 --- a/drivers/net/dsa/b53/b53_serdes.c +++ b/drivers/net/dsa/b53/b53_serdes.c @@ -17,6 +17,11 @@ #include "b53_serdes.h" #include "b53_regs.h" +static inline struct b53_pcs *pcs_to_b53_pcs(struct phylink_pcs *pcs) +{ + return container_of(pcs, struct b53_pcs, pcs); +} + static void b53_serdes_write_blk(struct b53_device *dev, u8 offset, u16 block, u16 value) { @@ -60,51 +65,47 @@ static u16 b53_serdes_read(struct b53_device *dev, u8 lane, return b53_serdes_read_blk(dev, offset, block); } -void b53_serdes_config(struct b53_device *dev, int port, unsigned int mode, - const struct phylink_link_state *state) +static int b53_serdes_config(struct phylink_pcs *pcs, unsigned int mode, + phy_interface_t interface, + const unsigned long *advertising, + bool permit_pause_to_mac) { - u8 lane = b53_serdes_map_lane(dev, port); + struct b53_device *dev = pcs_to_b53_pcs(pcs)->dev; + u8 lane = pcs_to_b53_pcs(pcs)->lane; u16 reg; - if (lane == B53_INVALID_LANE) - return; - reg = b53_serdes_read(dev, lane, B53_SERDES_DIGITAL_CONTROL(1), SERDES_DIGITAL_BLK); - if (state->interface == PHY_INTERFACE_MODE_1000BASEX) + if (interface == PHY_INTERFACE_MODE_1000BASEX) reg |= FIBER_MODE_1000X; else reg &= ~FIBER_MODE_1000X; b53_serdes_write(dev, lane, B53_SERDES_DIGITAL_CONTROL(1), SERDES_DIGITAL_BLK, reg); + + return 0; } -EXPORT_SYMBOL(b53_serdes_config); -void b53_serdes_an_restart(struct b53_device *dev, int port) +static void b53_serdes_an_restart(struct phylink_pcs *pcs) { - u8 lane = b53_serdes_map_lane(dev, port); + struct b53_device *dev = pcs_to_b53_pcs(pcs)->dev; + u8 lane = pcs_to_b53_pcs(pcs)->lane; u16 reg; - if (lane == B53_INVALID_LANE) - return; - reg = b53_serdes_read(dev, lane, B53_SERDES_MII_REG(MII_BMCR), SERDES_MII_BLK); reg |= BMCR_ANRESTART; b53_serdes_write(dev, lane, B53_SERDES_MII_REG(MII_BMCR), SERDES_MII_BLK, reg); } -EXPORT_SYMBOL(b53_serdes_an_restart); -int b53_serdes_link_state(struct b53_device *dev, int port, - struct phylink_link_state *state) +static void b53_serdes_get_state(struct phylink_pcs *pcs, + struct phylink_link_state *state) { - u8 lane = b53_serdes_map_lane(dev, port); + struct b53_device *dev = pcs_to_b53_pcs(pcs)->dev; + u8 lane = pcs_to_b53_pcs(pcs)->lane; u16 dig, bmsr; - if (lane == B53_INVALID_LANE) - return 1; - dig = b53_serdes_read(dev, lane, B53_SERDES_DIGITAL_STATUS, SERDES_DIGITAL_BLK); bmsr = b53_serdes_read(dev, lane, B53_SERDES_MII_REG(MII_BMSR), @@ -133,10 +134,7 @@ int b53_serdes_link_state(struct b53_device *dev, int port, state->pause |= MLO_PAUSE_RX; if (dig & PAUSE_RESOLUTION_TX_SIDE) state->pause |= MLO_PAUSE_TX; - - return 0; } -EXPORT_SYMBOL(b53_serdes_link_state); void b53_serdes_link_set(struct b53_device *dev, int port, unsigned int mode, phy_interface_t interface, bool link_up) @@ -158,6 +156,12 @@ void b53_serdes_link_set(struct b53_device *dev, int port, unsigned int mode, } EXPORT_SYMBOL(b53_serdes_link_set); +static const struct phylink_pcs_ops b53_pcs_ops = { + .pcs_get_state = b53_serdes_get_state, + .pcs_config = b53_serdes_config, + .pcs_an_restart = b53_serdes_an_restart, +}; + void b53_serdes_phylink_get_caps(struct b53_device *dev, int port, struct phylink_config *config) { @@ -187,9 +191,28 @@ void b53_serdes_phylink_get_caps(struct b53_device *dev, int port, } EXPORT_SYMBOL(b53_serdes_phylink_get_caps); +struct phylink_pcs *b53_serdes_phylink_mac_select_pcs(struct b53_device *dev, + int port, + phy_interface_t interface) +{ + u8 lane = b53_serdes_map_lane(dev, port); + + if (lane == B53_INVALID_LANE || lane >= B53_N_PCS || + !dev->pcs[lane].dev) + return NULL; + + if (!phy_interface_mode_is_8023z(interface) && + interface != PHY_INTERFACE_MODE_SGMII) + return NULL; + + return &dev->pcs[lane].pcs; +} +EXPORT_SYMBOL(b53_serdes_phylink_mac_select_pcs); + int b53_serdes_init(struct b53_device *dev, int port) { u8 lane = b53_serdes_map_lane(dev, port); + struct b53_pcs *pcs; u16 id0, msb, lsb; if (lane == B53_INVALID_LANE) @@ -212,6 +235,11 @@ int b53_serdes_init(struct b53_device *dev, int port) (id0 >> SERDES_ID0_REV_NUM_SHIFT) & SERDES_ID0_REV_NUM_MASK, (u32)msb << 16 | lsb); + pcs = &dev->pcs[lane]; + pcs->dev = dev; + pcs->lane = lane; + pcs->pcs.ops = &b53_pcs_ops; + return 0; } EXPORT_SYMBOL(b53_serdes_init); diff --git a/drivers/net/dsa/b53/b53_serdes.h b/drivers/net/dsa/b53/b53_serdes.h index f47d5caa7557..ef81f5da5f81 100644 --- a/drivers/net/dsa/b53/b53_serdes.h +++ b/drivers/net/dsa/b53/b53_serdes.h @@ -107,14 +107,11 @@ static inline u8 b53_serdes_map_lane(struct b53_device *dev, int port) return dev->ops->serdes_map_lane(dev, port); } -int b53_serdes_get_link(struct b53_device *dev, int port); -int b53_serdes_link_state(struct b53_device *dev, int port, - struct phylink_link_state *state); -void b53_serdes_config(struct b53_device *dev, int port, unsigned int mode, - const struct phylink_link_state *state); -void b53_serdes_an_restart(struct b53_device *dev, int port); void b53_serdes_link_set(struct b53_device *dev, int port, unsigned int mode, phy_interface_t interface, bool link_up); +struct phylink_pcs *b53_serdes_phylink_mac_select_pcs(struct b53_device *dev, + int port, + phy_interface_t interface); void b53_serdes_phylink_get_caps(struct b53_device *dev, int port, struct phylink_config *config); #if IS_ENABLED(CONFIG_B53_SERDES) diff --git a/drivers/net/dsa/b53/b53_srab.c b/drivers/net/dsa/b53/b53_srab.c index c51b716657db..da0b889880f6 100644 --- a/drivers/net/dsa/b53/b53_srab.c +++ b/drivers/net/dsa/b53/b53_srab.c @@ -491,10 +491,8 @@ static const struct b53_io_ops b53_srab_ops = { .irq_disable = b53_srab_irq_disable, .phylink_get_caps = b53_srab_phylink_get_caps, #if IS_ENABLED(CONFIG_B53_SERDES) + .phylink_mac_select_pcs = b53_serdes_phylink_mac_select_pcs, .serdes_map_lane = b53_srab_serdes_map_lane, - .serdes_link_state = b53_serdes_link_state, - .serdes_config = b53_serdes_config, - .serdes_an_restart = b53_serdes_an_restart, .serdes_link_set = b53_serdes_link_set, #endif }; diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index cf82b1fa9725..87e81c636339 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -809,6 +809,9 @@ static void bcm_sf2_sw_mac_link_down(struct dsa_switch *ds, int port, struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds); u32 reg, offset; + if (priv->wol_ports_mask & BIT(port)) + return; + if (port != core_readl(priv, CORE_IMP0_PRT_ID)) { if (priv->type == BCM4908_DEVICE_ID || priv->type == BCM7445_DEVICE_ID) diff --git a/drivers/net/dsa/lantiq_gswip.c b/drivers/net/dsa/lantiq_gswip.c index a416240d001b..12c15da55664 100644 --- a/drivers/net/dsa/lantiq_gswip.c +++ b/drivers/net/dsa/lantiq_gswip.c @@ -1681,9 +1681,6 @@ static void gswip_phylink_mac_config(struct dsa_switch *ds, int port, break; case PHY_INTERFACE_MODE_RMII: miicfg |= GSWIP_MII_CFG_MODE_RMIIM; - - /* Configure the RMII clock as output: */ - miicfg |= GSWIP_MII_CFG_RMII_CLK; break; case PHY_INTERFACE_MODE_RGMII: case PHY_INTERFACE_MODE_RGMII_ID: diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c index 8222c8a6c5ec..7310d19d1f06 100644 --- a/drivers/net/dsa/microchip/ksz9477.c +++ b/drivers/net/dsa/microchip/ksz9477.c @@ -1021,14 +1021,32 @@ static int ksz9477_port_mirror_add(struct dsa_switch *ds, int port, bool ingress, struct netlink_ext_ack *extack) { struct ksz_device *dev = ds->priv; + u8 data; + int p; + + /* Limit to one sniffer port + * Check if any of the port is already set for sniffing + * If yes, instruct the user to remove the previous entry & exit + */ + for (p = 0; p < dev->port_cnt; p++) { + /* Skip the current sniffing port */ + if (p == mirror->to_local_port) + continue; + + ksz_pread8(dev, p, P_MIRROR_CTRL, &data); + + if (data & PORT_MIRROR_SNIFFER) { + NL_SET_ERR_MSG_MOD(extack, + "Sniffer port is already configured, delete existing rules & retry"); + return -EBUSY; + } + } if (ingress) ksz_port_cfg(dev, port, P_MIRROR_CTRL, PORT_MIRROR_RX, true); else ksz_port_cfg(dev, port, P_MIRROR_CTRL, PORT_MIRROR_TX, true); - ksz_port_cfg(dev, port, P_MIRROR_CTRL, PORT_MIRROR_SNIFFER, false); - /* configure mirror port */ ksz_port_cfg(dev, mirror->to_local_port, P_MIRROR_CTRL, PORT_MIRROR_SNIFFER, true); @@ -1042,16 +1060,28 @@ static void ksz9477_port_mirror_del(struct dsa_switch *ds, int port, struct dsa_mall_mirror_tc_entry *mirror) { struct ksz_device *dev = ds->priv; + bool in_use = false; u8 data; + int p; if (mirror->ingress) ksz_port_cfg(dev, port, P_MIRROR_CTRL, PORT_MIRROR_RX, false); else ksz_port_cfg(dev, port, P_MIRROR_CTRL, PORT_MIRROR_TX, false); - ksz_pread8(dev, port, P_MIRROR_CTRL, &data); - if (!(data & (PORT_MIRROR_RX | PORT_MIRROR_TX))) + /* Check if any of the port is still referring to sniffer port */ + for (p = 0; p < dev->port_cnt; p++) { + ksz_pread8(dev, p, P_MIRROR_CTRL, &data); + + if ((data & (PORT_MIRROR_RX | PORT_MIRROR_TX))) { + in_use = true; + break; + } + } + + /* delete sniffing if there are no other mirroring rules */ + if (!in_use) ksz_port_cfg(dev, mirror->to_local_port, P_MIRROR_CTRL, PORT_MIRROR_SNIFFER, false); } diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index 19f0035d4410..fe3cb26f4287 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -2229,6 +2229,7 @@ mt7530_setup(struct dsa_switch *ds) ret = of_get_phy_mode(mac_np, &interface); if (ret && ret != -ENODEV) { of_node_put(mac_np); + of_node_put(phy_node); return ret; } id = of_mdio_parse_addr(ds->dev, phy_node); diff --git a/drivers/net/dsa/mv88e6xxx/port_hidden.c b/drivers/net/dsa/mv88e6xxx/port_hidden.c index b49d05f0e117..7a9f9ff6dedf 100644 --- a/drivers/net/dsa/mv88e6xxx/port_hidden.c +++ b/drivers/net/dsa/mv88e6xxx/port_hidden.c @@ -40,8 +40,9 @@ int mv88e6xxx_port_hidden_wait(struct mv88e6xxx_chip *chip) { int bit = __bf_shf(MV88E6XXX_PORT_RESERVED_1A_BUSY); - return mv88e6xxx_wait_bit(chip, MV88E6XXX_PORT_RESERVED_1A_CTRL_PORT, - MV88E6XXX_PORT_RESERVED_1A, bit, 0); + return mv88e6xxx_port_wait_bit(chip, + MV88E6XXX_PORT_RESERVED_1A_CTRL_PORT, + MV88E6XXX_PORT_RESERVED_1A, bit, 0); } int mv88e6xxx_port_hidden_read(struct mv88e6xxx_chip *chip, int block, int port, diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index 413b0006e9a2..faccfb3f0158 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -403,6 +403,7 @@ static int felix_update_trapping_destinations(struct dsa_switch *ds, { struct ocelot *ocelot = ds->priv; struct felix *felix = ocelot_to_felix(ocelot); + struct ocelot_vcap_block *block_vcap_is2; struct ocelot_vcap_filter *trap; enum ocelot_mask_mode mask_mode; unsigned long port_mask; @@ -422,9 +423,13 @@ static int felix_update_trapping_destinations(struct dsa_switch *ds, /* We are sure that "cpu" was found, otherwise * dsa_tree_setup_default_cpu() would have failed earlier. */ + block_vcap_is2 = &ocelot->block[VCAP_IS2]; /* Make sure all traps are set up for that destination */ - list_for_each_entry(trap, &ocelot->traps, trap_list) { + list_for_each_entry(trap, &block_vcap_is2->rules, list) { + if (!trap->is_trap) + continue; + /* Figure out the current trapping destination */ if (using_tag_8021q) { /* Redirect to the tag_8021q CPU port. If timestamps @@ -670,6 +675,8 @@ static int felix_change_tag_protocol(struct dsa_switch *ds, int cpu, struct ocelot *ocelot = ds->priv; struct felix *felix = ocelot_to_felix(ocelot); enum dsa_tag_protocol old_proto = felix->tag_proto; + bool cpu_port_active = false; + struct dsa_port *dp; int err; if (proto != DSA_TAG_PROTO_SEVILLE && @@ -677,6 +684,27 @@ static int felix_change_tag_protocol(struct dsa_switch *ds, int cpu, proto != DSA_TAG_PROTO_OCELOT_8021Q) return -EPROTONOSUPPORT; + /* We don't support multiple CPU ports, yet the DT blob may have + * multiple CPU ports defined. The first CPU port is the active one, + * the others are inactive. In this case, DSA will call + * ->change_tag_protocol() multiple times, once per CPU port. + * Since we implement the tagging protocol change towards "ocelot" or + * "seville" as effectively initializing the NPI port, what we are + * doing is effectively changing who the NPI port is to the last @cpu + * argument passed, which is an unused DSA CPU port and not the one + * that should actively pass traffic. + * Suppress DSA's calls on CPU ports that are inactive. + */ + dsa_switch_for_each_user_port(dp, ds) { + if (dp->cpu_dp->index == cpu) { + cpu_port_active = true; + break; + } + } + + if (!cpu_port_active) + return 0; + felix_del_tag_protocol(ds, cpu, old_proto); err = felix_set_tag_protocol(ds, cpu, proto); diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c index 8d382b27e625..52a8566071ed 100644 --- a/drivers/net/dsa/ocelot/felix_vsc9959.c +++ b/drivers/net/dsa/ocelot/felix_vsc9959.c @@ -2316,7 +2316,7 @@ static int felix_pci_probe(struct pci_dev *pdev, err = dsa_register_switch(ds); if (err) { - dev_err(&pdev->dev, "Failed to register DSA switch: %d\n", err); + dev_err_probe(&pdev->dev, err, "Failed to register DSA switch\n"); goto err_register_ds; } diff --git a/drivers/net/dsa/realtek/Kconfig b/drivers/net/dsa/realtek/Kconfig index 1aa79735355f..060165a85fb7 100644 --- a/drivers/net/dsa/realtek/Kconfig +++ b/drivers/net/dsa/realtek/Kconfig @@ -9,34 +9,46 @@ menuconfig NET_DSA_REALTEK help Select to enable support for Realtek Ethernet switch chips. + Note that at least one interface driver must be enabled for the + subdrivers to be loaded. Moreover, an interface driver cannot achieve + anything without at least one subdriver enabled. + +if NET_DSA_REALTEK + config NET_DSA_REALTEK_MDIO - tristate "Realtek MDIO connected switch driver" - depends on NET_DSA_REALTEK + tristate "Realtek MDIO interface driver" depends on OF + depends on NET_DSA_REALTEK_RTL8365MB || NET_DSA_REALTEK_RTL8366RB + depends on NET_DSA_REALTEK_RTL8365MB || !NET_DSA_REALTEK_RTL8365MB + depends on NET_DSA_REALTEK_RTL8366RB || !NET_DSA_REALTEK_RTL8366RB help Select to enable support for registering switches configured through MDIO. config NET_DSA_REALTEK_SMI - tristate "Realtek SMI connected switch driver" - depends on NET_DSA_REALTEK + tristate "Realtek SMI interface driver" depends on OF + depends on NET_DSA_REALTEK_RTL8365MB || NET_DSA_REALTEK_RTL8366RB + depends on NET_DSA_REALTEK_RTL8365MB || !NET_DSA_REALTEK_RTL8365MB + depends on NET_DSA_REALTEK_RTL8366RB || !NET_DSA_REALTEK_RTL8366RB help Select to enable support for registering switches connected through SMI. config NET_DSA_REALTEK_RTL8365MB tristate "Realtek RTL8365MB switch subdriver" - depends on NET_DSA_REALTEK - depends on NET_DSA_REALTEK_SMI || NET_DSA_REALTEK_MDIO + imply NET_DSA_REALTEK_SMI + imply NET_DSA_REALTEK_MDIO select NET_DSA_TAG_RTL8_4 help Select to enable support for Realtek RTL8365MB-VC and RTL8367S. config NET_DSA_REALTEK_RTL8366RB tristate "Realtek RTL8366RB switch subdriver" - depends on NET_DSA_REALTEK - depends on NET_DSA_REALTEK_SMI || NET_DSA_REALTEK_MDIO + imply NET_DSA_REALTEK_SMI + imply NET_DSA_REALTEK_MDIO select NET_DSA_TAG_RTL4_A help - Select to enable support for Realtek RTL8366RB + Select to enable support for Realtek RTL8366RB. + +endif diff --git a/drivers/net/dsa/realtek/realtek-mdio.c b/drivers/net/dsa/realtek/realtek-mdio.c index 31e1f100e48e..c58f49d558d2 100644 --- a/drivers/net/dsa/realtek/realtek-mdio.c +++ b/drivers/net/dsa/realtek/realtek-mdio.c @@ -267,7 +267,6 @@ static const struct of_device_id realtek_mdio_of_match[] = { #endif #if IS_ENABLED(CONFIG_NET_DSA_REALTEK_RTL8365MB) { .compatible = "realtek,rtl8365mb", .data = &rtl8365mb_variant, }, - { .compatible = "realtek,rtl8367s", .data = &rtl8365mb_variant, }, #endif { /* sentinel */ }, }; diff --git a/drivers/net/dsa/realtek/realtek-smi.c b/drivers/net/dsa/realtek/realtek-smi.c index 2243d3da55b2..45992f79ec8d 100644 --- a/drivers/net/dsa/realtek/realtek-smi.c +++ b/drivers/net/dsa/realtek/realtek-smi.c @@ -546,20 +546,11 @@ static const struct of_device_id realtek_smi_of_match[] = { .data = &rtl8366rb_variant, }, #endif - { - /* FIXME: add support for RTL8366S and more */ - .compatible = "realtek,rtl8366s", - .data = NULL, - }, #if IS_ENABLED(CONFIG_NET_DSA_REALTEK_RTL8365MB) { .compatible = "realtek,rtl8365mb", .data = &rtl8365mb_variant, }, - { - .compatible = "realtek,rtl8367s", - .data = &rtl8365mb_variant, - }, #endif { /* sentinel */ }, }; diff --git a/drivers/net/ethernet/Kconfig b/drivers/net/ethernet/Kconfig index bd4cb9d7c35d..827993022386 100644 --- a/drivers/net/ethernet/Kconfig +++ b/drivers/net/ethernet/Kconfig @@ -35,15 +35,6 @@ source "drivers/net/ethernet/aquantia/Kconfig" source "drivers/net/ethernet/arc/Kconfig" source "drivers/net/ethernet/asix/Kconfig" source "drivers/net/ethernet/atheros/Kconfig" -source "drivers/net/ethernet/broadcom/Kconfig" -source "drivers/net/ethernet/brocade/Kconfig" -source "drivers/net/ethernet/cadence/Kconfig" -source "drivers/net/ethernet/calxeda/Kconfig" -source "drivers/net/ethernet/cavium/Kconfig" -source "drivers/net/ethernet/chelsio/Kconfig" -source "drivers/net/ethernet/cirrus/Kconfig" -source "drivers/net/ethernet/cisco/Kconfig" -source "drivers/net/ethernet/cortina/Kconfig" config CX_ECAT tristate "Beckhoff CX5020 EtherCAT master support" @@ -57,6 +48,14 @@ config CX_ECAT To compile this driver as a module, choose M here. The module will be called ec_bhf. +source "drivers/net/ethernet/broadcom/Kconfig" +source "drivers/net/ethernet/cadence/Kconfig" +source "drivers/net/ethernet/calxeda/Kconfig" +source "drivers/net/ethernet/cavium/Kconfig" +source "drivers/net/ethernet/chelsio/Kconfig" +source "drivers/net/ethernet/cirrus/Kconfig" +source "drivers/net/ethernet/cisco/Kconfig" +source "drivers/net/ethernet/cortina/Kconfig" source "drivers/net/ethernet/davicom/Kconfig" config DNET @@ -85,7 +84,6 @@ source "drivers/net/ethernet/huawei/Kconfig" source "drivers/net/ethernet/i825xx/Kconfig" source "drivers/net/ethernet/ibm/Kconfig" source "drivers/net/ethernet/intel/Kconfig" -source "drivers/net/ethernet/microsoft/Kconfig" source "drivers/net/ethernet/xscale/Kconfig" config JME @@ -128,8 +126,9 @@ source "drivers/net/ethernet/mediatek/Kconfig" source "drivers/net/ethernet/mellanox/Kconfig" source "drivers/net/ethernet/micrel/Kconfig" source "drivers/net/ethernet/microchip/Kconfig" -source "drivers/net/ethernet/moxa/Kconfig" source "drivers/net/ethernet/mscc/Kconfig" +source "drivers/net/ethernet/microsoft/Kconfig" +source "drivers/net/ethernet/moxa/Kconfig" source "drivers/net/ethernet/myricom/Kconfig" config FEALNX @@ -141,10 +140,10 @@ config FEALNX Say Y here to support the Myson MTD-800 family of PCI-based Ethernet cards. <http://www.myson.com.tw/> +source "drivers/net/ethernet/ni/Kconfig" source "drivers/net/ethernet/natsemi/Kconfig" source "drivers/net/ethernet/neterion/Kconfig" source "drivers/net/ethernet/netronome/Kconfig" -source "drivers/net/ethernet/ni/Kconfig" source "drivers/net/ethernet/8390/Kconfig" source "drivers/net/ethernet/nvidia/Kconfig" source "drivers/net/ethernet/nxp/Kconfig" @@ -164,6 +163,7 @@ source "drivers/net/ethernet/packetengines/Kconfig" source "drivers/net/ethernet/pasemi/Kconfig" source "drivers/net/ethernet/pensando/Kconfig" source "drivers/net/ethernet/qlogic/Kconfig" +source "drivers/net/ethernet/brocade/Kconfig" source "drivers/net/ethernet/qualcomm/Kconfig" source "drivers/net/ethernet/rdc/Kconfig" source "drivers/net/ethernet/realtek/Kconfig" @@ -171,10 +171,10 @@ source "drivers/net/ethernet/renesas/Kconfig" source "drivers/net/ethernet/rocker/Kconfig" source "drivers/net/ethernet/samsung/Kconfig" source "drivers/net/ethernet/seeq/Kconfig" -source "drivers/net/ethernet/sfc/Kconfig" source "drivers/net/ethernet/sgi/Kconfig" source "drivers/net/ethernet/silan/Kconfig" source "drivers/net/ethernet/sis/Kconfig" +source "drivers/net/ethernet/sfc/Kconfig" source "drivers/net/ethernet/smsc/Kconfig" source "drivers/net/ethernet/socionext/Kconfig" source "drivers/net/ethernet/stmicro/Kconfig" diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c index 33f1a1377588..24d715c28a35 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c @@ -486,8 +486,8 @@ int aq_nic_start(struct aq_nic_s *self) if (err < 0) goto err_exit; - for (i = 0U, aq_vec = self->aq_vec[0]; - self->aq_vecs > i; ++i, aq_vec = self->aq_vec[i]) { + for (i = 0U; self->aq_vecs > i; ++i) { + aq_vec = self->aq_vec[i]; err = aq_vec_start(aq_vec); if (err < 0) goto err_exit; @@ -517,8 +517,8 @@ int aq_nic_start(struct aq_nic_s *self) mod_timer(&self->polling_timer, jiffies + AQ_CFG_POLLING_TIMER_INTERVAL); } else { - for (i = 0U, aq_vec = self->aq_vec[0]; - self->aq_vecs > i; ++i, aq_vec = self->aq_vec[i]) { + for (i = 0U; self->aq_vecs > i; ++i) { + aq_vec = self->aq_vec[i]; err = aq_pci_func_alloc_irq(self, i, self->ndev->name, aq_vec_isr, aq_vec, aq_vec_get_affinity_mask(aq_vec)); diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c index 797a95142d1f..831833911a52 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c @@ -444,7 +444,7 @@ err_exit: static int aq_pm_freeze(struct device *dev) { - return aq_suspend_common(dev, false); + return aq_suspend_common(dev, true); } static int aq_pm_suspend_poweroff(struct device *dev) @@ -454,7 +454,7 @@ static int aq_pm_suspend_poweroff(struct device *dev) static int aq_pm_thaw(struct device *dev) { - return atl_resume_common(dev, false); + return atl_resume_common(dev, true); } static int aq_pm_resume_restore(struct device *dev) diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c index 77e76c9efd32..8201ce7adb77 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c @@ -346,7 +346,6 @@ int aq_ring_rx_clean(struct aq_ring_s *self, int budget) { struct net_device *ndev = aq_nic_get_ndev(self->aq_nic); - bool is_rsc_completed = true; int err = 0; for (; (self->sw_head != self->hw_head) && budget; @@ -364,12 +363,17 @@ int aq_ring_rx_clean(struct aq_ring_s *self, continue; if (!buff->is_eop) { + unsigned int frag_cnt = 0U; buff_ = buff; do { + bool is_rsc_completed = true; + if (buff_->next >= self->size) { err = -EIO; goto err_exit; } + + frag_cnt++; next_ = buff_->next, buff_ = &self->buff_ring[next_]; is_rsc_completed = @@ -377,18 +381,17 @@ int aq_ring_rx_clean(struct aq_ring_s *self, next_, self->hw_head); - if (unlikely(!is_rsc_completed)) - break; + if (unlikely(!is_rsc_completed) || + frag_cnt > MAX_SKB_FRAGS) { + err = 0; + goto err_exit; + } buff->is_error |= buff_->is_error; buff->is_cso_err |= buff_->is_cso_err; } while (!buff_->is_eop); - if (!is_rsc_completed) { - err = 0; - goto err_exit; - } if (buff->is_error || (buff->is_lro && buff->is_cso_err)) { buff_ = buff; @@ -446,7 +449,7 @@ int aq_ring_rx_clean(struct aq_ring_s *self, ALIGN(hdr_len, sizeof(long))); if (buff->len - hdr_len > 0) { - skb_add_rx_frag(skb, 0, buff->rxdata.page, + skb_add_rx_frag(skb, i++, buff->rxdata.page, buff->rxdata.pg_off + hdr_len, buff->len - hdr_len, AQ_CFG_RX_FRAME_MAX); @@ -455,7 +458,6 @@ int aq_ring_rx_clean(struct aq_ring_s *self, if (!buff->is_eop) { buff_ = buff; - i = 1U; do { next_ = buff_->next; buff_ = &self->buff_ring[next_]; diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_vec.c b/drivers/net/ethernet/aquantia/atlantic/aq_vec.c index f4774cf051c9..6ab1f3212d24 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_vec.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_vec.c @@ -43,8 +43,8 @@ static int aq_vec_poll(struct napi_struct *napi, int budget) if (!self) { err = -EINVAL; } else { - for (i = 0U, ring = self->ring[0]; - self->tx_rings > i; ++i, ring = self->ring[i]) { + for (i = 0U; self->tx_rings > i; ++i) { + ring = self->ring[i]; u64_stats_update_begin(&ring[AQ_VEC_RX_ID].stats.rx.syncp); ring[AQ_VEC_RX_ID].stats.rx.polls++; u64_stats_update_end(&ring[AQ_VEC_RX_ID].stats.rx.syncp); @@ -182,8 +182,8 @@ int aq_vec_init(struct aq_vec_s *self, const struct aq_hw_ops *aq_hw_ops, self->aq_hw_ops = aq_hw_ops; self->aq_hw = aq_hw; - for (i = 0U, ring = self->ring[0]; - self->tx_rings > i; ++i, ring = self->ring[i]) { + for (i = 0U; self->tx_rings > i; ++i) { + ring = self->ring[i]; err = aq_ring_init(&ring[AQ_VEC_TX_ID], ATL_RING_TX); if (err < 0) goto err_exit; @@ -224,8 +224,8 @@ int aq_vec_start(struct aq_vec_s *self) unsigned int i = 0U; int err = 0; - for (i = 0U, ring = self->ring[0]; - self->tx_rings > i; ++i, ring = self->ring[i]) { + for (i = 0U; self->tx_rings > i; ++i) { + ring = self->ring[i]; err = self->aq_hw_ops->hw_ring_tx_start(self->aq_hw, &ring[AQ_VEC_TX_ID]); if (err < 0) @@ -248,8 +248,8 @@ void aq_vec_stop(struct aq_vec_s *self) struct aq_ring_s *ring = NULL; unsigned int i = 0U; - for (i = 0U, ring = self->ring[0]; - self->tx_rings > i; ++i, ring = self->ring[i]) { + for (i = 0U; self->tx_rings > i; ++i) { + ring = self->ring[i]; self->aq_hw_ops->hw_ring_tx_stop(self->aq_hw, &ring[AQ_VEC_TX_ID]); @@ -268,8 +268,8 @@ void aq_vec_deinit(struct aq_vec_s *self) if (!self) goto err_exit; - for (i = 0U, ring = self->ring[0]; - self->tx_rings > i; ++i, ring = self->ring[i]) { + for (i = 0U; self->tx_rings > i; ++i) { + ring = self->ring[i]; aq_ring_tx_clean(&ring[AQ_VEC_TX_ID]); aq_ring_rx_deinit(&ring[AQ_VEC_RX_ID]); } @@ -297,8 +297,8 @@ void aq_vec_ring_free(struct aq_vec_s *self) if (!self) goto err_exit; - for (i = 0U, ring = self->ring[0]; - self->tx_rings > i; ++i, ring = self->ring[i]) { + for (i = 0U; self->tx_rings > i; ++i) { + ring = self->ring[i]; aq_ring_free(&ring[AQ_VEC_TX_ID]); if (i < self->rx_rings) aq_ring_free(&ring[AQ_VEC_RX_ID]); diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c index d875ce3ec759..15ede7285fb5 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c @@ -889,6 +889,13 @@ int hw_atl_b0_hw_ring_tx_head_update(struct aq_hw_s *self, err = -ENXIO; goto err_exit; } + + /* Validate that the new hw_head_ is reasonable. */ + if (hw_head_ >= ring->size) { + err = -ENXIO; + goto err_exit; + } + ring->hw_head = hw_head_; err = aq_hw_err_from_flags(self); diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index 60dde29974bf..df51be3cbe06 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -2585,8 +2585,10 @@ static int bcm_sysport_probe(struct platform_device *pdev) device_set_wakeup_capable(&pdev->dev, 1); priv->wol_clk = devm_clk_get_optional(&pdev->dev, "sw_sysportwol"); - if (IS_ERR(priv->wol_clk)) - return PTR_ERR(priv->wol_clk); + if (IS_ERR(priv->wol_clk)) { + ret = PTR_ERR(priv->wol_clk); + goto err_deregister_fixed_link; + } /* Set the needed headroom once and for all */ BUILD_BUG_ON(sizeof(struct bcm_tsb) != 8); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index c19b072f3a23..962253db25b8 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -14153,10 +14153,6 @@ static int bnx2x_eeh_nic_unload(struct bnx2x *bp) /* Stop Tx */ bnx2x_tx_disable(bp); - /* Delete all NAPI objects */ - bnx2x_del_all_napi(bp); - if (CNIC_LOADED(bp)) - bnx2x_del_all_napi_cnic(bp); netdev_reset_tc(bp->dev); del_timer_sync(&bp->timer); @@ -14261,6 +14257,11 @@ static pci_ers_result_t bnx2x_io_slot_reset(struct pci_dev *pdev) bnx2x_drain_tx_queues(bp); bnx2x_send_unload_req(bp, UNLOAD_RECOVERY); bnx2x_netif_stop(bp, 1); + bnx2x_del_all_napi(bp); + + if (CNIC_LOADED(bp)) + bnx2x_del_all_napi_cnic(bp); + bnx2x_free_irq(bp); /* Report UNLOAD_DONE to MCP */ diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 1c28495875cf..1d69fe0737a1 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -2707,6 +2707,10 @@ static int bnxt_poll_p5(struct napi_struct *napi, int budget) u32 idx = le32_to_cpu(nqcmp->cq_handle_low); struct bnxt_cp_ring_info *cpr2; + /* No more budget for RX work */ + if (budget && work_done >= budget && idx == BNXT_RX_HDL) + break; + cpr2 = cpr->cp_ring_arr[idx]; work_done += __bnxt_poll_work(bp, cpr2, budget - work_done); @@ -3253,6 +3257,7 @@ static int bnxt_alloc_tx_rings(struct bnxt *bp) } qidx = bp->tc_to_qidx[j]; ring->queue_id = bp->q_info[qidx].queue_id; + spin_lock_init(&txr->xdp_tx_lock); if (i < bp->tx_nr_rings_xdp) continue; if (i % bp->tx_nr_rings_per_tc == (bp->tx_nr_rings_per_tc - 1)) @@ -10338,6 +10343,12 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init) if (irq_re_init) udp_tunnel_nic_reset_ntf(bp->dev); + if (bp->tx_nr_rings_xdp < num_possible_cpus()) { + if (!static_key_enabled(&bnxt_xdp_locking_key)) + static_branch_enable(&bnxt_xdp_locking_key); + } else if (static_key_enabled(&bnxt_xdp_locking_key)) { + static_branch_disable(&bnxt_xdp_locking_key); + } set_bit(BNXT_STATE_OPEN, &bp->state); bnxt_enable_int(bp); /* Enable TX queues */ @@ -10976,7 +10987,7 @@ static bool bnxt_rfs_capable(struct bnxt *bp) if (bp->flags & BNXT_FLAG_CHIP_P5) return bnxt_rfs_supported(bp); - if (!(bp->flags & BNXT_FLAG_MSIX_CAP) || !bnxt_can_reserve_rings(bp)) + if (!(bp->flags & BNXT_FLAG_MSIX_CAP) || !bnxt_can_reserve_rings(bp) || !bp->rx_nr_rings) return false; vnics = 1 + bp->rx_nr_rings; @@ -13227,10 +13238,9 @@ static int bnxt_init_dflt_ring_mode(struct bnxt *bp) goto init_dflt_ring_err; bp->tx_nr_rings_per_tc = bp->tx_nr_rings; - if (bnxt_rfs_supported(bp) && bnxt_rfs_capable(bp)) { - bp->flags |= BNXT_FLAG_RFS; - bp->dev->features |= NETIF_F_NTUPLE; - } + + bnxt_set_dflt_rfs(bp); + init_dflt_ring_err: bnxt_ulp_irq_restart(bp, rc); return rc; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 61aa3e8c5952..98453a78cbd0 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -593,7 +593,8 @@ struct nqe_cn { #define BNXT_MAX_MTU 9500 #define BNXT_MAX_PAGE_MODE_MTU \ ((unsigned int)PAGE_SIZE - VLAN_ETH_HLEN - NET_IP_ALIGN - \ - XDP_PACKET_HEADROOM) + XDP_PACKET_HEADROOM - \ + SKB_DATA_ALIGN((unsigned int)sizeof(struct skb_shared_info))) #define BNXT_MIN_PKT_SIZE 52 @@ -800,6 +801,8 @@ struct bnxt_tx_ring_info { u32 dev_state; struct bnxt_ring_struct tx_ring_struct; + /* Synchronize simultaneous xdp_xmit on same ring */ + spinlock_t xdp_tx_lock; }; #define BNXT_LEGACY_COAL_CMPL_PARAMS \ diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c index 9c2ad5e67a5d..00f2f80c0073 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c @@ -846,13 +846,6 @@ int bnxt_ptp_init(struct bnxt *bp, bool phc_cfg) if (rc) return rc; - if (bp->fw_cap & BNXT_FW_CAP_PTP_RTC) { - bnxt_ptp_timecounter_init(bp, false); - rc = bnxt_ptp_init_rtc(bp, phc_cfg); - if (rc) - goto out; - } - if (ptp->ptp_clock && bnxt_pps_config_ok(bp)) return 0; @@ -861,8 +854,14 @@ int bnxt_ptp_init(struct bnxt *bp, bool phc_cfg) atomic_set(&ptp->tx_avail, BNXT_MAX_TX_TS); spin_lock_init(&ptp->ptp_lock); - if (!(bp->fw_cap & BNXT_FW_CAP_PTP_RTC)) + if (bp->fw_cap & BNXT_FW_CAP_PTP_RTC) { + bnxt_ptp_timecounter_init(bp, false); + rc = bnxt_ptp_init_rtc(bp, phc_cfg); + if (rc) + goto out; + } else { bnxt_ptp_timecounter_init(bp, true); + } ptp->ptp_info = bnxt_ptp_caps; if ((bp->fw_cap & BNXT_FW_CAP_PTP_PPS)) { diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c index 52fad0fdeacf..03b1d6c04504 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c @@ -20,6 +20,8 @@ #include "bnxt.h" #include "bnxt_xdp.h" +DEFINE_STATIC_KEY_FALSE(bnxt_xdp_locking_key); + struct bnxt_sw_tx_bd *bnxt_xmit_bd(struct bnxt *bp, struct bnxt_tx_ring_info *txr, dma_addr_t mapping, u32 len) @@ -227,11 +229,16 @@ int bnxt_xdp_xmit(struct net_device *dev, int num_frames, ring = smp_processor_id() % bp->tx_nr_rings_xdp; txr = &bp->tx_ring[ring]; + if (READ_ONCE(txr->dev_state) == BNXT_DEV_STATE_CLOSING) + return -EINVAL; + + if (static_branch_unlikely(&bnxt_xdp_locking_key)) + spin_lock(&txr->xdp_tx_lock); + for (i = 0; i < num_frames; i++) { struct xdp_frame *xdp = frames[i]; - if (!txr || !bnxt_tx_avail(bp, txr) || - !(bp->bnapi[ring]->flags & BNXT_NAPI_FLAG_XDP)) + if (!bnxt_tx_avail(bp, txr)) break; mapping = dma_map_single(&pdev->dev, xdp->data, xdp->len, @@ -250,6 +257,9 @@ int bnxt_xdp_xmit(struct net_device *dev, int num_frames, bnxt_db_write(bp, &txr->tx_db, txr->tx_prod); } + if (static_branch_unlikely(&bnxt_xdp_locking_key)) + spin_unlock(&txr->xdp_tx_lock); + return nxmit; } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h index 0df40c3beb05..067bb5e821f5 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h @@ -10,6 +10,8 @@ #ifndef BNXT_XDP_H #define BNXT_XDP_H +DECLARE_STATIC_KEY_FALSE(bnxt_xdp_locking_key); + struct bnxt_sw_tx_bd *bnxt_xmit_bd(struct bnxt *bp, struct bnxt_tx_ring_info *txr, dma_addr_t mapping, u32 len); diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 2dd79af9411b..e87e46c47387 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -76,7 +76,7 @@ static inline void bcmgenet_writel(u32 value, void __iomem *offset) if (IS_ENABLED(CONFIG_MIPS) && IS_ENABLED(CONFIG_CPU_BIG_ENDIAN)) __raw_writel(value, offset); else - writel(value, offset); + writel_relaxed(value, offset); } static inline u32 bcmgenet_readl(void __iomem *offset) @@ -84,7 +84,7 @@ static inline u32 bcmgenet_readl(void __iomem *offset) if (IS_ENABLED(CONFIG_MIPS) && IS_ENABLED(CONFIG_CPU_BIG_ENDIAN)) return __raw_readl(offset); else - return readl(offset); + return readl_relaxed(offset); } static inline void dmadesc_set_length_status(struct bcmgenet_priv *priv, @@ -2035,6 +2035,11 @@ static struct sk_buff *bcmgenet_add_tsb(struct net_device *dev, return skb; } +static void bcmgenet_hide_tsb(struct sk_buff *skb) +{ + __skb_pull(skb, sizeof(struct status_64)); +} + static netdev_tx_t bcmgenet_xmit(struct sk_buff *skb, struct net_device *dev) { struct bcmgenet_priv *priv = netdev_priv(dev); @@ -2141,6 +2146,8 @@ static netdev_tx_t bcmgenet_xmit(struct sk_buff *skb, struct net_device *dev) } GENET_CB(skb)->last_cb = tx_cb_ptr; + + bcmgenet_hide_tsb(skb); skb_tx_timestamp(skb); /* Decrement total BD count and advance our write pointer */ @@ -3992,6 +3999,10 @@ static int bcmgenet_probe(struct platform_device *pdev) goto err; } priv->wol_irq = platform_get_irq_optional(pdev, 2); + if (priv->wol_irq == -EPROBE_DEFER) { + err = priv->wol_irq; + goto err; + } priv->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(priv->base)) { diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 800d5ced5800..61284baa0496 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -1219,7 +1219,6 @@ static void gem_rx_refill(struct macb_queue *queue) /* Make hw descriptor updates visible to CPU */ rmb(); - queue->rx_prepared_head++; desc = macb_rx_desc(queue, entry); if (!queue->rx_skbuff[entry]) { @@ -1258,6 +1257,7 @@ static void gem_rx_refill(struct macb_queue *queue) dma_wmb(); desc->addr &= ~MACB_BIT(RX_USED); } + queue->rx_prepared_head++; } /* Make descriptor updates visible to hardware */ @@ -1658,6 +1658,7 @@ static void macb_tx_restart(struct macb_queue *queue) unsigned int head = queue->tx_head; unsigned int tail = queue->tx_tail; struct macb *bp = queue->bp; + unsigned int head_idx, tbqp; if (bp->caps & MACB_CAPS_ISR_CLEAR_ON_WRITE) queue_writel(queue, ISR, MACB_BIT(TXUBR)); @@ -1665,6 +1666,13 @@ static void macb_tx_restart(struct macb_queue *queue) if (head == tail) return; + tbqp = queue_readl(queue, TBQP) / macb_dma_desc_get_size(bp); + tbqp = macb_adj_dma_desc_idx(bp, macb_tx_ring_wrap(bp, tbqp)); + head_idx = macb_adj_dma_desc_idx(bp, macb_tx_ring_wrap(bp, head)); + + if (tbqp == head_idx) + return; + macb_writel(bp, NCR, macb_readl(bp, NCR) | MACB_BIT(TSTART)); } diff --git a/drivers/net/ethernet/cavium/thunder/nic_main.c b/drivers/net/ethernet/cavium/thunder/nic_main.c index f2f1ce81fd9c..0ec65ec634df 100644 --- a/drivers/net/ethernet/cavium/thunder/nic_main.c +++ b/drivers/net/ethernet/cavium/thunder/nic_main.c @@ -59,7 +59,7 @@ struct nicpf { /* MSI-X */ u8 num_vec; - bool irq_allocated[NIC_PF_MSIX_VECTORS]; + unsigned int irq_allocated[NIC_PF_MSIX_VECTORS]; char irq_name[NIC_PF_MSIX_VECTORS][20]; }; @@ -1150,7 +1150,7 @@ static irqreturn_t nic_mbx_intr_handler(int irq, void *nic_irq) u64 intr; u8 vf; - if (irq == pci_irq_vector(nic->pdev, NIC_PF_INTR_ID_MBOX0)) + if (irq == nic->irq_allocated[NIC_PF_INTR_ID_MBOX0]) mbx = 0; else mbx = 1; @@ -1176,14 +1176,14 @@ static void nic_free_all_interrupts(struct nicpf *nic) for (irq = 0; irq < nic->num_vec; irq++) { if (nic->irq_allocated[irq]) - free_irq(pci_irq_vector(nic->pdev, irq), nic); - nic->irq_allocated[irq] = false; + free_irq(nic->irq_allocated[irq], nic); + nic->irq_allocated[irq] = 0; } } static int nic_register_interrupts(struct nicpf *nic) { - int i, ret; + int i, ret, irq; nic->num_vec = pci_msix_vec_count(nic->pdev); /* Enable MSI-X */ @@ -1201,13 +1201,13 @@ static int nic_register_interrupts(struct nicpf *nic) sprintf(nic->irq_name[i], "NICPF Mbox%d", (i - NIC_PF_INTR_ID_MBOX0)); - ret = request_irq(pci_irq_vector(nic->pdev, i), - nic_mbx_intr_handler, 0, + irq = pci_irq_vector(nic->pdev, i); + ret = request_irq(irq, nic_mbx_intr_handler, 0, nic->irq_name[i], nic); if (ret) goto fail; - nic->irq_allocated[i] = true; + nic->irq_allocated[i] = irq; } /* Enable mailbox interrupt */ diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index e7b4e3ed056c..8d719f82854a 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -2793,14 +2793,14 @@ int t4_get_raw_vpd_params(struct adapter *adapter, struct vpd_params *p) goto out; na = ret; - memcpy(p->id, vpd + id, min_t(int, id_len, ID_LEN)); + memcpy(p->id, vpd + id, min_t(unsigned int, id_len, ID_LEN)); strim(p->id); - memcpy(p->sn, vpd + sn, min_t(int, sn_len, SERNUM_LEN)); + memcpy(p->sn, vpd + sn, min_t(unsigned int, sn_len, SERNUM_LEN)); strim(p->sn); - memcpy(p->pn, vpd + pn, min_t(int, pn_len, PN_LEN)); + memcpy(p->pn, vpd + pn, min_t(unsigned int, pn_len, PN_LEN)); strim(p->pn); - memcpy(p->na, vpd + na, min_t(int, na_len, MACADDR_LEN)); - strim((char *)p->na); + memcpy(p->na, vpd + na, min_t(unsigned int, na_len, MACADDR_LEN)); + strim(p->na); out: vfree(vpd); diff --git a/drivers/net/ethernet/dec/tulip/tulip_core.c b/drivers/net/ethernet/dec/tulip/tulip_core.c index 79df5a72877b..0040dcaab945 100644 --- a/drivers/net/ethernet/dec/tulip/tulip_core.c +++ b/drivers/net/ethernet/dec/tulip/tulip_core.c @@ -1399,8 +1399,10 @@ static int tulip_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) /* alloc_etherdev ensures aligned and zeroed private structures */ dev = alloc_etherdev (sizeof (*tp)); - if (!dev) + if (!dev) { + pci_disable_device(pdev); return -ENOMEM; + } SET_NETDEV_DEV(dev, &pdev->dev); if (pci_resource_len (pdev, 0) < tulip_tbl[chip_idx].io_size) { @@ -1785,6 +1787,7 @@ err_out_free_res: err_out_free_netdev: free_netdev (dev); + pci_disable_device(pdev); return -ENODEV; } diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c index d5356db7539a..5231818943c6 100644 --- a/drivers/net/ethernet/faraday/ftgmac100.c +++ b/drivers/net/ethernet/faraday/ftgmac100.c @@ -1835,11 +1835,6 @@ static int ftgmac100_probe(struct platform_device *pdev) priv->rxdes0_edorr_mask = BIT(30); priv->txdes0_edotr_mask = BIT(30); priv->is_aspeed = true; - /* Disable ast2600 problematic HW arbitration */ - if (of_device_is_compatible(np, "aspeed,ast2600-mac")) { - iowrite32(FTGMAC100_TM_DEFAULT, - priv->base + FTGMAC100_OFFSET_TM); - } } else { priv->rxdes0_edorr_mask = BIT(15); priv->txdes0_edotr_mask = BIT(15); @@ -1911,6 +1906,11 @@ static int ftgmac100_probe(struct platform_device *pdev) err = ftgmac100_setup_clk(priv); if (err) goto err_phy_connect; + + /* Disable ast2600 problematic HW arbitration */ + if (of_device_is_compatible(np, "aspeed,ast2600-mac")) + iowrite32(FTGMAC100_TM_DEFAULT, + priv->base + FTGMAC100_OFFSET_TM); } /* Default ring sizes */ @@ -1928,6 +1928,11 @@ static int ftgmac100_probe(struct platform_device *pdev) /* AST2400 doesn't have working HW checksum generation */ if (np && (of_device_is_compatible(np, "aspeed,ast2400-mac"))) netdev->hw_features &= ~NETIF_F_HW_CSUM; + + /* AST2600 tx checksum with NCSI is broken */ + if (priv->use_ncsi && of_device_is_compatible(np, "aspeed,ast2600-mac")) + netdev->hw_features &= ~NETIF_F_HW_CSUM; + if (np && of_get_property(np, "no-hw-checksum", NULL)) netdev->hw_features &= ~(NETIF_F_HW_CSUM | NETIF_F_RXCSUM); netdev->features |= netdev->hw_features; diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c index 763d2c7b5fb1..5750f9a56393 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c @@ -489,11 +489,15 @@ static int dpaa_get_ts_info(struct net_device *net_dev, info->phc_index = -1; fman_node = of_get_parent(mac_node); - if (fman_node) + if (fman_node) { ptp_node = of_parse_phandle(fman_node, "ptimer-handle", 0); + of_node_put(fman_node); + } - if (ptp_node) + if (ptp_node) { ptp_dev = of_find_device_by_node(ptp_node); + of_node_put(ptp_node); + } if (ptp_dev) ptp = platform_get_drvdata(ptp_dev); diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.c index 5f5f8c53c4a0..c8cb541572ff 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.c @@ -167,7 +167,7 @@ static int dpaa2_ptp_probe(struct fsl_mc_device *mc_dev) base = of_iomap(node, 0); if (!base) { err = -ENOMEM; - goto err_close; + goto err_put; } err = fsl_mc_allocate_irqs(mc_dev); @@ -210,6 +210,8 @@ err_free_mc_irq: fsl_mc_free_irqs(mc_dev); err_unmap: iounmap(base); +err_put: + of_node_put(node); err_close: dprtc_close(mc_dev->mc_io, 0, mc_dev->mc_handle); err_free_mcp: diff --git a/drivers/net/ethernet/freescale/enetc/enetc_qos.c b/drivers/net/ethernet/freescale/enetc/enetc_qos.c index 79afb1d7289b..9182631856d5 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_qos.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_qos.c @@ -297,10 +297,6 @@ int enetc_setup_tc_txtime(struct net_device *ndev, void *type_data) if (tc < 0 || tc >= priv->num_tx_rings) return -EINVAL; - /* Do not support TXSTART and TX CSUM offload simutaniously */ - if (ndev->features & NETIF_F_CSUM_MASK) - return -EBUSY; - /* TSD and Qbv are mutually exclusive in hardware */ if (enetc_rd(&priv->si->hw, ENETC_QBV_PTGCR_OFFSET) & ENETC_QBV_TGE) return -EBUSY; diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 11227f51404c..9f33ec838b52 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -3731,7 +3731,7 @@ static int fec_enet_init_stop_mode(struct fec_enet_private *fep, ARRAY_SIZE(out_val)); if (ret) { dev_dbg(&fep->pdev->dev, "no stop mode property\n"); - return ret; + goto out; } fep->stop_gpr.gpr = syscon_node_to_regmap(gpr_np); diff --git a/drivers/net/ethernet/fungible/funcore/fun_dev.c b/drivers/net/ethernet/fungible/funcore/fun_dev.c index 5d7aef73df61..fb5120d90f26 100644 --- a/drivers/net/ethernet/fungible/funcore/fun_dev.c +++ b/drivers/net/ethernet/fungible/funcore/fun_dev.c @@ -586,8 +586,8 @@ static int fun_get_dev_limits(struct fun_dev *fdev) /* Calculate the max QID based on SQ/CQ/doorbell counts. * SQ/CQ doorbells alternate. */ - num_dbs = (pci_resource_len(pdev, 0) - NVME_REG_DBS) / - (fdev->db_stride * 4); + num_dbs = (pci_resource_len(pdev, 0) - NVME_REG_DBS) >> + (2 + NVME_CAP_STRIDE(fdev->cap_reg)); fdev->max_qid = min3(cq_count, sq_count, num_dbs / 2) - 1; fdev->kern_end_qid = fdev->max_qid + 1; return 0; diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c index 7edf8569514c..928d934cb21a 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c @@ -1065,19 +1065,23 @@ int hns_mac_init(struct dsaf_device *dsaf_dev) device_for_each_child_node(dsaf_dev->dev, child) { ret = fwnode_property_read_u32(child, "reg", &port_id); if (ret) { + fwnode_handle_put(child); dev_err(dsaf_dev->dev, "get reg fail, ret=%d!\n", ret); return ret; } if (port_id >= max_port_num) { + fwnode_handle_put(child); dev_err(dsaf_dev->dev, "reg(%u) out of range!\n", port_id); return -EINVAL; } mac_cb = devm_kzalloc(dsaf_dev->dev, sizeof(*mac_cb), GFP_KERNEL); - if (!mac_cb) + if (!mac_cb) { + fwnode_handle_put(child); return -ENOMEM; + } mac_cb->fw_port = child; mac_cb->mac_id = (u8)port_id; dsaf_dev->mac_cb[port_id] = mac_cb; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_tqp_stats.c b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_tqp_stats.c index 0c60f41fca8a..f3c9395d8351 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_tqp_stats.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_tqp_stats.c @@ -75,7 +75,7 @@ int hclge_comm_tqps_update_stats(struct hnae3_handle *handle, ret = hclge_comm_cmd_send(hw, &desc, 1); if (ret) { dev_err(&hw->cmq.csq.pdev->dev, - "failed to get tqp stat, ret = %d, tx = %u.\n", + "failed to get tqp stat, ret = %d, rx = %u.\n", ret, i); return ret; } @@ -89,7 +89,7 @@ int hclge_comm_tqps_update_stats(struct hnae3_handle *handle, ret = hclge_comm_cmd_send(hw, &desc, 1); if (ret) { dev_err(&hw->cmq.csq.pdev->dev, - "failed to get tqp stat, ret = %d, rx = %u.\n", + "failed to get tqp stat, ret = %d, tx = %u.\n", ret, i); return ret; } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c index 44d9b560b337..93aeb615191d 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c @@ -562,12 +562,12 @@ static void hns3_dbg_tx_spare_info(struct hns3_enet_ring *ring, char *buf, for (i = 0; i < ring_num; i++) { j = 0; - sprintf(result[j++], "%8u", i); - sprintf(result[j++], "%9u", ring->tx_copybreak); - sprintf(result[j++], "%3u", tx_spare->len); - sprintf(result[j++], "%3u", tx_spare->next_to_use); - sprintf(result[j++], "%3u", tx_spare->next_to_clean); - sprintf(result[j++], "%3u", tx_spare->last_to_clean); + sprintf(result[j++], "%u", i); + sprintf(result[j++], "%u", ring->tx_copybreak); + sprintf(result[j++], "%u", tx_spare->len); + sprintf(result[j++], "%u", tx_spare->next_to_use); + sprintf(result[j++], "%u", tx_spare->next_to_clean); + sprintf(result[j++], "%u", tx_spare->last_to_clean); sprintf(result[j++], "%pad", &tx_spare->dma); hns3_dbg_fill_content(content, sizeof(content), tx_spare_info_items, @@ -598,35 +598,35 @@ static void hns3_dump_rx_queue_info(struct hns3_enet_ring *ring, u32 base_add_l, base_add_h; u32 j = 0; - sprintf(result[j++], "%8u", index); + sprintf(result[j++], "%u", index); - sprintf(result[j++], "%6u", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base + HNS3_RING_RX_RING_BD_NUM_REG)); - sprintf(result[j++], "%6u", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base + HNS3_RING_RX_RING_BD_LEN_REG)); - sprintf(result[j++], "%4u", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base + HNS3_RING_RX_RING_TAIL_REG)); - sprintf(result[j++], "%4u", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base + HNS3_RING_RX_RING_HEAD_REG)); - sprintf(result[j++], "%6u", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base + HNS3_RING_RX_RING_FBDNUM_REG)); - sprintf(result[j++], "%6u", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base + HNS3_RING_RX_RING_PKTNUM_RECORD_REG)); - sprintf(result[j++], "%9u", ring->rx_copybreak); + sprintf(result[j++], "%u", ring->rx_copybreak); - sprintf(result[j++], "%7s", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%s", readl_relaxed(ring->tqp->io_base + HNS3_RING_EN_REG) ? "on" : "off"); if (hnae3_ae_dev_tqp_txrx_indep_supported(ae_dev)) - sprintf(result[j++], "%10s", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%s", readl_relaxed(ring->tqp->io_base + HNS3_RING_RX_EN_REG) ? "on" : "off"); else - sprintf(result[j++], "%10s", "NA"); + sprintf(result[j++], "%s", "NA"); base_add_h = readl_relaxed(ring->tqp->io_base + HNS3_RING_RX_RING_BASEADDR_H_REG); @@ -700,36 +700,36 @@ static void hns3_dump_tx_queue_info(struct hns3_enet_ring *ring, u32 base_add_l, base_add_h; u32 j = 0; - sprintf(result[j++], "%8u", index); - sprintf(result[j++], "%6u", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%u", index); + sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base + HNS3_RING_TX_RING_BD_NUM_REG)); - sprintf(result[j++], "%2u", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base + HNS3_RING_TX_RING_TC_REG)); - sprintf(result[j++], "%4u", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base + HNS3_RING_TX_RING_TAIL_REG)); - sprintf(result[j++], "%4u", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base + HNS3_RING_TX_RING_HEAD_REG)); - sprintf(result[j++], "%6u", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base + HNS3_RING_TX_RING_FBDNUM_REG)); - sprintf(result[j++], "%6u", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base + HNS3_RING_TX_RING_OFFSET_REG)); - sprintf(result[j++], "%6u", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base + HNS3_RING_TX_RING_PKTNUM_RECORD_REG)); - sprintf(result[j++], "%7s", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%s", readl_relaxed(ring->tqp->io_base + HNS3_RING_EN_REG) ? "on" : "off"); if (hnae3_ae_dev_tqp_txrx_indep_supported(ae_dev)) - sprintf(result[j++], "%10s", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%s", readl_relaxed(ring->tqp->io_base + HNS3_RING_TX_EN_REG) ? "on" : "off"); else - sprintf(result[j++], "%10s", "NA"); + sprintf(result[j++], "%s", "NA"); base_add_h = readl_relaxed(ring->tqp->io_base + HNS3_RING_TX_RING_BASEADDR_H_REG); @@ -848,15 +848,15 @@ static void hns3_dump_rx_bd_info(struct hns3_nic_priv *priv, { unsigned int j = 0; - sprintf(result[j++], "%5d", idx); + sprintf(result[j++], "%d", idx); sprintf(result[j++], "%#x", le32_to_cpu(desc->rx.l234_info)); - sprintf(result[j++], "%7u", le16_to_cpu(desc->rx.pkt_len)); - sprintf(result[j++], "%4u", le16_to_cpu(desc->rx.size)); + sprintf(result[j++], "%u", le16_to_cpu(desc->rx.pkt_len)); + sprintf(result[j++], "%u", le16_to_cpu(desc->rx.size)); sprintf(result[j++], "%#x", le32_to_cpu(desc->rx.rss_hash)); - sprintf(result[j++], "%5u", le16_to_cpu(desc->rx.fd_id)); - sprintf(result[j++], "%8u", le16_to_cpu(desc->rx.vlan_tag)); - sprintf(result[j++], "%15u", le16_to_cpu(desc->rx.o_dm_vlan_id_fb)); - sprintf(result[j++], "%11u", le16_to_cpu(desc->rx.ot_vlan_tag)); + sprintf(result[j++], "%u", le16_to_cpu(desc->rx.fd_id)); + sprintf(result[j++], "%u", le16_to_cpu(desc->rx.vlan_tag)); + sprintf(result[j++], "%u", le16_to_cpu(desc->rx.o_dm_vlan_id_fb)); + sprintf(result[j++], "%u", le16_to_cpu(desc->rx.ot_vlan_tag)); sprintf(result[j++], "%#x", le32_to_cpu(desc->rx.bd_base_info)); if (test_bit(HNS3_NIC_STATE_RXD_ADV_LAYOUT_ENABLE, &priv->state)) { u32 ol_info = le32_to_cpu(desc->rx.ol_info); @@ -930,19 +930,19 @@ static void hns3_dump_tx_bd_info(struct hns3_nic_priv *priv, { unsigned int j = 0; - sprintf(result[j++], "%6d", idx); + sprintf(result[j++], "%d", idx); sprintf(result[j++], "%#llx", le64_to_cpu(desc->addr)); - sprintf(result[j++], "%5u", le16_to_cpu(desc->tx.vlan_tag)); - sprintf(result[j++], "%5u", le16_to_cpu(desc->tx.send_size)); + sprintf(result[j++], "%u", le16_to_cpu(desc->tx.vlan_tag)); + sprintf(result[j++], "%u", le16_to_cpu(desc->tx.send_size)); sprintf(result[j++], "%#x", le32_to_cpu(desc->tx.type_cs_vlan_tso_len)); - sprintf(result[j++], "%5u", le16_to_cpu(desc->tx.outer_vlan_tag)); - sprintf(result[j++], "%5u", le16_to_cpu(desc->tx.tv)); - sprintf(result[j++], "%10u", + sprintf(result[j++], "%u", le16_to_cpu(desc->tx.outer_vlan_tag)); + sprintf(result[j++], "%u", le16_to_cpu(desc->tx.tv)); + sprintf(result[j++], "%u", le32_to_cpu(desc->tx.ol_type_vlan_len_msec)); sprintf(result[j++], "%#x", le32_to_cpu(desc->tx.paylen_ol4cs)); sprintf(result[j++], "%#x", le16_to_cpu(desc->tx.bdtp_fe_sc_vld_ra_ri)); - sprintf(result[j++], "%5u", le16_to_cpu(desc->tx.mss_hw_csum)); + sprintf(result[j++], "%u", le16_to_cpu(desc->tx.mss_hw_csum)); } static int hns3_dbg_tx_bd_info(struct hns3_dbg_data *d, char *buf, int len) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index 14dc12c2155d..a3ee7875d6a7 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -5203,6 +5203,13 @@ static void hns3_state_init(struct hnae3_handle *handle) set_bit(HNS3_NIC_STATE_RXD_ADV_LAYOUT_ENABLE, &priv->state); } +static void hns3_state_uninit(struct hnae3_handle *handle) +{ + struct hns3_nic_priv *priv = handle->priv; + + clear_bit(HNS3_NIC_STATE_INITED, &priv->state); +} + static int hns3_client_init(struct hnae3_handle *handle) { struct pci_dev *pdev = handle->pdev; @@ -5320,7 +5327,9 @@ static int hns3_client_init(struct hnae3_handle *handle) return ret; out_reg_netdev_fail: + hns3_state_uninit(handle); hns3_dbg_uninit(handle); + hns3_client_stop(handle); out_client_start: hns3_free_rx_cpu_rmap(netdev); hns3_nic_uninit_irq(priv); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c index 6799d16de34b..7998ca617a92 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c @@ -94,6 +94,13 @@ static int hclge_send_mbx_msg(struct hclge_vport *vport, u8 *msg, u16 msg_len, enum hclge_comm_cmd_status status; struct hclge_desc desc; + if (msg_len > HCLGE_MBX_MAX_MSG_SIZE) { + dev_err(&hdev->pdev->dev, + "msg data length(=%u) exceeds maximum(=%u)\n", + msg_len, HCLGE_MBX_MAX_MSG_SIZE); + return -EMSGSIZE; + } + resp_pf_to_vf = (struct hclge_mbx_pf_to_vf_cmd *)desc.data; hclge_cmd_setup_basic_desc(&desc, HCLGEVF_OPC_MBX_PF_TO_VF, false); @@ -176,7 +183,7 @@ static int hclge_get_ring_chain_from_mbx( ring_num = req->msg.ring_num; if (ring_num > HCLGE_MBX_MAX_RING_CHAIN_PARAM_NUM) - return -ENOMEM; + return -EINVAL; for (i = 0; i < ring_num; i++) { if (req->msg.param[i].tqp_index >= vport->nic.kinfo.rss_size) { @@ -587,9 +594,9 @@ static int hclge_set_vf_mtu(struct hclge_vport *vport, return hclge_set_vport_mtu(vport, mtu); } -static void hclge_get_queue_id_in_pf(struct hclge_vport *vport, - struct hclge_mbx_vf_to_pf_cmd *mbx_req, - struct hclge_respond_to_vf_msg *resp_msg) +static int hclge_get_queue_id_in_pf(struct hclge_vport *vport, + struct hclge_mbx_vf_to_pf_cmd *mbx_req, + struct hclge_respond_to_vf_msg *resp_msg) { struct hnae3_handle *handle = &vport->nic; struct hclge_dev *hdev = vport->back; @@ -599,17 +606,18 @@ static void hclge_get_queue_id_in_pf(struct hclge_vport *vport, if (queue_id >= handle->kinfo.num_tqps) { dev_err(&hdev->pdev->dev, "Invalid queue id(%u) from VF %u\n", queue_id, mbx_req->mbx_src_vfid); - return; + return -EINVAL; } qid_in_pf = hclge_covert_handle_qid_global(&vport->nic, queue_id); memcpy(resp_msg->data, &qid_in_pf, sizeof(qid_in_pf)); resp_msg->len = sizeof(qid_in_pf); + return 0; } -static void hclge_get_rss_key(struct hclge_vport *vport, - struct hclge_mbx_vf_to_pf_cmd *mbx_req, - struct hclge_respond_to_vf_msg *resp_msg) +static int hclge_get_rss_key(struct hclge_vport *vport, + struct hclge_mbx_vf_to_pf_cmd *mbx_req, + struct hclge_respond_to_vf_msg *resp_msg) { #define HCLGE_RSS_MBX_RESP_LEN 8 struct hclge_dev *hdev = vport->back; @@ -627,13 +635,14 @@ static void hclge_get_rss_key(struct hclge_vport *vport, dev_warn(&hdev->pdev->dev, "failed to get the rss hash key, the index(%u) invalid !\n", index); - return; + return -EINVAL; } memcpy(resp_msg->data, &rss_cfg->rss_hash_key[index * HCLGE_RSS_MBX_RESP_LEN], HCLGE_RSS_MBX_RESP_LEN); resp_msg->len = HCLGE_RSS_MBX_RESP_LEN; + return 0; } static void hclge_link_fail_parse(struct hclge_dev *hdev, u8 link_fail_code) @@ -809,10 +818,10 @@ void hclge_mbx_handler(struct hclge_dev *hdev) "VF fail(%d) to set mtu\n", ret); break; case HCLGE_MBX_GET_QID_IN_PF: - hclge_get_queue_id_in_pf(vport, req, &resp_msg); + ret = hclge_get_queue_id_in_pf(vport, req, &resp_msg); break; case HCLGE_MBX_GET_RSS_KEY: - hclge_get_rss_key(vport, req, &resp_msg); + ret = hclge_get_rss_key(vport, req, &resp_msg); break; case HCLGE_MBX_GET_LINK_MODE: hclge_get_link_mode(vport, req); diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.c index 2d9b06d7caad..f7dc7d825f63 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.c @@ -771,7 +771,7 @@ struct hinic_hw_wqe *hinic_get_wqe(struct hinic_wq *wq, unsigned int wqe_size, /* If we only have one page, still need to get shadown wqe when * wqe rolling-over page */ - if (curr_pg != end_pg || MASKED_WQE_IDX(wq, end_prod_idx) < *prod_idx) { + if (curr_pg != end_pg || end_prod_idx < *prod_idx) { void *shadow_addr = &wq->shadow_wqe[curr_pg * wq->max_wqe_size]; copy_wqe_to_shadow(wq, shadow_addr, num_wqebbs, *prod_idx); @@ -841,7 +841,10 @@ struct hinic_hw_wqe *hinic_read_wqe(struct hinic_wq *wq, unsigned int wqe_size, *cons_idx = curr_cons_idx; - if (curr_pg != end_pg) { + /* If we only have one page, still need to get shadown wqe when + * wqe rolling-over page + */ + if (curr_pg != end_pg || end_cons_idx < curr_cons_idx) { void *shadow_addr = &wq->shadow_wqe[curr_pg * wq->max_wqe_size]; copy_wqe_to_shadow(wq, shadow_addr, num_wqebbs, *cons_idx); diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 77683909ca3d..5c5931dba51d 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -3210,13 +3210,8 @@ static void ibmvnic_get_ringparam(struct net_device *netdev, { struct ibmvnic_adapter *adapter = netdev_priv(netdev); - if (adapter->priv_flags & IBMVNIC_USE_SERVER_MAXES) { - ring->rx_max_pending = adapter->max_rx_add_entries_per_subcrq; - ring->tx_max_pending = adapter->max_tx_entries_per_subcrq; - } else { - ring->rx_max_pending = IBMVNIC_MAX_QUEUE_SZ; - ring->tx_max_pending = IBMVNIC_MAX_QUEUE_SZ; - } + ring->rx_max_pending = adapter->max_rx_add_entries_per_subcrq; + ring->tx_max_pending = adapter->max_tx_entries_per_subcrq; ring->rx_mini_max_pending = 0; ring->rx_jumbo_max_pending = 0; ring->rx_pending = adapter->req_rx_add_entries_per_subcrq; @@ -3231,23 +3226,21 @@ static int ibmvnic_set_ringparam(struct net_device *netdev, struct netlink_ext_ack *extack) { struct ibmvnic_adapter *adapter = netdev_priv(netdev); - int ret; - ret = 0; + if (ring->rx_pending > adapter->max_rx_add_entries_per_subcrq || + ring->tx_pending > adapter->max_tx_entries_per_subcrq) { + netdev_err(netdev, "Invalid request.\n"); + netdev_err(netdev, "Max tx buffers = %llu\n", + adapter->max_rx_add_entries_per_subcrq); + netdev_err(netdev, "Max rx buffers = %llu\n", + adapter->max_tx_entries_per_subcrq); + return -EINVAL; + } + adapter->desired.rx_entries = ring->rx_pending; adapter->desired.tx_entries = ring->tx_pending; - ret = wait_for_reset(adapter); - - if (!ret && - (adapter->req_rx_add_entries_per_subcrq != ring->rx_pending || - adapter->req_tx_entries_per_subcrq != ring->tx_pending)) - netdev_info(netdev, - "Could not match full ringsize request. Requested: RX %d, TX %d; Allowed: RX %llu, TX %llu\n", - ring->rx_pending, ring->tx_pending, - adapter->req_rx_add_entries_per_subcrq, - adapter->req_tx_entries_per_subcrq); - return ret; + return wait_for_reset(adapter); } static void ibmvnic_get_channels(struct net_device *netdev, @@ -3255,14 +3248,8 @@ static void ibmvnic_get_channels(struct net_device *netdev, { struct ibmvnic_adapter *adapter = netdev_priv(netdev); - if (adapter->priv_flags & IBMVNIC_USE_SERVER_MAXES) { - channels->max_rx = adapter->max_rx_queues; - channels->max_tx = adapter->max_tx_queues; - } else { - channels->max_rx = IBMVNIC_MAX_QUEUES; - channels->max_tx = IBMVNIC_MAX_QUEUES; - } - + channels->max_rx = adapter->max_rx_queues; + channels->max_tx = adapter->max_tx_queues; channels->max_other = 0; channels->max_combined = 0; channels->rx_count = adapter->req_rx_queues; @@ -3275,22 +3262,11 @@ static int ibmvnic_set_channels(struct net_device *netdev, struct ethtool_channels *channels) { struct ibmvnic_adapter *adapter = netdev_priv(netdev); - int ret; - ret = 0; adapter->desired.rx_queues = channels->rx_count; adapter->desired.tx_queues = channels->tx_count; - ret = wait_for_reset(adapter); - - if (!ret && - (adapter->req_rx_queues != channels->rx_count || - adapter->req_tx_queues != channels->tx_count)) - netdev_info(netdev, - "Could not match full channels request. Requested: RX %d, TX %d; Allowed: RX %llu, TX %llu\n", - channels->rx_count, channels->tx_count, - adapter->req_rx_queues, adapter->req_tx_queues); - return ret; + return wait_for_reset(adapter); } static void ibmvnic_get_strings(struct net_device *dev, u32 stringset, u8 *data) @@ -3298,43 +3274,32 @@ static void ibmvnic_get_strings(struct net_device *dev, u32 stringset, u8 *data) struct ibmvnic_adapter *adapter = netdev_priv(dev); int i; - switch (stringset) { - case ETH_SS_STATS: - for (i = 0; i < ARRAY_SIZE(ibmvnic_stats); - i++, data += ETH_GSTRING_LEN) - memcpy(data, ibmvnic_stats[i].name, ETH_GSTRING_LEN); + if (stringset != ETH_SS_STATS) + return; - for (i = 0; i < adapter->req_tx_queues; i++) { - snprintf(data, ETH_GSTRING_LEN, "tx%d_packets", i); - data += ETH_GSTRING_LEN; + for (i = 0; i < ARRAY_SIZE(ibmvnic_stats); i++, data += ETH_GSTRING_LEN) + memcpy(data, ibmvnic_stats[i].name, ETH_GSTRING_LEN); - snprintf(data, ETH_GSTRING_LEN, "tx%d_bytes", i); - data += ETH_GSTRING_LEN; + for (i = 0; i < adapter->req_tx_queues; i++) { + snprintf(data, ETH_GSTRING_LEN, "tx%d_packets", i); + data += ETH_GSTRING_LEN; - snprintf(data, ETH_GSTRING_LEN, - "tx%d_dropped_packets", i); - data += ETH_GSTRING_LEN; - } + snprintf(data, ETH_GSTRING_LEN, "tx%d_bytes", i); + data += ETH_GSTRING_LEN; - for (i = 0; i < adapter->req_rx_queues; i++) { - snprintf(data, ETH_GSTRING_LEN, "rx%d_packets", i); - data += ETH_GSTRING_LEN; + snprintf(data, ETH_GSTRING_LEN, "tx%d_dropped_packets", i); + data += ETH_GSTRING_LEN; + } - snprintf(data, ETH_GSTRING_LEN, "rx%d_bytes", i); - data += ETH_GSTRING_LEN; + for (i = 0; i < adapter->req_rx_queues; i++) { + snprintf(data, ETH_GSTRING_LEN, "rx%d_packets", i); + data += ETH_GSTRING_LEN; - snprintf(data, ETH_GSTRING_LEN, "rx%d_interrupts", i); - data += ETH_GSTRING_LEN; - } - break; + snprintf(data, ETH_GSTRING_LEN, "rx%d_bytes", i); + data += ETH_GSTRING_LEN; - case ETH_SS_PRIV_FLAGS: - for (i = 0; i < ARRAY_SIZE(ibmvnic_priv_flags); i++) - strcpy(data + i * ETH_GSTRING_LEN, - ibmvnic_priv_flags[i]); - break; - default: - return; + snprintf(data, ETH_GSTRING_LEN, "rx%d_interrupts", i); + data += ETH_GSTRING_LEN; } } @@ -3347,8 +3312,6 @@ static int ibmvnic_get_sset_count(struct net_device *dev, int sset) return ARRAY_SIZE(ibmvnic_stats) + adapter->req_tx_queues * NUM_TX_STATS + adapter->req_rx_queues * NUM_RX_STATS; - case ETH_SS_PRIV_FLAGS: - return ARRAY_SIZE(ibmvnic_priv_flags); default: return -EOPNOTSUPP; } @@ -3401,26 +3364,6 @@ static void ibmvnic_get_ethtool_stats(struct net_device *dev, } } -static u32 ibmvnic_get_priv_flags(struct net_device *netdev) -{ - struct ibmvnic_adapter *adapter = netdev_priv(netdev); - - return adapter->priv_flags; -} - -static int ibmvnic_set_priv_flags(struct net_device *netdev, u32 flags) -{ - struct ibmvnic_adapter *adapter = netdev_priv(netdev); - bool which_maxes = !!(flags & IBMVNIC_USE_SERVER_MAXES); - - if (which_maxes) - adapter->priv_flags |= IBMVNIC_USE_SERVER_MAXES; - else - adapter->priv_flags &= ~IBMVNIC_USE_SERVER_MAXES; - - return 0; -} - static const struct ethtool_ops ibmvnic_ethtool_ops = { .get_drvinfo = ibmvnic_get_drvinfo, .get_msglevel = ibmvnic_get_msglevel, @@ -3434,8 +3377,6 @@ static const struct ethtool_ops ibmvnic_ethtool_ops = { .get_sset_count = ibmvnic_get_sset_count, .get_ethtool_stats = ibmvnic_get_ethtool_stats, .get_link_ksettings = ibmvnic_get_link_ksettings, - .get_priv_flags = ibmvnic_get_priv_flags, - .set_priv_flags = ibmvnic_set_priv_flags, }; /* Routines for managing CRQs/sCRQs */ diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h index 8f5cefb932dd..1310c861bf83 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.h +++ b/drivers/net/ethernet/ibm/ibmvnic.h @@ -41,11 +41,6 @@ #define IBMVNIC_RESET_DELAY 100 -static const char ibmvnic_priv_flags[][ETH_GSTRING_LEN] = { -#define IBMVNIC_USE_SERVER_MAXES 0x1 - "use-server-maxes" -}; - struct ibmvnic_login_buffer { __be32 len; __be32 version; @@ -883,7 +878,6 @@ struct ibmvnic_adapter { struct ibmvnic_control_ip_offload_buffer ip_offload_ctrl; dma_addr_t ip_offload_ctrl_tok; u32 msg_enable; - u32 priv_flags; /* Vital Product Data (VPD) */ struct ibmvnic_vpd *vpd; diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c index d60e2016d03c..e6c8e6d5234f 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.c +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c @@ -1009,8 +1009,8 @@ static s32 e1000_platform_pm_pch_lpt(struct e1000_hw *hw, bool link) { u32 reg = link << (E1000_LTRV_REQ_SHIFT + E1000_LTRV_NOSNOOP_SHIFT) | link << E1000_LTRV_REQ_SHIFT | E1000_LTRV_SEND; - u16 max_ltr_enc_d = 0; /* maximum LTR decoded by platform */ - u16 lat_enc_d = 0; /* latency decoded */ + u32 max_ltr_enc_d = 0; /* maximum LTR decoded by platform */ + u32 lat_enc_d = 0; /* latency decoded */ u16 lat_enc = 0; /* latency encoded */ if (link) { diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 6778df2177a1..98871f014994 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -7549,42 +7549,43 @@ static void i40e_free_macvlan_channels(struct i40e_vsi *vsi) static int i40e_fwd_ring_up(struct i40e_vsi *vsi, struct net_device *vdev, struct i40e_fwd_adapter *fwd) { + struct i40e_channel *ch = NULL, *ch_tmp, *iter; int ret = 0, num_tc = 1, i, aq_err; - struct i40e_channel *ch, *ch_tmp; struct i40e_pf *pf = vsi->back; struct i40e_hw *hw = &pf->hw; - if (list_empty(&vsi->macvlan_list)) - return -EINVAL; - /* Go through the list and find an available channel */ - list_for_each_entry_safe(ch, ch_tmp, &vsi->macvlan_list, list) { - if (!i40e_is_channel_macvlan(ch)) { - ch->fwd = fwd; + list_for_each_entry_safe(iter, ch_tmp, &vsi->macvlan_list, list) { + if (!i40e_is_channel_macvlan(iter)) { + iter->fwd = fwd; /* record configuration for macvlan interface in vdev */ for (i = 0; i < num_tc; i++) netdev_bind_sb_channel_queue(vsi->netdev, vdev, i, - ch->num_queue_pairs, - ch->base_queue); - for (i = 0; i < ch->num_queue_pairs; i++) { + iter->num_queue_pairs, + iter->base_queue); + for (i = 0; i < iter->num_queue_pairs; i++) { struct i40e_ring *tx_ring, *rx_ring; u16 pf_q; - pf_q = ch->base_queue + i; + pf_q = iter->base_queue + i; /* Get to TX ring ptr */ tx_ring = vsi->tx_rings[pf_q]; - tx_ring->ch = ch; + tx_ring->ch = iter; /* Get the RX ring ptr */ rx_ring = vsi->rx_rings[pf_q]; - rx_ring->ch = ch; + rx_ring->ch = iter; } + ch = iter; break; } } + if (!ch) + return -EINVAL; + /* Guarantee all rings are updated before we update the * MAC address filter. */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 190590d32faf..7dfcf78b57fb 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -2871,7 +2871,6 @@ continue_reset: running = adapter->state == __IAVF_RUNNING; if (running) { - netdev->flags &= ~IFF_UP; netif_carrier_off(netdev); netif_tx_stop_all_queues(netdev); adapter->link_up = false; @@ -2988,7 +2987,7 @@ continue_reset: * to __IAVF_RUNNING */ iavf_up_complete(adapter); - netdev->flags |= IFF_UP; + iavf_irq_enable(adapter, true); } else { iavf_change_state(adapter, __IAVF_DOWN); @@ -3004,10 +3003,8 @@ continue_reset: reset_err: mutex_unlock(&adapter->client_lock); mutex_unlock(&adapter->crit_lock); - if (running) { + if (running) iavf_change_state(adapter, __IAVF_RUNNING); - netdev->flags |= IFF_UP; - } dev_err(&adapter->pdev->dev, "failed to allocate resources during reinit\n"); iavf_close(netdev); } diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index d4f1874df7d0..a895e3a8e988 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -301,7 +301,6 @@ enum ice_vsi_state { ICE_VSI_NETDEV_REGISTERED, ICE_VSI_UMAC_FLTR_CHANGED, ICE_VSI_MMAC_FLTR_CHANGED, - ICE_VSI_VLAN_FLTR_CHANGED, ICE_VSI_PROMISC_CHANGED, ICE_VSI_STATE_NBITS /* must be last */ }; @@ -541,6 +540,7 @@ struct ice_pf { struct mutex avail_q_mutex; /* protects access to avail_[rx|tx]qs */ struct mutex sw_mutex; /* lock for protecting VSI alloc flow */ struct mutex tc_mutex; /* lock to protect TC changes */ + struct mutex adev_mutex; /* lock to protect aux device access */ u32 msg_enable; struct ice_ptp ptp; struct tty_driver *ice_gnss_tty_driver; @@ -672,7 +672,7 @@ static inline struct ice_pf *ice_netdev_to_pf(struct net_device *netdev) static inline bool ice_is_xdp_ena_vsi(struct ice_vsi *vsi) { - return !!vsi->xdp_prog; + return !!READ_ONCE(vsi->xdp_prog); } static inline void ice_set_ring_xdp(struct ice_tx_ring *ring) diff --git a/drivers/net/ethernet/intel/ice/ice_arfs.c b/drivers/net/ethernet/intel/ice/ice_arfs.c index 5daade32ea62..fba178e07600 100644 --- a/drivers/net/ethernet/intel/ice/ice_arfs.c +++ b/drivers/net/ethernet/intel/ice/ice_arfs.c @@ -577,7 +577,7 @@ void ice_free_cpu_rx_rmap(struct ice_vsi *vsi) { struct net_device *netdev; - if (!vsi || vsi->type != ICE_VSI_PF || !vsi->arfs_fltr_list) + if (!vsi || vsi->type != ICE_VSI_PF) return; netdev = vsi->netdev; @@ -599,7 +599,7 @@ int ice_set_cpu_rx_rmap(struct ice_vsi *vsi) int base_idx, i; if (!vsi || vsi->type != ICE_VSI_PF) - return -EINVAL; + return 0; pf = vsi->back; netdev = vsi->netdev; @@ -636,7 +636,6 @@ void ice_remove_arfs(struct ice_pf *pf) if (!pf_vsi) return; - ice_free_cpu_rx_rmap(pf_vsi); ice_clear_arfs(pf_vsi); } @@ -653,9 +652,5 @@ void ice_rebuild_arfs(struct ice_pf *pf) return; ice_remove_arfs(pf); - if (ice_set_cpu_rx_rmap(pf_vsi)) { - dev_err(ice_pf_to_dev(pf), "Failed to rebuild aRFS\n"); - return; - } ice_init_arfs(pf_vsi); } diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.c b/drivers/net/ethernet/intel/ice/ice_eswitch.c index 9a84d746a6c4..6a463b242c7d 100644 --- a/drivers/net/ethernet/intel/ice/ice_eswitch.c +++ b/drivers/net/ethernet/intel/ice/ice_eswitch.c @@ -361,7 +361,8 @@ ice_eswitch_port_start_xmit(struct sk_buff *skb, struct net_device *netdev) np = netdev_priv(netdev); vsi = np->vsi; - if (ice_is_reset_in_progress(vsi->back->state)) + if (ice_is_reset_in_progress(vsi->back->state) || + test_bit(ICE_VF_DIS, vsi->back->state)) return NETDEV_TX_BUSY; repr = ice_netdev_to_repr(netdev); diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.h b/drivers/net/ethernet/intel/ice/ice_eswitch.h index bd58d9d2e565..6a413331572b 100644 --- a/drivers/net/ethernet/intel/ice/ice_eswitch.h +++ b/drivers/net/ethernet/intel/ice/ice_eswitch.h @@ -52,7 +52,7 @@ static inline void ice_eswitch_update_repr(struct ice_vsi *vsi) { } static inline int ice_eswitch_configure(struct ice_pf *pf) { - return -EOPNOTSUPP; + return 0; } static inline int ice_eswitch_rebuild(struct ice_pf *pf) diff --git a/drivers/net/ethernet/intel/ice/ice_fltr.c b/drivers/net/ethernet/intel/ice/ice_fltr.c index af57eb114966..85a94483c2ed 100644 --- a/drivers/net/ethernet/intel/ice/ice_fltr.c +++ b/drivers/net/ethernet/intel/ice/ice_fltr.c @@ -58,7 +58,16 @@ int ice_fltr_set_vlan_vsi_promisc(struct ice_hw *hw, struct ice_vsi *vsi, u8 promisc_mask) { - return ice_set_vlan_vsi_promisc(hw, vsi->idx, promisc_mask, false); + struct ice_pf *pf = hw->back; + int result; + + result = ice_set_vlan_vsi_promisc(hw, vsi->idx, promisc_mask, false); + if (result) + dev_err(ice_pf_to_dev(pf), + "Error setting promisc mode on VSI %i (rc=%d)\n", + vsi->vsi_num, result); + + return result; } /** @@ -73,7 +82,16 @@ int ice_fltr_clear_vlan_vsi_promisc(struct ice_hw *hw, struct ice_vsi *vsi, u8 promisc_mask) { - return ice_set_vlan_vsi_promisc(hw, vsi->idx, promisc_mask, true); + struct ice_pf *pf = hw->back; + int result; + + result = ice_set_vlan_vsi_promisc(hw, vsi->idx, promisc_mask, true); + if (result) + dev_err(ice_pf_to_dev(pf), + "Error clearing promisc mode on VSI %i (rc=%d)\n", + vsi->vsi_num, result); + + return result; } /** @@ -87,7 +105,16 @@ int ice_fltr_clear_vsi_promisc(struct ice_hw *hw, u16 vsi_handle, u8 promisc_mask, u16 vid) { - return ice_clear_vsi_promisc(hw, vsi_handle, promisc_mask, vid); + struct ice_pf *pf = hw->back; + int result; + + result = ice_clear_vsi_promisc(hw, vsi_handle, promisc_mask, vid); + if (result) + dev_err(ice_pf_to_dev(pf), + "Error clearing promisc mode on VSI %i for VID %u (rc=%d)\n", + ice_get_hw_vsi_num(hw, vsi_handle), vid, result); + + return result; } /** @@ -101,7 +128,16 @@ int ice_fltr_set_vsi_promisc(struct ice_hw *hw, u16 vsi_handle, u8 promisc_mask, u16 vid) { - return ice_set_vsi_promisc(hw, vsi_handle, promisc_mask, vid); + struct ice_pf *pf = hw->back; + int result; + + result = ice_set_vsi_promisc(hw, vsi_handle, promisc_mask, vid); + if (result) + dev_err(ice_pf_to_dev(pf), + "Error setting promisc mode on VSI %i for VID %u (rc=%d)\n", + ice_get_hw_vsi_num(hw, vsi_handle), vid, result); + + return result; } /** diff --git a/drivers/net/ethernet/intel/ice/ice_idc.c b/drivers/net/ethernet/intel/ice/ice_idc.c index 25a436d342c2..3e3b2ed4cd5d 100644 --- a/drivers/net/ethernet/intel/ice/ice_idc.c +++ b/drivers/net/ethernet/intel/ice/ice_idc.c @@ -37,14 +37,17 @@ void ice_send_event_to_aux(struct ice_pf *pf, struct iidc_event *event) if (WARN_ON_ONCE(!in_task())) return; + mutex_lock(&pf->adev_mutex); if (!pf->adev) - return; + goto finish; device_lock(&pf->adev->dev); iadrv = ice_get_auxiliary_drv(pf); if (iadrv && iadrv->event_handler) iadrv->event_handler(pf, event); device_unlock(&pf->adev->dev); +finish: + mutex_unlock(&pf->adev_mutex); } /** @@ -290,7 +293,6 @@ int ice_plug_aux_dev(struct ice_pf *pf) return -ENOMEM; adev = &iadev->adev; - pf->adev = adev; iadev->pf = pf; adev->id = pf->aux_idx; @@ -300,18 +302,20 @@ int ice_plug_aux_dev(struct ice_pf *pf) ret = auxiliary_device_init(adev); if (ret) { - pf->adev = NULL; kfree(iadev); return ret; } ret = auxiliary_device_add(adev); if (ret) { - pf->adev = NULL; auxiliary_device_uninit(adev); return ret; } + mutex_lock(&pf->adev_mutex); + pf->adev = adev; + mutex_unlock(&pf->adev_mutex); + return 0; } @@ -320,12 +324,17 @@ int ice_plug_aux_dev(struct ice_pf *pf) */ void ice_unplug_aux_dev(struct ice_pf *pf) { - if (!pf->adev) - return; + struct auxiliary_device *adev; - auxiliary_device_delete(pf->adev); - auxiliary_device_uninit(pf->adev); + mutex_lock(&pf->adev_mutex); + adev = pf->adev; pf->adev = NULL; + mutex_unlock(&pf->adev_mutex); + + if (adev) { + auxiliary_device_delete(adev); + auxiliary_device_uninit(adev); + } } /** diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index b897926f817d..454e01ae09b9 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -1480,6 +1480,7 @@ static int ice_vsi_alloc_rings(struct ice_vsi *vsi) ring->tx_tstamps = &pf->ptp.port.tx; ring->dev = dev; ring->count = vsi->num_tx_desc; + ring->txq_teid = ICE_INVAL_TEID; if (dvm_ena) ring->flags |= ICE_TX_FLAGS_RING_VLAN_L2TAG2; else @@ -2688,6 +2689,8 @@ void ice_vsi_free_irq(struct ice_vsi *vsi) return; vsi->irqs_ready = false; + ice_free_cpu_rx_rmap(vsi); + ice_for_each_q_vector(vsi, i) { u16 vector = i + base; int irq_num; @@ -2701,7 +2704,8 @@ void ice_vsi_free_irq(struct ice_vsi *vsi) continue; /* clear the affinity notifier in the IRQ descriptor */ - irq_set_affinity_notifier(irq_num, NULL); + if (!IS_ENABLED(CONFIG_RFS_ACCEL)) + irq_set_affinity_notifier(irq_num, NULL); /* clear the affinity_mask in the IRQ descriptor */ irq_set_affinity_hint(irq_num, NULL); @@ -2983,6 +2987,8 @@ int ice_vsi_release(struct ice_vsi *vsi) } } + if (ice_is_vsi_dflt_vsi(pf->first_sw, vsi)) + ice_clear_dflt_vsi(pf->first_sw); ice_fltr_remove_all(vsi); ice_rm_vsi_lan_cfg(vsi->port_info, vsi->idx); err = ice_rm_vsi_rdma_cfg(vsi->port_info, vsi->idx); @@ -3037,8 +3043,8 @@ ice_vsi_rebuild_get_coalesce(struct ice_vsi *vsi, ice_for_each_q_vector(vsi, i) { struct ice_q_vector *q_vector = vsi->q_vectors[i]; - coalesce[i].itr_tx = q_vector->tx.itr_setting; - coalesce[i].itr_rx = q_vector->rx.itr_setting; + coalesce[i].itr_tx = q_vector->tx.itr_settings; + coalesce[i].itr_rx = q_vector->rx.itr_settings; coalesce[i].intrl = q_vector->intrl; if (i < vsi->num_txq) @@ -3094,21 +3100,21 @@ ice_vsi_rebuild_set_coalesce(struct ice_vsi *vsi, */ if (i < vsi->alloc_rxq && coalesce[i].rx_valid) { rc = &vsi->q_vectors[i]->rx; - rc->itr_setting = coalesce[i].itr_rx; + rc->itr_settings = coalesce[i].itr_rx; ice_write_itr(rc, rc->itr_setting); } else if (i < vsi->alloc_rxq) { rc = &vsi->q_vectors[i]->rx; - rc->itr_setting = coalesce[0].itr_rx; + rc->itr_settings = coalesce[0].itr_rx; ice_write_itr(rc, rc->itr_setting); } if (i < vsi->alloc_txq && coalesce[i].tx_valid) { rc = &vsi->q_vectors[i]->tx; - rc->itr_setting = coalesce[i].itr_tx; + rc->itr_settings = coalesce[i].itr_tx; ice_write_itr(rc, rc->itr_setting); } else if (i < vsi->alloc_txq) { rc = &vsi->q_vectors[i]->tx; - rc->itr_setting = coalesce[0].itr_tx; + rc->itr_settings = coalesce[0].itr_tx; ice_write_itr(rc, rc->itr_setting); } @@ -3122,12 +3128,12 @@ ice_vsi_rebuild_set_coalesce(struct ice_vsi *vsi, for (; i < vsi->num_q_vectors; i++) { /* transmit */ rc = &vsi->q_vectors[i]->tx; - rc->itr_setting = coalesce[0].itr_tx; + rc->itr_settings = coalesce[0].itr_tx; ice_write_itr(rc, rc->itr_setting); /* receive */ rc = &vsi->q_vectors[i]->rx; - rc->itr_setting = coalesce[0].itr_rx; + rc->itr_settings = coalesce[0].itr_rx; ice_write_itr(rc, rc->itr_setting); vsi->q_vectors[i]->intrl = coalesce[0].intrl; diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index b588d7995631..963a5f40e071 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -243,8 +243,7 @@ static int ice_add_mac_to_unsync_list(struct net_device *netdev, const u8 *addr) static bool ice_vsi_fltr_changed(struct ice_vsi *vsi) { return test_bit(ICE_VSI_UMAC_FLTR_CHANGED, vsi->state) || - test_bit(ICE_VSI_MMAC_FLTR_CHANGED, vsi->state) || - test_bit(ICE_VSI_VLAN_FLTR_CHANGED, vsi->state); + test_bit(ICE_VSI_MMAC_FLTR_CHANGED, vsi->state); } /** @@ -260,10 +259,15 @@ static int ice_set_promisc(struct ice_vsi *vsi, u8 promisc_m) if (vsi->type != ICE_VSI_PF) return 0; - if (ice_vsi_has_non_zero_vlans(vsi)) - status = ice_fltr_set_vlan_vsi_promisc(&vsi->back->hw, vsi, promisc_m); - else - status = ice_fltr_set_vsi_promisc(&vsi->back->hw, vsi->idx, promisc_m, 0); + if (ice_vsi_has_non_zero_vlans(vsi)) { + promisc_m |= (ICE_PROMISC_VLAN_RX | ICE_PROMISC_VLAN_TX); + status = ice_fltr_set_vlan_vsi_promisc(&vsi->back->hw, vsi, + promisc_m); + } else { + status = ice_fltr_set_vsi_promisc(&vsi->back->hw, vsi->idx, + promisc_m, 0); + } + return status; } @@ -280,10 +284,15 @@ static int ice_clear_promisc(struct ice_vsi *vsi, u8 promisc_m) if (vsi->type != ICE_VSI_PF) return 0; - if (ice_vsi_has_non_zero_vlans(vsi)) - status = ice_fltr_clear_vlan_vsi_promisc(&vsi->back->hw, vsi, promisc_m); - else - status = ice_fltr_clear_vsi_promisc(&vsi->back->hw, vsi->idx, promisc_m, 0); + if (ice_vsi_has_non_zero_vlans(vsi)) { + promisc_m |= (ICE_PROMISC_VLAN_RX | ICE_PROMISC_VLAN_TX); + status = ice_fltr_clear_vlan_vsi_promisc(&vsi->back->hw, vsi, + promisc_m); + } else { + status = ice_fltr_clear_vsi_promisc(&vsi->back->hw, vsi->idx, + promisc_m, 0); + } + return status; } @@ -302,7 +311,6 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi) struct ice_pf *pf = vsi->back; struct ice_hw *hw = &pf->hw; u32 changed_flags = 0; - u8 promisc_m; int err; if (!vsi->netdev) @@ -320,7 +328,6 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi) if (ice_vsi_fltr_changed(vsi)) { clear_bit(ICE_VSI_UMAC_FLTR_CHANGED, vsi->state); clear_bit(ICE_VSI_MMAC_FLTR_CHANGED, vsi->state); - clear_bit(ICE_VSI_VLAN_FLTR_CHANGED, vsi->state); /* grab the netdev's addr_list_lock */ netif_addr_lock_bh(netdev); @@ -369,29 +376,15 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi) /* check for changes in promiscuous modes */ if (changed_flags & IFF_ALLMULTI) { if (vsi->current_netdev_flags & IFF_ALLMULTI) { - if (ice_vsi_has_non_zero_vlans(vsi)) - promisc_m = ICE_MCAST_VLAN_PROMISC_BITS; - else - promisc_m = ICE_MCAST_PROMISC_BITS; - - err = ice_set_promisc(vsi, promisc_m); + err = ice_set_promisc(vsi, ICE_MCAST_PROMISC_BITS); if (err) { - netdev_err(netdev, "Error setting Multicast promiscuous mode on VSI %i\n", - vsi->vsi_num); vsi->current_netdev_flags &= ~IFF_ALLMULTI; goto out_promisc; } } else { /* !(vsi->current_netdev_flags & IFF_ALLMULTI) */ - if (ice_vsi_has_non_zero_vlans(vsi)) - promisc_m = ICE_MCAST_VLAN_PROMISC_BITS; - else - promisc_m = ICE_MCAST_PROMISC_BITS; - - err = ice_clear_promisc(vsi, promisc_m); + err = ice_clear_promisc(vsi, ICE_MCAST_PROMISC_BITS); if (err) { - netdev_err(netdev, "Error clearing Multicast promiscuous mode on VSI %i\n", - vsi->vsi_num); vsi->current_netdev_flags |= IFF_ALLMULTI; goto out_promisc; } @@ -2517,6 +2510,13 @@ static int ice_vsi_req_irq_msix(struct ice_vsi *vsi, char *basename) irq_set_affinity_hint(irq_num, &q_vector->affinity_mask); } + err = ice_set_cpu_rx_rmap(vsi); + if (err) { + netdev_err(vsi->netdev, "Failed to setup CPU RMAP on VSI %u: %pe\n", + vsi->vsi_num, ERR_PTR(err)); + goto free_q_irqs; + } + vsi->irqs_ready = true; return 0; @@ -2569,7 +2569,7 @@ static int ice_xdp_alloc_setup_rings(struct ice_vsi *vsi) spin_lock_init(&xdp_ring->tx_lock); for (j = 0; j < xdp_ring->count; j++) { tx_desc = ICE_TX_DESC(xdp_ring, j); - tx_desc->cmd_type_offset_bsz = cpu_to_le64(ICE_TX_DESC_DTYPE_DESC_DONE); + tx_desc->cmd_type_offset_bsz = 0; } } @@ -2765,8 +2765,10 @@ free_qmap: ice_for_each_xdp_txq(vsi, i) if (vsi->xdp_rings[i]) { - if (vsi->xdp_rings[i]->desc) + if (vsi->xdp_rings[i]->desc) { + synchronize_rcu(); ice_free_tx_ring(vsi->xdp_rings[i]); + } kfree_rcu(vsi->xdp_rings[i], rcu); vsi->xdp_rings[i] = NULL; } @@ -3488,6 +3490,20 @@ ice_vlan_rx_add_vid(struct net_device *netdev, __be16 proto, u16 vid) if (!vid) return 0; + while (test_and_set_bit(ICE_CFG_BUSY, vsi->state)) + usleep_range(1000, 2000); + + /* Add multicast promisc rule for the VLAN ID to be added if + * all-multicast is currently enabled. + */ + if (vsi->current_netdev_flags & IFF_ALLMULTI) { + ret = ice_fltr_set_vsi_promisc(&vsi->back->hw, vsi->idx, + ICE_MCAST_VLAN_PROMISC_BITS, + vid); + if (ret) + goto finish; + } + vlan_ops = ice_get_compat_vsi_vlan_ops(vsi); /* Add a switch rule for this VLAN ID so its corresponding VLAN tagged @@ -3495,8 +3511,23 @@ ice_vlan_rx_add_vid(struct net_device *netdev, __be16 proto, u16 vid) */ vlan = ICE_VLAN(be16_to_cpu(proto), vid, 0); ret = vlan_ops->add_vlan(vsi, &vlan); - if (!ret) - set_bit(ICE_VSI_VLAN_FLTR_CHANGED, vsi->state); + if (ret) + goto finish; + + /* If all-multicast is currently enabled and this VLAN ID is only one + * besides VLAN-0 we have to update look-up type of multicast promisc + * rule for VLAN-0 from ICE_SW_LKUP_PROMISC to ICE_SW_LKUP_PROMISC_VLAN. + */ + if ((vsi->current_netdev_flags & IFF_ALLMULTI) && + ice_vsi_num_non_zero_vlans(vsi) == 1) { + ice_fltr_clear_vsi_promisc(&vsi->back->hw, vsi->idx, + ICE_MCAST_PROMISC_BITS, 0); + ice_fltr_set_vsi_promisc(&vsi->back->hw, vsi->idx, + ICE_MCAST_VLAN_PROMISC_BITS, 0); + } + +finish: + clear_bit(ICE_CFG_BUSY, vsi->state); return ret; } @@ -3522,6 +3553,9 @@ ice_vlan_rx_kill_vid(struct net_device *netdev, __be16 proto, u16 vid) if (!vid) return 0; + while (test_and_set_bit(ICE_CFG_BUSY, vsi->state)) + usleep_range(1000, 2000); + vlan_ops = ice_get_compat_vsi_vlan_ops(vsi); /* Make sure VLAN delete is successful before updating VLAN @@ -3530,10 +3564,33 @@ ice_vlan_rx_kill_vid(struct net_device *netdev, __be16 proto, u16 vid) vlan = ICE_VLAN(be16_to_cpu(proto), vid, 0); ret = vlan_ops->del_vlan(vsi, &vlan); if (ret) - return ret; + goto finish; - set_bit(ICE_VSI_VLAN_FLTR_CHANGED, vsi->state); - return 0; + /* Remove multicast promisc rule for the removed VLAN ID if + * all-multicast is enabled. + */ + if (vsi->current_netdev_flags & IFF_ALLMULTI) + ice_fltr_clear_vsi_promisc(&vsi->back->hw, vsi->idx, + ICE_MCAST_VLAN_PROMISC_BITS, vid); + + if (!ice_vsi_has_non_zero_vlans(vsi)) { + /* Update look-up type of multicast promisc rule for VLAN 0 + * from ICE_SW_LKUP_PROMISC_VLAN to ICE_SW_LKUP_PROMISC when + * all-multicast is enabled and VLAN 0 is the only VLAN rule. + */ + if (vsi->current_netdev_flags & IFF_ALLMULTI) { + ice_fltr_clear_vsi_promisc(&vsi->back->hw, vsi->idx, + ICE_MCAST_VLAN_PROMISC_BITS, + 0); + ice_fltr_set_vsi_promisc(&vsi->back->hw, vsi->idx, + ICE_MCAST_PROMISC_BITS, 0); + } + } + +finish: + clear_bit(ICE_CFG_BUSY, vsi->state); + + return ret; } /** @@ -3642,20 +3699,12 @@ static int ice_setup_pf_sw(struct ice_pf *pf) */ ice_napi_add(vsi); - status = ice_set_cpu_rx_rmap(vsi); - if (status) { - dev_err(dev, "Failed to set CPU Rx map VSI %d error %d\n", - vsi->vsi_num, status); - goto unroll_napi_add; - } status = ice_init_mac_fltr(pf); if (status) - goto free_cpu_rx_map; + goto unroll_napi_add; return 0; -free_cpu_rx_map: - ice_free_cpu_rx_rmap(vsi); unroll_napi_add: ice_tc_indir_block_unregister(vsi); unroll_cfg_netdev: @@ -3720,6 +3769,7 @@ u16 ice_get_avail_rxq_count(struct ice_pf *pf) static void ice_deinit_pf(struct ice_pf *pf) { ice_service_task_stop(pf); + mutex_destroy(&pf->adev_mutex); mutex_destroy(&pf->sw_mutex); mutex_destroy(&pf->tc_mutex); mutex_destroy(&pf->avail_q_mutex); @@ -3798,6 +3848,7 @@ static int ice_init_pf(struct ice_pf *pf) mutex_init(&pf->sw_mutex); mutex_init(&pf->tc_mutex); + mutex_init(&pf->adev_mutex); INIT_HLIST_HEAD(&pf->aq_wait_list); spin_lock_init(&pf->aq_wait_lock); @@ -5117,7 +5168,6 @@ static int __maybe_unused ice_suspend(struct device *dev) continue; ice_vsi_free_q_vectors(pf->vsi[v]); } - ice_free_cpu_rx_rmap(ice_get_main_vsi(pf)); ice_clear_interrupt_scheme(pf); pci_save_state(pdev); @@ -5475,16 +5525,19 @@ static int ice_set_mac_address(struct net_device *netdev, void *pi) /* Add filter for new MAC. If filter exists, return success */ err = ice_fltr_add_mac(vsi, mac, ICE_FWD_TO_VSI); - if (err == -EEXIST) + if (err == -EEXIST) { /* Although this MAC filter is already present in hardware it's * possible in some cases (e.g. bonding) that dev_addr was * modified outside of the driver and needs to be restored back * to this value. */ netdev_dbg(netdev, "filter for MAC %pM already exists\n", mac); - else if (err) + + return 0; + } else if (err) { /* error if the new filter addition failed */ err = -EADDRNOTAVAIL; + } err_update_filters: if (err) { @@ -6119,9 +6172,10 @@ static int ice_up_complete(struct ice_vsi *vsi) ice_ptp_link_change(pf, pf->hw.pf_id, true); } - /* clear this now, and the first stats read will be used as baseline */ - vsi->stat_offsets_loaded = false; - + /* Perform an initial read of the statistics registers now to + * set the baseline so counters are ready when interface is up + */ + ice_update_eth_stats(vsi); ice_service_task_schedule(pf); return 0; @@ -6878,12 +6932,15 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) dev_dbg(dev, "rebuilding PF after reset_type=%d\n", reset_type); +#define ICE_EMP_RESET_SLEEP_MS 5000 if (reset_type == ICE_RESET_EMPR) { /* If an EMP reset has occurred, any previously pending flash * update will have completed. We no longer know whether or * not the NVM update EMP reset is restricted. */ pf->fw_emp_reset_disabled = false; + + msleep(ICE_EMP_RESET_SLEEP_MS); } err = ice_init_all_ctrlq(hw); diff --git a/drivers/net/ethernet/intel/ice/ice_nvm.c b/drivers/net/ethernet/intel/ice/ice_nvm.c index 4eb0599714f4..13cdb5ea594d 100644 --- a/drivers/net/ethernet/intel/ice/ice_nvm.c +++ b/drivers/net/ethernet/intel/ice/ice_nvm.c @@ -641,6 +641,7 @@ ice_get_orom_civd_data(struct ice_hw *hw, enum ice_bank_select bank, status = ice_read_flash_module(hw, bank, ICE_SR_1ST_OROM_BANK_PTR, 0, orom_data, hw->flash.banks.orom_size); if (status) { + vfree(orom_data); ice_debug(hw, ICE_DBG_NVM, "Unable to read Option ROM data\n"); return status; } diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c index a1cd33273ca4..662947c882e8 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp.c @@ -500,12 +500,19 @@ ice_ptp_read_src_clk_reg(struct ice_pf *pf, struct ptp_system_timestamp *sts) * This function must be called periodically to ensure that the cached value * is never more than 2 seconds old. It must also be called whenever the PHC * time has been changed. + * + * Return: + * * 0 - OK, successfully updated + * * -EAGAIN - PF was busy, need to reschedule the update */ -static void ice_ptp_update_cached_phctime(struct ice_pf *pf) +static int ice_ptp_update_cached_phctime(struct ice_pf *pf) { u64 systime; int i; + if (test_and_set_bit(ICE_CFG_BUSY, pf->state)) + return -EAGAIN; + /* Read the current PHC time */ systime = ice_ptp_read_src_clk_reg(pf, NULL); @@ -528,6 +535,9 @@ static void ice_ptp_update_cached_phctime(struct ice_pf *pf) WRITE_ONCE(vsi->rx_rings[j]->cached_phctime, systime); } } + clear_bit(ICE_CFG_BUSY, pf->state); + + return 0; } /** @@ -2287,6 +2297,7 @@ ice_ptp_init_tx_e810(struct ice_pf *pf, struct ice_ptp_tx *tx) /** * ice_ptp_tx_tstamp_cleanup - Cleanup old timestamp requests that got dropped + * @hw: pointer to the hw struct * @tx: PTP Tx tracker to clean up * * Loop through the Tx timestamp requests and see if any of them have been @@ -2295,7 +2306,7 @@ ice_ptp_init_tx_e810(struct ice_pf *pf, struct ice_ptp_tx *tx) * timestamp will never be captured. This might happen if the packet gets * discarded before it reaches the PHY timestamping block. */ -static void ice_ptp_tx_tstamp_cleanup(struct ice_ptp_tx *tx) +static void ice_ptp_tx_tstamp_cleanup(struct ice_hw *hw, struct ice_ptp_tx *tx) { u8 idx; @@ -2304,11 +2315,16 @@ static void ice_ptp_tx_tstamp_cleanup(struct ice_ptp_tx *tx) for_each_set_bit(idx, tx->in_use, tx->len) { struct sk_buff *skb; + u64 raw_tstamp; /* Check if this SKB has been waiting for too long */ if (time_is_after_jiffies(tx->tstamps[idx].start + 2 * HZ)) continue; + /* Read tstamp to be able to use this register again */ + ice_read_phy_tstamp(hw, tx->quad, idx + tx->quad_offset, + &raw_tstamp); + spin_lock(&tx->lock); skb = tx->tstamps[idx].skb; tx->tstamps[idx].skb = NULL; @@ -2324,17 +2340,18 @@ static void ice_ptp_periodic_work(struct kthread_work *work) { struct ice_ptp *ptp = container_of(work, struct ice_ptp, work.work); struct ice_pf *pf = container_of(ptp, struct ice_pf, ptp); + int err; if (!test_bit(ICE_FLAG_PTP, pf->flags)) return; - ice_ptp_update_cached_phctime(pf); + err = ice_ptp_update_cached_phctime(pf); - ice_ptp_tx_tstamp_cleanup(&pf->ptp.port.tx); + ice_ptp_tx_tstamp_cleanup(&pf->hw, &pf->ptp.port.tx); - /* Run twice a second */ + /* Run twice a second or reschedule if phc update failed */ kthread_queue_delayed_work(ptp->kworker, &ptp->work, - msecs_to_jiffies(500)); + msecs_to_jiffies(err ? 10 : 500)); } /** diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c index 8915a9d39e36..0c438219f7a3 100644 --- a/drivers/net/ethernet/intel/ice/ice_sriov.c +++ b/drivers/net/ethernet/intel/ice/ice_sriov.c @@ -1046,8 +1046,8 @@ int ice_sriov_configure(struct pci_dev *pdev, int num_vfs) if (!num_vfs) { if (!pci_vfs_assigned(pdev)) { - ice_mbx_deinit_snapshot(&pf->hw); ice_free_vfs(pf); + ice_mbx_deinit_snapshot(&pf->hw); if (pf->lag) ice_enable_lag(pf->lag); return 0; diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h index cead3eb149bd..ffb3f6a589da 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx.h @@ -384,9 +384,14 @@ struct ice_ring_container { /* this matches the maximum number of ITR bits, but in usec * values, so it is shifted left one bit (bit zero is ignored) */ - u16 itr_setting:13; - u16 itr_reserved:2; - u16 itr_mode:1; + union { + struct { + u16 itr_setting:13; + u16 itr_reserved:2; + u16 itr_mode:1; + }; + u16 itr_settings; + }; enum ice_container_type type; }; diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c index 3f1a63815bac..2889e050a4c9 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c @@ -1308,12 +1308,51 @@ error_param: } /** + * ice_vf_vsi_dis_single_txq - disable a single Tx queue + * @vf: VF to disable queue for + * @vsi: VSI for the VF + * @q_id: VF relative (0-based) queue ID + * + * Attempt to disable the Tx queue passed in. If the Tx queue was successfully + * disabled then clear q_id bit in the enabled queues bitmap and return + * success. Otherwise return error. + */ +static int +ice_vf_vsi_dis_single_txq(struct ice_vf *vf, struct ice_vsi *vsi, u16 q_id) +{ + struct ice_txq_meta txq_meta = { 0 }; + struct ice_tx_ring *ring; + int err; + + if (!test_bit(q_id, vf->txq_ena)) + dev_dbg(ice_pf_to_dev(vsi->back), "Queue %u on VSI %u is not enabled, but stopping it anyway\n", + q_id, vsi->vsi_num); + + ring = vsi->tx_rings[q_id]; + if (!ring) + return -EINVAL; + + ice_fill_txq_meta(vsi, ring, &txq_meta); + + err = ice_vsi_stop_tx_ring(vsi, ICE_NO_RESET, vf->vf_id, ring, &txq_meta); + if (err) { + dev_err(ice_pf_to_dev(vsi->back), "Failed to stop Tx ring %d on VSI %d\n", + q_id, vsi->vsi_num); + return err; + } + + /* Clear enabled queues flag */ + clear_bit(q_id, vf->txq_ena); + + return 0; +} + +/** * ice_vc_dis_qs_msg * @vf: pointer to the VF info * @msg: pointer to the msg buffer * - * called from the VF to disable all or specific - * queue(s) + * called from the VF to disable all or specific queue(s) */ static int ice_vc_dis_qs_msg(struct ice_vf *vf, u8 *msg) { @@ -1350,30 +1389,15 @@ static int ice_vc_dis_qs_msg(struct ice_vf *vf, u8 *msg) q_map = vqs->tx_queues; for_each_set_bit(vf_q_id, &q_map, ICE_MAX_RSS_QS_PER_VF) { - struct ice_tx_ring *ring = vsi->tx_rings[vf_q_id]; - struct ice_txq_meta txq_meta = { 0 }; - if (!ice_vc_isvalid_q_id(vf, vqs->vsi_id, vf_q_id)) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; } - /* Skip queue if not enabled */ - if (!test_bit(vf_q_id, vf->txq_ena)) - continue; - - ice_fill_txq_meta(vsi, ring, &txq_meta); - - if (ice_vsi_stop_tx_ring(vsi, ICE_NO_RESET, vf->vf_id, - ring, &txq_meta)) { - dev_err(ice_pf_to_dev(vsi->back), "Failed to stop Tx ring %d on VSI %d\n", - vf_q_id, vsi->vsi_num); + if (ice_vf_vsi_dis_single_txq(vf, vsi, vf_q_id)) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; } - - /* Clear enabled queues flag */ - clear_bit(vf_q_id, vf->txq_ena); } } @@ -1622,6 +1646,14 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg) if (qpi->txq.ring_len > 0) { vsi->tx_rings[i]->dma = qpi->txq.dma_ring_addr; vsi->tx_rings[i]->count = qpi->txq.ring_len; + + /* Disable any existing queue first */ + if (ice_vf_vsi_dis_single_txq(vf, vsi, q_idx)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + /* Configure a queue with the requested settings */ if (ice_vsi_cfg_single_txq(vsi, vsi->tx_rings, q_idx)) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; @@ -3625,6 +3657,8 @@ void ice_vc_process_vf_msg(struct ice_pf *pf, struct ice_rq_event_info *event) return; } + mutex_lock(&vf->cfg_lock); + /* Check if VF is disabled. */ if (test_bit(ICE_VF_STATE_DIS, vf->vf_states)) { err = -EPERM; @@ -3642,32 +3676,20 @@ void ice_vc_process_vf_msg(struct ice_pf *pf, struct ice_rq_event_info *event) err = -EINVAL; } - if (!ice_vc_is_opcode_allowed(vf, v_opcode)) { - ice_vc_send_msg_to_vf(vf, v_opcode, - VIRTCHNL_STATUS_ERR_NOT_SUPPORTED, NULL, - 0); - ice_put_vf(vf); - return; - } - error_handler: if (err) { ice_vc_send_msg_to_vf(vf, v_opcode, VIRTCHNL_STATUS_ERR_PARAM, NULL, 0); dev_err(dev, "Invalid message from VF %d, opcode %d, len %d, error %d\n", vf_id, v_opcode, msglen, err); - ice_put_vf(vf); - return; + goto finish; } - /* VF is being configured in another context that triggers a VFR, so no - * need to process this message - */ - if (!mutex_trylock(&vf->cfg_lock)) { - dev_info(dev, "VF %u is being configured in another context that will trigger a VFR, so there is no need to handle this message\n", - vf->vf_id); - ice_put_vf(vf); - return; + if (!ice_vc_is_opcode_allowed(vf, v_opcode)) { + ice_vc_send_msg_to_vf(vf, v_opcode, + VIRTCHNL_STATUS_ERR_NOT_SUPPORTED, NULL, + 0); + goto finish; } switch (v_opcode) { @@ -3780,6 +3802,7 @@ error_handler: vf_id, v_opcode, err); } +finish: mutex_unlock(&vf->cfg_lock); ice_put_vf(vf); } diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index dfbcaf08520e..9dd38f667059 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -41,8 +41,10 @@ static void ice_qp_reset_stats(struct ice_vsi *vsi, u16 q_idx) static void ice_qp_clean_rings(struct ice_vsi *vsi, u16 q_idx) { ice_clean_tx_ring(vsi->tx_rings[q_idx]); - if (ice_is_xdp_ena_vsi(vsi)) + if (ice_is_xdp_ena_vsi(vsi)) { + synchronize_rcu(); ice_clean_tx_ring(vsi->xdp_rings[q_idx]); + } ice_clean_rx_ring(vsi->rx_rings[q_idx]); } @@ -413,8 +415,8 @@ static u16 ice_fill_rx_descs(struct xsk_buff_pool *pool, struct xdp_buff **xdp, */ static bool __ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count) { + u32 nb_buffs_extra = 0, nb_buffs = 0; union ice_32b_rx_flex_desc *rx_desc; - u32 nb_buffs_extra = 0, nb_buffs; u16 ntu = rx_ring->next_to_use; u16 total_count = count; struct xdp_buff **xdp; @@ -426,6 +428,10 @@ static bool __ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count) nb_buffs_extra = ice_fill_rx_descs(rx_ring->xsk_pool, xdp, rx_desc, rx_ring->count - ntu); + if (nb_buffs_extra != rx_ring->count - ntu) { + ntu += nb_buffs_extra; + goto exit; + } rx_desc = ICE_RX_DESC(rx_ring, 0); xdp = ice_xdp_buf(rx_ring, 0); ntu = 0; @@ -439,6 +445,7 @@ static bool __ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count) if (ntu == rx_ring->count) ntu = 0; +exit: if (rx_ring->next_to_use != ntu) ice_release_rx_desc(rx_ring, ntu); @@ -918,7 +925,7 @@ ice_xsk_wakeup(struct net_device *netdev, u32 queue_id, struct ice_vsi *vsi = np->vsi; struct ice_tx_ring *ring; - if (test_bit(ICE_DOWN, vsi->state)) + if (test_bit(ICE_VSI_DOWN, vsi->state)) return -ENETDOWN; if (!ice_is_xdp_ena_vsi(vsi)) diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 34b33b21e0dc..68be2976f539 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -5505,7 +5505,8 @@ static void igb_watchdog_task(struct work_struct *work) break; } - if (adapter->link_speed != SPEED_1000) + if (adapter->link_speed != SPEED_1000 || + !hw->phy.ops.read_reg) goto no_wait; /* wait for Remote receiver status OK */ diff --git a/drivers/net/ethernet/intel/igc/igc_i225.c b/drivers/net/ethernet/intel/igc/igc_i225.c index 66ea566488d1..59d5c467ea6e 100644 --- a/drivers/net/ethernet/intel/igc/igc_i225.c +++ b/drivers/net/ethernet/intel/igc/igc_i225.c @@ -156,8 +156,15 @@ void igc_release_swfw_sync_i225(struct igc_hw *hw, u16 mask) { u32 swfw_sync; - while (igc_get_hw_semaphore_i225(hw)) - ; /* Empty */ + /* Releasing the resource requires first getting the HW semaphore. + * If we fail to get the semaphore, there is nothing we can do, + * except log an error and quit. We are not allowed to hang here + * indefinitely, as it may cause denial of service or system crash. + */ + if (igc_get_hw_semaphore_i225(hw)) { + hw_dbg("Failed to release SW_FW_SYNC.\n"); + return; + } swfw_sync = rd32(IGC_SW_FW_SYNC); swfw_sync &= ~mask; diff --git a/drivers/net/ethernet/intel/igc/igc_phy.c b/drivers/net/ethernet/intel/igc/igc_phy.c index 40dbf4b43234..6961f65d36b9 100644 --- a/drivers/net/ethernet/intel/igc/igc_phy.c +++ b/drivers/net/ethernet/intel/igc/igc_phy.c @@ -581,7 +581,7 @@ static s32 igc_read_phy_reg_mdic(struct igc_hw *hw, u32 offset, u16 *data) * the lower time out */ for (i = 0; i < IGC_GEN_POLL_TIMEOUT; i++) { - usleep_range(500, 1000); + udelay(50); mdic = rd32(IGC_MDIC); if (mdic & IGC_MDIC_READY) break; @@ -638,7 +638,7 @@ static s32 igc_write_phy_reg_mdic(struct igc_hw *hw, u32 offset, u16 data) * the lower time out */ for (i = 0; i < IGC_GEN_POLL_TIMEOUT; i++) { - usleep_range(500, 1000); + udelay(50); mdic = rd32(IGC_MDIC); if (mdic & IGC_MDIC_READY) break; diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c index 0d6e3215e98f..653e9f1e35b5 100644 --- a/drivers/net/ethernet/intel/igc/igc_ptp.c +++ b/drivers/net/ethernet/intel/igc/igc_ptp.c @@ -992,6 +992,17 @@ static void igc_ptp_time_restore(struct igc_adapter *adapter) igc_ptp_write_i225(adapter, &ts); } +static void igc_ptm_stop(struct igc_adapter *adapter) +{ + struct igc_hw *hw = &adapter->hw; + u32 ctrl; + + ctrl = rd32(IGC_PTM_CTRL); + ctrl &= ~IGC_PTM_CTRL_EN; + + wr32(IGC_PTM_CTRL, ctrl); +} + /** * igc_ptp_suspend - Disable PTP work items and prepare for suspend * @adapter: Board private structure @@ -1009,8 +1020,10 @@ void igc_ptp_suspend(struct igc_adapter *adapter) adapter->ptp_tx_skb = NULL; clear_bit_unlock(__IGC_PTP_TX_IN_PROGRESS, &adapter->state); - if (pci_device_is_present(adapter->pdev)) + if (pci_device_is_present(adapter->pdev)) { igc_ptp_time_save(adapter); + igc_ptm_stop(adapter); + } } /** diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c index e596e1a9fc75..69d11ff7677d 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c @@ -903,7 +903,8 @@ int ixgbe_ipsec_vf_add_sa(struct ixgbe_adapter *adapter, u32 *msgbuf, u32 vf) /* Tx IPsec offload doesn't seem to work on this * device, so block these requests for now. */ - if (!(sam->flags & XFRM_OFFLOAD_INBOUND)) { + sam->flags = sam->flags & ~XFRM_OFFLOAD_IPV6; + if (sam->flags != XFRM_OFFLOAD_INBOUND) { err = -EOPNOTSUPP; goto err_out; } diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c index 5f9ab1842d49..c18801490649 100644 --- a/drivers/net/ethernet/marvell/mv643xx_eth.c +++ b/drivers/net/ethernet/marvell/mv643xx_eth.c @@ -2751,7 +2751,7 @@ static int mv643xx_eth_shared_of_add_port(struct platform_device *pdev, } ret = of_get_mac_address(pnp, ppd.mac_addr); - if (ret) + if (ret == -EPROBE_DEFER) return ret; mv643xx_eth_property(pnp, "tx-queue-size", ppd.tx_queue_size); diff --git a/drivers/net/ethernet/mediatek/mtk_ppe.c b/drivers/net/ethernet/mediatek/mtk_ppe.c index 3ad10c793308..66298e2235c9 100644 --- a/drivers/net/ethernet/mediatek/mtk_ppe.c +++ b/drivers/net/ethernet/mediatek/mtk_ppe.c @@ -395,7 +395,7 @@ static void mtk_ppe_init_foe_table(struct mtk_ppe *ppe) static const u8 skip[] = { 12, 25, 38, 51, 76, 89, 102 }; int i, k; - memset(ppe->foe_table, 0, MTK_PPE_ENTRIES * sizeof(ppe->foe_table)); + memset(ppe->foe_table, 0, MTK_PPE_ENTRIES * sizeof(*ppe->foe_table)); if (!IS_ENABLED(CONFIG_SOC_MT7621)) return; diff --git a/drivers/net/ethernet/mediatek/mtk_sgmii.c b/drivers/net/ethernet/mediatek/mtk_sgmii.c index 32d83421226a..5897940a418b 100644 --- a/drivers/net/ethernet/mediatek/mtk_sgmii.c +++ b/drivers/net/ethernet/mediatek/mtk_sgmii.c @@ -26,6 +26,7 @@ int mtk_sgmii_init(struct mtk_sgmii *ss, struct device_node *r, u32 ana_rgc3) break; ss->regmap[i] = syscon_node_to_regmap(np); + of_node_put(np); if (IS_ERR(ss->regmap[i])) return PTR_ERR(ss->regmap[i]); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/rsc_dump.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/rsc_dump.c index 538adab6878b..c5b560a8b026 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/rsc_dump.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/rsc_dump.c @@ -31,6 +31,7 @@ static const char *const mlx5_rsc_sgmt_name[] = { struct mlx5_rsc_dump { u32 pdn; u32 mkey; + u32 number_of_menu_items; u16 fw_segment_type[MLX5_SGMT_TYPE_NUM]; }; @@ -50,21 +51,37 @@ static int mlx5_rsc_dump_sgmt_get_by_name(char *name) return -EINVAL; } -static void mlx5_rsc_dump_read_menu_sgmt(struct mlx5_rsc_dump *rsc_dump, struct page *page) +#define MLX5_RSC_DUMP_MENU_HEADER_SIZE (MLX5_ST_SZ_BYTES(resource_dump_info_segment) + \ + MLX5_ST_SZ_BYTES(resource_dump_command_segment) + \ + MLX5_ST_SZ_BYTES(resource_dump_menu_segment)) + +static int mlx5_rsc_dump_read_menu_sgmt(struct mlx5_rsc_dump *rsc_dump, struct page *page, + int read_size, int start_idx) { void *data = page_address(page); enum mlx5_sgmt_type sgmt_idx; int num_of_items; char *sgmt_name; void *member; + int size = 0; void *menu; int i; - menu = MLX5_ADDR_OF(menu_resource_dump_response, data, menu); - num_of_items = MLX5_GET(resource_dump_menu_segment, menu, num_of_records); + if (!start_idx) { + menu = MLX5_ADDR_OF(menu_resource_dump_response, data, menu); + rsc_dump->number_of_menu_items = MLX5_GET(resource_dump_menu_segment, menu, + num_of_records); + size = MLX5_RSC_DUMP_MENU_HEADER_SIZE; + data += size; + } + num_of_items = rsc_dump->number_of_menu_items; + + for (i = 0; start_idx + i < num_of_items; i++) { + size += MLX5_ST_SZ_BYTES(resource_dump_menu_record); + if (size >= read_size) + return start_idx + i; - for (i = 0; i < num_of_items; i++) { - member = MLX5_ADDR_OF(resource_dump_menu_segment, menu, record[i]); + member = data + MLX5_ST_SZ_BYTES(resource_dump_menu_record) * i; sgmt_name = MLX5_ADDR_OF(resource_dump_menu_record, member, segment_name); sgmt_idx = mlx5_rsc_dump_sgmt_get_by_name(sgmt_name); if (sgmt_idx == -EINVAL) @@ -72,6 +89,7 @@ static void mlx5_rsc_dump_read_menu_sgmt(struct mlx5_rsc_dump *rsc_dump, struct rsc_dump->fw_segment_type[sgmt_idx] = MLX5_GET(resource_dump_menu_record, member, segment_type); } + return 0; } static int mlx5_rsc_dump_trigger(struct mlx5_core_dev *dev, struct mlx5_rsc_dump_cmd *cmd, @@ -168,6 +186,7 @@ static int mlx5_rsc_dump_menu(struct mlx5_core_dev *dev) struct mlx5_rsc_dump_cmd *cmd = NULL; struct mlx5_rsc_key key = {}; struct page *page; + int start_idx = 0; int size; int err; @@ -189,7 +208,7 @@ static int mlx5_rsc_dump_menu(struct mlx5_core_dev *dev) if (err < 0) goto destroy_cmd; - mlx5_rsc_dump_read_menu_sgmt(dev->rsc_dump, page); + start_idx = mlx5_rsc_dump_read_menu_sgmt(dev->rsc_dump, page, size, start_idx); } while (err > 0); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c index 673f1c82d381..c9d5d8d93994 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c @@ -309,8 +309,8 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv, if (err) return err; - err = update_buffer_lossy(max_mtu, curr_pfc_en, prio2buffer, port_buff_cell_sz, - xoff, &port_buffer, &update_buffer); + err = update_buffer_lossy(max_mtu, curr_pfc_en, prio2buffer, xoff, + port_buff_cell_sz, &port_buffer, &update_buffer); if (err) return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.c index af37a8d247a1..2755c25ba324 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.c @@ -145,8 +145,7 @@ mlx5e_tc_act_post_parse(struct mlx5e_tc_act_parse_state *parse_state, flow_action_for_each(i, act, flow_action) { tc_act = mlx5e_tc_act_get(act->id, ns_type); - if (!tc_act || !tc_act->post_parse || - !tc_act->can_offload(parse_state, act, i, attr)) + if (!tc_act || !tc_act->post_parse) continue; err = tc_act->post_parse(parse_state, priv, attr); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/ct.c index b9d38fe807df..a829c94289c1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/ct.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/ct.c @@ -45,12 +45,41 @@ tc_act_parse_ct(struct mlx5e_tc_act_parse_state *parse_state, if (mlx5e_is_eswitch_flow(parse_state->flow)) attr->esw_attr->split_count = attr->esw_attr->out_count; - if (!clear_action) { + if (clear_action) { + parse_state->ct_clear = true; + } else { attr->flags |= MLX5_ATTR_FLAG_CT; flow_flag_set(parse_state->flow, CT); parse_state->ct = true; } - parse_state->ct_clear = clear_action; + + return 0; +} + +static int +tc_act_post_parse_ct(struct mlx5e_tc_act_parse_state *parse_state, + struct mlx5e_priv *priv, + struct mlx5_flow_attr *attr) +{ + struct mlx5e_tc_mod_hdr_acts *mod_acts = &attr->parse_attr->mod_hdr_acts; + int err; + + /* If ct action exist, we can ignore previous ct_clear actions */ + if (parse_state->ct) + return 0; + + if (parse_state->ct_clear) { + err = mlx5_tc_ct_set_ct_clear_regs(parse_state->ct_priv, mod_acts); + if (err) { + NL_SET_ERR_MSG_MOD(parse_state->extack, + "Failed to set registers for ct clear"); + return err; + } + attr->action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR; + + /* Prevent handling of additional, redundant clear actions */ + parse_state->ct_clear = false; + } return 0; } @@ -70,5 +99,6 @@ struct mlx5e_tc_act mlx5e_tc_act_ct = { .can_offload = tc_act_can_offload_ct, .parse_action = tc_act_parse_ct, .is_multi_table_act = tc_act_is_multi_table_act_ct, + .post_parse = tc_act_post_parse_ct, }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_smfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_smfs.c index 59988e24b704..bec9ed0103a9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_smfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_smfs.c @@ -23,7 +23,7 @@ struct mlx5_ct_fs_smfs_matcher { }; struct mlx5_ct_fs_smfs_matchers { - struct mlx5_ct_fs_smfs_matcher smfs_matchers[4]; + struct mlx5_ct_fs_smfs_matcher smfs_matchers[6]; struct list_head used; }; @@ -44,7 +44,8 @@ struct mlx5_ct_fs_smfs_rule { }; static inline void -mlx5_ct_fs_smfs_fill_mask(struct mlx5_ct_fs *fs, struct mlx5_flow_spec *spec, bool ipv4, bool tcp) +mlx5_ct_fs_smfs_fill_mask(struct mlx5_ct_fs *fs, struct mlx5_flow_spec *spec, bool ipv4, bool tcp, + bool gre) { void *headers_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, outer_headers); @@ -77,7 +78,7 @@ mlx5_ct_fs_smfs_fill_mask(struct mlx5_ct_fs *fs, struct mlx5_flow_spec *spec, bo MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, tcp_dport); MLX5_SET(fte_match_set_lyr_2_4, headers_c, tcp_flags, ntohs(MLX5_CT_TCP_FLAGS_MASK)); - } else { + } else if (!gre) { MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, udp_sport); MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, udp_dport); } @@ -87,7 +88,7 @@ mlx5_ct_fs_smfs_fill_mask(struct mlx5_ct_fs *fs, struct mlx5_flow_spec *spec, bo static struct mlx5dr_matcher * mlx5_ct_fs_smfs_matcher_create(struct mlx5_ct_fs *fs, struct mlx5dr_table *tbl, bool ipv4, - bool tcp, u32 priority) + bool tcp, bool gre, u32 priority) { struct mlx5dr_matcher *dr_matcher; struct mlx5_flow_spec *spec; @@ -96,7 +97,7 @@ mlx5_ct_fs_smfs_matcher_create(struct mlx5_ct_fs *fs, struct mlx5dr_table *tbl, if (!spec) return ERR_PTR(-ENOMEM); - mlx5_ct_fs_smfs_fill_mask(fs, spec, ipv4, tcp); + mlx5_ct_fs_smfs_fill_mask(fs, spec, ipv4, tcp, gre); spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2 | MLX5_MATCH_OUTER_HEADERS; dr_matcher = mlx5_smfs_matcher_create(tbl, priority, spec); @@ -108,7 +109,7 @@ mlx5_ct_fs_smfs_matcher_create(struct mlx5_ct_fs *fs, struct mlx5dr_table *tbl, } static struct mlx5_ct_fs_smfs_matcher * -mlx5_ct_fs_smfs_matcher_get(struct mlx5_ct_fs *fs, bool nat, bool ipv4, bool tcp) +mlx5_ct_fs_smfs_matcher_get(struct mlx5_ct_fs *fs, bool nat, bool ipv4, bool tcp, bool gre) { struct mlx5_ct_fs_smfs *fs_smfs = mlx5_ct_fs_priv(fs); struct mlx5_ct_fs_smfs_matcher *m, *smfs_matcher; @@ -119,7 +120,7 @@ mlx5_ct_fs_smfs_matcher_get(struct mlx5_ct_fs *fs, bool nat, bool ipv4, bool tcp int prio; matchers = nat ? &fs_smfs->matchers_nat : &fs_smfs->matchers; - smfs_matcher = &matchers->smfs_matchers[ipv4 * 2 + tcp]; + smfs_matcher = &matchers->smfs_matchers[ipv4 * 3 + tcp * 2 + gre]; if (refcount_inc_not_zero(&smfs_matcher->ref)) return smfs_matcher; @@ -145,11 +146,11 @@ mlx5_ct_fs_smfs_matcher_get(struct mlx5_ct_fs *fs, bool nat, bool ipv4, bool tcp } tbl = nat ? fs_smfs->ct_nat_tbl : fs_smfs->ct_tbl; - dr_matcher = mlx5_ct_fs_smfs_matcher_create(fs, tbl, ipv4, tcp, prio); + dr_matcher = mlx5_ct_fs_smfs_matcher_create(fs, tbl, ipv4, tcp, gre, prio); if (IS_ERR(dr_matcher)) { netdev_warn(fs->netdev, - "ct_fs_smfs: failed to create matcher (nat %d, ipv4 %d, tcp %d), err: %ld\n", - nat, ipv4, tcp, PTR_ERR(dr_matcher)); + "ct_fs_smfs: failed to create matcher (nat %d, ipv4 %d, tcp %d, gre %d), err: %ld\n", + nat, ipv4, tcp, gre, PTR_ERR(dr_matcher)); smfs_matcher = ERR_CAST(dr_matcher); goto out_unlock; @@ -222,16 +223,17 @@ mlx5_ct_fs_smfs_destroy(struct mlx5_ct_fs *fs) static inline bool mlx5_tc_ct_valid_used_dissector_keys(const u32 used_keys) { -#define DISSECTOR_BIT(name) BIT(FLOW_DISSECTOR_KEY_ ## name) - const u32 basic_keys = DISSECTOR_BIT(BASIC) | DISSECTOR_BIT(CONTROL) | - DISSECTOR_BIT(PORTS) | DISSECTOR_BIT(META); - const u32 ipv4_tcp = basic_keys | DISSECTOR_BIT(IPV4_ADDRS) | DISSECTOR_BIT(TCP); - const u32 ipv4_udp = basic_keys | DISSECTOR_BIT(IPV4_ADDRS); - const u32 ipv6_tcp = basic_keys | DISSECTOR_BIT(IPV6_ADDRS) | DISSECTOR_BIT(TCP); - const u32 ipv6_udp = basic_keys | DISSECTOR_BIT(IPV6_ADDRS); +#define DISS_BIT(name) BIT(FLOW_DISSECTOR_KEY_ ## name) + const u32 basic_keys = DISS_BIT(BASIC) | DISS_BIT(CONTROL) | DISS_BIT(META); + const u32 ipv4_tcp = basic_keys | DISS_BIT(IPV4_ADDRS) | DISS_BIT(PORTS) | DISS_BIT(TCP); + const u32 ipv6_tcp = basic_keys | DISS_BIT(IPV6_ADDRS) | DISS_BIT(PORTS) | DISS_BIT(TCP); + const u32 ipv4_udp = basic_keys | DISS_BIT(IPV4_ADDRS) | DISS_BIT(PORTS); + const u32 ipv6_udp = basic_keys | DISS_BIT(IPV6_ADDRS) | DISS_BIT(PORTS); + const u32 ipv4_gre = basic_keys | DISS_BIT(IPV4_ADDRS); + const u32 ipv6_gre = basic_keys | DISS_BIT(IPV6_ADDRS); return (used_keys == ipv4_tcp || used_keys == ipv4_udp || used_keys == ipv6_tcp || - used_keys == ipv6_udp); + used_keys == ipv6_udp || used_keys == ipv4_gre || used_keys == ipv6_gre); } static bool @@ -254,20 +256,24 @@ mlx5_ct_fs_smfs_ct_validate_flow_rule(struct mlx5_ct_fs *fs, struct flow_rule *f flow_rule_match_control(flow_rule, &control); flow_rule_match_ipv4_addrs(flow_rule, &ipv4_addrs); flow_rule_match_ipv6_addrs(flow_rule, &ipv6_addrs); - flow_rule_match_ports(flow_rule, &ports); - flow_rule_match_tcp(flow_rule, &tcp); + if (basic.key->ip_proto != IPPROTO_GRE) + flow_rule_match_ports(flow_rule, &ports); + if (basic.key->ip_proto == IPPROTO_TCP) + flow_rule_match_tcp(flow_rule, &tcp); if (basic.mask->n_proto != htons(0xFFFF) || (basic.key->n_proto != htons(ETH_P_IP) && basic.key->n_proto != htons(ETH_P_IPV6)) || basic.mask->ip_proto != 0xFF || - (basic.key->ip_proto != IPPROTO_UDP && basic.key->ip_proto != IPPROTO_TCP)) { + (basic.key->ip_proto != IPPROTO_UDP && basic.key->ip_proto != IPPROTO_TCP && + basic.key->ip_proto != IPPROTO_GRE)) { ct_dbg("rule uses unexpected basic match (n_proto 0x%04x/0x%04x, ip_proto 0x%02x/0x%02x)", ntohs(basic.key->n_proto), ntohs(basic.mask->n_proto), basic.key->ip_proto, basic.mask->ip_proto); return false; } - if (ports.mask->src != htons(0xFFFF) || ports.mask->dst != htons(0xFFFF)) { + if (basic.key->ip_proto != IPPROTO_GRE && + (ports.mask->src != htons(0xFFFF) || ports.mask->dst != htons(0xFFFF))) { ct_dbg("rule uses ports match (src 0x%04x, dst 0x%04x)", ports.mask->src, ports.mask->dst); return false; @@ -291,7 +297,7 @@ mlx5_ct_fs_smfs_ct_rule_add(struct mlx5_ct_fs *fs, struct mlx5_flow_spec *spec, struct mlx5dr_action *actions[5]; struct mlx5dr_rule *rule; int num_actions = 0, err; - bool nat, tcp, ipv4; + bool nat, tcp, ipv4, gre; if (!mlx5_ct_fs_smfs_ct_validate_flow_rule(fs, flow_rule)) return ERR_PTR(-EOPNOTSUPP); @@ -314,15 +320,17 @@ mlx5_ct_fs_smfs_ct_rule_add(struct mlx5_ct_fs *fs, struct mlx5_flow_spec *spec, ipv4 = mlx5e_tc_get_ip_version(spec, true) == 4; tcp = MLX5_GET(fte_match_param, spec->match_value, outer_headers.ip_protocol) == IPPROTO_TCP; + gre = MLX5_GET(fte_match_param, spec->match_value, + outer_headers.ip_protocol) == IPPROTO_GRE; - smfs_matcher = mlx5_ct_fs_smfs_matcher_get(fs, nat, ipv4, tcp); + smfs_matcher = mlx5_ct_fs_smfs_matcher_get(fs, nat, ipv4, tcp, gre); if (IS_ERR(smfs_matcher)) { err = PTR_ERR(smfs_matcher); goto err_matcher; } rule = mlx5_smfs_rule_create(smfs_matcher->dr_matcher, spec, num_actions, actions, - MLX5_FLOW_CONTEXT_FLOW_SOURCE_ANY_VPORT); + spec->flow_context.flow_source); if (!rule) { err = -EINVAL; goto err_create; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c index e49f51124c74..ab4b0f3ee2a0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c @@ -582,6 +582,12 @@ mlx5_tc_ct_entry_set_registers(struct mlx5_tc_ct_priv *ct_priv, return 0; } +int mlx5_tc_ct_set_ct_clear_regs(struct mlx5_tc_ct_priv *priv, + struct mlx5e_tc_mod_hdr_acts *mod_acts) +{ + return mlx5_tc_ct_entry_set_registers(priv, mod_acts, 0, 0, 0, 0); +} + static int mlx5_tc_ct_parse_mangle_to_mod_act(struct flow_action_entry *act, char *modact) @@ -1410,9 +1416,6 @@ mlx5_tc_ct_parse_action(struct mlx5_tc_ct_priv *priv, const struct flow_action_entry *act, struct netlink_ext_ack *extack) { - bool clear_action = act->ct.action & TCA_CT_ACT_CLEAR; - int err; - if (!priv) { NL_SET_ERR_MSG_MOD(extack, "offload of ct action isn't available"); @@ -1423,17 +1426,6 @@ mlx5_tc_ct_parse_action(struct mlx5_tc_ct_priv *priv, attr->ct_attr.ct_action = act->ct.action; attr->ct_attr.nf_ft = act->ct.flow_table; - if (!clear_action) - goto out; - - err = mlx5_tc_ct_entry_set_registers(priv, mod_acts, 0, 0, 0, 0); - if (err) { - NL_SET_ERR_MSG_MOD(extack, "Failed to set registers for ct clear"); - return err; - } - attr->action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR; - -out: return 0; } @@ -1749,6 +1741,8 @@ mlx5_tc_ct_flush_ft_entry(void *ptr, void *arg) static void mlx5_tc_ct_del_ft_cb(struct mlx5_tc_ct_priv *ct_priv, struct mlx5_ct_ft *ft) { + struct mlx5e_priv *priv; + if (!refcount_dec_and_test(&ft->refcount)) return; @@ -1758,6 +1752,8 @@ mlx5_tc_ct_del_ft_cb(struct mlx5_tc_ct_priv *ct_priv, struct mlx5_ct_ft *ft) rhashtable_free_and_destroy(&ft->ct_entries_ht, mlx5_tc_ct_flush_ft_entry, ct_priv); + priv = netdev_priv(ct_priv->netdev); + flush_workqueue(priv->wq); mlx5_tc_ct_free_pre_ct_tables(ft); mapping_remove(ct_priv->zone_mapping, ft->zone_restore_id); kfree(ft); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h index 36d3652bf829..00a3ba862afb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h @@ -129,6 +129,10 @@ bool mlx5e_tc_ct_restore_flow(struct mlx5_tc_ct_priv *ct_priv, struct sk_buff *skb, u8 zone_restore_id); +int +mlx5_tc_ct_set_ct_clear_regs(struct mlx5_tc_ct_priv *priv, + struct mlx5e_tc_mod_hdr_acts *mod_acts); + #else /* CONFIG_MLX5_TC_CT */ static inline struct mlx5_tc_ct_priv * @@ -171,6 +175,13 @@ mlx5_tc_ct_add_no_trk_match(struct mlx5_flow_spec *spec) } static inline int +mlx5_tc_ct_set_ct_clear_regs(struct mlx5_tc_ct_priv *priv, + struct mlx5e_tc_mod_hdr_acts *mod_acts) +{ + return -EOPNOTSUPP; +} + +static inline int mlx5_tc_ct_parse_action(struct mlx5_tc_ct_priv *priv, struct mlx5_flow_attr *attr, struct mlx5e_tc_mod_hdr_acts *mod_acts, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c index 378fc8e3bd97..d87bbb0be7c8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c @@ -713,6 +713,7 @@ int mlx5e_tc_tun_route_lookup(struct mlx5e_priv *priv, struct net_device *filter_dev) { struct mlx5_esw_flow_attr *esw_attr = flow_attr->esw_attr; + struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct mlx5e_tc_int_port *int_port; TC_TUN_ROUTE_ATTR_INIT(attr); u16 vport_num; @@ -747,7 +748,7 @@ int mlx5e_tc_tun_route_lookup(struct mlx5e_priv *priv, esw_attr->rx_tun_attr->vni = MLX5_GET(fte_match_param, spec->match_value, misc_parameters.vxlan_vni); esw_attr->rx_tun_attr->decap_vport = vport_num; - } else if (netif_is_ovs_master(attr.route_dev)) { + } else if (netif_is_ovs_master(attr.route_dev) && mlx5e_tc_int_port_supported(esw)) { int_port = mlx5e_tc_int_port_get(mlx5e_get_int_port_priv(priv), attr.route_dev->ifindex, MLX5E_TC_INT_PORT_INGRESS); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c index a55b066746cb..857840ab1e91 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c @@ -14,19 +14,26 @@ static int mlx5e_trap_napi_poll(struct napi_struct *napi, int budget) bool busy = false; int work_done = 0; + rcu_read_lock(); + ch_stats->poll++; work_done = mlx5e_poll_rx_cq(&rq->cq, budget); busy |= work_done == budget; busy |= rq->post_wqes(rq); - if (busy) - return budget; + if (busy) { + work_done = budget; + goto out; + } if (unlikely(!napi_complete_done(napi, work_done))) - return work_done; + goto out; mlx5e_cq_arm(&rq->cq); + +out: + rcu_read_unlock(); return work_done; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c index d659fe07d464..8ead2c82a52a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c @@ -1200,6 +1200,16 @@ static int mlx5e_trust_initialize(struct mlx5e_priv *priv) return err; WRITE_ONCE(priv->dcbx_dp.trust_state, trust_state); + if (priv->dcbx_dp.trust_state == MLX5_QPTS_TRUST_PCP && priv->dcbx.dscp_app_cnt) { + /* + * Align the driver state with the register state. + * Temporary state change is required to enable the app list reset. + */ + priv->dcbx_dp.trust_state = MLX5_QPTS_TRUST_DSCP; + mlx5e_dcbnl_delete_app(priv); + priv->dcbx_dp.trust_state = MLX5_QPTS_TRUST_PCP; + } + mlx5e_params_calc_trust_tx_min_inline_mode(priv->mdev, &priv->channels.params, priv->dcbx_dp.trust_state); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 2f1dedc721d1..fa229998606c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -3864,6 +3864,10 @@ static netdev_features_t mlx5e_fix_uplink_rep_features(struct net_device *netdev if (netdev->features & NETIF_F_NTUPLE) netdev_warn(netdev, "Disabling ntuple, not supported in switchdev mode\n"); + features &= ~NETIF_F_GRO_HW; + if (netdev->features & NETIF_F_GRO_HW) + netdev_warn(netdev, "Disabling HW_GRO, not supported in switchdev mode\n"); + return features; } @@ -3896,6 +3900,25 @@ static netdev_features_t mlx5e_fix_features(struct net_device *netdev, } } + if (params->xdp_prog) { + if (features & NETIF_F_LRO) { + netdev_warn(netdev, "LRO is incompatible with XDP\n"); + features &= ~NETIF_F_LRO; + } + if (features & NETIF_F_GRO_HW) { + netdev_warn(netdev, "HW GRO is incompatible with XDP\n"); + features &= ~NETIF_F_GRO_HW; + } + } + + if (priv->xsk.refcnt) { + if (features & NETIF_F_GRO_HW) { + netdev_warn(netdev, "HW GRO is incompatible with AF_XDP (%u XSKs are active)\n", + priv->xsk.refcnt); + features &= ~NETIF_F_GRO_HW; + } + } + if (MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS)) { features &= ~NETIF_F_RXHASH; if (netdev->features & NETIF_F_RXHASH) @@ -4850,10 +4873,6 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev) netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_FILTER; netdev->hw_features |= NETIF_F_HW_VLAN_STAG_TX; - if (!!MLX5_CAP_GEN(mdev, shampo) && - mlx5e_check_fragmented_striding_rq_cap(mdev)) - netdev->hw_features |= NETIF_F_GRO_HW; - if (mlx5e_tunnel_any_tx_proto_supported(mdev)) { netdev->hw_enc_features |= NETIF_F_HW_CSUM; netdev->hw_enc_features |= NETIF_F_TSO; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index e3fc15ae7bb1..ac0f73074f7a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -2459,6 +2459,17 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, match.key->vlan_priority); *match_level = MLX5_MATCH_L2; + + if (!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CVLAN) && + match.mask->vlan_eth_type && + MLX5_CAP_FLOWTABLE_TYPE(priv->mdev, + ft_field_support.outer_second_vid, + fs_type)) { + MLX5_SET(fte_match_set_misc, misc_c, + outer_second_cvlan_tag, 1); + spec->match_criteria_enable |= + MLX5_MATCH_MISC_PARAMETERS; + } } } else if (*match_level != MLX5_MATCH_NONE) { /* cvlan_tag enabled in match criteria and diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 3f63df127091..3b151332e2f8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -139,7 +139,7 @@ mlx5_eswitch_set_rule_source_port(struct mlx5_eswitch *esw, if (mlx5_esw_indir_table_decap_vport(attr)) vport = mlx5_esw_indir_table_decap_vport(attr); - if (esw_attr->int_port) + if (attr && !attr->chain && esw_attr->int_port) metadata = mlx5e_tc_int_port_get_metadata_for_match(esw_attr->int_port); else diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 816d991f7621..3ad67e6b5586 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -2663,28 +2663,6 @@ static void cleanup_root_ns(struct mlx5_flow_root_namespace *root_ns) clean_tree(&root_ns->ns.node); } -void mlx5_cleanup_fs(struct mlx5_core_dev *dev) -{ - struct mlx5_flow_steering *steering = dev->priv.steering; - - cleanup_root_ns(steering->root_ns); - cleanup_root_ns(steering->fdb_root_ns); - steering->fdb_root_ns = NULL; - kfree(steering->fdb_sub_ns); - steering->fdb_sub_ns = NULL; - cleanup_root_ns(steering->port_sel_root_ns); - cleanup_root_ns(steering->sniffer_rx_root_ns); - cleanup_root_ns(steering->sniffer_tx_root_ns); - cleanup_root_ns(steering->rdma_rx_root_ns); - cleanup_root_ns(steering->rdma_tx_root_ns); - cleanup_root_ns(steering->egress_root_ns); - mlx5_cleanup_fc_stats(dev); - kmem_cache_destroy(steering->ftes_cache); - kmem_cache_destroy(steering->fgs_cache); - mlx5_ft_pool_destroy(dev); - kfree(steering); -} - static int init_sniffer_tx_root_ns(struct mlx5_flow_steering *steering) { struct fs_prio *prio; @@ -3086,42 +3064,27 @@ cleanup: return err; } -int mlx5_init_fs(struct mlx5_core_dev *dev) +void mlx5_fs_core_cleanup(struct mlx5_core_dev *dev) { - struct mlx5_flow_steering *steering; - int err = 0; - - err = mlx5_init_fc_stats(dev); - if (err) - return err; - - err = mlx5_ft_pool_init(dev); - if (err) - return err; - - steering = kzalloc(sizeof(*steering), GFP_KERNEL); - if (!steering) { - err = -ENOMEM; - goto err; - } - - steering->dev = dev; - dev->priv.steering = steering; + struct mlx5_flow_steering *steering = dev->priv.steering; - if (mlx5_fs_dr_is_supported(dev)) - steering->mode = MLX5_FLOW_STEERING_MODE_SMFS; - else - steering->mode = MLX5_FLOW_STEERING_MODE_DMFS; + cleanup_root_ns(steering->root_ns); + cleanup_root_ns(steering->fdb_root_ns); + steering->fdb_root_ns = NULL; + kfree(steering->fdb_sub_ns); + steering->fdb_sub_ns = NULL; + cleanup_root_ns(steering->port_sel_root_ns); + cleanup_root_ns(steering->sniffer_rx_root_ns); + cleanup_root_ns(steering->sniffer_tx_root_ns); + cleanup_root_ns(steering->rdma_rx_root_ns); + cleanup_root_ns(steering->rdma_tx_root_ns); + cleanup_root_ns(steering->egress_root_ns); +} - steering->fgs_cache = kmem_cache_create("mlx5_fs_fgs", - sizeof(struct mlx5_flow_group), 0, - 0, NULL); - steering->ftes_cache = kmem_cache_create("mlx5_fs_ftes", sizeof(struct fs_fte), 0, - 0, NULL); - if (!steering->ftes_cache || !steering->fgs_cache) { - err = -ENOMEM; - goto err; - } +int mlx5_fs_core_init(struct mlx5_core_dev *dev) +{ + struct mlx5_flow_steering *steering = dev->priv.steering; + int err = 0; if ((((MLX5_CAP_GEN(dev, port_type) == MLX5_CAP_PORT_TYPE_ETH) && (MLX5_CAP_GEN(dev, nic_flow_table))) || @@ -3180,8 +3143,64 @@ int mlx5_init_fs(struct mlx5_core_dev *dev) } return 0; + +err: + mlx5_fs_core_cleanup(dev); + return err; +} + +void mlx5_fs_core_free(struct mlx5_core_dev *dev) +{ + struct mlx5_flow_steering *steering = dev->priv.steering; + + kmem_cache_destroy(steering->ftes_cache); + kmem_cache_destroy(steering->fgs_cache); + kfree(steering); + mlx5_ft_pool_destroy(dev); + mlx5_cleanup_fc_stats(dev); +} + +int mlx5_fs_core_alloc(struct mlx5_core_dev *dev) +{ + struct mlx5_flow_steering *steering; + int err = 0; + + err = mlx5_init_fc_stats(dev); + if (err) + return err; + + err = mlx5_ft_pool_init(dev); + if (err) + goto err; + + steering = kzalloc(sizeof(*steering), GFP_KERNEL); + if (!steering) { + err = -ENOMEM; + goto err; + } + + steering->dev = dev; + dev->priv.steering = steering; + + if (mlx5_fs_dr_is_supported(dev)) + steering->mode = MLX5_FLOW_STEERING_MODE_SMFS; + else + steering->mode = MLX5_FLOW_STEERING_MODE_DMFS; + + steering->fgs_cache = kmem_cache_create("mlx5_fs_fgs", + sizeof(struct mlx5_flow_group), 0, + 0, NULL); + steering->ftes_cache = kmem_cache_create("mlx5_fs_ftes", sizeof(struct fs_fte), 0, + 0, NULL); + if (!steering->ftes_cache || !steering->fgs_cache) { + err = -ENOMEM; + goto err; + } + + return 0; + err: - mlx5_cleanup_fs(dev); + mlx5_fs_core_free(dev); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index c488a7c5b07e..3f20523e514f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -298,8 +298,10 @@ int mlx5_flow_namespace_set_peer(struct mlx5_flow_root_namespace *ns, int mlx5_flow_namespace_set_mode(struct mlx5_flow_namespace *ns, enum mlx5_flow_steering_mode mode); -int mlx5_init_fs(struct mlx5_core_dev *dev); -void mlx5_cleanup_fs(struct mlx5_core_dev *dev); +int mlx5_fs_core_alloc(struct mlx5_core_dev *dev); +void mlx5_fs_core_free(struct mlx5_core_dev *dev); +int mlx5_fs_core_init(struct mlx5_core_dev *dev); +void mlx5_fs_core_cleanup(struct mlx5_core_dev *dev); int mlx5_fs_egress_acls_init(struct mlx5_core_dev *dev, int total_vports); void mlx5_fs_egress_acls_cleanup(struct mlx5_core_dev *dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c index 4aa22dce9b77..81eb67fb95b0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c @@ -8,7 +8,8 @@ enum { MLX5_FW_RESET_FLAGS_RESET_REQUESTED, MLX5_FW_RESET_FLAGS_NACK_RESET_REQUEST, - MLX5_FW_RESET_FLAGS_PENDING_COMP + MLX5_FW_RESET_FLAGS_PENDING_COMP, + MLX5_FW_RESET_FLAGS_DROP_NEW_REQUESTS }; struct mlx5_fw_reset { @@ -155,6 +156,28 @@ static void mlx5_fw_reset_complete_reload(struct mlx5_core_dev *dev) } } +static void mlx5_stop_sync_reset_poll(struct mlx5_core_dev *dev) +{ + struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset; + + del_timer_sync(&fw_reset->timer); +} + +static int mlx5_sync_reset_clear_reset_requested(struct mlx5_core_dev *dev, bool poll_health) +{ + struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset; + + if (!test_and_clear_bit(MLX5_FW_RESET_FLAGS_RESET_REQUESTED, &fw_reset->reset_flags)) { + mlx5_core_warn(dev, "Reset request was already cleared\n"); + return -EALREADY; + } + + mlx5_stop_sync_reset_poll(dev); + if (poll_health) + mlx5_start_health_poll(dev); + return 0; +} + static void mlx5_sync_reset_reload_work(struct work_struct *work) { struct mlx5_fw_reset *fw_reset = container_of(work, struct mlx5_fw_reset, @@ -162,6 +185,7 @@ static void mlx5_sync_reset_reload_work(struct work_struct *work) struct mlx5_core_dev *dev = fw_reset->dev; int err; + mlx5_sync_reset_clear_reset_requested(dev, false); mlx5_enter_error_state(dev, true); mlx5_unload_one(dev); err = mlx5_health_wait_pci_up(dev); @@ -171,23 +195,6 @@ static void mlx5_sync_reset_reload_work(struct work_struct *work) mlx5_fw_reset_complete_reload(dev); } -static void mlx5_stop_sync_reset_poll(struct mlx5_core_dev *dev) -{ - struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset; - - del_timer_sync(&fw_reset->timer); -} - -static void mlx5_sync_reset_clear_reset_requested(struct mlx5_core_dev *dev, bool poll_health) -{ - struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset; - - mlx5_stop_sync_reset_poll(dev); - clear_bit(MLX5_FW_RESET_FLAGS_RESET_REQUESTED, &fw_reset->reset_flags); - if (poll_health) - mlx5_start_health_poll(dev); -} - #define MLX5_RESET_POLL_INTERVAL (HZ / 10) static void poll_sync_reset(struct timer_list *t) { @@ -202,8 +209,10 @@ static void poll_sync_reset(struct timer_list *t) if (fatal_error) { mlx5_core_warn(dev, "Got Device Reset\n"); - mlx5_sync_reset_clear_reset_requested(dev, false); - queue_work(fw_reset->wq, &fw_reset->reset_reload_work); + if (!test_bit(MLX5_FW_RESET_FLAGS_DROP_NEW_REQUESTS, &fw_reset->reset_flags)) + queue_work(fw_reset->wq, &fw_reset->reset_reload_work); + else + mlx5_core_err(dev, "Device is being removed, Drop new reset work\n"); return; } @@ -229,13 +238,17 @@ static int mlx5_fw_reset_set_reset_sync_nack(struct mlx5_core_dev *dev) return mlx5_reg_mfrl_set(dev, MLX5_MFRL_REG_RESET_LEVEL3, 0, 2, false); } -static void mlx5_sync_reset_set_reset_requested(struct mlx5_core_dev *dev) +static int mlx5_sync_reset_set_reset_requested(struct mlx5_core_dev *dev) { struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset; + if (test_and_set_bit(MLX5_FW_RESET_FLAGS_RESET_REQUESTED, &fw_reset->reset_flags)) { + mlx5_core_warn(dev, "Reset request was already set\n"); + return -EALREADY; + } mlx5_stop_health_poll(dev, true); - set_bit(MLX5_FW_RESET_FLAGS_RESET_REQUESTED, &fw_reset->reset_flags); mlx5_start_sync_reset_poll(dev); + return 0; } static void mlx5_fw_live_patch_event(struct work_struct *work) @@ -264,7 +277,9 @@ static void mlx5_sync_reset_request_event(struct work_struct *work) err ? "Failed" : "Sent"); return; } - mlx5_sync_reset_set_reset_requested(dev); + if (mlx5_sync_reset_set_reset_requested(dev)) + return; + err = mlx5_fw_reset_set_reset_sync_ack(dev); if (err) mlx5_core_warn(dev, "PCI Sync FW Update Reset Ack Failed. Error code: %d\n", err); @@ -362,7 +377,8 @@ static void mlx5_sync_reset_now_event(struct work_struct *work) struct mlx5_core_dev *dev = fw_reset->dev; int err; - mlx5_sync_reset_clear_reset_requested(dev, false); + if (mlx5_sync_reset_clear_reset_requested(dev, false)) + return; mlx5_core_warn(dev, "Sync Reset now. Device is going to reset.\n"); @@ -391,10 +407,8 @@ static void mlx5_sync_reset_abort_event(struct work_struct *work) reset_abort_work); struct mlx5_core_dev *dev = fw_reset->dev; - if (!test_bit(MLX5_FW_RESET_FLAGS_RESET_REQUESTED, &fw_reset->reset_flags)) + if (mlx5_sync_reset_clear_reset_requested(dev, true)) return; - - mlx5_sync_reset_clear_reset_requested(dev, true); mlx5_core_warn(dev, "PCI Sync FW Update Reset Aborted.\n"); } @@ -423,9 +437,12 @@ static int fw_reset_event_notifier(struct notifier_block *nb, unsigned long acti struct mlx5_fw_reset *fw_reset = mlx5_nb_cof(nb, struct mlx5_fw_reset, nb); struct mlx5_eqe *eqe = data; + if (test_bit(MLX5_FW_RESET_FLAGS_DROP_NEW_REQUESTS, &fw_reset->reset_flags)) + return NOTIFY_DONE; + switch (eqe->sub_type) { case MLX5_GENERAL_SUBTYPE_FW_LIVE_PATCH_EVENT: - queue_work(fw_reset->wq, &fw_reset->fw_live_patch_work); + queue_work(fw_reset->wq, &fw_reset->fw_live_patch_work); break; case MLX5_GENERAL_SUBTYPE_PCI_SYNC_FOR_FW_UPDATE_EVENT: mlx5_sync_reset_events_handle(fw_reset, eqe); @@ -469,6 +486,18 @@ void mlx5_fw_reset_events_stop(struct mlx5_core_dev *dev) mlx5_eq_notifier_unregister(dev, &dev->priv.fw_reset->nb); } +void mlx5_drain_fw_reset(struct mlx5_core_dev *dev) +{ + struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset; + + set_bit(MLX5_FW_RESET_FLAGS_DROP_NEW_REQUESTS, &fw_reset->reset_flags); + cancel_work_sync(&fw_reset->fw_live_patch_work); + cancel_work_sync(&fw_reset->reset_request_work); + cancel_work_sync(&fw_reset->reset_reload_work); + cancel_work_sync(&fw_reset->reset_now_work); + cancel_work_sync(&fw_reset->reset_abort_work); +} + int mlx5_fw_reset_init(struct mlx5_core_dev *dev) { struct mlx5_fw_reset *fw_reset = kzalloc(sizeof(*fw_reset), GFP_KERNEL); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.h b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.h index 694fc7cb2684..dc141c7e641a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.h @@ -16,6 +16,7 @@ int mlx5_fw_reset_set_live_patch(struct mlx5_core_dev *dev); int mlx5_fw_reset_wait_reset_done(struct mlx5_core_dev *dev); void mlx5_fw_reset_events_start(struct mlx5_core_dev *dev); void mlx5_fw_reset_events_stop(struct mlx5_core_dev *dev); +void mlx5_drain_fw_reset(struct mlx5_core_dev *dev); int mlx5_fw_reset_init(struct mlx5_core_dev *dev); void mlx5_fw_reset_cleanup(struct mlx5_core_dev *dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c index 4a6ec15ef046..d6c3e6dfd71f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c @@ -100,6 +100,14 @@ static void mlx5_lag_fib_event_flush(struct notifier_block *nb) flush_workqueue(mp->wq); } +static void mlx5_lag_fib_set(struct lag_mp *mp, struct fib_info *fi, u32 dst, int dst_len) +{ + mp->fib.mfi = fi; + mp->fib.priority = fi->fib_priority; + mp->fib.dst = dst; + mp->fib.dst_len = dst_len; +} + struct mlx5_fib_event_work { struct work_struct work; struct mlx5_lag *ldev; @@ -110,10 +118,10 @@ struct mlx5_fib_event_work { }; }; -static void mlx5_lag_fib_route_event(struct mlx5_lag *ldev, - unsigned long event, - struct fib_info *fi) +static void mlx5_lag_fib_route_event(struct mlx5_lag *ldev, unsigned long event, + struct fib_entry_notifier_info *fen_info) { + struct fib_info *fi = fen_info->fi; struct lag_mp *mp = &ldev->lag_mp; struct fib_nh *fib_nh0, *fib_nh1; unsigned int nhs; @@ -121,13 +129,15 @@ static void mlx5_lag_fib_route_event(struct mlx5_lag *ldev, /* Handle delete event */ if (event == FIB_EVENT_ENTRY_DEL) { /* stop track */ - if (mp->mfi == fi) - mp->mfi = NULL; + if (mp->fib.mfi == fi) + mp->fib.mfi = NULL; return; } /* Handle multipath entry with lower priority value */ - if (mp->mfi && mp->mfi != fi && fi->fib_priority >= mp->mfi->fib_priority) + if (mp->fib.mfi && mp->fib.mfi != fi && + (mp->fib.dst != fen_info->dst || mp->fib.dst_len != fen_info->dst_len) && + fi->fib_priority >= mp->fib.priority) return; /* Handle add/replace event */ @@ -143,9 +153,9 @@ static void mlx5_lag_fib_route_event(struct mlx5_lag *ldev, i++; mlx5_lag_set_port_affinity(ldev, i); + mlx5_lag_fib_set(mp, fi, fen_info->dst, fen_info->dst_len); } - mp->mfi = fi; return; } @@ -165,7 +175,7 @@ static void mlx5_lag_fib_route_event(struct mlx5_lag *ldev, } /* First time we see multipath route */ - if (!mp->mfi && !__mlx5_lag_is_active(ldev)) { + if (!mp->fib.mfi && !__mlx5_lag_is_active(ldev)) { struct lag_tracker tracker; tracker = ldev->tracker; @@ -173,7 +183,7 @@ static void mlx5_lag_fib_route_event(struct mlx5_lag *ldev, } mlx5_lag_set_port_affinity(ldev, MLX5_LAG_NORMAL_AFFINITY); - mp->mfi = fi; + mlx5_lag_fib_set(mp, fi, fen_info->dst, fen_info->dst_len); } static void mlx5_lag_fib_nexthop_event(struct mlx5_lag *ldev, @@ -184,7 +194,7 @@ static void mlx5_lag_fib_nexthop_event(struct mlx5_lag *ldev, struct lag_mp *mp = &ldev->lag_mp; /* Check the nh event is related to the route */ - if (!mp->mfi || mp->mfi != fi) + if (!mp->fib.mfi || mp->fib.mfi != fi) return; /* nh added/removed */ @@ -214,7 +224,7 @@ static void mlx5_lag_fib_update(struct work_struct *work) case FIB_EVENT_ENTRY_REPLACE: case FIB_EVENT_ENTRY_DEL: mlx5_lag_fib_route_event(ldev, fib_work->event, - fib_work->fen_info.fi); + &fib_work->fen_info); fib_info_put(fib_work->fen_info.fi); break; case FIB_EVENT_NH_ADD: @@ -313,7 +323,7 @@ void mlx5_lag_mp_reset(struct mlx5_lag *ldev) /* Clear mfi, as it might become stale when a route delete event * has been missed, see mlx5_lag_fib_route_event(). */ - ldev->lag_mp.mfi = NULL; + ldev->lag_mp.fib.mfi = NULL; } int mlx5_lag_mp_init(struct mlx5_lag *ldev) @@ -324,7 +334,7 @@ int mlx5_lag_mp_init(struct mlx5_lag *ldev) /* always clear mfi, as it might become stale when a route delete event * has been missed */ - mp->mfi = NULL; + mp->fib.mfi = NULL; if (mp->fib_nb.notifier_call) return 0; @@ -354,5 +364,5 @@ void mlx5_lag_mp_cleanup(struct mlx5_lag *ldev) unregister_fib_notifier(&init_net, &mp->fib_nb); destroy_workqueue(mp->wq); mp->fib_nb.notifier_call = NULL; - mp->mfi = NULL; + mp->fib.mfi = NULL; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.h b/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.h index 57af962cad29..056a066da604 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.h @@ -15,7 +15,12 @@ enum mlx5_lag_port_affinity { struct lag_mp { struct notifier_block fib_nb; - struct fib_info *mfi; /* used in tracking fib events */ + struct { + const void *mfi; /* used in tracking fib events */ + u32 priority; + u32 dst; + int dst_len; + } fib; struct workqueue_struct *wq; }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c index a6592f9c3c05..5be322528279 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c @@ -505,7 +505,7 @@ static int mlx5_lag_create_inner_ttc_table(struct mlx5_lag *ldev) struct ttc_params ttc_params = {}; mlx5_lag_set_inner_ttc_params(ldev, &ttc_params); - port_sel->inner.ttc = mlx5_create_ttc_table(dev, &ttc_params); + port_sel->inner.ttc = mlx5_create_inner_ttc_table(dev, &ttc_params); if (IS_ERR(port_sel->inner.ttc)) return PTR_ERR(port_sel->inner.ttc); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c index b63dec24747a..b78f2ba25c19 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c @@ -408,6 +408,8 @@ static int mlx5_generate_inner_ttc_table_rules(struct mlx5_core_dev *dev, for (tt = 0; tt < MLX5_NUM_TT; tt++) { struct mlx5_ttc_rule *rule = &rules[tt]; + if (test_bit(tt, params->ignore_dests)) + continue; rule->rule = mlx5_generate_inner_ttc_rule(dev, ft, ¶ms->dests[tt], ttc_rules[tt].etype, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 2589e39eb9c7..ef196cb764e2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -938,6 +938,12 @@ static int mlx5_init_once(struct mlx5_core_dev *dev) goto err_sf_table_cleanup; } + err = mlx5_fs_core_alloc(dev); + if (err) { + mlx5_core_err(dev, "Failed to alloc flow steering\n"); + goto err_fs; + } + dev->dm = mlx5_dm_create(dev); if (IS_ERR(dev->dm)) mlx5_core_warn(dev, "Failed to init device memory%d\n", err); @@ -948,6 +954,8 @@ static int mlx5_init_once(struct mlx5_core_dev *dev) return 0; +err_fs: + mlx5_sf_table_cleanup(dev); err_sf_table_cleanup: mlx5_sf_hw_table_cleanup(dev); err_sf_hw_table_cleanup: @@ -985,6 +993,7 @@ static void mlx5_cleanup_once(struct mlx5_core_dev *dev) mlx5_hv_vhca_destroy(dev->hv_vhca); mlx5_fw_tracer_destroy(dev->tracer); mlx5_dm_cleanup(dev); + mlx5_fs_core_free(dev); mlx5_sf_table_cleanup(dev); mlx5_sf_hw_table_cleanup(dev); mlx5_vhca_event_cleanup(dev); @@ -1191,7 +1200,7 @@ static int mlx5_load(struct mlx5_core_dev *dev) goto err_tls_start; } - err = mlx5_init_fs(dev); + err = mlx5_fs_core_init(dev); if (err) { mlx5_core_err(dev, "Failed to init flow steering\n"); goto err_fs; @@ -1236,7 +1245,7 @@ err_ec: err_vhca: mlx5_vhca_event_stop(dev); err_set_hca: - mlx5_cleanup_fs(dev); + mlx5_fs_core_cleanup(dev); err_fs: mlx5_accel_tls_cleanup(dev); err_tls_start: @@ -1265,7 +1274,7 @@ static void mlx5_unload(struct mlx5_core_dev *dev) mlx5_ec_cleanup(dev); mlx5_sf_hw_table_destroy(dev); mlx5_vhca_event_stop(dev); - mlx5_cleanup_fs(dev); + mlx5_fs_core_cleanup(dev); mlx5_accel_ipsec_cleanup(dev); mlx5_accel_tls_cleanup(dev); mlx5_fpga_device_stop(dev); @@ -1618,6 +1627,10 @@ static void remove_one(struct pci_dev *pdev) struct mlx5_core_dev *dev = pci_get_drvdata(pdev); struct devlink *devlink = priv_to_devlink(dev); + /* mlx5_drain_fw_reset() is using devlink APIs. Hence, we must drain + * fw_reset before unregistering the devlink. + */ + mlx5_drain_fw_reset(dev); devlink_unregister(devlink); mlx5_sriov_disable(pdev); mlx5_crdump_disable(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c index 850937cd8bf9..1383550f44c1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c @@ -530,6 +530,37 @@ static int dr_action_handle_cs_recalc(struct mlx5dr_domain *dmn, return 0; } +static void dr_action_modify_ttl_adjust(struct mlx5dr_domain *dmn, + struct mlx5dr_ste_actions_attr *attr, + bool rx_rule, + bool *recalc_cs_required) +{ + *recalc_cs_required = false; + + /* if device supports csum recalculation - no adjustment needed */ + if (mlx5dr_ste_supp_ttl_cs_recalc(&dmn->info.caps)) + return; + + /* no adjustment needed on TX rules */ + if (!rx_rule) + return; + + if (!MLX5_CAP_ESW_FLOWTABLE(dmn->mdev, fdb_ipv4_ttl_modify)) { + /* Ignore the modify TTL action. + * It is always kept as last HW action. + */ + attr->modify_actions--; + return; + } + + if (dmn->type == MLX5DR_DOMAIN_TYPE_FDB) + /* Due to a HW bug on some devices, modifying TTL on RX flows + * will cause an incorrect checksum calculation. In such cases + * we will use a FW table to recalculate the checksum. + */ + *recalc_cs_required = true; +} + static void dr_action_print_sequence(struct mlx5dr_domain *dmn, struct mlx5dr_action *actions[], int last_idx) @@ -650,8 +681,9 @@ int mlx5dr_actions_build_ste_arr(struct mlx5dr_matcher *matcher, case DR_ACTION_TYP_MODIFY_HDR: attr.modify_index = action->rewrite->index; attr.modify_actions = action->rewrite->num_of_actions; - recalc_cs_required = action->rewrite->modify_ttl && - !mlx5dr_ste_supp_ttl_cs_recalc(&dmn->info.caps); + if (action->rewrite->modify_ttl) + dr_action_modify_ttl_adjust(dmn, &attr, rx_rule, + &recalc_cs_required); break; case DR_ACTION_TYP_L2_TO_TNL_L2: case DR_ACTION_TYP_L2_TO_TNL_L3: @@ -732,12 +764,7 @@ int mlx5dr_actions_build_ste_arr(struct mlx5dr_matcher *matcher, *new_hw_ste_arr_sz = nic_matcher->num_of_builders; last_ste = ste_arr + DR_STE_SIZE * (nic_matcher->num_of_builders - 1); - /* Due to a HW bug in some devices, modifying TTL on RX flows will - * cause an incorrect checksum calculation. In this case we will - * use a FW table to recalculate. - */ - if (dmn->type == MLX5DR_DOMAIN_TYPE_FDB && - rx_rule && recalc_cs_required && dest_action) { + if (recalc_cs_required && dest_action) { ret = dr_action_handle_cs_recalc(dmn, dest_action, &attr.final_icm_addr); if (ret) { mlx5dr_err(dmn, @@ -842,7 +869,8 @@ struct mlx5dr_action * mlx5dr_action_create_mult_dest_tbl(struct mlx5dr_domain *dmn, struct mlx5dr_action_dest *dests, u32 num_of_dests, - bool ignore_flow_level) + bool ignore_flow_level, + u32 flow_source) { struct mlx5dr_cmd_flow_destination_hw_info *hw_dests; struct mlx5dr_action **ref_actions; @@ -914,7 +942,8 @@ mlx5dr_action_create_mult_dest_tbl(struct mlx5dr_domain *dmn, reformat_req, &action->dest_tbl->fw_tbl.id, &action->dest_tbl->fw_tbl.group_id, - ignore_flow_level); + ignore_flow_level, + flow_source); if (ret) goto free_action; @@ -1556,12 +1585,6 @@ dr_action_modify_check_is_ttl_modify(const void *sw_action) return sw_field == MLX5_ACTION_IN_FIELD_OUT_IP_TTL; } -static bool dr_action_modify_ttl_ignore(struct mlx5dr_domain *dmn) -{ - return !mlx5dr_ste_supp_ttl_cs_recalc(&dmn->info.caps) && - !MLX5_CAP_ESW_FLOWTABLE(dmn->mdev, fdb_ipv4_ttl_modify); -} - static int dr_actions_convert_modify_header(struct mlx5dr_action *action, u32 max_hw_actions, u32 num_sw_actions, @@ -1573,6 +1596,7 @@ static int dr_actions_convert_modify_header(struct mlx5dr_action *action, const struct mlx5dr_ste_action_modify_field *hw_dst_action_info; const struct mlx5dr_ste_action_modify_field *hw_src_action_info; struct mlx5dr_domain *dmn = action->rewrite->dmn; + __be64 *modify_ttl_sw_action = NULL; int ret, i, hw_idx = 0; __be64 *sw_action; __be64 hw_action; @@ -1585,8 +1609,14 @@ static int dr_actions_convert_modify_header(struct mlx5dr_action *action, action->rewrite->allow_rx = 1; action->rewrite->allow_tx = 1; - for (i = 0; i < num_sw_actions; i++) { - sw_action = &sw_actions[i]; + for (i = 0; i < num_sw_actions || modify_ttl_sw_action; i++) { + /* modify TTL is handled separately, as a last action */ + if (i == num_sw_actions) { + sw_action = modify_ttl_sw_action; + modify_ttl_sw_action = NULL; + } else { + sw_action = &sw_actions[i]; + } ret = dr_action_modify_check_field_limitation(action, sw_action); @@ -1595,10 +1625,9 @@ static int dr_actions_convert_modify_header(struct mlx5dr_action *action, if (!(*modify_ttl) && dr_action_modify_check_is_ttl_modify(sw_action)) { - if (dr_action_modify_ttl_ignore(dmn)) - continue; - + modify_ttl_sw_action = sw_action; *modify_ttl = true; + continue; } /* Convert SW action to HW action */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_fw.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_fw.c index 68a4c32d5f34..f05ef0cd54ba 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_fw.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_fw.c @@ -104,7 +104,8 @@ int mlx5dr_fw_create_md_tbl(struct mlx5dr_domain *dmn, bool reformat_req, u32 *tbl_id, u32 *group_id, - bool ignore_flow_level) + bool ignore_flow_level, + u32 flow_source) { struct mlx5dr_cmd_create_flow_table_attr ft_attr = {}; struct mlx5dr_cmd_fte_info fte_info = {}; @@ -139,6 +140,7 @@ int mlx5dr_fw_create_md_tbl(struct mlx5dr_domain *dmn, fte_info.val = val; fte_info.dest_arr = dest; fte_info.ignore_flow_level = ignore_flow_level; + fte_info.flow_context.flow_source = flow_source; ret = mlx5dr_cmd_set_fte(dmn->mdev, 0, 0, &ft_info, *group_id, &fte_info); if (ret) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c index 5a322335f204..2010d4ac6519 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c @@ -420,7 +420,7 @@ dr_ste_v0_set_actions_tx(struct mlx5dr_domain *dmn, * encapsulation. The reason for that is that we support * modify headers for outer headers only */ - if (action_type_set[DR_ACTION_TYP_MODIFY_HDR]) { + if (action_type_set[DR_ACTION_TYP_MODIFY_HDR] && attr->modify_actions) { dr_ste_v0_set_entry_type(last_ste, DR_STE_TYPE_MODIFY_PKT); dr_ste_v0_set_rewrite_actions(last_ste, attr->modify_actions, @@ -513,7 +513,7 @@ dr_ste_v0_set_actions_rx(struct mlx5dr_domain *dmn, } } - if (action_type_set[DR_ACTION_TYP_MODIFY_HDR]) { + if (action_type_set[DR_ACTION_TYP_MODIFY_HDR] && attr->modify_actions) { if (dr_ste_v0_get_entry_type(last_ste) == DR_STE_TYPE_MODIFY_PKT) dr_ste_v0_arr_init_next(&last_ste, added_stes, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h index 46866a5fc5ca..98320e3945ad 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h @@ -1461,7 +1461,8 @@ int mlx5dr_fw_create_md_tbl(struct mlx5dr_domain *dmn, bool reformat_req, u32 *tbl_id, u32 *group_id, - bool ignore_flow_level); + bool ignore_flow_level, + u32 flow_source); void mlx5dr_fw_destroy_md_tbl(struct mlx5dr_domain *dmn, u32 tbl_id, u32 group_id); #endif /* _DR_TYPES_H_ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c index 045b0cf90063..728f81882589 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c @@ -520,6 +520,7 @@ static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns, } else if (num_term_actions > 1) { bool ignore_flow_level = !!(fte->action.flags & FLOW_ACT_IGNORE_FLOW_LEVEL); + u32 flow_source = fte->flow_context.flow_source; if (num_actions == MLX5_FLOW_CONTEXT_ACTION_MAX || fs_dr_num_actions == MLX5_FLOW_CONTEXT_ACTION_MAX) { @@ -529,7 +530,8 @@ static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns, tmp_action = mlx5dr_action_create_mult_dest_tbl(domain, term_actions, num_term_actions, - ignore_flow_level); + ignore_flow_level, + flow_source); if (!tmp_action) { err = -EOPNOTSUPP; goto free_actions; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h index ec5cbec0d455..7626c85643b1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h @@ -99,7 +99,8 @@ struct mlx5dr_action * mlx5dr_action_create_mult_dest_tbl(struct mlx5dr_domain *dmn, struct mlx5dr_action_dest *dests, u32 num_of_dests, - bool ignore_flow_level); + bool ignore_flow_level, + u32 flow_source); struct mlx5dr_action *mlx5dr_action_create_drop(void); diff --git a/drivers/net/ethernet/mellanox/mlxsw/i2c.c b/drivers/net/ethernet/mellanox/mlxsw/i2c.c index 939b692ffc33..ce843ea91464 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/i2c.c +++ b/drivers/net/ethernet/mellanox/mlxsw/i2c.c @@ -650,6 +650,7 @@ static int mlxsw_i2c_probe(struct i2c_client *client, return 0; errout: + mutex_destroy(&mlxsw_i2c->cmd.lock); i2c_set_clientdata(client, NULL); return err; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c index 01cf5a6a26bd..a2ee695a3f17 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c @@ -568,10 +568,8 @@ static int mlxsw_sp2_ipip_rem_addr_set_gre6(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_ipip_entry *ipip_entry) { - struct __ip6_tnl_parm parms6; - - parms6 = mlxsw_sp_ipip_netdev_parms6(ipip_entry->ol_dev); - return mlxsw_sp_ipv6_addr_kvdl_index_get(mlxsw_sp, &parms6.raddr, + return mlxsw_sp_ipv6_addr_kvdl_index_get(mlxsw_sp, + &ipip_entry->parms.daddr.addr6, &ipip_entry->dip_kvdl_index); } @@ -579,10 +577,7 @@ static void mlxsw_sp2_ipip_rem_addr_unset_gre6(struct mlxsw_sp *mlxsw_sp, const struct mlxsw_sp_ipip_entry *ipip_entry) { - struct __ip6_tnl_parm parms6; - - parms6 = mlxsw_sp_ipip_netdev_parms6(ipip_entry->ol_dev); - mlxsw_sp_ipv6_addr_put(mlxsw_sp, &parms6.raddr); + mlxsw_sp_ipv6_addr_put(mlxsw_sp, &ipip_entry->parms.daddr.addr6); } static const struct mlxsw_sp_ipip_ops mlxsw_sp2_ipip_gre6_ops = { diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c index b73466470f75..fe663b0ab708 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c @@ -423,7 +423,7 @@ mlxsw_sp_span_gretap4_route(const struct net_device *to_dev, parms = mlxsw_sp_ipip_netdev_parms4(to_dev); ip_tunnel_init_flow(&fl4, parms.iph.protocol, *daddrp, *saddrp, - 0, 0, parms.link, tun->fwmark, 0); + 0, 0, dev_net(to_dev), parms.link, tun->fwmark, 0); rt = ip_route_output_key(tun->net, &fl4); if (IS_ERR(rt)) diff --git a/drivers/net/ethernet/micrel/Kconfig b/drivers/net/ethernet/micrel/Kconfig index 93df3049cdc0..830363bafcce 100644 --- a/drivers/net/ethernet/micrel/Kconfig +++ b/drivers/net/ethernet/micrel/Kconfig @@ -28,6 +28,7 @@ config KS8842 config KS8851 tristate "Micrel KS8851 SPI" depends on SPI + depends on PTP_1588_CLOCK_OPTIONAL select MII select CRC32 select EEPROM_93CX6 @@ -39,6 +40,7 @@ config KS8851 config KS8851_MLL tristate "Micrel KS8851 MLL" depends on HAS_IOMEM + depends on PTP_1588_CLOCK_OPTIONAL select MII select CRC32 select EEPROM_93CX6 diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_mac.c b/drivers/net/ethernet/microchip/lan966x/lan966x_mac.c index ce5970bdcc6a..005e56ea5da1 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_mac.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_mac.c @@ -346,7 +346,8 @@ static void lan966x_mac_irq_process(struct lan966x *lan966x, u32 row, lan966x_mac_process_raw_entry(&raw_entries[column], mac, &vid, &dest_idx); - WARN_ON(dest_idx > lan966x->num_phys_ports); + if (WARN_ON(dest_idx >= lan966x->num_phys_ports)) + continue; /* If the entry in SW is found, then there is nothing * to do @@ -392,7 +393,8 @@ static void lan966x_mac_irq_process(struct lan966x *lan966x, u32 row, lan966x_mac_process_raw_entry(&raw_entries[column], mac, &vid, &dest_idx); - WARN_ON(dest_idx > lan966x->num_phys_ports); + if (WARN_ON(dest_idx >= lan966x->num_phys_ports)) + continue; mac_entry = lan966x_mac_alloc_entry(mac, vid, dest_idx); if (!mac_entry) diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c index 1f8c67f0261b..05f6dcc9dfd5 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c @@ -103,6 +103,24 @@ static int lan966x_create_targets(struct platform_device *pdev, return 0; } +static bool lan966x_port_unique_address(struct net_device *dev) +{ + struct lan966x_port *port = netdev_priv(dev); + struct lan966x *lan966x = port->lan966x; + int p; + + for (p = 0; p < lan966x->num_phys_ports; ++p) { + port = lan966x->ports[p]; + if (!port || port->dev == dev) + continue; + + if (ether_addr_equal(dev->dev_addr, port->dev->dev_addr)) + return false; + } + + return true; +} + static int lan966x_port_set_mac_address(struct net_device *dev, void *p) { struct lan966x_port *port = netdev_priv(dev); @@ -110,16 +128,26 @@ static int lan966x_port_set_mac_address(struct net_device *dev, void *p) const struct sockaddr *addr = p; int ret; + if (ether_addr_equal(addr->sa_data, dev->dev_addr)) + return 0; + /* Learn the new net device MAC address in the mac table. */ ret = lan966x_mac_cpu_learn(lan966x, addr->sa_data, HOST_PVID); if (ret) return ret; + /* If there is another port with the same address as the dev, then don't + * delete it from the MAC table + */ + if (!lan966x_port_unique_address(dev)) + goto out; + /* Then forget the previous one. */ ret = lan966x_mac_cpu_forget(lan966x, dev->dev_addr, HOST_PVID); if (ret) return ret; +out: eth_hw_addr_set(dev, addr->sa_data); return ret; } @@ -446,6 +474,12 @@ static bool lan966x_hw_offload(struct lan966x *lan966x, u32 port, ANA_CPU_FWD_CFG_MLD_REDIR_ENA))) return true; + if (eth_type_vlan(skb->protocol)) { + skb = skb_vlan_untag(skb); + if (unlikely(!skb)) + return false; + } + if (skb->protocol == htons(ETH_P_IP) && ip_hdr(skb)->protocol == IPPROTO_IGMP) return false; @@ -665,6 +699,9 @@ static void lan966x_cleanup_ports(struct lan966x *lan966x) disable_irq(lan966x->ana_irq); lan966x->ana_irq = -ENXIO; } + + if (lan966x->ptp_irq) + devm_free_irq(lan966x->dev, lan966x->ptp_irq, lan966x); } static int lan966x_probe_port(struct lan966x *lan966x, u32 p, diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_ptp.c b/drivers/net/ethernet/microchip/lan966x/lan966x_ptp.c index ae782778d6dd..0a1041da4384 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_ptp.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_ptp.c @@ -29,10 +29,10 @@ enum { static u64 lan966x_ptp_get_nominal_value(void) { - u64 res = 0x304d2df1; - - res <<= 32; - return res; + /* This is the default value that for each system clock, the time of day + * is increased. It has the format 5.59 nanosecond. + */ + return 0x304d4873ecade305; } int lan966x_ptp_hwtstamp_set(struct lan966x_port *port, struct ifreq *ifr) diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_switchdev.c b/drivers/net/ethernet/microchip/lan966x/lan966x_switchdev.c index e3555c94294d..df2bee678559 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_switchdev.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_switchdev.c @@ -322,8 +322,7 @@ static int lan966x_port_prechangeupper(struct net_device *dev, if (netif_is_bridge_master(info->upper_dev) && !info->linking) switchdev_bridge_port_unoffload(port->dev, port, - &lan966x_switchdev_nb, - &lan966x_switchdev_blocking_nb); + NULL, NULL); return NOTIFY_DONE; } diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index e443bd8b2d09..20ceac81a2c2 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -551,7 +551,7 @@ int ocelot_port_vlan_filtering(struct ocelot *ocelot, int port, struct ocelot_vcap_block *block = &ocelot->block[VCAP_IS1]; struct ocelot_port *ocelot_port = ocelot->ports[port]; struct ocelot_vcap_filter *filter; - int err; + int err = 0; u32 val; list_for_each_entry(filter, &block->rules, list) { @@ -570,7 +570,7 @@ int ocelot_port_vlan_filtering(struct ocelot *ocelot, int port, if (vlan_aware) err = ocelot_del_vlan_unaware_pvid(ocelot, port, ocelot_port->bridge); - else + else if (ocelot_port->bridge) err = ocelot_add_vlan_unaware_pvid(ocelot, port, ocelot_port->bridge); if (err) @@ -629,6 +629,13 @@ int ocelot_vlan_add(struct ocelot *ocelot, int port, u16 vid, bool pvid, { int err; + /* Ignore VID 0 added to our RX filter by the 8021q module, since + * that collides with OCELOT_STANDALONE_PVID and changes it from + * egress-untagged to egress-tagged. + */ + if (!vid) + return 0; + err = ocelot_vlan_member_add(ocelot, port, vid, untagged); if (err) return err; @@ -651,6 +658,9 @@ int ocelot_vlan_del(struct ocelot *ocelot, int port, u16 vid) bool del_pvid = false; int err; + if (!vid) + return 0; + if (ocelot_port->pvid_vlan && ocelot_port->pvid_vlan->vid == vid) del_pvid = true; @@ -1612,7 +1622,7 @@ int ocelot_trap_add(struct ocelot *ocelot, int port, trap->action.mask_mode = OCELOT_MASK_MODE_PERMIT_DENY; trap->action.port_mask = 0; trap->take_ts = take_ts; - list_add_tail(&trap->trap_list, &ocelot->traps); + trap->is_trap = true; new = true; } @@ -1624,10 +1634,8 @@ int ocelot_trap_add(struct ocelot *ocelot, int port, err = ocelot_vcap_filter_replace(ocelot, trap); if (err) { trap->ingress_port_mask &= ~BIT(port); - if (!trap->ingress_port_mask) { - list_del(&trap->trap_list); + if (!trap->ingress_port_mask) kfree(trap); - } return err; } @@ -1647,11 +1655,8 @@ int ocelot_trap_del(struct ocelot *ocelot, int port, unsigned long cookie) return 0; trap->ingress_port_mask &= ~BIT(port); - if (!trap->ingress_port_mask) { - list_del(&trap->trap_list); - + if (!trap->ingress_port_mask) return ocelot_vcap_filter_del(ocelot, trap); - } return ocelot_vcap_filter_replace(ocelot, trap); } @@ -2859,6 +2864,8 @@ static void ocelot_port_set_mcast_flood(struct ocelot *ocelot, int port, val = BIT(port); ocelot_rmw_rix(ocelot, val, BIT(port), ANA_PGID_PGID, PGID_MC); + ocelot_rmw_rix(ocelot, val, BIT(port), ANA_PGID_PGID, PGID_MCIPV4); + ocelot_rmw_rix(ocelot, val, BIT(port), ANA_PGID_PGID, PGID_MCIPV6); } static void ocelot_port_set_bcast_flood(struct ocelot *ocelot, int port, diff --git a/drivers/net/ethernet/mscc/ocelot_flower.c b/drivers/net/ethernet/mscc/ocelot_flower.c index 03b5e59d033e..51cf241ff7d0 100644 --- a/drivers/net/ethernet/mscc/ocelot_flower.c +++ b/drivers/net/ethernet/mscc/ocelot_flower.c @@ -280,9 +280,10 @@ static int ocelot_flower_parse_action(struct ocelot *ocelot, int port, filter->type = OCELOT_VCAP_FILTER_OFFLOAD; break; case FLOW_ACTION_TRAP: - if (filter->block_id != VCAP_IS2) { + if (filter->block_id != VCAP_IS2 || + filter->lookup != 0) { NL_SET_ERR_MSG_MOD(extack, - "Trap action can only be offloaded to VCAP IS2"); + "Trap action can only be offloaded to VCAP IS2 lookup 0"); return -EOPNOTSUPP; } if (filter->goto_target != -1) { @@ -295,7 +296,7 @@ static int ocelot_flower_parse_action(struct ocelot *ocelot, int port, filter->action.cpu_copy_ena = true; filter->action.cpu_qu_num = 0; filter->type = OCELOT_VCAP_FILTER_OFFLOAD; - list_add_tail(&filter->trap_list, &ocelot->traps); + filter->is_trap = true; break; case FLOW_ACTION_POLICE: if (filter->block_id == PSFP_BLOCK_ID) { @@ -878,8 +879,6 @@ int ocelot_cls_flower_replace(struct ocelot *ocelot, int port, ret = ocelot_flower_parse(ocelot, port, ingress, f, filter); if (ret) { - if (!list_empty(&filter->trap_list)) - list_del(&filter->trap_list); kfree(filter); return ret; } diff --git a/drivers/net/ethernet/mscc/ocelot_vcap.c b/drivers/net/ethernet/mscc/ocelot_vcap.c index c8701ac955a8..eeb4cc07dd16 100644 --- a/drivers/net/ethernet/mscc/ocelot_vcap.c +++ b/drivers/net/ethernet/mscc/ocelot_vcap.c @@ -374,7 +374,6 @@ static void is2_entry_set(struct ocelot *ocelot, int ix, OCELOT_VCAP_BIT_0); vcap_key_set(vcap, &data, VCAP_IS2_HK_IGR_PORT_MASK, 0, ~filter->ingress_port_mask); - vcap_key_bit_set(vcap, &data, VCAP_IS2_HK_FIRST, OCELOT_VCAP_BIT_ANY); vcap_key_bit_set(vcap, &data, VCAP_IS2_HK_HOST_MATCH, OCELOT_VCAP_BIT_ANY); vcap_key_bit_set(vcap, &data, VCAP_IS2_HK_L2_MC, filter->dmac_mc); @@ -1217,6 +1216,8 @@ int ocelot_vcap_filter_add(struct ocelot *ocelot, struct ocelot_vcap_filter *tmp; tmp = ocelot_vcap_block_find_filter_by_index(block, i); + /* Read back the filter's counters before moving it */ + vcap_entry_get(ocelot, i - 1, tmp); vcap_entry_set(ocelot, i, tmp); } @@ -1250,7 +1251,11 @@ int ocelot_vcap_filter_del(struct ocelot *ocelot, struct ocelot_vcap_filter del_filter; int i, index; + /* Need to inherit the block_id so that vcap_entry_set() + * does not get confused and knows where to install it. + */ memset(&del_filter, 0, sizeof(del_filter)); + del_filter.block_id = filter->block_id; /* Gets index of the filter */ index = ocelot_vcap_block_get_filter_index(block, filter); @@ -1265,6 +1270,8 @@ int ocelot_vcap_filter_del(struct ocelot *ocelot, struct ocelot_vcap_filter *tmp; tmp = ocelot_vcap_block_find_filter_by_index(block, i); + /* Read back the filter's counters before moving it */ + vcap_entry_get(ocelot, i + 1, tmp); vcap_entry_set(ocelot, i, tmp); } diff --git a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c index 50ac3ee2577a..21d2645885ce 100644 --- a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c +++ b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c @@ -2903,11 +2903,9 @@ static netdev_tx_t myri10ge_sw_tso(struct sk_buff *skb, status = myri10ge_xmit(curr, dev); if (status != 0) { dev_kfree_skb_any(curr); - if (segs != NULL) { - curr = segs; - segs = next; + skb_list_walk_safe(next, curr, next) { curr->next = NULL; - dev_kfree_skb_any(segs); + dev_kfree_skb_any(curr); } goto drop; } diff --git a/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c b/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c index 6ffc62c41165..0a7a757494bc 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c @@ -256,7 +256,7 @@ static int ionic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) err = ionic_map_bars(ionic); if (err) - goto err_out_pci_disable_device; + goto err_out_pci_release_regions; /* Configure the device */ err = ionic_setup(ionic); @@ -360,6 +360,7 @@ err_out_teardown: err_out_unmap_bars: ionic_unmap_bars(ionic); +err_out_pci_release_regions: pci_release_regions(pdev); err_out_pci_disable_device: pci_disable_device(pdev); diff --git a/drivers/net/ethernet/qlogic/qed/qed_debug.c b/drivers/net/ethernet/qlogic/qed/qed_debug.c index e3edca187ddf..5250d1d1e49c 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_debug.c +++ b/drivers/net/ethernet/qlogic/qed/qed_debug.c @@ -489,7 +489,7 @@ struct split_type_defs { #define STATIC_DEBUG_LINE_DWORDS 9 -#define NUM_COMMON_GLOBAL_PARAMS 11 +#define NUM_COMMON_GLOBAL_PARAMS 10 #define MAX_RECURSION_DEPTH 10 diff --git a/drivers/net/ethernet/qlogic/qede/qede_fp.c b/drivers/net/ethernet/qlogic/qede/qede_fp.c index b242000a77fd..b7cc36589f59 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_fp.c +++ b/drivers/net/ethernet/qlogic/qede/qede_fp.c @@ -748,6 +748,9 @@ qede_build_skb(struct qede_rx_queue *rxq, buf = page_address(bd->data) + bd->page_offset; skb = build_skb(buf, rxq->rx_buf_seg_size); + if (unlikely(!skb)) + return NULL; + skb_reserve(skb, pad); skb_put(skb, len); diff --git a/drivers/net/ethernet/qlogic/qla3xxx.c b/drivers/net/ethernet/qlogic/qla3xxx.c index b30589a135c2..06f4d9a9e938 100644 --- a/drivers/net/ethernet/qlogic/qla3xxx.c +++ b/drivers/net/ethernet/qlogic/qla3xxx.c @@ -3614,7 +3614,8 @@ static void ql_reset_work(struct work_struct *work) qdev->mem_map_registers; unsigned long hw_flags; - if (test_bit((QL_RESET_PER_SCSI | QL_RESET_START), &qdev->flags)) { + if (test_bit(QL_RESET_PER_SCSI, &qdev->flags) || + test_bit(QL_RESET_START, &qdev->flags)) { clear_bit(QL_LINK_MASTER, &qdev->flags); /* diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c index 50d535981a35..f8edb3f1b73a 100644 --- a/drivers/net/ethernet/sfc/ef10.c +++ b/drivers/net/ethernet/sfc/ef10.c @@ -3579,6 +3579,11 @@ static int efx_ef10_mtd_probe(struct efx_nic *efx) n_parts++; } + if (!n_parts) { + kfree(parts); + return 0; + } + rc = efx_mtd_add(efx, &parts[0].common, n_parts, sizeof(*parts)); fail: if (rc) diff --git a/drivers/net/ethernet/sfc/efx_channels.c b/drivers/net/ethernet/sfc/efx_channels.c index f9064532beb6..40df910aa140 100644 --- a/drivers/net/ethernet/sfc/efx_channels.c +++ b/drivers/net/ethernet/sfc/efx_channels.c @@ -786,9 +786,90 @@ void efx_remove_channels(struct efx_nic *efx) kfree(efx->xdp_tx_queues); } +static int efx_set_xdp_tx_queue(struct efx_nic *efx, int xdp_queue_number, + struct efx_tx_queue *tx_queue) +{ + if (xdp_queue_number >= efx->xdp_tx_queue_count) + return -EINVAL; + + netif_dbg(efx, drv, efx->net_dev, + "Channel %u TXQ %u is XDP %u, HW %u\n", + tx_queue->channel->channel, tx_queue->label, + xdp_queue_number, tx_queue->queue); + efx->xdp_tx_queues[xdp_queue_number] = tx_queue; + return 0; +} + +static void efx_set_xdp_channels(struct efx_nic *efx) +{ + struct efx_tx_queue *tx_queue; + struct efx_channel *channel; + unsigned int next_queue = 0; + int xdp_queue_number = 0; + int rc; + + /* We need to mark which channels really have RX and TX + * queues, and adjust the TX queue numbers if we have separate + * RX-only and TX-only channels. + */ + efx_for_each_channel(channel, efx) { + if (channel->channel < efx->tx_channel_offset) + continue; + + if (efx_channel_is_xdp_tx(channel)) { + efx_for_each_channel_tx_queue(tx_queue, channel) { + tx_queue->queue = next_queue++; + rc = efx_set_xdp_tx_queue(efx, xdp_queue_number, + tx_queue); + if (rc == 0) + xdp_queue_number++; + } + } else { + efx_for_each_channel_tx_queue(tx_queue, channel) { + tx_queue->queue = next_queue++; + netif_dbg(efx, drv, efx->net_dev, + "Channel %u TXQ %u is HW %u\n", + channel->channel, tx_queue->label, + tx_queue->queue); + } + + /* If XDP is borrowing queues from net stack, it must + * use the queue with no csum offload, which is the + * first one of the channel + * (note: tx_queue_by_type is not initialized yet) + */ + if (efx->xdp_txq_queues_mode == + EFX_XDP_TX_QUEUES_BORROWED) { + tx_queue = &channel->tx_queue[0]; + rc = efx_set_xdp_tx_queue(efx, xdp_queue_number, + tx_queue); + if (rc == 0) + xdp_queue_number++; + } + } + } + WARN_ON(efx->xdp_txq_queues_mode == EFX_XDP_TX_QUEUES_DEDICATED && + xdp_queue_number != efx->xdp_tx_queue_count); + WARN_ON(efx->xdp_txq_queues_mode != EFX_XDP_TX_QUEUES_DEDICATED && + xdp_queue_number > efx->xdp_tx_queue_count); + + /* If we have more CPUs than assigned XDP TX queues, assign the already + * existing queues to the exceeding CPUs + */ + next_queue = 0; + while (xdp_queue_number < efx->xdp_tx_queue_count) { + tx_queue = efx->xdp_tx_queues[next_queue++]; + rc = efx_set_xdp_tx_queue(efx, xdp_queue_number, tx_queue); + if (rc == 0) + xdp_queue_number++; + } +} + int efx_realloc_channels(struct efx_nic *efx, u32 rxq_entries, u32 txq_entries) { - struct efx_channel *other_channel[EFX_MAX_CHANNELS], *channel; + struct efx_channel *other_channel[EFX_MAX_CHANNELS], *channel, + *ptp_channel = efx_ptp_channel(efx); + struct efx_ptp_data *ptp_data = efx->ptp_data; unsigned int i, next_buffer_table = 0; u32 old_rxq_entries, old_txq_entries; int rc, rc2; @@ -857,7 +938,9 @@ int efx_realloc_channels(struct efx_nic *efx, u32 rxq_entries, u32 txq_entries) efx_init_napi_channel(efx->channel[i]); } + efx_set_xdp_channels(efx); out: + efx->ptp_data = NULL; /* Destroy unused channel structures */ for (i = 0; i < efx->n_channels; i++) { channel = other_channel[i]; @@ -868,6 +951,7 @@ out: } } + efx->ptp_data = ptp_data; rc2 = efx_soft_enable_interrupts(efx); if (rc2) { rc = rc ? rc : rc2; @@ -886,29 +970,13 @@ rollback: efx->txq_entries = old_txq_entries; for (i = 0; i < efx->n_channels; i++) swap(efx->channel[i], other_channel[i]); + efx_ptp_update_channel(efx, ptp_channel); goto out; } -static inline int -efx_set_xdp_tx_queue(struct efx_nic *efx, int xdp_queue_number, - struct efx_tx_queue *tx_queue) -{ - if (xdp_queue_number >= efx->xdp_tx_queue_count) - return -EINVAL; - - netif_dbg(efx, drv, efx->net_dev, "Channel %u TXQ %u is XDP %u, HW %u\n", - tx_queue->channel->channel, tx_queue->label, - xdp_queue_number, tx_queue->queue); - efx->xdp_tx_queues[xdp_queue_number] = tx_queue; - return 0; -} - int efx_set_channels(struct efx_nic *efx) { - struct efx_tx_queue *tx_queue; struct efx_channel *channel; - unsigned int next_queue = 0; - int xdp_queue_number; int rc; efx->tx_channel_offset = @@ -926,61 +994,14 @@ int efx_set_channels(struct efx_nic *efx) return -ENOMEM; } - /* We need to mark which channels really have RX and TX - * queues, and adjust the TX queue numbers if we have separate - * RX-only and TX-only channels. - */ - xdp_queue_number = 0; efx_for_each_channel(channel, efx) { if (channel->channel < efx->n_rx_channels) channel->rx_queue.core_index = channel->channel; else channel->rx_queue.core_index = -1; - - if (channel->channel >= efx->tx_channel_offset) { - if (efx_channel_is_xdp_tx(channel)) { - efx_for_each_channel_tx_queue(tx_queue, channel) { - tx_queue->queue = next_queue++; - rc = efx_set_xdp_tx_queue(efx, xdp_queue_number, tx_queue); - if (rc == 0) - xdp_queue_number++; - } - } else { - efx_for_each_channel_tx_queue(tx_queue, channel) { - tx_queue->queue = next_queue++; - netif_dbg(efx, drv, efx->net_dev, "Channel %u TXQ %u is HW %u\n", - channel->channel, tx_queue->label, - tx_queue->queue); - } - - /* If XDP is borrowing queues from net stack, it must use the queue - * with no csum offload, which is the first one of the channel - * (note: channel->tx_queue_by_type is not initialized yet) - */ - if (efx->xdp_txq_queues_mode == EFX_XDP_TX_QUEUES_BORROWED) { - tx_queue = &channel->tx_queue[0]; - rc = efx_set_xdp_tx_queue(efx, xdp_queue_number, tx_queue); - if (rc == 0) - xdp_queue_number++; - } - } - } } - WARN_ON(efx->xdp_txq_queues_mode == EFX_XDP_TX_QUEUES_DEDICATED && - xdp_queue_number != efx->xdp_tx_queue_count); - WARN_ON(efx->xdp_txq_queues_mode != EFX_XDP_TX_QUEUES_DEDICATED && - xdp_queue_number > efx->xdp_tx_queue_count); - /* If we have more CPUs than assigned XDP TX queues, assign the already - * existing queues to the exceeding CPUs - */ - next_queue = 0; - while (xdp_queue_number < efx->xdp_tx_queue_count) { - tx_queue = efx->xdp_tx_queues[next_queue++]; - rc = efx_set_xdp_tx_queue(efx, xdp_queue_number, tx_queue); - if (rc == 0) - xdp_queue_number++; - } + efx_set_xdp_channels(efx); rc = netif_set_real_num_tx_queues(efx->net_dev, efx->n_tx_channels); if (rc) @@ -1124,7 +1145,7 @@ void efx_start_channels(struct efx_nic *efx) struct efx_rx_queue *rx_queue; struct efx_channel *channel; - efx_for_each_channel(channel, efx) { + efx_for_each_channel_rev(channel, efx) { efx_for_each_channel_tx_queue(tx_queue, channel) { efx_init_tx_queue(tx_queue); atomic_inc(&efx->active_queues); diff --git a/drivers/net/ethernet/sfc/ptp.c b/drivers/net/ethernet/sfc/ptp.c index f0ef515e2ade..4625f85acab2 100644 --- a/drivers/net/ethernet/sfc/ptp.c +++ b/drivers/net/ethernet/sfc/ptp.c @@ -45,6 +45,7 @@ #include "farch_regs.h" #include "tx.h" #include "nic.h" /* indirectly includes ptp.h */ +#include "efx_channels.h" /* Maximum number of events expected to make up a PTP event */ #define MAX_EVENT_FRAGS 3 @@ -541,6 +542,12 @@ struct efx_channel *efx_ptp_channel(struct efx_nic *efx) return efx->ptp_data ? efx->ptp_data->channel : NULL; } +void efx_ptp_update_channel(struct efx_nic *efx, struct efx_channel *channel) +{ + if (efx->ptp_data) + efx->ptp_data->channel = channel; +} + static u32 last_sync_timestamp_major(struct efx_nic *efx) { struct efx_channel *channel = efx_ptp_channel(efx); @@ -1443,6 +1450,11 @@ int efx_ptp_probe(struct efx_nic *efx, struct efx_channel *channel) int rc = 0; unsigned int pos; + if (efx->ptp_data) { + efx->ptp_data->channel = channel; + return 0; + } + ptp = kzalloc(sizeof(struct efx_ptp_data), GFP_KERNEL); efx->ptp_data = ptp; if (!efx->ptp_data) @@ -2176,7 +2188,7 @@ static const struct efx_channel_type efx_ptp_channel_type = { .pre_probe = efx_ptp_probe_channel, .post_remove = efx_ptp_remove_channel, .get_name = efx_ptp_get_channel_name, - /* no copy operation; there is no need to reallocate this channel */ + .copy = efx_copy_channel, .receive_skb = efx_ptp_rx, .want_txqs = efx_ptp_want_txqs, .keep_eventq = false, diff --git a/drivers/net/ethernet/sfc/ptp.h b/drivers/net/ethernet/sfc/ptp.h index 9855e8c9e544..7b1ef7002b3f 100644 --- a/drivers/net/ethernet/sfc/ptp.h +++ b/drivers/net/ethernet/sfc/ptp.h @@ -16,6 +16,7 @@ struct ethtool_ts_info; int efx_ptp_probe(struct efx_nic *efx, struct efx_channel *channel); void efx_ptp_defer_probe_with_channel(struct efx_nic *efx); struct efx_channel *efx_ptp_channel(struct efx_nic *efx); +void efx_ptp_update_channel(struct efx_nic *efx, struct efx_channel *channel); void efx_ptp_remove(struct efx_nic *efx); int efx_ptp_set_ts_config(struct efx_nic *efx, struct ifreq *ifr); int efx_ptp_get_ts_config(struct efx_nic *efx, struct ifreq *ifr); diff --git a/drivers/net/ethernet/sfc/rx_common.c b/drivers/net/ethernet/sfc/rx_common.c index 1b22c7be0088..fa8b9aacca11 100644 --- a/drivers/net/ethernet/sfc/rx_common.c +++ b/drivers/net/ethernet/sfc/rx_common.c @@ -150,6 +150,9 @@ static void efx_fini_rx_recycle_ring(struct efx_rx_queue *rx_queue) struct efx_nic *efx = rx_queue->efx; int i; + if (unlikely(!rx_queue->page_ring)) + return; + /* Unmap and release the pages in the recycle ring. Remove the ring. */ for (i = 0; i <= rx_queue->page_ptr_mask; i++) { struct page *page = rx_queue->page_ring[i]; diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c index d16e031e95f4..6983799e1c05 100644 --- a/drivers/net/ethernet/sfc/tx.c +++ b/drivers/net/ethernet/sfc/tx.c @@ -443,6 +443,9 @@ int efx_xdp_tx_buffers(struct efx_nic *efx, int n, struct xdp_frame **xdpfs, if (unlikely(!tx_queue)) return -EINVAL; + if (!tx_queue->initialised) + return -EINVAL; + if (efx->xdp_txq_queues_mode != EFX_XDP_TX_QUEUES_DEDICATED) HARD_TX_LOCK(efx->net_dev, tx_queue->core_txq, cpu); diff --git a/drivers/net/ethernet/sfc/tx_common.c b/drivers/net/ethernet/sfc/tx_common.c index d530cde2b864..9bc8281b7f5b 100644 --- a/drivers/net/ethernet/sfc/tx_common.c +++ b/drivers/net/ethernet/sfc/tx_common.c @@ -101,6 +101,8 @@ void efx_fini_tx_queue(struct efx_tx_queue *tx_queue) netif_dbg(tx_queue->efx, drv, tx_queue->efx->net_dev, "shutting down TX queue %d\n", tx_queue->queue); + tx_queue->initialised = false; + if (!tx_queue->buffer) return; diff --git a/drivers/net/ethernet/smsc/smsc911x.c b/drivers/net/ethernet/smsc/smsc911x.c index 7a50ba00f8ae..c854efdf1f25 100644 --- a/drivers/net/ethernet/smsc/smsc911x.c +++ b/drivers/net/ethernet/smsc/smsc911x.c @@ -2431,7 +2431,7 @@ static int smsc911x_drv_probe(struct platform_device *pdev) if (irq == -EPROBE_DEFER) { retval = -EPROBE_DEFER; goto out_0; - } else if (irq <= 0) { + } else if (irq < 0) { pr_warn("Could not allocate irq resource\n"); retval = -ENODEV; goto out_0; diff --git a/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.c b/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.c index cd478d2cd871..00f6d347eaf7 100644 --- a/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.c +++ b/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.c @@ -57,10 +57,6 @@ #define TSE_PCS_USE_SGMII_ENA BIT(0) #define TSE_PCS_IF_USE_SGMII 0x03 -#define SGMII_ADAPTER_CTRL_REG 0x00 -#define SGMII_ADAPTER_DISABLE 0x0001 -#define SGMII_ADAPTER_ENABLE 0x0000 - #define AUTONEGO_LINK_TIMER 20 static int tse_pcs_reset(void __iomem *base, struct tse_pcs *pcs) @@ -202,12 +198,8 @@ void tse_pcs_fix_mac_speed(struct tse_pcs *pcs, struct phy_device *phy_dev, unsigned int speed) { void __iomem *tse_pcs_base = pcs->tse_pcs_base; - void __iomem *sgmii_adapter_base = pcs->sgmii_adapter_base; u32 val; - writew(SGMII_ADAPTER_ENABLE, - sgmii_adapter_base + SGMII_ADAPTER_CTRL_REG); - pcs->autoneg = phy_dev->autoneg; if (phy_dev->autoneg == AUTONEG_ENABLE) { diff --git a/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.h b/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.h index 442812c0a4bd..694ac25ef426 100644 --- a/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.h +++ b/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.h @@ -10,6 +10,10 @@ #include <linux/phy.h> #include <linux/timer.h> +#define SGMII_ADAPTER_CTRL_REG 0x00 +#define SGMII_ADAPTER_ENABLE 0x0000 +#define SGMII_ADAPTER_DISABLE 0x0001 + struct tse_pcs { struct device *dev; void __iomem *tse_pcs_base; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c index 63754a9c4ba7..0b0be0898ac5 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c @@ -454,6 +454,7 @@ static int intel_mgbe_common_data(struct pci_dev *pdev, plat->has_gmac4 = 1; plat->force_sf_dma_mode = 0; plat->tso_en = 1; + plat->sph_disable = 1; /* Multiplying factor to the clk_eee_i clock time * period to make it closer to 100 ns. This value diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c index ecf759ee1c9f..017dbbda0c1c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c @@ -205,7 +205,7 @@ static const struct pci_device_id loongson_dwmac_id_table[] = { }; MODULE_DEVICE_TABLE(pci, loongson_dwmac_id_table); -struct pci_driver loongson_dwmac_driver = { +static struct pci_driver loongson_dwmac_driver = { .name = "dwmac-loongson-pci", .id_table = loongson_dwmac_id_table, .probe = loongson_dwmac_probe, diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c index b7c2579c963b..6b447d8f0bd8 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c @@ -18,9 +18,6 @@ #include "altr_tse_pcs.h" -#define SGMII_ADAPTER_CTRL_REG 0x00 -#define SGMII_ADAPTER_DISABLE 0x0001 - #define SYSMGR_EMACGRP_CTRL_PHYSEL_ENUM_GMII_MII 0x0 #define SYSMGR_EMACGRP_CTRL_PHYSEL_ENUM_RGMII 0x1 #define SYSMGR_EMACGRP_CTRL_PHYSEL_ENUM_RMII 0x2 @@ -62,14 +59,13 @@ static void socfpga_dwmac_fix_mac_speed(void *priv, unsigned int speed) { struct socfpga_dwmac *dwmac = (struct socfpga_dwmac *)priv; void __iomem *splitter_base = dwmac->splitter_base; - void __iomem *tse_pcs_base = dwmac->pcs.tse_pcs_base; void __iomem *sgmii_adapter_base = dwmac->pcs.sgmii_adapter_base; struct device *dev = dwmac->dev; struct net_device *ndev = dev_get_drvdata(dev); struct phy_device *phy_dev = ndev->phydev; u32 val; - if ((tse_pcs_base) && (sgmii_adapter_base)) + if (sgmii_adapter_base) writew(SGMII_ADAPTER_DISABLE, sgmii_adapter_base + SGMII_ADAPTER_CTRL_REG); @@ -93,8 +89,11 @@ static void socfpga_dwmac_fix_mac_speed(void *priv, unsigned int speed) writel(val, splitter_base + EMAC_SPLITTER_CTRL_REG); } - if (tse_pcs_base && sgmii_adapter_base) + if (phy_dev && sgmii_adapter_base) { + writew(SGMII_ADAPTER_ENABLE, + sgmii_adapter_base + SGMII_ADAPTER_CTRL_REG); tse_pcs_fix_mac_speed(&dwmac->pcs, phy_dev, speed); + } } static int socfpga_dwmac_parse_data(struct socfpga_dwmac *dwmac, struct device *dev) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c index f86cc83003f2..f834472599f7 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c @@ -907,6 +907,7 @@ static int sun8i_dwmac_register_mdio_mux(struct stmmac_priv *priv) ret = mdio_mux_init(priv->device, mdio_mux, mdio_mux_syscon_switch_fn, &gmac->mux_handle, priv, priv->mii); + of_node_put(mdio_mux); return ret; } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c index 22fea0f67245..92d32940aff0 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c @@ -71,9 +71,9 @@ static int init_systime(void __iomem *ioaddr, u32 sec, u32 nsec) writel(value, ioaddr + PTP_TCR); /* wait for present system time initialize to complete */ - return readl_poll_timeout(ioaddr + PTP_TCR, value, + return readl_poll_timeout_atomic(ioaddr + PTP_TCR, value, !(value & PTP_TCR_TSINIT), - 10000, 100000); + 10, 100000); } static int config_addend(void __iomem *ioaddr, u32 addend) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 4a4b3651ab3e..2525a80353b7 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -7021,7 +7021,7 @@ int stmmac_dvr_probe(struct device *device, dev_info(priv->device, "TSO feature enabled\n"); } - if (priv->dma_cap.sphen) { + if (priv->dma_cap.sphen && !priv->plat->sph_disable) { ndev->hw_features |= NETIF_F_GRO; priv->sph_cap = true; priv->sph = priv->sph_cap; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c index fcf17d8a0494..644bb54f5f02 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c @@ -181,7 +181,7 @@ static int stmmac_pci_probe(struct pci_dev *pdev, return -ENOMEM; /* Enable pci device */ - ret = pci_enable_device(pdev); + ret = pcim_enable_device(pdev); if (ret) { dev_err(&pdev->dev, "%s: ERROR: failed to enable device\n", __func__); @@ -241,8 +241,6 @@ static void stmmac_pci_remove(struct pci_dev *pdev) pcim_iounmap_regions(pdev, BIT(i)); break; } - - pci_disable_device(pdev); } static int __maybe_unused stmmac_pci_suspend(struct device *dev) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 5d29f336315b..11e1055e8260 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -431,8 +431,7 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac) plat->phylink_node = np; /* Get max speed of operation from device tree */ - if (of_property_read_u32(np, "max-speed", &plat->max_speed)) - plat->max_speed = -1; + of_property_read_u32(np, "max-speed", &plat->max_speed); plat->bus_id = of_alias_get_id(np, "ethernet"); if (plat->bus_id < 0) diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c index 42460c0885fc..df70df29deea 100644 --- a/drivers/net/ethernet/sun/niu.c +++ b/drivers/net/ethernet/sun/niu.c @@ -35,6 +35,25 @@ #include "niu.h" +/* This driver wants to store a link to a "next page" within the + * page struct itself by overloading the content of the "mapping" + * member. This is not expected by the page API, but does currently + * work. However, the randstruct plugin gets very bothered by this + * case because "mapping" (struct address_space) is randomized, so + * casts to/from it trigger warnings. Hide this by way of a union, + * to create a typed alias of "mapping", since that's how it is + * actually being used here. + */ +union niu_page { + struct page page; + struct { + unsigned long __flags; /* unused alias of "flags" */ + struct list_head __lru; /* unused alias of "lru" */ + struct page *next; /* alias of "mapping" */ + }; +}; +#define niu_next_page(p) container_of(p, union niu_page, page)->next + #define DRV_MODULE_NAME "niu" #define DRV_MODULE_VERSION "1.1" #define DRV_MODULE_RELDATE "Apr 22, 2010" @@ -3283,7 +3302,7 @@ static struct page *niu_find_rxpage(struct rx_ring_info *rp, u64 addr, addr &= PAGE_MASK; pp = &rp->rxhash[h]; - for (; (p = *pp) != NULL; pp = (struct page **) &p->mapping) { + for (; (p = *pp) != NULL; pp = &niu_next_page(p)) { if (p->index == addr) { *link = pp; goto found; @@ -3300,7 +3319,7 @@ static void niu_hash_page(struct rx_ring_info *rp, struct page *page, u64 base) unsigned int h = niu_hash_rxaddr(rp, base); page->index = base; - page->mapping = (struct address_space *) rp->rxhash[h]; + niu_next_page(page) = rp->rxhash[h]; rp->rxhash[h] = page; } @@ -3382,11 +3401,11 @@ static int niu_rx_pkt_ignore(struct niu *np, struct rx_ring_info *rp) rcr_size = rp->rbr_sizes[(val & RCR_ENTRY_PKTBUFSZ) >> RCR_ENTRY_PKTBUFSZ_SHIFT]; if ((page->index + PAGE_SIZE) - rcr_size == addr) { - *link = (struct page *) page->mapping; + *link = niu_next_page(page); np->ops->unmap_page(np->device, page->index, PAGE_SIZE, DMA_FROM_DEVICE); page->index = 0; - page->mapping = NULL; + niu_next_page(page) = NULL; __free_page(page); rp->rbr_refill_pending++; } @@ -3451,11 +3470,11 @@ static int niu_process_rx_pkt(struct napi_struct *napi, struct niu *np, niu_rx_skb_append(skb, page, off, append_size, rcr_size); if ((page->index + rp->rbr_block_size) - rcr_size == addr) { - *link = (struct page *) page->mapping; + *link = niu_next_page(page); np->ops->unmap_page(np->device, page->index, PAGE_SIZE, DMA_FROM_DEVICE); page->index = 0; - page->mapping = NULL; + niu_next_page(page) = NULL; rp->rbr_refill_pending++; } else get_page(page); @@ -3518,13 +3537,13 @@ static void niu_rbr_free(struct niu *np, struct rx_ring_info *rp) page = rp->rxhash[i]; while (page) { - struct page *next = (struct page *) page->mapping; + struct page *next = niu_next_page(page); u64 base = page->index; np->ops->unmap_page(np->device, base, PAGE_SIZE, DMA_FROM_DEVICE); page->index = 0; - page->mapping = NULL; + niu_next_page(page) = NULL; __free_page(page); @@ -6440,8 +6459,7 @@ static void niu_reset_buffers(struct niu *np) page = rp->rxhash[j]; while (page) { - struct page *next = - (struct page *) page->mapping; + struct page *next = niu_next_page(page); u64 base = page->index; base = base >> RBR_DESCR_ADDR_SHIFT; rp->rbr[k++] = cpu_to_le32(base); @@ -10176,6 +10194,9 @@ static int __init niu_init(void) BUILD_BUG_ON(PAGE_SIZE < 4 * 1024); + BUILD_BUG_ON(offsetof(struct page, mapping) != + offsetof(union niu_page, next)); + niu_debug = netif_msg_init(debug, NIU_MSG_DEFAULT); #ifdef CONFIG_SPARC64 diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c index bd4b1528cf99..79e850fe4621 100644 --- a/drivers/net/ethernet/ti/cpsw_new.c +++ b/drivers/net/ethernet/ti/cpsw_new.c @@ -1246,8 +1246,10 @@ static int cpsw_probe_dt(struct cpsw_common *cpsw) data->slave_data = devm_kcalloc(dev, CPSW_SLAVE_PORTS_NUM, sizeof(struct cpsw_slave_data), GFP_KERNEL); - if (!data->slave_data) + if (!data->slave_data) { + of_node_put(tmp_node); return -ENOMEM; + } /* Populate all the child nodes here... */ @@ -1341,6 +1343,7 @@ static int cpsw_probe_dt(struct cpsw_common *cpsw) err_node_put: of_node_put(port_np); + of_node_put(tmp_node); return ret; } diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet.h b/drivers/net/ethernet/xilinx/xilinx_axienet.h index 0f9c88dd1a4a..d5c1e5c4a508 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet.h +++ b/drivers/net/ethernet/xilinx/xilinx_axienet.h @@ -433,8 +433,6 @@ struct axienet_local { struct net_device *ndev; struct device *dev; - struct device_node *phy_node; - struct phylink *phylink; struct phylink_config phylink_config; diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index c7eb05e4a6bf..d6fc3f7acdf0 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -2064,25 +2064,33 @@ static int axienet_probe(struct platform_device *pdev) if (ret) goto cleanup_clk; - lp->phy_node = of_parse_phandle(pdev->dev.of_node, "phy-handle", 0); - if (lp->phy_node) { - ret = axienet_mdio_setup(lp); - if (ret) - dev_warn(&pdev->dev, - "error registering MDIO bus: %d\n", ret); - } + ret = axienet_mdio_setup(lp); + if (ret) + dev_warn(&pdev->dev, + "error registering MDIO bus: %d\n", ret); + if (lp->phy_mode == PHY_INTERFACE_MODE_SGMII || lp->phy_mode == PHY_INTERFACE_MODE_1000BASEX) { - if (!lp->phy_node) { - dev_err(&pdev->dev, "phy-handle required for 1000BaseX/SGMII\n"); + np = of_parse_phandle(pdev->dev.of_node, "pcs-handle", 0); + if (!np) { + /* Deprecated: Always use "pcs-handle" for pcs_phy. + * Falling back to "phy-handle" here is only for + * backward compatibility with old device trees. + */ + np = of_parse_phandle(pdev->dev.of_node, "phy-handle", 0); + } + if (!np) { + dev_err(&pdev->dev, "pcs-handle (preferred) or phy-handle required for 1000BaseX/SGMII\n"); ret = -EINVAL; goto cleanup_mdio; } - lp->pcs_phy = of_mdio_find_device(lp->phy_node); + lp->pcs_phy = of_mdio_find_device(np); if (!lp->pcs_phy) { ret = -EPROBE_DEFER; + of_node_put(np); goto cleanup_mdio; } + of_node_put(np); lp->pcs.ops = &axienet_pcs_ops; lp->pcs.poll = true; } @@ -2125,8 +2133,6 @@ cleanup_mdio: put_device(&lp->pcs_phy->dev); if (lp->mii_bus) axienet_mdio_teardown(lp); - of_node_put(lp->phy_node); - cleanup_clk: clk_bulk_disable_unprepare(XAE_NUM_MISC_CLOCKS, lp->misc_clks); clk_disable_unprepare(lp->axi_clk); @@ -2155,9 +2161,6 @@ static int axienet_remove(struct platform_device *pdev) clk_bulk_disable_unprepare(XAE_NUM_MISC_CLOCKS, lp->misc_clks); clk_disable_unprepare(lp->axi_clk); - of_node_put(lp->phy_node); - lp->phy_node = NULL; - free_netdev(ndev); return 0; diff --git a/drivers/net/ethernet/xilinx/xilinx_emaclite.c b/drivers/net/ethernet/xilinx/xilinx_emaclite.c index 57a24f62e353..d770b3ac3f74 100644 --- a/drivers/net/ethernet/xilinx/xilinx_emaclite.c +++ b/drivers/net/ethernet/xilinx/xilinx_emaclite.c @@ -823,10 +823,10 @@ static int xemaclite_mdio_write(struct mii_bus *bus, int phy_id, int reg, static int xemaclite_mdio_setup(struct net_local *lp, struct device *dev) { struct mii_bus *bus; - int rc; struct resource res; struct device_node *np = of_get_parent(lp->phy_node); struct device_node *npp; + int rc, ret; /* Don't register the MDIO bus if the phy_node or its parent node * can't be found. @@ -836,8 +836,14 @@ static int xemaclite_mdio_setup(struct net_local *lp, struct device *dev) return -ENODEV; } npp = of_get_parent(np); - - of_address_to_resource(npp, 0, &res); + ret = of_address_to_resource(npp, 0, &res); + of_node_put(npp); + if (ret) { + dev_err(dev, "%s resource error!\n", + dev->of_node->full_name); + of_node_put(np); + return ret; + } if (lp->ndev->mem_start != res.start) { struct phy_device *phydev; phydev = of_phy_find_device(lp->phy_node); @@ -846,6 +852,7 @@ static int xemaclite_mdio_setup(struct net_local *lp, struct device *dev) "MDIO of the phy is not registered yet\n"); else put_device(&phydev->mdio.dev); + of_node_put(np); return 0; } @@ -858,6 +865,7 @@ static int xemaclite_mdio_setup(struct net_local *lp, struct device *dev) bus = mdiobus_alloc(); if (!bus) { dev_err(dev, "Failed to allocate mdiobus\n"); + of_node_put(np); return -ENOMEM; } @@ -870,6 +878,7 @@ static int xemaclite_mdio_setup(struct net_local *lp, struct device *dev) bus->parent = dev; rc = of_mdiobus_register(bus, np); + of_node_put(np); if (rc) { dev_err(dev, "Failed to register mdio bus.\n"); goto err_register; @@ -926,8 +935,6 @@ static int xemaclite_open(struct net_device *dev) xemaclite_disable_interrupts(lp); if (lp->phy_node) { - u32 bmcr; - lp->phy_dev = of_phy_connect(lp->ndev, lp->phy_node, xemaclite_adjust_link, 0, PHY_INTERFACE_MODE_MII); @@ -938,19 +945,6 @@ static int xemaclite_open(struct net_device *dev) /* EmacLite doesn't support giga-bit speeds */ phy_set_max_speed(lp->phy_dev, SPEED_100); - - /* Don't advertise 1000BASE-T Full/Half duplex speeds */ - phy_write(lp->phy_dev, MII_CTRL1000, 0); - - /* Advertise only 10 and 100mbps full/half duplex speeds */ - phy_write(lp->phy_dev, MII_ADVERTISE, ADVERTISE_ALL | - ADVERTISE_CSMA); - - /* Restart auto negotiation */ - bmcr = phy_read(lp->phy_dev, MII_BMCR); - bmcr |= (BMCR_ANENABLE | BMCR_ANRESTART); - phy_write(lp->phy_dev, MII_BMCR, bmcr); - phy_start(lp->phy_dev); } diff --git a/drivers/net/hippi/rrunner.c b/drivers/net/hippi/rrunner.c index 16105292b140..74e845fa2e07 100644 --- a/drivers/net/hippi/rrunner.c +++ b/drivers/net/hippi/rrunner.c @@ -1355,7 +1355,9 @@ static int rr_close(struct net_device *dev) rrpriv->fw_running = 0; + spin_unlock_irqrestore(&rrpriv->lock, flags); del_timer_sync(&rrpriv->timer); + spin_lock_irqsave(&rrpriv->lock, flags); writel(0, ®s->TxPi); writel(0, ®s->IpRxPi); diff --git a/drivers/net/ipa/gsi.c b/drivers/net/ipa/gsi.c index bc981043cc80..a701178a1d13 100644 --- a/drivers/net/ipa/gsi.c +++ b/drivers/net/ipa/gsi.c @@ -1367,9 +1367,10 @@ static void gsi_evt_ring_rx_update(struct gsi_evt_ring *evt_ring, u32 index) struct gsi_event *event_done; struct gsi_event *event; struct gsi_trans *trans; + u32 trans_count = 0; u32 byte_count = 0; - u32 old_index; u32 event_avail; + u32 old_index; trans_info = &channel->trans_info; @@ -1390,6 +1391,7 @@ static void gsi_evt_ring_rx_update(struct gsi_evt_ring *evt_ring, u32 index) do { trans->len = __le16_to_cpu(event->len); byte_count += trans->len; + trans_count++; /* Move on to the next event and transaction */ if (--event_avail) @@ -1401,7 +1403,7 @@ static void gsi_evt_ring_rx_update(struct gsi_evt_ring *evt_ring, u32 index) /* We record RX bytes when they are received */ channel->byte_count += byte_count; - channel->trans_count++; + channel->trans_count += trans_count; } /* Initialize a ring, including allocating DMA memory for its entries */ diff --git a/drivers/net/ipa/ipa_endpoint.c b/drivers/net/ipa/ipa_endpoint.c index 888e94278a84..cea7b2e2ce96 100644 --- a/drivers/net/ipa/ipa_endpoint.c +++ b/drivers/net/ipa/ipa_endpoint.c @@ -1150,13 +1150,12 @@ static void ipa_endpoint_skb_copy(struct ipa_endpoint *endpoint, return; skb = __dev_alloc_skb(len, GFP_ATOMIC); - if (!skb) - return; - - /* Copy the data into the socket buffer and receive it */ - skb_put(skb, len); - memcpy(skb->data, data, len); - skb->truesize += extra; + if (skb) { + /* Copy the data into the socket buffer and receive it */ + skb_put(skb, len); + memcpy(skb->data, data, len); + skb->truesize += extra; + } ipa_modem_skb_rx(endpoint->netdev, skb); } diff --git a/drivers/net/ipa/ipa_qmi.c b/drivers/net/ipa/ipa_qmi.c index 90f3aec55b36..ec010cf2e816 100644 --- a/drivers/net/ipa/ipa_qmi.c +++ b/drivers/net/ipa/ipa_qmi.c @@ -125,7 +125,7 @@ static void ipa_qmi_indication(struct ipa_qmi *ipa_qmi) */ static void ipa_qmi_ready(struct ipa_qmi *ipa_qmi) { - struct ipa *ipa = container_of(ipa_qmi, struct ipa, qmi); + struct ipa *ipa; int ret; /* We aren't ready until the modem and microcontroller are */ diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 069e8824c264..b00bc8173abe 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -460,8 +460,10 @@ static rx_handler_result_t macvlan_handle_frame(struct sk_buff **pskb) return RX_HANDLER_CONSUMED; *pskb = skb; eth = eth_hdr(skb); - if (macvlan_forward_source(skb, port, eth->h_source)) + if (macvlan_forward_source(skb, port, eth->h_source)) { + kfree_skb(skb); return RX_HANDLER_CONSUMED; + } src = macvlan_hash_lookup(port, eth->h_source); if (src && src->mode != MACVLAN_MODE_VEPA && src->mode != MACVLAN_MODE_BRIDGE) { @@ -480,8 +482,10 @@ static rx_handler_result_t macvlan_handle_frame(struct sk_buff **pskb) return RX_HANDLER_PASS; } - if (macvlan_forward_source(skb, port, eth->h_source)) + if (macvlan_forward_source(skb, port, eth->h_source)) { + kfree_skb(skb); return RX_HANDLER_CONSUMED; + } if (macvlan_passthru(port)) vlan = list_first_or_null_rcu(&port->vlans, struct macvlan_dev, list); diff --git a/drivers/net/mctp/mctp-i2c.c b/drivers/net/mctp/mctp-i2c.c index baf7afac7857..53846c6b56ca 100644 --- a/drivers/net/mctp/mctp-i2c.c +++ b/drivers/net/mctp/mctp-i2c.c @@ -553,7 +553,7 @@ static int mctp_i2c_header_create(struct sk_buff *skb, struct net_device *dev, hdr->source_slave = ((llsrc << 1) & 0xff) | 0x01; mhdr->ver = 0x01; - return 0; + return sizeof(struct mctp_i2c_hdr); } static int mctp_i2c_tx_thread(void *data) diff --git a/drivers/net/mdio/fwnode_mdio.c b/drivers/net/mdio/fwnode_mdio.c index 1becb1a731f6..1c1584fca632 100644 --- a/drivers/net/mdio/fwnode_mdio.c +++ b/drivers/net/mdio/fwnode_mdio.c @@ -43,6 +43,11 @@ int fwnode_mdiobus_phy_device_register(struct mii_bus *mdio, int rc; rc = fwnode_irq_get(child, 0); + /* Don't wait forever if the IRQ provider doesn't become available, + * just fall back to poll mode + */ + if (rc == -EPROBE_DEFER) + rc = driver_deferred_probe_check_state(&phy->mdio.dev); if (rc == -EPROBE_DEFER) return rc; diff --git a/drivers/net/mdio/mdio-mscc-miim.c b/drivers/net/mdio/mdio-mscc-miim.c index c483ba67c21f..582969751b4c 100644 --- a/drivers/net/mdio/mdio-mscc-miim.c +++ b/drivers/net/mdio/mdio-mscc-miim.c @@ -102,6 +102,9 @@ static int mscc_miim_read(struct mii_bus *bus, int mii_id, int regnum) u32 val; int ret; + if (regnum & MII_ADDR_C45) + return -EOPNOTSUPP; + ret = mscc_miim_wait_pending(bus); if (ret) goto out; @@ -145,6 +148,9 @@ static int mscc_miim_write(struct mii_bus *bus, int mii_id, struct mscc_miim_dev *miim = bus->priv; int ret; + if (regnum & MII_ADDR_C45) + return -EOPNOTSUPP; + ret = mscc_miim_wait_pending(bus); if (ret < 0) goto out; diff --git a/drivers/net/mdio/mdio-mux-bcm6368.c b/drivers/net/mdio/mdio-mux-bcm6368.c index 6dcbf987d61b..8b444a8eb6b5 100644 --- a/drivers/net/mdio/mdio-mux-bcm6368.c +++ b/drivers/net/mdio/mdio-mux-bcm6368.c @@ -115,7 +115,7 @@ static int bcm6368_mdiomux_probe(struct platform_device *pdev) md->mii_bus = devm_mdiobus_alloc(&pdev->dev); if (!md->mii_bus) { dev_err(&pdev->dev, "mdiomux bus alloc failed\n"); - return ENOMEM; + return -ENOMEM; } bus = md->mii_bus; diff --git a/drivers/net/phy/marvell10g.c b/drivers/net/phy/marvell10g.c index b6fea119fe13..2b7d0720720b 100644 --- a/drivers/net/phy/marvell10g.c +++ b/drivers/net/phy/marvell10g.c @@ -880,7 +880,7 @@ static int mv3310_read_status_copper(struct phy_device *phydev) cssr1 = phy_read_mmd(phydev, MDIO_MMD_PCS, MV_PCS_CSSR1); if (cssr1 < 0) - return val; + return cssr1; /* If the link settings are not resolved, mark the link down */ if (!(cssr1 & MV_PCS_CSSR1_RESOLVED)) { diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 19b11e896460..cd9aa353b653 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -99,15 +99,6 @@ #define PTP_TIMESTAMP_EN_PDREQ_ BIT(2) #define PTP_TIMESTAMP_EN_PDRES_ BIT(3) -#define PTP_RX_LATENCY_1000 0x0224 -#define PTP_TX_LATENCY_1000 0x0225 - -#define PTP_RX_LATENCY_100 0x0222 -#define PTP_TX_LATENCY_100 0x0223 - -#define PTP_RX_LATENCY_10 0x0220 -#define PTP_TX_LATENCY_10 0x0221 - #define PTP_TX_PARSE_L2_ADDR_EN 0x0284 #define PTP_RX_PARSE_L2_ADDR_EN 0x0244 @@ -268,15 +259,6 @@ struct lan8814_ptp_rx_ts { u16 seq_id; }; -struct kszphy_latencies { - u16 rx_10; - u16 tx_10; - u16 rx_100; - u16 tx_100; - u16 rx_1000; - u16 tx_1000; -}; - struct kszphy_ptp_priv { struct mii_timestamper mii_ts; struct phy_device *phydev; @@ -296,7 +278,6 @@ struct kszphy_ptp_priv { struct kszphy_priv { struct kszphy_ptp_priv ptp_priv; - struct kszphy_latencies latencies; const struct kszphy_type *type; int led_mode; bool rmii_ref_clk_sel; @@ -304,14 +285,6 @@ struct kszphy_priv { u64 stats[ARRAY_SIZE(kszphy_hw_stats)]; }; -static struct kszphy_latencies lan8814_latencies = { - .rx_10 = 0x22AA, - .tx_10 = 0x2E4A, - .rx_100 = 0x092A, - .tx_100 = 0x02C1, - .rx_1000 = 0x01AD, - .tx_1000 = 0x00C9, -}; static const struct kszphy_type ksz8021_type = { .led_mode_reg = MII_KSZPHY_CTRL_2, .has_broadcast_disable = true, @@ -1770,7 +1743,7 @@ static int ksz886x_cable_test_get_status(struct phy_device *phydev, static int lanphy_read_page_reg(struct phy_device *phydev, int page, u32 addr) { - u32 data; + int data; phy_lock_mdio_bus(phydev); __phy_write(phydev, LAN_EXT_PAGE_ACCESS_CONTROL, page); @@ -2471,8 +2444,7 @@ static int lan8804_config_init(struct phy_device *phydev) static irqreturn_t lan8814_handle_interrupt(struct phy_device *phydev) { - u16 tsu_irq_status; - int irq_status; + int irq_status, tsu_irq_status; irq_status = phy_read(phydev, LAN8814_INTS); if (irq_status > 0 && (irq_status & LAN8814_INT_LINK)) @@ -2618,55 +2590,6 @@ static int lan8814_ptp_probe_once(struct phy_device *phydev) return 0; } -static int lan8814_read_status(struct phy_device *phydev) -{ - struct kszphy_priv *priv = phydev->priv; - struct kszphy_latencies *latencies = &priv->latencies; - int err; - int regval; - - err = genphy_read_status(phydev); - if (err) - return err; - - switch (phydev->speed) { - case SPEED_1000: - lanphy_write_page_reg(phydev, 5, PTP_RX_LATENCY_1000, - latencies->rx_1000); - lanphy_write_page_reg(phydev, 5, PTP_TX_LATENCY_1000, - latencies->tx_1000); - break; - case SPEED_100: - lanphy_write_page_reg(phydev, 5, PTP_RX_LATENCY_100, - latencies->rx_100); - lanphy_write_page_reg(phydev, 5, PTP_TX_LATENCY_100, - latencies->tx_100); - break; - case SPEED_10: - lanphy_write_page_reg(phydev, 5, PTP_RX_LATENCY_10, - latencies->rx_10); - lanphy_write_page_reg(phydev, 5, PTP_TX_LATENCY_10, - latencies->tx_10); - break; - default: - break; - } - - /* Make sure the PHY is not broken. Read idle error count, - * and reset the PHY if it is maxed out. - */ - regval = phy_read(phydev, MII_STAT1000); - if ((regval & 0xFF) == 0xFF) { - phy_init_hw(phydev); - phydev->link = 0; - if (phydev->drv->config_intr && phy_interrupt_is_valid(phydev)) - phydev->drv->config_intr(phydev); - return genphy_config_aneg(phydev); - } - - return 0; -} - static int lan8814_config_init(struct phy_device *phydev) { int val; @@ -2690,30 +2613,8 @@ static int lan8814_config_init(struct phy_device *phydev) return 0; } -static void lan8814_parse_latency(struct phy_device *phydev) -{ - const struct device_node *np = phydev->mdio.dev.of_node; - struct kszphy_priv *priv = phydev->priv; - struct kszphy_latencies *latency = &priv->latencies; - u32 val; - - if (!of_property_read_u32(np, "lan8814,latency_rx_10", &val)) - latency->rx_10 = val; - if (!of_property_read_u32(np, "lan8814,latency_tx_10", &val)) - latency->tx_10 = val; - if (!of_property_read_u32(np, "lan8814,latency_rx_100", &val)) - latency->rx_100 = val; - if (!of_property_read_u32(np, "lan8814,latency_tx_100", &val)) - latency->tx_100 = val; - if (!of_property_read_u32(np, "lan8814,latency_rx_1000", &val)) - latency->rx_1000 = val; - if (!of_property_read_u32(np, "lan8814,latency_tx_1000", &val)) - latency->tx_1000 = val; -} - static int lan8814_probe(struct phy_device *phydev) { - const struct device_node *np = phydev->mdio.dev.of_node; struct kszphy_priv *priv; u16 addr; int err; @@ -2724,13 +2625,10 @@ static int lan8814_probe(struct phy_device *phydev) priv->led_mode = -1; - priv->latencies = lan8814_latencies; - phydev->priv = priv; if (!IS_ENABLED(CONFIG_PTP_1588_CLOCK) || - !IS_ENABLED(CONFIG_NETWORK_PHY_TIMESTAMPING) || - of_property_read_bool(np, "lan8814,ignore-ts")) + !IS_ENABLED(CONFIG_NETWORK_PHY_TIMESTAMPING)) return 0; /* Strap-in value for PHY address, below register read gives starting @@ -2746,7 +2644,6 @@ static int lan8814_probe(struct phy_device *phydev) return err; } - lan8814_parse_latency(phydev); lan8814_ptp_init(phydev); return 0; @@ -2759,6 +2656,7 @@ static struct phy_driver ksphy_driver[] = { .name = "Micrel KS8737", /* PHY_BASIC_FEATURES */ .driver_data = &ks8737_type, + .probe = kszphy_probe, .config_init = kszphy_config_init, .config_intr = kszphy_config_intr, .handle_interrupt = kszphy_handle_interrupt, @@ -2884,8 +2782,8 @@ static struct phy_driver ksphy_driver[] = { .config_init = ksz8061_config_init, .config_intr = kszphy_config_intr, .handle_interrupt = kszphy_handle_interrupt, - .suspend = kszphy_suspend, - .resume = kszphy_resume, + .suspend = genphy_suspend, + .resume = genphy_resume, }, { .phy_id = PHY_ID_KSZ9021, .phy_id_mask = 0x000ffffe, @@ -2928,7 +2826,7 @@ static struct phy_driver ksphy_driver[] = { .config_init = lan8814_config_init, .probe = lan8814_probe, .soft_reset = genphy_soft_reset, - .read_status = lan8814_read_status, + .read_status = ksz9031_read_status, .get_sset_count = kszphy_get_sset_count, .get_strings = kszphy_get_strings, .get_stats = kszphy_get_stats, diff --git a/drivers/net/phy/microchip_t1.c b/drivers/net/phy/microchip_t1.c index 389df3f4293c..c2c0e361fd3d 100644 --- a/drivers/net/phy/microchip_t1.c +++ b/drivers/net/phy/microchip_t1.c @@ -706,7 +706,6 @@ static int lan87xx_read_status(struct phy_device *phydev) static int lan87xx_config_aneg(struct phy_device *phydev) { u16 ctl = 0; - int rc; switch (phydev->master_slave_set) { case MASTER_SLAVE_CFG_MASTER_FORCE: @@ -722,11 +721,7 @@ static int lan87xx_config_aneg(struct phy_device *phydev) return -EOPNOTSUPP; } - rc = phy_modify_changed(phydev, MII_CTRL1000, CTL1000_AS_MASTER, ctl); - if (rc == 1) - rc = genphy_soft_reset(phydev); - - return rc; + return phy_modify_changed(phydev, MII_CTRL1000, CTL1000_AS_MASTER, ctl); } static struct phy_driver microchip_t1_phy_driver[] = { @@ -748,6 +743,7 @@ static struct phy_driver microchip_t1_phy_driver[] = { { PHY_ID_MATCH_MODEL(PHY_ID_LAN937X), .name = "Microchip LAN937x T1", + .flags = PHY_POLL_CABLE_TEST, .features = PHY_BASIC_T1_FEATURES, .config_init = lan87xx_config_init, .suspend = genphy_suspend, diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index beb2b66da132..f122026c4682 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -970,8 +970,13 @@ static irqreturn_t phy_interrupt(int irq, void *phy_dat) { struct phy_device *phydev = phy_dat; struct phy_driver *drv = phydev->drv; + irqreturn_t ret; - return drv->handle_interrupt(phydev); + mutex_lock(&phydev->lock); + ret = drv->handle_interrupt(phydev); + mutex_unlock(&phydev->lock); + + return ret; } /** diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c index 4dfb79807823..9a5d5a10560f 100644 --- a/drivers/net/phy/sfp.c +++ b/drivers/net/phy/sfp.c @@ -250,6 +250,7 @@ struct sfp { struct sfp_eeprom_id id; unsigned int module_power_mW; unsigned int module_t_start_up; + bool tx_fault_ignore; #if IS_ENABLED(CONFIG_HWMON) struct sfp_diag diag; @@ -1956,6 +1957,12 @@ static int sfp_sm_mod_probe(struct sfp *sfp, bool report) else sfp->module_t_start_up = T_START_UP; + if (!memcmp(id.base.vendor_name, "HUAWEI ", 16) && + !memcmp(id.base.vendor_pn, "MA5671A ", 16)) + sfp->tx_fault_ignore = true; + else + sfp->tx_fault_ignore = false; + return 0; } @@ -2409,7 +2416,10 @@ static void sfp_check_state(struct sfp *sfp) mutex_lock(&sfp->st_mutex); state = sfp_get_state(sfp); changed = state ^ sfp->state; - changed &= SFP_F_PRESENT | SFP_F_LOS | SFP_F_TX_FAULT; + if (sfp->tx_fault_ignore) + changed &= SFP_F_PRESENT | SFP_F_LOS; + else + changed &= SFP_F_PRESENT | SFP_F_LOS | SFP_F_TX_FAULT; for (i = 0; i < GPIO_MAX; i++) if (changed & BIT(i)) diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c index 3619520340b7..e172743948ed 100644 --- a/drivers/net/ppp/pppoe.c +++ b/drivers/net/ppp/pppoe.c @@ -988,6 +988,7 @@ static int pppoe_fill_forward_path(struct net_device_path_ctx *ctx, path->encap.proto = htons(ETH_P_PPP_SES); path->encap.id = be16_to_cpu(po->num); memcpy(path->encap.h_dest, po->pppoe_pa.remote, ETH_ALEN); + memcpy(ctx->daddr, po->pppoe_pa.remote, ETH_ALEN); path->dev = ctx->dev; ctx->dev = dev; diff --git a/drivers/net/slip/slip.c b/drivers/net/slip/slip.c index 88396ff99f03..6865d32270e5 100644 --- a/drivers/net/slip/slip.c +++ b/drivers/net/slip/slip.c @@ -469,7 +469,7 @@ static void sl_tx_timeout(struct net_device *dev, unsigned int txqueue) spin_lock(&sl->lock); if (netif_queue_stopped(dev)) { - if (!netif_running(dev)) + if (!netif_running(dev) || !sl->tty) goto out; /* May be we must check transmitter timeout here ? diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 276a0e42ca8e..dbe4c0a4be2c 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1124,7 +1124,7 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev) /* NETIF_F_LLTX requires to do our own update of trans_start */ queue = netdev_get_tx_queue(dev, txq); - queue->trans_start = jiffies; + txq_trans_cond_update(queue); /* Notify and wake up reader process */ if (tfile->flags & TUN_FASYNC) diff --git a/drivers/net/usb/aqc111.c b/drivers/net/usb/aqc111.c index ea06d10e1c21..ca409d450a29 100644 --- a/drivers/net/usb/aqc111.c +++ b/drivers/net/usb/aqc111.c @@ -1102,10 +1102,15 @@ static int aqc111_rx_fixup(struct usbnet *dev, struct sk_buff *skb) if (start_of_descs != desc_offset) goto err; - /* self check desc_offset from header*/ - if (desc_offset >= skb_len) + /* self check desc_offset from header and make sure that the + * bounds of the metadata array are inside the SKB + */ + if (pkt_count * 2 + desc_offset >= skb_len) goto err; + /* Packets must not overlap the metadata array */ + skb_trim(skb, desc_offset); + if (pkt_count == 0) goto err; diff --git a/drivers/net/veth.c b/drivers/net/veth.c index 1b5714926d81..eb0121a64d6d 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -320,7 +320,7 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev) rcu_read_lock(); rcv = rcu_dereference(priv->peer); - if (unlikely(!rcv)) { + if (unlikely(!rcv) || !pskb_may_pull(skb, ETH_HLEN)) { kfree_skb(skb); goto drop; } diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 87838cbe38cf..cbba9d2e8f32 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -1005,6 +1005,24 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, * xdp.data_meta were adjusted */ len = xdp.data_end - xdp.data + vi->hdr_len + metasize; + + /* recalculate headroom if xdp.data or xdp_data_meta + * were adjusted, note that offset should always point + * to the start of the reserved bytes for virtio_net + * header which are followed by xdp.data, that means + * that offset is equal to the headroom (when buf is + * starting at the beginning of the page, otherwise + * there is a base offset inside the page) but it's used + * with a different starting point (buf start) than + * xdp.data (buf start + vnet hdr size). If xdp.data or + * data_meta were adjusted by the xdp prog then the + * headroom size has changed and so has the offset, we + * can use data_hard_start, which points at buf start + + * vnet hdr size, to calculate the new headroom and use + * it later to compute buf start in page_to_skb() + */ + headroom = xdp.data - xdp.data_hard_start - metasize; + /* We can only create skb based on xdp_page. */ if (unlikely(xdp_page != page)) { rcu_read_unlock(); @@ -1012,7 +1030,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, head_skb = page_to_skb(vi, rq, xdp_page, offset, len, PAGE_SIZE, false, metasize, - VIRTIO_XDP_HEADROOM); + headroom); return head_skb; } break; diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c index d9d90baac72a..93e8d119d45f 100644 --- a/drivers/net/vmxnet3/vmxnet3_drv.c +++ b/drivers/net/vmxnet3/vmxnet3_drv.c @@ -589,6 +589,7 @@ vmxnet3_rq_alloc_rx_buf(struct vmxnet3_rx_queue *rq, u32 ring_idx, if (dma_mapping_error(&adapter->pdev->dev, rbi->dma_addr)) { dev_kfree_skb_any(rbi->skb); + rbi->skb = NULL; rq->stats.rx_buf_alloc_failure++; break; } @@ -613,6 +614,7 @@ vmxnet3_rq_alloc_rx_buf(struct vmxnet3_rx_queue *rq, u32 ring_idx, if (dma_mapping_error(&adapter->pdev->dev, rbi->dma_addr)) { put_page(rbi->page); + rbi->page = NULL; rq->stats.rx_buf_alloc_failure++; break; } @@ -1666,6 +1668,10 @@ vmxnet3_rq_cleanup(struct vmxnet3_rx_queue *rq, u32 i, ring_idx; struct Vmxnet3_RxDesc *rxd; + /* ring has already been cleaned up */ + if (!rq->rx_ring[0].base) + return; + for (ring_idx = 0; ring_idx < 2; ring_idx++) { for (i = 0; i < rq->rx_ring[ring_idx].size; i++) { #ifdef __BIG_ENDIAN_BITFIELD diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 85e362461d71..cfc30ce4c6e1 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -1265,6 +1265,7 @@ static int vrf_prepare_mac_header(struct sk_buff *skb, eth = (struct ethhdr *)skb->data; skb_reset_mac_header(skb); + skb_reset_mac_len(skb); /* we set the ethernet destination and the source addresses to the * address of the VRF device. @@ -1294,9 +1295,9 @@ static int vrf_prepare_mac_header(struct sk_buff *skb, */ static int vrf_add_mac_header_if_unset(struct sk_buff *skb, struct net_device *vrf_dev, - u16 proto) + u16 proto, struct net_device *orig_dev) { - if (skb_mac_header_was_set(skb)) + if (skb_mac_header_was_set(skb) && dev_has_header(orig_dev)) return 0; return vrf_prepare_mac_header(skb, vrf_dev, proto); @@ -1402,6 +1403,8 @@ static struct sk_buff *vrf_ip6_rcv(struct net_device *vrf_dev, /* if packet is NDISC then keep the ingress interface */ if (!is_ndisc) { + struct net_device *orig_dev = skb->dev; + vrf_rx_stats(vrf_dev, skb->len); skb->dev = vrf_dev; skb->skb_iif = vrf_dev->ifindex; @@ -1410,7 +1413,8 @@ static struct sk_buff *vrf_ip6_rcv(struct net_device *vrf_dev, int err; err = vrf_add_mac_header_if_unset(skb, vrf_dev, - ETH_P_IPV6); + ETH_P_IPV6, + orig_dev); if (likely(!err)) { skb_push(skb, skb->mac_len); dev_queue_xmit_nit(skb, vrf_dev); @@ -1440,6 +1444,8 @@ static struct sk_buff *vrf_ip6_rcv(struct net_device *vrf_dev, static struct sk_buff *vrf_ip_rcv(struct net_device *vrf_dev, struct sk_buff *skb) { + struct net_device *orig_dev = skb->dev; + skb->dev = vrf_dev; skb->skb_iif = vrf_dev->ifindex; IPCB(skb)->flags |= IPSKB_L3SLAVE; @@ -1460,7 +1466,8 @@ static struct sk_buff *vrf_ip_rcv(struct net_device *vrf_dev, if (!list_empty(&vrf_dev->ptype_all)) { int err; - err = vrf_add_mac_header_if_unset(skb, vrf_dev, ETH_P_IP); + err = vrf_add_mac_header_if_unset(skb, vrf_dev, ETH_P_IP, + orig_dev); if (likely(!err)) { skb_push(skb, skb->mac_len); dev_queue_xmit_nit(skb, vrf_dev); diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c index de97ff98d36e..8a5e3a6d32d7 100644 --- a/drivers/net/vxlan/vxlan_core.c +++ b/drivers/net/vxlan/vxlan_core.c @@ -651,11 +651,11 @@ static int vxlan_fdb_append(struct vxlan_fdb *f, rd = kmalloc(sizeof(*rd), GFP_ATOMIC); if (rd == NULL) - return -ENOBUFS; + return -ENOMEM; if (dst_cache_init(&rd->dst_cache, GFP_ATOMIC)) { kfree(rd); - return -ENOBUFS; + return -ENOMEM; } rd->remote_ip = *ip; diff --git a/drivers/net/wan/cosa.c b/drivers/net/wan/cosa.c index 23d2954d9747..1e5672019922 100644 --- a/drivers/net/wan/cosa.c +++ b/drivers/net/wan/cosa.c @@ -349,7 +349,7 @@ static int __init cosa_init(void) } } else { cosa_major = register_chrdev(0, "cosa", &cosa_fops); - if (!cosa_major) { + if (cosa_major < 0) { pr_warn("unable to register chardev\n"); err = -EIO; goto out; diff --git a/drivers/net/wireguard/device.c b/drivers/net/wireguard/device.c index 0fad1331303c..aa9a7a5970fd 100644 --- a/drivers/net/wireguard/device.c +++ b/drivers/net/wireguard/device.c @@ -19,6 +19,7 @@ #include <linux/if_arp.h> #include <linux/icmp.h> #include <linux/suspend.h> +#include <net/dst_metadata.h> #include <net/icmp.h> #include <net/rtnetlink.h> #include <net/ip_tunnels.h> @@ -167,7 +168,7 @@ static netdev_tx_t wg_xmit(struct sk_buff *skb, struct net_device *dev) goto err_peer; } - mtu = skb_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu; + mtu = skb_valid_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu; __skb_queue_head_init(&packets); if (!skb_is_gso(skb)) { diff --git a/drivers/net/wireless/ath/ath10k/sdio.c b/drivers/net/wireless/ath/ath10k/sdio.c index 63e1c2d783c5..73693c66cef1 100644 --- a/drivers/net/wireless/ath/ath10k/sdio.c +++ b/drivers/net/wireless/ath/ath10k/sdio.c @@ -1633,7 +1633,7 @@ static void ath10k_sdio_hif_power_down(struct ath10k *ar) return; } - ret = mmc_hw_reset(ar_sdio->func->card->host); + ret = mmc_hw_reset(ar_sdio->func->card); if (ret) ath10k_warn(ar, "unable to reset sdio: %d\n", ret); diff --git a/drivers/net/wireless/ath/ath11k/core.c b/drivers/net/wireless/ath/ath11k/core.c index 71eb7d04c3bf..90a5df1fbdbd 100644 --- a/drivers/net/wireless/ath/ath11k/core.c +++ b/drivers/net/wireless/ath/ath11k/core.c @@ -1288,6 +1288,7 @@ static void ath11k_core_restart(struct work_struct *work) ieee80211_stop_queues(ar->hw); ath11k_mac_drain_tx(ar); + complete(&ar->completed_11d_scan); complete(&ar->scan.started); complete(&ar->scan.completed); complete(&ar->peer_assoc_done); diff --git a/drivers/net/wireless/ath/ath11k/core.h b/drivers/net/wireless/ath/ath11k/core.h index c0228e91a596..b8634eddf49a 100644 --- a/drivers/net/wireless/ath/ath11k/core.h +++ b/drivers/net/wireless/ath/ath11k/core.h @@ -38,6 +38,8 @@ extern unsigned int ath11k_frame_mode; +#define ATH11K_SCAN_TIMEOUT_HZ (20 * HZ) + #define ATH11K_MON_TIMER_INTERVAL 10 enum ath11k_supported_bw { @@ -189,6 +191,12 @@ enum ath11k_scan_state { ATH11K_SCAN_ABORTING, }; +enum ath11k_11d_state { + ATH11K_11D_IDLE, + ATH11K_11D_PREPARING, + ATH11K_11D_RUNNING, +}; + enum ath11k_dev_flags { ATH11K_CAC_RUNNING, ATH11K_FLAG_CORE_REGISTERED, @@ -607,9 +615,8 @@ struct ath11k { bool dfs_block_radar_events; struct ath11k_thermal thermal; u32 vdev_id_11d_scan; - struct completion finish_11d_scan; - struct completion finish_11d_ch_list; - bool pending_11d; + struct completion completed_11d_scan; + enum ath11k_11d_state state_11d; bool regdom_set_by_user; int hw_rate_code; u8 twt_enabled; diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c index d5b83f90d27a..58ff761393db 100644 --- a/drivers/net/wireless/ath/ath11k/mac.c +++ b/drivers/net/wireless/ath/ath11k/mac.c @@ -3136,6 +3136,20 @@ static void ath11k_mac_op_bss_info_changed(struct ieee80211_hw *hw, arvif->do_not_send_tmpl = true; else arvif->do_not_send_tmpl = false; + + if (vif->bss_conf.he_support) { + ret = ath11k_wmi_vdev_set_param_cmd(ar, arvif->vdev_id, + WMI_VDEV_PARAM_BA_MODE, + WMI_BA_MODE_BUFFER_SIZE_256); + if (ret) + ath11k_warn(ar->ab, + "failed to set BA BUFFER SIZE 256 for vdev: %d\n", + arvif->vdev_id); + else + ath11k_dbg(ar->ab, ATH11K_DBG_MAC, + "Set BA BUFFER SIZE 256 for VDEV: %d\n", + arvif->vdev_id); + } } if (changed & (BSS_CHANGED_BEACON_INFO | BSS_CHANGED_BEACON)) { @@ -3171,14 +3185,6 @@ static void ath11k_mac_op_bss_info_changed(struct ieee80211_hw *hw, if (arvif->is_up && vif->bss_conf.he_support && vif->bss_conf.he_oper.params) { - ret = ath11k_wmi_vdev_set_param_cmd(ar, arvif->vdev_id, - WMI_VDEV_PARAM_BA_MODE, - WMI_BA_MODE_BUFFER_SIZE_256); - if (ret) - ath11k_warn(ar->ab, - "failed to set BA BUFFER SIZE 256 for vdev: %d\n", - arvif->vdev_id); - param_id = WMI_VDEV_PARAM_HEOPS_0_31; param_value = vif->bss_conf.he_oper.params; ret = ath11k_wmi_vdev_set_param_cmd(ar, arvif->vdev_id, @@ -3595,26 +3601,6 @@ static int ath11k_mac_op_hw_scan(struct ieee80211_hw *hw, if (ret) goto exit; - /* Currently the pending_11d=true only happened 1 time while - * wlan interface up in ath11k_mac_11d_scan_start(), it is called by - * ath11k_mac_op_add_interface(), after wlan interface up, - * pending_11d=false always. - * If remove below wait, it always happened scan fail and lead connect - * fail while wlan interface up, because it has a 11d scan which is running - * in firmware, and lead this scan failed. - */ - if (ar->pending_11d) { - long time_left; - unsigned long timeout = 5 * HZ; - - if (ar->supports_6ghz) - timeout += 5 * HZ; - - time_left = wait_for_completion_timeout(&ar->finish_11d_ch_list, timeout); - ath11k_dbg(ar->ab, ATH11K_DBG_MAC, - "mac wait 11d channel list time left %ld\n", time_left); - } - memset(&arg, 0, sizeof(arg)); ath11k_wmi_start_scan_init(ar, &arg); arg.vdev_id = arvif->vdev_id; @@ -3680,6 +3666,10 @@ exit: kfree(arg.extraie.ptr); mutex_unlock(&ar->conf_mutex); + + if (ar->state_11d == ATH11K_11D_PREPARING) + ath11k_mac_11d_scan_start(ar, arvif->vdev_id); + return ret; } @@ -5808,7 +5798,7 @@ static int ath11k_mac_op_start(struct ieee80211_hw *hw) /* TODO: Do we need to enable ANI? */ - ath11k_reg_update_chan_list(ar); + ath11k_reg_update_chan_list(ar, false); ar->num_started_vdevs = 0; ar->num_created_vdevs = 0; @@ -5875,6 +5865,11 @@ static void ath11k_mac_op_stop(struct ieee80211_hw *hw) cancel_work_sync(&ar->ab->update_11d_work); cancel_work_sync(&ar->ab->rfkill_work); + if (ar->state_11d == ATH11K_11D_PREPARING) { + ar->state_11d = ATH11K_11D_IDLE; + complete(&ar->completed_11d_scan); + } + spin_lock_bh(&ar->data_lock); list_for_each_entry_safe(ppdu_stats, tmp, &ar->ppdu_stats_info, list) { list_del(&ppdu_stats->list); @@ -6045,7 +6040,7 @@ static bool ath11k_mac_vif_ap_active_any(struct ath11k_base *ab) return false; } -void ath11k_mac_11d_scan_start(struct ath11k *ar, u32 vdev_id, bool wait) +void ath11k_mac_11d_scan_start(struct ath11k *ar, u32 vdev_id) { struct wmi_11d_scan_start_params param; int ret; @@ -6073,28 +6068,22 @@ void ath11k_mac_11d_scan_start(struct ath11k *ar, u32 vdev_id, bool wait) ath11k_dbg(ar->ab, ATH11K_DBG_MAC, "mac start 11d scan\n"); - if (wait) - reinit_completion(&ar->finish_11d_scan); - ret = ath11k_wmi_send_11d_scan_start_cmd(ar, ¶m); if (ret) { ath11k_warn(ar->ab, "failed to start 11d scan vdev %d ret: %d\n", vdev_id, ret); } else { ar->vdev_id_11d_scan = vdev_id; - if (wait) { - ar->pending_11d = true; - ret = wait_for_completion_timeout(&ar->finish_11d_scan, - 5 * HZ); - ath11k_dbg(ar->ab, ATH11K_DBG_MAC, - "mac 11d scan left time %d\n", ret); - - if (!ret) - ar->pending_11d = false; - } + if (ar->state_11d == ATH11K_11D_PREPARING) + ar->state_11d = ATH11K_11D_RUNNING; } fin: + if (ar->state_11d == ATH11K_11D_PREPARING) { + ar->state_11d = ATH11K_11D_IDLE; + complete(&ar->completed_11d_scan); + } + mutex_unlock(&ar->ab->vdev_id_11d_lock); } @@ -6117,12 +6106,15 @@ void ath11k_mac_11d_scan_stop(struct ath11k *ar) vdev_id = ar->vdev_id_11d_scan; ret = ath11k_wmi_send_11d_scan_stop_cmd(ar, vdev_id); - if (ret) + if (ret) { ath11k_warn(ar->ab, "failed to stopt 11d scan vdev %d ret: %d\n", vdev_id, ret); - else + } else { ar->vdev_id_11d_scan = ATH11K_11D_INVALID_VDEV_ID; + ar->state_11d = ATH11K_11D_IDLE; + complete(&ar->completed_11d_scan); + } } mutex_unlock(&ar->ab->vdev_id_11d_lock); } @@ -6318,8 +6310,10 @@ static int ath11k_mac_op_add_interface(struct ieee80211_hw *hw, goto err_peer_del; } - ath11k_mac_11d_scan_start(ar, arvif->vdev_id, true); - + if (test_bit(WMI_TLV_SERVICE_11D_OFFLOAD, ab->wmi_ab.svc_map)) { + reinit_completion(&ar->completed_11d_scan); + ar->state_11d = ATH11K_11D_PREPARING; + } break; case WMI_VDEV_TYPE_MONITOR: set_bit(ATH11K_FLAG_MONITOR_VDEV_CREATED, &ar->monitor_flags); @@ -7184,7 +7178,7 @@ ath11k_mac_op_unassign_vif_chanctx(struct ieee80211_hw *hw, } if (arvif->vdev_type == WMI_VDEV_TYPE_STA) - ath11k_mac_11d_scan_start(ar, arvif->vdev_id, false); + ath11k_mac_11d_scan_start(ar, arvif->vdev_id); mutex_unlock(&ar->conf_mutex); } @@ -8665,8 +8659,7 @@ int ath11k_mac_allocate(struct ath11k_base *ab) ar->monitor_vdev_id = -1; clear_bit(ATH11K_FLAG_MONITOR_VDEV_CREATED, &ar->monitor_flags); ar->vdev_id_11d_scan = ATH11K_11D_INVALID_VDEV_ID; - init_completion(&ar->finish_11d_scan); - init_completion(&ar->finish_11d_ch_list); + init_completion(&ar->completed_11d_scan); } return 0; diff --git a/drivers/net/wireless/ath/ath11k/mac.h b/drivers/net/wireless/ath/ath11k/mac.h index 0e6c870b09c8..29b523af66dd 100644 --- a/drivers/net/wireless/ath/ath11k/mac.h +++ b/drivers/net/wireless/ath/ath11k/mac.h @@ -130,7 +130,7 @@ extern const struct htt_rx_ring_tlv_filter ath11k_mac_mon_status_filter_default; #define ATH11K_SCAN_11D_INTERVAL 600000 #define ATH11K_11D_INVALID_VDEV_ID 0xFFFF -void ath11k_mac_11d_scan_start(struct ath11k *ar, u32 vdev_id, bool wait); +void ath11k_mac_11d_scan_start(struct ath11k *ar, u32 vdev_id); void ath11k_mac_11d_scan_stop(struct ath11k *ar); void ath11k_mac_11d_scan_stop_all(struct ath11k_base *ab); diff --git a/drivers/net/wireless/ath/ath11k/reg.c b/drivers/net/wireless/ath/ath11k/reg.c index 81e11cde31d7..80a697771393 100644 --- a/drivers/net/wireless/ath/ath11k/reg.c +++ b/drivers/net/wireless/ath/ath11k/reg.c @@ -102,7 +102,7 @@ ath11k_reg_notifier(struct wiphy *wiphy, struct regulatory_request *request) ar->regdom_set_by_user = true; } -int ath11k_reg_update_chan_list(struct ath11k *ar) +int ath11k_reg_update_chan_list(struct ath11k *ar, bool wait) { struct ieee80211_supported_band **bands; struct scan_chan_list_params *params; @@ -111,7 +111,32 @@ int ath11k_reg_update_chan_list(struct ath11k *ar) struct channel_param *ch; enum nl80211_band band; int num_channels = 0; - int i, ret; + int i, ret, left; + + if (wait && ar->state_11d != ATH11K_11D_IDLE) { + left = wait_for_completion_timeout(&ar->completed_11d_scan, + ATH11K_SCAN_TIMEOUT_HZ); + if (!left) { + ath11k_dbg(ar->ab, ATH11K_DBG_REG, + "failed to receive 11d scan complete: timed out\n"); + ar->state_11d = ATH11K_11D_IDLE; + } + ath11k_dbg(ar->ab, ATH11K_DBG_REG, + "reg 11d scan wait left time %d\n", left); + } + + if (wait && + (ar->scan.state == ATH11K_SCAN_STARTING || + ar->scan.state == ATH11K_SCAN_RUNNING)) { + left = wait_for_completion_timeout(&ar->scan.completed, + ATH11K_SCAN_TIMEOUT_HZ); + if (!left) + ath11k_dbg(ar->ab, ATH11K_DBG_REG, + "failed to receive hw scan complete: timed out\n"); + + ath11k_dbg(ar->ab, ATH11K_DBG_REG, + "reg hw scan wait left time %d\n", left); + } bands = hw->wiphy->bands; for (band = 0; band < NUM_NL80211_BANDS; band++) { @@ -193,11 +218,6 @@ int ath11k_reg_update_chan_list(struct ath11k *ar) ret = ath11k_wmi_send_scan_chan_list_cmd(ar, params); kfree(params); - if (ar->pending_11d) { - complete(&ar->finish_11d_ch_list); - ar->pending_11d = false; - } - return ret; } @@ -263,15 +283,8 @@ int ath11k_regd_update(struct ath11k *ar) goto err; } - if (ar->pending_11d) - complete(&ar->finish_11d_scan); - rtnl_lock(); wiphy_lock(ar->hw->wiphy); - - if (ar->pending_11d) - reinit_completion(&ar->finish_11d_ch_list); - ret = regulatory_set_wiphy_regd_sync(ar->hw->wiphy, regd_copy); wiphy_unlock(ar->hw->wiphy); rtnl_unlock(); @@ -282,7 +295,7 @@ int ath11k_regd_update(struct ath11k *ar) goto err; if (ar->state == ATH11K_STATE_ON) { - ret = ath11k_reg_update_chan_list(ar); + ret = ath11k_reg_update_chan_list(ar, true); if (ret) goto err; } diff --git a/drivers/net/wireless/ath/ath11k/reg.h b/drivers/net/wireless/ath/ath11k/reg.h index 5fb9dc03a74e..2f284f26378d 100644 --- a/drivers/net/wireless/ath/ath11k/reg.h +++ b/drivers/net/wireless/ath/ath11k/reg.h @@ -32,5 +32,5 @@ struct ieee80211_regdomain * ath11k_reg_build_regd(struct ath11k_base *ab, struct cur_regulatory_info *reg_info, bool intersect); int ath11k_regd_update(struct ath11k *ar); -int ath11k_reg_update_chan_list(struct ath11k *ar); +int ath11k_reg_update_chan_list(struct ath11k *ar, bool wait); #endif diff --git a/drivers/net/wireless/ath/ath11k/wmi.c b/drivers/net/wireless/ath/ath11k/wmi.c index b4f86c45d81f..2751fe8814df 100644 --- a/drivers/net/wireless/ath/ath11k/wmi.c +++ b/drivers/net/wireless/ath/ath11k/wmi.c @@ -2015,7 +2015,10 @@ void ath11k_wmi_start_scan_init(struct ath11k *ar, { /* setup commonly used values */ arg->scan_req_id = 1; - arg->scan_priority = WMI_SCAN_PRIORITY_LOW; + if (ar->state_11d == ATH11K_11D_PREPARING) + arg->scan_priority = WMI_SCAN_PRIORITY_MEDIUM; + else + arg->scan_priority = WMI_SCAN_PRIORITY_LOW; arg->dwell_time_active = 50; arg->dwell_time_active_2g = 0; arg->dwell_time_passive = 150; @@ -6350,8 +6353,10 @@ static void ath11k_wmi_op_ep_tx_credits(struct ath11k_base *ab) static int ath11k_reg_11d_new_cc_event(struct ath11k_base *ab, struct sk_buff *skb) { const struct wmi_11d_new_cc_ev *ev; + struct ath11k *ar; + struct ath11k_pdev *pdev; const void **tb; - int ret; + int ret, i; tb = ath11k_wmi_tlv_parse_alloc(ab, skb->data, skb->len, GFP_ATOMIC); if (IS_ERR(tb)) { @@ -6377,6 +6382,13 @@ static int ath11k_reg_11d_new_cc_event(struct ath11k_base *ab, struct sk_buff *s kfree(tb); + for (i = 0; i < ab->num_radios; i++) { + pdev = &ab->pdevs[i]; + ar = pdev->ar; + ar->state_11d = ATH11K_11D_IDLE; + complete(&ar->completed_11d_scan); + } + queue_work(ab->workqueue, &ab->update_11d_work); return 0; diff --git a/drivers/net/wireless/ath/ath9k/main.c b/drivers/net/wireless/ath/ath9k/main.c index 98090e40e1cf..e2791d45f5f5 100644 --- a/drivers/net/wireless/ath/ath9k/main.c +++ b/drivers/net/wireless/ath/ath9k/main.c @@ -839,7 +839,7 @@ static bool ath9k_txq_list_has_key(struct list_head *txq_list, u32 keyix) continue; txinfo = IEEE80211_SKB_CB(bf->bf_mpdu); - fi = (struct ath_frame_info *)&txinfo->rate_driver_data[0]; + fi = (struct ath_frame_info *)&txinfo->status.status_driver_data[0]; if (fi->keyix == keyix) return true; } diff --git a/drivers/net/wireless/ath/ath9k/xmit.c b/drivers/net/wireless/ath/ath9k/xmit.c index d0caf1de2bde..db83cc4ba810 100644 --- a/drivers/net/wireless/ath/ath9k/xmit.c +++ b/drivers/net/wireless/ath/ath9k/xmit.c @@ -141,8 +141,8 @@ static struct ath_frame_info *get_frame_info(struct sk_buff *skb) { struct ieee80211_tx_info *tx_info = IEEE80211_SKB_CB(skb); BUILD_BUG_ON(sizeof(struct ath_frame_info) > - sizeof(tx_info->rate_driver_data)); - return (struct ath_frame_info *) &tx_info->rate_driver_data[0]; + sizeof(tx_info->status.status_driver_data)); + return (struct ath_frame_info *) &tx_info->status.status_driver_data[0]; } static void ath_send_bar(struct ath_atx_tid *tid, u16 seqno) @@ -2542,6 +2542,16 @@ skip_tx_complete: spin_unlock_irqrestore(&sc->tx.txbuflock, flags); } +static void ath_clear_tx_status(struct ieee80211_tx_info *tx_info) +{ + void *ptr = &tx_info->status; + + memset(ptr + sizeof(tx_info->status.rates), 0, + sizeof(tx_info->status) - + sizeof(tx_info->status.rates) - + sizeof(tx_info->status.status_driver_data)); +} + static void ath_tx_rc_status(struct ath_softc *sc, struct ath_buf *bf, struct ath_tx_status *ts, int nframes, int nbad, int txok) @@ -2553,6 +2563,8 @@ static void ath_tx_rc_status(struct ath_softc *sc, struct ath_buf *bf, struct ath_hw *ah = sc->sc_ah; u8 i, tx_rateindex; + ath_clear_tx_status(tx_info); + if (txok) tx_info->status.ack_signal = ts->ts_rssi; @@ -2567,6 +2579,13 @@ static void ath_tx_rc_status(struct ath_softc *sc, struct ath_buf *bf, tx_info->status.ampdu_len = nframes; tx_info->status.ampdu_ack_len = nframes - nbad; + tx_info->status.rates[tx_rateindex].count = ts->ts_longretry + 1; + + for (i = tx_rateindex + 1; i < hw->max_rates; i++) { + tx_info->status.rates[i].count = 0; + tx_info->status.rates[i].idx = -1; + } + if ((ts->ts_status & ATH9K_TXERR_FILT) == 0 && (tx_info->flags & IEEE80211_TX_CTL_NO_ACK) == 0) { /* @@ -2588,16 +2607,6 @@ static void ath_tx_rc_status(struct ath_softc *sc, struct ath_buf *bf, tx_info->status.rates[tx_rateindex].count = hw->max_rate_tries; } - - for (i = tx_rateindex + 1; i < hw->max_rates; i++) { - tx_info->status.rates[i].count = 0; - tx_info->status.rates[i].idx = -1; - } - - tx_info->status.rates[tx_rateindex].count = ts->ts_longretry + 1; - - /* we report airtime in ath_tx_count_airtime(), don't report twice */ - tx_info->status.tx_time = 0; } static void ath_tx_processq(struct ath_softc *sc, struct ath_txq *txq) diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c index ba3c159111d3..212fbbe1cd7e 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c @@ -557,7 +557,7 @@ enum brcmf_sdio_frmtype { BRCMF_SDIO_FT_SUB, }; -#define SDIOD_DRVSTR_KEY(chip, pmu) (((chip) << 16) | (pmu)) +#define SDIOD_DRVSTR_KEY(chip, pmu) (((unsigned int)(chip) << 16) | (pmu)) /* SDIO Pad drive strength to select value mappings */ struct sdiod_drive_str { @@ -4165,7 +4165,7 @@ static int brcmf_sdio_bus_reset(struct device *dev) /* reset the adapter */ sdio_claim_host(sdiodev->func1); - mmc_hw_reset(sdiodev->func1->card->host); + mmc_hw_reset(sdiodev->func1->card); sdio_release_host(sdiodev->func1); brcmf_bus_change_state(sdiodev->bus_if, BRCMF_BUS_DOWN); diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c index 866a33f49915..3237d4b528b5 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c @@ -371,7 +371,7 @@ void iwl_dbg_tlv_del_timers(struct iwl_trans *trans) struct iwl_dbg_tlv_timer_node *node, *tmp; list_for_each_entry_safe(node, tmp, timer_list, list) { - del_timer(&node->timer); + del_timer_sync(&node->timer); list_del(&node->list); kfree(node); } diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 28bfa7b7b73c..e9ec63e0e395 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -2202,11 +2202,14 @@ mac80211_hwsim_sta_rc_update(struct ieee80211_hw *hw, if (!data->use_chanctx) { confbw = data->bw; } else { - struct ieee80211_chanctx_conf *chanctx_conf = - rcu_dereference(vif->chanctx_conf); + struct ieee80211_chanctx_conf *chanctx_conf; + + rcu_read_lock(); + chanctx_conf = rcu_dereference(vif->chanctx_conf); if (!WARN_ON(!chanctx_conf)) confbw = chanctx_conf->def.width; + rcu_read_unlock(); } WARN(bw > hwsim_get_chanwidth(confbw), @@ -2475,11 +2478,13 @@ static void hw_scan_work(struct work_struct *work) if (req->ie_len) skb_put_data(probe, req->ie, req->ie_len); + rcu_read_lock(); if (!ieee80211_tx_prepare_skb(hwsim->hw, hwsim->hw_scan_vif, probe, hwsim->tmp_chan->band, NULL)) { + rcu_read_unlock(); kfree_skb(probe); continue; } @@ -2487,6 +2492,7 @@ static void hw_scan_work(struct work_struct *work) local_bh_disable(); mac80211_hwsim_tx_frame(hwsim->hw, probe, hwsim->tmp_chan); + rcu_read_unlock(); local_bh_enable(); } } diff --git a/drivers/net/wireless/marvell/mwifiex/sdio.c b/drivers/net/wireless/marvell/mwifiex/sdio.c index bde9e4bbfffe..4f3238d2a171 100644 --- a/drivers/net/wireless/marvell/mwifiex/sdio.c +++ b/drivers/net/wireless/marvell/mwifiex/sdio.c @@ -2639,7 +2639,7 @@ static void mwifiex_sdio_card_reset_work(struct mwifiex_adapter *adapter) /* Run a HW reset of the SDIO interface. */ sdio_claim_host(func); - ret = mmc_hw_reset(func->card->host); + ret = mmc_hw_reset(func->card); sdio_release_host(func); switch (ret) { diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c index 8a22ee581674..df85ebc6e1df 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c @@ -80,7 +80,7 @@ mt76x2e_probe(struct pci_dev *pdev, const struct pci_device_id *id) mt76_rmw_field(dev, 0x15a10, 0x1f << 16, 0x9); /* RG_SSUSB_G1_CDR_BIC_LTR = 0xf */ - mt76_rmw_field(dev, 0x15a0c, 0xf << 28, 0xf); + mt76_rmw_field(dev, 0x15a0c, 0xfU << 28, 0xf); /* RG_SSUSB_CDR_BR_PE1D = 0x3 */ mt76_rmw_field(dev, 0x15c58, 0x3 << 6, 0x3); diff --git a/drivers/net/wireless/ti/wlcore/sdio.c b/drivers/net/wireless/ti/wlcore/sdio.c index 72fc41ac83c0..9140b0163474 100644 --- a/drivers/net/wireless/ti/wlcore/sdio.c +++ b/drivers/net/wireless/ti/wlcore/sdio.c @@ -146,7 +146,7 @@ static int wl12xx_sdio_power_on(struct wl12xx_sdio_glue *glue) * To guarantee that the SDIO card is power cycled, as required to make * the FW programming to succeed, let's do a brute force HW reset. */ - mmc_hw_reset(card->host); + mmc_hw_reset(card); sdio_enable_func(func); sdio_release_host(func); diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index e2b4a1893a13..65ab907aca5a 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -78,8 +78,6 @@ struct netfront_cb { #define RX_COPY_THRESHOLD 256 -#define GRANT_INVALID_REF 0 - #define NET_TX_RING_SIZE __CONST_RING_SIZE(xen_netif_tx, XEN_PAGE_SIZE) #define NET_RX_RING_SIZE __CONST_RING_SIZE(xen_netif_rx, XEN_PAGE_SIZE) @@ -224,7 +222,7 @@ static grant_ref_t xennet_get_rx_ref(struct netfront_queue *queue, { int i = xennet_rxidx(ri); grant_ref_t ref = queue->grant_rx_ref[i]; - queue->grant_rx_ref[i] = GRANT_INVALID_REF; + queue->grant_rx_ref[i] = INVALID_GRANT_REF; return ref; } @@ -432,7 +430,7 @@ static bool xennet_tx_buf_gc(struct netfront_queue *queue) } gnttab_release_grant_reference( &queue->gref_tx_head, queue->grant_tx_ref[id]); - queue->grant_tx_ref[id] = GRANT_INVALID_REF; + queue->grant_tx_ref[id] = INVALID_GRANT_REF; queue->grant_tx_page[id] = NULL; add_id_to_list(&queue->tx_skb_freelist, queue->tx_link, id); dev_kfree_skb_irq(skb); @@ -868,7 +866,7 @@ static void xennet_set_rx_rsp_cons(struct netfront_queue *queue, RING_IDX val) spin_lock_irqsave(&queue->rx_cons_lock, flags); queue->rx.rsp_cons = val; - queue->rx_rsp_unconsumed = RING_HAS_UNCONSUMED_RESPONSES(&queue->rx); + queue->rx_rsp_unconsumed = XEN_RING_NR_UNCONSUMED_RESPONSES(&queue->rx); spin_unlock_irqrestore(&queue->rx_cons_lock, flags); } @@ -1021,7 +1019,7 @@ static int xennet_get_responses(struct netfront_queue *queue, * the backend driver. In future this should flag the bad * situation to the system controller to reboot the backend. */ - if (ref == GRANT_INVALID_REF) { + if (ref == INVALID_GRANT_REF) { if (net_ratelimit()) dev_warn(dev, "Bad rx response id %d.\n", rx->id); @@ -1390,7 +1388,7 @@ static void xennet_release_tx_bufs(struct netfront_queue *queue) gnttab_end_foreign_access(queue->grant_tx_ref[i], (unsigned long)page_address(queue->grant_tx_page[i])); queue->grant_tx_page[i] = NULL; - queue->grant_tx_ref[i] = GRANT_INVALID_REF; + queue->grant_tx_ref[i] = INVALID_GRANT_REF; add_id_to_list(&queue->tx_skb_freelist, queue->tx_link, i); dev_kfree_skb_irq(skb); } @@ -1411,7 +1409,7 @@ static void xennet_release_rx_bufs(struct netfront_queue *queue) continue; ref = queue->grant_rx_ref[id]; - if (ref == GRANT_INVALID_REF) + if (ref == INVALID_GRANT_REF) continue; page = skb_frag_page(&skb_shinfo(skb)->frags[0]); @@ -1422,7 +1420,7 @@ static void xennet_release_rx_bufs(struct netfront_queue *queue) get_page(page); gnttab_end_foreign_access(ref, (unsigned long)page_address(page)); - queue->grant_rx_ref[id] = GRANT_INVALID_REF; + queue->grant_rx_ref[id] = INVALID_GRANT_REF; kfree_skb(skb); } @@ -1500,7 +1498,7 @@ static bool xennet_handle_rx(struct netfront_queue *queue, unsigned int *eoi) return false; spin_lock_irqsave(&queue->rx_cons_lock, flags); - work_queued = RING_HAS_UNCONSUMED_RESPONSES(&queue->rx); + work_queued = XEN_RING_NR_UNCONSUMED_RESPONSES(&queue->rx); if (work_queued > queue->rx_rsp_unconsumed) { queue->rx_rsp_unconsumed = work_queued; *eoi = 0; @@ -1761,7 +1759,7 @@ static int netfront_probe(struct xenbus_device *dev, static void xennet_end_access(int ref, void *page) { /* This frees the page as a side-effect */ - if (ref != GRANT_INVALID_REF) + if (ref != INVALID_GRANT_REF) gnttab_end_foreign_access(ref, (unsigned long)page); } @@ -1798,8 +1796,8 @@ static void xennet_disconnect_backend(struct netfront_info *info) xennet_end_access(queue->tx_ring_ref, queue->tx.sring); xennet_end_access(queue->rx_ring_ref, queue->rx.sring); - queue->tx_ring_ref = GRANT_INVALID_REF; - queue->rx_ring_ref = GRANT_INVALID_REF; + queue->tx_ring_ref = INVALID_GRANT_REF; + queue->rx_ring_ref = INVALID_GRANT_REF; queue->tx.sring = NULL; queue->rx.sring = NULL; @@ -1923,42 +1921,27 @@ static int setup_netfront(struct xenbus_device *dev, struct netfront_queue *queue, unsigned int feature_split_evtchn) { struct xen_netif_tx_sring *txs; - struct xen_netif_rx_sring *rxs = NULL; - grant_ref_t gref; + struct xen_netif_rx_sring *rxs; int err; - queue->tx_ring_ref = GRANT_INVALID_REF; - queue->rx_ring_ref = GRANT_INVALID_REF; + queue->tx_ring_ref = INVALID_GRANT_REF; + queue->rx_ring_ref = INVALID_GRANT_REF; queue->rx.sring = NULL; queue->tx.sring = NULL; - txs = (struct xen_netif_tx_sring *)get_zeroed_page(GFP_NOIO | __GFP_HIGH); - if (!txs) { - err = -ENOMEM; - xenbus_dev_fatal(dev, err, "allocating tx ring page"); + err = xenbus_setup_ring(dev, GFP_NOIO | __GFP_HIGH, (void **)&txs, + 1, &queue->tx_ring_ref); + if (err) goto fail; - } - SHARED_RING_INIT(txs); - FRONT_RING_INIT(&queue->tx, txs, XEN_PAGE_SIZE); - err = xenbus_grant_ring(dev, txs, 1, &gref); - if (err < 0) - goto fail; - queue->tx_ring_ref = gref; + XEN_FRONT_RING_INIT(&queue->tx, txs, XEN_PAGE_SIZE); - rxs = (struct xen_netif_rx_sring *)get_zeroed_page(GFP_NOIO | __GFP_HIGH); - if (!rxs) { - err = -ENOMEM; - xenbus_dev_fatal(dev, err, "allocating rx ring page"); + err = xenbus_setup_ring(dev, GFP_NOIO | __GFP_HIGH, (void **)&rxs, + 1, &queue->rx_ring_ref); + if (err) goto fail; - } - SHARED_RING_INIT(rxs); - FRONT_RING_INIT(&queue->rx, rxs, XEN_PAGE_SIZE); - err = xenbus_grant_ring(dev, rxs, 1, &gref); - if (err < 0) - goto fail; - queue->rx_ring_ref = gref; + XEN_FRONT_RING_INIT(&queue->rx, rxs, XEN_PAGE_SIZE); if (feature_split_evtchn) err = setup_netfront_split(queue); @@ -1974,24 +1957,10 @@ static int setup_netfront(struct xenbus_device *dev, return 0; - /* If we fail to setup netfront, it is safe to just revoke access to - * granted pages because backend is not accessing it at this point. - */ fail: - if (queue->rx_ring_ref != GRANT_INVALID_REF) { - gnttab_end_foreign_access(queue->rx_ring_ref, - (unsigned long)rxs); - queue->rx_ring_ref = GRANT_INVALID_REF; - } else { - free_page((unsigned long)rxs); - } - if (queue->tx_ring_ref != GRANT_INVALID_REF) { - gnttab_end_foreign_access(queue->tx_ring_ref, - (unsigned long)txs); - queue->tx_ring_ref = GRANT_INVALID_REF; - } else { - free_page((unsigned long)txs); - } + xenbus_teardown_ring((void **)&queue->rx.sring, 1, &queue->rx_ring_ref); + xenbus_teardown_ring((void **)&queue->tx.sring, 1, &queue->tx_ring_ref); + return err; } @@ -2020,7 +1989,7 @@ static int xennet_init_queue(struct netfront_queue *queue) queue->tx_pend_queue = TX_LINK_NONE; for (i = 0; i < NET_TX_RING_SIZE; i++) { queue->tx_link[i] = i + 1; - queue->grant_tx_ref[i] = GRANT_INVALID_REF; + queue->grant_tx_ref[i] = INVALID_GRANT_REF; queue->grant_tx_page[i] = NULL; } queue->tx_link[NET_TX_RING_SIZE - 1] = TX_LINK_NONE; @@ -2028,7 +1997,7 @@ static int xennet_init_queue(struct netfront_queue *queue) /* Clear out rx_skbs */ for (i = 0; i < NET_RX_RING_SIZE; i++) { queue->rx_skbs[i] = NULL; - queue->grant_rx_ref[i] = GRANT_INVALID_REF; + queue->grant_rx_ref[i] = INVALID_GRANT_REF; } /* A grant for every tx ring slot */ diff --git a/drivers/nfc/nfcmrvl/main.c b/drivers/nfc/nfcmrvl/main.c index 2fcf545012b1..1a5284de4341 100644 --- a/drivers/nfc/nfcmrvl/main.c +++ b/drivers/nfc/nfcmrvl/main.c @@ -183,6 +183,7 @@ void nfcmrvl_nci_unregister_dev(struct nfcmrvl_private *priv) { struct nci_dev *ndev = priv->ndev; + nci_unregister_device(ndev); if (priv->ndev->nfc_dev->fw_download_in_progress) nfcmrvl_fw_dnld_abort(priv); @@ -191,7 +192,6 @@ void nfcmrvl_nci_unregister_dev(struct nfcmrvl_private *priv) if (gpio_is_valid(priv->config.reset_n_io)) gpio_free(priv->config.reset_n_io); - nci_unregister_device(ndev); nci_free_device(ndev); kfree(priv); } diff --git a/drivers/nfc/pn533/pn533.c b/drivers/nfc/pn533/pn533.c index a491db46e3bd..d9f6367b9993 100644 --- a/drivers/nfc/pn533/pn533.c +++ b/drivers/nfc/pn533/pn533.c @@ -2787,13 +2787,14 @@ void pn53x_common_clean(struct pn533 *priv) { struct pn533_cmd *cmd, *n; + /* delete the timer before cleanup the worker */ + del_timer_sync(&priv->listen_timer); + flush_delayed_work(&priv->poll_work); destroy_workqueue(priv->wq); skb_queue_purge(&priv->resp_q); - del_timer(&priv->listen_timer); - list_for_each_entry_safe(cmd, n, &priv->cmd_queue, queue) { list_del(&cmd->queue); kfree(cmd); diff --git a/drivers/nvme/host/constants.c b/drivers/nvme/host/constants.c index 7d49eb34b348..4910543f00ff 100644 --- a/drivers/nvme/host/constants.c +++ b/drivers/nvme/host/constants.c @@ -4,7 +4,6 @@ * Copyright (c) 2022, Oracle and/or its affiliates */ -#include <linux/blkdev.h> #include "nvme.h" #ifdef CONFIG_NVME_VERBOSE_ERRORS @@ -92,6 +91,7 @@ static const char * const nvme_statuses[] = { [NVME_SC_NS_WRITE_PROTECTED] = "Namespace is Write Protected", [NVME_SC_CMD_INTERRUPTED] = "Command Interrupted", [NVME_SC_TRANSIENT_TR_ERR] = "Transient Transport Error", + [NVME_SC_ADMIN_COMMAND_MEDIA_NOT_READY] = "Admin Command Media Not Ready", [NVME_SC_INVALID_IO_CMD_SET] = "Invalid IO Command Set", [NVME_SC_LBA_RANGE] = "LBA Out of Range", [NVME_SC_CAP_EXCEEDED] = "Capacity Exceeded", @@ -155,10 +155,13 @@ static const char * const nvme_statuses[] = { [NVME_SC_COMPARE_FAILED] = "Compare Failure", [NVME_SC_ACCESS_DENIED] = "Access Denied", [NVME_SC_UNWRITTEN_BLOCK] = "Deallocated or Unwritten Logical Block", + [NVME_SC_INTERNAL_PATH_ERROR] = "Internal Pathing Error", [NVME_SC_ANA_PERSISTENT_LOSS] = "Asymmetric Access Persistent Loss", [NVME_SC_ANA_INACCESSIBLE] = "Asymmetric Access Inaccessible", [NVME_SC_ANA_TRANSITION] = "Asymmetric Access Transition", + [NVME_SC_CTRL_PATH_ERROR] = "Controller Pathing Error", [NVME_SC_HOST_PATH_ERROR] = "Host Pathing Error", + [NVME_SC_HOST_ABORTED_CMD] = "Host Aborted Command", }; const unsigned char *nvme_get_error_status_str(u16 status) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index efb85c6d8e2d..72f7c955c707 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -366,7 +366,7 @@ static inline void nvme_end_req(struct request *req) { blk_status_t status = nvme_error_status(nvme_req(req)->status); - if (unlikely(nvme_req(req)->status != NVME_SC_SUCCESS)) + if (unlikely(nvme_req(req)->status && !(req->rq_flags & RQF_QUIET))) nvme_log_error(req); nvme_end_req_zoned(req); nvme_trace_bio_complete(req); @@ -1015,6 +1015,7 @@ int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd, goto out; } + req->rq_flags |= RQF_QUIET; ret = nvme_execute_rq(req, at_head); if (result && ret >= 0) *result = nvme_req(req)->result; @@ -1206,6 +1207,7 @@ static void nvme_keep_alive_work(struct work_struct *work) rq->timeout = ctrl->kato * HZ; rq->end_io_data = ctrl; + rq->rq_flags |= RQF_QUIET; blk_execute_rq_nowait(rq, false, nvme_keep_alive_end_io); } @@ -1287,6 +1289,8 @@ static int nvme_process_ns_desc(struct nvme_ctrl *ctrl, struct nvme_ns_ids *ids, warn_str, cur->nidl); return -1; } + if (ctrl->quirks & NVME_QUIRK_BOGUS_NID) + return NVME_NIDT_EUI64_LEN; memcpy(ids->eui64, data + sizeof(*cur), NVME_NIDT_EUI64_LEN); return NVME_NIDT_EUI64_LEN; case NVME_NIDT_NGUID: @@ -1295,6 +1299,8 @@ static int nvme_process_ns_desc(struct nvme_ctrl *ctrl, struct nvme_ns_ids *ids, warn_str, cur->nidl); return -1; } + if (ctrl->quirks & NVME_QUIRK_BOGUS_NID) + return NVME_NIDT_NGUID_LEN; memcpy(ids->nguid, data + sizeof(*cur), NVME_NIDT_NGUID_LEN); return NVME_NIDT_NGUID_LEN; case NVME_NIDT_UUID: @@ -1303,6 +1309,8 @@ static int nvme_process_ns_desc(struct nvme_ctrl *ctrl, struct nvme_ns_ids *ids, warn_str, cur->nidl); return -1; } + if (ctrl->quirks & NVME_QUIRK_BOGUS_NID) + return NVME_NIDT_UUID_LEN; uuid_copy(&ids->uuid, data + sizeof(*cur)); return NVME_NIDT_UUID_LEN; case NVME_NIDT_CSI: @@ -1399,12 +1407,18 @@ static int nvme_identify_ns(struct nvme_ctrl *ctrl, unsigned nsid, if ((*id)->ncap == 0) /* namespace not allocated or attached */ goto out_free_id; - if (ctrl->vs >= NVME_VS(1, 1, 0) && - !memchr_inv(ids->eui64, 0, sizeof(ids->eui64))) - memcpy(ids->eui64, (*id)->eui64, sizeof(ids->eui64)); - if (ctrl->vs >= NVME_VS(1, 2, 0) && - !memchr_inv(ids->nguid, 0, sizeof(ids->nguid))) - memcpy(ids->nguid, (*id)->nguid, sizeof(ids->nguid)); + + if (ctrl->quirks & NVME_QUIRK_BOGUS_NID) { + dev_info(ctrl->device, + "Ignoring bogus Namespace Identifiers\n"); + } else { + if (ctrl->vs >= NVME_VS(1, 1, 0) && + !memchr_inv(ids->eui64, 0, sizeof(ids->eui64))) + memcpy(ids->eui64, (*id)->eui64, sizeof(ids->eui64)); + if (ctrl->vs >= NVME_VS(1, 2, 0) && + !memchr_inv(ids->nguid, 0, sizeof(ids->nguid))) + memcpy(ids->nguid, (*id)->nguid, sizeof(ids->nguid)); + } return 0; @@ -1413,6 +1427,32 @@ out_free_id: return error; } +static int nvme_identify_ns_cs_indep(struct nvme_ctrl *ctrl, unsigned nsid, + struct nvme_id_ns_cs_indep **id) +{ + struct nvme_command c = { + .identify.opcode = nvme_admin_identify, + .identify.nsid = cpu_to_le32(nsid), + .identify.cns = NVME_ID_CNS_NS_CS_INDEP, + }; + int ret; + + *id = kmalloc(sizeof(**id), GFP_KERNEL); + if (!*id) + return -ENOMEM; + + ret = nvme_submit_sync_cmd(ctrl->admin_q, &c, *id, sizeof(**id)); + if (ret) { + dev_warn(ctrl->device, + "Identify namespace (CS independent) failed (%d)\n", + ret); + kfree(*id); + return ret; + } + + return 0; +} + static int nvme_features(struct nvme_ctrl *dev, u8 op, unsigned int fid, unsigned int dword11, void *buffer, size_t buflen, u32 *result) { @@ -1608,20 +1648,22 @@ static void nvme_config_discard(struct gendisk *disk, struct nvme_ns *ns) u32 size = queue_logical_block_size(queue); if (ctrl->max_discard_sectors == 0) { - blk_queue_flag_clear(QUEUE_FLAG_DISCARD, queue); + blk_queue_max_discard_sectors(queue, 0); return; } BUILD_BUG_ON(PAGE_SIZE / sizeof(struct nvme_dsm_range) < NVME_DSM_MAX_RANGES); - queue->limits.discard_alignment = 0; queue->limits.discard_granularity = size; /* If discard is already enabled, don't reset queue limits */ - if (blk_queue_flag_test_and_set(QUEUE_FLAG_DISCARD, queue)) + if (queue->limits.max_discard_sectors) return; + if (ctrl->dmrsl && ctrl->dmrsl <= nvme_sect_to_lba(ns, UINT_MAX)) + ctrl->max_discard_sectors = nvme_lba_to_sect(ns, ctrl->dmrsl); + blk_queue_max_discard_sectors(queue, ctrl->max_discard_sectors); blk_queue_max_discard_segments(queue, ctrl->max_discard_segments); @@ -1758,7 +1800,7 @@ static void nvme_set_queue_limits(struct nvme_ctrl *ctrl, blk_queue_max_segments(q, min_t(u32, max_segments, USHRT_MAX)); } blk_queue_virt_boundary(q, NVME_CTRL_PAGE_SIZE - 1); - blk_queue_dma_alignment(q, 7); + blk_queue_dma_alignment(q, 3); blk_queue_write_cache(q, vwc, vwc); } @@ -2087,10 +2129,9 @@ static const struct block_device_operations nvme_bdev_ops = { .pr_ops = &nvme_pr_ops, }; -static int nvme_wait_ready(struct nvme_ctrl *ctrl, u64 cap, bool enabled) +static int nvme_wait_ready(struct nvme_ctrl *ctrl, u32 timeout, bool enabled) { - unsigned long timeout = - ((NVME_CAP_TIMEOUT(cap) + 1) * HZ / 2) + jiffies; + unsigned long timeout_jiffies = ((timeout + 1) * HZ / 2) + jiffies; u32 csts, bit = enabled ? NVME_CSTS_RDY : 0; int ret; @@ -2103,7 +2144,7 @@ static int nvme_wait_ready(struct nvme_ctrl *ctrl, u64 cap, bool enabled) usleep_range(1000, 2000); if (fatal_signal_pending(current)) return -EINTR; - if (time_after(jiffies, timeout)) { + if (time_after(jiffies, timeout_jiffies)) { dev_err(ctrl->device, "Device not ready; aborting %s, CSTS=0x%x\n", enabled ? "initialisation" : "reset", csts); @@ -2134,13 +2175,14 @@ int nvme_disable_ctrl(struct nvme_ctrl *ctrl) if (ctrl->quirks & NVME_QUIRK_DELAY_BEFORE_CHK_RDY) msleep(NVME_QUIRK_DELAY_AMOUNT); - return nvme_wait_ready(ctrl, ctrl->cap, false); + return nvme_wait_ready(ctrl, NVME_CAP_TIMEOUT(ctrl->cap), false); } EXPORT_SYMBOL_GPL(nvme_disable_ctrl); int nvme_enable_ctrl(struct nvme_ctrl *ctrl) { unsigned dev_page_min; + u32 timeout; int ret; ret = ctrl->ops->reg_read64(ctrl, NVME_REG_CAP, &ctrl->cap); @@ -2161,6 +2203,27 @@ int nvme_enable_ctrl(struct nvme_ctrl *ctrl) ctrl->ctrl_config = NVME_CC_CSS_CSI; else ctrl->ctrl_config = NVME_CC_CSS_NVM; + + if (ctrl->cap & NVME_CAP_CRMS_CRWMS) { + u32 crto; + + ret = ctrl->ops->reg_read32(ctrl, NVME_REG_CRTO, &crto); + if (ret) { + dev_err(ctrl->device, "Reading CRTO failed (%d)\n", + ret); + return ret; + } + + if (ctrl->cap & NVME_CAP_CRMS_CRIMS) { + ctrl->ctrl_config |= NVME_CC_CRIME; + timeout = NVME_CRTO_CRIMT(crto); + } else { + timeout = NVME_CRTO_CRWMT(crto); + } + } else { + timeout = NVME_CAP_TIMEOUT(ctrl->cap); + } + ctrl->ctrl_config |= (NVME_CTRL_PAGE_SHIFT - 12) << NVME_CC_MPS_SHIFT; ctrl->ctrl_config |= NVME_CC_AMS_RR | NVME_CC_SHN_NONE; ctrl->ctrl_config |= NVME_CC_IOSQES | NVME_CC_IOCQES; @@ -2169,7 +2232,7 @@ int nvme_enable_ctrl(struct nvme_ctrl *ctrl) ret = ctrl->ops->reg_write32(ctrl, NVME_REG_CC, ctrl->ctrl_config); if (ret) return ret; - return nvme_wait_ready(ctrl, ctrl->cap, true); + return nvme_wait_ready(ctrl, timeout, true); } EXPORT_SYMBOL_GPL(nvme_enable_ctrl); @@ -2881,8 +2944,7 @@ static int nvme_init_non_mdts_limits(struct nvme_ctrl *ctrl) if (id->dmrl) ctrl->max_discard_segments = id->dmrl; - if (id->dmrsl) - ctrl->max_discard_sectors = le32_to_cpu(id->dmrsl); + ctrl->dmrsl = le32_to_cpu(id->dmrsl); if (id->wzsl) ctrl->max_zeroes_sectors = nvme_mps_to_sectors(ctrl, id->wzsl); @@ -3067,10 +3129,6 @@ int nvme_init_ctrl_finish(struct nvme_ctrl *ctrl) if (ret) return ret; - ret = nvme_init_non_mdts_limits(ctrl); - if (ret < 0) - return ret; - ret = nvme_configure_apst(ctrl); if (ret < 0) return ret; @@ -3133,6 +3191,7 @@ static const struct file_operations nvme_dev_fops = { .release = nvme_dev_release, .unlocked_ioctl = nvme_dev_ioctl, .compat_ioctl = compat_ptr_ioctl, + .uring_cmd = nvme_dev_uring_cmd, }; static ssize_t nvme_sysfs_reset(struct device *dev, @@ -3686,6 +3745,7 @@ static const struct file_operations nvme_ns_chr_fops = { .release = nvme_ns_chr_release, .unlocked_ioctl = nvme_ns_chr_ioctl, .compat_ioctl = compat_ptr_ioctl, + .uring_cmd = nvme_ns_chr_uring_cmd, }; static int nvme_add_ns_cdev(struct nvme_ns *ns) @@ -4077,11 +4137,26 @@ out: static void nvme_validate_or_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) { struct nvme_ns_ids ids = { }; + struct nvme_id_ns_cs_indep *id; struct nvme_ns *ns; + bool ready = true; if (nvme_identify_ns_descs(ctrl, nsid, &ids)) return; + /* + * Check if the namespace is ready. If not ignore it, we will get an + * AEN once it becomes ready and restart the scan. + */ + if ((ctrl->cap & NVME_CAP_CRMS_CRIMS) && + !nvme_identify_ns_cs_indep(ctrl, nsid, &id)) { + ready = id->nstat & NVME_NSTAT_NRDY; + kfree(id); + } + + if (!ready) + return; + ns = nvme_find_get_ns(ctrl, nsid); if (ns) { nvme_validate_ns(ns, &ids); @@ -4224,11 +4299,26 @@ static void nvme_scan_work(struct work_struct *work) { struct nvme_ctrl *ctrl = container_of(work, struct nvme_ctrl, scan_work); + int ret; /* No tagset on a live ctrl means IO queues could not created */ if (ctrl->state != NVME_CTRL_LIVE || !ctrl->tagset) return; + /* + * Identify controller limits can change at controller reset due to + * new firmware download, even though it is not common we cannot ignore + * such scenario. Controller's non-mdts limits are reported in the unit + * of logical blocks that is dependent on the format of attached + * namespace. Hence re-read the limits at the time of ns allocation. + */ + ret = nvme_init_non_mdts_limits(ctrl); + if (ret < 0) { + dev_warn(ctrl->device, + "reading non-mdts-limits failed: %d\n", ret); + return; + } + if (test_and_clear_bit(NVME_AER_NOTICE_NS_CHANGED, &ctrl->events)) { dev_info(ctrl->device, "rescanning namespaces.\n"); nvme_clear_changed_ns_log(ctrl); @@ -4826,6 +4916,8 @@ static inline void _nvme_check_size(void) BUILD_BUG_ON(sizeof(struct nvme_command) != 64); BUILD_BUG_ON(sizeof(struct nvme_id_ctrl) != NVME_IDENTIFY_DATA_SIZE); BUILD_BUG_ON(sizeof(struct nvme_id_ns) != NVME_IDENTIFY_DATA_SIZE); + BUILD_BUG_ON(sizeof(struct nvme_id_ns_cs_indep) != + NVME_IDENTIFY_DATA_SIZE); BUILD_BUG_ON(sizeof(struct nvme_id_ns_zns) != NVME_IDENTIFY_DATA_SIZE); BUILD_BUG_ON(sizeof(struct nvme_id_ns_nvm) != NVME_IDENTIFY_DATA_SIZE); BUILD_BUG_ON(sizeof(struct nvme_id_ctrl_zns) != NVME_IDENTIFY_DATA_SIZE); diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h index 1e3a09cad961..46d6e194ac2b 100644 --- a/drivers/nvme/host/fabrics.h +++ b/drivers/nvme/host/fabrics.h @@ -187,6 +187,14 @@ static inline char *nvmf_ctrl_subsysnqn(struct nvme_ctrl *ctrl) return ctrl->subsys->subnqn; } +static inline void nvmf_complete_timed_out_request(struct request *rq) +{ + if (blk_mq_request_started(rq) && !blk_mq_request_completed(rq)) { + nvme_req(rq)->status = NVME_SC_HOST_ABORTED_CMD; + blk_mq_complete_request(rq); + } +} + int nvmf_reg_read32(struct nvme_ctrl *ctrl, u32 off, u32 *val); int nvmf_reg_read64(struct nvme_ctrl *ctrl, u32 off, u64 *val); int nvmf_reg_write32(struct nvme_ctrl *ctrl, u32 off, u32 val); diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 080f85f4105f..7ae72c7a211b 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -3831,6 +3831,9 @@ process_local_list: return count; } +static DEVICE_ATTR(nvme_discovery, 0200, NULL, nvme_fc_nvme_discovery_store); + +#ifdef CONFIG_BLK_CGROUP_FC_APPID /* Parse the cgroup id from a buf and return the length of cgrpid */ static int fc_parse_cgrpid(const char *buf, u64 *id) { @@ -3854,12 +3857,10 @@ static int fc_parse_cgrpid(const char *buf, u64 *id) } /* - * fc_update_appid: Parse and update the appid in the blkcg associated with - * cgroupid. - * @buf: buf contains both cgrpid and appid info - * @count: size of the buffer + * Parse and update the appid in the blkcg associated with the cgroupid. */ -static int fc_update_appid(const char *buf, size_t count) +static ssize_t fc_appid_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t count) { u64 cgrp_id; int appid_len = 0; @@ -3887,23 +3888,14 @@ static int fc_update_appid(const char *buf, size_t count) return ret; return count; } - -static ssize_t fc_appid_store(struct device *dev, - struct device_attribute *attr, const char *buf, size_t count) -{ - int ret = 0; - - ret = fc_update_appid(buf, count); - if (ret < 0) - return -EINVAL; - return count; -} -static DEVICE_ATTR(nvme_discovery, 0200, NULL, nvme_fc_nvme_discovery_store); static DEVICE_ATTR(appid_store, 0200, NULL, fc_appid_store); +#endif /* CONFIG_BLK_CGROUP_FC_APPID */ static struct attribute *nvme_fc_attrs[] = { &dev_attr_nvme_discovery.attr, +#ifdef CONFIG_BLK_CGROUP_FC_APPID &dev_attr_appid_store.attr, +#endif NULL }; diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c index 554566371ffa..096b1b47d750 100644 --- a/drivers/nvme/host/ioctl.c +++ b/drivers/nvme/host/ioctl.c @@ -5,6 +5,7 @@ */ #include <linux/ptrace.h> /* for force_successful_syscall_return */ #include <linux/nvme_ioctl.h> +#include <linux/io_uring.h> #include "nvme.h" /* @@ -53,10 +54,21 @@ out: return ERR_PTR(ret); } -static int nvme_submit_user_cmd(struct request_queue *q, +static int nvme_finish_user_metadata(struct request *req, void __user *ubuf, + void *meta, unsigned len, int ret) +{ + if (!ret && req_op(req) == REQ_OP_DRV_IN && + copy_to_user(ubuf, meta, len)) + ret = -EFAULT; + kfree(meta); + return ret; +} + +static struct request *nvme_alloc_user_request(struct request_queue *q, struct nvme_command *cmd, void __user *ubuffer, unsigned bufflen, void __user *meta_buffer, unsigned meta_len, - u32 meta_seed, u64 *result, unsigned timeout, bool vec) + u32 meta_seed, void **metap, unsigned timeout, bool vec, + unsigned int rq_flags, blk_mq_req_flags_t blk_flags) { bool write = nvme_is_write(cmd); struct nvme_ns *ns = q->queuedata; @@ -66,9 +78,9 @@ static int nvme_submit_user_cmd(struct request_queue *q, void *meta = NULL; int ret; - req = blk_mq_alloc_request(q, nvme_req_op(cmd), 0); + req = blk_mq_alloc_request(q, nvme_req_op(cmd) | rq_flags, blk_flags); if (IS_ERR(req)) - return PTR_ERR(req); + return req; nvme_init_request(req, cmd); if (timeout) @@ -105,26 +117,50 @@ static int nvme_submit_user_cmd(struct request_queue *q, goto out_unmap; } req->cmd_flags |= REQ_INTEGRITY; + *metap = meta; } } + return req; + +out_unmap: + if (bio) + blk_rq_unmap_user(bio); +out: + blk_mq_free_request(req); + return ERR_PTR(ret); +} + +static int nvme_submit_user_cmd(struct request_queue *q, + struct nvme_command *cmd, void __user *ubuffer, + unsigned bufflen, void __user *meta_buffer, unsigned meta_len, + u32 meta_seed, u64 *result, unsigned timeout, bool vec) +{ + struct request *req; + void *meta = NULL; + struct bio *bio; + int ret; + + req = nvme_alloc_user_request(q, cmd, ubuffer, bufflen, meta_buffer, + meta_len, meta_seed, &meta, timeout, vec, 0, 0); + if (IS_ERR(req)) + return PTR_ERR(req); + + bio = req->bio; + ret = nvme_execute_passthru_rq(req); + if (result) *result = le64_to_cpu(nvme_req(req)->result.u64); - if (meta && !ret && !write) { - if (copy_to_user(meta_buffer, meta, meta_len)) - ret = -EFAULT; - } - kfree(meta); - out_unmap: + if (meta) + ret = nvme_finish_user_metadata(req, meta_buffer, meta, + meta_len, ret); if (bio) blk_rq_unmap_user(bio); - out: blk_mq_free_request(req); return ret; } - static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio) { struct nvme_user_io io; @@ -296,6 +332,139 @@ static int nvme_user_cmd64(struct nvme_ctrl *ctrl, struct nvme_ns *ns, return status; } +struct nvme_uring_data { + __u64 metadata; + __u64 addr; + __u32 data_len; + __u32 metadata_len; + __u32 timeout_ms; +}; + +/* + * This overlays struct io_uring_cmd pdu. + * Expect build errors if this grows larger than that. + */ +struct nvme_uring_cmd_pdu { + union { + struct bio *bio; + struct request *req; + }; + void *meta; /* kernel-resident buffer */ + void __user *meta_buffer; + u32 meta_len; +}; + +static inline struct nvme_uring_cmd_pdu *nvme_uring_cmd_pdu( + struct io_uring_cmd *ioucmd) +{ + return (struct nvme_uring_cmd_pdu *)&ioucmd->pdu; +} + +static void nvme_uring_task_cb(struct io_uring_cmd *ioucmd) +{ + struct nvme_uring_cmd_pdu *pdu = nvme_uring_cmd_pdu(ioucmd); + struct request *req = pdu->req; + struct bio *bio = req->bio; + int status; + u64 result; + + if (nvme_req(req)->flags & NVME_REQ_CANCELLED) + status = -EINTR; + else + status = nvme_req(req)->status; + + result = le64_to_cpu(nvme_req(req)->result.u64); + + if (pdu->meta) + status = nvme_finish_user_metadata(req, pdu->meta_buffer, + pdu->meta, pdu->meta_len, status); + if (bio) + blk_rq_unmap_user(bio); + blk_mq_free_request(req); + + io_uring_cmd_done(ioucmd, status, result); +} + +static void nvme_uring_cmd_end_io(struct request *req, blk_status_t err) +{ + struct io_uring_cmd *ioucmd = req->end_io_data; + struct nvme_uring_cmd_pdu *pdu = nvme_uring_cmd_pdu(ioucmd); + /* extract bio before reusing the same field for request */ + struct bio *bio = pdu->bio; + + pdu->req = req; + req->bio = bio; + /* this takes care of moving rest of completion-work to task context */ + io_uring_cmd_complete_in_task(ioucmd, nvme_uring_task_cb); +} + +static int nvme_uring_cmd_io(struct nvme_ctrl *ctrl, struct nvme_ns *ns, + struct io_uring_cmd *ioucmd, unsigned int issue_flags, bool vec) +{ + struct nvme_uring_cmd_pdu *pdu = nvme_uring_cmd_pdu(ioucmd); + const struct nvme_uring_cmd *cmd = ioucmd->cmd; + struct request_queue *q = ns ? ns->queue : ctrl->admin_q; + struct nvme_uring_data d; + struct nvme_command c; + struct request *req; + unsigned int rq_flags = 0; + blk_mq_req_flags_t blk_flags = 0; + void *meta = NULL; + + if (!capable(CAP_SYS_ADMIN)) + return -EACCES; + + c.common.opcode = READ_ONCE(cmd->opcode); + c.common.flags = READ_ONCE(cmd->flags); + if (c.common.flags) + return -EINVAL; + + c.common.command_id = 0; + c.common.nsid = cpu_to_le32(cmd->nsid); + if (!nvme_validate_passthru_nsid(ctrl, ns, le32_to_cpu(c.common.nsid))) + return -EINVAL; + + c.common.cdw2[0] = cpu_to_le32(READ_ONCE(cmd->cdw2)); + c.common.cdw2[1] = cpu_to_le32(READ_ONCE(cmd->cdw3)); + c.common.metadata = 0; + c.common.dptr.prp1 = c.common.dptr.prp2 = 0; + c.common.cdw10 = cpu_to_le32(READ_ONCE(cmd->cdw10)); + c.common.cdw11 = cpu_to_le32(READ_ONCE(cmd->cdw11)); + c.common.cdw12 = cpu_to_le32(READ_ONCE(cmd->cdw12)); + c.common.cdw13 = cpu_to_le32(READ_ONCE(cmd->cdw13)); + c.common.cdw14 = cpu_to_le32(READ_ONCE(cmd->cdw14)); + c.common.cdw15 = cpu_to_le32(READ_ONCE(cmd->cdw15)); + + d.metadata = READ_ONCE(cmd->metadata); + d.addr = READ_ONCE(cmd->addr); + d.data_len = READ_ONCE(cmd->data_len); + d.metadata_len = READ_ONCE(cmd->metadata_len); + d.timeout_ms = READ_ONCE(cmd->timeout_ms); + + if (issue_flags & IO_URING_F_NONBLOCK) { + rq_flags = REQ_NOWAIT; + blk_flags = BLK_MQ_REQ_NOWAIT; + } + + req = nvme_alloc_user_request(q, &c, nvme_to_user_ptr(d.addr), + d.data_len, nvme_to_user_ptr(d.metadata), + d.metadata_len, 0, &meta, d.timeout_ms ? + msecs_to_jiffies(d.timeout_ms) : 0, vec, rq_flags, + blk_flags); + if (IS_ERR(req)) + return PTR_ERR(req); + req->end_io_data = ioucmd; + + /* to free bio on completion, as req->bio will be null at that time */ + pdu->bio = req->bio; + pdu->meta = meta; + pdu->meta_buffer = nvme_to_user_ptr(d.metadata); + pdu->meta_len = d.metadata_len; + + blk_execute_rq_nowait(req, 0, nvme_uring_cmd_end_io); + return -EIOCBQUEUED; +} + static bool is_ctrl_ioctl(unsigned int cmd) { if (cmd == NVME_IOCTL_ADMIN_CMD || cmd == NVME_IOCTL_ADMIN64_CMD) @@ -387,6 +556,53 @@ long nvme_ns_chr_ioctl(struct file *file, unsigned int cmd, unsigned long arg) return __nvme_ioctl(ns, cmd, (void __user *)arg); } +static int nvme_uring_cmd_checks(unsigned int issue_flags) +{ + /* IOPOLL not supported yet */ + if (issue_flags & IO_URING_F_IOPOLL) + return -EOPNOTSUPP; + + /* NVMe passthrough requires big SQE/CQE support */ + if ((issue_flags & (IO_URING_F_SQE128|IO_URING_F_CQE32)) != + (IO_URING_F_SQE128|IO_URING_F_CQE32)) + return -EOPNOTSUPP; + return 0; +} + +static int nvme_ns_uring_cmd(struct nvme_ns *ns, struct io_uring_cmd *ioucmd, + unsigned int issue_flags) +{ + struct nvme_ctrl *ctrl = ns->ctrl; + int ret; + + BUILD_BUG_ON(sizeof(struct nvme_uring_cmd_pdu) > sizeof(ioucmd->pdu)); + + ret = nvme_uring_cmd_checks(issue_flags); + if (ret) + return ret; + + switch (ioucmd->cmd_op) { + case NVME_URING_CMD_IO: + ret = nvme_uring_cmd_io(ctrl, ns, ioucmd, issue_flags, false); + break; + case NVME_URING_CMD_IO_VEC: + ret = nvme_uring_cmd_io(ctrl, ns, ioucmd, issue_flags, true); + break; + default: + ret = -ENOTTY; + } + + return ret; +} + +int nvme_ns_chr_uring_cmd(struct io_uring_cmd *ioucmd, unsigned int issue_flags) +{ + struct nvme_ns *ns = container_of(file_inode(ioucmd->file)->i_cdev, + struct nvme_ns, cdev); + + return nvme_ns_uring_cmd(ns, ioucmd, issue_flags); +} + #ifdef CONFIG_NVME_MULTIPATH static int nvme_ns_head_ctrl_ioctl(struct nvme_ns *ns, unsigned int cmd, void __user *argp, struct nvme_ns_head *head, int srcu_idx) @@ -453,8 +669,46 @@ out_unlock: srcu_read_unlock(&head->srcu, srcu_idx); return ret; } + +int nvme_ns_head_chr_uring_cmd(struct io_uring_cmd *ioucmd, + unsigned int issue_flags) +{ + struct cdev *cdev = file_inode(ioucmd->file)->i_cdev; + struct nvme_ns_head *head = container_of(cdev, struct nvme_ns_head, cdev); + int srcu_idx = srcu_read_lock(&head->srcu); + struct nvme_ns *ns = nvme_find_path(head); + int ret = -EINVAL; + + if (ns) + ret = nvme_ns_uring_cmd(ns, ioucmd, issue_flags); + srcu_read_unlock(&head->srcu, srcu_idx); + return ret; +} #endif /* CONFIG_NVME_MULTIPATH */ +int nvme_dev_uring_cmd(struct io_uring_cmd *ioucmd, unsigned int issue_flags) +{ + struct nvme_ctrl *ctrl = ioucmd->file->private_data; + int ret; + + ret = nvme_uring_cmd_checks(issue_flags); + if (ret) + return ret; + + switch (ioucmd->cmd_op) { + case NVME_URING_CMD_ADMIN: + ret = nvme_uring_cmd_io(ctrl, NULL, ioucmd, issue_flags, false); + break; + case NVME_URING_CMD_ADMIN_VEC: + ret = nvme_uring_cmd_io(ctrl, NULL, ioucmd, issue_flags, true); + break; + default: + ret = -ENOTTY; + } + + return ret; +} + static int nvme_dev_user_cmd(struct nvme_ctrl *ctrl, void __user *argp) { struct nvme_ns *ns; diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index d464fdf978fb..d3e2440d8abb 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -437,6 +437,7 @@ static const struct file_operations nvme_ns_head_chr_fops = { .release = nvme_ns_head_chr_release, .unlocked_ioctl = nvme_ns_head_chr_ioctl, .compat_ioctl = compat_ptr_ioctl, + .uring_cmd = nvme_ns_head_chr_uring_cmd, }; static int nvme_add_ns_head_cdev(struct nvme_ns_head *head) diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 1393bbf82d71..9b72b6ecf33c 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -144,6 +144,11 @@ enum nvme_quirks { * encoding the generation sequence number. */ NVME_QUIRK_SKIP_CID_GEN = (1 << 17), + + /* + * Reports garbage in the namespace identifiers (eui64, nguid, uuid). + */ + NVME_QUIRK_BOGUS_NID = (1 << 18), }; /* @@ -279,6 +284,7 @@ struct nvme_ctrl { #endif u16 crdt[3]; u16 oncs; + u32 dmrsl; u16 oacs; u16 sqsize; u32 max_namespaces; @@ -777,7 +783,12 @@ long nvme_ns_head_chr_ioctl(struct file *file, unsigned int cmd, unsigned long arg); long nvme_dev_ioctl(struct file *file, unsigned int cmd, unsigned long arg); +int nvme_ns_chr_uring_cmd(struct io_uring_cmd *ioucmd, + unsigned int issue_flags); +int nvme_ns_head_chr_uring_cmd(struct io_uring_cmd *ioucmd, + unsigned int issue_flags); int nvme_getgeo(struct block_device *bdev, struct hd_geometry *geo); +int nvme_dev_uring_cmd(struct io_uring_cmd *ioucmd, unsigned int issue_flags); extern const struct attribute_group *nvme_ns_id_attr_groups[]; extern const struct pr_ops nvme_pr_ops; diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index d817ca17463e..5a98a7de0964 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -1439,6 +1439,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved) nvme_init_request(abort_req, &cmd); abort_req->end_io_data = NULL; + abort_req->rq_flags |= RQF_QUIET; blk_execute_rq_nowait(abort_req, false, abort_endio); /* @@ -1775,6 +1776,7 @@ static int nvme_alloc_admin_tags(struct nvme_dev *dev) dev->ctrl.admin_q = blk_mq_init_queue(&dev->admin_tagset); if (IS_ERR(dev->ctrl.admin_q)) { blk_mq_free_tag_set(&dev->admin_tagset); + dev->ctrl.admin_q = NULL; return -ENOMEM; } if (!blk_get_queue(dev->ctrl.admin_q)) { @@ -2486,6 +2488,7 @@ static int nvme_delete_queue(struct nvme_queue *nvmeq, u8 opcode) req->end_io_data = nvmeq; init_completion(&nvmeq->delete_done); + req->rq_flags |= RQF_QUIET; blk_execute_rq_nowait(req, false, opcode == nvme_admin_delete_cq ? nvme_del_cq_end : nvme_del_queue_end); return 0; @@ -2675,7 +2678,7 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown) struct pci_dev *pdev = to_pci_dev(dev->dev); mutex_lock(&dev->shutdown_lock); - if (pci_is_enabled(pdev)) { + if (pci_device_is_present(pdev) && pci_is_enabled(pdev)) { u32 csts = readl(dev->bar + NVME_REG_CSTS); if (dev->ctrl.state == NVME_CTRL_LIVE || @@ -3409,7 +3412,10 @@ static const struct pci_device_id nvme_id_table[] = { .driver_data = NVME_QUIRK_IGNORE_DEV_SUBNQN, }, { PCI_VDEVICE(INTEL, 0x5845), /* Qemu emulated controller */ .driver_data = NVME_QUIRK_IDENTIFY_CNS | - NVME_QUIRK_DISABLE_WRITE_ZEROES, }, + NVME_QUIRK_DISABLE_WRITE_ZEROES | + NVME_QUIRK_BOGUS_NID, }, + { PCI_VDEVICE(REDHAT, 0x0010), /* Qemu emulated controller */ + .driver_data = NVME_QUIRK_BOGUS_NID, }, { PCI_DEVICE(0x126f, 0x2263), /* Silicon Motion unidentified */ .driver_data = NVME_QUIRK_NO_NS_DESC_LIST, }, { PCI_DEVICE(0x1bb1, 0x0100), /* Seagate Nytro Flash Storage */ @@ -3447,6 +3453,10 @@ static const struct pci_device_id nvme_id_table[] = { .driver_data = NVME_QUIRK_NO_DEEPEST_PS, }, { PCI_DEVICE(0x2646, 0x2263), /* KINGSTON A2000 NVMe SSD */ .driver_data = NVME_QUIRK_NO_DEEPEST_PS, }, + { PCI_DEVICE(0x1e4B, 0x1002), /* MAXIO MAP1002 */ + .driver_data = NVME_QUIRK_BOGUS_NID, }, + { PCI_DEVICE(0x1e4B, 0x1202), /* MAXIO MAP1202 */ + .driver_data = NVME_QUIRK_BOGUS_NID, }, { PCI_DEVICE(PCI_VENDOR_ID_AMAZON, 0x0061), .driver_data = NVME_QUIRK_DMA_ADDRESS_BITS_48, }, { PCI_DEVICE(PCI_VENDOR_ID_AMAZON, 0x0065), diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index d9f19d901313..b87c8ae41d9b 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -2010,10 +2010,7 @@ static void nvme_rdma_complete_timed_out(struct request *rq) struct nvme_rdma_queue *queue = req->queue; nvme_rdma_stop_queue(queue); - if (blk_mq_request_started(rq) && !blk_mq_request_completed(rq)) { - nvme_req(rq)->status = NVME_SC_HOST_ABORTED_CMD; - blk_mq_complete_request(rq); - } + nvmf_complete_timed_out_request(rq); } static enum blk_eh_timer_return diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index ad3a2bf2f1e9..bb67538d241b 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -2318,10 +2318,7 @@ static void nvme_tcp_complete_timed_out(struct request *rq) struct nvme_ctrl *ctrl = &req->queue->ctrl->ctrl; nvme_tcp_stop_queue(ctrl, nvme_tcp_queue_id(req->queue)); - if (blk_mq_request_started(rq) && !blk_mq_request_completed(rq)) { - nvme_req(rq)->status = NVME_SC_HOST_ABORTED_CMD; - blk_mq_complete_request(rq); - } + nvmf_complete_timed_out_request(rq); } static enum blk_eh_timer_return diff --git a/drivers/nvme/target/io-cmd-bdev.c b/drivers/nvme/target/io-cmd-bdev.c index d886c2c59554..27a72504d31c 100644 --- a/drivers/nvme/target/io-cmd-bdev.c +++ b/drivers/nvme/target/io-cmd-bdev.c @@ -360,7 +360,7 @@ static u16 nvmet_bdev_discard_range(struct nvmet_req *req, ret = __blkdev_issue_discard(ns->bdev, nvmet_lba_to_sect(ns, range->slba), le32_to_cpu(range->nlb) << (ns->blksize_shift - 9), - GFP_KERNEL, 0, bio); + GFP_KERNEL, bio); if (ret && ret != -EOPNOTSUPP) { req->error_slba = le64_to_cpu(range->slba); return errno_to_nvme_status(req, ret); diff --git a/drivers/nvme/target/zns.c b/drivers/nvme/target/zns.c index e34718b09550..82b61acf7a72 100644 --- a/drivers/nvme/target/zns.c +++ b/drivers/nvme/target/zns.c @@ -34,8 +34,7 @@ static int validate_conv_zones_cb(struct blk_zone *z, bool nvmet_bdev_zns_enable(struct nvmet_ns *ns) { - struct request_queue *q = ns->bdev->bd_disk->queue; - u8 zasl = nvmet_zasl(queue_max_zone_append_sectors(q)); + u8 zasl = nvmet_zasl(bdev_max_zone_append_sectors(ns->bdev)); struct gendisk *bd_disk = ns->bdev->bd_disk; int ret; diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c index ec315b060cd5..2f248d0acc04 100644 --- a/drivers/of/fdt.c +++ b/drivers/of/fdt.c @@ -973,16 +973,24 @@ static void __init early_init_dt_check_for_elfcorehdr(unsigned long node) static unsigned long chosen_node_offset = -FDT_ERR_NOTFOUND; +/* + * The main usage of linux,usable-memory-range is for crash dump kernel. + * Originally, the number of usable-memory regions is one. Now there may + * be two regions, low region and high region. + * To make compatibility with existing user-space and older kdump, the low + * region is always the last range of linux,usable-memory-range if exist. + */ +#define MAX_USABLE_RANGES 2 + /** * early_init_dt_check_for_usable_mem_range - Decode usable memory range * location from flat tree */ void __init early_init_dt_check_for_usable_mem_range(void) { - const __be32 *prop; - int len; - phys_addr_t cap_mem_addr; - phys_addr_t cap_mem_size; + struct memblock_region rgn[MAX_USABLE_RANGES] = {0}; + const __be32 *prop, *endp; + int len, i; unsigned long node = chosen_node_offset; if ((long)node < 0) @@ -991,16 +999,21 @@ void __init early_init_dt_check_for_usable_mem_range(void) pr_debug("Looking for usable-memory-range property... "); prop = of_get_flat_dt_prop(node, "linux,usable-memory-range", &len); - if (!prop || (len < (dt_root_addr_cells + dt_root_size_cells))) + if (!prop || (len % (dt_root_addr_cells + dt_root_size_cells))) return; - cap_mem_addr = dt_mem_next_cell(dt_root_addr_cells, &prop); - cap_mem_size = dt_mem_next_cell(dt_root_size_cells, &prop); + endp = prop + (len / sizeof(__be32)); + for (i = 0; i < MAX_USABLE_RANGES && prop < endp; i++) { + rgn[i].base = dt_mem_next_cell(dt_root_addr_cells, &prop); + rgn[i].size = dt_mem_next_cell(dt_root_size_cells, &prop); - pr_debug("cap_mem_start=%pa cap_mem_size=%pa\n", &cap_mem_addr, - &cap_mem_size); + pr_debug("cap_mem_regions[%d]: base=%pa, size=%pa\n", + i, &rgn[i].base, &rgn[i].size); + } - memblock_cap_memory_range(cap_mem_addr, cap_mem_size); + memblock_cap_memory_range(rgn[0].base, rgn[0].size); + for (i = 1; i < MAX_USABLE_RANGES && rgn[i].size; i++) + memblock_add(rgn[i].base, rgn[i].size); } #ifdef CONFIG_SERIAL_EARLYCON diff --git a/drivers/of/kexec.c b/drivers/of/kexec.c index b9bd1cff1793..8d374cc552be 100644 --- a/drivers/of/kexec.c +++ b/drivers/of/kexec.c @@ -386,6 +386,15 @@ void *of_kexec_alloc_and_setup_fdt(const struct kimage *image, crashk_res.end - crashk_res.start + 1); if (ret) goto out; + + if (crashk_low_res.end) { + ret = fdt_appendprop_addrrange(fdt, 0, chosen_node, + "linux,usable-memory-range", + crashk_low_res.start, + crashk_low_res.end - crashk_low_res.start + 1); + if (ret) + goto out; + } } /* add bootargs */ diff --git a/drivers/of/platform.c b/drivers/of/platform.c index a16b74f32aa9..55d62b82c650 100644 --- a/drivers/of/platform.c +++ b/drivers/of/platform.c @@ -509,6 +509,7 @@ EXPORT_SYMBOL_GPL(of_platform_default_populate); #ifndef CONFIG_PPC static const struct of_device_id reserved_mem_matches[] = { + { .compatible = "phram" }, { .compatible = "qcom,rmtfs-mem" }, { .compatible = "qcom,cmd-db" }, { .compatible = "qcom,smem" }, diff --git a/drivers/of/property.c b/drivers/of/property.c index 8e90071de6ed..9a50ad25906e 100644 --- a/drivers/of/property.c +++ b/drivers/of/property.c @@ -22,6 +22,7 @@ #define pr_fmt(fmt) "OF: " fmt #include <linux/of.h> +#include <linux/of_address.h> #include <linux/of_device.h> #include <linux/of_graph.h> #include <linux/of_irq.h> @@ -872,6 +873,20 @@ static bool of_fwnode_device_is_available(const struct fwnode_handle *fwnode) return of_device_is_available(to_of_node(fwnode)); } +static bool of_fwnode_device_dma_supported(const struct fwnode_handle *fwnode) +{ + return true; +} + +static enum dev_dma_attr +of_fwnode_device_get_dma_attr(const struct fwnode_handle *fwnode) +{ + if (of_dma_is_coherent(to_of_node(fwnode))) + return DEV_DMA_COHERENT; + else + return DEV_DMA_NON_COHERENT; +} + static bool of_fwnode_property_present(const struct fwnode_handle *fwnode, const char *propname) { @@ -1450,6 +1465,21 @@ static int of_link_property(struct device_node *con_np, const char *prop_name) return 0; } +static void __iomem *of_fwnode_iomap(struct fwnode_handle *fwnode, int index) +{ +#ifdef CONFIG_OF_ADDRESS + return of_iomap(to_of_node(fwnode), index); +#else + return NULL; +#endif +} + +static int of_fwnode_irq_get(const struct fwnode_handle *fwnode, + unsigned int index) +{ + return of_irq_get(to_of_node(fwnode), index); +} + static int of_fwnode_add_links(struct fwnode_handle *fwnode) { struct property *p; @@ -1472,6 +1502,8 @@ const struct fwnode_operations of_fwnode_ops = { .put = of_fwnode_put, .device_is_available = of_fwnode_device_is_available, .device_get_match_data = of_fwnode_device_get_match_data, + .device_dma_supported = of_fwnode_device_dma_supported, + .device_get_dma_attr = of_fwnode_device_get_dma_attr, .property_present = of_fwnode_property_present, .property_read_int_array = of_fwnode_property_read_int_array, .property_read_string_array = of_fwnode_property_read_string_array, @@ -1485,6 +1517,8 @@ const struct fwnode_operations of_fwnode_ops = { .graph_get_remote_endpoint = of_fwnode_graph_get_remote_endpoint, .graph_get_port_parent = of_fwnode_graph_get_port_parent, .graph_parse_endpoint = of_fwnode_graph_parse_endpoint, + .iomap = of_fwnode_iomap, + .irq_get = of_fwnode_irq_get, .add_links = of_fwnode_add_links, }; EXPORT_SYMBOL_GPL(of_fwnode_ops); diff --git a/drivers/opp/of.c b/drivers/opp/of.c index 440ab5a03df9..485ea980bde7 100644 --- a/drivers/opp/of.c +++ b/drivers/opp/of.c @@ -1448,7 +1448,7 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_of_node); * Returns 0 on success or a proper -EINVAL value in case of error. */ static int __maybe_unused -_get_dt_power(unsigned long *mW, unsigned long *kHz, struct device *dev) +_get_dt_power(struct device *dev, unsigned long *mW, unsigned long *kHz) { struct dev_pm_opp *opp; unsigned long opp_freq, opp_power; @@ -1482,8 +1482,8 @@ _get_dt_power(unsigned long *mW, unsigned long *kHz, struct device *dev) * Returns -EINVAL if the power calculation failed because of missing * parameters, 0 otherwise. */ -static int __maybe_unused _get_power(unsigned long *mW, unsigned long *kHz, - struct device *dev) +static int __maybe_unused _get_power(struct device *dev, unsigned long *mW, + unsigned long *kHz) { struct dev_pm_opp *opp; struct device_node *np; diff --git a/drivers/pci/controller/dwc/pcie-qcom.c b/drivers/pci/controller/dwc/pcie-qcom.c index 6ab90891801d..816028c0f6ed 100644 --- a/drivers/pci/controller/dwc/pcie-qcom.c +++ b/drivers/pci/controller/dwc/pcie-qcom.c @@ -1550,6 +1550,11 @@ static const struct qcom_pcie_cfg sc7280_cfg = { .pipe_clk_need_muxing = true, }; +static const struct qcom_pcie_cfg sc8180x_cfg = { + .ops = &ops_1_9_0, + .has_tbu_clk = true, +}; + static const struct dw_pcie_ops dw_pcie_ops = { .link_up = qcom_pcie_link_up, .start_link = qcom_pcie_start_link, @@ -1656,7 +1661,7 @@ static const struct of_device_id qcom_pcie_match[] = { { .compatible = "qcom,pcie-qcs404", .data = &ipq4019_cfg }, { .compatible = "qcom,pcie-sdm845", .data = &sdm845_cfg }, { .compatible = "qcom,pcie-sm8250", .data = &sm8250_cfg }, - { .compatible = "qcom,pcie-sc8180x", .data = &sm8250_cfg }, + { .compatible = "qcom,pcie-sc8180x", .data = &sc8180x_cfg }, { .compatible = "qcom,pcie-sm8450-pcie0", .data = &sm8450_pcie0_cfg }, { .compatible = "qcom,pcie-sm8450-pcie1", .data = &sm8450_pcie1_cfg }, { .compatible = "qcom,pcie-sc7280", .data = &sc7280_cfg }, diff --git a/drivers/pci/controller/pci-aardvark.c b/drivers/pci/controller/pci-aardvark.c index 09d9bf465d72..ffec82c8a523 100644 --- a/drivers/pci/controller/pci-aardvark.c +++ b/drivers/pci/controller/pci-aardvark.c @@ -272,7 +272,6 @@ struct advk_pcie { u32 actions; } wins[OB_WIN_COUNT]; u8 wins_count; - int irq; struct irq_domain *rp_irq_domain; struct irq_domain *irq_domain; struct irq_chip irq_chip; @@ -1570,26 +1569,21 @@ static void advk_pcie_handle_int(struct advk_pcie *pcie) } } -static void advk_pcie_irq_handler(struct irq_desc *desc) +static irqreturn_t advk_pcie_irq_handler(int irq, void *arg) { - struct advk_pcie *pcie = irq_desc_get_handler_data(desc); - struct irq_chip *chip = irq_desc_get_chip(desc); - u32 val, mask, status; + struct advk_pcie *pcie = arg; + u32 status; - chained_irq_enter(chip, desc); + status = advk_readl(pcie, HOST_CTRL_INT_STATUS_REG); + if (!(status & PCIE_IRQ_CORE_INT)) + return IRQ_NONE; - val = advk_readl(pcie, HOST_CTRL_INT_STATUS_REG); - mask = advk_readl(pcie, HOST_CTRL_INT_MASK_REG); - status = val & ((~mask) & PCIE_IRQ_ALL_MASK); + advk_pcie_handle_int(pcie); - if (status & PCIE_IRQ_CORE_INT) { - advk_pcie_handle_int(pcie); + /* Clear interrupt */ + advk_writel(pcie, PCIE_IRQ_CORE_INT, HOST_CTRL_INT_STATUS_REG); - /* Clear interrupt */ - advk_writel(pcie, PCIE_IRQ_CORE_INT, HOST_CTRL_INT_STATUS_REG); - } - - chained_irq_exit(chip, desc); + return IRQ_HANDLED; } static int advk_pcie_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) @@ -1669,7 +1663,7 @@ static int advk_pcie_probe(struct platform_device *pdev) struct advk_pcie *pcie; struct pci_host_bridge *bridge; struct resource_entry *entry; - int ret; + int ret, irq; bridge = devm_pci_alloc_host_bridge(dev, sizeof(struct advk_pcie)); if (!bridge) @@ -1755,9 +1749,17 @@ static int advk_pcie_probe(struct platform_device *pdev) if (IS_ERR(pcie->base)) return PTR_ERR(pcie->base); - pcie->irq = platform_get_irq(pdev, 0); - if (pcie->irq < 0) - return pcie->irq; + irq = platform_get_irq(pdev, 0); + if (irq < 0) + return irq; + + ret = devm_request_irq(dev, irq, advk_pcie_irq_handler, + IRQF_SHARED | IRQF_NO_THREAD, "advk-pcie", + pcie); + if (ret) { + dev_err(dev, "Failed to register interrupt\n"); + return ret; + } pcie->reset_gpio = devm_gpiod_get_from_of_node(dev, dev->of_node, "reset-gpios", 0, @@ -1814,15 +1816,12 @@ static int advk_pcie_probe(struct platform_device *pdev) return ret; } - irq_set_chained_handler_and_data(pcie->irq, advk_pcie_irq_handler, pcie); - bridge->sysdata = pcie; bridge->ops = &advk_pcie_ops; bridge->map_irq = advk_pcie_map_irq; ret = pci_host_probe(bridge); if (ret < 0) { - irq_set_chained_handler_and_data(pcie->irq, NULL, NULL); advk_pcie_remove_rp_irq_domain(pcie); advk_pcie_remove_msi_irq_domain(pcie); advk_pcie_remove_irq_domain(pcie); @@ -1871,9 +1870,6 @@ static int advk_pcie_remove(struct platform_device *pdev) advk_writel(pcie, PCIE_ISR1_ALL_MASK, PCIE_ISR1_REG); advk_writel(pcie, PCIE_IRQ_ALL_MASK, HOST_CTRL_INT_STATUS_REG); - /* Remove IRQ handler */ - irq_set_chained_handler_and_data(pcie->irq, NULL, NULL); - /* Remove IRQ domains */ advk_pcie_remove_rp_irq_domain(pcie); advk_pcie_remove_msi_irq_domain(pcie); diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c index 558b35aba610..d270a204324e 100644 --- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -3407,6 +3407,15 @@ static int hv_pci_probe(struct hv_device *hdev, hbus->bridge->domain_nr = dom; #ifdef CONFIG_X86 hbus->sysdata.domain = dom; +#elif defined(CONFIG_ARM64) + /* + * Set the PCI bus parent to be the corresponding VMbus + * device. Then the VMbus device will be assigned as the + * ACPI companion in pcibios_root_bridge_prepare() and + * pci_dma_configure() will propagate device coherence + * information to devices created on the bus. + */ + hbus->sysdata.parent = hdev->device.parent; #endif hbus->hdev = hdev; diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c index 1f15ab7eabf8..3787876ecb24 100644 --- a/drivers/pci/pci-acpi.c +++ b/drivers/pci/pci-acpi.c @@ -1374,6 +1374,9 @@ void pci_acpi_setup(struct device *dev, struct acpi_device *adev) acpi_pci_wakeup(pci_dev, false); acpi_device_power_add_dependent(adev, dev); + + if (pci_is_bridge(pci_dev)) + acpi_dev_power_up_children_with_adr(adev); } void pci_acpi_cleanup(struct device *dev, struct acpi_device *adev) diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 9ecce435fb3f..d25122fbe98a 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -2920,6 +2920,16 @@ static const struct dmi_system_id bridge_d3_blacklist[] = { DMI_MATCH(DMI_BOARD_VENDOR, "Gigabyte Technology Co., Ltd."), DMI_MATCH(DMI_BOARD_NAME, "X299 DESIGNARE EX-CF"), }, + /* + * Downstream device is not accessible after putting a root port + * into D3cold and back into D0 on Elo i2. + */ + .ident = "Elo i2", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Elo Touch Solutions"), + DMI_MATCH(DMI_PRODUCT_NAME, "Elo i2"), + DMI_MATCH(DMI_PRODUCT_VERSION, "RevB"), + }, }, #endif { } diff --git a/drivers/pci/xen-pcifront.c b/drivers/pci/xen-pcifront.c index 3edc1565a27c..689271c4245c 100644 --- a/drivers/pci/xen-pcifront.c +++ b/drivers/pci/xen-pcifront.c @@ -709,9 +709,8 @@ static struct pcifront_device *alloc_pdev(struct xenbus_device *xdev) if (pdev == NULL) goto out; - pdev->sh_info = - (struct xen_pci_sharedinfo *)__get_free_page(GFP_KERNEL); - if (pdev->sh_info == NULL) { + if (xenbus_setup_ring(xdev, GFP_KERNEL, (void **)&pdev->sh_info, 1, + &pdev->gnt_ref)) { kfree(pdev); pdev = NULL; goto out; @@ -729,7 +728,6 @@ static struct pcifront_device *alloc_pdev(struct xenbus_device *xdev) spin_lock_init(&pdev->sh_info_lock); pdev->evtchn = INVALID_EVTCHN; - pdev->gnt_ref = INVALID_GRANT_REF; pdev->irq = -1; INIT_WORK(&pdev->op_work, pcifront_do_aer); @@ -754,11 +752,7 @@ static void free_pdev(struct pcifront_device *pdev) if (pdev->evtchn != INVALID_EVTCHN) xenbus_free_evtchn(pdev->xdev, pdev->evtchn); - if (pdev->gnt_ref != INVALID_GRANT_REF) - gnttab_end_foreign_access(pdev->gnt_ref, - (unsigned long)pdev->sh_info); - else - free_page((unsigned long)pdev->sh_info); + xenbus_teardown_ring((void **)&pdev->sh_info, 1, &pdev->gnt_ref); dev_set_drvdata(&pdev->xdev->dev, NULL); @@ -769,13 +763,6 @@ static int pcifront_publish_info(struct pcifront_device *pdev) { int err = 0; struct xenbus_transaction trans; - grant_ref_t gref; - - err = xenbus_grant_ring(pdev->xdev, pdev->sh_info, 1, &gref); - if (err < 0) - goto out; - - pdev->gnt_ref = gref; err = xenbus_alloc_evtchn(pdev->xdev, &pdev->evtchn); if (err) diff --git a/drivers/perf/Kconfig b/drivers/perf/Kconfig index afdcb91601d2..1e2d69453771 100644 --- a/drivers/perf/Kconfig +++ b/drivers/perf/Kconfig @@ -187,7 +187,7 @@ source "drivers/perf/hisilicon/Kconfig" config MARVELL_CN10K_DDR_PMU tristate "Enable MARVELL CN10K DRAM Subsystem(DSS) PMU Support" - depends on ARM64 || (COMPILE_TEST && 64BIT) + depends on ARCH_THUNDER || (COMPILE_TEST && 64BIT) help Enable perf support for Marvell DDR Performance monitoring event on CN10K platform. diff --git a/drivers/perf/arm-cmn.c b/drivers/perf/arm-cmn.c index 9c1d82be7a2f..80d8309652a4 100644 --- a/drivers/perf/arm-cmn.c +++ b/drivers/perf/arm-cmn.c @@ -39,7 +39,7 @@ #define CMN_CHILD_NODE_ADDR GENMASK(27, 0) #define CMN_CHILD_NODE_EXTERNAL BIT(31) -#define CMN_MAX_DIMENSION 8 +#define CMN_MAX_DIMENSION 12 #define CMN_MAX_XPS (CMN_MAX_DIMENSION * CMN_MAX_DIMENSION) #define CMN_MAX_DTMS (CMN_MAX_XPS + (CMN_MAX_DIMENSION - 1) * 4) @@ -52,6 +52,10 @@ #define CMN_INFO_RSP_VC_NUM GENMASK_ULL(53, 52) #define CMN_INFO_DAT_VC_NUM GENMASK_ULL(51, 50) +#define CMN_CFGM_INFO_GLOBAL_1 0x908 +#define CMN_INFO_SNP_VC_NUM GENMASK_ULL(3, 2) +#define CMN_INFO_REQ_VC_NUM GENMASK_ULL(1, 0) + /* XPs also have some local topology info which has uses too */ #define CMN_MXP__CONNECT_INFO_P0 0x0008 #define CMN_MXP__CONNECT_INFO_P1 0x0010 @@ -59,18 +63,26 @@ #define CMN_MXP__CONNECT_INFO_P3 0x0030 #define CMN_MXP__CONNECT_INFO_P4 0x0038 #define CMN_MXP__CONNECT_INFO_P5 0x0040 +#define CMN__CONNECT_INFO_DEVICE_TYPE GENMASK_ULL(4, 0) /* PMU registers occupy the 3rd 4KB page of each node's region */ #define CMN_PMU_OFFSET 0x2000 /* For most nodes, this is all there is */ #define CMN_PMU_EVENT_SEL 0x000 -#define CMN_PMU_EVENTn_ID_SHIFT(n) ((n) * 8) +#define CMN__PMU_CBUSY_SNTHROTTLE_SEL GENMASK_ULL(44, 42) +#define CMN__PMU_CLASS_OCCUP_ID GENMASK_ULL(36, 35) +/* Technically this is 4 bits wide on DNs, but we only use 2 there anyway */ +#define CMN__PMU_OCCUP1_ID GENMASK_ULL(34, 32) + +/* HN-Ps are weird... */ +#define CMN_HNP_PMU_EVENT_SEL 0x008 /* DTMs live in the PMU space of XP registers */ #define CMN_DTM_WPn(n) (0x1A0 + (n) * 0x18) #define CMN_DTM_WPn_CONFIG(n) (CMN_DTM_WPn(n) + 0x00) -#define CMN_DTM_WPn_CONFIG_WP_DEV_SEL2 GENMASK_ULL(18,17) +#define CMN_DTM_WPn_CONFIG_WP_CHN_NUM GENMASK_ULL(20, 19) +#define CMN_DTM_WPn_CONFIG_WP_DEV_SEL2 GENMASK_ULL(18, 17) #define CMN_DTM_WPn_CONFIG_WP_COMBINE BIT(9) #define CMN_DTM_WPn_CONFIG_WP_EXCLUSIVE BIT(8) #define CMN600_WPn_CONFIG_WP_COMBINE BIT(6) @@ -143,8 +155,8 @@ /* Event attributes */ #define CMN_CONFIG_TYPE GENMASK_ULL(15, 0) -#define CMN_CONFIG_EVENTID GENMASK_ULL(23, 16) -#define CMN_CONFIG_OCCUPID GENMASK_ULL(27, 24) +#define CMN_CONFIG_EVENTID GENMASK_ULL(26, 16) +#define CMN_CONFIG_OCCUPID GENMASK_ULL(30, 27) #define CMN_CONFIG_BYNODEID BIT_ULL(31) #define CMN_CONFIG_NODEID GENMASK_ULL(47, 32) @@ -177,9 +189,14 @@ enum cmn_model { - CMN_ANY = -1, CMN600 = 1, - CI700 = 2, + CMN650 = 2, + CMN700 = 4, + CI700 = 8, + /* ...and then we can use bitmap tricks for commonality */ + CMN_ANY = -1, + NOT_CMN600 = -2, + CMN_650ON = CMN650 | CMN700, }; /* CMN-600 r0px shouldn't exist in silicon, thankfully */ @@ -191,6 +208,14 @@ enum cmn_revision { CMN600_R2P0, CMN600_R3P0, CMN600_R3P1, + CMN650_R0P0 = 0, + CMN650_R1P0, + CMN650_R1P1, + CMN650_R2P0, + CMN650_R1P2, + CMN700_R0P0 = 0, + CMN700_R1P0, + CMN700_R2P0, CI700_R0P0 = 0, CI700_R1P0, CI700_R2P0, @@ -211,13 +236,26 @@ enum cmn_node_type { CMN_TYPE_RND = 0xd, CMN_TYPE_RNSAM = 0xf, CMN_TYPE_MTSX, + CMN_TYPE_HNP, CMN_TYPE_CXRA = 0x100, - CMN_TYPE_CXHA = 0x101, - CMN_TYPE_CXLA = 0x102, + CMN_TYPE_CXHA, + CMN_TYPE_CXLA, + CMN_TYPE_CCRA, + CMN_TYPE_CCHA, + CMN_TYPE_CCLA, + CMN_TYPE_CCLA_RNI, /* Not a real node type */ CMN_TYPE_WP = 0x7770 }; +enum cmn_filter_select { + SEL_NONE = -1, + SEL_OCCUP1ID, + SEL_CLASS_OCCUP_ID, + SEL_CBUSY_SNTHROTTLE_SEL, + SEL_MAX +}; + struct arm_cmn_node { void __iomem *pmu_base; u16 id, logid; @@ -227,15 +265,17 @@ struct arm_cmn_node { union { /* DN/HN-F/CXHA */ struct { - u8 occupid_val; - u8 occupid_count; - }; + u8 val : 4; + u8 count : 4; + } occupid[SEL_MAX]; /* XP */ u8 dtc; }; union { u8 event[4]; __le32 event_sel; + u16 event_w[4]; + __le64 event_sel_w; }; }; @@ -278,6 +318,8 @@ struct arm_cmn { struct { unsigned int rsp_vc_num : 2; unsigned int dat_vc_num : 2; + unsigned int snp_vc_num : 2; + unsigned int req_vc_num : 2; }; struct arm_cmn_node *xps; @@ -307,9 +349,7 @@ struct arm_cmn_nodeid { static int arm_cmn_xyidbits(const struct arm_cmn *cmn) { - int dim = max(cmn->mesh_x, cmn->mesh_y); - - return dim > 4 ? 3 : 2; + return fls((cmn->mesh_x - 1) | (cmn->mesh_y - 1) | 2); } static struct arm_cmn_nodeid arm_cmn_nid(const struct arm_cmn *cmn, u16 id) @@ -361,7 +401,8 @@ static struct dentry *arm_cmn_debugfs; #ifdef CONFIG_DEBUG_FS static const char *arm_cmn_device_type(u8 type) { - switch(type) { + switch(FIELD_GET(CMN__CONNECT_INFO_DEVICE_TYPE, type)) { + case 0x00: return " |"; case 0x01: return " RN-I |"; case 0x02: return " RN-D |"; case 0x04: return " RN-F_B |"; @@ -371,6 +412,7 @@ static const char *arm_cmn_device_type(u8 type) case 0x08: return " HN-T |"; case 0x09: return " HN-I |"; case 0x0a: return " HN-D |"; + case 0x0b: return " HN-P |"; case 0x0c: return " SN-F |"; case 0x0d: return " SBSX |"; case 0x0e: return " HN-F |"; @@ -383,8 +425,12 @@ static const char *arm_cmn_device_type(u8 type) case 0x15: return "RN-F_D_E|"; case 0x16: return " RN-F_C |"; case 0x17: return "RN-F_C_E|"; + case 0x18: return " RN-F_E |"; + case 0x19: return "RN-F_E_E|"; case 0x1c: return " MTSX |"; - default: return " |"; + case 0x1d: return " HN-V |"; + case 0x1e: return " CCG |"; + default: return " ???? |"; } } @@ -492,11 +538,13 @@ static void arm_cmn_debugfs_init(struct arm_cmn *cmn, int id) {} struct arm_cmn_hw_event { struct arm_cmn_node *dn; - u64 dtm_idx[2]; + u64 dtm_idx[4]; unsigned int dtc_idx; u8 dtcs_used; u8 num_dns; u8 dtm_offset; + bool wide_sel; + enum cmn_filter_select filter_sel; }; #define for_each_hw_dn(hw, dn, i) \ @@ -522,7 +570,8 @@ struct arm_cmn_event_attr { struct device_attribute attr; enum cmn_model model; enum cmn_node_type type; - u8 eventid; + enum cmn_filter_select fsel; + u16 eventid; u8 occupid; }; @@ -532,23 +581,17 @@ struct arm_cmn_format_attr { int config; }; -#define CMN_EVENT_ATTR(_model, _name, _type, _eventid, _occupid) \ +#define _CMN_EVENT_ATTR(_model, _name, _type, _eventid, _occupid, _fsel)\ (&((struct arm_cmn_event_attr[]) {{ \ .attr = __ATTR(_name, 0444, arm_cmn_event_show, NULL), \ .model = _model, \ .type = _type, \ .eventid = _eventid, \ .occupid = _occupid, \ + .fsel = _fsel, \ }})[0].attr.attr) - -static bool arm_cmn_is_occup_event(enum cmn_model model, - enum cmn_node_type type, unsigned int id) -{ - if (type == CMN_TYPE_DVM) - return (model == CMN600 && id == 0x05) || - (model == CI700 && id == 0x0c); - return type == CMN_TYPE_HNF && id == 0x0f; -} +#define CMN_EVENT_ATTR(_model, _name, _type, _eventid) \ + _CMN_EVENT_ATTR(_model, _name, _type, _eventid, 0, SEL_NONE) static ssize_t arm_cmn_event_show(struct device *dev, struct device_attribute *attr, char *buf) @@ -565,7 +608,7 @@ static ssize_t arm_cmn_event_show(struct device *dev, "type=0x%x,eventid=0x%x,wp_dev_sel=?,wp_chn_sel=?,wp_grp=?,wp_val=?,wp_mask=?\n", eattr->type, eattr->eventid); - if (arm_cmn_is_occup_event(eattr->model, eattr->type, eattr->eventid)) + if (eattr->fsel > SEL_NONE) return sysfs_emit(buf, "type=0x%x,eventid=0x%x,occupid=0x%x\n", eattr->type, eattr->eventid, eattr->occupid); @@ -580,20 +623,25 @@ static umode_t arm_cmn_event_attr_is_visible(struct kobject *kobj, struct device *dev = kobj_to_dev(kobj); struct arm_cmn *cmn = to_cmn(dev_get_drvdata(dev)); struct arm_cmn_event_attr *eattr; + enum cmn_node_type type; + u16 eventid; eattr = container_of(attr, typeof(*eattr), attr.attr); if (!(eattr->model & cmn->model)) return 0; + type = eattr->type; + eventid = eattr->eventid; + /* Watchpoints aren't nodes, so avoid confusion */ - if (eattr->type == CMN_TYPE_WP) + if (type == CMN_TYPE_WP) return attr->mode; /* Hide XP events for unused interfaces/channels */ - if (eattr->type == CMN_TYPE_XP) { - unsigned int intf = (eattr->eventid >> 2) & 7; - unsigned int chan = eattr->eventid >> 5; + if (type == CMN_TYPE_XP) { + unsigned int intf = (eventid >> 2) & 7; + unsigned int chan = eventid >> 5; if ((intf & 4) && !(cmn->ports_used & BIT(intf & 3))) return 0; @@ -602,43 +650,107 @@ static umode_t arm_cmn_event_attr_is_visible(struct kobject *kobj, return 0; if ((chan == 5 && cmn->rsp_vc_num < 2) || - (chan == 6 && cmn->dat_vc_num < 2)) + (chan == 6 && cmn->dat_vc_num < 2) || + (chan == 7 && cmn->snp_vc_num < 2) || + (chan == 8 && cmn->req_vc_num < 2)) return 0; } /* Revision-specific differences */ - if (cmn->model == CMN600 && cmn->rev < CMN600_R1P2) { - if (eattr->type == CMN_TYPE_HNF && eattr->eventid == 0x1b) - return 0; + if (cmn->model == CMN600) { + if (cmn->rev < CMN600_R1P3) { + if (type == CMN_TYPE_CXRA && eventid > 0x10) + return 0; + } + if (cmn->rev < CMN600_R1P2) { + if (type == CMN_TYPE_HNF && eventid == 0x1b) + return 0; + if (type == CMN_TYPE_CXRA || type == CMN_TYPE_CXHA) + return 0; + } + } else if (cmn->model == CMN650) { + if (cmn->rev < CMN650_R2P0 || cmn->rev == CMN650_R1P2) { + if (type == CMN_TYPE_HNF && eventid > 0x22) + return 0; + if (type == CMN_TYPE_SBSX && eventid == 0x17) + return 0; + if (type == CMN_TYPE_RNI && eventid > 0x10) + return 0; + } + } else if (cmn->model == CMN700) { + if (cmn->rev < CMN700_R2P0) { + if (type == CMN_TYPE_HNF && eventid > 0x2c) + return 0; + if (type == CMN_TYPE_CCHA && eventid > 0x74) + return 0; + if (type == CMN_TYPE_CCLA && eventid > 0x27) + return 0; + } + if (cmn->rev < CMN700_R1P0) { + if (type == CMN_TYPE_HNF && eventid > 0x2b) + return 0; + } } - if (!arm_cmn_node(cmn, eattr->type)) + if (!arm_cmn_node(cmn, type)) return 0; return attr->mode; } -#define _CMN_EVENT_DVM(_model, _name, _event, _occup) \ - CMN_EVENT_ATTR(_model, dn_##_name, CMN_TYPE_DVM, _event, _occup) +#define _CMN_EVENT_DVM(_model, _name, _event, _occup, _fsel) \ + _CMN_EVENT_ATTR(_model, dn_##_name, CMN_TYPE_DVM, _event, _occup, _fsel) #define CMN_EVENT_DTC(_name) \ - CMN_EVENT_ATTR(CMN_ANY, dtc_##_name, CMN_TYPE_DTC, 0, 0) -#define _CMN_EVENT_HNF(_model, _name, _event, _occup) \ - CMN_EVENT_ATTR(_model, hnf_##_name, CMN_TYPE_HNF, _event, _occup) + CMN_EVENT_ATTR(CMN_ANY, dtc_##_name, CMN_TYPE_DTC, 0) +#define _CMN_EVENT_HNF(_model, _name, _event, _occup, _fsel) \ + _CMN_EVENT_ATTR(_model, hnf_##_name, CMN_TYPE_HNF, _event, _occup, _fsel) #define CMN_EVENT_HNI(_name, _event) \ - CMN_EVENT_ATTR(CMN_ANY, hni_##_name, CMN_TYPE_HNI, _event, 0) + CMN_EVENT_ATTR(CMN_ANY, hni_##_name, CMN_TYPE_HNI, _event) +#define CMN_EVENT_HNP(_name, _event) \ + CMN_EVENT_ATTR(CMN_ANY, hnp_##_name, CMN_TYPE_HNP, _event) #define __CMN_EVENT_XP(_name, _event) \ - CMN_EVENT_ATTR(CMN_ANY, mxp_##_name, CMN_TYPE_XP, _event, 0) + CMN_EVENT_ATTR(CMN_ANY, mxp_##_name, CMN_TYPE_XP, _event) #define CMN_EVENT_SBSX(_model, _name, _event) \ - CMN_EVENT_ATTR(_model, sbsx_##_name, CMN_TYPE_SBSX, _event, 0) + CMN_EVENT_ATTR(_model, sbsx_##_name, CMN_TYPE_SBSX, _event) #define CMN_EVENT_RNID(_model, _name, _event) \ - CMN_EVENT_ATTR(_model, rnid_##_name, CMN_TYPE_RNI, _event, 0) + CMN_EVENT_ATTR(_model, rnid_##_name, CMN_TYPE_RNI, _event) #define CMN_EVENT_MTSX(_name, _event) \ - CMN_EVENT_ATTR(CMN_ANY, mtsx_##_name, CMN_TYPE_MTSX, _event, 0) + CMN_EVENT_ATTR(CMN_ANY, mtsx_##_name, CMN_TYPE_MTSX, _event) +#define CMN_EVENT_CXRA(_model, _name, _event) \ + CMN_EVENT_ATTR(_model, cxra_##_name, CMN_TYPE_CXRA, _event) +#define CMN_EVENT_CXHA(_name, _event) \ + CMN_EVENT_ATTR(CMN_ANY, cxha_##_name, CMN_TYPE_CXHA, _event) +#define CMN_EVENT_CCRA(_name, _event) \ + CMN_EVENT_ATTR(CMN_ANY, ccra_##_name, CMN_TYPE_CCRA, _event) +#define CMN_EVENT_CCHA(_name, _event) \ + CMN_EVENT_ATTR(CMN_ANY, ccha_##_name, CMN_TYPE_CCHA, _event) +#define CMN_EVENT_CCLA(_name, _event) \ + CMN_EVENT_ATTR(CMN_ANY, ccla_##_name, CMN_TYPE_CCLA, _event) +#define CMN_EVENT_CCLA_RNI(_name, _event) \ + CMN_EVENT_ATTR(CMN_ANY, ccla_rni_##_name, CMN_TYPE_CCLA_RNI, _event) #define CMN_EVENT_DVM(_model, _name, _event) \ - _CMN_EVENT_DVM(_model, _name, _event, 0) + _CMN_EVENT_DVM(_model, _name, _event, 0, SEL_NONE) +#define CMN_EVENT_DVM_OCC(_model, _name, _event) \ + _CMN_EVENT_DVM(_model, _name##_all, _event, 0, SEL_OCCUP1ID), \ + _CMN_EVENT_DVM(_model, _name##_dvmop, _event, 1, SEL_OCCUP1ID), \ + _CMN_EVENT_DVM(_model, _name##_dvmsync, _event, 2, SEL_OCCUP1ID) #define CMN_EVENT_HNF(_model, _name, _event) \ - _CMN_EVENT_HNF(_model, _name, _event, 0) + _CMN_EVENT_HNF(_model, _name, _event, 0, SEL_NONE) +#define CMN_EVENT_HNF_CLS(_model, _name, _event) \ + _CMN_EVENT_HNF(_model, _name##_class0, _event, 0, SEL_CLASS_OCCUP_ID), \ + _CMN_EVENT_HNF(_model, _name##_class1, _event, 1, SEL_CLASS_OCCUP_ID), \ + _CMN_EVENT_HNF(_model, _name##_class2, _event, 2, SEL_CLASS_OCCUP_ID), \ + _CMN_EVENT_HNF(_model, _name##_class3, _event, 3, SEL_CLASS_OCCUP_ID) +#define CMN_EVENT_HNF_SNT(_model, _name, _event) \ + _CMN_EVENT_HNF(_model, _name##_all, _event, 0, SEL_CBUSY_SNTHROTTLE_SEL), \ + _CMN_EVENT_HNF(_model, _name##_group0_read, _event, 1, SEL_CBUSY_SNTHROTTLE_SEL), \ + _CMN_EVENT_HNF(_model, _name##_group0_write, _event, 2, SEL_CBUSY_SNTHROTTLE_SEL), \ + _CMN_EVENT_HNF(_model, _name##_group1_read, _event, 3, SEL_CBUSY_SNTHROTTLE_SEL), \ + _CMN_EVENT_HNF(_model, _name##_group1_write, _event, 4, SEL_CBUSY_SNTHROTTLE_SEL), \ + _CMN_EVENT_HNF(_model, _name##_read, _event, 5, SEL_CBUSY_SNTHROTTLE_SEL), \ + _CMN_EVENT_HNF(_model, _name##_write, _event, 6, SEL_CBUSY_SNTHROTTLE_SEL) + #define _CMN_EVENT_XP(_name, _event) \ __CMN_EVENT_XP(e_##_name, (_event) | (0 << 2)), \ __CMN_EVENT_XP(w_##_name, (_event) | (1 << 2)), \ @@ -657,7 +769,9 @@ static umode_t arm_cmn_event_attr_is_visible(struct kobject *kobj, _CMN_EVENT_XP(dat_##_name, (_event) | (3 << 5)), \ _CMN_EVENT_XP(pub_##_name, (_event) | (4 << 5)), \ _CMN_EVENT_XP(rsp2_##_name, (_event) | (5 << 5)), \ - _CMN_EVENT_XP(dat2_##_name, (_event) | (6 << 5)) + _CMN_EVENT_XP(dat2_##_name, (_event) | (6 << 5)), \ + _CMN_EVENT_XP(snp2_##_name, (_event) | (7 << 5)), \ + _CMN_EVENT_XP(req2_##_name, (_event) | (8 << 5)) static struct attribute *arm_cmn_event_attrs[] = { @@ -672,23 +786,27 @@ static struct attribute *arm_cmn_event_attrs[] = { CMN_EVENT_DVM(CMN600, rxreq_dvmsync, 0x02), CMN_EVENT_DVM(CMN600, rxreq_dvmop_vmid_filtered, 0x03), CMN_EVENT_DVM(CMN600, rxreq_retried, 0x04), - _CMN_EVENT_DVM(CMN600, rxreq_trk_occupancy_all, 0x05, 0), - _CMN_EVENT_DVM(CMN600, rxreq_trk_occupancy_dvmop, 0x05, 1), - _CMN_EVENT_DVM(CMN600, rxreq_trk_occupancy_dvmsync, 0x05, 2), - CMN_EVENT_DVM(CI700, dvmop_tlbi, 0x01), - CMN_EVENT_DVM(CI700, dvmop_bpi, 0x02), - CMN_EVENT_DVM(CI700, dvmop_pici, 0x03), - CMN_EVENT_DVM(CI700, dvmop_vici, 0x04), - CMN_EVENT_DVM(CI700, dvmsync, 0x05), - CMN_EVENT_DVM(CI700, vmid_filtered, 0x06), - CMN_EVENT_DVM(CI700, rndop_filtered, 0x07), - CMN_EVENT_DVM(CI700, retry, 0x08), - CMN_EVENT_DVM(CI700, txsnp_flitv, 0x09), - CMN_EVENT_DVM(CI700, txsnp_stall, 0x0a), - CMN_EVENT_DVM(CI700, trkfull, 0x0b), - _CMN_EVENT_DVM(CI700, trk_occupancy_all, 0x0c, 0), - _CMN_EVENT_DVM(CI700, trk_occupancy_dvmop, 0x0c, 1), - _CMN_EVENT_DVM(CI700, trk_occupancy_dvmsync, 0x0c, 2), + CMN_EVENT_DVM_OCC(CMN600, rxreq_trk_occupancy, 0x05), + CMN_EVENT_DVM(NOT_CMN600, dvmop_tlbi, 0x01), + CMN_EVENT_DVM(NOT_CMN600, dvmop_bpi, 0x02), + CMN_EVENT_DVM(NOT_CMN600, dvmop_pici, 0x03), + CMN_EVENT_DVM(NOT_CMN600, dvmop_vici, 0x04), + CMN_EVENT_DVM(NOT_CMN600, dvmsync, 0x05), + CMN_EVENT_DVM(NOT_CMN600, vmid_filtered, 0x06), + CMN_EVENT_DVM(NOT_CMN600, rndop_filtered, 0x07), + CMN_EVENT_DVM(NOT_CMN600, retry, 0x08), + CMN_EVENT_DVM(NOT_CMN600, txsnp_flitv, 0x09), + CMN_EVENT_DVM(NOT_CMN600, txsnp_stall, 0x0a), + CMN_EVENT_DVM(NOT_CMN600, trkfull, 0x0b), + CMN_EVENT_DVM_OCC(NOT_CMN600, trk_occupancy, 0x0c), + CMN_EVENT_DVM_OCC(CMN700, trk_occupancy_cxha, 0x0d), + CMN_EVENT_DVM_OCC(CMN700, trk_occupancy_pdn, 0x0e), + CMN_EVENT_DVM(CMN700, trk_alloc, 0x0f), + CMN_EVENT_DVM(CMN700, trk_cxha_alloc, 0x10), + CMN_EVENT_DVM(CMN700, trk_pdn_alloc, 0x11), + CMN_EVENT_DVM(CMN700, txsnp_stall_limit, 0x12), + CMN_EVENT_DVM(CMN700, rxsnp_stall_starv, 0x13), + CMN_EVENT_DVM(CMN700, txsnp_sync_stall_op, 0x14), CMN_EVENT_HNF(CMN_ANY, cache_miss, 0x01), CMN_EVENT_HNF(CMN_ANY, slc_sf_cache_access, 0x02), @@ -704,11 +822,11 @@ static struct attribute *arm_cmn_event_attrs[] = { CMN_EVENT_HNF(CMN_ANY, mc_retries, 0x0c), CMN_EVENT_HNF(CMN_ANY, mc_reqs, 0x0d), CMN_EVENT_HNF(CMN_ANY, qos_hh_retry, 0x0e), - _CMN_EVENT_HNF(CMN_ANY, qos_pocq_occupancy_all, 0x0f, 0), - _CMN_EVENT_HNF(CMN_ANY, qos_pocq_occupancy_read, 0x0f, 1), - _CMN_EVENT_HNF(CMN_ANY, qos_pocq_occupancy_write, 0x0f, 2), - _CMN_EVENT_HNF(CMN_ANY, qos_pocq_occupancy_atomic, 0x0f, 3), - _CMN_EVENT_HNF(CMN_ANY, qos_pocq_occupancy_stash, 0x0f, 4), + _CMN_EVENT_HNF(CMN_ANY, qos_pocq_occupancy_all, 0x0f, 0, SEL_OCCUP1ID), + _CMN_EVENT_HNF(CMN_ANY, qos_pocq_occupancy_read, 0x0f, 1, SEL_OCCUP1ID), + _CMN_EVENT_HNF(CMN_ANY, qos_pocq_occupancy_write, 0x0f, 2, SEL_OCCUP1ID), + _CMN_EVENT_HNF(CMN_ANY, qos_pocq_occupancy_atomic, 0x0f, 3, SEL_OCCUP1ID), + _CMN_EVENT_HNF(CMN_ANY, qos_pocq_occupancy_stash, 0x0f, 4, SEL_OCCUP1ID), CMN_EVENT_HNF(CMN_ANY, pocq_addrhaz, 0x10), CMN_EVENT_HNF(CMN_ANY, pocq_atomic_addrhaz, 0x11), CMN_EVENT_HNF(CMN_ANY, ld_st_swp_adq_full, 0x12), @@ -725,9 +843,22 @@ static struct attribute *arm_cmn_event_attrs[] = { CMN_EVENT_HNF(CMN_ANY, stash_snp_sent, 0x1d), CMN_EVENT_HNF(CMN_ANY, stash_data_pull, 0x1e), CMN_EVENT_HNF(CMN_ANY, snp_fwded, 0x1f), - CMN_EVENT_HNF(CI700, atomic_fwd, 0x20), - CMN_EVENT_HNF(CI700, mpam_hardlim, 0x21), - CMN_EVENT_HNF(CI700, mpam_softlim, 0x22), + CMN_EVENT_HNF(NOT_CMN600, atomic_fwd, 0x20), + CMN_EVENT_HNF(NOT_CMN600, mpam_hardlim, 0x21), + CMN_EVENT_HNF(NOT_CMN600, mpam_softlim, 0x22), + CMN_EVENT_HNF(CMN_650ON, snp_sent_cluster, 0x23), + CMN_EVENT_HNF(CMN_650ON, sf_imprecise_evict, 0x24), + CMN_EVENT_HNF(CMN_650ON, sf_evict_shared_line, 0x25), + CMN_EVENT_HNF_CLS(CMN700, pocq_class_occup, 0x26), + CMN_EVENT_HNF_CLS(CMN700, pocq_class_retry, 0x27), + CMN_EVENT_HNF_CLS(CMN700, class_mc_reqs, 0x28), + CMN_EVENT_HNF_CLS(CMN700, class_cgnt_cmin, 0x29), + CMN_EVENT_HNF_SNT(CMN700, sn_throttle, 0x2a), + CMN_EVENT_HNF_SNT(CMN700, sn_throttle_min, 0x2b), + CMN_EVENT_HNF(CMN700, sf_precise_to_imprecise, 0x2c), + CMN_EVENT_HNF(CMN700, snp_intv_cln, 0x2d), + CMN_EVENT_HNF(CMN700, nc_excl, 0x2e), + CMN_EVENT_HNF(CMN700, excl_mon_ovfl, 0x2f), CMN_EVENT_HNI(rrt_rd_occ_cnt_ovfl, 0x20), CMN_EVENT_HNI(rrt_wr_occ_cnt_ovfl, 0x21), @@ -749,12 +880,33 @@ static struct attribute *arm_cmn_event_attrs[] = { CMN_EVENT_HNI(nonpcie_serialization, 0x31), CMN_EVENT_HNI(pcie_serialization, 0x32), + /* + * HN-P events squat on top of the HN-I similarly to DVM events, except + * for being crammed into the same physical node as well. And of course + * where would the fun be if the same events were in the same order... + */ + CMN_EVENT_HNP(rrt_wr_occ_cnt_ovfl, 0x01), + CMN_EVENT_HNP(rdt_wr_occ_cnt_ovfl, 0x02), + CMN_EVENT_HNP(wdb_occ_cnt_ovfl, 0x03), + CMN_EVENT_HNP(rrt_wr_alloc, 0x04), + CMN_EVENT_HNP(rdt_wr_alloc, 0x05), + CMN_EVENT_HNP(wdb_alloc, 0x06), + CMN_EVENT_HNP(awvalid_no_awready, 0x07), + CMN_EVENT_HNP(awready_no_awvalid, 0x08), + CMN_EVENT_HNP(wvalid_no_wready, 0x09), + CMN_EVENT_HNP(rrt_rd_occ_cnt_ovfl, 0x11), + CMN_EVENT_HNP(rdt_rd_occ_cnt_ovfl, 0x12), + CMN_EVENT_HNP(rrt_rd_alloc, 0x13), + CMN_EVENT_HNP(rdt_rd_alloc, 0x14), + CMN_EVENT_HNP(arvalid_no_arready, 0x15), + CMN_EVENT_HNP(arready_no_arvalid, 0x16), + CMN_EVENT_XP(txflit_valid, 0x01), CMN_EVENT_XP(txflit_stall, 0x02), CMN_EVENT_XP(partial_dat_flit, 0x03), /* We treat watchpoints as a special made-up class of XP events */ - CMN_EVENT_ATTR(CMN_ANY, watchpoint_up, CMN_TYPE_WP, CMN_WP_UP, 0), - CMN_EVENT_ATTR(CMN_ANY, watchpoint_down, CMN_TYPE_WP, CMN_WP_DOWN, 0), + CMN_EVENT_ATTR(CMN_ANY, watchpoint_up, CMN_TYPE_WP, CMN_WP_UP), + CMN_EVENT_ATTR(CMN_ANY, watchpoint_down, CMN_TYPE_WP, CMN_WP_DOWN), CMN_EVENT_SBSX(CMN_ANY, rd_req, 0x01), CMN_EVENT_SBSX(CMN_ANY, wr_req, 0x02), @@ -768,7 +920,7 @@ static struct attribute *arm_cmn_event_attrs[] = { CMN_EVENT_SBSX(CMN_ANY, wdb_occ_cnt_ovfl, 0x14), CMN_EVENT_SBSX(CMN_ANY, rd_axi_trkr_occ_cnt_ovfl, 0x15), CMN_EVENT_SBSX(CMN_ANY, cmo_axi_trkr_occ_cnt_ovfl, 0x16), - CMN_EVENT_SBSX(CI700, rdb_occ_cnt_ovfl, 0x17), + CMN_EVENT_SBSX(NOT_CMN600, rdb_occ_cnt_ovfl, 0x17), CMN_EVENT_SBSX(CMN_ANY, arvalid_no_arready, 0x21), CMN_EVENT_SBSX(CMN_ANY, awvalid_no_awready, 0x22), CMN_EVENT_SBSX(CMN_ANY, wvalid_no_wready, 0x23), @@ -795,12 +947,25 @@ static struct attribute *arm_cmn_event_attrs[] = { CMN_EVENT_RNID(CMN600, rdb_replay, 0x12), CMN_EVENT_RNID(CMN600, rdb_hybrid, 0x13), CMN_EVENT_RNID(CMN600, rdb_ord, 0x14), - CMN_EVENT_RNID(CI700, padb_occ_ovfl, 0x11), - CMN_EVENT_RNID(CI700, rpdb_occ_ovfl, 0x12), - CMN_EVENT_RNID(CI700, rrt_occup_ovfl_slice1, 0x13), - CMN_EVENT_RNID(CI700, rrt_occup_ovfl_slice2, 0x14), - CMN_EVENT_RNID(CI700, rrt_occup_ovfl_slice3, 0x15), - CMN_EVENT_RNID(CI700, wrt_throttled, 0x16), + CMN_EVENT_RNID(NOT_CMN600, padb_occ_ovfl, 0x11), + CMN_EVENT_RNID(NOT_CMN600, rpdb_occ_ovfl, 0x12), + CMN_EVENT_RNID(NOT_CMN600, rrt_occup_ovfl_slice1, 0x13), + CMN_EVENT_RNID(NOT_CMN600, rrt_occup_ovfl_slice2, 0x14), + CMN_EVENT_RNID(NOT_CMN600, rrt_occup_ovfl_slice3, 0x15), + CMN_EVENT_RNID(NOT_CMN600, wrt_throttled, 0x16), + CMN_EVENT_RNID(CMN700, ldb_full, 0x17), + CMN_EVENT_RNID(CMN700, rrt_rd_req_occup_ovfl_slice0, 0x18), + CMN_EVENT_RNID(CMN700, rrt_rd_req_occup_ovfl_slice1, 0x19), + CMN_EVENT_RNID(CMN700, rrt_rd_req_occup_ovfl_slice2, 0x1a), + CMN_EVENT_RNID(CMN700, rrt_rd_req_occup_ovfl_slice3, 0x1b), + CMN_EVENT_RNID(CMN700, rrt_burst_occup_ovfl_slice0, 0x1c), + CMN_EVENT_RNID(CMN700, rrt_burst_occup_ovfl_slice1, 0x1d), + CMN_EVENT_RNID(CMN700, rrt_burst_occup_ovfl_slice2, 0x1e), + CMN_EVENT_RNID(CMN700, rrt_burst_occup_ovfl_slice3, 0x1f), + CMN_EVENT_RNID(CMN700, rrt_burst_alloc, 0x20), + CMN_EVENT_RNID(CMN700, awid_hash, 0x21), + CMN_EVENT_RNID(CMN700, atomic_alloc, 0x22), + CMN_EVENT_RNID(CMN700, atomic_occ_ovfl, 0x23), CMN_EVENT_MTSX(tc_lookup, 0x01), CMN_EVENT_MTSX(tc_fill, 0x02), @@ -815,6 +980,118 @@ static struct attribute *arm_cmn_event_attrs[] = { CMN_EVENT_MTSX(tcq_occ_cnt_ovfl, 0x0b), CMN_EVENT_MTSX(tdb_occ_cnt_ovfl, 0x0c), + CMN_EVENT_CXRA(CMN_ANY, rht_occ, 0x01), + CMN_EVENT_CXRA(CMN_ANY, sht_occ, 0x02), + CMN_EVENT_CXRA(CMN_ANY, rdb_occ, 0x03), + CMN_EVENT_CXRA(CMN_ANY, wdb_occ, 0x04), + CMN_EVENT_CXRA(CMN_ANY, ssb_occ, 0x05), + CMN_EVENT_CXRA(CMN_ANY, snp_bcasts, 0x06), + CMN_EVENT_CXRA(CMN_ANY, req_chains, 0x07), + CMN_EVENT_CXRA(CMN_ANY, req_chain_avglen, 0x08), + CMN_EVENT_CXRA(CMN_ANY, chirsp_stalls, 0x09), + CMN_EVENT_CXRA(CMN_ANY, chidat_stalls, 0x0a), + CMN_EVENT_CXRA(CMN_ANY, cxreq_pcrd_stalls_link0, 0x0b), + CMN_EVENT_CXRA(CMN_ANY, cxreq_pcrd_stalls_link1, 0x0c), + CMN_EVENT_CXRA(CMN_ANY, cxreq_pcrd_stalls_link2, 0x0d), + CMN_EVENT_CXRA(CMN_ANY, cxdat_pcrd_stalls_link0, 0x0e), + CMN_EVENT_CXRA(CMN_ANY, cxdat_pcrd_stalls_link1, 0x0f), + CMN_EVENT_CXRA(CMN_ANY, cxdat_pcrd_stalls_link2, 0x10), + CMN_EVENT_CXRA(CMN_ANY, external_chirsp_stalls, 0x11), + CMN_EVENT_CXRA(CMN_ANY, external_chidat_stalls, 0x12), + CMN_EVENT_CXRA(NOT_CMN600, cxmisc_pcrd_stalls_link0, 0x13), + CMN_EVENT_CXRA(NOT_CMN600, cxmisc_pcrd_stalls_link1, 0x14), + CMN_EVENT_CXRA(NOT_CMN600, cxmisc_pcrd_stalls_link2, 0x15), + + CMN_EVENT_CXHA(rddatbyp, 0x21), + CMN_EVENT_CXHA(chirsp_up_stall, 0x22), + CMN_EVENT_CXHA(chidat_up_stall, 0x23), + CMN_EVENT_CXHA(snppcrd_link0_stall, 0x24), + CMN_EVENT_CXHA(snppcrd_link1_stall, 0x25), + CMN_EVENT_CXHA(snppcrd_link2_stall, 0x26), + CMN_EVENT_CXHA(reqtrk_occ, 0x27), + CMN_EVENT_CXHA(rdb_occ, 0x28), + CMN_EVENT_CXHA(rdbyp_occ, 0x29), + CMN_EVENT_CXHA(wdb_occ, 0x2a), + CMN_EVENT_CXHA(snptrk_occ, 0x2b), + CMN_EVENT_CXHA(sdb_occ, 0x2c), + CMN_EVENT_CXHA(snphaz_occ, 0x2d), + + CMN_EVENT_CCRA(rht_occ, 0x41), + CMN_EVENT_CCRA(sht_occ, 0x42), + CMN_EVENT_CCRA(rdb_occ, 0x43), + CMN_EVENT_CCRA(wdb_occ, 0x44), + CMN_EVENT_CCRA(ssb_occ, 0x45), + CMN_EVENT_CCRA(snp_bcasts, 0x46), + CMN_EVENT_CCRA(req_chains, 0x47), + CMN_EVENT_CCRA(req_chain_avglen, 0x48), + CMN_EVENT_CCRA(chirsp_stalls, 0x49), + CMN_EVENT_CCRA(chidat_stalls, 0x4a), + CMN_EVENT_CCRA(cxreq_pcrd_stalls_link0, 0x4b), + CMN_EVENT_CCRA(cxreq_pcrd_stalls_link1, 0x4c), + CMN_EVENT_CCRA(cxreq_pcrd_stalls_link2, 0x4d), + CMN_EVENT_CCRA(cxdat_pcrd_stalls_link0, 0x4e), + CMN_EVENT_CCRA(cxdat_pcrd_stalls_link1, 0x4f), + CMN_EVENT_CCRA(cxdat_pcrd_stalls_link2, 0x50), + CMN_EVENT_CCRA(external_chirsp_stalls, 0x51), + CMN_EVENT_CCRA(external_chidat_stalls, 0x52), + CMN_EVENT_CCRA(cxmisc_pcrd_stalls_link0, 0x53), + CMN_EVENT_CCRA(cxmisc_pcrd_stalls_link1, 0x54), + CMN_EVENT_CCRA(cxmisc_pcrd_stalls_link2, 0x55), + CMN_EVENT_CCRA(rht_alloc, 0x56), + CMN_EVENT_CCRA(sht_alloc, 0x57), + CMN_EVENT_CCRA(rdb_alloc, 0x58), + CMN_EVENT_CCRA(wdb_alloc, 0x59), + CMN_EVENT_CCRA(ssb_alloc, 0x5a), + + CMN_EVENT_CCHA(rddatbyp, 0x61), + CMN_EVENT_CCHA(chirsp_up_stall, 0x62), + CMN_EVENT_CCHA(chidat_up_stall, 0x63), + CMN_EVENT_CCHA(snppcrd_link0_stall, 0x64), + CMN_EVENT_CCHA(snppcrd_link1_stall, 0x65), + CMN_EVENT_CCHA(snppcrd_link2_stall, 0x66), + CMN_EVENT_CCHA(reqtrk_occ, 0x67), + CMN_EVENT_CCHA(rdb_occ, 0x68), + CMN_EVENT_CCHA(rdbyp_occ, 0x69), + CMN_EVENT_CCHA(wdb_occ, 0x6a), + CMN_EVENT_CCHA(snptrk_occ, 0x6b), + CMN_EVENT_CCHA(sdb_occ, 0x6c), + CMN_EVENT_CCHA(snphaz_occ, 0x6d), + CMN_EVENT_CCHA(reqtrk_alloc, 0x6e), + CMN_EVENT_CCHA(rdb_alloc, 0x6f), + CMN_EVENT_CCHA(rdbyp_alloc, 0x70), + CMN_EVENT_CCHA(wdb_alloc, 0x71), + CMN_EVENT_CCHA(snptrk_alloc, 0x72), + CMN_EVENT_CCHA(sdb_alloc, 0x73), + CMN_EVENT_CCHA(snphaz_alloc, 0x74), + CMN_EVENT_CCHA(pb_rhu_req_occ, 0x75), + CMN_EVENT_CCHA(pb_rhu_req_alloc, 0x76), + CMN_EVENT_CCHA(pb_rhu_pcie_req_occ, 0x77), + CMN_EVENT_CCHA(pb_rhu_pcie_req_alloc, 0x78), + CMN_EVENT_CCHA(pb_pcie_wr_req_occ, 0x79), + CMN_EVENT_CCHA(pb_pcie_wr_req_alloc, 0x7a), + CMN_EVENT_CCHA(pb_pcie_reg_req_occ, 0x7b), + CMN_EVENT_CCHA(pb_pcie_reg_req_alloc, 0x7c), + CMN_EVENT_CCHA(pb_pcie_rsvd_req_occ, 0x7d), + CMN_EVENT_CCHA(pb_pcie_rsvd_req_alloc, 0x7e), + CMN_EVENT_CCHA(pb_rhu_dat_occ, 0x7f), + CMN_EVENT_CCHA(pb_rhu_dat_alloc, 0x80), + CMN_EVENT_CCHA(pb_rhu_pcie_dat_occ, 0x81), + CMN_EVENT_CCHA(pb_rhu_pcie_dat_alloc, 0x82), + CMN_EVENT_CCHA(pb_pcie_wr_dat_occ, 0x83), + CMN_EVENT_CCHA(pb_pcie_wr_dat_alloc, 0x84), + + CMN_EVENT_CCLA(rx_cxs, 0x21), + CMN_EVENT_CCLA(tx_cxs, 0x22), + CMN_EVENT_CCLA(rx_cxs_avg_size, 0x23), + CMN_EVENT_CCLA(tx_cxs_avg_size, 0x24), + CMN_EVENT_CCLA(tx_cxs_lcrd_backpressure, 0x25), + CMN_EVENT_CCLA(link_crdbuf_occ, 0x26), + CMN_EVENT_CCLA(link_crdbuf_alloc, 0x27), + CMN_EVENT_CCLA(pfwd_rcvr_cxs, 0x28), + CMN_EVENT_CCLA(pfwd_sndr_num_flits, 0x29), + CMN_EVENT_CCLA(pfwd_sndr_stalls_static_crd, 0x2a), + CMN_EVENT_CCLA(pfwd_sndr_stalls_dynmaic_crd, 0x2b), + NULL }; @@ -1032,6 +1309,42 @@ static void arm_cmn_event_read(struct perf_event *event) local64_add(delta, &event->count); } +static int arm_cmn_set_event_sel_hi(struct arm_cmn_node *dn, + enum cmn_filter_select fsel, u8 occupid) +{ + u64 reg; + + if (fsel == SEL_NONE) + return 0; + + if (!dn->occupid[fsel].count) { + dn->occupid[fsel].val = occupid; + reg = FIELD_PREP(CMN__PMU_CBUSY_SNTHROTTLE_SEL, + dn->occupid[SEL_CBUSY_SNTHROTTLE_SEL].val) | + FIELD_PREP(CMN__PMU_CLASS_OCCUP_ID, + dn->occupid[SEL_CLASS_OCCUP_ID].val) | + FIELD_PREP(CMN__PMU_OCCUP1_ID, + dn->occupid[SEL_OCCUP1ID].val); + writel_relaxed(reg >> 32, dn->pmu_base + CMN_PMU_EVENT_SEL + 4); + } else if (dn->occupid[fsel].val != occupid) { + return -EBUSY; + } + dn->occupid[fsel].count++; + return 0; +} + +static void arm_cmn_set_event_sel_lo(struct arm_cmn_node *dn, int dtm_idx, + int eventid, bool wide_sel) +{ + if (wide_sel) { + dn->event_w[dtm_idx] = eventid; + writeq_relaxed(le64_to_cpu(dn->event_sel_w), dn->pmu_base + CMN_PMU_EVENT_SEL); + } else { + dn->event[dtm_idx] = eventid; + writel_relaxed(le32_to_cpu(dn->event_sel), dn->pmu_base + CMN_PMU_EVENT_SEL); + } +} + static void arm_cmn_event_start(struct perf_event *event, int flags) { struct arm_cmn *cmn = to_cmn(event->pmu); @@ -1058,8 +1371,8 @@ static void arm_cmn_event_start(struct perf_event *event, int flags) } else for_each_hw_dn(hw, dn, i) { int dtm_idx = arm_cmn_get_index(hw->dtm_idx, i); - dn->event[dtm_idx] = CMN_EVENT_EVENTID(event); - writel_relaxed(le32_to_cpu(dn->event_sel), dn->pmu_base + CMN_PMU_EVENT_SEL); + arm_cmn_set_event_sel_lo(dn, dtm_idx, CMN_EVENT_EVENTID(event), + hw->wide_sel); } } @@ -1086,8 +1399,7 @@ static void arm_cmn_event_stop(struct perf_event *event, int flags) } else for_each_hw_dn(hw, dn, i) { int dtm_idx = arm_cmn_get_index(hw->dtm_idx, i); - dn->event[dtm_idx] = 0; - writel_relaxed(le32_to_cpu(dn->event_sel), dn->pmu_base + CMN_PMU_EVENT_SEL); + arm_cmn_set_event_sel_lo(dn, dtm_idx, 0, hw->wide_sel); } arm_cmn_event_read(event); @@ -1095,7 +1407,7 @@ static void arm_cmn_event_stop(struct perf_event *event, int flags) struct arm_cmn_val { u8 dtm_count[CMN_MAX_DTMS]; - u8 occupid[CMN_MAX_DTMS]; + u8 occupid[CMN_MAX_DTMS][SEL_MAX]; u8 wp[CMN_MAX_DTMS][4]; int dtc_count; bool cycles; @@ -1108,7 +1420,6 @@ static void arm_cmn_val_add_event(struct arm_cmn *cmn, struct arm_cmn_val *val, struct arm_cmn_node *dn; enum cmn_node_type type; int i; - u8 occupid; if (is_software_event(event)) return; @@ -1120,16 +1431,14 @@ static void arm_cmn_val_add_event(struct arm_cmn *cmn, struct arm_cmn_val *val, } val->dtc_count++; - if (arm_cmn_is_occup_event(cmn->model, type, CMN_EVENT_EVENTID(event))) - occupid = CMN_EVENT_OCCUPID(event) + 1; - else - occupid = 0; for_each_hw_dn(hw, dn, i) { - int wp_idx, dtm = dn->dtm; + int wp_idx, dtm = dn->dtm, sel = hw->filter_sel; val->dtm_count[dtm]++; - val->occupid[dtm] = occupid; + + if (sel > SEL_NONE) + val->occupid[dtm][sel] = CMN_EVENT_OCCUPID(event) + 1; if (type != CMN_TYPE_WP) continue; @@ -1147,7 +1456,6 @@ static int arm_cmn_validate_group(struct arm_cmn *cmn, struct perf_event *event) enum cmn_node_type type; struct arm_cmn_val *val; int i, ret = -EINVAL; - u8 occupid; if (leader == event) return 0; @@ -1172,18 +1480,14 @@ static int arm_cmn_validate_group(struct arm_cmn *cmn, struct perf_event *event) if (val->dtc_count == CMN_DT_NUM_COUNTERS) goto done; - if (arm_cmn_is_occup_event(cmn->model, type, CMN_EVENT_EVENTID(event))) - occupid = CMN_EVENT_OCCUPID(event) + 1; - else - occupid = 0; - for_each_hw_dn(hw, dn, i) { - int wp_idx, wp_cmb, dtm = dn->dtm; + int wp_idx, wp_cmb, dtm = dn->dtm, sel = hw->filter_sel; if (val->dtm_count[dtm] == CMN_DTM_NUM_COUNTERS) goto done; - if (occupid && val->occupid[dtm] && occupid != val->occupid[dtm]) + if (sel > SEL_NONE && val->occupid[dtm][sel] && + val->occupid[dtm][sel] != CMN_EVENT_OCCUPID(event) + 1) goto done; if (type != CMN_TYPE_WP) @@ -1204,6 +1508,22 @@ done: return ret; } +static enum cmn_filter_select arm_cmn_filter_sel(enum cmn_model model, + enum cmn_node_type type, + unsigned int eventid) +{ + struct arm_cmn_event_attr *e; + int i; + + for (i = 0; i < ARRAY_SIZE(arm_cmn_event_attrs) - 1; i++) { + e = container_of(arm_cmn_event_attrs[i], typeof(*e), attr.attr); + if (e->model & model && e->type == type && e->eventid == eventid) + return e->fsel; + } + return SEL_NONE; +} + + static int arm_cmn_event_init(struct perf_event *event) { struct arm_cmn *cmn = to_cmn(event->pmu); @@ -1228,18 +1548,23 @@ static int arm_cmn_event_init(struct perf_event *event) if (type == CMN_TYPE_DTC) return 0; + eventid = CMN_EVENT_EVENTID(event); /* For watchpoints we need the actual XP node here */ if (type == CMN_TYPE_WP) { type = CMN_TYPE_XP; /* ...and we need a "real" direction */ - eventid = CMN_EVENT_EVENTID(event); if (eventid != CMN_WP_UP && eventid != CMN_WP_DOWN) return -EINVAL; /* ...but the DTM may depend on which port we're watching */ if (cmn->multi_dtm) hw->dtm_offset = CMN_EVENT_WP_DEV_SEL(event) / 2; + } else if (type == CMN_TYPE_XP && cmn->model == CMN700) { + hw->wide_sel = true; } + /* This is sufficiently annoying to recalculate, so cache it */ + hw->filter_sel = arm_cmn_filter_sel(cmn->model, type, eventid); + bynodeid = CMN_EVENT_BYNODEID(event); nodeid = CMN_EVENT_NODEID(event); @@ -1281,8 +1606,8 @@ static void arm_cmn_event_clear(struct arm_cmn *cmn, struct perf_event *event, if (type == CMN_TYPE_WP) dtm->wp_event[arm_cmn_wp_idx(event)] = -1; - if (arm_cmn_is_occup_event(cmn->model, type, CMN_EVENT_EVENTID(event))) - hw->dn[i].occupid_count--; + if (hw->filter_sel > SEL_NONE) + hw->dn[i].occupid[hw->filter_sel].count--; dtm->pmu_config_low &= ~CMN__PMEVCNT_PAIRED(dtm_idx); writel_relaxed(dtm->pmu_config_low, dtm->base + CMN_DTM_PMU_CONFIG); @@ -1362,18 +1687,8 @@ static int arm_cmn_event_add(struct perf_event *event, int flags) input_sel = CMN__PMEVCNT0_INPUT_SEL_DEV + dtm_idx + (nid.port << 4) + (nid.dev << 2); - if (arm_cmn_is_occup_event(cmn->model, type, CMN_EVENT_EVENTID(event))) { - u8 occupid = CMN_EVENT_OCCUPID(event); - - if (dn->occupid_count == 0) { - dn->occupid_val = occupid; - writel_relaxed(occupid, - dn->pmu_base + CMN_PMU_EVENT_SEL + 4); - } else if (dn->occupid_val != occupid) { - goto free_dtms; - } - dn->occupid_count++; - } + if (arm_cmn_set_event_sel_hi(dn, hw->filter_sel, CMN_EVENT_OCCUPID(event))) + goto free_dtms; } arm_cmn_set_index(hw->dtm_idx, i, dtm_idx); @@ -1622,6 +1937,10 @@ static int arm_cmn_init_dtcs(struct arm_cmn *cmn) /* To the PMU, RN-Ds don't add anything over RN-Is, so smoosh them together */ if (dn->type == CMN_TYPE_RND) dn->type = CMN_TYPE_RNI; + + /* We split the RN-I off already, so let the CCLA part match CCLA events */ + if (dn->type == CMN_TYPE_CCLA_RNI) + dn->type = CMN_TYPE_CCLA; } writel_relaxed(CMN_DT_DTC_CTL_DT_EN, cmn->dtc[0].base + CMN_DT_DTC_CTL); @@ -1652,6 +1971,18 @@ static void arm_cmn_init_node_info(struct arm_cmn *cmn, u32 offset, struct arm_c node->type, node->logid, offset); } +static enum cmn_node_type arm_cmn_subtype(enum cmn_node_type type) +{ + switch (type) { + case CMN_TYPE_HNP: + return CMN_TYPE_HNI; + case CMN_TYPE_CCLA_RNI: + return CMN_TYPE_RNI; + default: + return CMN_TYPE_INVALID; + } +} + static int arm_cmn_discover(struct arm_cmn *cmn, unsigned int rgn_offset) { void __iomem *cfg_region; @@ -1676,6 +2007,10 @@ static int arm_cmn_discover(struct arm_cmn *cmn, unsigned int rgn_offset) cmn->rsp_vc_num = FIELD_GET(CMN_INFO_RSP_VC_NUM, reg); cmn->dat_vc_num = FIELD_GET(CMN_INFO_DAT_VC_NUM, reg); + reg = readq_relaxed(cfg_region + CMN_CFGM_INFO_GLOBAL_1); + cmn->snp_vc_num = FIELD_GET(CMN_INFO_SNP_VC_NUM, reg); + cmn->req_vc_num = FIELD_GET(CMN_INFO_REQ_VC_NUM, reg); + reg = readq_relaxed(cfg_region + CMN_CHILD_INFO); child_count = FIELD_GET(CMN_CI_CHILD_COUNT, reg); child_poff = FIELD_GET(CMN_CI_CHILD_PTR_OFFSET, reg); @@ -1692,8 +2027,13 @@ static int arm_cmn_discover(struct arm_cmn *cmn, unsigned int rgn_offset) cmn->num_dns += FIELD_GET(CMN_CI_CHILD_COUNT, reg); } - /* Cheeky +1 to help terminate pointer-based iteration later */ - dn = devm_kcalloc(cmn->dev, cmn->num_dns + 1, sizeof(*dn), GFP_KERNEL); + /* + * Some nodes effectively have two separate types, which we'll handle + * by creating one of each internally. For a (very) safe initial upper + * bound, account for double the number of non-XP nodes. + */ + dn = devm_kcalloc(cmn->dev, cmn->num_dns * 2 - cmn->num_xps, + sizeof(*dn), GFP_KERNEL); if (!dn) return -ENOMEM; @@ -1794,6 +2134,9 @@ static int arm_cmn_discover(struct arm_cmn *cmn, unsigned int rgn_offset) case CMN_TYPE_MTSX: case CMN_TYPE_CXRA: case CMN_TYPE_CXHA: + case CMN_TYPE_CCRA: + case CMN_TYPE_CCHA: + case CMN_TYPE_CCLA: dn++; break; /* Nothing to see here */ @@ -1802,6 +2145,19 @@ static int arm_cmn_discover(struct arm_cmn *cmn, unsigned int rgn_offset) case CMN_TYPE_RNSAM: case CMN_TYPE_CXLA: break; + /* + * Split "optimised" combination nodes into separate + * types for the different event sets. Offsetting the + * base address lets us handle the second pmu_event_sel + * register via the normal mechanism later. + */ + case CMN_TYPE_HNP: + case CMN_TYPE_CCLA_RNI: + dn[1] = dn[0]; + dn[0].pmu_base += CMN_HNP_PMU_EVENT_SEL; + dn[1].type = arm_cmn_subtype(dn->type); + dn += 2; + break; /* Something has gone horribly wrong */ default: dev_err(cmn->dev, "invalid device node type: 0x%x\n", dn->type); @@ -1810,9 +2166,10 @@ static int arm_cmn_discover(struct arm_cmn *cmn, unsigned int rgn_offset) } } - /* Correct for any nodes we skipped */ + /* Correct for any nodes we added or skipped */ cmn->num_dns = dn - cmn->dns; + /* Cheeky +1 to help terminate pointer-based iteration later */ sz = (void *)(dn + 1) - (void *)cmn->dns; dn = devm_krealloc(cmn->dev, cmn->dns, sz, GFP_KERNEL); if (dn) @@ -1970,6 +2327,8 @@ static int arm_cmn_remove(struct platform_device *pdev) #ifdef CONFIG_OF static const struct of_device_id arm_cmn_of_match[] = { { .compatible = "arm,cmn-600", .data = (void *)CMN600 }, + { .compatible = "arm,cmn-650", .data = (void *)CMN650 }, + { .compatible = "arm,cmn-700", .data = (void *)CMN700 }, { .compatible = "arm,ci-700", .data = (void *)CI700 }, {} }; @@ -1979,6 +2338,8 @@ MODULE_DEVICE_TABLE(of, arm_cmn_of_match); #ifdef CONFIG_ACPI static const struct acpi_device_id arm_cmn_acpi_match[] = { { "ARMHC600", CMN600 }, + { "ARMHC650", CMN650 }, + { "ARMHC700", CMN700 }, {} }; MODULE_DEVICE_TABLE(acpi, arm_cmn_acpi_match); diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c index 9694370651fa..59d3980b8ca2 100644 --- a/drivers/perf/arm_pmu.c +++ b/drivers/perf/arm_pmu.c @@ -400,6 +400,9 @@ validate_group(struct perf_event *event) if (!validate_event(event->pmu, &fake_pmu, leader)) return -EINVAL; + if (event == leader) + return 0; + for_each_sibling_event(sibling, leader) { if (!validate_event(event->pmu, &fake_pmu, sibling)) return -EINVAL; @@ -489,12 +492,7 @@ __hw_perf_event_init(struct perf_event *event) local64_set(&hwc->period_left, hwc->sample_period); } - if (event->group_leader != event) { - if (validate_group(event) != 0) - return -EINVAL; - } - - return 0; + return validate_group(event); } static int armpmu_event_init(struct perf_event *event) diff --git a/drivers/perf/arm_pmu_acpi.c b/drivers/perf/arm_pmu_acpi.c index f5c7a845cd7b..96ffadd654ff 100644 --- a/drivers/perf/arm_pmu_acpi.c +++ b/drivers/perf/arm_pmu_acpi.c @@ -159,7 +159,9 @@ static int arm_pmu_acpi_parse_irqs(void) * them with their PMUs. */ per_cpu(pmu_irqs, cpu) = irq; - armpmu_request_irq(irq, cpu); + err = armpmu_request_irq(irq, cpu); + if (err) + goto out_err; } return 0; diff --git a/drivers/perf/arm_spe_pmu.c b/drivers/perf/arm_spe_pmu.c index d44bcc29d99c..db670b265897 100644 --- a/drivers/perf/arm_spe_pmu.c +++ b/drivers/perf/arm_spe_pmu.c @@ -1035,6 +1035,9 @@ static void __arm_spe_pmu_dev_probe(void *info) fallthrough; case 2: spe_pmu->counter_sz = 12; + break; + case 3: + spe_pmu->counter_sz = 16; } dev_info(dev, diff --git a/drivers/perf/fsl_imx8_ddr_perf.c b/drivers/perf/fsl_imx8_ddr_perf.c index 94ebc1ecace7..b1b2a55de77f 100644 --- a/drivers/perf/fsl_imx8_ddr_perf.c +++ b/drivers/perf/fsl_imx8_ddr_perf.c @@ -29,7 +29,7 @@ #define CNTL_OVER_MASK 0xFFFFFFFE #define CNTL_CSV_SHIFT 24 -#define CNTL_CSV_MASK (0xFF << CNTL_CSV_SHIFT) +#define CNTL_CSV_MASK (0xFFU << CNTL_CSV_SHIFT) #define EVENT_CYCLES_ID 0 #define EVENT_CYCLES_COUNTER 0 diff --git a/drivers/perf/hisilicon/Makefile b/drivers/perf/hisilicon/Makefile index 506ed39e3266..6be83517acaa 100644 --- a/drivers/perf/hisilicon/Makefile +++ b/drivers/perf/hisilicon/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-only obj-$(CONFIG_HISI_PMU) += hisi_uncore_pmu.o hisi_uncore_l3c_pmu.o \ hisi_uncore_hha_pmu.o hisi_uncore_ddrc_pmu.o hisi_uncore_sllc_pmu.o \ - hisi_uncore_pa_pmu.o + hisi_uncore_pa_pmu.o hisi_uncore_cpa_pmu.o obj-$(CONFIG_HISI_PCIE_PMU) += hisi_pcie_pmu.o diff --git a/drivers/perf/hisilicon/hisi_uncore_cpa_pmu.c b/drivers/perf/hisilicon/hisi_uncore_cpa_pmu.c new file mode 100644 index 000000000000..a9bb73f76be4 --- /dev/null +++ b/drivers/perf/hisilicon/hisi_uncore_cpa_pmu.c @@ -0,0 +1,409 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * HiSilicon SoC CPA(Coherency Protocol Agent) hardware event counters support + * + * Copyright (C) 2022 HiSilicon Limited + * Author: Qi Liu <liuqi115@huawei.com> + * + * This code is based on the uncore PMUs like arm-cci and arm-ccn. + */ + +#define pr_fmt(fmt) "cpa pmu: " fmt +#include <linux/acpi.h> +#include <linux/bug.h> +#include <linux/cpuhotplug.h> +#include <linux/interrupt.h> +#include <linux/irq.h> +#include <linux/list.h> +#include <linux/smp.h> + +#include "hisi_uncore_pmu.h" + +/* CPA register definition */ +#define CPA_PERF_CTRL 0x1c00 +#define CPA_EVENT_CTRL 0x1c04 +#define CPA_INT_MASK 0x1c70 +#define CPA_INT_STATUS 0x1c78 +#define CPA_INT_CLEAR 0x1c7c +#define CPA_EVENT_TYPE0 0x1c80 +#define CPA_VERSION 0x1cf0 +#define CPA_CNT0_LOWER 0x1d00 +#define CPA_CFG_REG 0x0534 + +/* CPA operation command */ +#define CPA_PERF_CTRL_EN BIT_ULL(0) +#define CPA_EVTYPE_MASK 0xffUL +#define CPA_PM_CTRL BIT_ULL(9) + +/* CPA has 8-counters */ +#define CPA_NR_COUNTERS 0x8 +#define CPA_COUNTER_BITS 64 +#define CPA_NR_EVENTS 0xff +#define CPA_REG_OFFSET 0x8 + +static u32 hisi_cpa_pmu_get_counter_offset(int idx) +{ + return (CPA_CNT0_LOWER + idx * CPA_REG_OFFSET); +} + +static u64 hisi_cpa_pmu_read_counter(struct hisi_pmu *cpa_pmu, + struct hw_perf_event *hwc) +{ + return readq(cpa_pmu->base + hisi_cpa_pmu_get_counter_offset(hwc->idx)); +} + +static void hisi_cpa_pmu_write_counter(struct hisi_pmu *cpa_pmu, + struct hw_perf_event *hwc, u64 val) +{ + writeq(val, cpa_pmu->base + hisi_cpa_pmu_get_counter_offset(hwc->idx)); +} + +static void hisi_cpa_pmu_write_evtype(struct hisi_pmu *cpa_pmu, int idx, + u32 type) +{ + u32 reg, reg_idx, shift, val; + + /* + * Select the appropriate event select register(CPA_EVENT_TYPE0/1). + * There are 2 event select registers for the 8 hardware counters. + * Event code is 8-bits and for the former 4 hardware counters, + * CPA_EVENT_TYPE0 is chosen. For the latter 4 hardware counters, + * CPA_EVENT_TYPE1 is chosen. + */ + reg = CPA_EVENT_TYPE0 + (idx / 4) * 4; + reg_idx = idx % 4; + shift = CPA_REG_OFFSET * reg_idx; + + /* Write event code to CPA_EVENT_TYPEx Register */ + val = readl(cpa_pmu->base + reg); + val &= ~(CPA_EVTYPE_MASK << shift); + val |= type << shift; + writel(val, cpa_pmu->base + reg); +} + +static void hisi_cpa_pmu_start_counters(struct hisi_pmu *cpa_pmu) +{ + u32 val; + + val = readl(cpa_pmu->base + CPA_PERF_CTRL); + val |= CPA_PERF_CTRL_EN; + writel(val, cpa_pmu->base + CPA_PERF_CTRL); +} + +static void hisi_cpa_pmu_stop_counters(struct hisi_pmu *cpa_pmu) +{ + u32 val; + + val = readl(cpa_pmu->base + CPA_PERF_CTRL); + val &= ~(CPA_PERF_CTRL_EN); + writel(val, cpa_pmu->base + CPA_PERF_CTRL); +} + +static void hisi_cpa_pmu_disable_pm(struct hisi_pmu *cpa_pmu) +{ + u32 val; + + val = readl(cpa_pmu->base + CPA_CFG_REG); + val |= CPA_PM_CTRL; + writel(val, cpa_pmu->base + CPA_CFG_REG); +} + +static void hisi_cpa_pmu_enable_pm(struct hisi_pmu *cpa_pmu) +{ + u32 val; + + val = readl(cpa_pmu->base + CPA_CFG_REG); + val &= ~(CPA_PM_CTRL); + writel(val, cpa_pmu->base + CPA_CFG_REG); +} + +static void hisi_cpa_pmu_enable_counter(struct hisi_pmu *cpa_pmu, + struct hw_perf_event *hwc) +{ + u32 val; + + /* Enable counter index in CPA_EVENT_CTRL register */ + val = readl(cpa_pmu->base + CPA_EVENT_CTRL); + val |= 1 << hwc->idx; + writel(val, cpa_pmu->base + CPA_EVENT_CTRL); +} + +static void hisi_cpa_pmu_disable_counter(struct hisi_pmu *cpa_pmu, + struct hw_perf_event *hwc) +{ + u32 val; + + /* Clear counter index in CPA_EVENT_CTRL register */ + val = readl(cpa_pmu->base + CPA_EVENT_CTRL); + val &= ~(1UL << hwc->idx); + writel(val, cpa_pmu->base + CPA_EVENT_CTRL); +} + +static void hisi_cpa_pmu_enable_counter_int(struct hisi_pmu *cpa_pmu, + struct hw_perf_event *hwc) +{ + u32 val; + + /* Write 0 to enable interrupt */ + val = readl(cpa_pmu->base + CPA_INT_MASK); + val &= ~(1UL << hwc->idx); + writel(val, cpa_pmu->base + CPA_INT_MASK); +} + +static void hisi_cpa_pmu_disable_counter_int(struct hisi_pmu *cpa_pmu, + struct hw_perf_event *hwc) +{ + u32 val; + + /* Write 1 to mask interrupt */ + val = readl(cpa_pmu->base + CPA_INT_MASK); + val |= 1 << hwc->idx; + writel(val, cpa_pmu->base + CPA_INT_MASK); +} + +static u32 hisi_cpa_pmu_get_int_status(struct hisi_pmu *cpa_pmu) +{ + return readl(cpa_pmu->base + CPA_INT_STATUS); +} + +static void hisi_cpa_pmu_clear_int_status(struct hisi_pmu *cpa_pmu, int idx) +{ + writel(1 << idx, cpa_pmu->base + CPA_INT_CLEAR); +} + +static const struct acpi_device_id hisi_cpa_pmu_acpi_match[] = { + { "HISI0281", }, + {} +}; +MODULE_DEVICE_TABLE(acpi, hisi_cpa_pmu_acpi_match); + +static int hisi_cpa_pmu_init_data(struct platform_device *pdev, + struct hisi_pmu *cpa_pmu) +{ + if (device_property_read_u32(&pdev->dev, "hisilicon,scl-id", + &cpa_pmu->sicl_id)) { + dev_err(&pdev->dev, "Can not read sicl-id\n"); + return -EINVAL; + } + + if (device_property_read_u32(&pdev->dev, "hisilicon,idx-id", + &cpa_pmu->index_id)) { + dev_err(&pdev->dev, "Cannot read idx-id\n"); + return -EINVAL; + } + + cpa_pmu->ccl_id = -1; + cpa_pmu->sccl_id = -1; + cpa_pmu->base = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(cpa_pmu->base)) + return PTR_ERR(cpa_pmu->base); + + cpa_pmu->identifier = readl(cpa_pmu->base + CPA_VERSION); + + return 0; +} + +static struct attribute *hisi_cpa_pmu_format_attr[] = { + HISI_PMU_FORMAT_ATTR(event, "config:0-15"), + NULL +}; + +static const struct attribute_group hisi_cpa_pmu_format_group = { + .name = "format", + .attrs = hisi_cpa_pmu_format_attr, +}; + +static struct attribute *hisi_cpa_pmu_events_attr[] = { + HISI_PMU_EVENT_ATTR(cpa_cycles, 0x00), + HISI_PMU_EVENT_ATTR(cpa_p1_wr_dat, 0x61), + HISI_PMU_EVENT_ATTR(cpa_p1_rd_dat, 0x62), + HISI_PMU_EVENT_ATTR(cpa_p0_wr_dat, 0xE1), + HISI_PMU_EVENT_ATTR(cpa_p0_rd_dat, 0xE2), + NULL +}; + +static const struct attribute_group hisi_cpa_pmu_events_group = { + .name = "events", + .attrs = hisi_cpa_pmu_events_attr, +}; + +static DEVICE_ATTR(cpumask, 0444, hisi_cpumask_sysfs_show, NULL); + +static struct attribute *hisi_cpa_pmu_cpumask_attrs[] = { + &dev_attr_cpumask.attr, + NULL +}; + +static const struct attribute_group hisi_cpa_pmu_cpumask_attr_group = { + .attrs = hisi_cpa_pmu_cpumask_attrs, +}; + +static struct device_attribute hisi_cpa_pmu_identifier_attr = + __ATTR(identifier, 0444, hisi_uncore_pmu_identifier_attr_show, NULL); + +static struct attribute *hisi_cpa_pmu_identifier_attrs[] = { + &hisi_cpa_pmu_identifier_attr.attr, + NULL +}; + +static const struct attribute_group hisi_cpa_pmu_identifier_group = { + .attrs = hisi_cpa_pmu_identifier_attrs, +}; + +static const struct attribute_group *hisi_cpa_pmu_attr_groups[] = { + &hisi_cpa_pmu_format_group, + &hisi_cpa_pmu_events_group, + &hisi_cpa_pmu_cpumask_attr_group, + &hisi_cpa_pmu_identifier_group, + NULL +}; + +static const struct hisi_uncore_ops hisi_uncore_cpa_pmu_ops = { + .write_evtype = hisi_cpa_pmu_write_evtype, + .get_event_idx = hisi_uncore_pmu_get_event_idx, + .start_counters = hisi_cpa_pmu_start_counters, + .stop_counters = hisi_cpa_pmu_stop_counters, + .enable_counter = hisi_cpa_pmu_enable_counter, + .disable_counter = hisi_cpa_pmu_disable_counter, + .enable_counter_int = hisi_cpa_pmu_enable_counter_int, + .disable_counter_int = hisi_cpa_pmu_disable_counter_int, + .write_counter = hisi_cpa_pmu_write_counter, + .read_counter = hisi_cpa_pmu_read_counter, + .get_int_status = hisi_cpa_pmu_get_int_status, + .clear_int_status = hisi_cpa_pmu_clear_int_status, +}; + +static int hisi_cpa_pmu_dev_probe(struct platform_device *pdev, + struct hisi_pmu *cpa_pmu) +{ + int ret; + + ret = hisi_cpa_pmu_init_data(pdev, cpa_pmu); + if (ret) + return ret; + + ret = hisi_uncore_pmu_init_irq(cpa_pmu, pdev); + if (ret) + return ret; + + cpa_pmu->counter_bits = CPA_COUNTER_BITS; + cpa_pmu->check_event = CPA_NR_EVENTS; + cpa_pmu->pmu_events.attr_groups = hisi_cpa_pmu_attr_groups; + cpa_pmu->ops = &hisi_uncore_cpa_pmu_ops; + cpa_pmu->num_counters = CPA_NR_COUNTERS; + cpa_pmu->dev = &pdev->dev; + cpa_pmu->on_cpu = -1; + + return 0; +} + +static int hisi_cpa_pmu_probe(struct platform_device *pdev) +{ + struct hisi_pmu *cpa_pmu; + char *name; + int ret; + + cpa_pmu = devm_kzalloc(&pdev->dev, sizeof(*cpa_pmu), GFP_KERNEL); + if (!cpa_pmu) + return -ENOMEM; + + ret = hisi_cpa_pmu_dev_probe(pdev, cpa_pmu); + if (ret) + return ret; + + name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "hisi_sicl%d_cpa%u", + cpa_pmu->sicl_id, cpa_pmu->index_id); + if (!name) + return -ENOMEM; + + cpa_pmu->pmu = (struct pmu) { + .name = name, + .module = THIS_MODULE, + .task_ctx_nr = perf_invalid_context, + .event_init = hisi_uncore_pmu_event_init, + .pmu_enable = hisi_uncore_pmu_enable, + .pmu_disable = hisi_uncore_pmu_disable, + .add = hisi_uncore_pmu_add, + .del = hisi_uncore_pmu_del, + .start = hisi_uncore_pmu_start, + .stop = hisi_uncore_pmu_stop, + .read = hisi_uncore_pmu_read, + .attr_groups = cpa_pmu->pmu_events.attr_groups, + .capabilities = PERF_PMU_CAP_NO_EXCLUDE, + }; + + /* Power Management should be disabled before using CPA PMU. */ + hisi_cpa_pmu_disable_pm(cpa_pmu); + ret = cpuhp_state_add_instance(CPUHP_AP_PERF_ARM_HISI_CPA_ONLINE, + &cpa_pmu->node); + if (ret) { + dev_err(&pdev->dev, "Error %d registering hotplug\n", ret); + hisi_cpa_pmu_enable_pm(cpa_pmu); + return ret; + } + + ret = perf_pmu_register(&cpa_pmu->pmu, name, -1); + if (ret) { + dev_err(cpa_pmu->dev, "PMU register failed\n"); + cpuhp_state_remove_instance_nocalls( + CPUHP_AP_PERF_ARM_HISI_CPA_ONLINE, &cpa_pmu->node); + hisi_cpa_pmu_enable_pm(cpa_pmu); + return ret; + } + + platform_set_drvdata(pdev, cpa_pmu); + return ret; +} + +static int hisi_cpa_pmu_remove(struct platform_device *pdev) +{ + struct hisi_pmu *cpa_pmu = platform_get_drvdata(pdev); + + perf_pmu_unregister(&cpa_pmu->pmu); + cpuhp_state_remove_instance_nocalls(CPUHP_AP_PERF_ARM_HISI_CPA_ONLINE, + &cpa_pmu->node); + hisi_cpa_pmu_enable_pm(cpa_pmu); + return 0; +} + +static struct platform_driver hisi_cpa_pmu_driver = { + .driver = { + .name = "hisi_cpa_pmu", + .acpi_match_table = ACPI_PTR(hisi_cpa_pmu_acpi_match), + .suppress_bind_attrs = true, + }, + .probe = hisi_cpa_pmu_probe, + .remove = hisi_cpa_pmu_remove, +}; + +static int __init hisi_cpa_pmu_module_init(void) +{ + int ret; + + ret = cpuhp_setup_state_multi(CPUHP_AP_PERF_ARM_HISI_CPA_ONLINE, + "AP_PERF_ARM_HISI_CPA_ONLINE", + hisi_uncore_pmu_online_cpu, + hisi_uncore_pmu_offline_cpu); + if (ret) { + pr_err("setup hotplug failed: %d\n", ret); + return ret; + } + + ret = platform_driver_register(&hisi_cpa_pmu_driver); + if (ret) + cpuhp_remove_multi_state(CPUHP_AP_PERF_ARM_HISI_CPA_ONLINE); + + return ret; +} +module_init(hisi_cpa_pmu_module_init); + +static void __exit hisi_cpa_pmu_module_exit(void) +{ + platform_driver_unregister(&hisi_cpa_pmu_driver); + cpuhp_remove_multi_state(CPUHP_AP_PERF_ARM_HISI_CPA_ONLINE); +} +module_exit(hisi_cpa_pmu_module_exit); + +MODULE_DESCRIPTION("HiSilicon SoC CPA PMU driver"); +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Qi Liu <liuqi115@huawei.com>"); diff --git a/drivers/perf/hisilicon/hisi_uncore_pa_pmu.c b/drivers/perf/hisilicon/hisi_uncore_pa_pmu.c index bad99d149172..a0ee84d97c41 100644 --- a/drivers/perf/hisilicon/hisi_uncore_pa_pmu.c +++ b/drivers/perf/hisilicon/hisi_uncore_pa_pmu.c @@ -258,13 +258,12 @@ static int hisi_pa_pmu_init_data(struct platform_device *pdev, struct hisi_pmu *pa_pmu) { /* - * Use the SCCL_ID and the index ID to identify the PA PMU, - * while SCCL_ID is the nearst SCCL_ID from this SICL and - * CPU core is chosen from this SCCL to manage this PMU. + * As PA PMU is in a SICL, use the SICL_ID and the index ID + * to identify the PA PMU. */ if (device_property_read_u32(&pdev->dev, "hisilicon,scl-id", - &pa_pmu->sccl_id)) { - dev_err(&pdev->dev, "Cannot read sccl-id!\n"); + &pa_pmu->sicl_id)) { + dev_err(&pdev->dev, "Cannot read sicl-id!\n"); return -EINVAL; } @@ -275,6 +274,7 @@ static int hisi_pa_pmu_init_data(struct platform_device *pdev, } pa_pmu->ccl_id = -1; + pa_pmu->sccl_id = -1; pa_pmu->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(pa_pmu->base)) { @@ -399,13 +399,9 @@ static int hisi_pa_pmu_probe(struct platform_device *pdev) ret = hisi_pa_pmu_dev_probe(pdev, pa_pmu); if (ret) return ret; - /* - * PA is attached in SICL and the CPU core is chosen to manage this - * PMU which is the nearest SCCL, while its SCCL_ID is greater than - * one with the SICL_ID. - */ + name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "hisi_sicl%u_pa%u", - pa_pmu->sccl_id - 1, pa_pmu->index_id); + pa_pmu->sicl_id, pa_pmu->index_id); if (!name) return -ENOMEM; diff --git a/drivers/perf/hisilicon/hisi_uncore_pmu.c b/drivers/perf/hisilicon/hisi_uncore_pmu.c index 358e4e284a62..980b9ee6eb14 100644 --- a/drivers/perf/hisilicon/hisi_uncore_pmu.c +++ b/drivers/perf/hisilicon/hisi_uncore_pmu.c @@ -458,6 +458,10 @@ static bool hisi_pmu_cpu_is_associated_pmu(struct hisi_pmu *hisi_pmu) { int sccl_id, ccl_id; + /* If SCCL_ID is -1, the PMU is in a SICL and has no CPU affinity */ + if (hisi_pmu->sccl_id == -1) + return true; + if (hisi_pmu->ccl_id == -1) { /* If CCL_ID is -1, the PMU only shares the same SCCL */ hisi_read_sccl_and_ccl_id(&sccl_id, NULL); diff --git a/drivers/perf/hisilicon/hisi_uncore_pmu.h b/drivers/perf/hisilicon/hisi_uncore_pmu.h index 7f5841d6f592..96eeddad55ff 100644 --- a/drivers/perf/hisilicon/hisi_uncore_pmu.h +++ b/drivers/perf/hisilicon/hisi_uncore_pmu.h @@ -81,6 +81,7 @@ struct hisi_pmu { struct device *dev; struct hlist_node node; int sccl_id; + int sicl_id; int ccl_id; void __iomem *base; /* the ID of the PMU modules */ diff --git a/drivers/perf/marvell_cn10k_tad_pmu.c b/drivers/perf/marvell_cn10k_tad_pmu.c index ee67305f822d..282d3a071a67 100644 --- a/drivers/perf/marvell_cn10k_tad_pmu.c +++ b/drivers/perf/marvell_cn10k_tad_pmu.c @@ -146,12 +146,12 @@ static int tad_pmu_event_init(struct perf_event *event) { struct tad_pmu *tad_pmu = to_tad_pmu(event->pmu); - if (!event->attr.disabled) - return -EINVAL; - if (event->attr.type != event->pmu->type) return -ENOENT; + if (!event->attr.disabled) + return -EINVAL; + if (event->state != PERF_EVENT_STATE_OFF) return -EINVAL; diff --git a/drivers/perf/qcom_l2_pmu.c b/drivers/perf/qcom_l2_pmu.c index 7640491aab12..30234c261b05 100644 --- a/drivers/perf/qcom_l2_pmu.c +++ b/drivers/perf/qcom_l2_pmu.c @@ -736,7 +736,7 @@ static struct cluster_pmu *l2_cache_associate_cpu_with_cluster( { u64 mpidr; int cpu_cluster_id; - struct cluster_pmu *cluster = NULL; + struct cluster_pmu *cluster; /* * This assumes that the cluster_id is in MPIDR[aff1] for @@ -758,10 +758,10 @@ static struct cluster_pmu *l2_cache_associate_cpu_with_cluster( cluster->cluster_id); cpumask_set_cpu(cpu, &cluster->cluster_cpus); *per_cpu_ptr(l2cache_pmu->pmu_cluster, cpu) = cluster; - break; + return cluster; } - return cluster; + return NULL; } static int l2cache_pmu_online_cpu(unsigned int cpu, struct hlist_node *node) diff --git a/drivers/perf/riscv_pmu_sbi.c b/drivers/perf/riscv_pmu_sbi.c index a1317a483512..dca3537a8dcc 100644 --- a/drivers/perf/riscv_pmu_sbi.c +++ b/drivers/perf/riscv_pmu_sbi.c @@ -35,7 +35,7 @@ union sbi_pmu_ctr_info { }; }; -/** +/* * RISC-V doesn't have hetergenous harts yet. This need to be part of * per_cpu in case of harts with different pmu counters */ @@ -477,7 +477,7 @@ static int pmu_sbi_get_ctrinfo(int nctr) static inline void pmu_sbi_stop_all(struct riscv_pmu *pmu) { - /** + /* * No need to check the error because we are disabling all the counters * which may include counters that are not enabled yet. */ @@ -494,7 +494,7 @@ static inline void pmu_sbi_stop_hw_ctrs(struct riscv_pmu *pmu) cpu_hw_evt->used_hw_ctrs[0], 0, 0, 0, 0); } -/** +/* * This function starts all the used counters in two step approach. * Any counter that did not overflow can be start in a single step * while the overflowed counters need to be started with updated initialization @@ -563,7 +563,7 @@ static irqreturn_t pmu_sbi_ovf_handler(int irq, void *dev) /* Overflow status register should only be read after counter are stopped */ overflow = csr_read(CSR_SSCOUNTOVF); - /** + /* * Overflow interrupt pending bit should only be cleared after stopping * all the counters to avoid any race condition. */ diff --git a/drivers/phy/amlogic/phy-meson-g12a-usb3-pcie.c b/drivers/phy/amlogic/phy-meson-g12a-usb3-pcie.c index 5b471ab80fe2..54d65a6f0fcc 100644 --- a/drivers/phy/amlogic/phy-meson-g12a-usb3-pcie.c +++ b/drivers/phy/amlogic/phy-meson-g12a-usb3-pcie.c @@ -414,19 +414,19 @@ static int phy_g12a_usb3_pcie_probe(struct platform_device *pdev) ret = clk_prepare_enable(priv->clk_ref); if (ret) - goto err_disable_clk_ref; + return ret; priv->reset = devm_reset_control_array_get_exclusive(dev); - if (IS_ERR(priv->reset)) - return PTR_ERR(priv->reset); + if (IS_ERR(priv->reset)) { + ret = PTR_ERR(priv->reset); + goto err_disable_clk_ref; + } priv->phy = devm_phy_create(dev, np, &phy_g12a_usb3_pcie_ops); if (IS_ERR(priv->phy)) { ret = PTR_ERR(priv->phy); - if (ret != -EPROBE_DEFER) - dev_err(dev, "failed to create PHY\n"); - - return ret; + dev_err_probe(dev, ret, "failed to create PHY\n"); + goto err_disable_clk_ref; } phy_set_drvdata(priv->phy, priv); @@ -434,8 +434,12 @@ static int phy_g12a_usb3_pcie_probe(struct platform_device *pdev) phy_provider = devm_of_phy_provider_register(dev, phy_g12a_usb3_pcie_xlate); + if (IS_ERR(phy_provider)) { + ret = PTR_ERR(phy_provider); + goto err_disable_clk_ref; + } - return PTR_ERR_OR_ZERO(phy_provider); + return 0; err_disable_clk_ref: clk_disable_unprepare(priv->clk_ref); diff --git a/drivers/phy/motorola/phy-mapphone-mdm6600.c b/drivers/phy/motorola/phy-mapphone-mdm6600.c index 5172971f4c36..3cd4d51c247c 100644 --- a/drivers/phy/motorola/phy-mapphone-mdm6600.c +++ b/drivers/phy/motorola/phy-mapphone-mdm6600.c @@ -629,7 +629,8 @@ idle: cleanup: if (error < 0) phy_mdm6600_device_power_off(ddata); - + pm_runtime_disable(ddata->dev); + pm_runtime_dont_use_autosuspend(ddata->dev); return error; } diff --git a/drivers/phy/samsung/phy-exynos5250-sata.c b/drivers/phy/samsung/phy-exynos5250-sata.c index 9ec234243f7c..595adba5fb8f 100644 --- a/drivers/phy/samsung/phy-exynos5250-sata.c +++ b/drivers/phy/samsung/phy-exynos5250-sata.c @@ -187,6 +187,7 @@ static int exynos_sata_phy_probe(struct platform_device *pdev) return -EINVAL; sata_phy->client = of_find_i2c_device_by_node(node); + of_node_put(node); if (!sata_phy->client) return -EPROBE_DEFER; @@ -195,20 +196,21 @@ static int exynos_sata_phy_probe(struct platform_device *pdev) sata_phy->phyclk = devm_clk_get(dev, "sata_phyctrl"); if (IS_ERR(sata_phy->phyclk)) { dev_err(dev, "failed to get clk for PHY\n"); - return PTR_ERR(sata_phy->phyclk); + ret = PTR_ERR(sata_phy->phyclk); + goto put_dev; } ret = clk_prepare_enable(sata_phy->phyclk); if (ret < 0) { dev_err(dev, "failed to enable source clk\n"); - return ret; + goto put_dev; } sata_phy->phy = devm_phy_create(dev, NULL, &exynos_sata_phy_ops); if (IS_ERR(sata_phy->phy)) { - clk_disable_unprepare(sata_phy->phyclk); dev_err(dev, "failed to create PHY\n"); - return PTR_ERR(sata_phy->phy); + ret = PTR_ERR(sata_phy->phy); + goto clk_disable; } phy_set_drvdata(sata_phy->phy, sata_phy); @@ -216,11 +218,18 @@ static int exynos_sata_phy_probe(struct platform_device *pdev) phy_provider = devm_of_phy_provider_register(dev, of_phy_simple_xlate); if (IS_ERR(phy_provider)) { - clk_disable_unprepare(sata_phy->phyclk); - return PTR_ERR(phy_provider); + ret = PTR_ERR(phy_provider); + goto clk_disable; } return 0; + +clk_disable: + clk_disable_unprepare(sata_phy->phyclk); +put_dev: + put_device(&sata_phy->client->dev); + + return ret; } static const struct of_device_id exynos_sata_phy_of_match[] = { diff --git a/drivers/phy/ti/phy-am654-serdes.c b/drivers/phy/ti/phy-am654-serdes.c index c1211c4f863c..0be727bb9f79 100644 --- a/drivers/phy/ti/phy-am654-serdes.c +++ b/drivers/phy/ti/phy-am654-serdes.c @@ -838,7 +838,7 @@ static int serdes_am654_probe(struct platform_device *pdev) clk_err: of_clk_del_provider(node); - + pm_runtime_disable(dev); return ret; } diff --git a/drivers/phy/ti/phy-omap-usb2.c b/drivers/phy/ti/phy-omap-usb2.c index 3a505fe5715a..31a775877f6e 100644 --- a/drivers/phy/ti/phy-omap-usb2.c +++ b/drivers/phy/ti/phy-omap-usb2.c @@ -215,7 +215,7 @@ static int omap_usb2_enable_clocks(struct omap_usb *phy) return 0; err1: - clk_disable(phy->wkupclk); + clk_disable_unprepare(phy->wkupclk); err0: return ret; diff --git a/drivers/phy/ti/phy-ti-pipe3.c b/drivers/phy/ti/phy-ti-pipe3.c index 2cbc91e535d4..f502c36f3be5 100644 --- a/drivers/phy/ti/phy-ti-pipe3.c +++ b/drivers/phy/ti/phy-ti-pipe3.c @@ -696,6 +696,7 @@ static int ti_pipe3_get_sysctrl(struct ti_pipe3 *phy) } control_pdev = of_find_device_by_node(control_node); + of_node_put(control_node); if (!control_pdev) { dev_err(dev, "Failed to get control device\n"); return -EINVAL; diff --git a/drivers/phy/ti/phy-tusb1210.c b/drivers/phy/ti/phy-tusb1210.c index a0cdbcadf09e..c3ab4b69ea68 100644 --- a/drivers/phy/ti/phy-tusb1210.c +++ b/drivers/phy/ti/phy-tusb1210.c @@ -155,7 +155,7 @@ static int tusb1210_set_mode(struct phy *phy, enum phy_mode mode, int submode) } #ifdef CONFIG_POWER_SUPPLY -const char * const tusb1210_chg_det_states[] = { +static const char * const tusb1210_chg_det_states[] = { "CHG_DET_CONNECTING", "CHG_DET_START_DET", "CHG_DET_READ_DET", @@ -537,12 +537,18 @@ static int tusb1210_probe(struct ulpi *ulpi) tusb1210_probe_charger_detect(tusb); tusb->phy = ulpi_phy_create(ulpi, &phy_ops); - if (IS_ERR(tusb->phy)) - return PTR_ERR(tusb->phy); + if (IS_ERR(tusb->phy)) { + ret = PTR_ERR(tusb->phy); + goto err_remove_charger; + } phy_set_drvdata(tusb->phy, tusb); ulpi_set_drvdata(ulpi, tusb); return 0; + +err_remove_charger: + tusb1210_remove_charger_detect(tusb); + return ret; } static void tusb1210_remove(struct ulpi *ulpi) diff --git a/drivers/pinctrl/aspeed/pinctrl-aspeed-g6.c b/drivers/pinctrl/aspeed/pinctrl-aspeed-g6.c index a3fa03bcd9a3..80838dc54b3a 100644 --- a/drivers/pinctrl/aspeed/pinctrl-aspeed-g6.c +++ b/drivers/pinctrl/aspeed/pinctrl-aspeed-g6.c @@ -1236,18 +1236,17 @@ FUNC_GROUP_DECL(SALT8, AA12); FUNC_GROUP_DECL(WDTRST4, AA12); #define AE12 196 -SIG_EXPR_LIST_DECL_SEMG(AE12, FWSPIDQ2, FWQSPID, FWSPID, - SIG_DESC_SET(SCU438, 4)); +SIG_EXPR_LIST_DECL_SESG(AE12, FWSPIQ2, FWQSPI, SIG_DESC_SET(SCU438, 4)); SIG_EXPR_LIST_DECL_SESG(AE12, GPIOY4, GPIOY4); -PIN_DECL_(AE12, SIG_EXPR_LIST_PTR(AE12, FWSPIDQ2), +PIN_DECL_(AE12, SIG_EXPR_LIST_PTR(AE12, FWSPIQ2), SIG_EXPR_LIST_PTR(AE12, GPIOY4)); #define AF12 197 -SIG_EXPR_LIST_DECL_SEMG(AF12, FWSPIDQ3, FWQSPID, FWSPID, - SIG_DESC_SET(SCU438, 5)); +SIG_EXPR_LIST_DECL_SESG(AF12, FWSPIQ3, FWQSPI, SIG_DESC_SET(SCU438, 5)); SIG_EXPR_LIST_DECL_SESG(AF12, GPIOY5, GPIOY5); -PIN_DECL_(AF12, SIG_EXPR_LIST_PTR(AF12, FWSPIDQ3), +PIN_DECL_(AF12, SIG_EXPR_LIST_PTR(AF12, FWSPIQ3), SIG_EXPR_LIST_PTR(AF12, GPIOY5)); +FUNC_GROUP_DECL(FWQSPI, AE12, AF12); #define AC12 198 SSSF_PIN_DECL(AC12, GPIOY6, FWSPIABR, SIG_DESC_SET(SCU438, 6)); @@ -1520,9 +1519,8 @@ SIG_EXPR_LIST_DECL_SEMG(Y4, EMMCDAT7, EMMCG8, EMMC, SIG_DESC_SET(SCU404, 3)); PIN_DECL_3(Y4, GPIO18E3, FWSPIDMISO, VBMISO, EMMCDAT7); GROUP_DECL(FWSPID, Y1, Y2, Y3, Y4); -GROUP_DECL(FWQSPID, Y1, Y2, Y3, Y4, AE12, AF12); GROUP_DECL(EMMCG8, AB4, AA4, AC4, AA5, Y5, AB5, AB6, AC5, Y1, Y2, Y3, Y4); -FUNC_DECL_2(FWSPID, FWSPID, FWQSPID); +FUNC_DECL_1(FWSPID, FWSPID); FUNC_GROUP_DECL(VB, Y1, Y2, Y3, Y4); FUNC_DECL_3(EMMC, EMMCG1, EMMCG4, EMMCG8); /* @@ -1918,7 +1916,7 @@ static const struct aspeed_pin_group aspeed_g6_groups[] = { ASPEED_PINCTRL_GROUP(FSI2), ASPEED_PINCTRL_GROUP(FWSPIABR), ASPEED_PINCTRL_GROUP(FWSPID), - ASPEED_PINCTRL_GROUP(FWQSPID), + ASPEED_PINCTRL_GROUP(FWQSPI), ASPEED_PINCTRL_GROUP(FWSPIWP), ASPEED_PINCTRL_GROUP(GPIT0), ASPEED_PINCTRL_GROUP(GPIT1), @@ -2160,6 +2158,7 @@ static const struct aspeed_pin_function aspeed_g6_functions[] = { ASPEED_PINCTRL_FUNC(FSI2), ASPEED_PINCTRL_FUNC(FWSPIABR), ASPEED_PINCTRL_FUNC(FWSPID), + ASPEED_PINCTRL_FUNC(FWQSPI), ASPEED_PINCTRL_FUNC(FWSPIWP), ASPEED_PINCTRL_FUNC(GPIT0), ASPEED_PINCTRL_FUNC(GPIT1), diff --git a/drivers/pinctrl/intel/pinctrl-alderlake.c b/drivers/pinctrl/intel/pinctrl-alderlake.c index 32ba50efbceb..62dbd1e67513 100644 --- a/drivers/pinctrl/intel/pinctrl-alderlake.c +++ b/drivers/pinctrl/intel/pinctrl-alderlake.c @@ -14,11 +14,17 @@ #include "pinctrl-intel.h" -#define ADL_PAD_OWN 0x0a0 -#define ADL_PADCFGLOCK 0x110 -#define ADL_HOSTSW_OWN 0x150 -#define ADL_GPI_IS 0x200 -#define ADL_GPI_IE 0x220 +#define ADL_N_PAD_OWN 0x020 +#define ADL_N_PADCFGLOCK 0x080 +#define ADL_N_HOSTSW_OWN 0x0b0 +#define ADL_N_GPI_IS 0x100 +#define ADL_N_GPI_IE 0x120 + +#define ADL_S_PAD_OWN 0x0a0 +#define ADL_S_PADCFGLOCK 0x110 +#define ADL_S_HOSTSW_OWN 0x150 +#define ADL_S_GPI_IS 0x200 +#define ADL_S_GPI_IE 0x220 #define ADL_GPP(r, s, e, g) \ { \ @@ -28,14 +34,28 @@ .gpio_base = (g), \ } -#define ADL_COMMUNITY(b, s, e, g) \ +#define ADL_N_COMMUNITY(b, s, e, g) \ + { \ + .barno = (b), \ + .padown_offset = ADL_N_PAD_OWN, \ + .padcfglock_offset = ADL_N_PADCFGLOCK, \ + .hostown_offset = ADL_N_HOSTSW_OWN, \ + .is_offset = ADL_N_GPI_IS, \ + .ie_offset = ADL_N_GPI_IE, \ + .pin_base = (s), \ + .npins = ((e) - (s) + 1), \ + .gpps = (g), \ + .ngpps = ARRAY_SIZE(g), \ + } + +#define ADL_S_COMMUNITY(b, s, e, g) \ { \ .barno = (b), \ - .padown_offset = ADL_PAD_OWN, \ - .padcfglock_offset = ADL_PADCFGLOCK, \ - .hostown_offset = ADL_HOSTSW_OWN, \ - .is_offset = ADL_GPI_IS, \ - .ie_offset = ADL_GPI_IE, \ + .padown_offset = ADL_S_PAD_OWN, \ + .padcfglock_offset = ADL_S_PADCFGLOCK, \ + .hostown_offset = ADL_S_HOSTSW_OWN, \ + .is_offset = ADL_S_GPI_IS, \ + .ie_offset = ADL_S_GPI_IE, \ .pin_base = (s), \ .npins = ((e) - (s) + 1), \ .gpps = (g), \ @@ -342,10 +362,10 @@ static const struct intel_padgroup adln_community5_gpps[] = { }; static const struct intel_community adln_communities[] = { - ADL_COMMUNITY(0, 0, 66, adln_community0_gpps), - ADL_COMMUNITY(1, 67, 168, adln_community1_gpps), - ADL_COMMUNITY(2, 169, 248, adln_community4_gpps), - ADL_COMMUNITY(3, 249, 256, adln_community5_gpps), + ADL_N_COMMUNITY(0, 0, 66, adln_community0_gpps), + ADL_N_COMMUNITY(1, 67, 168, adln_community1_gpps), + ADL_N_COMMUNITY(2, 169, 248, adln_community4_gpps), + ADL_N_COMMUNITY(3, 249, 256, adln_community5_gpps), }; static const struct intel_pinctrl_soc_data adln_soc_data = { @@ -713,11 +733,11 @@ static const struct intel_padgroup adls_community5_gpps[] = { }; static const struct intel_community adls_communities[] = { - ADL_COMMUNITY(0, 0, 94, adls_community0_gpps), - ADL_COMMUNITY(1, 95, 150, adls_community1_gpps), - ADL_COMMUNITY(2, 151, 199, adls_community3_gpps), - ADL_COMMUNITY(3, 200, 269, adls_community4_gpps), - ADL_COMMUNITY(4, 270, 303, adls_community5_gpps), + ADL_S_COMMUNITY(0, 0, 94, adls_community0_gpps), + ADL_S_COMMUNITY(1, 95, 150, adls_community1_gpps), + ADL_S_COMMUNITY(2, 151, 199, adls_community3_gpps), + ADL_S_COMMUNITY(3, 200, 269, adls_community4_gpps), + ADL_S_COMMUNITY(4, 270, 303, adls_community5_gpps), }; static const struct intel_pinctrl_soc_data adls_soc_data = { diff --git a/drivers/pinctrl/mediatek/Kconfig b/drivers/pinctrl/mediatek/Kconfig index 8dca1ef04965..40accd110c3d 100644 --- a/drivers/pinctrl/mediatek/Kconfig +++ b/drivers/pinctrl/mediatek/Kconfig @@ -30,6 +30,7 @@ config PINCTRL_MTK_MOORE select GENERIC_PINMUX_FUNCTIONS select GPIOLIB select OF_GPIO + select EINT_MTK select PINCTRL_MTK_V2 config PINCTRL_MTK_PARIS diff --git a/drivers/pinctrl/mediatek/pinctrl-mt8365.c b/drivers/pinctrl/mediatek/pinctrl-mt8365.c index 727c65221aef..57f37a294063 100644 --- a/drivers/pinctrl/mediatek/pinctrl-mt8365.c +++ b/drivers/pinctrl/mediatek/pinctrl-mt8365.c @@ -259,7 +259,7 @@ static const struct mtk_pin_ies_smt_set mt8365_ies_set[] = { MTK_PIN_IES_SMT_SPEC(104, 104, 0x420, 13), MTK_PIN_IES_SMT_SPEC(105, 109, 0x420, 14), MTK_PIN_IES_SMT_SPEC(110, 113, 0x420, 15), - MTK_PIN_IES_SMT_SPEC(114, 112, 0x420, 16), + MTK_PIN_IES_SMT_SPEC(114, 116, 0x420, 16), MTK_PIN_IES_SMT_SPEC(117, 119, 0x420, 17), MTK_PIN_IES_SMT_SPEC(120, 122, 0x420, 18), MTK_PIN_IES_SMT_SPEC(123, 125, 0x420, 19), diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c index 1a7d686494ff..0645c2c24f50 100644 --- a/drivers/pinctrl/pinctrl-amd.c +++ b/drivers/pinctrl/pinctrl-amd.c @@ -387,6 +387,8 @@ static void amd_gpio_irq_enable(struct irq_data *d) struct gpio_chip *gc = irq_data_get_irq_chip_data(d); struct amd_gpio *gpio_dev = gpiochip_get_data(gc); + gpiochip_enable_irq(gc, d->hwirq); + raw_spin_lock_irqsave(&gpio_dev->lock, flags); pin_reg = readl(gpio_dev->base + (d->hwirq)*4); pin_reg |= BIT(INTERRUPT_ENABLE_OFF); @@ -408,6 +410,8 @@ static void amd_gpio_irq_disable(struct irq_data *d) pin_reg &= ~BIT(INTERRUPT_MASK_OFF); writel(pin_reg, gpio_dev->base + (d->hwirq)*4); raw_spin_unlock_irqrestore(&gpio_dev->lock, flags); + + gpiochip_disable_irq(gc, d->hwirq); } static void amd_gpio_irq_mask(struct irq_data *d) @@ -577,7 +581,7 @@ static void amd_irq_ack(struct irq_data *d) */ } -static struct irq_chip amd_gpio_irqchip = { +static const struct irq_chip amd_gpio_irqchip = { .name = "amd_gpio", .irq_ack = amd_irq_ack, .irq_enable = amd_gpio_irq_enable, @@ -593,7 +597,8 @@ static struct irq_chip amd_gpio_irqchip = { * the wake event. Otherwise the wake event will never clear and * prevent the system from suspending. */ - .flags = IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND, + .flags = IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND | IRQCHIP_IMMUTABLE, + GPIOCHIP_IRQ_RESOURCE_HELPERS, }; #define PIN_IRQ_PENDING (BIT(INTERRUPT_STS_OFF) | BIT(WAKE_STS_OFF)) @@ -1026,7 +1031,7 @@ static int amd_gpio_probe(struct platform_device *pdev) amd_gpio_irq_init(gpio_dev); girq = &gpio_dev->gc.irq; - girq->chip = &amd_gpio_irqchip; + gpio_irq_chip_set_chip(girq, &amd_gpio_irqchip); /* This will let us handle the parent IRQ in the driver */ girq->parent_handler = NULL; girq->num_parents = 0; diff --git a/drivers/pinctrl/pinctrl-apple-gpio.c b/drivers/pinctrl/pinctrl-apple-gpio.c index 72f4dd2466e1..5e610849dfc3 100644 --- a/drivers/pinctrl/pinctrl-apple-gpio.c +++ b/drivers/pinctrl/pinctrl-apple-gpio.c @@ -36,7 +36,6 @@ struct apple_gpio_pinctrl { struct pinctrl_desc pinctrl_desc; struct gpio_chip gpio_chip; - struct irq_chip irq_chip; u8 irqgrps[]; }; @@ -275,17 +274,21 @@ static unsigned int apple_gpio_irq_type(unsigned int type) static void apple_gpio_irq_mask(struct irq_data *data) { - struct apple_gpio_pinctrl *pctl = gpiochip_get_data(irq_data_get_irq_chip_data(data)); + struct gpio_chip *gc = irq_data_get_irq_chip_data(data); + struct apple_gpio_pinctrl *pctl = gpiochip_get_data(gc); apple_gpio_set_reg(pctl, data->hwirq, REG_GPIOx_MODE, FIELD_PREP(REG_GPIOx_MODE, REG_GPIOx_IN_IRQ_OFF)); + gpiochip_disable_irq(gc, data->hwirq); } static void apple_gpio_irq_unmask(struct irq_data *data) { - struct apple_gpio_pinctrl *pctl = gpiochip_get_data(irq_data_get_irq_chip_data(data)); + struct gpio_chip *gc = irq_data_get_irq_chip_data(data); + struct apple_gpio_pinctrl *pctl = gpiochip_get_data(gc); unsigned int irqtype = apple_gpio_irq_type(irqd_get_trigger_type(data)); + gpiochip_enable_irq(gc, data->hwirq); apple_gpio_set_reg(pctl, data->hwirq, REG_GPIOx_MODE, FIELD_PREP(REG_GPIOx_MODE, irqtype)); } @@ -343,13 +346,15 @@ static void apple_gpio_irq_handler(struct irq_desc *desc) chained_irq_exit(chip, desc); } -static struct irq_chip apple_gpio_irqchip = { - .name = "Apple-GPIO", - .irq_startup = apple_gpio_irq_startup, - .irq_ack = apple_gpio_irq_ack, - .irq_mask = apple_gpio_irq_mask, - .irq_unmask = apple_gpio_irq_unmask, - .irq_set_type = apple_gpio_irq_set_type, +static const struct irq_chip apple_gpio_irqchip = { + .name = "Apple-GPIO", + .irq_startup = apple_gpio_irq_startup, + .irq_ack = apple_gpio_irq_ack, + .irq_mask = apple_gpio_irq_mask, + .irq_unmask = apple_gpio_irq_unmask, + .irq_set_type = apple_gpio_irq_set_type, + .flags = IRQCHIP_IMMUTABLE, + GPIOCHIP_IRQ_RESOURCE_HELPERS, }; /* Probe & register */ @@ -360,8 +365,6 @@ static int apple_gpio_register(struct apple_gpio_pinctrl *pctl) void **irq_data = NULL; int ret; - pctl->irq_chip = apple_gpio_irqchip; - pctl->gpio_chip.label = dev_name(pctl->dev); pctl->gpio_chip.request = gpiochip_generic_request; pctl->gpio_chip.free = gpiochip_generic_free; @@ -377,7 +380,7 @@ static int apple_gpio_register(struct apple_gpio_pinctrl *pctl) if (girq->num_parents) { int i; - girq->chip = &pctl->irq_chip; + gpio_irq_chip_set_chip(girq, &apple_gpio_irqchip); girq->parent_handler = apple_gpio_irq_handler; girq->parents = kmalloc_array(girq->num_parents, diff --git a/drivers/pinctrl/pinctrl-ocelot.c b/drivers/pinctrl/pinctrl-ocelot.c index 003fb0e34153..6a956ee94494 100644 --- a/drivers/pinctrl/pinctrl-ocelot.c +++ b/drivers/pinctrl/pinctrl-ocelot.c @@ -129,6 +129,7 @@ enum { FUNC_PTP1, FUNC_PTP2, FUNC_PTP3, + FUNC_PTPSYNC_0, FUNC_PTPSYNC_1, FUNC_PTPSYNC_2, FUNC_PTPSYNC_3, @@ -252,6 +253,7 @@ static const char *const ocelot_function_names[] = { [FUNC_PTP1] = "ptp1", [FUNC_PTP2] = "ptp2", [FUNC_PTP3] = "ptp3", + [FUNC_PTPSYNC_0] = "ptpsync_0", [FUNC_PTPSYNC_1] = "ptpsync_1", [FUNC_PTPSYNC_2] = "ptpsync_2", [FUNC_PTPSYNC_3] = "ptpsync_3", @@ -983,7 +985,7 @@ LAN966X_P(31, GPIO, FC3_c, CAN1, NONE, OB_TRG, RECO_b, NON LAN966X_P(32, GPIO, FC3_c, NONE, SGPIO_a, NONE, MIIM_Sa, NONE, R); LAN966X_P(33, GPIO, FC1_b, NONE, SGPIO_a, NONE, MIIM_Sa, MIIM_b, R); LAN966X_P(34, GPIO, FC1_b, NONE, SGPIO_a, NONE, MIIM_Sa, MIIM_b, R); -LAN966X_P(35, GPIO, FC1_b, NONE, SGPIO_a, CAN0_b, NONE, NONE, R); +LAN966X_P(35, GPIO, FC1_b, PTPSYNC_0, SGPIO_a, CAN0_b, NONE, NONE, R); LAN966X_P(36, GPIO, NONE, PTPSYNC_1, NONE, CAN0_b, NONE, NONE, R); LAN966X_P(37, GPIO, FC_SHRD0, PTPSYNC_2, TWI_SLC_GATE_AD, NONE, NONE, NONE, R); LAN966X_P(38, GPIO, NONE, PTPSYNC_3, NONE, NONE, NONE, NONE, R); diff --git a/drivers/pinctrl/pinctrl-pistachio.c b/drivers/pinctrl/pinctrl-pistachio.c index 8d271c6b0ca4..5de691c630b4 100644 --- a/drivers/pinctrl/pinctrl-pistachio.c +++ b/drivers/pinctrl/pinctrl-pistachio.c @@ -1374,10 +1374,10 @@ static int pistachio_gpio_register(struct pistachio_pinctrl *pctl) } irq = irq_of_parse_and_map(child, 0); - if (irq < 0) { - dev_err(pctl->dev, "No IRQ for bank %u: %d\n", i, irq); + if (!irq) { + dev_err(pctl->dev, "No IRQ for bank %u\n", i); of_node_put(child); - ret = irq; + ret = -EINVAL; goto err; } diff --git a/drivers/pinctrl/pinctrl-rockchip.c b/drivers/pinctrl/pinctrl-rockchip.c index a1b598b86aa9..2cb79e649fcf 100644 --- a/drivers/pinctrl/pinctrl-rockchip.c +++ b/drivers/pinctrl/pinctrl-rockchip.c @@ -457,95 +457,110 @@ static struct rockchip_mux_recalced_data rk3128_mux_recalced_data[] = { static struct rockchip_mux_recalced_data rk3308_mux_recalced_data[] = { { + /* gpio1b6_sel */ .num = 1, .pin = 14, .reg = 0x28, .bit = 12, .mask = 0xf }, { + /* gpio1b7_sel */ .num = 1, .pin = 15, .reg = 0x2c, .bit = 0, .mask = 0x3 }, { + /* gpio1c2_sel */ .num = 1, .pin = 18, .reg = 0x30, .bit = 4, .mask = 0xf }, { + /* gpio1c3_sel */ .num = 1, .pin = 19, .reg = 0x30, .bit = 8, .mask = 0xf }, { + /* gpio1c4_sel */ .num = 1, .pin = 20, .reg = 0x30, .bit = 12, .mask = 0xf }, { + /* gpio1c5_sel */ .num = 1, .pin = 21, .reg = 0x34, .bit = 0, .mask = 0xf }, { + /* gpio1c6_sel */ .num = 1, .pin = 22, .reg = 0x34, .bit = 4, .mask = 0xf }, { + /* gpio1c7_sel */ .num = 1, .pin = 23, .reg = 0x34, .bit = 8, .mask = 0xf }, { - .num = 3, - .pin = 12, - .reg = 0x68, - .bit = 8, - .mask = 0xf - }, { - .num = 3, - .pin = 13, - .reg = 0x68, - .bit = 12, - .mask = 0xf - }, { + /* gpio2a2_sel */ .num = 2, .pin = 2, - .reg = 0x608, - .bit = 0, - .mask = 0x7 + .reg = 0x40, + .bit = 4, + .mask = 0x3 }, { + /* gpio2a3_sel */ .num = 2, .pin = 3, - .reg = 0x608, - .bit = 4, - .mask = 0x7 + .reg = 0x40, + .bit = 6, + .mask = 0x3 }, { + /* gpio2c0_sel */ .num = 2, .pin = 16, - .reg = 0x610, - .bit = 8, - .mask = 0x7 + .reg = 0x50, + .bit = 0, + .mask = 0x3 }, { + /* gpio3b2_sel */ .num = 3, .pin = 10, - .reg = 0x610, - .bit = 0, - .mask = 0x7 + .reg = 0x68, + .bit = 4, + .mask = 0x3 }, { + /* gpio3b3_sel */ .num = 3, .pin = 11, - .reg = 0x610, - .bit = 4, - .mask = 0x7 + .reg = 0x68, + .bit = 6, + .mask = 0x3 + }, { + /* gpio3b4_sel */ + .num = 3, + .pin = 12, + .reg = 0x68, + .bit = 8, + .mask = 0xf + }, { + /* gpio3b5_sel */ + .num = 3, + .pin = 13, + .reg = 0x68, + .bit = 12, + .mask = 0xf }, }; diff --git a/drivers/pinctrl/qcom/pinctrl-msm.c b/drivers/pinctrl/qcom/pinctrl-msm.c index 966ea6622ff3..a2abfe987ab1 100644 --- a/drivers/pinctrl/qcom/pinctrl-msm.c +++ b/drivers/pinctrl/qcom/pinctrl-msm.c @@ -42,7 +42,6 @@ * @chip: gpiochip handle. * @desc: pin controller descriptor * @restart_nb: restart notifier block. - * @irq_chip: irq chip information * @irq: parent irq for the TLMM irq_chip. * @intr_target_use_scm: route irq to application cpu using scm calls * @lock: Spinlock to protect register resources as well @@ -63,7 +62,6 @@ struct msm_pinctrl { struct pinctrl_desc desc; struct notifier_block restart_nb; - struct irq_chip irq_chip; int irq; bool intr_target_use_scm; @@ -868,6 +866,8 @@ static void msm_gpio_irq_enable(struct irq_data *d) struct gpio_chip *gc = irq_data_get_irq_chip_data(d); struct msm_pinctrl *pctrl = gpiochip_get_data(gc); + gpiochip_enable_irq(gc, d->hwirq); + if (d->parent_data) irq_chip_enable_parent(d); @@ -885,6 +885,8 @@ static void msm_gpio_irq_disable(struct irq_data *d) if (!test_bit(d->hwirq, pctrl->skip_wake_irqs)) msm_gpio_irq_mask(d); + + gpiochip_disable_irq(gc, d->hwirq); } /** @@ -958,6 +960,14 @@ static void msm_gpio_irq_ack(struct irq_data *d) raw_spin_unlock_irqrestore(&pctrl->lock, flags); } +static void msm_gpio_irq_eoi(struct irq_data *d) +{ + d = d->parent_data; + + if (d) + d->chip->irq_eoi(d); +} + static bool msm_gpio_needs_dual_edge_parent_workaround(struct irq_data *d, unsigned int type) { @@ -1255,6 +1265,26 @@ static bool msm_gpio_needs_valid_mask(struct msm_pinctrl *pctrl) return device_property_count_u16(pctrl->dev, "gpios") > 0; } +static const struct irq_chip msm_gpio_irq_chip = { + .name = "msmgpio", + .irq_enable = msm_gpio_irq_enable, + .irq_disable = msm_gpio_irq_disable, + .irq_mask = msm_gpio_irq_mask, + .irq_unmask = msm_gpio_irq_unmask, + .irq_ack = msm_gpio_irq_ack, + .irq_eoi = msm_gpio_irq_eoi, + .irq_set_type = msm_gpio_irq_set_type, + .irq_set_wake = msm_gpio_irq_set_wake, + .irq_request_resources = msm_gpio_irq_reqres, + .irq_release_resources = msm_gpio_irq_relres, + .irq_set_affinity = msm_gpio_irq_set_affinity, + .irq_set_vcpu_affinity = msm_gpio_irq_set_vcpu_affinity, + .flags = (IRQCHIP_MASK_ON_SUSPEND | + IRQCHIP_SET_TYPE_MASKED | + IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND | + IRQCHIP_IMMUTABLE), +}; + static int msm_gpio_init(struct msm_pinctrl *pctrl) { struct gpio_chip *chip; @@ -1276,22 +1306,6 @@ static int msm_gpio_init(struct msm_pinctrl *pctrl) if (msm_gpio_needs_valid_mask(pctrl)) chip->init_valid_mask = msm_gpio_init_valid_mask; - pctrl->irq_chip.name = "msmgpio"; - pctrl->irq_chip.irq_enable = msm_gpio_irq_enable; - pctrl->irq_chip.irq_disable = msm_gpio_irq_disable; - pctrl->irq_chip.irq_mask = msm_gpio_irq_mask; - pctrl->irq_chip.irq_unmask = msm_gpio_irq_unmask; - pctrl->irq_chip.irq_ack = msm_gpio_irq_ack; - pctrl->irq_chip.irq_set_type = msm_gpio_irq_set_type; - pctrl->irq_chip.irq_set_wake = msm_gpio_irq_set_wake; - pctrl->irq_chip.irq_request_resources = msm_gpio_irq_reqres; - pctrl->irq_chip.irq_release_resources = msm_gpio_irq_relres; - pctrl->irq_chip.irq_set_affinity = msm_gpio_irq_set_affinity; - pctrl->irq_chip.irq_set_vcpu_affinity = msm_gpio_irq_set_vcpu_affinity; - pctrl->irq_chip.flags = IRQCHIP_MASK_ON_SUSPEND | - IRQCHIP_SET_TYPE_MASKED | - IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND; - np = of_parse_phandle(pctrl->dev->of_node, "wakeup-parent", 0); if (np) { chip->irq.parent_domain = irq_find_matching_host(np, @@ -1300,7 +1314,6 @@ static int msm_gpio_init(struct msm_pinctrl *pctrl) if (!chip->irq.parent_domain) return -EPROBE_DEFER; chip->irq.child_to_parent_hwirq = msm_gpio_wakeirq; - pctrl->irq_chip.irq_eoi = irq_chip_eoi_parent; /* * Let's skip handling the GPIOs, if the parent irqchip * is handling the direct connect IRQ of the GPIO. @@ -1313,7 +1326,7 @@ static int msm_gpio_init(struct msm_pinctrl *pctrl) } girq = &chip->irq; - girq->chip = &pctrl->irq_chip; + gpio_irq_chip_set_chip(girq, &msm_gpio_irq_chip); girq->parent_handler = msm_gpio_irq_handler; girq->fwnode = pctrl->dev->fwnode; girq->num_parents = 1; diff --git a/drivers/pinctrl/qcom/pinctrl-sm6350.c b/drivers/pinctrl/qcom/pinctrl-sm6350.c index 4d37b817b232..a91a86628f2f 100644 --- a/drivers/pinctrl/qcom/pinctrl-sm6350.c +++ b/drivers/pinctrl/qcom/pinctrl-sm6350.c @@ -264,14 +264,14 @@ static const struct pinctrl_pin_desc sm6350_pins[] = { PINCTRL_PIN(153, "GPIO_153"), PINCTRL_PIN(154, "GPIO_154"), PINCTRL_PIN(155, "GPIO_155"), - PINCTRL_PIN(156, "SDC1_RCLK"), - PINCTRL_PIN(157, "SDC1_CLK"), - PINCTRL_PIN(158, "SDC1_CMD"), - PINCTRL_PIN(159, "SDC1_DATA"), - PINCTRL_PIN(160, "SDC2_CLK"), - PINCTRL_PIN(161, "SDC2_CMD"), - PINCTRL_PIN(162, "SDC2_DATA"), - PINCTRL_PIN(163, "UFS_RESET"), + PINCTRL_PIN(156, "UFS_RESET"), + PINCTRL_PIN(157, "SDC1_RCLK"), + PINCTRL_PIN(158, "SDC1_CLK"), + PINCTRL_PIN(159, "SDC1_CMD"), + PINCTRL_PIN(160, "SDC1_DATA"), + PINCTRL_PIN(161, "SDC2_CLK"), + PINCTRL_PIN(162, "SDC2_CMD"), + PINCTRL_PIN(163, "SDC2_DATA"), }; #define DECLARE_MSM_GPIO_PINS(pin) \ diff --git a/drivers/pinctrl/samsung/Kconfig b/drivers/pinctrl/samsung/Kconfig index dfd805e76862..7b0576f71376 100644 --- a/drivers/pinctrl/samsung/Kconfig +++ b/drivers/pinctrl/samsung/Kconfig @@ -4,14 +4,13 @@ # config PINCTRL_SAMSUNG bool - depends on OF_GPIO + select GPIOLIB select PINMUX select PINCONF config PINCTRL_EXYNOS bool "Pinctrl common driver part for Samsung Exynos SoCs" - depends on OF_GPIO - depends on ARCH_EXYNOS || ARCH_S5PV210 || COMPILE_TEST + depends on ARCH_EXYNOS || ARCH_S5PV210 || (COMPILE_TEST && OF) select PINCTRL_SAMSUNG select PINCTRL_EXYNOS_ARM if ARM && (ARCH_EXYNOS || ARCH_S5PV210) select PINCTRL_EXYNOS_ARM64 if ARM64 && ARCH_EXYNOS @@ -26,12 +25,10 @@ config PINCTRL_EXYNOS_ARM64 config PINCTRL_S3C24XX bool "Samsung S3C24XX SoC pinctrl driver" - depends on OF_GPIO - depends on ARCH_S3C24XX || COMPILE_TEST + depends on ARCH_S3C24XX || (COMPILE_TEST && OF) select PINCTRL_SAMSUNG config PINCTRL_S3C64XX bool "Samsung S3C64XX SoC pinctrl driver" - depends on OF_GPIO - depends on ARCH_S3C64XX || COMPILE_TEST + depends on ARCH_S3C64XX || (COMPILE_TEST && OF) select PINCTRL_SAMSUNG diff --git a/drivers/pinctrl/samsung/pinctrl-exynos-arm64.c b/drivers/pinctrl/samsung/pinctrl-exynos-arm64.c index d291819c2f77..cb965cf93705 100644 --- a/drivers/pinctrl/samsung/pinctrl-exynos-arm64.c +++ b/drivers/pinctrl/samsung/pinctrl-exynos-arm64.c @@ -770,7 +770,7 @@ static const struct samsung_pin_bank_data fsd_pin_banks2[] __initconst = { EXYNOS850_PIN_BANK_EINTN(3, 0x00, "gpq0"), }; -const struct samsung_pin_ctrl fsd_pin_ctrl[] __initconst = { +static const struct samsung_pin_ctrl fsd_pin_ctrl[] __initconst = { { /* pin-controller instance 0 FSYS0 data */ .pin_banks = fsd_pin_banks0, diff --git a/drivers/pinctrl/stm32/pinctrl-stm32.c b/drivers/pinctrl/stm32/pinctrl-stm32.c index 9ed764731570..f7c9459f6628 100644 --- a/drivers/pinctrl/stm32/pinctrl-stm32.c +++ b/drivers/pinctrl/stm32/pinctrl-stm32.c @@ -225,6 +225,13 @@ static void stm32_gpio_free(struct gpio_chip *chip, unsigned offset) pinctrl_gpio_free(chip->base + offset); } +static int stm32_gpio_get_noclk(struct gpio_chip *chip, unsigned int offset) +{ + struct stm32_gpio_bank *bank = gpiochip_get_data(chip); + + return !!(readl_relaxed(bank->base + STM32_GPIO_IDR) & BIT(offset)); +} + static int stm32_gpio_get(struct gpio_chip *chip, unsigned offset) { struct stm32_gpio_bank *bank = gpiochip_get_data(chip); @@ -232,7 +239,7 @@ static int stm32_gpio_get(struct gpio_chip *chip, unsigned offset) clk_enable(bank->clk); - ret = !!(readl_relaxed(bank->base + STM32_GPIO_IDR) & BIT(offset)); + ret = stm32_gpio_get_noclk(chip, offset); clk_disable(bank->clk); @@ -311,8 +318,12 @@ static void stm32_gpio_irq_trigger(struct irq_data *d) struct stm32_gpio_bank *bank = d->domain->host_data; int level; + /* Do not access the GPIO if this is not LEVEL triggered IRQ. */ + if (!(bank->irq_type[d->hwirq] & IRQ_TYPE_LEVEL_MASK)) + return; + /* If level interrupt type then retrig */ - level = stm32_gpio_get(&bank->gpio_chip, d->hwirq); + level = stm32_gpio_get_noclk(&bank->gpio_chip, d->hwirq); if ((level == 0 && bank->irq_type[d->hwirq] == IRQ_TYPE_LEVEL_LOW) || (level == 1 && bank->irq_type[d->hwirq] == IRQ_TYPE_LEVEL_HIGH)) irq_chip_retrigger_hierarchy(d); @@ -354,6 +365,7 @@ static int stm32_gpio_irq_request_resources(struct irq_data *irq_data) { struct stm32_gpio_bank *bank = irq_data->domain->host_data; struct stm32_pinctrl *pctl = dev_get_drvdata(bank->gpio_chip.parent); + unsigned long flags; int ret; ret = stm32_gpio_direction_input(&bank->gpio_chip, irq_data->hwirq); @@ -367,6 +379,10 @@ static int stm32_gpio_irq_request_resources(struct irq_data *irq_data) return ret; } + flags = irqd_get_trigger_type(irq_data); + if (flags & IRQ_TYPE_LEVEL_MASK) + clk_enable(bank->clk); + return 0; } @@ -374,6 +390,9 @@ static void stm32_gpio_irq_release_resources(struct irq_data *irq_data) { struct stm32_gpio_bank *bank = irq_data->domain->host_data; + if (bank->irq_type[irq_data->hwirq] & IRQ_TYPE_LEVEL_MASK) + clk_disable(bank->clk); + gpiochip_unlock_as_irq(&bank->gpio_chip, irq_data->hwirq); } diff --git a/drivers/pinctrl/sunplus/sppctl_sp7021.c b/drivers/pinctrl/sunplus/sppctl_sp7021.c index 9748345b9298..cd657760a644 100644 --- a/drivers/pinctrl/sunplus/sppctl_sp7021.c +++ b/drivers/pinctrl/sunplus/sppctl_sp7021.c @@ -419,7 +419,15 @@ static const struct sppctl_grp sp7021grps_prbp[] = { EGRP("PROBE_PORT2", 2, pins_prp2), }; +/* + * Due to compatible reason, the first valid item should start at the third + * position of the array. Please keep the first two items of the table + * no use (dummy). + */ const struct sppctl_func sppctl_list_funcs[] = { + FNCN("", pinmux_type_fpmx, 0x00, 0, 0), + FNCN("", pinmux_type_fpmx, 0x00, 0, 0), + FNCN("L2SW_CLK_OUT", pinmux_type_fpmx, 0x00, 0, 7), FNCN("L2SW_MAC_SMI_MDC", pinmux_type_fpmx, 0x00, 8, 7), FNCN("L2SW_LED_FLASH0", pinmux_type_fpmx, 0x01, 0, 7), diff --git a/drivers/pinctrl/sunxi/pinctrl-suniv-f1c100s.c b/drivers/pinctrl/sunxi/pinctrl-suniv-f1c100s.c index 2801ca706273..b8fc88a23cf4 100644 --- a/drivers/pinctrl/sunxi/pinctrl-suniv-f1c100s.c +++ b/drivers/pinctrl/sunxi/pinctrl-suniv-f1c100s.c @@ -51,7 +51,7 @@ static const struct sunxi_desc_pin suniv_f1c100s_pins[] = { SUNXI_FUNCTION(0x3, "pwm0"), /* PWM0 */ SUNXI_FUNCTION(0x4, "i2s"), /* IN */ SUNXI_FUNCTION(0x5, "uart1"), /* RX */ - SUNXI_FUNCTION(0x6, "spi1")), /* MOSI */ + SUNXI_FUNCTION(0x6, "spi1")), /* CLK */ SUNXI_PIN(SUNXI_PINCTRL_PIN(A, 3), SUNXI_FUNCTION(0x0, "gpio_in"), SUNXI_FUNCTION(0x1, "gpio_out"), @@ -204,7 +204,7 @@ static const struct sunxi_desc_pin suniv_f1c100s_pins[] = { SUNXI_FUNCTION(0x0, "gpio_in"), SUNXI_FUNCTION(0x1, "gpio_out"), SUNXI_FUNCTION(0x2, "lcd"), /* D20 */ - SUNXI_FUNCTION(0x3, "lvds1"), /* RX */ + SUNXI_FUNCTION(0x3, "uart2"), /* RX */ SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 14)), SUNXI_PIN(SUNXI_PINCTRL_PIN(D, 15), SUNXI_FUNCTION(0x0, "gpio_in"), diff --git a/drivers/platform/mellanox/Kconfig b/drivers/platform/mellanox/Kconfig index d4c5c170bca0..72df4b8f4dd8 100644 --- a/drivers/platform/mellanox/Kconfig +++ b/drivers/platform/mellanox/Kconfig @@ -78,4 +78,21 @@ config MLXBF_PMC to performance monitoring counters within various blocks in the Mellanox BlueField SoC via a sysfs interface. +config NVSW_SN2201 + tristate "Nvidia SN2201 platform driver support" + depends on REGMAP + depends on HWMON + depends on I2C + depends on REGMAP_I2C + help + This driver provides support for the Nvidia SN2201 platfom. + The SN2201 is a highly integrated for one rack unit system with + L3 management switches. It has 48 x 1Gbps RJ45 + 4 x 100G QSFP28 + ports in a compact 1RU form factor. The system also including a + serial port (RS-232 interface), an OOB port (1G/100M MDI interface) + and USB ports for management functions. + The processor used on SN2201 is Intel Atom®Processor C Series, + C3338R which is one of the Denverton product families. + System equipped with Nvidia®Spectrum-1 32x100GbE Ethernet switch. + endif # MELLANOX_PLATFORM diff --git a/drivers/platform/mellanox/Makefile b/drivers/platform/mellanox/Makefile index a4868366ff18..04703c0416b1 100644 --- a/drivers/platform/mellanox/Makefile +++ b/drivers/platform/mellanox/Makefile @@ -9,3 +9,4 @@ obj-$(CONFIG_MLXBF_TMFIFO) += mlxbf-tmfifo.o obj-$(CONFIG_MLXREG_HOTPLUG) += mlxreg-hotplug.o obj-$(CONFIG_MLXREG_IO) += mlxreg-io.o obj-$(CONFIG_MLXREG_LC) += mlxreg-lc.o +obj-$(CONFIG_NVSW_SN2201) += nvsw-sn2201.o diff --git a/drivers/platform/mellanox/nvsw-sn2201.c b/drivers/platform/mellanox/nvsw-sn2201.c new file mode 100644 index 000000000000..0bcdc7c75007 --- /dev/null +++ b/drivers/platform/mellanox/nvsw-sn2201.c @@ -0,0 +1,1261 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Nvidia sn2201 driver + * + * Copyright (C) 2022 Nvidia Technologies Ltd. + */ + +#include <linux/device.h> +#include <linux/i2c.h> +#include <linux/interrupt.h> +#include <linux/irq.h> +#include <linux/gpio.h> +#include <linux/module.h> +#include <linux/platform_data/mlxcpld.h> +#include <linux/platform_data/mlxreg.h> +#include <linux/platform_device.h> +#include <linux/regmap.h> + +/* SN2201 CPLD register offset. */ +#define NVSW_SN2201_CPLD_LPC_I2C_BASE_ADRR 0x2000 +#define NVSW_SN2201_CPLD_LPC_IO_RANGE 0x100 +#define NVSW_SN2201_HW_VER_ID_OFFSET 0x00 +#define NVSW_SN2201_BOARD_ID_OFFSET 0x01 +#define NVSW_SN2201_CPLD_VER_OFFSET 0x02 +#define NVSW_SN2201_CPLD_MVER_OFFSET 0x03 +#define NVSW_SN2201_CPLD_ID_OFFSET 0x04 +#define NVSW_SN2201_CPLD_PN_OFFSET 0x05 +#define NVSW_SN2201_CPLD_PN1_OFFSET 0x06 +#define NVSW_SN2201_PSU_CTRL_OFFSET 0x0a +#define NVSW_SN2201_QSFP28_STATUS_OFFSET 0x0b +#define NVSW_SN2201_QSFP28_INT_STATUS_OFFSET 0x0c +#define NVSW_SN2201_QSFP28_LP_STATUS_OFFSET 0x0d +#define NVSW_SN2201_QSFP28_RST_STATUS_OFFSET 0x0e +#define NVSW_SN2201_SYS_STATUS_OFFSET 0x0f +#define NVSW_SN2201_FRONT_SYS_LED_CTRL_OFFSET 0x10 +#define NVSW_SN2201_FRONT_PSU_LED_CTRL_OFFSET 0x12 +#define NVSW_SN2201_FRONT_UID_LED_CTRL_OFFSET 0x13 +#define NVSW_SN2201_QSFP28_LED_TEST_STATUS_OFFSET 0x14 +#define NVSW_SN2201_SYS_RST_STATUS_OFFSET 0x15 +#define NVSW_SN2201_SYS_INT_STATUS_OFFSET 0x21 +#define NVSW_SN2201_SYS_INT_MASK_OFFSET 0x22 +#define NVSW_SN2201_ASIC_STATUS_OFFSET 0x24 +#define NVSW_SN2201_ASIC_EVENT_OFFSET 0x25 +#define NVSW_SN2201_ASIC_MAKS_OFFSET 0x26 +#define NVSW_SN2201_THML_STATUS_OFFSET 0x27 +#define NVSW_SN2201_THML_EVENT_OFFSET 0x28 +#define NVSW_SN2201_THML_MASK_OFFSET 0x29 +#define NVSW_SN2201_PS_ALT_STATUS_OFFSET 0x2a +#define NVSW_SN2201_PS_ALT_EVENT_OFFSET 0x2b +#define NVSW_SN2201_PS_ALT_MASK_OFFSET 0x2c +#define NVSW_SN2201_PS_PRSNT_STATUS_OFFSET 0x30 +#define NVSW_SN2201_PS_PRSNT_EVENT_OFFSET 0x31 +#define NVSW_SN2201_PS_PRSNT_MASK_OFFSET 0x32 +#define NVSW_SN2201_PS_DC_OK_STATUS_OFFSET 0x33 +#define NVSW_SN2201_PS_DC_OK_EVENT_OFFSET 0x34 +#define NVSW_SN2201_PS_DC_OK_MASK_OFFSET 0x35 +#define NVSW_SN2201_RST_CAUSE1_OFFSET 0x36 +#define NVSW_SN2201_RST_CAUSE2_OFFSET 0x37 +#define NVSW_SN2201_RST_SW_CTRL_OFFSET 0x38 +#define NVSW_SN2201_FAN_PRSNT_STATUS_OFFSET 0x3a +#define NVSW_SN2201_FAN_PRSNT_EVENT_OFFSET 0x3b +#define NVSW_SN2201_FAN_PRSNT_MASK_OFFSET 0x3c +#define NVSW_SN2201_WD_TMR_OFFSET_LSB 0x40 +#define NVSW_SN2201_WD_TMR_OFFSET_MSB 0x41 +#define NVSW_SN2201_WD_ACT_OFFSET 0x42 +#define NVSW_SN2201_FAN_LED1_CTRL_OFFSET 0x50 +#define NVSW_SN2201_FAN_LED2_CTRL_OFFSET 0x51 +#define NVSW_SN2201_REG_MAX 0x52 + +/* Number of physical I2C busses. */ +#define NVSW_SN2201_PHY_I2C_BUS_NUM 2 +/* Number of main mux channels. */ +#define NVSW_SN2201_MAIN_MUX_CHNL_NUM 8 + +#define NVSW_SN2201_MAIN_NR 0 +#define NVSW_SN2201_MAIN_MUX_NR 1 +#define NVSW_SN2201_MAIN_MUX_DEFER_NR (NVSW_SN2201_PHY_I2C_BUS_NUM + \ + NVSW_SN2201_MAIN_MUX_CHNL_NUM - 1) + +#define NVSW_SN2201_MAIN_MUX_CH0_NR NVSW_SN2201_PHY_I2C_BUS_NUM +#define NVSW_SN2201_MAIN_MUX_CH1_NR (NVSW_SN2201_MAIN_MUX_CH0_NR + 1) +#define NVSW_SN2201_MAIN_MUX_CH2_NR (NVSW_SN2201_MAIN_MUX_CH0_NR + 2) +#define NVSW_SN2201_MAIN_MUX_CH3_NR (NVSW_SN2201_MAIN_MUX_CH0_NR + 3) +#define NVSW_SN2201_MAIN_MUX_CH5_NR (NVSW_SN2201_MAIN_MUX_CH0_NR + 5) +#define NVSW_SN2201_MAIN_MUX_CH6_NR (NVSW_SN2201_MAIN_MUX_CH0_NR + 6) +#define NVSW_SN2201_MAIN_MUX_CH7_NR (NVSW_SN2201_MAIN_MUX_CH0_NR + 7) + +#define NVSW_SN2201_CPLD_NR NVSW_SN2201_MAIN_MUX_CH0_NR +#define NVSW_SN2201_NR_NONE -1 + +/* Masks for aggregation, PSU presence and power, ASIC events + * in CPLD related registers. + */ +#define NVSW_SN2201_CPLD_AGGR_ASIC_MASK_DEF 0xe0 +#define NVSW_SN2201_CPLD_AGGR_PSU_MASK_DEF 0x04 +#define NVSW_SN2201_CPLD_AGGR_PWR_MASK_DEF 0x02 +#define NVSW_SN2201_CPLD_AGGR_FAN_MASK_DEF 0x10 +#define NVSW_SN2201_CPLD_AGGR_MASK_DEF \ + (NVSW_SN2201_CPLD_AGGR_ASIC_MASK_DEF \ + | NVSW_SN2201_CPLD_AGGR_PSU_MASK_DEF \ + | NVSW_SN2201_CPLD_AGGR_PWR_MASK_DEF \ + | NVSW_SN2201_CPLD_AGGR_FAN_MASK_DEF) + +#define NVSW_SN2201_CPLD_ASIC_MASK GENMASK(3, 1) +#define NVSW_SN2201_CPLD_PSU_MASK GENMASK(1, 0) +#define NVSW_SN2201_CPLD_PWR_MASK GENMASK(1, 0) +#define NVSW_SN2201_CPLD_FAN_MASK GENMASK(3, 0) + +#define NVSW_SN2201_CPLD_SYSIRQ 26 +#define NVSW_SN2201_LPC_SYSIRQ 28 +#define NVSW_SN2201_CPLD_I2CADDR 0x41 + +#define NVSW_SN2201_WD_DFLT_TIMEOUT 600 + +/* nvsw_sn2201 - device private data + * @dev: platform device; + * @io_data: register access platform data; + * @led_data: LED platform data; + * @hotplug_data: hotplug platform data; + * @i2c_data: I2C controller platform data; + * @led: LED device; + * @io_regs: register access device; + * @pdev_hotplug: hotplug device; + * @sn2201_devs: I2C devices for sn2201 devices; + * @sn2201_devs_num: number of I2C devices for sn2201 device; + * @main_mux_devs: I2C devices for main mux; + * @main_mux_devs_num: number of I2C devices for main mux; + * @cpld_devs: I2C devices for cpld; + * @cpld_devs_num: number of I2C devices for cpld; + * @main_mux_deferred_nr: I2C adapter number must be exist prior creating devices execution; + */ +struct nvsw_sn2201 { + struct device *dev; + struct mlxreg_core_platform_data *io_data; + struct mlxreg_core_platform_data *led_data; + struct mlxreg_core_platform_data *wd_data; + struct mlxreg_core_hotplug_platform_data *hotplug_data; + struct mlxreg_core_hotplug_platform_data *i2c_data; + struct platform_device *led; + struct platform_device *wd; + struct platform_device *io_regs; + struct platform_device *pdev_hotplug; + struct platform_device *pdev_i2c; + struct mlxreg_hotplug_device *sn2201_devs; + int sn2201_devs_num; + struct mlxreg_hotplug_device *main_mux_devs; + int main_mux_devs_num; + struct mlxreg_hotplug_device *cpld_devs; + int cpld_devs_num; + int main_mux_deferred_nr; +}; + +static bool nvsw_sn2201_writeable_reg(struct device *dev, unsigned int reg) +{ + switch (reg) { + case NVSW_SN2201_PSU_CTRL_OFFSET: + case NVSW_SN2201_QSFP28_LP_STATUS_OFFSET: + case NVSW_SN2201_QSFP28_RST_STATUS_OFFSET: + case NVSW_SN2201_FRONT_SYS_LED_CTRL_OFFSET: + case NVSW_SN2201_FRONT_PSU_LED_CTRL_OFFSET: + case NVSW_SN2201_FRONT_UID_LED_CTRL_OFFSET: + case NVSW_SN2201_QSFP28_LED_TEST_STATUS_OFFSET: + case NVSW_SN2201_SYS_RST_STATUS_OFFSET: + case NVSW_SN2201_SYS_INT_MASK_OFFSET: + case NVSW_SN2201_ASIC_EVENT_OFFSET: + case NVSW_SN2201_ASIC_MAKS_OFFSET: + case NVSW_SN2201_THML_EVENT_OFFSET: + case NVSW_SN2201_THML_MASK_OFFSET: + case NVSW_SN2201_PS_ALT_EVENT_OFFSET: + case NVSW_SN2201_PS_ALT_MASK_OFFSET: + case NVSW_SN2201_PS_PRSNT_EVENT_OFFSET: + case NVSW_SN2201_PS_PRSNT_MASK_OFFSET: + case NVSW_SN2201_PS_DC_OK_EVENT_OFFSET: + case NVSW_SN2201_PS_DC_OK_MASK_OFFSET: + case NVSW_SN2201_RST_SW_CTRL_OFFSET: + case NVSW_SN2201_FAN_PRSNT_EVENT_OFFSET: + case NVSW_SN2201_FAN_PRSNT_MASK_OFFSET: + case NVSW_SN2201_WD_TMR_OFFSET_LSB: + case NVSW_SN2201_WD_TMR_OFFSET_MSB: + case NVSW_SN2201_WD_ACT_OFFSET: + case NVSW_SN2201_FAN_LED1_CTRL_OFFSET: + case NVSW_SN2201_FAN_LED2_CTRL_OFFSET: + return true; + } + return false; +} + +static bool nvsw_sn2201_readable_reg(struct device *dev, unsigned int reg) +{ + switch (reg) { + case NVSW_SN2201_HW_VER_ID_OFFSET: + case NVSW_SN2201_BOARD_ID_OFFSET: + case NVSW_SN2201_CPLD_VER_OFFSET: + case NVSW_SN2201_CPLD_MVER_OFFSET: + case NVSW_SN2201_CPLD_ID_OFFSET: + case NVSW_SN2201_CPLD_PN_OFFSET: + case NVSW_SN2201_CPLD_PN1_OFFSET: + case NVSW_SN2201_PSU_CTRL_OFFSET: + case NVSW_SN2201_QSFP28_STATUS_OFFSET: + case NVSW_SN2201_QSFP28_INT_STATUS_OFFSET: + case NVSW_SN2201_QSFP28_LP_STATUS_OFFSET: + case NVSW_SN2201_QSFP28_RST_STATUS_OFFSET: + case NVSW_SN2201_SYS_STATUS_OFFSET: + case NVSW_SN2201_FRONT_SYS_LED_CTRL_OFFSET: + case NVSW_SN2201_FRONT_PSU_LED_CTRL_OFFSET: + case NVSW_SN2201_FRONT_UID_LED_CTRL_OFFSET: + case NVSW_SN2201_QSFP28_LED_TEST_STATUS_OFFSET: + case NVSW_SN2201_SYS_RST_STATUS_OFFSET: + case NVSW_SN2201_RST_CAUSE1_OFFSET: + case NVSW_SN2201_RST_CAUSE2_OFFSET: + case NVSW_SN2201_SYS_INT_STATUS_OFFSET: + case NVSW_SN2201_SYS_INT_MASK_OFFSET: + case NVSW_SN2201_ASIC_STATUS_OFFSET: + case NVSW_SN2201_ASIC_EVENT_OFFSET: + case NVSW_SN2201_ASIC_MAKS_OFFSET: + case NVSW_SN2201_THML_STATUS_OFFSET: + case NVSW_SN2201_THML_EVENT_OFFSET: + case NVSW_SN2201_THML_MASK_OFFSET: + case NVSW_SN2201_PS_ALT_STATUS_OFFSET: + case NVSW_SN2201_PS_ALT_EVENT_OFFSET: + case NVSW_SN2201_PS_ALT_MASK_OFFSET: + case NVSW_SN2201_PS_PRSNT_STATUS_OFFSET: + case NVSW_SN2201_PS_PRSNT_EVENT_OFFSET: + case NVSW_SN2201_PS_PRSNT_MASK_OFFSET: + case NVSW_SN2201_PS_DC_OK_STATUS_OFFSET: + case NVSW_SN2201_PS_DC_OK_EVENT_OFFSET: + case NVSW_SN2201_PS_DC_OK_MASK_OFFSET: + case NVSW_SN2201_RST_SW_CTRL_OFFSET: + case NVSW_SN2201_FAN_PRSNT_STATUS_OFFSET: + case NVSW_SN2201_FAN_PRSNT_EVENT_OFFSET: + case NVSW_SN2201_FAN_PRSNT_MASK_OFFSET: + case NVSW_SN2201_WD_TMR_OFFSET_LSB: + case NVSW_SN2201_WD_TMR_OFFSET_MSB: + case NVSW_SN2201_WD_ACT_OFFSET: + case NVSW_SN2201_FAN_LED1_CTRL_OFFSET: + case NVSW_SN2201_FAN_LED2_CTRL_OFFSET: + return true; + } + return false; +} + +static bool nvsw_sn2201_volatile_reg(struct device *dev, unsigned int reg) +{ + switch (reg) { + case NVSW_SN2201_HW_VER_ID_OFFSET: + case NVSW_SN2201_BOARD_ID_OFFSET: + case NVSW_SN2201_CPLD_VER_OFFSET: + case NVSW_SN2201_CPLD_MVER_OFFSET: + case NVSW_SN2201_CPLD_ID_OFFSET: + case NVSW_SN2201_CPLD_PN_OFFSET: + case NVSW_SN2201_CPLD_PN1_OFFSET: + case NVSW_SN2201_PSU_CTRL_OFFSET: + case NVSW_SN2201_QSFP28_STATUS_OFFSET: + case NVSW_SN2201_QSFP28_INT_STATUS_OFFSET: + case NVSW_SN2201_QSFP28_LP_STATUS_OFFSET: + case NVSW_SN2201_QSFP28_RST_STATUS_OFFSET: + case NVSW_SN2201_SYS_STATUS_OFFSET: + case NVSW_SN2201_FRONT_SYS_LED_CTRL_OFFSET: + case NVSW_SN2201_FRONT_PSU_LED_CTRL_OFFSET: + case NVSW_SN2201_FRONT_UID_LED_CTRL_OFFSET: + case NVSW_SN2201_QSFP28_LED_TEST_STATUS_OFFSET: + case NVSW_SN2201_SYS_RST_STATUS_OFFSET: + case NVSW_SN2201_RST_CAUSE1_OFFSET: + case NVSW_SN2201_RST_CAUSE2_OFFSET: + case NVSW_SN2201_SYS_INT_STATUS_OFFSET: + case NVSW_SN2201_SYS_INT_MASK_OFFSET: + case NVSW_SN2201_ASIC_STATUS_OFFSET: + case NVSW_SN2201_ASIC_EVENT_OFFSET: + case NVSW_SN2201_ASIC_MAKS_OFFSET: + case NVSW_SN2201_THML_STATUS_OFFSET: + case NVSW_SN2201_THML_EVENT_OFFSET: + case NVSW_SN2201_THML_MASK_OFFSET: + case NVSW_SN2201_PS_ALT_STATUS_OFFSET: + case NVSW_SN2201_PS_ALT_EVENT_OFFSET: + case NVSW_SN2201_PS_ALT_MASK_OFFSET: + case NVSW_SN2201_PS_PRSNT_STATUS_OFFSET: + case NVSW_SN2201_PS_PRSNT_EVENT_OFFSET: + case NVSW_SN2201_PS_PRSNT_MASK_OFFSET: + case NVSW_SN2201_PS_DC_OK_STATUS_OFFSET: + case NVSW_SN2201_PS_DC_OK_EVENT_OFFSET: + case NVSW_SN2201_PS_DC_OK_MASK_OFFSET: + case NVSW_SN2201_RST_SW_CTRL_OFFSET: + case NVSW_SN2201_FAN_PRSNT_STATUS_OFFSET: + case NVSW_SN2201_FAN_PRSNT_EVENT_OFFSET: + case NVSW_SN2201_FAN_PRSNT_MASK_OFFSET: + case NVSW_SN2201_WD_TMR_OFFSET_LSB: + case NVSW_SN2201_WD_TMR_OFFSET_MSB: + case NVSW_SN2201_FAN_LED1_CTRL_OFFSET: + case NVSW_SN2201_FAN_LED2_CTRL_OFFSET: + return true; + } + return false; +} + +static const struct reg_default nvsw_sn2201_regmap_default[] = { + { NVSW_SN2201_QSFP28_LED_TEST_STATUS_OFFSET, 0x00 }, + { NVSW_SN2201_WD_ACT_OFFSET, 0x00 }, +}; + +/* Configuration for the register map of a device with 1 bytes address space. */ +static const struct regmap_config nvsw_sn2201_regmap_conf = { + .reg_bits = 8, + .val_bits = 8, + .max_register = NVSW_SN2201_REG_MAX, + .cache_type = REGCACHE_FLAT, + .writeable_reg = nvsw_sn2201_writeable_reg, + .readable_reg = nvsw_sn2201_readable_reg, + .volatile_reg = nvsw_sn2201_volatile_reg, + .reg_defaults = nvsw_sn2201_regmap_default, + .num_reg_defaults = ARRAY_SIZE(nvsw_sn2201_regmap_default), +}; + +/* Regions for LPC I2C controller and LPC base register space. */ +static const struct resource nvsw_sn2201_lpc_io_resources[] = { + [0] = DEFINE_RES_NAMED(NVSW_SN2201_CPLD_LPC_I2C_BASE_ADRR, + NVSW_SN2201_CPLD_LPC_IO_RANGE, + "mlxplat_cpld_lpc_i2c_ctrl", IORESOURCE_IO), +}; + +static struct resource nvsw_sn2201_cpld_res[] = { + [0] = DEFINE_RES_IRQ_NAMED(NVSW_SN2201_CPLD_SYSIRQ, "mlxreg-hotplug"), +}; + +static struct resource nvsw_sn2201_lpc_res[] = { + [0] = DEFINE_RES_IRQ_NAMED(NVSW_SN2201_LPC_SYSIRQ, "i2c-mlxcpld"), +}; + +/* SN2201 I2C platform data. */ +struct mlxreg_core_hotplug_platform_data nvsw_sn2201_i2c_data = { + .irq = NVSW_SN2201_CPLD_SYSIRQ, +}; + +/* SN2201 CPLD device. */ +static struct i2c_board_info nvsw_sn2201_cpld_devices[] = { + { + I2C_BOARD_INFO("nvsw-sn2201", 0x41), + }, +}; + +/* SN2201 CPLD board info. */ +static struct mlxreg_hotplug_device nvsw_sn2201_cpld_brdinfo[] = { + { + .brdinfo = &nvsw_sn2201_cpld_devices[0], + .nr = NVSW_SN2201_CPLD_NR, + }, +}; + +/* SN2201 main mux device. */ +static struct i2c_board_info nvsw_sn2201_main_mux_devices[] = { + { + I2C_BOARD_INFO("pca9548", 0x70), + }, +}; + +/* SN2201 main mux board info. */ +static struct mlxreg_hotplug_device nvsw_sn2201_main_mux_brdinfo[] = { + { + .brdinfo = &nvsw_sn2201_main_mux_devices[0], + .nr = NVSW_SN2201_MAIN_MUX_NR, + }, +}; + +/* SN2201 power devices. */ +static struct i2c_board_info nvsw_sn2201_pwr_devices[] = { + { + I2C_BOARD_INFO("pmbus", 0x58), + }, + { + I2C_BOARD_INFO("pmbus", 0x58), + }, +}; + +/* SN2201 fan devices. */ +static struct i2c_board_info nvsw_sn2201_fan_devices[] = { + { + I2C_BOARD_INFO("24c02", 0x50), + }, + { + I2C_BOARD_INFO("24c02", 0x51), + }, + { + I2C_BOARD_INFO("24c02", 0x52), + }, + { + I2C_BOARD_INFO("24c02", 0x53), + }, +}; + +/* SN2201 hotplug default data. */ +static struct mlxreg_core_data nvsw_sn2201_psu_items_data[] = { + { + .label = "psu1", + .reg = NVSW_SN2201_PS_PRSNT_STATUS_OFFSET, + .mask = BIT(0), + .hpdev.nr = NVSW_SN2201_NR_NONE, + }, + { + .label = "psu2", + .reg = NVSW_SN2201_PS_PRSNT_STATUS_OFFSET, + .mask = BIT(1), + .hpdev.nr = NVSW_SN2201_NR_NONE, + }, +}; + +static struct mlxreg_core_data nvsw_sn2201_pwr_items_data[] = { + { + .label = "pwr1", + .reg = NVSW_SN2201_PS_DC_OK_STATUS_OFFSET, + .mask = BIT(0), + .hpdev.brdinfo = &nvsw_sn2201_pwr_devices[0], + .hpdev.nr = NVSW_SN2201_MAIN_MUX_CH1_NR, + }, + { + .label = "pwr2", + .reg = NVSW_SN2201_PS_DC_OK_STATUS_OFFSET, + .mask = BIT(1), + .hpdev.brdinfo = &nvsw_sn2201_pwr_devices[1], + .hpdev.nr = NVSW_SN2201_MAIN_MUX_CH2_NR, + }, +}; + +static struct mlxreg_core_data nvsw_sn2201_fan_items_data[] = { + { + .label = "fan1", + .reg = NVSW_SN2201_FAN_PRSNT_STATUS_OFFSET, + .mask = BIT(0), + .hpdev.brdinfo = &nvsw_sn2201_fan_devices[0], + .hpdev.nr = NVSW_SN2201_NR_NONE, + }, + { + .label = "fan2", + .reg = NVSW_SN2201_FAN_PRSNT_STATUS_OFFSET, + .mask = BIT(1), + .hpdev.brdinfo = &nvsw_sn2201_fan_devices[1], + .hpdev.nr = NVSW_SN2201_NR_NONE, + }, + { + .label = "fan3", + .reg = NVSW_SN2201_FAN_PRSNT_STATUS_OFFSET, + .mask = BIT(2), + .hpdev.brdinfo = &nvsw_sn2201_fan_devices[2], + .hpdev.nr = NVSW_SN2201_NR_NONE, + }, + { + .label = "fan4", + .reg = NVSW_SN2201_FAN_PRSNT_STATUS_OFFSET, + .mask = BIT(3), + .hpdev.brdinfo = &nvsw_sn2201_fan_devices[3], + .hpdev.nr = NVSW_SN2201_NR_NONE, + }, +}; + +static struct mlxreg_core_data nvsw_sn2201_sys_items_data[] = { + { + .label = "nic_smb_alert", + .reg = NVSW_SN2201_ASIC_STATUS_OFFSET, + .mask = BIT(1), + .hpdev.nr = NVSW_SN2201_NR_NONE, + }, + { + .label = "cpu_sd", + .reg = NVSW_SN2201_ASIC_STATUS_OFFSET, + .mask = BIT(2), + .hpdev.nr = NVSW_SN2201_NR_NONE, + }, + { + .label = "mac_health", + .reg = NVSW_SN2201_ASIC_STATUS_OFFSET, + .mask = BIT(3), + .hpdev.nr = NVSW_SN2201_NR_NONE, + }, +}; + +static struct mlxreg_core_item nvsw_sn2201_items[] = { + { + .data = nvsw_sn2201_psu_items_data, + .aggr_mask = NVSW_SN2201_CPLD_AGGR_PSU_MASK_DEF, + .reg = NVSW_SN2201_PS_PRSNT_STATUS_OFFSET, + .mask = NVSW_SN2201_CPLD_PSU_MASK, + .count = ARRAY_SIZE(nvsw_sn2201_psu_items_data), + .inversed = 1, + .health = false, + }, + { + .data = nvsw_sn2201_pwr_items_data, + .aggr_mask = NVSW_SN2201_CPLD_AGGR_PWR_MASK_DEF, + .reg = NVSW_SN2201_PS_DC_OK_STATUS_OFFSET, + .mask = NVSW_SN2201_CPLD_PWR_MASK, + .count = ARRAY_SIZE(nvsw_sn2201_pwr_items_data), + .inversed = 0, + .health = false, + }, + { + .data = nvsw_sn2201_fan_items_data, + .aggr_mask = NVSW_SN2201_CPLD_AGGR_FAN_MASK_DEF, + .reg = NVSW_SN2201_FAN_PRSNT_STATUS_OFFSET, + .mask = NVSW_SN2201_CPLD_FAN_MASK, + .count = ARRAY_SIZE(nvsw_sn2201_fan_items_data), + .inversed = 1, + .health = false, + }, + { + .data = nvsw_sn2201_sys_items_data, + .aggr_mask = NVSW_SN2201_CPLD_AGGR_ASIC_MASK_DEF, + .reg = NVSW_SN2201_ASIC_STATUS_OFFSET, + .mask = NVSW_SN2201_CPLD_ASIC_MASK, + .count = ARRAY_SIZE(nvsw_sn2201_sys_items_data), + .inversed = 1, + .health = false, + }, +}; + +static +struct mlxreg_core_hotplug_platform_data nvsw_sn2201_hotplug = { + .items = nvsw_sn2201_items, + .counter = ARRAY_SIZE(nvsw_sn2201_items), + .cell = NVSW_SN2201_SYS_INT_STATUS_OFFSET, + .mask = NVSW_SN2201_CPLD_AGGR_MASK_DEF, +}; + +/* SN2201 static devices. */ +static struct i2c_board_info nvsw_sn2201_static_devices[] = { + { + I2C_BOARD_INFO("24c02", 0x57), + }, + { + I2C_BOARD_INFO("lm75", 0x4b), + }, + { + I2C_BOARD_INFO("24c64", 0x56), + }, + { + I2C_BOARD_INFO("ads1015", 0x49), + }, + { + I2C_BOARD_INFO("pca9546", 0x71), + }, + { + I2C_BOARD_INFO("emc2305", 0x4d), + }, + { + I2C_BOARD_INFO("lm75", 0x49), + }, + { + I2C_BOARD_INFO("pca9555", 0x27), + }, + { + I2C_BOARD_INFO("powr1014", 0x37), + }, + { + I2C_BOARD_INFO("lm75", 0x4f), + }, + { + I2C_BOARD_INFO("pmbus", 0x40), + }, +}; + +/* SN2201 default static board info. */ +static struct mlxreg_hotplug_device nvsw_sn2201_static_brdinfo[] = { + { + .brdinfo = &nvsw_sn2201_static_devices[0], + .nr = NVSW_SN2201_MAIN_NR, + }, + { + .brdinfo = &nvsw_sn2201_static_devices[1], + .nr = NVSW_SN2201_MAIN_MUX_CH0_NR, + }, + { + .brdinfo = &nvsw_sn2201_static_devices[2], + .nr = NVSW_SN2201_MAIN_MUX_CH0_NR, + }, + { + .brdinfo = &nvsw_sn2201_static_devices[3], + .nr = NVSW_SN2201_MAIN_MUX_CH0_NR, + }, + { + .brdinfo = &nvsw_sn2201_static_devices[4], + .nr = NVSW_SN2201_MAIN_MUX_CH3_NR, + }, + { + .brdinfo = &nvsw_sn2201_static_devices[5], + .nr = NVSW_SN2201_MAIN_MUX_CH5_NR, + }, + { + .brdinfo = &nvsw_sn2201_static_devices[6], + .nr = NVSW_SN2201_MAIN_MUX_CH5_NR, + }, + { + .brdinfo = &nvsw_sn2201_static_devices[7], + .nr = NVSW_SN2201_MAIN_MUX_CH5_NR, + }, + { + .brdinfo = &nvsw_sn2201_static_devices[8], + .nr = NVSW_SN2201_MAIN_MUX_CH6_NR, + }, + { + .brdinfo = &nvsw_sn2201_static_devices[9], + .nr = NVSW_SN2201_MAIN_MUX_CH6_NR, + }, + { + .brdinfo = &nvsw_sn2201_static_devices[10], + .nr = NVSW_SN2201_MAIN_MUX_CH7_NR, + }, +}; + +/* LED default data. */ +static struct mlxreg_core_data nvsw_sn2201_led_data[] = { + { + .label = "status:green", + .reg = NVSW_SN2201_FRONT_SYS_LED_CTRL_OFFSET, + .mask = GENMASK(7, 4), + }, + { + .label = "status:orange", + .reg = NVSW_SN2201_FRONT_SYS_LED_CTRL_OFFSET, + .mask = GENMASK(7, 4), + }, + { + .label = "psu:green", + .reg = NVSW_SN2201_FRONT_PSU_LED_CTRL_OFFSET, + .mask = GENMASK(7, 4), + }, + { + .label = "psu:orange", + .reg = NVSW_SN2201_FRONT_PSU_LED_CTRL_OFFSET, + .mask = GENMASK(7, 4), + }, + { + .label = "uid:blue", + .reg = NVSW_SN2201_FRONT_UID_LED_CTRL_OFFSET, + .mask = GENMASK(7, 4), + }, + { + .label = "fan1:green", + .reg = NVSW_SN2201_FAN_LED1_CTRL_OFFSET, + .mask = GENMASK(7, 4), + }, + { + .label = "fan1:orange", + .reg = NVSW_SN2201_FAN_LED1_CTRL_OFFSET, + .mask = GENMASK(7, 4), + }, + { + .label = "fan2:green", + .reg = NVSW_SN2201_FAN_LED1_CTRL_OFFSET, + .mask = GENMASK(3, 0), + }, + { + .label = "fan2:orange", + .reg = NVSW_SN2201_FAN_LED1_CTRL_OFFSET, + .mask = GENMASK(3, 0), + }, + { + .label = "fan3:green", + .reg = NVSW_SN2201_FAN_LED2_CTRL_OFFSET, + .mask = GENMASK(7, 4), + }, + { + .label = "fan3:orange", + .reg = NVSW_SN2201_FAN_LED2_CTRL_OFFSET, + .mask = GENMASK(7, 4), + }, + { + .label = "fan4:green", + .reg = NVSW_SN2201_FAN_LED2_CTRL_OFFSET, + .mask = GENMASK(3, 0), + }, + { + .label = "fan4:orange", + .reg = NVSW_SN2201_FAN_LED2_CTRL_OFFSET, + .mask = GENMASK(3, 0), + }, +}; + +static struct mlxreg_core_platform_data nvsw_sn2201_led = { + .data = nvsw_sn2201_led_data, + .counter = ARRAY_SIZE(nvsw_sn2201_led_data), +}; + +/* Default register access data. */ +static struct mlxreg_core_data nvsw_sn2201_io_data[] = { + { + .label = "cpld1_version", + .reg = NVSW_SN2201_CPLD_VER_OFFSET, + .bit = GENMASK(7, 0), + .mode = 0444, + }, + { + .label = "cpld1_version_min", + .reg = NVSW_SN2201_CPLD_MVER_OFFSET, + .bit = GENMASK(7, 0), + .mode = 0444, + }, + { + .label = "cpld1_pn", + .reg = NVSW_SN2201_CPLD_PN_OFFSET, + .bit = GENMASK(15, 0), + .mode = 0444, + .regnum = 2, + }, + { + .label = "psu1_on", + .reg = NVSW_SN2201_PSU_CTRL_OFFSET, + .mask = GENMASK(7, 0) & ~BIT(0), + .mode = 0644, + }, + { + .label = "psu2_on", + .reg = NVSW_SN2201_PSU_CTRL_OFFSET, + .mask = GENMASK(7, 0) & ~BIT(1), + .mode = 0644, + }, + { + .label = "pwr_cycle", + .reg = NVSW_SN2201_PSU_CTRL_OFFSET, + .mask = GENMASK(7, 0) & ~BIT(2), + .mode = 0644, + }, + { + .label = "asic_health", + .reg = NVSW_SN2201_SYS_STATUS_OFFSET, + .mask = GENMASK(4, 3), + .bit = 4, + .mode = 0444, + }, + { + .label = "qsfp_pwr_good", + .reg = NVSW_SN2201_SYS_STATUS_OFFSET, + .mask = GENMASK(7, 0) & ~BIT(0), + .mode = 0444, + }, + { + .label = "phy_reset", + .reg = NVSW_SN2201_SYS_RST_STATUS_OFFSET, + .mask = GENMASK(7, 0) & ~BIT(3), + .mode = 0644, + }, + { + .label = "mac_reset", + .reg = NVSW_SN2201_SYS_RST_STATUS_OFFSET, + .mask = GENMASK(7, 0) & ~BIT(2), + .mode = 0644, + }, + { + .label = "pwr_down", + .reg = NVSW_SN2201_RST_SW_CTRL_OFFSET, + .mask = GENMASK(7, 0) & ~BIT(0), + .mode = 0644, + }, + { + .label = "reset_long_pb", + .reg = NVSW_SN2201_RST_CAUSE1_OFFSET, + .mask = GENMASK(7, 0) & ~BIT(0), + .mode = 0444, + }, + { + .label = "reset_short_pb", + .reg = NVSW_SN2201_RST_CAUSE1_OFFSET, + .mask = GENMASK(7, 0) & ~BIT(1), + .mode = 0444, + }, + { + .label = "reset_aux_pwr_or_fu", + .reg = NVSW_SN2201_RST_CAUSE1_OFFSET, + .mask = GENMASK(7, 0) & ~BIT(2), + .mode = 0444, + }, + { + .label = "reset_swb_dc_dc_pwr_fail", + .reg = NVSW_SN2201_RST_CAUSE1_OFFSET, + .mask = GENMASK(7, 0) & ~BIT(3), + .mode = 0444, + }, + { + .label = "reset_sw_reset", + .reg = NVSW_SN2201_RST_CAUSE1_OFFSET, + .mask = GENMASK(7, 0) & ~BIT(4), + .mode = 0444, + }, + { + .label = "reset_fw_reset", + .reg = NVSW_SN2201_RST_CAUSE1_OFFSET, + .mask = GENMASK(7, 0) & ~BIT(5), + .mode = 0444, + }, + { + .label = "reset_swb_wd", + .reg = NVSW_SN2201_RST_CAUSE1_OFFSET, + .mask = GENMASK(7, 0) & ~BIT(6), + .mode = 0444, + }, + { + .label = "reset_asic_thermal", + .reg = NVSW_SN2201_RST_CAUSE1_OFFSET, + .mask = GENMASK(7, 0) & ~BIT(7), + .mode = 0444, + }, + { + .label = "reset_system", + .reg = NVSW_SN2201_RST_CAUSE2_OFFSET, + .mask = GENMASK(7, 0) & ~BIT(1), + .mode = 0444, + }, + { + .label = "reset_sw_pwr_off", + .reg = NVSW_SN2201_RST_CAUSE2_OFFSET, + .mask = GENMASK(7, 0) & ~BIT(2), + .mode = 0444, + }, + { + .label = "reset_cpu_pwr_fail_thermal", + .reg = NVSW_SN2201_RST_CAUSE2_OFFSET, + .mask = GENMASK(7, 0) & ~BIT(4), + .mode = 0444, + }, + { + .label = "reset_reload_bios", + .reg = NVSW_SN2201_RST_CAUSE2_OFFSET, + .mask = GENMASK(7, 0) & ~BIT(5), + .mode = 0444, + }, + { + .label = "reset_ac_pwr_fail", + .reg = NVSW_SN2201_RST_CAUSE2_OFFSET, + .mask = GENMASK(7, 0) & ~BIT(6), + .mode = 0444, + }, + { + .label = "psu1", + .reg = NVSW_SN2201_PS_PRSNT_STATUS_OFFSET, + .mask = GENMASK(7, 0) & ~BIT(0), + .mode = 0444, + }, + { + .label = "psu2", + .reg = NVSW_SN2201_PS_PRSNT_STATUS_OFFSET, + .mask = GENMASK(7, 0) & ~BIT(1), + .mode = 0444, + }, +}; + +static struct mlxreg_core_platform_data nvsw_sn2201_regs_io = { + .data = nvsw_sn2201_io_data, + .counter = ARRAY_SIZE(nvsw_sn2201_io_data), +}; + +/* Default watchdog data. */ +static struct mlxreg_core_data nvsw_sn2201_wd_data[] = { + { + .label = "action", + .reg = NVSW_SN2201_WD_ACT_OFFSET, + .mask = GENMASK(7, 1), + .bit = 0, + }, + { + .label = "timeout", + .reg = NVSW_SN2201_WD_TMR_OFFSET_LSB, + .mask = 0, + .health_cntr = NVSW_SN2201_WD_DFLT_TIMEOUT, + }, + { + .label = "timeleft", + .reg = NVSW_SN2201_WD_TMR_OFFSET_LSB, + .mask = 0, + }, + { + .label = "ping", + .reg = NVSW_SN2201_WD_ACT_OFFSET, + .mask = GENMASK(7, 1), + .bit = 0, + }, + { + .label = "reset", + .reg = NVSW_SN2201_RST_CAUSE1_OFFSET, + .mask = GENMASK(7, 0) & ~BIT(6), + .bit = 6, + }, +}; + +static struct mlxreg_core_platform_data nvsw_sn2201_wd = { + .data = nvsw_sn2201_wd_data, + .counter = ARRAY_SIZE(nvsw_sn2201_wd_data), + .version = MLX_WDT_TYPE3, + .identity = "mlx-wdt-main", +}; + +static int +nvsw_sn2201_create_static_devices(struct nvsw_sn2201 *nvsw_sn2201, + struct mlxreg_hotplug_device *devs, + int size) +{ + struct mlxreg_hotplug_device *dev = devs; + int i; + + /* Create I2C static devices. */ + for (i = 0; i < size; i++, dev++) { + dev->client = i2c_new_client_device(dev->adapter, dev->brdinfo); + if (IS_ERR(dev->client)) { + dev_err(nvsw_sn2201->dev, "Failed to create client %s at bus %d at addr 0x%02x\n", + dev->brdinfo->type, + dev->nr, dev->brdinfo->addr); + + dev->adapter = NULL; + goto fail_create_static_devices; + } + } + + return 0; + +fail_create_static_devices: + while (--i >= 0) { + dev = devs + i; + i2c_unregister_device(dev->client); + dev->client = NULL; + dev->adapter = NULL; + } + return IS_ERR(dev->client); +} + +static void nvsw_sn2201_destroy_static_devices(struct nvsw_sn2201 *nvsw_sn2201, + struct mlxreg_hotplug_device *devs, int size) +{ + struct mlxreg_hotplug_device *dev = devs; + int i; + + /* Destroy static I2C device for SN2201 static devices. */ + for (i = 0; i < size; i++, dev++) { + if (dev->client) { + i2c_unregister_device(dev->client); + dev->client = NULL; + i2c_put_adapter(dev->adapter); + dev->adapter = NULL; + } + } +} + +static int nvsw_sn2201_config_post_init(struct nvsw_sn2201 *nvsw_sn2201) +{ + struct mlxreg_hotplug_device *sn2201_dev; + struct i2c_adapter *adap; + struct device *dev; + int i, err; + + dev = nvsw_sn2201->dev; + adap = i2c_get_adapter(nvsw_sn2201->main_mux_deferred_nr); + if (!adap) { + dev_err(dev, "Failed to get adapter for bus %d\n", + nvsw_sn2201->main_mux_deferred_nr); + return -ENODEV; + } + i2c_put_adapter(adap); + + /* Update board info. */ + sn2201_dev = nvsw_sn2201->sn2201_devs; + for (i = 0; i < nvsw_sn2201->sn2201_devs_num; i++, sn2201_dev++) { + sn2201_dev->adapter = i2c_get_adapter(sn2201_dev->nr); + if (!sn2201_dev->adapter) + return -ENODEV; + i2c_put_adapter(sn2201_dev->adapter); + } + + err = nvsw_sn2201_create_static_devices(nvsw_sn2201, nvsw_sn2201->sn2201_devs, + nvsw_sn2201->sn2201_devs_num); + if (err) + dev_err(dev, "Failed to create static devices\n"); + + return err; +} + +static int nvsw_sn2201_config_init(struct nvsw_sn2201 *nvsw_sn2201, void *regmap) +{ + struct device *dev = nvsw_sn2201->dev; + int err; + + nvsw_sn2201->io_data = &nvsw_sn2201_regs_io; + nvsw_sn2201->led_data = &nvsw_sn2201_led; + nvsw_sn2201->wd_data = &nvsw_sn2201_wd; + nvsw_sn2201->hotplug_data = &nvsw_sn2201_hotplug; + + /* Register IO access driver. */ + if (nvsw_sn2201->io_data) { + nvsw_sn2201->io_data->regmap = regmap; + nvsw_sn2201->io_regs = + platform_device_register_resndata(dev, "mlxreg-io", PLATFORM_DEVID_NONE, NULL, 0, + nvsw_sn2201->io_data, + sizeof(*nvsw_sn2201->io_data)); + if (IS_ERR(nvsw_sn2201->io_regs)) { + err = PTR_ERR(nvsw_sn2201->io_regs); + goto fail_register_io; + } + } + + /* Register LED driver. */ + if (nvsw_sn2201->led_data) { + nvsw_sn2201->led_data->regmap = regmap; + nvsw_sn2201->led = + platform_device_register_resndata(dev, "leds-mlxreg", PLATFORM_DEVID_NONE, NULL, 0, + nvsw_sn2201->led_data, + sizeof(*nvsw_sn2201->led_data)); + if (IS_ERR(nvsw_sn2201->led)) { + err = PTR_ERR(nvsw_sn2201->led); + goto fail_register_led; + } + } + + /* Register WD driver. */ + if (nvsw_sn2201->wd_data) { + nvsw_sn2201->wd_data->regmap = regmap; + nvsw_sn2201->wd = + platform_device_register_resndata(dev, "mlx-wdt", PLATFORM_DEVID_NONE, NULL, 0, + nvsw_sn2201->wd_data, + sizeof(*nvsw_sn2201->wd_data)); + if (IS_ERR(nvsw_sn2201->wd)) { + err = PTR_ERR(nvsw_sn2201->wd); + goto fail_register_wd; + } + } + + /* Register hotplug driver. */ + if (nvsw_sn2201->hotplug_data) { + nvsw_sn2201->hotplug_data->regmap = regmap; + nvsw_sn2201->pdev_hotplug = + platform_device_register_resndata(dev, "mlxreg-hotplug", PLATFORM_DEVID_NONE, + nvsw_sn2201_cpld_res, + ARRAY_SIZE(nvsw_sn2201_cpld_res), + nvsw_sn2201->hotplug_data, + sizeof(*nvsw_sn2201->hotplug_data)); + if (IS_ERR(nvsw_sn2201->pdev_hotplug)) { + err = PTR_ERR(nvsw_sn2201->pdev_hotplug); + goto fail_register_hotplug; + } + } + + return nvsw_sn2201_config_post_init(nvsw_sn2201); + +fail_register_hotplug: + if (nvsw_sn2201->wd) + platform_device_unregister(nvsw_sn2201->wd); +fail_register_wd: + if (nvsw_sn2201->led) + platform_device_unregister(nvsw_sn2201->led); +fail_register_led: + if (nvsw_sn2201->io_regs) + platform_device_unregister(nvsw_sn2201->io_regs); +fail_register_io: + + return err; +} + +static void nvsw_sn2201_config_exit(struct nvsw_sn2201 *nvsw_sn2201) +{ + /* Unregister hotplug driver. */ + if (nvsw_sn2201->pdev_hotplug) + platform_device_unregister(nvsw_sn2201->pdev_hotplug); + /* Unregister WD driver. */ + if (nvsw_sn2201->wd) + platform_device_unregister(nvsw_sn2201->wd); + /* Unregister LED driver. */ + if (nvsw_sn2201->led) + platform_device_unregister(nvsw_sn2201->led); + /* Unregister IO access driver. */ + if (nvsw_sn2201->io_regs) + platform_device_unregister(nvsw_sn2201->io_regs); +} + +/* + * Initialization is divided into two parts: + * - I2C main bus init. + * - Mux creation and attaching devices to the mux, + * which assumes that the main bus is already created. + * This separation is required for synchronization between these two parts. + * Completion notify callback is used to make this flow synchronized. + */ +static int nvsw_sn2201_i2c_completion_notify(void *handle, int id) +{ + struct nvsw_sn2201 *nvsw_sn2201 = handle; + void *regmap; + int i, err; + + /* Create main mux. */ + nvsw_sn2201->main_mux_devs->adapter = i2c_get_adapter(nvsw_sn2201->main_mux_devs->nr); + if (!nvsw_sn2201->main_mux_devs->adapter) { + err = -ENODEV; + dev_err(nvsw_sn2201->dev, "Failed to get adapter for bus %d\n", + nvsw_sn2201->cpld_devs->nr); + goto i2c_get_adapter_main_fail; + } + + nvsw_sn2201->main_mux_devs_num = ARRAY_SIZE(nvsw_sn2201_main_mux_brdinfo); + err = nvsw_sn2201_create_static_devices(nvsw_sn2201, nvsw_sn2201->main_mux_devs, + nvsw_sn2201->main_mux_devs_num); + if (err) { + dev_err(nvsw_sn2201->dev, "Failed to create main mux devices\n"); + goto nvsw_sn2201_create_static_devices_fail; + } + + nvsw_sn2201->cpld_devs->adapter = i2c_get_adapter(nvsw_sn2201->cpld_devs->nr); + if (!nvsw_sn2201->cpld_devs->adapter) { + err = -ENODEV; + dev_err(nvsw_sn2201->dev, "Failed to get adapter for bus %d\n", + nvsw_sn2201->cpld_devs->nr); + goto i2c_get_adapter_fail; + } + + /* Create CPLD device. */ + nvsw_sn2201->cpld_devs->client = i2c_new_dummy_device(nvsw_sn2201->cpld_devs->adapter, + NVSW_SN2201_CPLD_I2CADDR); + if (IS_ERR(nvsw_sn2201->cpld_devs->client)) { + err = PTR_ERR(nvsw_sn2201->cpld_devs->client); + dev_err(nvsw_sn2201->dev, "Failed to create %s cpld device at bus %d at addr 0x%02x\n", + nvsw_sn2201->cpld_devs->brdinfo->type, nvsw_sn2201->cpld_devs->nr, + nvsw_sn2201->cpld_devs->brdinfo->addr); + goto i2c_new_dummy_fail; + } + + regmap = devm_regmap_init_i2c(nvsw_sn2201->cpld_devs->client, &nvsw_sn2201_regmap_conf); + if (IS_ERR(regmap)) { + err = PTR_ERR(regmap); + dev_err(nvsw_sn2201->dev, "Failed to initialise managed register map\n"); + goto devm_regmap_init_i2c_fail; + } + + /* Set default registers. */ + for (i = 0; i < nvsw_sn2201_regmap_conf.num_reg_defaults; i++) { + err = regmap_write(regmap, nvsw_sn2201_regmap_default[i].reg, + nvsw_sn2201_regmap_default[i].def); + if (err) { + dev_err(nvsw_sn2201->dev, "Failed to set register at offset 0x%02x to default value: 0x%02x\n", + nvsw_sn2201_regmap_default[i].reg, + nvsw_sn2201_regmap_default[i].def); + goto regmap_write_fail; + } + } + + /* Sync registers with hardware. */ + regcache_mark_dirty(regmap); + err = regcache_sync(regmap); + if (err) { + dev_err(nvsw_sn2201->dev, "Failed to Sync registers with hardware\n"); + goto regcache_sync_fail; + } + + /* Configure SN2201 board. */ + err = nvsw_sn2201_config_init(nvsw_sn2201, regmap); + if (err) { + dev_err(nvsw_sn2201->dev, "Failed to configure board\n"); + goto nvsw_sn2201_config_init_fail; + } + + return 0; + +nvsw_sn2201_config_init_fail: + nvsw_sn2201_config_exit(nvsw_sn2201); +regcache_sync_fail: +regmap_write_fail: +devm_regmap_init_i2c_fail: +i2c_new_dummy_fail: + i2c_put_adapter(nvsw_sn2201->cpld_devs->adapter); + nvsw_sn2201->cpld_devs->adapter = NULL; +i2c_get_adapter_fail: + /* Destroy SN2201 static I2C devices. */ + nvsw_sn2201_destroy_static_devices(nvsw_sn2201, nvsw_sn2201->sn2201_devs, + nvsw_sn2201->sn2201_devs_num); + /* Destroy main mux device. */ + nvsw_sn2201_destroy_static_devices(nvsw_sn2201, nvsw_sn2201->main_mux_devs, + nvsw_sn2201->main_mux_devs_num); +nvsw_sn2201_create_static_devices_fail: + i2c_put_adapter(nvsw_sn2201->main_mux_devs->adapter); +i2c_get_adapter_main_fail: + return err; +} + +static int nvsw_sn2201_config_pre_init(struct nvsw_sn2201 *nvsw_sn2201) +{ + nvsw_sn2201->i2c_data = &nvsw_sn2201_i2c_data; + + /* Register I2C controller. */ + nvsw_sn2201->i2c_data->handle = nvsw_sn2201; + nvsw_sn2201->i2c_data->completion_notify = nvsw_sn2201_i2c_completion_notify; + nvsw_sn2201->pdev_i2c = platform_device_register_resndata(nvsw_sn2201->dev, "i2c_mlxcpld", + NVSW_SN2201_MAIN_MUX_NR, + nvsw_sn2201_lpc_res, + ARRAY_SIZE(nvsw_sn2201_lpc_res), + nvsw_sn2201->i2c_data, + sizeof(*nvsw_sn2201->i2c_data)); + if (IS_ERR(nvsw_sn2201->pdev_i2c)) + return PTR_ERR(nvsw_sn2201->pdev_i2c); + + return 0; +} + +static int nvsw_sn2201_probe(struct platform_device *pdev) +{ + struct nvsw_sn2201 *nvsw_sn2201; + + nvsw_sn2201 = devm_kzalloc(&pdev->dev, sizeof(*nvsw_sn2201), GFP_KERNEL); + if (!nvsw_sn2201) + return -ENOMEM; + + nvsw_sn2201->dev = &pdev->dev; + platform_set_drvdata(pdev, nvsw_sn2201); + platform_device_add_resources(pdev, nvsw_sn2201_lpc_io_resources, + ARRAY_SIZE(nvsw_sn2201_lpc_io_resources)); + + nvsw_sn2201->main_mux_deferred_nr = NVSW_SN2201_MAIN_MUX_DEFER_NR; + nvsw_sn2201->main_mux_devs = nvsw_sn2201_main_mux_brdinfo; + nvsw_sn2201->cpld_devs = nvsw_sn2201_cpld_brdinfo; + nvsw_sn2201->sn2201_devs = nvsw_sn2201_static_brdinfo; + nvsw_sn2201->sn2201_devs_num = ARRAY_SIZE(nvsw_sn2201_static_brdinfo); + + return nvsw_sn2201_config_pre_init(nvsw_sn2201); +} + +static int nvsw_sn2201_remove(struct platform_device *pdev) +{ + struct nvsw_sn2201 *nvsw_sn2201 = platform_get_drvdata(pdev); + + /* Unregister underlying drivers. */ + nvsw_sn2201_config_exit(nvsw_sn2201); + + /* Destroy SN2201 static I2C devices. */ + nvsw_sn2201_destroy_static_devices(nvsw_sn2201, + nvsw_sn2201->sn2201_devs, + nvsw_sn2201->sn2201_devs_num); + + i2c_put_adapter(nvsw_sn2201->cpld_devs->adapter); + nvsw_sn2201->cpld_devs->adapter = NULL; + /* Destroy main mux device. */ + nvsw_sn2201_destroy_static_devices(nvsw_sn2201, + nvsw_sn2201->main_mux_devs, + nvsw_sn2201->main_mux_devs_num); + + /* Unregister I2C controller. */ + if (nvsw_sn2201->pdev_i2c) + platform_device_unregister(nvsw_sn2201->pdev_i2c); + + return 0; +} + +static const struct acpi_device_id nvsw_sn2201_acpi_ids[] = { + {"NVSN2201", 0}, + {} +}; + +MODULE_DEVICE_TABLE(acpi, nvsw_sn2201_acpi_ids); + +static struct platform_driver nvsw_sn2201_driver = { + .probe = nvsw_sn2201_probe, + .remove = nvsw_sn2201_remove, + .driver = { + .name = "nvsw-sn2201", + .acpi_match_table = nvsw_sn2201_acpi_ids, + }, +}; + +module_platform_driver(nvsw_sn2201_driver); + +MODULE_AUTHOR("Nvidia"); +MODULE_DESCRIPTION("Nvidia sn2201 platform driver"); +MODULE_LICENSE("Dual BSD/GPL"); +MODULE_ALIAS("platform:nvsw-sn2201"); diff --git a/drivers/platform/surface/aggregator/core.c b/drivers/platform/surface/aggregator/core.c index d384d36098c2..a62c5dfe42d6 100644 --- a/drivers/platform/surface/aggregator/core.c +++ b/drivers/platform/surface/aggregator/core.c @@ -817,7 +817,7 @@ err_cpkg: err_bus: return status; } -module_init(ssam_core_init); +subsys_initcall(ssam_core_init); static void __exit ssam_core_exit(void) { diff --git a/drivers/platform/surface/surface_gpe.c b/drivers/platform/surface/surface_gpe.c index c1775db29efb..ec66fde28e75 100644 --- a/drivers/platform/surface/surface_gpe.c +++ b/drivers/platform/surface/surface_gpe.c @@ -100,6 +100,14 @@ static const struct dmi_system_id dmi_lid_device_table[] = { .driver_data = (void *)lid_device_props_l4D, }, { + .ident = "Surface Pro 8", + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Microsoft Corporation"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "Surface Pro 8"), + }, + .driver_data = (void *)lid_device_props_l4B, + }, + { .ident = "Surface Book 1", .matches = { DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Microsoft Corporation"), diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig index 5d9dd70e4e0f..f08ad85683cb 100644 --- a/drivers/platform/x86/Kconfig +++ b/drivers/platform/x86/Kconfig @@ -1152,6 +1152,14 @@ config SIEMENS_SIMATIC_IPC To compile this driver as a module, choose M here: the module will be called simatic-ipc. +config WINMATE_FM07_KEYS + tristate "Winmate FM07/FM07P front-panel keys driver" + depends on INPUT + help + Winmate FM07 and FM07P in-vehicle computers have a row of five + buttons below the display. This module adds an input device + that delivers key events when these buttons are pressed. + endif # X86_PLATFORM_DEVICES config PMC_ATOM diff --git a/drivers/platform/x86/Makefile b/drivers/platform/x86/Makefile index fe4d4c8970ef..4a59f47a46e2 100644 --- a/drivers/platform/x86/Makefile +++ b/drivers/platform/x86/Makefile @@ -130,3 +130,6 @@ obj-$(CONFIG_PMC_ATOM) += pmc_atom.o # Siemens Simatic Industrial PCs obj-$(CONFIG_SIEMENS_SIMATIC_IPC) += simatic-ipc.o + +# Winmate +obj-$(CONFIG_WINMATE_FM07_KEYS) += winmate-fm07-keys.o diff --git a/drivers/platform/x86/acerhdf.c b/drivers/platform/x86/acerhdf.c index 6b8b3ab8db48..3463629f8764 100644 --- a/drivers/platform/x86/acerhdf.c +++ b/drivers/platform/x86/acerhdf.c @@ -584,21 +584,6 @@ static struct platform_driver acerhdf_driver = { .remove = acerhdf_remove, }; -/* checks if str begins with start */ -static int str_starts_with(const char *str, const char *start) -{ - unsigned long str_len = 0, start_len = 0; - - str_len = strlen(str); - start_len = strlen(start); - - if (str_len >= start_len && - !strncmp(str, start, start_len)) - return 1; - - return 0; -} - /* check hardware */ static int __init acerhdf_check_hardware(void) { @@ -651,9 +636,9 @@ static int __init acerhdf_check_hardware(void) * check if actual hardware BIOS vendor, product and version * IDs start with the strings of BIOS table entry */ - if (str_starts_with(vendor, bt->vendor) && - str_starts_with(product, bt->product) && - str_starts_with(version, bt->version)) { + if (strstarts(vendor, bt->vendor) && + strstarts(product, bt->product) && + strstarts(version, bt->version)) { found = 1; break; } diff --git a/drivers/platform/x86/amd-pmc.c b/drivers/platform/x86/amd-pmc.c index e9d0dbbb2887..f11d18beac18 100644 --- a/drivers/platform/x86/amd-pmc.c +++ b/drivers/platform/x86/amd-pmc.c @@ -160,8 +160,10 @@ MODULE_PARM_DESC(enable_stb, "Enable the STB debug mechanism"); static struct amd_pmc_dev pmc; static int amd_pmc_send_cmd(struct amd_pmc_dev *dev, u32 arg, u32 *data, u8 msg, bool ret); -static int amd_pmc_write_stb(struct amd_pmc_dev *dev, u32 data); static int amd_pmc_read_stb(struct amd_pmc_dev *dev, u32 *buf); +#ifdef CONFIG_SUSPEND +static int amd_pmc_write_stb(struct amd_pmc_dev *dev, u32 data); +#endif static inline u32 amd_pmc_reg_read(struct amd_pmc_dev *dev, int reg_offset) { @@ -190,26 +192,6 @@ struct smu_metrics { u64 timecondition_notmet_totaltime[SOC_SUBSYSTEM_IP_MAX]; } __packed; -static int amd_pmc_get_smu_version(struct amd_pmc_dev *dev) -{ - int rc; - u32 val; - - rc = amd_pmc_send_cmd(dev, 0, &val, SMU_MSG_GETSMUVERSION, 1); - if (rc) - return rc; - - dev->smu_program = (val >> 24) & GENMASK(7, 0); - dev->major = (val >> 16) & GENMASK(7, 0); - dev->minor = (val >> 8) & GENMASK(7, 0); - dev->rev = (val >> 0) & GENMASK(7, 0); - - dev_dbg(dev->dev, "SMU program %u version is %u.%u.%u\n", - dev->smu_program, dev->major, dev->minor, dev->rev); - - return 0; -} - static int amd_pmc_stb_debugfs_open(struct inode *inode, struct file *filp) { struct amd_pmc_dev *dev = filp->f_inode->i_private; @@ -292,6 +274,40 @@ static const struct file_operations amd_pmc_stb_debugfs_fops_v2 = { .release = amd_pmc_stb_debugfs_release_v2, }; +#if defined(CONFIG_SUSPEND) || defined(CONFIG_DEBUG_FS) +static int amd_pmc_setup_smu_logging(struct amd_pmc_dev *dev) +{ + if (dev->cpu_id == AMD_CPU_ID_PCO) { + dev_warn_once(dev->dev, "SMU debugging info not supported on this platform\n"); + return -EINVAL; + } + + /* Get Active devices list from SMU */ + if (!dev->active_ips) + amd_pmc_send_cmd(dev, 0, &dev->active_ips, SMU_MSG_GET_SUP_CONSTRAINTS, 1); + + /* Get dram address */ + if (!dev->smu_virt_addr) { + u32 phys_addr_low, phys_addr_hi; + u64 smu_phys_addr; + + amd_pmc_send_cmd(dev, 0, &phys_addr_low, SMU_MSG_LOG_GETDRAM_ADDR_LO, 1); + amd_pmc_send_cmd(dev, 0, &phys_addr_hi, SMU_MSG_LOG_GETDRAM_ADDR_HI, 1); + smu_phys_addr = ((u64)phys_addr_hi << 32 | phys_addr_low); + + dev->smu_virt_addr = devm_ioremap(dev->dev, smu_phys_addr, + sizeof(struct smu_metrics)); + if (!dev->smu_virt_addr) + return -ENOMEM; + } + + /* Start the logging */ + amd_pmc_send_cmd(dev, 0, NULL, SMU_MSG_LOG_RESET, 0); + amd_pmc_send_cmd(dev, 0, NULL, SMU_MSG_LOG_START, 0); + + return 0; +} + static int amd_pmc_idlemask_read(struct amd_pmc_dev *pdev, struct device *dev, struct seq_file *s) { @@ -319,12 +335,21 @@ static int amd_pmc_idlemask_read(struct amd_pmc_dev *pdev, struct device *dev, static int get_metrics_table(struct amd_pmc_dev *pdev, struct smu_metrics *table) { + if (!pdev->smu_virt_addr) { + int ret = amd_pmc_setup_smu_logging(pdev); + + if (ret) + return ret; + } + if (pdev->cpu_id == AMD_CPU_ID_PCO) return -ENODEV; memcpy_fromio(table, pdev->smu_virt_addr, sizeof(struct smu_metrics)); return 0; } +#endif /* CONFIG_SUSPEND || CONFIG_DEBUG_FS */ +#ifdef CONFIG_SUSPEND static void amd_pmc_validate_deepest(struct amd_pmc_dev *pdev) { struct smu_metrics table; @@ -338,6 +363,7 @@ static void amd_pmc_validate_deepest(struct amd_pmc_dev *pdev) dev_dbg(pdev->dev, "Last suspend in deepest state for %lluus\n", table.timein_s0i3_lastcapture); } +#endif #ifdef CONFIG_DEBUG_FS static int smu_fw_info_show(struct seq_file *s, void *unused) @@ -375,6 +401,17 @@ static int s0ix_stats_show(struct seq_file *s, void *unused) struct amd_pmc_dev *dev = s->private; u64 entry_time, exit_time, residency; + /* Use FCH registers to get the S0ix stats */ + if (!dev->fch_virt_addr) { + u32 base_addr_lo = FCH_BASE_PHY_ADDR_LOW; + u32 base_addr_hi = FCH_BASE_PHY_ADDR_HIGH; + u64 fch_phys_addr = ((u64)base_addr_hi << 32 | base_addr_lo); + + dev->fch_virt_addr = devm_ioremap(dev->dev, fch_phys_addr, FCH_SSC_MAPPING_SIZE); + if (!dev->fch_virt_addr) + return -ENOMEM; + } + entry_time = ioread32(dev->fch_virt_addr + FCH_S0I3_ENTRY_TIME_H_OFFSET); entry_time = entry_time << 32 | ioread32(dev->fch_virt_addr + FCH_S0I3_ENTRY_TIME_L_OFFSET); @@ -394,11 +431,38 @@ static int s0ix_stats_show(struct seq_file *s, void *unused) } DEFINE_SHOW_ATTRIBUTE(s0ix_stats); +static int amd_pmc_get_smu_version(struct amd_pmc_dev *dev) +{ + int rc; + u32 val; + + rc = amd_pmc_send_cmd(dev, 0, &val, SMU_MSG_GETSMUVERSION, 1); + if (rc) + return rc; + + dev->smu_program = (val >> 24) & GENMASK(7, 0); + dev->major = (val >> 16) & GENMASK(7, 0); + dev->minor = (val >> 8) & GENMASK(7, 0); + dev->rev = (val >> 0) & GENMASK(7, 0); + + dev_dbg(dev->dev, "SMU program %u version is %u.%u.%u\n", + dev->smu_program, dev->major, dev->minor, dev->rev); + + return 0; +} + static int amd_pmc_idlemask_show(struct seq_file *s, void *unused) { struct amd_pmc_dev *dev = s->private; int rc; + /* we haven't yet read SMU version */ + if (!dev->major) { + rc = amd_pmc_get_smu_version(dev); + if (rc) + return rc; + } + if (dev->major > 56 || (dev->major >= 55 && dev->minor >= 37)) { rc = amd_pmc_idlemask_read(dev, NULL, s); if (rc) @@ -445,32 +509,6 @@ static inline void amd_pmc_dbgfs_unregister(struct amd_pmc_dev *dev) } #endif /* CONFIG_DEBUG_FS */ -static int amd_pmc_setup_smu_logging(struct amd_pmc_dev *dev) -{ - u32 phys_addr_low, phys_addr_hi; - u64 smu_phys_addr; - - if (dev->cpu_id == AMD_CPU_ID_PCO) - return -EINVAL; - - /* Get Active devices list from SMU */ - amd_pmc_send_cmd(dev, 0, &dev->active_ips, SMU_MSG_GET_SUP_CONSTRAINTS, 1); - - /* Get dram address */ - amd_pmc_send_cmd(dev, 0, &phys_addr_low, SMU_MSG_LOG_GETDRAM_ADDR_LO, 1); - amd_pmc_send_cmd(dev, 0, &phys_addr_hi, SMU_MSG_LOG_GETDRAM_ADDR_HI, 1); - smu_phys_addr = ((u64)phys_addr_hi << 32 | phys_addr_low); - - dev->smu_virt_addr = devm_ioremap(dev->dev, smu_phys_addr, sizeof(struct smu_metrics)); - if (!dev->smu_virt_addr) - return -ENOMEM; - - /* Start the logging */ - amd_pmc_send_cmd(dev, 0, NULL, SMU_MSG_LOG_START, 0); - - return 0; -} - static void amd_pmc_dump_registers(struct amd_pmc_dev *dev) { u32 value, message, argument, response; @@ -569,6 +607,7 @@ out_unlock: return rc; } +#ifdef CONFIG_SUSPEND static int amd_pmc_get_os_hint(struct amd_pmc_dev *dev) { switch (dev->cpu_id) { @@ -634,8 +673,7 @@ static void amd_pmc_s2idle_prepare(void) u32 arg = 1; /* Reset and Start SMU logging - to monitor the s0i3 stats */ - amd_pmc_send_cmd(pdev, 0, NULL, SMU_MSG_LOG_RESET, 0); - amd_pmc_send_cmd(pdev, 0, NULL, SMU_MSG_LOG_START, 0); + amd_pmc_setup_smu_logging(pdev); /* Activate CZN specific RTC functionality */ if (pdev->cpu_id == AMD_CPU_ID_CZN) { @@ -694,6 +732,7 @@ static struct acpi_s2idle_dev_ops amd_pmc_s2idle_dev_ops = { .prepare = amd_pmc_s2idle_prepare, .restore = amd_pmc_s2idle_restore, }; +#endif static const struct pci_device_id pmc_pci_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, AMD_CPU_ID_YC) }, @@ -733,6 +772,7 @@ static int amd_pmc_s2d_init(struct amd_pmc_dev *dev) return 0; } +#ifdef CONFIG_SUSPEND static int amd_pmc_write_stb(struct amd_pmc_dev *dev, u32 data) { int err; @@ -753,6 +793,7 @@ static int amd_pmc_write_stb(struct amd_pmc_dev *dev, u32 data) return 0; } +#endif static int amd_pmc_read_stb(struct amd_pmc_dev *dev, u32 *buf) { @@ -782,7 +823,7 @@ static int amd_pmc_probe(struct platform_device *pdev) struct amd_pmc_dev *dev = &pmc; struct pci_dev *rdev; u32 base_addr_lo, base_addr_hi; - u64 base_addr, fch_phys_addr; + u64 base_addr; int err; u32 val; @@ -836,32 +877,18 @@ static int amd_pmc_probe(struct platform_device *pdev) mutex_init(&dev->lock); - /* Use FCH registers to get the S0ix stats */ - base_addr_lo = FCH_BASE_PHY_ADDR_LOW; - base_addr_hi = FCH_BASE_PHY_ADDR_HIGH; - fch_phys_addr = ((u64)base_addr_hi << 32 | base_addr_lo); - dev->fch_virt_addr = devm_ioremap(dev->dev, fch_phys_addr, FCH_SSC_MAPPING_SIZE); - if (!dev->fch_virt_addr) { - err = -ENOMEM; - goto err_pci_dev_put; - } - - /* Use SMU to get the s0i3 debug stats */ - err = amd_pmc_setup_smu_logging(dev); - if (err) - dev_err(dev->dev, "SMU debugging info not supported on this platform\n"); - if (enable_stb && dev->cpu_id == AMD_CPU_ID_YC) { err = amd_pmc_s2d_init(dev); if (err) return err; } - amd_pmc_get_smu_version(dev); platform_set_drvdata(pdev, dev); +#ifdef CONFIG_SUSPEND err = acpi_register_lps0_dev(&amd_pmc_s2idle_dev_ops); if (err) dev_warn(dev->dev, "failed to register LPS0 sleep handler, expect increased power consumption\n"); +#endif amd_pmc_dbgfs_register(dev); return 0; @@ -875,7 +902,9 @@ static int amd_pmc_remove(struct platform_device *pdev) { struct amd_pmc_dev *dev = platform_get_drvdata(pdev); +#ifdef CONFIG_SUSPEND acpi_unregister_lps0_dev(&amd_pmc_s2idle_dev_ops); +#endif amd_pmc_dbgfs_unregister(dev); pci_dev_put(dev->rdev); mutex_destroy(&dev->lock); diff --git a/drivers/platform/x86/asus-nb-wmi.c b/drivers/platform/x86/asus-nb-wmi.c index a81dc4b191b7..57a07db659cb 100644 --- a/drivers/platform/x86/asus-nb-wmi.c +++ b/drivers/platform/x86/asus-nb-wmi.c @@ -553,6 +553,7 @@ static const struct key_entry asus_nb_wmi_keymap[] = { { KE_KEY, 0x7D, { KEY_BLUETOOTH } }, /* Bluetooth Enable */ { KE_KEY, 0x7E, { KEY_BLUETOOTH } }, /* Bluetooth Disable */ { KE_KEY, 0x82, { KEY_CAMERA } }, + { KE_KEY, 0x86, { KEY_PROG1 } }, /* MyASUS Key */ { KE_KEY, 0x88, { KEY_RFKILL } }, /* Radio Toggle Key */ { KE_KEY, 0x8A, { KEY_PROG1 } }, /* Color enhancement mode */ { KE_KEY, 0x8C, { KEY_SWITCHVIDEOMODE } }, /* SDSP DVI only */ diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c index 2104a2621e50..62ce198a3463 100644 --- a/drivers/platform/x86/asus-wmi.c +++ b/drivers/platform/x86/asus-wmi.c @@ -371,10 +371,14 @@ static int asus_wmi_evaluate_method_buf(u32 method_id, switch (obj->type) { case ACPI_TYPE_BUFFER: - if (obj->buffer.length > size) + if (obj->buffer.length > size) { err = -ENOSPC; - if (obj->buffer.length == 0) + break; + } + if (obj->buffer.length == 0) { err = -ENODATA; + break; + } memcpy(ret_buffer, obj->buffer.pointer, obj->buffer.length); break; @@ -2223,9 +2227,10 @@ static int fan_curve_check_present(struct asus_wmi *asus, bool *available, err = fan_curve_get_factory_default(asus, fan_dev); if (err) { - if (err == -ENODEV || err == -ENODATA) - return 0; - return err; + pr_debug("fan_curve_get_factory_default(0x%08x) failed: %d\n", + fan_dev, err); + /* Don't cause probe to fail on devices without fan-curves */ + return 0; } *available = true; @@ -2529,7 +2534,7 @@ static struct attribute *asus_fan_curve_attr[] = { static umode_t asus_fan_curve_is_visible(struct kobject *kobj, struct attribute *attr, int idx) { - struct device *dev = container_of(kobj, struct device, kobj); + struct device *dev = kobj_to_dev(kobj); struct asus_wmi *asus = dev_get_drvdata(dev->parent); /* @@ -3109,7 +3114,7 @@ static void asus_wmi_handle_event_code(int code, struct asus_wmi *asus) if (!sparse_keymap_report_event(asus->inputdev, code, key_value, autorelease)) - pr_info("Unknown key %x pressed\n", code); + pr_info("Unknown key code 0x%x\n", code); } static void asus_wmi_notify(u32 value, void *context) diff --git a/drivers/platform/x86/barco-p50-gpio.c b/drivers/platform/x86/barco-p50-gpio.c index f5c72e33f9ae..05534287bc26 100644 --- a/drivers/platform/x86/barco-p50-gpio.c +++ b/drivers/platform/x86/barco-p50-gpio.c @@ -10,7 +10,6 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#include <linux/io.h> #include <linux/delay.h> #include <linux/dmi.h> #include <linux/err.h> diff --git a/drivers/platform/x86/dell/dcdbas.c b/drivers/platform/x86/dell/dcdbas.c index db3633fafbd5..42beafbc54b2 100644 --- a/drivers/platform/x86/dell/dcdbas.c +++ b/drivers/platform/x86/dell/dcdbas.c @@ -40,13 +40,10 @@ static struct platform_device *dcdbas_pdev; -static u8 *smi_data_buf; -static dma_addr_t smi_data_buf_handle; -static unsigned long smi_data_buf_size; static unsigned long max_smi_data_buf_size = MAX_SMI_DATA_BUF_SIZE; -static u32 smi_data_buf_phys_addr; static DEFINE_MUTEX(smi_data_lock); static u8 *bios_buffer; +static struct smi_buffer smi_buf; static unsigned int host_control_action; static unsigned int host_control_smi_type; @@ -54,23 +51,49 @@ static unsigned int host_control_on_shutdown; static bool wsmt_enabled; +int dcdbas_smi_alloc(struct smi_buffer *smi_buffer, unsigned long size) +{ + smi_buffer->virt = dma_alloc_coherent(&dcdbas_pdev->dev, size, + &smi_buffer->dma, GFP_KERNEL); + if (!smi_buffer->virt) { + dev_dbg(&dcdbas_pdev->dev, + "%s: failed to allocate memory size %lu\n", + __func__, size); + return -ENOMEM; + } + smi_buffer->size = size; + + dev_dbg(&dcdbas_pdev->dev, "%s: phys: %x size: %lu\n", + __func__, (u32)smi_buffer->dma, smi_buffer->size); + + return 0; +} +EXPORT_SYMBOL_GPL(dcdbas_smi_alloc); + +void dcdbas_smi_free(struct smi_buffer *smi_buffer) +{ + if (!smi_buffer->virt) + return; + + dev_dbg(&dcdbas_pdev->dev, "%s: phys: %x size: %lu\n", + __func__, (u32)smi_buffer->dma, smi_buffer->size); + dma_free_coherent(&dcdbas_pdev->dev, smi_buffer->size, + smi_buffer->virt, smi_buffer->dma); + smi_buffer->virt = NULL; + smi_buffer->dma = 0; + smi_buffer->size = 0; +} +EXPORT_SYMBOL_GPL(dcdbas_smi_free); + /** * smi_data_buf_free: free SMI data buffer */ static void smi_data_buf_free(void) { - if (!smi_data_buf || wsmt_enabled) + if (!smi_buf.virt || wsmt_enabled) return; - dev_dbg(&dcdbas_pdev->dev, "%s: phys: %x size: %lu\n", - __func__, smi_data_buf_phys_addr, smi_data_buf_size); - - dma_free_coherent(&dcdbas_pdev->dev, smi_data_buf_size, smi_data_buf, - smi_data_buf_handle); - smi_data_buf = NULL; - smi_data_buf_handle = 0; - smi_data_buf_phys_addr = 0; - smi_data_buf_size = 0; + dcdbas_smi_free(&smi_buf); } /** @@ -78,39 +101,29 @@ static void smi_data_buf_free(void) */ static int smi_data_buf_realloc(unsigned long size) { - void *buf; - dma_addr_t handle; + struct smi_buffer tmp; + int ret; - if (smi_data_buf_size >= size) + if (smi_buf.size >= size) return 0; if (size > max_smi_data_buf_size) return -EINVAL; /* new buffer is needed */ - buf = dma_alloc_coherent(&dcdbas_pdev->dev, size, &handle, GFP_KERNEL); - if (!buf) { - dev_dbg(&dcdbas_pdev->dev, - "%s: failed to allocate memory size %lu\n", - __func__, size); - return -ENOMEM; - } - /* memory zeroed by dma_alloc_coherent */ + ret = dcdbas_smi_alloc(&tmp, size); + if (ret) + return ret; - if (smi_data_buf) - memcpy(buf, smi_data_buf, smi_data_buf_size); + /* memory zeroed by dma_alloc_coherent */ + if (smi_buf.virt) + memcpy(tmp.virt, smi_buf.virt, smi_buf.size); /* free any existing buffer */ smi_data_buf_free(); /* set up new buffer for use */ - smi_data_buf = buf; - smi_data_buf_handle = handle; - smi_data_buf_phys_addr = (u32) virt_to_phys(buf); - smi_data_buf_size = size; - - dev_dbg(&dcdbas_pdev->dev, "%s: phys: %x size: %lu\n", - __func__, smi_data_buf_phys_addr, smi_data_buf_size); + smi_buf = tmp; return 0; } @@ -119,14 +132,14 @@ static ssize_t smi_data_buf_phys_addr_show(struct device *dev, struct device_attribute *attr, char *buf) { - return sprintf(buf, "%x\n", smi_data_buf_phys_addr); + return sprintf(buf, "%x\n", (u32)smi_buf.dma); } static ssize_t smi_data_buf_size_show(struct device *dev, struct device_attribute *attr, char *buf) { - return sprintf(buf, "%lu\n", smi_data_buf_size); + return sprintf(buf, "%lu\n", smi_buf.size); } static ssize_t smi_data_buf_size_store(struct device *dev, @@ -155,8 +168,8 @@ static ssize_t smi_data_read(struct file *filp, struct kobject *kobj, ssize_t ret; mutex_lock(&smi_data_lock); - ret = memory_read_from_buffer(buf, count, &pos, smi_data_buf, - smi_data_buf_size); + ret = memory_read_from_buffer(buf, count, &pos, smi_buf.virt, + smi_buf.size); mutex_unlock(&smi_data_lock); return ret; } @@ -176,7 +189,7 @@ static ssize_t smi_data_write(struct file *filp, struct kobject *kobj, if (ret) goto out; - memcpy(smi_data_buf + pos, buf, count); + memcpy(smi_buf.virt + pos, buf, count); ret = count; out: mutex_unlock(&smi_data_lock); @@ -307,11 +320,11 @@ static ssize_t smi_request_store(struct device *dev, mutex_lock(&smi_data_lock); - if (smi_data_buf_size < sizeof(struct smi_cmd)) { + if (smi_buf.size < sizeof(struct smi_cmd)) { ret = -ENODEV; goto out; } - smi_cmd = (struct smi_cmd *)smi_data_buf; + smi_cmd = (struct smi_cmd *)smi_buf.virt; switch (val) { case 2: @@ -327,20 +340,20 @@ static ssize_t smi_request_store(struct device *dev, * Provide physical address of command buffer field within * the struct smi_cmd to BIOS. * - * Because the address that smi_cmd (smi_data_buf) points to + * Because the address that smi_cmd (smi_buf.virt) points to * will be from memremap() of a non-memory address if WSMT * is present, we can't use virt_to_phys() on smi_cmd, so * we have to use the physical address that was saved when * the virtual address for smi_cmd was received. */ - smi_cmd->ebx = smi_data_buf_phys_addr + + smi_cmd->ebx = (u32)smi_buf.dma + offsetof(struct smi_cmd, command_buffer); ret = dcdbas_smi_request(smi_cmd); if (!ret) ret = count; break; case 0: - memset(smi_data_buf, 0, smi_data_buf_size); + memset(smi_buf.virt, 0, smi_buf.size); ret = count; break; default: @@ -356,7 +369,7 @@ out: /** * host_control_smi: generate host control SMI * - * Caller must set up the host control command in smi_data_buf. + * Caller must set up the host control command in smi_buf.virt. */ static int host_control_smi(void) { @@ -367,14 +380,14 @@ static int host_control_smi(void) s8 cmd_status; u8 index; - apm_cmd = (struct apm_cmd *)smi_data_buf; + apm_cmd = (struct apm_cmd *)smi_buf.virt; apm_cmd->status = ESM_STATUS_CMD_UNSUCCESSFUL; switch (host_control_smi_type) { case HC_SMITYPE_TYPE1: spin_lock_irqsave(&rtc_lock, flags); /* write SMI data buffer physical address */ - data = (u8 *)&smi_data_buf_phys_addr; + data = (u8 *)&smi_buf.dma; for (index = PE1300_CMOS_CMD_STRUCT_PTR; index < (PE1300_CMOS_CMD_STRUCT_PTR + 4); index++, data++) { @@ -405,7 +418,7 @@ static int host_control_smi(void) case HC_SMITYPE_TYPE3: spin_lock_irqsave(&rtc_lock, flags); /* write SMI data buffer physical address */ - data = (u8 *)&smi_data_buf_phys_addr; + data = (u8 *)&smi_buf.dma; for (index = PE1400_CMOS_CMD_STRUCT_PTR; index < (PE1400_CMOS_CMD_STRUCT_PTR + 4); index++, data++) { @@ -450,7 +463,7 @@ static int host_control_smi(void) * This function is called by the driver after the system has * finished shutting down if the user application specified a * host control action to perform on shutdown. It is safe to - * use smi_data_buf at this point because the system has finished + * use smi_buf.virt at this point because the system has finished * shutting down and no userspace apps are running. */ static void dcdbas_host_control(void) @@ -464,18 +477,18 @@ static void dcdbas_host_control(void) action = host_control_action; host_control_action = HC_ACTION_NONE; - if (!smi_data_buf) { + if (!smi_buf.virt) { dev_dbg(&dcdbas_pdev->dev, "%s: no SMI buffer\n", __func__); return; } - if (smi_data_buf_size < sizeof(struct apm_cmd)) { + if (smi_buf.size < sizeof(struct apm_cmd)) { dev_dbg(&dcdbas_pdev->dev, "%s: SMI buffer too small\n", __func__); return; } - apm_cmd = (struct apm_cmd *)smi_data_buf; + apm_cmd = (struct apm_cmd *)smi_buf.virt; /* power off takes precedence */ if (action & HC_ACTION_HOST_CONTROL_POWEROFF) { @@ -583,11 +596,11 @@ remap: return -ENOMEM; } - /* First 8 bytes is for a semaphore, not part of the smi_data_buf */ - smi_data_buf_phys_addr = bios_buf_paddr + 8; - smi_data_buf = bios_buffer + 8; - smi_data_buf_size = remap_size - 8; - max_smi_data_buf_size = smi_data_buf_size; + /* First 8 bytes is for a semaphore, not part of the smi_buf.virt */ + smi_buf.dma = bios_buf_paddr + 8; + smi_buf.virt = bios_buffer + 8; + smi_buf.size = remap_size - 8; + max_smi_data_buf_size = smi_buf.size; wsmt_enabled = true; dev_info(&dcdbas_pdev->dev, "WSMT found, using firmware-provided SMI buffer.\n"); diff --git a/drivers/platform/x86/dell/dcdbas.h b/drivers/platform/x86/dell/dcdbas.h index c3cca5433525..942a23ddded0 100644 --- a/drivers/platform/x86/dell/dcdbas.h +++ b/drivers/platform/x86/dell/dcdbas.h @@ -105,5 +105,14 @@ struct smm_eps_table { u64 num_of_4k_pages; } __packed; +struct smi_buffer { + u8 *virt; + unsigned long size; + dma_addr_t dma; +}; + +int dcdbas_smi_alloc(struct smi_buffer *smi_buffer, unsigned long size); +void dcdbas_smi_free(struct smi_buffer *smi_buffer); + #endif /* _DCDBAS_H_ */ diff --git a/drivers/platform/x86/dell/dell-laptop.c b/drivers/platform/x86/dell/dell-laptop.c index 8230e7a68a5e..1321687d923e 100644 --- a/drivers/platform/x86/dell/dell-laptop.c +++ b/drivers/platform/x86/dell/dell-laptop.c @@ -80,6 +80,10 @@ static struct quirk_entry quirk_dell_inspiron_1012 = { .kbd_led_not_present = true, }; +static struct quirk_entry quirk_dell_latitude_7520 = { + .kbd_missing_ac_tag = true, +}; + static struct platform_driver platform_driver = { .driver = { .name = "dell-laptop", @@ -336,6 +340,15 @@ static const struct dmi_system_id dell_quirks[] __initconst = { }, .driver_data = &quirk_dell_inspiron_1012, }, + { + .callback = dmi_matched, + .ident = "Dell Latitude 7520", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Latitude 7520"), + }, + .driver_data = &quirk_dell_latitude_7520, + }, { } }; diff --git a/drivers/platform/x86/dell/dell-smbios-smm.c b/drivers/platform/x86/dell/dell-smbios-smm.c index 320c032418ac..4d375985c85f 100644 --- a/drivers/platform/x86/dell/dell-smbios-smm.c +++ b/drivers/platform/x86/dell/dell-smbios-smm.c @@ -20,6 +20,7 @@ static int da_command_address; static int da_command_code; +static struct smi_buffer smi_buf; static struct calling_interface_buffer *buffer; static struct platform_device *platform_device; static DEFINE_MUTEX(smm_mutex); @@ -57,7 +58,7 @@ static int dell_smbios_smm_call(struct calling_interface_buffer *input) command.magic = SMI_CMD_MAGIC; command.command_address = da_command_address; command.command_code = da_command_code; - command.ebx = virt_to_phys(buffer); + command.ebx = smi_buf.dma; command.ecx = 0x42534931; mutex_lock(&smm_mutex); @@ -101,9 +102,10 @@ int init_dell_smbios_smm(void) * Allocate buffer below 4GB for SMI data--only 32-bit physical addr * is passed to SMI handler. */ - buffer = (void *)__get_free_page(GFP_KERNEL | GFP_DMA32); - if (!buffer) - return -ENOMEM; + ret = dcdbas_smi_alloc(&smi_buf, PAGE_SIZE); + if (ret) + return ret; + buffer = (void *)smi_buf.virt; dmi_walk(find_cmd_address, NULL); @@ -138,7 +140,7 @@ fail_platform_device_add: fail_wsmt: fail_platform_device_alloc: - free_page((unsigned long)buffer); + dcdbas_smi_free(&smi_buf); return ret; } @@ -147,6 +149,6 @@ void exit_dell_smbios_smm(void) if (platform_device) { dell_smbios_unregister_device(&platform_device->dev); platform_device_unregister(platform_device); - free_page((unsigned long)buffer); + dcdbas_smi_free(&smi_buf); } } diff --git a/drivers/platform/x86/gigabyte-wmi.c b/drivers/platform/x86/gigabyte-wmi.c index 658bab4b7964..1ef606e3ef80 100644 --- a/drivers/platform/x86/gigabyte-wmi.c +++ b/drivers/platform/x86/gigabyte-wmi.c @@ -148,8 +148,11 @@ static const struct dmi_system_id gigabyte_wmi_known_working_platforms[] = { DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B550I AORUS PRO AX"), DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B550M AORUS PRO-P"), DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B550M DS3H"), + DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B660 GAMING X DDR4"), DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("Z390 I AORUS PRO WIFI-CF"), + DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("Z490 AORUS ELITE AC"), DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("X570 AORUS ELITE"), + DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("X570 AORUS ELITE WIFI"), DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("X570 GAMING X"), DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("X570 I AORUS PRO WIFI"), DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("X570 UD"), diff --git a/drivers/platform/x86/hp-wmi.c b/drivers/platform/x86/hp-wmi.c index 0e9a25b56e0e..667f94bba905 100644 --- a/drivers/platform/x86/hp-wmi.c +++ b/drivers/platform/x86/hp-wmi.c @@ -605,6 +605,7 @@ static int hp_wmi_rfkill2_refresh(void) for (i = 0; i < rfkill2_count; i++) { int num = rfkill2[i].num; struct bios_rfkill2_device_state *devstate; + devstate = &state.device[num]; if (num >= state.count || @@ -625,6 +626,7 @@ static ssize_t display_show(struct device *dev, struct device_attribute *attr, char *buf) { int value = hp_wmi_read_int(HPWMI_DISPLAY_QUERY); + if (value < 0) return value; return sprintf(buf, "%d\n", value); @@ -634,6 +636,7 @@ static ssize_t hddtemp_show(struct device *dev, struct device_attribute *attr, char *buf) { int value = hp_wmi_read_int(HPWMI_HDDTEMP_QUERY); + if (value < 0) return value; return sprintf(buf, "%d\n", value); @@ -643,6 +646,7 @@ static ssize_t als_show(struct device *dev, struct device_attribute *attr, char *buf) { int value = hp_wmi_read_int(HPWMI_ALS_QUERY); + if (value < 0) return value; return sprintf(buf, "%d\n", value); @@ -652,6 +656,7 @@ static ssize_t dock_show(struct device *dev, struct device_attribute *attr, char *buf) { int value = hp_wmi_get_dock_state(); + if (value < 0) return value; return sprintf(buf, "%d\n", value); @@ -661,6 +666,7 @@ static ssize_t tablet_show(struct device *dev, struct device_attribute *attr, char *buf) { int value = hp_wmi_get_tablet_mode(); + if (value < 0) return value; return sprintf(buf, "%d\n", value); @@ -671,6 +677,7 @@ static ssize_t postcode_show(struct device *dev, struct device_attribute *attr, { /* Get the POST error code of previous boot failure. */ int value = hp_wmi_read_int(HPWMI_POSTCODEERROR_QUERY); + if (value < 0) return value; return sprintf(buf, "0x%x\n", value); @@ -1013,6 +1020,7 @@ static int __init hp_wmi_rfkill2_setup(struct platform_device *device) struct rfkill *rfkill; enum rfkill_type type; char *name; + switch (state.device[i].radio_type) { case HPWMI_WIFI: type = RFKILL_TYPE_WLAN; diff --git a/drivers/platform/x86/intel/Kconfig b/drivers/platform/x86/intel/Kconfig index 1f01a8a23c57..794968bda115 100644 --- a/drivers/platform/x86/intel/Kconfig +++ b/drivers/platform/x86/intel/Kconfig @@ -4,6 +4,7 @@ # source "drivers/platform/x86/intel/atomisp2/Kconfig" +source "drivers/platform/x86/intel/ifs/Kconfig" source "drivers/platform/x86/intel/int1092/Kconfig" source "drivers/platform/x86/intel/int3472/Kconfig" source "drivers/platform/x86/intel/pmc/Kconfig" diff --git a/drivers/platform/x86/intel/Makefile b/drivers/platform/x86/intel/Makefile index c61bc3e97121..717933dd0cfd 100644 --- a/drivers/platform/x86/intel/Makefile +++ b/drivers/platform/x86/intel/Makefile @@ -5,6 +5,7 @@ # obj-$(CONFIG_INTEL_ATOMISP2_PDX86) += atomisp2/ +obj-$(CONFIG_INTEL_IFS) += ifs/ obj-$(CONFIG_INTEL_SAR_INT1092) += int1092/ obj-$(CONFIG_INTEL_SKL_INT3472) += int3472/ obj-$(CONFIG_INTEL_PMC_CORE) += pmc/ diff --git a/drivers/platform/x86/intel/chtwc_int33fe.c b/drivers/platform/x86/intel/chtwc_int33fe.c index 0de509fbf020..c52ac23e2331 100644 --- a/drivers/platform/x86/intel/chtwc_int33fe.c +++ b/drivers/platform/x86/intel/chtwc_int33fe.c @@ -389,6 +389,8 @@ static int cht_int33fe_typec_probe(struct platform_device *pdev) goto out_unregister_fusb302; } + platform_set_drvdata(pdev, data); + return 0; out_unregister_fusb302: diff --git a/drivers/platform/x86/intel/hid.c b/drivers/platform/x86/intel/hid.c index 2def562c6e1d..216d31e3403d 100644 --- a/drivers/platform/x86/intel/hid.c +++ b/drivers/platform/x86/intel/hid.c @@ -238,7 +238,7 @@ static bool intel_hid_evaluate_method(acpi_handle handle, method_name = (char *)intel_hid_dsm_fn_to_method[fn_index]; - if (!(intel_hid_dsm_fn_mask & fn_index)) + if (!(intel_hid_dsm_fn_mask & BIT(fn_index))) goto skip_dsm_eval; obj = acpi_evaluate_dsm_typed(handle, &intel_dsm_guid, diff --git a/drivers/platform/x86/intel/ifs/Kconfig b/drivers/platform/x86/intel/ifs/Kconfig new file mode 100644 index 000000000000..7ce896434b8f --- /dev/null +++ b/drivers/platform/x86/intel/ifs/Kconfig @@ -0,0 +1,13 @@ +config INTEL_IFS + tristate "Intel In Field Scan" + depends on X86 && CPU_SUP_INTEL && 64BIT && SMP + select INTEL_IFS_DEVICE + help + Enable support for the In Field Scan capability in select + CPUs. The capability allows for running low level tests via + a scan image distributed by Intel via Github to validate CPU + operation beyond baseline RAS capabilities. To compile this + support as a module, choose M here. The module will be called + intel_ifs. + + If unsure, say N. diff --git a/drivers/platform/x86/intel/ifs/Makefile b/drivers/platform/x86/intel/ifs/Makefile new file mode 100644 index 000000000000..30f035ef5581 --- /dev/null +++ b/drivers/platform/x86/intel/ifs/Makefile @@ -0,0 +1,3 @@ +obj-$(CONFIG_INTEL_IFS) += intel_ifs.o + +intel_ifs-objs := core.o load.o runtest.o sysfs.o diff --git a/drivers/platform/x86/intel/ifs/core.c b/drivers/platform/x86/intel/ifs/core.c new file mode 100644 index 000000000000..27204e3d674d --- /dev/null +++ b/drivers/platform/x86/intel/ifs/core.c @@ -0,0 +1,73 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright(c) 2022 Intel Corporation. */ + +#include <linux/module.h> +#include <linux/kdev_t.h> +#include <linux/semaphore.h> + +#include <asm/cpu_device_id.h> + +#include "ifs.h" + +#define X86_MATCH(model) \ + X86_MATCH_VENDOR_FAM_MODEL_FEATURE(INTEL, 6, \ + INTEL_FAM6_##model, X86_FEATURE_CORE_CAPABILITIES, NULL) + +static const struct x86_cpu_id ifs_cpu_ids[] __initconst = { + X86_MATCH(SAPPHIRERAPIDS_X), + {} +}; +MODULE_DEVICE_TABLE(x86cpu, ifs_cpu_ids); + +static struct ifs_device ifs_device = { + .data = { + .integrity_cap_bit = MSR_INTEGRITY_CAPS_PERIODIC_BIST_BIT, + }, + .misc = { + .name = "intel_ifs_0", + .nodename = "intel_ifs/0", + .minor = MISC_DYNAMIC_MINOR, + }, +}; + +static int __init ifs_init(void) +{ + const struct x86_cpu_id *m; + u64 msrval; + + m = x86_match_cpu(ifs_cpu_ids); + if (!m) + return -ENODEV; + + if (rdmsrl_safe(MSR_IA32_CORE_CAPS, &msrval)) + return -ENODEV; + + if (!(msrval & MSR_IA32_CORE_CAPS_INTEGRITY_CAPS)) + return -ENODEV; + + if (rdmsrl_safe(MSR_INTEGRITY_CAPS, &msrval)) + return -ENODEV; + + ifs_device.misc.groups = ifs_get_groups(); + + if ((msrval & BIT(ifs_device.data.integrity_cap_bit)) && + !misc_register(&ifs_device.misc)) { + down(&ifs_sem); + ifs_load_firmware(ifs_device.misc.this_device); + up(&ifs_sem); + return 0; + } + + return -ENODEV; +} + +static void __exit ifs_exit(void) +{ + misc_deregister(&ifs_device.misc); +} + +module_init(ifs_init); +module_exit(ifs_exit); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Intel In Field Scan (IFS) device"); diff --git a/drivers/platform/x86/intel/ifs/ifs.h b/drivers/platform/x86/intel/ifs/ifs.h new file mode 100644 index 000000000000..73c8e91cf144 --- /dev/null +++ b/drivers/platform/x86/intel/ifs/ifs.h @@ -0,0 +1,234 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright(c) 2022 Intel Corporation. */ + +#ifndef _IFS_H_ +#define _IFS_H_ + +/** + * DOC: In-Field Scan + * + * ============= + * In-Field Scan + * ============= + * + * Introduction + * ------------ + * + * In Field Scan (IFS) is a hardware feature to run circuit level tests on + * a CPU core to detect problems that are not caught by parity or ECC checks. + * Future CPUs will support more than one type of test which will show up + * with a new platform-device instance-id, for now only .0 is exposed. + * + * + * IFS Image + * --------- + * + * Intel provides a firmware file containing the scan tests via + * github [#f1]_. Similar to microcode there is a separate file for each + * family-model-stepping. + * + * IFS Image Loading + * ----------------- + * + * The driver loads the tests into memory reserved BIOS local to each CPU + * socket in a two step process using writes to MSRs to first load the + * SHA hashes for the test. Then the tests themselves. Status MSRs provide + * feedback on the success/failure of these steps. When a new test file + * is installed it can be loaded by writing to the driver reload file:: + * + * # echo 1 > /sys/devices/virtual/misc/intel_ifs_0/reload + * + * Similar to microcode, the current version of the scan tests is stored + * in a fixed location: /lib/firmware/intel/ifs.0/family-model-stepping.scan + * + * Running tests + * ------------- + * + * Tests are run by the driver synchronizing execution of all threads on a + * core and then writing to the ACTIVATE_SCAN MSR on all threads. Instruction + * execution continues when: + * + * 1) All tests have completed. + * 2) Execution was interrupted. + * 3) A test detected a problem. + * + * Note that ALL THREADS ON THE CORE ARE EFFECTIVELY OFFLINE FOR THE + * DURATION OF THE TEST. This can be up to 200 milliseconds. If the system + * is running latency sensitive applications that cannot tolerate an + * interruption of this magnitude, the system administrator must arrange + * to migrate those applications to other cores before running a core test. + * It may also be necessary to redirect interrupts to other CPUs. + * + * In all cases reading the SCAN_STATUS MSR provides details on what + * happened. The driver makes the value of this MSR visible to applications + * via the "details" file (see below). Interrupted tests may be restarted. + * + * The IFS driver provides sysfs interfaces via /sys/devices/virtual/misc/intel_ifs_0/ + * to control execution: + * + * Test a specific core:: + * + * # echo <cpu#> > /sys/devices/virtual/misc/intel_ifs_0/run_test + * + * when HT is enabled any of the sibling cpu# can be specified to test + * its corresponding physical core. Since the tests are per physical core, + * the result of testing any thread is same. All siblings must be online + * to run a core test. It is only necessary to test one thread. + * + * For e.g. to test core corresponding to cpu5 + * + * # echo 5 > /sys/devices/virtual/misc/intel_ifs_0/run_test + * + * Results of the last test is provided in /sys:: + * + * $ cat /sys/devices/virtual/misc/intel_ifs_0/status + * pass + * + * Status can be one of pass, fail, untested + * + * Additional details of the last test is provided by the details file:: + * + * $ cat /sys/devices/virtual/misc/intel_ifs_0/details + * 0x8081 + * + * The details file reports the hex value of the SCAN_STATUS MSR. + * Hardware defined error codes are documented in volume 4 of the Intel + * Software Developer's Manual but the error_code field may contain one of + * the following driver defined software codes: + * + * +------+--------------------+ + * | 0xFD | Software timeout | + * +------+--------------------+ + * | 0xFE | Partial completion | + * +------+--------------------+ + * + * Driver design choices + * --------------------- + * + * 1) The ACTIVATE_SCAN MSR allows for running any consecutive subrange of + * available tests. But the driver always tries to run all tests and only + * uses the subrange feature to restart an interrupted test. + * + * 2) Hardware allows for some number of cores to be tested in parallel. + * The driver does not make use of this, it only tests one core at a time. + * + * .. [#f1] https://github.com/intel/TBD + */ +#include <linux/device.h> +#include <linux/miscdevice.h> + +#define MSR_COPY_SCAN_HASHES 0x000002c2 +#define MSR_SCAN_HASHES_STATUS 0x000002c3 +#define MSR_AUTHENTICATE_AND_COPY_CHUNK 0x000002c4 +#define MSR_CHUNKS_AUTHENTICATION_STATUS 0x000002c5 +#define MSR_ACTIVATE_SCAN 0x000002c6 +#define MSR_SCAN_STATUS 0x000002c7 +#define SCAN_NOT_TESTED 0 +#define SCAN_TEST_PASS 1 +#define SCAN_TEST_FAIL 2 + +/* MSR_SCAN_HASHES_STATUS bit fields */ +union ifs_scan_hashes_status { + u64 data; + struct { + u32 chunk_size :16; + u32 num_chunks :8; + u32 rsvd1 :8; + u32 error_code :8; + u32 rsvd2 :11; + u32 max_core_limit :12; + u32 valid :1; + }; +}; + +/* MSR_CHUNKS_AUTH_STATUS bit fields */ +union ifs_chunks_auth_status { + u64 data; + struct { + u32 valid_chunks :8; + u32 total_chunks :8; + u32 rsvd1 :16; + u32 error_code :8; + u32 rsvd2 :24; + }; +}; + +/* MSR_ACTIVATE_SCAN bit fields */ +union ifs_scan { + u64 data; + struct { + u32 start :8; + u32 stop :8; + u32 rsvd :16; + u32 delay :31; + u32 sigmce :1; + }; +}; + +/* MSR_SCAN_STATUS bit fields */ +union ifs_status { + u64 data; + struct { + u32 chunk_num :8; + u32 chunk_stop_index :8; + u32 rsvd1 :16; + u32 error_code :8; + u32 rsvd2 :22; + u32 control_error :1; + u32 signature_error :1; + }; +}; + +/* + * Driver populated error-codes + * 0xFD: Test timed out before completing all the chunks. + * 0xFE: not all scan chunks were executed. Maximum forward progress retries exceeded. + */ +#define IFS_SW_TIMEOUT 0xFD +#define IFS_SW_PARTIAL_COMPLETION 0xFE + +/** + * struct ifs_data - attributes related to intel IFS driver + * @integrity_cap_bit: MSR_INTEGRITY_CAPS bit enumerating this test + * @loaded_version: stores the currently loaded ifs image version. + * @loaded: If a valid test binary has been loaded into the memory + * @loading_error: Error occurred on another CPU while loading image + * @valid_chunks: number of chunks which could be validated. + * @status: it holds simple status pass/fail/untested + * @scan_details: opaque scan status code from h/w + */ +struct ifs_data { + int integrity_cap_bit; + int loaded_version; + bool loaded; + bool loading_error; + int valid_chunks; + int status; + u64 scan_details; +}; + +struct ifs_work { + struct work_struct w; + struct device *dev; +}; + +struct ifs_device { + struct ifs_data data; + struct miscdevice misc; +}; + +static inline struct ifs_data *ifs_get_data(struct device *dev) +{ + struct miscdevice *m = dev_get_drvdata(dev); + struct ifs_device *d = container_of(m, struct ifs_device, misc); + + return &d->data; +} + +void ifs_load_firmware(struct device *dev); +int do_core_test(int cpu, struct device *dev); +const struct attribute_group **ifs_get_groups(void); + +extern struct semaphore ifs_sem; + +#endif diff --git a/drivers/platform/x86/intel/ifs/load.c b/drivers/platform/x86/intel/ifs/load.c new file mode 100644 index 000000000000..d056617ddc85 --- /dev/null +++ b/drivers/platform/x86/intel/ifs/load.c @@ -0,0 +1,266 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright(c) 2022 Intel Corporation. */ + +#include <linux/firmware.h> +#include <asm/cpu.h> +#include <linux/slab.h> +#include <asm/microcode_intel.h> + +#include "ifs.h" + +struct ifs_header { + u32 header_ver; + u32 blob_revision; + u32 date; + u32 processor_sig; + u32 check_sum; + u32 loader_rev; + u32 processor_flags; + u32 metadata_size; + u32 total_size; + u32 fusa_info; + u64 reserved; +}; + +#define IFS_HEADER_SIZE (sizeof(struct ifs_header)) +static struct ifs_header *ifs_header_ptr; /* pointer to the ifs image header */ +static u64 ifs_hash_ptr; /* Address of ifs metadata (hash) */ +static u64 ifs_test_image_ptr; /* 256B aligned address of test pattern */ +static DECLARE_COMPLETION(ifs_done); + +static const char * const scan_hash_status[] = { + [0] = "No error reported", + [1] = "Attempt to copy scan hashes when copy already in progress", + [2] = "Secure Memory not set up correctly", + [3] = "FuSaInfo.ProgramID does not match or ff-mm-ss does not match", + [4] = "Reserved", + [5] = "Integrity check failed", + [6] = "Scan reload or test is in progress" +}; + +static const char * const scan_authentication_status[] = { + [0] = "No error reported", + [1] = "Attempt to authenticate a chunk which is already marked as authentic", + [2] = "Chunk authentication error. The hash of chunk did not match expected value" +}; + +/* + * To copy scan hashes and authenticate test chunks, the initiating cpu must point + * to the EDX:EAX to the test image in linear address. + * Run wrmsr(MSR_COPY_SCAN_HASHES) for scan hash copy and run wrmsr(MSR_AUTHENTICATE_AND_COPY_CHUNK) + * for scan hash copy and test chunk authentication. + */ +static void copy_hashes_authenticate_chunks(struct work_struct *work) +{ + struct ifs_work *local_work = container_of(work, struct ifs_work, w); + union ifs_scan_hashes_status hashes_status; + union ifs_chunks_auth_status chunk_status; + struct device *dev = local_work->dev; + int i, num_chunks, chunk_size; + struct ifs_data *ifsd; + u64 linear_addr, base; + u32 err_code; + + ifsd = ifs_get_data(dev); + /* run scan hash copy */ + wrmsrl(MSR_COPY_SCAN_HASHES, ifs_hash_ptr); + rdmsrl(MSR_SCAN_HASHES_STATUS, hashes_status.data); + + /* enumerate the scan image information */ + num_chunks = hashes_status.num_chunks; + chunk_size = hashes_status.chunk_size * 1024; + err_code = hashes_status.error_code; + + if (!hashes_status.valid) { + ifsd->loading_error = true; + if (err_code >= ARRAY_SIZE(scan_hash_status)) { + dev_err(dev, "invalid error code 0x%x for hash copy\n", err_code); + goto done; + } + dev_err(dev, "Hash copy error : %s", scan_hash_status[err_code]); + goto done; + } + + /* base linear address to the scan data */ + base = ifs_test_image_ptr; + + /* scan data authentication and copy chunks to secured memory */ + for (i = 0; i < num_chunks; i++) { + linear_addr = base + i * chunk_size; + linear_addr |= i; + + wrmsrl(MSR_AUTHENTICATE_AND_COPY_CHUNK, linear_addr); + rdmsrl(MSR_CHUNKS_AUTHENTICATION_STATUS, chunk_status.data); + + ifsd->valid_chunks = chunk_status.valid_chunks; + err_code = chunk_status.error_code; + + if (err_code) { + ifsd->loading_error = true; + if (err_code >= ARRAY_SIZE(scan_authentication_status)) { + dev_err(dev, + "invalid error code 0x%x for authentication\n", err_code); + goto done; + } + dev_err(dev, "Chunk authentication error %s\n", + scan_authentication_status[err_code]); + goto done; + } + } +done: + complete(&ifs_done); +} + +/* + * IFS requires scan chunks authenticated per each socket in the platform. + * Once the test chunk is authenticated, it is automatically copied to secured memory + * and proceed the authentication for the next chunk. + */ +static int scan_chunks_sanity_check(struct device *dev) +{ + int metadata_size, curr_pkg, cpu, ret = -ENOMEM; + struct ifs_data *ifsd = ifs_get_data(dev); + bool *package_authenticated; + struct ifs_work local_work; + char *test_ptr; + + package_authenticated = kcalloc(topology_max_packages(), sizeof(bool), GFP_KERNEL); + if (!package_authenticated) + return ret; + + metadata_size = ifs_header_ptr->metadata_size; + + /* Spec says that if the Meta Data Size = 0 then it should be treated as 2000 */ + if (metadata_size == 0) + metadata_size = 2000; + + /* Scan chunk start must be 256 byte aligned */ + if ((metadata_size + IFS_HEADER_SIZE) % 256) { + dev_err(dev, "Scan pattern offset within the binary is not 256 byte aligned\n"); + return -EINVAL; + } + + test_ptr = (char *)ifs_header_ptr + IFS_HEADER_SIZE + metadata_size; + ifsd->loading_error = false; + + ifs_test_image_ptr = (u64)test_ptr; + ifsd->loaded_version = ifs_header_ptr->blob_revision; + + /* copy the scan hash and authenticate per package */ + cpus_read_lock(); + for_each_online_cpu(cpu) { + curr_pkg = topology_physical_package_id(cpu); + if (package_authenticated[curr_pkg]) + continue; + reinit_completion(&ifs_done); + local_work.dev = dev; + INIT_WORK(&local_work.w, copy_hashes_authenticate_chunks); + schedule_work_on(cpu, &local_work.w); + wait_for_completion(&ifs_done); + if (ifsd->loading_error) + goto out; + package_authenticated[curr_pkg] = 1; + } + ret = 0; +out: + cpus_read_unlock(); + kfree(package_authenticated); + + return ret; +} + +static int ifs_sanity_check(struct device *dev, + const struct microcode_header_intel *mc_header) +{ + unsigned long total_size, data_size; + u32 sum, *mc; + + total_size = get_totalsize(mc_header); + data_size = get_datasize(mc_header); + + if ((data_size + MC_HEADER_SIZE > total_size) || (total_size % sizeof(u32))) { + dev_err(dev, "bad ifs data file size.\n"); + return -EINVAL; + } + + if (mc_header->ldrver != 1 || mc_header->hdrver != 1) { + dev_err(dev, "invalid/unknown ifs update format.\n"); + return -EINVAL; + } + + mc = (u32 *)mc_header; + sum = 0; + for (int i = 0; i < total_size / sizeof(u32); i++) + sum += mc[i]; + + if (sum) { + dev_err(dev, "bad ifs data checksum, aborting.\n"); + return -EINVAL; + } + + return 0; +} + +static bool find_ifs_matching_signature(struct device *dev, struct ucode_cpu_info *uci, + const struct microcode_header_intel *shdr) +{ + unsigned int mc_size; + + mc_size = get_totalsize(shdr); + + if (!mc_size || ifs_sanity_check(dev, shdr) < 0) { + dev_err(dev, "ifs sanity check failure\n"); + return false; + } + + if (!intel_cpu_signatures_match(uci->cpu_sig.sig, uci->cpu_sig.pf, shdr->sig, shdr->pf)) { + dev_err(dev, "ifs signature, pf not matching\n"); + return false; + } + + return true; +} + +static bool ifs_image_sanity_check(struct device *dev, const struct microcode_header_intel *data) +{ + struct ucode_cpu_info uci; + + intel_cpu_collect_info(&uci); + + return find_ifs_matching_signature(dev, &uci, data); +} + +/* + * Load ifs image. Before loading ifs module, the ifs image must be located + * in /lib/firmware/intel/ifs and named as {family/model/stepping}.{testname}. + */ +void ifs_load_firmware(struct device *dev) +{ + struct ifs_data *ifsd = ifs_get_data(dev); + const struct firmware *fw; + char scan_path[32]; + int ret; + + snprintf(scan_path, sizeof(scan_path), "intel/ifs/%02x-%02x-%02x.scan", + boot_cpu_data.x86, boot_cpu_data.x86_model, boot_cpu_data.x86_stepping); + + ret = request_firmware_direct(&fw, scan_path, dev); + if (ret) { + dev_err(dev, "ifs file %s load failed\n", scan_path); + goto done; + } + + if (!ifs_image_sanity_check(dev, (struct microcode_header_intel *)fw->data)) { + dev_err(dev, "ifs header sanity check failed\n"); + goto release; + } + + ifs_header_ptr = (struct ifs_header *)fw->data; + ifs_hash_ptr = (u64)(ifs_header_ptr + 1); + + ret = scan_chunks_sanity_check(dev); +release: + release_firmware(fw); +done: + ifsd->loaded = (ret == 0); +} diff --git a/drivers/platform/x86/intel/ifs/runtest.c b/drivers/platform/x86/intel/ifs/runtest.c new file mode 100644 index 000000000000..b2ca2bb4501f --- /dev/null +++ b/drivers/platform/x86/intel/ifs/runtest.c @@ -0,0 +1,252 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright(c) 2022 Intel Corporation. */ + +#include <linux/cpu.h> +#include <linux/delay.h> +#include <linux/fs.h> +#include <linux/nmi.h> +#include <linux/slab.h> +#include <linux/stop_machine.h> + +#include "ifs.h" + +/* + * Note all code and data in this file is protected by + * ifs_sem. On HT systems all threads on a core will + * execute together, but only the first thread on the + * core will update results of the test. + */ + +#define CREATE_TRACE_POINTS +#include <trace/events/intel_ifs.h> + +/* Max retries on the same chunk */ +#define MAX_IFS_RETRIES 5 + +/* + * Number of TSC cycles that a logical CPU will wait for the other + * logical CPU on the core in the WRMSR(ACTIVATE_SCAN). + */ +#define IFS_THREAD_WAIT 100000 + +enum ifs_status_err_code { + IFS_NO_ERROR = 0, + IFS_OTHER_THREAD_COULD_NOT_JOIN = 1, + IFS_INTERRUPTED_BEFORE_RENDEZVOUS = 2, + IFS_POWER_MGMT_INADEQUATE_FOR_SCAN = 3, + IFS_INVALID_CHUNK_RANGE = 4, + IFS_MISMATCH_ARGUMENTS_BETWEEN_THREADS = 5, + IFS_CORE_NOT_CAPABLE_CURRENTLY = 6, + IFS_UNASSIGNED_ERROR_CODE = 7, + IFS_EXCEED_NUMBER_OF_THREADS_CONCURRENT = 8, + IFS_INTERRUPTED_DURING_EXECUTION = 9, +}; + +static const char * const scan_test_status[] = { + [IFS_NO_ERROR] = "SCAN no error", + [IFS_OTHER_THREAD_COULD_NOT_JOIN] = "Other thread could not join.", + [IFS_INTERRUPTED_BEFORE_RENDEZVOUS] = "Interrupt occurred prior to SCAN coordination.", + [IFS_POWER_MGMT_INADEQUATE_FOR_SCAN] = + "Core Abort SCAN Response due to power management condition.", + [IFS_INVALID_CHUNK_RANGE] = "Non valid chunks in the range", + [IFS_MISMATCH_ARGUMENTS_BETWEEN_THREADS] = "Mismatch in arguments between threads T0/T1.", + [IFS_CORE_NOT_CAPABLE_CURRENTLY] = "Core not capable of performing SCAN currently", + [IFS_UNASSIGNED_ERROR_CODE] = "Unassigned error code 0x7", + [IFS_EXCEED_NUMBER_OF_THREADS_CONCURRENT] = + "Exceeded number of Logical Processors (LP) allowed to run Scan-At-Field concurrently", + [IFS_INTERRUPTED_DURING_EXECUTION] = "Interrupt occurred prior to SCAN start", +}; + +static void message_not_tested(struct device *dev, int cpu, union ifs_status status) +{ + if (status.error_code < ARRAY_SIZE(scan_test_status)) { + dev_info(dev, "CPU(s) %*pbl: SCAN operation did not start. %s\n", + cpumask_pr_args(cpu_smt_mask(cpu)), + scan_test_status[status.error_code]); + } else if (status.error_code == IFS_SW_TIMEOUT) { + dev_info(dev, "CPU(s) %*pbl: software timeout during scan\n", + cpumask_pr_args(cpu_smt_mask(cpu))); + } else if (status.error_code == IFS_SW_PARTIAL_COMPLETION) { + dev_info(dev, "CPU(s) %*pbl: %s\n", + cpumask_pr_args(cpu_smt_mask(cpu)), + "Not all scan chunks were executed. Maximum forward progress retries exceeded"); + } else { + dev_info(dev, "CPU(s) %*pbl: SCAN unknown status %llx\n", + cpumask_pr_args(cpu_smt_mask(cpu)), status.data); + } +} + +static void message_fail(struct device *dev, int cpu, union ifs_status status) +{ + /* + * control_error is set when the microcode runs into a problem + * loading the image from the reserved BIOS memory, or it has + * been corrupted. Reloading the image may fix this issue. + */ + if (status.control_error) { + dev_err(dev, "CPU(s) %*pbl: could not execute from loaded scan image\n", + cpumask_pr_args(cpu_smt_mask(cpu))); + } + + /* + * signature_error is set when the output from the scan chains does not + * match the expected signature. This might be a transient problem (e.g. + * due to a bit flip from an alpha particle or neutron). If the problem + * repeats on a subsequent test, then it indicates an actual problem in + * the core being tested. + */ + if (status.signature_error) { + dev_err(dev, "CPU(s) %*pbl: test signature incorrect.\n", + cpumask_pr_args(cpu_smt_mask(cpu))); + } +} + +static bool can_restart(union ifs_status status) +{ + enum ifs_status_err_code err_code = status.error_code; + + /* Signature for chunk is bad, or scan test failed */ + if (status.signature_error || status.control_error) + return false; + + switch (err_code) { + case IFS_NO_ERROR: + case IFS_OTHER_THREAD_COULD_NOT_JOIN: + case IFS_INTERRUPTED_BEFORE_RENDEZVOUS: + case IFS_POWER_MGMT_INADEQUATE_FOR_SCAN: + case IFS_EXCEED_NUMBER_OF_THREADS_CONCURRENT: + case IFS_INTERRUPTED_DURING_EXECUTION: + return true; + case IFS_INVALID_CHUNK_RANGE: + case IFS_MISMATCH_ARGUMENTS_BETWEEN_THREADS: + case IFS_CORE_NOT_CAPABLE_CURRENTLY: + case IFS_UNASSIGNED_ERROR_CODE: + break; + } + return false; +} + +/* + * Execute the scan. Called "simultaneously" on all threads of a core + * at high priority using the stop_cpus mechanism. + */ +static int doscan(void *data) +{ + int cpu = smp_processor_id(); + u64 *msrs = data; + int first; + + /* Only the first logical CPU on a core reports result */ + first = cpumask_first(cpu_smt_mask(cpu)); + + /* + * This WRMSR will wait for other HT threads to also write + * to this MSR (at most for activate.delay cycles). Then it + * starts scan of each requested chunk. The core scan happens + * during the "execution" of the WRMSR. This instruction can + * take up to 200 milliseconds (in the case where all chunks + * are processed in a single pass) before it retires. + */ + wrmsrl(MSR_ACTIVATE_SCAN, msrs[0]); + + if (cpu == first) { + /* Pass back the result of the scan */ + rdmsrl(MSR_SCAN_STATUS, msrs[1]); + } + + return 0; +} + +/* + * Use stop_core_cpuslocked() to synchronize writing to MSR_ACTIVATE_SCAN + * on all threads of the core to be tested. Loop if necessary to complete + * run of all chunks. Include some defensive tests to make sure forward + * progress is made, and that the whole test completes in a reasonable time. + */ +static void ifs_test_core(int cpu, struct device *dev) +{ + union ifs_scan activate; + union ifs_status status; + unsigned long timeout; + struct ifs_data *ifsd; + u64 msrvals[2]; + int retries; + + ifsd = ifs_get_data(dev); + + activate.rsvd = 0; + activate.delay = IFS_THREAD_WAIT; + activate.sigmce = 0; + activate.start = 0; + activate.stop = ifsd->valid_chunks - 1; + + timeout = jiffies + HZ / 2; + retries = MAX_IFS_RETRIES; + + while (activate.start <= activate.stop) { + if (time_after(jiffies, timeout)) { + status.error_code = IFS_SW_TIMEOUT; + break; + } + + msrvals[0] = activate.data; + stop_core_cpuslocked(cpu, doscan, msrvals); + + status.data = msrvals[1]; + + trace_ifs_status(cpu, activate, status); + + /* Some cases can be retried, give up for others */ + if (!can_restart(status)) + break; + + if (status.chunk_num == activate.start) { + /* Check for forward progress */ + if (--retries == 0) { + if (status.error_code == IFS_NO_ERROR) + status.error_code = IFS_SW_PARTIAL_COMPLETION; + break; + } + } else { + retries = MAX_IFS_RETRIES; + activate.start = status.chunk_num; + } + } + + /* Update status for this core */ + ifsd->scan_details = status.data; + + if (status.control_error || status.signature_error) { + ifsd->status = SCAN_TEST_FAIL; + message_fail(dev, cpu, status); + } else if (status.error_code) { + ifsd->status = SCAN_NOT_TESTED; + message_not_tested(dev, cpu, status); + } else { + ifsd->status = SCAN_TEST_PASS; + } +} + +/* + * Initiate per core test. It wakes up work queue threads on the target cpu and + * its sibling cpu. Once all sibling threads wake up, the scan test gets executed and + * wait for all sibling threads to finish the scan test. + */ +int do_core_test(int cpu, struct device *dev) +{ + int ret = 0; + + /* Prevent CPUs from being taken offline during the scan test */ + cpus_read_lock(); + + if (!cpu_online(cpu)) { + dev_info(dev, "cannot test on the offline cpu %d\n", cpu); + ret = -EINVAL; + goto out; + } + + ifs_test_core(cpu, dev); +out: + cpus_read_unlock(); + return ret; +} diff --git a/drivers/platform/x86/intel/ifs/sysfs.c b/drivers/platform/x86/intel/ifs/sysfs.c new file mode 100644 index 000000000000..37d8380d6fa8 --- /dev/null +++ b/drivers/platform/x86/intel/ifs/sysfs.c @@ -0,0 +1,149 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright(c) 2022 Intel Corporation. */ + +#include <linux/cpu.h> +#include <linux/delay.h> +#include <linux/fs.h> +#include <linux/semaphore.h> +#include <linux/slab.h> + +#include "ifs.h" + +/* + * Protects against simultaneous tests on multiple cores, or + * reloading can file while a test is in progress + */ +DEFINE_SEMAPHORE(ifs_sem); + +/* + * The sysfs interface to check additional details of last test + * cat /sys/devices/system/platform/ifs/details + */ +static ssize_t details_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct ifs_data *ifsd = ifs_get_data(dev); + + return sysfs_emit(buf, "%#llx\n", ifsd->scan_details); +} + +static DEVICE_ATTR_RO(details); + +static const char * const status_msg[] = { + [SCAN_NOT_TESTED] = "untested", + [SCAN_TEST_PASS] = "pass", + [SCAN_TEST_FAIL] = "fail" +}; + +/* + * The sysfs interface to check the test status: + * To check the status of last test + * cat /sys/devices/platform/ifs/status + */ +static ssize_t status_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct ifs_data *ifsd = ifs_get_data(dev); + + return sysfs_emit(buf, "%s\n", status_msg[ifsd->status]); +} + +static DEVICE_ATTR_RO(status); + +/* + * The sysfs interface for single core testing + * To start test, for example, cpu5 + * echo 5 > /sys/devices/platform/ifs/run_test + * To check the result: + * cat /sys/devices/platform/ifs/result + * The sibling core gets tested at the same time. + */ +static ssize_t run_test_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct ifs_data *ifsd = ifs_get_data(dev); + unsigned int cpu; + int rc; + + rc = kstrtouint(buf, 0, &cpu); + if (rc < 0 || cpu >= nr_cpu_ids) + return -EINVAL; + + if (down_interruptible(&ifs_sem)) + return -EINTR; + + if (!ifsd->loaded) + rc = -EPERM; + else + rc = do_core_test(cpu, dev); + + up(&ifs_sem); + + return rc ? rc : count; +} + +static DEVICE_ATTR_WO(run_test); + +/* + * Reload the IFS image. When user wants to install new IFS image + */ +static ssize_t reload_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct ifs_data *ifsd = ifs_get_data(dev); + bool res; + + + if (kstrtobool(buf, &res)) + return -EINVAL; + if (!res) + return count; + + if (down_interruptible(&ifs_sem)) + return -EINTR; + + ifs_load_firmware(dev); + + up(&ifs_sem); + + return ifsd->loaded ? count : -ENODEV; +} + +static DEVICE_ATTR_WO(reload); + +/* + * Display currently loaded IFS image version. + */ +static ssize_t image_version_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct ifs_data *ifsd = ifs_get_data(dev); + + if (!ifsd->loaded) + return sysfs_emit(buf, "%s\n", "none"); + else + return sysfs_emit(buf, "%#x\n", ifsd->loaded_version); +} + +static DEVICE_ATTR_RO(image_version); + +/* global scan sysfs attributes */ +static struct attribute *plat_ifs_attrs[] = { + &dev_attr_details.attr, + &dev_attr_status.attr, + &dev_attr_run_test.attr, + &dev_attr_reload.attr, + &dev_attr_image_version.attr, + NULL +}; + +ATTRIBUTE_GROUPS(plat_ifs); + +const struct attribute_group **ifs_get_groups(void) +{ + return plat_ifs_groups; +} diff --git a/drivers/platform/x86/intel/pmc/core.c b/drivers/platform/x86/intel/pmc/core.c index ac19fcc9abbf..edaf22e5ae98 100644 --- a/drivers/platform/x86/intel/pmc/core.c +++ b/drivers/platform/x86/intel/pmc/core.c @@ -999,7 +999,7 @@ static umode_t etr3_is_visible(struct kobject *kobj, struct attribute *attr, int idx) { - struct device *dev = container_of(kobj, struct device, kobj); + struct device *dev = kobj_to_dev(kobj); struct pmc_dev *pmcdev = dev_get_drvdata(dev); const struct pmc_reg_map *map = pmcdev->map; u32 reg; diff --git a/drivers/platform/x86/intel/pmc/core.h b/drivers/platform/x86/intel/pmc/core.h index a46d3b53bf61..7a059e02c265 100644 --- a/drivers/platform/x86/intel/pmc/core.h +++ b/drivers/platform/x86/intel/pmc/core.h @@ -236,7 +236,7 @@ enum ppfear_regs { #define ADL_LPM_STATUS_LATCH_EN_OFFSET 0x1704 #define ADL_LPM_LIVE_STATUS_OFFSET 0x1764 -const char *pmc_lpm_modes[] = { +static const char *pmc_lpm_modes[] = { "S0i2.0", "S0i2.1", "S0i2.2", diff --git a/drivers/platform/x86/intel/pmt/telemetry.c b/drivers/platform/x86/intel/pmt/telemetry.c index 6b6f3e2a617a..f73ecfd4a309 100644 --- a/drivers/platform/x86/intel/pmt/telemetry.c +++ b/drivers/platform/x86/intel/pmt/telemetry.c @@ -103,7 +103,7 @@ static int pmt_telem_probe(struct auxiliary_device *auxdev, const struct auxilia auxiliary_set_drvdata(auxdev, priv); for (i = 0; i < intel_vsec_dev->num_resources; i++) { - struct intel_pmt_entry *entry = &priv->entry[i]; + struct intel_pmt_entry *entry = &priv->entry[priv->num_entries]; ret = intel_pmt_dev_create(entry, &pmt_telem_ns, intel_vsec_dev, i); if (ret < 0) diff --git a/drivers/platform/x86/intel/sdsi.c b/drivers/platform/x86/intel/sdsi.c index 11d14cc0ff0a..c830e98dfa38 100644 --- a/drivers/platform/x86/intel/sdsi.c +++ b/drivers/platform/x86/intel/sdsi.c @@ -51,6 +51,8 @@ #define MBOX_TIMEOUT_US 2000 #define MBOX_TIMEOUT_ACQUIRE_US 1000 #define MBOX_POLLING_PERIOD_US 100 +#define MBOX_ACQUIRE_NUM_RETRIES 5 +#define MBOX_ACQUIRE_RETRY_DELAY_MS 500 #define MBOX_MAX_PACKETS 4 #define MBOX_OWNER_NONE 0x00 @@ -81,7 +83,7 @@ enum sdsi_command { struct sdsi_mbox_info { u64 *payload; - u64 *buffer; + void *buffer; int size; }; @@ -163,9 +165,7 @@ static int sdsi_mbox_cmd_read(struct sdsi_priv *priv, struct sdsi_mbox_info *inf total = 0; loop = 0; do { - int offset = SDSI_SIZE_MAILBOX * loop; - void __iomem *addr = priv->mbox_addr + offset; - u64 *buf = info->buffer + offset / SDSI_SIZE_CMD; + void *buf = info->buffer + (SDSI_SIZE_MAILBOX * loop); u32 packet_size; /* Poll on ready bit */ @@ -196,7 +196,7 @@ static int sdsi_mbox_cmd_read(struct sdsi_priv *priv, struct sdsi_mbox_info *inf break; } - sdsi_memcpy64_fromio(buf, addr, round_up(packet_size, SDSI_SIZE_CMD)); + sdsi_memcpy64_fromio(buf, priv->mbox_addr, round_up(packet_size, SDSI_SIZE_CMD)); total += packet_size; @@ -243,8 +243,8 @@ static int sdsi_mbox_cmd_write(struct sdsi_priv *priv, struct sdsi_mbox_info *in FIELD_PREP(CTRL_PACKET_SIZE, info->size); writeq(control, priv->control_addr); - /* Poll on run_busy bit */ - ret = readq_poll_timeout(priv->control_addr, control, !(control & CTRL_RUN_BUSY), + /* Poll on ready bit */ + ret = readq_poll_timeout(priv->control_addr, control, control & CTRL_READY, MBOX_POLLING_PERIOD_US, MBOX_TIMEOUT_US); if (ret) @@ -263,7 +263,7 @@ static int sdsi_mbox_acquire(struct sdsi_priv *priv, struct sdsi_mbox_info *info { u64 control; u32 owner; - int ret; + int ret, retries = 0; lockdep_assert_held(&priv->mb_lock); @@ -273,13 +273,29 @@ static int sdsi_mbox_acquire(struct sdsi_priv *priv, struct sdsi_mbox_info *info if (owner != MBOX_OWNER_NONE) return -EBUSY; - /* Write first qword of payload */ - writeq(info->payload[0], priv->mbox_addr); + /* + * If there has been no recent transaction and no one owns the mailbox, + * we should acquire it in under 1ms. However, if we've accessed it + * recently it may take up to 2.1 seconds to acquire it again. + */ + do { + /* Write first qword of payload */ + writeq(info->payload[0], priv->mbox_addr); + + /* Check for ownership */ + ret = readq_poll_timeout(priv->control_addr, control, + FIELD_GET(CTRL_OWNER, control) == MBOX_OWNER_INBAND, + MBOX_POLLING_PERIOD_US, MBOX_TIMEOUT_ACQUIRE_US); + + if (FIELD_GET(CTRL_OWNER, control) == MBOX_OWNER_NONE && + retries++ < MBOX_ACQUIRE_NUM_RETRIES) { + msleep(MBOX_ACQUIRE_RETRY_DELAY_MS); + continue; + } - /* Check for ownership */ - ret = readq_poll_timeout(priv->control_addr, control, - FIELD_GET(CTRL_OWNER, control) & MBOX_OWNER_INBAND, - MBOX_POLLING_PERIOD_US, MBOX_TIMEOUT_ACQUIRE_US); + /* Either we got it or someone else did. */ + break; + } while (true); return ret; } diff --git a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency.c b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency.c index c61f804dd44e..8f9c571d7257 100644 --- a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency.c +++ b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency.c @@ -212,6 +212,9 @@ static int __init intel_uncore_init(void) const struct x86_cpu_id *id; int ret; + if (cpu_feature_enabled(X86_FEATURE_HYPERVISOR)) + return -ENODEV; + id = x86_match_cpu(intel_uncore_cpu_ids); if (!id) return -ENODEV; diff --git a/drivers/platform/x86/pmc_atom.c b/drivers/platform/x86/pmc_atom.c index a40fae6edc84..b8b1ed1406de 100644 --- a/drivers/platform/x86/pmc_atom.c +++ b/drivers/platform/x86/pmc_atom.c @@ -221,19 +221,6 @@ int pmc_atom_read(int offset, u32 *value) *value = pmc_reg_read(pmc, offset); return 0; } -EXPORT_SYMBOL_GPL(pmc_atom_read); - -int pmc_atom_write(int offset, u32 value) -{ - struct pmc_dev *pmc = &pmc_device; - - if (!pmc->init) - return -ENODEV; - - pmc_reg_write(pmc, offset, value); - return 0; -} -EXPORT_SYMBOL_GPL(pmc_atom_write); static void pmc_power_off(void) { diff --git a/drivers/platform/x86/samsung-laptop.c b/drivers/platform/x86/samsung-laptop.c index c1d9ed9b7b67..c187dcdf82f0 100644 --- a/drivers/platform/x86/samsung-laptop.c +++ b/drivers/platform/x86/samsung-laptop.c @@ -1121,8 +1121,6 @@ static void kbd_led_set(struct led_classdev *led_cdev, if (value > samsung->kbd_led.max_brightness) value = samsung->kbd_led.max_brightness; - else if (value < 0) - value = 0; samsung->kbd_led_wk = value; queue_work(samsung->led_workqueue, &samsung->kbd_led_work); @@ -1210,7 +1208,7 @@ static int __init samsung_backlight_init(struct samsung_laptop *samsung) static umode_t samsung_sysfs_is_visible(struct kobject *kobj, struct attribute *attr, int idx) { - struct device *dev = container_of(kobj, struct device, kobj); + struct device *dev = kobj_to_dev(kobj); struct samsung_laptop *samsung = dev_get_drvdata(dev); bool ok = true; diff --git a/drivers/platform/x86/think-lmi.c b/drivers/platform/x86/think-lmi.c index bce17ca97947..a01a92769c1a 100644 --- a/drivers/platform/x86/think-lmi.c +++ b/drivers/platform/x86/think-lmi.c @@ -740,16 +740,8 @@ static ssize_t certificate_store(struct kobject *kobj, if (!tlmi_priv.certificate_support) return -EOPNOTSUPP; - new_cert = kstrdup(buf, GFP_KERNEL); - if (!new_cert) - return -ENOMEM; - /* Strip out CR if one is present */ - strip_cr(new_cert); - /* If empty then clear installed certificate */ - if (new_cert[0] == '\0') { /* Clear installed certificate */ - kfree(new_cert); - + if ((buf[0] == '\0') || (buf[0] == '\n')) { /* Clear installed certificate */ /* Check that signature is set */ if (!setting->signature || !setting->signature[0]) return -EACCES; @@ -763,14 +755,16 @@ static ssize_t certificate_store(struct kobject *kobj, ret = tlmi_simple_call(LENOVO_CLEAR_BIOS_CERT_GUID, auth_str); kfree(auth_str); - if (ret) - return ret; - kfree(setting->certificate); - setting->certificate = NULL; - return count; + return ret ?: count; } + new_cert = kstrdup(buf, GFP_KERNEL); + if (!new_cert) + return -ENOMEM; + /* Strip out CR if one is present */ + strip_cr(new_cert); + if (setting->cert_installed) { /* Certificate is installed so this is an update */ if (!setting->signature || !setting->signature[0]) { @@ -792,21 +786,14 @@ static ssize_t certificate_store(struct kobject *kobj, auth_str = kasprintf(GFP_KERNEL, "%s,%s", new_cert, setting->password); } - if (!auth_str) { - kfree(new_cert); + kfree(new_cert); + if (!auth_str) return -ENOMEM; - } ret = tlmi_simple_call(guid, auth_str); kfree(auth_str); - if (ret) { - kfree(new_cert); - return ret; - } - kfree(setting->certificate); - setting->certificate = new_cert; - return count; + return ret ?: count; } static struct kobj_attribute auth_certificate = __ATTR_WO(certificate); @@ -1194,6 +1181,10 @@ static void tlmi_release_attr(void) kset_unregister(tlmi_priv.attribute_kset); + /* Free up any saved signatures */ + kfree(tlmi_priv.pwd_admin->signature); + kfree(tlmi_priv.pwd_admin->save_signature); + /* Authentication structures */ sysfs_remove_group(&tlmi_priv.pwd_admin->kobj, &auth_attr_group); kobject_put(&tlmi_priv.pwd_admin->kobj); @@ -1210,11 +1201,6 @@ static void tlmi_release_attr(void) } kset_unregister(tlmi_priv.authentication_kset); - - /* Free up any saved certificates/signatures */ - kfree(tlmi_priv.pwd_admin->certificate); - kfree(tlmi_priv.pwd_admin->signature); - kfree(tlmi_priv.pwd_admin->save_signature); } static int tlmi_sysfs_init(void) diff --git a/drivers/platform/x86/think-lmi.h b/drivers/platform/x86/think-lmi.h index 4f69df6eed07..4daba6151cd6 100644 --- a/drivers/platform/x86/think-lmi.h +++ b/drivers/platform/x86/think-lmi.h @@ -63,7 +63,6 @@ struct tlmi_pwd_setting { int index; /*Used for HDD and NVME auth */ enum level_option level; bool cert_installed; - char *certificate; char *signature; char *save_signature; }; diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index c568fae56db2..e6cb4a14cdd4 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -309,6 +309,20 @@ struct ibm_init_struct { struct ibm_struct *data; }; +/* DMI Quirks */ +struct quirk_entry { + bool btusb_bug; + u32 s2idle_bug_mmio; +}; + +static struct quirk_entry quirk_btusb_bug = { + .btusb_bug = true, +}; + +static struct quirk_entry quirk_s2idle_bug = { + .s2idle_bug_mmio = 0xfed80380, +}; + static struct { u32 bluetooth:1; u32 hotkey:1; @@ -338,6 +352,7 @@ static struct { u32 hotkey_poll_active:1; u32 has_adaptive_kbd:1; u32 kbd_lang:1; + struct quirk_entry *quirks; } tp_features; static struct { @@ -4359,9 +4374,10 @@ static void bluetooth_exit(void) bluetooth_shutdown(); } -static const struct dmi_system_id bt_fwbug_list[] __initconst = { +static const struct dmi_system_id fwbug_list[] __initconst = { { .ident = "ThinkPad E485", + .driver_data = &quirk_btusb_bug, .matches = { DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), DMI_MATCH(DMI_BOARD_NAME, "20KU"), @@ -4369,6 +4385,7 @@ static const struct dmi_system_id bt_fwbug_list[] __initconst = { }, { .ident = "ThinkPad E585", + .driver_data = &quirk_btusb_bug, .matches = { DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), DMI_MATCH(DMI_BOARD_NAME, "20KV"), @@ -4376,6 +4393,7 @@ static const struct dmi_system_id bt_fwbug_list[] __initconst = { }, { .ident = "ThinkPad A285 - 20MW", + .driver_data = &quirk_btusb_bug, .matches = { DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), DMI_MATCH(DMI_BOARD_NAME, "20MW"), @@ -4383,6 +4401,7 @@ static const struct dmi_system_id bt_fwbug_list[] __initconst = { }, { .ident = "ThinkPad A285 - 20MX", + .driver_data = &quirk_btusb_bug, .matches = { DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), DMI_MATCH(DMI_BOARD_NAME, "20MX"), @@ -4390,6 +4409,7 @@ static const struct dmi_system_id bt_fwbug_list[] __initconst = { }, { .ident = "ThinkPad A485 - 20MU", + .driver_data = &quirk_btusb_bug, .matches = { DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), DMI_MATCH(DMI_BOARD_NAME, "20MU"), @@ -4397,14 +4417,125 @@ static const struct dmi_system_id bt_fwbug_list[] __initconst = { }, { .ident = "ThinkPad A485 - 20MV", + .driver_data = &quirk_btusb_bug, .matches = { DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), DMI_MATCH(DMI_BOARD_NAME, "20MV"), }, }, + { + .ident = "L14 Gen2 AMD", + .driver_data = &quirk_s2idle_bug, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "20X5"), + } + }, + { + .ident = "T14s Gen2 AMD", + .driver_data = &quirk_s2idle_bug, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "20XF"), + } + }, + { + .ident = "X13 Gen2 AMD", + .driver_data = &quirk_s2idle_bug, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "20XH"), + } + }, + { + .ident = "T14 Gen2 AMD", + .driver_data = &quirk_s2idle_bug, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "20XK"), + } + }, + { + .ident = "T14 Gen1 AMD", + .driver_data = &quirk_s2idle_bug, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "20UD"), + } + }, + { + .ident = "T14 Gen1 AMD", + .driver_data = &quirk_s2idle_bug, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "20UE"), + } + }, + { + .ident = "T14s Gen1 AMD", + .driver_data = &quirk_s2idle_bug, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "20UH"), + } + }, + { + .ident = "P14s Gen1 AMD", + .driver_data = &quirk_s2idle_bug, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "20Y1"), + } + }, + { + .ident = "P14s Gen2 AMD", + .driver_data = &quirk_s2idle_bug, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "21A0"), + } + }, {} }; +#ifdef CONFIG_SUSPEND +/* + * Lenovo laptops from a variety of generations run a SMI handler during the D3->D0 + * transition that occurs specifically when exiting suspend to idle which can cause + * large delays during resume when the IOMMU translation layer is enabled (the default + * behavior) for NVME devices: + * + * To avoid this firmware problem, skip the SMI handler on these machines before the + * D0 transition occurs. + */ +static void thinkpad_acpi_amd_s2idle_restore(void) +{ + struct resource *res; + void __iomem *addr; + u8 val; + + res = request_mem_region_muxed(tp_features.quirks->s2idle_bug_mmio, 1, + "thinkpad_acpi_pm80"); + if (!res) + return; + + addr = ioremap(tp_features.quirks->s2idle_bug_mmio, 1); + if (!addr) + goto cleanup_resource; + + val = ioread8(addr); + iowrite8(val & ~BIT(0), addr); + + iounmap(addr); +cleanup_resource: + release_resource(res); +} + +static struct acpi_s2idle_dev_ops thinkpad_acpi_s2idle_dev_ops = { + .restore = thinkpad_acpi_amd_s2idle_restore, +}; +#endif + static const struct pci_device_id fwbug_cards_ids[] __initconst = { { PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x24F3) }, { PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x24FD) }, @@ -4419,7 +4550,8 @@ static int __init have_bt_fwbug(void) * Some AMD based ThinkPads have a firmware bug that calling * "GBDC" will cause bluetooth on Intel wireless cards blocked */ - if (dmi_check_system(bt_fwbug_list) && pci_dev_present(fwbug_cards_ids)) { + if (tp_features.quirks && tp_features.quirks->btusb_bug && + pci_dev_present(fwbug_cards_ids)) { vdbg_printk(TPACPI_DBG_INIT | TPACPI_DBG_RFKILL, FW_BUG "disable bluetooth subdriver for Intel cards\n"); return 1; @@ -8748,24 +8880,27 @@ static int __init fan_init(struct ibm_init_struct *iibm) fan_status_access_mode = TPACPI_FAN_RD_TPEC; if (quirks & TPACPI_FAN_Q1) fan_quirk1_setup(); - if (quirks & TPACPI_FAN_2FAN) { - tp_features.second_fan = 1; - pr_info("secondary fan support enabled\n"); - } - if (quirks & TPACPI_FAN_2CTL) { - tp_features.second_fan = 1; - tp_features.second_fan_ctl = 1; - pr_info("secondary fan control enabled\n"); - } /* Try and probe the 2nd fan */ + tp_features.second_fan = 1; /* needed for get_speed to work */ res = fan2_get_speed(&speed); if (res >= 0) { /* It responded - so let's assume it's there */ tp_features.second_fan = 1; tp_features.second_fan_ctl = 1; pr_info("secondary fan control detected & enabled\n"); + } else { + /* Fan not auto-detected */ + tp_features.second_fan = 0; + if (quirks & TPACPI_FAN_2FAN) { + tp_features.second_fan = 1; + pr_info("secondary fan support enabled\n"); + } + if (quirks & TPACPI_FAN_2CTL) { + tp_features.second_fan = 1; + tp_features.second_fan_ctl = 1; + pr_info("secondary fan control enabled\n"); + } } - } else { pr_err("ThinkPad ACPI EC access misbehaving, fan status and control unavailable\n"); return -ENODEV; @@ -11455,6 +11590,10 @@ static void thinkpad_acpi_module_exit(void) tpacpi_lifecycle = TPACPI_LIFE_EXITING; +#ifdef CONFIG_SUSPEND + if (tp_features.quirks && tp_features.quirks->s2idle_bug_mmio) + acpi_unregister_lps0_dev(&thinkpad_acpi_s2idle_dev_ops); +#endif if (tpacpi_hwmon) hwmon_device_unregister(tpacpi_hwmon); if (tp_features.sensors_pdrv_registered) @@ -11496,6 +11635,7 @@ static void thinkpad_acpi_module_exit(void) static int __init thinkpad_acpi_module_init(void) { + const struct dmi_system_id *dmi_id; int ret, i; tpacpi_lifecycle = TPACPI_LIFE_INIT; @@ -11535,6 +11675,10 @@ static int __init thinkpad_acpi_module_init(void) return -ENODEV; } + dmi_id = dmi_first_match(fwbug_list); + if (dmi_id) + tp_features.quirks = dmi_id->driver_data; + /* Device initialization */ tpacpi_pdev = platform_device_register_simple(TPACPI_DRVR_NAME, -1, NULL, 0); @@ -11623,6 +11767,13 @@ static int __init thinkpad_acpi_module_init(void) tp_features.input_device_registered = 1; } +#ifdef CONFIG_SUSPEND + if (tp_features.quirks && tp_features.quirks->s2idle_bug_mmio) { + if (!acpi_register_lps0_dev(&thinkpad_acpi_s2idle_dev_ops)) + pr_info("Using s2idle quirk to avoid %s platform firmware bug\n", + (dmi_id && dmi_id->ident) ? dmi_id->ident : ""); + } +#endif return 0; } diff --git a/drivers/platform/x86/toshiba_acpi.c b/drivers/platform/x86/toshiba_acpi.c index f113dec98e21..0fc9e8b8827b 100644 --- a/drivers/platform/x86/toshiba_acpi.c +++ b/drivers/platform/x86/toshiba_acpi.c @@ -2353,7 +2353,7 @@ static struct attribute *toshiba_attributes[] = { static umode_t toshiba_sysfs_is_visible(struct kobject *kobj, struct attribute *attr, int idx) { - struct device *dev = container_of(kobj, struct device, kobj); + struct device *dev = kobj_to_dev(kobj); struct toshiba_acpi_dev *drv = dev_get_drvdata(dev); bool exists = true; diff --git a/drivers/platform/x86/winmate-fm07-keys.c b/drivers/platform/x86/winmate-fm07-keys.c new file mode 100644 index 000000000000..2c90c5c7eca2 --- /dev/null +++ b/drivers/platform/x86/winmate-fm07-keys.c @@ -0,0 +1,189 @@ +// SPDX-License-Identifier: GPL-2.0 +// +// Driver for the Winmate FM07 front-panel keys +// +// Author: Daniel Beer <daniel.beer@tirotech.co.nz> + +#include <linux/init.h> +#include <linux/module.h> +#include <linux/input.h> +#include <linux/ioport.h> +#include <linux/platform_device.h> +#include <linux/dmi.h> +#include <linux/io.h> + +#define DRV_NAME "winmate-fm07keys" + +#define PORT_CMD 0x6c +#define PORT_DATA 0x68 + +#define EC_ADDR_KEYS 0x3b +#define EC_CMD_READ 0x80 + +#define BASE_KEY KEY_F13 +#define NUM_KEYS 5 + +/* Typically we're done in fewer than 10 iterations */ +#define LOOP_TIMEOUT 1000 + +static void fm07keys_poll(struct input_dev *input) +{ + uint8_t k; + int i; + + /* Flush output buffer */ + i = 0; + while (inb(PORT_CMD) & 0x01) { + if (++i >= LOOP_TIMEOUT) + goto timeout; + inb(PORT_DATA); + } + + /* Send request and wait for write completion */ + outb(EC_CMD_READ, PORT_CMD); + i = 0; + while (inb(PORT_CMD) & 0x02) + if (++i >= LOOP_TIMEOUT) + goto timeout; + + outb(EC_ADDR_KEYS, PORT_DATA); + i = 0; + while (inb(PORT_CMD) & 0x02) + if (++i >= LOOP_TIMEOUT) + goto timeout; + + /* Wait for data ready */ + i = 0; + while (!(inb(PORT_CMD) & 0x01)) + if (++i >= LOOP_TIMEOUT) + goto timeout; + k = inb(PORT_DATA); + + /* Notify of new key states */ + for (i = 0; i < NUM_KEYS; i++) { + input_report_key(input, BASE_KEY + i, (~k) & 1); + k >>= 1; + } + + input_sync(input); + return; + +timeout: + dev_warn_ratelimited(&input->dev, "timeout polling IO memory\n"); +} + +static int fm07keys_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct input_dev *input; + int ret; + int i; + + input = devm_input_allocate_device(dev); + if (!input) { + dev_err(dev, "no memory for input device\n"); + return -ENOMEM; + } + + if (!devm_request_region(dev, PORT_CMD, 1, "Winmate FM07 EC")) + return -EBUSY; + if (!devm_request_region(dev, PORT_DATA, 1, "Winmate FM07 EC")) + return -EBUSY; + + input->name = "Winmate FM07 front-panel keys"; + input->phys = DRV_NAME "/input0"; + + input->id.bustype = BUS_HOST; + input->id.vendor = 0x0001; + input->id.product = 0x0001; + input->id.version = 0x0100; + + __set_bit(EV_KEY, input->evbit); + + for (i = 0; i < NUM_KEYS; i++) + __set_bit(BASE_KEY + i, input->keybit); + + ret = input_setup_polling(input, fm07keys_poll); + if (ret) { + dev_err(dev, "unable to set up polling, err=%d\n", ret); + return ret; + } + + /* These are silicone buttons. They can't be pressed in rapid + * succession too quickly, and 50 Hz seems to be an adequate + * sampling rate without missing any events when tested. + */ + input_set_poll_interval(input, 20); + + ret = input_register_device(input); + if (ret) { + dev_err(dev, "unable to register polled device, err=%d\n", + ret); + return ret; + } + + input_sync(input); + return 0; +} + +static struct platform_driver fm07keys_driver = { + .probe = fm07keys_probe, + .driver = { + .name = DRV_NAME + }, +}; + +static struct platform_device *dev; + +static const struct dmi_system_id fm07keys_dmi_table[] __initconst = { + { + /* FM07 and FM07P */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Winmate Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "IP30"), + }, + }, + { } +}; + +MODULE_DEVICE_TABLE(dmi, fm07keys_dmi_table); + +static int __init fm07keys_init(void) +{ + int ret; + + if (!dmi_check_system(fm07keys_dmi_table)) + return -ENODEV; + + ret = platform_driver_register(&fm07keys_driver); + if (ret) { + pr_err("fm07keys: failed to register driver, err=%d\n", ret); + return ret; + } + + dev = platform_device_register_simple(DRV_NAME, -1, NULL, 0); + if (IS_ERR(dev)) { + ret = PTR_ERR(dev); + pr_err("fm07keys: failed to allocate device, err = %d\n", ret); + goto fail_register; + } + + return 0; + +fail_register: + platform_driver_unregister(&fm07keys_driver); + return ret; +} + +static void __exit fm07keys_exit(void) +{ + platform_driver_unregister(&fm07keys_driver); + platform_device_unregister(dev); +} + +module_init(fm07keys_init); +module_exit(fm07keys_exit); + +MODULE_AUTHOR("Daniel Beer <daniel.beer@tirotech.co.nz>"); +MODULE_DESCRIPTION("Winmate FM07 front-panel keys driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/platform/x86/wmi.c b/drivers/platform/x86/wmi.c index 58a23a9adbef..aed293b5af81 100644 --- a/drivers/platform/x86/wmi.c +++ b/drivers/platform/x86/wmi.c @@ -1308,21 +1308,20 @@ acpi_wmi_ec_space_handler(u32 function, acpi_physical_address address, static void acpi_wmi_notify_handler(acpi_handle handle, u32 event, void *context) { - struct wmi_block *wblock; - bool found_it = false; + struct wmi_block *wblock = NULL, *iter; - list_for_each_entry(wblock, &wmi_block_list, list) { - struct guid_block *block = &wblock->gblock; + list_for_each_entry(iter, &wmi_block_list, list) { + struct guid_block *block = &iter->gblock; - if (wblock->acpi_device->handle == handle && + if (iter->acpi_device->handle == handle && (block->flags & ACPI_WMI_EVENT) && (block->notify_id == event)) { - found_it = true; + wblock = iter; break; } } - if (!found_it) + if (!wblock) return; /* If a driver is bound, then notify the driver. */ diff --git a/drivers/power/supply/power_supply_core.c b/drivers/power/supply/power_supply_core.c index ea02c8dcd748..d925cb137e12 100644 --- a/drivers/power/supply/power_supply_core.c +++ b/drivers/power/supply/power_supply_core.c @@ -604,6 +604,12 @@ int power_supply_get_battery_info(struct power_supply *psy, err = samsung_sdi_battery_get_info(&psy->dev, value, &info); if (!err) goto out_ret_pointer; + else if (err == -ENODEV) + /* + * Device does not have a static battery. + * Proceed to look for a simple battery. + */ + err = 0; if (strcmp("simple-battery", value)) { err = -ENODEV; diff --git a/drivers/power/supply/samsung-sdi-battery.c b/drivers/power/supply/samsung-sdi-battery.c index 9d59f277f519..b33daab798b9 100644 --- a/drivers/power/supply/samsung-sdi-battery.c +++ b/drivers/power/supply/samsung-sdi-battery.c @@ -824,6 +824,7 @@ static struct samsung_sdi_battery samsung_sdi_batteries[] = { .constant_charge_current_max_ua = 900000, .constant_charge_voltage_max_uv = 4200000, .charge_term_current_ua = 200000, + .charge_restart_voltage_uv = 4170000, .maintenance_charge = samsung_maint_charge_table, .maintenance_charge_size = ARRAY_SIZE(samsung_maint_charge_table), .alert_low_temp_charge_current_ua = 300000, @@ -867,6 +868,7 @@ static struct samsung_sdi_battery samsung_sdi_batteries[] = { .constant_charge_current_max_ua = 1500000, .constant_charge_voltage_max_uv = 4350000, .charge_term_current_ua = 120000, + .charge_restart_voltage_uv = 4300000, .maintenance_charge = samsung_maint_charge_table, .maintenance_charge_size = ARRAY_SIZE(samsung_maint_charge_table), .alert_low_temp_charge_current_ua = 300000, diff --git a/drivers/powercap/dtpm_cpu.c b/drivers/powercap/dtpm_cpu.c index bca2f912d349..f5eced0842b3 100644 --- a/drivers/powercap/dtpm_cpu.c +++ b/drivers/powercap/dtpm_cpu.c @@ -211,7 +211,7 @@ static int __dtpm_cpu_setup(int cpu, struct dtpm *parent) return 0; pd = em_cpu_get(cpu); - if (!pd) + if (!pd || em_is_artificial(pd)) return -EINVAL; dtpm_cpu = kzalloc(sizeof(*dtpm_cpu), GFP_KERNEL); diff --git a/drivers/powercap/intel_rapl_common.c b/drivers/powercap/intel_rapl_common.c index 07611a00b78f..a9c99d9e8b42 100644 --- a/drivers/powercap/intel_rapl_common.c +++ b/drivers/powercap/intel_rapl_common.c @@ -1010,7 +1010,7 @@ static u64 rapl_compute_time_window_atom(struct rapl_package *rp, u64 value, * where time_unit is default to 1 sec. Never 0. */ if (!to_raw) - return (value) ? value *= rp->time_unit : rp->time_unit; + return (value) ? value * rp->time_unit : rp->time_unit; value = div64_u64(value, rp->time_unit); @@ -1107,6 +1107,8 @@ static const struct x86_cpu_id rapl_ids[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(ROCKETLAKE, &rapl_defaults_core), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE, &rapl_defaults_core), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, &rapl_defaults_core), + X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_N, &rapl_defaults_core), + X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE, &rapl_defaults_core), X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &rapl_defaults_spr_server), X86_MATCH_INTEL_FAM6_MODEL(LAKEFIELD, &rapl_defaults_core), diff --git a/drivers/powercap/intel_rapl_msr.c b/drivers/powercap/intel_rapl_msr.c index 1be45f36ab6c..9d23984d8931 100644 --- a/drivers/powercap/intel_rapl_msr.c +++ b/drivers/powercap/intel_rapl_msr.c @@ -140,6 +140,7 @@ static const struct x86_cpu_id pl4_support_ids[] = { { X86_VENDOR_INTEL, 6, INTEL_FAM6_TIGERLAKE_L, X86_FEATURE_ANY }, { X86_VENDOR_INTEL, 6, INTEL_FAM6_ALDERLAKE, X86_FEATURE_ANY }, { X86_VENDOR_INTEL, 6, INTEL_FAM6_ALDERLAKE_L, X86_FEATURE_ANY }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_RAPTORLAKE, X86_FEATURE_ANY }, {} }; diff --git a/drivers/ptp/ptp_ocp.c b/drivers/ptp/ptp_ocp.c index 0feaa4b45317..860672d6a03c 100644 --- a/drivers/ptp/ptp_ocp.c +++ b/drivers/ptp/ptp_ocp.c @@ -300,7 +300,7 @@ struct ptp_ocp { struct platform_device *spi_flash; struct clk_hw *i2c_clk; struct timer_list watchdog; - const struct ocp_attr_group *attr_tbl; + const struct attribute_group **attr_group; const struct ptp_ocp_eeprom_map *eeprom_map; struct dentry *debug_root; time64_t gnss_lost; @@ -841,7 +841,7 @@ __ptp_ocp_adjtime_locked(struct ptp_ocp *bp, u32 adj_val) } static void -ptp_ocp_adjtime_coarse(struct ptp_ocp *bp, u64 delta_ns) +ptp_ocp_adjtime_coarse(struct ptp_ocp *bp, s64 delta_ns) { struct timespec64 ts; unsigned long flags; @@ -850,7 +850,8 @@ ptp_ocp_adjtime_coarse(struct ptp_ocp *bp, u64 delta_ns) spin_lock_irqsave(&bp->lock, flags); err = __ptp_ocp_gettime_locked(bp, &ts, NULL); if (likely(!err)) { - timespec64_add_ns(&ts, delta_ns); + set_normalized_timespec64(&ts, ts.tv_sec, + ts.tv_nsec + delta_ns); __ptp_ocp_settime_locked(bp, &ts); } spin_unlock_irqrestore(&bp->lock, flags); @@ -1557,7 +1558,7 @@ ptp_ocp_signal_set(struct ptp_ocp *bp, int gen, struct ptp_ocp_signal *s) start_ns = ktime_set(ts.tv_sec, ts.tv_nsec) + NSEC_PER_MSEC; if (!s->start) { /* roundup() does not work on 32-bit systems */ - s->start = DIV_ROUND_UP_ULL(start_ns, s->period); + s->start = DIV64_U64_ROUND_UP(start_ns, s->period); s->start = ktime_add(s->start, s->phase); } @@ -1836,6 +1837,42 @@ ptp_ocp_signal_init(struct ptp_ocp *bp) } static void +ptp_ocp_attr_group_del(struct ptp_ocp *bp) +{ + sysfs_remove_groups(&bp->dev.kobj, bp->attr_group); + kfree(bp->attr_group); +} + +static int +ptp_ocp_attr_group_add(struct ptp_ocp *bp, + const struct ocp_attr_group *attr_tbl) +{ + int count, i; + int err; + + count = 0; + for (i = 0; attr_tbl[i].cap; i++) + if (attr_tbl[i].cap & bp->fw_cap) + count++; + + bp->attr_group = kcalloc(count + 1, sizeof(struct attribute_group *), + GFP_KERNEL); + if (!bp->attr_group) + return -ENOMEM; + + count = 0; + for (i = 0; attr_tbl[i].cap; i++) + if (attr_tbl[i].cap & bp->fw_cap) + bp->attr_group[count++] = attr_tbl[i].group; + + err = sysfs_create_groups(&bp->dev.kobj, bp->attr_group); + if (err) + bp->attr_group[0] = NULL; + + return err; +} + +static void ptp_ocp_sma_init(struct ptp_ocp *bp) { u32 reg; @@ -1904,7 +1941,6 @@ ptp_ocp_fb_board_init(struct ptp_ocp *bp, struct ocp_resource *r) bp->flash_start = 1024 * 4096; bp->eeprom_map = fb_eeprom_map; bp->fw_version = ioread32(&bp->image->version); - bp->attr_tbl = fb_timecard_groups; bp->fw_cap = OCP_CAP_BASIC; ver = bp->fw_version & 0xffff; @@ -1918,6 +1954,10 @@ ptp_ocp_fb_board_init(struct ptp_ocp *bp, struct ocp_resource *r) ptp_ocp_sma_init(bp); ptp_ocp_signal_init(bp); + err = ptp_ocp_attr_group_add(bp, fb_timecard_groups); + if (err) + return err; + err = ptp_ocp_fb_set_pins(bp); if (err) return err; @@ -3388,7 +3428,6 @@ ptp_ocp_complete(struct ptp_ocp *bp) { struct pps_device *pps; char buf[32]; - int i, err; if (bp->gnss_port != -1) { sprintf(buf, "ttyS%d", bp->gnss_port); @@ -3413,14 +3452,6 @@ ptp_ocp_complete(struct ptp_ocp *bp) if (pps) ptp_ocp_symlink(bp, pps->dev, "pps"); - for (i = 0; bp->attr_tbl[i].cap; i++) { - if (!(bp->attr_tbl[i].cap & bp->fw_cap)) - continue; - err = sysfs_create_group(&bp->dev.kobj, bp->attr_tbl[i].group); - if (err) - return err; - } - ptp_ocp_debugfs_add_device(bp); return 0; @@ -3492,15 +3523,11 @@ static void ptp_ocp_detach_sysfs(struct ptp_ocp *bp) { struct device *dev = &bp->dev; - int i; sysfs_remove_link(&dev->kobj, "ttyGNSS"); sysfs_remove_link(&dev->kobj, "ttyMAC"); sysfs_remove_link(&dev->kobj, "ptp"); sysfs_remove_link(&dev->kobj, "pps"); - if (bp->attr_tbl) - for (i = 0; bp->attr_tbl[i].cap; i++) - sysfs_remove_group(&dev->kobj, bp->attr_tbl[i].group); } static void @@ -3510,6 +3537,7 @@ ptp_ocp_detach(struct ptp_ocp *bp) ptp_ocp_debugfs_remove_device(bp); ptp_ocp_detach_sysfs(bp); + ptp_ocp_attr_group_del(bp); if (timer_pending(&bp->watchdog)) del_timer_sync(&bp->watchdog); if (bp->ts0) diff --git a/drivers/regulator/Kconfig b/drivers/regulator/Kconfig index 5ef2306fce04..cbe0f96ca342 100644 --- a/drivers/regulator/Kconfig +++ b/drivers/regulator/Kconfig @@ -1057,6 +1057,16 @@ config REGULATOR_RT5190A buck converters, 1 LDO, mute AC OFF depop function, with the general I2C control interface. +config REGULATOR_RT5759 + tristate "Richtek RT5759 Regulator" + depends on I2C + select REGMAP_I2C + help + This adds support for voltage regulator in Richtek RT5759. + The RT5759 is a high-performance, synchronous step-down DC-DC + converter that can deliver up to 9A output current from 3V to 6.5V + input supply. + config REGULATOR_RT6160 tristate "Richtek RT6160 BuckBoost voltage regulator" depends on I2C @@ -1157,6 +1167,13 @@ config REGULATOR_SLG51000 The SLG51000 is seven compact and customizable low dropout regulators. +config REGULATOR_SM5703 + tristate "Silicon Mitus SM5703 regulators" + depends on MFD_SM5703 + help + This driver provides support for voltage regulators of SM5703 + multi-function device. + config REGULATOR_STM32_BOOSTER tristate "STMicroelectronics STM32 BOOSTER" depends on ARCH_STM32 || COMPILE_TEST diff --git a/drivers/regulator/Makefile b/drivers/regulator/Makefile index 1b64ad5767be..8d3ee8b6d41d 100644 --- a/drivers/regulator/Makefile +++ b/drivers/regulator/Makefile @@ -127,6 +127,7 @@ obj-$(CONFIG_REGULATOR_RT4801) += rt4801-regulator.o obj-$(CONFIG_REGULATOR_RT4831) += rt4831-regulator.o obj-$(CONFIG_REGULATOR_RT5033) += rt5033-regulator.o obj-$(CONFIG_REGULATOR_RT5190A) += rt5190a-regulator.o +obj-$(CONFIG_REGULATOR_RT5759) += rt5759-regulator.o obj-$(CONFIG_REGULATOR_RT6160) += rt6160-regulator.o obj-$(CONFIG_REGULATOR_RT6245) += rt6245-regulator.o obj-$(CONFIG_REGULATOR_RTMV20) += rtmv20-regulator.o @@ -138,6 +139,7 @@ obj-$(CONFIG_REGULATOR_S5M8767) += s5m8767.o obj-$(CONFIG_REGULATOR_SC2731) += sc2731-regulator.o obj-$(CONFIG_REGULATOR_SKY81452) += sky81452-regulator.o obj-$(CONFIG_REGULATOR_SLG51000) += slg51000-regulator.o +obj-$(CONFIG_REGULATOR_SM5703) += sm5703-regulator.o obj-$(CONFIG_REGULATOR_STM32_BOOSTER) += stm32-booster.o obj-$(CONFIG_REGULATOR_STM32_VREFBUF) += stm32-vrefbuf.o obj-$(CONFIG_REGULATOR_STM32_PWR) += stm32-pwr.o diff --git a/drivers/regulator/atc260x-regulator.c b/drivers/regulator/atc260x-regulator.c index 05147d2c3842..485e58b264c0 100644 --- a/drivers/regulator/atc260x-regulator.c +++ b/drivers/regulator/atc260x-regulator.c @@ -292,6 +292,7 @@ enum atc2603c_reg_ids { .bypass_mask = BIT(5), \ .active_discharge_reg = ATC2603C_PMU_SWITCH_CTL, \ .active_discharge_mask = BIT(1), \ + .active_discharge_on = BIT(1), \ .owner = THIS_MODULE, \ } diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index d2553970a67b..1e54a833f2cf 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -83,6 +83,7 @@ struct regulator_supply_alias { static int _regulator_is_enabled(struct regulator_dev *rdev); static int _regulator_disable(struct regulator *regulator); +static int _regulator_get_error_flags(struct regulator_dev *rdev, unsigned int *flags); static int _regulator_get_current_limit(struct regulator_dev *rdev); static unsigned int _regulator_get_mode(struct regulator_dev *rdev); static int _notifier_call_chain(struct regulator_dev *rdev, @@ -911,6 +912,30 @@ static ssize_t bypass_show(struct device *dev, } static DEVICE_ATTR_RO(bypass); +#define REGULATOR_ERROR_ATTR(name, bit) \ + static ssize_t name##_show(struct device *dev, struct device_attribute *attr, \ + char *buf) \ + { \ + int ret; \ + unsigned int flags; \ + struct regulator_dev *rdev = dev_get_drvdata(dev); \ + ret = _regulator_get_error_flags(rdev, &flags); \ + if (ret) \ + return ret; \ + return sysfs_emit(buf, "%d\n", !!(flags & (bit))); \ + } \ + static DEVICE_ATTR_RO(name) + +REGULATOR_ERROR_ATTR(under_voltage, REGULATOR_ERROR_UNDER_VOLTAGE); +REGULATOR_ERROR_ATTR(over_current, REGULATOR_ERROR_OVER_CURRENT); +REGULATOR_ERROR_ATTR(regulation_out, REGULATOR_ERROR_REGULATION_OUT); +REGULATOR_ERROR_ATTR(fail, REGULATOR_ERROR_FAIL); +REGULATOR_ERROR_ATTR(over_temp, REGULATOR_ERROR_OVER_TEMP); +REGULATOR_ERROR_ATTR(under_voltage_warn, REGULATOR_ERROR_UNDER_VOLTAGE_WARN); +REGULATOR_ERROR_ATTR(over_current_warn, REGULATOR_ERROR_OVER_CURRENT_WARN); +REGULATOR_ERROR_ATTR(over_voltage_warn, REGULATOR_ERROR_OVER_VOLTAGE_WARN); +REGULATOR_ERROR_ATTR(over_temp_warn, REGULATOR_ERROR_OVER_TEMP_WARN); + /* Calculate the new optimum regulator operating mode based on the new total * consumer load. All locks held by caller */ @@ -1522,6 +1547,24 @@ static int set_machine_constraints(struct regulator_dev *rdev) } } + /* + * If there is no mechanism for controlling the regulator then + * flag it as always_on so we don't end up duplicating checks + * for this so much. Note that we could control the state of + * a supply to control the output on a regulator that has no + * direct control. + */ + if (!rdev->ena_pin && !ops->enable) { + if (rdev->supply_name && !rdev->supply) + return -EPROBE_DEFER; + + if (rdev->supply) + rdev->constraints->always_on = + rdev->supply->rdev->constraints->always_on; + else + rdev->constraints->always_on = true; + } + /* If the constraints say the regulator should be on at this point * and we have control then make sure it is enabled. */ @@ -2133,10 +2176,13 @@ struct regulator *_regulator_get(struct device *dev, const char *id, rdev->exclusive = 1; ret = _regulator_is_enabled(rdev); - if (ret > 0) + if (ret > 0) { rdev->use_count = 1; - else + regulator->enable_count = 1; + } else { rdev->use_count = 0; + regulator->enable_count = 0; + } } link = device_link_add(dev, &rdev->dev, DL_FLAG_STATELESS); @@ -2511,17 +2557,17 @@ static int regulator_ena_gpio_ctrl(struct regulator_dev *rdev, bool enable) } /** - * _regulator_enable_delay - a delay helper function + * _regulator_delay_helper - a delay helper function * @delay: time to delay in microseconds * * Delay for the requested amount of time as per the guidelines in: * * Documentation/timers/timers-howto.rst * - * The assumption here is that regulators will never be enabled in + * The assumption here is that these regulator operations will never used in * atomic context and therefore sleeping functions can be used. */ -static void _regulator_enable_delay(unsigned int delay) +static void _regulator_delay_helper(unsigned int delay) { unsigned int ms = delay / 1000; unsigned int us = delay % 1000; @@ -2603,7 +2649,7 @@ static int _regulator_do_enable(struct regulator_dev *rdev) s64 remaining = ktime_us_delta(end, ktime_get()); if (remaining > 0) - _regulator_enable_delay(remaining); + _regulator_delay_helper(remaining); } if (rdev->ena_pin) { @@ -2630,14 +2676,14 @@ static int _regulator_do_enable(struct regulator_dev *rdev) /* If poll_enabled_time is set, poll upto the delay calculated * above, delaying poll_enabled_time uS to check if the regulator * actually got enabled. - * If the regulator isn't enabled after enable_delay has - * expired, return -ETIMEDOUT. + * If the regulator isn't enabled after our delay helper has expired, + * return -ETIMEDOUT. */ if (rdev->desc->poll_enabled_time) { unsigned int time_remaining = delay; while (time_remaining > 0) { - _regulator_enable_delay(rdev->desc->poll_enabled_time); + _regulator_delay_helper(rdev->desc->poll_enabled_time); if (rdev->desc->ops->get_status) { ret = _regulator_check_status_enabled(rdev); @@ -2656,7 +2702,7 @@ static int _regulator_do_enable(struct regulator_dev *rdev) return -ETIMEDOUT; } } else { - _regulator_enable_delay(delay); + _regulator_delay_helper(delay); } trace_regulator_enable_complete(rdev_get_name(rdev)); @@ -3548,12 +3594,7 @@ static int _regulator_do_set_voltage(struct regulator_dev *rdev, } /* Insert any necessary delays */ - if (delay >= 1000) { - mdelay(delay / 1000); - udelay(delay % 1000); - } else if (delay) { - udelay(delay); - } + _regulator_delay_helper(delay); if (best_val >= 0) { unsigned long data = best_val; @@ -4971,6 +5012,15 @@ static struct attribute *regulator_dev_attrs[] = { &dev_attr_max_microvolts.attr, &dev_attr_min_microamps.attr, &dev_attr_max_microamps.attr, + &dev_attr_under_voltage.attr, + &dev_attr_over_current.attr, + &dev_attr_regulation_out.attr, + &dev_attr_fail.attr, + &dev_attr_over_temp.attr, + &dev_attr_under_voltage_warn.attr, + &dev_attr_over_current_warn.attr, + &dev_attr_over_voltage_warn.attr, + &dev_attr_over_temp_warn.attr, &dev_attr_suspend_standby_state.attr, &dev_attr_suspend_mem_state.attr, &dev_attr_suspend_disk_state.attr, @@ -5026,6 +5076,17 @@ static umode_t regulator_attr_is_visible(struct kobject *kobj, if (attr == &dev_attr_bypass.attr) return ops->get_bypass ? mode : 0; + if (attr == &dev_attr_under_voltage.attr || + attr == &dev_attr_over_current.attr || + attr == &dev_attr_regulation_out.attr || + attr == &dev_attr_fail.attr || + attr == &dev_attr_over_temp.attr || + attr == &dev_attr_under_voltage_warn.attr || + attr == &dev_attr_over_current_warn.attr || + attr == &dev_attr_over_voltage_warn.attr || + attr == &dev_attr_over_temp_warn.attr) + return ops->get_error_flags ? mode : 0; + /* constraints need specific supporting methods */ if (attr == &dev_attr_min_microvolts.attr || attr == &dev_attr_max_microvolts.attr) diff --git a/drivers/regulator/da9121-regulator.c b/drivers/regulator/da9121-regulator.c index eb9df485bd8a..76e0e23bf598 100644 --- a/drivers/regulator/da9121-regulator.c +++ b/drivers/regulator/da9121-regulator.c @@ -1030,6 +1030,8 @@ static int da9121_assign_chip_model(struct i2c_client *i2c, chip->variant_id = DA9121_TYPE_DA9142; regmap = &da9121_2ch_regmap_config; break; + default: + return -EINVAL; } /* Set these up for of_regulator_match call which may want .of_map_modes */ diff --git a/drivers/regulator/fixed.c b/drivers/regulator/fixed.c index 599ad201dca7..2a9867abba20 100644 --- a/drivers/regulator/fixed.c +++ b/drivers/regulator/fixed.c @@ -236,11 +236,8 @@ static int reg_fixed_voltage_probe(struct platform_device *pdev) drvdata->desc.supply_name = devm_kstrdup(&pdev->dev, config->input_supply, GFP_KERNEL); - if (!drvdata->desc.supply_name) { - dev_err(&pdev->dev, - "Failed to allocate input supply\n"); + if (!drvdata->desc.supply_name) return -ENOMEM; - } } if (config->microvolts) diff --git a/drivers/regulator/mt6358-regulator.c b/drivers/regulator/mt6358-regulator.c index eb8027813b99..8a5ce990f1bf 100644 --- a/drivers/regulator/mt6358-regulator.c +++ b/drivers/regulator/mt6358-regulator.c @@ -130,6 +130,102 @@ struct mt6358_regulator_info { .qi = BIT(15), \ } +#define MT6366_BUCK(match, vreg, min, max, step, \ + volt_ranges, vosel_mask, _da_vsel_reg, _da_vsel_mask, \ + _modeset_reg, _modeset_shift) \ +[MT6366_ID_##vreg] = { \ + .desc = { \ + .name = #vreg, \ + .of_match = of_match_ptr(match), \ + .ops = &mt6358_volt_range_ops, \ + .type = REGULATOR_VOLTAGE, \ + .id = MT6366_ID_##vreg, \ + .owner = THIS_MODULE, \ + .n_voltages = ((max) - (min)) / (step) + 1, \ + .linear_ranges = volt_ranges, \ + .n_linear_ranges = ARRAY_SIZE(volt_ranges), \ + .vsel_reg = MT6358_BUCK_##vreg##_ELR0, \ + .vsel_mask = vosel_mask, \ + .enable_reg = MT6358_BUCK_##vreg##_CON0, \ + .enable_mask = BIT(0), \ + .of_map_mode = mt6358_map_mode, \ + }, \ + .status_reg = MT6358_BUCK_##vreg##_DBG1, \ + .qi = BIT(0), \ + .da_vsel_reg = _da_vsel_reg, \ + .da_vsel_mask = _da_vsel_mask, \ + .modeset_reg = _modeset_reg, \ + .modeset_mask = BIT(_modeset_shift), \ +} + +#define MT6366_LDO(match, vreg, ldo_volt_table, \ + ldo_index_table, enreg, enbit, vosel, \ + vosel_mask) \ +[MT6366_ID_##vreg] = { \ + .desc = { \ + .name = #vreg, \ + .of_match = of_match_ptr(match), \ + .ops = &mt6358_volt_table_ops, \ + .type = REGULATOR_VOLTAGE, \ + .id = MT6366_ID_##vreg, \ + .owner = THIS_MODULE, \ + .n_voltages = ARRAY_SIZE(ldo_volt_table), \ + .volt_table = ldo_volt_table, \ + .vsel_reg = vosel, \ + .vsel_mask = vosel_mask, \ + .enable_reg = enreg, \ + .enable_mask = BIT(enbit), \ + }, \ + .status_reg = MT6358_LDO_##vreg##_CON1, \ + .qi = BIT(15), \ + .index_table = ldo_index_table, \ + .n_table = ARRAY_SIZE(ldo_index_table), \ +} + +#define MT6366_LDO1(match, vreg, min, max, step, \ + volt_ranges, _da_vsel_reg, _da_vsel_mask, \ + vosel, vosel_mask) \ +[MT6366_ID_##vreg] = { \ + .desc = { \ + .name = #vreg, \ + .of_match = of_match_ptr(match), \ + .ops = &mt6358_volt_range_ops, \ + .type = REGULATOR_VOLTAGE, \ + .id = MT6366_ID_##vreg, \ + .owner = THIS_MODULE, \ + .n_voltages = ((max) - (min)) / (step) + 1, \ + .linear_ranges = volt_ranges, \ + .n_linear_ranges = ARRAY_SIZE(volt_ranges), \ + .vsel_reg = vosel, \ + .vsel_mask = vosel_mask, \ + .enable_reg = MT6358_LDO_##vreg##_CON0, \ + .enable_mask = BIT(0), \ + }, \ + .da_vsel_reg = _da_vsel_reg, \ + .da_vsel_mask = _da_vsel_mask, \ + .status_reg = MT6358_LDO_##vreg##_DBG1, \ + .qi = BIT(0), \ +} + +#define MT6366_REG_FIXED(match, vreg, \ + enreg, enbit, volt) \ +[MT6366_ID_##vreg] = { \ + .desc = { \ + .name = #vreg, \ + .of_match = of_match_ptr(match), \ + .ops = &mt6358_volt_fixed_ops, \ + .type = REGULATOR_VOLTAGE, \ + .id = MT6366_ID_##vreg, \ + .owner = THIS_MODULE, \ + .n_voltages = 1, \ + .enable_reg = enreg, \ + .enable_mask = BIT(enbit), \ + .min_uV = volt, \ + }, \ + .status_reg = MT6358_LDO_##vreg##_CON1, \ + .qi = BIT(15), \ +} + static const struct linear_range buck_volt_range1[] = { REGULATOR_LINEAR_RANGE(500000, 0, 0x7f, 6250), }; @@ -409,6 +505,9 @@ static struct mt6358_regulator_info mt6358_regulators[] = { MT6358_BUCK("buck_vcore", VCORE, 500000, 1293750, 6250, buck_volt_range1, 0x7f, MT6358_BUCK_VCORE_DBG0, 0x7f, MT6358_VCORE_VGPU_ANA_CON0, 1), + MT6358_BUCK("buck_vcore_sshub", VCORE_SSHUB, 500000, 1293750, 6250, + buck_volt_range1, 0x7f, MT6358_BUCK_VCORE_SSHUB_ELR0, 0x7f, + MT6358_VCORE_VGPU_ANA_CON0, 1), MT6358_BUCK("buck_vpa", VPA, 500000, 3650000, 50000, buck_volt_range3, 0x3f, MT6358_BUCK_VPA_DBG0, 0x3f, MT6358_VPA_ANA_CON0, 3), @@ -488,6 +587,10 @@ static struct mt6358_regulator_info mt6358_regulators[] = { MT6358_LDO1("ldo_vsram_others", VSRAM_OTHERS, 500000, 1293750, 6250, buck_volt_range1, MT6358_LDO_VSRAM_OTHERS_DBG0, 0x7f00, MT6358_LDO_VSRAM_CON2, 0x7f), + MT6358_LDO1("ldo_vsram_others_sshub", VSRAM_OTHERS_SSHUB, 500000, + 1293750, 6250, buck_volt_range1, + MT6358_LDO_VSRAM_OTHERS_SSHUB_CON1, 0x7f, + MT6358_LDO_VSRAM_OTHERS_SSHUB_CON1, 0x7f), MT6358_LDO1("ldo_vsram_gpu", VSRAM_GPU, 500000, 1293750, 6250, buck_volt_range1, MT6358_LDO_VSRAM_GPU_DBG0, 0x7f00, MT6358_LDO_VSRAM_CON3, 0x7f), @@ -496,24 +599,124 @@ static struct mt6358_regulator_info mt6358_regulators[] = { MT6358_LDO_VSRAM_CON1, 0x7f), }; +/* The array is indexed by id(MT6366_ID_XXX) */ +static struct mt6358_regulator_info mt6366_regulators[] = { + MT6366_BUCK("buck_vdram1", VDRAM1, 500000, 2087500, 12500, + buck_volt_range2, 0x7f, MT6358_BUCK_VDRAM1_DBG0, 0x7f, + MT6358_VDRAM1_ANA_CON0, 8), + MT6366_BUCK("buck_vcore", VCORE, 500000, 1293750, 6250, + buck_volt_range1, 0x7f, MT6358_BUCK_VCORE_DBG0, 0x7f, + MT6358_VCORE_VGPU_ANA_CON0, 1), + MT6366_BUCK("buck_vcore_sshub", VCORE_SSHUB, 500000, 1293750, 6250, + buck_volt_range1, 0x7f, MT6358_BUCK_VCORE_SSHUB_ELR0, 0x7f, + MT6358_VCORE_VGPU_ANA_CON0, 1), + MT6366_BUCK("buck_vpa", VPA, 500000, 3650000, 50000, + buck_volt_range3, 0x3f, MT6358_BUCK_VPA_DBG0, 0x3f, + MT6358_VPA_ANA_CON0, 3), + MT6366_BUCK("buck_vproc11", VPROC11, 500000, 1293750, 6250, + buck_volt_range1, 0x7f, MT6358_BUCK_VPROC11_DBG0, 0x7f, + MT6358_VPROC_ANA_CON0, 1), + MT6366_BUCK("buck_vproc12", VPROC12, 500000, 1293750, 6250, + buck_volt_range1, 0x7f, MT6358_BUCK_VPROC12_DBG0, 0x7f, + MT6358_VPROC_ANA_CON0, 2), + MT6366_BUCK("buck_vgpu", VGPU, 500000, 1293750, 6250, + buck_volt_range1, 0x7f, MT6358_BUCK_VGPU_ELR0, 0x7f, + MT6358_VCORE_VGPU_ANA_CON0, 2), + MT6366_BUCK("buck_vs2", VS2, 500000, 2087500, 12500, + buck_volt_range2, 0x7f, MT6358_BUCK_VS2_DBG0, 0x7f, + MT6358_VS2_ANA_CON0, 8), + MT6366_BUCK("buck_vmodem", VMODEM, 500000, 1293750, 6250, + buck_volt_range1, 0x7f, MT6358_BUCK_VMODEM_DBG0, 0x7f, + MT6358_VMODEM_ANA_CON0, 8), + MT6366_BUCK("buck_vs1", VS1, 1000000, 2587500, 12500, + buck_volt_range4, 0x7f, MT6358_BUCK_VS1_DBG0, 0x7f, + MT6358_VS1_ANA_CON0, 8), + MT6366_REG_FIXED("ldo_vrf12", VRF12, + MT6358_LDO_VRF12_CON0, 0, 1200000), + MT6366_REG_FIXED("ldo_vio18", VIO18, + MT6358_LDO_VIO18_CON0, 0, 1800000), + MT6366_REG_FIXED("ldo_vcn18", VCN18, MT6358_LDO_VCN18_CON0, 0, 1800000), + MT6366_REG_FIXED("ldo_vfe28", VFE28, MT6358_LDO_VFE28_CON0, 0, 2800000), + MT6366_REG_FIXED("ldo_vcn28", VCN28, MT6358_LDO_VCN28_CON0, 0, 2800000), + MT6366_REG_FIXED("ldo_vxo22", VXO22, MT6358_LDO_VXO22_CON0, 0, 2200000), + MT6366_REG_FIXED("ldo_vaux18", VAUX18, + MT6358_LDO_VAUX18_CON0, 0, 1800000), + MT6366_REG_FIXED("ldo_vbif28", VBIF28, + MT6358_LDO_VBIF28_CON0, 0, 2800000), + MT6366_REG_FIXED("ldo_vio28", VIO28, MT6358_LDO_VIO28_CON0, 0, 2800000), + MT6366_REG_FIXED("ldo_va12", VA12, MT6358_LDO_VA12_CON0, 0, 1200000), + MT6366_REG_FIXED("ldo_vrf18", VRF18, MT6358_LDO_VRF18_CON0, 0, 1800000), + MT6366_REG_FIXED("ldo_vaud28", VAUD28, + MT6358_LDO_VAUD28_CON0, 0, 2800000), + MT6366_LDO("ldo_vdram2", VDRAM2, vdram2_voltages, vdram2_idx, + MT6358_LDO_VDRAM2_CON0, 0, MT6358_LDO_VDRAM2_ELR0, 0x10), + MT6366_LDO("ldo_vsim1", VSIM1, vsim_voltages, vsim_idx, + MT6358_LDO_VSIM1_CON0, 0, MT6358_VSIM1_ANA_CON0, 0xf00), + MT6366_LDO("ldo_vibr", VIBR, vibr_voltages, vibr_idx, + MT6358_LDO_VIBR_CON0, 0, MT6358_VIBR_ANA_CON0, 0xf00), + MT6366_LDO("ldo_vusb", VUSB, vusb_voltages, vusb_idx, + MT6358_LDO_VUSB_CON0_0, 0, MT6358_VUSB_ANA_CON0, 0x700), + MT6366_LDO("ldo_vefuse", VEFUSE, vefuse_voltages, vefuse_idx, + MT6358_LDO_VEFUSE_CON0, 0, MT6358_VEFUSE_ANA_CON0, 0xf00), + MT6366_LDO("ldo_vmch", VMCH, vmch_vemc_voltages, vmch_vemc_idx, + MT6358_LDO_VMCH_CON0, 0, MT6358_VMCH_ANA_CON0, 0x700), + MT6366_LDO("ldo_vemc", VEMC, vmch_vemc_voltages, vmch_vemc_idx, + MT6358_LDO_VEMC_CON0, 0, MT6358_VEMC_ANA_CON0, 0x700), + MT6366_LDO("ldo_vcn33_bt", VCN33_BT, vcn33_bt_wifi_voltages, + vcn33_bt_wifi_idx, MT6358_LDO_VCN33_CON0_0, + 0, MT6358_VCN33_ANA_CON0, 0x300), + MT6366_LDO("ldo_vcn33_wifi", VCN33_WIFI, vcn33_bt_wifi_voltages, + vcn33_bt_wifi_idx, MT6358_LDO_VCN33_CON0_1, + 0, MT6358_VCN33_ANA_CON0, 0x300), + MT6366_LDO("ldo_vmc", VMC, vmc_voltages, vmc_idx, + MT6358_LDO_VMC_CON0, 0, MT6358_VMC_ANA_CON0, 0xf00), + MT6366_LDO("ldo_vsim2", VSIM2, vsim_voltages, vsim_idx, + MT6358_LDO_VSIM2_CON0, 0, MT6358_VSIM2_ANA_CON0, 0xf00), + MT6366_LDO1("ldo_vsram_proc11", VSRAM_PROC11, 500000, 1293750, 6250, + buck_volt_range1, MT6358_LDO_VSRAM_PROC11_DBG0, 0x7f00, + MT6358_LDO_VSRAM_CON0, 0x7f), + MT6366_LDO1("ldo_vsram_others", VSRAM_OTHERS, 500000, 1293750, 6250, + buck_volt_range1, MT6358_LDO_VSRAM_OTHERS_DBG0, 0x7f00, + MT6358_LDO_VSRAM_CON2, 0x7f), + MT6366_LDO1("ldo_vsram_others_sshub", VSRAM_OTHERS_SSHUB, 500000, + 1293750, 6250, buck_volt_range1, + MT6358_LDO_VSRAM_OTHERS_SSHUB_CON1, 0x7f, + MT6358_LDO_VSRAM_OTHERS_SSHUB_CON1, 0x7f), + MT6366_LDO1("ldo_vsram_gpu", VSRAM_GPU, 500000, 1293750, 6250, + buck_volt_range1, MT6358_LDO_VSRAM_GPU_DBG0, 0x7f00, + MT6358_LDO_VSRAM_CON3, 0x7f), + MT6366_LDO1("ldo_vsram_proc12", VSRAM_PROC12, 500000, 1293750, 6250, + buck_volt_range1, MT6358_LDO_VSRAM_PROC12_DBG0, 0x7f00, + MT6358_LDO_VSRAM_CON1, 0x7f), +}; + static int mt6358_regulator_probe(struct platform_device *pdev) { struct mt6397_chip *mt6397 = dev_get_drvdata(pdev->dev.parent); struct regulator_config config = {}; struct regulator_dev *rdev; - int i; + struct mt6358_regulator_info *mt6358_info; + int i, max_regulator; + + if (mt6397->chip_id == MT6366_CHIP_ID) { + max_regulator = MT6366_MAX_REGULATOR; + mt6358_info = mt6366_regulators; + } else { + max_regulator = MT6358_MAX_REGULATOR; + mt6358_info = mt6358_regulators; + } - for (i = 0; i < MT6358_MAX_REGULATOR; i++) { + for (i = 0; i < max_regulator; i++) { config.dev = &pdev->dev; - config.driver_data = &mt6358_regulators[i]; + config.driver_data = &mt6358_info[i]; config.regmap = mt6397->regmap; rdev = devm_regulator_register(&pdev->dev, - &mt6358_regulators[i].desc, + &mt6358_info[i].desc, &config); if (IS_ERR(rdev)) { dev_err(&pdev->dev, "failed to register %s\n", - mt6358_regulators[i].desc.name); + mt6358_info[i].desc.name); return PTR_ERR(rdev); } } diff --git a/drivers/regulator/pca9450-regulator.c b/drivers/regulator/pca9450-regulator.c index 64e5f5f0cc84..14b7d3376516 100644 --- a/drivers/regulator/pca9450-regulator.c +++ b/drivers/regulator/pca9450-regulator.c @@ -174,6 +174,14 @@ static int buck_set_dvs(const struct regulator_desc *desc, } } + if (ret == 0) { + struct pca9450_regulator_desc *regulator = container_of(desc, + struct pca9450_regulator_desc, desc); + + /* Enable DVS control through PMIC_STBY_REQ for this BUCK */ + ret = regmap_update_bits(regmap, regulator->desc.enable_reg, + BUCK1_DVS_CTRL, BUCK1_DVS_CTRL); + } return ret; } @@ -702,6 +710,7 @@ static int pca9450_i2c_probe(struct i2c_client *i2c, struct regulator_config config = { }; struct pca9450 *pca9450; unsigned int device_id, i; + unsigned int reset_ctrl; int ret; if (!i2c->irq) { @@ -802,14 +811,30 @@ static int pca9450_i2c_probe(struct i2c_client *i2c, return ret; } + if (of_property_read_bool(i2c->dev.of_node, "nxp,wdog_b-warm-reset")) + reset_ctrl = WDOG_B_CFG_WARM; + else + reset_ctrl = WDOG_B_CFG_COLD_LDO12; + /* Set reset behavior on assertion of WDOG_B signal */ ret = regmap_update_bits(pca9450->regmap, PCA9450_REG_RESET_CTRL, - WDOG_B_CFG_MASK, WDOG_B_CFG_COLD_LDO12); + WDOG_B_CFG_MASK, reset_ctrl); if (ret) { dev_err(&i2c->dev, "Failed to set WDOG_B reset behavior\n"); return ret; } + if (of_property_read_bool(i2c->dev.of_node, "nxp,i2c-lt-enable")) { + /* Enable I2C Level Translator */ + ret = regmap_update_bits(pca9450->regmap, PCA9450_REG_CONFIG2, + I2C_LT_MASK, I2C_LT_ON_STANDBY_RUN); + if (ret) { + dev_err(&i2c->dev, + "Failed to enable I2C level translator\n"); + return ret; + } + } + /* * The driver uses the LDO5CTRL_H register to control the LDO5 regulator. * This is only valid if the SD_VSEL input of the PMIC is high. Let's diff --git a/drivers/regulator/pfuze100-regulator.c b/drivers/regulator/pfuze100-regulator.c index d60d7d1b7fa2..aa55cfca9e40 100644 --- a/drivers/regulator/pfuze100-regulator.c +++ b/drivers/regulator/pfuze100-regulator.c @@ -521,6 +521,7 @@ static int pfuze_parse_regulators_dt(struct pfuze_chip *chip) parent = of_get_child_by_name(np, "regulators"); if (!parent) { dev_err(dev, "regulators node not found\n"); + of_node_put(np); return -EINVAL; } @@ -550,6 +551,7 @@ static int pfuze_parse_regulators_dt(struct pfuze_chip *chip) } of_node_put(parent); + of_node_put(np); if (ret < 0) { dev_err(dev, "Error parsing regulator init data: %d\n", ret); diff --git a/drivers/regulator/qcom_smd-regulator.c b/drivers/regulator/qcom_smd-regulator.c index 8490aa8eecb1..7dff94a2eb7e 100644 --- a/drivers/regulator/qcom_smd-regulator.c +++ b/drivers/regulator/qcom_smd-regulator.c @@ -944,32 +944,31 @@ static const struct rpm_regulator_data rpm_pm8950_regulators[] = { { "s2", QCOM_SMD_RPM_SMPA, 2, &pm8950_hfsmps, "vdd_s2" }, { "s3", QCOM_SMD_RPM_SMPA, 3, &pm8950_hfsmps, "vdd_s3" }, { "s4", QCOM_SMD_RPM_SMPA, 4, &pm8950_hfsmps, "vdd_s4" }, - { "s5", QCOM_SMD_RPM_SMPA, 5, &pm8950_ftsmps2p5, "vdd_s5" }, + /* S5 is managed via SPMI. */ { "s6", QCOM_SMD_RPM_SMPA, 6, &pm8950_hfsmps, "vdd_s6" }, { "l1", QCOM_SMD_RPM_LDOA, 1, &pm8950_ult_nldo, "vdd_l1_l19" }, { "l2", QCOM_SMD_RPM_LDOA, 2, &pm8950_ult_nldo, "vdd_l2_l23" }, { "l3", QCOM_SMD_RPM_LDOA, 3, &pm8950_ult_nldo, "vdd_l3" }, - { "l4", QCOM_SMD_RPM_LDOA, 4, &pm8950_ult_pldo, "vdd_l4_l5_l6_l7_l16" }, - { "l5", QCOM_SMD_RPM_LDOA, 5, &pm8950_pldo_lv, "vdd_l4_l5_l6_l7_l16" }, - { "l6", QCOM_SMD_RPM_LDOA, 6, &pm8950_pldo_lv, "vdd_l4_l5_l6_l7_l16" }, - { "l7", QCOM_SMD_RPM_LDOA, 7, &pm8950_pldo_lv, "vdd_l4_l5_l6_l7_l16" }, + /* L4 seems not to exist. */ + { "l5", QCOM_SMD_RPM_LDOA, 5, &pm8950_pldo_lv, "vdd_l5_l6_l7_l16" }, + { "l6", QCOM_SMD_RPM_LDOA, 6, &pm8950_pldo_lv, "vdd_l5_l6_l7_l16" }, + { "l7", QCOM_SMD_RPM_LDOA, 7, &pm8950_pldo_lv, "vdd_l5_l6_l7_l16" }, { "l8", QCOM_SMD_RPM_LDOA, 8, &pm8950_ult_pldo, "vdd_l8_l11_l12_l17_l22" }, { "l9", QCOM_SMD_RPM_LDOA, 9, &pm8950_ult_pldo, "vdd_l9_l10_l13_l14_l15_l18" }, { "l10", QCOM_SMD_RPM_LDOA, 10, &pm8950_ult_nldo, "vdd_l9_l10_l13_l14_l15_l18"}, - { "l11", QCOM_SMD_RPM_LDOA, 11, &pm8950_ult_pldo, "vdd_l8_l11_l12_l17_l22"}, - { "l12", QCOM_SMD_RPM_LDOA, 12, &pm8950_ult_pldo, "vdd_l8_l11_l12_l17_l22"}, - { "l13", QCOM_SMD_RPM_LDOA, 13, &pm8950_ult_pldo, "vdd_l9_l10_l13_l14_l15_l18"}, - { "l14", QCOM_SMD_RPM_LDOA, 14, &pm8950_ult_pldo, "vdd_l9_l10_l13_l14_l15_l18"}, - { "l15", QCOM_SMD_RPM_LDOA, 15, &pm8950_ult_pldo, "vdd_l9_l10_l13_l14_l15_l18"}, - { "l16", QCOM_SMD_RPM_LDOA, 16, &pm8950_ult_pldo, "vdd_l4_l5_l6_l7_l16"}, - { "l17", QCOM_SMD_RPM_LDOA, 17, &pm8950_ult_pldo, "vdd_l8_l11_l12_l17_l22"}, - { "l18", QCOM_SMD_RPM_LDOA, 18, &pm8950_ult_pldo, "vdd_l9_l10_l13_l14_l15_l18"}, - { "l19", QCOM_SMD_RPM_LDOA, 18, &pm8950_pldo, "vdd_l1_l19"}, - { "l20", QCOM_SMD_RPM_LDOA, 18, &pm8950_pldo, "vdd_l20"}, - { "l21", QCOM_SMD_RPM_LDOA, 18, &pm8950_pldo, "vdd_l21"}, - { "l22", QCOM_SMD_RPM_LDOA, 18, &pm8950_pldo, "vdd_l8_l11_l12_l17_l22"}, - { "l23", QCOM_SMD_RPM_LDOA, 18, &pm8950_pldo, "vdd_l2_l23"}, + { "l11", QCOM_SMD_RPM_LDOA, 11, &pm8950_ult_pldo, "vdd_l8_l11_l12_l17_l22" }, + { "l12", QCOM_SMD_RPM_LDOA, 12, &pm8950_ult_pldo, "vdd_l8_l11_l12_l17_l22" }, + { "l13", QCOM_SMD_RPM_LDOA, 13, &pm8950_ult_pldo, "vdd_l9_l10_l13_l14_l15_l18" }, + { "l14", QCOM_SMD_RPM_LDOA, 14, &pm8950_ult_pldo, "vdd_l9_l10_l13_l14_l15_l18" }, + { "l15", QCOM_SMD_RPM_LDOA, 15, &pm8950_ult_pldo, "vdd_l9_l10_l13_l14_l15_l18" }, + { "l16", QCOM_SMD_RPM_LDOA, 16, &pm8950_ult_pldo, "vdd_l5_l6_l7_l16" }, + { "l17", QCOM_SMD_RPM_LDOA, 17, &pm8950_ult_pldo, "vdd_l8_l11_l12_l17_l22" }, + /* L18 seems not to exist. */ + { "l19", QCOM_SMD_RPM_LDOA, 19, &pm8950_pldo, "vdd_l1_l19" }, + /* L20 & L21 seem not to exist. */ + { "l22", QCOM_SMD_RPM_LDOA, 22, &pm8950_pldo, "vdd_l8_l11_l12_l17_l22" }, + { "l23", QCOM_SMD_RPM_LDOA, 23, &pm8950_pldo, "vdd_l2_l23" }, {} }; diff --git a/drivers/regulator/rpi-panel-attiny-regulator.c b/drivers/regulator/rpi-panel-attiny-regulator.c index f7df0f4b2f87..fa8706a352ce 100644 --- a/drivers/regulator/rpi-panel-attiny-regulator.c +++ b/drivers/regulator/rpi-panel-attiny-regulator.c @@ -364,7 +364,6 @@ static int attiny_i2c_probe(struct i2c_client *i2c, state->gc.parent = &i2c->dev; state->gc.label = i2c->name; state->gc.owner = THIS_MODULE; - state->gc.of_node = i2c->dev.of_node; state->gc.base = -1; state->gc.ngpio = NUM_GPIO; diff --git a/drivers/regulator/rt4801-regulator.c b/drivers/regulator/rt4801-regulator.c index 7a87788d3f09..563d79196fdd 100644 --- a/drivers/regulator/rt4801-regulator.c +++ b/drivers/regulator/rt4801-regulator.c @@ -29,11 +29,33 @@ struct rt4801_priv { struct device *dev; - struct gpio_descs *enable_gpios; + struct gpio_desc *enable_gpios[DSV_OUT_MAX]; unsigned int enable_flag; unsigned int volt_sel[DSV_OUT_MAX]; }; +static int rt4801_of_parse_cb(struct device_node *np, + const struct regulator_desc *desc, + struct regulator_config *config) +{ + struct rt4801_priv *priv = config->driver_data; + int id = desc->id; + + if (priv->enable_gpios[id]) { + dev_warn(priv->dev, "duplicated enable-gpios property\n"); + return 0; + } + priv->enable_gpios[id] = devm_fwnode_gpiod_get_index(priv->dev, + of_fwnode_handle(np), + "enable", 0, + GPIOD_OUT_HIGH, + "rt4801"); + if (IS_ERR(priv->enable_gpios[id])) + priv->enable_gpios[id] = NULL; + + return 0; +} + static int rt4801_set_voltage_sel(struct regulator_dev *rdev, unsigned int selector) { struct rt4801_priv *priv = rdev_get_drvdata(rdev); @@ -63,15 +85,14 @@ static int rt4801_get_voltage_sel(struct regulator_dev *rdev) static int rt4801_enable(struct regulator_dev *rdev) { struct rt4801_priv *priv = rdev_get_drvdata(rdev); - struct gpio_descs *gpios = priv->enable_gpios; int id = rdev_get_id(rdev), ret; - if (!gpios || gpios->ndescs <= id) { + if (!priv->enable_gpios[id]) { dev_warn(&rdev->dev, "no dedicated gpio can control\n"); goto bypass_gpio; } - gpiod_set_value(gpios->desc[id], 1); + gpiod_set_value(priv->enable_gpios[id], 1); bypass_gpio: ret = regmap_write(rdev->regmap, rdev->desc->vsel_reg, priv->volt_sel[id]); @@ -85,15 +106,14 @@ bypass_gpio: static int rt4801_disable(struct regulator_dev *rdev) { struct rt4801_priv *priv = rdev_get_drvdata(rdev); - struct gpio_descs *gpios = priv->enable_gpios; int id = rdev_get_id(rdev); - if (!gpios || gpios->ndescs <= id) { + if (!priv->enable_gpios[id]) { dev_warn(&rdev->dev, "no dedicated gpio can control\n"); goto bypass_gpio; } - gpiod_set_value(gpios->desc[id], 0); + gpiod_set_value(priv->enable_gpios[id], 0); bypass_gpio: priv->enable_flag &= ~BIT(id); @@ -122,6 +142,7 @@ static const struct regulator_desc rt4801_regulator_descs[] = { .name = "DSVP", .ops = &rt4801_regulator_ops, .of_match = of_match_ptr("DSVP"), + .of_parse_cb = rt4801_of_parse_cb, .type = REGULATOR_VOLTAGE, .id = DSV_OUT_POS, .min_uV = MIN_UV, @@ -135,6 +156,7 @@ static const struct regulator_desc rt4801_regulator_descs[] = { .name = "DSVN", .ops = &rt4801_regulator_ops, .of_match = of_match_ptr("DSVN"), + .of_parse_cb = rt4801_of_parse_cb, .type = REGULATOR_VOLTAGE, .id = DSV_OUT_NEG, .min_uV = MIN_UV, @@ -172,10 +194,15 @@ static int rt4801_probe(struct i2c_client *i2c) return PTR_ERR(regmap); } - priv->enable_gpios = devm_gpiod_get_array_optional(&i2c->dev, "enable", GPIOD_OUT_HIGH); - if (IS_ERR(priv->enable_gpios)) { - dev_err(&i2c->dev, "Failed to get gpios\n"); - return PTR_ERR(priv->enable_gpios); + for (i = 0; i < DSV_OUT_MAX; i++) { + priv->enable_gpios[i] = devm_gpiod_get_index_optional(&i2c->dev, + "enable", + i, + GPIOD_OUT_HIGH); + if (IS_ERR(priv->enable_gpios[i])) { + dev_err(&i2c->dev, "Failed to get gpios\n"); + return PTR_ERR(priv->enable_gpios[i]); + } } for (i = 0; i < DSV_OUT_MAX; i++) { diff --git a/drivers/regulator/rt5759-regulator.c b/drivers/regulator/rt5759-regulator.c new file mode 100644 index 000000000000..6b96899eb27e --- /dev/null +++ b/drivers/regulator/rt5759-regulator.c @@ -0,0 +1,369 @@ +// SPDX-License-Identifier: GPL-2.0+ + +#include <linux/bits.h> +#include <linux/i2c.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/of_device.h> +#include <linux/regmap.h> +#include <linux/regulator/driver.h> +#include <linux/regulator/of_regulator.h> + +#define RT5759_REG_VENDORINFO 0x00 +#define RT5759_REG_FREQ 0x01 +#define RT5759_REG_VSEL 0x02 +#define RT5759_REG_DCDCCTRL 0x03 +#define RT5759_REG_STATUS 0x04 +#define RT5759_REG_DCDCSET 0x05 +#define RT5759A_REG_WDTEN 0x42 + +#define RT5759_TSTEP_MASK GENMASK(3, 2) +#define RT5759_VSEL_MASK GENMASK(6, 0) +#define RT5759_DISCHARGE_MASK BIT(3) +#define RT5759_FPWM_MASK BIT(2) +#define RT5759_ENABLE_MASK BIT(1) +#define RT5759_OT_MASK BIT(1) +#define RT5759_UV_MASK BIT(0) +#define RT5957_OCLVL_MASK GENMASK(7, 6) +#define RT5759_OCLVL_SHIFT 6 +#define RT5957_OTLVL_MASK GENMASK(5, 4) +#define RT5759_OTLVL_SHIFT 4 +#define RT5759A_WDTEN_MASK BIT(1) + +#define RT5759_MANUFACTURER_ID 0x82 +/* vsel range 0x00 ~ 0x5A */ +#define RT5759_NUM_VOLTS 91 +#define RT5759_MIN_UV 600000 +#define RT5759_STEP_UV 10000 +#define RT5759A_STEP_UV 12500 +#define RT5759_MINSS_TIMEUS 1500 + +#define RT5759_PSKIP_MODE 0 +#define RT5759_FPWM_MODE 1 + +enum { + CHIP_TYPE_RT5759 = 0, + CHIP_TYPE_RT5759A, + CHIP_TYPE_MAX +}; + +struct rt5759_priv { + struct device *dev; + struct regmap *regmap; + struct regulator_desc desc; + unsigned long chip_type; +}; + +static int rt5759_set_mode(struct regulator_dev *rdev, unsigned int mode) +{ + struct regmap *regmap = rdev_get_regmap(rdev); + unsigned int mode_val; + + switch (mode) { + case REGULATOR_MODE_NORMAL: + mode_val = 0; + break; + case REGULATOR_MODE_FAST: + mode_val = RT5759_FPWM_MASK; + break; + default: + return -EINVAL; + } + + return regmap_update_bits(regmap, RT5759_REG_STATUS, RT5759_FPWM_MASK, + mode_val); +} + +static unsigned int rt5759_get_mode(struct regulator_dev *rdev) +{ + struct regmap *regmap = rdev_get_regmap(rdev); + unsigned int regval; + int ret; + + ret = regmap_read(regmap, RT5759_REG_DCDCCTRL, ®val); + if (ret) + return REGULATOR_MODE_INVALID; + + if (regval & RT5759_FPWM_MASK) + return REGULATOR_MODE_FAST; + + return REGULATOR_MODE_NORMAL; +} + +static int rt5759_get_error_flags(struct regulator_dev *rdev, + unsigned int *flags) +{ + struct regmap *regmap = rdev_get_regmap(rdev); + unsigned int status, events = 0; + int ret; + + ret = regmap_read(regmap, RT5759_REG_STATUS, &status); + if (ret) + return ret; + + if (status & RT5759_OT_MASK) + events |= REGULATOR_ERROR_OVER_TEMP; + + if (status & RT5759_UV_MASK) + events |= REGULATOR_ERROR_UNDER_VOLTAGE; + + *flags = events; + return 0; +} + +static int rt5759_set_ocp(struct regulator_dev *rdev, int lim_uA, int severity, + bool enable) +{ + struct regmap *regmap = rdev_get_regmap(rdev); + int ocp_lvl[] = { 9800000, 10800000, 11800000 }; + unsigned int ocp_regval; + int i; + + /* Only support over current protection parameter */ + if (severity != REGULATOR_SEVERITY_PROT) + return 0; + + if (enable) { + /* Default ocp level is 10.8A */ + if (lim_uA == 0) + lim_uA = 10800000; + + for (i = 0; i < ARRAY_SIZE(ocp_lvl); i++) { + if (lim_uA <= ocp_lvl[i]) + break; + } + + if (i == ARRAY_SIZE(ocp_lvl)) + i = ARRAY_SIZE(ocp_lvl) - 1; + + ocp_regval = i + 1; + } else + ocp_regval = 0; + + return regmap_update_bits(regmap, RT5759_REG_DCDCSET, RT5957_OCLVL_MASK, + ocp_regval << RT5759_OCLVL_SHIFT); +} + +static int rt5759_set_otp(struct regulator_dev *rdev, int lim, int severity, + bool enable) +{ + struct regmap *regmap = rdev_get_regmap(rdev); + int otp_lvl[] = { 140, 150, 170 }; + unsigned int otp_regval; + int i; + + /* Only support over temperature protection parameter */ + if (severity != REGULATOR_SEVERITY_PROT) + return 0; + + if (enable) { + /* Default otp level is 150'c */ + if (lim == 0) + lim = 150; + + for (i = 0; i < ARRAY_SIZE(otp_lvl); i++) { + if (lim <= otp_lvl[i]) + break; + } + + if (i == ARRAY_SIZE(otp_lvl)) + i = ARRAY_SIZE(otp_lvl) - 1; + + otp_regval = i + 1; + } else + otp_regval = 0; + + return regmap_update_bits(regmap, RT5759_REG_DCDCSET, RT5957_OTLVL_MASK, + otp_regval << RT5759_OTLVL_SHIFT); +} + +static const struct regulator_ops rt5759_regulator_ops = { + .list_voltage = regulator_list_voltage_linear, + .set_voltage_sel = regulator_set_voltage_sel_regmap, + .get_voltage_sel = regulator_get_voltage_sel_regmap, + .enable = regulator_enable_regmap, + .disable = regulator_disable_regmap, + .is_enabled = regulator_is_enabled_regmap, + .set_active_discharge = regulator_set_active_discharge_regmap, + .set_mode = rt5759_set_mode, + .get_mode = rt5759_get_mode, + .set_ramp_delay = regulator_set_ramp_delay_regmap, + .get_error_flags = rt5759_get_error_flags, + .set_over_current_protection = rt5759_set_ocp, + .set_thermal_protection = rt5759_set_otp, +}; + +static unsigned int rt5759_of_map_mode(unsigned int mode) +{ + switch (mode) { + case RT5759_FPWM_MODE: + return REGULATOR_MODE_FAST; + case RT5759_PSKIP_MODE: + return REGULATOR_MODE_NORMAL; + default: + return REGULATOR_MODE_INVALID; + } +} + +static const unsigned int rt5759_ramp_table[] = { 20000, 15000, 10000, 5000 }; + +static int rt5759_regulator_register(struct rt5759_priv *priv) +{ + struct device_node *np = priv->dev->of_node; + struct regulator_desc *reg_desc = &priv->desc; + struct regulator_config reg_cfg; + struct regulator_dev *rdev; + int ret; + + reg_desc->name = "rt5759-buck"; + reg_desc->type = REGULATOR_VOLTAGE; + reg_desc->owner = THIS_MODULE; + reg_desc->ops = &rt5759_regulator_ops; + reg_desc->n_voltages = RT5759_NUM_VOLTS; + reg_desc->min_uV = RT5759_MIN_UV; + reg_desc->uV_step = RT5759_STEP_UV; + reg_desc->vsel_reg = RT5759_REG_VSEL; + reg_desc->vsel_mask = RT5759_VSEL_MASK; + reg_desc->enable_reg = RT5759_REG_DCDCCTRL; + reg_desc->enable_mask = RT5759_ENABLE_MASK; + reg_desc->active_discharge_reg = RT5759_REG_DCDCCTRL; + reg_desc->active_discharge_mask = RT5759_DISCHARGE_MASK; + reg_desc->active_discharge_on = RT5759_DISCHARGE_MASK; + reg_desc->ramp_reg = RT5759_REG_FREQ; + reg_desc->ramp_mask = RT5759_TSTEP_MASK; + reg_desc->ramp_delay_table = rt5759_ramp_table; + reg_desc->n_ramp_values = ARRAY_SIZE(rt5759_ramp_table); + reg_desc->enable_time = RT5759_MINSS_TIMEUS; + reg_desc->of_map_mode = rt5759_of_map_mode; + + /* + * RT5759 step uV = 10000 + * RT5759A step uV = 12500 + */ + if (priv->chip_type == CHIP_TYPE_RT5759A) + reg_desc->uV_step = RT5759A_STEP_UV; + + reg_cfg.dev = priv->dev; + reg_cfg.of_node = np; + reg_cfg.init_data = of_get_regulator_init_data(priv->dev, np, reg_desc); + reg_cfg.regmap = priv->regmap; + + rdev = devm_regulator_register(priv->dev, reg_desc, ®_cfg); + if (IS_ERR(rdev)) { + ret = PTR_ERR(rdev); + dev_err(priv->dev, "Failed to register regulator (%d)\n", ret); + return ret; + } + + return 0; +} + +static int rt5759_init_device_property(struct rt5759_priv *priv) +{ + unsigned int val = 0; + + /* + * Only RT5759A support external watchdog input + */ + if (priv->chip_type != CHIP_TYPE_RT5759A) + return 0; + + if (device_property_read_bool(priv->dev, "richtek,watchdog-enable")) + val = RT5759A_WDTEN_MASK; + + return regmap_update_bits(priv->regmap, RT5759A_REG_WDTEN, + RT5759A_WDTEN_MASK, val); +} + +static int rt5759_manufacturer_check(struct rt5759_priv *priv) +{ + unsigned int vendor; + int ret; + + ret = regmap_read(priv->regmap, RT5759_REG_VENDORINFO, &vendor); + if (ret) + return ret; + + if (vendor != RT5759_MANUFACTURER_ID) { + dev_err(priv->dev, "vendor info not correct (%d)\n", vendor); + return -EINVAL; + } + + return 0; +} + +static bool rt5759_is_accessible_reg(struct device *dev, unsigned int reg) +{ + struct rt5759_priv *priv = dev_get_drvdata(dev); + + if (reg <= RT5759_REG_DCDCSET) + return true; + + if (priv->chip_type == CHIP_TYPE_RT5759A && reg == RT5759A_REG_WDTEN) + return true; + + return false; +} + +static const struct regmap_config rt5759_regmap_config = { + .reg_bits = 8, + .val_bits = 8, + .max_register = RT5759A_REG_WDTEN, + .readable_reg = rt5759_is_accessible_reg, + .writeable_reg = rt5759_is_accessible_reg, +}; + +static int rt5759_probe(struct i2c_client *i2c) +{ + struct rt5759_priv *priv; + int ret; + + priv = devm_kzalloc(&i2c->dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + priv->dev = &i2c->dev; + priv->chip_type = (unsigned long)of_device_get_match_data(&i2c->dev); + i2c_set_clientdata(i2c, priv); + + priv->regmap = devm_regmap_init_i2c(i2c, &rt5759_regmap_config); + if (IS_ERR(priv->regmap)) { + ret = PTR_ERR(priv->regmap); + dev_err(&i2c->dev, "Failed to allocate regmap (%d)\n", ret); + return ret; + } + + ret = rt5759_manufacturer_check(priv); + if (ret) { + dev_err(&i2c->dev, "Failed to check device (%d)\n", ret); + return ret; + } + + ret = rt5759_init_device_property(priv); + if (ret) { + dev_err(&i2c->dev, "Failed to init device (%d)\n", ret); + return ret; + } + + return rt5759_regulator_register(priv); +} + +static const struct of_device_id __maybe_unused rt5759_device_table[] = { + { .compatible = "richtek,rt5759", .data = (void *)CHIP_TYPE_RT5759 }, + { .compatible = "richtek,rt5759a", .data = (void *)CHIP_TYPE_RT5759A }, + {} +}; +MODULE_DEVICE_TABLE(of, rt5759_device_table); + +static struct i2c_driver rt5759_driver = { + .driver = { + .name = "rt5759", + .of_match_table = of_match_ptr(rt5759_device_table), + }, + .probe_new = rt5759_probe, +}; +module_i2c_driver(rt5759_driver); + +MODULE_AUTHOR("ChiYuan Huang <cy_huang@richtek.com>"); +MODULE_DESCRIPTION("Richtek RT5759 Regulator Driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/regulator/rtq2134-regulator.c b/drivers/regulator/rtq2134-regulator.c index f21e3f8b21f2..8e13dea354a2 100644 --- a/drivers/regulator/rtq2134-regulator.c +++ b/drivers/regulator/rtq2134-regulator.c @@ -285,6 +285,7 @@ static const unsigned int rtq2134_buck_ramp_delay_table[] = { .enable_mask = RTQ2134_VOUTEN_MASK, \ .active_discharge_reg = RTQ2134_REG_BUCK##_id##_CFG0, \ .active_discharge_mask = RTQ2134_ACTDISCHG_MASK, \ + .active_discharge_on = RTQ2134_ACTDISCHG_MASK, \ .ramp_reg = RTQ2134_REG_BUCK##_id##_RSPCFG, \ .ramp_mask = RTQ2134_RSPUP_MASK, \ .ramp_delay_table = rtq2134_buck_ramp_delay_table, \ diff --git a/drivers/regulator/scmi-regulator.c b/drivers/regulator/scmi-regulator.c index 1f02f60ad136..41ae7ac27ff6 100644 --- a/drivers/regulator/scmi-regulator.c +++ b/drivers/regulator/scmi-regulator.c @@ -352,7 +352,7 @@ static int scmi_regulator_probe(struct scmi_device *sdev) return ret; } } - + of_node_put(np); /* * Register a regulator for each valid regulator-DT-entry that we * can successfully reach via SCMI and has a valid associated voltage diff --git a/drivers/regulator/sm5703-regulator.c b/drivers/regulator/sm5703-regulator.c new file mode 100644 index 000000000000..05ad28fc4da8 --- /dev/null +++ b/drivers/regulator/sm5703-regulator.c @@ -0,0 +1,167 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <linux/mfd/sm5703.h> +#include <linux/module.h> +#include <linux/mod_devicetable.h> +#include <linux/platform_device.h> +#include <linux/regmap.h> +#include <linux/regulator/driver.h> +#include <linux/regulator/of_regulator.h> + +enum sm5703_regulators { + SM5703_BUCK, + SM5703_LDO1, + SM5703_LDO2, + SM5703_LDO3, + SM5703_USBLDO1, + SM5703_USBLDO2, + SM5703_VBUS, + SM5703_MAX_REGULATORS, +}; + +static const int sm5703_ldo_voltagemap[] = { + 1500000, 1800000, 2600000, 2800000, 3000000, 3300000, +}; + +static const int sm5703_buck_voltagemap[] = { + 1000000, 1000000, 1000000, 1000000, + 1000000, 1000000, 1000000, 1000000, + 1000000, 1000000, 1000000, 1100000, + 1200000, 1300000, 1400000, 1500000, + 1600000, 1700000, 1800000, 1900000, + 2000000, 2100000, 2200000, 2300000, + 2400000, 2500000, 2600000, 2700000, + 2800000, 2900000, 3000000, 3000000, +}; + +#define SM5703USBLDO(_name, _id) \ + [SM5703_USBLDO ## _id] = { \ + .name = _name, \ + .of_match = _name, \ + .regulators_node = "regulators", \ + .type = REGULATOR_VOLTAGE, \ + .id = SM5703_USBLDO ## _id, \ + .ops = &sm5703_regulator_ops_fixed, \ + .fixed_uV = SM5703_USBLDO_MICROVOLT, \ + .enable_reg = SM5703_REG_USBLDO12, \ + .enable_mask = SM5703_REG_EN_USBLDO ##_id, \ + .owner = THIS_MODULE, \ + } + +#define SM5703VBUS(_name) \ + [SM5703_VBUS] = { \ + .name = _name, \ + .of_match = _name, \ + .regulators_node = "regulators", \ + .type = REGULATOR_VOLTAGE, \ + .id = SM5703_VBUS, \ + .ops = &sm5703_regulator_ops_fixed, \ + .fixed_uV = SM5703_VBUS_MICROVOLT, \ + .enable_reg = SM5703_REG_CNTL, \ + .enable_mask = SM5703_OPERATION_MODE_MASK, \ + .enable_val = SM5703_OPERATION_MODE_USB_OTG_MODE, \ + .disable_val = SM5703_OPERATION_MODE_CHARGING_ON, \ + .owner = THIS_MODULE, \ + } + +#define SM5703BUCK(_name) \ + [SM5703_BUCK] = { \ + .name = _name, \ + .of_match = _name, \ + .regulators_node = "regulators", \ + .type = REGULATOR_VOLTAGE, \ + .id = SM5703_BUCK, \ + .ops = &sm5703_regulator_ops, \ + .n_voltages = ARRAY_SIZE(sm5703_buck_voltagemap), \ + .volt_table = sm5703_buck_voltagemap, \ + .vsel_reg = SM5703_REG_BUCK, \ + .vsel_mask = SM5703_BUCK_VOLT_MASK, \ + .enable_reg = SM5703_REG_BUCK, \ + .enable_mask = SM5703_REG_EN_BUCK, \ + .owner = THIS_MODULE, \ + } + +#define SM5703LDO(_name, _id) \ + [SM5703_LDO ## _id] = { \ + .name = _name, \ + .of_match = _name, \ + .regulators_node = "regulators", \ + .type = REGULATOR_VOLTAGE, \ + .id = SM5703_LDO ## _id, \ + .ops = &sm5703_regulator_ops, \ + .n_voltages = ARRAY_SIZE(sm5703_ldo_voltagemap), \ + .volt_table = sm5703_ldo_voltagemap, \ + .vsel_reg = SM5703_REG_LDO ##_id, \ + .vsel_mask = SM5703_LDO_VOLT_MASK, \ + .enable_reg = SM5703_REG_LDO ##_id, \ + .enable_mask = SM5703_LDO_EN, \ + .owner = THIS_MODULE, \ + } + +static const struct regulator_ops sm5703_regulator_ops = { + .enable = regulator_enable_regmap, + .disable = regulator_disable_regmap, + .is_enabled = regulator_is_enabled_regmap, + .list_voltage = regulator_list_voltage_table, + .get_voltage_sel = regulator_get_voltage_sel_regmap, + .set_voltage_sel = regulator_set_voltage_sel_regmap, +}; + +static const struct regulator_ops sm5703_regulator_ops_fixed = { + .enable = regulator_enable_regmap, + .disable = regulator_disable_regmap, + .is_enabled = regulator_is_enabled_regmap, +}; + +static struct regulator_desc sm5703_regulators_desc[SM5703_MAX_REGULATORS] = { + SM5703BUCK("buck"), + SM5703LDO("ldo1", 1), + SM5703LDO("ldo2", 2), + SM5703LDO("ldo3", 3), + SM5703USBLDO("usbldo1", 1), + SM5703USBLDO("usbldo2", 2), + SM5703VBUS("vbus"), +}; + +static int sm5703_regulator_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct regulator_config config = { NULL, }; + struct regulator_dev *rdev; + struct sm5703_dev *sm5703 = dev_get_drvdata(pdev->dev.parent); + int i; + + config.dev = dev->parent; + config.regmap = sm5703->regmap; + + for (i = 0; i < SM5703_MAX_REGULATORS; i++) { + rdev = devm_regulator_register(dev, + &sm5703_regulators_desc[i], + &config); + if (IS_ERR(rdev)) + return dev_err_probe(dev, PTR_ERR(rdev), + "Failed to register a regulator\n"); + } + + return 0; +} + +static const struct platform_device_id sm5703_regulator_id[] = { + { "sm5703-regulator", 0 }, + {} +}; +MODULE_DEVICE_TABLE(platform, sm5703_regulator_id); + +static struct platform_driver sm5703_regulator_driver = { + .driver = { + .name = "sm5703-regulator", + }, + .probe = sm5703_regulator_probe, + .id_table = sm5703_regulator_id, +}; + +module_platform_driver(sm5703_regulator_driver); + +MODULE_DESCRIPTION("Silicon Mitus SM5703 LDO/Buck/USB regulator driver"); +MODULE_AUTHOR("Markuss Broks <markuss.broks@gmail.com>"); +MODULE_LICENSE("GPL"); diff --git a/drivers/regulator/stm32-vrefbuf.c b/drivers/regulator/stm32-vrefbuf.c index 161622ea7259..30ea3bc8ca19 100644 --- a/drivers/regulator/stm32-vrefbuf.c +++ b/drivers/regulator/stm32-vrefbuf.c @@ -44,11 +44,9 @@ static int stm32_vrefbuf_enable(struct regulator_dev *rdev) u32 val; int ret; - ret = pm_runtime_get_sync(priv->dev); - if (ret < 0) { - pm_runtime_put_noidle(priv->dev); + ret = pm_runtime_resume_and_get(priv->dev); + if (ret < 0) return ret; - } val = readl_relaxed(priv->base + STM32_VREFBUF_CSR); val = (val & ~STM32_HIZ) | STM32_ENVR; @@ -81,11 +79,9 @@ static int stm32_vrefbuf_disable(struct regulator_dev *rdev) u32 val; int ret; - ret = pm_runtime_get_sync(priv->dev); - if (ret < 0) { - pm_runtime_put_noidle(priv->dev); + ret = pm_runtime_resume_and_get(priv->dev); + if (ret < 0) return ret; - } val = readl_relaxed(priv->base + STM32_VREFBUF_CSR); val &= ~STM32_ENVR; @@ -102,11 +98,9 @@ static int stm32_vrefbuf_is_enabled(struct regulator_dev *rdev) struct stm32_vrefbuf *priv = rdev_get_drvdata(rdev); int ret; - ret = pm_runtime_get_sync(priv->dev); - if (ret < 0) { - pm_runtime_put_noidle(priv->dev); + ret = pm_runtime_resume_and_get(priv->dev); + if (ret < 0) return ret; - } ret = readl_relaxed(priv->base + STM32_VREFBUF_CSR) & STM32_ENVR; @@ -123,11 +117,9 @@ static int stm32_vrefbuf_set_voltage_sel(struct regulator_dev *rdev, u32 val; int ret; - ret = pm_runtime_get_sync(priv->dev); - if (ret < 0) { - pm_runtime_put_noidle(priv->dev); + ret = pm_runtime_resume_and_get(priv->dev); + if (ret < 0) return ret; - } val = readl_relaxed(priv->base + STM32_VREFBUF_CSR); val = (val & ~STM32_VRS) | FIELD_PREP(STM32_VRS, sel); @@ -145,11 +137,9 @@ static int stm32_vrefbuf_get_voltage_sel(struct regulator_dev *rdev) u32 val; int ret; - ret = pm_runtime_get_sync(priv->dev); - if (ret < 0) { - pm_runtime_put_noidle(priv->dev); + ret = pm_runtime_resume_and_get(priv->dev); + if (ret < 0) return ret; - } val = readl_relaxed(priv->base + STM32_VREFBUF_CSR); ret = FIELD_GET(STM32_VRS, val); diff --git a/drivers/regulator/wm8994-regulator.c b/drivers/regulator/wm8994-regulator.c index cadea0344486..40befdd9dfa9 100644 --- a/drivers/regulator/wm8994-regulator.c +++ b/drivers/regulator/wm8994-regulator.c @@ -82,6 +82,35 @@ static const struct regulator_desc wm8994_ldo_desc[] = { .min_uV = 2400000, .uV_step = 100000, .enable_time = 3000, + .off_on_delay = 36000, + .owner = THIS_MODULE, + }, + { + .name = "LDO2", + .id = 2, + .type = REGULATOR_VOLTAGE, + .n_voltages = WM8994_LDO2_MAX_SELECTOR + 1, + .vsel_reg = WM8994_LDO_2, + .vsel_mask = WM8994_LDO2_VSEL_MASK, + .ops = &wm8994_ldo2_ops, + .enable_time = 3000, + .off_on_delay = 36000, + .owner = THIS_MODULE, + }, +}; + +static const struct regulator_desc wm8958_ldo_desc[] = { + { + .name = "LDO1", + .id = 1, + .type = REGULATOR_VOLTAGE, + .n_voltages = WM8994_LDO1_MAX_SELECTOR + 1, + .vsel_reg = WM8994_LDO_1, + .vsel_mask = WM8994_LDO1_VSEL_MASK, + .ops = &wm8994_ldo1_ops, + .min_uV = 2400000, + .uV_step = 100000, + .enable_time = 3000, .owner = THIS_MODULE, }, { @@ -172,9 +201,16 @@ static int wm8994_ldo_probe(struct platform_device *pdev) * regulator core and we need not worry about it on the * error path. */ - ldo->regulator = devm_regulator_register(&pdev->dev, - &wm8994_ldo_desc[id], - &config); + if (ldo->wm8994->type == WM8994) { + ldo->regulator = devm_regulator_register(&pdev->dev, + &wm8994_ldo_desc[id], + &config); + } else { + ldo->regulator = devm_regulator_register(&pdev->dev, + &wm8958_ldo_desc[id], + &config); + } + if (IS_ERR(ldo->regulator)) { ret = PTR_ERR(ldo->regulator); dev_err(wm8994->dev, "Failed to register LDO%d: %d\n", diff --git a/drivers/reset/reset-rzg2l-usbphy-ctrl.c b/drivers/reset/reset-rzg2l-usbphy-ctrl.c index 1e8315038850..a8dde4606360 100644 --- a/drivers/reset/reset-rzg2l-usbphy-ctrl.c +++ b/drivers/reset/reset-rzg2l-usbphy-ctrl.c @@ -121,7 +121,9 @@ static int rzg2l_usbphy_ctrl_probe(struct platform_device *pdev) return dev_err_probe(dev, PTR_ERR(priv->rstc), "failed to get reset\n"); - reset_control_deassert(priv->rstc); + error = reset_control_deassert(priv->rstc); + if (error) + return error; priv->rcdev.ops = &rzg2l_usbphy_ctrl_reset_ops; priv->rcdev.of_reset_n_cells = 1; diff --git a/drivers/reset/tegra/reset-bpmp.c b/drivers/reset/tegra/reset-bpmp.c index 24d3395964cc..4c5bba52b105 100644 --- a/drivers/reset/tegra/reset-bpmp.c +++ b/drivers/reset/tegra/reset-bpmp.c @@ -20,6 +20,7 @@ static int tegra_bpmp_reset_common(struct reset_controller_dev *rstc, struct tegra_bpmp *bpmp = to_tegra_bpmp(rstc); struct mrq_reset_request request; struct tegra_bpmp_message msg; + int err; memset(&request, 0, sizeof(request)); request.cmd = command; @@ -30,7 +31,13 @@ static int tegra_bpmp_reset_common(struct reset_controller_dev *rstc, msg.tx.data = &request; msg.tx.size = sizeof(request); - return tegra_bpmp_transfer(bpmp, &msg); + err = tegra_bpmp_transfer(bpmp, &msg); + if (err) + return err; + if (msg.rx.ret) + return -EINVAL; + + return 0; } static int tegra_bpmp_reset_module(struct reset_controller_dev *rstc, diff --git a/drivers/rtc/rtc-goldfish.c b/drivers/rtc/rtc-goldfish.c index 7ab95d052644..59c0f38cc08d 100644 --- a/drivers/rtc/rtc-goldfish.c +++ b/drivers/rtc/rtc-goldfish.c @@ -10,18 +10,8 @@ #include <linux/of.h> #include <linux/platform_device.h> #include <linux/rtc.h> - -#define TIMER_TIME_LOW 0x00 /* get low bits of current time */ - /* and update TIMER_TIME_HIGH */ -#define TIMER_TIME_HIGH 0x04 /* get high bits of time at last */ - /* TIMER_TIME_LOW read */ -#define TIMER_ALARM_LOW 0x08 /* set low bits of alarm and */ - /* activate it */ -#define TIMER_ALARM_HIGH 0x0c /* set high bits of next alarm */ -#define TIMER_IRQ_ENABLED 0x10 -#define TIMER_CLEAR_ALARM 0x14 -#define TIMER_ALARM_STATUS 0x18 -#define TIMER_CLEAR_INTERRUPT 0x1c +#include <linux/goldfish.h> +#include <clocksource/timer-goldfish.h> struct goldfish_rtc { void __iomem *base; @@ -41,8 +31,8 @@ static int goldfish_rtc_read_alarm(struct device *dev, rtcdrv = dev_get_drvdata(dev); base = rtcdrv->base; - rtc_alarm_low = readl(base + TIMER_ALARM_LOW); - rtc_alarm_high = readl(base + TIMER_ALARM_HIGH); + rtc_alarm_low = gf_ioread32(base + TIMER_ALARM_LOW); + rtc_alarm_high = gf_ioread32(base + TIMER_ALARM_HIGH); rtc_alarm = (rtc_alarm_high << 32) | rtc_alarm_low; do_div(rtc_alarm, NSEC_PER_SEC); @@ -50,7 +40,7 @@ static int goldfish_rtc_read_alarm(struct device *dev, rtc_time64_to_tm(rtc_alarm, &alrm->time); - if (readl(base + TIMER_ALARM_STATUS)) + if (gf_ioread32(base + TIMER_ALARM_STATUS)) alrm->enabled = 1; else alrm->enabled = 0; @@ -71,18 +61,18 @@ static int goldfish_rtc_set_alarm(struct device *dev, if (alrm->enabled) { rtc_alarm64 = rtc_tm_to_time64(&alrm->time) * NSEC_PER_SEC; - writel((rtc_alarm64 >> 32), base + TIMER_ALARM_HIGH); - writel(rtc_alarm64, base + TIMER_ALARM_LOW); - writel(1, base + TIMER_IRQ_ENABLED); + gf_iowrite32((rtc_alarm64 >> 32), base + TIMER_ALARM_HIGH); + gf_iowrite32(rtc_alarm64, base + TIMER_ALARM_LOW); + gf_iowrite32(1, base + TIMER_IRQ_ENABLED); } else { /* * if this function was called with enabled=0 * then it could mean that the application is * trying to cancel an ongoing alarm */ - rtc_status_reg = readl(base + TIMER_ALARM_STATUS); + rtc_status_reg = gf_ioread32(base + TIMER_ALARM_STATUS); if (rtc_status_reg) - writel(1, base + TIMER_CLEAR_ALARM); + gf_iowrite32(1, base + TIMER_CLEAR_ALARM); } return 0; @@ -98,9 +88,9 @@ static int goldfish_rtc_alarm_irq_enable(struct device *dev, base = rtcdrv->base; if (enabled) - writel(1, base + TIMER_IRQ_ENABLED); + gf_iowrite32(1, base + TIMER_IRQ_ENABLED); else - writel(0, base + TIMER_IRQ_ENABLED); + gf_iowrite32(0, base + TIMER_IRQ_ENABLED); return 0; } @@ -110,7 +100,7 @@ static irqreturn_t goldfish_rtc_interrupt(int irq, void *dev_id) struct goldfish_rtc *rtcdrv = dev_id; void __iomem *base = rtcdrv->base; - writel(1, base + TIMER_CLEAR_INTERRUPT); + gf_iowrite32(1, base + TIMER_CLEAR_INTERRUPT); rtc_update_irq(rtcdrv->rtc, 1, RTC_IRQF | RTC_AF); @@ -128,8 +118,8 @@ static int goldfish_rtc_read_time(struct device *dev, struct rtc_time *tm) rtcdrv = dev_get_drvdata(dev); base = rtcdrv->base; - time_low = readl(base + TIMER_TIME_LOW); - time_high = readl(base + TIMER_TIME_HIGH); + time_low = gf_ioread32(base + TIMER_TIME_LOW); + time_high = gf_ioread32(base + TIMER_TIME_HIGH); time = (time_high << 32) | time_low; do_div(time, NSEC_PER_SEC); @@ -149,8 +139,8 @@ static int goldfish_rtc_set_time(struct device *dev, struct rtc_time *tm) base = rtcdrv->base; now64 = rtc_tm_to_time64(tm) * NSEC_PER_SEC; - writel((now64 >> 32), base + TIMER_TIME_HIGH); - writel(now64, base + TIMER_TIME_LOW); + gf_iowrite32((now64 >> 32), base + TIMER_TIME_HIGH); + gf_iowrite32(now64, base + TIMER_TIME_LOW); return 0; } diff --git a/drivers/rtc/rtc-sun6i.c b/drivers/rtc/rtc-sun6i.c index 5b3e4da63406..5252ce4cbda4 100644 --- a/drivers/rtc/rtc-sun6i.c +++ b/drivers/rtc/rtc-sun6i.c @@ -370,6 +370,23 @@ CLK_OF_DECLARE_DRIVER(sun8i_h3_rtc_clk, "allwinner,sun8i-h3-rtc", CLK_OF_DECLARE_DRIVER(sun50i_h5_rtc_clk, "allwinner,sun50i-h5-rtc", sun8i_h3_rtc_clk_init); +static const struct sun6i_rtc_clk_data sun50i_h6_rtc_data = { + .rc_osc_rate = 16000000, + .fixed_prescaler = 32, + .has_prescaler = 1, + .has_out_clk = 1, + .export_iosc = 1, + .has_losc_en = 1, + .has_auto_swt = 1, +}; + +static void __init sun50i_h6_rtc_clk_init(struct device_node *node) +{ + sun6i_rtc_clk_init(node, &sun50i_h6_rtc_data); +} +CLK_OF_DECLARE_DRIVER(sun50i_h6_rtc_clk, "allwinner,sun50i-h6-rtc", + sun50i_h6_rtc_clk_init); + /* * The R40 user manual is self-conflicting on whether the prescaler is * fixed or configurable. The clock diagram shows it as fixed, but there diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c index 8e87a31e329d..ba6d78789660 100644 --- a/drivers/s390/block/dasd.c +++ b/drivers/s390/block/dasd.c @@ -1422,6 +1422,13 @@ int dasd_start_IO(struct dasd_ccw_req *cqr) if (!cqr->lpm) cqr->lpm = dasd_path_get_opm(device); } + /* + * remember the amount of formatted tracks to prevent double format on + * ESE devices + */ + if (cqr->block) + cqr->trkcount = atomic_read(&cqr->block->trkcount); + if (cqr->cpmode == 1) { rc = ccw_device_tm_start(device->cdev, cqr->cpaddr, (long) cqr, cqr->lpm); @@ -1639,6 +1646,7 @@ void dasd_int_handler(struct ccw_device *cdev, unsigned long intparm, unsigned long now; int nrf_suppressed = 0; int fp_suppressed = 0; + struct request *req; u8 *sense = NULL; int expires; @@ -1739,7 +1747,12 @@ void dasd_int_handler(struct ccw_device *cdev, unsigned long intparm, } if (dasd_ese_needs_format(cqr->block, irb)) { - if (rq_data_dir((struct request *)cqr->callback_data) == READ) { + req = dasd_get_callback_data(cqr); + if (!req) { + cqr->status = DASD_CQR_ERROR; + return; + } + if (rq_data_dir(req) == READ) { device->discipline->ese_read(cqr, irb); cqr->status = DASD_CQR_SUCCESS; cqr->stopclk = now; @@ -2765,8 +2778,7 @@ static void __dasd_cleanup_cqr(struct dasd_ccw_req *cqr) * complete a request partially. */ if (proc_bytes) { - blk_update_request(req, BLK_STS_OK, - blk_rq_bytes(req) - proc_bytes); + blk_update_request(req, BLK_STS_OK, proc_bytes); blk_mq_requeue_request(req, true); } else if (likely(!blk_should_fake_timeout(req->q))) { blk_mq_complete_request(req); diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c index 8410a25a65c1..836838f7d686 100644 --- a/drivers/s390/block/dasd_eckd.c +++ b/drivers/s390/block/dasd_eckd.c @@ -1480,7 +1480,7 @@ static int dasd_eckd_pe_handler(struct dasd_device *device, { struct pe_handler_work_data *data; - data = kmalloc(sizeof(*data), GFP_ATOMIC | GFP_DMA); + data = kzalloc(sizeof(*data), GFP_ATOMIC | GFP_DMA); if (!data) { if (mutex_trylock(&dasd_pe_handler_mutex)) { data = pe_handler_worker; @@ -1488,9 +1488,6 @@ static int dasd_eckd_pe_handler(struct dasd_device *device, } else { return -ENOMEM; } - } else { - memset(data, 0, sizeof(*data)); - data->isglobal = 0; } INIT_WORK(&data->worker, do_pe_handler_work); dasd_get_device(device); @@ -3083,13 +3080,24 @@ static int dasd_eckd_format_device(struct dasd_device *base, } static bool test_and_set_format_track(struct dasd_format_entry *to_format, - struct dasd_block *block) + struct dasd_ccw_req *cqr) { + struct dasd_block *block = cqr->block; struct dasd_format_entry *format; unsigned long flags; bool rc = false; spin_lock_irqsave(&block->format_lock, flags); + if (cqr->trkcount != atomic_read(&block->trkcount)) { + /* + * The number of formatted tracks has changed after request + * start and we can not tell if the current track was involved. + * To avoid data corruption treat it as if the current track is + * involved + */ + rc = true; + goto out; + } list_for_each_entry(format, &block->format_list, list) { if (format->track == to_format->track) { rc = true; @@ -3109,6 +3117,7 @@ static void clear_format_track(struct dasd_format_entry *format, unsigned long flags; spin_lock_irqsave(&block->format_lock, flags); + atomic_inc(&block->trkcount); list_del_init(&format->list); spin_unlock_irqrestore(&block->format_lock, flags); } @@ -3145,7 +3154,7 @@ dasd_eckd_ese_format(struct dasd_device *startdev, struct dasd_ccw_req *cqr, sector_t curr_trk; int rc; - req = cqr->callback_data; + req = dasd_get_callback_data(cqr); block = cqr->block; base = block->base; private = base->private; @@ -3170,8 +3179,11 @@ dasd_eckd_ese_format(struct dasd_device *startdev, struct dasd_ccw_req *cqr, } format->track = curr_trk; /* test if track is already in formatting by another thread */ - if (test_and_set_format_track(format, block)) + if (test_and_set_format_track(format, cqr)) { + /* this is no real error so do not count down retries */ + cqr->retries++; return ERR_PTR(-EEXIST); + } fdata.start_unit = curr_trk; fdata.stop_unit = curr_trk; @@ -3270,12 +3282,11 @@ static int dasd_eckd_ese_read(struct dasd_ccw_req *cqr, struct irb *irb) cqr->proc_bytes = blk_count * blksize; return 0; } - if (dst && !skip_block) { - dst += off; + if (dst && !skip_block) memset(dst, 0, blksize); - } else { + else skip_block--; - } + dst += blksize; blk_count++; } } diff --git a/drivers/s390/block/dasd_fba.c b/drivers/s390/block/dasd_fba.c index e084f4dedddd..60be7f7bf2d1 100644 --- a/drivers/s390/block/dasd_fba.c +++ b/drivers/s390/block/dasd_fba.c @@ -782,7 +782,6 @@ static void dasd_fba_setup_blk_queue(struct dasd_block *block) blk_queue_segment_boundary(q, PAGE_SIZE - 1); q->limits.discard_granularity = logical_block_size; - q->limits.discard_alignment = PAGE_SIZE; /* Calculate max_discard_sectors and make it PAGE aligned */ max_bytes = USHRT_MAX * logical_block_size; @@ -791,7 +790,6 @@ static void dasd_fba_setup_blk_queue(struct dasd_block *block) blk_queue_max_discard_sectors(q, max_discard_sectors); blk_queue_max_write_zeroes_sectors(q, max_discard_sectors); - blk_queue_flag_set(QUEUE_FLAG_DISCARD, q); } static int dasd_fba_pe_handler(struct dasd_device *device, diff --git a/drivers/s390/block/dasd_int.h b/drivers/s390/block/dasd_int.h index 3b7af00a7825..83b918b84b4a 100644 --- a/drivers/s390/block/dasd_int.h +++ b/drivers/s390/block/dasd_int.h @@ -187,6 +187,7 @@ struct dasd_ccw_req { void (*callback)(struct dasd_ccw_req *, void *data); void *callback_data; unsigned int proc_bytes; /* bytes for partial completion */ + unsigned int trkcount; /* count formatted tracks */ }; /* @@ -610,6 +611,7 @@ struct dasd_block { struct list_head format_list; spinlock_t format_lock; + atomic_t trkcount; }; struct dasd_attention_data { @@ -756,6 +758,18 @@ dasd_check_blocksize(int bsize) return 0; } +/* + * return the callback data of the original request in case there are + * ERP requests build on top of it + */ +static inline void *dasd_get_callback_data(struct dasd_ccw_req *cqr) +{ + while (cqr->refers) + cqr = cqr->refers; + + return cqr->callback_data; +} + /* externals in dasd.c */ #define DASD_PROFILE_OFF 0 #define DASD_PROFILE_ON 1 diff --git a/drivers/s390/char/con3215.c b/drivers/s390/char/con3215.c index f356607835d8..4ae07c7e2175 100644 --- a/drivers/s390/char/con3215.c +++ b/drivers/s390/char/con3215.c @@ -771,35 +771,36 @@ static struct tty_driver *con3215_device(struct console *c, int *index) } /* - * panic() calls con3215_flush through a panic_notifier - * before the system enters a disabled, endless loop. + * The below function is called as a panic/reboot notifier before the + * system enters a disabled, endless loop. + * + * Notice we must use the spin_trylock() alternative, to prevent lockups + * in atomic context (panic routine runs with secondary CPUs, local IRQs + * and preemption disabled). */ -static void con3215_flush(void) +static int con3215_notify(struct notifier_block *self, + unsigned long event, void *data) { struct raw3215_info *raw; unsigned long flags; raw = raw3215[0]; /* console 3215 is the first one */ - spin_lock_irqsave(get_ccwdev_lock(raw->cdev), flags); + if (!spin_trylock_irqsave(get_ccwdev_lock(raw->cdev), flags)) + return NOTIFY_DONE; raw3215_make_room(raw, RAW3215_BUFFER_SIZE); spin_unlock_irqrestore(get_ccwdev_lock(raw->cdev), flags); -} -static int con3215_notify(struct notifier_block *self, - unsigned long event, void *data) -{ - con3215_flush(); - return NOTIFY_OK; + return NOTIFY_DONE; } static struct notifier_block on_panic_nb = { .notifier_call = con3215_notify, - .priority = 0, + .priority = INT_MIN + 1, /* run the callback late */ }; static struct notifier_block on_reboot_nb = { .notifier_call = con3215_notify, - .priority = 0, + .priority = INT_MIN + 1, /* run the callback late */ }; /* diff --git a/drivers/s390/char/con3270.c b/drivers/s390/char/con3270.c index e4592890f20a..10f6a37fb153 100644 --- a/drivers/s390/char/con3270.c +++ b/drivers/s390/char/con3270.c @@ -535,20 +535,26 @@ con3270_wait_write(struct con3270 *cp) } /* - * panic() calls con3270_flush through a panic_notifier - * before the system enters a disabled, endless loop. + * The below function is called as a panic/reboot notifier before the + * system enters a disabled, endless loop. + * + * Notice we must use the spin_trylock() alternative, to prevent lockups + * in atomic context (panic routine runs with secondary CPUs, local IRQs + * and preemption disabled). */ -static void -con3270_flush(void) +static int con3270_notify(struct notifier_block *self, + unsigned long event, void *data) { struct con3270 *cp; unsigned long flags; cp = condev; if (!cp->view.dev) - return; - raw3270_activate_view(&cp->view); - spin_lock_irqsave(&cp->view.lock, flags); + return NOTIFY_DONE; + if (!raw3270_view_lock_unavailable(&cp->view)) + raw3270_activate_view(&cp->view); + if (!spin_trylock_irqsave(&cp->view.lock, flags)) + return NOTIFY_DONE; con3270_wait_write(cp); cp->nr_up = 0; con3270_rebuild_update(cp); @@ -560,23 +566,18 @@ con3270_flush(void) con3270_wait_write(cp); } spin_unlock_irqrestore(&cp->view.lock, flags); -} -static int con3270_notify(struct notifier_block *self, - unsigned long event, void *data) -{ - con3270_flush(); - return NOTIFY_OK; + return NOTIFY_DONE; } static struct notifier_block on_panic_nb = { .notifier_call = con3270_notify, - .priority = 0, + .priority = INT_MIN + 1, /* run the callback late */ }; static struct notifier_block on_reboot_nb = { .notifier_call = con3270_notify, - .priority = 0, + .priority = INT_MIN + 1, /* run the callback late */ }; /* diff --git a/drivers/s390/char/raw3270.c b/drivers/s390/char/raw3270.c index dfde0d941c3c..4e2b3a1a3b2e 100644 --- a/drivers/s390/char/raw3270.c +++ b/drivers/s390/char/raw3270.c @@ -831,6 +831,21 @@ raw3270_create_device(struct ccw_device *cdev) } /* + * This helper just validates that it is safe to activate a + * view in the panic() context, due to locking restrictions. + */ +int raw3270_view_lock_unavailable(struct raw3270_view *view) +{ + struct raw3270 *rp = view->dev; + + if (!rp) + return -ENODEV; + if (spin_is_locked(get_ccwdev_lock(rp->cdev))) + return -EBUSY; + return 0; +} + +/* * Activate a view. */ int diff --git a/drivers/s390/char/raw3270.h b/drivers/s390/char/raw3270.h index c6645167cd2b..4cb6b5ee44ca 100644 --- a/drivers/s390/char/raw3270.h +++ b/drivers/s390/char/raw3270.h @@ -160,6 +160,7 @@ struct raw3270_view { }; int raw3270_add_view(struct raw3270_view *, struct raw3270_fn *, int, int); +int raw3270_view_lock_unavailable(struct raw3270_view *view); int raw3270_activate_view(struct raw3270_view *); void raw3270_del_view(struct raw3270_view *); void raw3270_deactivate_view(struct raw3270_view *); diff --git a/drivers/s390/char/sclp_con.c b/drivers/s390/char/sclp_con.c index fe5ee2646fcf..e5d947c763ea 100644 --- a/drivers/s390/char/sclp_con.c +++ b/drivers/s390/char/sclp_con.c @@ -220,30 +220,34 @@ sclp_console_device(struct console *c, int *index) } /* - * Make sure that all buffers will be flushed to the SCLP. + * This panic/reboot notifier makes sure that all buffers + * will be flushed to the SCLP. */ -static void -sclp_console_flush(void) +static int sclp_console_notify(struct notifier_block *self, + unsigned long event, void *data) { + /* + * Perform the lock check before effectively getting the + * lock on sclp_conbuf_emit() / sclp_console_sync_queue() + * to prevent potential lockups in atomic context. + */ + if (spin_is_locked(&sclp_con_lock)) + return NOTIFY_DONE; + sclp_conbuf_emit(); sclp_console_sync_queue(); -} -static int sclp_console_notify(struct notifier_block *self, - unsigned long event, void *data) -{ - sclp_console_flush(); - return NOTIFY_OK; + return NOTIFY_DONE; } static struct notifier_block on_panic_nb = { .notifier_call = sclp_console_notify, - .priority = 1, + .priority = INT_MIN + 1, /* run the callback late */ }; static struct notifier_block on_reboot_nb = { .notifier_call = sclp_console_notify, - .priority = 1, + .priority = INT_MIN + 1, /* run the callback late */ }; /* diff --git a/drivers/s390/char/sclp_early.c b/drivers/s390/char/sclp_early.c index e9943a86c361..dd313ff57df3 100644 --- a/drivers/s390/char/sclp_early.c +++ b/drivers/s390/char/sclp_early.c @@ -49,8 +49,10 @@ static void __init sclp_early_facilities_detect(void) S390_lowcore.machine_flags |= MACHINE_FLAG_ESOP; if (sccb->fac91 & 0x40) S390_lowcore.machine_flags |= MACHINE_FLAG_TLB_GUEST; - if (sccb->cpuoff > 134) + if (sccb->cpuoff > 134) { sclp.has_diag318 = !!(sccb->byte_134 & 0x80); + sclp.has_iplcc = !!(sccb->byte_134 & 0x02); + } if (sccb->cpuoff > 137) sclp.has_sipl = !!(sccb->cbl & 0x4000); sclp.rnmax = sccb->rnmax ? sccb->rnmax : sccb->rnmax2; diff --git a/drivers/s390/char/sclp_vt220.c b/drivers/s390/char/sclp_vt220.c index 3b4e7e5d9b71..a32f34a1c6d2 100644 --- a/drivers/s390/char/sclp_vt220.c +++ b/drivers/s390/char/sclp_vt220.c @@ -769,21 +769,6 @@ __initcall(sclp_vt220_tty_init); #ifdef CONFIG_SCLP_VT220_CONSOLE -static void __sclp_vt220_flush_buffer(void) -{ - unsigned long flags; - - sclp_vt220_emit_current(); - spin_lock_irqsave(&sclp_vt220_lock, flags); - del_timer(&sclp_vt220_timer); - while (sclp_vt220_queue_running) { - spin_unlock_irqrestore(&sclp_vt220_lock, flags); - sclp_sync_wait(); - spin_lock_irqsave(&sclp_vt220_lock, flags); - } - spin_unlock_irqrestore(&sclp_vt220_lock, flags); -} - static void sclp_vt220_con_write(struct console *con, const char *buf, unsigned int count) { @@ -797,22 +782,41 @@ sclp_vt220_con_device(struct console *c, int *index) return sclp_vt220_driver; } +/* + * This panic/reboot notifier runs in atomic context, so + * locking restrictions apply to prevent potential lockups. + */ static int sclp_vt220_notify(struct notifier_block *self, unsigned long event, void *data) { - __sclp_vt220_flush_buffer(); - return NOTIFY_OK; + unsigned long flags; + + if (spin_is_locked(&sclp_vt220_lock)) + return NOTIFY_DONE; + + sclp_vt220_emit_current(); + + spin_lock_irqsave(&sclp_vt220_lock, flags); + del_timer(&sclp_vt220_timer); + while (sclp_vt220_queue_running) { + spin_unlock_irqrestore(&sclp_vt220_lock, flags); + sclp_sync_wait(); + spin_lock_irqsave(&sclp_vt220_lock, flags); + } + spin_unlock_irqrestore(&sclp_vt220_lock, flags); + + return NOTIFY_DONE; } static struct notifier_block on_panic_nb = { .notifier_call = sclp_vt220_notify, - .priority = 1, + .priority = INT_MIN + 1, /* run the callback late */ }; static struct notifier_block on_reboot_nb = { .notifier_call = sclp_vt220_notify, - .priority = 1, + .priority = INT_MIN + 1, /* run the callback late */ }; /* Structure needed to register with printk */ diff --git a/drivers/s390/cio/chsc.c b/drivers/s390/cio/chsc.c index 297fb399363c..620a917cd3a1 100644 --- a/drivers/s390/cio/chsc.c +++ b/drivers/s390/cio/chsc.c @@ -1255,7 +1255,7 @@ exit: EXPORT_SYMBOL_GPL(css_general_characteristics); EXPORT_SYMBOL_GPL(css_chsc_characteristics); -int chsc_sstpc(void *page, unsigned int op, u16 ctrl, u64 *clock_delta) +int chsc_sstpc(void *page, unsigned int op, u16 ctrl, long *clock_delta) { struct { struct chsc_header request; @@ -1266,7 +1266,7 @@ int chsc_sstpc(void *page, unsigned int op, u16 ctrl, u64 *clock_delta) unsigned int rsvd2[5]; struct chsc_header response; unsigned int rsvd3[3]; - u64 clock_delta; + s64 clock_delta; unsigned int rsvd4[2]; } *rr; int rc; diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c index fdf16cb70881..5c13d2079d96 100644 --- a/drivers/s390/crypto/ap_bus.c +++ b/drivers/s390/crypto/ap_bus.c @@ -179,7 +179,7 @@ static int ap_qci_available(void) * ap_apft_available(): Test if AP facilities test (APFT) * facility is available. * - * Returns 1 if APFT is is available. + * Returns 1 if APFT is available. */ static int ap_apft_available(void) { @@ -693,6 +693,24 @@ void ap_send_online_uevent(struct ap_device *ap_dev, int online) } EXPORT_SYMBOL(ap_send_online_uevent); +static void ap_send_mask_changed_uevent(unsigned long *newapm, + unsigned long *newaqm) +{ + char buf[100]; + char *envp[] = { buf, NULL }; + + if (newapm) + snprintf(buf, sizeof(buf), + "APMASK=0x%016lx%016lx%016lx%016lx\n", + newapm[0], newapm[1], newapm[2], newapm[3]); + else + snprintf(buf, sizeof(buf), + "AQMASK=0x%016lx%016lx%016lx%016lx\n", + newaqm[0], newaqm[1], newaqm[2], newaqm[3]); + + kobject_uevent_env(&ap_root_device->kobj, KOBJ_CHANGE, envp); +} + /* * calc # of bound APQNs */ @@ -704,7 +722,7 @@ struct __ap_calc_ctrs { static int __ap_calc_helper(struct device *dev, void *arg) { - struct __ap_calc_ctrs *pctrs = (struct __ap_calc_ctrs *) arg; + struct __ap_calc_ctrs *pctrs = (struct __ap_calc_ctrs *)arg; if (is_queue_dev(dev)) { pctrs->apqns++; @@ -720,7 +738,7 @@ static void ap_calc_bound_apqns(unsigned int *apqns, unsigned int *bound) struct __ap_calc_ctrs ctrs; memset(&ctrs, 0, sizeof(ctrs)); - bus_for_each_dev(&ap_bus_type, NULL, (void *) &ctrs, __ap_calc_helper); + bus_for_each_dev(&ap_bus_type, NULL, (void *)&ctrs, __ap_calc_helper); *apqns = ctrs.apqns; *bound = ctrs.bound; @@ -781,7 +799,7 @@ EXPORT_SYMBOL(ap_wait_init_apqn_bindings_complete); static int __ap_queue_devices_with_id_unregister(struct device *dev, void *data) { if (is_queue_dev(dev) && - AP_QID_CARD(to_ap_queue(dev)->qid) == (int)(long) data) + AP_QID_CARD(to_ap_queue(dev)->qid) == (int)(long)data) device_unregister(dev); return 0; } @@ -794,8 +812,8 @@ static int __ap_revise_reserved(struct device *dev, void *dummy) card = AP_QID_CARD(to_ap_queue(dev)->qid); queue = AP_QID_QUEUE(to_ap_queue(dev)->qid); mutex_lock(&ap_perms_mutex); - devres = test_bit_inv(card, ap_perms.apm) - && test_bit_inv(queue, ap_perms.aqm); + devres = test_bit_inv(card, ap_perms.apm) && + test_bit_inv(queue, ap_perms.aqm); mutex_unlock(&ap_perms_mutex); drvres = to_ap_drv(dev->driver)->flags & AP_DRIVER_FLAG_DEFAULT; @@ -826,8 +844,8 @@ int ap_owned_by_def_drv(int card, int queue) mutex_lock(&ap_perms_mutex); - if (test_bit_inv(card, ap_perms.apm) - && test_bit_inv(queue, ap_perms.aqm)) + if (test_bit_inv(card, ap_perms.apm) && + test_bit_inv(queue, ap_perms.aqm)) rc = 1; mutex_unlock(&ap_perms_mutex); @@ -876,8 +894,8 @@ static int ap_device_probe(struct device *dev) card = AP_QID_CARD(to_ap_queue(dev)->qid); queue = AP_QID_QUEUE(to_ap_queue(dev)->qid); mutex_lock(&ap_perms_mutex); - devres = test_bit_inv(card, ap_perms.apm) - && test_bit_inv(queue, ap_perms.aqm); + devres = test_bit_inv(card, ap_perms.apm) && + test_bit_inv(queue, ap_perms.aqm); mutex_unlock(&ap_perms_mutex); drvres = ap_drv->flags & AP_DRIVER_FLAG_DEFAULT; if (!!devres != !!drvres) @@ -898,8 +916,9 @@ static int ap_device_probe(struct device *dev) if (is_queue_dev(dev)) hash_del(&to_ap_queue(dev)->hnode); spin_unlock_bh(&ap_queues_lock); - } else + } else { ap_check_bindings_complete(); + } out: if (rc) @@ -980,8 +999,8 @@ void ap_bus_force_rescan(void) EXPORT_SYMBOL(ap_bus_force_rescan); /* -* A config change has happened, force an ap bus rescan. -*/ + * A config change has happened, force an ap bus rescan. + */ void ap_bus_cfg_chg(void) { AP_DBF_DBG("%s config change, forcing bus rescan\n", __func__); @@ -1105,7 +1124,7 @@ int ap_parse_mask_str(const char *str, if (bits & 0x07) return -EINVAL; - size = BITS_TO_LONGS(bits)*sizeof(unsigned long); + size = BITS_TO_LONGS(bits) * sizeof(unsigned long); newmap = kmalloc(size, GFP_KERNEL); if (!newmap) return -ENOMEM; @@ -1241,8 +1260,9 @@ static ssize_t poll_thread_store(struct bus_type *bus, rc = ap_poll_thread_start(); if (rc) count = rc; - } else + } else { ap_poll_thread_stop(); + } return count; } @@ -1355,7 +1375,7 @@ static int apmask_commit(unsigned long *newapm) static ssize_t apmask_store(struct bus_type *bus, const char *buf, size_t count) { - int rc; + int rc, changes = 0; DECLARE_BITMAP(newapm, AP_DEVICES); if (mutex_lock_interruptible(&ap_perms_mutex)) @@ -1365,14 +1385,19 @@ static ssize_t apmask_store(struct bus_type *bus, const char *buf, if (rc) goto done; - rc = apmask_commit(newapm); + changes = memcmp(ap_perms.apm, newapm, APMASKSIZE); + if (changes) + rc = apmask_commit(newapm); done: mutex_unlock(&ap_perms_mutex); if (rc) return rc; - ap_bus_revise_bindings(); + if (changes) { + ap_bus_revise_bindings(); + ap_send_mask_changed_uevent(newapm, NULL); + } return count; } @@ -1443,7 +1468,7 @@ static int aqmask_commit(unsigned long *newaqm) static ssize_t aqmask_store(struct bus_type *bus, const char *buf, size_t count) { - int rc; + int rc, changes = 0; DECLARE_BITMAP(newaqm, AP_DOMAINS); if (mutex_lock_interruptible(&ap_perms_mutex)) @@ -1453,14 +1478,19 @@ static ssize_t aqmask_store(struct bus_type *bus, const char *buf, if (rc) goto done; - rc = aqmask_commit(newaqm); + changes = memcmp(ap_perms.aqm, newaqm, APMASKSIZE); + if (changes) + rc = aqmask_commit(newaqm); done: mutex_unlock(&ap_perms_mutex); if (rc) return rc; - ap_bus_revise_bindings(); + if (changes) { + ap_bus_revise_bindings(); + ap_send_mask_changed_uevent(NULL, newaqm); + } return count; } @@ -1605,9 +1635,9 @@ static int ap_get_compatible_type(ap_qid_t qid, int rawtype, unsigned int func) apinfo.mode = (func >> 26) & 0x07; apinfo.cat = AP_DEVICE_TYPE_CEX8; status = ap_qact(qid, 0, &apinfo); - if (status.response_code == AP_RESPONSE_NORMAL - && apinfo.cat >= AP_DEVICE_TYPE_CEX2A - && apinfo.cat <= AP_DEVICE_TYPE_CEX8) + if (status.response_code == AP_RESPONSE_NORMAL && + apinfo.cat >= AP_DEVICE_TYPE_CEX2A && + apinfo.cat <= AP_DEVICE_TYPE_CEX8) comp_type = apinfo.cat; } if (!comp_type) @@ -1627,7 +1657,7 @@ static int ap_get_compatible_type(ap_qid_t qid, int rawtype, unsigned int func) */ static int __match_card_device_with_id(struct device *dev, const void *data) { - return is_card_dev(dev) && to_ap_card(dev)->id == (int)(long)(void *) data; + return is_card_dev(dev) && to_ap_card(dev)->id == (int)(long)(void *)data; } /* @@ -1636,7 +1666,7 @@ static int __match_card_device_with_id(struct device *dev, const void *data) */ static int __match_queue_device_with_qid(struct device *dev, const void *data) { - return is_queue_dev(dev) && to_ap_queue(dev)->qid == (int)(long) data; + return is_queue_dev(dev) && to_ap_queue(dev)->qid == (int)(long)data; } /* @@ -1645,8 +1675,8 @@ static int __match_queue_device_with_qid(struct device *dev, const void *data) */ static int __match_queue_device_with_queue_id(struct device *dev, const void *data) { - return is_queue_dev(dev) - && AP_QID_QUEUE(to_ap_queue(dev)->qid) == (int)(long) data; + return is_queue_dev(dev) && + AP_QID_QUEUE(to_ap_queue(dev)->qid) == (int)(long)data; } /* Helper function for notify_config_changed */ @@ -1699,7 +1729,7 @@ static inline void notify_scan_complete(void) static inline void ap_scan_rm_card_dev_and_queue_devs(struct ap_card *ac) { bus_for_each_dev(&ap_bus_type, NULL, - (void *)(long) ac->id, + (void *)(long)ac->id, __ap_queue_devices_with_id_unregister); device_unregister(&ac->ap_dev.device); } @@ -1727,7 +1757,7 @@ static inline void ap_scan_domains(struct ap_card *ac) for (dom = 0; dom <= ap_max_domain_id; dom++) { qid = AP_MKQID(ac->id, dom); dev = bus_find_device(&ap_bus_type, NULL, - (void *)(long) qid, + (void *)(long)qid, __match_queue_device_with_qid); aq = dev ? to_ap_queue(dev) : NULL; if (!ap_test_config_usage_domain(dom)) { @@ -1873,7 +1903,7 @@ static inline void ap_scan_adapter(int ap) /* Is there currently a card device for this adapter ? */ dev = bus_find_device(&ap_bus_type, NULL, - (void *)(long) ap, + (void *)(long)ap, __match_card_device_with_id); ac = dev ? to_ap_card(dev) : NULL; @@ -2074,7 +2104,7 @@ static void ap_scan_bus(struct work_struct *unused) if (ap_domain_index >= 0) { struct device *dev = bus_find_device(&ap_bus_type, NULL, - (void *)(long) ap_domain_index, + (void *)(long)ap_domain_index, __match_queue_device_with_queue_id); if (dev) put_device(dev); @@ -2109,7 +2139,7 @@ static int __init ap_debug_init(void) static void __init ap_perms_init(void) { - /* all resources useable if no kernel parameter string given */ + /* all resources usable if no kernel parameter string given */ memset(&ap_perms.ioctlm, 0xFF, sizeof(ap_perms.ioctlm)); memset(&ap_perms.apm, 0xFF, sizeof(ap_perms.apm)); memset(&ap_perms.aqm, 0xFF, sizeof(ap_perms.aqm)); diff --git a/drivers/s390/crypto/ap_bus.h b/drivers/s390/crypto/ap_bus.h index 6a65885f5f43..0c40af157df2 100644 --- a/drivers/s390/crypto/ap_bus.h +++ b/drivers/s390/crypto/ap_bus.h @@ -317,6 +317,7 @@ struct ap_perms { unsigned long aqm[BITS_TO_LONGS(AP_DOMAINS)]; unsigned long adm[BITS_TO_LONGS(AP_DOMAINS)]; }; + extern struct ap_perms ap_perms; extern struct mutex ap_perms_mutex; diff --git a/drivers/s390/crypto/ap_queue.c b/drivers/s390/crypto/ap_queue.c index 205045cd998d..c48b0db824e3 100644 --- a/drivers/s390/crypto/ap_queue.c +++ b/drivers/s390/crypto/ap_queue.c @@ -99,7 +99,7 @@ int ap_recv(ap_qid_t qid, unsigned long long *psmid, void *msg, size_t length) { struct ap_queue_status status; - if (msg == NULL) + if (!msg) return -EINVAL; status = ap_dqap(qid, psmid, msg, length, NULL, NULL); switch (status.response_code) { @@ -603,7 +603,7 @@ static ssize_t interrupt_show(struct device *dev, static DEVICE_ATTR_RO(interrupt); static ssize_t config_show(struct device *dev, - struct device_attribute *attr, char *buf) + struct device_attribute *attr, char *buf) { struct ap_queue *aq = to_ap_queue(dev); int rc; @@ -827,8 +827,9 @@ int ap_queue_message(struct ap_queue *aq, struct ap_message *ap_msg) aq->requestq_count++; aq->total_request_count++; atomic64_inc(&aq->card->total_request_count); - } else + } else { rc = -ENODEV; + } /* Send/receive as many request from the queue as possible. */ ap_wait(ap_sm_event_loop(aq, AP_SM_EVENT_POLL)); diff --git a/drivers/s390/crypto/pkey_api.c b/drivers/s390/crypto/pkey_api.c index 7f69ca695fc2..7329caa7d467 100644 --- a/drivers/s390/crypto/pkey_api.c +++ b/drivers/s390/crypto/pkey_api.c @@ -232,7 +232,7 @@ static int pkey_ep11key2pkey(const u8 *key, struct pkey_protkey *pkey) int i, rc; u16 card, dom; u32 nr_apqns, *apqns = NULL; - struct ep11keyblob *kb = (struct ep11keyblob *) key; + struct ep11keyblob *kb = (struct ep11keyblob *)key; zcrypt_wait_api_operational(); @@ -267,12 +267,12 @@ static int pkey_verifykey(const struct pkey_seckey *seckey, u16 *pcardnr, u16 *pdomain, u16 *pkeysize, u32 *pattributes) { - struct secaeskeytoken *t = (struct secaeskeytoken *) seckey; + struct secaeskeytoken *t = (struct secaeskeytoken *)seckey; u16 cardnr, domain; int rc; /* check the secure key for valid AES secure key */ - rc = cca_check_secaeskeytoken(debug_info, 3, (u8 *) seckey, 0); + rc = cca_check_secaeskeytoken(debug_info, 3, (u8 *)seckey, 0); if (rc) goto out; if (pattributes) @@ -425,9 +425,9 @@ static int pkey_nonccatok2pkey(const u8 *key, u32 keylen, t = (struct clearaeskeytoken *)key; if (keylen != sizeof(*t) + t->len) goto out; - if ((t->keytype == PKEY_KEYTYPE_AES_128 && t->len == 16) - || (t->keytype == PKEY_KEYTYPE_AES_192 && t->len == 24) - || (t->keytype == PKEY_KEYTYPE_AES_256 && t->len == 32)) + if ((t->keytype == PKEY_KEYTYPE_AES_128 && t->len == 16) || + (t->keytype == PKEY_KEYTYPE_AES_192 && t->len == 24) || + (t->keytype == PKEY_KEYTYPE_AES_256 && t->len == 32)) memcpy(ckey.clrkey, t->clearkey, t->len); else goto out; @@ -541,7 +541,6 @@ int pkey_keyblob2pkey(const u8 *key, u32 keylen, DEBUG_DBG("%s rc=%d\n", __func__, rc); return rc; - } EXPORT_SYMBOL(pkey_keyblob2pkey); @@ -588,9 +587,11 @@ static int pkey_genseckey2(const struct pkey_apqn *apqns, size_t nr_apqns, } else if (ktype == PKEY_TYPE_CCA_DATA) { rc = cca_genseckey(card, dom, ksize, keybuf); *keybufsize = (rc ? 0 : SECKEYBLOBSIZE); - } else /* TOKVER_CCA_VLSC */ + } else { + /* TOKVER_CCA_VLSC */ rc = cca_gencipherkey(card, dom, ksize, kflags, keybuf, keybufsize); + } if (rc == 0) break; } @@ -645,9 +646,11 @@ static int pkey_clr2seckey2(const struct pkey_apqn *apqns, size_t nr_apqns, rc = cca_clr2seckey(card, dom, ksize, clrkey, keybuf); *keybufsize = (rc ? 0 : SECKEYBLOBSIZE); - } else /* TOKVER_CCA_VLSC */ + } else { + /* TOKVER_CCA_VLSC */ rc = cca_clr2cipherkey(card, dom, ksize, kflags, clrkey, keybuf, keybufsize); + } if (rc == 0) break; } @@ -667,8 +670,8 @@ static int pkey_verifykey2(const u8 *key, size_t keylen, if (keylen < sizeof(struct keytoken_header)) return -EINVAL; - if (hdr->type == TOKTYPE_CCA_INTERNAL - && hdr->version == TOKVER_CCA_AES) { + if (hdr->type == TOKTYPE_CCA_INTERNAL && + hdr->version == TOKVER_CCA_AES) { struct secaeskeytoken *t = (struct secaeskeytoken *)key; rc = cca_check_secaeskeytoken(debug_info, 3, key, 0); @@ -677,7 +680,7 @@ static int pkey_verifykey2(const u8 *key, size_t keylen, if (ktype) *ktype = PKEY_TYPE_CCA_DATA; if (ksize) - *ksize = (enum pkey_key_size) t->bitsize; + *ksize = (enum pkey_key_size)t->bitsize; rc = cca_findcard2(&_apqns, &_nr_apqns, *cardnr, *domain, ZCRYPT_CEX3C, AES_MK_SET, t->mkvp, 0, 1); @@ -697,8 +700,8 @@ static int pkey_verifykey2(const u8 *key, size_t keylen, *cardnr = ((struct pkey_apqn *)_apqns)->card; *domain = ((struct pkey_apqn *)_apqns)->domain; - } else if (hdr->type == TOKTYPE_CCA_INTERNAL - && hdr->version == TOKVER_CCA_VLSC) { + } else if (hdr->type == TOKTYPE_CCA_INTERNAL && + hdr->version == TOKVER_CCA_VLSC) { struct cipherkeytoken *t = (struct cipherkeytoken *)key; rc = cca_check_secaescipherkey(debug_info, 3, key, 0, 1); @@ -734,8 +737,8 @@ static int pkey_verifykey2(const u8 *key, size_t keylen, *cardnr = ((struct pkey_apqn *)_apqns)->card; *domain = ((struct pkey_apqn *)_apqns)->domain; - } else if (hdr->type == TOKTYPE_NON_CCA - && hdr->version == TOKVER_EP11_AES) { + } else if (hdr->type == TOKTYPE_NON_CCA && + hdr->version == TOKVER_EP11_AES) { struct ep11keyblob *kb = (struct ep11keyblob *)key; rc = ep11_check_aes_key(debug_info, 3, key, keylen, 1); @@ -757,8 +760,9 @@ static int pkey_verifykey2(const u8 *key, size_t keylen, *cardnr = ((struct pkey_apqn *)_apqns)->card; *domain = ((struct pkey_apqn *)_apqns)->domain; - } else + } else { rc = -EINVAL; + } out: kfree(_apqns); @@ -816,16 +820,17 @@ static int pkey_keyblob2pkey2(const struct pkey_apqn *apqns, size_t nr_apqns, for (i = 0, rc = -ENODEV; i < nr_apqns; i++) { card = apqns[i].card; dom = apqns[i].domain; - if (hdr->type == TOKTYPE_CCA_INTERNAL - && hdr->version == TOKVER_CCA_AES) + if (hdr->type == TOKTYPE_CCA_INTERNAL && + hdr->version == TOKVER_CCA_AES) { rc = cca_sec2protkey(card, dom, key, pkey->protkey, &pkey->len, &pkey->type); - else if (hdr->type == TOKTYPE_CCA_INTERNAL - && hdr->version == TOKVER_CCA_VLSC) + } else if (hdr->type == TOKTYPE_CCA_INTERNAL && + hdr->version == TOKVER_CCA_VLSC) { rc = cca_cipher2protkey(card, dom, key, pkey->protkey, &pkey->len, &pkey->type); - else { /* EP11 AES secure key blob */ - struct ep11keyblob *kb = (struct ep11keyblob *) key; + } else { + /* EP11 AES secure key blob */ + struct ep11keyblob *kb = (struct ep11keyblob *)key; pkey->len = sizeof(pkey->protkey); rc = ep11_kblob2protkey(card, dom, key, kb->head.len, @@ -851,10 +856,10 @@ static int pkey_apqns4key(const u8 *key, size_t keylen, u32 flags, zcrypt_wait_api_operational(); - if (hdr->type == TOKTYPE_NON_CCA - && (hdr->version == TOKVER_EP11_AES_WITH_HEADER - || hdr->version == TOKVER_EP11_ECC_WITH_HEADER) - && is_ep11_keyblob(key + sizeof(struct ep11kblob_header))) { + if (hdr->type == TOKTYPE_NON_CCA && + (hdr->version == TOKVER_EP11_AES_WITH_HEADER || + hdr->version == TOKVER_EP11_ECC_WITH_HEADER) && + is_ep11_keyblob(key + sizeof(struct ep11kblob_header))) { int minhwtype = 0, api = 0; struct ep11keyblob *kb = (struct ep11keyblob *) (key + sizeof(struct ep11kblob_header)); @@ -869,11 +874,11 @@ static int pkey_apqns4key(const u8 *key, size_t keylen, u32 flags, minhwtype, api, kb->wkvp); if (rc) goto out; - } else if (hdr->type == TOKTYPE_NON_CCA - && hdr->version == TOKVER_EP11_AES - && is_ep11_keyblob(key)) { + } else if (hdr->type == TOKTYPE_NON_CCA && + hdr->version == TOKVER_EP11_AES && + is_ep11_keyblob(key)) { int minhwtype = 0, api = 0; - struct ep11keyblob *kb = (struct ep11keyblob *) key; + struct ep11keyblob *kb = (struct ep11keyblob *)key; if (flags != PKEY_FLAGS_MATCH_CUR_MKVP) return -EINVAL; @@ -931,8 +936,9 @@ static int pkey_apqns4key(const u8 *key, size_t keylen, u32 flags, cur_mkvp, old_mkvp, 1); if (rc) goto out; - } else + } else { return -EINVAL; + } if (apqns) { if (*nr_apqns < _nr_apqns) @@ -961,9 +967,9 @@ static int pkey_apqns4keytype(enum pkey_key_type ktype, int minhwtype = ZCRYPT_CEX3C; if (flags & PKEY_FLAGS_MATCH_CUR_MKVP) - cur_mkvp = *((u64 *) cur_mkvp); + cur_mkvp = *((u64 *)cur_mkvp); if (flags & PKEY_FLAGS_MATCH_ALT_MKVP) - old_mkvp = *((u64 *) alt_mkvp); + old_mkvp = *((u64 *)alt_mkvp); if (ktype == PKEY_TYPE_CCA_CIPHER) minhwtype = ZCRYPT_CEX6; rc = cca_findcard2(&_apqns, &_nr_apqns, 0xFFFF, 0xFFFF, @@ -975,9 +981,9 @@ static int pkey_apqns4keytype(enum pkey_key_type ktype, u64 cur_mkvp = 0, old_mkvp = 0; if (flags & PKEY_FLAGS_MATCH_CUR_MKVP) - cur_mkvp = *((u64 *) cur_mkvp); + cur_mkvp = *((u64 *)cur_mkvp); if (flags & PKEY_FLAGS_MATCH_ALT_MKVP) - old_mkvp = *((u64 *) alt_mkvp); + old_mkvp = *((u64 *)alt_mkvp); rc = cca_findcard2(&_apqns, &_nr_apqns, 0xFFFF, 0xFFFF, ZCRYPT_CEX7, APKA_MK_SET, cur_mkvp, old_mkvp, 1); @@ -996,8 +1002,9 @@ static int pkey_apqns4keytype(enum pkey_key_type ktype, if (rc) goto out; - } else + } else { return -EINVAL; + } if (apqns) { if (*nr_apqns < _nr_apqns) @@ -1026,21 +1033,21 @@ static int pkey_keyblob2pkey3(const struct pkey_apqn *apqns, size_t nr_apqns, if (keylen < sizeof(struct keytoken_header)) return -EINVAL; - if (hdr->type == TOKTYPE_NON_CCA - && hdr->version == TOKVER_EP11_AES_WITH_HEADER - && is_ep11_keyblob(key + sizeof(struct ep11kblob_header))) { + if (hdr->type == TOKTYPE_NON_CCA && + hdr->version == TOKVER_EP11_AES_WITH_HEADER && + is_ep11_keyblob(key + sizeof(struct ep11kblob_header))) { /* EP11 AES key blob with header */ if (ep11_check_aes_key_with_hdr(debug_info, 3, key, keylen, 1)) return -EINVAL; - } else if (hdr->type == TOKTYPE_NON_CCA - && hdr->version == TOKVER_EP11_ECC_WITH_HEADER - && is_ep11_keyblob(key + sizeof(struct ep11kblob_header))) { + } else if (hdr->type == TOKTYPE_NON_CCA && + hdr->version == TOKVER_EP11_ECC_WITH_HEADER && + is_ep11_keyblob(key + sizeof(struct ep11kblob_header))) { /* EP11 ECC key blob with header */ if (ep11_check_ecc_key_with_hdr(debug_info, 3, key, keylen, 1)) return -EINVAL; - } else if (hdr->type == TOKTYPE_NON_CCA - && hdr->version == TOKVER_EP11_AES - && is_ep11_keyblob(key)) { + } else if (hdr->type == TOKTYPE_NON_CCA && + hdr->version == TOKVER_EP11_AES && + is_ep11_keyblob(key)) { /* EP11 AES key blob with header in session field */ if (ep11_check_aes_key(debug_info, 3, key, keylen, 1)) return -EINVAL; @@ -1088,15 +1095,15 @@ static int pkey_keyblob2pkey3(const struct pkey_apqn *apqns, size_t nr_apqns, for (rc = -ENODEV, i = 0; rc && i < nr_apqns; i++) { card = apqns[i].card; dom = apqns[i].domain; - if (hdr->type == TOKTYPE_NON_CCA - && (hdr->version == TOKVER_EP11_AES_WITH_HEADER - || hdr->version == TOKVER_EP11_ECC_WITH_HEADER) - && is_ep11_keyblob(key + sizeof(struct ep11kblob_header))) + if (hdr->type == TOKTYPE_NON_CCA && + (hdr->version == TOKVER_EP11_AES_WITH_HEADER || + hdr->version == TOKVER_EP11_ECC_WITH_HEADER) && + is_ep11_keyblob(key + sizeof(struct ep11kblob_header))) rc = ep11_kblob2protkey(card, dom, key, hdr->len, protkey, protkeylen, protkeytype); - else if (hdr->type == TOKTYPE_NON_CCA - && hdr->version == TOKVER_EP11_AES - && is_ep11_keyblob(key)) + else if (hdr->type == TOKTYPE_NON_CCA && + hdr->version == TOKVER_EP11_AES && + is_ep11_keyblob(key)) rc = ep11_kblob2protkey(card, dom, key, hdr->len, protkey, protkeylen, protkeytype); else if (hdr->type == TOKTYPE_CCA_INTERNAL && @@ -1144,7 +1151,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, switch (cmd) { case PKEY_GENSECK: { - struct pkey_genseck __user *ugs = (void __user *) arg; + struct pkey_genseck __user *ugs = (void __user *)arg; struct pkey_genseck kgs; if (copy_from_user(&kgs, ugs, sizeof(kgs))) @@ -1159,7 +1166,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, break; } case PKEY_CLR2SECK: { - struct pkey_clr2seck __user *ucs = (void __user *) arg; + struct pkey_clr2seck __user *ucs = (void __user *)arg; struct pkey_clr2seck kcs; if (copy_from_user(&kcs, ucs, sizeof(kcs))) @@ -1175,7 +1182,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, break; } case PKEY_SEC2PROTK: { - struct pkey_sec2protk __user *usp = (void __user *) arg; + struct pkey_sec2protk __user *usp = (void __user *)arg; struct pkey_sec2protk ksp; if (copy_from_user(&ksp, usp, sizeof(ksp))) @@ -1191,7 +1198,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, break; } case PKEY_CLR2PROTK: { - struct pkey_clr2protk __user *ucp = (void __user *) arg; + struct pkey_clr2protk __user *ucp = (void __user *)arg; struct pkey_clr2protk kcp; if (copy_from_user(&kcp, ucp, sizeof(kcp))) @@ -1207,7 +1214,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, break; } case PKEY_FINDCARD: { - struct pkey_findcard __user *ufc = (void __user *) arg; + struct pkey_findcard __user *ufc = (void __user *)arg; struct pkey_findcard kfc; if (copy_from_user(&kfc, ufc, sizeof(kfc))) @@ -1222,7 +1229,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, break; } case PKEY_SKEY2PKEY: { - struct pkey_skey2pkey __user *usp = (void __user *) arg; + struct pkey_skey2pkey __user *usp = (void __user *)arg; struct pkey_skey2pkey ksp; if (copy_from_user(&ksp, usp, sizeof(ksp))) @@ -1236,7 +1243,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, break; } case PKEY_VERIFYKEY: { - struct pkey_verifykey __user *uvk = (void __user *) arg; + struct pkey_verifykey __user *uvk = (void __user *)arg; struct pkey_verifykey kvk; if (copy_from_user(&kvk, uvk, sizeof(kvk))) @@ -1251,7 +1258,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, break; } case PKEY_GENPROTK: { - struct pkey_genprotk __user *ugp = (void __user *) arg; + struct pkey_genprotk __user *ugp = (void __user *)arg; struct pkey_genprotk kgp; if (copy_from_user(&kgp, ugp, sizeof(kgp))) @@ -1265,7 +1272,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, break; } case PKEY_VERIFYPROTK: { - struct pkey_verifyprotk __user *uvp = (void __user *) arg; + struct pkey_verifyprotk __user *uvp = (void __user *)arg; struct pkey_verifyprotk kvp; if (copy_from_user(&kvp, uvp, sizeof(kvp))) @@ -1275,7 +1282,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, break; } case PKEY_KBLOB2PROTK: { - struct pkey_kblob2pkey __user *utp = (void __user *) arg; + struct pkey_kblob2pkey __user *utp = (void __user *)arg; struct pkey_kblob2pkey ktp; u8 *kkey; @@ -1294,7 +1301,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, break; } case PKEY_GENSECK2: { - struct pkey_genseck2 __user *ugs = (void __user *) arg; + struct pkey_genseck2 __user *ugs = (void __user *)arg; struct pkey_genseck2 kgs; struct pkey_apqn *apqns; size_t klen = KEYBLOBBUFSIZE; @@ -1336,7 +1343,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, break; } case PKEY_CLR2SECK2: { - struct pkey_clr2seck2 __user *ucs = (void __user *) arg; + struct pkey_clr2seck2 __user *ucs = (void __user *)arg; struct pkey_clr2seck2 kcs; struct pkey_apqn *apqns; size_t klen = KEYBLOBBUFSIZE; @@ -1379,7 +1386,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, break; } case PKEY_VERIFYKEY2: { - struct pkey_verifykey2 __user *uvk = (void __user *) arg; + struct pkey_verifykey2 __user *uvk = (void __user *)arg; struct pkey_verifykey2 kvk; u8 *kkey; @@ -1400,7 +1407,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, break; } case PKEY_KBLOB2PROTK2: { - struct pkey_kblob2pkey2 __user *utp = (void __user *) arg; + struct pkey_kblob2pkey2 __user *utp = (void __user *)arg; struct pkey_kblob2pkey2 ktp; struct pkey_apqn *apqns = NULL; u8 *kkey; @@ -1427,7 +1434,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, break; } case PKEY_APQNS4K: { - struct pkey_apqns4key __user *uak = (void __user *) arg; + struct pkey_apqns4key __user *uak = (void __user *)arg; struct pkey_apqns4key kak; struct pkey_apqn *apqns = NULL; size_t nr_apqns, len; @@ -1476,7 +1483,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, break; } case PKEY_APQNS4KT: { - struct pkey_apqns4keytype __user *uat = (void __user *) arg; + struct pkey_apqns4keytype __user *uat = (void __user *)arg; struct pkey_apqns4keytype kat; struct pkey_apqn *apqns = NULL; size_t nr_apqns, len; @@ -1518,7 +1525,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, break; } case PKEY_KBLOB2PROTK3: { - struct pkey_kblob2pkey3 __user *utp = (void __user *) arg; + struct pkey_kblob2pkey3 __user *utp = (void __user *)arg; struct pkey_kblob2pkey3 ktp; struct pkey_apqn *apqns = NULL; u32 protkeylen = PROTKEYBLOBBUFSIZE; @@ -1708,7 +1715,7 @@ static ssize_t pkey_ccadata_aes_attr_read(u32 keytype, bool is_xts, char *buf, loff_t off, size_t count) { int rc; - struct pkey_seckey *seckey = (struct pkey_seckey *) buf; + struct pkey_seckey *seckey = (struct pkey_seckey *)buf; if (off != 0 || count < sizeof(struct secaeskeytoken)) return -EINVAL; diff --git a/drivers/s390/crypto/vfio_ap_drv.c b/drivers/s390/crypto/vfio_ap_drv.c index 29ebd54f8919..4ac9c6521ec1 100644 --- a/drivers/s390/crypto/vfio_ap_drv.c +++ b/drivers/s390/crypto/vfio_ap_drv.c @@ -46,8 +46,6 @@ static struct ap_device_id ap_queue_ids[] = { { /* end of sibling */ }, }; -MODULE_DEVICE_TABLE(vfio_ap, ap_queue_ids); - static struct ap_matrix_mdev *vfio_ap_mdev_for_queue(struct vfio_ap_queue *q) { struct ap_matrix_mdev *matrix_mdev; diff --git a/drivers/s390/crypto/zcrypt_api.c b/drivers/s390/crypto/zcrypt_api.c index aa6dc3c0c353..f94b43ce9a65 100644 --- a/drivers/s390/crypto/zcrypt_api.c +++ b/drivers/s390/crypto/zcrypt_api.c @@ -104,7 +104,7 @@ struct zcrypt_ops *zcrypt_msgtype(unsigned char *name, int variant) struct zcrypt_ops *zops; list_for_each_entry(zops, &zcrypt_ops_list, list) - if ((zops->variant == variant) && + if (zops->variant == variant && (!strncmp(zops->name, name, sizeof(zops->name)))) return zops; return NULL; @@ -438,8 +438,8 @@ static int zcdn_create(const char *name) strncpy(nodename, name, sizeof(nodename)); else snprintf(nodename, sizeof(nodename), - ZCRYPT_NAME "_%d", (int) MINOR(devt)); - nodename[sizeof(nodename)-1] = '\0'; + ZCRYPT_NAME "_%d", (int)MINOR(devt)); + nodename[sizeof(nodename) - 1] = '\0'; if (dev_set_name(&zcdndev->device, nodename)) { rc = -EINVAL; goto unlockout; @@ -519,7 +519,7 @@ static ssize_t zcrypt_read(struct file *filp, char __user *buf, /* * zcrypt_write(): Not allowed. * - * Write is is not allowed + * Write is not allowed */ static ssize_t zcrypt_write(struct file *filp, const char __user *buf, size_t count, loff_t *f_pos) @@ -549,7 +549,7 @@ static int zcrypt_open(struct inode *inode, struct file *filp) perms = &zcdndev->perms; } #endif - filp->private_data = (void *) perms; + filp->private_data = (void *)perms; atomic_inc(&zcrypt_open_count); return stream_open(inode, filp); @@ -713,7 +713,7 @@ static long zcrypt_rsa_modexpo(struct ap_perms *perms, pref_zq = NULL; spin_lock(&zcrypt_list_lock); for_each_zcrypt_card(zc) { - /* Check for useable accelarator or CCA card */ + /* Check for usable accelarator or CCA card */ if (!zc->online || !zc->card->config || zc->card->chkstop || !(zc->card->functions & 0x18000000)) continue; @@ -733,7 +733,7 @@ static long zcrypt_rsa_modexpo(struct ap_perms *perms, if (!zcrypt_card_compare(zc, pref_zc, wgt + cpen, pref_wgt)) continue; for_each_zcrypt_queue(zq, zc) { - /* check if device is useable and eligible */ + /* check if device is usable and eligible */ if (!zq->online || !zq->ops->rsa_modexpo || !zq->queue->config || zq->queue->chkstop) continue; @@ -823,7 +823,7 @@ static long zcrypt_rsa_crt(struct ap_perms *perms, pref_zq = NULL; spin_lock(&zcrypt_list_lock); for_each_zcrypt_card(zc) { - /* Check for useable accelarator or CCA card */ + /* Check for usable accelarator or CCA card */ if (!zc->online || !zc->card->config || zc->card->chkstop || !(zc->card->functions & 0x18000000)) continue; @@ -843,7 +843,7 @@ static long zcrypt_rsa_crt(struct ap_perms *perms, if (!zcrypt_card_compare(zc, pref_zc, wgt + cpen, pref_wgt)) continue; for_each_zcrypt_queue(zq, zc) { - /* check if device is useable and eligible */ + /* check if device is usable and eligible */ if (!zq->online || !zq->ops->rsa_modexpo_crt || !zq->queue->config || zq->queue->chkstop) continue; @@ -893,7 +893,7 @@ out: static long _zcrypt_send_cprb(bool userspace, struct ap_perms *perms, struct zcrypt_track *tr, - struct ica_xcRB *xcRB) + struct ica_xcRB *xcrb) { struct zcrypt_card *zc, *pref_zc; struct zcrypt_queue *zq, *pref_zq; @@ -904,9 +904,9 @@ static long _zcrypt_send_cprb(bool userspace, struct ap_perms *perms, int cpen, qpen, qid = 0, rc = -ENODEV; struct module *mod; - trace_s390_zcrypt_req(xcRB, TB_ZSECSENDCPRB); + trace_s390_zcrypt_req(xcrb, TB_ZSECSENDCPRB); - xcRB->status = 0; + xcrb->status = 0; ap_init_message(&ap_msg); #ifdef CONFIG_ZCRYPT_DEBUG @@ -915,11 +915,11 @@ static long _zcrypt_send_cprb(bool userspace, struct ap_perms *perms, if (tr && tr->fi.action == AP_FI_ACTION_CCA_AGENT_FF) { ZCRYPT_DBF_WARN("%s fi cmd 0x%04x: forcing invalid agent_ID 'FF'\n", __func__, tr->fi.cmd); - xcRB->agent_ID = 0x4646; + xcrb->agent_ID = 0x4646; } #endif - rc = prep_cca_ap_msg(userspace, xcRB, &ap_msg, &func_code, &domain); + rc = prep_cca_ap_msg(userspace, xcrb, &ap_msg, &func_code, &domain); if (rc) goto out; @@ -948,13 +948,13 @@ static long _zcrypt_send_cprb(bool userspace, struct ap_perms *perms, pref_zq = NULL; spin_lock(&zcrypt_list_lock); for_each_zcrypt_card(zc) { - /* Check for useable CCA card */ + /* Check for usable CCA card */ if (!zc->online || !zc->card->config || zc->card->chkstop || !(zc->card->functions & 0x10000000)) continue; /* Check for user selected CCA card */ - if (xcRB->user_defined != AUTOSELECT && - xcRB->user_defined != zc->card->id) + if (xcrb->user_defined != AUTOSELECT && + xcrb->user_defined != zc->card->id) continue; /* check if request size exceeds card max msg size */ if (ap_msg.len > zc->card->maxmsgsize) @@ -971,7 +971,7 @@ static long _zcrypt_send_cprb(bool userspace, struct ap_perms *perms, if (!zcrypt_card_compare(zc, pref_zc, wgt + cpen, pref_wgt)) continue; for_each_zcrypt_queue(zq, zc) { - /* check for device useable and eligible */ + /* check for device usable and eligible */ if (!zq->online || !zq->ops->send_cprb || !zq->queue->config || zq->queue->chkstop || (tdom != AUTOSEL_DOM && @@ -998,7 +998,7 @@ static long _zcrypt_send_cprb(bool userspace, struct ap_perms *perms, if (!pref_zq) { ZCRYPT_DBF_DBG("%s no match for address %02x.%04x => ENODEV\n", - __func__, xcRB->user_defined, *domain); + __func__, xcrb->user_defined, *domain); rc = -ENODEV; goto out; } @@ -1016,7 +1016,7 @@ static long _zcrypt_send_cprb(bool userspace, struct ap_perms *perms, } #endif - rc = pref_zq->ops->send_cprb(userspace, pref_zq, xcRB, &ap_msg); + rc = pref_zq->ops->send_cprb(userspace, pref_zq, xcrb, &ap_msg); spin_lock(&zcrypt_list_lock); zcrypt_drop_queue(pref_zc, pref_zq, mod, wgt); @@ -1028,14 +1028,14 @@ out: tr->last_rc = rc; tr->last_qid = qid; } - trace_s390_zcrypt_rep(xcRB, func_code, rc, + trace_s390_zcrypt_rep(xcrb, func_code, rc, AP_QID_CARD(qid), AP_QID_QUEUE(qid)); return rc; } -long zcrypt_send_cprb(struct ica_xcRB *xcRB) +long zcrypt_send_cprb(struct ica_xcRB *xcrb) { - return _zcrypt_send_cprb(false, &ap_perms, NULL, xcRB); + return _zcrypt_send_cprb(false, &ap_perms, NULL, xcrb); } EXPORT_SYMBOL(zcrypt_send_cprb); @@ -1089,7 +1089,7 @@ static long _zcrypt_send_ep11_cprb(bool userspace, struct ap_perms *perms, ap_msg.fi.cmd = tr->fi.cmd; #endif - target_num = (unsigned short) xcrb->targets_num; + target_num = (unsigned short)xcrb->targets_num; /* empty list indicates autoselect (all available targets) */ targets = NULL; @@ -1103,9 +1103,9 @@ static long _zcrypt_send_ep11_cprb(bool userspace, struct ap_perms *perms, goto out; } - uptr = (struct ep11_target_dev __force __user *) xcrb->targets; + uptr = (struct ep11_target_dev __force __user *)xcrb->targets; if (z_copy_from_user(userspace, targets, uptr, - target_num * sizeof(*targets))) { + target_num * sizeof(*targets))) { func_code = 0; rc = -EFAULT; goto out_free; @@ -1132,7 +1132,7 @@ static long _zcrypt_send_ep11_cprb(bool userspace, struct ap_perms *perms, pref_zq = NULL; spin_lock(&zcrypt_list_lock); for_each_zcrypt_card(zc) { - /* Check for useable EP11 card */ + /* Check for usable EP11 card */ if (!zc->online || !zc->card->config || zc->card->chkstop || !(zc->card->functions & 0x04000000)) continue; @@ -1155,7 +1155,7 @@ static long _zcrypt_send_ep11_cprb(bool userspace, struct ap_perms *perms, if (!zcrypt_card_compare(zc, pref_zc, wgt + cpen, pref_wgt)) continue; for_each_zcrypt_queue(zq, zc) { - /* check if device is useable and eligible */ + /* check if device is usable and eligible */ if (!zq->online || !zq->ops->send_ep11_cprb || !zq->queue->config || zq->queue->chkstop || (targets && @@ -1184,11 +1184,11 @@ static long _zcrypt_send_ep11_cprb(bool userspace, struct ap_perms *perms, if (!pref_zq) { if (targets && target_num == 1) { ZCRYPT_DBF_DBG("%s no match for address %02x.%04x => ENODEV\n", - __func__, (int) targets->ap_id, - (int) targets->dom_id); + __func__, (int)targets->ap_id, + (int)targets->dom_id); } else if (targets) { ZCRYPT_DBF_DBG("%s no match for %d target addrs => ENODEV\n", - __func__, (int) target_num); + __func__, (int)target_num); } else { ZCRYPT_DBF_DBG("%s no match for address ff.ffff => ENODEV\n", __func__); @@ -1245,7 +1245,7 @@ static long zcrypt_rng(char *buffer) pref_zq = NULL; spin_lock(&zcrypt_list_lock); for_each_zcrypt_card(zc) { - /* Check for useable CCA card */ + /* Check for usable CCA card */ if (!zc->online || !zc->card->config || zc->card->chkstop || !(zc->card->functions & 0x10000000)) continue; @@ -1254,7 +1254,7 @@ static long zcrypt_rng(char *buffer) if (!zcrypt_card_compare(zc, pref_zc, wgt, pref_wgt)) continue; for_each_zcrypt_queue(zq, zc) { - /* check if device is useable and eligible */ + /* check if device is usable and eligible */ if (!zq->online || !zq->ops->rng || !zq->queue->config || zq->queue->chkstop) continue; @@ -1270,7 +1270,7 @@ static long zcrypt_rng(char *buffer) if (!pref_zq) { ZCRYPT_DBF_DBG("%s no matching queue found => ENODEV\n", - __func__); + __func__); rc = -ENODEV; goto out; } @@ -1381,8 +1381,8 @@ static void zcrypt_status_mask(char status[], size_t max_adapters) for_each_zcrypt_card(zc) { for_each_zcrypt_queue(zq, zc) { card = AP_QID_CARD(zq->queue->qid); - if (AP_QID_QUEUE(zq->queue->qid) != ap_domain_index - || card >= max_adapters) + if (AP_QID_QUEUE(zq->queue->qid) != ap_domain_index || + card >= max_adapters) continue; status[card] = zc->online ? zc->user_space_type : 0x0d; } @@ -1402,8 +1402,8 @@ static void zcrypt_qdepth_mask(char qdepth[], size_t max_adapters) for_each_zcrypt_card(zc) { for_each_zcrypt_queue(zq, zc) { card = AP_QID_CARD(zq->queue->qid); - if (AP_QID_QUEUE(zq->queue->qid) != ap_domain_index - || card >= max_adapters) + if (AP_QID_QUEUE(zq->queue->qid) != ap_domain_index || + card >= max_adapters) continue; spin_lock(&zq->queue->lock); qdepth[card] = @@ -1429,13 +1429,13 @@ static void zcrypt_perdev_reqcnt(u32 reqcnt[], size_t max_adapters) for_each_zcrypt_card(zc) { for_each_zcrypt_queue(zq, zc) { card = AP_QID_CARD(zq->queue->qid); - if (AP_QID_QUEUE(zq->queue->qid) != ap_domain_index - || card >= max_adapters) + if (AP_QID_QUEUE(zq->queue->qid) != ap_domain_index || + card >= max_adapters) continue; spin_lock(&zq->queue->lock); cnt = zq->queue->total_request_count; spin_unlock(&zq->queue->lock); - reqcnt[card] = (cnt < UINT_MAX) ? (u32) cnt : UINT_MAX; + reqcnt[card] = (cnt < UINT_MAX) ? (u32)cnt : UINT_MAX; } } local_bh_enable(); @@ -1493,7 +1493,7 @@ static int icarsamodexpo_ioctl(struct ap_perms *perms, unsigned long arg) int rc; struct zcrypt_track tr; struct ica_rsa_modexpo mex; - struct ica_rsa_modexpo __user *umex = (void __user *) arg; + struct ica_rsa_modexpo __user *umex = (void __user *)arg; memset(&tr, 0, sizeof(tr)); if (copy_from_user(&mex, umex, sizeof(mex))) @@ -1538,7 +1538,7 @@ static int icarsacrt_ioctl(struct ap_perms *perms, unsigned long arg) int rc; struct zcrypt_track tr; struct ica_rsa_modexpo_crt crt; - struct ica_rsa_modexpo_crt __user *ucrt = (void __user *) arg; + struct ica_rsa_modexpo_crt __user *ucrt = (void __user *)arg; memset(&tr, 0, sizeof(tr)); if (copy_from_user(&crt, ucrt, sizeof(crt))) @@ -1581,25 +1581,25 @@ static int icarsacrt_ioctl(struct ap_perms *perms, unsigned long arg) static int zsecsendcprb_ioctl(struct ap_perms *perms, unsigned long arg) { int rc; - struct ica_xcRB xcRB; + struct ica_xcRB xcrb; struct zcrypt_track tr; - struct ica_xcRB __user *uxcRB = (void __user *) arg; + struct ica_xcRB __user *uxcrb = (void __user *)arg; memset(&tr, 0, sizeof(tr)); - if (copy_from_user(&xcRB, uxcRB, sizeof(xcRB))) + if (copy_from_user(&xcrb, uxcrb, sizeof(xcrb))) return -EFAULT; #ifdef CONFIG_ZCRYPT_DEBUG - if ((xcRB.status & 0x8000FFFF) == 0x80004649 /* 'FI' */) { + if ((xcrb.status & 0x8000FFFF) == 0x80004649 /* 'FI' */) { if (!capable(CAP_SYS_ADMIN)) return -EPERM; - tr.fi.cmd = (u16)(xcRB.status >> 16); + tr.fi.cmd = (u16)(xcrb.status >> 16); } - xcRB.status = 0; + xcrb.status = 0; #endif do { - rc = _zcrypt_send_cprb(true, perms, &tr, &xcRB); + rc = _zcrypt_send_cprb(true, perms, &tr, &xcrb); if (rc == -EAGAIN) tr.again_counter++; #ifdef CONFIG_ZCRYPT_DEBUG @@ -1610,7 +1610,7 @@ static int zsecsendcprb_ioctl(struct ap_perms *perms, unsigned long arg) /* on failure: retry once again after a requested rescan */ if ((rc == -ENODEV) && (zcrypt_process_rescan())) do { - rc = _zcrypt_send_cprb(true, perms, &tr, &xcRB); + rc = _zcrypt_send_cprb(true, perms, &tr, &xcrb); if (rc == -EAGAIN) tr.again_counter++; } while (rc == -EAGAIN && tr.again_counter < TRACK_AGAIN_MAX); @@ -1618,8 +1618,8 @@ static int zsecsendcprb_ioctl(struct ap_perms *perms, unsigned long arg) rc = -EIO; if (rc) ZCRYPT_DBF_DBG("ioctl ZSENDCPRB rc=%d status=0x%x\n", - rc, xcRB.status); - if (copy_to_user(uxcRB, &xcRB, sizeof(xcRB))) + rc, xcrb.status); + if (copy_to_user(uxcrb, &xcrb, sizeof(xcrb))) return -EFAULT; return rc; } @@ -1674,7 +1674,7 @@ static long zcrypt_unlocked_ioctl(struct file *filp, unsigned int cmd, { int rc; struct ap_perms *perms = - (struct ap_perms *) filp->private_data; + (struct ap_perms *)filp->private_data; rc = zcrypt_check_ioctl(perms, cmd); if (rc) @@ -1698,7 +1698,7 @@ static long zcrypt_unlocked_ioctl(struct file *filp, unsigned int cmd, if (!device_status) return -ENOMEM; zcrypt_device_status_mask_ext(device_status); - if (copy_to_user((char __user *) arg, device_status, + if (copy_to_user((char __user *)arg, device_status, total_size)) rc = -EFAULT; kfree(device_status); @@ -1708,7 +1708,7 @@ static long zcrypt_unlocked_ioctl(struct file *filp, unsigned int cmd, char status[AP_DEVICES]; zcrypt_status_mask(status, AP_DEVICES); - if (copy_to_user((char __user *) arg, status, sizeof(status))) + if (copy_to_user((char __user *)arg, status, sizeof(status))) return -EFAULT; return 0; } @@ -1716,7 +1716,7 @@ static long zcrypt_unlocked_ioctl(struct file *filp, unsigned int cmd, char qdepth[AP_DEVICES]; zcrypt_qdepth_mask(qdepth, AP_DEVICES); - if (copy_to_user((char __user *) arg, qdepth, sizeof(qdepth))) + if (copy_to_user((char __user *)arg, qdepth, sizeof(qdepth))) return -EFAULT; return 0; } @@ -1727,21 +1727,21 @@ static long zcrypt_unlocked_ioctl(struct file *filp, unsigned int cmd, if (!reqcnt) return -ENOMEM; zcrypt_perdev_reqcnt(reqcnt, AP_DEVICES); - if (copy_to_user((int __user *) arg, reqcnt, + if (copy_to_user((int __user *)arg, reqcnt, sizeof(u32) * AP_DEVICES)) rc = -EFAULT; kfree(reqcnt); return rc; } case Z90STAT_REQUESTQ_COUNT: - return put_user(zcrypt_requestq_count(), (int __user *) arg); + return put_user(zcrypt_requestq_count(), (int __user *)arg); case Z90STAT_PENDINGQ_COUNT: - return put_user(zcrypt_pendingq_count(), (int __user *) arg); + return put_user(zcrypt_pendingq_count(), (int __user *)arg); case Z90STAT_TOTALOPEN_COUNT: return put_user(atomic_read(&zcrypt_open_count), - (int __user *) arg); + (int __user *)arg); case Z90STAT_DOMAIN_INDEX: - return put_user(ap_domain_index, (int __user *) arg); + return put_user(ap_domain_index, (int __user *)arg); /* * Deprecated ioctls */ @@ -1755,7 +1755,7 @@ static long zcrypt_unlocked_ioctl(struct file *filp, unsigned int cmd, if (!device_status) return -ENOMEM; zcrypt_device_status_mask(device_status); - if (copy_to_user((char __user *) arg, device_status, + if (copy_to_user((char __user *)arg, device_status, total_size)) rc = -EFAULT; kfree(device_status); @@ -1766,7 +1766,7 @@ static long zcrypt_unlocked_ioctl(struct file *filp, unsigned int cmd, char status[MAX_ZDEV_CARDIDS]; zcrypt_status_mask(status, MAX_ZDEV_CARDIDS); - if (copy_to_user((char __user *) arg, status, sizeof(status))) + if (copy_to_user((char __user *)arg, status, sizeof(status))) return -EFAULT; return 0; } @@ -1775,7 +1775,7 @@ static long zcrypt_unlocked_ioctl(struct file *filp, unsigned int cmd, char qdepth[MAX_ZDEV_CARDIDS]; zcrypt_qdepth_mask(qdepth, MAX_ZDEV_CARDIDS); - if (copy_to_user((char __user *) arg, qdepth, sizeof(qdepth))) + if (copy_to_user((char __user *)arg, qdepth, sizeof(qdepth))) return -EFAULT; return 0; } @@ -1784,7 +1784,7 @@ static long zcrypt_unlocked_ioctl(struct file *filp, unsigned int cmd, u32 reqcnt[MAX_ZDEV_CARDIDS]; zcrypt_perdev_reqcnt(reqcnt, MAX_ZDEV_CARDIDS); - if (copy_to_user((int __user *) arg, reqcnt, sizeof(reqcnt))) + if (copy_to_user((int __user *)arg, reqcnt, sizeof(reqcnt))) return -EFAULT; return 0; } @@ -1899,7 +1899,7 @@ static long trans_modexpo_crt32(struct ap_perms *perms, struct file *filp, &ucrt32->outputdatalength); } -struct compat_ica_xcRB { +struct compat_ica_xcrb { unsigned short agent_ID; unsigned int user_defined; unsigned short request_ID; @@ -1919,66 +1919,66 @@ struct compat_ica_xcRB { unsigned int status; } __packed; -static long trans_xcRB32(struct ap_perms *perms, struct file *filp, +static long trans_xcrb32(struct ap_perms *perms, struct file *filp, unsigned int cmd, unsigned long arg) { - struct compat_ica_xcRB __user *uxcRB32 = compat_ptr(arg); - struct compat_ica_xcRB xcRB32; + struct compat_ica_xcrb __user *uxcrb32 = compat_ptr(arg); + struct compat_ica_xcrb xcrb32; struct zcrypt_track tr; - struct ica_xcRB xcRB64; + struct ica_xcRB xcrb64; long rc; memset(&tr, 0, sizeof(tr)); - if (copy_from_user(&xcRB32, uxcRB32, sizeof(xcRB32))) + if (copy_from_user(&xcrb32, uxcrb32, sizeof(xcrb32))) return -EFAULT; - xcRB64.agent_ID = xcRB32.agent_ID; - xcRB64.user_defined = xcRB32.user_defined; - xcRB64.request_ID = xcRB32.request_ID; - xcRB64.request_control_blk_length = - xcRB32.request_control_blk_length; - xcRB64.request_control_blk_addr = - compat_ptr(xcRB32.request_control_blk_addr); - xcRB64.request_data_length = - xcRB32.request_data_length; - xcRB64.request_data_address = - compat_ptr(xcRB32.request_data_address); - xcRB64.reply_control_blk_length = - xcRB32.reply_control_blk_length; - xcRB64.reply_control_blk_addr = - compat_ptr(xcRB32.reply_control_blk_addr); - xcRB64.reply_data_length = xcRB32.reply_data_length; - xcRB64.reply_data_addr = - compat_ptr(xcRB32.reply_data_addr); - xcRB64.priority_window = xcRB32.priority_window; - xcRB64.status = xcRB32.status; + xcrb64.agent_ID = xcrb32.agent_ID; + xcrb64.user_defined = xcrb32.user_defined; + xcrb64.request_ID = xcrb32.request_ID; + xcrb64.request_control_blk_length = + xcrb32.request_control_blk_length; + xcrb64.request_control_blk_addr = + compat_ptr(xcrb32.request_control_blk_addr); + xcrb64.request_data_length = + xcrb32.request_data_length; + xcrb64.request_data_address = + compat_ptr(xcrb32.request_data_address); + xcrb64.reply_control_blk_length = + xcrb32.reply_control_blk_length; + xcrb64.reply_control_blk_addr = + compat_ptr(xcrb32.reply_control_blk_addr); + xcrb64.reply_data_length = xcrb32.reply_data_length; + xcrb64.reply_data_addr = + compat_ptr(xcrb32.reply_data_addr); + xcrb64.priority_window = xcrb32.priority_window; + xcrb64.status = xcrb32.status; do { - rc = _zcrypt_send_cprb(true, perms, &tr, &xcRB64); + rc = _zcrypt_send_cprb(true, perms, &tr, &xcrb64); if (rc == -EAGAIN) tr.again_counter++; } while (rc == -EAGAIN && tr.again_counter < TRACK_AGAIN_MAX); /* on failure: retry once again after a requested rescan */ if ((rc == -ENODEV) && (zcrypt_process_rescan())) do { - rc = _zcrypt_send_cprb(true, perms, &tr, &xcRB64); + rc = _zcrypt_send_cprb(true, perms, &tr, &xcrb64); if (rc == -EAGAIN) tr.again_counter++; } while (rc == -EAGAIN && tr.again_counter < TRACK_AGAIN_MAX); if (rc == -EAGAIN && tr.again_counter >= TRACK_AGAIN_MAX) rc = -EIO; - xcRB32.reply_control_blk_length = xcRB64.reply_control_blk_length; - xcRB32.reply_data_length = xcRB64.reply_data_length; - xcRB32.status = xcRB64.status; - if (copy_to_user(uxcRB32, &xcRB32, sizeof(xcRB32))) + xcrb32.reply_control_blk_length = xcrb64.reply_control_blk_length; + xcrb32.reply_data_length = xcrb64.reply_data_length; + xcrb32.status = xcrb64.status; + if (copy_to_user(uxcrb32, &xcrb32, sizeof(xcrb32))) return -EFAULT; return rc; } static long zcrypt_compat_ioctl(struct file *filp, unsigned int cmd, - unsigned long arg) + unsigned long arg) { int rc; struct ap_perms *perms = - (struct ap_perms *) filp->private_data; + (struct ap_perms *)filp->private_data; rc = zcrypt_check_ioctl(perms, cmd); if (rc) @@ -1989,7 +1989,7 @@ static long zcrypt_compat_ioctl(struct file *filp, unsigned int cmd, if (cmd == ICARSACRT) return trans_modexpo_crt32(perms, filp, cmd, arg); if (cmd == ZSECSENDCPRB) - return trans_xcRB32(perms, filp, cmd, arg); + return trans_xcrb32(perms, filp, cmd, arg); return zcrypt_unlocked_ioctl(filp, cmd, arg); } #endif @@ -2033,10 +2033,10 @@ static int zcrypt_rng_data_read(struct hwrng *rng, u32 *data) * read method calls. */ if (zcrypt_rng_buffer_index == 0) { - rc = zcrypt_rng((char *) zcrypt_rng_buffer); + rc = zcrypt_rng((char *)zcrypt_rng_buffer); /* on failure: retry once again after a requested rescan */ if ((rc == -ENODEV) && (zcrypt_process_rescan())) - rc = zcrypt_rng((char *) zcrypt_rng_buffer); + rc = zcrypt_rng((char *)zcrypt_rng_buffer); if (rc < 0) return -EIO; zcrypt_rng_buffer_index = rc / sizeof(*data); @@ -2057,7 +2057,7 @@ int zcrypt_rng_device_add(void) mutex_lock(&zcrypt_rng_mutex); if (zcrypt_rng_device_count == 0) { - zcrypt_rng_buffer = (u32 *) get_zeroed_page(GFP_KERNEL); + zcrypt_rng_buffer = (u32 *)get_zeroed_page(GFP_KERNEL); if (!zcrypt_rng_buffer) { rc = -ENOMEM; goto out; @@ -2069,13 +2069,14 @@ int zcrypt_rng_device_add(void) if (rc) goto out_free; zcrypt_rng_device_count = 1; - } else + } else { zcrypt_rng_device_count++; + } mutex_unlock(&zcrypt_rng_mutex); return 0; out_free: - free_page((unsigned long) zcrypt_rng_buffer); + free_page((unsigned long)zcrypt_rng_buffer); out: mutex_unlock(&zcrypt_rng_mutex); return rc; @@ -2087,7 +2088,7 @@ void zcrypt_rng_device_remove(void) zcrypt_rng_device_count--; if (zcrypt_rng_device_count == 0) { hwrng_unregister(&zcrypt_rng_dev); - free_page((unsigned long) zcrypt_rng_buffer); + free_page((unsigned long)zcrypt_rng_buffer); } mutex_unlock(&zcrypt_rng_mutex); } diff --git a/drivers/s390/crypto/zcrypt_api.h b/drivers/s390/crypto/zcrypt_api.h index 93e77e83ad14..f299deb8b8c7 100644 --- a/drivers/s390/crypto/zcrypt_api.h +++ b/drivers/s390/crypto/zcrypt_api.h @@ -170,7 +170,7 @@ static inline unsigned long z_copy_from_user(bool userspace, { if (likely(userspace)) return copy_from_user(to, from, n); - memcpy(to, (void __force *) from, n); + memcpy(to, (void __force *)from, n); return 0; } @@ -181,7 +181,7 @@ static inline unsigned long z_copy_to_user(bool userspace, { if (likely(userspace)) return copy_to_user(to, from, n); - memcpy((void __force *) to, from, n); + memcpy((void __force *)to, from, n); return 0; } diff --git a/drivers/s390/crypto/zcrypt_card.c b/drivers/s390/crypto/zcrypt_card.c index fcbd537530e8..6ca675042416 100644 --- a/drivers/s390/crypto/zcrypt_card.c +++ b/drivers/s390/crypto/zcrypt_card.c @@ -138,7 +138,7 @@ struct zcrypt_card *zcrypt_card_alloc(void) { struct zcrypt_card *zc; - zc = kzalloc(sizeof(struct zcrypt_card), GFP_KERNEL); + zc = kzalloc(sizeof(*zc), GFP_KERNEL); if (!zc) return NULL; INIT_LIST_HEAD(&zc->list); diff --git a/drivers/s390/crypto/zcrypt_cca_key.h b/drivers/s390/crypto/zcrypt_cca_key.h index f09bb850763b..6229ba9c56d9 100644 --- a/drivers/s390/crypto/zcrypt_cca_key.h +++ b/drivers/s390/crypto/zcrypt_cca_key.h @@ -11,7 +11,7 @@ #ifndef _ZCRYPT_CCA_KEY_H_ #define _ZCRYPT_CCA_KEY_H_ -struct T6_keyBlock_hdr { +struct t6_keyblock_hdr { unsigned short blen; unsigned short ulen; unsigned short flags; @@ -63,7 +63,7 @@ struct cca_public_sec { * complement of the residue modulo 8 of the sum of * (p_len + q_len + dp_len + dq_len + u_len). */ -struct cca_pvt_ext_CRT_sec { +struct cca_pvt_ext_crt_sec { unsigned char section_identifier; unsigned char version; unsigned short section_length; @@ -108,9 +108,9 @@ static inline int zcrypt_type6_mex_key_en(struct ica_rsa_modexpo *mex, void *p) .section_identifier = 0x04, }; struct { - struct T6_keyBlock_hdr t6_hdr; - struct cca_token_hdr pubHdr; - struct cca_public_sec pubSec; + struct t6_keyblock_hdr t6_hdr; + struct cca_token_hdr pubhdr; + struct cca_public_sec pubsec; char exponent[0]; } __packed *key = p; unsigned char *temp; @@ -127,8 +127,8 @@ static inline int zcrypt_type6_mex_key_en(struct ica_rsa_modexpo *mex, void *p) memset(key, 0, sizeof(*key)); - key->pubHdr = static_pub_hdr; - key->pubSec = static_pub_sec; + key->pubhdr = static_pub_hdr; + key->pubsec = static_pub_sec; /* key parameter block */ temp = key->exponent; @@ -146,16 +146,16 @@ static inline int zcrypt_type6_mex_key_en(struct ica_rsa_modexpo *mex, void *p) if (copy_from_user(temp, mex->n_modulus, mex->inputdatalength)) return -EFAULT; - key->pubSec.modulus_bit_len = 8 * mex->inputdatalength; - key->pubSec.modulus_byte_len = mex->inputdatalength; - key->pubSec.exponent_len = mex->inputdatalength - i; - key->pubSec.section_length = sizeof(key->pubSec) + - 2*mex->inputdatalength - i; - key->pubHdr.token_length = - key->pubSec.section_length + sizeof(key->pubHdr); - key->t6_hdr.ulen = key->pubHdr.token_length + 4; - key->t6_hdr.blen = key->pubHdr.token_length + 6; - return sizeof(*key) + 2*mex->inputdatalength - i; + key->pubsec.modulus_bit_len = 8 * mex->inputdatalength; + key->pubsec.modulus_byte_len = mex->inputdatalength; + key->pubsec.exponent_len = mex->inputdatalength - i; + key->pubsec.section_length = sizeof(key->pubsec) + + 2 * mex->inputdatalength - i; + key->pubhdr.token_length = + key->pubsec.section_length + sizeof(key->pubhdr); + key->t6_hdr.ulen = key->pubhdr.token_length + 4; + key->t6_hdr.blen = key->pubhdr.token_length + 6; + return sizeof(*key) + 2 * mex->inputdatalength - i; } /** @@ -177,9 +177,9 @@ static inline int zcrypt_type6_crt_key(struct ica_rsa_modexpo_crt *crt, void *p) }; static char pk_exponent[3] = { 0x01, 0x00, 0x01 }; struct { - struct T6_keyBlock_hdr t6_hdr; + struct t6_keyblock_hdr t6_hdr; struct cca_token_hdr token; - struct cca_pvt_ext_CRT_sec pvt; + struct cca_pvt_ext_crt_sec pvt; char key_parts[0]; } __packed *key = p; struct cca_public_sec *pub; @@ -198,8 +198,8 @@ static inline int zcrypt_type6_crt_key(struct ica_rsa_modexpo_crt *crt, void *p) short_len = (crt->inputdatalength + 1) / 2; long_len = short_len + 8; - pad_len = -(3*long_len + 2*short_len) & 7; - key_len = 3*long_len + 2*short_len + pad_len + crt->inputdatalength; + pad_len = -(3 * long_len + 2 * short_len) & 7; + key_len = 3 * long_len + 2 * short_len + pad_len + crt->inputdatalength; size = sizeof(*key) + key_len + sizeof(*pub) + 3; /* parameter block.key block */ @@ -223,15 +223,15 @@ static inline int zcrypt_type6_crt_key(struct ica_rsa_modexpo_crt *crt, void *p) /* key parts */ if (copy_from_user(key->key_parts, crt->np_prime, long_len) || copy_from_user(key->key_parts + long_len, - crt->nq_prime, short_len) || + crt->nq_prime, short_len) || copy_from_user(key->key_parts + long_len + short_len, - crt->bp_key, long_len) || - copy_from_user(key->key_parts + 2*long_len + short_len, - crt->bq_key, short_len) || - copy_from_user(key->key_parts + 2*long_len + 2*short_len, - crt->u_mult_inv, long_len)) + crt->bp_key, long_len) || + copy_from_user(key->key_parts + 2 * long_len + short_len, + crt->bq_key, short_len) || + copy_from_user(key->key_parts + 2 * long_len + 2 * short_len, + crt->u_mult_inv, long_len)) return -EFAULT; - memset(key->key_parts + 3*long_len + 2*short_len + pad_len, + memset(key->key_parts + 3 * long_len + 2 * short_len + pad_len, 0xff, crt->inputdatalength); pub = (struct cca_public_sec *)(key->key_parts + key_len); *pub = static_cca_pub_sec; @@ -241,7 +241,7 @@ static inline int zcrypt_type6_crt_key(struct ica_rsa_modexpo_crt *crt, void *p) * section. So, an arbitrary public exponent of 0x010001 will be * used. */ - memcpy((char *) (pub + 1), pk_exponent, 3); + memcpy((char *)(pub + 1), pk_exponent, 3); return size; } diff --git a/drivers/s390/crypto/zcrypt_ccamisc.c b/drivers/s390/crypto/zcrypt_ccamisc.c index 6a3c2b460965..60ba20a133be 100644 --- a/drivers/s390/crypto/zcrypt_ccamisc.c +++ b/drivers/s390/crypto/zcrypt_ccamisc.c @@ -53,26 +53,26 @@ static DEFINE_SPINLOCK(cca_info_list_lock); int cca_check_secaeskeytoken(debug_info_t *dbg, int dbflvl, const u8 *token, int keybitsize) { - struct secaeskeytoken *t = (struct secaeskeytoken *) token; + struct secaeskeytoken *t = (struct secaeskeytoken *)token; #define DBF(...) debug_sprintf_event(dbg, dbflvl, ##__VA_ARGS__) if (t->type != TOKTYPE_CCA_INTERNAL) { if (dbg) DBF("%s token check failed, type 0x%02x != 0x%02x\n", - __func__, (int) t->type, TOKTYPE_CCA_INTERNAL); + __func__, (int)t->type, TOKTYPE_CCA_INTERNAL); return -EINVAL; } if (t->version != TOKVER_CCA_AES) { if (dbg) DBF("%s token check failed, version 0x%02x != 0x%02x\n", - __func__, (int) t->version, TOKVER_CCA_AES); + __func__, (int)t->version, TOKVER_CCA_AES); return -EINVAL; } if (keybitsize > 0 && t->bitsize != keybitsize) { if (dbg) DBF("%s token check failed, bitsize %d != %d\n", - __func__, (int) t->bitsize, keybitsize); + __func__, (int)t->bitsize, keybitsize); return -EINVAL; } @@ -93,7 +93,7 @@ int cca_check_secaescipherkey(debug_info_t *dbg, int dbflvl, const u8 *token, int keybitsize, int checkcpacfexport) { - struct cipherkeytoken *t = (struct cipherkeytoken *) token; + struct cipherkeytoken *t = (struct cipherkeytoken *)token; bool keybitsizeok = true; #define DBF(...) debug_sprintf_event(dbg, dbflvl, ##__VA_ARGS__) @@ -101,37 +101,37 @@ int cca_check_secaescipherkey(debug_info_t *dbg, int dbflvl, if (t->type != TOKTYPE_CCA_INTERNAL) { if (dbg) DBF("%s token check failed, type 0x%02x != 0x%02x\n", - __func__, (int) t->type, TOKTYPE_CCA_INTERNAL); + __func__, (int)t->type, TOKTYPE_CCA_INTERNAL); return -EINVAL; } if (t->version != TOKVER_CCA_VLSC) { if (dbg) DBF("%s token check failed, version 0x%02x != 0x%02x\n", - __func__, (int) t->version, TOKVER_CCA_VLSC); + __func__, (int)t->version, TOKVER_CCA_VLSC); return -EINVAL; } if (t->algtype != 0x02) { if (dbg) DBF("%s token check failed, algtype 0x%02x != 0x02\n", - __func__, (int) t->algtype); + __func__, (int)t->algtype); return -EINVAL; } if (t->keytype != 0x0001) { if (dbg) DBF("%s token check failed, keytype 0x%04x != 0x0001\n", - __func__, (int) t->keytype); + __func__, (int)t->keytype); return -EINVAL; } if (t->plfver != 0x00 && t->plfver != 0x01) { if (dbg) DBF("%s token check failed, unknown plfver 0x%02x\n", - __func__, (int) t->plfver); + __func__, (int)t->plfver); return -EINVAL; } if (t->wpllen != 512 && t->wpllen != 576 && t->wpllen != 640) { if (dbg) DBF("%s token check failed, unknown wpllen %d\n", - __func__, (int) t->wpllen); + __func__, (int)t->wpllen); return -EINVAL; } if (keybitsize > 0) { @@ -180,26 +180,26 @@ int cca_check_sececckeytoken(debug_info_t *dbg, int dbflvl, const u8 *token, size_t keysize, int checkcpacfexport) { - struct eccprivkeytoken *t = (struct eccprivkeytoken *) token; + struct eccprivkeytoken *t = (struct eccprivkeytoken *)token; #define DBF(...) debug_sprintf_event(dbg, dbflvl, ##__VA_ARGS__) if (t->type != TOKTYPE_CCA_INTERNAL_PKA) { if (dbg) DBF("%s token check failed, type 0x%02x != 0x%02x\n", - __func__, (int) t->type, TOKTYPE_CCA_INTERNAL_PKA); + __func__, (int)t->type, TOKTYPE_CCA_INTERNAL_PKA); return -EINVAL; } if (t->len > keysize) { if (dbg) DBF("%s token check failed, len %d > keysize %zu\n", - __func__, (int) t->len, keysize); + __func__, (int)t->len, keysize); return -EINVAL; } if (t->secid != 0x20) { if (dbg) DBF("%s token check failed, secid 0x%02x != 0x20\n", - __func__, (int) t->secid); + __func__, (int)t->secid); return -EINVAL; } if (checkcpacfexport && !(t->kutc & 0x01)) { @@ -222,9 +222,9 @@ EXPORT_SYMBOL(cca_check_sececckeytoken); * on failure. */ static int alloc_and_prep_cprbmem(size_t paramblen, - u8 **pcprbmem, - struct CPRBX **preqCPRB, - struct CPRBX **prepCPRB) + u8 **p_cprb_mem, + struct CPRBX **p_req_cprb, + struct CPRBX **p_rep_cprb) { u8 *cprbmem; size_t cprbplusparamblen = sizeof(struct CPRBX) + paramblen; @@ -238,8 +238,8 @@ static int alloc_and_prep_cprbmem(size_t paramblen, if (!cprbmem) return -ENOMEM; - preqcblk = (struct CPRBX *) cprbmem; - prepcblk = (struct CPRBX *) (cprbmem + cprbplusparamblen); + preqcblk = (struct CPRBX *)cprbmem; + prepcblk = (struct CPRBX *)(cprbmem + cprbplusparamblen); /* fill request cprb struct */ preqcblk->cprb_len = sizeof(struct CPRBX); @@ -248,14 +248,14 @@ static int alloc_and_prep_cprbmem(size_t paramblen, preqcblk->rpl_msgbl = cprbplusparamblen; if (paramblen) { preqcblk->req_parmb = - ((u8 __user *) preqcblk) + sizeof(struct CPRBX); + ((u8 __user *)preqcblk) + sizeof(struct CPRBX); preqcblk->rpl_parmb = - ((u8 __user *) prepcblk) + sizeof(struct CPRBX); + ((u8 __user *)prepcblk) + sizeof(struct CPRBX); } - *pcprbmem = cprbmem; - *preqCPRB = preqcblk; - *prepCPRB = prepcblk; + *p_cprb_mem = cprbmem; + *p_req_cprb = preqcblk; + *p_rep_cprb = prepcblk; return 0; } @@ -286,9 +286,9 @@ static inline void prep_xcrb(struct ica_xcRB *pxcrb, pxcrb->user_defined = (cardnr == 0xFFFF ? AUTOSELECT : cardnr); pxcrb->request_control_blk_length = preqcblk->cprb_len + preqcblk->req_parml; - pxcrb->request_control_blk_addr = (void __user *) preqcblk; + pxcrb->request_control_blk_addr = (void __user *)preqcblk; pxcrb->reply_control_blk_length = preqcblk->rpl_msgbl; - pxcrb->reply_control_blk_addr = (void __user *) prepcblk; + pxcrb->reply_control_blk_addr = (void __user *)prepcblk; } /* @@ -345,7 +345,7 @@ int cca_genseckey(u16 cardnr, u16 domain, preqcblk->domain = domain; /* fill request cprb param block with KG request */ - preqparm = (struct kgreqparm __force *) preqcblk->req_parmb; + preqparm = (struct kgreqparm __force *)preqcblk->req_parmb; memcpy(preqparm->subfunc_code, "KG", 2); preqparm->rule_array_len = sizeof(preqparm->rule_array_len); preqparm->lv1.len = sizeof(struct lv1); @@ -387,7 +387,7 @@ int cca_genseckey(u16 cardnr, u16 domain, rc = zcrypt_send_cprb(&xcrb); if (rc) { DEBUG_ERR("%s zcrypt_send_cprb (cardnr=%d domain=%d) failed, errno %d\n", - __func__, (int) cardnr, (int) domain, rc); + __func__, (int)cardnr, (int)domain, rc); goto out; } @@ -395,16 +395,16 @@ int cca_genseckey(u16 cardnr, u16 domain, if (prepcblk->ccp_rtcode != 0) { DEBUG_ERR("%s secure key generate failure, card response %d/%d\n", __func__, - (int) prepcblk->ccp_rtcode, - (int) prepcblk->ccp_rscode); + (int)prepcblk->ccp_rtcode, + (int)prepcblk->ccp_rscode); rc = -EIO; goto out; } /* process response cprb param block */ - ptr = ((u8 *) prepcblk) + sizeof(struct CPRBX); - prepcblk->rpl_parmb = (u8 __user *) ptr; - prepparm = (struct kgrepparm *) ptr; + ptr = ((u8 *)prepcblk) + sizeof(struct CPRBX); + prepcblk->rpl_parmb = (u8 __user *)ptr; + prepparm = (struct kgrepparm *)ptr; /* check length of the returned secure key token */ seckeysize = prepparm->lv3.keyblock.toklen @@ -419,7 +419,7 @@ int cca_genseckey(u16 cardnr, u16 domain, /* check secure key token */ rc = cca_check_secaeskeytoken(zcrypt_dbf_info, DBF_ERR, - prepparm->lv3.keyblock.tok, 8*keysize); + prepparm->lv3.keyblock.tok, 8 * keysize); if (rc) { rc = -EIO; goto out; @@ -486,7 +486,7 @@ int cca_clr2seckey(u16 cardnr, u16 domain, u32 keybitsize, preqcblk->domain = domain; /* fill request cprb param block with CM request */ - preqparm = (struct cmreqparm __force *) preqcblk->req_parmb; + preqparm = (struct cmreqparm __force *)preqcblk->req_parmb; memcpy(preqparm->subfunc_code, "CM", 2); memcpy(preqparm->rule_array, "AES ", 8); preqparm->rule_array_len = @@ -512,7 +512,7 @@ int cca_clr2seckey(u16 cardnr, u16 domain, u32 keybitsize, } preqparm->lv1.len = sizeof(struct lv1) + keysize; memcpy(preqparm->lv1.clrkey, clrkey, keysize); - plv2 = (struct lv2 *) (((u8 *) &preqparm->lv2) + keysize); + plv2 = (struct lv2 *)(((u8 *)&preqparm->lv2) + keysize); plv2->len = sizeof(struct lv2); plv2->keyid.len = sizeof(struct keyid); plv2->keyid.attr = 0x30; @@ -525,7 +525,7 @@ int cca_clr2seckey(u16 cardnr, u16 domain, u32 keybitsize, rc = zcrypt_send_cprb(&xcrb); if (rc) { DEBUG_ERR("%s zcrypt_send_cprb (cardnr=%d domain=%d) failed, rc=%d\n", - __func__, (int) cardnr, (int) domain, rc); + __func__, (int)cardnr, (int)domain, rc); goto out; } @@ -533,16 +533,16 @@ int cca_clr2seckey(u16 cardnr, u16 domain, u32 keybitsize, if (prepcblk->ccp_rtcode != 0) { DEBUG_ERR("%s clear key import failure, card response %d/%d\n", __func__, - (int) prepcblk->ccp_rtcode, - (int) prepcblk->ccp_rscode); + (int)prepcblk->ccp_rtcode, + (int)prepcblk->ccp_rscode); rc = -EIO; goto out; } /* process response cprb param block */ - ptr = ((u8 *) prepcblk) + sizeof(struct CPRBX); - prepcblk->rpl_parmb = (u8 __user *) ptr; - prepparm = (struct cmrepparm *) ptr; + ptr = ((u8 *)prepcblk) + sizeof(struct CPRBX); + prepcblk->rpl_parmb = (u8 __user *)ptr; + prepparm = (struct cmrepparm *)ptr; /* check length of the returned secure key token */ seckeysize = prepparm->lv3.keyblock.toklen @@ -557,7 +557,7 @@ int cca_clr2seckey(u16 cardnr, u16 domain, u32 keybitsize, /* check secure key token */ rc = cca_check_secaeskeytoken(zcrypt_dbf_info, DBF_ERR, - prepparm->lv3.keyblock.tok, 8*keysize); + prepparm->lv3.keyblock.tok, 8 * keysize); if (rc) { rc = -EIO; goto out; @@ -632,7 +632,7 @@ int cca_sec2protkey(u16 cardnr, u16 domain, preqcblk->domain = domain; /* fill request cprb param block with USK request */ - preqparm = (struct uskreqparm __force *) preqcblk->req_parmb; + preqparm = (struct uskreqparm __force *)preqcblk->req_parmb; memcpy(preqparm->subfunc_code, "US", 2); preqparm->rule_array_len = sizeof(preqparm->rule_array_len); preqparm->lv1.len = sizeof(struct lv1); @@ -652,7 +652,7 @@ int cca_sec2protkey(u16 cardnr, u16 domain, rc = zcrypt_send_cprb(&xcrb); if (rc) { DEBUG_ERR("%s zcrypt_send_cprb (cardnr=%d domain=%d) failed, rc=%d\n", - __func__, (int) cardnr, (int) domain, rc); + __func__, (int)cardnr, (int)domain, rc); goto out; } @@ -660,8 +660,8 @@ int cca_sec2protkey(u16 cardnr, u16 domain, if (prepcblk->ccp_rtcode != 0) { DEBUG_ERR("%s unwrap secure key failure, card response %d/%d\n", __func__, - (int) prepcblk->ccp_rtcode, - (int) prepcblk->ccp_rscode); + (int)prepcblk->ccp_rtcode, + (int)prepcblk->ccp_rscode); if (prepcblk->ccp_rtcode == 8 && prepcblk->ccp_rscode == 2290) rc = -EAGAIN; else @@ -671,37 +671,37 @@ int cca_sec2protkey(u16 cardnr, u16 domain, if (prepcblk->ccp_rscode != 0) { DEBUG_WARN("%s unwrap secure key warning, card response %d/%d\n", __func__, - (int) prepcblk->ccp_rtcode, - (int) prepcblk->ccp_rscode); + (int)prepcblk->ccp_rtcode, + (int)prepcblk->ccp_rscode); } /* process response cprb param block */ - ptr = ((u8 *) prepcblk) + sizeof(struct CPRBX); - prepcblk->rpl_parmb = (u8 __user *) ptr; - prepparm = (struct uskrepparm *) ptr; + ptr = ((u8 *)prepcblk) + sizeof(struct CPRBX); + prepcblk->rpl_parmb = (u8 __user *)ptr; + prepparm = (struct uskrepparm *)ptr; /* check the returned keyblock */ if (prepparm->lv3.ckb.version != 0x01 && prepparm->lv3.ckb.version != 0x02) { DEBUG_ERR("%s reply param keyblock version mismatch 0x%02x\n", - __func__, (int) prepparm->lv3.ckb.version); + __func__, (int)prepparm->lv3.ckb.version); rc = -EIO; goto out; } /* copy the tanslated protected key */ switch (prepparm->lv3.ckb.len) { - case 16+32: + case 16 + 32: /* AES 128 protected key */ if (protkeytype) *protkeytype = PKEY_KEYTYPE_AES_128; break; - case 24+32: + case 24 + 32: /* AES 192 protected key */ if (protkeytype) *protkeytype = PKEY_KEYTYPE_AES_192; break; - case 32+32: + case 32 + 32: /* AES 256 protected key */ if (protkeytype) *protkeytype = PKEY_KEYTYPE_AES_256; @@ -751,7 +751,7 @@ int cca_gencipherkey(u16 cardnr, u16 domain, u32 keybitsize, u32 keygenflags, struct gkreqparm { u8 subfunc_code[2]; u16 rule_array_len; - char rule_array[2*8]; + char rule_array[2 * 8]; struct { u16 len; u8 key_type_1[8]; @@ -827,10 +827,10 @@ int cca_gencipherkey(u16 cardnr, u16 domain, u32 keybitsize, u32 keygenflags, preqcblk->req_parml = sizeof(struct gkreqparm); /* prepare request param block with GK request */ - preqparm = (struct gkreqparm __force *) preqcblk->req_parmb; + preqparm = (struct gkreqparm __force *)preqcblk->req_parmb; memcpy(preqparm->subfunc_code, "GK", 2); preqparm->rule_array_len = sizeof(uint16_t) + 2 * 8; - memcpy(preqparm->rule_array, "AES OP ", 2*8); + memcpy(preqparm->rule_array, "AES OP ", 2 * 8); /* prepare vud block */ preqparm->vud.len = sizeof(preqparm->vud); @@ -869,9 +869,9 @@ int cca_gencipherkey(u16 cardnr, u16 domain, u32 keybitsize, u32 keygenflags, /* patch the skeleton key token export flags inside the kb block */ if (keygenflags) { - t = (struct cipherkeytoken *) preqparm->kb.tlv3.gen_key_id_1; - t->kmf1 |= (u16) (keygenflags & 0x0000FF00); - t->kmf1 &= (u16) ~(keygenflags & 0x000000FF); + t = (struct cipherkeytoken *)preqparm->kb.tlv3.gen_key_id_1; + t->kmf1 |= (u16)(keygenflags & 0x0000FF00); + t->kmf1 &= (u16)~(keygenflags & 0x000000FF); } /* prepare xcrb struct */ @@ -882,7 +882,7 @@ int cca_gencipherkey(u16 cardnr, u16 domain, u32 keybitsize, u32 keygenflags, if (rc) { DEBUG_ERR( "%s zcrypt_send_cprb (cardnr=%d domain=%d) failed, rc=%d\n", - __func__, (int) cardnr, (int) domain, rc); + __func__, (int)cardnr, (int)domain, rc); goto out; } @@ -891,16 +891,16 @@ int cca_gencipherkey(u16 cardnr, u16 domain, u32 keybitsize, u32 keygenflags, DEBUG_ERR( "%s cipher key generate failure, card response %d/%d\n", __func__, - (int) prepcblk->ccp_rtcode, - (int) prepcblk->ccp_rscode); + (int)prepcblk->ccp_rtcode, + (int)prepcblk->ccp_rscode); rc = -EIO; goto out; } /* process response cprb param block */ - ptr = ((u8 *) prepcblk) + sizeof(struct CPRBX); - prepcblk->rpl_parmb = (u8 __user *) ptr; - prepparm = (struct gkrepparm *) ptr; + ptr = ((u8 *)prepcblk) + sizeof(struct CPRBX); + prepcblk->rpl_parmb = (u8 __user *)ptr; + prepparm = (struct gkrepparm *)ptr; /* do some plausibility checks on the key block */ if (prepparm->kb.len < 120 + 5 * sizeof(uint16_t) || @@ -921,7 +921,7 @@ int cca_gencipherkey(u16 cardnr, u16 domain, u32 keybitsize, u32 keygenflags, } /* copy the generated vlsc key token */ - t = (struct cipherkeytoken *) prepparm->kb.tlv1.gen_key; + t = (struct cipherkeytoken *)prepparm->kb.tlv1.gen_key; if (keybuf) { if (*keybufsize >= t->len) memcpy(keybuf, t, t->len); @@ -1006,7 +1006,7 @@ static int _ip_cprb_helper(u16 cardnr, u16 domain, preqcblk->req_parml = 0; /* prepare request param block with IP request */ - preq_ra_block = (struct rule_array_block __force *) preqcblk->req_parmb; + preq_ra_block = (struct rule_array_block __force *)preqcblk->req_parmb; memcpy(preq_ra_block->subfunc_code, "IP", 2); preq_ra_block->rule_array_len = sizeof(uint16_t) + 2 * 8; memcpy(preq_ra_block->rule_array, rule_array_1, 8); @@ -1050,7 +1050,7 @@ static int _ip_cprb_helper(u16 cardnr, u16 domain, if (rc) { DEBUG_ERR( "%s zcrypt_send_cprb (cardnr=%d domain=%d) failed, rc=%d\n", - __func__, (int) cardnr, (int) domain, rc); + __func__, (int)cardnr, (int)domain, rc); goto out; } @@ -1059,16 +1059,16 @@ static int _ip_cprb_helper(u16 cardnr, u16 domain, DEBUG_ERR( "%s CSNBKPI2 failure, card response %d/%d\n", __func__, - (int) prepcblk->ccp_rtcode, - (int) prepcblk->ccp_rscode); + (int)prepcblk->ccp_rtcode, + (int)prepcblk->ccp_rscode); rc = -EIO; goto out; } /* process response cprb param block */ - ptr = ((u8 *) prepcblk) + sizeof(struct CPRBX); - prepcblk->rpl_parmb = (u8 __user *) ptr; - prepparm = (struct iprepparm *) ptr; + ptr = ((u8 *)prepcblk) + sizeof(struct CPRBX); + prepcblk->rpl_parmb = (u8 __user *)ptr; + prepparm = (struct iprepparm *)ptr; /* do some plausibility checks on the key block */ if (prepparm->kb.len < 120 + 3 * sizeof(uint16_t) || @@ -1082,7 +1082,7 @@ static int _ip_cprb_helper(u16 cardnr, u16 domain, /* do not check the key here, it may be incomplete */ /* copy the vlsc key token back */ - t = (struct cipherkeytoken *) prepparm->kb.tlv1.key_token; + t = (struct cipherkeytoken *)prepparm->kb.tlv1.key_token; memcpy(key_token, t, t->len); *key_token_size = t->len; @@ -1117,9 +1117,9 @@ int cca_clr2cipherkey(u16 card, u16 dom, u32 keybitsize, u32 keygenflags, /* patch the skeleton key token export flags */ if (keygenflags) { - t = (struct cipherkeytoken *) token; - t->kmf1 |= (u16) (keygenflags & 0x0000FF00); - t->kmf1 &= (u16) ~(keygenflags & 0x000000FF); + t = (struct cipherkeytoken *)token; + t->kmf1 |= (u16)(keygenflags & 0x0000FF00); + t->kmf1 &= (u16)~(keygenflags & 0x000000FF); } /* @@ -1241,7 +1241,7 @@ int cca_cipher2protkey(u16 cardnr, u16 domain, const u8 *ckey, preqcblk->domain = domain; /* fill request cprb param block with AU request */ - preqparm = (struct aureqparm __force *) preqcblk->req_parmb; + preqparm = (struct aureqparm __force *)preqcblk->req_parmb; memcpy(preqparm->subfunc_code, "AU", 2); preqparm->rule_array_len = sizeof(preqparm->rule_array_len) @@ -1267,7 +1267,7 @@ int cca_cipher2protkey(u16 cardnr, u16 domain, const u8 *ckey, if (rc) { DEBUG_ERR( "%s zcrypt_send_cprb (cardnr=%d domain=%d) failed, rc=%d\n", - __func__, (int) cardnr, (int) domain, rc); + __func__, (int)cardnr, (int)domain, rc); goto out; } @@ -1276,8 +1276,8 @@ int cca_cipher2protkey(u16 cardnr, u16 domain, const u8 *ckey, DEBUG_ERR( "%s unwrap secure key failure, card response %d/%d\n", __func__, - (int) prepcblk->ccp_rtcode, - (int) prepcblk->ccp_rscode); + (int)prepcblk->ccp_rtcode, + (int)prepcblk->ccp_rscode); if (prepcblk->ccp_rtcode == 8 && prepcblk->ccp_rscode == 2290) rc = -EAGAIN; else @@ -1288,44 +1288,44 @@ int cca_cipher2protkey(u16 cardnr, u16 domain, const u8 *ckey, DEBUG_WARN( "%s unwrap secure key warning, card response %d/%d\n", __func__, - (int) prepcblk->ccp_rtcode, - (int) prepcblk->ccp_rscode); + (int)prepcblk->ccp_rtcode, + (int)prepcblk->ccp_rscode); } /* process response cprb param block */ - ptr = ((u8 *) prepcblk) + sizeof(struct CPRBX); - prepcblk->rpl_parmb = (u8 __user *) ptr; - prepparm = (struct aurepparm *) ptr; + ptr = ((u8 *)prepcblk) + sizeof(struct CPRBX); + prepcblk->rpl_parmb = (u8 __user *)ptr; + prepparm = (struct aurepparm *)ptr; /* check the returned keyblock */ if (prepparm->vud.ckb.version != 0x01 && prepparm->vud.ckb.version != 0x02) { DEBUG_ERR("%s reply param keyblock version mismatch 0x%02x\n", - __func__, (int) prepparm->vud.ckb.version); + __func__, (int)prepparm->vud.ckb.version); rc = -EIO; goto out; } if (prepparm->vud.ckb.algo != 0x02) { DEBUG_ERR( "%s reply param keyblock algo mismatch 0x%02x != 0x02\n", - __func__, (int) prepparm->vud.ckb.algo); + __func__, (int)prepparm->vud.ckb.algo); rc = -EIO; goto out; } /* copy the translated protected key */ switch (prepparm->vud.ckb.keylen) { - case 16+32: + case 16 + 32: /* AES 128 protected key */ if (protkeytype) *protkeytype = PKEY_KEYTYPE_AES_128; break; - case 24+32: + case 24 + 32: /* AES 192 protected key */ if (protkeytype) *protkeytype = PKEY_KEYTYPE_AES_192; break; - case 32+32: + case 32 + 32: /* AES 256 protected key */ if (protkeytype) *protkeytype = PKEY_KEYTYPE_AES_256; @@ -1410,7 +1410,7 @@ int cca_ecc2protkey(u16 cardnr, u16 domain, const u8 *key, preqcblk->domain = domain; /* fill request cprb param block with AU request */ - preqparm = (struct aureqparm __force *) preqcblk->req_parmb; + preqparm = (struct aureqparm __force *)preqcblk->req_parmb; memcpy(preqparm->subfunc_code, "AU", 2); preqparm->rule_array_len = sizeof(preqparm->rule_array_len) @@ -1436,7 +1436,7 @@ int cca_ecc2protkey(u16 cardnr, u16 domain, const u8 *key, if (rc) { DEBUG_ERR( "%s zcrypt_send_cprb (cardnr=%d domain=%d) failed, rc=%d\n", - __func__, (int) cardnr, (int) domain, rc); + __func__, (int)cardnr, (int)domain, rc); goto out; } @@ -1445,8 +1445,8 @@ int cca_ecc2protkey(u16 cardnr, u16 domain, const u8 *key, DEBUG_ERR( "%s unwrap secure key failure, card response %d/%d\n", __func__, - (int) prepcblk->ccp_rtcode, - (int) prepcblk->ccp_rscode); + (int)prepcblk->ccp_rtcode, + (int)prepcblk->ccp_rscode); if (prepcblk->ccp_rtcode == 8 && prepcblk->ccp_rscode == 2290) rc = -EAGAIN; else @@ -1457,26 +1457,26 @@ int cca_ecc2protkey(u16 cardnr, u16 domain, const u8 *key, DEBUG_WARN( "%s unwrap secure key warning, card response %d/%d\n", __func__, - (int) prepcblk->ccp_rtcode, - (int) prepcblk->ccp_rscode); + (int)prepcblk->ccp_rtcode, + (int)prepcblk->ccp_rscode); } /* process response cprb param block */ - ptr = ((u8 *) prepcblk) + sizeof(struct CPRBX); - prepcblk->rpl_parmb = (u8 __user *) ptr; - prepparm = (struct aurepparm *) ptr; + ptr = ((u8 *)prepcblk) + sizeof(struct CPRBX); + prepcblk->rpl_parmb = (u8 __user *)ptr; + prepparm = (struct aurepparm *)ptr; /* check the returned keyblock */ if (prepparm->vud.ckb.version != 0x02) { DEBUG_ERR("%s reply param keyblock version mismatch 0x%02x != 0x02\n", - __func__, (int) prepparm->vud.ckb.version); + __func__, (int)prepparm->vud.ckb.version); rc = -EIO; goto out; } if (prepparm->vud.ckb.algo != 0x81) { DEBUG_ERR( "%s reply param keyblock algo mismatch 0x%02x != 0x81\n", - __func__, (int) prepparm->vud.ckb.algo); + __func__, (int)prepparm->vud.ckb.algo); rc = -EIO; goto out; } @@ -1537,7 +1537,7 @@ int cca_query_crypto_facility(u16 cardnr, u16 domain, preqcblk->domain = domain; /* fill request cprb param block with FQ request */ - preqparm = (struct fqreqparm __force *) preqcblk->req_parmb; + preqparm = (struct fqreqparm __force *)preqcblk->req_parmb; memcpy(preqparm->subfunc_code, "FQ", 2); memcpy(preqparm->rule_array, keyword, sizeof(preqparm->rule_array)); preqparm->rule_array_len = @@ -1553,7 +1553,7 @@ int cca_query_crypto_facility(u16 cardnr, u16 domain, rc = zcrypt_send_cprb(&xcrb); if (rc) { DEBUG_ERR("%s zcrypt_send_cprb (cardnr=%d domain=%d) failed, rc=%d\n", - __func__, (int) cardnr, (int) domain, rc); + __func__, (int)cardnr, (int)domain, rc); goto out; } @@ -1561,20 +1561,20 @@ int cca_query_crypto_facility(u16 cardnr, u16 domain, if (prepcblk->ccp_rtcode != 0) { DEBUG_ERR("%s unwrap secure key failure, card response %d/%d\n", __func__, - (int) prepcblk->ccp_rtcode, - (int) prepcblk->ccp_rscode); + (int)prepcblk->ccp_rtcode, + (int)prepcblk->ccp_rscode); rc = -EIO; goto out; } /* process response cprb param block */ - ptr = ((u8 *) prepcblk) + sizeof(struct CPRBX); - prepcblk->rpl_parmb = (u8 __user *) ptr; - prepparm = (struct fqrepparm *) ptr; + ptr = ((u8 *)prepcblk) + sizeof(struct CPRBX); + prepcblk->rpl_parmb = (u8 __user *)ptr; + prepparm = (struct fqrepparm *)ptr; ptr = prepparm->lvdata; /* check and possibly copy reply rule array */ - len = *((u16 *) ptr); + len = *((u16 *)ptr); if (len > sizeof(u16)) { ptr += sizeof(u16); len -= sizeof(u16); @@ -1585,7 +1585,7 @@ int cca_query_crypto_facility(u16 cardnr, u16 domain, ptr += len; } /* check and possible copy reply var array */ - len = *((u16 *) ptr); + len = *((u16 *)ptr); if (len > sizeof(u16)) { ptr += sizeof(u16); len -= sizeof(u16); @@ -1696,21 +1696,30 @@ static int fetch_cca_info(u16 cardnr, u16 domain, struct cca_info *ci) ci->hwtype = devstat.hwtype; /* prep page for rule array and var array use */ - pg = (u8 *) __get_free_page(GFP_KERNEL); + pg = (u8 *)__get_free_page(GFP_KERNEL); if (!pg) return -ENOMEM; rarray = pg; - varray = pg + PAGE_SIZE/2; - rlen = vlen = PAGE_SIZE/2; + varray = pg + PAGE_SIZE / 2; + rlen = vlen = PAGE_SIZE / 2; /* QF for this card/domain */ rc = cca_query_crypto_facility(cardnr, domain, "STATICSA", rarray, &rlen, varray, &vlen); - if (rc == 0 && rlen >= 10*8 && vlen >= 204) { + if (rc == 0 && rlen >= 10 * 8 && vlen >= 204) { memcpy(ci->serial, rarray, 8); - ci->new_aes_mk_state = (char) rarray[7*8]; - ci->cur_aes_mk_state = (char) rarray[8*8]; - ci->old_aes_mk_state = (char) rarray[9*8]; + ci->new_asym_mk_state = (char)rarray[4 * 8]; + ci->cur_asym_mk_state = (char)rarray[5 * 8]; + ci->old_asym_mk_state = (char)rarray[6 * 8]; + if (ci->old_asym_mk_state == '2') + memcpy(ci->old_asym_mkvp, varray + 64, 16); + if (ci->cur_asym_mk_state == '2') + memcpy(ci->cur_asym_mkvp, varray + 84, 16); + if (ci->new_asym_mk_state == '3') + memcpy(ci->new_asym_mkvp, varray + 104, 16); + ci->new_aes_mk_state = (char)rarray[7 * 8]; + ci->cur_aes_mk_state = (char)rarray[8 * 8]; + ci->old_aes_mk_state = (char)rarray[9 * 8]; if (ci->old_aes_mk_state == '2') memcpy(&ci->old_aes_mkvp, varray + 172, 8); if (ci->cur_aes_mk_state == '2') @@ -1721,13 +1730,13 @@ static int fetch_cca_info(u16 cardnr, u16 domain, struct cca_info *ci) } if (!found) goto out; - rlen = vlen = PAGE_SIZE/2; + rlen = vlen = PAGE_SIZE / 2; rc = cca_query_crypto_facility(cardnr, domain, "STATICSB", rarray, &rlen, varray, &vlen); - if (rc == 0 && rlen >= 13*8 && vlen >= 240) { - ci->new_apka_mk_state = (char) rarray[10*8]; - ci->cur_apka_mk_state = (char) rarray[11*8]; - ci->old_apka_mk_state = (char) rarray[12*8]; + if (rc == 0 && rlen >= 13 * 8 && vlen >= 240) { + ci->new_apka_mk_state = (char)rarray[10 * 8]; + ci->cur_apka_mk_state = (char)rarray[11 * 8]; + ci->old_apka_mk_state = (char)rarray[12 * 8]; if (ci->old_apka_mk_state == '2') memcpy(&ci->old_apka_mkvp, varray + 208, 8); if (ci->cur_apka_mk_state == '2') @@ -1738,7 +1747,7 @@ static int fetch_cca_info(u16 cardnr, u16 domain, struct cca_info *ci) } out: - free_page((unsigned long) pg); + free_page((unsigned long)pg); return found == 2 ? 0 : -ENOENT; } @@ -1846,8 +1855,9 @@ static int findcard(u64 mkvp, u16 *pcardnr, u16 *pdomain, if (pdomain) *pdomain = dom; rc = (i < MAX_ZDEV_ENTRIES_EXT ? 0 : 1); - } else + } else { rc = -ENODEV; + } kvfree(device_status); return rc; @@ -1861,7 +1871,7 @@ int cca_findcard(const u8 *key, u16 *pcardnr, u16 *pdomain, int verify) { u64 mkvp; int minhwtype = 0; - const struct keytoken_header *hdr = (struct keytoken_header *) key; + const struct keytoken_header *hdr = (struct keytoken_header *)key; if (hdr->type != TOKTYPE_CCA_INTERNAL) return -EINVAL; @@ -1954,7 +1964,7 @@ int cca_findcard2(u32 **apqns, u32 *nr_apqns, u16 cardnr, u16 domain, } /* apqn passed all filtering criterons, add to the array */ if (_nr_apqns < 256) - _apqns[_nr_apqns++] = (((u16)card) << 16) | ((u16) dom); + _apqns[_nr_apqns++] = (((u16)card) << 16) | ((u16)dom); } /* nothing found ? */ diff --git a/drivers/s390/crypto/zcrypt_ccamisc.h b/drivers/s390/crypto/zcrypt_ccamisc.h index 3513cd8ab9bc..78bf5631848e 100644 --- a/drivers/s390/crypto/zcrypt_ccamisc.h +++ b/drivers/s390/crypto/zcrypt_ccamisc.h @@ -251,12 +251,18 @@ struct cca_info { char new_apka_mk_state; /* '1' empty, '2' partially full, '3' full */ char cur_apka_mk_state; /* '1' invalid, '2' valid */ char old_apka_mk_state; /* '1' invalid, '2' valid */ + char new_asym_mk_state; /* '1' empty, '2' partially full, '3' full */ + char cur_asym_mk_state; /* '1' invalid, '2' valid */ + char old_asym_mk_state; /* '1' invalid, '2' valid */ u64 new_aes_mkvp; /* truncated sha256 of new aes master key */ u64 cur_aes_mkvp; /* truncated sha256 of current aes master key */ u64 old_aes_mkvp; /* truncated sha256 of old aes master key */ u64 new_apka_mkvp; /* truncated sha256 of new apka master key */ u64 cur_apka_mkvp; /* truncated sha256 of current apka mk */ u64 old_apka_mkvp; /* truncated sha256 of old apka mk */ + u8 new_asym_mkvp[16]; /* verify pattern of new asym master key */ + u8 cur_asym_mkvp[16]; /* verify pattern of current asym master key */ + u8 old_asym_mkvp[16]; /* verify pattern of old asym master key */ char serial[9]; /* serial number (8 ascii numbers + 0x00) */ }; diff --git a/drivers/s390/crypto/zcrypt_cex2a.c b/drivers/s390/crypto/zcrypt_cex2a.c index 2bd49950ba81..83f692c9c197 100644 --- a/drivers/s390/crypto/zcrypt_cex2a.c +++ b/drivers/s390/crypto/zcrypt_cex2a.c @@ -34,10 +34,11 @@ #define CEX3A_MAX_RESPONSE_SIZE 0x210 /* 512 bit modulus * (max outputdatalength) + - * type80_hdr*/ + * type80_hdr + */ #define CEX3A_MAX_MESSAGE_SIZE sizeof(struct type50_crb3_msg) -#define CEX2A_CLEANUP_TIME (15*HZ) +#define CEX2A_CLEANUP_TIME (15 * HZ) #define CEX3A_CLEANUP_TIME CEX2A_CLEANUP_TIME MODULE_AUTHOR("IBM Corporation"); @@ -117,9 +118,8 @@ static int zcrypt_cex2a_card_probe(struct ap_device *ap_dev) zc->online = 1; rc = zcrypt_card_register(zc); - if (rc) { + if (rc) zcrypt_card_free(zc); - } return rc; } @@ -176,9 +176,8 @@ static int zcrypt_cex2a_queue_probe(struct ap_device *ap_dev) aq->request_timeout = CEX2A_CLEANUP_TIME; dev_set_drvdata(&ap_dev->device, zq); rc = zcrypt_queue_register(zq); - if (rc) { + if (rc) zcrypt_queue_free(zq); - } return rc; } diff --git a/drivers/s390/crypto/zcrypt_cex2c.c b/drivers/s390/crypto/zcrypt_cex2c.c index 6360fdd06160..cb7849defce3 100644 --- a/drivers/s390/crypto/zcrypt_cex2c.c +++ b/drivers/s390/crypto/zcrypt_cex2c.c @@ -31,8 +31,8 @@ #define CEX2C_MAX_MOD_SIZE 256 /* 2048 bits */ #define CEX3C_MIN_MOD_SIZE 16 /* 128 bits */ #define CEX3C_MAX_MOD_SIZE 512 /* 4096 bits */ -#define CEX2C_MAX_XCRB_MESSAGE_SIZE (12*1024) -#define CEX2C_CLEANUP_TIME (15*HZ) +#define CEX2C_MAX_XCRB_MESSAGE_SIZE (12 * 1024) +#define CEX2C_CLEANUP_TIME (15 * HZ) MODULE_AUTHOR("IBM Corporation"); MODULE_DESCRIPTION("CEX2C/CEX3C Cryptographic Coprocessor device driver, " \ @@ -200,11 +200,11 @@ static int zcrypt_cex2c_rng_supported(struct ap_queue *aq) int rc, i; ap_init_message(&ap_msg); - ap_msg.msg = (void *) get_zeroed_page(GFP_KERNEL); + ap_msg.msg = (void *)get_zeroed_page(GFP_KERNEL); if (!ap_msg.msg) return -ENOMEM; - rng_type6CPRB_msgX(&ap_msg, 4, &domain); + rng_type6cprb_msgx(&ap_msg, 4, &domain); msg = ap_msg.msg; msg->cprbx.domain = AP_QID_QUEUE(aq->qid); @@ -233,7 +233,7 @@ static int zcrypt_cex2c_rng_supported(struct ap_queue *aq) else rc = 0; out_free: - free_page((unsigned long) ap_msg.msg); + free_page((unsigned long)ap_msg.msg); return rc; } diff --git a/drivers/s390/crypto/zcrypt_cex4.c b/drivers/s390/crypto/zcrypt_cex4.c index fe5664c7589e..b03916b7538b 100644 --- a/drivers/s390/crypto/zcrypt_cex4.c +++ b/drivers/s390/crypto/zcrypt_cex4.c @@ -33,7 +33,7 @@ * But the maximum time limit managed by the stomper code is set to 60sec. * Hence we have to wait at least that time period. */ -#define CEX4_CLEANUP_TIME (900*HZ) +#define CEX4_CLEANUP_TIME (900 * HZ) MODULE_AUTHOR("IBM Corporation"); MODULE_DESCRIPTION("CEX[45678] Cryptographic Card device driver, " \ @@ -123,11 +123,12 @@ static ssize_t cca_mkvps_show(struct device *dev, &ci, zq->online); if (ci.new_aes_mk_state >= '1' && ci.new_aes_mk_state <= '3') - n = scnprintf(buf, PAGE_SIZE, "AES NEW: %s 0x%016llx\n", - new_state[ci.new_aes_mk_state - '1'], - ci.new_aes_mkvp); + n += scnprintf(buf + n, PAGE_SIZE, + "AES NEW: %s 0x%016llx\n", + new_state[ci.new_aes_mk_state - '1'], + ci.new_aes_mkvp); else - n = scnprintf(buf, PAGE_SIZE, "AES NEW: - -\n"); + n += scnprintf(buf + n, PAGE_SIZE, "AES NEW: - -\n"); if (ci.cur_aes_mk_state >= '1' && ci.cur_aes_mk_state <= '2') n += scnprintf(buf + n, PAGE_SIZE - n, @@ -169,6 +170,33 @@ static ssize_t cca_mkvps_show(struct device *dev, else n += scnprintf(buf + n, PAGE_SIZE - n, "APKA OLD: - -\n"); + if (ci.new_asym_mk_state >= '1' && ci.new_asym_mk_state <= '3') + n += scnprintf(buf + n, PAGE_SIZE, + "ASYM NEW: %s 0x%016llx%016llx\n", + new_state[ci.new_asym_mk_state - '1'], + *((u64 *)(ci.new_asym_mkvp)), + *((u64 *)(ci.new_asym_mkvp + sizeof(u64)))); + else + n += scnprintf(buf + n, PAGE_SIZE, "ASYM NEW: - -\n"); + + if (ci.cur_asym_mk_state >= '1' && ci.cur_asym_mk_state <= '2') + n += scnprintf(buf + n, PAGE_SIZE - n, + "ASYM CUR: %s 0x%016llx%016llx\n", + cao_state[ci.cur_asym_mk_state - '1'], + *((u64 *)(ci.cur_asym_mkvp)), + *((u64 *)(ci.cur_asym_mkvp + sizeof(u64)))); + else + n += scnprintf(buf + n, PAGE_SIZE - n, "ASYM CUR: - -\n"); + + if (ci.old_asym_mk_state >= '1' && ci.old_asym_mk_state <= '2') + n += scnprintf(buf + n, PAGE_SIZE - n, + "ASYM OLD: %s 0x%016llx%016llx\n", + cao_state[ci.old_asym_mk_state - '1'], + *((u64 *)(ci.old_asym_mkvp)), + *((u64 *)(ci.old_asym_mkvp + sizeof(u64)))); + else + n += scnprintf(buf + n, PAGE_SIZE - n, "ASYM OLD: - -\n"); + return n; } @@ -336,8 +364,9 @@ static ssize_t ep11_mkvps_show(struct device *dev, bin2hex(buf + n, di.cur_wkvp, sizeof(di.cur_wkvp)); n += 2 * sizeof(di.cur_wkvp); n += scnprintf(buf + n, PAGE_SIZE - n, "\n"); - } else + } else { n = scnprintf(buf, PAGE_SIZE, "WK CUR: - -\n"); + } if (di.new_wk_state == '0') { n += scnprintf(buf + n, PAGE_SIZE - n, "WK NEW: %s -\n", @@ -348,8 +377,9 @@ static ssize_t ep11_mkvps_show(struct device *dev, bin2hex(buf + n, di.new_wkvp, sizeof(di.new_wkvp)); n += 2 * sizeof(di.new_wkvp); n += scnprintf(buf + n, PAGE_SIZE - n, "\n"); - } else + } else { n += scnprintf(buf + n, PAGE_SIZE - n, "WK NEW: - -\n"); + } return n; } diff --git a/drivers/s390/crypto/zcrypt_ep11misc.c b/drivers/s390/crypto/zcrypt_ep11misc.c index 98d33f932b0b..b1c29017be5b 100644 --- a/drivers/s390/crypto/zcrypt_ep11misc.c +++ b/drivers/s390/crypto/zcrypt_ep11misc.c @@ -119,8 +119,8 @@ static void __exit card_cache_free(void) int ep11_check_aes_key_with_hdr(debug_info_t *dbg, int dbflvl, const u8 *key, size_t keylen, int checkcpacfexp) { - struct ep11kblob_header *hdr = (struct ep11kblob_header *) key; - struct ep11keyblob *kb = (struct ep11keyblob *) (key + sizeof(*hdr)); + struct ep11kblob_header *hdr = (struct ep11kblob_header *)key; + struct ep11keyblob *kb = (struct ep11keyblob *)(key + sizeof(*hdr)); #define DBF(...) debug_sprintf_event(dbg, dbflvl, ##__VA_ARGS__) @@ -133,38 +133,38 @@ int ep11_check_aes_key_with_hdr(debug_info_t *dbg, int dbflvl, if (hdr->type != TOKTYPE_NON_CCA) { if (dbg) DBF("%s key check failed, type 0x%02x != 0x%02x\n", - __func__, (int) hdr->type, TOKTYPE_NON_CCA); + __func__, (int)hdr->type, TOKTYPE_NON_CCA); return -EINVAL; } if (hdr->hver != 0x00) { if (dbg) DBF("%s key check failed, header version 0x%02x != 0x00\n", - __func__, (int) hdr->hver); + __func__, (int)hdr->hver); return -EINVAL; } if (hdr->version != TOKVER_EP11_AES_WITH_HEADER) { if (dbg) DBF("%s key check failed, version 0x%02x != 0x%02x\n", - __func__, (int) hdr->version, TOKVER_EP11_AES_WITH_HEADER); + __func__, (int)hdr->version, TOKVER_EP11_AES_WITH_HEADER); return -EINVAL; } if (hdr->len > keylen) { if (dbg) DBF("%s key check failed, header len %d keylen %zu mismatch\n", - __func__, (int) hdr->len, keylen); + __func__, (int)hdr->len, keylen); return -EINVAL; } if (hdr->len < sizeof(*hdr) + sizeof(*kb)) { if (dbg) DBF("%s key check failed, header len %d < %zu\n", - __func__, (int) hdr->len, sizeof(*hdr) + sizeof(*kb)); + __func__, (int)hdr->len, sizeof(*hdr) + sizeof(*kb)); return -EINVAL; } if (kb->version != EP11_STRUCT_MAGIC) { if (dbg) DBF("%s key check failed, blob magic 0x%04x != 0x%04x\n", - __func__, (int) kb->version, EP11_STRUCT_MAGIC); + __func__, (int)kb->version, EP11_STRUCT_MAGIC); return -EINVAL; } if (checkcpacfexp && !(kb->attr & EP11_BLOB_PKEY_EXTRACTABLE)) { @@ -186,8 +186,8 @@ EXPORT_SYMBOL(ep11_check_aes_key_with_hdr); int ep11_check_ecc_key_with_hdr(debug_info_t *dbg, int dbflvl, const u8 *key, size_t keylen, int checkcpacfexp) { - struct ep11kblob_header *hdr = (struct ep11kblob_header *) key; - struct ep11keyblob *kb = (struct ep11keyblob *) (key + sizeof(*hdr)); + struct ep11kblob_header *hdr = (struct ep11kblob_header *)key; + struct ep11keyblob *kb = (struct ep11keyblob *)(key + sizeof(*hdr)); #define DBF(...) debug_sprintf_event(dbg, dbflvl, ##__VA_ARGS__) @@ -200,38 +200,38 @@ int ep11_check_ecc_key_with_hdr(debug_info_t *dbg, int dbflvl, if (hdr->type != TOKTYPE_NON_CCA) { if (dbg) DBF("%s key check failed, type 0x%02x != 0x%02x\n", - __func__, (int) hdr->type, TOKTYPE_NON_CCA); + __func__, (int)hdr->type, TOKTYPE_NON_CCA); return -EINVAL; } if (hdr->hver != 0x00) { if (dbg) DBF("%s key check failed, header version 0x%02x != 0x00\n", - __func__, (int) hdr->hver); + __func__, (int)hdr->hver); return -EINVAL; } if (hdr->version != TOKVER_EP11_ECC_WITH_HEADER) { if (dbg) DBF("%s key check failed, version 0x%02x != 0x%02x\n", - __func__, (int) hdr->version, TOKVER_EP11_ECC_WITH_HEADER); + __func__, (int)hdr->version, TOKVER_EP11_ECC_WITH_HEADER); return -EINVAL; } if (hdr->len > keylen) { if (dbg) DBF("%s key check failed, header len %d keylen %zu mismatch\n", - __func__, (int) hdr->len, keylen); + __func__, (int)hdr->len, keylen); return -EINVAL; } if (hdr->len < sizeof(*hdr) + sizeof(*kb)) { if (dbg) DBF("%s key check failed, header len %d < %zu\n", - __func__, (int) hdr->len, sizeof(*hdr) + sizeof(*kb)); + __func__, (int)hdr->len, sizeof(*hdr) + sizeof(*kb)); return -EINVAL; } if (kb->version != EP11_STRUCT_MAGIC) { if (dbg) DBF("%s key check failed, blob magic 0x%04x != 0x%04x\n", - __func__, (int) kb->version, EP11_STRUCT_MAGIC); + __func__, (int)kb->version, EP11_STRUCT_MAGIC); return -EINVAL; } if (checkcpacfexp && !(kb->attr & EP11_BLOB_PKEY_EXTRACTABLE)) { @@ -254,7 +254,7 @@ EXPORT_SYMBOL(ep11_check_ecc_key_with_hdr); int ep11_check_aes_key(debug_info_t *dbg, int dbflvl, const u8 *key, size_t keylen, int checkcpacfexp) { - struct ep11keyblob *kb = (struct ep11keyblob *) key; + struct ep11keyblob *kb = (struct ep11keyblob *)key; #define DBF(...) debug_sprintf_event(dbg, dbflvl, ##__VA_ARGS__) @@ -267,32 +267,32 @@ int ep11_check_aes_key(debug_info_t *dbg, int dbflvl, if (kb->head.type != TOKTYPE_NON_CCA) { if (dbg) DBF("%s key check failed, type 0x%02x != 0x%02x\n", - __func__, (int) kb->head.type, TOKTYPE_NON_CCA); + __func__, (int)kb->head.type, TOKTYPE_NON_CCA); return -EINVAL; } if (kb->head.version != TOKVER_EP11_AES) { if (dbg) DBF("%s key check failed, version 0x%02x != 0x%02x\n", - __func__, (int) kb->head.version, TOKVER_EP11_AES); + __func__, (int)kb->head.version, TOKVER_EP11_AES); return -EINVAL; } if (kb->head.len > keylen) { if (dbg) DBF("%s key check failed, header len %d keylen %zu mismatch\n", - __func__, (int) kb->head.len, keylen); + __func__, (int)kb->head.len, keylen); return -EINVAL; } if (kb->head.len < sizeof(*kb)) { if (dbg) DBF("%s key check failed, header len %d < %zu\n", - __func__, (int) kb->head.len, sizeof(*kb)); + __func__, (int)kb->head.len, sizeof(*kb)); return -EINVAL; } if (kb->version != EP11_STRUCT_MAGIC) { if (dbg) DBF("%s key check failed, blob magic 0x%04x != 0x%04x\n", - __func__, (int) kb->version, EP11_STRUCT_MAGIC); + __func__, (int)kb->version, EP11_STRUCT_MAGIC); return -EINVAL; } if (checkcpacfexp && !(kb->attr & EP11_BLOB_PKEY_EXTRACTABLE)) { @@ -347,11 +347,11 @@ static int asn1tag_write(u8 *ptr, u8 tag, const u8 *pvalue, u16 valuelen) } if (valuelen > 127) { ptr[1] = 0x81; - ptr[2] = (u8) valuelen; + ptr[2] = (u8)valuelen; memcpy(ptr + 3, pvalue, valuelen); return 3 + valuelen; } - ptr[1] = (u8) valuelen; + ptr[1] = (u8)valuelen; memcpy(ptr + 2, pvalue, valuelen); return 2 + valuelen; } @@ -389,11 +389,11 @@ static inline void prep_urb(struct ep11_urb *u, struct ep11_cprb *req, size_t req_len, struct ep11_cprb *rep, size_t rep_len) { - u->targets = (u8 __user *) t; + u->targets = (u8 __user *)t; u->targets_num = nt; - u->req = (u8 __user *) req; + u->req = (u8 __user *)req; u->req_len = req_len; - u->resp = (u8 __user *) rep; + u->resp = (u8 __user *)rep; u->resp_len = rep_len; } @@ -462,7 +462,6 @@ static int check_reply_pl(const u8 *pl, const char *func) return 0; } - /* * Helper function which does an ep11 query with given query type. */ @@ -496,7 +495,7 @@ static int ep11_query_info(u16 cardnr, u16 domain, u32 query_type, req = alloc_cprb(sizeof(struct ep11_info_req_pl)); if (!req) goto out; - req_pl = (struct ep11_info_req_pl *) (((u8 *) req) + sizeof(*req)); + req_pl = (struct ep11_info_req_pl *)(((u8 *)req) + sizeof(*req)); prep_head(&req_pl->head, sizeof(*req_pl), api, 38); /* get xcp info */ req_pl->query_type_tag = 0x04; req_pl->query_type_len = sizeof(u32); @@ -508,10 +507,10 @@ static int ep11_query_info(u16 cardnr, u16 domain, u32 query_type, rep = alloc_cprb(sizeof(struct ep11_info_rep_pl) + buflen); if (!rep) goto out; - rep_pl = (struct ep11_info_rep_pl *) (((u8 *) rep) + sizeof(*rep)); + rep_pl = (struct ep11_info_rep_pl *)(((u8 *)rep) + sizeof(*rep)); /* urb and target */ - urb = kmalloc(sizeof(struct ep11_urb), GFP_KERNEL); + urb = kmalloc(sizeof(*urb), GFP_KERNEL); if (!urb) goto out; target.ap_id = cardnr; @@ -524,7 +523,7 @@ static int ep11_query_info(u16 cardnr, u16 domain, u32 query_type, if (rc) { DEBUG_ERR( "%s zcrypt_send_ep11_cprb(card=%d dom=%d) failed, rc=%d\n", - __func__, (int) cardnr, (int) domain, rc); + __func__, (int)cardnr, (int)domain, rc); goto out; } @@ -543,7 +542,7 @@ static int ep11_query_info(u16 cardnr, u16 domain, u32 query_type, goto out; } - memcpy(buf, ((u8 *) rep_pl) + sizeof(*rep_pl), rep_pl->data_len); + memcpy(buf, ((u8 *)rep_pl) + sizeof(*rep_pl), rep_pl->data_len); out: kfree(req); @@ -592,7 +591,7 @@ int ep11_get_card_info(u16 card, struct ep11_card_info *info, int verify) return -ENOMEM; rc = ep11_query_info(card, AUTOSEL_DOM, 0x01 /* module info query */, - sizeof(*pmqi), (u8 *) pmqi); + sizeof(*pmqi), (u8 *)pmqi); if (rc) { if (rc == -ENODEV) card_cache_scrub(card); @@ -632,7 +631,7 @@ int ep11_get_domain_info(u16 card, u16 domain, struct ep11_domain_info *info) return -ENOMEM; rc = ep11_query_info(card, domain, 0x03 /* domain info query */, - sizeof(*p_dom_info), (u8 *) p_dom_info); + sizeof(*p_dom_info), (u8 *)p_dom_info); if (rc) goto out; @@ -644,8 +643,8 @@ int ep11_get_domain_info(u16 card, u16 domain, struct ep11_domain_info *info) info->cur_wk_state = '1'; memcpy(info->cur_wkvp, p_dom_info->cur_WK_VP, 32); } - if (p_dom_info->dom_flags & 0x04 /* new wk present */ - || p_dom_info->dom_flags & 0x08 /* new wk committed */) { + if (p_dom_info->dom_flags & 0x04 || /* new wk present */ + p_dom_info->dom_flags & 0x08 /* new wk committed */) { info->new_wk_state = p_dom_info->dom_flags & 0x08 ? '2' : '1'; memcpy(info->new_wkvp, p_dom_info->new_WK_VP, 32); @@ -722,7 +721,7 @@ int ep11_genaeskey(u16 card, u16 domain, u32 keybitsize, u32 keygenflags, req = alloc_cprb(sizeof(struct keygen_req_pl)); if (!req) goto out; - req_pl = (struct keygen_req_pl *) (((u8 *) req) + sizeof(*req)); + req_pl = (struct keygen_req_pl *)(((u8 *)req) + sizeof(*req)); api = (!keygenflags || keygenflags & 0x00200000) ? 4 : 1; prep_head(&req_pl->head, sizeof(*req_pl), api, 21); /* GenerateKey */ req_pl->var_tag = 0x04; @@ -746,10 +745,10 @@ int ep11_genaeskey(u16 card, u16 domain, u32 keybitsize, u32 keygenflags, rep = alloc_cprb(sizeof(struct keygen_rep_pl)); if (!rep) goto out; - rep_pl = (struct keygen_rep_pl *) (((u8 *) rep) + sizeof(*rep)); + rep_pl = (struct keygen_rep_pl *)(((u8 *)rep) + sizeof(*rep)); /* urb and target */ - urb = kmalloc(sizeof(struct ep11_urb), GFP_KERNEL); + urb = kmalloc(sizeof(*urb), GFP_KERNEL); if (!urb) goto out; target.ap_id = card; @@ -762,7 +761,7 @@ int ep11_genaeskey(u16 card, u16 domain, u32 keybitsize, u32 keygenflags, if (rc) { DEBUG_ERR( "%s zcrypt_send_ep11_cprb(card=%d dom=%d) failed, rc=%d\n", - __func__, (int) card, (int) domain, rc); + __func__, (int)card, (int)domain, rc); goto out; } @@ -784,7 +783,7 @@ int ep11_genaeskey(u16 card, u16 domain, u32 keybitsize, u32 keygenflags, /* copy key blob and set header values */ memcpy(keybuf, rep_pl->data, rep_pl->data_len); *keybufsize = rep_pl->data_len; - kb = (struct ep11keyblob *) keybuf; + kb = (struct ep11keyblob *)keybuf; kb->head.type = TOKTYPE_NON_CCA; kb->head.len = rep_pl->data_len; kb->head.version = TOKVER_EP11_AES; @@ -844,7 +843,7 @@ static int ep11_cryptsingle(u16 card, u16 domain, req = alloc_cprb(req_pl_size); if (!req) goto out; - req_pl = (struct crypt_req_pl *) (((u8 *) req) + sizeof(*req)); + req_pl = (struct crypt_req_pl *)(((u8 *)req) + sizeof(*req)); prep_head(&req_pl->head, req_pl_size, api, (mode ? 20 : 19)); req_pl->var_tag = 0x04; req_pl->var_len = sizeof(u32); @@ -852,7 +851,7 @@ static int ep11_cryptsingle(u16 card, u16 domain, req_pl->mech_tag = 0x04; req_pl->mech_len = sizeof(u32) + (iv ? 16 : 0); req_pl->mech = (mech ? mech : 0x00001085); /* CKM_AES_CBC_PAD */ - p = ((u8 *) req_pl) + sizeof(*req_pl); + p = ((u8 *)req_pl) + sizeof(*req_pl); if (iv) { memcpy(p, iv, 16); p += 16; @@ -866,10 +865,10 @@ static int ep11_cryptsingle(u16 card, u16 domain, rep = alloc_cprb(rep_pl_size); if (!rep) goto out; - rep_pl = (struct crypt_rep_pl *) (((u8 *) rep) + sizeof(*rep)); + rep_pl = (struct crypt_rep_pl *)(((u8 *)rep) + sizeof(*rep)); /* urb and target */ - urb = kmalloc(sizeof(struct ep11_urb), GFP_KERNEL); + urb = kmalloc(sizeof(*urb), GFP_KERNEL); if (!urb) goto out; target.ap_id = card; @@ -882,7 +881,7 @@ static int ep11_cryptsingle(u16 card, u16 domain, if (rc) { DEBUG_ERR( "%s zcrypt_send_ep11_cprb(card=%d dom=%d) failed, rc=%d\n", - __func__, (int) card, (int) domain, rc); + __func__, (int)card, (int)domain, rc); goto out; } @@ -894,13 +893,13 @@ static int ep11_cryptsingle(u16 card, u16 domain, rc = -EIO; goto out; } - p = ((u8 *) rep_pl) + sizeof(*rep_pl); - if (rep_pl->data_lenfmt <= 127) + p = ((u8 *)rep_pl) + sizeof(*rep_pl); + if (rep_pl->data_lenfmt <= 127) { n = rep_pl->data_lenfmt; - else if (rep_pl->data_lenfmt == 0x81) + } else if (rep_pl->data_lenfmt == 0x81) { n = *p++; - else if (rep_pl->data_lenfmt == 0x82) { - n = *((u16 *) p); + } else if (rep_pl->data_lenfmt == 0x82) { + n = *((u16 *)p); p += 2; } else { DEBUG_ERR("%s unknown reply data length format 0x%02hhx\n", @@ -978,7 +977,7 @@ static int ep11_unwrapkey(u16 card, u16 domain, req = alloc_cprb(req_pl_size); if (!req) goto out; - req_pl = (struct uw_req_pl *) (((u8 *) req) + sizeof(*req)); + req_pl = (struct uw_req_pl *)(((u8 *)req) + sizeof(*req)); api = (!keygenflags || keygenflags & 0x00200000) ? 4 : 1; prep_head(&req_pl->head, req_pl_size, api, 34); /* UnwrapKey */ req_pl->attr_tag = 0x04; @@ -994,7 +993,7 @@ static int ep11_unwrapkey(u16 card, u16 domain, req_pl->mech_tag = 0x04; req_pl->mech_len = sizeof(u32) + (iv ? 16 : 0); req_pl->mech = (mech ? mech : 0x00001085); /* CKM_AES_CBC_PAD */ - p = ((u8 *) req_pl) + sizeof(*req_pl); + p = ((u8 *)req_pl) + sizeof(*req_pl); if (iv) { memcpy(p, iv, 16); p += 16; @@ -1014,10 +1013,10 @@ static int ep11_unwrapkey(u16 card, u16 domain, rep = alloc_cprb(sizeof(struct uw_rep_pl)); if (!rep) goto out; - rep_pl = (struct uw_rep_pl *) (((u8 *) rep) + sizeof(*rep)); + rep_pl = (struct uw_rep_pl *)(((u8 *)rep) + sizeof(*rep)); /* urb and target */ - urb = kmalloc(sizeof(struct ep11_urb), GFP_KERNEL); + urb = kmalloc(sizeof(*urb), GFP_KERNEL); if (!urb) goto out; target.ap_id = card; @@ -1030,7 +1029,7 @@ static int ep11_unwrapkey(u16 card, u16 domain, if (rc) { DEBUG_ERR( "%s zcrypt_send_ep11_cprb(card=%d dom=%d) failed, rc=%d\n", - __func__, (int) card, (int) domain, rc); + __func__, (int)card, (int)domain, rc); goto out; } @@ -1052,7 +1051,7 @@ static int ep11_unwrapkey(u16 card, u16 domain, /* copy key blob and set header values */ memcpy(keybuf, rep_pl->data, rep_pl->data_len); *keybufsize = rep_pl->data_len; - kb = (struct ep11keyblob *) keybuf; + kb = (struct ep11keyblob *)keybuf; kb->head.type = TOKTYPE_NON_CCA; kb->head.len = rep_pl->data_len; kb->head.version = TOKVER_EP11_AES; @@ -1105,7 +1104,7 @@ static int ep11_wrapkey(u16 card, u16 domain, u8 *p; /* maybe the session field holds a header with key info */ - kb = (struct ep11keyblob *) key; + kb = (struct ep11keyblob *)key; if (kb->head.type == TOKTYPE_NON_CCA && kb->head.version == TOKVER_EP11_AES) { has_header = true; @@ -1120,7 +1119,7 @@ static int ep11_wrapkey(u16 card, u16 domain, goto out; if (!mech || mech == 0x80060001) req->flags |= 0x20; /* CPACF_WRAP needs special bit */ - req_pl = (struct wk_req_pl *) (((u8 *) req) + sizeof(*req)); + req_pl = (struct wk_req_pl *)(((u8 *)req) + sizeof(*req)); api = (!mech || mech == 0x80060001) ? 4 : 1; /* CKM_IBM_CPACF_WRAP */ prep_head(&req_pl->head, req_pl_size, api, 33); /* WrapKey */ req_pl->var_tag = 0x04; @@ -1129,7 +1128,7 @@ static int ep11_wrapkey(u16 card, u16 domain, req_pl->mech_tag = 0x04; req_pl->mech_len = sizeof(u32) + (iv ? 16 : 0); req_pl->mech = (mech ? mech : 0x80060001); /* CKM_IBM_CPACF_WRAP */ - p = ((u8 *) req_pl) + sizeof(*req_pl); + p = ((u8 *)req_pl) + sizeof(*req_pl); if (iv) { memcpy(p, iv, 16); p += 16; @@ -1152,10 +1151,10 @@ static int ep11_wrapkey(u16 card, u16 domain, rep = alloc_cprb(sizeof(struct wk_rep_pl)); if (!rep) goto out; - rep_pl = (struct wk_rep_pl *) (((u8 *) rep) + sizeof(*rep)); + rep_pl = (struct wk_rep_pl *)(((u8 *)rep) + sizeof(*rep)); /* urb and target */ - urb = kmalloc(sizeof(struct ep11_urb), GFP_KERNEL); + urb = kmalloc(sizeof(*urb), GFP_KERNEL); if (!urb) goto out; target.ap_id = card; @@ -1168,7 +1167,7 @@ static int ep11_wrapkey(u16 card, u16 domain, if (rc) { DEBUG_ERR( "%s zcrypt_send_ep11_cprb(card=%d dom=%d) failed, rc=%d\n", - __func__, (int) card, (int) domain, rc); + __func__, (int)card, (int)domain, rc); goto out; } @@ -1206,9 +1205,9 @@ int ep11_clr2keyblob(u16 card, u16 domain, u32 keybitsize, u32 keygenflags, u8 encbuf[64], *kek = NULL; size_t clrkeylen, keklen, encbuflen = sizeof(encbuf); - if (keybitsize == 128 || keybitsize == 192 || keybitsize == 256) + if (keybitsize == 128 || keybitsize == 192 || keybitsize == 256) { clrkeylen = keybitsize / 8; - else { + } else { DEBUG_ERR( "%s unknown/unsupported keybitsize %d\n", __func__, keybitsize); @@ -1233,7 +1232,7 @@ int ep11_clr2keyblob(u16 card, u16 domain, u32 keybitsize, u32 keygenflags, __func__, rc); goto out; } - kb = (struct ep11keyblob *) kek; + kb = (struct ep11keyblob *)kek; memset(&kb->head, 0, sizeof(kb->head)); /* Step 2: encrypt clear key value with the kek key */ @@ -1282,17 +1281,17 @@ int ep11_kblob2protkey(u16 card, u16 dom, const u8 *keyblob, size_t keybloblen, struct ep11kblob_header *hdr; /* key with or without header ? */ - hdr = (struct ep11kblob_header *) keyblob; - if (hdr->type == TOKTYPE_NON_CCA - && (hdr->version == TOKVER_EP11_AES_WITH_HEADER - || hdr->version == TOKVER_EP11_ECC_WITH_HEADER) - && is_ep11_keyblob(keyblob + sizeof(struct ep11kblob_header))) { + hdr = (struct ep11kblob_header *)keyblob; + if (hdr->type == TOKTYPE_NON_CCA && + (hdr->version == TOKVER_EP11_AES_WITH_HEADER || + hdr->version == TOKVER_EP11_ECC_WITH_HEADER) && + is_ep11_keyblob(keyblob + sizeof(struct ep11kblob_header))) { /* EP11 AES or ECC key with header */ key = keyblob + sizeof(struct ep11kblob_header); keylen = hdr->len - sizeof(struct ep11kblob_header); - } else if (hdr->type == TOKTYPE_NON_CCA - && hdr->version == TOKVER_EP11_AES - && is_ep11_keyblob(keyblob)) { + } else if (hdr->type == TOKTYPE_NON_CCA && + hdr->version == TOKVER_EP11_AES && + is_ep11_keyblob(keyblob)) { /* EP11 AES key (old style) */ key = keyblob; keylen = hdr->len; @@ -1300,8 +1299,9 @@ int ep11_kblob2protkey(u16 card, u16 dom, const u8 *keyblob, size_t keybloblen, /* raw EP11 key blob */ key = keyblob; keylen = keybloblen; - } else + } else { return -EINVAL; + } /* alloc temp working buffer */ wkbuflen = (keylen + AES_BLOCK_SIZE) & (~(AES_BLOCK_SIZE - 1)); @@ -1318,12 +1318,12 @@ int ep11_kblob2protkey(u16 card, u16 dom, const u8 *keyblob, size_t keybloblen, __func__, rc); goto out; } - wki = (struct wk_info *) wkbuf; + wki = (struct wk_info *)wkbuf; /* check struct version and pkey type */ if (wki->version != 1 || wki->pkeytype < 1 || wki->pkeytype > 5) { DEBUG_ERR("%s wk info version %d or pkeytype %d mismatch.\n", - __func__, (int) wki->version, (int) wki->pkeytype); + __func__, (int)wki->version, (int)wki->pkeytype); rc = -EIO; goto out; } @@ -1332,24 +1332,24 @@ int ep11_kblob2protkey(u16 card, u16 dom, const u8 *keyblob, size_t keybloblen, switch (wki->pkeytype) { case 1: /* AES */ switch (wki->pkeysize) { - case 16+32: + case 16 + 32: /* AES 128 protected key */ if (protkeytype) *protkeytype = PKEY_KEYTYPE_AES_128; break; - case 24+32: + case 24 + 32: /* AES 192 protected key */ if (protkeytype) *protkeytype = PKEY_KEYTYPE_AES_192; break; - case 32+32: + case 32 + 32: /* AES 256 protected key */ if (protkeytype) *protkeytype = PKEY_KEYTYPE_AES_256; break; default: DEBUG_ERR("%s unknown/unsupported AES pkeysize %d\n", - __func__, (int) wki->pkeysize); + __func__, (int)wki->pkeysize); rc = -EIO; goto out; } @@ -1363,7 +1363,7 @@ int ep11_kblob2protkey(u16 card, u16 dom, const u8 *keyblob, size_t keybloblen, case 2: /* TDES */ default: DEBUG_ERR("%s unknown/unsupported key type %d\n", - __func__, (int) wki->pkeytype); + __func__, (int)wki->pkeytype); rc = -EIO; goto out; } @@ -1445,7 +1445,7 @@ int ep11_findcard2(u32 **apqns, u32 *nr_apqns, u16 cardnr, u16 domain, } /* apqn passed all filtering criterons, add to the array */ if (_nr_apqns < 256) - _apqns[_nr_apqns++] = (((u16)card) << 16) | ((u16) dom); + _apqns[_nr_apqns++] = (((u16)card) << 16) | ((u16)dom); } /* nothing found ? */ diff --git a/drivers/s390/crypto/zcrypt_ep11misc.h b/drivers/s390/crypto/zcrypt_ep11misc.h index 1e02b197c003..07445041869f 100644 --- a/drivers/s390/crypto/zcrypt_ep11misc.h +++ b/drivers/s390/crypto/zcrypt_ep11misc.h @@ -50,7 +50,7 @@ struct ep11keyblob { /* check ep11 key magic to find out if this is an ep11 key blob */ static inline bool is_ep11_keyblob(const u8 *key) { - struct ep11keyblob *kb = (struct ep11keyblob *) key; + struct ep11keyblob *kb = (struct ep11keyblob *)key; return (kb->version == EP11_STRUCT_MAGIC); } diff --git a/drivers/s390/crypto/zcrypt_error.h b/drivers/s390/crypto/zcrypt_error.h index 8b0ce600b749..d36177e65a3d 100644 --- a/drivers/s390/crypto/zcrypt_error.h +++ b/drivers/s390/crypto/zcrypt_error.h @@ -121,10 +121,11 @@ static inline int convert_error(struct zcrypt_queue *zq, ZCRYPT_DBF_WARN( "%s dev=%02x.%04x RY=0x%02x apfs=0x%x => bus rescan, rc=EAGAIN\n", __func__, card, queue, ehdr->reply_code, apfs); - } else + } else { ZCRYPT_DBF_WARN("%s dev=%02x.%04x RY=0x%02x => bus rescan, rc=EAGAIN\n", __func__, card, queue, ehdr->reply_code); + } return -EAGAIN; default: /* Assume request is valid and a retry will be worth it */ diff --git a/drivers/s390/crypto/zcrypt_msgtype50.c b/drivers/s390/crypto/zcrypt_msgtype50.c index 259145aa393f..7d245645fdd5 100644 --- a/drivers/s390/crypto/zcrypt_msgtype50.c +++ b/drivers/s390/crypto/zcrypt_msgtype50.c @@ -158,7 +158,6 @@ struct type80_hdr { int get_rsa_modex_fc(struct ica_rsa_modexpo *mex, int *fcode) { - if (!mex->inputdatalength) return -EINVAL; @@ -174,7 +173,6 @@ int get_rsa_modex_fc(struct ica_rsa_modexpo *mex, int *fcode) int get_rsa_crt_fc(struct ica_rsa_modexpo_crt *crt, int *fcode) { - if (!crt->inputdatalength) return -EINVAL; @@ -239,8 +237,9 @@ static int ICAMEX_msg_to_type50MEX_msg(struct zcrypt_queue *zq, mod = meb3->modulus + sizeof(meb3->modulus) - mod_len; exp = meb3->exponent + sizeof(meb3->exponent) - mod_len; inp = meb3->message + sizeof(meb3->message) - mod_len; - } else + } else { return -EINVAL; + } if (copy_from_user(mod, mex->n_modulus, mod_len) || copy_from_user(exp, mex->b_key, mod_len) || @@ -323,8 +322,9 @@ static int ICACRT_msg_to_type50CRT_msg(struct zcrypt_queue *zq, dq = crb3->dq + sizeof(crb3->dq) - short_len; u = crb3->u + sizeof(crb3->u) - short_len; inp = crb3->message + sizeof(crb3->message) - mod_len; - } else + } else { return -EINVAL; + } /* * correct the offset of p, bp and mult_inv according zcrypt.h @@ -392,7 +392,7 @@ static int convert_response_cex2a(struct zcrypt_queue *zq, unsigned int outputdatalength) { /* Response type byte is the second byte in the response. */ - unsigned char rtype = ((unsigned char *) reply->msg)[1]; + unsigned char rtype = ((unsigned char *)reply->msg)[1]; switch (rtype) { case TYPE82_RSP_CODE: @@ -406,11 +406,11 @@ static int convert_response_cex2a(struct zcrypt_queue *zq, pr_err("Crypto dev=%02x.%04x unknown response type 0x%02x => online=0 rc=EAGAIN\n", AP_QID_CARD(zq->queue->qid), AP_QID_QUEUE(zq->queue->qid), - (int) rtype); + (int)rtype); ZCRYPT_DBF_ERR( "%s dev=%02x.%04x unknown response type 0x%02x => online=0 rc=EAGAIN\n", __func__, AP_QID_CARD(zq->queue->qid), - AP_QID_QUEUE(zq->queue->qid), (int) rtype); + AP_QID_QUEUE(zq->queue->qid), (int)rtype); ap_send_online_uevent(&zq->queue->ap_dev, zq->online); return -EAGAIN; } @@ -447,10 +447,11 @@ static void zcrypt_cex2a_receive(struct ap_queue *aq, memcpy(msg->msg, reply->msg, len); msg->len = len; } - } else + } else { memcpy(msg->msg, reply->msg, sizeof(error_reply)); + } out: - complete((struct completion *) msg->private); + complete((struct completion *)msg->private); } static atomic_t zcrypt_step = ATOMIC_INIT(0); @@ -475,7 +476,7 @@ static long zcrypt_cex2a_modexpo(struct zcrypt_queue *zq, if (!ap_msg->msg) return -ENOMEM; ap_msg->receive = zcrypt_cex2a_receive; - ap_msg->psmid = (((unsigned long long) current->pid) << 32) + + ap_msg->psmid = (((unsigned long long)current->pid) << 32) + atomic_inc_return(&zcrypt_step); ap_msg->private = &work; rc = ICAMEX_msg_to_type50MEX_msg(zq, ap_msg, mex); @@ -492,9 +493,11 @@ static long zcrypt_cex2a_modexpo(struct zcrypt_queue *zq, rc = convert_response_cex2a(zq, ap_msg, mex->outputdata, mex->outputdatalength); - } else + } else { /* Signal pending. */ ap_cancel_message(zq->queue, ap_msg); + } + out: ap_msg->private = NULL; if (rc) @@ -524,7 +527,7 @@ static long zcrypt_cex2a_modexpo_crt(struct zcrypt_queue *zq, if (!ap_msg->msg) return -ENOMEM; ap_msg->receive = zcrypt_cex2a_receive; - ap_msg->psmid = (((unsigned long long) current->pid) << 32) + + ap_msg->psmid = (((unsigned long long)current->pid) << 32) + atomic_inc_return(&zcrypt_step); ap_msg->private = &work; rc = ICACRT_msg_to_type50CRT_msg(zq, ap_msg, crt); @@ -541,9 +544,11 @@ static long zcrypt_cex2a_modexpo_crt(struct zcrypt_queue *zq, rc = convert_response_cex2a(zq, ap_msg, crt->outputdata, crt->outputdatalength); - } else + } else { /* Signal pending. */ ap_cancel_message(zq->queue, ap_msg); + } + out: ap_msg->private = NULL; if (rc) diff --git a/drivers/s390/crypto/zcrypt_msgtype6.c b/drivers/s390/crypto/zcrypt_msgtype6.c index 57d885158cf0..8fb34b8eeb18 100644 --- a/drivers/s390/crypto/zcrypt_msgtype6.c +++ b/drivers/s390/crypto/zcrypt_msgtype6.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0+ /* - * Copyright IBM Corp. 2001, 2012 + * Copyright IBM Corp. 2001, 2022 * Author(s): Robert Burroughs * Eric Rossman (edrossma@us.ibm.com) * @@ -29,12 +29,13 @@ #define CEXXC_MAX_ICA_RESPONSE_SIZE 0x77c /* max size type86 v2 reply */ -#define CEIL4(x) ((((x)+3)/4)*4) +#define CEIL4(x) ((((x) + 3) / 4) * 4) struct response_type { struct completion work; int type; }; + #define CEXXC_RESPONSE_TYPE_ICA 0 #define CEXXC_RESPONSE_TYPE_XCRB 1 #define CEXXC_RESPONSE_TYPE_EP11 2 @@ -44,63 +45,6 @@ MODULE_DESCRIPTION("Cryptographic Coprocessor (message type 6), " \ "Copyright IBM Corp. 2001, 2012"); MODULE_LICENSE("GPL"); -/* - * CPRB - * Note that all shorts, ints and longs are little-endian. - * All pointer fields are 32-bits long, and mean nothing - * - * A request CPRB is followed by a request_parameter_block. - * - * The request (or reply) parameter block is organized thus: - * function code - * VUD block - * key block - */ -struct CPRB { - unsigned short cprb_len; /* CPRB length */ - unsigned char cprb_ver_id; /* CPRB version id. */ - unsigned char pad_000; /* Alignment pad byte. */ - unsigned char srpi_rtcode[4]; /* SRPI return code LELONG */ - unsigned char srpi_verb; /* SRPI verb type */ - unsigned char flags; /* flags */ - unsigned char func_id[2]; /* function id */ - unsigned char checkpoint_flag; /* */ - unsigned char resv2; /* reserved */ - unsigned short req_parml; /* request parameter buffer */ - /* length 16-bit little endian */ - unsigned char req_parmp[4]; /* request parameter buffer * - * pointer (means nothing: the * - * parameter buffer follows * - * the CPRB). */ - unsigned char req_datal[4]; /* request data buffer */ - /* length ULELONG */ - unsigned char req_datap[4]; /* request data buffer */ - /* pointer */ - unsigned short rpl_parml; /* reply parameter buffer */ - /* length 16-bit little endian */ - unsigned char pad_001[2]; /* Alignment pad bytes. ULESHORT */ - unsigned char rpl_parmp[4]; /* reply parameter buffer * - * pointer (means nothing: the * - * parameter buffer follows * - * the CPRB). */ - unsigned char rpl_datal[4]; /* reply data buffer len ULELONG */ - unsigned char rpl_datap[4]; /* reply data buffer */ - /* pointer */ - unsigned short ccp_rscode; /* server reason code ULESHORT */ - unsigned short ccp_rtcode; /* server return code ULESHORT */ - unsigned char repd_parml[2]; /* replied parameter len ULESHORT*/ - unsigned char mac_data_len[2]; /* Mac Data Length ULESHORT */ - unsigned char repd_datal[4]; /* replied data length ULELONG */ - unsigned char req_pc[2]; /* PC identifier */ - unsigned char res_origin[8]; /* resource origin */ - unsigned char mac_value[8]; /* Mac Value */ - unsigned char logon_id[8]; /* Logon Identifier */ - unsigned char usage_domain[2]; /* cdx */ - unsigned char resv3[18]; /* reserved for requestor */ - unsigned short svr_namel; /* server name length ULESHORT */ - unsigned char svr_name[8]; /* server name */ -} __packed; - struct function_and_rules_block { unsigned char function_code[2]; unsigned short ulen; @@ -235,7 +179,6 @@ int speed_idx_ep11(int req_type) } } - /* * Convert a ICAMEX message to a type6 MEX message. * @@ -245,7 +188,7 @@ int speed_idx_ep11(int req_type) * * Returns 0 on success or negative errno value. */ -static int ICAMEX_msg_to_type6MEX_msgX(struct zcrypt_queue *zq, +static int icamex_msg_to_type6mex_msgx(struct zcrypt_queue *zq, struct ap_message *ap_msg, struct ica_rsa_modexpo *mex) { @@ -283,19 +226,19 @@ static int ICAMEX_msg_to_type6MEX_msgX(struct zcrypt_queue *zq, return -EFAULT; /* Set up key which is located after the variable length text. */ - size = zcrypt_type6_mex_key_en(mex, msg->text+mex->inputdatalength); + size = zcrypt_type6_mex_key_en(mex, msg->text + mex->inputdatalength); if (size < 0) return size; size += sizeof(*msg) + mex->inputdatalength; /* message header, cprbx and f&r */ msg->hdr = static_type6_hdrX; - msg->hdr.ToCardLen1 = size - sizeof(msg->hdr); - msg->hdr.FromCardLen1 = CEXXC_MAX_ICA_RESPONSE_SIZE - sizeof(msg->hdr); + msg->hdr.tocardlen1 = size - sizeof(msg->hdr); + msg->hdr.fromcardlen1 = CEXXC_MAX_ICA_RESPONSE_SIZE - sizeof(msg->hdr); msg->cprbx = static_cprbx; msg->cprbx.domain = AP_QID_QUEUE(zq->queue->qid); - msg->cprbx.rpl_msgbl = msg->hdr.FromCardLen1; + msg->cprbx.rpl_msgbl = msg->hdr.fromcardlen1; msg->fr = static_pke_fnr; @@ -314,7 +257,7 @@ static int ICAMEX_msg_to_type6MEX_msgX(struct zcrypt_queue *zq, * * Returns 0 on success or negative errno value. */ -static int ICACRT_msg_to_type6CRT_msgX(struct zcrypt_queue *zq, +static int icacrt_msg_to_type6crt_msgx(struct zcrypt_queue *zq, struct ap_message *ap_msg, struct ica_rsa_modexpo_crt *crt) { @@ -360,8 +303,8 @@ static int ICACRT_msg_to_type6CRT_msgX(struct zcrypt_queue *zq, /* message header, cprbx and f&r */ msg->hdr = static_type6_hdrX; - msg->hdr.ToCardLen1 = size - sizeof(msg->hdr); - msg->hdr.FromCardLen1 = CEXXC_MAX_ICA_RESPONSE_SIZE - sizeof(msg->hdr); + msg->hdr.tocardlen1 = size - sizeof(msg->hdr); + msg->hdr.fromcardlen1 = CEXXC_MAX_ICA_RESPONSE_SIZE - sizeof(msg->hdr); msg->cprbx = static_cprbx; msg->cprbx.domain = AP_QID_QUEUE(zq->queue->qid); @@ -388,8 +331,8 @@ struct type86_fmt2_msg { struct type86_fmt2_ext fmt2; } __packed; -static int XCRB_msg_to_type6CPRB_msgX(bool userspace, struct ap_message *ap_msg, - struct ica_xcRB *xcRB, +static int xcrb_msg_to_type6cprb_msgx(bool userspace, struct ap_message *ap_msg, + struct ica_xcRB *xcrb, unsigned int *fcode, unsigned short **dom) { @@ -402,19 +345,19 @@ static int XCRB_msg_to_type6CPRB_msgX(bool userspace, struct ap_message *ap_msg, struct CPRBX cprbx; } __packed * msg = ap_msg->msg; - int rcblen = CEIL4(xcRB->request_control_blk_length); + int rcblen = CEIL4(xcrb->request_control_blk_length); int req_sumlen, resp_sumlen; char *req_data = ap_msg->msg + sizeof(struct type6_hdr) + rcblen; char *function_code; - if (CEIL4(xcRB->request_control_blk_length) < - xcRB->request_control_blk_length) + if (CEIL4(xcrb->request_control_blk_length) < + xcrb->request_control_blk_length) return -EINVAL; /* overflow after alignment*/ /* length checks */ ap_msg->len = sizeof(struct type6_hdr) + - CEIL4(xcRB->request_control_blk_length) + - xcRB->request_data_length; + CEIL4(xcrb->request_control_blk_length) + + xcrb->request_data_length; if (ap_msg->len > ap_msg->bufsize) return -EINVAL; @@ -422,48 +365,49 @@ static int XCRB_msg_to_type6CPRB_msgX(bool userspace, struct ap_message *ap_msg, * Overflow check * sum must be greater (or equal) than the largest operand */ - req_sumlen = CEIL4(xcRB->request_control_blk_length) + - xcRB->request_data_length; - if ((CEIL4(xcRB->request_control_blk_length) <= - xcRB->request_data_length) ? - (req_sumlen < xcRB->request_data_length) : - (req_sumlen < CEIL4(xcRB->request_control_blk_length))) { + req_sumlen = CEIL4(xcrb->request_control_blk_length) + + xcrb->request_data_length; + if ((CEIL4(xcrb->request_control_blk_length) <= + xcrb->request_data_length) ? + req_sumlen < xcrb->request_data_length : + req_sumlen < CEIL4(xcrb->request_control_blk_length)) { return -EINVAL; } - if (CEIL4(xcRB->reply_control_blk_length) < - xcRB->reply_control_blk_length) + if (CEIL4(xcrb->reply_control_blk_length) < + xcrb->reply_control_blk_length) return -EINVAL; /* overflow after alignment*/ /* * Overflow check * sum must be greater (or equal) than the largest operand */ - resp_sumlen = CEIL4(xcRB->reply_control_blk_length) + - xcRB->reply_data_length; - if ((CEIL4(xcRB->reply_control_blk_length) <= xcRB->reply_data_length) ? - (resp_sumlen < xcRB->reply_data_length) : - (resp_sumlen < CEIL4(xcRB->reply_control_blk_length))) { + resp_sumlen = CEIL4(xcrb->reply_control_blk_length) + + xcrb->reply_data_length; + if ((CEIL4(xcrb->reply_control_blk_length) <= + xcrb->reply_data_length) ? + resp_sumlen < xcrb->reply_data_length : + resp_sumlen < CEIL4(xcrb->reply_control_blk_length)) { return -EINVAL; } /* prepare type6 header */ msg->hdr = static_type6_hdrX; - memcpy(msg->hdr.agent_id, &(xcRB->agent_ID), sizeof(xcRB->agent_ID)); - msg->hdr.ToCardLen1 = xcRB->request_control_blk_length; - if (xcRB->request_data_length) { + memcpy(msg->hdr.agent_id, &xcrb->agent_ID, sizeof(xcrb->agent_ID)); + msg->hdr.tocardlen1 = xcrb->request_control_blk_length; + if (xcrb->request_data_length) { msg->hdr.offset2 = msg->hdr.offset1 + rcblen; - msg->hdr.ToCardLen2 = xcRB->request_data_length; + msg->hdr.tocardlen2 = xcrb->request_data_length; } - msg->hdr.FromCardLen1 = xcRB->reply_control_blk_length; - msg->hdr.FromCardLen2 = xcRB->reply_data_length; + msg->hdr.fromcardlen1 = xcrb->reply_control_blk_length; + msg->hdr.fromcardlen2 = xcrb->reply_data_length; /* prepare CPRB */ - if (z_copy_from_user(userspace, &(msg->cprbx), xcRB->request_control_blk_addr, - xcRB->request_control_blk_length)) + if (z_copy_from_user(userspace, &msg->cprbx, xcrb->request_control_blk_addr, + xcrb->request_control_blk_length)) return -EFAULT; if (msg->cprbx.cprb_len + sizeof(msg->hdr.function_code) > - xcRB->request_control_blk_length) + xcrb->request_control_blk_length) return -EINVAL; function_code = ((unsigned char *)&msg->cprbx) + msg->cprbx.cprb_len; memcpy(msg->hdr.function_code, function_code, @@ -473,8 +417,8 @@ static int XCRB_msg_to_type6CPRB_msgX(bool userspace, struct ap_message *ap_msg, *dom = (unsigned short *)&msg->cprbx.domain; /* check subfunction, US and AU need special flag with NQAP */ - if (memcmp(function_code, "US", 2) == 0 - || memcmp(function_code, "AU", 2) == 0) + if (memcmp(function_code, "US", 2) == 0 || + memcmp(function_code, "AU", 2) == 0) ap_msg->flags |= AP_MSG_FLAG_SPECIAL; #ifdef CONFIG_ZCRYPT_DEBUG @@ -500,16 +444,16 @@ static int XCRB_msg_to_type6CPRB_msgX(bool userspace, struct ap_message *ap_msg, } /* copy data block */ - if (xcRB->request_data_length && - z_copy_from_user(userspace, req_data, xcRB->request_data_address, - xcRB->request_data_length)) + if (xcrb->request_data_length && + z_copy_from_user(userspace, req_data, xcrb->request_data_address, + xcrb->request_data_length)) return -EFAULT; return 0; } static int xcrb_msg_to_type6_ep11cprb_msgx(bool userspace, struct ap_message *ap_msg, - struct ep11_urb *xcRB, + struct ep11_urb *xcrb, unsigned int *fcode, unsigned int *domain) { @@ -539,25 +483,25 @@ static int xcrb_msg_to_type6_ep11cprb_msgx(bool userspace, struct ap_message *ap unsigned int dom_val; /* domain id */ } __packed * payload_hdr = NULL; - if (CEIL4(xcRB->req_len) < xcRB->req_len) + if (CEIL4(xcrb->req_len) < xcrb->req_len) return -EINVAL; /* overflow after alignment*/ /* length checks */ - ap_msg->len = sizeof(struct type6_hdr) + CEIL4(xcRB->req_len); + ap_msg->len = sizeof(struct type6_hdr) + CEIL4(xcrb->req_len); if (ap_msg->len > ap_msg->bufsize) return -EINVAL; - if (CEIL4(xcRB->resp_len) < xcRB->resp_len) + if (CEIL4(xcrb->resp_len) < xcrb->resp_len) return -EINVAL; /* overflow after alignment*/ /* prepare type6 header */ msg->hdr = static_type6_ep11_hdr; - msg->hdr.ToCardLen1 = xcRB->req_len; - msg->hdr.FromCardLen1 = xcRB->resp_len; + msg->hdr.tocardlen1 = xcrb->req_len; + msg->hdr.fromcardlen1 = xcrb->resp_len; /* Import CPRB data from the ioctl input parameter */ - if (z_copy_from_user(userspace, &(msg->cprbx.cprb_len), - (char __force __user *)xcRB->req, xcRB->req_len)) { + if (z_copy_from_user(userspace, &msg->cprbx.cprb_len, + (char __force __user *)xcrb->req, xcrb->req_len)) { return -EFAULT; } @@ -575,7 +519,7 @@ static int xcrb_msg_to_type6_ep11cprb_msgx(bool userspace, struct ap_message *ap } else { lfmt = 1; /* length format #1 */ } - payload_hdr = (struct pld_hdr *)((&(msg->pld_lenfmt))+lfmt); + payload_hdr = (struct pld_hdr *)((&msg->pld_lenfmt) + lfmt); *fcode = payload_hdr->func_val & 0xFFFF; /* enable special processing based on the cprbs flags special bit */ @@ -624,9 +568,9 @@ struct type86_ep11_reply { } __packed; static int convert_type86_ica(struct zcrypt_queue *zq, - struct ap_message *reply, - char __user *outputdata, - unsigned int outputdatalength) + struct ap_message *reply, + char __user *outputdata, + unsigned int outputdatalength) { static unsigned char static_pad[] = { 0x00, 0x02, @@ -679,18 +623,18 @@ static int convert_type86_ica(struct zcrypt_queue *zq, ZCRYPT_DBF_WARN("%s dev=%02x.%04x rc/rs=%d/%d => rc=EINVAL\n", __func__, AP_QID_CARD(zq->queue->qid), AP_QID_QUEUE(zq->queue->qid), - (int) service_rc, (int) service_rs); + (int)service_rc, (int)service_rs); return -EINVAL; } zq->online = 0; pr_err("Crypto dev=%02x.%04x rc/rs=%d/%d online=0 rc=EAGAIN\n", AP_QID_CARD(zq->queue->qid), AP_QID_QUEUE(zq->queue->qid), - (int) service_rc, (int) service_rs); + (int)service_rc, (int)service_rs); ZCRYPT_DBF_ERR("%s dev=%02x.%04x rc/rs=%d/%d => online=0 rc=EAGAIN\n", __func__, AP_QID_CARD(zq->queue->qid), AP_QID_QUEUE(zq->queue->qid), - (int) service_rc, (int) service_rs); + (int)service_rc, (int)service_rs); ap_send_online_uevent(&zq->queue->ap_dev, zq->online); return -EAGAIN; } @@ -729,42 +673,42 @@ static int convert_type86_ica(struct zcrypt_queue *zq, * * @zq: crypto device pointer * @reply: reply AP message. - * @xcRB: pointer to XCRB + * @xcrb: pointer to XCRB * * Returns 0 on success or -EINVAL, -EFAULT, -EAGAIN in case of an error. */ static int convert_type86_xcrb(bool userspace, struct zcrypt_queue *zq, struct ap_message *reply, - struct ica_xcRB *xcRB) + struct ica_xcRB *xcrb) { struct type86_fmt2_msg *msg = reply->msg; char *data = reply->msg; /* Copy CPRB to user */ - if (xcRB->reply_control_blk_length < msg->fmt2.count1) { + if (xcrb->reply_control_blk_length < msg->fmt2.count1) { ZCRYPT_DBF_DBG("%s reply_control_blk_length %u < required %u => EMSGSIZE\n", - __func__, xcRB->reply_control_blk_length, + __func__, xcrb->reply_control_blk_length, msg->fmt2.count1); return -EMSGSIZE; } - if (z_copy_to_user(userspace, xcRB->reply_control_blk_addr, + if (z_copy_to_user(userspace, xcrb->reply_control_blk_addr, data + msg->fmt2.offset1, msg->fmt2.count1)) return -EFAULT; - xcRB->reply_control_blk_length = msg->fmt2.count1; + xcrb->reply_control_blk_length = msg->fmt2.count1; /* Copy data buffer to user */ if (msg->fmt2.count2) { - if (xcRB->reply_data_length < msg->fmt2.count2) { + if (xcrb->reply_data_length < msg->fmt2.count2) { ZCRYPT_DBF_DBG("%s reply_data_length %u < required %u => EMSGSIZE\n", - __func__, xcRB->reply_data_length, + __func__, xcrb->reply_data_length, msg->fmt2.count2); return -EMSGSIZE; } - if (z_copy_to_user(userspace, xcRB->reply_data_addr, + if (z_copy_to_user(userspace, xcrb->reply_data_addr, data + msg->fmt2.offset2, msg->fmt2.count2)) return -EFAULT; } - xcRB->reply_data_length = msg->fmt2.count2; + xcrb->reply_data_length = msg->fmt2.count2; return 0; } @@ -774,35 +718,35 @@ static int convert_type86_xcrb(bool userspace, struct zcrypt_queue *zq, * * @zq: crypto device pointer * @reply: reply AP message. - * @xcRB: pointer to EP11 user request block + * @xcrb: pointer to EP11 user request block * * Returns 0 on success or -EINVAL, -EFAULT, -EAGAIN in case of an error. */ static int convert_type86_ep11_xcrb(bool userspace, struct zcrypt_queue *zq, struct ap_message *reply, - struct ep11_urb *xcRB) + struct ep11_urb *xcrb) { struct type86_fmt2_msg *msg = reply->msg; char *data = reply->msg; - if (xcRB->resp_len < msg->fmt2.count1) { + if (xcrb->resp_len < msg->fmt2.count1) { ZCRYPT_DBF_DBG("%s resp_len %u < required %u => EMSGSIZE\n", - __func__, (unsigned int)xcRB->resp_len, + __func__, (unsigned int)xcrb->resp_len, msg->fmt2.count1); return -EMSGSIZE; } /* Copy response CPRB to user */ - if (z_copy_to_user(userspace, (char __force __user *)xcRB->resp, + if (z_copy_to_user(userspace, (char __force __user *)xcrb->resp, data + msg->fmt2.offset1, msg->fmt2.count1)) return -EFAULT; - xcRB->resp_len = msg->fmt2.count1; + xcrb->resp_len = msg->fmt2.count1; return 0; } static int convert_type86_rng(struct zcrypt_queue *zq, - struct ap_message *reply, - char *buffer) + struct ap_message *reply, + char *buffer) { struct { struct type86_hdr hdr; @@ -818,9 +762,9 @@ static int convert_type86_rng(struct zcrypt_queue *zq, } static int convert_response_ica(struct zcrypt_queue *zq, - struct ap_message *reply, - char __user *outputdata, - unsigned int outputdatalength) + struct ap_message *reply, + char __user *outputdata, + unsigned int outputdatalength) { struct type86x_reply *msg = reply->msg; @@ -830,13 +774,14 @@ static int convert_response_ica(struct zcrypt_queue *zq, return convert_error(zq, reply); case TYPE86_RSP_CODE: if (msg->cprbx.ccp_rtcode && - (msg->cprbx.ccp_rscode == 0x14f) && - (outputdatalength > 256)) { + msg->cprbx.ccp_rscode == 0x14f && + outputdatalength > 256) { if (zq->zcard->max_exp_bit_length <= 17) { zq->zcard->max_exp_bit_length = 17; return -EAGAIN; - } else + } else { return -EINVAL; + } } if (msg->hdr.reply_code) return convert_error(zq, reply); @@ -850,11 +795,11 @@ static int convert_response_ica(struct zcrypt_queue *zq, pr_err("Crypto dev=%02x.%04x unknown response type 0x%02x => online=0 rc=EAGAIN\n", AP_QID_CARD(zq->queue->qid), AP_QID_QUEUE(zq->queue->qid), - (int) msg->hdr.type); + (int)msg->hdr.type); ZCRYPT_DBF_ERR( "%s dev=%02x.%04x unknown response type 0x%02x => online=0 rc=EAGAIN\n", __func__, AP_QID_CARD(zq->queue->qid), - AP_QID_QUEUE(zq->queue->qid), (int) msg->hdr.type); + AP_QID_QUEUE(zq->queue->qid), (int)msg->hdr.type); ap_send_online_uevent(&zq->queue->ap_dev, zq->online); return -EAGAIN; } @@ -862,41 +807,41 @@ static int convert_response_ica(struct zcrypt_queue *zq, static int convert_response_xcrb(bool userspace, struct zcrypt_queue *zq, struct ap_message *reply, - struct ica_xcRB *xcRB) + struct ica_xcRB *xcrb) { struct type86x_reply *msg = reply->msg; switch (msg->hdr.type) { case TYPE82_RSP_CODE: case TYPE88_RSP_CODE: - xcRB->status = 0x0008044DL; /* HDD_InvalidParm */ + xcrb->status = 0x0008044DL; /* HDD_InvalidParm */ return convert_error(zq, reply); case TYPE86_RSP_CODE: if (msg->hdr.reply_code) { - memcpy(&(xcRB->status), msg->fmt2.apfs, sizeof(u32)); + memcpy(&xcrb->status, msg->fmt2.apfs, sizeof(u32)); return convert_error(zq, reply); } if (msg->cprbx.cprb_ver_id == 0x02) - return convert_type86_xcrb(userspace, zq, reply, xcRB); + return convert_type86_xcrb(userspace, zq, reply, xcrb); fallthrough; /* wrong cprb version is an unknown response */ default: /* Unknown response type, this should NEVER EVER happen */ - xcRB->status = 0x0008044DL; /* HDD_InvalidParm */ + xcrb->status = 0x0008044DL; /* HDD_InvalidParm */ zq->online = 0; pr_err("Crypto dev=%02x.%04x unknown response type 0x%02x => online=0 rc=EAGAIN\n", AP_QID_CARD(zq->queue->qid), AP_QID_QUEUE(zq->queue->qid), - (int) msg->hdr.type); + (int)msg->hdr.type); ZCRYPT_DBF_ERR( "%s dev=%02x.%04x unknown response type 0x%02x => online=0 rc=EAGAIN\n", __func__, AP_QID_CARD(zq->queue->qid), - AP_QID_QUEUE(zq->queue->qid), (int) msg->hdr.type); + AP_QID_QUEUE(zq->queue->qid), (int)msg->hdr.type); ap_send_online_uevent(&zq->queue->ap_dev, zq->online); return -EAGAIN; } } static int convert_response_ep11_xcrb(bool userspace, struct zcrypt_queue *zq, - struct ap_message *reply, struct ep11_urb *xcRB) + struct ap_message *reply, struct ep11_urb *xcrb) { struct type86_ep11_reply *msg = reply->msg; @@ -908,26 +853,26 @@ static int convert_response_ep11_xcrb(bool userspace, struct zcrypt_queue *zq, if (msg->hdr.reply_code) return convert_error(zq, reply); if (msg->cprbx.cprb_ver_id == 0x04) - return convert_type86_ep11_xcrb(userspace, zq, reply, xcRB); + return convert_type86_ep11_xcrb(userspace, zq, reply, xcrb); fallthrough; /* wrong cprb version is an unknown resp */ default: /* Unknown response type, this should NEVER EVER happen */ zq->online = 0; pr_err("Crypto dev=%02x.%04x unknown response type 0x%02x => online=0 rc=EAGAIN\n", AP_QID_CARD(zq->queue->qid), AP_QID_QUEUE(zq->queue->qid), - (int) msg->hdr.type); + (int)msg->hdr.type); ZCRYPT_DBF_ERR( "%s dev=%02x.%04x unknown response type 0x%02x => online=0 rc=EAGAIN\n", __func__, AP_QID_CARD(zq->queue->qid), - AP_QID_QUEUE(zq->queue->qid), (int) msg->hdr.type); + AP_QID_QUEUE(zq->queue->qid), (int)msg->hdr.type); ap_send_online_uevent(&zq->queue->ap_dev, zq->online); return -EAGAIN; } } static int convert_response_rng(struct zcrypt_queue *zq, - struct ap_message *reply, - char *data) + struct ap_message *reply, + char *data) { struct type86x_reply *msg = reply->msg; @@ -946,11 +891,11 @@ static int convert_response_rng(struct zcrypt_queue *zq, pr_err("Crypto dev=%02x.%04x unknown response type 0x%02x => online=0 rc=EAGAIN\n", AP_QID_CARD(zq->queue->qid), AP_QID_QUEUE(zq->queue->qid), - (int) msg->hdr.type); + (int)msg->hdr.type); ZCRYPT_DBF_ERR( "%s dev=%02x.%04x unknown response type 0x%02x => online=0 rc=EAGAIN\n", __func__, AP_QID_CARD(zq->queue->qid), - AP_QID_QUEUE(zq->queue->qid), (int) msg->hdr.type); + AP_QID_QUEUE(zq->queue->qid), (int)msg->hdr.type); ap_send_online_uevent(&zq->queue->ap_dev, zq->online); return -EAGAIN; } @@ -965,15 +910,15 @@ static int convert_response_rng(struct zcrypt_queue *zq, * @reply: pointer to the AP reply message */ static void zcrypt_msgtype6_receive(struct ap_queue *aq, - struct ap_message *msg, - struct ap_message *reply) + struct ap_message *msg, + struct ap_message *reply) { static struct error_hdr error_reply = { .type = TYPE82_RSP_CODE, .reply_code = REP82_ERROR_MACHINE_FAILURE, }; struct response_type *resp_type = - (struct response_type *) msg->private; + (struct response_type *)msg->private; struct type86x_reply *t86r; int len; @@ -982,7 +927,7 @@ static void zcrypt_msgtype6_receive(struct ap_queue *aq, goto out; /* ap_msg->rc indicates the error */ t86r = reply->msg; if (t86r->hdr.type == TYPE86_RSP_CODE && - t86r->cprbx.cprb_ver_id == 0x02) { + t86r->cprbx.cprb_ver_id == 0x02) { switch (resp_type->type) { case CEXXC_RESPONSE_TYPE_ICA: len = sizeof(struct type86x_reply) + t86r->length - 2; @@ -1005,10 +950,11 @@ static void zcrypt_msgtype6_receive(struct ap_queue *aq, default: memcpy(msg->msg, &error_reply, sizeof(error_reply)); } - } else + } else { memcpy(msg->msg, reply->msg, sizeof(error_reply)); + } out: - complete(&(resp_type->work)); + complete(&resp_type->work); } /* @@ -1055,7 +1001,7 @@ static void zcrypt_msgtype6_receive_ep11(struct ap_queue *aq, memcpy(msg->msg, reply->msg, sizeof(error_reply)); } out: - complete(&(resp_type->work)); + complete(&resp_type->work); } static atomic_t zcrypt_step = ATOMIC_INIT(0); @@ -1076,15 +1022,15 @@ static long zcrypt_msgtype6_modexpo(struct zcrypt_queue *zq, }; int rc; - ap_msg->msg = (void *) get_zeroed_page(GFP_KERNEL); + ap_msg->msg = (void *)get_zeroed_page(GFP_KERNEL); if (!ap_msg->msg) return -ENOMEM; ap_msg->bufsize = PAGE_SIZE; ap_msg->receive = zcrypt_msgtype6_receive; - ap_msg->psmid = (((unsigned long long) current->pid) << 32) + + ap_msg->psmid = (((unsigned long long)current->pid) << 32) + atomic_inc_return(&zcrypt_step); ap_msg->private = &resp_type; - rc = ICAMEX_msg_to_type6MEX_msgX(zq, ap_msg, mex); + rc = icamex_msg_to_type6mex_msgx(zq, ap_msg, mex); if (rc) goto out_free; init_completion(&resp_type.work); @@ -1098,11 +1044,13 @@ static long zcrypt_msgtype6_modexpo(struct zcrypt_queue *zq, rc = convert_response_ica(zq, ap_msg, mex->outputdata, mex->outputdatalength); - } else + } else { /* Signal pending. */ ap_cancel_message(zq->queue, ap_msg); + } + out_free: - free_page((unsigned long) ap_msg->msg); + free_page((unsigned long)ap_msg->msg); ap_msg->private = NULL; ap_msg->msg = NULL; return rc; @@ -1124,15 +1072,15 @@ static long zcrypt_msgtype6_modexpo_crt(struct zcrypt_queue *zq, }; int rc; - ap_msg->msg = (void *) get_zeroed_page(GFP_KERNEL); + ap_msg->msg = (void *)get_zeroed_page(GFP_KERNEL); if (!ap_msg->msg) return -ENOMEM; ap_msg->bufsize = PAGE_SIZE; ap_msg->receive = zcrypt_msgtype6_receive; - ap_msg->psmid = (((unsigned long long) current->pid) << 32) + + ap_msg->psmid = (((unsigned long long)current->pid) << 32) + atomic_inc_return(&zcrypt_step); ap_msg->private = &resp_type; - rc = ICACRT_msg_to_type6CRT_msgX(zq, ap_msg, crt); + rc = icacrt_msg_to_type6crt_msgx(zq, ap_msg, crt); if (rc) goto out_free; init_completion(&resp_type.work); @@ -1150,8 +1098,9 @@ static long zcrypt_msgtype6_modexpo_crt(struct zcrypt_queue *zq, /* Signal pending. */ ap_cancel_message(zq->queue, ap_msg); } + out_free: - free_page((unsigned long) ap_msg->msg); + free_page((unsigned long)ap_msg->msg); ap_msg->private = NULL; ap_msg->msg = NULL; return rc; @@ -1166,7 +1115,7 @@ out_free: * by the caller with ap_init_message(). Also the caller has to * make sure ap_release_message() is always called even on failure. */ -int prep_cca_ap_msg(bool userspace, struct ica_xcRB *xcRB, +int prep_cca_ap_msg(bool userspace, struct ica_xcRB *xcrb, struct ap_message *ap_msg, unsigned int *func_code, unsigned short **dom) { @@ -1179,12 +1128,12 @@ int prep_cca_ap_msg(bool userspace, struct ica_xcRB *xcRB, if (!ap_msg->msg) return -ENOMEM; ap_msg->receive = zcrypt_msgtype6_receive; - ap_msg->psmid = (((unsigned long long) current->pid) << 32) + + ap_msg->psmid = (((unsigned long long)current->pid) << 32) + atomic_inc_return(&zcrypt_step); ap_msg->private = kmemdup(&resp_type, sizeof(resp_type), GFP_KERNEL); if (!ap_msg->private) return -ENOMEM; - return XCRB_msg_to_type6CPRB_msgX(userspace, ap_msg, xcRB, func_code, dom); + return xcrb_msg_to_type6cprb_msgx(userspace, ap_msg, xcrb, func_code, dom); } /* @@ -1192,10 +1141,10 @@ int prep_cca_ap_msg(bool userspace, struct ica_xcRB *xcRB, * device to handle a send_cprb request. * @zq: pointer to zcrypt_queue structure that identifies the * CEXxC device to the request distributor - * @xcRB: pointer to the send_cprb request buffer + * @xcrb: pointer to the send_cprb request buffer */ static long zcrypt_msgtype6_send_cprb(bool userspace, struct zcrypt_queue *zq, - struct ica_xcRB *xcRB, + struct ica_xcRB *xcrb, struct ap_message *ap_msg) { int rc; @@ -1210,11 +1159,11 @@ static long zcrypt_msgtype6_send_cprb(bool userspace, struct zcrypt_queue *zq, * Set the queue's reply buffer length minus 128 byte padding * as reply limit for the card firmware. */ - msg->hdr.FromCardLen1 = min_t(unsigned int, msg->hdr.FromCardLen1, + msg->hdr.fromcardlen1 = min_t(unsigned int, msg->hdr.fromcardlen1, zq->reply.bufsize - 128); - if (msg->hdr.FromCardLen2) - msg->hdr.FromCardLen2 = - zq->reply.bufsize - msg->hdr.FromCardLen1 - 128; + if (msg->hdr.fromcardlen2) + msg->hdr.fromcardlen2 = + zq->reply.bufsize - msg->hdr.fromcardlen1 - 128; init_completion(&rtype->work); rc = ap_queue_message(zq->queue, ap_msg); @@ -1224,10 +1173,12 @@ static long zcrypt_msgtype6_send_cprb(bool userspace, struct zcrypt_queue *zq, if (rc == 0) { rc = ap_msg->rc; if (rc == 0) - rc = convert_response_xcrb(userspace, zq, ap_msg, xcRB); - } else + rc = convert_response_xcrb(userspace, zq, ap_msg, xcrb); + } else { /* Signal pending. */ ap_cancel_message(zq->queue, ap_msg); + } + out: if (rc) ZCRYPT_DBF_DBG("%s send cprb at dev=%02x.%04x rc=%d\n", @@ -1258,7 +1209,7 @@ int prep_ep11_ap_msg(bool userspace, struct ep11_urb *xcrb, if (!ap_msg->msg) return -ENOMEM; ap_msg->receive = zcrypt_msgtype6_receive_ep11; - ap_msg->psmid = (((unsigned long long) current->pid) << 32) + + ap_msg->psmid = (((unsigned long long)current->pid) << 32) + atomic_inc_return(&zcrypt_step); ap_msg->private = kmemdup(&resp_type, sizeof(resp_type), GFP_KERNEL); if (!ap_msg->private) @@ -1272,7 +1223,7 @@ int prep_ep11_ap_msg(bool userspace, struct ep11_urb *xcrb, * device to handle a send_ep11_cprb request. * @zq: pointer to zcrypt_queue structure that identifies the * CEX4P device to the request distributor - * @xcRB: pointer to the ep11 user request block + * @xcrb: pointer to the ep11 user request block */ static long zcrypt_msgtype6_send_ep11_cprb(bool userspace, struct zcrypt_queue *zq, struct ep11_urb *xcrb, @@ -1322,7 +1273,7 @@ static long zcrypt_msgtype6_send_ep11_cprb(bool userspace, struct zcrypt_queue * } else { lfmt = 1; /* length format #1 */ } - payload_hdr = (struct pld_hdr *)((&(msg->pld_lenfmt))+lfmt); + payload_hdr = (struct pld_hdr *)((&msg->pld_lenfmt) + lfmt); payload_hdr->dom_val = (unsigned int) AP_QID_QUEUE(zq->queue->qid); } @@ -1331,7 +1282,7 @@ static long zcrypt_msgtype6_send_ep11_cprb(bool userspace, struct zcrypt_queue * * Set the queue's reply buffer length minus the two prepend headers * as reply limit for the card firmware. */ - msg->hdr.FromCardLen1 = zq->reply.bufsize - + msg->hdr.fromcardlen1 = zq->reply.bufsize - sizeof(struct type86_hdr) - sizeof(struct type86_fmt2_ext); init_completion(&rtype->work); @@ -1343,9 +1294,11 @@ static long zcrypt_msgtype6_send_ep11_cprb(bool userspace, struct zcrypt_queue * rc = ap_msg->rc; if (rc == 0) rc = convert_response_ep11_xcrb(userspace, zq, ap_msg, xcrb); - } else + } else { /* Signal pending. */ ap_cancel_message(zq->queue, ap_msg); + } + out: if (rc) ZCRYPT_DBF_DBG("%s send cprb at dev=%02x.%04x rc=%d\n", @@ -1366,13 +1319,13 @@ int prep_rng_ap_msg(struct ap_message *ap_msg, int *func_code, if (!ap_msg->msg) return -ENOMEM; ap_msg->receive = zcrypt_msgtype6_receive; - ap_msg->psmid = (((unsigned long long) current->pid) << 32) + + ap_msg->psmid = (((unsigned long long)current->pid) << 32) + atomic_inc_return(&zcrypt_step); ap_msg->private = kmemdup(&resp_type, sizeof(resp_type), GFP_KERNEL); if (!ap_msg->private) return -ENOMEM; - rng_type6CPRB_msgX(ap_msg, ZCRYPT_RNG_BUFFER_SIZE, domain); + rng_type6cprb_msgx(ap_msg, ZCRYPT_RNG_BUFFER_SIZE, domain); *func_code = HWRNG; return 0; @@ -1411,9 +1364,10 @@ static long zcrypt_msgtype6_rng(struct zcrypt_queue *zq, rc = ap_msg->rc; if (rc == 0) rc = convert_response_rng(zq, ap_msg, buffer); - } else + } else { /* Signal pending. */ ap_cancel_message(zq->queue, ap_msg); + } out: return rc; } diff --git a/drivers/s390/crypto/zcrypt_msgtype6.h b/drivers/s390/crypto/zcrypt_msgtype6.h index 9da4f4175c44..6f5ced8d6cda 100644 --- a/drivers/s390/crypto/zcrypt_msgtype6.h +++ b/drivers/s390/crypto/zcrypt_msgtype6.h @@ -45,14 +45,14 @@ struct type6_hdr { unsigned char reserved5[2]; /* 0x0000 */ unsigned char function_code[2]; /* for PKD, 0x5044 (ascii 'PD') */ unsigned char reserved6[2]; /* 0x0000 */ - unsigned int ToCardLen1; /* (request CPRB len + 3) & -4 */ - unsigned int ToCardLen2; /* db len 0x00000000 for PKD */ - unsigned int ToCardLen3; /* 0x00000000 */ - unsigned int ToCardLen4; /* 0x00000000 */ - unsigned int FromCardLen1; /* response buffer length */ - unsigned int FromCardLen2; /* db len 0x00000000 for PKD */ - unsigned int FromCardLen3; /* 0x00000000 */ - unsigned int FromCardLen4; /* 0x00000000 */ + unsigned int tocardlen1; /* (request CPRB len + 3) & -4 */ + unsigned int tocardlen2; /* db len 0x00000000 for PKD */ + unsigned int tocardlen3; /* 0x00000000 */ + unsigned int tocardlen4; /* 0x00000000 */ + unsigned int fromcardlen1; /* response buffer length */ + unsigned int fromcardlen2; /* db len 0x00000000 for PKD */ + unsigned int fromcardlen3; /* 0x00000000 */ + unsigned int fromcardlen4; /* 0x00000000 */ } __packed; /** @@ -116,7 +116,7 @@ int speed_idx_ep11(int); * @ap_dev: AP device pointer * @ap_msg: pointer to AP message */ -static inline void rng_type6CPRB_msgX(struct ap_message *ap_msg, +static inline void rng_type6cprb_msgx(struct ap_message *ap_msg, unsigned int random_number_length, unsigned int *domain) { @@ -134,8 +134,8 @@ static inline void rng_type6CPRB_msgX(struct ap_message *ap_msg, .offset1 = 0x00000058, .agent_id = {'C', 'A'}, .function_code = {'R', 'L'}, - .ToCardLen1 = sizeof(*msg) - sizeof(msg->hdr), - .FromCardLen1 = sizeof(*msg) - sizeof(msg->hdr), + .tocardlen1 = sizeof(*msg) - sizeof(msg->hdr), + .fromcardlen1 = sizeof(*msg) - sizeof(msg->hdr), }; static struct CPRBX local_cprbx = { .cprb_len = 0x00dc, @@ -147,9 +147,9 @@ static inline void rng_type6CPRB_msgX(struct ap_message *ap_msg, }; msg->hdr = static_type6_hdrX; - msg->hdr.FromCardLen2 = random_number_length, + msg->hdr.fromcardlen2 = random_number_length; msg->cprbx = local_cprbx; - msg->cprbx.rpl_datal = random_number_length, + msg->cprbx.rpl_datal = random_number_length; memcpy(msg->function_code, msg->hdr.function_code, 0x02); msg->rule_length = 0x0a; memcpy(msg->rule, "RANDOM ", 8); diff --git a/drivers/s390/crypto/zcrypt_queue.c b/drivers/s390/crypto/zcrypt_queue.c index 1552a850a52e..cdc5a4b2c019 100644 --- a/drivers/s390/crypto/zcrypt_queue.c +++ b/drivers/s390/crypto/zcrypt_queue.c @@ -114,7 +114,7 @@ struct zcrypt_queue *zcrypt_queue_alloc(size_t reply_buf_size) { struct zcrypt_queue *zq; - zq = kzalloc(sizeof(struct zcrypt_queue), GFP_KERNEL); + zq = kzalloc(sizeof(*zq), GFP_KERNEL); if (!zq) return NULL; zq->reply.msg = kmalloc(reply_buf_size, GFP_KERNEL); diff --git a/drivers/s390/net/ctcm_mpc.c b/drivers/s390/net/ctcm_mpc.c index 88abfb5e8045..8ac213a55141 100644 --- a/drivers/s390/net/ctcm_mpc.c +++ b/drivers/s390/net/ctcm_mpc.c @@ -626,8 +626,6 @@ static void mpc_rcvd_sweep_resp(struct mpcg_info *mpcginfo) ctcm_clear_busy_do(dev); } - kfree(mpcginfo); - return; } @@ -1192,10 +1190,10 @@ static void ctcmpc_unpack_skb(struct channel *ch, struct sk_buff *pskb) CTCM_FUNTAIL, dev->name); priv->stats.rx_dropped++; /* mpcginfo only used for non-data transfers */ - kfree(mpcginfo); if (do_debug_data) ctcmpc_dump_skb(pskb, -8); } + kfree(mpcginfo); } done: @@ -1977,7 +1975,6 @@ static void mpc_action_rcvd_xid0(fsm_instance *fsm, int event, void *arg) } break; } - kfree(mpcginfo); CTCM_PR_DEBUG("ctcmpc:%s() %s xid2:%i xid7:%i xidt_p2:%i \n", __func__, ch->id, grp->outstanding_xid2, @@ -2038,7 +2035,6 @@ static void mpc_action_rcvd_xid7(fsm_instance *fsm, int event, void *arg) mpc_validate_xid(mpcginfo); break; } - kfree(mpcginfo); return; } diff --git a/drivers/s390/net/ctcm_sysfs.c b/drivers/s390/net/ctcm_sysfs.c index ded1930a00b2..e3813a7aa5e6 100644 --- a/drivers/s390/net/ctcm_sysfs.c +++ b/drivers/s390/net/ctcm_sysfs.c @@ -39,11 +39,12 @@ static ssize_t ctcm_buffer_write(struct device *dev, struct ctcm_priv *priv = dev_get_drvdata(dev); int rc; - ndev = priv->channel[CTCM_READ]->netdev; - if (!(priv && priv->channel[CTCM_READ] && ndev)) { + if (!(priv && priv->channel[CTCM_READ] && + priv->channel[CTCM_READ]->netdev)) { CTCM_DBF_TEXT(SETUP, CTC_DBF_ERROR, "bfnondev"); return -ENODEV; } + ndev = priv->channel[CTCM_READ]->netdev; rc = kstrtouint(buf, 0, &bs1); if (rc) diff --git a/drivers/s390/net/lcs.c b/drivers/s390/net/lcs.c index bab9b34926c6..84c8981317b4 100644 --- a/drivers/s390/net/lcs.c +++ b/drivers/s390/net/lcs.c @@ -1736,10 +1736,11 @@ lcs_get_control(struct lcs_card *card, struct lcs_cmd *cmd) lcs_schedule_recovery(card); break; case LCS_CMD_STOPLAN: - pr_warn("Stoplan for %s initiated by LGW\n", - card->dev->name); - if (card->dev) + if (card->dev) { + pr_warn("Stoplan for %s initiated by LGW\n", + card->dev->name); netif_carrier_off(card->dev); + } break; default: LCS_DBF_TEXT(5, trace, "noLGWcmd"); diff --git a/drivers/scsi/aha152x.c b/drivers/scsi/aha152x.c index 5f554a3a0f62..caeebfb67149 100644 --- a/drivers/scsi/aha152x.c +++ b/drivers/scsi/aha152x.c @@ -317,14 +317,18 @@ enum { }; struct aha152x_cmd_priv { - struct scsi_pointer scsi_pointer; + char *ptr; + int this_residual; + struct scatterlist *buffer; + int status; + int message; + int sent_command; + int phase; }; -static struct scsi_pointer *aha152x_scsi_pointer(struct scsi_cmnd *cmd) +static struct aha152x_cmd_priv *aha152x_priv(struct scsi_cmnd *cmd) { - struct aha152x_cmd_priv *acmd = scsi_cmd_priv(cmd); - - return &acmd->scsi_pointer; + return scsi_cmd_priv(cmd); } MODULE_AUTHOR("Jürgen Fischer"); @@ -890,17 +894,16 @@ void aha152x_release(struct Scsi_Host *shpnt) static int setup_expected_interrupts(struct Scsi_Host *shpnt) { if(CURRENT_SC) { - struct scsi_pointer *scsi_pointer = - aha152x_scsi_pointer(CURRENT_SC); + struct aha152x_cmd_priv *acp = aha152x_priv(CURRENT_SC); - scsi_pointer->phase |= 1 << 16; + acp->phase |= 1 << 16; - if (scsi_pointer->phase & selecting) { + if (acp->phase & selecting) { SETPORT(SSTAT1, SELTO); SETPORT(SIMODE0, ENSELDO | (DISCONNECTED_SC ? ENSELDI : 0)); SETPORT(SIMODE1, ENSELTIMO); } else { - SETPORT(SIMODE0, (scsi_pointer->phase & spiordy) ? ENSPIORDY : 0); + SETPORT(SIMODE0, (acp->phase & spiordy) ? ENSPIORDY : 0); SETPORT(SIMODE1, ENPHASEMIS | ENSCSIRST | ENSCSIPERR | ENBUSFREE); } } else if(STATE==seldi) { @@ -924,17 +927,16 @@ static int setup_expected_interrupts(struct Scsi_Host *shpnt) static int aha152x_internal_queue(struct scsi_cmnd *SCpnt, struct completion *complete, int phase) { - struct scsi_pointer *scsi_pointer = aha152x_scsi_pointer(SCpnt); + struct aha152x_cmd_priv *acp = aha152x_priv(SCpnt); struct Scsi_Host *shpnt = SCpnt->device->host; unsigned long flags; - scsi_pointer->phase = not_issued | phase; - scsi_pointer->Status = 0x1; /* Ilegal status by SCSI standard */ - scsi_pointer->Message = 0; - scsi_pointer->have_data_in = 0; - scsi_pointer->sent_command = 0; + acp->phase = not_issued | phase; + acp->status = 0x1; /* Illegal status by SCSI standard */ + acp->message = 0; + acp->sent_command = 0; - if (scsi_pointer->phase & (resetting | check_condition)) { + if (acp->phase & (resetting | check_condition)) { if (!SCpnt->host_scribble || SCSEM(SCpnt) || SCNEXT(SCpnt)) { scmd_printk(KERN_ERR, SCpnt, "cannot reuse command\n"); return FAILED; @@ -957,15 +959,15 @@ static int aha152x_internal_queue(struct scsi_cmnd *SCpnt, SCp.phase : current state of the command */ if ((phase & resetting) || !scsi_sglist(SCpnt)) { - scsi_pointer->ptr = NULL; - scsi_pointer->this_residual = 0; + acp->ptr = NULL; + acp->this_residual = 0; scsi_set_resid(SCpnt, 0); - scsi_pointer->buffer = NULL; + acp->buffer = NULL; } else { scsi_set_resid(SCpnt, scsi_bufflen(SCpnt)); - scsi_pointer->buffer = scsi_sglist(SCpnt); - scsi_pointer->ptr = SG_ADDRESS(scsi_pointer->buffer); - scsi_pointer->this_residual = scsi_pointer->buffer->length; + acp->buffer = scsi_sglist(SCpnt); + acp->ptr = SG_ADDRESS(acp->buffer); + acp->this_residual = acp->buffer->length; } DO_LOCK(flags); @@ -1015,7 +1017,7 @@ static void reset_done(struct scsi_cmnd *SCpnt) static void aha152x_scsi_done(struct scsi_cmnd *SCpnt) { - if (aha152x_scsi_pointer(SCpnt)->phase & resetting) + if (aha152x_priv(SCpnt)->phase & resetting) reset_done(SCpnt); else scsi_done(SCpnt); @@ -1101,7 +1103,7 @@ static int aha152x_device_reset(struct scsi_cmnd * SCpnt) DO_LOCK(flags); - if (aha152x_scsi_pointer(SCpnt)->phase & resetted) { + if (aha152x_priv(SCpnt)->phase & resetted) { HOSTDATA(shpnt)->commands--; if (!HOSTDATA(shpnt)->commands) SETPORT(PORTA, 0); @@ -1395,31 +1397,30 @@ static void busfree_run(struct Scsi_Host *shpnt) SETPORT(SSTAT1, CLRBUSFREE); if(CURRENT_SC) { - struct scsi_pointer *scsi_pointer = - aha152x_scsi_pointer(CURRENT_SC); + struct aha152x_cmd_priv *acp = aha152x_priv(CURRENT_SC); #if defined(AHA152X_STAT) action++; #endif - scsi_pointer->phase &= ~syncneg; + acp->phase &= ~syncneg; - if (scsi_pointer->phase & completed) { + if (acp->phase & completed) { /* target sent COMMAND COMPLETE */ - done(shpnt, scsi_pointer->Status, DID_OK); + done(shpnt, acp->status, DID_OK); - } else if (scsi_pointer->phase & aborted) { - done(shpnt, scsi_pointer->Status, DID_ABORT); + } else if (acp->phase & aborted) { + done(shpnt, acp->status, DID_ABORT); - } else if (scsi_pointer->phase & resetted) { - done(shpnt, scsi_pointer->Status, DID_RESET); + } else if (acp->phase & resetted) { + done(shpnt, acp->status, DID_RESET); - } else if (scsi_pointer->phase & disconnected) { + } else if (acp->phase & disconnected) { /* target sent DISCONNECT */ #if defined(AHA152X_STAT) HOSTDATA(shpnt)->disconnections++; #endif append_SC(&DISCONNECTED_SC, CURRENT_SC); - scsi_pointer->phase |= 1 << 16; + acp->phase |= 1 << 16; CURRENT_SC = NULL; } else { @@ -1438,24 +1439,23 @@ static void busfree_run(struct Scsi_Host *shpnt) action++; #endif - if (aha152x_scsi_pointer(DONE_SC)->phase & check_condition) { + if (aha152x_priv(DONE_SC)->phase & check_condition) { struct scsi_cmnd *cmd = HOSTDATA(shpnt)->done_SC; struct aha152x_scdata *sc = SCDATA(cmd); scsi_eh_restore_cmnd(cmd, &sc->ses); - aha152x_scsi_pointer(cmd)->Status = SAM_STAT_CHECK_CONDITION; + aha152x_priv(cmd)->status = SAM_STAT_CHECK_CONDITION; HOSTDATA(shpnt)->commands--; if (!HOSTDATA(shpnt)->commands) SETPORT(PORTA, 0); /* turn led off */ - } else if (aha152x_scsi_pointer(DONE_SC)->Status == - SAM_STAT_CHECK_CONDITION) { + } else if (aha152x_priv(DONE_SC)->status == SAM_STAT_CHECK_CONDITION) { #if defined(AHA152X_STAT) HOSTDATA(shpnt)->busfree_with_check_condition++; #endif - if(!(aha152x_scsi_pointer(DONE_SC)->phase & not_issued)) { + if (!(aha152x_priv(DONE_SC)->phase & not_issued)) { struct aha152x_scdata *sc; struct scsi_cmnd *ptr = DONE_SC; DONE_SC=NULL; @@ -1480,7 +1480,7 @@ static void busfree_run(struct Scsi_Host *shpnt) if (!HOSTDATA(shpnt)->commands) SETPORT(PORTA, 0); /* turn led off */ - if (!(aha152x_scsi_pointer(ptr)->phase & resetting)) { + if (!(aha152x_priv(ptr)->phase & resetting)) { kfree(ptr->host_scribble); ptr->host_scribble=NULL; } @@ -1503,13 +1503,12 @@ static void busfree_run(struct Scsi_Host *shpnt) DO_UNLOCK(flags); if(CURRENT_SC) { - struct scsi_pointer *scsi_pointer = - aha152x_scsi_pointer(CURRENT_SC); + struct aha152x_cmd_priv *acp = aha152x_priv(CURRENT_SC); #if defined(AHA152X_STAT) action++; #endif - scsi_pointer->phase |= selecting; + acp->phase |= selecting; /* clear selection timeout */ SETPORT(SSTAT1, SELTO); @@ -1537,13 +1536,13 @@ static void busfree_run(struct Scsi_Host *shpnt) */ static void seldo_run(struct Scsi_Host *shpnt) { - struct scsi_pointer *scsi_pointer = aha152x_scsi_pointer(CURRENT_SC); + struct aha152x_cmd_priv *acp = aha152x_priv(CURRENT_SC); SETPORT(SCSISIG, 0); SETPORT(SSTAT1, CLRBUSFREE); SETPORT(SSTAT1, CLRPHASECHG); - scsi_pointer->phase &= ~(selecting | not_issued); + acp->phase &= ~(selecting | not_issued); SETPORT(SCSISEQ, 0); @@ -1558,12 +1557,12 @@ static void seldo_run(struct Scsi_Host *shpnt) ADDMSGO(IDENTIFY(RECONNECT, CURRENT_SC->device->lun)); - if (scsi_pointer->phase & aborting) { + if (acp->phase & aborting) { ADDMSGO(ABORT); - } else if (scsi_pointer->phase & resetting) { + } else if (acp->phase & resetting) { ADDMSGO(BUS_DEVICE_RESET); } else if (SYNCNEG==0 && SYNCHRONOUS) { - scsi_pointer->phase |= syncneg; + acp->phase |= syncneg; MSGOLEN += spi_populate_sync_msg(&MSGO(MSGOLEN), 50, 8); SYNCNEG=1; /* negotiation in progress */ } @@ -1578,7 +1577,7 @@ static void seldo_run(struct Scsi_Host *shpnt) */ static void selto_run(struct Scsi_Host *shpnt) { - struct scsi_pointer *scsi_pointer = aha152x_scsi_pointer(CURRENT_SC); + struct aha152x_cmd_priv *acp; SETPORT(SCSISEQ, 0); SETPORT(SSTAT1, CLRSELTIMO); @@ -1586,9 +1585,10 @@ static void selto_run(struct Scsi_Host *shpnt) if (!CURRENT_SC) return; - scsi_pointer->phase &= ~selecting; + acp = aha152x_priv(CURRENT_SC); + acp->phase &= ~selecting; - if (scsi_pointer->phase & aborted) + if (acp->phase & aborted) done(shpnt, SAM_STAT_GOOD, DID_ABORT); else if (TESTLO(SSTAT0, SELINGO)) done(shpnt, SAM_STAT_GOOD, DID_BUS_BUSY); @@ -1616,10 +1616,9 @@ static void seldi_run(struct Scsi_Host *shpnt) SETPORT(SSTAT1, CLRPHASECHG); if(CURRENT_SC) { - struct scsi_pointer *scsi_pointer = - aha152x_scsi_pointer(CURRENT_SC); + struct aha152x_cmd_priv *acp = aha152x_priv(CURRENT_SC); - if (!(scsi_pointer->phase & not_issued)) + if (!(acp->phase & not_issued)) scmd_printk(KERN_ERR, CURRENT_SC, "command should not have been issued yet\n"); @@ -1676,7 +1675,7 @@ static void seldi_run(struct Scsi_Host *shpnt) static void msgi_run(struct Scsi_Host *shpnt) { for(;;) { - struct scsi_pointer *scsi_pointer; + struct aha152x_cmd_priv *acp; int sstat1 = GETPORT(SSTAT1); if(sstat1 & (PHASECHG|PHASEMIS|BUSFREE) || !(sstat1 & REQINIT)) @@ -1714,9 +1713,9 @@ static void msgi_run(struct Scsi_Host *shpnt) continue; } - scsi_pointer = aha152x_scsi_pointer(CURRENT_SC); - scsi_pointer->Message = MSGI(0); - scsi_pointer->phase &= ~disconnected; + acp = aha152x_priv(CURRENT_SC); + acp->message = MSGI(0); + acp->phase &= ~disconnected; MSGILEN=0; @@ -1724,8 +1723,8 @@ static void msgi_run(struct Scsi_Host *shpnt) continue; } - scsi_pointer = aha152x_scsi_pointer(CURRENT_SC); - scsi_pointer->Message = MSGI(0); + acp = aha152x_priv(CURRENT_SC); + acp->message = MSGI(0); switch (MSGI(0)) { case DISCONNECT: @@ -1733,11 +1732,11 @@ static void msgi_run(struct Scsi_Host *shpnt) scmd_printk(KERN_WARNING, CURRENT_SC, "target was not allowed to disconnect\n"); - scsi_pointer->phase |= disconnected; + acp->phase |= disconnected; break; case COMMAND_COMPLETE: - scsi_pointer->phase |= completed; + acp->phase |= completed; break; case MESSAGE_REJECT: @@ -1867,11 +1866,9 @@ static void msgi_end(struct Scsi_Host *shpnt) */ static void msgo_init(struct Scsi_Host *shpnt) { - struct scsi_pointer *scsi_pointer = aha152x_scsi_pointer(CURRENT_SC); - if(MSGOLEN==0) { - if ((scsi_pointer->phase & syncneg) && SYNCNEG==2 && - SYNCRATE==0) { + if ((aha152x_priv(CURRENT_SC)->phase & syncneg) && + SYNCNEG == 2 && SYNCRATE == 0) { ADDMSGO(IDENTIFY(RECONNECT, CURRENT_SC->device->lun)); } else { scmd_printk(KERN_INFO, CURRENT_SC, @@ -1888,7 +1885,7 @@ static void msgo_init(struct Scsi_Host *shpnt) */ static void msgo_run(struct Scsi_Host *shpnt) { - struct scsi_pointer *scsi_pointer = aha152x_scsi_pointer(CURRENT_SC); + struct aha152x_cmd_priv *acp = aha152x_priv(CURRENT_SC); while(MSGO_I<MSGOLEN) { if (TESTLO(SSTAT0, SPIORDY)) @@ -1901,13 +1898,13 @@ static void msgo_run(struct Scsi_Host *shpnt) if (MSGO(MSGO_I) & IDENTIFY_BASE) - scsi_pointer->phase |= identified; + acp->phase |= identified; if (MSGO(MSGO_I)==ABORT) - scsi_pointer->phase |= aborted; + acp->phase |= aborted; if (MSGO(MSGO_I)==BUS_DEVICE_RESET) - scsi_pointer->phase |= resetted; + acp->phase |= resetted; SETPORT(SCSIDAT, MSGO(MSGO_I++)); } @@ -1936,7 +1933,7 @@ static void msgo_end(struct Scsi_Host *shpnt) */ static void cmd_init(struct Scsi_Host *shpnt) { - if (aha152x_scsi_pointer(CURRENT_SC)->sent_command) { + if (aha152x_priv(CURRENT_SC)->sent_command) { scmd_printk(KERN_ERR, CURRENT_SC, "command already sent\n"); done(shpnt, SAM_STAT_GOOD, DID_ERROR); @@ -1967,7 +1964,7 @@ static void cmd_end(struct Scsi_Host *shpnt) "command sent incompletely (%d/%d)\n", CMD_I, CURRENT_SC->cmd_len); else - aha152x_scsi_pointer(CURRENT_SC)->sent_command++; + aha152x_priv(CURRENT_SC)->sent_command++; } /* @@ -1979,7 +1976,7 @@ static void status_run(struct Scsi_Host *shpnt) if (TESTLO(SSTAT0, SPIORDY)) return; - aha152x_scsi_pointer(CURRENT_SC)->Status = GETPORT(SCSIDAT); + aha152x_priv(CURRENT_SC)->status = GETPORT(SCSIDAT); } @@ -2003,7 +2000,7 @@ static void datai_init(struct Scsi_Host *shpnt) static void datai_run(struct Scsi_Host *shpnt) { - struct scsi_pointer *scsi_pointer; + struct aha152x_cmd_priv *acp; unsigned long the_time; int fifodata, data_count; @@ -2041,36 +2038,35 @@ static void datai_run(struct Scsi_Host *shpnt) fifodata = GETPORT(FIFOSTAT); } - scsi_pointer = aha152x_scsi_pointer(CURRENT_SC); - if (scsi_pointer->this_residual > 0) { - while (fifodata > 0 && scsi_pointer->this_residual > 0) { - data_count = fifodata > scsi_pointer->this_residual ? - scsi_pointer->this_residual : - fifodata; + acp = aha152x_priv(CURRENT_SC); + if (acp->this_residual > 0) { + while (fifodata > 0 && acp->this_residual > 0) { + data_count = fifodata > acp->this_residual ? + acp->this_residual : fifodata; fifodata -= data_count; if (data_count & 1) { SETPORT(DMACNTRL0, ENDMA|_8BIT); - *scsi_pointer->ptr++ = GETPORT(DATAPORT); - scsi_pointer->this_residual--; + *acp->ptr++ = GETPORT(DATAPORT); + acp->this_residual--; DATA_LEN++; SETPORT(DMACNTRL0, ENDMA); } if (data_count > 1) { data_count >>= 1; - insw(DATAPORT, scsi_pointer->ptr, data_count); - scsi_pointer->ptr += 2 * data_count; - scsi_pointer->this_residual -= 2 * data_count; + insw(DATAPORT, acp->ptr, data_count); + acp->ptr += 2 * data_count; + acp->this_residual -= 2 * data_count; DATA_LEN += 2 * data_count; } - if (scsi_pointer->this_residual == 0 && - !sg_is_last(scsi_pointer->buffer)) { + if (acp->this_residual == 0 && + !sg_is_last(acp->buffer)) { /* advance to next buffer */ - scsi_pointer->buffer = sg_next(scsi_pointer->buffer); - scsi_pointer->ptr = SG_ADDRESS(scsi_pointer->buffer); - scsi_pointer->this_residual = scsi_pointer->buffer->length; + acp->buffer = sg_next(acp->buffer); + acp->ptr = SG_ADDRESS(acp->buffer); + acp->this_residual = acp->buffer->length; } } } else if (fifodata > 0) { @@ -2138,15 +2134,15 @@ static void datao_init(struct Scsi_Host *shpnt) static void datao_run(struct Scsi_Host *shpnt) { - struct scsi_pointer *scsi_pointer = aha152x_scsi_pointer(CURRENT_SC); + struct aha152x_cmd_priv *acp = aha152x_priv(CURRENT_SC); unsigned long the_time; int data_count; /* until phase changes or all data sent */ - while (TESTLO(DMASTAT, INTSTAT) && scsi_pointer->this_residual > 0) { + while (TESTLO(DMASTAT, INTSTAT) && acp->this_residual > 0) { data_count = 128; - if (data_count > scsi_pointer->this_residual) - data_count = scsi_pointer->this_residual; + if (data_count > acp->this_residual) + data_count = acp->this_residual; if(TESTLO(DMASTAT, DFIFOEMP)) { scmd_printk(KERN_ERR, CURRENT_SC, @@ -2157,26 +2153,25 @@ static void datao_run(struct Scsi_Host *shpnt) if(data_count & 1) { SETPORT(DMACNTRL0,WRITE_READ|ENDMA|_8BIT); - SETPORT(DATAPORT, *scsi_pointer->ptr++); - scsi_pointer->this_residual--; + SETPORT(DATAPORT, *acp->ptr++); + acp->this_residual--; CMD_INC_RESID(CURRENT_SC, -1); SETPORT(DMACNTRL0,WRITE_READ|ENDMA); } if(data_count > 1) { data_count >>= 1; - outsw(DATAPORT, scsi_pointer->ptr, data_count); - scsi_pointer->ptr += 2 * data_count; - scsi_pointer->this_residual -= 2 * data_count; + outsw(DATAPORT, acp->ptr, data_count); + acp->ptr += 2 * data_count; + acp->this_residual -= 2 * data_count; CMD_INC_RESID(CURRENT_SC, -2 * data_count); } - if (scsi_pointer->this_residual == 0 && - !sg_is_last(scsi_pointer->buffer)) { + if (acp->this_residual == 0 && !sg_is_last(acp->buffer)) { /* advance to next buffer */ - scsi_pointer->buffer = sg_next(scsi_pointer->buffer); - scsi_pointer->ptr = SG_ADDRESS(scsi_pointer->buffer); - scsi_pointer->this_residual = scsi_pointer->buffer->length; + acp->buffer = sg_next(acp->buffer); + acp->ptr = SG_ADDRESS(acp->buffer); + acp->this_residual = acp->buffer->length; } the_time=jiffies + 100*HZ; @@ -2192,7 +2187,7 @@ static void datao_run(struct Scsi_Host *shpnt) static void datao_end(struct Scsi_Host *shpnt) { - struct scsi_pointer *scsi_pointer = aha152x_scsi_pointer(CURRENT_SC); + struct aha152x_cmd_priv *acp = aha152x_priv(CURRENT_SC); if(TESTLO(DMASTAT, DFIFOEMP)) { u32 datao_cnt = GETSTCNT(); @@ -2211,10 +2206,9 @@ static void datao_end(struct Scsi_Host *shpnt) sg = sg_next(sg); } - scsi_pointer->buffer = sg; - scsi_pointer->ptr = SG_ADDRESS(scsi_pointer->buffer) + done; - scsi_pointer->this_residual = scsi_pointer->buffer->length - - done; + acp->buffer = sg; + acp->ptr = SG_ADDRESS(acp->buffer) + done; + acp->this_residual = acp->buffer->length - done; } SETPORT(SXFRCTL0, CH1|CLRCH1|CLRSTCNT); @@ -2229,7 +2223,6 @@ static void datao_end(struct Scsi_Host *shpnt) */ static int update_state(struct Scsi_Host *shpnt) { - struct scsi_pointer *scsi_pointer = aha152x_scsi_pointer(CURRENT_SC); int dataphase=0; unsigned int stat0 = GETPORT(SSTAT0); unsigned int stat1 = GETPORT(SSTAT1); @@ -2244,7 +2237,7 @@ static int update_state(struct Scsi_Host *shpnt) } else if (stat0 & SELDI && PREVSTATE == busfree) { STATE=seldi; } else if (stat0 & SELDO && CURRENT_SC && - (scsi_pointer->phase & selecting)) { + (aha152x_priv(CURRENT_SC)->phase & selecting)) { STATE=seldo; } else if(stat1 & SELTO) { STATE=selto; @@ -2376,8 +2369,7 @@ static void is_complete(struct Scsi_Host *shpnt) SETPORT(SXFRCTL0, CH1); SETPORT(DMACNTRL0, 0); if(CURRENT_SC) - aha152x_scsi_pointer(CURRENT_SC)->phase &= - ~spiordy; + aha152x_priv(CURRENT_SC)->phase &= ~spiordy; } /* @@ -2399,8 +2391,7 @@ static void is_complete(struct Scsi_Host *shpnt) SETPORT(DMACNTRL0, 0); SETPORT(SXFRCTL0, CH1|SPIOEN); if(CURRENT_SC) - aha152x_scsi_pointer(CURRENT_SC)->phase |= - spiordy; + aha152x_priv(CURRENT_SC)->phase |= spiordy; } /* @@ -2490,7 +2481,7 @@ static void disp_enintr(struct Scsi_Host *shpnt) */ static void show_command(struct scsi_cmnd *ptr) { - const int phase = aha152x_scsi_pointer(ptr)->phase; + const int phase = aha152x_priv(ptr)->phase; scsi_print_command(ptr); scmd_printk(KERN_DEBUG, ptr, @@ -2538,8 +2529,8 @@ static void show_queues(struct Scsi_Host *shpnt) static void get_command(struct seq_file *m, struct scsi_cmnd * ptr) { - struct scsi_pointer *scsi_pointer = aha152x_scsi_pointer(ptr); - const int phase = scsi_pointer->phase; + struct aha152x_cmd_priv *acp = aha152x_priv(ptr); + const int phase = acp->phase; int i; seq_printf(m, "%p: target=%d; lun=%d; cmnd=( ", @@ -2549,8 +2540,8 @@ static void get_command(struct seq_file *m, struct scsi_cmnd * ptr) seq_printf(m, "0x%02x ", ptr->cmnd[i]); seq_printf(m, "); resid=%d; residual=%d; buffers=%d; phase |", - scsi_get_resid(ptr), scsi_pointer->this_residual, - sg_nents(scsi_pointer->buffer) - 1); + scsi_get_resid(ptr), acp->this_residual, + sg_nents(acp->buffer) - 1); if (phase & not_issued) seq_puts(m, "not issued|"); diff --git a/drivers/scsi/aic7xxx/aic79xx_osm.h b/drivers/scsi/aic7xxx/aic79xx_osm.h index 679a4fd13874..793fe19993a9 100644 --- a/drivers/scsi/aic7xxx/aic79xx_osm.h +++ b/drivers/scsi/aic7xxx/aic79xx_osm.h @@ -420,8 +420,6 @@ ahd_unlock(struct ahd_softc *ahd, unsigned long *flags) /* config registers for header type 0 devices */ #define PCIR_MAPS 0x10 -#define PCIR_SUBVEND_0 0x2c -#define PCIR_SUBDEV_0 0x2e /****************************** PCI-X definitions *****************************/ #define PCIXR_COMMAND 0x96 diff --git a/drivers/scsi/aic7xxx/aic79xx_pci.c b/drivers/scsi/aic7xxx/aic79xx_pci.c index 2f0bdb9225a4..5fad41b1ab58 100644 --- a/drivers/scsi/aic7xxx/aic79xx_pci.c +++ b/drivers/scsi/aic7xxx/aic79xx_pci.c @@ -260,8 +260,8 @@ ahd_find_pci_device(ahd_dev_softc_t pci) vendor = ahd_pci_read_config(pci, PCIR_DEVVENDOR, /*bytes*/2); device = ahd_pci_read_config(pci, PCIR_DEVICE, /*bytes*/2); - subvendor = ahd_pci_read_config(pci, PCIR_SUBVEND_0, /*bytes*/2); - subdevice = ahd_pci_read_config(pci, PCIR_SUBDEV_0, /*bytes*/2); + subvendor = ahd_pci_read_config(pci, PCI_SUBSYSTEM_VENDOR_ID, /*bytes*/2); + subdevice = ahd_pci_read_config(pci, PCI_SUBSYSTEM_ID, /*bytes*/2); full_id = ahd_compose_id(device, vendor, subdevice, @@ -298,7 +298,7 @@ ahd_pci_config(struct ahd_softc *ahd, const struct ahd_pci_identity *entry) * Record if this is an HP board. */ subvendor = ahd_pci_read_config(ahd->dev_softc, - PCIR_SUBVEND_0, /*bytes*/2); + PCI_SUBSYSTEM_VENDOR_ID, /*bytes*/2); if (subvendor == SUBID_HP) ahd->flags |= AHD_HP_BOARD; diff --git a/drivers/scsi/aic7xxx/aic7xxx_osm.h b/drivers/scsi/aic7xxx/aic7xxx_osm.h index 4782a304e93c..51d9f4de0734 100644 --- a/drivers/scsi/aic7xxx/aic7xxx_osm.h +++ b/drivers/scsi/aic7xxx/aic7xxx_osm.h @@ -433,8 +433,6 @@ ahc_unlock(struct ahc_softc *ahc, unsigned long *flags) /* config registers for header type 0 devices */ #define PCIR_MAPS 0x10 -#define PCIR_SUBVEND_0 0x2c -#define PCIR_SUBDEV_0 0x2e typedef enum { diff --git a/drivers/scsi/aic7xxx/aic7xxx_pci.c b/drivers/scsi/aic7xxx/aic7xxx_pci.c index dab3a6d12c4d..2d4c85426dc3 100644 --- a/drivers/scsi/aic7xxx/aic7xxx_pci.c +++ b/drivers/scsi/aic7xxx/aic7xxx_pci.c @@ -673,8 +673,8 @@ ahc_find_pci_device(ahc_dev_softc_t pci) vendor = ahc_pci_read_config(pci, PCIR_DEVVENDOR, /*bytes*/2); device = ahc_pci_read_config(pci, PCIR_DEVICE, /*bytes*/2); - subvendor = ahc_pci_read_config(pci, PCIR_SUBVEND_0, /*bytes*/2); - subdevice = ahc_pci_read_config(pci, PCIR_SUBDEV_0, /*bytes*/2); + subvendor = ahc_pci_read_config(pci, PCI_SUBSYSTEM_VENDOR_ID, /*bytes*/2); + subdevice = ahc_pci_read_config(pci, PCI_SUBSYSTEM_ID, /*bytes*/2); full_id = ahc_compose_id(device, vendor, subdevice, subvendor); /* diff --git a/drivers/scsi/bnx2fc/bnx2fc_hwi.c b/drivers/scsi/bnx2fc/bnx2fc_hwi.c index 0103f811cc25..776544385598 100644 --- a/drivers/scsi/bnx2fc/bnx2fc_hwi.c +++ b/drivers/scsi/bnx2fc/bnx2fc_hwi.c @@ -1169,7 +1169,7 @@ static void bnx2fc_process_ofld_cmpl(struct bnx2fc_hba *hba, ofld_kcqe->fcoe_conn_context_id); interface = tgt->port->priv; if (hba != interface->hba) { - printk(KERN_ERR PFX "ERROR:ofld_cmpl: HBA mis-match\n"); + printk(KERN_ERR PFX "ERROR:ofld_cmpl: HBA mismatch\n"); goto ofld_cmpl_err; } /* @@ -1226,12 +1226,12 @@ static void bnx2fc_process_enable_conn_cmpl(struct bnx2fc_hba *hba, * and enable */ if (tgt->context_id != context_id) { - printk(KERN_ERR PFX "context id mis-match\n"); + printk(KERN_ERR PFX "context id mismatch\n"); return; } interface = tgt->port->priv; if (hba != interface->hba) { - printk(KERN_ERR PFX "bnx2fc-enbl_cmpl: HBA mis-match\n"); + printk(KERN_ERR PFX "bnx2fc-enbl_cmpl: HBA mismatch\n"); goto enbl_cmpl_err; } if (!ofld_kcqe->completion_status) diff --git a/drivers/scsi/bnx2i/bnx2i_hwi.c b/drivers/scsi/bnx2i/bnx2i_hwi.c index 5521469ce678..6c864b093ac9 100644 --- a/drivers/scsi/bnx2i/bnx2i_hwi.c +++ b/drivers/scsi/bnx2i/bnx2i_hwi.c @@ -1977,7 +1977,7 @@ static int bnx2i_process_new_cqes(struct bnx2i_conn *bnx2i_conn) if (nopin->cq_req_sn != qp->cqe_exp_seq_sn) break; - if (unlikely(test_bit(ISCSI_SUSPEND_BIT, &conn->suspend_rx))) { + if (unlikely(test_bit(ISCSI_CONN_FLAG_SUSPEND_RX, &conn->flags))) { if (nopin->op_code == ISCSI_OP_NOOP_IN && nopin->itt == (u16) RESERVED_ITT) { printk(KERN_ALERT "bnx2i: Unsolicited " @@ -2398,7 +2398,7 @@ static void bnx2i_process_conn_destroy_cmpl(struct bnx2i_hba *hba, } if (hba != ep->hba) { - printk(KERN_ALERT "conn destroy- error hba mis-match\n"); + printk(KERN_ALERT "conn destroy- error hba mismatch\n"); return; } @@ -2432,7 +2432,7 @@ static void bnx2i_process_ofld_cmpl(struct bnx2i_hba *hba, } if (hba != ep->hba) { - printk(KERN_ALERT "ofld_cmpl: error hba mis-match\n"); + printk(KERN_ALERT "ofld_cmpl: error hba mismatch\n"); return; } diff --git a/drivers/scsi/bnx2i/bnx2i_iscsi.c b/drivers/scsi/bnx2i/bnx2i_iscsi.c index fe86fd61a995..15fbd09baa94 100644 --- a/drivers/scsi/bnx2i/bnx2i_iscsi.c +++ b/drivers/scsi/bnx2i/bnx2i_iscsi.c @@ -1721,7 +1721,7 @@ static int bnx2i_tear_down_conn(struct bnx2i_hba *hba, struct iscsi_conn *conn = ep->conn->cls_conn->dd_data; /* Must suspend all rx queue activity for this ep */ - set_bit(ISCSI_SUSPEND_BIT, &conn->suspend_rx); + set_bit(ISCSI_CONN_FLAG_SUSPEND_RX, &conn->flags); } /* CONN_DISCONNECT timeout may or may not be an issue depending * on what transcribed in TCP layer, different targets behave diff --git a/drivers/scsi/cxgbi/libcxgbi.c b/drivers/scsi/cxgbi/libcxgbi.c index 8c7d4dda4cf2..4365d52c6430 100644 --- a/drivers/scsi/cxgbi/libcxgbi.c +++ b/drivers/scsi/cxgbi/libcxgbi.c @@ -1634,11 +1634,11 @@ void cxgbi_conn_pdu_ready(struct cxgbi_sock *csk) log_debug(1 << CXGBI_DBG_PDU_RX, "csk 0x%p, conn 0x%p.\n", csk, conn); - if (unlikely(!conn || conn->suspend_rx)) { + if (unlikely(!conn || test_bit(ISCSI_CONN_FLAG_SUSPEND_RX, &conn->flags))) { log_debug(1 << CXGBI_DBG_PDU_RX, - "csk 0x%p, conn 0x%p, id %d, suspend_rx %lu!\n", + "csk 0x%p, conn 0x%p, id %d, conn flags 0x%lx!\n", csk, conn, conn ? conn->id : 0xFF, - conn ? conn->suspend_rx : 0xFF); + conn ? conn->flags : 0xFF); return; } diff --git a/drivers/scsi/device_handler/scsi_dh_alua.c b/drivers/scsi/device_handler/scsi_dh_alua.c index 37d06f993b76..1d9be771f3ee 100644 --- a/drivers/scsi/device_handler/scsi_dh_alua.c +++ b/drivers/scsi/device_handler/scsi_dh_alua.c @@ -1172,9 +1172,8 @@ static blk_status_t alua_prep_fn(struct scsi_device *sdev, struct request *req) case SCSI_ACCESS_STATE_OPTIMAL: case SCSI_ACCESS_STATE_ACTIVE: case SCSI_ACCESS_STATE_LBA: - return BLK_STS_OK; case SCSI_ACCESS_STATE_TRANSITIONING: - return BLK_STS_AGAIN; + return BLK_STS_OK; default: req->rq_flags |= RQF_QUIET; return BLK_STS_IOERR; diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c index 461ef8a76c4c..4bda2f6cb352 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_main.c +++ b/drivers/scsi/hisi_sas/hisi_sas_main.c @@ -442,7 +442,6 @@ void hisi_sas_task_deliver(struct hisi_hba *hisi_hba, case SAS_PROTOCOL_INTERNAL_ABORT: hisi_sas_task_prep_abort(hisi_hba, slot); break; - fallthrough; default: return; } diff --git a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c index 80238e6a3c98..eee1a24f7e15 100644 --- a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c +++ b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c @@ -36,7 +36,7 @@ #define IBMVSCSIS_VERSION "v0.2" -#define INITIAL_SRP_LIMIT 800 +#define INITIAL_SRP_LIMIT 1024 #define DEFAULT_MAX_SECTORS 256 #define MAX_TXU 1024 * 1024 diff --git a/drivers/scsi/isci/host.c b/drivers/scsi/isci/host.c index d690d9cf7eb1..35589b6af90d 100644 --- a/drivers/scsi/isci/host.c +++ b/drivers/scsi/isci/host.c @@ -413,7 +413,7 @@ static void sci_controller_event_completion(struct isci_host *ihost, u32 ent) dev_warn(&ihost->pdev->dev, "%s: SCIC Controller 0x%p received " "event 0x%x for io request object " - "that doesnt exist.\n", + "that doesn't exist.\n", __func__, ihost, ent); @@ -428,7 +428,7 @@ static void sci_controller_event_completion(struct isci_host *ihost, u32 ent) dev_warn(&ihost->pdev->dev, "%s: SCIC Controller 0x%p received " "event 0x%x for remote device object " - "that doesnt exist.\n", + "that doesn't exist.\n", __func__, ihost, ent); @@ -462,7 +462,7 @@ static void sci_controller_event_completion(struct isci_host *ihost, u32 ent) } else dev_err(&ihost->pdev->dev, "%s: SCIC Controller 0x%p received event 0x%x " - "for remote device object 0x%0x that doesnt " + "for remote device object 0x%0x that doesn't " "exist.\n", __func__, ihost, diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c index d09926e6c8a8..797abf4f5399 100644 --- a/drivers/scsi/libiscsi.c +++ b/drivers/scsi/libiscsi.c @@ -678,7 +678,8 @@ __iscsi_conn_send_pdu(struct iscsi_conn *conn, struct iscsi_hdr *hdr, struct iscsi_task *task; itt_t itt; - if (session->state == ISCSI_STATE_TERMINATE) + if (session->state == ISCSI_STATE_TERMINATE || + !test_bit(ISCSI_CONN_FLAG_BOUND, &conn->flags)) return NULL; if (opcode == ISCSI_OP_LOGIN || opcode == ISCSI_OP_TEXT) { @@ -1392,8 +1393,8 @@ static bool iscsi_set_conn_failed(struct iscsi_conn *conn) if (conn->stop_stage == 0) session->state = ISCSI_STATE_FAILED; - set_bit(ISCSI_SUSPEND_BIT, &conn->suspend_tx); - set_bit(ISCSI_SUSPEND_BIT, &conn->suspend_rx); + set_bit(ISCSI_CONN_FLAG_SUSPEND_TX, &conn->flags); + set_bit(ISCSI_CONN_FLAG_SUSPEND_RX, &conn->flags); return true; } @@ -1454,7 +1455,7 @@ static int iscsi_xmit_task(struct iscsi_conn *conn, struct iscsi_task *task, * Do this after dropping the extra ref because if this was a requeue * it's removed from that list and cleanup_queued_task would miss it. */ - if (test_bit(ISCSI_SUSPEND_BIT, &conn->suspend_tx)) { + if (test_bit(ISCSI_CONN_FLAG_SUSPEND_TX, &conn->flags)) { /* * Save the task and ref in case we weren't cleaning up this * task and get woken up again. @@ -1532,7 +1533,7 @@ static int iscsi_data_xmit(struct iscsi_conn *conn) int rc = 0; spin_lock_bh(&conn->session->frwd_lock); - if (test_bit(ISCSI_SUSPEND_BIT, &conn->suspend_tx)) { + if (test_bit(ISCSI_CONN_FLAG_SUSPEND_TX, &conn->flags)) { ISCSI_DBG_SESSION(conn->session, "Tx suspended!\n"); spin_unlock_bh(&conn->session->frwd_lock); return -ENODATA; @@ -1746,7 +1747,7 @@ int iscsi_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *sc) goto fault; } - if (test_bit(ISCSI_SUSPEND_BIT, &conn->suspend_tx)) { + if (test_bit(ISCSI_CONN_FLAG_SUSPEND_TX, &conn->flags)) { reason = FAILURE_SESSION_IN_RECOVERY; sc->result = DID_REQUEUE << 16; goto fault; @@ -1935,7 +1936,7 @@ static void fail_scsi_tasks(struct iscsi_conn *conn, u64 lun, int error) void iscsi_suspend_queue(struct iscsi_conn *conn) { spin_lock_bh(&conn->session->frwd_lock); - set_bit(ISCSI_SUSPEND_BIT, &conn->suspend_tx); + set_bit(ISCSI_CONN_FLAG_SUSPEND_TX, &conn->flags); spin_unlock_bh(&conn->session->frwd_lock); } EXPORT_SYMBOL_GPL(iscsi_suspend_queue); @@ -1953,7 +1954,7 @@ void iscsi_suspend_tx(struct iscsi_conn *conn) struct Scsi_Host *shost = conn->session->host; struct iscsi_host *ihost = shost_priv(shost); - set_bit(ISCSI_SUSPEND_BIT, &conn->suspend_tx); + set_bit(ISCSI_CONN_FLAG_SUSPEND_TX, &conn->flags); if (ihost->workq) flush_workqueue(ihost->workq); } @@ -1961,7 +1962,7 @@ EXPORT_SYMBOL_GPL(iscsi_suspend_tx); static void iscsi_start_tx(struct iscsi_conn *conn) { - clear_bit(ISCSI_SUSPEND_BIT, &conn->suspend_tx); + clear_bit(ISCSI_CONN_FLAG_SUSPEND_TX, &conn->flags); iscsi_conn_queue_work(conn); } @@ -2214,6 +2215,8 @@ void iscsi_conn_unbind(struct iscsi_cls_conn *cls_conn, bool is_active) iscsi_suspend_tx(conn); spin_lock_bh(&session->frwd_lock); + clear_bit(ISCSI_CONN_FLAG_BOUND, &conn->flags); + if (!is_active) { /* * if logout timed out before userspace could even send a PDU @@ -3045,7 +3048,6 @@ iscsi_conn_setup(struct iscsi_cls_session *cls_session, int dd_size, if (!cls_conn) return NULL; conn = cls_conn->dd_data; - memset(conn, 0, sizeof(*conn) + dd_size); conn->dd_data = cls_conn->dd_data + sizeof(*conn); conn->session = session; @@ -3318,6 +3320,8 @@ int iscsi_conn_bind(struct iscsi_cls_session *cls_session, spin_lock_bh(&session->frwd_lock); if (is_leading) session->leadconn = conn; + + set_bit(ISCSI_CONN_FLAG_BOUND, &conn->flags); spin_unlock_bh(&session->frwd_lock); /* @@ -3330,8 +3334,8 @@ int iscsi_conn_bind(struct iscsi_cls_session *cls_session, /* * Unblock xmitworker(), Login Phase will pass through. */ - clear_bit(ISCSI_SUSPEND_BIT, &conn->suspend_rx); - clear_bit(ISCSI_SUSPEND_BIT, &conn->suspend_tx); + clear_bit(ISCSI_CONN_FLAG_SUSPEND_RX, &conn->flags); + clear_bit(ISCSI_CONN_FLAG_SUSPEND_TX, &conn->flags); return 0; } EXPORT_SYMBOL_GPL(iscsi_conn_bind); diff --git a/drivers/scsi/libiscsi_tcp.c b/drivers/scsi/libiscsi_tcp.c index 2e9ffe3d1a55..883005757ddb 100644 --- a/drivers/scsi/libiscsi_tcp.c +++ b/drivers/scsi/libiscsi_tcp.c @@ -927,7 +927,7 @@ int iscsi_tcp_recv_skb(struct iscsi_conn *conn, struct sk_buff *skb, */ conn->last_recv = jiffies; - if (unlikely(conn->suspend_rx)) { + if (unlikely(test_bit(ISCSI_CONN_FLAG_SUSPEND_RX, &conn->flags))) { ISCSI_DBG_TCP(conn, "Rx suspended!\n"); *status = ISCSI_TCP_SUSPENDED; return 0; diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h index f0cf8ffdc5f3..0025760230e5 100644 --- a/drivers/scsi/lpfc/lpfc.h +++ b/drivers/scsi/lpfc/lpfc.h @@ -897,6 +897,11 @@ enum lpfc_irq_chann_mode { NHT_MODE, }; +enum lpfc_hba_bit_flags { + FABRIC_COMANDS_BLOCKED, + HBA_PCI_ERR, +}; + struct lpfc_hba { /* SCSI interface function jump table entries */ struct lpfc_io_buf * (*lpfc_get_scsi_buf) @@ -1043,7 +1048,6 @@ struct lpfc_hba { * Firmware supports Forced Link Speed * capability */ -#define HBA_PCI_ERR 0x80000 /* The PCI slot is offline */ #define HBA_FLOGI_ISSUED 0x100000 /* FLOGI was issued */ #define HBA_SHORT_CMF 0x200000 /* shorter CMF timer routine */ #define HBA_CGN_DAY_WRAP 0x400000 /* HBA Congestion info day wraps */ @@ -1350,7 +1354,6 @@ struct lpfc_hba { atomic_t fabric_iocb_count; struct timer_list fabric_block_timer; unsigned long bit_flags; -#define FABRIC_COMANDS_BLOCKED 0 atomic_t num_rsrc_err; atomic_t num_cmd_success; unsigned long last_rsrc_error_time; diff --git a/drivers/scsi/lpfc/lpfc_crtn.h b/drivers/scsi/lpfc/lpfc_crtn.h index 96408cd6c4c8..9897a1aa387b 100644 --- a/drivers/scsi/lpfc/lpfc_crtn.h +++ b/drivers/scsi/lpfc/lpfc_crtn.h @@ -670,3 +670,6 @@ struct lpfc_vmid *lpfc_get_vmid_from_hashtable(struct lpfc_vport *vport, uint32_t hash, uint8_t *buf); void lpfc_vmid_vport_cleanup(struct lpfc_vport *vport); int lpfc_issue_els_qfpa(struct lpfc_vport *vport); + +void lpfc_sli_rpi_release(struct lpfc_vport *vport, + struct lpfc_nodelist *ndlp); diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c index ef6e8cd8c26a..872a26376ccb 100644 --- a/drivers/scsi/lpfc/lpfc_els.c +++ b/drivers/scsi/lpfc/lpfc_els.c @@ -1330,7 +1330,7 @@ lpfc_issue_els_flogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp, if (bf_get(lpfc_sli_intf_if_type, &phba->sli4_hba.sli_intf) == LPFC_SLI_INTF_IF_TYPE_0) { /* FLOGI needs to be 3 for WQE FCFI */ - ct = ((SLI4_CT_FCFI >> 1) & 1) | (SLI4_CT_FCFI & 1); + ct = SLI4_CT_FCFI; bf_set(wqe_ct, &wqe->els_req.wqe_com, ct); /* Set the fcfi to the fcfi we registered with */ diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c index 0144da30e3db..2b877dff5ed4 100644 --- a/drivers/scsi/lpfc/lpfc_hbadisc.c +++ b/drivers/scsi/lpfc/lpfc_hbadisc.c @@ -109,8 +109,8 @@ lpfc_rport_invalid(struct fc_rport *rport) ndlp = rdata->pnode; if (!rdata->pnode) { - pr_err("**** %s: NULL ndlp on rport x%px SID x%x\n", - __func__, rport, rport->scsi_target_id); + pr_info("**** %s: NULL ndlp on rport x%px SID x%x\n", + __func__, rport, rport->scsi_target_id); return -EINVAL; } @@ -169,9 +169,10 @@ lpfc_dev_loss_tmo_callbk(struct fc_rport *rport) lpfc_printf_vlog(ndlp->vport, KERN_INFO, LOG_NODE, "3181 dev_loss_callbk x%06x, rport x%px flg x%x " - "load_flag x%x refcnt %d\n", + "load_flag x%x refcnt %d state %d xpt x%x\n", ndlp->nlp_DID, ndlp->rport, ndlp->nlp_flag, - vport->load_flag, kref_read(&ndlp->kref)); + vport->load_flag, kref_read(&ndlp->kref), + ndlp->nlp_state, ndlp->fc4_xpt_flags); /* Don't schedule a worker thread event if the vport is going down. * The teardown process cleans up the node via lpfc_drop_node. @@ -181,6 +182,11 @@ lpfc_dev_loss_tmo_callbk(struct fc_rport *rport) ndlp->rport = NULL; ndlp->fc4_xpt_flags &= ~SCSI_XPT_REGD; + /* clear the NLP_XPT_REGD if the node is not registered + * with nvme-fc + */ + if (ndlp->fc4_xpt_flags == NLP_XPT_REGD) + ndlp->fc4_xpt_flags &= ~NLP_XPT_REGD; /* Remove the node reference from remote_port_add now. * The driver will not call remote_port_delete. @@ -225,18 +231,36 @@ lpfc_dev_loss_tmo_callbk(struct fc_rport *rport) ndlp->rport = NULL; spin_unlock_irqrestore(&ndlp->lock, iflags); - /* We need to hold the node by incrementing the reference - * count until this queued work is done - */ - evtp->evt_arg1 = lpfc_nlp_get(ndlp); + if (phba->worker_thread) { + /* We need to hold the node by incrementing the reference + * count until this queued work is done + */ + evtp->evt_arg1 = lpfc_nlp_get(ndlp); + + spin_lock_irqsave(&phba->hbalock, iflags); + if (evtp->evt_arg1) { + evtp->evt = LPFC_EVT_DEV_LOSS; + list_add_tail(&evtp->evt_listp, &phba->work_list); + lpfc_worker_wake_up(phba); + } + spin_unlock_irqrestore(&phba->hbalock, iflags); + } else { + lpfc_printf_vlog(ndlp->vport, KERN_INFO, LOG_NODE, + "3188 worker thread is stopped %s x%06x, " + " rport x%px flg x%x load_flag x%x refcnt " + "%d\n", __func__, ndlp->nlp_DID, + ndlp->rport, ndlp->nlp_flag, + vport->load_flag, kref_read(&ndlp->kref)); + if (!(ndlp->fc4_xpt_flags & NVME_XPT_REGD)) { + spin_lock_irqsave(&ndlp->lock, iflags); + /* Node is in dev loss. No further transaction. */ + ndlp->nlp_flag &= ~NLP_IN_DEV_LOSS; + spin_unlock_irqrestore(&ndlp->lock, iflags); + lpfc_disc_state_machine(vport, ndlp, NULL, + NLP_EVT_DEVICE_RM); + } - spin_lock_irqsave(&phba->hbalock, iflags); - if (evtp->evt_arg1) { - evtp->evt = LPFC_EVT_DEV_LOSS; - list_add_tail(&evtp->evt_listp, &phba->work_list); - lpfc_worker_wake_up(phba); } - spin_unlock_irqrestore(&phba->hbalock, iflags); return; } @@ -503,11 +527,12 @@ lpfc_dev_loss_tmo_handler(struct lpfc_nodelist *ndlp) lpfc_printf_vlog(vport, KERN_ERR, LOG_TRACE_EVENT, "0203 Devloss timeout on " "WWPN %02x:%02x:%02x:%02x:%02x:%02x:%02x:%02x " - "NPort x%06x Data: x%x x%x x%x\n", + "NPort x%06x Data: x%x x%x x%x refcnt %d\n", *name, *(name+1), *(name+2), *(name+3), *(name+4), *(name+5), *(name+6), *(name+7), ndlp->nlp_DID, ndlp->nlp_flag, - ndlp->nlp_state, ndlp->nlp_rpi); + ndlp->nlp_state, ndlp->nlp_rpi, + kref_read(&ndlp->kref)); } else { lpfc_printf_vlog(vport, KERN_INFO, LOG_TRACE_EVENT, "0204 Devloss timeout on " @@ -755,18 +780,22 @@ lpfc_work_list_done(struct lpfc_hba *phba) int free_evt; int fcf_inuse; uint32_t nlp_did; + bool hba_pci_err; spin_lock_irq(&phba->hbalock); while (!list_empty(&phba->work_list)) { list_remove_head((&phba->work_list), evtp, typeof(*evtp), evt_listp); spin_unlock_irq(&phba->hbalock); + hba_pci_err = test_bit(HBA_PCI_ERR, &phba->bit_flags); free_evt = 1; switch (evtp->evt) { case LPFC_EVT_ELS_RETRY: ndlp = (struct lpfc_nodelist *) (evtp->evt_arg1); - lpfc_els_retry_delay_handler(ndlp); - free_evt = 0; /* evt is part of ndlp */ + if (!hba_pci_err) { + lpfc_els_retry_delay_handler(ndlp); + free_evt = 0; /* evt is part of ndlp */ + } /* decrement the node reference count held * for this queued work */ @@ -788,8 +817,10 @@ lpfc_work_list_done(struct lpfc_hba *phba) break; case LPFC_EVT_RECOVER_PORT: ndlp = (struct lpfc_nodelist *)(evtp->evt_arg1); - lpfc_sli_abts_recover_port(ndlp->vport, ndlp); - free_evt = 0; + if (!hba_pci_err) { + lpfc_sli_abts_recover_port(ndlp->vport, ndlp); + free_evt = 0; + } /* decrement the node reference count held for * this queued work */ @@ -859,14 +890,18 @@ lpfc_work_done(struct lpfc_hba *phba) struct lpfc_vport **vports; struct lpfc_vport *vport; int i; + bool hba_pci_err; + hba_pci_err = test_bit(HBA_PCI_ERR, &phba->bit_flags); spin_lock_irq(&phba->hbalock); ha_copy = phba->work_ha; phba->work_ha = 0; spin_unlock_irq(&phba->hbalock); + if (hba_pci_err) + ha_copy = 0; /* First, try to post the next mailbox command to SLI4 device */ - if (phba->pci_dev_grp == LPFC_PCI_DEV_OC) + if (phba->pci_dev_grp == LPFC_PCI_DEV_OC && !hba_pci_err) lpfc_sli4_post_async_mbox(phba); if (ha_copy & HA_ERATT) { @@ -886,7 +921,7 @@ lpfc_work_done(struct lpfc_hba *phba) lpfc_handle_latt(phba); /* Handle VMID Events */ - if (lpfc_is_vmid_enabled(phba)) { + if (lpfc_is_vmid_enabled(phba) && !hba_pci_err) { if (phba->pport->work_port_events & WORKER_CHECK_VMID_ISSUE_QFPA) { lpfc_check_vmid_qfpa_issue(phba); @@ -936,6 +971,8 @@ lpfc_work_done(struct lpfc_hba *phba) work_port_events = vport->work_port_events; vport->work_port_events &= ~work_port_events; spin_unlock_irq(&vport->work_port_lock); + if (hba_pci_err) + continue; if (work_port_events & WORKER_DISC_TMO) lpfc_disc_timeout_handler(vport); if (work_port_events & WORKER_ELS_TMO) @@ -1173,12 +1210,14 @@ lpfc_linkdown(struct lpfc_hba *phba) struct lpfc_vport **vports; LPFC_MBOXQ_t *mb; int i; + int offline; if (phba->link_state == LPFC_LINK_DOWN) return 0; /* Block all SCSI stack I/Os */ lpfc_scsi_dev_block(phba); + offline = pci_channel_offline(phba->pcidev); phba->defer_flogi_acc_flag = false; @@ -1219,7 +1258,7 @@ lpfc_linkdown(struct lpfc_hba *phba) lpfc_destroy_vport_work_array(phba, vports); /* Clean up any SLI3 firmware default rpi's */ - if (phba->sli_rev > LPFC_SLI_REV3) + if (phba->sli_rev > LPFC_SLI_REV3 || offline) goto skip_unreg_did; mb = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL); @@ -4712,6 +4751,11 @@ lpfc_nlp_unreg_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) spin_lock_irqsave(&ndlp->lock, iflags); if (!(ndlp->fc4_xpt_flags & NLP_XPT_REGD)) { spin_unlock_irqrestore(&ndlp->lock, iflags); + lpfc_printf_vlog(vport, KERN_INFO, LOG_SLI, + "0999 %s Not regd: ndlp x%px rport x%px DID " + "x%x FLG x%x XPT x%x\n", + __func__, ndlp, ndlp->rport, ndlp->nlp_DID, + ndlp->nlp_flag, ndlp->fc4_xpt_flags); return; } @@ -4722,6 +4766,13 @@ lpfc_nlp_unreg_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) ndlp->fc4_xpt_flags & SCSI_XPT_REGD) { vport->phba->nport_event_cnt++; lpfc_unregister_remote_port(ndlp); + } else if (!ndlp->rport) { + lpfc_printf_vlog(vport, KERN_INFO, LOG_SLI, + "1999 %s NDLP in devloss x%px DID x%x FLG x%x" + " XPT x%x refcnt %d\n", + __func__, ndlp, ndlp->nlp_DID, ndlp->nlp_flag, + ndlp->fc4_xpt_flags, + kref_read(&ndlp->kref)); } if (ndlp->fc4_xpt_flags & NVME_XPT_REGD) { @@ -5371,6 +5422,7 @@ lpfc_unreg_rpi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) ndlp->nlp_flag &= ~NLP_UNREG_INP; mempool_free(mbox, phba->mbox_mem_pool); acc_plogi = 1; + lpfc_nlp_put(ndlp); } } else { lpfc_printf_vlog(vport, KERN_INFO, @@ -6097,12 +6149,34 @@ lpfc_disc_flush_list(struct lpfc_vport *vport) } } +/* + * lpfc_notify_xport_npr - notifies xport of node disappearance + * @vport: Pointer to Virtual Port object. + * + * Transitions all ndlps to NPR state. When lpfc_nlp_set_state + * calls lpfc_nlp_state_cleanup, the ndlp->rport is unregistered + * and transport notified that the node is gone. + * Return Code: + * none + */ +static void +lpfc_notify_xport_npr(struct lpfc_vport *vport) +{ + struct lpfc_nodelist *ndlp, *next_ndlp; + + list_for_each_entry_safe(ndlp, next_ndlp, &vport->fc_nodes, + nlp_listp) { + lpfc_nlp_set_state(vport, ndlp, NLP_STE_NPR_NODE); + } +} void lpfc_cleanup_discovery_resources(struct lpfc_vport *vport) { lpfc_els_flush_rscn(vport); lpfc_els_flush_cmd(vport); lpfc_disc_flush_list(vport); + if (pci_channel_offline(vport->phba->pcidev)) + lpfc_notify_xport_npr(vport); } /*****************************************************************************/ diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c index eed6464bd880..461d333b1b3a 100644 --- a/drivers/scsi/lpfc/lpfc_init.c +++ b/drivers/scsi/lpfc/lpfc_init.c @@ -95,6 +95,7 @@ static void lpfc_sli4_oas_verify(struct lpfc_hba *phba); static uint16_t lpfc_find_cpu_handle(struct lpfc_hba *, uint16_t, int); static void lpfc_setup_bg(struct lpfc_hba *, struct Scsi_Host *); static int lpfc_sli4_cgn_parm_chg_evt(struct lpfc_hba *); +static void lpfc_sli4_prep_dev_for_reset(struct lpfc_hba *phba); static struct scsi_transport_template *lpfc_transport_template = NULL; static struct scsi_transport_template *lpfc_vport_transport_template = NULL; @@ -1642,7 +1643,7 @@ lpfc_sli4_offline_eratt(struct lpfc_hba *phba) { spin_lock_irq(&phba->hbalock); if (phba->link_state == LPFC_HBA_ERROR && - phba->hba_flag & HBA_PCI_ERR) { + test_bit(HBA_PCI_ERR, &phba->bit_flags)) { spin_unlock_irq(&phba->hbalock); return; } @@ -1985,6 +1986,7 @@ lpfc_handle_eratt_s4(struct lpfc_hba *phba) if (pci_channel_offline(phba->pcidev)) { lpfc_printf_log(phba, KERN_ERR, LOG_TRACE_EVENT, "3166 pci channel is offline\n"); + lpfc_sli_flush_io_rings(phba); return; } @@ -2973,6 +2975,22 @@ lpfc_cleanup(struct lpfc_vport *vport) NLP_EVT_DEVICE_RM); } + /* This is a special case flush to return all + * IOs before entering this loop. There are + * two points in the code where a flush is + * avoided if the FC_UNLOADING flag is set. + * one is in the multipool destroy, + * (this prevents a crash) and the other is + * in the nvme abort handler, ( also prevents + * a crash). Both of these exceptions are + * cases where the slot is still accessible. + * The flush here is only when the pci slot + * is offline. + */ + if (vport->load_flag & FC_UNLOADING && + pci_channel_offline(phba->pcidev)) + lpfc_sli_flush_io_rings(vport->phba); + /* At this point, ALL ndlp's should be gone * because of the previous NLP_EVT_DEVICE_RM. * Lets wait for this to happen, if needed. @@ -2985,7 +3003,7 @@ lpfc_cleanup(struct lpfc_vport *vport) list_for_each_entry_safe(ndlp, next_ndlp, &vport->fc_nodes, nlp_listp) { lpfc_printf_vlog(ndlp->vport, KERN_ERR, - LOG_TRACE_EVENT, + LOG_DISCOVERY, "0282 did:x%x ndlp:x%px " "refcnt:%d xflags x%x nflag x%x\n", ndlp->nlp_DID, (void *)ndlp, @@ -3682,7 +3700,8 @@ lpfc_offline_prep(struct lpfc_hba *phba, int mbx_action) struct lpfc_vport **vports; struct Scsi_Host *shost; int i; - int offline = 0; + int offline; + bool hba_pci_err; if (vport->fc_flag & FC_OFFLINE_MODE) return; @@ -3692,6 +3711,7 @@ lpfc_offline_prep(struct lpfc_hba *phba, int mbx_action) lpfc_linkdown(phba); offline = pci_channel_offline(phba->pcidev); + hba_pci_err = test_bit(HBA_PCI_ERR, &phba->bit_flags); /* Issue an unreg_login to all nodes on all vports */ vports = lpfc_create_vport_work_array(phba); @@ -3715,11 +3735,14 @@ lpfc_offline_prep(struct lpfc_hba *phba, int mbx_action) ndlp->nlp_flag &= ~NLP_NPR_ADISC; spin_unlock_irq(&ndlp->lock); - if (offline) { + if (offline || hba_pci_err) { spin_lock_irq(&ndlp->lock); ndlp->nlp_flag &= ~(NLP_UNREG_INP | NLP_RPI_REGISTERED); spin_unlock_irq(&ndlp->lock); + if (phba->sli_rev == LPFC_SLI_REV4) + lpfc_sli_rpi_release(vports[i], + ndlp); } else { lpfc_unreg_rpi(vports[i], ndlp); } @@ -13354,8 +13377,9 @@ lpfc_sli4_hba_unset(struct lpfc_hba *phba) /* Abort all iocbs associated with the hba */ lpfc_sli_hba_iocb_abort(phba); - /* Wait for completion of device XRI exchange busy */ - lpfc_sli4_xri_exchange_busy_wait(phba); + if (!pci_channel_offline(phba->pcidev)) + /* Wait for completion of device XRI exchange busy */ + lpfc_sli4_xri_exchange_busy_wait(phba); /* per-phba callback de-registration for hotplug event */ if (phba->pport) @@ -13374,15 +13398,12 @@ lpfc_sli4_hba_unset(struct lpfc_hba *phba) /* Disable FW logging to host memory */ lpfc_ras_stop_fwlog(phba); - /* Unset the queues shared with the hardware then release all - * allocated resources. - */ - lpfc_sli4_queue_unset(phba); - lpfc_sli4_queue_destroy(phba); - /* Reset SLI4 HBA FCoE function */ lpfc_pci_function_reset(phba); + /* release all queue allocated resources. */ + lpfc_sli4_queue_destroy(phba); + /* Free RAS DMA memory */ if (phba->ras_fwlog.ras_enabled) lpfc_sli4_ras_dma_free(phba); @@ -14262,6 +14283,7 @@ lpfc_sli_prep_dev_for_perm_failure(struct lpfc_hba *phba) "2711 PCI channel permanent disable for failure\n"); /* Block all SCSI devices' I/Os on the host */ lpfc_scsi_dev_block(phba); + lpfc_sli4_prep_dev_for_reset(phba); /* stop all timers */ lpfc_stop_hba_timers(phba); @@ -15057,24 +15079,28 @@ lpfc_sli4_prep_dev_for_recover(struct lpfc_hba *phba) static void lpfc_sli4_prep_dev_for_reset(struct lpfc_hba *phba) { - lpfc_printf_log(phba, KERN_ERR, LOG_TRACE_EVENT, - "2826 PCI channel disable preparing for reset\n"); + int offline = pci_channel_offline(phba->pcidev); + + lpfc_printf_log(phba, KERN_ERR, LOG_INIT, + "2826 PCI channel disable preparing for reset offline" + " %d\n", offline); /* Block any management I/Os to the device */ lpfc_block_mgmt_io(phba, LPFC_MBX_NO_WAIT); - /* Block all SCSI devices' I/Os on the host */ - lpfc_scsi_dev_block(phba); + /* HBA_PCI_ERR was set in io_error_detect */ + lpfc_offline_prep(phba, LPFC_MBX_NO_WAIT); /* Flush all driver's outstanding I/Os as we are to reset */ lpfc_sli_flush_io_rings(phba); + lpfc_offline(phba); /* stop all timers */ lpfc_stop_hba_timers(phba); + lpfc_sli4_queue_destroy(phba); /* Disable interrupt and pci device */ lpfc_sli4_disable_intr(phba); - lpfc_sli4_queue_destroy(phba); pci_disable_device(phba->pcidev); } @@ -15123,6 +15149,7 @@ lpfc_io_error_detected_s4(struct pci_dev *pdev, pci_channel_state_t state) { struct Scsi_Host *shost = pci_get_drvdata(pdev); struct lpfc_hba *phba = ((struct lpfc_vport *)shost->hostdata)->phba; + bool hba_pci_err; switch (state) { case pci_channel_io_normal: @@ -15130,17 +15157,24 @@ lpfc_io_error_detected_s4(struct pci_dev *pdev, pci_channel_state_t state) lpfc_sli4_prep_dev_for_recover(phba); return PCI_ERS_RESULT_CAN_RECOVER; case pci_channel_io_frozen: - phba->hba_flag |= HBA_PCI_ERR; + hba_pci_err = test_and_set_bit(HBA_PCI_ERR, &phba->bit_flags); /* Fatal error, prepare for slot reset */ - lpfc_sli4_prep_dev_for_reset(phba); + if (!hba_pci_err) + lpfc_sli4_prep_dev_for_reset(phba); + else + lpfc_printf_log(phba, KERN_ERR, LOG_INIT, + "2832 Already handling PCI error " + "state: x%x\n", state); return PCI_ERS_RESULT_NEED_RESET; case pci_channel_io_perm_failure: - phba->hba_flag |= HBA_PCI_ERR; + set_bit(HBA_PCI_ERR, &phba->bit_flags); /* Permanent failure, prepare for device down */ lpfc_sli4_prep_dev_for_perm_failure(phba); return PCI_ERS_RESULT_DISCONNECT; default: - phba->hba_flag |= HBA_PCI_ERR; + hba_pci_err = test_and_set_bit(HBA_PCI_ERR, &phba->bit_flags); + if (!hba_pci_err) + lpfc_sli4_prep_dev_for_reset(phba); /* Unknown state, prepare and request slot reset */ lpfc_printf_log(phba, KERN_ERR, LOG_TRACE_EVENT, "2825 Unknown PCI error state: x%x\n", state); @@ -15174,17 +15208,21 @@ lpfc_io_slot_reset_s4(struct pci_dev *pdev) struct lpfc_hba *phba = ((struct lpfc_vport *)shost->hostdata)->phba; struct lpfc_sli *psli = &phba->sli; uint32_t intr_mode; + bool hba_pci_err; dev_printk(KERN_INFO, &pdev->dev, "recovering from a slot reset.\n"); if (pci_enable_device_mem(pdev)) { printk(KERN_ERR "lpfc: Cannot re-enable " - "PCI device after reset.\n"); + "PCI device after reset.\n"); return PCI_ERS_RESULT_DISCONNECT; } pci_restore_state(pdev); - phba->hba_flag &= ~HBA_PCI_ERR; + hba_pci_err = test_and_clear_bit(HBA_PCI_ERR, &phba->bit_flags); + if (!hba_pci_err) + dev_info(&pdev->dev, + "hba_pci_err was not set, recovering slot reset.\n"); /* * As the new kernel behavior of pci_restore_state() API call clears * device saved_state flag, need to save the restored state again. @@ -15198,6 +15236,8 @@ lpfc_io_slot_reset_s4(struct pci_dev *pdev) psli->sli_flag &= ~LPFC_SLI_ACTIVE; spin_unlock_irq(&phba->hbalock); + /* Init cpu_map array */ + lpfc_cpu_map_array_init(phba); /* Configure and enable interrupt */ intr_mode = lpfc_sli4_enable_intr(phba, phba->intr_mode); if (intr_mode == LPFC_INTR_ERROR) { @@ -15239,8 +15279,6 @@ lpfc_io_resume_s4(struct pci_dev *pdev) */ if (!(phba->sli.sli_flag & LPFC_SLI_ACTIVE)) { /* Perform device reset */ - lpfc_offline_prep(phba, LPFC_MBX_WAIT); - lpfc_offline(phba); lpfc_sli_brdrestart(phba); /* Bring the device back online */ lpfc_online(phba); diff --git a/drivers/scsi/lpfc/lpfc_nvme.c b/drivers/scsi/lpfc/lpfc_nvme.c index 1213a299f9aa..8d26f207ebd2 100644 --- a/drivers/scsi/lpfc/lpfc_nvme.c +++ b/drivers/scsi/lpfc/lpfc_nvme.c @@ -93,6 +93,11 @@ lpfc_nvme_create_queue(struct nvme_fc_local_port *pnvme_lport, lport = (struct lpfc_nvme_lport *)pnvme_lport->private; vport = lport->vport; + + if (!vport || vport->load_flag & FC_UNLOADING || + vport->phba->hba_flag & HBA_IOQ_FLUSH) + return -ENODEV; + qhandle = kzalloc(sizeof(struct lpfc_nvme_qhandle), GFP_KERNEL); if (qhandle == NULL) return -ENOMEM; @@ -267,7 +272,8 @@ lpfc_nvme_handle_lsreq(struct lpfc_hba *phba, return -EINVAL; remoteport = lpfc_rport->remoteport; - if (!vport->localport) + if (!vport->localport || + vport->phba->hba_flag & HBA_IOQ_FLUSH) return -EINVAL; lport = vport->localport->private; @@ -559,6 +565,8 @@ __lpfc_nvme_ls_req(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp, ndlp->nlp_DID, ntype, nstate); return -ENODEV; } + if (vport->phba->hba_flag & HBA_IOQ_FLUSH) + return -ENODEV; if (!vport->phba->sli4_hba.nvmels_wq) return -ENOMEM; @@ -662,7 +670,8 @@ lpfc_nvme_ls_req(struct nvme_fc_local_port *pnvme_lport, return -EINVAL; vport = lport->vport; - if (vport->load_flag & FC_UNLOADING) + if (vport->load_flag & FC_UNLOADING || + vport->phba->hba_flag & HBA_IOQ_FLUSH) return -ENODEV; atomic_inc(&lport->fc4NvmeLsRequests); @@ -1516,7 +1525,8 @@ lpfc_nvme_fcp_io_submit(struct nvme_fc_local_port *pnvme_lport, phba = vport->phba; - if (unlikely(vport->load_flag & FC_UNLOADING)) { + if ((unlikely(vport->load_flag & FC_UNLOADING)) || + phba->hba_flag & HBA_IOQ_FLUSH) { lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME_IOERR, "6124 Fail IO, Driver unload\n"); atomic_inc(&lport->xmt_fcp_err); @@ -2169,8 +2179,7 @@ lpfc_nvme_lport_unreg_wait(struct lpfc_vport *vport, abts_nvme = 0; for (i = 0; i < phba->cfg_hdw_queue; i++) { qp = &phba->sli4_hba.hdwq[i]; - if (!vport || !vport->localport || - !qp || !qp->io_wq) + if (!vport->localport || !qp || !qp->io_wq) return; pring = qp->io_wq->pring; @@ -2180,8 +2189,9 @@ lpfc_nvme_lport_unreg_wait(struct lpfc_vport *vport, abts_scsi += qp->abts_scsi_io_bufs; abts_nvme += qp->abts_nvme_io_bufs; } - if (!vport || !vport->localport || - vport->phba->hba_flag & HBA_PCI_ERR) + if (!vport->localport || + test_bit(HBA_PCI_ERR, &vport->phba->bit_flags) || + vport->load_flag & FC_UNLOADING) return; lpfc_printf_vlog(vport, KERN_ERR, LOG_TRACE_EVENT, @@ -2541,8 +2551,7 @@ lpfc_nvme_unregister_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) * return values is ignored. The upcall is a courtesy to the * transport. */ - if (vport->load_flag & FC_UNLOADING || - unlikely(vport->phba->hba_flag & HBA_PCI_ERR)) + if (vport->load_flag & FC_UNLOADING) (void)nvme_fc_set_remoteport_devloss(remoteport, 0); ret = nvme_fc_unregister_remoteport(remoteport); diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c index 3c132604fd91..f6b83853f7ee 100644 --- a/drivers/scsi/lpfc/lpfc_scsi.c +++ b/drivers/scsi/lpfc/lpfc_scsi.c @@ -5528,7 +5528,9 @@ static char *lpfc_is_command_vm_io(struct scsi_cmnd *cmd) { struct bio *bio = scsi_cmd_to_rq(cmd)->bio; - return bio ? blkcg_get_fc_appid(bio) : NULL; + if (!IS_ENABLED(CONFIG_BLK_CGROUP_FC_APPID) || !bio) + return NULL; + return blkcg_get_fc_appid(bio); } /** @@ -5929,13 +5931,15 @@ lpfc_abort_handler(struct scsi_cmnd *cmnd) } lpfc_cmd->waitq = &waitq; - if (phba->sli_rev == LPFC_SLI_REV4) + if (phba->sli_rev == LPFC_SLI_REV4) { spin_unlock(&pring_s4->ring_lock); - else + ret_val = lpfc_sli4_issue_abort_iotag(phba, iocb, + lpfc_sli_abort_fcp_cmpl); + } else { pring = &phba->sli.sli3_ring[LPFC_FCP_RING]; - - ret_val = lpfc_sli_issue_abort_iotag(phba, pring, iocb, - lpfc_sli_abort_fcp_cmpl); + ret_val = lpfc_sli_issue_abort_iotag(phba, pring, iocb, + lpfc_sli_abort_fcp_cmpl); + } /* Make sure HBA is alive */ lpfc_issue_hb_tmo(phba); diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c index 20d40957a385..6adaf79e67cc 100644 --- a/drivers/scsi/lpfc/lpfc_sli.c +++ b/drivers/scsi/lpfc/lpfc_sli.c @@ -2828,6 +2828,12 @@ __lpfc_sli_rpi_release(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) ndlp->nlp_flag &= ~NLP_UNREG_INP; } +void +lpfc_sli_rpi_release(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) +{ + __lpfc_sli_rpi_release(vport, ndlp); +} + /** * lpfc_sli_def_mbox_cmpl - Default mailbox completion handler * @phba: Pointer to HBA context object. @@ -3715,7 +3721,15 @@ lpfc_sli_process_sol_iocb(struct lpfc_hba *phba, struct lpfc_sli_ring *pring, unsigned long iflag; u32 ulp_command, ulp_status, ulp_word4, ulp_context, iotag; + if (phba->sli_rev == LPFC_SLI_REV4) + spin_lock_irqsave(&pring->ring_lock, iflag); + else + spin_lock_irqsave(&phba->hbalock, iflag); cmdiocbp = lpfc_sli_iocbq_lookup(phba, pring, saveq); + if (phba->sli_rev == LPFC_SLI_REV4) + spin_unlock_irqrestore(&pring->ring_lock, iflag); + else + spin_unlock_irqrestore(&phba->hbalock, iflag); ulp_command = get_job_cmnd(phba, saveq); ulp_status = get_job_ulpstatus(phba, saveq); @@ -4052,10 +4066,8 @@ lpfc_sli_handle_fast_ring_event(struct lpfc_hba *phba, break; } - spin_unlock_irqrestore(&phba->hbalock, iflag); cmdiocbq = lpfc_sli_iocbq_lookup(phba, pring, &rspiocbq); - spin_lock_irqsave(&phba->hbalock, iflag); if (unlikely(!cmdiocbq)) break; if (cmdiocbq->cmd_flag & LPFC_DRIVER_ABORTED) @@ -4536,42 +4548,62 @@ lpfc_sli_handle_slow_ring_event_s4(struct lpfc_hba *phba, void lpfc_sli_abort_iocb_ring(struct lpfc_hba *phba, struct lpfc_sli_ring *pring) { - LIST_HEAD(completions); + LIST_HEAD(tx_completions); + LIST_HEAD(txcmplq_completions); struct lpfc_iocbq *iocb, *next_iocb; + int offline; if (pring->ringno == LPFC_ELS_RING) { lpfc_fabric_abort_hba(phba); } + offline = pci_channel_offline(phba->pcidev); /* Error everything on txq and txcmplq * First do the txq. */ if (phba->sli_rev >= LPFC_SLI_REV4) { spin_lock_irq(&pring->ring_lock); - list_splice_init(&pring->txq, &completions); + list_splice_init(&pring->txq, &tx_completions); pring->txq_cnt = 0; - spin_unlock_irq(&pring->ring_lock); - spin_lock_irq(&phba->hbalock); - /* Next issue ABTS for everything on the txcmplq */ - list_for_each_entry_safe(iocb, next_iocb, &pring->txcmplq, list) - lpfc_sli_issue_abort_iotag(phba, pring, iocb, NULL); - spin_unlock_irq(&phba->hbalock); + if (offline) { + list_splice_init(&pring->txcmplq, + &txcmplq_completions); + } else { + /* Next issue ABTS for everything on the txcmplq */ + list_for_each_entry_safe(iocb, next_iocb, + &pring->txcmplq, list) + lpfc_sli_issue_abort_iotag(phba, pring, + iocb, NULL); + } + spin_unlock_irq(&pring->ring_lock); } else { spin_lock_irq(&phba->hbalock); - list_splice_init(&pring->txq, &completions); + list_splice_init(&pring->txq, &tx_completions); pring->txq_cnt = 0; - /* Next issue ABTS for everything on the txcmplq */ - list_for_each_entry_safe(iocb, next_iocb, &pring->txcmplq, list) - lpfc_sli_issue_abort_iotag(phba, pring, iocb, NULL); + if (offline) { + list_splice_init(&pring->txcmplq, &txcmplq_completions); + } else { + /* Next issue ABTS for everything on the txcmplq */ + list_for_each_entry_safe(iocb, next_iocb, + &pring->txcmplq, list) + lpfc_sli_issue_abort_iotag(phba, pring, + iocb, NULL); + } spin_unlock_irq(&phba->hbalock); } - /* Make sure HBA is alive */ - lpfc_issue_hb_tmo(phba); + if (offline) { + /* Cancel all the IOCBs from the completions list */ + lpfc_sli_cancel_iocbs(phba, &txcmplq_completions, + IOSTAT_LOCAL_REJECT, IOERR_SLI_ABORTED); + } else { + /* Make sure HBA is alive */ + lpfc_issue_hb_tmo(phba); + } /* Cancel all the IOCBs from the completions list */ - lpfc_sli_cancel_iocbs(phba, &completions, IOSTAT_LOCAL_REJECT, + lpfc_sli_cancel_iocbs(phba, &tx_completions, IOSTAT_LOCAL_REJECT, IOERR_SLI_ABORTED); } @@ -4624,11 +4656,6 @@ lpfc_sli_flush_io_rings(struct lpfc_hba *phba) struct lpfc_iocbq *piocb, *next_iocb; spin_lock_irq(&phba->hbalock); - if (phba->hba_flag & HBA_IOQ_FLUSH || - !phba->sli4_hba.hdwq) { - spin_unlock_irq(&phba->hbalock); - return; - } /* Indicate the I/O queues are flushed */ phba->hba_flag |= HBA_IOQ_FLUSH; spin_unlock_irq(&phba->hbalock); @@ -10693,10 +10720,10 @@ __lpfc_sli_prep_gen_req_s4(struct lpfc_iocbq *cmdiocbq, struct lpfc_dmabuf *bmp, /* Words 0 - 2 */ bde = (struct ulp_bde64_le *)&cmdwqe->generic.bde; - bde->addr_low = cpu_to_le32(putPaddrLow(bmp->phys)); - bde->addr_high = cpu_to_le32(putPaddrHigh(bmp->phys)); + bde->addr_low = bpl->addr_low; + bde->addr_high = bpl->addr_high; bde->type_size = cpu_to_le32(xmit_len); - bde->type_size |= cpu_to_le32(ULP_BDE64_TYPE_BLP_64); + bde->type_size |= cpu_to_le32(ULP_BDE64_TYPE_BDE_64); /* Word 3 */ cmdwqe->gen_req.request_payload_len = xmit_len; @@ -10997,6 +11024,10 @@ lpfc_sli_issue_iocb(struct lpfc_hba *phba, uint32_t ring_number, unsigned long iflags; int rc; + /* If the PCI channel is in offline state, do not post iocbs. */ + if (unlikely(pci_channel_offline(phba->pcidev))) + return IOCB_ERROR; + if (phba->sli_rev == LPFC_SLI_REV4) { lpfc_sli_prep_wqe(phba, piocb); diff --git a/drivers/scsi/lpfc/lpfc_version.h b/drivers/scsi/lpfc/lpfc_version.h index e52f37e5d896..a4d3259b8c52 100644 --- a/drivers/scsi/lpfc/lpfc_version.h +++ b/drivers/scsi/lpfc/lpfc_version.h @@ -20,7 +20,7 @@ * included with this package. * *******************************************************************/ -#define LPFC_DRIVER_VERSION "14.2.0.0" +#define LPFC_DRIVER_VERSION "14.2.0.1" #define LPFC_DRIVER_NAME "lpfc" /* Used for SLI 2/3 */ diff --git a/drivers/scsi/megaraid/megaraid_sas.h b/drivers/scsi/megaraid/megaraid_sas.h index 611871ef15b5..4919ea54b827 100644 --- a/drivers/scsi/megaraid/megaraid_sas.h +++ b/drivers/scsi/megaraid/megaraid_sas.h @@ -2560,6 +2560,9 @@ struct megasas_instance_template { #define MEGASAS_IS_LOGICAL(sdev) \ ((sdev->channel < MEGASAS_MAX_PD_CHANNELS) ? 0 : 1) +#define MEGASAS_IS_LUN_VALID(sdev) \ + (((sdev)->lun == 0) ? 1 : 0) + #define MEGASAS_DEV_INDEX(scp) \ (((scp->device->channel % 2) * MEGASAS_MAX_DEV_PER_CHANNEL) + \ scp->device->id) diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c index 8bf72dbc33b7..db6793608447 100644 --- a/drivers/scsi/megaraid/megaraid_sas_base.c +++ b/drivers/scsi/megaraid/megaraid_sas_base.c @@ -2126,6 +2126,9 @@ static int megasas_slave_alloc(struct scsi_device *sdev) goto scan_target; } return -ENXIO; + } else if (!MEGASAS_IS_LUN_VALID(sdev)) { + sdev_printk(KERN_INFO, sdev, "%s: invalid LUN\n", __func__); + return -ENXIO; } scan_target: @@ -2156,6 +2159,10 @@ static void megasas_slave_destroy(struct scsi_device *sdev) instance = megasas_lookup_instance(sdev->host->host_no); if (MEGASAS_IS_LOGICAL(sdev)) { + if (!MEGASAS_IS_LUN_VALID(sdev)) { + sdev_printk(KERN_INFO, sdev, "%s: invalid LUN\n", __func__); + return; + } ld_tgt_id = MEGASAS_TARGET_ID(sdev); instance->ld_tgtid_status[ld_tgt_id] = LD_TARGET_ID_DELETED; if (megasas_dbg_lvl & LD_PD_DEBUG) diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index b57f1803371e..538d2c0cd971 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -5716,13 +5716,12 @@ _base_release_memory_pools(struct MPT3SAS_ADAPTER *ioc) /** * mpt3sas_check_same_4gb_region - checks whether all reply queues in a set are * having same upper 32bits in their base memory address. - * @reply_pool_start_address: Base address of a reply queue set + * @start_address: Base address of a reply queue set * @pool_sz: Size of single Reply Descriptor Post Queues pool size * * Return: 1 if reply queues in a set have a same upper 32bits in their base * memory address, else 0. */ - static int mpt3sas_check_same_4gb_region(dma_addr_t start_address, u32 pool_sz) { diff --git a/drivers/scsi/mpt3sas/mpt3sas_config.c b/drivers/scsi/mpt3sas/mpt3sas_config.c index 0563078227de..a8dd14c91efd 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_config.c +++ b/drivers/scsi/mpt3sas/mpt3sas_config.c @@ -394,10 +394,13 @@ _config_request(struct MPT3SAS_ADAPTER *ioc, Mpi2ConfigRequest_t retry_count++; if (ioc->config_cmds.smid == smid) mpt3sas_base_free_smid(ioc, smid); - if ((ioc->shost_recovery) || (ioc->config_cmds.status & - MPT3_CMD_RESET) || ioc->pci_error_recovery) + if (ioc->config_cmds.status & MPT3_CMD_RESET) goto retry_config; - issue_host_reset = 1; + if (ioc->shost_recovery || ioc->pci_error_recovery) { + issue_host_reset = 0; + r = -EFAULT; + } else + issue_host_reset = 1; goto free_mem; } diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c index 00792767c620..7e476f50935b 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c +++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c @@ -11035,6 +11035,7 @@ _scsih_expander_node_remove(struct MPT3SAS_ADAPTER *ioc, { struct _sas_port *mpt3sas_port, *next; unsigned long flags; + int port_id; /* remove sibling ports attached to this expander */ list_for_each_entry_safe(mpt3sas_port, next, @@ -11055,6 +11056,8 @@ _scsih_expander_node_remove(struct MPT3SAS_ADAPTER *ioc, mpt3sas_port->hba_port); } + port_id = sas_expander->port->port_id; + mpt3sas_transport_port_remove(ioc, sas_expander->sas_address, sas_expander->sas_address_parent, sas_expander->port); @@ -11062,7 +11065,7 @@ _scsih_expander_node_remove(struct MPT3SAS_ADAPTER *ioc, "expander_remove: handle(0x%04x), sas_addr(0x%016llx), port:%d\n", sas_expander->handle, (unsigned long long) sas_expander->sas_address, - sas_expander->port->port_id); + port_id); spin_lock_irqsave(&ioc->sas_node_lock, flags); list_del(&sas_expander->list); diff --git a/drivers/scsi/mvsas/mv_init.c b/drivers/scsi/mvsas/mv_init.c index 7ac63eb5ccd3..2fde496fff5f 100644 --- a/drivers/scsi/mvsas/mv_init.c +++ b/drivers/scsi/mvsas/mv_init.c @@ -647,6 +647,7 @@ static struct pci_device_id mvs_pci_table[] = { { PCI_VDEVICE(ARECA, PCI_DEVICE_ID_ARECA_1300), chip_1300 }, { PCI_VDEVICE(ARECA, PCI_DEVICE_ID_ARECA_1320), chip_1320 }, { PCI_VDEVICE(ADAPTEC2, 0x0450), chip_6440 }, + { PCI_VDEVICE(TTI, 0x2640), chip_6440 }, { PCI_VDEVICE(TTI, 0x2710), chip_9480 }, { PCI_VDEVICE(TTI, 0x2720), chip_9480 }, { PCI_VDEVICE(TTI, 0x2721), chip_9480 }, diff --git a/drivers/scsi/pcmcia/sym53c500_cs.c b/drivers/scsi/pcmcia/sym53c500_cs.c index c4a838635893..5d7dfefd6f6c 100644 --- a/drivers/scsi/pcmcia/sym53c500_cs.c +++ b/drivers/scsi/pcmcia/sym53c500_cs.c @@ -192,10 +192,11 @@ struct sym53c500_data { int fast_pio; }; -static struct scsi_pointer *sym53c500_scsi_pointer(struct scsi_cmnd *cmd) -{ - return scsi_cmd_priv(cmd); -} +struct sym53c500_cmd_priv { + int status; + int message; + int phase; +}; enum Phase { idle, @@ -356,7 +357,7 @@ SYM53C500_intr(int irq, void *dev_id) struct sym53c500_data *data = (struct sym53c500_data *)dev->hostdata; struct scsi_cmnd *curSC = data->current_SC; - struct scsi_pointer *scsi_pointer = sym53c500_scsi_pointer(curSC); + struct sym53c500_cmd_priv *scp = scsi_cmd_priv(curSC); int fast_pio = data->fast_pio; spin_lock_irqsave(dev->host_lock, flags); @@ -403,12 +404,11 @@ SYM53C500_intr(int irq, void *dev_id) if (int_reg & 0x20) { /* Disconnect */ DEB(printk("SYM53C500: disconnect intr received\n")); - if (scsi_pointer->phase != message_in) { /* Unexpected disconnect */ + if (scp->phase != message_in) { /* Unexpected disconnect */ curSC->result = DID_NO_CONNECT << 16; } else { /* Command complete, return status and message */ - curSC->result = (scsi_pointer->Status & 0xff) | - ((scsi_pointer->Message & 0xff) << 8) | - (DID_OK << 16); + curSC->result = (scp->status & 0xff) | + ((scp->message & 0xff) << 8) | (DID_OK << 16); } goto idle_out; } @@ -419,7 +419,7 @@ SYM53C500_intr(int irq, void *dev_id) struct scatterlist *sg; int i; - scsi_pointer->phase = data_out; + scp->phase = data_out; VDEB(printk("SYM53C500: Data-Out phase\n")); outb(FLUSH_FIFO, port_base + CMD_REG); LOAD_DMA_COUNT(port_base, scsi_bufflen(curSC)); /* Max transfer size */ @@ -438,7 +438,7 @@ SYM53C500_intr(int irq, void *dev_id) struct scatterlist *sg; int i; - scsi_pointer->phase = data_in; + scp->phase = data_in; VDEB(printk("SYM53C500: Data-In phase\n")); outb(FLUSH_FIFO, port_base + CMD_REG); LOAD_DMA_COUNT(port_base, scsi_bufflen(curSC)); /* Max transfer size */ @@ -453,12 +453,12 @@ SYM53C500_intr(int irq, void *dev_id) break; case 0x02: /* COMMAND */ - scsi_pointer->phase = command_ph; + scp->phase = command_ph; printk("SYM53C500: Warning: Unknown interrupt occurred in command phase!\n"); break; case 0x03: /* STATUS */ - scsi_pointer->phase = status_ph; + scp->phase = status_ph; VDEB(printk("SYM53C500: Status phase\n")); outb(FLUSH_FIFO, port_base + CMD_REG); outb(INIT_CMD_COMPLETE, port_base + CMD_REG); @@ -471,24 +471,22 @@ SYM53C500_intr(int irq, void *dev_id) case 0x06: /* MESSAGE-OUT */ DEB(printk("SYM53C500: Message-Out phase\n")); - scsi_pointer->phase = message_out; + scp->phase = message_out; outb(SET_ATN, port_base + CMD_REG); /* Reject the message */ outb(MSG_ACCEPT, port_base + CMD_REG); break; case 0x07: /* MESSAGE-IN */ VDEB(printk("SYM53C500: Message-In phase\n")); - scsi_pointer->phase = message_in; + scp->phase = message_in; - scsi_pointer->Status = inb(port_base + SCSI_FIFO); - scsi_pointer->Message = inb(port_base + SCSI_FIFO); + scp->status = inb(port_base + SCSI_FIFO); + scp->message = inb(port_base + SCSI_FIFO); VDEB(printk("SCSI FIFO size=%d\n", inb(port_base + FIFO_FLAGS) & 0x1f)); - DEB(printk("Status = %02x Message = %02x\n", - scsi_pointer->Status, scsi_pointer->Message)); + DEB(printk("Status = %02x Message = %02x\n", scp->status, scp->message)); - if (scsi_pointer->Message == SAVE_POINTERS || - scsi_pointer->Message == DISCONNECT) { + if (scp->message == SAVE_POINTERS || scp->message == DISCONNECT) { outb(SET_ATN, port_base + CMD_REG); /* Reject message */ DEB(printk("Discarding SAVE_POINTERS message\n")); } @@ -500,7 +498,7 @@ out: return IRQ_HANDLED; idle_out: - scsi_pointer->phase = idle; + scp->phase = idle; scsi_done(curSC); goto out; } @@ -548,7 +546,7 @@ SYM53C500_info(struct Scsi_Host *SChost) static int SYM53C500_queue_lck(struct scsi_cmnd *SCpnt) { - struct scsi_pointer *scsi_pointer = sym53c500_scsi_pointer(SCpnt); + struct sym53c500_cmd_priv *scp = scsi_cmd_priv(SCpnt); int i; int port_base = SCpnt->device->host->io_port; struct sym53c500_data *data = @@ -565,9 +563,9 @@ static int SYM53C500_queue_lck(struct scsi_cmnd *SCpnt) VDEB(printk("\n")); data->current_SC = SCpnt; - scsi_pointer->phase = command_ph; - scsi_pointer->Status = 0; - scsi_pointer->Message = 0; + scp->phase = command_ph; + scp->status = 0; + scp->message = 0; /* We are locked here already by the mid layer */ REG0(port_base); @@ -682,7 +680,7 @@ static struct scsi_host_template sym53c500_driver_template = { .this_id = 7, .sg_tablesize = 32, .shost_groups = SYM53C500_shost_groups, - .cmd_size = sizeof(struct scsi_pointer), + .cmd_size = sizeof(struct sym53c500_cmd_priv), }; static int SYM53C500_config_check(struct pcmcia_device *p_dev, void *priv_data) diff --git a/drivers/scsi/pm8001/pm80xx_hwi.c b/drivers/scsi/pm8001/pm80xx_hwi.c index f90b707c190b..01c5e8ff4cc5 100644 --- a/drivers/scsi/pm8001/pm80xx_hwi.c +++ b/drivers/scsi/pm8001/pm80xx_hwi.c @@ -766,6 +766,10 @@ static void init_default_table_values(struct pm8001_hba_info *pm8001_ha) pm8001_ha->main_cfg_tbl.pm80xx_tbl.pcs_event_log_severity = 0x01; pm8001_ha->main_cfg_tbl.pm80xx_tbl.fatal_err_interrupt = 0x01; + /* Enable higher IQs and OQs, 32 to 63, bit 16 */ + if (pm8001_ha->max_q_num > 32) + pm8001_ha->main_cfg_tbl.pm80xx_tbl.fatal_err_interrupt |= + 1 << 16; /* Disable end to end CRC checking */ pm8001_ha->main_cfg_tbl.pm80xx_tbl.crc_core_dump = (0x1 << 16); @@ -1027,6 +1031,13 @@ static int mpi_init_check(struct pm8001_hba_info *pm8001_ha) if (0x0000 != gst_len_mpistate) return -EBUSY; + /* + * As per controller datasheet, after successful MPI + * initialization minimum 500ms delay is required before + * issuing commands. + */ + msleep(500); + return 0; } @@ -1727,10 +1738,11 @@ static void pm80xx_chip_interrupt_enable(struct pm8001_hba_info *pm8001_ha, u8 vec) { #ifdef PM8001_USE_MSIX - u32 mask; - mask = (u32)(1 << vec); - - pm8001_cw32(pm8001_ha, 0, MSGU_ODMR_CLR, (u32)(mask & 0xFFFFFFFF)); + if (vec < 32) + pm8001_cw32(pm8001_ha, 0, MSGU_ODMR_CLR, 1U << vec); + else + pm8001_cw32(pm8001_ha, 0, MSGU_ODMR_CLR_U, + 1U << (vec - 32)); return; #endif pm80xx_chip_intx_interrupt_enable(pm8001_ha); @@ -1746,12 +1758,15 @@ static void pm80xx_chip_interrupt_disable(struct pm8001_hba_info *pm8001_ha, u8 vec) { #ifdef PM8001_USE_MSIX - u32 mask; - if (vec == 0xFF) - mask = 0xFFFFFFFF; + if (vec == 0xFF) { + /* disable all vectors 0-31, 32-63 */ + pm8001_cw32(pm8001_ha, 0, MSGU_ODMR, 0xFFFFFFFF); + pm8001_cw32(pm8001_ha, 0, MSGU_ODMR_U, 0xFFFFFFFF); + } else if (vec < 32) + pm8001_cw32(pm8001_ha, 0, MSGU_ODMR, 1U << vec); else - mask = (u32)(1 << vec); - pm8001_cw32(pm8001_ha, 0, MSGU_ODMR, (u32)(mask & 0xFFFFFFFF)); + pm8001_cw32(pm8001_ha, 0, MSGU_ODMR_U, + 1U << (vec - 32)); return; #endif pm80xx_chip_intx_interrupt_disable(pm8001_ha); diff --git a/drivers/scsi/pmcraid.c b/drivers/scsi/pmcraid.c index 928532180d32..fd674ed1febe 100644 --- a/drivers/scsi/pmcraid.c +++ b/drivers/scsi/pmcraid.c @@ -3182,124 +3182,6 @@ static int pmcraid_build_ioadl( } /** - * pmcraid_free_sglist - Frees an allocated SG buffer list - * @sglist: scatter/gather list pointer - * - * Free a DMA'able memory previously allocated with pmcraid_alloc_sglist - * - * Return value: - * none - */ -static void pmcraid_free_sglist(struct pmcraid_sglist *sglist) -{ - sgl_free_order(sglist->scatterlist, sglist->order); - kfree(sglist); -} - -/** - * pmcraid_alloc_sglist - Allocates memory for a SG list - * @buflen: buffer length - * - * Allocates a DMA'able buffer in chunks and assembles a scatter/gather - * list. - * - * Return value - * pointer to sglist / NULL on failure - */ -static struct pmcraid_sglist *pmcraid_alloc_sglist(int buflen) -{ - struct pmcraid_sglist *sglist; - int sg_size; - int order; - - sg_size = buflen / (PMCRAID_MAX_IOADLS - 1); - order = (sg_size > 0) ? get_order(sg_size) : 0; - - /* Allocate a scatter/gather list for the DMA */ - sglist = kzalloc(sizeof(struct pmcraid_sglist), GFP_KERNEL); - if (sglist == NULL) - return NULL; - - sglist->order = order; - sgl_alloc_order(buflen, order, false, GFP_KERNEL | __GFP_ZERO, - &sglist->num_sg); - - return sglist; -} - -/** - * pmcraid_copy_sglist - Copy user buffer to kernel buffer's SG list - * @sglist: scatter/gather list pointer - * @buffer: buffer pointer - * @len: buffer length - * @direction: data transfer direction - * - * Copy a user buffer into a buffer allocated by pmcraid_alloc_sglist - * - * Return value: - * 0 on success / other on failure - */ -static int pmcraid_copy_sglist( - struct pmcraid_sglist *sglist, - void __user *buffer, - u32 len, - int direction -) -{ - struct scatterlist *sg; - void *kaddr; - int bsize_elem; - int i; - int rc = 0; - - /* Determine the actual number of bytes per element */ - bsize_elem = PAGE_SIZE * (1 << sglist->order); - - sg = sglist->scatterlist; - - for (i = 0; i < (len / bsize_elem); i++, sg = sg_next(sg), buffer += bsize_elem) { - struct page *page = sg_page(sg); - - kaddr = kmap(page); - if (direction == DMA_TO_DEVICE) - rc = copy_from_user(kaddr, buffer, bsize_elem); - else - rc = copy_to_user(buffer, kaddr, bsize_elem); - - kunmap(page); - - if (rc) { - pmcraid_err("failed to copy user data into sg list\n"); - return -EFAULT; - } - - sg->length = bsize_elem; - } - - if (len % bsize_elem) { - struct page *page = sg_page(sg); - - kaddr = kmap(page); - - if (direction == DMA_TO_DEVICE) - rc = copy_from_user(kaddr, buffer, len % bsize_elem); - else - rc = copy_to_user(buffer, kaddr, len % bsize_elem); - - kunmap(page); - - sg->length = len % bsize_elem; - } - - if (rc) { - pmcraid_err("failed to copy user data into sg list\n"); - rc = -EFAULT; - } - - return rc; -} - -/** * pmcraid_queuecommand_lck - Queue a mid-layer request * @scsi_cmd: scsi command struct * @@ -3454,365 +3336,6 @@ static int pmcraid_chr_fasync(int fd, struct file *filep, int mode) return rc; } - -/** - * pmcraid_build_passthrough_ioadls - builds SG elements for passthrough - * commands sent over IOCTL interface - * - * @cmd : pointer to struct pmcraid_cmd - * @buflen : length of the request buffer - * @direction : data transfer direction - * - * Return value - * 0 on success, non-zero error code on failure - */ -static int pmcraid_build_passthrough_ioadls( - struct pmcraid_cmd *cmd, - int buflen, - int direction -) -{ - struct pmcraid_sglist *sglist = NULL; - struct scatterlist *sg = NULL; - struct pmcraid_ioarcb *ioarcb = &cmd->ioa_cb->ioarcb; - struct pmcraid_ioadl_desc *ioadl; - int i; - - sglist = pmcraid_alloc_sglist(buflen); - - if (!sglist) { - pmcraid_err("can't allocate memory for passthrough SGls\n"); - return -ENOMEM; - } - - sglist->num_dma_sg = dma_map_sg(&cmd->drv_inst->pdev->dev, - sglist->scatterlist, - sglist->num_sg, direction); - - if (!sglist->num_dma_sg || sglist->num_dma_sg > PMCRAID_MAX_IOADLS) { - dev_err(&cmd->drv_inst->pdev->dev, - "Failed to map passthrough buffer!\n"); - pmcraid_free_sglist(sglist); - return -EIO; - } - - cmd->sglist = sglist; - ioarcb->request_flags0 |= NO_LINK_DESCS; - - ioadl = pmcraid_init_ioadls(cmd, sglist->num_dma_sg); - - /* Initialize IOADL descriptor addresses */ - for_each_sg(sglist->scatterlist, sg, sglist->num_dma_sg, i) { - ioadl[i].data_len = cpu_to_le32(sg_dma_len(sg)); - ioadl[i].address = cpu_to_le64(sg_dma_address(sg)); - ioadl[i].flags = 0; - } - - /* setup the last descriptor */ - ioadl[i - 1].flags = IOADL_FLAGS_LAST_DESC; - - return 0; -} - - -/** - * pmcraid_release_passthrough_ioadls - release passthrough ioadls - * - * @cmd: pointer to struct pmcraid_cmd for which ioadls were allocated - * @buflen: size of the request buffer - * @direction: data transfer direction - * - * Return value - * 0 on success, non-zero error code on failure - */ -static void pmcraid_release_passthrough_ioadls( - struct pmcraid_cmd *cmd, - int buflen, - int direction -) -{ - struct pmcraid_sglist *sglist = cmd->sglist; - - if (buflen > 0) { - dma_unmap_sg(&cmd->drv_inst->pdev->dev, - sglist->scatterlist, - sglist->num_sg, - direction); - pmcraid_free_sglist(sglist); - cmd->sglist = NULL; - } -} - -/** - * pmcraid_ioctl_passthrough - handling passthrough IOCTL commands - * - * @pinstance: pointer to adapter instance structure - * @ioctl_cmd: ioctl code - * @buflen: unused - * @arg: pointer to pmcraid_passthrough_buffer user buffer - * - * Return value - * 0 on success, non-zero error code on failure - */ -static long pmcraid_ioctl_passthrough( - struct pmcraid_instance *pinstance, - unsigned int ioctl_cmd, - unsigned int buflen, - void __user *arg -) -{ - struct pmcraid_passthrough_ioctl_buffer *buffer; - struct pmcraid_ioarcb *ioarcb; - struct pmcraid_cmd *cmd; - struct pmcraid_cmd *cancel_cmd; - void __user *request_buffer; - unsigned long request_offset; - unsigned long lock_flags; - void __user *ioasa; - u32 ioasc; - int request_size; - int buffer_size; - u8 direction; - int rc = 0; - - /* If IOA reset is in progress, wait 10 secs for reset to complete */ - if (pinstance->ioa_reset_in_progress) { - rc = wait_event_interruptible_timeout( - pinstance->reset_wait_q, - !pinstance->ioa_reset_in_progress, - msecs_to_jiffies(10000)); - - if (!rc) - return -ETIMEDOUT; - else if (rc < 0) - return -ERESTARTSYS; - } - - /* If adapter is not in operational state, return error */ - if (pinstance->ioa_state != IOA_STATE_OPERATIONAL) { - pmcraid_err("IOA is not operational\n"); - return -ENOTTY; - } - - buffer_size = sizeof(struct pmcraid_passthrough_ioctl_buffer); - buffer = kmalloc(buffer_size, GFP_KERNEL); - - if (!buffer) { - pmcraid_err("no memory for passthrough buffer\n"); - return -ENOMEM; - } - - request_offset = - offsetof(struct pmcraid_passthrough_ioctl_buffer, request_buffer); - - request_buffer = arg + request_offset; - - rc = copy_from_user(buffer, arg, - sizeof(struct pmcraid_passthrough_ioctl_buffer)); - - ioasa = arg + offsetof(struct pmcraid_passthrough_ioctl_buffer, ioasa); - - if (rc) { - pmcraid_err("ioctl: can't copy passthrough buffer\n"); - rc = -EFAULT; - goto out_free_buffer; - } - - request_size = le32_to_cpu(buffer->ioarcb.data_transfer_length); - - if (buffer->ioarcb.request_flags0 & TRANSFER_DIR_WRITE) { - direction = DMA_TO_DEVICE; - } else { - direction = DMA_FROM_DEVICE; - } - - if (request_size < 0) { - rc = -EINVAL; - goto out_free_buffer; - } - - /* check if we have any additional command parameters */ - if (le16_to_cpu(buffer->ioarcb.add_cmd_param_length) - > PMCRAID_ADD_CMD_PARAM_LEN) { - rc = -EINVAL; - goto out_free_buffer; - } - - cmd = pmcraid_get_free_cmd(pinstance); - - if (!cmd) { - pmcraid_err("free command block is not available\n"); - rc = -ENOMEM; - goto out_free_buffer; - } - - cmd->scsi_cmd = NULL; - ioarcb = &(cmd->ioa_cb->ioarcb); - - /* Copy the user-provided IOARCB stuff field by field */ - ioarcb->resource_handle = buffer->ioarcb.resource_handle; - ioarcb->data_transfer_length = buffer->ioarcb.data_transfer_length; - ioarcb->cmd_timeout = buffer->ioarcb.cmd_timeout; - ioarcb->request_type = buffer->ioarcb.request_type; - ioarcb->request_flags0 = buffer->ioarcb.request_flags0; - ioarcb->request_flags1 = buffer->ioarcb.request_flags1; - memcpy(ioarcb->cdb, buffer->ioarcb.cdb, PMCRAID_MAX_CDB_LEN); - - if (buffer->ioarcb.add_cmd_param_length) { - ioarcb->add_cmd_param_length = - buffer->ioarcb.add_cmd_param_length; - ioarcb->add_cmd_param_offset = - buffer->ioarcb.add_cmd_param_offset; - memcpy(ioarcb->add_data.u.add_cmd_params, - buffer->ioarcb.add_data.u.add_cmd_params, - le16_to_cpu(buffer->ioarcb.add_cmd_param_length)); - } - - /* set hrrq number where the IOA should respond to. Note that all cmds - * generated internally uses hrrq_id 0, exception to this is the cmd - * block of scsi_cmd which is re-used (e.g. cancel/abort), which uses - * hrrq_id assigned here in queuecommand - */ - ioarcb->hrrq_id = atomic_add_return(1, &(pinstance->last_message_id)) % - pinstance->num_hrrq; - - if (request_size) { - rc = pmcraid_build_passthrough_ioadls(cmd, - request_size, - direction); - if (rc) { - pmcraid_err("couldn't build passthrough ioadls\n"); - goto out_free_cmd; - } - } - - /* If data is being written into the device, copy the data from user - * buffers - */ - if (direction == DMA_TO_DEVICE && request_size > 0) { - rc = pmcraid_copy_sglist(cmd->sglist, - request_buffer, - request_size, - direction); - if (rc) { - pmcraid_err("failed to copy user buffer\n"); - goto out_free_sglist; - } - } - - /* passthrough ioctl is a blocking command so, put the user to sleep - * until timeout. Note that a timeout value of 0 means, do timeout. - */ - cmd->cmd_done = pmcraid_internal_done; - init_completion(&cmd->wait_for_completion); - cmd->completion_req = 1; - - pmcraid_info("command(%d) (CDB[0] = %x) for %x\n", - le32_to_cpu(cmd->ioa_cb->ioarcb.response_handle) >> 2, - cmd->ioa_cb->ioarcb.cdb[0], - le32_to_cpu(cmd->ioa_cb->ioarcb.resource_handle)); - - spin_lock_irqsave(pinstance->host->host_lock, lock_flags); - _pmcraid_fire_command(cmd); - spin_unlock_irqrestore(pinstance->host->host_lock, lock_flags); - - /* NOTE ! Remove the below line once abort_task is implemented - * in firmware. This line disables ioctl command timeout handling logic - * similar to IO command timeout handling, making ioctl commands to wait - * until the command completion regardless of timeout value specified in - * ioarcb - */ - buffer->ioarcb.cmd_timeout = 0; - - /* If command timeout is specified put caller to wait till that time, - * otherwise it would be blocking wait. If command gets timed out, it - * will be aborted. - */ - if (buffer->ioarcb.cmd_timeout == 0) { - wait_for_completion(&cmd->wait_for_completion); - } else if (!wait_for_completion_timeout( - &cmd->wait_for_completion, - msecs_to_jiffies(le16_to_cpu(buffer->ioarcb.cmd_timeout) * 1000))) { - - pmcraid_info("aborting cmd %d (CDB[0] = %x) due to timeout\n", - le32_to_cpu(cmd->ioa_cb->ioarcb.response_handle) >> 2, - cmd->ioa_cb->ioarcb.cdb[0]); - - spin_lock_irqsave(pinstance->host->host_lock, lock_flags); - cancel_cmd = pmcraid_abort_cmd(cmd); - spin_unlock_irqrestore(pinstance->host->host_lock, lock_flags); - - if (cancel_cmd) { - wait_for_completion(&cancel_cmd->wait_for_completion); - ioasc = le32_to_cpu(cancel_cmd->ioa_cb->ioasa.ioasc); - pmcraid_return_cmd(cancel_cmd); - - /* if abort task couldn't find the command i.e it got - * completed prior to aborting, return good completion. - * if command got aborted successfully or there was IOA - * reset due to abort task itself getting timedout then - * return -ETIMEDOUT - */ - if (ioasc == PMCRAID_IOASC_IOA_WAS_RESET || - PMCRAID_IOASC_SENSE_KEY(ioasc) == 0x00) { - if (ioasc != PMCRAID_IOASC_GC_IOARCB_NOTFOUND) - rc = -ETIMEDOUT; - goto out_handle_response; - } - } - - /* no command block for abort task or abort task failed to abort - * the IOARCB, then wait for 150 more seconds and initiate reset - * sequence after timeout - */ - if (!wait_for_completion_timeout( - &cmd->wait_for_completion, - msecs_to_jiffies(150 * 1000))) { - pmcraid_reset_bringup(cmd->drv_inst); - rc = -ETIMEDOUT; - } - } - -out_handle_response: - /* copy entire IOASA buffer and return IOCTL success. - * If copying IOASA to user-buffer fails, return - * EFAULT - */ - if (copy_to_user(ioasa, &cmd->ioa_cb->ioasa, - sizeof(struct pmcraid_ioasa))) { - pmcraid_err("failed to copy ioasa buffer to user\n"); - rc = -EFAULT; - } - - /* If the data transfer was from device, copy the data onto user - * buffers - */ - else if (direction == DMA_FROM_DEVICE && request_size > 0) { - rc = pmcraid_copy_sglist(cmd->sglist, - request_buffer, - request_size, - direction); - if (rc) { - pmcraid_err("failed to copy user buffer\n"); - rc = -EFAULT; - } - } - -out_free_sglist: - pmcraid_release_passthrough_ioadls(cmd, request_size, direction); - -out_free_cmd: - pmcraid_return_cmd(cmd); - -out_free_buffer: - kfree(buffer); - - return rc; -} - - - - /** * pmcraid_ioctl_driver - ioctl handler for commands handled by driver itself * @@ -3922,20 +3445,6 @@ static long pmcraid_chr_ioctl( switch (_IOC_TYPE(cmd)) { - case PMCRAID_PASSTHROUGH_IOCTL: - /* If ioctl code is to download microcode, we need to block - * mid-layer requests. - */ - if (cmd == PMCRAID_IOCTL_DOWNLOAD_MICROCODE) - scsi_block_requests(pinstance->host); - - retval = pmcraid_ioctl_passthrough(pinstance, cmd, - hdr->buffer_length, argp); - - if (cmd == PMCRAID_IOCTL_DOWNLOAD_MICROCODE) - scsi_unblock_requests(pinstance->host); - break; - case PMCRAID_DRIVER_IOCTL: arg += sizeof(struct pmcraid_ioctl_header); retval = pmcraid_ioctl_driver(pinstance, cmd, diff --git a/drivers/scsi/pmcraid.h b/drivers/scsi/pmcraid.h index bbb75318f1e7..9f59930e8b4f 100644 --- a/drivers/scsi/pmcraid.h +++ b/drivers/scsi/pmcraid.h @@ -1023,40 +1023,15 @@ struct pmcraid_ioctl_header { #define PMCRAID_IOCTL_SIGNATURE "PMCRAID" /* - * pmcraid_passthrough_ioctl_buffer - structure given as argument to - * passthrough(or firmware handled) IOCTL commands. Note that ioarcb requires - * 32-byte alignment so, it is necessary to pack this structure to avoid any - * holes between ioctl_header and passthrough buffer - * - * .ioactl_header : ioctl header - * .ioarcb : filled-up ioarcb buffer, driver always reads this buffer - * .ioasa : buffer for ioasa, driver fills this with IOASA from firmware - * .request_buffer: The I/O buffer (flat), driver reads/writes to this based on - * the transfer directions passed in ioarcb.flags0. Contents - * of this buffer are valid only when ioarcb.data_transfer_len - * is not zero. - */ -struct pmcraid_passthrough_ioctl_buffer { - struct pmcraid_ioctl_header ioctl_header; - struct pmcraid_ioarcb ioarcb; - struct pmcraid_ioasa ioasa; - u8 request_buffer[]; -} __attribute__ ((packed, aligned(PMCRAID_IOARCB_ALIGNMENT))); - -/* * keys to differentiate between driver handled IOCTLs and passthrough * IOCTLs passed to IOA. driver determines the ioctl type using macro * _IOC_TYPE */ #define PMCRAID_DRIVER_IOCTL 'D' -#define PMCRAID_PASSTHROUGH_IOCTL 'F' #define DRV_IOCTL(n, size) \ _IOC(_IOC_READ|_IOC_WRITE, PMCRAID_DRIVER_IOCTL, (n), (size)) -#define FMW_IOCTL(n, size) \ - _IOC(_IOC_READ|_IOC_WRITE, PMCRAID_PASSTHROUGH_IOCTL, (n), (size)) - /* * _ARGSIZE: macro that gives size of the argument type passed to an IOCTL cmd. * This is to facilitate applications avoiding un-necessary memory allocations. @@ -1069,12 +1044,4 @@ struct pmcraid_passthrough_ioctl_buffer { #define PMCRAID_IOCTL_RESET_ADAPTER \ DRV_IOCTL(5, sizeof(struct pmcraid_ioctl_header)) -/* passthrough/firmware handled commands */ -#define PMCRAID_IOCTL_PASSTHROUGH_COMMAND \ - FMW_IOCTL(1, sizeof(struct pmcraid_passthrough_ioctl_buffer)) - -#define PMCRAID_IOCTL_DOWNLOAD_MICROCODE \ - FMW_IOCTL(2, sizeof(struct pmcraid_passthrough_ioctl_buffer)) - - #endif /* _PMCRAID_H */ diff --git a/drivers/scsi/qedi/qedi_iscsi.c b/drivers/scsi/qedi/qedi_iscsi.c index 8196f89f404e..31ec429104e2 100644 --- a/drivers/scsi/qedi/qedi_iscsi.c +++ b/drivers/scsi/qedi/qedi_iscsi.c @@ -860,6 +860,37 @@ static int qedi_task_xmit(struct iscsi_task *task) return qedi_iscsi_send_ioreq(task); } +static void qedi_offload_work(struct work_struct *work) +{ + struct qedi_endpoint *qedi_ep = + container_of(work, struct qedi_endpoint, offload_work); + struct qedi_ctx *qedi; + int wait_delay = 5 * HZ; + int ret; + + qedi = qedi_ep->qedi; + + ret = qedi_iscsi_offload_conn(qedi_ep); + if (ret) { + QEDI_ERR(&qedi->dbg_ctx, + "offload error: iscsi_cid=%u, qedi_ep=%p, ret=%d\n", + qedi_ep->iscsi_cid, qedi_ep, ret); + qedi_ep->state = EP_STATE_OFLDCONN_FAILED; + return; + } + + ret = wait_event_interruptible_timeout(qedi_ep->tcp_ofld_wait, + (qedi_ep->state == + EP_STATE_OFLDCONN_COMPL), + wait_delay); + if (ret <= 0 || qedi_ep->state != EP_STATE_OFLDCONN_COMPL) { + qedi_ep->state = EP_STATE_OFLDCONN_FAILED; + QEDI_ERR(&qedi->dbg_ctx, + "Offload conn TIMEOUT iscsi_cid=%u, qedi_ep=%p\n", + qedi_ep->iscsi_cid, qedi_ep); + } +} + static struct iscsi_endpoint * qedi_ep_connect(struct Scsi_Host *shost, struct sockaddr *dst_addr, int non_blocking) @@ -908,6 +939,7 @@ qedi_ep_connect(struct Scsi_Host *shost, struct sockaddr *dst_addr, } qedi_ep = ep->dd_data; memset(qedi_ep, 0, sizeof(struct qedi_endpoint)); + INIT_WORK(&qedi_ep->offload_work, qedi_offload_work); qedi_ep->state = EP_STATE_IDLE; qedi_ep->iscsi_cid = (u32)-1; qedi_ep->qedi = qedi; @@ -1056,12 +1088,11 @@ static void qedi_ep_disconnect(struct iscsi_endpoint *ep) qedi_ep = ep->dd_data; qedi = qedi_ep->qedi; + flush_work(&qedi_ep->offload_work); + if (qedi_ep->state == EP_STATE_OFLDCONN_START) goto ep_exit_recover; - if (qedi_ep->state != EP_STATE_OFLDCONN_NONE) - flush_work(&qedi_ep->offload_work); - if (qedi_ep->conn) { qedi_conn = qedi_ep->conn; abrt_conn = qedi_conn->abrt_conn; @@ -1235,37 +1266,6 @@ static int qedi_data_avail(struct qedi_ctx *qedi, u16 vlanid) return rc; } -static void qedi_offload_work(struct work_struct *work) -{ - struct qedi_endpoint *qedi_ep = - container_of(work, struct qedi_endpoint, offload_work); - struct qedi_ctx *qedi; - int wait_delay = 5 * HZ; - int ret; - - qedi = qedi_ep->qedi; - - ret = qedi_iscsi_offload_conn(qedi_ep); - if (ret) { - QEDI_ERR(&qedi->dbg_ctx, - "offload error: iscsi_cid=%u, qedi_ep=%p, ret=%d\n", - qedi_ep->iscsi_cid, qedi_ep, ret); - qedi_ep->state = EP_STATE_OFLDCONN_FAILED; - return; - } - - ret = wait_event_interruptible_timeout(qedi_ep->tcp_ofld_wait, - (qedi_ep->state == - EP_STATE_OFLDCONN_COMPL), - wait_delay); - if ((ret <= 0) || (qedi_ep->state != EP_STATE_OFLDCONN_COMPL)) { - qedi_ep->state = EP_STATE_OFLDCONN_FAILED; - QEDI_ERR(&qedi->dbg_ctx, - "Offload conn TIMEOUT iscsi_cid=%u, qedi_ep=%p\n", - qedi_ep->iscsi_cid, qedi_ep); - } -} - static int qedi_set_path(struct Scsi_Host *shost, struct iscsi_path *path_data) { struct qedi_ctx *qedi; @@ -1381,7 +1381,6 @@ static int qedi_set_path(struct Scsi_Host *shost, struct iscsi_path *path_data) qedi_ep->dst_addr, qedi_ep->dst_port); } - INIT_WORK(&qedi_ep->offload_work, qedi_offload_work); queue_work(qedi->offload_thread, &qedi_ep->offload_work); ret = 0; diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index 85dbf81f3204..6dfcfd8e7337 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -3826,6 +3826,9 @@ int qlt_abort_cmd(struct qla_tgt_cmd *cmd) spin_lock_irqsave(&cmd->cmd_lock, flags); if (cmd->aborted) { + if (cmd->sg_mapped) + qlt_unmap_sg(vha, cmd); + spin_unlock_irqrestore(&cmd->cmd_lock, flags); /* * It's normal to see 2 calls in this path: diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c index c607755cce00..592a290e6cfa 100644 --- a/drivers/scsi/scsi_debug.c +++ b/drivers/scsi/scsi_debug.c @@ -32,7 +32,6 @@ #include <linux/blkdev.h> #include <linux/crc-t10dif.h> #include <linux/spinlock.h> -#include <linux/mutex.h> #include <linux/interrupt.h> #include <linux/atomic.h> #include <linux/hrtimer.h> @@ -732,9 +731,7 @@ static const struct opcode_info_t opcode_info_arr[SDEB_I_LAST_ELEM_P1 + 1] = { {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0} }, }; -static atomic_t sdebug_num_hosts; -static DEFINE_MUTEX(add_host_mutex); - +static int sdebug_num_hosts; static int sdebug_add_host = DEF_NUM_HOST; /* in sysfs this is relative */ static int sdebug_ato = DEF_ATO; static int sdebug_cdb_len = DEF_CDB_LEN; @@ -781,7 +778,6 @@ static int sdebug_uuid_ctl = DEF_UUID_CTL; static bool sdebug_random = DEF_RANDOM; static bool sdebug_per_host_store = DEF_PER_HOST_STORE; static bool sdebug_removable = DEF_REMOVABLE; -static bool sdebug_deflect_incoming; static bool sdebug_clustering; static bool sdebug_host_lock = DEF_HOST_LOCK; static bool sdebug_strict = DEF_STRICT; @@ -5122,10 +5118,6 @@ static int scsi_debug_slave_configure(struct scsi_device *sdp) sdp->host->host_no, sdp->channel, sdp->id, sdp->lun); if (sdp->host->max_cmd_len != SDEBUG_MAX_CMD_LEN) sdp->host->max_cmd_len = SDEBUG_MAX_CMD_LEN; - if (smp_load_acquire(&sdebug_deflect_incoming)) { - pr_info("Exit early due to deflect_incoming\n"); - return 1; - } if (devip == NULL) { devip = find_build_dev_info(sdp); if (devip == NULL) @@ -5211,7 +5203,7 @@ static bool stop_queued_cmnd(struct scsi_cmnd *cmnd) } /* Deletes (stops) timers or work queues of all queued commands */ -static void stop_all_queued(bool done_with_no_conn) +static void stop_all_queued(void) { unsigned long iflags; int j, k; @@ -5220,15 +5212,13 @@ static void stop_all_queued(bool done_with_no_conn) struct sdebug_queued_cmd *sqcp; struct sdebug_dev_info *devip; struct sdebug_defer *sd_dp; - struct scsi_cmnd *scp; for (j = 0, sqp = sdebug_q_arr; j < submit_queues; ++j, ++sqp) { spin_lock_irqsave(&sqp->qc_lock, iflags); for (k = 0; k < SDEBUG_CANQUEUE; ++k) { if (test_bit(k, sqp->in_use_bm)) { sqcp = &sqp->qc_arr[k]; - scp = sqcp->a_cmnd; - if (!scp) + if (sqcp->a_cmnd == NULL) continue; devip = (struct sdebug_dev_info *) sqcp->a_cmnd->device->hostdata; @@ -5243,10 +5233,6 @@ static void stop_all_queued(bool done_with_no_conn) l_defer_t = SDEB_DEFER_NONE; spin_unlock_irqrestore(&sqp->qc_lock, iflags); stop_qc_helper(sd_dp, l_defer_t); - if (done_with_no_conn && l_defer_t != SDEB_DEFER_NONE) { - scp->result = DID_NO_CONNECT << 16; - scsi_done(scp); - } clear_bit(k, sqp->in_use_bm); spin_lock_irqsave(&sqp->qc_lock, iflags); } @@ -5389,7 +5375,7 @@ static int scsi_debug_host_reset(struct scsi_cmnd *SCpnt) } } spin_unlock(&sdebug_host_list_lock); - stop_all_queued(false); + stop_all_queued(); if (SDEBUG_OPT_RESET_NOISE & sdebug_opts) sdev_printk(KERN_INFO, SCpnt->device, "%s: %d device(s) found\n", __func__, k); @@ -5449,50 +5435,13 @@ static void sdebug_build_parts(unsigned char *ramp, unsigned long store_size) } } -static void sdeb_block_all_queues(void) -{ - int j; - struct sdebug_queue *sqp; - - for (j = 0, sqp = sdebug_q_arr; j < submit_queues; ++j, ++sqp) - atomic_set(&sqp->blocked, (int)true); -} - -static void sdeb_unblock_all_queues(void) +static void block_unblock_all_queues(bool block) { int j; struct sdebug_queue *sqp; for (j = 0, sqp = sdebug_q_arr; j < submit_queues; ++j, ++sqp) - atomic_set(&sqp->blocked, (int)false); -} - -static void -sdeb_add_n_hosts(int num_hosts) -{ - if (num_hosts < 1) - return; - do { - bool found; - unsigned long idx; - struct sdeb_store_info *sip; - bool want_phs = (sdebug_fake_rw == 0) && sdebug_per_host_store; - - found = false; - if (want_phs) { - xa_for_each_marked(per_store_ap, idx, sip, SDEB_XA_NOT_IN_USE) { - sdeb_most_recent_idx = (int)idx; - found = true; - break; - } - if (found) /* re-use case */ - sdebug_add_host_helper((int)idx); - else - sdebug_do_add_host(true /* make new store */); - } else { - sdebug_do_add_host(false); - } - } while (--num_hosts); + atomic_set(&sqp->blocked, (int)block); } /* Adjust (by rounding down) the sdebug_cmnd_count so abs(every_nth)-1 @@ -5505,10 +5454,10 @@ static void tweak_cmnd_count(void) modulo = abs(sdebug_every_nth); if (modulo < 2) return; - sdeb_block_all_queues(); + block_unblock_all_queues(true); count = atomic_read(&sdebug_cmnd_count); atomic_set(&sdebug_cmnd_count, (count / modulo) * modulo); - sdeb_unblock_all_queues(); + block_unblock_all_queues(false); } static void clear_queue_stats(void) @@ -5526,15 +5475,6 @@ static bool inject_on_this_cmd(void) return (atomic_read(&sdebug_cmnd_count) % abs(sdebug_every_nth)) == 0; } -static int process_deflect_incoming(struct scsi_cmnd *scp) -{ - u8 opcode = scp->cmnd[0]; - - if (opcode == SYNCHRONIZE_CACHE || opcode == SYNCHRONIZE_CACHE_16) - return 0; - return DID_NO_CONNECT << 16; -} - #define INCLUSIVE_TIMING_MAX_NS 1000000 /* 1 millisecond */ /* Complete the processing of the thread that queued a SCSI command to this @@ -5544,7 +5484,8 @@ static int process_deflect_incoming(struct scsi_cmnd *scp) */ static int schedule_resp(struct scsi_cmnd *cmnd, struct sdebug_dev_info *devip, int scsi_result, - int (*pfp)(struct scsi_cmnd *, struct sdebug_dev_info *), + int (*pfp)(struct scsi_cmnd *, + struct sdebug_dev_info *), int delta_jiff, int ndelay) { bool new_sd_dp; @@ -5565,27 +5506,13 @@ static int schedule_resp(struct scsi_cmnd *cmnd, struct sdebug_dev_info *devip, } sdp = cmnd->device; - if (delta_jiff == 0) { - sqp = get_queue(cmnd); - if (atomic_read(&sqp->blocked)) { - if (smp_load_acquire(&sdebug_deflect_incoming)) - return process_deflect_incoming(cmnd); - else - return SCSI_MLQUEUE_HOST_BUSY; - } + if (delta_jiff == 0) goto respond_in_thread; - } sqp = get_queue(cmnd); spin_lock_irqsave(&sqp->qc_lock, iflags); if (unlikely(atomic_read(&sqp->blocked))) { spin_unlock_irqrestore(&sqp->qc_lock, iflags); - if (smp_load_acquire(&sdebug_deflect_incoming)) { - scsi_result = process_deflect_incoming(cmnd); - goto respond_in_thread; - } - if (sdebug_verbose) - pr_info("blocked --> SCSI_MLQUEUE_HOST_BUSY\n"); return SCSI_MLQUEUE_HOST_BUSY; } num_in_q = atomic_read(&devip->num_in_q); @@ -5774,12 +5701,8 @@ static int schedule_resp(struct scsi_cmnd *cmnd, struct sdebug_dev_info *devip, respond_in_thread: /* call back to mid-layer using invocation thread */ cmnd->result = pfp != NULL ? pfp(cmnd, devip) : 0; cmnd->result &= ~SDEG_RES_IMMED_MASK; - if (cmnd->result == 0 && scsi_result != 0) { + if (cmnd->result == 0 && scsi_result != 0) cmnd->result = scsi_result; - if (sdebug_verbose) - pr_info("respond_in_thread: tag=0x%x, scp->result=0x%x\n", - blk_mq_unique_tag(scsi_cmd_to_rq(cmnd)), scsi_result); - } scsi_done(cmnd); return 0; } @@ -6064,7 +5987,7 @@ static ssize_t delay_store(struct device_driver *ddp, const char *buf, int j, k; struct sdebug_queue *sqp; - sdeb_block_all_queues(); + block_unblock_all_queues(true); for (j = 0, sqp = sdebug_q_arr; j < submit_queues; ++j, ++sqp) { k = find_first_bit(sqp->in_use_bm, @@ -6078,7 +6001,7 @@ static ssize_t delay_store(struct device_driver *ddp, const char *buf, sdebug_jdelay = jdelay; sdebug_ndelay = 0; } - sdeb_unblock_all_queues(); + block_unblock_all_queues(false); } return res; } @@ -6104,7 +6027,7 @@ static ssize_t ndelay_store(struct device_driver *ddp, const char *buf, int j, k; struct sdebug_queue *sqp; - sdeb_block_all_queues(); + block_unblock_all_queues(true); for (j = 0, sqp = sdebug_q_arr; j < submit_queues; ++j, ++sqp) { k = find_first_bit(sqp->in_use_bm, @@ -6119,7 +6042,7 @@ static ssize_t ndelay_store(struct device_driver *ddp, const char *buf, sdebug_jdelay = ndelay ? JDELAY_OVERRIDDEN : DEF_JDELAY; } - sdeb_unblock_all_queues(); + block_unblock_all_queues(false); } return res; } @@ -6433,7 +6356,7 @@ static ssize_t max_queue_store(struct device_driver *ddp, const char *buf, if ((count > 0) && (1 == sscanf(buf, "%d", &n)) && (n > 0) && (n <= SDEBUG_CANQUEUE) && (sdebug_host_max_queue == 0)) { - sdeb_block_all_queues(); + block_unblock_all_queues(true); k = 0; for (j = 0, sqp = sdebug_q_arr; j < submit_queues; ++j, ++sqp) { @@ -6448,7 +6371,7 @@ static ssize_t max_queue_store(struct device_driver *ddp, const char *buf, atomic_set(&retired_max_queue, k + 1); else atomic_set(&retired_max_queue, 0); - sdeb_unblock_all_queues(); + block_unblock_all_queues(false); return count; } return -EINVAL; @@ -6537,48 +6460,43 @@ static DRIVER_ATTR_RW(virtual_gb); static ssize_t add_host_show(struct device_driver *ddp, char *buf) { /* absolute number of hosts currently active is what is shown */ - return scnprintf(buf, PAGE_SIZE, "%d\n", atomic_read(&sdebug_num_hosts)); + return scnprintf(buf, PAGE_SIZE, "%d\n", sdebug_num_hosts); } -/* - * Accept positive and negative values. Hex values (only positive) may be prefixed by '0x'. - * To remove all hosts use a large negative number (e.g. -9999). The value 0 does nothing. - * Returns -EBUSY if another add_host sysfs invocation is active. - */ static ssize_t add_host_store(struct device_driver *ddp, const char *buf, size_t count) { + bool found; + unsigned long idx; + struct sdeb_store_info *sip; + bool want_phs = (sdebug_fake_rw == 0) && sdebug_per_host_store; int delta_hosts; - if (count == 0 || kstrtoint(buf, 0, &delta_hosts)) + if (sscanf(buf, "%d", &delta_hosts) != 1) return -EINVAL; - if (sdebug_verbose) - pr_info("prior num_hosts=%d, num_to_add=%d\n", - atomic_read(&sdebug_num_hosts), delta_hosts); - if (delta_hosts == 0) - return count; - if (mutex_trylock(&add_host_mutex) == 0) - return -EBUSY; if (delta_hosts > 0) { - sdeb_add_n_hosts(delta_hosts); - } else if (delta_hosts < 0) { - smp_store_release(&sdebug_deflect_incoming, true); - sdeb_block_all_queues(); - if (delta_hosts >= atomic_read(&sdebug_num_hosts)) - stop_all_queued(true); do { - if (atomic_read(&sdebug_num_hosts) < 1) { - free_all_queued(); - break; + found = false; + if (want_phs) { + xa_for_each_marked(per_store_ap, idx, sip, + SDEB_XA_NOT_IN_USE) { + sdeb_most_recent_idx = (int)idx; + found = true; + break; + } + if (found) /* re-use case */ + sdebug_add_host_helper((int)idx); + else + sdebug_do_add_host(true); + } else { + sdebug_do_add_host(false); } + } while (--delta_hosts); + } else if (delta_hosts < 0) { + do { sdebug_do_remove_host(false); } while (++delta_hosts); - sdeb_unblock_all_queues(); - smp_store_release(&sdebug_deflect_incoming, false); } - mutex_unlock(&add_host_mutex); - if (sdebug_verbose) - pr_info("post num_hosts=%d\n", atomic_read(&sdebug_num_hosts)); return count; } static DRIVER_ATTR_RW(add_host); @@ -7089,10 +7007,6 @@ static int __init scsi_debug_init(void) sdebug_add_host = 0; for (k = 0; k < hosts_to_add; k++) { - if (smp_load_acquire(&sdebug_deflect_incoming)) { - pr_info("exit early as sdebug_deflect_incoming is set\n"); - return 0; - } if (want_store && k == 0) { ret = sdebug_add_host_helper(idx); if (ret < 0) { @@ -7110,12 +7024,8 @@ static int __init scsi_debug_init(void) } } if (sdebug_verbose) - pr_info("built %d host(s)\n", atomic_read(&sdebug_num_hosts)); + pr_info("built %d host(s)\n", sdebug_num_hosts); - /* - * Even though all the hosts have been established, due to async device (LU) scanning - * by the scsi mid-level, there may still be devices (LUs) being set up. - */ return 0; bus_unreg: @@ -7131,17 +7041,12 @@ free_q_arr: static void __exit scsi_debug_exit(void) { - int k; + int k = sdebug_num_hosts; - /* Possible race with LUs still being set up; stop them asap */ - sdeb_block_all_queues(); - smp_store_release(&sdebug_deflect_incoming, true); - stop_all_queued(false); - for (k = 0; atomic_read(&sdebug_num_hosts) > 0; k++) + stop_all_queued(); + for (; k; k--) sdebug_do_remove_host(true); free_all_queued(); - if (sdebug_verbose) - pr_info("removed %d hosts\n", k); driver_unregister(&sdebug_driverfs_driver); bus_unregister(&pseudo_lld_bus); root_device_unregister(pseudo_primary); @@ -7311,13 +7216,13 @@ static int sdebug_add_host_helper(int per_host_idx) sdbg_host->dev.bus = &pseudo_lld_bus; sdbg_host->dev.parent = pseudo_primary; sdbg_host->dev.release = &sdebug_release_adapter; - dev_set_name(&sdbg_host->dev, "adapter%d", atomic_read(&sdebug_num_hosts)); + dev_set_name(&sdbg_host->dev, "adapter%d", sdebug_num_hosts); error = device_register(&sdbg_host->dev); if (error) goto clean; - atomic_inc(&sdebug_num_hosts); + ++sdebug_num_hosts; return 0; clean: @@ -7381,7 +7286,7 @@ static void sdebug_do_remove_host(bool the_end) return; device_unregister(&sdbg_host->dev); - atomic_dec(&sdebug_num_hosts); + --sdebug_num_hosts; } static int sdebug_change_qdepth(struct scsi_device *sdev, int qdepth) @@ -7389,10 +7294,10 @@ static int sdebug_change_qdepth(struct scsi_device *sdev, int qdepth) int num_in_q = 0; struct sdebug_dev_info *devip; - sdeb_block_all_queues(); + block_unblock_all_queues(true); devip = (struct sdebug_dev_info *)sdev->hostdata; if (NULL == devip) { - sdeb_unblock_all_queues(); + block_unblock_all_queues(false); return -ENODEV; } num_in_q = atomic_read(&devip->num_in_q); @@ -7411,7 +7316,7 @@ static int sdebug_change_qdepth(struct scsi_device *sdev, int qdepth) sdev_printk(KERN_INFO, sdev, "%s: qdepth=%d, num_in_q=%d\n", __func__, qdepth, num_in_q); } - sdeb_unblock_all_queues(); + block_unblock_all_queues(false); return sdev->queue_depth; } @@ -7519,12 +7424,13 @@ static int sdebug_blk_mq_poll(struct Scsi_Host *shost, unsigned int queue_num) struct sdebug_defer *sd_dp; sqp = sdebug_q_arr + queue_num; - qc_idx = find_first_bit(sqp->in_use_bm, sdebug_max_queue); - if (qc_idx >= sdebug_max_queue) - return 0; spin_lock_irqsave(&sqp->qc_lock, iflags); + qc_idx = find_first_bit(sqp->in_use_bm, sdebug_max_queue); + if (qc_idx >= sdebug_max_queue) + goto unlock; + for (first = true; first || qc_idx + 1 < sdebug_max_queue; ) { if (first) { first = false; @@ -7589,6 +7495,7 @@ static int sdebug_blk_mq_poll(struct Scsi_Host *shost, unsigned int queue_num) break; } +unlock: spin_unlock_irqrestore(&sqp->qc_lock, iflags); if (num_entries > 0) diff --git a/drivers/scsi/scsi_logging.c b/drivers/scsi/scsi_logging.c index ff89de86545d..b02af340c2d3 100644 --- a/drivers/scsi/scsi_logging.c +++ b/drivers/scsi/scsi_logging.c @@ -30,7 +30,7 @@ static inline const char *scmd_name(const struct scsi_cmnd *scmd) { struct request *rq = scsi_cmd_to_rq((struct scsi_cmnd *)scmd); - if (!rq->q->disk) + if (!rq->q || !rq->q->disk) return NULL; return rq->q->disk->disk_name; } diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c index f4e6c68ac99e..2ef78083f1ef 100644 --- a/drivers/scsi/scsi_scan.c +++ b/drivers/scsi/scsi_scan.c @@ -223,6 +223,8 @@ static int scsi_realloc_sdev_budget_map(struct scsi_device *sdev, int ret; struct sbitmap sb_backup; + depth = min_t(unsigned int, depth, scsi_device_max_queue_depth(sdev)); + /* * realloc if new shift is calculated, which is caused by setting * up one new default queue depth after calling ->slave_configure @@ -245,6 +247,9 @@ static int scsi_realloc_sdev_budget_map(struct scsi_device *sdev, scsi_device_max_queue_depth(sdev), new_shift, GFP_KERNEL, sdev->request_queue->node, false, true); + if (!ret) + sbitmap_resize(&sdev->budget_map, depth); + if (need_free) { if (ret) sdev->budget_map = sb_backup; diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c index 226a50944c00..dc6872e352bd 100644 --- a/drivers/scsi/scsi_sysfs.c +++ b/drivers/scsi/scsi_sysfs.c @@ -1384,10 +1384,6 @@ int scsi_sysfs_add_sdev(struct scsi_device *sdev) if (IS_ENABLED(CONFIG_BLK_DEV_BSG)) { sdev->bsg_dev = scsi_bsg_register_queue(sdev); if (IS_ERR(sdev->bsg_dev)) { - /* - * We're treating error on bsg register as non-fatal, so - * pretend nothing went wrong. - */ error = PTR_ERR(sdev->bsg_dev); sdev_printk(KERN_INFO, sdev, "Failed to register bsg queue, errno=%d\n", diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c index 27951ea05dd4..2c0dd64159b0 100644 --- a/drivers/scsi/scsi_transport_iscsi.c +++ b/drivers/scsi/scsi_transport_iscsi.c @@ -86,6 +86,9 @@ struct iscsi_internal { struct transport_container session_cont; }; +static DEFINE_IDR(iscsi_ep_idr); +static DEFINE_MUTEX(iscsi_ep_idr_mutex); + static atomic_t iscsi_session_nr; /* sysfs session id for next new session */ static struct workqueue_struct *iscsi_conn_cleanup_workq; @@ -168,6 +171,11 @@ struct device_attribute dev_attr_##_prefix##_##_name = \ static void iscsi_endpoint_release(struct device *dev) { struct iscsi_endpoint *ep = iscsi_dev_to_endpoint(dev); + + mutex_lock(&iscsi_ep_idr_mutex); + idr_remove(&iscsi_ep_idr, ep->id); + mutex_unlock(&iscsi_ep_idr_mutex); + kfree(ep); } @@ -180,7 +188,7 @@ static ssize_t show_ep_handle(struct device *dev, struct device_attribute *attr, char *buf) { struct iscsi_endpoint *ep = iscsi_dev_to_endpoint(dev); - return sysfs_emit(buf, "%llu\n", (unsigned long long) ep->id); + return sysfs_emit(buf, "%d\n", ep->id); } static ISCSI_ATTR(ep, handle, S_IRUGO, show_ep_handle, NULL); @@ -193,48 +201,32 @@ static struct attribute_group iscsi_endpoint_group = { .attrs = iscsi_endpoint_attrs, }; -#define ISCSI_MAX_EPID -1 - -static int iscsi_match_epid(struct device *dev, const void *data) -{ - struct iscsi_endpoint *ep = iscsi_dev_to_endpoint(dev); - const uint64_t *epid = data; - - return *epid == ep->id; -} - struct iscsi_endpoint * iscsi_create_endpoint(int dd_size) { - struct device *dev; struct iscsi_endpoint *ep; - uint64_t id; - int err; - - for (id = 1; id < ISCSI_MAX_EPID; id++) { - dev = class_find_device(&iscsi_endpoint_class, NULL, &id, - iscsi_match_epid); - if (!dev) - break; - else - put_device(dev); - } - if (id == ISCSI_MAX_EPID) { - printk(KERN_ERR "Too many connections. Max supported %u\n", - ISCSI_MAX_EPID - 1); - return NULL; - } + int err, id; ep = kzalloc(sizeof(*ep) + dd_size, GFP_KERNEL); if (!ep) return NULL; + mutex_lock(&iscsi_ep_idr_mutex); + id = idr_alloc(&iscsi_ep_idr, ep, 0, -1, GFP_NOIO); + if (id < 0) { + mutex_unlock(&iscsi_ep_idr_mutex); + printk(KERN_ERR "Could not allocate endpoint ID. Error %d.\n", + id); + goto free_ep; + } + mutex_unlock(&iscsi_ep_idr_mutex); + ep->id = id; ep->dev.class = &iscsi_endpoint_class; - dev_set_name(&ep->dev, "ep-%llu", (unsigned long long) id); + dev_set_name(&ep->dev, "ep-%d", id); err = device_register(&ep->dev); if (err) - goto free_ep; + goto free_id; err = sysfs_create_group(&ep->dev.kobj, &iscsi_endpoint_group); if (err) @@ -248,6 +240,10 @@ unregister_dev: device_unregister(&ep->dev); return NULL; +free_id: + mutex_lock(&iscsi_ep_idr_mutex); + idr_remove(&iscsi_ep_idr, id); + mutex_unlock(&iscsi_ep_idr_mutex); free_ep: kfree(ep); return NULL; @@ -275,14 +271,17 @@ EXPORT_SYMBOL_GPL(iscsi_put_endpoint); */ struct iscsi_endpoint *iscsi_lookup_endpoint(u64 handle) { - struct device *dev; + struct iscsi_endpoint *ep; - dev = class_find_device(&iscsi_endpoint_class, NULL, &handle, - iscsi_match_epid); - if (!dev) - return NULL; + mutex_lock(&iscsi_ep_idr_mutex); + ep = idr_find(&iscsi_ep_idr, handle); + if (!ep) + goto unlock; - return iscsi_dev_to_endpoint(dev); + get_device(&ep->dev); +unlock: + mutex_unlock(&iscsi_ep_idr_mutex); + return ep; } EXPORT_SYMBOL_GPL(iscsi_lookup_endpoint); @@ -2202,10 +2201,10 @@ static void iscsi_stop_conn(struct iscsi_cls_conn *conn, int flag) switch (flag) { case STOP_CONN_RECOVER: - conn->state = ISCSI_CONN_FAILED; + WRITE_ONCE(conn->state, ISCSI_CONN_FAILED); break; case STOP_CONN_TERM: - conn->state = ISCSI_CONN_DOWN; + WRITE_ONCE(conn->state, ISCSI_CONN_DOWN); break; default: iscsi_cls_conn_printk(KERN_ERR, conn, "invalid stop flag %d\n", @@ -2217,6 +2216,49 @@ static void iscsi_stop_conn(struct iscsi_cls_conn *conn, int flag) ISCSI_DBG_TRANS_CONN(conn, "Stopping conn done.\n"); } +static void iscsi_ep_disconnect(struct iscsi_cls_conn *conn, bool is_active) +{ + struct iscsi_cls_session *session = iscsi_conn_to_session(conn); + struct iscsi_endpoint *ep; + + ISCSI_DBG_TRANS_CONN(conn, "disconnect ep.\n"); + WRITE_ONCE(conn->state, ISCSI_CONN_FAILED); + + if (!conn->ep || !session->transport->ep_disconnect) + return; + + ep = conn->ep; + conn->ep = NULL; + + session->transport->unbind_conn(conn, is_active); + session->transport->ep_disconnect(ep); + ISCSI_DBG_TRANS_CONN(conn, "disconnect ep done.\n"); +} + +static void iscsi_if_disconnect_bound_ep(struct iscsi_cls_conn *conn, + struct iscsi_endpoint *ep, + bool is_active) +{ + /* Check if this was a conn error and the kernel took ownership */ + spin_lock_irq(&conn->lock); + if (!test_bit(ISCSI_CLS_CONN_BIT_CLEANUP, &conn->flags)) { + spin_unlock_irq(&conn->lock); + iscsi_ep_disconnect(conn, is_active); + } else { + spin_unlock_irq(&conn->lock); + ISCSI_DBG_TRANS_CONN(conn, "flush kernel conn cleanup.\n"); + mutex_unlock(&conn->ep_mutex); + + flush_work(&conn->cleanup_work); + /* + * Userspace is now done with the EP so we can release the ref + * iscsi_cleanup_conn_work_fn took. + */ + iscsi_put_endpoint(ep); + mutex_lock(&conn->ep_mutex); + } +} + static int iscsi_if_stop_conn(struct iscsi_transport *transport, struct iscsi_uevent *ev) { @@ -2238,11 +2280,24 @@ static int iscsi_if_stop_conn(struct iscsi_transport *transport, iscsi_stop_conn(conn, flag); } else { /* + * For offload, when iscsid is restarted it won't know about + * existing endpoints so it can't do a ep_disconnect. We clean + * it up here for userspace. + */ + mutex_lock(&conn->ep_mutex); + if (conn->ep) + iscsi_if_disconnect_bound_ep(conn, conn->ep, true); + mutex_unlock(&conn->ep_mutex); + + /* * Figure out if it was the kernel or userspace initiating this. */ + spin_lock_irq(&conn->lock); if (!test_and_set_bit(ISCSI_CLS_CONN_BIT_CLEANUP, &conn->flags)) { + spin_unlock_irq(&conn->lock); iscsi_stop_conn(conn, flag); } else { + spin_unlock_irq(&conn->lock); ISCSI_DBG_TRANS_CONN(conn, "flush kernel conn cleanup.\n"); flush_work(&conn->cleanup_work); @@ -2251,31 +2306,14 @@ static int iscsi_if_stop_conn(struct iscsi_transport *transport, * Only clear for recovery to avoid extra cleanup runs during * termination. */ + spin_lock_irq(&conn->lock); clear_bit(ISCSI_CLS_CONN_BIT_CLEANUP, &conn->flags); + spin_unlock_irq(&conn->lock); } ISCSI_DBG_TRANS_CONN(conn, "iscsi if conn stop done.\n"); return 0; } -static void iscsi_ep_disconnect(struct iscsi_cls_conn *conn, bool is_active) -{ - struct iscsi_cls_session *session = iscsi_conn_to_session(conn); - struct iscsi_endpoint *ep; - - ISCSI_DBG_TRANS_CONN(conn, "disconnect ep.\n"); - conn->state = ISCSI_CONN_FAILED; - - if (!conn->ep || !session->transport->ep_disconnect) - return; - - ep = conn->ep; - conn->ep = NULL; - - session->transport->unbind_conn(conn, is_active); - session->transport->ep_disconnect(ep); - ISCSI_DBG_TRANS_CONN(conn, "disconnect ep done.\n"); -} - static void iscsi_cleanup_conn_work_fn(struct work_struct *work) { struct iscsi_cls_conn *conn = container_of(work, struct iscsi_cls_conn, @@ -2284,18 +2322,11 @@ static void iscsi_cleanup_conn_work_fn(struct work_struct *work) mutex_lock(&conn->ep_mutex); /* - * If we are not at least bound there is nothing for us to do. Userspace - * will do a ep_disconnect call if offload is used, but will not be - * doing a stop since there is nothing to clean up, so we have to clear - * the cleanup bit here. + * Get a ref to the ep, so we don't release its ID until after + * userspace is done referencing it in iscsi_if_disconnect_bound_ep. */ - if (conn->state != ISCSI_CONN_BOUND && conn->state != ISCSI_CONN_UP) { - ISCSI_DBG_TRANS_CONN(conn, "Got error while conn is already failed. Ignoring.\n"); - clear_bit(ISCSI_CLS_CONN_BIT_CLEANUP, &conn->flags); - mutex_unlock(&conn->ep_mutex); - return; - } - + if (conn->ep) + get_device(&conn->ep->dev); iscsi_ep_disconnect(conn, false); if (system_state != SYSTEM_RUNNING) { @@ -2340,11 +2371,12 @@ iscsi_alloc_conn(struct iscsi_cls_session *session, int dd_size, uint32_t cid) conn->dd_data = &conn[1]; mutex_init(&conn->ep_mutex); + spin_lock_init(&conn->lock); INIT_LIST_HEAD(&conn->conn_list); INIT_WORK(&conn->cleanup_work, iscsi_cleanup_conn_work_fn); conn->transport = transport; conn->cid = cid; - conn->state = ISCSI_CONN_DOWN; + WRITE_ONCE(conn->state, ISCSI_CONN_DOWN); /* this is released in the dev's release function */ if (!get_device(&session->dev)) @@ -2542,9 +2574,32 @@ void iscsi_conn_error_event(struct iscsi_cls_conn *conn, enum iscsi_err error) struct iscsi_uevent *ev; struct iscsi_internal *priv; int len = nlmsg_total_size(sizeof(*ev)); + unsigned long flags; + int state; - if (!test_and_set_bit(ISCSI_CLS_CONN_BIT_CLEANUP, &conn->flags)) - queue_work(iscsi_conn_cleanup_workq, &conn->cleanup_work); + spin_lock_irqsave(&conn->lock, flags); + /* + * Userspace will only do a stop call if we are at least bound. And, we + * only need to do the in kernel cleanup if in the UP state so cmds can + * be released to upper layers. If in other states just wait for + * userspace to avoid races that can leave the cleanup_work queued. + */ + state = READ_ONCE(conn->state); + switch (state) { + case ISCSI_CONN_BOUND: + case ISCSI_CONN_UP: + if (!test_and_set_bit(ISCSI_CLS_CONN_BIT_CLEANUP, + &conn->flags)) { + queue_work(iscsi_conn_cleanup_workq, + &conn->cleanup_work); + } + break; + default: + ISCSI_DBG_TRANS_CONN(conn, "Got conn error in state %d\n", + state); + break; + } + spin_unlock_irqrestore(&conn->lock, flags); priv = iscsi_if_transport_lookup(conn->transport); if (!priv) @@ -2894,7 +2949,7 @@ iscsi_set_param(struct iscsi_transport *transport, struct iscsi_uevent *ev) char *data = (char*)ev + sizeof(*ev); struct iscsi_cls_conn *conn; struct iscsi_cls_session *session; - int err = 0, value = 0; + int err = 0, value = 0, state; if (ev->u.set_param.len > PAGE_SIZE) return -EINVAL; @@ -2911,8 +2966,8 @@ iscsi_set_param(struct iscsi_transport *transport, struct iscsi_uevent *ev) session->recovery_tmo = value; break; default: - if ((conn->state == ISCSI_CONN_BOUND) || - (conn->state == ISCSI_CONN_UP)) { + state = READ_ONCE(conn->state); + if (state == ISCSI_CONN_BOUND || state == ISCSI_CONN_UP) { err = transport->set_param(conn, ev->u.set_param.param, data, ev->u.set_param.len); } else { @@ -2984,16 +3039,7 @@ static int iscsi_if_ep_disconnect(struct iscsi_transport *transport, } mutex_lock(&conn->ep_mutex); - /* Check if this was a conn error and the kernel took ownership */ - if (test_bit(ISCSI_CLS_CONN_BIT_CLEANUP, &conn->flags)) { - ISCSI_DBG_TRANS_CONN(conn, "flush kernel conn cleanup.\n"); - mutex_unlock(&conn->ep_mutex); - - flush_work(&conn->cleanup_work); - goto put_ep; - } - - iscsi_ep_disconnect(conn, false); + iscsi_if_disconnect_bound_ep(conn, ep, false); mutex_unlock(&conn->ep_mutex); put_ep: iscsi_put_endpoint(ep); @@ -3696,24 +3742,17 @@ static int iscsi_if_transport_conn(struct iscsi_transport *transport, return -EINVAL; mutex_lock(&conn->ep_mutex); + spin_lock_irq(&conn->lock); if (test_bit(ISCSI_CLS_CONN_BIT_CLEANUP, &conn->flags)) { + spin_unlock_irq(&conn->lock); mutex_unlock(&conn->ep_mutex); ev->r.retcode = -ENOTCONN; return 0; } + spin_unlock_irq(&conn->lock); switch (nlh->nlmsg_type) { case ISCSI_UEVENT_BIND_CONN: - if (conn->ep) { - /* - * For offload boot support where iscsid is restarted - * during the pivot root stage, the ep will be intact - * here when the new iscsid instance starts up and - * reconnects. - */ - iscsi_ep_disconnect(conn, true); - } - session = iscsi_session_lookup(ev->u.b_conn.sid); if (!session) { err = -EINVAL; @@ -3724,7 +3763,7 @@ static int iscsi_if_transport_conn(struct iscsi_transport *transport, ev->u.b_conn.transport_eph, ev->u.b_conn.is_leading); if (!ev->r.retcode) - conn->state = ISCSI_CONN_BOUND; + WRITE_ONCE(conn->state, ISCSI_CONN_BOUND); if (ev->r.retcode || !transport->ep_connect) break; @@ -3743,7 +3782,8 @@ static int iscsi_if_transport_conn(struct iscsi_transport *transport, case ISCSI_UEVENT_START_CONN: ev->r.retcode = transport->start_conn(conn); if (!ev->r.retcode) - conn->state = ISCSI_CONN_UP; + WRITE_ONCE(conn->state, ISCSI_CONN_UP); + break; case ISCSI_UEVENT_SEND_PDU: pdu_len = nlh->nlmsg_len - sizeof(*nlh) - sizeof(*ev); @@ -4050,10 +4090,11 @@ static ssize_t show_conn_state(struct device *dev, { struct iscsi_cls_conn *conn = iscsi_dev_to_conn(dev->parent); const char *state = "unknown"; + int conn_state = READ_ONCE(conn->state); - if (conn->state >= 0 && - conn->state < ARRAY_SIZE(connection_state_names)) - state = connection_state_names[conn->state]; + if (conn_state >= 0 && + conn_state < ARRAY_SIZE(connection_state_names)) + state = connection_state_names[conn_state]; return sysfs_emit(buf, "%s\n", state); } diff --git a/drivers/scsi/scsicam.c b/drivers/scsi/scsicam.c index acdc0aceca5e..e2c7d8ef205f 100644 --- a/drivers/scsi/scsicam.c +++ b/drivers/scsi/scsicam.c @@ -34,15 +34,14 @@ unsigned char *scsi_bios_ptable(struct block_device *dev) { struct address_space *mapping = bdev_whole(dev)->bd_inode->i_mapping; unsigned char *res = NULL; - struct page *page; + struct folio *folio; - page = read_mapping_page(mapping, 0, NULL); - if (IS_ERR(page)) + folio = read_mapping_folio(mapping, 0, NULL); + if (IS_ERR(folio)) return NULL; - if (!PageError(page)) - res = kmemdup(page_address(page) + 0x1be, 66, GFP_KERNEL); - put_page(page); + res = kmemdup(folio_address(folio) + 0x1be, 66, GFP_KERNEL); + folio_put(folio); return res; } EXPORT_SYMBOL(scsi_bios_ptable); diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index a390679cf458..9694e2cfaf9a 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -797,7 +797,6 @@ static void sd_config_discard(struct scsi_disk *sdkp, unsigned int mode) case SD_LBP_FULL: case SD_LBP_DISABLE: blk_queue_max_discard_sectors(q, 0); - blk_queue_flag_clear(QUEUE_FLAG_DISCARD, q); return; case SD_LBP_UNMAP: @@ -830,7 +829,6 @@ static void sd_config_discard(struct scsi_disk *sdkp, unsigned int mode) } blk_queue_max_discard_sectors(q, max_blocks * (logical_block_size >> 9)); - blk_queue_flag_set(QUEUE_FLAG_DISCARD, q); } static blk_status_t sd_setup_unmap_cmnd(struct scsi_cmnd *cmd) @@ -3216,6 +3214,7 @@ static int sd_revalidate_disk(struct gendisk *disk) sd_read_block_limits(sdkp); sd_read_block_characteristics(sdkp); sd_zbc_read_zones(sdkp, buffer); + sd_read_cpr(sdkp); } sd_print_capacity(sdkp, old_capacity); @@ -3225,7 +3224,6 @@ static int sd_revalidate_disk(struct gendisk *disk) sd_read_app_tag_own(sdkp, buffer); sd_read_write_same(sdkp, buffer); sd_read_security(sdkp, buffer); - sd_read_cpr(sdkp); } /* @@ -3475,6 +3473,7 @@ static int sd_probe(struct device *dev) error = device_add_disk(dev, gd, NULL); if (error) { put_device(&sdkp->disk_dev); + blk_cleanup_disk(gd); goto out; } diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c index 5ba9df334968..cbd92891a762 100644 --- a/drivers/scsi/sr.c +++ b/drivers/scsi/sr.c @@ -535,7 +535,7 @@ static int sr_block_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, scsi_autopm_get_device(sdev); - if (ret != CDROMCLOSETRAY && ret != CDROMEJECT) { + if (cmd != CDROMCLOSETRAY && cmd != CDROMEJECT) { ret = cdrom_ioctl(&cd->cdi, bdev, mode, cmd, arg); if (ret != -ENOSYS) goto put; diff --git a/drivers/scsi/sr_ioctl.c b/drivers/scsi/sr_ioctl.c index ddd00efc4882..fbdb5124d7f7 100644 --- a/drivers/scsi/sr_ioctl.c +++ b/drivers/scsi/sr_ioctl.c @@ -41,7 +41,7 @@ static int sr_read_tochdr(struct cdrom_device_info *cdi, int result; unsigned char *buffer; - buffer = kmalloc(32, GFP_KERNEL); + buffer = kzalloc(32, GFP_KERNEL); if (!buffer) return -ENOMEM; @@ -55,10 +55,13 @@ static int sr_read_tochdr(struct cdrom_device_info *cdi, cgc.data_direction = DMA_FROM_DEVICE; result = sr_do_ioctl(cd, &cgc); + if (result) + goto err; tochdr->cdth_trk0 = buffer[2]; tochdr->cdth_trk1 = buffer[3]; +err: kfree(buffer); return result; } @@ -71,7 +74,7 @@ static int sr_read_tocentry(struct cdrom_device_info *cdi, int result; unsigned char *buffer; - buffer = kmalloc(32, GFP_KERNEL); + buffer = kzalloc(32, GFP_KERNEL); if (!buffer) return -ENOMEM; @@ -86,6 +89,8 @@ static int sr_read_tocentry(struct cdrom_device_info *cdi, cgc.data_direction = DMA_FROM_DEVICE; result = sr_do_ioctl(cd, &cgc); + if (result) + goto err; tocentry->cdte_ctrl = buffer[5] & 0xf; tocentry->cdte_adr = buffer[5] >> 4; @@ -98,6 +103,7 @@ static int sr_read_tocentry(struct cdrom_device_info *cdi, tocentry->cdte_addr.lba = (((((buffer[8] << 8) + buffer[9]) << 8) + buffer[10]) << 8) + buffer[11]; +err: kfree(buffer); return result; } @@ -384,7 +390,7 @@ int sr_get_mcn(struct cdrom_device_info *cdi, struct cdrom_mcn *mcn) { Scsi_CD *cd = cdi->handle; struct packet_command cgc; - char *buffer = kmalloc(32, GFP_KERNEL); + char *buffer = kzalloc(32, GFP_KERNEL); int result; if (!buffer) @@ -400,10 +406,13 @@ int sr_get_mcn(struct cdrom_device_info *cdi, struct cdrom_mcn *mcn) cgc.data_direction = DMA_FROM_DEVICE; cgc.timeout = IOCTL_TIMEOUT; result = sr_do_ioctl(cd, &cgc); + if (result) + goto err; memcpy(mcn->medium_catalog_number, buffer + 9, 13); mcn->medium_catalog_number[13] = 0; +err: kfree(buffer); return result; } diff --git a/drivers/scsi/ufs/ufs-qcom.c b/drivers/scsi/ufs/ufs-qcom.c index 0d2e950d0865..586c0e567ff9 100644 --- a/drivers/scsi/ufs/ufs-qcom.c +++ b/drivers/scsi/ufs/ufs-qcom.c @@ -957,18 +957,6 @@ static const struct reset_control_ops ufs_qcom_reset_ops = { .deassert = ufs_qcom_reset_deassert, }; -#define ANDROID_BOOT_DEV_MAX 30 -static char android_boot_dev[ANDROID_BOOT_DEV_MAX]; - -#ifndef MODULE -static int __init get_android_boot_dev(char *str) -{ - strlcpy(android_boot_dev, str, ANDROID_BOOT_DEV_MAX); - return 1; -} -__setup("androidboot.bootdevice=", get_android_boot_dev); -#endif - /** * ufs_qcom_init - bind phy with controller * @hba: host controller instance @@ -988,9 +976,6 @@ static int ufs_qcom_init(struct ufs_hba *hba) struct resource *res; struct ufs_clk_info *clki; - if (strlen(android_boot_dev) && strcmp(android_boot_dev, dev_name(dev))) - return -ENODEV; - host = devm_kzalloc(dev, sizeof(*host), GFP_KERNEL); if (!host) { err = -ENOMEM; diff --git a/drivers/scsi/ufs/ufshcd-pci.c b/drivers/scsi/ufs/ufshcd-pci.c index f76692053ca1..e892b9feffb1 100644 --- a/drivers/scsi/ufs/ufshcd-pci.c +++ b/drivers/scsi/ufs/ufshcd-pci.c @@ -428,6 +428,12 @@ static int ufs_intel_adl_init(struct ufs_hba *hba) return ufs_intel_common_init(hba); } +static int ufs_intel_mtl_init(struct ufs_hba *hba) +{ + hba->caps |= UFSHCD_CAP_CRYPTO | UFSHCD_CAP_WB_EN; + return ufs_intel_common_init(hba); +} + static struct ufs_hba_variant_ops ufs_intel_cnl_hba_vops = { .name = "intel-pci", .init = ufs_intel_common_init, @@ -465,6 +471,16 @@ static struct ufs_hba_variant_ops ufs_intel_adl_hba_vops = { .device_reset = ufs_intel_device_reset, }; +static struct ufs_hba_variant_ops ufs_intel_mtl_hba_vops = { + .name = "intel-pci", + .init = ufs_intel_mtl_init, + .exit = ufs_intel_common_exit, + .hce_enable_notify = ufs_intel_hce_enable_notify, + .link_startup_notify = ufs_intel_link_startup_notify, + .resume = ufs_intel_resume, + .device_reset = ufs_intel_device_reset, +}; + #ifdef CONFIG_PM_SLEEP static int ufshcd_pci_restore(struct device *dev) { @@ -579,6 +595,7 @@ static const struct pci_device_id ufshcd_pci_tbl[] = { { PCI_VDEVICE(INTEL, 0x98FA), (kernel_ulong_t)&ufs_intel_lkf_hba_vops }, { PCI_VDEVICE(INTEL, 0x51FF), (kernel_ulong_t)&ufs_intel_adl_hba_vops }, { PCI_VDEVICE(INTEL, 0x54FF), (kernel_ulong_t)&ufs_intel_adl_hba_vops }, + { PCI_VDEVICE(INTEL, 0x7E47), (kernel_ulong_t)&ufs_intel_mtl_hba_vops }, { } /* terminate list */ }; diff --git a/drivers/scsi/ufs/ufshcd.h b/drivers/scsi/ufs/ufshcd.h index 88c20f3608c2..94f545be183a 100644 --- a/drivers/scsi/ufs/ufshcd.h +++ b/drivers/scsi/ufs/ufshcd.h @@ -820,8 +820,6 @@ struct ufs_hba { enum ufs_pm_level rpm_lvl; /* Desired UFS power management level during system PM */ enum ufs_pm_level spm_lvl; - struct device_attribute rpm_lvl_attr; - struct device_attribute spm_lvl_attr; int pm_op_in_progress; /* Auto-Hibernate Idle Timer register value */ diff --git a/drivers/scsi/ufs/ufshpb.c b/drivers/scsi/ufs/ufshpb.c index b2bec19022cd..588c0329b80c 100644 --- a/drivers/scsi/ufs/ufshpb.c +++ b/drivers/scsi/ufs/ufshpb.c @@ -867,12 +867,6 @@ static struct ufshpb_region *ufshpb_victim_lru_info(struct ufshpb_lu *hpb) struct ufshpb_region *rgn, *victim_rgn = NULL; list_for_each_entry(rgn, &lru_info->lh_lru_rgn, list_lru_rgn) { - if (!rgn) { - dev_err(&hpb->sdev_ufs_lu->sdev_dev, - "%s: no region allocated\n", - __func__); - return NULL; - } if (ufshpb_check_srgns_issue_state(hpb, rgn)) continue; @@ -888,6 +882,11 @@ static struct ufshpb_region *ufshpb_victim_lru_info(struct ufshpb_lu *hpb) break; } + if (!victim_rgn) + dev_err(&hpb->sdev_ufs_lu->sdev_dev, + "%s: no region allocated\n", + __func__); + return victim_rgn; } @@ -1255,6 +1254,13 @@ void ufshpb_rsp_upiu(struct ufs_hba *hba, struct ufshcd_lrb *lrbp) struct utp_hpb_rsp *rsp_field = &lrbp->ucd_rsp_ptr->hr; int data_seg_len; + data_seg_len = be32_to_cpu(lrbp->ucd_rsp_ptr->header.dword_2) + & MASK_RSP_UPIU_DATA_SEG_LEN; + + /* If data segment length is zero, rsp_field is not valid */ + if (!data_seg_len) + return; + if (unlikely(lrbp->lun != rsp_field->lun)) { struct scsi_device *sdev; bool found = false; @@ -1289,18 +1295,6 @@ void ufshpb_rsp_upiu(struct ufs_hba *hba, struct ufshcd_lrb *lrbp) return; } - data_seg_len = be32_to_cpu(lrbp->ucd_rsp_ptr->header.dword_2) - & MASK_RSP_UPIU_DATA_SEG_LEN; - - /* To flush remained rsp_list, we queue the map_work task */ - if (!data_seg_len) { - if (!ufshpb_is_general_lun(hpb->lun)) - return; - - ufshpb_kick_map_work(hpb); - return; - } - BUILD_BUG_ON(sizeof(struct utp_hpb_rsp) != UTP_HPB_RSP_SIZE); if (!ufshpb_is_hpb_rsp_valid(hba, lrbp, rsp_field)) diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c index 0e6110da69e7..578c4b6d0f7d 100644 --- a/drivers/scsi/virtio_scsi.c +++ b/drivers/scsi/virtio_scsi.c @@ -988,7 +988,7 @@ static struct virtio_driver virtio_scsi_driver = { .remove = virtscsi_remove, }; -static int __init init(void) +static int __init virtio_scsi_init(void) { int ret = -ENOMEM; @@ -1020,14 +1020,14 @@ error: return ret; } -static void __exit fini(void) +static void __exit virtio_scsi_fini(void) { unregister_virtio_driver(&virtio_scsi_driver); mempool_destroy(virtscsi_cmd_pool); kmem_cache_destroy(virtscsi_cmd_cache); } -module_init(init); -module_exit(fini); +module_init(virtio_scsi_init); +module_exit(virtio_scsi_fini); MODULE_DEVICE_TABLE(virtio, id_table); MODULE_DESCRIPTION("Virtio SCSI HBA driver"); diff --git a/drivers/scsi/xen-scsifront.c b/drivers/scsi/xen-scsifront.c index 12109e4c73d4..51afc66e839d 100644 --- a/drivers/scsi/xen-scsifront.c +++ b/drivers/scsi/xen-scsifront.c @@ -58,9 +58,6 @@ #include <asm/xen/hypervisor.h> - -#define GRANT_INVALID_REF 0 - #define VSCSIFRONT_OP_ADD_LUN 1 #define VSCSIFRONT_OP_DEL_LUN 2 #define VSCSIFRONT_OP_READD_LUN 3 @@ -83,6 +80,8 @@ struct vscsifrnt_shadow { uint16_t rqid; uint16_t ref_rqid; + bool inflight; + unsigned int nr_grants; /* number of grants in gref[] */ struct scsiif_request_segment *sg; /* scatter/gather elements */ struct scsiif_request_segment seg[VSCSIIF_SG_TABLESIZE]; @@ -104,7 +103,11 @@ struct vscsifrnt_info { struct xenbus_device *dev; struct Scsi_Host *host; - int host_active; + enum { + STATE_INACTIVE, + STATE_ACTIVE, + STATE_ERROR + } host_active; unsigned int evtchn; unsigned int irq; @@ -217,6 +220,8 @@ static int scsifront_do_request(struct vscsifrnt_info *info, for (i = 0; i < (shadow->nr_segments & ~VSCSIIF_SG_GRANT); i++) ring_req->seg[i] = shadow->seg[i]; + shadow->inflight = true; + RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(ring, notify); if (notify) notify_remote_via_irq(info->irq); @@ -224,6 +229,13 @@ static int scsifront_do_request(struct vscsifrnt_info *info, return 0; } +static void scsifront_set_error(struct vscsifrnt_info *info, const char *msg) +{ + shost_printk(KERN_ERR, info->host, KBUILD_MODNAME "%s\n" + "Disabling device for further use\n", msg); + info->host_active = STATE_ERROR; +} + static void scsifront_gnttab_done(struct vscsifrnt_info *info, struct vscsifrnt_shadow *shadow) { @@ -234,15 +246,64 @@ static void scsifront_gnttab_done(struct vscsifrnt_info *info, for (i = 0; i < shadow->nr_grants; i++) { if (unlikely(!gnttab_try_end_foreign_access(shadow->gref[i]))) { - shost_printk(KERN_ALERT, info->host, KBUILD_MODNAME - "grant still in use by backend\n"); - BUG(); + scsifront_set_error(info, "grant still in use by backend"); + return; } } kfree(shadow->sg); } +static unsigned int scsifront_host_byte(int32_t rslt) +{ + switch (XEN_VSCSIIF_RSLT_HOST(rslt)) { + case XEN_VSCSIIF_RSLT_HOST_OK: + return DID_OK; + case XEN_VSCSIIF_RSLT_HOST_NO_CONNECT: + return DID_NO_CONNECT; + case XEN_VSCSIIF_RSLT_HOST_BUS_BUSY: + return DID_BUS_BUSY; + case XEN_VSCSIIF_RSLT_HOST_TIME_OUT: + return DID_TIME_OUT; + case XEN_VSCSIIF_RSLT_HOST_BAD_TARGET: + return DID_BAD_TARGET; + case XEN_VSCSIIF_RSLT_HOST_ABORT: + return DID_ABORT; + case XEN_VSCSIIF_RSLT_HOST_PARITY: + return DID_PARITY; + case XEN_VSCSIIF_RSLT_HOST_ERROR: + return DID_ERROR; + case XEN_VSCSIIF_RSLT_HOST_RESET: + return DID_RESET; + case XEN_VSCSIIF_RSLT_HOST_BAD_INTR: + return DID_BAD_INTR; + case XEN_VSCSIIF_RSLT_HOST_PASSTHROUGH: + return DID_PASSTHROUGH; + case XEN_VSCSIIF_RSLT_HOST_SOFT_ERROR: + return DID_SOFT_ERROR; + case XEN_VSCSIIF_RSLT_HOST_IMM_RETRY: + return DID_IMM_RETRY; + case XEN_VSCSIIF_RSLT_HOST_REQUEUE: + return DID_REQUEUE; + case XEN_VSCSIIF_RSLT_HOST_TRANSPORT_DISRUPTED: + return DID_TRANSPORT_DISRUPTED; + case XEN_VSCSIIF_RSLT_HOST_TRANSPORT_FAILFAST: + return DID_TRANSPORT_FAILFAST; + case XEN_VSCSIIF_RSLT_HOST_TARGET_FAILURE: + return DID_TARGET_FAILURE; + case XEN_VSCSIIF_RSLT_HOST_NEXUS_FAILURE: + return DID_NEXUS_FAILURE; + case XEN_VSCSIIF_RSLT_HOST_ALLOC_FAILURE: + return DID_ALLOC_FAILURE; + case XEN_VSCSIIF_RSLT_HOST_MEDIUM_ERROR: + return DID_MEDIUM_ERROR; + case XEN_VSCSIIF_RSLT_HOST_TRANSPORT_MARGINAL: + return DID_TRANSPORT_MARGINAL; + default: + return DID_ERROR; + } +} + static void scsifront_cdb_cmd_done(struct vscsifrnt_info *info, struct vscsiif_response *ring_rsp) { @@ -250,7 +311,6 @@ static void scsifront_cdb_cmd_done(struct vscsifrnt_info *info, struct scsi_cmnd *sc; uint32_t id; uint8_t sense_len; - int result; id = ring_rsp->rqid; shadow = info->shadow[id]; @@ -259,14 +319,12 @@ static void scsifront_cdb_cmd_done(struct vscsifrnt_info *info, BUG_ON(sc == NULL); scsifront_gnttab_done(info, shadow); + if (info->host_active == STATE_ERROR) + return; scsifront_put_rqid(info, id); - result = ring_rsp->rslt; - if (result >> 24) - set_host_byte(sc, DID_ERROR); - else - set_host_byte(sc, host_byte(result)); - set_status_byte(sc, result & 0xff); + set_host_byte(sc, scsifront_host_byte(ring_rsp->rslt)); + set_status_byte(sc, XEN_VSCSIIF_RSLT_STATUS(ring_rsp->rslt)); scsi_set_resid(sc, ring_rsp->residual_len); sense_len = min_t(uint8_t, VSCSIIF_SENSE_BUFFERSIZE, @@ -290,7 +348,10 @@ static void scsifront_sync_cmd_done(struct vscsifrnt_info *info, shadow->wait_reset = 1; switch (shadow->rslt_reset) { case RSLT_RESET_WAITING: - shadow->rslt_reset = ring_rsp->rslt; + if (ring_rsp->rslt == XEN_VSCSIIF_RSLT_RESET_SUCCESS) + shadow->rslt_reset = SUCCESS; + else + shadow->rslt_reset = FAILED; break; case RSLT_RESET_ERR: kick = _scsifront_put_rqid(info, id); @@ -300,9 +361,7 @@ static void scsifront_sync_cmd_done(struct vscsifrnt_info *info, scsifront_wake_up(info); return; default: - shost_printk(KERN_ERR, info->host, KBUILD_MODNAME - "bad reset state %d, possibly leaking %u\n", - shadow->rslt_reset, id); + scsifront_set_error(info, "bad reset state"); break; } spin_unlock_irqrestore(&info->shadow_lock, flags); @@ -313,28 +372,41 @@ static void scsifront_sync_cmd_done(struct vscsifrnt_info *info, static void scsifront_do_response(struct vscsifrnt_info *info, struct vscsiif_response *ring_rsp) { - if (WARN(ring_rsp->rqid >= VSCSIIF_MAX_REQS || - test_bit(ring_rsp->rqid, info->shadow_free_bitmap), - "illegal rqid %u returned by backend!\n", ring_rsp->rqid)) + struct vscsifrnt_shadow *shadow; + + if (ring_rsp->rqid >= VSCSIIF_MAX_REQS || + !info->shadow[ring_rsp->rqid]->inflight) { + scsifront_set_error(info, "illegal rqid returned by backend!"); return; + } + shadow = info->shadow[ring_rsp->rqid]; + shadow->inflight = false; - if (info->shadow[ring_rsp->rqid]->act == VSCSIIF_ACT_SCSI_CDB) + if (shadow->act == VSCSIIF_ACT_SCSI_CDB) scsifront_cdb_cmd_done(info, ring_rsp); else scsifront_sync_cmd_done(info, ring_rsp); } -static int scsifront_ring_drain(struct vscsifrnt_info *info) +static int scsifront_ring_drain(struct vscsifrnt_info *info, + unsigned int *eoiflag) { - struct vscsiif_response *ring_rsp; + struct vscsiif_response ring_rsp; RING_IDX i, rp; int more_to_do = 0; - rp = info->ring.sring->rsp_prod; - rmb(); /* ordering required respective to dom0 */ + rp = READ_ONCE(info->ring.sring->rsp_prod); + virt_rmb(); /* ordering required respective to backend */ + if (RING_RESPONSE_PROD_OVERFLOW(&info->ring, rp)) { + scsifront_set_error(info, "illegal number of responses"); + return 0; + } for (i = info->ring.rsp_cons; i != rp; i++) { - ring_rsp = RING_GET_RESPONSE(&info->ring, i); - scsifront_do_response(info, ring_rsp); + RING_COPY_RESPONSE(&info->ring, i, &ring_rsp); + scsifront_do_response(info, &ring_rsp); + if (info->host_active == STATE_ERROR) + return 0; + *eoiflag &= ~XEN_EOI_FLAG_SPURIOUS; } info->ring.rsp_cons = i; @@ -347,14 +419,15 @@ static int scsifront_ring_drain(struct vscsifrnt_info *info) return more_to_do; } -static int scsifront_cmd_done(struct vscsifrnt_info *info) +static int scsifront_cmd_done(struct vscsifrnt_info *info, + unsigned int *eoiflag) { int more_to_do; unsigned long flags; spin_lock_irqsave(info->host->host_lock, flags); - more_to_do = scsifront_ring_drain(info); + more_to_do = scsifront_ring_drain(info, eoiflag); info->wait_ring_available = 0; @@ -368,20 +441,28 @@ static int scsifront_cmd_done(struct vscsifrnt_info *info) static irqreturn_t scsifront_irq_fn(int irq, void *dev_id) { struct vscsifrnt_info *info = dev_id; + unsigned int eoiflag = XEN_EOI_FLAG_SPURIOUS; - while (scsifront_cmd_done(info)) + if (info->host_active == STATE_ERROR) { + xen_irq_lateeoi(irq, XEN_EOI_FLAG_SPURIOUS); + return IRQ_HANDLED; + } + + while (scsifront_cmd_done(info, &eoiflag)) /* Yield point for this unbounded loop. */ cond_resched(); + xen_irq_lateeoi(irq, eoiflag); + return IRQ_HANDLED; } static void scsifront_finish_all(struct vscsifrnt_info *info) { - unsigned i; + unsigned int i, dummy; struct vscsiif_response resp; - scsifront_ring_drain(info); + scsifront_ring_drain(info, &dummy); for (i = 0; i < VSCSIIF_MAX_REQS; i++) { if (test_bit(i, info->shadow_free_bitmap)) @@ -538,6 +619,9 @@ static int scsifront_queuecommand(struct Scsi_Host *shost, unsigned long flags; int err; + if (info->host_active == STATE_ERROR) + return SCSI_MLQUEUE_HOST_BUSY; + sc->result = 0; shadow->sc = sc; @@ -590,6 +674,9 @@ static int scsifront_action_handler(struct scsi_cmnd *sc, uint8_t act) struct vscsifrnt_shadow *shadow, *s = scsi_cmd_priv(sc); int err = 0; + if (info->host_active == STATE_ERROR) + return FAILED; + shadow = kzalloc(sizeof(*shadow), GFP_NOIO); if (!shadow) return FAILED; @@ -661,6 +748,9 @@ static int scsifront_sdev_configure(struct scsi_device *sdev) struct vscsifrnt_info *info = shost_priv(sdev->host); int err; + if (info->host_active == STATE_ERROR) + return -EIO; + if (info && current == info->curr) { err = xenbus_printf(XBT_NIL, info->dev->nodename, info->dev_state_path, "%d", XenbusStateConnected); @@ -708,27 +798,15 @@ static int scsifront_alloc_ring(struct vscsifrnt_info *info) { struct xenbus_device *dev = info->dev; struct vscsiif_sring *sring; - grant_ref_t gref; - int err = -ENOMEM; + int err; /***** Frontend to Backend ring start *****/ - sring = (struct vscsiif_sring *)__get_free_page(GFP_KERNEL); - if (!sring) { - xenbus_dev_fatal(dev, err, - "fail to allocate shared ring (Front to Back)"); + err = xenbus_setup_ring(dev, GFP_KERNEL, (void **)&sring, 1, + &info->ring_ref); + if (err) return err; - } - SHARED_RING_INIT(sring); - FRONT_RING_INIT(&info->ring, sring, PAGE_SIZE); - err = xenbus_grant_ring(dev, sring, 1, &gref); - if (err < 0) { - free_page((unsigned long)sring); - xenbus_dev_fatal(dev, err, - "fail to grant shared ring (Front to Back)"); - return err; - } - info->ring_ref = gref; + XEN_FRONT_RING_INIT(&info->ring, sring, PAGE_SIZE); err = xenbus_alloc_evtchn(dev, &info->evtchn); if (err) { @@ -736,7 +814,7 @@ static int scsifront_alloc_ring(struct vscsifrnt_info *info) goto free_gnttab; } - err = bind_evtchn_to_irq(info->evtchn); + err = bind_evtchn_to_irq_lateeoi(info->evtchn); if (err <= 0) { xenbus_dev_fatal(dev, err, "bind_evtchn_to_irq"); goto free_gnttab; @@ -757,8 +835,7 @@ static int scsifront_alloc_ring(struct vscsifrnt_info *info) free_irq: unbind_from_irqhandler(info->irq, info); free_gnttab: - gnttab_end_foreign_access(info->ring_ref, - (unsigned long)info->ring.sring); + xenbus_teardown_ring((void **)&sring, 1, &info->ring_ref); return err; } @@ -766,8 +843,7 @@ free_gnttab: static void scsifront_free_ring(struct vscsifrnt_info *info) { unbind_from_irqhandler(info->irq, info); - gnttab_end_foreign_access(info->ring_ref, - (unsigned long)info->ring.sring); + xenbus_teardown_ring((void **)&info->ring.sring, 1, &info->ring_ref); } static int scsifront_init_ring(struct vscsifrnt_info *info) @@ -866,7 +942,7 @@ static int scsifront_probe(struct xenbus_device *dev, goto free_sring; } info->host = host; - info->host_active = 1; + info->host_active = STATE_ACTIVE; xenbus_switch_state(dev, XenbusStateInitialised); @@ -934,10 +1010,10 @@ static int scsifront_remove(struct xenbus_device *dev) pr_debug("%s: %s removed\n", __func__, dev->nodename); mutex_lock(&scsifront_mutex); - if (info->host_active) { + if (info->host_active != STATE_INACTIVE) { /* Scsi_host not yet removed */ scsi_remove_host(info->host); - info->host_active = 0; + info->host_active = STATE_INACTIVE; } mutex_unlock(&scsifront_mutex); @@ -961,9 +1037,9 @@ static void scsifront_disconnect(struct vscsifrnt_info *info) */ mutex_lock(&scsifront_mutex); - if (info->host_active) { + if (info->host_active != STATE_INACTIVE) { scsi_remove_host(host); - info->host_active = 0; + info->host_active = STATE_INACTIVE; } mutex_unlock(&scsifront_mutex); @@ -981,6 +1057,9 @@ static void scsifront_do_lun_hotplug(struct vscsifrnt_info *info, int op) unsigned int hst, chn, tgt, lun; struct scsi_device *sdev; + if (info->host_active == STATE_ERROR) + return; + dir = xenbus_directory(XBT_NIL, dev->otherend, "vscsi-devs", &dir_n); if (IS_ERR(dir)) return; diff --git a/drivers/scsi/zorro7xx.c b/drivers/scsi/zorro7xx.c index 27b9e2baab1a..7acf9193a9e8 100644 --- a/drivers/scsi/zorro7xx.c +++ b/drivers/scsi/zorro7xx.c @@ -159,6 +159,8 @@ static void zorro7xx_remove_one(struct zorro_dev *z) scsi_remove_host(host); NCR_700_release(host); + if (host->base > 0x01000000) + iounmap(hostdata->base); kfree(hostdata); free_irq(host->irq, host); zorro_release_device(z); diff --git a/drivers/slimbus/qcom-ctrl.c b/drivers/slimbus/qcom-ctrl.c index f04b961b96cd..ec58091fc948 100644 --- a/drivers/slimbus/qcom-ctrl.c +++ b/drivers/slimbus/qcom-ctrl.c @@ -510,9 +510,9 @@ static int qcom_slim_probe(struct platform_device *pdev) } ctrl->irq = platform_get_irq(pdev, 0); - if (!ctrl->irq) { + if (ctrl->irq < 0) { dev_err(&pdev->dev, "no slimbus IRQ\n"); - return -ENODEV; + return ctrl->irq; } sctrl = &ctrl->ctrl; diff --git a/drivers/soc/imx/imx8m-blk-ctrl.c b/drivers/soc/imx/imx8m-blk-ctrl.c index 122f9c884b38..ccd0577a771e 100644 --- a/drivers/soc/imx/imx8m-blk-ctrl.c +++ b/drivers/soc/imx/imx8m-blk-ctrl.c @@ -50,7 +50,7 @@ struct imx8m_blk_ctrl_domain_data { u32 mipi_phy_rst_mask; }; -#define DOMAIN_MAX_CLKS 3 +#define DOMAIN_MAX_CLKS 4 struct imx8m_blk_ctrl_domain { struct generic_pm_domain genpd; diff --git a/drivers/soc/rockchip/pm_domains.c b/drivers/soc/rockchip/pm_domains.c index 0868b7d406fb..b1cf7d29dafd 100644 --- a/drivers/soc/rockchip/pm_domains.c +++ b/drivers/soc/rockchip/pm_domains.c @@ -8,6 +8,7 @@ #include <linux/io.h> #include <linux/iopoll.h> #include <linux/err.h> +#include <linux/mutex.h> #include <linux/pm_clock.h> #include <linux/pm_domain.h> #include <linux/of_address.h> @@ -16,6 +17,7 @@ #include <linux/clk.h> #include <linux/regmap.h> #include <linux/mfd/syscon.h> +#include <soc/rockchip/pm_domains.h> #include <dt-bindings/power/px30-power.h> #include <dt-bindings/power/rk3036-power.h> #include <dt-bindings/power/rk3066-power.h> @@ -139,6 +141,109 @@ struct rockchip_pmu { #define DOMAIN_RK3568(name, pwr, req, wakeup) \ DOMAIN_M(name, pwr, pwr, req, req, req, wakeup) +/* + * Dynamic Memory Controller may need to coordinate with us -- see + * rockchip_pmu_block(). + * + * dmc_pmu_mutex protects registration-time races, so DMC driver doesn't try to + * block() while we're initializing the PMU. + */ +static DEFINE_MUTEX(dmc_pmu_mutex); +static struct rockchip_pmu *dmc_pmu; + +/* + * Block PMU transitions and make sure they don't interfere with ARM Trusted + * Firmware operations. There are two conflicts, noted in the comments below. + * + * Caller must unblock PMU transitions via rockchip_pmu_unblock(). + */ +int rockchip_pmu_block(void) +{ + struct rockchip_pmu *pmu; + struct generic_pm_domain *genpd; + struct rockchip_pm_domain *pd; + int i, ret; + + mutex_lock(&dmc_pmu_mutex); + + /* No PMU (yet)? Then we just block rockchip_pmu_probe(). */ + if (!dmc_pmu) + return 0; + pmu = dmc_pmu; + + /* + * mutex blocks all idle transitions: we can't touch the + * PMU_BUS_IDLE_REQ (our ".idle_offset") register while ARM Trusted + * Firmware might be using it. + */ + mutex_lock(&pmu->mutex); + + /* + * Power domain clocks: Per Rockchip, we *must* keep certain clocks + * enabled for the duration of power-domain transitions. Most + * transitions are handled by this driver, but some cases (in + * particular, DRAM DVFS / memory-controller idle) must be handled by + * firmware. Firmware can handle most clock management via a special + * "ungate" register (PMU_CRU_GATEDIS_CON0), but unfortunately, this + * doesn't handle PLLs. We can assist this transition by doing the + * clock management on behalf of firmware. + */ + for (i = 0; i < pmu->genpd_data.num_domains; i++) { + genpd = pmu->genpd_data.domains[i]; + if (genpd) { + pd = to_rockchip_pd(genpd); + ret = clk_bulk_enable(pd->num_clks, pd->clks); + if (ret < 0) { + dev_err(pmu->dev, + "failed to enable clks for domain '%s': %d\n", + genpd->name, ret); + goto err; + } + } + } + + return 0; + +err: + for (i = i - 1; i >= 0; i--) { + genpd = pmu->genpd_data.domains[i]; + if (genpd) { + pd = to_rockchip_pd(genpd); + clk_bulk_disable(pd->num_clks, pd->clks); + } + } + mutex_unlock(&pmu->mutex); + mutex_unlock(&dmc_pmu_mutex); + + return ret; +} +EXPORT_SYMBOL_GPL(rockchip_pmu_block); + +/* Unblock PMU transitions. */ +void rockchip_pmu_unblock(void) +{ + struct rockchip_pmu *pmu; + struct generic_pm_domain *genpd; + struct rockchip_pm_domain *pd; + int i; + + if (dmc_pmu) { + pmu = dmc_pmu; + for (i = 0; i < pmu->genpd_data.num_domains; i++) { + genpd = pmu->genpd_data.domains[i]; + if (genpd) { + pd = to_rockchip_pd(genpd); + clk_bulk_disable(pd->num_clks, pd->clks); + } + } + + mutex_unlock(&pmu->mutex); + } + + mutex_unlock(&dmc_pmu_mutex); +} +EXPORT_SYMBOL_GPL(rockchip_pmu_unblock); + static bool rockchip_pmu_domain_is_idle(struct rockchip_pm_domain *pd) { struct rockchip_pmu *pmu = pd->pmu; @@ -690,6 +795,12 @@ static int rockchip_pm_domain_probe(struct platform_device *pdev) error = -ENODEV; + /* + * Prevent any rockchip_pmu_block() from racing with the remainder of + * setup (clocks, register initialization). + */ + mutex_lock(&dmc_pmu_mutex); + for_each_available_child_of_node(np, node) { error = rockchip_pm_add_one_domain(pmu, node); if (error) { @@ -719,10 +830,17 @@ static int rockchip_pm_domain_probe(struct platform_device *pdev) goto err_out; } + /* We only expect one PMU. */ + if (!WARN_ON_ONCE(dmc_pmu)) + dmc_pmu = pmu; + + mutex_unlock(&dmc_pmu_mutex); + return 0; err_out: rockchip_pm_domain_cleanup(pmu); + mutex_unlock(&dmc_pmu_mutex); return error; } diff --git a/drivers/spi/Kconfig b/drivers/spi/Kconfig index d2815eb361c0..38117775ff79 100644 --- a/drivers/spi/Kconfig +++ b/drivers/spi/Kconfig @@ -101,6 +101,17 @@ config SPI_ARMADA_3700 This enables support for the SPI controller present on the Marvell Armada 3700 SoCs. +config SPI_ASPEED_SMC + tristate "Aspeed flash controllers in SPI mode" + depends on ARCH_ASPEED || COMPILE_TEST + depends on OF + help + This enables support for the Firmware Memory controller (FMC) + in the Aspeed AST2600, AST2500 and AST2400 SoCs when attached + to SPI NOR chips, and support for the SPI flash memory + controller (SPI) for the host firmware. The implementation + only supports SPI NOR. + config SPI_ATMEL tristate "Atmel SPI Controller" depends on ARCH_AT91 || COMPILE_TEST @@ -414,15 +425,14 @@ config SPI_IMG_SPFI config SPI_IMX tristate "Freescale i.MX SPI controllers" depends on ARCH_MXC || COMPILE_TEST - select SPI_BITBANG help This enables support for the Freescale i.MX SPI controllers. config SPI_INGENIC - tristate "Ingenic JZ47xx SoCs SPI controller" + tristate "Ingenic SoCs SPI controller" depends on MACH_INGENIC || COMPILE_TEST help - This enables support for the Ingenic JZ47xx SoCs SPI controller. + This enables support for the Ingenic SoCs SPI controller. To compile this driver as a module, choose M here: the module will be called spi-ingenic. @@ -590,6 +600,16 @@ config SPI_MTK_NOR SPI interface as well as several SPI NOR specific instructions via SPI MEM interface. +config SPI_MTK_SNFI + tristate "MediaTek SPI NAND Flash Interface" + depends on ARCH_MEDIATEK || COMPILE_TEST + depends on MTD_NAND_ECC_MEDIATEK + help + This enables support for SPI-NAND mode on the MediaTek NAND + Flash Interface found on MediaTek ARM SoCs. This controller + is implemented as a SPI-MEM controller with pipelined ECC + capcability. + config SPI_NPCM_FIU tristate "Nuvoton NPCM FLASH Interface Unit" depends on ARCH_NPCM || COMPILE_TEST diff --git a/drivers/spi/Makefile b/drivers/spi/Makefile index 3aa28ed3f761..0f44eb6083a5 100644 --- a/drivers/spi/Makefile +++ b/drivers/spi/Makefile @@ -19,6 +19,7 @@ obj-$(CONFIG_SPI_ALTERA_CORE) += spi-altera-core.o obj-$(CONFIG_SPI_ALTERA_DFL) += spi-altera-dfl.o obj-$(CONFIG_SPI_AR934X) += spi-ar934x.o obj-$(CONFIG_SPI_ARMADA_3700) += spi-armada-3700.o +obj-$(CONFIG_SPI_ASPEED_SMC) += spi-aspeed-smc.o obj-$(CONFIG_SPI_ATMEL) += spi-atmel.o obj-$(CONFIG_SPI_ATMEL_QUADSPI) += atmel-quadspi.o obj-$(CONFIG_SPI_AT91_USART) += spi-at91-usart.o @@ -76,6 +77,7 @@ obj-$(CONFIG_SPI_MPC52xx) += spi-mpc52xx.o obj-$(CONFIG_SPI_MT65XX) += spi-mt65xx.o obj-$(CONFIG_SPI_MT7621) += spi-mt7621.o obj-$(CONFIG_SPI_MTK_NOR) += spi-mtk-nor.o +obj-$(CONFIG_SPI_MTK_SNFI) += spi-mtk-snfi.o obj-$(CONFIG_SPI_MXIC) += spi-mxic.o obj-$(CONFIG_SPI_MXS) += spi-mxs.o obj-$(CONFIG_SPI_NPCM_FIU) += spi-npcm-fiu.o diff --git a/drivers/spi/atmel-quadspi.c b/drivers/spi/atmel-quadspi.c index 92d9610df1fd..480c0c8c18e4 100644 --- a/drivers/spi/atmel-quadspi.c +++ b/drivers/spi/atmel-quadspi.c @@ -277,6 +277,9 @@ static int atmel_qspi_find_mode(const struct spi_mem_op *op) static bool atmel_qspi_supports_op(struct spi_mem *mem, const struct spi_mem_op *op) { + if (!spi_mem_default_supports_op(mem, op)) + return false; + if (atmel_qspi_find_mode(op) < 0) return false; @@ -285,12 +288,6 @@ static bool atmel_qspi_supports_op(struct spi_mem *mem, op->dummy.nbytes == 0) return false; - /* DTR ops not supported. */ - if (op->cmd.dtr || op->addr.dtr || op->dummy.dtr || op->data.dtr) - return false; - if (op->cmd.nbytes != 1) - return false; - return true; } diff --git a/drivers/spi/spi-aspeed-smc.c b/drivers/spi/spi-aspeed-smc.c new file mode 100644 index 000000000000..496f3e1e9079 --- /dev/null +++ b/drivers/spi/spi-aspeed-smc.c @@ -0,0 +1,1210 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * ASPEED FMC/SPI Memory Controller Driver + * + * Copyright (c) 2015-2022, IBM Corporation. + * Copyright (c) 2020, ASPEED Corporation. + */ + +#include <linux/clk.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/of_platform.h> +#include <linux/platform_device.h> +#include <linux/spi/spi.h> +#include <linux/spi/spi-mem.h> + +#define DEVICE_NAME "spi-aspeed-smc" + +/* Type setting Register */ +#define CONFIG_REG 0x0 +#define CONFIG_TYPE_SPI 0x2 + +/* CE Control Register */ +#define CE_CTRL_REG 0x4 + +/* CEx Control Register */ +#define CE0_CTRL_REG 0x10 +#define CTRL_IO_MODE_MASK GENMASK(30, 28) +#define CTRL_IO_SINGLE_DATA 0x0 +#define CTRL_IO_DUAL_DATA BIT(29) +#define CTRL_IO_QUAD_DATA BIT(30) +#define CTRL_COMMAND_SHIFT 16 +#define CTRL_IO_ADDRESS_4B BIT(13) /* AST2400 SPI only */ +#define CTRL_IO_DUMMY_SET(dummy) \ + (((((dummy) >> 2) & 0x1) << 14) | (((dummy) & 0x3) << 6)) +#define CTRL_FREQ_SEL_SHIFT 8 +#define CTRL_FREQ_SEL_MASK GENMASK(11, CTRL_FREQ_SEL_SHIFT) +#define CTRL_CE_STOP_ACTIVE BIT(2) +#define CTRL_IO_MODE_CMD_MASK GENMASK(1, 0) +#define CTRL_IO_MODE_NORMAL 0x0 +#define CTRL_IO_MODE_READ 0x1 +#define CTRL_IO_MODE_WRITE 0x2 +#define CTRL_IO_MODE_USER 0x3 + +#define CTRL_IO_CMD_MASK 0xf0ff40c3 + +/* CEx Address Decoding Range Register */ +#define CE0_SEGMENT_ADDR_REG 0x30 + +/* CEx Read timing compensation register */ +#define CE0_TIMING_COMPENSATION_REG 0x94 + +enum aspeed_spi_ctl_reg_value { + ASPEED_SPI_BASE, + ASPEED_SPI_READ, + ASPEED_SPI_WRITE, + ASPEED_SPI_MAX, +}; + +struct aspeed_spi; + +struct aspeed_spi_chip { + struct aspeed_spi *aspi; + u32 cs; + void __iomem *ctl; + void __iomem *ahb_base; + u32 ahb_window_size; + u32 ctl_val[ASPEED_SPI_MAX]; + u32 clk_freq; +}; + +struct aspeed_spi_data { + u32 ctl0; + u32 max_cs; + bool hastype; + u32 mode_bits; + u32 we0; + u32 timing; + u32 hclk_mask; + u32 hdiv_max; + + u32 (*segment_start)(struct aspeed_spi *aspi, u32 reg); + u32 (*segment_end)(struct aspeed_spi *aspi, u32 reg); + u32 (*segment_reg)(struct aspeed_spi *aspi, u32 start, u32 end); + int (*calibrate)(struct aspeed_spi_chip *chip, u32 hdiv, + const u8 *golden_buf, u8 *test_buf); +}; + +#define ASPEED_SPI_MAX_NUM_CS 5 + +struct aspeed_spi { + const struct aspeed_spi_data *data; + + void __iomem *regs; + void __iomem *ahb_base; + u32 ahb_base_phy; + u32 ahb_window_size; + struct device *dev; + + struct clk *clk; + u32 clk_freq; + + struct aspeed_spi_chip chips[ASPEED_SPI_MAX_NUM_CS]; +}; + +static u32 aspeed_spi_get_io_mode(const struct spi_mem_op *op) +{ + switch (op->data.buswidth) { + case 1: + return CTRL_IO_SINGLE_DATA; + case 2: + return CTRL_IO_DUAL_DATA; + case 4: + return CTRL_IO_QUAD_DATA; + default: + return CTRL_IO_SINGLE_DATA; + } +} + +static void aspeed_spi_set_io_mode(struct aspeed_spi_chip *chip, u32 io_mode) +{ + u32 ctl; + + if (io_mode > 0) { + ctl = readl(chip->ctl) & ~CTRL_IO_MODE_MASK; + ctl |= io_mode; + writel(ctl, chip->ctl); + } +} + +static void aspeed_spi_start_user(struct aspeed_spi_chip *chip) +{ + u32 ctl = chip->ctl_val[ASPEED_SPI_BASE]; + + ctl |= CTRL_IO_MODE_USER | CTRL_CE_STOP_ACTIVE; + writel(ctl, chip->ctl); + + ctl &= ~CTRL_CE_STOP_ACTIVE; + writel(ctl, chip->ctl); +} + +static void aspeed_spi_stop_user(struct aspeed_spi_chip *chip) +{ + u32 ctl = chip->ctl_val[ASPEED_SPI_READ] | + CTRL_IO_MODE_USER | CTRL_CE_STOP_ACTIVE; + + writel(ctl, chip->ctl); + + /* Restore defaults */ + writel(chip->ctl_val[ASPEED_SPI_READ], chip->ctl); +} + +static int aspeed_spi_read_from_ahb(void *buf, void __iomem *src, size_t len) +{ + size_t offset = 0; + + if (IS_ALIGNED((uintptr_t)src, sizeof(uintptr_t)) && + IS_ALIGNED((uintptr_t)buf, sizeof(uintptr_t))) { + ioread32_rep(src, buf, len >> 2); + offset = len & ~0x3; + len -= offset; + } + ioread8_rep(src, (u8 *)buf + offset, len); + return 0; +} + +static int aspeed_spi_write_to_ahb(void __iomem *dst, const void *buf, size_t len) +{ + size_t offset = 0; + + if (IS_ALIGNED((uintptr_t)dst, sizeof(uintptr_t)) && + IS_ALIGNED((uintptr_t)buf, sizeof(uintptr_t))) { + iowrite32_rep(dst, buf, len >> 2); + offset = len & ~0x3; + len -= offset; + } + iowrite8_rep(dst, (const u8 *)buf + offset, len); + return 0; +} + +static int aspeed_spi_send_cmd_addr(struct aspeed_spi_chip *chip, u8 addr_nbytes, + u64 offset, u32 opcode) +{ + __be32 temp; + u32 cmdaddr; + + switch (addr_nbytes) { + case 3: + cmdaddr = offset & 0xFFFFFF; + cmdaddr |= opcode << 24; + + temp = cpu_to_be32(cmdaddr); + aspeed_spi_write_to_ahb(chip->ahb_base, &temp, 4); + break; + case 4: + temp = cpu_to_be32(offset); + aspeed_spi_write_to_ahb(chip->ahb_base, &opcode, 1); + aspeed_spi_write_to_ahb(chip->ahb_base, &temp, 4); + break; + default: + WARN_ONCE(1, "Unexpected address width %u", addr_nbytes); + return -EOPNOTSUPP; + } + return 0; +} + +static int aspeed_spi_read_reg(struct aspeed_spi_chip *chip, + const struct spi_mem_op *op) +{ + aspeed_spi_start_user(chip); + aspeed_spi_write_to_ahb(chip->ahb_base, &op->cmd.opcode, 1); + aspeed_spi_read_from_ahb(op->data.buf.in, + chip->ahb_base, op->data.nbytes); + aspeed_spi_stop_user(chip); + return 0; +} + +static int aspeed_spi_write_reg(struct aspeed_spi_chip *chip, + const struct spi_mem_op *op) +{ + aspeed_spi_start_user(chip); + aspeed_spi_write_to_ahb(chip->ahb_base, &op->cmd.opcode, 1); + aspeed_spi_write_to_ahb(chip->ahb_base, op->data.buf.out, + op->data.nbytes); + aspeed_spi_stop_user(chip); + return 0; +} + +static ssize_t aspeed_spi_read_user(struct aspeed_spi_chip *chip, + const struct spi_mem_op *op, + u64 offset, size_t len, void *buf) +{ + int io_mode = aspeed_spi_get_io_mode(op); + u8 dummy = 0xFF; + int i; + int ret; + + aspeed_spi_start_user(chip); + + ret = aspeed_spi_send_cmd_addr(chip, op->addr.nbytes, offset, op->cmd.opcode); + if (ret < 0) + return ret; + + if (op->dummy.buswidth && op->dummy.nbytes) { + for (i = 0; i < op->dummy.nbytes / op->dummy.buswidth; i++) + aspeed_spi_write_to_ahb(chip->ahb_base, &dummy, sizeof(dummy)); + } + + aspeed_spi_set_io_mode(chip, io_mode); + + aspeed_spi_read_from_ahb(buf, chip->ahb_base, len); + aspeed_spi_stop_user(chip); + return 0; +} + +static ssize_t aspeed_spi_write_user(struct aspeed_spi_chip *chip, + const struct spi_mem_op *op) +{ + int ret; + + aspeed_spi_start_user(chip); + ret = aspeed_spi_send_cmd_addr(chip, op->addr.nbytes, op->addr.val, op->cmd.opcode); + if (ret < 0) + return ret; + aspeed_spi_write_to_ahb(chip->ahb_base, op->data.buf.out, op->data.nbytes); + aspeed_spi_stop_user(chip); + return 0; +} + +/* support for 1-1-1, 1-1-2 or 1-1-4 */ +static bool aspeed_spi_supports_op(struct spi_mem *mem, const struct spi_mem_op *op) +{ + if (op->cmd.buswidth > 1) + return false; + + if (op->addr.nbytes != 0) { + if (op->addr.buswidth > 1) + return false; + if (op->addr.nbytes < 3 || op->addr.nbytes > 4) + return false; + } + + if (op->dummy.nbytes != 0) { + if (op->dummy.buswidth > 1 || op->dummy.nbytes > 7) + return false; + } + + if (op->data.nbytes != 0 && op->data.buswidth > 4) + return false; + + return spi_mem_default_supports_op(mem, op); +} + +static const struct aspeed_spi_data ast2400_spi_data; + +static int do_aspeed_spi_exec_op(struct spi_mem *mem, const struct spi_mem_op *op) +{ + struct aspeed_spi *aspi = spi_controller_get_devdata(mem->spi->master); + struct aspeed_spi_chip *chip = &aspi->chips[mem->spi->chip_select]; + u32 addr_mode, addr_mode_backup; + u32 ctl_val; + int ret = 0; + + dev_dbg(aspi->dev, + "CE%d %s OP %#x mode:%d.%d.%d.%d naddr:%#x ndummies:%#x len:%#x", + chip->cs, op->data.dir == SPI_MEM_DATA_IN ? "read" : "write", + op->cmd.opcode, op->cmd.buswidth, op->addr.buswidth, + op->dummy.buswidth, op->data.buswidth, + op->addr.nbytes, op->dummy.nbytes, op->data.nbytes); + + addr_mode = readl(aspi->regs + CE_CTRL_REG); + addr_mode_backup = addr_mode; + + ctl_val = chip->ctl_val[ASPEED_SPI_BASE]; + ctl_val &= ~CTRL_IO_CMD_MASK; + + ctl_val |= op->cmd.opcode << CTRL_COMMAND_SHIFT; + + /* 4BYTE address mode */ + if (op->addr.nbytes) { + if (op->addr.nbytes == 4) + addr_mode |= (0x11 << chip->cs); + else + addr_mode &= ~(0x11 << chip->cs); + + if (op->addr.nbytes == 4 && chip->aspi->data == &ast2400_spi_data) + ctl_val |= CTRL_IO_ADDRESS_4B; + } + + if (op->dummy.nbytes) + ctl_val |= CTRL_IO_DUMMY_SET(op->dummy.nbytes / op->dummy.buswidth); + + if (op->data.nbytes) + ctl_val |= aspeed_spi_get_io_mode(op); + + if (op->data.dir == SPI_MEM_DATA_OUT) + ctl_val |= CTRL_IO_MODE_WRITE; + else + ctl_val |= CTRL_IO_MODE_READ; + + if (addr_mode != addr_mode_backup) + writel(addr_mode, aspi->regs + CE_CTRL_REG); + writel(ctl_val, chip->ctl); + + if (op->data.dir == SPI_MEM_DATA_IN) { + if (!op->addr.nbytes) + ret = aspeed_spi_read_reg(chip, op); + else + ret = aspeed_spi_read_user(chip, op, op->addr.val, + op->data.nbytes, op->data.buf.in); + } else { + if (!op->addr.nbytes) + ret = aspeed_spi_write_reg(chip, op); + else + ret = aspeed_spi_write_user(chip, op); + } + + /* Restore defaults */ + if (addr_mode != addr_mode_backup) + writel(addr_mode_backup, aspi->regs + CE_CTRL_REG); + writel(chip->ctl_val[ASPEED_SPI_READ], chip->ctl); + return ret; +} + +static int aspeed_spi_exec_op(struct spi_mem *mem, const struct spi_mem_op *op) +{ + int ret; + + ret = do_aspeed_spi_exec_op(mem, op); + if (ret) + dev_err(&mem->spi->dev, "operation failed: %d\n", ret); + return ret; +} + +static const char *aspeed_spi_get_name(struct spi_mem *mem) +{ + struct aspeed_spi *aspi = spi_controller_get_devdata(mem->spi->master); + struct device *dev = aspi->dev; + + return devm_kasprintf(dev, GFP_KERNEL, "%s.%d", dev_name(dev), mem->spi->chip_select); +} + +struct aspeed_spi_window { + u32 cs; + u32 offset; + u32 size; +}; + +static void aspeed_spi_get_windows(struct aspeed_spi *aspi, + struct aspeed_spi_window windows[ASPEED_SPI_MAX_NUM_CS]) +{ + const struct aspeed_spi_data *data = aspi->data; + u32 reg_val; + u32 cs; + + for (cs = 0; cs < aspi->data->max_cs; cs++) { + reg_val = readl(aspi->regs + CE0_SEGMENT_ADDR_REG + cs * 4); + windows[cs].cs = cs; + windows[cs].size = data->segment_end(aspi, reg_val) - + data->segment_start(aspi, reg_val); + windows[cs].offset = cs ? windows[cs - 1].offset + windows[cs - 1].size : 0; + dev_vdbg(aspi->dev, "CE%d offset=0x%.8x size=0x%x\n", cs, + windows[cs].offset, windows[cs].size); + } +} + +/* + * On the AST2600, some CE windows are closed by default at reset but + * U-Boot should open all. + */ +static int aspeed_spi_chip_set_default_window(struct aspeed_spi_chip *chip) +{ + struct aspeed_spi *aspi = chip->aspi; + struct aspeed_spi_window windows[ASPEED_SPI_MAX_NUM_CS] = { 0 }; + struct aspeed_spi_window *win = &windows[chip->cs]; + + /* No segment registers for the AST2400 SPI controller */ + if (aspi->data == &ast2400_spi_data) { + win->offset = 0; + win->size = aspi->ahb_window_size; + } else { + aspeed_spi_get_windows(aspi, windows); + } + + chip->ahb_base = aspi->ahb_base + win->offset; + chip->ahb_window_size = win->size; + + dev_dbg(aspi->dev, "CE%d default window [ 0x%.8x - 0x%.8x ] %dMB", + chip->cs, aspi->ahb_base_phy + win->offset, + aspi->ahb_base_phy + win->offset + win->size - 1, + win->size >> 20); + + return chip->ahb_window_size ? 0 : -1; +} + +static int aspeed_spi_set_window(struct aspeed_spi *aspi, + const struct aspeed_spi_window *win) +{ + u32 start = aspi->ahb_base_phy + win->offset; + u32 end = start + win->size; + void __iomem *seg_reg = aspi->regs + CE0_SEGMENT_ADDR_REG + win->cs * 4; + u32 seg_val_backup = readl(seg_reg); + u32 seg_val = aspi->data->segment_reg(aspi, start, end); + + if (seg_val == seg_val_backup) + return 0; + + writel(seg_val, seg_reg); + + /* + * Restore initial value if something goes wrong else we could + * loose access to the chip. + */ + if (seg_val != readl(seg_reg)) { + dev_err(aspi->dev, "CE%d invalid window [ 0x%.8x - 0x%.8x ] %dMB", + win->cs, start, end - 1, win->size >> 20); + writel(seg_val_backup, seg_reg); + return -EIO; + } + + if (win->size) + dev_dbg(aspi->dev, "CE%d new window [ 0x%.8x - 0x%.8x ] %dMB", + win->cs, start, end - 1, win->size >> 20); + else + dev_dbg(aspi->dev, "CE%d window closed", win->cs); + + return 0; +} + +/* + * Yet to be done when possible : + * - Align mappings on flash size (we don't have the info) + * - ioremap each window, not strictly necessary since the overall window + * is correct. + */ +static const struct aspeed_spi_data ast2500_spi_data; +static const struct aspeed_spi_data ast2600_spi_data; +static const struct aspeed_spi_data ast2600_fmc_data; + +static int aspeed_spi_chip_adjust_window(struct aspeed_spi_chip *chip, + u32 local_offset, u32 size) +{ + struct aspeed_spi *aspi = chip->aspi; + struct aspeed_spi_window windows[ASPEED_SPI_MAX_NUM_CS] = { 0 }; + struct aspeed_spi_window *win = &windows[chip->cs]; + int ret; + + /* No segment registers for the AST2400 SPI controller */ + if (aspi->data == &ast2400_spi_data) + return 0; + + /* + * Due to an HW issue on the AST2500 SPI controller, the CE0 + * window size should be smaller than the maximum 128MB. + */ + if (aspi->data == &ast2500_spi_data && chip->cs == 0 && size == SZ_128M) { + size = 120 << 20; + dev_info(aspi->dev, "CE%d window resized to %dMB (AST2500 HW quirk)", + chip->cs, size >> 20); + } + + /* + * The decoding size of AST2600 SPI controller should set at + * least 2MB. + */ + if ((aspi->data == &ast2600_spi_data || aspi->data == &ast2600_fmc_data) && + size < SZ_2M) { + size = SZ_2M; + dev_info(aspi->dev, "CE%d window resized to %dMB (AST2600 Decoding)", + chip->cs, size >> 20); + } + + aspeed_spi_get_windows(aspi, windows); + + /* Adjust this chip window */ + win->offset += local_offset; + win->size = size; + + if (win->offset + win->size > aspi->ahb_window_size) { + win->size = aspi->ahb_window_size - win->offset; + dev_warn(aspi->dev, "CE%d window resized to %dMB", chip->cs, win->size >> 20); + } + + ret = aspeed_spi_set_window(aspi, win); + if (ret) + return ret; + + /* Update chip mapping info */ + chip->ahb_base = aspi->ahb_base + win->offset; + chip->ahb_window_size = win->size; + + /* + * Also adjust next chip window to make sure that it does not + * overlap with the current window. + */ + if (chip->cs < aspi->data->max_cs - 1) { + struct aspeed_spi_window *next = &windows[chip->cs + 1]; + + /* Change offset and size to keep the same end address */ + if ((next->offset + next->size) > (win->offset + win->size)) + next->size = (next->offset + next->size) - (win->offset + win->size); + else + next->size = 0; + next->offset = win->offset + win->size; + + aspeed_spi_set_window(aspi, next); + } + return 0; +} + +static int aspeed_spi_do_calibration(struct aspeed_spi_chip *chip); + +static int aspeed_spi_dirmap_create(struct spi_mem_dirmap_desc *desc) +{ + struct aspeed_spi *aspi = spi_controller_get_devdata(desc->mem->spi->master); + struct aspeed_spi_chip *chip = &aspi->chips[desc->mem->spi->chip_select]; + struct spi_mem_op *op = &desc->info.op_tmpl; + u32 ctl_val; + int ret = 0; + + chip->clk_freq = desc->mem->spi->max_speed_hz; + + /* Only for reads */ + if (op->data.dir != SPI_MEM_DATA_IN) + return -EOPNOTSUPP; + + aspeed_spi_chip_adjust_window(chip, desc->info.offset, desc->info.length); + + if (desc->info.length > chip->ahb_window_size) + dev_warn(aspi->dev, "CE%d window (%dMB) too small for mapping", + chip->cs, chip->ahb_window_size >> 20); + + /* Define the default IO read settings */ + ctl_val = readl(chip->ctl) & ~CTRL_IO_CMD_MASK; + ctl_val |= aspeed_spi_get_io_mode(op) | + op->cmd.opcode << CTRL_COMMAND_SHIFT | + CTRL_IO_DUMMY_SET(op->dummy.nbytes / op->dummy.buswidth) | + CTRL_IO_MODE_READ; + + /* Tune 4BYTE address mode */ + if (op->addr.nbytes) { + u32 addr_mode = readl(aspi->regs + CE_CTRL_REG); + + if (op->addr.nbytes == 4) + addr_mode |= (0x11 << chip->cs); + else + addr_mode &= ~(0x11 << chip->cs); + writel(addr_mode, aspi->regs + CE_CTRL_REG); + + /* AST2400 SPI controller sets 4BYTE address mode in + * CE0 Control Register + */ + if (op->addr.nbytes == 4 && chip->aspi->data == &ast2400_spi_data) + ctl_val |= CTRL_IO_ADDRESS_4B; + } + + /* READ mode is the controller default setting */ + chip->ctl_val[ASPEED_SPI_READ] = ctl_val; + writel(chip->ctl_val[ASPEED_SPI_READ], chip->ctl); + + ret = aspeed_spi_do_calibration(chip); + + dev_info(aspi->dev, "CE%d read buswidth:%d [0x%08x]\n", + chip->cs, op->data.buswidth, chip->ctl_val[ASPEED_SPI_READ]); + + return ret; +} + +static ssize_t aspeed_spi_dirmap_read(struct spi_mem_dirmap_desc *desc, + u64 offset, size_t len, void *buf) +{ + struct aspeed_spi *aspi = spi_controller_get_devdata(desc->mem->spi->master); + struct aspeed_spi_chip *chip = &aspi->chips[desc->mem->spi->chip_select]; + + /* Switch to USER command mode if mapping window is too small */ + if (chip->ahb_window_size < offset + len) { + int ret; + + ret = aspeed_spi_read_user(chip, &desc->info.op_tmpl, offset, len, buf); + if (ret < 0) + return ret; + } else { + memcpy_fromio(buf, chip->ahb_base + offset, len); + } + + return len; +} + +static const struct spi_controller_mem_ops aspeed_spi_mem_ops = { + .supports_op = aspeed_spi_supports_op, + .exec_op = aspeed_spi_exec_op, + .get_name = aspeed_spi_get_name, + .dirmap_create = aspeed_spi_dirmap_create, + .dirmap_read = aspeed_spi_dirmap_read, +}; + +static void aspeed_spi_chip_set_type(struct aspeed_spi *aspi, unsigned int cs, int type) +{ + u32 reg; + + reg = readl(aspi->regs + CONFIG_REG); + reg &= ~(0x3 << (cs * 2)); + reg |= type << (cs * 2); + writel(reg, aspi->regs + CONFIG_REG); +} + +static void aspeed_spi_chip_enable(struct aspeed_spi *aspi, unsigned int cs, bool enable) +{ + u32 we_bit = BIT(aspi->data->we0 + cs); + u32 reg = readl(aspi->regs + CONFIG_REG); + + if (enable) + reg |= we_bit; + else + reg &= ~we_bit; + writel(reg, aspi->regs + CONFIG_REG); +} + +static int aspeed_spi_setup(struct spi_device *spi) +{ + struct aspeed_spi *aspi = spi_controller_get_devdata(spi->master); + const struct aspeed_spi_data *data = aspi->data; + unsigned int cs = spi->chip_select; + struct aspeed_spi_chip *chip = &aspi->chips[cs]; + + chip->aspi = aspi; + chip->cs = cs; + chip->ctl = aspi->regs + data->ctl0 + cs * 4; + + /* The driver only supports SPI type flash */ + if (data->hastype) + aspeed_spi_chip_set_type(aspi, cs, CONFIG_TYPE_SPI); + + if (aspeed_spi_chip_set_default_window(chip) < 0) { + dev_warn(aspi->dev, "CE%d window invalid", cs); + return -EINVAL; + } + + aspeed_spi_chip_enable(aspi, cs, true); + + chip->ctl_val[ASPEED_SPI_BASE] = CTRL_CE_STOP_ACTIVE | CTRL_IO_MODE_USER; + + dev_dbg(aspi->dev, "CE%d setup done\n", cs); + return 0; +} + +static void aspeed_spi_cleanup(struct spi_device *spi) +{ + struct aspeed_spi *aspi = spi_controller_get_devdata(spi->master); + unsigned int cs = spi->chip_select; + + aspeed_spi_chip_enable(aspi, cs, false); + + dev_dbg(aspi->dev, "CE%d cleanup done\n", cs); +} + +static void aspeed_spi_enable(struct aspeed_spi *aspi, bool enable) +{ + int cs; + + for (cs = 0; cs < aspi->data->max_cs; cs++) + aspeed_spi_chip_enable(aspi, cs, enable); +} + +static int aspeed_spi_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + const struct aspeed_spi_data *data; + struct spi_controller *ctlr; + struct aspeed_spi *aspi; + struct resource *res; + int ret; + + data = of_device_get_match_data(&pdev->dev); + if (!data) + return -ENODEV; + + ctlr = devm_spi_alloc_master(dev, sizeof(*aspi)); + if (!ctlr) + return -ENOMEM; + + aspi = spi_controller_get_devdata(ctlr); + platform_set_drvdata(pdev, aspi); + aspi->data = data; + aspi->dev = dev; + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + aspi->regs = devm_ioremap_resource(dev, res); + if (IS_ERR(aspi->regs)) { + dev_err(dev, "missing AHB register window\n"); + return PTR_ERR(aspi->regs); + } + + res = platform_get_resource(pdev, IORESOURCE_MEM, 1); + aspi->ahb_base = devm_ioremap_resource(dev, res); + if (IS_ERR(aspi->ahb_base)) { + dev_err(dev, "missing AHB mapping window\n"); + return PTR_ERR(aspi->ahb_base); + } + + aspi->ahb_window_size = resource_size(res); + aspi->ahb_base_phy = res->start; + + aspi->clk = devm_clk_get(&pdev->dev, NULL); + if (IS_ERR(aspi->clk)) { + dev_err(dev, "missing clock\n"); + return PTR_ERR(aspi->clk); + } + + aspi->clk_freq = clk_get_rate(aspi->clk); + if (!aspi->clk_freq) { + dev_err(dev, "invalid clock\n"); + return -EINVAL; + } + + ret = clk_prepare_enable(aspi->clk); + if (ret) { + dev_err(dev, "can not enable the clock\n"); + return ret; + } + + /* IRQ is for DMA, which the driver doesn't support yet */ + + ctlr->mode_bits = SPI_RX_DUAL | SPI_TX_DUAL | data->mode_bits; + ctlr->bus_num = pdev->id; + ctlr->mem_ops = &aspeed_spi_mem_ops; + ctlr->setup = aspeed_spi_setup; + ctlr->cleanup = aspeed_spi_cleanup; + ctlr->num_chipselect = data->max_cs; + ctlr->dev.of_node = dev->of_node; + + ret = devm_spi_register_controller(dev, ctlr); + if (ret) { + dev_err(&pdev->dev, "spi_register_controller failed\n"); + goto disable_clk; + } + return 0; + +disable_clk: + clk_disable_unprepare(aspi->clk); + return ret; +} + +static int aspeed_spi_remove(struct platform_device *pdev) +{ + struct aspeed_spi *aspi = platform_get_drvdata(pdev); + + aspeed_spi_enable(aspi, false); + clk_disable_unprepare(aspi->clk); + return 0; +} + +/* + * AHB mappings + */ + +/* + * The Segment Registers of the AST2400 and AST2500 use a 8MB unit. + * The address range is encoded with absolute addresses in the overall + * mapping window. + */ +static u32 aspeed_spi_segment_start(struct aspeed_spi *aspi, u32 reg) +{ + return ((reg >> 16) & 0xFF) << 23; +} + +static u32 aspeed_spi_segment_end(struct aspeed_spi *aspi, u32 reg) +{ + return ((reg >> 24) & 0xFF) << 23; +} + +static u32 aspeed_spi_segment_reg(struct aspeed_spi *aspi, u32 start, u32 end) +{ + return (((start >> 23) & 0xFF) << 16) | (((end >> 23) & 0xFF) << 24); +} + +/* + * The Segment Registers of the AST2600 use a 1MB unit. The address + * range is encoded with offsets in the overall mapping window. + */ + +#define AST2600_SEG_ADDR_MASK 0x0ff00000 + +static u32 aspeed_spi_segment_ast2600_start(struct aspeed_spi *aspi, + u32 reg) +{ + u32 start_offset = (reg << 16) & AST2600_SEG_ADDR_MASK; + + return aspi->ahb_base_phy + start_offset; +} + +static u32 aspeed_spi_segment_ast2600_end(struct aspeed_spi *aspi, + u32 reg) +{ + u32 end_offset = reg & AST2600_SEG_ADDR_MASK; + + /* segment is disabled */ + if (!end_offset) + return aspi->ahb_base_phy; + + return aspi->ahb_base_phy + end_offset + 0x100000; +} + +static u32 aspeed_spi_segment_ast2600_reg(struct aspeed_spi *aspi, + u32 start, u32 end) +{ + /* disable zero size segments */ + if (start == end) + return 0; + + return ((start & AST2600_SEG_ADDR_MASK) >> 16) | + ((end - 1) & AST2600_SEG_ADDR_MASK); +} + +/* + * Read timing compensation sequences + */ + +#define CALIBRATE_BUF_SIZE SZ_16K + +static bool aspeed_spi_check_reads(struct aspeed_spi_chip *chip, + const u8 *golden_buf, u8 *test_buf) +{ + int i; + + for (i = 0; i < 10; i++) { + memcpy_fromio(test_buf, chip->ahb_base, CALIBRATE_BUF_SIZE); + if (memcmp(test_buf, golden_buf, CALIBRATE_BUF_SIZE) != 0) { +#if defined(VERBOSE_DEBUG) + print_hex_dump_bytes(DEVICE_NAME " fail: ", DUMP_PREFIX_NONE, + test_buf, 0x100); +#endif + return false; + } + } + return true; +} + +#define FREAD_TPASS(i) (((i) / 2) | (((i) & 1) ? 0 : 8)) + +/* + * The timing register is shared by all devices. Only update for CE0. + */ +static int aspeed_spi_calibrate(struct aspeed_spi_chip *chip, u32 hdiv, + const u8 *golden_buf, u8 *test_buf) +{ + struct aspeed_spi *aspi = chip->aspi; + const struct aspeed_spi_data *data = aspi->data; + int i; + int good_pass = -1, pass_count = 0; + u32 shift = (hdiv - 1) << 2; + u32 mask = ~(0xfu << shift); + u32 fread_timing_val = 0; + + /* Try HCLK delay 0..5, each one with/without delay and look for a + * good pair. + */ + for (i = 0; i < 12; i++) { + bool pass; + + if (chip->cs == 0) { + fread_timing_val &= mask; + fread_timing_val |= FREAD_TPASS(i) << shift; + writel(fread_timing_val, aspi->regs + data->timing); + } + pass = aspeed_spi_check_reads(chip, golden_buf, test_buf); + dev_dbg(aspi->dev, + " * [%08x] %d HCLK delay, %dns DI delay : %s", + fread_timing_val, i / 2, (i & 1) ? 0 : 4, + pass ? "PASS" : "FAIL"); + if (pass) { + pass_count++; + if (pass_count == 3) { + good_pass = i - 1; + break; + } + } else { + pass_count = 0; + } + } + + /* No good setting for this frequency */ + if (good_pass < 0) + return -1; + + /* We have at least one pass of margin, let's use first pass */ + if (chip->cs == 0) { + fread_timing_val &= mask; + fread_timing_val |= FREAD_TPASS(good_pass) << shift; + writel(fread_timing_val, aspi->regs + data->timing); + } + dev_dbg(aspi->dev, " * -> good is pass %d [0x%08x]", + good_pass, fread_timing_val); + return 0; +} + +static bool aspeed_spi_check_calib_data(const u8 *test_buf, u32 size) +{ + const u32 *tb32 = (const u32 *)test_buf; + u32 i, cnt = 0; + + /* We check if we have enough words that are neither all 0 + * nor all 1's so the calibration can be considered valid. + * + * I use an arbitrary threshold for now of 64 + */ + size >>= 2; + for (i = 0; i < size; i++) { + if (tb32[i] != 0 && tb32[i] != 0xffffffff) + cnt++; + } + return cnt >= 64; +} + +static const u32 aspeed_spi_hclk_divs[] = { + 0xf, /* HCLK */ + 0x7, /* HCLK/2 */ + 0xe, /* HCLK/3 */ + 0x6, /* HCLK/4 */ + 0xd, /* HCLK/5 */ +}; + +#define ASPEED_SPI_HCLK_DIV(i) \ + (aspeed_spi_hclk_divs[(i) - 1] << CTRL_FREQ_SEL_SHIFT) + +static int aspeed_spi_do_calibration(struct aspeed_spi_chip *chip) +{ + struct aspeed_spi *aspi = chip->aspi; + const struct aspeed_spi_data *data = aspi->data; + u32 ahb_freq = aspi->clk_freq; + u32 max_freq = chip->clk_freq; + u32 ctl_val; + u8 *golden_buf = NULL; + u8 *test_buf = NULL; + int i, rc, best_div = -1; + + dev_dbg(aspi->dev, "calculate timing compensation - AHB freq: %d MHz", + ahb_freq / 1000000); + + /* + * use the related low frequency to get check calibration data + * and get golden data. + */ + ctl_val = chip->ctl_val[ASPEED_SPI_READ] & data->hclk_mask; + writel(ctl_val, chip->ctl); + + test_buf = kzalloc(CALIBRATE_BUF_SIZE * 2, GFP_KERNEL); + if (!test_buf) + return -ENOMEM; + + golden_buf = test_buf + CALIBRATE_BUF_SIZE; + + memcpy_fromio(golden_buf, chip->ahb_base, CALIBRATE_BUF_SIZE); + if (!aspeed_spi_check_calib_data(golden_buf, CALIBRATE_BUF_SIZE)) { + dev_info(aspi->dev, "Calibration area too uniform, using low speed"); + goto no_calib; + } + +#if defined(VERBOSE_DEBUG) + print_hex_dump_bytes(DEVICE_NAME " good: ", DUMP_PREFIX_NONE, + golden_buf, 0x100); +#endif + + /* Now we iterate the HCLK dividers until we find our breaking point */ + for (i = ARRAY_SIZE(aspeed_spi_hclk_divs); i > data->hdiv_max - 1; i--) { + u32 tv, freq; + + freq = ahb_freq / i; + if (freq > max_freq) + continue; + + /* Set the timing */ + tv = chip->ctl_val[ASPEED_SPI_READ] | ASPEED_SPI_HCLK_DIV(i); + writel(tv, chip->ctl); + dev_dbg(aspi->dev, "Trying HCLK/%d [%08x] ...", i, tv); + rc = data->calibrate(chip, i, golden_buf, test_buf); + if (rc == 0) + best_div = i; + } + + /* Nothing found ? */ + if (best_div < 0) { + dev_warn(aspi->dev, "No good frequency, using dumb slow"); + } else { + dev_dbg(aspi->dev, "Found good read timings at HCLK/%d", best_div); + + /* Record the freq */ + for (i = 0; i < ASPEED_SPI_MAX; i++) + chip->ctl_val[i] = (chip->ctl_val[i] & data->hclk_mask) | + ASPEED_SPI_HCLK_DIV(best_div); + } + +no_calib: + writel(chip->ctl_val[ASPEED_SPI_READ], chip->ctl); + kfree(test_buf); + return 0; +} + +#define TIMING_DELAY_DI BIT(3) +#define TIMING_DELAY_HCYCLE_MAX 5 +#define TIMING_REG_AST2600(chip) \ + ((chip)->aspi->regs + (chip)->aspi->data->timing + \ + (chip)->cs * 4) + +static int aspeed_spi_ast2600_calibrate(struct aspeed_spi_chip *chip, u32 hdiv, + const u8 *golden_buf, u8 *test_buf) +{ + struct aspeed_spi *aspi = chip->aspi; + int hcycle; + u32 shift = (hdiv - 2) << 3; + u32 mask = ~(0xfu << shift); + u32 fread_timing_val = 0; + + for (hcycle = 0; hcycle <= TIMING_DELAY_HCYCLE_MAX; hcycle++) { + int delay_ns; + bool pass = false; + + fread_timing_val &= mask; + fread_timing_val |= hcycle << shift; + + /* no DI input delay first */ + writel(fread_timing_val, TIMING_REG_AST2600(chip)); + pass = aspeed_spi_check_reads(chip, golden_buf, test_buf); + dev_dbg(aspi->dev, + " * [%08x] %d HCLK delay, DI delay none : %s", + fread_timing_val, hcycle, pass ? "PASS" : "FAIL"); + if (pass) + return 0; + + /* Add DI input delays */ + fread_timing_val &= mask; + fread_timing_val |= (TIMING_DELAY_DI | hcycle) << shift; + + for (delay_ns = 0; delay_ns < 0x10; delay_ns++) { + fread_timing_val &= ~(0xf << (4 + shift)); + fread_timing_val |= delay_ns << (4 + shift); + + writel(fread_timing_val, TIMING_REG_AST2600(chip)); + pass = aspeed_spi_check_reads(chip, golden_buf, test_buf); + dev_dbg(aspi->dev, + " * [%08x] %d HCLK delay, DI delay %d.%dns : %s", + fread_timing_val, hcycle, (delay_ns + 1) / 2, + (delay_ns + 1) & 1 ? 5 : 5, pass ? "PASS" : "FAIL"); + /* + * TODO: This is optimistic. We should look + * for a working interval and save the middle + * value in the read timing register. + */ + if (pass) + return 0; + } + } + + /* No good setting for this frequency */ + return -1; +} + +/* + * Platform definitions + */ +static const struct aspeed_spi_data ast2400_fmc_data = { + .max_cs = 5, + .hastype = true, + .we0 = 16, + .ctl0 = CE0_CTRL_REG, + .timing = CE0_TIMING_COMPENSATION_REG, + .hclk_mask = 0xfffff0ff, + .hdiv_max = 1, + .calibrate = aspeed_spi_calibrate, + .segment_start = aspeed_spi_segment_start, + .segment_end = aspeed_spi_segment_end, + .segment_reg = aspeed_spi_segment_reg, +}; + +static const struct aspeed_spi_data ast2400_spi_data = { + .max_cs = 1, + .hastype = false, + .we0 = 0, + .ctl0 = 0x04, + .timing = 0x14, + .hclk_mask = 0xfffff0ff, + .hdiv_max = 1, + .calibrate = aspeed_spi_calibrate, + /* No segment registers */ +}; + +static const struct aspeed_spi_data ast2500_fmc_data = { + .max_cs = 3, + .hastype = true, + .we0 = 16, + .ctl0 = CE0_CTRL_REG, + .timing = CE0_TIMING_COMPENSATION_REG, + .hclk_mask = 0xffffd0ff, + .hdiv_max = 1, + .calibrate = aspeed_spi_calibrate, + .segment_start = aspeed_spi_segment_start, + .segment_end = aspeed_spi_segment_end, + .segment_reg = aspeed_spi_segment_reg, +}; + +static const struct aspeed_spi_data ast2500_spi_data = { + .max_cs = 2, + .hastype = false, + .we0 = 16, + .ctl0 = CE0_CTRL_REG, + .timing = CE0_TIMING_COMPENSATION_REG, + .hclk_mask = 0xffffd0ff, + .hdiv_max = 1, + .calibrate = aspeed_spi_calibrate, + .segment_start = aspeed_spi_segment_start, + .segment_end = aspeed_spi_segment_end, + .segment_reg = aspeed_spi_segment_reg, +}; + +static const struct aspeed_spi_data ast2600_fmc_data = { + .max_cs = 3, + .hastype = false, + .mode_bits = SPI_RX_QUAD | SPI_RX_QUAD, + .we0 = 16, + .ctl0 = CE0_CTRL_REG, + .timing = CE0_TIMING_COMPENSATION_REG, + .hclk_mask = 0xf0fff0ff, + .hdiv_max = 2, + .calibrate = aspeed_spi_ast2600_calibrate, + .segment_start = aspeed_spi_segment_ast2600_start, + .segment_end = aspeed_spi_segment_ast2600_end, + .segment_reg = aspeed_spi_segment_ast2600_reg, +}; + +static const struct aspeed_spi_data ast2600_spi_data = { + .max_cs = 2, + .hastype = false, + .mode_bits = SPI_RX_QUAD | SPI_RX_QUAD, + .we0 = 16, + .ctl0 = CE0_CTRL_REG, + .timing = CE0_TIMING_COMPENSATION_REG, + .hclk_mask = 0xf0fff0ff, + .hdiv_max = 2, + .calibrate = aspeed_spi_ast2600_calibrate, + .segment_start = aspeed_spi_segment_ast2600_start, + .segment_end = aspeed_spi_segment_ast2600_end, + .segment_reg = aspeed_spi_segment_ast2600_reg, +}; + +static const struct of_device_id aspeed_spi_matches[] = { + { .compatible = "aspeed,ast2400-fmc", .data = &ast2400_fmc_data }, + { .compatible = "aspeed,ast2400-spi", .data = &ast2400_spi_data }, + { .compatible = "aspeed,ast2500-fmc", .data = &ast2500_fmc_data }, + { .compatible = "aspeed,ast2500-spi", .data = &ast2500_spi_data }, + { .compatible = "aspeed,ast2600-fmc", .data = &ast2600_fmc_data }, + { .compatible = "aspeed,ast2600-spi", .data = &ast2600_spi_data }, + { } +}; +MODULE_DEVICE_TABLE(of, aspeed_spi_matches); + +static struct platform_driver aspeed_spi_driver = { + .probe = aspeed_spi_probe, + .remove = aspeed_spi_remove, + .driver = { + .name = DEVICE_NAME, + .of_match_table = aspeed_spi_matches, + } +}; + +module_platform_driver(aspeed_spi_driver); + +MODULE_DESCRIPTION("ASPEED Static Memory Controller Driver"); +MODULE_AUTHOR("Chin-Ting Kuo <chin-ting_kuo@aspeedtech.com>"); +MODULE_AUTHOR("Cedric Le Goater <clg@kaod.org>"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/spi/spi-au1550.c b/drivers/spi/spi-au1550.c index 4b59a1b1bf7e..e008761298da 100644 --- a/drivers/spi/spi-au1550.c +++ b/drivers/spi/spi-au1550.c @@ -405,7 +405,7 @@ static int au1550_spi_dma_txrxb(struct spi_device *spi, struct spi_transfer *t) dma_unmap_single(hw->dev, dma_tx_addr, t->len, DMA_TO_DEVICE); - return hw->rx_count < hw->tx_count ? hw->rx_count : hw->tx_count; + return min(hw->rx_count, hw->tx_count); } static irqreturn_t au1550_spi_dma_irq_callback(struct au1550_spi *hw) @@ -539,7 +539,7 @@ static int au1550_spi_pio_txrxb(struct spi_device *spi, struct spi_transfer *t) wait_for_completion(&hw->master_done); - return hw->rx_count < hw->tx_count ? hw->rx_count : hw->tx_count; + return min(hw->rx_count, hw->tx_count); } static irqreturn_t au1550_spi_pio_irq_callback(struct au1550_spi *hw) diff --git a/drivers/spi/spi-bcm-qspi.c b/drivers/spi/spi-bcm-qspi.c index 86c76211b3d3..cad2d55dcd3d 100644 --- a/drivers/spi/spi-bcm-qspi.c +++ b/drivers/spi/spi-bcm-qspi.c @@ -1205,7 +1205,7 @@ static int bcm_qspi_exec_mem_op(struct spi_mem *mem, addr = op->addr.val; len = op->data.nbytes; - if (bcm_qspi_bspi_ver_three(qspi) == true) { + if (has_bspi(qspi) && bcm_qspi_bspi_ver_three(qspi) == true) { /* * The address coming into this function is a raw flash offset. * But for BSPI <= V3, we need to convert it to a remapped BSPI @@ -1224,7 +1224,7 @@ static int bcm_qspi_exec_mem_op(struct spi_mem *mem, len < 4) mspi_read = true; - if (mspi_read) + if (!has_bspi(qspi) || mspi_read) return bcm_qspi_mspi_exec_mem_op(spi, op); ret = bcm_qspi_bspi_set_mode(qspi, op, 0); diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c index b0c9f62ccefb..2b9fc8449a62 100644 --- a/drivers/spi/spi-cadence-quadspi.c +++ b/drivers/spi/spi-cadence-quadspi.c @@ -19,6 +19,7 @@ #include <linux/iopoll.h> #include <linux/jiffies.h> #include <linux/kernel.h> +#include <linux/log2.h> #include <linux/module.h> #include <linux/of_device.h> #include <linux/of.h> @@ -42,6 +43,8 @@ /* Capabilities */ #define CQSPI_SUPPORTS_OCTAL BIT(0) +#define CQSPI_OP_WIDTH(part) ((part).nbytes ? ilog2((part).buswidth) : 0) + struct cqspi_st; struct cqspi_flash_pdata { @@ -52,16 +55,12 @@ struct cqspi_flash_pdata { u32 tsd2d_ns; u32 tchsh_ns; u32 tslch_ns; - u8 inst_width; - u8 addr_width; - u8 data_width; - bool dtr; u8 cs; }; struct cqspi_st { struct platform_device *pdev; - + struct spi_master *master; struct clk *clk; unsigned int sclk; @@ -102,12 +101,6 @@ struct cqspi_driver_platdata { #define CQSPI_TIMEOUT_MS 500 #define CQSPI_READ_TIMEOUT_MS 10 -/* Instruction type */ -#define CQSPI_INST_TYPE_SINGLE 0 -#define CQSPI_INST_TYPE_DUAL 1 -#define CQSPI_INST_TYPE_QUAD 2 -#define CQSPI_INST_TYPE_OCTAL 3 - #define CQSPI_DUMMY_CLKS_PER_BYTE 8 #define CQSPI_DUMMY_BYTES_MAX 4 #define CQSPI_DUMMY_CLKS_MAX 31 @@ -348,18 +341,18 @@ static irqreturn_t cqspi_irq_handler(int this_irq, void *dev) return IRQ_HANDLED; } -static unsigned int cqspi_calc_rdreg(struct cqspi_flash_pdata *f_pdata) +static unsigned int cqspi_calc_rdreg(const struct spi_mem_op *op) { u32 rdreg = 0; - rdreg |= f_pdata->inst_width << CQSPI_REG_RD_INSTR_TYPE_INSTR_LSB; - rdreg |= f_pdata->addr_width << CQSPI_REG_RD_INSTR_TYPE_ADDR_LSB; - rdreg |= f_pdata->data_width << CQSPI_REG_RD_INSTR_TYPE_DATA_LSB; + rdreg |= CQSPI_OP_WIDTH(op->cmd) << CQSPI_REG_RD_INSTR_TYPE_INSTR_LSB; + rdreg |= CQSPI_OP_WIDTH(op->addr) << CQSPI_REG_RD_INSTR_TYPE_ADDR_LSB; + rdreg |= CQSPI_OP_WIDTH(op->data) << CQSPI_REG_RD_INSTR_TYPE_DATA_LSB; return rdreg; } -static unsigned int cqspi_calc_dummy(const struct spi_mem_op *op, bool dtr) +static unsigned int cqspi_calc_dummy(const struct spi_mem_op *op) { unsigned int dummy_clk; @@ -367,83 +360,12 @@ static unsigned int cqspi_calc_dummy(const struct spi_mem_op *op, bool dtr) return 0; dummy_clk = op->dummy.nbytes * (8 / op->dummy.buswidth); - if (dtr) + if (op->cmd.dtr) dummy_clk /= 2; return dummy_clk; } -static int cqspi_set_protocol(struct cqspi_flash_pdata *f_pdata, - const struct spi_mem_op *op) -{ - f_pdata->inst_width = CQSPI_INST_TYPE_SINGLE; - f_pdata->addr_width = CQSPI_INST_TYPE_SINGLE; - f_pdata->data_width = CQSPI_INST_TYPE_SINGLE; - - /* - * For an op to be DTR, cmd phase along with every other non-empty - * phase should have dtr field set to 1. If an op phase has zero - * nbytes, ignore its dtr field; otherwise, check its dtr field. - */ - f_pdata->dtr = op->cmd.dtr && - (!op->addr.nbytes || op->addr.dtr) && - (!op->data.nbytes || op->data.dtr); - - switch (op->data.buswidth) { - case 0: - break; - case 1: - f_pdata->data_width = CQSPI_INST_TYPE_SINGLE; - break; - case 2: - f_pdata->data_width = CQSPI_INST_TYPE_DUAL; - break; - case 4: - f_pdata->data_width = CQSPI_INST_TYPE_QUAD; - break; - case 8: - f_pdata->data_width = CQSPI_INST_TYPE_OCTAL; - break; - default: - return -EINVAL; - } - - /* Right now we only support 8-8-8 DTR mode. */ - if (f_pdata->dtr) { - switch (op->cmd.buswidth) { - case 0: - break; - case 8: - f_pdata->inst_width = CQSPI_INST_TYPE_OCTAL; - break; - default: - return -EINVAL; - } - - switch (op->addr.buswidth) { - case 0: - break; - case 8: - f_pdata->addr_width = CQSPI_INST_TYPE_OCTAL; - break; - default: - return -EINVAL; - } - - switch (op->data.buswidth) { - case 0: - break; - case 8: - f_pdata->data_width = CQSPI_INST_TYPE_OCTAL; - break; - default: - return -EINVAL; - } - } - - return 0; -} - static int cqspi_wait_idle(struct cqspi_st *cqspi) { const unsigned int poll_idle_retry = 3; @@ -525,8 +447,7 @@ static int cqspi_setup_opcode_ext(struct cqspi_flash_pdata *f_pdata, } static int cqspi_enable_dtr(struct cqspi_flash_pdata *f_pdata, - const struct spi_mem_op *op, unsigned int shift, - bool enable) + const struct spi_mem_op *op, unsigned int shift) { struct cqspi_st *cqspi = f_pdata->cqspi; void __iomem *reg_base = cqspi->iobase; @@ -539,7 +460,7 @@ static int cqspi_enable_dtr(struct cqspi_flash_pdata *f_pdata, * We enable dual byte opcode here. The callers have to set up the * extension opcode based on which type of operation it is. */ - if (enable) { + if (op->cmd.dtr) { reg |= CQSPI_REG_CONFIG_DTR_PROTO; reg |= CQSPI_REG_CONFIG_DUAL_OPCODE; @@ -571,12 +492,7 @@ static int cqspi_command_read(struct cqspi_flash_pdata *f_pdata, size_t read_len; int status; - status = cqspi_set_protocol(f_pdata, op); - if (status) - return status; - - status = cqspi_enable_dtr(f_pdata, op, CQSPI_REG_OP_EXT_STIG_LSB, - f_pdata->dtr); + status = cqspi_enable_dtr(f_pdata, op, CQSPI_REG_OP_EXT_STIG_LSB); if (status) return status; @@ -587,17 +503,17 @@ static int cqspi_command_read(struct cqspi_flash_pdata *f_pdata, return -EINVAL; } - if (f_pdata->dtr) + if (op->cmd.dtr) opcode = op->cmd.opcode >> 8; else opcode = op->cmd.opcode; reg = opcode << CQSPI_REG_CMDCTRL_OPCODE_LSB; - rdreg = cqspi_calc_rdreg(f_pdata); + rdreg = cqspi_calc_rdreg(op); writel(rdreg, reg_base + CQSPI_REG_RD_INSTR); - dummy_clk = cqspi_calc_dummy(op, f_pdata->dtr); + dummy_clk = cqspi_calc_dummy(op); if (dummy_clk > CQSPI_DUMMY_CLKS_MAX) return -EOPNOTSUPP; @@ -644,12 +560,7 @@ static int cqspi_command_write(struct cqspi_flash_pdata *f_pdata, size_t write_len; int ret; - ret = cqspi_set_protocol(f_pdata, op); - if (ret) - return ret; - - ret = cqspi_enable_dtr(f_pdata, op, CQSPI_REG_OP_EXT_STIG_LSB, - f_pdata->dtr); + ret = cqspi_enable_dtr(f_pdata, op, CQSPI_REG_OP_EXT_STIG_LSB); if (ret) return ret; @@ -660,10 +571,10 @@ static int cqspi_command_write(struct cqspi_flash_pdata *f_pdata, return -EINVAL; } - reg = cqspi_calc_rdreg(f_pdata); + reg = cqspi_calc_rdreg(op); writel(reg, reg_base + CQSPI_REG_RD_INSTR); - if (f_pdata->dtr) + if (op->cmd.dtr) opcode = op->cmd.opcode >> 8; else opcode = op->cmd.opcode; @@ -710,21 +621,20 @@ static int cqspi_read_setup(struct cqspi_flash_pdata *f_pdata, int ret; u8 opcode; - ret = cqspi_enable_dtr(f_pdata, op, CQSPI_REG_OP_EXT_READ_LSB, - f_pdata->dtr); + ret = cqspi_enable_dtr(f_pdata, op, CQSPI_REG_OP_EXT_READ_LSB); if (ret) return ret; - if (f_pdata->dtr) + if (op->cmd.dtr) opcode = op->cmd.opcode >> 8; else opcode = op->cmd.opcode; reg = opcode << CQSPI_REG_RD_INSTR_OPCODE_LSB; - reg |= cqspi_calc_rdreg(f_pdata); + reg |= cqspi_calc_rdreg(op); /* Setup dummy clock cycles */ - dummy_clk = cqspi_calc_dummy(op, f_pdata->dtr); + dummy_clk = cqspi_calc_dummy(op); if (dummy_clk > CQSPI_DUMMY_CLKS_MAX) return -EOPNOTSUPP; @@ -969,22 +879,21 @@ static int cqspi_write_setup(struct cqspi_flash_pdata *f_pdata, void __iomem *reg_base = cqspi->iobase; u8 opcode; - ret = cqspi_enable_dtr(f_pdata, op, CQSPI_REG_OP_EXT_WRITE_LSB, - f_pdata->dtr); + ret = cqspi_enable_dtr(f_pdata, op, CQSPI_REG_OP_EXT_WRITE_LSB); if (ret) return ret; - if (f_pdata->dtr) + if (op->cmd.dtr) opcode = op->cmd.opcode >> 8; else opcode = op->cmd.opcode; /* Set opcode. */ reg = opcode << CQSPI_REG_WR_INSTR_OPCODE_LSB; - reg |= f_pdata->data_width << CQSPI_REG_WR_INSTR_TYPE_DATA_LSB; - reg |= f_pdata->addr_width << CQSPI_REG_WR_INSTR_TYPE_ADDR_LSB; + reg |= CQSPI_OP_WIDTH(op->data) << CQSPI_REG_WR_INSTR_TYPE_DATA_LSB; + reg |= CQSPI_OP_WIDTH(op->addr) << CQSPI_REG_WR_INSTR_TYPE_ADDR_LSB; writel(reg, reg_base + CQSPI_REG_WR_INSTR); - reg = cqspi_calc_rdreg(f_pdata); + reg = cqspi_calc_rdreg(op); writel(reg, reg_base + CQSPI_REG_RD_INSTR); /* @@ -1266,10 +1175,6 @@ static ssize_t cqspi_write(struct cqspi_flash_pdata *f_pdata, const u_char *buf = op->data.buf.out; int ret; - ret = cqspi_set_protocol(f_pdata, op); - if (ret) - return ret; - ret = cqspi_write_setup(f_pdata, op); if (ret) return ret; @@ -1282,7 +1187,7 @@ static ssize_t cqspi_write(struct cqspi_flash_pdata *f_pdata, * mode. So, we can not use direct mode when in DTR mode for writing * data. */ - if (!f_pdata->dtr && cqspi->use_direct_mode && + if (!op->cmd.dtr && cqspi->use_direct_mode && ((to + len) <= cqspi->ahb_size)) { memcpy_toio(cqspi->ahb_base + to, buf, len); return cqspi_wait_idle(cqspi); @@ -1370,9 +1275,6 @@ static ssize_t cqspi_read(struct cqspi_flash_pdata *f_pdata, int ret; ddata = of_device_get_match_data(dev); - ret = cqspi_set_protocol(f_pdata, op); - if (ret) - return ret; ret = cqspi_read_setup(f_pdata, op); if (ret) @@ -1437,9 +1339,18 @@ static bool cqspi_supports_mem_op(struct spi_mem *mem, all_false = !op->cmd.dtr && !op->addr.dtr && !op->dummy.dtr && !op->data.dtr; - /* Mixed DTR modes not supported. */ - if (!(all_true || all_false)) + if (all_true) { + /* Right now we only support 8-8-8 DTR mode. */ + if (op->cmd.nbytes && op->cmd.buswidth != 8) + return false; + if (op->addr.nbytes && op->addr.buswidth != 8) + return false; + if (op->data.nbytes && op->data.buswidth != 8) + return false; + } else if (!all_false) { + /* Mixed DTR modes are not supported. */ return false; + } return spi_mem_default_supports_op(mem, op); } @@ -1570,6 +1481,7 @@ static int cqspi_request_mmap_dma(struct cqspi_st *cqspi) cqspi->rx_chan = dma_request_chan_by_mask(&mask); if (IS_ERR(cqspi->rx_chan)) { int ret = PTR_ERR(cqspi->rx_chan); + cqspi->rx_chan = NULL; return dev_err_probe(&cqspi->pdev->dev, ret, "No Rx DMA available\n"); } @@ -1646,7 +1558,7 @@ static int cqspi_probe(struct platform_device *pdev) int ret; int irq; - master = spi_alloc_master(&pdev->dev, sizeof(*cqspi)); + master = devm_spi_alloc_master(&pdev->dev, sizeof(*cqspi)); if (!master) { dev_err(&pdev->dev, "spi_alloc_master failed\n"); return -ENOMEM; @@ -1659,6 +1571,7 @@ static int cqspi_probe(struct platform_device *pdev) cqspi = spi_master_get_devdata(master); cqspi->pdev = pdev; + cqspi->master = master; platform_set_drvdata(pdev, cqspi); /* Obtain configuration from OF. */ @@ -1707,11 +1620,9 @@ static int cqspi_probe(struct platform_device *pdev) } pm_runtime_enable(dev); - ret = pm_runtime_get_sync(dev); - if (ret < 0) { - pm_runtime_put_noidle(dev); + ret = pm_runtime_resume_and_get(dev); + if (ret < 0) goto probe_master_put; - } ret = clk_prepare_enable(cqspi->clk); if (ret) { @@ -1791,7 +1702,7 @@ static int cqspi_probe(struct platform_device *pdev) goto probe_setup_failed; } - ret = devm_spi_register_master(dev, master); + ret = spi_register_master(master); if (ret) { dev_err(&pdev->dev, "failed to register SPI ctlr %d\n", ret); goto probe_setup_failed; @@ -1814,6 +1725,7 @@ static int cqspi_remove(struct platform_device *pdev) { struct cqspi_st *cqspi = platform_get_drvdata(pdev); + spi_unregister_master(cqspi->master); cqspi_controller_enable(cqspi, 0); if (cqspi->rx_chan) @@ -1872,7 +1784,7 @@ static const struct cqspi_driver_platdata intel_lgm_qspi = { }; static const struct cqspi_driver_platdata socfpga_qspi = { - .quirks = CQSPI_NO_SUPPORT_WR_COMPLETION, + .quirks = CQSPI_DISABLE_DAC_MODE | CQSPI_NO_SUPPORT_WR_COMPLETION, }; static const struct cqspi_driver_platdata versal_ospi = { @@ -1901,11 +1813,11 @@ static const struct of_device_id cqspi_dt_ids[] = { }, { .compatible = "xlnx,versal-ospi-1.0", - .data = (void *)&versal_ospi, + .data = &versal_ospi, }, { .compatible = "intel,socfpga-qspi", - .data = (void *)&socfpga_qspi, + .data = &socfpga_qspi, }, { /* end of table */ } }; diff --git a/drivers/spi/spi-cadence.c b/drivers/spi/spi-cadence.c index ceb16e70d235..a23d4f6329f5 100644 --- a/drivers/spi/spi-cadence.c +++ b/drivers/spi/spi-cadence.c @@ -342,7 +342,8 @@ static irqreturn_t cdns_spi_irq(int irq, void *dev_id) { struct spi_master *master = dev_id; struct cdns_spi *xspi = spi_master_get_devdata(master); - u32 intr_status, status; + irqreturn_t status; + u32 intr_status; status = IRQ_NONE; intr_status = cdns_spi_read(xspi, CDNS_SPI_ISR); @@ -657,7 +658,7 @@ static int __maybe_unused cdns_spi_resume(struct device *dev) * * Return: 0 on success and error value on error */ -static int __maybe_unused cnds_runtime_resume(struct device *dev) +static int __maybe_unused cdns_spi_runtime_resume(struct device *dev) { struct spi_master *master = dev_get_drvdata(dev); struct cdns_spi *xspi = spi_master_get_devdata(master); @@ -686,7 +687,7 @@ static int __maybe_unused cnds_runtime_resume(struct device *dev) * * Return: Always 0 */ -static int __maybe_unused cnds_runtime_suspend(struct device *dev) +static int __maybe_unused cdns_spi_runtime_suspend(struct device *dev) { struct spi_master *master = dev_get_drvdata(dev); struct cdns_spi *xspi = spi_master_get_devdata(master); @@ -698,8 +699,8 @@ static int __maybe_unused cnds_runtime_suspend(struct device *dev) } static const struct dev_pm_ops cdns_spi_dev_pm_ops = { - SET_RUNTIME_PM_OPS(cnds_runtime_suspend, - cnds_runtime_resume, NULL) + SET_RUNTIME_PM_OPS(cdns_spi_runtime_suspend, + cdns_spi_runtime_resume, NULL) SET_SYSTEM_SLEEP_PM_OPS(cdns_spi_suspend, cdns_spi_resume) }; diff --git a/drivers/spi/spi-clps711x.c b/drivers/spi/spi-clps711x.c index 0bef5ce08094..c005ed26a3e1 100644 --- a/drivers/spi/spi-clps711x.c +++ b/drivers/spi/spi-clps711x.c @@ -9,6 +9,7 @@ #include <linux/clk.h> #include <linux/gpio/consumer.h> #include <linux/module.h> +#include <linux/of.h> #include <linux/interrupt.h> #include <linux/platform_device.h> #include <linux/regmap.h> @@ -89,6 +90,7 @@ static irqreturn_t spi_clps711x_isr(int irq, void *dev_id) static int spi_clps711x_probe(struct platform_device *pdev) { + struct device_node *np = pdev->dev.of_node; struct spi_clps711x_data *hw; struct spi_master *master; int irq, ret; @@ -117,8 +119,7 @@ static int spi_clps711x_probe(struct platform_device *pdev) goto err_out; } - hw->syscon = - syscon_regmap_lookup_by_compatible("cirrus,ep7209-syscon3"); + hw->syscon = syscon_regmap_lookup_by_phandle(np, "syscon"); if (IS_ERR(hw->syscon)) { ret = PTR_ERR(hw->syscon); goto err_out; diff --git a/drivers/spi/spi-fsl-qspi.c b/drivers/spi/spi-fsl-qspi.c index 9851551ebbe0..46ae46a944c5 100644 --- a/drivers/spi/spi-fsl-qspi.c +++ b/drivers/spi/spi-fsl-qspi.c @@ -876,6 +876,10 @@ static int fsl_qspi_probe(struct platform_device *pdev) res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "QuadSPI-memory"); + if (!res) { + ret = -EINVAL; + goto err_put_ctrl; + } q->memmap_phy = res->start; /* Since there are 4 cs, map size required is 4 times ahb_buf_size */ q->ahb_addr = devm_ioremap(dev, q->memmap_phy, diff --git a/drivers/spi/spi-img-spfi.c b/drivers/spi/spi-img-spfi.c index 5f05d519fbbd..71376b6df89d 100644 --- a/drivers/spi/spi-img-spfi.c +++ b/drivers/spi/spi-img-spfi.c @@ -731,7 +731,7 @@ static int img_spfi_resume(struct device *dev) int ret; ret = pm_runtime_get_sync(dev); - if (ret) { + if (ret < 0) { pm_runtime_put_noidle(dev); return ret; } diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c index b2dd0a4d2446..bc97337fddf5 100644 --- a/drivers/spi/spi-imx.c +++ b/drivers/spi/spi-imx.c @@ -18,7 +18,6 @@ #include <linux/pm_runtime.h> #include <linux/slab.h> #include <linux/spi/spi.h> -#include <linux/spi/spi_bitbang.h> #include <linux/types.h> #include <linux/of.h> #include <linux/of_device.h> @@ -32,6 +31,12 @@ static bool use_dma = true; module_param(use_dma, bool, 0644); MODULE_PARM_DESC(use_dma, "Enable usage of DMA when available (default)"); +/* define polling limits */ +static unsigned int polling_limit_us = 30; +module_param(polling_limit_us, uint, 0664); +MODULE_PARM_DESC(polling_limit_us, + "time in us to run a transfer in polling mode\n"); + #define MXC_RPM_TIMEOUT 2000 /* 2000ms */ #define MXC_CSPIRXDATA 0x00 @@ -64,15 +69,15 @@ enum spi_imx_devtype { struct spi_imx_data; struct spi_imx_devtype_data { - void (*intctrl)(struct spi_imx_data *, int); - int (*prepare_message)(struct spi_imx_data *, struct spi_message *); - int (*prepare_transfer)(struct spi_imx_data *, struct spi_device *); - void (*trigger)(struct spi_imx_data *); - int (*rx_available)(struct spi_imx_data *); - void (*reset)(struct spi_imx_data *); - void (*setup_wml)(struct spi_imx_data *); - void (*disable)(struct spi_imx_data *); - void (*disable_dma)(struct spi_imx_data *); + void (*intctrl)(struct spi_imx_data *spi_imx, int enable); + int (*prepare_message)(struct spi_imx_data *spi_imx, struct spi_message *msg); + int (*prepare_transfer)(struct spi_imx_data *spi_imx, struct spi_device *spi); + void (*trigger)(struct spi_imx_data *spi_imx); + int (*rx_available)(struct spi_imx_data *spi_imx); + void (*reset)(struct spi_imx_data *spi_imx); + void (*setup_wml)(struct spi_imx_data *spi_imx); + void (*disable)(struct spi_imx_data *spi_imx); + void (*disable_dma)(struct spi_imx_data *spi_imx); bool has_dmamode; bool has_slavemode; unsigned int fifo_size; @@ -86,7 +91,7 @@ struct spi_imx_devtype_data { }; struct spi_imx_data { - struct spi_bitbang bitbang; + struct spi_controller *controller; struct device *dev; struct completion xfer_done; @@ -102,12 +107,13 @@ struct spi_imx_data { unsigned int spi_drctl; unsigned int count, remainder; - void (*tx)(struct spi_imx_data *); - void (*rx)(struct spi_imx_data *); + void (*tx)(struct spi_imx_data *spi_imx); + void (*rx)(struct spi_imx_data *spi_imx); void *rx_buf; const void *tx_buf; unsigned int txfifo; /* number of words pushed in tx FIFO */ unsigned int dynamic_burst; + bool rx_only; /* Slave mode */ bool slave_mode; @@ -225,15 +231,15 @@ static int spi_imx_bytes_per_word(const int bits_per_word) return 4; } -static bool spi_imx_can_dma(struct spi_master *master, struct spi_device *spi, +static bool spi_imx_can_dma(struct spi_controller *controller, struct spi_device *spi, struct spi_transfer *transfer) { - struct spi_imx_data *spi_imx = spi_master_get_devdata(master); + struct spi_imx_data *spi_imx = spi_controller_get_devdata(controller); - if (!use_dma || master->fallback) + if (!use_dma || controller->fallback) return false; - if (!master->dma_rx) + if (!controller->dma_rx) return false; if (spi_imx->slave_mode) @@ -289,17 +295,16 @@ static bool spi_imx_can_dma(struct spi_master *master, struct spi_device *spi, static void spi_imx_buf_rx_swap_u32(struct spi_imx_data *spi_imx) { unsigned int val = readl(spi_imx->base + MXC_CSPIRXDATA); -#ifdef __LITTLE_ENDIAN - unsigned int bytes_per_word; -#endif if (spi_imx->rx_buf) { #ifdef __LITTLE_ENDIAN + unsigned int bytes_per_word; + bytes_per_word = spi_imx_bytes_per_word(spi_imx->bits_per_word); if (bytes_per_word == 1) - val = cpu_to_be32(val); + swab32s(&val); else if (bytes_per_word == 2) - val = (val << 16) | (val >> 16); + swahw32s(&val); #endif *(u32 *)spi_imx->rx_buf = val; spi_imx->rx_buf += sizeof(u32); @@ -353,9 +358,9 @@ static void spi_imx_buf_tx_swap_u32(struct spi_imx_data *spi_imx) bytes_per_word = spi_imx_bytes_per_word(spi_imx->bits_per_word); if (bytes_per_word == 1) - val = cpu_to_be32(val); + swab32s(&val); else if (bytes_per_word == 2) - val = (val << 16) | (val >> 16); + swahw32s(&val); #endif writel(val, spi_imx->base + MXC_CSPITXDATA); } @@ -469,7 +474,7 @@ static unsigned int mx51_ecspi_clkdiv(struct spi_imx_data *spi_imx, static void mx51_ecspi_intctrl(struct spi_imx_data *spi_imx, int enable) { - unsigned val = 0; + unsigned int val = 0; if (enable & MXC_INT_TE) val |= MX51_ECSPI_INT_TEEN; @@ -515,6 +520,7 @@ static int mx51_ecspi_prepare_message(struct spi_imx_data *spi_imx, u32 min_speed_hz = ~0U; u32 testreg, delay; u32 cfg = readl(spi_imx->base + MX51_ECSPI_CONFIG); + u32 current_cfg = cfg; /* set Master or Slave mode */ if (spi_imx->slave_mode) @@ -554,11 +560,6 @@ static int mx51_ecspi_prepare_message(struct spi_imx_data *spi_imx, else cfg |= MX51_ECSPI_CONFIG_SBBCTRL(spi->chip_select); - if (spi->mode & SPI_CPHA) - cfg |= MX51_ECSPI_CONFIG_SCLKPHA(spi->chip_select); - else - cfg &= ~MX51_ECSPI_CONFIG_SCLKPHA(spi->chip_select); - if (spi->mode & SPI_CPOL) { cfg |= MX51_ECSPI_CONFIG_SCLKPOL(spi->chip_select); cfg |= MX51_ECSPI_CONFIG_SCLKCTL(spi->chip_select); @@ -572,6 +573,9 @@ static int mx51_ecspi_prepare_message(struct spi_imx_data *spi_imx, else cfg &= ~MX51_ECSPI_CONFIG_SSBPOL(spi->chip_select); + if (cfg == current_cfg) + return 0; + writel(cfg, spi_imx->base + MX51_ECSPI_CONFIG); /* @@ -585,7 +589,7 @@ static int mx51_ecspi_prepare_message(struct spi_imx_data *spi_imx, * the SPI communication as the device on the other end would consider * the change of SCLK polarity as a clock tick already. * - * Because spi_imx->spi_bus_clk is only set in bitbang prepare_message + * Because spi_imx->spi_bus_clk is only set in prepare_message * callback, iterate over all the transfers in spi_message, find the * one with lowest bus frequency, and use that bus frequency for the * delay calculation. In case all transfers have speed_hz == 0, then @@ -606,6 +610,24 @@ static int mx51_ecspi_prepare_message(struct spi_imx_data *spi_imx, return 0; } +static void mx51_configure_cpha(struct spi_imx_data *spi_imx, + struct spi_device *spi) +{ + bool cpha = (spi->mode & SPI_CPHA); + bool flip_cpha = (spi->mode & SPI_RX_CPHA_FLIP) && spi_imx->rx_only; + u32 cfg = readl(spi_imx->base + MX51_ECSPI_CONFIG); + + /* Flip cpha logical value iff flip_cpha */ + cpha ^= flip_cpha; + + if (cpha) + cfg |= MX51_ECSPI_CONFIG_SCLKPHA(spi->chip_select); + else + cfg &= ~MX51_ECSPI_CONFIG_SCLKPHA(spi->chip_select); + + writel(cfg, spi_imx->base + MX51_ECSPI_CONFIG); +} + static int mx51_ecspi_prepare_transfer(struct spi_imx_data *spi_imx, struct spi_device *spi) { @@ -627,6 +649,8 @@ static int mx51_ecspi_prepare_transfer(struct spi_imx_data *spi_imx, ctrl |= mx51_ecspi_clkdiv(spi_imx, spi_imx->spi_bus_clk, &clk); spi_imx->spi_bus_clk = clk; + mx51_configure_cpha(spi_imx, spi); + /* * ERR009165: work in XHC mode instead of SMC as PIO on the chips * before i.mx6ul. @@ -1153,12 +1177,12 @@ static irqreturn_t spi_imx_isr(int irq, void *dev_id) return IRQ_HANDLED; } -static int spi_imx_dma_configure(struct spi_master *master) +static int spi_imx_dma_configure(struct spi_controller *controller) { int ret; enum dma_slave_buswidth buswidth; struct dma_slave_config rx = {}, tx = {}; - struct spi_imx_data *spi_imx = spi_master_get_devdata(master); + struct spi_imx_data *spi_imx = spi_controller_get_devdata(controller); switch (spi_imx_bytes_per_word(spi_imx->bits_per_word)) { case 4: @@ -1178,7 +1202,7 @@ static int spi_imx_dma_configure(struct spi_master *master) tx.dst_addr = spi_imx->base_phys + MXC_CSPITXDATA; tx.dst_addr_width = buswidth; tx.dst_maxburst = spi_imx->wml; - ret = dmaengine_slave_config(master->dma_tx, &tx); + ret = dmaengine_slave_config(controller->dma_tx, &tx); if (ret) { dev_err(spi_imx->dev, "TX dma configuration failed with %d\n", ret); return ret; @@ -1188,7 +1212,7 @@ static int spi_imx_dma_configure(struct spi_master *master) rx.src_addr = spi_imx->base_phys + MXC_CSPIRXDATA; rx.src_addr_width = buswidth; rx.src_maxburst = spi_imx->wml; - ret = dmaengine_slave_config(master->dma_rx, &rx); + ret = dmaengine_slave_config(controller->dma_rx, &rx); if (ret) { dev_err(spi_imx->dev, "RX dma configuration failed with %d\n", ret); return ret; @@ -1200,7 +1224,7 @@ static int spi_imx_dma_configure(struct spi_master *master) static int spi_imx_setupxfer(struct spi_device *spi, struct spi_transfer *t) { - struct spi_imx_data *spi_imx = spi_master_get_devdata(spi->master); + struct spi_imx_data *spi_imx = spi_controller_get_devdata(spi->controller); if (!t) return 0; @@ -1246,11 +1270,14 @@ static int spi_imx_setupxfer(struct spi_device *spi, spi_imx->dynamic_burst = 0; } - if (spi_imx_can_dma(spi_imx->bitbang.master, spi, t)) + if (spi_imx_can_dma(spi_imx->controller, spi, t)) spi_imx->usedma = true; else spi_imx->usedma = false; + spi_imx->rx_only = ((t->tx_buf == NULL) + || (t->tx_buf == spi->controller->dummy_tx)); + if (is_imx53_ecspi(spi_imx) && spi_imx->slave_mode) { spi_imx->rx = mx53_ecspi_rx_slave; spi_imx->tx = mx53_ecspi_tx_slave; @@ -1264,50 +1291,50 @@ static int spi_imx_setupxfer(struct spi_device *spi, static void spi_imx_sdma_exit(struct spi_imx_data *spi_imx) { - struct spi_master *master = spi_imx->bitbang.master; + struct spi_controller *controller = spi_imx->controller; - if (master->dma_rx) { - dma_release_channel(master->dma_rx); - master->dma_rx = NULL; + if (controller->dma_rx) { + dma_release_channel(controller->dma_rx); + controller->dma_rx = NULL; } - if (master->dma_tx) { - dma_release_channel(master->dma_tx); - master->dma_tx = NULL; + if (controller->dma_tx) { + dma_release_channel(controller->dma_tx); + controller->dma_tx = NULL; } } static int spi_imx_sdma_init(struct device *dev, struct spi_imx_data *spi_imx, - struct spi_master *master) + struct spi_controller *controller) { int ret; spi_imx->wml = spi_imx->devtype_data->fifo_size / 2; /* Prepare for TX DMA: */ - master->dma_tx = dma_request_chan(dev, "tx"); - if (IS_ERR(master->dma_tx)) { - ret = PTR_ERR(master->dma_tx); + controller->dma_tx = dma_request_chan(dev, "tx"); + if (IS_ERR(controller->dma_tx)) { + ret = PTR_ERR(controller->dma_tx); dev_dbg(dev, "can't get the TX DMA channel, error %d!\n", ret); - master->dma_tx = NULL; + controller->dma_tx = NULL; goto err; } /* Prepare for RX : */ - master->dma_rx = dma_request_chan(dev, "rx"); - if (IS_ERR(master->dma_rx)) { - ret = PTR_ERR(master->dma_rx); + controller->dma_rx = dma_request_chan(dev, "rx"); + if (IS_ERR(controller->dma_rx)) { + ret = PTR_ERR(controller->dma_rx); dev_dbg(dev, "can't get the RX DMA channel, error %d\n", ret); - master->dma_rx = NULL; + controller->dma_rx = NULL; goto err; } init_completion(&spi_imx->dma_rx_completion); init_completion(&spi_imx->dma_tx_completion); - master->can_dma = spi_imx_can_dma; - master->max_dma_len = MAX_SDMA_BD_BYTES; - spi_imx->bitbang.master->flags = SPI_MASTER_MUST_RX | - SPI_MASTER_MUST_TX; + controller->can_dma = spi_imx_can_dma; + controller->max_dma_len = MAX_SDMA_BD_BYTES; + spi_imx->controller->flags = SPI_CONTROLLER_MUST_RX | + SPI_CONTROLLER_MUST_TX; return 0; err: @@ -1349,7 +1376,7 @@ static int spi_imx_dma_transfer(struct spi_imx_data *spi_imx, struct dma_async_tx_descriptor *desc_tx, *desc_rx; unsigned long transfer_timeout; unsigned long timeout; - struct spi_master *master = spi_imx->bitbang.master; + struct spi_controller *controller = spi_imx->controller; struct sg_table *tx = &transfer->tx_sg, *rx = &transfer->rx_sg; struct scatterlist *last_sg = sg_last(rx->sgl, rx->nents); unsigned int bytes_per_word, i; @@ -1367,7 +1394,7 @@ static int spi_imx_dma_transfer(struct spi_imx_data *spi_imx, spi_imx->wml = i; - ret = spi_imx_dma_configure(master); + ret = spi_imx_dma_configure(controller); if (ret) goto dma_failure_no_start; @@ -1382,7 +1409,7 @@ static int spi_imx_dma_transfer(struct spi_imx_data *spi_imx, * The TX DMA setup starts the transfer, so make sure RX is configured * before TX. */ - desc_rx = dmaengine_prep_slave_sg(master->dma_rx, + desc_rx = dmaengine_prep_slave_sg(controller->dma_rx, rx->sgl, rx->nents, DMA_DEV_TO_MEM, DMA_PREP_INTERRUPT | DMA_CTRL_ACK); if (!desc_rx) { @@ -1394,14 +1421,14 @@ static int spi_imx_dma_transfer(struct spi_imx_data *spi_imx, desc_rx->callback_param = (void *)spi_imx; dmaengine_submit(desc_rx); reinit_completion(&spi_imx->dma_rx_completion); - dma_async_issue_pending(master->dma_rx); + dma_async_issue_pending(controller->dma_rx); - desc_tx = dmaengine_prep_slave_sg(master->dma_tx, + desc_tx = dmaengine_prep_slave_sg(controller->dma_tx, tx->sgl, tx->nents, DMA_MEM_TO_DEV, DMA_PREP_INTERRUPT | DMA_CTRL_ACK); if (!desc_tx) { - dmaengine_terminate_all(master->dma_tx); - dmaengine_terminate_all(master->dma_rx); + dmaengine_terminate_all(controller->dma_tx); + dmaengine_terminate_all(controller->dma_rx); return -EINVAL; } @@ -1409,7 +1436,7 @@ static int spi_imx_dma_transfer(struct spi_imx_data *spi_imx, desc_tx->callback_param = (void *)spi_imx; dmaengine_submit(desc_tx); reinit_completion(&spi_imx->dma_tx_completion); - dma_async_issue_pending(master->dma_tx); + dma_async_issue_pending(controller->dma_tx); transfer_timeout = spi_imx_calculate_timeout(spi_imx, transfer->len); @@ -1418,21 +1445,21 @@ static int spi_imx_dma_transfer(struct spi_imx_data *spi_imx, transfer_timeout); if (!timeout) { dev_err(spi_imx->dev, "I/O Error in DMA TX\n"); - dmaengine_terminate_all(master->dma_tx); - dmaengine_terminate_all(master->dma_rx); + dmaengine_terminate_all(controller->dma_tx); + dmaengine_terminate_all(controller->dma_rx); return -ETIMEDOUT; } timeout = wait_for_completion_timeout(&spi_imx->dma_rx_completion, transfer_timeout); if (!timeout) { - dev_err(&master->dev, "I/O Error in DMA RX\n"); + dev_err(&controller->dev, "I/O Error in DMA RX\n"); spi_imx->devtype_data->reset(spi_imx); - dmaengine_terminate_all(master->dma_rx); + dmaengine_terminate_all(controller->dma_rx); return -ETIMEDOUT; } - return transfer->len; + return 0; /* fallback to pio */ dma_failure_no_start: transfer->error |= SPI_TRANS_FAIL_NO_START; @@ -1442,7 +1469,7 @@ dma_failure_no_start: static int spi_imx_pio_transfer(struct spi_device *spi, struct spi_transfer *transfer) { - struct spi_imx_data *spi_imx = spi_master_get_devdata(spi->master); + struct spi_imx_data *spi_imx = spi_controller_get_devdata(spi->controller); unsigned long transfer_timeout; unsigned long timeout; @@ -1468,14 +1495,62 @@ static int spi_imx_pio_transfer(struct spi_device *spi, return -ETIMEDOUT; } - return transfer->len; + return 0; +} + +static int spi_imx_poll_transfer(struct spi_device *spi, + struct spi_transfer *transfer) +{ + struct spi_imx_data *spi_imx = spi_controller_get_devdata(spi->controller); + unsigned long timeout; + + spi_imx->tx_buf = transfer->tx_buf; + spi_imx->rx_buf = transfer->rx_buf; + spi_imx->count = transfer->len; + spi_imx->txfifo = 0; + spi_imx->remainder = 0; + + /* fill in the fifo before timeout calculations if we are + * interrupted here, then the data is getting transferred by + * the HW while we are interrupted + */ + spi_imx_push(spi_imx); + + timeout = spi_imx_calculate_timeout(spi_imx, transfer->len) + jiffies; + while (spi_imx->txfifo) { + /* RX */ + while (spi_imx->txfifo && + spi_imx->devtype_data->rx_available(spi_imx)) { + spi_imx->rx(spi_imx); + spi_imx->txfifo--; + } + + /* TX */ + if (spi_imx->count) { + spi_imx_push(spi_imx); + continue; + } + + if (spi_imx->txfifo && + time_after(jiffies, timeout)) { + + dev_err_ratelimited(&spi->dev, + "timeout period reached: jiffies: %lu- falling back to interrupt mode\n", + jiffies - timeout); + + /* fall back to interrupt mode */ + return spi_imx_pio_transfer(spi, transfer); + } + } + + return 0; } static int spi_imx_pio_transfer_slave(struct spi_device *spi, struct spi_transfer *transfer) { - struct spi_imx_data *spi_imx = spi_master_get_devdata(spi->master); - int ret = transfer->len; + struct spi_imx_data *spi_imx = spi_controller_get_devdata(spi->controller); + int ret = 0; if (is_imx53_ecspi(spi_imx) && transfer->len > MX53_MAX_TRANSFER_BYTES) { @@ -1515,11 +1590,14 @@ static int spi_imx_pio_transfer_slave(struct spi_device *spi, return ret; } -static int spi_imx_transfer(struct spi_device *spi, +static int spi_imx_transfer_one(struct spi_controller *controller, + struct spi_device *spi, struct spi_transfer *transfer) { - struct spi_imx_data *spi_imx = spi_master_get_devdata(spi->master); + struct spi_imx_data *spi_imx = spi_controller_get_devdata(spi->controller); + unsigned long hz_per_byte, byte_limit; + spi_imx_setupxfer(spi, transfer); transfer->effective_speed_hz = spi_imx->spi_bus_clk; /* flush rxfifo before transfer */ @@ -1529,6 +1607,17 @@ static int spi_imx_transfer(struct spi_device *spi, if (spi_imx->slave_mode) return spi_imx_pio_transfer_slave(spi, transfer); + /* + * Calculate the estimated time in us the transfer runs. Find + * the number of Hz per byte per polling limit. + */ + hz_per_byte = polling_limit_us ? ((8 + 4) * USEC_PER_SEC) / polling_limit_us : 0; + byte_limit = hz_per_byte ? transfer->effective_speed_hz / hz_per_byte : 1; + + /* run in polling mode for short transfers */ + if (transfer->len < byte_limit) + return spi_imx_poll_transfer(spi, transfer); + if (spi_imx->usedma) return spi_imx_dma_transfer(spi_imx, transfer); @@ -1548,14 +1637,13 @@ static void spi_imx_cleanup(struct spi_device *spi) } static int -spi_imx_prepare_message(struct spi_master *master, struct spi_message *msg) +spi_imx_prepare_message(struct spi_controller *controller, struct spi_message *msg) { - struct spi_imx_data *spi_imx = spi_master_get_devdata(master); + struct spi_imx_data *spi_imx = spi_controller_get_devdata(controller); int ret; - ret = pm_runtime_get_sync(spi_imx->dev); + ret = pm_runtime_resume_and_get(spi_imx->dev); if (ret < 0) { - pm_runtime_put_noidle(spi_imx->dev); dev_err(spi_imx->dev, "failed to enable clock\n"); return ret; } @@ -1570,18 +1658,18 @@ spi_imx_prepare_message(struct spi_master *master, struct spi_message *msg) } static int -spi_imx_unprepare_message(struct spi_master *master, struct spi_message *msg) +spi_imx_unprepare_message(struct spi_controller *controller, struct spi_message *msg) { - struct spi_imx_data *spi_imx = spi_master_get_devdata(master); + struct spi_imx_data *spi_imx = spi_controller_get_devdata(controller); pm_runtime_mark_last_busy(spi_imx->dev); pm_runtime_put_autosuspend(spi_imx->dev); return 0; } -static int spi_imx_slave_abort(struct spi_master *master) +static int spi_imx_slave_abort(struct spi_controller *controller) { - struct spi_imx_data *spi_imx = spi_master_get_devdata(master); + struct spi_imx_data *spi_imx = spi_controller_get_devdata(controller); spi_imx->slave_aborted = true; complete(&spi_imx->xfer_done); @@ -1592,7 +1680,7 @@ static int spi_imx_slave_abort(struct spi_master *master) static int spi_imx_probe(struct platform_device *pdev) { struct device_node *np = pdev->dev.of_node; - struct spi_master *master; + struct spi_controller *controller; struct spi_imx_data *spi_imx; struct resource *res; int ret, irq, spi_drctl; @@ -1604,12 +1692,12 @@ static int spi_imx_probe(struct platform_device *pdev) slave_mode = devtype_data->has_slavemode && of_property_read_bool(np, "spi-slave"); if (slave_mode) - master = spi_alloc_slave(&pdev->dev, - sizeof(struct spi_imx_data)); + controller = spi_alloc_slave(&pdev->dev, + sizeof(struct spi_imx_data)); else - master = spi_alloc_master(&pdev->dev, - sizeof(struct spi_imx_data)); - if (!master) + controller = spi_alloc_master(&pdev->dev, + sizeof(struct spi_imx_data)); + if (!controller) return -ENOMEM; ret = of_property_read_u32(np, "fsl,spi-rdy-drctl", &spi_drctl); @@ -1618,14 +1706,14 @@ static int spi_imx_probe(struct platform_device *pdev) spi_drctl = 0; } - platform_set_drvdata(pdev, master); + platform_set_drvdata(pdev, controller); - master->bits_per_word_mask = SPI_BPW_RANGE_MASK(1, 32); - master->bus_num = np ? -1 : pdev->id; - master->use_gpio_descriptors = true; + controller->bits_per_word_mask = SPI_BPW_RANGE_MASK(1, 32); + controller->bus_num = np ? -1 : pdev->id; + controller->use_gpio_descriptors = true; - spi_imx = spi_master_get_devdata(master); - spi_imx->bitbang.master = master; + spi_imx = spi_controller_get_devdata(controller); + spi_imx->controller = controller; spi_imx->dev = &pdev->dev; spi_imx->slave_mode = slave_mode; @@ -1638,22 +1726,24 @@ static int spi_imx_probe(struct platform_device *pdev) * board files have <= 3 chip selects. */ if (!device_property_read_u32(&pdev->dev, "num-cs", &val)) - master->num_chipselect = val; + controller->num_chipselect = val; else - master->num_chipselect = 3; - - spi_imx->bitbang.setup_transfer = spi_imx_setupxfer; - spi_imx->bitbang.txrx_bufs = spi_imx_transfer; - spi_imx->bitbang.master->setup = spi_imx_setup; - spi_imx->bitbang.master->cleanup = spi_imx_cleanup; - spi_imx->bitbang.master->prepare_message = spi_imx_prepare_message; - spi_imx->bitbang.master->unprepare_message = spi_imx_unprepare_message; - spi_imx->bitbang.master->slave_abort = spi_imx_slave_abort; - spi_imx->bitbang.master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH \ - | SPI_NO_CS; + controller->num_chipselect = 3; + + spi_imx->controller->transfer_one = spi_imx_transfer_one; + spi_imx->controller->setup = spi_imx_setup; + spi_imx->controller->cleanup = spi_imx_cleanup; + spi_imx->controller->prepare_message = spi_imx_prepare_message; + spi_imx->controller->unprepare_message = spi_imx_unprepare_message; + spi_imx->controller->slave_abort = spi_imx_slave_abort; + spi_imx->controller->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH | SPI_NO_CS; + if (is_imx35_cspi(spi_imx) || is_imx51_ecspi(spi_imx) || is_imx53_ecspi(spi_imx)) - spi_imx->bitbang.master->mode_bits |= SPI_LOOP | SPI_READY; + spi_imx->controller->mode_bits |= SPI_LOOP | SPI_READY; + + if (is_imx51_ecspi(spi_imx) || is_imx53_ecspi(spi_imx)) + spi_imx->controller->mode_bits |= SPI_RX_CPHA_FLIP; if (is_imx51_ecspi(spi_imx) && device_property_read_u32(&pdev->dev, "cs-gpios", NULL)) @@ -1662,7 +1752,7 @@ static int spi_imx_probe(struct platform_device *pdev) * setting the burst length to the word size. This is * considerably faster than manually controlling the CS. */ - spi_imx->bitbang.master->mode_bits |= SPI_CS_WORD; + spi_imx->controller->mode_bits |= SPI_CS_WORD; spi_imx->spi_drctl = spi_drctl; @@ -1672,38 +1762,38 @@ static int spi_imx_probe(struct platform_device *pdev) spi_imx->base = devm_ioremap_resource(&pdev->dev, res); if (IS_ERR(spi_imx->base)) { ret = PTR_ERR(spi_imx->base); - goto out_master_put; + goto out_controller_put; } spi_imx->base_phys = res->start; irq = platform_get_irq(pdev, 0); if (irq < 0) { ret = irq; - goto out_master_put; + goto out_controller_put; } ret = devm_request_irq(&pdev->dev, irq, spi_imx_isr, 0, dev_name(&pdev->dev), spi_imx); if (ret) { dev_err(&pdev->dev, "can't get irq%d: %d\n", irq, ret); - goto out_master_put; + goto out_controller_put; } spi_imx->clk_ipg = devm_clk_get(&pdev->dev, "ipg"); if (IS_ERR(spi_imx->clk_ipg)) { ret = PTR_ERR(spi_imx->clk_ipg); - goto out_master_put; + goto out_controller_put; } spi_imx->clk_per = devm_clk_get(&pdev->dev, "per"); if (IS_ERR(spi_imx->clk_per)) { ret = PTR_ERR(spi_imx->clk_per); - goto out_master_put; + goto out_controller_put; } ret = clk_prepare_enable(spi_imx->clk_per); if (ret) - goto out_master_put; + goto out_controller_put; ret = clk_prepare_enable(spi_imx->clk_ipg); if (ret) @@ -1721,7 +1811,7 @@ static int spi_imx_probe(struct platform_device *pdev) * if validated on other chips. */ if (spi_imx->devtype_data->has_dmamode) { - ret = spi_imx_sdma_init(&pdev->dev, spi_imx, master); + ret = spi_imx_sdma_init(&pdev->dev, spi_imx, controller); if (ret == -EPROBE_DEFER) goto out_runtime_pm_put; @@ -1734,11 +1824,11 @@ static int spi_imx_probe(struct platform_device *pdev) spi_imx->devtype_data->intctrl(spi_imx, 0); - master->dev.of_node = pdev->dev.of_node; - ret = spi_bitbang_start(&spi_imx->bitbang); + controller->dev.of_node = pdev->dev.of_node; + ret = spi_register_controller(controller); if (ret) { - dev_err_probe(&pdev->dev, ret, "bitbang start failed\n"); - goto out_bitbang_start; + dev_err_probe(&pdev->dev, ret, "register controller failed\n"); + goto out_register_controller; } pm_runtime_mark_last_busy(spi_imx->dev); @@ -1746,7 +1836,7 @@ static int spi_imx_probe(struct platform_device *pdev) return ret; -out_bitbang_start: +out_register_controller: if (spi_imx->devtype_data->has_dmamode) spi_imx_sdma_exit(spi_imx); out_runtime_pm_put: @@ -1757,23 +1847,22 @@ out_runtime_pm_put: clk_disable_unprepare(spi_imx->clk_ipg); out_put_per: clk_disable_unprepare(spi_imx->clk_per); -out_master_put: - spi_master_put(master); +out_controller_put: + spi_controller_put(controller); return ret; } static int spi_imx_remove(struct platform_device *pdev) { - struct spi_master *master = platform_get_drvdata(pdev); - struct spi_imx_data *spi_imx = spi_master_get_devdata(master); + struct spi_controller *controller = platform_get_drvdata(pdev); + struct spi_imx_data *spi_imx = spi_controller_get_devdata(controller); int ret; - spi_bitbang_stop(&spi_imx->bitbang); + spi_unregister_controller(controller); - ret = pm_runtime_get_sync(spi_imx->dev); + ret = pm_runtime_resume_and_get(spi_imx->dev); if (ret < 0) { - pm_runtime_put_noidle(spi_imx->dev); dev_err(spi_imx->dev, "failed to enable clock\n"); return ret; } @@ -1785,18 +1874,17 @@ static int spi_imx_remove(struct platform_device *pdev) pm_runtime_disable(spi_imx->dev); spi_imx_sdma_exit(spi_imx); - spi_master_put(master); return 0; } static int __maybe_unused spi_imx_runtime_resume(struct device *dev) { - struct spi_master *master = dev_get_drvdata(dev); + struct spi_controller *controller = dev_get_drvdata(dev); struct spi_imx_data *spi_imx; int ret; - spi_imx = spi_master_get_devdata(master); + spi_imx = spi_controller_get_devdata(controller); ret = clk_prepare_enable(spi_imx->clk_per); if (ret) @@ -1813,10 +1901,10 @@ static int __maybe_unused spi_imx_runtime_resume(struct device *dev) static int __maybe_unused spi_imx_runtime_suspend(struct device *dev) { - struct spi_master *master = dev_get_drvdata(dev); + struct spi_controller *controller = dev_get_drvdata(dev); struct spi_imx_data *spi_imx; - spi_imx = spi_master_get_devdata(master); + spi_imx = spi_controller_get_devdata(controller); clk_disable_unprepare(spi_imx->clk_per); clk_disable_unprepare(spi_imx->clk_ipg); diff --git a/drivers/spi/spi-ingenic.c b/drivers/spi/spi-ingenic.c index 03077a7e11c8..713a238bee63 100644 --- a/drivers/spi/spi-ingenic.c +++ b/drivers/spi/spi-ingenic.c @@ -1,8 +1,9 @@ // SPDX-License-Identifier: GPL-2.0 /* - * SPI bus driver for the Ingenic JZ47xx SoCs + * SPI bus driver for the Ingenic SoCs * Copyright (c) 2017-2021 Artur Rojek <contact@artur-rojek.eu> * Copyright (c) 2017-2021 Paul Cercueil <paul@crapouillou.net> + * Copyright (c) 2022 周琰杰 (Zhou Yanjie) <zhouyanjie@wanyeetech.com> */ #include <linux/clk.h> @@ -52,6 +53,9 @@ struct jz_soc_info { u32 bits_per_word_mask; struct reg_field flen_field; bool has_trendian; + + unsigned int max_speed_hz; + unsigned int max_native_cs; }; struct ingenic_spi { @@ -380,7 +384,7 @@ static int spi_ingenic_probe(struct platform_device *pdev) struct spi_controller *ctlr; struct ingenic_spi *priv; void __iomem *base; - int ret; + int num_cs, ret; pdata = of_device_get_match_data(dev); if (!pdata) { @@ -416,6 +420,9 @@ static int spi_ingenic_probe(struct platform_device *pdev) if (IS_ERR(priv->flen_field)) return PTR_ERR(priv->flen_field); + if (device_property_read_u32(dev, "num-cs", &num_cs)) + num_cs = pdata->max_native_cs; + platform_set_drvdata(pdev, ctlr); ctlr->prepare_transfer_hardware = spi_ingenic_prepare_hardware; @@ -428,8 +435,10 @@ static int spi_ingenic_probe(struct platform_device *pdev) ctlr->max_dma_len = SPI_INGENIC_FIFO_SIZE; ctlr->bits_per_word_mask = pdata->bits_per_word_mask; ctlr->min_speed_hz = 7200; - ctlr->max_speed_hz = 54000000; - ctlr->num_chipselect = 2; + ctlr->max_speed_hz = pdata->max_speed_hz; + ctlr->use_gpio_descriptors = true; + ctlr->max_native_cs = pdata->max_native_cs; + ctlr->num_chipselect = num_cs; ctlr->dev.of_node = pdev->dev.of_node; if (spi_ingenic_request_dma(ctlr, dev)) @@ -452,17 +461,44 @@ static const struct jz_soc_info jz4750_soc_info = { .bits_per_word_mask = SPI_BPW_RANGE_MASK(2, 17), .flen_field = REG_FIELD(REG_SSICR1, 4, 7), .has_trendian = false, + + .max_speed_hz = 54000000, + .max_native_cs = 2, }; static const struct jz_soc_info jz4780_soc_info = { .bits_per_word_mask = SPI_BPW_RANGE_MASK(2, 32), .flen_field = REG_FIELD(REG_SSICR1, 3, 7), .has_trendian = true, + + .max_speed_hz = 54000000, + .max_native_cs = 2, +}; + +static const struct jz_soc_info x1000_soc_info = { + .bits_per_word_mask = SPI_BPW_RANGE_MASK(2, 32), + .flen_field = REG_FIELD(REG_SSICR1, 3, 7), + .has_trendian = true, + + .max_speed_hz = 50000000, + .max_native_cs = 2, +}; + +static const struct jz_soc_info x2000_soc_info = { + .bits_per_word_mask = SPI_BPW_RANGE_MASK(2, 32), + .flen_field = REG_FIELD(REG_SSICR1, 3, 7), + .has_trendian = true, + + .max_speed_hz = 50000000, + .max_native_cs = 1, }; static const struct of_device_id spi_ingenic_of_match[] = { { .compatible = "ingenic,jz4750-spi", .data = &jz4750_soc_info }, + { .compatible = "ingenic,jz4775-spi", .data = &jz4780_soc_info }, { .compatible = "ingenic,jz4780-spi", .data = &jz4780_soc_info }, + { .compatible = "ingenic,x1000-spi", .data = &x1000_soc_info }, + { .compatible = "ingenic,x2000-spi", .data = &x2000_soc_info }, {} }; MODULE_DEVICE_TABLE(of, spi_ingenic_of_match); @@ -476,7 +512,8 @@ static struct platform_driver spi_ingenic_driver = { }; module_platform_driver(spi_ingenic_driver); -MODULE_DESCRIPTION("SPI bus driver for the Ingenic JZ47xx SoCs"); +MODULE_DESCRIPTION("SPI bus driver for the Ingenic SoCs"); MODULE_AUTHOR("Artur Rojek <contact@artur-rojek.eu>"); MODULE_AUTHOR("Paul Cercueil <paul@crapouillou.net>"); +MODULE_AUTHOR("周琰杰 (Zhou Yanjie) <zhouyanjie@wanyeetech.com>"); MODULE_LICENSE("GPL"); diff --git a/drivers/spi/spi-intel-pci.c b/drivers/spi/spi-intel-pci.c index a5ef7a526a7f..f6eec7a869b6 100644 --- a/drivers/spi/spi-intel-pci.c +++ b/drivers/spi/spi-intel-pci.c @@ -72,6 +72,7 @@ static const struct pci_device_id intel_spi_pci_ids[] = { { PCI_VDEVICE(INTEL, 0x4da4), (unsigned long)&bxt_info }, { PCI_VDEVICE(INTEL, 0x51a4), (unsigned long)&cnl_info }, { PCI_VDEVICE(INTEL, 0x54a4), (unsigned long)&cnl_info }, + { PCI_VDEVICE(INTEL, 0x7a24), (unsigned long)&cnl_info }, { PCI_VDEVICE(INTEL, 0x7aa4), (unsigned long)&cnl_info }, { PCI_VDEVICE(INTEL, 0xa0a4), (unsigned long)&bxt_info }, { PCI_VDEVICE(INTEL, 0xa1a4), (unsigned long)&bxt_info }, diff --git a/drivers/spi/spi-intel.c b/drivers/spi/spi-intel.c index e937cfe85559..50f42983b950 100644 --- a/drivers/spi/spi-intel.c +++ b/drivers/spi/spi-intel.c @@ -779,10 +779,59 @@ static const char *intel_spi_get_name(struct spi_mem *mem) return dev_name(ispi->dev); } +static int intel_spi_dirmap_create(struct spi_mem_dirmap_desc *desc) +{ + struct intel_spi *ispi = spi_master_get_devdata(desc->mem->spi->master); + const struct intel_spi_mem_op *iop; + + iop = intel_spi_match_mem_op(ispi, &desc->info.op_tmpl); + if (!iop) + return -EOPNOTSUPP; + + desc->priv = (void *)iop; + return 0; +} + +static ssize_t intel_spi_dirmap_read(struct spi_mem_dirmap_desc *desc, u64 offs, + size_t len, void *buf) +{ + struct intel_spi *ispi = spi_master_get_devdata(desc->mem->spi->master); + const struct intel_spi_mem_op *iop = desc->priv; + struct spi_mem_op op = desc->info.op_tmpl; + int ret; + + /* Fill in the gaps */ + op.addr.val = offs; + op.data.nbytes = len; + op.data.buf.in = buf; + + ret = iop->exec_op(ispi, iop, &op); + return ret ? ret : len; +} + +static ssize_t intel_spi_dirmap_write(struct spi_mem_dirmap_desc *desc, u64 offs, + size_t len, const void *buf) +{ + struct intel_spi *ispi = spi_master_get_devdata(desc->mem->spi->master); + const struct intel_spi_mem_op *iop = desc->priv; + struct spi_mem_op op = desc->info.op_tmpl; + int ret; + + op.addr.val = offs; + op.data.nbytes = len; + op.data.buf.out = buf; + + ret = iop->exec_op(ispi, iop, &op); + return ret ? ret : len; +} + static const struct spi_controller_mem_ops intel_spi_mem_ops = { .supports_op = intel_spi_supports_mem_op, .exec_op = intel_spi_exec_mem_op, .get_name = intel_spi_get_name, + .dirmap_create = intel_spi_dirmap_create, + .dirmap_read = intel_spi_dirmap_read, + .dirmap_write = intel_spi_dirmap_write, }; #define INTEL_SPI_OP_ADDR(__nbytes) \ @@ -1205,7 +1254,7 @@ static int intel_spi_populate_chip(struct intel_spi *ispi) * intel_spi_probe() - Probe the Intel SPI flash controller * @dev: Pointer to the parent device * @mem: MMIO resource - * @info: Platform spefific information + * @info: Platform specific information * * Probes Intel SPI flash controller and creates the flash chip device. * Returns %0 on success and negative errno in case of failure. diff --git a/drivers/spi/spi-mem.c b/drivers/spi/spi-mem.c index 0e8dafc62d94..e8de4f5017cd 100644 --- a/drivers/spi/spi-mem.c +++ b/drivers/spi/spi-mem.c @@ -10,6 +10,7 @@ #include <linux/pm_runtime.h> #include <linux/spi/spi.h> #include <linux/spi/spi-mem.h> +#include <linux/sched/task_stack.h> #include "internals.h" @@ -211,6 +212,15 @@ static int spi_mem_check_op(const struct spi_mem_op *op) !spi_mem_buswidth_is_valid(op->data.buswidth)) return -EINVAL; + /* Buffers must be DMA-able. */ + if (WARN_ON_ONCE(op->data.dir == SPI_MEM_DATA_IN && + object_is_on_stack(op->data.buf.in))) + return -EINVAL; + + if (WARN_ON_ONCE(op->data.dir == SPI_MEM_DATA_OUT && + object_is_on_stack(op->data.buf.out))) + return -EINVAL; + return 0; } @@ -262,9 +272,8 @@ static int spi_mem_access_start(struct spi_mem *mem) if (ctlr->auto_runtime_pm) { int ret; - ret = pm_runtime_get_sync(ctlr->dev.parent); + ret = pm_runtime_resume_and_get(ctlr->dev.parent); if (ret < 0) { - pm_runtime_put_noidle(ctlr->dev.parent); dev_err(&ctlr->dev, "Failed to power device: %d\n", ret); return ret; diff --git a/drivers/spi/spi-mpc52xx-psc.c b/drivers/spi/spi-mpc52xx-psc.c index 21ef5d481faf..7654736c2c0e 100644 --- a/drivers/spi/spi-mpc52xx-psc.c +++ b/drivers/spi/spi-mpc52xx-psc.c @@ -20,6 +20,7 @@ #include <linux/spi/spi.h> #include <linux/fsl_devices.h> #include <linux/slab.h> +#include <linux/of_irq.h> #include <asm/mpc52xx.h> #include <asm/mpc52xx_psc.h> diff --git a/drivers/spi/spi-mpc52xx.c b/drivers/spi/spi-mpc52xx.c index 51041526546d..3ebdce804b90 100644 --- a/drivers/spi/spi-mpc52xx.c +++ b/drivers/spi/spi-mpc52xx.c @@ -19,6 +19,9 @@ #include <linux/io.h> #include <linux/of_gpio.h> #include <linux/slab.h> +#include <linux/of_address.h> +#include <linux/of_irq.h> + #include <asm/time.h> #include <asm/mpc52xx.h> diff --git a/drivers/spi/spi-mt65xx.c b/drivers/spi/spi-mt65xx.c index 1a0b3208dfca..0a3b9f7eed30 100644 --- a/drivers/spi/spi-mt65xx.c +++ b/drivers/spi/spi-mt65xx.c @@ -17,105 +17,148 @@ #include <linux/platform_data/spi-mt65xx.h> #include <linux/pm_runtime.h> #include <linux/spi/spi.h> +#include <linux/spi/spi-mem.h> #include <linux/dma-mapping.h> -#define SPI_CFG0_REG 0x0000 -#define SPI_CFG1_REG 0x0004 -#define SPI_TX_SRC_REG 0x0008 -#define SPI_RX_DST_REG 0x000c -#define SPI_TX_DATA_REG 0x0010 -#define SPI_RX_DATA_REG 0x0014 -#define SPI_CMD_REG 0x0018 -#define SPI_STATUS0_REG 0x001c -#define SPI_PAD_SEL_REG 0x0024 -#define SPI_CFG2_REG 0x0028 -#define SPI_TX_SRC_REG_64 0x002c -#define SPI_RX_DST_REG_64 0x0030 -#define SPI_CFG3_IPM_REG 0x0040 - -#define SPI_CFG0_SCK_HIGH_OFFSET 0 -#define SPI_CFG0_SCK_LOW_OFFSET 8 -#define SPI_CFG0_CS_HOLD_OFFSET 16 -#define SPI_CFG0_CS_SETUP_OFFSET 24 -#define SPI_ADJUST_CFG0_CS_HOLD_OFFSET 0 -#define SPI_ADJUST_CFG0_CS_SETUP_OFFSET 16 - -#define SPI_CFG1_CS_IDLE_OFFSET 0 -#define SPI_CFG1_PACKET_LOOP_OFFSET 8 -#define SPI_CFG1_PACKET_LENGTH_OFFSET 16 -#define SPI_CFG1_GET_TICK_DLY_OFFSET 29 -#define SPI_CFG1_GET_TICK_DLY_OFFSET_V1 30 - -#define SPI_CFG1_GET_TICK_DLY_MASK 0xe0000000 -#define SPI_CFG1_GET_TICK_DLY_MASK_V1 0xc0000000 - -#define SPI_CFG1_CS_IDLE_MASK 0xff -#define SPI_CFG1_PACKET_LOOP_MASK 0xff00 -#define SPI_CFG1_PACKET_LENGTH_MASK 0x3ff0000 -#define SPI_CFG1_IPM_PACKET_LENGTH_MASK GENMASK(31, 16) -#define SPI_CFG2_SCK_HIGH_OFFSET 0 -#define SPI_CFG2_SCK_LOW_OFFSET 16 - -#define SPI_CMD_ACT BIT(0) -#define SPI_CMD_RESUME BIT(1) -#define SPI_CMD_RST BIT(2) -#define SPI_CMD_PAUSE_EN BIT(4) -#define SPI_CMD_DEASSERT BIT(5) -#define SPI_CMD_SAMPLE_SEL BIT(6) -#define SPI_CMD_CS_POL BIT(7) -#define SPI_CMD_CPHA BIT(8) -#define SPI_CMD_CPOL BIT(9) -#define SPI_CMD_RX_DMA BIT(10) -#define SPI_CMD_TX_DMA BIT(11) -#define SPI_CMD_TXMSBF BIT(12) -#define SPI_CMD_RXMSBF BIT(13) -#define SPI_CMD_RX_ENDIAN BIT(14) -#define SPI_CMD_TX_ENDIAN BIT(15) -#define SPI_CMD_FINISH_IE BIT(16) -#define SPI_CMD_PAUSE_IE BIT(17) -#define SPI_CMD_IPM_NONIDLE_MODE BIT(19) -#define SPI_CMD_IPM_SPIM_LOOP BIT(21) -#define SPI_CMD_IPM_GET_TICKDLY_OFFSET 22 +#define SPI_CFG0_REG 0x0000 +#define SPI_CFG1_REG 0x0004 +#define SPI_TX_SRC_REG 0x0008 +#define SPI_RX_DST_REG 0x000c +#define SPI_TX_DATA_REG 0x0010 +#define SPI_RX_DATA_REG 0x0014 +#define SPI_CMD_REG 0x0018 +#define SPI_STATUS0_REG 0x001c +#define SPI_PAD_SEL_REG 0x0024 +#define SPI_CFG2_REG 0x0028 +#define SPI_TX_SRC_REG_64 0x002c +#define SPI_RX_DST_REG_64 0x0030 +#define SPI_CFG3_IPM_REG 0x0040 + +#define SPI_CFG0_SCK_HIGH_OFFSET 0 +#define SPI_CFG0_SCK_LOW_OFFSET 8 +#define SPI_CFG0_CS_HOLD_OFFSET 16 +#define SPI_CFG0_CS_SETUP_OFFSET 24 +#define SPI_ADJUST_CFG0_CS_HOLD_OFFSET 0 +#define SPI_ADJUST_CFG0_CS_SETUP_OFFSET 16 + +#define SPI_CFG1_CS_IDLE_OFFSET 0 +#define SPI_CFG1_PACKET_LOOP_OFFSET 8 +#define SPI_CFG1_PACKET_LENGTH_OFFSET 16 +#define SPI_CFG1_GET_TICK_DLY_OFFSET 29 +#define SPI_CFG1_GET_TICK_DLY_OFFSET_V1 30 + +#define SPI_CFG1_GET_TICK_DLY_MASK 0xe0000000 +#define SPI_CFG1_GET_TICK_DLY_MASK_V1 0xc0000000 + +#define SPI_CFG1_CS_IDLE_MASK 0xff +#define SPI_CFG1_PACKET_LOOP_MASK 0xff00 +#define SPI_CFG1_PACKET_LENGTH_MASK 0x3ff0000 +#define SPI_CFG1_IPM_PACKET_LENGTH_MASK GENMASK(31, 16) +#define SPI_CFG2_SCK_HIGH_OFFSET 0 +#define SPI_CFG2_SCK_LOW_OFFSET 16 + +#define SPI_CMD_ACT BIT(0) +#define SPI_CMD_RESUME BIT(1) +#define SPI_CMD_RST BIT(2) +#define SPI_CMD_PAUSE_EN BIT(4) +#define SPI_CMD_DEASSERT BIT(5) +#define SPI_CMD_SAMPLE_SEL BIT(6) +#define SPI_CMD_CS_POL BIT(7) +#define SPI_CMD_CPHA BIT(8) +#define SPI_CMD_CPOL BIT(9) +#define SPI_CMD_RX_DMA BIT(10) +#define SPI_CMD_TX_DMA BIT(11) +#define SPI_CMD_TXMSBF BIT(12) +#define SPI_CMD_RXMSBF BIT(13) +#define SPI_CMD_RX_ENDIAN BIT(14) +#define SPI_CMD_TX_ENDIAN BIT(15) +#define SPI_CMD_FINISH_IE BIT(16) +#define SPI_CMD_PAUSE_IE BIT(17) +#define SPI_CMD_IPM_NONIDLE_MODE BIT(19) +#define SPI_CMD_IPM_SPIM_LOOP BIT(21) +#define SPI_CMD_IPM_GET_TICKDLY_OFFSET 22 #define SPI_CMD_IPM_GET_TICKDLY_MASK GENMASK(24, 22) -#define SPI_CFG3_IPM_HALF_DUPLEX_DIR BIT(2) -#define SPI_CFG3_IPM_HALF_DUPLEX_EN BIT(3) -#define MT8173_SPI_MAX_PAD_SEL 3 -#define MTK_SPI_PAUSE_INT_STATUS 0x2 +#define PIN_MODE_CFG(x) ((x) / 2) -#define MTK_SPI_IDLE 0 -#define MTK_SPI_PAUSED 1 +#define SPI_CFG3_IPM_HALF_DUPLEX_DIR BIT(2) +#define SPI_CFG3_IPM_HALF_DUPLEX_EN BIT(3) +#define SPI_CFG3_IPM_XMODE_EN BIT(4) +#define SPI_CFG3_IPM_NODATA_FLAG BIT(5) +#define SPI_CFG3_IPM_CMD_BYTELEN_OFFSET 8 +#define SPI_CFG3_IPM_ADDR_BYTELEN_OFFSET 12 -#define MTK_SPI_MAX_FIFO_SIZE 32U -#define MTK_SPI_PACKET_SIZE 1024 -#define MTK_SPI_IPM_PACKET_SIZE SZ_64K -#define MTK_SPI_32BITS_MASK (0xffffffff) +#define SPI_CFG3_IPM_CMD_PIN_MODE_MASK GENMASK(1, 0) +#define SPI_CFG3_IPM_CMD_BYTELEN_MASK GENMASK(11, 8) +#define SPI_CFG3_IPM_ADDR_BYTELEN_MASK GENMASK(15, 12) -#define DMA_ADDR_EXT_BITS (36) -#define DMA_ADDR_DEF_BITS (32) +#define MT8173_SPI_MAX_PAD_SEL 3 +#define MTK_SPI_PAUSE_INT_STATUS 0x2 + +#define MTK_SPI_MAX_FIFO_SIZE 32U +#define MTK_SPI_PACKET_SIZE 1024 +#define MTK_SPI_IPM_PACKET_SIZE SZ_64K +#define MTK_SPI_IPM_PACKET_LOOP SZ_256 + +#define MTK_SPI_IDLE 0 +#define MTK_SPI_PAUSED 1 + +#define MTK_SPI_32BITS_MASK (0xffffffff) + +#define DMA_ADDR_EXT_BITS (36) +#define DMA_ADDR_DEF_BITS (32) + +/** + * struct mtk_spi_compatible - device data structure + * @need_pad_sel: Enable pad (pins) selection in SPI controller + * @must_tx: Must explicitly send dummy TX bytes to do RX only transfer + * @enhance_timing: Enable adjusting cfg register to enhance time accuracy + * @dma_ext: DMA address extension supported + * @no_need_unprepare: Don't unprepare the SPI clk during runtime + * @ipm_design: Adjust/extend registers to support IPM design IP features + */ struct mtk_spi_compatible { bool need_pad_sel; - /* Must explicitly send dummy Tx bytes to do Rx only transfer */ bool must_tx; - /* some IC design adjust cfg register to enhance time accuracy */ bool enhance_timing; - /* some IC support DMA addr extension */ bool dma_ext; - /* some IC no need unprepare SPI clk */ bool no_need_unprepare; - /* IPM design adjust and extend register to support more features */ bool ipm_design; - }; +/** + * struct mtk_spi - SPI driver instance + * @base: Start address of the SPI controller registers + * @state: SPI controller state + * @pad_num: Number of pad_sel entries + * @pad_sel: Groups of pins to select + * @parent_clk: Parent of sel_clk + * @sel_clk: SPI master mux clock + * @spi_clk: Peripheral clock + * @spi_hclk: AHB bus clock + * @cur_transfer: Currently processed SPI transfer + * @xfer_len: Number of bytes to transfer + * @num_xfered: Number of transferred bytes + * @tx_sgl: TX transfer scatterlist + * @rx_sgl: RX transfer scatterlist + * @tx_sgl_len: Size of TX DMA transfer + * @rx_sgl_len: Size of RX DMA transfer + * @dev_comp: Device data structure + * @spi_clk_hz: Current SPI clock in Hz + * @spimem_done: SPI-MEM operation completion + * @use_spimem: Enables SPI-MEM + * @dev: Device pointer + * @tx_dma: DMA start for SPI-MEM TX + * @rx_dma: DMA start for SPI-MEM RX + */ struct mtk_spi { void __iomem *base; u32 state; int pad_num; u32 *pad_sel; - struct clk *parent_clk, *sel_clk, *spi_clk; + struct clk *parent_clk, *sel_clk, *spi_clk, *spi_hclk; struct spi_transfer *cur_transfer; u32 xfer_len; u32 num_xfered; @@ -123,6 +166,11 @@ struct mtk_spi { u32 tx_sgl_len, rx_sgl_len; const struct mtk_spi_compatible *dev_comp; u32 spi_clk_hz; + struct completion spimem_done; + bool use_spimem; + struct device *dev; + dma_addr_t tx_dma; + dma_addr_t rx_dma; }; static const struct mtk_spi_compatible mtk_common_compat; @@ -704,6 +752,12 @@ static irqreturn_t mtk_spi_interrupt(int irq, void *dev_id) else mdata->state = MTK_SPI_IDLE; + /* SPI-MEM ops */ + if (mdata->use_spimem) { + complete(&mdata->spimem_done); + return IRQ_HANDLED; + } + if (!master->can_dma(master, NULL, trans)) { if (trans->rx_buf) { cnt = mdata->xfer_len / 4; @@ -787,21 +841,287 @@ static irqreturn_t mtk_spi_interrupt(int irq, void *dev_id) return IRQ_HANDLED; } +static int mtk_spi_mem_adjust_op_size(struct spi_mem *mem, + struct spi_mem_op *op) +{ + int opcode_len; + + if (op->data.dir != SPI_MEM_NO_DATA) { + opcode_len = 1 + op->addr.nbytes + op->dummy.nbytes; + if (opcode_len + op->data.nbytes > MTK_SPI_IPM_PACKET_SIZE) { + op->data.nbytes = MTK_SPI_IPM_PACKET_SIZE - opcode_len; + /* force data buffer dma-aligned. */ + op->data.nbytes -= op->data.nbytes % 4; + } + } + + return 0; +} + +static bool mtk_spi_mem_supports_op(struct spi_mem *mem, + const struct spi_mem_op *op) +{ + if (!spi_mem_default_supports_op(mem, op)) + return false; + + if (op->addr.nbytes && op->dummy.nbytes && + op->addr.buswidth != op->dummy.buswidth) + return false; + + if (op->addr.nbytes + op->dummy.nbytes > 16) + return false; + + if (op->data.nbytes > MTK_SPI_IPM_PACKET_SIZE) { + if (op->data.nbytes / MTK_SPI_IPM_PACKET_SIZE > + MTK_SPI_IPM_PACKET_LOOP || + op->data.nbytes % MTK_SPI_IPM_PACKET_SIZE != 0) + return false; + } + + return true; +} + +static void mtk_spi_mem_setup_dma_xfer(struct spi_master *master, + const struct spi_mem_op *op) +{ + struct mtk_spi *mdata = spi_master_get_devdata(master); + + writel((u32)(mdata->tx_dma & MTK_SPI_32BITS_MASK), + mdata->base + SPI_TX_SRC_REG); +#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT + if (mdata->dev_comp->dma_ext) + writel((u32)(mdata->tx_dma >> 32), + mdata->base + SPI_TX_SRC_REG_64); +#endif + + if (op->data.dir == SPI_MEM_DATA_IN) { + writel((u32)(mdata->rx_dma & MTK_SPI_32BITS_MASK), + mdata->base + SPI_RX_DST_REG); +#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT + if (mdata->dev_comp->dma_ext) + writel((u32)(mdata->rx_dma >> 32), + mdata->base + SPI_RX_DST_REG_64); +#endif + } +} + +static int mtk_spi_transfer_wait(struct spi_mem *mem, + const struct spi_mem_op *op) +{ + struct mtk_spi *mdata = spi_master_get_devdata(mem->spi->master); + /* + * For each byte we wait for 8 cycles of the SPI clock. + * Since speed is defined in Hz and we want milliseconds, + * so it should be 8 * 1000. + */ + u64 ms = 8000LL; + + if (op->data.dir == SPI_MEM_NO_DATA) + ms *= 32; /* prevent we may get 0 for short transfers. */ + else + ms *= op->data.nbytes; + ms = div_u64(ms, mem->spi->max_speed_hz); + ms += ms + 1000; /* 1s tolerance */ + + if (ms > UINT_MAX) + ms = UINT_MAX; + + if (!wait_for_completion_timeout(&mdata->spimem_done, + msecs_to_jiffies(ms))) { + dev_err(mdata->dev, "spi-mem transfer timeout\n"); + return -ETIMEDOUT; + } + + return 0; +} + +static int mtk_spi_mem_exec_op(struct spi_mem *mem, + const struct spi_mem_op *op) +{ + struct mtk_spi *mdata = spi_master_get_devdata(mem->spi->master); + u32 reg_val, nio, tx_size; + char *tx_tmp_buf, *rx_tmp_buf; + int ret = 0; + + mdata->use_spimem = true; + reinit_completion(&mdata->spimem_done); + + mtk_spi_reset(mdata); + mtk_spi_hw_init(mem->spi->master, mem->spi); + mtk_spi_prepare_transfer(mem->spi->master, mem->spi->max_speed_hz); + + reg_val = readl(mdata->base + SPI_CFG3_IPM_REG); + /* opcode byte len */ + reg_val &= ~SPI_CFG3_IPM_CMD_BYTELEN_MASK; + reg_val |= 1 << SPI_CFG3_IPM_CMD_BYTELEN_OFFSET; + + /* addr & dummy byte len */ + reg_val &= ~SPI_CFG3_IPM_ADDR_BYTELEN_MASK; + if (op->addr.nbytes || op->dummy.nbytes) + reg_val |= (op->addr.nbytes + op->dummy.nbytes) << + SPI_CFG3_IPM_ADDR_BYTELEN_OFFSET; + + /* data byte len */ + if (op->data.dir == SPI_MEM_NO_DATA) { + reg_val |= SPI_CFG3_IPM_NODATA_FLAG; + writel(0, mdata->base + SPI_CFG1_REG); + } else { + reg_val &= ~SPI_CFG3_IPM_NODATA_FLAG; + mdata->xfer_len = op->data.nbytes; + mtk_spi_setup_packet(mem->spi->master); + } + + if (op->addr.nbytes || op->dummy.nbytes) { + if (op->addr.buswidth == 1 || op->dummy.buswidth == 1) + reg_val |= SPI_CFG3_IPM_XMODE_EN; + else + reg_val &= ~SPI_CFG3_IPM_XMODE_EN; + } + + if (op->addr.buswidth == 2 || + op->dummy.buswidth == 2 || + op->data.buswidth == 2) + nio = 2; + else if (op->addr.buswidth == 4 || + op->dummy.buswidth == 4 || + op->data.buswidth == 4) + nio = 4; + else + nio = 1; + + reg_val &= ~SPI_CFG3_IPM_CMD_PIN_MODE_MASK; + reg_val |= PIN_MODE_CFG(nio); + + reg_val |= SPI_CFG3_IPM_HALF_DUPLEX_EN; + if (op->data.dir == SPI_MEM_DATA_IN) + reg_val |= SPI_CFG3_IPM_HALF_DUPLEX_DIR; + else + reg_val &= ~SPI_CFG3_IPM_HALF_DUPLEX_DIR; + writel(reg_val, mdata->base + SPI_CFG3_IPM_REG); + + tx_size = 1 + op->addr.nbytes + op->dummy.nbytes; + if (op->data.dir == SPI_MEM_DATA_OUT) + tx_size += op->data.nbytes; + + tx_size = max_t(u32, tx_size, 32); + + tx_tmp_buf = kzalloc(tx_size, GFP_KERNEL | GFP_DMA); + if (!tx_tmp_buf) { + mdata->use_spimem = false; + return -ENOMEM; + } + + tx_tmp_buf[0] = op->cmd.opcode; + + if (op->addr.nbytes) { + int i; + + for (i = 0; i < op->addr.nbytes; i++) + tx_tmp_buf[i + 1] = op->addr.val >> + (8 * (op->addr.nbytes - i - 1)); + } + + if (op->dummy.nbytes) + memset(tx_tmp_buf + op->addr.nbytes + 1, + 0xff, + op->dummy.nbytes); + + if (op->data.nbytes && op->data.dir == SPI_MEM_DATA_OUT) + memcpy(tx_tmp_buf + op->dummy.nbytes + op->addr.nbytes + 1, + op->data.buf.out, + op->data.nbytes); + + mdata->tx_dma = dma_map_single(mdata->dev, tx_tmp_buf, + tx_size, DMA_TO_DEVICE); + if (dma_mapping_error(mdata->dev, mdata->tx_dma)) { + ret = -ENOMEM; + goto err_exit; + } + + if (op->data.dir == SPI_MEM_DATA_IN) { + if (!IS_ALIGNED((size_t)op->data.buf.in, 4)) { + rx_tmp_buf = kzalloc(op->data.nbytes, + GFP_KERNEL | GFP_DMA); + if (!rx_tmp_buf) { + ret = -ENOMEM; + goto unmap_tx_dma; + } + } else { + rx_tmp_buf = op->data.buf.in; + } + + mdata->rx_dma = dma_map_single(mdata->dev, + rx_tmp_buf, + op->data.nbytes, + DMA_FROM_DEVICE); + if (dma_mapping_error(mdata->dev, mdata->rx_dma)) { + ret = -ENOMEM; + goto kfree_rx_tmp_buf; + } + } + + reg_val = readl(mdata->base + SPI_CMD_REG); + reg_val |= SPI_CMD_TX_DMA; + if (op->data.dir == SPI_MEM_DATA_IN) + reg_val |= SPI_CMD_RX_DMA; + writel(reg_val, mdata->base + SPI_CMD_REG); + + mtk_spi_mem_setup_dma_xfer(mem->spi->master, op); + + mtk_spi_enable_transfer(mem->spi->master); + + /* Wait for the interrupt. */ + ret = mtk_spi_transfer_wait(mem, op); + if (ret) + goto unmap_rx_dma; + + /* spi disable dma */ + reg_val = readl(mdata->base + SPI_CMD_REG); + reg_val &= ~SPI_CMD_TX_DMA; + if (op->data.dir == SPI_MEM_DATA_IN) + reg_val &= ~SPI_CMD_RX_DMA; + writel(reg_val, mdata->base + SPI_CMD_REG); + +unmap_rx_dma: + if (op->data.dir == SPI_MEM_DATA_IN) { + dma_unmap_single(mdata->dev, mdata->rx_dma, + op->data.nbytes, DMA_FROM_DEVICE); + if (!IS_ALIGNED((size_t)op->data.buf.in, 4)) + memcpy(op->data.buf.in, rx_tmp_buf, op->data.nbytes); + } +kfree_rx_tmp_buf: + if (op->data.dir == SPI_MEM_DATA_IN && + !IS_ALIGNED((size_t)op->data.buf.in, 4)) + kfree(rx_tmp_buf); +unmap_tx_dma: + dma_unmap_single(mdata->dev, mdata->tx_dma, + tx_size, DMA_TO_DEVICE); +err_exit: + kfree(tx_tmp_buf); + mdata->use_spimem = false; + + return ret; +} + +static const struct spi_controller_mem_ops mtk_spi_mem_ops = { + .adjust_op_size = mtk_spi_mem_adjust_op_size, + .supports_op = mtk_spi_mem_supports_op, + .exec_op = mtk_spi_mem_exec_op, +}; + static int mtk_spi_probe(struct platform_device *pdev) { + struct device *dev = &pdev->dev; struct spi_master *master; struct mtk_spi *mdata; - const struct of_device_id *of_id; int i, irq, ret, addr_bits; - master = spi_alloc_master(&pdev->dev, sizeof(*mdata)); - if (!master) { - dev_err(&pdev->dev, "failed to alloc spi master\n"); - return -ENOMEM; - } + master = devm_spi_alloc_master(dev, sizeof(*mdata)); + if (!master) + return dev_err_probe(dev, -ENOMEM, "failed to alloc spi master\n"); master->auto_runtime_pm = true; - master->dev.of_node = pdev->dev.of_node; + master->dev.of_node = dev->of_node; master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_LSB_FIRST; master->set_cs = mtk_spi_set_cs; @@ -812,15 +1132,8 @@ static int mtk_spi_probe(struct platform_device *pdev) master->set_cs_timing = mtk_spi_set_hw_cs_timing; master->use_gpio_descriptors = true; - of_id = of_match_node(mtk_spi_of_match, pdev->dev.of_node); - if (!of_id) { - dev_err(&pdev->dev, "failed to probe of_node\n"); - ret = -EINVAL; - goto err_put_master; - } - mdata = spi_master_get_devdata(master); - mdata->dev_comp = of_id->data; + mdata->dev_comp = device_get_match_data(dev); if (mdata->dev_comp->enhance_timing) master->mode_bits |= SPI_CS_HIGH; @@ -830,143 +1143,122 @@ static int mtk_spi_probe(struct platform_device *pdev) if (mdata->dev_comp->ipm_design) master->mode_bits |= SPI_LOOP; + if (mdata->dev_comp->ipm_design) { + mdata->dev = dev; + master->mem_ops = &mtk_spi_mem_ops; + init_completion(&mdata->spimem_done); + } + if (mdata->dev_comp->need_pad_sel) { - mdata->pad_num = of_property_count_u32_elems( - pdev->dev.of_node, + mdata->pad_num = of_property_count_u32_elems(dev->of_node, "mediatek,pad-select"); - if (mdata->pad_num < 0) { - dev_err(&pdev->dev, + if (mdata->pad_num < 0) + return dev_err_probe(dev, -EINVAL, "No 'mediatek,pad-select' property\n"); - ret = -EINVAL; - goto err_put_master; - } - mdata->pad_sel = devm_kmalloc_array(&pdev->dev, mdata->pad_num, + mdata->pad_sel = devm_kmalloc_array(dev, mdata->pad_num, sizeof(u32), GFP_KERNEL); - if (!mdata->pad_sel) { - ret = -ENOMEM; - goto err_put_master; - } + if (!mdata->pad_sel) + return -ENOMEM; for (i = 0; i < mdata->pad_num; i++) { - of_property_read_u32_index(pdev->dev.of_node, + of_property_read_u32_index(dev->of_node, "mediatek,pad-select", i, &mdata->pad_sel[i]); - if (mdata->pad_sel[i] > MT8173_SPI_MAX_PAD_SEL) { - dev_err(&pdev->dev, "wrong pad-sel[%d]: %u\n", - i, mdata->pad_sel[i]); - ret = -EINVAL; - goto err_put_master; - } + if (mdata->pad_sel[i] > MT8173_SPI_MAX_PAD_SEL) + return dev_err_probe(dev, -EINVAL, + "wrong pad-sel[%d]: %u\n", + i, mdata->pad_sel[i]); } } platform_set_drvdata(pdev, master); mdata->base = devm_platform_ioremap_resource(pdev, 0); - if (IS_ERR(mdata->base)) { - ret = PTR_ERR(mdata->base); - goto err_put_master; - } + if (IS_ERR(mdata->base)) + return PTR_ERR(mdata->base); irq = platform_get_irq(pdev, 0); - if (irq < 0) { - ret = irq; - goto err_put_master; - } + if (irq < 0) + return irq; - if (!pdev->dev.dma_mask) - pdev->dev.dma_mask = &pdev->dev.coherent_dma_mask; + if (!dev->dma_mask) + dev->dma_mask = &dev->coherent_dma_mask; - ret = devm_request_irq(&pdev->dev, irq, mtk_spi_interrupt, - IRQF_TRIGGER_NONE, dev_name(&pdev->dev), master); - if (ret) { - dev_err(&pdev->dev, "failed to register irq (%d)\n", ret); - goto err_put_master; - } + ret = devm_request_irq(dev, irq, mtk_spi_interrupt, + IRQF_TRIGGER_NONE, dev_name(dev), master); + if (ret) + return dev_err_probe(dev, ret, "failed to register irq\n"); - mdata->parent_clk = devm_clk_get(&pdev->dev, "parent-clk"); - if (IS_ERR(mdata->parent_clk)) { - ret = PTR_ERR(mdata->parent_clk); - dev_err(&pdev->dev, "failed to get parent-clk: %d\n", ret); - goto err_put_master; - } + mdata->parent_clk = devm_clk_get(dev, "parent-clk"); + if (IS_ERR(mdata->parent_clk)) + return dev_err_probe(dev, PTR_ERR(mdata->parent_clk), + "failed to get parent-clk\n"); - mdata->sel_clk = devm_clk_get(&pdev->dev, "sel-clk"); - if (IS_ERR(mdata->sel_clk)) { - ret = PTR_ERR(mdata->sel_clk); - dev_err(&pdev->dev, "failed to get sel-clk: %d\n", ret); - goto err_put_master; - } + mdata->sel_clk = devm_clk_get(dev, "sel-clk"); + if (IS_ERR(mdata->sel_clk)) + return dev_err_probe(dev, PTR_ERR(mdata->sel_clk), "failed to get sel-clk\n"); - mdata->spi_clk = devm_clk_get(&pdev->dev, "spi-clk"); - if (IS_ERR(mdata->spi_clk)) { - ret = PTR_ERR(mdata->spi_clk); - dev_err(&pdev->dev, "failed to get spi-clk: %d\n", ret); - goto err_put_master; - } + mdata->spi_clk = devm_clk_get(dev, "spi-clk"); + if (IS_ERR(mdata->spi_clk)) + return dev_err_probe(dev, PTR_ERR(mdata->spi_clk), "failed to get spi-clk\n"); - ret = clk_prepare_enable(mdata->spi_clk); - if (ret < 0) { - dev_err(&pdev->dev, "failed to enable spi_clk (%d)\n", ret); - goto err_put_master; - } + mdata->spi_hclk = devm_clk_get_optional(dev, "hclk"); + if (IS_ERR(mdata->spi_hclk)) + return dev_err_probe(dev, PTR_ERR(mdata->spi_hclk), "failed to get hclk\n"); ret = clk_set_parent(mdata->sel_clk, mdata->parent_clk); + if (ret < 0) + return dev_err_probe(dev, ret, "failed to clk_set_parent\n"); + + ret = clk_prepare_enable(mdata->spi_hclk); + if (ret < 0) + return dev_err_probe(dev, ret, "failed to enable hclk\n"); + + ret = clk_prepare_enable(mdata->spi_clk); if (ret < 0) { - dev_err(&pdev->dev, "failed to clk_set_parent (%d)\n", ret); - clk_disable_unprepare(mdata->spi_clk); - goto err_put_master; + clk_disable_unprepare(mdata->spi_hclk); + return dev_err_probe(dev, ret, "failed to enable spi_clk\n"); } mdata->spi_clk_hz = clk_get_rate(mdata->spi_clk); - if (mdata->dev_comp->no_need_unprepare) + if (mdata->dev_comp->no_need_unprepare) { clk_disable(mdata->spi_clk); - else + clk_disable(mdata->spi_hclk); + } else { clk_disable_unprepare(mdata->spi_clk); - - pm_runtime_enable(&pdev->dev); + clk_disable_unprepare(mdata->spi_hclk); + } if (mdata->dev_comp->need_pad_sel) { - if (mdata->pad_num != master->num_chipselect) { - dev_err(&pdev->dev, + if (mdata->pad_num != master->num_chipselect) + return dev_err_probe(dev, -EINVAL, "pad_num does not match num_chipselect(%d != %d)\n", mdata->pad_num, master->num_chipselect); - ret = -EINVAL; - goto err_disable_runtime_pm; - } - if (!master->cs_gpiods && master->num_chipselect > 1) { - dev_err(&pdev->dev, + if (!master->cs_gpiods && master->num_chipselect > 1) + return dev_err_probe(dev, -EINVAL, "cs_gpios not specified and num_chipselect > 1\n"); - ret = -EINVAL; - goto err_disable_runtime_pm; - } } if (mdata->dev_comp->dma_ext) addr_bits = DMA_ADDR_EXT_BITS; else addr_bits = DMA_ADDR_DEF_BITS; - ret = dma_set_mask(&pdev->dev, DMA_BIT_MASK(addr_bits)); + ret = dma_set_mask(dev, DMA_BIT_MASK(addr_bits)); if (ret) - dev_notice(&pdev->dev, "SPI dma_set_mask(%d) failed, ret:%d\n", + dev_notice(dev, "SPI dma_set_mask(%d) failed, ret:%d\n", addr_bits, ret); - ret = devm_spi_register_master(&pdev->dev, master); + pm_runtime_enable(dev); + + ret = devm_spi_register_master(dev, master); if (ret) { - dev_err(&pdev->dev, "failed to register master (%d)\n", ret); - goto err_disable_runtime_pm; + pm_runtime_disable(dev); + return dev_err_probe(dev, ret, "failed to register master\n"); } return 0; - -err_disable_runtime_pm: - pm_runtime_disable(&pdev->dev); -err_put_master: - spi_master_put(master); - - return ret; } static int mtk_spi_remove(struct platform_device *pdev) @@ -978,8 +1270,10 @@ static int mtk_spi_remove(struct platform_device *pdev) mtk_spi_reset(mdata); - if (mdata->dev_comp->no_need_unprepare) + if (mdata->dev_comp->no_need_unprepare) { clk_unprepare(mdata->spi_clk); + clk_unprepare(mdata->spi_hclk); + } return 0; } @@ -995,8 +1289,10 @@ static int mtk_spi_suspend(struct device *dev) if (ret) return ret; - if (!pm_runtime_suspended(dev)) + if (!pm_runtime_suspended(dev)) { clk_disable_unprepare(mdata->spi_clk); + clk_disable_unprepare(mdata->spi_hclk); + } return ret; } @@ -1013,11 +1309,20 @@ static int mtk_spi_resume(struct device *dev) dev_err(dev, "failed to enable spi_clk (%d)\n", ret); return ret; } + + ret = clk_prepare_enable(mdata->spi_hclk); + if (ret < 0) { + dev_err(dev, "failed to enable spi_hclk (%d)\n", ret); + clk_disable_unprepare(mdata->spi_clk); + return ret; + } } ret = spi_master_resume(master); - if (ret < 0) + if (ret < 0) { clk_disable_unprepare(mdata->spi_clk); + clk_disable_unprepare(mdata->spi_hclk); + } return ret; } @@ -1029,10 +1334,13 @@ static int mtk_spi_runtime_suspend(struct device *dev) struct spi_master *master = dev_get_drvdata(dev); struct mtk_spi *mdata = spi_master_get_devdata(master); - if (mdata->dev_comp->no_need_unprepare) + if (mdata->dev_comp->no_need_unprepare) { clk_disable(mdata->spi_clk); - else + clk_disable(mdata->spi_hclk); + } else { clk_disable_unprepare(mdata->spi_clk); + clk_disable_unprepare(mdata->spi_hclk); + } return 0; } @@ -1043,13 +1351,31 @@ static int mtk_spi_runtime_resume(struct device *dev) struct mtk_spi *mdata = spi_master_get_devdata(master); int ret; - if (mdata->dev_comp->no_need_unprepare) + if (mdata->dev_comp->no_need_unprepare) { ret = clk_enable(mdata->spi_clk); - else + if (ret < 0) { + dev_err(dev, "failed to enable spi_clk (%d)\n", ret); + return ret; + } + ret = clk_enable(mdata->spi_hclk); + if (ret < 0) { + dev_err(dev, "failed to enable spi_hclk (%d)\n", ret); + clk_disable(mdata->spi_clk); + return ret; + } + } else { ret = clk_prepare_enable(mdata->spi_clk); - if (ret < 0) { - dev_err(dev, "failed to enable spi_clk (%d)\n", ret); - return ret; + if (ret < 0) { + dev_err(dev, "failed to prepare_enable spi_clk (%d)\n", ret); + return ret; + } + + ret = clk_prepare_enable(mdata->spi_hclk); + if (ret < 0) { + dev_err(dev, "failed to prepare_enable spi_hclk (%d)\n", ret); + clk_disable_unprepare(mdata->spi_clk); + return ret; + } } return 0; diff --git a/drivers/spi/spi-mtk-nor.c b/drivers/spi/spi-mtk-nor.c index 94fb09696677..d167699a1a96 100644 --- a/drivers/spi/spi-mtk-nor.c +++ b/drivers/spi/spi-mtk-nor.c @@ -960,7 +960,17 @@ static int __maybe_unused mtk_nor_suspend(struct device *dev) static int __maybe_unused mtk_nor_resume(struct device *dev) { - return pm_runtime_force_resume(dev); + struct spi_controller *ctlr = dev_get_drvdata(dev); + struct mtk_nor *sp = spi_controller_get_devdata(ctlr); + int ret; + + ret = pm_runtime_force_resume(dev); + if (ret) + return ret; + + mtk_nor_init(sp); + + return 0; } static const struct dev_pm_ops mtk_nor_pm_ops = { diff --git a/drivers/spi/spi-mtk-snfi.c b/drivers/spi/spi-mtk-snfi.c new file mode 100644 index 000000000000..d66bf9762557 --- /dev/null +++ b/drivers/spi/spi-mtk-snfi.c @@ -0,0 +1,1472 @@ +// SPDX-License-Identifier: GPL-2.0 +// +// Driver for the SPI-NAND mode of Mediatek NAND Flash Interface +// +// Copyright (c) 2022 Chuanhong Guo <gch981213@gmail.com> +// +// This driver is based on the SPI-NAND mtd driver from Mediatek SDK: +// +// Copyright (C) 2020 MediaTek Inc. +// Author: Weijie Gao <weijie.gao@mediatek.com> +// +// This controller organize the page data as several interleaved sectors +// like the following: (sizeof(FDM + ECC) = snf->nfi_cfg.spare_size) +// +---------+------+------+---------+------+------+-----+ +// | Sector1 | FDM1 | ECC1 | Sector2 | FDM2 | ECC2 | ... | +// +---------+------+------+---------+------+------+-----+ +// With auto-format turned on, DMA only returns this part: +// +---------+---------+-----+ +// | Sector1 | Sector2 | ... | +// +---------+---------+-----+ +// The FDM data will be filled to the registers, and ECC parity data isn't +// accessible. +// With auto-format off, all ((Sector+FDM+ECC)*nsectors) will be read over DMA +// in it's original order shown in the first table. ECC can't be turned on when +// auto-format is off. +// +// However, Linux SPI-NAND driver expects the data returned as: +// +------+-----+ +// | Page | OOB | +// +------+-----+ +// where the page data is continuously stored instead of interleaved. +// So we assume all instructions matching the page_op template between ECC +// prepare_io_req and finish_io_req are for page cache r/w. +// Here's how this spi-mem driver operates when reading: +// 1. Always set snf->autofmt = true in prepare_io_req (even when ECC is off). +// 2. Perform page ops and let the controller fill the DMA bounce buffer with +// de-interleaved sector data and set FDM registers. +// 3. Return the data as: +// +---------+---------+-----+------+------+-----+ +// | Sector1 | Sector2 | ... | FDM1 | FDM2 | ... | +// +---------+---------+-----+------+------+-----+ +// 4. For other matching spi_mem ops outside a prepare/finish_io_req pair, +// read the data with auto-format off into the bounce buffer and copy +// needed data to the buffer specified in the request. +// +// Write requests operates in a similar manner. +// As a limitation of this strategy, we won't be able to access any ECC parity +// data at all in Linux. +// +// Here's the bad block mark situation on MTK chips: +// In older chips like mt7622, MTK uses the first FDM byte in the first sector +// as the bad block mark. After de-interleaving, this byte appears at [pagesize] +// in the returned data, which is the BBM position expected by kernel. However, +// the conventional bad block mark is the first byte of the OOB, which is part +// of the last sector data in the interleaved layout. Instead of fixing their +// hardware, MTK decided to address this inconsistency in software. On these +// later chips, the BootROM expects the following: +// 1. The [pagesize] byte on a nand page is used as BBM, which will appear at +// (page_size - (nsectors - 1) * spare_size) in the DMA buffer. +// 2. The original byte stored at that position in the DMA buffer will be stored +// as the first byte of the FDM section in the last sector. +// We can't disagree with the BootROM, so after de-interleaving, we need to +// perform the following swaps in read: +// 1. Store the BBM at [page_size - (nsectors - 1) * spare_size] to [page_size], +// which is the expected BBM position by kernel. +// 2. Store the page data byte at [pagesize + (nsectors-1) * fdm] back to +// [page_size - (nsectors - 1) * spare_size] +// Similarly, when writing, we need to perform swaps in the other direction. + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/init.h> +#include <linux/device.h> +#include <linux/mutex.h> +#include <linux/clk.h> +#include <linux/interrupt.h> +#include <linux/dma-mapping.h> +#include <linux/iopoll.h> +#include <linux/of_platform.h> +#include <linux/mtd/nand-ecc-mtk.h> +#include <linux/spi/spi.h> +#include <linux/spi/spi-mem.h> +#include <linux/mtd/nand.h> + +// NFI registers +#define NFI_CNFG 0x000 +#define CNFG_OP_MODE_S 12 +#define CNFG_OP_MODE_CUST 6 +#define CNFG_OP_MODE_PROGRAM 3 +#define CNFG_AUTO_FMT_EN BIT(9) +#define CNFG_HW_ECC_EN BIT(8) +#define CNFG_DMA_BURST_EN BIT(2) +#define CNFG_READ_MODE BIT(1) +#define CNFG_DMA_MODE BIT(0) + +#define NFI_PAGEFMT 0x0004 +#define NFI_SPARE_SIZE_LS_S 16 +#define NFI_FDM_ECC_NUM_S 12 +#define NFI_FDM_NUM_S 8 +#define NFI_SPARE_SIZE_S 4 +#define NFI_SEC_SEL_512 BIT(2) +#define NFI_PAGE_SIZE_S 0 +#define NFI_PAGE_SIZE_512_2K 0 +#define NFI_PAGE_SIZE_2K_4K 1 +#define NFI_PAGE_SIZE_4K_8K 2 +#define NFI_PAGE_SIZE_8K_16K 3 + +#define NFI_CON 0x008 +#define CON_SEC_NUM_S 12 +#define CON_BWR BIT(9) +#define CON_BRD BIT(8) +#define CON_NFI_RST BIT(1) +#define CON_FIFO_FLUSH BIT(0) + +#define NFI_INTR_EN 0x010 +#define NFI_INTR_STA 0x014 +#define NFI_IRQ_INTR_EN BIT(31) +#define NFI_IRQ_CUS_READ BIT(8) +#define NFI_IRQ_CUS_PG BIT(7) + +#define NFI_CMD 0x020 +#define NFI_CMD_DUMMY_READ 0x00 +#define NFI_CMD_DUMMY_WRITE 0x80 + +#define NFI_STRDATA 0x040 +#define STR_DATA BIT(0) + +#define NFI_STA 0x060 +#define NFI_NAND_FSM GENMASK(28, 24) +#define NFI_FSM GENMASK(19, 16) +#define READ_EMPTY BIT(12) + +#define NFI_FIFOSTA 0x064 +#define FIFO_WR_REMAIN_S 8 +#define FIFO_RD_REMAIN_S 0 + +#define NFI_ADDRCNTR 0x070 +#define SEC_CNTR GENMASK(16, 12) +#define SEC_CNTR_S 12 +#define NFI_SEC_CNTR(val) (((val)&SEC_CNTR) >> SEC_CNTR_S) + +#define NFI_STRADDR 0x080 + +#define NFI_BYTELEN 0x084 +#define BUS_SEC_CNTR(val) (((val)&SEC_CNTR) >> SEC_CNTR_S) + +#define NFI_FDM0L 0x0a0 +#define NFI_FDM0M 0x0a4 +#define NFI_FDML(n) (NFI_FDM0L + (n)*8) +#define NFI_FDMM(n) (NFI_FDM0M + (n)*8) + +#define NFI_DEBUG_CON1 0x220 +#define WBUF_EN BIT(2) + +#define NFI_MASTERSTA 0x224 +#define MAS_ADDR GENMASK(11, 9) +#define MAS_RD GENMASK(8, 6) +#define MAS_WR GENMASK(5, 3) +#define MAS_RDDLY GENMASK(2, 0) +#define NFI_MASTERSTA_MASK_7622 (MAS_ADDR | MAS_RD | MAS_WR | MAS_RDDLY) + +// SNFI registers +#define SNF_MAC_CTL 0x500 +#define MAC_XIO_SEL BIT(4) +#define SF_MAC_EN BIT(3) +#define SF_TRIG BIT(2) +#define WIP_READY BIT(1) +#define WIP BIT(0) + +#define SNF_MAC_OUTL 0x504 +#define SNF_MAC_INL 0x508 + +#define SNF_RD_CTL2 0x510 +#define DATA_READ_DUMMY_S 8 +#define DATA_READ_MAX_DUMMY 0xf +#define DATA_READ_CMD_S 0 + +#define SNF_RD_CTL3 0x514 + +#define SNF_PG_CTL1 0x524 +#define PG_LOAD_CMD_S 8 + +#define SNF_PG_CTL2 0x528 + +#define SNF_MISC_CTL 0x538 +#define SW_RST BIT(28) +#define FIFO_RD_LTC_S 25 +#define PG_LOAD_X4_EN BIT(20) +#define DATA_READ_MODE_S 16 +#define DATA_READ_MODE GENMASK(18, 16) +#define DATA_READ_MODE_X1 0 +#define DATA_READ_MODE_X2 1 +#define DATA_READ_MODE_X4 2 +#define DATA_READ_MODE_DUAL 5 +#define DATA_READ_MODE_QUAD 6 +#define PG_LOAD_CUSTOM_EN BIT(7) +#define DATARD_CUSTOM_EN BIT(6) +#define CS_DESELECT_CYC_S 0 + +#define SNF_MISC_CTL2 0x53c +#define PROGRAM_LOAD_BYTE_NUM_S 16 +#define READ_DATA_BYTE_NUM_S 11 + +#define SNF_DLY_CTL3 0x548 +#define SFCK_SAM_DLY_S 0 + +#define SNF_STA_CTL1 0x550 +#define CUS_PG_DONE BIT(28) +#define CUS_READ_DONE BIT(27) +#define SPI_STATE_S 0 +#define SPI_STATE GENMASK(3, 0) + +#define SNF_CFG 0x55c +#define SPI_MODE BIT(0) + +#define SNF_GPRAM 0x800 +#define SNF_GPRAM_SIZE 0xa0 + +#define SNFI_POLL_INTERVAL 1000000 + +static const u8 mt7622_spare_sizes[] = { 16, 26, 27, 28 }; + +struct mtk_snand_caps { + u16 sector_size; + u16 max_sectors; + u16 fdm_size; + u16 fdm_ecc_size; + u16 fifo_size; + + bool bbm_swap; + bool empty_page_check; + u32 mastersta_mask; + + const u8 *spare_sizes; + u32 num_spare_size; +}; + +static const struct mtk_snand_caps mt7622_snand_caps = { + .sector_size = 512, + .max_sectors = 8, + .fdm_size = 8, + .fdm_ecc_size = 1, + .fifo_size = 32, + .bbm_swap = false, + .empty_page_check = false, + .mastersta_mask = NFI_MASTERSTA_MASK_7622, + .spare_sizes = mt7622_spare_sizes, + .num_spare_size = ARRAY_SIZE(mt7622_spare_sizes) +}; + +static const struct mtk_snand_caps mt7629_snand_caps = { + .sector_size = 512, + .max_sectors = 8, + .fdm_size = 8, + .fdm_ecc_size = 1, + .fifo_size = 32, + .bbm_swap = true, + .empty_page_check = false, + .mastersta_mask = NFI_MASTERSTA_MASK_7622, + .spare_sizes = mt7622_spare_sizes, + .num_spare_size = ARRAY_SIZE(mt7622_spare_sizes) +}; + +struct mtk_snand_conf { + size_t page_size; + size_t oob_size; + u8 nsectors; + u8 spare_size; +}; + +struct mtk_snand { + struct spi_controller *ctlr; + struct device *dev; + struct clk *nfi_clk; + struct clk *pad_clk; + void __iomem *nfi_base; + int irq; + struct completion op_done; + const struct mtk_snand_caps *caps; + struct mtk_ecc_config *ecc_cfg; + struct mtk_ecc *ecc; + struct mtk_snand_conf nfi_cfg; + struct mtk_ecc_stats ecc_stats; + struct nand_ecc_engine ecc_eng; + bool autofmt; + u8 *buf; + size_t buf_len; +}; + +static struct mtk_snand *nand_to_mtk_snand(struct nand_device *nand) +{ + struct nand_ecc_engine *eng = nand->ecc.engine; + + return container_of(eng, struct mtk_snand, ecc_eng); +} + +static inline int snand_prepare_bouncebuf(struct mtk_snand *snf, size_t size) +{ + if (snf->buf_len >= size) + return 0; + kfree(snf->buf); + snf->buf = kmalloc(size, GFP_KERNEL); + if (!snf->buf) + return -ENOMEM; + snf->buf_len = size; + memset(snf->buf, 0xff, snf->buf_len); + return 0; +} + +static inline u32 nfi_read32(struct mtk_snand *snf, u32 reg) +{ + return readl(snf->nfi_base + reg); +} + +static inline void nfi_write32(struct mtk_snand *snf, u32 reg, u32 val) +{ + writel(val, snf->nfi_base + reg); +} + +static inline void nfi_write16(struct mtk_snand *snf, u32 reg, u16 val) +{ + writew(val, snf->nfi_base + reg); +} + +static inline void nfi_rmw32(struct mtk_snand *snf, u32 reg, u32 clr, u32 set) +{ + u32 val; + + val = readl(snf->nfi_base + reg); + val &= ~clr; + val |= set; + writel(val, snf->nfi_base + reg); +} + +static void nfi_read_data(struct mtk_snand *snf, u32 reg, u8 *data, u32 len) +{ + u32 i, val = 0, es = sizeof(u32); + + for (i = reg; i < reg + len; i++) { + if (i == reg || i % es == 0) + val = nfi_read32(snf, i & ~(es - 1)); + + *data++ = (u8)(val >> (8 * (i % es))); + } +} + +static int mtk_nfi_reset(struct mtk_snand *snf) +{ + u32 val, fifo_mask; + int ret; + + nfi_write32(snf, NFI_CON, CON_FIFO_FLUSH | CON_NFI_RST); + + ret = readw_poll_timeout(snf->nfi_base + NFI_MASTERSTA, val, + !(val & snf->caps->mastersta_mask), 0, + SNFI_POLL_INTERVAL); + if (ret) { + dev_err(snf->dev, "NFI master is still busy after reset\n"); + return ret; + } + + ret = readl_poll_timeout(snf->nfi_base + NFI_STA, val, + !(val & (NFI_FSM | NFI_NAND_FSM)), 0, + SNFI_POLL_INTERVAL); + if (ret) { + dev_err(snf->dev, "Failed to reset NFI\n"); + return ret; + } + + fifo_mask = ((snf->caps->fifo_size - 1) << FIFO_RD_REMAIN_S) | + ((snf->caps->fifo_size - 1) << FIFO_WR_REMAIN_S); + ret = readw_poll_timeout(snf->nfi_base + NFI_FIFOSTA, val, + !(val & fifo_mask), 0, SNFI_POLL_INTERVAL); + if (ret) { + dev_err(snf->dev, "NFI FIFOs are not empty\n"); + return ret; + } + + return 0; +} + +static int mtk_snand_mac_reset(struct mtk_snand *snf) +{ + int ret; + u32 val; + + nfi_rmw32(snf, SNF_MISC_CTL, 0, SW_RST); + + ret = readl_poll_timeout(snf->nfi_base + SNF_STA_CTL1, val, + !(val & SPI_STATE), 0, SNFI_POLL_INTERVAL); + if (ret) + dev_err(snf->dev, "Failed to reset SNFI MAC\n"); + + nfi_write32(snf, SNF_MISC_CTL, + (2 << FIFO_RD_LTC_S) | (10 << CS_DESELECT_CYC_S)); + + return ret; +} + +static int mtk_snand_mac_trigger(struct mtk_snand *snf, u32 outlen, u32 inlen) +{ + int ret; + u32 val; + + nfi_write32(snf, SNF_MAC_CTL, SF_MAC_EN); + nfi_write32(snf, SNF_MAC_OUTL, outlen); + nfi_write32(snf, SNF_MAC_INL, inlen); + + nfi_write32(snf, SNF_MAC_CTL, SF_MAC_EN | SF_TRIG); + + ret = readl_poll_timeout(snf->nfi_base + SNF_MAC_CTL, val, + val & WIP_READY, 0, SNFI_POLL_INTERVAL); + if (ret) { + dev_err(snf->dev, "Timed out waiting for WIP_READY\n"); + goto cleanup; + } + + ret = readl_poll_timeout(snf->nfi_base + SNF_MAC_CTL, val, !(val & WIP), + 0, SNFI_POLL_INTERVAL); + if (ret) + dev_err(snf->dev, "Timed out waiting for WIP cleared\n"); + +cleanup: + nfi_write32(snf, SNF_MAC_CTL, 0); + + return ret; +} + +static int mtk_snand_mac_io(struct mtk_snand *snf, const struct spi_mem_op *op) +{ + u32 rx_len = 0; + u32 reg_offs = 0; + u32 val = 0; + const u8 *tx_buf = NULL; + u8 *rx_buf = NULL; + int i, ret; + u8 b; + + if (op->data.dir == SPI_MEM_DATA_IN) { + rx_len = op->data.nbytes; + rx_buf = op->data.buf.in; + } else { + tx_buf = op->data.buf.out; + } + + mtk_snand_mac_reset(snf); + + for (i = 0; i < op->cmd.nbytes; i++, reg_offs++) { + b = (op->cmd.opcode >> ((op->cmd.nbytes - i - 1) * 8)) & 0xff; + val |= b << (8 * (reg_offs % 4)); + if (reg_offs % 4 == 3) { + nfi_write32(snf, SNF_GPRAM + reg_offs - 3, val); + val = 0; + } + } + + for (i = 0; i < op->addr.nbytes; i++, reg_offs++) { + b = (op->addr.val >> ((op->addr.nbytes - i - 1) * 8)) & 0xff; + val |= b << (8 * (reg_offs % 4)); + if (reg_offs % 4 == 3) { + nfi_write32(snf, SNF_GPRAM + reg_offs - 3, val); + val = 0; + } + } + + for (i = 0; i < op->dummy.nbytes; i++, reg_offs++) { + if (reg_offs % 4 == 3) { + nfi_write32(snf, SNF_GPRAM + reg_offs - 3, val); + val = 0; + } + } + + if (op->data.dir == SPI_MEM_DATA_OUT) { + for (i = 0; i < op->data.nbytes; i++, reg_offs++) { + val |= tx_buf[i] << (8 * (reg_offs % 4)); + if (reg_offs % 4 == 3) { + nfi_write32(snf, SNF_GPRAM + reg_offs - 3, val); + val = 0; + } + } + } + + if (reg_offs % 4) + nfi_write32(snf, SNF_GPRAM + (reg_offs & ~3), val); + + for (i = 0; i < reg_offs; i += 4) + dev_dbg(snf->dev, "%d: %08X", i, + nfi_read32(snf, SNF_GPRAM + i)); + + dev_dbg(snf->dev, "SNF TX: %u RX: %u", reg_offs, rx_len); + + ret = mtk_snand_mac_trigger(snf, reg_offs, rx_len); + if (ret) + return ret; + + if (!rx_len) + return 0; + + nfi_read_data(snf, SNF_GPRAM + reg_offs, rx_buf, rx_len); + return 0; +} + +static int mtk_snand_setup_pagefmt(struct mtk_snand *snf, u32 page_size, + u32 oob_size) +{ + int spare_idx = -1; + u32 spare_size, spare_size_shift, pagesize_idx; + u32 sector_size_512; + u8 nsectors; + int i; + + // skip if it's already configured as required. + if (snf->nfi_cfg.page_size == page_size && + snf->nfi_cfg.oob_size == oob_size) + return 0; + + nsectors = page_size / snf->caps->sector_size; + if (nsectors > snf->caps->max_sectors) { + dev_err(snf->dev, "too many sectors required.\n"); + goto err; + } + + if (snf->caps->sector_size == 512) { + sector_size_512 = NFI_SEC_SEL_512; + spare_size_shift = NFI_SPARE_SIZE_S; + } else { + sector_size_512 = 0; + spare_size_shift = NFI_SPARE_SIZE_LS_S; + } + + switch (page_size) { + case SZ_512: + pagesize_idx = NFI_PAGE_SIZE_512_2K; + break; + case SZ_2K: + if (snf->caps->sector_size == 512) + pagesize_idx = NFI_PAGE_SIZE_2K_4K; + else + pagesize_idx = NFI_PAGE_SIZE_512_2K; + break; + case SZ_4K: + if (snf->caps->sector_size == 512) + pagesize_idx = NFI_PAGE_SIZE_4K_8K; + else + pagesize_idx = NFI_PAGE_SIZE_2K_4K; + break; + case SZ_8K: + if (snf->caps->sector_size == 512) + pagesize_idx = NFI_PAGE_SIZE_8K_16K; + else + pagesize_idx = NFI_PAGE_SIZE_4K_8K; + break; + case SZ_16K: + pagesize_idx = NFI_PAGE_SIZE_8K_16K; + break; + default: + dev_err(snf->dev, "unsupported page size.\n"); + goto err; + } + + spare_size = oob_size / nsectors; + // If we're using the 1KB sector size, HW will automatically double the + // spare size. We should only use half of the value in this case. + if (snf->caps->sector_size == 1024) + spare_size /= 2; + + for (i = snf->caps->num_spare_size - 1; i >= 0; i--) { + if (snf->caps->spare_sizes[i] <= spare_size) { + spare_size = snf->caps->spare_sizes[i]; + if (snf->caps->sector_size == 1024) + spare_size *= 2; + spare_idx = i; + break; + } + } + + if (spare_idx < 0) { + dev_err(snf->dev, "unsupported spare size: %u\n", spare_size); + goto err; + } + + nfi_write32(snf, NFI_PAGEFMT, + (snf->caps->fdm_ecc_size << NFI_FDM_ECC_NUM_S) | + (snf->caps->fdm_size << NFI_FDM_NUM_S) | + (spare_idx << spare_size_shift) | + (pagesize_idx << NFI_PAGE_SIZE_S) | + sector_size_512); + + snf->nfi_cfg.page_size = page_size; + snf->nfi_cfg.oob_size = oob_size; + snf->nfi_cfg.nsectors = nsectors; + snf->nfi_cfg.spare_size = spare_size; + + dev_dbg(snf->dev, "page format: (%u + %u) * %u\n", + snf->caps->sector_size, spare_size, nsectors); + return snand_prepare_bouncebuf(snf, page_size + oob_size); +err: + dev_err(snf->dev, "page size %u + %u is not supported\n", page_size, + oob_size); + return -EOPNOTSUPP; +} + +static int mtk_snand_ooblayout_ecc(struct mtd_info *mtd, int section, + struct mtd_oob_region *oobecc) +{ + // ECC area is not accessible + return -ERANGE; +} + +static int mtk_snand_ooblayout_free(struct mtd_info *mtd, int section, + struct mtd_oob_region *oobfree) +{ + struct nand_device *nand = mtd_to_nanddev(mtd); + struct mtk_snand *ms = nand_to_mtk_snand(nand); + + if (section >= ms->nfi_cfg.nsectors) + return -ERANGE; + + oobfree->length = ms->caps->fdm_size - 1; + oobfree->offset = section * ms->caps->fdm_size + 1; + return 0; +} + +static const struct mtd_ooblayout_ops mtk_snand_ooblayout = { + .ecc = mtk_snand_ooblayout_ecc, + .free = mtk_snand_ooblayout_free, +}; + +static int mtk_snand_ecc_init_ctx(struct nand_device *nand) +{ + struct mtk_snand *snf = nand_to_mtk_snand(nand); + struct nand_ecc_props *conf = &nand->ecc.ctx.conf; + struct nand_ecc_props *reqs = &nand->ecc.requirements; + struct nand_ecc_props *user = &nand->ecc.user_conf; + struct mtd_info *mtd = nanddev_to_mtd(nand); + int step_size = 0, strength = 0, desired_correction = 0, steps; + bool ecc_user = false; + int ret; + u32 parity_bits, max_ecc_bytes; + struct mtk_ecc_config *ecc_cfg; + + ret = mtk_snand_setup_pagefmt(snf, nand->memorg.pagesize, + nand->memorg.oobsize); + if (ret) + return ret; + + ecc_cfg = kzalloc(sizeof(*ecc_cfg), GFP_KERNEL); + if (!ecc_cfg) + return -ENOMEM; + + nand->ecc.ctx.priv = ecc_cfg; + + if (user->step_size && user->strength) { + step_size = user->step_size; + strength = user->strength; + ecc_user = true; + } else if (reqs->step_size && reqs->strength) { + step_size = reqs->step_size; + strength = reqs->strength; + } + + if (step_size && strength) { + steps = mtd->writesize / step_size; + desired_correction = steps * strength; + strength = desired_correction / snf->nfi_cfg.nsectors; + } + + ecc_cfg->mode = ECC_NFI_MODE; + ecc_cfg->sectors = snf->nfi_cfg.nsectors; + ecc_cfg->len = snf->caps->sector_size + snf->caps->fdm_ecc_size; + + // calculate the max possible strength under current page format + parity_bits = mtk_ecc_get_parity_bits(snf->ecc); + max_ecc_bytes = snf->nfi_cfg.spare_size - snf->caps->fdm_size; + ecc_cfg->strength = max_ecc_bytes * 8 / parity_bits; + mtk_ecc_adjust_strength(snf->ecc, &ecc_cfg->strength); + + // if there's a user requested strength, find the minimum strength that + // meets the requirement. Otherwise use the maximum strength which is + // expected by BootROM. + if (ecc_user && strength) { + u32 s_next = ecc_cfg->strength - 1; + + while (1) { + mtk_ecc_adjust_strength(snf->ecc, &s_next); + if (s_next >= ecc_cfg->strength) + break; + if (s_next < strength) + break; + s_next = ecc_cfg->strength - 1; + } + } + + mtd_set_ooblayout(mtd, &mtk_snand_ooblayout); + + conf->step_size = snf->caps->sector_size; + conf->strength = ecc_cfg->strength; + + if (ecc_cfg->strength < strength) + dev_warn(snf->dev, "unable to fulfill ECC of %u bits.\n", + strength); + dev_info(snf->dev, "ECC strength: %u bits per %u bytes\n", + ecc_cfg->strength, snf->caps->sector_size); + + return 0; +} + +static void mtk_snand_ecc_cleanup_ctx(struct nand_device *nand) +{ + struct mtk_ecc_config *ecc_cfg = nand_to_ecc_ctx(nand); + + kfree(ecc_cfg); +} + +static int mtk_snand_ecc_prepare_io_req(struct nand_device *nand, + struct nand_page_io_req *req) +{ + struct mtk_snand *snf = nand_to_mtk_snand(nand); + struct mtk_ecc_config *ecc_cfg = nand_to_ecc_ctx(nand); + int ret; + + ret = mtk_snand_setup_pagefmt(snf, nand->memorg.pagesize, + nand->memorg.oobsize); + if (ret) + return ret; + snf->autofmt = true; + snf->ecc_cfg = ecc_cfg; + return 0; +} + +static int mtk_snand_ecc_finish_io_req(struct nand_device *nand, + struct nand_page_io_req *req) +{ + struct mtk_snand *snf = nand_to_mtk_snand(nand); + struct mtd_info *mtd = nanddev_to_mtd(nand); + + snf->ecc_cfg = NULL; + snf->autofmt = false; + if ((req->mode == MTD_OPS_RAW) || (req->type != NAND_PAGE_READ)) + return 0; + + if (snf->ecc_stats.failed) + mtd->ecc_stats.failed += snf->ecc_stats.failed; + mtd->ecc_stats.corrected += snf->ecc_stats.corrected; + return snf->ecc_stats.failed ? -EBADMSG : snf->ecc_stats.bitflips; +} + +static struct nand_ecc_engine_ops mtk_snfi_ecc_engine_ops = { + .init_ctx = mtk_snand_ecc_init_ctx, + .cleanup_ctx = mtk_snand_ecc_cleanup_ctx, + .prepare_io_req = mtk_snand_ecc_prepare_io_req, + .finish_io_req = mtk_snand_ecc_finish_io_req, +}; + +static void mtk_snand_read_fdm(struct mtk_snand *snf, u8 *buf) +{ + u32 vall, valm; + u8 *oobptr = buf; + int i, j; + + for (i = 0; i < snf->nfi_cfg.nsectors; i++) { + vall = nfi_read32(snf, NFI_FDML(i)); + valm = nfi_read32(snf, NFI_FDMM(i)); + + for (j = 0; j < snf->caps->fdm_size; j++) + oobptr[j] = (j >= 4 ? valm : vall) >> ((j % 4) * 8); + + oobptr += snf->caps->fdm_size; + } +} + +static void mtk_snand_write_fdm(struct mtk_snand *snf, const u8 *buf) +{ + u32 fdm_size = snf->caps->fdm_size; + const u8 *oobptr = buf; + u32 vall, valm; + int i, j; + + for (i = 0; i < snf->nfi_cfg.nsectors; i++) { + vall = 0; + valm = 0; + + for (j = 0; j < 8; j++) { + if (j < 4) + vall |= (j < fdm_size ? oobptr[j] : 0xff) + << (j * 8); + else + valm |= (j < fdm_size ? oobptr[j] : 0xff) + << ((j - 4) * 8); + } + + nfi_write32(snf, NFI_FDML(i), vall); + nfi_write32(snf, NFI_FDMM(i), valm); + + oobptr += fdm_size; + } +} + +static void mtk_snand_bm_swap(struct mtk_snand *snf, u8 *buf) +{ + u32 buf_bbm_pos, fdm_bbm_pos; + + if (!snf->caps->bbm_swap || snf->nfi_cfg.nsectors == 1) + return; + + // swap [pagesize] byte on nand with the first fdm byte + // in the last sector. + buf_bbm_pos = snf->nfi_cfg.page_size - + (snf->nfi_cfg.nsectors - 1) * snf->nfi_cfg.spare_size; + fdm_bbm_pos = snf->nfi_cfg.page_size + + (snf->nfi_cfg.nsectors - 1) * snf->caps->fdm_size; + + swap(snf->buf[fdm_bbm_pos], buf[buf_bbm_pos]); +} + +static void mtk_snand_fdm_bm_swap(struct mtk_snand *snf) +{ + u32 fdm_bbm_pos1, fdm_bbm_pos2; + + if (!snf->caps->bbm_swap || snf->nfi_cfg.nsectors == 1) + return; + + // swap the first fdm byte in the first and the last sector. + fdm_bbm_pos1 = snf->nfi_cfg.page_size; + fdm_bbm_pos2 = snf->nfi_cfg.page_size + + (snf->nfi_cfg.nsectors - 1) * snf->caps->fdm_size; + swap(snf->buf[fdm_bbm_pos1], snf->buf[fdm_bbm_pos2]); +} + +static int mtk_snand_read_page_cache(struct mtk_snand *snf, + const struct spi_mem_op *op) +{ + u8 *buf = snf->buf; + u8 *buf_fdm = buf + snf->nfi_cfg.page_size; + // the address part to be sent by the controller + u32 op_addr = op->addr.val; + // where to start copying data from bounce buffer + u32 rd_offset = 0; + u32 dummy_clk = (op->dummy.nbytes * BITS_PER_BYTE / op->dummy.buswidth); + u32 op_mode = 0; + u32 dma_len = snf->buf_len; + int ret = 0; + u32 rd_mode, rd_bytes, val; + dma_addr_t buf_dma; + + if (snf->autofmt) { + u32 last_bit; + u32 mask; + + dma_len = snf->nfi_cfg.page_size; + op_mode = CNFG_AUTO_FMT_EN; + if (op->data.ecc) + op_mode |= CNFG_HW_ECC_EN; + // extract the plane bit: + // Find the highest bit set in (pagesize+oobsize). + // Bits higher than that in op->addr are kept and sent over SPI + // Lower bits are used as an offset for copying data from DMA + // bounce buffer. + last_bit = fls(snf->nfi_cfg.page_size + snf->nfi_cfg.oob_size); + mask = (1 << last_bit) - 1; + rd_offset = op_addr & mask; + op_addr &= ~mask; + + // check if we can dma to the caller memory + if (rd_offset == 0 && op->data.nbytes >= snf->nfi_cfg.page_size) + buf = op->data.buf.in; + } + mtk_snand_mac_reset(snf); + mtk_nfi_reset(snf); + + // command and dummy cycles + nfi_write32(snf, SNF_RD_CTL2, + (dummy_clk << DATA_READ_DUMMY_S) | + (op->cmd.opcode << DATA_READ_CMD_S)); + + // read address + nfi_write32(snf, SNF_RD_CTL3, op_addr); + + // Set read op_mode + if (op->data.buswidth == 4) + rd_mode = op->addr.buswidth == 4 ? DATA_READ_MODE_QUAD : + DATA_READ_MODE_X4; + else if (op->data.buswidth == 2) + rd_mode = op->addr.buswidth == 2 ? DATA_READ_MODE_DUAL : + DATA_READ_MODE_X2; + else + rd_mode = DATA_READ_MODE_X1; + rd_mode <<= DATA_READ_MODE_S; + nfi_rmw32(snf, SNF_MISC_CTL, DATA_READ_MODE, + rd_mode | DATARD_CUSTOM_EN); + + // Set bytes to read + rd_bytes = (snf->nfi_cfg.spare_size + snf->caps->sector_size) * + snf->nfi_cfg.nsectors; + nfi_write32(snf, SNF_MISC_CTL2, + (rd_bytes << PROGRAM_LOAD_BYTE_NUM_S) | rd_bytes); + + // NFI read prepare + nfi_write16(snf, NFI_CNFG, + (CNFG_OP_MODE_CUST << CNFG_OP_MODE_S) | CNFG_DMA_BURST_EN | + CNFG_READ_MODE | CNFG_DMA_MODE | op_mode); + + nfi_write32(snf, NFI_CON, (snf->nfi_cfg.nsectors << CON_SEC_NUM_S)); + + buf_dma = dma_map_single(snf->dev, buf, dma_len, DMA_FROM_DEVICE); + ret = dma_mapping_error(snf->dev, buf_dma); + if (ret) { + dev_err(snf->dev, "DMA mapping failed.\n"); + goto cleanup; + } + nfi_write32(snf, NFI_STRADDR, buf_dma); + if (op->data.ecc) { + snf->ecc_cfg->op = ECC_DECODE; + ret = mtk_ecc_enable(snf->ecc, snf->ecc_cfg); + if (ret) + goto cleanup_dma; + } + // Prepare for custom read interrupt + nfi_write32(snf, NFI_INTR_EN, NFI_IRQ_INTR_EN | NFI_IRQ_CUS_READ); + reinit_completion(&snf->op_done); + + // Trigger NFI into custom mode + nfi_write16(snf, NFI_CMD, NFI_CMD_DUMMY_READ); + + // Start DMA read + nfi_rmw32(snf, NFI_CON, 0, CON_BRD); + nfi_write16(snf, NFI_STRDATA, STR_DATA); + + if (!wait_for_completion_timeout( + &snf->op_done, usecs_to_jiffies(SNFI_POLL_INTERVAL))) { + dev_err(snf->dev, "DMA timed out for reading from cache.\n"); + ret = -ETIMEDOUT; + goto cleanup; + } + + // Wait for BUS_SEC_CNTR returning expected value + ret = readl_poll_timeout(snf->nfi_base + NFI_BYTELEN, val, + BUS_SEC_CNTR(val) >= snf->nfi_cfg.nsectors, 0, + SNFI_POLL_INTERVAL); + if (ret) { + dev_err(snf->dev, "Timed out waiting for BUS_SEC_CNTR\n"); + goto cleanup2; + } + + // Wait for bus becoming idle + ret = readl_poll_timeout(snf->nfi_base + NFI_MASTERSTA, val, + !(val & snf->caps->mastersta_mask), 0, + SNFI_POLL_INTERVAL); + if (ret) { + dev_err(snf->dev, "Timed out waiting for bus becoming idle\n"); + goto cleanup2; + } + + if (op->data.ecc) { + ret = mtk_ecc_wait_done(snf->ecc, ECC_DECODE); + if (ret) { + dev_err(snf->dev, "wait ecc done timeout\n"); + goto cleanup2; + } + // save status before disabling ecc + mtk_ecc_get_stats(snf->ecc, &snf->ecc_stats, + snf->nfi_cfg.nsectors); + } + + dma_unmap_single(snf->dev, buf_dma, dma_len, DMA_FROM_DEVICE); + + if (snf->autofmt) { + mtk_snand_read_fdm(snf, buf_fdm); + if (snf->caps->bbm_swap) { + mtk_snand_bm_swap(snf, buf); + mtk_snand_fdm_bm_swap(snf); + } + } + + // copy data back + if (nfi_read32(snf, NFI_STA) & READ_EMPTY) { + memset(op->data.buf.in, 0xff, op->data.nbytes); + snf->ecc_stats.bitflips = 0; + snf->ecc_stats.failed = 0; + snf->ecc_stats.corrected = 0; + } else { + if (buf == op->data.buf.in) { + u32 cap_len = snf->buf_len - snf->nfi_cfg.page_size; + u32 req_left = op->data.nbytes - snf->nfi_cfg.page_size; + + if (req_left) + memcpy(op->data.buf.in + snf->nfi_cfg.page_size, + buf_fdm, + cap_len < req_left ? cap_len : req_left); + } else if (rd_offset < snf->buf_len) { + u32 cap_len = snf->buf_len - rd_offset; + + if (op->data.nbytes < cap_len) + cap_len = op->data.nbytes; + memcpy(op->data.buf.in, snf->buf + rd_offset, cap_len); + } + } +cleanup2: + if (op->data.ecc) + mtk_ecc_disable(snf->ecc); +cleanup_dma: + // unmap dma only if any error happens. (otherwise it's done before + // data copying) + if (ret) + dma_unmap_single(snf->dev, buf_dma, dma_len, DMA_FROM_DEVICE); +cleanup: + // Stop read + nfi_write32(snf, NFI_CON, 0); + nfi_write16(snf, NFI_CNFG, 0); + + // Clear SNF done flag + nfi_rmw32(snf, SNF_STA_CTL1, 0, CUS_READ_DONE); + nfi_write32(snf, SNF_STA_CTL1, 0); + + // Disable interrupt + nfi_read32(snf, NFI_INTR_STA); + nfi_write32(snf, NFI_INTR_EN, 0); + + nfi_rmw32(snf, SNF_MISC_CTL, DATARD_CUSTOM_EN, 0); + return ret; +} + +static int mtk_snand_write_page_cache(struct mtk_snand *snf, + const struct spi_mem_op *op) +{ + // the address part to be sent by the controller + u32 op_addr = op->addr.val; + // where to start copying data from bounce buffer + u32 wr_offset = 0; + u32 op_mode = 0; + int ret = 0; + u32 wr_mode = 0; + u32 dma_len = snf->buf_len; + u32 wr_bytes, val; + size_t cap_len; + dma_addr_t buf_dma; + + if (snf->autofmt) { + u32 last_bit; + u32 mask; + + dma_len = snf->nfi_cfg.page_size; + op_mode = CNFG_AUTO_FMT_EN; + if (op->data.ecc) + op_mode |= CNFG_HW_ECC_EN; + + last_bit = fls(snf->nfi_cfg.page_size + snf->nfi_cfg.oob_size); + mask = (1 << last_bit) - 1; + wr_offset = op_addr & mask; + op_addr &= ~mask; + } + mtk_snand_mac_reset(snf); + mtk_nfi_reset(snf); + + if (wr_offset) + memset(snf->buf, 0xff, wr_offset); + + cap_len = snf->buf_len - wr_offset; + if (op->data.nbytes < cap_len) + cap_len = op->data.nbytes; + memcpy(snf->buf + wr_offset, op->data.buf.out, cap_len); + if (snf->autofmt) { + if (snf->caps->bbm_swap) { + mtk_snand_fdm_bm_swap(snf); + mtk_snand_bm_swap(snf, snf->buf); + } + mtk_snand_write_fdm(snf, snf->buf + snf->nfi_cfg.page_size); + } + + // Command + nfi_write32(snf, SNF_PG_CTL1, (op->cmd.opcode << PG_LOAD_CMD_S)); + + // write address + nfi_write32(snf, SNF_PG_CTL2, op_addr); + + // Set read op_mode + if (op->data.buswidth == 4) + wr_mode = PG_LOAD_X4_EN; + + nfi_rmw32(snf, SNF_MISC_CTL, PG_LOAD_X4_EN, + wr_mode | PG_LOAD_CUSTOM_EN); + + // Set bytes to write + wr_bytes = (snf->nfi_cfg.spare_size + snf->caps->sector_size) * + snf->nfi_cfg.nsectors; + nfi_write32(snf, SNF_MISC_CTL2, + (wr_bytes << PROGRAM_LOAD_BYTE_NUM_S) | wr_bytes); + + // NFI write prepare + nfi_write16(snf, NFI_CNFG, + (CNFG_OP_MODE_PROGRAM << CNFG_OP_MODE_S) | + CNFG_DMA_BURST_EN | CNFG_DMA_MODE | op_mode); + + nfi_write32(snf, NFI_CON, (snf->nfi_cfg.nsectors << CON_SEC_NUM_S)); + buf_dma = dma_map_single(snf->dev, snf->buf, dma_len, DMA_TO_DEVICE); + ret = dma_mapping_error(snf->dev, buf_dma); + if (ret) { + dev_err(snf->dev, "DMA mapping failed.\n"); + goto cleanup; + } + nfi_write32(snf, NFI_STRADDR, buf_dma); + if (op->data.ecc) { + snf->ecc_cfg->op = ECC_ENCODE; + ret = mtk_ecc_enable(snf->ecc, snf->ecc_cfg); + if (ret) + goto cleanup_dma; + } + // Prepare for custom write interrupt + nfi_write32(snf, NFI_INTR_EN, NFI_IRQ_INTR_EN | NFI_IRQ_CUS_PG); + reinit_completion(&snf->op_done); + ; + + // Trigger NFI into custom mode + nfi_write16(snf, NFI_CMD, NFI_CMD_DUMMY_WRITE); + + // Start DMA write + nfi_rmw32(snf, NFI_CON, 0, CON_BWR); + nfi_write16(snf, NFI_STRDATA, STR_DATA); + + if (!wait_for_completion_timeout( + &snf->op_done, usecs_to_jiffies(SNFI_POLL_INTERVAL))) { + dev_err(snf->dev, "DMA timed out for program load.\n"); + ret = -ETIMEDOUT; + goto cleanup_ecc; + } + + // Wait for NFI_SEC_CNTR returning expected value + ret = readl_poll_timeout(snf->nfi_base + NFI_ADDRCNTR, val, + NFI_SEC_CNTR(val) >= snf->nfi_cfg.nsectors, 0, + SNFI_POLL_INTERVAL); + if (ret) + dev_err(snf->dev, "Timed out waiting for NFI_SEC_CNTR\n"); + +cleanup_ecc: + if (op->data.ecc) + mtk_ecc_disable(snf->ecc); +cleanup_dma: + dma_unmap_single(snf->dev, buf_dma, dma_len, DMA_TO_DEVICE); +cleanup: + // Stop write + nfi_write32(snf, NFI_CON, 0); + nfi_write16(snf, NFI_CNFG, 0); + + // Clear SNF done flag + nfi_rmw32(snf, SNF_STA_CTL1, 0, CUS_PG_DONE); + nfi_write32(snf, SNF_STA_CTL1, 0); + + // Disable interrupt + nfi_read32(snf, NFI_INTR_STA); + nfi_write32(snf, NFI_INTR_EN, 0); + + nfi_rmw32(snf, SNF_MISC_CTL, PG_LOAD_CUSTOM_EN, 0); + + return ret; +} + +/** + * mtk_snand_is_page_ops() - check if the op is a controller supported page op. + * @op spi-mem op to check + * + * Check whether op can be executed with read_from_cache or program_load + * mode in the controller. + * This controller can execute typical Read From Cache and Program Load + * instructions found on SPI-NAND with 2-byte address. + * DTR and cmd buswidth & nbytes should be checked before calling this. + * + * Return: true if the op matches the instruction template + */ +static bool mtk_snand_is_page_ops(const struct spi_mem_op *op) +{ + if (op->addr.nbytes != 2) + return false; + + if (op->addr.buswidth != 1 && op->addr.buswidth != 2 && + op->addr.buswidth != 4) + return false; + + // match read from page instructions + if (op->data.dir == SPI_MEM_DATA_IN) { + // check dummy cycle first + if (op->dummy.nbytes * BITS_PER_BYTE / op->dummy.buswidth > + DATA_READ_MAX_DUMMY) + return false; + // quad io / quad out + if ((op->addr.buswidth == 4 || op->addr.buswidth == 1) && + op->data.buswidth == 4) + return true; + + // dual io / dual out + if ((op->addr.buswidth == 2 || op->addr.buswidth == 1) && + op->data.buswidth == 2) + return true; + + // standard spi + if (op->addr.buswidth == 1 && op->data.buswidth == 1) + return true; + } else if (op->data.dir == SPI_MEM_DATA_OUT) { + // check dummy cycle first + if (op->dummy.nbytes) + return false; + // program load quad out + if (op->addr.buswidth == 1 && op->data.buswidth == 4) + return true; + // standard spi + if (op->addr.buswidth == 1 && op->data.buswidth == 1) + return true; + } + return false; +} + +static bool mtk_snand_supports_op(struct spi_mem *mem, + const struct spi_mem_op *op) +{ + if (!spi_mem_default_supports_op(mem, op)) + return false; + if (op->cmd.nbytes != 1 || op->cmd.buswidth != 1) + return false; + if (mtk_snand_is_page_ops(op)) + return true; + return ((op->addr.nbytes == 0 || op->addr.buswidth == 1) && + (op->dummy.nbytes == 0 || op->dummy.buswidth == 1) && + (op->data.nbytes == 0 || op->data.buswidth == 1)); +} + +static int mtk_snand_adjust_op_size(struct spi_mem *mem, struct spi_mem_op *op) +{ + struct mtk_snand *ms = spi_controller_get_devdata(mem->spi->master); + // page ops transfer size must be exactly ((sector_size + spare_size) * + // nsectors). Limit the op size if the caller requests more than that. + // exec_op will read more than needed and discard the leftover if the + // caller requests less data. + if (mtk_snand_is_page_ops(op)) { + size_t l; + // skip adjust_op_size for page ops + if (ms->autofmt) + return 0; + l = ms->caps->sector_size + ms->nfi_cfg.spare_size; + l *= ms->nfi_cfg.nsectors; + if (op->data.nbytes > l) + op->data.nbytes = l; + } else { + size_t hl = op->cmd.nbytes + op->addr.nbytes + op->dummy.nbytes; + + if (hl >= SNF_GPRAM_SIZE) + return -EOPNOTSUPP; + if (op->data.nbytes > SNF_GPRAM_SIZE - hl) + op->data.nbytes = SNF_GPRAM_SIZE - hl; + } + return 0; +} + +static int mtk_snand_exec_op(struct spi_mem *mem, const struct spi_mem_op *op) +{ + struct mtk_snand *ms = spi_controller_get_devdata(mem->spi->master); + + dev_dbg(ms->dev, "OP %02x ADDR %08llX@%d:%u DATA %d:%u", op->cmd.opcode, + op->addr.val, op->addr.buswidth, op->addr.nbytes, + op->data.buswidth, op->data.nbytes); + if (mtk_snand_is_page_ops(op)) { + if (op->data.dir == SPI_MEM_DATA_IN) + return mtk_snand_read_page_cache(ms, op); + else + return mtk_snand_write_page_cache(ms, op); + } else { + return mtk_snand_mac_io(ms, op); + } +} + +static const struct spi_controller_mem_ops mtk_snand_mem_ops = { + .adjust_op_size = mtk_snand_adjust_op_size, + .supports_op = mtk_snand_supports_op, + .exec_op = mtk_snand_exec_op, +}; + +static const struct spi_controller_mem_caps mtk_snand_mem_caps = { + .ecc = true, +}; + +static irqreturn_t mtk_snand_irq(int irq, void *id) +{ + struct mtk_snand *snf = id; + u32 sta, ien; + + sta = nfi_read32(snf, NFI_INTR_STA); + ien = nfi_read32(snf, NFI_INTR_EN); + + if (!(sta & ien)) + return IRQ_NONE; + + nfi_write32(snf, NFI_INTR_EN, 0); + complete(&snf->op_done); + return IRQ_HANDLED; +} + +static const struct of_device_id mtk_snand_ids[] = { + { .compatible = "mediatek,mt7622-snand", .data = &mt7622_snand_caps }, + { .compatible = "mediatek,mt7629-snand", .data = &mt7629_snand_caps }, + {}, +}; + +MODULE_DEVICE_TABLE(of, mtk_snand_ids); + +static int mtk_snand_enable_clk(struct mtk_snand *ms) +{ + int ret; + + ret = clk_prepare_enable(ms->nfi_clk); + if (ret) { + dev_err(ms->dev, "unable to enable nfi clk\n"); + return ret; + } + ret = clk_prepare_enable(ms->pad_clk); + if (ret) { + dev_err(ms->dev, "unable to enable pad clk\n"); + goto err1; + } + return 0; +err1: + clk_disable_unprepare(ms->nfi_clk); + return ret; +} + +static void mtk_snand_disable_clk(struct mtk_snand *ms) +{ + clk_disable_unprepare(ms->pad_clk); + clk_disable_unprepare(ms->nfi_clk); +} + +static int mtk_snand_probe(struct platform_device *pdev) +{ + struct device_node *np = pdev->dev.of_node; + const struct of_device_id *dev_id; + struct spi_controller *ctlr; + struct mtk_snand *ms; + int ret; + + dev_id = of_match_node(mtk_snand_ids, np); + if (!dev_id) + return -EINVAL; + + ctlr = devm_spi_alloc_master(&pdev->dev, sizeof(*ms)); + if (!ctlr) + return -ENOMEM; + platform_set_drvdata(pdev, ctlr); + + ms = spi_controller_get_devdata(ctlr); + + ms->ctlr = ctlr; + ms->caps = dev_id->data; + + ms->ecc = of_mtk_ecc_get(np); + if (IS_ERR(ms->ecc)) + return PTR_ERR(ms->ecc); + else if (!ms->ecc) + return -ENODEV; + + ms->nfi_base = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(ms->nfi_base)) { + ret = PTR_ERR(ms->nfi_base); + goto release_ecc; + } + + ms->dev = &pdev->dev; + + ms->nfi_clk = devm_clk_get(&pdev->dev, "nfi_clk"); + if (IS_ERR(ms->nfi_clk)) { + ret = PTR_ERR(ms->nfi_clk); + dev_err(&pdev->dev, "unable to get nfi_clk, err = %d\n", ret); + goto release_ecc; + } + + ms->pad_clk = devm_clk_get(&pdev->dev, "pad_clk"); + if (IS_ERR(ms->pad_clk)) { + ret = PTR_ERR(ms->pad_clk); + dev_err(&pdev->dev, "unable to get pad_clk, err = %d\n", ret); + goto release_ecc; + } + + ret = mtk_snand_enable_clk(ms); + if (ret) + goto release_ecc; + + init_completion(&ms->op_done); + + ms->irq = platform_get_irq(pdev, 0); + if (ms->irq < 0) { + ret = ms->irq; + goto disable_clk; + } + ret = devm_request_irq(ms->dev, ms->irq, mtk_snand_irq, 0x0, + "mtk-snand", ms); + if (ret) { + dev_err(ms->dev, "failed to request snfi irq\n"); + goto disable_clk; + } + + ret = dma_set_mask(ms->dev, DMA_BIT_MASK(32)); + if (ret) { + dev_err(ms->dev, "failed to set dma mask\n"); + goto disable_clk; + } + + // switch to SNFI mode + nfi_write32(ms, SNF_CFG, SPI_MODE); + + // setup an initial page format for ops matching page_cache_op template + // before ECC is called. + ret = mtk_snand_setup_pagefmt(ms, ms->caps->sector_size, + ms->caps->spare_sizes[0]); + if (ret) { + dev_err(ms->dev, "failed to set initial page format\n"); + goto disable_clk; + } + + // setup ECC engine + ms->ecc_eng.dev = &pdev->dev; + ms->ecc_eng.integration = NAND_ECC_ENGINE_INTEGRATION_PIPELINED; + ms->ecc_eng.ops = &mtk_snfi_ecc_engine_ops; + ms->ecc_eng.priv = ms; + + ret = nand_ecc_register_on_host_hw_engine(&ms->ecc_eng); + if (ret) { + dev_err(&pdev->dev, "failed to register ecc engine.\n"); + goto disable_clk; + } + + ctlr->num_chipselect = 1; + ctlr->mem_ops = &mtk_snand_mem_ops; + ctlr->mem_caps = &mtk_snand_mem_caps; + ctlr->bits_per_word_mask = SPI_BPW_MASK(8); + ctlr->mode_bits = SPI_RX_DUAL | SPI_RX_QUAD | SPI_TX_DUAL | SPI_TX_QUAD; + ctlr->dev.of_node = pdev->dev.of_node; + ret = spi_register_controller(ctlr); + if (ret) { + dev_err(&pdev->dev, "spi_register_controller failed.\n"); + goto disable_clk; + } + + return 0; +disable_clk: + mtk_snand_disable_clk(ms); +release_ecc: + mtk_ecc_release(ms->ecc); + return ret; +} + +static int mtk_snand_remove(struct platform_device *pdev) +{ + struct spi_controller *ctlr = platform_get_drvdata(pdev); + struct mtk_snand *ms = spi_controller_get_devdata(ctlr); + + spi_unregister_controller(ctlr); + mtk_snand_disable_clk(ms); + mtk_ecc_release(ms->ecc); + kfree(ms->buf); + return 0; +} + +static struct platform_driver mtk_snand_driver = { + .probe = mtk_snand_probe, + .remove = mtk_snand_remove, + .driver = { + .name = "mtk-snand", + .of_match_table = mtk_snand_ids, + }, +}; + +module_platform_driver(mtk_snand_driver); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Chuanhong Guo <gch981213@gmail.com>"); +MODULE_DESCRIPTION("MeidaTek SPI-NAND Flash Controller Driver"); diff --git a/drivers/spi/spi-mxic.c b/drivers/spi/spi-mxic.c index 55c092069301..65be8e085ab8 100644 --- a/drivers/spi/spi-mxic.c +++ b/drivers/spi/spi-mxic.c @@ -813,6 +813,7 @@ static int mxic_spi_probe(struct platform_device *pdev) if (ret) { dev_err(&pdev->dev, "spi_register_master failed\n"); pm_runtime_disable(&pdev->dev); + mxic_spi_mem_ecc_remove(mxic); } return ret; diff --git a/drivers/spi/spi-mxs.c b/drivers/spi/spi-mxs.c index 435309b09227..55178579f3c6 100644 --- a/drivers/spi/spi-mxs.c +++ b/drivers/spi/spi-mxs.c @@ -605,9 +605,8 @@ static int mxs_spi_probe(struct platform_device *pdev) } } - ret = pm_runtime_get_sync(ssp->dev); + ret = pm_runtime_resume_and_get(ssp->dev); if (ret < 0) { - pm_runtime_put_noidle(ssp->dev); dev_err(ssp->dev, "runtime_get_sync failed\n"); goto out_pm_runtime_disable; } diff --git a/drivers/spi/spi-omap2-mcspi.c b/drivers/spi/spi-omap2-mcspi.c index 60c9cdf1c94b..c42e59df38fe 100644 --- a/drivers/spi/spi-omap2-mcspi.c +++ b/drivers/spi/spi-omap2-mcspi.c @@ -246,9 +246,8 @@ static void omap2_mcspi_set_cs(struct spi_device *spi, bool enable) enable = !enable; if (spi->controller_state) { - int err = pm_runtime_get_sync(mcspi->dev); + int err = pm_runtime_resume_and_get(mcspi->dev); if (err < 0) { - pm_runtime_put_noidle(mcspi->dev); dev_err(mcspi->dev, "failed to get sync: %d\n", err); return; } @@ -758,6 +757,8 @@ omap2_mcspi_txrx_pio(struct spi_device *spi, struct spi_transfer *xfer) dev_vdbg(&spi->dev, "read-%d %02x\n", word_len, *(rx - 1)); } + /* Add word delay between each word */ + spi_delay_exec(&xfer->word_delay, xfer); } while (c); } else if (word_len <= 16) { u16 *rx; @@ -805,6 +806,8 @@ omap2_mcspi_txrx_pio(struct spi_device *spi, struct spi_transfer *xfer) dev_vdbg(&spi->dev, "read-%d %04x\n", word_len, *(rx - 1)); } + /* Add word delay between each word */ + spi_delay_exec(&xfer->word_delay, xfer); } while (c >= 2); } else if (word_len <= 32) { u32 *rx; @@ -852,6 +855,8 @@ omap2_mcspi_txrx_pio(struct spi_device *spi, struct spi_transfer *xfer) dev_vdbg(&spi->dev, "read-%d %08x\n", word_len, *(rx - 1)); } + /* Add word delay between each word */ + spi_delay_exec(&xfer->word_delay, xfer); } while (c >= 4); } @@ -1068,9 +1073,8 @@ static int omap2_mcspi_setup(struct spi_device *spi) initial_setup = true; } - ret = pm_runtime_get_sync(mcspi->dev); + ret = pm_runtime_resume_and_get(mcspi->dev); if (ret < 0) { - pm_runtime_put_noidle(mcspi->dev); if (initial_setup) omap2_mcspi_cleanup(spi); @@ -1317,12 +1321,9 @@ static int omap2_mcspi_controller_setup(struct omap2_mcspi *mcspi) struct omap2_mcspi_regs *ctx = &mcspi->ctx; int ret = 0; - ret = pm_runtime_get_sync(mcspi->dev); - if (ret < 0) { - pm_runtime_put_noidle(mcspi->dev); - + ret = pm_runtime_resume_and_get(mcspi->dev); + if (ret < 0) return ret; - } mcspi_write_reg(master, OMAP2_MCSPI_WAKEUPENABLE, OMAP2_MCSPI_WAKEUPENABLE_WKEN); diff --git a/drivers/spi/spi-rockchip.c b/drivers/spi/spi-rockchip.c index cdc16eecaf6b..a08215eb9e14 100644 --- a/drivers/spi/spi-rockchip.c +++ b/drivers/spi/spi-rockchip.c @@ -196,6 +196,8 @@ struct rockchip_spi { bool slave_abort; bool cs_inactive; /* spi slave tansmition stop when cs inactive */ + bool cs_high_supported; /* native CS supports active-high polarity */ + struct spi_transfer *xfer; /* Store xfer temporarily */ }; @@ -719,6 +721,11 @@ static int rockchip_spi_setup(struct spi_device *spi) struct rockchip_spi *rs = spi_controller_get_devdata(spi->controller); u32 cr0; + if (!spi->cs_gpiod && (spi->mode & SPI_CS_HIGH) && !rs->cs_high_supported) { + dev_warn(&spi->dev, "setup: non GPIO CS can't be active-high\n"); + return -EINVAL; + } + pm_runtime_get_sync(rs->dev); cr0 = readl_relaxed(rs->regs + ROCKCHIP_SPI_CTRLR0); @@ -899,6 +906,7 @@ static int rockchip_spi_probe(struct platform_device *pdev) switch (readl_relaxed(rs->regs + ROCKCHIP_SPI_VERSION)) { case ROCKCHIP_SPI_VER2_TYPE2: + rs->cs_high_supported = true; ctlr->mode_bits |= SPI_CS_HIGH; if (ctlr->can_dma && slave_mode) rs->cs_inactive = true; diff --git a/drivers/spi/spi-rpc-if.c b/drivers/spi/spi-rpc-if.c index fe82f3575df4..24ec1c83f379 100644 --- a/drivers/spi/spi-rpc-if.c +++ b/drivers/spi/spi-rpc-if.c @@ -158,14 +158,18 @@ static int rpcif_spi_probe(struct platform_device *pdev) error = rpcif_hw_init(rpc, false); if (error) - return error; + goto out_disable_rpm; error = spi_register_controller(ctlr); if (error) { dev_err(&pdev->dev, "spi_register_controller failed\n"); - rpcif_disable_rpm(rpc); + goto out_disable_rpm; } + return 0; + +out_disable_rpm: + rpcif_disable_rpm(rpc); return error; } diff --git a/drivers/spi/spi-rspi.c b/drivers/spi/spi-rspi.c index bd5708d7e5a1..7a014eeec2d0 100644 --- a/drivers/spi/spi-rspi.c +++ b/drivers/spi/spi-rspi.c @@ -1108,14 +1108,11 @@ static struct dma_chan *rspi_request_dma_chan(struct device *dev, } memset(&cfg, 0, sizeof(cfg)); + cfg.dst_addr = port_addr + RSPI_SPDR; + cfg.src_addr = port_addr + RSPI_SPDR; + cfg.dst_addr_width = DMA_SLAVE_BUSWIDTH_1_BYTE; + cfg.src_addr_width = DMA_SLAVE_BUSWIDTH_1_BYTE; cfg.direction = dir; - if (dir == DMA_MEM_TO_DEV) { - cfg.dst_addr = port_addr; - cfg.dst_addr_width = DMA_SLAVE_BUSWIDTH_1_BYTE; - } else { - cfg.src_addr = port_addr; - cfg.src_addr_width = DMA_SLAVE_BUSWIDTH_1_BYTE; - } ret = dmaengine_slave_config(chan, &cfg); if (ret) { @@ -1146,12 +1143,12 @@ static int rspi_request_dma(struct device *dev, struct spi_controller *ctlr, } ctlr->dma_tx = rspi_request_dma_chan(dev, DMA_MEM_TO_DEV, dma_tx_id, - res->start + RSPI_SPDR); + res->start); if (!ctlr->dma_tx) return -ENODEV; ctlr->dma_rx = rspi_request_dma_chan(dev, DMA_DEV_TO_MEM, dma_rx_id, - res->start + RSPI_SPDR); + res->start); if (!ctlr->dma_rx) { dma_release_channel(ctlr->dma_tx); ctlr->dma_tx = NULL; diff --git a/drivers/spi/spi-sprd.c b/drivers/spi/spi-sprd.c index 28e70db9bbba..65b8075da4eb 100644 --- a/drivers/spi/spi-sprd.c +++ b/drivers/spi/spi-sprd.c @@ -1008,9 +1008,8 @@ static int sprd_spi_remove(struct platform_device *pdev) struct sprd_spi *ss = spi_controller_get_devdata(sctlr); int ret; - ret = pm_runtime_get_sync(ss->dev); + ret = pm_runtime_resume_and_get(ss->dev); if (ret < 0) { - pm_runtime_put_noidle(ss->dev); dev_err(ss->dev, "failed to resume SPI controller\n"); return ret; } diff --git a/drivers/spi/spi-stm32-qspi.c b/drivers/spi/spi-stm32-qspi.c index ffdc55f87e82..c0239e405c39 100644 --- a/drivers/spi/spi-stm32-qspi.c +++ b/drivers/spi/spi-stm32-qspi.c @@ -305,10 +305,8 @@ static int stm32_qspi_wait_cmd(struct stm32_qspi *qspi, u32 cr, sr; int err = 0; - if (!op->data.nbytes) - goto wait_nobusy; - - if (readl_relaxed(qspi->io_base + QSPI_SR) & SR_TCF) + if ((readl_relaxed(qspi->io_base + QSPI_SR) & SR_TCF) || + qspi->fmode == CCR_FMODE_APM) goto out; reinit_completion(&qspi->data_completion); @@ -327,7 +325,6 @@ static int stm32_qspi_wait_cmd(struct stm32_qspi *qspi, out: /* clear flags */ writel_relaxed(FCR_CTCF | FCR_CTEF, qspi->io_base + QSPI_FCR); -wait_nobusy: if (!err) err = stm32_qspi_wait_nobusy(qspi); @@ -372,10 +369,6 @@ static int stm32_qspi_send(struct spi_mem *mem, const struct spi_mem_op *op) op->dummy.buswidth, op->data.buswidth, op->addr.val, op->data.nbytes); - err = stm32_qspi_wait_nobusy(qspi); - if (err) - goto abort; - cr = readl_relaxed(qspi->io_base + QSPI_CR); cr &= ~CR_PRESC_MASK & ~CR_FSEL; cr |= FIELD_PREP(CR_PRESC_MASK, flash->presc); @@ -463,11 +456,9 @@ static int stm32_qspi_poll_status(struct spi_mem *mem, const struct spi_mem_op * if (!spi_mem_supports_op(mem, op)) return -EOPNOTSUPP; - ret = pm_runtime_get_sync(qspi->dev); - if (ret < 0) { - pm_runtime_put_noidle(qspi->dev); + ret = pm_runtime_resume_and_get(qspi->dev); + if (ret < 0) return ret; - } mutex_lock(&qspi->lock); @@ -490,11 +481,9 @@ static int stm32_qspi_exec_op(struct spi_mem *mem, const struct spi_mem_op *op) struct stm32_qspi *qspi = spi_controller_get_devdata(mem->spi->master); int ret; - ret = pm_runtime_get_sync(qspi->dev); - if (ret < 0) { - pm_runtime_put_noidle(qspi->dev); + ret = pm_runtime_resume_and_get(qspi->dev); + if (ret < 0) return ret; - } mutex_lock(&qspi->lock); if (op->data.dir == SPI_MEM_DATA_IN && op->data.nbytes) @@ -536,11 +525,9 @@ static ssize_t stm32_qspi_dirmap_read(struct spi_mem_dirmap_desc *desc, u32 addr_max; int ret; - ret = pm_runtime_get_sync(qspi->dev); - if (ret < 0) { - pm_runtime_put_noidle(qspi->dev); + ret = pm_runtime_resume_and_get(qspi->dev); + if (ret < 0) return ret; - } mutex_lock(&qspi->lock); /* make a local copy of desc op_tmpl and complete dirmap rdesc @@ -583,11 +570,9 @@ static int stm32_qspi_setup(struct spi_device *spi) if (!spi->max_speed_hz) return -EINVAL; - ret = pm_runtime_get_sync(qspi->dev); - if (ret < 0) { - pm_runtime_put_noidle(qspi->dev); + ret = pm_runtime_resume_and_get(qspi->dev); + if (ret < 0) return ret; - } presc = DIV_ROUND_UP(qspi->clk_rate, spi->max_speed_hz) - 1; @@ -851,11 +836,9 @@ static int __maybe_unused stm32_qspi_resume(struct device *dev) pinctrl_pm_select_default_state(dev); - ret = pm_runtime_get_sync(dev); - if (ret < 0) { - pm_runtime_put_noidle(dev); + ret = pm_runtime_resume_and_get(dev); + if (ret < 0) return ret; - } writel_relaxed(qspi->cr_reg, qspi->io_base + QSPI_CR); writel_relaxed(qspi->dcr_reg, qspi->io_base + QSPI_DCR); diff --git a/drivers/spi/spi-stm32.c b/drivers/spi/spi-stm32.c index a6adc20f6862..6fe617b445a5 100644 --- a/drivers/spi/spi-stm32.c +++ b/drivers/spi/spi-stm32.c @@ -2000,9 +2000,8 @@ static int __maybe_unused stm32_spi_resume(struct device *dev) return ret; } - ret = pm_runtime_get_sync(dev); + ret = pm_runtime_resume_and_get(dev); if (ret < 0) { - pm_runtime_put_noidle(dev); dev_err(dev, "Unable to power device:%d\n", ret); return ret; } diff --git a/drivers/spi/spi-sunplus-sp7021.c b/drivers/spi/spi-sunplus-sp7021.c index f989f7b99296..f1fa88777575 100644 --- a/drivers/spi/spi-sunplus-sp7021.c +++ b/drivers/spi/spi-sunplus-sp7021.c @@ -85,8 +85,6 @@ struct sp7021_spi_ctlr { int s_irq; struct clk *spi_clk; struct reset_control *rstc; - // irq spin lock - spinlock_t lock; // data xfer lock struct mutex buf_lock; struct completion isr_done; @@ -199,8 +197,6 @@ static irqreturn_t sp7021_spi_master_irq(int irq, void *dev) if (tx_len == 0 && total_len == 0) return IRQ_NONE; - spin_lock_irq(&pspim->lock); - rx_cnt = FIELD_GET(SP7021_RX_CNT_MASK, fd_status); if (fd_status & SP7021_RX_FULL_FLAG) rx_cnt = pspim->data_unit; @@ -239,7 +235,6 @@ static irqreturn_t sp7021_spi_master_irq(int irq, void *dev) if (isrdone) complete(&pspim->isr_done); - spin_unlock_irq(&pspim->lock); return IRQ_HANDLED; } @@ -446,7 +441,6 @@ static int sp7021_spi_controller_probe(struct platform_device *pdev) pspim->mode = mode; pspim->ctlr = ctlr; pspim->dev = dev; - spin_lock_init(&pspim->lock); mutex_init(&pspim->buf_lock); init_completion(&pspim->isr_done); init_completion(&pspim->slave_isr); diff --git a/drivers/spi/spi-tegra114.c b/drivers/spi/spi-tegra114.c index 8f345247a8c3..d9be80e3e1bc 100644 --- a/drivers/spi/spi-tegra114.c +++ b/drivers/spi/spi-tegra114.c @@ -964,9 +964,8 @@ static int tegra_spi_setup(struct spi_device *spi) spi->controller_data = cdata; } - ret = pm_runtime_get_sync(tspi->dev); + ret = pm_runtime_resume_and_get(tspi->dev); if (ret < 0) { - pm_runtime_put_noidle(tspi->dev); dev_err(tspi->dev, "pm runtime failed, e = %d\n", ret); if (cdata) tegra_spi_cleanup(spi); @@ -1394,10 +1393,9 @@ static int tegra_spi_probe(struct platform_device *pdev) goto exit_pm_disable; } - ret = pm_runtime_get_sync(&pdev->dev); + ret = pm_runtime_resume_and_get(&pdev->dev); if (ret < 0) { dev_err(&pdev->dev, "pm runtime get failed, e = %d\n", ret); - pm_runtime_put_noidle(&pdev->dev); goto exit_pm_disable; } @@ -1476,9 +1474,8 @@ static int tegra_spi_resume(struct device *dev) struct tegra_spi_data *tspi = spi_master_get_devdata(master); int ret; - ret = pm_runtime_get_sync(dev); + ret = pm_runtime_resume_and_get(dev); if (ret < 0) { - pm_runtime_put_noidle(dev); dev_err(dev, "pm runtime failed, e = %d\n", ret); return ret; } diff --git a/drivers/spi/spi-tegra20-sflash.c b/drivers/spi/spi-tegra20-sflash.c index 2888d8a8dc6d..220ee08c4a06 100644 --- a/drivers/spi/spi-tegra20-sflash.c +++ b/drivers/spi/spi-tegra20-sflash.c @@ -486,10 +486,9 @@ static int tegra_sflash_probe(struct platform_device *pdev) goto exit_pm_disable; } - ret = pm_runtime_get_sync(&pdev->dev); + ret = pm_runtime_resume_and_get(&pdev->dev); if (ret < 0) { dev_err(&pdev->dev, "pm runtime get failed, e = %d\n", ret); - pm_runtime_put_noidle(&pdev->dev); goto exit_pm_disable; } @@ -549,9 +548,8 @@ static int tegra_sflash_resume(struct device *dev) struct tegra_sflash_data *tsd = spi_master_get_devdata(master); int ret; - ret = pm_runtime_get_sync(dev); + ret = pm_runtime_resume_and_get(dev); if (ret < 0) { - pm_runtime_put_noidle(dev); dev_err(dev, "pm runtime failed, e = %d\n", ret); return ret; } diff --git a/drivers/spi/spi-tegra20-slink.c b/drivers/spi/spi-tegra20-slink.c index 80c3787deea9..38360434d6e9 100644 --- a/drivers/spi/spi-tegra20-slink.c +++ b/drivers/spi/spi-tegra20-slink.c @@ -749,9 +749,8 @@ static int tegra_slink_setup(struct spi_device *spi) spi->mode & SPI_CPHA ? "" : "~", spi->max_speed_hz); - ret = pm_runtime_get_sync(tspi->dev); + ret = pm_runtime_resume_and_get(tspi->dev); if (ret < 0) { - pm_runtime_put_noidle(tspi->dev); dev_err(tspi->dev, "pm runtime failed, e = %d\n", ret); return ret; } @@ -1169,9 +1168,8 @@ static int tegra_slink_resume(struct device *dev) struct tegra_slink_data *tspi = spi_master_get_devdata(master); int ret; - ret = pm_runtime_get_sync(dev); + ret = pm_runtime_resume_and_get(dev); if (ret < 0) { - pm_runtime_put_noidle(dev); dev_err(dev, "pm runtime failed, e = %d\n", ret); return ret; } diff --git a/drivers/spi/spi-ti-qspi.c b/drivers/spi/spi-ti-qspi.c index e06aafe169e0..b5b65d882d7a 100644 --- a/drivers/spi/spi-ti-qspi.c +++ b/drivers/spi/spi-ti-qspi.c @@ -172,9 +172,8 @@ static int ti_qspi_setup(struct spi_device *spi) dev_dbg(qspi->dev, "hz: %d, clock divider %d\n", qspi->spi_max_frequency, clk_div); - ret = pm_runtime_get_sync(qspi->dev); + ret = pm_runtime_resume_and_get(qspi->dev); if (ret < 0) { - pm_runtime_put_noidle(qspi->dev); dev_err(qspi->dev, "pm_runtime_get_sync() failed\n"); return ret; } @@ -448,6 +447,7 @@ static int ti_qspi_dma_xfer(struct ti_qspi *qspi, dma_addr_t dma_dst, enum dma_ctrl_flags flags = DMA_CTRL_ACK | DMA_PREP_INTERRUPT; struct dma_async_tx_descriptor *tx; int ret; + unsigned long time_left; tx = dmaengine_prep_dma_memcpy(chan, dma_dst, dma_src, len, flags); if (!tx) { @@ -467,9 +467,9 @@ static int ti_qspi_dma_xfer(struct ti_qspi *qspi, dma_addr_t dma_dst, } dma_async_issue_pending(chan); - ret = wait_for_completion_timeout(&qspi->transfer_complete, + time_left = wait_for_completion_timeout(&qspi->transfer_complete, msecs_to_jiffies(len)); - if (ret <= 0) { + if (time_left == 0) { dmaengine_terminate_sync(chan); dev_err(qspi->dev, "DMA wait_for_completion_timeout\n"); return -ETIMEDOUT; diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index c4dd1200fe99..fe252a8075a7 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -1130,11 +1130,15 @@ static int __spi_unmap_msg(struct spi_controller *ctlr, struct spi_message *msg) if (ctlr->dma_tx) tx_dev = ctlr->dma_tx->device->dev; + else if (ctlr->dma_map_dev) + tx_dev = ctlr->dma_map_dev; else tx_dev = ctlr->dev.parent; if (ctlr->dma_rx) rx_dev = ctlr->dma_rx->device->dev; + else if (ctlr->dma_map_dev) + rx_dev = ctlr->dma_map_dev; else rx_dev = ctlr->dev.parent; @@ -1607,9 +1611,8 @@ static void __spi_pump_messages(struct spi_controller *ctlr, bool in_kthread) mutex_lock(&ctlr->io_mutex); if (!was_busy && ctlr->auto_runtime_pm) { - ret = pm_runtime_get_sync(ctlr->dev.parent); + ret = pm_runtime_resume_and_get(ctlr->dev.parent); if (ret < 0) { - pm_runtime_put_noidle(ctlr->dev.parent); dev_err(&ctlr->dev, "Failed to power device: %d\n", ret); mutex_unlock(&ctlr->io_mutex); @@ -2406,7 +2409,8 @@ static int acpi_spi_add_resource(struct acpi_resource *ares, void *data) } else { struct acpi_device *adev; - if (acpi_bus_get_device(parent_handle, &adev)) + adev = acpi_fetch_acpi_dev(parent_handle); + if (!adev) return -ENODEV; ctlr = acpi_spi_find_controller_by_adev(adev); @@ -3470,7 +3474,7 @@ static int __spi_validate_bits_per_word(struct spi_controller *ctlr, int spi_setup(struct spi_device *spi) { unsigned bad_bits, ugly_bits; - int status; + int status = 0; /* * Check mode to prevent that any two of DUAL, QUAD and NO_MOSI/MISO @@ -3513,13 +3517,18 @@ int spi_setup(struct spi_device *spi) return -EINVAL; } - if (!spi->bits_per_word) + if (!spi->bits_per_word) { spi->bits_per_word = 8; - - status = __spi_validate_bits_per_word(spi->controller, - spi->bits_per_word); - if (status) - return status; + } else { + /* + * Some controllers may not support the default 8 bits-per-word + * so only perform the check when this is explicitly provided. + */ + status = __spi_validate_bits_per_word(spi->controller, + spi->bits_per_word); + if (status) + return status; + } if (spi->controller->max_speed_hz && (!spi->max_speed_hz || @@ -3539,10 +3548,9 @@ int spi_setup(struct spi_device *spi) } if (spi->controller->auto_runtime_pm && spi->controller->set_cs) { - status = pm_runtime_get_sync(spi->controller->dev.parent); + status = pm_runtime_resume_and_get(spi->controller->dev.parent); if (status < 0) { mutex_unlock(&spi->controller->io_mutex); - pm_runtime_put_noidle(spi->controller->dev.parent); dev_err(&spi->controller->dev, "Failed to power device: %d\n", status); return status; diff --git a/drivers/spi/spidev.c b/drivers/spi/spidev.c index 53a551714265..b2775d82d2d7 100644 --- a/drivers/spi/spidev.c +++ b/drivers/spi/spidev.c @@ -8,19 +8,18 @@ */ #include <linux/init.h> -#include <linux/module.h> #include <linux/ioctl.h> #include <linux/fs.h> #include <linux/device.h> #include <linux/err.h> #include <linux/list.h> #include <linux/errno.h> +#include <linux/mod_devicetable.h> +#include <linux/module.h> #include <linux/mutex.h> +#include <linux/property.h> #include <linux/slab.h> #include <linux/compat.h> -#include <linux/of.h> -#include <linux/of_device.h> -#include <linux/acpi.h> #include <linux/spi/spi.h> #include <linux/spi/spidev.h> @@ -46,6 +45,7 @@ static DECLARE_BITMAP(minors, N_SPI_MINORS); +static_assert(N_SPI_MINORS > 0 && N_SPI_MINORS <= 256); /* Bit masks for spi_device.mode management. Note that incorrect * settings for some settings can cause *lots* of trouble for other @@ -63,7 +63,8 @@ static DECLARE_BITMAP(minors, N_SPI_MINORS); | SPI_LSB_FIRST | SPI_3WIRE | SPI_LOOP \ | SPI_NO_CS | SPI_READY | SPI_TX_DUAL \ | SPI_TX_QUAD | SPI_TX_OCTAL | SPI_RX_DUAL \ - | SPI_RX_QUAD | SPI_RX_OCTAL) + | SPI_RX_QUAD | SPI_RX_OCTAL \ + | SPI_RX_CPHA_FLIP) struct spidev_data { dev_t devt; @@ -568,19 +569,20 @@ spidev_compat_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) static int spidev_open(struct inode *inode, struct file *filp) { - struct spidev_data *spidev; + struct spidev_data *spidev = NULL, *iter; int status = -ENXIO; mutex_lock(&device_list_lock); - list_for_each_entry(spidev, &device_list, device_entry) { - if (spidev->devt == inode->i_rdev) { + list_for_each_entry(iter, &device_list, device_entry) { + if (iter->devt == inode->i_rdev) { status = 0; + spidev = iter; break; } } - if (status) { + if (!spidev) { pr_debug("spidev: nothing for minor %d\n", iminor(inode)); goto err_find_dev; } @@ -693,25 +695,38 @@ static const struct spi_device_id spidev_spi_ids[] = { }; MODULE_DEVICE_TABLE(spi, spidev_spi_ids); -#ifdef CONFIG_OF +/* + * spidev should never be referenced in DT without a specific compatible string, + * it is a Linux implementation thing rather than a description of the hardware. + */ +static int spidev_of_check(struct device *dev) +{ + if (device_property_match_string(dev, "compatible", "spidev") < 0) + return 0; + + dev_err(dev, "spidev listed directly in DT is not supported\n"); + return -EINVAL; +} + static const struct of_device_id spidev_dt_ids[] = { - { .compatible = "rohm,dh2228fv" }, - { .compatible = "lineartechnology,ltc2488" }, - { .compatible = "semtech,sx1301" }, - { .compatible = "lwn,bk4" }, - { .compatible = "dh,dhcom-board" }, - { .compatible = "menlo,m53cpld" }, - { .compatible = "cisco,spi-petra" }, - { .compatible = "micron,spi-authenta" }, + { .compatible = "rohm,dh2228fv", .data = &spidev_of_check }, + { .compatible = "lineartechnology,ltc2488", .data = &spidev_of_check }, + { .compatible = "semtech,sx1301", .data = &spidev_of_check }, + { .compatible = "lwn,bk4", .data = &spidev_of_check }, + { .compatible = "dh,dhcom-board", .data = &spidev_of_check }, + { .compatible = "menlo,m53cpld", .data = &spidev_of_check }, + { .compatible = "cisco,spi-petra", .data = &spidev_of_check }, + { .compatible = "micron,spi-authenta", .data = &spidev_of_check }, {}, }; MODULE_DEVICE_TABLE(of, spidev_dt_ids); -#endif - -#ifdef CONFIG_ACPI /* Dummy SPI devices not to be used in production systems */ -#define SPIDEV_ACPI_DUMMY 1 +static int spidev_acpi_check(struct device *dev) +{ + dev_warn(dev, "do not use this driver in production systems!\n"); + return 0; +} static const struct acpi_device_id spidev_acpi_ids[] = { /* @@ -720,51 +735,29 @@ static const struct acpi_device_id spidev_acpi_ids[] = { * description of the connected peripheral and they should also use * a proper driver instead of poking directly to the SPI bus. */ - { "SPT0001", SPIDEV_ACPI_DUMMY }, - { "SPT0002", SPIDEV_ACPI_DUMMY }, - { "SPT0003", SPIDEV_ACPI_DUMMY }, + { "SPT0001", (kernel_ulong_t)&spidev_acpi_check }, + { "SPT0002", (kernel_ulong_t)&spidev_acpi_check }, + { "SPT0003", (kernel_ulong_t)&spidev_acpi_check }, {}, }; MODULE_DEVICE_TABLE(acpi, spidev_acpi_ids); -static void spidev_probe_acpi(struct spi_device *spi) -{ - const struct acpi_device_id *id; - - if (!has_acpi_companion(&spi->dev)) - return; - - id = acpi_match_device(spidev_acpi_ids, &spi->dev); - if (WARN_ON(!id)) - return; - - if (id->driver_data == SPIDEV_ACPI_DUMMY) - dev_warn(&spi->dev, "do not use this driver in production systems!\n"); -} -#else -static inline void spidev_probe_acpi(struct spi_device *spi) {} -#endif - /*-------------------------------------------------------------------------*/ static int spidev_probe(struct spi_device *spi) { + int (*match)(struct device *dev); struct spidev_data *spidev; int status; unsigned long minor; - /* - * spidev should never be referenced in DT without a specific - * compatible string, it is a Linux implementation thing - * rather than a description of the hardware. - */ - if (spi->dev.of_node && of_device_is_compatible(spi->dev.of_node, "spidev")) { - dev_err(&spi->dev, "spidev listed directly in DT is not supported\n"); - return -EINVAL; + match = device_get_match_data(&spi->dev); + if (match) { + status = match(&spi->dev); + if (status) + return status; } - spidev_probe_acpi(spi); - /* Allocate driver data */ spidev = kzalloc(sizeof(*spidev), GFP_KERNEL); if (!spidev) @@ -832,8 +825,8 @@ static void spidev_remove(struct spi_device *spi) static struct spi_driver spidev_spi_driver = { .driver = { .name = "spidev", - .of_match_table = of_match_ptr(spidev_dt_ids), - .acpi_match_table = ACPI_PTR(spidev_acpi_ids), + .of_match_table = spidev_dt_ids, + .acpi_match_table = spidev_acpi_ids, }, .probe = spidev_probe, .remove = spidev_remove, @@ -856,7 +849,6 @@ static int __init spidev_init(void) * that will key udev/mdev to add/remove /dev nodes. Last, register * the driver which manages those device numbers. */ - BUILD_BUG_ON(N_SPI_MINORS > 256); status = register_chrdev(SPIDEV_MAJOR, "spi", &spidev_fops); if (status < 0) return status; diff --git a/drivers/staging/media/atomisp/pci/runtime/rmgr/src/rmgr_vbuf.c b/drivers/staging/media/atomisp/pci/runtime/rmgr/src/rmgr_vbuf.c index d96aaa4bc75d..39604752785b 100644 --- a/drivers/staging/media/atomisp/pci/runtime/rmgr/src/rmgr_vbuf.c +++ b/drivers/staging/media/atomisp/pci/runtime/rmgr/src/rmgr_vbuf.c @@ -254,7 +254,7 @@ void rmgr_pop_handle(struct ia_css_rmgr_vbuf_pool *pool, void ia_css_rmgr_acq_vbuf(struct ia_css_rmgr_vbuf_pool *pool, struct ia_css_rmgr_vbuf_handle **handle) { - struct ia_css_rmgr_vbuf_handle h; + struct ia_css_rmgr_vbuf_handle h = { 0 }; if ((!pool) || (!handle) || (!*handle)) { IA_CSS_LOG("Invalid inputs"); @@ -272,7 +272,7 @@ void ia_css_rmgr_acq_vbuf(struct ia_css_rmgr_vbuf_pool *pool, h.size = (*handle)->size; /* release ref to current buffer */ ia_css_rmgr_refcount_release_vbuf(handle); - *handle = &h; + **handle = h; } /* get new buffer for needed size */ if ((*handle)->vptr == 0x0) { diff --git a/drivers/staging/media/av7110/av7110_av.c b/drivers/staging/media/av7110/av7110_av.c index 91f4866c7e59..ab7cf496b454 100644 --- a/drivers/staging/media/av7110/av7110_av.c +++ b/drivers/staging/media/av7110/av7110_av.c @@ -595,10 +595,10 @@ static int find_pes_header(u8 const *buf, long int length, int *frags) case PROG_STREAM_MAP: case PRIVATE_STREAM2: case PROG_STREAM_DIR: - case ECM_STREAM : - case EMM_STREAM : - case PADDING_STREAM : - case DSM_CC_STREAM : + case ECM_STREAM: + case EMM_STREAM: + case PADDING_STREAM: + case DSM_CC_STREAM: case ISO13522_STREAM: case PRIVATE_STREAM1: case AUDIO_STREAM_S ... AUDIO_STREAM_E: @@ -659,10 +659,10 @@ void av7110_p2t_write(u8 const *buf, long int length, u16 pid, struct av7110_p2t case PROG_STREAM_MAP: case PRIVATE_STREAM2: case PROG_STREAM_DIR: - case ECM_STREAM : - case EMM_STREAM : - case PADDING_STREAM : - case DSM_CC_STREAM : + case ECM_STREAM: + case EMM_STREAM: + case PADDING_STREAM: + case DSM_CC_STREAM: case ISO13522_STREAM: case PRIVATE_STREAM1: case AUDIO_STREAM_S ... AUDIO_STREAM_E: @@ -770,22 +770,22 @@ static void p_to_t(u8 const *buf, long int length, u16 pid, u8 *counter, if (length > 3 && buf[0] == 0x00 && buf[1] == 0x00 && buf[2] == 0x01) switch (buf[3]) { - case PROG_STREAM_MAP: - case PRIVATE_STREAM2: - case PROG_STREAM_DIR: - case ECM_STREAM : - case EMM_STREAM : - case PADDING_STREAM : - case DSM_CC_STREAM : - case ISO13522_STREAM: - case PRIVATE_STREAM1: - case AUDIO_STREAM_S ... AUDIO_STREAM_E: - case VIDEO_STREAM_S ... VIDEO_STREAM_E: - pes_start = 1; - break; + case PROG_STREAM_MAP: + case PRIVATE_STREAM2: + case PROG_STREAM_DIR: + case ECM_STREAM: + case EMM_STREAM: + case PADDING_STREAM: + case DSM_CC_STREAM: + case ISO13522_STREAM: + case PRIVATE_STREAM1: + case AUDIO_STREAM_S ... AUDIO_STREAM_E: + case VIDEO_STREAM_S ... VIDEO_STREAM_E: + pes_start = 1; + break; - default: - break; + default: + break; } while (c < length) { diff --git a/drivers/staging/media/hantro/TODO b/drivers/staging/media/hantro/TODO index 1d7fed936019..8483ff482146 100644 --- a/drivers/staging/media/hantro/TODO +++ b/drivers/staging/media/hantro/TODO @@ -1,6 +1,2 @@ -* Support for VP8, VP9 and H264 is planned for this driver. - - Given the V4L controls for those CODECs will be part of - the uABI, it will be required to have the driver in staging. - - For this reason, we are keeping this driver in staging for now. +The V4L controls for the HEVC CODEC are not yet part of the stable uABI, +we are keeping this driver in staging until the HEVC uABI has been merged. diff --git a/drivers/staging/media/hantro/hantro.h b/drivers/staging/media/hantro/hantro.h index 357f83b86809..26308bb29adc 100644 --- a/drivers/staging/media/hantro/hantro.h +++ b/drivers/staging/media/hantro/hantro.h @@ -475,5 +475,7 @@ void hantro_postproc_disable(struct hantro_ctx *ctx); void hantro_postproc_enable(struct hantro_ctx *ctx); void hantro_postproc_free(struct hantro_ctx *ctx); int hantro_postproc_alloc(struct hantro_ctx *ctx); +int hanto_postproc_enum_framesizes(struct hantro_ctx *ctx, + struct v4l2_frmsizeenum *fsize); #endif /* HANTRO_H_ */ diff --git a/drivers/staging/media/hantro/hantro_drv.c b/drivers/staging/media/hantro/hantro_drv.c index dc768884cb79..ac232b5f7825 100644 --- a/drivers/staging/media/hantro/hantro_drv.c +++ b/drivers/staging/media/hantro/hantro_drv.c @@ -56,6 +56,10 @@ dma_addr_t hantro_get_ref(struct hantro_ctx *ctx, u64 ts) return hantro_get_dec_buf_addr(ctx, buf); } +static const struct v4l2_event hantro_eos_event = { + .type = V4L2_EVENT_EOS +}; + static void hantro_job_finish_no_pm(struct hantro_dev *vpu, struct hantro_ctx *ctx, enum vb2_buffer_state result) @@ -73,6 +77,12 @@ static void hantro_job_finish_no_pm(struct hantro_dev *vpu, src->sequence = ctx->sequence_out++; dst->sequence = ctx->sequence_cap++; + if (v4l2_m2m_is_last_draining_src_buf(ctx->fh.m2m_ctx, src)) { + dst->flags |= V4L2_BUF_FLAG_LAST; + v4l2_event_queue_fh(&ctx->fh, &hantro_eos_event); + v4l2_m2m_mark_stopped(ctx->fh.m2m_ctx); + } + v4l2_m2m_buf_done_and_job_finish(ctx->dev->m2m_dev, ctx->fh.m2m_ctx, result); } @@ -628,6 +638,7 @@ static const struct of_device_id of_hantro_match[] = { { .compatible = "rockchip,rk3288-vpu", .data = &rk3288_vpu_variant, }, { .compatible = "rockchip,rk3328-vpu", .data = &rk3328_vpu_variant, }, { .compatible = "rockchip,rk3399-vpu", .data = &rk3399_vpu_variant, }, + { .compatible = "rockchip,rk3568-vpu", .data = &rk3568_vpu_variant, }, #endif #ifdef CONFIG_VIDEO_HANTRO_IMX8M { .compatible = "nxp,imx8mm-vpu-g1", .data = &imx8mm_vpu_g1_variant, }, @@ -809,10 +820,13 @@ static int hantro_add_func(struct hantro_dev *vpu, unsigned int funcid) snprintf(vfd->name, sizeof(vfd->name), "%s-%s", match->compatible, funcid == MEDIA_ENT_F_PROC_VIDEO_ENCODER ? "enc" : "dec"); - if (funcid == MEDIA_ENT_F_PROC_VIDEO_ENCODER) + if (funcid == MEDIA_ENT_F_PROC_VIDEO_ENCODER) { vpu->encoder = func; - else + } else { vpu->decoder = func; + v4l2_disable_ioctl(vfd, VIDIOC_TRY_ENCODER_CMD); + v4l2_disable_ioctl(vfd, VIDIOC_ENCODER_CMD); + } video_set_drvdata(vfd, vpu); diff --git a/drivers/staging/media/hantro/hantro_g1_h264_dec.c b/drivers/staging/media/hantro/hantro_g1_h264_dec.c index f49dbfb8a843..9de7f05eff2a 100644 --- a/drivers/staging/media/hantro/hantro_g1_h264_dec.c +++ b/drivers/staging/media/hantro/hantro_g1_h264_dec.c @@ -126,7 +126,7 @@ static void set_params(struct hantro_ctx *ctx, struct vb2_v4l2_buffer *src_buf) static void set_ref(struct hantro_ctx *ctx) { - const u8 *b0_reflist, *b1_reflist, *p_reflist; + const struct v4l2_h264_reference *b0_reflist, *b1_reflist, *p_reflist; struct hantro_dev *vpu = ctx->dev; int reg_num; u32 reg; @@ -157,12 +157,12 @@ static void set_ref(struct hantro_ctx *ctx) */ reg_num = 0; for (i = 0; i < 15; i += 3) { - reg = G1_REG_BD_REF_PIC_BINIT_RLIST_F0(b0_reflist[i]) | - G1_REG_BD_REF_PIC_BINIT_RLIST_F1(b0_reflist[i + 1]) | - G1_REG_BD_REF_PIC_BINIT_RLIST_F2(b0_reflist[i + 2]) | - G1_REG_BD_REF_PIC_BINIT_RLIST_B0(b1_reflist[i]) | - G1_REG_BD_REF_PIC_BINIT_RLIST_B1(b1_reflist[i + 1]) | - G1_REG_BD_REF_PIC_BINIT_RLIST_B2(b1_reflist[i + 2]); + reg = G1_REG_BD_REF_PIC_BINIT_RLIST_F0(b0_reflist[i].index) | + G1_REG_BD_REF_PIC_BINIT_RLIST_F1(b0_reflist[i + 1].index) | + G1_REG_BD_REF_PIC_BINIT_RLIST_F2(b0_reflist[i + 2].index) | + G1_REG_BD_REF_PIC_BINIT_RLIST_B0(b1_reflist[i].index) | + G1_REG_BD_REF_PIC_BINIT_RLIST_B1(b1_reflist[i + 1].index) | + G1_REG_BD_REF_PIC_BINIT_RLIST_B2(b1_reflist[i + 2].index); vdpu_write_relaxed(vpu, reg, G1_REG_BD_REF_PIC(reg_num++)); } @@ -171,12 +171,12 @@ static void set_ref(struct hantro_ctx *ctx) * of forward and backward reference picture lists and first 4 entries * of P forward picture list. */ - reg = G1_REG_BD_P_REF_PIC_BINIT_RLIST_F15(b0_reflist[15]) | - G1_REG_BD_P_REF_PIC_BINIT_RLIST_B15(b1_reflist[15]) | - G1_REG_BD_P_REF_PIC_PINIT_RLIST_F0(p_reflist[0]) | - G1_REG_BD_P_REF_PIC_PINIT_RLIST_F1(p_reflist[1]) | - G1_REG_BD_P_REF_PIC_PINIT_RLIST_F2(p_reflist[2]) | - G1_REG_BD_P_REF_PIC_PINIT_RLIST_F3(p_reflist[3]); + reg = G1_REG_BD_P_REF_PIC_BINIT_RLIST_F15(b0_reflist[15].index) | + G1_REG_BD_P_REF_PIC_BINIT_RLIST_B15(b1_reflist[15].index) | + G1_REG_BD_P_REF_PIC_PINIT_RLIST_F0(p_reflist[0].index) | + G1_REG_BD_P_REF_PIC_PINIT_RLIST_F1(p_reflist[1].index) | + G1_REG_BD_P_REF_PIC_PINIT_RLIST_F2(p_reflist[2].index) | + G1_REG_BD_P_REF_PIC_PINIT_RLIST_F3(p_reflist[3].index); vdpu_write_relaxed(vpu, reg, G1_REG_BD_P_REF_PIC); /* @@ -185,12 +185,12 @@ static void set_ref(struct hantro_ctx *ctx) */ reg_num = 0; for (i = 4; i < HANTRO_H264_DPB_SIZE; i += 6) { - reg = G1_REG_FWD_PIC_PINIT_RLIST_F0(p_reflist[i]) | - G1_REG_FWD_PIC_PINIT_RLIST_F1(p_reflist[i + 1]) | - G1_REG_FWD_PIC_PINIT_RLIST_F2(p_reflist[i + 2]) | - G1_REG_FWD_PIC_PINIT_RLIST_F3(p_reflist[i + 3]) | - G1_REG_FWD_PIC_PINIT_RLIST_F4(p_reflist[i + 4]) | - G1_REG_FWD_PIC_PINIT_RLIST_F5(p_reflist[i + 5]); + reg = G1_REG_FWD_PIC_PINIT_RLIST_F0(p_reflist[i].index) | + G1_REG_FWD_PIC_PINIT_RLIST_F1(p_reflist[i + 1].index) | + G1_REG_FWD_PIC_PINIT_RLIST_F2(p_reflist[i + 2].index) | + G1_REG_FWD_PIC_PINIT_RLIST_F3(p_reflist[i + 3].index) | + G1_REG_FWD_PIC_PINIT_RLIST_F4(p_reflist[i + 4].index) | + G1_REG_FWD_PIC_PINIT_RLIST_F5(p_reflist[i + 5].index); vdpu_write_relaxed(vpu, reg, G1_REG_FWD_PIC(reg_num++)); } diff --git a/drivers/staging/media/hantro/hantro_g2_hevc_dec.c b/drivers/staging/media/hantro/hantro_g2_hevc_dec.c index c524af41baf5..5df6f08e26f5 100644 --- a/drivers/staging/media/hantro/hantro_g2_hevc_dec.c +++ b/drivers/staging/media/hantro/hantro_g2_hevc_dec.c @@ -8,6 +8,20 @@ #include "hantro_hw.h" #include "hantro_g2_regs.h" +#define G2_ALIGN 16 + +static size_t hantro_hevc_chroma_offset(struct hantro_ctx *ctx) +{ + return ctx->dst_fmt.width * ctx->dst_fmt.height; +} + +static size_t hantro_hevc_motion_vectors_offset(struct hantro_ctx *ctx) +{ + size_t cr_offset = hantro_hevc_chroma_offset(ctx); + + return ALIGN((cr_offset * 3) / 2, G2_ALIGN); +} + static void prepare_tile_info_buffer(struct hantro_ctx *ctx) { struct hantro_dev *vpu = ctx->dev; @@ -60,7 +74,7 @@ static void prepare_tile_info_buffer(struct hantro_ctx *ctx) no_chroma = 1; for (j = 0, tmp_w = 0; j < num_tile_cols - 1; j++) { tmp_w += pps->column_width_minus1[j] + 1; - *p++ = pps->column_width_minus1[j + 1]; + *p++ = pps->column_width_minus1[j] + 1; *p++ = h; if (i == 0 && h == 1 && ctb_size == 16) no_chroma = 1; @@ -180,13 +194,8 @@ static void set_params(struct hantro_ctx *ctx) hantro_reg_write(vpu, &g2_max_cu_qpd_depth, 0); } - if (pps->flags & V4L2_HEVC_PPS_FLAG_PPS_SLICE_CHROMA_QP_OFFSETS_PRESENT) { - hantro_reg_write(vpu, &g2_cb_qp_offset, pps->pps_cb_qp_offset); - hantro_reg_write(vpu, &g2_cr_qp_offset, pps->pps_cr_qp_offset); - } else { - hantro_reg_write(vpu, &g2_cb_qp_offset, 0); - hantro_reg_write(vpu, &g2_cr_qp_offset, 0); - } + hantro_reg_write(vpu, &g2_cb_qp_offset, pps->pps_cb_qp_offset); + hantro_reg_write(vpu, &g2_cr_qp_offset, pps->pps_cr_qp_offset); hantro_reg_write(vpu, &g2_filt_offset_beta, pps->pps_beta_offset_div2); hantro_reg_write(vpu, &g2_filt_offset_tc, pps->pps_tc_offset_div2); @@ -335,7 +344,6 @@ static void set_ref_pic_list(struct hantro_ctx *ctx) static int set_ref(struct hantro_ctx *ctx) { const struct hantro_hevc_dec_ctrls *ctrls = &ctx->hevc_dec.ctrls; - const struct v4l2_ctrl_hevc_sps *sps = ctrls->sps; const struct v4l2_ctrl_hevc_pps *pps = ctrls->pps; const struct v4l2_ctrl_hevc_decode_params *decode_params = ctrls->decode_params; const struct v4l2_hevc_dpb_entry *dpb = decode_params->dpb; @@ -343,8 +351,8 @@ static int set_ref(struct hantro_ctx *ctx) struct hantro_dev *vpu = ctx->dev; struct vb2_v4l2_buffer *vb2_dst; struct hantro_decoded_buffer *dst; - size_t cr_offset = hantro_hevc_chroma_offset(sps); - size_t mv_offset = hantro_hevc_motion_vectors_offset(sps); + size_t cr_offset = hantro_hevc_chroma_offset(ctx); + size_t mv_offset = hantro_hevc_motion_vectors_offset(ctx); u32 max_ref_frames; u16 dpb_longterm_e; static const struct hantro_reg cur_poc[] = { @@ -406,8 +414,8 @@ static int set_ref(struct hantro_ctx *ctx) set_ref_pic_list(ctx); - /* We will only keep the references picture that are still used */ - ctx->hevc_dec.ref_bufs_used = 0; + /* We will only keep the reference pictures that are still used */ + hantro_hevc_ref_init(ctx); /* Set up addresses of DPB buffers */ dpb_longterm_e = 0; @@ -448,8 +456,6 @@ static int set_ref(struct hantro_ctx *ctx) hantro_write_addr(vpu, G2_OUT_CHROMA_ADDR, chroma_addr); hantro_write_addr(vpu, G2_OUT_MV_ADDR, mv_addr); - hantro_hevc_ref_remove_unused(ctx); - for (; i < V4L2_HEVC_DPB_ENTRIES_NUM_MAX; i++) { hantro_write_addr(vpu, G2_REF_LUMA_ADDR(i), 0); hantro_write_addr(vpu, G2_REF_CHROMA_ADDR(i), 0); diff --git a/drivers/staging/media/hantro/hantro_g2_regs.h b/drivers/staging/media/hantro/hantro_g2_regs.h index b7c6f9877b9d..877d663a8181 100644 --- a/drivers/staging/media/hantro/hantro_g2_regs.h +++ b/drivers/staging/media/hantro/hantro_g2_regs.h @@ -290,6 +290,10 @@ #define g2_buswidth G2_DEC_REG(58, 8, 0x7) #define g2_max_burst G2_DEC_REG(58, 0, 0xff) +#define g2_down_scale_e G2_DEC_REG(184, 7, 0x1) +#define g2_down_scale_y G2_DEC_REG(184, 2, 0x3) +#define g2_down_scale_x G2_DEC_REG(184, 0, 0x3) + #define G2_REG_CONFIG G2_SWREG(58) #define G2_REG_CONFIG_DEC_CLK_GATE_E BIT(16) #define G2_REG_CONFIG_DEC_CLK_GATE_IDLE_E BIT(17) @@ -312,6 +316,8 @@ #define G2_TILE_FILTER_ADDR (G2_SWREG(179)) #define G2_TILE_SAO_ADDR (G2_SWREG(181)) #define G2_TILE_BSD_ADDR (G2_SWREG(183)) +#define G2_DS_DST (G2_SWREG(186)) +#define G2_DS_DST_CHR (G2_SWREG(188)) #define g2_strm_buffer_len G2_DEC_REG(258, 0, 0xffffffff) #define g2_strm_start_offset G2_DEC_REG(259, 0, 0xffffffff) diff --git a/drivers/staging/media/hantro/hantro_h264.c b/drivers/staging/media/hantro/hantro_h264.c index 0b4d2491be3b..4e9a0ecf5c13 100644 --- a/drivers/staging/media/hantro/hantro_h264.c +++ b/drivers/staging/media/hantro/hantro_h264.c @@ -22,6 +22,12 @@ #define POC_BUFFER_SIZE 34 #define SCALING_LIST_SIZE (6 * 16 + 2 * 64) +/* + * For valid and long term reference marking, index are reversed, so bit 31 + * indicates the status of the picture 0. + */ +#define REF_BIT(i) BIT(32 - 1 - (i)) + /* Data structure describing auxiliary buffer format. */ struct hantro_h264_dec_priv_tbl { u32 cabac_table[CABAC_INIT_BUFFER_SIZE]; @@ -227,6 +233,7 @@ static void prepare_table(struct hantro_ctx *ctx) { const struct hantro_h264_dec_ctrls *ctrls = &ctx->h264_dec.ctrls; const struct v4l2_ctrl_h264_decode_params *dec_param = ctrls->decode; + const struct v4l2_ctrl_h264_sps *sps = ctrls->sps; struct hantro_h264_dec_priv_tbl *tbl = ctx->h264_dec.priv.cpu; const struct v4l2_h264_dpb_entry *dpb = ctx->h264_dec.dpb; u32 dpb_longterm = 0; @@ -237,20 +244,45 @@ static void prepare_table(struct hantro_ctx *ctx) tbl->poc[i * 2] = dpb[i].top_field_order_cnt; tbl->poc[i * 2 + 1] = dpb[i].bottom_field_order_cnt; + if (!(dpb[i].flags & V4L2_H264_DPB_ENTRY_FLAG_VALID)) + continue; + /* * Set up bit maps of valid and long term DPBs. - * NOTE: The bits are reversed, i.e. MSb is DPB 0. + * NOTE: The bits are reversed, i.e. MSb is DPB 0. For frame + * decoding, bit 31 to 15 are used, while for field decoding, + * all bits are used, with bit 31 being a top field, 30 a bottom + * field and so on. */ - if (dpb[i].flags & V4L2_H264_DPB_ENTRY_FLAG_ACTIVE) - dpb_valid |= BIT(HANTRO_H264_DPB_SIZE - 1 - i); - if (dpb[i].flags & V4L2_H264_DPB_ENTRY_FLAG_LONG_TERM) - dpb_longterm |= BIT(HANTRO_H264_DPB_SIZE - 1 - i); + if (dec_param->flags & V4L2_H264_DECODE_PARAM_FLAG_FIELD_PIC) { + if (dpb[i].fields & V4L2_H264_TOP_FIELD_REF) + dpb_valid |= REF_BIT(i * 2); + + if (dpb[i].fields & V4L2_H264_BOTTOM_FIELD_REF) + dpb_valid |= REF_BIT(i * 2 + 1); + + if (dpb[i].flags & V4L2_H264_DPB_ENTRY_FLAG_LONG_TERM) { + dpb_longterm |= REF_BIT(i * 2); + dpb_longterm |= REF_BIT(i * 2 + 1); + } + } else { + dpb_valid |= REF_BIT(i); + + if (dpb[i].flags & V4L2_H264_DPB_ENTRY_FLAG_LONG_TERM) + dpb_longterm |= REF_BIT(i); + } + } + ctx->h264_dec.dpb_valid = dpb_valid; + ctx->h264_dec.dpb_longterm = dpb_longterm; + + if ((dec_param->flags & V4L2_H264_DECODE_PARAM_FLAG_FIELD_PIC) || + !(sps->flags & V4L2_H264_SPS_FLAG_MB_ADAPTIVE_FRAME_FIELD)) { + tbl->poc[32] = ctx->h264_dec.cur_poc; + tbl->poc[33] = 0; + } else { + tbl->poc[32] = dec_param->top_field_order_cnt; + tbl->poc[33] = dec_param->bottom_field_order_cnt; } - ctx->h264_dec.dpb_valid = dpb_valid << 16; - ctx->h264_dec.dpb_longterm = dpb_longterm << 16; - - tbl->poc[32] = dec_param->top_field_order_cnt; - tbl->poc[33] = dec_param->bottom_field_order_cnt; assemble_scaling_list(ctx); } @@ -258,8 +290,7 @@ static void prepare_table(struct hantro_ctx *ctx) static bool dpb_entry_match(const struct v4l2_h264_dpb_entry *a, const struct v4l2_h264_dpb_entry *b) { - return a->top_field_order_cnt == b->top_field_order_cnt && - a->bottom_field_order_cnt == b->bottom_field_order_cnt; + return a->reference_ts == b->reference_ts; } static void update_dpb(struct hantro_ctx *ctx) @@ -273,13 +304,13 @@ static void update_dpb(struct hantro_ctx *ctx) /* Disable all entries by default. */ for (i = 0; i < ARRAY_SIZE(ctx->h264_dec.dpb); i++) - ctx->h264_dec.dpb[i].flags &= ~V4L2_H264_DPB_ENTRY_FLAG_ACTIVE; + ctx->h264_dec.dpb[i].flags = 0; /* Try to match new DPB entries with existing ones by their POCs. */ for (i = 0; i < ARRAY_SIZE(dec_param->dpb); i++) { const struct v4l2_h264_dpb_entry *ndpb = &dec_param->dpb[i]; - if (!(ndpb->flags & V4L2_H264_DPB_ENTRY_FLAG_ACTIVE)) + if (!(ndpb->flags & V4L2_H264_DPB_ENTRY_FLAG_VALID)) continue; /* @@ -290,8 +321,7 @@ static void update_dpb(struct hantro_ctx *ctx) struct v4l2_h264_dpb_entry *cdpb; cdpb = &ctx->h264_dec.dpb[j]; - if (cdpb->flags & V4L2_H264_DPB_ENTRY_FLAG_ACTIVE || - !dpb_entry_match(cdpb, ndpb)) + if (!dpb_entry_match(cdpb, ndpb)) continue; *cdpb = *ndpb; @@ -328,6 +358,8 @@ dma_addr_t hantro_h264_get_ref_buf(struct hantro_ctx *ctx, { struct v4l2_h264_dpb_entry *dpb = ctx->h264_dec.dpb; dma_addr_t dma_addr = 0; + s32 cur_poc = ctx->h264_dec.cur_poc; + u32 flags; if (dpb[dpb_idx].flags & V4L2_H264_DPB_ENTRY_FLAG_ACTIVE) dma_addr = hantro_get_ref(ctx, dpb[dpb_idx].reference_ts); @@ -345,7 +377,12 @@ dma_addr_t hantro_h264_get_ref_buf(struct hantro_ctx *ctx, dma_addr = hantro_get_dec_buf_addr(ctx, buf); } - return dma_addr; + flags = dpb[dpb_idx].flags & V4L2_H264_DPB_ENTRY_FLAG_FIELD ? 0x2 : 0; + flags |= abs(dpb[dpb_idx].top_field_order_cnt - cur_poc) < + abs(dpb[dpb_idx].bottom_field_order_cnt - cur_poc) ? + 0x1 : 0; + + return dma_addr | flags; } u16 hantro_h264_get_ref_nbr(struct hantro_ctx *ctx, unsigned int dpb_idx) @@ -354,11 +391,50 @@ u16 hantro_h264_get_ref_nbr(struct hantro_ctx *ctx, unsigned int dpb_idx) if (!(dpb->flags & V4L2_H264_DPB_ENTRY_FLAG_ACTIVE)) return 0; - if (dpb->flags & V4L2_H264_DPB_ENTRY_FLAG_LONG_TERM) - return dpb->pic_num; return dpb->frame_num; } +/* + * Removes all references with the same parity as the current picture from the + * reference list. The remaining list will have references with the opposite + * parity. This is effectively a deduplication of references since each buffer + * stores two fields. For this reason, each buffer is found twice in the + * reference list. + * + * This technique has been chosen through trial and error. This simple approach + * resulted in the highest conformance score. Note that this method may suffer + * worse quality in the case an opposite reference frame has been lost. If this + * becomes a problem in the future, it should be possible to add a preprocessing + * to identify un-paired fields and avoid removing them. + */ +static void deduplicate_reflist(struct v4l2_h264_reflist_builder *b, + struct v4l2_h264_reference *reflist) +{ + int write_idx = 0; + int i; + + if (b->cur_pic_fields == V4L2_H264_FRAME_REF) { + write_idx = b->num_valid; + goto done; + } + + for (i = 0; i < b->num_valid; i++) { + if (!(b->cur_pic_fields == reflist[i].fields)) { + reflist[write_idx++] = reflist[i]; + continue; + } + } + +done: + /* Should not happen unless we have a bug in the reflist builder. */ + if (WARN_ON(write_idx > 16)) + write_idx = 16; + + /* Clear the remaining, some streams fails otherwise */ + for (; write_idx < 16; write_idx++) + reflist[write_idx].index = 15; +} + int hantro_h264_dec_prepare_run(struct hantro_ctx *ctx) { struct hantro_h264_dec_hw_ctx *h264_ctx = &ctx->h264_dec; @@ -390,15 +466,29 @@ int hantro_h264_dec_prepare_run(struct hantro_ctx *ctx) /* Update the DPB with new refs. */ update_dpb(ctx); - /* Prepare data in memory. */ - prepare_table(ctx); - /* Build the P/B{0,1} ref lists. */ v4l2_h264_init_reflist_builder(&reflist_builder, ctrls->decode, ctrls->sps, ctx->h264_dec.dpb); + h264_ctx->cur_poc = reflist_builder.cur_pic_order_count; + + /* Prepare data in memory. */ + prepare_table(ctx); + v4l2_h264_build_p_ref_list(&reflist_builder, h264_ctx->reflists.p); v4l2_h264_build_b_ref_lists(&reflist_builder, h264_ctx->reflists.b0, h264_ctx->reflists.b1); + + /* + * Reduce ref lists to at most 16 entries, Hantro hardware will deduce + * the actual picture lists in field through the dpb_valid, + * dpb_longterm bitmap along with the current frame parity. + */ + if (reflist_builder.cur_pic_fields != V4L2_H264_FRAME_REF) { + deduplicate_reflist(&reflist_builder, h264_ctx->reflists.p); + deduplicate_reflist(&reflist_builder, h264_ctx->reflists.b0); + deduplicate_reflist(&reflist_builder, h264_ctx->reflists.b1); + } + return 0; } diff --git a/drivers/staging/media/hantro/hantro_hevc.c b/drivers/staging/media/hantro/hantro_hevc.c index b49a41d7ae91..f86c98e19177 100644 --- a/drivers/staging/media/hantro/hantro_hevc.c +++ b/drivers/staging/media/hantro/hantro_hevc.c @@ -25,32 +25,11 @@ #define MAX_TILE_COLS 20 #define MAX_TILE_ROWS 22 -#define UNUSED_REF -1 - -#define G2_ALIGN 16 - -size_t hantro_hevc_chroma_offset(const struct v4l2_ctrl_hevc_sps *sps) -{ - int bytes_per_pixel = sps->bit_depth_luma_minus8 == 0 ? 1 : 2; - - return sps->pic_width_in_luma_samples * - sps->pic_height_in_luma_samples * bytes_per_pixel; -} - -size_t hantro_hevc_motion_vectors_offset(const struct v4l2_ctrl_hevc_sps *sps) -{ - size_t cr_offset = hantro_hevc_chroma_offset(sps); - - return ALIGN((cr_offset * 3) / 2, G2_ALIGN); -} - -static void hantro_hevc_ref_init(struct hantro_ctx *ctx) +void hantro_hevc_ref_init(struct hantro_ctx *ctx) { struct hantro_hevc_dec_hw_ctx *hevc_dec = &ctx->hevc_dec; - int i; - for (i = 0; i < NUM_REF_PICTURES; i++) - hevc_dec->ref_bufs_poc[i] = UNUSED_REF; + hevc_dec->ref_bufs_used = 0; } dma_addr_t hantro_hevc_get_ref_buf(struct hantro_ctx *ctx, @@ -59,7 +38,7 @@ dma_addr_t hantro_hevc_get_ref_buf(struct hantro_ctx *ctx, struct hantro_hevc_dec_hw_ctx *hevc_dec = &ctx->hevc_dec; int i; - /* Find the reference buffer in already know ones */ + /* Find the reference buffer in already known ones */ for (i = 0; i < NUM_REF_PICTURES; i++) { if (hevc_dec->ref_bufs_poc[i] == poc) { hevc_dec->ref_bufs_used |= 1 << i; @@ -77,7 +56,7 @@ int hantro_hevc_add_ref_buf(struct hantro_ctx *ctx, int poc, dma_addr_t addr) /* Add a new reference buffer */ for (i = 0; i < NUM_REF_PICTURES; i++) { - if (hevc_dec->ref_bufs_poc[i] == UNUSED_REF) { + if (!(hevc_dec->ref_bufs_used & 1 << i)) { hevc_dec->ref_bufs_used |= 1 << i; hevc_dec->ref_bufs_poc[i] = poc; hevc_dec->ref_bufs[i].dma = addr; @@ -88,23 +67,6 @@ int hantro_hevc_add_ref_buf(struct hantro_ctx *ctx, int poc, dma_addr_t addr) return -EINVAL; } -void hantro_hevc_ref_remove_unused(struct hantro_ctx *ctx) -{ - struct hantro_hevc_dec_hw_ctx *hevc_dec = &ctx->hevc_dec; - int i; - - /* Just tag buffer as unused, do not free them */ - for (i = 0; i < NUM_REF_PICTURES; i++) { - if (hevc_dec->ref_bufs_poc[i] == UNUSED_REF) - continue; - - if (hevc_dec->ref_bufs_used & (1 << i)) - continue; - - hevc_dec->ref_bufs_poc[i] = UNUSED_REF; - } -} - static int tile_buffer_reallocate(struct hantro_ctx *ctx) { struct hantro_dev *vpu = ctx->dev; diff --git a/drivers/staging/media/hantro/hantro_hw.h b/drivers/staging/media/hantro/hantro_hw.h index ed018e293ba0..52a960f6fa4a 100644 --- a/drivers/staging/media/hantro/hantro_hw.h +++ b/drivers/staging/media/hantro/hantro_hw.h @@ -69,9 +69,9 @@ struct hantro_h264_dec_ctrls { * @b1: B1 reflist */ struct hantro_h264_dec_reflists { - u8 p[HANTRO_H264_DPB_SIZE]; - u8 b0[HANTRO_H264_DPB_SIZE]; - u8 b1[HANTRO_H264_DPB_SIZE]; + struct v4l2_h264_reference p[V4L2_H264_REF_LIST_LEN]; + struct v4l2_h264_reference b0[V4L2_H264_REF_LIST_LEN]; + struct v4l2_h264_reference b1[V4L2_H264_REF_LIST_LEN]; }; /** @@ -83,6 +83,7 @@ struct hantro_h264_dec_reflists { * @ctrls: V4L2 controls attached to a run * @dpb_longterm: DPB long-term * @dpb_valid: DPB valid + * @cur_poc: Current picture order count */ struct hantro_h264_dec_hw_ctx { struct hantro_aux_buf priv; @@ -91,6 +92,7 @@ struct hantro_h264_dec_hw_ctx { struct hantro_h264_dec_ctrls ctrls; u32 dpb_longterm; u32 dpb_valid; + s32 cur_poc; }; /** @@ -245,12 +247,16 @@ struct hantro_postproc_ctx { /** * struct hantro_postproc_ops - post-processor operations * - * @enable: Enable the post-processor block. Optional. - * @disable: Disable the post-processor block. Optional. + * @enable: Enable the post-processor block. Optional. + * @disable: Disable the post-processor block. Optional. + * @enum_framesizes: Enumerate possible scaled output formats. + * Returns zero if OK, a negative value in error cases. + * Optional. */ struct hantro_postproc_ops { void (*enable)(struct hantro_ctx *ctx); void (*disable)(struct hantro_ctx *ctx); + int (*enum_framesizes)(struct hantro_ctx *ctx, struct v4l2_frmsizeenum *fsize); }; /** @@ -300,6 +306,7 @@ extern const struct hantro_variant rk3066_vpu_variant; extern const struct hantro_variant rk3288_vpu_variant; extern const struct hantro_variant rk3328_vpu_variant; extern const struct hantro_variant rk3399_vpu_variant; +extern const struct hantro_variant rk3568_vpu_variant; extern const struct hantro_variant sama5d4_vdec_variant; extern const struct hantro_variant sunxi_vpu_variant; @@ -337,11 +344,9 @@ int hantro_hevc_dec_init(struct hantro_ctx *ctx); void hantro_hevc_dec_exit(struct hantro_ctx *ctx); int hantro_g2_hevc_dec_run(struct hantro_ctx *ctx); int hantro_hevc_dec_prepare_run(struct hantro_ctx *ctx); +void hantro_hevc_ref_init(struct hantro_ctx *ctx); dma_addr_t hantro_hevc_get_ref_buf(struct hantro_ctx *ctx, int poc); int hantro_hevc_add_ref_buf(struct hantro_ctx *ctx, int poc, dma_addr_t addr); -void hantro_hevc_ref_remove_unused(struct hantro_ctx *ctx); -size_t hantro_hevc_chroma_offset(const struct v4l2_ctrl_hevc_sps *sps); -size_t hantro_hevc_motion_vectors_offset(const struct v4l2_ctrl_hevc_sps *sps); static inline unsigned short hantro_vp9_num_sbs(unsigned short dimension) { diff --git a/drivers/staging/media/hantro/hantro_postproc.c b/drivers/staging/media/hantro/hantro_postproc.c index 248abe5423f0..ab168c1c0d28 100644 --- a/drivers/staging/media/hantro/hantro_postproc.c +++ b/drivers/staging/media/hantro/hantro_postproc.c @@ -100,21 +100,58 @@ static void hantro_postproc_g1_enable(struct hantro_ctx *ctx) HANTRO_PP_REG_WRITE(vpu, display_width, ctx->dst_fmt.width); } +static int down_scale_factor(struct hantro_ctx *ctx) +{ + if (ctx->src_fmt.width == ctx->dst_fmt.width) + return 0; + + return DIV_ROUND_CLOSEST(ctx->src_fmt.width, ctx->dst_fmt.width); +} + static void hantro_postproc_g2_enable(struct hantro_ctx *ctx) { struct hantro_dev *vpu = ctx->dev; struct vb2_v4l2_buffer *dst_buf; size_t chroma_offset = ctx->dst_fmt.width * ctx->dst_fmt.height; + int down_scale = down_scale_factor(ctx); dma_addr_t dst_dma; dst_buf = hantro_get_dst_buf(ctx); dst_dma = vb2_dma_contig_plane_dma_addr(&dst_buf->vb2_buf, 0); - hantro_write_addr(vpu, G2_RS_OUT_LUMA_ADDR, dst_dma); - hantro_write_addr(vpu, G2_RS_OUT_CHROMA_ADDR, dst_dma + chroma_offset); + if (down_scale) { + hantro_reg_write(vpu, &g2_down_scale_e, 1); + hantro_reg_write(vpu, &g2_down_scale_y, down_scale >> 2); + hantro_reg_write(vpu, &g2_down_scale_x, down_scale >> 2); + hantro_write_addr(vpu, G2_DS_DST, dst_dma); + hantro_write_addr(vpu, G2_DS_DST_CHR, dst_dma + (chroma_offset >> down_scale)); + } else { + hantro_write_addr(vpu, G2_RS_OUT_LUMA_ADDR, dst_dma); + hantro_write_addr(vpu, G2_RS_OUT_CHROMA_ADDR, dst_dma + chroma_offset); + } hantro_reg_write(vpu, &g2_out_rs_e, 1); } +static int hantro_postproc_g2_enum_framesizes(struct hantro_ctx *ctx, + struct v4l2_frmsizeenum *fsize) +{ + /** + * G2 scaler can scale down by 0, 2, 4 or 8 + * use fsize->index has power of 2 diviser + **/ + if (fsize->index > 3) + return -EINVAL; + + if (!ctx->src_fmt.width || !ctx->src_fmt.height) + return -EINVAL; + + fsize->type = V4L2_FRMSIZE_TYPE_DISCRETE; + fsize->discrete.width = ctx->src_fmt.width >> fsize->index; + fsize->discrete.height = ctx->src_fmt.height >> fsize->index; + + return 0; +} + void hantro_postproc_free(struct hantro_ctx *ctx) { struct hantro_dev *vpu = ctx->dev; @@ -197,6 +234,17 @@ void hantro_postproc_enable(struct hantro_ctx *ctx) vpu->variant->postproc_ops->enable(ctx); } +int hanto_postproc_enum_framesizes(struct hantro_ctx *ctx, + struct v4l2_frmsizeenum *fsize) +{ + struct hantro_dev *vpu = ctx->dev; + + if (vpu->variant->postproc_ops && vpu->variant->postproc_ops->enum_framesizes) + return vpu->variant->postproc_ops->enum_framesizes(ctx, fsize); + + return -EINVAL; +} + const struct hantro_postproc_ops hantro_g1_postproc_ops = { .enable = hantro_postproc_g1_enable, .disable = hantro_postproc_g1_disable, @@ -205,4 +253,5 @@ const struct hantro_postproc_ops hantro_g1_postproc_ops = { const struct hantro_postproc_ops hantro_g2_postproc_ops = { .enable = hantro_postproc_g2_enable, .disable = hantro_postproc_g2_disable, + .enum_framesizes = hantro_postproc_g2_enum_framesizes, }; diff --git a/drivers/staging/media/hantro/hantro_v4l2.c b/drivers/staging/media/hantro/hantro_v4l2.c index 67148ba346f5..22ad182ee972 100644 --- a/drivers/staging/media/hantro/hantro_v4l2.c +++ b/drivers/staging/media/hantro/hantro_v4l2.c @@ -116,12 +116,6 @@ static int vidioc_enum_framesizes(struct file *file, void *priv, struct hantro_ctx *ctx = fh_to_ctx(priv); const struct hantro_fmt *fmt; - if (fsize->index != 0) { - vpu_debug(0, "invalid frame size index (expected 0, got %d)\n", - fsize->index); - return -EINVAL; - } - fmt = hantro_find_format(ctx, fsize->pixel_format); if (!fmt) { vpu_debug(0, "unsupported bitstream format (%08x)\n", @@ -129,9 +123,14 @@ static int vidioc_enum_framesizes(struct file *file, void *priv, return -EINVAL; } - /* This only makes sense for coded formats */ - if (fmt->codec_mode == HANTRO_MODE_NONE) + /* For non-coded formats check if postprocessing scaling is possible */ + if (fmt->codec_mode == HANTRO_MODE_NONE && hantro_needs_postproc(ctx, fmt)) { + return hanto_postproc_enum_framesizes(ctx, fsize); + } else if (fsize->index != 0) { + vpu_debug(0, "invalid frame size index (expected 0, got %d)\n", + fsize->index); return -EINVAL; + } fsize->type = V4L2_FRMSIZE_TYPE_STEPWISE; fsize->stepwise = fmt->frmsize; @@ -409,6 +408,30 @@ hantro_update_requires_request(struct hantro_ctx *ctx, u32 fourcc) } } +static void +hantro_update_requires_hold_capture_buf(struct hantro_ctx *ctx, u32 fourcc) +{ + struct vb2_queue *vq; + + vq = v4l2_m2m_get_vq(ctx->fh.m2m_ctx, + V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE); + + switch (fourcc) { + case V4L2_PIX_FMT_JPEG: + case V4L2_PIX_FMT_MPEG2_SLICE: + case V4L2_PIX_FMT_VP8_FRAME: + case V4L2_PIX_FMT_HEVC_SLICE: + case V4L2_PIX_FMT_VP9_FRAME: + vq->subsystem_flags &= ~(VB2_V4L2_FL_SUPPORTS_M2M_HOLD_CAPTURE_BUF); + break; + case V4L2_PIX_FMT_H264_SLICE: + vq->subsystem_flags |= VB2_V4L2_FL_SUPPORTS_M2M_HOLD_CAPTURE_BUF; + break; + default: + break; + } +} + static int hantro_set_fmt_out(struct hantro_ctx *ctx, struct v4l2_pix_format_mplane *pix_mp) { @@ -472,6 +495,7 @@ static int hantro_set_fmt_out(struct hantro_ctx *ctx, ctx->dst_fmt.quantization = pix_mp->quantization; hantro_update_requires_request(ctx, pix_mp->pixelformat); + hantro_update_requires_hold_capture_buf(ctx, pix_mp->pixelformat); vpu_debug(0, "OUTPUT codec mode: %d\n", ctx->vpu_src_fmt->codec_mode); vpu_debug(0, "fmt - w: %d, h: %d\n", @@ -628,6 +652,38 @@ static int vidioc_s_selection(struct file *file, void *priv, return 0; } +static const struct v4l2_event hantro_eos_event = { + .type = V4L2_EVENT_EOS +}; + +static int vidioc_encoder_cmd(struct file *file, void *priv, + struct v4l2_encoder_cmd *ec) +{ + struct hantro_ctx *ctx = fh_to_ctx(priv); + int ret; + + ret = v4l2_m2m_ioctl_try_encoder_cmd(file, priv, ec); + if (ret < 0) + return ret; + + if (!vb2_is_streaming(v4l2_m2m_get_src_vq(ctx->fh.m2m_ctx)) || + !vb2_is_streaming(v4l2_m2m_get_dst_vq(ctx->fh.m2m_ctx))) + return 0; + + ret = v4l2_m2m_ioctl_encoder_cmd(file, priv, ec); + if (ret < 0) + return ret; + + if (ec->cmd == V4L2_ENC_CMD_STOP && + v4l2_m2m_has_stopped(ctx->fh.m2m_ctx)) + v4l2_event_queue_fh(&ctx->fh, &hantro_eos_event); + + if (ec->cmd == V4L2_ENC_CMD_START) + vb2_clear_last_buffer_dequeued(&ctx->fh.m2m_ctx->cap_q_ctx.q); + + return 0; +} + const struct v4l2_ioctl_ops hantro_ioctl_ops = { .vidioc_querycap = vidioc_querycap, .vidioc_enum_framesizes = vidioc_enum_framesizes, @@ -657,6 +713,9 @@ const struct v4l2_ioctl_ops hantro_ioctl_ops = { .vidioc_g_selection = vidioc_g_selection, .vidioc_s_selection = vidioc_s_selection, + + .vidioc_try_encoder_cmd = v4l2_m2m_ioctl_try_encoder_cmd, + .vidioc_encoder_cmd = vidioc_encoder_cmd, }; static int @@ -733,8 +792,12 @@ static int hantro_buf_prepare(struct vb2_buffer *vb) * (for OUTPUT buffers, if userspace passes 0 bytesused, v4l2-core sets * it to buffer length). */ - if (V4L2_TYPE_IS_CAPTURE(vq->type)) - vb2_set_plane_payload(vb, 0, pix_fmt->plane_fmt[0].sizeimage); + if (V4L2_TYPE_IS_CAPTURE(vq->type)) { + if (ctx->is_encoder) + vb2_set_plane_payload(vb, 0, 0); + else + vb2_set_plane_payload(vb, 0, pix_fmt->plane_fmt[0].sizeimage); + } return 0; } @@ -744,6 +807,22 @@ static void hantro_buf_queue(struct vb2_buffer *vb) struct hantro_ctx *ctx = vb2_get_drv_priv(vb->vb2_queue); struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb); + if (V4L2_TYPE_IS_CAPTURE(vb->vb2_queue->type) && + vb2_is_streaming(vb->vb2_queue) && + v4l2_m2m_dst_buf_is_last(ctx->fh.m2m_ctx)) { + unsigned int i; + + for (i = 0; i < vb->num_planes; i++) + vb2_set_plane_payload(vb, i, 0); + + vbuf->field = V4L2_FIELD_NONE; + vbuf->sequence = ctx->sequence_cap++; + + v4l2_m2m_last_buffer_done(ctx->fh.m2m_ctx, vbuf); + v4l2_event_queue_fh(&ctx->fh, &hantro_eos_event); + return; + } + v4l2_m2m_buf_queue(ctx->fh.m2m_ctx, vbuf); } @@ -759,6 +838,8 @@ static int hantro_start_streaming(struct vb2_queue *q, unsigned int count) struct hantro_ctx *ctx = vb2_get_drv_priv(q); int ret = 0; + v4l2_m2m_update_start_streaming_state(ctx->fh.m2m_ctx, q); + if (V4L2_TYPE_IS_OUTPUT(q->type)) ctx->sequence_out = 0; else @@ -831,6 +912,12 @@ static void hantro_stop_streaming(struct vb2_queue *q) hantro_return_bufs(q, v4l2_m2m_src_buf_remove); else hantro_return_bufs(q, v4l2_m2m_dst_buf_remove); + + v4l2_m2m_update_stop_streaming_state(ctx->fh.m2m_ctx, q); + + if (V4L2_TYPE_IS_OUTPUT(q->type) && + v4l2_m2m_has_stopped(ctx->fh.m2m_ctx)) + v4l2_event_queue_fh(&ctx->fh, &hantro_eos_event); } static void hantro_buf_request_complete(struct vb2_buffer *vb) diff --git a/drivers/staging/media/hantro/rockchip_vpu2_hw_h264_dec.c b/drivers/staging/media/hantro/rockchip_vpu2_hw_h264_dec.c index 64a6330475eb..46c1a83bcc4e 100644 --- a/drivers/staging/media/hantro/rockchip_vpu2_hw_h264_dec.c +++ b/drivers/staging/media/hantro/rockchip_vpu2_hw_h264_dec.c @@ -298,7 +298,7 @@ static void set_params(struct hantro_ctx *ctx, struct vb2_v4l2_buffer *src_buf) static void set_ref(struct hantro_ctx *ctx) { - const u8 *b0_reflist, *b1_reflist, *p_reflist; + const struct v4l2_h264_reference *b0_reflist, *b1_reflist, *p_reflist; struct hantro_dev *vpu = ctx->dev; u32 reg; int i; @@ -307,20 +307,20 @@ static void set_ref(struct hantro_ctx *ctx) b1_reflist = ctx->h264_dec.reflists.b1; p_reflist = ctx->h264_dec.reflists.p; - reg = VDPU_REG_PINIT_RLIST_F9(p_reflist[9]) | - VDPU_REG_PINIT_RLIST_F8(p_reflist[8]) | - VDPU_REG_PINIT_RLIST_F7(p_reflist[7]) | - VDPU_REG_PINIT_RLIST_F6(p_reflist[6]) | - VDPU_REG_PINIT_RLIST_F5(p_reflist[5]) | - VDPU_REG_PINIT_RLIST_F4(p_reflist[4]); + reg = VDPU_REG_PINIT_RLIST_F9(p_reflist[9].index) | + VDPU_REG_PINIT_RLIST_F8(p_reflist[8].index) | + VDPU_REG_PINIT_RLIST_F7(p_reflist[7].index) | + VDPU_REG_PINIT_RLIST_F6(p_reflist[6].index) | + VDPU_REG_PINIT_RLIST_F5(p_reflist[5].index) | + VDPU_REG_PINIT_RLIST_F4(p_reflist[4].index); vdpu_write_relaxed(vpu, reg, VDPU_SWREG(74)); - reg = VDPU_REG_PINIT_RLIST_F15(p_reflist[15]) | - VDPU_REG_PINIT_RLIST_F14(p_reflist[14]) | - VDPU_REG_PINIT_RLIST_F13(p_reflist[13]) | - VDPU_REG_PINIT_RLIST_F12(p_reflist[12]) | - VDPU_REG_PINIT_RLIST_F11(p_reflist[11]) | - VDPU_REG_PINIT_RLIST_F10(p_reflist[10]); + reg = VDPU_REG_PINIT_RLIST_F15(p_reflist[15].index) | + VDPU_REG_PINIT_RLIST_F14(p_reflist[14].index) | + VDPU_REG_PINIT_RLIST_F13(p_reflist[13].index) | + VDPU_REG_PINIT_RLIST_F12(p_reflist[12].index) | + VDPU_REG_PINIT_RLIST_F11(p_reflist[11].index) | + VDPU_REG_PINIT_RLIST_F10(p_reflist[10].index); vdpu_write_relaxed(vpu, reg, VDPU_SWREG(75)); reg = VDPU_REG_REFER1_NBR(hantro_h264_get_ref_nbr(ctx, 1)) | @@ -355,54 +355,54 @@ static void set_ref(struct hantro_ctx *ctx) VDPU_REG_REFER14_NBR(hantro_h264_get_ref_nbr(ctx, 14)); vdpu_write_relaxed(vpu, reg, VDPU_SWREG(83)); - reg = VDPU_REG_BINIT_RLIST_F5(b0_reflist[5]) | - VDPU_REG_BINIT_RLIST_F4(b0_reflist[4]) | - VDPU_REG_BINIT_RLIST_F3(b0_reflist[3]) | - VDPU_REG_BINIT_RLIST_F2(b0_reflist[2]) | - VDPU_REG_BINIT_RLIST_F1(b0_reflist[1]) | - VDPU_REG_BINIT_RLIST_F0(b0_reflist[0]); + reg = VDPU_REG_BINIT_RLIST_F5(b0_reflist[5].index) | + VDPU_REG_BINIT_RLIST_F4(b0_reflist[4].index) | + VDPU_REG_BINIT_RLIST_F3(b0_reflist[3].index) | + VDPU_REG_BINIT_RLIST_F2(b0_reflist[2].index) | + VDPU_REG_BINIT_RLIST_F1(b0_reflist[1].index) | + VDPU_REG_BINIT_RLIST_F0(b0_reflist[0].index); vdpu_write_relaxed(vpu, reg, VDPU_SWREG(100)); - reg = VDPU_REG_BINIT_RLIST_F11(b0_reflist[11]) | - VDPU_REG_BINIT_RLIST_F10(b0_reflist[10]) | - VDPU_REG_BINIT_RLIST_F9(b0_reflist[9]) | - VDPU_REG_BINIT_RLIST_F8(b0_reflist[8]) | - VDPU_REG_BINIT_RLIST_F7(b0_reflist[7]) | - VDPU_REG_BINIT_RLIST_F6(b0_reflist[6]); + reg = VDPU_REG_BINIT_RLIST_F11(b0_reflist[11].index) | + VDPU_REG_BINIT_RLIST_F10(b0_reflist[10].index) | + VDPU_REG_BINIT_RLIST_F9(b0_reflist[9].index) | + VDPU_REG_BINIT_RLIST_F8(b0_reflist[8].index) | + VDPU_REG_BINIT_RLIST_F7(b0_reflist[7].index) | + VDPU_REG_BINIT_RLIST_F6(b0_reflist[6].index); vdpu_write_relaxed(vpu, reg, VDPU_SWREG(101)); - reg = VDPU_REG_BINIT_RLIST_F15(b0_reflist[15]) | - VDPU_REG_BINIT_RLIST_F14(b0_reflist[14]) | - VDPU_REG_BINIT_RLIST_F13(b0_reflist[13]) | - VDPU_REG_BINIT_RLIST_F12(b0_reflist[12]); + reg = VDPU_REG_BINIT_RLIST_F15(b0_reflist[15].index) | + VDPU_REG_BINIT_RLIST_F14(b0_reflist[14].index) | + VDPU_REG_BINIT_RLIST_F13(b0_reflist[13].index) | + VDPU_REG_BINIT_RLIST_F12(b0_reflist[12].index); vdpu_write_relaxed(vpu, reg, VDPU_SWREG(102)); - reg = VDPU_REG_BINIT_RLIST_B5(b1_reflist[5]) | - VDPU_REG_BINIT_RLIST_B4(b1_reflist[4]) | - VDPU_REG_BINIT_RLIST_B3(b1_reflist[3]) | - VDPU_REG_BINIT_RLIST_B2(b1_reflist[2]) | - VDPU_REG_BINIT_RLIST_B1(b1_reflist[1]) | - VDPU_REG_BINIT_RLIST_B0(b1_reflist[0]); + reg = VDPU_REG_BINIT_RLIST_B5(b1_reflist[5].index) | + VDPU_REG_BINIT_RLIST_B4(b1_reflist[4].index) | + VDPU_REG_BINIT_RLIST_B3(b1_reflist[3].index) | + VDPU_REG_BINIT_RLIST_B2(b1_reflist[2].index) | + VDPU_REG_BINIT_RLIST_B1(b1_reflist[1].index) | + VDPU_REG_BINIT_RLIST_B0(b1_reflist[0].index); vdpu_write_relaxed(vpu, reg, VDPU_SWREG(103)); - reg = VDPU_REG_BINIT_RLIST_B11(b1_reflist[11]) | - VDPU_REG_BINIT_RLIST_B10(b1_reflist[10]) | - VDPU_REG_BINIT_RLIST_B9(b1_reflist[9]) | - VDPU_REG_BINIT_RLIST_B8(b1_reflist[8]) | - VDPU_REG_BINIT_RLIST_B7(b1_reflist[7]) | - VDPU_REG_BINIT_RLIST_B6(b1_reflist[6]); + reg = VDPU_REG_BINIT_RLIST_B11(b1_reflist[11].index) | + VDPU_REG_BINIT_RLIST_B10(b1_reflist[10].index) | + VDPU_REG_BINIT_RLIST_B9(b1_reflist[9].index) | + VDPU_REG_BINIT_RLIST_B8(b1_reflist[8].index) | + VDPU_REG_BINIT_RLIST_B7(b1_reflist[7].index) | + VDPU_REG_BINIT_RLIST_B6(b1_reflist[6].index); vdpu_write_relaxed(vpu, reg, VDPU_SWREG(104)); - reg = VDPU_REG_BINIT_RLIST_B15(b1_reflist[15]) | - VDPU_REG_BINIT_RLIST_B14(b1_reflist[14]) | - VDPU_REG_BINIT_RLIST_B13(b1_reflist[13]) | - VDPU_REG_BINIT_RLIST_B12(b1_reflist[12]); + reg = VDPU_REG_BINIT_RLIST_B15(b1_reflist[15].index) | + VDPU_REG_BINIT_RLIST_B14(b1_reflist[14].index) | + VDPU_REG_BINIT_RLIST_B13(b1_reflist[13].index) | + VDPU_REG_BINIT_RLIST_B12(b1_reflist[12].index); vdpu_write_relaxed(vpu, reg, VDPU_SWREG(105)); - reg = VDPU_REG_PINIT_RLIST_F3(p_reflist[3]) | - VDPU_REG_PINIT_RLIST_F2(p_reflist[2]) | - VDPU_REG_PINIT_RLIST_F1(p_reflist[1]) | - VDPU_REG_PINIT_RLIST_F0(p_reflist[0]); + reg = VDPU_REG_PINIT_RLIST_F3(p_reflist[3].index) | + VDPU_REG_PINIT_RLIST_F2(p_reflist[2].index) | + VDPU_REG_PINIT_RLIST_F1(p_reflist[1].index) | + VDPU_REG_PINIT_RLIST_F0(p_reflist[0].index); vdpu_write_relaxed(vpu, reg, VDPU_SWREG(106)); reg = VDPU_REG_REFER_LTERM_E(ctx->h264_dec.dpb_longterm); diff --git a/drivers/staging/media/hantro/rockchip_vpu_hw.c b/drivers/staging/media/hantro/rockchip_vpu_hw.c index 163cf92eafca..fc96501f3bc8 100644 --- a/drivers/staging/media/hantro/rockchip_vpu_hw.c +++ b/drivers/staging/media/hantro/rockchip_vpu_hw.c @@ -545,6 +545,20 @@ const struct hantro_variant rk3399_vpu_variant = { .num_clocks = ARRAY_SIZE(rockchip_vpu_clk_names) }; +const struct hantro_variant rk3568_vpu_variant = { + .dec_offset = 0x400, + .dec_fmts = rk3399_vpu_dec_fmts, + .num_dec_fmts = ARRAY_SIZE(rk3399_vpu_dec_fmts), + .codec = HANTRO_MPEG2_DECODER | + HANTRO_VP8_DECODER | HANTRO_H264_DECODER, + .codec_ops = rk3399_vpu_codec_ops, + .irqs = rockchip_vdpu2_irqs, + .num_irqs = ARRAY_SIZE(rockchip_vdpu2_irqs), + .init = rockchip_vpu_hw_init, + .clk_names = rockchip_vpu_clk_names, + .num_clocks = ARRAY_SIZE(rockchip_vpu_clk_names) +}; + const struct hantro_variant px30_vpu_variant = { .enc_offset = 0x0, .enc_fmts = rockchip_vpu_enc_fmts, diff --git a/drivers/staging/media/ipu3/ipu3-css-fw.c b/drivers/staging/media/ipu3/ipu3-css-fw.c index 981693eed815..2b659b0ccca1 100644 --- a/drivers/staging/media/ipu3/ipu3-css-fw.c +++ b/drivers/staging/media/ipu3/ipu3-css-fw.c @@ -117,7 +117,9 @@ int imgu_css_fw_init(struct imgu_css *css) unsigned int i, j, binary_nr; int r; - r = request_firmware(&css->fw, IMGU_FW_NAME, css->dev); + r = request_firmware(&css->fw, IMGU_FW_NAME_20161208, css->dev); + if (r == -ENOENT) + r = request_firmware(&css->fw, IMGU_FW_NAME, css->dev); if (r) return r; diff --git a/drivers/staging/media/ipu3/ipu3-css-fw.h b/drivers/staging/media/ipu3/ipu3-css-fw.h index c0bc57fd678a..f9403da75785 100644 --- a/drivers/staging/media/ipu3/ipu3-css-fw.h +++ b/drivers/staging/media/ipu3/ipu3-css-fw.h @@ -6,7 +6,9 @@ /******************* Firmware file definitions *******************/ -#define IMGU_FW_NAME "intel/ipu3-fw.bin" +#define IMGU_FW_NAME "intel/ipu3-fw.bin" +#define IMGU_FW_NAME_20161208 \ + "intel/irci_irci_ecr-master_20161208_0213_20170112_1500.bin" typedef u32 imgu_fw_ptr; diff --git a/drivers/staging/media/ipu3/ipu3-css-params.c b/drivers/staging/media/ipu3/ipu3-css-params.c index d9e3c3785075..76ad802d694e 100644 --- a/drivers/staging/media/ipu3/ipu3-css-params.c +++ b/drivers/staging/media/ipu3/ipu3-css-params.c @@ -2556,6 +2556,15 @@ int imgu_css_cfg_acc(struct imgu_css *css, unsigned int pipe, /* Enable only for rightmost stripe, disable left */ acc->af.stripes[0].grid_cfg.y_start &= ~IPU3_UAPI_GRID_Y_START_EN; + acc->af.stripes[1].grid_cfg.x_start = + (acc->af.stripes[1].grid_cfg.x_start - + acc->stripe.down_scaled_stripes[1].offset) & + IPU3_UAPI_GRID_START_MASK; + b_w_log2 = acc->af.stripes[1].grid_cfg.block_width_log2; + acc->af.stripes[1].grid_cfg.x_end = + imgu_css_grid_end(acc->af.stripes[1].grid_cfg.x_start, + acc->af.stripes[1].grid_cfg.width, + b_w_log2); } else if (acc->af.config.grid_cfg.x_end <= acc->stripe.bds_out_stripes[0].width - min_overlap) { /* Enable only for leftmost stripe, disable right */ @@ -2627,6 +2636,17 @@ int imgu_css_cfg_acc(struct imgu_css *css, unsigned int pipe, acc->stripe.down_scaled_stripes[1].offset + min_overlap) { /* Enable only for rightmost stripe, disable left */ acc->awb.stripes[0].rgbs_thr_b &= ~IPU3_UAPI_AWB_RGBS_THR_B_EN; + + acc->awb.stripes[1].grid.x_start = + (acc->awb.stripes[1].grid.x_start - + acc->stripe.down_scaled_stripes[1].offset) & + IPU3_UAPI_GRID_START_MASK; + + b_w_log2 = acc->awb.stripes[1].grid.block_width_log2; + acc->awb.stripes[1].grid.x_end = + imgu_css_grid_end(acc->awb.stripes[1].grid.x_start, + acc->awb.stripes[1].grid.width, + b_w_log2); } else if (acc->awb.config.grid.x_end <= acc->stripe.bds_out_stripes[0].width - min_overlap) { /* Enable only for leftmost stripe, disable right */ diff --git a/drivers/staging/media/ipu3/ipu3-v4l2.c b/drivers/staging/media/ipu3/ipu3-v4l2.c index 0473457b4e64..d1c539cefba8 100644 --- a/drivers/staging/media/ipu3/ipu3-v4l2.c +++ b/drivers/staging/media/ipu3/ipu3-v4l2.c @@ -485,6 +485,7 @@ static int imgu_vb2_start_streaming(struct vb2_queue *vq, unsigned int count) pipe = node->pipe; imgu_pipe = &imgu->imgu_pipe[pipe]; + atomic_set(&node->sequence, 0); r = media_pipeline_start(&node->vdev.entity, &imgu_pipe->pipeline); if (r < 0) goto fail_return_bufs; diff --git a/drivers/staging/media/ipu3/ipu3.c b/drivers/staging/media/ipu3/ipu3.c index 8e1e9e46e604..0c453b37f8c4 100644 --- a/drivers/staging/media/ipu3/ipu3.c +++ b/drivers/staging/media/ipu3/ipu3.c @@ -440,6 +440,16 @@ fail_start_streaming: return r; } +static void imgu_video_nodes_exit(struct imgu_device *imgu) +{ + int i; + + for (i = 0; i < IMGU_MAX_PIPE_NUM; i++) + imgu_dummybufs_cleanup(imgu, i); + + imgu_v4l2_unregister(imgu); +} + static int imgu_video_nodes_init(struct imgu_device *imgu) { struct v4l2_pix_format_mplane *fmts[IPU3_CSS_QUEUES] = { NULL }; @@ -489,24 +499,11 @@ static int imgu_video_nodes_init(struct imgu_device *imgu) return 0; out_cleanup: - for (j = 0; j < IMGU_MAX_PIPE_NUM; j++) - imgu_dummybufs_cleanup(imgu, j); - - imgu_v4l2_unregister(imgu); + imgu_video_nodes_exit(imgu); return r; } -static void imgu_video_nodes_exit(struct imgu_device *imgu) -{ - int i; - - for (i = 0; i < IMGU_MAX_PIPE_NUM; i++) - imgu_dummybufs_cleanup(imgu, i); - - imgu_v4l2_unregister(imgu); -} - /**************** PCI interface ****************/ static irqreturn_t imgu_isr_threaded(int irq, void *imgu_ptr) diff --git a/drivers/staging/media/rkvdec/TODO b/drivers/staging/media/rkvdec/TODO index e0f0f12f0ac5..2c0779383276 100644 --- a/drivers/staging/media/rkvdec/TODO +++ b/drivers/staging/media/rkvdec/TODO @@ -1,6 +1,6 @@ -* Support for VP9 is planned for this driver. +* Support for HEVC is planned for this driver. - Given the V4L controls for those CODECs will be part of + Given the V4L controls for that CODEC will be part of the uABI, it will be required to have the driver in staging. For this reason, we are keeping this driver in staging for now. diff --git a/drivers/staging/media/rkvdec/rkvdec-h264.c b/drivers/staging/media/rkvdec/rkvdec-h264.c index 951e19231da2..2992fb87cf72 100644 --- a/drivers/staging/media/rkvdec/rkvdec-h264.c +++ b/drivers/staging/media/rkvdec/rkvdec-h264.c @@ -97,13 +97,10 @@ struct rkvdec_h264_priv_tbl { u8 err_info[RKV_ERROR_INFO_SIZE]; }; -#define RKVDEC_H264_DPB_SIZE 16 - struct rkvdec_h264_reflists { - u8 p[RKVDEC_H264_DPB_SIZE]; - u8 b0[RKVDEC_H264_DPB_SIZE]; - u8 b1[RKVDEC_H264_DPB_SIZE]; - u8 num_valid; + struct v4l2_h264_reference p[V4L2_H264_REF_LIST_LEN]; + struct v4l2_h264_reference b0[V4L2_H264_REF_LIST_LEN]; + struct v4l2_h264_reference b1[V4L2_H264_REF_LIST_LEN]; }; struct rkvdec_h264_run { @@ -112,6 +109,7 @@ struct rkvdec_h264_run { const struct v4l2_ctrl_h264_sps *sps; const struct v4l2_ctrl_h264_pps *pps; const struct v4l2_ctrl_h264_scaling_matrix *scaling_matrix; + int ref_buf_idx[V4L2_H264_NUM_DPB_ENTRIES]; }; struct rkvdec_h264_ctx { @@ -661,8 +659,8 @@ static void assemble_hw_pps(struct rkvdec_ctx *ctx, WRITE_PPS(0xff, PROFILE_IDC); WRITE_PPS(1, CONSTRAINT_SET3_FLAG); WRITE_PPS(sps->chroma_format_idc, CHROMA_FORMAT_IDC); - WRITE_PPS(sps->bit_depth_luma_minus8 + 8, BIT_DEPTH_LUMA); - WRITE_PPS(sps->bit_depth_chroma_minus8 + 8, BIT_DEPTH_CHROMA); + WRITE_PPS(sps->bit_depth_luma_minus8, BIT_DEPTH_LUMA); + WRITE_PPS(sps->bit_depth_chroma_minus8, BIT_DEPTH_CHROMA); WRITE_PPS(0, QPPRIME_Y_ZERO_TRANSFORM_BYPASS_FLAG); WRITE_PPS(sps->log2_max_frame_num_minus4, LOG2_MAX_FRAME_NUM_MINUS4); WRITE_PPS(sps->max_num_ref_frames, MAX_NUM_REF_FRAMES); @@ -671,8 +669,17 @@ static void assemble_hw_pps(struct rkvdec_ctx *ctx, LOG2_MAX_PIC_ORDER_CNT_LSB_MINUS4); WRITE_PPS(!!(sps->flags & V4L2_H264_SPS_FLAG_DELTA_PIC_ORDER_ALWAYS_ZERO), DELTA_PIC_ORDER_ALWAYS_ZERO_FLAG); - WRITE_PPS(DIV_ROUND_UP(ctx->coded_fmt.fmt.pix_mp.width, 16), PIC_WIDTH_IN_MBS); - WRITE_PPS(DIV_ROUND_UP(ctx->coded_fmt.fmt.pix_mp.height, 16), PIC_HEIGHT_IN_MBS); + + /* + * Use the SPS values since they are already in macroblocks + * dimensions, height can be field height (halved) if + * V4L2_H264_SPS_FLAG_FRAME_MBS_ONLY is not set and also it allows + * decoding smaller images into larger allocation which can be used + * to implementing SVC spatial layer support. + */ + WRITE_PPS(sps->pic_width_in_mbs_minus1 + 1, PIC_WIDTH_IN_MBS); + WRITE_PPS(sps->pic_height_in_map_units_minus1 + 1, PIC_HEIGHT_IN_MBS); + WRITE_PPS(!!(sps->flags & V4L2_H264_SPS_FLAG_FRAME_MBS_ONLY), FRAME_MBS_ONLY_FLAG); WRITE_PPS(!!(sps->flags & V4L2_H264_SPS_FLAG_MB_ADAPTIVE_FRAME_FIELD), @@ -725,15 +732,38 @@ static void assemble_hw_pps(struct rkvdec_ctx *ctx, } } +static void lookup_ref_buf_idx(struct rkvdec_ctx *ctx, + struct rkvdec_h264_run *run) +{ + const struct v4l2_ctrl_h264_decode_params *dec_params = run->decode_params; + u32 i; + + for (i = 0; i < ARRAY_SIZE(dec_params->dpb); i++) { + struct v4l2_m2m_ctx *m2m_ctx = ctx->fh.m2m_ctx; + const struct v4l2_h264_dpb_entry *dpb = run->decode_params->dpb; + struct vb2_queue *cap_q = &m2m_ctx->cap_q_ctx.q; + int buf_idx = -1; + + if (dpb[i].flags & V4L2_H264_DPB_ENTRY_FLAG_ACTIVE) { + buf_idx = vb2_find_timestamp(cap_q, + dpb[i].reference_ts, 0); + if (buf_idx < 0) + pr_debug("No buffer for reference_ts %llu", + dpb[i].reference_ts); + } + + run->ref_buf_idx[i] = buf_idx; + } +} + static void assemble_hw_rps(struct rkvdec_ctx *ctx, + struct v4l2_h264_reflist_builder *builder, struct rkvdec_h264_run *run) { const struct v4l2_ctrl_h264_decode_params *dec_params = run->decode_params; const struct v4l2_h264_dpb_entry *dpb = dec_params->dpb; struct rkvdec_h264_ctx *h264_ctx = ctx->priv; - const struct v4l2_ctrl_h264_sps *sps = run->sps; struct rkvdec_h264_priv_tbl *priv_tbl = h264_ctx->priv_tbl.cpu; - u32 max_frame_num = 1 << (sps->log2_max_frame_num_minus4 + 4); u32 *hw_rps = priv_tbl->rps; u32 i, j; @@ -751,39 +781,36 @@ static void assemble_hw_rps(struct rkvdec_ctx *ctx, if (!(dpb[i].flags & V4L2_H264_DPB_ENTRY_FLAG_ACTIVE)) continue; - if (dpb[i].flags & V4L2_H264_DPB_ENTRY_FLAG_LONG_TERM || - dpb[i].frame_num < dec_params->frame_num) { - p[i] = dpb[i].frame_num; - continue; - } - - p[i] = dpb[i].frame_num - max_frame_num; + p[i] = builder->refs[i].frame_num; } for (j = 0; j < RKVDEC_NUM_REFLIST; j++) { - for (i = 0; i < h264_ctx->reflists.num_valid; i++) { - u8 dpb_valid = 0; - u8 idx = 0; + for (i = 0; i < builder->num_valid; i++) { + struct v4l2_h264_reference *ref; + bool dpb_valid; + bool bottom; switch (j) { case 0: - idx = h264_ctx->reflists.p[i]; + ref = &h264_ctx->reflists.p[i]; break; case 1: - idx = h264_ctx->reflists.b0[i]; + ref = &h264_ctx->reflists.b0[i]; break; case 2: - idx = h264_ctx->reflists.b1[i]; + ref = &h264_ctx->reflists.b1[i]; break; } - if (idx >= ARRAY_SIZE(dec_params->dpb)) + if (WARN_ON(ref->index >= ARRAY_SIZE(dec_params->dpb))) continue; - dpb_valid = !!(dpb[idx].flags & - V4L2_H264_DPB_ENTRY_FLAG_ACTIVE); + + dpb_valid = run->ref_buf_idx[ref->index] >= 0; + bottom = ref->fields == V4L2_H264_BOTTOM_FIELD_REF; set_ps_field(hw_rps, DPB_INFO(i, j), - idx | dpb_valid << 4); + ref->index | dpb_valid << 4); + set_ps_field(hw_rps, BOTTOM_FLAG(i, j), bottom); } } } @@ -859,13 +886,8 @@ get_ref_buf(struct rkvdec_ctx *ctx, struct rkvdec_h264_run *run, unsigned int dpb_idx) { struct v4l2_m2m_ctx *m2m_ctx = ctx->fh.m2m_ctx; - const struct v4l2_h264_dpb_entry *dpb = run->decode_params->dpb; struct vb2_queue *cap_q = &m2m_ctx->cap_q_ctx.q; - int buf_idx = -1; - - if (dpb[dpb_idx].flags & V4L2_H264_DPB_ENTRY_FLAG_ACTIVE) - buf_idx = vb2_find_timestamp(cap_q, - dpb[dpb_idx].reference_ts, 0); + int buf_idx = run->ref_buf_idx[dpb_idx]; /* * If a DPB entry is unused or invalid, address of current destination @@ -976,10 +998,6 @@ static void config_registers(struct rkvdec_ctx *ctx, rkvdec->regs + RKVDEC_REG_H264_BASE_REFER15); } - /* - * Since support frame mode only - * top_field_order_cnt is the same as bottom_field_order_cnt - */ reg = RKVDEC_CUR_POC(dec_params->top_field_order_cnt); writel_relaxed(reg, rkvdec->regs + RKVDEC_REG_CUR_POC0); @@ -1021,13 +1039,61 @@ static int rkvdec_h264_adjust_fmt(struct rkvdec_ctx *ctx, return 0; } +static int rkvdec_h264_validate_sps(struct rkvdec_ctx *ctx, + const struct v4l2_ctrl_h264_sps *sps) +{ + unsigned int width, height; + + /* + * TODO: The hardware supports 10-bit and 4:2:2 profiles, + * but it's currently broken in the driver. + * Reject them for now, until it's fixed. + */ + if (sps->chroma_format_idc > 1) + /* Only 4:0:0 and 4:2:0 are supported */ + return -EINVAL; + if (sps->bit_depth_luma_minus8 != sps->bit_depth_chroma_minus8) + /* Luma and chroma bit depth mismatch */ + return -EINVAL; + if (sps->bit_depth_luma_minus8 != 0) + /* Only 8-bit is supported */ + return -EINVAL; + + width = (sps->pic_width_in_mbs_minus1 + 1) * 16; + height = (sps->pic_height_in_map_units_minus1 + 1) * 16; + + /* + * When frame_mbs_only_flag is not set, this is field height, + * which is half the final height (see (7-18) in the + * specification) + */ + if (!(sps->flags & V4L2_H264_SPS_FLAG_FRAME_MBS_ONLY)) + height *= 2; + + if (width > ctx->coded_fmt.fmt.pix_mp.width || + height > ctx->coded_fmt.fmt.pix_mp.height) + return -EINVAL; + + return 0; +} + static int rkvdec_h264_start(struct rkvdec_ctx *ctx) { struct rkvdec_dev *rkvdec = ctx->dev; struct rkvdec_h264_priv_tbl *priv_tbl; struct rkvdec_h264_ctx *h264_ctx; + struct v4l2_ctrl *ctrl; int ret; + ctrl = v4l2_ctrl_find(&ctx->ctrl_hdl, + V4L2_CID_STATELESS_H264_SPS); + if (!ctrl) + return -EINVAL; + + ret = rkvdec_h264_validate_sps(ctx, ctrl->p_new.p_h264_sps); + if (ret) + return ret; + h264_ctx = kzalloc(sizeof(*h264_ctx), GFP_KERNEL); if (!h264_ctx) return -ENOMEM; @@ -1095,14 +1161,14 @@ static int rkvdec_h264_run(struct rkvdec_ctx *ctx) /* Build the P/B{0,1} ref lists. */ v4l2_h264_init_reflist_builder(&reflist_builder, run.decode_params, run.sps, run.decode_params->dpb); - h264_ctx->reflists.num_valid = reflist_builder.num_valid; v4l2_h264_build_p_ref_list(&reflist_builder, h264_ctx->reflists.p); v4l2_h264_build_b_ref_lists(&reflist_builder, h264_ctx->reflists.b0, h264_ctx->reflists.b1); assemble_hw_scaling_list(ctx, &run); assemble_hw_pps(ctx, &run); - assemble_hw_rps(ctx, &run); + lookup_ref_buf_idx(ctx, &run); + assemble_hw_rps(ctx, &reflist_builder, &run); config_registers(ctx, &run); rkvdec_run_postamble(ctx, &run.base); @@ -1122,9 +1188,18 @@ static int rkvdec_h264_run(struct rkvdec_ctx *ctx) return 0; } +static int rkvdec_h264_try_ctrl(struct rkvdec_ctx *ctx, struct v4l2_ctrl *ctrl) +{ + if (ctrl->id == V4L2_CID_STATELESS_H264_SPS) + return rkvdec_h264_validate_sps(ctx, ctrl->p_new.p_h264_sps); + + return 0; +} + const struct rkvdec_coded_fmt_ops rkvdec_h264_fmt_ops = { .adjust_fmt = rkvdec_h264_adjust_fmt, .start = rkvdec_h264_start, .stop = rkvdec_h264_stop, .run = rkvdec_h264_run, + .try_ctrl = rkvdec_h264_try_ctrl, }; diff --git a/drivers/staging/media/rkvdec/rkvdec.c b/drivers/staging/media/rkvdec/rkvdec.c index c0cf3488f970..7bab7586918c 100644 --- a/drivers/staging/media/rkvdec/rkvdec.c +++ b/drivers/staging/media/rkvdec/rkvdec.c @@ -29,23 +29,12 @@ static int rkvdec_try_ctrl(struct v4l2_ctrl *ctrl) { - if (ctrl->id == V4L2_CID_STATELESS_H264_SPS) { - const struct v4l2_ctrl_h264_sps *sps = ctrl->p_new.p_h264_sps; - /* - * TODO: The hardware supports 10-bit and 4:2:2 profiles, - * but it's currently broken in the driver. - * Reject them for now, until it's fixed. - */ - if (sps->chroma_format_idc > 1) - /* Only 4:0:0 and 4:2:0 are supported */ - return -EINVAL; - if (sps->bit_depth_luma_minus8 != sps->bit_depth_chroma_minus8) - /* Luma and chroma bit depth mismatch */ - return -EINVAL; - if (sps->bit_depth_luma_minus8 != 0) - /* Only 8-bit is supported */ - return -EINVAL; - } + struct rkvdec_ctx *ctx = container_of(ctrl->handler, struct rkvdec_ctx, ctrl_hdl); + const struct rkvdec_coded_fmt_desc *desc = ctx->coded_fmt_desc; + + if (desc->ops->try_ctrl) + return desc->ops->try_ctrl(ctx, ctrl); + return 0; } @@ -138,6 +127,7 @@ static const struct rkvdec_coded_fmt_desc rkvdec_coded_fmts[] = { .ops = &rkvdec_h264_fmt_ops, .num_decoded_fmts = ARRAY_SIZE(rkvdec_h264_vp9_decoded_fmts), .decoded_fmts = rkvdec_h264_vp9_decoded_fmts, + .subsystem_flags = VB2_V4L2_FL_SUPPORTS_M2M_HOLD_CAPTURE_BUF, }, { .fourcc = V4L2_PIX_FMT_VP9_FRAME, @@ -268,6 +258,8 @@ static int rkvdec_try_capture_fmt(struct file *file, void *priv, pix_mp->pixelformat = coded_desc->decoded_fmts[0]; /* Always apply the frmsize constraint of the coded end. */ + pix_mp->width = max(pix_mp->width, ctx->coded_fmt.fmt.pix_mp.width); + pix_mp->height = max(pix_mp->height, ctx->coded_fmt.fmt.pix_mp.height); v4l2_apply_frmsize_constraints(&pix_mp->width, &pix_mp->height, &coded_desc->frmsize); @@ -394,6 +386,9 @@ static int rkvdec_s_output_fmt(struct file *file, void *priv, cap_fmt->fmt.pix_mp.ycbcr_enc = f->fmt.pix_mp.ycbcr_enc; cap_fmt->fmt.pix_mp.quantization = f->fmt.pix_mp.quantization; + /* Enable format specific queue features */ + vq->subsystem_flags |= desc->subsystem_flags; + return 0; } @@ -1027,12 +1022,6 @@ static int rkvdec_probe(struct platform_device *pdev) if (ret) return ret; - /* - * Bump ACLK to max. possible freq. (500 MHz) to improve performance - * When 4k video playback. - */ - clk_set_rate(rkvdec->clocks[0].clk, 500 * 1000 * 1000); - rkvdec->regs = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(rkvdec->regs)) return PTR_ERR(rkvdec->regs); diff --git a/drivers/staging/media/rkvdec/rkvdec.h b/drivers/staging/media/rkvdec/rkvdec.h index 2f4ea1786b93..633335ebb9c4 100644 --- a/drivers/staging/media/rkvdec/rkvdec.h +++ b/drivers/staging/media/rkvdec/rkvdec.h @@ -72,6 +72,7 @@ struct rkvdec_coded_fmt_ops { void (*done)(struct rkvdec_ctx *ctx, struct vb2_v4l2_buffer *src_buf, struct vb2_v4l2_buffer *dst_buf, enum vb2_buffer_state result); + int (*try_ctrl)(struct rkvdec_ctx *ctx, struct v4l2_ctrl *ctrl); }; struct rkvdec_coded_fmt_desc { @@ -81,6 +82,7 @@ struct rkvdec_coded_fmt_desc { const struct rkvdec_coded_fmt_ops *ops; unsigned int num_decoded_fmts; const u32 *decoded_fmts; + u32 subsystem_flags; }; struct rkvdec_dev { diff --git a/drivers/staging/media/tegra-video/vi.c b/drivers/staging/media/tegra-video/vi.c index d1f43f465c22..8e184aa4c252 100644 --- a/drivers/staging/media/tegra-video/vi.c +++ b/drivers/staging/media/tegra-video/vi.c @@ -491,6 +491,7 @@ static int __tegra_channel_try_format(struct tegra_vi_channel *chan, struct v4l2_pix_format *pix) { const struct tegra_video_format *fmtinfo; + static struct lock_class_key key; struct v4l2_subdev *subdev; struct v4l2_subdev_format fmt; struct v4l2_subdev_state *sd_state; @@ -507,7 +508,12 @@ static int __tegra_channel_try_format(struct tegra_vi_channel *chan, if (!subdev) return -ENODEV; - sd_state = v4l2_subdev_alloc_state(subdev); + /* + * FIXME: Drop this call, drivers are not supposed to use + * __v4l2_subdev_state_alloc(). + */ + sd_state = __v4l2_subdev_state_alloc(subdev, "tegra:state->lock", + &key); if (IS_ERR(sd_state)) return PTR_ERR(sd_state); /* @@ -558,7 +564,7 @@ static int __tegra_channel_try_format(struct tegra_vi_channel *chan, v4l2_fill_pix_format(pix, &fmt.format); tegra_channel_fmt_align(chan, pix, fmtinfo->bpp); - v4l2_subdev_free_state(sd_state); + __v4l2_subdev_state_free(sd_state); return 0; } diff --git a/drivers/staging/r8188eu/core/rtw_br_ext.c b/drivers/staging/r8188eu/core/rtw_br_ext.c index d68611ef22f8..f056204c0fdb 100644 --- a/drivers/staging/r8188eu/core/rtw_br_ext.c +++ b/drivers/staging/r8188eu/core/rtw_br_ext.c @@ -70,7 +70,7 @@ static int __nat25_add_pppoe_tag(struct sk_buff *skb, struct pppoe_tag *tag) struct pppoe_hdr *ph = (struct pppoe_hdr *)(skb->data + ETH_HLEN); int data_len; - data_len = tag->tag_len + TAG_HDR_LEN; + data_len = be16_to_cpu(tag->tag_len) + TAG_HDR_LEN; if (skb_tailroom(skb) < data_len) return -1; diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index 6fe6a6bab3f4..ddf6c2a7212b 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -3596,10 +3596,7 @@ static int iscsit_send_reject( void iscsit_thread_get_cpumask(struct iscsi_conn *conn) { int ord, cpu; - cpumask_t conn_allowed_cpumask; - - cpumask_and(&conn_allowed_cpumask, iscsit_global->allowed_cpumask, - cpu_online_mask); + cpumask_var_t conn_allowed_cpumask; /* * bitmap_id is assigned from iscsit_global->ts_bitmap from @@ -3609,13 +3606,28 @@ void iscsit_thread_get_cpumask(struct iscsi_conn *conn) * iSCSI connection's RX/TX threads will be scheduled to * execute upon. */ - cpumask_clear(conn->conn_cpumask); - ord = conn->bitmap_id % cpumask_weight(&conn_allowed_cpumask); - for_each_cpu(cpu, &conn_allowed_cpumask) { - if (ord-- == 0) { - cpumask_set_cpu(cpu, conn->conn_cpumask); - return; + if (!zalloc_cpumask_var(&conn_allowed_cpumask, GFP_KERNEL)) { + ord = conn->bitmap_id % cpumask_weight(cpu_online_mask); + for_each_online_cpu(cpu) { + if (ord-- == 0) { + cpumask_set_cpu(cpu, conn->conn_cpumask); + return; + } + } + } else { + cpumask_and(conn_allowed_cpumask, iscsit_global->allowed_cpumask, + cpu_online_mask); + + cpumask_clear(conn->conn_cpumask); + ord = conn->bitmap_id % cpumask_weight(conn_allowed_cpumask); + for_each_cpu(cpu, conn_allowed_cpumask) { + if (ord-- == 0) { + cpumask_set_cpu(cpu, conn->conn_cpumask); + free_cpumask_var(conn_allowed_cpumask); + return; + } } + free_cpumask_var(conn_allowed_cpumask); } /* * This should never be reached.. diff --git a/drivers/target/iscsi/iscsi_target_configfs.c b/drivers/target/iscsi/iscsi_target_configfs.c index 0cedcfe207b5..57b4fd56d92a 100644 --- a/drivers/target/iscsi/iscsi_target_configfs.c +++ b/drivers/target/iscsi/iscsi_target_configfs.c @@ -1137,23 +1137,27 @@ static ssize_t lio_target_wwn_cpus_allowed_list_show( static ssize_t lio_target_wwn_cpus_allowed_list_store( struct config_item *item, const char *page, size_t count) { - int ret; + int ret = -ENOMEM; char *orig; - cpumask_t new_allowed_cpumask; + cpumask_var_t new_allowed_cpumask; + + if (!zalloc_cpumask_var(&new_allowed_cpumask, GFP_KERNEL)) + goto out; orig = kstrdup(page, GFP_KERNEL); if (!orig) - return -ENOMEM; + goto out_free_cpumask; - cpumask_clear(&new_allowed_cpumask); - ret = cpulist_parse(orig, &new_allowed_cpumask); + ret = cpulist_parse(orig, new_allowed_cpumask); + if (!ret) + cpumask_copy(iscsit_global->allowed_cpumask, + new_allowed_cpumask); kfree(orig); - if (ret != 0) - return ret; - - cpumask_copy(iscsit_global->allowed_cpumask, &new_allowed_cpumask); - return count; +out_free_cpumask: + free_cpumask_var(new_allowed_cpumask); +out: + return ret ? ret : count; } CONFIGFS_ATTR(lio_target_wwn_, cpus_allowed_list); diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c index 44bb380e7390..25f33eb25337 100644 --- a/drivers/target/target_core_device.c +++ b/drivers/target/target_core_device.c @@ -829,28 +829,26 @@ struct se_device *target_alloc_device(struct se_hba *hba, const char *name) } /* - * Check if the underlying struct block_device request_queue supports - * the QUEUE_FLAG_DISCARD bit for UNMAP/WRITE_SAME in SCSI + TRIM - * in ATA and we need to set TPE=1 + * Check if the underlying struct block_device supports discard and if yes + * configure the UNMAP parameters. */ bool target_configure_unmap_from_queue(struct se_dev_attrib *attrib, - struct request_queue *q) + struct block_device *bdev) { - int block_size = queue_logical_block_size(q); + int block_size = bdev_logical_block_size(bdev); - if (!blk_queue_discard(q)) + if (!bdev_max_discard_sectors(bdev)) return false; attrib->max_unmap_lba_count = - q->limits.max_discard_sectors >> (ilog2(block_size) - 9); + bdev_max_discard_sectors(bdev) >> (ilog2(block_size) - 9); /* * Currently hardcoded to 1 in Linux/SCSI code.. */ attrib->max_unmap_block_desc_count = 1; - attrib->unmap_granularity = q->limits.discard_granularity / block_size; - attrib->unmap_granularity_alignment = q->limits.discard_alignment / - block_size; - attrib->unmap_zeroes_data = !!(q->limits.max_write_zeroes_sectors); + attrib->unmap_granularity = bdev_discard_granularity(bdev) / block_size; + attrib->unmap_granularity_alignment = + bdev_discard_alignment(bdev) / block_size; return true; } EXPORT_SYMBOL(target_configure_unmap_from_queue); diff --git a/drivers/target/target_core_file.c b/drivers/target/target_core_file.c index 8190b840065f..e68f1cc8ef98 100644 --- a/drivers/target/target_core_file.c +++ b/drivers/target/target_core_file.c @@ -134,10 +134,10 @@ static int fd_configure_device(struct se_device *dev) */ inode = file->f_mapping->host; if (S_ISBLK(inode->i_mode)) { - struct request_queue *q = bdev_get_queue(I_BDEV(inode)); + struct block_device *bdev = I_BDEV(inode); unsigned long long dev_size; - fd_dev->fd_block_size = bdev_logical_block_size(I_BDEV(inode)); + fd_dev->fd_block_size = bdev_logical_block_size(bdev); /* * Determine the number of bytes from i_size_read() minus * one (1) logical sector from underlying struct block_device @@ -150,7 +150,7 @@ static int fd_configure_device(struct se_device *dev) dev_size, div_u64(dev_size, fd_dev->fd_block_size), fd_dev->fd_block_size); - if (target_configure_unmap_from_queue(&dev->dev_attrib, q)) + if (target_configure_unmap_from_queue(&dev->dev_attrib, bdev)) pr_debug("IFILE: BLOCK Discard support available," " disabled by default\n"); /* @@ -159,7 +159,7 @@ static int fd_configure_device(struct se_device *dev) */ dev->dev_attrib.max_write_same_len = 0xFFFF; - if (blk_queue_nonrot(q)) + if (bdev_nonrot(bdev)) dev->dev_attrib.is_nonrot = 1; } else { if (!(fd_dev->fbd_flags & FBDF_HAS_SIZE)) { @@ -558,7 +558,7 @@ fd_execute_unmap(struct se_cmd *cmd, sector_t lba, sector_t nolb) ret = blkdev_issue_discard(bdev, target_to_linux_sector(dev, lba), target_to_linux_sector(dev, nolb), - GFP_KERNEL, 0); + GFP_KERNEL); if (ret < 0) { pr_warn("FILEIO: blkdev_issue_discard() failed: %d\n", ret); diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c index 87ede165ddba..378c80313a0f 100644 --- a/drivers/target/target_core_iblock.c +++ b/drivers/target/target_core_iblock.c @@ -119,7 +119,7 @@ static int iblock_configure_device(struct se_device *dev) dev->dev_attrib.hw_max_sectors = queue_max_hw_sectors(q); dev->dev_attrib.hw_queue_depth = q->nr_requests; - if (target_configure_unmap_from_queue(&dev->dev_attrib, q)) + if (target_configure_unmap_from_queue(&dev->dev_attrib, bd)) pr_debug("IBLOCK: BLOCK Discard support available," " disabled by default\n"); @@ -133,7 +133,7 @@ static int iblock_configure_device(struct se_device *dev) else dev->dev_attrib.max_write_same_len = 0xFFFF; - if (blk_queue_nonrot(q)) + if (bdev_nonrot(bd)) dev->dev_attrib.is_nonrot = 1; bi = bdev_get_integrity(bd); @@ -434,7 +434,7 @@ iblock_execute_unmap(struct se_cmd *cmd, sector_t lba, sector_t nolb) ret = blkdev_issue_discard(bdev, target_to_linux_sector(dev, lba), target_to_linux_sector(dev, nolb), - GFP_KERNEL, 0); + GFP_KERNEL); if (ret < 0) { pr_err("blkdev_issue_discard() failed: %d\n", ret); return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; @@ -727,17 +727,16 @@ iblock_execute_rw(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents, if (data_direction == DMA_TO_DEVICE) { struct iblock_dev *ib_dev = IBLOCK_DEV(dev); - struct request_queue *q = bdev_get_queue(ib_dev->ibd_bd); /* * Force writethrough using REQ_FUA if a volatile write cache * is not enabled, or if initiator set the Force Unit Access bit. */ opf = REQ_OP_WRITE; miter_dir = SG_MITER_TO_SG; - if (test_bit(QUEUE_FLAG_FUA, &q->queue_flags)) { + if (bdev_fua(ib_dev->ibd_bd)) { if (cmd->se_cmd_flags & SCF_FUA) opf |= REQ_FUA; - else if (!test_bit(QUEUE_FLAG_WC, &q->queue_flags)) + else if (!bdev_write_cache(ib_dev->ibd_bd)) opf |= REQ_FUA; } } else { @@ -886,11 +885,7 @@ iblock_parse_cdb(struct se_cmd *cmd) static bool iblock_get_write_cache(struct se_device *dev) { - struct iblock_dev *ib_dev = IBLOCK_DEV(dev); - struct block_device *bd = ib_dev->ibd_bd; - struct request_queue *q = bdev_get_queue(bd); - - return test_bit(QUEUE_FLAG_WC, &q->queue_flags); + return bdev_write_cache(IBLOCK_DEV(dev)->ibd_bd); } static const struct target_backend_ops iblock_ops = { diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c index ff292b75e23f..bb3fb18b2316 100644 --- a/drivers/target/target_core_pscsi.c +++ b/drivers/target/target_core_pscsi.c @@ -588,7 +588,7 @@ static void pscsi_destroy_device(struct se_device *dev) } static void pscsi_complete_cmd(struct se_cmd *cmd, u8 scsi_status, - unsigned char *req_sense) + unsigned char *req_sense, int valid_data) { struct pscsi_dev_virt *pdv = PSCSI_DEV(cmd->se_dev); struct scsi_device *sd = pdv->pdv_sd; @@ -681,7 +681,7 @@ after_mode_select: * back despite framework assumption that a * check condition means there is no data */ - if (sd->type == TYPE_TAPE && + if (sd->type == TYPE_TAPE && valid_data && cmd->data_direction == DMA_FROM_DEVICE) { /* * is sense data valid, fixed format, @@ -818,24 +818,8 @@ static ssize_t pscsi_show_configfs_dev_params(struct se_device *dev, char *b) static void pscsi_bi_endio(struct bio *bio) { - bio_put(bio); -} - -static inline struct bio *pscsi_get_bio(int nr_vecs) -{ - struct bio *bio; - /* - * Use bio_malloc() following the comment in for bio -> struct request - * in block/blk-core.c:blk_make_request() - */ - bio = bio_kmalloc(GFP_KERNEL, nr_vecs); - if (!bio) { - pr_err("PSCSI: bio_kmalloc() failed\n"); - return NULL; - } - bio->bi_end_io = pscsi_bi_endio; - - return bio; + bio_uninit(bio); + kfree(bio); } static sense_reason_t @@ -878,15 +862,12 @@ pscsi_map_sg(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents, if (!bio) { new_bio: nr_vecs = bio_max_segs(nr_pages); - /* - * Calls bio_kmalloc() and sets bio->bi_end_io() - */ - bio = pscsi_get_bio(nr_vecs); + bio = bio_kmalloc(nr_vecs, GFP_KERNEL); if (!bio) goto fail; - - if (rw) - bio_set_op_attrs(bio, REQ_OP_WRITE, 0); + bio_init(bio, NULL, bio->bi_inline_vecs, nr_vecs, + rw ? REQ_OP_WRITE : REQ_OP_READ); + bio->bi_end_io = pscsi_bi_endio; pr_debug("PSCSI: Allocated bio: %p," " dir: %s nr_vecs: %d\n", bio, @@ -912,11 +893,6 @@ new_bio: goto fail; } - /* - * Clear the pointer so that another bio will - * be allocated with pscsi_get_bio() above. - */ - bio = NULL; goto new_bio; } @@ -1032,6 +1008,7 @@ static void pscsi_req_done(struct request *req, blk_status_t status) struct se_cmd *cmd = req->end_io_data; struct scsi_cmnd *scmd = blk_mq_rq_to_pdu(req); enum sam_status scsi_status = scmd->result & 0xff; + int valid_data = cmd->data_length - scmd->resid_len; u8 *cdb = cmd->priv; if (scsi_status != SAM_STAT_GOOD) { @@ -1039,12 +1016,11 @@ static void pscsi_req_done(struct request *req, blk_status_t status) " 0x%02x Result: 0x%08x\n", cmd, cdb[0], scmd->result); } - pscsi_complete_cmd(cmd, scsi_status, scmd->sense_buffer); + pscsi_complete_cmd(cmd, scsi_status, scmd->sense_buffer, valid_data); switch (host_byte(scmd->result)) { case DID_OK: - target_complete_cmd_with_length(cmd, scsi_status, - cmd->data_length - scmd->resid_len); + target_complete_cmd_with_length(cmd, scsi_status, valid_data); break; default: pr_debug("PSCSI Host Byte exception at cmd: %p CDB:" diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c index 95d4ca50a605..fd7267baa707 100644 --- a/drivers/target/target_core_user.c +++ b/drivers/target/target_core_user.c @@ -1821,6 +1821,7 @@ static struct page *tcmu_try_get_data_page(struct tcmu_dev *udev, uint32_t dpi) mutex_lock(&udev->cmdr_lock); page = xa_load(&udev->data_pages, dpi); if (likely(page)) { + get_page(page); mutex_unlock(&udev->cmdr_lock); return page; } @@ -1877,6 +1878,7 @@ static vm_fault_t tcmu_vma_fault(struct vm_fault *vmf) /* For the vmalloc()ed cmd area pages */ addr = (void *)(unsigned long)info->mem[mi].addr + offset; page = vmalloc_to_page(addr); + get_page(page); } else { uint32_t dpi; @@ -1887,7 +1889,6 @@ static vm_fault_t tcmu_vma_fault(struct vm_fault *vmf) return VM_FAULT_SIGBUS; } - get_page(page); vmf->page = page; return 0; } diff --git a/drivers/tee/optee/ffa_abi.c b/drivers/tee/optee/ffa_abi.c index a5eb4ef46971..c9b3b2cfb2b2 100644 --- a/drivers/tee/optee/ffa_abi.c +++ b/drivers/tee/optee/ffa_abi.c @@ -865,6 +865,7 @@ err_rhashtable_free: rhashtable_free_and_destroy(&optee->ffa.global_ids, rh_free_fn, NULL); optee_supp_uninit(&optee->supp); mutex_destroy(&optee->call_queue.mutex); + mutex_destroy(&optee->ffa.mutex); err_unreg_supp_teedev: tee_device_unregister(optee->supp_teedev); err_unreg_teedev: diff --git a/drivers/thermal/Kconfig b/drivers/thermal/Kconfig index e37691e0bf20..0e5cc948373c 100644 --- a/drivers/thermal/Kconfig +++ b/drivers/thermal/Kconfig @@ -113,8 +113,10 @@ config THERMAL_DEFAULT_GOV_USER_SPACE bool "user_space" select THERMAL_GOV_USER_SPACE help - Select this if you want to let the user space manage the - platform thermals. + The Userspace governor allows to get trip point crossed + notification from the kernel via uevents. It is recommended + to use the netlink interface instead which gives richer + information about the thermal framework events. config THERMAL_DEFAULT_GOV_POWER_ALLOCATOR bool "power_allocator" diff --git a/drivers/thermal/Makefile b/drivers/thermal/Makefile index f0c36a1530d5..def8e1a0399c 100644 --- a/drivers/thermal/Makefile +++ b/drivers/thermal/Makefile @@ -28,7 +28,7 @@ thermal_sys-$(CONFIG_CPU_IDLE_THERMAL) += cpuidle_cooling.o # devfreq cooling thermal_sys-$(CONFIG_DEVFREQ_THERMAL) += devfreq_cooling.o -obj-$(CONFIG_K3_THERMAL) += k3_bandgap.o +obj-$(CONFIG_K3_THERMAL) += k3_bandgap.o k3_j72xx_bandgap.o # platform thermal drivers obj-y += broadcom/ obj-$(CONFIG_THERMAL_MMIO) += thermal_mmio.o diff --git a/drivers/thermal/broadcom/bcm2711_thermal.c b/drivers/thermal/broadcom/bcm2711_thermal.c index 1ec57d9ecf53..e9bef5c3414b 100644 --- a/drivers/thermal/broadcom/bcm2711_thermal.c +++ b/drivers/thermal/broadcom/bcm2711_thermal.c @@ -38,7 +38,6 @@ static int bcm2711_get_temp(void *data, int *temp) int offset = thermal_zone_get_offset(priv->thermal); u32 val; int ret; - long t; ret = regmap_read(priv->regmap, AVS_RO_TEMP_STATUS, &val); if (ret) @@ -50,9 +49,7 @@ static int bcm2711_get_temp(void *data, int *temp) val &= AVS_RO_TEMP_STATUS_DATA_MSK; /* Convert a HW code to a temperature reading (millidegree celsius) */ - t = slope * val + offset; - - *temp = t < 0 ? 0 : t; + *temp = slope * val + offset; return 0; } diff --git a/drivers/thermal/broadcom/sr-thermal.c b/drivers/thermal/broadcom/sr-thermal.c index 475ce2900771..85ab9edd580c 100644 --- a/drivers/thermal/broadcom/sr-thermal.c +++ b/drivers/thermal/broadcom/sr-thermal.c @@ -60,6 +60,9 @@ static int sr_thermal_probe(struct platform_device *pdev) return -ENOMEM; res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (!res) + return -ENOENT; + sr_thermal->regs = (void __iomem *)devm_memremap(&pdev->dev, res->start, resource_size(res), MEMREMAP_WB); diff --git a/drivers/thermal/cpufreq_cooling.c b/drivers/thermal/cpufreq_cooling.c index 0bfb8eebd126..b8151d95a806 100644 --- a/drivers/thermal/cpufreq_cooling.c +++ b/drivers/thermal/cpufreq_cooling.c @@ -328,7 +328,7 @@ static inline bool em_is_sane(struct cpufreq_cooling_device *cpufreq_cdev, struct cpufreq_policy *policy; unsigned int nr_levels; - if (!em) + if (!em || em_is_artificial(em)) return false; policy = cpufreq_cdev->policy; diff --git a/drivers/thermal/devfreq_cooling.c b/drivers/thermal/devfreq_cooling.c index 4310cb342a9f..8c76f9655e57 100644 --- a/drivers/thermal/devfreq_cooling.c +++ b/drivers/thermal/devfreq_cooling.c @@ -358,28 +358,37 @@ of_devfreq_cooling_register_power(struct device_node *np, struct devfreq *df, struct thermal_cooling_device *cdev; struct device *dev = df->dev.parent; struct devfreq_cooling_device *dfc; + struct em_perf_domain *em; + struct thermal_cooling_device_ops *ops; char *name; int err, num_opps; - dfc = kzalloc(sizeof(*dfc), GFP_KERNEL); - if (!dfc) + ops = kmemdup(&devfreq_cooling_ops, sizeof(*ops), GFP_KERNEL); + if (!ops) return ERR_PTR(-ENOMEM); + dfc = kzalloc(sizeof(*dfc), GFP_KERNEL); + if (!dfc) { + err = -ENOMEM; + goto free_ops; + } + dfc->devfreq = df; - dfc->em_pd = em_pd_get(dev); - if (dfc->em_pd) { - devfreq_cooling_ops.get_requested_power = + em = em_pd_get(dev); + if (em && !em_is_artificial(em)) { + dfc->em_pd = em; + ops->get_requested_power = devfreq_cooling_get_requested_power; - devfreq_cooling_ops.state2power = devfreq_cooling_state2power; - devfreq_cooling_ops.power2state = devfreq_cooling_power2state; + ops->state2power = devfreq_cooling_state2power; + ops->power2state = devfreq_cooling_power2state; dfc->power_ops = dfc_power; num_opps = em_pd_nr_perf_states(dfc->em_pd); } else { /* Backward compatibility for drivers which do not use IPA */ - dev_dbg(dev, "missing EM for cooling device\n"); + dev_dbg(dev, "missing proper EM for cooling device\n"); num_opps = dev_pm_opp_get_opp_count(dev); @@ -407,8 +416,7 @@ of_devfreq_cooling_register_power(struct device_node *np, struct devfreq *df, if (!name) goto remove_qos_req; - cdev = thermal_of_cooling_device_register(np, name, dfc, - &devfreq_cooling_ops); + cdev = thermal_of_cooling_device_register(np, name, dfc, ops); kfree(name); if (IS_ERR(cdev)) { @@ -429,6 +437,8 @@ free_table: kfree(dfc->freq_table); free_dfc: kfree(dfc); +free_ops: + kfree(ops); return ERR_PTR(err); } @@ -510,11 +520,13 @@ EXPORT_SYMBOL_GPL(devfreq_cooling_em_register); void devfreq_cooling_unregister(struct thermal_cooling_device *cdev) { struct devfreq_cooling_device *dfc; + const struct thermal_cooling_device_ops *ops; struct device *dev; if (IS_ERR_OR_NULL(cdev)) return; + ops = cdev->ops; dfc = cdev->devdata; dev = dfc->devfreq->dev.parent; @@ -525,5 +537,6 @@ void devfreq_cooling_unregister(struct thermal_cooling_device *cdev) kfree(dfc->freq_table); kfree(dfc); + kfree(ops); } EXPORT_SYMBOL_GPL(devfreq_cooling_unregister); diff --git a/drivers/thermal/gov_user_space.c b/drivers/thermal/gov_user_space.c index 64a18e354a20..a62a4e90bd3f 100644 --- a/drivers/thermal/gov_user_space.c +++ b/drivers/thermal/gov_user_space.c @@ -17,8 +17,7 @@ static int user_space_bind(struct thermal_zone_device *tz) { - pr_warn_once("Userspace governor deprecated: use thermal netlink " \ - "notification instead\n"); + pr_info_once("Consider using thermal netlink events interface\n"); return 0; } diff --git a/drivers/thermal/hisi_thermal.c b/drivers/thermal/hisi_thermal.c index 9a21ac0ceb11..b29ab09040d5 100644 --- a/drivers/thermal/hisi_thermal.c +++ b/drivers/thermal/hisi_thermal.c @@ -629,7 +629,6 @@ static int hisi_thermal_remove(struct platform_device *pdev) return 0; } -#ifdef CONFIG_PM_SLEEP static int hisi_thermal_suspend(struct device *dev) { struct hisi_thermal_data *data = dev_get_drvdata(dev); @@ -651,15 +650,14 @@ static int hisi_thermal_resume(struct device *dev) return ret; } -#endif -static SIMPLE_DEV_PM_OPS(hisi_thermal_pm_ops, +static DEFINE_SIMPLE_DEV_PM_OPS(hisi_thermal_pm_ops, hisi_thermal_suspend, hisi_thermal_resume); static struct platform_driver hisi_thermal_driver = { .driver = { .name = "hisi_thermal", - .pm = &hisi_thermal_pm_ops, + .pm = pm_sleep_ptr(&hisi_thermal_pm_ops), .of_match_table = of_hisi_thermal_match, }, .probe = hisi_thermal_probe, diff --git a/drivers/thermal/imx_sc_thermal.c b/drivers/thermal/imx_sc_thermal.c index 8d76dbfde6a9..331a241eb0ef 100644 --- a/drivers/thermal/imx_sc_thermal.c +++ b/drivers/thermal/imx_sc_thermal.c @@ -94,8 +94,8 @@ static int imx_sc_thermal_probe(struct platform_device *pdev) sensor = devm_kzalloc(&pdev->dev, sizeof(*sensor), GFP_KERNEL); if (!sensor) { of_node_put(child); - of_node_put(sensor_np); - return -ENOMEM; + ret = -ENOMEM; + goto put_node; } ret = thermal_zone_of_get_sensor_id(child, @@ -124,7 +124,9 @@ static int imx_sc_thermal_probe(struct platform_device *pdev) dev_warn(&pdev->dev, "failed to add hwmon sysfs attributes\n"); } +put_node: of_node_put(sensor_np); + of_node_put(np); return ret; } diff --git a/drivers/thermal/intel/int340x_thermal/int3400_thermal.c b/drivers/thermal/intel/int340x_thermal/int3400_thermal.c index 4954800b9850..770d2b0299c3 100644 --- a/drivers/thermal/intel/int340x_thermal/int3400_thermal.c +++ b/drivers/thermal/intel/int340x_thermal/int3400_thermal.c @@ -68,7 +68,7 @@ static int evaluate_odvp(struct int3400_thermal_priv *priv); struct odvp_attr { int odvp; struct int3400_thermal_priv *priv; - struct kobj_attribute attr; + struct device_attribute attr; }; static ssize_t data_vault_read(struct file *file, struct kobject *kobj, @@ -169,37 +169,53 @@ static int int3400_thermal_run_osc(acpi_handle handle, char *uuid_str, int *enab acpi_status status; int result = 0; struct acpi_osc_context context = { - .uuid_str = NULL, + .uuid_str = uuid_str, .rev = 1, .cap.length = 8, + .cap.pointer = buf, }; - context.uuid_str = uuid_str; - buf[OSC_QUERY_DWORD] = 0; buf[OSC_SUPPORT_DWORD] = *enable; - context.cap.pointer = buf; - status = acpi_run_osc(handle, &context); if (ACPI_SUCCESS(status)) { ret = *((u32 *)(context.ret.pointer + 4)); if (ret != *enable) result = -EPERM; + + kfree(context.ret.pointer); } else result = -EPERM; - kfree(context.ret.pointer); - return result; } +static int set_os_uuid_mask(struct int3400_thermal_priv *priv, u32 mask) +{ + int cap = 0; + + /* + * Capability bits: + * Bit 0: set to 1 to indicate DPTF is active + * Bi1 1: set to 1 to active cooling is supported by user space daemon + * Bit 2: set to 1 to passive cooling is supported by user space daemon + * Bit 3: set to 1 to critical trip is handled by user space daemon + */ + if (mask) + cap = (priv->os_uuid_mask << 1) | 0x01; + + return int3400_thermal_run_osc(priv->adev->handle, + "b23ba85d-c8b7-3542-88de-8de2ffcfd698", + &cap); +} + static ssize_t current_uuid_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct int3400_thermal_priv *priv = dev_get_drvdata(dev); - int i; + int ret, i; for (i = 0; i < INT3400_THERMAL_MAXIMUM_UUID; ++i) { if (!strncmp(buf, int3400_thermal_uuids[i], @@ -231,19 +247,7 @@ static ssize_t current_uuid_store(struct device *dev, } if (priv->os_uuid_mask) { - int cap, ret; - - /* - * Capability bits: - * Bit 0: set to 1 to indicate DPTF is active - * Bi1 1: set to 1 to active cooling is supported by user space daemon - * Bit 2: set to 1 to passive cooling is supported by user space daemon - * Bit 3: set to 1 to critical trip is handled by user space daemon - */ - cap = ((priv->os_uuid_mask << 1) | 0x01); - ret = int3400_thermal_run_osc(priv->adev->handle, - "b23ba85d-c8b7-3542-88de-8de2ffcfd698", - &cap); + ret = set_os_uuid_mask(priv, priv->os_uuid_mask); if (ret) return ret; } @@ -311,7 +315,7 @@ end: return result; } -static ssize_t odvp_show(struct kobject *kobj, struct kobj_attribute *attr, +static ssize_t odvp_show(struct device *dev, struct device_attribute *attr, char *buf) { struct odvp_attr *odvp_attr; @@ -469,17 +473,26 @@ static int int3400_thermal_change_mode(struct thermal_zone_device *thermal, if (mode != thermal->mode) { int enabled; + enabled = mode == THERMAL_DEVICE_ENABLED; + + if (priv->os_uuid_mask) { + if (!enabled) { + priv->os_uuid_mask = 0; + result = set_os_uuid_mask(priv, priv->os_uuid_mask); + } + goto eval_odvp; + } + if (priv->current_uuid_index < 0 || priv->current_uuid_index >= INT3400_THERMAL_MAXIMUM_UUID) return -EINVAL; - enabled = (mode == THERMAL_DEVICE_ENABLED); result = int3400_thermal_run_osc(priv->adev->handle, int3400_thermal_uuids[priv->current_uuid_index], &enabled); } - +eval_odvp: evaluate_odvp(priv); return result; @@ -508,21 +521,18 @@ static void int3400_setup_gddv(struct int3400_thermal_priv *priv) obj = buffer.pointer; if (obj->type != ACPI_TYPE_PACKAGE || obj->package.count != 1 - || obj->package.elements[0].type != ACPI_TYPE_BUFFER) { - kfree(buffer.pointer); - return; - } + || obj->package.elements[0].type != ACPI_TYPE_BUFFER) + goto out_free; priv->data_vault = kmemdup(obj->package.elements[0].buffer.pointer, obj->package.elements[0].buffer.length, GFP_KERNEL); - if (!priv->data_vault) { - kfree(buffer.pointer); - return; - } + if (!priv->data_vault) + goto out_free; bin_attr_data_vault.private = priv->data_vault; bin_attr_data_vault.size = obj->package.elements[0].buffer.length; +out_free: kfree(buffer.pointer); } diff --git a/drivers/thermal/intel/intel_hfi.c b/drivers/thermal/intel/intel_hfi.c index 730fd121df6e..a0640f762dc5 100644 --- a/drivers/thermal/intel/intel_hfi.c +++ b/drivers/thermal/intel/intel_hfi.c @@ -243,8 +243,6 @@ static void hfi_update_work_fn(struct work_struct *work) hfi_instance = container_of(to_delayed_work(work), struct hfi_instance, update_work); - if (!hfi_instance) - return; update_capabilities(hfi_instance); } diff --git a/drivers/thermal/intel/intel_pch_thermal.c b/drivers/thermal/intel/intel_pch_thermal.c index 527c91f5960b..c1fa2b29b153 100644 --- a/drivers/thermal/intel/intel_pch_thermal.c +++ b/drivers/thermal/intel/intel_pch_thermal.c @@ -70,8 +70,8 @@ static unsigned int delay_timeout = 100; module_param(delay_timeout, int, 0644); MODULE_PARM_DESC(delay_timeout, "amount of time delay for each iteration."); -/* Number of iterations for cooling delay, 10 counts by default for now */ -static unsigned int delay_cnt = 10; +/* Number of iterations for cooling delay, 600 counts by default for now */ +static unsigned int delay_cnt = 600; module_param(delay_cnt, int, 0644); MODULE_PARM_DESC(delay_cnt, "total number of iterations for time delay."); @@ -193,10 +193,11 @@ static int pch_wpt_get_temp(struct pch_thermal_device *ptd, int *temp) return 0; } +/* Cool the PCH when it's overheat in .suspend_noirq phase */ static int pch_wpt_suspend(struct pch_thermal_device *ptd) { u8 tsel; - u8 pch_delay_cnt = 1; + int pch_delay_cnt = 0; u16 pch_thr_temp, pch_cur_temp; /* Shutdown the thermal sensor if it is not enabled by BIOS */ @@ -232,26 +233,38 @@ static int pch_wpt_suspend(struct pch_thermal_device *ptd) * temperature stays above threshold, notify the warning message * which helps to indentify the reason why S0ix entry was rejected. */ - while (pch_delay_cnt <= delay_cnt) { - if (pch_cur_temp <= pch_thr_temp) + while (pch_delay_cnt < delay_cnt) { + if (pch_cur_temp < pch_thr_temp) break; - dev_warn(&ptd->pdev->dev, + if (pm_wakeup_pending()) { + dev_warn(&ptd->pdev->dev, "Wakeup event detected, abort cooling\n"); + return 0; + } + + pch_delay_cnt++; + dev_dbg(&ptd->pdev->dev, "CPU-PCH current temp [%dC] higher than the threshold temp [%dC], sleep %d times for %d ms duration\n", pch_cur_temp, pch_thr_temp, pch_delay_cnt, delay_timeout); msleep(delay_timeout); /* Read the PCH current temperature for next cycle. */ pch_cur_temp = GET_PCH_TEMP(WPT_TEMP_TSR & readw(ptd->hw_base + WPT_TEMP)); - pch_delay_cnt++; } - if (pch_cur_temp > pch_thr_temp) + if (pch_cur_temp >= pch_thr_temp) dev_warn(&ptd->pdev->dev, - "CPU-PCH is hot [%dC] even after delay, continue to suspend. S0ix might fail\n", - pch_cur_temp); - else - dev_info(&ptd->pdev->dev, - "CPU-PCH is cool [%dC], continue to suspend\n", pch_cur_temp); + "CPU-PCH is hot [%dC] after %d ms delay. S0ix might fail\n", + pch_cur_temp, pch_delay_cnt * delay_timeout); + else { + if (pch_delay_cnt) + dev_info(&ptd->pdev->dev, + "CPU-PCH is cool [%dC] after %d ms delay\n", + pch_cur_temp, pch_delay_cnt * delay_timeout); + else + dev_info(&ptd->pdev->dev, + "CPU-PCH is cool [%dC]\n", + pch_cur_temp); + } return 0; } @@ -455,7 +468,7 @@ static void intel_pch_thermal_remove(struct pci_dev *pdev) pci_disable_device(pdev); } -static int intel_pch_thermal_suspend(struct device *device) +static int intel_pch_thermal_suspend_noirq(struct device *device) { struct pch_thermal_device *ptd = dev_get_drvdata(device); @@ -495,7 +508,7 @@ static const struct pci_device_id intel_pch_thermal_id[] = { MODULE_DEVICE_TABLE(pci, intel_pch_thermal_id); static const struct dev_pm_ops intel_pch_pm_ops = { - .suspend = intel_pch_thermal_suspend, + .suspend_noirq = intel_pch_thermal_suspend_noirq, .resume = intel_pch_thermal_resume, }; diff --git a/drivers/thermal/k3_bandgap.c b/drivers/thermal/k3_bandgap.c index 35f41e8a0b75..5d0b3ffc6f46 100644 --- a/drivers/thermal/k3_bandgap.c +++ b/drivers/thermal/k3_bandgap.c @@ -16,6 +16,8 @@ #include <linux/thermal.h> #include <linux/types.h> +#include "thermal_hwmon.h" + #define K3_VTM_DEVINFO_PWR0_OFFSET 0x4 #define K3_VTM_DEVINFO_PWR0_TEMPSENS_CT_MASK 0xf0 #define K3_VTM_TMPSENS0_CTRL_OFFSET 0x80 @@ -219,6 +221,9 @@ static int k3_bandgap_probe(struct platform_device *pdev) ret = PTR_ERR(data[id].tzd); goto err_alloc; } + + if (devm_thermal_add_hwmon_sysfs(data[id].tzd)) + dev_warn(dev, "Failed to add hwmon sysfs attributes\n"); } platform_set_drvdata(pdev, bgp); diff --git a/drivers/thermal/k3_j72xx_bandgap.c b/drivers/thermal/k3_j72xx_bandgap.c new file mode 100644 index 000000000000..64e323158952 --- /dev/null +++ b/drivers/thermal/k3_j72xx_bandgap.c @@ -0,0 +1,566 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * TI Bandgap temperature sensor driver for J72XX SoC Family + * + * Copyright (C) 2021 Texas Instruments Incorporated - http://www.ti.com/ + */ + +#include <linux/math.h> +#include <linux/math64.h> +#include <linux/module.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/pm_runtime.h> +#include <linux/err.h> +#include <linux/types.h> +#include <linux/of_platform.h> +#include <linux/io.h> +#include <linux/thermal.h> +#include <linux/of.h> +#include <linux/delay.h> +#include <linux/slab.h> + +#define K3_VTM_DEVINFO_PWR0_OFFSET 0x4 +#define K3_VTM_DEVINFO_PWR0_TEMPSENS_CT_MASK 0xf0 +#define K3_VTM_TMPSENS0_CTRL_OFFSET 0x300 +#define K3_VTM_MISC_CTRL_OFFSET 0xc +#define K3_VTM_TMPSENS_STAT_OFFSET 0x8 +#define K3_VTM_ANYMAXT_OUTRG_ALERT_EN 0x1 +#define K3_VTM_MISC_CTRL2_OFFSET 0x10 +#define K3_VTM_TS_STAT_DTEMP_MASK 0x3ff +#define K3_VTM_MAX_NUM_TS 8 +#define K3_VTM_TMPSENS_CTRL_SOC BIT(5) +#define K3_VTM_TMPSENS_CTRL_CLRZ BIT(6) +#define K3_VTM_TMPSENS_CTRL_CLKON_REQ BIT(7) +#define K3_VTM_TMPSENS_CTRL_MAXT_OUTRG_EN BIT(11) + +#define K3_VTM_CORRECTION_TEMP_CNT 3 + +#define MINUS40CREF 5 +#define PLUS30CREF 253 +#define PLUS125CREF 730 +#define PLUS150CREF 940 + +#define TABLE_SIZE 1024 +#define MAX_TEMP 123000 +#define COOL_DOWN_TEMP 105000 + +#define FACTORS_REDUCTION 13 +static int *derived_table; + +static int compute_value(int index, const s64 *factors, int nr_factors, + int reduction) +{ + s64 value = 0; + int i; + + for (i = 0; i < nr_factors; i++) + value += factors[i] * int_pow(index, i); + + return (int)div64_s64(value, int_pow(10, reduction)); +} + +static void init_table(int factors_size, int *table, const s64 *factors) +{ + int i; + + for (i = 0; i < TABLE_SIZE; i++) + table[i] = compute_value(i, factors, factors_size, + FACTORS_REDUCTION); +} + +/** + * struct err_values - structure containing error/reference values + * @refs: reference error values for -40C, 30C, 125C & 150C + * @errs: Actual error values for -40C, 30C, 125C & 150C read from the efuse + */ +struct err_values { + int refs[4]; + int errs[4]; +}; + +static void create_table_segments(struct err_values *err_vals, int seg, + int *ref_table) +{ + int m = 0, c, num, den, i, err, idx1, idx2, err1, err2, ref1, ref2; + + if (seg == 0) + idx1 = 0; + else + idx1 = err_vals->refs[seg]; + + idx2 = err_vals->refs[seg + 1]; + err1 = err_vals->errs[seg]; + err2 = err_vals->errs[seg + 1]; + ref1 = err_vals->refs[seg]; + ref2 = err_vals->refs[seg + 1]; + + /* + * Calculate the slope with adc values read from the register + * as the y-axis param and err in adc value as x-axis param + */ + num = ref2 - ref1; + den = err2 - err1; + if (den) + m = num / den; + c = ref2 - m * err2; + + /* + * Take care of divide by zero error if error values are same + * Or when the slope is 0 + */ + if (den != 0 && m != 0) { + for (i = idx1; i <= idx2; i++) { + err = (i - c) / m; + if (((i + err) < 0) || ((i + err) >= TABLE_SIZE)) + continue; + derived_table[i] = ref_table[i + err]; + } + } else { /* Constant error take care of divide by zero */ + for (i = idx1; i <= idx2; i++) { + if (((i + err1) < 0) || ((i + err1) >= TABLE_SIZE)) + continue; + derived_table[i] = ref_table[i + err1]; + } + } +} + +static int prep_lookup_table(struct err_values *err_vals, int *ref_table) +{ + int inc, i, seg; + + /* + * Fill up the lookup table under 3 segments + * region -40C to +30C + * region +30C to +125C + * region +125C to +150C + */ + for (seg = 0; seg < 3; seg++) + create_table_segments(err_vals, seg, ref_table); + + /* Get to the first valid temperature */ + i = 0; + while (!derived_table[i]) + i++; + + /* + * Get to the last zero index and back fill the temperature for + * sake of continuity + */ + if (i) { + /* 300 milli celsius steps */ + while (i--) + derived_table[i] = derived_table[i + 1] - 300; + /* case 0 */ + derived_table[i] = derived_table[i + 1] - 300; + } + + /* + * Fill the last trailing 0s which are unfilled with increments of + * 100 milli celsius till 1023 code + */ + i = TABLE_SIZE - 1; + while (!derived_table[i]) + i--; + + i++; + inc = 1; + while (i < TABLE_SIZE) { + derived_table[i] = derived_table[i - 1] + inc * 100; + i++; + } + + return 0; +} + +struct k3_thermal_data; + +struct k3_j72xx_bandgap { + struct device *dev; + void __iomem *base; + void __iomem *cfg2_base; + void __iomem *fuse_base; + struct k3_thermal_data *ts_data[K3_VTM_MAX_NUM_TS]; +}; + +/* common data structures */ +struct k3_thermal_data { + struct k3_j72xx_bandgap *bgp; + u32 ctrl_offset; + u32 stat_offset; +}; + +static int two_cmp(int tmp, int mask) +{ + tmp = ~(tmp); + tmp &= mask; + tmp += 1; + + /* Return negative value */ + return (0 - tmp); +} + +static unsigned int vtm_get_best_value(unsigned int s0, unsigned int s1, + unsigned int s2) +{ + int d01 = abs(s0 - s1); + int d02 = abs(s0 - s2); + int d12 = abs(s1 - s2); + + if (d01 <= d02 && d01 <= d12) + return (s0 + s1) / 2; + + if (d02 <= d01 && d02 <= d12) + return (s0 + s2) / 2; + + return (s1 + s2) / 2; +} + +static inline int k3_bgp_read_temp(struct k3_thermal_data *devdata, + int *temp) +{ + struct k3_j72xx_bandgap *bgp; + unsigned int dtemp, s0, s1, s2; + + bgp = devdata->bgp; + /* + * Errata is applicable for am654 pg 1.0 silicon/J7ES. There + * is a variation of the order for certain degree centigrade on AM654. + * Work around that by getting the average of two closest + * readings out of three readings everytime we want to + * report temperatures. + * + * Errata workaround. + */ + s0 = readl(bgp->base + devdata->stat_offset) & + K3_VTM_TS_STAT_DTEMP_MASK; + s1 = readl(bgp->base + devdata->stat_offset) & + K3_VTM_TS_STAT_DTEMP_MASK; + s2 = readl(bgp->base + devdata->stat_offset) & + K3_VTM_TS_STAT_DTEMP_MASK; + dtemp = vtm_get_best_value(s0, s1, s2); + + if (dtemp < 0 || dtemp >= TABLE_SIZE) + return -EINVAL; + + *temp = derived_table[dtemp]; + + return 0; +} + +/* Get temperature callback function for thermal zone */ +static int k3_thermal_get_temp(void *devdata, int *temp) +{ + struct k3_thermal_data *data = devdata; + int ret = 0; + + ret = k3_bgp_read_temp(data, temp); + if (ret) + return ret; + + return ret; +} + +static const struct thermal_zone_of_device_ops k3_of_thermal_ops = { + .get_temp = k3_thermal_get_temp, +}; + +static int k3_j72xx_bandgap_temp_to_adc_code(int temp) +{ + int low = 0, high = TABLE_SIZE - 1, mid; + + if (temp > 160000 || temp < -50000) + return -EINVAL; + + /* Binary search to find the adc code */ + while (low < (high - 1)) { + mid = (low + high) / 2; + if (temp <= derived_table[mid]) + high = mid; + else + low = mid; + } + + return mid; +} + +static void get_efuse_values(int id, struct k3_thermal_data *data, int *err, + struct k3_j72xx_bandgap *bgp) +{ + int i, tmp, pow; + int ct_offsets[5][K3_VTM_CORRECTION_TEMP_CNT] = { + { 0x0, 0x8, 0x4 }, + { 0x0, 0x8, 0x4 }, + { 0x0, -1, 0x4 }, + { 0x0, 0xC, -1 }, + { 0x0, 0xc, 0x8 } + }; + int ct_bm[5][K3_VTM_CORRECTION_TEMP_CNT] = { + { 0x3f, 0x1fe000, 0x1ff }, + { 0xfc0, 0x1fe000, 0x3fe00 }, + { 0x3f000, 0x7f800000, 0x7fc0000 }, + { 0xfc0000, 0x1fe0, 0x1f800000 }, + { 0x3f000000, 0x1fe000, 0x1ff0 } + }; + + for (i = 0; i < 3; i++) { + /* Extract the offset value using bit-mask */ + if (ct_offsets[id][i] == -1 && i == 1) { + /* 25C offset Case of Sensor 2 split between 2 regs */ + tmp = (readl(bgp->fuse_base + 0x8) & 0xE0000000) >> (29); + tmp |= ((readl(bgp->fuse_base + 0xC) & 0x1F) << 3); + pow = tmp & 0x80; + } else if (ct_offsets[id][i] == -1 && i == 2) { + /* 125C Case of Sensor 3 split between 2 regs */ + tmp = (readl(bgp->fuse_base + 0x4) & 0xF8000000) >> (27); + tmp |= ((readl(bgp->fuse_base + 0x8) & 0xF) << 5); + pow = tmp & 0x100; + } else { + tmp = readl(bgp->fuse_base + ct_offsets[id][i]); + tmp &= ct_bm[id][i]; + tmp = tmp >> __ffs(ct_bm[id][i]); + + /* Obtain the sign bit pow*/ + pow = ct_bm[id][i] >> __ffs(ct_bm[id][i]); + pow += 1; + pow /= 2; + } + + /* Check for negative value */ + if (tmp & pow) { + /* 2's complement value */ + tmp = two_cmp(tmp, ct_bm[id][i] >> __ffs(ct_bm[id][i])); + } + err[i] = tmp; + } + + /* Err value for 150C is set to 0 */ + err[i] = 0; +} + +static void print_look_up_table(struct device *dev, int *ref_table) +{ + int i; + + dev_dbg(dev, "The contents of derived array\n"); + dev_dbg(dev, "Code Temperature\n"); + for (i = 0; i < TABLE_SIZE; i++) + dev_dbg(dev, "%d %d %d\n", i, derived_table[i], ref_table[i]); +} + +struct k3_j72xx_bandgap_data { + unsigned int has_errata_i2128; +}; + +static int k3_j72xx_bandgap_probe(struct platform_device *pdev) +{ + int ret = 0, cnt, val, id; + int high_max, low_temp; + struct resource *res; + struct device *dev = &pdev->dev; + struct k3_j72xx_bandgap *bgp; + struct k3_thermal_data *data; + int workaround_needed = 0; + const struct k3_j72xx_bandgap_data *driver_data; + struct thermal_zone_device *ti_thermal; + int *ref_table; + struct err_values err_vals; + + const s64 golden_factors[] = { + -490019999999999936, + 3251200000000000, + -1705800000000, + 603730000, + -92627, + }; + + const s64 pvt_wa_factors[] = { + -415230000000000000, + 3126600000000000, + -1157800000000, + }; + + bgp = devm_kzalloc(&pdev->dev, sizeof(*bgp), GFP_KERNEL); + if (!bgp) + return -ENOMEM; + + bgp->dev = dev; + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + bgp->base = devm_ioremap_resource(dev, res); + if (IS_ERR(bgp->base)) + return PTR_ERR(bgp->base); + + res = platform_get_resource(pdev, IORESOURCE_MEM, 1); + bgp->cfg2_base = devm_ioremap_resource(dev, res); + if (IS_ERR(bgp->cfg2_base)) + return PTR_ERR(bgp->cfg2_base); + + res = platform_get_resource(pdev, IORESOURCE_MEM, 2); + bgp->fuse_base = devm_ioremap_resource(dev, res); + if (IS_ERR(bgp->fuse_base)) + return PTR_ERR(bgp->fuse_base); + + driver_data = of_device_get_match_data(dev); + if (driver_data) + workaround_needed = driver_data->has_errata_i2128; + + pm_runtime_enable(dev); + ret = pm_runtime_get_sync(dev); + if (ret < 0) { + pm_runtime_put_noidle(dev); + pm_runtime_disable(dev); + return ret; + } + + /* Get the sensor count in the VTM */ + val = readl(bgp->base + K3_VTM_DEVINFO_PWR0_OFFSET); + cnt = val & K3_VTM_DEVINFO_PWR0_TEMPSENS_CT_MASK; + cnt >>= __ffs(K3_VTM_DEVINFO_PWR0_TEMPSENS_CT_MASK); + + data = devm_kcalloc(bgp->dev, cnt, sizeof(*data), GFP_KERNEL); + if (!data) { + ret = -ENOMEM; + goto err_alloc; + } + + ref_table = kzalloc(sizeof(*ref_table) * TABLE_SIZE, GFP_KERNEL); + if (!ref_table) { + ret = -ENOMEM; + goto err_alloc; + } + + derived_table = devm_kzalloc(bgp->dev, sizeof(*derived_table) * TABLE_SIZE, + GFP_KERNEL); + if (!derived_table) { + ret = -ENOMEM; + goto err_alloc; + } + + /* Workaround not needed if bit30/bit31 is set even for J721e */ + if (workaround_needed && (readl(bgp->fuse_base + 0x0) & 0xc0000000) == 0xc0000000) + workaround_needed = false; + + dev_dbg(bgp->dev, "Work around %sneeded\n", + workaround_needed ? "not " : ""); + + if (!workaround_needed) + init_table(5, ref_table, golden_factors); + else + init_table(3, ref_table, pvt_wa_factors); + + /* Register the thermal sensors */ + for (id = 0; id < cnt; id++) { + data[id].bgp = bgp; + data[id].ctrl_offset = K3_VTM_TMPSENS0_CTRL_OFFSET + id * 0x20; + data[id].stat_offset = data[id].ctrl_offset + + K3_VTM_TMPSENS_STAT_OFFSET; + + if (workaround_needed) { + /* ref adc values for -40C, 30C & 125C respectively */ + err_vals.refs[0] = MINUS40CREF; + err_vals.refs[1] = PLUS30CREF; + err_vals.refs[2] = PLUS125CREF; + err_vals.refs[3] = PLUS150CREF; + get_efuse_values(id, &data[id], err_vals.errs, bgp); + } + + if (id == 0 && workaround_needed) + prep_lookup_table(&err_vals, ref_table); + else if (id == 0 && !workaround_needed) + memcpy(derived_table, ref_table, TABLE_SIZE * 4); + + val = readl(data[id].bgp->cfg2_base + data[id].ctrl_offset); + val |= (K3_VTM_TMPSENS_CTRL_MAXT_OUTRG_EN | + K3_VTM_TMPSENS_CTRL_SOC | + K3_VTM_TMPSENS_CTRL_CLRZ | BIT(4)); + writel(val, data[id].bgp->cfg2_base + data[id].ctrl_offset); + + bgp->ts_data[id] = &data[id]; + ti_thermal = + devm_thermal_zone_of_sensor_register(bgp->dev, id, + &data[id], + &k3_of_thermal_ops); + if (IS_ERR(ti_thermal)) { + dev_err(bgp->dev, "thermal zone device is NULL\n"); + ret = PTR_ERR(ti_thermal); + goto err_alloc; + } + } + + /* + * Program TSHUT thresholds + * Step 1: set the thresholds to ~123C and 105C WKUP_VTM_MISC_CTRL2 + * Step 2: WKUP_VTM_TMPSENS_CTRL_j set the MAXT_OUTRG_EN bit + * This is already taken care as per of init + * Step 3: WKUP_VTM_MISC_CTRL set the ANYMAXT_OUTRG_ALERT_EN bit + */ + high_max = k3_j72xx_bandgap_temp_to_adc_code(MAX_TEMP); + low_temp = k3_j72xx_bandgap_temp_to_adc_code(COOL_DOWN_TEMP); + + writel((low_temp << 16) | high_max, data[0].bgp->cfg2_base + + K3_VTM_MISC_CTRL2_OFFSET); + mdelay(100); + writel(K3_VTM_ANYMAXT_OUTRG_ALERT_EN, data[0].bgp->cfg2_base + + K3_VTM_MISC_CTRL_OFFSET); + + platform_set_drvdata(pdev, bgp); + + print_look_up_table(dev, ref_table); + /* + * Now that the derived_table has the appropriate look up values + * Free up the ref_table + */ + kfree(ref_table); + + return 0; + +err_alloc: + pm_runtime_put_sync(&pdev->dev); + pm_runtime_disable(&pdev->dev); + + return ret; +} + +static int k3_j72xx_bandgap_remove(struct platform_device *pdev) +{ + pm_runtime_put_sync(&pdev->dev); + pm_runtime_disable(&pdev->dev); + + return 0; +} + +const struct k3_j72xx_bandgap_data k3_j72xx_bandgap_j721e_data = { + .has_errata_i2128 = 1, +}; + +const struct k3_j72xx_bandgap_data k3_j72xx_bandgap_j7200_data = { + .has_errata_i2128 = 0, +}; + +static const struct of_device_id of_k3_j72xx_bandgap_match[] = { + { + .compatible = "ti,j721e-vtm", + .data = &k3_j72xx_bandgap_j721e_data, + }, + { + .compatible = "ti,j7200-vtm", + .data = &k3_j72xx_bandgap_j7200_data, + }, + { /* sentinel */ }, +}; +MODULE_DEVICE_TABLE(of, of_k3_j72xx_bandgap_match); + +static struct platform_driver k3_j72xx_bandgap_sensor_driver = { + .probe = k3_j72xx_bandgap_probe, + .remove = k3_j72xx_bandgap_remove, + .driver = { + .name = "k3-j72xx-soc-thermal", + .of_match_table = of_k3_j72xx_bandgap_match, + }, +}; + +module_platform_driver(k3_j72xx_bandgap_sensor_driver); + +MODULE_DESCRIPTION("K3 bandgap temperature sensor driver"); +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("J Keerthy <j-keerthy@ti.com>"); diff --git a/drivers/thermal/qcom/lmh.c b/drivers/thermal/qcom/lmh.c index c7f91cbdccc7..d3d9b9fa49e8 100644 --- a/drivers/thermal/qcom/lmh.c +++ b/drivers/thermal/qcom/lmh.c @@ -220,6 +220,7 @@ static int lmh_probe(struct platform_device *pdev) } static const struct of_device_id lmh_table[] = { + { .compatible = "qcom,sc8180x-lmh", }, { .compatible = "qcom,sdm845-lmh", .data = (void *)LMH_ENABLE_ALGOS}, { .compatible = "qcom,sm8150-lmh", }, {} diff --git a/drivers/thermal/qcom/qcom-spmi-adc-tm5.c b/drivers/thermal/qcom/qcom-spmi-adc-tm5.c index 824671cf494a..d9c9c975f931 100644 --- a/drivers/thermal/qcom/qcom-spmi-adc-tm5.c +++ b/drivers/thermal/qcom/qcom-spmi-adc-tm5.c @@ -4,7 +4,10 @@ * * Based on original driver: * Copyright (c) 2012-2020, The Linux Foundation. All rights reserved. + * + * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved. */ + #include <linux/bitfield.h> #include <linux/iio/adc/qcom-vadc-common.h> #include <linux/iio/consumer.h> @@ -15,6 +18,7 @@ #include <linux/platform_device.h> #include <linux/regmap.h> #include <linux/thermal.h> +#include <asm-generic/unaligned.h> /* * Thermal monitoring block consists of 8 (ADC_TM5_NUM_CHANNELS) channels. Each @@ -71,6 +75,60 @@ #define ADC_TM5_M_HIGH_THR_INT_EN BIT(1) #define ADC_TM5_M_LOW_THR_INT_EN BIT(0) +#define ADC_TM_GEN2_STATUS1 0x08 +#define ADC_TM_GEN2_STATUS_LOW_SET 0x09 +#define ADC_TM_GEN2_STATUS_LOW_CLR 0x0a +#define ADC_TM_GEN2_STATUS_HIGH_SET 0x0b +#define ADC_TM_GEN2_STATUS_HIGH_CLR 0x0c + +#define ADC_TM_GEN2_CFG_HS_SET 0x0d +#define ADC_TM_GEN2_CFG_HS_FLAG BIT(0) +#define ADC_TM_GEN2_CFG_HS_CLR 0x0e + +#define ADC_TM_GEN2_SID 0x40 + +#define ADC_TM_GEN2_CH_CTL 0x41 +#define ADC_TM_GEN2_TM_CH_SEL GENMASK(7, 5) +#define ADC_TM_GEN2_MEAS_INT_SEL GENMASK(3, 2) + +#define ADC_TM_GEN2_ADC_DIG_PARAM 0x42 +#define ADC_TM_GEN2_CTL_CAL_SEL GENMASK(5, 4) +#define ADC_TM_GEN2_CTL_DEC_RATIO_MASK GENMASK(3, 2) + +#define ADC_TM_GEN2_FAST_AVG_CTL 0x43 +#define ADC_TM_GEN2_FAST_AVG_EN BIT(7) + +#define ADC_TM_GEN2_ADC_CH_SEL_CTL 0x44 + +#define ADC_TM_GEN2_DELAY_CTL 0x45 +#define ADC_TM_GEN2_HW_SETTLE_DELAY GENMASK(3, 0) + +#define ADC_TM_GEN2_EN_CTL1 0x46 +#define ADC_TM_GEN2_EN BIT(7) + +#define ADC_TM_GEN2_CONV_REQ 0x47 +#define ADC_TM_GEN2_CONV_REQ_EN BIT(7) + +#define ADC_TM_GEN2_LOW_THR0 0x49 +#define ADC_TM_GEN2_LOW_THR1 0x4a +#define ADC_TM_GEN2_HIGH_THR0 0x4b +#define ADC_TM_GEN2_HIGH_THR1 0x4c +#define ADC_TM_GEN2_LOWER_MASK(n) ((n) & GENMASK(7, 0)) +#define ADC_TM_GEN2_UPPER_MASK(n) (((n) & GENMASK(15, 8)) >> 8) + +#define ADC_TM_GEN2_MEAS_IRQ_EN 0x4d +#define ADC_TM_GEN2_MEAS_EN BIT(7) +#define ADC_TM5_GEN2_HIGH_THR_INT_EN BIT(1) +#define ADC_TM5_GEN2_LOW_THR_INT_EN BIT(0) + +#define ADC_TM_GEN2_MEAS_INT_LSB 0x50 +#define ADC_TM_GEN2_MEAS_INT_MSB 0x51 +#define ADC_TM_GEN2_MEAS_INT_MODE 0x52 + +#define ADC_TM_GEN2_Mn_DATA0(n) ((n * 2) + 0xa0) +#define ADC_TM_GEN2_Mn_DATA1(n) ((n * 2) + 0xa1) +#define ADC_TM_GEN2_DATA_SHIFT 8 + enum adc5_timer_select { ADC5_TIMER_SEL_1 = 0, ADC5_TIMER_SEL_2, @@ -78,11 +136,11 @@ enum adc5_timer_select { ADC5_TIMER_SEL_NONE, }; -struct adc_tm5_data { - const u32 full_scale_code_volt; - unsigned int *decimation; - unsigned int *hw_settle; - bool is_hc; +enum adc5_gen { + ADC_TM5, + ADC_TM_HC, + ADC_TM5_GEN2, + ADC_TM5_MAX }; enum adc_tm5_cal_method { @@ -91,7 +149,28 @@ enum adc_tm5_cal_method { ADC_TM5_ABSOLUTE_CAL }; +enum adc_tm_gen2_time_select { + MEAS_INT_50MS = 0, + MEAS_INT_100MS, + MEAS_INT_1S, + MEAS_INT_SET, + MEAS_INT_NONE, +}; + struct adc_tm5_chip; +struct adc_tm5_channel; + +struct adc_tm5_data { + const u32 full_scale_code_volt; + unsigned int *decimation; + unsigned int *hw_settle; + int (*disable_channel)(struct adc_tm5_channel *channel); + int (*configure)(struct adc_tm5_channel *channel, int low, int high); + irqreturn_t (*isr)(int irq, void *data); + int (*init)(struct adc_tm5_chip *chip); + char *irq_name; + int gen; +}; /** * struct adc_tm5_channel - ADC Thermal Monitoring channel data. @@ -101,6 +180,12 @@ struct adc_tm5_chip; * @prescale: channel scaling performed on the input signal. * @hw_settle_time: the time between AMUX being configured and the * start of conversion. + * @decimation: sampling rate supported for the channel. + * @avg_samples: ability to provide single result from the ADC + * that is an average of multiple measurements. + * @high_thr_en: channel upper voltage threshold enable state. + * @low_thr_en: channel lower voltage threshold enable state. + * @meas_en: recurring measurement enable state * @iio: IIO channel instance used by this channel. * @chip: ADC TM chip instance. * @tzd: thermal zone device used by this channel. @@ -111,6 +196,11 @@ struct adc_tm5_channel { enum adc_tm5_cal_method cal_method; unsigned int prescale; unsigned int hw_settle_time; + unsigned int decimation; /* For Gen2 ADC_TM */ + unsigned int avg_samples; /* For Gen2 ADC_TM */ + bool high_thr_en; /* For Gen2 ADC_TM */ + bool low_thr_en; /* For Gen2 ADC_TM */ + bool meas_en; /* For Gen2 ADC_TM */ struct iio_channel *iio; struct adc_tm5_chip *chip; struct thermal_zone_device *tzd; @@ -124,9 +214,15 @@ struct adc_tm5_channel { * @channels: array of ADC TM channel data. * @nchannels: amount of channels defined/allocated * @decimation: sampling rate supported for the channel. + * Applies to all channels, used only on Gen1 ADC_TM. * @avg_samples: ability to provide single result from the ADC - * that is an average of multiple measurements. + * that is an average of multiple measurements. Applies to all + * channels, used only on Gen1 ADC_TM. * @base: base address of TM registers. + * @adc_mutex_lock: ADC_TM mutex lock, used only on Gen2 ADC_TM. + * It is used to ensure only one ADC channel configuration + * is done at a time using the shared set of configuration + * registers. */ struct adc_tm5_chip { struct regmap *regmap; @@ -137,22 +233,7 @@ struct adc_tm5_chip { unsigned int decimation; unsigned int avg_samples; u16 base; -}; - -static const struct adc_tm5_data adc_tm5_data_pmic = { - .full_scale_code_volt = 0x70e4, - .decimation = (unsigned int []) { 250, 420, 840 }, - .hw_settle = (unsigned int []) { 15, 100, 200, 300, 400, 500, 600, 700, - 1000, 2000, 4000, 8000, 16000, 32000, - 64000, 128000 }, -}; - -static const struct adc_tm5_data adc_tm_hc_data_pmic = { - .full_scale_code_volt = 0x70e4, - .decimation = (unsigned int []) { 256, 512, 1024 }, - .hw_settle = (unsigned int []) { 0, 100, 200, 300, 400, 500, 600, 700, - 1000, 2000, 4000, 6000, 8000, 10000 }, - .is_hc = true, + struct mutex adc_mutex_lock; }; static int adc_tm5_read(struct adc_tm5_chip *adc_tm, u16 offset, u8 *data, int len) @@ -219,6 +300,61 @@ static irqreturn_t adc_tm5_isr(int irq, void *data) return IRQ_HANDLED; } +static irqreturn_t adc_tm5_gen2_isr(int irq, void *data) +{ + struct adc_tm5_chip *chip = data; + u8 status_low, status_high; + int ret, i; + + ret = adc_tm5_read(chip, ADC_TM_GEN2_STATUS_LOW_CLR, &status_low, sizeof(status_low)); + if (ret) { + dev_err(chip->dev, "read status_low failed: %d\n", ret); + return IRQ_HANDLED; + } + + ret = adc_tm5_read(chip, ADC_TM_GEN2_STATUS_HIGH_CLR, &status_high, sizeof(status_high)); + if (ret) { + dev_err(chip->dev, "read status_high failed: %d\n", ret); + return IRQ_HANDLED; + } + + ret = adc_tm5_write(chip, ADC_TM_GEN2_STATUS_LOW_CLR, &status_low, sizeof(status_low)); + if (ret < 0) { + dev_err(chip->dev, "clear status low failed with %d\n", ret); + return IRQ_HANDLED; + } + + ret = adc_tm5_write(chip, ADC_TM_GEN2_STATUS_HIGH_CLR, &status_high, sizeof(status_high)); + if (ret < 0) { + dev_err(chip->dev, "clear status high failed with %d\n", ret); + return IRQ_HANDLED; + } + + for (i = 0; i < chip->nchannels; i++) { + bool upper_set = false, lower_set = false; + unsigned int ch = chip->channels[i].channel; + + /* No TZD, we warned at the boot time */ + if (!chip->channels[i].tzd) + continue; + + if (!chip->channels[i].meas_en) + continue; + + lower_set = (status_low & BIT(ch)) && + (chip->channels[i].low_thr_en); + + upper_set = (status_high & BIT(ch)) && + (chip->channels[i].high_thr_en); + + if (upper_set || lower_set) + thermal_zone_device_update(chip->channels[i].tzd, + THERMAL_EVENT_UNSPECIFIED); + } + + return IRQ_HANDLED; +} + static int adc_tm5_get_temp(void *data, int *temp) { struct adc_tm5_channel *channel = data; @@ -249,6 +385,104 @@ static int adc_tm5_disable_channel(struct adc_tm5_channel *channel) 0); } +#define ADC_TM_GEN2_POLL_DELAY_MIN_US 100 +#define ADC_TM_GEN2_POLL_DELAY_MAX_US 110 +#define ADC_TM_GEN2_POLL_RETRY_COUNT 3 + +static int32_t adc_tm5_gen2_conv_req(struct adc_tm5_chip *chip) +{ + int ret; + u8 data; + unsigned int count; + + data = ADC_TM_GEN2_EN; + ret = adc_tm5_write(chip, ADC_TM_GEN2_EN_CTL1, &data, 1); + if (ret < 0) { + dev_err(chip->dev, "adc-tm enable failed with %d\n", ret); + return ret; + } + + data = ADC_TM_GEN2_CFG_HS_FLAG; + ret = adc_tm5_write(chip, ADC_TM_GEN2_CFG_HS_SET, &data, 1); + if (ret < 0) { + dev_err(chip->dev, "adc-tm handshake failed with %d\n", ret); + return ret; + } + + data = ADC_TM_GEN2_CONV_REQ_EN; + ret = adc_tm5_write(chip, ADC_TM_GEN2_CONV_REQ, &data, 1); + if (ret < 0) { + dev_err(chip->dev, "adc-tm request conversion failed with %d\n", ret); + return ret; + } + + /* + * SW sets a handshake bit and waits for PBS to clear it + * before the next conversion request can be queued. + */ + + for (count = 0; count < ADC_TM_GEN2_POLL_RETRY_COUNT; count++) { + ret = adc_tm5_read(chip, ADC_TM_GEN2_CFG_HS_SET, &data, sizeof(data)); + if (ret < 0) { + dev_err(chip->dev, "adc-tm read failed with %d\n", ret); + return ret; + } + + if (!(data & ADC_TM_GEN2_CFG_HS_FLAG)) + return ret; + usleep_range(ADC_TM_GEN2_POLL_DELAY_MIN_US, + ADC_TM_GEN2_POLL_DELAY_MAX_US); + } + + dev_err(chip->dev, "adc-tm conversion request handshake timed out\n"); + + return -ETIMEDOUT; +} + +static int adc_tm5_gen2_disable_channel(struct adc_tm5_channel *channel) +{ + struct adc_tm5_chip *chip = channel->chip; + int ret; + u8 val; + + mutex_lock(&chip->adc_mutex_lock); + + channel->meas_en = false; + channel->high_thr_en = false; + channel->low_thr_en = false; + + ret = adc_tm5_read(chip, ADC_TM_GEN2_CH_CTL, &val, sizeof(val)); + if (ret < 0) { + dev_err(chip->dev, "adc-tm block read failed with %d\n", ret); + goto disable_fail; + } + + val &= ~ADC_TM_GEN2_TM_CH_SEL; + val |= FIELD_PREP(ADC_TM_GEN2_TM_CH_SEL, channel->channel); + + ret = adc_tm5_write(chip, ADC_TM_GEN2_CH_CTL, &val, 1); + if (ret < 0) { + dev_err(chip->dev, "adc-tm channel disable failed with %d\n", ret); + goto disable_fail; + } + + val = 0; + ret = adc_tm5_write(chip, ADC_TM_GEN2_MEAS_IRQ_EN, &val, 1); + if (ret < 0) { + dev_err(chip->dev, "adc-tm interrupt disable failed with %d\n", ret); + goto disable_fail; + } + + + ret = adc_tm5_gen2_conv_req(channel->chip); + if (ret < 0) + dev_err(chip->dev, "adc-tm channel configure failed with %d\n", ret); + +disable_fail: + mutex_unlock(&chip->adc_mutex_lock); + return ret; +} + static int adc_tm5_enable(struct adc_tm5_chip *chip) { int ret; @@ -291,8 +525,7 @@ static int adc_tm5_configure(struct adc_tm5_channel *channel, int low, int high) u16 adc_code = qcom_adc_tm5_temp_volt_scale(channel->prescale, chip->data->full_scale_code_volt, high); - buf[1] = adc_code & 0xff; - buf[2] = adc_code >> 8; + put_unaligned_le16(adc_code, &buf[1]); buf[7] |= ADC_TM5_M_LOW_THR_INT_EN; } else { buf[7] &= ~ADC_TM5_M_LOW_THR_INT_EN; @@ -303,8 +536,7 @@ static int adc_tm5_configure(struct adc_tm5_channel *channel, int low, int high) u16 adc_code = qcom_adc_tm5_temp_volt_scale(channel->prescale, chip->data->full_scale_code_volt, low); - buf[3] = adc_code & 0xff; - buf[4] = adc_code >> 8; + put_unaligned_le16(adc_code, &buf[3]); buf[7] |= ADC_TM5_M_HIGH_THR_INT_EN; } else { buf[7] &= ~ADC_TM5_M_HIGH_THR_INT_EN; @@ -329,6 +561,82 @@ static int adc_tm5_configure(struct adc_tm5_channel *channel, int low, int high) return adc_tm5_enable(chip); } +static int adc_tm5_gen2_configure(struct adc_tm5_channel *channel, int low, int high) +{ + struct adc_tm5_chip *chip = channel->chip; + int ret; + u8 buf[14]; + u16 adc_code; + + mutex_lock(&chip->adc_mutex_lock); + + channel->meas_en = true; + + ret = adc_tm5_read(chip, ADC_TM_GEN2_SID, buf, sizeof(buf)); + if (ret < 0) { + dev_err(chip->dev, "adc-tm block read failed with %d\n", ret); + goto config_fail; + } + + /* Set SID from virtual channel number */ + buf[0] = channel->adc_channel >> 8; + + /* Set TM channel number used and measurement interval */ + buf[1] &= ~ADC_TM_GEN2_TM_CH_SEL; + buf[1] |= FIELD_PREP(ADC_TM_GEN2_TM_CH_SEL, channel->channel); + buf[1] &= ~ADC_TM_GEN2_MEAS_INT_SEL; + buf[1] |= FIELD_PREP(ADC_TM_GEN2_MEAS_INT_SEL, MEAS_INT_1S); + + buf[2] &= ~ADC_TM_GEN2_CTL_DEC_RATIO_MASK; + buf[2] |= FIELD_PREP(ADC_TM_GEN2_CTL_DEC_RATIO_MASK, channel->decimation); + buf[2] &= ~ADC_TM_GEN2_CTL_CAL_SEL; + buf[2] |= FIELD_PREP(ADC_TM_GEN2_CTL_CAL_SEL, channel->cal_method); + + buf[3] = channel->avg_samples | ADC_TM_GEN2_FAST_AVG_EN; + + buf[4] = channel->adc_channel & 0xff; + + buf[5] = channel->hw_settle_time & ADC_TM_GEN2_HW_SETTLE_DELAY; + + /* High temperature corresponds to low voltage threshold */ + if (high != INT_MAX) { + channel->low_thr_en = true; + adc_code = qcom_adc_tm5_gen2_temp_res_scale(high); + put_unaligned_le16(adc_code, &buf[9]); + } else { + channel->low_thr_en = false; + } + + /* Low temperature corresponds to high voltage threshold */ + if (low != -INT_MAX) { + channel->high_thr_en = true; + adc_code = qcom_adc_tm5_gen2_temp_res_scale(low); + put_unaligned_le16(adc_code, &buf[11]); + } else { + channel->high_thr_en = false; + } + + buf[13] = ADC_TM_GEN2_MEAS_EN; + if (channel->high_thr_en) + buf[13] |= ADC_TM5_GEN2_HIGH_THR_INT_EN; + if (channel->low_thr_en) + buf[13] |= ADC_TM5_GEN2_LOW_THR_INT_EN; + + ret = adc_tm5_write(chip, ADC_TM_GEN2_SID, buf, sizeof(buf)); + if (ret) { + dev_err(chip->dev, "channel %d params write failed: %d\n", channel->channel, ret); + goto config_fail; + } + + ret = adc_tm5_gen2_conv_req(channel->chip); + if (ret < 0) + dev_err(chip->dev, "adc-tm channel configure failed with %d\n", ret); + +config_fail: + mutex_unlock(&chip->adc_mutex_lock); + return ret; +} + static int adc_tm5_set_trips(void *data, int low, int high) { struct adc_tm5_channel *channel = data; @@ -343,14 +651,14 @@ static int adc_tm5_set_trips(void *data, int low, int high) channel->channel, low, high); if (high == INT_MAX && low <= -INT_MAX) - ret = adc_tm5_disable_channel(channel); + ret = chip->data->disable_channel(channel); else - ret = adc_tm5_configure(channel, low, high); + ret = chip->data->configure(channel, low, high); return ret; } -static struct thermal_zone_of_device_ops adc_tm5_ops = { +static struct thermal_zone_of_device_ops adc_tm5_thermal_ops = { .get_temp = adc_tm5_get_temp, .set_trips = adc_tm5_set_trips, }; @@ -366,7 +674,7 @@ static int adc_tm5_register_tzd(struct adc_tm5_chip *adc_tm) tzd = devm_thermal_zone_of_sensor_register(adc_tm->dev, adc_tm->channels[i].channel, &adc_tm->channels[i], - &adc_tm5_ops); + &adc_tm5_thermal_ops); if (IS_ERR(tzd)) { if (PTR_ERR(tzd) == -ENODEV) { dev_warn(adc_tm->dev, "thermal sensor on channel %d is not used\n", @@ -442,12 +750,37 @@ static int adc_tm5_init(struct adc_tm5_chip *chip) return ret; } +static int adc_tm5_gen2_init(struct adc_tm5_chip *chip) +{ + u8 channels_available; + int ret; + unsigned int i; + + ret = adc_tm5_read(chip, ADC_TM5_NUM_BTM, + &channels_available, sizeof(channels_available)); + if (ret) { + dev_err(chip->dev, "read failed for BTM channels\n"); + return ret; + } + + for (i = 0; i < chip->nchannels; i++) { + if (chip->channels[i].channel >= channels_available) { + dev_err(chip->dev, "Invalid channel %d\n", chip->channels[i].channel); + return -EINVAL; + } + } + + mutex_init(&chip->adc_mutex_lock); + + return ret; +} + static int adc_tm5_get_dt_channel_data(struct adc_tm5_chip *adc_tm, struct adc_tm5_channel *channel, struct device_node *node) { const char *name = node->name; - u32 chan, value, varr[2]; + u32 chan, value, adc_channel, varr[2]; int ret; struct device *dev = adc_tm->dev; struct of_phandle_args args; @@ -477,7 +810,16 @@ static int adc_tm5_get_dt_channel_data(struct adc_tm5_chip *adc_tm, } of_node_put(args.np); - if (args.args_count != 1 || args.args[0] >= ADC5_MAX_CHANNEL) { + if (args.args_count != 1) { + dev_err(dev, "%s: invalid args count for ADC channel %d\n", name, chan); + return -EINVAL; + } + + adc_channel = args.args[0]; + if (adc_tm->data->gen == ADC_TM5_GEN2) + adc_channel &= 0xff; + + if (adc_channel >= ADC5_MAX_CHANNEL) { dev_err(dev, "%s: invalid ADC channel number %d\n", name, chan); return -EINVAL; } @@ -523,9 +865,76 @@ static int adc_tm5_get_dt_channel_data(struct adc_tm5_chip *adc_tm, else channel->cal_method = ADC_TM5_ABSOLUTE_CAL; + if (adc_tm->data->gen == ADC_TM5_GEN2) { + ret = of_property_read_u32(node, "qcom,decimation", &value); + if (!ret) { + ret = qcom_adc5_decimation_from_dt(value, adc_tm->data->decimation); + if (ret < 0) { + dev_err(dev, "invalid decimation %d\n", value); + return ret; + } + channel->decimation = ret; + } else { + channel->decimation = ADC5_DECIMATION_DEFAULT; + } + + ret = of_property_read_u32(node, "qcom,avg-samples", &value); + if (!ret) { + ret = qcom_adc5_avg_samples_from_dt(value); + if (ret < 0) { + dev_err(dev, "invalid avg-samples %d\n", value); + return ret; + } + channel->avg_samples = ret; + } else { + channel->avg_samples = VADC_DEF_AVG_SAMPLES; + } + } + return 0; } +static const struct adc_tm5_data adc_tm5_data_pmic = { + .full_scale_code_volt = 0x70e4, + .decimation = (unsigned int []) { 250, 420, 840 }, + .hw_settle = (unsigned int []) { 15, 100, 200, 300, 400, 500, 600, 700, + 1000, 2000, 4000, 8000, 16000, 32000, + 64000, 128000 }, + .disable_channel = adc_tm5_disable_channel, + .configure = adc_tm5_configure, + .isr = adc_tm5_isr, + .init = adc_tm5_init, + .irq_name = "pm-adc-tm5", + .gen = ADC_TM5, +}; + +static const struct adc_tm5_data adc_tm_hc_data_pmic = { + .full_scale_code_volt = 0x70e4, + .decimation = (unsigned int []) { 256, 512, 1024 }, + .hw_settle = (unsigned int []) { 0, 100, 200, 300, 400, 500, 600, 700, + 1000, 2000, 4000, 6000, 8000, 10000 }, + .disable_channel = adc_tm5_disable_channel, + .configure = adc_tm5_configure, + .isr = adc_tm5_isr, + .init = adc_tm_hc_init, + .irq_name = "pm-adc-tm5", + .gen = ADC_TM_HC, +}; + +static const struct adc_tm5_data adc_tm5_gen2_data_pmic = { + .full_scale_code_volt = 0x70e4, + .decimation = (unsigned int []) { 85, 340, 1360 }, + .hw_settle = (unsigned int []) { 15, 100, 200, 300, 400, 500, 600, 700, + 1000, 2000, 4000, 8000, 16000, 32000, + 64000, 128000 }, + .disable_channel = adc_tm5_gen2_disable_channel, + .configure = adc_tm5_gen2_configure, + .isr = adc_tm5_gen2_isr, + .init = adc_tm5_gen2_init, + .irq_name = "pm-adc-tm5-gen2", + .gen = ADC_TM5_GEN2, +}; + static int adc_tm5_get_dt_data(struct adc_tm5_chip *adc_tm, struct device_node *node) { struct adc_tm5_channel *channels; @@ -623,10 +1032,7 @@ static int adc_tm5_probe(struct platform_device *pdev) return ret; } - if (adc_tm->data->is_hc) - ret = adc_tm_hc_init(adc_tm); - else - ret = adc_tm5_init(adc_tm); + ret = adc_tm->data->init(adc_tm); if (ret) { dev_err(dev, "adc-tm init failed\n"); return ret; @@ -638,8 +1044,8 @@ static int adc_tm5_probe(struct platform_device *pdev) return ret; } - return devm_request_threaded_irq(dev, irq, NULL, adc_tm5_isr, - IRQF_ONESHOT, "pm-adc-tm5", adc_tm); + return devm_request_threaded_irq(dev, irq, NULL, adc_tm->data->isr, + IRQF_ONESHOT, adc_tm->data->irq_name, adc_tm); } static const struct of_device_id adc_tm5_match_table[] = { @@ -651,6 +1057,10 @@ static const struct of_device_id adc_tm5_match_table[] = { .compatible = "qcom,spmi-adc-tm-hc", .data = &adc_tm_hc_data_pmic, }, + { + .compatible = "qcom,spmi-adc-tm5-gen2", + .data = &adc_tm5_gen2_data_pmic, + }, { } }; MODULE_DEVICE_TABLE(of, adc_tm5_match_table); diff --git a/drivers/thermal/qcom/tsens.c b/drivers/thermal/qcom/tsens.c index 154d3cb19c88..7963ee33bf75 100644 --- a/drivers/thermal/qcom/tsens.c +++ b/drivers/thermal/qcom/tsens.c @@ -980,6 +980,9 @@ static const struct of_device_id tsens_table[] = { .compatible = "qcom,msm8939-tsens", .data = &data_8939, }, { + .compatible = "qcom,msm8960-tsens", + .data = &data_8960, + }, { .compatible = "qcom,msm8974-tsens", .data = &data_8974, }, { diff --git a/drivers/thermal/rcar_thermal.c b/drivers/thermal/rcar_thermal.c index b49f04daaf47..1d729ed4d685 100644 --- a/drivers/thermal/rcar_thermal.c +++ b/drivers/thermal/rcar_thermal.c @@ -445,7 +445,7 @@ static int rcar_thermal_probe(struct platform_device *pdev) struct rcar_thermal_common *common; struct rcar_thermal_priv *priv; struct device *dev = &pdev->dev; - struct resource *res, *irq; + struct resource *res; const struct rcar_thermal_chip *chip = of_device_get_match_data(dev); int mres = 0; int i; @@ -467,9 +467,16 @@ static int rcar_thermal_probe(struct platform_device *pdev) pm_runtime_get_sync(dev); for (i = 0; i < chip->nirqs; i++) { - irq = platform_get_resource(pdev, IORESOURCE_IRQ, i); - if (!irq) - continue; + int irq; + + ret = platform_get_irq_optional(pdev, i); + if (ret < 0 && ret != -ENXIO) + goto error_unregister; + if (ret > 0) + irq = ret; + else + break; + if (!common->base) { /* * platform has IRQ support. @@ -487,7 +494,7 @@ static int rcar_thermal_probe(struct platform_device *pdev) idle = 0; /* polling delay is not needed */ } - ret = devm_request_irq(dev, irq->start, rcar_thermal_irq, + ret = devm_request_irq(dev, irq, rcar_thermal_irq, IRQF_SHARED, dev_name(dev), common); if (ret) { dev_err(dev, "irq request failed\n "); diff --git a/drivers/thermal/rzg2l_thermal.c b/drivers/thermal/rzg2l_thermal.c index 7a9cdc1f37ca..be07e04c6926 100644 --- a/drivers/thermal/rzg2l_thermal.c +++ b/drivers/thermal/rzg2l_thermal.c @@ -32,6 +32,8 @@ #define TSU_SS 0x10 #define OTPTSUTRIM_REG(n) (0x18 + ((n) * 0x4)) +#define OTPTSUTRIM_EN_MASK BIT(31) +#define OTPTSUTRIM_MASK GENMASK(11, 0) /* Sensor Mode Register(TSU_SM) */ #define TSU_SM_EN_TS BIT(0) @@ -183,11 +185,15 @@ static int rzg2l_thermal_probe(struct platform_device *pdev) pm_runtime_get_sync(dev); priv->calib0 = rzg2l_thermal_read(priv, OTPTSUTRIM_REG(0)); - if (!priv->calib0) + if (priv->calib0 & OTPTSUTRIM_EN_MASK) + priv->calib0 &= OTPTSUTRIM_MASK; + else priv->calib0 = SW_CALIB0_VAL; priv->calib1 = rzg2l_thermal_read(priv, OTPTSUTRIM_REG(1)); - if (!priv->calib1) + if (priv->calib1 & OTPTSUTRIM_EN_MASK) + priv->calib1 &= OTPTSUTRIM_MASK; + else priv->calib1 = SW_CALIB1_VAL; platform_set_drvdata(pdev, priv); diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c index 82654dc8382b..cdc0552e8c42 100644 --- a/drivers/thermal/thermal_core.c +++ b/drivers/thermal/thermal_core.c @@ -947,6 +947,7 @@ __thermal_cooling_device_register(struct device_node *np, return cdev; out_kfree_type: + thermal_cooling_device_destroy_sysfs(cdev); kfree(cdev->type); put_device(&cdev->device); cdev = NULL; diff --git a/drivers/thermal/thermal_hwmon.c b/drivers/thermal/thermal_hwmon.c index ad03262cca56..09e49ec8b6f4 100644 --- a/drivers/thermal/thermal_hwmon.c +++ b/drivers/thermal/thermal_hwmon.c @@ -149,8 +149,8 @@ int thermal_add_hwmon_sysfs(struct thermal_zone_device *tz) INIT_LIST_HEAD(&hwmon->tz_list); strlcpy(hwmon->type, tz->type, THERMAL_NAME_LENGTH); strreplace(hwmon->type, '-', '_'); - hwmon->device = hwmon_device_register_with_info(&tz->device, hwmon->type, - hwmon, NULL, NULL); + hwmon->device = hwmon_device_register_for_thermal(&tz->device, + hwmon->type, hwmon); if (IS_ERR(hwmon->device)) { result = PTR_ERR(hwmon->device); goto free_mem; @@ -277,3 +277,5 @@ int devm_thermal_add_hwmon_sysfs(struct thermal_zone_device *tz) return ret; } EXPORT_SYMBOL_GPL(devm_thermal_add_hwmon_sysfs); + +MODULE_IMPORT_NS(HWMON_THERMAL); diff --git a/drivers/thermal/thermal_of.c b/drivers/thermal/thermal_of.c index 9233f7e74454..b65d435cb92f 100644 --- a/drivers/thermal/thermal_of.c +++ b/drivers/thermal/thermal_of.c @@ -35,7 +35,7 @@ struct __thermal_cooling_bind_param { }; /** - * struct __thermal_bind_param - a match between trip and cooling device + * struct __thermal_bind_params - a match between trip and cooling device * @tcbp: a pointer to an array of cooling devices * @count: number of elements in array * @trip_id: the trip point index @@ -203,6 +203,14 @@ static int of_thermal_get_trend(struct thermal_zone_device *tz, int trip, return data->ops->get_trend(data->sensor_data, trip, trend); } +static int of_thermal_change_mode(struct thermal_zone_device *tz, + enum thermal_device_mode mode) +{ + struct __thermal_zone *data = tz->devdata; + + return data->ops->change_mode(data->sensor_data, mode); +} + static int of_thermal_bind(struct thermal_zone_device *thermal, struct thermal_cooling_device *cdev) { @@ -408,6 +416,9 @@ thermal_zone_of_add_sensor(struct device_node *zone, if (ops->set_emul_temp) tzd->ops->set_emul_temp = of_thermal_set_emul_temp; + if (ops->change_mode) + tzd->ops->change_mode = of_thermal_change_mode; + mutex_unlock(&tzd->lock); return tzd; @@ -569,6 +580,7 @@ void thermal_zone_of_sensor_unregister(struct device *dev, tzd->ops->get_temp = NULL; tzd->ops->get_trend = NULL; tzd->ops->set_emul_temp = NULL; + tzd->ops->change_mode = NULL; tz->ops = NULL; tz->sensor_data = NULL; diff --git a/drivers/thermal/thermal_sysfs.c b/drivers/thermal/thermal_sysfs.c index f154bada2906..1c4aac8464a7 100644 --- a/drivers/thermal/thermal_sysfs.c +++ b/drivers/thermal/thermal_sysfs.c @@ -610,9 +610,6 @@ cur_state_store(struct device *dev, struct device_attribute *attr, unsigned long state; int result; - dev_warn_once(&cdev->device, - "Setting cooling device state is deprecated\n"); - if (sscanf(buf, "%ld\n", &state) != 1) return -EINVAL; diff --git a/drivers/tty/goldfish.c b/drivers/tty/goldfish.c index ad13532e92fe..9e8ccb8ed6d6 100644 --- a/drivers/tty/goldfish.c +++ b/drivers/tty/goldfish.c @@ -61,13 +61,13 @@ static void do_rw_io(struct goldfish_tty *qtty, spin_lock_irqsave(&qtty->lock, irq_flags); gf_write_ptr((void *)address, base + GOLDFISH_TTY_REG_DATA_PTR, base + GOLDFISH_TTY_REG_DATA_PTR_HIGH); - __raw_writel(count, base + GOLDFISH_TTY_REG_DATA_LEN); + gf_iowrite32(count, base + GOLDFISH_TTY_REG_DATA_LEN); if (is_write) - __raw_writel(GOLDFISH_TTY_CMD_WRITE_BUFFER, + gf_iowrite32(GOLDFISH_TTY_CMD_WRITE_BUFFER, base + GOLDFISH_TTY_REG_CMD); else - __raw_writel(GOLDFISH_TTY_CMD_READ_BUFFER, + gf_iowrite32(GOLDFISH_TTY_CMD_READ_BUFFER, base + GOLDFISH_TTY_REG_CMD); spin_unlock_irqrestore(&qtty->lock, irq_flags); @@ -142,7 +142,7 @@ static irqreturn_t goldfish_tty_interrupt(int irq, void *dev_id) unsigned char *buf; u32 count; - count = __raw_readl(base + GOLDFISH_TTY_REG_BYTES_READY); + count = gf_ioread32(base + GOLDFISH_TTY_REG_BYTES_READY); if (count == 0) return IRQ_NONE; @@ -159,7 +159,7 @@ static int goldfish_tty_activate(struct tty_port *port, struct tty_struct *tty) { struct goldfish_tty *qtty = container_of(port, struct goldfish_tty, port); - __raw_writel(GOLDFISH_TTY_CMD_INT_ENABLE, qtty->base + GOLDFISH_TTY_REG_CMD); + gf_iowrite32(GOLDFISH_TTY_CMD_INT_ENABLE, qtty->base + GOLDFISH_TTY_REG_CMD); return 0; } @@ -167,7 +167,7 @@ static void goldfish_tty_shutdown(struct tty_port *port) { struct goldfish_tty *qtty = container_of(port, struct goldfish_tty, port); - __raw_writel(GOLDFISH_TTY_CMD_INT_DISABLE, qtty->base + GOLDFISH_TTY_REG_CMD); + gf_iowrite32(GOLDFISH_TTY_CMD_INT_DISABLE, qtty->base + GOLDFISH_TTY_REG_CMD); } static int goldfish_tty_open(struct tty_struct *tty, struct file *filp) @@ -202,7 +202,7 @@ static unsigned int goldfish_tty_chars_in_buffer(struct tty_struct *tty) { struct goldfish_tty *qtty = &goldfish_ttys[tty->index]; void __iomem *base = qtty->base; - return __raw_readl(base + GOLDFISH_TTY_REG_BYTES_READY); + return gf_ioread32(base + GOLDFISH_TTY_REG_BYTES_READY); } static void goldfish_tty_console_write(struct console *co, const char *b, @@ -355,7 +355,7 @@ static int goldfish_tty_probe(struct platform_device *pdev) * on Ranchu emulator (qemu2) returns 1 here and * driver will use physical addresses. */ - qtty->version = __raw_readl(base + GOLDFISH_TTY_REG_VERSION); + qtty->version = gf_ioread32(base + GOLDFISH_TTY_REG_VERSION); /* * Goldfish TTY device on Ranchu emulator (qemu2) @@ -374,7 +374,7 @@ static int goldfish_tty_probe(struct platform_device *pdev) } } - __raw_writel(GOLDFISH_TTY_CMD_INT_DISABLE, base + GOLDFISH_TTY_REG_CMD); + gf_iowrite32(GOLDFISH_TTY_CMD_INT_DISABLE, base + GOLDFISH_TTY_REG_CMD); ret = request_irq(irq, goldfish_tty_interrupt, IRQF_SHARED, "goldfish_tty", qtty); @@ -436,7 +436,7 @@ static int goldfish_tty_remove(struct platform_device *pdev) #ifdef CONFIG_GOLDFISH_TTY_EARLY_CONSOLE static void gf_early_console_putchar(struct uart_port *port, unsigned char ch) { - __raw_writel(ch, port->membase); + gf_iowrite32(ch, port->membase); } static void gf_early_write(struct console *con, const char *s, unsigned int n) diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c index fa92f727fdf8..fd8b86dde525 100644 --- a/drivers/tty/n_gsm.c +++ b/drivers/tty/n_gsm.c @@ -73,6 +73,8 @@ module_param(debug, int, 0600); */ #define MAX_MRU 1500 #define MAX_MTU 1500 +/* SOF, ADDR, CTRL, LEN1, LEN2, ..., FCS, EOF */ +#define PROT_OVERHEAD 7 #define GSM_NET_TX_TIMEOUT (HZ*10) /* @@ -135,6 +137,7 @@ struct gsm_dlci { int retries; /* Uplink tty if active */ struct tty_port port; /* The tty bound to this DLCI if there is one */ +#define TX_SIZE 4096 /* Must be power of 2. */ struct kfifo fifo; /* Queue fifo for the DLCI */ int adaption; /* Adaption layer in use */ int prev_adaption; @@ -219,7 +222,6 @@ struct gsm_mux { int encoding; u8 control; u8 fcs; - u8 received_fcs; u8 *txframe; /* TX framing buffer */ /* Method for the receiver side */ @@ -231,6 +233,7 @@ struct gsm_mux { int initiator; /* Did we initiate connection */ bool dead; /* Has the mux been shut down */ struct gsm_dlci *dlci[NUM_DLCI]; + int old_c_iflag; /* termios c_iflag value before attach */ bool constipated; /* Asked by remote to shut up */ spinlock_t tx_lock; @@ -271,10 +274,6 @@ static DEFINE_SPINLOCK(gsm_mux_lock); static struct tty_driver *gsm_tty_driver; -/* Save dlci open address */ -static int addr_open[256] = { 0 }; -/* Save dlci open count */ -static int addr_cnt; /* * This section of the driver logic implements the GSM encodings * both the basic and the 'advanced'. Reliable transport is not @@ -369,6 +368,7 @@ static const u8 gsm_fcs8[256] = { #define GOOD_FCS 0xCF static int gsmld_output(struct gsm_mux *gsm, u8 *data, int len); +static int gsm_modem_update(struct gsm_dlci *dlci, u8 brk); /** * gsm_fcs_add - update FCS @@ -832,7 +832,7 @@ static int gsm_dlci_data_output(struct gsm_mux *gsm, struct gsm_dlci *dlci) break; case 2: /* Unstructed with modem bits. Always one byte as we never send inline break data */ - *dp++ = gsm_encode_modem(dlci); + *dp++ = (gsm_encode_modem(dlci) << 1) | EA; break; } WARN_ON(kfifo_out_locked(&dlci->fifo, dp , len, &dlci->lock) != len); @@ -917,6 +917,66 @@ static int gsm_dlci_data_output_framed(struct gsm_mux *gsm, } /** + * gsm_dlci_modem_output - try and push modem status out of a DLCI + * @gsm: mux + * @dlci: the DLCI to pull modem status from + * @brk: break signal + * + * Push an empty frame in to the transmit queue to update the modem status + * bits and to transmit an optional break. + * + * Caller must hold the tx_lock of the mux. + */ + +static int gsm_dlci_modem_output(struct gsm_mux *gsm, struct gsm_dlci *dlci, + u8 brk) +{ + u8 *dp = NULL; + struct gsm_msg *msg; + int size = 0; + + /* for modem bits without break data */ + switch (dlci->adaption) { + case 1: /* Unstructured */ + break; + case 2: /* Unstructured with modem bits. */ + size++; + if (brk > 0) + size++; + break; + default: + pr_err("%s: unsupported adaption %d\n", __func__, + dlci->adaption); + return -EINVAL; + } + + msg = gsm_data_alloc(gsm, dlci->addr, size, gsm->ftype); + if (!msg) { + pr_err("%s: gsm_data_alloc error", __func__); + return -ENOMEM; + } + dp = msg->data; + switch (dlci->adaption) { + case 1: /* Unstructured */ + break; + case 2: /* Unstructured with modem bits. */ + if (brk == 0) { + *dp++ = (gsm_encode_modem(dlci) << 1) | EA; + } else { + *dp++ = gsm_encode_modem(dlci) << 1; + *dp++ = (brk << 4) | 2 | EA; /* Length, Break, EA */ + } + break; + default: + /* Handled above */ + break; + } + + __gsm_data_queue(dlci, msg); + return size; +} + +/** * gsm_dlci_data_sweep - look for data to send * @gsm: the GSM mux * @@ -1093,7 +1153,6 @@ static void gsm_control_modem(struct gsm_mux *gsm, const u8 *data, int clen) { unsigned int addr = 0; unsigned int modem = 0; - unsigned int brk = 0; struct gsm_dlci *dlci; int len = clen; int slen; @@ -1123,17 +1182,8 @@ static void gsm_control_modem(struct gsm_mux *gsm, const u8 *data, int clen) return; } len--; - if (len > 0) { - while (gsm_read_ea(&brk, *dp++) == 0) { - len--; - if (len == 0) - return; - } - modem <<= 7; - modem |= (brk & 0x7f); - } tty = tty_port_tty_get(&dlci->port); - gsm_process_modem(tty, dlci, modem, slen); + gsm_process_modem(tty, dlci, modem, slen - len); if (tty) { tty_wakeup(tty); tty_kref_put(tty); @@ -1193,7 +1243,6 @@ static void gsm_control_rls(struct gsm_mux *gsm, const u8 *data, int clen) } static void gsm_dlci_begin_close(struct gsm_dlci *dlci); -static void gsm_dlci_close(struct gsm_dlci *dlci); /** * gsm_control_message - DLCI 0 control processing @@ -1212,28 +1261,15 @@ static void gsm_control_message(struct gsm_mux *gsm, unsigned int command, { u8 buf[1]; unsigned long flags; - struct gsm_dlci *dlci; - int i; - int address; switch (command) { case CMD_CLD: { - if (addr_cnt > 0) { - for (i = 0; i < addr_cnt; i++) { - address = addr_open[i]; - dlci = gsm->dlci[address]; - gsm_dlci_close(dlci); - addr_open[i] = 0; - } - } + struct gsm_dlci *dlci = gsm->dlci[0]; /* Modem wishes to close down */ - dlci = gsm->dlci[0]; if (dlci) { dlci->dead = true; gsm->dead = true; - gsm_dlci_close(dlci); - addr_cnt = 0; - gsm_response(gsm, 0, UA|PF); + gsm_dlci_begin_close(dlci); } } break; @@ -1326,11 +1362,12 @@ static void gsm_control_response(struct gsm_mux *gsm, unsigned int command, static void gsm_control_transmit(struct gsm_mux *gsm, struct gsm_control *ctrl) { - struct gsm_msg *msg = gsm_data_alloc(gsm, 0, ctrl->len + 1, gsm->ftype); + struct gsm_msg *msg = gsm_data_alloc(gsm, 0, ctrl->len + 2, gsm->ftype); if (msg == NULL) return; - msg->data[0] = (ctrl->cmd << 1) | 2 | EA; /* command */ - memcpy(msg->data + 1, ctrl->data, ctrl->len); + msg->data[0] = (ctrl->cmd << 1) | CR | EA; /* command */ + msg->data[1] = (ctrl->len << 1) | EA; + memcpy(msg->data + 2, ctrl->data, ctrl->len); gsm_data_queue(gsm->dlci[0], msg); } @@ -1353,7 +1390,6 @@ static void gsm_control_retransmit(struct timer_list *t) spin_lock_irqsave(&gsm->control_lock, flags); ctrl = gsm->pending_cmd; if (ctrl) { - gsm->cretries--; if (gsm->cretries == 0) { gsm->pending_cmd = NULL; ctrl->error = -ETIMEDOUT; @@ -1362,6 +1398,7 @@ static void gsm_control_retransmit(struct timer_list *t) wake_up(&gsm->event); return; } + gsm->cretries--; gsm_control_transmit(gsm, ctrl); mod_timer(&gsm->t2_timer, jiffies + gsm->t2 * HZ / 100); } @@ -1402,7 +1439,7 @@ retry: /* If DLCI0 is in ADM mode skip retries, it won't respond */ if (gsm->dlci[0]->mode == DLCI_MODE_ADM) - gsm->cretries = 1; + gsm->cretries = 0; else gsm->cretries = gsm->n2; @@ -1450,20 +1487,22 @@ static int gsm_control_wait(struct gsm_mux *gsm, struct gsm_control *control) static void gsm_dlci_close(struct gsm_dlci *dlci) { + unsigned long flags; + del_timer(&dlci->t1); if (debug & 8) pr_debug("DLCI %d goes closed.\n", dlci->addr); dlci->state = DLCI_CLOSED; if (dlci->addr != 0) { tty_port_tty_hangup(&dlci->port, false); + spin_lock_irqsave(&dlci->lock, flags); kfifo_reset(&dlci->fifo); + spin_unlock_irqrestore(&dlci->lock, flags); /* Ensure that gsmtty_open() can return. */ tty_port_set_initialized(&dlci->port, 0); wake_up_interruptible(&dlci->port.open_wait); } else dlci->gsm->dead = true; - /* Unregister gsmtty driver,report gsmtty dev remove uevent for user */ - tty_unregister_device(gsm_tty_driver, dlci->addr); wake_up(&dlci->gsm->event); /* A DLCI 0 close is a MUX termination so we need to kick that back to userspace somehow */ @@ -1485,8 +1524,9 @@ static void gsm_dlci_open(struct gsm_dlci *dlci) dlci->state = DLCI_OPEN; if (debug & 8) pr_debug("DLCI %d goes open.\n", dlci->addr); - /* Register gsmtty driver,report gsmtty dev add uevent for user */ - tty_register_device(gsm_tty_driver, dlci->addr, NULL); + /* Send current modem state */ + if (dlci->addr) + gsm_modem_update(dlci, 0); wake_up(&dlci->gsm->event); } @@ -1619,10 +1659,12 @@ static void gsm_dlci_data(struct gsm_dlci *dlci, const u8 *data, int clen) if (len == 0) return; } + len--; slen++; tty = tty_port_tty_get(port); if (tty) { gsm_process_modem(tty, dlci, modem, slen); + tty_wakeup(tty); tty_kref_put(tty); } fallthrough; @@ -1690,7 +1732,7 @@ static struct gsm_dlci *gsm_dlci_alloc(struct gsm_mux *gsm, int addr) return NULL; spin_lock_init(&dlci->lock); mutex_init(&dlci->mutex); - if (kfifo_alloc(&dlci->fifo, 4096, GFP_KERNEL) < 0) { + if (kfifo_alloc(&dlci->fifo, TX_SIZE, GFP_KERNEL) < 0) { kfree(dlci); return NULL; } @@ -1793,19 +1835,7 @@ static void gsm_queue(struct gsm_mux *gsm) struct gsm_dlci *dlci; u8 cr; int address; - int i, j, k, address_tmp; - /* We have to sneak a look at the packet body to do the FCS. - A somewhat layering violation in the spec */ - if ((gsm->control & ~PF) == UI) - gsm->fcs = gsm_fcs_add_block(gsm->fcs, gsm->buf, gsm->len); - if (gsm->encoding == 0) { - /* WARNING: gsm->received_fcs is used for - gsm->encoding = 0 only. - In this case it contain the last piece of data - required to generate final CRC */ - gsm->fcs = gsm_fcs_add(gsm->fcs, gsm->received_fcs); - } if (gsm->fcs != GOOD_FCS) { gsm->bad_fcs++; if (debug & 4) @@ -1836,11 +1866,6 @@ static void gsm_queue(struct gsm_mux *gsm) else { gsm_response(gsm, address, UA|PF); gsm_dlci_open(dlci); - /* Save dlci open address */ - if (address) { - addr_open[addr_cnt] = address; - addr_cnt++; - } } break; case DISC|PF: @@ -1851,35 +1876,9 @@ static void gsm_queue(struct gsm_mux *gsm) return; } /* Real close complete */ - if (!address) { - if (addr_cnt > 0) { - for (i = 0; i < addr_cnt; i++) { - address = addr_open[i]; - dlci = gsm->dlci[address]; - gsm_dlci_close(dlci); - addr_open[i] = 0; - } - } - dlci = gsm->dlci[0]; - gsm_dlci_close(dlci); - addr_cnt = 0; - gsm_response(gsm, 0, UA|PF); - } else { - gsm_response(gsm, address, UA|PF); - gsm_dlci_close(dlci); - /* clear dlci address */ - for (j = 0; j < addr_cnt; j++) { - address_tmp = addr_open[j]; - if (address_tmp == address) { - for (k = j; k < addr_cnt; k++) - addr_open[k] = addr_open[k+1]; - addr_cnt--; - break; - } - } - } + gsm_response(gsm, address, UA|PF); + gsm_dlci_close(dlci); break; - case UA: case UA|PF: if (cr == 0 || dlci == NULL) break; @@ -1993,19 +1992,25 @@ static void gsm0_receive(struct gsm_mux *gsm, unsigned char c) break; case GSM_DATA: /* Data */ gsm->buf[gsm->count++] = c; - if (gsm->count == gsm->len) + if (gsm->count == gsm->len) { + /* Calculate final FCS for UI frames over all data */ + if ((gsm->control & ~PF) != UIH) { + gsm->fcs = gsm_fcs_add_block(gsm->fcs, gsm->buf, + gsm->count); + } gsm->state = GSM_FCS; + } break; case GSM_FCS: /* FCS follows the packet */ - gsm->received_fcs = c; - gsm_queue(gsm); + gsm->fcs = gsm_fcs_add(gsm->fcs, c); gsm->state = GSM_SSOF; break; case GSM_SSOF: - if (c == GSM0_SOF) { - gsm->state = GSM_SEARCH; - break; - } + gsm->state = GSM_SEARCH; + if (c == GSM0_SOF) + gsm_queue(gsm); + else + gsm->bad_size++; break; default: pr_debug("%s: unhandled state: %d\n", __func__, gsm->state); @@ -2023,12 +2028,35 @@ static void gsm0_receive(struct gsm_mux *gsm, unsigned char c) static void gsm1_receive(struct gsm_mux *gsm, unsigned char c) { + /* handle XON/XOFF */ + if ((c & ISO_IEC_646_MASK) == XON) { + gsm->constipated = true; + return; + } else if ((c & ISO_IEC_646_MASK) == XOFF) { + gsm->constipated = false; + /* Kick the link in case it is idling */ + gsm_data_kick(gsm, NULL); + return; + } if (c == GSM1_SOF) { - /* EOF is only valid in frame if we have got to the data state - and received at least one byte (the FCS) */ - if (gsm->state == GSM_DATA && gsm->count) { - /* Extract the FCS */ + /* EOF is only valid in frame if we have got to the data state */ + if (gsm->state == GSM_DATA) { + if (gsm->count < 1) { + /* Missing FSC */ + gsm->malformed++; + gsm->state = GSM_START; + return; + } + /* Remove the FCS from data */ gsm->count--; + if ((gsm->control & ~PF) != UIH) { + /* Calculate final FCS for UI frames over all + * data but FCS + */ + gsm->fcs = gsm_fcs_add_block(gsm->fcs, gsm->buf, + gsm->count); + } + /* Add the FCS itself to test against GOOD_FCS */ gsm->fcs = gsm_fcs_add(gsm->fcs, gsm->buf[gsm->count]); gsm->len = gsm->count; gsm_queue(gsm); @@ -2037,7 +2065,8 @@ static void gsm1_receive(struct gsm_mux *gsm, unsigned char c) } /* Any partial frame was a runt so go back to start */ if (gsm->state != GSM_START) { - gsm->malformed++; + if (gsm->state != GSM_SEARCH) + gsm->malformed++; gsm->state = GSM_START; } /* A SOF in GSM_START means we are still reading idling or @@ -2106,74 +2135,43 @@ static void gsm_error(struct gsm_mux *gsm) gsm->io_error++; } -static int gsm_disconnect(struct gsm_mux *gsm) -{ - struct gsm_dlci *dlci = gsm->dlci[0]; - struct gsm_control *gc; - - if (!dlci) - return 0; - - /* In theory disconnecting DLCI 0 is sufficient but for some - modems this is apparently not the case. */ - gc = gsm_control_send(gsm, CMD_CLD, NULL, 0); - if (gc) - gsm_control_wait(gsm, gc); - - del_timer_sync(&gsm->t2_timer); - /* Now we are sure T2 has stopped */ - - gsm_dlci_begin_close(dlci); - wait_event_interruptible(gsm->event, - dlci->state == DLCI_CLOSED); - - if (signal_pending(current)) - return -EINTR; - - return 0; -} - /** * gsm_cleanup_mux - generic GSM protocol cleanup * @gsm: our mux + * @disc: disconnect link? * * Clean up the bits of the mux which are the same for all framing * protocols. Remove the mux from the mux table, stop all the timers * and then shut down each device hanging up the channels as we go. */ -static void gsm_cleanup_mux(struct gsm_mux *gsm) +static void gsm_cleanup_mux(struct gsm_mux *gsm, bool disc) { int i; struct gsm_dlci *dlci = gsm->dlci[0]; struct gsm_msg *txq, *ntxq; gsm->dead = true; + mutex_lock(&gsm->mutex); - spin_lock(&gsm_mux_lock); - for (i = 0; i < MAX_MUX; i++) { - if (gsm_mux[i] == gsm) { - gsm_mux[i] = NULL; - break; + if (dlci) { + if (disc && dlci->state != DLCI_CLOSED) { + gsm_dlci_begin_close(dlci); + wait_event(gsm->event, dlci->state == DLCI_CLOSED); } + dlci->dead = true; } - spin_unlock(&gsm_mux_lock); - /* open failed before registering => nothing to do */ - if (i == MAX_MUX) - return; + /* Finish outstanding timers, making sure they are done */ del_timer_sync(&gsm->t2_timer); - /* Now we are sure T2 has stopped */ - if (dlci) - dlci->dead = true; - /* Free up any link layer users */ - mutex_lock(&gsm->mutex); - for (i = 0; i < NUM_DLCI; i++) + /* Free up any link layer users and finally the control channel */ + for (i = NUM_DLCI - 1; i >= 0; i--) if (gsm->dlci[i]) gsm_dlci_release(gsm->dlci[i]); mutex_unlock(&gsm->mutex); /* Now wipe the queues */ + tty_ldisc_flush(gsm->tty); list_for_each_entry_safe(txq, ntxq, &gsm->tx_list, list) kfree(txq); INIT_LIST_HEAD(&gsm->tx_list); @@ -2191,7 +2189,6 @@ static void gsm_cleanup_mux(struct gsm_mux *gsm) static int gsm_activate_mux(struct gsm_mux *gsm) { struct gsm_dlci *dlci; - int i = 0; timer_setup(&gsm->t2_timer, gsm_control_retransmit, 0); init_waitqueue_head(&gsm->event); @@ -2203,18 +2200,6 @@ static int gsm_activate_mux(struct gsm_mux *gsm) else gsm->receive = gsm1_receive; - spin_lock(&gsm_mux_lock); - for (i = 0; i < MAX_MUX; i++) { - if (gsm_mux[i] == NULL) { - gsm->num = i; - gsm_mux[i] = gsm; - break; - } - } - spin_unlock(&gsm_mux_lock); - if (i == MAX_MUX) - return -EBUSY; - dlci = gsm_dlci_alloc(gsm, 0); if (dlci == NULL) return -ENOMEM; @@ -2230,6 +2215,15 @@ static int gsm_activate_mux(struct gsm_mux *gsm) */ static void gsm_free_mux(struct gsm_mux *gsm) { + int i; + + for (i = 0; i < MAX_MUX; i++) { + if (gsm == gsm_mux[i]) { + gsm_mux[i] = NULL; + break; + } + } + mutex_destroy(&gsm->mutex); kfree(gsm->txframe); kfree(gsm->buf); kfree(gsm); @@ -2249,12 +2243,20 @@ static void gsm_free_muxr(struct kref *ref) static inline void mux_get(struct gsm_mux *gsm) { + unsigned long flags; + + spin_lock_irqsave(&gsm_mux_lock, flags); kref_get(&gsm->ref); + spin_unlock_irqrestore(&gsm_mux_lock, flags); } static inline void mux_put(struct gsm_mux *gsm) { + unsigned long flags; + + spin_lock_irqsave(&gsm_mux_lock, flags); kref_put(&gsm->ref, gsm_free_muxr); + spin_unlock_irqrestore(&gsm_mux_lock, flags); } static inline unsigned int mux_num_to_base(struct gsm_mux *gsm) @@ -2275,6 +2277,7 @@ static inline unsigned int mux_line_to_num(unsigned int line) static struct gsm_mux *gsm_alloc_mux(void) { + int i; struct gsm_mux *gsm = kzalloc(sizeof(struct gsm_mux), GFP_KERNEL); if (gsm == NULL) return NULL; @@ -2283,7 +2286,7 @@ static struct gsm_mux *gsm_alloc_mux(void) kfree(gsm); return NULL; } - gsm->txframe = kmalloc(2 * MAX_MRU + 2, GFP_KERNEL); + gsm->txframe = kmalloc(2 * (MAX_MTU + PROT_OVERHEAD - 1), GFP_KERNEL); if (gsm->txframe == NULL) { kfree(gsm->buf); kfree(gsm); @@ -2304,6 +2307,26 @@ static struct gsm_mux *gsm_alloc_mux(void) gsm->mtu = 64; gsm->dead = true; /* Avoid early tty opens */ + /* Store the instance to the mux array or abort if no space is + * available. + */ + spin_lock(&gsm_mux_lock); + for (i = 0; i < MAX_MUX; i++) { + if (!gsm_mux[i]) { + gsm_mux[i] = gsm; + gsm->num = i; + break; + } + } + spin_unlock(&gsm_mux_lock); + if (i == MAX_MUX) { + mutex_destroy(&gsm->mutex); + kfree(gsm->txframe); + kfree(gsm->buf); + kfree(gsm); + return NULL; + } + return gsm; } @@ -2330,6 +2353,7 @@ static void gsm_copy_config_values(struct gsm_mux *gsm, static int gsm_config(struct gsm_mux *gsm, struct gsm_config *c) { + int ret = 0; int need_close = 0; int need_restart = 0; @@ -2339,7 +2363,7 @@ static int gsm_config(struct gsm_mux *gsm, struct gsm_config *c) /* Check the MRU/MTU range looks sane */ if (c->mru > MAX_MRU || c->mtu > MAX_MTU || c->mru < 8 || c->mtu < 8) return -EINVAL; - if (c->n2 < 3) + if (c->n2 > 255) return -EINVAL; if (c->encapsulation > 1) /* Basic, advanced, no I */ return -EINVAL; @@ -2370,19 +2394,11 @@ static int gsm_config(struct gsm_mux *gsm, struct gsm_config *c) /* * Close down what is needed, restart and initiate the new - * configuration + * configuration. On the first time there is no DLCI[0] + * and closing or cleaning up is not necessary. */ - - if (gsm->initiator && (need_close || need_restart)) { - int ret; - - ret = gsm_disconnect(gsm); - - if (ret) - return ret; - } - if (need_restart) - gsm_cleanup_mux(gsm); + if (need_close || need_restart) + gsm_cleanup_mux(gsm, true); gsm->initiator = c->initiator; gsm->mru = c->mru; @@ -2405,10 +2421,13 @@ static int gsm_config(struct gsm_mux *gsm, struct gsm_config *c) * FIXME: We need to separate activation/deactivation from adding * and removing from the mux array */ - if (need_restart) - gsm_activate_mux(gsm); - if (gsm->initiator && need_close) - gsm_dlci_begin_open(gsm->dlci[0]); + if (gsm->dead) { + ret = gsm_activate_mux(gsm); + if (ret) + return ret; + if (gsm->initiator) + gsm_dlci_begin_open(gsm->dlci[0]); + } return 0; } @@ -2450,25 +2469,26 @@ static int gsmld_attach_gsm(struct tty_struct *tty, struct gsm_mux *gsm) int ret, i; gsm->tty = tty_kref_get(tty); + /* Turn off tty XON/XOFF handling to handle it explicitly. */ + gsm->old_c_iflag = tty->termios.c_iflag; + tty->termios.c_iflag &= (IXON | IXOFF); ret = gsm_activate_mux(gsm); if (ret != 0) tty_kref_put(gsm->tty); else { /* Don't register device 0 - this is the control channel and not a usable tty interface */ - if (gsm->initiator) { - base = mux_num_to_base(gsm); /* Base for this MUX */ - for (i = 1; i < NUM_DLCI; i++) { - struct device *dev; + base = mux_num_to_base(gsm); /* Base for this MUX */ + for (i = 1; i < NUM_DLCI; i++) { + struct device *dev; - dev = tty_register_device(gsm_tty_driver, + dev = tty_register_device(gsm_tty_driver, base + i, NULL); - if (IS_ERR(dev)) { - for (i--; i >= 1; i--) - tty_unregister_device(gsm_tty_driver, - base + i); - return PTR_ERR(dev); - } + if (IS_ERR(dev)) { + for (i--; i >= 1; i--) + tty_unregister_device(gsm_tty_driver, + base + i); + return PTR_ERR(dev); } } } @@ -2490,11 +2510,10 @@ static void gsmld_detach_gsm(struct tty_struct *tty, struct gsm_mux *gsm) int i; WARN_ON(tty != gsm->tty); - if (gsm->initiator) { - for (i = 1; i < NUM_DLCI; i++) - tty_unregister_device(gsm_tty_driver, base + i); - } - gsm_cleanup_mux(gsm); + for (i = 1; i < NUM_DLCI; i++) + tty_unregister_device(gsm_tty_driver, base + i); + /* Restore tty XON/XOFF handling. */ + gsm->tty->termios.c_iflag = gsm->old_c_iflag; tty_kref_put(gsm->tty); gsm->tty = NULL; } @@ -2559,6 +2578,12 @@ static void gsmld_close(struct tty_struct *tty) { struct gsm_mux *gsm = tty->disc_data; + /* The ldisc locks and closes the port before calling our close. This + * means we have no way to do a proper disconnect. We will not bother + * to do one. + */ + gsm_cleanup_mux(gsm, false); + gsmld_detach_gsm(tty, gsm); gsmld_flush_buffer(tty); @@ -2597,7 +2622,7 @@ static int gsmld_open(struct tty_struct *tty) ret = gsmld_attach_gsm(tty, gsm); if (ret != 0) { - gsm_cleanup_mux(gsm); + gsm_cleanup_mux(gsm, false); mux_put(gsm); } return ret; @@ -2952,28 +2977,78 @@ static struct tty_ldisc_ops tty_ldisc_packet = { * Virtual tty side */ -#define TX_SIZE 512 +/** + * gsm_modem_upd_via_data - send modem bits via convergence layer + * @dlci: channel + * @brk: break signal + * + * Send an empty frame to signal mobile state changes and to transmit the + * break signal for adaption 2. + */ + +static void gsm_modem_upd_via_data(struct gsm_dlci *dlci, u8 brk) +{ + struct gsm_mux *gsm = dlci->gsm; + unsigned long flags; + + if (dlci->state != DLCI_OPEN || dlci->adaption != 2) + return; + + spin_lock_irqsave(&gsm->tx_lock, flags); + gsm_dlci_modem_output(gsm, dlci, brk); + spin_unlock_irqrestore(&gsm->tx_lock, flags); +} + +/** + * gsm_modem_upd_via_msc - send modem bits via control frame + * @dlci: channel + * @brk: break signal + */ -static int gsmtty_modem_update(struct gsm_dlci *dlci, u8 brk) +static int gsm_modem_upd_via_msc(struct gsm_dlci *dlci, u8 brk) { - u8 modembits[5]; + u8 modembits[3]; struct gsm_control *ctrl; int len = 2; - if (brk) - len++; + if (dlci->gsm->encoding != 0) + return 0; - modembits[0] = len << 1 | EA; /* Data bytes */ - modembits[1] = dlci->addr << 2 | 3; /* DLCI, EA, 1 */ - modembits[2] = gsm_encode_modem(dlci) << 1 | EA; - if (brk) - modembits[3] = brk << 4 | 2 | EA; /* Valid, EA */ - ctrl = gsm_control_send(dlci->gsm, CMD_MSC, modembits, len + 1); + modembits[0] = (dlci->addr << 2) | 2 | EA; /* DLCI, Valid, EA */ + if (!brk) { + modembits[1] = (gsm_encode_modem(dlci) << 1) | EA; + } else { + modembits[1] = gsm_encode_modem(dlci) << 1; + modembits[2] = (brk << 4) | 2 | EA; /* Length, Break, EA */ + len++; + } + ctrl = gsm_control_send(dlci->gsm, CMD_MSC, modembits, len); if (ctrl == NULL) return -ENOMEM; return gsm_control_wait(dlci->gsm, ctrl); } +/** + * gsm_modem_update - send modem status line state + * @dlci: channel + * @brk: break signal + */ + +static int gsm_modem_update(struct gsm_dlci *dlci, u8 brk) +{ + if (dlci->adaption == 2) { + /* Send convergence layer type 2 empty data frame. */ + gsm_modem_upd_via_data(dlci, brk); + return 0; + } else if (dlci->gsm->encoding == 0) { + /* Send as MSC control message. */ + return gsm_modem_upd_via_msc(dlci, brk); + } + + /* Modem status lines are not supported. */ + return -EPROTONOSUPPORT; +} + static int gsm_carrier_raised(struct tty_port *port) { struct gsm_dlci *dlci = container_of(port, struct gsm_dlci, port); @@ -3006,7 +3081,7 @@ static void gsm_dtr_rts(struct tty_port *port, int onoff) modem_tx &= ~(TIOCM_DTR | TIOCM_RTS); if (modem_tx != dlci->modem_tx) { dlci->modem_tx = modem_tx; - gsmtty_modem_update(dlci, 0); + gsm_modem_update(dlci, 0); } } @@ -3141,7 +3216,7 @@ static unsigned int gsmtty_write_room(struct tty_struct *tty) struct gsm_dlci *dlci = tty->driver_data; if (dlci->state == DLCI_CLOSED) return 0; - return TX_SIZE - kfifo_len(&dlci->fifo); + return kfifo_avail(&dlci->fifo); } static unsigned int gsmtty_chars_in_buffer(struct tty_struct *tty) @@ -3155,13 +3230,17 @@ static unsigned int gsmtty_chars_in_buffer(struct tty_struct *tty) static void gsmtty_flush_buffer(struct tty_struct *tty) { struct gsm_dlci *dlci = tty->driver_data; + unsigned long flags; + if (dlci->state == DLCI_CLOSED) return; /* Caution needed: If we implement reliable transport classes then the data being transmitted can't simply be junked once it has first hit the stack. Until then we can just blow it away */ + spin_lock_irqsave(&dlci->lock, flags); kfifo_reset(&dlci->fifo); + spin_unlock_irqrestore(&dlci->lock, flags); /* Need to unhook this DLCI from the transmit queue logic */ } @@ -3193,7 +3272,7 @@ static int gsmtty_tiocmset(struct tty_struct *tty, if (modem_tx != dlci->modem_tx) { dlci->modem_tx = modem_tx; - return gsmtty_modem_update(dlci, 0); + return gsm_modem_update(dlci, 0); } return 0; } @@ -3254,7 +3333,7 @@ static void gsmtty_throttle(struct tty_struct *tty) dlci->modem_tx &= ~TIOCM_RTS; dlci->throttled = true; /* Send an MSC with RTS cleared */ - gsmtty_modem_update(dlci, 0); + gsm_modem_update(dlci, 0); } static void gsmtty_unthrottle(struct tty_struct *tty) @@ -3266,7 +3345,7 @@ static void gsmtty_unthrottle(struct tty_struct *tty) dlci->modem_tx |= TIOCM_RTS; dlci->throttled = false; /* Send an MSC with RTS set */ - gsmtty_modem_update(dlci, 0); + gsm_modem_update(dlci, 0); } static int gsmtty_break_ctl(struct tty_struct *tty, int state) @@ -3284,7 +3363,7 @@ static int gsmtty_break_ctl(struct tty_struct *tty, int state) if (encode > 0x0F) encode = 0x0F; /* Best effort */ } - return gsmtty_modem_update(dlci, encode); + return gsm_modem_update(dlci, encode); } static void gsmtty_cleanup(struct tty_struct *tty) diff --git a/drivers/tty/serial/8250/8250_mtk.c b/drivers/tty/serial/8250/8250_mtk.c index f4a0caa56f84..21053db93ff1 100644 --- a/drivers/tty/serial/8250/8250_mtk.c +++ b/drivers/tty/serial/8250/8250_mtk.c @@ -37,6 +37,7 @@ #define MTK_UART_IER_RTSI 0x40 /* Enable RTS Modem status interrupt */ #define MTK_UART_IER_CTSI 0x80 /* Enable CTS Modem status interrupt */ +#define MTK_UART_EFR 38 /* I/O: Extended Features Register */ #define MTK_UART_EFR_EN 0x10 /* Enable enhancement feature */ #define MTK_UART_EFR_RTS 0x40 /* Enable hardware rx flow control */ #define MTK_UART_EFR_CTS 0x80 /* Enable hardware tx flow control */ @@ -53,6 +54,12 @@ #define MTK_UART_TX_TRIGGER 1 #define MTK_UART_RX_TRIGGER MTK_UART_RX_SIZE +#define MTK_UART_FEATURE_SEL 39 /* Feature Selection register */ +#define MTK_UART_FEAT_NEWRMAP BIT(0) /* Use new register map */ + +#define MTK_UART_XON1 40 /* I/O: Xon character 1 */ +#define MTK_UART_XOFF1 42 /* I/O: Xoff character 1 */ + #ifdef CONFIG_SERIAL_8250_DMA enum dma_rx_status { DMA_RX_START = 0, @@ -169,7 +176,7 @@ static void mtk8250_dma_enable(struct uart_8250_port *up) MTK_UART_DMA_EN_RX | MTK_UART_DMA_EN_TX); serial_out(up, UART_LCR, UART_LCR_CONF_MODE_B); - serial_out(up, UART_EFR, UART_EFR_ECB); + serial_out(up, MTK_UART_EFR, UART_EFR_ECB); serial_out(up, UART_LCR, lcr); if (dmaengine_slave_config(dma->rxchan, &dma->rxconf) != 0) @@ -232,7 +239,7 @@ static void mtk8250_set_flow_ctrl(struct uart_8250_port *up, int mode) int lcr = serial_in(up, UART_LCR); serial_out(up, UART_LCR, UART_LCR_CONF_MODE_B); - serial_out(up, UART_EFR, UART_EFR_ECB); + serial_out(up, MTK_UART_EFR, UART_EFR_ECB); serial_out(up, UART_LCR, lcr); lcr = serial_in(up, UART_LCR); @@ -241,7 +248,7 @@ static void mtk8250_set_flow_ctrl(struct uart_8250_port *up, int mode) serial_out(up, MTK_UART_ESCAPE_DAT, MTK_UART_ESCAPE_CHAR); serial_out(up, MTK_UART_ESCAPE_EN, 0x00); serial_out(up, UART_LCR, UART_LCR_CONF_MODE_B); - serial_out(up, UART_EFR, serial_in(up, UART_EFR) & + serial_out(up, MTK_UART_EFR, serial_in(up, MTK_UART_EFR) & (~(MTK_UART_EFR_HW_FC | MTK_UART_EFR_SW_FC_MASK))); serial_out(up, UART_LCR, lcr); mtk8250_disable_intrs(up, MTK_UART_IER_XOFFI | @@ -255,8 +262,8 @@ static void mtk8250_set_flow_ctrl(struct uart_8250_port *up, int mode) serial_out(up, UART_LCR, UART_LCR_CONF_MODE_B); /*enable hw flow control*/ - serial_out(up, UART_EFR, MTK_UART_EFR_HW_FC | - (serial_in(up, UART_EFR) & + serial_out(up, MTK_UART_EFR, MTK_UART_EFR_HW_FC | + (serial_in(up, MTK_UART_EFR) & (~(MTK_UART_EFR_HW_FC | MTK_UART_EFR_SW_FC_MASK)))); serial_out(up, UART_LCR, lcr); @@ -270,12 +277,12 @@ static void mtk8250_set_flow_ctrl(struct uart_8250_port *up, int mode) serial_out(up, UART_LCR, UART_LCR_CONF_MODE_B); /*enable sw flow control */ - serial_out(up, UART_EFR, MTK_UART_EFR_XON1_XOFF1 | - (serial_in(up, UART_EFR) & + serial_out(up, MTK_UART_EFR, MTK_UART_EFR_XON1_XOFF1 | + (serial_in(up, MTK_UART_EFR) & (~(MTK_UART_EFR_HW_FC | MTK_UART_EFR_SW_FC_MASK)))); - serial_out(up, UART_XON1, START_CHAR(port->state->port.tty)); - serial_out(up, UART_XOFF1, STOP_CHAR(port->state->port.tty)); + serial_out(up, MTK_UART_XON1, START_CHAR(port->state->port.tty)); + serial_out(up, MTK_UART_XOFF1, STOP_CHAR(port->state->port.tty)); serial_out(up, UART_LCR, lcr); mtk8250_disable_intrs(up, MTK_UART_IER_CTSI|MTK_UART_IER_RTSI); mtk8250_enable_intrs(up, MTK_UART_IER_XOFFI); @@ -568,6 +575,10 @@ static int mtk8250_probe(struct platform_device *pdev) uart.dma = data->dma; #endif + /* Set AP UART new register map */ + writel(MTK_UART_FEAT_NEWRMAP, uart.port.membase + + (MTK_UART_FEATURE_SEL << uart.port.regshift)); + /* Disable Rate Fix function */ writel(0x0, uart.port.membase + (MTK_UART_RATE_FIX << uart.port.regshift)); diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c index e17e97ea86fa..a293e9f107d0 100644 --- a/drivers/tty/serial/8250/8250_pci.c +++ b/drivers/tty/serial/8250/8250_pci.c @@ -2667,7 +2667,7 @@ enum pci_board_num_t { pbn_panacom2, pbn_panacom4, pbn_plx_romulus, - pbn_endrun_2_4000000, + pbn_endrun_2_3906250, pbn_oxsemi, pbn_oxsemi_1_3906250, pbn_oxsemi_2_3906250, @@ -3195,10 +3195,10 @@ static struct pciserial_board pci_boards[] = { * signal now many ports are available * 2 port 952 Uart support */ - [pbn_endrun_2_4000000] = { + [pbn_endrun_2_3906250] = { .flags = FL_BASE0, .num_ports = 2, - .base_baud = 4000000, + .base_baud = 3906250, .uart_offset = 0x200, .first_offset = 0x1000, }, @@ -4115,7 +4115,7 @@ static const struct pci_device_id serial_pci_tbl[] = { */ { PCI_VENDOR_ID_ENDRUN, PCI_DEVICE_ID_ENDRUN_1588, PCI_ANY_ID, PCI_ANY_ID, 0, 0, - pbn_endrun_2_4000000 }, + pbn_endrun_2_3906250 }, /* * Quatech cards. These actually have configurable clocks but for * now we just use the default. diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index 318af6f13605..1fbd5bf264be 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -1675,11 +1675,11 @@ static void serial8250_start_tx(struct uart_port *port) struct uart_8250_port *up = up_to_u8250p(port); struct uart_8250_em485 *em485 = up->em485; - serial8250_rpm_get_tx(up); - if (!port->x_char && uart_circ_empty(&port->state->xmit)) return; + serial8250_rpm_get_tx(up); + if (em485 && em485->active_timer == &em485->start_tx_timer) return; @@ -3329,7 +3329,7 @@ static void serial8250_console_restore(struct uart_8250_port *up) serial8250_set_divisor(port, baud, quot, frac); serial_port_out(port, UART_LCR, up->lcr); - serial8250_out_MCR(up, UART_MCR_DTR | UART_MCR_RTS); + serial8250_out_MCR(up, up->mcr | UART_MCR_DTR | UART_MCR_RTS); } /* diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c index 51ecb050ae40..4d11a3e547f9 100644 --- a/drivers/tty/serial/amba-pl011.c +++ b/drivers/tty/serial/amba-pl011.c @@ -1255,13 +1255,18 @@ static inline bool pl011_dma_rx_running(struct uart_amba_port *uap) static void pl011_rs485_tx_stop(struct uart_amba_port *uap) { + /* + * To be on the safe side only time out after twice as many iterations + * as fifo size. + */ + const int MAX_TX_DRAIN_ITERS = uap->port.fifosize * 2; struct uart_port *port = &uap->port; int i = 0; u32 cr; /* Wait until hardware tx queue is empty */ while (!pl011_tx_empty(port)) { - if (i == port->fifosize) { + if (i > MAX_TX_DRAIN_ITERS) { dev_warn(port->dev, "timeout while draining hardware tx queue\n"); break; @@ -2052,7 +2057,7 @@ pl011_set_termios(struct uart_port *port, struct ktermios *termios, * with the given baud rate. We use this as the poll interval when we * wait for the tx queue to empty. */ - uap->rs485_tx_drain_interval = (bits * 1000 * 1000) / baud; + uap->rs485_tx_drain_interval = DIV_ROUND_UP(bits * 1000 * 1000, baud); pl011_setup_status_masks(port, termios); diff --git a/drivers/tty/serial/digicolor-usart.c b/drivers/tty/serial/digicolor-usart.c index 6d70fea76bb3..e37a917b9dbb 100644 --- a/drivers/tty/serial/digicolor-usart.c +++ b/drivers/tty/serial/digicolor-usart.c @@ -471,11 +471,10 @@ static int digicolor_uart_probe(struct platform_device *pdev) if (IS_ERR(uart_clk)) return PTR_ERR(uart_clk); - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - dp->port.mapbase = res->start; - dp->port.membase = devm_ioremap_resource(&pdev->dev, res); + dp->port.membase = devm_platform_get_and_ioremap_resource(pdev, 0, &res); if (IS_ERR(dp->port.membase)) return PTR_ERR(dp->port.membase); + dp->port.mapbase = res->start; irq = platform_get_irq(pdev, 0); if (irq < 0) diff --git a/drivers/tty/serial/fsl_lpuart.c b/drivers/tty/serial/fsl_lpuart.c index 87789872f400..be12fee94db5 100644 --- a/drivers/tty/serial/fsl_lpuart.c +++ b/drivers/tty/serial/fsl_lpuart.c @@ -2664,6 +2664,7 @@ static int lpuart_probe(struct platform_device *pdev) struct device_node *np = pdev->dev.of_node; struct lpuart_port *sport; struct resource *res; + irq_handler_t handler; int ret; sport = devm_kzalloc(&pdev->dev, sizeof(*sport), GFP_KERNEL); @@ -2741,17 +2742,11 @@ static int lpuart_probe(struct platform_device *pdev) if (lpuart_is_32(sport)) { lpuart_reg.cons = LPUART32_CONSOLE; - ret = devm_request_irq(&pdev->dev, sport->port.irq, lpuart32_int, 0, - DRIVER_NAME, sport); + handler = lpuart32_int; } else { lpuart_reg.cons = LPUART_CONSOLE; - ret = devm_request_irq(&pdev->dev, sport->port.irq, lpuart_int, 0, - DRIVER_NAME, sport); + handler = lpuart_int; } - - if (ret) - goto failed_irq_request; - ret = uart_add_one_port(&lpuart_reg, &sport->port); if (ret) goto failed_attach_port; @@ -2773,13 +2768,18 @@ static int lpuart_probe(struct platform_device *pdev) sport->port.rs485_config(&sport->port, &sport->port.rs485); + ret = devm_request_irq(&pdev->dev, sport->port.irq, handler, 0, + DRIVER_NAME, sport); + if (ret) + goto failed_irq_request; + return 0; +failed_irq_request: failed_get_rs485: failed_reset: uart_remove_one_port(&lpuart_reg, &sport->port); failed_attach_port: -failed_irq_request: lpuart_disable_clks(sport); failed_clock_enable: failed_out_of_range: diff --git a/drivers/tty/serial/imx.c b/drivers/tty/serial/imx.c index fd38e6ed4fda..a2100be8d554 100644 --- a/drivers/tty/serial/imx.c +++ b/drivers/tty/serial/imx.c @@ -1448,7 +1448,7 @@ static int imx_uart_startup(struct uart_port *port) imx_uart_writel(sport, ucr1, UCR1); ucr4 = imx_uart_readl(sport, UCR4) & ~(UCR4_OREN | UCR4_INVR); - if (!sport->dma_is_enabled) + if (!dma_is_inited) ucr4 |= UCR4_OREN; if (sport->inverted_rx) ucr4 |= UCR4_INVR; diff --git a/drivers/tty/serial/mpc52xx_uart.c b/drivers/tty/serial/mpc52xx_uart.c index 8a6958377764..3acc0f185762 100644 --- a/drivers/tty/serial/mpc52xx_uart.c +++ b/drivers/tty/serial/mpc52xx_uart.c @@ -436,31 +436,31 @@ static void mpc512x_psc_fifo_init(struct uart_port *port) out_be32(&FIFO_512x(port)->rximr, MPC512x_PSC_FIFO_ALARM); } -static int mpc512x_psc_raw_rx_rdy(struct uart_port *port) +static unsigned int mpc512x_psc_raw_rx_rdy(struct uart_port *port) { return !(in_be32(&FIFO_512x(port)->rxsr) & MPC512x_PSC_FIFO_EMPTY); } -static int mpc512x_psc_raw_tx_rdy(struct uart_port *port) +static unsigned int mpc512x_psc_raw_tx_rdy(struct uart_port *port) { return !(in_be32(&FIFO_512x(port)->txsr) & MPC512x_PSC_FIFO_FULL); } -static int mpc512x_psc_rx_rdy(struct uart_port *port) +static unsigned int mpc512x_psc_rx_rdy(struct uart_port *port) { return in_be32(&FIFO_512x(port)->rxsr) & in_be32(&FIFO_512x(port)->rximr) & MPC512x_PSC_FIFO_ALARM; } -static int mpc512x_psc_tx_rdy(struct uart_port *port) +static unsigned int mpc512x_psc_tx_rdy(struct uart_port *port) { return in_be32(&FIFO_512x(port)->txsr) & in_be32(&FIFO_512x(port)->tximr) & MPC512x_PSC_FIFO_ALARM; } -static int mpc512x_psc_tx_empty(struct uart_port *port) +static unsigned int mpc512x_psc_tx_empty(struct uart_port *port) { return in_be32(&FIFO_512x(port)->txsr) & MPC512x_PSC_FIFO_EMPTY; @@ -780,29 +780,29 @@ static void mpc5125_psc_fifo_init(struct uart_port *port) out_be32(&FIFO_5125(port)->rximr, MPC512x_PSC_FIFO_ALARM); } -static int mpc5125_psc_raw_rx_rdy(struct uart_port *port) +static unsigned int mpc5125_psc_raw_rx_rdy(struct uart_port *port) { return !(in_be32(&FIFO_5125(port)->rxsr) & MPC512x_PSC_FIFO_EMPTY); } -static int mpc5125_psc_raw_tx_rdy(struct uart_port *port) +static unsigned int mpc5125_psc_raw_tx_rdy(struct uart_port *port) { return !(in_be32(&FIFO_5125(port)->txsr) & MPC512x_PSC_FIFO_FULL); } -static int mpc5125_psc_rx_rdy(struct uart_port *port) +static unsigned int mpc5125_psc_rx_rdy(struct uart_port *port) { return in_be32(&FIFO_5125(port)->rxsr) & in_be32(&FIFO_5125(port)->rximr) & MPC512x_PSC_FIFO_ALARM; } -static int mpc5125_psc_tx_rdy(struct uart_port *port) +static unsigned int mpc5125_psc_tx_rdy(struct uart_port *port) { return in_be32(&FIFO_5125(port)->txsr) & in_be32(&FIFO_5125(port)->tximr) & MPC512x_PSC_FIFO_ALARM; } -static int mpc5125_psc_tx_empty(struct uart_port *port) +static unsigned int mpc5125_psc_tx_empty(struct uart_port *port) { return in_be32(&FIFO_5125(port)->txsr) & MPC512x_PSC_FIFO_EMPTY; } diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c index e857fb61efbf..5fb201c1b563 100644 --- a/drivers/tty/serial/sc16is7xx.c +++ b/drivers/tty/serial/sc16is7xx.c @@ -1238,12 +1238,10 @@ static void sc16is7xx_shutdown(struct uart_port *port) /* Disable all interrupts */ sc16is7xx_port_write(port, SC16IS7XX_IER_REG, 0); - /* Disable TX/RX, clear auto RS485 and RTS invert */ + /* Disable TX/RX */ sc16is7xx_port_update(port, SC16IS7XX_EFCR_REG, SC16IS7XX_EFCR_RXDISABLE_BIT | - SC16IS7XX_EFCR_TXDISABLE_BIT | - SC16IS7XX_EFCR_AUTO_RS485_BIT | - SC16IS7XX_EFCR_RTS_INVERT_BIT, + SC16IS7XX_EFCR_TXDISABLE_BIT, SC16IS7XX_EFCR_RXDISABLE_BIT | SC16IS7XX_EFCR_TXDISABLE_BIT); diff --git a/drivers/tty/sysrq.c b/drivers/tty/sysrq.c index bbfd004449b5..2884cd638d64 100644 --- a/drivers/tty/sysrq.c +++ b/drivers/tty/sysrq.c @@ -578,6 +578,7 @@ void __handle_sysrq(int key, bool check_mask) rcu_sysrq_start(); rcu_read_lock(); + printk_prefer_direct_enter(); /* * Raise the apparent loglevel to maximum so that the sysrq header * is shown to provide the user with positive feedback. We do not @@ -619,6 +620,7 @@ void __handle_sysrq(int key, bool check_mask) pr_cont("\n"); console_loglevel = orig_log_level; } + printk_prefer_direct_exit(); rcu_read_unlock(); rcu_sysrq_end(); diff --git a/drivers/usb/cdns3/cdns3-gadget.c b/drivers/usb/cdns3/cdns3-gadget.c index f9af7ebe003d..d6d515d598dc 100644 --- a/drivers/usb/cdns3/cdns3-gadget.c +++ b/drivers/usb/cdns3/cdns3-gadget.c @@ -2684,6 +2684,7 @@ int __cdns3_gadget_ep_clear_halt(struct cdns3_endpoint *priv_ep) struct usb_request *request; struct cdns3_request *priv_req; struct cdns3_trb *trb = NULL; + struct cdns3_trb trb_tmp; int ret; int val; @@ -2693,8 +2694,10 @@ int __cdns3_gadget_ep_clear_halt(struct cdns3_endpoint *priv_ep) if (request) { priv_req = to_cdns3_request(request); trb = priv_req->trb; - if (trb) + if (trb) { + trb_tmp = *trb; trb->control = trb->control ^ cpu_to_le32(TRB_CYCLE); + } } writel(EP_CMD_CSTALL | EP_CMD_EPRST, &priv_dev->regs->ep_cmd); @@ -2709,7 +2712,7 @@ int __cdns3_gadget_ep_clear_halt(struct cdns3_endpoint *priv_ep) if (request) { if (trb) - trb->control = trb->control ^ cpu_to_le32(TRB_CYCLE); + *trb = trb_tmp; cdns3_rearm_transfer(priv_ep, 1); } diff --git a/drivers/usb/class/cdc-wdm.c b/drivers/usb/class/cdc-wdm.c index 7f2c83f299d3..eebe782380fb 100644 --- a/drivers/usb/class/cdc-wdm.c +++ b/drivers/usb/class/cdc-wdm.c @@ -774,6 +774,7 @@ static int wdm_release(struct inode *inode, struct file *file) poison_urbs(desc); spin_lock_irq(&desc->iuspin); desc->resp_count = 0; + clear_bit(WDM_RESPONDING, &desc->flags); spin_unlock_irq(&desc->iuspin); desc->manage_power(desc->intf, 0); unpoison_urbs(desc); diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c index 6abb7294e919..b5b85bf80329 100644 --- a/drivers/usb/core/devio.c +++ b/drivers/usb/core/devio.c @@ -1209,12 +1209,16 @@ static int do_proc_control(struct usb_dev_state *ps, usb_unlock_device(dev); i = usbfs_start_wait_urb(urb, tmo, &actlen); + + /* Linger a bit, prior to the next control message. */ + if (dev->quirks & USB_QUIRK_DELAY_CTRL_MSG) + msleep(200); usb_lock_device(dev); snoop_urb(dev, NULL, pipe, actlen, i, COMPLETE, tbuf, actlen); if (!i && actlen) { if (copy_to_user(ctrl->data, tbuf, actlen)) { ret = -EFAULT; - goto recv_fault; + goto done; } } } else { @@ -1231,6 +1235,10 @@ static int do_proc_control(struct usb_dev_state *ps, usb_unlock_device(dev); i = usbfs_start_wait_urb(urb, tmo, &actlen); + + /* Linger a bit, prior to the next control message. */ + if (dev->quirks & USB_QUIRK_DELAY_CTRL_MSG) + msleep(200); usb_lock_device(dev); snoop_urb(dev, NULL, pipe, actlen, i, COMPLETE, NULL, 0); } @@ -1242,10 +1250,6 @@ static int do_proc_control(struct usb_dev_state *ps, } ret = (i < 0 ? i : actlen); - recv_fault: - /* Linger a bit, prior to the next control message. */ - if (dev->quirks & USB_QUIRK_DELAY_CTRL_MSG) - msleep(200); done: kfree(dr); usb_free_urb(urb); diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index d3c14b5ed4a1..97b44a68668a 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -404,6 +404,9 @@ static const struct usb_device_id usb_quirk_list[] = { { USB_DEVICE(0x0b05, 0x17e0), .driver_info = USB_QUIRK_IGNORE_REMOTE_WAKEUP }, + /* Realtek Semiconductor Corp. Mass Storage Device (Multicard Reader)*/ + { USB_DEVICE(0x0bda, 0x0151), .driver_info = USB_QUIRK_CONFIG_INTF_STRINGS }, + /* Realtek hub in Dell WD19 (Type-C) */ { USB_DEVICE(0x0bda, 0x0487), .driver_info = USB_QUIRK_NO_LPM }, @@ -507,6 +510,9 @@ static const struct usb_device_id usb_quirk_list[] = { /* DJI CineSSD */ { USB_DEVICE(0x2ca3, 0x0031), .driver_info = USB_QUIRK_NO_LPM }, + /* VCOM device */ + { USB_DEVICE(0x4296, 0x7570), .driver_info = USB_QUIRK_CONFIG_INTF_STRINGS }, + /* INTEL VALUE SSD */ { USB_DEVICE(0x8086, 0xf1a5), .driver_info = USB_QUIRK_RESET_RESUME }, diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index 1170b800acdc..d28cd1a6709b 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -274,7 +274,8 @@ int dwc3_core_soft_reset(struct dwc3 *dwc) reg = dwc3_readl(dwc->regs, DWC3_DCTL); reg |= DWC3_DCTL_CSFTRST; - dwc3_writel(dwc->regs, DWC3_DCTL, reg); + reg &= ~DWC3_DCTL_RUN_STOP; + dwc3_gadget_dctl_write_safe(dwc, reg); /* * For DWC_usb31 controller 1.90a and later, the DCTL.CSFRST bit @@ -1377,10 +1378,10 @@ static void dwc3_get_properties(struct dwc3 *dwc) u8 lpm_nyet_threshold; u8 tx_de_emphasis; u8 hird_threshold; - u8 rx_thr_num_pkt_prd; - u8 rx_max_burst_prd; - u8 tx_thr_num_pkt_prd; - u8 tx_max_burst_prd; + u8 rx_thr_num_pkt_prd = 0; + u8 rx_max_burst_prd = 0; + u8 tx_thr_num_pkt_prd = 0; + u8 tx_max_burst_prd = 0; u8 tx_fifo_resize_max_num; const char *usb_psy_name; int ret; @@ -1690,21 +1691,44 @@ static int dwc3_probe(struct platform_device *pdev) /* * Clocks are optional, but new DT platforms should support all * clocks as required by the DT-binding. + * Some devices have different clock names in legacy device trees, + * check for them to retain backwards compatibility. */ dwc->bus_clk = devm_clk_get_optional(dev, "bus_early"); if (IS_ERR(dwc->bus_clk)) return dev_err_probe(dev, PTR_ERR(dwc->bus_clk), "could not get bus clock\n"); + if (dwc->bus_clk == NULL) { + dwc->bus_clk = devm_clk_get_optional(dev, "bus_clk"); + if (IS_ERR(dwc->bus_clk)) + return dev_err_probe(dev, PTR_ERR(dwc->bus_clk), + "could not get bus clock\n"); + } + dwc->ref_clk = devm_clk_get_optional(dev, "ref"); if (IS_ERR(dwc->ref_clk)) return dev_err_probe(dev, PTR_ERR(dwc->ref_clk), "could not get ref clock\n"); + if (dwc->ref_clk == NULL) { + dwc->ref_clk = devm_clk_get_optional(dev, "ref_clk"); + if (IS_ERR(dwc->ref_clk)) + return dev_err_probe(dev, PTR_ERR(dwc->ref_clk), + "could not get ref clock\n"); + } + dwc->susp_clk = devm_clk_get_optional(dev, "suspend"); if (IS_ERR(dwc->susp_clk)) return dev_err_probe(dev, PTR_ERR(dwc->susp_clk), "could not get suspend clock\n"); + + if (dwc->susp_clk == NULL) { + dwc->susp_clk = devm_clk_get_optional(dev, "suspend_clk"); + if (IS_ERR(dwc->susp_clk)) + return dev_err_probe(dev, PTR_ERR(dwc->susp_clk), + "could not get suspend clock\n"); + } } ret = reset_control_deassert(dwc->reset); diff --git a/drivers/usb/dwc3/drd.c b/drivers/usb/dwc3/drd.c index b60b5f7b6dff..8cad9e7d3368 100644 --- a/drivers/usb/dwc3/drd.c +++ b/drivers/usb/dwc3/drd.c @@ -584,16 +584,15 @@ int dwc3_drd_init(struct dwc3 *dwc) { int ret, irq; + if (ROLE_SWITCH && + device_property_read_bool(dwc->dev, "usb-role-switch")) + return dwc3_setup_role_switch(dwc); + dwc->edev = dwc3_get_extcon(dwc); if (IS_ERR(dwc->edev)) return PTR_ERR(dwc->edev); - if (ROLE_SWITCH && - device_property_read_bool(dwc->dev, "usb-role-switch")) { - ret = dwc3_setup_role_switch(dwc); - if (ret < 0) - return ret; - } else if (dwc->edev) { + if (dwc->edev) { dwc->edev_nb.notifier_call = dwc3_drd_notifier; ret = extcon_register_notifier(dwc->edev, EXTCON_USB_HOST, &dwc->edev_nb); diff --git a/drivers/usb/dwc3/dwc3-pci.c b/drivers/usb/dwc3/dwc3-pci.c index 33f657d83246..2e19e0e4ea53 100644 --- a/drivers/usb/dwc3/dwc3-pci.c +++ b/drivers/usb/dwc3/dwc3-pci.c @@ -45,6 +45,8 @@ #define PCI_DEVICE_ID_INTEL_ADLM 0x54ee #define PCI_DEVICE_ID_INTEL_ADLS 0x7ae1 #define PCI_DEVICE_ID_INTEL_RPLS 0x7a61 +#define PCI_DEVICE_ID_INTEL_MTLP 0x7ec1 +#define PCI_DEVICE_ID_INTEL_MTL 0x7e7e #define PCI_DEVICE_ID_INTEL_TGL 0x9a15 #define PCI_DEVICE_ID_AMD_MR 0x163a @@ -456,6 +458,12 @@ static const struct pci_device_id dwc3_pci_id_table[] = { { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_RPLS), (kernel_ulong_t) &dwc3_pci_intel_swnode, }, + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_MTLP), + (kernel_ulong_t) &dwc3_pci_intel_swnode, }, + + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_MTL), + (kernel_ulong_t) &dwc3_pci_intel_swnode, }, + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_TGL), (kernel_ulong_t) &dwc3_pci_intel_swnode, }, diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index ab725d2262d6..0b9c2493844a 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -3274,6 +3274,7 @@ static int dwc3_gadget_ep_cleanup_completed_request(struct dwc3_ep *dep, const struct dwc3_event_depevt *event, struct dwc3_request *req, int status) { + int request_status; int ret; if (req->request.num_mapped_sgs) @@ -3294,7 +3295,35 @@ static int dwc3_gadget_ep_cleanup_completed_request(struct dwc3_ep *dep, req->needs_extra_trb = false; } - dwc3_gadget_giveback(dep, req, status); + /* + * The event status only reflects the status of the TRB with IOC set. + * For the requests that don't set interrupt on completion, the driver + * needs to check and return the status of the completed TRBs associated + * with the request. Use the status of the last TRB of the request. + */ + if (req->request.no_interrupt) { + struct dwc3_trb *trb; + + trb = dwc3_ep_prev_trb(dep, dep->trb_dequeue); + switch (DWC3_TRB_SIZE_TRBSTS(trb->size)) { + case DWC3_TRBSTS_MISSED_ISOC: + /* Isoc endpoint only */ + request_status = -EXDEV; + break; + case DWC3_TRB_STS_XFER_IN_PROG: + /* Applicable when End Transfer with ForceRM=0 */ + case DWC3_TRBSTS_SETUP_PENDING: + /* Control endpoint only */ + case DWC3_TRBSTS_OK: + default: + request_status = 0; + break; + } + } else { + request_status = status; + } + + dwc3_gadget_giveback(dep, req, request_status); out: return ret; diff --git a/drivers/usb/gadget/configfs.c b/drivers/usb/gadget/configfs.c index 1fb837d9271e..84b73cb03f87 100644 --- a/drivers/usb/gadget/configfs.c +++ b/drivers/usb/gadget/configfs.c @@ -1438,6 +1438,8 @@ static void configfs_composite_unbind(struct usb_gadget *gadget) usb_ep_autoconfig_reset(cdev->gadget); spin_lock_irqsave(&gi->spinlock, flags); cdev->gadget = NULL; + cdev->deactivations = 0; + gadget->deactivated = false; set_gadget_data(gadget, NULL); spin_unlock_irqrestore(&gi->spinlock, flags); } diff --git a/drivers/usb/gadget/function/f_uvc.c b/drivers/usb/gadget/function/f_uvc.c index 71bb5e477dba..d37965867b23 100644 --- a/drivers/usb/gadget/function/f_uvc.c +++ b/drivers/usb/gadget/function/f_uvc.c @@ -890,13 +890,37 @@ static void uvc_function_unbind(struct usb_configuration *c, { struct usb_composite_dev *cdev = c->cdev; struct uvc_device *uvc = to_uvc(f); + long wait_ret = 1; uvcg_info(f, "%s()\n", __func__); + /* If we know we're connected via v4l2, then there should be a cleanup + * of the device from userspace either via UVC_EVENT_DISCONNECT or + * though the video device removal uevent. Allow some time for the + * application to close out before things get deleted. + */ + if (uvc->func_connected) { + uvcg_dbg(f, "waiting for clean disconnect\n"); + wait_ret = wait_event_interruptible_timeout(uvc->func_connected_queue, + uvc->func_connected == false, msecs_to_jiffies(500)); + uvcg_dbg(f, "done waiting with ret: %ld\n", wait_ret); + } + device_remove_file(&uvc->vdev.dev, &dev_attr_function_name); video_unregister_device(&uvc->vdev); v4l2_device_unregister(&uvc->v4l2_dev); + if (uvc->func_connected) { + /* Wait for the release to occur to ensure there are no longer any + * pending operations that may cause panics when resources are cleaned + * up. + */ + uvcg_warn(f, "%s no clean disconnect, wait for release\n", __func__); + wait_ret = wait_event_interruptible_timeout(uvc->func_connected_queue, + uvc->func_connected == false, msecs_to_jiffies(1000)); + uvcg_dbg(f, "done waiting for release with ret: %ld\n", wait_ret); + } + usb_ep_free_request(cdev->gadget->ep0, uvc->control_req); kfree(uvc->control_buf); @@ -915,6 +939,7 @@ static struct usb_function *uvc_alloc(struct usb_function_instance *fi) mutex_init(&uvc->video.mutex); uvc->state = UVC_STATE_DISCONNECTED; + init_waitqueue_head(&uvc->func_connected_queue); opts = fi_to_f_uvc_opts(fi); mutex_lock(&opts->lock); diff --git a/drivers/usb/gadget/function/uvc.h b/drivers/usb/gadget/function/uvc.h index c3607a32b986..886103a1fe9b 100644 --- a/drivers/usb/gadget/function/uvc.h +++ b/drivers/usb/gadget/function/uvc.h @@ -14,6 +14,7 @@ #include <linux/spinlock.h> #include <linux/usb/composite.h> #include <linux/videodev2.h> +#include <linux/wait.h> #include <media/v4l2-device.h> #include <media/v4l2-dev.h> @@ -129,6 +130,7 @@ struct uvc_device { struct usb_function func; struct uvc_video video; bool func_connected; + wait_queue_head_t func_connected_queue; /* Descriptors */ struct { diff --git a/drivers/usb/gadget/function/uvc_queue.c b/drivers/usb/gadget/function/uvc_queue.c index d852ac9e47e7..2cda982f3765 100644 --- a/drivers/usb/gadget/function/uvc_queue.c +++ b/drivers/usb/gadget/function/uvc_queue.c @@ -264,6 +264,8 @@ void uvcg_queue_cancel(struct uvc_video_queue *queue, int disconnect) buf->state = UVC_BUF_STATE_ERROR; vb2_buffer_done(&buf->buf.vb2_buf, VB2_BUF_STATE_ERROR); } + queue->buf_used = 0; + /* This must be protected by the irqlock spinlock to avoid race * conditions between uvc_queue_buffer and the disconnection event that * could result in an interruptible wait in uvc_dequeue_buffer. Do not diff --git a/drivers/usb/gadget/function/uvc_v4l2.c b/drivers/usb/gadget/function/uvc_v4l2.c index a2c78690c5c2..fd8f73bb726d 100644 --- a/drivers/usb/gadget/function/uvc_v4l2.c +++ b/drivers/usb/gadget/function/uvc_v4l2.c @@ -253,10 +253,11 @@ uvc_v4l2_subscribe_event(struct v4l2_fh *fh, static void uvc_v4l2_disable(struct uvc_device *uvc) { - uvc->func_connected = false; uvc_function_disconnect(uvc); uvcg_video_enable(&uvc->video, 0); uvcg_free_buffers(&uvc->video.queue); + uvc->func_connected = false; + wake_up_interruptible(&uvc->func_connected_queue); } static int diff --git a/drivers/usb/gadget/legacy/raw_gadget.c b/drivers/usb/gadget/legacy/raw_gadget.c index 8d40a1f2ec57..e9440f7bf019 100644 --- a/drivers/usb/gadget/legacy/raw_gadget.c +++ b/drivers/usb/gadget/legacy/raw_gadget.c @@ -145,6 +145,7 @@ enum dev_state { STATE_DEV_INVALID = 0, STATE_DEV_OPENED, STATE_DEV_INITIALIZED, + STATE_DEV_REGISTERING, STATE_DEV_RUNNING, STATE_DEV_CLOSED, STATE_DEV_FAILED @@ -508,6 +509,7 @@ static int raw_ioctl_run(struct raw_dev *dev, unsigned long value) ret = -EINVAL; goto out_unlock; } + dev->state = STATE_DEV_REGISTERING; spin_unlock_irqrestore(&dev->lock, flags); ret = usb_gadget_probe_driver(&dev->driver); diff --git a/drivers/usb/host/ehci-hcd.c b/drivers/usb/host/ehci-hcd.c index 3d82e0b853be..684164fa9716 100644 --- a/drivers/usb/host/ehci-hcd.c +++ b/drivers/usb/host/ehci-hcd.c @@ -1103,6 +1103,26 @@ static void ehci_remove_device(struct usb_hcd *hcd, struct usb_device *udev) #ifdef CONFIG_PM +/* Clear wakeup signal locked in zhaoxin platform when device plug in. */ +static void ehci_zx_wakeup_clear(struct ehci_hcd *ehci) +{ + u32 __iomem *reg = &ehci->regs->port_status[4]; + u32 t1 = ehci_readl(ehci, reg); + + t1 &= (u32)~0xf0000; + t1 |= PORT_TEST_FORCE; + ehci_writel(ehci, t1, reg); + t1 = ehci_readl(ehci, reg); + msleep(1); + t1 &= (u32)~0xf0000; + ehci_writel(ehci, t1, reg); + ehci_readl(ehci, reg); + msleep(1); + t1 = ehci_readl(ehci, reg); + ehci_writel(ehci, t1 | PORT_CSC, reg); + ehci_readl(ehci, reg); +} + /* suspend/resume, section 4.3 */ /* These routines handle the generic parts of controller suspend/resume */ @@ -1154,6 +1174,9 @@ int ehci_resume(struct usb_hcd *hcd, bool force_reset) if (ehci->shutdown) return 0; /* Controller is dead */ + if (ehci->zx_wakeup_clear_needed) + ehci_zx_wakeup_clear(ehci); + /* * If CF is still set and reset isn't forced * then we maintained suspend power. diff --git a/drivers/usb/host/ehci-pci.c b/drivers/usb/host/ehci-pci.c index 638f03b89739..9937c5a7efc2 100644 --- a/drivers/usb/host/ehci-pci.c +++ b/drivers/usb/host/ehci-pci.c @@ -231,6 +231,10 @@ static int ehci_pci_setup(struct usb_hcd *hcd) ehci->is_aspeed = 1; } break; + case PCI_VENDOR_ID_ZHAOXIN: + if (pdev->device == 0x3104 && (pdev->revision & 0xf0) == 0x90) + ehci->zx_wakeup_clear_needed = 1; + break; } /* optional debug port, normally in the first BAR */ diff --git a/drivers/usb/host/ehci.h b/drivers/usb/host/ehci.h index fdd073cc053b..ad3f13a3eaf1 100644 --- a/drivers/usb/host/ehci.h +++ b/drivers/usb/host/ehci.h @@ -220,6 +220,7 @@ struct ehci_hcd { /* one per controller */ unsigned imx28_write_fix:1; /* For Freescale i.MX28 */ unsigned spurious_oc:1; unsigned is_aspeed:1; + unsigned zx_wakeup_clear_needed:1; /* required for usb32 quirk */ #define OHCI_CTRL_HCFS (3 << 6) diff --git a/drivers/usb/host/xen-hcd.c b/drivers/usb/host/xen-hcd.c index 3e487baf8422..de1b09158318 100644 --- a/drivers/usb/host/xen-hcd.c +++ b/drivers/usb/host/xen-hcd.c @@ -87,8 +87,6 @@ struct xenhcd_info { bool error; }; -#define GRANT_INVALID_REF 0 - #define XENHCD_RING_JIFFIES (HZ/200) #define XENHCD_SCAN_JIFFIES 1 @@ -1100,19 +1098,10 @@ static void xenhcd_destroy_rings(struct xenhcd_info *info) unbind_from_irqhandler(info->irq, info); info->irq = 0; - if (info->urb_ring_ref != GRANT_INVALID_REF) { - gnttab_end_foreign_access(info->urb_ring_ref, - (unsigned long)info->urb_ring.sring); - info->urb_ring_ref = GRANT_INVALID_REF; - } - info->urb_ring.sring = NULL; - - if (info->conn_ring_ref != GRANT_INVALID_REF) { - gnttab_end_foreign_access(info->conn_ring_ref, - (unsigned long)info->conn_ring.sring); - info->conn_ring_ref = GRANT_INVALID_REF; - } - info->conn_ring.sring = NULL; + xenbus_teardown_ring((void **)&info->urb_ring.sring, 1, + &info->urb_ring_ref); + xenbus_teardown_ring((void **)&info->conn_ring.sring, 1, + &info->conn_ring_ref); } static int xenhcd_setup_rings(struct xenbus_device *dev, @@ -1120,46 +1109,24 @@ static int xenhcd_setup_rings(struct xenbus_device *dev, { struct xenusb_urb_sring *urb_sring; struct xenusb_conn_sring *conn_sring; - grant_ref_t gref; int err; - info->urb_ring_ref = GRANT_INVALID_REF; - info->conn_ring_ref = GRANT_INVALID_REF; - - urb_sring = (struct xenusb_urb_sring *)get_zeroed_page( - GFP_NOIO | __GFP_HIGH); - if (!urb_sring) { - xenbus_dev_fatal(dev, -ENOMEM, "allocating urb ring"); - return -ENOMEM; - } - SHARED_RING_INIT(urb_sring); - FRONT_RING_INIT(&info->urb_ring, urb_sring, PAGE_SIZE); - - err = xenbus_grant_ring(dev, urb_sring, 1, &gref); - if (err < 0) { - free_page((unsigned long)urb_sring); - info->urb_ring.sring = NULL; - goto fail; - } - info->urb_ring_ref = gref; - - conn_sring = (struct xenusb_conn_sring *)get_zeroed_page( - GFP_NOIO | __GFP_HIGH); - if (!conn_sring) { - xenbus_dev_fatal(dev, -ENOMEM, "allocating conn ring"); - err = -ENOMEM; - goto fail; + info->conn_ring_ref = INVALID_GRANT_REF; + err = xenbus_setup_ring(dev, GFP_NOIO | __GFP_HIGH, + (void **)&urb_sring, 1, &info->urb_ring_ref); + if (err) { + xenbus_dev_fatal(dev, err, "allocating urb ring"); + return err; } - SHARED_RING_INIT(conn_sring); - FRONT_RING_INIT(&info->conn_ring, conn_sring, PAGE_SIZE); + XEN_FRONT_RING_INIT(&info->urb_ring, urb_sring, PAGE_SIZE); - err = xenbus_grant_ring(dev, conn_sring, 1, &gref); - if (err < 0) { - free_page((unsigned long)conn_sring); - info->conn_ring.sring = NULL; + err = xenbus_setup_ring(dev, GFP_NOIO | __GFP_HIGH, + (void **)&conn_sring, 1, &info->conn_ring_ref); + if (err) { + xenbus_dev_fatal(dev, err, "allocating conn ring"); goto fail; } - info->conn_ring_ref = gref; + XEN_FRONT_RING_INIT(&info->conn_ring, conn_sring, PAGE_SIZE); err = xenbus_alloc_evtchn(dev, &info->evtchn); if (err) { diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c index 1e7dc130c39a..f65f1ba2b592 100644 --- a/drivers/usb/host/xhci-hub.c +++ b/drivers/usb/host/xhci-hub.c @@ -1434,7 +1434,7 @@ int xhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue, } spin_unlock_irqrestore(&xhci->lock, flags); if (!wait_for_completion_timeout(&bus_state->u3exit_done[wIndex], - msecs_to_jiffies(100))) + msecs_to_jiffies(500))) xhci_dbg(xhci, "missing U0 port change event for port %d-%d\n", hcd->self.busnum, wIndex + 1); spin_lock_irqsave(&xhci->lock, flags); diff --git a/drivers/usb/host/xhci-mtk-sch.c b/drivers/usb/host/xhci-mtk-sch.c index f3139ce7b0a9..06a6b19acaae 100644 --- a/drivers/usb/host/xhci-mtk-sch.c +++ b/drivers/usb/host/xhci-mtk-sch.c @@ -19,11 +19,6 @@ #define HS_BW_BOUNDARY 6144 /* usb2 spec section11.18.1: at most 188 FS bytes per microframe */ #define FS_PAYLOAD_MAX 188 -/* - * max number of microframes for split transfer, - * for fs isoc in : 1 ss + 1 idle + 7 cs - */ -#define TT_MICROFRAMES_MAX 9 #define DBG_BUF_EN 64 @@ -242,28 +237,17 @@ static void drop_tt(struct usb_device *udev) static struct mu3h_sch_ep_info * create_sch_ep(struct xhci_hcd_mtk *mtk, struct usb_device *udev, - struct usb_host_endpoint *ep, struct xhci_ep_ctx *ep_ctx) + struct usb_host_endpoint *ep) { struct mu3h_sch_ep_info *sch_ep; struct mu3h_sch_bw_info *bw_info; struct mu3h_sch_tt *tt = NULL; - u32 len_bw_budget_table; bw_info = get_bw_info(mtk, udev, ep); if (!bw_info) return ERR_PTR(-ENODEV); - if (is_fs_or_ls(udev->speed)) - len_bw_budget_table = TT_MICROFRAMES_MAX; - else if ((udev->speed >= USB_SPEED_SUPER) - && usb_endpoint_xfer_isoc(&ep->desc)) - len_bw_budget_table = get_esit(ep_ctx); - else - len_bw_budget_table = 1; - - sch_ep = kzalloc(struct_size(sch_ep, bw_budget_table, - len_bw_budget_table), - GFP_KERNEL); + sch_ep = kzalloc(sizeof(*sch_ep), GFP_KERNEL); if (!sch_ep) return ERR_PTR(-ENOMEM); @@ -295,8 +279,6 @@ static void setup_sch_info(struct xhci_ep_ctx *ep_ctx, u32 mult; u32 esit_pkts; u32 max_esit_payload; - u32 *bwb_table = sch_ep->bw_budget_table; - int i; ep_type = CTX_TO_EP_TYPE(le32_to_cpu(ep_ctx->ep_info2)); maxpkt = MAX_PACKET_DECODED(le32_to_cpu(ep_ctx->ep_info2)); @@ -332,7 +314,6 @@ static void setup_sch_info(struct xhci_ep_ctx *ep_ctx, */ sch_ep->pkts = max_burst + 1; sch_ep->bw_cost_per_microframe = maxpkt * sch_ep->pkts; - bwb_table[0] = sch_ep->bw_cost_per_microframe; } else if (sch_ep->speed >= USB_SPEED_SUPER) { /* usb3_r1 spec section4.4.7 & 4.4.8 */ sch_ep->cs_count = 0; @@ -349,7 +330,6 @@ static void setup_sch_info(struct xhci_ep_ctx *ep_ctx, if (ep_type == INT_IN_EP || ep_type == INT_OUT_EP) { sch_ep->pkts = esit_pkts; sch_ep->num_budget_microframes = 1; - bwb_table[0] = maxpkt * sch_ep->pkts; } if (ep_type == ISOC_IN_EP || ep_type == ISOC_OUT_EP) { @@ -366,15 +346,8 @@ static void setup_sch_info(struct xhci_ep_ctx *ep_ctx, DIV_ROUND_UP(esit_pkts, sch_ep->pkts); sch_ep->repeat = !!(sch_ep->num_budget_microframes > 1); - sch_ep->bw_cost_per_microframe = maxpkt * sch_ep->pkts; - - for (i = 0; i < sch_ep->num_budget_microframes - 1; i++) - bwb_table[i] = sch_ep->bw_cost_per_microframe; - - /* last one <= bw_cost_per_microframe */ - bwb_table[i] = maxpkt * esit_pkts - - i * sch_ep->bw_cost_per_microframe; } + sch_ep->bw_cost_per_microframe = maxpkt * sch_ep->pkts; } else if (is_fs_or_ls(sch_ep->speed)) { sch_ep->pkts = 1; /* at most one packet for each microframe */ @@ -384,28 +357,7 @@ static void setup_sch_info(struct xhci_ep_ctx *ep_ctx, */ sch_ep->cs_count = DIV_ROUND_UP(maxpkt, FS_PAYLOAD_MAX); sch_ep->num_budget_microframes = sch_ep->cs_count; - sch_ep->bw_cost_per_microframe = - (maxpkt < FS_PAYLOAD_MAX) ? maxpkt : FS_PAYLOAD_MAX; - - /* init budget table */ - if (ep_type == ISOC_OUT_EP) { - for (i = 0; i < sch_ep->num_budget_microframes; i++) - bwb_table[i] = sch_ep->bw_cost_per_microframe; - } else if (ep_type == INT_OUT_EP) { - /* only first one consumes bandwidth, others as zero */ - bwb_table[0] = sch_ep->bw_cost_per_microframe; - } else { /* INT_IN_EP or ISOC_IN_EP */ - bwb_table[0] = 0; /* start split */ - bwb_table[1] = 0; /* idle */ - /* - * due to cs_count will be updated according to cs - * position, assign all remainder budget array - * elements as @bw_cost_per_microframe, but only first - * @num_budget_microframes elements will be used later - */ - for (i = 2; i < TT_MICROFRAMES_MAX; i++) - bwb_table[i] = sch_ep->bw_cost_per_microframe; - } + sch_ep->bw_cost_per_microframe = min_t(u32, maxpkt, FS_PAYLOAD_MAX); } } @@ -422,7 +374,7 @@ static u32 get_max_bw(struct mu3h_sch_bw_info *sch_bw, for (j = 0; j < sch_ep->num_budget_microframes; j++) { k = XHCI_MTK_BW_INDEX(base + j); - bw = sch_bw->bus_bw[k] + sch_ep->bw_budget_table[j]; + bw = sch_bw->bus_bw[k] + sch_ep->bw_cost_per_microframe; if (bw > max_bw) max_bw = bw; } @@ -433,18 +385,16 @@ static u32 get_max_bw(struct mu3h_sch_bw_info *sch_bw, static void update_bus_bw(struct mu3h_sch_bw_info *sch_bw, struct mu3h_sch_ep_info *sch_ep, bool used) { + int bw_updated; u32 base; - int i, j, k; + int i, j; + + bw_updated = sch_ep->bw_cost_per_microframe * (used ? 1 : -1); for (i = 0; i < sch_ep->num_esit; i++) { base = sch_ep->offset + i * sch_ep->esit; - for (j = 0; j < sch_ep->num_budget_microframes; j++) { - k = XHCI_MTK_BW_INDEX(base + j); - if (used) - sch_bw->bus_bw[k] += sch_ep->bw_budget_table[j]; - else - sch_bw->bus_bw[k] -= sch_ep->bw_budget_table[j]; - } + for (j = 0; j < sch_ep->num_budget_microframes; j++) + sch_bw->bus_bw[XHCI_MTK_BW_INDEX(base + j)] += bw_updated; } } @@ -464,7 +414,7 @@ static int check_fs_bus_bw(struct mu3h_sch_ep_info *sch_ep, int offset) */ for (j = 0; j < sch_ep->num_budget_microframes; j++) { k = XHCI_MTK_BW_INDEX(base + j); - tmp = tt->fs_bus_bw[k] + sch_ep->bw_budget_table[j]; + tmp = tt->fs_bus_bw[k] + sch_ep->bw_cost_per_microframe; if (tmp > FS_PAYLOAD_MAX) return -ESCH_BW_OVERFLOW; } @@ -538,19 +488,17 @@ static int check_sch_tt(struct mu3h_sch_ep_info *sch_ep, u32 offset) static void update_sch_tt(struct mu3h_sch_ep_info *sch_ep, bool used) { struct mu3h_sch_tt *tt = sch_ep->sch_tt; + int bw_updated; u32 base; - int i, j, k; + int i, j; + + bw_updated = sch_ep->bw_cost_per_microframe * (used ? 1 : -1); for (i = 0; i < sch_ep->num_esit; i++) { base = sch_ep->offset + i * sch_ep->esit; - for (j = 0; j < sch_ep->num_budget_microframes; j++) { - k = XHCI_MTK_BW_INDEX(base + j); - if (used) - tt->fs_bus_bw[k] += sch_ep->bw_budget_table[j]; - else - tt->fs_bus_bw[k] -= sch_ep->bw_budget_table[j]; - } + for (j = 0; j < sch_ep->num_budget_microframes; j++) + tt->fs_bus_bw[XHCI_MTK_BW_INDEX(base + j)] += bw_updated; } if (used) @@ -710,7 +658,7 @@ static int add_ep_quirk(struct usb_hcd *hcd, struct usb_device *udev, xhci_dbg(xhci, "%s %s\n", __func__, decode_ep(ep, udev->speed)); - sch_ep = create_sch_ep(mtk, udev, ep, ep_ctx); + sch_ep = create_sch_ep(mtk, udev, ep); if (IS_ERR_OR_NULL(sch_ep)) return -ENOMEM; diff --git a/drivers/usb/host/xhci-mtk.h b/drivers/usb/host/xhci-mtk.h index ffd4b493b4ba..1174a510dd38 100644 --- a/drivers/usb/host/xhci-mtk.h +++ b/drivers/usb/host/xhci-mtk.h @@ -83,7 +83,6 @@ struct mu3h_sch_bw_info { * times; 1: distribute the (bMaxBurst+1)*(Mult+1) packets * according to @pkts and @repeat. normal mode is used by * default - * @bw_budget_table: table to record bandwidth budget per microframe */ struct mu3h_sch_ep_info { u32 esit; @@ -109,7 +108,6 @@ struct mu3h_sch_ep_info { u32 pkts; u32 cs_count; u32 burst_mode; - u32 bw_budget_table[]; }; #define MU3C_U3_PORT_MAX 4 diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index 5c351970cdf1..d7e0e6ebf080 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -59,6 +59,7 @@ #define PCI_DEVICE_ID_INTEL_TIGER_LAKE_XHCI 0x9a13 #define PCI_DEVICE_ID_INTEL_MAPLE_RIDGE_XHCI 0x1138 #define PCI_DEVICE_ID_INTEL_ALDER_LAKE_XHCI 0x461e +#define PCI_DEVICE_ID_INTEL_ALDER_LAKE_PCH_XHCI 0x51ed #define PCI_DEVICE_ID_AMD_RENOIR_XHCI 0x1639 #define PCI_DEVICE_ID_AMD_PROMONTORYA_4 0x43b9 @@ -266,7 +267,8 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) pdev->device == PCI_DEVICE_ID_INTEL_ICE_LAKE_XHCI || pdev->device == PCI_DEVICE_ID_INTEL_TIGER_LAKE_XHCI || pdev->device == PCI_DEVICE_ID_INTEL_MAPLE_RIDGE_XHCI || - pdev->device == PCI_DEVICE_ID_INTEL_ALDER_LAKE_XHCI)) + pdev->device == PCI_DEVICE_ID_INTEL_ALDER_LAKE_XHCI || + pdev->device == PCI_DEVICE_ID_INTEL_ALDER_LAKE_PCH_XHCI)) xhci->quirks |= XHCI_DEFAULT_PM_RUNTIME_ALLOW; if (pdev->vendor == PCI_VENDOR_ID_ETRON && diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index d0b6806275e0..f9707997969d 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -3141,6 +3141,7 @@ irqreturn_t xhci_irq(struct usb_hcd *hcd) if (event_loop++ < TRBS_PER_SEGMENT / 2) continue; xhci_update_erst_dequeue(xhci, event_ring_deq); + event_ring_deq = xhci->event_ring->dequeue; /* ring is half-full, force isoc trbs to interrupt more often */ if (xhci->isoc_bei_interval > AVOID_BEI_INTERVAL_MIN) diff --git a/drivers/usb/host/xhci-tegra.c b/drivers/usb/host/xhci-tegra.c index c8af2cd2216d..996958a6565c 100644 --- a/drivers/usb/host/xhci-tegra.c +++ b/drivers/usb/host/xhci-tegra.c @@ -1034,13 +1034,13 @@ static int tegra_xusb_unpowergate_partitions(struct tegra_xusb *tegra) int rc; if (tegra->use_genpd) { - rc = pm_runtime_get_sync(tegra->genpd_dev_ss); + rc = pm_runtime_resume_and_get(tegra->genpd_dev_ss); if (rc < 0) { dev_err(dev, "failed to enable XUSB SS partition\n"); return rc; } - rc = pm_runtime_get_sync(tegra->genpd_dev_host); + rc = pm_runtime_resume_and_get(tegra->genpd_dev_host); if (rc < 0) { dev_err(dev, "failed to enable XUSB Host partition\n"); pm_runtime_put_sync(tegra->genpd_dev_ss); diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index 642610c78f58..25b87e99b4dd 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -781,6 +781,17 @@ void xhci_shutdown(struct usb_hcd *hcd) if (xhci->quirks & XHCI_SPURIOUS_REBOOT) usb_disable_xhci_ports(to_pci_dev(hcd->self.sysdev)); + /* Don't poll the roothubs after shutdown. */ + xhci_dbg(xhci, "%s: stopping usb%d port polling.\n", + __func__, hcd->self.busnum); + clear_bit(HCD_FLAG_POLL_RH, &hcd->flags); + del_timer_sync(&hcd->rh_timer); + + if (xhci->shared_hcd) { + clear_bit(HCD_FLAG_POLL_RH, &xhci->shared_hcd->flags); + del_timer_sync(&xhci->shared_hcd->rh_timer); + } + spin_lock_irq(&xhci->lock); xhci_halt(xhci); /* Workaround for spurious wakeups at shutdown with HSW */ diff --git a/drivers/usb/misc/qcom_eud.c b/drivers/usb/misc/qcom_eud.c index f929bffdc5d1..b7f13df00764 100644 --- a/drivers/usb/misc/qcom_eud.c +++ b/drivers/usb/misc/qcom_eud.c @@ -186,16 +186,16 @@ static int eud_probe(struct platform_device *pdev) chip->dev = &pdev->dev; - ret = devm_add_action_or_reset(chip->dev, eud_role_switch_release, chip); - if (ret) - return dev_err_probe(chip->dev, ret, - "failed to add role switch release action\n"); - chip->role_sw = usb_role_switch_get(&pdev->dev); if (IS_ERR(chip->role_sw)) return dev_err_probe(chip->dev, PTR_ERR(chip->role_sw), "failed to get role switch\n"); + ret = devm_add_action_or_reset(chip->dev, eud_role_switch_release, chip); + if (ret) + return dev_err_probe(chip->dev, ret, + "failed to add role switch release action\n"); + chip->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(chip->base)) return PTR_ERR(chip->base); diff --git a/drivers/usb/misc/uss720.c b/drivers/usb/misc/uss720.c index 748139d26263..0be8efcda15d 100644 --- a/drivers/usb/misc/uss720.c +++ b/drivers/usb/misc/uss720.c @@ -71,6 +71,7 @@ static void destroy_priv(struct kref *kref) dev_dbg(&priv->usbdev->dev, "destroying priv datastructure\n"); usb_put_dev(priv->usbdev); + priv->usbdev = NULL; kfree(priv); } @@ -736,7 +737,6 @@ static int uss720_probe(struct usb_interface *intf, parport_announce_port(pp); usb_set_intfdata(intf, pp); - usb_put_dev(usbdev); return 0; probe_abort: @@ -754,7 +754,6 @@ static void uss720_disconnect(struct usb_interface *intf) usb_set_intfdata(intf, NULL); if (pp) { priv = pp->private_data; - priv->usbdev = NULL; priv->pp = NULL; dev_dbg(&intf->dev, "parport_remove_port\n"); parport_remove_port(pp); diff --git a/drivers/usb/mtu3/mtu3_dr.c b/drivers/usb/mtu3/mtu3_dr.c index a6b04831b20b..9b8aded3d95e 100644 --- a/drivers/usb/mtu3/mtu3_dr.c +++ b/drivers/usb/mtu3/mtu3_dr.c @@ -21,10 +21,8 @@ static inline struct ssusb_mtk *otg_sx_to_ssusb(struct otg_switch_mtk *otg_sx) static void toggle_opstate(struct ssusb_mtk *ssusb) { - if (!ssusb->otg_switch.is_u3_drd) { - mtu3_setbits(ssusb->mac_base, U3D_DEVICE_CONTROL, DC_SESSION); - mtu3_setbits(ssusb->mac_base, U3D_POWER_MANAGEMENT, SOFT_CONN); - } + mtu3_setbits(ssusb->mac_base, U3D_DEVICE_CONTROL, DC_SESSION); + mtu3_setbits(ssusb->mac_base, U3D_POWER_MANAGEMENT, SOFT_CONN); } /* only port0 supports dual-role mode */ diff --git a/drivers/usb/phy/phy-generic.c b/drivers/usb/phy/phy-generic.c index 661a229c105d..34b9f8140187 100644 --- a/drivers/usb/phy/phy-generic.c +++ b/drivers/usb/phy/phy-generic.c @@ -268,6 +268,13 @@ int usb_phy_gen_create_phy(struct device *dev, struct usb_phy_generic *nop) return -EPROBE_DEFER; } + nop->vbus_draw = devm_regulator_get_exclusive(dev, "vbus"); + if (PTR_ERR(nop->vbus_draw) == -ENODEV) + nop->vbus_draw = NULL; + if (IS_ERR(nop->vbus_draw)) + return dev_err_probe(dev, PTR_ERR(nop->vbus_draw), + "could not get vbus regulator\n"); + nop->dev = dev; nop->phy.dev = nop->dev; nop->phy.label = "nop-xceiv"; diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c index a27f7efcec6a..c374620a486f 100644 --- a/drivers/usb/serial/cp210x.c +++ b/drivers/usb/serial/cp210x.c @@ -194,6 +194,8 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x16DC, 0x0015) }, /* W-IE-NE-R Plein & Baus GmbH CML Control, Monitoring and Data Logger */ { USB_DEVICE(0x17A8, 0x0001) }, /* Kamstrup Optical Eye/3-wire */ { USB_DEVICE(0x17A8, 0x0005) }, /* Kamstrup M-Bus Master MultiPort 250D */ + { USB_DEVICE(0x17A8, 0x0101) }, /* Kamstrup 868 MHz wM-Bus C-Mode Meter Reader (Int Ant) */ + { USB_DEVICE(0x17A8, 0x0102) }, /* Kamstrup 868 MHz wM-Bus C-Mode Meter Reader (Ext Ant) */ { USB_DEVICE(0x17F4, 0xAAAA) }, /* Wavesense Jazz blood glucose meter */ { USB_DEVICE(0x1843, 0x0200) }, /* Vaisala USB Instrument Cable */ { USB_DEVICE(0x18EF, 0xE00F) }, /* ELV USB-I2C-Interface */ diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index e7755d9cfc61..152ad882657d 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -432,6 +432,8 @@ static void option_instat_callback(struct urb *urb); #define CINTERION_PRODUCT_CLS8 0x00b0 #define CINTERION_PRODUCT_MV31_MBIM 0x00b3 #define CINTERION_PRODUCT_MV31_RMNET 0x00b7 +#define CINTERION_PRODUCT_MV32_WA 0x00f1 +#define CINTERION_PRODUCT_MV32_WB 0x00f2 /* Olivetti products */ #define OLIVETTI_VENDOR_ID 0x0b3c @@ -1217,6 +1219,10 @@ static const struct usb_device_id option_ids[] = { .driver_info = NCTRL(0) | RSVD(1) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1056, 0xff), /* Telit FD980 */ .driver_info = NCTRL(2) | RSVD(3) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1057, 0xff), /* Telit FN980 */ + .driver_info = NCTRL(0) | RSVD(1) | RSVD(2) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1058, 0xff), /* Telit FN980 (PCIe) */ + .driver_info = NCTRL(0) | RSVD(1) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1060, 0xff), /* Telit LN920 (rmnet) */ .driver_info = NCTRL(0) | RSVD(1) | RSVD(2) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1061, 0xff), /* Telit LN920 (MBIM) */ @@ -1233,6 +1239,8 @@ static const struct usb_device_id option_ids[] = { .driver_info = NCTRL(2) | RSVD(3) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1073, 0xff), /* Telit FN990 (ECM) */ .driver_info = NCTRL(0) | RSVD(1) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1075, 0xff), /* Telit FN990 (PCIe) */ + .driver_info = RSVD(0) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910), .driver_info = NCTRL(0) | RSVD(1) | RSVD(3) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910_DUAL_MODEM), @@ -1969,6 +1977,10 @@ static const struct usb_device_id option_ids[] = { .driver_info = RSVD(3)}, { USB_DEVICE_INTERFACE_CLASS(CINTERION_VENDOR_ID, CINTERION_PRODUCT_MV31_RMNET, 0xff), .driver_info = RSVD(0)}, + { USB_DEVICE_INTERFACE_CLASS(CINTERION_VENDOR_ID, CINTERION_PRODUCT_MV32_WA, 0xff), + .driver_info = RSVD(3)}, + { USB_DEVICE_INTERFACE_CLASS(CINTERION_VENDOR_ID, CINTERION_PRODUCT_MV32_WB, 0xff), + .driver_info = RSVD(3)}, { USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD100), .driver_info = RSVD(4) }, { USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD120), @@ -2111,10 +2123,14 @@ static const struct usb_device_id option_ids[] = { .driver_info = RSVD(3) }, { USB_DEVICE(0x1508, 0x1001), /* Fibocom NL668 (IOT version) */ .driver_info = RSVD(4) | RSVD(5) | RSVD(6) }, + { USB_DEVICE(0x1782, 0x4d10) }, /* Fibocom L610 (AT mode) */ + { USB_DEVICE_INTERFACE_CLASS(0x1782, 0x4d11, 0xff) }, /* Fibocom L610 (ECM/RNDIS mode) */ { USB_DEVICE(0x2cb7, 0x0104), /* Fibocom NL678 series */ .driver_info = RSVD(4) | RSVD(5) }, { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x0105, 0xff), /* Fibocom NL678 series */ .driver_info = RSVD(6) }, + { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x0106, 0xff) }, /* Fibocom MA510 (ECM mode w/ diag intf.) */ + { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x010a, 0xff) }, /* Fibocom MA510 (ECM mode) */ { USB_DEVICE_AND_INTERFACE_INFO(0x2cb7, 0x010b, 0xff, 0xff, 0x30) }, /* Fibocom FG150 Diag */ { USB_DEVICE_AND_INTERFACE_INFO(0x2cb7, 0x010b, 0xff, 0, 0) }, /* Fibocom FG150 AT */ { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x01a0, 0xff) }, /* Fibocom NL668-AM/NL652-EU (laptop MBIM) */ diff --git a/drivers/usb/serial/pl2303.c b/drivers/usb/serial/pl2303.c index 88b284d61681..1d878d05a658 100644 --- a/drivers/usb/serial/pl2303.c +++ b/drivers/usb/serial/pl2303.c @@ -106,6 +106,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(HP_VENDOR_ID, HP_LCM220_PRODUCT_ID) }, { USB_DEVICE(HP_VENDOR_ID, HP_LCM960_PRODUCT_ID) }, { USB_DEVICE(HP_VENDOR_ID, HP_LM920_PRODUCT_ID) }, + { USB_DEVICE(HP_VENDOR_ID, HP_LM930_PRODUCT_ID) }, { USB_DEVICE(HP_VENDOR_ID, HP_LM940_PRODUCT_ID) }, { USB_DEVICE(HP_VENDOR_ID, HP_TD620_PRODUCT_ID) }, { USB_DEVICE(CRESSI_VENDOR_ID, CRESSI_EDY_PRODUCT_ID) }, diff --git a/drivers/usb/serial/pl2303.h b/drivers/usb/serial/pl2303.h index c5406452b774..732f9b13ad5d 100644 --- a/drivers/usb/serial/pl2303.h +++ b/drivers/usb/serial/pl2303.h @@ -135,6 +135,7 @@ #define HP_TD620_PRODUCT_ID 0x0956 #define HP_LD960_PRODUCT_ID 0x0b39 #define HP_LD381_PRODUCT_ID 0x0f7f +#define HP_LM930_PRODUCT_ID 0x0f9b #define HP_LCM220_PRODUCT_ID 0x3139 #define HP_LCM960_PRODUCT_ID 0x3239 #define HP_LD220_PRODUCT_ID 0x3524 diff --git a/drivers/usb/serial/qcserial.c b/drivers/usb/serial/qcserial.c index c18bf8164bc2..586ef5551e76 100644 --- a/drivers/usb/serial/qcserial.c +++ b/drivers/usb/serial/qcserial.c @@ -166,6 +166,8 @@ static const struct usb_device_id id_table[] = { {DEVICE_SWI(0x1199, 0x9090)}, /* Sierra Wireless EM7565 QDL */ {DEVICE_SWI(0x1199, 0x9091)}, /* Sierra Wireless EM7565 */ {DEVICE_SWI(0x1199, 0x90d2)}, /* Sierra Wireless EM9191 QDL */ + {DEVICE_SWI(0x1199, 0xc080)}, /* Sierra Wireless EM7590 QDL */ + {DEVICE_SWI(0x1199, 0xc081)}, /* Sierra Wireless EM7590 */ {DEVICE_SWI(0x413c, 0x81a2)}, /* Dell Wireless 5806 Gobi(TM) 4G LTE Mobile Broadband Card */ {DEVICE_SWI(0x413c, 0x81a3)}, /* Dell Wireless 5570 HSPA+ (42Mbps) Mobile Broadband Card */ {DEVICE_SWI(0x413c, 0x81a4)}, /* Dell Wireless 5570e HSPA+ (42Mbps) Mobile Broadband Card */ diff --git a/drivers/usb/serial/whiteheat.c b/drivers/usb/serial/whiteheat.c index da65d14c9ed5..06aad0d727dd 100644 --- a/drivers/usb/serial/whiteheat.c +++ b/drivers/usb/serial/whiteheat.c @@ -584,9 +584,8 @@ static int firm_send_command(struct usb_serial_port *port, __u8 command, switch (command) { case WHITEHEAT_GET_DTR_RTS: info = usb_get_serial_port_data(port); - memcpy(&info->mcr, command_info->result_buffer, - sizeof(struct whiteheat_dr_info)); - break; + info->mcr = command_info->result_buffer[0]; + break; } } exit: diff --git a/drivers/usb/typec/Kconfig b/drivers/usb/typec/Kconfig index 8f921213b17d..ba24847fb245 100644 --- a/drivers/usb/typec/Kconfig +++ b/drivers/usb/typec/Kconfig @@ -56,6 +56,7 @@ config TYPEC_RT1719 tristate "Richtek RT1719 Sink Only Type-C controller driver" depends on USB_ROLE_SWITCH || !USB_ROLE_SWITCH depends on I2C + depends on POWER_SUPPLY select REGMAP_I2C help Say Y or M here if your system has Richtek RT1719 sink only diff --git a/drivers/usb/typec/tcpm/tcpci.c b/drivers/usb/typec/tcpm/tcpci.c index e07d26a3cd8e..f33e08eb7670 100644 --- a/drivers/usb/typec/tcpm/tcpci.c +++ b/drivers/usb/typec/tcpm/tcpci.c @@ -877,7 +877,7 @@ static int tcpci_remove(struct i2c_client *client) /* Disable chip interrupts before unregistering port */ err = tcpci_write16(chip->tcpci, TCPC_ALERT_MASK, 0); if (err < 0) - return err; + dev_warn(&client->dev, "Failed to disable irqs (%pe)\n", ERR_PTR(err)); tcpci_unregister_port(chip->tcpci); diff --git a/drivers/usb/typec/tcpm/tcpci_mt6360.c b/drivers/usb/typec/tcpm/tcpci_mt6360.c index f1bd9e09bc87..8a952eaf9016 100644 --- a/drivers/usb/typec/tcpm/tcpci_mt6360.c +++ b/drivers/usb/typec/tcpm/tcpci_mt6360.c @@ -15,6 +15,9 @@ #include "tcpci.h" +#define MT6360_REG_PHYCTRL1 0x80 +#define MT6360_REG_PHYCTRL3 0x82 +#define MT6360_REG_PHYCTRL7 0x86 #define MT6360_REG_VCONNCTRL1 0x8C #define MT6360_REG_MODECTRL2 0x8F #define MT6360_REG_SWRESET 0xA0 @@ -22,6 +25,8 @@ #define MT6360_REG_DRPCTRL1 0xA2 #define MT6360_REG_DRPCTRL2 0xA3 #define MT6360_REG_I2CTORST 0xBF +#define MT6360_REG_PHYCTRL11 0xCA +#define MT6360_REG_RXCTRL1 0xCE #define MT6360_REG_RXCTRL2 0xCF #define MT6360_REG_CTDCTRL2 0xEC @@ -106,6 +111,27 @@ static int mt6360_tcpc_init(struct tcpci *tcpci, struct tcpci_data *tdata) if (ret) return ret; + /* BMC PHY */ + ret = mt6360_tcpc_write16(regmap, MT6360_REG_PHYCTRL1, 0x3A70); + if (ret) + return ret; + + ret = regmap_write(regmap, MT6360_REG_PHYCTRL3, 0x82); + if (ret) + return ret; + + ret = regmap_write(regmap, MT6360_REG_PHYCTRL7, 0x36); + if (ret) + return ret; + + ret = mt6360_tcpc_write16(regmap, MT6360_REG_PHYCTRL11, 0x3C60); + if (ret) + return ret; + + ret = regmap_write(regmap, MT6360_REG_RXCTRL1, 0xE8); + if (ret) + return ret; + /* Set shipping mode off, AUTOIDLE on */ return regmap_write(regmap, MT6360_REG_MODECTRL2, 0x7A); } diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c index f0c2fa19f3e0..a6045aef0d04 100644 --- a/drivers/usb/typec/ucsi/ucsi.c +++ b/drivers/usb/typec/ucsi/ucsi.c @@ -949,6 +949,8 @@ static int ucsi_dr_swap(struct typec_port *port, enum typec_data_role role) role == TYPEC_HOST)) goto out_unlock; + reinit_completion(&con->complete); + command = UCSI_SET_UOR | UCSI_CONNECTOR_NUMBER(con->num); command |= UCSI_SET_UOR_ROLE(role); command |= UCSI_SET_UOR_ACCEPT_ROLE_SWAPS; @@ -956,14 +958,18 @@ static int ucsi_dr_swap(struct typec_port *port, enum typec_data_role role) if (ret < 0) goto out_unlock; + mutex_unlock(&con->lock); + if (!wait_for_completion_timeout(&con->complete, - msecs_to_jiffies(UCSI_SWAP_TIMEOUT_MS))) - ret = -ETIMEDOUT; + msecs_to_jiffies(UCSI_SWAP_TIMEOUT_MS))) + return -ETIMEDOUT; + + return 0; out_unlock: mutex_unlock(&con->lock); - return ret < 0 ? ret : 0; + return ret; } static int ucsi_pr_swap(struct typec_port *port, enum typec_role role) @@ -985,6 +991,8 @@ static int ucsi_pr_swap(struct typec_port *port, enum typec_role role) if (cur_role == role) goto out_unlock; + reinit_completion(&con->complete); + command = UCSI_SET_PDR | UCSI_CONNECTOR_NUMBER(con->num); command |= UCSI_SET_PDR_ROLE(role); command |= UCSI_SET_PDR_ACCEPT_ROLE_SWAPS; @@ -992,11 +1000,13 @@ static int ucsi_pr_swap(struct typec_port *port, enum typec_role role) if (ret < 0) goto out_unlock; + mutex_unlock(&con->lock); + if (!wait_for_completion_timeout(&con->complete, - msecs_to_jiffies(UCSI_SWAP_TIMEOUT_MS))) { - ret = -ETIMEDOUT; - goto out_unlock; - } + msecs_to_jiffies(UCSI_SWAP_TIMEOUT_MS))) + return -ETIMEDOUT; + + mutex_lock(&con->lock); /* Something has gone wrong while swapping the role */ if (UCSI_CONSTAT_PWR_OPMODE(con->status.flags) != diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c index 2f4fb09f1e89..e0de44000d92 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -161,8 +161,10 @@ struct mlx5_vdpa_net { struct mlx5_flow_handle *rx_rule_mcast; bool setup; u32 cur_num_vqs; + u32 rqt_size; struct notifier_block nb; struct vdpa_callback config_cb; + struct mlx5_vdpa_wq_ent cvq_ent; }; static void free_resources(struct mlx5_vdpa_net *ndev); @@ -203,17 +205,12 @@ static __virtio16 cpu_to_mlx5vdpa16(struct mlx5_vdpa_dev *mvdev, u16 val) return __cpu_to_virtio16(mlx5_vdpa_is_little_endian(mvdev), val); } -static inline u32 mlx5_vdpa_max_qps(int max_vqs) -{ - return max_vqs / 2; -} - static u16 ctrl_vq_idx(struct mlx5_vdpa_dev *mvdev) { if (!(mvdev->actual_features & BIT_ULL(VIRTIO_NET_F_MQ))) return 2; - return 2 * mlx5_vdpa_max_qps(mvdev->max_vqs); + return mvdev->max_vqs; } static bool is_ctrl_vq_idx(struct mlx5_vdpa_dev *mvdev, u16 idx) @@ -1235,25 +1232,13 @@ static void teardown_vq(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue * static int create_rqt(struct mlx5_vdpa_net *ndev) { __be32 *list; - int max_rqt; void *rqtc; int inlen; void *in; int i, j; int err; - int num; - - if (!(ndev->mvdev.actual_features & BIT_ULL(VIRTIO_NET_F_MQ))) - num = 1; - else - num = ndev->cur_num_vqs / 2; - - max_rqt = min_t(int, roundup_pow_of_two(num), - 1 << MLX5_CAP_GEN(ndev->mvdev.mdev, log_max_rqt_size)); - if (max_rqt < 1) - return -EOPNOTSUPP; - inlen = MLX5_ST_SZ_BYTES(create_rqt_in) + max_rqt * MLX5_ST_SZ_BYTES(rq_num); + inlen = MLX5_ST_SZ_BYTES(create_rqt_in) + ndev->rqt_size * MLX5_ST_SZ_BYTES(rq_num); in = kzalloc(inlen, GFP_KERNEL); if (!in) return -ENOMEM; @@ -1262,12 +1247,12 @@ static int create_rqt(struct mlx5_vdpa_net *ndev) rqtc = MLX5_ADDR_OF(create_rqt_in, in, rqt_context); MLX5_SET(rqtc, rqtc, list_q_type, MLX5_RQTC_LIST_Q_TYPE_VIRTIO_NET_Q); - MLX5_SET(rqtc, rqtc, rqt_max_size, max_rqt); + MLX5_SET(rqtc, rqtc, rqt_max_size, ndev->rqt_size); list = MLX5_ADDR_OF(rqtc, rqtc, rq_num[0]); - for (i = 0, j = 0; i < max_rqt; i++, j += 2) - list[i] = cpu_to_be32(ndev->vqs[j % (2 * num)].virtq_id); + for (i = 0, j = 0; i < ndev->rqt_size; i++, j += 2) + list[i] = cpu_to_be32(ndev->vqs[j % ndev->cur_num_vqs].virtq_id); - MLX5_SET(rqtc, rqtc, rqt_actual_size, max_rqt); + MLX5_SET(rqtc, rqtc, rqt_actual_size, ndev->rqt_size); err = mlx5_vdpa_create_rqt(&ndev->mvdev, in, inlen, &ndev->res.rqtn); kfree(in); if (err) @@ -1281,19 +1266,13 @@ static int create_rqt(struct mlx5_vdpa_net *ndev) static int modify_rqt(struct mlx5_vdpa_net *ndev, int num) { __be32 *list; - int max_rqt; void *rqtc; int inlen; void *in; int i, j; int err; - max_rqt = min_t(int, roundup_pow_of_two(ndev->cur_num_vqs / 2), - 1 << MLX5_CAP_GEN(ndev->mvdev.mdev, log_max_rqt_size)); - if (max_rqt < 1) - return -EOPNOTSUPP; - - inlen = MLX5_ST_SZ_BYTES(modify_rqt_in) + max_rqt * MLX5_ST_SZ_BYTES(rq_num); + inlen = MLX5_ST_SZ_BYTES(modify_rqt_in) + ndev->rqt_size * MLX5_ST_SZ_BYTES(rq_num); in = kzalloc(inlen, GFP_KERNEL); if (!in) return -ENOMEM; @@ -1304,10 +1283,10 @@ static int modify_rqt(struct mlx5_vdpa_net *ndev, int num) MLX5_SET(rqtc, rqtc, list_q_type, MLX5_RQTC_LIST_Q_TYPE_VIRTIO_NET_Q); list = MLX5_ADDR_OF(rqtc, rqtc, rq_num[0]); - for (i = 0, j = 0; i < max_rqt; i++, j += 2) + for (i = 0, j = 0; i < ndev->rqt_size; i++, j += 2) list[i] = cpu_to_be32(ndev->vqs[j % num].virtq_id); - MLX5_SET(rqtc, rqtc, rqt_actual_size, max_rqt); + MLX5_SET(rqtc, rqtc, rqt_actual_size, ndev->rqt_size); err = mlx5_vdpa_modify_rqt(&ndev->mvdev, in, inlen, ndev->res.rqtn); kfree(in); if (err) @@ -1624,7 +1603,7 @@ static virtio_net_ctrl_ack handle_ctrl_mq(struct mlx5_vdpa_dev *mvdev, u8 cmd) newqps = mlx5vdpa16_to_cpu(mvdev, mq.virtqueue_pairs); if (newqps < VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MIN || - newqps > mlx5_vdpa_max_qps(mvdev->max_vqs)) + newqps > ndev->rqt_size) break; if (ndev->cur_num_vqs == 2 * newqps) { @@ -1658,6 +1637,12 @@ static void mlx5_cvq_kick_handler(struct work_struct *work) mvdev = wqent->mvdev; ndev = to_mlx5_vdpa_ndev(mvdev); cvq = &mvdev->cvq; + + mutex_lock(&ndev->reslock); + + if (!(mvdev->status & VIRTIO_CONFIG_S_DRIVER_OK)) + goto out; + if (!(ndev->mvdev.actual_features & BIT_ULL(VIRTIO_NET_F_CTRL_VQ))) goto out; @@ -1696,9 +1681,13 @@ static void mlx5_cvq_kick_handler(struct work_struct *work) if (vringh_need_notify_iotlb(&cvq->vring)) vringh_notify(&cvq->vring); + + queue_work(mvdev->wq, &wqent->work); + break; } + out: - kfree(wqent); + mutex_unlock(&ndev->reslock); } static void mlx5_vdpa_kick_vq(struct vdpa_device *vdev, u16 idx) @@ -1706,7 +1695,6 @@ static void mlx5_vdpa_kick_vq(struct vdpa_device *vdev, u16 idx) struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev); struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev); struct mlx5_vdpa_virtqueue *mvq; - struct mlx5_vdpa_wq_ent *wqent; if (!is_index_valid(mvdev, idx)) return; @@ -1715,13 +1703,7 @@ static void mlx5_vdpa_kick_vq(struct vdpa_device *vdev, u16 idx) if (!mvdev->wq || !mvdev->cvq.ready) return; - wqent = kzalloc(sizeof(*wqent), GFP_ATOMIC); - if (!wqent) - return; - - wqent->mvdev = mvdev; - INIT_WORK(&wqent->work, mlx5_cvq_kick_handler); - queue_work(mvdev->wq, &wqent->work); + queue_work(mvdev->wq, &ndev->cvq_ent.work); return; } @@ -1985,7 +1967,7 @@ static int setup_virtqueues(struct mlx5_vdpa_dev *mvdev) int err; int i; - for (i = 0; i < 2 * mlx5_vdpa_max_qps(mvdev->max_vqs); i++) { + for (i = 0; i < mvdev->max_vqs; i++) { err = setup_vq(ndev, &ndev->vqs[i]); if (err) goto err_vq; @@ -2056,9 +2038,11 @@ static int mlx5_vdpa_set_driver_features(struct vdpa_device *vdev, u64 features) ndev->mvdev.actual_features = features & ndev->mvdev.mlx_features; if (ndev->mvdev.actual_features & BIT_ULL(VIRTIO_NET_F_MQ)) - ndev->cur_num_vqs = 2 * mlx5vdpa16_to_cpu(mvdev, ndev->config.max_virtqueue_pairs); + ndev->rqt_size = mlx5vdpa16_to_cpu(mvdev, ndev->config.max_virtqueue_pairs); else - ndev->cur_num_vqs = 2; + ndev->rqt_size = 1; + + ndev->cur_num_vqs = 2 * ndev->rqt_size; update_cvq_info(mvdev); return err; @@ -2180,7 +2164,7 @@ static int mlx5_vdpa_change_map(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb goto err_mr; if (!(mvdev->status & VIRTIO_CONFIG_S_DRIVER_OK)) - return 0; + goto err_mr; restore_channels_info(ndev); err = setup_driver(mvdev); @@ -2195,12 +2179,14 @@ err_mr: return err; } +/* reslock must be held for this function */ static int setup_driver(struct mlx5_vdpa_dev *mvdev) { struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev); int err; - mutex_lock(&ndev->reslock); + WARN_ON(!mutex_is_locked(&ndev->reslock)); + if (ndev->setup) { mlx5_vdpa_warn(mvdev, "setup driver called for already setup driver\n"); err = 0; @@ -2230,7 +2216,6 @@ static int setup_driver(struct mlx5_vdpa_dev *mvdev) goto err_fwd; } ndev->setup = true; - mutex_unlock(&ndev->reslock); return 0; @@ -2241,23 +2226,23 @@ err_tir: err_rqt: teardown_virtqueues(ndev); out: - mutex_unlock(&ndev->reslock); return err; } +/* reslock must be held for this function */ static void teardown_driver(struct mlx5_vdpa_net *ndev) { - mutex_lock(&ndev->reslock); + + WARN_ON(!mutex_is_locked(&ndev->reslock)); + if (!ndev->setup) - goto out; + return; remove_fwd_to_tir(ndev); destroy_tir(ndev); destroy_rqt(ndev); teardown_virtqueues(ndev); ndev->setup = false; -out: - mutex_unlock(&ndev->reslock); } static void clear_vqs_ready(struct mlx5_vdpa_net *ndev) @@ -2278,6 +2263,8 @@ static void mlx5_vdpa_set_status(struct vdpa_device *vdev, u8 status) print_status(mvdev, status, true); + mutex_lock(&ndev->reslock); + if ((status ^ ndev->mvdev.status) & VIRTIO_CONFIG_S_DRIVER_OK) { if (status & VIRTIO_CONFIG_S_DRIVER_OK) { err = setup_driver(mvdev); @@ -2287,16 +2274,19 @@ static void mlx5_vdpa_set_status(struct vdpa_device *vdev, u8 status) } } else { mlx5_vdpa_warn(mvdev, "did not expect DRIVER_OK to be cleared\n"); - return; + goto err_clear; } } ndev->mvdev.status = status; + mutex_unlock(&ndev->reslock); return; err_setup: mlx5_vdpa_destroy_mr(&ndev->mvdev); ndev->mvdev.status |= VIRTIO_CONFIG_S_FAILED; +err_clear: + mutex_unlock(&ndev->reslock); } static int mlx5_vdpa_reset(struct vdpa_device *vdev) @@ -2306,6 +2296,8 @@ static int mlx5_vdpa_reset(struct vdpa_device *vdev) print_status(mvdev, 0, true); mlx5_vdpa_info(mvdev, "performing device reset\n"); + + mutex_lock(&ndev->reslock); teardown_driver(ndev); clear_vqs_ready(ndev); mlx5_vdpa_destroy_mr(&ndev->mvdev); @@ -2318,6 +2310,7 @@ static int mlx5_vdpa_reset(struct vdpa_device *vdev) if (mlx5_vdpa_create_mr(mvdev, NULL)) mlx5_vdpa_warn(mvdev, "create MR failed\n"); } + mutex_unlock(&ndev->reslock); return 0; } @@ -2353,19 +2346,24 @@ static u32 mlx5_vdpa_get_generation(struct vdpa_device *vdev) static int mlx5_vdpa_set_map(struct vdpa_device *vdev, struct vhost_iotlb *iotlb) { struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev); + struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev); bool change_map; int err; + mutex_lock(&ndev->reslock); + err = mlx5_vdpa_handle_set_map(mvdev, iotlb, &change_map); if (err) { mlx5_vdpa_warn(mvdev, "set map failed(%d)\n", err); - return err; + goto err; } if (change_map) - return mlx5_vdpa_change_map(mvdev, iotlb); + err = mlx5_vdpa_change_map(mvdev, iotlb); - return 0; +err: + mutex_unlock(&ndev->reslock); + return err; } static void mlx5_vdpa_free(struct vdpa_device *vdev) @@ -2511,7 +2509,7 @@ static void init_mvqs(struct mlx5_vdpa_net *ndev) struct mlx5_vdpa_virtqueue *mvq; int i; - for (i = 0; i < 2 * mlx5_vdpa_max_qps(ndev->mvdev.max_vqs); ++i) { + for (i = 0; i < ndev->mvdev.max_vqs; ++i) { mvq = &ndev->vqs[i]; memset(mvq, 0, offsetof(struct mlx5_vdpa_virtqueue, ri)); mvq->index = i; @@ -2653,7 +2651,8 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name, return -EOPNOTSUPP; } - max_vqs = MLX5_CAP_DEV_VDPA_EMULATION(mdev, max_num_virtio_queues); + max_vqs = min_t(int, MLX5_CAP_DEV_VDPA_EMULATION(mdev, max_num_virtio_queues), + 1 << MLX5_CAP_GEN(mdev, log_max_rqt_size)); if (max_vqs < 2) { dev_warn(mdev->device, "%d virtqueues are supported. At least 2 are required\n", @@ -2724,7 +2723,7 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name, ndev->mvdev.mlx_features |= BIT_ULL(VIRTIO_NET_F_MAC); } - config->max_virtqueue_pairs = cpu_to_mlx5vdpa16(mvdev, mlx5_vdpa_max_qps(max_vqs)); + config->max_virtqueue_pairs = cpu_to_mlx5vdpa16(mvdev, max_vqs / 2); mvdev->vdev.dma_dev = &mdev->pdev->dev; err = mlx5_vdpa_alloc_resources(&ndev->mvdev); if (err) @@ -2740,6 +2739,8 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name, if (err) goto err_mr; + ndev->cvq_ent.mvdev = mvdev; + INIT_WORK(&ndev->cvq_ent.work, mlx5_cvq_kick_handler); mvdev->wq = create_singlethread_workqueue("mlx5_vdpa_wq"); if (!mvdev->wq) { err = -ENOMEM; @@ -2749,7 +2750,7 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name, ndev->nb.notifier_call = event_handler; mlx5_notifier_register(mdev, &ndev->nb); mvdev->vdev.mdev = &mgtdev->mgtdev; - err = _vdpa_register_device(&mvdev->vdev, 2 * mlx5_vdpa_max_qps(max_vqs) + 1); + err = _vdpa_register_device(&mvdev->vdev, max_vqs + 1); if (err) goto err_reg; diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c index b7bb16f92ac6..06b6f3594a13 100644 --- a/drivers/vfio/pci/vfio_pci_core.c +++ b/drivers/vfio/pci/vfio_pci_core.c @@ -36,6 +36,10 @@ static bool nointxmask; static bool disable_vga; static bool disable_idle_d3; +/* List of PF's that vfio_pci_core_sriov_configure() has been called on */ +static DEFINE_MUTEX(vfio_pci_sriov_pfs_mutex); +static LIST_HEAD(vfio_pci_sriov_pfs); + static inline bool vfio_vga_disabled(void) { #ifdef CONFIG_VFIO_PCI_VGA @@ -434,47 +438,17 @@ out: } EXPORT_SYMBOL_GPL(vfio_pci_core_disable); -static struct vfio_pci_core_device *get_pf_vdev(struct vfio_pci_core_device *vdev) -{ - struct pci_dev *physfn = pci_physfn(vdev->pdev); - struct vfio_device *pf_dev; - - if (!vdev->pdev->is_virtfn) - return NULL; - - pf_dev = vfio_device_get_from_dev(&physfn->dev); - if (!pf_dev) - return NULL; - - if (pci_dev_driver(physfn) != pci_dev_driver(vdev->pdev)) { - vfio_device_put(pf_dev); - return NULL; - } - - return container_of(pf_dev, struct vfio_pci_core_device, vdev); -} - -static void vfio_pci_vf_token_user_add(struct vfio_pci_core_device *vdev, int val) -{ - struct vfio_pci_core_device *pf_vdev = get_pf_vdev(vdev); - - if (!pf_vdev) - return; - - mutex_lock(&pf_vdev->vf_token->lock); - pf_vdev->vf_token->users += val; - WARN_ON(pf_vdev->vf_token->users < 0); - mutex_unlock(&pf_vdev->vf_token->lock); - - vfio_device_put(&pf_vdev->vdev); -} - void vfio_pci_core_close_device(struct vfio_device *core_vdev) { struct vfio_pci_core_device *vdev = container_of(core_vdev, struct vfio_pci_core_device, vdev); - vfio_pci_vf_token_user_add(vdev, -1); + if (vdev->sriov_pf_core_dev) { + mutex_lock(&vdev->sriov_pf_core_dev->vf_token->lock); + WARN_ON(!vdev->sriov_pf_core_dev->vf_token->users); + vdev->sriov_pf_core_dev->vf_token->users--; + mutex_unlock(&vdev->sriov_pf_core_dev->vf_token->lock); + } vfio_spapr_pci_eeh_release(vdev->pdev); vfio_pci_core_disable(vdev); @@ -495,7 +469,12 @@ void vfio_pci_core_finish_enable(struct vfio_pci_core_device *vdev) { vfio_pci_probe_mmaps(vdev); vfio_spapr_pci_eeh_open(vdev->pdev); - vfio_pci_vf_token_user_add(vdev, 1); + + if (vdev->sriov_pf_core_dev) { + mutex_lock(&vdev->sriov_pf_core_dev->vf_token->lock); + vdev->sriov_pf_core_dev->vf_token->users++; + mutex_unlock(&vdev->sriov_pf_core_dev->vf_token->lock); + } } EXPORT_SYMBOL_GPL(vfio_pci_core_finish_enable); @@ -1583,11 +1562,8 @@ static int vfio_pci_validate_vf_token(struct vfio_pci_core_device *vdev, * * If the VF token is provided but unused, an error is generated. */ - if (!vdev->pdev->is_virtfn && !vdev->vf_token && !vf_token) - return 0; /* No VF token provided or required */ - if (vdev->pdev->is_virtfn) { - struct vfio_pci_core_device *pf_vdev = get_pf_vdev(vdev); + struct vfio_pci_core_device *pf_vdev = vdev->sriov_pf_core_dev; bool match; if (!pf_vdev) { @@ -1600,7 +1576,6 @@ static int vfio_pci_validate_vf_token(struct vfio_pci_core_device *vdev, } if (!vf_token) { - vfio_device_put(&pf_vdev->vdev); pci_info_ratelimited(vdev->pdev, "VF token required to access device\n"); return -EACCES; @@ -1610,8 +1585,6 @@ static int vfio_pci_validate_vf_token(struct vfio_pci_core_device *vdev, match = uuid_equal(uuid, &pf_vdev->vf_token->uuid); mutex_unlock(&pf_vdev->vf_token->lock); - vfio_device_put(&pf_vdev->vdev); - if (!match) { pci_info_ratelimited(vdev->pdev, "Incorrect VF token provided for device\n"); @@ -1732,8 +1705,30 @@ static int vfio_pci_bus_notifier(struct notifier_block *nb, static int vfio_pci_vf_init(struct vfio_pci_core_device *vdev) { struct pci_dev *pdev = vdev->pdev; + struct vfio_pci_core_device *cur; + struct pci_dev *physfn; int ret; + if (pdev->is_virtfn) { + /* + * If this VF was created by our vfio_pci_core_sriov_configure() + * then we can find the PF vfio_pci_core_device now, and due to + * the locking in pci_disable_sriov() it cannot change until + * this VF device driver is removed. + */ + physfn = pci_physfn(vdev->pdev); + mutex_lock(&vfio_pci_sriov_pfs_mutex); + list_for_each_entry(cur, &vfio_pci_sriov_pfs, sriov_pfs_item) { + if (cur->pdev == physfn) { + vdev->sriov_pf_core_dev = cur; + break; + } + } + mutex_unlock(&vfio_pci_sriov_pfs_mutex); + return 0; + } + + /* Not a SRIOV PF */ if (!pdev->is_physfn) return 0; @@ -1805,6 +1800,7 @@ void vfio_pci_core_init_device(struct vfio_pci_core_device *vdev, INIT_LIST_HEAD(&vdev->ioeventfds_list); mutex_init(&vdev->vma_lock); INIT_LIST_HEAD(&vdev->vma_list); + INIT_LIST_HEAD(&vdev->sriov_pfs_item); init_rwsem(&vdev->memory_lock); } EXPORT_SYMBOL_GPL(vfio_pci_core_init_device); @@ -1896,7 +1892,7 @@ void vfio_pci_core_unregister_device(struct vfio_pci_core_device *vdev) { struct pci_dev *pdev = vdev->pdev; - pci_disable_sriov(pdev); + vfio_pci_core_sriov_configure(pdev, 0); vfio_unregister_group_dev(&vdev->vdev); @@ -1935,21 +1931,49 @@ EXPORT_SYMBOL_GPL(vfio_pci_core_aer_err_detected); int vfio_pci_core_sriov_configure(struct pci_dev *pdev, int nr_virtfn) { + struct vfio_pci_core_device *vdev; struct vfio_device *device; int ret = 0; + device_lock_assert(&pdev->dev); + device = vfio_device_get_from_dev(&pdev->dev); if (!device) return -ENODEV; - if (nr_virtfn == 0) - pci_disable_sriov(pdev); - else + vdev = container_of(device, struct vfio_pci_core_device, vdev); + + if (nr_virtfn) { + mutex_lock(&vfio_pci_sriov_pfs_mutex); + /* + * The thread that adds the vdev to the list is the only thread + * that gets to call pci_enable_sriov() and we will only allow + * it to be called once without going through + * pci_disable_sriov() + */ + if (!list_empty(&vdev->sriov_pfs_item)) { + ret = -EINVAL; + goto out_unlock; + } + list_add_tail(&vdev->sriov_pfs_item, &vfio_pci_sriov_pfs); + mutex_unlock(&vfio_pci_sriov_pfs_mutex); ret = pci_enable_sriov(pdev, nr_virtfn); + if (ret) + goto out_del; + ret = nr_virtfn; + goto out_put; + } - vfio_device_put(device); + pci_disable_sriov(pdev); - return ret < 0 ? ret : nr_virtfn; +out_del: + mutex_lock(&vfio_pci_sriov_pfs_mutex); + list_del_init(&vdev->sriov_pfs_item); +out_unlock: + mutex_unlock(&vfio_pci_sriov_pfs_mutex); +out_put: + vfio_device_put(device); + return ret; } EXPORT_SYMBOL_GPL(vfio_pci_core_sriov_configure); diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 792ab5f23647..297b5db47454 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -1450,13 +1450,9 @@ err: return ERR_PTR(r); } -static struct ptr_ring *get_tap_ptr_ring(int fd) +static struct ptr_ring *get_tap_ptr_ring(struct file *file) { struct ptr_ring *ring; - struct file *file = fget(fd); - - if (!file) - return NULL; ring = tun_get_tx_ring(file); if (!IS_ERR(ring)) goto out; @@ -1465,7 +1461,6 @@ static struct ptr_ring *get_tap_ptr_ring(int fd) goto out; ring = NULL; out: - fput(file); return ring; } @@ -1552,8 +1547,12 @@ static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd) r = vhost_net_enable_vq(n, vq); if (r) goto err_used; - if (index == VHOST_NET_VQ_RX) - nvq->rx_ring = get_tap_ptr_ring(fd); + if (index == VHOST_NET_VQ_RX) { + if (sock) + nvq->rx_ring = get_tap_ptr_ring(sock->file); + else + nvq->rx_ring = NULL; + } oldubufs = nvq->ubufs; nvq->ubufs = ubufs; diff --git a/drivers/video/fbdev/arkfb.c b/drivers/video/fbdev/arkfb.c index edf169d0816e..eb3e47c58c5f 100644 --- a/drivers/video/fbdev/arkfb.c +++ b/drivers/video/fbdev/arkfb.c @@ -566,6 +566,9 @@ static int arkfb_check_var(struct fb_var_screeninfo *var, struct fb_info *info) { int rv, mem, step; + if (!var->pixclock) + return -EINVAL; + /* Find appropriate format */ rv = svga_match_format (arkfb_formats, var, NULL); if (rv < 0) diff --git a/drivers/video/fbdev/aty/aty128fb.c b/drivers/video/fbdev/aty/aty128fb.c index 6ff16d3132e5..b26c81233b6b 100644 --- a/drivers/video/fbdev/aty/aty128fb.c +++ b/drivers/video/fbdev/aty/aty128fb.c @@ -68,7 +68,6 @@ #ifdef CONFIG_PPC_PMAC #include <asm/machdep.h> #include <asm/pmac_feature.h> -#include <asm/prom.h> #include "../macmodes.h" #endif diff --git a/drivers/video/fbdev/aty/atyfb_base.c b/drivers/video/fbdev/aty/atyfb_base.c index 1aef3d6ebd88..a3e6faed7745 100644 --- a/drivers/video/fbdev/aty/atyfb_base.c +++ b/drivers/video/fbdev/aty/atyfb_base.c @@ -79,7 +79,6 @@ #ifdef __powerpc__ #include <asm/machdep.h> -#include <asm/prom.h> #include "../macmodes.h" #endif #ifdef __sparc__ diff --git a/drivers/video/fbdev/aty/radeon_pm.c b/drivers/video/fbdev/aty/radeon_pm.c index b5fbd5329652..97a5972f5b1f 100644 --- a/drivers/video/fbdev/aty/radeon_pm.c +++ b/drivers/video/fbdev/aty/radeon_pm.c @@ -22,7 +22,6 @@ #ifdef CONFIG_PPC_PMAC #include <asm/machdep.h> -#include <asm/prom.h> #include <asm/pmac_feature.h> #endif diff --git a/drivers/video/fbdev/aty/radeonfb.h b/drivers/video/fbdev/aty/radeonfb.h index 93f403cbb415..91d81b576231 100644 --- a/drivers/video/fbdev/aty/radeonfb.h +++ b/drivers/video/fbdev/aty/radeonfb.h @@ -21,7 +21,7 @@ #include <asm/io.h> -#if defined(CONFIG_PPC) || defined(CONFIG_SPARC) +#ifdef CONFIG_SPARC #include <asm/prom.h> #endif diff --git a/drivers/video/fbdev/clps711x-fb.c b/drivers/video/fbdev/clps711x-fb.c index c5d15c6db287..771ce1f76951 100644 --- a/drivers/video/fbdev/clps711x-fb.c +++ b/drivers/video/fbdev/clps711x-fb.c @@ -268,8 +268,7 @@ static int clps711x_fb_probe(struct platform_device *pdev) goto out_fb_release; } - cfb->syscon = - syscon_regmap_lookup_by_compatible("cirrus,ep7209-syscon1"); + cfb->syscon = syscon_regmap_lookup_by_phandle(np, "syscon"); if (IS_ERR(cfb->syscon)) { ret = PTR_ERR(cfb->syscon); goto out_fb_release; diff --git a/drivers/video/fbdev/controlfb.c b/drivers/video/fbdev/controlfb.c index bd59e7b11ed5..aba46118b208 100644 --- a/drivers/video/fbdev/controlfb.c +++ b/drivers/video/fbdev/controlfb.c @@ -47,9 +47,6 @@ #include <linux/nvram.h> #include <linux/adb.h> #include <linux/cuda.h> -#ifdef CONFIG_PPC_PMAC -#include <asm/prom.h> -#endif #ifdef CONFIG_BOOTX_TEXT #include <asm/btext.h> #endif diff --git a/drivers/video/fbdev/core/fbmem.c b/drivers/video/fbdev/core/fbmem.c index 34d6bb1bf82e..a6bb0e438216 100644 --- a/drivers/video/fbdev/core/fbmem.c +++ b/drivers/video/fbdev/core/fbmem.c @@ -1579,7 +1579,14 @@ static void do_remove_conflicting_framebuffers(struct apertures_struct *a, * If it's not a platform device, at least print a warning. A * fix would add code to remove the device from the system. */ - if (dev_is_platform(device)) { + if (!device) { + /* TODO: Represent each OF framebuffer as its own + * device in the device hierarchy. For now, offb + * doesn't have such a device, so unregister the + * framebuffer as before without warning. + */ + do_unregister_framebuffer(registered_fb[i]); + } else if (dev_is_platform(device)) { registered_fb[i]->forced_out = true; platform_device_unregister(to_platform_device(device)); } else { diff --git a/drivers/video/fbdev/core/fbsysfs.c b/drivers/video/fbdev/core/fbsysfs.c index 26892940c213..82e31a2d845e 100644 --- a/drivers/video/fbdev/core/fbsysfs.c +++ b/drivers/video/fbdev/core/fbsysfs.c @@ -80,6 +80,10 @@ void framebuffer_release(struct fb_info *info) { if (!info) return; + + if (WARN_ON(refcount_read(&info->count))) + return; + kfree(info->apertures); kfree(info); } diff --git a/drivers/video/fbdev/efifb.c b/drivers/video/fbdev/efifb.c index ea42ba6445b2..b3d5f884c544 100644 --- a/drivers/video/fbdev/efifb.c +++ b/drivers/video/fbdev/efifb.c @@ -243,6 +243,10 @@ error: static inline void efifb_show_boot_graphics(struct fb_info *info) {} #endif +/* + * fb_ops.fb_destroy is called by the last put_fb_info() call at the end + * of unregister_framebuffer() or fb_release(). Do any cleanup here. + */ static void efifb_destroy(struct fb_info *info) { if (efifb_pci_dev) @@ -254,10 +258,13 @@ static void efifb_destroy(struct fb_info *info) else memunmap(info->screen_base); } + if (request_mem_succeeded) release_mem_region(info->apertures->ranges[0].base, info->apertures->ranges[0].size); fb_dealloc_cmap(&info->cmap); + + framebuffer_release(info); } static const struct fb_ops efifb_ops = { @@ -620,9 +627,9 @@ static int efifb_remove(struct platform_device *pdev) { struct fb_info *info = platform_get_drvdata(pdev); + /* efifb_destroy takes care of info cleanup */ unregister_framebuffer(info); sysfs_remove_groups(&pdev->dev.kobj, efifb_groups); - framebuffer_release(info); return 0; } diff --git a/drivers/video/fbdev/i740fb.c b/drivers/video/fbdev/i740fb.c index 52cce0db8bd3..09dd85553d4f 100644 --- a/drivers/video/fbdev/i740fb.c +++ b/drivers/video/fbdev/i740fb.c @@ -657,6 +657,9 @@ static int i740fb_decode_var(const struct fb_var_screeninfo *var, static int i740fb_check_var(struct fb_var_screeninfo *var, struct fb_info *info) { + if (!var->pixclock) + return -EINVAL; + switch (var->bits_per_pixel) { case 8: var->red.offset = var->green.offset = var->blue.offset = 0; @@ -740,7 +743,7 @@ static int i740fb_set_par(struct fb_info *info) if (i) return i; - memset(info->screen_base, 0, info->screen_size); + memset_io(info->screen_base, 0, info->screen_size); vga_protect(par); diff --git a/drivers/video/fbdev/imxfb.c b/drivers/video/fbdev/imxfb.c index 68288756ffff..a2f644c97f28 100644 --- a/drivers/video/fbdev/imxfb.c +++ b/drivers/video/fbdev/imxfb.c @@ -925,10 +925,12 @@ static int imxfb_probe(struct platform_device *pdev) sizeof(struct imx_fb_videomode), GFP_KERNEL); if (!fbi->mode) { ret = -ENOMEM; + of_node_put(display_np); goto failed_of_parse; } ret = imxfb_of_read_mode(&pdev->dev, display_np, fbi->mode); + of_node_put(display_np); if (ret) goto failed_of_parse; } diff --git a/drivers/video/fbdev/kyro/fbdev.c b/drivers/video/fbdev/kyro/fbdev.c index 25801e8e3f74..d57772f96ad2 100644 --- a/drivers/video/fbdev/kyro/fbdev.c +++ b/drivers/video/fbdev/kyro/fbdev.c @@ -494,6 +494,8 @@ static int kyrofb_set_par(struct fb_info *info) info->var.hsync_len + info->var.left_margin)) / 1000; + if (!lineclock) + return -EINVAL; /* time for a frame in ns (precision in 32bpp) */ frameclock = lineclock * (info->var.yres + diff --git a/drivers/video/fbdev/matrox/matroxfb_base.h b/drivers/video/fbdev/matrox/matroxfb_base.h index 759dee996af1..958be6805f87 100644 --- a/drivers/video/fbdev/matrox/matroxfb_base.h +++ b/drivers/video/fbdev/matrox/matroxfb_base.h @@ -47,7 +47,6 @@ #include <asm/unaligned.h> #if defined(CONFIG_PPC_PMAC) -#include <asm/prom.h> #include "../macmodes.h" #endif diff --git a/drivers/video/fbdev/mb862xx/mb862xxfbdrv.c b/drivers/video/fbdev/mb862xx/mb862xxfbdrv.c index 63721337a377..a7508f5be343 100644 --- a/drivers/video/fbdev/mb862xx/mb862xxfbdrv.c +++ b/drivers/video/fbdev/mb862xx/mb862xxfbdrv.c @@ -18,6 +18,8 @@ #include <linux/interrupt.h> #include <linux/pci.h> #if defined(CONFIG_OF) +#include <linux/of_address.h> +#include <linux/of_irq.h> #include <linux/of_platform.h> #endif #include "mb862xxfb.h" diff --git a/drivers/video/fbdev/mmp/core.c b/drivers/video/fbdev/mmp/core.c index 154127256a2c..03707461eced 100644 --- a/drivers/video/fbdev/mmp/core.c +++ b/drivers/video/fbdev/mmp/core.c @@ -127,19 +127,18 @@ EXPORT_SYMBOL_GPL(mmp_unregister_panel); */ struct mmp_path *mmp_get_path(const char *name) { - struct mmp_path *path; - int found = 0; + struct mmp_path *path = NULL, *iter; mutex_lock(&disp_lock); - list_for_each_entry(path, &path_list, node) { - if (!strcmp(name, path->name)) { - found = 1; + list_for_each_entry(iter, &path_list, node) { + if (!strcmp(name, iter->name)) { + path = iter; break; } } mutex_unlock(&disp_lock); - return found ? path : NULL; + return path; } EXPORT_SYMBOL_GPL(mmp_get_path); diff --git a/drivers/video/fbdev/neofb.c b/drivers/video/fbdev/neofb.c index 966df2a07360..28d32cbf496b 100644 --- a/drivers/video/fbdev/neofb.c +++ b/drivers/video/fbdev/neofb.c @@ -585,7 +585,7 @@ neofb_check_var(struct fb_var_screeninfo *var, struct fb_info *info) DBG("neofb_check_var"); - if (var->pixclock && PICOS2KHZ(var->pixclock) > par->maxClock) + if (!var->pixclock || PICOS2KHZ(var->pixclock) > par->maxClock) return -EINVAL; /* Is the mode larger than the LCD panel? */ diff --git a/drivers/video/fbdev/omap/hwa742.c b/drivers/video/fbdev/omap/hwa742.c index b191bef22d98..9d9fe5c3a7a1 100644 --- a/drivers/video/fbdev/omap/hwa742.c +++ b/drivers/video/fbdev/omap/hwa742.c @@ -964,7 +964,7 @@ static int hwa742_init(struct omapfb_device *fbdev, int ext_mode, if ((r = calc_extif_timings(ext_clk, &extif_mem_div)) < 0) goto err3; hwa742.extif->set_timings(&hwa742.reg_timings); - clk_enable(hwa742.sys_ck); + clk_prepare_enable(hwa742.sys_ck); calc_hwa742_clk_rates(ext_clk, &sys_clk, &pix_clk); if ((r = calc_extif_timings(sys_clk, &extif_mem_div)) < 0) @@ -1023,7 +1023,7 @@ static int hwa742_init(struct omapfb_device *fbdev, int ext_mode, return 0; err4: - clk_disable(hwa742.sys_ck); + clk_disable_unprepare(hwa742.sys_ck); err3: hwa742.extif->cleanup(); err2: @@ -1037,7 +1037,7 @@ static void hwa742_cleanup(void) hwa742_set_update_mode(OMAPFB_UPDATE_DISABLED); hwa742.extif->cleanup(); hwa742.int_ctrl->cleanup(); - clk_disable(hwa742.sys_ck); + clk_disable_unprepare(hwa742.sys_ck); } struct lcd_ctrl hwa742_ctrl = { diff --git a/drivers/video/fbdev/omap/lcdc.c b/drivers/video/fbdev/omap/lcdc.c index 7317c9aad677..97d20dc0d1d0 100644 --- a/drivers/video/fbdev/omap/lcdc.c +++ b/drivers/video/fbdev/omap/lcdc.c @@ -711,7 +711,7 @@ static int omap_lcdc_init(struct omapfb_device *fbdev, int ext_mode, dev_err(fbdev->dev, "failed to adjust LCD rate\n"); goto fail1; } - clk_enable(lcdc.lcd_ck); + clk_prepare_enable(lcdc.lcd_ck); r = request_irq(OMAP_LCDC_IRQ, lcdc_irq_handler, 0, MODULE_NAME, fbdev); if (r) { @@ -746,7 +746,7 @@ fail4: fail3: free_irq(OMAP_LCDC_IRQ, lcdc.fbdev); fail2: - clk_disable(lcdc.lcd_ck); + clk_disable_unprepare(lcdc.lcd_ck); fail1: clk_put(lcdc.lcd_ck); fail0: @@ -760,7 +760,7 @@ static void omap_lcdc_cleanup(void) free_fbmem(); omap_free_lcd_dma(); free_irq(OMAP_LCDC_IRQ, lcdc.fbdev); - clk_disable(lcdc.lcd_ck); + clk_disable_unprepare(lcdc.lcd_ck); clk_put(lcdc.lcd_ck); } diff --git a/drivers/video/fbdev/omap/sossi.c b/drivers/video/fbdev/omap/sossi.c index 80ac67f27f0d..b9cb8b386627 100644 --- a/drivers/video/fbdev/omap/sossi.c +++ b/drivers/video/fbdev/omap/sossi.c @@ -598,7 +598,7 @@ static int sossi_init(struct omapfb_device *fbdev) l &= ~CONF_SOSSI_RESET_R; omap_writel(l, MOD_CONF_CTRL_1); - clk_enable(sossi.fck); + clk_prepare_enable(sossi.fck); l = omap_readl(ARM_IDLECT2); l &= ~(1 << 8); /* DMACK_REQ */ omap_writel(l, ARM_IDLECT2); @@ -649,7 +649,7 @@ static int sossi_init(struct omapfb_device *fbdev) return 0; err: - clk_disable(sossi.fck); + clk_disable_unprepare(sossi.fck); clk_put(sossi.fck); return r; } @@ -657,6 +657,7 @@ err: static void sossi_cleanup(void) { omap_lcdc_free_dma_callback(); + clk_unprepare(sossi.fck); clk_put(sossi.fck); iounmap(sossi.base); } diff --git a/drivers/video/fbdev/platinumfb.c b/drivers/video/fbdev/platinumfb.c index ce413a9df06e..5b9e26ea6449 100644 --- a/drivers/video/fbdev/platinumfb.c +++ b/drivers/video/fbdev/platinumfb.c @@ -30,9 +30,9 @@ #include <linux/fb.h> #include <linux/init.h> #include <linux/nvram.h> +#include <linux/of_address.h> #include <linux/of_device.h> #include <linux/of_platform.h> -#include <asm/prom.h> #include "macmodes.h" #include "platinumfb.h" diff --git a/drivers/video/fbdev/pm2fb.c b/drivers/video/fbdev/pm2fb.c index c68725eebee3..d3be2c64f1c0 100644 --- a/drivers/video/fbdev/pm2fb.c +++ b/drivers/video/fbdev/pm2fb.c @@ -1504,9 +1504,7 @@ static const struct fb_ops pm2fb_ops = { /** - * Device initialisation - * - * Initialise and allocate resource for PCI device. + * pm2fb_probe - Initialise and allocate resource for PCI device. * * @pdev: PCI device. * @id: PCI device ID. @@ -1711,9 +1709,7 @@ static int pm2fb_probe(struct pci_dev *pdev, const struct pci_device_id *id) } /** - * Device removal. - * - * Release all device resources. + * pm2fb_remove - Release all device resources. * * @pdev: PCI device to clean up. */ diff --git a/drivers/video/fbdev/pxafb.c b/drivers/video/fbdev/pxafb.c index f1551e00eb12..8ad91c251fe6 100644 --- a/drivers/video/fbdev/pxafb.c +++ b/drivers/video/fbdev/pxafb.c @@ -2256,10 +2256,10 @@ static int pxafb_probe(struct platform_device *dev) goto failed; for (i = 0; i < inf->num_modes; i++) inf->modes[i] = pdata->modes[i]; + } else { + inf = of_pxafb_of_mach_info(&dev->dev); } - if (!pdata) - inf = of_pxafb_of_mach_info(&dev->dev); if (IS_ERR_OR_NULL(inf)) goto failed; diff --git a/drivers/video/fbdev/s3fb.c b/drivers/video/fbdev/s3fb.c index 5c74253e7b2c..b93c8eb02336 100644 --- a/drivers/video/fbdev/s3fb.c +++ b/drivers/video/fbdev/s3fb.c @@ -549,6 +549,9 @@ static int s3fb_check_var(struct fb_var_screeninfo *var, struct fb_info *info) int rv, mem, step; u16 m, n, r; + if (!var->pixclock) + return -EINVAL; + /* Find appropriate format */ rv = svga_match_format (s3fb_formats, var, NULL); diff --git a/drivers/video/fbdev/sh_mobile_lcdcfb.c b/drivers/video/fbdev/sh_mobile_lcdcfb.c index aa4ebe3192ec..9a4417430b4e 100644 --- a/drivers/video/fbdev/sh_mobile_lcdcfb.c +++ b/drivers/video/fbdev/sh_mobile_lcdcfb.c @@ -531,9 +531,6 @@ static void sh_mobile_lcdc_display_off(struct sh_mobile_lcdc_chan *ch) ch->tx_dev->ops->display_off(ch->tx_dev); } -static int sh_mobile_lcdc_check_var(struct fb_var_screeninfo *var, - struct fb_info *info); - /* ----------------------------------------------------------------------------- * Format helpers */ diff --git a/drivers/video/fbdev/simplefb.c b/drivers/video/fbdev/simplefb.c index 94fc9c6d0411..2c198561c338 100644 --- a/drivers/video/fbdev/simplefb.c +++ b/drivers/video/fbdev/simplefb.c @@ -84,6 +84,10 @@ struct simplefb_par { static void simplefb_clocks_destroy(struct simplefb_par *par); static void simplefb_regulators_destroy(struct simplefb_par *par); +/* + * fb_ops.fb_destroy is called by the last put_fb_info() call at the end + * of unregister_framebuffer() or fb_release(). Do any cleanup here. + */ static void simplefb_destroy(struct fb_info *info) { struct simplefb_par *par = info->par; @@ -94,6 +98,8 @@ static void simplefb_destroy(struct fb_info *info) if (info->screen_base) iounmap(info->screen_base); + framebuffer_release(info); + if (mem) release_mem_region(mem->start, resource_size(mem)); } @@ -545,8 +551,8 @@ static int simplefb_remove(struct platform_device *pdev) { struct fb_info *info = platform_get_drvdata(pdev); + /* simplefb_destroy takes care of info cleanup */ unregister_framebuffer(info); - framebuffer_release(info); return 0; } diff --git a/drivers/video/fbdev/sis/sis_main.c b/drivers/video/fbdev/sis/sis_main.c index 742f62986b80..f28fd69d5eb7 100644 --- a/drivers/video/fbdev/sis/sis_main.c +++ b/drivers/video/fbdev/sis/sis_main.c @@ -4463,7 +4463,7 @@ static void sisfb_post_sis300(struct pci_dev *pdev) SiS_SetReg(SISCR, 0x37, 0x02); SiS_SetReg(SISPART2, 0x00, 0x1c); v4 = 0x00; v5 = 0x00; v6 = 0x10; - if(ivideo->SiS_Pr.UseROM) { + if (ivideo->SiS_Pr.UseROM && bios) { v4 = bios[0xf5]; v5 = bios[0xf6]; v6 = bios[0xf7]; diff --git a/drivers/video/fbdev/tridentfb.c b/drivers/video/fbdev/tridentfb.c index 4d20cb557ff0..319131bd72cf 100644 --- a/drivers/video/fbdev/tridentfb.c +++ b/drivers/video/fbdev/tridentfb.c @@ -996,6 +996,9 @@ static int tridentfb_check_var(struct fb_var_screeninfo *var, int ramdac = 230000; /* 230MHz for most 3D chips */ debug("enter\n"); + if (!var->pixclock) + return -EINVAL; + /* check color depth */ if (bpp == 24) bpp = var->bits_per_pixel = 32; diff --git a/drivers/video/fbdev/udlfb.c b/drivers/video/fbdev/udlfb.c index b6ec0b8e2b72..d280733f283b 100644 --- a/drivers/video/fbdev/udlfb.c +++ b/drivers/video/fbdev/udlfb.c @@ -1650,8 +1650,9 @@ static int dlfb_usb_probe(struct usb_interface *intf, const struct device_attribute *attr; struct dlfb_data *dlfb; struct fb_info *info; - int retval = -ENOMEM; + int retval; struct usb_device *usbdev = interface_to_usbdev(intf); + struct usb_endpoint_descriptor *out; /* usb initialization */ dlfb = kzalloc(sizeof(*dlfb), GFP_KERNEL); @@ -1665,6 +1666,12 @@ static int dlfb_usb_probe(struct usb_interface *intf, dlfb->udev = usb_get_dev(usbdev); usb_set_intfdata(intf, dlfb); + retval = usb_find_common_endpoints(intf->cur_altsetting, NULL, &out, NULL, NULL); + if (retval) { + dev_err(&intf->dev, "Device should have at lease 1 bulk endpoint!\n"); + goto error; + } + dev_dbg(&intf->dev, "console enable=%d\n", console); dev_dbg(&intf->dev, "fb_defio enable=%d\n", fb_defio); dev_dbg(&intf->dev, "shadow enable=%d\n", shadow); @@ -1674,6 +1681,7 @@ static int dlfb_usb_probe(struct usb_interface *intf, if (!dlfb_parse_vendor_descriptor(dlfb, intf)) { dev_err(&intf->dev, "firmware not recognized, incompatible device?\n"); + retval = -ENODEV; goto error; } @@ -1687,8 +1695,10 @@ static int dlfb_usb_probe(struct usb_interface *intf, /* allocates framebuffer driver structure, not framebuffer memory */ info = framebuffer_alloc(0, &dlfb->udev->dev); - if (!info) + if (!info) { + retval = -ENOMEM; goto error; + } dlfb->info = info; info->par = dlfb; diff --git a/drivers/video/fbdev/valkyriefb.c b/drivers/video/fbdev/valkyriefb.c index 8425afe37d7c..a6c9d4f26669 100644 --- a/drivers/video/fbdev/valkyriefb.c +++ b/drivers/video/fbdev/valkyriefb.c @@ -54,10 +54,9 @@ #include <linux/nvram.h> #include <linux/adb.h> #include <linux/cuda.h> +#include <linux/of_address.h> #ifdef CONFIG_MAC #include <asm/macintosh.h> -#else -#include <asm/prom.h> #endif #include "macmodes.h" diff --git a/drivers/video/fbdev/vesafb.c b/drivers/video/fbdev/vesafb.c index df6de5a9dd4c..e25e8de5ff67 100644 --- a/drivers/video/fbdev/vesafb.c +++ b/drivers/video/fbdev/vesafb.c @@ -179,6 +179,10 @@ static int vesafb_setcolreg(unsigned regno, unsigned red, unsigned green, return err; } +/* + * fb_ops.fb_destroy is called by the last put_fb_info() call at the end + * of unregister_framebuffer() or fb_release(). Do any cleanup here. + */ static void vesafb_destroy(struct fb_info *info) { struct vesafb_par *par = info->par; @@ -188,6 +192,8 @@ static void vesafb_destroy(struct fb_info *info) if (info->screen_base) iounmap(info->screen_base); release_mem_region(info->apertures->ranges[0].base, info->apertures->ranges[0].size); + + framebuffer_release(info); } static struct fb_ops vesafb_ops = { @@ -484,10 +490,10 @@ static int vesafb_remove(struct platform_device *pdev) { struct fb_info *info = platform_get_drvdata(pdev); + /* vesafb_destroy takes care of info cleanup */ unregister_framebuffer(info); if (((struct vesafb_par *)(info->par))->region) release_region(0x3c0, 32); - framebuffer_release(info); return 0; } diff --git a/drivers/video/fbdev/vt8623fb.c b/drivers/video/fbdev/vt8623fb.c index 7a959e5ba90b..a92a8c670cf0 100644 --- a/drivers/video/fbdev/vt8623fb.c +++ b/drivers/video/fbdev/vt8623fb.c @@ -321,6 +321,9 @@ static int vt8623fb_check_var(struct fb_var_screeninfo *var, struct fb_info *inf { int rv, mem, step; + if (!var->pixclock) + return -EINVAL; + /* Find appropriate format */ rv = svga_match_format (vt8623fb_formats, var, NULL); if (rv < 0) diff --git a/drivers/video/of_display_timing.c b/drivers/video/of_display_timing.c index f93b6abbe258..bebd371c6b93 100644 --- a/drivers/video/of_display_timing.c +++ b/drivers/video/of_display_timing.c @@ -199,7 +199,7 @@ struct display_timings *of_get_display_timings(const struct device_node *np) struct display_timing *dt; int r; - dt = kzalloc(sizeof(*dt), GFP_KERNEL); + dt = kmalloc(sizeof(*dt), GFP_KERNEL); if (!dt) { pr_err("%pOF: could not allocate display_timing struct\n", np); diff --git a/drivers/virt/Kconfig b/drivers/virt/Kconfig index 121b9293c737..87ef258cec64 100644 --- a/drivers/virt/Kconfig +++ b/drivers/virt/Kconfig @@ -47,4 +47,9 @@ source "drivers/virt/vboxguest/Kconfig" source "drivers/virt/nitro_enclaves/Kconfig" source "drivers/virt/acrn/Kconfig" + +source "drivers/virt/coco/efi_secret/Kconfig" + +source "drivers/virt/coco/sev-guest/Kconfig" + endif diff --git a/drivers/virt/Makefile b/drivers/virt/Makefile index 108d0ffcc9aa..093674e05c40 100644 --- a/drivers/virt/Makefile +++ b/drivers/virt/Makefile @@ -9,3 +9,5 @@ obj-y += vboxguest/ obj-$(CONFIG_NITRO_ENCLAVES) += nitro_enclaves/ obj-$(CONFIG_ACRN_HSM) += acrn/ +obj-$(CONFIG_EFI_SECRET) += coco/efi_secret/ +obj-$(CONFIG_SEV_GUEST) += coco/sev-guest/ diff --git a/drivers/virt/coco/efi_secret/Kconfig b/drivers/virt/coco/efi_secret/Kconfig new file mode 100644 index 000000000000..4404d198f3b2 --- /dev/null +++ b/drivers/virt/coco/efi_secret/Kconfig @@ -0,0 +1,16 @@ +# SPDX-License-Identifier: GPL-2.0-only +config EFI_SECRET + tristate "EFI secret area securityfs support" + depends on EFI && X86_64 + select EFI_COCO_SECRET + select SECURITYFS + help + This is a driver for accessing the EFI secret area via securityfs. + The EFI secret area is a memory area designated by the firmware for + confidential computing secret injection (for example for AMD SEV + guests). The driver exposes the secrets as files in + <securityfs>/secrets/coco. Files can be read and deleted (deleting + a file wipes the secret from memory). + + To compile this driver as a module, choose M here. + The module will be called efi_secret. diff --git a/drivers/virt/coco/efi_secret/Makefile b/drivers/virt/coco/efi_secret/Makefile new file mode 100644 index 000000000000..c7047ce804f7 --- /dev/null +++ b/drivers/virt/coco/efi_secret/Makefile @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only +obj-$(CONFIG_EFI_SECRET) += efi_secret.o diff --git a/drivers/virt/coco/efi_secret/efi_secret.c b/drivers/virt/coco/efi_secret/efi_secret.c new file mode 100644 index 000000000000..e700a5ef7043 --- /dev/null +++ b/drivers/virt/coco/efi_secret/efi_secret.c @@ -0,0 +1,349 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * efi_secret module + * + * Copyright (C) 2022 IBM Corporation + * Author: Dov Murik <dovmurik@linux.ibm.com> + */ + +/** + * DOC: efi_secret: Allow reading EFI confidential computing (coco) secret area + * via securityfs interface. + * + * When the module is loaded (and securityfs is mounted, typically under + * /sys/kernel/security), a "secrets/coco" directory is created in securityfs. + * In it, a file is created for each secret entry. The name of each such file + * is the GUID of the secret entry, and its content is the secret data. + */ + +#include <linux/platform_device.h> +#include <linux/seq_file.h> +#include <linux/fs.h> +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/io.h> +#include <linux/security.h> +#include <linux/efi.h> +#include <linux/cacheflush.h> + +#define EFI_SECRET_NUM_FILES 64 + +struct efi_secret { + struct dentry *secrets_dir; + struct dentry *fs_dir; + struct dentry *fs_files[EFI_SECRET_NUM_FILES]; + void __iomem *secret_data; + u64 secret_data_len; +}; + +/* + * Structure of the EFI secret area + * + * Offset Length + * (bytes) (bytes) Usage + * ------- ------- ----- + * 0 16 Secret table header GUID (must be 1e74f542-71dd-4d66-963e-ef4287ff173b) + * 16 4 Length of bytes of the entire secret area + * + * 20 16 First secret entry's GUID + * 36 4 First secret entry's length in bytes (= 16 + 4 + x) + * 40 x First secret entry's data + * + * 40+x 16 Second secret entry's GUID + * 56+x 4 Second secret entry's length in bytes (= 16 + 4 + y) + * 60+x y Second secret entry's data + * + * (... and so on for additional entries) + * + * The GUID of each secret entry designates the usage of the secret data. + */ + +/** + * struct secret_header - Header of entire secret area; this should be followed + * by instances of struct secret_entry. + * @guid: Must be EFI_SECRET_TABLE_HEADER_GUID + * @len: Length in bytes of entire secret area, including header + */ +struct secret_header { + efi_guid_t guid; + u32 len; +} __attribute((packed)); + +/** + * struct secret_entry - Holds one secret entry + * @guid: Secret-specific GUID (or NULL_GUID if this secret entry was deleted) + * @len: Length of secret entry, including its guid and len fields + * @data: The secret data (full of zeros if this secret entry was deleted) + */ +struct secret_entry { + efi_guid_t guid; + u32 len; + u8 data[]; +} __attribute((packed)); + +static size_t secret_entry_data_len(struct secret_entry *e) +{ + return e->len - sizeof(*e); +} + +static struct efi_secret the_efi_secret; + +static inline struct efi_secret *efi_secret_get(void) +{ + return &the_efi_secret; +} + +static int efi_secret_bin_file_show(struct seq_file *file, void *data) +{ + struct secret_entry *e = file->private; + + if (e) + seq_write(file, e->data, secret_entry_data_len(e)); + + return 0; +} +DEFINE_SHOW_ATTRIBUTE(efi_secret_bin_file); + +/* + * Overwrite memory content with zeroes, and ensure that dirty cache lines are + * actually written back to memory, to clear out the secret. + */ +static void wipe_memory(void *addr, size_t size) +{ + memzero_explicit(addr, size); +#ifdef CONFIG_X86 + clflush_cache_range(addr, size); +#endif +} + +static int efi_secret_unlink(struct inode *dir, struct dentry *dentry) +{ + struct efi_secret *s = efi_secret_get(); + struct inode *inode = d_inode(dentry); + struct secret_entry *e = (struct secret_entry *)inode->i_private; + int i; + + if (e) { + /* Zero out the secret data */ + wipe_memory(e->data, secret_entry_data_len(e)); + e->guid = NULL_GUID; + } + + inode->i_private = NULL; + + for (i = 0; i < EFI_SECRET_NUM_FILES; i++) + if (s->fs_files[i] == dentry) + s->fs_files[i] = NULL; + + /* + * securityfs_remove tries to lock the directory's inode, but we reach + * the unlink callback when it's already locked + */ + inode_unlock(dir); + securityfs_remove(dentry); + inode_lock(dir); + + return 0; +} + +static const struct inode_operations efi_secret_dir_inode_operations = { + .lookup = simple_lookup, + .unlink = efi_secret_unlink, +}; + +static int efi_secret_map_area(struct platform_device *dev) +{ + int ret; + struct efi_secret *s = efi_secret_get(); + struct linux_efi_coco_secret_area *secret_area; + + if (efi.coco_secret == EFI_INVALID_TABLE_ADDR) { + dev_err(&dev->dev, "Secret area address is not available\n"); + return -EINVAL; + } + + secret_area = memremap(efi.coco_secret, sizeof(*secret_area), MEMREMAP_WB); + if (secret_area == NULL) { + dev_err(&dev->dev, "Could not map secret area EFI config entry\n"); + return -ENOMEM; + } + if (!secret_area->base_pa || secret_area->size < sizeof(struct secret_header)) { + dev_err(&dev->dev, + "Invalid secret area memory location (base_pa=0x%llx size=0x%llx)\n", + secret_area->base_pa, secret_area->size); + ret = -EINVAL; + goto unmap; + } + + s->secret_data = ioremap_encrypted(secret_area->base_pa, secret_area->size); + if (s->secret_data == NULL) { + dev_err(&dev->dev, "Could not map secret area\n"); + ret = -ENOMEM; + goto unmap; + } + + s->secret_data_len = secret_area->size; + ret = 0; + +unmap: + memunmap(secret_area); + return ret; +} + +static void efi_secret_securityfs_teardown(struct platform_device *dev) +{ + struct efi_secret *s = efi_secret_get(); + int i; + + for (i = (EFI_SECRET_NUM_FILES - 1); i >= 0; i--) { + securityfs_remove(s->fs_files[i]); + s->fs_files[i] = NULL; + } + + securityfs_remove(s->fs_dir); + s->fs_dir = NULL; + + securityfs_remove(s->secrets_dir); + s->secrets_dir = NULL; + + dev_dbg(&dev->dev, "Removed securityfs entries\n"); +} + +static int efi_secret_securityfs_setup(struct platform_device *dev) +{ + struct efi_secret *s = efi_secret_get(); + int ret = 0, i = 0, bytes_left; + unsigned char *ptr; + struct secret_header *h; + struct secret_entry *e; + struct dentry *dent; + char guid_str[EFI_VARIABLE_GUID_LEN + 1]; + + ptr = (void __force *)s->secret_data; + h = (struct secret_header *)ptr; + if (efi_guidcmp(h->guid, EFI_SECRET_TABLE_HEADER_GUID)) { + /* + * This is not an error: it just means that EFI defines secret + * area but it was not populated by the Guest Owner. + */ + dev_dbg(&dev->dev, "EFI secret area does not start with correct GUID\n"); + return -ENODEV; + } + if (h->len < sizeof(*h)) { + dev_err(&dev->dev, "EFI secret area reported length is too small\n"); + return -EINVAL; + } + if (h->len > s->secret_data_len) { + dev_err(&dev->dev, "EFI secret area reported length is too big\n"); + return -EINVAL; + } + + s->secrets_dir = NULL; + s->fs_dir = NULL; + memset(s->fs_files, 0, sizeof(s->fs_files)); + + dent = securityfs_create_dir("secrets", NULL); + if (IS_ERR(dent)) { + dev_err(&dev->dev, "Error creating secrets securityfs directory entry err=%ld\n", + PTR_ERR(dent)); + return PTR_ERR(dent); + } + s->secrets_dir = dent; + + dent = securityfs_create_dir("coco", s->secrets_dir); + if (IS_ERR(dent)) { + dev_err(&dev->dev, "Error creating coco securityfs directory entry err=%ld\n", + PTR_ERR(dent)); + return PTR_ERR(dent); + } + d_inode(dent)->i_op = &efi_secret_dir_inode_operations; + s->fs_dir = dent; + + bytes_left = h->len - sizeof(*h); + ptr += sizeof(*h); + while (bytes_left >= (int)sizeof(*e) && i < EFI_SECRET_NUM_FILES) { + e = (struct secret_entry *)ptr; + if (e->len < sizeof(*e) || e->len > (unsigned int)bytes_left) { + dev_err(&dev->dev, "EFI secret area is corrupted\n"); + ret = -EINVAL; + goto err_cleanup; + } + + /* Skip deleted entries (which will have NULL_GUID) */ + if (efi_guidcmp(e->guid, NULL_GUID)) { + efi_guid_to_str(&e->guid, guid_str); + + dent = securityfs_create_file(guid_str, 0440, s->fs_dir, (void *)e, + &efi_secret_bin_file_fops); + if (IS_ERR(dent)) { + dev_err(&dev->dev, "Error creating efi_secret securityfs entry\n"); + ret = PTR_ERR(dent); + goto err_cleanup; + } + + s->fs_files[i++] = dent; + } + ptr += e->len; + bytes_left -= e->len; + } + + dev_info(&dev->dev, "Created %d entries in securityfs secrets/coco\n", i); + return 0; + +err_cleanup: + efi_secret_securityfs_teardown(dev); + return ret; +} + +static void efi_secret_unmap_area(void) +{ + struct efi_secret *s = efi_secret_get(); + + if (s->secret_data) { + iounmap(s->secret_data); + s->secret_data = NULL; + s->secret_data_len = 0; + } +} + +static int efi_secret_probe(struct platform_device *dev) +{ + int ret; + + ret = efi_secret_map_area(dev); + if (ret) + return ret; + + ret = efi_secret_securityfs_setup(dev); + if (ret) + goto err_unmap; + + return ret; + +err_unmap: + efi_secret_unmap_area(); + return ret; +} + +static int efi_secret_remove(struct platform_device *dev) +{ + efi_secret_securityfs_teardown(dev); + efi_secret_unmap_area(); + return 0; +} + +static struct platform_driver efi_secret_driver = { + .probe = efi_secret_probe, + .remove = efi_secret_remove, + .driver = { + .name = "efi_secret", + }, +}; + +module_platform_driver(efi_secret_driver); + +MODULE_DESCRIPTION("Confidential computing EFI secret area access"); +MODULE_AUTHOR("IBM"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("platform:efi_secret"); diff --git a/drivers/virt/coco/sev-guest/Kconfig b/drivers/virt/coco/sev-guest/Kconfig new file mode 100644 index 000000000000..f9db0799ae67 --- /dev/null +++ b/drivers/virt/coco/sev-guest/Kconfig @@ -0,0 +1,14 @@ +config SEV_GUEST + tristate "AMD SEV Guest driver" + default m + depends on AMD_MEM_ENCRYPT + select CRYPTO_AEAD2 + select CRYPTO_GCM + help + SEV-SNP firmware provides the guest a mechanism to communicate with + the PSP without risk from a malicious hypervisor who wishes to read, + alter, drop or replay the messages sent. The driver provides + userspace interface to communicate with the PSP to request the + attestation report and more. + + If you choose 'M' here, this module will be called sev-guest. diff --git a/arch/s390/boot/compressed/.gitignore b/drivers/virt/coco/sev-guest/Makefile index 01d93832cf4a..63d67c27723a 100644 --- a/arch/s390/boot/compressed/.gitignore +++ b/drivers/virt/coco/sev-guest/Makefile @@ -1,4 +1,2 @@ # SPDX-License-Identifier: GPL-2.0-only -vmlinux -vmlinux.lds -vmlinux.syms +obj-$(CONFIG_SEV_GUEST) += sev-guest.o diff --git a/drivers/virt/coco/sev-guest/sev-guest.c b/drivers/virt/coco/sev-guest/sev-guest.c new file mode 100644 index 000000000000..90ce16b6e05f --- /dev/null +++ b/drivers/virt/coco/sev-guest/sev-guest.c @@ -0,0 +1,743 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * AMD Secure Encrypted Virtualization (SEV) guest driver interface + * + * Copyright (C) 2021 Advanced Micro Devices, Inc. + * + * Author: Brijesh Singh <brijesh.singh@amd.com> + */ + +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/types.h> +#include <linux/mutex.h> +#include <linux/io.h> +#include <linux/platform_device.h> +#include <linux/miscdevice.h> +#include <linux/set_memory.h> +#include <linux/fs.h> +#include <crypto/aead.h> +#include <linux/scatterlist.h> +#include <linux/psp-sev.h> +#include <uapi/linux/sev-guest.h> +#include <uapi/linux/psp-sev.h> + +#include <asm/svm.h> +#include <asm/sev.h> + +#include "sev-guest.h" + +#define DEVICE_NAME "sev-guest" +#define AAD_LEN 48 +#define MSG_HDR_VER 1 + +struct snp_guest_crypto { + struct crypto_aead *tfm; + u8 *iv, *authtag; + int iv_len, a_len; +}; + +struct snp_guest_dev { + struct device *dev; + struct miscdevice misc; + + void *certs_data; + struct snp_guest_crypto *crypto; + struct snp_guest_msg *request, *response; + struct snp_secrets_page_layout *layout; + struct snp_req_data input; + u32 *os_area_msg_seqno; + u8 *vmpck; +}; + +static u32 vmpck_id; +module_param(vmpck_id, uint, 0444); +MODULE_PARM_DESC(vmpck_id, "The VMPCK ID to use when communicating with the PSP."); + +/* Mutex to serialize the shared buffer access and command handling. */ +static DEFINE_MUTEX(snp_cmd_mutex); + +static bool is_vmpck_empty(struct snp_guest_dev *snp_dev) +{ + char zero_key[VMPCK_KEY_LEN] = {0}; + + if (snp_dev->vmpck) + return !memcmp(snp_dev->vmpck, zero_key, VMPCK_KEY_LEN); + + return true; +} + +static void snp_disable_vmpck(struct snp_guest_dev *snp_dev) +{ + memzero_explicit(snp_dev->vmpck, VMPCK_KEY_LEN); + snp_dev->vmpck = NULL; +} + +static inline u64 __snp_get_msg_seqno(struct snp_guest_dev *snp_dev) +{ + u64 count; + + lockdep_assert_held(&snp_cmd_mutex); + + /* Read the current message sequence counter from secrets pages */ + count = *snp_dev->os_area_msg_seqno; + + return count + 1; +} + +/* Return a non-zero on success */ +static u64 snp_get_msg_seqno(struct snp_guest_dev *snp_dev) +{ + u64 count = __snp_get_msg_seqno(snp_dev); + + /* + * The message sequence counter for the SNP guest request is a 64-bit + * value but the version 2 of GHCB specification defines a 32-bit storage + * for it. If the counter exceeds the 32-bit value then return zero. + * The caller should check the return value, but if the caller happens to + * not check the value and use it, then the firmware treats zero as an + * invalid number and will fail the message request. + */ + if (count >= UINT_MAX) { + dev_err(snp_dev->dev, "request message sequence counter overflow\n"); + return 0; + } + + return count; +} + +static void snp_inc_msg_seqno(struct snp_guest_dev *snp_dev) +{ + /* + * The counter is also incremented by the PSP, so increment it by 2 + * and save in secrets page. + */ + *snp_dev->os_area_msg_seqno += 2; +} + +static inline struct snp_guest_dev *to_snp_dev(struct file *file) +{ + struct miscdevice *dev = file->private_data; + + return container_of(dev, struct snp_guest_dev, misc); +} + +static struct snp_guest_crypto *init_crypto(struct snp_guest_dev *snp_dev, u8 *key, size_t keylen) +{ + struct snp_guest_crypto *crypto; + + crypto = kzalloc(sizeof(*crypto), GFP_KERNEL_ACCOUNT); + if (!crypto) + return NULL; + + crypto->tfm = crypto_alloc_aead("gcm(aes)", 0, 0); + if (IS_ERR(crypto->tfm)) + goto e_free; + + if (crypto_aead_setkey(crypto->tfm, key, keylen)) + goto e_free_crypto; + + crypto->iv_len = crypto_aead_ivsize(crypto->tfm); + crypto->iv = kmalloc(crypto->iv_len, GFP_KERNEL_ACCOUNT); + if (!crypto->iv) + goto e_free_crypto; + + if (crypto_aead_authsize(crypto->tfm) > MAX_AUTHTAG_LEN) { + if (crypto_aead_setauthsize(crypto->tfm, MAX_AUTHTAG_LEN)) { + dev_err(snp_dev->dev, "failed to set authsize to %d\n", MAX_AUTHTAG_LEN); + goto e_free_iv; + } + } + + crypto->a_len = crypto_aead_authsize(crypto->tfm); + crypto->authtag = kmalloc(crypto->a_len, GFP_KERNEL_ACCOUNT); + if (!crypto->authtag) + goto e_free_auth; + + return crypto; + +e_free_auth: + kfree(crypto->authtag); +e_free_iv: + kfree(crypto->iv); +e_free_crypto: + crypto_free_aead(crypto->tfm); +e_free: + kfree(crypto); + + return NULL; +} + +static void deinit_crypto(struct snp_guest_crypto *crypto) +{ + crypto_free_aead(crypto->tfm); + kfree(crypto->iv); + kfree(crypto->authtag); + kfree(crypto); +} + +static int enc_dec_message(struct snp_guest_crypto *crypto, struct snp_guest_msg *msg, + u8 *src_buf, u8 *dst_buf, size_t len, bool enc) +{ + struct snp_guest_msg_hdr *hdr = &msg->hdr; + struct scatterlist src[3], dst[3]; + DECLARE_CRYPTO_WAIT(wait); + struct aead_request *req; + int ret; + + req = aead_request_alloc(crypto->tfm, GFP_KERNEL); + if (!req) + return -ENOMEM; + + /* + * AEAD memory operations: + * +------ AAD -------+------- DATA -----+---- AUTHTAG----+ + * | msg header | plaintext | hdr->authtag | + * | bytes 30h - 5Fh | or | | + * | | cipher | | + * +------------------+------------------+----------------+ + */ + sg_init_table(src, 3); + sg_set_buf(&src[0], &hdr->algo, AAD_LEN); + sg_set_buf(&src[1], src_buf, hdr->msg_sz); + sg_set_buf(&src[2], hdr->authtag, crypto->a_len); + + sg_init_table(dst, 3); + sg_set_buf(&dst[0], &hdr->algo, AAD_LEN); + sg_set_buf(&dst[1], dst_buf, hdr->msg_sz); + sg_set_buf(&dst[2], hdr->authtag, crypto->a_len); + + aead_request_set_ad(req, AAD_LEN); + aead_request_set_tfm(req, crypto->tfm); + aead_request_set_callback(req, 0, crypto_req_done, &wait); + + aead_request_set_crypt(req, src, dst, len, crypto->iv); + ret = crypto_wait_req(enc ? crypto_aead_encrypt(req) : crypto_aead_decrypt(req), &wait); + + aead_request_free(req); + return ret; +} + +static int __enc_payload(struct snp_guest_dev *snp_dev, struct snp_guest_msg *msg, + void *plaintext, size_t len) +{ + struct snp_guest_crypto *crypto = snp_dev->crypto; + struct snp_guest_msg_hdr *hdr = &msg->hdr; + + memset(crypto->iv, 0, crypto->iv_len); + memcpy(crypto->iv, &hdr->msg_seqno, sizeof(hdr->msg_seqno)); + + return enc_dec_message(crypto, msg, plaintext, msg->payload, len, true); +} + +static int dec_payload(struct snp_guest_dev *snp_dev, struct snp_guest_msg *msg, + void *plaintext, size_t len) +{ + struct snp_guest_crypto *crypto = snp_dev->crypto; + struct snp_guest_msg_hdr *hdr = &msg->hdr; + + /* Build IV with response buffer sequence number */ + memset(crypto->iv, 0, crypto->iv_len); + memcpy(crypto->iv, &hdr->msg_seqno, sizeof(hdr->msg_seqno)); + + return enc_dec_message(crypto, msg, msg->payload, plaintext, len, false); +} + +static int verify_and_dec_payload(struct snp_guest_dev *snp_dev, void *payload, u32 sz) +{ + struct snp_guest_crypto *crypto = snp_dev->crypto; + struct snp_guest_msg *resp = snp_dev->response; + struct snp_guest_msg *req = snp_dev->request; + struct snp_guest_msg_hdr *req_hdr = &req->hdr; + struct snp_guest_msg_hdr *resp_hdr = &resp->hdr; + + dev_dbg(snp_dev->dev, "response [seqno %lld type %d version %d sz %d]\n", + resp_hdr->msg_seqno, resp_hdr->msg_type, resp_hdr->msg_version, resp_hdr->msg_sz); + + /* Verify that the sequence counter is incremented by 1 */ + if (unlikely(resp_hdr->msg_seqno != (req_hdr->msg_seqno + 1))) + return -EBADMSG; + + /* Verify response message type and version number. */ + if (resp_hdr->msg_type != (req_hdr->msg_type + 1) || + resp_hdr->msg_version != req_hdr->msg_version) + return -EBADMSG; + + /* + * If the message size is greater than our buffer length then return + * an error. + */ + if (unlikely((resp_hdr->msg_sz + crypto->a_len) > sz)) + return -EBADMSG; + + /* Decrypt the payload */ + return dec_payload(snp_dev, resp, payload, resp_hdr->msg_sz + crypto->a_len); +} + +static int enc_payload(struct snp_guest_dev *snp_dev, u64 seqno, int version, u8 type, + void *payload, size_t sz) +{ + struct snp_guest_msg *req = snp_dev->request; + struct snp_guest_msg_hdr *hdr = &req->hdr; + + memset(req, 0, sizeof(*req)); + + hdr->algo = SNP_AEAD_AES_256_GCM; + hdr->hdr_version = MSG_HDR_VER; + hdr->hdr_sz = sizeof(*hdr); + hdr->msg_type = type; + hdr->msg_version = version; + hdr->msg_seqno = seqno; + hdr->msg_vmpck = vmpck_id; + hdr->msg_sz = sz; + + /* Verify the sequence number is non-zero */ + if (!hdr->msg_seqno) + return -ENOSR; + + dev_dbg(snp_dev->dev, "request [seqno %lld type %d version %d sz %d]\n", + hdr->msg_seqno, hdr->msg_type, hdr->msg_version, hdr->msg_sz); + + return __enc_payload(snp_dev, req, payload, sz); +} + +static int handle_guest_request(struct snp_guest_dev *snp_dev, u64 exit_code, int msg_ver, + u8 type, void *req_buf, size_t req_sz, void *resp_buf, + u32 resp_sz, __u64 *fw_err) +{ + unsigned long err; + u64 seqno; + int rc; + + /* Get message sequence and verify that its a non-zero */ + seqno = snp_get_msg_seqno(snp_dev); + if (!seqno) + return -EIO; + + memset(snp_dev->response, 0, sizeof(struct snp_guest_msg)); + + /* Encrypt the userspace provided payload */ + rc = enc_payload(snp_dev, seqno, msg_ver, type, req_buf, req_sz); + if (rc) + return rc; + + /* Call firmware to process the request */ + rc = snp_issue_guest_request(exit_code, &snp_dev->input, &err); + if (fw_err) + *fw_err = err; + + if (rc) + return rc; + + /* + * The verify_and_dec_payload() will fail only if the hypervisor is + * actively modifying the message header or corrupting the encrypted payload. + * This hints that hypervisor is acting in a bad faith. Disable the VMPCK so that + * the key cannot be used for any communication. The key is disabled to ensure + * that AES-GCM does not use the same IV while encrypting the request payload. + */ + rc = verify_and_dec_payload(snp_dev, resp_buf, resp_sz); + if (rc) { + dev_alert(snp_dev->dev, + "Detected unexpected decode failure, disabling the vmpck_id %d\n", + vmpck_id); + snp_disable_vmpck(snp_dev); + return rc; + } + + /* Increment to new message sequence after payload decryption was successful. */ + snp_inc_msg_seqno(snp_dev); + + return 0; +} + +static int get_report(struct snp_guest_dev *snp_dev, struct snp_guest_request_ioctl *arg) +{ + struct snp_guest_crypto *crypto = snp_dev->crypto; + struct snp_report_resp *resp; + struct snp_report_req req; + int rc, resp_len; + + lockdep_assert_held(&snp_cmd_mutex); + + if (!arg->req_data || !arg->resp_data) + return -EINVAL; + + if (copy_from_user(&req, (void __user *)arg->req_data, sizeof(req))) + return -EFAULT; + + /* + * The intermediate response buffer is used while decrypting the + * response payload. Make sure that it has enough space to cover the + * authtag. + */ + resp_len = sizeof(resp->data) + crypto->a_len; + resp = kzalloc(resp_len, GFP_KERNEL_ACCOUNT); + if (!resp) + return -ENOMEM; + + rc = handle_guest_request(snp_dev, SVM_VMGEXIT_GUEST_REQUEST, arg->msg_version, + SNP_MSG_REPORT_REQ, &req, sizeof(req), resp->data, + resp_len, &arg->fw_err); + if (rc) + goto e_free; + + if (copy_to_user((void __user *)arg->resp_data, resp, sizeof(*resp))) + rc = -EFAULT; + +e_free: + kfree(resp); + return rc; +} + +static int get_derived_key(struct snp_guest_dev *snp_dev, struct snp_guest_request_ioctl *arg) +{ + struct snp_guest_crypto *crypto = snp_dev->crypto; + struct snp_derived_key_resp resp = {0}; + struct snp_derived_key_req req; + int rc, resp_len; + /* Response data is 64 bytes and max authsize for GCM is 16 bytes. */ + u8 buf[64 + 16]; + + lockdep_assert_held(&snp_cmd_mutex); + + if (!arg->req_data || !arg->resp_data) + return -EINVAL; + + /* + * The intermediate response buffer is used while decrypting the + * response payload. Make sure that it has enough space to cover the + * authtag. + */ + resp_len = sizeof(resp.data) + crypto->a_len; + if (sizeof(buf) < resp_len) + return -ENOMEM; + + if (copy_from_user(&req, (void __user *)arg->req_data, sizeof(req))) + return -EFAULT; + + rc = handle_guest_request(snp_dev, SVM_VMGEXIT_GUEST_REQUEST, arg->msg_version, + SNP_MSG_KEY_REQ, &req, sizeof(req), buf, resp_len, + &arg->fw_err); + if (rc) + return rc; + + memcpy(resp.data, buf, sizeof(resp.data)); + if (copy_to_user((void __user *)arg->resp_data, &resp, sizeof(resp))) + rc = -EFAULT; + + /* The response buffer contains the sensitive data, explicitly clear it. */ + memzero_explicit(buf, sizeof(buf)); + memzero_explicit(&resp, sizeof(resp)); + return rc; +} + +static int get_ext_report(struct snp_guest_dev *snp_dev, struct snp_guest_request_ioctl *arg) +{ + struct snp_guest_crypto *crypto = snp_dev->crypto; + struct snp_ext_report_req req; + struct snp_report_resp *resp; + int ret, npages = 0, resp_len; + + lockdep_assert_held(&snp_cmd_mutex); + + if (!arg->req_data || !arg->resp_data) + return -EINVAL; + + if (copy_from_user(&req, (void __user *)arg->req_data, sizeof(req))) + return -EFAULT; + + /* userspace does not want certificate data */ + if (!req.certs_len || !req.certs_address) + goto cmd; + + if (req.certs_len > SEV_FW_BLOB_MAX_SIZE || + !IS_ALIGNED(req.certs_len, PAGE_SIZE)) + return -EINVAL; + + if (!access_ok((const void __user *)req.certs_address, req.certs_len)) + return -EFAULT; + + /* + * Initialize the intermediate buffer with all zeros. This buffer + * is used in the guest request message to get the certs blob from + * the host. If host does not supply any certs in it, then copy + * zeros to indicate that certificate data was not provided. + */ + memset(snp_dev->certs_data, 0, req.certs_len); + npages = req.certs_len >> PAGE_SHIFT; +cmd: + /* + * The intermediate response buffer is used while decrypting the + * response payload. Make sure that it has enough space to cover the + * authtag. + */ + resp_len = sizeof(resp->data) + crypto->a_len; + resp = kzalloc(resp_len, GFP_KERNEL_ACCOUNT); + if (!resp) + return -ENOMEM; + + snp_dev->input.data_npages = npages; + ret = handle_guest_request(snp_dev, SVM_VMGEXIT_EXT_GUEST_REQUEST, arg->msg_version, + SNP_MSG_REPORT_REQ, &req.data, + sizeof(req.data), resp->data, resp_len, &arg->fw_err); + + /* If certs length is invalid then copy the returned length */ + if (arg->fw_err == SNP_GUEST_REQ_INVALID_LEN) { + req.certs_len = snp_dev->input.data_npages << PAGE_SHIFT; + + if (copy_to_user((void __user *)arg->req_data, &req, sizeof(req))) + ret = -EFAULT; + } + + if (ret) + goto e_free; + + if (npages && + copy_to_user((void __user *)req.certs_address, snp_dev->certs_data, + req.certs_len)) { + ret = -EFAULT; + goto e_free; + } + + if (copy_to_user((void __user *)arg->resp_data, resp, sizeof(*resp))) + ret = -EFAULT; + +e_free: + kfree(resp); + return ret; +} + +static long snp_guest_ioctl(struct file *file, unsigned int ioctl, unsigned long arg) +{ + struct snp_guest_dev *snp_dev = to_snp_dev(file); + void __user *argp = (void __user *)arg; + struct snp_guest_request_ioctl input; + int ret = -ENOTTY; + + if (copy_from_user(&input, argp, sizeof(input))) + return -EFAULT; + + input.fw_err = 0xff; + + /* Message version must be non-zero */ + if (!input.msg_version) + return -EINVAL; + + mutex_lock(&snp_cmd_mutex); + + /* Check if the VMPCK is not empty */ + if (is_vmpck_empty(snp_dev)) { + dev_err_ratelimited(snp_dev->dev, "VMPCK is disabled\n"); + mutex_unlock(&snp_cmd_mutex); + return -ENOTTY; + } + + switch (ioctl) { + case SNP_GET_REPORT: + ret = get_report(snp_dev, &input); + break; + case SNP_GET_DERIVED_KEY: + ret = get_derived_key(snp_dev, &input); + break; + case SNP_GET_EXT_REPORT: + ret = get_ext_report(snp_dev, &input); + break; + default: + break; + } + + mutex_unlock(&snp_cmd_mutex); + + if (input.fw_err && copy_to_user(argp, &input, sizeof(input))) + return -EFAULT; + + return ret; +} + +static void free_shared_pages(void *buf, size_t sz) +{ + unsigned int npages = PAGE_ALIGN(sz) >> PAGE_SHIFT; + int ret; + + if (!buf) + return; + + ret = set_memory_encrypted((unsigned long)buf, npages); + if (ret) { + WARN_ONCE(ret, "failed to restore encryption mask (leak it)\n"); + return; + } + + __free_pages(virt_to_page(buf), get_order(sz)); +} + +static void *alloc_shared_pages(struct device *dev, size_t sz) +{ + unsigned int npages = PAGE_ALIGN(sz) >> PAGE_SHIFT; + struct page *page; + int ret; + + page = alloc_pages(GFP_KERNEL_ACCOUNT, get_order(sz)); + if (!page) + return NULL; + + ret = set_memory_decrypted((unsigned long)page_address(page), npages); + if (ret) { + dev_err(dev, "failed to mark page shared, ret=%d\n", ret); + __free_pages(page, get_order(sz)); + return NULL; + } + + return page_address(page); +} + +static const struct file_operations snp_guest_fops = { + .owner = THIS_MODULE, + .unlocked_ioctl = snp_guest_ioctl, +}; + +static u8 *get_vmpck(int id, struct snp_secrets_page_layout *layout, u32 **seqno) +{ + u8 *key = NULL; + + switch (id) { + case 0: + *seqno = &layout->os_area.msg_seqno_0; + key = layout->vmpck0; + break; + case 1: + *seqno = &layout->os_area.msg_seqno_1; + key = layout->vmpck1; + break; + case 2: + *seqno = &layout->os_area.msg_seqno_2; + key = layout->vmpck2; + break; + case 3: + *seqno = &layout->os_area.msg_seqno_3; + key = layout->vmpck3; + break; + default: + break; + } + + return key; +} + +static int __init sev_guest_probe(struct platform_device *pdev) +{ + struct snp_secrets_page_layout *layout; + struct sev_guest_platform_data *data; + struct device *dev = &pdev->dev; + struct snp_guest_dev *snp_dev; + struct miscdevice *misc; + int ret; + + if (!dev->platform_data) + return -ENODEV; + + data = (struct sev_guest_platform_data *)dev->platform_data; + layout = (__force void *)ioremap_encrypted(data->secrets_gpa, PAGE_SIZE); + if (!layout) + return -ENODEV; + + ret = -ENOMEM; + snp_dev = devm_kzalloc(&pdev->dev, sizeof(struct snp_guest_dev), GFP_KERNEL); + if (!snp_dev) + goto e_unmap; + + ret = -EINVAL; + snp_dev->vmpck = get_vmpck(vmpck_id, layout, &snp_dev->os_area_msg_seqno); + if (!snp_dev->vmpck) { + dev_err(dev, "invalid vmpck id %d\n", vmpck_id); + goto e_unmap; + } + + /* Verify that VMPCK is not zero. */ + if (is_vmpck_empty(snp_dev)) { + dev_err(dev, "vmpck id %d is null\n", vmpck_id); + goto e_unmap; + } + + platform_set_drvdata(pdev, snp_dev); + snp_dev->dev = dev; + snp_dev->layout = layout; + + /* Allocate the shared page used for the request and response message. */ + snp_dev->request = alloc_shared_pages(dev, sizeof(struct snp_guest_msg)); + if (!snp_dev->request) + goto e_unmap; + + snp_dev->response = alloc_shared_pages(dev, sizeof(struct snp_guest_msg)); + if (!snp_dev->response) + goto e_free_request; + + snp_dev->certs_data = alloc_shared_pages(dev, SEV_FW_BLOB_MAX_SIZE); + if (!snp_dev->certs_data) + goto e_free_response; + + ret = -EIO; + snp_dev->crypto = init_crypto(snp_dev, snp_dev->vmpck, VMPCK_KEY_LEN); + if (!snp_dev->crypto) + goto e_free_cert_data; + + misc = &snp_dev->misc; + misc->minor = MISC_DYNAMIC_MINOR; + misc->name = DEVICE_NAME; + misc->fops = &snp_guest_fops; + + /* initial the input address for guest request */ + snp_dev->input.req_gpa = __pa(snp_dev->request); + snp_dev->input.resp_gpa = __pa(snp_dev->response); + snp_dev->input.data_gpa = __pa(snp_dev->certs_data); + + ret = misc_register(misc); + if (ret) + goto e_free_cert_data; + + dev_info(dev, "Initialized SEV guest driver (using vmpck_id %d)\n", vmpck_id); + return 0; + +e_free_cert_data: + free_shared_pages(snp_dev->certs_data, SEV_FW_BLOB_MAX_SIZE); +e_free_response: + free_shared_pages(snp_dev->response, sizeof(struct snp_guest_msg)); +e_free_request: + free_shared_pages(snp_dev->request, sizeof(struct snp_guest_msg)); +e_unmap: + iounmap(layout); + return ret; +} + +static int __exit sev_guest_remove(struct platform_device *pdev) +{ + struct snp_guest_dev *snp_dev = platform_get_drvdata(pdev); + + free_shared_pages(snp_dev->certs_data, SEV_FW_BLOB_MAX_SIZE); + free_shared_pages(snp_dev->response, sizeof(struct snp_guest_msg)); + free_shared_pages(snp_dev->request, sizeof(struct snp_guest_msg)); + deinit_crypto(snp_dev->crypto); + misc_deregister(&snp_dev->misc); + + return 0; +} + +/* + * This driver is meant to be a common SEV guest interface driver and to + * support any SEV guest API. As such, even though it has been introduced + * with the SEV-SNP support, it is named "sev-guest". + */ +static struct platform_driver sev_guest_driver = { + .remove = __exit_p(sev_guest_remove), + .driver = { + .name = "sev-guest", + }, +}; + +module_platform_driver_probe(sev_guest_driver, sev_guest_probe); + +MODULE_AUTHOR("Brijesh Singh <brijesh.singh@amd.com>"); +MODULE_LICENSE("GPL"); +MODULE_VERSION("1.0.0"); +MODULE_DESCRIPTION("AMD SEV Guest Driver"); diff --git a/drivers/virt/coco/sev-guest/sev-guest.h b/drivers/virt/coco/sev-guest/sev-guest.h new file mode 100644 index 000000000000..21bda26fdb95 --- /dev/null +++ b/drivers/virt/coco/sev-guest/sev-guest.h @@ -0,0 +1,63 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2021 Advanced Micro Devices, Inc. + * + * Author: Brijesh Singh <brijesh.singh@amd.com> + * + * SEV-SNP API spec is available at https://developer.amd.com/sev + */ + +#ifndef __VIRT_SEVGUEST_H__ +#define __VIRT_SEVGUEST_H__ + +#include <linux/types.h> + +#define MAX_AUTHTAG_LEN 32 + +/* See SNP spec SNP_GUEST_REQUEST section for the structure */ +enum msg_type { + SNP_MSG_TYPE_INVALID = 0, + SNP_MSG_CPUID_REQ, + SNP_MSG_CPUID_RSP, + SNP_MSG_KEY_REQ, + SNP_MSG_KEY_RSP, + SNP_MSG_REPORT_REQ, + SNP_MSG_REPORT_RSP, + SNP_MSG_EXPORT_REQ, + SNP_MSG_EXPORT_RSP, + SNP_MSG_IMPORT_REQ, + SNP_MSG_IMPORT_RSP, + SNP_MSG_ABSORB_REQ, + SNP_MSG_ABSORB_RSP, + SNP_MSG_VMRK_REQ, + SNP_MSG_VMRK_RSP, + + SNP_MSG_TYPE_MAX +}; + +enum aead_algo { + SNP_AEAD_INVALID, + SNP_AEAD_AES_256_GCM, +}; + +struct snp_guest_msg_hdr { + u8 authtag[MAX_AUTHTAG_LEN]; + u64 msg_seqno; + u8 rsvd1[8]; + u8 algo; + u8 hdr_version; + u16 hdr_sz; + u8 msg_type; + u8 msg_version; + u16 msg_sz; + u32 rsvd2; + u8 msg_vmpck; + u8 rsvd3[35]; +} __packed; + +struct snp_guest_msg { + struct snp_guest_msg_hdr hdr; + u8 payload[4000]; +} __packed; + +#endif /* __VIRT_SEVGUEST_H__ */ diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c index 75c8d560bbd3..22f15f444f75 100644 --- a/drivers/virtio/virtio.c +++ b/drivers/virtio/virtio.c @@ -526,9 +526,8 @@ int virtio_device_restore(struct virtio_device *dev) goto err; } - /* If restore didn't do it, mark device DRIVER_OK ourselves. */ - if (!(dev->config->get_status(dev) & VIRTIO_CONFIG_S_DRIVER_OK)) - virtio_device_ready(dev); + /* Finally, tell the device we're all set */ + virtio_add_status(dev, VIRTIO_CONFIG_S_DRIVER_OK); virtio_config_enable(dev); diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c index dfe26fa17e95..617a7f4f07a8 100644 --- a/drivers/xen/balloon.c +++ b/drivers/xen/balloon.c @@ -689,29 +689,34 @@ void xen_free_ballooned_pages(unsigned int nr_pages, struct page **pages) } EXPORT_SYMBOL(xen_free_ballooned_pages); -#if defined(CONFIG_XEN_PV) && !defined(CONFIG_XEN_UNPOPULATED_ALLOC) -static void __init balloon_add_region(unsigned long start_pfn, - unsigned long pages) +static void __init balloon_add_regions(void) { +#if defined(CONFIG_XEN_PV) + unsigned long start_pfn, pages; unsigned long pfn, extra_pfn_end; + unsigned int i; - /* - * If the amount of usable memory has been limited (e.g., with - * the 'mem' command line parameter), don't add pages beyond - * this limit. - */ - extra_pfn_end = min(max_pfn, start_pfn + pages); + for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) { + pages = xen_extra_mem[i].n_pfns; + if (!pages) + continue; - for (pfn = start_pfn; pfn < extra_pfn_end; pfn++) { - /* totalram_pages and totalhigh_pages do not - include the boot-time balloon extension, so - don't subtract from it. */ - balloon_append(pfn_to_page(pfn)); - } + start_pfn = xen_extra_mem[i].start_pfn; - balloon_stats.total_pages += extra_pfn_end - start_pfn; -} + /* + * If the amount of usable memory has been limited (e.g., with + * the 'mem' command line parameter), don't add pages beyond + * this limit. + */ + extra_pfn_end = min(max_pfn, start_pfn + pages); + + for (pfn = start_pfn; pfn < extra_pfn_end; pfn++) + balloon_append(pfn_to_page(pfn)); + + balloon_stats.total_pages += extra_pfn_end - start_pfn; + } #endif +} static int __init balloon_init(void) { @@ -745,20 +750,7 @@ static int __init balloon_init(void) register_sysctl_table(xen_root); #endif -#if defined(CONFIG_XEN_PV) && !defined(CONFIG_XEN_UNPOPULATED_ALLOC) - { - int i; - - /* - * Initialize the balloon with pages from the extra memory - * regions (see arch/x86/xen/setup.c). - */ - for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) - if (xen_extra_mem[i].n_pfns) - balloon_add_region(xen_extra_mem[i].start_pfn, - xen_extra_mem[i].n_pfns); - } -#endif + balloon_add_regions(); task = kthread_run(balloon_thread, NULL, "xen-balloon"); if (IS_ERR(task)) { diff --git a/drivers/xen/gntalloc.c b/drivers/xen/gntalloc.c index 4849f94372a4..55acb32842a3 100644 --- a/drivers/xen/gntalloc.c +++ b/drivers/xen/gntalloc.c @@ -178,9 +178,9 @@ static void __del_gref(struct gntalloc_gref *gref) unsigned long addr; if (gref->notify.flags & UNMAP_NOTIFY_CLEAR_BYTE) { - uint8_t *tmp = kmap(gref->page); + uint8_t *tmp = kmap_local_page(gref->page); tmp[gref->notify.pgoff] = 0; - kunmap(gref->page); + kunmap_local(tmp); } if (gref->notify.flags & UNMAP_NOTIFY_SEND_EVENT) { notify_remote_via_evtchn(gref->notify.event); diff --git a/drivers/xen/gntdev-dmabuf.c b/drivers/xen/gntdev-dmabuf.c index d5bfd7b867fc..91073b4e4a20 100644 --- a/drivers/xen/gntdev-dmabuf.c +++ b/drivers/xen/gntdev-dmabuf.c @@ -24,15 +24,6 @@ MODULE_IMPORT_NS(DMA_BUF); -#ifndef GRANT_INVALID_REF -/* - * Note on usage of grant reference 0 as invalid grant reference: - * grant reference 0 is valid, but never exposed to a driver, - * because of the fact it is already in use/reserved by the PV console. - */ -#define GRANT_INVALID_REF 0 -#endif - struct gntdev_dmabuf { struct gntdev_dmabuf_priv *priv; struct dma_buf *dmabuf; @@ -532,7 +523,7 @@ static void dmabuf_imp_end_foreign_access(u32 *refs, int count) int i; for (i = 0; i < count; i++) - if (refs[i] != GRANT_INVALID_REF) + if (refs[i] != INVALID_GRANT_REF) gnttab_end_foreign_access(refs[i], 0UL); } @@ -567,7 +558,7 @@ static struct gntdev_dmabuf *dmabuf_imp_alloc_storage(int count) gntdev_dmabuf->nr_pages = count; for (i = 0; i < count; i++) - gntdev_dmabuf->u.imp.refs[i] = GRANT_INVALID_REF; + gntdev_dmabuf->u.imp.refs[i] = INVALID_GRANT_REF; return gntdev_dmabuf; diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c index 8ccccace2a4f..1a1aec0a88a1 100644 --- a/drivers/xen/grant-table.c +++ b/drivers/xen/grant-table.c @@ -66,8 +66,6 @@ #include <asm/sync_bitops.h> -/* External tools reserve first few grant table entries. */ -#define NR_RESERVED_ENTRIES 8 #define GNTTAB_LIST_END 0xffffffff static grant_ref_t **gnttab_list; @@ -209,6 +207,10 @@ static inline void check_free_callbacks(void) static void put_free_entry(grant_ref_t ref) { unsigned long flags; + + if (unlikely(ref < GNTTAB_NR_RESERVED_ENTRIES)) + return; + spin_lock_irqsave(&gnttab_list_lock, flags); gnttab_entry(ref) = gnttab_free_head; gnttab_free_head = ref; @@ -1465,12 +1467,12 @@ int gnttab_init(void) nr_init_grefs = nr_grant_frames * gnttab_interface->grefs_per_grant_frame; - for (i = NR_RESERVED_ENTRIES; i < nr_init_grefs - 1; i++) + for (i = GNTTAB_NR_RESERVED_ENTRIES; i < nr_init_grefs - 1; i++) gnttab_entry(i) = i + 1; gnttab_entry(nr_init_grefs - 1) = GNTTAB_LIST_END; - gnttab_free_count = nr_init_grefs - NR_RESERVED_ENTRIES; - gnttab_free_head = NR_RESERVED_ENTRIES; + gnttab_free_count = nr_init_grefs - GNTTAB_NR_RESERVED_ENTRIES; + gnttab_free_head = GNTTAB_NR_RESERVED_ENTRIES; printk("Grant table initialized\n"); return 0; diff --git a/drivers/xen/unpopulated-alloc.c b/drivers/xen/unpopulated-alloc.c index a8b41057c382..a39f2d36dd9c 100644 --- a/drivers/xen/unpopulated-alloc.c +++ b/drivers/xen/unpopulated-alloc.c @@ -230,39 +230,6 @@ void xen_free_unpopulated_pages(unsigned int nr_pages, struct page **pages) } EXPORT_SYMBOL(xen_free_unpopulated_pages); -#ifdef CONFIG_XEN_PV -static int __init init(void) -{ - unsigned int i; - - if (!xen_domain()) - return -ENODEV; - - if (!xen_pv_domain()) - return 0; - - /* - * Initialize with pages from the extra memory regions (see - * arch/x86/xen/setup.c). - */ - for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) { - unsigned int j; - - for (j = 0; j < xen_extra_mem[i].n_pfns; j++) { - struct page *pg = - pfn_to_page(xen_extra_mem[i].start_pfn + j); - - pg->zone_device_data = page_list; - page_list = pg; - list_count++; - } - } - - return 0; -} -subsys_initcall(init); -#endif - static int __init unpopulated_init(void) { int ret; diff --git a/drivers/xen/xen-front-pgdir-shbuf.c b/drivers/xen/xen-front-pgdir-shbuf.c index a959dee21134..b6433761d42c 100644 --- a/drivers/xen/xen-front-pgdir-shbuf.c +++ b/drivers/xen/xen-front-pgdir-shbuf.c @@ -21,15 +21,6 @@ #include <xen/xen-front-pgdir-shbuf.h> -#ifndef GRANT_INVALID_REF -/* - * FIXME: usage of grant reference 0 as invalid grant reference: - * grant reference 0 is valid, but never exposed to a PV driver, - * because of the fact it is already in use/reserved by the PV console. - */ -#define GRANT_INVALID_REF 0 -#endif - /** * This structure represents the structure of a shared page * that contains grant references to the pages of the shared @@ -38,6 +29,7 @@ */ struct xen_page_directory { grant_ref_t gref_dir_next_page; +#define XEN_GREF_LIST_END 0 grant_ref_t gref[1]; /* Variable length */ }; @@ -83,7 +75,7 @@ grant_ref_t xen_front_pgdir_shbuf_get_dir_start(struct xen_front_pgdir_shbuf *buf) { if (!buf->grefs) - return GRANT_INVALID_REF; + return INVALID_GRANT_REF; return buf->grefs[0]; } @@ -142,7 +134,7 @@ void xen_front_pgdir_shbuf_free(struct xen_front_pgdir_shbuf *buf) int i; for (i = 0; i < buf->num_grefs; i++) - if (buf->grefs[i] != GRANT_INVALID_REF) + if (buf->grefs[i] != INVALID_GRANT_REF) gnttab_end_foreign_access(buf->grefs[i], 0UL); } kfree(buf->grefs); @@ -355,7 +347,7 @@ static void backend_fill_page_dir(struct xen_front_pgdir_shbuf *buf) } /* Last page must say there is no more pages. */ page_dir = (struct xen_page_directory *)ptr; - page_dir->gref_dir_next_page = GRANT_INVALID_REF; + page_dir->gref_dir_next_page = XEN_GREF_LIST_END; } /** @@ -384,7 +376,7 @@ static void guest_fill_page_dir(struct xen_front_pgdir_shbuf *buf) if (grefs_left <= XEN_NUM_GREFS_PER_PAGE) { to_copy = grefs_left; - page_dir->gref_dir_next_page = GRANT_INVALID_REF; + page_dir->gref_dir_next_page = XEN_GREF_LIST_END; } else { to_copy = XEN_NUM_GREFS_PER_PAGE; page_dir->gref_dir_next_page = buf->grefs[i + 1]; diff --git a/drivers/xen/xen-scsiback.c b/drivers/xen/xen-scsiback.c index 0c5e565aa8cf..7a0c93acc2c5 100644 --- a/drivers/xen/xen-scsiback.c +++ b/drivers/xen/xen-scsiback.c @@ -280,6 +280,82 @@ static void scsiback_free_translation_entry(struct kref *kref) kfree(entry); } +static int32_t scsiback_result(int32_t result) +{ + int32_t host_status; + + switch (XEN_VSCSIIF_RSLT_HOST(result)) { + case DID_OK: + host_status = XEN_VSCSIIF_RSLT_HOST_OK; + break; + case DID_NO_CONNECT: + host_status = XEN_VSCSIIF_RSLT_HOST_NO_CONNECT; + break; + case DID_BUS_BUSY: + host_status = XEN_VSCSIIF_RSLT_HOST_BUS_BUSY; + break; + case DID_TIME_OUT: + host_status = XEN_VSCSIIF_RSLT_HOST_TIME_OUT; + break; + case DID_BAD_TARGET: + host_status = XEN_VSCSIIF_RSLT_HOST_BAD_TARGET; + break; + case DID_ABORT: + host_status = XEN_VSCSIIF_RSLT_HOST_ABORT; + break; + case DID_PARITY: + host_status = XEN_VSCSIIF_RSLT_HOST_PARITY; + break; + case DID_ERROR: + host_status = XEN_VSCSIIF_RSLT_HOST_ERROR; + break; + case DID_RESET: + host_status = XEN_VSCSIIF_RSLT_HOST_RESET; + break; + case DID_BAD_INTR: + host_status = XEN_VSCSIIF_RSLT_HOST_BAD_INTR; + break; + case DID_PASSTHROUGH: + host_status = XEN_VSCSIIF_RSLT_HOST_PASSTHROUGH; + break; + case DID_SOFT_ERROR: + host_status = XEN_VSCSIIF_RSLT_HOST_SOFT_ERROR; + break; + case DID_IMM_RETRY: + host_status = XEN_VSCSIIF_RSLT_HOST_IMM_RETRY; + break; + case DID_REQUEUE: + host_status = XEN_VSCSIIF_RSLT_HOST_REQUEUE; + break; + case DID_TRANSPORT_DISRUPTED: + host_status = XEN_VSCSIIF_RSLT_HOST_TRANSPORT_DISRUPTED; + break; + case DID_TRANSPORT_FAILFAST: + host_status = XEN_VSCSIIF_RSLT_HOST_TRANSPORT_FAILFAST; + break; + case DID_TARGET_FAILURE: + host_status = XEN_VSCSIIF_RSLT_HOST_TARGET_FAILURE; + break; + case DID_NEXUS_FAILURE: + host_status = XEN_VSCSIIF_RSLT_HOST_NEXUS_FAILURE; + break; + case DID_ALLOC_FAILURE: + host_status = XEN_VSCSIIF_RSLT_HOST_ALLOC_FAILURE; + break; + case DID_MEDIUM_ERROR: + host_status = XEN_VSCSIIF_RSLT_HOST_MEDIUM_ERROR; + break; + case DID_TRANSPORT_MARGINAL: + host_status = XEN_VSCSIIF_RSLT_HOST_TRANSPORT_MARGINAL; + break; + default: + host_status = XEN_VSCSIIF_RSLT_HOST_ERROR; + break; + } + + return (host_status << 16) | (result & 0x00ffff); +} + static void scsiback_send_response(struct vscsibk_info *info, char *sense_buffer, int32_t result, uint32_t resid, uint16_t rqid) @@ -295,7 +371,7 @@ static void scsiback_send_response(struct vscsibk_info *info, ring_res = RING_GET_RESPONSE(&info->ring, info->ring.rsp_prod_pvt); info->ring.rsp_prod_pvt++; - ring_res->rslt = result; + ring_res->rslt = scsiback_result(result); ring_res->rqid = rqid; if (sense_buffer != NULL && @@ -555,7 +631,7 @@ static void scsiback_device_action(struct vscsibk_pend *pending_req, struct scsiback_nexus *nexus = tpg->tpg_nexus; struct se_cmd *se_cmd = &pending_req->se_cmd; u64 unpacked_lun = pending_req->v2p->lun; - int rc, err = FAILED; + int rc, err = XEN_VSCSIIF_RSLT_RESET_FAILED; init_completion(&pending_req->tmr_done); @@ -569,7 +645,7 @@ static void scsiback_device_action(struct vscsibk_pend *pending_req, wait_for_completion(&pending_req->tmr_done); err = (se_cmd->se_tmr_req->response == TMR_FUNCTION_COMPLETE) ? - SUCCESS : FAILED; + XEN_VSCSIIF_RSLT_RESET_SUCCESS : XEN_VSCSIIF_RSLT_RESET_FAILED; scsiback_do_resp_with_sense(NULL, err, 0, pending_req); transport_generic_free_cmd(&pending_req->se_cmd, 0); diff --git a/drivers/xen/xenbus/xenbus_client.c b/drivers/xen/xenbus/xenbus_client.c index df6890681231..d6fdd2d209d3 100644 --- a/drivers/xen/xenbus/xenbus_client.c +++ b/drivers/xen/xenbus/xenbus_client.c @@ -363,50 +363,92 @@ static void xenbus_switch_fatal(struct xenbus_device *dev, int depth, int err, __xenbus_switch_state(dev, XenbusStateClosing, 1); } -/** - * xenbus_grant_ring +/* + * xenbus_setup_ring * @dev: xenbus device - * @vaddr: starting virtual address of the ring + * @vaddr: pointer to starting virtual address of the ring * @nr_pages: number of pages to be granted * @grefs: grant reference array to be filled in * - * Grant access to the given @vaddr to the peer of the given device. - * Then fill in @grefs with grant references. Return 0 on success, or - * -errno on error. On error, the device will switch to - * XenbusStateClosing, and the error will be saved in the store. + * Allocate physically contiguous pages for a shared ring buffer and grant it + * to the peer of the given device. The ring buffer is initially filled with + * zeroes. The virtual address of the ring is stored at @vaddr and the + * grant references are stored in the @grefs array. In case of error @vaddr + * will be set to NULL and @grefs will be filled with INVALID_GRANT_REF. */ -int xenbus_grant_ring(struct xenbus_device *dev, void *vaddr, +int xenbus_setup_ring(struct xenbus_device *dev, gfp_t gfp, void **vaddr, unsigned int nr_pages, grant_ref_t *grefs) { - int err; - unsigned int i; + unsigned long ring_size = nr_pages * XEN_PAGE_SIZE; grant_ref_t gref_head; + unsigned int i; + int ret; - err = gnttab_alloc_grant_references(nr_pages, &gref_head); - if (err) { - xenbus_dev_fatal(dev, err, "granting access to ring page"); - return err; + *vaddr = alloc_pages_exact(ring_size, gfp | __GFP_ZERO); + if (!*vaddr) { + ret = -ENOMEM; + goto err; + } + + ret = gnttab_alloc_grant_references(nr_pages, &gref_head); + if (ret) { + xenbus_dev_fatal(dev, ret, "granting access to %u ring pages", + nr_pages); + goto err; } for (i = 0; i < nr_pages; i++) { unsigned long gfn; - if (is_vmalloc_addr(vaddr)) - gfn = pfn_to_gfn(vmalloc_to_pfn(vaddr)); + if (is_vmalloc_addr(*vaddr)) + gfn = pfn_to_gfn(vmalloc_to_pfn(vaddr[i])); else - gfn = virt_to_gfn(vaddr); + gfn = virt_to_gfn(vaddr[i]); grefs[i] = gnttab_claim_grant_reference(&gref_head); gnttab_grant_foreign_access_ref(grefs[i], dev->otherend_id, gfn, 0); - - vaddr = vaddr + XEN_PAGE_SIZE; } return 0; + + err: + if (*vaddr) + free_pages_exact(*vaddr, ring_size); + for (i = 0; i < nr_pages; i++) + grefs[i] = INVALID_GRANT_REF; + *vaddr = NULL; + + return ret; } -EXPORT_SYMBOL_GPL(xenbus_grant_ring); +EXPORT_SYMBOL_GPL(xenbus_setup_ring); +/* + * xenbus_teardown_ring + * @vaddr: starting virtual address of the ring + * @nr_pages: number of pages + * @grefs: grant reference array + * + * Remove grants for the shared ring buffer and free the associated memory. + * On return the grant reference array is filled with INVALID_GRANT_REF. + */ +void xenbus_teardown_ring(void **vaddr, unsigned int nr_pages, + grant_ref_t *grefs) +{ + unsigned int i; + + for (i = 0; i < nr_pages; i++) { + if (grefs[i] != INVALID_GRANT_REF) { + gnttab_end_foreign_access(grefs[i], 0); + grefs[i] = INVALID_GRANT_REF; + } + } + + if (*vaddr) + free_pages_exact(*vaddr, nr_pages * XEN_PAGE_SIZE); + *vaddr = NULL; +} +EXPORT_SYMBOL_GPL(xenbus_teardown_ring); /** * Allocate an event channel for the given xenbus_device, assigning the newly diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c index fe360c33ce71..d367f2bd2b93 100644 --- a/drivers/xen/xenbus/xenbus_probe.c +++ b/drivers/xen/xenbus/xenbus_probe.c @@ -65,6 +65,7 @@ #include "xenbus.h" +static int xs_init_irq; int xen_store_evtchn; EXPORT_SYMBOL_GPL(xen_store_evtchn); @@ -750,6 +751,20 @@ static void xenbus_probe(void) { xenstored_ready = 1; + if (!xen_store_interface) { + xen_store_interface = xen_remap(xen_store_gfn << XEN_PAGE_SHIFT, + XEN_PAGE_SIZE); + /* + * Now it is safe to free the IRQ used for xenstore late + * initialization. No need to unbind: it is about to be + * bound again from xb_init_comms. Note that calling + * unbind_from_irqhandler now would result in xen_evtchn_close() + * being called and the event channel not being enabled again + * afterwards, resulting in missed event notifications. + */ + free_irq(xs_init_irq, &xb_waitq); + } + /* * In the HVM case, xenbus_init() deferred its call to * xs_init() in case callbacks were not operational yet. @@ -798,20 +813,22 @@ static int __init xenbus_probe_initcall(void) { /* * Probe XenBus here in the XS_PV case, and also XS_HVM unless we - * need to wait for the platform PCI device to come up. + * need to wait for the platform PCI device to come up or + * xen_store_interface is not ready. */ if (xen_store_domain_type == XS_PV || (xen_store_domain_type == XS_HVM && - !xs_hvm_defer_init_for_callback())) + !xs_hvm_defer_init_for_callback() && + xen_store_interface != NULL)) xenbus_probe(); /* - * For XS_LOCAL, spawn a thread which will wait for xenstored - * or a xenstore-stubdom to be started, then probe. It will be - * triggered when communication starts happening, by waiting - * on xb_waitq. + * For XS_LOCAL or when xen_store_interface is not ready, spawn a + * thread which will wait for xenstored or a xenstore-stubdom to be + * started, then probe. It will be triggered when communication + * starts happening, by waiting on xb_waitq. */ - if (xen_store_domain_type == XS_LOCAL) { + if (xen_store_domain_type == XS_LOCAL || xen_store_interface == NULL) { struct task_struct *probe_task; probe_task = kthread_run(xenbus_probe_thread, NULL, @@ -907,10 +924,25 @@ static struct notifier_block xenbus_resume_nb = { .notifier_call = xenbus_resume_cb, }; +static irqreturn_t xenbus_late_init(int irq, void *unused) +{ + int err; + uint64_t v = 0; + + err = hvm_get_parameter(HVM_PARAM_STORE_PFN, &v); + if (err || !v || !~v) + return IRQ_HANDLED; + xen_store_gfn = (unsigned long)v; + + wake_up(&xb_waitq); + return IRQ_HANDLED; +} + static int __init xenbus_init(void) { int err; uint64_t v = 0; + bool wait = false; xen_store_domain_type = XS_UNKNOWN; if (!xen_domain()) @@ -957,25 +989,44 @@ static int __init xenbus_init(void) * been properly initialized. Instead of attempting to map a * wrong guest physical address return error. * - * Also recognize all bits set as an invalid value. + * Also recognize all bits set as an invalid/uninitialized value. */ - if (!v || !~v) { + if (!v) { err = -ENOENT; goto out_error; } - /* Avoid truncation on 32-bit. */ + if (v == ~0ULL) { + wait = true; + } else { + /* Avoid truncation on 32-bit. */ #if BITS_PER_LONG == 32 - if (v > ULONG_MAX) { - pr_err("%s: cannot handle HVM_PARAM_STORE_PFN=%llx > ULONG_MAX\n", - __func__, v); - err = -EINVAL; - goto out_error; - } + if (v > ULONG_MAX) { + pr_err("%s: cannot handle HVM_PARAM_STORE_PFN=%llx > ULONG_MAX\n", + __func__, v); + err = -EINVAL; + goto out_error; + } #endif - xen_store_gfn = (unsigned long)v; - xen_store_interface = - xen_remap(xen_store_gfn << XEN_PAGE_SHIFT, - XEN_PAGE_SIZE); + xen_store_gfn = (unsigned long)v; + xen_store_interface = + xen_remap(xen_store_gfn << XEN_PAGE_SHIFT, + XEN_PAGE_SIZE); + if (xen_store_interface->connection != XENSTORE_CONNECTED) + wait = true; + } + if (wait) { + err = bind_evtchn_to_irqhandler(xen_store_evtchn, + xenbus_late_init, + 0, "xenstore_late_init", + &xb_waitq); + if (err < 0) { + pr_err("xenstore_late_init couldn't bind irq err=%d\n", + err); + return err; + } + + xs_init_irq = err; + } break; default: pr_warn("Xenstore state unknown\n"); diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c index 501128188343..8ce82ff1e40a 100644 --- a/fs/9p/vfs_addr.c +++ b/fs/9p/vfs_addr.c @@ -100,29 +100,28 @@ const struct netfs_request_ops v9fs_req_ops = { }; /** - * v9fs_release_page - release the private state associated with a page - * @page: The page to be released + * v9fs_release_folio - release the private state associated with a folio + * @folio: The folio to be released * @gfp: The caller's allocation restrictions * - * Returns 1 if the page can be released, false otherwise. + * Returns true if the page can be released, false otherwise. */ -static int v9fs_release_page(struct page *page, gfp_t gfp) +static bool v9fs_release_folio(struct folio *folio, gfp_t gfp) { - struct folio *folio = page_folio(page); struct inode *inode = folio_inode(folio); if (folio_test_private(folio)) - return 0; + return false; #ifdef CONFIG_9P_FSCACHE if (folio_test_fscache(folio)) { if (current_is_kswapd() || !(gfp & __GFP_FS)) - return 0; + return false; folio_wait_fscache(folio); } #endif fscache_note_page_release(v9fs_inode_cookie(V9FS_I(inode))); - return 1; + return true; } static void v9fs_invalidate_folio(struct folio *folio, size_t offset, @@ -260,7 +259,7 @@ v9fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) } static int v9fs_write_begin(struct file *filp, struct address_space *mapping, - loff_t pos, unsigned int len, unsigned int flags, + loff_t pos, unsigned int len, struct page **subpagep, void **fsdata) { int retval; @@ -275,7 +274,7 @@ static int v9fs_write_begin(struct file *filp, struct address_space *mapping, * file. We need to do this before we get a lock on the page in case * there's more than one writer competing for the same cache block. */ - retval = netfs_write_begin(filp, mapping, pos, len, flags, &folio, fsdata); + retval = netfs_write_begin(filp, mapping, pos, len, &folio, fsdata); if (retval < 0) return retval; @@ -336,13 +335,13 @@ static bool v9fs_dirty_folio(struct address_space *mapping, struct folio *folio) #endif const struct address_space_operations v9fs_addr_operations = { - .readpage = netfs_readpage, + .read_folio = netfs_read_folio, .readahead = netfs_readahead, .dirty_folio = v9fs_dirty_folio, .writepage = v9fs_vfs_writepage, .write_begin = v9fs_write_begin, .write_end = v9fs_write_end, - .releasepage = v9fs_release_page, + .release_folio = v9fs_release_folio, .invalidate_folio = v9fs_invalidate_folio, .launder_folio = v9fs_launder_folio, .direct_IO = v9fs_direct_IO, diff --git a/fs/Kconfig.binfmt b/fs/Kconfig.binfmt index 21c6332fa785..32dff7ba3dda 100644 --- a/fs/Kconfig.binfmt +++ b/fs/Kconfig.binfmt @@ -142,12 +142,6 @@ config BINFMT_ZFLAT help Support FLAT format compressed binaries -config BINFMT_SHARED_FLAT - bool "Enable shared FLAT support" - depends on BINFMT_FLAT - help - Support FLAT shared libraries - config HAVE_AOUT def_bool n diff --git a/fs/adfs/inode.c b/fs/adfs/inode.c index 561bc748c04a..ee22278b0cfc 100644 --- a/fs/adfs/inode.c +++ b/fs/adfs/inode.c @@ -38,9 +38,9 @@ static int adfs_writepage(struct page *page, struct writeback_control *wbc) return block_write_full_page(page, adfs_get_block, wbc); } -static int adfs_readpage(struct file *file, struct page *page) +static int adfs_read_folio(struct file *file, struct folio *folio) { - return block_read_full_page(page, adfs_get_block); + return block_read_full_folio(folio, adfs_get_block); } static void adfs_write_failed(struct address_space *mapping, loff_t to) @@ -52,13 +52,13 @@ static void adfs_write_failed(struct address_space *mapping, loff_t to) } static int adfs_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, + loff_t pos, unsigned len, struct page **pagep, void **fsdata) { int ret; *pagep = NULL; - ret = cont_write_begin(file, mapping, pos, len, flags, pagep, fsdata, + ret = cont_write_begin(file, mapping, pos, len, pagep, fsdata, adfs_get_block, &ADFS_I(mapping->host)->mmu_private); if (unlikely(ret)) @@ -75,7 +75,7 @@ static sector_t _adfs_bmap(struct address_space *mapping, sector_t block) static const struct address_space_operations adfs_aops = { .dirty_folio = block_dirty_folio, .invalidate_folio = block_invalidate_folio, - .readpage = adfs_readpage, + .read_folio = adfs_read_folio, .writepage = adfs_writepage, .write_begin = adfs_write_begin, .write_end = generic_write_end, diff --git a/fs/affs/file.c b/fs/affs/file.c index b3f81d84ff4c..cd00a4c68a12 100644 --- a/fs/affs/file.c +++ b/fs/affs/file.c @@ -375,9 +375,9 @@ static int affs_writepage(struct page *page, struct writeback_control *wbc) return block_write_full_page(page, affs_get_block, wbc); } -static int affs_readpage(struct file *file, struct page *page) +static int affs_read_folio(struct file *file, struct folio *folio) { - return block_read_full_page(page, affs_get_block); + return block_read_full_folio(folio, affs_get_block); } static void affs_write_failed(struct address_space *mapping, loff_t to) @@ -414,13 +414,13 @@ affs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) } static int affs_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, + loff_t pos, unsigned len, struct page **pagep, void **fsdata) { int ret; *pagep = NULL; - ret = cont_write_begin(file, mapping, pos, len, flags, pagep, fsdata, + ret = cont_write_begin(file, mapping, pos, len, pagep, fsdata, affs_get_block, &AFFS_I(mapping->host)->mmu_private); if (unlikely(ret)) @@ -455,7 +455,7 @@ static sector_t _affs_bmap(struct address_space *mapping, sector_t block) const struct address_space_operations affs_aops = { .dirty_folio = block_dirty_folio, .invalidate_folio = block_invalidate_folio, - .readpage = affs_readpage, + .read_folio = affs_read_folio, .writepage = affs_writepage, .write_begin = affs_write_begin, .write_end = affs_write_end, @@ -629,8 +629,9 @@ out: } static int -affs_readpage_ofs(struct file *file, struct page *page) +affs_read_folio_ofs(struct file *file, struct folio *folio) { + struct page *page = &folio->page; struct inode *inode = page->mapping->host; u32 to; int err; @@ -650,7 +651,7 @@ affs_readpage_ofs(struct file *file, struct page *page) } static int affs_write_begin_ofs(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, + loff_t pos, unsigned len, struct page **pagep, void **fsdata) { struct inode *inode = mapping->host; @@ -670,7 +671,7 @@ static int affs_write_begin_ofs(struct file *file, struct address_space *mapping } index = pos >> PAGE_SHIFT; - page = grab_cache_page_write_begin(mapping, index, flags); + page = grab_cache_page_write_begin(mapping, index); if (!page) return -ENOMEM; *pagep = page; @@ -837,7 +838,7 @@ err_bh: const struct address_space_operations affs_aops_ofs = { .dirty_folio = block_dirty_folio, .invalidate_folio = block_invalidate_folio, - .readpage = affs_readpage_ofs, + .read_folio = affs_read_folio_ofs, //.writepage = affs_writepage_ofs, .write_begin = affs_write_begin_ofs, .write_end = affs_write_end_ofs @@ -887,7 +888,7 @@ affs_truncate(struct inode *inode) loff_t isize = inode->i_size; int res; - res = mapping->a_ops->write_begin(NULL, mapping, isize, 0, 0, &page, &fsdata); + res = mapping->a_ops->write_begin(NULL, mapping, isize, 0, &page, &fsdata); if (!res) res = mapping->a_ops->write_end(NULL, mapping, isize, 0, 0, page, fsdata); else diff --git a/fs/affs/symlink.c b/fs/affs/symlink.c index a7531b26e8f0..31d6446dc166 100644 --- a/fs/affs/symlink.c +++ b/fs/affs/symlink.c @@ -11,8 +11,9 @@ #include "affs.h" -static int affs_symlink_readpage(struct file *file, struct page *page) +static int affs_symlink_read_folio(struct file *file, struct folio *folio) { + struct page *page = &folio->page; struct buffer_head *bh; struct inode *inode = page->mapping->host; char *link = page_address(page); @@ -67,7 +68,7 @@ fail: } const struct address_space_operations affs_symlink_aops = { - .readpage = affs_symlink_readpage, + .read_folio = affs_symlink_read_folio, }; const struct inode_operations affs_symlink_inode_operations = { diff --git a/fs/afs/dir.c b/fs/afs/dir.c index 932e61e28e5d..94aa7356248e 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -41,7 +41,7 @@ static int afs_symlink(struct user_namespace *mnt_userns, struct inode *dir, static int afs_rename(struct user_namespace *mnt_userns, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags); -static int afs_dir_releasepage(struct page *page, gfp_t gfp_flags); +static bool afs_dir_release_folio(struct folio *folio, gfp_t gfp_flags); static void afs_dir_invalidate_folio(struct folio *folio, size_t offset, size_t length); @@ -75,7 +75,7 @@ const struct inode_operations afs_dir_inode_operations = { const struct address_space_operations afs_dir_aops = { .dirty_folio = afs_dir_dirty_folio, - .releasepage = afs_dir_releasepage, + .release_folio = afs_dir_release_folio, .invalidate_folio = afs_dir_invalidate_folio, }; @@ -2002,9 +2002,8 @@ error: * Release a directory folio and clean up its private state if it's not busy * - return true if the folio can now be released, false if not */ -static int afs_dir_releasepage(struct page *subpage, gfp_t gfp_flags) +static bool afs_dir_release_folio(struct folio *folio, gfp_t gfp_flags) { - struct folio *folio = page_folio(subpage); struct afs_vnode *dvnode = AFS_FS_I(folio_inode(folio)); _enter("{{%llx:%llu}[%lu]}", dvnode->fid.vid, dvnode->fid.vnode, folio_index(folio)); diff --git a/fs/afs/file.c b/fs/afs/file.c index 26292a110a8f..a8e8832179e4 100644 --- a/fs/afs/file.c +++ b/fs/afs/file.c @@ -19,10 +19,10 @@ #include "internal.h" static int afs_file_mmap(struct file *file, struct vm_area_struct *vma); -static int afs_symlink_readpage(struct file *file, struct page *page); +static int afs_symlink_read_folio(struct file *file, struct folio *folio); static void afs_invalidate_folio(struct folio *folio, size_t offset, size_t length); -static int afs_releasepage(struct page *page, gfp_t gfp_flags); +static bool afs_release_folio(struct folio *folio, gfp_t gfp_flags); static ssize_t afs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter); static void afs_vm_open(struct vm_area_struct *area); @@ -50,11 +50,11 @@ const struct inode_operations afs_file_inode_operations = { }; const struct address_space_operations afs_file_aops = { - .readpage = netfs_readpage, + .read_folio = netfs_read_folio, .readahead = netfs_readahead, .dirty_folio = afs_dirty_folio, .launder_folio = afs_launder_folio, - .releasepage = afs_releasepage, + .release_folio = afs_release_folio, .invalidate_folio = afs_invalidate_folio, .write_begin = afs_write_begin, .write_end = afs_write_end, @@ -63,8 +63,8 @@ const struct address_space_operations afs_file_aops = { }; const struct address_space_operations afs_symlink_aops = { - .readpage = afs_symlink_readpage, - .releasepage = afs_releasepage, + .read_folio = afs_symlink_read_folio, + .release_folio = afs_release_folio, .invalidate_folio = afs_invalidate_folio, }; @@ -332,11 +332,10 @@ static void afs_issue_read(struct netfs_io_subrequest *subreq) afs_put_read(fsreq); } -static int afs_symlink_readpage(struct file *file, struct page *page) +static int afs_symlink_read_folio(struct file *file, struct folio *folio) { - struct afs_vnode *vnode = AFS_FS_I(page->mapping->host); + struct afs_vnode *vnode = AFS_FS_I(folio->mapping->host); struct afs_read *fsreq; - struct folio *folio = page_folio(page); int ret; fsreq = afs_alloc_read(GFP_NOFS); @@ -347,13 +346,13 @@ static int afs_symlink_readpage(struct file *file, struct page *page) fsreq->len = folio_size(folio); fsreq->vnode = vnode; fsreq->iter = &fsreq->def_iter; - iov_iter_xarray(&fsreq->def_iter, READ, &page->mapping->i_pages, + iov_iter_xarray(&fsreq->def_iter, READ, &folio->mapping->i_pages, fsreq->pos, fsreq->len); ret = afs_fetch_data(fsreq->vnode, fsreq); if (ret == 0) - SetPageUptodate(page); - unlock_page(page); + folio_mark_uptodate(folio); + folio_unlock(folio); return ret; } @@ -482,16 +481,15 @@ static void afs_invalidate_folio(struct folio *folio, size_t offset, * release a page and clean up its private state if it's not busy * - return true if the page can now be released, false if not */ -static int afs_releasepage(struct page *page, gfp_t gfp) +static bool afs_release_folio(struct folio *folio, gfp_t gfp) { - struct folio *folio = page_folio(page); struct afs_vnode *vnode = AFS_FS_I(folio_inode(folio)); _enter("{{%llx:%llu}[%lu],%lx},%x", vnode->fid.vid, vnode->fid.vnode, folio_index(folio), folio->flags, gfp); - /* deny if page is being written to the cache and the caller hasn't + /* deny if folio is being written to the cache and the caller hasn't * elected to wait */ #ifdef CONFIG_AFS_FSCACHE if (folio_test_fscache(folio)) { diff --git a/fs/afs/inode.c b/fs/afs/inode.c index 2fe402483ad5..30b066299d39 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -740,10 +740,22 @@ int afs_getattr(struct user_namespace *mnt_userns, const struct path *path, { struct inode *inode = d_inode(path->dentry); struct afs_vnode *vnode = AFS_FS_I(inode); - int seq = 0; + struct key *key; + int ret, seq = 0; _enter("{ ino=%lu v=%u }", inode->i_ino, inode->i_generation); + if (!(query_flags & AT_STATX_DONT_SYNC) && + !test_bit(AFS_VNODE_CB_PROMISED, &vnode->flags)) { + key = afs_request_key(vnode->volume->cell); + if (IS_ERR(key)) + return PTR_ERR(key); + ret = afs_validate(vnode, key); + key_put(key); + if (ret < 0) + return ret; + } + do { read_seqbegin_or_lock(&vnode->cb_lock, &seq); generic_fillattr(&init_user_ns, inode, stat); diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 7b7ef945dc78..a30995901266 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -311,7 +311,7 @@ struct afs_net { atomic_t n_lookup; /* Number of lookups done */ atomic_t n_reval; /* Number of dentries needing revalidation */ atomic_t n_inval; /* Number of invalidations by the server */ - atomic_t n_relpg; /* Number of invalidations by releasepage */ + atomic_t n_relpg; /* Number of invalidations by release_folio */ atomic_t n_read_dir; /* Number of directory pages read */ atomic_t n_dir_cr; /* Number of directory entry creation edits */ atomic_t n_dir_rm; /* Number of directory entry removal edits */ @@ -1535,7 +1535,7 @@ bool afs_dirty_folio(struct address_space *, struct folio *); #define afs_dirty_folio filemap_dirty_folio #endif extern int afs_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, + loff_t pos, unsigned len, struct page **pagep, void **fsdata); extern int afs_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, diff --git a/fs/afs/write.c b/fs/afs/write.c index 6bcf1475511b..5224e346fbad 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -42,7 +42,7 @@ static void afs_folio_start_fscache(bool caching, struct folio *folio) * prepare to perform part of a write to a page */ int afs_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, + loff_t pos, unsigned len, struct page **_page, void **fsdata) { struct afs_vnode *vnode = AFS_FS_I(file_inode(file)); @@ -60,7 +60,7 @@ int afs_write_begin(struct file *file, struct address_space *mapping, * file. We need to do this before we get a lock on the page in case * there's more than one writer competing for the same cache block. */ - ret = netfs_write_begin(file, mapping, pos, len, flags, &folio, fsdata); + ret = netfs_write_begin(file, mapping, pos, len, &folio, fsdata); if (ret < 0) return ret; @@ -616,8 +616,7 @@ static ssize_t afs_write_back_from_locked_folio(struct address_space *mapping, _debug("write discard %x @%llx [%llx]", len, start, i_size); /* The dirty region was entirely beyond the EOF. */ - fscache_clear_page_bits(afs_vnode_cache(vnode), - mapping, start, len, caching); + fscache_clear_page_bits(mapping, start, len, caching); afs_pages_written_back(vnode, start, len); ret = 0; } diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c index b4b3567ac655..be383fa46b12 100644 --- a/fs/befs/linuxvfs.c +++ b/fs/befs/linuxvfs.c @@ -40,7 +40,7 @@ MODULE_LICENSE("GPL"); static int befs_readdir(struct file *, struct dir_context *); static int befs_get_block(struct inode *, sector_t, struct buffer_head *, int); -static int befs_readpage(struct file *file, struct page *page); +static int befs_read_folio(struct file *file, struct folio *folio); static sector_t befs_bmap(struct address_space *mapping, sector_t block); static struct dentry *befs_lookup(struct inode *, struct dentry *, unsigned int); @@ -48,7 +48,7 @@ static struct inode *befs_iget(struct super_block *, unsigned long); static struct inode *befs_alloc_inode(struct super_block *sb); static void befs_free_inode(struct inode *inode); static void befs_destroy_inodecache(void); -static int befs_symlink_readpage(struct file *, struct page *); +static int befs_symlink_read_folio(struct file *, struct folio *); static int befs_utf2nls(struct super_block *sb, const char *in, int in_len, char **out, int *out_len); static int befs_nls2utf(struct super_block *sb, const char *in, int in_len, @@ -87,12 +87,12 @@ static const struct inode_operations befs_dir_inode_operations = { }; static const struct address_space_operations befs_aops = { - .readpage = befs_readpage, + .read_folio = befs_read_folio, .bmap = befs_bmap, }; static const struct address_space_operations befs_symlink_aops = { - .readpage = befs_symlink_readpage, + .read_folio = befs_symlink_read_folio, }; static const struct export_operations befs_export_operations = { @@ -102,16 +102,16 @@ static const struct export_operations befs_export_operations = { }; /* - * Called by generic_file_read() to read a page of data + * Called by generic_file_read() to read a folio of data * * In turn, simply calls a generic block read function and * passes it the address of befs_get_block, for mapping file * positions to disk blocks. */ static int -befs_readpage(struct file *file, struct page *page) +befs_read_folio(struct file *file, struct folio *folio) { - return block_read_full_page(page, befs_get_block); + return block_read_full_folio(folio, befs_get_block); } static sector_t @@ -468,8 +468,9 @@ befs_destroy_inodecache(void) * The data stream become link name. Unless the LONG_SYMLINK * flag is set. */ -static int befs_symlink_readpage(struct file *unused, struct page *page) +static int befs_symlink_read_folio(struct file *unused, struct folio *folio) { + struct page *page = &folio->page; struct inode *inode = page->mapping->host; struct super_block *sb = inode->i_sb; struct befs_inode_info *befs_ino = BEFS_I(inode); diff --git a/fs/bfs/file.c b/fs/bfs/file.c index 03139344568f..57ae5ee6deec 100644 --- a/fs/bfs/file.c +++ b/fs/bfs/file.c @@ -155,9 +155,9 @@ static int bfs_writepage(struct page *page, struct writeback_control *wbc) return block_write_full_page(page, bfs_get_block, wbc); } -static int bfs_readpage(struct file *file, struct page *page) +static int bfs_read_folio(struct file *file, struct folio *folio) { - return block_read_full_page(page, bfs_get_block); + return block_read_full_folio(folio, bfs_get_block); } static void bfs_write_failed(struct address_space *mapping, loff_t to) @@ -169,13 +169,12 @@ static void bfs_write_failed(struct address_space *mapping, loff_t to) } static int bfs_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, + loff_t pos, unsigned len, struct page **pagep, void **fsdata) { int ret; - ret = block_write_begin(mapping, pos, len, flags, pagep, - bfs_get_block); + ret = block_write_begin(mapping, pos, len, pagep, bfs_get_block); if (unlikely(ret)) bfs_write_failed(mapping, pos + len); @@ -190,7 +189,7 @@ static sector_t bfs_bmap(struct address_space *mapping, sector_t block) const struct address_space_operations bfs_aops = { .dirty_folio = block_dirty_folio, .invalidate_folio = block_invalidate_folio, - .readpage = bfs_readpage, + .read_folio = bfs_read_folio, .writepage = bfs_writepage, .write_begin = bfs_write_begin, .write_end = generic_write_end, diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 6556e13ed95f..63c7ebb0da89 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -1117,11 +1117,11 @@ out_free_interp: * independently randomized mmap region (0 load_bias * without MAP_FIXED nor MAP_FIXED_NOREPLACE). */ - alignment = maximum_alignment(elf_phdata, elf_ex->e_phnum); - if (interpreter || alignment > ELF_MIN_ALIGN) { + if (interpreter) { load_bias = ELF_ET_DYN_BASE; if (current->flags & PF_RANDOMIZE) load_bias += arch_mmap_rnd(); + alignment = maximum_alignment(elf_phdata, elf_ex->e_phnum); if (alignment) load_bias &= ~(alignment - 1); elf_flags |= MAP_FIXED_NOREPLACE; diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c index 626898150011..c26545d71d39 100644 --- a/fs/binfmt_flat.c +++ b/fs/binfmt_flat.c @@ -37,7 +37,6 @@ #include <linux/flat.h> #include <linux/uaccess.h> #include <linux/vmalloc.h> -#include <linux/coredump.h> #include <asm/byteorder.h> #include <asm/unaligned.h> @@ -69,11 +68,7 @@ #define RELOC_FAILED 0xff00ff01 /* Relocation incorrect somewhere */ #define UNLOADED_LIB 0x7ff000ff /* Placeholder for unused library */ -#ifdef CONFIG_BINFMT_SHARED_FLAT -#define MAX_SHARED_LIBS (4) -#else -#define MAX_SHARED_LIBS (1) -#endif +#define MAX_SHARED_LIBS (1) #ifdef CONFIG_BINFMT_FLAT_NO_DATA_START_OFFSET #define DATA_START_OFFSET_WORDS (0) @@ -93,38 +88,13 @@ struct lib_info { } lib_list[MAX_SHARED_LIBS]; }; -#ifdef CONFIG_BINFMT_SHARED_FLAT -static int load_flat_shared_library(int id, struct lib_info *p); -#endif - static int load_flat_binary(struct linux_binprm *); -#ifdef CONFIG_COREDUMP -static int flat_core_dump(struct coredump_params *cprm); -#endif static struct linux_binfmt flat_format = { .module = THIS_MODULE, .load_binary = load_flat_binary, -#ifdef CONFIG_COREDUMP - .core_dump = flat_core_dump, - .min_coredump = PAGE_SIZE -#endif }; -/****************************************************************************/ -/* - * Routine writes a core dump image in the current directory. - * Currently only a stub-function. - */ - -#ifdef CONFIG_COREDUMP -static int flat_core_dump(struct coredump_params *cprm) -{ - pr_warn("Process %s:%d received signr %d and should have core dumped\n", - current->comm, current->pid, cprm->siginfo->si_signo); - return 1; -} -#endif /****************************************************************************/ /* @@ -329,51 +299,18 @@ out_free: /****************************************************************************/ static unsigned long -calc_reloc(unsigned long r, struct lib_info *p, int curid, int internalp) +calc_reloc(unsigned long r, struct lib_info *p) { unsigned long addr; - int id; unsigned long start_brk; unsigned long start_data; unsigned long text_len; unsigned long start_code; -#ifdef CONFIG_BINFMT_SHARED_FLAT - if (r == 0) - id = curid; /* Relocs of 0 are always self referring */ - else { - id = (r >> 24) & 0xff; /* Find ID for this reloc */ - r &= 0x00ffffff; /* Trim ID off here */ - } - if (id >= MAX_SHARED_LIBS) { - pr_err("reference 0x%lx to shared library %d", r, id); - goto failed; - } - if (curid != id) { - if (internalp) { - pr_err("reloc address 0x%lx not in same module " - "(%d != %d)", r, curid, id); - goto failed; - } else if (!p->lib_list[id].loaded && - load_flat_shared_library(id, p) < 0) { - pr_err("failed to load library %d", id); - goto failed; - } - /* Check versioning information (i.e. time stamps) */ - if (p->lib_list[id].build_date && p->lib_list[curid].build_date && - p->lib_list[curid].build_date < p->lib_list[id].build_date) { - pr_err("library %d is younger than %d", id, curid); - goto failed; - } - } -#else - id = 0; -#endif - - start_brk = p->lib_list[id].start_brk; - start_data = p->lib_list[id].start_data; - start_code = p->lib_list[id].start_code; - text_len = p->lib_list[id].text_len; + start_brk = p->lib_list[0].start_brk; + start_data = p->lib_list[0].start_data; + start_code = p->lib_list[0].start_code; + text_len = p->lib_list[0].text_len; if (r > start_brk - start_data + text_len) { pr_err("reloc outside program 0x%lx (0 - 0x%lx/0x%lx)", @@ -440,8 +377,32 @@ static void old_reloc(unsigned long rl) /****************************************************************************/ +static inline u32 __user *skip_got_header(u32 __user *rp) +{ + if (IS_ENABLED(CONFIG_RISCV)) { + /* + * RISC-V has a 16 byte GOT PLT header for elf64-riscv + * and 8 byte GOT PLT header for elf32-riscv. + * Skip the whole GOT PLT header, since it is reserved + * for the dynamic linker (ld.so). + */ + u32 rp_val0, rp_val1; + + if (get_user(rp_val0, rp)) + return rp; + if (get_user(rp_val1, rp + 1)) + return rp; + + if (rp_val0 == 0xffffffff && rp_val1 == 0xffffffff) + rp += 4; + else if (rp_val0 == 0xffffffff) + rp += 2; + } + return rp; +} + static int load_flat_file(struct linux_binprm *bprm, - struct lib_info *libinfo, int id, unsigned long *extra_stack) + struct lib_info *libinfo, unsigned long *extra_stack) { struct flat_hdr *hdr; unsigned long textpos, datapos, realdatastart; @@ -493,14 +454,6 @@ static int load_flat_file(struct linux_binprm *bprm, goto err; } - /* Don't allow old format executables to use shared libraries */ - if (rev == OLD_FLAT_VERSION && id != 0) { - pr_err("shared libraries are not available before rev 0x%lx\n", - FLAT_VERSION); - ret = -ENOEXEC; - goto err; - } - /* * fix up the flags for the older format, there were all kinds * of endian hacks, this only works for the simple cases @@ -551,15 +504,13 @@ static int load_flat_file(struct linux_binprm *bprm, } /* Flush all traces of the currently running executable */ - if (id == 0) { - ret = begin_new_exec(bprm); - if (ret) - goto err; + ret = begin_new_exec(bprm); + if (ret) + goto err; - /* OK, This is the point of no return */ - set_personality(PER_LINUX_32BIT); - setup_new_exec(bprm); - } + /* OK, This is the point of no return */ + set_personality(PER_LINUX_32BIT); + setup_new_exec(bprm); /* * calculate the extra space we need to map in @@ -739,42 +690,40 @@ static int load_flat_file(struct linux_binprm *bprm, text_len -= sizeof(struct flat_hdr); /* the real code len */ /* The main program needs a little extra setup in the task structure */ - if (id == 0) { - current->mm->start_code = start_code; - current->mm->end_code = end_code; - current->mm->start_data = datapos; - current->mm->end_data = datapos + data_len; - /* - * set up the brk stuff, uses any slack left in data/bss/stack - * allocation. We put the brk after the bss (between the bss - * and stack) like other platforms. - * Userspace code relies on the stack pointer starting out at - * an address right at the end of a page. - */ - current->mm->start_brk = datapos + data_len + bss_len; - current->mm->brk = (current->mm->start_brk + 3) & ~3; + current->mm->start_code = start_code; + current->mm->end_code = end_code; + current->mm->start_data = datapos; + current->mm->end_data = datapos + data_len; + /* + * set up the brk stuff, uses any slack left in data/bss/stack + * allocation. We put the brk after the bss (between the bss + * and stack) like other platforms. + * Userspace code relies on the stack pointer starting out at + * an address right at the end of a page. + */ + current->mm->start_brk = datapos + data_len + bss_len; + current->mm->brk = (current->mm->start_brk + 3) & ~3; #ifndef CONFIG_MMU - current->mm->context.end_brk = memp + memp_size - stack_len; + current->mm->context.end_brk = memp + memp_size - stack_len; #endif - } if (flags & FLAT_FLAG_KTRACE) { pr_info("Mapping is %lx, Entry point is %x, data_start is %x\n", textpos, 0x00ffffff&ntohl(hdr->entry), ntohl(hdr->data_start)); pr_info("%s %s: TEXT=%lx-%lx DATA=%lx-%lx BSS=%lx-%lx\n", - id ? "Lib" : "Load", bprm->filename, + "Load", bprm->filename, start_code, end_code, datapos, datapos + data_len, datapos + data_len, (datapos + data_len + bss_len + 3) & ~3); } /* Store the current module values into the global library structure */ - libinfo->lib_list[id].start_code = start_code; - libinfo->lib_list[id].start_data = datapos; - libinfo->lib_list[id].start_brk = datapos + data_len + bss_len; - libinfo->lib_list[id].text_len = text_len; - libinfo->lib_list[id].loaded = 1; - libinfo->lib_list[id].entry = (0x00ffffff & ntohl(hdr->entry)) + textpos; - libinfo->lib_list[id].build_date = ntohl(hdr->build_date); + libinfo->lib_list[0].start_code = start_code; + libinfo->lib_list[0].start_data = datapos; + libinfo->lib_list[0].start_brk = datapos + data_len + bss_len; + libinfo->lib_list[0].text_len = text_len; + libinfo->lib_list[0].loaded = 1; + libinfo->lib_list[0].entry = (0x00ffffff & ntohl(hdr->entry)) + textpos; + libinfo->lib_list[0].build_date = ntohl(hdr->build_date); /* * We just load the allocations into some temporary memory to @@ -789,14 +738,15 @@ static int load_flat_file(struct linux_binprm *bprm, * image. */ if (flags & FLAT_FLAG_GOTPIC) { - for (rp = (u32 __user *)datapos; ; rp++) { + rp = skip_got_header((u32 __user *) datapos); + for (; ; rp++) { u32 addr, rp_val; if (get_user(rp_val, rp)) return -EFAULT; if (rp_val == 0xffffffff) break; if (rp_val) { - addr = calc_reloc(rp_val, libinfo, id, 0); + addr = calc_reloc(rp_val, libinfo); if (addr == RELOC_FAILED) { ret = -ENOEXEC; goto err; @@ -832,7 +782,7 @@ static int load_flat_file(struct linux_binprm *bprm, return -EFAULT; relval = ntohl(tmp); addr = flat_get_relocate_addr(relval); - rp = (u32 __user *)calc_reloc(addr, libinfo, id, 1); + rp = (u32 __user *)calc_reloc(addr, libinfo); if (rp == (u32 __user *)RELOC_FAILED) { ret = -ENOEXEC; goto err; @@ -855,7 +805,7 @@ static int load_flat_file(struct linux_binprm *bprm, */ addr = ntohl((__force __be32)addr); } - addr = calc_reloc(addr, libinfo, id, 0); + addr = calc_reloc(addr, libinfo); if (addr == RELOC_FAILED) { ret = -ENOEXEC; goto err; @@ -883,7 +833,7 @@ static int load_flat_file(struct linux_binprm *bprm, /* zero the BSS, BRK and stack areas */ if (clear_user((void __user *)(datapos + data_len), bss_len + (memp + memp_size - stack_len - /* end brk */ - libinfo->lib_list[id].start_brk) + /* start brk */ + libinfo->lib_list[0].start_brk) + /* start brk */ stack_len)) return -EFAULT; @@ -894,49 +844,6 @@ err: /****************************************************************************/ -#ifdef CONFIG_BINFMT_SHARED_FLAT - -/* - * Load a shared library into memory. The library gets its own data - * segment (including bss) but not argv/argc/environ. - */ - -static int load_flat_shared_library(int id, struct lib_info *libs) -{ - /* - * This is a fake bprm struct; only the members "buf", "file" and - * "filename" are actually used. - */ - struct linux_binprm bprm; - int res; - char buf[16]; - loff_t pos = 0; - - memset(&bprm, 0, sizeof(bprm)); - - /* Create the file name */ - sprintf(buf, "/lib/lib%d.so", id); - - /* Open the file up */ - bprm.filename = buf; - bprm.file = open_exec(bprm.filename); - res = PTR_ERR(bprm.file); - if (IS_ERR(bprm.file)) - return res; - - res = kernel_read(bprm.file, bprm.buf, BINPRM_BUF_SIZE, &pos); - - if (res >= 0) - res = load_flat_file(&bprm, libs, id, NULL); - - allow_write_access(bprm.file); - fput(bprm.file); - - return res; -} - -#endif /* CONFIG_BINFMT_SHARED_FLAT */ -/****************************************************************************/ /* * These are the functions used to load flat style executables and shared @@ -968,7 +875,7 @@ static int load_flat_binary(struct linux_binprm *bprm) stack_len += (bprm->envc + 1) * sizeof(char *); /* the envp array */ stack_len = ALIGN(stack_len, FLAT_STACK_ALIGN); - res = load_flat_file(bprm, &libinfo, 0, &stack_len); + res = load_flat_file(bprm, &libinfo, &stack_len); if (res < 0) return res; @@ -1013,20 +920,6 @@ static int load_flat_binary(struct linux_binprm *bprm) */ start_addr = libinfo.lib_list[0].entry; -#ifdef CONFIG_BINFMT_SHARED_FLAT - for (i = MAX_SHARED_LIBS-1; i > 0; i--) { - if (libinfo.lib_list[i].loaded) { - /* Push previos first to call address */ - unsigned long __user *sp; - current->mm->start_stack -= sizeof(unsigned long); - sp = (unsigned long __user *)current->mm->start_stack; - if (put_user(start_addr, sp)) - return -EFAULT; - start_addr = libinfo.lib_list[i].entry; - } - } -#endif - #ifdef FLAT_PLAT_INIT FLAT_PLAT_INIT(regs); #endif diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c index 0a0d0eccee4e..548d6a5477b4 100644 --- a/fs/btrfs/acl.c +++ b/fs/btrfs/acl.c @@ -55,9 +55,8 @@ struct posix_acl *btrfs_get_acl(struct inode *inode, int type, bool rcu) return acl; } -static int __btrfs_set_acl(struct btrfs_trans_handle *trans, - struct user_namespace *mnt_userns, - struct inode *inode, struct posix_acl *acl, int type) +int __btrfs_set_acl(struct btrfs_trans_handle *trans, struct inode *inode, + struct posix_acl *acl, int type) { int ret, size = 0; const char *name; @@ -123,40 +122,8 @@ int btrfs_set_acl(struct user_namespace *mnt_userns, struct inode *inode, if (ret) return ret; } - ret = __btrfs_set_acl(NULL, mnt_userns, inode, acl, type); + ret = __btrfs_set_acl(NULL, inode, acl, type); if (ret) inode->i_mode = old_mode; return ret; } - -int btrfs_init_acl(struct btrfs_trans_handle *trans, - struct inode *inode, struct inode *dir) -{ - struct posix_acl *default_acl, *acl; - int ret = 0; - - /* this happens with subvols */ - if (!dir) - return 0; - - ret = posix_acl_create(dir, &inode->i_mode, &default_acl, &acl); - if (ret) - return ret; - - if (default_acl) { - ret = __btrfs_set_acl(trans, &init_user_ns, inode, default_acl, - ACL_TYPE_DEFAULT); - posix_acl_release(default_acl); - } - - if (acl) { - if (!ret) - ret = __btrfs_set_acl(trans, &init_user_ns, inode, acl, - ACL_TYPE_ACCESS); - posix_acl_release(acl); - } - - if (!default_acl && !acl) - cache_no_acl(inode); - return ret; -} diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c index 43c89952b7d2..aac240430efe 100644 --- a/fs/btrfs/async-thread.c +++ b/fs/btrfs/async-thread.c @@ -15,13 +15,12 @@ enum { WORK_DONE_BIT, WORK_ORDER_DONE_BIT, - WORK_HIGH_PRIO_BIT, }; #define NO_THRESHOLD (-1) #define DFT_THRESHOLD (32) -struct __btrfs_workqueue { +struct btrfs_workqueue { struct workqueue_struct *normal_wq; /* File system this workqueue services */ @@ -48,12 +47,7 @@ struct __btrfs_workqueue { spinlock_t thres_lock; }; -struct btrfs_workqueue { - struct __btrfs_workqueue *normal; - struct __btrfs_workqueue *high; -}; - -struct btrfs_fs_info * __pure btrfs_workqueue_owner(const struct __btrfs_workqueue *wq) +struct btrfs_fs_info * __pure btrfs_workqueue_owner(const struct btrfs_workqueue *wq) { return wq->fs_info; } @@ -66,22 +60,22 @@ struct btrfs_fs_info * __pure btrfs_work_owner(const struct btrfs_work *work) bool btrfs_workqueue_normal_congested(const struct btrfs_workqueue *wq) { /* - * We could compare wq->normal->pending with num_online_cpus() + * We could compare wq->pending with num_online_cpus() * to support "thresh == NO_THRESHOLD" case, but it requires * moving up atomic_inc/dec in thresh_queue/exec_hook. Let's * postpone it until someone needs the support of that case. */ - if (wq->normal->thresh == NO_THRESHOLD) + if (wq->thresh == NO_THRESHOLD) return false; - return atomic_read(&wq->normal->pending) > wq->normal->thresh * 2; + return atomic_read(&wq->pending) > wq->thresh * 2; } -static struct __btrfs_workqueue * -__btrfs_alloc_workqueue(struct btrfs_fs_info *fs_info, const char *name, - unsigned int flags, int limit_active, int thresh) +struct btrfs_workqueue *btrfs_alloc_workqueue(struct btrfs_fs_info *fs_info, + const char *name, unsigned int flags, + int limit_active, int thresh) { - struct __btrfs_workqueue *ret = kzalloc(sizeof(*ret), GFP_KERNEL); + struct btrfs_workqueue *ret = kzalloc(sizeof(*ret), GFP_KERNEL); if (!ret) return NULL; @@ -105,12 +99,8 @@ __btrfs_alloc_workqueue(struct btrfs_fs_info *fs_info, const char *name, ret->thresh = thresh; } - if (flags & WQ_HIGHPRI) - ret->normal_wq = alloc_workqueue("btrfs-%s-high", flags, - ret->current_active, name); - else - ret->normal_wq = alloc_workqueue("btrfs-%s", flags, - ret->current_active, name); + ret->normal_wq = alloc_workqueue("btrfs-%s", flags, ret->current_active, + name); if (!ret->normal_wq) { kfree(ret); return NULL; @@ -119,41 +109,7 @@ __btrfs_alloc_workqueue(struct btrfs_fs_info *fs_info, const char *name, INIT_LIST_HEAD(&ret->ordered_list); spin_lock_init(&ret->list_lock); spin_lock_init(&ret->thres_lock); - trace_btrfs_workqueue_alloc(ret, name, flags & WQ_HIGHPRI); - return ret; -} - -static inline void -__btrfs_destroy_workqueue(struct __btrfs_workqueue *wq); - -struct btrfs_workqueue *btrfs_alloc_workqueue(struct btrfs_fs_info *fs_info, - const char *name, - unsigned int flags, - int limit_active, - int thresh) -{ - struct btrfs_workqueue *ret = kzalloc(sizeof(*ret), GFP_KERNEL); - - if (!ret) - return NULL; - - ret->normal = __btrfs_alloc_workqueue(fs_info, name, - flags & ~WQ_HIGHPRI, - limit_active, thresh); - if (!ret->normal) { - kfree(ret); - return NULL; - } - - if (flags & WQ_HIGHPRI) { - ret->high = __btrfs_alloc_workqueue(fs_info, name, flags, - limit_active, thresh); - if (!ret->high) { - __btrfs_destroy_workqueue(ret->normal); - kfree(ret); - return NULL; - } - } + trace_btrfs_workqueue_alloc(ret, name); return ret; } @@ -162,7 +118,7 @@ struct btrfs_workqueue *btrfs_alloc_workqueue(struct btrfs_fs_info *fs_info, * This hook WILL be called in IRQ handler context, * so workqueue_set_max_active MUST NOT be called in this hook */ -static inline void thresh_queue_hook(struct __btrfs_workqueue *wq) +static inline void thresh_queue_hook(struct btrfs_workqueue *wq) { if (wq->thresh == NO_THRESHOLD) return; @@ -174,7 +130,7 @@ static inline void thresh_queue_hook(struct __btrfs_workqueue *wq) * This hook is called in kthread content. * So workqueue_set_max_active is called here. */ -static inline void thresh_exec_hook(struct __btrfs_workqueue *wq) +static inline void thresh_exec_hook(struct btrfs_workqueue *wq) { int new_current_active; long pending; @@ -217,7 +173,7 @@ out: } } -static void run_ordered_work(struct __btrfs_workqueue *wq, +static void run_ordered_work(struct btrfs_workqueue *wq, struct btrfs_work *self) { struct list_head *list = &wq->ordered_list; @@ -305,7 +261,7 @@ static void btrfs_work_helper(struct work_struct *normal_work) { struct btrfs_work *work = container_of(normal_work, struct btrfs_work, normal_work); - struct __btrfs_workqueue *wq; + struct btrfs_workqueue *wq = work->wq; int need_order = 0; /* @@ -318,7 +274,6 @@ static void btrfs_work_helper(struct work_struct *normal_work) */ if (work->ordered_func) need_order = 1; - wq = work->wq; trace_btrfs_work_sched(work); thresh_exec_hook(wq); @@ -350,8 +305,7 @@ void btrfs_init_work(struct btrfs_work *work, btrfs_func_t func, work->flags = 0; } -static inline void __btrfs_queue_work(struct __btrfs_workqueue *wq, - struct btrfs_work *work) +void btrfs_queue_work(struct btrfs_workqueue *wq, struct btrfs_work *work) { unsigned long flags; @@ -366,54 +320,22 @@ static inline void __btrfs_queue_work(struct __btrfs_workqueue *wq, queue_work(wq->normal_wq, &work->normal_work); } -void btrfs_queue_work(struct btrfs_workqueue *wq, - struct btrfs_work *work) -{ - struct __btrfs_workqueue *dest_wq; - - if (test_bit(WORK_HIGH_PRIO_BIT, &work->flags) && wq->high) - dest_wq = wq->high; - else - dest_wq = wq->normal; - __btrfs_queue_work(dest_wq, work); -} - -static inline void -__btrfs_destroy_workqueue(struct __btrfs_workqueue *wq) -{ - destroy_workqueue(wq->normal_wq); - trace_btrfs_workqueue_destroy(wq); - kfree(wq); -} - void btrfs_destroy_workqueue(struct btrfs_workqueue *wq) { if (!wq) return; - if (wq->high) - __btrfs_destroy_workqueue(wq->high); - __btrfs_destroy_workqueue(wq->normal); + destroy_workqueue(wq->normal_wq); + trace_btrfs_workqueue_destroy(wq); kfree(wq); } void btrfs_workqueue_set_max(struct btrfs_workqueue *wq, int limit_active) { - if (!wq) - return; - wq->normal->limit_active = limit_active; - if (wq->high) - wq->high->limit_active = limit_active; -} - -void btrfs_set_work_high_priority(struct btrfs_work *work) -{ - set_bit(WORK_HIGH_PRIO_BIT, &work->flags); + if (wq) + wq->limit_active = limit_active; } void btrfs_flush_workqueue(struct btrfs_workqueue *wq) { - if (wq->high) - flush_workqueue(wq->high->normal_wq); - - flush_workqueue(wq->normal->normal_wq); + flush_workqueue(wq->normal_wq); } diff --git a/fs/btrfs/async-thread.h b/fs/btrfs/async-thread.h index 3204daa51b95..07960529b360 100644 --- a/fs/btrfs/async-thread.h +++ b/fs/btrfs/async-thread.h @@ -11,8 +11,6 @@ struct btrfs_fs_info; struct btrfs_workqueue; -/* Internal use only */ -struct __btrfs_workqueue; struct btrfs_work; typedef void (*btrfs_func_t)(struct btrfs_work *arg); typedef void (*btrfs_work_func_t)(struct work_struct *arg); @@ -25,7 +23,7 @@ struct btrfs_work { /* Don't touch things below */ struct work_struct normal_work; struct list_head ordered_list; - struct __btrfs_workqueue *wq; + struct btrfs_workqueue *wq; unsigned long flags; }; @@ -40,9 +38,8 @@ void btrfs_queue_work(struct btrfs_workqueue *wq, struct btrfs_work *work); void btrfs_destroy_workqueue(struct btrfs_workqueue *wq); void btrfs_workqueue_set_max(struct btrfs_workqueue *wq, int max); -void btrfs_set_work_high_priority(struct btrfs_work *work); struct btrfs_fs_info * __pure btrfs_work_owner(const struct btrfs_work *work); -struct btrfs_fs_info * __pure btrfs_workqueue_owner(const struct __btrfs_workqueue *wq); +struct btrfs_fs_info * __pure btrfs_workqueue_owner(const struct btrfs_workqueue *wq); bool btrfs_workqueue_normal_congested(const struct btrfs_workqueue *wq); void btrfs_flush_workqueue(struct btrfs_workqueue *wq); diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index c22d287e020b..ede389f2602d 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -168,11 +168,12 @@ static int btrfs_add_block_group_cache(struct btrfs_fs_info *info, struct rb_node **p; struct rb_node *parent = NULL; struct btrfs_block_group *cache; + bool leftmost = true; ASSERT(block_group->length != 0); - spin_lock(&info->block_group_cache_lock); - p = &info->block_group_cache_tree.rb_node; + write_lock(&info->block_group_cache_lock); + p = &info->block_group_cache_tree.rb_root.rb_node; while (*p) { parent = *p; @@ -181,20 +182,18 @@ static int btrfs_add_block_group_cache(struct btrfs_fs_info *info, p = &(*p)->rb_left; } else if (block_group->start > cache->start) { p = &(*p)->rb_right; + leftmost = false; } else { - spin_unlock(&info->block_group_cache_lock); + write_unlock(&info->block_group_cache_lock); return -EEXIST; } } rb_link_node(&block_group->cache_node, parent, p); - rb_insert_color(&block_group->cache_node, - &info->block_group_cache_tree); + rb_insert_color_cached(&block_group->cache_node, + &info->block_group_cache_tree, leftmost); - if (info->first_logical_byte > block_group->start) - info->first_logical_byte = block_group->start; - - spin_unlock(&info->block_group_cache_lock); + write_unlock(&info->block_group_cache_lock); return 0; } @@ -210,8 +209,8 @@ static struct btrfs_block_group *block_group_cache_tree_search( struct rb_node *n; u64 end, start; - spin_lock(&info->block_group_cache_lock); - n = info->block_group_cache_tree.rb_node; + read_lock(&info->block_group_cache_lock); + n = info->block_group_cache_tree.rb_root.rb_node; while (n) { cache = rb_entry(n, struct btrfs_block_group, cache_node); @@ -233,12 +232,9 @@ static struct btrfs_block_group *block_group_cache_tree_search( break; } } - if (ret) { + if (ret) btrfs_get_block_group(ret); - if (bytenr == 0 && info->first_logical_byte > ret->start) - info->first_logical_byte = ret->start; - } - spin_unlock(&info->block_group_cache_lock); + read_unlock(&info->block_group_cache_lock); return ret; } @@ -267,15 +263,15 @@ struct btrfs_block_group *btrfs_next_block_group( struct btrfs_fs_info *fs_info = cache->fs_info; struct rb_node *node; - spin_lock(&fs_info->block_group_cache_lock); + read_lock(&fs_info->block_group_cache_lock); /* If our block group was removed, we need a full search. */ if (RB_EMPTY_NODE(&cache->cache_node)) { const u64 next_bytenr = cache->start + cache->length; - spin_unlock(&fs_info->block_group_cache_lock); + read_unlock(&fs_info->block_group_cache_lock); btrfs_put_block_group(cache); - cache = btrfs_lookup_first_block_group(fs_info, next_bytenr); return cache; + return btrfs_lookup_first_block_group(fs_info, next_bytenr); } node = rb_next(&cache->cache_node); btrfs_put_block_group(cache); @@ -284,46 +280,70 @@ struct btrfs_block_group *btrfs_next_block_group( btrfs_get_block_group(cache); } else cache = NULL; - spin_unlock(&fs_info->block_group_cache_lock); + read_unlock(&fs_info->block_group_cache_lock); return cache; } -bool btrfs_inc_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr) +/** + * Check if we can do a NOCOW write for a given extent. + * + * @fs_info: The filesystem information object. + * @bytenr: Logical start address of the extent. + * + * Check if we can do a NOCOW write for the given extent, and increments the + * number of NOCOW writers in the block group that contains the extent, as long + * as the block group exists and it's currently not in read-only mode. + * + * Returns: A non-NULL block group pointer if we can do a NOCOW write, the caller + * is responsible for calling btrfs_dec_nocow_writers() later. + * + * Or NULL if we can not do a NOCOW write + */ +struct btrfs_block_group *btrfs_inc_nocow_writers(struct btrfs_fs_info *fs_info, + u64 bytenr) { struct btrfs_block_group *bg; - bool ret = true; + bool can_nocow = true; bg = btrfs_lookup_block_group(fs_info, bytenr); if (!bg) - return false; + return NULL; spin_lock(&bg->lock); if (bg->ro) - ret = false; + can_nocow = false; else atomic_inc(&bg->nocow_writers); spin_unlock(&bg->lock); - /* No put on block group, done by btrfs_dec_nocow_writers */ - if (!ret) + if (!can_nocow) { btrfs_put_block_group(bg); + return NULL; + } - return ret; + /* No put on block group, done by btrfs_dec_nocow_writers(). */ + return bg; } -void btrfs_dec_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr) +/** + * Decrement the number of NOCOW writers in a block group. + * + * @bg: The block group. + * + * This is meant to be called after a previous call to btrfs_inc_nocow_writers(), + * and on the block group returned by that call. Typically this is called after + * creating an ordered extent for a NOCOW write, to prevent races with scrub and + * relocation. + * + * After this call, the caller should not use the block group anymore. It it wants + * to use it, then it should get a reference on it before calling this function. + */ +void btrfs_dec_nocow_writers(struct btrfs_block_group *bg) { - struct btrfs_block_group *bg; - - bg = btrfs_lookup_block_group(fs_info, bytenr); - ASSERT(bg); if (atomic_dec_and_test(&bg->nocow_writers)) wake_up_var(&bg->nocow_writers); - /* - * Once for our lookup and once for the lookup done by a previous call - * to btrfs_inc_nocow_writers() - */ - btrfs_put_block_group(bg); + + /* For the lookup done by a previous call to btrfs_inc_nocow_writers(). */ btrfs_put_block_group(bg); } @@ -772,10 +792,10 @@ int btrfs_cache_block_group(struct btrfs_block_group *cache, int load_cache_only cache->has_caching_ctl = 1; spin_unlock(&cache->lock); - spin_lock(&fs_info->block_group_cache_lock); + write_lock(&fs_info->block_group_cache_lock); refcount_inc(&caching_ctl->count); list_add_tail(&caching_ctl->list, &fs_info->caching_block_groups); - spin_unlock(&fs_info->block_group_cache_lock); + write_unlock(&fs_info->block_group_cache_lock); btrfs_get_block_group(cache); @@ -957,17 +977,15 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, if (ret) goto out; - spin_lock(&fs_info->block_group_cache_lock); - rb_erase(&block_group->cache_node, - &fs_info->block_group_cache_tree); + write_lock(&fs_info->block_group_cache_lock); + rb_erase_cached(&block_group->cache_node, + &fs_info->block_group_cache_tree); RB_CLEAR_NODE(&block_group->cache_node); /* Once for the block groups rbtree */ btrfs_put_block_group(block_group); - if (fs_info->first_logical_byte == block_group->start) - fs_info->first_logical_byte = (u64)-1; - spin_unlock(&fs_info->block_group_cache_lock); + write_unlock(&fs_info->block_group_cache_lock); down_write(&block_group->space_info->groups_sem); /* @@ -992,7 +1010,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, if (block_group->cached == BTRFS_CACHE_STARTED) btrfs_wait_block_group_cache_done(block_group); if (block_group->has_caching_ctl) { - spin_lock(&fs_info->block_group_cache_lock); + write_lock(&fs_info->block_group_cache_lock); if (!caching_ctl) { struct btrfs_caching_control *ctl; @@ -1006,7 +1024,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, } if (caching_ctl) list_del_init(&caching_ctl->list); - spin_unlock(&fs_info->block_group_cache_lock); + write_unlock(&fs_info->block_group_cache_lock); if (caching_ctl) { /* Once for the caching bgs list and once for us. */ btrfs_put_caching_control(caching_ctl); @@ -1367,6 +1385,14 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info) goto next; } + ret = btrfs_zone_finish(block_group); + if (ret < 0) { + btrfs_dec_block_group_ro(block_group); + if (ret == -EAGAIN) + ret = 0; + goto next; + } + /* * Want to do this before we do anything else so we can recover * properly if we fail to join the transaction. @@ -1512,6 +1538,13 @@ static int reclaim_bgs_cmp(void *unused, const struct list_head *a, return bg1->used > bg2->used; } +static inline bool btrfs_should_reclaim(struct btrfs_fs_info *fs_info) +{ + if (btrfs_is_zoned(fs_info)) + return btrfs_zoned_should_reclaim(fs_info); + return true; +} + void btrfs_reclaim_bgs_work(struct work_struct *work) { struct btrfs_fs_info *fs_info = @@ -1522,6 +1555,9 @@ void btrfs_reclaim_bgs_work(struct work_struct *work) if (!test_bit(BTRFS_FS_OPEN, &fs_info->flags)) return; + if (!btrfs_should_reclaim(fs_info)) + return; + sb_start_write(fs_info->sb); if (!btrfs_exclop_start(fs_info, BTRFS_EXCLOP_BALANCE)) { @@ -1692,35 +1728,13 @@ static int find_first_block_group(struct btrfs_fs_info *fs_info, struct btrfs_root *root = btrfs_block_group_root(fs_info); int ret; struct btrfs_key found_key; - struct extent_buffer *leaf; - int slot; - - ret = btrfs_search_slot(NULL, root, key, path, 0, 0); - if (ret < 0) - return ret; - - while (1) { - slot = path->slots[0]; - leaf = path->nodes[0]; - if (slot >= btrfs_header_nritems(leaf)) { - ret = btrfs_next_leaf(root, path); - if (ret == 0) - continue; - if (ret < 0) - goto out; - break; - } - btrfs_item_key_to_cpu(leaf, &found_key, slot); + btrfs_for_each_slot(root, key, &found_key, path, ret) { if (found_key.objectid >= key->objectid && found_key.type == BTRFS_BLOCK_GROUP_ITEM_KEY) { - ret = read_bg_from_eb(fs_info, &found_key, path); - break; + return read_bg_from_eb(fs_info, &found_key, path); } - - path->slots[0]++; } -out: return ret; } @@ -2503,12 +2517,6 @@ struct btrfs_block_group *btrfs_make_block_group(struct btrfs_trans_handle *tran return ERR_PTR(ret); } - /* - * New block group is likely to be used soon. Try to activate it now. - * Failure is OK for now. - */ - btrfs_zone_activate(cache); - ret = exclude_super_stripes(cache); if (ret) { /* We may have excluded something, so call this just in case */ @@ -2946,7 +2954,6 @@ int btrfs_start_dirty_block_groups(struct btrfs_trans_handle *trans) struct btrfs_path *path = NULL; LIST_HEAD(dirty); struct list_head *io = &cur_trans->io_bgs; - int num_started = 0; int loops = 0; spin_lock(&cur_trans->dirty_bgs_lock); @@ -3012,7 +3019,6 @@ again: cache->io_ctl.inode = NULL; ret = btrfs_write_out_cache(trans, cache, path); if (ret == 0 && cache->io_ctl.inode) { - num_started++; should_put = 0; /* @@ -3113,7 +3119,6 @@ int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans) int should_put; struct btrfs_path *path; struct list_head *io = &cur_trans->io_bgs; - int num_started = 0; path = btrfs_alloc_path(); if (!path) @@ -3171,7 +3176,6 @@ int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans) cache->io_ctl.inode = NULL; ret = btrfs_write_out_cache(trans, cache, path); if (ret == 0 && cache->io_ctl.inode) { - num_started++; should_put = 0; list_add_tail(&cache->io_list, io); } else { @@ -3230,6 +3234,31 @@ int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans) return ret; } +static inline bool should_reclaim_block_group(struct btrfs_block_group *bg, + u64 bytes_freed) +{ + const struct btrfs_space_info *space_info = bg->space_info; + const int reclaim_thresh = READ_ONCE(space_info->bg_reclaim_threshold); + const u64 new_val = bg->used; + const u64 old_val = new_val + bytes_freed; + u64 thresh; + + if (reclaim_thresh == 0) + return false; + + thresh = div_factor_fine(bg->length, reclaim_thresh); + + /* + * If we were below the threshold before don't reclaim, we are likely a + * brand new block group and we don't want to relocate new block groups. + */ + if (old_val < thresh) + return false; + if (new_val >= thresh) + return false; + return true; +} + int btrfs_update_block_group(struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, bool alloc) { @@ -3252,6 +3281,8 @@ int btrfs_update_block_group(struct btrfs_trans_handle *trans, spin_unlock(&info->delalloc_root_lock); while (total) { + bool reclaim; + cache = btrfs_lookup_block_group(info, bytenr); if (!cache) { ret = -ENOENT; @@ -3297,6 +3328,8 @@ int btrfs_update_block_group(struct btrfs_trans_handle *trans, cache->space_info, num_bytes); cache->space_info->bytes_used -= num_bytes; cache->space_info->disk_used -= num_bytes * factor; + + reclaim = should_reclaim_block_group(cache, num_bytes); spin_unlock(&cache->lock); spin_unlock(&cache->space_info->lock); @@ -3323,6 +3356,8 @@ int btrfs_update_block_group(struct btrfs_trans_handle *trans, if (!alloc && old_val == 0) { if (!btrfs_test_opt(info, DISCARD_ASYNC)) btrfs_mark_bg_unused(cache); + } else if (!alloc && reclaim) { + btrfs_mark_bg_to_reclaim(cache); } btrfs_put_block_group(cache); @@ -3455,7 +3490,7 @@ int btrfs_force_chunk_alloc(struct btrfs_trans_handle *trans, u64 type) return btrfs_chunk_alloc(trans, alloc_flags, CHUNK_ALLOC_FORCE); } -static int do_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags) +static struct btrfs_block_group *do_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags) { struct btrfs_block_group *bg; int ret; @@ -3542,7 +3577,11 @@ static int do_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags) out: btrfs_trans_release_chunk_metadata(trans); - return ret; + if (ret) + return ERR_PTR(ret); + + btrfs_get_block_group(bg); + return bg; } /* @@ -3657,10 +3696,17 @@ int btrfs_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags, { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_space_info *space_info; + struct btrfs_block_group *ret_bg; bool wait_for_alloc = false; bool should_alloc = false; + bool from_extent_allocation = false; int ret = 0; + if (force == CHUNK_ALLOC_FORCE_FOR_EXTENT) { + from_extent_allocation = true; + force = CHUNK_ALLOC_FORCE; + } + /* Don't re-enter if we're already allocating a chunk */ if (trans->allocating_chunk) return -ENOSPC; @@ -3750,9 +3796,22 @@ int btrfs_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags, force_metadata_allocation(fs_info); } - ret = do_chunk_alloc(trans, flags); + ret_bg = do_chunk_alloc(trans, flags); trans->allocating_chunk = false; + if (IS_ERR(ret_bg)) { + ret = PTR_ERR(ret_bg); + } else if (from_extent_allocation) { + /* + * New block group is likely to be used soon. Try to activate + * it now. Failure is OK for now. + */ + btrfs_zone_activate(ret_bg); + } + + if (!ret) + btrfs_put_block_group(ret_bg); + spin_lock(&space_info->lock); if (ret < 0) { if (ret == -ENOSPC) @@ -3943,14 +4002,14 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info) struct btrfs_caching_control *caching_ctl; struct rb_node *n; - spin_lock(&info->block_group_cache_lock); + write_lock(&info->block_group_cache_lock); while (!list_empty(&info->caching_block_groups)) { caching_ctl = list_entry(info->caching_block_groups.next, struct btrfs_caching_control, list); list_del(&caching_ctl->list); btrfs_put_caching_control(caching_ctl); } - spin_unlock(&info->block_group_cache_lock); + write_unlock(&info->block_group_cache_lock); spin_lock(&info->unused_bgs_lock); while (!list_empty(&info->unused_bgs)) { @@ -3980,14 +4039,14 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info) } spin_unlock(&info->zone_active_bgs_lock); - spin_lock(&info->block_group_cache_lock); - while ((n = rb_last(&info->block_group_cache_tree)) != NULL) { + write_lock(&info->block_group_cache_lock); + while ((n = rb_last(&info->block_group_cache_tree.rb_root)) != NULL) { block_group = rb_entry(n, struct btrfs_block_group, cache_node); - rb_erase(&block_group->cache_node, - &info->block_group_cache_tree); + rb_erase_cached(&block_group->cache_node, + &info->block_group_cache_tree); RB_CLEAR_NODE(&block_group->cache_node); - spin_unlock(&info->block_group_cache_lock); + write_unlock(&info->block_group_cache_lock); down_write(&block_group->space_info->groups_sem); list_del(&block_group->list); @@ -4010,9 +4069,9 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info) ASSERT(block_group->swap_extents == 0); btrfs_put_block_group(block_group); - spin_lock(&info->block_group_cache_lock); + write_lock(&info->block_group_cache_lock); } - spin_unlock(&info->block_group_cache_lock); + write_unlock(&info->block_group_cache_lock); btrfs_release_global_block_rsv(info); diff --git a/fs/btrfs/block-group.h b/fs/btrfs/block-group.h index 93aabc68bb6a..3ac668ace50a 100644 --- a/fs/btrfs/block-group.h +++ b/fs/btrfs/block-group.h @@ -35,11 +35,15 @@ enum btrfs_discard_state { * the FS with empty chunks * * CHUNK_ALLOC_FORCE means it must try to allocate one + * + * CHUNK_ALLOC_FORCE_FOR_EXTENT like CHUNK_ALLOC_FORCE but called from + * find_free_extent() that also activaes the zone */ enum btrfs_chunk_alloc_enum { CHUNK_ALLOC_NO_FORCE, CHUNK_ALLOC_LIMITED, CHUNK_ALLOC_FORCE, + CHUNK_ALLOC_FORCE_FOR_EXTENT, }; struct btrfs_caching_control { @@ -208,6 +212,8 @@ struct btrfs_block_group { u64 meta_write_pointer; struct map_lookup *physical_map; struct list_head active_bg_list; + struct work_struct zone_finish_work; + struct extent_buffer *last_eb; }; static inline u64 btrfs_block_group_end(struct btrfs_block_group *block_group) @@ -250,8 +256,9 @@ void btrfs_put_block_group(struct btrfs_block_group *cache); void btrfs_dec_block_group_reservations(struct btrfs_fs_info *fs_info, const u64 start); void btrfs_wait_block_group_reservations(struct btrfs_block_group *bg); -bool btrfs_inc_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr); -void btrfs_dec_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr); +struct btrfs_block_group *btrfs_inc_nocow_writers(struct btrfs_fs_info *fs_info, + u64 bytenr); +void btrfs_dec_nocow_writers(struct btrfs_block_group *bg); void btrfs_wait_nocow_writers(struct btrfs_block_group *bg); void btrfs_wait_block_group_cache_progress(struct btrfs_block_group *cache, u64 num_bytes); diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h index 47e72d72f7d0..33811e896623 100644 --- a/fs/btrfs/btrfs_inode.h +++ b/fs/btrfs/btrfs_inode.h @@ -384,30 +384,16 @@ static inline bool btrfs_inode_in_log(struct btrfs_inode *inode, u64 generation) return ret; } -struct btrfs_dio_private { - struct inode *inode; - - /* - * Since DIO can use anonymous page, we cannot use page_offset() to - * grab the file offset, thus need a dedicated member for file offset. - */ - u64 file_offset; - u64 disk_bytenr; - /* Used for bio::bi_size */ - u32 bytes; - - /* - * References to this structure. There is one reference per in-flight - * bio plus one while we're still setting up. - */ - refcount_t refs; - - /* dio_bio came from fs/direct-io.c */ - struct bio *dio_bio; - - /* Array of checksums */ - u8 csums[]; -}; +/* + * Check if the inode has flags compatible with compression + */ +static inline bool btrfs_inode_can_compress(const struct btrfs_inode *inode) +{ + if (inode->flags & BTRFS_INODE_NODATACOW || + inode->flags & BTRFS_INODE_NODATASUM) + return false; + return true; +} /* * btrfs_inode_item stores flags in a u64, btrfs_inode stores them in two diff --git a/fs/btrfs/check-integrity.c b/fs/btrfs/check-integrity.c index abac86a75840..5d20137b7b67 100644 --- a/fs/btrfs/check-integrity.c +++ b/fs/btrfs/check-integrity.c @@ -1552,21 +1552,18 @@ static int btrfsic_read_block(struct btrfsic_state *state, return -ENOMEM; block_ctx->datav = block_ctx->mem_to_free; block_ctx->pagev = (struct page **)(block_ctx->datav + num_pages); - for (i = 0; i < num_pages; i++) { - block_ctx->pagev[i] = alloc_page(GFP_NOFS); - if (!block_ctx->pagev[i]) - return -1; - } + ret = btrfs_alloc_page_array(num_pages, block_ctx->pagev); + if (ret) + return ret; dev_bytenr = block_ctx->dev_bytenr; for (i = 0; i < num_pages;) { struct bio *bio; unsigned int j; - bio = btrfs_bio_alloc(num_pages - i); - bio_set_dev(bio, block_ctx->dev->bdev); + bio = bio_alloc(block_ctx->dev->bdev, num_pages - i, + REQ_OP_READ, GFP_NOFS); bio->bi_iter.bi_sector = dev_bytenr >> 9; - bio->bi_opf = REQ_OP_READ; for (j = i; j < num_pages; j++) { ret = bio_add_page(bio, block_ctx->pagev[j], @@ -2033,7 +2030,7 @@ continue_loop: static void btrfsic_bio_end_io(struct bio *bp) { - struct btrfsic_block *block = (struct btrfsic_block *)bp->bi_private; + struct btrfsic_block *block = bp->bi_private; int iodone_w_error; /* mutex is not held! This is not save if IO is not yet completed @@ -2635,100 +2632,93 @@ static struct btrfsic_dev_state *btrfsic_dev_state_lookup(dev_t dev) &btrfsic_dev_state_hashtable); } -static void __btrfsic_submit_bio(struct bio *bio) +static void btrfsic_check_write_bio(struct bio *bio, struct btrfsic_dev_state *dev_state) { - struct btrfsic_dev_state *dev_state; + unsigned int segs = bio_segments(bio); + u64 dev_bytenr = 512 * bio->bi_iter.bi_sector; + u64 cur_bytenr = dev_bytenr; + struct bvec_iter iter; + struct bio_vec bvec; + char **mapped_datav; + int bio_is_patched = 0; + int i = 0; + + if (dev_state->state->print_mask & BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH) + pr_info( +"submit_bio(rw=%d,0x%x, bi_vcnt=%u, bi_sector=%llu (bytenr %llu), bi_bdev=%p)\n", + bio_op(bio), bio->bi_opf, segs, + bio->bi_iter.bi_sector, dev_bytenr, bio->bi_bdev); - if (!btrfsic_is_initialized) + mapped_datav = kmalloc_array(segs, sizeof(*mapped_datav), GFP_NOFS); + if (!mapped_datav) return; - mutex_lock(&btrfsic_mutex); - /* since btrfsic_submit_bio() is also called before - * btrfsic_mount(), this might return NULL */ - dev_state = btrfsic_dev_state_lookup(bio->bi_bdev->bd_dev); - if (NULL != dev_state && - (bio_op(bio) == REQ_OP_WRITE) && bio_has_data(bio)) { - int i = 0; - u64 dev_bytenr; - u64 cur_bytenr; - struct bio_vec bvec; - struct bvec_iter iter; - int bio_is_patched; - char **mapped_datav; - unsigned int segs = bio_segments(bio); - - dev_bytenr = 512 * bio->bi_iter.bi_sector; - bio_is_patched = 0; - if (dev_state->state->print_mask & - BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH) - pr_info("submit_bio(rw=%d,0x%x, bi_vcnt=%u, bi_sector=%llu (bytenr %llu), bi_bdev=%p)\n", - bio_op(bio), bio->bi_opf, segs, - bio->bi_iter.bi_sector, dev_bytenr, bio->bi_bdev); - - mapped_datav = kmalloc_array(segs, - sizeof(*mapped_datav), GFP_NOFS); - if (!mapped_datav) - goto leave; - cur_bytenr = dev_bytenr; - - bio_for_each_segment(bvec, bio, iter) { - BUG_ON(bvec.bv_len != PAGE_SIZE); - mapped_datav[i] = page_address(bvec.bv_page); - i++; - - if (dev_state->state->print_mask & - BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH_VERBOSE) - pr_info("#%u: bytenr=%llu, len=%u, offset=%u\n", - i, cur_bytenr, bvec.bv_len, bvec.bv_offset); - cur_bytenr += bvec.bv_len; - } - btrfsic_process_written_block(dev_state, dev_bytenr, - mapped_datav, segs, - bio, &bio_is_patched, - bio->bi_opf); - kfree(mapped_datav); - } else if (NULL != dev_state && (bio->bi_opf & REQ_PREFLUSH)) { - if (dev_state->state->print_mask & - BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH) - pr_info("submit_bio(rw=%d,0x%x FLUSH, bdev=%p)\n", - bio_op(bio), bio->bi_opf, bio->bi_bdev); - if (!dev_state->dummy_block_for_bio_bh_flush.is_iodone) { - if ((dev_state->state->print_mask & - (BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH | - BTRFSIC_PRINT_MASK_VERBOSE))) - pr_info( -"btrfsic_submit_bio(%pg) with FLUSH but dummy block already in use (ignored)!\n", - dev_state->bdev); - } else { - struct btrfsic_block *const block = - &dev_state->dummy_block_for_bio_bh_flush; + bio_for_each_segment(bvec, bio, iter) { + BUG_ON(bvec.bv_len != PAGE_SIZE); + mapped_datav[i] = page_address(bvec.bv_page); + i++; - block->is_iodone = 0; - block->never_written = 0; - block->iodone_w_error = 0; - block->flush_gen = dev_state->last_flush_gen + 1; - block->submit_bio_bh_rw = bio->bi_opf; - block->orig_bio_private = bio->bi_private; - block->orig_bio_end_io = bio->bi_end_io; - block->next_in_same_bio = NULL; - bio->bi_private = block; - bio->bi_end_io = btrfsic_bio_end_io; - } + if (dev_state->state->print_mask & + BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH_VERBOSE) + pr_info("#%u: bytenr=%llu, len=%u, offset=%u\n", + i, cur_bytenr, bvec.bv_len, bvec.bv_offset); + cur_bytenr += bvec.bv_len; } -leave: - mutex_unlock(&btrfsic_mutex); + + btrfsic_process_written_block(dev_state, dev_bytenr, mapped_datav, segs, + bio, &bio_is_patched, bio->bi_opf); + kfree(mapped_datav); } -void btrfsic_submit_bio(struct bio *bio) +static void btrfsic_check_flush_bio(struct bio *bio, struct btrfsic_dev_state *dev_state) { - __btrfsic_submit_bio(bio); - submit_bio(bio); + if (dev_state->state->print_mask & BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH) + pr_info("submit_bio(rw=%d,0x%x FLUSH, bdev=%p)\n", + bio_op(bio), bio->bi_opf, bio->bi_bdev); + + if (dev_state->dummy_block_for_bio_bh_flush.is_iodone) { + struct btrfsic_block *const block = + &dev_state->dummy_block_for_bio_bh_flush; + + block->is_iodone = 0; + block->never_written = 0; + block->iodone_w_error = 0; + block->flush_gen = dev_state->last_flush_gen + 1; + block->submit_bio_bh_rw = bio->bi_opf; + block->orig_bio_private = bio->bi_private; + block->orig_bio_end_io = bio->bi_end_io; + block->next_in_same_bio = NULL; + bio->bi_private = block; + bio->bi_end_io = btrfsic_bio_end_io; + } else if ((dev_state->state->print_mask & + (BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH | + BTRFSIC_PRINT_MASK_VERBOSE))) { + pr_info( +"btrfsic_submit_bio(%pg) with FLUSH but dummy block already in use (ignored)!\n", + dev_state->bdev); + } } -int btrfsic_submit_bio_wait(struct bio *bio) +void btrfsic_check_bio(struct bio *bio) { - __btrfsic_submit_bio(bio); - return submit_bio_wait(bio); + struct btrfsic_dev_state *dev_state; + + if (!btrfsic_is_initialized) + return; + + /* + * We can be called before btrfsic_mount, so there might not be a + * dev_state. + */ + dev_state = btrfsic_dev_state_lookup(bio->bi_bdev->bd_dev); + mutex_lock(&btrfsic_mutex); + if (dev_state) { + if (bio_op(bio) == REQ_OP_WRITE && bio_has_data(bio)) + btrfsic_check_write_bio(bio, dev_state); + else if (bio->bi_opf & REQ_PREFLUSH) + btrfsic_check_flush_bio(bio, dev_state); + } + mutex_unlock(&btrfsic_mutex); } int btrfsic_mount(struct btrfs_fs_info *fs_info, diff --git a/fs/btrfs/check-integrity.h b/fs/btrfs/check-integrity.h index bcc730a06cb5..e4c8aed7996f 100644 --- a/fs/btrfs/check-integrity.h +++ b/fs/btrfs/check-integrity.h @@ -7,11 +7,9 @@ #define BTRFS_CHECK_INTEGRITY_H #ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY -void btrfsic_submit_bio(struct bio *bio); -int btrfsic_submit_bio_wait(struct bio *bio); +void btrfsic_check_bio(struct bio *bio); #else -#define btrfsic_submit_bio submit_bio -#define btrfsic_submit_bio_wait submit_bio_wait +static inline void btrfsic_check_bio(struct bio *bio) { } #endif int btrfsic_mount(struct btrfs_fs_info *fs_info, diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index be476f094300..f4564f32f6d9 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -425,7 +425,6 @@ out: } static blk_status_t submit_compressed_bio(struct btrfs_fs_info *fs_info, - struct compressed_bio *cb, struct bio *bio, int mirror_num) { blk_status_t ret; @@ -537,6 +536,9 @@ blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start, cb->orig_bio = NULL; cb->nr_pages = nr_pages; + if (blkcg_css) + kthread_associate_blkcg(blkcg_css); + while (cur_disk_bytenr < disk_start + compressed_len) { u64 offset = cur_disk_bytenr - disk_start; unsigned int index = offset >> PAGE_SHIFT; @@ -555,6 +557,8 @@ blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start, bio = NULL; goto finish_cb; } + if (blkcg_css) + bio->bi_opf |= REQ_CGROUP_PUNT; } /* * We should never reach next_stripe_start start as we will @@ -599,7 +603,7 @@ blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start, goto finish_cb; } - ret = submit_compressed_bio(fs_info, cb, bio, 0); + ret = submit_compressed_bio(fs_info, bio, 0); if (ret) goto finish_cb; bio = NULL; @@ -612,6 +616,9 @@ blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start, return 0; finish_cb: + if (blkcg_css) + kthread_associate_blkcg(NULL); + if (bio) { bio->bi_status = ret; bio_endio(bio); @@ -794,15 +801,13 @@ static noinline int add_ra_bio_pages(struct inode *inode, * After the compressed pages are read, we copy the bytes into the * bio we were passed and then call the bio end_io calls */ -blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, - int mirror_num, unsigned long bio_flags) +void btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, + int mirror_num) { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct extent_map_tree *em_tree; struct compressed_bio *cb; unsigned int compressed_len; - unsigned int nr_pages; - unsigned int pg_index; struct bio *comp_bio = NULL; const u64 disk_bytenr = bio->bi_iter.bi_sector << SECTOR_SHIFT; u64 cur_disk_byte = disk_bytenr; @@ -812,7 +817,8 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, u64 em_start; struct extent_map *em; blk_status_t ret; - int faili = 0; + int ret2; + int i; u8 *sums; em_tree = &BTRFS_I(inode)->extent_tree; @@ -847,32 +853,26 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, em_len = em->len; em_start = em->start; - free_extent_map(em); - em = NULL; - cb->len = bio->bi_iter.bi_size; cb->compressed_len = compressed_len; - cb->compress_type = extent_compress_type(bio_flags); + cb->compress_type = em->compress_type; cb->orig_bio = bio; - nr_pages = DIV_ROUND_UP(compressed_len, PAGE_SIZE); - cb->compressed_pages = kcalloc(nr_pages, sizeof(struct page *), - GFP_NOFS); + free_extent_map(em); + em = NULL; + + cb->nr_pages = DIV_ROUND_UP(compressed_len, PAGE_SIZE); + cb->compressed_pages = kcalloc(cb->nr_pages, sizeof(struct page *), GFP_NOFS); if (!cb->compressed_pages) { ret = BLK_STS_RESOURCE; - goto fail1; + goto fail; } - for (pg_index = 0; pg_index < nr_pages; pg_index++) { - cb->compressed_pages[pg_index] = alloc_page(GFP_NOFS); - if (!cb->compressed_pages[pg_index]) { - faili = pg_index - 1; - ret = BLK_STS_RESOURCE; - goto fail2; - } + ret2 = btrfs_alloc_page_array(cb->nr_pages, cb->compressed_pages); + if (ret2) { + ret = BLK_STS_RESOURCE; + goto fail; } - faili = nr_pages - 1; - cb->nr_pages = nr_pages; add_ra_bio_pages(inode, em_start + em_len, cb); @@ -941,28 +941,29 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, fs_info->sectorsize); sums += fs_info->csum_size * nr_sectors; - ret = submit_compressed_bio(fs_info, cb, comp_bio, mirror_num); + ret = submit_compressed_bio(fs_info, comp_bio, mirror_num); if (ret) goto finish_cb; comp_bio = NULL; } } - return BLK_STS_OK; + return; -fail2: - while (faili >= 0) { - __free_page(cb->compressed_pages[faili]); - faili--; +fail: + if (cb->compressed_pages) { + for (i = 0; i < cb->nr_pages; i++) { + if (cb->compressed_pages[i]) + __free_page(cb->compressed_pages[i]); + } } kfree(cb->compressed_pages); -fail1: kfree(cb); out: free_extent_map(em); bio->bi_status = ret; bio_endio(bio); - return ret; + return; finish_cb: if (comp_bio) { comp_bio->bi_status = ret; @@ -970,7 +971,7 @@ finish_cb: } /* All bytes of @cb is submitted, endio will free @cb */ if (cur_disk_byte == disk_bytenr + compressed_len) - return ret; + return; wait_var_event(cb, refcount_read(&cb->pending_sectors) == (disk_bytenr + compressed_len - cur_disk_byte) >> @@ -982,7 +983,6 @@ finish_cb: ASSERT(refcount_read(&cb->pending_sectors)); /* Now we are the only one referring @cb, can finish it safely. */ finish_compressed_bio_read(cb); - return ret; } /* diff --git a/fs/btrfs/compression.h b/fs/btrfs/compression.h index ac5b20731d2a..2707404389a5 100644 --- a/fs/btrfs/compression.h +++ b/fs/btrfs/compression.h @@ -102,8 +102,8 @@ blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start, unsigned int write_flags, struct cgroup_subsys_state *blkcg_css, bool writeback); -blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, - int mirror_num, unsigned long bio_flags); +void btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, + int mirror_num); unsigned int btrfs_compress_str2level(unsigned int type, const char *str); diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 0eecf98d0abb..6e556031a8f3 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -16,6 +16,7 @@ #include "volumes.h" #include "qgroup.h" #include "tree-mod-log.h" +#include "tree-checker.h" static int split_node(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, int level); @@ -342,7 +343,7 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans, int level = btrfs_header_level(buf); ret = btrfs_set_disk_extent_flags(trans, buf, - new_flags, level, 0); + new_flags, level); if (ret) return ret; } @@ -1390,12 +1391,13 @@ static noinline void unlock_up(struct btrfs_path *path, int level, } /* - * helper function for btrfs_search_slot. The goal is to find a block - * in cache without setting the path to blocking. If we find the block - * we return zero and the path is unchanged. + * Helper function for btrfs_search_slot() and other functions that do a search + * on a btree. The goal is to find a tree block in the cache (the radix tree at + * fs_info->buffer_radix), but if we can't find it, or it's not up to date, read + * its pages from disk. * - * If we can't find the block, we set the path blocking and do some - * reada. -EAGAIN is returned and the search must be repeated. + * Returns -EAGAIN, with the path unlocked, if the caller needs to repeat the + * whole btree search, starting again from the current root node. */ static int read_block_for_search(struct btrfs_root *root, struct btrfs_path *p, @@ -1409,12 +1411,21 @@ read_block_for_search(struct btrfs_root *root, struct btrfs_path *p, struct btrfs_key first_key; int ret; int parent_level; + bool unlock_up; + unlock_up = ((level + 1 < BTRFS_MAX_LEVEL) && p->locks[level + 1]); blocknr = btrfs_node_blockptr(*eb_ret, slot); gen = btrfs_node_ptr_generation(*eb_ret, slot); parent_level = btrfs_header_level(*eb_ret); btrfs_node_key_to_cpu(*eb_ret, &first_key, slot); + /* + * If we need to read an extent buffer from disk and we are holding locks + * on upper level nodes, we unlock all the upper nodes before reading the + * extent buffer, and then return -EAGAIN to the caller as it needs to + * restart the search. We don't release the lock on the current level + * because we need to walk this node to figure out which blocks to read. + */ tmp = find_extent_buffer(fs_info, blocknr); if (tmp) { if (p->reada == READA_FORWARD_ALWAYS) @@ -1436,30 +1447,38 @@ read_block_for_search(struct btrfs_root *root, struct btrfs_path *p, return 0; } + if (unlock_up) + btrfs_unlock_up_safe(p, level + 1); + /* now we're allowed to do a blocking uptodate check */ - ret = btrfs_read_buffer(tmp, gen, parent_level - 1, &first_key); + ret = btrfs_read_extent_buffer(tmp, gen, parent_level - 1, &first_key); if (ret) { free_extent_buffer(tmp); btrfs_release_path(p); return -EIO; } - *eb_ret = tmp; - return 0; + if (btrfs_check_eb_owner(tmp, root->root_key.objectid)) { + free_extent_buffer(tmp); + btrfs_release_path(p); + return -EUCLEAN; + } + + if (unlock_up) + ret = -EAGAIN; + + goto out; } - /* - * reduce lock contention at high levels - * of the btree by dropping locks before - * we read. Don't release the lock on the current - * level because we need to walk this node to figure - * out which blocks to read. - */ - btrfs_unlock_up_safe(p, level + 1); + if (unlock_up) { + btrfs_unlock_up_safe(p, level + 1); + ret = -EAGAIN; + } else { + ret = 0; + } if (p->reada != READA_NONE) reada_for_search(fs_info, p, level, slot, key->objectid); - ret = -EAGAIN; tmp = read_tree_block(fs_info, blocknr, root->root_key.objectid, gen, parent_level - 1, &first_key); if (IS_ERR(tmp)) { @@ -1474,9 +1493,15 @@ read_block_for_search(struct btrfs_root *root, struct btrfs_path *p, */ if (!extent_buffer_uptodate(tmp)) ret = -EIO; - free_extent_buffer(tmp); - btrfs_release_path(p); +out: + if (ret == 0) { + *eb_ret = tmp; + } else { + free_extent_buffer(tmp); + btrfs_release_path(p); + } + return ret; } @@ -2279,6 +2304,43 @@ int btrfs_search_backwards(struct btrfs_root *root, struct btrfs_key *key, return ret; } +/** + * Search for a valid slot for the given path. + * + * @root: The root node of the tree. + * @key: Will contain a valid item if found. + * @path: The starting point to validate the slot. + * + * Return: 0 if the item is valid + * 1 if not found + * <0 if error. + */ +int btrfs_get_next_valid_item(struct btrfs_root *root, struct btrfs_key *key, + struct btrfs_path *path) +{ + while (1) { + int ret; + const int slot = path->slots[0]; + const struct extent_buffer *leaf = path->nodes[0]; + + /* This is where we start walking the path. */ + if (slot >= btrfs_header_nritems(leaf)) { + /* + * If we've reached the last slot in this leaf we need + * to go to the next leaf and reset the path. + */ + ret = btrfs_next_leaf(root, path); + if (ret) + return ret; + continue; + } + /* Store the found, valid item in @key. */ + btrfs_item_key_to_cpu(leaf, key, slot); + break; + } + return 0; +} + /* * adjust the pointers going up the tree, starting at level * making sure the right key of each node is points to 'key'. diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index b7631b88426e..0e49b1a0c071 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -675,13 +675,13 @@ struct btrfs_fs_info { rwlock_t global_root_lock; struct rb_root global_root_tree; - spinlock_t fs_roots_radix_lock; - struct radix_tree_root fs_roots_radix; + /* The xarray that holds all the FS roots */ + spinlock_t fs_roots_lock; + struct xarray fs_roots; /* block group cache stuff */ - spinlock_t block_group_cache_lock; - u64 first_logical_byte; - struct rb_root block_group_cache_tree; + rwlock_t block_group_cache_lock; + struct rb_root_cached block_group_cache_tree; /* keep track of unallocated space */ atomic64_t free_chunk_space; @@ -848,12 +848,13 @@ struct btrfs_fs_info { * two */ struct btrfs_workqueue *workers; + struct btrfs_workqueue *hipri_workers; struct btrfs_workqueue *delalloc_workers; struct btrfs_workqueue *flush_workers; struct btrfs_workqueue *endio_workers; struct btrfs_workqueue *endio_meta_workers; struct btrfs_workqueue *endio_raid56_workers; - struct btrfs_workqueue *rmw_workers; + struct workqueue_struct *rmw_workers; struct btrfs_workqueue *endio_meta_write_workers; struct btrfs_workqueue *endio_write_workers; struct btrfs_workqueue *endio_freespace_worker; @@ -946,9 +947,9 @@ struct btrfs_fs_info { * running. */ refcount_t scrub_workers_refcnt; - struct btrfs_workqueue *scrub_workers; - struct btrfs_workqueue *scrub_wr_completion_workers; - struct btrfs_workqueue *scrub_parity_workers; + struct workqueue_struct *scrub_workers; + struct workqueue_struct *scrub_wr_completion_workers; + struct workqueue_struct *scrub_parity_workers; struct btrfs_subpage_info *subpage_info; struct btrfs_discard_ctl discard_ctl; @@ -994,10 +995,10 @@ struct btrfs_fs_info { struct btrfs_delayed_root *delayed_root; - /* Extent buffer radix tree */ + /* Extent buffer xarray */ spinlock_t buffer_lock; /* Entries are eb->start / sectorsize */ - struct radix_tree_root buffer_radix; + struct xarray extent_buffers; /* next backup root to be overwritten */ int backup_root_index; @@ -1045,10 +1046,7 @@ struct btrfs_fs_info { * Zone size > 0 when in ZONED mode, otherwise it's used for a check * if the mode is enabled */ - union { - u64 zone_size; - u64 zoned; - }; + u64 zone_size; struct mutex zoned_meta_io_lock; spinlock_t treelog_bg_lock; @@ -1060,6 +1058,7 @@ struct btrfs_fs_info { */ spinlock_t relocation_bg_lock; u64 data_reloc_bg; + struct mutex zoned_data_reloc_io_lock; u64 nr_global_roots; @@ -1120,7 +1119,8 @@ enum { */ BTRFS_ROOT_SHAREABLE, BTRFS_ROOT_TRACK_DIRTY, - BTRFS_ROOT_IN_RADIX, + /* The root is tracked in fs_info::fs_roots */ + BTRFS_ROOT_REGISTERED, BTRFS_ROOT_ORPHAN_ITEM_INSERTED, BTRFS_ROOT_DEFRAG_RUNNING, BTRFS_ROOT_FORCE_COW, @@ -1224,10 +1224,10 @@ struct btrfs_root { struct rb_root inode_tree; /* - * radix tree that keeps track of delayed nodes of every inode, - * protected by inode_lock + * Xarray that keeps track of delayed nodes of every inode, protected + * by inode_lock */ - struct radix_tree_root delayed_nodes_tree; + struct xarray delayed_nodes; /* * right now this just gets used so that a root has its own devid * for stat. It may be used for more later @@ -2783,7 +2783,8 @@ int btrfs_pin_extent_for_log_replay(struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes); int btrfs_exclude_logged_extents(struct extent_buffer *eb); int btrfs_cross_ref_exist(struct btrfs_root *root, - u64 objectid, u64 offset, u64 bytenr, bool strict); + u64 objectid, u64 offset, u64 bytenr, bool strict, + struct btrfs_path *path); struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 parent, u64 root_objectid, @@ -2810,8 +2811,7 @@ int btrfs_inc_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root, int btrfs_dec_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *buf, int full_backref); int btrfs_set_disk_extent_flags(struct btrfs_trans_handle *trans, - struct extent_buffer *eb, u64 flags, - int level, int is_data); + struct extent_buffer *eb, u64 flags, int level); int btrfs_free_extent(struct btrfs_trans_handle *trans, struct btrfs_ref *ref); int btrfs_free_reserved_extent(struct btrfs_fs_info *fs_info, @@ -2891,7 +2891,7 @@ void btrfs_subvolume_release_metadata(struct btrfs_root *root, void btrfs_delalloc_release_extents(struct btrfs_inode *inode, u64 num_bytes); int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes, - u64 disk_num_bytes); + u64 disk_num_bytes, bool noflush); u64 btrfs_account_ro_block_groups_free_space(struct btrfs_space_info *sinfo); int btrfs_error_unpin_extent_range(struct btrfs_fs_info *fs_info, u64 start, u64 end); @@ -3038,6 +3038,35 @@ int btrfs_next_old_leaf(struct btrfs_root *root, struct btrfs_path *path, int btrfs_search_backwards(struct btrfs_root *root, struct btrfs_key *key, struct btrfs_path *path); +int btrfs_get_next_valid_item(struct btrfs_root *root, struct btrfs_key *key, + struct btrfs_path *path); + +/* + * Search in @root for a given @key, and store the slot found in @found_key. + * + * @root: The root node of the tree. + * @key: The key we are looking for. + * @found_key: Will hold the found item. + * @path: Holds the current slot/leaf. + * @iter_ret: Contains the value returned from btrfs_search_slot or + * btrfs_get_next_valid_item, whichever was executed last. + * + * The @iter_ret is an output variable that will contain the return value of + * btrfs_search_slot, if it encountered an error, or the value returned from + * btrfs_get_next_valid_item otherwise. That return value can be 0, if a valid + * slot was found, 1 if there were no more leaves, and <0 if there was an error. + * + * It's recommended to use a separate variable for iter_ret and then use it to + * set the function return value so there's no confusion of the 0/1/errno + * values stemming from btrfs_search_slot. + */ +#define btrfs_for_each_slot(root, key, found_key, path, iter_ret) \ + for (iter_ret = btrfs_search_slot(NULL, (root), (key), (path), 0, 0); \ + (iter_ret) >= 0 && \ + (iter_ret = btrfs_get_next_valid_item((root), (found_key), (path))) == 0; \ + (path)->slots[0]++ \ + ) + static inline int btrfs_next_old_item(struct btrfs_root *root, struct btrfs_path *p, u64 time_seq) { @@ -3189,7 +3218,6 @@ int btrfs_del_orphan_item(struct btrfs_trans_handle *trans, int btrfs_find_orphan_item(struct btrfs_root *root, u64 offset); /* file-item.c */ -struct btrfs_dio_private; int btrfs_del_csums(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 bytenr, u64 len); blk_status_t btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio, u8 *dst); @@ -3223,8 +3251,8 @@ void btrfs_inode_safe_disk_i_size_write(struct btrfs_inode *inode, u64 new_i_siz u64 btrfs_file_extent_end(const struct btrfs_path *path); /* inode.c */ -blk_status_t btrfs_submit_data_bio(struct inode *inode, struct bio *bio, - int mirror_num, unsigned long bio_flags); +void btrfs_submit_data_bio(struct inode *inode, struct bio *bio, + int mirror_num, enum btrfs_compression_type compress_type); unsigned int btrfs_verify_data_csum(struct btrfs_bio *bbio, u32 bio_offset, struct page *page, u64 start, u64 end); @@ -3254,10 +3282,28 @@ int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, long nr, int btrfs_set_extent_delalloc(struct btrfs_inode *inode, u64 start, u64 end, unsigned int extra_bits, struct extent_state **cached_state); -int btrfs_create_subvol_root(struct btrfs_trans_handle *trans, - struct btrfs_root *new_root, - struct btrfs_root *parent_root, - struct user_namespace *mnt_userns); +struct btrfs_new_inode_args { + /* Input */ + struct inode *dir; + struct dentry *dentry; + struct inode *inode; + bool orphan; + bool subvol; + + /* + * Output from btrfs_new_inode_prepare(), input to + * btrfs_create_new_inode(). + */ + struct posix_acl *default_acl; + struct posix_acl *acl; +}; +int btrfs_new_inode_prepare(struct btrfs_new_inode_args *args, + unsigned int *trans_num_items); +int btrfs_create_new_inode(struct btrfs_trans_handle *trans, + struct btrfs_new_inode_args *args); +void btrfs_new_inode_args_destroy(struct btrfs_new_inode_args *args); +struct inode *btrfs_new_subvol_inode(struct user_namespace *mnt_userns, + struct inode *dir); void btrfs_set_delalloc_extent(struct inode *inode, struct extent_state *state, unsigned *bits); void btrfs_clear_delalloc_extent(struct inode *inode, @@ -3268,7 +3314,6 @@ void btrfs_split_delalloc_extent(struct inode *inode, struct extent_state *orig, u64 split); void btrfs_set_range_writeback(struct btrfs_inode *inode, u64 start, u64 end); vm_fault_t btrfs_page_mkwrite(struct vm_fault *vmf); -int btrfs_readpage(struct file *file, struct page *page); void btrfs_evict_inode(struct inode *inode); int btrfs_write_inode(struct inode *inode, struct writeback_control *wbc); struct inode *btrfs_alloc_inode(struct super_block *sb); @@ -3313,9 +3358,9 @@ ssize_t btrfs_encoded_read(struct kiocb *iocb, struct iov_iter *iter, ssize_t btrfs_do_encoded_write(struct kiocb *iocb, struct iov_iter *from, const struct btrfs_ioctl_encoded_io_args *encoded); +ssize_t btrfs_dio_rw(struct kiocb *iocb, struct iov_iter *iter, size_t done_before); + extern const struct dentry_operations btrfs_dentry_operations; -extern const struct iomap_ops btrfs_dio_iomap_ops; -extern const struct iomap_dio_ops btrfs_dio_ops; /* Inode locking type flags, by default the exclusive lock is taken */ #define BTRFS_ILOCK_SHARED (1U << 0) @@ -3327,6 +3372,7 @@ void btrfs_inode_unlock(struct inode *inode, unsigned int ilock_flags); void btrfs_update_inode_bytes(struct btrfs_inode *inode, const u64 add_bytes, const u64 del_bytes); +void btrfs_assert_inode_range_clean(struct btrfs_inode *inode, u64 start, u64 end); /* ioctl.c */ long btrfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg); @@ -3402,11 +3448,29 @@ void btrfs_no_printk(const struct btrfs_fs_info *fs_info, const char *fmt, ...) { } -#ifdef CONFIG_PRINTK +#ifdef CONFIG_PRINTK_INDEX + +#define btrfs_printk(fs_info, fmt, args...) \ +do { \ + printk_index_subsys_emit("%sBTRFS %s (device %s): ", NULL, fmt); \ + _btrfs_printk(fs_info, fmt, ##args); \ +} while (0) + __printf(2, 3) __cold -void btrfs_printk(const struct btrfs_fs_info *fs_info, const char *fmt, ...); +void _btrfs_printk(const struct btrfs_fs_info *fs_info, const char *fmt, ...); + +#elif defined(CONFIG_PRINTK) + +#define btrfs_printk(fs_info, fmt, args...) \ + _btrfs_printk(fs_info, fmt, ##args) + +__printf(2, 3) +__cold +void _btrfs_printk(const struct btrfs_fs_info *fs_info, const char *fmt, ...); + #else + #define btrfs_printk(fs_info, fmt, args...) \ btrfs_no_printk(fs_info, fmt, ##args) #endif @@ -3657,12 +3721,25 @@ do { \ __LINE__, (errno)); \ } while (0) +#ifdef CONFIG_PRINTK_INDEX + #define btrfs_handle_fs_error(fs_info, errno, fmt, args...) \ -do { \ - __btrfs_handle_fs_error((fs_info), __func__, __LINE__, \ - (errno), fmt, ##args); \ +do { \ + printk_index_subsys_emit( \ + "BTRFS: error (device %s%s) in %s:%d: errno=%d %s", \ + KERN_CRIT, fmt); \ + __btrfs_handle_fs_error((fs_info), __func__, __LINE__, \ + (errno), fmt, ##args); \ } while (0) +#else + +#define btrfs_handle_fs_error(fs_info, errno, fmt, args...) \ + __btrfs_handle_fs_error((fs_info), __func__, __LINE__, \ + (errno), fmt, ##args) + +#endif + #define BTRFS_FS_ERROR(fs_info) (unlikely(test_bit(BTRFS_FS_STATE_ERROR, \ &(fs_info)->fs_state))) #define BTRFS_FS_LOG_CLEANUP_ERROR(fs_info) \ @@ -3815,15 +3892,16 @@ static inline int __btrfs_fs_compat_ro(struct btrfs_fs_info *fs_info, u64 flag) struct posix_acl *btrfs_get_acl(struct inode *inode, int type, bool rcu); int btrfs_set_acl(struct user_namespace *mnt_userns, struct inode *inode, struct posix_acl *acl, int type); -int btrfs_init_acl(struct btrfs_trans_handle *trans, - struct inode *inode, struct inode *dir); +int __btrfs_set_acl(struct btrfs_trans_handle *trans, struct inode *inode, + struct posix_acl *acl, int type); #else #define btrfs_get_acl NULL #define btrfs_set_acl NULL -static inline int btrfs_init_acl(struct btrfs_trans_handle *trans, - struct inode *inode, struct inode *dir) +static inline int __btrfs_set_acl(struct btrfs_trans_handle *trans, + struct inode *inode, struct posix_acl *acl, + int type) { - return 0; + return -EOPNOTSUPP; } #endif @@ -3928,7 +4006,7 @@ static inline int btrfs_is_testing(struct btrfs_fs_info *fs_info) static inline bool btrfs_is_zoned(const struct btrfs_fs_info *fs_info) { - return fs_info->zoned != 0; + return fs_info->zone_size > 0; } static inline bool btrfs_is_data_reloc_root(const struct btrfs_root *root) diff --git a/fs/btrfs/delalloc-space.c b/fs/btrfs/delalloc-space.c index bd8267c4687d..36ab0859a263 100644 --- a/fs/btrfs/delalloc-space.c +++ b/fs/btrfs/delalloc-space.c @@ -289,7 +289,7 @@ static void calc_inode_reservations(struct btrfs_fs_info *fs_info, } int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes, - u64 disk_num_bytes) + u64 disk_num_bytes, bool noflush) { struct btrfs_root *root = inode->root; struct btrfs_fs_info *fs_info = root->fs_info; @@ -308,7 +308,7 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes, * If we have a transaction open (can happen if we call truncate_block * from truncate), then we need FLUSH_LIMIT so we don't deadlock. */ - if (btrfs_is_free_space_inode(inode)) { + if (noflush || btrfs_is_free_space_inode(inode)) { flush = BTRFS_RESERVE_NO_FLUSH; } else { if (current->journal_info) @@ -333,7 +333,8 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes, */ calc_inode_reservations(fs_info, num_bytes, disk_num_bytes, &meta_reserve, &qgroup_reserve); - ret = btrfs_qgroup_reserve_meta_prealloc(root, qgroup_reserve, true); + ret = btrfs_qgroup_reserve_meta_prealloc(root, qgroup_reserve, true, + noflush); if (ret) return ret; ret = btrfs_reserve_metadata_bytes(fs_info, block_rsv, meta_reserve, flush); @@ -456,7 +457,7 @@ int btrfs_delalloc_reserve_space(struct btrfs_inode *inode, ret = btrfs_check_data_free_space(inode, reserved, start, len); if (ret < 0) return ret; - ret = btrfs_delalloc_reserve_metadata(inode, len, len); + ret = btrfs_delalloc_reserve_metadata(inode, len, len, false); if (ret < 0) { btrfs_free_reserved_data_space(inode, *reserved, start, len); extent_changeset_free(*reserved); diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index 748bf6b0d860..66779ab3ed4a 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -78,7 +78,7 @@ static struct btrfs_delayed_node *btrfs_get_delayed_node( } spin_lock(&root->inode_lock); - node = radix_tree_lookup(&root->delayed_nodes_tree, ino); + node = xa_load(&root->delayed_nodes, ino); if (node) { if (btrfs_inode->delayed_node) { @@ -90,9 +90,9 @@ static struct btrfs_delayed_node *btrfs_get_delayed_node( /* * It's possible that we're racing into the middle of removing - * this node from the radix tree. In this case, the refcount + * this node from the xarray. In this case, the refcount * was zero and it should never go back to one. Just return - * NULL like it was never in the radix at all; our release + * NULL like it was never in the xarray at all; our release * function is in the process of removing it. * * Some implementations of refcount_inc refuse to bump the @@ -100,7 +100,7 @@ static struct btrfs_delayed_node *btrfs_get_delayed_node( * here, refcount_inc() may decide to just WARN_ONCE() instead * of actually bumping the refcount. * - * If this node is properly in the radix, we want to bump the + * If this node is properly in the xarray, we want to bump the * refcount twice, once for the inode and once for this get * operation. */ @@ -128,36 +128,30 @@ static struct btrfs_delayed_node *btrfs_get_or_create_delayed_node( u64 ino = btrfs_ino(btrfs_inode); int ret; -again: - node = btrfs_get_delayed_node(btrfs_inode); - if (node) - return node; + do { + node = btrfs_get_delayed_node(btrfs_inode); + if (node) + return node; - node = kmem_cache_zalloc(delayed_node_cache, GFP_NOFS); - if (!node) - return ERR_PTR(-ENOMEM); - btrfs_init_delayed_node(node, root, ino); + node = kmem_cache_zalloc(delayed_node_cache, GFP_NOFS); + if (!node) + return ERR_PTR(-ENOMEM); + btrfs_init_delayed_node(node, root, ino); - /* cached in the btrfs inode and can be accessed */ - refcount_set(&node->refs, 2); + /* Cached in the inode and can be accessed */ + refcount_set(&node->refs, 2); - ret = radix_tree_preload(GFP_NOFS); - if (ret) { - kmem_cache_free(delayed_node_cache, node); - return ERR_PTR(ret); - } - - spin_lock(&root->inode_lock); - ret = radix_tree_insert(&root->delayed_nodes_tree, ino, node); - if (ret == -EEXIST) { - spin_unlock(&root->inode_lock); - kmem_cache_free(delayed_node_cache, node); - radix_tree_preload_end(); - goto again; - } + spin_lock(&root->inode_lock); + ret = xa_insert(&root->delayed_nodes, ino, node, GFP_NOFS); + if (ret) { + spin_unlock(&root->inode_lock); + kmem_cache_free(delayed_node_cache, node); + if (ret != -EBUSY) + return ERR_PTR(ret); + } + } while (ret); btrfs_inode->delayed_node = node; spin_unlock(&root->inode_lock); - radix_tree_preload_end(); return node; } @@ -276,8 +270,7 @@ static void __btrfs_release_delayed_node( * back up. We can delete it now. */ ASSERT(refcount_read(&delayed_node->refs) == 0); - radix_tree_delete(&root->delayed_nodes_tree, - delayed_node->inode_id); + xa_erase(&root->delayed_nodes, delayed_node->inode_id); spin_unlock(&root->inode_lock); kmem_cache_free(delayed_node_cache, delayed_node); } @@ -1870,34 +1863,35 @@ void btrfs_kill_delayed_inode_items(struct btrfs_inode *inode) void btrfs_kill_all_delayed_nodes(struct btrfs_root *root) { - u64 inode_id = 0; + unsigned long index = 0; + struct btrfs_delayed_node *delayed_node; struct btrfs_delayed_node *delayed_nodes[8]; - int i, n; while (1) { + int n = 0; + spin_lock(&root->inode_lock); - n = radix_tree_gang_lookup(&root->delayed_nodes_tree, - (void **)delayed_nodes, inode_id, - ARRAY_SIZE(delayed_nodes)); - if (!n) { + if (xa_empty(&root->delayed_nodes)) { spin_unlock(&root->inode_lock); - break; + return; } - inode_id = delayed_nodes[n - 1]->inode_id + 1; - for (i = 0; i < n; i++) { + xa_for_each_start(&root->delayed_nodes, index, delayed_node, index) { /* * Don't increase refs in case the node is dead and * about to be removed from the tree in the loop below */ - if (!refcount_inc_not_zero(&delayed_nodes[i]->refs)) - delayed_nodes[i] = NULL; + if (refcount_inc_not_zero(&delayed_node->refs)) { + delayed_nodes[n] = delayed_node; + n++; + } + if (n >= ARRAY_SIZE(delayed_nodes)) + break; } + index++; spin_unlock(&root->inode_lock); - for (i = 0; i < n; i++) { - if (!delayed_nodes[i]) - continue; + for (int i = 0; i < n; i++) { __btrfs_kill_delayed_node(delayed_nodes[i]); btrfs_release_delayed_node(delayed_nodes[i]); } diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c index 4176df149d04..99f37fca2e96 100644 --- a/fs/btrfs/delayed-ref.c +++ b/fs/btrfs/delayed-ref.c @@ -930,7 +930,6 @@ int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans, is_system = (generic_ref->tree_ref.owning_root == BTRFS_CHUNK_TREE_OBJECTID); ASSERT(generic_ref->type == BTRFS_REF_METADATA && generic_ref->action); - BUG_ON(extent_op && extent_op->is_data); ref = kmem_cache_alloc(btrfs_delayed_tree_ref_cachep, GFP_NOFS); if (!ref) return -ENOMEM; @@ -1103,8 +1102,7 @@ int btrfs_add_delayed_extent_op(struct btrfs_trans_handle *trans, return -ENOMEM; init_delayed_ref_head(head_ref, NULL, bytenr, num_bytes, 0, 0, - BTRFS_UPDATE_DELAYED_HEAD, extent_op->is_data, - false); + BTRFS_UPDATE_DELAYED_HEAD, false, false); head_ref->extent_op = extent_op; delayed_refs = &trans->transaction->delayed_refs; diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h index 91a3aabad150..d6304b690ec4 100644 --- a/fs/btrfs/delayed-ref.h +++ b/fs/btrfs/delayed-ref.h @@ -58,7 +58,6 @@ struct btrfs_delayed_extent_op { u8 level; bool update_key; bool update_flags; - bool is_data; u64 flags_to_set; }; diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index 71fd99b48283..a7dd6ba25e99 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -474,6 +474,7 @@ static int mark_block_group_to_copy(struct btrfs_fs_info *fs_info, struct btrfs_dev_extent *dev_extent = NULL; struct btrfs_block_group *cache; struct btrfs_trans_handle *trans; + int iter_ret = 0; int ret = 0; u64 chunk_offset; @@ -524,29 +525,8 @@ static int mark_block_group_to_copy(struct btrfs_fs_info *fs_info, key.type = BTRFS_DEV_EXTENT_KEY; key.offset = 0; - ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); - if (ret < 0) - goto free_path; - if (ret > 0) { - if (path->slots[0] >= - btrfs_header_nritems(path->nodes[0])) { - ret = btrfs_next_leaf(root, path); - if (ret < 0) - goto free_path; - if (ret > 0) { - ret = 0; - goto free_path; - } - } else { - ret = 0; - } - } - - while (1) { + btrfs_for_each_slot(root, &key, &found_key, path, iter_ret) { struct extent_buffer *leaf = path->nodes[0]; - int slot = path->slots[0]; - - btrfs_item_key_to_cpu(leaf, &found_key, slot); if (found_key.objectid != src_dev->devid) break; @@ -557,30 +537,23 @@ static int mark_block_group_to_copy(struct btrfs_fs_info *fs_info, if (found_key.offset < key.offset) break; - dev_extent = btrfs_item_ptr(leaf, slot, struct btrfs_dev_extent); + dev_extent = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_dev_extent); chunk_offset = btrfs_dev_extent_chunk_offset(leaf, dev_extent); cache = btrfs_lookup_block_group(fs_info, chunk_offset); if (!cache) - goto skip; + continue; spin_lock(&cache->lock); cache->to_copy = 1; spin_unlock(&cache->lock); btrfs_put_block_group(cache); - -skip: - ret = btrfs_next_item(root, path); - if (ret != 0) { - if (ret > 0) - ret = 0; - break; - } } + if (iter_ret < 0) + ret = iter_ret; -free_path: btrfs_free_path(path); unlock: mutex_unlock(&fs_info->chunk_mutex); @@ -734,7 +707,12 @@ static int btrfs_dev_replace_start(struct btrfs_fs_info *fs_info, btrfs_wait_ordered_roots(fs_info, U64_MAX, 0, (u64)-1); - /* Commit dev_replace state and reserve 1 item for it. */ + /* + * Commit dev_replace state and reserve 1 item for it. + * This is crucial to ensure we won't miss copying extents for new block + * groups that are allocated after we started the device replace, and + * must be done after setting up the device replace state. + */ trans = btrfs_start_transaction(root, 1); if (IS_ERR(trans)) { ret = PTR_ERR(trans); @@ -876,6 +854,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info, int scrub_ret) { struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace; + struct btrfs_fs_devices *fs_devices = fs_info->fs_devices; struct btrfs_device *tgt_device; struct btrfs_device *src_device; struct btrfs_root *root = fs_info->tree_root; @@ -925,12 +904,12 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info, WARN_ON(ret); /* Prevent write_all_supers() during the finishing procedure */ - mutex_lock(&fs_info->fs_devices->device_list_mutex); + mutex_lock(&fs_devices->device_list_mutex); /* Prevent new chunks being allocated on the source device */ mutex_lock(&fs_info->chunk_mutex); if (!list_empty(&src_device->post_commit_list)) { - mutex_unlock(&fs_info->fs_devices->device_list_mutex); + mutex_unlock(&fs_devices->device_list_mutex); mutex_unlock(&fs_info->chunk_mutex); } else { break; @@ -967,7 +946,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info, error: up_write(&dev_replace->rwsem); mutex_unlock(&fs_info->chunk_mutex); - mutex_unlock(&fs_info->fs_devices->device_list_mutex); + mutex_unlock(&fs_devices->device_list_mutex); btrfs_rm_dev_replace_blocked(fs_info); if (tgt_device) btrfs_destroy_dev_replace_tgtdev(tgt_device); @@ -996,8 +975,8 @@ error: btrfs_assign_next_active_device(src_device, tgt_device); - list_add(&tgt_device->dev_alloc_list, &fs_info->fs_devices->alloc_list); - fs_info->fs_devices->rw_devices++; + list_add(&tgt_device->dev_alloc_list, &fs_devices->alloc_list); + fs_devices->rw_devices++; up_write(&dev_replace->rwsem); btrfs_rm_dev_replace_blocked(fs_info); @@ -1020,7 +999,7 @@ error: * belong to this filesystem. */ mutex_unlock(&fs_info->chunk_mutex); - mutex_unlock(&fs_info->fs_devices->device_list_mutex); + mutex_unlock(&fs_devices->device_list_mutex); /* replace the sysfs entry */ btrfs_sysfs_remove_device(src_device); diff --git a/fs/btrfs/dir-item.c b/fs/btrfs/dir-item.c index 3b532bab0755..72fb2c518a2b 100644 --- a/fs/btrfs/dir-item.c +++ b/fs/btrfs/dir-item.c @@ -325,36 +325,15 @@ btrfs_search_dir_index_item(struct btrfs_root *root, struct btrfs_path *path, u64 dirid, const char *name, int name_len) { - struct extent_buffer *leaf; struct btrfs_dir_item *di; struct btrfs_key key; - u32 nritems; int ret; key.objectid = dirid; key.type = BTRFS_DIR_INDEX_KEY; key.offset = 0; - ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); - if (ret < 0) - return ERR_PTR(ret); - - leaf = path->nodes[0]; - nritems = btrfs_header_nritems(leaf); - - while (1) { - if (path->slots[0] >= nritems) { - ret = btrfs_next_leaf(root, path); - if (ret < 0) - return ERR_PTR(ret); - if (ret > 0) - break; - leaf = path->nodes[0]; - nritems = btrfs_header_nritems(leaf); - continue; - } - - btrfs_item_key_to_cpu(leaf, &key, path->slots[0]); + btrfs_for_each_slot(root, &key, &key, path, ret) { if (key.objectid != dirid || key.type != BTRFS_DIR_INDEX_KEY) break; @@ -362,10 +341,12 @@ btrfs_search_dir_index_item(struct btrfs_root *root, name, name_len); if (di) return di; - - path->slots[0]++; } - return NULL; + /* Adjust return code if the key was not found in the next leaf. */ + if (ret > 0) + ret = 0; + + return ERR_PTR(ret); } struct btrfs_dir_item *btrfs_lookup_xattr(struct btrfs_trans_handle *trans, diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index b30309f187cf..89e94ea2fef5 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -5,7 +5,6 @@ #include <linux/fs.h> #include <linux/blkdev.h> -#include <linux/radix-tree.h> #include <linux/writeback.h> #include <linux/workqueue.h> #include <linux/kthread.h> @@ -374,9 +373,9 @@ int btrfs_verify_level_key(struct extent_buffer *eb, int level, * @level: expected level, mandatory check * @first_key: expected key of first slot, skip check if NULL */ -static int btree_read_extent_buffer_pages(struct extent_buffer *eb, - u64 parent_transid, int level, - struct btrfs_key *first_key) +int btrfs_read_extent_buffer(struct extent_buffer *eb, + u64 parent_transid, int level, + struct btrfs_key *first_key) { struct btrfs_fs_info *fs_info = eb->fs_info; struct extent_io_tree *io_tree; @@ -486,7 +485,7 @@ static int csum_dirty_subpage_buffers(struct btrfs_fs_info *fs_info, uptodate = btrfs_subpage_test_uptodate(fs_info, page, cur, fs_info->nodesize); - /* A dirty eb shouldn't disappear from buffer_radix */ + /* A dirty eb shouldn't disappear from extent_buffers */ if (WARN_ON(!eb)) return -EUCLEAN; @@ -519,7 +518,7 @@ static int csum_dirty_buffer(struct btrfs_fs_info *fs_info, struct bio_vec *bvec u64 found_start; struct extent_buffer *eb; - if (fs_info->sectorsize < PAGE_SIZE) + if (fs_info->nodesize < PAGE_SIZE) return csum_dirty_subpage_buffers(fs_info, bvec); eb = (struct extent_buffer *)page->private; @@ -704,7 +703,7 @@ int btrfs_validate_metadata_buffer(struct btrfs_bio *bbio, ASSERT(page->private); - if (btrfs_sb(page->mapping->host->i_sb)->sectorsize < PAGE_SIZE) + if (btrfs_sb(page->mapping->host->i_sb)->nodesize < PAGE_SIZE) return validate_subpage_buffer(page, start, end, mirror); eb = (struct extent_buffer *)page->private; @@ -850,8 +849,7 @@ static void run_one_async_free(struct btrfs_work *work) } blk_status_t btrfs_wq_submit_bio(struct inode *inode, struct bio *bio, - int mirror_num, unsigned long bio_flags, - u64 dio_file_offset, + int mirror_num, u64 dio_file_offset, extent_submit_bio_start_t *submit_bio_start) { struct btrfs_fs_info *fs_info = BTRFS_I(inode)->root->fs_info; @@ -874,9 +872,9 @@ blk_status_t btrfs_wq_submit_bio(struct inode *inode, struct bio *bio, async->status = 0; if (op_is_sync(bio->bi_opf)) - btrfs_set_work_high_priority(&async->work); - - btrfs_queue_work(fs_info->workers, &async->work); + btrfs_queue_work(fs_info->hipri_workers, &async->work); + else + btrfs_queue_work(fs_info->workers, &async->work); return 0; } @@ -920,8 +918,7 @@ static bool should_async_write(struct btrfs_fs_info *fs_info, return true; } -blk_status_t btrfs_submit_metadata_bio(struct inode *inode, struct bio *bio, - int mirror_num, unsigned long bio_flags) +void btrfs_submit_metadata_bio(struct inode *inode, struct bio *bio, int mirror_num) { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); blk_status_t ret; @@ -933,31 +930,25 @@ blk_status_t btrfs_submit_metadata_bio(struct inode *inode, struct bio *bio, */ ret = btrfs_bio_wq_end_io(fs_info, bio, BTRFS_WQ_ENDIO_METADATA); - if (ret) - goto out_w_error; - ret = btrfs_map_bio(fs_info, bio, mirror_num); + if (!ret) + ret = btrfs_map_bio(fs_info, bio, mirror_num); } else if (!should_async_write(fs_info, BTRFS_I(inode))) { ret = btree_csum_one_bio(bio); - if (ret) - goto out_w_error; - ret = btrfs_map_bio(fs_info, bio, mirror_num); + if (!ret) + ret = btrfs_map_bio(fs_info, bio, mirror_num); } else { /* * kthread helpers are used to submit writes so that * checksumming can happen in parallel across all CPUs */ ret = btrfs_wq_submit_bio(inode, bio, mirror_num, 0, - 0, btree_submit_bio_start); + btree_submit_bio_start); } - if (ret) - goto out_w_error; - return 0; - -out_w_error: - bio->bi_status = ret; - bio_endio(bio); - return ret; + if (ret) { + bio->bi_status = ret; + bio_endio(bio); + } } #ifdef CONFIG_MIGRATION @@ -1005,12 +996,12 @@ static int btree_writepages(struct address_space *mapping, return btree_write_cache_pages(mapping, wbc); } -static int btree_releasepage(struct page *page, gfp_t gfp_flags) +static bool btree_release_folio(struct folio *folio, gfp_t gfp_flags) { - if (PageWriteback(page) || PageDirty(page)) - return 0; + if (folio_test_writeback(folio) || folio_test_dirty(folio)) + return false; - return try_release_extent_buffer(page); + return try_release_extent_buffer(&folio->page); } static void btree_invalidate_folio(struct folio *folio, size_t offset, @@ -1019,7 +1010,7 @@ static void btree_invalidate_folio(struct folio *folio, size_t offset, struct extent_io_tree *tree; tree = &BTRFS_I(folio->mapping->host)->io_tree; extent_invalidate_folio(tree, folio, offset); - btree_releasepage(&folio->page, GFP_NOFS); + btree_release_folio(folio, GFP_NOFS); if (folio_get_private(folio)) { btrfs_warn(BTRFS_I(folio->mapping->host)->root->fs_info, "folio private not zero on folio %llu", @@ -1080,7 +1071,7 @@ static bool btree_dirty_folio(struct address_space *mapping, static const struct address_space_operations btree_aops = { .writepages = btree_writepages, - .releasepage = btree_releasepage, + .release_folio = btree_release_folio, .invalidate_folio = btree_invalidate_folio, #ifdef CONFIG_MIGRATION .migratepage = btree_migratepage, @@ -1118,12 +1109,15 @@ struct extent_buffer *read_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr, if (IS_ERR(buf)) return buf; - ret = btree_read_extent_buffer_pages(buf, parent_transid, - level, first_key); + ret = btrfs_read_extent_buffer(buf, parent_transid, level, first_key); if (ret) { free_extent_buffer_stale(buf); return ERR_PTR(ret); } + if (btrfs_check_eb_owner(buf, owner_root)) { + free_extent_buffer_stale(buf); + return ERR_PTR(-EUCLEAN); + } return buf; } @@ -1164,7 +1158,7 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info, root->nr_delalloc_inodes = 0; root->nr_ordered_extents = 0; root->inode_tree = RB_ROOT; - INIT_RADIX_TREE(&root->delayed_nodes_tree, GFP_ATOMIC); + xa_init_flags(&root->delayed_nodes, GFP_ATOMIC); btrfs_init_root_block_rsv(root); @@ -1216,9 +1210,9 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info, btrfs_qgroup_init_swapped_blocks(&root->swapped_blocks); #ifdef CONFIG_BTRFS_DEBUG INIT_LIST_HEAD(&root->leak_list); - spin_lock(&fs_info->fs_roots_radix_lock); + spin_lock(&fs_info->fs_roots_lock); list_add_tail(&root->leak_list, &fs_info->allocated_roots); - spin_unlock(&fs_info->fs_roots_radix_lock); + spin_unlock(&fs_info->fs_roots_lock); #endif } @@ -1563,6 +1557,23 @@ static struct btrfs_root *read_tree_root_path(struct btrfs_root *tree_root, ret = -EIO; goto fail; } + + /* + * For real fs, and not log/reloc trees, root owner must + * match its root node owner + */ + if (!test_bit(BTRFS_FS_STATE_DUMMY_FS_INFO, &fs_info->fs_state) && + root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID && + root->root_key.objectid != BTRFS_TREE_RELOC_OBJECTID && + root->root_key.objectid != btrfs_header_owner(root->node)) { + btrfs_crit(fs_info, +"root=%llu block=%llu, tree root owner mismatch, have %llu expect %llu", + root->root_key.objectid, root->node->start, + btrfs_header_owner(root->node), + root->root_key.objectid); + ret = -EUCLEAN; + goto fail; + } root->commit_root = btrfs_root_node(root); return root; fail: @@ -1648,12 +1659,11 @@ static struct btrfs_root *btrfs_lookup_fs_root(struct btrfs_fs_info *fs_info, { struct btrfs_root *root; - spin_lock(&fs_info->fs_roots_radix_lock); - root = radix_tree_lookup(&fs_info->fs_roots_radix, - (unsigned long)root_id); + spin_lock(&fs_info->fs_roots_lock); + root = xa_load(&fs_info->fs_roots, (unsigned long)root_id); if (root) root = btrfs_grab_root(root); - spin_unlock(&fs_info->fs_roots_radix_lock); + spin_unlock(&fs_info->fs_roots_lock); return root; } @@ -1695,20 +1705,14 @@ int btrfs_insert_fs_root(struct btrfs_fs_info *fs_info, { int ret; - ret = radix_tree_preload(GFP_NOFS); - if (ret) - return ret; - - spin_lock(&fs_info->fs_roots_radix_lock); - ret = radix_tree_insert(&fs_info->fs_roots_radix, - (unsigned long)root->root_key.objectid, - root); + spin_lock(&fs_info->fs_roots_lock); + ret = xa_insert(&fs_info->fs_roots, (unsigned long)root->root_key.objectid, + root, GFP_NOFS); if (ret == 0) { btrfs_grab_root(root); - set_bit(BTRFS_ROOT_IN_RADIX, &root->state); + set_bit(BTRFS_ROOT_REGISTERED, &root->state); } - spin_unlock(&fs_info->fs_roots_radix_lock); - radix_tree_preload_end(); + spin_unlock(&fs_info->fs_roots_lock); return ret; } @@ -1850,9 +1854,10 @@ again: ret = btrfs_insert_fs_root(fs_info, root); if (ret) { - btrfs_put_root(root); - if (ret == -EEXIST) + if (ret == -EEXIST) { + btrfs_put_root(root); goto again; + } goto fail; } return root; @@ -1963,7 +1968,7 @@ static void end_workqueue_fn(struct btrfs_work *work) static int cleaner_kthread(void *arg) { - struct btrfs_fs_info *fs_info = (struct btrfs_fs_info *)arg; + struct btrfs_fs_info *fs_info = arg; int again; while (1) { @@ -2265,10 +2270,12 @@ static void btrfs_stop_all_workers(struct btrfs_fs_info *fs_info) { btrfs_destroy_workqueue(fs_info->fixup_workers); btrfs_destroy_workqueue(fs_info->delalloc_workers); + btrfs_destroy_workqueue(fs_info->hipri_workers); btrfs_destroy_workqueue(fs_info->workers); btrfs_destroy_workqueue(fs_info->endio_workers); btrfs_destroy_workqueue(fs_info->endio_raid56_workers); - btrfs_destroy_workqueue(fs_info->rmw_workers); + if (fs_info->rmw_workers) + destroy_workqueue(fs_info->rmw_workers); btrfs_destroy_workqueue(fs_info->endio_write_workers); btrfs_destroy_workqueue(fs_info->endio_freespace_worker); btrfs_destroy_workqueue(fs_info->delayed_workers); @@ -2335,9 +2342,9 @@ void btrfs_put_root(struct btrfs_root *root) btrfs_drew_lock_destroy(&root->snapshot_lock); free_root_extent_buffers(root); #ifdef CONFIG_BTRFS_DEBUG - spin_lock(&root->fs_info->fs_roots_radix_lock); + spin_lock(&root->fs_info->fs_roots_lock); list_del_init(&root->leak_list); - spin_unlock(&root->fs_info->fs_roots_radix_lock); + spin_unlock(&root->fs_info->fs_roots_lock); #endif kfree(root); } @@ -2345,28 +2352,21 @@ void btrfs_put_root(struct btrfs_root *root) void btrfs_free_fs_roots(struct btrfs_fs_info *fs_info) { - int ret; - struct btrfs_root *gang[8]; - int i; + struct btrfs_root *root; + unsigned long index = 0; while (!list_empty(&fs_info->dead_roots)) { - gang[0] = list_entry(fs_info->dead_roots.next, - struct btrfs_root, root_list); - list_del(&gang[0]->root_list); + root = list_entry(fs_info->dead_roots.next, + struct btrfs_root, root_list); + list_del(&root->root_list); - if (test_bit(BTRFS_ROOT_IN_RADIX, &gang[0]->state)) - btrfs_drop_and_free_fs_root(fs_info, gang[0]); - btrfs_put_root(gang[0]); + if (test_bit(BTRFS_ROOT_REGISTERED, &root->state)) + btrfs_drop_and_free_fs_root(fs_info, root); + btrfs_put_root(root); } - while (1) { - ret = radix_tree_gang_lookup(&fs_info->fs_roots_radix, - (void **)gang, 0, - ARRAY_SIZE(gang)); - if (!ret) - break; - for (i = 0; i < ret; i++) - btrfs_drop_and_free_fs_root(fs_info, gang[i]); + xa_for_each(&fs_info->fs_roots, index, root) { + btrfs_drop_and_free_fs_root(fs_info, root); } } @@ -2443,7 +2443,9 @@ static int btrfs_init_workqueues(struct btrfs_fs_info *fs_info) unsigned int flags = WQ_MEM_RECLAIM | WQ_FREEZABLE | WQ_UNBOUND; fs_info->workers = - btrfs_alloc_workqueue(fs_info, "worker", + btrfs_alloc_workqueue(fs_info, "worker", flags, max_active, 16); + fs_info->hipri_workers = + btrfs_alloc_workqueue(fs_info, "worker-high", flags | WQ_HIGHPRI, max_active, 16); fs_info->delalloc_workers = @@ -2475,8 +2477,7 @@ static int btrfs_init_workqueues(struct btrfs_fs_info *fs_info) fs_info->endio_raid56_workers = btrfs_alloc_workqueue(fs_info, "endio-raid56", flags, max_active, 4); - fs_info->rmw_workers = - btrfs_alloc_workqueue(fs_info, "rmw", flags, max_active, 2); + fs_info->rmw_workers = alloc_workqueue("btrfs-rmw", flags, max_active); fs_info->endio_write_workers = btrfs_alloc_workqueue(fs_info, "endio-write", flags, max_active, 2); @@ -2491,8 +2492,8 @@ static int btrfs_init_workqueues(struct btrfs_fs_info *fs_info) fs_info->discard_ctl.discard_workers = alloc_workqueue("btrfs_discard", WQ_UNBOUND | WQ_FREEZABLE, 1); - if (!(fs_info->workers && fs_info->delalloc_workers && - fs_info->flush_workers && + if (!(fs_info->workers && fs_info->hipri_workers && + fs_info->delalloc_workers && fs_info->flush_workers && fs_info->endio_workers && fs_info->endio_meta_workers && fs_info->endio_meta_write_workers && fs_info->endio_write_workers && fs_info->endio_raid56_workers && @@ -2814,12 +2815,14 @@ static int validate_super(struct btrfs_fs_info *fs_info, } /* - * For 4K page size, we only support 4K sector size. - * For 64K page size, we support 64K and 4K sector sizes. + * We only support at most two sectorsizes: 4K and PAGE_SIZE. + * + * We can support 16K sectorsize with 64K page size without problem, + * but such sectorsize/pagesize combination doesn't make much sense. + * 4K will be our future standard, PAGE_SIZE is supported from the very + * beginning. */ - if ((PAGE_SIZE == SZ_4K && sectorsize != PAGE_SIZE) || - (PAGE_SIZE == SZ_64K && (sectorsize != SZ_4K && - sectorsize != SZ_64K))) { + if (sectorsize > PAGE_SIZE || (sectorsize != SZ_4K && sectorsize != PAGE_SIZE)) { btrfs_err(fs_info, "sectorsize %llu not yet supported for page size %lu", sectorsize, PAGE_SIZE); @@ -3131,8 +3134,8 @@ static int __cold init_tree_roots(struct btrfs_fs_info *fs_info) void btrfs_init_fs_info(struct btrfs_fs_info *fs_info) { - INIT_RADIX_TREE(&fs_info->fs_roots_radix, GFP_ATOMIC); - INIT_RADIX_TREE(&fs_info->buffer_radix, GFP_ATOMIC); + xa_init_flags(&fs_info->fs_roots, GFP_ATOMIC); + xa_init_flags(&fs_info->extent_buffers, GFP_ATOMIC); INIT_LIST_HEAD(&fs_info->trans_list); INIT_LIST_HEAD(&fs_info->dead_roots); INIT_LIST_HEAD(&fs_info->delayed_iputs); @@ -3140,7 +3143,7 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info) INIT_LIST_HEAD(&fs_info->caching_block_groups); spin_lock_init(&fs_info->delalloc_root_lock); spin_lock_init(&fs_info->trans_lock); - spin_lock_init(&fs_info->fs_roots_radix_lock); + spin_lock_init(&fs_info->fs_roots_lock); spin_lock_init(&fs_info->delayed_iput_lock); spin_lock_init(&fs_info->defrag_inodes_lock); spin_lock_init(&fs_info->super_lock); @@ -3156,6 +3159,7 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info) mutex_init(&fs_info->reloc_mutex); mutex_init(&fs_info->delalloc_root_mutex); mutex_init(&fs_info->zoned_meta_io_lock); + mutex_init(&fs_info->zoned_data_reloc_io_lock); seqlock_init(&fs_info->profiles_lock); INIT_LIST_HEAD(&fs_info->dirty_cowonly_roots); @@ -3207,9 +3211,8 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info) btrfs_init_balance(fs_info); btrfs_init_async_reclaim_work(fs_info); - spin_lock_init(&fs_info->block_group_cache_lock); - fs_info->block_group_cache_tree = RB_ROOT; - fs_info->first_logical_byte = (u64)-1; + rwlock_init(&fs_info->block_group_cache_lock); + fs_info->block_group_cache_tree = RB_ROOT_CACHED; extent_io_tree_init(fs_info, &fs_info->excluded_extents, IO_TREE_FS_EXCLUDED_EXTENTS, NULL); @@ -3293,7 +3296,7 @@ static int init_mount_fs_info(struct btrfs_fs_info *fs_info, struct super_block static int btrfs_uuid_rescan_kthread(void *data) { - struct btrfs_fs_info *fs_info = (struct btrfs_fs_info *)data; + struct btrfs_fs_info *fs_info = data; int ret; /* @@ -3371,7 +3374,7 @@ int btrfs_start_pre_rw_mount(struct btrfs_fs_info *fs_info) /* * btrfs_find_orphan_roots() is responsible for finding all the dead * roots (with 0 refs), flag them with BTRFS_ROOT_DEAD_TREE and load - * them into the fs_info->fs_roots_radix tree. This must be done before + * them into the fs_info->fs_roots. This must be done before * calling btrfs_orphan_cleanup() on the tree root. If we don't do it * first, then btrfs_orphan_cleanup() will delete a dead root's orphan * item before the root's tree is deleted - this means that if we unmount @@ -3609,7 +3612,7 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device ~BTRFS_FEATURE_INCOMPAT_SUPP; if (features) { btrfs_err(fs_info, - "cannot mount because of unsupported optional features (%llx)", + "cannot mount because of unsupported optional features (0x%llx)", features); err = -EINVAL; goto fail_alloc; @@ -3647,7 +3650,7 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device ~BTRFS_FEATURE_COMPAT_RO_SUPP; if (!sb_rdonly(sb) && features) { btrfs_err(fs_info, - "cannot mount read-write because of unsupported optional features (%llx)", + "cannot mount read-write because of unsupported optional features (0x%llx)", features); err = -EINVAL; goto fail_alloc; @@ -3656,17 +3659,20 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device if (sectorsize < PAGE_SIZE) { struct btrfs_subpage_info *subpage_info; + /* + * V1 space cache has some hardcoded PAGE_SIZE usage, and is + * going to be deprecated. + * + * Force to use v2 cache for subpage case. + */ + btrfs_clear_opt(fs_info->mount_opt, SPACE_CACHE); + btrfs_set_and_info(fs_info, FREE_SPACE_TREE, + "forcing free space tree for sector size %u with page size %lu", + sectorsize, PAGE_SIZE); + btrfs_warn(fs_info, "read-write for sector size %u with page size %lu is experimental", sectorsize, PAGE_SIZE); - if (btrfs_super_incompat_flags(fs_info->super_copy) & - BTRFS_FEATURE_INCOMPAT_RAID56) { - btrfs_err(fs_info, - "RAID56 is not yet supported for sector size %u with page size %lu", - sectorsize, PAGE_SIZE); - err = -EINVAL; - goto fail_alloc; - } subpage_info = kzalloc(sizeof(*subpage_info), GFP_KERNEL); if (!subpage_info) goto fail_alloc; @@ -4144,7 +4150,8 @@ static int write_dev_supers(struct btrfs_device *device, if (i == 0 && !btrfs_test_opt(device->fs_info, NOBARRIER)) bio->bi_opf |= REQ_FUA; - btrfsic_submit_bio(bio); + btrfsic_check_bio(bio); + submit_bio(bio); if (btrfs_advance_sb_log(device, i)) errors++; @@ -4225,6 +4232,7 @@ static int wait_dev_supers(struct btrfs_device *device, int max_mirrors) */ static void btrfs_end_empty_barrier(struct bio *bio) { + bio_uninit(bio); complete(bio->bi_private); } @@ -4234,7 +4242,7 @@ static void btrfs_end_empty_barrier(struct bio *bio) */ static void write_dev_flush(struct btrfs_device *device) { - struct bio *bio = device->flush_bio; + struct bio *bio = &device->flush_bio; #ifndef CONFIG_BTRFS_FS_CHECK_INTEGRITY /* @@ -4247,17 +4255,18 @@ static void write_dev_flush(struct btrfs_device *device) * of simplicity, since this is a debug tool and not meant for use in * non-debug builds. */ - struct request_queue *q = bdev_get_queue(device->bdev); - if (!test_bit(QUEUE_FLAG_WC, &q->queue_flags)) + if (!bdev_write_cache(device->bdev)) return; #endif - bio_reset(bio, device->bdev, REQ_OP_WRITE | REQ_SYNC | REQ_PREFLUSH); + bio_init(bio, device->bdev, NULL, 0, + REQ_OP_WRITE | REQ_SYNC | REQ_PREFLUSH); bio->bi_end_io = btrfs_end_empty_barrier; init_completion(&device->flush_wait); bio->bi_private = &device->flush_wait; - btrfsic_submit_bio(bio); + btrfsic_check_bio(bio); + submit_bio(bio); set_bit(BTRFS_DEV_STATE_FLUSH_SENT, &device->dev_state); } @@ -4266,7 +4275,7 @@ static void write_dev_flush(struct btrfs_device *device) */ static blk_status_t wait_dev_flush(struct btrfs_device *device) { - struct bio *bio = device->flush_bio; + struct bio *bio = &device->flush_bio; if (!test_bit(BTRFS_DEV_STATE_FLUSH_SENT, &device->dev_state)) return BLK_STS_OK; @@ -4490,12 +4499,11 @@ void btrfs_drop_and_free_fs_root(struct btrfs_fs_info *fs_info, { bool drop_ref = false; - spin_lock(&fs_info->fs_roots_radix_lock); - radix_tree_delete(&fs_info->fs_roots_radix, - (unsigned long)root->root_key.objectid); - if (test_and_clear_bit(BTRFS_ROOT_IN_RADIX, &root->state)) + spin_lock(&fs_info->fs_roots_lock); + xa_erase(&fs_info->fs_roots, (unsigned long)root->root_key.objectid); + if (test_and_clear_bit(BTRFS_ROOT_REGISTERED, &root->state)) drop_ref = true; - spin_unlock(&fs_info->fs_roots_radix_lock); + spin_unlock(&fs_info->fs_roots_lock); if (BTRFS_FS_ERROR(fs_info)) { ASSERT(root->log_root == NULL); @@ -4511,50 +4519,48 @@ void btrfs_drop_and_free_fs_root(struct btrfs_fs_info *fs_info, int btrfs_cleanup_fs_roots(struct btrfs_fs_info *fs_info) { - u64 root_objectid = 0; - struct btrfs_root *gang[8]; - int i = 0; + struct btrfs_root *roots[8]; + unsigned long index = 0; + int i; int err = 0; - unsigned int ret = 0; + int grabbed; while (1) { - spin_lock(&fs_info->fs_roots_radix_lock); - ret = radix_tree_gang_lookup(&fs_info->fs_roots_radix, - (void **)gang, root_objectid, - ARRAY_SIZE(gang)); - if (!ret) { - spin_unlock(&fs_info->fs_roots_radix_lock); - break; + struct btrfs_root *root; + + spin_lock(&fs_info->fs_roots_lock); + if (!xa_find(&fs_info->fs_roots, &index, ULONG_MAX, XA_PRESENT)) { + spin_unlock(&fs_info->fs_roots_lock); + return err; } - root_objectid = gang[ret - 1]->root_key.objectid + 1; - for (i = 0; i < ret; i++) { - /* Avoid to grab roots in dead_roots */ - if (btrfs_root_refs(&gang[i]->root_item) == 0) { - gang[i] = NULL; - continue; - } - /* grab all the search result for later use */ - gang[i] = btrfs_grab_root(gang[i]); + grabbed = 0; + xa_for_each_start(&fs_info->fs_roots, index, root, index) { + /* Avoid grabbing roots in dead_roots */ + if (btrfs_root_refs(&root->root_item) > 0) + roots[grabbed++] = btrfs_grab_root(root); + if (grabbed >= ARRAY_SIZE(roots)) + break; } - spin_unlock(&fs_info->fs_roots_radix_lock); + spin_unlock(&fs_info->fs_roots_lock); - for (i = 0; i < ret; i++) { - if (!gang[i]) + for (i = 0; i < grabbed; i++) { + if (!roots[i]) continue; - root_objectid = gang[i]->root_key.objectid; - err = btrfs_orphan_cleanup(gang[i]); + index = roots[i]->root_key.objectid; + err = btrfs_orphan_cleanup(roots[i]); if (err) - break; - btrfs_put_root(gang[i]); + goto out; + btrfs_put_root(roots[i]); } - root_objectid++; + index++; } - /* release the uncleaned roots due to error */ - for (; i < ret; i++) { - if (gang[i]) - btrfs_put_root(gang[i]); +out: + /* Release the roots that remain uncleaned due to error */ + for (; i < grabbed; i++) { + if (roots[i]) + btrfs_put_root(roots[i]); } return err; } @@ -4849,13 +4855,6 @@ void btrfs_btree_balance_dirty_nodelay(struct btrfs_fs_info *fs_info) __btrfs_btree_balance_dirty(fs_info, 0); } -int btrfs_read_buffer(struct extent_buffer *buf, u64 parent_transid, int level, - struct btrfs_key *first_key) -{ - return btree_read_extent_buffer_pages(buf, parent_transid, - level, first_key); -} - static void btrfs_error_commit_super(struct btrfs_fs_info *fs_info) { /* cleanup FS via transaction */ @@ -4871,31 +4870,28 @@ static void btrfs_error_commit_super(struct btrfs_fs_info *fs_info) static void btrfs_drop_all_logs(struct btrfs_fs_info *fs_info) { - struct btrfs_root *gang[8]; - u64 root_objectid = 0; - int ret; - - spin_lock(&fs_info->fs_roots_radix_lock); - while ((ret = radix_tree_gang_lookup(&fs_info->fs_roots_radix, - (void **)gang, root_objectid, - ARRAY_SIZE(gang))) != 0) { - int i; + unsigned long index = 0; + int grabbed = 0; + struct btrfs_root *roots[8]; - for (i = 0; i < ret; i++) - gang[i] = btrfs_grab_root(gang[i]); - spin_unlock(&fs_info->fs_roots_radix_lock); + spin_lock(&fs_info->fs_roots_lock); + while ((grabbed = xa_extract(&fs_info->fs_roots, (void **)roots, index, + ULONG_MAX, 8, XA_PRESENT))) { + for (int i = 0; i < grabbed; i++) + roots[i] = btrfs_grab_root(roots[i]); + spin_unlock(&fs_info->fs_roots_lock); - for (i = 0; i < ret; i++) { - if (!gang[i]) + for (int i = 0; i < grabbed; i++) { + if (!roots[i]) continue; - root_objectid = gang[i]->root_key.objectid; - btrfs_free_log(NULL, gang[i]); - btrfs_put_root(gang[i]); + index = roots[i]->root_key.objectid; + btrfs_free_log(NULL, roots[i]); + btrfs_put_root(roots[i]); } - root_objectid++; - spin_lock(&fs_info->fs_roots_radix_lock); + index++; + spin_lock(&fs_info->fs_roots_lock); } - spin_unlock(&fs_info->fs_roots_radix_lock); + spin_unlock(&fs_info->fs_roots_lock); btrfs_free_log_root_tree(NULL, fs_info); } diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h index 2e10514ecda8..4ee8c42c9f78 100644 --- a/fs/btrfs/disk-io.h +++ b/fs/btrfs/disk-io.h @@ -87,8 +87,7 @@ void btrfs_drop_and_free_fs_root(struct btrfs_fs_info *fs_info, int btrfs_validate_metadata_buffer(struct btrfs_bio *bbio, struct page *page, u64 start, u64 end, int mirror); -blk_status_t btrfs_submit_metadata_bio(struct inode *inode, struct bio *bio, - int mirror_num, unsigned long bio_flags); +void btrfs_submit_metadata_bio(struct inode *inode, struct bio *bio, int mirror_num); #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS struct btrfs_root *btrfs_alloc_dummy_root(struct btrfs_fs_info *fs_info); #endif @@ -120,13 +119,12 @@ void btrfs_put_root(struct btrfs_root *root); void btrfs_mark_buffer_dirty(struct extent_buffer *buf); int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid, int atomic); -int btrfs_read_buffer(struct extent_buffer *buf, u64 parent_transid, int level, - struct btrfs_key *first_key); +int btrfs_read_extent_buffer(struct extent_buffer *buf, u64 parent_transid, + int level, struct btrfs_key *first_key); blk_status_t btrfs_bio_wq_end_io(struct btrfs_fs_info *info, struct bio *bio, enum btrfs_wq_endio_type metadata); blk_status_t btrfs_wq_submit_bio(struct inode *inode, struct bio *bio, - int mirror_num, unsigned long bio_flags, - u64 dio_file_offset, + int mirror_num, u64 dio_file_offset, extent_submit_bio_start_t *submit_bio_start); blk_status_t btrfs_submit_bio_done(void *private_data, struct bio *bio, int mirror_num); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index f477035a2ac2..0867c5cd6e01 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -895,7 +895,13 @@ again: err = -ENOENT; while (1) { if (ptr >= end) { - WARN_ON(ptr > end); + if (ptr > end) { + err = -EUCLEAN; + btrfs_print_leaf(path->nodes[0]); + btrfs_crit(fs_info, +"overrun extent record at slot %d while looking for inline extent for root %llu owner %llu offset %llu parent %llu", + path->slots[0], root_objectid, owner, offset, parent); + } break; } iref = (struct btrfs_extent_inline_ref *)ptr; @@ -1239,7 +1245,7 @@ static int btrfs_issue_discard(struct block_device *bdev, u64 start, u64 len, if (size) { ret = blkdev_issue_discard(bdev, start >> 9, size >> 9, - GFP_NOFS, 0); + GFP_NOFS); if (!ret) *discarded_bytes += size; else if (ret != -EOPNOTSUPP) @@ -1256,7 +1262,7 @@ static int btrfs_issue_discard(struct block_device *bdev, u64 start, u64 len, if (bytes_left) { ret = blkdev_issue_discard(bdev, start >> 9, bytes_left >> 9, - GFP_NOFS, 0); + GFP_NOFS); if (!ret) *discarded_bytes += bytes_left; } @@ -1291,7 +1297,7 @@ static int do_discard_extent(struct btrfs_io_stripe *stripe, u64 *bytes) ret = btrfs_reset_device_zone(dev_replace->tgtdev, phys, len, &discarded); discarded += src_disc; - } else if (blk_queue_discard(bdev_get_queue(stripe->dev->bdev))) { + } else if (bdev_max_discard_sectors(stripe->dev->bdev)) { ret = btrfs_issue_discard(dev->bdev, phys, len, &discarded); } else { ret = 0; @@ -1577,12 +1583,12 @@ static int run_delayed_extent_op(struct btrfs_trans_handle *trans, u32 item_size; int ret; int err = 0; - int metadata = !extent_op->is_data; + int metadata = 1; if (TRANS_ABORTED(trans)) return 0; - if (metadata && !btrfs_fs_incompat(fs_info, SKINNY_METADATA)) + if (!btrfs_fs_incompat(fs_info, SKINNY_METADATA)) metadata = 0; path = btrfs_alloc_path(); @@ -2180,7 +2186,7 @@ out: int btrfs_set_disk_extent_flags(struct btrfs_trans_handle *trans, struct extent_buffer *eb, u64 flags, - int level, int is_data) + int level) { struct btrfs_delayed_extent_op *extent_op; int ret; @@ -2192,7 +2198,6 @@ int btrfs_set_disk_extent_flags(struct btrfs_trans_handle *trans, extent_op->flags_to_set = flags; extent_op->update_flags = true; extent_op->update_key = false; - extent_op->is_data = is_data ? true : false; extent_op->level = level; ret = btrfs_add_delayed_extent_op(trans, eb->start, eb->len, extent_op); @@ -2357,15 +2362,10 @@ out: } int btrfs_cross_ref_exist(struct btrfs_root *root, u64 objectid, u64 offset, - u64 bytenr, bool strict) + u64 bytenr, bool strict, struct btrfs_path *path) { - struct btrfs_path *path; int ret; - path = btrfs_alloc_path(); - if (!path) - return -ENOMEM; - do { ret = check_committed_ref(root, path, objectid, offset, bytenr, strict); @@ -2376,7 +2376,7 @@ int btrfs_cross_ref_exist(struct btrfs_root *root, u64 objectid, u64 offset, } while (ret == -EAGAIN); out: - btrfs_free_path(path); + btrfs_release_path(path); if (btrfs_is_data_reloc_root(root)) WARN_ON(ret > 0); return ret; @@ -2497,24 +2497,21 @@ static u64 get_alloc_profile_by_root(struct btrfs_root *root, int data) return ret; } -static u64 first_logical_byte(struct btrfs_fs_info *fs_info, u64 search_start) +static u64 first_logical_byte(struct btrfs_fs_info *fs_info) { - struct btrfs_block_group *cache; - u64 bytenr; - - spin_lock(&fs_info->block_group_cache_lock); - bytenr = fs_info->first_logical_byte; - spin_unlock(&fs_info->block_group_cache_lock); - - if (bytenr < (u64)-1) - return bytenr; + struct rb_node *leftmost; + u64 bytenr = 0; - cache = btrfs_lookup_first_block_group(fs_info, search_start); - if (!cache) - return 0; + read_lock(&fs_info->block_group_cache_lock); + /* Get the block group with the lowest logical start address. */ + leftmost = rb_first_cached(&fs_info->block_group_cache_tree); + if (leftmost) { + struct btrfs_block_group *bg; - bytenr = cache->start; - btrfs_put_block_group(cache); + bg = rb_entry(leftmost, struct btrfs_block_group, cache_node); + bytenr = bg->start; + } + read_unlock(&fs_info->block_group_cache_lock); return bytenr; } @@ -3803,8 +3800,7 @@ static int do_allocation_zoned(struct btrfs_block_group *block_group, /* Check RO and no space case before trying to activate it */ spin_lock(&block_group->lock); - if (block_group->ro || - block_group->alloc_offset == block_group->zone_capacity) { + if (block_group->ro || btrfs_zoned_bg_is_full(block_group)) { ret = 1; /* * May need to clear fs_info->{treelog,data_reloc}_bg. @@ -4082,7 +4078,7 @@ static int find_free_extent_update_loop(struct btrfs_fs_info *fs_info, } ret = btrfs_chunk_alloc(trans, ffe_ctl->flags, - CHUNK_ALLOC_FORCE); + CHUNK_ALLOC_FORCE_FOR_EXTENT); /* Do not bail out on ENOSPC since we can do more. */ if (ret == -ENOSPC) @@ -4272,7 +4268,7 @@ static noinline int find_free_extent(struct btrfs_root *root, return ret; ffe_ctl->search_start = max(ffe_ctl->search_start, - first_logical_byte(fs_info, 0)); + first_logical_byte(fs_info)); ffe_ctl->search_start = max(ffe_ctl->search_start, ffe_ctl->hint_byte); if (ffe_ctl->search_start == ffe_ctl->hint_byte) { block_group = btrfs_lookup_block_group(fs_info, @@ -4959,7 +4955,6 @@ struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans, extent_op->flags_to_set = flags; extent_op->update_key = skinny_metadata ? false : true; extent_op->update_flags = true; - extent_op->is_data = false; extent_op->level = level; btrfs_init_generic_ref(&generic_ref, BTRFS_ADD_DELAYED_EXTENT, @@ -5144,7 +5139,7 @@ static noinline int walk_down_proc(struct btrfs_trans_handle *trans, ret = btrfs_dec_ref(trans, root, eb, 0); BUG_ON(ret); /* -ENOMEM */ ret = btrfs_set_disk_extent_flags(trans, eb, flag, - btrfs_header_level(eb), 0); + btrfs_header_level(eb)); BUG_ON(ret); /* -ENOMEM */ wc->flags[level] |= flag; } @@ -5818,7 +5813,7 @@ int btrfs_drop_snapshot(struct btrfs_root *root, int update_ref, int for_reloc) btrfs_qgroup_convert_reserved_meta(root, INT_MAX); btrfs_qgroup_free_meta_all_pertrans(root); - if (test_bit(BTRFS_ROOT_IN_RADIX, &root->state)) + if (test_bit(BTRFS_ROOT_REGISTERED, &root->state)) btrfs_add_dropped_root(trans, root); else btrfs_put_root(root); @@ -5987,7 +5982,7 @@ static int btrfs_trim_free_extents(struct btrfs_device *device, u64 *trimmed) *trimmed = 0; /* Discard not supported = nothing to do. */ - if (!blk_queue_discard(bdev_get_queue(device->bdev))) + if (!bdev_max_discard_sectors(device->bdev)) return 0; /* Not writable = nothing to do. */ diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 724e8fe06aa0..8f6b544ae616 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -6,6 +6,7 @@ #include <linux/mm.h> #include <linux/pagemap.h> #include <linux/page-flags.h> +#include <linux/sched/mm.h> #include <linux/spinlock.h> #include <linux/blkdev.h> #include <linux/swap.h> @@ -28,6 +29,7 @@ #include "subpage.h" #include "zoned.h" #include "block-group.h" +#include "compression.h" static struct kmem_cache *extent_state_cache; static struct kmem_cache *extent_buffer_cache; @@ -75,6 +77,7 @@ void btrfs_extent_buffer_leak_debug_check(struct btrfs_fs_info *fs_info) if (!fs_info->allocated_ebs.next) return; + WARN_ON(!list_empty(&fs_info->allocated_ebs)); spin_lock_irqsave(&fs_info->eb_leak_lock, flags); while (!list_empty(&fs_info->allocated_ebs)) { eb = list_first_entry(&fs_info->allocated_ebs, @@ -135,6 +138,17 @@ struct tree_entry { struct rb_node rb_node; }; +/* + * Structure to record info about the bio being assembled, and other info like + * how many bytes are there before stripe/ordered extent boundary. + */ +struct btrfs_bio_ctrl { + struct bio *bio; + enum btrfs_compression_type compress_type; + u32 len_to_stripe_boundary; + u32 len_to_oe_boundary; +}; + struct extent_page_data { struct btrfs_bio_ctrl bio_ctrl; /* tells writepage not to lock the state bits for this range @@ -164,24 +178,27 @@ static int add_extent_changeset(struct extent_state *state, u32 bits, return ret; } -int __must_check submit_one_bio(struct bio *bio, int mirror_num, - unsigned long bio_flags) +static void submit_one_bio(struct bio *bio, int mirror_num, + enum btrfs_compression_type compress_type) { - blk_status_t ret = 0; struct extent_io_tree *tree = bio->bi_private; bio->bi_private = NULL; /* Caller should ensure the bio has at least some range added */ ASSERT(bio->bi_iter.bi_size); + if (is_data_inode(tree->private_data)) - ret = btrfs_submit_data_bio(tree->private_data, bio, mirror_num, - bio_flags); + btrfs_submit_data_bio(tree->private_data, bio, mirror_num, + compress_type); else - ret = btrfs_submit_metadata_bio(tree->private_data, bio, - mirror_num, bio_flags); - - return blk_status_to_errno(ret); + btrfs_submit_metadata_bio(tree->private_data, bio, mirror_num); + /* + * Above submission hooks will handle the error by ending the bio, + * which will do the cleanup properly. So here we should not return + * any error, or the caller of submit_extent_page() will do cleanup + * again, causing problems. + */ } /* Cleanup unsubmitted bios */ @@ -202,13 +219,12 @@ static void end_write_bio(struct extent_page_data *epd, int ret) * Return 0 if everything is OK. * Return <0 for error. */ -static int __must_check flush_write_bio(struct extent_page_data *epd) +static void flush_write_bio(struct extent_page_data *epd) { - int ret = 0; struct bio *bio = epd->bio_ctrl.bio; if (bio) { - ret = submit_one_bio(bio, 0, 0); + submit_one_bio(bio, 0, 0); /* * Clean up of epd->bio is handled by its endio function. * And endio is either triggered by successful bio execution @@ -218,7 +234,6 @@ static int __must_check flush_write_bio(struct extent_page_data *epd) */ epd->bio_ctrl.bio = NULL; } - return ret; } int __init extent_state_cache_init(void) @@ -2303,12 +2318,13 @@ static int repair_io_failure(struct btrfs_fs_info *fs_info, u64 ino, u64 start, u64 length, u64 logical, struct page *page, unsigned int pg_offset, int mirror_num) { - struct bio *bio; struct btrfs_device *dev; + struct bio_vec bvec; + struct bio bio; u64 map_length = 0; u64 sector; struct btrfs_io_context *bioc = NULL; - int ret; + int ret = 0; ASSERT(!(fs_info->sb->s_flags & SB_RDONLY)); BUG_ON(!mirror_num); @@ -2316,8 +2332,6 @@ static int repair_io_failure(struct btrfs_fs_info *fs_info, u64 ino, u64 start, if (btrfs_repair_one_zone(fs_info, logical)) return 0; - bio = btrfs_bio_alloc(1); - bio->bi_iter.bi_size = 0; map_length = length; /* @@ -2335,52 +2349,50 @@ static int repair_io_failure(struct btrfs_fs_info *fs_info, u64 ino, u64 start, */ ret = btrfs_map_block(fs_info, BTRFS_MAP_READ, logical, &map_length, &bioc, 0); - if (ret) { - btrfs_bio_counter_dec(fs_info); - bio_put(bio); - return -EIO; - } + if (ret) + goto out_counter_dec; ASSERT(bioc->mirror_num == 1); } else { ret = btrfs_map_block(fs_info, BTRFS_MAP_WRITE, logical, &map_length, &bioc, mirror_num); - if (ret) { - btrfs_bio_counter_dec(fs_info); - bio_put(bio); - return -EIO; - } + if (ret) + goto out_counter_dec; BUG_ON(mirror_num != bioc->mirror_num); } sector = bioc->stripes[bioc->mirror_num - 1].physical >> 9; - bio->bi_iter.bi_sector = sector; dev = bioc->stripes[bioc->mirror_num - 1].dev; btrfs_put_bioc(bioc); + if (!dev || !dev->bdev || !test_bit(BTRFS_DEV_STATE_WRITEABLE, &dev->dev_state)) { - btrfs_bio_counter_dec(fs_info); - bio_put(bio); - return -EIO; + ret = -EIO; + goto out_counter_dec; } - bio_set_dev(bio, dev->bdev); - bio->bi_opf = REQ_OP_WRITE | REQ_SYNC; - bio_add_page(bio, page, length, pg_offset); - if (btrfsic_submit_bio_wait(bio)) { + bio_init(&bio, dev->bdev, &bvec, 1, REQ_OP_WRITE | REQ_SYNC); + bio.bi_iter.bi_sector = sector; + __bio_add_page(&bio, page, length, pg_offset); + + btrfsic_check_bio(&bio); + ret = submit_bio_wait(&bio); + if (ret) { /* try to remap that extent elsewhere? */ - btrfs_bio_counter_dec(fs_info); - bio_put(bio); btrfs_dev_stat_inc_and_print(dev, BTRFS_DEV_STAT_WRITE_ERRS); - return -EIO; + goto out_bio_uninit; } btrfs_info_rl_in_rcu(fs_info, "read error corrected: ino %llu off %llu (dev %s sector %llu)", ino, start, rcu_str_deref(dev->name), sector); + ret = 0; + +out_bio_uninit: + bio_uninit(&bio); +out_counter_dec: btrfs_bio_counter_dec(fs_info); - bio_put(bio); - return 0; + return ret; } int btrfs_repair_eb_io_failure(const struct extent_buffer *eb, int mirror_num) @@ -2527,7 +2539,7 @@ static struct io_failure_record *btrfs_get_io_failure_record(struct inode *inode failrec->start = start; failrec->len = sectorsize; failrec->this_mirror = 0; - failrec->bio_flags = 0; + failrec->compress_type = BTRFS_COMPRESS_NONE; read_lock(&em_tree->lock); em = lookup_extent_mapping(em_tree, start, failrec->len); @@ -2551,8 +2563,7 @@ static struct io_failure_record *btrfs_get_io_failure_record(struct inode *inode logical = em->block_start + logical; if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags)) { logical = em->block_start; - failrec->bio_flags = EXTENT_BIO_COMPRESSED; - extent_set_compress_type(&failrec->bio_flags, em->compress_type); + failrec->compress_type = em->compress_type; } btrfs_debug(fs_info, @@ -2658,6 +2669,7 @@ int btrfs_repair_one_sector(struct inode *inode, repair_bio = btrfs_bio_alloc(1); repair_bbio = btrfs_bio(repair_bio); + repair_bbio->file_offset = start; repair_bio->bi_opf = REQ_OP_READ; repair_bio->bi_end_io = failed_bio->bi_end_io; repair_bio->bi_iter.bi_sector = failrec->logical >> 9; @@ -2683,7 +2695,7 @@ int btrfs_repair_one_sector(struct inode *inode, * will be handled by the endio on the repair_bio, so we can't return an * error here. */ - submit_bio_hook(inode, repair_bio, failrec->this_mirror, failrec->bio_flags); + submit_bio_hook(inode, repair_bio, failrec->this_mirror, failrec->compress_type); return BLK_STS_OK; } @@ -2709,18 +2721,19 @@ static void end_page_read(struct page *page, bool uptodate, u64 start, u32 len) btrfs_page_set_error(fs_info, page, start, len); } - if (fs_info->sectorsize == PAGE_SIZE) + if (!btrfs_is_subpage(fs_info, page)) unlock_page(page); else btrfs_subpage_end_reader(fs_info, page, start, len); } -static blk_status_t submit_read_repair(struct inode *inode, - struct bio *failed_bio, u32 bio_offset, - struct page *page, unsigned int pgoff, - u64 start, u64 end, int failed_mirror, - unsigned int error_bitmap, - submit_bio_hook_t *submit_bio_hook) +static blk_status_t submit_data_read_repair(struct inode *inode, + struct bio *failed_bio, + u32 bio_offset, struct page *page, + unsigned int pgoff, + u64 start, u64 end, + int failed_mirror, + unsigned int error_bitmap) { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); const u32 sectorsize = fs_info->sectorsize; @@ -2730,6 +2743,9 @@ static blk_status_t submit_read_repair(struct inode *inode, BUG_ON(bio_op(failed_bio) == REQ_OP_WRITE); + /* This repair is only for data */ + ASSERT(is_data_inode(inode)); + /* We're here because we had some read errors or csum mismatch */ ASSERT(error_bitmap); @@ -2758,7 +2774,7 @@ static blk_status_t submit_read_repair(struct inode *inode, ret = btrfs_repair_one_sector(inode, failed_bio, bio_offset + offset, page, pgoff + offset, start + offset, - failed_mirror, submit_bio_hook); + failed_mirror, btrfs_submit_data_bio); if (!ret) { /* * We have submitted the read repair, the page release @@ -2942,7 +2958,7 @@ update: static void begin_page_read(struct btrfs_fs_info *fs_info, struct page *page) { ASSERT(PageLocked(page)); - if (fs_info->sectorsize == PAGE_SIZE) + if (!btrfs_is_subpage(fs_info, page)) return; ASSERT(PagePrivate(page)); @@ -2950,7 +2966,7 @@ static void begin_page_read(struct btrfs_fs_info *fs_info, struct page *page) } /* - * Find extent buffer for a givne bytenr. + * Find extent buffer for a given bytenr. * * This is for end_bio_extent_readpage(), thus we can't do any unsafe locking * in endio context. @@ -2964,16 +2980,14 @@ static struct extent_buffer *find_extent_buffer_readpage( * For regular sectorsize, we can use page->private to grab extent * buffer */ - if (fs_info->sectorsize == PAGE_SIZE) { + if (fs_info->nodesize >= PAGE_SIZE) { ASSERT(PagePrivate(page) && page->private); return (struct extent_buffer *)page->private; } - /* For subpage case, we need to lookup buffer radix tree */ - rcu_read_lock(); - eb = radix_tree_lookup(&fs_info->buffer_radix, - bytenr >> fs_info->sectorsize_bits); - rcu_read_unlock(); + /* For subpage case, we need to lookup extent buffer xarray */ + eb = xa_load(&fs_info->extent_buffers, + bytenr >> fs_info->sectorsize_bits); ASSERT(eb); return eb; } @@ -3076,13 +3090,13 @@ static void end_bio_extent_readpage(struct bio *bio) goto readpage_ok; /* - * btrfs_submit_read_repair() will handle all the good + * submit_data_read_repair() will handle all the good * and bad sectors, we just continue to the next bvec. */ - submit_read_repair(inode, bio, bio_offset, page, - start - page_offset(page), start, - end, mirror, error_bitmap, - btrfs_submit_data_bio); + submit_data_read_repair(inode, bio, bio_offset, page, + start - page_offset(page), + start, end, mirror, + error_bitmap); ASSERT(bio_offset + len > bio_offset); bio_offset += len; @@ -3131,6 +3145,42 @@ readpage_ok: bio_put(bio); } +/** + * Populate every free slot in a provided array with pages. + * + * @nr_pages: number of pages to allocate + * @page_array: the array to fill with pages; any existing non-null entries in + * the array will be skipped + * + * Return: 0 if all pages were able to be allocated; + * -ENOMEM otherwise, and the caller is responsible for freeing all + * non-null page pointers in the array. + */ +int btrfs_alloc_page_array(unsigned int nr_pages, struct page **page_array) +{ + unsigned int allocated; + + for (allocated = 0; allocated < nr_pages;) { + unsigned int last = allocated; + + allocated = alloc_pages_bulk_array(GFP_NOFS, nr_pages, page_array); + + if (allocated == nr_pages) + return 0; + + /* + * During this iteration, no page could be allocated, even + * though alloc_pages_bulk_array() falls back to alloc_page() + * if it could not bulk-allocate. So we must be out of memory. + */ + if (allocated == last) + return -ENOMEM; + + memalloc_retry_wait(GFP_NOFS); + } + return 0; +} + /* * Initialize the members up to but not including 'bio'. Use after allocating a * new bio by bio_alloc_bioset as it does not initialize the bytes outside of @@ -3156,13 +3206,13 @@ struct bio *btrfs_bio_alloc(unsigned int nr_iovecs) return bio; } -struct bio *btrfs_bio_clone(struct bio *bio) +struct bio *btrfs_bio_clone(struct block_device *bdev, struct bio *bio) { struct btrfs_bio *bbio; struct bio *new; /* Bio allocation backed by a bioset does not fail */ - new = bio_alloc_clone(bio->bi_bdev, bio, GFP_NOFS, &btrfs_bioset); + new = bio_alloc_clone(bdev, bio, GFP_NOFS, &btrfs_bioset); bbio = btrfs_bio(new); btrfs_bio_init(bbio); bbio->iter = bio->bi_iter; @@ -3197,7 +3247,7 @@ struct bio *btrfs_bio_clone_partial(struct bio *orig, u64 offset, u64 size) * a contiguous page to the previous one * @size: portion of page that we want to write * @pg_offset: starting offset in the page - * @bio_flags: flags of the current bio to see if we can merge them + * @compress_type: compression type of the current bio to see if we can merge them * * Attempt to add a page to bio considering stripe alignment etc. * @@ -3209,7 +3259,7 @@ static int btrfs_bio_add_page(struct btrfs_bio_ctrl *bio_ctrl, struct page *page, u64 disk_bytenr, unsigned int size, unsigned int pg_offset, - unsigned long bio_flags) + enum btrfs_compression_type compress_type) { struct bio *bio = bio_ctrl->bio; u32 bio_size = bio->bi_iter.bi_size; @@ -3221,10 +3271,10 @@ static int btrfs_bio_add_page(struct btrfs_bio_ctrl *bio_ctrl, ASSERT(bio); /* The limit should be calculated when bio_ctrl->bio is allocated */ ASSERT(bio_ctrl->len_to_oe_boundary && bio_ctrl->len_to_stripe_boundary); - if (bio_ctrl->bio_flags != bio_flags) + if (bio_ctrl->compress_type != compress_type) return 0; - if (bio_ctrl->bio_flags & EXTENT_BIO_COMPRESSED) + if (bio_ctrl->compress_type != BTRFS_COMPRESS_NONE) contig = bio->bi_iter.bi_sector == sector; else contig = bio_end_sector(bio) == sector; @@ -3267,7 +3317,7 @@ static int calc_bio_boundaries(struct btrfs_bio_ctrl *bio_ctrl, * The split happens for real compressed bio, which happens in * btrfs_submit_compressed_read/write(). */ - if (bio_ctrl->bio_flags & EXTENT_BIO_COMPRESSED) { + if (bio_ctrl->compress_type != BTRFS_COMPRESS_NONE) { bio_ctrl->len_to_oe_boundary = U32_MAX; bio_ctrl->len_to_stripe_boundary = U32_MAX; return 0; @@ -3310,7 +3360,7 @@ static int alloc_new_bio(struct btrfs_inode *inode, unsigned int opf, bio_end_io_t end_io_func, u64 disk_bytenr, u32 offset, u64 file_offset, - unsigned long bio_flags) + enum btrfs_compression_type compress_type) { struct btrfs_fs_info *fs_info = inode->root->fs_info; struct bio *bio; @@ -3321,36 +3371,49 @@ static int alloc_new_bio(struct btrfs_inode *inode, * For compressed page range, its disk_bytenr is always @disk_bytenr * passed in, no matter if we have added any range into previous bio. */ - if (bio_flags & EXTENT_BIO_COMPRESSED) + if (compress_type != BTRFS_COMPRESS_NONE) bio->bi_iter.bi_sector = disk_bytenr >> SECTOR_SHIFT; else bio->bi_iter.bi_sector = (disk_bytenr + offset) >> SECTOR_SHIFT; bio_ctrl->bio = bio; - bio_ctrl->bio_flags = bio_flags; + bio_ctrl->compress_type = compress_type; bio->bi_end_io = end_io_func; bio->bi_private = &inode->io_tree; bio->bi_opf = opf; ret = calc_bio_boundaries(bio_ctrl, inode, file_offset); if (ret < 0) goto error; - if (wbc) { - struct block_device *bdev; - bdev = fs_info->fs_devices->latest_dev->bdev; - bio_set_dev(bio, bdev); - wbc_init_bio(wbc, bio); - } - if (bio_op(bio) == REQ_OP_ZONE_APPEND) { - struct btrfs_device *device; + if (wbc) { + /* + * For Zone append we need the correct block_device that we are + * going to write to set in the bio to be able to respect the + * hardware limitation. Look it up here: + */ + if (bio_op(bio) == REQ_OP_ZONE_APPEND) { + struct btrfs_device *dev; + + dev = btrfs_zoned_get_device(fs_info, disk_bytenr, + fs_info->sectorsize); + if (IS_ERR(dev)) { + ret = PTR_ERR(dev); + goto error; + } - device = btrfs_zoned_get_device(fs_info, disk_bytenr, - fs_info->sectorsize); - if (IS_ERR(device)) { - ret = PTR_ERR(device); - goto error; + bio_set_dev(bio, dev->bdev); + } else { + /* + * Otherwise pick the last added device to support + * cgroup writeback. For multi-device file systems this + * means blk-cgroup policies have to always be set on the + * last added/replaced device. This is a bit odd but has + * been like that for a long time. + */ + bio_set_dev(bio, fs_info->fs_devices->latest_dev->bdev); } - - btrfs_bio(bio)->device = device; + wbc_init_bio(wbc, bio); + } else { + ASSERT(bio_op(bio) != REQ_OP_ZONE_APPEND); } return 0; error: @@ -3372,7 +3435,7 @@ error: * @end_io_func: end_io callback for new bio * @mirror_num: desired mirror to read/write * @prev_bio_flags: flags of previous bio to see if we can merge the current one - * @bio_flags: flags of the current bio to see if we can merge them + * @compress_type: compress type for current bio */ static int submit_extent_page(unsigned int opf, struct writeback_control *wbc, @@ -3381,7 +3444,7 @@ static int submit_extent_page(unsigned int opf, size_t size, unsigned long pg_offset, bio_end_io_t end_io_func, int mirror_num, - unsigned long bio_flags, + enum btrfs_compression_type compress_type, bool force_bio_submit) { int ret = 0; @@ -3393,10 +3456,8 @@ static int submit_extent_page(unsigned int opf, ASSERT(pg_offset < PAGE_SIZE && size <= PAGE_SIZE && pg_offset + size <= PAGE_SIZE); if (force_bio_submit && bio_ctrl->bio) { - ret = submit_one_bio(bio_ctrl->bio, mirror_num, bio_ctrl->bio_flags); + submit_one_bio(bio_ctrl->bio, mirror_num, bio_ctrl->compress_type); bio_ctrl->bio = NULL; - if (ret < 0) - return ret; } while (cur < pg_offset + size) { @@ -3408,7 +3469,7 @@ static int submit_extent_page(unsigned int opf, ret = alloc_new_bio(inode, bio_ctrl, wbc, opf, end_io_func, disk_bytenr, offset, page_offset(page) + cur, - bio_flags); + compress_type); if (ret < 0) return ret; } @@ -3416,14 +3477,14 @@ static int submit_extent_page(unsigned int opf, * We must go through btrfs_bio_add_page() to ensure each * page range won't cross various boundaries. */ - if (bio_flags & EXTENT_BIO_COMPRESSED) + if (compress_type != BTRFS_COMPRESS_NONE) added = btrfs_bio_add_page(bio_ctrl, page, disk_bytenr, size - offset, pg_offset + offset, - bio_flags); + compress_type); else added = btrfs_bio_add_page(bio_ctrl, page, disk_bytenr + offset, size - offset, - pg_offset + offset, bio_flags); + pg_offset + offset, compress_type); /* Metadata page range should never be split */ if (!is_data_inode(&inode->vfs_inode)) @@ -3437,11 +3498,8 @@ static int submit_extent_page(unsigned int opf, if (added < size - offset) { /* The bio should contain some page(s) */ ASSERT(bio_ctrl->bio->bi_iter.bi_size); - ret = submit_one_bio(bio_ctrl->bio, mirror_num, - bio_ctrl->bio_flags); + submit_one_bio(bio_ctrl->bio, mirror_num, bio_ctrl->compress_type); bio_ctrl->bio = NULL; - if (ret < 0) - return ret; } cur += added; } @@ -3464,7 +3522,7 @@ static int attach_extent_buffer_page(struct extent_buffer *eb, if (page->mapping) lockdep_assert_held(&page->mapping->private_lock); - if (fs_info->sectorsize == PAGE_SIZE) { + if (fs_info->nodesize >= PAGE_SIZE) { if (!PagePrivate(page)) attach_page_private(page, eb); else @@ -3499,7 +3557,7 @@ int set_page_extent_mapped(struct page *page) fs_info = btrfs_sb(page->mapping->host->i_sb); - if (fs_info->sectorsize < PAGE_SIZE) + if (btrfs_is_subpage(fs_info, page)) return btrfs_attach_subpage(fs_info, page, BTRFS_SUBPAGE_DATA); attach_page_private(page, (void *)EXTENT_PAGE_PRIVATE); @@ -3516,7 +3574,7 @@ void clear_page_extent_mapped(struct page *page) return; fs_info = btrfs_sb(page->mapping->host->i_sb); - if (fs_info->sectorsize < PAGE_SIZE) + if (btrfs_is_subpage(fs_info, page)) return btrfs_detach_subpage(fs_info, page); detach_page_private(page); @@ -3555,7 +3613,7 @@ __get_extent_map(struct inode *inode, struct page *page, size_t pg_offset, * XXX JDM: This needs looking at to ensure proper page locking * return 0 on success, otherwise return error */ -int btrfs_do_readpage(struct page *page, struct extent_map **em_cached, +static int btrfs_do_readpage(struct page *page, struct extent_map **em_cached, struct btrfs_bio_ctrl *bio_ctrl, unsigned int read_flags, u64 *prev_em_start) { @@ -3624,16 +3682,13 @@ int btrfs_do_readpage(struct page *page, struct extent_map **em_cached, BUG_ON(extent_map_end(em) <= cur); BUG_ON(end < cur); - if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags)) { - this_bio_flag |= EXTENT_BIO_COMPRESSED; - extent_set_compress_type(&this_bio_flag, - em->compress_type); - } + if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags)) + this_bio_flag = em->compress_type; iosize = min(extent_map_end(em) - cur, end - cur + 1); cur_end = min(extent_map_end(em) - 1, end); iosize = ALIGN(iosize, blocksize); - if (this_bio_flag & EXTENT_BIO_COMPRESSED) + if (this_bio_flag != BTRFS_COMPRESS_NONE) disk_bytenr = em->block_start; else disk_bytenr = em->block_start + extent_offset; @@ -3729,8 +3784,12 @@ int btrfs_do_readpage(struct page *page, struct extent_map **em_cached, this_bio_flag, force_bio_submit); if (ret) { - unlock_extent(tree, cur, cur + iosize - 1); - end_page_read(page, false, cur, iosize); + /* + * We have to unlock the remaining range, or the page + * will never be unlocked. + */ + unlock_extent(tree, cur, end); + end_page_read(page, false, cur, end + 1 - cur); goto out; } cur = cur + iosize; @@ -3740,6 +3799,27 @@ out: return ret; } +int btrfs_read_folio(struct file *file, struct folio *folio) +{ + struct page *page = &folio->page; + struct btrfs_inode *inode = BTRFS_I(page->mapping->host); + u64 start = page_offset(page); + u64 end = start + PAGE_SIZE - 1; + struct btrfs_bio_ctrl bio_ctrl = { 0 }; + int ret; + + btrfs_lock_and_flush_ordered_range(inode, start, end, NULL); + + ret = btrfs_do_readpage(page, NULL, &bio_ctrl, 0, NULL); + /* + * If btrfs_do_readpage() failed we will want to submit the assembled + * bio to do the cleanup. + */ + if (bio_ctrl.bio) + submit_one_bio(bio_ctrl.bio, 0, bio_ctrl.compress_type); + return ret; +} + static inline void contiguous_readpages(struct page *pages[], int nr_pages, u64 start, u64 end, struct extent_map **em_cached, @@ -3758,12 +3838,6 @@ static inline void contiguous_readpages(struct page *pages[], int nr_pages, } } -static void update_nr_written(struct writeback_control *wbc, - unsigned long nr_written) -{ - wbc->nr_to_write -= nr_written; -} - /* * helper for __extent_writepage, doing all of the delayed allocation setup. * @@ -3863,7 +3937,7 @@ static void find_next_dirty_byte(struct btrfs_fs_info *fs_info, * For regular sector size == page size case, since one page only * contains one sector, we return the page offset directly. */ - if (fs_info->sectorsize == PAGE_SIZE) { + if (!btrfs_is_subpage(fs_info, page)) { *start = page_offset(page); *end = page_offset(page) + PAGE_SIZE; return; @@ -3906,10 +3980,12 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode, u64 extent_offset; u64 block_start; struct extent_map *em; + int saved_ret = 0; int ret = 0; int nr = 0; u32 opf = REQ_OP_WRITE; const unsigned int write_flags = wbc_to_write_flags(wbc); + bool has_error = false; bool compressed; ret = btrfs_writepage_cow_fixup(page); @@ -3924,7 +4000,7 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode, * we don't want to touch the inode after unlocking the page, * so we update the mapping writeback index now */ - update_nr_written(wbc, 1); + wbc->nr_to_write--; while (cur <= end) { u64 disk_bytenr; @@ -3959,6 +4035,9 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode, if (IS_ERR(em)) { btrfs_page_set_error(fs_info, page, cur, end - cur + 1); ret = PTR_ERR_OR_ZERO(em); + has_error = true; + if (!saved_ret) + saved_ret = ret; break; } @@ -4022,6 +4101,10 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode, end_bio_extent_writepage, 0, 0, false); if (ret) { + has_error = true; + if (!saved_ret) + saved_ret = ret; + btrfs_page_set_error(fs_info, page, cur, iosize); if (PageWriteback(page)) btrfs_page_clear_writeback(fs_info, page, cur, @@ -4035,8 +4118,10 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode, * If we finish without problem, we should not only clear page dirty, * but also empty subpage dirty bits */ - if (!ret) + if (!has_error) btrfs_page_assert_not_dirty(fs_info, page); + else + ret = saved_ret; *nr_ret = nr; return ret; } @@ -4167,9 +4252,6 @@ void wait_on_extent_buffer_writeback(struct extent_buffer *eb) static void end_extent_buffer_writeback(struct extent_buffer *eb) { - if (test_bit(EXTENT_BUFFER_ZONE_FINISH, &eb->bflags)) - btrfs_zone_finish_endio(eb->fs_info, eb->start, eb->len); - clear_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags); smp_mb__after_atomic(); wake_up_bit(&eb->bflags, EXTENT_BUFFER_WRITEBACK); @@ -4189,14 +4271,12 @@ static noinline_for_stack int lock_extent_buffer_for_io(struct extent_buffer *eb struct extent_page_data *epd) { struct btrfs_fs_info *fs_info = eb->fs_info; - int i, num_pages, failed_page_nr; + int i, num_pages; int flush = 0; int ret = 0; if (!btrfs_try_tree_write_lock(eb)) { - ret = flush_write_bio(epd); - if (ret < 0) - return ret; + flush_write_bio(epd); flush = 1; btrfs_tree_lock(eb); } @@ -4206,9 +4286,7 @@ static noinline_for_stack int lock_extent_buffer_for_io(struct extent_buffer *eb if (!epd->sync_io) return 0; if (!flush) { - ret = flush_write_bio(epd); - if (ret < 0) - return ret; + flush_write_bio(epd); flush = 1; } while (1) { @@ -4246,7 +4324,7 @@ static noinline_for_stack int lock_extent_buffer_for_io(struct extent_buffer *eb * Subpage metadata doesn't use page locking at all, so we can skip * the page locking. */ - if (!ret || fs_info->sectorsize < PAGE_SIZE) + if (!ret || fs_info->nodesize < PAGE_SIZE) return ret; num_pages = num_extent_pages(eb); @@ -4255,14 +4333,7 @@ static noinline_for_stack int lock_extent_buffer_for_io(struct extent_buffer *eb if (!trylock_page(p)) { if (!flush) { - int err; - - err = flush_write_bio(epd); - if (err < 0) { - ret = err; - failed_page_nr = i; - goto err_unlock; - } + flush_write_bio(epd); flush = 1; } lock_page(p); @@ -4270,25 +4341,6 @@ static noinline_for_stack int lock_extent_buffer_for_io(struct extent_buffer *eb } return ret; -err_unlock: - /* Unlock already locked pages */ - for (i = 0; i < failed_page_nr; i++) - unlock_page(eb->pages[i]); - /* - * Clear EXTENT_BUFFER_WRITEBACK and wake up anyone waiting on it. - * Also set back EXTENT_BUFFER_DIRTY so future attempts to this eb can - * be made and undo everything done before. - */ - btrfs_tree_lock(eb); - spin_lock(&eb->refs_lock); - set_bit(EXTENT_BUFFER_DIRTY, &eb->bflags); - end_extent_buffer_writeback(eb); - spin_unlock(&eb->refs_lock); - percpu_counter_add_batch(&fs_info->dirty_metadata_bytes, eb->len, - fs_info->dirty_metadata_batch); - btrfs_clear_header_flag(eb, BTRFS_HEADER_FLAG_WRITTEN); - btrfs_tree_unlock(eb); - return ret; } static void set_btree_ioerr(struct page *page, struct extent_buffer *eb) @@ -4383,8 +4435,8 @@ static struct extent_buffer *find_extent_buffer_nolock( struct extent_buffer *eb; rcu_read_lock(); - eb = radix_tree_lookup(&fs_info->buffer_radix, - start >> fs_info->sectorsize_bits); + eb = xa_load(&fs_info->extent_buffers, + start >> fs_info->sectorsize_bits); if (eb && atomic_inc_not_zero(&eb->refs)) { rcu_read_unlock(); return eb; @@ -4406,7 +4458,7 @@ static void end_bio_subpage_eb_writepage(struct bio *bio) struct bvec_iter_all iter_all; fs_info = btrfs_sb(bio_first_page_all(bio)->mapping->host->i_sb); - ASSERT(fs_info->sectorsize < PAGE_SIZE); + ASSERT(fs_info->nodesize < PAGE_SIZE); ASSERT(!bio_flagged(bio, BIO_CLONED)); bio_for_each_segment_all(bvec, bio, iter_all) { @@ -4558,7 +4610,7 @@ static int write_one_subpage_eb(struct extent_buffer *eb, * dirty anymore, we have submitted a page. Update nr_written in wbc. */ if (no_dirty_ebs) - update_nr_written(wbc, 1); + wbc->nr_to_write--; return ret; } @@ -4594,7 +4646,7 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb, break; } disk_bytenr += PAGE_SIZE; - update_nr_written(wbc, 1); + wbc->nr_to_write--; unlock_page(p); } @@ -4733,7 +4785,7 @@ static int submit_eb_page(struct page *page, struct writeback_control *wbc, if (!PagePrivate(page)) return 0; - if (btrfs_sb(page->mapping->host->i_sb)->sectorsize < PAGE_SIZE) + if (btrfs_sb(page->mapping->host->i_sb)->nodesize < PAGE_SIZE) return submit_eb_subpage(page, wbc, epd); spin_lock(&mapping->private_lock); @@ -4789,8 +4841,7 @@ static int submit_eb_page(struct page *page, struct writeback_control *wbc, /* * Implies write in zoned mode. Mark the last eb in a block group. */ - if (cache->seq_zone && eb->start + eb->len == cache->zone_capacity) - set_bit(EXTENT_BUFFER_ZONE_FINISH, &eb->bflags); + btrfs_schedule_zone_finish_bg(cache, eb); btrfs_put_block_group(cache); } ret = write_one_eb(eb, wbc, epd); @@ -4909,13 +4960,19 @@ retry: * if the fs already has error. */ if (!BTRFS_FS_ERROR(fs_info)) { - ret = flush_write_bio(&epd); + flush_write_bio(&epd); } else { ret = -EROFS; end_write_bio(&epd, ret); } out: btrfs_zoned_meta_io_unlock(fs_info); + /* + * We can get ret > 0 from submit_extent_page() indicating how many ebs + * were submitted. Reset it to 0 to avoid false alerts for the caller. + */ + if (ret > 0) + ret = 0; return ret; } @@ -5017,8 +5074,7 @@ retry: * tmpfs file mapping */ if (!trylock_page(page)) { - ret = flush_write_bio(epd); - BUG_ON(ret < 0); + flush_write_bio(epd); lock_page(page); } @@ -5028,10 +5084,8 @@ retry: } if (wbc->sync_mode != WB_SYNC_NONE) { - if (PageWriteback(page)) { - ret = flush_write_bio(epd); - BUG_ON(ret < 0); - } + if (PageWriteback(page)) + flush_write_bio(epd); wait_on_page_writeback(page); } @@ -5071,9 +5125,8 @@ retry: * page in our current bio, and thus deadlock, so flush the * write bio here. */ - ret = flush_write_bio(epd); - if (!ret) - goto retry; + flush_write_bio(epd); + goto retry; } if (wbc->range_cyclic || (wbc->nr_to_write > 0 && range_whole)) @@ -5099,8 +5152,7 @@ int extent_write_full_page(struct page *page, struct writeback_control *wbc) return ret; } - ret = flush_write_bio(&epd); - ASSERT(ret <= 0); + flush_write_bio(&epd); return ret; } @@ -5162,7 +5214,7 @@ int extent_write_locked_range(struct inode *inode, u64 start, u64 end) } if (!found_error) - ret = flush_write_bio(&epd); + flush_write_bio(&epd); else end_write_bio(&epd, ret); @@ -5195,7 +5247,7 @@ int extent_writepages(struct address_space *mapping, end_write_bio(&epd, ret); return ret; } - ret = flush_write_bio(&epd); + flush_write_bio(&epd); return ret; } @@ -5218,10 +5270,8 @@ void extent_readahead(struct readahead_control *rac) if (em_cached) free_extent_map(em_cached); - if (bio_ctrl.bio) { - if (submit_one_bio(bio_ctrl.bio, 0, bio_ctrl.bio_flags)) - return; - } + if (bio_ctrl.bio) + submit_one_bio(bio_ctrl.bio, 0, bio_ctrl.compress_type); } /* @@ -5257,7 +5307,7 @@ int extent_invalidate_folio(struct extent_io_tree *tree, } /* - * a helper for releasepage, this tests for areas of the page that + * a helper for release_folio, this tests for areas of the page that * are locked or under IO and drops the related state bits if it is safe * to drop the page. */ @@ -5293,7 +5343,7 @@ static int try_release_extent_state(struct extent_io_tree *tree, } /* - * a helper for releasepage. As long as there are no locked extents + * a helper for release_folio. As long as there are no locked extents * in the range corresponding to the page, both state records and extent * map records are removed */ @@ -5790,7 +5840,7 @@ static void detach_extent_buffer_page(struct extent_buffer *eb, struct page *pag return; } - if (fs_info->sectorsize == PAGE_SIZE) { + if (fs_info->nodesize >= PAGE_SIZE) { /* * We do this since we'll remove the pages after we've * removed the eb from the radix tree, so we could race @@ -5897,9 +5947,9 @@ __alloc_extent_buffer(struct btrfs_fs_info *fs_info, u64 start, struct extent_buffer *btrfs_clone_extent_buffer(const struct extent_buffer *src) { int i; - struct page *p; struct extent_buffer *new; int num_pages = num_extent_pages(src); + int ret; new = __alloc_extent_buffer(src->fs_info, src->start, src->len); if (new == NULL) @@ -5912,22 +5962,23 @@ struct extent_buffer *btrfs_clone_extent_buffer(const struct extent_buffer *src) */ set_bit(EXTENT_BUFFER_UNMAPPED, &new->bflags); + memset(new->pages, 0, sizeof(*new->pages) * num_pages); + ret = btrfs_alloc_page_array(num_pages, new->pages); + if (ret) { + btrfs_release_extent_buffer(new); + return NULL; + } + for (i = 0; i < num_pages; i++) { int ret; + struct page *p = new->pages[i]; - p = alloc_page(GFP_NOFS); - if (!p) { - btrfs_release_extent_buffer(new); - return NULL; - } ret = attach_extent_buffer_page(new, p, NULL); if (ret < 0) { - put_page(p); btrfs_release_extent_buffer(new); return NULL; } WARN_ON(PageDirty(p)); - new->pages[i] = p; copy_page(page_address(p), page_address(src->pages[i])); } set_extent_buffer_uptodate(new); @@ -5941,31 +5992,36 @@ struct extent_buffer *__alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info, struct extent_buffer *eb; int num_pages; int i; + int ret; eb = __alloc_extent_buffer(fs_info, start, len); if (!eb) return NULL; num_pages = num_extent_pages(eb); + ret = btrfs_alloc_page_array(num_pages, eb->pages); + if (ret) + goto err; + for (i = 0; i < num_pages; i++) { - int ret; + struct page *p = eb->pages[i]; - eb->pages[i] = alloc_page(GFP_NOFS); - if (!eb->pages[i]) - goto err; - ret = attach_extent_buffer_page(eb, eb->pages[i], NULL); + ret = attach_extent_buffer_page(eb, p, NULL); if (ret < 0) goto err; } + set_extent_buffer_uptodate(eb); btrfs_set_header_nritems(eb, 0); set_bit(EXTENT_BUFFER_UNMAPPED, &eb->bflags); return eb; err: - for (; i > 0; i--) { - detach_extent_buffer_page(eb, eb->pages[i - 1]); - __free_page(eb->pages[i - 1]); + for (i = 0; i < num_pages; i++) { + if (eb->pages[i]) { + detach_extent_buffer_page(eb, eb->pages[i]); + __free_page(eb->pages[i]); + } } __free_extent_buffer(eb); return NULL; @@ -5987,10 +6043,10 @@ static void check_buffer_tree_ref(struct extent_buffer *eb) * * It is only cleared in two cases: freeing the last non-tree * reference to the extent_buffer when its STALE bit is set or - * calling releasepage when the tree reference is the only reference. + * calling release_folio when the tree reference is the only reference. * * In both cases, care is taken to ensure that the extent_buffer's - * pages are not under io. However, releasepage can be concurrently + * pages are not under io. However, release_folio can be concurrently * called with creating new references, which is prone to race * conditions between the calls to check_buffer_tree_ref in those * codepaths and clearing TREE_REF in try_release_extent_buffer. @@ -6072,24 +6128,22 @@ struct extent_buffer *alloc_test_extent_buffer(struct btrfs_fs_info *fs_info, if (!eb) return ERR_PTR(-ENOMEM); eb->fs_info = fs_info; -again: - ret = radix_tree_preload(GFP_NOFS); - if (ret) { - exists = ERR_PTR(ret); - goto free_eb; - } - spin_lock(&fs_info->buffer_lock); - ret = radix_tree_insert(&fs_info->buffer_radix, - start >> fs_info->sectorsize_bits, eb); - spin_unlock(&fs_info->buffer_lock); - radix_tree_preload_end(); - if (ret == -EEXIST) { - exists = find_extent_buffer(fs_info, start); - if (exists) + + do { + ret = xa_insert(&fs_info->extent_buffers, + start >> fs_info->sectorsize_bits, + eb, GFP_NOFS); + if (ret == -ENOMEM) { + exists = ERR_PTR(ret); goto free_eb; - else - goto again; - } + } + if (ret == -EBUSY) { + exists = find_extent_buffer(fs_info, start); + if (exists) + goto free_eb; + } + } while (ret); + check_buffer_tree_ref(eb); set_bit(EXTENT_BUFFER_IN_TREE, &eb->bflags); @@ -6110,7 +6164,7 @@ static struct extent_buffer *grab_extent_buffer( * don't try to insert two ebs for the same bytenr. So here we always * return NULL and just continue. */ - if (fs_info->sectorsize < PAGE_SIZE) + if (fs_info->nodesize < PAGE_SIZE) return NULL; /* Page not yet attached to an extent buffer */ @@ -6132,6 +6186,30 @@ static struct extent_buffer *grab_extent_buffer( return NULL; } +static int check_eb_alignment(struct btrfs_fs_info *fs_info, u64 start) +{ + if (!IS_ALIGNED(start, fs_info->sectorsize)) { + btrfs_err(fs_info, "bad tree block start %llu", start); + return -EINVAL; + } + + if (fs_info->nodesize < PAGE_SIZE && + offset_in_page(start) + fs_info->nodesize > PAGE_SIZE) { + btrfs_err(fs_info, + "tree block crosses page boundary, start %llu nodesize %u", + start, fs_info->nodesize); + return -EINVAL; + } + if (fs_info->nodesize >= PAGE_SIZE && + !IS_ALIGNED(start, PAGE_SIZE)) { + btrfs_err(fs_info, + "tree block is not page aligned, start %llu nodesize %u", + start, fs_info->nodesize); + return -EINVAL; + } + return 0; +} + struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, u64 start, u64 owner_root, int level) { @@ -6146,10 +6224,8 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, int uptodate = 1; int ret; - if (!IS_ALIGNED(start, fs_info->sectorsize)) { - btrfs_err(fs_info, "bad tree block start %llu", start); + if (check_eb_alignment(fs_info, start)) return ERR_PTR(-EINVAL); - } #if BITS_PER_LONG == 32 if (start >= MAX_LFS_FILESIZE) { @@ -6162,14 +6238,6 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, btrfs_warn_32bit_limit(fs_info); #endif - if (fs_info->sectorsize < PAGE_SIZE && - offset_in_page(start) + len > PAGE_SIZE) { - btrfs_err(fs_info, - "tree block crosses page boundary, start %llu nodesize %lu", - start, len); - return ERR_PTR(-EINVAL); - } - eb = find_extent_buffer(fs_info, start); if (eb) return eb; @@ -6199,7 +6267,7 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, * page, but it may change in the future for 16K page size * support, so we still preallocate the memory in the loop. */ - if (fs_info->sectorsize < PAGE_SIZE) { + if (fs_info->nodesize < PAGE_SIZE) { prealloc = btrfs_alloc_subpage(fs_info, BTRFS_SUBPAGE_METADATA); if (IS_ERR(prealloc)) { ret = PTR_ERR(prealloc); @@ -6243,39 +6311,36 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, /* * We can't unlock the pages just yet since the extent buffer * hasn't been properly inserted in the radix tree, this - * opens a race with btree_releasepage which can free a page + * opens a race with btree_release_folio which can free a page * while we are still filling in all pages for the buffer and * we could crash. */ } if (uptodate) set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags); -again: - ret = radix_tree_preload(GFP_NOFS); - if (ret) { - exists = ERR_PTR(ret); - goto free_eb; - } - - spin_lock(&fs_info->buffer_lock); - ret = radix_tree_insert(&fs_info->buffer_radix, - start >> fs_info->sectorsize_bits, eb); - spin_unlock(&fs_info->buffer_lock); - radix_tree_preload_end(); - if (ret == -EEXIST) { - exists = find_extent_buffer(fs_info, start); - if (exists) + + do { + ret = xa_insert(&fs_info->extent_buffers, + start >> fs_info->sectorsize_bits, + eb, GFP_NOFS); + if (ret == -ENOMEM) { + exists = ERR_PTR(ret); goto free_eb; - else - goto again; - } + } + if (ret == -EBUSY) { + exists = find_extent_buffer(fs_info, start); + if (exists) + goto free_eb; + } + } while (ret); + /* add one reference for the tree */ check_buffer_tree_ref(eb); set_bit(EXTENT_BUFFER_IN_TREE, &eb->bflags); /* * Now it's safe to unlock the pages because any calls to - * btree_releasepage will correctly detect that a page belongs to a + * btree_release_folio will correctly detect that a page belongs to a * live buffer and won't free them prematurely. */ for (i = 0; i < num_pages; i++) @@ -6313,10 +6378,8 @@ static int release_extent_buffer(struct extent_buffer *eb) spin_unlock(&eb->refs_lock); - spin_lock(&fs_info->buffer_lock); - radix_tree_delete(&fs_info->buffer_radix, - eb->start >> fs_info->sectorsize_bits); - spin_unlock(&fs_info->buffer_lock); + xa_erase(&fs_info->extent_buffers, + eb->start >> fs_info->sectorsize_bits); } else { spin_unlock(&eb->refs_lock); } @@ -6418,7 +6481,7 @@ void clear_extent_buffer_dirty(const struct extent_buffer *eb) int num_pages; struct page *page; - if (eb->fs_info->sectorsize < PAGE_SIZE) + if (eb->fs_info->nodesize < PAGE_SIZE) return clear_subpage_extent_buffer_dirty(eb); num_pages = num_extent_pages(eb); @@ -6450,7 +6513,7 @@ bool set_extent_buffer_dirty(struct extent_buffer *eb) WARN_ON(!test_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags)); if (!was_dirty) { - bool subpage = eb->fs_info->sectorsize < PAGE_SIZE; + bool subpage = eb->fs_info->nodesize < PAGE_SIZE; /* * For subpage case, we can have other extent buffers in the @@ -6490,9 +6553,18 @@ void clear_extent_buffer_uptodate(struct extent_buffer *eb) num_pages = num_extent_pages(eb); for (i = 0; i < num_pages; i++) { page = eb->pages[i]; - if (page) - btrfs_page_clear_uptodate(fs_info, page, - eb->start, eb->len); + if (!page) + continue; + + /* + * This is special handling for metadata subpage, as regular + * btrfs_is_subpage() can not handle cloned/dummy metadata. + */ + if (fs_info->nodesize >= PAGE_SIZE) + ClearPageUptodate(page); + else + btrfs_subpage_clear_uptodate(fs_info, page, eb->start, + eb->len); } } @@ -6507,7 +6579,16 @@ void set_extent_buffer_uptodate(struct extent_buffer *eb) num_pages = num_extent_pages(eb); for (i = 0; i < num_pages; i++) { page = eb->pages[i]; - btrfs_page_set_uptodate(fs_info, page, eb->start, eb->len); + + /* + * This is special handling for metadata subpage, as regular + * btrfs_is_subpage() can not handle cloned/dummy metadata. + */ + if (fs_info->nodesize >= PAGE_SIZE) + SetPageUptodate(page); + else + btrfs_subpage_set_uptodate(fs_info, page, eb->start, + eb->len); } } @@ -6563,12 +6644,8 @@ static int read_extent_buffer_subpage(struct extent_buffer *eb, int wait, atomic_dec(&eb->io_pages); } if (bio_ctrl.bio) { - int tmp; - - tmp = submit_one_bio(bio_ctrl.bio, mirror_num, 0); + submit_one_bio(bio_ctrl.bio, mirror_num, 0); bio_ctrl.bio = NULL; - if (tmp < 0) - return tmp; } if (ret || wait != WAIT_COMPLETE) return ret; @@ -6602,7 +6679,7 @@ int read_extent_buffer_pages(struct extent_buffer *eb, int wait, int mirror_num) if (unlikely(test_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags))) return -EIO; - if (eb->fs_info->sectorsize < PAGE_SIZE) + if (eb->fs_info->nodesize < PAGE_SIZE) return read_extent_buffer_subpage(eb, wait, mirror_num); num_pages = num_extent_pages(eb); @@ -6645,7 +6722,7 @@ int read_extent_buffer_pages(struct extent_buffer *eb, int wait, int mirror_num) eb->read_mirror = 0; atomic_set(&eb->io_pages, num_reads); /* - * It is possible for releasepage to clear the TREE_REF bit before we + * It is possible for release_folio to clear the TREE_REF bit before we * set io_pages. See check_buffer_tree_ref for a more detailed comment. */ check_buffer_tree_ref(eb); @@ -6681,10 +6758,8 @@ int read_extent_buffer_pages(struct extent_buffer *eb, int wait, int mirror_num) } if (bio_ctrl.bio) { - err = submit_one_bio(bio_ctrl.bio, mirror_num, bio_ctrl.bio_flags); + submit_one_bio(bio_ctrl.bio, mirror_num, bio_ctrl.compress_type); bio_ctrl.bio = NULL; - if (err) - return err; } if (ret || wait != WAIT_COMPLETE) @@ -6857,7 +6932,7 @@ static void assert_eb_page_uptodate(const struct extent_buffer *eb, * would have !PageUptodate && !PageError, as we clear PageError before * reading. */ - if (fs_info->sectorsize < PAGE_SIZE) { + if (fs_info->nodesize < PAGE_SIZE) { bool uptodate, error; uptodate = btrfs_subpage_test_uptodate(fs_info, page, @@ -6959,7 +7034,7 @@ void copy_extent_buffer_full(const struct extent_buffer *dst, ASSERT(dst->len == src->len); - if (dst->fs_info->sectorsize == PAGE_SIZE) { + if (dst->fs_info->nodesize >= PAGE_SIZE) { num_pages = num_extent_pages(dst); for (i = 0; i < num_pages; i++) copy_page(page_address(dst->pages[i]), @@ -6968,7 +7043,7 @@ void copy_extent_buffer_full(const struct extent_buffer *dst, size_t src_offset = get_eb_offset_in_page(src, 0); size_t dst_offset = get_eb_offset_in_page(dst, 0); - ASSERT(src->fs_info->sectorsize < PAGE_SIZE); + ASSERT(src->fs_info->nodesize < PAGE_SIZE); memcpy(page_address(dst->pages[0]) + dst_offset, page_address(src->pages[0]) + src_offset, src->len); @@ -7249,42 +7324,25 @@ void memmove_extent_buffer(const struct extent_buffer *dst, } } -#define GANG_LOOKUP_SIZE 16 static struct extent_buffer *get_next_extent_buffer( struct btrfs_fs_info *fs_info, struct page *page, u64 bytenr) { - struct extent_buffer *gang[GANG_LOOKUP_SIZE]; - struct extent_buffer *found = NULL; + struct extent_buffer *eb; + unsigned long index; u64 page_start = page_offset(page); - u64 cur = page_start; ASSERT(in_range(bytenr, page_start, PAGE_SIZE)); lockdep_assert_held(&fs_info->buffer_lock); - while (cur < page_start + PAGE_SIZE) { - int ret; - int i; - - ret = radix_tree_gang_lookup(&fs_info->buffer_radix, - (void **)gang, cur >> fs_info->sectorsize_bits, - min_t(unsigned int, GANG_LOOKUP_SIZE, - PAGE_SIZE / fs_info->nodesize)); - if (ret == 0) - goto out; - for (i = 0; i < ret; i++) { - /* Already beyond page end */ - if (gang[i]->start >= page_start + PAGE_SIZE) - goto out; - /* Found one */ - if (gang[i]->start >= bytenr) { - found = gang[i]; - goto out; - } - } - cur = gang[ret - 1]->start + gang[ret - 1]->len; + xa_for_each_start(&fs_info->extent_buffers, index, eb, + page_start >> fs_info->sectorsize_bits) { + if (in_range(eb->start, page_start, PAGE_SIZE)) + return eb; + else if (eb->start >= page_start + PAGE_SIZE) + /* Already beyond page end */ + return NULL; } -out: - return found; + return NULL; } static int try_release_subpage_extent_buffer(struct page *page) @@ -7361,7 +7419,7 @@ int try_release_extent_buffer(struct page *page) { struct extent_buffer *eb; - if (btrfs_sb(page->mapping->host->i_sb)->sectorsize < PAGE_SIZE) + if (btrfs_sb(page->mapping->host->i_sb)->nodesize < PAGE_SIZE) return try_release_subpage_extent_buffer(page); /* diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index 0399cf8e3c32..23d4103c8831 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -7,15 +7,9 @@ #include <linux/refcount.h> #include <linux/fiemap.h> #include <linux/btrfs_tree.h> +#include "compression.h" #include "ulist.h" -/* - * flags for bio submission. The high bits indicate the compression - * type for this bio - */ -#define EXTENT_BIO_COMPRESSED 1 -#define EXTENT_BIO_FLAG_SHIFT 16 - enum { EXTENT_BUFFER_UPTODATE, EXTENT_BUFFER_DIRTY, @@ -32,7 +26,6 @@ enum { /* write IO error */ EXTENT_BUFFER_WRITE_ERR, EXTENT_BUFFER_NO_CHECK, - EXTENT_BUFFER_ZONE_FINISH, }; /* these are flags for __process_pages_contig */ @@ -71,9 +64,9 @@ struct btrfs_fs_info; struct io_failure_record; struct extent_io_tree; -typedef blk_status_t (submit_bio_hook_t)(struct inode *inode, struct bio *bio, +typedef void (submit_bio_hook_t)(struct inode *inode, struct bio *bio, int mirror_num, - unsigned long bio_flags); + enum btrfs_compression_type compress_type); typedef blk_status_t (extent_submit_bio_start_t)(struct inode *inode, struct bio *bio, u64 dio_file_offset); @@ -103,22 +96,11 @@ struct extent_buffer { }; /* - * Structure to record info about the bio being assembled, and other info like - * how many bytes are there before stripe/ordered extent boundary. - */ -struct btrfs_bio_ctrl { - struct bio *bio; - unsigned long bio_flags; - u32 len_to_stripe_boundary; - u32 len_to_oe_boundary; -}; - -/* * Structure to record how many bytes and which ranges are set/cleared */ struct extent_changeset { /* How many bytes are set/cleared in this operation */ - unsigned int bytes_changed; + u64 bytes_changed; /* Changed ranges */ struct ulist range_changed; @@ -158,17 +140,6 @@ static inline void extent_changeset_free(struct extent_changeset *changeset) kfree(changeset); } -static inline void extent_set_compress_type(unsigned long *bio_flags, - int compress_type) -{ - *bio_flags |= compress_type << EXTENT_BIO_FLAG_SHIFT; -} - -static inline int extent_compress_type(unsigned long bio_flags) -{ - return bio_flags >> EXTENT_BIO_FLAG_SHIFT; -} - struct extent_map_tree; typedef struct extent_map *(get_extent_t)(struct btrfs_inode *inode, @@ -178,11 +149,7 @@ typedef struct extent_map *(get_extent_t)(struct btrfs_inode *inode, int try_release_extent_mapping(struct page *page, gfp_t mask); int try_release_extent_buffer(struct page *page); -int __must_check submit_one_bio(struct bio *bio, int mirror_num, - unsigned long bio_flags); -int btrfs_do_readpage(struct page *page, struct extent_map **em_cached, - struct btrfs_bio_ctrl *bio_ctrl, - unsigned int read_flags, u64 *prev_em_start); +int btrfs_read_folio(struct file *file, struct folio *folio); int extent_write_full_page(struct page *page, struct writeback_control *wbc); int extent_write_locked_range(struct inode *inode, u64 start, u64 end); int extent_writepages(struct address_space *mapping, @@ -277,8 +244,10 @@ void extent_range_redirty_for_io(struct inode *inode, u64 start, u64 end); void extent_clear_unlock_delalloc(struct btrfs_inode *inode, u64 start, u64 end, struct page *locked_page, u32 bits_to_clear, unsigned long page_ops); + +int btrfs_alloc_page_array(unsigned int nr_pages, struct page **page_array); struct bio *btrfs_bio_alloc(unsigned int nr_iovecs); -struct bio *btrfs_bio_clone(struct bio *bio); +struct bio *btrfs_bio_clone(struct block_device *bdev, struct bio *bio); struct bio *btrfs_bio_clone_partial(struct bio *orig, u64 offset, u64 size); void end_extent_writepage(struct page *page, int err, u64 start, u64 end); @@ -297,7 +266,7 @@ struct io_failure_record { u64 start; u64 len; u64 logical; - unsigned long bio_flags; + enum btrfs_compression_type compress_type; int this_mirror; int failed_mirror; }; diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 9f455c96c974..1fd827b99c1b 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1307,11 +1307,12 @@ static int prepare_uptodate_page(struct inode *inode, struct page *page, u64 pos, bool force_uptodate) { + struct folio *folio = page_folio(page); int ret = 0; if (((pos & (PAGE_SIZE - 1)) || force_uptodate) && !PageUptodate(page)) { - ret = btrfs_readpage(NULL, page); + ret = btrfs_read_folio(NULL, folio); if (ret) return ret; lock_page(page); @@ -1321,8 +1322,8 @@ static int prepare_uptodate_page(struct inode *inode, } /* - * Since btrfs_readpage() will unlock the page before it - * returns, there is a window where btrfs_releasepage() can be + * Since btrfs_read_folio() will unlock the folio before it + * returns, there is a window where btrfs_release_folio() can be * called to release the page. Here we check both inode * mapping and PagePrivate() to make sure the page was not * released. @@ -1460,8 +1461,27 @@ lock_and_cleanup_extent_if_need(struct btrfs_inode *inode, struct page **pages, return ret; } -static int check_can_nocow(struct btrfs_inode *inode, loff_t pos, - size_t *write_bytes, bool nowait) +/* + * Check if we can do nocow write into the range [@pos, @pos + @write_bytes) + * + * @pos: File offset. + * @write_bytes: The length to write, will be updated to the nocow writeable + * range. + * + * This function will flush ordered extents in the range to ensure proper + * nocow checks. + * + * Return: + * > 0 If we can nocow, and updates @write_bytes. + * 0 If we can't do a nocow write. + * -EAGAIN If we can't do a nocow write because snapshoting of the inode's + * root is in progress. + * < 0 If an error happened. + * + * NOTE: Callers need to call btrfs_check_nocow_unlock() if we return > 0. + */ +int btrfs_check_nocow_lock(struct btrfs_inode *inode, loff_t pos, + size_t *write_bytes) { struct btrfs_fs_info *fs_info = inode->root->fs_info; struct btrfs_root *root = inode->root; @@ -1472,7 +1492,7 @@ static int check_can_nocow(struct btrfs_inode *inode, loff_t pos, if (!(inode->flags & (BTRFS_INODE_NODATACOW | BTRFS_INODE_PREALLOC))) return 0; - if (!nowait && !btrfs_drew_try_write_lock(&root->snapshot_lock)) + if (!btrfs_drew_try_write_lock(&root->snapshot_lock)) return -EAGAIN; lockstart = round_down(pos, fs_info->sectorsize); @@ -1480,71 +1500,21 @@ static int check_can_nocow(struct btrfs_inode *inode, loff_t pos, fs_info->sectorsize) - 1; num_bytes = lockend - lockstart + 1; - if (nowait) { - struct btrfs_ordered_extent *ordered; - - if (!try_lock_extent(&inode->io_tree, lockstart, lockend)) - return -EAGAIN; - - ordered = btrfs_lookup_ordered_range(inode, lockstart, - num_bytes); - if (ordered) { - btrfs_put_ordered_extent(ordered); - ret = -EAGAIN; - goto out_unlock; - } - } else { - btrfs_lock_and_flush_ordered_range(inode, lockstart, - lockend, NULL); - } - + btrfs_lock_and_flush_ordered_range(inode, lockstart, lockend, NULL); ret = can_nocow_extent(&inode->vfs_inode, lockstart, &num_bytes, NULL, NULL, NULL, false); if (ret <= 0) { ret = 0; - if (!nowait) - btrfs_drew_write_unlock(&root->snapshot_lock); + btrfs_drew_write_unlock(&root->snapshot_lock); } else { *write_bytes = min_t(size_t, *write_bytes , num_bytes - pos + lockstart); } -out_unlock: unlock_extent(&inode->io_tree, lockstart, lockend); return ret; } -static int check_nocow_nolock(struct btrfs_inode *inode, loff_t pos, - size_t *write_bytes) -{ - return check_can_nocow(inode, pos, write_bytes, true); -} - -/* - * Check if we can do nocow write into the range [@pos, @pos + @write_bytes) - * - * @pos: File offset - * @write_bytes: The length to write, will be updated to the nocow writeable - * range - * - * This function will flush ordered extents in the range to ensure proper - * nocow checks. - * - * Return: - * >0 and update @write_bytes if we can do nocow write - * 0 if we can't do nocow write - * -EAGAIN if we can't get the needed lock or there are ordered extents - * for * (nowait == true) case - * <0 if other error happened - * - * NOTE: Callers need to release the lock by btrfs_check_nocow_unlock(). - */ -int btrfs_check_nocow_lock(struct btrfs_inode *inode, loff_t pos, - size_t *write_bytes) -{ - return check_can_nocow(inode, pos, write_bytes, false); -} - void btrfs_check_nocow_unlock(struct btrfs_inode *inode) { btrfs_drew_write_unlock(&inode->root->snapshot_lock); @@ -1579,20 +1549,15 @@ static int btrfs_write_check(struct kiocb *iocb, struct iov_iter *from, loff_t oldsize; loff_t start_pos; - if (iocb->ki_flags & IOCB_NOWAIT) { - size_t nocow_bytes = count; - - /* We will allocate space in case nodatacow is not set, so bail */ - if (check_nocow_nolock(BTRFS_I(inode), pos, &nocow_bytes) <= 0) - return -EAGAIN; - /* - * There are holes in the range or parts of the range that must - * be COWed (shared extents, RO block groups, etc), so just bail - * out. - */ - if (nocow_bytes < count) - return -EAGAIN; - } + /* + * Quickly bail out on NOWAIT writes if we don't have the nodatacow or + * prealloc flags, as without those flags we always have to COW. We will + * later check if we can really COW into the target range (using + * can_nocow_extent() at btrfs_get_blocks_direct_write()). + */ + if ((iocb->ki_flags & IOCB_NOWAIT) && + !(BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW | BTRFS_INODE_PREALLOC))) + return -EAGAIN; current->backing_dev_info = inode_to_bdi(inode); ret = file_remove_privs(file); @@ -1720,7 +1685,7 @@ static noinline ssize_t btrfs_buffered_write(struct kiocb *iocb, WARN_ON(reserve_bytes == 0); ret = btrfs_delalloc_reserve_metadata(BTRFS_I(inode), reserve_bytes, - reserve_bytes); + reserve_bytes, false); if (ret) { if (!only_release_metadata) btrfs_free_reserved_data_space(BTRFS_I(inode), @@ -1965,8 +1930,7 @@ relock: */ again: from->nofault = true; - err = iomap_dio_rw(iocb, from, &btrfs_dio_iomap_ops, &btrfs_dio_ops, - IOMAP_DIO_PARTIAL, written); + err = btrfs_dio_rw(iocb, from, written); from->nofault = false; /* No increment (+=) because iomap returns a cumulative value. */ @@ -2401,7 +2365,7 @@ static int btrfs_file_mmap(struct file *filp, struct vm_area_struct *vma) { struct address_space *mapping = filp->f_mapping; - if (!mapping->a_ops->readpage) + if (!mapping->a_ops->read_folio) return -ENOEXEC; file_accessed(filp); @@ -2570,10 +2534,10 @@ static int find_first_non_hole(struct btrfs_inode *inode, u64 *start, u64 *len) return ret; } -static int btrfs_punch_hole_lock_range(struct inode *inode, - const u64 lockstart, - const u64 lockend, - struct extent_state **cached_state) +static void btrfs_punch_hole_lock_range(struct inode *inode, + const u64 lockstart, + const u64 lockend, + struct extent_state **cached_state) { /* * For subpage case, if the range is not at page boundary, we could @@ -2587,40 +2551,29 @@ static int btrfs_punch_hole_lock_range(struct inode *inode, const u64 page_lockend = round_down(lockend + 1, PAGE_SIZE) - 1; while (1) { - struct btrfs_ordered_extent *ordered; - int ret; - truncate_pagecache_range(inode, lockstart, lockend); lock_extent_bits(&BTRFS_I(inode)->io_tree, lockstart, lockend, cached_state); - ordered = btrfs_lookup_first_ordered_extent(BTRFS_I(inode), - lockend); - /* - * We need to make sure we have no ordered extents in this range - * and nobody raced in and read a page in this range, if we did - * we need to try again. + * We can't have ordered extents in the range, nor dirty/writeback + * pages, because we have locked the inode's VFS lock in exclusive + * mode, we have locked the inode's i_mmap_lock in exclusive mode, + * we have flushed all delalloc in the range and we have waited + * for any ordered extents in the range to complete. + * We can race with anyone reading pages from this range, so after + * locking the range check if we have pages in the range, and if + * we do, unlock the range and retry. */ - if ((!ordered || - (ordered->file_offset + ordered->num_bytes <= lockstart || - ordered->file_offset > lockend)) && - !filemap_range_has_page(inode->i_mapping, - page_lockstart, page_lockend)) { - if (ordered) - btrfs_put_ordered_extent(ordered); + if (!filemap_range_has_page(inode->i_mapping, page_lockstart, + page_lockend)) break; - } - if (ordered) - btrfs_put_ordered_extent(ordered); + unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart, lockend, cached_state); - ret = btrfs_wait_ordered_range(inode, lockstart, - lockend - lockstart + 1); - if (ret) - return ret; } - return 0; + + btrfs_assert_inode_range_clean(BTRFS_I(inode), lockstart, lockend); } static int btrfs_insert_replace_extent(struct btrfs_trans_handle *trans, @@ -2957,8 +2910,9 @@ out: return ret; } -static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len) +static int btrfs_punch_hole(struct file *file, loff_t offset, loff_t len) { + struct inode *inode = file_inode(file); struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct btrfs_root *root = BTRFS_I(inode)->root; struct extent_state *cached_state = NULL; @@ -2975,11 +2929,12 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len) bool truncated_block = false; bool updated_inode = false; + btrfs_inode_lock(inode, BTRFS_ILOCK_MMAP); + ret = btrfs_wait_ordered_range(inode, offset, len); if (ret) - return ret; + goto out_only_mutex; - btrfs_inode_lock(inode, BTRFS_ILOCK_MMAP); ino_size = round_up(inode->i_size, fs_info->sectorsize); ret = find_first_non_hole(BTRFS_I(inode), &offset, &len); if (ret < 0) @@ -2990,6 +2945,10 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len) goto out_only_mutex; } + ret = file_modified(file); + if (ret) + goto out_only_mutex; + lockstart = round_up(offset, btrfs_inode_sectorsize(BTRFS_I(inode))); lockend = round_down(offset + len, btrfs_inode_sectorsize(BTRFS_I(inode))) - 1; @@ -3067,10 +3026,7 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len) goto out_only_mutex; } - ret = btrfs_punch_hole_lock_range(inode, lockstart, lockend, - &cached_state); - if (ret) - goto out_only_mutex; + btrfs_punch_hole_lock_range(inode, lockstart, lockend, &cached_state); path = btrfs_alloc_path(); if (!path) { @@ -3232,8 +3188,6 @@ static int btrfs_zero_range(struct inode *inode, u64 bytes_to_reserve = 0; bool space_reserved = false; - inode_dio_wait(inode); - em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, alloc_start, alloc_end - alloc_start); if (IS_ERR(em)) { @@ -3363,10 +3317,8 @@ reserve_space: if (ret < 0) goto out; space_reserved = true; - ret = btrfs_punch_hole_lock_range(inode, lockstart, lockend, - &cached_state); - if (ret) - goto out; + btrfs_punch_hole_lock_range(inode, lockstart, lockend, + &cached_state); ret = btrfs_qgroup_reserve_data(BTRFS_I(inode), &data_reserved, alloc_start, bytes_to_reserve); if (ret) { @@ -3412,6 +3364,9 @@ static long btrfs_fallocate(struct file *file, int mode, u64 alloc_hint = 0; u64 locked_end; u64 actual_end = 0; + u64 data_space_needed = 0; + u64 data_space_reserved = 0; + u64 qgroup_reserved = 0; struct extent_map *em; int blocksize = btrfs_inode_sectorsize(BTRFS_I(inode)); int ret; @@ -3430,19 +3385,7 @@ static long btrfs_fallocate(struct file *file, int mode, return -EOPNOTSUPP; if (mode & FALLOC_FL_PUNCH_HOLE) - return btrfs_punch_hole(inode, offset, len); - - /* - * Only trigger disk allocation, don't trigger qgroup reserve - * - * For qgroup space, it will be checked later. - */ - if (!(mode & FALLOC_FL_ZERO_RANGE)) { - ret = btrfs_alloc_data_chunk_ondemand(BTRFS_I(inode), - alloc_end - alloc_start); - if (ret < 0) - return ret; - } + return btrfs_punch_hole(file, offset, len); btrfs_inode_lock(inode, BTRFS_ILOCK_MMAP); @@ -3452,6 +3395,10 @@ static long btrfs_fallocate(struct file *file, int mode, goto out; } + ret = file_modified(file); + if (ret) + goto out; + /* * TODO: Move these two operations after we have checked * accurate reserved space, or fallocate can still fail but @@ -3476,8 +3423,12 @@ static long btrfs_fallocate(struct file *file, int mode, } /* - * wait for ordered IO before we have any locks. We'll loop again - * below with the locks held. + * We have locked the inode at the VFS level (in exclusive mode) and we + * have locked the i_mmap_lock lock (in exclusive mode). Now before + * locking the file range, flush all dealloc in the range and wait for + * all ordered extents in the range to complete. After this we can lock + * the file range and, due to the previous locking we did, we know there + * can't be more delalloc or ordered extents in the range. */ ret = btrfs_wait_ordered_range(inode, alloc_start, alloc_end - alloc_start); @@ -3491,38 +3442,10 @@ static long btrfs_fallocate(struct file *file, int mode, } locked_end = alloc_end - 1; - while (1) { - struct btrfs_ordered_extent *ordered; - - /* the extent lock is ordered inside the running - * transaction - */ - lock_extent_bits(&BTRFS_I(inode)->io_tree, alloc_start, - locked_end, &cached_state); - ordered = btrfs_lookup_first_ordered_extent(BTRFS_I(inode), - locked_end); + lock_extent_bits(&BTRFS_I(inode)->io_tree, alloc_start, locked_end, + &cached_state); - if (ordered && - ordered->file_offset + ordered->num_bytes > alloc_start && - ordered->file_offset < alloc_end) { - btrfs_put_ordered_extent(ordered); - unlock_extent_cached(&BTRFS_I(inode)->io_tree, - alloc_start, locked_end, - &cached_state); - /* - * we can't wait on the range with the transaction - * running or with the extent lock held - */ - ret = btrfs_wait_ordered_range(inode, alloc_start, - alloc_end - alloc_start); - if (ret) - goto out; - } else { - if (ordered) - btrfs_put_ordered_extent(ordered); - break; - } - } + btrfs_assert_inode_range_clean(BTRFS_I(inode), alloc_start, locked_end); /* First, check if we exceed the qgroup limit */ INIT_LIST_HEAD(&reserve_list); @@ -3539,48 +3462,64 @@ static long btrfs_fallocate(struct file *file, int mode, if (em->block_start == EXTENT_MAP_HOLE || (cur_offset >= inode->i_size && !test_bit(EXTENT_FLAG_PREALLOC, &em->flags))) { - ret = add_falloc_range(&reserve_list, cur_offset, - last_byte - cur_offset); + const u64 range_len = last_byte - cur_offset; + + ret = add_falloc_range(&reserve_list, cur_offset, range_len); if (ret < 0) { free_extent_map(em); break; } ret = btrfs_qgroup_reserve_data(BTRFS_I(inode), - &data_reserved, cur_offset, - last_byte - cur_offset); + &data_reserved, cur_offset, range_len); if (ret < 0) { - cur_offset = last_byte; free_extent_map(em); break; } - } else { - /* - * Do not need to reserve unwritten extent for this - * range, free reserved data space first, otherwise - * it'll result in false ENOSPC error. - */ - btrfs_free_reserved_data_space(BTRFS_I(inode), - data_reserved, cur_offset, - last_byte - cur_offset); + qgroup_reserved += range_len; + data_space_needed += range_len; } free_extent_map(em); cur_offset = last_byte; } + if (!ret && data_space_needed > 0) { + /* + * We are safe to reserve space here as we can't have delalloc + * in the range, see above. + */ + ret = btrfs_alloc_data_chunk_ondemand(BTRFS_I(inode), + data_space_needed); + if (!ret) + data_space_reserved = data_space_needed; + } + /* * If ret is still 0, means we're OK to fallocate. * Or just cleanup the list and exit. */ list_for_each_entry_safe(range, tmp, &reserve_list, list) { - if (!ret) + if (!ret) { ret = btrfs_prealloc_file_range(inode, mode, range->start, range->len, i_blocksize(inode), offset + len, &alloc_hint); - else + /* + * btrfs_prealloc_file_range() releases space even + * if it returns an error. + */ + data_space_reserved -= range->len; + qgroup_reserved -= range->len; + } else if (data_space_reserved > 0) { btrfs_free_reserved_data_space(BTRFS_I(inode), - data_reserved, range->start, - range->len); + data_reserved, range->start, + range->len); + data_space_reserved -= range->len; + qgroup_reserved -= range->len; + } else if (qgroup_reserved > 0) { + btrfs_qgroup_free_data(BTRFS_I(inode), data_reserved, + range->start, range->len); + qgroup_reserved -= range->len; + } list_del(&range->list); kfree(range); } @@ -3597,10 +3536,6 @@ out_unlock: &cached_state); out: btrfs_inode_unlock(inode, BTRFS_ILOCK_MMAP); - /* Let go of our reservation. */ - if (ret != 0 && !(mode & FALLOC_FL_ZERO_RANGE)) - btrfs_free_reserved_data_space(BTRFS_I(inode), data_reserved, - cur_offset, alloc_end - cur_offset); extent_changeset_free(data_reserved); return ret; } @@ -3758,8 +3693,7 @@ again: */ pagefault_disable(); to->nofault = true; - ret = iomap_dio_rw(iocb, to, &btrfs_dio_iomap_ops, &btrfs_dio_ops, - IOMAP_DIO_PARTIAL, read); + ret = btrfs_dio_rw(iocb, to, read); to->nofault = false; pagefault_enable(); diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index 01a408db5683..b1ae3ba2ca2c 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -465,7 +465,7 @@ static int io_ctl_prepare_pages(struct btrfs_io_ctl *io_ctl, bool uptodate) io_ctl->pages[i] = page; if (uptodate && !PageUptodate(page)) { - btrfs_readpage(NULL, page); + btrfs_read_folio(NULL, page_folio(page)); lock_page(page); if (page->mapping != inode->i_mapping) { btrfs_err(BTRFS_I(inode)->root->fs_info, @@ -2630,16 +2630,19 @@ out: static int __btrfs_add_free_space_zoned(struct btrfs_block_group *block_group, u64 bytenr, u64 size, bool used) { - struct btrfs_fs_info *fs_info = block_group->fs_info; + struct btrfs_space_info *sinfo = block_group->space_info; struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl; u64 offset = bytenr - block_group->start; u64 to_free, to_unusable; - const int bg_reclaim_threshold = READ_ONCE(fs_info->bg_reclaim_threshold); + int bg_reclaim_threshold = 0; bool initial = (size == block_group->length); u64 reclaimable_unusable; WARN_ON(!initial && offset + size > block_group->zone_capacity); + if (!initial) + bg_reclaim_threshold = READ_ONCE(sinfo->bg_reclaim_threshold); + spin_lock(&ctl->tree_lock); if (!used) to_free = size; @@ -4069,7 +4072,7 @@ static int cleanup_free_space_cache_v1(struct btrfs_fs_info *fs_info, btrfs_info(fs_info, "cleaning free space cache v1"); - node = rb_first(&fs_info->block_group_cache_tree); + node = rb_first_cached(&fs_info->block_group_cache_tree); while (node) { block_group = rb_entry(node, struct btrfs_block_group, cache_node); ret = btrfs_remove_free_space_inode(trans, NULL, block_group); diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c index 0ae54d8c10d6..1bf89aa67216 100644 --- a/fs/btrfs/free-space-tree.c +++ b/fs/btrfs/free-space-tree.c @@ -1178,7 +1178,7 @@ int btrfs_create_free_space_tree(struct btrfs_fs_info *fs_info) goto abort; } - node = rb_first(&fs_info->block_group_cache_tree); + node = rb_first_cached(&fs_info->block_group_cache_tree); while (node) { block_group = rb_entry(node, struct btrfs_block_group, cache_node); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 6bfc4343c98d..81737eff92f3 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -64,8 +64,36 @@ struct btrfs_iget_args { struct btrfs_dio_data { ssize_t submitted; struct extent_changeset *data_reserved; + bool data_space_reserved; + bool nocow_done; }; +struct btrfs_dio_private { + struct inode *inode; + + /* + * Since DIO can use anonymous page, we cannot use page_offset() to + * grab the file offset, thus need a dedicated member for file offset. + */ + u64 file_offset; + /* Used for bio::bi_size */ + u32 bytes; + + /* + * References to this structure. There is one reference per in-flight + * bio plus one while we're still setting up. + */ + refcount_t refs; + + /* Array of checksums */ + u8 *csums; + + /* This must be last */ + struct bio bio; +}; + +static struct bio_set btrfs_dio_bioset; + struct btrfs_rename_ctx { /* Output field. Stores the index number of the old directory entry. */ u64 index; @@ -222,15 +250,25 @@ static inline void btrfs_cleanup_ordered_extents(struct btrfs_inode *inode, static int btrfs_dirty_inode(struct inode *inode); static int btrfs_init_inode_security(struct btrfs_trans_handle *trans, - struct inode *inode, struct inode *dir, - const struct qstr *qstr) + struct btrfs_new_inode_args *args) { int err; - err = btrfs_init_acl(trans, inode, dir); - if (!err) - err = btrfs_xattr_security_init(trans, inode, dir, qstr); - return err; + if (args->default_acl) { + err = __btrfs_set_acl(trans, args->inode, args->default_acl, + ACL_TYPE_DEFAULT); + if (err) + return err; + } + if (args->acl) { + err = __btrfs_set_acl(trans, args->inode, args->acl, ACL_TYPE_ACCESS); + if (err) + return err; + } + if (!args->default_acl && !args->acl) + cache_no_acl(args->inode); + return btrfs_xattr_security_init(trans, args->inode, args->dir, + &args->dentry->d_name); } /* @@ -481,17 +519,6 @@ static noinline int add_async_extent(struct async_chunk *cow, } /* - * Check if the inode has flags compatible with compression - */ -static inline bool inode_can_compress(struct btrfs_inode *inode) -{ - if (inode->flags & BTRFS_INODE_NODATACOW || - inode->flags & BTRFS_INODE_NODATASUM) - return false; - return true; -} - -/* * Check if the inode needs to be submitted to compression, based on mount * options, defragmentation, properties or heuristics. */ @@ -500,7 +527,7 @@ static inline int inode_need_compress(struct btrfs_inode *inode, u64 start, { struct btrfs_fs_info *fs_info = inode->root->fs_info; - if (!inode_can_compress(inode)) { + if (!btrfs_inode_can_compress(inode)) { WARN(IS_ENABLED(CONFIG_BTRFS_DEBUG), KERN_ERR "BTRFS: unexpected compression for ino %llu\n", btrfs_ino(inode)); @@ -1128,7 +1155,6 @@ static noinline int cow_file_range(struct btrfs_inode *inode, int ret = 0; if (btrfs_is_free_space_inode(inode)) { - WARN_ON_ONCE(1); ret = -EINVAL; goto out_unlock; } @@ -1619,6 +1645,141 @@ static int fallback_to_cow(struct btrfs_inode *inode, struct page *locked_page, nr_written, 1); } +struct can_nocow_file_extent_args { + /* Input fields. */ + + /* Start file offset of the range we want to NOCOW. */ + u64 start; + /* End file offset (inclusive) of the range we want to NOCOW. */ + u64 end; + bool writeback_path; + bool strict; + /* + * Free the path passed to can_nocow_file_extent() once it's not needed + * anymore. + */ + bool free_path; + + /* Output fields. Only set when can_nocow_file_extent() returns 1. */ + + u64 disk_bytenr; + u64 disk_num_bytes; + u64 extent_offset; + /* Number of bytes that can be written to in NOCOW mode. */ + u64 num_bytes; +}; + +/* + * Check if we can NOCOW the file extent that the path points to. + * This function may return with the path released, so the caller should check + * if path->nodes[0] is NULL or not if it needs to use the path afterwards. + * + * Returns: < 0 on error + * 0 if we can not NOCOW + * 1 if we can NOCOW + */ +static int can_nocow_file_extent(struct btrfs_path *path, + struct btrfs_key *key, + struct btrfs_inode *inode, + struct can_nocow_file_extent_args *args) +{ + const bool is_freespace_inode = btrfs_is_free_space_inode(inode); + struct extent_buffer *leaf = path->nodes[0]; + struct btrfs_root *root = inode->root; + struct btrfs_file_extent_item *fi; + u64 extent_end; + u8 extent_type; + int can_nocow = 0; + int ret = 0; + + fi = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_file_extent_item); + extent_type = btrfs_file_extent_type(leaf, fi); + + if (extent_type == BTRFS_FILE_EXTENT_INLINE) + goto out; + + /* Can't access these fields unless we know it's not an inline extent. */ + args->disk_bytenr = btrfs_file_extent_disk_bytenr(leaf, fi); + args->disk_num_bytes = btrfs_file_extent_disk_num_bytes(leaf, fi); + args->extent_offset = btrfs_file_extent_offset(leaf, fi); + + if (!(inode->flags & BTRFS_INODE_NODATACOW) && + extent_type == BTRFS_FILE_EXTENT_REG) + goto out; + + /* + * If the extent was created before the generation where the last snapshot + * for its subvolume was created, then this implies the extent is shared, + * hence we must COW. + */ + if (!args->strict && + btrfs_file_extent_generation(leaf, fi) <= + btrfs_root_last_snapshot(&root->root_item)) + goto out; + + /* An explicit hole, must COW. */ + if (args->disk_bytenr == 0) + goto out; + + /* Compressed/encrypted/encoded extents must be COWed. */ + if (btrfs_file_extent_compression(leaf, fi) || + btrfs_file_extent_encryption(leaf, fi) || + btrfs_file_extent_other_encoding(leaf, fi)) + goto out; + + extent_end = btrfs_file_extent_end(path); + + /* + * The following checks can be expensive, as they need to take other + * locks and do btree or rbtree searches, so release the path to avoid + * blocking other tasks for too long. + */ + btrfs_release_path(path); + + ret = btrfs_cross_ref_exist(root, btrfs_ino(inode), + key->offset - args->extent_offset, + args->disk_bytenr, false, path); + WARN_ON_ONCE(ret > 0 && is_freespace_inode); + if (ret != 0) + goto out; + + if (args->free_path) { + /* + * We don't need the path anymore, plus through the + * csum_exist_in_range() call below we will end up allocating + * another path. So free the path to avoid unnecessary extra + * memory usage. + */ + btrfs_free_path(path); + path = NULL; + } + + /* If there are pending snapshots for this root, we must COW. */ + if (args->writeback_path && !is_freespace_inode && + atomic_read(&root->snapshot_force_cow)) + goto out; + + args->disk_bytenr += args->extent_offset; + args->disk_bytenr += args->start - key->offset; + args->num_bytes = min(args->end + 1, extent_end) - args->start; + + /* + * Force COW if csums exist in the range. This ensures that csums for a + * given extent are either valid or do not exist. + */ + ret = csum_exist_in_range(root->fs_info, args->disk_bytenr, args->num_bytes); + WARN_ON_ONCE(ret > 0 && is_freespace_inode); + if (ret != 0) + goto out; + + can_nocow = 1; + out: + if (args->free_path && path) + btrfs_free_path(path); + + return ret < 0 ? ret : can_nocow; +} + /* * when nowcow writeback call back. This checks for snapshots or COW copies * of the extents that exist in the file, and COWs the file as required. @@ -1639,11 +1800,10 @@ static noinline int run_delalloc_nocow(struct btrfs_inode *inode, u64 cur_offset = start; int ret; bool check_prev = true; - const bool freespace_inode = btrfs_is_free_space_inode(inode); u64 ino = btrfs_ino(inode); + struct btrfs_block_group *bg; bool nocow = false; - u64 disk_bytenr = 0; - const bool force = inode->flags & BTRFS_INODE_NODATACOW; + struct can_nocow_file_extent_args nocow_args = { 0 }; path = btrfs_alloc_path(); if (!path) { @@ -1656,15 +1816,16 @@ static noinline int run_delalloc_nocow(struct btrfs_inode *inode, return -ENOMEM; } + nocow_args.end = end; + nocow_args.writeback_path = true; + while (1) { struct btrfs_key found_key; struct btrfs_file_extent_item *fi; struct extent_buffer *leaf; u64 extent_end; - u64 extent_offset; - u64 num_bytes = 0; - u64 disk_num_bytes; u64 ram_bytes; + u64 nocow_end; int extent_type; nocow = false; @@ -1740,116 +1901,38 @@ next_slot: fi = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_file_extent_item); extent_type = btrfs_file_extent_type(leaf, fi); - + /* If this is triggered then we have a memory corruption. */ + ASSERT(extent_type < BTRFS_NR_FILE_EXTENT_TYPES); + if (WARN_ON(extent_type >= BTRFS_NR_FILE_EXTENT_TYPES)) { + ret = -EUCLEAN; + goto error; + } ram_bytes = btrfs_file_extent_ram_bytes(leaf, fi); - if (extent_type == BTRFS_FILE_EXTENT_REG || - extent_type == BTRFS_FILE_EXTENT_PREALLOC) { - disk_bytenr = btrfs_file_extent_disk_bytenr(leaf, fi); - extent_offset = btrfs_file_extent_offset(leaf, fi); - extent_end = found_key.offset + - btrfs_file_extent_num_bytes(leaf, fi); - disk_num_bytes = - btrfs_file_extent_disk_num_bytes(leaf, fi); - /* - * If the extent we got ends before our current offset, - * skip to the next extent. - */ - if (extent_end <= cur_offset) { - path->slots[0]++; - goto next_slot; - } - /* Skip holes */ - if (disk_bytenr == 0) - goto out_check; - /* Skip compressed/encrypted/encoded extents */ - if (btrfs_file_extent_compression(leaf, fi) || - btrfs_file_extent_encryption(leaf, fi) || - btrfs_file_extent_other_encoding(leaf, fi)) - goto out_check; - /* - * If extent is created before the last volume's snapshot - * this implies the extent is shared, hence we can't do - * nocow. This is the same check as in - * btrfs_cross_ref_exist but without calling - * btrfs_search_slot. - */ - if (!freespace_inode && - btrfs_file_extent_generation(leaf, fi) <= - btrfs_root_last_snapshot(&root->root_item)) - goto out_check; - if (extent_type == BTRFS_FILE_EXTENT_REG && !force) - goto out_check; + extent_end = btrfs_file_extent_end(path); - /* - * The following checks can be expensive, as they need to - * take other locks and do btree or rbtree searches, so - * release the path to avoid blocking other tasks for too - * long. - */ - btrfs_release_path(path); + /* + * If the extent we got ends before our current offset, skip to + * the next extent. + */ + if (extent_end <= cur_offset) { + path->slots[0]++; + goto next_slot; + } - ret = btrfs_cross_ref_exist(root, ino, - found_key.offset - - extent_offset, disk_bytenr, false); - if (ret) { - /* - * ret could be -EIO if the above fails to read - * metadata. - */ - if (ret < 0) { - if (cow_start != (u64)-1) - cur_offset = cow_start; - goto error; - } + nocow_args.start = cur_offset; + ret = can_nocow_file_extent(path, &found_key, inode, &nocow_args); + if (ret < 0) { + if (cow_start != (u64)-1) + cur_offset = cow_start; + goto error; + } else if (ret == 0) { + goto out_check; + } - WARN_ON_ONCE(freespace_inode); - goto out_check; - } - disk_bytenr += extent_offset; - disk_bytenr += cur_offset - found_key.offset; - num_bytes = min(end + 1, extent_end) - cur_offset; - /* - * If there are pending snapshots for this root, we - * fall into common COW way - */ - if (!freespace_inode && atomic_read(&root->snapshot_force_cow)) - goto out_check; - /* - * force cow if csum exists in the range. - * this ensure that csum for a given extent are - * either valid or do not exist. - */ - ret = csum_exist_in_range(fs_info, disk_bytenr, - num_bytes); - if (ret) { - /* - * ret could be -EIO if the above fails to read - * metadata. - */ - if (ret < 0) { - if (cow_start != (u64)-1) - cur_offset = cow_start; - goto error; - } - WARN_ON_ONCE(freespace_inode); - goto out_check; - } - /* If the extent's block group is RO, we must COW */ - if (!btrfs_inc_nocow_writers(fs_info, disk_bytenr)) - goto out_check; + ret = 0; + bg = btrfs_inc_nocow_writers(fs_info, nocow_args.disk_bytenr); + if (bg) nocow = true; - } else if (extent_type == BTRFS_FILE_EXTENT_INLINE) { - extent_end = found_key.offset + ram_bytes; - extent_end = ALIGN(extent_end, fs_info->sectorsize); - /* Skip extents outside of our requested range */ - if (extent_end <= start) { - path->slots[0]++; - goto next_slot; - } - } else { - /* If this triggers then we have a memory corruption */ - BUG(); - } out_check: /* * If nocow is false then record the beginning of the range @@ -1881,15 +1964,17 @@ out_check: cow_start = (u64)-1; } + nocow_end = cur_offset + nocow_args.num_bytes - 1; + if (extent_type == BTRFS_FILE_EXTENT_PREALLOC) { - u64 orig_start = found_key.offset - extent_offset; + u64 orig_start = found_key.offset - nocow_args.extent_offset; struct extent_map *em; - em = create_io_em(inode, cur_offset, num_bytes, + em = create_io_em(inode, cur_offset, nocow_args.num_bytes, orig_start, - disk_bytenr, /* block_start */ - num_bytes, /* block_len */ - disk_num_bytes, /* orig_block_len */ + nocow_args.disk_bytenr, /* block_start */ + nocow_args.num_bytes, /* block_len */ + nocow_args.disk_num_bytes, /* orig_block_len */ ram_bytes, BTRFS_COMPRESS_NONE, BTRFS_ORDERED_PREALLOC); if (IS_ERR(em)) { @@ -1898,20 +1983,23 @@ out_check: } free_extent_map(em); ret = btrfs_add_ordered_extent(inode, - cur_offset, num_bytes, num_bytes, - disk_bytenr, num_bytes, 0, + cur_offset, nocow_args.num_bytes, + nocow_args.num_bytes, + nocow_args.disk_bytenr, + nocow_args.num_bytes, 0, 1 << BTRFS_ORDERED_PREALLOC, BTRFS_COMPRESS_NONE); if (ret) { btrfs_drop_extent_cache(inode, cur_offset, - cur_offset + num_bytes - 1, - 0); + nocow_end, 0); goto error; } } else { ret = btrfs_add_ordered_extent(inode, cur_offset, - num_bytes, num_bytes, - disk_bytenr, num_bytes, + nocow_args.num_bytes, + nocow_args.num_bytes, + nocow_args.disk_bytenr, + nocow_args.num_bytes, 0, 1 << BTRFS_ORDERED_NOCOW, BTRFS_COMPRESS_NONE); @@ -1919,9 +2007,10 @@ out_check: goto error; } - if (nocow) - btrfs_dec_nocow_writers(fs_info, disk_bytenr); - nocow = false; + if (nocow) { + btrfs_dec_nocow_writers(bg); + nocow = false; + } if (btrfs_is_data_reloc_root(root)) /* @@ -1930,10 +2019,9 @@ out_check: * from freeing metadata of created ordered extent. */ ret = btrfs_reloc_clone_csums(inode, cur_offset, - num_bytes); + nocow_args.num_bytes); - extent_clear_unlock_delalloc(inode, cur_offset, - cur_offset + num_bytes - 1, + extent_clear_unlock_delalloc(inode, cur_offset, nocow_end, locked_page, EXTENT_LOCKED | EXTENT_DELALLOC | EXTENT_CLEAR_DATA_RESV, @@ -1966,7 +2054,7 @@ out_check: error: if (nocow) - btrfs_dec_nocow_writers(fs_info, disk_bytenr); + btrfs_dec_nocow_writers(bg); if (ret && cur_offset < end) extent_clear_unlock_delalloc(inode, cur_offset, end, @@ -2017,11 +2105,10 @@ int btrfs_run_delalloc_range(struct btrfs_inode *inode, struct page *locked_page * to use run_delalloc_nocow() here, like for regular * preallocated inodes. */ - ASSERT(!zoned || - (zoned && btrfs_is_data_reloc_root(inode->root))); + ASSERT(!zoned || btrfs_is_data_reloc_root(inode->root)); ret = run_delalloc_nocow(inode, locked_page, start, end, page_started, nr_written); - } else if (!inode_can_compress(inode) || + } else if (!btrfs_inode_can_compress(inode) || !inode_need_compress(inode, start, end)) { if (zoned) ret = run_delalloc_zoned(inode, locked_page, start, end, @@ -2511,9 +2598,8 @@ out: * * c-3) otherwise: async submit */ -blk_status_t btrfs_submit_data_bio(struct inode *inode, struct bio *bio, - int mirror_num, unsigned long bio_flags) - +void btrfs_submit_data_bio(struct inode *inode, struct bio *bio, + int mirror_num, enum btrfs_compression_type compress_type) { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct btrfs_root *root = BTRFS_I(inode)->root; @@ -2542,16 +2628,14 @@ blk_status_t btrfs_submit_data_bio(struct inode *inode, struct bio *bio, if (ret) goto out; - if (bio_flags & EXTENT_BIO_COMPRESSED) { + if (compress_type != BTRFS_COMPRESS_NONE) { /* * btrfs_submit_compressed_read will handle completing * the bio if there were any errors, so just return * here. */ - ret = btrfs_submit_compressed_read(inode, bio, - mirror_num, - bio_flags); - goto out_no_endio; + btrfs_submit_compressed_read(inode, bio, mirror_num); + return; } else { /* * Lookup bio sums does extra checks around whether we @@ -2568,7 +2652,7 @@ blk_status_t btrfs_submit_data_bio(struct inode *inode, struct bio *bio, if (btrfs_is_data_reloc_root(root)) goto mapit; /* we're doing a write, do the async checksumming */ - ret = btrfs_wq_submit_bio(inode, bio, mirror_num, bio_flags, + ret = btrfs_wq_submit_bio(inode, bio, mirror_num, 0, btrfs_submit_bio_start); goto out; } else if (!skip_sum) { @@ -2585,8 +2669,6 @@ out: bio->bi_status = ret; bio_endio(bio); } -out_no_endio: - return ret; } /* @@ -3277,11 +3359,11 @@ static int check_data_csum(struct inode *inode, struct btrfs_bio *bbio, shash->tfm = fs_info->csum_shash; crypto_shash_digest(shash, kaddr + pgoff, len, csum); + kunmap_atomic(kaddr); if (memcmp(csum, csum_expected, csum_size)) goto zeroit; - kunmap_atomic(kaddr); return 0; zeroit: btrfs_print_data_csum_error(BTRFS_I(inode), start, csum, csum_expected, @@ -3289,9 +3371,7 @@ zeroit: if (bbio->device) btrfs_dev_stat_inc_and_print(bbio->device, BTRFS_DEV_STAT_CORRUPTION_ERRS); - memset(kaddr + pgoff, 1, len); - flush_dcache_page(page); - kunmap_atomic(kaddr); + memzero_page(page, pgoff, len); return -EIO; } @@ -3496,6 +3576,7 @@ int btrfs_orphan_cleanup(struct btrfs_root *root) u64 last_objectid = 0; int ret = 0, nr_unlink = 0; + /* Bail out if the cleanup is already running. */ if (test_and_set_bit(BTRFS_ROOT_ORPHAN_CLEANUP, &root->state)) return 0; @@ -3578,17 +3659,17 @@ int btrfs_orphan_cleanup(struct btrfs_root *root) * * btrfs_find_orphan_roots() ran before us, which has * found all deleted roots and loaded them into - * fs_info->fs_roots_radix. So here we can find if an + * fs_info->fs_roots. So here we can find if an * orphan item corresponds to a deleted root by looking - * up the root from that radix tree. + * up the root from that xarray. */ - spin_lock(&fs_info->fs_roots_radix_lock); - dead_root = radix_tree_lookup(&fs_info->fs_roots_radix, - (unsigned long)found_key.objectid); + spin_lock(&fs_info->fs_roots_lock); + dead_root = xa_load(&fs_info->fs_roots, + (unsigned long)found_key.objectid); if (dead_root && btrfs_root_refs(&dead_root->root_item) == 0) is_dead_root = 1; - spin_unlock(&fs_info->fs_roots_radix_lock); + spin_unlock(&fs_info->fs_roots_lock); if (is_dead_root) { /* prevent this orphan from being found again */ @@ -3828,7 +3909,7 @@ cache_index: * cache. * * This is required for both inode re-read from disk and delayed inode - * in delayed_nodes_tree. + * in the delayed_nodes xarray. */ if (BTRFS_I(inode)->last_trans == fs_info->generation) set_bit(BTRFS_INODE_NEEDS_FULL_SYNC, @@ -4212,8 +4293,9 @@ static struct btrfs_trans_handle *__unlink_start_trans(struct inode *dir) * 1 for the dir index * 1 for the inode ref * 1 for the inode + * 1 for the parent inode */ - return btrfs_start_transaction_fallback_global_rsv(root, 5); + return btrfs_start_transaction_fallback_global_rsv(root, 6); } static int btrfs_unlink(struct inode *dir, struct dentry *dentry) @@ -4488,6 +4570,13 @@ int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry) dest->root_key.objectid); return -EPERM; } + if (atomic_read(&dest->nr_swapfiles)) { + spin_unlock(&dest->root_item_lock); + btrfs_warn(fs_info, + "attempt to delete subvolume %llu with active swapfile", + root->root_key.objectid); + return -EPERM; + } root_flags = btrfs_root_flags(&dest->root_item); btrfs_set_root_flags(&dest->root_item, root_flags | BTRFS_ROOT_SUBVOL_DEAD); @@ -4699,7 +4788,7 @@ int btrfs_truncate_block(struct btrfs_inode *inode, loff_t from, loff_t len, goto out; } } - ret = btrfs_delalloc_reserve_metadata(inode, blocksize, blocksize); + ret = btrfs_delalloc_reserve_metadata(inode, blocksize, blocksize, false); if (ret < 0) { if (!only_release_metadata) btrfs_free_reserved_data_space(inode, data_reserved, @@ -4720,7 +4809,7 @@ again: goto out_unlock; if (!PageUptodate(page)) { - ret = btrfs_readpage(NULL, page); + ret = btrfs_read_folio(NULL, page_folio(page)); lock_page(page); if (page->mapping != mapping) { unlock_page(page); @@ -5786,8 +5875,6 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx) struct list_head ins_list; struct list_head del_list; int ret; - struct extent_buffer *leaf; - int slot; char *name_ptr; int name_len; int entries = 0; @@ -5814,35 +5901,19 @@ again: key.offset = ctx->pos; key.objectid = btrfs_ino(BTRFS_I(inode)); - ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); - if (ret < 0) - goto err; - - while (1) { + btrfs_for_each_slot(root, &key, &found_key, path, ret) { struct dir_entry *entry; - - leaf = path->nodes[0]; - slot = path->slots[0]; - if (slot >= btrfs_header_nritems(leaf)) { - ret = btrfs_next_leaf(root, path); - if (ret < 0) - goto err; - else if (ret > 0) - break; - continue; - } - - btrfs_item_key_to_cpu(leaf, &found_key, slot); + struct extent_buffer *leaf = path->nodes[0]; if (found_key.objectid != key.objectid) break; if (found_key.type != BTRFS_DIR_INDEX_KEY) break; if (found_key.offset < ctx->pos) - goto next; + continue; if (btrfs_should_delete_dir_index(&del_list, found_key.offset)) - goto next; - di = btrfs_item_ptr(leaf, slot, struct btrfs_dir_item); + continue; + di = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_dir_item); name_len = btrfs_dir_name_len(leaf, di); if ((total_len + sizeof(struct dir_entry) + name_len) >= PAGE_SIZE) { @@ -5869,9 +5940,11 @@ again: entries++; addr += sizeof(struct dir_entry) + name_len; total_len += sizeof(struct dir_entry) + name_len; -next: - path->slots[0]++; } + /* Catch error encountered during iteration */ + if (ret < 0) + goto err; + btrfs_release_path(path); ret = btrfs_filldir(private->filldir_buf, entries, ctx); @@ -6059,6 +6132,57 @@ static int btrfs_insert_inode_locked(struct inode *inode) btrfs_find_actor, &args); } +int btrfs_new_inode_prepare(struct btrfs_new_inode_args *args, + unsigned int *trans_num_items) +{ + struct inode *dir = args->dir; + struct inode *inode = args->inode; + int ret; + + ret = posix_acl_create(dir, &inode->i_mode, &args->default_acl, &args->acl); + if (ret) + return ret; + + /* 1 to add inode item */ + *trans_num_items = 1; + /* 1 to add compression property */ + if (BTRFS_I(dir)->prop_compress) + (*trans_num_items)++; + /* 1 to add default ACL xattr */ + if (args->default_acl) + (*trans_num_items)++; + /* 1 to add access ACL xattr */ + if (args->acl) + (*trans_num_items)++; +#ifdef CONFIG_SECURITY + /* 1 to add LSM xattr */ + if (dir->i_security) + (*trans_num_items)++; +#endif + if (args->orphan) { + /* 1 to add orphan item */ + (*trans_num_items)++; + } else { + /* + * 1 to add dir item + * 1 to add dir index + * 1 to update parent inode item + * + * No need for 1 unit for the inode ref item because it is + * inserted in a batch together with the inode item at + * btrfs_create_new_inode(). + */ + *trans_num_items += 3; + } + return 0; +} + +void btrfs_new_inode_args_destroy(struct btrfs_new_inode_args *args) +{ + posix_acl_release(args->acl); + posix_acl_release(args->default_acl); +} + /* * Inherit flags from the parent inode. * @@ -6068,9 +6192,6 @@ static void btrfs_inherit_iflags(struct inode *inode, struct inode *dir) { unsigned int flags; - if (!dir) - return; - flags = BTRFS_I(dir)->flags; if (flags & BTRFS_INODE_NOCOMPRESS) { @@ -6090,76 +6211,86 @@ static void btrfs_inherit_iflags(struct inode *inode, struct inode *dir) btrfs_sync_inode_flags_to_i_flags(inode); } -static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans, - struct btrfs_root *root, - struct user_namespace *mnt_userns, - struct inode *dir, - const char *name, int name_len, - u64 ref_objectid, u64 objectid, - umode_t mode, u64 *index) +int btrfs_create_new_inode(struct btrfs_trans_handle *trans, + struct btrfs_new_inode_args *args) { - struct btrfs_fs_info *fs_info = root->fs_info; - struct inode *inode; + struct inode *dir = args->dir; + struct inode *inode = args->inode; + const char *name = args->orphan ? NULL : args->dentry->d_name.name; + int name_len = args->orphan ? 0 : args->dentry->d_name.len; + struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb); + struct btrfs_root *root; struct btrfs_inode_item *inode_item; struct btrfs_key *location; struct btrfs_path *path; + u64 objectid; struct btrfs_inode_ref *ref; struct btrfs_key key[2]; u32 sizes[2]; struct btrfs_item_batch batch; unsigned long ptr; - unsigned int nofs_flag; int ret; path = btrfs_alloc_path(); if (!path) - return ERR_PTR(-ENOMEM); - - nofs_flag = memalloc_nofs_save(); - inode = new_inode(fs_info->sb); - memalloc_nofs_restore(nofs_flag); - if (!inode) { - btrfs_free_path(path); - return ERR_PTR(-ENOMEM); - } + return -ENOMEM; - /* - * O_TMPFILE, set link count to 0, so that after this point, - * we fill in an inode item with the correct link count. - */ - if (!name) - set_nlink(inode, 0); + if (!args->subvol) + BTRFS_I(inode)->root = btrfs_grab_root(BTRFS_I(dir)->root); + root = BTRFS_I(inode)->root; - /* - * we have to initialize this early, so we can reclaim the inode - * number if we fail afterwards in this function. - */ + ret = btrfs_get_free_objectid(root, &objectid); + if (ret) + goto out; inode->i_ino = objectid; - if (dir && name) { + if (args->orphan) { + /* + * O_TMPFILE, set link count to 0, so that after this point, we + * fill in an inode item with the correct link count. + */ + set_nlink(inode, 0); + } else { trace_btrfs_inode_request(dir); - ret = btrfs_set_inode_index(BTRFS_I(dir), index); - if (ret) { - btrfs_free_path(path); - iput(inode); - return ERR_PTR(ret); - } - } else if (dir) { - *index = 0; + ret = btrfs_set_inode_index(BTRFS_I(dir), &BTRFS_I(inode)->dir_index); + if (ret) + goto out; } - /* - * index_cnt is ignored for everything but a dir, - * btrfs_set_inode_index_count has an explanation for the magic - * number - */ - BTRFS_I(inode)->index_cnt = 2; - BTRFS_I(inode)->dir_index = *index; - BTRFS_I(inode)->root = btrfs_grab_root(root); + /* index_cnt is ignored for everything but a dir. */ + BTRFS_I(inode)->index_cnt = BTRFS_DIR_START_INDEX; BTRFS_I(inode)->generation = trans->transid; inode->i_generation = BTRFS_I(inode)->generation; /* + * Subvolumes don't inherit flags from their parent directory. + * Originally this was probably by accident, but we probably can't + * change it now without compatibility issues. + */ + if (!args->subvol) + btrfs_inherit_iflags(inode, dir); + + if (S_ISREG(inode->i_mode)) { + if (btrfs_test_opt(fs_info, NODATASUM)) + BTRFS_I(inode)->flags |= BTRFS_INODE_NODATASUM; + if (btrfs_test_opt(fs_info, NODATACOW)) + BTRFS_I(inode)->flags |= BTRFS_INODE_NODATACOW | + BTRFS_INODE_NODATASUM; + } + + location = &BTRFS_I(inode)->location; + location->objectid = objectid; + location->offset = 0; + location->type = BTRFS_INODE_ITEM_KEY; + + ret = btrfs_insert_inode_locked(inode); + if (ret < 0) { + if (!args->orphan) + BTRFS_I(dir)->index_cnt--; + goto out; + } + + /* * We could have gotten an inode number from somebody who was fsynced * and then removed in this same transaction, so let's just set full * sync since it will be a full sync anyway and this will blow away the @@ -6173,7 +6304,7 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans, sizes[0] = sizeof(struct btrfs_inode_item); - if (name) { + if (!args->orphan) { /* * Start new inodes with an inode_ref. This is slightly more * efficient for small numbers of hard links since they will @@ -6182,64 +6313,95 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans, */ key[1].objectid = objectid; key[1].type = BTRFS_INODE_REF_KEY; - key[1].offset = ref_objectid; - - sizes[1] = name_len + sizeof(*ref); - } - - location = &BTRFS_I(inode)->location; - location->objectid = objectid; - location->offset = 0; - location->type = BTRFS_INODE_ITEM_KEY; - - ret = btrfs_insert_inode_locked(inode); - if (ret < 0) { - iput(inode); - goto fail; + if (args->subvol) { + key[1].offset = objectid; + sizes[1] = 2 + sizeof(*ref); + } else { + key[1].offset = btrfs_ino(BTRFS_I(dir)); + sizes[1] = name_len + sizeof(*ref); + } } batch.keys = &key[0]; batch.data_sizes = &sizes[0]; - batch.total_data_size = sizes[0] + (name ? sizes[1] : 0); - batch.nr = name ? 2 : 1; + batch.total_data_size = sizes[0] + (args->orphan ? 0 : sizes[1]); + batch.nr = args->orphan ? 1 : 2; ret = btrfs_insert_empty_items(trans, root, path, &batch); - if (ret != 0) - goto fail_unlock; - - inode_init_owner(mnt_userns, inode, dir, mode); - inode_set_bytes(inode, 0); + if (ret != 0) { + btrfs_abort_transaction(trans, ret); + goto discard; + } inode->i_mtime = current_time(inode); inode->i_atime = inode->i_mtime; inode->i_ctime = inode->i_mtime; BTRFS_I(inode)->i_otime = inode->i_mtime; + /* + * We're going to fill the inode item now, so at this point the inode + * must be fully initialized. + */ + inode_item = btrfs_item_ptr(path->nodes[0], path->slots[0], struct btrfs_inode_item); memzero_extent_buffer(path->nodes[0], (unsigned long)inode_item, sizeof(*inode_item)); fill_inode_item(trans, path->nodes[0], inode_item, inode); - if (name) { + if (!args->orphan) { ref = btrfs_item_ptr(path->nodes[0], path->slots[0] + 1, struct btrfs_inode_ref); - btrfs_set_inode_ref_name_len(path->nodes[0], ref, name_len); - btrfs_set_inode_ref_index(path->nodes[0], ref, *index); ptr = (unsigned long)(ref + 1); - write_extent_buffer(path->nodes[0], name, ptr, name_len); + if (args->subvol) { + btrfs_set_inode_ref_name_len(path->nodes[0], ref, 2); + btrfs_set_inode_ref_index(path->nodes[0], ref, 0); + write_extent_buffer(path->nodes[0], "..", ptr, 2); + } else { + btrfs_set_inode_ref_name_len(path->nodes[0], ref, name_len); + btrfs_set_inode_ref_index(path->nodes[0], ref, + BTRFS_I(inode)->dir_index); + write_extent_buffer(path->nodes[0], name, ptr, name_len); + } } btrfs_mark_buffer_dirty(path->nodes[0]); - btrfs_free_path(path); + btrfs_release_path(path); - btrfs_inherit_iflags(inode, dir); + if (args->subvol) { + struct inode *parent; - if (S_ISREG(mode)) { - if (btrfs_test_opt(fs_info, NODATASUM)) - BTRFS_I(inode)->flags |= BTRFS_INODE_NODATASUM; - if (btrfs_test_opt(fs_info, NODATACOW)) - BTRFS_I(inode)->flags |= BTRFS_INODE_NODATACOW | - BTRFS_INODE_NODATASUM; + /* + * Subvolumes inherit properties from their parent subvolume, + * not the directory they were created in. + */ + parent = btrfs_iget(fs_info->sb, BTRFS_FIRST_FREE_OBJECTID, + BTRFS_I(dir)->root); + if (IS_ERR(parent)) { + ret = PTR_ERR(parent); + } else { + ret = btrfs_inode_inherit_props(trans, inode, parent); + iput(parent); + } + } else { + ret = btrfs_inode_inherit_props(trans, inode, dir); + } + if (ret) { + btrfs_err(fs_info, + "error inheriting props for ino %llu (root %llu): %d", + btrfs_ino(BTRFS_I(inode)), root->root_key.objectid, + ret); + } + + /* + * Subvolumes don't inherit ACLs or get passed to the LSM. This is + * probably a bug. + */ + if (!args->subvol) { + ret = btrfs_init_inode_security(trans, args); + if (ret) { + btrfs_abort_transaction(trans, ret); + goto discard; + } } inode_tree_add(inode); @@ -6249,21 +6411,30 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans, btrfs_update_root_times(trans, root); - ret = btrfs_inode_inherit_props(trans, inode, dir); - if (ret) - btrfs_err(fs_info, - "error inheriting props for ino %llu (root %llu): %d", - btrfs_ino(BTRFS_I(inode)), root->root_key.objectid, ret); + if (args->orphan) { + ret = btrfs_orphan_add(trans, BTRFS_I(inode)); + } else { + ret = btrfs_add_link(trans, BTRFS_I(dir), BTRFS_I(inode), name, + name_len, 0, BTRFS_I(inode)->dir_index); + } + if (ret) { + btrfs_abort_transaction(trans, ret); + goto discard; + } - return inode; + ret = 0; + goto out; -fail_unlock: +discard: + /* + * discard_new_inode() calls iput(), but the caller owns the reference + * to the inode. + */ + ihold(inode); discard_new_inode(inode); -fail: - if (dir && name) - BTRFS_I(dir)->index_cnt--; +out: btrfs_free_path(path); - return ERR_PTR(ret); + return ret; } /* @@ -6355,147 +6526,71 @@ fail_dir_item: return ret; } -static int btrfs_add_nondir(struct btrfs_trans_handle *trans, - struct btrfs_inode *dir, struct dentry *dentry, - struct btrfs_inode *inode, int backref, u64 index) -{ - int err = btrfs_add_link(trans, dir, inode, - dentry->d_name.name, dentry->d_name.len, - backref, index); - if (err > 0) - err = -EEXIST; - return err; -} - -static int btrfs_mknod(struct user_namespace *mnt_userns, struct inode *dir, - struct dentry *dentry, umode_t mode, dev_t rdev) +static int btrfs_create_common(struct inode *dir, struct dentry *dentry, + struct inode *inode) { struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb); - struct btrfs_trans_handle *trans; struct btrfs_root *root = BTRFS_I(dir)->root; - struct inode *inode = NULL; + struct btrfs_new_inode_args new_inode_args = { + .dir = dir, + .dentry = dentry, + .inode = inode, + }; + unsigned int trans_num_items; + struct btrfs_trans_handle *trans; int err; - u64 objectid; - u64 index = 0; - /* - * 2 for inode item and ref - * 2 for dir items - * 1 for xattr if selinux is on - */ - trans = btrfs_start_transaction(root, 5); - if (IS_ERR(trans)) - return PTR_ERR(trans); - - err = btrfs_get_free_objectid(root, &objectid); + err = btrfs_new_inode_prepare(&new_inode_args, &trans_num_items); if (err) - goto out_unlock; + goto out_inode; - inode = btrfs_new_inode(trans, root, mnt_userns, dir, - dentry->d_name.name, dentry->d_name.len, - btrfs_ino(BTRFS_I(dir)), objectid, mode, &index); - if (IS_ERR(inode)) { - err = PTR_ERR(inode); - inode = NULL; - goto out_unlock; + trans = btrfs_start_transaction(root, trans_num_items); + if (IS_ERR(trans)) { + err = PTR_ERR(trans); + goto out_new_inode_args; } - /* - * If the active LSM wants to access the inode during - * d_instantiate it needs these. Smack checks to see - * if the filesystem supports xattrs by looking at the - * ops vector. - */ - inode->i_op = &btrfs_special_inode_operations; - init_special_inode(inode, inode->i_mode, rdev); - - err = btrfs_init_inode_security(trans, inode, dir, &dentry->d_name); - if (err) - goto out_unlock; - - err = btrfs_add_nondir(trans, BTRFS_I(dir), dentry, BTRFS_I(inode), - 0, index); - if (err) - goto out_unlock; - - btrfs_update_inode(trans, root, BTRFS_I(inode)); - d_instantiate_new(dentry, inode); + err = btrfs_create_new_inode(trans, &new_inode_args); + if (!err) + d_instantiate_new(dentry, inode); -out_unlock: btrfs_end_transaction(trans); btrfs_btree_balance_dirty(fs_info); - if (err && inode) { - inode_dec_link_count(inode); - discard_new_inode(inode); - } +out_new_inode_args: + btrfs_new_inode_args_destroy(&new_inode_args); +out_inode: + if (err) + iput(inode); return err; } -static int btrfs_create(struct user_namespace *mnt_userns, struct inode *dir, - struct dentry *dentry, umode_t mode, bool excl) +static int btrfs_mknod(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode, dev_t rdev) { - struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb); - struct btrfs_trans_handle *trans; - struct btrfs_root *root = BTRFS_I(dir)->root; - struct inode *inode = NULL; - int err; - u64 objectid; - u64 index = 0; + struct inode *inode; - /* - * 2 for inode item and ref - * 2 for dir items - * 1 for xattr if selinux is on - */ - trans = btrfs_start_transaction(root, 5); - if (IS_ERR(trans)) - return PTR_ERR(trans); + inode = new_inode(dir->i_sb); + if (!inode) + return -ENOMEM; + inode_init_owner(mnt_userns, inode, dir, mode); + inode->i_op = &btrfs_special_inode_operations; + init_special_inode(inode, inode->i_mode, rdev); + return btrfs_create_common(dir, dentry, inode); +} - err = btrfs_get_free_objectid(root, &objectid); - if (err) - goto out_unlock; +static int btrfs_create(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode, bool excl) +{ + struct inode *inode; - inode = btrfs_new_inode(trans, root, mnt_userns, dir, - dentry->d_name.name, dentry->d_name.len, - btrfs_ino(BTRFS_I(dir)), objectid, mode, &index); - if (IS_ERR(inode)) { - err = PTR_ERR(inode); - inode = NULL; - goto out_unlock; - } - /* - * If the active LSM wants to access the inode during - * d_instantiate it needs these. Smack checks to see - * if the filesystem supports xattrs by looking at the - * ops vector. - */ + inode = new_inode(dir->i_sb); + if (!inode) + return -ENOMEM; + inode_init_owner(mnt_userns, inode, dir, mode); inode->i_fop = &btrfs_file_operations; inode->i_op = &btrfs_file_inode_operations; inode->i_mapping->a_ops = &btrfs_aops; - - err = btrfs_init_inode_security(trans, inode, dir, &dentry->d_name); - if (err) - goto out_unlock; - - err = btrfs_update_inode(trans, root, BTRFS_I(inode)); - if (err) - goto out_unlock; - - err = btrfs_add_nondir(trans, BTRFS_I(dir), dentry, BTRFS_I(inode), - 0, index); - if (err) - goto out_unlock; - - d_instantiate_new(dentry, inode); - -out_unlock: - btrfs_end_transaction(trans); - if (err && inode) { - inode_dec_link_count(inode); - discard_new_inode(inode); - } - btrfs_btree_balance_dirty(fs_info); - return err; + return btrfs_create_common(dir, dentry, inode); } static int btrfs_link(struct dentry *old_dentry, struct inode *dir, @@ -6541,8 +6636,8 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir, ihold(inode); set_bit(BTRFS_INODE_COPY_EVERYTHING, &BTRFS_I(inode)->runtime_flags); - err = btrfs_add_nondir(trans, BTRFS_I(dir), dentry, BTRFS_I(inode), - 1, index); + err = btrfs_add_link(trans, BTRFS_I(dir), BTRFS_I(inode), + dentry->d_name.name, dentry->d_name.len, 1, index); if (err) { drop_inode = 1; @@ -6579,66 +6674,15 @@ fail: static int btrfs_mkdir(struct user_namespace *mnt_userns, struct inode *dir, struct dentry *dentry, umode_t mode) { - struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb); - struct inode *inode = NULL; - struct btrfs_trans_handle *trans; - struct btrfs_root *root = BTRFS_I(dir)->root; - int err = 0; - u64 objectid = 0; - u64 index = 0; - - /* - * 2 items for inode and ref - * 2 items for dir items - * 1 for xattr if selinux is on - */ - trans = btrfs_start_transaction(root, 5); - if (IS_ERR(trans)) - return PTR_ERR(trans); - - err = btrfs_get_free_objectid(root, &objectid); - if (err) - goto out_fail; - - inode = btrfs_new_inode(trans, root, mnt_userns, dir, - dentry->d_name.name, dentry->d_name.len, - btrfs_ino(BTRFS_I(dir)), objectid, - S_IFDIR | mode, &index); - if (IS_ERR(inode)) { - err = PTR_ERR(inode); - inode = NULL; - goto out_fail; - } + struct inode *inode; - /* these must be set before we unlock the inode */ + inode = new_inode(dir->i_sb); + if (!inode) + return -ENOMEM; + inode_init_owner(mnt_userns, inode, dir, S_IFDIR | mode); inode->i_op = &btrfs_dir_inode_operations; inode->i_fop = &btrfs_dir_file_operations; - - err = btrfs_init_inode_security(trans, inode, dir, &dentry->d_name); - if (err) - goto out_fail; - - btrfs_i_size_write(BTRFS_I(inode), 0); - err = btrfs_update_inode(trans, root, BTRFS_I(inode)); - if (err) - goto out_fail; - - err = btrfs_add_link(trans, BTRFS_I(dir), BTRFS_I(inode), - dentry->d_name.name, - dentry->d_name.len, 0, index); - if (err) - goto out_fail; - - d_instantiate_new(dentry, inode); - -out_fail: - btrfs_end_transaction(trans); - if (err && inode) { - inode_dec_link_count(inode); - discard_new_inode(inode); - } - btrfs_btree_balance_dirty(fs_info); - return err; + return btrfs_create_common(dir, dentry, inode); } static noinline int uncompress_inline(struct btrfs_path *path, @@ -7147,6 +7191,7 @@ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len, u64 *ram_bytes, bool strict) { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct can_nocow_file_extent_args nocow_args = { 0 }; struct btrfs_path *path; int ret; struct extent_buffer *leaf; @@ -7154,13 +7199,7 @@ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len, struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree; struct btrfs_file_extent_item *fi; struct btrfs_key key; - u64 disk_bytenr; - u64 backref_offset; - u64 extent_end; - u64 num_bytes; - int slot; int found_type; - bool nocow = (BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW); path = btrfs_alloc_path(); if (!path) @@ -7171,18 +7210,17 @@ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len, if (ret < 0) goto out; - slot = path->slots[0]; if (ret == 1) { - if (slot == 0) { + if (path->slots[0] == 0) { /* can't find the item, must cow */ ret = 0; goto out; } - slot--; + path->slots[0]--; } ret = 0; leaf = path->nodes[0]; - btrfs_item_key_to_cpu(leaf, &key, slot); + btrfs_item_key_to_cpu(leaf, &key, path->slots[0]); if (key.objectid != btrfs_ino(BTRFS_I(inode)) || key.type != BTRFS_EXTENT_DATA_KEY) { /* not our file or wrong item type, must cow */ @@ -7194,55 +7232,38 @@ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len, goto out; } - fi = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item); - found_type = btrfs_file_extent_type(leaf, fi); - if (found_type != BTRFS_FILE_EXTENT_REG && - found_type != BTRFS_FILE_EXTENT_PREALLOC) { - /* not a regular extent, must cow */ - goto out; - } - - if (!nocow && found_type == BTRFS_FILE_EXTENT_REG) + if (btrfs_file_extent_end(path) <= offset) goto out; - extent_end = key.offset + btrfs_file_extent_num_bytes(leaf, fi); - if (extent_end <= offset) - goto out; + fi = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_file_extent_item); + found_type = btrfs_file_extent_type(leaf, fi); + if (ram_bytes) + *ram_bytes = btrfs_file_extent_ram_bytes(leaf, fi); - disk_bytenr = btrfs_file_extent_disk_bytenr(leaf, fi); - if (disk_bytenr == 0) - goto out; + nocow_args.start = offset; + nocow_args.end = offset + *len - 1; + nocow_args.strict = strict; + nocow_args.free_path = true; - if (btrfs_file_extent_compression(leaf, fi) || - btrfs_file_extent_encryption(leaf, fi) || - btrfs_file_extent_other_encoding(leaf, fi)) - goto out; + ret = can_nocow_file_extent(path, &key, BTRFS_I(inode), &nocow_args); + /* can_nocow_file_extent() has freed the path. */ + path = NULL; - /* - * Do the same check as in btrfs_cross_ref_exist but without the - * unnecessary search. - */ - if (!strict && - (btrfs_file_extent_generation(leaf, fi) <= - btrfs_root_last_snapshot(&root->root_item))) + if (ret != 1) { + /* Treat errors as not being able to NOCOW. */ + ret = 0; goto out; - - backref_offset = btrfs_file_extent_offset(leaf, fi); - - if (orig_start) { - *orig_start = key.offset - backref_offset; - *orig_block_len = btrfs_file_extent_disk_num_bytes(leaf, fi); - *ram_bytes = btrfs_file_extent_ram_bytes(leaf, fi); } - if (btrfs_extent_readonly(fs_info, disk_bytenr)) + ret = 0; + if (btrfs_extent_readonly(fs_info, nocow_args.disk_bytenr)) goto out; - num_bytes = min(offset + *len, extent_end) - offset; - if (!nocow && found_type == BTRFS_FILE_EXTENT_PREALLOC) { + if (!(BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW) && + found_type == BTRFS_FILE_EXTENT_PREALLOC) { u64 range_end; - range_end = round_up(offset + num_bytes, + range_end = round_up(offset + nocow_args.num_bytes, root->fs_info->sectorsize) - 1; ret = test_range_bit(io_tree, offset, range_end, EXTENT_DELALLOC, 0, NULL); @@ -7252,36 +7273,12 @@ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len, } } - btrfs_release_path(path); - - /* - * look for other files referencing this extent, if we - * find any we must cow - */ - - ret = btrfs_cross_ref_exist(root, btrfs_ino(BTRFS_I(inode)), - key.offset - backref_offset, disk_bytenr, - strict); - if (ret) { - ret = 0; - goto out; - } + if (orig_start) + *orig_start = key.offset - nocow_args.extent_offset; + if (orig_block_len) + *orig_block_len = nocow_args.disk_num_bytes; - /* - * adjust disk_bytenr and num_bytes to cover just the bytes - * in this extent we are about to write. If there - * are any csums in that range we have to cow in order - * to keep the csums correct - */ - disk_bytenr += backref_offset; - disk_bytenr += offset - key.offset; - if (csum_exist_in_range(fs_info, disk_bytenr, num_bytes)) - goto out; - /* - * all of the above have passed, it is safe to overwrite this extent - * without cow - */ - *len = num_bytes; + *len = nocow_args.num_bytes; ret = 1; out: btrfs_free_path(path); @@ -7289,14 +7286,22 @@ out: } static int lock_extent_direct(struct inode *inode, u64 lockstart, u64 lockend, - struct extent_state **cached_state, bool writing) + struct extent_state **cached_state, + unsigned int iomap_flags) { + const bool writing = (iomap_flags & IOMAP_WRITE); + const bool nowait = (iomap_flags & IOMAP_NOWAIT); + struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree; struct btrfs_ordered_extent *ordered; int ret = 0; while (1) { - lock_extent_bits(&BTRFS_I(inode)->io_tree, lockstart, lockend, - cached_state); + if (nowait) { + if (!try_lock_extent(io_tree, lockstart, lockend)) + return -EAGAIN; + } else { + lock_extent_bits(io_tree, lockstart, lockend, cached_state); + } /* * We're concerned with the entire range that we're going to be * doing DIO to, so we need to make sure there's no ordered @@ -7317,10 +7322,14 @@ static int lock_extent_direct(struct inode *inode, u64 lockstart, u64 lockend, lockstart, lockend))) break; - unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart, lockend, - cached_state); + unlock_extent_cached(io_tree, lockstart, lockend, cached_state); if (ordered) { + if (nowait) { + btrfs_put_ordered_extent(ordered); + ret = -EAGAIN; + break; + } /* * If we are doing a DIO read and the ordered extent we * found is for a buffered write, we can not wait for it @@ -7340,7 +7349,7 @@ static int lock_extent_direct(struct inode *inode, u64 lockstart, u64 lockend, test_bit(BTRFS_ORDERED_DIRECT, &ordered->flags)) btrfs_start_ordered_extent(ordered, 1); else - ret = -ENOTBLK; + ret = nowait ? -EAGAIN : -ENOTBLK; btrfs_put_ordered_extent(ordered); } else { /* @@ -7356,7 +7365,7 @@ static int lock_extent_direct(struct inode *inode, u64 lockstart, u64 lockend, * ordered extent to complete while holding a lock on * that page. */ - ret = -ENOTBLK; + ret = nowait ? -EAGAIN : -ENOTBLK; } if (ret) @@ -7430,14 +7439,18 @@ static struct extent_map *create_io_em(struct btrfs_inode *inode, u64 start, static int btrfs_get_blocks_direct_write(struct extent_map **map, struct inode *inode, struct btrfs_dio_data *dio_data, - u64 start, u64 len) + u64 start, u64 len, + unsigned int iomap_flags) { + const bool nowait = (iomap_flags & IOMAP_NOWAIT); struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct extent_map *em = *map; int type; u64 block_start, orig_start, orig_block_len, ram_bytes; + struct btrfs_block_group *bg; bool can_nocow = false; bool space_reserved = false; + u64 prev_len; int ret = 0; /* @@ -7460,21 +7473,27 @@ static int btrfs_get_blocks_direct_write(struct extent_map **map, block_start = em->block_start + (start - em->start); if (can_nocow_extent(inode, start, &len, &orig_start, - &orig_block_len, &ram_bytes, false) == 1 && - btrfs_inc_nocow_writers(fs_info, block_start)) - can_nocow = true; + &orig_block_len, &ram_bytes, false) == 1) { + bg = btrfs_inc_nocow_writers(fs_info, block_start); + if (bg) + can_nocow = true; + } } + prev_len = len; if (can_nocow) { struct extent_map *em2; /* We can NOCOW, so only need to reserve metadata space. */ - ret = btrfs_delalloc_reserve_metadata(BTRFS_I(inode), len, len); + ret = btrfs_delalloc_reserve_metadata(BTRFS_I(inode), len, len, + nowait); if (ret < 0) { /* Our caller expects us to free the input extent map. */ free_extent_map(em); *map = NULL; - btrfs_dec_nocow_writers(fs_info, block_start); + btrfs_dec_nocow_writers(bg); + if (nowait && (ret == -ENOSPC || ret == -EDQUOT)) + ret = -EAGAIN; goto out; } space_reserved = true; @@ -7483,7 +7502,7 @@ static int btrfs_get_blocks_direct_write(struct extent_map **map, orig_start, block_start, len, orig_block_len, ram_bytes, type); - btrfs_dec_nocow_writers(fs_info, block_start); + btrfs_dec_nocow_writers(bg); if (type == BTRFS_ORDERED_PREALLOC) { free_extent_map(em); *map = em = em2; @@ -7493,17 +7512,29 @@ static int btrfs_get_blocks_direct_write(struct extent_map **map, ret = PTR_ERR(em2); goto out; } - } else { - const u64 prev_len = len; + dio_data->nocow_done = true; + } else { /* Our caller expects us to free the input extent map. */ free_extent_map(em); *map = NULL; - /* We have to COW, so need to reserve metadata and data space. */ - ret = btrfs_delalloc_reserve_space(BTRFS_I(inode), - &dio_data->data_reserved, - start, len); + if (nowait) + return -EAGAIN; + + /* + * If we could not allocate data space before locking the file + * range and we can't do a NOCOW write, then we have to fail. + */ + if (!dio_data->data_space_reserved) + return -ENOSPC; + + /* + * We have to COW and we have already reserved data space before, + * so now we reserve only metadata. + */ + ret = btrfs_delalloc_reserve_metadata(BTRFS_I(inode), len, len, + false); if (ret < 0) goto out; space_reserved = true; @@ -7516,17 +7547,15 @@ static int btrfs_get_blocks_direct_write(struct extent_map **map, *map = em; len = min(len, em->len - (start - em->start)); if (len < prev_len) - btrfs_delalloc_release_space(BTRFS_I(inode), - dio_data->data_reserved, - start + len, prev_len - len, - true); + btrfs_delalloc_release_metadata(BTRFS_I(inode), + prev_len - len, true); } /* * We have created our ordered extent, so we can now release our reservation * for an outstanding extent. */ - btrfs_delalloc_release_extents(BTRFS_I(inode), len); + btrfs_delalloc_release_extents(BTRFS_I(inode), prev_len); /* * Need to update the i_size under the extent lock so buffered @@ -7537,15 +7566,7 @@ static int btrfs_get_blocks_direct_write(struct extent_map **map, out: if (ret && space_reserved) { btrfs_delalloc_release_extents(BTRFS_I(inode), len); - if (can_nocow) { - btrfs_delalloc_release_metadata(BTRFS_I(inode), len, true); - } else { - btrfs_delalloc_release_space(BTRFS_I(inode), - dio_data->data_reserved, - start, len, true); - extent_changeset_free(dio_data->data_reserved); - dio_data->data_reserved = NULL; - } + btrfs_delalloc_release_metadata(BTRFS_I(inode), len, true); } return ret; } @@ -7554,14 +7575,16 @@ static int btrfs_dio_iomap_begin(struct inode *inode, loff_t start, loff_t length, unsigned int flags, struct iomap *iomap, struct iomap *srcmap) { + struct iomap_iter *iter = container_of(iomap, struct iomap_iter, iomap); struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct extent_map *em; struct extent_state *cached_state = NULL; - struct btrfs_dio_data *dio_data = NULL; + struct btrfs_dio_data *dio_data = iter->private; u64 lockstart, lockend; const bool write = !!(flags & IOMAP_WRITE); int ret = 0; u64 len = length; + const u64 data_alloc_len = length; bool unlock_extents = false; if (!write) @@ -7571,34 +7594,67 @@ static int btrfs_dio_iomap_begin(struct inode *inode, loff_t start, lockend = start + len - 1; /* - * The generic stuff only does filemap_write_and_wait_range, which - * isn't enough if we've written compressed pages to this area, so we - * need to flush the dirty pages again to make absolutely sure that any - * outstanding dirty pages are on disk. + * iomap_dio_rw() only does filemap_write_and_wait_range(), which isn't + * enough if we've written compressed pages to this area, so we need to + * flush the dirty pages again to make absolutely sure that any + * outstanding dirty pages are on disk - the first flush only starts + * compression on the data, while keeping the pages locked, so by the + * time the second flush returns we know bios for the compressed pages + * were submitted and finished, and the pages no longer under writeback. + * + * If we have a NOWAIT request and we have any pages in the range that + * are locked, likely due to compression still in progress, we don't want + * to block on page locks. We also don't want to block on pages marked as + * dirty or under writeback (same as for the non-compression case). + * iomap_dio_rw() did the same check, but after that and before we got + * here, mmap'ed writes may have happened or buffered reads started + * (readpage() and readahead(), which lock pages), as we haven't locked + * the file range yet. */ if (test_bit(BTRFS_INODE_HAS_ASYNC_EXTENT, &BTRFS_I(inode)->runtime_flags)) { - ret = filemap_fdatawrite_range(inode->i_mapping, start, - start + length - 1); - if (ret) - return ret; + if (flags & IOMAP_NOWAIT) { + if (filemap_range_needs_writeback(inode->i_mapping, + lockstart, lockend)) + return -EAGAIN; + } else { + ret = filemap_fdatawrite_range(inode->i_mapping, start, + start + length - 1); + if (ret) + return ret; + } } - dio_data = kzalloc(sizeof(*dio_data), GFP_NOFS); - if (!dio_data) - return -ENOMEM; - - iomap->private = dio_data; + memset(dio_data, 0, sizeof(*dio_data)); + /* + * We always try to allocate data space and must do it before locking + * the file range, to avoid deadlocks with concurrent writes to the same + * range if the range has several extents and the writes don't expand the + * current i_size (the inode lock is taken in shared mode). If we fail to + * allocate data space here we continue and later, after locking the + * file range, we fail with ENOSPC only if we figure out we can not do a + * NOCOW write. + */ + if (write && !(flags & IOMAP_NOWAIT)) { + ret = btrfs_check_data_free_space(BTRFS_I(inode), + &dio_data->data_reserved, + start, data_alloc_len); + if (!ret) + dio_data->data_space_reserved = true; + else if (ret && !(BTRFS_I(inode)->flags & + (BTRFS_INODE_NODATACOW | BTRFS_INODE_PREALLOC))) + goto err; + } /* * If this errors out it's because we couldn't invalidate pagecache for - * this range and we need to fallback to buffered. + * this range and we need to fallback to buffered IO, or we are doing a + * NOWAIT read/write and we need to block. */ - if (lock_extent_direct(inode, lockstart, lockend, &cached_state, write)) { - ret = -ENOTBLK; + ret = lock_extent_direct(inode, lockstart, lockend, &cached_state, flags); + if (ret < 0) goto err; - } em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, start, len); if (IS_ERR(em)) { @@ -7658,12 +7714,30 @@ static int btrfs_dio_iomap_begin(struct inode *inode, loff_t start, if (write) { ret = btrfs_get_blocks_direct_write(&em, inode, dio_data, - start, len); + start, len, flags); if (ret < 0) goto unlock_err; unlock_extents = true; /* Recalc len in case the new em is smaller than requested */ len = min(len, em->len - (start - em->start)); + if (dio_data->data_space_reserved) { + u64 release_offset; + u64 release_len = 0; + + if (dio_data->nocow_done) { + release_offset = start; + release_len = data_alloc_len; + } else if (len < data_alloc_len) { + release_offset = start + len; + release_len = data_alloc_len - len; + } + + if (release_len > 0) + btrfs_free_reserved_data_space(BTRFS_I(inode), + dio_data->data_reserved, + release_offset, + release_len); + } } else { /* * We need to unlock only the end area that we aren't using. @@ -7708,7 +7782,12 @@ unlock_err: unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart, lockend, &cached_state); err: - kfree(dio_data); + if (dio_data->data_space_reserved) { + btrfs_free_reserved_data_space(BTRFS_I(inode), + dio_data->data_reserved, + start, data_alloc_len); + extent_changeset_free(dio_data->data_reserved); + } return ret; } @@ -7716,15 +7795,16 @@ err: static int btrfs_dio_iomap_end(struct inode *inode, loff_t pos, loff_t length, ssize_t written, unsigned int flags, struct iomap *iomap) { - int ret = 0; - struct btrfs_dio_data *dio_data = iomap->private; + struct iomap_iter *iter = container_of(iomap, struct iomap_iter, iomap); + struct btrfs_dio_data *dio_data = iter->private; size_t submitted = dio_data->submitted; const bool write = !!(flags & IOMAP_WRITE); + int ret = 0; if (!write && (iomap->type == IOMAP_HOLE)) { /* If reading from a hole, unlock and return */ unlock_extent(&BTRFS_I(inode)->io_tree, pos, pos + length - 1); - goto out; + return 0; } if (submitted < length) { @@ -7741,10 +7821,6 @@ static int btrfs_dio_iomap_end(struct inode *inode, loff_t pos, loff_t length, if (write) extent_changeset_free(dio_data->data_reserved); -out: - kfree(dio_data); - iomap->private = NULL; - return ret; } @@ -7757,40 +7833,36 @@ static void btrfs_dio_private_put(struct btrfs_dio_private *dip) if (!refcount_dec_and_test(&dip->refs)) return; - if (btrfs_op(dip->dio_bio) == BTRFS_MAP_WRITE) { + if (btrfs_op(&dip->bio) == BTRFS_MAP_WRITE) { __endio_write_update_ordered(BTRFS_I(dip->inode), dip->file_offset, dip->bytes, - !dip->dio_bio->bi_status); + !dip->bio.bi_status); } else { unlock_extent(&BTRFS_I(dip->inode)->io_tree, dip->file_offset, dip->file_offset + dip->bytes - 1); } - bio_endio(dip->dio_bio); - kfree(dip); + kfree(dip->csums); + bio_endio(&dip->bio); } -static blk_status_t submit_dio_repair_bio(struct inode *inode, struct bio *bio, - int mirror_num, - unsigned long bio_flags) +static void submit_dio_repair_bio(struct inode *inode, struct bio *bio, + int mirror_num, + enum btrfs_compression_type compress_type) { struct btrfs_dio_private *dip = bio->bi_private; struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); - blk_status_t ret; BUG_ON(bio_op(bio) == REQ_OP_WRITE); - ret = btrfs_bio_wq_end_io(fs_info, bio, BTRFS_WQ_ENDIO_DATA); - if (ret) - return ret; + if (btrfs_bio_wq_end_io(fs_info, bio, BTRFS_WQ_ENDIO_DATA)) + return; refcount_inc(&dip->refs); - ret = btrfs_map_bio(fs_info, bio, mirror_num); - if (ret) + if (btrfs_map_bio(fs_info, bio, mirror_num)) refcount_dec(&dip->refs); - return ret; } static blk_status_t btrfs_check_read_dio_bio(struct btrfs_dio_private *dip, @@ -7805,8 +7877,6 @@ static blk_status_t btrfs_check_read_dio_bio(struct btrfs_dio_private *dip, const bool csum = !(BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM); struct bio_vec bvec; struct bvec_iter iter; - const u64 orig_file_offset = dip->file_offset; - u64 start = orig_file_offset; u32 bio_offset = 0; blk_status_t err = BLK_STS_OK; @@ -7816,6 +7886,8 @@ static blk_status_t btrfs_check_read_dio_bio(struct btrfs_dio_private *dip, nr_sectors = BTRFS_BYTES_TO_BLKS(fs_info, bvec.bv_len); pgoff = bvec.bv_offset; for (i = 0; i < nr_sectors; i++) { + u64 start = bbio->file_offset + bio_offset; + ASSERT(pgoff < PAGE_SIZE); if (uptodate && (!csum || !check_data_csum(inode, bbio, @@ -7828,17 +7900,13 @@ static blk_status_t btrfs_check_read_dio_bio(struct btrfs_dio_private *dip, } else { int ret; - ASSERT((start - orig_file_offset) < UINT_MAX); - ret = btrfs_repair_one_sector(inode, - &bbio->bio, - start - orig_file_offset, - bvec.bv_page, pgoff, + ret = btrfs_repair_one_sector(inode, &bbio->bio, + bio_offset, bvec.bv_page, pgoff, start, bbio->mirror_num, submit_dio_repair_bio); if (ret) err = errno_to_blk_status(ret); } - start += sectorsize; ASSERT(bio_offset + sectorsize > bio_offset); bio_offset += sectorsize; pgoff += sectorsize; @@ -7865,6 +7933,7 @@ static blk_status_t btrfs_submit_bio_start_direct_io(struct inode *inode, static void btrfs_end_dio_bio(struct bio *bio) { struct btrfs_dio_private *dip = bio->bi_private; + struct btrfs_bio *bbio = btrfs_bio(bio); blk_status_t err = bio->bi_status; if (err) @@ -7875,12 +7944,12 @@ static void btrfs_end_dio_bio(struct bio *bio) bio->bi_iter.bi_size, err); if (bio_op(bio) == REQ_OP_READ) - err = btrfs_check_read_dio_bio(dip, btrfs_bio(bio), !err); + err = btrfs_check_read_dio_bio(dip, bbio, !err); if (err) - dip->dio_bio->bi_status = err; + dip->bio.bi_status = err; - btrfs_record_physical_zoned(dip->inode, dip->file_offset, bio); + btrfs_record_physical_zoned(dip->inode, bbio->file_offset, bio); bio_put(bio); btrfs_dio_private_put(dip); @@ -7908,7 +7977,7 @@ static inline blk_status_t btrfs_submit_dio_bio(struct bio *bio, goto map; if (write && async_submit) { - ret = btrfs_wq_submit_bio(inode, bio, 0, 0, file_offset, + ret = btrfs_wq_submit_bio(inode, bio, 0, file_offset, btrfs_submit_bio_start_direct_io); goto err; } else if (write) { @@ -7933,50 +8002,16 @@ err: return ret; } -/* - * If this succeeds, the btrfs_dio_private is responsible for cleaning up locked - * or ordered extents whether or not we submit any bios. - */ -static struct btrfs_dio_private *btrfs_create_dio_private(struct bio *dio_bio, - struct inode *inode, - loff_t file_offset) -{ - const bool write = (btrfs_op(dio_bio) == BTRFS_MAP_WRITE); - const bool csum = !(BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM); - size_t dip_size; - struct btrfs_dio_private *dip; - - dip_size = sizeof(*dip); - if (!write && csum) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); - size_t nblocks; - - nblocks = dio_bio->bi_iter.bi_size >> fs_info->sectorsize_bits; - dip_size += fs_info->csum_size * nblocks; - } - - dip = kzalloc(dip_size, GFP_NOFS); - if (!dip) - return NULL; - - dip->inode = inode; - dip->file_offset = file_offset; - dip->bytes = dio_bio->bi_iter.bi_size; - dip->disk_bytenr = dio_bio->bi_iter.bi_sector << 9; - dip->dio_bio = dio_bio; - refcount_set(&dip->refs, 1); - return dip; -} - static void btrfs_submit_direct(const struct iomap_iter *iter, struct bio *dio_bio, loff_t file_offset) { + struct btrfs_dio_private *dip = + container_of(dio_bio, struct btrfs_dio_private, bio); struct inode *inode = iter->inode; const bool write = (btrfs_op(dio_bio) == BTRFS_MAP_WRITE); struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); const bool raid56 = (btrfs_data_alloc_profile(fs_info) & BTRFS_BLOCK_GROUP_RAID56_MASK); - struct btrfs_dio_private *dip; struct bio *bio; u64 start_sector; int async_submit = 0; @@ -7987,27 +8022,28 @@ static void btrfs_submit_direct(const struct iomap_iter *iter, int ret; blk_status_t status; struct btrfs_io_geometry geom; - struct btrfs_dio_data *dio_data = iter->iomap.private; + struct btrfs_dio_data *dio_data = iter->private; struct extent_map *em = NULL; - dip = btrfs_create_dio_private(dio_bio, inode, file_offset); - if (!dip) { - if (!write) { - unlock_extent(&BTRFS_I(inode)->io_tree, file_offset, - file_offset + dio_bio->bi_iter.bi_size - 1); - } - dio_bio->bi_status = BLK_STS_RESOURCE; - bio_endio(dio_bio); - return; - } + dip->inode = inode; + dip->file_offset = file_offset; + dip->bytes = dio_bio->bi_iter.bi_size; + refcount_set(&dip->refs, 1); + dip->csums = NULL; + + if (!write && !(BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM)) { + unsigned int nr_sectors = + (dio_bio->bi_iter.bi_size >> fs_info->sectorsize_bits); - if (!write) { /* * Load the csums up front to reduce csum tree searches and * contention when submitting bios. - * - * If we have csums disabled this will do nothing. */ + status = BLK_STS_RESOURCE; + dip->csums = kcalloc(nr_sectors, fs_info->csum_size, GFP_NOFS); + if (!dip) + goto out_err; + status = btrfs_lookup_bio_sums(inode, dio_bio, dip->csums); if (status != BLK_STS_OK) goto out_err; @@ -8041,6 +8077,7 @@ static void btrfs_submit_direct(const struct iomap_iter *iter, bio = btrfs_bio_clone_partial(dio_bio, clone_offset, clone_len); bio->bi_private = dip; bio->bi_end_io = btrfs_end_dio_bio; + btrfs_bio(bio)->file_offset = file_offset; if (bio_op(bio) == REQ_OP_ZONE_APPEND) { status = extract_ordered_extent(BTRFS_I(inode), bio, @@ -8096,19 +8133,28 @@ static void btrfs_submit_direct(const struct iomap_iter *iter, out_err_em: free_extent_map(em); out_err: - dip->dio_bio->bi_status = status; + dio_bio->bi_status = status; btrfs_dio_private_put(dip); } -const struct iomap_ops btrfs_dio_iomap_ops = { +static const struct iomap_ops btrfs_dio_iomap_ops = { .iomap_begin = btrfs_dio_iomap_begin, .iomap_end = btrfs_dio_iomap_end, }; -const struct iomap_dio_ops btrfs_dio_ops = { +static const struct iomap_dio_ops btrfs_dio_ops = { .submit_io = btrfs_submit_direct, + .bio_set = &btrfs_dio_bioset, }; +ssize_t btrfs_dio_rw(struct kiocb *iocb, struct iov_iter *iter, size_t done_before) +{ + struct btrfs_dio_data data; + + return iomap_dio_rw(iocb, iter, &btrfs_dio_iomap_ops, &btrfs_dio_ops, + IOMAP_DIO_PARTIAL, &data, done_before); +} + static int btrfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 len) { @@ -8121,27 +8167,6 @@ static int btrfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, return extent_fiemap(BTRFS_I(inode), fieinfo, start, len); } -int btrfs_readpage(struct file *file, struct page *page) -{ - struct btrfs_inode *inode = BTRFS_I(page->mapping->host); - u64 start = page_offset(page); - u64 end = start + PAGE_SIZE - 1; - struct btrfs_bio_ctrl bio_ctrl = { 0 }; - int ret; - - btrfs_lock_and_flush_ordered_range(inode, start, end, NULL); - - ret = btrfs_do_readpage(page, NULL, &bio_ctrl, 0, NULL); - if (bio_ctrl.bio) { - int ret2; - - ret2 = submit_one_bio(bio_ctrl.bio, 0, bio_ctrl.bio_flags); - if (ret == 0) - ret = ret2; - } - return ret; -} - static int btrfs_writepage(struct page *page, struct writeback_control *wbc) { struct inode *inode = page->mapping->host; @@ -8179,7 +8204,7 @@ static void btrfs_readahead(struct readahead_control *rac) } /* - * For releasepage() and invalidate_folio() we have a race window where + * For release_folio() and invalidate_folio() we have a race window where * folio_end_writeback() is called but the subpage spinlock is not yet released. * If we continue to release/invalidate the page, we could cause use-after-free * for subpage spinlock. So this function is to spin and wait for subpage @@ -8190,7 +8215,7 @@ static void wait_subpage_spinlock(struct page *page) struct btrfs_fs_info *fs_info = btrfs_sb(page->mapping->host->i_sb); struct btrfs_subpage *subpage; - if (fs_info->sectorsize == PAGE_SIZE) + if (!btrfs_is_subpage(fs_info, page)) return; ASSERT(PagePrivate(page) && page->private); @@ -8211,22 +8236,22 @@ static void wait_subpage_spinlock(struct page *page) spin_unlock_irq(&subpage->lock); } -static int __btrfs_releasepage(struct page *page, gfp_t gfp_flags) +static bool __btrfs_release_folio(struct folio *folio, gfp_t gfp_flags) { - int ret = try_release_extent_mapping(page, gfp_flags); + int ret = try_release_extent_mapping(&folio->page, gfp_flags); if (ret == 1) { - wait_subpage_spinlock(page); - clear_page_extent_mapped(page); + wait_subpage_spinlock(&folio->page); + clear_page_extent_mapped(&folio->page); } return ret; } -static int btrfs_releasepage(struct page *page, gfp_t gfp_flags) +static bool btrfs_release_folio(struct folio *folio, gfp_t gfp_flags) { - if (PageWriteback(page) || PageDirty(page)) - return 0; - return __btrfs_releasepage(page, gfp_flags); + if (folio_test_writeback(folio) || folio_test_dirty(folio)) + return false; + return __btrfs_release_folio(folio, gfp_flags); } #ifdef CONFIG_MIGRATION @@ -8297,7 +8322,7 @@ static void btrfs_invalidate_folio(struct folio *folio, size_t offset, * still safe to wait for ordered extent to finish. */ if (!(offset == 0 && length == folio_size(folio))) { - btrfs_releasepage(&folio->page, GFP_NOFS); + btrfs_release_folio(folio, GFP_NOFS); return; } @@ -8421,7 +8446,7 @@ next: ASSERT(!folio_test_ordered(folio)); btrfs_page_clear_checked(fs_info, &folio->page, folio_pos(folio), folio_size(folio)); if (!inode_evicting) - __btrfs_releasepage(&folio->page, GFP_NOFS); + __btrfs_release_folio(folio, GFP_NOFS); clear_page_extent_mapped(&folio->page); } @@ -8772,46 +8797,23 @@ out: return ret; } -/* - * create a new subvolume directory/inode (helper for the ioctl). - */ -int btrfs_create_subvol_root(struct btrfs_trans_handle *trans, - struct btrfs_root *new_root, - struct btrfs_root *parent_root, - struct user_namespace *mnt_userns) +struct inode *btrfs_new_subvol_inode(struct user_namespace *mnt_userns, + struct inode *dir) { struct inode *inode; - int err; - u64 index = 0; - u64 ino; - - err = btrfs_get_free_objectid(new_root, &ino); - if (err < 0) - return err; - inode = btrfs_new_inode(trans, new_root, mnt_userns, NULL, "..", 2, - ino, ino, - S_IFDIR | (~current_umask() & S_IRWXUGO), - &index); - if (IS_ERR(inode)) - return PTR_ERR(inode); - inode->i_op = &btrfs_dir_inode_operations; - inode->i_fop = &btrfs_dir_file_operations; - - set_nlink(inode, 1); - btrfs_i_size_write(BTRFS_I(inode), 0); - unlock_new_inode(inode); - - err = btrfs_subvol_inherit_props(trans, new_root, parent_root); - if (err) - btrfs_err(new_root->fs_info, - "error inheriting subvolume %llu properties: %d", - new_root->root_key.objectid, err); - - err = btrfs_update_inode(trans, new_root, BTRFS_I(inode)); - - iput(inode); - return err; + inode = new_inode(dir->i_sb); + if (inode) { + /* + * Subvolumes don't inherit the sgid bit or the parent's gid if + * the parent's sgid bit is set. This is probably a bug. + */ + inode_init_owner(mnt_userns, inode, NULL, + S_IFDIR | (~current_umask() & S_IRWXUGO)); + inode->i_op = &btrfs_dir_inode_operations; + inode->i_fop = &btrfs_dir_file_operations; + } + return inode; } struct inode *btrfs_alloc_inode(struct super_block *sb) @@ -8951,7 +8953,7 @@ int btrfs_drop_inode(struct inode *inode) static void init_once(void *foo) { - struct btrfs_inode *ei = (struct btrfs_inode *) foo; + struct btrfs_inode *ei = foo; inode_init_once(&ei->vfs_inode); } @@ -8963,6 +8965,7 @@ void __cold btrfs_destroy_cachep(void) * destroy cache. */ rcu_barrier(); + bioset_exit(&btrfs_dio_bioset); kmem_cache_destroy(btrfs_inode_cachep); kmem_cache_destroy(btrfs_trans_handle_cachep); kmem_cache_destroy(btrfs_path_cachep); @@ -9003,6 +9006,11 @@ int __init btrfs_init_cachep(void) if (!btrfs_free_space_bitmap_cachep) goto fail; + if (bioset_init(&btrfs_dio_bioset, BIO_POOL_SIZE, + offsetof(struct btrfs_dio_private, bio), + BIOSET_NEED_BVECS)) + goto fail; + return 0; fail: btrfs_destroy_cachep(); @@ -9058,6 +9066,7 @@ static int btrfs_rename_exchange(struct inode *old_dir, { struct btrfs_fs_info *fs_info = btrfs_sb(old_dir->i_sb); struct btrfs_trans_handle *trans; + unsigned int trans_num_items; struct btrfs_root *root = BTRFS_I(old_dir)->root; struct btrfs_root *dest = BTRFS_I(new_dir)->root; struct inode *new_inode = new_dentry->d_inode; @@ -9089,14 +9098,37 @@ static int btrfs_rename_exchange(struct inode *old_dir, down_read(&fs_info->subvol_sem); /* - * We want to reserve the absolute worst case amount of items. So if - * both inodes are subvols and we need to unlink them then that would - * require 4 item modifications, but if they are both normal inodes it - * would require 5 item modifications, so we'll assume their normal - * inodes. So 5 * 2 is 10, plus 2 for the new links, so 12 total items - * should cover the worst case number of items we'll modify. + * For each inode: + * 1 to remove old dir item + * 1 to remove old dir index + * 1 to add new dir item + * 1 to add new dir index + * 1 to update parent inode + * + * If the parents are the same, we only need to account for one */ - trans = btrfs_start_transaction(root, 12); + trans_num_items = (old_dir == new_dir ? 9 : 10); + if (old_ino == BTRFS_FIRST_FREE_OBJECTID) { + /* + * 1 to remove old root ref + * 1 to remove old root backref + * 1 to add new root ref + * 1 to add new root backref + */ + trans_num_items += 4; + } else { + /* + * 1 to update inode item + * 1 to remove old inode ref + * 1 to add new inode ref + */ + trans_num_items += 3; + } + if (new_ino == BTRFS_FIRST_FREE_OBJECTID) + trans_num_items += 4; + else + trans_num_items += 3; + trans = btrfs_start_transaction(root, trans_num_items); if (IS_ERR(trans)) { ret = PTR_ERR(trans); goto out_notrans; @@ -9263,56 +9295,19 @@ out_notrans: return ret; } -static int btrfs_whiteout_for_rename(struct btrfs_trans_handle *trans, - struct btrfs_root *root, - struct user_namespace *mnt_userns, - struct inode *dir, - struct dentry *dentry) +static struct inode *new_whiteout_inode(struct user_namespace *mnt_userns, + struct inode *dir) { - int ret; struct inode *inode; - u64 objectid; - u64 index; - - ret = btrfs_get_free_objectid(root, &objectid); - if (ret) - return ret; - inode = btrfs_new_inode(trans, root, mnt_userns, dir, - dentry->d_name.name, - dentry->d_name.len, - btrfs_ino(BTRFS_I(dir)), - objectid, - S_IFCHR | WHITEOUT_MODE, - &index); - - if (IS_ERR(inode)) { - ret = PTR_ERR(inode); - return ret; + inode = new_inode(dir->i_sb); + if (inode) { + inode_init_owner(mnt_userns, inode, dir, + S_IFCHR | WHITEOUT_MODE); + inode->i_op = &btrfs_special_inode_operations; + init_special_inode(inode, inode->i_mode, WHITEOUT_DEV); } - - inode->i_op = &btrfs_special_inode_operations; - init_special_inode(inode, inode->i_mode, - WHITEOUT_DEV); - - ret = btrfs_init_inode_security(trans, inode, dir, - &dentry->d_name); - if (ret) - goto out; - - ret = btrfs_add_nondir(trans, BTRFS_I(dir), dentry, - BTRFS_I(inode), 0, index); - if (ret) - goto out; - - ret = btrfs_update_inode(trans, root, BTRFS_I(inode)); -out: - unlock_new_inode(inode); - if (ret) - inode_dec_link_count(inode); - iput(inode); - - return ret; + return inode; } static int btrfs_rename(struct user_namespace *mnt_userns, @@ -9321,6 +9316,10 @@ static int btrfs_rename(struct user_namespace *mnt_userns, unsigned int flags) { struct btrfs_fs_info *fs_info = btrfs_sb(old_dir->i_sb); + struct btrfs_new_inode_args whiteout_args = { + .dir = old_dir, + .dentry = old_dentry, + }; struct btrfs_trans_handle *trans; unsigned int trans_num_items; struct btrfs_root *root = BTRFS_I(old_dir)->root; @@ -9375,23 +9374,56 @@ static int btrfs_rename(struct user_namespace *mnt_userns, if (new_inode && S_ISREG(old_inode->i_mode) && new_inode->i_size) filemap_flush(old_inode->i_mapping); - /* close the racy window with snapshot create/destroy ioctl */ - if (old_ino == BTRFS_FIRST_FREE_OBJECTID) + if (flags & RENAME_WHITEOUT) { + whiteout_args.inode = new_whiteout_inode(mnt_userns, old_dir); + if (!whiteout_args.inode) + return -ENOMEM; + ret = btrfs_new_inode_prepare(&whiteout_args, &trans_num_items); + if (ret) + goto out_whiteout_inode; + } else { + /* 1 to update the old parent inode. */ + trans_num_items = 1; + } + + if (old_ino == BTRFS_FIRST_FREE_OBJECTID) { + /* Close the race window with snapshot create/destroy ioctl */ down_read(&fs_info->subvol_sem); + /* + * 1 to remove old root ref + * 1 to remove old root backref + * 1 to add new root ref + * 1 to add new root backref + */ + trans_num_items += 4; + } else { + /* + * 1 to update inode + * 1 to remove old inode ref + * 1 to add new inode ref + */ + trans_num_items += 3; + } /* - * We want to reserve the absolute worst case amount of items. So if - * both inodes are subvols and we need to unlink them then that would - * require 4 item modifications, but if they are both normal inodes it - * would require 5 item modifications, so we'll assume they are normal - * inodes. So 5 * 2 is 10, plus 1 for the new link, so 11 total items - * should cover the worst case number of items we'll modify. - * If our rename has the whiteout flag, we need more 5 units for the - * new inode (1 inode item, 1 inode ref, 2 dir items and 1 xattr item - * when selinux is enabled). + * 1 to remove old dir item + * 1 to remove old dir index + * 1 to add new dir item + * 1 to add new dir index */ - trans_num_items = 11; - if (flags & RENAME_WHITEOUT) + trans_num_items += 4; + /* 1 to update new parent inode if it's not the same as the old parent */ + if (new_dir != old_dir) + trans_num_items++; + if (new_inode) { + /* + * 1 to update inode + * 1 to remove inode ref + * 1 to remove dir item + * 1 to remove dir index + * 1 to possibly add orphan item + */ trans_num_items += 5; + } trans = btrfs_start_transaction(root, trans_num_items); if (IS_ERR(trans)) { ret = PTR_ERR(trans); @@ -9487,12 +9519,14 @@ static int btrfs_rename(struct user_namespace *mnt_userns, rename_ctx.index, new_dentry->d_parent); if (flags & RENAME_WHITEOUT) { - ret = btrfs_whiteout_for_rename(trans, root, mnt_userns, - old_dir, old_dentry); - + ret = btrfs_create_new_inode(trans, &whiteout_args); if (ret) { btrfs_abort_transaction(trans, ret); goto out_fail; + } else { + unlock_new_inode(whiteout_args.inode); + iput(whiteout_args.inode); + whiteout_args.inode = NULL; } } out_fail: @@ -9501,7 +9535,11 @@ out_fail: out_notrans: if (old_ino == BTRFS_FIRST_FREE_OBJECTID) up_read(&fs_info->subvol_sem); - + if (flags & RENAME_WHITEOUT) + btrfs_new_inode_args_destroy(&whiteout_args); +out_whiteout_inode: + if (flags & RENAME_WHITEOUT) + iput(whiteout_args.inode); return ret; } @@ -9720,10 +9758,13 @@ static int btrfs_symlink(struct user_namespace *mnt_userns, struct inode *dir, struct btrfs_root *root = BTRFS_I(dir)->root; struct btrfs_path *path; struct btrfs_key key; - struct inode *inode = NULL; + struct inode *inode; + struct btrfs_new_inode_args new_inode_args = { + .dir = dir, + .dentry = dentry, + }; + unsigned int trans_num_items; int err; - u64 objectid; - u64 index = 0; int name_len; int datasize; unsigned long ptr; @@ -9734,49 +9775,40 @@ static int btrfs_symlink(struct user_namespace *mnt_userns, struct inode *dir, if (name_len > BTRFS_MAX_INLINE_DATA_SIZE(fs_info)) return -ENAMETOOLONG; - /* - * 2 items for inode item and ref - * 2 items for dir items - * 1 item for updating parent inode item - * 1 item for the inline extent item - * 1 item for xattr if selinux is on - */ - trans = btrfs_start_transaction(root, 7); - if (IS_ERR(trans)) - return PTR_ERR(trans); + inode = new_inode(dir->i_sb); + if (!inode) + return -ENOMEM; + inode_init_owner(mnt_userns, inode, dir, S_IFLNK | S_IRWXUGO); + inode->i_op = &btrfs_symlink_inode_operations; + inode_nohighmem(inode); + inode->i_mapping->a_ops = &btrfs_aops; + btrfs_i_size_write(BTRFS_I(inode), name_len); + inode_set_bytes(inode, name_len); - err = btrfs_get_free_objectid(root, &objectid); + new_inode_args.inode = inode; + err = btrfs_new_inode_prepare(&new_inode_args, &trans_num_items); if (err) - goto out_unlock; + goto out_inode; + /* 1 additional item for the inline extent */ + trans_num_items++; - inode = btrfs_new_inode(trans, root, mnt_userns, dir, - dentry->d_name.name, dentry->d_name.len, - btrfs_ino(BTRFS_I(dir)), objectid, - S_IFLNK | S_IRWXUGO, &index); - if (IS_ERR(inode)) { - err = PTR_ERR(inode); - inode = NULL; - goto out_unlock; + trans = btrfs_start_transaction(root, trans_num_items); + if (IS_ERR(trans)) { + err = PTR_ERR(trans); + goto out_new_inode_args; } - /* - * If the active LSM wants to access the inode during - * d_instantiate it needs these. Smack checks to see - * if the filesystem supports xattrs by looking at the - * ops vector. - */ - inode->i_fop = &btrfs_file_operations; - inode->i_op = &btrfs_file_inode_operations; - inode->i_mapping->a_ops = &btrfs_aops; - - err = btrfs_init_inode_security(trans, inode, dir, &dentry->d_name); + err = btrfs_create_new_inode(trans, &new_inode_args); if (err) - goto out_unlock; + goto out; path = btrfs_alloc_path(); if (!path) { err = -ENOMEM; - goto out_unlock; + btrfs_abort_transaction(trans, err); + discard_new_inode(inode); + inode = NULL; + goto out; } key.objectid = btrfs_ino(BTRFS_I(inode)); key.offset = 0; @@ -9785,8 +9817,11 @@ static int btrfs_symlink(struct user_namespace *mnt_userns, struct inode *dir, err = btrfs_insert_empty_item(trans, root, path, &key, datasize); if (err) { + btrfs_abort_transaction(trans, err); btrfs_free_path(path); - goto out_unlock; + discard_new_inode(inode); + inode = NULL; + goto out; } leaf = path->nodes[0]; ei = btrfs_item_ptr(leaf, path->slots[0], @@ -9804,31 +9839,16 @@ static int btrfs_symlink(struct user_namespace *mnt_userns, struct inode *dir, btrfs_mark_buffer_dirty(leaf); btrfs_free_path(path); - inode->i_op = &btrfs_symlink_inode_operations; - inode_nohighmem(inode); - inode_set_bytes(inode, name_len); - btrfs_i_size_write(BTRFS_I(inode), name_len); - err = btrfs_update_inode(trans, root, BTRFS_I(inode)); - /* - * Last step, add directory indexes for our symlink inode. This is the - * last step to avoid extra cleanup of these indexes if an error happens - * elsewhere above. - */ - if (!err) - err = btrfs_add_nondir(trans, BTRFS_I(dir), dentry, - BTRFS_I(inode), 0, index); - if (err) - goto out_unlock; - d_instantiate_new(dentry, inode); - -out_unlock: + err = 0; +out: btrfs_end_transaction(trans); - if (err && inode) { - inode_dec_link_count(inode); - discard_new_inode(inode); - } btrfs_btree_balance_dirty(fs_info); +out_new_inode_args: + btrfs_new_inode_args_destroy(&new_inode_args); +out_inode: + if (err) + iput(inode); return err; } @@ -10079,62 +10099,58 @@ static int btrfs_tmpfile(struct user_namespace *mnt_userns, struct inode *dir, struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb); struct btrfs_trans_handle *trans; struct btrfs_root *root = BTRFS_I(dir)->root; - struct inode *inode = NULL; - u64 objectid; - u64 index; - int ret = 0; - - /* - * 5 units required for adding orphan entry - */ - trans = btrfs_start_transaction(root, 5); - if (IS_ERR(trans)) - return PTR_ERR(trans); - - ret = btrfs_get_free_objectid(root, &objectid); - if (ret) - goto out; - - inode = btrfs_new_inode(trans, root, mnt_userns, dir, NULL, 0, - btrfs_ino(BTRFS_I(dir)), objectid, mode, &index); - if (IS_ERR(inode)) { - ret = PTR_ERR(inode); - inode = NULL; - goto out; - } + struct inode *inode; + struct btrfs_new_inode_args new_inode_args = { + .dir = dir, + .dentry = dentry, + .orphan = true, + }; + unsigned int trans_num_items; + int ret; + inode = new_inode(dir->i_sb); + if (!inode) + return -ENOMEM; + inode_init_owner(mnt_userns, inode, dir, mode); inode->i_fop = &btrfs_file_operations; inode->i_op = &btrfs_file_inode_operations; - inode->i_mapping->a_ops = &btrfs_aops; - ret = btrfs_init_inode_security(trans, inode, dir, NULL); + new_inode_args.inode = inode; + ret = btrfs_new_inode_prepare(&new_inode_args, &trans_num_items); if (ret) - goto out; + goto out_inode; - ret = btrfs_update_inode(trans, root, BTRFS_I(inode)); - if (ret) - goto out; - ret = btrfs_orphan_add(trans, BTRFS_I(inode)); - if (ret) - goto out; + trans = btrfs_start_transaction(root, trans_num_items); + if (IS_ERR(trans)) { + ret = PTR_ERR(trans); + goto out_new_inode_args; + } + + ret = btrfs_create_new_inode(trans, &new_inode_args); /* - * We set number of links to 0 in btrfs_new_inode(), and here we set - * it to 1 because d_tmpfile() will issue a warning if the count is 0, - * through: + * We set number of links to 0 in btrfs_create_new_inode(), and here we + * set it to 1 because d_tmpfile() will issue a warning if the count is + * 0, through: * * d_tmpfile() -> inode_dec_link_count() -> drop_nlink() */ set_nlink(inode, 1); - d_tmpfile(dentry, inode); - unlock_new_inode(inode); - mark_inode_dirty(inode); -out: + + if (!ret) { + d_tmpfile(dentry, inode); + unlock_new_inode(inode); + mark_inode_dirty(inode); + } + btrfs_end_transaction(trans); - if (ret && inode) - discard_new_inode(inode); btrfs_btree_balance_dirty(fs_info); +out_new_inode_args: + btrfs_new_inode_args_destroy(&new_inode_args); +out_inode: + if (ret) + iput(inode); return ret; } @@ -10466,13 +10482,11 @@ static ssize_t btrfs_encoded_read_regular(struct kiocb *iocb, pages = kcalloc(nr_pages, sizeof(struct page *), GFP_NOFS); if (!pages) return -ENOMEM; - for (i = 0; i < nr_pages; i++) { - pages[i] = alloc_page(GFP_NOFS); - if (!pages[i]) { - ret = -ENOMEM; - goto out; + ret = btrfs_alloc_page_array(nr_pages, pages); + if (ret) { + ret = -ENOMEM; + goto out; } - } ret = btrfs_encoded_read_regular_fill_pages(inode, start, disk_bytenr, disk_io_size, pages); @@ -10808,7 +10822,8 @@ ssize_t btrfs_do_encoded_write(struct kiocb *iocb, struct iov_iter *from, ret = btrfs_qgroup_reserve_data(inode, &data_reserved, start, num_bytes); if (ret) goto out_free_data_space; - ret = btrfs_delalloc_reserve_metadata(inode, num_bytes, disk_num_bytes); + ret = btrfs_delalloc_reserve_metadata(inode, num_bytes, disk_num_bytes, + false); if (ret) goto out_qgroup_free_data; @@ -11107,8 +11122,23 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, * set. We use this counter to prevent snapshots. We must increment it * before walking the extents because we don't want a concurrent * snapshot to run after we've already checked the extents. + * + * It is possible that subvolume is marked for deletion but still not + * removed yet. To prevent this race, we check the root status before + * activating the swapfile. */ + spin_lock(&root->root_item_lock); + if (btrfs_root_dead(root)) { + spin_unlock(&root->root_item_lock); + + btrfs_exclop_finish(fs_info); + btrfs_warn(fs_info, + "cannot activate swapfile because subvolume %llu is being deleted", + root->root_key.objectid); + return -EPERM; + } atomic_inc(&root->nr_swapfiles); + spin_unlock(&root->root_item_lock); isize = ALIGN_DOWN(inode->i_size, fs_info->sectorsize); @@ -11302,6 +11332,41 @@ void btrfs_update_inode_bytes(struct btrfs_inode *inode, spin_unlock(&inode->lock); } +/** + * Verify that there are no ordered extents for a given file range. + * + * @inode: The target inode. + * @start: Start offset of the file range, should be sector size aligned. + * @end: End offset (inclusive) of the file range, its value +1 should be + * sector size aligned. + * + * This should typically be used for cases where we locked an inode's VFS lock in + * exclusive mode, we have also locked the inode's i_mmap_lock in exclusive mode, + * we have flushed all delalloc in the range, we have waited for all ordered + * extents in the range to complete and finally we have locked the file range in + * the inode's io_tree. + */ +void btrfs_assert_inode_range_clean(struct btrfs_inode *inode, u64 start, u64 end) +{ + struct btrfs_root *root = inode->root; + struct btrfs_ordered_extent *ordered; + + if (!IS_ENABLED(CONFIG_BTRFS_ASSERT)) + return; + + ordered = btrfs_lookup_first_ordered_range(inode, start, end + 1 - start); + if (ordered) { + btrfs_err(root->fs_info, +"found unexpected ordered extent in file range [%llu, %llu] for inode %llu root %llu (ordered range [%llu, %llu])", + start, end, btrfs_ino(inode), root->root_key.objectid, + ordered->file_offset, + ordered->file_offset + ordered->num_bytes - 1); + btrfs_put_ordered_extent(ordered); + } + + ASSERT(ordered == NULL); +} + static const struct inode_operations btrfs_dir_inode_operations = { .getattr = btrfs_getattr, .lookup = btrfs_lookup, @@ -11350,13 +11415,13 @@ static const struct file_operations btrfs_dir_file_operations = { * For now we're avoiding this by dropping bmap. */ static const struct address_space_operations btrfs_aops = { - .readpage = btrfs_readpage, + .read_folio = btrfs_read_folio, .writepage = btrfs_writepage, .writepages = btrfs_writepages, .readahead = btrfs_readahead, .direct_IO = noop_direct_IO, .invalidate_folio = btrfs_invalidate_folio, - .releasepage = btrfs_releasepage, + .release_folio = btrfs_release_folio, #ifdef CONFIG_MIGRATION .migratepage = btrfs_migratepage, #endif diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 238cee5b5254..0f79af919bc4 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -468,7 +468,6 @@ static noinline int btrfs_ioctl_fitrim(struct btrfs_fs_info *fs_info, void __user *arg) { struct btrfs_device *device; - struct request_queue *q; struct fstrim_range range; u64 minlen = ULLONG_MAX; u64 num_devices = 0; @@ -498,14 +497,11 @@ static noinline int btrfs_ioctl_fitrim(struct btrfs_fs_info *fs_info, rcu_read_lock(); list_for_each_entry_rcu(device, &fs_info->fs_devices->devices, dev_list) { - if (!device->bdev) + if (!device->bdev || !bdev_max_discard_sectors(device->bdev)) continue; - q = bdev_get_queue(device->bdev); - if (blk_queue_discard(q)) { - num_devices++; - minlen = min_t(u64, q->limits.discard_granularity, - minlen); - } + num_devices++; + minlen = min_t(u64, bdev_discard_granularity(device->bdev), + minlen); } rcu_read_unlock(); @@ -544,9 +540,35 @@ int __pure btrfs_is_empty_uuid(u8 *uuid) return 1; } +/* + * Calculate the number of transaction items to reserve for creating a subvolume + * or snapshot, not including the inode, directory entries, or parent directory. + */ +static unsigned int create_subvol_num_items(struct btrfs_qgroup_inherit *inherit) +{ + /* + * 1 to add root block + * 1 to add root item + * 1 to add root ref + * 1 to add root backref + * 1 to add UUID item + * 1 to add qgroup info + * 1 to add qgroup limit + * + * Ideally the last two would only be accounted if qgroups are enabled, + * but that can change between now and the time we would insert them. + */ + unsigned int num_items = 7; + + if (inherit) { + /* 2 to add qgroup relations for each inherited qgroup */ + num_items += 2 * inherit->num_qgroups; + } + return num_items; +} + static noinline int create_subvol(struct user_namespace *mnt_userns, struct inode *dir, struct dentry *dentry, - const char *name, int namelen, struct btrfs_qgroup_inherit *inherit) { struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb); @@ -559,11 +581,15 @@ static noinline int create_subvol(struct user_namespace *mnt_userns, struct btrfs_root *new_root; struct btrfs_block_rsv block_rsv; struct timespec64 cur_time = current_time(dir); - struct inode *inode; + struct btrfs_new_inode_args new_inode_args = { + .dir = dir, + .dentry = dentry, + .subvol = true, + }; + unsigned int trans_num_items; int ret; - dev_t anon_dev = 0; + dev_t anon_dev; u64 objectid; - u64 index = 0; root_item = kzalloc(sizeof(*root_item), GFP_KERNEL); if (!root_item) @@ -571,11 +597,7 @@ static noinline int create_subvol(struct user_namespace *mnt_userns, ret = btrfs_get_free_objectid(fs_info->tree_root, &objectid); if (ret) - goto fail_free; - - ret = get_anon_bdev(&anon_dev); - if (ret < 0) - goto fail_free; + goto out_root_item; /* * Don't create subvolume whose level is not zero. Or qgroup will be @@ -583,36 +605,47 @@ static noinline int create_subvol(struct user_namespace *mnt_userns, */ if (btrfs_qgroup_level(objectid)) { ret = -ENOSPC; - goto fail_free; + goto out_root_item; + } + + ret = get_anon_bdev(&anon_dev); + if (ret < 0) + goto out_root_item; + + new_inode_args.inode = btrfs_new_subvol_inode(mnt_userns, dir); + if (!new_inode_args.inode) { + ret = -ENOMEM; + goto out_anon_dev; } + ret = btrfs_new_inode_prepare(&new_inode_args, &trans_num_items); + if (ret) + goto out_inode; + trans_num_items += create_subvol_num_items(inherit); btrfs_init_block_rsv(&block_rsv, BTRFS_BLOCK_RSV_TEMP); - /* - * The same as the snapshot creation, please see the comment - * of create_snapshot(). - */ - ret = btrfs_subvolume_reserve_metadata(root, &block_rsv, 8, false); + ret = btrfs_subvolume_reserve_metadata(root, &block_rsv, + trans_num_items, false); if (ret) - goto fail_free; + goto out_new_inode_args; trans = btrfs_start_transaction(root, 0); if (IS_ERR(trans)) { ret = PTR_ERR(trans); btrfs_subvolume_release_metadata(root, &block_rsv); - goto fail_free; + goto out_new_inode_args; } trans->block_rsv = &block_rsv; trans->bytes_reserved = block_rsv.size; ret = btrfs_qgroup_inherit(trans, 0, objectid, inherit); if (ret) - goto fail; + goto out; leaf = btrfs_alloc_tree_block(trans, root, 0, objectid, NULL, 0, 0, 0, BTRFS_NESTING_NORMAL); if (IS_ERR(leaf)) { ret = PTR_ERR(leaf); - goto fail; + goto out; } btrfs_mark_buffer_dirty(leaf); @@ -667,75 +700,46 @@ static noinline int create_subvol(struct user_namespace *mnt_userns, btrfs_tree_unlock(leaf); btrfs_free_tree_block(trans, objectid, leaf, 0, 1); free_extent_buffer(leaf); - goto fail; + goto out; } free_extent_buffer(leaf); leaf = NULL; - key.offset = (u64)-1; new_root = btrfs_get_new_fs_root(fs_info, objectid, anon_dev); if (IS_ERR(new_root)) { - free_anon_bdev(anon_dev); ret = PTR_ERR(new_root); btrfs_abort_transaction(trans, ret); - goto fail; + goto out; } - /* Freeing will be done in btrfs_put_root() of new_root */ + /* anon_dev is owned by new_root now. */ anon_dev = 0; + BTRFS_I(new_inode_args.inode)->root = new_root; + /* ... and new_root is owned by new_inode_args.inode now. */ ret = btrfs_record_root_in_trans(trans, new_root); if (ret) { - btrfs_put_root(new_root); - btrfs_abort_transaction(trans, ret); - goto fail; - } - - ret = btrfs_create_subvol_root(trans, new_root, root, mnt_userns); - btrfs_put_root(new_root); - if (ret) { - /* We potentially lose an unused inode item here */ - btrfs_abort_transaction(trans, ret); - goto fail; - } - - /* - * insert the directory item - */ - ret = btrfs_set_inode_index(BTRFS_I(dir), &index); - if (ret) { - btrfs_abort_transaction(trans, ret); - goto fail; - } - - ret = btrfs_insert_dir_item(trans, name, namelen, BTRFS_I(dir), &key, - BTRFS_FT_DIR, index); - if (ret) { btrfs_abort_transaction(trans, ret); - goto fail; + goto out; } - btrfs_i_size_write(BTRFS_I(dir), dir->i_size + namelen * 2); - ret = btrfs_update_inode(trans, root, BTRFS_I(dir)); + ret = btrfs_uuid_tree_add(trans, root_item->uuid, + BTRFS_UUID_KEY_SUBVOL, objectid); if (ret) { btrfs_abort_transaction(trans, ret); - goto fail; + goto out; } - ret = btrfs_add_root_ref(trans, objectid, root->root_key.objectid, - btrfs_ino(BTRFS_I(dir)), index, name, namelen); + ret = btrfs_create_new_inode(trans, &new_inode_args); if (ret) { btrfs_abort_transaction(trans, ret); - goto fail; + goto out; } - ret = btrfs_uuid_tree_add(trans, root_item->uuid, - BTRFS_UUID_KEY_SUBVOL, objectid); - if (ret) - btrfs_abort_transaction(trans, ret); + d_instantiate_new(dentry, new_inode_args.inode); + new_inode_args.inode = NULL; -fail: - kfree(root_item); +out: trans->block_rsv = NULL; trans->bytes_reserved = 0; btrfs_subvolume_release_metadata(root, &block_rsv); @@ -744,18 +748,14 @@ fail: btrfs_end_transaction(trans); else ret = btrfs_commit_transaction(trans); - - if (!ret) { - inode = btrfs_lookup_dentry(dir, dentry); - if (IS_ERR(inode)) - return PTR_ERR(inode); - d_instantiate(dentry, inode); - } - return ret; - -fail_free: +out_new_inode_args: + btrfs_new_inode_args_destroy(&new_inode_args); +out_inode: + iput(new_inode_args.inode); +out_anon_dev: if (anon_dev) free_anon_bdev(anon_dev); +out_root_item: kfree(root_item); return ret; } @@ -767,6 +767,7 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir, struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb); struct inode *inode; struct btrfs_pending_snapshot *pending_snapshot; + unsigned int trans_num_items; struct btrfs_trans_handle *trans; int ret; @@ -804,16 +805,14 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir, btrfs_init_block_rsv(&pending_snapshot->block_rsv, BTRFS_BLOCK_RSV_TEMP); /* - * 1 - parent dir inode - * 2 - dir entries - * 1 - root item - * 2 - root ref/backref - * 1 - root of snapshot - * 1 - UUID item + * 1 to add dir item + * 1 to add dir index + * 1 to update parent inode item */ + trans_num_items = create_subvol_num_items(inherit) + 3; ret = btrfs_subvolume_reserve_metadata(BTRFS_I(dir)->root, - &pending_snapshot->block_rsv, 8, - false); + &pending_snapshot->block_rsv, + trans_num_items, false); if (ret) goto free_pending; @@ -983,7 +982,7 @@ static noinline int btrfs_mksubvol(const struct path *parent, if (snap_src) error = create_snapshot(snap_src, dir, dentry, readonly, inherit); else - error = create_subvol(mnt_userns, dir, dentry, name, namelen, inherit); + error = create_subvol(mnt_userns, dir, dentry, inherit); if (!error) fsnotify_mkdir(dir, dentry); @@ -1239,7 +1238,7 @@ static u32 get_extent_max_capacity(const struct extent_map *em) } static bool defrag_check_next_extent(struct inode *inode, struct extent_map *em, - bool locked) + u32 extent_thresh, u64 newer_than, bool locked) { struct extent_map *next; bool ret = false; @@ -1249,11 +1248,12 @@ static bool defrag_check_next_extent(struct inode *inode, struct extent_map *em, return false; /* - * We want to check if the next extent can be merged with the current - * one, which can be an extent created in a past generation, so we pass - * a minimum generation of 0 to defrag_lookup_extent(). + * Here we need to pass @newer_then when checking the next extent, or + * we will hit a case we mark current extent for defrag, but the next + * one will not be a target. + * This will just cause extra IO without really reducing the fragments. */ - next = defrag_lookup_extent(inode, em->start + em->len, 0, locked); + next = defrag_lookup_extent(inode, em->start + em->len, newer_than, locked); /* No more em or hole */ if (!next || next->block_start >= EXTENT_MAP_LAST_BYTE) goto out; @@ -1265,6 +1265,13 @@ static bool defrag_check_next_extent(struct inode *inode, struct extent_map *em, */ if (next->len >= get_extent_max_capacity(em)) goto out; + /* Skip older extent */ + if (next->generation < newer_than) + goto out; + /* Also check extent size */ + if (next->len >= extent_thresh) + goto out; + ret = true; out: free_extent_map(next); @@ -1351,7 +1358,7 @@ again: * make it uptodate. */ if (!PageUptodate(page)) { - btrfs_readpage(NULL, page); + btrfs_read_folio(NULL, page_folio(page)); lock_page(page); if (page->mapping != mapping || !PagePrivate(page)) { unlock_page(page); @@ -1409,8 +1416,19 @@ static int defrag_collect_targets(struct btrfs_inode *inode, if (!em) break; - /* Skip hole/inline/preallocated extents */ - if (em->block_start >= EXTENT_MAP_LAST_BYTE || + /* + * If the file extent is an inlined one, we may still want to + * defrag it (fallthrough) if it will cause a regular extent. + * This is for users who want to convert inline extents to + * regular ones through max_inline= mount option. + */ + if (em->block_start == EXTENT_MAP_INLINE && + em->len <= inode->root->fs_info->max_inline) + goto next; + + /* Skip hole/delalloc/preallocated extents */ + if (em->block_start == EXTENT_MAP_HOLE || + em->block_start == EXTENT_MAP_DELALLOC || test_bit(EXTENT_FLAG_PREALLOC, &em->flags)) goto next; @@ -1469,8 +1487,17 @@ static int defrag_collect_targets(struct btrfs_inode *inode, if (em->len >= get_extent_max_capacity(em)) goto next; + /* + * Normally there are no more extents after an inline one, thus + * @next_mergeable will normally be false and not defragged. + * So if an inline extent passed all above checks, just add it + * for defrag, and be converted to regular extents. + */ + if (em->block_start == EXTENT_MAP_INLINE) + goto add; + next_mergeable = defrag_check_next_extent(&inode->vfs_inode, em, - locked); + extent_thresh, newer_than, locked); if (!next_mergeable) { struct defrag_target_range *last; @@ -2557,7 +2584,12 @@ static noinline int search_ioctl(struct inode *inode, while (1) { ret = -EFAULT; - if (fault_in_writeable(ubuf + sk_offset, *buf_size - sk_offset)) + /* + * Ensure that the whole user buffer is faulted in at sub-page + * granularity, otherwise the loop may live-lock. + */ + if (fault_in_subpage_writeable(ubuf + sk_offset, + *buf_size - sk_offset)) break; ret = btrfs_search_forward(root, &key, path, sk->min_transid); @@ -2585,7 +2617,7 @@ err: static noinline int btrfs_ioctl_tree_search(struct inode *inode, void __user *argp) { - struct btrfs_ioctl_search_args __user *uargs; + struct btrfs_ioctl_search_args __user *uargs = argp; struct btrfs_ioctl_search_key sk; int ret; size_t buf_size; @@ -2593,8 +2625,6 @@ static noinline int btrfs_ioctl_tree_search(struct inode *inode, if (!capable(CAP_SYS_ADMIN)) return -EPERM; - uargs = (struct btrfs_ioctl_search_args __user *)argp; - if (copy_from_user(&sk, &uargs->key, sizeof(sk))) return -EFAULT; @@ -2617,7 +2647,7 @@ static noinline int btrfs_ioctl_tree_search(struct inode *inode, static noinline int btrfs_ioctl_tree_search_v2(struct inode *inode, void __user *argp) { - struct btrfs_ioctl_search_args_v2 __user *uarg; + struct btrfs_ioctl_search_args_v2 __user *uarg = argp; struct btrfs_ioctl_search_args_v2 args; int ret; size_t buf_size; @@ -2627,7 +2657,6 @@ static noinline int btrfs_ioctl_tree_search_v2(struct inode *inode, return -EPERM; /* copy search header and buffer size */ - uarg = (struct btrfs_ioctl_search_args_v2 __user *)argp; if (copy_from_user(&args, uarg, sizeof(args))) return -EFAULT; @@ -4335,10 +4364,6 @@ static long btrfs_ioctl_balance(struct file *file, void __user *arg) bool need_unlock; /* for mut. excl. ops lock */ int ret; - if (!arg) - btrfs_warn(fs_info, - "IOC_BALANCE ioctl (v1) is deprecated and will be removed in kernel 5.18"); - if (!capable(CAP_SYS_ADMIN)) return -EPERM; @@ -4346,6 +4371,13 @@ static long btrfs_ioctl_balance(struct file *file, void __user *arg) if (ret) return ret; + bargs = memdup_user(arg, sizeof(*bargs)); + if (IS_ERR(bargs)) { + ret = PTR_ERR(bargs); + bargs = NULL; + goto out; + } + again: if (btrfs_exclop_start(fs_info, BTRFS_EXCLOP_BALANCE)) { mutex_lock(&fs_info->balance_mutex); @@ -4393,59 +4425,42 @@ again: } locked: - - if (arg) { - bargs = memdup_user(arg, sizeof(*bargs)); - if (IS_ERR(bargs)) { - ret = PTR_ERR(bargs); + if (bargs->flags & BTRFS_BALANCE_RESUME) { + if (!fs_info->balance_ctl) { + ret = -ENOTCONN; goto out_unlock; } - if (bargs->flags & BTRFS_BALANCE_RESUME) { - if (!fs_info->balance_ctl) { - ret = -ENOTCONN; - goto out_bargs; - } + bctl = fs_info->balance_ctl; + spin_lock(&fs_info->balance_lock); + bctl->flags |= BTRFS_BALANCE_RESUME; + spin_unlock(&fs_info->balance_lock); + btrfs_exclop_balance(fs_info, BTRFS_EXCLOP_BALANCE); - bctl = fs_info->balance_ctl; - spin_lock(&fs_info->balance_lock); - bctl->flags |= BTRFS_BALANCE_RESUME; - spin_unlock(&fs_info->balance_lock); - btrfs_exclop_balance(fs_info, BTRFS_EXCLOP_BALANCE); + goto do_balance; + } - goto do_balance; - } - } else { - bargs = NULL; + if (bargs->flags & ~(BTRFS_BALANCE_ARGS_MASK | BTRFS_BALANCE_TYPE_MASK)) { + ret = -EINVAL; + goto out_unlock; } if (fs_info->balance_ctl) { ret = -EINPROGRESS; - goto out_bargs; + goto out_unlock; } bctl = kzalloc(sizeof(*bctl), GFP_KERNEL); if (!bctl) { ret = -ENOMEM; - goto out_bargs; - } - - if (arg) { - memcpy(&bctl->data, &bargs->data, sizeof(bctl->data)); - memcpy(&bctl->meta, &bargs->meta, sizeof(bctl->meta)); - memcpy(&bctl->sys, &bargs->sys, sizeof(bctl->sys)); - - bctl->flags = bargs->flags; - } else { - /* balance everything - no filters */ - bctl->flags |= BTRFS_BALANCE_TYPE_MASK; + goto out_unlock; } - if (bctl->flags & ~(BTRFS_BALANCE_ARGS_MASK | BTRFS_BALANCE_TYPE_MASK)) { - ret = -EINVAL; - goto out_bctl; - } + memcpy(&bctl->data, &bargs->data, sizeof(bctl->data)); + memcpy(&bctl->meta, &bargs->meta, sizeof(bctl->meta)); + memcpy(&bctl->sys, &bargs->sys, sizeof(bctl->sys)); + bctl->flags = bargs->flags; do_balance: /* * Ownership of bctl and exclusive operation goes to btrfs_balance. @@ -4458,21 +4473,19 @@ do_balance: ret = btrfs_balance(fs_info, bctl, bargs); bctl = NULL; - if ((ret == 0 || ret == -ECANCELED) && arg) { + if (ret == 0 || ret == -ECANCELED) { if (copy_to_user(arg, bargs, sizeof(*bargs))) ret = -EFAULT; } -out_bctl: kfree(bctl); -out_bargs: - kfree(bargs); out_unlock: mutex_unlock(&fs_info->balance_mutex); if (need_unlock) btrfs_exclop_finish(fs_info); out: mnt_drop_write_file(file); + kfree(bargs); return ret; } @@ -5448,8 +5461,6 @@ long btrfs_ioctl(struct file *file, unsigned int return btrfs_ioctl_fs_info(fs_info, argp); case BTRFS_IOC_DEV_INFO: return btrfs_ioctl_dev_info(fs_info, argp); - case BTRFS_IOC_BALANCE: - return btrfs_ioctl_balance(file, NULL); case BTRFS_IOC_TREE_SEARCH: return btrfs_ioctl_tree_search(inode, argp); case BTRFS_IOC_TREE_SEARCH_V2: diff --git a/fs/btrfs/props.c b/fs/btrfs/props.c index 1a6d2d5b4b33..a2ec8ecae8de 100644 --- a/fs/btrfs/props.c +++ b/fs/btrfs/props.c @@ -17,9 +17,11 @@ static DEFINE_HASHTABLE(prop_handlers_ht, BTRFS_PROP_HANDLERS_HT_BITS); struct prop_handler { struct hlist_node node; const char *xattr_name; - int (*validate)(const char *value, size_t len); + int (*validate)(const struct btrfs_inode *inode, const char *value, + size_t len); int (*apply)(struct inode *inode, const char *value, size_t len); const char *(*extract)(struct inode *inode); + bool (*ignore)(const struct btrfs_inode *inode); int inheritable; }; @@ -55,7 +57,8 @@ find_prop_handler(const char *name, return NULL; } -int btrfs_validate_prop(const char *name, const char *value, size_t value_len) +int btrfs_validate_prop(const struct btrfs_inode *inode, const char *name, + const char *value, size_t value_len) { const struct prop_handler *handler; @@ -69,7 +72,29 @@ int btrfs_validate_prop(const char *name, const char *value, size_t value_len) if (value_len == 0) return 0; - return handler->validate(value, value_len); + return handler->validate(inode, value, value_len); +} + +/* + * Check if a property should be ignored (not set) for an inode. + * + * @inode: The target inode. + * @name: The property's name. + * + * The caller must be sure the given property name is valid, for example by + * having previously called btrfs_validate_prop(). + * + * Returns: true if the property should be ignored for the given inode + * false if the property must not be ignored for the given inode + */ +bool btrfs_ignore_prop(const struct btrfs_inode *inode, const char *name) +{ + const struct prop_handler *handler; + + handler = find_prop_handler(name, NULL); + ASSERT(handler != NULL); + + return handler->ignore(inode); } int btrfs_set_prop(struct btrfs_trans_handle *trans, struct inode *inode, @@ -252,8 +277,12 @@ int btrfs_load_inode_props(struct inode *inode, struct btrfs_path *path) return ret; } -static int prop_compression_validate(const char *value, size_t len) +static int prop_compression_validate(const struct btrfs_inode *inode, + const char *value, size_t len) { + if (!btrfs_inode_can_compress(inode)) + return -EINVAL; + if (!value) return 0; @@ -310,6 +339,22 @@ static int prop_compression_apply(struct inode *inode, const char *value, return 0; } +static bool prop_compression_ignore(const struct btrfs_inode *inode) +{ + /* + * Compression only has effect for regular files, and for directories + * we set it just to propagate it to new files created inside them. + * Everything else (symlinks, devices, sockets, fifos) is pointless as + * it will do nothing, so don't waste metadata space on a compression + * xattr for anything that is neither a file nor a directory. + */ + if (!S_ISREG(inode->vfs_inode.i_mode) && + !S_ISDIR(inode->vfs_inode.i_mode)) + return true; + + return false; +} + static const char *prop_compression_extract(struct inode *inode) { switch (BTRFS_I(inode)->prop_compress) { @@ -330,13 +375,13 @@ static struct prop_handler prop_handlers[] = { .validate = prop_compression_validate, .apply = prop_compression_apply, .extract = prop_compression_extract, + .ignore = prop_compression_ignore, .inheritable = 1 }, }; -static int inherit_props(struct btrfs_trans_handle *trans, - struct inode *inode, - struct inode *parent) +int btrfs_inode_inherit_props(struct btrfs_trans_handle *trans, + struct inode *inode, struct inode *parent) { struct btrfs_root *root = BTRFS_I(inode)->root; struct btrfs_fs_info *fs_info = root->fs_info; @@ -356,6 +401,9 @@ static int inherit_props(struct btrfs_trans_handle *trans, if (!h->inheritable) continue; + if (h->ignore(BTRFS_I(inode))) + continue; + value = h->extract(parent); if (!value) continue; @@ -364,7 +412,7 @@ static int inherit_props(struct btrfs_trans_handle *trans, * This is not strictly necessary as the property should be * valid, but in case it isn't, don't propagate it further. */ - ret = h->validate(value, strlen(value)); + ret = h->validate(BTRFS_I(inode), value, strlen(value)); if (ret) continue; @@ -408,41 +456,6 @@ static int inherit_props(struct btrfs_trans_handle *trans, return 0; } -int btrfs_inode_inherit_props(struct btrfs_trans_handle *trans, - struct inode *inode, - struct inode *dir) -{ - if (!dir) - return 0; - - return inherit_props(trans, inode, dir); -} - -int btrfs_subvol_inherit_props(struct btrfs_trans_handle *trans, - struct btrfs_root *root, - struct btrfs_root *parent_root) -{ - struct super_block *sb = root->fs_info->sb; - struct inode *parent_inode, *child_inode; - int ret; - - parent_inode = btrfs_iget(sb, BTRFS_FIRST_FREE_OBJECTID, parent_root); - if (IS_ERR(parent_inode)) - return PTR_ERR(parent_inode); - - child_inode = btrfs_iget(sb, BTRFS_FIRST_FREE_OBJECTID, root); - if (IS_ERR(child_inode)) { - iput(parent_inode); - return PTR_ERR(child_inode); - } - - ret = inherit_props(trans, child_inode, parent_inode); - iput(child_inode); - iput(parent_inode); - - return ret; -} - void __init btrfs_props_init(void) { int i; diff --git a/fs/btrfs/props.h b/fs/btrfs/props.h index 40b2c65b518c..ca9dd3df129b 100644 --- a/fs/btrfs/props.h +++ b/fs/btrfs/props.h @@ -13,7 +13,9 @@ void __init btrfs_props_init(void); int btrfs_set_prop(struct btrfs_trans_handle *trans, struct inode *inode, const char *name, const char *value, size_t value_len, int flags); -int btrfs_validate_prop(const char *name, const char *value, size_t value_len); +int btrfs_validate_prop(const struct btrfs_inode *inode, const char *name, + const char *value, size_t value_len); +bool btrfs_ignore_prop(const struct btrfs_inode *inode, const char *name); int btrfs_load_inode_props(struct inode *inode, struct btrfs_path *path); @@ -21,8 +23,4 @@ int btrfs_inode_inherit_props(struct btrfs_trans_handle *trans, struct inode *inode, struct inode *dir); -int btrfs_subvol_inherit_props(struct btrfs_trans_handle *trans, - struct btrfs_root *root, - struct btrfs_root *parent_root); - #endif diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 1866b1f0da01..db723c0026bd 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -2290,7 +2290,7 @@ int btrfs_qgroup_trace_subtree(struct btrfs_trans_handle *trans, return 0; if (!extent_buffer_uptodate(root_eb)) { - ret = btrfs_read_buffer(root_eb, root_gen, root_level, NULL); + ret = btrfs_read_extent_buffer(root_eb, root_gen, root_level, NULL); if (ret) goto out; } @@ -3939,12 +3939,13 @@ int btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes, } int __btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes, - enum btrfs_qgroup_rsv_type type, bool enforce) + enum btrfs_qgroup_rsv_type type, bool enforce, + bool noflush) { int ret; ret = btrfs_qgroup_reserve_meta(root, num_bytes, type, enforce); - if (ret <= 0 && ret != -EDQUOT) + if ((ret <= 0 && ret != -EDQUOT) || noflush) return ret; ret = try_flush_qgroup(root); diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h index 880e9df0dac1..0c4dd2a9af96 100644 --- a/fs/btrfs/qgroup.h +++ b/fs/btrfs/qgroup.h @@ -364,19 +364,23 @@ int btrfs_qgroup_free_data(struct btrfs_inode *inode, int btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes, enum btrfs_qgroup_rsv_type type, bool enforce); int __btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes, - enum btrfs_qgroup_rsv_type type, bool enforce); + enum btrfs_qgroup_rsv_type type, bool enforce, + bool noflush); /* Reserve metadata space for pertrans and prealloc type */ static inline int btrfs_qgroup_reserve_meta_pertrans(struct btrfs_root *root, int num_bytes, bool enforce) { return __btrfs_qgroup_reserve_meta(root, num_bytes, - BTRFS_QGROUP_RSV_META_PERTRANS, enforce); + BTRFS_QGROUP_RSV_META_PERTRANS, + enforce, false); } static inline int btrfs_qgroup_reserve_meta_prealloc(struct btrfs_root *root, - int num_bytes, bool enforce) + int num_bytes, bool enforce, + bool noflush) { return __btrfs_qgroup_reserve_meta(root, num_bytes, - BTRFS_QGROUP_RSV_META_PREALLOC, enforce); + BTRFS_QGROUP_RSV_META_PREALLOC, + enforce, noflush); } void __btrfs_qgroup_free_meta(struct btrfs_root *root, int num_bytes, diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c index 0e239a4c3b26..a5b623ee6fac 100644 --- a/fs/btrfs/raid56.c +++ b/fs/btrfs/raid56.c @@ -52,6 +52,17 @@ struct btrfs_stripe_hash_table { struct btrfs_stripe_hash table[]; }; +/* + * A bvec like structure to present a sector inside a page. + * + * Unlike bvec we don't need bvlen, as it's fixed to sectorsize. + */ +struct sector_ptr { + struct page *page; + unsigned int pgoff:24; + unsigned int uptodate:8; +}; + enum btrfs_rbio_ops { BTRFS_RBIO_WRITE, BTRFS_RBIO_READ_REBUILD, @@ -77,7 +88,7 @@ struct btrfs_raid_bio { /* * for scheduling work in the helper threads */ - struct btrfs_work work; + struct work_struct work; /* * bio list and bio_list_lock are used @@ -101,15 +112,6 @@ struct btrfs_raid_bio { */ unsigned long flags; - /* size of each individual stripe on disk */ - int stripe_len; - - /* number of data stripes (no p/q) */ - int nr_data; - - int real_stripes; - - int stripe_npages; /* * set if we're doing a parity rebuild * for a read from higher up, which is handled @@ -118,18 +120,35 @@ struct btrfs_raid_bio { */ enum btrfs_rbio_ops operation; - /* first bad stripe */ - int faila; + /* Size of each individual stripe on disk */ + u32 stripe_len; - /* second bad stripe (for raid6 use) */ - int failb; + /* How many pages there are for the full stripe including P/Q */ + u16 nr_pages; - int scrubp; - /* - * number of pages needed to represent the full - * stripe - */ - int nr_pages; + /* How many sectors there are for the full stripe including P/Q */ + u16 nr_sectors; + + /* Number of data stripes (no p/q) */ + u8 nr_data; + + /* Numer of all stripes (including P/Q) */ + u8 real_stripes; + + /* How many pages there are for each stripe */ + u8 stripe_npages; + + /* How many sectors there are for each stripe */ + u8 stripe_nsectors; + + /* First bad stripe, -1 means no corruption */ + s8 faila; + + /* Second bad stripe (for RAID6 use) */ + s8 failb; + + /* Stripe number that we're scrubbing */ + u8 scrubp; /* * size of all the bios in the bio_list. This @@ -156,28 +175,29 @@ struct btrfs_raid_bio { */ struct page **stripe_pages; - /* - * pointers to the pages in the bio_list. Stored - * here for faster lookup - */ - struct page **bio_pages; + /* Pointers to the sectors in the bio_list, for faster lookup */ + struct sector_ptr *bio_sectors; /* - * bitmap to record which horizontal stripe has data + * For subpage support, we need to map each sector to above + * stripe_pages. */ + struct sector_ptr *stripe_sectors; + + /* Bitmap to record which horizontal stripe has data */ unsigned long *dbitmap; /* allocated with real_stripes-many pointers for finish_*() calls */ void **finish_pointers; - /* allocated with stripe_npages-many bits for finish_*() calls */ + /* Allocated with stripe_nsectors-many bits for finish_*() calls */ unsigned long *finish_pbitmap; }; static int __raid56_parity_recover(struct btrfs_raid_bio *rbio); static noinline void finish_rmw(struct btrfs_raid_bio *rbio); -static void rmw_work(struct btrfs_work *work); -static void read_rebuild_work(struct btrfs_work *work); +static void rmw_work(struct work_struct *work); +static void read_rebuild_work(struct work_struct *work); static int fail_bio_stripe(struct btrfs_raid_bio *rbio, struct bio *bio); static int fail_rbio_index(struct btrfs_raid_bio *rbio, int failed); static void __free_raid_bio(struct btrfs_raid_bio *rbio); @@ -186,12 +206,12 @@ static int alloc_rbio_pages(struct btrfs_raid_bio *rbio); static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio, int need_check); -static void scrub_parity_work(struct btrfs_work *work); +static void scrub_parity_work(struct work_struct *work); -static void start_async_work(struct btrfs_raid_bio *rbio, btrfs_func_t work_func) +static void start_async_work(struct btrfs_raid_bio *rbio, work_func_t work_func) { - btrfs_init_work(&rbio->work, work_func, NULL, NULL); - btrfs_queue_work(rbio->bioc->fs_info->rmw_workers, &rbio->work); + INIT_WORK(&rbio->work, work_func); + queue_work(rbio->bioc->fs_info->rmw_workers, &rbio->work); } /* @@ -239,7 +259,7 @@ int btrfs_alloc_stripe_hash_table(struct btrfs_fs_info *info) /* * caching an rbio means to copy anything from the - * bio_pages array into the stripe_pages array. We + * bio_sectors array into the stripe_pages array. We * use the page uptodate bit in the stripe cache array * to indicate if it has valid data * @@ -255,12 +275,18 @@ static void cache_rbio_pages(struct btrfs_raid_bio *rbio) if (ret) return; - for (i = 0; i < rbio->nr_pages; i++) { - if (!rbio->bio_pages[i]) + for (i = 0; i < rbio->nr_sectors; i++) { + /* Some range not covered by bio (partial write), skip it */ + if (!rbio->bio_sectors[i].page) continue; - copy_highpage(rbio->stripe_pages[i], rbio->bio_pages[i]); - SetPageUptodate(rbio->stripe_pages[i]); + ASSERT(rbio->stripe_sectors[i].page); + memcpy_page(rbio->stripe_sectors[i].page, + rbio->stripe_sectors[i].pgoff, + rbio->bio_sectors[i].page, + rbio->bio_sectors[i].pgoff, + rbio->bioc->fs_info->sectorsize); + rbio->stripe_sectors[i].uptodate = 1; } set_bit(RBIO_CACHE_READY_BIT, &rbio->flags); } @@ -283,9 +309,50 @@ static int rbio_bucket(struct btrfs_raid_bio *rbio) return hash_64(num >> 16, BTRFS_STRIPE_HASH_TABLE_BITS); } +static bool full_page_sectors_uptodate(struct btrfs_raid_bio *rbio, + unsigned int page_nr) +{ + const u32 sectorsize = rbio->bioc->fs_info->sectorsize; + const u32 sectors_per_page = PAGE_SIZE / sectorsize; + int i; + + ASSERT(page_nr < rbio->nr_pages); + + for (i = sectors_per_page * page_nr; + i < sectors_per_page * page_nr + sectors_per_page; + i++) { + if (!rbio->stripe_sectors[i].uptodate) + return false; + } + return true; +} + /* - * stealing an rbio means taking all the uptodate pages from the stripe - * array in the source rbio and putting them into the destination rbio + * Update the stripe_sectors[] array to use correct page and pgoff + * + * Should be called every time any page pointer in stripes_pages[] got modified. + */ +static void index_stripe_sectors(struct btrfs_raid_bio *rbio) +{ + const u32 sectorsize = rbio->bioc->fs_info->sectorsize; + u32 offset; + int i; + + for (i = 0, offset = 0; i < rbio->nr_sectors; i++, offset += sectorsize) { + int page_index = offset >> PAGE_SHIFT; + + ASSERT(page_index < rbio->nr_pages); + rbio->stripe_sectors[i].page = rbio->stripe_pages[page_index]; + rbio->stripe_sectors[i].pgoff = offset_in_page(offset); + } +} + +/* + * Stealing an rbio means taking all the uptodate pages from the stripe array + * in the source rbio and putting them into the destination rbio. + * + * This will also update the involved stripe_sectors[] which are referring to + * the old pages. */ static void steal_rbio(struct btrfs_raid_bio *src, struct btrfs_raid_bio *dest) { @@ -298,9 +365,8 @@ static void steal_rbio(struct btrfs_raid_bio *src, struct btrfs_raid_bio *dest) for (i = 0; i < dest->nr_pages; i++) { s = src->stripe_pages[i]; - if (!s || !PageUptodate(s)) { + if (!s || !full_page_sectors_uptodate(src, i)) continue; - } d = dest->stripe_pages[i]; if (d) @@ -309,6 +375,8 @@ static void steal_rbio(struct btrfs_raid_bio *src, struct btrfs_raid_bio *dest) dest->stripe_pages[i] = s; src->stripe_pages[i] = NULL; } + index_stripe_sectors(dest); + index_stripe_sectors(src); } /* @@ -600,39 +668,39 @@ static int rbio_can_merge(struct btrfs_raid_bio *last, return 1; } -static int rbio_stripe_page_index(struct btrfs_raid_bio *rbio, int stripe, - int index) +static unsigned int rbio_stripe_sector_index(const struct btrfs_raid_bio *rbio, + unsigned int stripe_nr, + unsigned int sector_nr) { - return stripe * rbio->stripe_npages + index; + ASSERT(stripe_nr < rbio->real_stripes); + ASSERT(sector_nr < rbio->stripe_nsectors); + + return stripe_nr * rbio->stripe_nsectors + sector_nr; } -/* - * these are just the pages from the rbio array, not from anything - * the FS sent down to us - */ -static struct page *rbio_stripe_page(struct btrfs_raid_bio *rbio, int stripe, - int index) +/* Return a sector from rbio->stripe_sectors, not from the bio list */ +static struct sector_ptr *rbio_stripe_sector(const struct btrfs_raid_bio *rbio, + unsigned int stripe_nr, + unsigned int sector_nr) { - return rbio->stripe_pages[rbio_stripe_page_index(rbio, stripe, index)]; + return &rbio->stripe_sectors[rbio_stripe_sector_index(rbio, stripe_nr, + sector_nr)]; } -/* - * helper to index into the pstripe - */ -static struct page *rbio_pstripe_page(struct btrfs_raid_bio *rbio, int index) +/* Grab a sector inside P stripe */ +static struct sector_ptr *rbio_pstripe_sector(const struct btrfs_raid_bio *rbio, + unsigned int sector_nr) { - return rbio_stripe_page(rbio, rbio->nr_data, index); + return rbio_stripe_sector(rbio, rbio->nr_data, sector_nr); } -/* - * helper to index into the qstripe, returns null - * if there is no qstripe - */ -static struct page *rbio_qstripe_page(struct btrfs_raid_bio *rbio, int index) +/* Grab a sector inside Q stripe, return NULL if not RAID6 */ +static struct sector_ptr *rbio_qstripe_sector(const struct btrfs_raid_bio *rbio, + unsigned int sector_nr) { if (rbio->nr_data + 1 == rbio->real_stripes) return NULL; - return rbio_stripe_page(rbio, rbio->nr_data + 1, index); + return rbio_stripe_sector(rbio, rbio->nr_data + 1, sector_nr); } /* @@ -911,47 +979,43 @@ static void raid_write_end_io(struct bio *bio) rbio_orig_end_io(rbio, err); } -/* - * the read/modify/write code wants to use the original bio for - * any pages it included, and then use the rbio for everything - * else. This function decides if a given index (stripe number) - * and page number in that stripe fall inside the original bio - * or the rbio. - * - * if you set bio_list_only, you'll get a NULL back for any ranges - * that are outside the bio_list +/** + * Get a sector pointer specified by its @stripe_nr and @sector_nr * - * This doesn't take any refs on anything, you get a bare page pointer - * and the caller must bump refs as required. + * @rbio: The raid bio + * @stripe_nr: Stripe number, valid range [0, real_stripe) + * @sector_nr: Sector number inside the stripe, + * valid range [0, stripe_nsectors) + * @bio_list_only: Whether to use sectors inside the bio list only. * - * You must call index_rbio_pages once before you can trust - * the answers from this function. + * The read/modify/write code wants to reuse the original bio page as much + * as possible, and only use stripe_sectors as fallback. */ -static struct page *page_in_rbio(struct btrfs_raid_bio *rbio, - int index, int pagenr, int bio_list_only) +static struct sector_ptr *sector_in_rbio(struct btrfs_raid_bio *rbio, + int stripe_nr, int sector_nr, + bool bio_list_only) { - int chunk_page; - struct page *p = NULL; + struct sector_ptr *sector; + int index; + + ASSERT(stripe_nr >= 0 && stripe_nr < rbio->real_stripes); + ASSERT(sector_nr >= 0 && sector_nr < rbio->stripe_nsectors); - chunk_page = index * (rbio->stripe_len >> PAGE_SHIFT) + pagenr; + index = stripe_nr * rbio->stripe_nsectors + sector_nr; + ASSERT(index >= 0 && index < rbio->nr_sectors); spin_lock_irq(&rbio->bio_list_lock); - p = rbio->bio_pages[chunk_page]; + sector = &rbio->bio_sectors[index]; + if (sector->page || bio_list_only) { + /* Don't return sector without a valid page pointer */ + if (!sector->page) + sector = NULL; + spin_unlock_irq(&rbio->bio_list_lock); + return sector; + } spin_unlock_irq(&rbio->bio_list_lock); - if (p || bio_list_only) - return p; - - return rbio->stripe_pages[chunk_page]; -} - -/* - * number of pages we need for the entire stripe across all the - * drives - */ -static unsigned long rbio_nr_pages(unsigned long stripe_len, int nr_stripes) -{ - return DIV_ROUND_UP(stripe_len, PAGE_SIZE) * nr_stripes; + return &rbio->stripe_sectors[index]; } /* @@ -960,22 +1024,28 @@ static unsigned long rbio_nr_pages(unsigned long stripe_len, int nr_stripes) */ static struct btrfs_raid_bio *alloc_rbio(struct btrfs_fs_info *fs_info, struct btrfs_io_context *bioc, - u64 stripe_len) + u32 stripe_len) { + const unsigned int real_stripes = bioc->num_stripes - bioc->num_tgtdevs; + const unsigned int stripe_npages = stripe_len >> PAGE_SHIFT; + const unsigned int num_pages = stripe_npages * real_stripes; + const unsigned int stripe_nsectors = stripe_len >> fs_info->sectorsize_bits; + const unsigned int num_sectors = stripe_nsectors * real_stripes; struct btrfs_raid_bio *rbio; int nr_data = 0; - int real_stripes = bioc->num_stripes - bioc->num_tgtdevs; - int num_pages = rbio_nr_pages(stripe_len, real_stripes); - int stripe_npages = DIV_ROUND_UP(stripe_len, PAGE_SIZE); void *p; + ASSERT(IS_ALIGNED(stripe_len, PAGE_SIZE)); + /* PAGE_SIZE must also be aligned to sectorsize for subpage support */ + ASSERT(IS_ALIGNED(PAGE_SIZE, fs_info->sectorsize)); + rbio = kzalloc(sizeof(*rbio) + sizeof(*rbio->stripe_pages) * num_pages + - sizeof(*rbio->bio_pages) * num_pages + + sizeof(*rbio->bio_sectors) * num_sectors + + sizeof(*rbio->stripe_sectors) * num_sectors + sizeof(*rbio->finish_pointers) * real_stripes + - sizeof(*rbio->dbitmap) * BITS_TO_LONGS(stripe_npages) + - sizeof(*rbio->finish_pbitmap) * - BITS_TO_LONGS(stripe_npages), + sizeof(*rbio->dbitmap) * BITS_TO_LONGS(stripe_nsectors) + + sizeof(*rbio->finish_pbitmap) * BITS_TO_LONGS(stripe_nsectors), GFP_NOFS); if (!rbio) return ERR_PTR(-ENOMEM); @@ -988,8 +1058,10 @@ static struct btrfs_raid_bio *alloc_rbio(struct btrfs_fs_info *fs_info, rbio->bioc = bioc; rbio->stripe_len = stripe_len; rbio->nr_pages = num_pages; + rbio->nr_sectors = num_sectors; rbio->real_stripes = real_stripes; rbio->stripe_npages = stripe_npages; + rbio->stripe_nsectors = stripe_nsectors; rbio->faila = -1; rbio->failb = -1; refcount_set(&rbio->refs, 1); @@ -997,8 +1069,8 @@ static struct btrfs_raid_bio *alloc_rbio(struct btrfs_fs_info *fs_info, atomic_set(&rbio->stripes_pending, 0); /* - * the stripe_pages, bio_pages, etc arrays point to the extra - * memory we allocated past the end of the rbio + * The stripe_pages, bio_sectors, etc arrays point to the extra memory + * we allocated past the end of the rbio. */ p = rbio + 1; #define CONSUME_ALLOC(ptr, count) do { \ @@ -1006,10 +1078,11 @@ static struct btrfs_raid_bio *alloc_rbio(struct btrfs_fs_info *fs_info, p = (unsigned char *)p + sizeof(*(ptr)) * (count); \ } while (0) CONSUME_ALLOC(rbio->stripe_pages, num_pages); - CONSUME_ALLOC(rbio->bio_pages, num_pages); + CONSUME_ALLOC(rbio->bio_sectors, num_sectors); + CONSUME_ALLOC(rbio->stripe_sectors, num_sectors); CONSUME_ALLOC(rbio->finish_pointers, real_stripes); - CONSUME_ALLOC(rbio->dbitmap, BITS_TO_LONGS(stripe_npages)); - CONSUME_ALLOC(rbio->finish_pbitmap, BITS_TO_LONGS(stripe_npages)); + CONSUME_ALLOC(rbio->dbitmap, BITS_TO_LONGS(stripe_nsectors)); + CONSUME_ALLOC(rbio->finish_pbitmap, BITS_TO_LONGS(stripe_nsectors)); #undef CONSUME_ALLOC if (bioc->map_type & BTRFS_BLOCK_GROUP_RAID5) @@ -1026,59 +1099,63 @@ static struct btrfs_raid_bio *alloc_rbio(struct btrfs_fs_info *fs_info, /* allocate pages for all the stripes in the bio, including parity */ static int alloc_rbio_pages(struct btrfs_raid_bio *rbio) { - int i; - struct page *page; + int ret; - for (i = 0; i < rbio->nr_pages; i++) { - if (rbio->stripe_pages[i]) - continue; - page = alloc_page(GFP_NOFS); - if (!page) - return -ENOMEM; - rbio->stripe_pages[i] = page; - } + ret = btrfs_alloc_page_array(rbio->nr_pages, rbio->stripe_pages); + if (ret < 0) + return ret; + /* Mapping all sectors */ + index_stripe_sectors(rbio); return 0; } /* only allocate pages for p/q stripes */ static int alloc_rbio_parity_pages(struct btrfs_raid_bio *rbio) { - int i; - struct page *page; + const int data_pages = rbio->nr_data * rbio->stripe_npages; + int ret; - i = rbio_stripe_page_index(rbio, rbio->nr_data, 0); + ret = btrfs_alloc_page_array(rbio->nr_pages - data_pages, + rbio->stripe_pages + data_pages); + if (ret < 0) + return ret; - for (; i < rbio->nr_pages; i++) { - if (rbio->stripe_pages[i]) - continue; - page = alloc_page(GFP_NOFS); - if (!page) - return -ENOMEM; - rbio->stripe_pages[i] = page; - } + index_stripe_sectors(rbio); return 0; } /* - * add a single page from a specific stripe into our list of bios for IO - * this will try to merge into existing bios if possible, and returns - * zero if all went well. + * Add a single sector @sector into our list of bios for IO. + * + * Return 0 if everything went well. + * Return <0 for error. */ -static int rbio_add_io_page(struct btrfs_raid_bio *rbio, - struct bio_list *bio_list, - struct page *page, - int stripe_nr, - unsigned long page_index, - unsigned long bio_max_len) -{ +static int rbio_add_io_sector(struct btrfs_raid_bio *rbio, + struct bio_list *bio_list, + struct sector_ptr *sector, + unsigned int stripe_nr, + unsigned int sector_nr, + unsigned long bio_max_len, + unsigned int opf) +{ + const u32 sectorsize = rbio->bioc->fs_info->sectorsize; struct bio *last = bio_list->tail; int ret; struct bio *bio; struct btrfs_io_stripe *stripe; u64 disk_start; + /* + * Note: here stripe_nr has taken device replace into consideration, + * thus it can be larger than rbio->real_stripe. + * So here we check against bioc->num_stripes, not rbio->real_stripes. + */ + ASSERT(stripe_nr >= 0 && stripe_nr < rbio->bioc->num_stripes); + ASSERT(sector_nr >= 0 && sector_nr < rbio->stripe_nsectors); + ASSERT(sector->page); + stripe = &rbio->bioc->stripes[stripe_nr]; - disk_start = stripe->physical + (page_index << PAGE_SHIFT); + disk_start = stripe->physical + sector_nr * sectorsize; /* if the device is missing, just fail this stripe */ if (!stripe->dev->bdev) @@ -1095,20 +1172,20 @@ static int rbio_add_io_page(struct btrfs_raid_bio *rbio, */ if (last_end == disk_start && !last->bi_status && last->bi_bdev == stripe->dev->bdev) { - ret = bio_add_page(last, page, PAGE_SIZE, 0); - if (ret == PAGE_SIZE) + ret = bio_add_page(last, sector->page, sectorsize, + sector->pgoff); + if (ret == sectorsize) return 0; } } /* put a new bio on the list */ - bio = btrfs_bio_alloc(bio_max_len >> PAGE_SHIFT ?: 1); - btrfs_bio(bio)->device = stripe->dev; - bio->bi_iter.bi_size = 0; - bio_set_dev(bio, stripe->dev->bdev); + bio = bio_alloc(stripe->dev->bdev, max(bio_max_len >> PAGE_SHIFT, 1UL), + opf, GFP_NOFS); bio->bi_iter.bi_sector = disk_start >> 9; + bio->bi_private = rbio; - bio_add_page(bio, page, PAGE_SIZE, 0); + bio_add_page(bio, sector->page, sectorsize, sector->pgoff); bio_list_add(bio_list, bio); return 0; } @@ -1130,6 +1207,32 @@ static void validate_rbio_for_rmw(struct btrfs_raid_bio *rbio) } } +static void index_one_bio(struct btrfs_raid_bio *rbio, struct bio *bio) +{ + const u32 sectorsize = rbio->bioc->fs_info->sectorsize; + struct bio_vec bvec; + struct bvec_iter iter; + u32 offset = (bio->bi_iter.bi_sector << SECTOR_SHIFT) - + rbio->bioc->raid_map[0]; + + if (bio_flagged(bio, BIO_CLONED)) + bio->bi_iter = btrfs_bio(bio)->iter; + + bio_for_each_segment(bvec, bio, iter) { + u32 bvec_offset; + + for (bvec_offset = 0; bvec_offset < bvec.bv_len; + bvec_offset += sectorsize, offset += sectorsize) { + int index = offset / sectorsize; + struct sector_ptr *sector = &rbio->bio_sectors[index]; + + sector->page = bvec.bv_page; + sector->pgoff = bvec.bv_offset + bvec_offset; + ASSERT(sector->pgoff < PAGE_SIZE); + } + } +} + /* * helper function to walk our bio list and populate the bio_pages array with * the result. This seems expensive, but it is faster than constantly @@ -1141,28 +1244,11 @@ static void validate_rbio_for_rmw(struct btrfs_raid_bio *rbio) static void index_rbio_pages(struct btrfs_raid_bio *rbio) { struct bio *bio; - u64 start; - unsigned long stripe_offset; - unsigned long page_index; spin_lock_irq(&rbio->bio_list_lock); - bio_list_for_each(bio, &rbio->bio_list) { - struct bio_vec bvec; - struct bvec_iter iter; - int i = 0; + bio_list_for_each(bio, &rbio->bio_list) + index_one_bio(rbio, bio); - start = bio->bi_iter.bi_sector << 9; - stripe_offset = start - rbio->bioc->raid_map[0]; - page_index = stripe_offset >> PAGE_SHIFT; - - if (bio_flagged(bio, BIO_CLONED)) - bio->bi_iter = btrfs_bio(bio)->iter; - - bio_for_each_segment(bvec, bio, iter) { - rbio->bio_pages[page_index + i] = bvec.bv_page; - i++; - } - } spin_unlock_irq(&rbio->bio_list_lock); } @@ -1177,10 +1263,11 @@ static void index_rbio_pages(struct btrfs_raid_bio *rbio) static noinline void finish_rmw(struct btrfs_raid_bio *rbio) { struct btrfs_io_context *bioc = rbio->bioc; + const u32 sectorsize = bioc->fs_info->sectorsize; void **pointers = rbio->finish_pointers; int nr_data = rbio->nr_data; int stripe; - int pagenr; + int sectornr; bool has_qstripe; struct bio_list bio_list; struct bio *bio; @@ -1224,35 +1311,37 @@ static noinline void finish_rmw(struct btrfs_raid_bio *rbio) else clear_bit(RBIO_CACHE_READY_BIT, &rbio->flags); - for (pagenr = 0; pagenr < rbio->stripe_npages; pagenr++) { - struct page *p; - /* first collect one page from each data stripe */ + for (sectornr = 0; sectornr < rbio->stripe_nsectors; sectornr++) { + struct sector_ptr *sector; + + /* First collect one sector from each data stripe */ for (stripe = 0; stripe < nr_data; stripe++) { - p = page_in_rbio(rbio, stripe, pagenr, 0); - pointers[stripe] = kmap_local_page(p); + sector = sector_in_rbio(rbio, stripe, sectornr, 0); + pointers[stripe] = kmap_local_page(sector->page) + + sector->pgoff; } - /* then add the parity stripe */ - p = rbio_pstripe_page(rbio, pagenr); - SetPageUptodate(p); - pointers[stripe++] = kmap_local_page(p); + /* Then add the parity stripe */ + sector = rbio_pstripe_sector(rbio, sectornr); + sector->uptodate = 1; + pointers[stripe++] = kmap_local_page(sector->page) + sector->pgoff; if (has_qstripe) { - /* - * raid6, add the qstripe and call the - * library function to fill in our p/q + * RAID6, add the qstripe and call the library function + * to fill in our p/q */ - p = rbio_qstripe_page(rbio, pagenr); - SetPageUptodate(p); - pointers[stripe++] = kmap_local_page(p); + sector = rbio_qstripe_sector(rbio, sectornr); + sector->uptodate = 1; + pointers[stripe++] = kmap_local_page(sector->page) + + sector->pgoff; - raid6_call.gen_syndrome(rbio->real_stripes, PAGE_SIZE, + raid6_call.gen_syndrome(rbio->real_stripes, sectorsize, pointers); } else { /* raid5 */ - copy_page(pointers[nr_data], pointers[0]); - run_xor(pointers + 1, nr_data - 1, PAGE_SIZE); + memcpy(pointers[nr_data], pointers[0], sectorsize); + run_xor(pointers + 1, nr_data - 1, sectorsize); } for (stripe = stripe - 1; stripe >= 0; stripe--) kunmap_local(pointers[stripe]); @@ -1264,18 +1353,20 @@ static noinline void finish_rmw(struct btrfs_raid_bio *rbio) * everything else. */ for (stripe = 0; stripe < rbio->real_stripes; stripe++) { - for (pagenr = 0; pagenr < rbio->stripe_npages; pagenr++) { - struct page *page; + for (sectornr = 0; sectornr < rbio->stripe_nsectors; sectornr++) { + struct sector_ptr *sector; + if (stripe < rbio->nr_data) { - page = page_in_rbio(rbio, stripe, pagenr, 1); - if (!page) + sector = sector_in_rbio(rbio, stripe, sectornr, 1); + if (!sector) continue; } else { - page = rbio_stripe_page(rbio, stripe, pagenr); + sector = rbio_stripe_sector(rbio, stripe, sectornr); } - ret = rbio_add_io_page(rbio, &bio_list, - page, stripe, pagenr, rbio->stripe_len); + ret = rbio_add_io_sector(rbio, &bio_list, sector, stripe, + sectornr, rbio->stripe_len, + REQ_OP_WRITE); if (ret) goto cleanup; } @@ -1288,19 +1379,21 @@ static noinline void finish_rmw(struct btrfs_raid_bio *rbio) if (!bioc->tgtdev_map[stripe]) continue; - for (pagenr = 0; pagenr < rbio->stripe_npages; pagenr++) { - struct page *page; + for (sectornr = 0; sectornr < rbio->stripe_nsectors; sectornr++) { + struct sector_ptr *sector; + if (stripe < rbio->nr_data) { - page = page_in_rbio(rbio, stripe, pagenr, 1); - if (!page) + sector = sector_in_rbio(rbio, stripe, sectornr, 1); + if (!sector) continue; } else { - page = rbio_stripe_page(rbio, stripe, pagenr); + sector = rbio_stripe_sector(rbio, stripe, sectornr); } - ret = rbio_add_io_page(rbio, &bio_list, page, + ret = rbio_add_io_sector(rbio, &bio_list, sector, rbio->bioc->tgtdev_map[stripe], - pagenr, rbio->stripe_len); + sectornr, rbio->stripe_len, + REQ_OP_WRITE); if (ret) goto cleanup; } @@ -1311,9 +1404,7 @@ write_data: BUG_ON(atomic_read(&rbio->stripes_pending) == 0); while ((bio = bio_list_pop(&bio_list))) { - bio->bi_private = rbio; bio->bi_end_io = raid_write_end_io; - bio->bi_opf = REQ_OP_WRITE; submit_bio(bio); } @@ -1417,18 +1508,48 @@ static int fail_bio_stripe(struct btrfs_raid_bio *rbio, } /* + * For subpage case, we can no longer set page Uptodate directly for + * stripe_pages[], thus we need to locate the sector. + */ +static struct sector_ptr *find_stripe_sector(struct btrfs_raid_bio *rbio, + struct page *page, + unsigned int pgoff) +{ + int i; + + for (i = 0; i < rbio->nr_sectors; i++) { + struct sector_ptr *sector = &rbio->stripe_sectors[i]; + + if (sector->page == page && sector->pgoff == pgoff) + return sector; + } + return NULL; +} + +/* * this sets each page in the bio uptodate. It should only be used on private * rbio pages, nothing that comes in from the higher layers */ -static void set_bio_pages_uptodate(struct bio *bio) +static void set_bio_pages_uptodate(struct btrfs_raid_bio *rbio, struct bio *bio) { + const u32 sectorsize = rbio->bioc->fs_info->sectorsize; struct bio_vec *bvec; struct bvec_iter_all iter_all; ASSERT(!bio_flagged(bio, BIO_CLONED)); - bio_for_each_segment_all(bvec, bio, iter_all) - SetPageUptodate(bvec->bv_page); + bio_for_each_segment_all(bvec, bio, iter_all) { + struct sector_ptr *sector; + int pgoff; + + for (pgoff = bvec->bv_offset; pgoff - bvec->bv_offset < bvec->bv_len; + pgoff += sectorsize) { + sector = find_stripe_sector(rbio, bvec->bv_page, pgoff); + ASSERT(sector); + if (sector) + sector->uptodate = 1; + } + } } /* @@ -1446,7 +1567,7 @@ static void raid_rmw_end_io(struct bio *bio) if (bio->bi_status) fail_bio_stripe(rbio, bio); else - set_bio_pages_uptodate(bio); + set_bio_pages_uptodate(rbio, bio); bio_put(bio); @@ -1478,7 +1599,7 @@ static int raid56_rmw_stripe(struct btrfs_raid_bio *rbio) int bios_to_read = 0; struct bio_list bio_list; int ret; - int pagenr; + int sectornr; int stripe; struct bio *bio; @@ -1496,28 +1617,30 @@ static int raid56_rmw_stripe(struct btrfs_raid_bio *rbio) * stripe */ for (stripe = 0; stripe < rbio->nr_data; stripe++) { - for (pagenr = 0; pagenr < rbio->stripe_npages; pagenr++) { - struct page *page; + for (sectornr = 0; sectornr < rbio->stripe_nsectors; sectornr++) { + struct sector_ptr *sector; + /* - * we want to find all the pages missing from - * the rbio and read them from the disk. If - * page_in_rbio finds a page in the bio list - * we don't need to read it off the stripe. + * We want to find all the sectors missing from the + * rbio and read them from the disk. If * sector_in_rbio() + * finds a page in the bio list we don't need to read + * it off the stripe. */ - page = page_in_rbio(rbio, stripe, pagenr, 1); - if (page) + sector = sector_in_rbio(rbio, stripe, sectornr, 1); + if (sector) continue; - page = rbio_stripe_page(rbio, stripe, pagenr); + sector = rbio_stripe_sector(rbio, stripe, sectornr); /* - * the bio cache may have handed us an uptodate - * page. If so, be happy and use it + * The bio cache may have handed us an uptodate page. + * If so, be happy and use it. */ - if (PageUptodate(page)) + if (sector->uptodate) continue; - ret = rbio_add_io_page(rbio, &bio_list, page, - stripe, pagenr, rbio->stripe_len); + ret = rbio_add_io_sector(rbio, &bio_list, sector, + stripe, sectornr, rbio->stripe_len, + REQ_OP_READ); if (ret) goto cleanup; } @@ -1540,9 +1663,7 @@ static int raid56_rmw_stripe(struct btrfs_raid_bio *rbio) */ atomic_set(&rbio->stripes_pending, bios_to_read); while ((bio = bio_list_pop(&bio_list))) { - bio->bi_private = rbio; bio->bi_end_io = raid_rmw_end_io; - bio->bi_opf = REQ_OP_READ; btrfs_bio_wq_end_io(rbio->bioc->fs_info, bio, BTRFS_WQ_ENDIO_RAID56); @@ -1624,7 +1745,7 @@ struct btrfs_plug_cb { struct blk_plug_cb cb; struct btrfs_fs_info *info; struct list_head rbio_list; - struct btrfs_work work; + struct work_struct work; }; /* @@ -1692,7 +1813,7 @@ static void run_plug(struct btrfs_plug_cb *plug) * if the unplug comes from schedule, we have to push the * work off to a helper thread */ -static void unplug_work(struct btrfs_work *work) +static void unplug_work(struct work_struct *work) { struct btrfs_plug_cb *plug; plug = container_of(work, struct btrfs_plug_cb, work); @@ -1705,9 +1826,8 @@ static void btrfs_raid_unplug(struct blk_plug_cb *cb, bool from_schedule) plug = container_of(cb, struct btrfs_plug_cb, cb); if (from_schedule) { - btrfs_init_work(&plug->work, unplug_work, NULL, NULL); - btrfs_queue_work(plug->info->rmw_workers, - &plug->work); + INIT_WORK(&plug->work, unplug_work); + queue_work(plug->info->rmw_workers, &plug->work); return; } run_plug(plug); @@ -1716,8 +1836,7 @@ static void btrfs_raid_unplug(struct blk_plug_cb *cb, bool from_schedule) /* * our main entry point for writes from the rest of the FS. */ -int raid56_parity_write(struct bio *bio, struct btrfs_io_context *bioc, - u64 stripe_len) +int raid56_parity_write(struct bio *bio, struct btrfs_io_context *bioc, u32 stripe_len) { struct btrfs_fs_info *fs_info = bioc->fs_info; struct btrfs_raid_bio *rbio; @@ -1772,14 +1891,18 @@ int raid56_parity_write(struct bio *bio, struct btrfs_io_context *bioc, */ static void __raid_recover_end_io(struct btrfs_raid_bio *rbio) { - int pagenr, stripe; + const u32 sectorsize = rbio->bioc->fs_info->sectorsize; + int sectornr, stripe; void **pointers; void **unmap_array; int faila = -1, failb = -1; - struct page *page; blk_status_t err; int i; + /* + * This array stores the pointer for each sector, thus it has the extra + * pgoff value added from each sector + */ pointers = kcalloc(rbio->real_stripes, sizeof(void *), GFP_NOFS); if (!pointers) { err = BLK_STS_RESOURCE; @@ -1808,43 +1931,44 @@ static void __raid_recover_end_io(struct btrfs_raid_bio *rbio) index_rbio_pages(rbio); - for (pagenr = 0; pagenr < rbio->stripe_npages; pagenr++) { + for (sectornr = 0; sectornr < rbio->stripe_nsectors; sectornr++) { + struct sector_ptr *sector; + /* * Now we just use bitmap to mark the horizontal stripes in * which we have data when doing parity scrub. */ if (rbio->operation == BTRFS_RBIO_PARITY_SCRUB && - !test_bit(pagenr, rbio->dbitmap)) + !test_bit(sectornr, rbio->dbitmap)) continue; /* - * Setup our array of pointers with pages from each stripe + * Setup our array of pointers with sectors from each stripe * * NOTE: store a duplicate array of pointers to preserve the * pointer order */ for (stripe = 0; stripe < rbio->real_stripes; stripe++) { /* - * if we're rebuilding a read, we have to use + * If we're rebuilding a read, we have to use * pages from the bio list */ if ((rbio->operation == BTRFS_RBIO_READ_REBUILD || rbio->operation == BTRFS_RBIO_REBUILD_MISSING) && (stripe == faila || stripe == failb)) { - page = page_in_rbio(rbio, stripe, pagenr, 0); + sector = sector_in_rbio(rbio, stripe, sectornr, 0); } else { - page = rbio_stripe_page(rbio, stripe, pagenr); + sector = rbio_stripe_sector(rbio, stripe, sectornr); } - pointers[stripe] = kmap_local_page(page); + ASSERT(sector->page); + pointers[stripe] = kmap_local_page(sector->page) + + sector->pgoff; unmap_array[stripe] = pointers[stripe]; } - /* all raid6 handling here */ + /* All raid6 handling here */ if (rbio->bioc->map_type & BTRFS_BLOCK_GROUP_RAID6) { - /* - * single failure, rebuild from parity raid5 - * style - */ + /* Single failure, rebuild from parity raid5 style */ if (failb < 0) { if (faila == rbio->nr_data) { /* @@ -1887,10 +2011,10 @@ static void __raid_recover_end_io(struct btrfs_raid_bio *rbio) if (rbio->bioc->raid_map[failb] == RAID5_P_STRIPE) { raid6_datap_recov(rbio->real_stripes, - PAGE_SIZE, faila, pointers); + sectorsize, faila, pointers); } else { raid6_2data_recov(rbio->real_stripes, - PAGE_SIZE, faila, failb, + sectorsize, faila, failb, pointers); } } else { @@ -1900,7 +2024,7 @@ static void __raid_recover_end_io(struct btrfs_raid_bio *rbio) BUG_ON(failb != -1); pstripe: /* Copy parity block into failed block to start with */ - copy_page(pointers[faila], pointers[rbio->nr_data]); + memcpy(pointers[faila], pointers[rbio->nr_data], sectorsize); /* rearrange the pointer array */ p = pointers[faila]; @@ -1909,7 +2033,7 @@ pstripe: pointers[rbio->nr_data - 1] = p; /* xor in the rest */ - run_xor(pointers, rbio->nr_data - 1, PAGE_SIZE); + run_xor(pointers, rbio->nr_data - 1, sectorsize); } /* if we're doing this rebuild as part of an rmw, go through * and set all of our private rbio pages in the @@ -1918,14 +2042,14 @@ pstripe: * other endio functions will fiddle the uptodate bits */ if (rbio->operation == BTRFS_RBIO_WRITE) { - for (i = 0; i < rbio->stripe_npages; i++) { + for (i = 0; i < rbio->stripe_nsectors; i++) { if (faila != -1) { - page = rbio_stripe_page(rbio, faila, i); - SetPageUptodate(page); + sector = rbio_stripe_sector(rbio, faila, i); + sector->uptodate = 1; } if (failb != -1) { - page = rbio_stripe_page(rbio, failb, i); - SetPageUptodate(page); + sector = rbio_stripe_sector(rbio, failb, i); + sector->uptodate = 1; } } } @@ -1998,7 +2122,7 @@ static void raid_recover_end_io(struct bio *bio) if (bio->bi_status) fail_bio_stripe(rbio, bio); else - set_bio_pages_uptodate(bio); + set_bio_pages_uptodate(rbio, bio); bio_put(bio); if (!atomic_dec_and_test(&rbio->stripes_pending)) @@ -2023,7 +2147,7 @@ static int __raid56_parity_recover(struct btrfs_raid_bio *rbio) int bios_to_read = 0; struct bio_list bio_list; int ret; - int pagenr; + int sectornr; int stripe; struct bio *bio; @@ -2046,20 +2170,20 @@ static int __raid56_parity_recover(struct btrfs_raid_bio *rbio) continue; } - for (pagenr = 0; pagenr < rbio->stripe_npages; pagenr++) { - struct page *p; + for (sectornr = 0; sectornr < rbio->stripe_nsectors; sectornr++) { + struct sector_ptr *sector; /* * the rmw code may have already read this * page in */ - p = rbio_stripe_page(rbio, stripe, pagenr); - if (PageUptodate(p)) + sector = rbio_stripe_sector(rbio, stripe, sectornr); + if (sector->uptodate) continue; - ret = rbio_add_io_page(rbio, &bio_list, - rbio_stripe_page(rbio, stripe, pagenr), - stripe, pagenr, rbio->stripe_len); + ret = rbio_add_io_sector(rbio, &bio_list, sector, + stripe, sectornr, rbio->stripe_len, + REQ_OP_READ); if (ret < 0) goto cleanup; } @@ -2086,9 +2210,7 @@ static int __raid56_parity_recover(struct btrfs_raid_bio *rbio) */ atomic_set(&rbio->stripes_pending, bios_to_read); while ((bio = bio_list_pop(&bio_list))) { - bio->bi_private = rbio; bio->bi_end_io = raid_recover_end_io; - bio->bi_opf = REQ_OP_READ; btrfs_bio_wq_end_io(rbio->bioc->fs_info, bio, BTRFS_WQ_ENDIO_RAID56); @@ -2115,7 +2237,7 @@ cleanup: * of the drive. */ int raid56_parity_recover(struct bio *bio, struct btrfs_io_context *bioc, - u64 stripe_len, int mirror_num, int generic_io) + u32 stripe_len, int mirror_num, int generic_io) { struct btrfs_fs_info *fs_info = bioc->fs_info; struct btrfs_raid_bio *rbio; @@ -2193,7 +2315,7 @@ int raid56_parity_recover(struct bio *bio, struct btrfs_io_context *bioc, } -static void rmw_work(struct btrfs_work *work) +static void rmw_work(struct work_struct *work) { struct btrfs_raid_bio *rbio; @@ -2201,7 +2323,7 @@ static void rmw_work(struct btrfs_work *work) raid56_rmw_stripe(rbio); } -static void read_rebuild_work(struct btrfs_work *work) +static void read_rebuild_work(struct work_struct *work) { struct btrfs_raid_bio *rbio; @@ -2221,7 +2343,7 @@ static void read_rebuild_work(struct btrfs_work *work) struct btrfs_raid_bio *raid56_parity_alloc_scrub_rbio(struct bio *bio, struct btrfs_io_context *bioc, - u64 stripe_len, struct btrfs_device *scrub_dev, + u32 stripe_len, struct btrfs_device *scrub_dev, unsigned long *dbitmap, int stripe_nsectors) { struct btrfs_fs_info *fs_info = bioc->fs_info; @@ -2252,9 +2374,6 @@ struct btrfs_raid_bio *raid56_parity_alloc_scrub_rbio(struct bio *bio, } ASSERT(i < rbio->real_stripes); - /* Now we just support the sectorsize equals to page size */ - ASSERT(fs_info->sectorsize == PAGE_SIZE); - ASSERT(rbio->stripe_npages == stripe_nsectors); bitmap_copy(rbio->dbitmap, dbitmap, stripe_nsectors); /* @@ -2268,17 +2387,19 @@ struct btrfs_raid_bio *raid56_parity_alloc_scrub_rbio(struct bio *bio, /* Used for both parity scrub and missing. */ void raid56_add_scrub_pages(struct btrfs_raid_bio *rbio, struct page *page, - u64 logical) + unsigned int pgoff, u64 logical) { + const u32 sectorsize = rbio->bioc->fs_info->sectorsize; int stripe_offset; int index; ASSERT(logical >= rbio->bioc->raid_map[0]); - ASSERT(logical + PAGE_SIZE <= rbio->bioc->raid_map[0] + + ASSERT(logical + sectorsize <= rbio->bioc->raid_map[0] + rbio->stripe_len * rbio->nr_data); stripe_offset = (int)(logical - rbio->bioc->raid_map[0]); - index = stripe_offset >> PAGE_SHIFT; - rbio->bio_pages[index] = page; + index = stripe_offset / sectorsize; + rbio->bio_sectors[index].page = page; + rbio->bio_sectors[index].pgoff = pgoff; } /* @@ -2287,14 +2408,16 @@ void raid56_add_scrub_pages(struct btrfs_raid_bio *rbio, struct page *page, */ static int alloc_rbio_essential_pages(struct btrfs_raid_bio *rbio) { - int i; - int bit; - int index; - struct page *page; + const u32 sectorsize = rbio->bioc->fs_info->sectorsize; + int stripe; + int sectornr; + + for_each_set_bit(sectornr, rbio->dbitmap, rbio->stripe_nsectors) { + for (stripe = 0; stripe < rbio->real_stripes; stripe++) { + struct page *page; + int index = (stripe * rbio->stripe_nsectors + sectornr) * + sectorsize >> PAGE_SHIFT; - for_each_set_bit(bit, rbio->dbitmap, rbio->stripe_npages) { - for (i = 0; i < rbio->real_stripes; i++) { - index = i * rbio->stripe_npages + bit; if (rbio->stripe_pages[index]) continue; @@ -2304,6 +2427,7 @@ static int alloc_rbio_essential_pages(struct btrfs_raid_bio *rbio) rbio->stripe_pages[index] = page; } } + index_stripe_sectors(rbio); return 0; } @@ -2311,14 +2435,15 @@ static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio, int need_check) { struct btrfs_io_context *bioc = rbio->bioc; + const u32 sectorsize = bioc->fs_info->sectorsize; void **pointers = rbio->finish_pointers; unsigned long *pbitmap = rbio->finish_pbitmap; int nr_data = rbio->nr_data; int stripe; - int pagenr; + int sectornr; bool has_qstripe; - struct page *p_page = NULL; - struct page *q_page = NULL; + struct sector_ptr p_sector = { 0 }; + struct sector_ptr q_sector = { 0 }; struct bio_list bio_list; struct bio *bio; int is_replace = 0; @@ -2335,7 +2460,7 @@ static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio, if (bioc->num_tgtdevs && bioc->tgtdev_map[rbio->scrubp]) { is_replace = 1; - bitmap_copy(pbitmap, rbio->dbitmap, rbio->stripe_npages); + bitmap_copy(pbitmap, rbio->dbitmap, rbio->stripe_nsectors); } /* @@ -2348,54 +2473,59 @@ static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio, if (!need_check) goto writeback; - p_page = alloc_page(GFP_NOFS); - if (!p_page) + p_sector.page = alloc_page(GFP_NOFS); + if (!p_sector.page) goto cleanup; - SetPageUptodate(p_page); + p_sector.pgoff = 0; + p_sector.uptodate = 1; if (has_qstripe) { /* RAID6, allocate and map temp space for the Q stripe */ - q_page = alloc_page(GFP_NOFS); - if (!q_page) { - __free_page(p_page); + q_sector.page = alloc_page(GFP_NOFS); + if (!q_sector.page) { + __free_page(p_sector.page); + p_sector.page = NULL; goto cleanup; } - SetPageUptodate(q_page); - pointers[rbio->real_stripes - 1] = kmap_local_page(q_page); + q_sector.pgoff = 0; + q_sector.uptodate = 1; + pointers[rbio->real_stripes - 1] = kmap_local_page(q_sector.page); } atomic_set(&rbio->error, 0); /* Map the parity stripe just once */ - pointers[nr_data] = kmap_local_page(p_page); + pointers[nr_data] = kmap_local_page(p_sector.page); - for_each_set_bit(pagenr, rbio->dbitmap, rbio->stripe_npages) { - struct page *p; + for_each_set_bit(sectornr, rbio->dbitmap, rbio->stripe_nsectors) { + struct sector_ptr *sector; void *parity; + /* first collect one page from each data stripe */ for (stripe = 0; stripe < nr_data; stripe++) { - p = page_in_rbio(rbio, stripe, pagenr, 0); - pointers[stripe] = kmap_local_page(p); + sector = sector_in_rbio(rbio, stripe, sectornr, 0); + pointers[stripe] = kmap_local_page(sector->page) + + sector->pgoff; } if (has_qstripe) { /* RAID6, call the library function to fill in our P/Q */ - raid6_call.gen_syndrome(rbio->real_stripes, PAGE_SIZE, + raid6_call.gen_syndrome(rbio->real_stripes, sectorsize, pointers); } else { /* raid5 */ - copy_page(pointers[nr_data], pointers[0]); - run_xor(pointers + 1, nr_data - 1, PAGE_SIZE); + memcpy(pointers[nr_data], pointers[0], sectorsize); + run_xor(pointers + 1, nr_data - 1, sectorsize); } /* Check scrubbing parity and repair it */ - p = rbio_stripe_page(rbio, rbio->scrubp, pagenr); - parity = kmap_local_page(p); - if (memcmp(parity, pointers[rbio->scrubp], PAGE_SIZE)) - copy_page(parity, pointers[rbio->scrubp]); + sector = rbio_stripe_sector(rbio, rbio->scrubp, sectornr); + parity = kmap_local_page(sector->page) + sector->pgoff; + if (memcmp(parity, pointers[rbio->scrubp], sectorsize) != 0) + memcpy(parity, pointers[rbio->scrubp], sectorsize); else /* Parity is right, needn't writeback */ - bitmap_clear(rbio->dbitmap, pagenr, 1); + bitmap_clear(rbio->dbitmap, sectornr, 1); kunmap_local(parity); for (stripe = nr_data - 1; stripe >= 0; stripe--) @@ -2403,10 +2533,12 @@ static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio, } kunmap_local(pointers[nr_data]); - __free_page(p_page); - if (q_page) { + __free_page(p_sector.page); + p_sector.page = NULL; + if (q_sector.page) { kunmap_local(pointers[rbio->real_stripes - 1]); - __free_page(q_page); + __free_page(q_sector.page); + q_sector.page = NULL; } writeback: @@ -2415,12 +2547,12 @@ writeback: * higher layers (the bio_list in our rbio) and our p/q. Ignore * everything else. */ - for_each_set_bit(pagenr, rbio->dbitmap, rbio->stripe_npages) { - struct page *page; + for_each_set_bit(sectornr, rbio->dbitmap, rbio->stripe_nsectors) { + struct sector_ptr *sector; - page = rbio_stripe_page(rbio, rbio->scrubp, pagenr); - ret = rbio_add_io_page(rbio, &bio_list, - page, rbio->scrubp, pagenr, rbio->stripe_len); + sector = rbio_stripe_sector(rbio, rbio->scrubp, sectornr); + ret = rbio_add_io_sector(rbio, &bio_list, sector, rbio->scrubp, + sectornr, rbio->stripe_len, REQ_OP_WRITE); if (ret) goto cleanup; } @@ -2428,13 +2560,13 @@ writeback: if (!is_replace) goto submit_write; - for_each_set_bit(pagenr, pbitmap, rbio->stripe_npages) { - struct page *page; + for_each_set_bit(sectornr, pbitmap, rbio->stripe_nsectors) { + struct sector_ptr *sector; - page = rbio_stripe_page(rbio, rbio->scrubp, pagenr); - ret = rbio_add_io_page(rbio, &bio_list, page, + sector = rbio_stripe_sector(rbio, rbio->scrubp, sectornr); + ret = rbio_add_io_sector(rbio, &bio_list, sector, bioc->tgtdev_map[rbio->scrubp], - pagenr, rbio->stripe_len); + sectornr, rbio->stripe_len, REQ_OP_WRITE); if (ret) goto cleanup; } @@ -2450,9 +2582,7 @@ submit_write: atomic_set(&rbio->stripes_pending, nr_data); while ((bio = bio_list_pop(&bio_list))) { - bio->bi_private = rbio; bio->bi_end_io = raid_write_end_io; - bio->bi_opf = REQ_OP_WRITE; submit_bio(bio); } @@ -2548,7 +2678,7 @@ static void raid56_parity_scrub_end_io(struct bio *bio) if (bio->bi_status) fail_bio_stripe(rbio, bio); else - set_bio_pages_uptodate(bio); + set_bio_pages_uptodate(rbio, bio); bio_put(bio); @@ -2568,7 +2698,7 @@ static void raid56_parity_scrub_stripe(struct btrfs_raid_bio *rbio) int bios_to_read = 0; struct bio_list bio_list; int ret; - int pagenr; + int sectornr; int stripe; struct bio *bio; @@ -2584,28 +2714,29 @@ static void raid56_parity_scrub_stripe(struct btrfs_raid_bio *rbio) * stripe */ for (stripe = 0; stripe < rbio->real_stripes; stripe++) { - for_each_set_bit(pagenr, rbio->dbitmap, rbio->stripe_npages) { - struct page *page; + for_each_set_bit(sectornr , rbio->dbitmap, rbio->stripe_nsectors) { + struct sector_ptr *sector; /* - * we want to find all the pages missing from - * the rbio and read them from the disk. If - * page_in_rbio finds a page in the bio list - * we don't need to read it off the stripe. + * We want to find all the sectors missing from the + * rbio and read them from the disk. If * sector_in_rbio() + * finds a sector in the bio list we don't need to read + * it off the stripe. */ - page = page_in_rbio(rbio, stripe, pagenr, 1); - if (page) + sector = sector_in_rbio(rbio, stripe, sectornr, 1); + if (sector) continue; - page = rbio_stripe_page(rbio, stripe, pagenr); + sector = rbio_stripe_sector(rbio, stripe, sectornr); /* - * the bio cache may have handed us an uptodate - * page. If so, be happy and use it + * The bio cache may have handed us an uptodate sector. + * If so, be happy and use it. */ - if (PageUptodate(page)) + if (sector->uptodate) continue; - ret = rbio_add_io_page(rbio, &bio_list, page, - stripe, pagenr, rbio->stripe_len); + ret = rbio_add_io_sector(rbio, &bio_list, sector, + stripe, sectornr, rbio->stripe_len, + REQ_OP_READ); if (ret) goto cleanup; } @@ -2628,9 +2759,7 @@ static void raid56_parity_scrub_stripe(struct btrfs_raid_bio *rbio) */ atomic_set(&rbio->stripes_pending, bios_to_read); while ((bio = bio_list_pop(&bio_list))) { - bio->bi_private = rbio; bio->bi_end_io = raid56_parity_scrub_end_io; - bio->bi_opf = REQ_OP_READ; btrfs_bio_wq_end_io(rbio->bioc->fs_info, bio, BTRFS_WQ_ENDIO_RAID56); @@ -2651,7 +2780,7 @@ finish: validate_rbio_for_parity_scrub(rbio); } -static void scrub_parity_work(struct btrfs_work *work) +static void scrub_parity_work(struct work_struct *work) { struct btrfs_raid_bio *rbio; diff --git a/fs/btrfs/raid56.h b/fs/btrfs/raid56.h index 72c00fc284b5..aaad08aefd7d 100644 --- a/fs/btrfs/raid56.h +++ b/fs/btrfs/raid56.h @@ -31,15 +31,14 @@ struct btrfs_raid_bio; struct btrfs_device; int raid56_parity_recover(struct bio *bio, struct btrfs_io_context *bioc, - u64 stripe_len, int mirror_num, int generic_io); -int raid56_parity_write(struct bio *bio, struct btrfs_io_context *bioc, - u64 stripe_len); + u32 stripe_len, int mirror_num, int generic_io); +int raid56_parity_write(struct bio *bio, struct btrfs_io_context *bioc, u32 stripe_len); void raid56_add_scrub_pages(struct btrfs_raid_bio *rbio, struct page *page, - u64 logical); + unsigned int pgoff, u64 logical); struct btrfs_raid_bio *raid56_parity_alloc_scrub_rbio(struct bio *bio, - struct btrfs_io_context *bioc, u64 stripe_len, + struct btrfs_io_context *bioc, u32 stripe_len, struct btrfs_device *scrub_dev, unsigned long *dbitmap, int stripe_nsectors); void raid56_parity_submit_scrub_rbio(struct btrfs_raid_bio *rbio); diff --git a/fs/btrfs/reflink.c b/fs/btrfs/reflink.c index 998e3f180d90..c39f8b3a5a4a 100644 --- a/fs/btrfs/reflink.c +++ b/fs/btrfs/reflink.c @@ -614,14 +614,23 @@ static void btrfs_double_extent_unlock(struct inode *inode1, u64 loff1, static void btrfs_double_extent_lock(struct inode *inode1, u64 loff1, struct inode *inode2, u64 loff2, u64 len) { + u64 range1_end = loff1 + len - 1; + u64 range2_end = loff2 + len - 1; + if (inode1 < inode2) { swap(inode1, inode2); swap(loff1, loff2); + swap(range1_end, range2_end); } else if (inode1 == inode2 && loff2 < loff1) { swap(loff1, loff2); + swap(range1_end, range2_end); } - lock_extent(&BTRFS_I(inode1)->io_tree, loff1, loff1 + len - 1); - lock_extent(&BTRFS_I(inode2)->io_tree, loff2, loff2 + len - 1); + + lock_extent(&BTRFS_I(inode1)->io_tree, loff1, range1_end); + lock_extent(&BTRFS_I(inode2)->io_tree, loff2, range2_end); + + btrfs_assert_inode_range_clean(BTRFS_I(inode1), loff1, range1_end); + btrfs_assert_inode_range_clean(BTRFS_I(inode2), loff2, range2_end); } static void btrfs_double_mmap_lock(struct inode *inode1, struct inode *inode2) @@ -771,7 +780,6 @@ static int btrfs_remap_file_range_prep(struct file *file_in, loff_t pos_in, struct inode *inode_in = file_inode(file_in); struct inode *inode_out = file_inode(file_out); u64 bs = BTRFS_I(inode_out)->root->fs_info->sb->s_blocksize; - bool same_inode = inode_out == inode_in; u64 wb_len; int ret; @@ -810,15 +818,6 @@ static int btrfs_remap_file_range_prep(struct file *file_in, loff_t pos_in, wb_len = ALIGN(*len, bs); /* - * Since we don't lock ranges, wait for ongoing lockless dio writes (as - * any in progress could create its ordered extents after we wait for - * existing ordered extents below). - */ - inode_dio_wait(inode_in); - if (!same_inode) - inode_dio_wait(inode_out); - - /* * Workaround to make sure NOCOW buffered write reach disk as NOCOW. * * Btrfs' back references do not have a block level granularity, they diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index fdc2c4b411f0..a6dc827e75af 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -362,7 +362,7 @@ struct btrfs_root *find_reloc_root(struct btrfs_fs_info *fs_info, u64 bytenr) rb_node = rb_simple_search(&rc->reloc_root_tree.rb_root, bytenr); if (rb_node) { node = rb_entry(rb_node, struct mapping_node, rb_node); - root = (struct btrfs_root *)node->data; + root = node->data; } spin_unlock(&rc->reloc_root_tree.lock); return btrfs_grab_root(root); @@ -1101,7 +1101,7 @@ int replace_file_extents(struct btrfs_trans_handle *trans, continue; /* - * if we are modifying block in fs tree, wait for readpage + * if we are modifying block in fs tree, wait for read_folio * to complete and drop the extent cache */ if (root->root_key.objectid != BTRFS_TREE_RELOC_OBJECTID) { @@ -1563,7 +1563,7 @@ static int invalidate_extent_cache(struct btrfs_root *root, end = (u64)-1; } - /* the lock_extent waits for readpage to complete */ + /* the lock_extent waits for read_folio to complete */ lock_extent(&BTRFS_I(inode)->io_tree, start, end); btrfs_drop_extent_cache(BTRFS_I(inode), start, end, 1); unlock_extent(&BTRFS_I(inode)->io_tree, start, end); @@ -2818,7 +2818,7 @@ static noinline_for_stack int prealloc_file_extent_cluster( * Subpage can't handle page with DIRTY but without UPTODATE * bit as it can lead to the following deadlock: * - * btrfs_readpage() + * btrfs_read_folio() * | Page already *locked* * |- btrfs_lock_and_flush_ordered_range() * |- btrfs_start_ordered_extent() @@ -2967,11 +2967,12 @@ static int relocate_one_page(struct inode *inode, struct file_ra_state *ra, goto release_page; if (PageReadahead(page)) - page_cache_async_readahead(inode->i_mapping, ra, NULL, page, - page_index, last_index + 1 - page_index); + page_cache_async_readahead(inode->i_mapping, ra, NULL, + page_folio(page), page_index, + last_index + 1 - page_index); if (!PageUptodate(page)) { - btrfs_readpage(NULL, page); + btrfs_read_folio(NULL, page_folio(page)); lock_page(page); if (!PageUptodate(page)) { ret = -EIO; @@ -2997,7 +2998,8 @@ static int relocate_one_page(struct inode *inode, struct file_ra_state *ra, /* Reserve metadata for this range */ ret = btrfs_delalloc_reserve_metadata(BTRFS_I(inode), - clamped_len, clamped_len); + clamped_len, clamped_len, + false); if (ret) goto release_page; @@ -3845,8 +3847,7 @@ out: btrfs_end_transaction(trans); btrfs_btree_balance_dirty(fs_info); if (err) { - if (inode) - iput(inode); + iput(inode); inode = ERR_PTR(err); } return inode; @@ -3977,6 +3978,17 @@ int btrfs_relocate_block_group(struct btrfs_fs_info *fs_info, u64 group_start) if (!bg) return -ENOENT; + /* + * Relocation of a data block group creates ordered extents. Without + * sb_start_write(), we can freeze the filesystem while unfinished + * ordered extents are left. Such ordered extents can cause a deadlock + * e.g. when syncfs() is waiting for their completion but they can't + * finish because they block when joining a transaction, due to the + * fact that the freeze locks are being held in write mode. + */ + if (bg->flags & BTRFS_BLOCK_GROUP_DATA) + ASSERT(sb_write_started(fs_info->sb)); + if (btrfs_pinned_by_swapfile(fs_info, bg)) { btrfs_put_block_group(bg); return -ETXTBSY; diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c index ca7426ef61c8..a64b26b16904 100644 --- a/fs/btrfs/root-tree.c +++ b/fs/btrfs/root-tree.c @@ -509,7 +509,8 @@ int btrfs_subvolume_reserve_metadata(struct btrfs_root *root, /* One for parent inode, two for dir entries */ qgroup_num_bytes = 3 * fs_info->nodesize; ret = btrfs_qgroup_reserve_meta_prealloc(root, - qgroup_num_bytes, true); + qgroup_num_bytes, true, + false); if (ret) return ret; } diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 11089568b287..e7b0323e6efd 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -45,14 +45,14 @@ struct scrub_ctx; * operations. The first one configures an upper limit for the number * of (dynamically allocated) pages that are added to a bio. */ -#define SCRUB_PAGES_PER_BIO 32 /* 128KiB per bio for x86 */ -#define SCRUB_BIOS_PER_SCTX 64 /* 8MiB per device in flight for x86 */ +#define SCRUB_SECTORS_PER_BIO 32 /* 128KiB per bio for 4KiB pages */ +#define SCRUB_BIOS_PER_SCTX 64 /* 8MiB per device in flight for 4KiB pages */ /* * The following value times PAGE_SIZE needs to be large enough to match the * largest node/leaf/sector size that shall be supported. */ -#define SCRUB_MAX_PAGES_PER_BLOCK (BTRFS_MAX_METADATA_BLOCKSIZE / SZ_4K) +#define SCRUB_MAX_SECTORS_PER_BLOCK (BTRFS_MAX_METADATA_BLOCKSIZE / SZ_4K) struct scrub_recover { refcount_t refs; @@ -60,7 +60,7 @@ struct scrub_recover { u64 map_length; }; -struct scrub_page { +struct scrub_sector { struct scrub_block *sblock; struct page *page; struct btrfs_device *dev; @@ -87,16 +87,16 @@ struct scrub_bio { blk_status_t status; u64 logical; u64 physical; - struct scrub_page *pagev[SCRUB_PAGES_PER_BIO]; - int page_count; + struct scrub_sector *sectors[SCRUB_SECTORS_PER_BIO]; + int sector_count; int next_free; - struct btrfs_work work; + struct work_struct work; }; struct scrub_block { - struct scrub_page *pagev[SCRUB_MAX_PAGES_PER_BLOCK]; - int page_count; - atomic_t outstanding_pages; + struct scrub_sector *sectors[SCRUB_MAX_SECTORS_PER_BLOCK]; + int sector_count; + atomic_t outstanding_sectors; refcount_t refs; /* free mem on transition to zero */ struct scrub_ctx *sctx; struct scrub_parity *sparity; @@ -110,7 +110,7 @@ struct scrub_block { /* It is for the data with checksum */ unsigned int data_corrected:1; }; - struct btrfs_work work; + struct work_struct work; }; /* Used for the chunks with parity stripe such RAID5/6 */ @@ -129,10 +129,10 @@ struct scrub_parity { refcount_t refs; - struct list_head spages; + struct list_head sectors_list; /* Work of parity check and repair */ - struct btrfs_work work; + struct work_struct work; /* Mark the parity blocks which have data */ unsigned long *dbitmap; @@ -158,7 +158,7 @@ struct scrub_ctx { struct list_head csum_list; atomic_t cancel_req; int readonly; - int pages_per_bio; + int sectors_per_bio; /* State of IO submission throttling affecting the associated device */ ktime_t throttle_deadline; @@ -212,43 +212,43 @@ static void scrub_recheck_block(struct btrfs_fs_info *fs_info, static void scrub_recheck_block_checksum(struct scrub_block *sblock); static int scrub_repair_block_from_good_copy(struct scrub_block *sblock_bad, struct scrub_block *sblock_good); -static int scrub_repair_page_from_good_copy(struct scrub_block *sblock_bad, +static int scrub_repair_sector_from_good_copy(struct scrub_block *sblock_bad, struct scrub_block *sblock_good, - int page_num, int force_write); + int sector_num, int force_write); static void scrub_write_block_to_dev_replace(struct scrub_block *sblock); -static int scrub_write_page_to_dev_replace(struct scrub_block *sblock, - int page_num); +static int scrub_write_sector_to_dev_replace(struct scrub_block *sblock, + int sector_num); static int scrub_checksum_data(struct scrub_block *sblock); static int scrub_checksum_tree_block(struct scrub_block *sblock); static int scrub_checksum_super(struct scrub_block *sblock); static void scrub_block_put(struct scrub_block *sblock); -static void scrub_page_get(struct scrub_page *spage); -static void scrub_page_put(struct scrub_page *spage); +static void scrub_sector_get(struct scrub_sector *sector); +static void scrub_sector_put(struct scrub_sector *sector); static void scrub_parity_get(struct scrub_parity *sparity); static void scrub_parity_put(struct scrub_parity *sparity); -static int scrub_pages(struct scrub_ctx *sctx, u64 logical, u32 len, - u64 physical, struct btrfs_device *dev, u64 flags, - u64 gen, int mirror_num, u8 *csum, - u64 physical_for_dev_replace); +static int scrub_sectors(struct scrub_ctx *sctx, u64 logical, u32 len, + u64 physical, struct btrfs_device *dev, u64 flags, + u64 gen, int mirror_num, u8 *csum, + u64 physical_for_dev_replace); static void scrub_bio_end_io(struct bio *bio); -static void scrub_bio_end_io_worker(struct btrfs_work *work); +static void scrub_bio_end_io_worker(struct work_struct *work); static void scrub_block_complete(struct scrub_block *sblock); -static void scrub_remap_extent(struct btrfs_fs_info *fs_info, - u64 extent_logical, u32 extent_len, - u64 *extent_physical, - struct btrfs_device **extent_dev, - int *extent_mirror_num); -static int scrub_add_page_to_wr_bio(struct scrub_ctx *sctx, - struct scrub_page *spage); +static void scrub_find_good_copy(struct btrfs_fs_info *fs_info, + u64 extent_logical, u32 extent_len, + u64 *extent_physical, + struct btrfs_device **extent_dev, + int *extent_mirror_num); +static int scrub_add_sector_to_wr_bio(struct scrub_ctx *sctx, + struct scrub_sector *sector); static void scrub_wr_submit(struct scrub_ctx *sctx); static void scrub_wr_bio_end_io(struct bio *bio); -static void scrub_wr_bio_end_io_worker(struct btrfs_work *work); +static void scrub_wr_bio_end_io_worker(struct work_struct *work); static void scrub_put_ctx(struct scrub_ctx *sctx); -static inline int scrub_is_page_on_raid56(struct scrub_page *spage) +static inline int scrub_is_page_on_raid56(struct scrub_sector *sector) { - return spage->recover && - (spage->recover->bioc->map_type & BTRFS_BLOCK_GROUP_RAID56_MASK); + return sector->recover && + (sector->recover->bioc->map_type & BTRFS_BLOCK_GROUP_RAID56_MASK); } static void scrub_pending_bio_inc(struct scrub_ctx *sctx) @@ -535,9 +535,9 @@ static noinline_for_stack void scrub_free_ctx(struct scrub_ctx *sctx) if (sctx->curr != -1) { struct scrub_bio *sbio = sctx->bios[sctx->curr]; - for (i = 0; i < sbio->page_count; i++) { - WARN_ON(!sbio->pagev[i]->page); - scrub_block_put(sbio->pagev[i]->sblock); + for (i = 0; i < sbio->sector_count; i++) { + WARN_ON(!sbio->sectors[i]->page); + scrub_block_put(sbio->sectors[i]->sblock); } bio_put(sbio->bio); } @@ -572,7 +572,7 @@ static noinline_for_stack struct scrub_ctx *scrub_setup_ctx( goto nomem; refcount_set(&sctx->refs, 1); sctx->is_dev_replace = is_dev_replace; - sctx->pages_per_bio = SCRUB_PAGES_PER_BIO; + sctx->sectors_per_bio = SCRUB_SECTORS_PER_BIO; sctx->curr = -1; sctx->fs_info = fs_info; INIT_LIST_HEAD(&sctx->csum_list); @@ -586,9 +586,8 @@ static noinline_for_stack struct scrub_ctx *scrub_setup_ctx( sbio->index = i; sbio->sctx = sctx; - sbio->page_count = 0; - btrfs_init_work(&sbio->work, scrub_bio_end_io_worker, NULL, - NULL); + sbio->sector_count = 0; + INIT_WORK(&sbio->work, scrub_bio_end_io_worker); if (i != SCRUB_BIOS_PER_SCTX - 1) sctx->bios[i]->next_free = i + 1; @@ -728,16 +727,16 @@ static void scrub_print_warning(const char *errstr, struct scrub_block *sblock) u8 ref_level = 0; int ret; - WARN_ON(sblock->page_count < 1); - dev = sblock->pagev[0]->dev; + WARN_ON(sblock->sector_count < 1); + dev = sblock->sectors[0]->dev; fs_info = sblock->sctx->fs_info; path = btrfs_alloc_path(); if (!path) return; - swarn.physical = sblock->pagev[0]->physical; - swarn.logical = sblock->pagev[0]->logical; + swarn.physical = sblock->sectors[0]->physical; + swarn.logical = sblock->sectors[0]->logical; swarn.errstr = errstr; swarn.dev = NULL; @@ -798,8 +797,8 @@ static inline void scrub_put_recover(struct btrfs_fs_info *fs_info, /* * scrub_handle_errored_block gets called when either verification of the - * pages failed or the bio failed to read, e.g. with EIO. In the latter - * case, this function handles all pages in the bio, even though only one + * sectors failed or the bio failed to read, e.g. with EIO. In the latter + * case, this function handles all sectors in the bio, even though only one * may be bad. * The goal of this function is to repair the errored block by using the * contents of one of the mirrors. @@ -817,16 +816,16 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check) struct scrub_block *sblock_bad; int ret; int mirror_index; - int page_num; + int sector_num; int success; bool full_stripe_locked; unsigned int nofs_flag; static DEFINE_RATELIMIT_STATE(rs, DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST); - BUG_ON(sblock_to_check->page_count < 1); + BUG_ON(sblock_to_check->sector_count < 1); fs_info = sctx->fs_info; - if (sblock_to_check->pagev[0]->flags & BTRFS_EXTENT_FLAG_SUPER) { + if (sblock_to_check->sectors[0]->flags & BTRFS_EXTENT_FLAG_SUPER) { /* * if we find an error in a super block, we just report it. * They will get written with the next transaction commit @@ -837,13 +836,13 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check) spin_unlock(&sctx->stat_lock); return 0; } - logical = sblock_to_check->pagev[0]->logical; - BUG_ON(sblock_to_check->pagev[0]->mirror_num < 1); - failed_mirror_index = sblock_to_check->pagev[0]->mirror_num - 1; - is_metadata = !(sblock_to_check->pagev[0]->flags & + logical = sblock_to_check->sectors[0]->logical; + BUG_ON(sblock_to_check->sectors[0]->mirror_num < 1); + failed_mirror_index = sblock_to_check->sectors[0]->mirror_num - 1; + is_metadata = !(sblock_to_check->sectors[0]->flags & BTRFS_EXTENT_FLAG_DATA); - have_csum = sblock_to_check->pagev[0]->have_csum; - dev = sblock_to_check->pagev[0]->dev; + have_csum = sblock_to_check->sectors[0]->have_csum; + dev = sblock_to_check->sectors[0]->dev; if (!sctx->is_dev_replace && btrfs_repair_one_zone(fs_info, logical)) return 0; @@ -854,7 +853,7 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check) * might be waiting the scrub task to pause (which needs to wait for all * the worker tasks to complete before pausing). * We do allocations in the workers through insert_full_stripe_lock() - * and scrub_add_page_to_wr_bio(), which happens down the call chain of + * and scrub_add_sector_to_wr_bio(), which happens down the call chain of * this function. */ nofs_flag = memalloc_nofs_save(); @@ -918,7 +917,7 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check) goto out; } - /* setup the context, map the logical blocks and alloc the pages */ + /* Setup the context, map the logical blocks and alloc the sectors */ ret = scrub_setup_recheck_block(sblock_to_check, sblocks_for_recheck); if (ret) { spin_lock(&sctx->stat_lock); @@ -937,7 +936,7 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check) if (!sblock_bad->header_error && !sblock_bad->checksum_error && sblock_bad->no_io_error_seen) { /* - * the error disappeared after reading page by page, or + * The error disappeared after reading sector by sector, or * the area was part of a huge bio and other parts of the * bio caused I/O errors, or the block layer merged several * read requests into one and the error is caused by a @@ -998,10 +997,10 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check) * that is known to contain an error is rewritten. Afterwards * the block is known to be corrected. * If a mirror is found which is completely correct, and no - * checksum is present, only those pages are rewritten that had + * checksum is present, only those sectors are rewritten that had * an I/O error in the block to be repaired, since it cannot be - * determined, which copy of the other pages is better (and it - * could happen otherwise that a correct page would be + * determined, which copy of the other sectors is better (and it + * could happen otherwise that a correct sector would be * overwritten by a bad one). */ for (mirror_index = 0; ;mirror_index++) { @@ -1011,25 +1010,25 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check) continue; /* raid56's mirror can be more than BTRFS_MAX_MIRRORS */ - if (!scrub_is_page_on_raid56(sblock_bad->pagev[0])) { + if (!scrub_is_page_on_raid56(sblock_bad->sectors[0])) { if (mirror_index >= BTRFS_MAX_MIRRORS) break; - if (!sblocks_for_recheck[mirror_index].page_count) + if (!sblocks_for_recheck[mirror_index].sector_count) break; sblock_other = sblocks_for_recheck + mirror_index; } else { - struct scrub_recover *r = sblock_bad->pagev[0]->recover; + struct scrub_recover *r = sblock_bad->sectors[0]->recover; int max_allowed = r->bioc->num_stripes - r->bioc->num_tgtdevs; if (mirror_index >= max_allowed) break; - if (!sblocks_for_recheck[1].page_count) + if (!sblocks_for_recheck[1].sector_count) break; ASSERT(failed_mirror_index == 0); sblock_other = sblocks_for_recheck + 1; - sblock_other->pagev[0]->mirror_num = 1 + mirror_index; + sblock_other->sectors[0]->mirror_num = 1 + mirror_index; } /* build and submit the bios, check checksums */ @@ -1078,16 +1077,16 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check) * area are unreadable. */ success = 1; - for (page_num = 0; page_num < sblock_bad->page_count; - page_num++) { - struct scrub_page *spage_bad = sblock_bad->pagev[page_num]; + for (sector_num = 0; sector_num < sblock_bad->sector_count; + sector_num++) { + struct scrub_sector *sector_bad = sblock_bad->sectors[sector_num]; struct scrub_block *sblock_other = NULL; - /* skip no-io-error page in scrub */ - if (!spage_bad->io_error && !sctx->is_dev_replace) + /* Skip no-io-error sectors in scrub */ + if (!sector_bad->io_error && !sctx->is_dev_replace) continue; - if (scrub_is_page_on_raid56(sblock_bad->pagev[0])) { + if (scrub_is_page_on_raid56(sblock_bad->sectors[0])) { /* * In case of dev replace, if raid56 rebuild process * didn't work out correct data, then copy the content @@ -1096,14 +1095,14 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check) * sblock_for_recheck array to target device. */ sblock_other = NULL; - } else if (spage_bad->io_error) { - /* try to find no-io-error page in mirrors */ + } else if (sector_bad->io_error) { + /* Try to find no-io-error sector in mirrors */ for (mirror_index = 0; mirror_index < BTRFS_MAX_MIRRORS && - sblocks_for_recheck[mirror_index].page_count > 0; + sblocks_for_recheck[mirror_index].sector_count > 0; mirror_index++) { if (!sblocks_for_recheck[mirror_index]. - pagev[page_num]->io_error) { + sectors[sector_num]->io_error) { sblock_other = sblocks_for_recheck + mirror_index; break; @@ -1115,27 +1114,26 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check) if (sctx->is_dev_replace) { /* - * did not find a mirror to fetch the page - * from. scrub_write_page_to_dev_replace() - * handles this case (page->io_error), by - * filling the block with zeros before - * submitting the write request + * Did not find a mirror to fetch the sector from. + * scrub_write_sector_to_dev_replace() handles this + * case (sector->io_error), by filling the block with + * zeros before submitting the write request */ if (!sblock_other) sblock_other = sblock_bad; - if (scrub_write_page_to_dev_replace(sblock_other, - page_num) != 0) { + if (scrub_write_sector_to_dev_replace(sblock_other, + sector_num) != 0) { atomic64_inc( &fs_info->dev_replace.num_write_errors); success = 0; } } else if (sblock_other) { - ret = scrub_repair_page_from_good_copy(sblock_bad, - sblock_other, - page_num, 0); + ret = scrub_repair_sector_from_good_copy(sblock_bad, + sblock_other, + sector_num, 0); if (0 == ret) - spage_bad->io_error = 0; + sector_bad->io_error = 0; else success = 0; } @@ -1186,18 +1184,16 @@ out: struct scrub_block *sblock = sblocks_for_recheck + mirror_index; struct scrub_recover *recover; - int page_index; + int i; - for (page_index = 0; page_index < sblock->page_count; - page_index++) { - sblock->pagev[page_index]->sblock = NULL; - recover = sblock->pagev[page_index]->recover; + for (i = 0; i < sblock->sector_count; i++) { + sblock->sectors[i]->sblock = NULL; + recover = sblock->sectors[i]->recover; if (recover) { scrub_put_recover(fs_info, recover); - sblock->pagev[page_index]->recover = - NULL; + sblock->sectors[i]->recover = NULL; } - scrub_page_put(sblock->pagev[page_index]); + scrub_sector_put(sblock->sectors[i]); } } kfree(sblocks_for_recheck); @@ -1255,26 +1251,25 @@ static int scrub_setup_recheck_block(struct scrub_block *original_sblock, { struct scrub_ctx *sctx = original_sblock->sctx; struct btrfs_fs_info *fs_info = sctx->fs_info; - u64 length = original_sblock->page_count * fs_info->sectorsize; - u64 logical = original_sblock->pagev[0]->logical; - u64 generation = original_sblock->pagev[0]->generation; - u64 flags = original_sblock->pagev[0]->flags; - u64 have_csum = original_sblock->pagev[0]->have_csum; + u64 length = original_sblock->sector_count << fs_info->sectorsize_bits; + u64 logical = original_sblock->sectors[0]->logical; + u64 generation = original_sblock->sectors[0]->generation; + u64 flags = original_sblock->sectors[0]->flags; + u64 have_csum = original_sblock->sectors[0]->have_csum; struct scrub_recover *recover; struct btrfs_io_context *bioc; u64 sublen; u64 mapped_length; u64 stripe_offset; int stripe_index; - int page_index = 0; + int sector_index = 0; int mirror_index; int nmirrors; int ret; /* - * note: the two members refs and outstanding_pages - * are not used (and not set) in the blocks that are used for - * the recheck procedure + * Note: the two members refs and outstanding_sectors are not used (and + * not set) in the blocks that are used for the recheck procedure. */ while (length > 0) { @@ -1306,20 +1301,20 @@ static int scrub_setup_recheck_block(struct scrub_block *original_sblock, recover->bioc = bioc; recover->map_length = mapped_length; - ASSERT(page_index < SCRUB_MAX_PAGES_PER_BLOCK); + ASSERT(sector_index < SCRUB_MAX_SECTORS_PER_BLOCK); nmirrors = min(scrub_nr_raid_mirrors(bioc), BTRFS_MAX_MIRRORS); for (mirror_index = 0; mirror_index < nmirrors; mirror_index++) { struct scrub_block *sblock; - struct scrub_page *spage; + struct scrub_sector *sector; sblock = sblocks_for_recheck + mirror_index; sblock->sctx = sctx; - spage = kzalloc(sizeof(*spage), GFP_NOFS); - if (!spage) { + sector = kzalloc(sizeof(*sector), GFP_NOFS); + if (!sector) { leave_nomem: spin_lock(&sctx->stat_lock); sctx->stat.malloc_errors++; @@ -1327,16 +1322,16 @@ leave_nomem: scrub_put_recover(fs_info, recover); return -ENOMEM; } - scrub_page_get(spage); - sblock->pagev[page_index] = spage; - spage->sblock = sblock; - spage->flags = flags; - spage->generation = generation; - spage->logical = logical; - spage->have_csum = have_csum; + scrub_sector_get(sector); + sblock->sectors[sector_index] = sector; + sector->sblock = sblock; + sector->flags = flags; + sector->generation = generation; + sector->logical = logical; + sector->have_csum = have_csum; if (have_csum) - memcpy(spage->csum, - original_sblock->pagev[0]->csum, + memcpy(sector->csum, + original_sblock->sectors[0]->csum, sctx->fs_info->csum_size); scrub_stripe_index_and_offset(logical, @@ -1348,28 +1343,28 @@ leave_nomem: mirror_index, &stripe_index, &stripe_offset); - spage->physical = bioc->stripes[stripe_index].physical + + sector->physical = bioc->stripes[stripe_index].physical + stripe_offset; - spage->dev = bioc->stripes[stripe_index].dev; + sector->dev = bioc->stripes[stripe_index].dev; - BUG_ON(page_index >= original_sblock->page_count); - spage->physical_for_dev_replace = - original_sblock->pagev[page_index]-> + BUG_ON(sector_index >= original_sblock->sector_count); + sector->physical_for_dev_replace = + original_sblock->sectors[sector_index]-> physical_for_dev_replace; - /* for missing devices, dev->bdev is NULL */ - spage->mirror_num = mirror_index + 1; - sblock->page_count++; - spage->page = alloc_page(GFP_NOFS); - if (!spage->page) + /* For missing devices, dev->bdev is NULL */ + sector->mirror_num = mirror_index + 1; + sblock->sector_count++; + sector->page = alloc_page(GFP_NOFS); + if (!sector->page) goto leave_nomem; scrub_get_recover(recover); - spage->recover = recover; + sector->recover = recover; } scrub_put_recover(fs_info, recover); length -= sublen; logical += sublen; - page_index++; + sector_index++; } return 0; @@ -1382,19 +1377,19 @@ static void scrub_bio_wait_endio(struct bio *bio) static int scrub_submit_raid56_bio_wait(struct btrfs_fs_info *fs_info, struct bio *bio, - struct scrub_page *spage) + struct scrub_sector *sector) { DECLARE_COMPLETION_ONSTACK(done); int ret; int mirror_num; - bio->bi_iter.bi_sector = spage->logical >> 9; + bio->bi_iter.bi_sector = sector->logical >> 9; bio->bi_private = &done; bio->bi_end_io = scrub_bio_wait_endio; - mirror_num = spage->sblock->pagev[0]->mirror_num; - ret = raid56_parity_recover(bio, spage->recover->bioc, - spage->recover->map_length, + mirror_num = sector->sblock->sectors[0]->mirror_num; + ret = raid56_parity_recover(bio, sector->recover->bioc, + sector->recover->map_length, mirror_num, 0); if (ret) return ret; @@ -1406,26 +1401,25 @@ static int scrub_submit_raid56_bio_wait(struct btrfs_fs_info *fs_info, static void scrub_recheck_block_on_raid56(struct btrfs_fs_info *fs_info, struct scrub_block *sblock) { - struct scrub_page *first_page = sblock->pagev[0]; + struct scrub_sector *first_sector = sblock->sectors[0]; struct bio *bio; - int page_num; + int i; - /* All pages in sblock belong to the same stripe on the same device. */ - ASSERT(first_page->dev); - if (!first_page->dev->bdev) + /* All sectors in sblock belong to the same stripe on the same device. */ + ASSERT(first_sector->dev); + if (!first_sector->dev->bdev) goto out; - bio = btrfs_bio_alloc(BIO_MAX_VECS); - bio_set_dev(bio, first_page->dev->bdev); + bio = bio_alloc(first_sector->dev->bdev, BIO_MAX_VECS, REQ_OP_READ, GFP_NOFS); - for (page_num = 0; page_num < sblock->page_count; page_num++) { - struct scrub_page *spage = sblock->pagev[page_num]; + for (i = 0; i < sblock->sector_count; i++) { + struct scrub_sector *sector = sblock->sectors[i]; - WARN_ON(!spage->page); - bio_add_page(bio, spage->page, PAGE_SIZE, 0); + WARN_ON(!sector->page); + bio_add_page(bio, sector->page, PAGE_SIZE, 0); } - if (scrub_submit_raid56_bio_wait(fs_info, bio, first_page)) { + if (scrub_submit_raid56_bio_wait(fs_info, bio, first_sector)) { bio_put(bio); goto out; } @@ -1436,65 +1430,63 @@ static void scrub_recheck_block_on_raid56(struct btrfs_fs_info *fs_info, return; out: - for (page_num = 0; page_num < sblock->page_count; page_num++) - sblock->pagev[page_num]->io_error = 1; + for (i = 0; i < sblock->sector_count; i++) + sblock->sectors[i]->io_error = 1; sblock->no_io_error_seen = 0; } /* - * this function will check the on disk data for checksum errors, header - * errors and read I/O errors. If any I/O errors happen, the exact pages - * which are errored are marked as being bad. The goal is to enable scrub - * to take those pages that are not errored from all the mirrors so that - * the pages that are errored in the just handled mirror can be repaired. + * This function will check the on disk data for checksum errors, header errors + * and read I/O errors. If any I/O errors happen, the exact sectors which are + * errored are marked as being bad. The goal is to enable scrub to take those + * sectors that are not errored from all the mirrors so that the sectors that + * are errored in the just handled mirror can be repaired. */ static void scrub_recheck_block(struct btrfs_fs_info *fs_info, struct scrub_block *sblock, int retry_failed_mirror) { - int page_num; + int i; sblock->no_io_error_seen = 1; /* short cut for raid56 */ - if (!retry_failed_mirror && scrub_is_page_on_raid56(sblock->pagev[0])) + if (!retry_failed_mirror && scrub_is_page_on_raid56(sblock->sectors[0])) return scrub_recheck_block_on_raid56(fs_info, sblock); - for (page_num = 0; page_num < sblock->page_count; page_num++) { - struct bio *bio; - struct scrub_page *spage = sblock->pagev[page_num]; + for (i = 0; i < sblock->sector_count; i++) { + struct scrub_sector *sector = sblock->sectors[i]; + struct bio bio; + struct bio_vec bvec; - if (spage->dev->bdev == NULL) { - spage->io_error = 1; + if (sector->dev->bdev == NULL) { + sector->io_error = 1; sblock->no_io_error_seen = 0; continue; } - WARN_ON(!spage->page); - bio = btrfs_bio_alloc(1); - bio_set_dev(bio, spage->dev->bdev); + WARN_ON(!sector->page); + bio_init(&bio, sector->dev->bdev, &bvec, 1, REQ_OP_READ); + bio_add_page(&bio, sector->page, fs_info->sectorsize, 0); + bio.bi_iter.bi_sector = sector->physical >> 9; - bio_add_page(bio, spage->page, fs_info->sectorsize, 0); - bio->bi_iter.bi_sector = spage->physical >> 9; - bio->bi_opf = REQ_OP_READ; - - if (btrfsic_submit_bio_wait(bio)) { - spage->io_error = 1; + btrfsic_check_bio(&bio); + if (submit_bio_wait(&bio)) { + sector->io_error = 1; sblock->no_io_error_seen = 0; } - bio_put(bio); + bio_uninit(&bio); } if (sblock->no_io_error_seen) scrub_recheck_block_checksum(sblock); } -static inline int scrub_check_fsid(u8 fsid[], - struct scrub_page *spage) +static inline int scrub_check_fsid(u8 fsid[], struct scrub_sector *sector) { - struct btrfs_fs_devices *fs_devices = spage->dev->fs_devices; + struct btrfs_fs_devices *fs_devices = sector->dev->fs_devices; int ret; ret = memcmp(fsid, fs_devices->fsid, BTRFS_FSID_SIZE); @@ -1507,7 +1499,7 @@ static void scrub_recheck_block_checksum(struct scrub_block *sblock) sblock->checksum_error = 0; sblock->generation_error = 0; - if (sblock->pagev[0]->flags & BTRFS_EXTENT_FLAG_DATA) + if (sblock->sectors[0]->flags & BTRFS_EXTENT_FLAG_DATA) scrub_checksum_data(sblock); else scrub_checksum_tree_block(sblock); @@ -1516,15 +1508,14 @@ static void scrub_recheck_block_checksum(struct scrub_block *sblock) static int scrub_repair_block_from_good_copy(struct scrub_block *sblock_bad, struct scrub_block *sblock_good) { - int page_num; + int i; int ret = 0; - for (page_num = 0; page_num < sblock_bad->page_count; page_num++) { + for (i = 0; i < sblock_bad->sector_count; i++) { int ret_sub; - ret_sub = scrub_repair_page_from_good_copy(sblock_bad, - sblock_good, - page_num, 1); + ret_sub = scrub_repair_sector_from_good_copy(sblock_bad, + sblock_good, i, 1); if (ret_sub) ret = ret_sub; } @@ -1532,47 +1523,43 @@ static int scrub_repair_block_from_good_copy(struct scrub_block *sblock_bad, return ret; } -static int scrub_repair_page_from_good_copy(struct scrub_block *sblock_bad, - struct scrub_block *sblock_good, - int page_num, int force_write) +static int scrub_repair_sector_from_good_copy(struct scrub_block *sblock_bad, + struct scrub_block *sblock_good, + int sector_num, int force_write) { - struct scrub_page *spage_bad = sblock_bad->pagev[page_num]; - struct scrub_page *spage_good = sblock_good->pagev[page_num]; + struct scrub_sector *sector_bad = sblock_bad->sectors[sector_num]; + struct scrub_sector *sector_good = sblock_good->sectors[sector_num]; struct btrfs_fs_info *fs_info = sblock_bad->sctx->fs_info; const u32 sectorsize = fs_info->sectorsize; - BUG_ON(spage_bad->page == NULL); - BUG_ON(spage_good->page == NULL); + BUG_ON(sector_bad->page == NULL); + BUG_ON(sector_good->page == NULL); if (force_write || sblock_bad->header_error || - sblock_bad->checksum_error || spage_bad->io_error) { - struct bio *bio; + sblock_bad->checksum_error || sector_bad->io_error) { + struct bio bio; + struct bio_vec bvec; int ret; - if (!spage_bad->dev->bdev) { + if (!sector_bad->dev->bdev) { btrfs_warn_rl(fs_info, "scrub_repair_page_from_good_copy(bdev == NULL) is unexpected"); return -EIO; } - bio = btrfs_bio_alloc(1); - bio_set_dev(bio, spage_bad->dev->bdev); - bio->bi_iter.bi_sector = spage_bad->physical >> 9; - bio->bi_opf = REQ_OP_WRITE; + bio_init(&bio, sector_bad->dev->bdev, &bvec, 1, REQ_OP_WRITE); + bio.bi_iter.bi_sector = sector_bad->physical >> 9; + __bio_add_page(&bio, sector_good->page, sectorsize, 0); - ret = bio_add_page(bio, spage_good->page, sectorsize, 0); - if (ret != sectorsize) { - bio_put(bio); - return -EIO; - } + btrfsic_check_bio(&bio); + ret = submit_bio_wait(&bio); + bio_uninit(&bio); - if (btrfsic_submit_bio_wait(bio)) { - btrfs_dev_stat_inc_and_print(spage_bad->dev, + if (ret) { + btrfs_dev_stat_inc_and_print(sector_bad->dev, BTRFS_DEV_STAT_WRITE_ERRS); atomic64_inc(&fs_info->dev_replace.num_write_errors); - bio_put(bio); return -EIO; } - bio_put(bio); } return 0; @@ -1581,7 +1568,7 @@ static int scrub_repair_page_from_good_copy(struct scrub_block *sblock_bad, static void scrub_write_block_to_dev_replace(struct scrub_block *sblock) { struct btrfs_fs_info *fs_info = sblock->sctx->fs_info; - int page_num; + int i; /* * This block is used for the check of the parity on the source device, @@ -1590,25 +1577,24 @@ static void scrub_write_block_to_dev_replace(struct scrub_block *sblock) if (sblock->sparity) return; - for (page_num = 0; page_num < sblock->page_count; page_num++) { + for (i = 0; i < sblock->sector_count; i++) { int ret; - ret = scrub_write_page_to_dev_replace(sblock, page_num); + ret = scrub_write_sector_to_dev_replace(sblock, i); if (ret) atomic64_inc(&fs_info->dev_replace.num_write_errors); } } -static int scrub_write_page_to_dev_replace(struct scrub_block *sblock, - int page_num) +static int scrub_write_sector_to_dev_replace(struct scrub_block *sblock, int sector_num) { - struct scrub_page *spage = sblock->pagev[page_num]; + struct scrub_sector *sector = sblock->sectors[sector_num]; - BUG_ON(spage->page == NULL); - if (spage->io_error) - clear_page(page_address(spage->page)); + BUG_ON(sector->page == NULL); + if (sector->io_error) + clear_page(page_address(sector->page)); - return scrub_add_page_to_wr_bio(sblock->sctx, spage); + return scrub_add_sector_to_wr_bio(sblock->sctx, sector); } static int fill_writer_pointer_gap(struct scrub_ctx *sctx, u64 physical) @@ -1633,8 +1619,8 @@ static int fill_writer_pointer_gap(struct scrub_ctx *sctx, u64 physical) return ret; } -static int scrub_add_page_to_wr_bio(struct scrub_ctx *sctx, - struct scrub_page *spage) +static int scrub_add_sector_to_wr_bio(struct scrub_ctx *sctx, + struct scrub_sector *sector) { struct scrub_bio *sbio; int ret; @@ -1650,45 +1636,38 @@ again: return -ENOMEM; } sctx->wr_curr_bio->sctx = sctx; - sctx->wr_curr_bio->page_count = 0; + sctx->wr_curr_bio->sector_count = 0; } sbio = sctx->wr_curr_bio; - if (sbio->page_count == 0) { - struct bio *bio; - - ret = fill_writer_pointer_gap(sctx, - spage->physical_for_dev_replace); + if (sbio->sector_count == 0) { + ret = fill_writer_pointer_gap(sctx, sector->physical_for_dev_replace); if (ret) { mutex_unlock(&sctx->wr_lock); return ret; } - sbio->physical = spage->physical_for_dev_replace; - sbio->logical = spage->logical; + sbio->physical = sector->physical_for_dev_replace; + sbio->logical = sector->logical; sbio->dev = sctx->wr_tgtdev; - bio = sbio->bio; - if (!bio) { - bio = btrfs_bio_alloc(sctx->pages_per_bio); - sbio->bio = bio; + if (!sbio->bio) { + sbio->bio = bio_alloc(sbio->dev->bdev, sctx->sectors_per_bio, + REQ_OP_WRITE, GFP_NOFS); } - - bio->bi_private = sbio; - bio->bi_end_io = scrub_wr_bio_end_io; - bio_set_dev(bio, sbio->dev->bdev); - bio->bi_iter.bi_sector = sbio->physical >> 9; - bio->bi_opf = REQ_OP_WRITE; + sbio->bio->bi_private = sbio; + sbio->bio->bi_end_io = scrub_wr_bio_end_io; + sbio->bio->bi_iter.bi_sector = sbio->physical >> 9; sbio->status = 0; - } else if (sbio->physical + sbio->page_count * sectorsize != - spage->physical_for_dev_replace || - sbio->logical + sbio->page_count * sectorsize != - spage->logical) { + } else if (sbio->physical + sbio->sector_count * sectorsize != + sector->physical_for_dev_replace || + sbio->logical + sbio->sector_count * sectorsize != + sector->logical) { scrub_wr_submit(sctx); goto again; } - ret = bio_add_page(sbio->bio, spage->page, sectorsize, 0); + ret = bio_add_page(sbio->bio, sector->page, sectorsize, 0); if (ret != sectorsize) { - if (sbio->page_count < 1) { + if (sbio->sector_count < 1) { bio_put(sbio->bio); sbio->bio = NULL; mutex_unlock(&sctx->wr_lock); @@ -1698,10 +1677,10 @@ again: goto again; } - sbio->pagev[sbio->page_count] = spage; - scrub_page_get(spage); - sbio->page_count++; - if (sbio->page_count == sctx->pages_per_bio) + sbio->sectors[sbio->sector_count] = sector; + scrub_sector_get(sector); + sbio->sector_count++; + if (sbio->sector_count == sctx->sectors_per_bio) scrub_wr_submit(sctx); mutex_unlock(&sctx->wr_lock); @@ -1717,16 +1696,16 @@ static void scrub_wr_submit(struct scrub_ctx *sctx) sbio = sctx->wr_curr_bio; sctx->wr_curr_bio = NULL; - WARN_ON(!sbio->bio->bi_bdev); scrub_pending_bio_inc(sctx); /* process all writes in a single worker thread. Then the block layer * orders the requests before sending them to the driver which * doubled the write performance on spinning disks when measured * with Linux 3.5 */ - btrfsic_submit_bio(sbio->bio); + btrfsic_check_bio(sbio->bio); + submit_bio(sbio->bio); if (btrfs_is_zoned(sctx->fs_info)) - sctx->write_pointer = sbio->physical + sbio->page_count * + sctx->write_pointer = sbio->physical + sbio->sector_count * sctx->fs_info->sectorsize; } @@ -1738,31 +1717,31 @@ static void scrub_wr_bio_end_io(struct bio *bio) sbio->status = bio->bi_status; sbio->bio = bio; - btrfs_init_work(&sbio->work, scrub_wr_bio_end_io_worker, NULL, NULL); - btrfs_queue_work(fs_info->scrub_wr_completion_workers, &sbio->work); + INIT_WORK(&sbio->work, scrub_wr_bio_end_io_worker); + queue_work(fs_info->scrub_wr_completion_workers, &sbio->work); } -static void scrub_wr_bio_end_io_worker(struct btrfs_work *work) +static void scrub_wr_bio_end_io_worker(struct work_struct *work) { struct scrub_bio *sbio = container_of(work, struct scrub_bio, work); struct scrub_ctx *sctx = sbio->sctx; int i; - ASSERT(sbio->page_count <= SCRUB_PAGES_PER_BIO); + ASSERT(sbio->sector_count <= SCRUB_SECTORS_PER_BIO); if (sbio->status) { struct btrfs_dev_replace *dev_replace = &sbio->sctx->fs_info->dev_replace; - for (i = 0; i < sbio->page_count; i++) { - struct scrub_page *spage = sbio->pagev[i]; + for (i = 0; i < sbio->sector_count; i++) { + struct scrub_sector *sector = sbio->sectors[i]; - spage->io_error = 1; + sector->io_error = 1; atomic64_inc(&dev_replace->num_write_errors); } } - for (i = 0; i < sbio->page_count; i++) - scrub_page_put(sbio->pagev[i]); + for (i = 0; i < sbio->sector_count; i++) + scrub_sector_put(sbio->sectors[i]); bio_put(sbio->bio); kfree(sbio); @@ -1786,8 +1765,8 @@ static int scrub_checksum(struct scrub_block *sblock) sblock->generation_error = 0; sblock->checksum_error = 0; - WARN_ON(sblock->page_count < 1); - flags = sblock->pagev[0]->flags; + WARN_ON(sblock->sector_count < 1); + flags = sblock->sectors[0]->flags; ret = 0; if (flags & BTRFS_EXTENT_FLAG_DATA) ret = scrub_checksum_data(sblock); @@ -1809,26 +1788,26 @@ static int scrub_checksum_data(struct scrub_block *sblock) struct btrfs_fs_info *fs_info = sctx->fs_info; SHASH_DESC_ON_STACK(shash, fs_info->csum_shash); u8 csum[BTRFS_CSUM_SIZE]; - struct scrub_page *spage; + struct scrub_sector *sector; char *kaddr; - BUG_ON(sblock->page_count < 1); - spage = sblock->pagev[0]; - if (!spage->have_csum) + BUG_ON(sblock->sector_count < 1); + sector = sblock->sectors[0]; + if (!sector->have_csum) return 0; - kaddr = page_address(spage->page); + kaddr = page_address(sector->page); shash->tfm = fs_info->csum_shash; crypto_shash_init(shash); /* - * In scrub_pages() and scrub_pages_for_parity() we ensure each spage + * In scrub_sectors() and scrub_sectors_for_parity() we ensure each sector * only contains one sector of data. */ crypto_shash_digest(shash, kaddr, fs_info->sectorsize, csum); - if (memcmp(csum, spage->csum, fs_info->csum_size)) + if (memcmp(csum, sector->csum, fs_info->csum_size)) sblock->checksum_error = 1; return sblock->checksum_error; } @@ -1849,16 +1828,16 @@ static int scrub_checksum_tree_block(struct scrub_block *sblock) const u32 sectorsize = sctx->fs_info->sectorsize; const int num_sectors = fs_info->nodesize >> fs_info->sectorsize_bits; int i; - struct scrub_page *spage; + struct scrub_sector *sector; char *kaddr; - BUG_ON(sblock->page_count < 1); + BUG_ON(sblock->sector_count < 1); - /* Each member in pagev is just one block, not a full page */ - ASSERT(sblock->page_count == num_sectors); + /* Each member in sectors is just one sector */ + ASSERT(sblock->sector_count == num_sectors); - spage = sblock->pagev[0]; - kaddr = page_address(spage->page); + sector = sblock->sectors[0]; + kaddr = page_address(sector->page); h = (struct btrfs_header *)kaddr; memcpy(on_disk_csum, h->csum, sctx->fs_info->csum_size); @@ -1867,15 +1846,15 @@ static int scrub_checksum_tree_block(struct scrub_block *sblock) * a) don't have an extent buffer and * b) the page is already kmapped */ - if (spage->logical != btrfs_stack_header_bytenr(h)) + if (sector->logical != btrfs_stack_header_bytenr(h)) sblock->header_error = 1; - if (spage->generation != btrfs_stack_header_generation(h)) { + if (sector->generation != btrfs_stack_header_generation(h)) { sblock->header_error = 1; sblock->generation_error = 1; } - if (!scrub_check_fsid(h->fsid, spage)) + if (!scrub_check_fsid(h->fsid, sector)) sblock->header_error = 1; if (memcmp(h->chunk_tree_uuid, fs_info->chunk_tree_uuid, @@ -1888,7 +1867,7 @@ static int scrub_checksum_tree_block(struct scrub_block *sblock) sectorsize - BTRFS_CSUM_SIZE); for (i = 1; i < num_sectors; i++) { - kaddr = page_address(sblock->pagev[i]->page); + kaddr = page_address(sblock->sectors[i]->page); crypto_shash_update(shash, kaddr, sectorsize); } @@ -1906,23 +1885,23 @@ static int scrub_checksum_super(struct scrub_block *sblock) struct btrfs_fs_info *fs_info = sctx->fs_info; SHASH_DESC_ON_STACK(shash, fs_info->csum_shash); u8 calculated_csum[BTRFS_CSUM_SIZE]; - struct scrub_page *spage; + struct scrub_sector *sector; char *kaddr; int fail_gen = 0; int fail_cor = 0; - BUG_ON(sblock->page_count < 1); - spage = sblock->pagev[0]; - kaddr = page_address(spage->page); + BUG_ON(sblock->sector_count < 1); + sector = sblock->sectors[0]; + kaddr = page_address(sector->page); s = (struct btrfs_super_block *)kaddr; - if (spage->logical != btrfs_super_bytenr(s)) + if (sector->logical != btrfs_super_bytenr(s)) ++fail_cor; - if (spage->generation != btrfs_super_generation(s)) + if (sector->generation != btrfs_super_generation(s)) ++fail_gen; - if (!scrub_check_fsid(s->fsid, spage)) + if (!scrub_check_fsid(s->fsid, sector)) ++fail_cor; shash->tfm = fs_info->csum_shash; @@ -1943,10 +1922,10 @@ static int scrub_checksum_super(struct scrub_block *sblock) ++sctx->stat.super_errors; spin_unlock(&sctx->stat_lock); if (fail_cor) - btrfs_dev_stat_inc_and_print(spage->dev, + btrfs_dev_stat_inc_and_print(sector->dev, BTRFS_DEV_STAT_CORRUPTION_ERRS); else - btrfs_dev_stat_inc_and_print(spage->dev, + btrfs_dev_stat_inc_and_print(sector->dev, BTRFS_DEV_STAT_GENERATION_ERRS); } @@ -1966,23 +1945,23 @@ static void scrub_block_put(struct scrub_block *sblock) if (sblock->sparity) scrub_parity_put(sblock->sparity); - for (i = 0; i < sblock->page_count; i++) - scrub_page_put(sblock->pagev[i]); + for (i = 0; i < sblock->sector_count; i++) + scrub_sector_put(sblock->sectors[i]); kfree(sblock); } } -static void scrub_page_get(struct scrub_page *spage) +static void scrub_sector_get(struct scrub_sector *sector) { - atomic_inc(&spage->refs); + atomic_inc(§or->refs); } -static void scrub_page_put(struct scrub_page *spage) +static void scrub_sector_put(struct scrub_sector *sector) { - if (atomic_dec_and_test(&spage->refs)) { - if (spage->page) - __free_page(spage->page); - kfree(spage); + if (atomic_dec_and_test(§or->refs)) { + if (sector->page) + __free_page(sector->page); + kfree(sector); } } @@ -2057,13 +2036,14 @@ static void scrub_submit(struct scrub_ctx *sctx) sbio = sctx->bios[sctx->curr]; sctx->curr = -1; scrub_pending_bio_inc(sctx); - btrfsic_submit_bio(sbio->bio); + btrfsic_check_bio(sbio->bio); + submit_bio(sbio->bio); } -static int scrub_add_page_to_rd_bio(struct scrub_ctx *sctx, - struct scrub_page *spage) +static int scrub_add_sector_to_rd_bio(struct scrub_ctx *sctx, + struct scrub_sector *sector) { - struct scrub_block *sblock = spage->sblock; + struct scrub_block *sblock = sector->sblock; struct scrub_bio *sbio; const u32 sectorsize = sctx->fs_info->sectorsize; int ret; @@ -2078,7 +2058,7 @@ again: if (sctx->curr != -1) { sctx->first_free = sctx->bios[sctx->curr]->next_free; sctx->bios[sctx->curr]->next_free = -1; - sctx->bios[sctx->curr]->page_count = 0; + sctx->bios[sctx->curr]->sector_count = 0; spin_unlock(&sctx->list_lock); } else { spin_unlock(&sctx->list_lock); @@ -2086,37 +2066,31 @@ again: } } sbio = sctx->bios[sctx->curr]; - if (sbio->page_count == 0) { - struct bio *bio; - - sbio->physical = spage->physical; - sbio->logical = spage->logical; - sbio->dev = spage->dev; - bio = sbio->bio; - if (!bio) { - bio = btrfs_bio_alloc(sctx->pages_per_bio); - sbio->bio = bio; + if (sbio->sector_count == 0) { + sbio->physical = sector->physical; + sbio->logical = sector->logical; + sbio->dev = sector->dev; + if (!sbio->bio) { + sbio->bio = bio_alloc(sbio->dev->bdev, sctx->sectors_per_bio, + REQ_OP_READ, GFP_NOFS); } - - bio->bi_private = sbio; - bio->bi_end_io = scrub_bio_end_io; - bio_set_dev(bio, sbio->dev->bdev); - bio->bi_iter.bi_sector = sbio->physical >> 9; - bio->bi_opf = REQ_OP_READ; + sbio->bio->bi_private = sbio; + sbio->bio->bi_end_io = scrub_bio_end_io; + sbio->bio->bi_iter.bi_sector = sbio->physical >> 9; sbio->status = 0; - } else if (sbio->physical + sbio->page_count * sectorsize != - spage->physical || - sbio->logical + sbio->page_count * sectorsize != - spage->logical || - sbio->dev != spage->dev) { + } else if (sbio->physical + sbio->sector_count * sectorsize != + sector->physical || + sbio->logical + sbio->sector_count * sectorsize != + sector->logical || + sbio->dev != sector->dev) { scrub_submit(sctx); goto again; } - sbio->pagev[sbio->page_count] = spage; - ret = bio_add_page(sbio->bio, spage->page, sectorsize, 0); + sbio->sectors[sbio->sector_count] = sector; + ret = bio_add_page(sbio->bio, sector->page, sectorsize, 0); if (ret != sectorsize) { - if (sbio->page_count < 1) { + if (sbio->sector_count < 1) { bio_put(sbio->bio); sbio->bio = NULL; return -EIO; @@ -2126,9 +2100,9 @@ again: } scrub_block_get(sblock); /* one for the page added to the bio */ - atomic_inc(&sblock->outstanding_pages); - sbio->page_count++; - if (sbio->page_count == sctx->pages_per_bio) + atomic_inc(&sblock->outstanding_sectors); + sbio->sector_count++; + if (sbio->sector_count == sctx->sectors_per_bio) scrub_submit(sctx); return 0; @@ -2144,10 +2118,10 @@ static void scrub_missing_raid56_end_io(struct bio *bio) bio_put(bio); - btrfs_queue_work(fs_info->scrub_workers, &sblock->work); + queue_work(fs_info->scrub_workers, &sblock->work); } -static void scrub_missing_raid56_worker(struct btrfs_work *work) +static void scrub_missing_raid56_worker(struct work_struct *work) { struct scrub_block *sblock = container_of(work, struct scrub_block, work); struct scrub_ctx *sctx = sblock->sctx; @@ -2155,8 +2129,8 @@ static void scrub_missing_raid56_worker(struct btrfs_work *work) u64 logical; struct btrfs_device *dev; - logical = sblock->pagev[0]->logical; - dev = sblock->pagev[0]->dev; + logical = sblock->sectors[0]->logical; + dev = sblock->sectors[0]->dev; if (sblock->no_io_error_seen) scrub_recheck_block_checksum(sblock); @@ -2193,8 +2167,8 @@ static void scrub_missing_raid56_pages(struct scrub_block *sblock) { struct scrub_ctx *sctx = sblock->sctx; struct btrfs_fs_info *fs_info = sctx->fs_info; - u64 length = sblock->page_count * PAGE_SIZE; - u64 logical = sblock->pagev[0]->logical; + u64 length = sblock->sector_count << fs_info->sectorsize_bits; + u64 logical = sblock->sectors[0]->logical; struct btrfs_io_context *bioc = NULL; struct bio *bio; struct btrfs_raid_bio *rbio; @@ -2213,12 +2187,12 @@ static void scrub_missing_raid56_pages(struct scrub_block *sblock) * We shouldn't be scrubbing a missing device. Even for dev * replace, we should only get here for RAID 5/6. We either * managed to mount something with no mirrors remaining or - * there's a bug in scrub_remap_extent()/btrfs_map_block(). + * there's a bug in scrub_find_good_copy()/btrfs_map_block(). */ goto bioc_out; } - bio = btrfs_bio_alloc(BIO_MAX_VECS); + bio = bio_alloc(NULL, BIO_MAX_VECS, REQ_OP_READ, GFP_NOFS); bio->bi_iter.bi_sector = logical >> 9; bio->bi_private = sblock; bio->bi_end_io = scrub_missing_raid56_end_io; @@ -2227,13 +2201,17 @@ static void scrub_missing_raid56_pages(struct scrub_block *sblock) if (!rbio) goto rbio_out; - for (i = 0; i < sblock->page_count; i++) { - struct scrub_page *spage = sblock->pagev[i]; + for (i = 0; i < sblock->sector_count; i++) { + struct scrub_sector *sector = sblock->sectors[i]; - raid56_add_scrub_pages(rbio, spage->page, spage->logical); + /* + * For now, our scrub is still one page per sector, so pgoff + * is always 0. + */ + raid56_add_scrub_pages(rbio, sector->page, 0, sector->logical); } - btrfs_init_work(&sblock->work, scrub_missing_raid56_worker, NULL, NULL); + INIT_WORK(&sblock->work, scrub_missing_raid56_worker); scrub_block_get(sblock); scrub_pending_bio_inc(sctx); raid56_submit_missing_rbio(rbio); @@ -2249,7 +2227,7 @@ bioc_out: spin_unlock(&sctx->stat_lock); } -static int scrub_pages(struct scrub_ctx *sctx, u64 logical, u32 len, +static int scrub_sectors(struct scrub_ctx *sctx, u64 logical, u32 len, u64 physical, struct btrfs_device *dev, u64 flags, u64 gen, int mirror_num, u8 *csum, u64 physical_for_dev_replace) @@ -2273,7 +2251,7 @@ static int scrub_pages(struct scrub_ctx *sctx, u64 logical, u32 len, sblock->no_io_error_seen = 1; for (index = 0; len > 0; index++) { - struct scrub_page *spage; + struct scrub_sector *sector; /* * Here we will allocate one page for one sector to scrub. * This is fine if PAGE_SIZE == sectorsize, but will cost @@ -2281,8 +2259,8 @@ static int scrub_pages(struct scrub_ctx *sctx, u64 logical, u32 len, */ u32 l = min(sectorsize, len); - spage = kzalloc(sizeof(*spage), GFP_KERNEL); - if (!spage) { + sector = kzalloc(sizeof(*sector), GFP_KERNEL); + if (!sector) { leave_nomem: spin_lock(&sctx->stat_lock); sctx->stat.malloc_errors++; @@ -2290,26 +2268,26 @@ leave_nomem: scrub_block_put(sblock); return -ENOMEM; } - ASSERT(index < SCRUB_MAX_PAGES_PER_BLOCK); - scrub_page_get(spage); - sblock->pagev[index] = spage; - spage->sblock = sblock; - spage->dev = dev; - spage->flags = flags; - spage->generation = gen; - spage->logical = logical; - spage->physical = physical; - spage->physical_for_dev_replace = physical_for_dev_replace; - spage->mirror_num = mirror_num; + ASSERT(index < SCRUB_MAX_SECTORS_PER_BLOCK); + scrub_sector_get(sector); + sblock->sectors[index] = sector; + sector->sblock = sblock; + sector->dev = dev; + sector->flags = flags; + sector->generation = gen; + sector->logical = logical; + sector->physical = physical; + sector->physical_for_dev_replace = physical_for_dev_replace; + sector->mirror_num = mirror_num; if (csum) { - spage->have_csum = 1; - memcpy(spage->csum, csum, sctx->fs_info->csum_size); + sector->have_csum = 1; + memcpy(sector->csum, csum, sctx->fs_info->csum_size); } else { - spage->have_csum = 0; + sector->have_csum = 0; } - sblock->page_count++; - spage->page = alloc_page(GFP_KERNEL); - if (!spage->page) + sblock->sector_count++; + sector->page = alloc_page(GFP_KERNEL); + if (!sector->page) goto leave_nomem; len -= l; logical += l; @@ -2317,7 +2295,7 @@ leave_nomem: physical_for_dev_replace += l; } - WARN_ON(sblock->page_count == 0); + WARN_ON(sblock->sector_count == 0); if (test_bit(BTRFS_DEV_STATE_MISSING, &dev->dev_state)) { /* * This case should only be hit for RAID 5/6 device replace. See @@ -2325,11 +2303,11 @@ leave_nomem: */ scrub_missing_raid56_pages(sblock); } else { - for (index = 0; index < sblock->page_count; index++) { - struct scrub_page *spage = sblock->pagev[index]; + for (index = 0; index < sblock->sector_count; index++) { + struct scrub_sector *sector = sblock->sectors[index]; int ret; - ret = scrub_add_page_to_rd_bio(sctx, spage); + ret = scrub_add_sector_to_rd_bio(sctx, sector); if (ret) { scrub_block_put(sblock); return ret; @@ -2353,31 +2331,31 @@ static void scrub_bio_end_io(struct bio *bio) sbio->status = bio->bi_status; sbio->bio = bio; - btrfs_queue_work(fs_info->scrub_workers, &sbio->work); + queue_work(fs_info->scrub_workers, &sbio->work); } -static void scrub_bio_end_io_worker(struct btrfs_work *work) +static void scrub_bio_end_io_worker(struct work_struct *work) { struct scrub_bio *sbio = container_of(work, struct scrub_bio, work); struct scrub_ctx *sctx = sbio->sctx; int i; - ASSERT(sbio->page_count <= SCRUB_PAGES_PER_BIO); + ASSERT(sbio->sector_count <= SCRUB_SECTORS_PER_BIO); if (sbio->status) { - for (i = 0; i < sbio->page_count; i++) { - struct scrub_page *spage = sbio->pagev[i]; + for (i = 0; i < sbio->sector_count; i++) { + struct scrub_sector *sector = sbio->sectors[i]; - spage->io_error = 1; - spage->sblock->no_io_error_seen = 0; + sector->io_error = 1; + sector->sblock->no_io_error_seen = 0; } } - /* now complete the scrub_block items that have all pages completed */ - for (i = 0; i < sbio->page_count; i++) { - struct scrub_page *spage = sbio->pagev[i]; - struct scrub_block *sblock = spage->sblock; + /* Now complete the scrub_block items that have all pages completed */ + for (i = 0; i < sbio->sector_count; i++) { + struct scrub_sector *sector = sbio->sectors[i]; + struct scrub_block *sblock = sector->sblock; - if (atomic_dec_and_test(&sblock->outstanding_pages)) + if (atomic_dec_and_test(&sblock->outstanding_sectors)) scrub_block_complete(sblock); scrub_block_put(sblock); } @@ -2456,8 +2434,8 @@ static void scrub_block_complete(struct scrub_block *sblock) } if (sblock->sparity && corrupted && !sblock->data_corrected) { - u64 start = sblock->pagev[0]->logical; - u64 end = sblock->pagev[sblock->page_count - 1]->logical + + u64 start = sblock->sectors[0]->logical; + u64 end = sblock->sectors[sblock->sector_count - 1]->logical + sblock->sctx->fs_info->sectorsize; ASSERT(end - start <= U32_MAX); @@ -2532,8 +2510,11 @@ static int scrub_find_csum(struct scrub_ctx *sctx, u64 logical, u8 *csum) static int scrub_extent(struct scrub_ctx *sctx, struct map_lookup *map, u64 logical, u32 len, u64 physical, struct btrfs_device *dev, u64 flags, - u64 gen, int mirror_num, u64 physical_for_dev_replace) + u64 gen, int mirror_num) { + struct btrfs_device *src_dev = dev; + u64 src_physical = physical; + int src_mirror = mirror_num; int ret; u8 csum[BTRFS_CSUM_SIZE]; u32 blocksize; @@ -2561,6 +2542,18 @@ static int scrub_extent(struct scrub_ctx *sctx, struct map_lookup *map, WARN_ON(1); } + /* + * For dev-replace case, we can have @dev being a missing device. + * Regular scrub will avoid its execution on missing device at all, + * as that would trigger tons of read error. + * + * Reading from missing device will cause read error counts to + * increase unnecessarily. + * So here we change the read source to a good mirror. + */ + if (sctx->is_dev_replace && !dev->bdev) + scrub_find_good_copy(sctx->fs_info, logical, len, &src_physical, + &src_dev, &src_mirror); while (len) { u32 l = min(len, blocksize); int have_csum = 0; @@ -2571,20 +2564,20 @@ static int scrub_extent(struct scrub_ctx *sctx, struct map_lookup *map, if (have_csum == 0) ++sctx->stat.no_csum; } - ret = scrub_pages(sctx, logical, l, physical, dev, flags, gen, - mirror_num, have_csum ? csum : NULL, - physical_for_dev_replace); + ret = scrub_sectors(sctx, logical, l, src_physical, src_dev, + flags, gen, src_mirror, + have_csum ? csum : NULL, physical); if (ret) return ret; len -= l; logical += l; physical += l; - physical_for_dev_replace += l; + src_physical += l; } return 0; } -static int scrub_pages_for_parity(struct scrub_parity *sparity, +static int scrub_sectors_for_parity(struct scrub_parity *sparity, u64 logical, u32 len, u64 physical, struct btrfs_device *dev, u64 flags, u64 gen, int mirror_num, u8 *csum) @@ -2613,10 +2606,10 @@ static int scrub_pages_for_parity(struct scrub_parity *sparity, scrub_parity_get(sparity); for (index = 0; len > 0; index++) { - struct scrub_page *spage; + struct scrub_sector *sector; - spage = kzalloc(sizeof(*spage), GFP_KERNEL); - if (!spage) { + sector = kzalloc(sizeof(*sector), GFP_KERNEL); + if (!sector) { leave_nomem: spin_lock(&sctx->stat_lock); sctx->stat.malloc_errors++; @@ -2624,29 +2617,29 @@ leave_nomem: scrub_block_put(sblock); return -ENOMEM; } - ASSERT(index < SCRUB_MAX_PAGES_PER_BLOCK); + ASSERT(index < SCRUB_MAX_SECTORS_PER_BLOCK); /* For scrub block */ - scrub_page_get(spage); - sblock->pagev[index] = spage; + scrub_sector_get(sector); + sblock->sectors[index] = sector; /* For scrub parity */ - scrub_page_get(spage); - list_add_tail(&spage->list, &sparity->spages); - spage->sblock = sblock; - spage->dev = dev; - spage->flags = flags; - spage->generation = gen; - spage->logical = logical; - spage->physical = physical; - spage->mirror_num = mirror_num; + scrub_sector_get(sector); + list_add_tail(§or->list, &sparity->sectors_list); + sector->sblock = sblock; + sector->dev = dev; + sector->flags = flags; + sector->generation = gen; + sector->logical = logical; + sector->physical = physical; + sector->mirror_num = mirror_num; if (csum) { - spage->have_csum = 1; - memcpy(spage->csum, csum, sctx->fs_info->csum_size); + sector->have_csum = 1; + memcpy(sector->csum, csum, sctx->fs_info->csum_size); } else { - spage->have_csum = 0; + sector->have_csum = 0; } - sblock->page_count++; - spage->page = alloc_page(GFP_KERNEL); - if (!spage->page) + sblock->sector_count++; + sector->page = alloc_page(GFP_KERNEL); + if (!sector->page) goto leave_nomem; @@ -2656,19 +2649,19 @@ leave_nomem: physical += sectorsize; } - WARN_ON(sblock->page_count == 0); - for (index = 0; index < sblock->page_count; index++) { - struct scrub_page *spage = sblock->pagev[index]; + WARN_ON(sblock->sector_count == 0); + for (index = 0; index < sblock->sector_count; index++) { + struct scrub_sector *sector = sblock->sectors[index]; int ret; - ret = scrub_add_page_to_rd_bio(sctx, spage); + ret = scrub_add_sector_to_rd_bio(sctx, sector); if (ret) { scrub_block_put(sblock); return ret; } } - /* last one frees, either here or in bio completion for last page */ + /* Last one frees, either here or in bio completion for last sector */ scrub_block_put(sblock); return 0; } @@ -2707,7 +2700,7 @@ static int scrub_extent_for_parity(struct scrub_parity *sparity, if (have_csum == 0) goto skip; } - ret = scrub_pages_for_parity(sparity, logical, l, physical, dev, + ret = scrub_sectors_for_parity(sparity, logical, l, physical, dev, flags, gen, mirror_num, have_csum ? csum : NULL); if (ret) @@ -2767,7 +2760,7 @@ static int get_raid56_logic_offset(u64 physical, int num, static void scrub_free_parity(struct scrub_parity *sparity) { struct scrub_ctx *sctx = sparity->sctx; - struct scrub_page *curr, *next; + struct scrub_sector *curr, *next; int nbits; nbits = bitmap_weight(sparity->ebitmap, sparity->nsectors); @@ -2778,15 +2771,15 @@ static void scrub_free_parity(struct scrub_parity *sparity) spin_unlock(&sctx->stat_lock); } - list_for_each_entry_safe(curr, next, &sparity->spages, list) { + list_for_each_entry_safe(curr, next, &sparity->sectors_list, list) { list_del_init(&curr->list); - scrub_page_put(curr); + scrub_sector_put(curr); } kfree(sparity); } -static void scrub_parity_bio_endio_worker(struct btrfs_work *work) +static void scrub_parity_bio_endio_worker(struct work_struct *work) { struct scrub_parity *sparity = container_of(work, struct scrub_parity, work); @@ -2798,7 +2791,7 @@ static void scrub_parity_bio_endio_worker(struct btrfs_work *work) static void scrub_parity_bio_endio(struct bio *bio) { - struct scrub_parity *sparity = (struct scrub_parity *)bio->bi_private; + struct scrub_parity *sparity = bio->bi_private; struct btrfs_fs_info *fs_info = sparity->sctx->fs_info; if (bio->bi_status) @@ -2807,9 +2800,8 @@ static void scrub_parity_bio_endio(struct bio *bio) bio_put(bio); - btrfs_init_work(&sparity->work, scrub_parity_bio_endio_worker, NULL, - NULL); - btrfs_queue_work(fs_info->scrub_parity_workers, &sparity->work); + INIT_WORK(&sparity->work, scrub_parity_bio_endio_worker); + queue_work(fs_info->scrub_parity_workers, &sparity->work); } static void scrub_parity_check_and_repair(struct scrub_parity *sparity) @@ -2834,7 +2826,7 @@ static void scrub_parity_check_and_repair(struct scrub_parity *sparity) if (ret || !bioc || !bioc->raid_map) goto bioc_out; - bio = btrfs_bio_alloc(BIO_MAX_VECS); + bio = bio_alloc(NULL, BIO_MAX_VECS, REQ_OP_READ, GFP_NOFS); bio->bi_iter.bi_sector = sparity->logic_start >> 9; bio->bi_private = sparity; bio->bi_end_io = scrub_parity_bio_endio; @@ -2882,6 +2874,251 @@ static void scrub_parity_put(struct scrub_parity *sparity) scrub_parity_check_and_repair(sparity); } +/* + * Return 0 if the extent item range covers any byte of the range. + * Return <0 if the extent item is before @search_start. + * Return >0 if the extent item is after @start_start + @search_len. + */ +static int compare_extent_item_range(struct btrfs_path *path, + u64 search_start, u64 search_len) +{ + struct btrfs_fs_info *fs_info = path->nodes[0]->fs_info; + u64 len; + struct btrfs_key key; + + btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); + ASSERT(key.type == BTRFS_EXTENT_ITEM_KEY || + key.type == BTRFS_METADATA_ITEM_KEY); + if (key.type == BTRFS_METADATA_ITEM_KEY) + len = fs_info->nodesize; + else + len = key.offset; + + if (key.objectid + len <= search_start) + return -1; + if (key.objectid >= search_start + search_len) + return 1; + return 0; +} + +/* + * Locate one extent item which covers any byte in range + * [@search_start, @search_start + @search_length) + * + * If the path is not initialized, we will initialize the search by doing + * a btrfs_search_slot(). + * If the path is already initialized, we will use the path as the initial + * slot, to avoid duplicated btrfs_search_slot() calls. + * + * NOTE: If an extent item starts before @search_start, we will still + * return the extent item. This is for data extent crossing stripe boundary. + * + * Return 0 if we found such extent item, and @path will point to the extent item. + * Return >0 if no such extent item can be found, and @path will be released. + * Return <0 if hit fatal error, and @path will be released. + */ +static int find_first_extent_item(struct btrfs_root *extent_root, + struct btrfs_path *path, + u64 search_start, u64 search_len) +{ + struct btrfs_fs_info *fs_info = extent_root->fs_info; + struct btrfs_key key; + int ret; + + /* Continue using the existing path */ + if (path->nodes[0]) + goto search_forward; + + if (btrfs_fs_incompat(fs_info, SKINNY_METADATA)) + key.type = BTRFS_METADATA_ITEM_KEY; + else + key.type = BTRFS_EXTENT_ITEM_KEY; + key.objectid = search_start; + key.offset = (u64)-1; + + ret = btrfs_search_slot(NULL, extent_root, &key, path, 0, 0); + if (ret < 0) + return ret; + + ASSERT(ret > 0); + /* + * Here we intentionally pass 0 as @min_objectid, as there could be + * an extent item starting before @search_start. + */ + ret = btrfs_previous_extent_item(extent_root, path, 0); + if (ret < 0) + return ret; + /* + * No matter whether we have found an extent item, the next loop will + * properly do every check on the key. + */ +search_forward: + while (true) { + btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); + if (key.objectid >= search_start + search_len) + break; + if (key.type != BTRFS_METADATA_ITEM_KEY && + key.type != BTRFS_EXTENT_ITEM_KEY) + goto next; + + ret = compare_extent_item_range(path, search_start, search_len); + if (ret == 0) + return ret; + if (ret > 0) + break; +next: + path->slots[0]++; + if (path->slots[0] >= btrfs_header_nritems(path->nodes[0])) { + ret = btrfs_next_leaf(extent_root, path); + if (ret) { + /* Either no more item or fatal error */ + btrfs_release_path(path); + return ret; + } + } + } + btrfs_release_path(path); + return 1; +} + +static void get_extent_info(struct btrfs_path *path, u64 *extent_start_ret, + u64 *size_ret, u64 *flags_ret, u64 *generation_ret) +{ + struct btrfs_key key; + struct btrfs_extent_item *ei; + + btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); + ASSERT(key.type == BTRFS_METADATA_ITEM_KEY || + key.type == BTRFS_EXTENT_ITEM_KEY); + *extent_start_ret = key.objectid; + if (key.type == BTRFS_METADATA_ITEM_KEY) + *size_ret = path->nodes[0]->fs_info->nodesize; + else + *size_ret = key.offset; + ei = btrfs_item_ptr(path->nodes[0], path->slots[0], struct btrfs_extent_item); + *flags_ret = btrfs_extent_flags(path->nodes[0], ei); + *generation_ret = btrfs_extent_generation(path->nodes[0], ei); +} + +static bool does_range_cross_boundary(u64 extent_start, u64 extent_len, + u64 boundary_start, u64 boudary_len) +{ + return (extent_start < boundary_start && + extent_start + extent_len > boundary_start) || + (extent_start < boundary_start + boudary_len && + extent_start + extent_len > boundary_start + boudary_len); +} + +static int scrub_raid56_data_stripe_for_parity(struct scrub_ctx *sctx, + struct scrub_parity *sparity, + struct map_lookup *map, + struct btrfs_device *sdev, + struct btrfs_path *path, + u64 logical) +{ + struct btrfs_fs_info *fs_info = sctx->fs_info; + struct btrfs_root *extent_root = btrfs_extent_root(fs_info, logical); + struct btrfs_root *csum_root = btrfs_csum_root(fs_info, logical); + u64 cur_logical = logical; + int ret; + + ASSERT(map->type & BTRFS_BLOCK_GROUP_RAID56_MASK); + + /* Path must not be populated */ + ASSERT(!path->nodes[0]); + + while (cur_logical < logical + map->stripe_len) { + struct btrfs_io_context *bioc = NULL; + struct btrfs_device *extent_dev; + u64 extent_start; + u64 extent_size; + u64 mapped_length; + u64 extent_flags; + u64 extent_gen; + u64 extent_physical; + u64 extent_mirror_num; + + ret = find_first_extent_item(extent_root, path, cur_logical, + logical + map->stripe_len - cur_logical); + /* No more extent item in this data stripe */ + if (ret > 0) { + ret = 0; + break; + } + if (ret < 0) + break; + get_extent_info(path, &extent_start, &extent_size, &extent_flags, + &extent_gen); + + /* Metadata should not cross stripe boundaries */ + if ((extent_flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) && + does_range_cross_boundary(extent_start, extent_size, + logical, map->stripe_len)) { + btrfs_err(fs_info, + "scrub: tree block %llu spanning stripes, ignored. logical=%llu", + extent_start, logical); + spin_lock(&sctx->stat_lock); + sctx->stat.uncorrectable_errors++; + spin_unlock(&sctx->stat_lock); + cur_logical += extent_size; + continue; + } + + /* Skip hole range which doesn't have any extent */ + cur_logical = max(extent_start, cur_logical); + + /* Truncate the range inside this data stripe */ + extent_size = min(extent_start + extent_size, + logical + map->stripe_len) - cur_logical; + extent_start = cur_logical; + ASSERT(extent_size <= U32_MAX); + + scrub_parity_mark_sectors_data(sparity, extent_start, extent_size); + + mapped_length = extent_size; + ret = btrfs_map_block(fs_info, BTRFS_MAP_READ, extent_start, + &mapped_length, &bioc, 0); + if (!ret && (!bioc || mapped_length < extent_size)) + ret = -EIO; + if (ret) { + btrfs_put_bioc(bioc); + scrub_parity_mark_sectors_error(sparity, extent_start, + extent_size); + break; + } + extent_physical = bioc->stripes[0].physical; + extent_mirror_num = bioc->mirror_num; + extent_dev = bioc->stripes[0].dev; + btrfs_put_bioc(bioc); + + ret = btrfs_lookup_csums_range(csum_root, extent_start, + extent_start + extent_size - 1, + &sctx->csum_list, 1); + if (ret) { + scrub_parity_mark_sectors_error(sparity, extent_start, + extent_size); + break; + } + + ret = scrub_extent_for_parity(sparity, extent_start, + extent_size, extent_physical, + extent_dev, extent_flags, + extent_gen, extent_mirror_num); + scrub_free_csums(sctx); + + if (ret) { + scrub_parity_mark_sectors_error(sparity, extent_start, + extent_size); + break; + } + + cond_resched(); + cur_logical += extent_size; + } + btrfs_release_path(path); + return ret; +} + static noinline_for_stack int scrub_raid56_parity(struct scrub_ctx *sctx, struct map_lookup *map, struct btrfs_device *sdev, @@ -2889,28 +3126,12 @@ static noinline_for_stack int scrub_raid56_parity(struct scrub_ctx *sctx, u64 logic_end) { struct btrfs_fs_info *fs_info = sctx->fs_info; - struct btrfs_root *root = btrfs_extent_root(fs_info, logic_start); - struct btrfs_root *csum_root; - struct btrfs_extent_item *extent; - struct btrfs_io_context *bioc = NULL; struct btrfs_path *path; - u64 flags; + u64 cur_logical; int ret; - int slot; - struct extent_buffer *l; - struct btrfs_key key; - u64 generation; - u64 extent_logical; - u64 extent_physical; - /* Check the comment in scrub_stripe() for why u32 is enough here */ - u32 extent_len; - u64 mapped_length; - struct btrfs_device *extent_dev; struct scrub_parity *sparity; int nsectors; int bitmap_len; - int extent_mirror_num; - int stop_loop = 0; path = btrfs_alloc_path(); if (!path) { @@ -2943,178 +3164,19 @@ static noinline_for_stack int scrub_raid56_parity(struct scrub_ctx *sctx, sparity->logic_start = logic_start; sparity->logic_end = logic_end; refcount_set(&sparity->refs, 1); - INIT_LIST_HEAD(&sparity->spages); + INIT_LIST_HEAD(&sparity->sectors_list); sparity->dbitmap = sparity->bitmap; sparity->ebitmap = (void *)sparity->bitmap + bitmap_len; ret = 0; - while (logic_start < logic_end) { - if (btrfs_fs_incompat(fs_info, SKINNY_METADATA)) - key.type = BTRFS_METADATA_ITEM_KEY; - else - key.type = BTRFS_EXTENT_ITEM_KEY; - key.objectid = logic_start; - key.offset = (u64)-1; - - ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); + for (cur_logical = logic_start; cur_logical < logic_end; + cur_logical += map->stripe_len) { + ret = scrub_raid56_data_stripe_for_parity(sctx, sparity, map, + sdev, path, cur_logical); if (ret < 0) - goto out; - - if (ret > 0) { - ret = btrfs_previous_extent_item(root, path, 0); - if (ret < 0) - goto out; - if (ret > 0) { - btrfs_release_path(path); - ret = btrfs_search_slot(NULL, root, &key, - path, 0, 0); - if (ret < 0) - goto out; - } - } - - stop_loop = 0; - while (1) { - u64 bytes; - - l = path->nodes[0]; - slot = path->slots[0]; - if (slot >= btrfs_header_nritems(l)) { - ret = btrfs_next_leaf(root, path); - if (ret == 0) - continue; - if (ret < 0) - goto out; - - stop_loop = 1; - break; - } - btrfs_item_key_to_cpu(l, &key, slot); - - if (key.type != BTRFS_EXTENT_ITEM_KEY && - key.type != BTRFS_METADATA_ITEM_KEY) - goto next; - - if (key.type == BTRFS_METADATA_ITEM_KEY) - bytes = fs_info->nodesize; - else - bytes = key.offset; - - if (key.objectid + bytes <= logic_start) - goto next; - - if (key.objectid >= logic_end) { - stop_loop = 1; - break; - } - - while (key.objectid >= logic_start + map->stripe_len) - logic_start += map->stripe_len; - - extent = btrfs_item_ptr(l, slot, - struct btrfs_extent_item); - flags = btrfs_extent_flags(l, extent); - generation = btrfs_extent_generation(l, extent); - - if ((flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) && - (key.objectid < logic_start || - key.objectid + bytes > - logic_start + map->stripe_len)) { - btrfs_err(fs_info, - "scrub: tree block %llu spanning stripes, ignored. logical=%llu", - key.objectid, logic_start); - spin_lock(&sctx->stat_lock); - sctx->stat.uncorrectable_errors++; - spin_unlock(&sctx->stat_lock); - goto next; - } -again: - extent_logical = key.objectid; - ASSERT(bytes <= U32_MAX); - extent_len = bytes; - - if (extent_logical < logic_start) { - extent_len -= logic_start - extent_logical; - extent_logical = logic_start; - } - - if (extent_logical + extent_len > - logic_start + map->stripe_len) - extent_len = logic_start + map->stripe_len - - extent_logical; - - scrub_parity_mark_sectors_data(sparity, extent_logical, - extent_len); - - mapped_length = extent_len; - bioc = NULL; - ret = btrfs_map_block(fs_info, BTRFS_MAP_READ, - extent_logical, &mapped_length, &bioc, - 0); - if (!ret) { - if (!bioc || mapped_length < extent_len) - ret = -EIO; - } - if (ret) { - btrfs_put_bioc(bioc); - goto out; - } - extent_physical = bioc->stripes[0].physical; - extent_mirror_num = bioc->mirror_num; - extent_dev = bioc->stripes[0].dev; - btrfs_put_bioc(bioc); - - csum_root = btrfs_csum_root(fs_info, extent_logical); - ret = btrfs_lookup_csums_range(csum_root, - extent_logical, - extent_logical + extent_len - 1, - &sctx->csum_list, 1); - if (ret) - goto out; - - ret = scrub_extent_for_parity(sparity, extent_logical, - extent_len, - extent_physical, - extent_dev, flags, - generation, - extent_mirror_num); - - scrub_free_csums(sctx); - - if (ret) - goto out; - - if (extent_logical + extent_len < - key.objectid + bytes) { - logic_start += map->stripe_len; - - if (logic_start >= logic_end) { - stop_loop = 1; - break; - } - - if (logic_start < key.objectid + bytes) { - cond_resched(); - goto again; - } - } -next: - path->slots[0]++; - } - - btrfs_release_path(path); - - if (stop_loop) break; - - logic_start += map->stripe_len; - } -out: - if (ret < 0) { - ASSERT(logic_end - logic_start <= U32_MAX); - scrub_parity_mark_sectors_error(sparity, logic_start, - logic_end - logic_start); } + scrub_parity_put(sparity); scrub_submit(sctx); mutex_lock(&sctx->wr_lock); @@ -3165,6 +3227,206 @@ static int sync_write_pointer_for_zoned(struct scrub_ctx *sctx, u64 logical, return ret; } +/* + * Scrub one range which can only has simple mirror based profile. + * (Including all range in SINGLE/DUP/RAID1/RAID1C*, and each stripe in + * RAID0/RAID10). + * + * Since we may need to handle a subset of block group, we need @logical_start + * and @logical_length parameter. + */ +static int scrub_simple_mirror(struct scrub_ctx *sctx, + struct btrfs_root *extent_root, + struct btrfs_root *csum_root, + struct btrfs_block_group *bg, + struct map_lookup *map, + u64 logical_start, u64 logical_length, + struct btrfs_device *device, + u64 physical, int mirror_num) +{ + struct btrfs_fs_info *fs_info = sctx->fs_info; + const u64 logical_end = logical_start + logical_length; + /* An artificial limit, inherit from old scrub behavior */ + const u32 max_length = SZ_64K; + struct btrfs_path path = { 0 }; + u64 cur_logical = logical_start; + int ret; + + /* The range must be inside the bg */ + ASSERT(logical_start >= bg->start && logical_end <= bg->start + bg->length); + + path.search_commit_root = 1; + path.skip_locking = 1; + /* Go through each extent items inside the logical range */ + while (cur_logical < logical_end) { + u64 extent_start; + u64 extent_len; + u64 extent_flags; + u64 extent_gen; + u64 scrub_len; + + /* Canceled? */ + if (atomic_read(&fs_info->scrub_cancel_req) || + atomic_read(&sctx->cancel_req)) { + ret = -ECANCELED; + break; + } + /* Paused? */ + if (atomic_read(&fs_info->scrub_pause_req)) { + /* Push queued extents */ + sctx->flush_all_writes = true; + scrub_submit(sctx); + mutex_lock(&sctx->wr_lock); + scrub_wr_submit(sctx); + mutex_unlock(&sctx->wr_lock); + wait_event(sctx->list_wait, + atomic_read(&sctx->bios_in_flight) == 0); + sctx->flush_all_writes = false; + scrub_blocked_if_needed(fs_info); + } + /* Block group removed? */ + spin_lock(&bg->lock); + if (bg->removed) { + spin_unlock(&bg->lock); + ret = 0; + break; + } + spin_unlock(&bg->lock); + + ret = find_first_extent_item(extent_root, &path, cur_logical, + logical_end - cur_logical); + if (ret > 0) { + /* No more extent, just update the accounting */ + sctx->stat.last_physical = physical + logical_length; + ret = 0; + break; + } + if (ret < 0) + break; + get_extent_info(&path, &extent_start, &extent_len, + &extent_flags, &extent_gen); + /* Skip hole range which doesn't have any extent */ + cur_logical = max(extent_start, cur_logical); + + /* + * Scrub len has three limits: + * - Extent size limit + * - Scrub range limit + * This is especially imporatant for RAID0/RAID10 to reuse + * this function + * - Max scrub size limit + */ + scrub_len = min(min(extent_start + extent_len, + logical_end), cur_logical + max_length) - + cur_logical; + + if (extent_flags & BTRFS_EXTENT_FLAG_DATA) { + ret = btrfs_lookup_csums_range(csum_root, cur_logical, + cur_logical + scrub_len - 1, + &sctx->csum_list, 1); + if (ret) + break; + } + if ((extent_flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) && + does_range_cross_boundary(extent_start, extent_len, + logical_start, logical_length)) { + btrfs_err(fs_info, +"scrub: tree block %llu spanning boundaries, ignored. boundary=[%llu, %llu)", + extent_start, logical_start, logical_end); + spin_lock(&sctx->stat_lock); + sctx->stat.uncorrectable_errors++; + spin_unlock(&sctx->stat_lock); + cur_logical += scrub_len; + continue; + } + ret = scrub_extent(sctx, map, cur_logical, scrub_len, + cur_logical - logical_start + physical, + device, extent_flags, extent_gen, + mirror_num); + scrub_free_csums(sctx); + if (ret) + break; + if (sctx->is_dev_replace) + sync_replace_for_zoned(sctx); + cur_logical += scrub_len; + /* Don't hold CPU for too long time */ + cond_resched(); + } + btrfs_release_path(&path); + return ret; +} + +/* Calculate the full stripe length for simple stripe based profiles */ +static u64 simple_stripe_full_stripe_len(const struct map_lookup *map) +{ + ASSERT(map->type & (BTRFS_BLOCK_GROUP_RAID0 | + BTRFS_BLOCK_GROUP_RAID10)); + + return map->num_stripes / map->sub_stripes * map->stripe_len; +} + +/* Get the logical bytenr for the stripe */ +static u64 simple_stripe_get_logical(struct map_lookup *map, + struct btrfs_block_group *bg, + int stripe_index) +{ + ASSERT(map->type & (BTRFS_BLOCK_GROUP_RAID0 | + BTRFS_BLOCK_GROUP_RAID10)); + ASSERT(stripe_index < map->num_stripes); + + /* + * (stripe_index / sub_stripes) gives how many data stripes we need to + * skip. + */ + return (stripe_index / map->sub_stripes) * map->stripe_len + bg->start; +} + +/* Get the mirror number for the stripe */ +static int simple_stripe_mirror_num(struct map_lookup *map, int stripe_index) +{ + ASSERT(map->type & (BTRFS_BLOCK_GROUP_RAID0 | + BTRFS_BLOCK_GROUP_RAID10)); + ASSERT(stripe_index < map->num_stripes); + + /* For RAID0, it's fixed to 1, for RAID10 it's 0,1,0,1... */ + return stripe_index % map->sub_stripes + 1; +} + +static int scrub_simple_stripe(struct scrub_ctx *sctx, + struct btrfs_root *extent_root, + struct btrfs_root *csum_root, + struct btrfs_block_group *bg, + struct map_lookup *map, + struct btrfs_device *device, + int stripe_index) +{ + const u64 logical_increment = simple_stripe_full_stripe_len(map); + const u64 orig_logical = simple_stripe_get_logical(map, bg, stripe_index); + const u64 orig_physical = map->stripes[stripe_index].physical; + const int mirror_num = simple_stripe_mirror_num(map, stripe_index); + u64 cur_logical = orig_logical; + u64 cur_physical = orig_physical; + int ret = 0; + + while (cur_logical < bg->start + bg->length) { + /* + * Inside each stripe, RAID0 is just SINGLE, and RAID10 is + * just RAID1, so we can reuse scrub_simple_mirror() to scrub + * this stripe. + */ + ret = scrub_simple_mirror(sctx, extent_root, csum_root, bg, map, + cur_logical, map->stripe_len, device, + cur_physical, mirror_num); + if (ret) + return ret; + /* Skip to next stripe which belongs to the target device */ + cur_logical += logical_increment; + /* For physical offset, we just go to next stripe */ + cur_physical += map->stripe_len; + } + return ret; +} + static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx, struct btrfs_block_group *bg, struct map_lookup *map, @@ -3175,59 +3437,22 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx, struct btrfs_fs_info *fs_info = sctx->fs_info; struct btrfs_root *root; struct btrfs_root *csum_root; - struct btrfs_extent_item *extent; struct blk_plug plug; + const u64 profile = map->type & BTRFS_BLOCK_GROUP_PROFILE_MASK; const u64 chunk_logical = bg->start; - u64 flags; int ret; - int slot; - u64 nstripes; - struct extent_buffer *l; - u64 physical; + u64 physical = map->stripes[stripe_index].physical; + const u64 physical_end = physical + dev_extent_len; u64 logical; u64 logic_end; - u64 physical_end; - u64 generation; - int mirror_num; - struct btrfs_key key; + /* The logical increment after finishing one stripe */ u64 increment; + /* Offset inside the chunk */ u64 offset; - u64 extent_logical; - u64 extent_physical; - /* - * Unlike chunk length, extent length should never go beyond - * BTRFS_MAX_EXTENT_SIZE, thus u32 is enough here. - */ - u32 extent_len; u64 stripe_logical; u64 stripe_end; - struct btrfs_device *extent_dev; - int extent_mirror_num; int stop_loop = 0; - physical = map->stripes[stripe_index].physical; - offset = 0; - nstripes = div64_u64(dev_extent_len, map->stripe_len); - mirror_num = 1; - increment = map->stripe_len; - if (map->type & BTRFS_BLOCK_GROUP_RAID0) { - offset = map->stripe_len * stripe_index; - increment = map->stripe_len * map->num_stripes; - } else if (map->type & BTRFS_BLOCK_GROUP_RAID10) { - int factor = map->num_stripes / map->sub_stripes; - offset = map->stripe_len * (stripe_index / map->sub_stripes); - increment = map->stripe_len * factor; - mirror_num = stripe_index % map->sub_stripes + 1; - } else if (map->type & BTRFS_BLOCK_GROUP_RAID1_MASK) { - mirror_num = stripe_index % map->num_stripes + 1; - } else if (map->type & BTRFS_BLOCK_GROUP_DUP) { - mirror_num = stripe_index % map->num_stripes + 1; - } else if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) { - get_raid56_logic_offset(physical, stripe_index, map, &offset, - NULL); - increment = map->stripe_len * nr_data_stripes(map); - } - path = btrfs_alloc_path(); if (!path) return -ENOMEM; @@ -3241,21 +3466,12 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx, path->skip_locking = 1; path->reada = READA_FORWARD; - logical = chunk_logical + offset; - physical_end = physical + nstripes * map->stripe_len; - if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) { - get_raid56_logic_offset(physical_end, stripe_index, - map, &logic_end, NULL); - logic_end += chunk_logical; - } else { - logic_end = logical + increment * nstripes; - } wait_event(sctx->list_wait, atomic_read(&sctx->bios_in_flight) == 0); scrub_blocked_if_needed(fs_info); - root = btrfs_extent_root(fs_info, logical); - csum_root = btrfs_csum_root(fs_info, logical); + root = btrfs_extent_root(fs_info, bg->start); + csum_root = btrfs_csum_root(fs_info, bg->start); /* * collect all data csums for the stripe to avoid seeking during @@ -3272,241 +3488,83 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx, } /* - * now find all extents for each stripe and scrub them + * There used to be a big double loop to handle all profiles using the + * same routine, which grows larger and more gross over time. + * + * So here we handle each profile differently, so simpler profiles + * have simpler scrubbing function. */ - ret = 0; - while (physical < physical_end) { - /* - * canceled? - */ - if (atomic_read(&fs_info->scrub_cancel_req) || - atomic_read(&sctx->cancel_req)) { - ret = -ECANCELED; - goto out; - } + if (!(profile & (BTRFS_BLOCK_GROUP_RAID0 | BTRFS_BLOCK_GROUP_RAID10 | + BTRFS_BLOCK_GROUP_RAID56_MASK))) { /* - * check to see if we have to pause + * Above check rules out all complex profile, the remaining + * profiles are SINGLE|DUP|RAID1|RAID1C*, which is simple + * mirrored duplication without stripe. + * + * Only @physical and @mirror_num needs to calculated using + * @stripe_index. */ - if (atomic_read(&fs_info->scrub_pause_req)) { - /* push queued extents */ - sctx->flush_all_writes = true; - scrub_submit(sctx); - mutex_lock(&sctx->wr_lock); - scrub_wr_submit(sctx); - mutex_unlock(&sctx->wr_lock); - wait_event(sctx->list_wait, - atomic_read(&sctx->bios_in_flight) == 0); - sctx->flush_all_writes = false; - scrub_blocked_if_needed(fs_info); - } - - if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) { - ret = get_raid56_logic_offset(physical, stripe_index, - map, &logical, - &stripe_logical); - logical += chunk_logical; - if (ret) { - /* it is parity strip */ - stripe_logical += chunk_logical; - stripe_end = stripe_logical + increment; - ret = scrub_raid56_parity(sctx, map, scrub_dev, - stripe_logical, - stripe_end); - if (ret) - goto out; - goto skip; - } - } - - if (btrfs_fs_incompat(fs_info, SKINNY_METADATA)) - key.type = BTRFS_METADATA_ITEM_KEY; - else - key.type = BTRFS_EXTENT_ITEM_KEY; - key.objectid = logical; - key.offset = (u64)-1; - - ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); - if (ret < 0) - goto out; - - if (ret > 0) { - ret = btrfs_previous_extent_item(root, path, 0); - if (ret < 0) - goto out; - if (ret > 0) { - /* there's no smaller item, so stick with the - * larger one */ - btrfs_release_path(path); - ret = btrfs_search_slot(NULL, root, &key, - path, 0, 0); - if (ret < 0) - goto out; - } - } - - stop_loop = 0; - while (1) { - u64 bytes; - - l = path->nodes[0]; - slot = path->slots[0]; - if (slot >= btrfs_header_nritems(l)) { - ret = btrfs_next_leaf(root, path); - if (ret == 0) - continue; - if (ret < 0) - goto out; - - stop_loop = 1; - break; - } - btrfs_item_key_to_cpu(l, &key, slot); - - if (key.type != BTRFS_EXTENT_ITEM_KEY && - key.type != BTRFS_METADATA_ITEM_KEY) - goto next; - - if (key.type == BTRFS_METADATA_ITEM_KEY) - bytes = fs_info->nodesize; - else - bytes = key.offset; - - if (key.objectid + bytes <= logical) - goto next; - - if (key.objectid >= logical + map->stripe_len) { - /* out of this device extent */ - if (key.objectid >= logic_end) - stop_loop = 1; - break; - } - - /* - * If our block group was removed in the meanwhile, just - * stop scrubbing since there is no point in continuing. - * Continuing would prevent reusing its device extents - * for new block groups for a long time. - */ - spin_lock(&bg->lock); - if (bg->removed) { - spin_unlock(&bg->lock); - ret = 0; - goto out; - } - spin_unlock(&bg->lock); - - extent = btrfs_item_ptr(l, slot, - struct btrfs_extent_item); - flags = btrfs_extent_flags(l, extent); - generation = btrfs_extent_generation(l, extent); - - if ((flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) && - (key.objectid < logical || - key.objectid + bytes > - logical + map->stripe_len)) { - btrfs_err(fs_info, - "scrub: tree block %llu spanning stripes, ignored. logical=%llu", - key.objectid, logical); - spin_lock(&sctx->stat_lock); - sctx->stat.uncorrectable_errors++; - spin_unlock(&sctx->stat_lock); - goto next; - } - -again: - extent_logical = key.objectid; - ASSERT(bytes <= U32_MAX); - extent_len = bytes; - - /* - * trim extent to this stripe - */ - if (extent_logical < logical) { - extent_len -= logical - extent_logical; - extent_logical = logical; - } - if (extent_logical + extent_len > - logical + map->stripe_len) { - extent_len = logical + map->stripe_len - - extent_logical; - } + ret = scrub_simple_mirror(sctx, root, csum_root, bg, map, + bg->start, bg->length, scrub_dev, + map->stripes[stripe_index].physical, + stripe_index + 1); + offset = 0; + goto out; + } + if (profile & (BTRFS_BLOCK_GROUP_RAID0 | BTRFS_BLOCK_GROUP_RAID10)) { + ret = scrub_simple_stripe(sctx, root, csum_root, bg, map, + scrub_dev, stripe_index); + offset = map->stripe_len * (stripe_index / map->sub_stripes); + goto out; + } - extent_physical = extent_logical - logical + physical; - extent_dev = scrub_dev; - extent_mirror_num = mirror_num; - if (sctx->is_dev_replace) - scrub_remap_extent(fs_info, extent_logical, - extent_len, &extent_physical, - &extent_dev, - &extent_mirror_num); - - if (flags & BTRFS_EXTENT_FLAG_DATA) { - ret = btrfs_lookup_csums_range(csum_root, - extent_logical, - extent_logical + extent_len - 1, - &sctx->csum_list, 1); - if (ret) - goto out; - } + /* Only RAID56 goes through the old code */ + ASSERT(map->type & BTRFS_BLOCK_GROUP_RAID56_MASK); + ret = 0; - ret = scrub_extent(sctx, map, extent_logical, extent_len, - extent_physical, extent_dev, flags, - generation, extent_mirror_num, - extent_logical - logical + physical); + /* Calculate the logical end of the stripe */ + get_raid56_logic_offset(physical_end, stripe_index, + map, &logic_end, NULL); + logic_end += chunk_logical; - scrub_free_csums(sctx); + /* Initialize @offset in case we need to go to out: label */ + get_raid56_logic_offset(physical, stripe_index, map, &offset, NULL); + increment = map->stripe_len * nr_data_stripes(map); + /* + * Due to the rotation, for RAID56 it's better to iterate each stripe + * using their physical offset. + */ + while (physical < physical_end) { + ret = get_raid56_logic_offset(physical, stripe_index, map, + &logical, &stripe_logical); + logical += chunk_logical; + if (ret) { + /* it is parity strip */ + stripe_logical += chunk_logical; + stripe_end = stripe_logical + increment; + ret = scrub_raid56_parity(sctx, map, scrub_dev, + stripe_logical, + stripe_end); if (ret) goto out; + goto next; + } - if (sctx->is_dev_replace) - sync_replace_for_zoned(sctx); - - if (extent_logical + extent_len < - key.objectid + bytes) { - if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) { - /* - * loop until we find next data stripe - * or we have finished all stripes. - */ -loop: - physical += map->stripe_len; - ret = get_raid56_logic_offset(physical, - stripe_index, map, - &logical, &stripe_logical); - logical += chunk_logical; - - if (ret && physical < physical_end) { - stripe_logical += chunk_logical; - stripe_end = stripe_logical + - increment; - ret = scrub_raid56_parity(sctx, - map, scrub_dev, - stripe_logical, - stripe_end); - if (ret) - goto out; - goto loop; - } - } else { - physical += map->stripe_len; - logical += increment; - } - if (logical < key.objectid + bytes) { - cond_resched(); - goto again; - } - - if (physical >= physical_end) { - stop_loop = 1; - break; - } - } + /* + * Now we're at a data stripe, scrub each extents in the range. + * + * At this stage, if we ignore the repair part, inside each data + * stripe it is no different than SINGLE profile. + * We can reuse scrub_simple_mirror() here, as the repair part + * is still based on @mirror_num. + */ + ret = scrub_simple_mirror(sctx, root, csum_root, bg, map, + logical, map->stripe_len, + scrub_dev, physical, 1); + if (ret < 0) + goto out; next: - path->slots[0]++; - } - btrfs_release_path(path); -skip: logical += increment; physical += map->stripe_len; spin_lock(&sctx->stat_lock); @@ -3699,6 +3757,31 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx, if (!cache) goto skip; + ASSERT(cache->start <= chunk_offset); + /* + * We are using the commit root to search for device extents, so + * that means we could have found a device extent item from a + * block group that was deleted in the current transaction. The + * logical start offset of the deleted block group, stored at + * @chunk_offset, might be part of the logical address range of + * a new block group (which uses different physical extents). + * In this case btrfs_lookup_block_group() has returned the new + * block group, and its start address is less than @chunk_offset. + * + * We skip such new block groups, because it's pointless to + * process them, as we won't find their extents because we search + * for them using the commit root of the extent tree. For a device + * replace it's also fine to skip it, we won't miss copying them + * to the target device because we have the write duplication + * setup through the regular write path (by btrfs_map_block()), + * and we have committed a transaction when we started the device + * replace, right after setting up the device replace state. + */ + if (cache->start < chunk_offset) { + btrfs_put_block_group(cache); + goto skip; + } + if (sctx->is_dev_replace && btrfs_is_zoned(fs_info)) { spin_lock(&cache->lock); if (!cache->to_copy) { @@ -3822,7 +3905,6 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx, dev_replace->item_needs_writeback = 1; up_write(&dev_replace->rwsem); - ASSERT(cache->start == chunk_offset); ret = scrub_chunk(sctx, cache, scrub_dev, found_key.offset, dev_extent_len); @@ -3940,9 +4022,9 @@ static noinline_for_stack int scrub_supers(struct scrub_ctx *sctx, if (!btrfs_check_super_location(scrub_dev, bytenr)) continue; - ret = scrub_pages(sctx, bytenr, BTRFS_SUPER_INFO_SIZE, bytenr, - scrub_dev, BTRFS_EXTENT_FLAG_SUPER, gen, i, - NULL, bytenr); + ret = scrub_sectors(sctx, bytenr, BTRFS_SUPER_INFO_SIZE, bytenr, + scrub_dev, BTRFS_EXTENT_FLAG_SUPER, gen, i, + NULL, bytenr); if (ret) return ret; } @@ -3955,22 +4037,23 @@ static void scrub_workers_put(struct btrfs_fs_info *fs_info) { if (refcount_dec_and_mutex_lock(&fs_info->scrub_workers_refcnt, &fs_info->scrub_lock)) { - struct btrfs_workqueue *scrub_workers = NULL; - struct btrfs_workqueue *scrub_wr_comp = NULL; - struct btrfs_workqueue *scrub_parity = NULL; - - scrub_workers = fs_info->scrub_workers; - scrub_wr_comp = fs_info->scrub_wr_completion_workers; - scrub_parity = fs_info->scrub_parity_workers; + struct workqueue_struct *scrub_workers = fs_info->scrub_workers; + struct workqueue_struct *scrub_wr_comp = + fs_info->scrub_wr_completion_workers; + struct workqueue_struct *scrub_parity = + fs_info->scrub_parity_workers; fs_info->scrub_workers = NULL; fs_info->scrub_wr_completion_workers = NULL; fs_info->scrub_parity_workers = NULL; mutex_unlock(&fs_info->scrub_lock); - btrfs_destroy_workqueue(scrub_workers); - btrfs_destroy_workqueue(scrub_wr_comp); - btrfs_destroy_workqueue(scrub_parity); + if (scrub_workers) + destroy_workqueue(scrub_workers); + if (scrub_wr_comp) + destroy_workqueue(scrub_wr_comp); + if (scrub_parity) + destroy_workqueue(scrub_parity); } } @@ -3980,9 +4063,9 @@ static void scrub_workers_put(struct btrfs_fs_info *fs_info) static noinline_for_stack int scrub_workers_get(struct btrfs_fs_info *fs_info, int is_dev_replace) { - struct btrfs_workqueue *scrub_workers = NULL; - struct btrfs_workqueue *scrub_wr_comp = NULL; - struct btrfs_workqueue *scrub_parity = NULL; + struct workqueue_struct *scrub_workers = NULL; + struct workqueue_struct *scrub_wr_comp = NULL; + struct workqueue_struct *scrub_parity = NULL; unsigned int flags = WQ_FREEZABLE | WQ_UNBOUND; int max_active = fs_info->thread_pool_size; int ret = -ENOMEM; @@ -3990,18 +4073,16 @@ static noinline_for_stack int scrub_workers_get(struct btrfs_fs_info *fs_info, if (refcount_inc_not_zero(&fs_info->scrub_workers_refcnt)) return 0; - scrub_workers = btrfs_alloc_workqueue(fs_info, "scrub", flags, - is_dev_replace ? 1 : max_active, 4); + scrub_workers = alloc_workqueue("btrfs-scrub", flags, + is_dev_replace ? 1 : max_active); if (!scrub_workers) goto fail_scrub_workers; - scrub_wr_comp = btrfs_alloc_workqueue(fs_info, "scrubwrc", flags, - max_active, 2); + scrub_wr_comp = alloc_workqueue("btrfs-scrubwrc", flags, max_active); if (!scrub_wr_comp) goto fail_scrub_wr_completion_workers; - scrub_parity = btrfs_alloc_workqueue(fs_info, "scrubparity", flags, - max_active, 2); + scrub_parity = alloc_workqueue("btrfs-scrubparity", flags, max_active); if (!scrub_parity) goto fail_scrub_parity_workers; @@ -4022,11 +4103,11 @@ static noinline_for_stack int scrub_workers_get(struct btrfs_fs_info *fs_info, mutex_unlock(&fs_info->scrub_lock); ret = 0; - btrfs_destroy_workqueue(scrub_parity); + destroy_workqueue(scrub_parity); fail_scrub_parity_workers: - btrfs_destroy_workqueue(scrub_wr_comp); + destroy_workqueue(scrub_wr_comp); fail_scrub_wr_completion_workers: - btrfs_destroy_workqueue(scrub_workers); + destroy_workqueue(scrub_workers); fail_scrub_workers: return ret; } @@ -4058,18 +4139,16 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start, } if (fs_info->nodesize > - PAGE_SIZE * SCRUB_MAX_PAGES_PER_BLOCK || - fs_info->sectorsize > PAGE_SIZE * SCRUB_MAX_PAGES_PER_BLOCK) { + SCRUB_MAX_SECTORS_PER_BLOCK << fs_info->sectorsize_bits || + fs_info->sectorsize > PAGE_SIZE * SCRUB_MAX_SECTORS_PER_BLOCK) { /* - * would exhaust the array bounds of pagev member in + * Would exhaust the array bounds of sectorv member in * struct scrub_block */ btrfs_err(fs_info, - "scrub: size assumption nodesize and sectorsize <= SCRUB_MAX_PAGES_PER_BLOCK (%d <= %d && %d <= %d) fails", - fs_info->nodesize, - SCRUB_MAX_PAGES_PER_BLOCK, - fs_info->sectorsize, - SCRUB_MAX_PAGES_PER_BLOCK); +"scrub: nodesize and sectorsize <= SCRUB_MAX_SECTORS_PER_BLOCK (%d <= %d && %d <= %d) fails", + fs_info->nodesize, SCRUB_MAX_SECTORS_PER_BLOCK, + fs_info->sectorsize, SCRUB_MAX_SECTORS_PER_BLOCK); return -EINVAL; } @@ -4137,7 +4216,7 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start, /* * In order to avoid deadlock with reclaim when there is a transaction * trying to pause scrub, make sure we use GFP_NOFS for all the - * allocations done at btrfs_scrub_pages() and scrub_pages_for_parity() + * allocations done at btrfs_scrub_sectors() and scrub_sectors_for_parity() * invoked by our callees. The pausing request is done when the * transaction commit starts, and it blocks the transaction until scrub * is paused (done at specific points at scrub_stripe() or right above @@ -4271,11 +4350,11 @@ int btrfs_scrub_progress(struct btrfs_fs_info *fs_info, u64 devid, return dev ? (sctx ? 0 : -ENOTCONN) : -ENODEV; } -static void scrub_remap_extent(struct btrfs_fs_info *fs_info, - u64 extent_logical, u32 extent_len, - u64 *extent_physical, - struct btrfs_device **extent_dev, - int *extent_mirror_num) +static void scrub_find_good_copy(struct btrfs_fs_info *fs_info, + u64 extent_logical, u32 extent_len, + u64 *extent_physical, + struct btrfs_device **extent_dev, + int *extent_mirror_num) { u64 mapped_length; struct btrfs_io_context *bioc = NULL; diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 7d1642937274..fa56890ff81f 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -10,7 +10,6 @@ #include <linux/mount.h> #include <linux/xattr.h> #include <linux/posix_acl_xattr.h> -#include <linux/radix-tree.h> #include <linux/vmalloc.h> #include <linux/string.h> #include <linux/compat.h> @@ -128,11 +127,18 @@ struct send_ctx { struct list_head new_refs; struct list_head deleted_refs; - struct radix_tree_root name_cache; + struct xarray name_cache; struct list_head name_cache_list; int name_cache_size; + /* + * The inode we are currently processing. It's not NULL only when we + * need to issue write commands for data extents from this inode. + */ + struct inode *cur_inode; struct file_ra_state ra; + u64 page_cache_clear_start; + bool clean_page_cache; /* * We process inodes by their increasing order, so if before an @@ -262,14 +268,13 @@ struct orphan_dir_info { struct name_cache_entry { struct list_head list; /* - * radix_tree has only 32bit entries but we need to handle 64bit inums. - * We use the lower 32bit of the 64bit inum to store it in the tree. If - * more then one inum would fall into the same entry, we use radix_list - * to store the additional entries. radix_list is also used to store - * entries where two entries have the same inum but different - * generations. + * On 32bit kernels, xarray has only 32bit indices, but we need to + * handle 64bit inums. We use the lower 32bit of the 64bit inum to store + * it in the tree. If more than one inum would fall into the same entry, + * we use inum_aliases to store the additional entries. inum_aliases is + * also used to store entries with the same inum but different generations. */ - struct list_head radix_list; + struct list_head inum_aliases; u64 ino; u64 gen; u64 parent_ino; @@ -2019,9 +2024,9 @@ out: } /* - * Insert a name cache entry. On 32bit kernels the radix tree index is 32bit, + * Insert a name cache entry. On 32bit kernels the xarray index is 32bit, * so we need to do some special handling in case we have clashes. This function - * takes care of this with the help of name_cache_entry::radix_list. + * takes care of this with the help of name_cache_entry::inum_aliases. * In case of error, nce is kfreed. */ static int name_cache_insert(struct send_ctx *sctx, @@ -2030,8 +2035,7 @@ static int name_cache_insert(struct send_ctx *sctx, int ret = 0; struct list_head *nce_head; - nce_head = radix_tree_lookup(&sctx->name_cache, - (unsigned long)nce->ino); + nce_head = xa_load(&sctx->name_cache, (unsigned long)nce->ino); if (!nce_head) { nce_head = kmalloc(sizeof(*nce_head), GFP_KERNEL); if (!nce_head) { @@ -2040,14 +2044,14 @@ static int name_cache_insert(struct send_ctx *sctx, } INIT_LIST_HEAD(nce_head); - ret = radix_tree_insert(&sctx->name_cache, nce->ino, nce_head); + ret = xa_insert(&sctx->name_cache, nce->ino, nce_head, GFP_KERNEL); if (ret < 0) { kfree(nce_head); kfree(nce); return ret; } } - list_add_tail(&nce->radix_list, nce_head); + list_add_tail(&nce->inum_aliases, nce_head); list_add_tail(&nce->list, &sctx->name_cache_list); sctx->name_cache_size++; @@ -2059,15 +2063,14 @@ static void name_cache_delete(struct send_ctx *sctx, { struct list_head *nce_head; - nce_head = radix_tree_lookup(&sctx->name_cache, - (unsigned long)nce->ino); + nce_head = xa_load(&sctx->name_cache, (unsigned long)nce->ino); if (!nce_head) { btrfs_err(sctx->send_root->fs_info, "name_cache_delete lookup failed ino %llu cache size %d, leaking memory", nce->ino, sctx->name_cache_size); } - list_del(&nce->radix_list); + list_del(&nce->inum_aliases); list_del(&nce->list); sctx->name_cache_size--; @@ -2075,7 +2078,7 @@ static void name_cache_delete(struct send_ctx *sctx, * We may not get to the final release of nce_head if the lookup fails */ if (nce_head && list_empty(nce_head)) { - radix_tree_delete(&sctx->name_cache, (unsigned long)nce->ino); + xa_erase(&sctx->name_cache, (unsigned long)nce->ino); kfree(nce_head); } } @@ -2086,11 +2089,11 @@ static struct name_cache_entry *name_cache_search(struct send_ctx *sctx, struct list_head *nce_head; struct name_cache_entry *cur; - nce_head = radix_tree_lookup(&sctx->name_cache, (unsigned long)ino); + nce_head = xa_load(&sctx->name_cache, (unsigned long)ino); if (!nce_head) return NULL; - list_for_each_entry(cur, nce_head, radix_list) { + list_for_each_entry(cur, nce_head, inum_aliases) { if (cur->ino == ino && cur->gen == gen) return cur; } @@ -2675,61 +2678,43 @@ out: static int did_create_dir(struct send_ctx *sctx, u64 dir) { int ret = 0; + int iter_ret = 0; struct btrfs_path *path = NULL; struct btrfs_key key; struct btrfs_key found_key; struct btrfs_key di_key; - struct extent_buffer *eb; struct btrfs_dir_item *di; - int slot; path = alloc_path_for_send(); - if (!path) { - ret = -ENOMEM; - goto out; - } + if (!path) + return -ENOMEM; key.objectid = dir; key.type = BTRFS_DIR_INDEX_KEY; key.offset = 0; - ret = btrfs_search_slot(NULL, sctx->send_root, &key, path, 0, 0); - if (ret < 0) - goto out; - while (1) { - eb = path->nodes[0]; - slot = path->slots[0]; - if (slot >= btrfs_header_nritems(eb)) { - ret = btrfs_next_leaf(sctx->send_root, path); - if (ret < 0) { - goto out; - } else if (ret > 0) { - ret = 0; - break; - } - continue; - } + btrfs_for_each_slot(sctx->send_root, &key, &found_key, path, iter_ret) { + struct extent_buffer *eb = path->nodes[0]; - btrfs_item_key_to_cpu(eb, &found_key, slot); if (found_key.objectid != key.objectid || found_key.type != key.type) { ret = 0; - goto out; + break; } - di = btrfs_item_ptr(eb, slot, struct btrfs_dir_item); + di = btrfs_item_ptr(eb, path->slots[0], struct btrfs_dir_item); btrfs_dir_item_key_to_cpu(eb, di, &di_key); if (di_key.type != BTRFS_ROOT_ITEM_KEY && di_key.objectid < sctx->send_progress) { ret = 1; - goto out; + break; } - - path->slots[0]++; } + /* Catch error found during iteration */ + if (iter_ret < 0) + ret = iter_ret; -out: btrfs_free_path(path); return ret; } @@ -2933,6 +2918,7 @@ static int can_rmdir(struct send_ctx *sctx, u64 dir, u64 dir_gen, u64 send_progress) { int ret = 0; + int iter_ret = 0; struct btrfs_root *root = sctx->parent_root; struct btrfs_path *path; struct btrfs_key key; @@ -2959,23 +2945,9 @@ static int can_rmdir(struct send_ctx *sctx, u64 dir, u64 dir_gen, if (odi) key.offset = odi->last_dir_index_offset; - ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); - if (ret < 0) - goto out; - - while (1) { + btrfs_for_each_slot(root, &key, &found_key, path, iter_ret) { struct waiting_dir_move *dm; - if (path->slots[0] >= btrfs_header_nritems(path->nodes[0])) { - ret = btrfs_next_leaf(root, path); - if (ret < 0) - goto out; - else if (ret > 0) - break; - continue; - } - btrfs_item_key_to_cpu(path->nodes[0], &found_key, - path->slots[0]); if (found_key.objectid != key.objectid || found_key.type != key.type) break; @@ -3010,8 +2982,10 @@ static int can_rmdir(struct send_ctx *sctx, u64 dir, u64 dir_gen, ret = 0; goto out; } - - path->slots[0]++; + } + if (iter_ret < 0) { + ret = iter_ret; + goto out; } free_orphan_dir_info(sctx, odi); @@ -3579,7 +3553,7 @@ static int check_ino_in_path(struct btrfs_root *root, } /* - * Check if ino ino1 is an ancestor of inode ino2 in the given root for any + * Check if inode ino1 is an ancestor of inode ino2 in the given root for any * possible path (in case ino2 is not a directory and has multiple hard links). * Return 1 if true, 0 if false and < 0 on error. */ @@ -3591,6 +3565,7 @@ static int is_ancestor(struct btrfs_root *root, { bool free_fs_path = false; int ret = 0; + int iter_ret = 0; struct btrfs_path *path = NULL; struct btrfs_key key; @@ -3611,26 +3586,12 @@ static int is_ancestor(struct btrfs_root *root, key.type = BTRFS_INODE_REF_KEY; key.offset = 0; - ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); - if (ret < 0) - goto out; - - while (true) { + btrfs_for_each_slot(root, &key, &key, path, iter_ret) { struct extent_buffer *leaf = path->nodes[0]; int slot = path->slots[0]; u32 cur_offset = 0; u32 item_size; - if (slot >= btrfs_header_nritems(leaf)) { - ret = btrfs_next_leaf(root, path); - if (ret < 0) - goto out; - if (ret > 0) - break; - continue; - } - - btrfs_item_key_to_cpu(leaf, &key, slot); if (key.objectid != ino2) break; if (key.type != BTRFS_INODE_REF_KEY && @@ -3668,10 +3629,12 @@ static int is_ancestor(struct btrfs_root *root, if (ret) goto out; } - path->slots[0]++; } ret = 0; - out: + if (iter_ret < 0) + ret = iter_ret; + +out: btrfs_free_path(path); if (free_fs_path) fs_path_free(fs_path); @@ -4551,13 +4514,12 @@ out: static int process_all_refs(struct send_ctx *sctx, enum btrfs_compare_tree_result cmd) { - int ret; + int ret = 0; + int iter_ret = 0; struct btrfs_root *root; struct btrfs_path *path; struct btrfs_key key; struct btrfs_key found_key; - struct extent_buffer *eb; - int slot; iterate_inode_ref_t cb; int pending_move = 0; @@ -4581,24 +4543,7 @@ static int process_all_refs(struct send_ctx *sctx, key.objectid = sctx->cmp_key->objectid; key.type = BTRFS_INODE_REF_KEY; key.offset = 0; - ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); - if (ret < 0) - goto out; - - while (1) { - eb = path->nodes[0]; - slot = path->slots[0]; - if (slot >= btrfs_header_nritems(eb)) { - ret = btrfs_next_leaf(root, path); - if (ret < 0) - goto out; - else if (ret > 0) - break; - continue; - } - - btrfs_item_key_to_cpu(eb, &found_key, slot); - + btrfs_for_each_slot(root, &key, &found_key, path, iter_ret) { if (found_key.objectid != key.objectid || (found_key.type != BTRFS_INODE_REF_KEY && found_key.type != BTRFS_INODE_EXTREF_KEY)) @@ -4607,8 +4552,11 @@ static int process_all_refs(struct send_ctx *sctx, ret = iterate_inode_ref(root, path, &found_key, 0, cb, sctx); if (ret < 0) goto out; - - path->slots[0]++; + } + /* Catch error found during iteration */ + if (iter_ret < 0) { + ret = iter_ret; + goto out; } btrfs_release_path(path); @@ -4870,13 +4818,12 @@ out: static int process_all_new_xattrs(struct send_ctx *sctx) { - int ret; + int ret = 0; + int iter_ret = 0; struct btrfs_root *root; struct btrfs_path *path; struct btrfs_key key; struct btrfs_key found_key; - struct extent_buffer *eb; - int slot; path = alloc_path_for_send(); if (!path) @@ -4887,39 +4834,21 @@ static int process_all_new_xattrs(struct send_ctx *sctx) key.objectid = sctx->cmp_key->objectid; key.type = BTRFS_XATTR_ITEM_KEY; key.offset = 0; - ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); - if (ret < 0) - goto out; - - while (1) { - eb = path->nodes[0]; - slot = path->slots[0]; - if (slot >= btrfs_header_nritems(eb)) { - ret = btrfs_next_leaf(root, path); - if (ret < 0) { - goto out; - } else if (ret > 0) { - ret = 0; - break; - } - continue; - } - - btrfs_item_key_to_cpu(eb, &found_key, slot); + btrfs_for_each_slot(root, &key, &found_key, path, iter_ret) { if (found_key.objectid != key.objectid || found_key.type != key.type) { ret = 0; - goto out; + break; } ret = iterate_dir_item(root, path, __process_new_xattr, sctx); if (ret < 0) - goto out; - - path->slots[0]++; + break; } + /* Catch error found during iteration */ + if (iter_ret < 0) + ret = iter_ret; -out: btrfs_free_path(path); return ret; } @@ -4946,7 +4875,6 @@ static int put_file_data(struct send_ctx *sctx, u64 offset, u32 len) { struct btrfs_root *root = sctx->send_root; struct btrfs_fs_info *fs_info = root->fs_info; - struct inode *inode; struct page *page; pgoff_t index = offset >> PAGE_SHIFT; pgoff_t last_index; @@ -4957,40 +4885,33 @@ static int put_file_data(struct send_ctx *sctx, u64 offset, u32 len) if (ret) return ret; - inode = btrfs_iget(fs_info->sb, sctx->cur_ino, root); - if (IS_ERR(inode)) - return PTR_ERR(inode); - last_index = (offset + len - 1) >> PAGE_SHIFT; - /* initial readahead */ - memset(&sctx->ra, 0, sizeof(struct file_ra_state)); - file_ra_state_init(&sctx->ra, inode->i_mapping); - while (index <= last_index) { unsigned cur_len = min_t(unsigned, len, PAGE_SIZE - pg_offset); - page = find_lock_page(inode->i_mapping, index); + page = find_lock_page(sctx->cur_inode->i_mapping, index); if (!page) { - page_cache_sync_readahead(inode->i_mapping, &sctx->ra, - NULL, index, last_index + 1 - index); + page_cache_sync_readahead(sctx->cur_inode->i_mapping, + &sctx->ra, NULL, index, + last_index + 1 - index); - page = find_or_create_page(inode->i_mapping, index, - GFP_KERNEL); + page = find_or_create_page(sctx->cur_inode->i_mapping, + index, GFP_KERNEL); if (!page) { ret = -ENOMEM; break; } } - if (PageReadahead(page)) { - page_cache_async_readahead(inode->i_mapping, &sctx->ra, - NULL, page, index, last_index + 1 - index); - } + if (PageReadahead(page)) + page_cache_async_readahead(sctx->cur_inode->i_mapping, + &sctx->ra, NULL, page_folio(page), + index, last_index + 1 - index); if (!PageUptodate(page)) { - btrfs_readpage(NULL, page); + btrfs_read_folio(NULL, page_folio(page)); lock_page(page); if (!PageUptodate(page)) { unlock_page(page); @@ -5013,7 +4934,7 @@ static int put_file_data(struct send_ctx *sctx, u64 offset, u32 len) len -= cur_len; sctx->send_size += cur_len; } - iput(inode); + return ret; } @@ -5220,12 +5141,49 @@ static int send_extent_data(struct send_ctx *sctx, const u64 offset, const u64 len) { + const u64 end = offset + len; u64 read_size = max_send_read_size(sctx); u64 sent = 0; if (sctx->flags & BTRFS_SEND_FLAG_NO_FILE_DATA) return send_update_extent(sctx, offset, len); + if (sctx->cur_inode == NULL) { + struct btrfs_root *root = sctx->send_root; + + sctx->cur_inode = btrfs_iget(root->fs_info->sb, sctx->cur_ino, root); + if (IS_ERR(sctx->cur_inode)) { + int err = PTR_ERR(sctx->cur_inode); + + sctx->cur_inode = NULL; + return err; + } + memset(&sctx->ra, 0, sizeof(struct file_ra_state)); + file_ra_state_init(&sctx->ra, sctx->cur_inode->i_mapping); + + /* + * It's very likely there are no pages from this inode in the page + * cache, so after reading extents and sending their data, we clean + * the page cache to avoid trashing the page cache (adding pressure + * to the page cache and forcing eviction of other data more useful + * for applications). + * + * We decide if we should clean the page cache simply by checking + * if the inode's mapping nrpages is 0 when we first open it, and + * not by using something like filemap_range_has_page() before + * reading an extent because when we ask the readahead code to + * read a given file range, it may (and almost always does) read + * pages from beyond that range (see the documentation for + * page_cache_sync_readahead()), so it would not be reliable, + * because after reading the first extent future calls to + * filemap_range_has_page() would return true because the readahead + * on the previous extent resulted in reading pages of the current + * extent as well. + */ + sctx->clean_page_cache = (sctx->cur_inode->i_mapping->nrpages == 0); + sctx->page_cache_clear_start = round_down(offset, PAGE_SIZE); + } + while (sent < len) { u64 size = min(len - sent, read_size); int ret; @@ -5235,6 +5193,37 @@ static int send_extent_data(struct send_ctx *sctx, return ret; sent += size; } + + if (sctx->clean_page_cache && IS_ALIGNED(end, PAGE_SIZE)) { + /* + * Always operate only on ranges that are a multiple of the page + * size. This is not only to prevent zeroing parts of a page in + * the case of subpage sector size, but also to guarantee we evict + * pages, as passing a range that is smaller than page size does + * not evict the respective page (only zeroes part of its content). + * + * Always start from the end offset of the last range cleared. + * This is because the readahead code may (and very often does) + * reads pages beyond the range we request for readahead. So if + * we have an extent layout like this: + * + * [ extent A ] [ extent B ] [ extent C ] + * + * When we ask page_cache_sync_readahead() to read extent A, it + * may also trigger reads for pages of extent B. If we are doing + * an incremental send and extent B has not changed between the + * parent and send snapshots, some or all of its pages may end + * up being read and placed in the page cache. So when truncating + * the page cache we always start from the end offset of the + * previously processed extent up to the end of the current + * extent. + */ + truncate_inode_pages_range(&sctx->cur_inode->i_data, + sctx->page_cache_clear_start, + end - 1); + sctx->page_cache_clear_start = end; + } + return 0; } @@ -5965,13 +5954,12 @@ out: static int process_all_extents(struct send_ctx *sctx) { - int ret; + int ret = 0; + int iter_ret = 0; struct btrfs_root *root; struct btrfs_path *path; struct btrfs_key key; struct btrfs_key found_key; - struct extent_buffer *eb; - int slot; root = sctx->send_root; path = alloc_path_for_send(); @@ -5981,41 +5969,21 @@ static int process_all_extents(struct send_ctx *sctx) key.objectid = sctx->cmp_key->objectid; key.type = BTRFS_EXTENT_DATA_KEY; key.offset = 0; - ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); - if (ret < 0) - goto out; - - while (1) { - eb = path->nodes[0]; - slot = path->slots[0]; - - if (slot >= btrfs_header_nritems(eb)) { - ret = btrfs_next_leaf(root, path); - if (ret < 0) { - goto out; - } else if (ret > 0) { - ret = 0; - break; - } - continue; - } - - btrfs_item_key_to_cpu(eb, &found_key, slot); - + btrfs_for_each_slot(root, &key, &found_key, path, iter_ret) { if (found_key.objectid != key.objectid || found_key.type != key.type) { ret = 0; - goto out; + break; } ret = process_extent(sctx, path, &found_key); if (ret < 0) - goto out; - - path->slots[0]++; + break; } + /* Catch error found during iteration */ + if (iter_ret < 0) + ret = iter_ret; -out: btrfs_free_path(path); return ret; } @@ -6205,8 +6173,11 @@ static int btrfs_unlink_all_paths(struct send_ctx *sctx) { LIST_HEAD(deleted_refs); struct btrfs_path *path; + struct btrfs_root *root = sctx->parent_root; struct btrfs_key key; + struct btrfs_key found_key; struct parent_paths_ctx ctx; + int iter_ret = 0; int ret; path = alloc_path_for_send(); @@ -6216,39 +6187,26 @@ static int btrfs_unlink_all_paths(struct send_ctx *sctx) key.objectid = sctx->cur_ino; key.type = BTRFS_INODE_REF_KEY; key.offset = 0; - ret = btrfs_search_slot(NULL, sctx->parent_root, &key, path, 0, 0); - if (ret < 0) - goto out; ctx.refs = &deleted_refs; ctx.sctx = sctx; - while (true) { - struct extent_buffer *eb = path->nodes[0]; - int slot = path->slots[0]; - - if (slot >= btrfs_header_nritems(eb)) { - ret = btrfs_next_leaf(sctx->parent_root, path); - if (ret < 0) - goto out; - else if (ret > 0) - break; - continue; - } - - btrfs_item_key_to_cpu(eb, &key, slot); - if (key.objectid != sctx->cur_ino) + btrfs_for_each_slot(root, &key, &found_key, path, iter_ret) { + if (found_key.objectid != key.objectid) break; - if (key.type != BTRFS_INODE_REF_KEY && - key.type != BTRFS_INODE_EXTREF_KEY) + if (found_key.type != key.type && + found_key.type != BTRFS_INODE_EXTREF_KEY) break; - ret = iterate_inode_ref(sctx->parent_root, path, &key, 1, + ret = iterate_inode_ref(root, path, &found_key, 1, record_parent_ref, &ctx); if (ret < 0) goto out; - - path->slots[0]++; + } + /* Catch error found during iteration */ + if (iter_ret < 0) { + ret = iter_ret; + goto out; } while (!list_empty(&deleted_refs)) { @@ -6270,6 +6228,30 @@ out: return ret; } +static void close_current_inode(struct send_ctx *sctx) +{ + u64 i_size; + + if (sctx->cur_inode == NULL) + return; + + i_size = i_size_read(sctx->cur_inode); + + /* + * If we are doing an incremental send, we may have extents between the + * last processed extent and the i_size that have not been processed + * because they haven't changed but we may have read some of their pages + * through readahead, see the comments at send_extent_data(). + */ + if (sctx->clean_page_cache && sctx->page_cache_clear_start < i_size) + truncate_inode_pages_range(&sctx->cur_inode->i_data, + sctx->page_cache_clear_start, + round_up(i_size, PAGE_SIZE) - 1); + + iput(sctx->cur_inode); + sctx->cur_inode = NULL; +} + static int changed_inode(struct send_ctx *sctx, enum btrfs_compare_tree_result result) { @@ -6280,6 +6262,8 @@ static int changed_inode(struct send_ctx *sctx, u64 left_gen = 0; u64 right_gen = 0; + close_current_inode(sctx); + sctx->cur_ino = key->objectid; sctx->cur_inode_new_gen = 0; sctx->cur_inode_last_extent = (u64)-1; @@ -7534,7 +7518,7 @@ long btrfs_ioctl_send(struct inode *inode, struct btrfs_ioctl_send_args *arg) INIT_LIST_HEAD(&sctx->new_refs); INIT_LIST_HEAD(&sctx->deleted_refs); - INIT_RADIX_TREE(&sctx->name_cache, GFP_KERNEL); + xa_init_flags(&sctx->name_cache, GFP_KERNEL); INIT_LIST_HEAD(&sctx->name_cache_list); sctx->flags = arg->flags; @@ -7766,6 +7750,8 @@ out: name_cache_free(sctx); + close_current_inode(sctx); + kfree(sctx); } diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c index b87931a458eb..2dd8754cb990 100644 --- a/fs/btrfs/space-info.c +++ b/fs/btrfs/space-info.c @@ -181,6 +181,12 @@ void btrfs_clear_space_info_full(struct btrfs_fs_info *info) found->full = 0; } +/* + * Block groups with more than this value (percents) of unusable space will be + * scheduled for background reclaim. + */ +#define BTRFS_DEFAULT_ZONED_RECLAIM_THRESH (75) + static int create_space_info(struct btrfs_fs_info *info, u64 flags) { @@ -203,6 +209,9 @@ static int create_space_info(struct btrfs_fs_info *info, u64 flags) INIT_LIST_HEAD(&space_info->priority_tickets); space_info->clamp = 1; + if (btrfs_is_zoned(info)) + space_info->bg_reclaim_threshold = BTRFS_DEFAULT_ZONED_RECLAIM_THRESH; + ret = btrfs_sysfs_add_space_info_type(info, space_info); if (ret) return ret; @@ -519,7 +528,7 @@ static void shrink_delalloc(struct btrfs_fs_info *fs_info, items = calc_reclaim_items_nr(fs_info, to_reclaim) * 2; } - trans = (struct btrfs_trans_handle *)current->journal_info; + trans = current->journal_info; /* * If we are doing more ordered than delalloc we need to just wait on diff --git a/fs/btrfs/space-info.h b/fs/btrfs/space-info.h index d841fed73492..c096695598c1 100644 --- a/fs/btrfs/space-info.h +++ b/fs/btrfs/space-info.h @@ -3,6 +3,8 @@ #ifndef BTRFS_SPACE_INFO_H #define BTRFS_SPACE_INFO_H +#include "volumes.h" + struct btrfs_space_info { spinlock_t lock; @@ -24,6 +26,12 @@ struct btrfs_space_info { the space info if we had an ENOSPC in the allocator. */ + /* + * Once a block group drops below this threshold (percents) we'll + * schedule it for reclaim. + */ + int bg_reclaim_threshold; + int clamp; /* Used to scale our threshold for preemptive flushing. The value is >> clamp, so turns out to be a 2^clamp divisor. */ diff --git a/fs/btrfs/subpage.c b/fs/btrfs/subpage.c index ef7ae20d2b77..a105b291444f 100644 --- a/fs/btrfs/subpage.c +++ b/fs/btrfs/subpage.c @@ -63,6 +63,29 @@ * This means a slightly higher tree locking latency. */ +bool btrfs_is_subpage(const struct btrfs_fs_info *fs_info, struct page *page) +{ + if (fs_info->sectorsize >= PAGE_SIZE) + return false; + + /* + * Only data pages (either through DIO or compression) can have no + * mapping. And if page->mapping->host is data inode, it's subpage. + * As we have ruled our sectorsize >= PAGE_SIZE case already. + */ + if (!page->mapping || !page->mapping->host || + is_data_inode(page->mapping->host)) + return true; + + /* + * Now the only remaining case is metadata, which we only go subpage + * routine if nodesize < PAGE_SIZE. + */ + if (fs_info->nodesize < PAGE_SIZE) + return true; + return false; +} + void btrfs_init_subpage_info(struct btrfs_subpage_info *subpage_info, u32 sectorsize) { unsigned int cur = 0; @@ -107,7 +130,7 @@ int btrfs_attach_subpage(const struct btrfs_fs_info *fs_info, ASSERT(PageLocked(page)); /* Either not subpage, or the page already has private attached */ - if (fs_info->sectorsize == PAGE_SIZE || PagePrivate(page)) + if (!btrfs_is_subpage(fs_info, page) || PagePrivate(page)) return 0; subpage = btrfs_alloc_subpage(fs_info, type); @@ -124,10 +147,10 @@ void btrfs_detach_subpage(const struct btrfs_fs_info *fs_info, struct btrfs_subpage *subpage; /* Either not subpage, or already detached */ - if (fs_info->sectorsize == PAGE_SIZE || !PagePrivate(page)) + if (!btrfs_is_subpage(fs_info, page) || !PagePrivate(page)) return; - subpage = (struct btrfs_subpage *)detach_page_private(page); + subpage = detach_page_private(page); ASSERT(subpage); btrfs_free_subpage(subpage); } @@ -175,7 +198,7 @@ void btrfs_page_inc_eb_refs(const struct btrfs_fs_info *fs_info, { struct btrfs_subpage *subpage; - if (fs_info->sectorsize == PAGE_SIZE) + if (!btrfs_is_subpage(fs_info, page)) return; ASSERT(PagePrivate(page) && page->mapping); @@ -190,7 +213,7 @@ void btrfs_page_dec_eb_refs(const struct btrfs_fs_info *fs_info, { struct btrfs_subpage *subpage; - if (fs_info->sectorsize == PAGE_SIZE) + if (!btrfs_is_subpage(fs_info, page)) return; ASSERT(PagePrivate(page) && page->mapping); @@ -319,7 +342,7 @@ bool btrfs_subpage_end_and_test_writer(const struct btrfs_fs_info *fs_info, int btrfs_page_start_writer_lock(const struct btrfs_fs_info *fs_info, struct page *page, u64 start, u32 len) { - if (unlikely(!fs_info) || fs_info->sectorsize == PAGE_SIZE) { + if (unlikely(!fs_info) || !btrfs_is_subpage(fs_info, page)) { lock_page(page); return 0; } @@ -336,7 +359,7 @@ int btrfs_page_start_writer_lock(const struct btrfs_fs_info *fs_info, void btrfs_page_end_writer_lock(const struct btrfs_fs_info *fs_info, struct page *page, u64 start, u32 len) { - if (unlikely(!fs_info) || fs_info->sectorsize == PAGE_SIZE) + if (unlikely(!fs_info) || !btrfs_is_subpage(fs_info, page)) return unlock_page(page); btrfs_subpage_clamp_range(page, &start, &len); if (btrfs_subpage_end_and_test_writer(fs_info, page, start, len)) @@ -620,7 +643,7 @@ IMPLEMENT_BTRFS_SUBPAGE_TEST_OP(checked); void btrfs_page_set_##name(const struct btrfs_fs_info *fs_info, \ struct page *page, u64 start, u32 len) \ { \ - if (unlikely(!fs_info) || fs_info->sectorsize == PAGE_SIZE) { \ + if (unlikely(!fs_info) || !btrfs_is_subpage(fs_info, page)) { \ set_page_func(page); \ return; \ } \ @@ -629,7 +652,7 @@ void btrfs_page_set_##name(const struct btrfs_fs_info *fs_info, \ void btrfs_page_clear_##name(const struct btrfs_fs_info *fs_info, \ struct page *page, u64 start, u32 len) \ { \ - if (unlikely(!fs_info) || fs_info->sectorsize == PAGE_SIZE) { \ + if (unlikely(!fs_info) || !btrfs_is_subpage(fs_info, page)) { \ clear_page_func(page); \ return; \ } \ @@ -638,14 +661,14 @@ void btrfs_page_clear_##name(const struct btrfs_fs_info *fs_info, \ bool btrfs_page_test_##name(const struct btrfs_fs_info *fs_info, \ struct page *page, u64 start, u32 len) \ { \ - if (unlikely(!fs_info) || fs_info->sectorsize == PAGE_SIZE) \ + if (unlikely(!fs_info) || !btrfs_is_subpage(fs_info, page)) \ return test_page_func(page); \ return btrfs_subpage_test_##name(fs_info, page, start, len); \ } \ void btrfs_page_clamp_set_##name(const struct btrfs_fs_info *fs_info, \ struct page *page, u64 start, u32 len) \ { \ - if (unlikely(!fs_info) || fs_info->sectorsize == PAGE_SIZE) { \ + if (unlikely(!fs_info) || !btrfs_is_subpage(fs_info, page)) { \ set_page_func(page); \ return; \ } \ @@ -655,7 +678,7 @@ void btrfs_page_clamp_set_##name(const struct btrfs_fs_info *fs_info, \ void btrfs_page_clamp_clear_##name(const struct btrfs_fs_info *fs_info, \ struct page *page, u64 start, u32 len) \ { \ - if (unlikely(!fs_info) || fs_info->sectorsize == PAGE_SIZE) { \ + if (unlikely(!fs_info) || !btrfs_is_subpage(fs_info, page)) { \ clear_page_func(page); \ return; \ } \ @@ -665,7 +688,7 @@ void btrfs_page_clamp_clear_##name(const struct btrfs_fs_info *fs_info, \ bool btrfs_page_clamp_test_##name(const struct btrfs_fs_info *fs_info, \ struct page *page, u64 start, u32 len) \ { \ - if (unlikely(!fs_info) || fs_info->sectorsize == PAGE_SIZE) \ + if (unlikely(!fs_info) || !btrfs_is_subpage(fs_info, page)) \ return test_page_func(page); \ btrfs_subpage_clamp_range(page, &start, &len); \ return btrfs_subpage_test_##name(fs_info, page, start, len); \ @@ -694,7 +717,7 @@ void btrfs_page_assert_not_dirty(const struct btrfs_fs_info *fs_info, return; ASSERT(!PageDirty(page)); - if (fs_info->sectorsize == PAGE_SIZE) + if (!btrfs_is_subpage(fs_info, page)) return; ASSERT(PagePrivate(page) && page->private); @@ -722,8 +745,8 @@ void btrfs_page_unlock_writer(struct btrfs_fs_info *fs_info, struct page *page, struct btrfs_subpage *subpage; ASSERT(PageLocked(page)); - /* For regular page size case, we just unlock the page */ - if (fs_info->sectorsize == PAGE_SIZE) + /* For non-subpage case, we just unlock the page */ + if (!btrfs_is_subpage(fs_info, page)) return unlock_page(page); ASSERT(PagePrivate(page) && page->private); diff --git a/fs/btrfs/subpage.h b/fs/btrfs/subpage.h index 7accb5c40d33..0e80ad336904 100644 --- a/fs/btrfs/subpage.h +++ b/fs/btrfs/subpage.h @@ -74,6 +74,8 @@ enum btrfs_subpage_type { BTRFS_SUBPAGE_DATA, }; +bool btrfs_is_subpage(const struct btrfs_fs_info *fs_info, struct page *page); + void btrfs_init_subpage_info(struct btrfs_subpage_info *subpage_info, u32 sectorsize); int btrfs_attach_subpage(const struct btrfs_fs_info *fs_info, struct page *page, enum btrfs_subpage_type type); diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index b228efe8ab6e..b1fdc6a26c76 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -261,7 +261,7 @@ static struct ratelimit_state printk_limits[] = { RATELIMIT_STATE_INIT(printk_limits[7], DEFAULT_RATELIMIT_INTERVAL, 100), }; -void __cold btrfs_printk(const struct btrfs_fs_info *fs_info, const char *fmt, ...) +void __cold _btrfs_printk(const struct btrfs_fs_info *fs_info, const char *fmt, ...) { char lvl[PRINTK_MAX_SINGLE_HEADER_LEN + 1] = "\0"; struct va_format vaf; @@ -292,10 +292,10 @@ void __cold btrfs_printk(const struct btrfs_fs_info *fs_info, const char *fmt, . char statestr[STATE_STRING_BUF_LEN]; btrfs_state_to_string(fs_info, statestr); - printk("%sBTRFS %s (device %s%s): %pV\n", lvl, type, + _printk("%sBTRFS %s (device %s%s): %pV\n", lvl, type, fs_info->sb->s_id, statestr, &vaf); } else { - printk("%sBTRFS %s: %pV\n", lvl, type, &vaf); + _printk("%sBTRFS %s: %pV\n", lvl, type, &vaf); } } @@ -1903,6 +1903,7 @@ static void btrfs_resize_thread_pool(struct btrfs_fs_info *fs_info, old_pool_size, new_pool_size); btrfs_workqueue_set_max(fs_info->workers, new_pool_size); + btrfs_workqueue_set_max(fs_info->hipri_workers, new_pool_size); btrfs_workqueue_set_max(fs_info->delalloc_workers, new_pool_size); btrfs_workqueue_set_max(fs_info->caching_workers, new_pool_size); btrfs_workqueue_set_max(fs_info->endio_workers, new_pool_size); @@ -1912,8 +1913,6 @@ static void btrfs_resize_thread_pool(struct btrfs_fs_info *fs_info, btrfs_workqueue_set_max(fs_info->endio_write_workers, new_pool_size); btrfs_workqueue_set_max(fs_info->endio_freespace_worker, new_pool_size); btrfs_workqueue_set_max(fs_info->delayed_workers, new_pool_size); - btrfs_workqueue_set_max(fs_info->scrub_wr_completion_workers, - new_pool_size); } static inline void btrfs_remount_begin(struct btrfs_fs_info *fs_info, diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c index 17389a42a3ab..92a1fa8e3da6 100644 --- a/fs/btrfs/sysfs.c +++ b/fs/btrfs/sysfs.c @@ -394,11 +394,9 @@ static ssize_t supported_sectorsizes_show(struct kobject *kobj, { ssize_t ret = 0; - /* 4K sector size is also supported with 64K page size */ - if (PAGE_SIZE == SZ_64K) + /* An artificial limit to only support 4K and PAGE_SIZE */ + if (PAGE_SIZE > SZ_4K) ret += sysfs_emit_at(buf, ret, "%u ", SZ_4K); - - /* Only sectorsize == PAGE_SIZE is now supported */ ret += sysfs_emit_at(buf, ret, "%lu\n", PAGE_SIZE); return ret; @@ -722,6 +720,42 @@ SPACE_INFO_ATTR(bytes_zone_unusable); SPACE_INFO_ATTR(disk_used); SPACE_INFO_ATTR(disk_total); +static ssize_t btrfs_sinfo_bg_reclaim_threshold_show(struct kobject *kobj, + struct kobj_attribute *a, + char *buf) +{ + struct btrfs_space_info *space_info = to_space_info(kobj); + ssize_t ret; + + ret = sysfs_emit(buf, "%d\n", READ_ONCE(space_info->bg_reclaim_threshold)); + + return ret; +} + +static ssize_t btrfs_sinfo_bg_reclaim_threshold_store(struct kobject *kobj, + struct kobj_attribute *a, + const char *buf, size_t len) +{ + struct btrfs_space_info *space_info = to_space_info(kobj); + int thresh; + int ret; + + ret = kstrtoint(buf, 10, &thresh); + if (ret) + return ret; + + if (thresh < 0 || thresh > 100) + return -EINVAL; + + WRITE_ONCE(space_info->bg_reclaim_threshold, thresh); + + return len; +} + +BTRFS_ATTR_RW(space_info, bg_reclaim_threshold, + btrfs_sinfo_bg_reclaim_threshold_show, + btrfs_sinfo_bg_reclaim_threshold_store); + /* * Allocation information about block group types. * @@ -738,6 +772,7 @@ static struct attribute *space_info_attrs[] = { BTRFS_ATTR_PTR(space_info, bytes_zone_unusable), BTRFS_ATTR_PTR(space_info, disk_used), BTRFS_ATTR_PTR(space_info, disk_total), + BTRFS_ATTR_PTR(space_info, bg_reclaim_threshold), NULL, }; ATTRIBUTE_GROUPS(space_info); @@ -922,6 +957,9 @@ static ssize_t btrfs_exclusive_operation_show(struct kobject *kobj, case BTRFS_EXCLOP_BALANCE: str = "balance\n"; break; + case BTRFS_EXCLOP_BALANCE_PAUSED: + str = "balance paused\n"; + break; case BTRFS_EXCLOP_DEV_ADD: str = "device add\n"; break; diff --git a/fs/btrfs/tests/btrfs-tests.c b/fs/btrfs/tests/btrfs-tests.c index d8e56edd6991..1591bfa55bcc 100644 --- a/fs/btrfs/tests/btrfs-tests.c +++ b/fs/btrfs/tests/btrfs-tests.c @@ -150,8 +150,8 @@ struct btrfs_fs_info *btrfs_alloc_dummy_fs_info(u32 nodesize, u32 sectorsize) void btrfs_free_dummy_fs_info(struct btrfs_fs_info *fs_info) { - struct radix_tree_iter iter; - void **slot; + unsigned long index; + struct extent_buffer *eb; struct btrfs_device *dev, *tmp; if (!fs_info) @@ -163,25 +163,9 @@ void btrfs_free_dummy_fs_info(struct btrfs_fs_info *fs_info) test_mnt->mnt_sb->s_fs_info = NULL; - spin_lock(&fs_info->buffer_lock); - radix_tree_for_each_slot(slot, &fs_info->buffer_radix, &iter, 0) { - struct extent_buffer *eb; - - eb = radix_tree_deref_slot_protected(slot, &fs_info->buffer_lock); - if (!eb) - continue; - /* Shouldn't happen but that kind of thinking creates CVE's */ - if (radix_tree_exception(eb)) { - if (radix_tree_deref_retry(eb)) - slot = radix_tree_iter_retry(&iter); - continue; - } - slot = radix_tree_iter_resume(slot, &iter); - spin_unlock(&fs_info->buffer_lock); + xa_for_each(&fs_info->extent_buffers, index, eb) { free_extent_buffer_stale(eb); - spin_lock(&fs_info->buffer_lock); } - spin_unlock(&fs_info->buffer_lock); btrfs_mapping_tree_free(&fs_info->mapping_tree); list_for_each_entry_safe(dev, tmp, &fs_info->fs_devices->devices, @@ -202,7 +186,7 @@ void btrfs_free_dummy_root(struct btrfs_root *root) if (!root) return; /* Will be freed by btrfs_free_fs_roots */ - if (WARN_ON(test_bit(BTRFS_ROOT_IN_RADIX, &root->state))) + if (WARN_ON(test_bit(BTRFS_ROOT_REGISTERED, &root->state))) return; btrfs_global_root_delete(root); btrfs_put_root(root); diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index b008c5110958..06c0a958d114 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -23,7 +23,7 @@ #include "space-info.h" #include "zoned.h" -#define BTRFS_ROOT_TRANS_TAG 0 +#define BTRFS_ROOT_TRANS_TAG XA_MARK_0 /* * Transaction states and transitions @@ -221,7 +221,7 @@ static noinline void switch_commit_roots(struct btrfs_trans_handle *trans) * the caching thread will re-start it's search from 3, and thus find * the hole from [4,6) to add to the free space cache. */ - spin_lock(&fs_info->block_group_cache_lock); + write_lock(&fs_info->block_group_cache_lock); list_for_each_entry_safe(caching_ctl, next, &fs_info->caching_block_groups, list) { struct btrfs_block_group *cache = caching_ctl->block_group; @@ -234,7 +234,7 @@ static noinline void switch_commit_roots(struct btrfs_trans_handle *trans) cache->last_byte_to_unpin = caching_ctl->progress; } } - spin_unlock(&fs_info->block_group_cache_lock); + write_unlock(&fs_info->block_group_cache_lock); up_write(&fs_info->commit_root_sem); } @@ -437,15 +437,15 @@ static int record_root_in_trans(struct btrfs_trans_handle *trans, */ smp_wmb(); - spin_lock(&fs_info->fs_roots_radix_lock); + spin_lock(&fs_info->fs_roots_lock); if (root->last_trans == trans->transid && !force) { - spin_unlock(&fs_info->fs_roots_radix_lock); + spin_unlock(&fs_info->fs_roots_lock); return 0; } - radix_tree_tag_set(&fs_info->fs_roots_radix, - (unsigned long)root->root_key.objectid, - BTRFS_ROOT_TRANS_TAG); - spin_unlock(&fs_info->fs_roots_radix_lock); + xa_set_mark(&fs_info->fs_roots, + (unsigned long)root->root_key.objectid, + BTRFS_ROOT_TRANS_TAG); + spin_unlock(&fs_info->fs_roots_lock); root->last_trans = trans->transid; /* this is pretty tricky. We don't want to @@ -487,11 +487,9 @@ void btrfs_add_dropped_root(struct btrfs_trans_handle *trans, spin_unlock(&cur_trans->dropped_roots_lock); /* Make sure we don't try to update the root at commit time */ - spin_lock(&fs_info->fs_roots_radix_lock); - radix_tree_tag_clear(&fs_info->fs_roots_radix, - (unsigned long)root->root_key.objectid, - BTRFS_ROOT_TRANS_TAG); - spin_unlock(&fs_info->fs_roots_radix_lock); + xa_clear_mark(&fs_info->fs_roots, + (unsigned long)root->root_key.objectid, + BTRFS_ROOT_TRANS_TAG); } int btrfs_record_root_in_trans(struct btrfs_trans_handle *trans, @@ -1404,9 +1402,8 @@ void btrfs_add_dead_root(struct btrfs_root *root) static noinline int commit_fs_roots(struct btrfs_trans_handle *trans) { struct btrfs_fs_info *fs_info = trans->fs_info; - struct btrfs_root *gang[8]; - int i; - int ret; + struct btrfs_root *root; + unsigned long index; /* * At this point no one can be using this transaction to modify any tree @@ -1414,57 +1411,46 @@ static noinline int commit_fs_roots(struct btrfs_trans_handle *trans) */ ASSERT(trans->transaction->state == TRANS_STATE_COMMIT_DOING); - spin_lock(&fs_info->fs_roots_radix_lock); - while (1) { - ret = radix_tree_gang_lookup_tag(&fs_info->fs_roots_radix, - (void **)gang, 0, - ARRAY_SIZE(gang), - BTRFS_ROOT_TRANS_TAG); - if (ret == 0) - break; - for (i = 0; i < ret; i++) { - struct btrfs_root *root = gang[i]; - int ret2; - - /* - * At this point we can neither have tasks logging inodes - * from a root nor trying to commit a log tree. - */ - ASSERT(atomic_read(&root->log_writers) == 0); - ASSERT(atomic_read(&root->log_commit[0]) == 0); - ASSERT(atomic_read(&root->log_commit[1]) == 0); - - radix_tree_tag_clear(&fs_info->fs_roots_radix, - (unsigned long)root->root_key.objectid, - BTRFS_ROOT_TRANS_TAG); - spin_unlock(&fs_info->fs_roots_radix_lock); - - btrfs_free_log(trans, root); - ret2 = btrfs_update_reloc_root(trans, root); - if (ret2) - return ret2; - - /* see comments in should_cow_block() */ - clear_bit(BTRFS_ROOT_FORCE_COW, &root->state); - smp_mb__after_atomic(); - - if (root->commit_root != root->node) { - list_add_tail(&root->dirty_list, - &trans->transaction->switch_commits); - btrfs_set_root_node(&root->root_item, - root->node); - } + spin_lock(&fs_info->fs_roots_lock); + xa_for_each_marked(&fs_info->fs_roots, index, root, BTRFS_ROOT_TRANS_TAG) { + int ret; + + /* + * At this point we can neither have tasks logging inodes + * from a root nor trying to commit a log tree. + */ + ASSERT(atomic_read(&root->log_writers) == 0); + ASSERT(atomic_read(&root->log_commit[0]) == 0); + ASSERT(atomic_read(&root->log_commit[1]) == 0); + + xa_clear_mark(&fs_info->fs_roots, + (unsigned long)root->root_key.objectid, + BTRFS_ROOT_TRANS_TAG); + spin_unlock(&fs_info->fs_roots_lock); - ret2 = btrfs_update_root(trans, fs_info->tree_root, - &root->root_key, - &root->root_item); - if (ret2) - return ret2; - spin_lock(&fs_info->fs_roots_radix_lock); - btrfs_qgroup_free_meta_all_pertrans(root); + btrfs_free_log(trans, root); + ret = btrfs_update_reloc_root(trans, root); + if (ret) + return ret; + + /* See comments in should_cow_block() */ + clear_bit(BTRFS_ROOT_FORCE_COW, &root->state); + smp_mb__after_atomic(); + + if (root->commit_root != root->node) { + list_add_tail(&root->dirty_list, + &trans->transaction->switch_commits); + btrfs_set_root_node(&root->root_item, root->node); } + + ret = btrfs_update_root(trans, fs_info->tree_root, + &root->root_key, &root->root_item); + if (ret) + return ret; + spin_lock(&fs_info->fs_roots_lock); + btrfs_qgroup_free_meta_all_pertrans(root); } - spin_unlock(&fs_info->fs_roots_radix_lock); + spin_unlock(&fs_info->fs_roots_lock); return 0; } diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index e56c0107eea3..9e0e0ae2288c 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -1855,3 +1855,58 @@ out: return ret; } ALLOW_ERROR_INJECTION(btrfs_check_node, ERRNO); + +int btrfs_check_eb_owner(const struct extent_buffer *eb, u64 root_owner) +{ + const bool is_subvol = is_fstree(root_owner); + const u64 eb_owner = btrfs_header_owner(eb); + + /* + * Skip dummy fs, as selftests don't create unique ebs for each dummy + * root. + */ + if (test_bit(BTRFS_FS_STATE_DUMMY_FS_INFO, &eb->fs_info->fs_state)) + return 0; + /* + * There are several call sites (backref walking, qgroup, and data + * reloc) passing 0 as @root_owner, as they are not holding the + * tree root. In that case, we can not do a reliable ownership check, + * so just exit. + */ + if (root_owner == 0) + return 0; + /* + * These trees use key.offset as their owner, our callers don't have + * the extra capacity to pass key.offset here. So we just skip them. + */ + if (root_owner == BTRFS_TREE_LOG_OBJECTID || + root_owner == BTRFS_TREE_RELOC_OBJECTID) + return 0; + + if (!is_subvol) { + /* For non-subvolume trees, the eb owner should match root owner */ + if (unlikely(root_owner != eb_owner)) { + btrfs_crit(eb->fs_info, +"corrupted %s, root=%llu block=%llu owner mismatch, have %llu expect %llu", + btrfs_header_level(eb) == 0 ? "leaf" : "node", + root_owner, btrfs_header_bytenr(eb), eb_owner, + root_owner); + return -EUCLEAN; + } + return 0; + } + + /* + * For subvolume trees, owners can mismatch, but they should all belong + * to subvolume trees. + */ + if (unlikely(is_subvol != is_fstree(eb_owner))) { + btrfs_crit(eb->fs_info, +"corrupted %s, root=%llu block=%llu owner mismatch, have %llu expect [%llu, %llu]", + btrfs_header_level(eb) == 0 ? "leaf" : "node", + root_owner, btrfs_header_bytenr(eb), eb_owner, + BTRFS_FIRST_FREE_OBJECTID, BTRFS_LAST_FREE_OBJECTID); + return -EUCLEAN; + } + return 0; +} diff --git a/fs/btrfs/tree-checker.h b/fs/btrfs/tree-checker.h index 32fecc9dc1dd..ece497e26558 100644 --- a/fs/btrfs/tree-checker.h +++ b/fs/btrfs/tree-checker.h @@ -25,5 +25,6 @@ int btrfs_check_node(struct extent_buffer *node); int btrfs_check_chunk_valid(struct extent_buffer *leaf, struct btrfs_chunk *chunk, u64 logical); +int btrfs_check_eb_owner(const struct extent_buffer *eb, u64 root_owner); #endif diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 571dae8ad65e..370388fadf96 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -333,7 +333,7 @@ static int process_one_buffer(struct btrfs_root *log, * pin down any logged extents, so we have to read the block. */ if (btrfs_fs_incompat(fs_info, MIXED_GROUPS)) { - ret = btrfs_read_buffer(eb, gen, level, NULL); + ret = btrfs_read_extent_buffer(eb, gen, level, NULL); if (ret) return ret; } @@ -894,8 +894,7 @@ update_inode: btrfs_update_inode_bytes(BTRFS_I(inode), nbytes, drop_args.bytes_found); ret = btrfs_update_inode(trans, root, BTRFS_I(inode)); out: - if (inode) - iput(inode); + iput(inode); return ret; } @@ -2575,7 +2574,7 @@ static int replay_one_buffer(struct btrfs_root *log, struct extent_buffer *eb, int i; int ret; - ret = btrfs_read_buffer(eb, gen, level, NULL); + ret = btrfs_read_extent_buffer(eb, gen, level, NULL); if (ret) return ret; @@ -2786,7 +2785,7 @@ static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans, path->slots[*level]++; if (wc->free) { - ret = btrfs_read_buffer(next, ptr_gen, + ret = btrfs_read_extent_buffer(next, ptr_gen, *level - 1, &first_key); if (ret) { free_extent_buffer(next); @@ -2815,7 +2814,7 @@ static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans, free_extent_buffer(next); continue; } - ret = btrfs_read_buffer(next, ptr_gen, *level - 1, &first_key); + ret = btrfs_read_extent_buffer(next, ptr_gen, *level - 1, &first_key); if (ret) { free_extent_buffer(next); return ret; @@ -3188,6 +3187,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, ret = btrfs_alloc_log_tree_node(trans, log_root_tree); if (ret) { mutex_unlock(&fs_info->tree_root->log_mutex); + blk_finish_plug(&plug); goto out; } } @@ -3720,11 +3720,29 @@ static noinline int insert_dir_log_key(struct btrfs_trans_handle *trans, key.offset = first_offset; key.type = BTRFS_DIR_LOG_INDEX_KEY; ret = btrfs_insert_empty_item(trans, log, path, &key, sizeof(*item)); - if (ret) + /* + * -EEXIST is fine and can happen sporadically when we are logging a + * directory and have concurrent insertions in the subvolume's tree for + * items from other inodes and that result in pushing off some dir items + * from one leaf to another in order to accommodate for the new items. + * This results in logging the same dir index range key. + */ + if (ret && ret != -EEXIST) return ret; item = btrfs_item_ptr(path->nodes[0], path->slots[0], struct btrfs_dir_log_item); + if (ret == -EEXIST) { + const u64 curr_end = btrfs_dir_log_end(path->nodes[0], item); + + /* + * btrfs_del_dir_entries_in_log() might have been called during + * an unlink between the initial insertion of this key and the + * current update, or we might be logging a single entry deletion + * during a rename, so set the new last_offset to the max value. + */ + last_offset = max(last_offset, curr_end); + } btrfs_set_dir_log_end(path->nodes[0], item, last_offset); btrfs_mark_buffer_dirty(path->nodes[0]); btrfs_release_path(path); @@ -3848,13 +3866,6 @@ static int process_dir_items_leaf(struct btrfs_trans_handle *trans, ret = insert_dir_log_key(trans, log, dst_path, ino, *last_old_dentry_offset + 1, key.offset - 1); - /* - * -EEXIST should never happen because when we - * log a directory in full mode (LOG_INODE_ALL) - * we drop all BTRFS_DIR_LOG_INDEX_KEY keys from - * the log tree. - */ - ASSERT(ret != -EEXIST); if (ret < 0) return ret; } @@ -5804,6 +5815,18 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans, } /* + * For symlinks, we must always log their content, which is stored in an + * inline extent, otherwise we could end up with an empty symlink after + * log replay, which is invalid on linux (symlink(2) returns -ENOENT if + * one attempts to create an empty symlink). + * We don't need to worry about flushing delalloc, because when we create + * the inline extent when the symlink is created (we never have delalloc + * for symlinks). + */ + if (S_ISLNK(inode->vfs_inode.i_mode)) + inode_only = LOG_INODE_ALL; + + /* * Before logging the inode item, cache the value returned by * inode_logged(), because after that we have the need to figure out if * the inode was previously logged in this transaction. @@ -6181,7 +6204,7 @@ again: } ctx->log_new_dentries = false; - if (type == BTRFS_FT_DIR || type == BTRFS_FT_SYMLINK) + if (type == BTRFS_FT_DIR) log_mode = LOG_INODE_ALL; ret = btrfs_log_inode(trans, BTRFS_I(di_inode), log_mode, ctx); @@ -7018,12 +7041,12 @@ void btrfs_log_new_name(struct btrfs_trans_handle *trans, /* * Other concurrent task might be logging the old directory, * as it can be triggered when logging other inode that had or - * still has a dentry in the old directory. So take the old - * directory's log_mutex to prevent getting an -EEXIST when - * logging a key to record the deletion, or having that other - * task logging the old directory get an -EEXIST if it attempts - * to log the same key after we just did it. In both cases that - * would result in falling back to a transaction commit. + * still has a dentry in the old directory. We lock the old + * directory's log_mutex to ensure the deletion of the old + * name is persisted, because during directory logging we + * delete all BTRFS_DIR_LOG_INDEX_KEY keys and the deletion of + * the old name's dir index item is in the delayed items, so + * it could be missed by an in progress directory logging. */ mutex_lock(&old_dir->log_mutex); ret = del_logged_dentry(trans, log, path, btrfs_ino(old_dir), diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 1be7cb2f955f..9c20049d1fec 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -164,24 +164,12 @@ const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES] = { */ enum btrfs_raid_types __attribute_const__ btrfs_bg_flags_to_raid_index(u64 flags) { - if (flags & BTRFS_BLOCK_GROUP_RAID10) - return BTRFS_RAID_RAID10; - else if (flags & BTRFS_BLOCK_GROUP_RAID1) - return BTRFS_RAID_RAID1; - else if (flags & BTRFS_BLOCK_GROUP_RAID1C3) - return BTRFS_RAID_RAID1C3; - else if (flags & BTRFS_BLOCK_GROUP_RAID1C4) - return BTRFS_RAID_RAID1C4; - else if (flags & BTRFS_BLOCK_GROUP_DUP) - return BTRFS_RAID_DUP; - else if (flags & BTRFS_BLOCK_GROUP_RAID0) - return BTRFS_RAID_RAID0; - else if (flags & BTRFS_BLOCK_GROUP_RAID5) - return BTRFS_RAID_RAID5; - else if (flags & BTRFS_BLOCK_GROUP_RAID6) - return BTRFS_RAID_RAID6; - - return BTRFS_RAID_SINGLE; /* BTRFS_BLOCK_GROUP_SINGLE */ + const u64 profile = (flags & BTRFS_BLOCK_GROUP_PROFILE_MASK); + + if (!profile) + return BTRFS_RAID_SINGLE; + + return BTRFS_BG_FLAG_TO_INDEX(profile); } const char *btrfs_bg_type_to_raid_name(u64 flags) @@ -405,7 +393,6 @@ void btrfs_free_device(struct btrfs_device *device) WARN_ON(!list_empty(&device->post_commit_list)); rcu_string_free(device->name); extent_io_tree_release(&device->alloc_state); - bio_put(device->flush_bio); btrfs_destroy_dev_zone_info(device); kfree(device); } @@ -643,7 +630,7 @@ static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices, set_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state); } - if (!blk_queue_nonrot(bdev_get_queue(bdev))) + if (!bdev_nonrot(bdev)) fs_devices->rotating = true; device->bdev = bdev; @@ -1896,23 +1883,18 @@ static void update_dev_time(const char *device_path) path_put(&path); } -static int btrfs_rm_dev_item(struct btrfs_device *device) +static int btrfs_rm_dev_item(struct btrfs_trans_handle *trans, + struct btrfs_device *device) { struct btrfs_root *root = device->fs_info->chunk_root; int ret; struct btrfs_path *path; struct btrfs_key key; - struct btrfs_trans_handle *trans; path = btrfs_alloc_path(); if (!path) return -ENOMEM; - trans = btrfs_start_transaction(root, 0); - if (IS_ERR(trans)) { - btrfs_free_path(path); - return PTR_ERR(trans); - } key.objectid = BTRFS_DEV_ITEMS_OBJECTID; key.type = BTRFS_DEV_ITEM_KEY; key.offset = device->devid; @@ -1923,21 +1905,12 @@ static int btrfs_rm_dev_item(struct btrfs_device *device) if (ret) { if (ret > 0) ret = -ENOENT; - btrfs_abort_transaction(trans, ret); - btrfs_end_transaction(trans); goto out; } ret = btrfs_del_item(trans, root, path); - if (ret) { - btrfs_abort_transaction(trans, ret); - btrfs_end_transaction(trans); - } - out: btrfs_free_path(path); - if (!ret) - ret = btrfs_commit_transaction(trans); return ret; } @@ -2078,6 +2051,7 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info, struct btrfs_dev_lookup_args *args, struct block_device **bdev, fmode_t *mode) { + struct btrfs_trans_handle *trans; struct btrfs_device *device; struct btrfs_fs_devices *cur_devices; struct btrfs_fs_devices *fs_devices = fs_info->fs_devices; @@ -2098,7 +2072,7 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info, ret = btrfs_check_raid_min_devices(fs_info, num_devices - 1); if (ret) - goto out; + return ret; device = btrfs_find_device(fs_info->fs_devices, args); if (!device) { @@ -2106,27 +2080,22 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info, ret = BTRFS_ERROR_DEV_MISSING_NOT_FOUND; else ret = -ENOENT; - goto out; + return ret; } if (btrfs_pinned_by_swapfile(fs_info, device)) { btrfs_warn_in_rcu(fs_info, "cannot remove device %s (devid %llu) due to active swapfile", rcu_str_deref(device->name), device->devid); - ret = -ETXTBSY; - goto out; + return -ETXTBSY; } - if (test_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state)) { - ret = BTRFS_ERROR_DEV_TGT_REPLACE; - goto out; - } + if (test_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state)) + return BTRFS_ERROR_DEV_TGT_REPLACE; if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state) && - fs_info->fs_devices->rw_devices == 1) { - ret = BTRFS_ERROR_DEV_ONLY_WRITABLE; - goto out; - } + fs_info->fs_devices->rw_devices == 1) + return BTRFS_ERROR_DEV_ONLY_WRITABLE; if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state)) { mutex_lock(&fs_info->chunk_mutex); @@ -2139,14 +2108,22 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info, if (ret) goto error_undo; - /* - * TODO: the superblock still includes this device in its num_devices - * counter although write_all_supers() is not locked out. This - * could give a filesystem state which requires a degraded mount. - */ - ret = btrfs_rm_dev_item(device); - if (ret) + trans = btrfs_start_transaction(fs_info->chunk_root, 0); + if (IS_ERR(trans)) { + ret = PTR_ERR(trans); goto error_undo; + } + + ret = btrfs_rm_dev_item(trans, device); + if (ret) { + /* Any error in dev item removal is critical */ + btrfs_crit(fs_info, + "failed to remove device item for devid %llu: %d", + device->devid, ret); + btrfs_abort_transaction(trans, ret); + btrfs_end_transaction(trans); + return ret; + } clear_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state); btrfs_scrub_cancel_dev(device); @@ -2229,7 +2206,8 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info, free_fs_devices(cur_devices); } -out: + ret = btrfs_commit_transaction(trans); + return ret; error_undo: @@ -2240,7 +2218,7 @@ error_undo: device->fs_devices->rw_devices++; mutex_unlock(&fs_info->chunk_mutex); } - goto out; + return ret; } void btrfs_rm_dev_replace_remove_srcdev(struct btrfs_device *srcdev) @@ -2715,7 +2693,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path atomic64_add(device->total_bytes, &fs_info->free_chunk_space); - if (!blk_queue_nonrot(bdev_get_queue(bdev))) + if (!bdev_nonrot(bdev)) fs_devices->rotating = true; orig_super_total_bytes = btrfs_super_total_bytes(fs_info->super_copy); @@ -4072,13 +4050,6 @@ static inline int validate_convert_profile(struct btrfs_fs_info *fs_info, if (!(bargs->flags & BTRFS_BALANCE_ARGS_CONVERT)) return true; - if (fs_info->sectorsize < PAGE_SIZE && - bargs->target & BTRFS_BLOCK_GROUP_RAID56_MASK) { - btrfs_err(fs_info, - "RAID56 is not yet supported for sectorsize %u with page size %lu", - fs_info->sectorsize, PAGE_SIZE); - return false; - } /* Profile is valid and does not have bits outside of the allowed set */ if (alloc_profile_is_valid(bargs->target, 1) && (bargs->target & ~allowed) == 0) @@ -4439,10 +4410,12 @@ static int balance_kthread(void *data) struct btrfs_fs_info *fs_info = data; int ret = 0; + sb_start_write(fs_info->sb); mutex_lock(&fs_info->balance_mutex); if (fs_info->balance_ctl) ret = btrfs_balance(fs_info, fs_info->balance_ctl, NULL); mutex_unlock(&fs_info->balance_mutex); + sb_end_write(fs_info->sb); return ret; } @@ -6320,7 +6293,7 @@ int btrfs_get_io_geometry(struct btrfs_fs_info *fs_info, struct extent_map *em, u64 offset; u64 stripe_offset; u64 stripe_nr; - u64 stripe_len; + u32 stripe_len; u64 raid56_full_stripe_start = (u64)-1; int data_stripes; @@ -6331,19 +6304,13 @@ int btrfs_get_io_geometry(struct btrfs_fs_info *fs_info, struct extent_map *em, offset = logical - em->start; /* Len of a stripe in a chunk */ stripe_len = map->stripe_len; - /* Stripe where this block falls in */ - stripe_nr = div64_u64(offset, stripe_len); - /* Offset of stripe in the chunk */ - stripe_offset = stripe_nr * stripe_len; - if (offset < stripe_offset) { - btrfs_crit(fs_info, -"stripe math has gone wrong, stripe_offset=%llu offset=%llu start=%llu logical=%llu stripe_len=%llu", - stripe_offset, offset, em->start, logical, stripe_len); - return -EINVAL; - } + /* + * Stripe_nr is where this block falls in + * stripe_offset is the offset of this block in its stripe. + */ + stripe_nr = div64_u64_rem(offset, stripe_len, &stripe_offset); + ASSERT(stripe_offset < U32_MAX); - /* stripe_offset is the offset of this block in its stripe */ - stripe_offset = offset - stripe_offset; data_stripes = nr_data_stripes(map); /* Only stripe based profiles needs to check against stripe length. */ @@ -6745,11 +6712,11 @@ static void submit_stripe_bio(struct btrfs_io_context *bioc, struct bio *bio, bio_op(bio), bio->bi_opf, bio->bi_iter.bi_sector, (unsigned long)dev->bdev->bd_dev, rcu_str_deref(dev->name), dev->devid, bio->bi_iter.bi_size); - bio_set_dev(bio, dev->bdev); btrfs_bio_counter_inc_noblocked(fs_info); - btrfsic_submit_bio(bio); + btrfsic_check_bio(bio); + submit_bio(bio); } static void bioc_error(struct btrfs_io_context *bioc, struct bio *bio, u64 logical) @@ -6831,10 +6798,12 @@ blk_status_t btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio, continue; } - if (dev_nr < total_devs - 1) - bio = btrfs_bio_clone(first_bio); - else + if (dev_nr < total_devs - 1) { + bio = btrfs_bio_clone(dev->bdev, first_bio); + } else { bio = first_bio; + bio_set_dev(bio, dev->bdev); + } submit_stripe_bio(bioc, bio, bioc->stripes[dev_nr].physical, dev); } @@ -6956,16 +6925,6 @@ struct btrfs_device *btrfs_alloc_device(struct btrfs_fs_info *fs_info, if (!dev) return ERR_PTR(-ENOMEM); - /* - * Preallocate a bio that's always going to be used for flushing device - * barriers and matches the device lifespan - */ - dev->flush_bio = bio_kmalloc(GFP_KERNEL, 0); - if (!dev->flush_bio) { - kfree(dev); - return ERR_PTR(-ENOMEM); - } - INIT_LIST_HEAD(&dev->dev_list); INIT_LIST_HEAD(&dev->dev_alloc_list); INIT_LIST_HEAD(&dev->post_commit_list); @@ -7377,7 +7336,6 @@ static int read_one_dev(struct extent_buffer *leaf, int btrfs_read_sys_array(struct btrfs_fs_info *fs_info) { - struct btrfs_root *root = fs_info->tree_root; struct btrfs_super_block *super_copy = fs_info->super_copy; struct extent_buffer *sb; struct btrfs_disk_key *disk_key; @@ -7393,30 +7351,16 @@ int btrfs_read_sys_array(struct btrfs_fs_info *fs_info) struct btrfs_key key; ASSERT(BTRFS_SUPER_INFO_SIZE <= fs_info->nodesize); + /* - * This will create extent buffer of nodesize, superblock size is - * fixed to BTRFS_SUPER_INFO_SIZE. If nodesize > sb size, this will - * overallocate but we can keep it as-is, only the first page is used. + * We allocated a dummy extent, just to use extent buffer accessors. + * There will be unused space after BTRFS_SUPER_INFO_SIZE, but + * that's fine, we will not go beyond system chunk array anyway. */ - sb = btrfs_find_create_tree_block(fs_info, BTRFS_SUPER_INFO_OFFSET, - root->root_key.objectid, 0); - if (IS_ERR(sb)) - return PTR_ERR(sb); + sb = alloc_dummy_extent_buffer(fs_info, BTRFS_SUPER_INFO_OFFSET); + if (!sb) + return -ENOMEM; set_extent_buffer_uptodate(sb); - /* - * The sb extent buffer is artificial and just used to read the system array. - * set_extent_buffer_uptodate() call does not properly mark all it's - * pages up-to-date when the page is larger: extent does not cover the - * whole page and consequently check_page_uptodate does not find all - * the page's extents up-to-date (the hole beyond sb), - * write_extent_buffer then triggers a WARN_ON. - * - * Regular short extents go through mark_extent_buffer_dirty/writeback cycle, - * but sb spans only this function. Add an explicit SetPageUptodate call - * to silence the warning eg. on PowerPC 64. - */ - if (PAGE_SIZE > BTRFS_SUPER_INFO_SIZE) - SetPageUptodate(sb->pages[0]); write_extent_buffer(sb, super_copy, 0, BTRFS_SUPER_INFO_SIZE); array_size = btrfs_super_sys_array_size(super_copy); @@ -7579,6 +7523,7 @@ int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info) struct btrfs_key found_key; int ret; int slot; + int iter_ret = 0; u64 total_dev = 0; u64 last_ra_node = 0; @@ -7622,30 +7567,18 @@ int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info) key.objectid = BTRFS_DEV_ITEMS_OBJECTID; key.offset = 0; key.type = 0; - ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); - if (ret < 0) - goto error; - while (1) { - struct extent_buffer *node; + btrfs_for_each_slot(root, &key, &found_key, path, iter_ret) { + struct extent_buffer *node = path->nodes[1]; leaf = path->nodes[0]; slot = path->slots[0]; - if (slot >= btrfs_header_nritems(leaf)) { - ret = btrfs_next_leaf(root, path); - if (ret == 0) - continue; - if (ret < 0) - goto error; - break; - } - node = path->nodes[1]; + if (node) { if (last_ra_node != node->start) { readahead_tree_node_children(node); last_ra_node = node->start; } } - btrfs_item_key_to_cpu(leaf, &found_key, slot); if (found_key.type == BTRFS_DEV_ITEM_KEY) { struct btrfs_dev_item *dev_item; dev_item = btrfs_item_ptr(leaf, slot, @@ -7670,7 +7603,11 @@ int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info) if (ret) goto error; } - path->slots[0]++; + } + /* Catch error found during iteration */ + if (iter_ret < 0) { + ret = iter_ret; + goto error; } /* @@ -7678,12 +7615,12 @@ int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info) * do another round of validation checks. */ if (total_dev != fs_info->fs_devices->total_devices) { - btrfs_err(fs_info, - "super_num_devices %llu mismatch with num_devices %llu found here", + btrfs_warn(fs_info, +"super block num_devices %llu mismatch with DEV_ITEM count %llu, will be repaired on next transaction commit", btrfs_super_num_devices(fs_info->super_copy), total_dev); - ret = -EINVAL; - goto error; + fs_info->fs_devices->total_devices = total_dev; + btrfs_set_super_num_devices(fs_info->super_copy, total_dev); } if (btrfs_super_total_bytes(fs_info->super_copy) < fs_info->fs_devices->total_rw_bytes) { @@ -8295,7 +8232,7 @@ bool btrfs_pinned_by_swapfile(struct btrfs_fs_info *fs_info, void *ptr) static int relocating_repair_kthread(void *data) { - struct btrfs_block_group *cache = (struct btrfs_block_group *)data; + struct btrfs_block_group *cache = data; struct btrfs_fs_info *fs_info = cache->fs_info; u64 target; int ret = 0; diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index bd297f23d19e..6721002000ee 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -17,17 +17,51 @@ extern struct mutex uuid_mutex; #define BTRFS_STRIPE_LEN SZ_64K +/* Used by sanity check for btrfs_raid_types. */ +#define const_ffs(n) (__builtin_ctzll(n) + 1) + +/* + * The conversion from BTRFS_BLOCK_GROUP_* bits to btrfs_raid_type requires + * RAID0 always to be the lowest profile bit. + * Although it's part of on-disk format and should never change, do extra + * compile-time sanity checks. + */ +static_assert(const_ffs(BTRFS_BLOCK_GROUP_RAID0) < + const_ffs(BTRFS_BLOCK_GROUP_PROFILE_MASK & ~BTRFS_BLOCK_GROUP_RAID0)); +static_assert(const_ilog2(BTRFS_BLOCK_GROUP_RAID0) > + ilog2(BTRFS_BLOCK_GROUP_TYPE_MASK)); + +/* ilog2() can handle both constants and variables */ +#define BTRFS_BG_FLAG_TO_INDEX(profile) \ + ilog2((profile) >> (ilog2(BTRFS_BLOCK_GROUP_RAID0) - 1)) + +enum btrfs_raid_types { + /* SINGLE is the special one as it doesn't have on-disk bit. */ + BTRFS_RAID_SINGLE = 0, + + BTRFS_RAID_RAID0 = BTRFS_BG_FLAG_TO_INDEX(BTRFS_BLOCK_GROUP_RAID0), + BTRFS_RAID_RAID1 = BTRFS_BG_FLAG_TO_INDEX(BTRFS_BLOCK_GROUP_RAID1), + BTRFS_RAID_DUP = BTRFS_BG_FLAG_TO_INDEX(BTRFS_BLOCK_GROUP_DUP), + BTRFS_RAID_RAID10 = BTRFS_BG_FLAG_TO_INDEX(BTRFS_BLOCK_GROUP_RAID10), + BTRFS_RAID_RAID5 = BTRFS_BG_FLAG_TO_INDEX(BTRFS_BLOCK_GROUP_RAID5), + BTRFS_RAID_RAID6 = BTRFS_BG_FLAG_TO_INDEX(BTRFS_BLOCK_GROUP_RAID6), + BTRFS_RAID_RAID1C3 = BTRFS_BG_FLAG_TO_INDEX(BTRFS_BLOCK_GROUP_RAID1C3), + BTRFS_RAID_RAID1C4 = BTRFS_BG_FLAG_TO_INDEX(BTRFS_BLOCK_GROUP_RAID1C4), + + BTRFS_NR_RAID_TYPES +}; + struct btrfs_io_geometry { /* remaining bytes before crossing a stripe */ u64 len; /* offset of logical address in chunk */ u64 offset; /* length of single IO stripe */ - u64 stripe_len; + u32 stripe_len; + /* offset of address in stripe */ + u32 stripe_offset; /* number of stripe where address falls */ u64 stripe_nr; - /* offset of address in stripe */ - u64 stripe_offset; /* offset of raid56 stripe into the chunk */ u64 raid56_stripe_offset; }; @@ -121,8 +155,8 @@ struct btrfs_device { /* bytes used on the current transaction */ u64 commit_bytes_used; - /* for sending down flush barriers */ - struct bio *flush_bio; + /* Bio used for flushing device barriers */ + struct bio flush_bio; struct completion flush_wait; /* per-device scrub information */ @@ -328,6 +362,9 @@ struct btrfs_fs_devices { struct btrfs_bio { unsigned int mirror_num; + /* for direct I/O */ + u64 file_offset; + /* @device is for stripe IO submission. */ struct btrfs_device *device; u8 *csum; @@ -427,7 +464,7 @@ struct map_lookup { u64 type; int io_align; int io_width; - u64 stripe_len; + u32 stripe_len; int num_stripes; int sub_stripes; int verified_stripes; /* For mount time dev extent verification */ diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c index 99abf41b89b9..7421abcf325a 100644 --- a/fs/btrfs/xattr.c +++ b/fs/btrfs/xattr.c @@ -262,7 +262,8 @@ int btrfs_setxattr_trans(struct inode *inode, const char *name, inode_inc_iversion(inode); inode->i_ctime = current_time(inode); ret = btrfs_update_inode(trans, root, BTRFS_I(inode)); - BUG_ON(ret); + if (ret) + btrfs_abort_transaction(trans, ret); out: if (start_trans) btrfs_end_transaction(trans); @@ -271,10 +272,12 @@ out: ssize_t btrfs_listxattr(struct dentry *dentry, char *buffer, size_t size) { + struct btrfs_key found_key; struct btrfs_key key; struct inode *inode = d_inode(dentry); struct btrfs_root *root = BTRFS_I(inode)->root; struct btrfs_path *path; + int iter_ret = 0; int ret = 0; size_t total_size = 0, size_left = size; @@ -293,44 +296,23 @@ ssize_t btrfs_listxattr(struct dentry *dentry, char *buffer, size_t size) path->reada = READA_FORWARD; /* search for our xattrs */ - ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); - if (ret < 0) - goto err; - - while (1) { + btrfs_for_each_slot(root, &key, &found_key, path, iter_ret) { struct extent_buffer *leaf; int slot; struct btrfs_dir_item *di; - struct btrfs_key found_key; u32 item_size; u32 cur; leaf = path->nodes[0]; slot = path->slots[0]; - /* this is where we start walking through the path */ - if (slot >= btrfs_header_nritems(leaf)) { - /* - * if we've reached the last slot in this leaf we need - * to go to the next leaf and reset everything - */ - ret = btrfs_next_leaf(root, path); - if (ret < 0) - goto err; - else if (ret > 0) - break; - continue; - } - - btrfs_item_key_to_cpu(leaf, &found_key, slot); - /* check to make sure this item is what we want */ if (found_key.objectid != key.objectid) break; if (found_key.type > BTRFS_XATTR_ITEM_KEY) break; if (found_key.type < BTRFS_XATTR_ITEM_KEY) - goto next_item; + continue; di = btrfs_item_ptr(leaf, slot, struct btrfs_dir_item); item_size = btrfs_item_size(leaf, slot); @@ -350,8 +332,8 @@ ssize_t btrfs_listxattr(struct dentry *dentry, char *buffer, size_t size) goto next; if (!buffer || (name_len + 1) > size_left) { - ret = -ERANGE; - goto err; + iter_ret = -ERANGE; + break; } read_extent_buffer(leaf, buffer, name_ptr, name_len); @@ -363,12 +345,13 @@ next: cur += this_len; di = (struct btrfs_dir_item *)((char *)di + this_len); } -next_item: - path->slots[0]++; } - ret = total_size; -err: + if (iter_ret < 0) + ret = iter_ret; + else + ret = total_size; + btrfs_free_path(path); return ret; @@ -403,10 +386,13 @@ static int btrfs_xattr_handler_set_prop(const struct xattr_handler *handler, struct btrfs_root *root = BTRFS_I(inode)->root; name = xattr_full_name(handler, name); - ret = btrfs_validate_prop(name, value, size); + ret = btrfs_validate_prop(BTRFS_I(inode), name, value, size); if (ret) return ret; + if (btrfs_ignore_prop(BTRFS_I(inode), name)) + return 0; + trans = btrfs_start_transaction(root, 2); if (IS_ERR(trans)) return PTR_ERR(trans); @@ -416,7 +402,8 @@ static int btrfs_xattr_handler_set_prop(const struct xattr_handler *handler, inode_inc_iversion(inode); inode->i_ctime = current_time(inode); ret = btrfs_update_inode(trans, root, BTRFS_I(inode)); - BUG_ON(ret); + if (ret) + btrfs_abort_transaction(trans, ret); } btrfs_end_transaction(trans); diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index b7b5fac1c779..11237a913bee 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -51,11 +51,13 @@ #define BTRFS_MIN_ACTIVE_ZONES (BTRFS_SUPER_MIRROR_MAX + 5) /* - * Maximum supported zone size. Currently, SMR disks have a zone size of - * 256MiB, and we are expecting ZNS drives to be in the 1-4GiB range. We do not - * expect the zone size to become larger than 8GiB in the near future. + * Minimum / maximum supported zone size. Currently, SMR disks have a zone + * size of 256MiB, and we are expecting ZNS drives to be in the 1-4GiB range. + * We do not expect the zone size to become larger than 8GiB or smaller than + * 4MiB in the near future. */ #define BTRFS_MAX_ZONE_SIZE SZ_8G +#define BTRFS_MIN_ZONE_SIZE SZ_4M #define SUPER_INFO_SECTORS ((u64)BTRFS_SUPER_INFO_SIZE >> SECTOR_SHIFT) @@ -350,7 +352,6 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device, bool populate_cache) struct btrfs_fs_info *fs_info = device->fs_info; struct btrfs_zoned_device_info *zone_info = NULL; struct block_device *bdev = device->bdev; - struct request_queue *queue = bdev_get_queue(bdev); unsigned int max_active_zones; unsigned int nactive; sector_t nr_sectors; @@ -402,6 +403,13 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device, bool populate_cache) zone_info->zone_size, BTRFS_MAX_ZONE_SIZE); ret = -EINVAL; goto out; + } else if (zone_info->zone_size < BTRFS_MIN_ZONE_SIZE) { + btrfs_err_in_rcu(fs_info, + "zoned: %s: zone size %llu smaller than supported minimum %u", + rcu_str_deref(device->name), + zone_info->zone_size, BTRFS_MIN_ZONE_SIZE); + ret = -EINVAL; + goto out; } nr_sectors = bdev_nr_sectors(bdev); @@ -410,7 +418,7 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device, bool populate_cache) if (!IS_ALIGNED(nr_sectors, zone_sectors)) zone_info->nr_zones++; - max_active_zones = queue_max_active_zones(queue); + max_active_zones = bdev_max_active_zones(bdev); if (max_active_zones && max_active_zones < BTRFS_MIN_ACTIVE_ZONES) { btrfs_err_in_rcu(fs_info, "zoned: %s: max active zones %u is too small, need at least %u active zones", @@ -1801,7 +1809,6 @@ struct btrfs_device *btrfs_zoned_get_device(struct btrfs_fs_info *fs_info, map = em->map_lookup; /* We only support single profile for now */ - ASSERT(map->num_stripes == 1); device = map->stripes[0].dev; free_extent_map(em); @@ -1836,6 +1843,12 @@ bool btrfs_zone_activate(struct btrfs_block_group *block_group) goto out_unlock; } + /* No space left */ + if (btrfs_zoned_bg_is_full(block_group)) { + ret = false; + goto out_unlock; + } + for (i = 0; i < map->num_stripes; i++) { device = map->stripes[i].dev; physical = map->stripes[i].physical; @@ -1843,35 +1856,23 @@ bool btrfs_zone_activate(struct btrfs_block_group *block_group) if (device->zone_info->max_active_zones == 0) continue; - /* No space left */ - if (block_group->alloc_offset == block_group->zone_capacity) { - ret = false; - goto out_unlock; - } - if (!btrfs_dev_set_active_zone(device, physical)) { /* Cannot activate the zone */ ret = false; goto out_unlock; } - - /* Successfully activated all the zones */ - if (i == map->num_stripes - 1) - block_group->zone_is_active = 1; - - } + + /* Successfully activated all the zones */ + block_group->zone_is_active = 1; spin_unlock(&block_group->lock); - if (block_group->zone_is_active) { - /* For the active block group list */ - btrfs_get_block_group(block_group); + /* For the active block group list */ + btrfs_get_block_group(block_group); - spin_lock(&fs_info->zone_active_bgs_lock); - list_add_tail(&block_group->active_bg_list, - &fs_info->zone_active_bgs); - spin_unlock(&fs_info->zone_active_bgs_lock); - } + spin_lock(&fs_info->zone_active_bgs_lock); + list_add_tail(&block_group->active_bg_list, &fs_info->zone_active_bgs); + spin_unlock(&fs_info->zone_active_bgs_lock); return true; @@ -1880,20 +1881,14 @@ out_unlock: return ret; } -int btrfs_zone_finish(struct btrfs_block_group *block_group) +static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_written) { struct btrfs_fs_info *fs_info = block_group->fs_info; struct map_lookup *map; - struct btrfs_device *device; - u64 physical; + bool need_zone_finish; int ret = 0; int i; - if (!btrfs_is_zoned(fs_info)) - return 0; - - map = block_group->physical_map; - spin_lock(&block_group->lock); if (!block_group->zone_is_active) { spin_unlock(&block_group->lock); @@ -1903,40 +1898,56 @@ int btrfs_zone_finish(struct btrfs_block_group *block_group) /* Check if we have unwritten allocated space */ if ((block_group->flags & (BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_SYSTEM)) && - block_group->alloc_offset > block_group->meta_write_pointer) { + block_group->start + block_group->alloc_offset > block_group->meta_write_pointer) { spin_unlock(&block_group->lock); return -EAGAIN; } - spin_unlock(&block_group->lock); - - ret = btrfs_inc_block_group_ro(block_group, false); - if (ret) - return ret; - - /* Ensure all writes in this block group finish */ - btrfs_wait_block_group_reservations(block_group); - /* No need to wait for NOCOW writers. Zoned mode does not allow that. */ - btrfs_wait_ordered_roots(fs_info, U64_MAX, block_group->start, - block_group->length); - - spin_lock(&block_group->lock); /* - * Bail out if someone already deactivated the block group, or - * allocated space is left in the block group. + * If we are sure that the block group is full (= no more room left for + * new allocation) and the IO for the last usable block is completed, we + * don't need to wait for the other IOs. This holds because we ensure + * the sequential IO submissions using the ZONE_APPEND command for data + * and block_group->meta_write_pointer for metadata. */ - if (!block_group->zone_is_active) { + if (!fully_written) { spin_unlock(&block_group->lock); - btrfs_dec_block_group_ro(block_group); - return 0; - } - if (block_group->reserved) { - spin_unlock(&block_group->lock); - btrfs_dec_block_group_ro(block_group); - return -EAGAIN; + ret = btrfs_inc_block_group_ro(block_group, false); + if (ret) + return ret; + + /* Ensure all writes in this block group finish */ + btrfs_wait_block_group_reservations(block_group); + /* No need to wait for NOCOW writers. Zoned mode does not allow that */ + btrfs_wait_ordered_roots(fs_info, U64_MAX, block_group->start, + block_group->length); + + spin_lock(&block_group->lock); + + /* + * Bail out if someone already deactivated the block group, or + * allocated space is left in the block group. + */ + if (!block_group->zone_is_active) { + spin_unlock(&block_group->lock); + btrfs_dec_block_group_ro(block_group); + return 0; + } + + if (block_group->reserved) { + spin_unlock(&block_group->lock); + btrfs_dec_block_group_ro(block_group); + return -EAGAIN; + } } + /* + * The block group is not fully allocated, so not fully written yet. We + * need to send ZONE_FINISH command to free up an active zone. + */ + need_zone_finish = !btrfs_zoned_bg_is_full(block_group); + block_group->zone_is_active = 0; block_group->alloc_offset = block_group->zone_capacity; block_group->free_space_ctl->free_space = 0; @@ -1944,24 +1955,29 @@ int btrfs_zone_finish(struct btrfs_block_group *block_group) btrfs_clear_data_reloc_bg(block_group); spin_unlock(&block_group->lock); + map = block_group->physical_map; for (i = 0; i < map->num_stripes; i++) { - device = map->stripes[i].dev; - physical = map->stripes[i].physical; + struct btrfs_device *device = map->stripes[i].dev; + const u64 physical = map->stripes[i].physical; if (device->zone_info->max_active_zones == 0) continue; - ret = blkdev_zone_mgmt(device->bdev, REQ_OP_ZONE_FINISH, - physical >> SECTOR_SHIFT, - device->zone_info->zone_size >> SECTOR_SHIFT, - GFP_NOFS); + if (need_zone_finish) { + ret = blkdev_zone_mgmt(device->bdev, REQ_OP_ZONE_FINISH, + physical >> SECTOR_SHIFT, + device->zone_info->zone_size >> SECTOR_SHIFT, + GFP_NOFS); - if (ret) - return ret; + if (ret) + return ret; + } btrfs_dev_clear_active_zone(device, physical); } - btrfs_dec_block_group_ro(block_group); + + if (!fully_written) + btrfs_dec_block_group_ro(block_group); spin_lock(&fs_info->zone_active_bgs_lock); ASSERT(!list_empty(&block_group->active_bg_list)); @@ -1974,20 +1990,26 @@ int btrfs_zone_finish(struct btrfs_block_group *block_group) return 0; } +int btrfs_zone_finish(struct btrfs_block_group *block_group) +{ + if (!btrfs_is_zoned(block_group->fs_info)) + return 0; + + return do_zone_finish(block_group, false); +} + bool btrfs_can_activate_zone(struct btrfs_fs_devices *fs_devices, u64 flags) { + struct btrfs_fs_info *fs_info = fs_devices->fs_info; struct btrfs_device *device; bool ret = false; - if (!btrfs_is_zoned(fs_devices->fs_info)) + if (!btrfs_is_zoned(fs_info)) return true; - /* Non-single profiles are not supported yet */ - ASSERT((flags & BTRFS_BLOCK_GROUP_PROFILE_MASK) == 0); - /* Check if there is a device with active zones left */ - mutex_lock(&fs_devices->device_list_mutex); - list_for_each_entry(device, &fs_devices->devices, dev_list) { + mutex_lock(&fs_info->chunk_mutex); + list_for_each_entry(device, &fs_devices->alloc_list, dev_alloc_list) { struct btrfs_zoned_device_info *zinfo = device->zone_info; if (!device->bdev) @@ -1999,7 +2021,7 @@ bool btrfs_can_activate_zone(struct btrfs_fs_devices *fs_devices, u64 flags) break; } } - mutex_unlock(&fs_devices->device_list_mutex); + mutex_unlock(&fs_info->chunk_mutex); return ret; } @@ -2007,9 +2029,7 @@ bool btrfs_can_activate_zone(struct btrfs_fs_devices *fs_devices, u64 flags) void btrfs_zone_finish_endio(struct btrfs_fs_info *fs_info, u64 logical, u64 length) { struct btrfs_block_group *block_group; - struct map_lookup *map; - struct btrfs_device *device; - u64 physical; + u64 min_alloc_bytes; if (!btrfs_is_zoned(fs_info)) return; @@ -2017,42 +2037,52 @@ void btrfs_zone_finish_endio(struct btrfs_fs_info *fs_info, u64 logical, u64 len block_group = btrfs_lookup_block_group(fs_info, logical); ASSERT(block_group); - if (logical + length < block_group->start + block_group->zone_capacity) - goto out; - - spin_lock(&block_group->lock); + /* No MIXED_BG on zoned btrfs. */ + if (block_group->flags & BTRFS_BLOCK_GROUP_DATA) + min_alloc_bytes = fs_info->sectorsize; + else + min_alloc_bytes = fs_info->nodesize; - if (!block_group->zone_is_active) { - spin_unlock(&block_group->lock); + /* Bail out if we can allocate more data from this block group. */ + if (logical + length + min_alloc_bytes <= + block_group->start + block_group->zone_capacity) goto out; - } - block_group->zone_is_active = 0; - /* We should have consumed all the free space */ - ASSERT(block_group->alloc_offset == block_group->zone_capacity); - ASSERT(block_group->free_space_ctl->free_space == 0); - btrfs_clear_treelog_bg(block_group); - btrfs_clear_data_reloc_bg(block_group); - spin_unlock(&block_group->lock); + do_zone_finish(block_group, true); - map = block_group->physical_map; - device = map->stripes[0].dev; - physical = map->stripes[0].physical; +out: + btrfs_put_block_group(block_group); +} - if (!device->zone_info->max_active_zones) - goto out; +static void btrfs_zone_finish_endio_workfn(struct work_struct *work) +{ + struct btrfs_block_group *bg = + container_of(work, struct btrfs_block_group, zone_finish_work); - btrfs_dev_clear_active_zone(device, physical); + wait_on_extent_buffer_writeback(bg->last_eb); + free_extent_buffer(bg->last_eb); + btrfs_zone_finish_endio(bg->fs_info, bg->start, bg->length); + btrfs_put_block_group(bg); +} - spin_lock(&fs_info->zone_active_bgs_lock); - ASSERT(!list_empty(&block_group->active_bg_list)); - list_del_init(&block_group->active_bg_list); - spin_unlock(&fs_info->zone_active_bgs_lock); +void btrfs_schedule_zone_finish_bg(struct btrfs_block_group *bg, + struct extent_buffer *eb) +{ + if (!bg->seq_zone || eb->start + eb->len * 2 <= bg->start + bg->zone_capacity) + return; - btrfs_put_block_group(block_group); + if (WARN_ON(bg->zone_finish_work.func == btrfs_zone_finish_endio_workfn)) { + btrfs_err(bg->fs_info, "double scheduling of bg %llu zone finishing", + bg->start); + return; + } -out: - btrfs_put_block_group(block_group); + /* For the work */ + btrfs_get_block_group(bg); + atomic_inc(&eb->refs); + bg->last_eb = eb; + INIT_WORK(&bg->zone_finish_work, btrfs_zone_finish_endio_workfn); + queue_work(system_unbound_wq, &bg->zone_finish_work); } void btrfs_clear_data_reloc_bg(struct btrfs_block_group *bg) @@ -2082,3 +2112,30 @@ void btrfs_free_zone_cache(struct btrfs_fs_info *fs_info) } mutex_unlock(&fs_devices->device_list_mutex); } + +bool btrfs_zoned_should_reclaim(struct btrfs_fs_info *fs_info) +{ + struct btrfs_fs_devices *fs_devices = fs_info->fs_devices; + struct btrfs_device *device; + u64 used = 0; + u64 total = 0; + u64 factor; + + ASSERT(btrfs_is_zoned(fs_info)); + + if (fs_info->bg_reclaim_threshold == 0) + return false; + + mutex_lock(&fs_devices->device_list_mutex); + list_for_each_entry(device, &fs_devices->devices, dev_list) { + if (!device->bdev) + continue; + + total += device->disk_total_bytes; + used += device->bytes_used; + } + mutex_unlock(&fs_devices->device_list_mutex); + + factor = div64_u64(used * 100, total); + return factor >= fs_info->bg_reclaim_threshold; +} diff --git a/fs/btrfs/zoned.h b/fs/btrfs/zoned.h index cbf016a7bb5d..bb1a189e11f9 100644 --- a/fs/btrfs/zoned.h +++ b/fs/btrfs/zoned.h @@ -10,11 +10,7 @@ #include "block-group.h" #include "btrfs_inode.h" -/* - * Block groups with more than this value (percents) of unusable space will be - * scheduled for background reclaim. - */ -#define BTRFS_DEFAULT_RECLAIM_THRESH 75 +#define BTRFS_DEFAULT_RECLAIM_THRESH (75) struct btrfs_zoned_device_info { /* @@ -76,8 +72,11 @@ int btrfs_zone_finish(struct btrfs_block_group *block_group); bool btrfs_can_activate_zone(struct btrfs_fs_devices *fs_devices, u64 flags); void btrfs_zone_finish_endio(struct btrfs_fs_info *fs_info, u64 logical, u64 length); +void btrfs_schedule_zone_finish_bg(struct btrfs_block_group *bg, + struct extent_buffer *eb); void btrfs_clear_data_reloc_bg(struct btrfs_block_group *bg); void btrfs_free_zone_cache(struct btrfs_fs_info *fs_info); +bool btrfs_zoned_should_reclaim(struct btrfs_fs_info *fs_info); #else /* CONFIG_BLK_DEV_ZONED */ static inline int btrfs_get_dev_zone(struct btrfs_device *device, u64 pos, struct blk_zone *zone) @@ -233,9 +232,17 @@ static inline bool btrfs_can_activate_zone(struct btrfs_fs_devices *fs_devices, static inline void btrfs_zone_finish_endio(struct btrfs_fs_info *fs_info, u64 logical, u64 length) { } +static inline void btrfs_schedule_zone_finish_bg(struct btrfs_block_group *bg, + struct extent_buffer *eb) { } + static inline void btrfs_clear_data_reloc_bg(struct btrfs_block_group *bg) { } static inline void btrfs_free_zone_cache(struct btrfs_fs_info *fs_info) { } + +static inline bool btrfs_zoned_should_reclaim(struct btrfs_fs_info *fs_info) +{ + return false; +} #endif static inline bool btrfs_dev_is_sequential(struct btrfs_device *device, u64 pos) @@ -359,7 +366,7 @@ static inline void btrfs_zoned_data_reloc_lock(struct btrfs_inode *inode) struct btrfs_root *root = inode->root; if (btrfs_is_data_reloc_root(root) && btrfs_is_zoned(root->fs_info)) - btrfs_inode_lock(&inode->vfs_inode, 0); + mutex_lock(&root->fs_info->zoned_data_reloc_io_lock); } static inline void btrfs_zoned_data_reloc_unlock(struct btrfs_inode *inode) @@ -367,7 +374,13 @@ static inline void btrfs_zoned_data_reloc_unlock(struct btrfs_inode *inode) struct btrfs_root *root = inode->root; if (btrfs_is_data_reloc_root(root) && btrfs_is_zoned(root->fs_info)) - btrfs_inode_unlock(&inode->vfs_inode, 0); + mutex_unlock(&root->fs_info->zoned_data_reloc_io_lock); +} + +static inline bool btrfs_zoned_bg_is_full(const struct btrfs_block_group *bg) +{ + ASSERT(btrfs_is_zoned(bg->fs_info)); + return (bg->alloc_offset == bg->zone_capacity); } #endif diff --git a/fs/btrfs/zstd.c b/fs/btrfs/zstd.c index fc42dd0badd7..0fe31a6f6e68 100644 --- a/fs/btrfs/zstd.c +++ b/fs/btrfs/zstd.c @@ -93,22 +93,26 @@ static inline struct workspace *list_to_workspace(struct list_head *list) void zstd_free_workspace(struct list_head *ws); struct list_head *zstd_alloc_workspace(unsigned int level); -/* - * zstd_reclaim_timer_fn - reclaim timer + +/** + * Timer callback to free unused workspaces. + * * @t: timer * * This scans the lru_list and attempts to reclaim any workspace that hasn't * been used for ZSTD_BTRFS_RECLAIM_JIFFIES. + * + * The context is softirq and does not need the _bh locking primitives. */ static void zstd_reclaim_timer_fn(struct timer_list *timer) { unsigned long reclaim_threshold = jiffies - ZSTD_BTRFS_RECLAIM_JIFFIES; struct list_head *pos, *next; - spin_lock_bh(&wsm.lock); + spin_lock(&wsm.lock); if (list_empty(&wsm.lru_list)) { - spin_unlock_bh(&wsm.lock); + spin_unlock(&wsm.lock); return; } @@ -137,7 +141,7 @@ static void zstd_reclaim_timer_fn(struct timer_list *timer) if (!list_empty(&wsm.lru_list)) mod_timer(&wsm.timer, jiffies + ZSTD_BTRFS_RECLAIM_JIFFIES); - spin_unlock_bh(&wsm.lock); + spin_unlock(&wsm.lock); } /* diff --git a/fs/buffer.c b/fs/buffer.c index 2b5561ae5d0b..898c7f301b1b 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -79,26 +79,26 @@ void unlock_buffer(struct buffer_head *bh) EXPORT_SYMBOL(unlock_buffer); /* - * Returns if the page has dirty or writeback buffers. If all the buffers - * are unlocked and clean then the PageDirty information is stale. If - * any of the pages are locked, it is assumed they are locked for IO. + * Returns if the folio has dirty or writeback buffers. If all the buffers + * are unlocked and clean then the folio_test_dirty information is stale. If + * any of the buffers are locked, it is assumed they are locked for IO. */ -void buffer_check_dirty_writeback(struct page *page, +void buffer_check_dirty_writeback(struct folio *folio, bool *dirty, bool *writeback) { struct buffer_head *head, *bh; *dirty = false; *writeback = false; - BUG_ON(!PageLocked(page)); + BUG_ON(!folio_test_locked(folio)); - if (!page_has_buffers(page)) + head = folio_buffers(folio); + if (!head) return; - if (PageWriteback(page)) + if (folio_test_writeback(folio)) *writeback = true; - head = page_buffers(page); bh = head; do { if (buffer_locked(bh)) @@ -314,7 +314,7 @@ static void decrypt_bh(struct work_struct *work) } /* - * I/O completion handler for block_read_full_page() - pages + * I/O completion handler for block_read_full_folio() - pages * which come unlocked at the end of I/O. */ static void end_buffer_async_read_io(struct buffer_head *bh, int uptodate) @@ -955,7 +955,7 @@ grow_dev_page(struct block_device *bdev, sector_t block, size); goto done; } - if (!try_to_free_buffers(page)) + if (!try_to_free_buffers(page_folio(page))) goto failed; } @@ -1060,8 +1060,8 @@ __getblk_slow(struct block_device *bdev, sector_t block, * Also. When blockdev buffers are explicitly read with bread(), they * individually become uptodate. But their backing page remains not * uptodate - even if all of its buffers are uptodate. A subsequent - * block_read_full_page() against that page will discover all the uptodate - * buffers, will set the page uptodate and will perform no I/O. + * block_read_full_folio() against that folio will discover all the uptodate + * buffers, will set the folio uptodate and will perform no I/O. */ /** @@ -2088,7 +2088,7 @@ static int __block_commit_write(struct inode *inode, struct page *page, /* * If this is a partial write which happened to make all buffers - * uptodate then we can optimize away a bogus readpage() for + * uptodate then we can optimize away a bogus read_folio() for * the next read(). Here we 'discover' whether the page went * uptodate as a result of this (potentially partial) write. */ @@ -2104,13 +2104,13 @@ static int __block_commit_write(struct inode *inode, struct page *page, * The filesystem needs to handle block truncation upon failure. */ int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len, - unsigned flags, struct page **pagep, get_block_t *get_block) + struct page **pagep, get_block_t *get_block) { pgoff_t index = pos >> PAGE_SHIFT; struct page *page; int status; - page = grab_cache_page_write_begin(mapping, index, flags); + page = grab_cache_page_write_begin(mapping, index); if (!page) return -ENOMEM; @@ -2137,12 +2137,12 @@ int block_write_end(struct file *file, struct address_space *mapping, if (unlikely(copied < len)) { /* - * The buffers that were written will now be uptodate, so we - * don't have to worry about a readpage reading them and - * overwriting a partial write. However if we have encountered - * a short write and only partially written into a buffer, it - * will not be marked uptodate, so a readpage might come in and - * destroy our partial write. + * The buffers that were written will now be uptodate, so + * we don't have to worry about a read_folio reading them + * and overwriting a partial write. However if we have + * encountered a short write and only partially written + * into a buffer, it will not be marked uptodate, so a + * read_folio might come in and destroy our partial write. * * Do the simplest thing, and just treat any short write to a * non uptodate page as a zero-length write, and force the @@ -2245,26 +2245,28 @@ bool block_is_partially_uptodate(struct folio *folio, size_t from, size_t count) EXPORT_SYMBOL(block_is_partially_uptodate); /* - * Generic "read page" function for block devices that have the normal + * Generic "read_folio" function for block devices that have the normal * get_block functionality. This is most of the block device filesystems. - * Reads the page asynchronously --- the unlock_buffer() and + * Reads the folio asynchronously --- the unlock_buffer() and * set/clear_buffer_uptodate() functions propagate buffer state into the - * page struct once IO has completed. + * folio once IO has completed. */ -int block_read_full_page(struct page *page, get_block_t *get_block) +int block_read_full_folio(struct folio *folio, get_block_t *get_block) { - struct inode *inode = page->mapping->host; + struct inode *inode = folio->mapping->host; sector_t iblock, lblock; struct buffer_head *bh, *head, *arr[MAX_BUF_PER_PAGE]; unsigned int blocksize, bbits; int nr, i; int fully_mapped = 1; - head = create_page_buffers(page, inode, 0); + VM_BUG_ON_FOLIO(folio_test_large(folio), folio); + + head = create_page_buffers(&folio->page, inode, 0); blocksize = head->b_size; bbits = block_size_bits(blocksize); - iblock = (sector_t)page->index << (PAGE_SHIFT - bbits); + iblock = (sector_t)folio->index << (PAGE_SHIFT - bbits); lblock = (i_size_read(inode)+blocksize-1) >> bbits; bh = head; nr = 0; @@ -2282,10 +2284,11 @@ int block_read_full_page(struct page *page, get_block_t *get_block) WARN_ON(bh->b_size != blocksize); err = get_block(inode, iblock, bh, 0); if (err) - SetPageError(page); + folio_set_error(folio); } if (!buffer_mapped(bh)) { - zero_user(page, i * blocksize, blocksize); + folio_zero_range(folio, i * blocksize, + blocksize); if (!err) set_buffer_uptodate(bh); continue; @@ -2301,16 +2304,16 @@ int block_read_full_page(struct page *page, get_block_t *get_block) } while (i++, iblock++, (bh = bh->b_this_page) != head); if (fully_mapped) - SetPageMappedToDisk(page); + folio_set_mappedtodisk(folio); if (!nr) { /* - * All buffers are uptodate - we can set the page uptodate + * All buffers are uptodate - we can set the folio uptodate * as well. But not if get_block() returned an error. */ - if (!PageError(page)) - SetPageUptodate(page); - unlock_page(page); + if (!folio_test_error(folio)) + folio_mark_uptodate(folio); + folio_unlock(folio); return 0; } @@ -2335,7 +2338,7 @@ int block_read_full_page(struct page *page, get_block_t *get_block) } return 0; } -EXPORT_SYMBOL(block_read_full_page); +EXPORT_SYMBOL(block_read_full_folio); /* utility function for filesystems that need to do work on expanding * truncates. Uses filesystem pagecache writes to allow the filesystem to @@ -2344,6 +2347,7 @@ EXPORT_SYMBOL(block_read_full_page); int generic_cont_expand_simple(struct inode *inode, loff_t size) { struct address_space *mapping = inode->i_mapping; + const struct address_space_operations *aops = mapping->a_ops; struct page *page; void *fsdata; int err; @@ -2352,11 +2356,11 @@ int generic_cont_expand_simple(struct inode *inode, loff_t size) if (err) goto out; - err = pagecache_write_begin(NULL, mapping, size, 0, 0, &page, &fsdata); + err = aops->write_begin(NULL, mapping, size, 0, &page, &fsdata); if (err) goto out; - err = pagecache_write_end(NULL, mapping, size, 0, 0, page, fsdata); + err = aops->write_end(NULL, mapping, size, 0, 0, page, fsdata); BUG_ON(err > 0); out: @@ -2368,6 +2372,7 @@ static int cont_expand_zero(struct file *file, struct address_space *mapping, loff_t pos, loff_t *bytes) { struct inode *inode = mapping->host; + const struct address_space_operations *aops = mapping->a_ops; unsigned int blocksize = i_blocksize(inode); struct page *page; void *fsdata; @@ -2387,12 +2392,12 @@ static int cont_expand_zero(struct file *file, struct address_space *mapping, } len = PAGE_SIZE - zerofrom; - err = pagecache_write_begin(file, mapping, curpos, len, 0, + err = aops->write_begin(file, mapping, curpos, len, &page, &fsdata); if (err) goto out; zero_user(page, zerofrom, len); - err = pagecache_write_end(file, mapping, curpos, len, len, + err = aops->write_end(file, mapping, curpos, len, len, page, fsdata); if (err < 0) goto out; @@ -2420,12 +2425,12 @@ static int cont_expand_zero(struct file *file, struct address_space *mapping, } len = offset - zerofrom; - err = pagecache_write_begin(file, mapping, curpos, len, 0, + err = aops->write_begin(file, mapping, curpos, len, &page, &fsdata); if (err) goto out; zero_user(page, zerofrom, len); - err = pagecache_write_end(file, mapping, curpos, len, len, + err = aops->write_end(file, mapping, curpos, len, len, page, fsdata); if (err < 0) goto out; @@ -2441,7 +2446,7 @@ out: * We may have to extend the file. */ int cont_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, + loff_t pos, unsigned len, struct page **pagep, void **fsdata, get_block_t *get_block, loff_t *bytes) { @@ -2460,7 +2465,7 @@ int cont_write_begin(struct file *file, struct address_space *mapping, (*bytes)++; } - return block_write_begin(mapping, pos, len, flags, pagep, get_block); + return block_write_begin(mapping, pos, len, pagep, get_block); } EXPORT_SYMBOL(cont_write_begin); @@ -2568,8 +2573,7 @@ static void attach_nobh_buffers(struct page *page, struct buffer_head *head) * On exit the page is fully uptodate in the areas outside (from,to) * The filesystem needs to handle block truncation upon failure. */ -int nobh_write_begin(struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, +int nobh_write_begin(struct address_space *mapping, loff_t pos, unsigned len, struct page **pagep, void **fsdata, get_block_t *get_block) { @@ -2591,7 +2595,7 @@ int nobh_write_begin(struct address_space *mapping, from = pos & (PAGE_SIZE - 1); to = from + len; - page = grab_cache_page_write_begin(mapping, index, flags); + page = grab_cache_page_write_begin(mapping, index); if (!page) return -ENOMEM; *pagep = page; @@ -2790,44 +2794,28 @@ int nobh_truncate_page(struct address_space *mapping, loff_t from, get_block_t *get_block) { pgoff_t index = from >> PAGE_SHIFT; - unsigned offset = from & (PAGE_SIZE-1); - unsigned blocksize; - sector_t iblock; - unsigned length, pos; struct inode *inode = mapping->host; - struct page *page; + unsigned blocksize = i_blocksize(inode); + struct folio *folio; struct buffer_head map_bh; + size_t offset; + sector_t iblock; int err; - blocksize = i_blocksize(inode); - length = offset & (blocksize - 1); - /* Block boundary? Nothing to do */ - if (!length) + if (!(from & (blocksize - 1))) return 0; - length = blocksize - length; - iblock = (sector_t)index << (PAGE_SHIFT - inode->i_blkbits); - - page = grab_cache_page(mapping, index); + folio = __filemap_get_folio(mapping, index, FGP_LOCK | FGP_CREAT, + mapping_gfp_mask(mapping)); err = -ENOMEM; - if (!page) + if (!folio) goto out; - if (page_has_buffers(page)) { -has_buffers: - unlock_page(page); - put_page(page); - return block_truncate_page(mapping, from, get_block); - } - - /* Find the buffer that contains "offset" */ - pos = blocksize; - while (offset >= pos) { - iblock++; - pos += blocksize; - } + if (folio_buffers(folio)) + goto has_buffers; + iblock = from >> inode->i_blkbits; map_bh.b_size = blocksize; map_bh.b_state = 0; err = get_block(inode, iblock, &map_bh, 0); @@ -2838,29 +2826,35 @@ has_buffers: goto unlock; /* Ok, it's mapped. Make sure it's up-to-date */ - if (!PageUptodate(page)) { - err = mapping->a_ops->readpage(NULL, page); + if (!folio_test_uptodate(folio)) { + err = mapping->a_ops->read_folio(NULL, folio); if (err) { - put_page(page); + folio_put(folio); goto out; } - lock_page(page); - if (!PageUptodate(page)) { + folio_lock(folio); + if (!folio_test_uptodate(folio)) { err = -EIO; goto unlock; } - if (page_has_buffers(page)) + if (folio_buffers(folio)) goto has_buffers; } - zero_user(page, offset, length); - set_page_dirty(page); + offset = offset_in_folio(folio, from); + folio_zero_segment(folio, offset, round_up(offset, blocksize)); + folio_mark_dirty(folio); err = 0; unlock: - unlock_page(page); - put_page(page); + folio_unlock(folio); + folio_put(folio); out: return err; + +has_buffers: + folio_unlock(folio); + folio_put(folio); + return block_truncate_page(mapping, from, get_block); } EXPORT_SYMBOL(nobh_truncate_page); @@ -3161,20 +3155,20 @@ int sync_dirty_buffer(struct buffer_head *bh) EXPORT_SYMBOL(sync_dirty_buffer); /* - * try_to_free_buffers() checks if all the buffers on this particular page + * try_to_free_buffers() checks if all the buffers on this particular folio * are unused, and releases them if so. * * Exclusion against try_to_free_buffers may be obtained by either - * locking the page or by holding its mapping's private_lock. + * locking the folio or by holding its mapping's private_lock. * - * If the page is dirty but all the buffers are clean then we need to - * be sure to mark the page clean as well. This is because the page + * If the folio is dirty but all the buffers are clean then we need to + * be sure to mark the folio clean as well. This is because the folio * may be against a block device, and a later reattachment of buffers - * to a dirty page will set *all* buffers dirty. Which would corrupt + * to a dirty folio will set *all* buffers dirty. Which would corrupt * filesystem data on the same device. * - * The same applies to regular filesystem pages: if all the buffers are - * clean then we set the page clean and proceed. To do that, we require + * The same applies to regular filesystem folios: if all the buffers are + * clean then we set the folio clean and proceed. To do that, we require * total exclusion from block_dirty_folio(). That is obtained with * private_lock. * @@ -3186,10 +3180,10 @@ static inline int buffer_busy(struct buffer_head *bh) (bh->b_state & ((1 << BH_Dirty) | (1 << BH_Lock))); } -static int -drop_buffers(struct page *page, struct buffer_head **buffers_to_free) +static bool +drop_buffers(struct folio *folio, struct buffer_head **buffers_to_free) { - struct buffer_head *head = page_buffers(page); + struct buffer_head *head = folio_buffers(folio); struct buffer_head *bh; bh = head; @@ -3207,46 +3201,46 @@ drop_buffers(struct page *page, struct buffer_head **buffers_to_free) bh = next; } while (bh != head); *buffers_to_free = head; - detach_page_private(page); - return 1; + folio_detach_private(folio); + return true; failed: - return 0; + return false; } -int try_to_free_buffers(struct page *page) +bool try_to_free_buffers(struct folio *folio) { - struct address_space * const mapping = page->mapping; + struct address_space * const mapping = folio->mapping; struct buffer_head *buffers_to_free = NULL; - int ret = 0; + bool ret = 0; - BUG_ON(!PageLocked(page)); - if (PageWriteback(page)) - return 0; + BUG_ON(!folio_test_locked(folio)); + if (folio_test_writeback(folio)) + return false; if (mapping == NULL) { /* can this still happen? */ - ret = drop_buffers(page, &buffers_to_free); + ret = drop_buffers(folio, &buffers_to_free); goto out; } spin_lock(&mapping->private_lock); - ret = drop_buffers(page, &buffers_to_free); + ret = drop_buffers(folio, &buffers_to_free); /* * If the filesystem writes its buffers by hand (eg ext3) - * then we can have clean buffers against a dirty page. We - * clean the page here; otherwise the VM will never notice + * then we can have clean buffers against a dirty folio. We + * clean the folio here; otherwise the VM will never notice * that the filesystem did any IO at all. * * Also, during truncate, discard_buffer will have marked all - * the page's buffers clean. We discover that here and clean - * the page also. + * the folio's buffers clean. We discover that here and clean + * the folio also. * * private_lock must be held over this entire operation in order * to synchronise against block_dirty_folio and prevent the * dirty bit from being lost. */ if (ret) - cancel_dirty_page(page); + folio_cancel_dirty(folio); spin_unlock(&mapping->private_lock); out: if (buffers_to_free) { diff --git a/fs/cachefiles/Kconfig b/fs/cachefiles/Kconfig index 719faeeda168..8df715640a48 100644 --- a/fs/cachefiles/Kconfig +++ b/fs/cachefiles/Kconfig @@ -26,3 +26,15 @@ config CACHEFILES_ERROR_INJECTION help This permits error injection to be enabled in cachefiles whilst a cache is in service. + +config CACHEFILES_ONDEMAND + bool "Support for on-demand read" + depends on CACHEFILES + default n + help + This permits userspace to enable the cachefiles on-demand read mode. + In this mode, when a cache miss occurs, responsibility for fetching + the data lies with the cachefiles backend instead of with the netfs + and is delegated to userspace. + + If unsure, say N. diff --git a/fs/cachefiles/Makefile b/fs/cachefiles/Makefile index 16d811f1a2fa..c37a7a9af10b 100644 --- a/fs/cachefiles/Makefile +++ b/fs/cachefiles/Makefile @@ -16,5 +16,6 @@ cachefiles-y := \ xattr.o cachefiles-$(CONFIG_CACHEFILES_ERROR_INJECTION) += error_inject.o +cachefiles-$(CONFIG_CACHEFILES_ONDEMAND) += ondemand.o obj-$(CONFIG_CACHEFILES) := cachefiles.o diff --git a/fs/cachefiles/daemon.c b/fs/cachefiles/daemon.c index 7ac04ee2c0a0..aa4efcabb5e3 100644 --- a/fs/cachefiles/daemon.c +++ b/fs/cachefiles/daemon.c @@ -75,6 +75,9 @@ static const struct cachefiles_daemon_cmd cachefiles_daemon_cmds[] = { { "inuse", cachefiles_daemon_inuse }, { "secctx", cachefiles_daemon_secctx }, { "tag", cachefiles_daemon_tag }, +#ifdef CONFIG_CACHEFILES_ONDEMAND + { "copen", cachefiles_ondemand_copen }, +#endif { "", NULL } }; @@ -108,6 +111,9 @@ static int cachefiles_daemon_open(struct inode *inode, struct file *file) INIT_LIST_HEAD(&cache->volumes); INIT_LIST_HEAD(&cache->object_list); spin_lock_init(&cache->object_list_lock); + refcount_set(&cache->unbind_pincount, 1); + xa_init_flags(&cache->reqs, XA_FLAGS_ALLOC); + xa_init_flags(&cache->ondemand_ids, XA_FLAGS_ALLOC1); /* set default caching limits * - limit at 1% free space and/or free files @@ -126,6 +132,53 @@ static int cachefiles_daemon_open(struct inode *inode, struct file *file) return 0; } +static void cachefiles_flush_reqs(struct cachefiles_cache *cache) +{ + struct xarray *xa = &cache->reqs; + struct cachefiles_req *req; + unsigned long index; + + /* + * Make sure the following two operations won't be reordered. + * 1) set CACHEFILES_DEAD bit + * 2) flush requests in the xarray + * Otherwise the request may be enqueued after xarray has been + * flushed, leaving the orphan request never being completed. + * + * CPU 1 CPU 2 + * ===== ===== + * flush requests in the xarray + * test CACHEFILES_DEAD bit + * enqueue the request + * set CACHEFILES_DEAD bit + */ + smp_mb(); + + xa_lock(xa); + xa_for_each(xa, index, req) { + req->error = -EIO; + complete(&req->done); + } + xa_unlock(xa); + + xa_destroy(&cache->reqs); + xa_destroy(&cache->ondemand_ids); +} + +void cachefiles_put_unbind_pincount(struct cachefiles_cache *cache) +{ + if (refcount_dec_and_test(&cache->unbind_pincount)) { + cachefiles_daemon_unbind(cache); + cachefiles_open = 0; + kfree(cache); + } +} + +void cachefiles_get_unbind_pincount(struct cachefiles_cache *cache) +{ + refcount_inc(&cache->unbind_pincount); +} + /* * Release a cache. */ @@ -139,36 +192,27 @@ static int cachefiles_daemon_release(struct inode *inode, struct file *file) set_bit(CACHEFILES_DEAD, &cache->flags); - cachefiles_daemon_unbind(cache); + if (cachefiles_in_ondemand_mode(cache)) + cachefiles_flush_reqs(cache); /* clean up the control file interface */ cache->cachefilesd = NULL; file->private_data = NULL; - cachefiles_open = 0; - kfree(cache); + cachefiles_put_unbind_pincount(cache); _leave(""); return 0; } -/* - * Read the cache state. - */ -static ssize_t cachefiles_daemon_read(struct file *file, char __user *_buffer, - size_t buflen, loff_t *pos) +static ssize_t cachefiles_do_daemon_read(struct cachefiles_cache *cache, + char __user *_buffer, size_t buflen) { - struct cachefiles_cache *cache = file->private_data; unsigned long long b_released; unsigned f_released; char buffer[256]; int n; - //_enter(",,%zu,", buflen); - - if (!test_bit(CACHEFILES_READY, &cache->flags)) - return 0; - /* check how much space the cache has */ cachefiles_has_space(cache, 0, 0, cachefiles_has_space_check); @@ -207,6 +251,25 @@ static ssize_t cachefiles_daemon_read(struct file *file, char __user *_buffer, } /* + * Read the cache state. + */ +static ssize_t cachefiles_daemon_read(struct file *file, char __user *_buffer, + size_t buflen, loff_t *pos) +{ + struct cachefiles_cache *cache = file->private_data; + + //_enter(",,%zu,", buflen); + + if (!test_bit(CACHEFILES_READY, &cache->flags)) + return 0; + + if (cachefiles_in_ondemand_mode(cache)) + return cachefiles_ondemand_daemon_read(cache, _buffer, buflen); + else + return cachefiles_do_daemon_read(cache, _buffer, buflen); +} + +/* * Take a command from cachefilesd, parse it and act on it. */ static ssize_t cachefiles_daemon_write(struct file *file, @@ -297,8 +360,13 @@ static __poll_t cachefiles_daemon_poll(struct file *file, poll_wait(file, &cache->daemon_pollwq, poll); mask = 0; - if (test_bit(CACHEFILES_STATE_CHANGED, &cache->flags)) - mask |= EPOLLIN; + if (cachefiles_in_ondemand_mode(cache)) { + if (!xa_empty(&cache->reqs)) + mask |= EPOLLIN; + } else { + if (test_bit(CACHEFILES_STATE_CHANGED, &cache->flags)) + mask |= EPOLLIN; + } if (test_bit(CACHEFILES_CULLING, &cache->flags)) mask |= EPOLLOUT; @@ -687,11 +755,6 @@ static int cachefiles_daemon_bind(struct cachefiles_cache *cache, char *args) cache->brun_percent >= 100) return -ERANGE; - if (*args) { - pr_err("'bind' command doesn't take an argument\n"); - return -EINVAL; - } - if (!cache->rootdirname) { pr_err("No cache directory specified\n"); return -EINVAL; @@ -703,6 +766,18 @@ static int cachefiles_daemon_bind(struct cachefiles_cache *cache, char *args) return -EBUSY; } + if (IS_ENABLED(CONFIG_CACHEFILES_ONDEMAND)) { + if (!strcmp(args, "ondemand")) { + set_bit(CACHEFILES_ONDEMAND_MODE, &cache->flags); + } else if (*args) { + pr_err("Invalid argument to the 'bind' command\n"); + return -EINVAL; + } + } else if (*args) { + pr_err("'bind' command doesn't take an argument\n"); + return -EINVAL; + } + /* Make sure we have copies of the tag string */ if (!cache->tag) { /* diff --git a/fs/cachefiles/interface.c b/fs/cachefiles/interface.c index ae93cee9d25d..a69073a1d3f0 100644 --- a/fs/cachefiles/interface.c +++ b/fs/cachefiles/interface.c @@ -362,6 +362,8 @@ static void cachefiles_withdraw_cookie(struct fscache_cookie *cookie) spin_unlock(&cache->object_list_lock); } + cachefiles_ondemand_clean_object(object); + if (object->file) { cachefiles_begin_secure(cache, &saved_cred); cachefiles_clean_up_object(object, cache); diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h index c793d33b0224..6cba2c6de2f9 100644 --- a/fs/cachefiles/internal.h +++ b/fs/cachefiles/internal.h @@ -15,6 +15,8 @@ #include <linux/fscache-cache.h> #include <linux/cred.h> #include <linux/security.h> +#include <linux/xarray.h> +#include <linux/cachefiles.h> #define CACHEFILES_DIO_BLOCK_SIZE 4096 @@ -58,8 +60,13 @@ struct cachefiles_object { enum cachefiles_content content_info:8; /* Info about content presence */ unsigned long flags; #define CACHEFILES_OBJECT_USING_TMPFILE 0 /* Have an unlinked tmpfile */ +#ifdef CONFIG_CACHEFILES_ONDEMAND + int ondemand_id; +#endif }; +#define CACHEFILES_ONDEMAND_ID_CLOSED -1 + /* * Cache files cache definition */ @@ -98,11 +105,31 @@ struct cachefiles_cache { #define CACHEFILES_DEAD 1 /* T if cache dead */ #define CACHEFILES_CULLING 2 /* T if cull engaged */ #define CACHEFILES_STATE_CHANGED 3 /* T if state changed (poll trigger) */ +#define CACHEFILES_ONDEMAND_MODE 4 /* T if in on-demand read mode */ char *rootdirname; /* name of cache root directory */ char *secctx; /* LSM security context */ char *tag; /* cache binding tag */ + refcount_t unbind_pincount;/* refcount to do daemon unbind */ + struct xarray reqs; /* xarray of pending on-demand requests */ + struct xarray ondemand_ids; /* xarray for ondemand_id allocation */ + u32 ondemand_id_next; +}; + +static inline bool cachefiles_in_ondemand_mode(struct cachefiles_cache *cache) +{ + return IS_ENABLED(CONFIG_CACHEFILES_ONDEMAND) && + test_bit(CACHEFILES_ONDEMAND_MODE, &cache->flags); +} + +struct cachefiles_req { + struct cachefiles_object *object; + struct completion done; + int error; + struct cachefiles_msg msg; }; +#define CACHEFILES_REQ_NEW XA_MARK_1 + #include <trace/events/cachefiles.h> static inline @@ -145,6 +172,8 @@ extern int cachefiles_has_space(struct cachefiles_cache *cache, * daemon.c */ extern const struct file_operations cachefiles_daemon_fops; +extern void cachefiles_get_unbind_pincount(struct cachefiles_cache *cache); +extern void cachefiles_put_unbind_pincount(struct cachefiles_cache *cache); /* * error_inject.c @@ -201,6 +230,16 @@ extern void cachefiles_put_object(struct cachefiles_object *object, */ extern bool cachefiles_begin_operation(struct netfs_cache_resources *cres, enum fscache_want_state want_state); +extern int __cachefiles_prepare_write(struct cachefiles_object *object, + struct file *file, + loff_t *_start, size_t *_len, + bool no_space_allocated_yet); +extern int __cachefiles_write(struct cachefiles_object *object, + struct file *file, + loff_t start_pos, + struct iov_iter *iter, + netfs_io_terminated_t term_func, + void *term_func_priv); /* * key.c @@ -241,6 +280,45 @@ extern bool cachefiles_commit_tmpfile(struct cachefiles_cache *cache, struct cachefiles_object *object); /* + * ondemand.c + */ +#ifdef CONFIG_CACHEFILES_ONDEMAND +extern ssize_t cachefiles_ondemand_daemon_read(struct cachefiles_cache *cache, + char __user *_buffer, size_t buflen); + +extern int cachefiles_ondemand_copen(struct cachefiles_cache *cache, + char *args); + +extern int cachefiles_ondemand_init_object(struct cachefiles_object *object); +extern void cachefiles_ondemand_clean_object(struct cachefiles_object *object); + +extern int cachefiles_ondemand_read(struct cachefiles_object *object, + loff_t pos, size_t len); + +#else +static inline ssize_t cachefiles_ondemand_daemon_read(struct cachefiles_cache *cache, + char __user *_buffer, size_t buflen) +{ + return -EOPNOTSUPP; +} + +static inline int cachefiles_ondemand_init_object(struct cachefiles_object *object) +{ + return 0; +} + +static inline void cachefiles_ondemand_clean_object(struct cachefiles_object *object) +{ +} + +static inline int cachefiles_ondemand_read(struct cachefiles_object *object, + loff_t pos, size_t len) +{ + return -EOPNOTSUPP; +} +#endif + +/* * security.c */ extern int cachefiles_get_security_ID(struct cachefiles_cache *cache); diff --git a/fs/cachefiles/io.c b/fs/cachefiles/io.c index 9dc81e781f2b..000a28f46e59 100644 --- a/fs/cachefiles/io.c +++ b/fs/cachefiles/io.c @@ -277,36 +277,33 @@ static void cachefiles_write_complete(struct kiocb *iocb, long ret) /* * Initiate a write to the cache. */ -static int cachefiles_write(struct netfs_cache_resources *cres, - loff_t start_pos, - struct iov_iter *iter, - netfs_io_terminated_t term_func, - void *term_func_priv) +int __cachefiles_write(struct cachefiles_object *object, + struct file *file, + loff_t start_pos, + struct iov_iter *iter, + netfs_io_terminated_t term_func, + void *term_func_priv) { - struct cachefiles_object *object; struct cachefiles_cache *cache; struct cachefiles_kiocb *ki; struct inode *inode; - struct file *file; unsigned int old_nofs; - ssize_t ret = -ENOBUFS; + ssize_t ret; size_t len = iov_iter_count(iter); - if (!fscache_wait_for_operation(cres, FSCACHE_WANT_WRITE)) - goto presubmission_error; fscache_count_write(); - object = cachefiles_cres_object(cres); cache = object->volume->cache; - file = cachefiles_cres_file(cres); _enter("%pD,%li,%llx,%zx/%llx", file, file_inode(file)->i_ino, start_pos, len, i_size_read(file_inode(file))); - ret = -ENOMEM; ki = kzalloc(sizeof(struct cachefiles_kiocb), GFP_KERNEL); - if (!ki) - goto presubmission_error; + if (!ki) { + if (term_func) + term_func(term_func_priv, -ENOMEM, false); + return -ENOMEM; + } refcount_set(&ki->ki_refcnt, 2); ki->iocb.ki_filp = file; @@ -314,7 +311,6 @@ static int cachefiles_write(struct netfs_cache_resources *cres, ki->iocb.ki_flags = IOCB_DIRECT | IOCB_WRITE; ki->iocb.ki_ioprio = get_current_ioprio(); ki->object = object; - ki->inval_counter = cres->inval_counter; ki->start = start_pos; ki->len = len; ki->term_func = term_func; @@ -369,11 +365,24 @@ in_progress: cachefiles_put_kiocb(ki); _leave(" = %zd", ret); return ret; +} -presubmission_error: - if (term_func) - term_func(term_func_priv, ret, false); - return ret; +static int cachefiles_write(struct netfs_cache_resources *cres, + loff_t start_pos, + struct iov_iter *iter, + netfs_io_terminated_t term_func, + void *term_func_priv) +{ + if (!fscache_wait_for_operation(cres, FSCACHE_WANT_WRITE)) { + if (term_func) + term_func(term_func_priv, -ENOBUFS, false); + return -ENOBUFS; + } + + return __cachefiles_write(cachefiles_cres_object(cres), + cachefiles_cres_file(cres), + start_pos, iter, + term_func, term_func_priv); } /* @@ -394,6 +403,7 @@ static enum netfs_io_source cachefiles_prepare_read(struct netfs_io_subrequest * enum netfs_io_source ret = NETFS_DOWNLOAD_FROM_SERVER; loff_t off, to; ino_t ino = file ? file_inode(file)->i_ino : 0; + int rc; _enter("%zx @%llx/%llx", subreq->len, subreq->start, i_size); @@ -406,7 +416,8 @@ static enum netfs_io_source cachefiles_prepare_read(struct netfs_io_subrequest * if (test_bit(FSCACHE_COOKIE_NO_DATA_TO_READ, &cookie->flags)) { __set_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags); why = cachefiles_trace_read_no_data; - goto out_no_object; + if (!test_bit(NETFS_SREQ_ONDEMAND, &subreq->flags)) + goto out_no_object; } /* The object and the file may be being created in the background. */ @@ -423,7 +434,7 @@ static enum netfs_io_source cachefiles_prepare_read(struct netfs_io_subrequest * object = cachefiles_cres_object(cres); cache = object->volume->cache; cachefiles_begin_secure(cache, &saved_cred); - +retry: off = cachefiles_inject_read_error(); if (off == 0) off = vfs_llseek(file, subreq->start, SEEK_DATA); @@ -474,6 +485,15 @@ static enum netfs_io_source cachefiles_prepare_read(struct netfs_io_subrequest * download_and_store: __set_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags); + if (test_bit(NETFS_SREQ_ONDEMAND, &subreq->flags)) { + rc = cachefiles_ondemand_read(object, subreq->start, + subreq->len); + if (!rc) { + __clear_bit(NETFS_SREQ_ONDEMAND, &subreq->flags); + goto retry; + } + ret = NETFS_INVALID_READ; + } out: cachefiles_end_secure(cache, saved_cred); out_no_object: @@ -484,13 +504,12 @@ out_no_object: /* * Prepare for a write to occur. */ -static int __cachefiles_prepare_write(struct netfs_cache_resources *cres, - loff_t *_start, size_t *_len, loff_t i_size, - bool no_space_allocated_yet) +int __cachefiles_prepare_write(struct cachefiles_object *object, + struct file *file, + loff_t *_start, size_t *_len, + bool no_space_allocated_yet) { - struct cachefiles_object *object = cachefiles_cres_object(cres); struct cachefiles_cache *cache = object->volume->cache; - struct file *file = cachefiles_cres_file(cres); loff_t start = *_start, pos; size_t len = *_len, down; int ret; @@ -577,7 +596,8 @@ static int cachefiles_prepare_write(struct netfs_cache_resources *cres, } cachefiles_begin_secure(cache, &saved_cred); - ret = __cachefiles_prepare_write(cres, _start, _len, i_size, + ret = __cachefiles_prepare_write(object, cachefiles_cres_file(cres), + _start, _len, no_space_allocated_yet); cachefiles_end_secure(cache, saved_cred); return ret; diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c index f256c8aff7bb..facf2ebe464b 100644 --- a/fs/cachefiles/namei.c +++ b/fs/cachefiles/namei.c @@ -57,6 +57,16 @@ static void __cachefiles_unmark_inode_in_use(struct cachefiles_object *object, trace_cachefiles_mark_inactive(object, inode); } +static void cachefiles_do_unmark_inode_in_use(struct cachefiles_object *object, + struct dentry *dentry) +{ + struct inode *inode = d_backing_inode(dentry); + + inode_lock(inode); + __cachefiles_unmark_inode_in_use(object, dentry); + inode_unlock(inode); +} + /* * Unmark a backing inode and tell cachefilesd that there's something that can * be culled. @@ -68,9 +78,7 @@ void cachefiles_unmark_inode_in_use(struct cachefiles_object *object, struct inode *inode = file_inode(file); if (inode) { - inode_lock(inode); - __cachefiles_unmark_inode_in_use(object, file->f_path.dentry); - inode_unlock(inode); + cachefiles_do_unmark_inode_in_use(object, file->f_path.dentry); if (!test_bit(CACHEFILES_OBJECT_USING_TMPFILE, &object->flags)) { atomic_long_add(inode->i_blocks, &cache->b_released); @@ -444,10 +452,9 @@ struct file *cachefiles_create_tmpfile(struct cachefiles_object *object) struct dentry *fan = volume->fanout[(u8)object->cookie->key_hash]; struct file *file; struct path path; - uint64_t ni_size = object->cookie->object_size; + uint64_t ni_size; long ret; - ni_size = round_up(ni_size, CACHEFILES_DIO_BLOCK_SIZE); cachefiles_begin_secure(cache, &saved_cred); @@ -473,6 +480,15 @@ struct file *cachefiles_create_tmpfile(struct cachefiles_object *object) goto out_dput; } + ret = cachefiles_ondemand_init_object(object); + if (ret < 0) { + file = ERR_PTR(ret); + goto out_unuse; + } + + ni_size = object->cookie->object_size; + ni_size = round_up(ni_size, CACHEFILES_DIO_BLOCK_SIZE); + if (ni_size > 0) { trace_cachefiles_trunc(object, d_backing_inode(path.dentry), 0, ni_size, cachefiles_trunc_expand_tmpfile); @@ -484,7 +500,7 @@ struct file *cachefiles_create_tmpfile(struct cachefiles_object *object) object, d_backing_inode(path.dentry), ret, cachefiles_trace_trunc_error); file = ERR_PTR(ret); - goto out_dput; + goto out_unuse; } } @@ -494,15 +510,20 @@ struct file *cachefiles_create_tmpfile(struct cachefiles_object *object) trace_cachefiles_vfs_error(object, d_backing_inode(path.dentry), PTR_ERR(file), cachefiles_trace_open_error); - goto out_dput; + goto out_unuse; } if (unlikely(!file->f_op->read_iter) || unlikely(!file->f_op->write_iter)) { fput(file); pr_notice("Cache does not support read_iter and write_iter\n"); file = ERR_PTR(-EINVAL); + goto out_unuse; } + goto out_dput; + +out_unuse: + cachefiles_do_unmark_inode_in_use(object, path.dentry); out_dput: dput(path.dentry); out: @@ -573,6 +594,10 @@ static bool cachefiles_open_file(struct cachefiles_object *object, } _debug("file -> %pd positive", dentry); + ret = cachefiles_ondemand_init_object(object); + if (ret < 0) + goto error_fput; + ret = cachefiles_check_auxdata(object, file); if (ret < 0) goto check_failed; @@ -590,14 +615,16 @@ static bool cachefiles_open_file(struct cachefiles_object *object, check_failed: fscache_cookie_lookup_negative(object->cookie); cachefiles_unmark_inode_in_use(object, file); - if (ret == -ESTALE) { - fput(file); - dput(dentry); + fput(file); + dput(dentry); + if (ret == -ESTALE) return cachefiles_create_file(object); - } + return false; + error_fput: fput(file); error: + cachefiles_do_unmark_inode_in_use(object, dentry); dput(dentry); return false; } diff --git a/fs/cachefiles/ondemand.c b/fs/cachefiles/ondemand.c new file mode 100644 index 000000000000..a41ae6efc545 --- /dev/null +++ b/fs/cachefiles/ondemand.c @@ -0,0 +1,503 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +#include <linux/fdtable.h> +#include <linux/anon_inodes.h> +#include <linux/uio.h> +#include "internal.h" + +static int cachefiles_ondemand_fd_release(struct inode *inode, + struct file *file) +{ + struct cachefiles_object *object = file->private_data; + struct cachefiles_cache *cache = object->volume->cache; + int object_id = object->ondemand_id; + struct cachefiles_req *req; + XA_STATE(xas, &cache->reqs, 0); + + xa_lock(&cache->reqs); + object->ondemand_id = CACHEFILES_ONDEMAND_ID_CLOSED; + + /* + * Flush all pending READ requests since their completion depends on + * anon_fd. + */ + xas_for_each(&xas, req, ULONG_MAX) { + if (req->msg.opcode == CACHEFILES_OP_READ) { + req->error = -EIO; + complete(&req->done); + xas_store(&xas, NULL); + } + } + xa_unlock(&cache->reqs); + + xa_erase(&cache->ondemand_ids, object_id); + trace_cachefiles_ondemand_fd_release(object, object_id); + cachefiles_put_object(object, cachefiles_obj_put_ondemand_fd); + cachefiles_put_unbind_pincount(cache); + return 0; +} + +static ssize_t cachefiles_ondemand_fd_write_iter(struct kiocb *kiocb, + struct iov_iter *iter) +{ + struct cachefiles_object *object = kiocb->ki_filp->private_data; + struct cachefiles_cache *cache = object->volume->cache; + struct file *file = object->file; + size_t len = iter->count; + loff_t pos = kiocb->ki_pos; + const struct cred *saved_cred; + int ret; + + if (!file) + return -ENOBUFS; + + cachefiles_begin_secure(cache, &saved_cred); + ret = __cachefiles_prepare_write(object, file, &pos, &len, true); + cachefiles_end_secure(cache, saved_cred); + if (ret < 0) + return ret; + + trace_cachefiles_ondemand_fd_write(object, file_inode(file), pos, len); + ret = __cachefiles_write(object, file, pos, iter, NULL, NULL); + if (!ret) + ret = len; + + return ret; +} + +static loff_t cachefiles_ondemand_fd_llseek(struct file *filp, loff_t pos, + int whence) +{ + struct cachefiles_object *object = filp->private_data; + struct file *file = object->file; + + if (!file) + return -ENOBUFS; + + return vfs_llseek(file, pos, whence); +} + +static long cachefiles_ondemand_fd_ioctl(struct file *filp, unsigned int ioctl, + unsigned long arg) +{ + struct cachefiles_object *object = filp->private_data; + struct cachefiles_cache *cache = object->volume->cache; + struct cachefiles_req *req; + unsigned long id; + + if (ioctl != CACHEFILES_IOC_READ_COMPLETE) + return -EINVAL; + + if (!test_bit(CACHEFILES_ONDEMAND_MODE, &cache->flags)) + return -EOPNOTSUPP; + + id = arg; + req = xa_erase(&cache->reqs, id); + if (!req) + return -EINVAL; + + trace_cachefiles_ondemand_cread(object, id); + complete(&req->done); + return 0; +} + +static const struct file_operations cachefiles_ondemand_fd_fops = { + .owner = THIS_MODULE, + .release = cachefiles_ondemand_fd_release, + .write_iter = cachefiles_ondemand_fd_write_iter, + .llseek = cachefiles_ondemand_fd_llseek, + .unlocked_ioctl = cachefiles_ondemand_fd_ioctl, +}; + +/* + * OPEN request Completion (copen) + * - command: "copen <id>,<cache_size>" + * <cache_size> indicates the object size if >=0, error code if negative + */ +int cachefiles_ondemand_copen(struct cachefiles_cache *cache, char *args) +{ + struct cachefiles_req *req; + struct fscache_cookie *cookie; + char *pid, *psize; + unsigned long id; + long size; + int ret; + + if (!test_bit(CACHEFILES_ONDEMAND_MODE, &cache->flags)) + return -EOPNOTSUPP; + + if (!*args) { + pr_err("Empty id specified\n"); + return -EINVAL; + } + + pid = args; + psize = strchr(args, ','); + if (!psize) { + pr_err("Cache size is not specified\n"); + return -EINVAL; + } + + *psize = 0; + psize++; + + ret = kstrtoul(pid, 0, &id); + if (ret) + return ret; + + req = xa_erase(&cache->reqs, id); + if (!req) + return -EINVAL; + + /* fail OPEN request if copen format is invalid */ + ret = kstrtol(psize, 0, &size); + if (ret) { + req->error = ret; + goto out; + } + + /* fail OPEN request if daemon reports an error */ + if (size < 0) { + if (!IS_ERR_VALUE(size)) + size = -EINVAL; + req->error = size; + goto out; + } + + cookie = req->object->cookie; + cookie->object_size = size; + if (size) + clear_bit(FSCACHE_COOKIE_NO_DATA_TO_READ, &cookie->flags); + else + set_bit(FSCACHE_COOKIE_NO_DATA_TO_READ, &cookie->flags); + trace_cachefiles_ondemand_copen(req->object, id, size); + +out: + complete(&req->done); + return ret; +} + +static int cachefiles_ondemand_get_fd(struct cachefiles_req *req) +{ + struct cachefiles_object *object; + struct cachefiles_cache *cache; + struct cachefiles_open *load; + struct file *file; + u32 object_id; + int ret, fd; + + object = cachefiles_grab_object(req->object, + cachefiles_obj_get_ondemand_fd); + cache = object->volume->cache; + + ret = xa_alloc_cyclic(&cache->ondemand_ids, &object_id, NULL, + XA_LIMIT(1, INT_MAX), + &cache->ondemand_id_next, GFP_KERNEL); + if (ret < 0) + goto err; + + fd = get_unused_fd_flags(O_WRONLY); + if (fd < 0) { + ret = fd; + goto err_free_id; + } + + file = anon_inode_getfile("[cachefiles]", &cachefiles_ondemand_fd_fops, + object, O_WRONLY); + if (IS_ERR(file)) { + ret = PTR_ERR(file); + goto err_put_fd; + } + + file->f_mode |= FMODE_PWRITE | FMODE_LSEEK; + fd_install(fd, file); + + load = (void *)req->msg.data; + load->fd = fd; + req->msg.object_id = object_id; + object->ondemand_id = object_id; + + cachefiles_get_unbind_pincount(cache); + trace_cachefiles_ondemand_open(object, &req->msg, load); + return 0; + +err_put_fd: + put_unused_fd(fd); +err_free_id: + xa_erase(&cache->ondemand_ids, object_id); +err: + cachefiles_put_object(object, cachefiles_obj_put_ondemand_fd); + return ret; +} + +ssize_t cachefiles_ondemand_daemon_read(struct cachefiles_cache *cache, + char __user *_buffer, size_t buflen) +{ + struct cachefiles_req *req; + struct cachefiles_msg *msg; + unsigned long id = 0; + size_t n; + int ret = 0; + XA_STATE(xas, &cache->reqs, 0); + + /* + * Search for a request that has not ever been processed, to prevent + * requests from being processed repeatedly. + */ + xa_lock(&cache->reqs); + req = xas_find_marked(&xas, UINT_MAX, CACHEFILES_REQ_NEW); + if (!req) { + xa_unlock(&cache->reqs); + return 0; + } + + msg = &req->msg; + n = msg->len; + + if (n > buflen) { + xa_unlock(&cache->reqs); + return -EMSGSIZE; + } + + xas_clear_mark(&xas, CACHEFILES_REQ_NEW); + xa_unlock(&cache->reqs); + + id = xas.xa_index; + msg->msg_id = id; + + if (msg->opcode == CACHEFILES_OP_OPEN) { + ret = cachefiles_ondemand_get_fd(req); + if (ret) + goto error; + } + + if (copy_to_user(_buffer, msg, n) != 0) { + ret = -EFAULT; + goto err_put_fd; + } + + /* CLOSE request has no reply */ + if (msg->opcode == CACHEFILES_OP_CLOSE) { + xa_erase(&cache->reqs, id); + complete(&req->done); + } + + return n; + +err_put_fd: + if (msg->opcode == CACHEFILES_OP_OPEN) + close_fd(((struct cachefiles_open *)msg->data)->fd); +error: + xa_erase(&cache->reqs, id); + req->error = ret; + complete(&req->done); + return ret; +} + +typedef int (*init_req_fn)(struct cachefiles_req *req, void *private); + +static int cachefiles_ondemand_send_req(struct cachefiles_object *object, + enum cachefiles_opcode opcode, + size_t data_len, + init_req_fn init_req, + void *private) +{ + struct cachefiles_cache *cache = object->volume->cache; + struct cachefiles_req *req; + XA_STATE(xas, &cache->reqs, 0); + int ret; + + if (!test_bit(CACHEFILES_ONDEMAND_MODE, &cache->flags)) + return 0; + + if (test_bit(CACHEFILES_DEAD, &cache->flags)) + return -EIO; + + req = kzalloc(sizeof(*req) + data_len, GFP_KERNEL); + if (!req) + return -ENOMEM; + + req->object = object; + init_completion(&req->done); + req->msg.opcode = opcode; + req->msg.len = sizeof(struct cachefiles_msg) + data_len; + + ret = init_req(req, private); + if (ret) + goto out; + + do { + /* + * Stop enqueuing the request when daemon is dying. The + * following two operations need to be atomic as a whole. + * 1) check cache state, and + * 2) enqueue request if cache is alive. + * Otherwise the request may be enqueued after xarray has been + * flushed, leaving the orphan request never being completed. + * + * CPU 1 CPU 2 + * ===== ===== + * test CACHEFILES_DEAD bit + * set CACHEFILES_DEAD bit + * flush requests in the xarray + * enqueue the request + */ + xas_lock(&xas); + + if (test_bit(CACHEFILES_DEAD, &cache->flags)) { + xas_unlock(&xas); + ret = -EIO; + goto out; + } + + /* coupled with the barrier in cachefiles_flush_reqs() */ + smp_mb(); + + if (opcode != CACHEFILES_OP_OPEN && object->ondemand_id <= 0) { + WARN_ON_ONCE(object->ondemand_id == 0); + xas_unlock(&xas); + ret = -EIO; + goto out; + } + + xas.xa_index = 0; + xas_find_marked(&xas, UINT_MAX, XA_FREE_MARK); + if (xas.xa_node == XAS_RESTART) + xas_set_err(&xas, -EBUSY); + xas_store(&xas, req); + xas_clear_mark(&xas, XA_FREE_MARK); + xas_set_mark(&xas, CACHEFILES_REQ_NEW); + xas_unlock(&xas); + } while (xas_nomem(&xas, GFP_KERNEL)); + + ret = xas_error(&xas); + if (ret) + goto out; + + wake_up_all(&cache->daemon_pollwq); + wait_for_completion(&req->done); + ret = req->error; +out: + kfree(req); + return ret; +} + +static int cachefiles_ondemand_init_open_req(struct cachefiles_req *req, + void *private) +{ + struct cachefiles_object *object = req->object; + struct fscache_cookie *cookie = object->cookie; + struct fscache_volume *volume = object->volume->vcookie; + struct cachefiles_open *load = (void *)req->msg.data; + size_t volume_key_size, cookie_key_size; + void *volume_key, *cookie_key; + + /* + * Volume key is a NUL-terminated string. key[0] stores strlen() of the + * string, followed by the content of the string (excluding '\0'). + */ + volume_key_size = volume->key[0] + 1; + volume_key = volume->key + 1; + + /* Cookie key is binary data, which is netfs specific. */ + cookie_key_size = cookie->key_len; + cookie_key = fscache_get_key(cookie); + + if (!(object->cookie->advice & FSCACHE_ADV_WANT_CACHE_SIZE)) { + pr_err("WANT_CACHE_SIZE is needed for on-demand mode\n"); + return -EINVAL; + } + + load->volume_key_size = volume_key_size; + load->cookie_key_size = cookie_key_size; + memcpy(load->data, volume_key, volume_key_size); + memcpy(load->data + volume_key_size, cookie_key, cookie_key_size); + + return 0; +} + +static int cachefiles_ondemand_init_close_req(struct cachefiles_req *req, + void *private) +{ + struct cachefiles_object *object = req->object; + int object_id = object->ondemand_id; + + /* + * It's possible that object id is still 0 if the cookie looking up + * phase failed before OPEN request has ever been sent. Also avoid + * sending CLOSE request for CACHEFILES_ONDEMAND_ID_CLOSED, which means + * anon_fd has already been closed. + */ + if (object_id <= 0) + return -ENOENT; + + req->msg.object_id = object_id; + trace_cachefiles_ondemand_close(object, &req->msg); + return 0; +} + +struct cachefiles_read_ctx { + loff_t off; + size_t len; +}; + +static int cachefiles_ondemand_init_read_req(struct cachefiles_req *req, + void *private) +{ + struct cachefiles_object *object = req->object; + struct cachefiles_read *load = (void *)req->msg.data; + struct cachefiles_read_ctx *read_ctx = private; + int object_id = object->ondemand_id; + + /* Stop enqueuing requests when daemon has closed anon_fd. */ + if (object_id <= 0) { + WARN_ON_ONCE(object_id == 0); + pr_info_once("READ: anonymous fd closed prematurely.\n"); + return -EIO; + } + + req->msg.object_id = object_id; + load->off = read_ctx->off; + load->len = read_ctx->len; + trace_cachefiles_ondemand_read(object, &req->msg, load); + return 0; +} + +int cachefiles_ondemand_init_object(struct cachefiles_object *object) +{ + struct fscache_cookie *cookie = object->cookie; + struct fscache_volume *volume = object->volume->vcookie; + size_t volume_key_size, cookie_key_size, data_len; + + /* + * CacheFiles will firstly check the cache file under the root cache + * directory. If the coherency check failed, it will fallback to + * creating a new tmpfile as the cache file. Reuse the previously + * allocated object ID if any. + */ + if (object->ondemand_id > 0) + return 0; + + volume_key_size = volume->key[0] + 1; + cookie_key_size = cookie->key_len; + data_len = sizeof(struct cachefiles_open) + + volume_key_size + cookie_key_size; + + return cachefiles_ondemand_send_req(object, CACHEFILES_OP_OPEN, + data_len, cachefiles_ondemand_init_open_req, NULL); +} + +void cachefiles_ondemand_clean_object(struct cachefiles_object *object) +{ + cachefiles_ondemand_send_req(object, CACHEFILES_OP_CLOSE, 0, + cachefiles_ondemand_init_close_req, NULL); +} + +int cachefiles_ondemand_read(struct cachefiles_object *object, + loff_t pos, size_t len) +{ + struct cachefiles_read_ctx read_ctx = {pos, len}; + + return cachefiles_ondemand_send_req(object, CACHEFILES_OP_READ, + sizeof(struct cachefiles_read), + cachefiles_ondemand_init_read_req, &read_ctx); +} diff --git a/fs/cachefiles/xattr.c b/fs/cachefiles/xattr.c index 35465109d9c4..00b087c14995 100644 --- a/fs/cachefiles/xattr.c +++ b/fs/cachefiles/xattr.c @@ -203,7 +203,7 @@ bool cachefiles_set_volume_xattr(struct cachefiles_volume *volume) if (!buf) return false; buf->reserved = cpu_to_be32(0); - memcpy(buf->data, p, len); + memcpy(buf->data, p, volume->vcookie->coherency_len); ret = cachefiles_inject_write_error(); if (ret == 0) diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index aa25bffd4823..7584aa6e5025 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -85,7 +85,7 @@ static bool ceph_dirty_folio(struct address_space *mapping, struct folio *folio) if (folio_test_dirty(folio)) { dout("%p dirty_folio %p idx %lu -- already dirty\n", mapping->host, folio, folio->index); - BUG_ON(!folio_get_private(folio)); + VM_BUG_ON_FOLIO(!folio_test_private(folio), folio); return false; } @@ -122,7 +122,7 @@ static bool ceph_dirty_folio(struct address_space *mapping, struct folio *folio) * Reference snap context in folio->private. Also set * PagePrivate so that we get invalidate_folio callback. */ - BUG_ON(folio_get_private(folio)); + VM_BUG_ON_FOLIO(folio_test_private(folio), folio); folio_attach_private(folio, snapc); return ceph_fscache_dirty_folio(mapping, folio); @@ -150,7 +150,7 @@ static void ceph_invalidate_folio(struct folio *folio, size_t offset, } WARN_ON(!folio_test_locked(folio)); - if (folio_get_private(folio)) { + if (folio_test_private(folio)) { dout("%p invalidate_folio idx %lu full dirty page\n", inode, folio->index); @@ -162,24 +162,24 @@ static void ceph_invalidate_folio(struct folio *folio, size_t offset, folio_wait_fscache(folio); } -static int ceph_releasepage(struct page *page, gfp_t gfp) +static bool ceph_release_folio(struct folio *folio, gfp_t gfp) { - struct inode *inode = page->mapping->host; + struct inode *inode = folio->mapping->host; - dout("%llx:%llx releasepage %p idx %lu (%sdirty)\n", - ceph_vinop(inode), page, - page->index, PageDirty(page) ? "" : "not "); + dout("%llx:%llx release_folio idx %lu (%sdirty)\n", + ceph_vinop(inode), + folio->index, folio_test_dirty(folio) ? "" : "not "); - if (PagePrivate(page)) - return 0; + if (folio_test_private(folio)) + return false; - if (PageFsCache(page)) { + if (folio_test_fscache(folio)) { if (current_is_kswapd() || !(gfp & __GFP_FS)) - return 0; - wait_on_page_fscache(page); + return false; + folio_wait_fscache(folio); } ceph_fscache_note_page_release(inode); - return 1; + return true; } static void ceph_netfs_expand_readahead(struct netfs_io_request *rreq) @@ -729,8 +729,11 @@ static void writepages_finish(struct ceph_osd_request *req) /* clean all pages */ for (i = 0; i < req->r_num_ops; i++) { - if (req->r_ops[i].op != CEPH_OSD_OP_WRITE) + if (req->r_ops[i].op != CEPH_OSD_OP_WRITE) { + pr_warn("%s incorrect op %d req %p index %d tid %llu\n", + __func__, req->r_ops[i].op, req, i, req->r_tid); break; + } osd_data = osd_req_op_extent_osd_data(req, i); BUG_ON(osd_data->type != CEPH_OSD_DATA_TYPE_PAGES); @@ -1311,14 +1314,14 @@ static int ceph_netfs_check_write_begin(struct file *file, loff_t pos, unsigned * clean, or already dirty within the same snap context. */ static int ceph_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned aop_flags, + loff_t pos, unsigned len, struct page **pagep, void **fsdata) { struct inode *inode = file_inode(file); struct folio *folio = NULL; int r; - r = netfs_write_begin(file, inode->i_mapping, pos, len, 0, &folio, NULL); + r = netfs_write_begin(file, inode->i_mapping, pos, len, &folio, NULL); if (r == 0) folio_wait_fscache(folio); if (r < 0) { @@ -1372,7 +1375,7 @@ out: } const struct address_space_operations ceph_aops = { - .readpage = netfs_readpage, + .read_folio = netfs_read_folio, .readahead = netfs_readahead, .writepage = ceph_writepage, .writepages = ceph_writepages_start, @@ -1380,7 +1383,7 @@ const struct address_space_operations ceph_aops = { .write_end = ceph_write_end, .dirty_folio = ceph_dirty_folio, .invalidate_folio = ceph_invalidate_folio, - .releasepage = ceph_releasepage, + .release_folio = ceph_release_folio, .direct_IO = noop_direct_IO, }; @@ -1772,7 +1775,7 @@ int ceph_mmap(struct file *file, struct vm_area_struct *vma) { struct address_space *mapping = file->f_mapping; - if (!mapping->a_ops->readpage) + if (!mapping->a_ops->read_folio) return -ENOEXEC; file_accessed(file); vma->vm_ops = &ceph_vmops; diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index f1ad6884d4da..5c14ef04e474 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -2274,6 +2274,8 @@ retry: list_for_each_entry(req, &ci->i_unsafe_dirops, r_unsafe_dir_item) { s = req->r_session; + if (!s) + continue; if (unlikely(s->s_mds >= max_sessions)) { spin_unlock(&ci->i_unsafe_lock); for (i = 0; i < max_sessions; i++) { @@ -2294,6 +2296,8 @@ retry: list_for_each_entry(req, &ci->i_unsafe_iops, r_unsafe_target_item) { s = req->r_session; + if (!s) + continue; if (unlikely(s->s_mds >= max_sessions)) { spin_unlock(&ci->i_unsafe_lock); for (i = 0; i < max_sessions; i++) { @@ -3870,6 +3874,7 @@ static void handle_cap_export(struct inode *inode, struct ceph_mds_caps *ex, dout("handle_cap_export inode %p ci %p mds%d mseq %d target %d\n", inode, ci, mds, mseq, target); retry: + down_read(&mdsc->snap_rwsem); spin_lock(&ci->i_ceph_lock); cap = __get_cap_for_mds(ci, mds); if (!cap || cap->cap_id != le64_to_cpu(ex->cap_id)) @@ -3933,6 +3938,7 @@ retry: } spin_unlock(&ci->i_ceph_lock); + up_read(&mdsc->snap_rwsem); mutex_unlock(&session->s_mutex); /* open target session */ @@ -3958,6 +3964,7 @@ retry: out_unlock: spin_unlock(&ci->i_ceph_lock); + up_read(&mdsc->snap_rwsem); mutex_unlock(&session->s_mutex); if (tsession) { mutex_unlock(&tsession->s_mutex); diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 6c9e837aa1d3..8c8226c0feac 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -629,9 +629,15 @@ static int ceph_finish_async_create(struct inode *dir, struct dentry *dentry, iinfo.change_attr = 1; ceph_encode_timespec64(&iinfo.btime, &now); - iinfo.xattr_len = ARRAY_SIZE(xattr_buf); - iinfo.xattr_data = xattr_buf; - memset(iinfo.xattr_data, 0, iinfo.xattr_len); + if (req->r_pagelist) { + iinfo.xattr_len = req->r_pagelist->length; + iinfo.xattr_data = req->r_pagelist->mapped_tail; + } else { + /* fake it */ + iinfo.xattr_len = ARRAY_SIZE(xattr_buf); + iinfo.xattr_data = xattr_buf; + memset(iinfo.xattr_data, 0, iinfo.xattr_len); + } in.ino = cpu_to_le64(vino.ino); in.snapid = cpu_to_le64(CEPH_NOSNAP); @@ -743,6 +749,10 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry, err = ceph_security_init_secctx(dentry, mode, &as_ctx); if (err < 0) goto out_ctx; + /* Async create can't handle more than a page of xattrs */ + if (as_ctx.pagelist && + !list_is_singular(&as_ctx.pagelist->head)) + try_async = false; } else if (!d_in_lookup(dentry)) { /* If it's not being looked up, it's negative */ return -ENOENT; diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index fa38c013126d..00c3de177dd6 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -4434,8 +4434,6 @@ static void maybe_recover_session(struct ceph_mds_client *mdsc) bool check_session_state(struct ceph_mds_session *s) { - struct ceph_fs_client *fsc = s->s_mdsc->fsc; - switch (s->s_state) { case CEPH_MDS_SESSION_OPEN: if (s->s_ttl && time_after(jiffies, s->s_ttl)) { @@ -4444,10 +4442,6 @@ bool check_session_state(struct ceph_mds_session *s) } break; case CEPH_MDS_SESSION_CLOSING: - /* Should never reach this when not force unmounting */ - WARN_ON_ONCE(s->s_ttl && - READ_ONCE(fsc->mount_state) != CEPH_MOUNT_SHUTDOWN); - fallthrough; case CEPH_MDS_SESSION_NEW: case CEPH_MDS_SESSION_RESTARTING: case CEPH_MDS_SESSION_CLOSED: diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index a47fa44b6d52..2b1a1c029c75 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -266,22 +266,24 @@ static void cifs_kill_sb(struct super_block *sb) * before we kill the sb. */ if (cifs_sb->root) { + for (node = rb_first(root); node; node = rb_next(node)) { + tlink = rb_entry(node, struct tcon_link, tl_rbnode); + tcon = tlink_tcon(tlink); + if (IS_ERR(tcon)) + continue; + cfid = &tcon->crfid; + mutex_lock(&cfid->fid_mutex); + if (cfid->dentry) { + dput(cfid->dentry); + cfid->dentry = NULL; + } + mutex_unlock(&cfid->fid_mutex); + } + + /* finally release root dentry */ dput(cifs_sb->root); cifs_sb->root = NULL; } - node = rb_first(root); - while (node != NULL) { - tlink = rb_entry(node, struct tcon_link, tl_rbnode); - tcon = tlink_tcon(tlink); - cfid = &tcon->crfid; - mutex_lock(&cfid->fid_mutex); - if (cfid->dentry) { - dput(cfid->dentry); - cfid->dentry = NULL; - } - mutex_unlock(&cfid->fid_mutex); - node = rb_next(node); - } kill_anon_super(sb); cifs_umount(cifs_sb); @@ -944,7 +946,7 @@ cifs_loose_read_iter(struct kiocb *iocb, struct iov_iter *iter) ssize_t rc; struct inode *inode = file_inode(iocb->ki_filp); - if (iocb->ki_filp->f_flags & O_DIRECT) + if (iocb->ki_flags & IOCB_DIRECT) return cifs_user_readv(iocb, iter); rc = cifs_revalidate_mapping(inode); diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index 15a5c5db038b..c0542bdcd06b 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -153,5 +153,5 @@ extern const struct export_operations cifs_export_ops; #endif /* CONFIG_CIFS_NFSD_EXPORT */ #define SMB3_PRODUCT_BUILD 35 -#define CIFS_VERSION "2.35" +#define CIFS_VERSION "2.36" #endif /* _CIFSFS_H */ diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index ee3b7c15e884..42e14f408856 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -453,9 +453,7 @@ static int reconnect_target_unlocked(struct TCP_Server_Info *server, struct dfs_ return rc; } -static int -reconnect_dfs_server(struct TCP_Server_Info *server, - bool mark_smb_session) +static int reconnect_dfs_server(struct TCP_Server_Info *server) { int rc = 0; const char *refpath = server->current_fullpath + 1; @@ -479,7 +477,12 @@ reconnect_dfs_server(struct TCP_Server_Info *server, if (!cifs_tcp_ses_needs_reconnect(server, num_targets)) return 0; - cifs_mark_tcp_ses_conns_for_reconnect(server, mark_smb_session); + /* + * Unconditionally mark all sessions & tcons for reconnect as we might be connecting to a + * different server or share during failover. It could be improved by adding some logic to + * only do that in case it connects to a different server or share, though. + */ + cifs_mark_tcp_ses_conns_for_reconnect(server, true); cifs_abort_connection(server); @@ -531,13 +534,20 @@ int cifs_reconnect(struct TCP_Server_Info *server, bool mark_smb_session) { /* If tcp session is not an dfs connection, then reconnect to last target server */ spin_lock(&cifs_tcp_ses_lock); - if (!server->is_dfs_conn || !server->origin_fullpath || !server->leaf_fullpath) { + if (!server->is_dfs_conn) { spin_unlock(&cifs_tcp_ses_lock); return __cifs_reconnect(server, mark_smb_session); } spin_unlock(&cifs_tcp_ses_lock); - return reconnect_dfs_server(server, mark_smb_session); + mutex_lock(&server->refpath_lock); + if (!server->origin_fullpath || !server->leaf_fullpath) { + mutex_unlock(&server->refpath_lock); + return __cifs_reconnect(server, mark_smb_session); + } + mutex_unlock(&server->refpath_lock); + + return reconnect_dfs_server(server); } #else int cifs_reconnect(struct TCP_Server_Info *server, bool mark_smb_session) @@ -1046,7 +1056,7 @@ smb2_add_credits_from_hdr(char *buffer, struct TCP_Server_Info *server) spin_unlock(&server->req_lock); wake_up(&server->request_q); - trace_smb3_add_credits(server->CurrentMid, + trace_smb3_hdr_credits(server->CurrentMid, server->conn_id, server->hostname, scredits, le16_to_cpu(shdr->CreditRequest), in_flight); cifs_server_dbg(FYI, "%s: added %u credits total=%d\n", @@ -3672,9 +3682,11 @@ static void setup_server_referral_paths(struct mount_ctx *mnt_ctx) { struct TCP_Server_Info *server = mnt_ctx->server; + mutex_lock(&server->refpath_lock); server->origin_fullpath = mnt_ctx->origin_fullpath; server->leaf_fullpath = mnt_ctx->leaf_fullpath; server->current_fullpath = mnt_ctx->leaf_fullpath; + mutex_unlock(&server->refpath_lock); mnt_ctx->origin_fullpath = mnt_ctx->leaf_fullpath = NULL; } @@ -4465,7 +4477,7 @@ static int tree_connect_dfs_target(const unsigned int xid, struct cifs_tcon *tco */ if (rc && server->current_fullpath != server->origin_fullpath) { server->current_fullpath = server->origin_fullpath; - cifs_reconnect(tcon->ses->server, true); + cifs_signal_cifsd_for_reconnect(server, true); } dfs_cache_free_tgts(tl); diff --git a/fs/cifs/dfs_cache.c b/fs/cifs/dfs_cache.c index 30e040da4f09..956f8e5cf3e7 100644 --- a/fs/cifs/dfs_cache.c +++ b/fs/cifs/dfs_cache.c @@ -1422,12 +1422,14 @@ static int refresh_tcon(struct cifs_ses **sessions, struct cifs_tcon *tcon, bool struct TCP_Server_Info *server = tcon->ses->server; mutex_lock(&server->refpath_lock); - if (strcasecmp(server->leaf_fullpath, server->origin_fullpath)) - __refresh_tcon(server->leaf_fullpath + 1, sessions, tcon, force_refresh); + if (server->origin_fullpath) { + if (server->leaf_fullpath && strcasecmp(server->leaf_fullpath, + server->origin_fullpath)) + __refresh_tcon(server->leaf_fullpath + 1, sessions, tcon, force_refresh); + __refresh_tcon(server->origin_fullpath + 1, sessions, tcon, force_refresh); + } mutex_unlock(&server->refpath_lock); - __refresh_tcon(server->origin_fullpath + 1, sessions, tcon, force_refresh); - return 0; } @@ -1530,11 +1532,14 @@ static void refresh_mounts(struct cifs_ses **sessions) list_del_init(&tcon->ulist); mutex_lock(&server->refpath_lock); - if (strcasecmp(server->leaf_fullpath, server->origin_fullpath)) - __refresh_tcon(server->leaf_fullpath + 1, sessions, tcon, false); + if (server->origin_fullpath) { + if (server->leaf_fullpath && strcasecmp(server->leaf_fullpath, + server->origin_fullpath)) + __refresh_tcon(server->leaf_fullpath + 1, sessions, tcon, false); + __refresh_tcon(server->origin_fullpath + 1, sessions, tcon, false); + } mutex_unlock(&server->refpath_lock); - __refresh_tcon(server->origin_fullpath + 1, sessions, tcon, false); cifs_put_tcon(tcon); } } diff --git a/fs/cifs/file.c b/fs/cifs/file.c index d511a78383c3..06003bb9cbe9 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -4612,8 +4612,9 @@ read_complete: return rc; } -static int cifs_readpage(struct file *file, struct page *page) +static int cifs_read_folio(struct file *file, struct folio *folio) { + struct page *page = &folio->page; loff_t offset = page_file_offset(page); int rc = -EACCES; unsigned int xid; @@ -4626,7 +4627,7 @@ static int cifs_readpage(struct file *file, struct page *page) return rc; } - cifs_dbg(FYI, "readpage %p at offset %d 0x%x\n", + cifs_dbg(FYI, "read_folio %p at offset %d 0x%x\n", page, (int)offset, (int)offset); rc = cifs_readpage_worker(file, page, &offset); @@ -4681,7 +4682,7 @@ bool is_size_safe_to_change(struct cifsInodeInfo *cifsInode, __u64 end_of_file) } static int cifs_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, + loff_t pos, unsigned len, struct page **pagep, void **fsdata) { int oncethru = 0; @@ -4695,7 +4696,7 @@ static int cifs_write_begin(struct file *file, struct address_space *mapping, cifs_dbg(FYI, "write_begin from %lld len %d\n", (long long)pos, len); start: - page = grab_cache_page_write_begin(mapping, index, flags); + page = grab_cache_page_write_begin(mapping, index); if (!page) { rc = -ENOMEM; goto out; @@ -4757,16 +4758,16 @@ out: return rc; } -static int cifs_release_page(struct page *page, gfp_t gfp) +static bool cifs_release_folio(struct folio *folio, gfp_t gfp) { - if (PagePrivate(page)) + if (folio_test_private(folio)) return 0; - if (PageFsCache(page)) { + if (folio_test_fscache(folio)) { if (current_is_kswapd() || !(gfp & __GFP_FS)) return false; - wait_on_page_fscache(page); + folio_wait_fscache(folio); } - fscache_note_page_release(cifs_inode_cookie(page->mapping->host)); + fscache_note_page_release(cifs_inode_cookie(folio->mapping->host)); return true; } @@ -4965,14 +4966,14 @@ static bool cifs_dirty_folio(struct address_space *mapping, struct folio *folio) #endif const struct address_space_operations cifs_addr_ops = { - .readpage = cifs_readpage, + .read_folio = cifs_read_folio, .readahead = cifs_readahead, .writepage = cifs_writepage, .writepages = cifs_writepages, .write_begin = cifs_write_begin, .write_end = cifs_write_end, .dirty_folio = cifs_dirty_folio, - .releasepage = cifs_release_page, + .release_folio = cifs_release_folio, .direct_IO = cifs_direct_io, .invalidate_folio = cifs_invalidate_folio, .launder_folio = cifs_launder_folio, @@ -4986,18 +4987,18 @@ const struct address_space_operations cifs_addr_ops = { }; /* - * cifs_readpages requires the server to support a buffer large enough to + * cifs_readahead requires the server to support a buffer large enough to * contain the header plus one complete page of data. Otherwise, we need - * to leave cifs_readpages out of the address space operations. + * to leave cifs_readahead out of the address space operations. */ const struct address_space_operations cifs_addr_ops_smallbuf = { - .readpage = cifs_readpage, + .read_folio = cifs_read_folio, .writepage = cifs_writepage, .writepages = cifs_writepages, .write_begin = cifs_write_begin, .write_end = cifs_write_end, .dirty_folio = cifs_dirty_folio, - .releasepage = cifs_release_page, + .release_folio = cifs_release_folio, .invalidate_folio = cifs_invalidate_folio, .launder_folio = cifs_launder_folio, }; diff --git a/fs/cifs/link.c b/fs/cifs/link.c index 852e54ee82c2..bbdf3281559c 100644 --- a/fs/cifs/link.c +++ b/fs/cifs/link.c @@ -85,6 +85,9 @@ parse_mf_symlink(const u8 *buf, unsigned int buf_len, unsigned int *_link_len, if (rc != 1) return -EINVAL; + if (link_len > CIFS_MF_SYMLINK_LINK_MAXLEN) + return -EINVAL; + rc = symlink_hash(link_len, link_str, md5_hash); if (rc) { cifs_dbg(FYI, "%s: MD5 hash failure: %d\n", __func__, rc); diff --git a/fs/cifs/netmisc.c b/fs/cifs/netmisc.c index ebe236b9d9f5..235aa1b395eb 100644 --- a/fs/cifs/netmisc.c +++ b/fs/cifs/netmisc.c @@ -896,7 +896,7 @@ map_and_check_smb_error(struct mid_q_entry *mid, bool logErr) if (class == ERRSRV && code == ERRbaduid) { cifs_dbg(FYI, "Server returned 0x%x, reconnecting session...\n", code); - cifs_reconnect(mid->server, false); + cifs_signal_cifsd_for_reconnect(mid->server, false); } } diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c index c653beb735b8..3fe47a88f47d 100644 --- a/fs/cifs/smb2misc.c +++ b/fs/cifs/smb2misc.c @@ -150,16 +150,18 @@ smb2_check_message(char *buf, unsigned int len, struct TCP_Server_Info *srvr) struct smb2_transform_hdr *thdr = (struct smb2_transform_hdr *)buf; struct cifs_ses *ses = NULL; + struct cifs_ses *iter; /* decrypt frame now that it is completely read in */ spin_lock(&cifs_tcp_ses_lock); - list_for_each_entry(ses, &srvr->smb_ses_list, smb_ses_list) { - if (ses->Suid == le64_to_cpu(thdr->SessionId)) + list_for_each_entry(iter, &srvr->smb_ses_list, smb_ses_list) { + if (iter->Suid == le64_to_cpu(thdr->SessionId)) { + ses = iter; break; + } } spin_unlock(&cifs_tcp_ses_lock); - if (list_entry_is_head(ses, &srvr->smb_ses_list, - smb_ses_list)) { + if (!ses) { cifs_dbg(VFS, "no decryption - session id not found\n"); return 1; } diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index db23f5b404ba..d6aaeff4a30a 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -86,6 +86,9 @@ smb2_add_credits(struct TCP_Server_Info *server, if (*val > 65000) { *val = 65000; /* Don't get near 64K credits, avoid srv bugs */ pr_warn_once("server overflowed SMB3 credits\n"); + trace_smb3_overflow_credits(server->CurrentMid, + server->conn_id, server->hostname, *val, + add, server->in_flight); } server->in_flight--; if (server->in_flight == 0 && @@ -251,7 +254,7 @@ smb2_wait_mtu_credits(struct TCP_Server_Info *server, unsigned int size, in_flight = server->in_flight; spin_unlock(&server->req_lock); - trace_smb3_add_credits(server->CurrentMid, + trace_smb3_wait_credits(server->CurrentMid, server->conn_id, server->hostname, scredits, -(credits->value), in_flight); cifs_dbg(FYI, "%s: removed %u credits total=%d\n", __func__, credits->value, scredits); @@ -300,7 +303,7 @@ smb2_adjust_credits(struct TCP_Server_Info *server, spin_unlock(&server->req_lock); wake_up(&server->request_q); - trace_smb3_add_credits(server->CurrentMid, + trace_smb3_adj_credits(server->CurrentMid, server->conn_id, server->hostname, scredits, credits->value - new_val, in_flight); cifs_dbg(FYI, "%s: adjust added %u credits total=%d\n", @@ -1855,9 +1858,17 @@ smb2_copychunk_range(const unsigned int xid, int chunks_copied = 0; bool chunk_sizes_updated = false; ssize_t bytes_written, total_bytes_written = 0; + struct inode *inode; pcchunk = kmalloc(sizeof(struct copychunk_ioctl), GFP_KERNEL); + /* + * We need to flush all unwritten data before we can send the + * copychunk ioctl to the server. + */ + inode = d_inode(trgtfile->dentry); + filemap_write_and_wait(inode->i_mapping); + if (pcchunk == NULL) return -ENOMEM; @@ -2492,7 +2503,7 @@ smb2_is_status_pending(char *buf, struct TCP_Server_Info *server) spin_unlock(&server->req_lock); wake_up(&server->request_q); - trace_smb3_add_credits(server->CurrentMid, + trace_smb3_pend_credits(server->CurrentMid, server->conn_id, server->hostname, scredits, le16_to_cpu(shdr->CreditRequest), in_flight); cifs_dbg(FYI, "%s: status pending add %u credits total=%d\n", diff --git a/fs/cifs/trace.h b/fs/cifs/trace.h index 6cecf302dcfd..bc279616c513 100644 --- a/fs/cifs/trace.h +++ b/fs/cifs/trace.h @@ -1006,6 +1006,13 @@ DEFINE_SMB3_CREDIT_EVENT(credit_timeout); DEFINE_SMB3_CREDIT_EVENT(insufficient_credits); DEFINE_SMB3_CREDIT_EVENT(too_many_credits); DEFINE_SMB3_CREDIT_EVENT(add_credits); +DEFINE_SMB3_CREDIT_EVENT(adj_credits); +DEFINE_SMB3_CREDIT_EVENT(hdr_credits); +DEFINE_SMB3_CREDIT_EVENT(nblk_credits); +DEFINE_SMB3_CREDIT_EVENT(pend_credits); +DEFINE_SMB3_CREDIT_EVENT(wait_credits); +DEFINE_SMB3_CREDIT_EVENT(waitff_credits); +DEFINE_SMB3_CREDIT_EVENT(overflow_credits); DEFINE_SMB3_CREDIT_EVENT(set_credits); #endif /* _CIFS_TRACE_H */ diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index eeb1a699bd6f..c667e6ddfe2f 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -464,13 +464,12 @@ smb_send_rqst(struct TCP_Server_Info *server, int num_rqst, return -EIO; } - tr_hdr = kmalloc(sizeof(*tr_hdr), GFP_NOFS); + tr_hdr = kzalloc(sizeof(*tr_hdr), GFP_NOFS); if (!tr_hdr) return -ENOMEM; memset(&cur_rqst[0], 0, sizeof(cur_rqst)); memset(&iov, 0, sizeof(iov)); - memset(tr_hdr, 0, sizeof(*tr_hdr)); iov.iov_base = tr_hdr; iov.iov_len = sizeof(*tr_hdr); @@ -542,7 +541,7 @@ wait_for_free_credits(struct TCP_Server_Info *server, const int num_credits, in_flight = server->in_flight; spin_unlock(&server->req_lock); - trace_smb3_add_credits(server->CurrentMid, + trace_smb3_nblk_credits(server->CurrentMid, server->conn_id, server->hostname, scredits, -1, in_flight); cifs_dbg(FYI, "%s: remove %u credits total=%d\n", __func__, 1, scredits); @@ -648,7 +647,7 @@ wait_for_free_credits(struct TCP_Server_Info *server, const int num_credits, in_flight = server->in_flight; spin_unlock(&server->req_lock); - trace_smb3_add_credits(server->CurrentMid, + trace_smb3_waitff_credits(server->CurrentMid, server->conn_id, server->hostname, scredits, -(num_credits), in_flight); cifs_dbg(FYI, "%s: remove %u credits total=%d\n", diff --git a/fs/coda/symlink.c b/fs/coda/symlink.c index 8907d0508198..8adf81042498 100644 --- a/fs/coda/symlink.c +++ b/fs/coda/symlink.c @@ -20,9 +20,10 @@ #include "coda_psdev.h" #include "coda_linux.h" -static int coda_symlink_filler(struct file *file, struct page *page) +static int coda_symlink_filler(struct file *file, struct folio *folio) { - struct inode *inode = page->mapping->host; + struct page *page = &folio->page; + struct inode *inode = folio->mapping->host; int error; struct coda_inode_info *cii; unsigned int len = PAGE_SIZE; @@ -44,5 +45,5 @@ fail: } const struct address_space_operations coda_symlink_aops = { - .readpage = coda_symlink_filler, + .read_folio = coda_symlink_filler, }; diff --git a/fs/cramfs/README b/fs/cramfs/README index d71b27e0ff15..778df5c4d70b 100644 --- a/fs/cramfs/README +++ b/fs/cramfs/README @@ -115,7 +115,7 @@ Block Size (Block size in cramfs refers to the size of input data that is compressed at a time. It's intended to be somewhere around -PAGE_SIZE for cramfs_readpage's convenience.) +PAGE_SIZE for cramfs_read_folio's convenience.) The superblock ought to indicate the block size that the fs was written for, since comments in <linux/pagemap.h> indicate that @@ -161,7 +161,7 @@ size. The options are: PAGE_SIZE. It's easy enough to change the kernel to use a smaller value than -PAGE_SIZE: just make cramfs_readpage read multiple blocks. +PAGE_SIZE: just make cramfs_read_folio read multiple blocks. The cost of option 1 is that kernels with a larger PAGE_SIZE value don't get as good compression as they can. @@ -173,9 +173,9 @@ they don't mind their cramfs being inaccessible to kernels with smaller PAGE_SIZE values. Option 3 is easy to implement if we don't mind being CPU-inefficient: -e.g. get readpage to decompress to a buffer of size MAX_BLKSIZE (which +e.g. get read_folio to decompress to a buffer of size MAX_BLKSIZE (which must be no larger than 32KB) and discard what it doesn't need. -Getting readpage to read into all the covered pages is harder. +Getting read_folio to read into all the covered pages is harder. The main advantage of option 3 over 1, 2, is better compression. The cost is greater complexity. Probably not worth it, but I hope someone diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c index 666aa380011e..7ae59a6afc5c 100644 --- a/fs/cramfs/inode.c +++ b/fs/cramfs/inode.c @@ -414,7 +414,7 @@ static int cramfs_physmem_mmap(struct file *file, struct vm_area_struct *vma) /* * Let's create a mixed map if we can't map it all. * The normal paging machinery will take care of the - * unpopulated ptes via cramfs_readpage(). + * unpopulated ptes via cramfs_read_folio(). */ int i; vma->vm_flags |= VM_MIXEDMAP; @@ -814,8 +814,9 @@ out: return d_splice_alias(inode, dentry); } -static int cramfs_readpage(struct file *file, struct page *page) +static int cramfs_read_folio(struct file *file, struct folio *folio) { + struct page *page = &folio->page; struct inode *inode = page->mapping->host; u32 maxblock; int bytes_filled; @@ -925,7 +926,7 @@ err: } static const struct address_space_operations cramfs_aops = { - .readpage = cramfs_readpage + .read_folio = cramfs_read_folio }; /* diff --git a/fs/crypto/crypto.c b/fs/crypto/crypto.c index 526a4c1bed99..e78be66bbf01 100644 --- a/fs/crypto/crypto.c +++ b/fs/crypto/crypto.c @@ -113,7 +113,7 @@ int fscrypt_crypt_block(const struct inode *inode, fscrypt_direction_t rw, if (WARN_ON_ONCE(len <= 0)) return -EINVAL; - if (WARN_ON_ONCE(len % FS_CRYPTO_BLOCK_SIZE != 0)) + if (WARN_ON_ONCE(len % FSCRYPT_CONTENTS_ALIGNMENT != 0)) return -EINVAL; fscrypt_generate_iv(&iv, lblk_num, ci); @@ -213,8 +213,8 @@ EXPORT_SYMBOL(fscrypt_encrypt_pagecache_blocks); * fscrypt_encrypt_block_inplace() - Encrypt a filesystem block in-place * @inode: The inode to which this block belongs * @page: The page containing the block to encrypt - * @len: Size of block to encrypt. Doesn't need to be a multiple of the - * fs block size, but must be a multiple of FS_CRYPTO_BLOCK_SIZE. + * @len: Size of block to encrypt. This must be a multiple of + * FSCRYPT_CONTENTS_ALIGNMENT. * @offs: Byte offset within @page at which the block to encrypt begins * @lblk_num: Filesystem logical block number of the block, i.e. the 0-based * number of the block within the file @@ -283,8 +283,8 @@ EXPORT_SYMBOL(fscrypt_decrypt_pagecache_blocks); * fscrypt_decrypt_block_inplace() - Decrypt a filesystem block in-place * @inode: The inode to which this block belongs * @page: The page containing the block to decrypt - * @len: Size of block to decrypt. Doesn't need to be a multiple of the - * fs block size, but must be a multiple of FS_CRYPTO_BLOCK_SIZE. + * @len: Size of block to decrypt. This must be a multiple of + * FSCRYPT_CONTENTS_ALIGNMENT. * @offs: Byte offset within @page at which the block to decrypt begins * @lblk_num: Filesystem logical block number of the block, i.e. the 0-based * number of the block within the file diff --git a/fs/crypto/fname.c b/fs/crypto/fname.c index a9be4bc74a94..14e0ef5e9a20 100644 --- a/fs/crypto/fname.c +++ b/fs/crypto/fname.c @@ -19,6 +19,13 @@ #include "fscrypt_private.h" /* + * The minimum message length (input and output length), in bytes, for all + * filenames encryption modes. Filenames shorter than this will be zero-padded + * before being encrypted. + */ +#define FSCRYPT_FNAME_MIN_MSG_LEN 16 + +/* * struct fscrypt_nokey_name - identifier for directory entry when key is absent * * When userspace lists an encrypted directory without access to the key, the @@ -267,7 +274,7 @@ bool fscrypt_fname_encrypted_size(const union fscrypt_policy *policy, if (orig_len > max_len) return false; - encrypted_len = max(orig_len, (u32)FS_CRYPTO_BLOCK_SIZE); + encrypted_len = max_t(u32, orig_len, FSCRYPT_FNAME_MIN_MSG_LEN); encrypted_len = round_up(encrypted_len, padding); *encrypted_len_ret = min(encrypted_len, max_len); return true; @@ -350,7 +357,7 @@ int fscrypt_fname_disk_to_usr(const struct inode *inode, return 0; } - if (iname->len < FS_CRYPTO_BLOCK_SIZE) + if (iname->len < FSCRYPT_FNAME_MIN_MSG_LEN) return -EUCLEAN; if (fscrypt_has_encryption_key(inode)) diff --git a/fs/crypto/fscrypt_private.h b/fs/crypto/fscrypt_private.h index 5b0a9e6478b5..6b4c8094cc7b 100644 --- a/fs/crypto/fscrypt_private.h +++ b/fs/crypto/fscrypt_private.h @@ -545,8 +545,8 @@ struct key * fscrypt_find_master_key(struct super_block *sb, const struct fscrypt_key_specifier *mk_spec); -int fscrypt_add_test_dummy_key(struct super_block *sb, - struct fscrypt_key_specifier *key_spec); +int fscrypt_get_test_dummy_key_identifier( + u8 key_identifier[FSCRYPT_KEY_IDENTIFIER_SIZE]); int fscrypt_verify_key_added(struct super_block *sb, const u8 identifier[FSCRYPT_KEY_IDENTIFIER_SIZE]); @@ -561,7 +561,9 @@ struct fscrypt_mode { int keysize; /* key size in bytes */ int security_strength; /* security strength in bytes */ int ivsize; /* IV size in bytes */ - int logged_impl_name; + int logged_cryptoapi_impl; + int logged_blk_crypto_native; + int logged_blk_crypto_fallback; enum blk_crypto_mode_num blk_crypto_mode; }; @@ -621,6 +623,8 @@ int fscrypt_setup_v1_file_key_via_subscribed_keyrings(struct fscrypt_info *ci); bool fscrypt_policies_equal(const union fscrypt_policy *policy1, const union fscrypt_policy *policy2); +int fscrypt_policy_to_key_spec(const union fscrypt_policy *policy, + struct fscrypt_key_specifier *key_spec); bool fscrypt_supported_policy(const union fscrypt_policy *policy_u, const struct inode *inode); int fscrypt_policy_from_context(union fscrypt_policy *policy_u, diff --git a/fs/crypto/inline_crypt.c b/fs/crypto/inline_crypt.c index 93c2ca858092..90f3e68f166e 100644 --- a/fs/crypto/inline_crypt.c +++ b/fs/crypto/inline_crypt.c @@ -12,7 +12,7 @@ * provides the key and IV to use. */ -#include <linux/blk-crypto.h> +#include <linux/blk-crypto-profile.h> #include <linux/blkdev.h> #include <linux/buffer_head.h> #include <linux/sched/mm.h> @@ -64,6 +64,35 @@ static unsigned int fscrypt_get_dun_bytes(const struct fscrypt_info *ci) return DIV_ROUND_UP(lblk_bits, 8); } +/* + * Log a message when starting to use blk-crypto (native) or blk-crypto-fallback + * for an encryption mode for the first time. This is the blk-crypto + * counterpart to the message logged when starting to use the crypto API for the + * first time. A limitation is that these messages don't convey which specific + * filesystems or files are using each implementation. However, *usually* + * systems use just one implementation per mode, which makes these messages + * helpful for debugging problems where the "wrong" implementation is used. + */ +static void fscrypt_log_blk_crypto_impl(struct fscrypt_mode *mode, + struct request_queue **devs, + int num_devs, + const struct blk_crypto_config *cfg) +{ + int i; + + for (i = 0; i < num_devs; i++) { + if (!IS_ENABLED(CONFIG_BLK_INLINE_ENCRYPTION_FALLBACK) || + __blk_crypto_cfg_supported(devs[i]->crypto_profile, cfg)) { + if (!xchg(&mode->logged_blk_crypto_native, 1)) + pr_info("fscrypt: %s using blk-crypto (native)\n", + mode->friendly_name); + } else if (!xchg(&mode->logged_blk_crypto_fallback, 1)) { + pr_info("fscrypt: %s using blk-crypto-fallback\n", + mode->friendly_name); + } + } +} + /* Enable inline encryption for this file if supported. */ int fscrypt_select_encryption_impl(struct fscrypt_info *ci) { @@ -117,6 +146,8 @@ int fscrypt_select_encryption_impl(struct fscrypt_info *ci) goto out_free_devs; } + fscrypt_log_blk_crypto_impl(ci->ci_mode, devs, num_devs, &crypto_cfg); + ci->ci_inlinecrypt = true; out_free_devs: kfree(devs); diff --git a/fs/crypto/keyring.c b/fs/crypto/keyring.c index 0b3ffbb4faf4..caee9f8620dd 100644 --- a/fs/crypto/keyring.c +++ b/fs/crypto/keyring.c @@ -688,28 +688,68 @@ out_wipe_secret: } EXPORT_SYMBOL_GPL(fscrypt_ioctl_add_key); -/* - * Add the key for '-o test_dummy_encryption' to the filesystem keyring. - * - * Use a per-boot random key to prevent people from misusing this option. - */ -int fscrypt_add_test_dummy_key(struct super_block *sb, - struct fscrypt_key_specifier *key_spec) +static void +fscrypt_get_test_dummy_secret(struct fscrypt_master_key_secret *secret) { static u8 test_key[FSCRYPT_MAX_KEY_SIZE]; + + get_random_once(test_key, FSCRYPT_MAX_KEY_SIZE); + + memset(secret, 0, sizeof(*secret)); + secret->size = FSCRYPT_MAX_KEY_SIZE; + memcpy(secret->raw, test_key, FSCRYPT_MAX_KEY_SIZE); +} + +int fscrypt_get_test_dummy_key_identifier( + u8 key_identifier[FSCRYPT_KEY_IDENTIFIER_SIZE]) +{ struct fscrypt_master_key_secret secret; int err; - get_random_once(test_key, FSCRYPT_MAX_KEY_SIZE); + fscrypt_get_test_dummy_secret(&secret); - memset(&secret, 0, sizeof(secret)); - secret.size = FSCRYPT_MAX_KEY_SIZE; - memcpy(secret.raw, test_key, FSCRYPT_MAX_KEY_SIZE); + err = fscrypt_init_hkdf(&secret.hkdf, secret.raw, secret.size); + if (err) + goto out; + err = fscrypt_hkdf_expand(&secret.hkdf, HKDF_CONTEXT_KEY_IDENTIFIER, + NULL, 0, key_identifier, + FSCRYPT_KEY_IDENTIFIER_SIZE); +out: + wipe_master_key_secret(&secret); + return err; +} + +/** + * fscrypt_add_test_dummy_key() - add the test dummy encryption key + * @sb: the filesystem instance to add the key to + * @dummy_policy: the encryption policy for test_dummy_encryption + * + * If needed, add the key for the test_dummy_encryption mount option to the + * filesystem. To prevent misuse of this mount option, a per-boot random key is + * used instead of a hardcoded one. This makes it so that any encrypted files + * created using this option won't be accessible after a reboot. + * + * Return: 0 on success, -errno on failure + */ +int fscrypt_add_test_dummy_key(struct super_block *sb, + const struct fscrypt_dummy_policy *dummy_policy) +{ + const union fscrypt_policy *policy = dummy_policy->policy; + struct fscrypt_key_specifier key_spec; + struct fscrypt_master_key_secret secret; + int err; - err = add_master_key(sb, &secret, key_spec); + if (!policy) + return 0; + err = fscrypt_policy_to_key_spec(policy, &key_spec); + if (err) + return err; + fscrypt_get_test_dummy_secret(&secret); + err = add_master_key(sb, &secret, &key_spec); wipe_master_key_secret(&secret); return err; } +EXPORT_SYMBOL_GPL(fscrypt_add_test_dummy_key); /* * Verify that the current user has added a master key with the given identifier diff --git a/fs/crypto/keysetup.c b/fs/crypto/keysetup.c index eede186b04ce..c35711896bd4 100644 --- a/fs/crypto/keysetup.c +++ b/fs/crypto/keysetup.c @@ -94,7 +94,7 @@ fscrypt_allocate_skcipher(struct fscrypt_mode *mode, const u8 *raw_key, mode->cipher_str, PTR_ERR(tfm)); return tfm; } - if (!xchg(&mode->logged_impl_name, 1)) { + if (!xchg(&mode->logged_cryptoapi_impl, 1)) { /* * fscrypt performance can vary greatly depending on which * crypto algorithm implementation is used. Help people debug @@ -425,23 +425,9 @@ static int setup_file_encryption_key(struct fscrypt_info *ci, if (err) return err; - switch (ci->ci_policy.version) { - case FSCRYPT_POLICY_V1: - mk_spec.type = FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR; - memcpy(mk_spec.u.descriptor, - ci->ci_policy.v1.master_key_descriptor, - FSCRYPT_KEY_DESCRIPTOR_SIZE); - break; - case FSCRYPT_POLICY_V2: - mk_spec.type = FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER; - memcpy(mk_spec.u.identifier, - ci->ci_policy.v2.master_key_identifier, - FSCRYPT_KEY_IDENTIFIER_SIZE); - break; - default: - WARN_ON(1); - return -EINVAL; - } + err = fscrypt_policy_to_key_spec(&ci->ci_policy, &mk_spec); + if (err) + return err; key = fscrypt_find_master_key(ci->ci_inode->i_sb, &mk_spec); if (IS_ERR(key)) { diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c index ed3d623724cd..5f858cee1e3b 100644 --- a/fs/crypto/policy.c +++ b/fs/crypto/policy.c @@ -10,6 +10,7 @@ * Modified by Eric Biggers, 2019 for v2 policy support. */ +#include <linux/fs_context.h> #include <linux/random.h> #include <linux/seq_file.h> #include <linux/string.h> @@ -32,6 +33,26 @@ bool fscrypt_policies_equal(const union fscrypt_policy *policy1, return !memcmp(policy1, policy2, fscrypt_policy_size(policy1)); } +int fscrypt_policy_to_key_spec(const union fscrypt_policy *policy, + struct fscrypt_key_specifier *key_spec) +{ + switch (policy->version) { + case FSCRYPT_POLICY_V1: + key_spec->type = FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR; + memcpy(key_spec->u.descriptor, policy->v1.master_key_descriptor, + FSCRYPT_KEY_DESCRIPTOR_SIZE); + return 0; + case FSCRYPT_POLICY_V2: + key_spec->type = FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER; + memcpy(key_spec->u.identifier, policy->v2.master_key_identifier, + FSCRYPT_KEY_IDENTIFIER_SIZE); + return 0; + default: + WARN_ON(1); + return -EINVAL; + } +} + static const union fscrypt_policy * fscrypt_get_dummy_policy(struct super_block *sb) { @@ -704,73 +725,45 @@ int fscrypt_set_context(struct inode *inode, void *fs_data) EXPORT_SYMBOL_GPL(fscrypt_set_context); /** - * fscrypt_set_test_dummy_encryption() - handle '-o test_dummy_encryption' - * @sb: the filesystem on which test_dummy_encryption is being specified - * @arg: the argument to the test_dummy_encryption option. May be NULL. - * @dummy_policy: the filesystem's current dummy policy (input/output, see - * below) - * - * Handle the test_dummy_encryption mount option by creating a dummy encryption - * policy, saving it in @dummy_policy, and adding the corresponding dummy - * encryption key to the filesystem. If the @dummy_policy is already set, then - * instead validate that it matches @arg. Don't support changing it via - * remount, as that is difficult to do safely. + * fscrypt_parse_test_dummy_encryption() - parse the test_dummy_encryption mount option + * @param: the mount option + * @dummy_policy: (input/output) the place to write the dummy policy that will + * result from parsing the option. Zero-initialize this. If a policy is + * already set here (due to test_dummy_encryption being given multiple + * times), then this function will verify that the policies are the same. * - * Return: 0 on success (dummy policy set, or the same policy is already set); - * -EEXIST if a different dummy policy is already set; - * or another -errno value. + * Return: 0 on success; -EINVAL if the argument is invalid; -EEXIST if the + * argument conflicts with one already specified; or -ENOMEM. */ -int fscrypt_set_test_dummy_encryption(struct super_block *sb, const char *arg, - struct fscrypt_dummy_policy *dummy_policy) +int fscrypt_parse_test_dummy_encryption(const struct fs_parameter *param, + struct fscrypt_dummy_policy *dummy_policy) { - struct fscrypt_key_specifier key_spec = { 0 }; - int version; - union fscrypt_policy *policy = NULL; + const char *arg = "v2"; + union fscrypt_policy *policy; int err; - if (!arg) - arg = "v2"; - - if (!strcmp(arg, "v1")) { - version = FSCRYPT_POLICY_V1; - key_spec.type = FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR; - memset(key_spec.u.descriptor, 0x42, - FSCRYPT_KEY_DESCRIPTOR_SIZE); - } else if (!strcmp(arg, "v2")) { - version = FSCRYPT_POLICY_V2; - key_spec.type = FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER; - /* key_spec.u.identifier gets filled in when adding the key */ - } else { - err = -EINVAL; - goto out; - } + if (param->type == fs_value_is_string && *param->string) + arg = param->string; policy = kzalloc(sizeof(*policy), GFP_KERNEL); - if (!policy) { - err = -ENOMEM; - goto out; - } - - err = fscrypt_add_test_dummy_key(sb, &key_spec); - if (err) - goto out; + if (!policy) + return -ENOMEM; - policy->version = version; - switch (policy->version) { - case FSCRYPT_POLICY_V1: + if (!strcmp(arg, "v1")) { + policy->version = FSCRYPT_POLICY_V1; policy->v1.contents_encryption_mode = FSCRYPT_MODE_AES_256_XTS; policy->v1.filenames_encryption_mode = FSCRYPT_MODE_AES_256_CTS; - memcpy(policy->v1.master_key_descriptor, key_spec.u.descriptor, + memset(policy->v1.master_key_descriptor, 0x42, FSCRYPT_KEY_DESCRIPTOR_SIZE); - break; - case FSCRYPT_POLICY_V2: + } else if (!strcmp(arg, "v2")) { + policy->version = FSCRYPT_POLICY_V2; policy->v2.contents_encryption_mode = FSCRYPT_MODE_AES_256_XTS; policy->v2.filenames_encryption_mode = FSCRYPT_MODE_AES_256_CTS; - memcpy(policy->v2.master_key_identifier, key_spec.u.identifier, - FSCRYPT_KEY_IDENTIFIER_SIZE); - break; - default: - WARN_ON(1); + err = fscrypt_get_test_dummy_key_identifier( + policy->v2.master_key_identifier); + if (err) + goto out; + } else { err = -EINVAL; goto out; } @@ -789,6 +782,37 @@ out: kfree(policy); return err; } +EXPORT_SYMBOL_GPL(fscrypt_parse_test_dummy_encryption); + +/** + * fscrypt_dummy_policies_equal() - check whether two dummy policies are equal + * @p1: the first test dummy policy (may be unset) + * @p2: the second test dummy policy (may be unset) + * + * Return: %true if the dummy policies are both set and equal, or both unset. + */ +bool fscrypt_dummy_policies_equal(const struct fscrypt_dummy_policy *p1, + const struct fscrypt_dummy_policy *p2) +{ + if (!p1->policy && !p2->policy) + return true; + if (!p1->policy || !p2->policy) + return false; + return fscrypt_policies_equal(p1->policy, p2->policy); +} +EXPORT_SYMBOL_GPL(fscrypt_dummy_policies_equal); + +/* Deprecated, do not use */ +int fscrypt_set_test_dummy_encryption(struct super_block *sb, const char *arg, + struct fscrypt_dummy_policy *dummy_policy) +{ + struct fs_parameter param = { + .type = fs_value_is_string, + .string = arg ? (char *)arg : "", + }; + return fscrypt_parse_test_dummy_encryption(¶m, dummy_policy) ?: + fscrypt_add_test_dummy_key(sb, dummy_policy); +} EXPORT_SYMBOL_GPL(fscrypt_set_test_dummy_encryption); /** diff --git a/fs/direct-io.c b/fs/direct-io.c index aef06e607b40..840752006f60 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -1115,11 +1115,10 @@ static inline int drop_refcount(struct dio *dio) * individual fields and will generate much worse code. This is important * for the whole file. */ -static inline ssize_t -do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, - struct block_device *bdev, struct iov_iter *iter, - get_block_t get_block, dio_iodone_t end_io, - dio_submit_t submit_io, int flags) +ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, + struct block_device *bdev, struct iov_iter *iter, + get_block_t get_block, dio_iodone_t end_io, + dio_submit_t submit_io, int flags) { unsigned i_blkbits = READ_ONCE(inode->i_blkbits); unsigned blkbits = i_blkbits; @@ -1334,29 +1333,6 @@ fail_dio: kmem_cache_free(dio_cache, dio); return retval; } - -ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, - struct block_device *bdev, struct iov_iter *iter, - get_block_t get_block, - dio_iodone_t end_io, dio_submit_t submit_io, - int flags) -{ - /* - * The block device state is needed in the end to finally - * submit everything. Since it's likely to be cache cold - * prefetch it here as first thing to hide some of the - * latency. - * - * Attempt to prefetch the pieces we likely need later. - */ - prefetch(&bdev->bd_disk->part_tbl); - prefetch(bdev->bd_disk->queue); - prefetch((char *)bdev->bd_disk->queue + SMP_CACHE_BYTES); - - return do_blockdev_direct_IO(iocb, inode, bdev, iter, get_block, - end_io, submit_io, flags); -} - EXPORT_SYMBOL(__blockdev_direct_IO); static __init int dio_init(void) diff --git a/fs/dlm/dir.c b/fs/dlm/dir.c index b6692f81ec83..fb1981654bb2 100644 --- a/fs/dlm/dir.c +++ b/fs/dlm/dir.c @@ -101,7 +101,7 @@ int dlm_recover_directory(struct dlm_ls *ls) */ b = ls->ls_recover_buf->rc_buf; - left = ls->ls_recover_buf->rc_header.h_length; + left = le16_to_cpu(ls->ls_recover_buf->rc_header.h_length); left -= sizeof(struct dlm_rcom); for (;;) { diff --git a/fs/dlm/dlm_internal.h b/fs/dlm/dlm_internal.h index 74a9590a4dd5..776c3ed519f0 100644 --- a/fs/dlm/dlm_internal.h +++ b/fs/dlm/dlm_internal.h @@ -379,15 +379,15 @@ static inline int rsb_flag(struct dlm_rsb *r, enum rsb_flags flag) #define DLM_FIN 5 struct dlm_header { - uint32_t h_version; + __le32 h_version; union { /* for DLM_MSG and DLM_RCOM */ - uint32_t h_lockspace; + __le32 h_lockspace; /* for DLM_ACK and DLM_OPTS */ - uint32_t h_seq; + __le32 h_seq; } u; - uint32_t h_nodeid; /* nodeid of sender */ - uint16_t h_length; + __le32 h_nodeid; /* nodeid of sender */ + __le16 h_length; uint8_t h_cmd; /* DLM_MSG, DLM_RCOM */ uint8_t h_pad; }; @@ -409,24 +409,24 @@ struct dlm_header { struct dlm_message { struct dlm_header m_header; - uint32_t m_type; /* DLM_MSG_ */ - uint32_t m_nodeid; - uint32_t m_pid; - uint32_t m_lkid; /* lkid on sender */ - uint32_t m_remid; /* lkid on receiver */ - uint32_t m_parent_lkid; - uint32_t m_parent_remid; - uint32_t m_exflags; - uint32_t m_sbflags; - uint32_t m_flags; - uint32_t m_lvbseq; - uint32_t m_hash; - int m_status; - int m_grmode; - int m_rqmode; - int m_bastmode; - int m_asts; - int m_result; /* 0 or -EXXX */ + __le32 m_type; /* DLM_MSG_ */ + __le32 m_nodeid; + __le32 m_pid; + __le32 m_lkid; /* lkid on sender */ + __le32 m_remid; /* lkid on receiver */ + __le32 m_parent_lkid; + __le32 m_parent_remid; + __le32 m_exflags; + __le32 m_sbflags; + __le32 m_flags; + __le32 m_lvbseq; + __le32 m_hash; + __le32 m_status; + __le32 m_grmode; + __le32 m_rqmode; + __le32 m_bastmode; + __le32 m_asts; + __le32 m_result; /* 0 or -EXXX */ char m_extra[]; /* name or lvb */ }; @@ -451,18 +451,18 @@ struct dlm_message { struct dlm_rcom { struct dlm_header rc_header; - uint32_t rc_type; /* DLM_RCOM_ */ - int rc_result; /* multi-purpose */ - uint64_t rc_id; /* match reply with request */ - uint64_t rc_seq; /* sender's ls_recover_seq */ - uint64_t rc_seq_reply; /* remote ls_recover_seq */ + __le32 rc_type; /* DLM_RCOM_ */ + __le32 rc_result; /* multi-purpose */ + __le64 rc_id; /* match reply with request */ + __le64 rc_seq; /* sender's ls_recover_seq */ + __le64 rc_seq_reply; /* remote ls_recover_seq */ char rc_buf[]; }; struct dlm_opt_header { - uint16_t t_type; - uint16_t t_length; - uint32_t t_pad; + __le16 t_type; + __le16 t_length; + __le32 t_pad; /* need to be 8 byte aligned */ char t_value[]; }; @@ -472,8 +472,8 @@ struct dlm_opts { struct dlm_header o_header; uint8_t o_nextcmd; uint8_t o_pad; - uint16_t o_optlen; - uint32_t o_pad2; + __le16 o_optlen; + __le32 o_pad2; char o_opts[]; }; diff --git a/fs/dlm/lock.c b/fs/dlm/lock.c index bdb51d209ba2..226822f49d30 100644 --- a/fs/dlm/lock.c +++ b/fs/dlm/lock.c @@ -350,10 +350,12 @@ static void put_rsb(struct dlm_rsb *r) { struct dlm_ls *ls = r->res_ls; uint32_t bucket = r->res_bucket; + int rv; - spin_lock(&ls->ls_rsbtbl[bucket].lock); - kref_put(&r->res_ref, toss_rsb); - spin_unlock(&ls->ls_rsbtbl[bucket].lock); + rv = kref_put_lock(&r->res_ref, toss_rsb, + &ls->ls_rsbtbl[bucket].lock); + if (rv) + spin_unlock(&ls->ls_rsbtbl[bucket].lock); } void dlm_put_rsb(struct dlm_rsb *r) @@ -602,7 +604,6 @@ static int find_rsb_dir(struct dlm_ls *ls, char *name, int len, */ kref_get(&r->res_ref); - error = 0; goto out_unlock; @@ -880,6 +881,88 @@ static int validate_master_nodeid(struct dlm_ls *ls, struct dlm_rsb *r, } } +static void __dlm_master_lookup(struct dlm_ls *ls, struct dlm_rsb *r, int our_nodeid, + int from_nodeid, bool toss_list, unsigned int flags, + int *r_nodeid, int *result) +{ + int fix_master = (flags & DLM_LU_RECOVER_MASTER); + int from_master = (flags & DLM_LU_RECOVER_DIR); + + if (r->res_dir_nodeid != our_nodeid) { + /* should not happen, but may as well fix it and carry on */ + log_error(ls, "%s res_dir %d our %d %s", __func__, + r->res_dir_nodeid, our_nodeid, r->res_name); + r->res_dir_nodeid = our_nodeid; + } + + if (fix_master && dlm_is_removed(ls, r->res_master_nodeid)) { + /* Recovery uses this function to set a new master when + * the previous master failed. Setting NEW_MASTER will + * force dlm_recover_masters to call recover_master on this + * rsb even though the res_nodeid is no longer removed. + */ + + r->res_master_nodeid = from_nodeid; + r->res_nodeid = from_nodeid; + rsb_set_flag(r, RSB_NEW_MASTER); + + if (toss_list) { + /* I don't think we should ever find it on toss list. */ + log_error(ls, "%s fix_master on toss", __func__); + dlm_dump_rsb(r); + } + } + + if (from_master && (r->res_master_nodeid != from_nodeid)) { + /* this will happen if from_nodeid became master during + * a previous recovery cycle, and we aborted the previous + * cycle before recovering this master value + */ + + log_limit(ls, "%s from_master %d master_nodeid %d res_nodeid %d first %x %s", + __func__, from_nodeid, r->res_master_nodeid, + r->res_nodeid, r->res_first_lkid, r->res_name); + + if (r->res_master_nodeid == our_nodeid) { + log_error(ls, "from_master %d our_master", from_nodeid); + dlm_dump_rsb(r); + goto ret_assign; + } + + r->res_master_nodeid = from_nodeid; + r->res_nodeid = from_nodeid; + rsb_set_flag(r, RSB_NEW_MASTER); + } + + if (!r->res_master_nodeid) { + /* this will happen if recovery happens while we're looking + * up the master for this rsb + */ + + log_debug(ls, "%s master 0 to %d first %x %s", __func__, + from_nodeid, r->res_first_lkid, r->res_name); + r->res_master_nodeid = from_nodeid; + r->res_nodeid = from_nodeid; + } + + if (!from_master && !fix_master && + (r->res_master_nodeid == from_nodeid)) { + /* this can happen when the master sends remove, the dir node + * finds the rsb on the keep list and ignores the remove, + * and the former master sends a lookup + */ + + log_limit(ls, "%s from master %d flags %x first %x %s", + __func__, from_nodeid, flags, r->res_first_lkid, + r->res_name); + } + + ret_assign: + *r_nodeid = r->res_master_nodeid; + if (result) + *result = DLM_LU_MATCH; +} + /* * We're the dir node for this res and another node wants to know the * master nodeid. During normal operation (non recovery) this is only @@ -914,10 +997,8 @@ int dlm_master_lookup(struct dlm_ls *ls, int from_nodeid, char *name, int len, { struct dlm_rsb *r = NULL; uint32_t hash, b; - int from_master = (flags & DLM_LU_RECOVER_DIR); - int fix_master = (flags & DLM_LU_RECOVER_MASTER); int our_nodeid = dlm_our_nodeid(); - int dir_nodeid, error, toss_list = 0; + int dir_nodeid, error; if (len > DLM_RESNAME_MAXLEN) return -EINVAL; @@ -949,12 +1030,21 @@ int dlm_master_lookup(struct dlm_ls *ls, int from_nodeid, char *name, int len, error = dlm_search_rsb_tree(&ls->ls_rsbtbl[b].keep, name, len, &r); if (!error) { /* because the rsb is active, we need to lock_rsb before - checking/changing re_master_nodeid */ + * checking/changing re_master_nodeid + */ hold_rsb(r); spin_unlock(&ls->ls_rsbtbl[b].lock); lock_rsb(r); - goto found; + + __dlm_master_lookup(ls, r, our_nodeid, from_nodeid, false, + flags, r_nodeid, result); + + /* the rsb was active */ + unlock_rsb(r); + put_rsb(r); + + return 0; } error = dlm_search_rsb_tree(&ls->ls_rsbtbl[b].toss, name, len, &r); @@ -962,90 +1052,16 @@ int dlm_master_lookup(struct dlm_ls *ls, int from_nodeid, char *name, int len, goto not_found; /* because the rsb is inactive (on toss list), it's not refcounted - and lock_rsb is not used, but is protected by the rsbtbl lock */ - - toss_list = 1; - found: - if (r->res_dir_nodeid != our_nodeid) { - /* should not happen, but may as well fix it and carry on */ - log_error(ls, "dlm_master_lookup res_dir %d our %d %s", - r->res_dir_nodeid, our_nodeid, r->res_name); - r->res_dir_nodeid = our_nodeid; - } - - if (fix_master && dlm_is_removed(ls, r->res_master_nodeid)) { - /* Recovery uses this function to set a new master when - the previous master failed. Setting NEW_MASTER will - force dlm_recover_masters to call recover_master on this - rsb even though the res_nodeid is no longer removed. */ - - r->res_master_nodeid = from_nodeid; - r->res_nodeid = from_nodeid; - rsb_set_flag(r, RSB_NEW_MASTER); - - if (toss_list) { - /* I don't think we should ever find it on toss list. */ - log_error(ls, "dlm_master_lookup fix_master on toss"); - dlm_dump_rsb(r); - } - } - - if (from_master && (r->res_master_nodeid != from_nodeid)) { - /* this will happen if from_nodeid became master during - a previous recovery cycle, and we aborted the previous - cycle before recovering this master value */ - - log_limit(ls, "dlm_master_lookup from_master %d " - "master_nodeid %d res_nodeid %d first %x %s", - from_nodeid, r->res_master_nodeid, r->res_nodeid, - r->res_first_lkid, r->res_name); - - if (r->res_master_nodeid == our_nodeid) { - log_error(ls, "from_master %d our_master", from_nodeid); - dlm_dump_rsb(r); - goto out_found; - } - - r->res_master_nodeid = from_nodeid; - r->res_nodeid = from_nodeid; - rsb_set_flag(r, RSB_NEW_MASTER); - } - - if (!r->res_master_nodeid) { - /* this will happen if recovery happens while we're looking - up the master for this rsb */ - - log_debug(ls, "dlm_master_lookup master 0 to %d first %x %s", - from_nodeid, r->res_first_lkid, r->res_name); - r->res_master_nodeid = from_nodeid; - r->res_nodeid = from_nodeid; - } - - if (!from_master && !fix_master && - (r->res_master_nodeid == from_nodeid)) { - /* this can happen when the master sends remove, the dir node - finds the rsb on the keep list and ignores the remove, - and the former master sends a lookup */ + * and lock_rsb is not used, but is protected by the rsbtbl lock + */ - log_limit(ls, "dlm_master_lookup from master %d flags %x " - "first %x %s", from_nodeid, flags, - r->res_first_lkid, r->res_name); - } + __dlm_master_lookup(ls, r, our_nodeid, from_nodeid, true, flags, + r_nodeid, result); - out_found: - *r_nodeid = r->res_master_nodeid; - if (result) - *result = DLM_LU_MATCH; + r->res_toss_time = jiffies; + /* the rsb was inactive (on toss list) */ + spin_unlock(&ls->ls_rsbtbl[b].lock); - if (toss_list) { - r->res_toss_time = jiffies; - /* the rsb was inactive (on toss list) */ - spin_unlock(&ls->ls_rsbtbl[b].lock); - } else { - /* the rsb was active */ - unlock_rsb(r); - put_rsb(r); - } return 0; not_found: @@ -1076,7 +1092,6 @@ int dlm_master_lookup(struct dlm_ls *ls, int from_nodeid, char *name, int len, if (result) *result = DLM_LU_ADD; *r_nodeid = from_nodeid; - error = 0; out_unlock: spin_unlock(&ls->ls_rsbtbl[b].lock); return error; @@ -1253,9 +1268,11 @@ static void kill_lkb(struct kref *kref) static int __put_lkb(struct dlm_ls *ls, struct dlm_lkb *lkb) { uint32_t lkid = lkb->lkb_id; + int rv; - spin_lock(&ls->ls_lkbidr_spin); - if (kref_put(&lkb->lkb_ref, kill_lkb)) { + rv = kref_put_lock(&lkb->lkb_ref, kill_lkb, + &ls->ls_lkbidr_spin); + if (rv) { idr_remove(&ls->ls_lkbidr, lkid); spin_unlock(&ls->ls_lkbidr_spin); @@ -1265,11 +1282,9 @@ static int __put_lkb(struct dlm_ls *ls, struct dlm_lkb *lkb) if (lkb->lkb_lvbptr && is_master_copy(lkb)) dlm_free_lvb(lkb->lkb_lvbptr); dlm_free_lkb(lkb); - return 1; - } else { - spin_unlock(&ls->ls_lkbidr_spin); - return 0; } + + return rv; } int dlm_put_lkb(struct dlm_lkb *lkb) @@ -1306,13 +1321,17 @@ static inline void unhold_lkb(struct dlm_lkb *lkb) static void lkb_add_ordered(struct list_head *new, struct list_head *head, int mode) { - struct dlm_lkb *lkb = NULL; + struct dlm_lkb *lkb = NULL, *iter; - list_for_each_entry(lkb, head, lkb_statequeue) - if (lkb->lkb_rqmode < mode) + list_for_each_entry(iter, head, lkb_statequeue) + if (iter->lkb_rqmode < mode) { + lkb = iter; + list_add_tail(new, &iter->lkb_statequeue); break; + } - __list_add(new, lkb->lkb_statequeue.prev, &lkb->lkb_statequeue); + if (!lkb) + list_add_tail(new, head); } /* add/remove lkb to rsb's grant/convert/wait queue */ @@ -1559,6 +1578,7 @@ static int _remove_from_waiters(struct dlm_lkb *lkb, int mstype, lkb->lkb_wait_type = 0; lkb->lkb_flags &= ~DLM_IFL_OVERLAP_CANCEL; lkb->lkb_wait_count--; + unhold_lkb(lkb); goto out_del; } @@ -1571,8 +1591,8 @@ static int _remove_from_waiters(struct dlm_lkb *lkb, int mstype, } log_error(ls, "remwait error %x remote %d %x msg %d flags %x no wait", - lkb->lkb_id, ms ? ms->m_header.h_nodeid : 0, lkb->lkb_remid, - mstype, lkb->lkb_flags); + lkb->lkb_id, ms ? le32_to_cpu(ms->m_header.h_nodeid) : 0, + lkb->lkb_remid, mstype, lkb->lkb_flags); return -1; out_del: @@ -1585,6 +1605,7 @@ static int _remove_from_waiters(struct dlm_lkb *lkb, int mstype, log_error(ls, "remwait error %x reply %d wait_type %d overlap", lkb->lkb_id, mstype, lkb->lkb_wait_type); lkb->lkb_wait_count--; + unhold_lkb(lkb); lkb->lkb_wait_type = 0; } @@ -1617,10 +1638,10 @@ static int remove_from_waiters_ms(struct dlm_lkb *lkb, struct dlm_message *ms) struct dlm_ls *ls = lkb->lkb_resource->res_ls; int error; - if (ms->m_flags != DLM_IFL_STUB_MS) + if (ms->m_flags != cpu_to_le32(DLM_IFL_STUB_MS)) mutex_lock(&ls->ls_waiters_mutex); - error = _remove_from_waiters(lkb, ms->m_type, ms); - if (ms->m_flags != DLM_IFL_STUB_MS) + error = _remove_from_waiters(lkb, le32_to_cpu(ms->m_type), ms); + if (ms->m_flags != cpu_to_le32(DLM_IFL_STUB_MS)) mutex_unlock(&ls->ls_waiters_mutex); return error; } @@ -1795,7 +1816,6 @@ static void shrink_bucket(struct dlm_ls *ls, int b) memcpy(ls->ls_remove_name, name, DLM_RESNAME_MAXLEN); spin_unlock(&ls->ls_remove_spin); spin_unlock(&ls->ls_rsbtbl[b].lock); - wake_up(&ls->ls_remove_wait); send_remove(r); @@ -1804,6 +1824,7 @@ static void shrink_bucket(struct dlm_ls *ls, int b) ls->ls_remove_len = 0; memset(ls->ls_remove_name, 0, DLM_RESNAME_MAXLEN); spin_unlock(&ls->ls_remove_spin); + wake_up(&ls->ls_remove_wait); dlm_free_rsb(r); } @@ -1866,7 +1887,7 @@ static void del_timeout(struct dlm_lkb *lkb) void dlm_scan_timeout(struct dlm_ls *ls) { struct dlm_rsb *r; - struct dlm_lkb *lkb; + struct dlm_lkb *lkb = NULL, *iter; int do_cancel, do_warn; s64 wait_us; @@ -1877,27 +1898,28 @@ void dlm_scan_timeout(struct dlm_ls *ls) do_cancel = 0; do_warn = 0; mutex_lock(&ls->ls_timeout_mutex); - list_for_each_entry(lkb, &ls->ls_timeout, lkb_time_list) { + list_for_each_entry(iter, &ls->ls_timeout, lkb_time_list) { wait_us = ktime_to_us(ktime_sub(ktime_get(), - lkb->lkb_timestamp)); + iter->lkb_timestamp)); - if ((lkb->lkb_exflags & DLM_LKF_TIMEOUT) && - wait_us >= (lkb->lkb_timeout_cs * 10000)) + if ((iter->lkb_exflags & DLM_LKF_TIMEOUT) && + wait_us >= (iter->lkb_timeout_cs * 10000)) do_cancel = 1; - if ((lkb->lkb_flags & DLM_IFL_WATCH_TIMEWARN) && + if ((iter->lkb_flags & DLM_IFL_WATCH_TIMEWARN) && wait_us >= dlm_config.ci_timewarn_cs * 10000) do_warn = 1; if (!do_cancel && !do_warn) continue; - hold_lkb(lkb); + hold_lkb(iter); + lkb = iter; break; } mutex_unlock(&ls->ls_timeout_mutex); - if (!do_cancel && !do_warn) + if (!lkb) break; r = lkb->lkb_resource; @@ -2051,7 +2073,7 @@ static void set_lvb_lock_pc(struct dlm_rsb *r, struct dlm_lkb *lkb, if (len > r->res_ls->ls_lvblen) len = r->res_ls->ls_lvblen; memcpy(lkb->lkb_lvbptr, ms->m_extra, len); - lkb->lkb_lvbseq = ms->m_lvbseq; + lkb->lkb_lvbseq = le32_to_cpu(ms->m_lvbseq); } } @@ -2182,10 +2204,10 @@ static void munge_demoted(struct dlm_lkb *lkb) static void munge_altmode(struct dlm_lkb *lkb, struct dlm_message *ms) { - if (ms->m_type != DLM_MSG_REQUEST_REPLY && - ms->m_type != DLM_MSG_GRANT) { + if (ms->m_type != cpu_to_le32(DLM_MSG_REQUEST_REPLY) && + ms->m_type != cpu_to_le32(DLM_MSG_GRANT)) { log_print("munge_altmode %x invalid reply type %d", - lkb->lkb_id, ms->m_type); + lkb->lkb_id, le32_to_cpu(ms->m_type)); return; } @@ -2912,7 +2934,8 @@ static int validate_lock_args(struct dlm_ls *ls, struct dlm_lkb *lkb, if (lkb->lkb_status != DLM_LKSTS_GRANTED) goto out; - if (lkb->lkb_wait_type) + /* lock not allowed if there's any op in progress */ + if (lkb->lkb_wait_type || lkb->lkb_wait_count) goto out; if (is_overlap(lkb)) @@ -3563,13 +3586,13 @@ static int _create_message(struct dlm_ls *ls, int mb_len, ms = (struct dlm_message *) mb; - ms->m_header.h_version = (DLM_HEADER_MAJOR | DLM_HEADER_MINOR); - ms->m_header.u.h_lockspace = ls->ls_global_id; - ms->m_header.h_nodeid = dlm_our_nodeid(); - ms->m_header.h_length = mb_len; + ms->m_header.h_version = cpu_to_le32(DLM_HEADER_MAJOR | DLM_HEADER_MINOR); + ms->m_header.u.h_lockspace = cpu_to_le32(ls->ls_global_id); + ms->m_header.h_nodeid = cpu_to_le32(dlm_our_nodeid()); + ms->m_header.h_length = cpu_to_le16(mb_len); ms->m_header.h_cmd = DLM_MSG; - ms->m_type = mstype; + ms->m_type = cpu_to_le32(mstype); *mh_ret = mh; *ms_ret = ms; @@ -3608,7 +3631,6 @@ static int create_message(struct dlm_rsb *r, struct dlm_lkb *lkb, static int send_message(struct dlm_mhandle *mh, struct dlm_message *ms) { - dlm_message_out(ms); dlm_midcomms_commit_mhandle(mh); return 0; } @@ -3616,40 +3638,40 @@ static int send_message(struct dlm_mhandle *mh, struct dlm_message *ms) static void send_args(struct dlm_rsb *r, struct dlm_lkb *lkb, struct dlm_message *ms) { - ms->m_nodeid = lkb->lkb_nodeid; - ms->m_pid = lkb->lkb_ownpid; - ms->m_lkid = lkb->lkb_id; - ms->m_remid = lkb->lkb_remid; - ms->m_exflags = lkb->lkb_exflags; - ms->m_sbflags = lkb->lkb_sbflags; - ms->m_flags = lkb->lkb_flags; - ms->m_lvbseq = lkb->lkb_lvbseq; - ms->m_status = lkb->lkb_status; - ms->m_grmode = lkb->lkb_grmode; - ms->m_rqmode = lkb->lkb_rqmode; - ms->m_hash = r->res_hash; + ms->m_nodeid = cpu_to_le32(lkb->lkb_nodeid); + ms->m_pid = cpu_to_le32(lkb->lkb_ownpid); + ms->m_lkid = cpu_to_le32(lkb->lkb_id); + ms->m_remid = cpu_to_le32(lkb->lkb_remid); + ms->m_exflags = cpu_to_le32(lkb->lkb_exflags); + ms->m_sbflags = cpu_to_le32(lkb->lkb_sbflags); + ms->m_flags = cpu_to_le32(lkb->lkb_flags); + ms->m_lvbseq = cpu_to_le32(lkb->lkb_lvbseq); + ms->m_status = cpu_to_le32(lkb->lkb_status); + ms->m_grmode = cpu_to_le32(lkb->lkb_grmode); + ms->m_rqmode = cpu_to_le32(lkb->lkb_rqmode); + ms->m_hash = cpu_to_le32(r->res_hash); /* m_result and m_bastmode are set from function args, not from lkb fields */ if (lkb->lkb_bastfn) - ms->m_asts |= DLM_CB_BAST; + ms->m_asts |= cpu_to_le32(DLM_CB_BAST); if (lkb->lkb_astfn) - ms->m_asts |= DLM_CB_CAST; + ms->m_asts |= cpu_to_le32(DLM_CB_CAST); /* compare with switch in create_message; send_remove() doesn't use send_args() */ switch (ms->m_type) { - case DLM_MSG_REQUEST: - case DLM_MSG_LOOKUP: + case cpu_to_le32(DLM_MSG_REQUEST): + case cpu_to_le32(DLM_MSG_LOOKUP): memcpy(ms->m_extra, r->res_name, r->res_length); break; - case DLM_MSG_CONVERT: - case DLM_MSG_UNLOCK: - case DLM_MSG_REQUEST_REPLY: - case DLM_MSG_CONVERT_REPLY: - case DLM_MSG_GRANT: + case cpu_to_le32(DLM_MSG_CONVERT): + case cpu_to_le32(DLM_MSG_UNLOCK): + case cpu_to_le32(DLM_MSG_REQUEST_REPLY): + case cpu_to_le32(DLM_MSG_CONVERT_REPLY): + case cpu_to_le32(DLM_MSG_GRANT): if (!lkb->lkb_lvbptr) break; memcpy(ms->m_extra, lkb->lkb_lvbptr, r->res_ls->ls_lvblen); @@ -3699,8 +3721,8 @@ static int send_convert(struct dlm_rsb *r, struct dlm_lkb *lkb) /* down conversions go without a reply from the master */ if (!error && down_conversion(lkb)) { remove_from_waiters(lkb, DLM_MSG_CONVERT_REPLY); - r->res_ls->ls_stub_ms.m_flags = DLM_IFL_STUB_MS; - r->res_ls->ls_stub_ms.m_type = DLM_MSG_CONVERT_REPLY; + r->res_ls->ls_stub_ms.m_flags = cpu_to_le32(DLM_IFL_STUB_MS); + r->res_ls->ls_stub_ms.m_type = cpu_to_le32(DLM_MSG_CONVERT_REPLY); r->res_ls->ls_stub_ms.m_result = 0; __receive_convert_reply(r, lkb, &r->res_ls->ls_stub_ms); } @@ -3757,7 +3779,7 @@ static int send_bast(struct dlm_rsb *r, struct dlm_lkb *lkb, int mode) send_args(r, lkb, ms); - ms->m_bastmode = mode; + ms->m_bastmode = cpu_to_le32(mode); error = send_message(mh, ms); out: @@ -3805,7 +3827,7 @@ static int send_remove(struct dlm_rsb *r) goto out; memcpy(ms->m_extra, r->res_name, r->res_length); - ms->m_hash = r->res_hash; + ms->m_hash = cpu_to_le32(r->res_hash); error = send_message(mh, ms); out: @@ -3827,7 +3849,7 @@ static int send_common_reply(struct dlm_rsb *r, struct dlm_lkb *lkb, send_args(r, lkb, ms); - ms->m_result = rv; + ms->m_result = cpu_to_le32(to_dlm_errno(rv)); error = send_message(mh, ms); out: @@ -3860,15 +3882,15 @@ static int send_lookup_reply(struct dlm_ls *ls, struct dlm_message *ms_in, struct dlm_rsb *r = &ls->ls_stub_rsb; struct dlm_message *ms; struct dlm_mhandle *mh; - int error, nodeid = ms_in->m_header.h_nodeid; + int error, nodeid = le32_to_cpu(ms_in->m_header.h_nodeid); error = create_message(r, NULL, nodeid, DLM_MSG_LOOKUP_REPLY, &ms, &mh); if (error) goto out; ms->m_lkid = ms_in->m_lkid; - ms->m_result = rv; - ms->m_nodeid = ret_nodeid; + ms->m_result = cpu_to_le32(to_dlm_errno(rv)); + ms->m_nodeid = cpu_to_le32(ret_nodeid); error = send_message(mh, ms); out: @@ -3881,25 +3903,26 @@ static int send_lookup_reply(struct dlm_ls *ls, struct dlm_message *ms_in, static void receive_flags(struct dlm_lkb *lkb, struct dlm_message *ms) { - lkb->lkb_exflags = ms->m_exflags; - lkb->lkb_sbflags = ms->m_sbflags; + lkb->lkb_exflags = le32_to_cpu(ms->m_exflags); + lkb->lkb_sbflags = le32_to_cpu(ms->m_sbflags); lkb->lkb_flags = (lkb->lkb_flags & 0xFFFF0000) | - (ms->m_flags & 0x0000FFFF); + (le32_to_cpu(ms->m_flags) & 0x0000FFFF); } static void receive_flags_reply(struct dlm_lkb *lkb, struct dlm_message *ms) { - if (ms->m_flags == DLM_IFL_STUB_MS) + if (ms->m_flags == cpu_to_le32(DLM_IFL_STUB_MS)) return; - lkb->lkb_sbflags = ms->m_sbflags; + lkb->lkb_sbflags = le32_to_cpu(ms->m_sbflags); lkb->lkb_flags = (lkb->lkb_flags & 0xFFFF0000) | - (ms->m_flags & 0x0000FFFF); + (le32_to_cpu(ms->m_flags) & 0x0000FFFF); } static int receive_extralen(struct dlm_message *ms) { - return (ms->m_header.h_length - sizeof(struct dlm_message)); + return (le16_to_cpu(ms->m_header.h_length) - + sizeof(struct dlm_message)); } static int receive_lvb(struct dlm_ls *ls, struct dlm_lkb *lkb, @@ -3933,14 +3956,14 @@ static void fake_astfn(void *astparam) static int receive_request_args(struct dlm_ls *ls, struct dlm_lkb *lkb, struct dlm_message *ms) { - lkb->lkb_nodeid = ms->m_header.h_nodeid; - lkb->lkb_ownpid = ms->m_pid; - lkb->lkb_remid = ms->m_lkid; + lkb->lkb_nodeid = le32_to_cpu(ms->m_header.h_nodeid); + lkb->lkb_ownpid = le32_to_cpu(ms->m_pid); + lkb->lkb_remid = le32_to_cpu(ms->m_lkid); lkb->lkb_grmode = DLM_LOCK_IV; - lkb->lkb_rqmode = ms->m_rqmode; + lkb->lkb_rqmode = le32_to_cpu(ms->m_rqmode); - lkb->lkb_bastfn = (ms->m_asts & DLM_CB_BAST) ? &fake_bastfn : NULL; - lkb->lkb_astfn = (ms->m_asts & DLM_CB_CAST) ? &fake_astfn : NULL; + lkb->lkb_bastfn = (ms->m_asts & cpu_to_le32(DLM_CB_BAST)) ? &fake_bastfn : NULL; + lkb->lkb_astfn = (ms->m_asts & cpu_to_le32(DLM_CB_CAST)) ? &fake_astfn : NULL; if (lkb->lkb_exflags & DLM_LKF_VALBLK) { /* lkb was just created so there won't be an lvb yet */ @@ -3961,8 +3984,8 @@ static int receive_convert_args(struct dlm_ls *ls, struct dlm_lkb *lkb, if (receive_lvb(ls, lkb, ms)) return -ENOMEM; - lkb->lkb_rqmode = ms->m_rqmode; - lkb->lkb_lvbseq = ms->m_lvbseq; + lkb->lkb_rqmode = le32_to_cpu(ms->m_rqmode); + lkb->lkb_lvbseq = le32_to_cpu(ms->m_lvbseq); return 0; } @@ -3981,8 +4004,8 @@ static int receive_unlock_args(struct dlm_ls *ls, struct dlm_lkb *lkb, static void setup_stub_lkb(struct dlm_ls *ls, struct dlm_message *ms) { struct dlm_lkb *lkb = &ls->ls_stub_lkb; - lkb->lkb_nodeid = ms->m_header.h_nodeid; - lkb->lkb_remid = ms->m_lkid; + lkb->lkb_nodeid = le32_to_cpu(ms->m_header.h_nodeid); + lkb->lkb_remid = le32_to_cpu(ms->m_lkid); } /* This is called after the rsb is locked so that we can safely inspect @@ -3990,11 +4013,12 @@ static void setup_stub_lkb(struct dlm_ls *ls, struct dlm_message *ms) static int validate_message(struct dlm_lkb *lkb, struct dlm_message *ms) { - int from = ms->m_header.h_nodeid; + int from = le32_to_cpu(ms->m_header.h_nodeid); int error = 0; /* currently mixing of user/kernel locks are not supported */ - if (ms->m_flags & DLM_IFL_USER && ~lkb->lkb_flags & DLM_IFL_USER) { + if (ms->m_flags & cpu_to_le32(DLM_IFL_USER) && + ~lkb->lkb_flags & DLM_IFL_USER) { log_error(lkb->lkb_resource->res_ls, "got user dlm message for a kernel lock"); error = -EINVAL; @@ -4002,23 +4026,23 @@ static int validate_message(struct dlm_lkb *lkb, struct dlm_message *ms) } switch (ms->m_type) { - case DLM_MSG_CONVERT: - case DLM_MSG_UNLOCK: - case DLM_MSG_CANCEL: + case cpu_to_le32(DLM_MSG_CONVERT): + case cpu_to_le32(DLM_MSG_UNLOCK): + case cpu_to_le32(DLM_MSG_CANCEL): if (!is_master_copy(lkb) || lkb->lkb_nodeid != from) error = -EINVAL; break; - case DLM_MSG_CONVERT_REPLY: - case DLM_MSG_UNLOCK_REPLY: - case DLM_MSG_CANCEL_REPLY: - case DLM_MSG_GRANT: - case DLM_MSG_BAST: + case cpu_to_le32(DLM_MSG_CONVERT_REPLY): + case cpu_to_le32(DLM_MSG_UNLOCK_REPLY): + case cpu_to_le32(DLM_MSG_CANCEL_REPLY): + case cpu_to_le32(DLM_MSG_GRANT): + case cpu_to_le32(DLM_MSG_BAST): if (!is_process_copy(lkb) || lkb->lkb_nodeid != from) error = -EINVAL; break; - case DLM_MSG_REQUEST_REPLY: + case cpu_to_le32(DLM_MSG_REQUEST_REPLY): if (!is_process_copy(lkb)) error = -EINVAL; else if (lkb->lkb_nodeid != -1 && lkb->lkb_nodeid != from) @@ -4033,8 +4057,8 @@ out: if (error) log_error(lkb->lkb_resource->res_ls, "ignore invalid message %d from %d %x %x %x %d", - ms->m_type, from, lkb->lkb_id, lkb->lkb_remid, - lkb->lkb_flags, lkb->lkb_nodeid); + le32_to_cpu(ms->m_type), from, lkb->lkb_id, + lkb->lkb_remid, lkb->lkb_flags, lkb->lkb_nodeid); return error; } @@ -4079,22 +4103,23 @@ static void send_repeat_remove(struct dlm_ls *ls, char *ms_name, int len) memcpy(ls->ls_remove_name, name, DLM_RESNAME_MAXLEN); spin_unlock(&ls->ls_remove_spin); spin_unlock(&ls->ls_rsbtbl[b].lock); - wake_up(&ls->ls_remove_wait); rv = _create_message(ls, sizeof(struct dlm_message) + len, dir_nodeid, DLM_MSG_REMOVE, &ms, &mh); if (rv) - return; + goto out; memcpy(ms->m_extra, name, len); - ms->m_hash = hash; + ms->m_hash = cpu_to_le32(hash); send_message(mh, ms); +out: spin_lock(&ls->ls_remove_spin); ls->ls_remove_len = 0; memset(ls->ls_remove_name, 0, DLM_RESNAME_MAXLEN); spin_unlock(&ls->ls_remove_spin); + wake_up(&ls->ls_remove_wait); } static int receive_request(struct dlm_ls *ls, struct dlm_message *ms) @@ -4104,7 +4129,7 @@ static int receive_request(struct dlm_ls *ls, struct dlm_message *ms) int from_nodeid; int error, namelen = 0; - from_nodeid = ms->m_header.h_nodeid; + from_nodeid = le32_to_cpu(ms->m_header.h_nodeid); error = create_lkb(ls, &lkb); if (error) @@ -4177,7 +4202,7 @@ static int receive_request(struct dlm_ls *ls, struct dlm_message *ms) if (error != -ENOTBLK) { log_limit(ls, "receive_request %x from %d %d", - ms->m_lkid, from_nodeid, error); + le32_to_cpu(ms->m_lkid), from_nodeid, error); } if (namelen && error == -EBADR) { @@ -4196,15 +4221,16 @@ static int receive_convert(struct dlm_ls *ls, struct dlm_message *ms) struct dlm_rsb *r; int error, reply = 1; - error = find_lkb(ls, ms->m_remid, &lkb); + error = find_lkb(ls, le32_to_cpu(ms->m_remid), &lkb); if (error) goto fail; - if (lkb->lkb_remid != ms->m_lkid) { + if (lkb->lkb_remid != le32_to_cpu(ms->m_lkid)) { log_error(ls, "receive_convert %x remid %x recover_seq %llu " "remote %d %x", lkb->lkb_id, lkb->lkb_remid, (unsigned long long)lkb->lkb_recover_seq, - ms->m_header.h_nodeid, ms->m_lkid); + le32_to_cpu(ms->m_header.h_nodeid), + le32_to_cpu(ms->m_lkid)); error = -ENOENT; dlm_put_lkb(lkb); goto fail; @@ -4251,14 +4277,15 @@ static int receive_unlock(struct dlm_ls *ls, struct dlm_message *ms) struct dlm_rsb *r; int error; - error = find_lkb(ls, ms->m_remid, &lkb); + error = find_lkb(ls, le32_to_cpu(ms->m_remid), &lkb); if (error) goto fail; - if (lkb->lkb_remid != ms->m_lkid) { + if (lkb->lkb_remid != le32_to_cpu(ms->m_lkid)) { log_error(ls, "receive_unlock %x remid %x remote %d %x", lkb->lkb_id, lkb->lkb_remid, - ms->m_header.h_nodeid, ms->m_lkid); + le32_to_cpu(ms->m_header.h_nodeid), + le32_to_cpu(ms->m_lkid)); error = -ENOENT; dlm_put_lkb(lkb); goto fail; @@ -4302,7 +4329,7 @@ static int receive_cancel(struct dlm_ls *ls, struct dlm_message *ms) struct dlm_rsb *r; int error; - error = find_lkb(ls, ms->m_remid, &lkb); + error = find_lkb(ls, le32_to_cpu(ms->m_remid), &lkb); if (error) goto fail; @@ -4338,7 +4365,7 @@ static int receive_grant(struct dlm_ls *ls, struct dlm_message *ms) struct dlm_rsb *r; int error; - error = find_lkb(ls, ms->m_remid, &lkb); + error = find_lkb(ls, le32_to_cpu(ms->m_remid), &lkb); if (error) return error; @@ -4369,7 +4396,7 @@ static int receive_bast(struct dlm_ls *ls, struct dlm_message *ms) struct dlm_rsb *r; int error; - error = find_lkb(ls, ms->m_remid, &lkb); + error = find_lkb(ls, le32_to_cpu(ms->m_remid), &lkb); if (error) return error; @@ -4382,8 +4409,8 @@ static int receive_bast(struct dlm_ls *ls, struct dlm_message *ms) if (error) goto out; - queue_bast(r, lkb, ms->m_bastmode); - lkb->lkb_highbast = ms->m_bastmode; + queue_bast(r, lkb, le32_to_cpu(ms->m_bastmode)); + lkb->lkb_highbast = le32_to_cpu(ms->m_bastmode); out: unlock_rsb(r); put_rsb(r); @@ -4395,7 +4422,7 @@ static void receive_lookup(struct dlm_ls *ls, struct dlm_message *ms) { int len, error, ret_nodeid, from_nodeid, our_nodeid; - from_nodeid = ms->m_header.h_nodeid; + from_nodeid = le32_to_cpu(ms->m_header.h_nodeid); our_nodeid = dlm_our_nodeid(); len = receive_extralen(ms); @@ -4418,7 +4445,7 @@ static void receive_remove(struct dlm_ls *ls, struct dlm_message *ms) uint32_t hash, b; int rv, len, dir_nodeid, from_nodeid; - from_nodeid = ms->m_header.h_nodeid; + from_nodeid = le32_to_cpu(ms->m_header.h_nodeid); len = receive_extralen(ms); @@ -4428,7 +4455,7 @@ static void receive_remove(struct dlm_ls *ls, struct dlm_message *ms) return; } - dir_nodeid = dlm_hash2nodeid(ls, ms->m_hash); + dir_nodeid = dlm_hash2nodeid(ls, le32_to_cpu(ms->m_hash)); if (dir_nodeid != dlm_our_nodeid()) { log_error(ls, "receive_remove from %d bad nodeid %d", from_nodeid, dir_nodeid); @@ -4501,7 +4528,7 @@ static void receive_remove(struct dlm_ls *ls, struct dlm_message *ms) static void receive_purge(struct dlm_ls *ls, struct dlm_message *ms) { - do_purge(ls, ms->m_nodeid, ms->m_pid); + do_purge(ls, le32_to_cpu(ms->m_nodeid), le32_to_cpu(ms->m_pid)); } static int receive_request_reply(struct dlm_ls *ls, struct dlm_message *ms) @@ -4509,9 +4536,9 @@ static int receive_request_reply(struct dlm_ls *ls, struct dlm_message *ms) struct dlm_lkb *lkb; struct dlm_rsb *r; int error, mstype, result; - int from_nodeid = ms->m_header.h_nodeid; + int from_nodeid = le32_to_cpu(ms->m_header.h_nodeid); - error = find_lkb(ls, ms->m_remid, &lkb); + error = find_lkb(ls, le32_to_cpu(ms->m_remid), &lkb); if (error) return error; @@ -4527,7 +4554,8 @@ static int receive_request_reply(struct dlm_ls *ls, struct dlm_message *ms) error = remove_from_waiters(lkb, DLM_MSG_REQUEST_REPLY); if (error) { log_error(ls, "receive_request_reply %x remote %d %x result %d", - lkb->lkb_id, from_nodeid, ms->m_lkid, ms->m_result); + lkb->lkb_id, from_nodeid, le32_to_cpu(ms->m_lkid), + from_dlm_errno(le32_to_cpu(ms->m_result))); dlm_dump_rsb(r); goto out; } @@ -4541,7 +4569,7 @@ static int receive_request_reply(struct dlm_ls *ls, struct dlm_message *ms) } /* this is the value returned from do_request() on the master */ - result = ms->m_result; + result = from_dlm_errno(le32_to_cpu(ms->m_result)); switch (result) { case -EAGAIN: @@ -4555,7 +4583,7 @@ static int receive_request_reply(struct dlm_ls *ls, struct dlm_message *ms) case 0: /* request was queued or granted on remote master */ receive_flags_reply(lkb, ms); - lkb->lkb_remid = ms->m_lkid; + lkb->lkb_remid = le32_to_cpu(ms->m_lkid); if (is_altmode(lkb)) munge_altmode(lkb, ms); if (result) { @@ -4628,7 +4656,7 @@ static void __receive_convert_reply(struct dlm_rsb *r, struct dlm_lkb *lkb, struct dlm_message *ms) { /* this is the value returned from do_convert() on the master */ - switch (ms->m_result) { + switch (from_dlm_errno(le32_to_cpu(ms->m_result))) { case -EAGAIN: /* convert would block (be queued) on remote master */ queue_cast(r, lkb, -EAGAIN); @@ -4661,8 +4689,9 @@ static void __receive_convert_reply(struct dlm_rsb *r, struct dlm_lkb *lkb, default: log_error(r->res_ls, "receive_convert_reply %x remote %d %x %d", - lkb->lkb_id, ms->m_header.h_nodeid, ms->m_lkid, - ms->m_result); + lkb->lkb_id, le32_to_cpu(ms->m_header.h_nodeid), + le32_to_cpu(ms->m_lkid), + from_dlm_errno(le32_to_cpu(ms->m_result))); dlm_print_rsb(r); dlm_print_lkb(lkb); } @@ -4696,7 +4725,7 @@ static int receive_convert_reply(struct dlm_ls *ls, struct dlm_message *ms) struct dlm_lkb *lkb; int error; - error = find_lkb(ls, ms->m_remid, &lkb); + error = find_lkb(ls, le32_to_cpu(ms->m_remid), &lkb); if (error) return error; @@ -4724,7 +4753,7 @@ static void _receive_unlock_reply(struct dlm_lkb *lkb, struct dlm_message *ms) /* this is the value returned from do_unlock() on the master */ - switch (ms->m_result) { + switch (from_dlm_errno(le32_to_cpu(ms->m_result))) { case -DLM_EUNLOCK: receive_flags_reply(lkb, ms); remove_lock_pc(r, lkb); @@ -4734,7 +4763,7 @@ static void _receive_unlock_reply(struct dlm_lkb *lkb, struct dlm_message *ms) break; default: log_error(r->res_ls, "receive_unlock_reply %x error %d", - lkb->lkb_id, ms->m_result); + lkb->lkb_id, from_dlm_errno(le32_to_cpu(ms->m_result))); } out: unlock_rsb(r); @@ -4746,7 +4775,7 @@ static int receive_unlock_reply(struct dlm_ls *ls, struct dlm_message *ms) struct dlm_lkb *lkb; int error; - error = find_lkb(ls, ms->m_remid, &lkb); + error = find_lkb(ls, le32_to_cpu(ms->m_remid), &lkb); if (error) return error; @@ -4774,7 +4803,7 @@ static void _receive_cancel_reply(struct dlm_lkb *lkb, struct dlm_message *ms) /* this is the value returned from do_cancel() on the master */ - switch (ms->m_result) { + switch (from_dlm_errno(le32_to_cpu(ms->m_result))) { case -DLM_ECANCEL: receive_flags_reply(lkb, ms); revert_lock_pc(r, lkb); @@ -4784,7 +4813,8 @@ static void _receive_cancel_reply(struct dlm_lkb *lkb, struct dlm_message *ms) break; default: log_error(r->res_ls, "receive_cancel_reply %x error %d", - lkb->lkb_id, ms->m_result); + lkb->lkb_id, + from_dlm_errno(le32_to_cpu(ms->m_result))); } out: unlock_rsb(r); @@ -4796,7 +4826,7 @@ static int receive_cancel_reply(struct dlm_ls *ls, struct dlm_message *ms) struct dlm_lkb *lkb; int error; - error = find_lkb(ls, ms->m_remid, &lkb); + error = find_lkb(ls, le32_to_cpu(ms->m_remid), &lkb); if (error) return error; @@ -4812,9 +4842,10 @@ static void receive_lookup_reply(struct dlm_ls *ls, struct dlm_message *ms) int error, ret_nodeid; int do_lookup_list = 0; - error = find_lkb(ls, ms->m_lkid, &lkb); + error = find_lkb(ls, le32_to_cpu(ms->m_lkid), &lkb); if (error) { - log_error(ls, "receive_lookup_reply no lkid %x", ms->m_lkid); + log_error(ls, "%s no lkid %x", __func__, + le32_to_cpu(ms->m_lkid)); return; } @@ -4829,7 +4860,7 @@ static void receive_lookup_reply(struct dlm_ls *ls, struct dlm_message *ms) if (error) goto out; - ret_nodeid = ms->m_nodeid; + ret_nodeid = le32_to_cpu(ms->m_nodeid); /* We sometimes receive a request from the dir node for this rsb before we've received the dir node's loookup_reply for it. @@ -4841,8 +4872,8 @@ static void receive_lookup_reply(struct dlm_ls *ls, struct dlm_message *ms) /* This should never happen */ log_error(ls, "receive_lookup_reply %x from %d ret %d " "master %d dir %d our %d first %x %s", - lkb->lkb_id, ms->m_header.h_nodeid, ret_nodeid, - r->res_master_nodeid, r->res_dir_nodeid, + lkb->lkb_id, le32_to_cpu(ms->m_header.h_nodeid), + ret_nodeid, r->res_master_nodeid, r->res_dir_nodeid, dlm_our_nodeid(), r->res_first_lkid, r->res_name); } @@ -4854,7 +4885,7 @@ static void receive_lookup_reply(struct dlm_ls *ls, struct dlm_message *ms) } else if (ret_nodeid == -1) { /* the remote node doesn't believe it's the dir node */ log_error(ls, "receive_lookup_reply %x from %d bad ret_nodeid", - lkb->lkb_id, ms->m_header.h_nodeid); + lkb->lkb_id, le32_to_cpu(ms->m_header.h_nodeid)); r->res_master_nodeid = 0; r->res_nodeid = -1; lkb->lkb_nodeid = -1; @@ -4888,10 +4919,12 @@ static void _receive_message(struct dlm_ls *ls, struct dlm_message *ms, { int error = 0, noent = 0; - if (!dlm_is_member(ls, ms->m_header.h_nodeid)) { + if (!dlm_is_member(ls, le32_to_cpu(ms->m_header.h_nodeid))) { log_limit(ls, "receive %d from non-member %d %x %x %d", - ms->m_type, ms->m_header.h_nodeid, ms->m_lkid, - ms->m_remid, ms->m_result); + le32_to_cpu(ms->m_type), + le32_to_cpu(ms->m_header.h_nodeid), + le32_to_cpu(ms->m_lkid), le32_to_cpu(ms->m_remid), + from_dlm_errno(le32_to_cpu(ms->m_result))); return; } @@ -4899,77 +4932,78 @@ static void _receive_message(struct dlm_ls *ls, struct dlm_message *ms, /* messages sent to a master node */ - case DLM_MSG_REQUEST: + case cpu_to_le32(DLM_MSG_REQUEST): error = receive_request(ls, ms); break; - case DLM_MSG_CONVERT: + case cpu_to_le32(DLM_MSG_CONVERT): error = receive_convert(ls, ms); break; - case DLM_MSG_UNLOCK: + case cpu_to_le32(DLM_MSG_UNLOCK): error = receive_unlock(ls, ms); break; - case DLM_MSG_CANCEL: + case cpu_to_le32(DLM_MSG_CANCEL): noent = 1; error = receive_cancel(ls, ms); break; /* messages sent from a master node (replies to above) */ - case DLM_MSG_REQUEST_REPLY: + case cpu_to_le32(DLM_MSG_REQUEST_REPLY): error = receive_request_reply(ls, ms); break; - case DLM_MSG_CONVERT_REPLY: + case cpu_to_le32(DLM_MSG_CONVERT_REPLY): error = receive_convert_reply(ls, ms); break; - case DLM_MSG_UNLOCK_REPLY: + case cpu_to_le32(DLM_MSG_UNLOCK_REPLY): error = receive_unlock_reply(ls, ms); break; - case DLM_MSG_CANCEL_REPLY: + case cpu_to_le32(DLM_MSG_CANCEL_REPLY): error = receive_cancel_reply(ls, ms); break; /* messages sent from a master node (only two types of async msg) */ - case DLM_MSG_GRANT: + case cpu_to_le32(DLM_MSG_GRANT): noent = 1; error = receive_grant(ls, ms); break; - case DLM_MSG_BAST: + case cpu_to_le32(DLM_MSG_BAST): noent = 1; error = receive_bast(ls, ms); break; /* messages sent to a dir node */ - case DLM_MSG_LOOKUP: + case cpu_to_le32(DLM_MSG_LOOKUP): receive_lookup(ls, ms); break; - case DLM_MSG_REMOVE: + case cpu_to_le32(DLM_MSG_REMOVE): receive_remove(ls, ms); break; /* messages sent from a dir node (remove has no reply) */ - case DLM_MSG_LOOKUP_REPLY: + case cpu_to_le32(DLM_MSG_LOOKUP_REPLY): receive_lookup_reply(ls, ms); break; /* other messages */ - case DLM_MSG_PURGE: + case cpu_to_le32(DLM_MSG_PURGE): receive_purge(ls, ms); break; default: - log_error(ls, "unknown message type %d", ms->m_type); + log_error(ls, "unknown message type %d", + le32_to_cpu(ms->m_type)); } /* @@ -4985,22 +5019,26 @@ static void _receive_message(struct dlm_ls *ls, struct dlm_message *ms, if (error == -ENOENT && noent) { log_debug(ls, "receive %d no %x remote %d %x saved_seq %u", - ms->m_type, ms->m_remid, ms->m_header.h_nodeid, - ms->m_lkid, saved_seq); + le32_to_cpu(ms->m_type), le32_to_cpu(ms->m_remid), + le32_to_cpu(ms->m_header.h_nodeid), + le32_to_cpu(ms->m_lkid), saved_seq); } else if (error == -ENOENT) { log_error(ls, "receive %d no %x remote %d %x saved_seq %u", - ms->m_type, ms->m_remid, ms->m_header.h_nodeid, - ms->m_lkid, saved_seq); + le32_to_cpu(ms->m_type), le32_to_cpu(ms->m_remid), + le32_to_cpu(ms->m_header.h_nodeid), + le32_to_cpu(ms->m_lkid), saved_seq); - if (ms->m_type == DLM_MSG_CONVERT) - dlm_dump_rsb_hash(ls, ms->m_hash); + if (ms->m_type == cpu_to_le32(DLM_MSG_CONVERT)) + dlm_dump_rsb_hash(ls, le32_to_cpu(ms->m_hash)); } if (error == -EINVAL) { log_error(ls, "receive %d inval from %d lkid %x remid %x " "saved_seq %u", - ms->m_type, ms->m_header.h_nodeid, - ms->m_lkid, ms->m_remid, saved_seq); + le32_to_cpu(ms->m_type), + le32_to_cpu(ms->m_header.h_nodeid), + le32_to_cpu(ms->m_lkid), le32_to_cpu(ms->m_remid), + saved_seq); } } @@ -5021,7 +5059,7 @@ static void dlm_receive_message(struct dlm_ls *ls, struct dlm_message *ms, lockspace generation before we left. */ if (!ls->ls_generation) { log_limit(ls, "receive %d from %d ignore old gen", - ms->m_type, nodeid); + le32_to_cpu(ms->m_type), nodeid); return; } @@ -5054,30 +5092,30 @@ void dlm_receive_buffer(union dlm_packet *p, int nodeid) switch (hd->h_cmd) { case DLM_MSG: - dlm_message_in(&p->message); - type = p->message.m_type; + type = le32_to_cpu(p->message.m_type); break; case DLM_RCOM: - dlm_rcom_in(&p->rcom); - type = p->rcom.rc_type; + type = le32_to_cpu(p->rcom.rc_type); break; default: log_print("invalid h_cmd %d from %u", hd->h_cmd, nodeid); return; } - if (hd->h_nodeid != nodeid) { + if (le32_to_cpu(hd->h_nodeid) != nodeid) { log_print("invalid h_nodeid %d from %d lockspace %x", - hd->h_nodeid, nodeid, hd->u.h_lockspace); + le32_to_cpu(hd->h_nodeid), nodeid, + le32_to_cpu(hd->u.h_lockspace)); return; } - ls = dlm_find_lockspace_global(hd->u.h_lockspace); + ls = dlm_find_lockspace_global(le32_to_cpu(hd->u.h_lockspace)); if (!ls) { if (dlm_config.ci_log_debug) { printk_ratelimited(KERN_DEBUG "dlm: invalid lockspace " "%u from %d cmd %d type %d\n", - hd->u.h_lockspace, nodeid, hd->h_cmd, type); + le32_to_cpu(hd->u.h_lockspace), nodeid, + hd->h_cmd, type); } if (hd->h_cmd == DLM_RCOM && type == DLM_RCOM_STATUS) @@ -5104,10 +5142,10 @@ static void recover_convert_waiter(struct dlm_ls *ls, struct dlm_lkb *lkb, if (middle_conversion(lkb)) { hold_lkb(lkb); memset(ms_stub, 0, sizeof(struct dlm_message)); - ms_stub->m_flags = DLM_IFL_STUB_MS; - ms_stub->m_type = DLM_MSG_CONVERT_REPLY; - ms_stub->m_result = -EINPROGRESS; - ms_stub->m_header.h_nodeid = lkb->lkb_nodeid; + ms_stub->m_flags = cpu_to_le32(DLM_IFL_STUB_MS); + ms_stub->m_type = cpu_to_le32(DLM_MSG_CONVERT_REPLY); + ms_stub->m_result = cpu_to_le32(to_dlm_errno(-EINPROGRESS)); + ms_stub->m_header.h_nodeid = cpu_to_le32(lkb->lkb_nodeid); _receive_convert_reply(lkb, ms_stub); /* Same special case as in receive_rcom_lock_args() */ @@ -5226,10 +5264,10 @@ void dlm_recover_waiters_pre(struct dlm_ls *ls) case DLM_MSG_UNLOCK: hold_lkb(lkb); memset(ms_stub, 0, sizeof(struct dlm_message)); - ms_stub->m_flags = DLM_IFL_STUB_MS; - ms_stub->m_type = DLM_MSG_UNLOCK_REPLY; - ms_stub->m_result = stub_unlock_result; - ms_stub->m_header.h_nodeid = lkb->lkb_nodeid; + ms_stub->m_flags = cpu_to_le32(DLM_IFL_STUB_MS); + ms_stub->m_type = cpu_to_le32(DLM_MSG_UNLOCK_REPLY); + ms_stub->m_result = cpu_to_le32(to_dlm_errno(stub_unlock_result)); + ms_stub->m_header.h_nodeid = cpu_to_le32(lkb->lkb_nodeid); _receive_unlock_reply(lkb, ms_stub); dlm_put_lkb(lkb); break; @@ -5237,10 +5275,10 @@ void dlm_recover_waiters_pre(struct dlm_ls *ls) case DLM_MSG_CANCEL: hold_lkb(lkb); memset(ms_stub, 0, sizeof(struct dlm_message)); - ms_stub->m_flags = DLM_IFL_STUB_MS; - ms_stub->m_type = DLM_MSG_CANCEL_REPLY; - ms_stub->m_result = stub_cancel_result; - ms_stub->m_header.h_nodeid = lkb->lkb_nodeid; + ms_stub->m_flags = cpu_to_le32(DLM_IFL_STUB_MS); + ms_stub->m_type = cpu_to_le32(DLM_MSG_CANCEL_REPLY); + ms_stub->m_result = cpu_to_le32(to_dlm_errno(stub_cancel_result)); + ms_stub->m_header.h_nodeid = cpu_to_le32(lkb->lkb_nodeid); _receive_cancel_reply(lkb, ms_stub); dlm_put_lkb(lkb); break; @@ -5257,21 +5295,18 @@ void dlm_recover_waiters_pre(struct dlm_ls *ls) static struct dlm_lkb *find_resend_waiter(struct dlm_ls *ls) { - struct dlm_lkb *lkb; - int found = 0; + struct dlm_lkb *lkb = NULL, *iter; mutex_lock(&ls->ls_waiters_mutex); - list_for_each_entry(lkb, &ls->ls_waiters, lkb_wait_reply) { - if (lkb->lkb_flags & DLM_IFL_RESEND) { - hold_lkb(lkb); - found = 1; + list_for_each_entry(iter, &ls->ls_waiters, lkb_wait_reply) { + if (iter->lkb_flags & DLM_IFL_RESEND) { + hold_lkb(iter); + lkb = iter; break; } } mutex_unlock(&ls->ls_waiters_mutex); - if (!found) - lkb = NULL; return lkb; } @@ -5331,11 +5366,16 @@ int dlm_recover_waiters_post(struct dlm_ls *ls) lkb->lkb_flags &= ~DLM_IFL_OVERLAP_UNLOCK; lkb->lkb_flags &= ~DLM_IFL_OVERLAP_CANCEL; lkb->lkb_wait_type = 0; - lkb->lkb_wait_count = 0; + /* drop all wait_count references we still + * hold a reference for this iteration. + */ + while (lkb->lkb_wait_count) { + lkb->lkb_wait_count--; + unhold_lkb(lkb); + } mutex_lock(&ls->ls_waiters_mutex); list_del_init(&lkb->lkb_wait_reply); mutex_unlock(&ls->ls_waiters_mutex); - unhold_lkb(lkb); /* for waiters list */ if (oc || ou) { /* do an unlock or cancel instead of resending */ @@ -5605,7 +5645,7 @@ static int receive_rcom_lock_args(struct dlm_ls *ls, struct dlm_lkb *lkb, { struct rcom_lock *rl = (struct rcom_lock *) rc->rc_buf; - lkb->lkb_nodeid = rc->rc_header.h_nodeid; + lkb->lkb_nodeid = le32_to_cpu(rc->rc_header.h_nodeid); lkb->lkb_ownpid = le32_to_cpu(rl->rl_ownpid); lkb->lkb_remid = le32_to_cpu(rl->rl_lkid); lkb->lkb_exflags = le32_to_cpu(rl->rl_exflags); @@ -5620,8 +5660,8 @@ static int receive_rcom_lock_args(struct dlm_ls *ls, struct dlm_lkb *lkb, lkb->lkb_astfn = (rl->rl_asts & DLM_CB_CAST) ? &fake_astfn : NULL; if (lkb->lkb_exflags & DLM_LKF_VALBLK) { - int lvblen = rc->rc_header.h_length - sizeof(struct dlm_rcom) - - sizeof(struct rcom_lock); + int lvblen = le16_to_cpu(rc->rc_header.h_length) - + sizeof(struct dlm_rcom) - sizeof(struct rcom_lock); if (lvblen > ls->ls_lvblen) return -EINVAL; lkb->lkb_lvbptr = dlm_allocate_lvb(ls); @@ -5657,7 +5697,7 @@ int dlm_recover_master_copy(struct dlm_ls *ls, struct dlm_rcom *rc) struct dlm_rsb *r; struct dlm_lkb *lkb; uint32_t remid = 0; - int from_nodeid = rc->rc_header.h_nodeid; + int from_nodeid = le32_to_cpu(rc->rc_header.h_nodeid); int error; if (rl->rl_parent_lkid) { @@ -5707,7 +5747,6 @@ int dlm_recover_master_copy(struct dlm_ls *ls, struct dlm_rcom *rc) attach_lkb(r, lkb); add_lkb(r, lkb, rl->rl_status); - error = 0; ls->ls_recover_locks_in++; if (!list_empty(&r->res_waitqueue) || !list_empty(&r->res_convertqueue)) @@ -5747,7 +5786,8 @@ int dlm_recover_process_copy(struct dlm_ls *ls, struct dlm_rcom *rc) error = find_lkb(ls, lkid, &lkb); if (error) { log_error(ls, "dlm_recover_process_copy no %x remote %d %x %d", - lkid, rc->rc_header.h_nodeid, remid, result); + lkid, le32_to_cpu(rc->rc_header.h_nodeid), remid, + result); return error; } @@ -5757,7 +5797,8 @@ int dlm_recover_process_copy(struct dlm_ls *ls, struct dlm_rcom *rc) if (!is_process_copy(lkb)) { log_error(ls, "dlm_recover_process_copy bad %x remote %d %x %d", - lkid, rc->rc_header.h_nodeid, remid, result); + lkid, le32_to_cpu(rc->rc_header.h_nodeid), remid, + result); dlm_dump_rsb(r); unlock_rsb(r); put_rsb(r); @@ -5772,7 +5813,8 @@ int dlm_recover_process_copy(struct dlm_ls *ls, struct dlm_rcom *rc) a barrier between recover_masters and recover_locks. */ log_debug(ls, "dlm_recover_process_copy %x remote %d %x %d", - lkid, rc->rc_header.h_nodeid, remid, result); + lkid, le32_to_cpu(rc->rc_header.h_nodeid), remid, + result); dlm_send_rcom_lock(r, lkb); goto out; @@ -5782,7 +5824,8 @@ int dlm_recover_process_copy(struct dlm_ls *ls, struct dlm_rcom *rc) break; default: log_error(ls, "dlm_recover_process_copy %x remote %d %x %d unk", - lkid, rc->rc_header.h_nodeid, remid, result); + lkid, le32_to_cpu(rc->rc_header.h_nodeid), remid, + result); } /* an ack for dlm_recover_locks() which waits for replies from @@ -5925,37 +5968,36 @@ int dlm_user_adopt_orphan(struct dlm_ls *ls, struct dlm_user_args *ua_tmp, int mode, uint32_t flags, void *name, unsigned int namelen, unsigned long timeout_cs, uint32_t *lkid) { - struct dlm_lkb *lkb; + struct dlm_lkb *lkb = NULL, *iter; struct dlm_user_args *ua; int found_other_mode = 0; - int found = 0; int rv = 0; mutex_lock(&ls->ls_orphans_mutex); - list_for_each_entry(lkb, &ls->ls_orphans, lkb_ownqueue) { - if (lkb->lkb_resource->res_length != namelen) + list_for_each_entry(iter, &ls->ls_orphans, lkb_ownqueue) { + if (iter->lkb_resource->res_length != namelen) continue; - if (memcmp(lkb->lkb_resource->res_name, name, namelen)) + if (memcmp(iter->lkb_resource->res_name, name, namelen)) continue; - if (lkb->lkb_grmode != mode) { + if (iter->lkb_grmode != mode) { found_other_mode = 1; continue; } - found = 1; - list_del_init(&lkb->lkb_ownqueue); - lkb->lkb_flags &= ~DLM_IFL_ORPHAN; - *lkid = lkb->lkb_id; + lkb = iter; + list_del_init(&iter->lkb_ownqueue); + iter->lkb_flags &= ~DLM_IFL_ORPHAN; + *lkid = iter->lkb_id; break; } mutex_unlock(&ls->ls_orphans_mutex); - if (!found && found_other_mode) { + if (!lkb && found_other_mode) { rv = -EAGAIN; goto out; } - if (!found) { + if (!lkb) { rv = -ENOENT; goto out; } @@ -6307,8 +6349,8 @@ static int send_purge(struct dlm_ls *ls, int nodeid, int pid) DLM_MSG_PURGE, &ms, &mh); if (error) return error; - ms->m_nodeid = nodeid; - ms->m_pid = pid; + ms->m_nodeid = cpu_to_le32(nodeid); + ms->m_pid = cpu_to_le32(pid); return send_message(mh, ms); } diff --git a/fs/dlm/lockspace.c b/fs/dlm/lockspace.c index 0d3833a124a3..19ed41a5da93 100644 --- a/fs/dlm/lockspace.c +++ b/fs/dlm/lockspace.c @@ -922,3 +922,15 @@ void dlm_stop_lockspaces(void) log_print("dlm user daemon left %d lockspaces", count); } +void dlm_stop_lockspaces_check(void) +{ + struct dlm_ls *ls; + + spin_lock(&lslist_lock); + list_for_each_entry(ls, &lslist, ls_list) { + if (WARN_ON(!rwsem_is_locked(&ls->ls_in_recovery) || + !dlm_locking_stopped(ls))) + break; + } + spin_unlock(&lslist_lock); +} diff --git a/fs/dlm/lockspace.h b/fs/dlm/lockspace.h index a78d853b9342..306fc4f4ea15 100644 --- a/fs/dlm/lockspace.h +++ b/fs/dlm/lockspace.h @@ -19,6 +19,7 @@ struct dlm_ls *dlm_find_lockspace_local(void *id); struct dlm_ls *dlm_find_lockspace_device(int minor); void dlm_put_lockspace(struct dlm_ls *ls); void dlm_stop_lockspaces(void); +void dlm_stop_lockspaces_check(void); #endif /* __LOCKSPACE_DOT_H__ */ diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c index e284d696c1fd..19e82f08c0e0 100644 --- a/fs/dlm/lowcomms.c +++ b/fs/dlm/lowcomms.c @@ -1303,6 +1303,10 @@ static struct dlm_msg *dlm_lowcomms_new_msg_con(struct connection *con, int len, return msg; } +/* avoid false positive for nodes_srcu, unlock happens in + * dlm_lowcomms_commit_msg which is a must call if success + */ +#ifndef __CHECKER__ struct dlm_msg *dlm_lowcomms_new_msg(int nodeid, int len, gfp_t allocation, char **ppc, void (*cb)(void *data), void *data) @@ -1336,6 +1340,7 @@ struct dlm_msg *dlm_lowcomms_new_msg(int nodeid, int len, gfp_t allocation, msg->idx = idx; return msg; } +#endif static void _dlm_lowcomms_commit_msg(struct dlm_msg *msg) { @@ -1362,11 +1367,16 @@ out: return; } +/* avoid false positive for nodes_srcu, lock was happen in + * dlm_lowcomms_new_msg + */ +#ifndef __CHECKER__ void dlm_lowcomms_commit_msg(struct dlm_msg *msg) { _dlm_lowcomms_commit_msg(msg); srcu_read_unlock(&connections_srcu, msg->idx); } +#endif void dlm_lowcomms_put_msg(struct dlm_msg *msg) { @@ -1789,7 +1799,7 @@ static int dlm_listen_for_all(void) SOCK_STREAM, dlm_proto_ops->proto, &sock); if (result < 0) { log_print("Can't create comms socket: %d", result); - goto out; + return result; } sock_set_mark(sock->sk, dlm_config.ci_mark); diff --git a/fs/dlm/member.c b/fs/dlm/member.c index 61f906e705db..98084e0cfccf 100644 --- a/fs/dlm/member.c +++ b/fs/dlm/member.c @@ -20,7 +20,7 @@ int dlm_slots_version(struct dlm_header *h) { - if ((h->h_version & 0x0000FFFF) < DLM_HEADER_SLOTS) + if ((le32_to_cpu(h->h_version) & 0x0000FFFF) < DLM_HEADER_SLOTS) return 0; return 1; } @@ -120,18 +120,13 @@ int dlm_slots_copy_in(struct dlm_ls *ls) ro0 = (struct rcom_slot *)(rc->rc_buf + sizeof(struct rcom_config)); - for (i = 0, ro = ro0; i < num_slots; i++, ro++) { - ro->ro_nodeid = le32_to_cpu(ro->ro_nodeid); - ro->ro_slot = le16_to_cpu(ro->ro_slot); - } - log_slots(ls, gen, num_slots, ro0, NULL, 0); list_for_each_entry(memb, &ls->ls_nodes, list) { for (i = 0, ro = ro0; i < num_slots; i++, ro++) { - if (ro->ro_nodeid != memb->nodeid) + if (le32_to_cpu(ro->ro_nodeid) != memb->nodeid) continue; - memb->slot = ro->ro_slot; + memb->slot = le16_to_cpu(ro->ro_slot); memb->slot_prev = memb->slot; break; } diff --git a/fs/dlm/midcomms.c b/fs/dlm/midcomms.c index 3635e42b0669..6489bc22ad61 100644 --- a/fs/dlm/midcomms.c +++ b/fs/dlm/midcomms.c @@ -135,6 +135,7 @@ #include <net/tcp.h> #include "dlm_internal.h" +#include "lockspace.h" #include "lowcomms.h" #include "config.h" #include "memory.h" @@ -380,13 +381,12 @@ static int dlm_send_ack(int nodeid, uint32_t seq) m_header = (struct dlm_header *)ppc; - m_header->h_version = (DLM_HEADER_MAJOR | DLM_HEADER_MINOR); - m_header->h_nodeid = dlm_our_nodeid(); - m_header->h_length = mb_len; + m_header->h_version = cpu_to_le32(DLM_HEADER_MAJOR | DLM_HEADER_MINOR); + m_header->h_nodeid = cpu_to_le32(dlm_our_nodeid()); + m_header->h_length = cpu_to_le16(mb_len); m_header->h_cmd = DLM_ACK; - m_header->u.h_seq = seq; + m_header->u.h_seq = cpu_to_le32(seq); - header_out(m_header); dlm_lowcomms_commit_msg(msg); dlm_lowcomms_put_msg(msg); @@ -409,13 +409,11 @@ static int dlm_send_fin(struct midcomms_node *node, m_header = (struct dlm_header *)ppc; - m_header->h_version = (DLM_HEADER_MAJOR | DLM_HEADER_MINOR); - m_header->h_nodeid = dlm_our_nodeid(); - m_header->h_length = mb_len; + m_header->h_version = cpu_to_le32(DLM_HEADER_MAJOR | DLM_HEADER_MINOR); + m_header->h_nodeid = cpu_to_le32(dlm_our_nodeid()); + m_header->h_length = cpu_to_le16(mb_len); m_header->h_cmd = DLM_FIN; - header_out(m_header); - pr_debug("sending fin msg to node %d\n", node->nodeid); dlm_midcomms_commit_mhandle(mh); set_bit(DLM_NODE_FLAG_STOP_TX, &node->flags); @@ -574,14 +572,14 @@ dlm_midcomms_recv_node_lookup(int nodeid, const union dlm_packet *p, return NULL; } - switch (le32_to_cpu(p->rcom.rc_type)) { - case DLM_RCOM_NAMES: + switch (p->rcom.rc_type) { + case cpu_to_le32(DLM_RCOM_NAMES): fallthrough; - case DLM_RCOM_NAMES_REPLY: + case cpu_to_le32(DLM_RCOM_NAMES_REPLY): fallthrough; - case DLM_RCOM_STATUS: + case cpu_to_le32(DLM_RCOM_STATUS): fallthrough; - case DLM_RCOM_STATUS_REPLY: + case cpu_to_le32(DLM_RCOM_STATUS_REPLY): node = nodeid2node(nodeid, 0); if (node) { spin_lock(&node->state_lock); @@ -741,14 +739,14 @@ static void dlm_midcomms_receive_buffer_3_2(union dlm_packet *p, int nodeid) * * length already checked. */ - switch (le32_to_cpu(p->rcom.rc_type)) { - case DLM_RCOM_NAMES: + switch (p->rcom.rc_type) { + case cpu_to_le32(DLM_RCOM_NAMES): fallthrough; - case DLM_RCOM_NAMES_REPLY: + case cpu_to_le32(DLM_RCOM_NAMES_REPLY): fallthrough; - case DLM_RCOM_STATUS: + case cpu_to_le32(DLM_RCOM_STATUS): fallthrough; - case DLM_RCOM_STATUS_REPLY: + case cpu_to_le32(DLM_RCOM_STATUS_REPLY): break; default: log_print("unsupported rcom type received: %u, will skip this message from node %d", @@ -1020,11 +1018,10 @@ static void dlm_fill_opts_header(struct dlm_opts *opts, uint16_t inner_len, uint32_t seq) { opts->o_header.h_cmd = DLM_OPTS; - opts->o_header.h_version = (DLM_HEADER_MAJOR | DLM_HEADER_MINOR); - opts->o_header.h_nodeid = dlm_our_nodeid(); - opts->o_header.h_length = DLM_MIDCOMMS_OPT_LEN + inner_len; - opts->o_header.u.h_seq = seq; - header_out(&opts->o_header); + opts->o_header.h_version = cpu_to_le32(DLM_HEADER_MAJOR | DLM_HEADER_MINOR); + opts->o_header.h_nodeid = cpu_to_le32(dlm_our_nodeid()); + opts->o_header.h_length = cpu_to_le16(DLM_MIDCOMMS_OPT_LEN + inner_len); + opts->o_header.u.h_seq = cpu_to_le32(seq); } static void midcomms_new_msg_cb(void *data) @@ -1062,6 +1059,10 @@ static struct dlm_msg *dlm_midcomms_get_msg_3_2(struct dlm_mhandle *mh, int node return msg; } +/* avoid false positive for nodes_srcu, unlock happens in + * dlm_midcomms_commit_mhandle which is a must call if success + */ +#ifndef __CHECKER__ struct dlm_mhandle *dlm_midcomms_get_mhandle(int nodeid, int len, gfp_t allocation, char **ppc) { @@ -1127,6 +1128,7 @@ err: srcu_read_unlock(&nodes_srcu, idx); return NULL; } +#endif static void dlm_midcomms_commit_msg_3_2(struct dlm_mhandle *mh) { @@ -1136,6 +1138,10 @@ static void dlm_midcomms_commit_msg_3_2(struct dlm_mhandle *mh) dlm_lowcomms_commit_msg(mh->msg); } +/* avoid false positive for nodes_srcu, lock was happen in + * dlm_midcomms_get_mhandle + */ +#ifndef __CHECKER__ void dlm_midcomms_commit_mhandle(struct dlm_mhandle *mh) { switch (mh->node->version) { @@ -1157,6 +1163,7 @@ void dlm_midcomms_commit_mhandle(struct dlm_mhandle *mh) break; } } +#endif int dlm_midcomms_start(void) { @@ -1406,6 +1413,8 @@ int dlm_midcomms_close(int nodeid) if (nodeid == dlm_our_nodeid()) return 0; + dlm_stop_lockspaces_check(); + idx = srcu_read_lock(&nodes_srcu); /* Abort pending close/remove operation */ node = nodeid2node(nodeid, 0); @@ -1455,7 +1464,7 @@ static void midcomms_new_rawmsg_cb(void *data) switch (h->h_cmd) { case DLM_OPTS: if (!h->u.h_seq) - h->u.h_seq = rd->node->seq_send++; + h->u.h_seq = cpu_to_le32(rd->node->seq_send++); break; default: break; diff --git a/fs/dlm/plock.c b/fs/dlm/plock.c index c38b2b8ffd1d..0993eebf2060 100644 --- a/fs/dlm/plock.c +++ b/fs/dlm/plock.c @@ -13,26 +13,26 @@ #include "dlm_internal.h" #include "lockspace.h" -static spinlock_t ops_lock; -static struct list_head send_list; -static struct list_head recv_list; -static wait_queue_head_t send_wq; -static wait_queue_head_t recv_wq; +static DEFINE_SPINLOCK(ops_lock); +static LIST_HEAD(send_list); +static LIST_HEAD(recv_list); +static DECLARE_WAIT_QUEUE_HEAD(send_wq); +static DECLARE_WAIT_QUEUE_HEAD(recv_wq); -struct plock_op { - struct list_head list; - int done; - struct dlm_plock_info info; -}; - -struct plock_xop { - struct plock_op xop; - int (*callback)(struct file_lock *fl, int result); +struct plock_async_data { void *fl; void *file; struct file_lock flc; + int (*callback)(struct file_lock *fl, int result); }; +struct plock_op { + struct list_head list; + int done; + struct dlm_plock_info info; + /* if set indicates async handling */ + struct plock_async_data *data; +}; static inline void set_version(struct dlm_plock_info *info) { @@ -58,10 +58,15 @@ static int check_version(struct dlm_plock_info *info) return 0; } +static void dlm_release_plock_op(struct plock_op *op) +{ + kfree(op->data); + kfree(op); +} + static void send_op(struct plock_op *op) { set_version(&op->info); - INIT_LIST_HEAD(&op->list); spin_lock(&ops_lock); list_add_tail(&op->list, &send_list); spin_unlock(&ops_lock); @@ -101,22 +106,21 @@ static void do_unlock_close(struct dlm_ls *ls, u64 number, int dlm_posix_lock(dlm_lockspace_t *lockspace, u64 number, struct file *file, int cmd, struct file_lock *fl) { + struct plock_async_data *op_data; struct dlm_ls *ls; struct plock_op *op; - struct plock_xop *xop; int rv; ls = dlm_find_lockspace_local(lockspace); if (!ls) return -EINVAL; - xop = kzalloc(sizeof(*xop), GFP_NOFS); - if (!xop) { + op = kzalloc(sizeof(*op), GFP_NOFS); + if (!op) { rv = -ENOMEM; goto out; } - op = &xop->xop; op->info.optype = DLM_PLOCK_OP_LOCK; op->info.pid = fl->fl_pid; op->info.ex = (fl->fl_type == F_WRLCK); @@ -125,46 +129,49 @@ int dlm_posix_lock(dlm_lockspace_t *lockspace, u64 number, struct file *file, op->info.number = number; op->info.start = fl->fl_start; op->info.end = fl->fl_end; + /* async handling */ if (fl->fl_lmops && fl->fl_lmops->lm_grant) { + op_data = kzalloc(sizeof(*op_data), GFP_NOFS); + if (!op_data) { + dlm_release_plock_op(op); + rv = -ENOMEM; + goto out; + } + /* fl_owner is lockd which doesn't distinguish processes on the nfs client */ op->info.owner = (__u64) fl->fl_pid; - xop->callback = fl->fl_lmops->lm_grant; - locks_init_lock(&xop->flc); - locks_copy_lock(&xop->flc, fl); - xop->fl = fl; - xop->file = file; + op_data->callback = fl->fl_lmops->lm_grant; + locks_init_lock(&op_data->flc); + locks_copy_lock(&op_data->flc, fl); + op_data->fl = fl; + op_data->file = file; + + op->data = op_data; + + send_op(op); + rv = FILE_LOCK_DEFERRED; + goto out; } else { op->info.owner = (__u64)(long) fl->fl_owner; - xop->callback = NULL; } send_op(op); - if (xop->callback == NULL) { - rv = wait_event_interruptible(recv_wq, (op->done != 0)); - if (rv == -ERESTARTSYS) { - log_debug(ls, "dlm_posix_lock: wait killed %llx", - (unsigned long long)number); - spin_lock(&ops_lock); - list_del(&op->list); - spin_unlock(&ops_lock); - kfree(xop); - do_unlock_close(ls, number, file, fl); - goto out; - } - } else { - rv = FILE_LOCK_DEFERRED; + rv = wait_event_interruptible(recv_wq, (op->done != 0)); + if (rv == -ERESTARTSYS) { + spin_lock(&ops_lock); + list_del(&op->list); + spin_unlock(&ops_lock); + log_print("%s: wait interrupted %x %llx, op removed", + __func__, ls->ls_global_id, + (unsigned long long)number); + dlm_release_plock_op(op); + do_unlock_close(ls, number, file, fl); goto out; } - spin_lock(&ops_lock); - if (!list_empty(&op->list)) { - log_error(ls, "dlm_posix_lock: op on list %llx", - (unsigned long long)number); - list_del(&op->list); - } - spin_unlock(&ops_lock); + WARN_ON(!list_empty(&op->list)); rv = op->info.rv; @@ -174,7 +181,7 @@ int dlm_posix_lock(dlm_lockspace_t *lockspace, u64 number, struct file *file, (unsigned long long)number); } - kfree(xop); + dlm_release_plock_op(op); out: dlm_put_lockspace(ls); return rv; @@ -184,26 +191,20 @@ EXPORT_SYMBOL_GPL(dlm_posix_lock); /* Returns failure iff a successful lock operation should be canceled */ static int dlm_plock_callback(struct plock_op *op) { + struct plock_async_data *op_data = op->data; struct file *file; struct file_lock *fl; struct file_lock *flc; int (*notify)(struct file_lock *fl, int result) = NULL; - struct plock_xop *xop = (struct plock_xop *)op; int rv = 0; - spin_lock(&ops_lock); - if (!list_empty(&op->list)) { - log_print("dlm_plock_callback: op on list %llx", - (unsigned long long)op->info.number); - list_del(&op->list); - } - spin_unlock(&ops_lock); + WARN_ON(!list_empty(&op->list)); /* check if the following 2 are still valid or make a copy */ - file = xop->file; - flc = &xop->flc; - fl = xop->fl; - notify = xop->callback; + file = op_data->file; + flc = &op_data->flc; + fl = op_data->fl; + notify = op_data->callback; if (op->info.rv) { notify(fl, op->info.rv); @@ -234,7 +235,7 @@ static int dlm_plock_callback(struct plock_op *op) } out: - kfree(xop); + dlm_release_plock_op(op); return rv; } @@ -290,13 +291,7 @@ int dlm_posix_unlock(dlm_lockspace_t *lockspace, u64 number, struct file *file, send_op(op); wait_event(recv_wq, (op->done != 0)); - spin_lock(&ops_lock); - if (!list_empty(&op->list)) { - log_error(ls, "dlm_posix_unlock: op on list %llx", - (unsigned long long)number); - list_del(&op->list); - } - spin_unlock(&ops_lock); + WARN_ON(!list_empty(&op->list)); rv = op->info.rv; @@ -304,7 +299,7 @@ int dlm_posix_unlock(dlm_lockspace_t *lockspace, u64 number, struct file *file, rv = 0; out_free: - kfree(op); + dlm_release_plock_op(op); out: dlm_put_lockspace(ls); fl->fl_flags = fl_flags; @@ -344,13 +339,7 @@ int dlm_posix_get(dlm_lockspace_t *lockspace, u64 number, struct file *file, send_op(op); wait_event(recv_wq, (op->done != 0)); - spin_lock(&ops_lock); - if (!list_empty(&op->list)) { - log_error(ls, "dlm_posix_get: op on list %llx", - (unsigned long long)number); - list_del(&op->list); - } - spin_unlock(&ops_lock); + WARN_ON(!list_empty(&op->list)); /* info.rv from userspace is 1 for conflict, 0 for no-conflict, -ENOENT if there are no locks on the file */ @@ -370,7 +359,7 @@ int dlm_posix_get(dlm_lockspace_t *lockspace, u64 number, struct file *file, rv = 0; } - kfree(op); + dlm_release_plock_op(op); out: dlm_put_lockspace(ls); return rv; @@ -406,7 +395,7 @@ static ssize_t dev_read(struct file *file, char __user *u, size_t count, (the process did not make an unlock call). */ if (op->info.flags & DLM_PLOCK_FL_CLOSE) - kfree(op); + dlm_release_plock_op(op); if (copy_to_user(u, &info, sizeof(info))) return -EFAULT; @@ -418,9 +407,9 @@ static ssize_t dev_read(struct file *file, char __user *u, size_t count, static ssize_t dev_write(struct file *file, const char __user *u, size_t count, loff_t *ppos) { + struct plock_op *op = NULL, *iter; struct dlm_plock_info info; - struct plock_op *op; - int found = 0, do_callback = 0; + int do_callback = 0; if (count != sizeof(info)) return -EINVAL; @@ -432,31 +421,30 @@ static ssize_t dev_write(struct file *file, const char __user *u, size_t count, return -EINVAL; spin_lock(&ops_lock); - list_for_each_entry(op, &recv_list, list) { - if (op->info.fsid == info.fsid && - op->info.number == info.number && - op->info.owner == info.owner) { - struct plock_xop *xop = (struct plock_xop *)op; - list_del_init(&op->list); - memcpy(&op->info, &info, sizeof(info)); - if (xop->callback) + list_for_each_entry(iter, &recv_list, list) { + if (iter->info.fsid == info.fsid && + iter->info.number == info.number && + iter->info.owner == info.owner) { + list_del_init(&iter->list); + memcpy(&iter->info, &info, sizeof(info)); + if (iter->data) do_callback = 1; else - op->done = 1; - found = 1; + iter->done = 1; + op = iter; break; } } spin_unlock(&ops_lock); - if (found) { + if (op) { if (do_callback) dlm_plock_callback(op); else wake_up(&recv_wq); } else - log_print("dev_write no op %x %llx", info.fsid, - (unsigned long long)info.number); + log_print("%s: no op %x %llx - may got interrupted?", __func__, + info.fsid, (unsigned long long)info.number); return count; } @@ -492,12 +480,6 @@ int dlm_plock_init(void) { int rv; - spin_lock_init(&ops_lock); - INIT_LIST_HEAD(&send_list); - INIT_LIST_HEAD(&recv_list); - init_waitqueue_head(&send_wq); - init_waitqueue_head(&recv_wq); - rv = misc_register(&plock_dev_misc); if (rv) log_print("dlm_plock_init: misc_register failed %d", rv); diff --git a/fs/dlm/rcom.c b/fs/dlm/rcom.c index 5821b777a1a7..f19860315043 100644 --- a/fs/dlm/rcom.c +++ b/fs/dlm/rcom.c @@ -34,16 +34,16 @@ static void _create_rcom(struct dlm_ls *ls, int to_nodeid, int type, int len, rc = (struct dlm_rcom *) mb; - rc->rc_header.h_version = (DLM_HEADER_MAJOR | DLM_HEADER_MINOR); - rc->rc_header.u.h_lockspace = ls->ls_global_id; - rc->rc_header.h_nodeid = dlm_our_nodeid(); - rc->rc_header.h_length = mb_len; + rc->rc_header.h_version = cpu_to_le32(DLM_HEADER_MAJOR | DLM_HEADER_MINOR); + rc->rc_header.u.h_lockspace = cpu_to_le32(ls->ls_global_id); + rc->rc_header.h_nodeid = cpu_to_le32(dlm_our_nodeid()); + rc->rc_header.h_length = cpu_to_le16(mb_len); rc->rc_header.h_cmd = DLM_RCOM; - rc->rc_type = type; + rc->rc_type = cpu_to_le32(type); spin_lock(&ls->ls_recover_lock); - rc->rc_seq = ls->ls_recover_seq; + rc->rc_seq = cpu_to_le64(ls->ls_recover_seq); spin_unlock(&ls->ls_recover_lock); *rc_ret = rc; @@ -91,13 +91,11 @@ static int create_rcom_stateless(struct dlm_ls *ls, int to_nodeid, int type, static void send_rcom(struct dlm_mhandle *mh, struct dlm_rcom *rc) { - dlm_rcom_out(rc); dlm_midcomms_commit_mhandle(mh); } static void send_rcom_stateless(struct dlm_msg *msg, struct dlm_rcom *rc) { - dlm_rcom_out(rc); dlm_lowcomms_commit_msg(msg); dlm_lowcomms_put_msg(msg); } @@ -127,10 +125,10 @@ static int check_rcom_config(struct dlm_ls *ls, struct dlm_rcom *rc, int nodeid) { struct rcom_config *rf = (struct rcom_config *) rc->rc_buf; - if ((rc->rc_header.h_version & 0xFFFF0000) != DLM_HEADER_MAJOR) { + if ((le32_to_cpu(rc->rc_header.h_version) & 0xFFFF0000) != DLM_HEADER_MAJOR) { log_error(ls, "version mismatch: %x nodeid %d: %x", DLM_HEADER_MAJOR | DLM_HEADER_MINOR, nodeid, - rc->rc_header.h_version); + le32_to_cpu(rc->rc_header.h_version)); return -EPROTO; } @@ -145,10 +143,10 @@ static int check_rcom_config(struct dlm_ls *ls, struct dlm_rcom *rc, int nodeid) return 0; } -static void allow_sync_reply(struct dlm_ls *ls, uint64_t *new_seq) +static void allow_sync_reply(struct dlm_ls *ls, __le64 *new_seq) { spin_lock(&ls->ls_rcom_spin); - *new_seq = ++ls->ls_rcom_seq; + *new_seq = cpu_to_le64(++ls->ls_rcom_seq); set_bit(LSFL_RCOM_WAIT, &ls->ls_flags); spin_unlock(&ls->ls_rcom_spin); } @@ -182,7 +180,7 @@ int dlm_rcom_status(struct dlm_ls *ls, int nodeid, uint32_t status_flags) if (nodeid == dlm_our_nodeid()) { rc = ls->ls_recover_buf; - rc->rc_result = dlm_recover_status(ls); + rc->rc_result = cpu_to_le32(dlm_recover_status(ls)); goto out; } @@ -208,7 +206,7 @@ retry: rc = ls->ls_recover_buf; - if (rc->rc_result == -ESRCH) { + if (rc->rc_result == cpu_to_le32(-ESRCH)) { /* we pretend the remote lockspace exists with 0 status */ log_debug(ls, "remote node %d not ready", nodeid); rc->rc_result = 0; @@ -227,7 +225,7 @@ static void receive_rcom_status(struct dlm_ls *ls, struct dlm_rcom *rc_in) struct dlm_rcom *rc; struct rcom_status *rs; uint32_t status; - int nodeid = rc_in->rc_header.h_nodeid; + int nodeid = le32_to_cpu(rc_in->rc_header.h_nodeid); int len = sizeof(struct rcom_config); struct dlm_msg *msg; int num_slots = 0; @@ -259,7 +257,7 @@ static void receive_rcom_status(struct dlm_ls *ls, struct dlm_rcom *rc_in) rc->rc_id = rc_in->rc_id; rc->rc_seq_reply = rc_in->rc_seq; - rc->rc_result = status; + rc->rc_result = cpu_to_le32(status); set_rcom_config(ls, (struct rcom_config *)rc->rc_buf, num_slots); @@ -287,14 +285,16 @@ static void receive_sync_reply(struct dlm_ls *ls, struct dlm_rcom *rc_in) { spin_lock(&ls->ls_rcom_spin); if (!test_bit(LSFL_RCOM_WAIT, &ls->ls_flags) || - rc_in->rc_id != ls->ls_rcom_seq) { + le64_to_cpu(rc_in->rc_id) != ls->ls_rcom_seq) { log_debug(ls, "reject reply %d from %d seq %llx expect %llx", - rc_in->rc_type, rc_in->rc_header.h_nodeid, - (unsigned long long)rc_in->rc_id, + le32_to_cpu(rc_in->rc_type), + le32_to_cpu(rc_in->rc_header.h_nodeid), + (unsigned long long)le64_to_cpu(rc_in->rc_id), (unsigned long long)ls->ls_rcom_seq); goto out; } - memcpy(ls->ls_recover_buf, rc_in, rc_in->rc_header.h_length); + memcpy(ls->ls_recover_buf, rc_in, + le16_to_cpu(rc_in->rc_header.h_length)); set_bit(LSFL_RCOM_READY, &ls->ls_flags); clear_bit(LSFL_RCOM_WAIT, &ls->ls_flags); wake_up(&ls->ls_wait_general); @@ -336,8 +336,9 @@ static void receive_rcom_names(struct dlm_ls *ls, struct dlm_rcom *rc_in) int error, inlen, outlen, nodeid; struct dlm_msg *msg; - nodeid = rc_in->rc_header.h_nodeid; - inlen = rc_in->rc_header.h_length - sizeof(struct dlm_rcom); + nodeid = le32_to_cpu(rc_in->rc_header.h_nodeid); + inlen = le16_to_cpu(rc_in->rc_header.h_length) - + sizeof(struct dlm_rcom); outlen = DLM_MAX_APP_BUFSIZE - sizeof(struct dlm_rcom); error = create_rcom_stateless(ls, nodeid, DLM_RCOM_NAMES_REPLY, outlen, @@ -364,7 +365,7 @@ int dlm_send_rcom_lookup(struct dlm_rsb *r, int dir_nodeid) if (error) goto out; memcpy(rc->rc_buf, r->res_name, r->res_length); - rc->rc_id = (unsigned long) r->res_id; + rc->rc_id = cpu_to_le64(r->res_id); send_rcom(mh, rc); out: @@ -375,11 +376,12 @@ static void receive_rcom_lookup(struct dlm_ls *ls, struct dlm_rcom *rc_in) { struct dlm_rcom *rc; struct dlm_mhandle *mh; - int error, ret_nodeid, nodeid = rc_in->rc_header.h_nodeid; - int len = rc_in->rc_header.h_length - sizeof(struct dlm_rcom); + int error, ret_nodeid, nodeid = le32_to_cpu(rc_in->rc_header.h_nodeid); + int len = le16_to_cpu(rc_in->rc_header.h_length) - + sizeof(struct dlm_rcom); /* Old code would send this special id to trigger a debug dump. */ - if (rc_in->rc_id == 0xFFFFFFFF) { + if (rc_in->rc_id == cpu_to_le64(0xFFFFFFFF)) { log_error(ls, "receive_rcom_lookup dump from %d", nodeid); dlm_dump_rsb_name(ls, rc_in->rc_buf, len); return; @@ -393,7 +395,7 @@ static void receive_rcom_lookup(struct dlm_ls *ls, struct dlm_rcom *rc_in) DLM_LU_RECOVER_MASTER, &ret_nodeid, NULL); if (error) ret_nodeid = error; - rc->rc_result = ret_nodeid; + rc->rc_result = cpu_to_le32(ret_nodeid); rc->rc_id = rc_in->rc_id; rc->rc_seq_reply = rc_in->rc_seq; @@ -452,7 +454,7 @@ int dlm_send_rcom_lock(struct dlm_rsb *r, struct dlm_lkb *lkb) rl = (struct rcom_lock *) rc->rc_buf; pack_rcom_lock(r, lkb, rl); - rc->rc_id = (unsigned long) r; + rc->rc_id = cpu_to_le64((uintptr_t)r); send_rcom(mh, rc); out: @@ -464,7 +466,7 @@ static void receive_rcom_lock(struct dlm_ls *ls, struct dlm_rcom *rc_in) { struct dlm_rcom *rc; struct dlm_mhandle *mh; - int error, nodeid = rc_in->rc_header.h_nodeid; + int error, nodeid = le32_to_cpu(rc_in->rc_header.h_nodeid); dlm_recover_master_copy(ls, rc_in); @@ -500,21 +502,20 @@ int dlm_send_ls_not_ready(int nodeid, struct dlm_rcom *rc_in) rc = (struct dlm_rcom *) mb; - rc->rc_header.h_version = (DLM_HEADER_MAJOR | DLM_HEADER_MINOR); + rc->rc_header.h_version = cpu_to_le32(DLM_HEADER_MAJOR | DLM_HEADER_MINOR); rc->rc_header.u.h_lockspace = rc_in->rc_header.u.h_lockspace; - rc->rc_header.h_nodeid = dlm_our_nodeid(); - rc->rc_header.h_length = mb_len; + rc->rc_header.h_nodeid = cpu_to_le32(dlm_our_nodeid()); + rc->rc_header.h_length = cpu_to_le16(mb_len); rc->rc_header.h_cmd = DLM_RCOM; - rc->rc_type = DLM_RCOM_STATUS_REPLY; + rc->rc_type = cpu_to_le32(DLM_RCOM_STATUS_REPLY); rc->rc_id = rc_in->rc_id; rc->rc_seq_reply = rc_in->rc_seq; - rc->rc_result = -ESRCH; + rc->rc_result = cpu_to_le32(-ESRCH); rf = (struct rcom_config *) rc->rc_buf; rf->rf_lvblen = cpu_to_le32(~0U); - dlm_rcom_out(rc); dlm_midcomms_commit_mhandle(mh); return 0; @@ -573,27 +574,27 @@ void dlm_receive_rcom(struct dlm_ls *ls, struct dlm_rcom *rc, int nodeid) uint64_t seq; switch (rc->rc_type) { - case DLM_RCOM_STATUS_REPLY: + case cpu_to_le32(DLM_RCOM_STATUS_REPLY): reply = 1; break; - case DLM_RCOM_NAMES: + case cpu_to_le32(DLM_RCOM_NAMES): names = 1; break; - case DLM_RCOM_NAMES_REPLY: + case cpu_to_le32(DLM_RCOM_NAMES_REPLY): names = 1; reply = 1; break; - case DLM_RCOM_LOOKUP: + case cpu_to_le32(DLM_RCOM_LOOKUP): lookup = 1; break; - case DLM_RCOM_LOOKUP_REPLY: + case cpu_to_le32(DLM_RCOM_LOOKUP_REPLY): lookup = 1; reply = 1; break; - case DLM_RCOM_LOCK: + case cpu_to_le32(DLM_RCOM_LOCK): lock = 1; break; - case DLM_RCOM_LOCK_REPLY: + case cpu_to_le32(DLM_RCOM_LOCK_REPLY): lock = 1; reply = 1; break; @@ -605,10 +606,10 @@ void dlm_receive_rcom(struct dlm_ls *ls, struct dlm_rcom *rc, int nodeid) seq = ls->ls_recover_seq; spin_unlock(&ls->ls_recover_lock); - if (stop && (rc->rc_type != DLM_RCOM_STATUS)) + if (stop && (rc->rc_type != cpu_to_le32(DLM_RCOM_STATUS))) goto ignore; - if (reply && (rc->rc_seq_reply != seq)) + if (reply && (le64_to_cpu(rc->rc_seq_reply) != seq)) goto ignore; if (!(status & DLM_RS_NODES) && (names || lookup || lock)) @@ -618,59 +619,60 @@ void dlm_receive_rcom(struct dlm_ls *ls, struct dlm_rcom *rc, int nodeid) goto ignore; switch (rc->rc_type) { - case DLM_RCOM_STATUS: + case cpu_to_le32(DLM_RCOM_STATUS): receive_rcom_status(ls, rc); break; - case DLM_RCOM_NAMES: + case cpu_to_le32(DLM_RCOM_NAMES): receive_rcom_names(ls, rc); break; - case DLM_RCOM_LOOKUP: + case cpu_to_le32(DLM_RCOM_LOOKUP): receive_rcom_lookup(ls, rc); break; - case DLM_RCOM_LOCK: - if (rc->rc_header.h_length < lock_size) + case cpu_to_le32(DLM_RCOM_LOCK): + if (le16_to_cpu(rc->rc_header.h_length) < lock_size) goto Eshort; receive_rcom_lock(ls, rc); break; - case DLM_RCOM_STATUS_REPLY: + case cpu_to_le32(DLM_RCOM_STATUS_REPLY): receive_sync_reply(ls, rc); break; - case DLM_RCOM_NAMES_REPLY: + case cpu_to_le32(DLM_RCOM_NAMES_REPLY): receive_sync_reply(ls, rc); break; - case DLM_RCOM_LOOKUP_REPLY: + case cpu_to_le32(DLM_RCOM_LOOKUP_REPLY): receive_rcom_lookup_reply(ls, rc); break; - case DLM_RCOM_LOCK_REPLY: - if (rc->rc_header.h_length < lock_size) + case cpu_to_le32(DLM_RCOM_LOCK_REPLY): + if (le16_to_cpu(rc->rc_header.h_length) < lock_size) goto Eshort; dlm_recover_process_copy(ls, rc); break; default: - log_error(ls, "receive_rcom bad type %d", rc->rc_type); + log_error(ls, "receive_rcom bad type %d", + le32_to_cpu(rc->rc_type)); } return; ignore: log_limit(ls, "dlm_receive_rcom ignore msg %d " "from %d %llu %llu recover seq %llu sts %x gen %u", - rc->rc_type, + le32_to_cpu(rc->rc_type), nodeid, - (unsigned long long)rc->rc_seq, - (unsigned long long)rc->rc_seq_reply, + (unsigned long long)le64_to_cpu(rc->rc_seq), + (unsigned long long)le64_to_cpu(rc->rc_seq_reply), (unsigned long long)seq, status, ls->ls_generation); return; Eshort: log_error(ls, "recovery message %d from %d is too short", - rc->rc_type, nodeid); + le32_to_cpu(rc->rc_type), nodeid); } diff --git a/fs/dlm/recover.c b/fs/dlm/recover.c index 8928e99dfd47..ccff1791803f 100644 --- a/fs/dlm/recover.c +++ b/fs/dlm/recover.c @@ -114,7 +114,7 @@ static int wait_status_all(struct dlm_ls *ls, uint32_t wait_status, if (save_slots) dlm_slot_save(ls, rc, memb); - if (rc->rc_result & wait_status) + if (le32_to_cpu(rc->rc_result) & wait_status) break; if (delay < 1000) delay += 20; @@ -141,7 +141,7 @@ static int wait_status_low(struct dlm_ls *ls, uint32_t wait_status, if (error) break; - if (rc->rc_result & wait_status) + if (le32_to_cpu(rc->rc_result) & wait_status) break; if (delay < 1000) delay += 20; @@ -568,14 +568,14 @@ int dlm_recover_master_reply(struct dlm_ls *ls, struct dlm_rcom *rc) struct dlm_rsb *r; int ret_nodeid, new_master; - r = recover_idr_find(ls, rc->rc_id); + r = recover_idr_find(ls, le64_to_cpu(rc->rc_id)); if (!r) { log_error(ls, "dlm_recover_master_reply no id %llx", - (unsigned long long)rc->rc_id); + (unsigned long long)le64_to_cpu(rc->rc_id)); goto out; } - ret_nodeid = rc->rc_result; + ret_nodeid = le32_to_cpu(rc->rc_result); if (ret_nodeid == dlm_our_nodeid()) new_master = 0; @@ -732,10 +732,9 @@ void dlm_recovered_lock(struct dlm_rsb *r) static void recover_lvb(struct dlm_rsb *r) { - struct dlm_lkb *lkb, *high_lkb = NULL; + struct dlm_lkb *big_lkb = NULL, *iter, *high_lkb = NULL; uint32_t high_seq = 0; int lock_lvb_exists = 0; - int big_lock_exists = 0; int lvblen = r->res_ls->ls_lvblen; if (!rsb_flag(r, RSB_NEW_MASTER2) && @@ -751,37 +750,37 @@ static void recover_lvb(struct dlm_rsb *r) /* we are the new master, so figure out if VALNOTVALID should be set, and set the rsb lvb from the best lkb available. */ - list_for_each_entry(lkb, &r->res_grantqueue, lkb_statequeue) { - if (!(lkb->lkb_exflags & DLM_LKF_VALBLK)) + list_for_each_entry(iter, &r->res_grantqueue, lkb_statequeue) { + if (!(iter->lkb_exflags & DLM_LKF_VALBLK)) continue; lock_lvb_exists = 1; - if (lkb->lkb_grmode > DLM_LOCK_CR) { - big_lock_exists = 1; + if (iter->lkb_grmode > DLM_LOCK_CR) { + big_lkb = iter; goto setflag; } - if (((int)lkb->lkb_lvbseq - (int)high_seq) >= 0) { - high_lkb = lkb; - high_seq = lkb->lkb_lvbseq; + if (((int)iter->lkb_lvbseq - (int)high_seq) >= 0) { + high_lkb = iter; + high_seq = iter->lkb_lvbseq; } } - list_for_each_entry(lkb, &r->res_convertqueue, lkb_statequeue) { - if (!(lkb->lkb_exflags & DLM_LKF_VALBLK)) + list_for_each_entry(iter, &r->res_convertqueue, lkb_statequeue) { + if (!(iter->lkb_exflags & DLM_LKF_VALBLK)) continue; lock_lvb_exists = 1; - if (lkb->lkb_grmode > DLM_LOCK_CR) { - big_lock_exists = 1; + if (iter->lkb_grmode > DLM_LOCK_CR) { + big_lkb = iter; goto setflag; } - if (((int)lkb->lkb_lvbseq - (int)high_seq) >= 0) { - high_lkb = lkb; - high_seq = lkb->lkb_lvbseq; + if (((int)iter->lkb_lvbseq - (int)high_seq) >= 0) { + high_lkb = iter; + high_seq = iter->lkb_lvbseq; } } @@ -790,7 +789,7 @@ static void recover_lvb(struct dlm_rsb *r) goto out; /* lvb is invalidated if only NL/CR locks remain */ - if (!big_lock_exists) + if (!big_lkb) rsb_set_flag(r, RSB_VALNOTVALID); if (!r->res_lvbptr) { @@ -799,9 +798,9 @@ static void recover_lvb(struct dlm_rsb *r) goto out; } - if (big_lock_exists) { - r->res_lvbseq = lkb->lkb_lvbseq; - memcpy(r->res_lvbptr, lkb->lkb_lvbptr, lvblen); + if (big_lkb) { + r->res_lvbseq = big_lkb->lkb_lvbseq; + memcpy(r->res_lvbptr, big_lkb->lkb_lvbptr, lvblen); } else if (high_lkb) { r->res_lvbseq = high_lkb->lkb_lvbseq; memcpy(r->res_lvbptr, high_lkb->lkb_lvbptr, lvblen); diff --git a/fs/dlm/requestqueue.c b/fs/dlm/requestqueue.c index ccb5307c21e9..036a9a0078f6 100644 --- a/fs/dlm/requestqueue.c +++ b/fs/dlm/requestqueue.c @@ -14,6 +14,7 @@ #include "dir.h" #include "config.h" #include "requestqueue.h" +#include "util.h" struct rq_entry { struct list_head list; @@ -32,7 +33,8 @@ struct rq_entry { void dlm_add_requestqueue(struct dlm_ls *ls, int nodeid, struct dlm_message *ms) { struct rq_entry *e; - int length = ms->m_header.h_length - sizeof(struct dlm_message); + int length = le16_to_cpu(ms->m_header.h_length) - + sizeof(struct dlm_message); e = kmalloc(sizeof(struct rq_entry) + length, GFP_NOFS); if (!e) { @@ -42,7 +44,7 @@ void dlm_add_requestqueue(struct dlm_ls *ls, int nodeid, struct dlm_message *ms) e->recover_seq = ls->ls_recover_seq & 0xFFFFFFFF; e->nodeid = nodeid; - memcpy(&e->request, ms, ms->m_header.h_length); + memcpy(&e->request, ms, le16_to_cpu(ms->m_header.h_length)); atomic_inc(&ls->ls_requestqueue_cnt); mutex_lock(&ls->ls_requestqueue_mutex); @@ -82,8 +84,10 @@ int dlm_process_requestqueue(struct dlm_ls *ls) log_limit(ls, "dlm_process_requestqueue msg %d from %d " "lkid %x remid %x result %d seq %u", - ms->m_type, ms->m_header.h_nodeid, - ms->m_lkid, ms->m_remid, ms->m_result, + le32_to_cpu(ms->m_type), + le32_to_cpu(ms->m_header.h_nodeid), + le32_to_cpu(ms->m_lkid), le32_to_cpu(ms->m_remid), + from_dlm_errno(le32_to_cpu(ms->m_result)), e->recover_seq); dlm_receive_message_saved(ls, &e->request, e->recover_seq); @@ -124,7 +128,7 @@ void dlm_wait_requestqueue(struct dlm_ls *ls) static int purge_request(struct dlm_ls *ls, struct dlm_message *ms, int nodeid) { - uint32_t type = ms->m_type; + __le32 type = ms->m_type; /* the ls is being cleaned up and freed by release_lockspace */ if (!atomic_read(&ls->ls_count)) @@ -136,9 +140,9 @@ static int purge_request(struct dlm_ls *ls, struct dlm_message *ms, int nodeid) /* directory operations are always purged because the directory is always rebuilt during recovery and the lookups resent */ - if (type == DLM_MSG_REMOVE || - type == DLM_MSG_LOOKUP || - type == DLM_MSG_LOOKUP_REPLY) + if (type == cpu_to_le32(DLM_MSG_REMOVE) || + type == cpu_to_le32(DLM_MSG_LOOKUP) || + type == cpu_to_le32(DLM_MSG_LOOKUP_REPLY)) return 1; if (!dlm_no_directory(ls)) diff --git a/fs/dlm/user.c b/fs/dlm/user.c index e5cefa90b1ce..1060b24f18d4 100644 --- a/fs/dlm/user.c +++ b/fs/dlm/user.c @@ -108,11 +108,11 @@ static void compat_input(struct dlm_write_request *kb, kb->i.lock.parent = kb32->i.lock.parent; kb->i.lock.xid = kb32->i.lock.xid; kb->i.lock.timeout = kb32->i.lock.timeout; - kb->i.lock.castparam = (void *)(long)kb32->i.lock.castparam; - kb->i.lock.castaddr = (void *)(long)kb32->i.lock.castaddr; - kb->i.lock.bastparam = (void *)(long)kb32->i.lock.bastparam; - kb->i.lock.bastaddr = (void *)(long)kb32->i.lock.bastaddr; - kb->i.lock.lksb = (void *)(long)kb32->i.lock.lksb; + kb->i.lock.castparam = (__user void *)(long)kb32->i.lock.castparam; + kb->i.lock.castaddr = (__user void *)(long)kb32->i.lock.castaddr; + kb->i.lock.bastparam = (__user void *)(long)kb32->i.lock.bastparam; + kb->i.lock.bastaddr = (__user void *)(long)kb32->i.lock.bastaddr; + kb->i.lock.lksb = (__user void *)(long)kb32->i.lock.lksb; memcpy(kb->i.lock.lvb, kb32->i.lock.lvb, DLM_USER_LVB_LEN); memcpy(kb->i.lock.name, kb32->i.lock.name, namelen); } @@ -127,9 +127,9 @@ static void compat_output(struct dlm_lock_result *res, res32->version[1] = res->version[1]; res32->version[2] = res->version[2]; - res32->user_astaddr = (__u32)(long)res->user_astaddr; - res32->user_astparam = (__u32)(long)res->user_astparam; - res32->user_lksb = (__u32)(long)res->user_lksb; + res32->user_astaddr = (__u32)(__force long)res->user_astaddr; + res32->user_astparam = (__u32)(__force long)res->user_astparam; + res32->user_lksb = (__u32)(__force long)res->user_lksb; res32->bast_mode = res->bast_mode; res32->lvb_offset = res->lvb_offset; diff --git a/fs/dlm/util.c b/fs/dlm/util.c index 58acbcc2081a..f2bc401f312f 100644 --- a/fs/dlm/util.c +++ b/fs/dlm/util.c @@ -20,28 +20,10 @@ #define DLM_ERRNO_ETIMEDOUT 110 #define DLM_ERRNO_EINPROGRESS 115 -void header_out(struct dlm_header *hd) -{ - hd->h_version = cpu_to_le32(hd->h_version); - /* does it for others u32 in union as well */ - hd->u.h_lockspace = cpu_to_le32(hd->u.h_lockspace); - hd->h_nodeid = cpu_to_le32(hd->h_nodeid); - hd->h_length = cpu_to_le16(hd->h_length); -} - -void header_in(struct dlm_header *hd) -{ - hd->h_version = le32_to_cpu(hd->h_version); - /* does it for others u32 in union as well */ - hd->u.h_lockspace = le32_to_cpu(hd->u.h_lockspace); - hd->h_nodeid = le32_to_cpu(hd->h_nodeid); - hd->h_length = le16_to_cpu(hd->h_length); -} - /* higher errno values are inconsistent across architectures, so select one set of values for on the wire */ -static int to_dlm_errno(int err) +int to_dlm_errno(int err) { switch (err) { case -EDEADLK: @@ -62,7 +44,7 @@ static int to_dlm_errno(int err) return err; } -static int from_dlm_errno(int err) +int from_dlm_errno(int err) { switch (err) { case -DLM_ERRNO_EDEADLK: @@ -82,73 +64,3 @@ static int from_dlm_errno(int err) } return err; } - -void dlm_message_out(struct dlm_message *ms) -{ - header_out(&ms->m_header); - - ms->m_type = cpu_to_le32(ms->m_type); - ms->m_nodeid = cpu_to_le32(ms->m_nodeid); - ms->m_pid = cpu_to_le32(ms->m_pid); - ms->m_lkid = cpu_to_le32(ms->m_lkid); - ms->m_remid = cpu_to_le32(ms->m_remid); - ms->m_parent_lkid = cpu_to_le32(ms->m_parent_lkid); - ms->m_parent_remid = cpu_to_le32(ms->m_parent_remid); - ms->m_exflags = cpu_to_le32(ms->m_exflags); - ms->m_sbflags = cpu_to_le32(ms->m_sbflags); - ms->m_flags = cpu_to_le32(ms->m_flags); - ms->m_lvbseq = cpu_to_le32(ms->m_lvbseq); - ms->m_hash = cpu_to_le32(ms->m_hash); - ms->m_status = cpu_to_le32(ms->m_status); - ms->m_grmode = cpu_to_le32(ms->m_grmode); - ms->m_rqmode = cpu_to_le32(ms->m_rqmode); - ms->m_bastmode = cpu_to_le32(ms->m_bastmode); - ms->m_asts = cpu_to_le32(ms->m_asts); - ms->m_result = cpu_to_le32(to_dlm_errno(ms->m_result)); -} - -void dlm_message_in(struct dlm_message *ms) -{ - header_in(&ms->m_header); - - ms->m_type = le32_to_cpu(ms->m_type); - ms->m_nodeid = le32_to_cpu(ms->m_nodeid); - ms->m_pid = le32_to_cpu(ms->m_pid); - ms->m_lkid = le32_to_cpu(ms->m_lkid); - ms->m_remid = le32_to_cpu(ms->m_remid); - ms->m_parent_lkid = le32_to_cpu(ms->m_parent_lkid); - ms->m_parent_remid = le32_to_cpu(ms->m_parent_remid); - ms->m_exflags = le32_to_cpu(ms->m_exflags); - ms->m_sbflags = le32_to_cpu(ms->m_sbflags); - ms->m_flags = le32_to_cpu(ms->m_flags); - ms->m_lvbseq = le32_to_cpu(ms->m_lvbseq); - ms->m_hash = le32_to_cpu(ms->m_hash); - ms->m_status = le32_to_cpu(ms->m_status); - ms->m_grmode = le32_to_cpu(ms->m_grmode); - ms->m_rqmode = le32_to_cpu(ms->m_rqmode); - ms->m_bastmode = le32_to_cpu(ms->m_bastmode); - ms->m_asts = le32_to_cpu(ms->m_asts); - ms->m_result = from_dlm_errno(le32_to_cpu(ms->m_result)); -} - -void dlm_rcom_out(struct dlm_rcom *rc) -{ - header_out(&rc->rc_header); - - rc->rc_type = cpu_to_le32(rc->rc_type); - rc->rc_result = cpu_to_le32(rc->rc_result); - rc->rc_id = cpu_to_le64(rc->rc_id); - rc->rc_seq = cpu_to_le64(rc->rc_seq); - rc->rc_seq_reply = cpu_to_le64(rc->rc_seq_reply); -} - -void dlm_rcom_in(struct dlm_rcom *rc) -{ - header_in(&rc->rc_header); - - rc->rc_type = le32_to_cpu(rc->rc_type); - rc->rc_result = le32_to_cpu(rc->rc_result); - rc->rc_id = le64_to_cpu(rc->rc_id); - rc->rc_seq = le64_to_cpu(rc->rc_seq); - rc->rc_seq_reply = le64_to_cpu(rc->rc_seq_reply); -} diff --git a/fs/dlm/util.h b/fs/dlm/util.h index d46f23c7a6a0..b6a4b8adca8d 100644 --- a/fs/dlm/util.h +++ b/fs/dlm/util.h @@ -11,12 +11,8 @@ #ifndef __UTIL_DOT_H__ #define __UTIL_DOT_H__ -void dlm_message_out(struct dlm_message *ms); -void dlm_message_in(struct dlm_message *ms); -void dlm_rcom_out(struct dlm_rcom *rc); -void dlm_rcom_in(struct dlm_rcom *rc); -void header_out(struct dlm_header *hd); -void header_in(struct dlm_header *hd); +int to_dlm_errno(int err); +int from_dlm_errno(int err); #endif diff --git a/fs/ecryptfs/mmap.c b/fs/ecryptfs/mmap.c index 9ad61b582f07..19af229eb7ca 100644 --- a/fs/ecryptfs/mmap.c +++ b/fs/ecryptfs/mmap.c @@ -170,16 +170,17 @@ out: } /** - * ecryptfs_readpage + * ecryptfs_read_folio * @file: An eCryptfs file - * @page: Page from eCryptfs inode mapping into which to stick the read data + * @folio: Folio from eCryptfs inode mapping into which to stick the read data * - * Read in a page, decrypting if necessary. + * Read in a folio, decrypting if necessary. * * Returns zero on success; non-zero on error. */ -static int ecryptfs_readpage(struct file *file, struct page *page) +static int ecryptfs_read_folio(struct file *file, struct folio *folio) { + struct page *page = &folio->page; struct ecryptfs_crypt_stat *crypt_stat = &ecryptfs_inode_to_private(page->mapping->host)->crypt_stat; int rc = 0; @@ -264,7 +265,7 @@ out: */ static int ecryptfs_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, + loff_t pos, unsigned len, struct page **pagep, void **fsdata) { pgoff_t index = pos >> PAGE_SHIFT; @@ -272,7 +273,7 @@ static int ecryptfs_write_begin(struct file *file, loff_t prev_page_end_size; int rc = 0; - page = grab_cache_page_write_begin(mapping, index, flags); + page = grab_cache_page_write_begin(mapping, index); if (!page) return -ENOMEM; *pagep = page; @@ -549,7 +550,7 @@ const struct address_space_operations ecryptfs_aops = { .invalidate_folio = block_invalidate_folio, #endif .writepage = ecryptfs_writepage, - .readpage = ecryptfs_readpage, + .read_folio = ecryptfs_read_folio, .write_begin = ecryptfs_write_begin, .write_end = ecryptfs_write_end, .bmap = ecryptfs_bmap, diff --git a/fs/efs/inode.c b/fs/efs/inode.c index 89e73a6f0d36..3ba94bb005a6 100644 --- a/fs/efs/inode.c +++ b/fs/efs/inode.c @@ -14,16 +14,18 @@ #include "efs.h" #include <linux/efs_fs_sb.h> -static int efs_readpage(struct file *file, struct page *page) +static int efs_read_folio(struct file *file, struct folio *folio) { - return block_read_full_page(page,efs_get_block); + return block_read_full_folio(folio, efs_get_block); } + static sector_t _efs_bmap(struct address_space *mapping, sector_t block) { return generic_block_bmap(mapping,block,efs_get_block); } + static const struct address_space_operations efs_aops = { - .readpage = efs_readpage, + .read_folio = efs_read_folio, .bmap = _efs_bmap }; diff --git a/fs/efs/symlink.c b/fs/efs/symlink.c index 923eb91654d5..3b03a573cb1a 100644 --- a/fs/efs/symlink.c +++ b/fs/efs/symlink.c @@ -12,8 +12,9 @@ #include <linux/buffer_head.h> #include "efs.h" -static int efs_symlink_readpage(struct file *file, struct page *page) +static int efs_symlink_read_folio(struct file *file, struct folio *folio) { + struct page *page = &folio->page; char *link = page_address(page); struct buffer_head * bh; struct inode * inode = page->mapping->host; @@ -49,5 +50,5 @@ fail: } const struct address_space_operations efs_symlink_aops = { - .readpage = efs_symlink_readpage + .read_folio = efs_symlink_read_folio }; diff --git a/fs/erofs/Kconfig b/fs/erofs/Kconfig index f57255ab88ed..85490370e0ca 100644 --- a/fs/erofs/Kconfig +++ b/fs/erofs/Kconfig @@ -98,3 +98,13 @@ config EROFS_FS_ZIP_LZMA systems will be readable without selecting this option. If unsure, say N. + +config EROFS_FS_ONDEMAND + bool "EROFS fscache-based on-demand read support" + depends on CACHEFILES_ONDEMAND && (EROFS_FS=m && FSCACHE || EROFS_FS=y && FSCACHE=y) + default n + help + This permits EROFS to use fscache-backed data blobs with on-demand + read support. + + If unsure, say N. diff --git a/fs/erofs/Makefile b/fs/erofs/Makefile index 8a3317e38e5a..99bbc597a3e9 100644 --- a/fs/erofs/Makefile +++ b/fs/erofs/Makefile @@ -5,3 +5,4 @@ erofs-objs := super.o inode.o data.o namei.o dir.o utils.o pcpubuf.o sysfs.o erofs-$(CONFIG_EROFS_FS_XATTR) += xattr.o erofs-$(CONFIG_EROFS_FS_ZIP) += decompressor.o zmap.o zdata.o erofs-$(CONFIG_EROFS_FS_ZIP_LZMA) += decompressor_lzma.o +erofs-$(CONFIG_EROFS_FS_ONDEMAND) += fscache.o diff --git a/fs/erofs/data.c b/fs/erofs/data.c index 780db1e5f4b7..fbb037ba326e 100644 --- a/fs/erofs/data.c +++ b/fs/erofs/data.c @@ -6,6 +6,7 @@ */ #include "internal.h" #include <linux/prefetch.h> +#include <linux/sched/mm.h> #include <linux/dax.h> #include <trace/events/erofs.h> @@ -35,14 +36,20 @@ void *erofs_bread(struct erofs_buf *buf, struct inode *inode, erofs_off_t offset = blknr_to_addr(blkaddr); pgoff_t index = offset >> PAGE_SHIFT; struct page *page = buf->page; + struct folio *folio; + unsigned int nofs_flag; if (!page || page->index != index) { erofs_put_metabuf(buf); - page = read_cache_page_gfp(mapping, index, - mapping_gfp_constraint(mapping, ~__GFP_FS)); - if (IS_ERR(page)) - return page; + + nofs_flag = memalloc_nofs_save(); + folio = read_cache_folio(mapping, index, NULL, NULL); + memalloc_nofs_restore(nofs_flag); + if (IS_ERR(folio)) + return folio; + /* should already be PageUptodate, no need to lock page */ + page = folio_file_page(folio, index); buf->page = page; } if (buf->kmap_type == EROFS_NO_KMAP) { @@ -63,6 +70,10 @@ void *erofs_bread(struct erofs_buf *buf, struct inode *inode, void *erofs_read_metabuf(struct erofs_buf *buf, struct super_block *sb, erofs_blk_t blkaddr, enum erofs_kmap_type type) { + if (erofs_is_fscache_mode(sb)) + return erofs_bread(buf, EROFS_SB(sb)->s_fscache->inode, + blkaddr, type); + return erofs_bread(buf, sb->s_bdev->bd_inode, blkaddr, type); } @@ -110,8 +121,8 @@ static int erofs_map_blocks_flatmode(struct inode *inode, return 0; } -static int erofs_map_blocks(struct inode *inode, - struct erofs_map_blocks *map, int flags) +int erofs_map_blocks(struct inode *inode, + struct erofs_map_blocks *map, int flags) { struct super_block *sb = inode->i_sb; struct erofs_inode *vi = EROFS_I(inode); @@ -199,6 +210,7 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map) map->m_bdev = sb->s_bdev; map->m_daxdev = EROFS_SB(sb)->dax_dev; map->m_dax_part_off = EROFS_SB(sb)->dax_part_off; + map->m_fscache = EROFS_SB(sb)->s_fscache; if (map->m_deviceid) { down_read(&devs->rwsem); @@ -210,6 +222,7 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map) map->m_bdev = dif->bdev; map->m_daxdev = dif->dax_dev; map->m_dax_part_off = dif->dax_part_off; + map->m_fscache = dif->fscache; up_read(&devs->rwsem); } else if (devs->extra_devices) { down_read(&devs->rwsem); @@ -227,6 +240,7 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map) map->m_bdev = dif->bdev; map->m_daxdev = dif->dax_dev; map->m_dax_part_off = dif->dax_part_off; + map->m_fscache = dif->fscache; break; } } @@ -337,9 +351,9 @@ int erofs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, * since we dont have write or truncate flows, so no inode * locking needs to be held at the moment. */ -static int erofs_readpage(struct file *file, struct page *page) +static int erofs_read_folio(struct file *file, struct folio *folio) { - return iomap_readpage(page, &erofs_iomap_ops); + return iomap_read_folio(folio, &erofs_iomap_ops); } static void erofs_readahead(struct readahead_control *rac) @@ -385,7 +399,7 @@ static ssize_t erofs_file_read_iter(struct kiocb *iocb, struct iov_iter *to) if (!err) return iomap_dio_rw(iocb, to, &erofs_iomap_ops, - NULL, 0, 0); + NULL, 0, NULL, 0); if (err < 0) return err; } @@ -394,7 +408,7 @@ static ssize_t erofs_file_read_iter(struct kiocb *iocb, struct iov_iter *to) /* for uncompressed (aligned) files and raw access for other files */ const struct address_space_operations erofs_raw_access_aops = { - .readpage = erofs_readpage, + .read_folio = erofs_read_folio, .readahead = erofs_readahead, .bmap = erofs_bmap, .direct_IO = noop_direct_IO, diff --git a/fs/erofs/decompressor.c b/fs/erofs/decompressor.c index 3efa686c7644..6dca1900c733 100644 --- a/fs/erofs/decompressor.c +++ b/fs/erofs/decompressor.c @@ -46,8 +46,6 @@ int z_erofs_load_lz4_config(struct super_block *sb, erofs_err(sb, "too large lz4 pclusterblks %u", sbi->lz4.max_pclusterblks); return -EINVAL; - } else if (sbi->lz4.max_pclusterblks >= 2) { - erofs_info(sb, "EXPERIMENTAL big pcluster feature in use. Use at your own risk!"); } } else { distance = le16_to_cpu(dsb->u1.lz4_max_distance); @@ -322,6 +320,7 @@ static int z_erofs_shifted_transform(struct z_erofs_decompress_req *rq, PAGE_ALIGN(rq->pageofs_out + rq->outputsize) >> PAGE_SHIFT; const unsigned int righthalf = min_t(unsigned int, rq->outputsize, PAGE_SIZE - rq->pageofs_out); + const unsigned int lefthalf = rq->outputsize - righthalf; unsigned char *src, *dst; if (nrpages_out > 2) { @@ -344,10 +343,10 @@ static int z_erofs_shifted_transform(struct z_erofs_decompress_req *rq, if (nrpages_out == 2) { DBG_BUGON(!rq->out[1]); if (rq->out[1] == *rq->in) { - memmove(src, src + righthalf, rq->pageofs_out); + memmove(src, src + righthalf, lefthalf); } else { dst = kmap_atomic(rq->out[1]); - memcpy(dst, src + righthalf, rq->pageofs_out); + memcpy(dst, src + righthalf, lefthalf); kunmap_atomic(dst); } } diff --git a/fs/erofs/erofs_fs.h b/fs/erofs/erofs_fs.h index 1238ca104f09..2b48373f690b 100644 --- a/fs/erofs/erofs_fs.h +++ b/fs/erofs/erofs_fs.h @@ -37,12 +37,9 @@ #define EROFS_SB_EXTSLOT_SIZE 16 struct erofs_deviceslot { - union { - u8 uuid[16]; /* used for device manager later */ - u8 userdata[64]; /* digest(sha256), etc. */ - } u; - __le32 blocks; /* total fs blocks of this device */ - __le32 mapped_blkaddr; /* map starting at mapped_blkaddr */ + u8 tag[64]; /* digest(sha256), etc. */ + __le32 blocks; /* total fs blocks of this device */ + __le32 mapped_blkaddr; /* map starting at mapped_blkaddr */ u8 reserved[56]; }; #define EROFS_DEVT_SLOT_SIZE sizeof(struct erofs_deviceslot) @@ -58,8 +55,8 @@ struct erofs_super_block { __le16 root_nid; /* nid of root directory */ __le64 inos; /* total valid ino # (== f_files - f_favail) */ - __le64 build_time; /* inode v1 time derivation */ - __le32 build_time_nsec; /* inode v1 time derivation in nano scale */ + __le64 build_time; /* compact inode time derivation */ + __le32 build_time_nsec; /* compact inode time derivation in ns scale */ __le32 blocks; /* used for statfs */ __le32 meta_blkaddr; /* start block address of metadata area */ __le32 xattr_blkaddr; /* start block address of shared xattr area */ @@ -79,15 +76,15 @@ struct erofs_super_block { /* * erofs inode datalayout (i_format in on-disk inode): - * 0 - inode plain without inline data A: + * 0 - uncompressed flat inode without tail-packing inline data: * inode, [xattrs], ... | ... | no-holed data - * 1 - inode VLE compression B (legacy): - * inode, [xattrs], extents ... | ... - * 2 - inode plain with inline data C: - * inode, [xattrs], last_inline_data, ... | ... | no-holed data - * 3 - inode compression D: + * 1 - compressed inode with non-compact indexes: + * inode, [xattrs], [map_header], extents ... | ... + * 2 - uncompressed flat inode with tail-packing inline data: + * inode, [xattrs], tailpacking data, ... | ... | no-holed data + * 3 - compressed inode with compact indexes: * inode, [xattrs], map_header, extents ... | ... - * 4 - inode chunk-based E: + * 4 - chunk-based inode with (optional) multi-device support: * inode, [xattrs], chunk indexes ... | ... * 5~7 - reserved */ @@ -106,7 +103,7 @@ static inline bool erofs_inode_is_data_compressed(unsigned int datamode) datamode == EROFS_INODE_FLAT_COMPRESSION_LEGACY; } -/* bit definitions of inode i_advise */ +/* bit definitions of inode i_format */ #define EROFS_I_VERSION_BITS 1 #define EROFS_I_DATALAYOUT_BITS 3 @@ -140,8 +137,9 @@ struct erofs_inode_compact { __le32 i_size; __le32 i_reserved; union { - /* file total compressed blocks for data mapping 1 */ + /* total compressed blocks for compressed inodes */ __le32 compressed_blocks; + /* block address for uncompressed flat inodes */ __le32 raw_blkaddr; /* for device files, used to indicate old/new device # */ @@ -156,9 +154,9 @@ struct erofs_inode_compact { __le32 i_reserved2; }; -/* 32 bytes on-disk inode */ +/* 32-byte on-disk inode */ #define EROFS_INODE_LAYOUT_COMPACT 0 -/* 64 bytes on-disk inode */ +/* 64-byte on-disk inode */ #define EROFS_INODE_LAYOUT_EXTENDED 1 /* 64-byte complete form of an ondisk inode */ @@ -171,8 +169,9 @@ struct erofs_inode_extended { __le16 i_reserved; __le64 i_size; union { - /* file total compressed blocks for data mapping 1 */ + /* total compressed blocks for compressed inodes */ __le32 compressed_blocks; + /* block address for uncompressed flat inodes */ __le32 raw_blkaddr; /* for device files, used to indicate old/new device # */ @@ -365,17 +364,16 @@ enum { struct z_erofs_vle_decompressed_index { __le16 di_advise; - /* where to decompress in the head cluster */ + /* where to decompress in the head lcluster */ __le16 di_clusterofs; union { - /* for the head cluster */ + /* for the HEAD lclusters */ __le32 blkaddr; /* - * for the rest clusters - * eg. for 4k page-sized cluster, maximum 4K*64k = 256M) - * [0] - pointing to the head cluster - * [1] - pointing to the tail cluster + * for the NONHEAD lclusters + * [0] - distance to its HEAD lcluster + * [1] - distance to the next HEAD lcluster */ __le16 delta[2]; } di_u; diff --git a/fs/erofs/fscache.c b/fs/erofs/fscache.c new file mode 100644 index 000000000000..a5cc4ed2cd0d --- /dev/null +++ b/fs/erofs/fscache.c @@ -0,0 +1,519 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (C) 2022, Alibaba Cloud + */ +#include <linux/fscache.h> +#include "internal.h" + +static struct netfs_io_request *erofs_fscache_alloc_request(struct address_space *mapping, + loff_t start, size_t len) +{ + struct netfs_io_request *rreq; + + rreq = kzalloc(sizeof(struct netfs_io_request), GFP_KERNEL); + if (!rreq) + return ERR_PTR(-ENOMEM); + + rreq->start = start; + rreq->len = len; + rreq->mapping = mapping; + INIT_LIST_HEAD(&rreq->subrequests); + refcount_set(&rreq->ref, 1); + return rreq; +} + +static void erofs_fscache_put_request(struct netfs_io_request *rreq) +{ + if (!refcount_dec_and_test(&rreq->ref)) + return; + if (rreq->cache_resources.ops) + rreq->cache_resources.ops->end_operation(&rreq->cache_resources); + kfree(rreq); +} + +static void erofs_fscache_put_subrequest(struct netfs_io_subrequest *subreq) +{ + if (!refcount_dec_and_test(&subreq->ref)) + return; + erofs_fscache_put_request(subreq->rreq); + kfree(subreq); +} + +static void erofs_fscache_clear_subrequests(struct netfs_io_request *rreq) +{ + struct netfs_io_subrequest *subreq; + + while (!list_empty(&rreq->subrequests)) { + subreq = list_first_entry(&rreq->subrequests, + struct netfs_io_subrequest, rreq_link); + list_del(&subreq->rreq_link); + erofs_fscache_put_subrequest(subreq); + } +} + +static void erofs_fscache_rreq_unlock_folios(struct netfs_io_request *rreq) +{ + struct netfs_io_subrequest *subreq; + struct folio *folio; + unsigned int iopos = 0; + pgoff_t start_page = rreq->start / PAGE_SIZE; + pgoff_t last_page = ((rreq->start + rreq->len) / PAGE_SIZE) - 1; + bool subreq_failed = false; + + XA_STATE(xas, &rreq->mapping->i_pages, start_page); + + subreq = list_first_entry(&rreq->subrequests, + struct netfs_io_subrequest, rreq_link); + subreq_failed = (subreq->error < 0); + + rcu_read_lock(); + xas_for_each(&xas, folio, last_page) { + unsigned int pgpos = + (folio_index(folio) - start_page) * PAGE_SIZE; + unsigned int pgend = pgpos + folio_size(folio); + bool pg_failed = false; + + for (;;) { + if (!subreq) { + pg_failed = true; + break; + } + + pg_failed |= subreq_failed; + if (pgend < iopos + subreq->len) + break; + + iopos += subreq->len; + if (!list_is_last(&subreq->rreq_link, + &rreq->subrequests)) { + subreq = list_next_entry(subreq, rreq_link); + subreq_failed = (subreq->error < 0); + } else { + subreq = NULL; + subreq_failed = false; + } + if (pgend == iopos) + break; + } + + if (!pg_failed) + folio_mark_uptodate(folio); + + folio_unlock(folio); + } + rcu_read_unlock(); +} + +static void erofs_fscache_rreq_complete(struct netfs_io_request *rreq) +{ + erofs_fscache_rreq_unlock_folios(rreq); + erofs_fscache_clear_subrequests(rreq); + erofs_fscache_put_request(rreq); +} + +static void erofc_fscache_subreq_complete(void *priv, + ssize_t transferred_or_error, bool was_async) +{ + struct netfs_io_subrequest *subreq = priv; + struct netfs_io_request *rreq = subreq->rreq; + + if (IS_ERR_VALUE(transferred_or_error)) + subreq->error = transferred_or_error; + + if (atomic_dec_and_test(&rreq->nr_outstanding)) + erofs_fscache_rreq_complete(rreq); + + erofs_fscache_put_subrequest(subreq); +} + +/* + * Read data from fscache and fill the read data into page cache described by + * @rreq, which shall be both aligned with PAGE_SIZE. @pstart describes + * the start physical address in the cache file. + */ +static int erofs_fscache_read_folios_async(struct fscache_cookie *cookie, + struct netfs_io_request *rreq, loff_t pstart) +{ + enum netfs_io_source source; + struct super_block *sb = rreq->mapping->host->i_sb; + struct netfs_io_subrequest *subreq; + struct netfs_cache_resources *cres = &rreq->cache_resources; + struct iov_iter iter; + loff_t start = rreq->start; + size_t len = rreq->len; + size_t done = 0; + int ret; + + atomic_set(&rreq->nr_outstanding, 1); + + ret = fscache_begin_read_operation(cres, cookie); + if (ret) + goto out; + + while (done < len) { + subreq = kzalloc(sizeof(struct netfs_io_subrequest), + GFP_KERNEL); + if (subreq) { + INIT_LIST_HEAD(&subreq->rreq_link); + refcount_set(&subreq->ref, 2); + subreq->rreq = rreq; + refcount_inc(&rreq->ref); + } else { + ret = -ENOMEM; + goto out; + } + + subreq->start = pstart + done; + subreq->len = len - done; + subreq->flags = 1 << NETFS_SREQ_ONDEMAND; + + list_add_tail(&subreq->rreq_link, &rreq->subrequests); + + source = cres->ops->prepare_read(subreq, LLONG_MAX); + if (WARN_ON(subreq->len == 0)) + source = NETFS_INVALID_READ; + if (source != NETFS_READ_FROM_CACHE) { + erofs_err(sb, "failed to fscache prepare_read (source %d)", + source); + ret = -EIO; + subreq->error = ret; + erofs_fscache_put_subrequest(subreq); + goto out; + } + + atomic_inc(&rreq->nr_outstanding); + + iov_iter_xarray(&iter, READ, &rreq->mapping->i_pages, + start + done, subreq->len); + + ret = fscache_read(cres, subreq->start, &iter, + NETFS_READ_HOLE_FAIL, + erofc_fscache_subreq_complete, subreq); + if (ret == -EIOCBQUEUED) + ret = 0; + if (ret) { + erofs_err(sb, "failed to fscache_read (ret %d)", ret); + goto out; + } + + done += subreq->len; + } +out: + if (atomic_dec_and_test(&rreq->nr_outstanding)) + erofs_fscache_rreq_complete(rreq); + + return ret; +} + +static int erofs_fscache_meta_read_folio(struct file *data, struct folio *folio) +{ + int ret; + struct super_block *sb = folio_mapping(folio)->host->i_sb; + struct netfs_io_request *rreq; + struct erofs_map_dev mdev = { + .m_deviceid = 0, + .m_pa = folio_pos(folio), + }; + + ret = erofs_map_dev(sb, &mdev); + if (ret) + goto out; + + rreq = erofs_fscache_alloc_request(folio_mapping(folio), + folio_pos(folio), folio_size(folio)); + if (IS_ERR(rreq)) + goto out; + + return erofs_fscache_read_folios_async(mdev.m_fscache->cookie, + rreq, mdev.m_pa); +out: + folio_unlock(folio); + return ret; +} + +static int erofs_fscache_read_folio_inline(struct folio *folio, + struct erofs_map_blocks *map) +{ + struct super_block *sb = folio_mapping(folio)->host->i_sb; + struct erofs_buf buf = __EROFS_BUF_INITIALIZER; + erofs_blk_t blknr; + size_t offset, len; + void *src, *dst; + + /* For tail packing layout, the offset may be non-zero. */ + offset = erofs_blkoff(map->m_pa); + blknr = erofs_blknr(map->m_pa); + len = map->m_llen; + + src = erofs_read_metabuf(&buf, sb, blknr, EROFS_KMAP); + if (IS_ERR(src)) + return PTR_ERR(src); + + dst = kmap_local_folio(folio, 0); + memcpy(dst, src + offset, len); + memset(dst + len, 0, PAGE_SIZE - len); + kunmap_local(dst); + + erofs_put_metabuf(&buf); + return 0; +} + +static int erofs_fscache_read_folio(struct file *file, struct folio *folio) +{ + struct inode *inode = folio_mapping(folio)->host; + struct super_block *sb = inode->i_sb; + struct erofs_map_blocks map; + struct erofs_map_dev mdev; + struct netfs_io_request *rreq; + erofs_off_t pos; + loff_t pstart; + int ret; + + DBG_BUGON(folio_size(folio) != EROFS_BLKSIZ); + + pos = folio_pos(folio); + map.m_la = pos; + + ret = erofs_map_blocks(inode, &map, EROFS_GET_BLOCKS_RAW); + if (ret) + goto out_unlock; + + if (!(map.m_flags & EROFS_MAP_MAPPED)) { + folio_zero_range(folio, 0, folio_size(folio)); + goto out_uptodate; + } + + if (map.m_flags & EROFS_MAP_META) { + ret = erofs_fscache_read_folio_inline(folio, &map); + goto out_uptodate; + } + + mdev = (struct erofs_map_dev) { + .m_deviceid = map.m_deviceid, + .m_pa = map.m_pa, + }; + + ret = erofs_map_dev(sb, &mdev); + if (ret) + goto out_unlock; + + + rreq = erofs_fscache_alloc_request(folio_mapping(folio), + folio_pos(folio), folio_size(folio)); + if (IS_ERR(rreq)) + goto out_unlock; + + pstart = mdev.m_pa + (pos - map.m_la); + return erofs_fscache_read_folios_async(mdev.m_fscache->cookie, + rreq, pstart); + +out_uptodate: + if (!ret) + folio_mark_uptodate(folio); +out_unlock: + folio_unlock(folio); + return ret; +} + +static void erofs_fscache_advance_folios(struct readahead_control *rac, + size_t len, bool unlock) +{ + while (len) { + struct folio *folio = readahead_folio(rac); + len -= folio_size(folio); + if (unlock) { + folio_mark_uptodate(folio); + folio_unlock(folio); + } + } +} + +static void erofs_fscache_readahead(struct readahead_control *rac) +{ + struct inode *inode = rac->mapping->host; + struct super_block *sb = inode->i_sb; + size_t len, count, done = 0; + erofs_off_t pos; + loff_t start, offset; + int ret; + + if (!readahead_count(rac)) + return; + + start = readahead_pos(rac); + len = readahead_length(rac); + + do { + struct erofs_map_blocks map; + struct erofs_map_dev mdev; + struct netfs_io_request *rreq; + + pos = start + done; + map.m_la = pos; + + ret = erofs_map_blocks(inode, &map, EROFS_GET_BLOCKS_RAW); + if (ret) + return; + + offset = start + done; + count = min_t(size_t, map.m_llen - (pos - map.m_la), + len - done); + + if (!(map.m_flags & EROFS_MAP_MAPPED)) { + struct iov_iter iter; + + iov_iter_xarray(&iter, READ, &rac->mapping->i_pages, + offset, count); + iov_iter_zero(count, &iter); + + erofs_fscache_advance_folios(rac, count, true); + ret = count; + continue; + } + + if (map.m_flags & EROFS_MAP_META) { + struct folio *folio = readahead_folio(rac); + + ret = erofs_fscache_read_folio_inline(folio, &map); + if (!ret) { + folio_mark_uptodate(folio); + ret = folio_size(folio); + } + + folio_unlock(folio); + continue; + } + + mdev = (struct erofs_map_dev) { + .m_deviceid = map.m_deviceid, + .m_pa = map.m_pa, + }; + ret = erofs_map_dev(sb, &mdev); + if (ret) + return; + + rreq = erofs_fscache_alloc_request(rac->mapping, offset, count); + if (IS_ERR(rreq)) + return; + /* + * Drop the ref of folios here. Unlock them in + * rreq_unlock_folios() when rreq complete. + */ + erofs_fscache_advance_folios(rac, count, false); + ret = erofs_fscache_read_folios_async(mdev.m_fscache->cookie, + rreq, mdev.m_pa + (pos - map.m_la)); + if (!ret) + ret = count; + } while (ret > 0 && ((done += ret) < len)); +} + +static const struct address_space_operations erofs_fscache_meta_aops = { + .read_folio = erofs_fscache_meta_read_folio, +}; + +const struct address_space_operations erofs_fscache_access_aops = { + .read_folio = erofs_fscache_read_folio, + .readahead = erofs_fscache_readahead, +}; + +int erofs_fscache_register_cookie(struct super_block *sb, + struct erofs_fscache **fscache, + char *name, bool need_inode) +{ + struct fscache_volume *volume = EROFS_SB(sb)->volume; + struct erofs_fscache *ctx; + struct fscache_cookie *cookie; + int ret; + + ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + + cookie = fscache_acquire_cookie(volume, FSCACHE_ADV_WANT_CACHE_SIZE, + name, strlen(name), NULL, 0, 0); + if (!cookie) { + erofs_err(sb, "failed to get cookie for %s", name); + ret = -EINVAL; + goto err; + } + + fscache_use_cookie(cookie, false); + ctx->cookie = cookie; + + if (need_inode) { + struct inode *const inode = new_inode(sb); + + if (!inode) { + erofs_err(sb, "failed to get anon inode for %s", name); + ret = -ENOMEM; + goto err_cookie; + } + + set_nlink(inode, 1); + inode->i_size = OFFSET_MAX; + inode->i_mapping->a_ops = &erofs_fscache_meta_aops; + mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS); + + ctx->inode = inode; + } + + *fscache = ctx; + return 0; + +err_cookie: + fscache_unuse_cookie(ctx->cookie, NULL, NULL); + fscache_relinquish_cookie(ctx->cookie, false); + ctx->cookie = NULL; +err: + kfree(ctx); + return ret; +} + +void erofs_fscache_unregister_cookie(struct erofs_fscache **fscache) +{ + struct erofs_fscache *ctx = *fscache; + + if (!ctx) + return; + + fscache_unuse_cookie(ctx->cookie, NULL, NULL); + fscache_relinquish_cookie(ctx->cookie, false); + ctx->cookie = NULL; + + iput(ctx->inode); + ctx->inode = NULL; + + kfree(ctx); + *fscache = NULL; +} + +int erofs_fscache_register_fs(struct super_block *sb) +{ + struct erofs_sb_info *sbi = EROFS_SB(sb); + struct fscache_volume *volume; + char *name; + int ret = 0; + + name = kasprintf(GFP_KERNEL, "erofs,%s", sbi->opt.fsid); + if (!name) + return -ENOMEM; + + volume = fscache_acquire_volume(name, NULL, NULL, 0); + if (IS_ERR_OR_NULL(volume)) { + erofs_err(sb, "failed to register volume for %s", name); + ret = volume ? PTR_ERR(volume) : -EOPNOTSUPP; + volume = NULL; + } + + sbi->volume = volume; + kfree(name); + return ret; +} + +void erofs_fscache_unregister_fs(struct super_block *sb) +{ + struct erofs_sb_info *sbi = EROFS_SB(sb); + + fscache_relinquish_volume(sbi->volume, NULL, false); + sbi->volume = NULL; +} diff --git a/fs/erofs/inode.c b/fs/erofs/inode.c index e8b37ba5e9ad..bcc8335b46b3 100644 --- a/fs/erofs/inode.c +++ b/fs/erofs/inode.c @@ -8,11 +8,6 @@ #include <trace/events/erofs.h> -/* - * if inode is successfully read, return its inode page (or sometimes - * the inode payload page if it's an extended inode) in order to fill - * inline data if possible. - */ static void *erofs_read_inode(struct erofs_buf *buf, struct inode *inode, unsigned int *ofs) { @@ -297,6 +292,10 @@ static int erofs_fill_inode(struct inode *inode, int isdir) goto out_unlock; } inode->i_mapping->a_ops = &erofs_raw_access_aops; +#ifdef CONFIG_EROFS_FS_ONDEMAND + if (erofs_is_fscache_mode(inode->i_sb)) + inode->i_mapping->a_ops = &erofs_fscache_access_aops; +#endif out_unlock: erofs_put_metabuf(&buf); @@ -370,7 +369,7 @@ int erofs_getattr(struct user_namespace *mnt_userns, const struct path *path, stat->attributes_mask |= (STATX_ATTR_COMPRESSED | STATX_ATTR_IMMUTABLE); - generic_fillattr(&init_user_ns, inode, stat); + generic_fillattr(mnt_userns, inode, stat); return 0; } diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h index 5298c4ee277d..cfee49d33b95 100644 --- a/fs/erofs/internal.h +++ b/fs/erofs/internal.h @@ -49,6 +49,7 @@ typedef u32 erofs_blk_t; struct erofs_device_info { char *path; + struct erofs_fscache *fscache; struct block_device *bdev; struct dax_device *dax_dev; u64 dax_part_off; @@ -74,6 +75,7 @@ struct erofs_mount_opts { unsigned int max_sync_decompress_pages; #endif unsigned int mount_opt; + char *fsid; }; struct erofs_dev_context { @@ -96,6 +98,11 @@ struct erofs_sb_lz4_info { u16 max_pclusterblks; }; +struct erofs_fscache { + struct fscache_cookie *cookie; + struct inode *inode; +}; + struct erofs_sb_info { struct erofs_mount_opts opt; /* options */ #ifdef CONFIG_EROFS_FS_ZIP @@ -146,6 +153,10 @@ struct erofs_sb_info { /* sysfs support */ struct kobject s_kobj; /* /sys/fs/erofs/<devname> */ struct completion s_kobj_unregister; + + /* fscache support */ + struct fscache_volume *volume; + struct erofs_fscache *s_fscache; }; #define EROFS_SB(sb) ((struct erofs_sb_info *)(sb)->s_fs_info) @@ -161,6 +172,11 @@ struct erofs_sb_info { #define set_opt(opt, option) ((opt)->mount_opt |= EROFS_MOUNT_##option) #define test_opt(opt, option) ((opt)->mount_opt & EROFS_MOUNT_##option) +static inline bool erofs_is_fscache_mode(struct super_block *sb) +{ + return IS_ENABLED(CONFIG_EROFS_FS_ONDEMAND) && !sb->s_bdev; +} + enum { EROFS_ZIP_CACHE_DISABLED, EROFS_ZIP_CACHE_READAHEAD, @@ -381,31 +397,6 @@ extern const struct super_operations erofs_sops; extern const struct address_space_operations erofs_raw_access_aops; extern const struct address_space_operations z_erofs_aops; -/* - * Logical to physical block mapping - * - * Different with other file systems, it is used for 2 access modes: - * - * 1) RAW access mode: - * - * Users pass a valid (m_lblk, m_lofs -- usually 0) pair, - * and get the valid m_pblk, m_pofs and the longest m_len(in bytes). - * - * Note that m_lblk in the RAW access mode refers to the number of - * the compressed ondisk block rather than the uncompressed - * in-memory block for the compressed file. - * - * m_pofs equals to m_lofs except for the inline data page. - * - * 2) Normal access mode: - * - * If the inode is not compressed, it has no difference with - * the RAW access mode. However, if the inode is compressed, - * users should pass a valid (m_lblk, m_lofs) pair, and get - * the needed m_pblk, m_pofs, m_len to get the compressed data - * and the updated m_lblk, m_lofs which indicates the start - * of the corresponding uncompressed data in the file. - */ enum { BH_Encoded = BH_PrivateStart, BH_FullMapped, @@ -467,6 +458,7 @@ static inline int z_erofs_map_blocks_iter(struct inode *inode, #endif /* !CONFIG_EROFS_FS_ZIP */ struct erofs_map_dev { + struct erofs_fscache *m_fscache; struct block_device *m_bdev; struct dax_device *m_daxdev; u64 m_dax_part_off; @@ -486,6 +478,8 @@ void *erofs_read_metabuf(struct erofs_buf *buf, struct super_block *sb, int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *dev); int erofs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 len); +int erofs_map_blocks(struct inode *inode, + struct erofs_map_blocks *map, int flags); /* inode.c */ static inline unsigned long erofs_inode_hash(erofs_nid_t nid) @@ -509,7 +503,7 @@ int erofs_getattr(struct user_namespace *mnt_userns, const struct path *path, /* namei.c */ extern const struct inode_operations erofs_dir_iops; -int erofs_namei(struct inode *dir, struct qstr *name, +int erofs_namei(struct inode *dir, const struct qstr *name, erofs_nid_t *nid, unsigned int *d_type); /* dir.c */ @@ -611,6 +605,36 @@ static inline int z_erofs_load_lzma_config(struct super_block *sb, } #endif /* !CONFIG_EROFS_FS_ZIP */ +/* fscache.c */ +#ifdef CONFIG_EROFS_FS_ONDEMAND +int erofs_fscache_register_fs(struct super_block *sb); +void erofs_fscache_unregister_fs(struct super_block *sb); + +int erofs_fscache_register_cookie(struct super_block *sb, + struct erofs_fscache **fscache, + char *name, bool need_inode); +void erofs_fscache_unregister_cookie(struct erofs_fscache **fscache); + +extern const struct address_space_operations erofs_fscache_access_aops; +#else +static inline int erofs_fscache_register_fs(struct super_block *sb) +{ + return 0; +} +static inline void erofs_fscache_unregister_fs(struct super_block *sb) {} + +static inline int erofs_fscache_register_cookie(struct super_block *sb, + struct erofs_fscache **fscache, + char *name, bool need_inode) +{ + return -EOPNOTSUPP; +} + +static inline void erofs_fscache_unregister_cookie(struct erofs_fscache **fscache) +{ +} +#endif + #define EFSCORRUPTED EUCLEAN /* Filesystem is corrupted */ #endif /* __EROFS_INTERNAL_H */ diff --git a/fs/erofs/namei.c b/fs/erofs/namei.c index 554efa363317..fd75506799c4 100644 --- a/fs/erofs/namei.c +++ b/fs/erofs/namei.c @@ -165,9 +165,8 @@ out: /* free if the candidate is valid */ return candidate; } -int erofs_namei(struct inode *dir, - struct qstr *name, - erofs_nid_t *nid, unsigned int *d_type) +int erofs_namei(struct inode *dir, const struct qstr *name, erofs_nid_t *nid, + unsigned int *d_type) { int ndirents; struct erofs_buf buf = __EROFS_BUF_INITIALIZER; diff --git a/fs/erofs/super.c b/fs/erofs/super.c index 0c4b41130c2f..95addc5c9d34 100644 --- a/fs/erofs/super.c +++ b/fs/erofs/super.c @@ -13,6 +13,7 @@ #include <linux/fs_context.h> #include <linux/fs_parser.h> #include <linux/dax.h> +#include <linux/exportfs.h> #include "xattr.h" #define CREATE_TRACE_POINTS @@ -219,7 +220,52 @@ static int erofs_load_compr_cfgs(struct super_block *sb, } #endif -static int erofs_init_devices(struct super_block *sb, +static int erofs_init_device(struct erofs_buf *buf, struct super_block *sb, + struct erofs_device_info *dif, erofs_off_t *pos) +{ + struct erofs_sb_info *sbi = EROFS_SB(sb); + struct erofs_deviceslot *dis; + struct block_device *bdev; + void *ptr; + int ret; + + ptr = erofs_read_metabuf(buf, sb, erofs_blknr(*pos), EROFS_KMAP); + if (IS_ERR(ptr)) + return PTR_ERR(ptr); + dis = ptr + erofs_blkoff(*pos); + + if (!dif->path) { + if (!dis->tag[0]) { + erofs_err(sb, "empty device tag @ pos %llu", *pos); + return -EINVAL; + } + dif->path = kmemdup_nul(dis->tag, sizeof(dis->tag), GFP_KERNEL); + if (!dif->path) + return -ENOMEM; + } + + if (erofs_is_fscache_mode(sb)) { + ret = erofs_fscache_register_cookie(sb, &dif->fscache, + dif->path, false); + if (ret) + return ret; + } else { + bdev = blkdev_get_by_path(dif->path, FMODE_READ | FMODE_EXCL, + sb->s_type); + if (IS_ERR(bdev)) + return PTR_ERR(bdev); + dif->bdev = bdev; + dif->dax_dev = fs_dax_get_by_bdev(bdev, &dif->dax_part_off); + } + + dif->blocks = le32_to_cpu(dis->blocks); + dif->mapped_blkaddr = le32_to_cpu(dis->mapped_blkaddr); + sbi->total_blocks += dif->blocks; + *pos += EROFS_DEVT_SLOT_SIZE; + return 0; +} + +static int erofs_scan_devices(struct super_block *sb, struct erofs_super_block *dsb) { struct erofs_sb_info *sbi = EROFS_SB(sb); @@ -227,8 +273,6 @@ static int erofs_init_devices(struct super_block *sb, erofs_off_t pos; struct erofs_buf buf = __EROFS_BUF_INITIALIZER; struct erofs_device_info *dif; - struct erofs_deviceslot *dis; - void *ptr; int id, err = 0; sbi->total_blocks = sbi->primarydevice_blocks; @@ -237,7 +281,8 @@ static int erofs_init_devices(struct super_block *sb, else ondisk_extradevs = le16_to_cpu(dsb->extra_devices); - if (ondisk_extradevs != sbi->devs->extra_devices) { + if (sbi->devs->extra_devices && + ondisk_extradevs != sbi->devs->extra_devices) { erofs_err(sb, "extra devices don't match (ondisk %u, given %u)", ondisk_extradevs, sbi->devs->extra_devices); return -EINVAL; @@ -248,30 +293,31 @@ static int erofs_init_devices(struct super_block *sb, sbi->device_id_mask = roundup_pow_of_two(ondisk_extradevs + 1) - 1; pos = le16_to_cpu(dsb->devt_slotoff) * EROFS_DEVT_SLOT_SIZE; down_read(&sbi->devs->rwsem); - idr_for_each_entry(&sbi->devs->tree, dif, id) { - struct block_device *bdev; - - ptr = erofs_read_metabuf(&buf, sb, erofs_blknr(pos), - EROFS_KMAP); - if (IS_ERR(ptr)) { - err = PTR_ERR(ptr); - break; + if (sbi->devs->extra_devices) { + idr_for_each_entry(&sbi->devs->tree, dif, id) { + err = erofs_init_device(&buf, sb, dif, &pos); + if (err) + break; } - dis = ptr + erofs_blkoff(pos); - - bdev = blkdev_get_by_path(dif->path, - FMODE_READ | FMODE_EXCL, - sb->s_type); - if (IS_ERR(bdev)) { - err = PTR_ERR(bdev); - break; + } else { + for (id = 0; id < ondisk_extradevs; id++) { + dif = kzalloc(sizeof(*dif), GFP_KERNEL); + if (!dif) { + err = -ENOMEM; + break; + } + + err = idr_alloc(&sbi->devs->tree, dif, 0, 0, GFP_KERNEL); + if (err < 0) { + kfree(dif); + break; + } + ++sbi->devs->extra_devices; + + err = erofs_init_device(&buf, sb, dif, &pos); + if (err) + break; } - dif->bdev = bdev; - dif->dax_dev = fs_dax_get_by_bdev(bdev, &dif->dax_part_off); - dif->blocks = le32_to_cpu(dis->blocks); - dif->mapped_blkaddr = le32_to_cpu(dis->mapped_blkaddr); - sbi->total_blocks += dif->blocks; - pos += EROFS_DEVT_SLOT_SIZE; } up_read(&sbi->devs->rwsem); erofs_put_metabuf(&buf); @@ -358,10 +404,12 @@ static int erofs_read_superblock(struct super_block *sb) goto out; /* handle multiple devices */ - ret = erofs_init_devices(sb, dsb); + ret = erofs_scan_devices(sb, dsb); if (erofs_sb_has_ztailpacking(sbi)) erofs_info(sb, "EXPERIMENTAL compressed inline data feature in use. Use at your own risk!"); + if (erofs_is_fscache_mode(sb)) + erofs_info(sb, "EXPERIMENTAL fscache-based on-demand read feature in use. Use at your own risk!"); out: erofs_put_metabuf(&buf); return ret; @@ -390,6 +438,7 @@ enum { Opt_dax, Opt_dax_enum, Opt_device, + Opt_fsid, Opt_err }; @@ -414,6 +463,7 @@ static const struct fs_parameter_spec erofs_fs_parameters[] = { fsparam_flag("dax", Opt_dax), fsparam_enum("dax", Opt_dax_enum, erofs_dax_param_enums), fsparam_string("device", Opt_device), + fsparam_string("fsid", Opt_fsid), {} }; @@ -509,6 +559,16 @@ static int erofs_fc_parse_param(struct fs_context *fc, } ++ctx->devs->extra_devices; break; + case Opt_fsid: +#ifdef CONFIG_EROFS_FS_ONDEMAND + kfree(ctx->opt.fsid); + ctx->opt.fsid = kstrdup(param->string, GFP_KERNEL); + if (!ctx->opt.fsid) + return -ENOMEM; +#else + errorfc(fc, "fsid option not supported"); +#endif + break; default: return -ENOPARAM; } @@ -518,16 +578,16 @@ static int erofs_fc_parse_param(struct fs_context *fc, #ifdef CONFIG_EROFS_FS_ZIP static const struct address_space_operations managed_cache_aops; -static int erofs_managed_cache_releasepage(struct page *page, gfp_t gfp_mask) +static bool erofs_managed_cache_release_folio(struct folio *folio, gfp_t gfp) { - int ret = 1; /* 0 - busy */ - struct address_space *const mapping = page->mapping; + bool ret = true; + struct address_space *const mapping = folio->mapping; - DBG_BUGON(!PageLocked(page)); + DBG_BUGON(!folio_test_locked(folio)); DBG_BUGON(mapping->a_ops != &managed_cache_aops); - if (PagePrivate(page)) - ret = erofs_try_to_free_cached_page(page); + if (folio_test_private(folio)) + ret = erofs_try_to_free_cached_page(&folio->page); return ret; } @@ -548,12 +608,12 @@ static void erofs_managed_cache_invalidate_folio(struct folio *folio, DBG_BUGON(stop > folio_size(folio) || stop < length); if (offset == 0 && stop == folio_size(folio)) - while (!erofs_managed_cache_releasepage(&folio->page, GFP_NOFS)) + while (!erofs_managed_cache_release_folio(folio, GFP_NOFS)) cond_resched(); } static const struct address_space_operations managed_cache_aops = { - .releasepage = erofs_managed_cache_releasepage, + .release_folio = erofs_managed_cache_release_folio, .invalidate_folio = erofs_managed_cache_invalidate_folio, }; @@ -577,6 +637,44 @@ static int erofs_init_managed_cache(struct super_block *sb) static int erofs_init_managed_cache(struct super_block *sb) { return 0; } #endif +static struct inode *erofs_nfs_get_inode(struct super_block *sb, + u64 ino, u32 generation) +{ + return erofs_iget(sb, ino, false); +} + +static struct dentry *erofs_fh_to_dentry(struct super_block *sb, + struct fid *fid, int fh_len, int fh_type) +{ + return generic_fh_to_dentry(sb, fid, fh_len, fh_type, + erofs_nfs_get_inode); +} + +static struct dentry *erofs_fh_to_parent(struct super_block *sb, + struct fid *fid, int fh_len, int fh_type) +{ + return generic_fh_to_parent(sb, fid, fh_len, fh_type, + erofs_nfs_get_inode); +} + +static struct dentry *erofs_get_parent(struct dentry *child) +{ + erofs_nid_t nid; + unsigned int d_type; + int err; + + err = erofs_namei(d_inode(child), &dotdot_name, &nid, &d_type); + if (err) + return ERR_PTR(err); + return d_obtain_alias(erofs_iget(child->d_sb, nid, d_type == FT_DIR)); +} + +static const struct export_operations erofs_export_ops = { + .fh_to_dentry = erofs_fh_to_dentry, + .fh_to_parent = erofs_fh_to_parent, + .get_parent = erofs_get_parent, +}; + static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) { struct inode *inode; @@ -585,11 +683,9 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) int err; sb->s_magic = EROFS_SUPER_MAGIC; - - if (!sb_set_blocksize(sb, EROFS_BLKSIZ)) { - erofs_err(sb, "failed to set erofs blksize"); - return -EINVAL; - } + sb->s_flags |= SB_RDONLY | SB_NOATIME; + sb->s_maxbytes = MAX_LFS_FILESIZE; + sb->s_op = &erofs_sops; sbi = kzalloc(sizeof(*sbi), GFP_KERNEL); if (!sbi) @@ -597,10 +693,36 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) sb->s_fs_info = sbi; sbi->opt = ctx->opt; - sbi->dax_dev = fs_dax_get_by_bdev(sb->s_bdev, &sbi->dax_part_off); + ctx->opt.fsid = NULL; sbi->devs = ctx->devs; ctx->devs = NULL; + if (erofs_is_fscache_mode(sb)) { + sb->s_blocksize = EROFS_BLKSIZ; + sb->s_blocksize_bits = LOG_BLOCK_SIZE; + + err = erofs_fscache_register_fs(sb); + if (err) + return err; + + err = erofs_fscache_register_cookie(sb, &sbi->s_fscache, + sbi->opt.fsid, true); + if (err) + return err; + + err = super_setup_bdi(sb); + if (err) + return err; + } else { + if (!sb_set_blocksize(sb, EROFS_BLKSIZ)) { + erofs_err(sb, "failed to set erofs blksize"); + return -EINVAL; + } + + sbi->dax_dev = fs_dax_get_by_bdev(sb->s_bdev, + &sbi->dax_part_off); + } + err = erofs_read_superblock(sb); if (err) return err; @@ -613,12 +735,10 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) clear_opt(&sbi->opt, DAX_ALWAYS); } } - sb->s_flags |= SB_RDONLY | SB_NOATIME; - sb->s_maxbytes = MAX_LFS_FILESIZE; - sb->s_time_gran = 1; - sb->s_op = &erofs_sops; + sb->s_time_gran = 1; sb->s_xattr = erofs_xattr_handlers; + sb->s_export_op = &erofs_export_ops; if (test_opt(&sbi->opt, POSIX_ACL)) sb->s_flags |= SB_POSIXACL; @@ -661,6 +781,11 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) static int erofs_fc_get_tree(struct fs_context *fc) { + struct erofs_fs_context *ctx = fc->fs_private; + + if (IS_ENABLED(CONFIG_EROFS_FS_ONDEMAND) && ctx->opt.fsid) + return get_tree_nodev(fc, erofs_fc_fill_super); + return get_tree_bdev(fc, erofs_fc_fill_super); } @@ -690,6 +815,7 @@ static int erofs_release_device_info(int id, void *ptr, void *data) fs_put_dax(dif->dax_dev); if (dif->bdev) blkdev_put(dif->bdev, FMODE_READ | FMODE_EXCL); + erofs_fscache_unregister_cookie(&dif->fscache); kfree(dif->path); kfree(dif); return 0; @@ -709,6 +835,7 @@ static void erofs_fc_free(struct fs_context *fc) struct erofs_fs_context *ctx = fc->fs_private; erofs_free_dev_context(ctx->devs); + kfree(ctx->opt.fsid); kfree(ctx); } @@ -749,7 +876,10 @@ static void erofs_kill_sb(struct super_block *sb) WARN_ON(sb->s_magic != EROFS_SUPER_MAGIC); - kill_block_super(sb); + if (erofs_is_fscache_mode(sb)) + generic_shutdown_super(sb); + else + kill_block_super(sb); sbi = EROFS_SB(sb); if (!sbi) @@ -757,6 +887,9 @@ static void erofs_kill_sb(struct super_block *sb) erofs_free_dev_context(sbi->devs); fs_put_dax(sbi->dax_dev); + erofs_fscache_unregister_cookie(&sbi->s_fscache); + erofs_fscache_unregister_fs(sb); + kfree(sbi->opt.fsid); kfree(sbi); sb->s_fs_info = NULL; } @@ -774,6 +907,7 @@ static void erofs_put_super(struct super_block *sb) iput(sbi->managed_cache); sbi->managed_cache = NULL; #endif + erofs_fscache_unregister_cookie(&sbi->s_fscache); } static struct file_system_type erofs_fs_type = { @@ -781,7 +915,7 @@ static struct file_system_type erofs_fs_type = { .name = "erofs", .init_fs_context = erofs_init_fs_context, .kill_sb = erofs_kill_sb, - .fs_flags = FS_REQUIRES_DEV, + .fs_flags = FS_REQUIRES_DEV | FS_ALLOW_IDMAP, }; MODULE_ALIAS_FS("erofs"); @@ -857,7 +991,10 @@ static int erofs_statfs(struct dentry *dentry, struct kstatfs *buf) { struct super_block *sb = dentry->d_sb; struct erofs_sb_info *sbi = EROFS_SB(sb); - u64 id = huge_encode_dev(sb->s_bdev->bd_dev); + u64 id = 0; + + if (!erofs_is_fscache_mode(sb)) + id = huge_encode_dev(sb->s_bdev->bd_dev); buf->f_type = sb->s_magic; buf->f_bsize = EROFS_BLKSIZ; @@ -902,6 +1039,10 @@ static int erofs_show_options(struct seq_file *seq, struct dentry *root) seq_puts(seq, ",dax=always"); if (test_opt(opt, DAX_NEVER)) seq_puts(seq, ",dax=never"); +#ifdef CONFIG_EROFS_FS_ONDEMAND + if (opt->fsid) + seq_printf(seq, ",fsid=%s", opt->fsid); +#endif return 0; } diff --git a/fs/erofs/sysfs.c b/fs/erofs/sysfs.c index f3babf1e6608..c1383e508bbe 100644 --- a/fs/erofs/sysfs.c +++ b/fs/erofs/sysfs.c @@ -205,8 +205,8 @@ int erofs_register_sysfs(struct super_block *sb) sbi->s_kobj.kset = &erofs_root; init_completion(&sbi->s_kobj_unregister); - err = kobject_init_and_add(&sbi->s_kobj, &erofs_sb_ktype, NULL, - "%s", sb->s_id); + err = kobject_init_and_add(&sbi->s_kobj, &erofs_sb_ktype, NULL, "%s", + erofs_is_fscache_mode(sb) ? sbi->opt.fsid : sb->s_id); if (err) goto put_sb_kobj; return 0; diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index 0ed880f42525..95efc127b2ba 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -791,7 +791,7 @@ err_out: static bool z_erofs_get_sync_decompress_policy(struct erofs_sb_info *sbi, unsigned int readahead_pages) { - /* auto: enable for readpage, disable for readahead */ + /* auto: enable for read_folio, disable for readahead */ if ((sbi->opt.sync_decompress == EROFS_SYNC_DECOMPRESS_AUTO) && !readahead_pages) return true; @@ -1066,12 +1066,9 @@ static void z_erofs_decompress_kickoff(struct z_erofs_decompressqueue *io, /* wake up the caller thread for sync decompression */ if (sync) { - unsigned long flags; - - spin_lock_irqsave(&io->u.wait.lock, flags); if (!atomic_add_return(bios, &io->pending_bios)) - wake_up_locked(&io->u.wait); - spin_unlock_irqrestore(&io->u.wait.lock, flags); + complete(&io->u.done); + return; } @@ -1217,7 +1214,7 @@ jobqueue_init(struct super_block *sb, } else { fg_out: q = fgq; - init_waitqueue_head(&fgq->u.wait); + init_completion(&fgq->u.done); atomic_set(&fgq->pending_bios, 0); } q->sb = sb; @@ -1419,8 +1416,7 @@ static void z_erofs_runqueue(struct super_block *sb, return; /* wait until all bios are completed */ - io_wait_event(io[JQ_SUBMIT].u.wait, - !atomic_read(&io[JQ_SUBMIT].pending_bios)); + wait_for_completion_io(&io[JQ_SUBMIT].u.done); /* handle synchronous decompress queue in the caller context */ z_erofs_decompress_queue(&io[JQ_SUBMIT], pagepool); @@ -1492,8 +1488,9 @@ skip: } } -static int z_erofs_readpage(struct file *file, struct page *page) +static int z_erofs_read_folio(struct file *file, struct folio *folio) { + struct page *page = &folio->page; struct inode *const inode = page->mapping->host; struct erofs_sb_info *const sbi = EROFS_I_SB(inode); struct z_erofs_decompress_frontend f = DECOMPRESS_FRONTEND_INIT(inode); @@ -1567,6 +1564,6 @@ static void z_erofs_readahead(struct readahead_control *rac) } const struct address_space_operations z_erofs_aops = { - .readpage = z_erofs_readpage, + .read_folio = z_erofs_read_folio, .readahead = z_erofs_readahead, }; diff --git a/fs/erofs/zdata.h b/fs/erofs/zdata.h index e043216b545f..800b11c53f57 100644 --- a/fs/erofs/zdata.h +++ b/fs/erofs/zdata.h @@ -97,7 +97,7 @@ struct z_erofs_decompressqueue { z_erofs_next_pcluster_t head; union { - wait_queue_head_t wait; + struct completion done; struct work_struct work; } u; }; diff --git a/fs/exfat/balloc.c b/fs/exfat/balloc.c index 03f142307174..9f42f25fab92 100644 --- a/fs/exfat/balloc.c +++ b/fs/exfat/balloc.c @@ -148,7 +148,9 @@ int exfat_set_bitmap(struct inode *inode, unsigned int clu, bool sync) struct super_block *sb = inode->i_sb; struct exfat_sb_info *sbi = EXFAT_SB(sb); - WARN_ON(clu < EXFAT_FIRST_CLUSTER); + if (!is_valid_cluster(sbi, clu)) + return -EINVAL; + ent_idx = CLUSTER_TO_BITMAP_ENT(clu); i = BITMAP_OFFSET_SECTOR_INDEX(sb, ent_idx); b = BITMAP_OFFSET_BIT_IN_SECTOR(sb, ent_idx); @@ -166,7 +168,9 @@ void exfat_clear_bitmap(struct inode *inode, unsigned int clu, bool sync) struct exfat_sb_info *sbi = EXFAT_SB(sb); struct exfat_mount_options *opts = &sbi->options; - WARN_ON(clu < EXFAT_FIRST_CLUSTER); + if (!is_valid_cluster(sbi, clu)) + return; + ent_idx = CLUSTER_TO_BITMAP_ENT(clu); i = BITMAP_OFFSET_SECTOR_INDEX(sb, ent_idx); b = BITMAP_OFFSET_BIT_IN_SECTOR(sb, ent_idx); diff --git a/fs/exfat/exfat_fs.h b/fs/exfat/exfat_fs.h index c6800b880920..4a7a2308eb72 100644 --- a/fs/exfat/exfat_fs.h +++ b/fs/exfat/exfat_fs.h @@ -203,6 +203,7 @@ struct exfat_mount_options { /* on error: continue, panic, remount-ro */ enum exfat_error_mode errors; unsigned utf8:1, /* Use of UTF-8 character set */ + sys_tz:1, /* Use local timezone */ discard:1, /* Issue discard requests on deletions */ keep_last_dots:1; /* Keep trailing periods in paths */ int time_offset; /* Offset of timestamps from UTC (in minutes) */ @@ -381,6 +382,12 @@ static inline int exfat_sector_to_cluster(struct exfat_sb_info *sbi, EXFAT_RESERVED_CLUSTERS; } +static inline bool is_valid_cluster(struct exfat_sb_info *sbi, + unsigned int clus) +{ + return clus >= EXFAT_FIRST_CLUSTER && clus < sbi->num_clusters; +} + /* super.c */ int exfat_set_volume_dirty(struct super_block *sb); int exfat_clear_volume_dirty(struct super_block *sb); diff --git a/fs/exfat/fatent.c b/fs/exfat/fatent.c index a3464e56a7e1..9de6a6b844c9 100644 --- a/fs/exfat/fatent.c +++ b/fs/exfat/fatent.c @@ -6,6 +6,7 @@ #include <linux/slab.h> #include <asm/unaligned.h> #include <linux/buffer_head.h> +#include <linux/blkdev.h> #include "exfat_raw.h" #include "exfat_fs.h" @@ -81,12 +82,6 @@ int exfat_ent_set(struct super_block *sb, unsigned int loc, return 0; } -static inline bool is_valid_cluster(struct exfat_sb_info *sbi, - unsigned int clus) -{ - return clus >= EXFAT_FIRST_CLUSTER && clus < sbi->num_clusters; -} - int exfat_ent_get(struct super_block *sb, unsigned int loc, unsigned int *content) { @@ -274,10 +269,9 @@ int exfat_zeroed_cluster(struct inode *dir, unsigned int clu) { struct super_block *sb = dir->i_sb; struct exfat_sb_info *sbi = EXFAT_SB(sb); - struct buffer_head *bhs[MAX_BUF_PER_PAGE]; - int nr_bhs = MAX_BUF_PER_PAGE; + struct buffer_head *bh; sector_t blknr, last_blknr; - int err, i, n; + int i; blknr = exfat_cluster_to_sector(sbi, clu); last_blknr = blknr + sbi->sect_per_clus; @@ -291,30 +285,23 @@ int exfat_zeroed_cluster(struct inode *dir, unsigned int clu) } /* Zeroing the unused blocks on this cluster */ - while (blknr < last_blknr) { - for (n = 0; n < nr_bhs && blknr < last_blknr; n++, blknr++) { - bhs[n] = sb_getblk(sb, blknr); - if (!bhs[n]) { - err = -ENOMEM; - goto release_bhs; - } - memset(bhs[n]->b_data, 0, sb->s_blocksize); - } - - err = exfat_update_bhs(bhs, n, IS_DIRSYNC(dir)); - if (err) - goto release_bhs; + for (i = blknr; i < last_blknr; i++) { + bh = sb_getblk(sb, i); + if (!bh) + return -ENOMEM; - for (i = 0; i < n; i++) - brelse(bhs[i]); + memset(bh->b_data, 0, sb->s_blocksize); + set_buffer_uptodate(bh); + mark_buffer_dirty(bh); + brelse(bh); } - return 0; -release_bhs: - exfat_err(sb, "failed zeroed sect %llu\n", (unsigned long long)blknr); - for (i = 0; i < n; i++) - bforget(bhs[i]); - return err; + if (IS_DIRSYNC(dir)) + return sync_blockdev_range(sb->s_bdev, + EXFAT_BLK_TO_B(blknr, sb), + EXFAT_BLK_TO_B(last_blknr, sb) - 1); + + return 0; } int exfat_alloc_cluster(struct inode *inode, unsigned int num_alloc, diff --git a/fs/exfat/file.c b/fs/exfat/file.c index 2f5130059236..20d4e47f57ab 100644 --- a/fs/exfat/file.c +++ b/fs/exfat/file.c @@ -351,21 +351,20 @@ out: static int exfat_ioctl_fitrim(struct inode *inode, unsigned long arg) { - struct request_queue *q = bdev_get_queue(inode->i_sb->s_bdev); struct fstrim_range range; int ret = 0; if (!capable(CAP_SYS_ADMIN)) return -EPERM; - if (!blk_queue_discard(q)) + if (!bdev_max_discard_sectors(inode->i_sb->s_bdev)) return -EOPNOTSUPP; if (copy_from_user(&range, (struct fstrim_range __user *)arg, sizeof(range))) return -EFAULT; range.minlen = max_t(unsigned int, range.minlen, - q->limits.discard_granularity); + bdev_discard_granularity(inode->i_sb->s_bdev)); ret = exfat_trim_fs(inode, &range); if (ret < 0) diff --git a/fs/exfat/inode.c b/fs/exfat/inode.c index fc0ea1684880..0133d385d8e8 100644 --- a/fs/exfat/inode.c +++ b/fs/exfat/inode.c @@ -357,9 +357,9 @@ unlock_ret: return err; } -static int exfat_readpage(struct file *file, struct page *page) +static int exfat_read_folio(struct file *file, struct folio *folio) { - return mpage_readpage(page, exfat_get_block); + return mpage_read_folio(folio, exfat_get_block); } static void exfat_readahead(struct readahead_control *rac) @@ -389,13 +389,13 @@ static void exfat_write_failed(struct address_space *mapping, loff_t to) } static int exfat_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned int len, unsigned int flags, + loff_t pos, unsigned int len, struct page **pagep, void **fsdata) { int ret; *pagep = NULL; - ret = cont_write_begin(file, mapping, pos, len, flags, pagep, fsdata, + ret = cont_write_begin(file, mapping, pos, len, pagep, fsdata, exfat_get_block, &EXFAT_I(mapping->host)->i_size_ondisk); @@ -492,7 +492,7 @@ int exfat_block_truncate_page(struct inode *inode, loff_t from) static const struct address_space_operations exfat_aops = { .dirty_folio = block_dirty_folio, .invalidate_folio = block_invalidate_folio, - .readpage = exfat_readpage, + .read_folio = exfat_read_folio, .readahead = exfat_readahead, .writepage = exfat_writepage, .writepages = exfat_writepages, diff --git a/fs/exfat/misc.c b/fs/exfat/misc.c index d5bd8e6d9741..9380e0188b55 100644 --- a/fs/exfat/misc.c +++ b/fs/exfat/misc.c @@ -74,6 +74,13 @@ static void exfat_adjust_tz(struct timespec64 *ts, u8 tz_off) ts->tv_sec += TIMEZONE_SEC(0x80 - tz_off); } +static inline int exfat_tz_offset(struct exfat_sb_info *sbi) +{ + if (sbi->options.sys_tz) + return -sys_tz.tz_minuteswest; + return sbi->options.time_offset; +} + /* Convert a EXFAT time/date pair to a UNIX date (seconds since 1 1 70). */ void exfat_get_entry_time(struct exfat_sb_info *sbi, struct timespec64 *ts, u8 tz, __le16 time, __le16 date, u8 time_cs) @@ -96,8 +103,7 @@ void exfat_get_entry_time(struct exfat_sb_info *sbi, struct timespec64 *ts, /* Adjust timezone to UTC0. */ exfat_adjust_tz(ts, tz & ~EXFAT_TZ_VALID); else - /* Convert from local time to UTC using time_offset. */ - ts->tv_sec -= sbi->options.time_offset * SECS_PER_MIN; + ts->tv_sec -= exfat_tz_offset(sbi) * SECS_PER_MIN; } /* Convert linear UNIX date to a EXFAT time/date pair. */ diff --git a/fs/exfat/namei.c b/fs/exfat/namei.c index a02a04a993bf..76acc3721951 100644 --- a/fs/exfat/namei.c +++ b/fs/exfat/namei.c @@ -1080,6 +1080,7 @@ static int exfat_rename_file(struct inode *inode, struct exfat_chain *p_dir, exfat_remove_entries(inode, p_dir, oldentry, 0, num_old_entries); + ei->dir = *p_dir; ei->entry = newentry; } else { if (exfat_get_entry_type(epold) == TYPE_FILE) { @@ -1167,28 +1168,6 @@ static int exfat_move_file(struct inode *inode, struct exfat_chain *p_olddir, return 0; } -static void exfat_update_parent_info(struct exfat_inode_info *ei, - struct inode *parent_inode) -{ - struct exfat_sb_info *sbi = EXFAT_SB(parent_inode->i_sb); - struct exfat_inode_info *parent_ei = EXFAT_I(parent_inode); - loff_t parent_isize = i_size_read(parent_inode); - - /* - * the problem that struct exfat_inode_info caches wrong parent info. - * - * because of flag-mismatch of ei->dir, - * there is abnormal traversing cluster chain. - */ - if (unlikely(parent_ei->flags != ei->dir.flags || - parent_isize != EXFAT_CLU_TO_B(ei->dir.size, sbi) || - parent_ei->start_clu != ei->dir.dir)) { - exfat_chain_set(&ei->dir, parent_ei->start_clu, - EXFAT_B_TO_CLU_ROUND_UP(parent_isize, sbi), - parent_ei->flags); - } -} - /* rename or move a old file into a new file */ static int __exfat_rename(struct inode *old_parent_inode, struct exfat_inode_info *ei, struct inode *new_parent_inode, @@ -1219,8 +1198,6 @@ static int __exfat_rename(struct inode *old_parent_inode, return -ENOENT; } - exfat_update_parent_info(ei, old_parent_inode); - exfat_chain_dup(&olddir, &ei->dir); dentry = ei->entry; @@ -1241,8 +1218,6 @@ static int __exfat_rename(struct inode *old_parent_inode, goto out; } - exfat_update_parent_info(new_ei, new_parent_inode); - p_dir = &(new_ei->dir); new_entry = new_ei->entry; ep = exfat_get_dentry(sb, p_dir, new_entry, &new_bh); diff --git a/fs/exfat/super.c b/fs/exfat/super.c index 8ca21e7917d1..6a4dfe9f31ee 100644 --- a/fs/exfat/super.c +++ b/fs/exfat/super.c @@ -170,7 +170,9 @@ static int exfat_show_options(struct seq_file *m, struct dentry *root) seq_puts(m, ",discard"); if (opts->keep_last_dots) seq_puts(m, ",keep_last_dots"); - if (opts->time_offset) + if (opts->sys_tz) + seq_puts(m, ",sys_tz"); + else if (opts->time_offset) seq_printf(m, ",time_offset=%d", opts->time_offset); return 0; } @@ -214,6 +216,7 @@ enum { Opt_errors, Opt_discard, Opt_keep_last_dots, + Opt_sys_tz, Opt_time_offset, /* Deprecated options */ @@ -241,6 +244,7 @@ static const struct fs_parameter_spec exfat_parameters[] = { fsparam_enum("errors", Opt_errors, exfat_param_enums), fsparam_flag("discard", Opt_discard), fsparam_flag("keep_last_dots", Opt_keep_last_dots), + fsparam_flag("sys_tz", Opt_sys_tz), fsparam_s32("time_offset", Opt_time_offset), __fsparam(NULL, "utf8", Opt_utf8, fs_param_deprecated, NULL), @@ -298,6 +302,9 @@ static int exfat_parse_param(struct fs_context *fc, struct fs_parameter *param) case Opt_keep_last_dots: opts->keep_last_dots = 1; break; + case Opt_sys_tz: + opts->sys_tz = 1; + break; case Opt_time_offset: /* * Make the limit 24 just in case someone invents something @@ -627,13 +634,9 @@ static int exfat_fill_super(struct super_block *sb, struct fs_context *fc) if (opts->allow_utime == (unsigned short)-1) opts->allow_utime = ~opts->fs_dmask & 0022; - if (opts->discard) { - struct request_queue *q = bdev_get_queue(sb->s_bdev); - - if (!blk_queue_discard(q)) { - exfat_warn(sb, "mounting with \"discard\" option, but the device does not support discard"); - opts->discard = 0; - } + if (opts->discard && !bdev_max_discard_sectors(sb->s_bdev)) { + exfat_warn(sb, "mounting with \"discard\" option, but the device does not support discard"); + opts->discard = 0; } sb->s_flags |= SB_NODIRATIME; diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 52377a0ee735..9e1ecd89f47f 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -875,9 +875,9 @@ static int ext2_writepage(struct page *page, struct writeback_control *wbc) return block_write_full_page(page, ext2_get_block, wbc); } -static int ext2_readpage(struct file *file, struct page *page) +static int ext2_read_folio(struct file *file, struct folio *folio) { - return mpage_readpage(page, ext2_get_block); + return mpage_read_folio(folio, ext2_get_block); } static void ext2_readahead(struct readahead_control *rac) @@ -887,13 +887,11 @@ static void ext2_readahead(struct readahead_control *rac) static int ext2_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, - struct page **pagep, void **fsdata) + loff_t pos, unsigned len, struct page **pagep, void **fsdata) { int ret; - ret = block_write_begin(mapping, pos, len, flags, pagep, - ext2_get_block); + ret = block_write_begin(mapping, pos, len, pagep, ext2_get_block); if (ret < 0) ext2_write_failed(mapping, pos + len); return ret; @@ -913,12 +911,11 @@ static int ext2_write_end(struct file *file, struct address_space *mapping, static int ext2_nobh_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, - struct page **pagep, void **fsdata) + loff_t pos, unsigned len, struct page **pagep, void **fsdata) { int ret; - ret = nobh_write_begin(mapping, pos, len, flags, pagep, fsdata, + ret = nobh_write_begin(mapping, pos, len, pagep, fsdata, ext2_get_block); if (ret < 0) ext2_write_failed(mapping, pos + len); @@ -969,7 +966,7 @@ ext2_dax_writepages(struct address_space *mapping, struct writeback_control *wbc const struct address_space_operations ext2_aops = { .dirty_folio = block_dirty_folio, .invalidate_folio = block_invalidate_folio, - .readpage = ext2_readpage, + .read_folio = ext2_read_folio, .readahead = ext2_readahead, .writepage = ext2_writepage, .write_begin = ext2_write_begin, @@ -985,7 +982,7 @@ const struct address_space_operations ext2_aops = { const struct address_space_operations ext2_nobh_aops = { .dirty_folio = block_dirty_folio, .invalidate_folio = block_invalidate_folio, - .readpage = ext2_readpage, + .read_folio = ext2_read_folio, .readahead = ext2_readahead, .writepage = ext2_nobh_writepage, .write_begin = ext2_nobh_write_begin, diff --git a/fs/ext4/Makefile b/fs/ext4/Makefile index 7d89142e1421..72206a292676 100644 --- a/fs/ext4/Makefile +++ b/fs/ext4/Makefile @@ -17,3 +17,4 @@ ext4-$(CONFIG_EXT4_FS_SECURITY) += xattr_security.o ext4-inode-test-objs += inode-test.o obj-$(CONFIG_EXT4_KUNIT_TESTS) += ext4-inode-test.o ext4-$(CONFIG_FS_VERITY) += verity.o +ext4-$(CONFIG_FS_ENCRYPTION) += crypto.o diff --git a/fs/ext4/crypto.c b/fs/ext4/crypto.c new file mode 100644 index 000000000000..e20ac0654b3f --- /dev/null +++ b/fs/ext4/crypto.c @@ -0,0 +1,246 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/quotaops.h> +#include <linux/uuid.h> + +#include "ext4.h" +#include "xattr.h" +#include "ext4_jbd2.h" + +static void ext4_fname_from_fscrypt_name(struct ext4_filename *dst, + const struct fscrypt_name *src) +{ + memset(dst, 0, sizeof(*dst)); + + dst->usr_fname = src->usr_fname; + dst->disk_name = src->disk_name; + dst->hinfo.hash = src->hash; + dst->hinfo.minor_hash = src->minor_hash; + dst->crypto_buf = src->crypto_buf; +} + +int ext4_fname_setup_filename(struct inode *dir, const struct qstr *iname, + int lookup, struct ext4_filename *fname) +{ + struct fscrypt_name name; + int err; + + err = fscrypt_setup_filename(dir, iname, lookup, &name); + if (err) + return err; + + ext4_fname_from_fscrypt_name(fname, &name); + +#if IS_ENABLED(CONFIG_UNICODE) + err = ext4_fname_setup_ci_filename(dir, iname, fname); +#endif + return err; +} + +int ext4_fname_prepare_lookup(struct inode *dir, struct dentry *dentry, + struct ext4_filename *fname) +{ + struct fscrypt_name name; + int err; + + err = fscrypt_prepare_lookup(dir, dentry, &name); + if (err) + return err; + + ext4_fname_from_fscrypt_name(fname, &name); + +#if IS_ENABLED(CONFIG_UNICODE) + err = ext4_fname_setup_ci_filename(dir, &dentry->d_name, fname); +#endif + return err; +} + +void ext4_fname_free_filename(struct ext4_filename *fname) +{ + struct fscrypt_name name; + + name.crypto_buf = fname->crypto_buf; + fscrypt_free_filename(&name); + + fname->crypto_buf.name = NULL; + fname->usr_fname = NULL; + fname->disk_name.name = NULL; + +#if IS_ENABLED(CONFIG_UNICODE) + kfree(fname->cf_name.name); + fname->cf_name.name = NULL; +#endif +} + +static bool uuid_is_zero(__u8 u[16]) +{ + int i; + + for (i = 0; i < 16; i++) + if (u[i]) + return false; + return true; +} + +int ext4_ioctl_get_encryption_pwsalt(struct file *filp, void __user *arg) +{ + struct super_block *sb = file_inode(filp)->i_sb; + struct ext4_sb_info *sbi = EXT4_SB(sb); + int err, err2; + handle_t *handle; + + if (!ext4_has_feature_encrypt(sb)) + return -EOPNOTSUPP; + + if (uuid_is_zero(sbi->s_es->s_encrypt_pw_salt)) { + err = mnt_want_write_file(filp); + if (err) + return err; + handle = ext4_journal_start_sb(sb, EXT4_HT_MISC, 1); + if (IS_ERR(handle)) { + err = PTR_ERR(handle); + goto pwsalt_err_exit; + } + err = ext4_journal_get_write_access(handle, sb, sbi->s_sbh, + EXT4_JTR_NONE); + if (err) + goto pwsalt_err_journal; + lock_buffer(sbi->s_sbh); + generate_random_uuid(sbi->s_es->s_encrypt_pw_salt); + ext4_superblock_csum_set(sb); + unlock_buffer(sbi->s_sbh); + err = ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh); +pwsalt_err_journal: + err2 = ext4_journal_stop(handle); + if (err2 && !err) + err = err2; +pwsalt_err_exit: + mnt_drop_write_file(filp); + if (err) + return err; + } + + if (copy_to_user(arg, sbi->s_es->s_encrypt_pw_salt, 16)) + return -EFAULT; + return 0; +} + +static int ext4_get_context(struct inode *inode, void *ctx, size_t len) +{ + return ext4_xattr_get(inode, EXT4_XATTR_INDEX_ENCRYPTION, + EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, ctx, len); +} + +static int ext4_set_context(struct inode *inode, const void *ctx, size_t len, + void *fs_data) +{ + handle_t *handle = fs_data; + int res, res2, credits, retries = 0; + + /* + * Encrypting the root directory is not allowed because e2fsck expects + * lost+found to exist and be unencrypted, and encrypting the root + * directory would imply encrypting the lost+found directory as well as + * the filename "lost+found" itself. + */ + if (inode->i_ino == EXT4_ROOT_INO) + return -EPERM; + + if (WARN_ON_ONCE(IS_DAX(inode) && i_size_read(inode))) + return -EINVAL; + + if (ext4_test_inode_flag(inode, EXT4_INODE_DAX)) + return -EOPNOTSUPP; + + res = ext4_convert_inline_data(inode); + if (res) + return res; + + /* + * If a journal handle was specified, then the encryption context is + * being set on a new inode via inheritance and is part of a larger + * transaction to create the inode. Otherwise the encryption context is + * being set on an existing inode in its own transaction. Only in the + * latter case should the "retry on ENOSPC" logic be used. + */ + + if (handle) { + res = ext4_xattr_set_handle(handle, inode, + EXT4_XATTR_INDEX_ENCRYPTION, + EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, + ctx, len, 0); + if (!res) { + ext4_set_inode_flag(inode, EXT4_INODE_ENCRYPT); + ext4_clear_inode_state(inode, + EXT4_STATE_MAY_INLINE_DATA); + /* + * Update inode->i_flags - S_ENCRYPTED will be enabled, + * S_DAX may be disabled + */ + ext4_set_inode_flags(inode, false); + } + return res; + } + + res = dquot_initialize(inode); + if (res) + return res; +retry: + res = ext4_xattr_set_credits(inode, len, false /* is_create */, + &credits); + if (res) + return res; + + handle = ext4_journal_start(inode, EXT4_HT_MISC, credits); + if (IS_ERR(handle)) + return PTR_ERR(handle); + + res = ext4_xattr_set_handle(handle, inode, EXT4_XATTR_INDEX_ENCRYPTION, + EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, + ctx, len, 0); + if (!res) { + ext4_set_inode_flag(inode, EXT4_INODE_ENCRYPT); + /* + * Update inode->i_flags - S_ENCRYPTED will be enabled, + * S_DAX may be disabled + */ + ext4_set_inode_flags(inode, false); + res = ext4_mark_inode_dirty(handle, inode); + if (res) + EXT4_ERROR_INODE(inode, "Failed to mark inode dirty"); + } + res2 = ext4_journal_stop(handle); + + if (res == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) + goto retry; + if (!res) + res = res2; + return res; +} + +static const union fscrypt_policy *ext4_get_dummy_policy(struct super_block *sb) +{ + return EXT4_SB(sb)->s_dummy_enc_policy.policy; +} + +static bool ext4_has_stable_inodes(struct super_block *sb) +{ + return ext4_has_feature_stable_inodes(sb); +} + +static void ext4_get_ino_and_lblk_bits(struct super_block *sb, + int *ino_bits_ret, int *lblk_bits_ret) +{ + *ino_bits_ret = 8 * sizeof(EXT4_SB(sb)->s_es->s_inodes_count); + *lblk_bits_ret = 8 * sizeof(ext4_lblk_t); +} + +const struct fscrypt_operations ext4_cryptops = { + .key_prefix = "ext4:", + .get_context = ext4_get_context, + .set_context = ext4_set_context, + .get_dummy_policy = ext4_get_dummy_policy, + .empty_dir = ext4_empty_dir, + .has_stable_inodes = ext4_has_stable_inodes, + .get_ino_and_lblk_bits = ext4_get_ino_and_lblk_bits, +}; diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c index a6bb86f52b9a..3985f8c33f95 100644 --- a/fs/ext4/dir.c +++ b/fs/ext4/dir.c @@ -412,7 +412,7 @@ struct fname { }; /* - * This functoin implements a non-recursive way of freeing all of the + * This function implements a non-recursive way of freeing all of the * nodes in the red-black tree. */ static void free_rb_tree_fname(struct rb_root *root) @@ -515,7 +515,7 @@ int ext4_htree_store_dirent(struct file *dir_file, __u32 hash, /* * This is a helper function for ext4_dx_readdir. It calls filldir - * for all entres on the fname linked list. (Normally there is only + * for all entries on the fname linked list. (Normally there is only * one entry on the linked list, unless there are 62 bit hash collisions.) */ static int call_filldir(struct file *file, struct dir_context *ctx, @@ -648,7 +648,7 @@ int ext4_check_all_de(struct inode *dir, struct buffer_head *bh, void *buf, unsigned int offset = 0; char *top; - de = (struct ext4_dir_entry_2 *)buf; + de = buf; top = buf + buf_size; while ((char *) de < top) { if (ext4_check_dir_entry(dir, NULL, de, bh, diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 3f87cca49f0c..75b8d81b2469 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -673,6 +673,8 @@ enum { /* Caller will submit data before dropping transaction handle. This * allows jbd2 to avoid submitting data before commit. */ #define EXT4_GET_BLOCKS_IO_SUBMIT 0x0400 + /* Caller is in the atomic contex, find extent if it has been cached */ +#define EXT4_GET_BLOCKS_CACHED_NOWAIT 0x0800 /* * The bit position of these flags must not overlap with any of the @@ -1440,12 +1442,6 @@ struct ext4_super_block { #ifdef __KERNEL__ -#ifdef CONFIG_FS_ENCRYPTION -#define DUMMY_ENCRYPTION_ENABLED(sbi) ((sbi)->s_dummy_enc_policy.policy != NULL) -#else -#define DUMMY_ENCRYPTION_ENABLED(sbi) (0) -#endif - /* Number of quota types we support */ #define EXT4_MAXQUOTAS 3 @@ -2273,6 +2269,10 @@ static inline int ext4_forced_shutdown(struct ext4_sb_info *sbi) * Structure of a directory entry */ #define EXT4_NAME_LEN 255 +/* + * Base length of the ext4 directory entry excluding the name length + */ +#define EXT4_BASE_DIR_LEN (sizeof(struct ext4_dir_entry_2) - EXT4_NAME_LEN) struct ext4_dir_entry { __le32 inode; /* Inode number */ @@ -2727,74 +2727,20 @@ extern int ext4_fname_setup_ci_filename(struct inode *dir, struct ext4_filename *fname); #endif +/* ext4 encryption related stuff goes here crypto.c */ #ifdef CONFIG_FS_ENCRYPTION -static inline void ext4_fname_from_fscrypt_name(struct ext4_filename *dst, - const struct fscrypt_name *src) -{ - memset(dst, 0, sizeof(*dst)); - - dst->usr_fname = src->usr_fname; - dst->disk_name = src->disk_name; - dst->hinfo.hash = src->hash; - dst->hinfo.minor_hash = src->minor_hash; - dst->crypto_buf = src->crypto_buf; -} - -static inline int ext4_fname_setup_filename(struct inode *dir, - const struct qstr *iname, - int lookup, - struct ext4_filename *fname) -{ - struct fscrypt_name name; - int err; - - err = fscrypt_setup_filename(dir, iname, lookup, &name); - if (err) - return err; - - ext4_fname_from_fscrypt_name(fname, &name); - -#if IS_ENABLED(CONFIG_UNICODE) - err = ext4_fname_setup_ci_filename(dir, iname, fname); -#endif - return err; -} - -static inline int ext4_fname_prepare_lookup(struct inode *dir, - struct dentry *dentry, - struct ext4_filename *fname) -{ - struct fscrypt_name name; - int err; +extern const struct fscrypt_operations ext4_cryptops; - err = fscrypt_prepare_lookup(dir, dentry, &name); - if (err) - return err; - - ext4_fname_from_fscrypt_name(fname, &name); - -#if IS_ENABLED(CONFIG_UNICODE) - err = ext4_fname_setup_ci_filename(dir, &dentry->d_name, fname); -#endif - return err; -} +int ext4_fname_setup_filename(struct inode *dir, const struct qstr *iname, + int lookup, struct ext4_filename *fname); -static inline void ext4_fname_free_filename(struct ext4_filename *fname) -{ - struct fscrypt_name name; +int ext4_fname_prepare_lookup(struct inode *dir, struct dentry *dentry, + struct ext4_filename *fname); - name.crypto_buf = fname->crypto_buf; - fscrypt_free_filename(&name); +void ext4_fname_free_filename(struct ext4_filename *fname); - fname->crypto_buf.name = NULL; - fname->usr_fname = NULL; - fname->disk_name.name = NULL; +int ext4_ioctl_get_encryption_pwsalt(struct file *filp, void __user *arg); -#if IS_ENABLED(CONFIG_UNICODE) - kfree(fname->cf_name.name); - fname->cf_name.name = NULL; -#endif -} #else /* !CONFIG_FS_ENCRYPTION */ static inline int ext4_fname_setup_filename(struct inode *dir, const struct qstr *iname, @@ -2827,6 +2773,12 @@ static inline void ext4_fname_free_filename(struct ext4_filename *fname) fname->cf_name.name = NULL; #endif } + +static inline int ext4_ioctl_get_encryption_pwsalt(struct file *filp, + void __user *arg) +{ + return -EOPNOTSUPP; +} #endif /* !CONFIG_FS_ENCRYPTION */ /* dir.c */ @@ -3032,7 +2984,7 @@ extern int ext4_inode_attach_jinode(struct inode *inode); extern int ext4_can_truncate(struct inode *inode); extern int ext4_truncate(struct inode *); extern int ext4_break_layouts(struct inode *); -extern int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length); +extern int ext4_punch_hole(struct file *file, loff_t offset, loff_t length); extern void ext4_set_inode_flags(struct inode *, bool init); extern int ext4_alloc_da_blocks(struct inode *inode); extern void ext4_set_aops(struct inode *inode); @@ -3064,6 +3016,7 @@ int ext4_fileattr_set(struct user_namespace *mnt_userns, struct dentry *dentry, struct fileattr *fa); int ext4_fileattr_get(struct dentry *dentry, struct fileattr *fa); extern void ext4_reset_inode_seed(struct inode *inode); +int ext4_update_overhead(struct super_block *sb); /* migrate.c */ extern int ext4_ext_migrate(struct inode *); @@ -3586,7 +3539,6 @@ extern int ext4_readpage_inline(struct inode *inode, struct page *page); extern int ext4_try_to_write_inline_data(struct address_space *mapping, struct inode *inode, loff_t pos, unsigned len, - unsigned flags, struct page **pagep); extern int ext4_write_inline_data_end(struct inode *inode, loff_t pos, unsigned len, @@ -3599,7 +3551,6 @@ ext4_journalled_write_inline_data(struct inode *inode, extern int ext4_da_write_inline_data_begin(struct address_space *mapping, struct inode *inode, loff_t pos, unsigned len, - unsigned flags, struct page **pagep, void **fsdata); extern int ext4_try_add_inline_entry(handle_t *handle, diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 0d98cf402282..c148bb97b527 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -372,7 +372,7 @@ static int ext4_valid_extent_entries(struct inode *inode, { unsigned short entries; ext4_lblk_t lblock = 0; - ext4_lblk_t prev = 0; + ext4_lblk_t cur = 0; if (eh->eh_entries == 0) return 1; @@ -396,11 +396,11 @@ static int ext4_valid_extent_entries(struct inode *inode, /* Check for overlapping extents */ lblock = le32_to_cpu(ext->ee_block); - if ((lblock <= prev) && prev) { + if (lblock < cur) { *pblk = ext4_ext_pblock(ext); return 0; } - prev = lblock + ext4_ext_get_actual_len(ext) - 1; + cur = lblock + ext4_ext_get_actual_len(ext); ext++; entries--; } @@ -420,13 +420,13 @@ static int ext4_valid_extent_entries(struct inode *inode, /* Check for overlapping index extents */ lblock = le32_to_cpu(ext_idx->ei_block); - if ((lblock <= prev) && prev) { + if (lblock < cur) { *pblk = ext4_idx_pblock(ext_idx); return 0; } ext_idx++; entries--; - prev = lblock; + cur = lblock + 1; } } return 1; @@ -4500,9 +4500,9 @@ retry: return ret > 0 ? ret2 : ret; } -static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len); +static int ext4_collapse_range(struct file *file, loff_t offset, loff_t len); -static int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len); +static int ext4_insert_range(struct file *file, loff_t offset, loff_t len); static long ext4_zero_range(struct file *file, loff_t offset, loff_t len, int mode) @@ -4574,6 +4574,10 @@ static long ext4_zero_range(struct file *file, loff_t offset, /* Wait all existing dio workers, newcomers will block on i_rwsem */ inode_dio_wait(inode); + ret = file_modified(file); + if (ret) + goto out_mutex; + /* Preallocate the range including the unaligned edges */ if (partial_begin || partial_end) { ret = ext4_alloc_file_blocks(file, @@ -4689,22 +4693,24 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len) FALLOC_FL_INSERT_RANGE)) return -EOPNOTSUPP; - if (mode & FALLOC_FL_PUNCH_HOLE) { - ret = ext4_punch_hole(inode, offset, len); - goto exit; - } - + inode_lock(inode); ret = ext4_convert_inline_data(inode); + inode_unlock(inode); if (ret) goto exit; + if (mode & FALLOC_FL_PUNCH_HOLE) { + ret = ext4_punch_hole(file, offset, len); + goto exit; + } + if (mode & FALLOC_FL_COLLAPSE_RANGE) { - ret = ext4_collapse_range(inode, offset, len); + ret = ext4_collapse_range(file, offset, len); goto exit; } if (mode & FALLOC_FL_INSERT_RANGE) { - ret = ext4_insert_range(inode, offset, len); + ret = ext4_insert_range(file, offset, len); goto exit; } @@ -4740,6 +4746,10 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len) /* Wait all existing dio workers, newcomers will block on i_rwsem */ inode_dio_wait(inode); + ret = file_modified(file); + if (ret) + goto out; + ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size, flags); if (ret) goto out; @@ -5241,8 +5251,9 @@ out: * This implements the fallocate's collapse range functionality for ext4 * Returns: 0 and non-zero on error. */ -static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len) +static int ext4_collapse_range(struct file *file, loff_t offset, loff_t len) { + struct inode *inode = file_inode(file); struct super_block *sb = inode->i_sb; struct address_space *mapping = inode->i_mapping; ext4_lblk_t punch_start, punch_stop; @@ -5294,6 +5305,10 @@ static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len) /* Wait for existing dio to complete */ inode_dio_wait(inode); + ret = file_modified(file); + if (ret) + goto out_mutex; + /* * Prevent page faults from reinstantiating pages we have released from * page cache. @@ -5387,8 +5402,9 @@ out_mutex: * by len bytes. * Returns 0 on success, error otherwise. */ -static int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len) +static int ext4_insert_range(struct file *file, loff_t offset, loff_t len) { + struct inode *inode = file_inode(file); struct super_block *sb = inode->i_sb; struct address_space *mapping = inode->i_mapping; handle_t *handle; @@ -5445,6 +5461,10 @@ static int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len) /* Wait for existing dio to complete */ inode_dio_wait(inode); + ret = file_modified(file); + if (ret) + goto out_mutex; + /* * Prevent page faults from reinstantiating pages we have released from * page cache. diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c index 3d72565ec6e8..795a60ad1897 100644 --- a/fs/ext4/fast_commit.c +++ b/fs/ext4/fast_commit.c @@ -970,7 +970,7 @@ static int ext4_fc_write_inode_data(struct inode *inode, u32 *crc) /* Submit data for all the fast commit inodes */ static int ext4_fc_submit_inode_data_all(journal_t *journal) { - struct super_block *sb = (struct super_block *)(journal->j_private); + struct super_block *sb = journal->j_private; struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_inode_info *ei; int ret = 0; @@ -1004,7 +1004,7 @@ static int ext4_fc_submit_inode_data_all(journal_t *journal) /* Wait for completion of data for all the fast commit inodes */ static int ext4_fc_wait_inode_data_all(journal_t *journal) { - struct super_block *sb = (struct super_block *)(journal->j_private); + struct super_block *sb = journal->j_private; struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_inode_info *pos, *n; int ret = 0; @@ -1031,7 +1031,7 @@ static int ext4_fc_commit_dentry_updates(journal_t *journal, u32 *crc) __acquires(&sbi->s_fc_lock) __releases(&sbi->s_fc_lock) { - struct super_block *sb = (struct super_block *)(journal->j_private); + struct super_block *sb = journal->j_private; struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_fc_dentry_update *fc_dentry, *fc_dentry_n; struct inode *inode; @@ -1093,7 +1093,7 @@ lock_and_exit: static int ext4_fc_perform_commit(journal_t *journal) { - struct super_block *sb = (struct super_block *)(journal->j_private); + struct super_block *sb = journal->j_private; struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_inode_info *iter; struct ext4_fc_head head; @@ -1198,7 +1198,7 @@ static void ext4_fc_update_stats(struct super_block *sb, int status, */ int ext4_fc_commit(journal_t *journal, tid_t commit_tid) { - struct super_block *sb = (struct super_block *)(journal->j_private); + struct super_block *sb = journal->j_private; struct ext4_sb_info *sbi = EXT4_SB(sb); int nblks = 0, ret, bsize = journal->j_blocksize; int subtid = atomic_read(&sbi->s_fc_subtid); @@ -1659,8 +1659,7 @@ static int ext4_fc_replay_create(struct super_block *sb, struct ext4_fc_tl *tl, set_nlink(inode, 1); ext4_mark_inode_dirty(NULL, inode); out: - if (inode) - iput(inode); + iput(inode); return ret; } diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 6feb07e3e1eb..109d07629f81 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -76,7 +76,7 @@ static ssize_t ext4_dio_read_iter(struct kiocb *iocb, struct iov_iter *to) return generic_file_read_iter(iocb, to); } - ret = iomap_dio_rw(iocb, to, &ext4_iomap_ops, NULL, 0, 0); + ret = iomap_dio_rw(iocb, to, &ext4_iomap_ops, NULL, 0, NULL, 0); inode_unlock_shared(inode); file_accessed(iocb->ki_filp); @@ -565,7 +565,7 @@ static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from) iomap_ops = &ext4_iomap_overwrite_ops; ret = iomap_dio_rw(iocb, from, iomap_ops, &ext4_dio_write_ops, (unaligned_io || extend) ? IOMAP_DIO_FORCE_WAIT : 0, - 0); + NULL, 0); if (ret == -ENOTBLK) ret = 0; diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index 9c076262770d..cff52ff6549d 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -527,13 +527,13 @@ int ext4_readpage_inline(struct inode *inode, struct page *page) } static int ext4_convert_inline_data_to_extent(struct address_space *mapping, - struct inode *inode, - unsigned flags) + struct inode *inode) { int ret, needed_blocks, no_expand; handle_t *handle = NULL; int retries = 0, sem_held = 0; struct page *page = NULL; + unsigned int flags; unsigned from, to; struct ext4_iloc iloc; @@ -562,9 +562,9 @@ retry: /* We cannot recurse into the filesystem as the transaction is already * started */ - flags |= AOP_FLAG_NOFS; - - page = grab_cache_page_write_begin(mapping, 0, flags); + flags = memalloc_nofs_save(); + page = grab_cache_page_write_begin(mapping, 0); + memalloc_nofs_restore(flags); if (!page) { ret = -ENOMEM; goto out; @@ -649,11 +649,11 @@ out: int ext4_try_to_write_inline_data(struct address_space *mapping, struct inode *inode, loff_t pos, unsigned len, - unsigned flags, struct page **pagep) { int ret; handle_t *handle; + unsigned int flags; struct page *page; struct ext4_iloc iloc; @@ -691,9 +691,9 @@ int ext4_try_to_write_inline_data(struct address_space *mapping, if (ret) goto out; - flags |= AOP_FLAG_NOFS; - - page = grab_cache_page_write_begin(mapping, 0, flags); + flags = memalloc_nofs_save(); + page = grab_cache_page_write_begin(mapping, 0); + memalloc_nofs_restore(flags); if (!page) { ret = -ENOMEM; goto out; @@ -727,8 +727,7 @@ out: brelse(iloc.bh); return ret; convert: - return ext4_convert_inline_data_to_extent(mapping, - inode, flags); + return ext4_convert_inline_data_to_extent(mapping, inode); } int ext4_write_inline_data_end(struct inode *inode, loff_t pos, unsigned len, @@ -848,13 +847,12 @@ ext4_journalled_write_inline_data(struct inode *inode, */ static int ext4_da_convert_inline_data_to_extent(struct address_space *mapping, struct inode *inode, - unsigned flags, void **fsdata) { int ret = 0, inline_size; struct page *page; - page = grab_cache_page_write_begin(mapping, 0, flags); + page = grab_cache_page_write_begin(mapping, 0); if (!page) return -ENOMEM; @@ -907,7 +905,6 @@ out: int ext4_da_write_inline_data_begin(struct address_space *mapping, struct inode *inode, loff_t pos, unsigned len, - unsigned flags, struct page **pagep, void **fsdata) { @@ -916,6 +913,7 @@ int ext4_da_write_inline_data_begin(struct address_space *mapping, struct page *page; struct ext4_iloc iloc; int retries = 0; + unsigned int flags; ret = ext4_get_inode_loc(inode, &iloc); if (ret) @@ -932,17 +930,10 @@ retry_journal: if (ret && ret != -ENOSPC) goto out_journal; - /* - * We cannot recurse into the filesystem as the transaction - * is already started. - */ - flags |= AOP_FLAG_NOFS; - if (ret == -ENOSPC) { ext4_journal_stop(handle); ret = ext4_da_convert_inline_data_to_extent(mapping, inode, - flags, fsdata); if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) @@ -950,7 +941,13 @@ retry_journal: goto out; } - page = grab_cache_page_write_begin(mapping, 0, flags); + /* + * We cannot recurse into the filesystem as the transaction + * is already started. + */ + flags = memalloc_nofs_save(); + page = grab_cache_page_write_begin(mapping, 0); + memalloc_nofs_restore(flags); if (!page) { ret = -ENOMEM; goto out_journal; @@ -1083,14 +1080,14 @@ static void ext4_update_final_de(void *de_buf, int old_size, int new_size) void *limit; int de_len; - de = (struct ext4_dir_entry_2 *)de_buf; + de = de_buf; if (old_size) { limit = de_buf + old_size; do { prev_de = de; de_len = ext4_rec_len_from_disk(de->rec_len, old_size); de_buf += de_len; - de = (struct ext4_dir_entry_2 *)de_buf; + de = de_buf; } while (de_buf < limit); prev_de->rec_len = ext4_rec_len_to_disk(de_len + new_size - @@ -1155,7 +1152,7 @@ static int ext4_finish_convert_inline_dir(handle_t *handle, * First create "." and ".." and then copy the dir information * back to the block. */ - de = (struct ext4_dir_entry_2 *)target; + de = target; de = ext4_init_dot_dotdot(inode, de, inode->i_sb->s_blocksize, csum_size, le32_to_cpu(((struct ext4_dir_entry_2 *)buf)->inode), 1); @@ -2005,6 +2002,18 @@ int ext4_convert_inline_data(struct inode *inode) if (!ext4_has_inline_data(inode)) { ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); return 0; + } else if (!ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) { + /* + * Inode has inline data but EXT4_STATE_MAY_INLINE_DATA is + * cleared. This means we are in the middle of moving of + * inline data to delay allocated block. Just force writeout + * here to finish conversion. + */ + error = filemap_flush(inode->i_mapping); + if (error) + return error; + if (!ext4_has_inline_data(inode)) + return 0; } needed_blocks = ext4_writepage_trans_blocks(inode); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 13740f2d0e61..3dce7d058985 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -41,7 +41,6 @@ #include <linux/bitops.h> #include <linux/iomap.h> #include <linux/iversion.h> -#include <linux/dax.h> #include "ext4_jbd2.h" #include "xattr.h" @@ -199,8 +198,7 @@ void ext4_evict_inode(struct inode *inode) */ if (inode->i_ino != EXT4_JOURNAL_INO && ext4_should_journal_data(inode) && - (S_ISLNK(inode->i_mode) || S_ISREG(inode->i_mode)) && - inode->i_data.nrpages) { + S_ISREG(inode->i_mode) && inode->i_data.nrpages) { journal_t *journal = EXT4_SB(inode->i_sb)->s_journal; tid_t commit_tid = EXT4_I(inode)->i_datasync_tid; @@ -545,12 +543,21 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode, } else { BUG(); } + + if (flags & EXT4_GET_BLOCKS_CACHED_NOWAIT) + return retval; #ifdef ES_AGGRESSIVE_TEST ext4_map_blocks_es_recheck(handle, inode, map, &orig_map, flags); #endif goto found; } + /* + * In the query cache no-wait mode, nothing we can do more if we + * cannot find extent in the cache. + */ + if (flags & EXT4_GET_BLOCKS_CACHED_NOWAIT) + return 0; /* * Try to see if we can get the block without requesting a new @@ -837,10 +844,12 @@ struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode, struct ext4_map_blocks map; struct buffer_head *bh; int create = map_flags & EXT4_GET_BLOCKS_CREATE; + bool nowait = map_flags & EXT4_GET_BLOCKS_CACHED_NOWAIT; int err; ASSERT((EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) || handle != NULL || create == 0); + ASSERT(create == 0 || !nowait); map.m_lblk = block; map.m_len = 1; @@ -851,6 +860,9 @@ struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode, if (err < 0) return ERR_PTR(err); + if (nowait) + return sb_find_get_block(inode->i_sb, map.m_pblk); + bh = sb_getblk(inode->i_sb, map.m_pblk); if (unlikely(!bh)) return ERR_PTR(-ENOMEM); @@ -1130,7 +1142,7 @@ static int ext4_block_write_begin(struct page *page, loff_t pos, unsigned len, #endif static int ext4_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, + loff_t pos, unsigned len, struct page **pagep, void **fsdata) { struct inode *inode = mapping->host; @@ -1144,7 +1156,7 @@ static int ext4_write_begin(struct file *file, struct address_space *mapping, if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) return -EIO; - trace_ext4_write_begin(inode, pos, len, flags); + trace_ext4_write_begin(inode, pos, len); /* * Reserve one block more for addition to orphan list in case * we allocate blocks but write fails for some reason @@ -1156,7 +1168,7 @@ static int ext4_write_begin(struct file *file, struct address_space *mapping, if (ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) { ret = ext4_try_to_write_inline_data(mapping, inode, pos, len, - flags, pagep); + pagep); if (ret < 0) return ret; if (ret == 1) @@ -1171,7 +1183,7 @@ static int ext4_write_begin(struct file *file, struct address_space *mapping, * the page (if needed) without using GFP_NOFS. */ retry_grab: - page = grab_cache_page_write_begin(mapping, index, flags); + page = grab_cache_page_write_begin(mapping, index); if (!page) return -ENOMEM; unlock_page(page); @@ -2931,7 +2943,7 @@ static int ext4_nonda_switch(struct super_block *sb) } static int ext4_da_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, + loff_t pos, unsigned len, struct page **pagep, void **fsdata) { int ret, retries = 0; @@ -2944,18 +2956,16 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping, index = pos >> PAGE_SHIFT; - if (ext4_nonda_switch(inode->i_sb) || S_ISLNK(inode->i_mode) || - ext4_verity_in_progress(inode)) { + if (ext4_nonda_switch(inode->i_sb) || ext4_verity_in_progress(inode)) { *fsdata = (void *)FALL_BACK_TO_NONDELALLOC; return ext4_write_begin(file, mapping, pos, - len, flags, pagep, fsdata); + len, pagep, fsdata); } *fsdata = (void *)0; - trace_ext4_da_write_begin(inode, pos, len, flags); + trace_ext4_da_write_begin(inode, pos, len); if (ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) { - ret = ext4_da_write_inline_data_begin(mapping, inode, - pos, len, flags, + ret = ext4_da_write_inline_data_begin(mapping, inode, pos, len, pagep, fsdata); if (ret < 0) return ret; @@ -2964,7 +2974,7 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping, } retry: - page = grab_cache_page_write_begin(mapping, index, flags); + page = grab_cache_page_write_begin(mapping, index); if (!page) return -ENOMEM; @@ -3181,8 +3191,9 @@ static sector_t ext4_bmap(struct address_space *mapping, sector_t block) return iomap_bmap(mapping, block, &ext4_iomap_ops); } -static int ext4_readpage(struct file *file, struct page *page) +static int ext4_read_folio(struct file *file, struct folio *folio) { + struct page *page = &folio->page; int ret = -EAGAIN; struct inode *inode = page->mapping->host; @@ -3243,19 +3254,19 @@ static void ext4_journalled_invalidate_folio(struct folio *folio, WARN_ON(__ext4_journalled_invalidate_folio(folio, offset, length) < 0); } -static int ext4_releasepage(struct page *page, gfp_t wait) +static bool ext4_release_folio(struct folio *folio, gfp_t wait) { - journal_t *journal = EXT4_JOURNAL(page->mapping->host); + journal_t *journal = EXT4_JOURNAL(folio->mapping->host); - trace_ext4_releasepage(page); + trace_ext4_releasepage(&folio->page); /* Page has dirty journalled data -> cannot release */ - if (PageChecked(page)) - return 0; + if (folio_test_checked(folio)) + return false; if (journal) - return jbd2_journal_try_to_free_buffers(journal, page); + return jbd2_journal_try_to_free_buffers(journal, folio); else - return try_to_free_buffers(page); + return try_to_free_buffers(folio); } static bool ext4_inode_datasync_dirty(struct inode *inode) @@ -3609,7 +3620,7 @@ static int ext4_iomap_swap_activate(struct swap_info_struct *sis, } static const struct address_space_operations ext4_aops = { - .readpage = ext4_readpage, + .read_folio = ext4_read_folio, .readahead = ext4_readahead, .writepage = ext4_writepage, .writepages = ext4_writepages, @@ -3618,7 +3629,7 @@ static const struct address_space_operations ext4_aops = { .dirty_folio = ext4_dirty_folio, .bmap = ext4_bmap, .invalidate_folio = ext4_invalidate_folio, - .releasepage = ext4_releasepage, + .release_folio = ext4_release_folio, .direct_IO = noop_direct_IO, .migratepage = buffer_migrate_page, .is_partially_uptodate = block_is_partially_uptodate, @@ -3627,7 +3638,7 @@ static const struct address_space_operations ext4_aops = { }; static const struct address_space_operations ext4_journalled_aops = { - .readpage = ext4_readpage, + .read_folio = ext4_read_folio, .readahead = ext4_readahead, .writepage = ext4_writepage, .writepages = ext4_writepages, @@ -3636,7 +3647,7 @@ static const struct address_space_operations ext4_journalled_aops = { .dirty_folio = ext4_journalled_dirty_folio, .bmap = ext4_bmap, .invalidate_folio = ext4_journalled_invalidate_folio, - .releasepage = ext4_releasepage, + .release_folio = ext4_release_folio, .direct_IO = noop_direct_IO, .is_partially_uptodate = block_is_partially_uptodate, .error_remove_page = generic_error_remove_page, @@ -3644,7 +3655,7 @@ static const struct address_space_operations ext4_journalled_aops = { }; static const struct address_space_operations ext4_da_aops = { - .readpage = ext4_readpage, + .read_folio = ext4_read_folio, .readahead = ext4_readahead, .writepage = ext4_writepage, .writepages = ext4_writepages, @@ -3653,7 +3664,7 @@ static const struct address_space_operations ext4_da_aops = { .dirty_folio = ext4_dirty_folio, .bmap = ext4_bmap, .invalidate_folio = ext4_invalidate_folio, - .releasepage = ext4_releasepage, + .release_folio = ext4_release_folio, .direct_IO = noop_direct_IO, .migratepage = buffer_migrate_page, .is_partially_uptodate = block_is_partially_uptodate, @@ -3953,27 +3964,20 @@ int ext4_break_layouts(struct inode *inode) * Returns: 0 on success or negative on failure */ -int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length) +int ext4_punch_hole(struct file *file, loff_t offset, loff_t length) { + struct inode *inode = file_inode(file); struct super_block *sb = inode->i_sb; ext4_lblk_t first_block, stop_block; struct address_space *mapping = inode->i_mapping; - loff_t first_block_offset, last_block_offset; + loff_t first_block_offset, last_block_offset, max_length; + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); handle_t *handle; unsigned int credits; int ret = 0, ret2 = 0; trace_ext4_punch_hole(inode, offset, length, 0); - ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); - if (ext4_has_inline_data(inode)) { - filemap_invalidate_lock(mapping); - ret = ext4_convert_inline_data(inode); - filemap_invalidate_unlock(mapping); - if (ret) - return ret; - } - /* * Write out all dirty pages to avoid race conditions * Then release them. @@ -4001,6 +4005,14 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length) offset; } + /* + * For punch hole the length + offset needs to be within one block + * before last range. Adjust the length if it goes beyond that limit. + */ + max_length = sbi->s_bitmap_maxbytes - inode->i_sb->s_blocksize; + if (offset + length > max_length) + length = max_length - offset; + if (offset & (sb->s_blocksize - 1) || (offset + length) & (sb->s_blocksize - 1)) { /* @@ -4016,6 +4028,10 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length) /* Wait all existing dio workers, newcomers will block on i_rwsem */ inode_dio_wait(inode); + ret = file_modified(file); + if (ret) + goto out_mutex; + /* * Prevent page faults from reinstantiating pages we have released from * page cache. @@ -4977,7 +4993,6 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, } if (IS_ENCRYPTED(inode)) { inode->i_op = &ext4_encrypted_symlink_inode_operations; - ext4_set_aops(inode); } else if (ext4_inode_is_fast_symlink(inode)) { inode->i_link = (char *)ei->i_data; inode->i_op = &ext4_fast_symlink_inode_operations; @@ -4985,9 +5000,7 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, sizeof(ei->i_data) - 1); } else { inode->i_op = &ext4_symlink_inode_operations; - ext4_set_aops(inode); } - inode_nohighmem(inode); } else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) || S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) { inode->i_op = &ext4_special_inode_operations; @@ -5384,6 +5397,7 @@ int ext4_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, if (attr->ia_valid & ATTR_SIZE) { handle_t *handle; loff_t oldsize = inode->i_size; + loff_t old_disksize; int shrink = (attr->ia_size < inode->i_size); if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) { @@ -5455,6 +5469,7 @@ int ext4_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, inode->i_sb->s_blocksize_bits); down_write(&EXT4_I(inode)->i_data_sem); + old_disksize = EXT4_I(inode)->i_disksize; EXT4_I(inode)->i_disksize = attr->ia_size; rc = ext4_mark_inode_dirty(handle, inode); if (!error) @@ -5466,6 +5481,8 @@ int ext4_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, */ if (!error) i_size_write(inode, attr->ia_size); + else + EXT4_I(inode)->i_disksize = old_disksize; up_write(&EXT4_I(inode)->i_data_sem); ext4_journal_stop(handle); if (error) diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index 992229ca2d83..cb01c1da0f9d 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -16,7 +16,6 @@ #include <linux/file.h> #include <linux/quotaops.h> #include <linux/random.h> -#include <linux/uuid.h> #include <linux/uaccess.h> #include <linux/delay.h> #include <linux/iversion.h> @@ -504,18 +503,6 @@ journal_err_out: return err; } -#ifdef CONFIG_FS_ENCRYPTION -static int uuid_is_zero(__u8 u[16]) -{ - int i; - - for (i = 0; i < 16; i++) - if (u[i]) - return 0; - return 1; -} -#endif - /* * If immutable is set and we are not clearing it, we're not allowed to change * anything else in the inode. Don't error out if we're only trying to set @@ -1044,7 +1031,6 @@ static int ext4_ioctl_checkpoint(struct file *filp, unsigned long arg) __u32 flags = 0; unsigned int flush_flags = 0; struct super_block *sb = file_inode(filp)->i_sb; - struct request_queue *q; if (copy_from_user(&flags, (__u32 __user *)arg, sizeof(__u32))) @@ -1065,10 +1051,8 @@ static int ext4_ioctl_checkpoint(struct file *filp, unsigned long arg) if (flags & ~EXT4_IOC_CHECKPOINT_FLAG_VALID) return -EINVAL; - q = bdev_get_queue(EXT4_SB(sb)->s_journal->j_dev); - if (!q) - return -ENXIO; - if ((flags & JBD2_JOURNAL_FLUSH_DISCARD) && !blk_queue_discard(q)) + if ((flags & JBD2_JOURNAL_FLUSH_DISCARD) && + !bdev_max_discard_sectors(EXT4_SB(sb)->s_journal->j_dev)) return -EOPNOTSUPP; if (flags & EXT4_IOC_CHECKPOINT_FLAG_DRY_RUN) @@ -1393,14 +1377,13 @@ resizefs_out: case FITRIM: { - struct request_queue *q = bdev_get_queue(sb->s_bdev); struct fstrim_range range; int ret = 0; if (!capable(CAP_SYS_ADMIN)) return -EPERM; - if (!blk_queue_discard(q)) + if (!bdev_max_discard_sectors(sb->s_bdev)) return -EOPNOTSUPP; /* @@ -1432,51 +1415,9 @@ resizefs_out: return -EOPNOTSUPP; return fscrypt_ioctl_set_policy(filp, (const void __user *)arg); - case FS_IOC_GET_ENCRYPTION_PWSALT: { -#ifdef CONFIG_FS_ENCRYPTION - int err, err2; - struct ext4_sb_info *sbi = EXT4_SB(sb); - handle_t *handle; + case FS_IOC_GET_ENCRYPTION_PWSALT: + return ext4_ioctl_get_encryption_pwsalt(filp, (void __user *)arg); - if (!ext4_has_feature_encrypt(sb)) - return -EOPNOTSUPP; - if (uuid_is_zero(sbi->s_es->s_encrypt_pw_salt)) { - err = mnt_want_write_file(filp); - if (err) - return err; - handle = ext4_journal_start_sb(sb, EXT4_HT_MISC, 1); - if (IS_ERR(handle)) { - err = PTR_ERR(handle); - goto pwsalt_err_exit; - } - err = ext4_journal_get_write_access(handle, sb, - sbi->s_sbh, - EXT4_JTR_NONE); - if (err) - goto pwsalt_err_journal; - lock_buffer(sbi->s_sbh); - generate_random_uuid(sbi->s_es->s_encrypt_pw_salt); - ext4_superblock_csum_set(sb); - unlock_buffer(sbi->s_sbh); - err = ext4_handle_dirty_metadata(handle, NULL, - sbi->s_sbh); - pwsalt_err_journal: - err2 = ext4_journal_stop(handle); - if (err2 && !err) - err = err2; - pwsalt_err_exit: - mnt_drop_write_file(filp); - if (err) - return err; - } - if (copy_to_user((void __user *) arg, - sbi->s_es->s_encrypt_pw_salt, 16)) - return -EFAULT; - return 0; -#else - return -EOPNOTSUPP; -#endif - } case FS_IOC_GET_ENCRYPTION_POLICY: if (!ext4_has_feature_encrypt(sb)) return -EOPNOTSUPP; @@ -1652,3 +1593,19 @@ long ext4_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) return ext4_ioctl(file, cmd, (unsigned long) compat_ptr(arg)); } #endif + +static void set_overhead(struct ext4_super_block *es, const void *arg) +{ + es->s_overhead_clusters = cpu_to_le32(*((unsigned long *) arg)); +} + +int ext4_update_overhead(struct super_block *sb) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + + if (sb_rdonly(sb) || sbi->s_overhead == 0 || + sbi->s_overhead == le32_to_cpu(sbi->s_es->s_overhead_clusters)) + return 0; + + return ext4_update_superblocks_fn(sb, set_overhead, &sbi->s_overhead); +} diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 252c168454c7..9f12f29bc346 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -695,13 +695,10 @@ static int __mb_check_buddy(struct ext4_buddy *e4b, char *file, for (i = 0; i < max; i++) { if (mb_test_bit(i, buddy)) { - /* only single bit in buddy2 may be 1 */ + /* only single bit in buddy2 may be 0 */ if (!mb_test_bit(i << 1, buddy2)) { MB_CHECK_ASSERT( mb_test_bit((i<<1)+1, buddy2)); - } else if (!mb_test_bit((i << 1) + 1, buddy2)) { - MB_CHECK_ASSERT( - mb_test_bit(i << 1, buddy2)); } continue; } @@ -2919,7 +2916,7 @@ const struct seq_operations ext4_mb_seq_groups_ops = { int ext4_seq_mb_stats_show(struct seq_file *seq, void *offset) { - struct super_block *sb = (struct super_block *)seq->private; + struct super_block *sb = seq->private; struct ext4_sb_info *sbi = EXT4_SB(sb); seq_puts(seq, "mballoc:\n"); @@ -3498,7 +3495,7 @@ int ext4_mb_init(struct super_block *sb) spin_lock_init(&lg->lg_prealloc_lock); } - if (blk_queue_nonrot(bdev_get_queue(sb->s_bdev))) + if (bdev_nonrot(sb->s_bdev)) sbi->s_mb_max_linear_groups = 0; else sbi->s_mb_max_linear_groups = MB_DEFAULT_LINEAR_LIMIT; @@ -3629,7 +3626,7 @@ static inline int ext4_issue_discard(struct super_block *sb, return __blkdev_issue_discard(sb->s_bdev, (sector_t)discard_block << (sb->s_blocksize_bits - 9), (sector_t)count << (sb->s_blocksize_bits - 9), - GFP_NOFS, 0, biop); + GFP_NOFS, biop); } else return sb_issue_discard(sb, discard_block, count, GFP_NOFS, 0); } @@ -6398,6 +6395,7 @@ __releases(ext4_group_lock_ptr(sb, e4b->bd_group)) * @start: first group block to examine * @max: last group block to examine * @minblocks: minimum extent block count + * @set_trimmed: set the trimmed flag if at least one block is trimmed * * ext4_trim_all_free walks through group's block bitmap searching for free * extents. When the free extent is found, mark it as used in group buddy @@ -6407,7 +6405,7 @@ __releases(ext4_group_lock_ptr(sb, e4b->bd_group)) static ext4_grpblk_t ext4_trim_all_free(struct super_block *sb, ext4_group_t group, ext4_grpblk_t start, ext4_grpblk_t max, - ext4_grpblk_t minblocks) + ext4_grpblk_t minblocks, bool set_trimmed) { struct ext4_buddy e4b; int ret; @@ -6426,7 +6424,7 @@ ext4_trim_all_free(struct super_block *sb, ext4_group_t group, if (!EXT4_MB_GRP_WAS_TRIMMED(e4b.bd_info) || minblocks < EXT4_SB(sb)->s_last_trim_minblks) { ret = ext4_try_to_trim_range(sb, &e4b, start, max, minblocks); - if (ret >= 0) + if (ret >= 0 && set_trimmed) EXT4_MB_GRP_SET_TRIMMED(e4b.bd_info); } else { ret = 0; @@ -6455,7 +6453,7 @@ ext4_trim_all_free(struct super_block *sb, ext4_group_t group, */ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range) { - struct request_queue *q = bdev_get_queue(sb->s_bdev); + unsigned int discard_granularity = bdev_discard_granularity(sb->s_bdev); struct ext4_group_info *grp; ext4_group_t group, first_group, last_group; ext4_grpblk_t cnt = 0, first_cluster, last_cluster; @@ -6463,6 +6461,7 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range) ext4_fsblk_t first_data_blk = le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block); ext4_fsblk_t max_blks = ext4_blocks_count(EXT4_SB(sb)->s_es); + bool whole_group, eof = false; int ret = 0; start = range->start >> sb->s_blocksize_bits; @@ -6475,14 +6474,16 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range) range->len < sb->s_blocksize) return -EINVAL; /* No point to try to trim less than discard granularity */ - if (range->minlen < q->limits.discard_granularity) { + if (range->minlen < discard_granularity) { minlen = EXT4_NUM_B2C(EXT4_SB(sb), - q->limits.discard_granularity >> sb->s_blocksize_bits); + discard_granularity >> sb->s_blocksize_bits); if (minlen > EXT4_CLUSTERS_PER_GROUP(sb)) goto out; } - if (end >= max_blks) + if (end >= max_blks - 1) { end = max_blks - 1; + eof = true; + } if (end <= first_data_blk) goto out; if (start < first_data_blk) @@ -6496,6 +6497,7 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range) /* end now represents the last cluster to discard in this group */ end = EXT4_CLUSTERS_PER_GROUP(sb) - 1; + whole_group = true; for (group = first_group; group <= last_group; group++) { grp = ext4_get_group_info(sb, group); @@ -6512,12 +6514,13 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range) * change it for the last group, note that last_cluster is * already computed earlier by ext4_get_group_no_and_offset() */ - if (group == last_group) + if (group == last_group) { end = last_cluster; - + whole_group = eof ? true : end == EXT4_CLUSTERS_PER_GROUP(sb) - 1; + } if (grp->bb_free >= minlen) { cnt = ext4_trim_all_free(sb, group, first_cluster, - end, minlen); + end, minlen, whole_group); if (cnt < 0) { ret = cnt; break; diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c index cebea4270817..79d05e464c43 100644 --- a/fs/ext4/mmp.c +++ b/fs/ext4/mmp.c @@ -127,7 +127,7 @@ void __dump_mmp_msg(struct super_block *sb, struct mmp_struct *mmp, */ static int kmmpd(void *data) { - struct super_block *sb = (struct super_block *) data; + struct super_block *sb = data; struct ext4_super_block *es = EXT4_SB(sb)->s_es; struct buffer_head *bh = EXT4_SB(sb)->s_mmp_bh; struct mmp_struct *mmp; diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index 95aa212f0863..701f1d6a217f 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -8,6 +8,7 @@ #include <linux/fs.h> #include <linux/quotaops.h> #include <linux/slab.h> +#include <linux/sched/mm.h> #include "ext4_jbd2.h" #include "ext4.h" #include "ext4_extents.h" @@ -127,7 +128,7 @@ mext_page_double_lock(struct inode *inode1, struct inode *inode2, pgoff_t index1, pgoff_t index2, struct page *page[2]) { struct address_space *mapping[2]; - unsigned fl = AOP_FLAG_NOFS; + unsigned int flags; BUG_ON(!inode1 || !inode2); if (inode1 < inode2) { @@ -139,11 +140,15 @@ mext_page_double_lock(struct inode *inode1, struct inode *inode2, mapping[1] = inode1->i_mapping; } - page[0] = grab_cache_page_write_begin(mapping[0], index1, fl); - if (!page[0]) + flags = memalloc_nofs_save(); + page[0] = grab_cache_page_write_begin(mapping[0], index1); + if (!page[0]) { + memalloc_nofs_restore(flags); return -ENOMEM; + } - page[1] = grab_cache_page_write_begin(mapping[1], index2, fl); + page[1] = grab_cache_page_write_begin(mapping[1], index2); + memalloc_nofs_restore(flags); if (!page[1]) { unlock_page(page[0]); put_page(page[0]); @@ -664,8 +669,8 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 orig_blk, * Up semaphore to avoid following problems: * a. transaction deadlock among ext4_journal_start, * ->write_begin via pagefault, and jbd2_journal_commit - * b. racing with ->readpage, ->write_begin, and ext4_get_block - * in move_extent_per_page + * b. racing with ->read_folio, ->write_begin, and + * ext4_get_block in move_extent_per_page */ ext4_double_up_write_data_sem(orig_inode, donor_inode); /* Swap original branches with new branches */ diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index e37da8d5cd0c..47d0ca4c795b 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -277,9 +277,9 @@ static struct dx_frame *dx_probe(struct ext4_filename *fname, struct dx_hash_info *hinfo, struct dx_frame *frame); static void dx_release(struct dx_frame *frames); -static int dx_make_map(struct inode *dir, struct ext4_dir_entry_2 *de, - unsigned blocksize, struct dx_hash_info *hinfo, - struct dx_map_entry map[]); +static int dx_make_map(struct inode *dir, struct buffer_head *bh, + struct dx_hash_info *hinfo, + struct dx_map_entry *map_tail); static void dx_sort_map(struct dx_map_entry *map, unsigned count); static struct ext4_dir_entry_2 *dx_move_dirents(struct inode *dir, char *from, char *to, struct dx_map_entry *offsets, @@ -777,12 +777,14 @@ static struct dx_frame * dx_probe(struct ext4_filename *fname, struct inode *dir, struct dx_hash_info *hinfo, struct dx_frame *frame_in) { - unsigned count, indirect; + unsigned count, indirect, level, i; struct dx_entry *at, *entries, *p, *q, *m; struct dx_root *root; struct dx_frame *frame = frame_in; struct dx_frame *ret_err = ERR_PTR(ERR_BAD_DX_DIR); u32 hash; + ext4_lblk_t block; + ext4_lblk_t blocks[EXT4_HTREE_LEVEL]; memset(frame_in, 0, EXT4_HTREE_LEVEL * sizeof(frame_in[0])); frame->bh = ext4_read_dirblock(dir, 0, INDEX); @@ -854,6 +856,8 @@ dx_probe(struct ext4_filename *fname, struct inode *dir, } dxtrace(printk("Look up %x", hash)); + level = 0; + blocks[0] = 0; while (1) { count = dx_get_count(entries); if (!count || count > dx_get_limit(entries)) { @@ -882,15 +886,27 @@ dx_probe(struct ext4_filename *fname, struct inode *dir, dx_get_block(at))); frame->entries = entries; frame->at = at; - if (!indirect--) + + block = dx_get_block(at); + for (i = 0; i <= level; i++) { + if (blocks[i] == block) { + ext4_warning_inode(dir, + "dx entry: tree cycle block %u points back to block %u", + blocks[level], block); + goto fail; + } + } + if (++level > indirect) return frame; + blocks[level] = block; frame++; - frame->bh = ext4_read_dirblock(dir, dx_get_block(at), INDEX); + frame->bh = ext4_read_dirblock(dir, block, INDEX); if (IS_ERR(frame->bh)) { ret_err = (struct dx_frame *) frame->bh; frame->bh = NULL; goto fail; } + entries = ((struct dx_node *) frame->bh->b_data)->entries; if (dx_get_limit(entries) != dx_node_limit(dir)) { @@ -1249,15 +1265,23 @@ static inline int search_dirblock(struct buffer_head *bh, * Create map of hash values, offsets, and sizes, stored at end of block. * Returns number of entries mapped. */ -static int dx_make_map(struct inode *dir, struct ext4_dir_entry_2 *de, - unsigned blocksize, struct dx_hash_info *hinfo, +static int dx_make_map(struct inode *dir, struct buffer_head *bh, + struct dx_hash_info *hinfo, struct dx_map_entry *map_tail) { int count = 0; - char *base = (char *) de; + struct ext4_dir_entry_2 *de = (struct ext4_dir_entry_2 *)bh->b_data; + unsigned int buflen = bh->b_size; + char *base = bh->b_data; struct dx_hash_info h = *hinfo; - while ((char *) de < base + blocksize) { + if (ext4_has_metadata_csum(dir->i_sb)) + buflen -= sizeof(struct ext4_dir_entry_tail); + + while ((char *) de < base + buflen) { + if (ext4_check_dir_entry(dir, NULL, de, bh, base, buflen, + ((char *)de) - base)) + return -EFSCORRUPTED; if (de->name_len && de->inode) { if (ext4_hash_in_dirent(dir)) h.hash = EXT4_DIRENT_HASH(de); @@ -1270,8 +1294,7 @@ static int dx_make_map(struct inode *dir, struct ext4_dir_entry_2 *de, count++; cond_resched(); } - /* XXX: do we need to check rec_len == 0 case? -Chris */ - de = ext4_next_entry(de, blocksize); + de = ext4_next_entry(de, dir->i_sb->s_blocksize); } return count; } @@ -1466,10 +1489,10 @@ int ext4_search_dir(struct buffer_head *bh, char *search_buf, int buf_size, de = (struct ext4_dir_entry_2 *)search_buf; dlimit = search_buf + buf_size; - while ((char *) de < dlimit) { + while ((char *) de < dlimit - EXT4_BASE_DIR_LEN) { /* this code is executed quadratically often */ /* do minimal checking `by hand' */ - if ((char *) de + de->name_len <= dlimit && + if (de->name + de->name_len <= dlimit && ext4_match(dir, fname, de)) { /* found a match - just to be sure, do * a full check */ @@ -1943,8 +1966,11 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir, /* create map in the end of data2 block */ map = (struct dx_map_entry *) (data2 + blocksize); - count = dx_make_map(dir, (struct ext4_dir_entry_2 *) data1, - blocksize, hinfo, map); + count = dx_make_map(dir, *bh, hinfo, map); + if (count < 0) { + err = count; + goto journal_error; + } map -= count; dx_sort_map(map, count); /* Ensure that neither split block is over half full */ @@ -2031,7 +2057,7 @@ int ext4_find_dest_de(struct inode *dir, struct inode *inode, unsigned int offset = 0; char *top; - de = (struct ext4_dir_entry_2 *)buf; + de = buf; top = buf + buf_size - reclen; while ((char *) de <= top) { if (ext4_check_dir_entry(dir, NULL, de, bh, @@ -2587,7 +2613,7 @@ int ext4_generic_delete_entry(struct inode *dir, i = 0; pde = NULL; - de = (struct ext4_dir_entry_2 *)entry_buf; + de = entry_buf; while (i < buf_size - csum_size) { if (ext4_check_dir_entry(dir, NULL, de, bh, entry_buf, buf_size, i)) @@ -3249,6 +3275,32 @@ out_trace: return retval; } +static int ext4_init_symlink_block(handle_t *handle, struct inode *inode, + struct fscrypt_str *disk_link) +{ + struct buffer_head *bh; + char *kaddr; + int err = 0; + + bh = ext4_bread(handle, inode, 0, EXT4_GET_BLOCKS_CREATE); + if (IS_ERR(bh)) + return PTR_ERR(bh); + + BUFFER_TRACE(bh, "get_write_access"); + err = ext4_journal_get_write_access(handle, inode->i_sb, bh, EXT4_JTR_NONE); + if (err) + goto out; + + kaddr = (char *)bh->b_data; + memcpy(kaddr, disk_link->name, disk_link->len); + inode->i_size = disk_link->len - 1; + EXT4_I(inode)->i_disksize = inode->i_size; + err = ext4_handle_dirty_metadata(handle, inode, bh); +out: + brelse(bh); + return err; +} + static int ext4_symlink(struct user_namespace *mnt_userns, struct inode *dir, struct dentry *dentry, const char *symname) { @@ -3257,6 +3309,7 @@ static int ext4_symlink(struct user_namespace *mnt_userns, struct inode *dir, int err, len = strlen(symname); int credits; struct fscrypt_str disk_link; + int retries = 0; if (unlikely(ext4_forced_shutdown(EXT4_SB(dir->i_sb)))) return -EIO; @@ -3270,26 +3323,15 @@ static int ext4_symlink(struct user_namespace *mnt_userns, struct inode *dir, if (err) return err; - if ((disk_link.len > EXT4_N_BLOCKS * 4)) { - /* - * For non-fast symlinks, we just allocate inode and put it on - * orphan list in the first transaction => we need bitmap, - * group descriptor, sb, inode block, quota blocks, and - * possibly selinux xattr blocks. - */ - credits = 4 + EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb) + - EXT4_XATTR_TRANS_BLOCKS; - } else { - /* - * Fast symlink. We have to add entry to directory - * (EXT4_DATA_TRANS_BLOCKS + EXT4_INDEX_EXTRA_TRANS_BLOCKS), - * allocate new inode (bitmap, group descriptor, inode block, - * quota blocks, sb is already counted in previous macros). - */ - credits = EXT4_DATA_TRANS_BLOCKS(dir->i_sb) + - EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3; - } - + /* + * EXT4_INDEX_EXTRA_TRANS_BLOCKS for addition of entry into the + * directory. +3 for inode, inode bitmap, group descriptor allocation. + * EXT4_DATA_TRANS_BLOCKS for the data block allocation and + * modification. + */ + credits = EXT4_DATA_TRANS_BLOCKS(dir->i_sb) + + EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3; +retry: inode = ext4_new_inode_start_handle(mnt_userns, dir, S_IFLNK|S_IRWXUGO, &dentry->d_name, 0, NULL, EXT4_HT_DIR, credits); @@ -3297,7 +3339,8 @@ static int ext4_symlink(struct user_namespace *mnt_userns, struct inode *dir, if (IS_ERR(inode)) { if (handle) ext4_journal_stop(handle); - return PTR_ERR(inode); + err = PTR_ERR(inode); + goto out_retry; } if (IS_ENCRYPTED(inode)) { @@ -3305,75 +3348,44 @@ static int ext4_symlink(struct user_namespace *mnt_userns, struct inode *dir, if (err) goto err_drop_inode; inode->i_op = &ext4_encrypted_symlink_inode_operations; + } else { + if ((disk_link.len > EXT4_N_BLOCKS * 4)) { + inode->i_op = &ext4_symlink_inode_operations; + } else { + inode->i_op = &ext4_fast_symlink_inode_operations; + inode->i_link = (char *)&EXT4_I(inode)->i_data; + } } if ((disk_link.len > EXT4_N_BLOCKS * 4)) { - if (!IS_ENCRYPTED(inode)) - inode->i_op = &ext4_symlink_inode_operations; - inode_nohighmem(inode); - ext4_set_aops(inode); - /* - * We cannot call page_symlink() with transaction started - * because it calls into ext4_write_begin() which can wait - * for transaction commit if we are running out of space - * and thus we deadlock. So we have to stop transaction now - * and restart it when symlink contents is written. - * - * To keep fs consistent in case of crash, we have to put inode - * to orphan list in the mean time. - */ - drop_nlink(inode); - err = ext4_orphan_add(handle, inode); - if (handle) - ext4_journal_stop(handle); - handle = NULL; - if (err) - goto err_drop_inode; - err = __page_symlink(inode, disk_link.name, disk_link.len, 1); - if (err) - goto err_drop_inode; - /* - * Now inode is being linked into dir (EXT4_DATA_TRANS_BLOCKS - * + EXT4_INDEX_EXTRA_TRANS_BLOCKS), inode is also modified - */ - handle = ext4_journal_start(dir, EXT4_HT_DIR, - EXT4_DATA_TRANS_BLOCKS(dir->i_sb) + - EXT4_INDEX_EXTRA_TRANS_BLOCKS + 1); - if (IS_ERR(handle)) { - err = PTR_ERR(handle); - handle = NULL; - goto err_drop_inode; - } - set_nlink(inode, 1); - err = ext4_orphan_del(handle, inode); + /* alloc symlink block and fill it */ + err = ext4_init_symlink_block(handle, inode, &disk_link); if (err) goto err_drop_inode; } else { /* clear the extent format for fast symlink */ ext4_clear_inode_flag(inode, EXT4_INODE_EXTENTS); - if (!IS_ENCRYPTED(inode)) { - inode->i_op = &ext4_fast_symlink_inode_operations; - inode->i_link = (char *)&EXT4_I(inode)->i_data; - } memcpy((char *)&EXT4_I(inode)->i_data, disk_link.name, disk_link.len); inode->i_size = disk_link.len - 1; + EXT4_I(inode)->i_disksize = inode->i_size; } - EXT4_I(inode)->i_disksize = inode->i_size; err = ext4_add_nondir(handle, dentry, &inode); if (handle) ext4_journal_stop(handle); - if (inode) - iput(inode); - goto out_free_encrypted_link; + iput(inode); + goto out_retry; err_drop_inode: - if (handle) - ext4_journal_stop(handle); clear_nlink(inode); + ext4_orphan_add(handle, inode); unlock_new_inode(inode); + if (handle) + ext4_journal_stop(handle); iput(inode); -out_free_encrypted_link: +out_retry: + if (err == -ENOSPC && ext4_should_retry_alloc(dir->i_sb, &retries)) + goto retry; if (disk_link.name != (unsigned char *)symname) kfree(disk_link.name); return err; @@ -3455,6 +3467,9 @@ static struct buffer_head *ext4_get_first_dir_block(handle_t *handle, struct buffer_head *bh; if (!ext4_has_inline_data(inode)) { + struct ext4_dir_entry_2 *de; + unsigned int offset; + /* The first directory block must not be a hole, so * treat it as DIRENT_HTREE */ @@ -3463,9 +3478,30 @@ static struct buffer_head *ext4_get_first_dir_block(handle_t *handle, *retval = PTR_ERR(bh); return NULL; } - *parent_de = ext4_next_entry( - (struct ext4_dir_entry_2 *)bh->b_data, - inode->i_sb->s_blocksize); + + de = (struct ext4_dir_entry_2 *) bh->b_data; + if (ext4_check_dir_entry(inode, NULL, de, bh, bh->b_data, + bh->b_size, 0) || + le32_to_cpu(de->inode) != inode->i_ino || + strcmp(".", de->name)) { + EXT4_ERROR_INODE(inode, "directory missing '.'"); + brelse(bh); + *retval = -EFSCORRUPTED; + return NULL; + } + offset = ext4_rec_len_from_disk(de->rec_len, + inode->i_sb->s_blocksize); + de = ext4_next_entry(de, inode->i_sb->s_blocksize); + if (ext4_check_dir_entry(inode, NULL, de, bh, bh->b_data, + bh->b_size, offset) || + le32_to_cpu(de->inode) == 0 || strcmp("..", de->name)) { + EXT4_ERROR_INODE(inode, "directory missing '..'"); + brelse(bh); + *retval = -EFSCORRUPTED; + return NULL; + } + *parent_de = de; + return bh; } diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index 495ce59fb4ad..14695e2b5042 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -134,8 +134,10 @@ static void ext4_finish_bio(struct bio *bio) continue; } clear_buffer_async_write(bh); - if (bio->bi_status) + if (bio->bi_status) { + set_buffer_write_io_error(bh); buffer_io_error(bh); + } } while ((bh = bh->b_this_page) != head); spin_unlock_irqrestore(&head->b_uptodate_lock, flags); if (!under_io) { diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c index af491e170c4a..e02a5f14e021 100644 --- a/fs/ext4/readpage.c +++ b/fs/ext4/readpage.c @@ -163,7 +163,7 @@ static bool bio_post_read_required(struct bio *bio) * * The mpage code never puts partial pages into a BIO (except for end-of-file). * If a page does not map to a contiguous run of blocks then it simply falls - * back to block_read_full_page(). + * back to block_read_full_folio(). * * Why is this? If a page's completion depends on a number of different BIOs * which can complete in any order (or at the same time) then determining the @@ -394,7 +394,7 @@ int ext4_mpage_readpages(struct inode *inode, bio = NULL; } if (!PageUptodate(page)) - block_read_full_page(page, ext4_get_block); + block_read_full_folio(page_folio(page), ext4_get_block); else unlock_page(page); next_page: diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 81749eaddf4c..450c918d68fc 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1199,20 +1199,28 @@ static void ext4_put_super(struct super_block *sb) int aborted = 0; int i, err; - ext4_unregister_li_request(sb); - ext4_quota_off_umount(sb); - - flush_work(&sbi->s_error_work); - destroy_workqueue(sbi->rsv_conversion_wq); - ext4_release_orphan_info(sb); - /* * Unregister sysfs before destroying jbd2 journal. * Since we could still access attr_journal_task attribute via sysfs * path which could have sbi->s_journal->j_task as NULL + * Unregister sysfs before flush sbi->s_error_work. + * Since user may read /proc/fs/ext4/xx/mb_groups during umount, If + * read metadata verify failed then will queue error work. + * flush_stashed_error_work will call start_this_handle may trigger + * BUG_ON. */ ext4_unregister_sysfs(sb); + if (___ratelimit(&ext4_mount_msg_ratelimit, "EXT4-fs unmount")) + ext4_msg(sb, KERN_INFO, "unmounting filesystem."); + + ext4_unregister_li_request(sb); + ext4_quota_off_umount(sb); + + flush_work(&sbi->s_error_work); + destroy_workqueue(sbi->rsv_conversion_wq); + ext4_release_orphan_info(sb); + if (sbi->s_journal) { aborted = is_journal_aborted(sbi->s_journal); err = jbd2_journal_destroy(sbi->s_journal); @@ -1392,7 +1400,7 @@ static void ext4_destroy_inode(struct inode *inode) static void init_once(void *foo) { - struct ext4_inode_info *ei = (struct ext4_inode_info *) foo; + struct ext4_inode_info *ei = foo; INIT_LIST_HEAD(&ei->i_orphan); init_rwsem(&ei->xattr_sem); @@ -1487,128 +1495,6 @@ static int ext4_nfs_commit_metadata(struct inode *inode) return ext4_write_inode(inode, &wbc); } -#ifdef CONFIG_FS_ENCRYPTION -static int ext4_get_context(struct inode *inode, void *ctx, size_t len) -{ - return ext4_xattr_get(inode, EXT4_XATTR_INDEX_ENCRYPTION, - EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, ctx, len); -} - -static int ext4_set_context(struct inode *inode, const void *ctx, size_t len, - void *fs_data) -{ - handle_t *handle = fs_data; - int res, res2, credits, retries = 0; - - /* - * Encrypting the root directory is not allowed because e2fsck expects - * lost+found to exist and be unencrypted, and encrypting the root - * directory would imply encrypting the lost+found directory as well as - * the filename "lost+found" itself. - */ - if (inode->i_ino == EXT4_ROOT_INO) - return -EPERM; - - if (WARN_ON_ONCE(IS_DAX(inode) && i_size_read(inode))) - return -EINVAL; - - if (ext4_test_inode_flag(inode, EXT4_INODE_DAX)) - return -EOPNOTSUPP; - - res = ext4_convert_inline_data(inode); - if (res) - return res; - - /* - * If a journal handle was specified, then the encryption context is - * being set on a new inode via inheritance and is part of a larger - * transaction to create the inode. Otherwise the encryption context is - * being set on an existing inode in its own transaction. Only in the - * latter case should the "retry on ENOSPC" logic be used. - */ - - if (handle) { - res = ext4_xattr_set_handle(handle, inode, - EXT4_XATTR_INDEX_ENCRYPTION, - EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, - ctx, len, 0); - if (!res) { - ext4_set_inode_flag(inode, EXT4_INODE_ENCRYPT); - ext4_clear_inode_state(inode, - EXT4_STATE_MAY_INLINE_DATA); - /* - * Update inode->i_flags - S_ENCRYPTED will be enabled, - * S_DAX may be disabled - */ - ext4_set_inode_flags(inode, false); - } - return res; - } - - res = dquot_initialize(inode); - if (res) - return res; -retry: - res = ext4_xattr_set_credits(inode, len, false /* is_create */, - &credits); - if (res) - return res; - - handle = ext4_journal_start(inode, EXT4_HT_MISC, credits); - if (IS_ERR(handle)) - return PTR_ERR(handle); - - res = ext4_xattr_set_handle(handle, inode, EXT4_XATTR_INDEX_ENCRYPTION, - EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, - ctx, len, 0); - if (!res) { - ext4_set_inode_flag(inode, EXT4_INODE_ENCRYPT); - /* - * Update inode->i_flags - S_ENCRYPTED will be enabled, - * S_DAX may be disabled - */ - ext4_set_inode_flags(inode, false); - res = ext4_mark_inode_dirty(handle, inode); - if (res) - EXT4_ERROR_INODE(inode, "Failed to mark inode dirty"); - } - res2 = ext4_journal_stop(handle); - - if (res == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) - goto retry; - if (!res) - res = res2; - return res; -} - -static const union fscrypt_policy *ext4_get_dummy_policy(struct super_block *sb) -{ - return EXT4_SB(sb)->s_dummy_enc_policy.policy; -} - -static bool ext4_has_stable_inodes(struct super_block *sb) -{ - return ext4_has_feature_stable_inodes(sb); -} - -static void ext4_get_ino_and_lblk_bits(struct super_block *sb, - int *ino_bits_ret, int *lblk_bits_ret) -{ - *ino_bits_ret = 8 * sizeof(EXT4_SB(sb)->s_es->s_inodes_count); - *lblk_bits_ret = 8 * sizeof(ext4_lblk_t); -} - -static const struct fscrypt_operations ext4_cryptops = { - .key_prefix = "ext4:", - .get_context = ext4_get_context, - .set_context = ext4_set_context, - .get_dummy_policy = ext4_get_dummy_policy, - .empty_dir = ext4_empty_dir, - .has_stable_inodes = ext4_has_stable_inodes, - .get_ino_and_lblk_bits = ext4_get_ino_and_lblk_bits, -}; -#endif - #ifdef CONFIG_QUOTA static const char * const quotatypes[] = INITQFNAMES; #define QTYPE2NAME(t) (quotatypes[t]) @@ -1862,7 +1748,6 @@ static const struct fs_parameter_spec ext4_param_specs[] = { }; #define DEFAULT_JOURNAL_IOPRIO (IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, 3)) -#define DEFAULT_MB_OPTIMIZE_SCAN (-1) static const char deprecated_msg[] = "Mount option \"%s\" will be removed by %s\n" @@ -1908,6 +1793,7 @@ static const struct mount_opts { MOPT_EXT4_ONLY | MOPT_CLEAR}, {Opt_warn_on_error, EXT4_MOUNT_WARN_ON_ERROR, MOPT_SET}, {Opt_nowarn_on_error, EXT4_MOUNT_WARN_ON_ERROR, MOPT_CLEAR}, + {Opt_commit, 0, MOPT_NO_EXT2}, {Opt_nojournal_checksum, EXT4_MOUNT_JOURNAL_CHECKSUM, MOPT_EXT4_ONLY | MOPT_CLEAR}, {Opt_journal_checksum, EXT4_MOUNT_JOURNAL_CHECKSUM, @@ -2422,11 +2308,12 @@ static int ext4_parse_param(struct fs_context *fc, struct fs_parameter *param) ctx->spec |= EXT4_SPEC_DUMMY_ENCRYPTION; ctx->test_dummy_enc_arg = kmemdup_nul(param->string, param->size, GFP_KERNEL); + return 0; #else ext4_msg(NULL, KERN_WARNING, - "Test dummy encryption mount option ignored"); + "test_dummy_encryption option not supported"); + return -EINVAL; #endif - return 0; case Opt_dax: case Opt_dax_type: #ifdef CONFIG_FS_DAX @@ -2620,8 +2507,10 @@ parse_failed: ret = ext4_apply_options(fc, sb); out_free: - kfree(s_ctx); - kfree(fc); + if (fc) { + ext4_fc_free(fc); + kfree(fc); + } kfree(s_mount_opts); return ret; } @@ -2781,12 +2670,44 @@ err_jquota_specified: #endif } +static int ext4_check_test_dummy_encryption(const struct fs_context *fc, + struct super_block *sb) +{ +#ifdef CONFIG_FS_ENCRYPTION + const struct ext4_fs_context *ctx = fc->fs_private; + const struct ext4_sb_info *sbi = EXT4_SB(sb); + + if (!(ctx->spec & EXT4_SPEC_DUMMY_ENCRYPTION)) + return 0; + + if (!ext4_has_feature_encrypt(sb)) { + ext4_msg(NULL, KERN_WARNING, + "test_dummy_encryption requires encrypt feature"); + return -EINVAL; + } + /* + * This mount option is just for testing, and it's not worthwhile to + * implement the extra complexity (e.g. RCU protection) that would be + * needed to allow it to be set or changed during remount. We do allow + * it to be specified during remount, but only if there is no change. + */ + if (fc->purpose == FS_CONTEXT_FOR_RECONFIGURE && + !sbi->s_dummy_enc_policy.policy) { + ext4_msg(NULL, KERN_WARNING, + "Can't set test_dummy_encryption on remount"); + return -EINVAL; + } +#endif /* CONFIG_FS_ENCRYPTION */ + return 0; +} + static int ext4_check_opt_consistency(struct fs_context *fc, struct super_block *sb) { struct ext4_fs_context *ctx = fc->fs_private; struct ext4_sb_info *sbi = fc->s_fs_info; int is_remount = fc->purpose == FS_CONTEXT_FOR_RECONFIGURE; + int err; if ((ctx->opt_flags & MOPT_NO_EXT2) && IS_EXT2_SB(sb)) { ext4_msg(NULL, KERN_ERR, @@ -2816,20 +2737,9 @@ static int ext4_check_opt_consistency(struct fs_context *fc, "for blocksize < PAGE_SIZE"); } -#ifdef CONFIG_FS_ENCRYPTION - /* - * This mount option is just for testing, and it's not worthwhile to - * implement the extra complexity (e.g. RCU protection) that would be - * needed to allow it to be set or changed during remount. We do allow - * it to be specified during remount, but only if there is no change. - */ - if ((ctx->spec & EXT4_SPEC_DUMMY_ENCRYPTION) && - is_remount && !sbi->s_dummy_enc_policy.policy) { - ext4_msg(NULL, KERN_WARNING, - "Can't set test_dummy_encryption on remount"); - return -1; - } -#endif + err = ext4_check_test_dummy_encryption(fc, sb); + if (err) + return err; if ((ctx->spec & EXT4_SPEC_DATAJ) && is_remount) { if (!sbi->s_journal) { @@ -3832,7 +3742,7 @@ static struct task_struct *ext4_lazyinit_task; */ static int ext4_lazyinit_thread(void *arg) { - struct ext4_lazy_init *eli = (struct ext4_lazy_init *)arg; + struct ext4_lazy_init *eli = arg; struct list_head *pos, *n; struct ext4_li_request *elr; unsigned long next_wakeup, cur; @@ -4172,9 +4082,11 @@ static int count_overhead(struct super_block *sb, ext4_group_t grp, ext4_fsblk_t first_block, last_block, b; ext4_group_t i, ngroups = ext4_get_groups_count(sb); int s, j, count = 0; + int has_super = ext4_bg_has_super(sb, grp); if (!ext4_has_feature_bigalloc(sb)) - return (ext4_bg_has_super(sb, grp) + ext4_bg_num_gdb(sb, grp) + + return (has_super + ext4_bg_num_gdb(sb, grp) + + (has_super ? le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks) : 0) + sbi->s_itb_per_group + 2); first_block = le32_to_cpu(sbi->s_es->s_first_data_block) + @@ -4402,7 +4314,8 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) int silent = fc->sb_flags & SB_SILENT; /* Set defaults for the variables that will be set during parsing */ - ctx->journal_ioprio = DEFAULT_JOURNAL_IOPRIO; + if (!(ctx->spec & EXT4_SPEC_JOURNAL_IOPRIO)) + ctx->journal_ioprio = DEFAULT_JOURNAL_IOPRIO; sbi->s_inode_readahead_blks = EXT4_DEF_INODE_READAHEAD_BLKS; sbi->s_sectors_written_start = @@ -4879,7 +4792,7 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) sbi->s_inodes_per_block; sbi->s_desc_per_block = blocksize / EXT4_DESC_SIZE(sb); sbi->s_sbh = bh; - sbi->s_mount_state = le16_to_cpu(es->s_state); + sbi->s_mount_state = le16_to_cpu(es->s_state) & ~EXT4_FC_REPLAY; sbi->s_addr_per_block_bits = ilog2(EXT4_ADDR_PER_BLOCK(sb)); sbi->s_desc_per_block_bits = ilog2(EXT4_DESC_PER_BLOCK(sb)); @@ -5272,19 +5185,22 @@ no_journal: goto failed_mount_wq; } - if (DUMMY_ENCRYPTION_ENABLED(sbi) && !sb_rdonly(sb) && - !ext4_has_feature_encrypt(sb)) { - ext4_set_feature_encrypt(sb); - ext4_commit_super(sb); - } - /* * Get the # of file system overhead blocks from the * superblock if present. */ - if (es->s_overhead_clusters) - sbi->s_overhead = le32_to_cpu(es->s_overhead_clusters); - else { + sbi->s_overhead = le32_to_cpu(es->s_overhead_clusters); + /* ignore the precalculated value if it is ridiculous */ + if (sbi->s_overhead > ext4_blocks_count(es)) + sbi->s_overhead = 0; + /* + * If the bigalloc feature is not enabled recalculating the + * overhead doesn't take long, so we might as well just redo + * it to make sure we are using the correct value. + */ + if (!ext4_has_feature_bigalloc(sb)) + sbi->s_overhead = 0; + if (sbi->s_overhead == 0) { err = ext4_calculate_overhead(sb); if (err) goto failed_mount_wq; @@ -5458,13 +5374,9 @@ no_journal: goto failed_mount9; } - if (test_opt(sb, DISCARD)) { - struct request_queue *q = bdev_get_queue(sb->s_bdev); - if (!blk_queue_discard(q)) - ext4_msg(sb, KERN_WARNING, - "mounting with \"discard\" option, but " - "the device does not support discard"); - } + if (test_opt(sb, DISCARD) && !bdev_max_discard_sectors(sb->s_bdev)) + ext4_msg(sb, KERN_WARNING, + "mounting with \"discard\" option, but the device does not support discard"); if (es->s_error_count) mod_timer(&sbi->s_err_report, jiffies + 300*HZ); /* 5 minutes */ @@ -5602,6 +5514,8 @@ static int ext4_fill_super(struct super_block *sb, struct fs_context *fc) ext4_msg(sb, KERN_INFO, "mounted filesystem with%s. " "Quota mode: %s.", descr, ext4_quota_mode(sb)); + /* Update the s_overhead_clusters if necessary */ + ext4_update_overhead(sb); return 0; free_sbi: @@ -6258,7 +6172,6 @@ static int __ext4_remount(struct fs_context *fc, struct super_block *sb) char *to_free[EXT4_MAXQUOTAS]; #endif - ctx->journal_ioprio = DEFAULT_JOURNAL_IOPRIO; /* Store the original options */ old_sb_flags = sb->s_flags; @@ -6284,9 +6197,14 @@ static int __ext4_remount(struct fs_context *fc, struct super_block *sb) } else old_opts.s_qf_names[i] = NULL; #endif - if (sbi->s_journal && sbi->s_journal->j_task->io_context) - ctx->journal_ioprio = - sbi->s_journal->j_task->io_context->ioprio; + if (!(ctx->spec & EXT4_SPEC_JOURNAL_IOPRIO)) { + if (sbi->s_journal && sbi->s_journal->j_task->io_context) + ctx->journal_ioprio = + sbi->s_journal->j_task->io_context->ioprio; + else + ctx->journal_ioprio = DEFAULT_JOURNAL_IOPRIO; + + } ext4_apply_options(fc, sb); @@ -6427,7 +6345,8 @@ static int __ext4_remount(struct fs_context *fc, struct super_block *sb) if (err) goto restore_opts; } - sbi->s_mount_state = le16_to_cpu(es->s_state); + sbi->s_mount_state = (le16_to_cpu(es->s_state) & + ~EXT4_FC_REPLAY); err = ext4_setup_super(sb, es, 0); if (err) diff --git a/fs/ext4/symlink.c b/fs/ext4/symlink.c index 69109746e6e2..d281f5bcc526 100644 --- a/fs/ext4/symlink.c +++ b/fs/ext4/symlink.c @@ -27,7 +27,7 @@ static const char *ext4_encrypted_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *done) { - struct page *cpage = NULL; + struct buffer_head *bh = NULL; const void *caddr; unsigned int max_size; const char *paddr; @@ -39,16 +39,19 @@ static const char *ext4_encrypted_get_link(struct dentry *dentry, caddr = EXT4_I(inode)->i_data; max_size = sizeof(EXT4_I(inode)->i_data); } else { - cpage = read_mapping_page(inode->i_mapping, 0, NULL); - if (IS_ERR(cpage)) - return ERR_CAST(cpage); - caddr = page_address(cpage); + bh = ext4_bread(NULL, inode, 0, 0); + if (IS_ERR(bh)) + return ERR_CAST(bh); + if (!bh) { + EXT4_ERROR_INODE(inode, "bad symlink."); + return ERR_PTR(-EFSCORRUPTED); + } + caddr = bh->b_data; max_size = inode->i_sb->s_blocksize; } paddr = fscrypt_get_symlink(inode, caddr, max_size, done); - if (cpage) - put_page(cpage); + brelse(bh); return paddr; } @@ -62,6 +65,38 @@ static int ext4_encrypted_symlink_getattr(struct user_namespace *mnt_userns, return fscrypt_symlink_getattr(path, stat); } +static void ext4_free_link(void *bh) +{ + brelse(bh); +} + +static const char *ext4_get_link(struct dentry *dentry, struct inode *inode, + struct delayed_call *callback) +{ + struct buffer_head *bh; + + if (!dentry) { + bh = ext4_getblk(NULL, inode, 0, EXT4_GET_BLOCKS_CACHED_NOWAIT); + if (IS_ERR(bh)) + return ERR_CAST(bh); + if (!bh || !ext4_buffer_uptodate(bh)) + return ERR_PTR(-ECHILD); + } else { + bh = ext4_bread(NULL, inode, 0, 0); + if (IS_ERR(bh)) + return ERR_CAST(bh); + if (!bh) { + EXT4_ERROR_INODE(inode, "bad symlink."); + return ERR_PTR(-EFSCORRUPTED); + } + } + + set_delayed_call(callback, ext4_free_link, bh); + nd_terminate_link(bh->b_data, inode->i_size, + inode->i_sb->s_blocksize - 1); + return bh->b_data; +} + const struct inode_operations ext4_encrypted_symlink_inode_operations = { .get_link = ext4_encrypted_get_link, .setattr = ext4_setattr, @@ -70,7 +105,7 @@ const struct inode_operations ext4_encrypted_symlink_inode_operations = { }; const struct inode_operations ext4_symlink_inode_operations = { - .get_link = page_get_link, + .get_link = ext4_get_link, .setattr = ext4_setattr, .getattr = ext4_getattr, .listxattr = ext4_listxattr, diff --git a/fs/ext4/verity.c b/fs/ext4/verity.c index eacbd489e3bf..b051d19b5c8a 100644 --- a/fs/ext4/verity.c +++ b/fs/ext4/verity.c @@ -69,6 +69,9 @@ static int pagecache_read(struct inode *inode, void *buf, size_t count, static int pagecache_write(struct inode *inode, const void *buf, size_t count, loff_t pos) { + struct address_space *mapping = inode->i_mapping; + const struct address_space_operations *aops = mapping->a_ops; + if (pos + count > inode->i_sb->s_maxbytes) return -EFBIG; @@ -79,15 +82,13 @@ static int pagecache_write(struct inode *inode, const void *buf, size_t count, void *fsdata; int res; - res = pagecache_write_begin(NULL, inode->i_mapping, pos, n, 0, - &page, &fsdata); + res = aops->write_begin(NULL, mapping, pos, n, &page, &fsdata); if (res) return res; memcpy_to_page(page, offset_in_page(pos), buf, n); - res = pagecache_write_end(NULL, inode->i_mapping, pos, n, n, - page, fsdata); + res = aops->write_end(NULL, mapping, pos, n, n, page, fsdata); if (res < 0) return res; if (res != n) diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index f5366feea82d..456c1e89386a 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -98,9 +98,9 @@ repeat: } if (unlikely(!PageUptodate(page))) { - if (page->index == sbi->metapage_eio_ofs && - sbi->metapage_eio_cnt++ == MAX_RETRY_META_PAGE_EIO) { - set_ckpt_flags(sbi, CP_ERROR_FLAG); + if (page->index == sbi->metapage_eio_ofs) { + if (sbi->metapage_eio_cnt++ == MAX_RETRY_META_PAGE_EIO) + set_ckpt_flags(sbi, CP_ERROR_FLAG); } else { sbi->metapage_eio_ofs = page->index; sbi->metapage_eio_cnt = 0; @@ -468,7 +468,7 @@ const struct address_space_operations f2fs_meta_aops = { .writepages = f2fs_write_meta_pages, .dirty_folio = f2fs_dirty_meta_folio, .invalidate_folio = f2fs_invalidate_folio, - .releasepage = f2fs_release_page, + .release_folio = f2fs_release_folio, #ifdef CONFIG_MIGRATION .migratepage = f2fs_migrate_page, #endif diff --git a/fs/f2fs/compress.c b/fs/f2fs/compress.c index 12a56f9e1572..24824cd96f36 100644 --- a/fs/f2fs/compress.c +++ b/fs/f2fs/compress.c @@ -1746,7 +1746,7 @@ unsigned int f2fs_cluster_blocks_are_contiguous(struct dnode_of_data *dn) } const struct address_space_operations f2fs_compress_aops = { - .releasepage = f2fs_release_page, + .release_folio = f2fs_release_folio, .invalidate_folio = f2fs_invalidate_folio, }; diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 8e0c2e773c8d..8f38c26bb16c 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -388,11 +388,23 @@ int f2fs_target_device_index(struct f2fs_sb_info *sbi, block_t blkaddr) return 0; } -static void __attach_io_flag(struct f2fs_io_info *fio, unsigned int io_flag) +static unsigned int f2fs_io_flags(struct f2fs_io_info *fio) { unsigned int temp_mask = (1 << NR_TEMP_TYPE) - 1; - unsigned int fua_flag = io_flag & temp_mask; - unsigned int meta_flag = (io_flag >> NR_TEMP_TYPE) & temp_mask; + unsigned int fua_flag, meta_flag, io_flag; + unsigned int op_flags = 0; + + if (fio->op != REQ_OP_WRITE) + return 0; + if (fio->type == DATA) + io_flag = fio->sbi->data_io_flag; + else if (fio->type == NODE) + io_flag = fio->sbi->node_io_flag; + else + return 0; + + fua_flag = io_flag & temp_mask; + meta_flag = (io_flag >> NR_TEMP_TYPE) & temp_mask; /* * data/node io flag bits per temp: @@ -401,9 +413,10 @@ static void __attach_io_flag(struct f2fs_io_info *fio, unsigned int io_flag) * Cold | Warm | Hot | Cold | Warm | Hot | */ if ((1 << fio->temp) & meta_flag) - fio->op_flags |= REQ_META; + op_flags |= REQ_META; if ((1 << fio->temp) & fua_flag) - fio->op_flags |= REQ_FUA; + op_flags |= REQ_FUA; + return op_flags; } static struct bio *__bio_alloc(struct f2fs_io_info *fio, int npages) @@ -413,14 +426,10 @@ static struct bio *__bio_alloc(struct f2fs_io_info *fio, int npages) sector_t sector; struct bio *bio; - if (fio->type == DATA) - __attach_io_flag(fio, sbi->data_io_flag); - else if (fio->type == NODE) - __attach_io_flag(fio, sbi->node_io_flag); - bdev = f2fs_target_device(sbi, fio->new_blkaddr, §or); - bio = bio_alloc_bioset(bdev, npages, fio->op | fio->op_flags, GFP_NOIO, - &f2fs_bioset); + bio = bio_alloc_bioset(bdev, npages, + fio->op | fio->op_flags | f2fs_io_flags(fio), + GFP_NOIO, &f2fs_bioset); bio->bi_iter.bi_sector = sector; if (is_read_io(fio->op)) { bio->bi_end_io = f2fs_read_end_io; @@ -2363,8 +2372,9 @@ next_page: return ret; } -static int f2fs_read_data_page(struct file *file, struct page *page) +static int f2fs_read_data_folio(struct file *file, struct folio *folio) { + struct page *page = &folio->page; struct inode *inode = page_file_mapping(page)->host; int ret = -EAGAIN; @@ -3305,8 +3315,7 @@ unlock_out: } static int f2fs_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, - struct page **pagep, void **fsdata) + loff_t pos, unsigned len, struct page **pagep, void **fsdata) { struct inode *inode = mapping->host; struct f2fs_sb_info *sbi = F2FS_I_SB(inode); @@ -3316,7 +3325,7 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping, block_t blkaddr = NULL_ADDR; int err = 0; - trace_f2fs_write_begin(inode, pos, len, flags); + trace_f2fs_write_begin(inode, pos, len); if (!f2fs_is_checkpoint_ready(sbi)) { err = -ENOSPC; @@ -3519,28 +3528,30 @@ void f2fs_invalidate_folio(struct folio *folio, size_t offset, size_t length) folio_detach_private(folio); } -int f2fs_release_page(struct page *page, gfp_t wait) +bool f2fs_release_folio(struct folio *folio, gfp_t wait) { - /* If this is dirty page, keep PagePrivate */ - if (PageDirty(page)) - return 0; + struct f2fs_sb_info *sbi; + + /* If this is dirty folio, keep private data */ + if (folio_test_dirty(folio)) + return false; /* This is atomic written page, keep Private */ - if (page_private_atomic(page)) - return 0; + if (page_private_atomic(&folio->page)) + return false; - if (test_opt(F2FS_P_SB(page), COMPRESS_CACHE)) { - struct inode *inode = page->mapping->host; + sbi = F2FS_M_SB(folio->mapping); + if (test_opt(sbi, COMPRESS_CACHE)) { + struct inode *inode = folio->mapping->host; - if (inode->i_ino == F2FS_COMPRESS_INO(F2FS_I_SB(inode))) - clear_page_private_data(page); + if (inode->i_ino == F2FS_COMPRESS_INO(sbi)) + clear_page_private_data(&folio->page); } - clear_page_private_gcing(page); + clear_page_private_gcing(&folio->page); - detach_page_private(page); - set_page_private(page, 0); - return 1; + folio_detach_private(folio); + return true; } static bool f2fs_dirty_data_folio(struct address_space *mapping, @@ -3927,7 +3938,7 @@ static void f2fs_swap_deactivate(struct file *file) #endif const struct address_space_operations f2fs_dblock_aops = { - .readpage = f2fs_read_data_page, + .read_folio = f2fs_read_data_folio, .readahead = f2fs_readahead, .writepage = f2fs_write_data_page, .writepages = f2fs_write_data_pages, @@ -3935,7 +3946,7 @@ const struct address_space_operations f2fs_dblock_aops = { .write_end = f2fs_write_end, .dirty_folio = f2fs_dirty_data_folio, .invalidate_folio = f2fs_invalidate_folio, - .releasepage = f2fs_release_page, + .release_folio = f2fs_release_folio, .direct_IO = noop_direct_IO, .bmap = f2fs_bmap, .swap_activate = f2fs_swap_activate, diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index cd1e65bcf0b0..10d1f138d14f 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -18,6 +18,7 @@ #include <linux/kobject.h> #include <linux/sched.h> #include <linux/cred.h> +#include <linux/sched/mm.h> #include <linux/vmalloc.h> #include <linux/bio.h> #include <linux/blkdev.h> @@ -154,7 +155,6 @@ struct f2fs_mount_info { int s_jquota_fmt; /* Format of quota to use */ #endif /* For which write hints are passed down to block layer */ - int whint_mode; int alloc_mode; /* segment allocation policy */ int fsync_mode; /* fsync policy */ int fs_mode; /* fs mode: LFS or ADAPTIVE */ @@ -1334,12 +1334,6 @@ enum { }; enum { - WHINT_MODE_OFF, /* not pass down write hints */ - WHINT_MODE_USER, /* try to pass down hints given by users */ - WHINT_MODE_FS, /* pass down hints with F2FS policy */ -}; - -enum { ALLOC_MODE_DEFAULT, /* stay default */ ALLOC_MODE_REUSE, /* reuse segments as much as possible */ }; @@ -2661,6 +2655,7 @@ static inline struct page *f2fs_grab_cache_page(struct address_space *mapping, pgoff_t index, bool for_write) { struct page *page; + unsigned int flags; if (IS_ENABLED(CONFIG_F2FS_FAULT_INJECTION)) { if (!for_write) @@ -2680,7 +2675,12 @@ static inline struct page *f2fs_grab_cache_page(struct address_space *mapping, if (!for_write) return grab_cache_page(mapping, index); - return grab_cache_page_write_begin(mapping, index, AOP_FLAG_NOFS); + + flags = memalloc_nofs_save(); + page = grab_cache_page_write_begin(mapping, index); + memalloc_nofs_restore(flags); + + return page; } static inline struct page *f2fs_pagecache_get_page( @@ -3657,8 +3657,6 @@ void f2fs_destroy_segment_manager(struct f2fs_sb_info *sbi); int __init f2fs_create_segment_manager_caches(void); void f2fs_destroy_segment_manager_caches(void); int f2fs_rw_hint_to_seg_type(enum rw_hint hint); -enum rw_hint f2fs_io_type_to_rw_hint(struct f2fs_sb_info *sbi, - enum page_type type, enum temp_type temp); unsigned int f2fs_usable_segs_in_sec(struct f2fs_sb_info *sbi, unsigned int segno); unsigned int f2fs_usable_blks_in_seg(struct f2fs_sb_info *sbi, @@ -3770,7 +3768,7 @@ int f2fs_write_single_data_page(struct page *page, int *submitted, int compr_blocks, bool allow_balance); void f2fs_write_failed(struct inode *inode, loff_t to); void f2fs_invalidate_folio(struct folio *folio, size_t offset, size_t length); -int f2fs_release_page(struct page *page, gfp_t wait); +bool f2fs_release_folio(struct folio *folio, gfp_t wait); #ifdef CONFIG_MIGRATION int f2fs_migrate_page(struct address_space *mapping, struct page *newpage, struct page *page, enum migrate_mode mode); @@ -4381,8 +4379,7 @@ static inline bool f2fs_hw_should_discard(struct f2fs_sb_info *sbi) static inline bool f2fs_bdev_support_discard(struct block_device *bdev) { - return blk_queue_discard(bdev_get_queue(bdev)) || - bdev_is_zoned(bdev); + return bdev_max_discard_sectors(bdev) || bdev_is_zoned(bdev); } static inline bool f2fs_hw_support_discard(struct f2fs_sb_info *sbi) diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 5b89af0f27f0..100637b1adb3 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -2285,7 +2285,6 @@ static int f2fs_ioc_fitrim(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); struct super_block *sb = inode->i_sb; - struct request_queue *q = bdev_get_queue(sb->s_bdev); struct fstrim_range range; int ret; @@ -2304,7 +2303,7 @@ static int f2fs_ioc_fitrim(struct file *filp, unsigned long arg) return ret; range.minlen = max((unsigned int)range.minlen, - q->limits.discard_granularity); + bdev_discard_granularity(sb->s_bdev)); ret = f2fs_trim_fs(F2FS_SB(sb), &range); mnt_drop_write_file(filp); if (ret < 0) @@ -3686,18 +3685,18 @@ out: static int f2fs_secure_erase(struct block_device *bdev, struct inode *inode, pgoff_t off, block_t block, block_t len, u32 flags) { - struct request_queue *q = bdev_get_queue(bdev); sector_t sector = SECTOR_FROM_BLOCK(block); sector_t nr_sects = SECTOR_FROM_BLOCK(len); int ret = 0; - if (!q) - return -ENXIO; - - if (flags & F2FS_TRIM_FILE_DISCARD) - ret = blkdev_issue_discard(bdev, sector, nr_sects, GFP_NOFS, - blk_queue_secure_erase(q) ? - BLKDEV_DISCARD_SECURE : 0); + if (flags & F2FS_TRIM_FILE_DISCARD) { + if (bdev_max_secure_erase_sectors(bdev)) + ret = blkdev_issue_secure_erase(bdev, sector, nr_sects, + GFP_NOFS); + else + ret = blkdev_issue_discard(bdev, sector, nr_sects, + GFP_NOFS); + } if (!ret && (flags & F2FS_TRIM_FILE_ZEROOUT)) { if (IS_ENCRYPTED(inode)) @@ -4309,7 +4308,7 @@ static ssize_t f2fs_dio_read_iter(struct kiocb *iocb, struct iov_iter *to) */ inc_page_count(sbi, F2FS_DIO_READ); dio = __iomap_dio_rw(iocb, to, &f2fs_iomap_ops, - &f2fs_iomap_dio_read_ops, 0, 0); + &f2fs_iomap_dio_read_ops, 0, NULL, 0); if (IS_ERR_OR_NULL(dio)) { ret = PTR_ERR_OR_ZERO(dio); if (ret != -EIOCBQUEUED) @@ -4527,7 +4526,7 @@ static ssize_t f2fs_dio_write_iter(struct kiocb *iocb, struct iov_iter *from, if (pos + count > inode->i_size) dio_flags |= IOMAP_DIO_FORCE_WAIT; dio = __iomap_dio_rw(iocb, from, &f2fs_iomap_ops, - &f2fs_iomap_dio_write_ops, dio_flags, 0); + &f2fs_iomap_dio_write_ops, dio_flags, NULL, 0); if (IS_ERR_OR_NULL(dio)) { ret = PTR_ERR_OR_ZERO(dio); if (ret == -ENOTBLK) diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index 71f232dcf3c2..83639238a1fe 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -550,7 +550,8 @@ make_now: } f2fs_set_inode_flags(inode); - if (file_should_truncate(inode)) { + if (file_should_truncate(inode) && + !is_sbi_flag_set(sbi, SBI_POR_DOING)) { ret = f2fs_truncate(inode); if (ret) goto bad_inode; diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index c45d341dcf6e..8ccff18560ff 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -2165,7 +2165,7 @@ const struct address_space_operations f2fs_node_aops = { .writepages = f2fs_write_node_pages, .dirty_folio = f2fs_dirty_node_folio, .invalidate_folio = f2fs_invalidate_folio, - .releasepage = f2fs_release_page, + .release_folio = f2fs_release_folio, #ifdef CONFIG_MIGRATION .migratepage = f2fs_migrate_page, #endif diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index 22dfeb991529..7225ce09f3ab 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -1196,9 +1196,8 @@ static int __submit_discard_cmd(struct f2fs_sb_info *sbi, unsigned int *issued) { struct block_device *bdev = dc->bdev; - struct request_queue *q = bdev_get_queue(bdev); unsigned int max_discard_blocks = - SECTOR_TO_BLOCK(q->limits.max_discard_sectors); + SECTOR_TO_BLOCK(bdev_max_discard_sectors(bdev)); struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; struct list_head *wait_list = (dpolicy->type == DPOLICY_FSTRIM) ? &(dcc->fstrim_list) : &(dcc->wait_list); @@ -1245,7 +1244,7 @@ static int __submit_discard_cmd(struct f2fs_sb_info *sbi, err = __blkdev_issue_discard(bdev, SECTOR_FROM_BLOCK(start), SECTOR_FROM_BLOCK(len), - GFP_NOFS, 0, &bio); + GFP_NOFS, &bio); submit: if (err) { spin_lock_irqsave(&dc->lock, flags); @@ -1375,9 +1374,8 @@ static void __update_discard_tree_range(struct f2fs_sb_info *sbi, struct discard_cmd *dc; struct discard_info di = {0}; struct rb_node **insert_p = NULL, *insert_parent = NULL; - struct request_queue *q = bdev_get_queue(bdev); unsigned int max_discard_blocks = - SECTOR_TO_BLOCK(q->limits.max_discard_sectors); + SECTOR_TO_BLOCK(bdev_max_discard_sectors(bdev)); block_t end = lstart + len; dc = (struct discard_cmd *)f2fs_lookup_rb_tree_ret(&dcc->root, @@ -3243,101 +3241,6 @@ int f2fs_rw_hint_to_seg_type(enum rw_hint hint) } } -/* This returns write hints for each segment type. This hints will be - * passed down to block layer. There are mapping tables which depend on - * the mount option 'whint_mode'. - * - * 1) whint_mode=off. F2FS only passes down WRITE_LIFE_NOT_SET. - * - * 2) whint_mode=user-based. F2FS tries to pass down hints given by users. - * - * User F2FS Block - * ---- ---- ----- - * META WRITE_LIFE_NOT_SET - * HOT_NODE " - * WARM_NODE " - * COLD_NODE " - * ioctl(COLD) COLD_DATA WRITE_LIFE_EXTREME - * extension list " " - * - * -- buffered io - * WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME - * WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT - * WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_NOT_SET - * WRITE_LIFE_NONE " " - * WRITE_LIFE_MEDIUM " " - * WRITE_LIFE_LONG " " - * - * -- direct io - * WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME - * WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT - * WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_NOT_SET - * WRITE_LIFE_NONE " WRITE_LIFE_NONE - * WRITE_LIFE_MEDIUM " WRITE_LIFE_MEDIUM - * WRITE_LIFE_LONG " WRITE_LIFE_LONG - * - * 3) whint_mode=fs-based. F2FS passes down hints with its policy. - * - * User F2FS Block - * ---- ---- ----- - * META WRITE_LIFE_MEDIUM; - * HOT_NODE WRITE_LIFE_NOT_SET - * WARM_NODE " - * COLD_NODE WRITE_LIFE_NONE - * ioctl(COLD) COLD_DATA WRITE_LIFE_EXTREME - * extension list " " - * - * -- buffered io - * WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME - * WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT - * WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_LONG - * WRITE_LIFE_NONE " " - * WRITE_LIFE_MEDIUM " " - * WRITE_LIFE_LONG " " - * - * -- direct io - * WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME - * WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT - * WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_NOT_SET - * WRITE_LIFE_NONE " WRITE_LIFE_NONE - * WRITE_LIFE_MEDIUM " WRITE_LIFE_MEDIUM - * WRITE_LIFE_LONG " WRITE_LIFE_LONG - */ - -enum rw_hint f2fs_io_type_to_rw_hint(struct f2fs_sb_info *sbi, - enum page_type type, enum temp_type temp) -{ - if (F2FS_OPTION(sbi).whint_mode == WHINT_MODE_USER) { - if (type == DATA) { - if (temp == WARM) - return WRITE_LIFE_NOT_SET; - else if (temp == HOT) - return WRITE_LIFE_SHORT; - else if (temp == COLD) - return WRITE_LIFE_EXTREME; - } else { - return WRITE_LIFE_NOT_SET; - } - } else if (F2FS_OPTION(sbi).whint_mode == WHINT_MODE_FS) { - if (type == DATA) { - if (temp == WARM) - return WRITE_LIFE_LONG; - else if (temp == HOT) - return WRITE_LIFE_SHORT; - else if (temp == COLD) - return WRITE_LIFE_EXTREME; - } else if (type == NODE) { - if (temp == WARM || temp == HOT) - return WRITE_LIFE_NOT_SET; - else if (temp == COLD) - return WRITE_LIFE_NONE; - } else if (type == META) { - return WRITE_LIFE_MEDIUM; - } - } - return WRITE_LIFE_NOT_SET; -} - static int __get_segment_type_2(struct f2fs_io_info *fio) { if (fio->type == DATA) diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index ea939db18f88..ed3e8b7a8260 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -138,7 +138,6 @@ enum { Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_jqfmt_vfsv1, - Opt_whint, Opt_alloc, Opt_fsync, Opt_test_dummy_encryption, @@ -214,7 +213,6 @@ static match_table_t f2fs_tokens = { {Opt_jqfmt_vfsold, "jqfmt=vfsold"}, {Opt_jqfmt_vfsv0, "jqfmt=vfsv0"}, {Opt_jqfmt_vfsv1, "jqfmt=vfsv1"}, - {Opt_whint, "whint_mode=%s"}, {Opt_alloc, "alloc_mode=%s"}, {Opt_fsync, "fsync_mode=%s"}, {Opt_test_dummy_encryption, "test_dummy_encryption=%s"}, @@ -975,22 +973,6 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount) f2fs_info(sbi, "quota operations not supported"); break; #endif - case Opt_whint: - name = match_strdup(&args[0]); - if (!name) - return -ENOMEM; - if (!strcmp(name, "user-based")) { - F2FS_OPTION(sbi).whint_mode = WHINT_MODE_USER; - } else if (!strcmp(name, "off")) { - F2FS_OPTION(sbi).whint_mode = WHINT_MODE_OFF; - } else if (!strcmp(name, "fs-based")) { - F2FS_OPTION(sbi).whint_mode = WHINT_MODE_FS; - } else { - kfree(name); - return -EINVAL; - } - kfree(name); - break; case Opt_alloc: name = match_strdup(&args[0]); if (!name) @@ -1328,12 +1310,6 @@ default_check: return -EINVAL; } - /* Not pass down write hints if the number of active logs is lesser - * than NR_CURSEG_PERSIST_TYPE. - */ - if (F2FS_OPTION(sbi).active_logs != NR_CURSEG_PERSIST_TYPE) - F2FS_OPTION(sbi).whint_mode = WHINT_MODE_OFF; - if (f2fs_sb_has_readonly(sbi) && !f2fs_readonly(sbi->sb)) { f2fs_err(sbi, "Allow to mount readonly mode only"); return -EROFS; @@ -1978,10 +1954,6 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root) seq_puts(seq, ",prjquota"); #endif f2fs_show_quota_options(seq, sbi->sb); - if (F2FS_OPTION(sbi).whint_mode == WHINT_MODE_USER) - seq_printf(seq, ",whint_mode=%s", "user-based"); - else if (F2FS_OPTION(sbi).whint_mode == WHINT_MODE_FS) - seq_printf(seq, ",whint_mode=%s", "fs-based"); fscrypt_show_test_dummy_encryption(seq, ',', sbi->sb); @@ -2033,7 +2005,6 @@ static void default_options(struct f2fs_sb_info *sbi) F2FS_OPTION(sbi).active_logs = NR_CURSEG_PERSIST_TYPE; F2FS_OPTION(sbi).inline_xattr_size = DEFAULT_INLINE_XATTR_ADDRS; - F2FS_OPTION(sbi).whint_mode = WHINT_MODE_OFF; F2FS_OPTION(sbi).alloc_mode = ALLOC_MODE_DEFAULT; F2FS_OPTION(sbi).fsync_mode = FSYNC_MODE_POSIX; F2FS_OPTION(sbi).s_resuid = make_kuid(&init_user_ns, F2FS_DEF_RESUID); @@ -2314,8 +2285,7 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) need_stop_gc = true; } - if (*flags & SB_RDONLY || - F2FS_OPTION(sbi).whint_mode != org_mount_opt.whint_mode) { + if (*flags & SB_RDONLY) { sync_inodes_sb(sb); set_sbi_flag(sbi, SBI_IS_DIRTY); @@ -2513,7 +2483,7 @@ static ssize_t f2fs_quota_write(struct super_block *sb, int type, tocopy = min_t(unsigned long, sb->s_blocksize - offset, towrite); retry: - err = a_ops->write_begin(NULL, mapping, off, tocopy, 0, + err = a_ops->write_begin(NULL, mapping, off, tocopy, &page, &fsdata); if (unlikely(err)) { if (err == -ENOMEM) { diff --git a/fs/f2fs/verity.c b/fs/f2fs/verity.c index 3d793202cc9f..65395ae188aa 100644 --- a/fs/f2fs/verity.c +++ b/fs/f2fs/verity.c @@ -74,6 +74,9 @@ static int pagecache_read(struct inode *inode, void *buf, size_t count, static int pagecache_write(struct inode *inode, const void *buf, size_t count, loff_t pos) { + struct address_space *mapping = inode->i_mapping; + const struct address_space_operations *aops = mapping->a_ops; + if (pos + count > inode->i_sb->s_maxbytes) return -EFBIG; @@ -85,8 +88,7 @@ static int pagecache_write(struct inode *inode, const void *buf, size_t count, void *addr; int res; - res = pagecache_write_begin(NULL, inode->i_mapping, pos, n, 0, - &page, &fsdata); + res = aops->write_begin(NULL, mapping, pos, n, &page, &fsdata); if (res) return res; @@ -94,8 +96,7 @@ static int pagecache_write(struct inode *inode, const void *buf, size_t count, memcpy(addr + offset_in_page(pos), buf, n); kunmap_atomic(addr); - res = pagecache_write_end(NULL, inode->i_mapping, pos, n, n, - page, fsdata); + res = aops->write_end(NULL, mapping, pos, n, n, page, fsdata); if (res < 0) return res; if (res != n) diff --git a/fs/fat/file.c b/fs/fat/file.c index a5a309fcc7fa..bf91f977debe 100644 --- a/fs/fat/file.c +++ b/fs/fat/file.c @@ -127,13 +127,12 @@ static int fat_ioctl_fitrim(struct inode *inode, unsigned long arg) struct super_block *sb = inode->i_sb; struct fstrim_range __user *user_range; struct fstrim_range range; - struct request_queue *q = bdev_get_queue(sb->s_bdev); int err; if (!capable(CAP_SYS_ADMIN)) return -EPERM; - if (!blk_queue_discard(q)) + if (!bdev_max_discard_sectors(sb->s_bdev)) return -EOPNOTSUPP; user_range = (struct fstrim_range __user *)arg; @@ -141,7 +140,7 @@ static int fat_ioctl_fitrim(struct inode *inode, unsigned long arg) return -EFAULT; range.minlen = max_t(unsigned int, range.minlen, - q->limits.discard_granularity); + bdev_discard_granularity(sb->s_bdev)); err = fat_trim_fs(inode, &range); if (err < 0) diff --git a/fs/fat/inode.c b/fs/fat/inode.c index bf6051bdf1d1..69b4d4ae64d7 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -205,9 +205,9 @@ static int fat_writepages(struct address_space *mapping, return mpage_writepages(mapping, wbc, fat_get_block); } -static int fat_readpage(struct file *file, struct page *page) +static int fat_read_folio(struct file *file, struct folio *folio) { - return mpage_readpage(page, fat_get_block); + return mpage_read_folio(folio, fat_get_block); } static void fat_readahead(struct readahead_control *rac) @@ -226,13 +226,13 @@ static void fat_write_failed(struct address_space *mapping, loff_t to) } static int fat_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, + loff_t pos, unsigned len, struct page **pagep, void **fsdata) { int err; *pagep = NULL; - err = cont_write_begin(file, mapping, pos, len, flags, + err = cont_write_begin(file, mapping, pos, len, pagep, fsdata, fat_get_block, &MSDOS_I(mapping->host)->mmu_private); if (err < 0) @@ -344,7 +344,7 @@ int fat_block_truncate_page(struct inode *inode, loff_t from) static const struct address_space_operations fat_aops = { .dirty_folio = block_dirty_folio, .invalidate_folio = block_invalidate_folio, - .readpage = fat_readpage, + .read_folio = fat_read_folio, .readahead = fat_readahead, .writepage = fat_writepage, .writepages = fat_writepages, @@ -1872,13 +1872,9 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat, goto out_fail; } - if (sbi->options.discard) { - struct request_queue *q = bdev_get_queue(sb->s_bdev); - if (!blk_queue_discard(q)) - fat_msg(sb, KERN_WARNING, - "mounting with \"discard\" option, but " - "the device does not support discard"); - } + if (sbi->options.discard && !bdev_max_discard_sectors(sb->s_bdev)) + fat_msg(sb, KERN_WARNING, + "mounting with \"discard\" option, but the device does not support discard"); fat_set_state(sb, 1, 0); return 0; diff --git a/fs/file_table.c b/fs/file_table.c index 7d2e692b66a9..ada8fe814db9 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -412,6 +412,7 @@ void __fput_sync(struct file *file) } EXPORT_SYMBOL(fput); +EXPORT_SYMBOL(__fput_sync); void __init files_init(void) { diff --git a/fs/freevxfs/vxfs_immed.c b/fs/freevxfs/vxfs_immed.c index bfc780c682fb..a37431e443d3 100644 --- a/fs/freevxfs/vxfs_immed.c +++ b/fs/freevxfs/vxfs_immed.c @@ -38,33 +38,34 @@ #include "vxfs_inode.h" -static int vxfs_immed_readpage(struct file *, struct page *); +static int vxfs_immed_read_folio(struct file *, struct folio *); /* * Address space operations for immed files and directories. */ const struct address_space_operations vxfs_immed_aops = { - .readpage = vxfs_immed_readpage, + .read_folio = vxfs_immed_read_folio, }; /** - * vxfs_immed_readpage - read part of an immed inode into pagecache + * vxfs_immed_read_folio - read part of an immed inode into pagecache * @file: file context (unused) - * @page: page frame to fill in. + * @folio: folio to fill in. * * Description: - * vxfs_immed_readpage reads a part of the immed area of the + * vxfs_immed_read_folio reads a part of the immed area of the * file that hosts @pp into the pagecache. * * Returns: * Zero on success, else a negative error code. * * Locking status: - * @page is locked and will be unlocked. + * @folio is locked and will be unlocked. */ static int -vxfs_immed_readpage(struct file *fp, struct page *pp) +vxfs_immed_read_folio(struct file *fp, struct folio *folio) { + struct page *pp = &folio->page; struct vxfs_inode_info *vip = VXFS_INO(pp->mapping->host); u_int64_t offset = (u_int64_t)pp->index << PAGE_SHIFT; caddr_t kaddr; diff --git a/fs/freevxfs/vxfs_subr.c b/fs/freevxfs/vxfs_subr.c index e806694d4145..6143ebab940d 100644 --- a/fs/freevxfs/vxfs_subr.c +++ b/fs/freevxfs/vxfs_subr.c @@ -38,11 +38,11 @@ #include "vxfs_extern.h" -static int vxfs_readpage(struct file *, struct page *); +static int vxfs_read_folio(struct file *, struct folio *); static sector_t vxfs_bmap(struct address_space *, sector_t); const struct address_space_operations vxfs_aops = { - .readpage = vxfs_readpage, + .read_folio = vxfs_read_folio, .bmap = vxfs_bmap, }; @@ -141,24 +141,23 @@ vxfs_getblk(struct inode *ip, sector_t iblock, } /** - * vxfs_readpage - read one page synchronously into the pagecache + * vxfs_read_folio - read one page synchronously into the pagecache * @file: file context (unused) - * @page: page frame to fill in. + * @folio: folio to fill in. * * Description: - * The vxfs_readpage routine reads @page synchronously into the + * The vxfs_read_folio routine reads @folio synchronously into the * pagecache. * * Returns: * Zero on success, else a negative error code. * * Locking status: - * @page is locked and will be unlocked. + * @folio is locked and will be unlocked. */ -static int -vxfs_readpage(struct file *file, struct page *page) +static int vxfs_read_folio(struct file *file, struct folio *folio) { - return block_read_full_page(page, vxfs_getblk); + return block_read_full_folio(folio, vxfs_getblk); } /** diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 591fe9cf1659..a1074a26e784 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -1712,6 +1712,10 @@ static int writeback_single_inode(struct inode *inode, */ if (!(inode->i_state & I_DIRTY_ALL)) inode_cgwb_move_to_attached(inode, wb); + else if (!(inode->i_state & I_SYNC_QUEUED) && + (inode->i_state & I_DIRTY)) + redirty_tail_locked(inode, wb); + spin_unlock(&wb->list_lock); inode_sync_complete(inode); out: @@ -1775,11 +1779,12 @@ static long writeback_sb_inodes(struct super_block *sb, }; unsigned long start_time = jiffies; long write_chunk; - long wrote = 0; /* count both pages and inodes */ + long total_wrote = 0; /* count both pages and inodes */ while (!list_empty(&wb->b_io)) { struct inode *inode = wb_inode(wb->b_io.prev); struct bdi_writeback *tmp_wb; + long wrote; if (inode->i_sb != sb) { if (work->sb) { @@ -1855,7 +1860,9 @@ static long writeback_sb_inodes(struct super_block *sb, wbc_detach_inode(&wbc); work->nr_pages -= write_chunk - wbc.nr_to_write; - wrote += write_chunk - wbc.nr_to_write; + wrote = write_chunk - wbc.nr_to_write - wbc.pages_skipped; + wrote = wrote < 0 ? 0 : wrote; + total_wrote += wrote; if (need_resched()) { /* @@ -1877,7 +1884,7 @@ static long writeback_sb_inodes(struct super_block *sb, tmp_wb = inode_to_wb_and_lock_list(inode); spin_lock(&inode->i_lock); if (!(inode->i_state & I_DIRTY_ALL)) - wrote++; + total_wrote++; requeue_inode(inode, tmp_wb, &wbc); inode_sync_complete(inode); spin_unlock(&inode->i_lock); @@ -1891,14 +1898,14 @@ static long writeback_sb_inodes(struct super_block *sb, * bail out to wb_writeback() often enough to check * background threshold and other termination conditions. */ - if (wrote) { + if (total_wrote) { if (time_is_before_jiffies(start_time + HZ / 10UL)) break; if (work->nr_pages <= 0) break; } } - return wrote; + return total_wrote; } static long __writeback_inodes_wb(struct bdi_writeback *wb, diff --git a/fs/fscache/Kconfig b/fs/fscache/Kconfig index 76316c4a3fb7..b313a978ae0a 100644 --- a/fs/fscache/Kconfig +++ b/fs/fscache/Kconfig @@ -38,6 +38,3 @@ config FSCACHE_DEBUG enabled by setting bits in /sys/modules/fscache/parameter/debug. See Documentation/filesystems/caching/fscache.rst for more information. - -config FSCACHE_OLD_API - bool diff --git a/fs/fscache/cache.c b/fs/fscache/cache.c index 2749933852a9..d645f8b302a2 100644 --- a/fs/fscache/cache.c +++ b/fs/fscache/cache.c @@ -214,7 +214,7 @@ void fscache_relinquish_cache(struct fscache_cache *cache) cache->ops = NULL; cache->cache_priv = NULL; - smp_store_release(&cache->state, FSCACHE_CACHE_IS_NOT_PRESENT); + fscache_set_cache_state(cache, FSCACHE_CACHE_IS_NOT_PRESENT); fscache_put_cache(cache, where); } EXPORT_SYMBOL(fscache_relinquish_cache); diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c index 9bb1ab5fe5ed..9d3cf0111709 100644 --- a/fs/fscache/cookie.c +++ b/fs/fscache/cookie.c @@ -30,7 +30,7 @@ static DEFINE_SPINLOCK(fscache_cookie_lru_lock); DEFINE_TIMER(fscache_cookie_lru_timer, fscache_cookie_lru_timed_out); static DECLARE_WORK(fscache_cookie_lru_work, fscache_cookie_lru_worker); static const char fscache_cookie_states[FSCACHE_COOKIE_STATE__NR] = "-LCAIFUWRD"; -unsigned int fscache_lru_cookie_timeout = 10 * HZ; +static unsigned int fscache_lru_cookie_timeout = 10 * HZ; void fscache_print_cookie(struct fscache_cookie *cookie, char prefix) { @@ -1069,6 +1069,7 @@ void __fscache_invalidate(struct fscache_cookie *cookie, } EXPORT_SYMBOL(__fscache_invalidate); +#ifdef CONFIG_PROC_FS /* * Generate a list of extant cookies in /proc/fs/fscache/cookies */ @@ -1145,3 +1146,4 @@ const struct seq_operations fscache_cookies_seq_ops = { .stop = fscache_cookies_seq_stop, .show = fscache_cookies_seq_show, }; +#endif diff --git a/fs/fscache/internal.h b/fs/fscache/internal.h index ed1c9ed737f2..1336f517e9b1 100644 --- a/fs/fscache/internal.h +++ b/fs/fscache/internal.h @@ -56,7 +56,9 @@ static inline bool fscache_set_cache_state_maybe(struct fscache_cache *cache, * cookie.c */ extern struct kmem_cache *fscache_cookie_jar; +#ifdef CONFIG_PROC_FS extern const struct seq_operations fscache_cookies_seq_ops; +#endif extern struct timer_list fscache_cookie_lru_timer; extern void fscache_print_cookie(struct fscache_cookie *cookie, char prefix); @@ -137,7 +139,9 @@ int fscache_stats_show(struct seq_file *m, void *v); /* * volume.c */ +#ifdef CONFIG_PROC_FS extern const struct seq_operations fscache_volumes_seq_ops; +#endif struct fscache_volume *fscache_get_volume(struct fscache_volume *volume, enum fscache_volume_trace where); diff --git a/fs/fscache/io.c b/fs/fscache/io.c index c8c7fe9e9a6e..3af3b08a9bb3 100644 --- a/fs/fscache/io.c +++ b/fs/fscache/io.c @@ -235,8 +235,7 @@ static void fscache_wreq_done(void *priv, ssize_t transferred_or_error, { struct fscache_write_request *wreq = priv; - fscache_clear_page_bits(fscache_cres_cookie(&wreq->cache_resources), - wreq->mapping, wreq->start, wreq->len, + fscache_clear_page_bits(wreq->mapping, wreq->start, wreq->len, wreq->set_bits); if (wreq->term_func) @@ -296,7 +295,7 @@ abandon_end: abandon_free: kfree(wreq); abandon: - fscache_clear_page_bits(cookie, mapping, start, len, cond); + fscache_clear_page_bits(mapping, start, len, cond); if (term_func) term_func(term_func_priv, ret, false); } diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 9ff27b8a9782..74303d6e987b 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -1957,20 +1957,20 @@ void fuse_init_dir(struct inode *inode) fi->rdc.version = 0; } -static int fuse_symlink_readpage(struct file *null, struct page *page) +static int fuse_symlink_read_folio(struct file *null, struct folio *folio) { - int err = fuse_readlink_page(page->mapping->host, page); + int err = fuse_readlink_page(folio->mapping->host, &folio->page); if (!err) - SetPageUptodate(page); + folio_mark_uptodate(folio); - unlock_page(page); + folio_unlock(folio); return err; } static const struct address_space_operations fuse_symlink_aops = { - .readpage = fuse_symlink_readpage, + .read_folio = fuse_symlink_read_folio, }; void fuse_init_symlink(struct inode *inode) diff --git a/fs/fuse/file.c b/fs/fuse/file.c index f18d14d5fea1..05caa2b9272e 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -857,8 +857,9 @@ static int fuse_do_readpage(struct file *file, struct page *page) return 0; } -static int fuse_readpage(struct file *file, struct page *page) +static int fuse_read_folio(struct file *file, struct folio *folio) { + struct page *page = &folio->page; struct inode *inode = page->mapping->host; int err; @@ -1174,7 +1175,7 @@ static ssize_t fuse_fill_write_pages(struct fuse_io_args *ia, break; err = -ENOMEM; - page = grab_cache_page_write_begin(mapping, index, 0); + page = grab_cache_page_write_begin(mapping, index); if (!page) break; @@ -2273,8 +2274,7 @@ out: * but how to implement it without killing performance need more thinking. */ static int fuse_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, - struct page **pagep, void **fsdata) + loff_t pos, unsigned len, struct page **pagep, void **fsdata) { pgoff_t index = pos >> PAGE_SHIFT; struct fuse_conn *fc = get_fuse_conn(file_inode(file)); @@ -2284,7 +2284,7 @@ static int fuse_write_begin(struct file *file, struct address_space *mapping, WARN_ON(!fc->writeback_cache); - page = grab_cache_page_write_begin(mapping, index, flags); + page = grab_cache_page_write_begin(mapping, index); if (!page) goto error; @@ -3175,7 +3175,7 @@ static const struct file_operations fuse_file_operations = { }; static const struct address_space_operations fuse_file_aops = { - .readpage = fuse_readpage, + .read_folio = fuse_read_folio, .readahead = fuse_readahead, .writepage = fuse_writepage, .writepages = fuse_writepages, diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c index 72c9f31ce724..106e90a36583 100644 --- a/fs/gfs2/aops.c +++ b/fs/gfs2/aops.c @@ -464,22 +464,26 @@ static int stuffed_readpage(struct gfs2_inode *ip, struct page *page) return 0; } - -static int __gfs2_readpage(void *file, struct page *page) +/** + * gfs2_read_folio - read a folio from a file + * @file: The file to read + * @folio: The folio in the file + */ +static int gfs2_read_folio(struct file *file, struct folio *folio) { - struct inode *inode = page->mapping->host; + struct inode *inode = folio->mapping->host; struct gfs2_inode *ip = GFS2_I(inode); struct gfs2_sbd *sdp = GFS2_SB(inode); int error; if (!gfs2_is_jdata(ip) || - (i_blocksize(inode) == PAGE_SIZE && !page_has_buffers(page))) { - error = iomap_readpage(page, &gfs2_iomap_ops); + (i_blocksize(inode) == PAGE_SIZE && !folio_buffers(folio))) { + error = iomap_read_folio(folio, &gfs2_iomap_ops); } else if (gfs2_is_stuffed(ip)) { - error = stuffed_readpage(ip, page); - unlock_page(page); + error = stuffed_readpage(ip, &folio->page); + folio_unlock(folio); } else { - error = mpage_readpage(page, gfs2_block_map); + error = mpage_read_folio(folio, gfs2_block_map); } if (unlikely(gfs2_withdrawn(sdp))) @@ -489,17 +493,6 @@ static int __gfs2_readpage(void *file, struct page *page) } /** - * gfs2_readpage - read a page of a file - * @file: The file to read - * @page: The page of the file - */ - -static int gfs2_readpage(struct file *file, struct page *page) -{ - return __gfs2_readpage(file, page); -} - -/** * gfs2_internal_read - read an internal file * @ip: The gfs2 inode * @buf: The buffer to fill @@ -523,7 +516,7 @@ int gfs2_internal_read(struct gfs2_inode *ip, char *buf, loff_t *pos, amt = size - copied; if (offset + size > PAGE_SIZE) amt = PAGE_SIZE - offset; - page = read_cache_page(mapping, index, __gfs2_readpage, NULL); + page = read_cache_page(mapping, index, gfs2_read_folio, NULL); if (IS_ERR(page)) return PTR_ERR(page); p = kmap_atomic(page); @@ -698,38 +691,40 @@ out: } /** - * gfs2_releasepage - free the metadata associated with a page - * @page: the page that's being released + * gfs2_release_folio - free the metadata associated with a folio + * @folio: the folio that's being released * @gfp_mask: passed from Linux VFS, ignored by us * - * Calls try_to_free_buffers() to free the buffers and put the page if the + * Calls try_to_free_buffers() to free the buffers and put the folio if the * buffers can be released. * - * Returns: 1 if the page was put or else 0 + * Returns: true if the folio was put or else false */ -int gfs2_releasepage(struct page *page, gfp_t gfp_mask) +bool gfs2_release_folio(struct folio *folio, gfp_t gfp_mask) { - struct address_space *mapping = page->mapping; + struct address_space *mapping = folio->mapping; struct gfs2_sbd *sdp = gfs2_mapping2sbd(mapping); struct buffer_head *bh, *head; struct gfs2_bufdata *bd; - if (!page_has_buffers(page)) - return 0; + head = folio_buffers(folio); + if (!head) + return false; /* - * From xfs_vm_releasepage: mm accommodates an old ext3 case where - * clean pages might not have had the dirty bit cleared. Thus, it can - * send actual dirty pages to ->releasepage() via shrink_active_list(). + * mm accommodates an old ext3 case where clean folios might + * not have had the dirty bit cleared. Thus, it can send actual + * dirty folios to ->release_folio() via shrink_active_list(). * - * As a workaround, we skip pages that contain dirty buffers below. - * Once ->releasepage isn't called on dirty pages anymore, we can warn - * on dirty buffers like we used to here again. + * As a workaround, we skip folios that contain dirty buffers + * below. Once ->release_folio isn't called on dirty folios + * anymore, we can warn on dirty buffers like we used to here + * again. */ gfs2_log_lock(sdp); - head = bh = page_buffers(page); + bh = head; do { if (atomic_read(&bh->b_count)) goto cannot_release; @@ -739,9 +734,9 @@ int gfs2_releasepage(struct page *page, gfp_t gfp_mask) if (buffer_dirty(bh) || WARN_ON(buffer_pinned(bh))) goto cannot_release; bh = bh->b_this_page; - } while(bh != head); + } while (bh != head); - head = bh = page_buffers(page); + bh = head; do { bd = bh->b_private; if (bd) { @@ -762,20 +757,20 @@ int gfs2_releasepage(struct page *page, gfp_t gfp_mask) } while (bh != head); gfs2_log_unlock(sdp); - return try_to_free_buffers(page); + return try_to_free_buffers(folio); cannot_release: gfs2_log_unlock(sdp); - return 0; + return false; } static const struct address_space_operations gfs2_aops = { .writepage = gfs2_writepage, .writepages = gfs2_writepages, - .readpage = gfs2_readpage, + .read_folio = gfs2_read_folio, .readahead = gfs2_readahead, .dirty_folio = filemap_dirty_folio, - .releasepage = iomap_releasepage, + .release_folio = iomap_release_folio, .invalidate_folio = iomap_invalidate_folio, .bmap = gfs2_bmap, .direct_IO = noop_direct_IO, @@ -787,12 +782,12 @@ static const struct address_space_operations gfs2_aops = { static const struct address_space_operations gfs2_jdata_aops = { .writepage = gfs2_jdata_writepage, .writepages = gfs2_jdata_writepages, - .readpage = gfs2_readpage, + .read_folio = gfs2_read_folio, .readahead = gfs2_readahead, .dirty_folio = jdata_dirty_folio, .bmap = gfs2_bmap, .invalidate_folio = gfs2_invalidate_folio, - .releasepage = gfs2_releasepage, + .release_folio = gfs2_release_folio, .is_partially_uptodate = block_is_partially_uptodate, .error_remove_page = generic_error_remove_page, }; diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index 39080b2d6cf8..b6697333bb2b 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -1153,13 +1153,12 @@ static int gfs2_iomap_end(struct inode *inode, loff_t pos, loff_t length, if (length != written && (iomap->flags & IOMAP_F_NEW)) { /* Deallocate blocks that were just allocated. */ - loff_t blockmask = i_blocksize(inode) - 1; - loff_t end = (pos + length) & ~blockmask; + loff_t hstart = round_up(pos + written, i_blocksize(inode)); + loff_t hend = iomap->offset + iomap->length; - pos = (pos + written + blockmask) & ~blockmask; - if (pos < end) { - truncate_pagecache_range(inode, pos, end - 1); - punch_hole(ip, pos, end - pos); + if (hstart < hend) { + truncate_pagecache_range(inode, hstart, hend - 1); + punch_hole(ip, hstart, hend - hstart); } } diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index 22b41acfbbc3..2cceb193dcd8 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -770,30 +770,27 @@ static int gfs2_fsync(struct file *file, loff_t start, loff_t end, return ret ? ret : ret1; } -static inline bool should_fault_in_pages(ssize_t ret, struct iov_iter *i, +static inline bool should_fault_in_pages(struct iov_iter *i, + struct kiocb *iocb, size_t *prev_count, size_t *window_size) { size_t count = iov_iter_count(i); size_t size, offs; - if (likely(!count)) - return false; - if (ret <= 0 && ret != -EFAULT) + if (!count) return false; if (!iter_is_iovec(i)) return false; size = PAGE_SIZE; - offs = offset_in_page(i->iov[0].iov_base + i->iov_offset); + offs = offset_in_page(iocb->ki_pos); if (*prev_count != count || !*window_size) { size_t nr_dirtied; - size = ALIGN(offs + count, PAGE_SIZE); - size = min_t(size_t, size, SZ_1M); nr_dirtied = max(current->nr_dirtied_pause - current->nr_dirtied, 8); - size = min(size, nr_dirtied << PAGE_SHIFT); + size = min_t(size_t, SZ_1M, nr_dirtied << PAGE_SHIFT); } *prev_count = count; @@ -807,7 +804,7 @@ static ssize_t gfs2_file_direct_read(struct kiocb *iocb, struct iov_iter *to, struct file *file = iocb->ki_filp; struct gfs2_inode *ip = GFS2_I(file->f_mapping->host); size_t prev_count = 0, window_size = 0; - size_t written = 0; + size_t read = 0; ssize_t ret; /* @@ -835,35 +832,33 @@ retry: ret = gfs2_glock_nq(gh); if (ret) goto out_uninit; -retry_under_glock: pagefault_disable(); to->nofault = true; ret = iomap_dio_rw(iocb, to, &gfs2_iomap_ops, NULL, - IOMAP_DIO_PARTIAL, written); + IOMAP_DIO_PARTIAL, NULL, read); to->nofault = false; pagefault_enable(); + if (ret <= 0 && ret != -EFAULT) + goto out_unlock; + /* No increment (+=) because iomap_dio_rw returns a cumulative value. */ if (ret > 0) - written = ret; - - if (should_fault_in_pages(ret, to, &prev_count, &window_size)) { - size_t leftover; + read = ret; - gfs2_holder_allow_demote(gh); - leftover = fault_in_iov_iter_writeable(to, window_size); - gfs2_holder_disallow_demote(gh); - if (leftover != window_size) { - if (gfs2_holder_queued(gh)) - goto retry_under_glock; + if (should_fault_in_pages(to, iocb, &prev_count, &window_size)) { + gfs2_glock_dq(gh); + window_size -= fault_in_iov_iter_writeable(to, window_size); + if (window_size) goto retry; - } } +out_unlock: if (gfs2_holder_queued(gh)) gfs2_glock_dq(gh); out_uninit: gfs2_holder_uninit(gh); + /* User space doesn't expect partial success. */ if (ret < 0) return ret; - return written; + return read; } static ssize_t gfs2_file_direct_write(struct kiocb *iocb, struct iov_iter *from, @@ -873,7 +868,7 @@ static ssize_t gfs2_file_direct_write(struct kiocb *iocb, struct iov_iter *from, struct inode *inode = file->f_mapping->host; struct gfs2_inode *ip = GFS2_I(inode); size_t prev_count = 0, window_size = 0; - size_t read = 0; + size_t written = 0; ssize_t ret; /* @@ -899,41 +894,39 @@ retry: ret = gfs2_glock_nq(gh); if (ret) goto out_uninit; -retry_under_glock: /* Silently fall back to buffered I/O when writing beyond EOF */ if (iocb->ki_pos + iov_iter_count(from) > i_size_read(&ip->i_inode)) - goto out; + goto out_unlock; from->nofault = true; ret = iomap_dio_rw(iocb, from, &gfs2_iomap_ops, NULL, - IOMAP_DIO_PARTIAL, read); + IOMAP_DIO_PARTIAL, NULL, written); from->nofault = false; - - if (ret == -ENOTBLK) - ret = 0; + if (ret <= 0) { + if (ret == -ENOTBLK) + ret = 0; + if (ret != -EFAULT) + goto out_unlock; + } + /* No increment (+=) because iomap_dio_rw returns a cumulative value. */ if (ret > 0) - read = ret; - - if (should_fault_in_pages(ret, from, &prev_count, &window_size)) { - size_t leftover; + written = ret; - gfs2_holder_allow_demote(gh); - leftover = fault_in_iov_iter_readable(from, window_size); - gfs2_holder_disallow_demote(gh); - if (leftover != window_size) { - if (gfs2_holder_queued(gh)) - goto retry_under_glock; + if (should_fault_in_pages(from, iocb, &prev_count, &window_size)) { + gfs2_glock_dq(gh); + window_size -= fault_in_iov_iter_readable(from, window_size); + if (window_size) goto retry; - } } -out: +out_unlock: if (gfs2_holder_queued(gh)) gfs2_glock_dq(gh); out_uninit: gfs2_holder_uninit(gh); + /* User space doesn't expect partial success. */ if (ret < 0) return ret; - return read; + return written; } static ssize_t gfs2_file_read_iter(struct kiocb *iocb, struct iov_iter *to) @@ -941,7 +934,7 @@ static ssize_t gfs2_file_read_iter(struct kiocb *iocb, struct iov_iter *to) struct gfs2_inode *ip; struct gfs2_holder gh; size_t prev_count = 0, window_size = 0; - size_t written = 0; + size_t read = 0; ssize_t ret; /* @@ -962,7 +955,7 @@ static ssize_t gfs2_file_read_iter(struct kiocb *iocb, struct iov_iter *to) if (ret >= 0) { if (!iov_iter_count(to)) return ret; - written = ret; + read = ret; } else if (ret != -EFAULT) { if (ret != -EAGAIN) return ret; @@ -975,32 +968,26 @@ retry: ret = gfs2_glock_nq(&gh); if (ret) goto out_uninit; -retry_under_glock: pagefault_disable(); ret = generic_file_read_iter(iocb, to); pagefault_enable(); + if (ret <= 0 && ret != -EFAULT) + goto out_unlock; if (ret > 0) - written += ret; + read += ret; - if (should_fault_in_pages(ret, to, &prev_count, &window_size)) { - size_t leftover; - - gfs2_holder_allow_demote(&gh); - leftover = fault_in_iov_iter_writeable(to, window_size); - gfs2_holder_disallow_demote(&gh); - if (leftover != window_size) { - if (gfs2_holder_queued(&gh)) - goto retry_under_glock; - if (written) - goto out_uninit; + if (should_fault_in_pages(to, iocb, &prev_count, &window_size)) { + gfs2_glock_dq(&gh); + window_size -= fault_in_iov_iter_writeable(to, window_size); + if (window_size) goto retry; - } } +out_unlock: if (gfs2_holder_queued(&gh)) gfs2_glock_dq(&gh); out_uninit: gfs2_holder_uninit(&gh); - return written ? written : ret; + return read ? read : ret; } static ssize_t gfs2_file_buffered_write(struct kiocb *iocb, @@ -1014,7 +1001,7 @@ static ssize_t gfs2_file_buffered_write(struct kiocb *iocb, struct gfs2_holder *statfs_gh = NULL; size_t prev_count = 0, window_size = 0; size_t orig_count = iov_iter_count(from); - size_t read = 0; + size_t written = 0; ssize_t ret; /* @@ -1032,10 +1019,18 @@ static ssize_t gfs2_file_buffered_write(struct kiocb *iocb, gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, gh); retry: + if (should_fault_in_pages(from, iocb, &prev_count, &window_size)) { + window_size -= fault_in_iov_iter_readable(from, window_size); + if (!window_size) { + ret = -EFAULT; + goto out_uninit; + } + from->count = min(from->count, window_size); + } ret = gfs2_glock_nq(gh); if (ret) goto out_uninit; -retry_under_glock: + if (inode == sdp->sd_rindex) { struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode); @@ -1052,27 +1047,19 @@ retry_under_glock: current->backing_dev_info = NULL; if (ret > 0) { iocb->ki_pos += ret; - read += ret; + written += ret; } if (inode == sdp->sd_rindex) gfs2_glock_dq_uninit(statfs_gh); - from->count = orig_count - read; - if (should_fault_in_pages(ret, from, &prev_count, &window_size)) { - size_t leftover; - - gfs2_holder_allow_demote(gh); - leftover = fault_in_iov_iter_readable(from, window_size); - gfs2_holder_disallow_demote(gh); - if (leftover != window_size) { - from->count = min(from->count, window_size - leftover); - if (gfs2_holder_queued(gh)) - goto retry_under_glock; - if (read && !(iocb->ki_flags & IOCB_DIRECT)) - goto out_uninit; - goto retry; - } + if (ret <= 0 && ret != -EFAULT) + goto out_unlock; + + from->count = orig_count - written; + if (should_fault_in_pages(from, iocb, &prev_count, &window_size)) { + gfs2_glock_dq(gh); + goto retry; } out_unlock: if (gfs2_holder_queued(gh)) @@ -1081,8 +1068,8 @@ out_uninit: gfs2_holder_uninit(gh); if (statfs_gh) kfree(statfs_gh); - from->count = orig_count - read; - return read ? read : ret; + from->count = orig_count - written; + return written ? written : ret; } /** diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 630c6550eacf..c992d53013d3 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -127,9 +127,11 @@ static void gfs2_glock_dealloc(struct rcu_head *rcu) struct gfs2_glock *gl = container_of(rcu, struct gfs2_glock, gl_rcu); kfree(gl->gl_lksb.sb_lvbptr); - if (gl->gl_ops->go_flags & GLOF_ASPACE) - kmem_cache_free(gfs2_glock_aspace_cachep, gl); - else + if (gl->gl_ops->go_flags & GLOF_ASPACE) { + struct gfs2_glock_aspace *gla = + container_of(gl, struct gfs2_glock_aspace, glock); + kmem_cache_free(gfs2_glock_aspace_cachep, gla); + } else kmem_cache_free(gfs2_glock_cachep, gl); } @@ -1159,7 +1161,6 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number, .ln_sbd = sdp }; struct gfs2_glock *gl, *tmp; struct address_space *mapping; - struct kmem_cache *cachep; int ret = 0; gl = find_insert_glock(&name, NULL); @@ -1170,20 +1171,24 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number, if (!create) return -ENOENT; - if (glops->go_flags & GLOF_ASPACE) - cachep = gfs2_glock_aspace_cachep; - else - cachep = gfs2_glock_cachep; - gl = kmem_cache_alloc(cachep, GFP_NOFS); - if (!gl) - return -ENOMEM; - + if (glops->go_flags & GLOF_ASPACE) { + struct gfs2_glock_aspace *gla = + kmem_cache_alloc(gfs2_glock_aspace_cachep, GFP_NOFS); + if (!gla) + return -ENOMEM; + gl = &gla->glock; + } else { + gl = kmem_cache_alloc(gfs2_glock_cachep, GFP_NOFS); + if (!gl) + return -ENOMEM; + } memset(&gl->gl_lksb, 0, sizeof(struct dlm_lksb)); + gl->gl_ops = glops; if (glops->go_flags & GLOF_LVB) { gl->gl_lksb.sb_lvbptr = kzalloc(GDLM_LVB_SIZE, GFP_NOFS); if (!gl->gl_lksb.sb_lvbptr) { - kmem_cache_free(cachep, gl); + gfs2_glock_dealloc(&gl->gl_rcu); return -ENOMEM; } } @@ -1197,7 +1202,6 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number, gl->gl_state = LM_ST_UNLOCKED; gl->gl_target = LM_ST_UNLOCKED; gl->gl_demote_state = LM_ST_EXCLUSIVE; - gl->gl_ops = glops; gl->gl_dstamp = 0; preempt_disable(); /* We use the global stats to estimate the initial per-glock stats */ @@ -1234,8 +1238,7 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number, *glp = tmp; out_free: - kfree(gl->gl_lksb.sb_lvbptr); - kmem_cache_free(cachep, gl); + gfs2_glock_dealloc(&gl->gl_rcu); if (atomic_dec_and_test(&sdp->sd_glock_disposal)) wake_up(&sdp->sd_glock_wait); diff --git a/fs/gfs2/glock.h b/fs/gfs2/glock.h index 4f8642301801..c0ae9100a0bc 100644 --- a/fs/gfs2/glock.h +++ b/fs/gfs2/glock.h @@ -138,6 +138,11 @@ struct lm_lockops { const match_table_t *lm_tokens; }; +struct gfs2_glock_aspace { + struct gfs2_glock glock; + struct address_space mapping; +}; + extern struct workqueue_struct *gfs2_delete_workqueue; static inline struct gfs2_holder *gfs2_glock_is_locked_by_me(struct gfs2_glock *gl) { @@ -179,8 +184,11 @@ static inline int gfs2_glock_is_held_shrd(struct gfs2_glock *gl) static inline struct address_space *gfs2_glock2aspace(struct gfs2_glock *gl) { - if (gl->gl_ops->go_flags & GLOF_ASPACE) - return (struct address_space *)(gl + 1); + if (gl->gl_ops->go_flags & GLOF_ASPACE) { + struct gfs2_glock_aspace *gla = + container_of(gl, struct gfs2_glock_aspace, glock); + return &gla->mapping; + } return NULL; } diff --git a/fs/gfs2/inode.h b/fs/gfs2/inode.h index 7b2c1f390db7..0264d514dda7 100644 --- a/fs/gfs2/inode.h +++ b/fs/gfs2/inode.h @@ -12,7 +12,7 @@ #include <linux/mm.h> #include "util.h" -extern int gfs2_releasepage(struct page *page, gfp_t gfp_mask); +bool gfs2_release_folio(struct folio *folio, gfp_t gfp_mask); extern int gfs2_internal_read(struct gfs2_inode *ip, char *buf, loff_t *pos, unsigned size); extern void gfs2_set_aops(struct inode *inode); diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c index 28d0eb23e18e..244187e3e70f 100644 --- a/fs/gfs2/main.c +++ b/fs/gfs2/main.c @@ -62,11 +62,10 @@ static void gfs2_init_glock_once(void *foo) static void gfs2_init_gl_aspace_once(void *foo) { - struct gfs2_glock *gl = foo; - struct address_space *mapping = (struct address_space *)(gl + 1); + struct gfs2_glock_aspace *gla = foo; - gfs2_init_glock_once(gl); - address_space_init_once(mapping); + gfs2_init_glock_once(&gla->glock); + address_space_init_once(&gla->mapping); } /** @@ -104,8 +103,7 @@ static int __init init_gfs2_fs(void) goto fail_cachep1; gfs2_glock_aspace_cachep = kmem_cache_create("gfs2_glock(aspace)", - sizeof(struct gfs2_glock) + - sizeof(struct address_space), + sizeof(struct gfs2_glock_aspace), 0, 0, gfs2_init_gl_aspace_once); if (!gfs2_glock_aspace_cachep) diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c index d8bd1d48bd78..868dcc71b581 100644 --- a/fs/gfs2/meta_io.c +++ b/fs/gfs2/meta_io.c @@ -92,14 +92,14 @@ const struct address_space_operations gfs2_meta_aops = { .dirty_folio = block_dirty_folio, .invalidate_folio = block_invalidate_folio, .writepage = gfs2_aspace_writepage, - .releasepage = gfs2_releasepage, + .release_folio = gfs2_release_folio, }; const struct address_space_operations gfs2_rgrp_aops = { .dirty_folio = block_dirty_folio, .invalidate_folio = block_invalidate_folio, .writepage = gfs2_aspace_writepage, - .releasepage = gfs2_releasepage, + .release_folio = gfs2_release_folio, }; /** diff --git a/fs/gfs2/meta_io.h b/fs/gfs2/meta_io.h index 21880d72081a..d0a58cdd433a 100644 --- a/fs/gfs2/meta_io.h +++ b/fs/gfs2/meta_io.h @@ -40,9 +40,11 @@ extern const struct address_space_operations gfs2_rgrp_aops; static inline struct gfs2_sbd *gfs2_mapping2sbd(struct address_space *mapping) { struct inode *inode = mapping->host; - if (mapping->a_ops == &gfs2_meta_aops) - return (((struct gfs2_glock *)mapping) - 1)->gl_name.ln_sbd; - else if (mapping->a_ops == &gfs2_rgrp_aops) + if (mapping->a_ops == &gfs2_meta_aops) { + struct gfs2_glock_aspace *gla = + container_of(mapping, struct gfs2_glock_aspace, mapping); + return gla->glock.gl_name.ln_sbd; + } else if (mapping->a_ops == &gfs2_rgrp_aops) return container_of(mapping, struct gfs2_sbd, sd_aspace); else return inode->i_sb->s_fs_info; diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index be0997e24d60..59d727a4ae2c 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -365,11 +365,12 @@ static void slot_put(struct gfs2_quota_data *qd) static int bh_get(struct gfs2_quota_data *qd) { struct gfs2_sbd *sdp = qd->qd_gl->gl_name.ln_sbd; - struct gfs2_inode *ip = GFS2_I(sdp->sd_qc_inode); + struct inode *inode = sdp->sd_qc_inode; + struct gfs2_inode *ip = GFS2_I(inode); unsigned int block, offset; struct buffer_head *bh; + struct iomap iomap = { }; int error; - struct buffer_head bh_map = { .b_state = 0, .b_blocknr = 0 }; mutex_lock(&sdp->sd_quota_mutex); @@ -381,11 +382,17 @@ static int bh_get(struct gfs2_quota_data *qd) block = qd->qd_slot / sdp->sd_qc_per_block; offset = qd->qd_slot % sdp->sd_qc_per_block; - bh_map.b_size = BIT(ip->i_inode.i_blkbits); - error = gfs2_block_map(&ip->i_inode, block, &bh_map, 0); + error = gfs2_iomap_get(inode, + (loff_t)block << inode->i_blkbits, + i_blocksize(inode), &iomap); if (error) goto fail; - error = gfs2_meta_read(ip->i_gl, bh_map.b_blocknr, DIO_WAIT, 0, &bh); + error = -ENOENT; + if (iomap.type != IOMAP_MAPPED) + goto fail; + + error = gfs2_meta_read(ip->i_gl, iomap.addr >> inode->i_blkbits, + DIO_WAIT, 0, &bh); if (error) goto fail; error = -EIO; @@ -443,9 +450,8 @@ static int qd_check_sync(struct gfs2_sbd *sdp, struct gfs2_quota_data *qd, static int qd_fish(struct gfs2_sbd *sdp, struct gfs2_quota_data **qdp) { - struct gfs2_quota_data *qd = NULL; + struct gfs2_quota_data *qd = NULL, *iter; int error; - int found = 0; *qdp = NULL; @@ -454,15 +460,13 @@ static int qd_fish(struct gfs2_sbd *sdp, struct gfs2_quota_data **qdp) spin_lock(&qd_lock); - list_for_each_entry(qd, &sdp->sd_quota_list, qd_list) { - found = qd_check_sync(sdp, qd, &sdp->sd_quota_sync_gen); - if (found) + list_for_each_entry(iter, &sdp->sd_quota_list, qd_list) { + if (qd_check_sync(sdp, iter, &sdp->sd_quota_sync_gen)) { + qd = iter; break; + } } - if (!found) - qd = NULL; - spin_unlock(&qd_lock); if (qd) { @@ -531,34 +535,42 @@ static void qdsb_put(struct gfs2_quota_data *qd) */ int gfs2_qa_get(struct gfs2_inode *ip) { - int error = 0; struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); + struct inode *inode = &ip->i_inode; if (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF) return 0; - down_write(&ip->i_rw_mutex); + spin_lock(&inode->i_lock); if (ip->i_qadata == NULL) { - ip->i_qadata = kmem_cache_zalloc(gfs2_qadata_cachep, GFP_NOFS); - if (!ip->i_qadata) { - error = -ENOMEM; - goto out; - } + struct gfs2_qadata *tmp; + + spin_unlock(&inode->i_lock); + tmp = kmem_cache_zalloc(gfs2_qadata_cachep, GFP_NOFS); + if (!tmp) + return -ENOMEM; + + spin_lock(&inode->i_lock); + if (ip->i_qadata == NULL) + ip->i_qadata = tmp; + else + kmem_cache_free(gfs2_qadata_cachep, tmp); } ip->i_qadata->qa_ref++; -out: - up_write(&ip->i_rw_mutex); - return error; + spin_unlock(&inode->i_lock); + return 0; } void gfs2_qa_put(struct gfs2_inode *ip) { - down_write(&ip->i_rw_mutex); + struct inode *inode = &ip->i_inode; + + spin_lock(&inode->i_lock); if (ip->i_qadata && --ip->i_qadata->qa_ref == 0) { kmem_cache_free(gfs2_qadata_cachep, ip->i_qadata); ip->i_qadata = NULL; } - up_write(&ip->i_rw_mutex); + spin_unlock(&inode->i_lock); } int gfs2_quota_hold(struct gfs2_inode *ip, kuid_t uid, kgid_t gid) diff --git a/fs/gfs2/recovery.c b/fs/gfs2/recovery.c index 016ed1b2ca1d..2bb085a72e8e 100644 --- a/fs/gfs2/recovery.c +++ b/fs/gfs2/recovery.c @@ -55,17 +55,16 @@ int gfs2_replay_read_block(struct gfs2_jdesc *jd, unsigned int blk, int gfs2_revoke_add(struct gfs2_jdesc *jd, u64 blkno, unsigned int where) { struct list_head *head = &jd->jd_revoke_list; - struct gfs2_revoke_replay *rr; - int found = 0; + struct gfs2_revoke_replay *rr = NULL, *iter; - list_for_each_entry(rr, head, rr_list) { - if (rr->rr_blkno == blkno) { - found = 1; + list_for_each_entry(iter, head, rr_list) { + if (iter->rr_blkno == blkno) { + rr = iter; break; } } - if (found) { + if (rr) { rr->rr_where = where; return 0; } @@ -83,18 +82,17 @@ int gfs2_revoke_add(struct gfs2_jdesc *jd, u64 blkno, unsigned int where) int gfs2_revoke_check(struct gfs2_jdesc *jd, u64 blkno, unsigned int where) { - struct gfs2_revoke_replay *rr; + struct gfs2_revoke_replay *rr = NULL, *iter; int wrap, a, b, revoke; - int found = 0; - list_for_each_entry(rr, &jd->jd_revoke_list, rr_list) { - if (rr->rr_blkno == blkno) { - found = 1; + list_for_each_entry(iter, &jd->jd_revoke_list, rr_list) { + if (iter->rr_blkno == blkno) { + rr = iter; break; } } - if (!found) + if (!rr) return 0; wrap = (rr->rr_where < jd->jd_replay_tail); diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index 801ad9f4f2be..8a63870eef5a 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.c @@ -1315,7 +1315,7 @@ int gfs2_rgrp_send_discards(struct gfs2_sbd *sdp, u64 offset, u64 blk; sector_t start = 0; sector_t nr_blks = 0; - int rv; + int rv = -EIO; unsigned int x; u32 trimmed = 0; u8 diff; @@ -1371,7 +1371,7 @@ fail: if (sdp->sd_args.ar_discard) fs_warn(sdp, "error %d on discard request, turning discards off for this filesystem\n", rv); sdp->sd_args.ar_discard = 0; - return -EIO; + return rv; } /** @@ -1386,7 +1386,7 @@ int gfs2_fitrim(struct file *filp, void __user *argp) { struct inode *inode = file_inode(filp); struct gfs2_sbd *sdp = GFS2_SB(inode); - struct request_queue *q = bdev_get_queue(sdp->sd_vfs->s_bdev); + struct block_device *bdev = sdp->sd_vfs->s_bdev; struct buffer_head *bh; struct gfs2_rgrpd *rgd; struct gfs2_rgrpd *rgd_end; @@ -1405,7 +1405,7 @@ int gfs2_fitrim(struct file *filp, void __user *argp) if (!test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) return -EROFS; - if (!blk_queue_discard(q)) + if (!bdev_max_discard_sectors(bdev)) return -EOPNOTSUPP; if (copy_from_user(&r, argp, sizeof(r))) @@ -1418,8 +1418,7 @@ int gfs2_fitrim(struct file *filp, void __user *argp) start = r.start >> bs_shift; end = start + (r.len >> bs_shift); minlen = max_t(u64, r.minlen, sdp->sd_sb.sb_bsize); - minlen = max_t(u64, minlen, - q->limits.discard_granularity) >> bs_shift; + minlen = max_t(u64, minlen, bdev_discard_granularity(bdev)) >> bs_shift; if (end <= start || minlen > sdp->sd_max_rg_data) return -EINVAL; diff --git a/fs/hfs/extent.c b/fs/hfs/extent.c index 263d5028d9d1..3f7e9bef9874 100644 --- a/fs/hfs/extent.c +++ b/fs/hfs/extent.c @@ -491,10 +491,10 @@ void hfs_file_truncate(struct inode *inode) /* XXX: Can use generic_cont_expand? */ size = inode->i_size - 1; - res = pagecache_write_begin(NULL, mapping, size+1, 0, 0, - &page, &fsdata); + res = hfs_write_begin(NULL, mapping, size + 1, 0, &page, + &fsdata); if (!res) { - res = pagecache_write_end(NULL, mapping, size+1, 0, 0, + res = generic_write_end(NULL, mapping, size + 1, 0, 0, page, fsdata); } if (res) diff --git a/fs/hfs/hfs_fs.h b/fs/hfs/hfs_fs.h index b8eb0322a3e5..68d0305880f7 100644 --- a/fs/hfs/hfs_fs.h +++ b/fs/hfs/hfs_fs.h @@ -201,6 +201,8 @@ extern int hfs_get_block(struct inode *, sector_t, struct buffer_head *, int); extern const struct address_space_operations hfs_aops; extern const struct address_space_operations hfs_btree_aops; +int hfs_write_begin(struct file *file, struct address_space *mapping, + loff_t pos, unsigned len, struct page **pagep, void **fsdata); extern struct inode *hfs_new_inode(struct inode *, const struct qstr *, umode_t); extern void hfs_inode_write_fork(struct inode *, struct hfs_extent *, __be32 *, __be32 *); extern int hfs_write_inode(struct inode *, struct writeback_control *); diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index 55f45e9b4930..c4526f16355d 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -34,9 +34,9 @@ static int hfs_writepage(struct page *page, struct writeback_control *wbc) return block_write_full_page(page, hfs_get_block, wbc); } -static int hfs_readpage(struct file *file, struct page *page) +static int hfs_read_folio(struct file *file, struct folio *folio) { - return block_read_full_page(page, hfs_get_block); + return block_read_full_folio(folio, hfs_get_block); } static void hfs_write_failed(struct address_space *mapping, loff_t to) @@ -49,14 +49,13 @@ static void hfs_write_failed(struct address_space *mapping, loff_t to) } } -static int hfs_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, - struct page **pagep, void **fsdata) +int hfs_write_begin(struct file *file, struct address_space *mapping, + loff_t pos, unsigned len, struct page **pagep, void **fsdata) { int ret; *pagep = NULL; - ret = cont_write_begin(file, mapping, pos, len, flags, pagep, fsdata, + ret = cont_write_begin(file, mapping, pos, len, pagep, fsdata, hfs_get_block, &HFS_I(mapping->host)->phys_size); if (unlikely(ret)) @@ -70,14 +69,15 @@ static sector_t hfs_bmap(struct address_space *mapping, sector_t block) return generic_block_bmap(mapping, block, hfs_get_block); } -static int hfs_releasepage(struct page *page, gfp_t mask) +static bool hfs_release_folio(struct folio *folio, gfp_t mask) { - struct inode *inode = page->mapping->host; + struct inode *inode = folio->mapping->host; struct super_block *sb = inode->i_sb; struct hfs_btree *tree; struct hfs_bnode *node; u32 nidx; - int i, res = 1; + int i; + bool res = true; switch (inode->i_ino) { case HFS_EXT_CNID: @@ -88,27 +88,27 @@ static int hfs_releasepage(struct page *page, gfp_t mask) break; default: BUG(); - return 0; + return false; } if (!tree) - return 0; + return false; if (tree->node_size >= PAGE_SIZE) { - nidx = page->index >> (tree->node_size_shift - PAGE_SHIFT); + nidx = folio->index >> (tree->node_size_shift - PAGE_SHIFT); spin_lock(&tree->hash_lock); node = hfs_bnode_findhash(tree, nidx); if (!node) ; else if (atomic_read(&node->refcnt)) - res = 0; + res = false; if (res && node) { hfs_bnode_unhash(node); hfs_bnode_free(node); } spin_unlock(&tree->hash_lock); } else { - nidx = page->index << (PAGE_SHIFT - tree->node_size_shift); + nidx = folio->index << (PAGE_SHIFT - tree->node_size_shift); i = 1 << (PAGE_SHIFT - tree->node_size_shift); spin_lock(&tree->hash_lock); do { @@ -116,7 +116,7 @@ static int hfs_releasepage(struct page *page, gfp_t mask) if (!node) continue; if (atomic_read(&node->refcnt)) { - res = 0; + res = false; break; } hfs_bnode_unhash(node); @@ -124,7 +124,7 @@ static int hfs_releasepage(struct page *page, gfp_t mask) } while (--i && nidx < tree->node_count); spin_unlock(&tree->hash_lock); } - return res ? try_to_free_buffers(page) : 0; + return res ? try_to_free_buffers(folio) : false; } static ssize_t hfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) @@ -161,18 +161,18 @@ static int hfs_writepages(struct address_space *mapping, const struct address_space_operations hfs_btree_aops = { .dirty_folio = block_dirty_folio, .invalidate_folio = block_invalidate_folio, - .readpage = hfs_readpage, + .read_folio = hfs_read_folio, .writepage = hfs_writepage, .write_begin = hfs_write_begin, .write_end = generic_write_end, .bmap = hfs_bmap, - .releasepage = hfs_releasepage, + .release_folio = hfs_release_folio, }; const struct address_space_operations hfs_aops = { .dirty_folio = block_dirty_folio, .invalidate_folio = block_invalidate_folio, - .readpage = hfs_readpage, + .read_folio = hfs_read_folio, .writepage = hfs_writepage, .write_begin = hfs_write_begin, .write_end = generic_write_end, diff --git a/fs/hfsplus/extents.c b/fs/hfsplus/extents.c index 7054a542689f..721f779b4ec3 100644 --- a/fs/hfsplus/extents.c +++ b/fs/hfsplus/extents.c @@ -557,12 +557,12 @@ void hfsplus_file_truncate(struct inode *inode) void *fsdata; loff_t size = inode->i_size; - res = pagecache_write_begin(NULL, mapping, size, 0, 0, - &page, &fsdata); + res = hfsplus_write_begin(NULL, mapping, size, 0, + &page, &fsdata); if (res) return; - res = pagecache_write_end(NULL, mapping, size, - 0, 0, page, fsdata); + res = generic_write_end(NULL, mapping, size, 0, 0, + page, fsdata); if (res < 0) return; mark_inode_dirty(inode); diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h index 1798949f269b..396e73aa0961 100644 --- a/fs/hfsplus/hfsplus_fs.h +++ b/fs/hfsplus/hfsplus_fs.h @@ -468,6 +468,8 @@ extern const struct address_space_operations hfsplus_aops; extern const struct address_space_operations hfsplus_btree_aops; extern const struct dentry_operations hfsplus_dentry_operations; +int hfsplus_write_begin(struct file *file, struct address_space *mapping, + loff_t pos, unsigned len, struct page **pagep, void **fsdata); struct inode *hfsplus_new_inode(struct super_block *sb, struct inode *dir, umode_t mode); void hfsplus_delete_inode(struct inode *inode); diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index 446a816aa8e1..aeab83ed1c9c 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -23,9 +23,9 @@ #include "hfsplus_raw.h" #include "xattr.h" -static int hfsplus_readpage(struct file *file, struct page *page) +static int hfsplus_read_folio(struct file *file, struct folio *folio) { - return block_read_full_page(page, hfsplus_get_block); + return block_read_full_folio(folio, hfsplus_get_block); } static int hfsplus_writepage(struct page *page, struct writeback_control *wbc) @@ -43,14 +43,13 @@ static void hfsplus_write_failed(struct address_space *mapping, loff_t to) } } -static int hfsplus_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, - struct page **pagep, void **fsdata) +int hfsplus_write_begin(struct file *file, struct address_space *mapping, + loff_t pos, unsigned len, struct page **pagep, void **fsdata) { int ret; *pagep = NULL; - ret = cont_write_begin(file, mapping, pos, len, flags, pagep, fsdata, + ret = cont_write_begin(file, mapping, pos, len, pagep, fsdata, hfsplus_get_block, &HFSPLUS_I(mapping->host)->phys_size); if (unlikely(ret)) @@ -64,14 +63,15 @@ static sector_t hfsplus_bmap(struct address_space *mapping, sector_t block) return generic_block_bmap(mapping, block, hfsplus_get_block); } -static int hfsplus_releasepage(struct page *page, gfp_t mask) +static bool hfsplus_release_folio(struct folio *folio, gfp_t mask) { - struct inode *inode = page->mapping->host; + struct inode *inode = folio->mapping->host; struct super_block *sb = inode->i_sb; struct hfs_btree *tree; struct hfs_bnode *node; u32 nidx; - int i, res = 1; + int i; + bool res = true; switch (inode->i_ino) { case HFSPLUS_EXT_CNID: @@ -85,26 +85,26 @@ static int hfsplus_releasepage(struct page *page, gfp_t mask) break; default: BUG(); - return 0; + return false; } if (!tree) - return 0; + return false; if (tree->node_size >= PAGE_SIZE) { - nidx = page->index >> + nidx = folio->index >> (tree->node_size_shift - PAGE_SHIFT); spin_lock(&tree->hash_lock); node = hfs_bnode_findhash(tree, nidx); if (!node) ; else if (atomic_read(&node->refcnt)) - res = 0; + res = false; if (res && node) { hfs_bnode_unhash(node); hfs_bnode_free(node); } spin_unlock(&tree->hash_lock); } else { - nidx = page->index << + nidx = folio->index << (PAGE_SHIFT - tree->node_size_shift); i = 1 << (PAGE_SHIFT - tree->node_size_shift); spin_lock(&tree->hash_lock); @@ -113,7 +113,7 @@ static int hfsplus_releasepage(struct page *page, gfp_t mask) if (!node) continue; if (atomic_read(&node->refcnt)) { - res = 0; + res = false; break; } hfs_bnode_unhash(node); @@ -121,7 +121,7 @@ static int hfsplus_releasepage(struct page *page, gfp_t mask) } while (--i && nidx < tree->node_count); spin_unlock(&tree->hash_lock); } - return res ? try_to_free_buffers(page) : 0; + return res ? try_to_free_buffers(folio) : false; } static ssize_t hfsplus_direct_IO(struct kiocb *iocb, struct iov_iter *iter) @@ -158,18 +158,18 @@ static int hfsplus_writepages(struct address_space *mapping, const struct address_space_operations hfsplus_btree_aops = { .dirty_folio = block_dirty_folio, .invalidate_folio = block_invalidate_folio, - .readpage = hfsplus_readpage, + .read_folio = hfsplus_read_folio, .writepage = hfsplus_writepage, .write_begin = hfsplus_write_begin, .write_end = generic_write_end, .bmap = hfsplus_bmap, - .releasepage = hfsplus_releasepage, + .release_folio = hfsplus_release_folio, }; const struct address_space_operations hfsplus_aops = { .dirty_folio = block_dirty_folio, .invalidate_folio = block_invalidate_folio, - .readpage = hfsplus_readpage, + .read_folio = hfsplus_read_folio, .writepage = hfsplus_writepage, .write_begin = hfsplus_write_begin, .write_end = generic_write_end, diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index 14f9ac973a2e..cc1bc6f93a01 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -434,8 +434,9 @@ static int hostfs_writepage(struct page *page, struct writeback_control *wbc) return err; } -static int hostfs_readpage(struct file *file, struct page *page) +static int hostfs_read_folio(struct file *file, struct folio *folio) { + struct page *page = &folio->page; char *buffer; loff_t start = page_offset(page); int bytes_read, ret = 0; @@ -463,12 +464,12 @@ static int hostfs_readpage(struct file *file, struct page *page) } static int hostfs_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, + loff_t pos, unsigned len, struct page **pagep, void **fsdata) { pgoff_t index = pos >> PAGE_SHIFT; - *pagep = grab_cache_page_write_begin(mapping, index, flags); + *pagep = grab_cache_page_write_begin(mapping, index); if (!*pagep) return -ENOMEM; return 0; @@ -504,7 +505,7 @@ static int hostfs_write_end(struct file *file, struct address_space *mapping, static const struct address_space_operations hostfs_aops = { .writepage = hostfs_writepage, - .readpage = hostfs_readpage, + .read_folio = hostfs_read_folio, .dirty_folio = filemap_dirty_folio, .write_begin = hostfs_write_begin, .write_end = hostfs_write_end, diff --git a/fs/hpfs/file.c b/fs/hpfs/file.c index 99493a23c5d0..f7547a62c81f 100644 --- a/fs/hpfs/file.c +++ b/fs/hpfs/file.c @@ -158,9 +158,9 @@ static const struct iomap_ops hpfs_iomap_ops = { .iomap_begin = hpfs_iomap_begin, }; -static int hpfs_readpage(struct file *file, struct page *page) +static int hpfs_read_folio(struct file *file, struct folio *folio) { - return mpage_readpage(page, hpfs_get_block); + return mpage_read_folio(folio, hpfs_get_block); } static int hpfs_writepage(struct page *page, struct writeback_control *wbc) @@ -194,13 +194,13 @@ static void hpfs_write_failed(struct address_space *mapping, loff_t to) } static int hpfs_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, + loff_t pos, unsigned len, struct page **pagep, void **fsdata) { int ret; *pagep = NULL; - ret = cont_write_begin(file, mapping, pos, len, flags, pagep, fsdata, + ret = cont_write_begin(file, mapping, pos, len, pagep, fsdata, hpfs_get_block, &hpfs_i(mapping->host)->mmu_private); if (unlikely(ret)) @@ -247,7 +247,7 @@ static int hpfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, const struct address_space_operations hpfs_aops = { .dirty_folio = block_dirty_folio, .invalidate_folio = block_invalidate_folio, - .readpage = hpfs_readpage, + .read_folio = hpfs_read_folio, .writepage = hpfs_writepage, .readahead = hpfs_readahead, .writepages = hpfs_writepages, diff --git a/fs/hpfs/namei.c b/fs/hpfs/namei.c index d73f8a67168e..15fc63276caa 100644 --- a/fs/hpfs/namei.c +++ b/fs/hpfs/namei.c @@ -479,8 +479,9 @@ out: return err; } -static int hpfs_symlink_readpage(struct file *file, struct page *page) +static int hpfs_symlink_read_folio(struct file *file, struct folio *folio) { + struct page *page = &folio->page; char *link = page_address(page); struct inode *i = page->mapping->host; struct fnode *fnode; @@ -508,7 +509,7 @@ fail: } const struct address_space_operations hpfs_symlink_aops = { - .readpage = hpfs_symlink_readpage + .read_folio = hpfs_symlink_read_folio }; static int hpfs_rename(struct user_namespace *mnt_userns, struct inode *old_dir, diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 99c7477cee5c..2de9ca5d260d 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -206,7 +206,7 @@ hugetlb_get_unmapped_area_bottomup(struct file *file, unsigned long addr, info.flags = 0; info.length = len; info.low_limit = current->mm->mmap_base; - info.high_limit = TASK_SIZE; + info.high_limit = arch_get_mmap_end(addr); info.align_mask = PAGE_MASK & ~huge_page_mask(h); info.align_offset = 0; return vm_unmapped_area(&info); @@ -222,7 +222,7 @@ hugetlb_get_unmapped_area_topdown(struct file *file, unsigned long addr, info.flags = VM_UNMAPPED_AREA_TOPDOWN; info.length = len; info.low_limit = max(PAGE_SIZE, mmap_min_addr); - info.high_limit = current->mm->mmap_base; + info.high_limit = arch_get_mmap_base(addr, current->mm->mmap_base); info.align_mask = PAGE_MASK & ~huge_page_mask(h); info.align_offset = 0; addr = vm_unmapped_area(&info); @@ -237,7 +237,7 @@ hugetlb_get_unmapped_area_topdown(struct file *file, unsigned long addr, VM_BUG_ON(addr != -ENOMEM); info.flags = 0; info.low_limit = current->mm->mmap_base; - info.high_limit = TASK_SIZE; + info.high_limit = arch_get_mmap_end(addr); addr = vm_unmapped_area(&info); } @@ -251,6 +251,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr, struct mm_struct *mm = current->mm; struct vm_area_struct *vma; struct hstate *h = hstate_file(file); + const unsigned long mmap_end = arch_get_mmap_end(addr); if (len & ~huge_page_mask(h)) return -EINVAL; @@ -266,7 +267,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr, if (addr) { addr = ALIGN(addr, huge_page_size(h)); vma = find_vma(mm, addr); - if (TASK_SIZE - len >= addr && + if (mmap_end - len >= addr && (!vma || addr + len <= vm_start_gap(vma))) return addr; } @@ -382,7 +383,7 @@ static ssize_t hugetlbfs_read_iter(struct kiocb *iocb, struct iov_iter *to) static int hugetlbfs_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, + loff_t pos, unsigned len, struct page **pagep, void **fsdata) { return -EINVAL; diff --git a/fs/internal.h b/fs/internal.h index 08503dc68d2b..9a6c233ee7f1 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -191,3 +191,32 @@ long splice_file_to_pipe(struct file *in, struct pipe_inode_info *opipe, loff_t *offset, size_t len, unsigned int flags); + +/* + * fs/xattr.c: + */ +struct xattr_name { + char name[XATTR_NAME_MAX + 1]; +}; + +struct xattr_ctx { + /* Value of attribute */ + union { + const void __user *cvalue; + void __user *value; + }; + void *kvalue; + size_t size; + /* Attribute name */ + struct xattr_name *kname; + unsigned int flags; +}; + + +ssize_t do_getxattr(struct user_namespace *mnt_userns, + struct dentry *d, + struct xattr_ctx *ctx); + +int setxattr_copy(const char __user *name, struct xattr_ctx *ctx); +int do_setxattr(struct user_namespace *mnt_userns, struct dentry *dentry, + struct xattr_ctx *ctx); diff --git a/fs/io-wq.c b/fs/io-wq.c index 32aeb2c581c5..824623bcf1a5 100644 --- a/fs/io-wq.c +++ b/fs/io-wq.c @@ -871,7 +871,7 @@ static bool io_wq_for_each_worker(struct io_wqe *wqe, static bool io_wq_worker_wake(struct io_worker *worker, void *data) { - set_notify_signal(worker->task); + __set_notify_signal(worker->task); wake_up_process(worker->task); return false; } @@ -991,7 +991,7 @@ static bool __io_wq_worker_cancel(struct io_worker *worker, { if (work && match->fn(work, match->data)) { work->flags |= IO_WQ_WORK_CANCEL; - set_notify_signal(worker->task); + __set_notify_signal(worker->task); return true; } diff --git a/fs/io-wq.h b/fs/io-wq.h index dbecd27656c7..ba6eee76d028 100644 --- a/fs/io-wq.h +++ b/fs/io-wq.h @@ -155,6 +155,7 @@ struct io_wq_work_node *wq_stack_extract(struct io_wq_work_node *stack) struct io_wq_work { struct io_wq_work_node list; unsigned flags; + int cancel_seq; }; static inline struct io_wq_work *wq_next_work(struct io_wq_work *work) diff --git a/fs/io_uring.c b/fs/io_uring.c index a8413f006417..9f1c682d7caf 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -63,7 +63,6 @@ #include <net/sock.h> #include <net/af_unix.h> #include <net/scm.h> -#include <net/busy_poll.h> #include <linux/anon_inodes.h> #include <linux/sched/mm.h> #include <linux/uaccess.h> @@ -81,6 +80,7 @@ #include <linux/io_uring.h> #include <linux/audit.h> #include <linux/security.h> +#include <linux/xattr.h> #define CREATE_TRACE_POINTS #include <trace/events/io_uring.h> @@ -95,7 +95,7 @@ #define IORING_SQPOLL_CAP_ENTRIES_VALUE 8 /* only define max */ -#define IORING_MAX_FIXED_FILES (1U << 15) +#define IORING_MAX_FIXED_FILES (1U << 20) #define IORING_MAX_RESTRICTIONS (IORING_RESTRICTION_LAST + \ IORING_REGISTER_LAST + IORING_OP_LAST) @@ -112,8 +112,12 @@ IOSQE_IO_DRAIN | IOSQE_CQE_SKIP_SUCCESS) #define IO_REQ_CLEAN_FLAGS (REQ_F_BUFFER_SELECTED | REQ_F_NEED_CLEANUP | \ - REQ_F_POLLED | REQ_F_INFLIGHT | REQ_F_CREDS | \ - REQ_F_ASYNC_DATA) + REQ_F_POLLED | REQ_F_CREDS | REQ_F_ASYNC_DATA) + +#define IO_REQ_CLEAN_SLOW_FLAGS (REQ_F_REFCOUNT | REQ_F_LINK | REQ_F_HARDLINK |\ + IO_REQ_CLEAN_FLAGS) + +#define IO_APOLL_MULTI_POLLED (REQ_F_APOLL_MULTISHOT | REQ_F_POLLED) #define IO_TCTX_REFS_CACHE_NR (1U << 10) @@ -168,7 +172,7 @@ struct io_rings { * The application needs a full memory barrier before checking * for IORING_SQ_NEED_WAKEUP after updating the sq tail. */ - u32 sq_flags; + atomic_t sq_flags; /* * Runtime CQ flags * @@ -200,13 +204,6 @@ struct io_rings { struct io_uring_cqe cqes[] ____cacheline_aligned_in_smp; }; -enum io_uring_cmd_flags { - IO_URING_F_COMPLETE_DEFER = 1, - IO_URING_F_UNLOCKED = 2, - /* int's last bit, sign checks are usually faster than a bit test */ - IO_URING_F_NONBLOCK = INT_MIN, -}; - struct io_mapped_ubuf { u64 ubuf; u64 ubuf_end; @@ -218,10 +215,27 @@ struct io_mapped_ubuf { struct io_ring_ctx; struct io_overflow_cqe { - struct io_uring_cqe cqe; struct list_head list; + struct io_uring_cqe cqe; }; +/* + * FFS_SCM is only available on 64-bit archs, for 32-bit we just define it as 0 + * and define IO_URING_SCM_ALL. For this case, we use SCM for all files as we + * can't safely always dereference the file when the task has exited and ring + * cleanup is done. If a file is tracked and part of SCM, then unix gc on + * process exit may reap it before __io_sqe_files_unregister() is run. + */ +#define FFS_NOWAIT 0x1UL +#define FFS_ISREG 0x2UL +#if defined(CONFIG_64BIT) +#define FFS_SCM 0x4UL +#else +#define IO_URING_SCM_ALL +#define FFS_SCM 0x0UL +#endif +#define FFS_MASK ~(FFS_NOWAIT|FFS_ISREG|FFS_SCM) + struct io_fixed_file { /* file * with additional FFS_* flags */ unsigned long file_ptr; @@ -239,6 +253,8 @@ struct io_rsrc_put { struct io_file_table { struct io_fixed_file *files; + unsigned long *bitmap; + unsigned int alloc_hint; }; struct io_rsrc_node { @@ -263,10 +279,26 @@ struct io_rsrc_data { bool quiesce; }; +#define IO_BUFFER_LIST_BUF_PER_PAGE (PAGE_SIZE / sizeof(struct io_uring_buf)) struct io_buffer_list { - struct list_head list; - struct list_head buf_list; + /* + * If ->buf_nr_pages is set, then buf_pages/buf_ring are used. If not, + * then these are classic provided buffers and ->buf_list is used. + */ + union { + struct list_head buf_list; + struct { + struct page **buf_pages; + struct io_uring_buf_ring *buf_ring; + }; + }; __u16 bgid; + + /* below is for ring provided buffers */ + __u16 buf_nr_pages; + __u16 nr_entries; + __u32 head; + __u32 mask; }; struct io_buffer { @@ -339,7 +371,7 @@ struct io_ev_fd { struct rcu_head rcu; }; -#define IO_BUFFERS_HASH_BITS 5 +#define BGID_ARRAY 64 struct io_ring_ctx { /* const or read-mostly hot data */ @@ -348,6 +380,7 @@ struct io_ring_ctx { struct io_rings *rings; unsigned int flags; + enum task_work_notify_mode notify_method; unsigned int compat: 1; unsigned int drain_next: 1; unsigned int restricted: 1; @@ -355,6 +388,7 @@ struct io_ring_ctx { unsigned int drain_active: 1; unsigned int drain_disabled: 1; unsigned int has_evfd: 1; + unsigned int syscall_iopoll: 1; } ____cacheline_aligned_in_smp; /* submission data */ @@ -384,17 +418,21 @@ struct io_ring_ctx { */ struct io_rsrc_node *rsrc_node; int rsrc_cached_refs; + atomic_t cancel_seq; struct io_file_table file_table; unsigned nr_user_files; unsigned nr_user_bufs; struct io_mapped_ubuf **user_bufs; struct io_submit_state submit_state; + + struct io_buffer_list *io_bl; + struct xarray io_bl_xa; + struct list_head io_buffers_cache; + struct list_head timeout_list; struct list_head ltimeout_list; struct list_head cq_overflow_list; - struct list_head *io_buffers; - struct list_head io_buffers_cache; struct list_head apoll_cache; struct xarray personalities; u32 pers_next; @@ -411,14 +449,16 @@ struct io_ring_ctx { struct wait_queue_head sqo_sq_wait; struct list_head sqd_list; - unsigned long check_cq_overflow; -#ifdef CONFIG_NET_RX_BUSY_POLL - /* used to track busy poll napi_id */ - struct list_head napi_list; - spinlock_t napi_lock; /* napi_list lock */ -#endif + unsigned long check_cq; struct { + /* + * We cache a range of free CQEs we can use, once exhausted it + * should go through a slower range setup, see __io_get_cqe() + */ + struct io_uring_cqe *cqe_cached; + struct io_uring_cqe *cqe_sentinel; + unsigned cached_cq_tail; unsigned cq_entries; struct io_ev_fd __rcu *io_ev_fd; @@ -500,12 +540,11 @@ struct io_uring_task { const struct io_ring_ctx *last; struct io_wq *io_wq; struct percpu_counter inflight; - atomic_t inflight_tracked; atomic_t in_idle; spinlock_t task_lock; struct io_wq_work_list task_list; - struct io_wq_work_list prior_task_list; + struct io_wq_work_list prio_task_list; struct callback_head task_work; struct file **registered_rings; bool task_running; @@ -554,6 +593,16 @@ struct io_accept { unsigned long nofile; }; +struct io_socket { + struct file *file; + int domain; + int type; + int protocol; + int flags; + u32 file_slot; + unsigned long nofile; +}; + struct io_sync { struct file *file; loff_t len; @@ -565,6 +614,8 @@ struct io_sync { struct io_cancel { struct file *file; u64 addr; + u32 flags; + s32 fd; }; struct io_timeout { @@ -592,7 +643,8 @@ struct io_rw { /* NOTE: kiocb has the file as the first member, so don't do it here */ struct kiocb kiocb; u64 addr; - u64 len; + u32 len; + rwf_t flags; }; struct io_connect { @@ -609,9 +661,9 @@ struct io_sr_msg { void __user *buf; }; int msg_flags; - int bgid; size_t len; size_t done_io; + unsigned int flags; }; struct io_open { @@ -654,10 +706,10 @@ struct io_epoll { struct io_splice { struct file *file_out; - struct file *file_in; loff_t off_out; loff_t off_in; u64 len; + int splice_fd_in; unsigned int flags; }; @@ -729,6 +781,12 @@ struct io_msg { u32 len; }; +struct io_nop { + struct file *file; + u64 extra1; + u64 extra2; +}; + struct io_async_connect { struct sockaddr_storage address; }; @@ -755,6 +813,12 @@ struct io_async_rw { struct wait_page_queue wpq; }; +struct io_xattr { + struct file *file; + struct xattr_ctx ctx; + struct filename *filename; +}; + enum { REQ_F_FIXED_FILE_BIT = IOSQE_FIXED_FILE_BIT, REQ_F_IO_DRAIN_BIT = IOSQE_IO_DRAIN_BIT, @@ -773,6 +837,7 @@ enum { REQ_F_NEED_CLEANUP_BIT, REQ_F_POLLED_BIT, REQ_F_BUFFER_SELECTED_BIT, + REQ_F_BUFFER_RING_BIT, REQ_F_COMPLETE_INLINE_BIT, REQ_F_REISSUE_BIT, REQ_F_CREDS_BIT, @@ -783,6 +848,7 @@ enum { REQ_F_SINGLE_POLL_BIT, REQ_F_DOUBLE_POLL_BIT, REQ_F_PARTIAL_IO_BIT, + REQ_F_APOLL_MULTISHOT_BIT, /* keep async read/write and isreg together and in order */ REQ_F_SUPPORT_NOWAIT_BIT, REQ_F_ISREG_BIT, @@ -823,6 +889,8 @@ enum { REQ_F_POLLED = BIT(REQ_F_POLLED_BIT), /* buffer already selected */ REQ_F_BUFFER_SELECTED = BIT(REQ_F_BUFFER_SELECTED_BIT), + /* buffer selected from ring, needs commit */ + REQ_F_BUFFER_RING = BIT(REQ_F_BUFFER_RING_BIT), /* completion is deferred through io_comp_state */ REQ_F_COMPLETE_INLINE = BIT(REQ_F_COMPLETE_INLINE_BIT), /* caller should reissue async */ @@ -847,6 +915,8 @@ enum { REQ_F_DOUBLE_POLL = BIT(REQ_F_DOUBLE_POLL_BIT), /* request has already done partial IO */ REQ_F_PARTIAL_IO = BIT(REQ_F_PARTIAL_IO_BIT), + /* fast poll multishot mode */ + REQ_F_APOLL_MULTISHOT = BIT(REQ_F_APOLL_MULTISHOT_BIT), }; struct async_poll { @@ -869,6 +939,21 @@ enum { IORING_RSRC_BUFFER = 1, }; +struct io_cqe { + __u64 user_data; + __s32 res; + /* fd initially, then cflags for completion */ + union { + __u32 flags; + int fd; + }; +}; + +enum { + IO_CHECK_CQ_OVERFLOW_BIT, + IO_CHECK_CQ_DROPPED_BIT, +}; + /* * NOTE! Each of the iocb union members has the file pointer * as the first entry in their struct definition. So you can @@ -904,38 +989,65 @@ struct io_kiocb { struct io_symlink symlink; struct io_hardlink hardlink; struct io_msg msg; + struct io_xattr xattr; + struct io_socket sock; + struct io_nop nop; + struct io_uring_cmd uring_cmd; }; u8 opcode; /* polled IO has completed */ u8 iopoll_completed; + /* + * Can be either a fixed buffer index, or used with provided buffers. + * For the latter, before issue it points to the buffer group ID, + * and after selection it points to the buffer ID itself. + */ u16 buf_index; unsigned int flags; - u64 user_data; - u32 result; - u32 cflags; + struct io_cqe cqe; struct io_ring_ctx *ctx; struct task_struct *task; - struct percpu_ref *fixed_rsrc_refs; - /* store used ubuf, so we can prevent reloading */ - struct io_mapped_ubuf *imu; + struct io_rsrc_node *rsrc_node; + + union { + /* store used ubuf, so we can prevent reloading */ + struct io_mapped_ubuf *imu; + + /* stores selected buf, valid IFF REQ_F_BUFFER_SELECTED is set */ + struct io_buffer *kbuf; - /* used by request caches, completion batching and iopoll */ - struct io_wq_work_node comp_list; + /* + * stores buffer ID for ring provided buffers, valid IFF + * REQ_F_BUFFER_RING is set. + */ + struct io_buffer_list *buf_list; + }; + + union { + /* used by request caches, completion batching and iopoll */ + struct io_wq_work_node comp_list; + /* cache ->apoll->events */ + __poll_t apoll_events; + }; atomic_t refs; atomic_t poll_refs; struct io_task_work io_task_work; /* for polled requests, i.e. IORING_OP_POLL_ADD and async armed poll */ - struct hlist_node hash_node; + union { + struct hlist_node hash_node; + struct { + u64 extra1; + u64 extra2; + }; + }; /* internal polling, see IORING_FEAT_FAST_POLL */ struct async_poll *apoll; /* opcode allocated if it needs to store data for async defer */ void *async_data; - /* stores selected buf, valid IFF REQ_F_BUFFER_SELECTED is set */ - struct io_buffer *kbuf; /* linked requests, IFF REQ_F_HARDLINK or REQ_F_LINK are set */ struct io_kiocb *link; /* custom credentials, valid IFF REQ_F_CREDS is set */ @@ -955,6 +1067,24 @@ struct io_defer_entry { u32 seq; }; +struct io_cancel_data { + struct io_ring_ctx *ctx; + union { + u64 data; + struct file *file; + }; + u32 flags; + int seq; +}; + +/* + * The URING_CMD payload starts at 'cmd' in the first sqe, and continues into + * the following sqe if SQE128 is used. + */ +#define uring_cmd_pdu_size(is_sqe128) \ + ((1 + !!(is_sqe128)) * sizeof(struct io_uring_sqe) - \ + offsetof(struct io_uring_sqe, cmd)) + struct io_op_def { /* needs req->file assigned */ unsigned needs_file : 1; @@ -976,12 +1106,20 @@ struct io_op_def { unsigned not_supported : 1; /* skip auditing */ unsigned audit_skip : 1; + /* supports ioprio */ + unsigned ioprio : 1; + /* supports iopoll */ + unsigned iopoll : 1; /* size of async data needed, if any */ unsigned short async_size; }; static const struct io_op_def io_op_defs[] = { - [IORING_OP_NOP] = {}, + [IORING_OP_NOP] = { + .audit_skip = 1, + .iopoll = 1, + .buffer_select = 1, + }, [IORING_OP_READV] = { .needs_file = 1, .unbound_nonreg_file = 1, @@ -990,6 +1128,8 @@ static const struct io_op_def io_op_defs[] = { .needs_async_setup = 1, .plug = 1, .audit_skip = 1, + .ioprio = 1, + .iopoll = 1, .async_size = sizeof(struct io_async_rw), }, [IORING_OP_WRITEV] = { @@ -1000,6 +1140,8 @@ static const struct io_op_def io_op_defs[] = { .needs_async_setup = 1, .plug = 1, .audit_skip = 1, + .ioprio = 1, + .iopoll = 1, .async_size = sizeof(struct io_async_rw), }, [IORING_OP_FSYNC] = { @@ -1012,6 +1154,8 @@ static const struct io_op_def io_op_defs[] = { .pollin = 1, .plug = 1, .audit_skip = 1, + .ioprio = 1, + .iopoll = 1, .async_size = sizeof(struct io_async_rw), }, [IORING_OP_WRITE_FIXED] = { @@ -1021,6 +1165,8 @@ static const struct io_op_def io_op_defs[] = { .pollout = 1, .plug = 1, .audit_skip = 1, + .ioprio = 1, + .iopoll = 1, .async_size = sizeof(struct io_async_rw), }, [IORING_OP_POLL_ADD] = { @@ -1063,6 +1209,7 @@ static const struct io_op_def io_op_defs[] = { .unbound_nonreg_file = 1, .pollin = 1, .poll_exclusive = 1, + .ioprio = 1, /* used for flags */ }, [IORING_OP_ASYNC_CANCEL] = { .audit_skip = 1, @@ -1085,6 +1232,7 @@ static const struct io_op_def io_op_defs[] = { [IORING_OP_CLOSE] = {}, [IORING_OP_FILES_UPDATE] = { .audit_skip = 1, + .iopoll = 1, }, [IORING_OP_STATX] = { .audit_skip = 1, @@ -1096,6 +1244,8 @@ static const struct io_op_def io_op_defs[] = { .buffer_select = 1, .plug = 1, .audit_skip = 1, + .ioprio = 1, + .iopoll = 1, .async_size = sizeof(struct io_async_rw), }, [IORING_OP_WRITE] = { @@ -1105,6 +1255,8 @@ static const struct io_op_def io_op_defs[] = { .pollout = 1, .plug = 1, .audit_skip = 1, + .ioprio = 1, + .iopoll = 1, .async_size = sizeof(struct io_async_rw), }, [IORING_OP_FADVISE] = { @@ -1139,9 +1291,11 @@ static const struct io_op_def io_op_defs[] = { }, [IORING_OP_PROVIDE_BUFFERS] = { .audit_skip = 1, + .iopoll = 1, }, [IORING_OP_REMOVE_BUFFERS] = { .audit_skip = 1, + .iopoll = 1, }, [IORING_OP_TEE] = { .needs_file = 1, @@ -1159,11 +1313,30 @@ static const struct io_op_def io_op_defs[] = { [IORING_OP_LINKAT] = {}, [IORING_OP_MSG_RING] = { .needs_file = 1, + .iopoll = 1, + }, + [IORING_OP_FSETXATTR] = { + .needs_file = 1 + }, + [IORING_OP_SETXATTR] = {}, + [IORING_OP_FGETXATTR] = { + .needs_file = 1 + }, + [IORING_OP_GETXATTR] = {}, + [IORING_OP_SOCKET] = { + .audit_skip = 1, + }, + [IORING_OP_URING_CMD] = { + .needs_file = 1, + .plug = 1, + .needs_async_setup = 1, + .async_size = uring_cmd_pdu_size(1), }, }; /* requests with any of those set should undergo io_disarm_next() */ #define IO_DISARM_MASK (REQ_F_ARM_LTIMEOUT | REQ_F_LINK_TIMEOUT | REQ_F_FAIL) +#define IO_REQ_LINK_FLAGS (REQ_F_LINK | REQ_F_HARDLINK) static bool io_disarm_next(struct io_kiocb *req); static void io_uring_del_tctx_node(unsigned long index); @@ -1172,19 +1345,19 @@ static void io_uring_try_cancel_requests(struct io_ring_ctx *ctx, bool cancel_all); static void io_uring_cancel_generic(bool cancel_all, struct io_sq_data *sqd); -static void io_fill_cqe_req(struct io_kiocb *req, s32 res, u32 cflags); - -static void io_put_req(struct io_kiocb *req); -static void io_put_req_deferred(struct io_kiocb *req); +static void __io_req_complete_post(struct io_kiocb *req, s32 res, u32 cflags); static void io_dismantle_req(struct io_kiocb *req); static void io_queue_linked_timeout(struct io_kiocb *req); static int __io_register_rsrc_update(struct io_ring_ctx *ctx, unsigned type, struct io_uring_rsrc_update2 *up, unsigned nr_args); static void io_clean_op(struct io_kiocb *req); -static struct file *io_file_get(struct io_ring_ctx *ctx, - struct io_kiocb *req, int fd, bool fixed); -static void __io_queue_sqe(struct io_kiocb *req); +static inline struct file *io_file_get_fixed(struct io_kiocb *req, int fd, + unsigned issue_flags); +static struct file *io_file_get_normal(struct io_kiocb *req, int fd); +static void io_drop_inflight_file(struct io_kiocb *req); +static bool io_assign_file(struct io_kiocb *req, unsigned int issue_flags); +static void io_queue_sqe(struct io_kiocb *req); static void io_rsrc_put_work(struct work_struct *work); static void io_req_task_queue(struct io_kiocb *req); @@ -1197,11 +1370,115 @@ static int io_close_fixed(struct io_kiocb *req, unsigned int issue_flags); static enum hrtimer_restart io_link_timeout_fn(struct hrtimer *timer); static void io_eventfd_signal(struct io_ring_ctx *ctx); +static void io_req_tw_post_queue(struct io_kiocb *req, s32 res, u32 cflags); static struct kmem_cache *req_cachep; static const struct file_operations io_uring_fops; +const char *io_uring_get_opcode(u8 opcode) +{ + switch ((enum io_uring_op)opcode) { + case IORING_OP_NOP: + return "NOP"; + case IORING_OP_READV: + return "READV"; + case IORING_OP_WRITEV: + return "WRITEV"; + case IORING_OP_FSYNC: + return "FSYNC"; + case IORING_OP_READ_FIXED: + return "READ_FIXED"; + case IORING_OP_WRITE_FIXED: + return "WRITE_FIXED"; + case IORING_OP_POLL_ADD: + return "POLL_ADD"; + case IORING_OP_POLL_REMOVE: + return "POLL_REMOVE"; + case IORING_OP_SYNC_FILE_RANGE: + return "SYNC_FILE_RANGE"; + case IORING_OP_SENDMSG: + return "SENDMSG"; + case IORING_OP_RECVMSG: + return "RECVMSG"; + case IORING_OP_TIMEOUT: + return "TIMEOUT"; + case IORING_OP_TIMEOUT_REMOVE: + return "TIMEOUT_REMOVE"; + case IORING_OP_ACCEPT: + return "ACCEPT"; + case IORING_OP_ASYNC_CANCEL: + return "ASYNC_CANCEL"; + case IORING_OP_LINK_TIMEOUT: + return "LINK_TIMEOUT"; + case IORING_OP_CONNECT: + return "CONNECT"; + case IORING_OP_FALLOCATE: + return "FALLOCATE"; + case IORING_OP_OPENAT: + return "OPENAT"; + case IORING_OP_CLOSE: + return "CLOSE"; + case IORING_OP_FILES_UPDATE: + return "FILES_UPDATE"; + case IORING_OP_STATX: + return "STATX"; + case IORING_OP_READ: + return "READ"; + case IORING_OP_WRITE: + return "WRITE"; + case IORING_OP_FADVISE: + return "FADVISE"; + case IORING_OP_MADVISE: + return "MADVISE"; + case IORING_OP_SEND: + return "SEND"; + case IORING_OP_RECV: + return "RECV"; + case IORING_OP_OPENAT2: + return "OPENAT2"; + case IORING_OP_EPOLL_CTL: + return "EPOLL_CTL"; + case IORING_OP_SPLICE: + return "SPLICE"; + case IORING_OP_PROVIDE_BUFFERS: + return "PROVIDE_BUFFERS"; + case IORING_OP_REMOVE_BUFFERS: + return "REMOVE_BUFFERS"; + case IORING_OP_TEE: + return "TEE"; + case IORING_OP_SHUTDOWN: + return "SHUTDOWN"; + case IORING_OP_RENAMEAT: + return "RENAMEAT"; + case IORING_OP_UNLINKAT: + return "UNLINKAT"; + case IORING_OP_MKDIRAT: + return "MKDIRAT"; + case IORING_OP_SYMLINKAT: + return "SYMLINKAT"; + case IORING_OP_LINKAT: + return "LINKAT"; + case IORING_OP_MSG_RING: + return "MSG_RING"; + case IORING_OP_FSETXATTR: + return "FSETXATTR"; + case IORING_OP_SETXATTR: + return "SETXATTR"; + case IORING_OP_FGETXATTR: + return "FGETXATTR"; + case IORING_OP_GETXATTR: + return "GETXATTR"; + case IORING_OP_SOCKET: + return "SOCKET"; + case IORING_OP_URING_CMD: + return "URING_CMD"; + case IORING_OP_LAST: + return "INVALID"; + } + return "INVALID"; +} + struct sock *io_uring_get_socket(struct file *file) { #if defined(CONFIG_UNIX) @@ -1215,6 +1492,42 @@ struct sock *io_uring_get_socket(struct file *file) } EXPORT_SYMBOL(io_uring_get_socket); +#if defined(CONFIG_UNIX) +static inline bool io_file_need_scm(struct file *filp) +{ +#if defined(IO_URING_SCM_ALL) + return true; +#else + return !!unix_get_socket(filp); +#endif +} +#else +static inline bool io_file_need_scm(struct file *filp) +{ + return false; +} +#endif + +static void io_ring_submit_unlock(struct io_ring_ctx *ctx, unsigned issue_flags) +{ + lockdep_assert_held(&ctx->uring_lock); + if (issue_flags & IO_URING_F_UNLOCKED) + mutex_unlock(&ctx->uring_lock); +} + +static void io_ring_submit_lock(struct io_ring_ctx *ctx, unsigned issue_flags) +{ + /* + * "Normal" inline submissions always hold the uring_lock, since we + * grab it from the system call. Same is true for the SQPOLL offload. + * The only exception is when we've detached the request and issue it + * from an async worker thread, grab the lock for that case. + */ + if (issue_flags & IO_URING_F_UNLOCKED) + mutex_lock(&ctx->uring_lock); + lockdep_assert_held(&ctx->uring_lock); +} + static inline void io_tw_lock(struct io_ring_ctx *ctx, bool *locked) { if (!*locked) { @@ -1276,31 +1589,36 @@ static inline void io_req_set_refcount(struct io_kiocb *req) #define IO_RSRC_REF_BATCH 100 +static void io_rsrc_put_node(struct io_rsrc_node *node, int nr) +{ + percpu_ref_put_many(&node->refs, nr); +} + static inline void io_req_put_rsrc_locked(struct io_kiocb *req, struct io_ring_ctx *ctx) __must_hold(&ctx->uring_lock) { - struct percpu_ref *ref = req->fixed_rsrc_refs; + struct io_rsrc_node *node = req->rsrc_node; - if (ref) { - if (ref == &ctx->rsrc_node->refs) + if (node) { + if (node == ctx->rsrc_node) ctx->rsrc_cached_refs++; else - percpu_ref_put(ref); + io_rsrc_put_node(node, 1); } } -static inline void io_req_put_rsrc(struct io_kiocb *req, struct io_ring_ctx *ctx) +static inline void io_req_put_rsrc(struct io_kiocb *req) { - if (req->fixed_rsrc_refs) - percpu_ref_put(req->fixed_rsrc_refs); + if (req->rsrc_node) + io_rsrc_put_node(req->rsrc_node, 1); } static __cold void io_rsrc_refs_drop(struct io_ring_ctx *ctx) __must_hold(&ctx->uring_lock) { if (ctx->rsrc_cached_refs) { - percpu_ref_put_many(&ctx->rsrc_node->refs, ctx->rsrc_cached_refs); + io_rsrc_put_node(ctx->rsrc_node, ctx->rsrc_cached_refs); ctx->rsrc_cached_refs = 0; } } @@ -1313,33 +1631,42 @@ static void io_rsrc_refs_refill(struct io_ring_ctx *ctx) } static inline void io_req_set_rsrc_node(struct io_kiocb *req, - struct io_ring_ctx *ctx) + struct io_ring_ctx *ctx, + unsigned int issue_flags) { - if (!req->fixed_rsrc_refs) { - req->fixed_rsrc_refs = &ctx->rsrc_node->refs; - ctx->rsrc_cached_refs--; - if (unlikely(ctx->rsrc_cached_refs < 0)) - io_rsrc_refs_refill(ctx); + if (!req->rsrc_node) { + req->rsrc_node = ctx->rsrc_node; + + if (!(issue_flags & IO_URING_F_UNLOCKED)) { + lockdep_assert_held(&ctx->uring_lock); + ctx->rsrc_cached_refs--; + if (unlikely(ctx->rsrc_cached_refs < 0)) + io_rsrc_refs_refill(ctx); + } else { + percpu_ref_get(&req->rsrc_node->refs); + } } } static unsigned int __io_put_kbuf(struct io_kiocb *req, struct list_head *list) { - struct io_buffer *kbuf = req->kbuf; - unsigned int cflags; + if (req->flags & REQ_F_BUFFER_RING) { + if (req->buf_list) + req->buf_list->head++; + req->flags &= ~REQ_F_BUFFER_RING; + } else { + list_add(&req->kbuf->list, list); + req->flags &= ~REQ_F_BUFFER_SELECTED; + } - cflags = IORING_CQE_F_BUFFER | (kbuf->bid << IORING_CQE_BUFFER_SHIFT); - req->flags &= ~REQ_F_BUFFER_SELECTED; - list_add(&kbuf->list, list); - req->kbuf = NULL; - return cflags; + return IORING_CQE_F_BUFFER | (req->buf_index << IORING_CQE_BUFFER_SHIFT); } static inline unsigned int io_put_kbuf_comp(struct io_kiocb *req) { lockdep_assert_held(&req->ctx->completion_lock); - if (likely(!(req->flags & REQ_F_BUFFER_SELECTED))) + if (!(req->flags & (REQ_F_BUFFER_SELECTED|REQ_F_BUFFER_RING))) return 0; return __io_put_kbuf(req, &req->ctx->io_buffers_comp); } @@ -1349,7 +1676,7 @@ static inline unsigned int io_put_kbuf(struct io_kiocb *req, { unsigned int cflags; - if (likely(!(req->flags & REQ_F_BUFFER_SELECTED))) + if (!(req->flags & (REQ_F_BUFFER_SELECTED|REQ_F_BUFFER_RING))) return 0; /* @@ -1364,7 +1691,10 @@ static inline unsigned int io_put_kbuf(struct io_kiocb *req, * We migrate buffers from the comp_list to the issue cache list * when we need one. */ - if (issue_flags & IO_URING_F_UNLOCKED) { + if (req->flags & REQ_F_BUFFER_RING) { + /* no buffers to recycle for this case */ + cflags = __io_put_kbuf(req, NULL); + } else if (issue_flags & IO_URING_F_UNLOCKED) { struct io_ring_ctx *ctx = req->ctx; spin_lock(&ctx->completion_lock); @@ -1382,15 +1712,10 @@ static inline unsigned int io_put_kbuf(struct io_kiocb *req, static struct io_buffer_list *io_buffer_get_list(struct io_ring_ctx *ctx, unsigned int bgid) { - struct list_head *hash_list; - struct io_buffer_list *bl; - - hash_list = &ctx->io_buffers[hash_32(bgid, IO_BUFFERS_HASH_BITS)]; - list_for_each_entry(bl, hash_list, list) - if (bl->bgid == bgid || bgid == -1U) - return bl; + if (ctx->io_bl && bgid < BGID_ARRAY) + return &ctx->io_bl[bgid]; - return NULL; + return xa_load(&ctx->io_bl_xa, bgid); } static void io_kbuf_recycle(struct io_kiocb *req, unsigned issue_flags) @@ -1399,54 +1724,42 @@ static void io_kbuf_recycle(struct io_kiocb *req, unsigned issue_flags) struct io_buffer_list *bl; struct io_buffer *buf; - if (likely(!(req->flags & REQ_F_BUFFER_SELECTED))) + if (!(req->flags & (REQ_F_BUFFER_SELECTED|REQ_F_BUFFER_RING))) return; /* don't recycle if we already did IO to this buffer */ if (req->flags & REQ_F_PARTIAL_IO) return; + /* + * We don't need to recycle for REQ_F_BUFFER_RING, we can just clear + * the flag and hence ensure that bl->head doesn't get incremented. + * If the tail has already been incremented, hang on to it. + */ + if (req->flags & REQ_F_BUFFER_RING) { + if (req->buf_list) { + req->buf_index = req->buf_list->bgid; + req->flags &= ~REQ_F_BUFFER_RING; + } + return; + } - if (issue_flags & IO_URING_F_UNLOCKED) - mutex_lock(&ctx->uring_lock); - - lockdep_assert_held(&ctx->uring_lock); + io_ring_submit_lock(ctx, issue_flags); buf = req->kbuf; bl = io_buffer_get_list(ctx, buf->bgid); list_add(&buf->list, &bl->buf_list); req->flags &= ~REQ_F_BUFFER_SELECTED; - req->kbuf = NULL; + req->buf_index = buf->bgid; - if (issue_flags & IO_URING_F_UNLOCKED) - mutex_unlock(&ctx->uring_lock); + io_ring_submit_unlock(ctx, issue_flags); } static bool io_match_task(struct io_kiocb *head, struct task_struct *task, bool cancel_all) __must_hold(&req->ctx->timeout_lock) { - struct io_kiocb *req; - if (task && head->task != task) return false; - if (cancel_all) - return true; - - io_for_each_link(req, head) { - if (req->flags & REQ_F_INFLIGHT) - return true; - } - return false; -} - -static bool io_match_linked(struct io_kiocb *head) -{ - struct io_kiocb *req; - - io_for_each_link(req, head) { - if (req->flags & REQ_F_INFLIGHT) - return true; - } - return false; + return cancel_all; } /* @@ -1456,24 +1769,9 @@ static bool io_match_linked(struct io_kiocb *head) static bool io_match_task_safe(struct io_kiocb *head, struct task_struct *task, bool cancel_all) { - bool matched; - if (task && head->task != task) return false; - if (cancel_all) - return true; - - if (head->flags & REQ_F_LINK_TIMEOUT) { - struct io_ring_ctx *ctx = head->ctx; - - /* protect against races with linked timeouts */ - spin_lock_irq(&ctx->timeout_lock); - matched = io_match_linked(head); - spin_unlock_irq(&ctx->timeout_lock); - } else { - matched = io_match_linked(head); - } - return matched; + return cancel_all; } static inline bool req_has_async_data(struct io_kiocb *req) @@ -1493,7 +1791,12 @@ static inline void req_set_fail(struct io_kiocb *req) static inline void req_fail_link_node(struct io_kiocb *req, int res) { req_set_fail(req); - req->result = res; + req->cqe.res = res; +} + +static inline void io_req_add_to_cache(struct io_kiocb *req, struct io_ring_ctx *ctx) +{ + wq_stack_add_head(&req->comp_list, &ctx->submit_state.free_list); } static __cold void io_ring_ctx_ref_free(struct percpu_ref *ref) @@ -1530,12 +1833,14 @@ static __cold void io_fallback_req_func(struct work_struct *work) static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) { struct io_ring_ctx *ctx; - int i, hash_bits; + int hash_bits; ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); if (!ctx) return NULL; + xa_init(&ctx->io_bl_xa); + /* * Use 5 bits less than the max cq entries, that should give us around * 32 entries per hash list if totally full and uniformly spread. @@ -1557,13 +1862,6 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) /* set invalid range, so io_import_fixed() fails meeting it */ ctx->dummy_ubuf->ubuf = -1UL; - ctx->io_buffers = kcalloc(1U << IO_BUFFERS_HASH_BITS, - sizeof(struct list_head), GFP_KERNEL); - if (!ctx->io_buffers) - goto err; - for (i = 0; i < (1U << IO_BUFFERS_HASH_BITS); i++) - INIT_LIST_HEAD(&ctx->io_buffers[i]); - if (percpu_ref_init(&ctx->refs, io_ring_ctx_ref_free, PERCPU_REF_ALLOW_REINIT, GFP_KERNEL)) goto err; @@ -1595,15 +1893,12 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) INIT_WQ_LIST(&ctx->locked_free_list); INIT_DELAYED_WORK(&ctx->fallback_work, io_fallback_req_func); INIT_WQ_LIST(&ctx->submit_state.compl_reqs); -#ifdef CONFIG_NET_RX_BUSY_POLL - INIT_LIST_HEAD(&ctx->napi_list); - spin_lock_init(&ctx->napi_lock); -#endif return ctx; err: kfree(ctx->dummy_ubuf); kfree(ctx->cancel_hash); - kfree(ctx->io_buffers); + kfree(ctx->io_bl); + xa_destroy(&ctx->io_bl_xa); kfree(ctx); return NULL; } @@ -1627,23 +1922,11 @@ static bool req_need_defer(struct io_kiocb *req, u32 seq) return false; } -#define FFS_NOWAIT 0x1UL -#define FFS_ISREG 0x2UL -#define FFS_MASK ~(FFS_NOWAIT|FFS_ISREG) - static inline bool io_req_ffs_set(struct io_kiocb *req) { return req->flags & REQ_F_FIXED_FILE; } -static inline void io_req_track_inflight(struct io_kiocb *req) -{ - if (!(req->flags & REQ_F_INFLIGHT)) { - req->flags |= REQ_F_INFLIGHT; - atomic_inc(¤t->io_uring->inflight_tracked); - } -} - static struct io_kiocb *__io_prep_linked_timeout(struct io_kiocb *req) { if (WARN_ON_ONCE(!req->link)) @@ -1665,6 +1948,17 @@ static inline struct io_kiocb *io_prep_linked_timeout(struct io_kiocb *req) return __io_prep_linked_timeout(req); } +static noinline void __io_arm_ltimeout(struct io_kiocb *req) +{ + io_queue_linked_timeout(__io_prep_linked_timeout(req)); +} + +static inline void io_arm_ltimeout(struct io_kiocb *req) +{ + if (unlikely(req->flags & REQ_F_ARM_LTIMEOUT)) + __io_arm_ltimeout(req); +} + static void io_prep_async_work(struct io_kiocb *req) { const struct io_op_def *def = &io_op_defs[req->opcode]; @@ -1677,6 +1971,7 @@ static void io_prep_async_work(struct io_kiocb *req) req->work.list.next = NULL; req->work.flags = 0; + req->work.cancel_seq = atomic_read(&ctx->cancel_seq); if (req->flags & REQ_F_FORCE_ASYNC) req->work.flags |= IO_WQ_WORK_CONCURRENT; @@ -1687,14 +1982,6 @@ static void io_prep_async_work(struct io_kiocb *req) if (def->unbound_nonreg_file) req->work.flags |= IO_WQ_WORK_UNBOUND; } - - switch (req->opcode) { - case IORING_OP_SPLICE: - case IORING_OP_TEE: - if (!S_ISREG(file_inode(req->splice.file_in)->i_mode)) - req->work.flags |= IO_WQ_WORK_UNBOUND; - break; - } } static void io_prep_async_link(struct io_kiocb *req) @@ -1716,17 +2003,15 @@ static void io_prep_async_link(struct io_kiocb *req) static inline void io_req_add_compl_list(struct io_kiocb *req) { - struct io_ring_ctx *ctx = req->ctx; - struct io_submit_state *state = &ctx->submit_state; + struct io_submit_state *state = &req->ctx->submit_state; if (!(req->flags & REQ_F_CQE_SKIP)) - ctx->submit_state.flush_cqes = true; + state->flush_cqes = true; wq_list_add_tail(&req->comp_list, &state->compl_reqs); } -static void io_queue_async_work(struct io_kiocb *req, bool *dont_use) +static void io_queue_iowq(struct io_kiocb *req, bool *dont_use) { - struct io_ring_ctx *ctx = req->ctx; struct io_kiocb *link = io_prep_linked_timeout(req); struct io_uring_task *tctx = req->task->io_uring; @@ -1746,8 +2031,9 @@ static void io_queue_async_work(struct io_kiocb *req, bool *dont_use) if (WARN_ON_ONCE(!same_thread_group(req->task, current))) req->work.flags |= IO_WQ_WORK_CANCEL; - trace_io_uring_queue_async_work(ctx, req, req->user_data, req->opcode, req->flags, - &req->work, io_wq_is_hashed(&req->work)); + trace_io_uring_queue_async_work(req->ctx, req, req->cqe.user_data, + req->opcode, req->flags, &req->work, + io_wq_is_hashed(&req->work)); io_wq_enqueue(tctx->io_wq, &req->work); if (link) io_queue_linked_timeout(link); @@ -1765,8 +2051,7 @@ static void io_kill_timeout(struct io_kiocb *req, int status) atomic_set(&req->ctx->cq_timeouts, atomic_read(&req->ctx->cq_timeouts) + 1); list_del_init(&req->timeout.list); - io_fill_cqe_req(req, status, 0); - io_put_req_deferred(req); + io_req_tw_post_queue(req, status, 0); } } @@ -1788,12 +2073,11 @@ static __cold void io_flush_timeouts(struct io_ring_ctx *ctx) __must_hold(&ctx->completion_lock) { u32 seq = ctx->cached_cq_tail - atomic_read(&ctx->cq_timeouts); + struct io_kiocb *req, *tmp; spin_lock_irq(&ctx->timeout_lock); - while (!list_empty(&ctx->timeout_list)) { + list_for_each_entry_safe(req, tmp, &ctx->timeout_list, timeout.list) { u32 events_needed, events_got; - struct io_kiocb *req = list_first_entry(&ctx->timeout_list, - struct io_kiocb, timeout.list); if (io_is_timeout_noseq(req)) break; @@ -1810,7 +2094,6 @@ static __cold void io_flush_timeouts(struct io_ring_ctx *ctx) if (events_got < events_needed) break; - list_del_init(&req->timeout.list); io_kill_timeout(req, 0); } ctx->cq_last_tm_flush = seq; @@ -1850,21 +2133,53 @@ static inline unsigned int __io_cqring_events(struct io_ring_ctx *ctx) return ctx->cached_cq_tail - READ_ONCE(ctx->rings->cq.head); } -static inline struct io_uring_cqe *io_get_cqe(struct io_ring_ctx *ctx) +/* + * writes to the cq entry need to come after reading head; the + * control dependency is enough as we're using WRITE_ONCE to + * fill the cq entry + */ +static noinline struct io_uring_cqe *__io_get_cqe(struct io_ring_ctx *ctx) { struct io_rings *rings = ctx->rings; - unsigned tail, mask = ctx->cq_entries - 1; - - /* - * writes to the cq entry need to come after reading head; the - * control dependency is enough as we're using WRITE_ONCE to - * fill the cq entry - */ - if (__io_cqring_events(ctx) == ctx->cq_entries) + unsigned int off = ctx->cached_cq_tail & (ctx->cq_entries - 1); + unsigned int shift = 0; + unsigned int free, queued, len; + + if (ctx->flags & IORING_SETUP_CQE32) + shift = 1; + + /* userspace may cheat modifying the tail, be safe and do min */ + queued = min(__io_cqring_events(ctx), ctx->cq_entries); + free = ctx->cq_entries - queued; + /* we need a contiguous range, limit based on the current array offset */ + len = min(free, ctx->cq_entries - off); + if (!len) return NULL; - tail = ctx->cached_cq_tail++; - return &rings->cqes[tail & mask]; + ctx->cached_cq_tail++; + ctx->cqe_cached = &rings->cqes[off]; + ctx->cqe_sentinel = ctx->cqe_cached + len; + ctx->cqe_cached++; + return &rings->cqes[off << shift]; +} + +static inline struct io_uring_cqe *io_get_cqe(struct io_ring_ctx *ctx) +{ + if (likely(ctx->cqe_cached < ctx->cqe_sentinel)) { + struct io_uring_cqe *cqe = ctx->cqe_cached; + + if (ctx->flags & IORING_SETUP_CQE32) { + unsigned int off = ctx->cqe_cached - ctx->rings->cqes; + + cqe += off; + } + + ctx->cached_cq_tail++; + ctx->cqe_cached++; + return cqe; + } + + return __io_get_cqe(ctx); } static void io_eventfd_signal(struct io_ring_ctx *ctx) @@ -1935,10 +2250,14 @@ static void io_cqring_ev_posted_iopoll(struct io_ring_ctx *ctx) static bool __io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force) { bool all_flushed, posted; + size_t cqe_size = sizeof(struct io_uring_cqe); if (!force && __io_cqring_events(ctx) == ctx->cq_entries) return false; + if (ctx->flags & IORING_SETUP_CQE32) + cqe_size <<= 1; + posted = false; spin_lock(&ctx->completion_lock); while (!list_empty(&ctx->cq_overflow_list)) { @@ -1950,7 +2269,7 @@ static bool __io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force) ocqe = list_first_entry(&ctx->cq_overflow_list, struct io_overflow_cqe, list); if (cqe) - memcpy(cqe, &ocqe->cqe, sizeof(*cqe)); + memcpy(cqe, &ocqe->cqe, cqe_size); else io_account_cq_overflow(ctx); @@ -1961,13 +2280,11 @@ static bool __io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force) all_flushed = list_empty(&ctx->cq_overflow_list); if (all_flushed) { - clear_bit(0, &ctx->check_cq_overflow); - WRITE_ONCE(ctx->rings->sq_flags, - ctx->rings->sq_flags & ~IORING_SQ_CQ_OVERFLOW); + clear_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq); + atomic_andnot(IORING_SQ_CQ_OVERFLOW, &ctx->rings->sq_flags); } - if (posted) - io_commit_cqring(ctx); + io_commit_cqring(ctx); spin_unlock(&ctx->completion_lock); if (posted) io_cqring_ev_posted(ctx); @@ -1978,7 +2295,7 @@ static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx) { bool ret = true; - if (test_bit(0, &ctx->check_cq_overflow)) { + if (test_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq)) { /* iopoll syncs against uring_lock, not completion_lock */ if (ctx->flags & IORING_SETUP_IOPOLL) mutex_lock(&ctx->uring_lock); @@ -1990,19 +2307,23 @@ static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx) return ret; } -/* must to be called somewhat shortly after putting a request */ -static inline void io_put_task(struct task_struct *task, int nr) +static void __io_put_task(struct task_struct *task, int nr) { struct io_uring_task *tctx = task->io_uring; - if (likely(task == current)) { - tctx->cached_refs += nr; - } else { - percpu_counter_sub(&tctx->inflight, nr); - if (unlikely(atomic_read(&tctx->in_idle))) - wake_up(&tctx->wait); - put_task_struct_many(task, nr); - } + percpu_counter_sub(&tctx->inflight, nr); + if (unlikely(atomic_read(&tctx->in_idle))) + wake_up(&tctx->wait); + put_task_struct_many(task, nr); +} + +/* must to be called somewhat shortly after putting a request */ +static inline void io_put_task(struct task_struct *task, int nr) +{ + if (likely(task == current)) + task->io_uring->cached_refs += nr; + else + __io_put_task(task, nr); } static void io_task_refs_refill(struct io_uring_task *tctx) @@ -2036,11 +2357,18 @@ static __cold void io_uring_drop_tctx_refs(struct task_struct *task) } static bool io_cqring_event_overflow(struct io_ring_ctx *ctx, u64 user_data, - s32 res, u32 cflags) + s32 res, u32 cflags, u64 extra1, + u64 extra2) { struct io_overflow_cqe *ocqe; + size_t ocq_size = sizeof(struct io_overflow_cqe); + bool is_cqe32 = (ctx->flags & IORING_SETUP_CQE32); - ocqe = kmalloc(sizeof(*ocqe), GFP_ATOMIC | __GFP_ACCOUNT); + if (is_cqe32) + ocq_size += sizeof(struct io_uring_cqe); + + ocqe = kmalloc(ocq_size, GFP_ATOMIC | __GFP_ACCOUNT); + trace_io_uring_cqe_overflow(ctx, user_data, res, cflags, ocqe); if (!ocqe) { /* * If we're in ring overflow flush mode, or in task cancel mode, @@ -2048,17 +2376,21 @@ static bool io_cqring_event_overflow(struct io_ring_ctx *ctx, u64 user_data, * on the floor. */ io_account_cq_overflow(ctx); + set_bit(IO_CHECK_CQ_DROPPED_BIT, &ctx->check_cq); return false; } if (list_empty(&ctx->cq_overflow_list)) { - set_bit(0, &ctx->check_cq_overflow); - WRITE_ONCE(ctx->rings->sq_flags, - ctx->rings->sq_flags | IORING_SQ_CQ_OVERFLOW); + set_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq); + atomic_or(IORING_SQ_CQ_OVERFLOW, &ctx->rings->sq_flags); } ocqe->cqe.user_data = user_data; ocqe->cqe.res = res; ocqe->cqe.flags = cflags; + if (is_cqe32) { + ocqe->cqe.big_cqe[0] = extra1; + ocqe->cqe.big_cqe[1] = extra2; + } list_add_tail(&ocqe->list, &ctx->cq_overflow_list); return true; } @@ -2080,42 +2412,114 @@ static inline bool __io_fill_cqe(struct io_ring_ctx *ctx, u64 user_data, WRITE_ONCE(cqe->flags, cflags); return true; } - return io_cqring_event_overflow(ctx, user_data, res, cflags); + return io_cqring_event_overflow(ctx, user_data, res, cflags, 0, 0); +} + +static inline bool __io_fill_cqe_req_filled(struct io_ring_ctx *ctx, + struct io_kiocb *req) +{ + struct io_uring_cqe *cqe; + + trace_io_uring_complete(req->ctx, req, req->cqe.user_data, + req->cqe.res, req->cqe.flags, 0, 0); + + /* + * If we can't get a cq entry, userspace overflowed the + * submission (by quite a lot). Increment the overflow count in + * the ring. + */ + cqe = io_get_cqe(ctx); + if (likely(cqe)) { + memcpy(cqe, &req->cqe, sizeof(*cqe)); + return true; + } + return io_cqring_event_overflow(ctx, req->cqe.user_data, + req->cqe.res, req->cqe.flags, 0, 0); +} + +static inline bool __io_fill_cqe32_req_filled(struct io_ring_ctx *ctx, + struct io_kiocb *req) +{ + struct io_uring_cqe *cqe; + u64 extra1 = req->extra1; + u64 extra2 = req->extra2; + + trace_io_uring_complete(req->ctx, req, req->cqe.user_data, + req->cqe.res, req->cqe.flags, extra1, extra2); + + /* + * If we can't get a cq entry, userspace overflowed the + * submission (by quite a lot). Increment the overflow count in + * the ring. + */ + cqe = io_get_cqe(ctx); + if (likely(cqe)) { + memcpy(cqe, &req->cqe, sizeof(struct io_uring_cqe)); + cqe->big_cqe[0] = extra1; + cqe->big_cqe[1] = extra2; + return true; + } + + return io_cqring_event_overflow(ctx, req->cqe.user_data, req->cqe.res, + req->cqe.flags, extra1, extra2); } static inline bool __io_fill_cqe_req(struct io_kiocb *req, s32 res, u32 cflags) { - trace_io_uring_complete(req->ctx, req, req->user_data, res, cflags); - return __io_fill_cqe(req->ctx, req->user_data, res, cflags); + trace_io_uring_complete(req->ctx, req, req->cqe.user_data, res, cflags, 0, 0); + return __io_fill_cqe(req->ctx, req->cqe.user_data, res, cflags); } -static noinline void io_fill_cqe_req(struct io_kiocb *req, s32 res, u32 cflags) +static inline void __io_fill_cqe32_req(struct io_kiocb *req, s32 res, u32 cflags, + u64 extra1, u64 extra2) { - if (!(req->flags & REQ_F_CQE_SKIP)) - __io_fill_cqe_req(req, res, cflags); + struct io_ring_ctx *ctx = req->ctx; + struct io_uring_cqe *cqe; + + if (WARN_ON_ONCE(!(ctx->flags & IORING_SETUP_CQE32))) + return; + if (req->flags & REQ_F_CQE_SKIP) + return; + + trace_io_uring_complete(ctx, req, req->cqe.user_data, res, cflags, + extra1, extra2); + + /* + * If we can't get a cq entry, userspace overflowed the + * submission (by quite a lot). Increment the overflow count in + * the ring. + */ + cqe = io_get_cqe(ctx); + if (likely(cqe)) { + WRITE_ONCE(cqe->user_data, req->cqe.user_data); + WRITE_ONCE(cqe->res, res); + WRITE_ONCE(cqe->flags, cflags); + WRITE_ONCE(cqe->big_cqe[0], extra1); + WRITE_ONCE(cqe->big_cqe[1], extra2); + return; + } + + io_cqring_event_overflow(ctx, req->cqe.user_data, res, cflags, extra1, extra2); } static noinline bool io_fill_cqe_aux(struct io_ring_ctx *ctx, u64 user_data, s32 res, u32 cflags) { ctx->cq_extra++; - trace_io_uring_complete(ctx, NULL, user_data, res, cflags); + trace_io_uring_complete(ctx, NULL, user_data, res, cflags, 0, 0); return __io_fill_cqe(ctx, user_data, res, cflags); } -static void __io_req_complete_post(struct io_kiocb *req, s32 res, - u32 cflags) +static void __io_req_complete_put(struct io_kiocb *req) { - struct io_ring_ctx *ctx = req->ctx; - - if (!(req->flags & REQ_F_CQE_SKIP)) - __io_fill_cqe_req(req, res, cflags); /* * If we're the last reference to this request, add to our locked * free_list cache. */ if (req_ref_put_and_test(req)) { - if (req->flags & (REQ_F_LINK | REQ_F_HARDLINK)) { + struct io_ring_ctx *ctx = req->ctx; + + if (req->flags & IO_REQ_LINK_FLAGS) { if (req->flags & IO_DISARM_MASK) io_disarm_next(req); if (req->link) { @@ -2123,7 +2527,7 @@ static void __io_req_complete_post(struct io_kiocb *req, s32 res, req->link = NULL; } } - io_req_put_rsrc(req, ctx); + io_req_put_rsrc(req); /* * Selected buffer deallocation in io_clean_op() assumes that * we don't hold ->completion_lock. Clean them here to avoid @@ -2137,8 +2541,23 @@ static void __io_req_complete_post(struct io_kiocb *req, s32 res, } } -static void io_req_complete_post(struct io_kiocb *req, s32 res, - u32 cflags) +static void __io_req_complete_post(struct io_kiocb *req, s32 res, + u32 cflags) +{ + if (!(req->flags & REQ_F_CQE_SKIP)) + __io_fill_cqe_req(req, res, cflags); + __io_req_complete_put(req); +} + +static void __io_req_complete_post32(struct io_kiocb *req, s32 res, + u32 cflags, u64 extra1, u64 extra2) +{ + if (!(req->flags & REQ_F_CQE_SKIP)) + __io_fill_cqe32_req(req, res, cflags, extra1, extra2); + __io_req_complete_put(req); +} + +static void io_req_complete_post(struct io_kiocb *req, s32 res, u32 cflags) { struct io_ring_ctx *ctx = req->ctx; @@ -2149,11 +2568,23 @@ static void io_req_complete_post(struct io_kiocb *req, s32 res, io_cqring_ev_posted(ctx); } +static void io_req_complete_post32(struct io_kiocb *req, s32 res, + u32 cflags, u64 extra1, u64 extra2) +{ + struct io_ring_ctx *ctx = req->ctx; + + spin_lock(&ctx->completion_lock); + __io_req_complete_post32(req, res, cflags, extra1, extra2); + io_commit_cqring(ctx); + spin_unlock(&ctx->completion_lock); + io_cqring_ev_posted(ctx); +} + static inline void io_req_complete_state(struct io_kiocb *req, s32 res, u32 cflags) { - req->result = res; - req->cflags = cflags; + req->cqe.res = res; + req->cqe.flags = cflags; req->flags |= REQ_F_COMPLETE_INLINE; } @@ -2166,8 +2597,23 @@ static inline void __io_req_complete(struct io_kiocb *req, unsigned issue_flags, io_req_complete_post(req, res, cflags); } +static inline void __io_req_complete32(struct io_kiocb *req, + unsigned int issue_flags, s32 res, + u32 cflags, u64 extra1, u64 extra2) +{ + if (issue_flags & IO_URING_F_COMPLETE_DEFER) { + io_req_complete_state(req, res, cflags); + req->extra1 = extra1; + req->extra2 = extra2; + } else { + io_req_complete_post32(req, res, cflags, extra1, extra2); + } +} + static inline void io_req_complete(struct io_kiocb *req, s32 res) { + if (res < 0) + req_set_fail(req); __io_req_complete(req, 0, res, 0); } @@ -2177,17 +2623,6 @@ static void io_req_complete_failed(struct io_kiocb *req, s32 res) io_req_complete_post(req, res, io_put_kbuf(req, IO_URING_F_UNLOCKED)); } -static void io_req_complete_fail_submit(struct io_kiocb *req) -{ - /* - * We don't submit, fail them all, for that replace hardlinks with - * normal links. Extra REQ_F_LINK is tolerated. - */ - req->flags &= ~REQ_F_HARDLINK; - req->flags |= REQ_F_LINK; - io_req_complete_failed(req, req->result); -} - /* * Don't initialise the fields below on every allocation, but do that in * advance and keep them valid across allocations. @@ -2198,7 +2633,7 @@ static void io_preinit_req(struct io_kiocb *req, struct io_ring_ctx *ctx) req->link = NULL; req->async_data = NULL; /* not necessary, but safer to zero */ - req->result = 0; + req->cqe.res = 0; } static void io_flush_cached_locked_reqs(struct io_ring_ctx *ctx, @@ -2210,19 +2645,9 @@ static void io_flush_cached_locked_reqs(struct io_ring_ctx *ctx, spin_unlock(&ctx->completion_lock); } -/* Returns true IFF there are requests in the cache */ -static bool io_flush_cached_reqs(struct io_ring_ctx *ctx) +static inline bool io_req_cache_empty(struct io_ring_ctx *ctx) { - struct io_submit_state *state = &ctx->submit_state; - - /* - * If we have more than a batch's worth of requests in our IRQ side - * locked cache, grab the lock and move them over to our submission - * side cache. - */ - if (READ_ONCE(ctx->locked_free_nr) > IO_COMPL_BATCH) - io_flush_cached_locked_reqs(ctx, state); - return !!state->free_list.next; + return !ctx->submit_state.free_list.next; } /* @@ -2234,14 +2659,20 @@ static bool io_flush_cached_reqs(struct io_ring_ctx *ctx) static __cold bool __io_alloc_req_refill(struct io_ring_ctx *ctx) __must_hold(&ctx->uring_lock) { - struct io_submit_state *state = &ctx->submit_state; gfp_t gfp = GFP_KERNEL | __GFP_NOWARN; void *reqs[IO_REQ_ALLOC_BATCH]; - struct io_kiocb *req; int ret, i; - if (likely(state->free_list.next || io_flush_cached_reqs(ctx))) - return true; + /* + * If we have more than a batch's worth of requests in our IRQ side + * locked cache, grab the lock and move them over to our submission + * side cache. + */ + if (data_race(ctx->locked_free_nr) > IO_COMPL_BATCH) { + io_flush_cached_locked_reqs(ctx, &ctx->submit_state); + if (!io_req_cache_empty(ctx)) + return true; + } ret = kmem_cache_alloc_bulk(req_cachep, gfp, ARRAY_SIZE(reqs), reqs); @@ -2258,17 +2689,17 @@ static __cold bool __io_alloc_req_refill(struct io_ring_ctx *ctx) percpu_ref_get_many(&ctx->refs, ret); for (i = 0; i < ret; i++) { - req = reqs[i]; + struct io_kiocb *req = reqs[i]; io_preinit_req(req, ctx); - wq_stack_add_head(&req->comp_list, &state->free_list); + io_req_add_to_cache(req, ctx); } return true; } static inline bool io_alloc_req_refill(struct io_ring_ctx *ctx) { - if (unlikely(!ctx->submit_state.free_list.next)) + if (unlikely(io_req_cache_empty(ctx))) return __io_alloc_req_refill(ctx); return true; } @@ -2297,11 +2728,11 @@ static inline void io_dismantle_req(struct io_kiocb *req) io_put_file(req->file); } -static __cold void __io_free_req(struct io_kiocb *req) +static __cold void io_free_req(struct io_kiocb *req) { struct io_ring_ctx *ctx = req->ctx; - io_req_put_rsrc(req, ctx); + io_req_put_rsrc(req); io_dismantle_req(req); io_put_task(req->task, 1); @@ -2319,7 +2750,7 @@ static inline void io_remove_next_linked(struct io_kiocb *req) nxt->link = NULL; } -static bool io_kill_linked_timeout(struct io_kiocb *req) +static struct io_kiocb *io_disarm_linked_timeout(struct io_kiocb *req) __must_hold(&req->ctx->completion_lock) __must_hold(&req->ctx->timeout_lock) { @@ -2332,13 +2763,10 @@ static bool io_kill_linked_timeout(struct io_kiocb *req) link->timeout.head = NULL; if (hrtimer_try_to_cancel(&io->timer) != -1) { list_del(&link->timeout.list); - /* leave REQ_F_CQE_SKIP to io_fill_cqe_req */ - io_fill_cqe_req(link, -ECANCELED, 0); - io_put_req_deferred(link); - return true; + return link; } } - return false; + return NULL; } static void io_fail_links(struct io_kiocb *req) @@ -2352,19 +2780,19 @@ static void io_fail_links(struct io_kiocb *req) long res = -ECANCELED; if (link->flags & REQ_F_FAIL) - res = link->result; + res = link->cqe.res; nxt = link->link; link->link = NULL; - trace_io_uring_fail_link(req->ctx, req, req->user_data, + trace_io_uring_fail_link(req->ctx, req, req->cqe.user_data, req->opcode, link); - if (!ignore_cqes) { + if (ignore_cqes) + link->flags |= REQ_F_CQE_SKIP; + else link->flags &= ~REQ_F_CQE_SKIP; - io_fill_cqe_req(link, res, 0); - } - io_put_req_deferred(link); + __io_req_complete_post(link, res, 0); link = nxt; } } @@ -2372,25 +2800,27 @@ static void io_fail_links(struct io_kiocb *req) static bool io_disarm_next(struct io_kiocb *req) __must_hold(&req->ctx->completion_lock) { + struct io_kiocb *link = NULL; bool posted = false; if (req->flags & REQ_F_ARM_LTIMEOUT) { - struct io_kiocb *link = req->link; - + link = req->link; req->flags &= ~REQ_F_ARM_LTIMEOUT; if (link && link->opcode == IORING_OP_LINK_TIMEOUT) { io_remove_next_linked(req); - /* leave REQ_F_CQE_SKIP to io_fill_cqe_req */ - io_fill_cqe_req(link, -ECANCELED, 0); - io_put_req_deferred(link); + io_req_tw_post_queue(link, -ECANCELED, 0); posted = true; } } else if (req->flags & REQ_F_LINK_TIMEOUT) { struct io_ring_ctx *ctx = req->ctx; spin_lock_irq(&ctx->timeout_lock); - posted = io_kill_linked_timeout(req); + link = io_disarm_linked_timeout(req); spin_unlock_irq(&ctx->timeout_lock); + if (link) { + posted = true; + io_req_tw_post_queue(link, -ECANCELED, 0); + } } if (unlikely((req->flags & REQ_F_FAIL) && !(req->flags & REQ_F_HARDLINK))) { @@ -2407,8 +2837,7 @@ static void __io_req_find_next_prep(struct io_kiocb *req) spin_lock(&ctx->completion_lock); posted = io_disarm_next(req); - if (posted) - io_commit_cqring(ctx); + io_commit_cqring(ctx); spin_unlock(&ctx->completion_lock); if (posted) io_cqring_ev_posted(ctx); @@ -2418,8 +2847,6 @@ static inline struct io_kiocb *io_req_find_next(struct io_kiocb *req) { struct io_kiocb *nxt; - if (likely(!(req->flags & (REQ_F_LINK|REQ_F_HARDLINK)))) - return NULL; /* * If LINK is set, we have dependent requests in this chain. If we * didn't fail this request, queue the first one up, moving any other @@ -2437,6 +2864,8 @@ static void ctx_flush_and_put(struct io_ring_ctx *ctx, bool *locked) { if (!ctx) return; + if (ctx->flags & IORING_SETUP_TASKRUN_FLAG) + atomic_andnot(IORING_SQ_TASKRUN, &ctx->rings->sq_flags); if (*locked) { io_submit_flush_completions(ctx); mutex_unlock(&ctx->uring_lock); @@ -2480,7 +2909,7 @@ static void handle_prev_tw_list(struct io_wq_work_node *node, if (likely(*uring_locked)) req->io_task_work.func(req, uring_locked); else - __io_req_complete_post(req, req->result, + __io_req_complete_post(req, req->cqe.res, io_put_kbuf_comp(req)); node = next; } while (node); @@ -2521,15 +2950,11 @@ static void tctx_task_work(struct callback_head *cb) while (1) { struct io_wq_work_node *node1, *node2; - if (!tctx->task_list.first && - !tctx->prior_task_list.first && uring_locked) - io_submit_flush_completions(ctx); - spin_lock_irq(&tctx->task_lock); - node1 = tctx->prior_task_list.first; + node1 = tctx->prio_task_list.first; node2 = tctx->task_list.first; INIT_WQ_LIST(&tctx->task_list); - INIT_WQ_LIST(&tctx->prior_task_list); + INIT_WQ_LIST(&tctx->prio_task_list); if (!node2 && !node1) tctx->task_running = false; spin_unlock_irq(&tctx->task_lock); @@ -2538,10 +2963,13 @@ static void tctx_task_work(struct callback_head *cb) if (node1) handle_prev_tw_list(node1, &ctx, &uring_locked); - if (node2) handle_tw_list(node2, &ctx, &uring_locked); cond_resched(); + + if (data_race(!tctx->task_list.first) && + data_race(!tctx->prio_task_list.first) && uring_locked) + io_submit_flush_completions(ctx); } ctx_flush_and_put(ctx, &uring_locked); @@ -2551,22 +2979,19 @@ static void tctx_task_work(struct callback_head *cb) io_uring_drop_tctx_refs(current); } -static void io_req_task_work_add(struct io_kiocb *req, bool priority) +static void __io_req_task_work_add(struct io_kiocb *req, + struct io_uring_task *tctx, + struct io_wq_work_list *list) { - struct task_struct *tsk = req->task; - struct io_uring_task *tctx = tsk->io_uring; - enum task_work_notify_mode notify; + struct io_ring_ctx *ctx = req->ctx; struct io_wq_work_node *node; unsigned long flags; bool running; - WARN_ON_ONCE(!tctx); + io_drop_inflight_file(req); spin_lock_irqsave(&tctx->task_lock, flags); - if (priority) - wq_list_add_tail(&req->io_task_work.node, &tctx->prior_task_list); - else - wq_list_add_tail(&req->io_task_work.node, &tctx->task_list); + wq_list_add_tail(&req->io_task_work.node, list); running = tctx->task_running; if (!running) tctx->task_running = true; @@ -2576,22 +3001,15 @@ static void io_req_task_work_add(struct io_kiocb *req, bool priority) if (running) return; - /* - * SQPOLL kernel thread doesn't need notification, just a wakeup. For - * all other cases, use TWA_SIGNAL unconditionally to ensure we're - * processing task_work. There's no reliable way to tell if TWA_RESUME - * will do the job. - */ - notify = (req->ctx->flags & IORING_SETUP_SQPOLL) ? TWA_NONE : TWA_SIGNAL; - if (likely(!task_work_add(tsk, &tctx->task_work, notify))) { - if (notify == TWA_NONE) - wake_up_process(tsk); + if (ctx->flags & IORING_SETUP_TASKRUN_FLAG) + atomic_or(IORING_SQ_TASKRUN, &ctx->rings->sq_flags); + + if (likely(!task_work_add(req->task, &tctx->task_work, ctx->notify_method))) return; - } spin_lock_irqsave(&tctx->task_lock, flags); tctx->task_running = false; - node = wq_list_merge(&tctx->prior_task_list, &tctx->task_list); + node = wq_list_merge(&tctx->prio_task_list, &tctx->task_list); spin_unlock_irqrestore(&tctx->task_lock, flags); while (node) { @@ -2603,47 +3021,73 @@ static void io_req_task_work_add(struct io_kiocb *req, bool priority) } } -static void io_req_task_cancel(struct io_kiocb *req, bool *locked) +static void io_req_task_work_add(struct io_kiocb *req) { - struct io_ring_ctx *ctx = req->ctx; + struct io_uring_task *tctx = req->task->io_uring; + + __io_req_task_work_add(req, tctx, &tctx->task_list); +} + +static void io_req_task_prio_work_add(struct io_kiocb *req) +{ + struct io_uring_task *tctx = req->task->io_uring; + + if (req->ctx->flags & IORING_SETUP_SQPOLL) + __io_req_task_work_add(req, tctx, &tctx->prio_task_list); + else + __io_req_task_work_add(req, tctx, &tctx->task_list); +} + +static void io_req_tw_post(struct io_kiocb *req, bool *locked) +{ + io_req_complete_post(req, req->cqe.res, req->cqe.flags); +} +static void io_req_tw_post_queue(struct io_kiocb *req, s32 res, u32 cflags) +{ + req->cqe.res = res; + req->cqe.flags = cflags; + req->io_task_work.func = io_req_tw_post; + io_req_task_work_add(req); +} + +static void io_req_task_cancel(struct io_kiocb *req, bool *locked) +{ /* not needed for normal modes, but SQPOLL depends on it */ - io_tw_lock(ctx, locked); - io_req_complete_failed(req, req->result); + io_tw_lock(req->ctx, locked); + io_req_complete_failed(req, req->cqe.res); } static void io_req_task_submit(struct io_kiocb *req, bool *locked) { - struct io_ring_ctx *ctx = req->ctx; - - io_tw_lock(ctx, locked); + io_tw_lock(req->ctx, locked); /* req->task == current here, checking PF_EXITING is safe */ if (likely(!(req->task->flags & PF_EXITING))) - __io_queue_sqe(req); + io_queue_sqe(req); else io_req_complete_failed(req, -EFAULT); } static void io_req_task_queue_fail(struct io_kiocb *req, int ret) { - req->result = ret; + req->cqe.res = ret; req->io_task_work.func = io_req_task_cancel; - io_req_task_work_add(req, false); + io_req_task_work_add(req); } static void io_req_task_queue(struct io_kiocb *req) { req->io_task_work.func = io_req_task_submit; - io_req_task_work_add(req, false); + io_req_task_work_add(req); } static void io_req_task_queue_reissue(struct io_kiocb *req) { - req->io_task_work.func = io_queue_async_work; - io_req_task_work_add(req, false); + req->io_task_work.func = io_queue_iowq; + io_req_task_work_add(req); } -static inline void io_queue_next(struct io_kiocb *req) +static void io_queue_next(struct io_kiocb *req) { struct io_kiocb *nxt = io_req_find_next(req); @@ -2651,17 +3095,6 @@ static inline void io_queue_next(struct io_kiocb *req) io_req_task_queue(nxt); } -static void io_free_req(struct io_kiocb *req) -{ - io_queue_next(req); - __io_free_req(req); -} - -static void io_free_req_work(struct io_kiocb *req, bool *locked) -{ - io_free_req(req); -} - static void io_free_batch_list(struct io_ring_ctx *ctx, struct io_wq_work_node *node) __must_hold(&ctx->uring_lock) @@ -2673,15 +3106,30 @@ static void io_free_batch_list(struct io_ring_ctx *ctx, struct io_kiocb *req = container_of(node, struct io_kiocb, comp_list); - if (unlikely(req->flags & REQ_F_REFCOUNT)) { - node = req->comp_list.next; - if (!req_ref_put_and_test(req)) - continue; + if (unlikely(req->flags & IO_REQ_CLEAN_SLOW_FLAGS)) { + if (req->flags & REQ_F_REFCOUNT) { + node = req->comp_list.next; + if (!req_ref_put_and_test(req)) + continue; + } + if ((req->flags & REQ_F_POLLED) && req->apoll) { + struct async_poll *apoll = req->apoll; + + if (apoll->double_poll) + kfree(apoll->double_poll); + list_add(&apoll->poll.wait.entry, + &ctx->apoll_cache); + req->flags &= ~REQ_F_POLLED; + } + if (req->flags & IO_REQ_LINK_FLAGS) + io_queue_next(req); + if (unlikely(req->flags & IO_REQ_CLEAN_FLAGS)) + io_clean_op(req); } + if (!(req->flags & REQ_F_FIXED_FILE)) + io_put_file(req->file); io_req_put_rsrc_locked(req, ctx); - io_queue_next(req); - io_dismantle_req(req); if (req->task != task) { if (task) @@ -2691,7 +3139,7 @@ static void io_free_batch_list(struct io_ring_ctx *ctx, } task_refs++; node = req->comp_list.next; - wq_stack_add_head(&req->comp_list, &ctx->submit_state.free_list); + io_req_add_to_cache(req, ctx); } while (node); if (task) @@ -2710,16 +3158,11 @@ static void __io_submit_flush_completions(struct io_ring_ctx *ctx) struct io_kiocb *req = container_of(node, struct io_kiocb, comp_list); - if (!(req->flags & REQ_F_CQE_SKIP)) - __io_fill_cqe_req(req, req->result, req->cflags); - if ((req->flags & REQ_F_POLLED) && req->apoll) { - struct async_poll *apoll = req->apoll; - - if (apoll->double_poll) - kfree(apoll->double_poll); - list_add(&apoll->poll.wait.entry, - &ctx->apoll_cache); - req->flags &= ~REQ_F_POLLED; + if (!(req->flags & REQ_F_CQE_SKIP)) { + if (!(ctx->flags & IORING_SETUP_CQE32)) + __io_fill_cqe_req_filled(ctx, req); + else + __io_fill_cqe32_req_filled(ctx, req); } } @@ -2742,23 +3185,18 @@ static inline struct io_kiocb *io_put_req_find_next(struct io_kiocb *req) struct io_kiocb *nxt = NULL; if (req_ref_put_and_test(req)) { - nxt = io_req_find_next(req); - __io_free_req(req); + if (unlikely(req->flags & IO_REQ_LINK_FLAGS)) + nxt = io_req_find_next(req); + io_free_req(req); } return nxt; } static inline void io_put_req(struct io_kiocb *req) { - if (req_ref_put_and_test(req)) - io_free_req(req); -} - -static inline void io_put_req_deferred(struct io_kiocb *req) -{ if (req_ref_put_and_test(req)) { - req->io_task_work.func = io_free_req_work; - io_req_task_work_add(req, false); + io_queue_next(req); + io_free_req(req); } } @@ -2841,11 +3279,10 @@ static int io_do_iopoll(struct io_ring_ctx *ctx, bool force_nonspin) /* order with io_complete_rw_iopoll(), e.g. ->result updates */ if (!smp_load_acquire(&req->iopoll_completed)) break; + nr_events++; if (unlikely(req->flags & REQ_F_CQE_SKIP)) continue; - - __io_fill_cqe_req(req, req->result, io_put_kbuf(req, 0)); - nr_events++; + __io_fill_cqe_req(req, req->cqe.res, io_put_kbuf(req, 0)); } if (unlikely(!nr_events)) @@ -2891,22 +3328,26 @@ static int io_iopoll_check(struct io_ring_ctx *ctx, long min) { unsigned int nr_events = 0; int ret = 0; + unsigned long check_cq; /* - * We disallow the app entering submit/complete with polling, but we - * still need to lock the ring to prevent racing with polled issue - * that got punted to a workqueue. - */ - mutex_lock(&ctx->uring_lock); - /* * Don't enter poll loop if we already have events pending. * If we do, we can potentially be spinning for commands that * already triggered a CQE (eg in error). */ - if (test_bit(0, &ctx->check_cq_overflow)) + check_cq = READ_ONCE(ctx->check_cq); + if (check_cq & BIT(IO_CHECK_CQ_OVERFLOW_BIT)) __io_cqring_overflow_flush(ctx, false); if (io_cqring_events(ctx)) - goto out; + return 0; + + /* + * Similarly do not spin if we have not informed the user of any + * dropped CQE. + */ + if (unlikely(check_cq & BIT(IO_CHECK_CQ_DROPPED_BIT))) + return -EBADR; + do { /* * If a submit got punted to a workqueue, we can have the @@ -2936,8 +3377,7 @@ static int io_iopoll_check(struct io_ring_ctx *ctx, long min) nr_events += ret; ret = 0; } while (nr_events < min && !need_resched()); -out: - mutex_unlock(&ctx->uring_lock); + return ret; } @@ -3010,21 +3450,21 @@ static bool __io_complete_rw_common(struct io_kiocb *req, long res) } else { fsnotify_access(req->file); } - if (unlikely(res != req->result)) { + if (unlikely(res != req->cqe.res)) { if ((res == -EAGAIN || res == -EOPNOTSUPP) && io_rw_should_reissue(req)) { req->flags |= REQ_F_REISSUE; return true; } req_set_fail(req); - req->result = res; + req->cqe.res = res; } return false; } static inline void io_req_task_complete(struct io_kiocb *req, bool *locked) { - int res = req->result; + int res = req->cqe.res; if (*locked) { io_req_complete_state(req, res, io_put_kbuf(req, 0)); @@ -3040,7 +3480,7 @@ static void __io_complete_rw(struct io_kiocb *req, long res, { if (__io_complete_rw_common(req, res)) return; - __io_req_complete(req, issue_flags, req->result, + __io_req_complete(req, issue_flags, req->cqe.res, io_put_kbuf(req, issue_flags)); } @@ -3050,9 +3490,9 @@ static void io_complete_rw(struct kiocb *kiocb, long res) if (__io_complete_rw_common(req, res)) return; - req->result = res; + req->cqe.res = res; req->io_task_work.func = io_req_task_complete; - io_req_task_work_add(req, !!(req->ctx->flags & IORING_SETUP_SQPOLL)); + io_req_task_prio_work_add(req); } static void io_complete_rw_iopoll(struct kiocb *kiocb, long res) @@ -3061,12 +3501,12 @@ static void io_complete_rw_iopoll(struct kiocb *kiocb, long res) if (kiocb->ki_flags & IOCB_WRITE) kiocb_end_write(req); - if (unlikely(res != req->result)) { + if (unlikely(res != req->cqe.res)) { if (res == -EAGAIN && io_rw_should_reissue(req)) { req->flags |= REQ_F_REISSUE; return; } - req->result = res; + req->cqe.res = res; } /* order with io_iopoll_complete() checking ->iopoll_completed */ @@ -3176,6 +3616,8 @@ static unsigned int io_file_get_flags(struct file *file) res |= FFS_ISREG; if (__io_file_supports_nowait(file, mode)) res |= FFS_NOWAIT; + if (io_file_need_scm(file)) + res |= FFS_SCM; return res; } @@ -3186,42 +3628,11 @@ static inline bool io_file_supports_nowait(struct io_kiocb *req) static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe) { - struct io_ring_ctx *ctx = req->ctx; struct kiocb *kiocb = &req->rw.kiocb; - struct file *file = req->file; unsigned ioprio; int ret; - if (!io_req_ffs_set(req)) - req->flags |= io_file_get_flags(file) << REQ_F_SUPPORT_NOWAIT_BIT; - kiocb->ki_pos = READ_ONCE(sqe->off); - kiocb->ki_flags = iocb_flags(file); - ret = kiocb_set_rw_flags(kiocb, READ_ONCE(sqe->rw_flags)); - if (unlikely(ret)) - return ret; - - /* - * If the file is marked O_NONBLOCK, still allow retry for it if it - * supports async. Otherwise it's impossible to use O_NONBLOCK files - * reliably. If not, or it IOCB_NOWAIT is set, don't retry. - */ - if ((kiocb->ki_flags & IOCB_NOWAIT) || - ((file->f_flags & O_NONBLOCK) && !io_file_supports_nowait(req))) - req->flags |= REQ_F_NOWAIT; - - if (ctx->flags & IORING_SETUP_IOPOLL) { - if (!(kiocb->ki_flags & IOCB_DIRECT) || !file->f_op->iopoll) - return -EOPNOTSUPP; - - kiocb->ki_flags |= IOCB_HIPRI | IOCB_ALLOC_CACHE; - kiocb->ki_complete = io_complete_rw_iopoll; - req->iopoll_completed = 0; - } else { - if (kiocb->ki_flags & IOCB_HIPRI) - return -EINVAL; - kiocb->ki_complete = io_complete_rw; - } ioprio = READ_ONCE(sqe->ioprio); if (ioprio) { @@ -3237,6 +3648,8 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe) req->imu = NULL; req->rw.addr = READ_ONCE(sqe->addr); req->rw.len = READ_ONCE(sqe->len); + req->rw.flags = READ_ONCE(sqe->rw_flags); + /* used for fixed read/write too - just read unconditionally */ req->buf_index = READ_ONCE(sqe->buf_index); return 0; } @@ -3265,19 +3678,18 @@ static inline void io_rw_done(struct kiocb *kiocb, ssize_t ret) static inline loff_t *io_kiocb_update_pos(struct io_kiocb *req) { struct kiocb *kiocb = &req->rw.kiocb; - bool is_stream = req->file->f_mode & FMODE_STREAM; - if (kiocb->ki_pos == -1) { - if (!is_stream) { - req->flags |= REQ_F_CUR_POS; - kiocb->ki_pos = req->file->f_pos; - return &kiocb->ki_pos; - } else { - kiocb->ki_pos = 0; - return NULL; - } + if (kiocb->ki_pos != -1) + return &kiocb->ki_pos; + + if (!(req->file->f_mode & FMODE_STREAM)) { + req->flags |= REQ_F_CUR_POS; + kiocb->ki_pos = req->file->f_pos; + return &kiocb->ki_pos; } - return is_stream ? NULL : &kiocb->ki_pos; + + kiocb->ki_pos = 0; + return NULL; } static void kiocb_done(struct io_kiocb *req, ssize_t ret, @@ -3367,7 +3779,8 @@ static int __io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter return 0; } -static int io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter) +static int io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter, + unsigned int issue_flags) { struct io_mapped_ubuf *imu = req->imu; u16 index, buf_index = req->buf_index; @@ -3377,7 +3790,7 @@ static int io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter) if (unlikely(buf_index >= ctx->nr_user_bufs)) return -EFAULT; - io_req_set_rsrc_node(req, ctx); + io_req_set_rsrc_node(req, ctx, issue_flags); index = array_index_nospec(buf_index, ctx->nr_user_bufs); imu = READ_ONCE(ctx->user_bufs[index]); req->imu = imu; @@ -3385,77 +3798,96 @@ static int io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter) return __io_import_fixed(req, rw, iter, imu); } -static void io_ring_submit_unlock(struct io_ring_ctx *ctx, bool needs_lock) +static int io_buffer_add_list(struct io_ring_ctx *ctx, + struct io_buffer_list *bl, unsigned int bgid) { - if (needs_lock) - mutex_unlock(&ctx->uring_lock); -} - -static void io_ring_submit_lock(struct io_ring_ctx *ctx, bool needs_lock) -{ - /* - * "Normal" inline submissions always hold the uring_lock, since we - * grab it from the system call. Same is true for the SQPOLL offload. - * The only exception is when we've detached the request and issue it - * from an async worker thread, grab the lock for that case. - */ - if (needs_lock) - mutex_lock(&ctx->uring_lock); -} - -static void io_buffer_add_list(struct io_ring_ctx *ctx, - struct io_buffer_list *bl, unsigned int bgid) -{ - struct list_head *list; - - list = &ctx->io_buffers[hash_32(bgid, IO_BUFFERS_HASH_BITS)]; - INIT_LIST_HEAD(&bl->buf_list); bl->bgid = bgid; - list_add(&bl->list, list); + if (bgid < BGID_ARRAY) + return 0; + + return xa_err(xa_store(&ctx->io_bl_xa, bgid, bl, GFP_KERNEL)); } -static struct io_buffer *io_buffer_select(struct io_kiocb *req, size_t *len, - int bgid, unsigned int issue_flags) +static void __user *io_provided_buffer_select(struct io_kiocb *req, size_t *len, + struct io_buffer_list *bl) { - struct io_buffer *kbuf = req->kbuf; - bool needs_lock = issue_flags & IO_URING_F_UNLOCKED; - struct io_ring_ctx *ctx = req->ctx; - struct io_buffer_list *bl; - - if (req->flags & REQ_F_BUFFER_SELECTED) - return kbuf; - - io_ring_submit_lock(ctx, needs_lock); + if (!list_empty(&bl->buf_list)) { + struct io_buffer *kbuf; - lockdep_assert_held(&ctx->uring_lock); - - bl = io_buffer_get_list(ctx, bgid); - if (bl && !list_empty(&bl->buf_list)) { kbuf = list_first_entry(&bl->buf_list, struct io_buffer, list); list_del(&kbuf->list); if (*len > kbuf->len) *len = kbuf->len; req->flags |= REQ_F_BUFFER_SELECTED; req->kbuf = kbuf; + req->buf_index = kbuf->bid; + return u64_to_user_ptr(kbuf->addr); + } + return NULL; +} + +static void __user *io_ring_buffer_select(struct io_kiocb *req, size_t *len, + struct io_buffer_list *bl, + unsigned int issue_flags) +{ + struct io_uring_buf_ring *br = bl->buf_ring; + struct io_uring_buf *buf; + __u32 head = bl->head; + + if (unlikely(smp_load_acquire(&br->tail) == head)) { + io_ring_submit_unlock(req->ctx, issue_flags); + return NULL; + } + + head &= bl->mask; + if (head < IO_BUFFER_LIST_BUF_PER_PAGE) { + buf = &br->bufs[head]; } else { - kbuf = ERR_PTR(-ENOBUFS); + int off = head & (IO_BUFFER_LIST_BUF_PER_PAGE - 1); + int index = head / IO_BUFFER_LIST_BUF_PER_PAGE - 1; + buf = page_address(bl->buf_pages[index]); + buf += off; } + if (*len > buf->len) + *len = buf->len; + req->flags |= REQ_F_BUFFER_RING; + req->buf_list = bl; + req->buf_index = buf->bid; - io_ring_submit_unlock(req->ctx, needs_lock); - return kbuf; + if (issue_flags & IO_URING_F_UNLOCKED) { + /* + * If we came in unlocked, we have no choice but to consume the + * buffer here. This does mean it'll be pinned until the IO + * completes. But coming in unlocked means we're in io-wq + * context, hence there should be no further retry. For the + * locked case, the caller must ensure to call the commit when + * the transfer completes (or if we get -EAGAIN and must poll + * or retry). + */ + req->buf_list = NULL; + bl->head++; + } + return u64_to_user_ptr(buf->addr); } -static void __user *io_rw_buffer_select(struct io_kiocb *req, size_t *len, - unsigned int issue_flags) +static void __user *io_buffer_select(struct io_kiocb *req, size_t *len, + unsigned int issue_flags) { - struct io_buffer *kbuf; - u16 bgid; + struct io_ring_ctx *ctx = req->ctx; + struct io_buffer_list *bl; + void __user *ret = NULL; - bgid = req->buf_index; - kbuf = io_buffer_select(req, len, bgid, issue_flags); - if (IS_ERR(kbuf)) - return kbuf; - return u64_to_user_ptr(kbuf->addr); + io_ring_submit_lock(req->ctx, issue_flags); + + bl = io_buffer_get_list(ctx, req->buf_index); + if (likely(bl)) { + if (bl->buf_nr_pages) + ret = io_ring_buffer_select(req, len, bl, issue_flags); + else + ret = io_provided_buffer_select(req, len, bl); + } + io_ring_submit_unlock(req->ctx, issue_flags); + return ret; } #ifdef CONFIG_COMPAT @@ -3465,7 +3897,7 @@ static ssize_t io_compat_import(struct io_kiocb *req, struct iovec *iov, struct compat_iovec __user *uiov; compat_ssize_t clen; void __user *buf; - ssize_t len; + size_t len; uiov = u64_to_user_ptr(req->rw.addr); if (!access_ok(uiov, sizeof(*uiov))) @@ -3476,11 +3908,12 @@ static ssize_t io_compat_import(struct io_kiocb *req, struct iovec *iov, return -EINVAL; len = clen; - buf = io_rw_buffer_select(req, &len, issue_flags); - if (IS_ERR(buf)) - return PTR_ERR(buf); + buf = io_buffer_select(req, &len, issue_flags); + if (!buf) + return -ENOBUFS; + req->rw.addr = (unsigned long) buf; iov[0].iov_base = buf; - iov[0].iov_len = (compat_size_t) len; + req->rw.len = iov[0].iov_len = (compat_size_t) len; return 0; } #endif @@ -3498,22 +3931,21 @@ static ssize_t __io_iov_buffer_select(struct io_kiocb *req, struct iovec *iov, len = iov[0].iov_len; if (len < 0) return -EINVAL; - buf = io_rw_buffer_select(req, &len, issue_flags); - if (IS_ERR(buf)) - return PTR_ERR(buf); + buf = io_buffer_select(req, &len, issue_flags); + if (!buf) + return -ENOBUFS; + req->rw.addr = (unsigned long) buf; iov[0].iov_base = buf; - iov[0].iov_len = len; + req->rw.len = iov[0].iov_len = len; return 0; } static ssize_t io_iov_buffer_select(struct io_kiocb *req, struct iovec *iov, unsigned int issue_flags) { - if (req->flags & REQ_F_BUFFER_SELECTED) { - struct io_buffer *kbuf = req->kbuf; - - iov[0].iov_base = u64_to_user_ptr(kbuf->addr); - iov[0].iov_len = kbuf->len; + if (req->flags & (REQ_F_BUFFER_SELECTED|REQ_F_BUFFER_RING)) { + iov[0].iov_base = u64_to_user_ptr(req->rw.addr); + iov[0].iov_len = req->rw.len; return 0; } if (req->rw.len != 1) @@ -3527,6 +3959,13 @@ static ssize_t io_iov_buffer_select(struct io_kiocb *req, struct iovec *iov, return __io_iov_buffer_select(req, iov, issue_flags); } +static inline bool io_do_buffer_select(struct io_kiocb *req) +{ + if (!(req->flags & REQ_F_BUFFER_SELECT)) + return false; + return !(req->flags & (REQ_F_BUFFER_SELECTED|REQ_F_BUFFER_RING)); +} + static struct iovec *__io_import_iovec(int rw, struct io_kiocb *req, struct io_rw_state *s, unsigned int issue_flags) @@ -3539,24 +3978,21 @@ static struct iovec *__io_import_iovec(int rw, struct io_kiocb *req, ssize_t ret; if (opcode == IORING_OP_READ_FIXED || opcode == IORING_OP_WRITE_FIXED) { - ret = io_import_fixed(req, rw, iter); + ret = io_import_fixed(req, rw, iter, issue_flags); if (ret) return ERR_PTR(ret); return NULL; } - /* buffer index only valid with fixed read/write, or buffer select */ - if (unlikely(req->buf_index && !(req->flags & REQ_F_BUFFER_SELECT))) - return ERR_PTR(-EINVAL); - buf = u64_to_user_ptr(req->rw.addr); sqe_len = req->rw.len; if (opcode == IORING_OP_READ || opcode == IORING_OP_WRITE) { - if (req->flags & REQ_F_BUFFER_SELECT) { - buf = io_rw_buffer_select(req, &sqe_len, issue_flags); - if (IS_ERR(buf)) - return ERR_CAST(buf); + if (io_do_buffer_select(req)) { + buf = io_buffer_select(req, &sqe_len, issue_flags); + if (!buf) + return ERR_PTR(-ENOBUFS); + req->rw.addr = (unsigned long) buf; req->rw.len = sqe_len; } @@ -3740,13 +4176,6 @@ static inline int io_rw_prep_async(struct io_kiocb *req, int rw) return 0; } -static int io_read_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) -{ - if (unlikely(!(req->file->f_mode & FMODE_READ))) - return -EBADF; - return io_prep_rw(req, sqe); -} - /* * This is our waitqueue callback handler, registered through __folio_lock_async() * when we initially tried to do the IO with the iocb armed our waitqueue. @@ -3834,6 +4263,50 @@ static bool need_read_all(struct io_kiocb *req) S_ISBLK(file_inode(req->file)->i_mode); } +static int io_rw_init_file(struct io_kiocb *req, fmode_t mode) +{ + struct kiocb *kiocb = &req->rw.kiocb; + struct io_ring_ctx *ctx = req->ctx; + struct file *file = req->file; + int ret; + + if (unlikely(!file || !(file->f_mode & mode))) + return -EBADF; + + if (!io_req_ffs_set(req)) + req->flags |= io_file_get_flags(file) << REQ_F_SUPPORT_NOWAIT_BIT; + + kiocb->ki_flags = iocb_flags(file); + ret = kiocb_set_rw_flags(kiocb, req->rw.flags); + if (unlikely(ret)) + return ret; + + /* + * If the file is marked O_NONBLOCK, still allow retry for it if it + * supports async. Otherwise it's impossible to use O_NONBLOCK files + * reliably. If not, or it IOCB_NOWAIT is set, don't retry. + */ + if ((kiocb->ki_flags & IOCB_NOWAIT) || + ((file->f_flags & O_NONBLOCK) && !io_file_supports_nowait(req))) + req->flags |= REQ_F_NOWAIT; + + if (ctx->flags & IORING_SETUP_IOPOLL) { + if (!(kiocb->ki_flags & IOCB_DIRECT) || !file->f_op->iopoll) + return -EOPNOTSUPP; + + kiocb->private = NULL; + kiocb->ki_flags |= IOCB_HIPRI | IOCB_ALLOC_CACHE; + kiocb->ki_complete = io_complete_rw_iopoll; + req->iopoll_completed = 0; + } else { + if (kiocb->ki_flags & IOCB_HIPRI) + return -EINVAL; + kiocb->ki_complete = io_complete_rw; + } + + return 0; +} + static int io_read(struct io_kiocb *req, unsigned int issue_flags) { struct io_rw_state __s, *s = &__s; @@ -3869,7 +4342,12 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags) iov_iter_restore(&s->iter, &s->iter_state); iovec = NULL; } - req->result = iov_iter_count(&s->iter); + ret = io_rw_init_file(req, FMODE_READ); + if (unlikely(ret)) { + kfree(iovec); + return ret; + } + req->cqe.res = iov_iter_count(&s->iter); if (force_nonblock) { /* If the file doesn't support async, just async punt */ @@ -3885,7 +4363,7 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags) ppos = io_kiocb_update_pos(req); - ret = rw_verify_area(READ, req->file, ppos, req->result); + ret = rw_verify_area(READ, req->file, ppos, req->cqe.res); if (unlikely(ret)) { kfree(iovec); return ret; @@ -3907,7 +4385,7 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags) ret = 0; } else if (ret == -EIOCBQUEUED) { goto out_free; - } else if (ret == req->result || ret <= 0 || !force_nonblock || + } else if (ret == req->cqe.res || ret <= 0 || !force_nonblock || (req->flags & REQ_F_NOWAIT) || !need_read_all(req)) { /* read all, failed, already did sync or don't want to retry */ goto done; @@ -3972,13 +4450,6 @@ out_free: return 0; } -static int io_write_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) -{ - if (unlikely(!(req->file->f_mode & FMODE_WRITE))) - return -EBADF; - return io_prep_rw(req, sqe); -} - static int io_write(struct io_kiocb *req, unsigned int issue_flags) { struct io_rw_state __s, *s = &__s; @@ -3999,7 +4470,12 @@ static int io_write(struct io_kiocb *req, unsigned int issue_flags) iov_iter_restore(&s->iter, &s->iter_state); iovec = NULL; } - req->result = iov_iter_count(&s->iter); + ret = io_rw_init_file(req, FMODE_WRITE); + if (unlikely(ret)) { + kfree(iovec); + return ret; + } + req->cqe.res = iov_iter_count(&s->iter); if (force_nonblock) { /* If the file doesn't support async, just async punt */ @@ -4019,7 +4495,7 @@ static int io_write(struct io_kiocb *req, unsigned int issue_flags) ppos = io_kiocb_update_pos(req); - ret = rw_verify_area(WRITE, req->file, ppos, req->result); + ret = rw_verify_area(WRITE, req->file, ppos, req->cqe.res); if (unlikely(ret)) goto out_free; @@ -4083,9 +4559,7 @@ static int io_renameat_prep(struct io_kiocb *req, struct io_rename *ren = &req->rename; const char __user *oldf, *newf; - if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) - return -EINVAL; - if (sqe->ioprio || sqe->buf_index || sqe->splice_fd_in) + if (sqe->buf_index || sqe->splice_fd_in) return -EINVAL; if (unlikely(req->flags & REQ_F_FIXED_FILE)) return -EBADF; @@ -4122,22 +4596,257 @@ static int io_renameat(struct io_kiocb *req, unsigned int issue_flags) ren->newpath, ren->flags); req->flags &= ~REQ_F_NEED_CLEANUP; - if (ret < 0) - req_set_fail(req); io_req_complete(req, ret); return 0; } +static inline void __io_xattr_finish(struct io_kiocb *req) +{ + struct io_xattr *ix = &req->xattr; + + if (ix->filename) + putname(ix->filename); + + kfree(ix->ctx.kname); + kvfree(ix->ctx.kvalue); +} + +static void io_xattr_finish(struct io_kiocb *req, int ret) +{ + req->flags &= ~REQ_F_NEED_CLEANUP; + + __io_xattr_finish(req); + io_req_complete(req, ret); +} + +static int __io_getxattr_prep(struct io_kiocb *req, + const struct io_uring_sqe *sqe) +{ + struct io_xattr *ix = &req->xattr; + const char __user *name; + int ret; + + if (unlikely(req->flags & REQ_F_FIXED_FILE)) + return -EBADF; + + ix->filename = NULL; + ix->ctx.kvalue = NULL; + name = u64_to_user_ptr(READ_ONCE(sqe->addr)); + ix->ctx.cvalue = u64_to_user_ptr(READ_ONCE(sqe->addr2)); + ix->ctx.size = READ_ONCE(sqe->len); + ix->ctx.flags = READ_ONCE(sqe->xattr_flags); + + if (ix->ctx.flags) + return -EINVAL; + + ix->ctx.kname = kmalloc(sizeof(*ix->ctx.kname), GFP_KERNEL); + if (!ix->ctx.kname) + return -ENOMEM; + + ret = strncpy_from_user(ix->ctx.kname->name, name, + sizeof(ix->ctx.kname->name)); + if (!ret || ret == sizeof(ix->ctx.kname->name)) + ret = -ERANGE; + if (ret < 0) { + kfree(ix->ctx.kname); + return ret; + } + + req->flags |= REQ_F_NEED_CLEANUP; + return 0; +} + +static int io_fgetxattr_prep(struct io_kiocb *req, + const struct io_uring_sqe *sqe) +{ + return __io_getxattr_prep(req, sqe); +} + +static int io_getxattr_prep(struct io_kiocb *req, + const struct io_uring_sqe *sqe) +{ + struct io_xattr *ix = &req->xattr; + const char __user *path; + int ret; + + ret = __io_getxattr_prep(req, sqe); + if (ret) + return ret; + + path = u64_to_user_ptr(READ_ONCE(sqe->addr3)); + + ix->filename = getname_flags(path, LOOKUP_FOLLOW, NULL); + if (IS_ERR(ix->filename)) { + ret = PTR_ERR(ix->filename); + ix->filename = NULL; + } + + return ret; +} + +static int io_fgetxattr(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_xattr *ix = &req->xattr; + int ret; + + if (issue_flags & IO_URING_F_NONBLOCK) + return -EAGAIN; + + ret = do_getxattr(mnt_user_ns(req->file->f_path.mnt), + req->file->f_path.dentry, + &ix->ctx); + + io_xattr_finish(req, ret); + return 0; +} + +static int io_getxattr(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_xattr *ix = &req->xattr; + unsigned int lookup_flags = LOOKUP_FOLLOW; + struct path path; + int ret; + + if (issue_flags & IO_URING_F_NONBLOCK) + return -EAGAIN; + +retry: + ret = filename_lookup(AT_FDCWD, ix->filename, lookup_flags, &path, NULL); + if (!ret) { + ret = do_getxattr(mnt_user_ns(path.mnt), + path.dentry, + &ix->ctx); + + path_put(&path); + if (retry_estale(ret, lookup_flags)) { + lookup_flags |= LOOKUP_REVAL; + goto retry; + } + } + + io_xattr_finish(req, ret); + return 0; +} + +static int __io_setxattr_prep(struct io_kiocb *req, + const struct io_uring_sqe *sqe) +{ + struct io_xattr *ix = &req->xattr; + const char __user *name; + int ret; + + if (unlikely(req->flags & REQ_F_FIXED_FILE)) + return -EBADF; + + ix->filename = NULL; + name = u64_to_user_ptr(READ_ONCE(sqe->addr)); + ix->ctx.cvalue = u64_to_user_ptr(READ_ONCE(sqe->addr2)); + ix->ctx.kvalue = NULL; + ix->ctx.size = READ_ONCE(sqe->len); + ix->ctx.flags = READ_ONCE(sqe->xattr_flags); + + ix->ctx.kname = kmalloc(sizeof(*ix->ctx.kname), GFP_KERNEL); + if (!ix->ctx.kname) + return -ENOMEM; + + ret = setxattr_copy(name, &ix->ctx); + if (ret) { + kfree(ix->ctx.kname); + return ret; + } + + req->flags |= REQ_F_NEED_CLEANUP; + return 0; +} + +static int io_setxattr_prep(struct io_kiocb *req, + const struct io_uring_sqe *sqe) +{ + struct io_xattr *ix = &req->xattr; + const char __user *path; + int ret; + + ret = __io_setxattr_prep(req, sqe); + if (ret) + return ret; + + path = u64_to_user_ptr(READ_ONCE(sqe->addr3)); + + ix->filename = getname_flags(path, LOOKUP_FOLLOW, NULL); + if (IS_ERR(ix->filename)) { + ret = PTR_ERR(ix->filename); + ix->filename = NULL; + } + + return ret; +} + +static int io_fsetxattr_prep(struct io_kiocb *req, + const struct io_uring_sqe *sqe) +{ + return __io_setxattr_prep(req, sqe); +} + +static int __io_setxattr(struct io_kiocb *req, unsigned int issue_flags, + struct path *path) +{ + struct io_xattr *ix = &req->xattr; + int ret; + + ret = mnt_want_write(path->mnt); + if (!ret) { + ret = do_setxattr(mnt_user_ns(path->mnt), path->dentry, &ix->ctx); + mnt_drop_write(path->mnt); + } + + return ret; +} + +static int io_fsetxattr(struct io_kiocb *req, unsigned int issue_flags) +{ + int ret; + + if (issue_flags & IO_URING_F_NONBLOCK) + return -EAGAIN; + + ret = __io_setxattr(req, issue_flags, &req->file->f_path); + io_xattr_finish(req, ret); + + return 0; +} + +static int io_setxattr(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_xattr *ix = &req->xattr; + unsigned int lookup_flags = LOOKUP_FOLLOW; + struct path path; + int ret; + + if (issue_flags & IO_URING_F_NONBLOCK) + return -EAGAIN; + +retry: + ret = filename_lookup(AT_FDCWD, ix->filename, lookup_flags, &path, NULL); + if (!ret) { + ret = __io_setxattr(req, issue_flags, &path); + path_put(&path); + if (retry_estale(ret, lookup_flags)) { + lookup_flags |= LOOKUP_REVAL; + goto retry; + } + } + + io_xattr_finish(req, ret); + return 0; +} + static int io_unlinkat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_unlink *un = &req->unlink; const char __user *fname; - if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) - return -EINVAL; - if (sqe->ioprio || sqe->off || sqe->len || sqe->buf_index || - sqe->splice_fd_in) + if (sqe->off || sqe->len || sqe->buf_index || sqe->splice_fd_in) return -EINVAL; if (unlikely(req->flags & REQ_F_FIXED_FILE)) return -EBADF; @@ -4171,8 +4880,6 @@ static int io_unlinkat(struct io_kiocb *req, unsigned int issue_flags) ret = do_unlinkat(un->dfd, un->filename); req->flags &= ~REQ_F_NEED_CLEANUP; - if (ret < 0) - req_set_fail(req); io_req_complete(req, ret); return 0; } @@ -4183,10 +4890,7 @@ static int io_mkdirat_prep(struct io_kiocb *req, struct io_mkdir *mkd = &req->mkdir; const char __user *fname; - if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) - return -EINVAL; - if (sqe->ioprio || sqe->off || sqe->rw_flags || sqe->buf_index || - sqe->splice_fd_in) + if (sqe->off || sqe->rw_flags || sqe->buf_index || sqe->splice_fd_in) return -EINVAL; if (unlikely(req->flags & REQ_F_FIXED_FILE)) return -EBADF; @@ -4214,8 +4918,6 @@ static int io_mkdirat(struct io_kiocb *req, unsigned int issue_flags) ret = do_mkdirat(mkd->dfd, mkd->filename, mkd->mode); req->flags &= ~REQ_F_NEED_CLEANUP; - if (ret < 0) - req_set_fail(req); io_req_complete(req, ret); return 0; } @@ -4226,10 +4928,7 @@ static int io_symlinkat_prep(struct io_kiocb *req, struct io_symlink *sl = &req->symlink; const char __user *oldpath, *newpath; - if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) - return -EINVAL; - if (sqe->ioprio || sqe->len || sqe->rw_flags || sqe->buf_index || - sqe->splice_fd_in) + if (sqe->len || sqe->rw_flags || sqe->buf_index || sqe->splice_fd_in) return -EINVAL; if (unlikely(req->flags & REQ_F_FIXED_FILE)) return -EBADF; @@ -4263,8 +4962,6 @@ static int io_symlinkat(struct io_kiocb *req, unsigned int issue_flags) ret = do_symlinkat(sl->oldpath, sl->new_dfd, sl->newpath); req->flags &= ~REQ_F_NEED_CLEANUP; - if (ret < 0) - req_set_fail(req); io_req_complete(req, ret); return 0; } @@ -4275,9 +4972,7 @@ static int io_linkat_prep(struct io_kiocb *req, struct io_hardlink *lnk = &req->hardlink; const char __user *oldf, *newf; - if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) - return -EINVAL; - if (sqe->ioprio || sqe->rw_flags || sqe->buf_index || sqe->splice_fd_in) + if (sqe->rw_flags || sqe->buf_index || sqe->splice_fd_in) return -EINVAL; if (unlikely(req->flags & REQ_F_FIXED_FILE)) return -EBADF; @@ -4314,9 +5009,97 @@ static int io_linkat(struct io_kiocb *req, unsigned int issue_flags) lnk->newpath, lnk->flags); req->flags &= ~REQ_F_NEED_CLEANUP; + io_req_complete(req, ret); + return 0; +} + +static void io_uring_cmd_work(struct io_kiocb *req, bool *locked) +{ + req->uring_cmd.task_work_cb(&req->uring_cmd); +} + +void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd, + void (*task_work_cb)(struct io_uring_cmd *)) +{ + struct io_kiocb *req = container_of(ioucmd, struct io_kiocb, uring_cmd); + + req->uring_cmd.task_work_cb = task_work_cb; + req->io_task_work.func = io_uring_cmd_work; + io_req_task_prio_work_add(req); +} +EXPORT_SYMBOL_GPL(io_uring_cmd_complete_in_task); + +/* + * Called by consumers of io_uring_cmd, if they originally returned + * -EIOCBQUEUED upon receiving the command. + */ +void io_uring_cmd_done(struct io_uring_cmd *ioucmd, ssize_t ret, ssize_t res2) +{ + struct io_kiocb *req = container_of(ioucmd, struct io_kiocb, uring_cmd); + if (ret < 0) req_set_fail(req); - io_req_complete(req, ret); + if (req->ctx->flags & IORING_SETUP_CQE32) + __io_req_complete32(req, 0, ret, 0, res2, 0); + else + io_req_complete(req, ret); +} +EXPORT_SYMBOL_GPL(io_uring_cmd_done); + +static int io_uring_cmd_prep_async(struct io_kiocb *req) +{ + size_t cmd_size; + + cmd_size = uring_cmd_pdu_size(req->ctx->flags & IORING_SETUP_SQE128); + + memcpy(req->async_data, req->uring_cmd.cmd, cmd_size); + return 0; +} + +static int io_uring_cmd_prep(struct io_kiocb *req, + const struct io_uring_sqe *sqe) +{ + struct io_uring_cmd *ioucmd = &req->uring_cmd; + + if (sqe->rw_flags) + return -EINVAL; + ioucmd->cmd = sqe->cmd; + ioucmd->cmd_op = READ_ONCE(sqe->cmd_op); + return 0; +} + +static int io_uring_cmd(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_uring_cmd *ioucmd = &req->uring_cmd; + struct io_ring_ctx *ctx = req->ctx; + struct file *file = req->file; + int ret; + + if (!req->file->f_op->uring_cmd) + return -EOPNOTSUPP; + + if (ctx->flags & IORING_SETUP_SQE128) + issue_flags |= IO_URING_F_SQE128; + if (ctx->flags & IORING_SETUP_CQE32) + issue_flags |= IO_URING_F_CQE32; + if (ctx->flags & IORING_SETUP_IOPOLL) + issue_flags |= IO_URING_F_IOPOLL; + + if (req_has_async_data(req)) + ioucmd->cmd = req->async_data; + + ret = file->f_op->uring_cmd(ioucmd, issue_flags); + if (ret == -EAGAIN) { + if (!req_has_async_data(req)) { + if (io_alloc_async_data(req)) + return -ENOMEM; + io_uring_cmd_prep_async(req); + } + return -EAGAIN; + } + + if (ret != -EIOCBQUEUED) + io_uring_cmd_done(ioucmd, ret, 0); return 0; } @@ -4324,9 +5107,7 @@ static int io_shutdown_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { #if defined(CONFIG_NET) - if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) - return -EINVAL; - if (unlikely(sqe->ioprio || sqe->off || sqe->addr || sqe->rw_flags || + if (unlikely(sqe->off || sqe->addr || sqe->rw_flags || sqe->buf_index || sqe->splice_fd_in)) return -EINVAL; @@ -4351,8 +5132,6 @@ static int io_shutdown(struct io_kiocb *req, unsigned int issue_flags) return -ENOTSOCK; ret = __sys_shutdown_sock(sock, req->shutdown.how); - if (ret < 0) - req_set_fail(req); io_req_complete(req, ret); return 0; #else @@ -4366,21 +5145,11 @@ static int __io_splice_prep(struct io_kiocb *req, struct io_splice *sp = &req->splice; unsigned int valid_flags = SPLICE_F_FD_IN_FIXED | SPLICE_F_ALL; - if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) - return -EINVAL; - - sp->file_in = NULL; sp->len = READ_ONCE(sqe->len); sp->flags = READ_ONCE(sqe->splice_flags); - if (unlikely(sp->flags & ~valid_flags)) return -EINVAL; - - sp->file_in = io_file_get(req->ctx, req, READ_ONCE(sqe->splice_fd_in), - (sp->flags & SPLICE_F_FD_IN_FIXED)); - if (!sp->file_in) - return -EBADF; - req->flags |= REQ_F_NEED_CLEANUP; + sp->splice_fd_in = READ_ONCE(sqe->splice_fd_in); return 0; } @@ -4395,23 +5164,32 @@ static int io_tee_prep(struct io_kiocb *req, static int io_tee(struct io_kiocb *req, unsigned int issue_flags) { struct io_splice *sp = &req->splice; - struct file *in = sp->file_in; struct file *out = sp->file_out; unsigned int flags = sp->flags & ~SPLICE_F_FD_IN_FIXED; + struct file *in; long ret = 0; if (issue_flags & IO_URING_F_NONBLOCK) return -EAGAIN; + + if (sp->flags & SPLICE_F_FD_IN_FIXED) + in = io_file_get_fixed(req, sp->splice_fd_in, issue_flags); + else + in = io_file_get_normal(req, sp->splice_fd_in); + if (!in) { + ret = -EBADF; + goto done; + } + if (sp->len) ret = do_tee(in, out, sp->len, flags); if (!(sp->flags & SPLICE_F_FD_IN_FIXED)) io_put_file(in); - req->flags &= ~REQ_F_NEED_CLEANUP; - +done: if (ret != sp->len) req_set_fail(req); - io_req_complete(req, ret); + __io_req_complete(req, 0, ret, 0); return 0; } @@ -4427,15 +5205,24 @@ static int io_splice_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) static int io_splice(struct io_kiocb *req, unsigned int issue_flags) { struct io_splice *sp = &req->splice; - struct file *in = sp->file_in; struct file *out = sp->file_out; unsigned int flags = sp->flags & ~SPLICE_F_FD_IN_FIXED; loff_t *poff_in, *poff_out; + struct file *in; long ret = 0; if (issue_flags & IO_URING_F_NONBLOCK) return -EAGAIN; + if (sp->flags & SPLICE_F_FD_IN_FIXED) + in = io_file_get_fixed(req, sp->splice_fd_in, issue_flags); + else + in = io_file_get_normal(req, sp->splice_fd_in); + if (!in) { + ret = -EBADF; + goto done; + } + poff_in = (sp->off_in == -1) ? NULL : &sp->off_in; poff_out = (sp->off_out == -1) ? NULL : &sp->off_out; @@ -4444,11 +5231,23 @@ static int io_splice(struct io_kiocb *req, unsigned int issue_flags) if (!(sp->flags & SPLICE_F_FD_IN_FIXED)) io_put_file(in); - req->flags &= ~REQ_F_NEED_CLEANUP; - +done: if (ret != sp->len) req_set_fail(req); - io_req_complete(req, ret); + __io_req_complete(req, 0, ret, 0); + return 0; +} + +static int io_nop_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + /* + * If the ring is setup with CQE32, relay back addr/addr + */ + if (req->ctx->flags & IORING_SETUP_CQE32) { + req->nop.extra1 = READ_ONCE(sqe->addr); + req->nop.extra2 = READ_ONCE(sqe->addr2); + } + return 0; } @@ -4457,20 +5256,31 @@ static int io_splice(struct io_kiocb *req, unsigned int issue_flags) */ static int io_nop(struct io_kiocb *req, unsigned int issue_flags) { - struct io_ring_ctx *ctx = req->ctx; + unsigned int cflags; + void __user *buf; - if (unlikely(ctx->flags & IORING_SETUP_IOPOLL)) - return -EINVAL; + if (req->flags & REQ_F_BUFFER_SELECT) { + size_t len = 1; - __io_req_complete(req, issue_flags, 0, 0); + buf = io_buffer_select(req, &len, issue_flags); + if (!buf) + return -ENOBUFS; + } + + cflags = io_put_kbuf(req, issue_flags); + if (!(req->ctx->flags & IORING_SETUP_CQE32)) + __io_req_complete(req, issue_flags, 0, cflags); + else + __io_req_complete32(req, issue_flags, 0, cflags, + req->nop.extra1, req->nop.extra2); return 0; } static int io_msg_ring_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { - if (unlikely(sqe->addr || sqe->ioprio || sqe->rw_flags || - sqe->splice_fd_in || sqe->buf_index || sqe->personality)) + if (unlikely(sqe->addr || sqe->rw_flags || sqe->splice_fd_in || + sqe->buf_index || sqe->personality)) return -EINVAL; req->msg.user_data = READ_ONCE(sqe->off); @@ -4506,20 +5316,15 @@ done: if (ret < 0) req_set_fail(req); __io_req_complete(req, issue_flags, ret, 0); + /* put file to avoid an attempt to IOPOLL the req */ + io_put_file(req->file); + req->file = NULL; return 0; } static int io_fsync_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { - struct io_ring_ctx *ctx = req->ctx; - - if (!req->file) - return -EBADF; - - if (unlikely(ctx->flags & IORING_SETUP_IOPOLL)) - return -EINVAL; - if (unlikely(sqe->addr || sqe->ioprio || sqe->buf_index || - sqe->splice_fd_in)) + if (unlikely(sqe->addr || sqe->buf_index || sqe->splice_fd_in)) return -EINVAL; req->sync.flags = READ_ONCE(sqe->fsync_flags); @@ -4543,8 +5348,6 @@ static int io_fsync(struct io_kiocb *req, unsigned int issue_flags) ret = vfs_fsync_range(req->file, req->sync.off, end > 0 ? end : LLONG_MAX, req->sync.flags & IORING_FSYNC_DATASYNC); - if (ret < 0) - req_set_fail(req); io_req_complete(req, ret); return 0; } @@ -4552,10 +5355,7 @@ static int io_fsync(struct io_kiocb *req, unsigned int issue_flags) static int io_fallocate_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { - if (sqe->ioprio || sqe->buf_index || sqe->rw_flags || - sqe->splice_fd_in) - return -EINVAL; - if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + if (sqe->buf_index || sqe->rw_flags || sqe->splice_fd_in) return -EINVAL; req->sync.off = READ_ONCE(sqe->off); @@ -4573,9 +5373,7 @@ static int io_fallocate(struct io_kiocb *req, unsigned int issue_flags) return -EAGAIN; ret = vfs_fallocate(req->file, req->sync.mode, req->sync.off, req->sync.len); - if (ret < 0) - req_set_fail(req); - else + if (ret >= 0) fsnotify_modify(req->file); io_req_complete(req, ret); return 0; @@ -4586,9 +5384,7 @@ static int __io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe const char __user *fname; int ret; - if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) - return -EINVAL; - if (unlikely(sqe->ioprio || sqe->buf_index)) + if (unlikely(sqe->buf_index)) return -EINVAL; if (unlikely(req->flags & REQ_F_FIXED_FILE)) return -EBADF; @@ -4643,6 +5439,61 @@ static int io_openat2_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) return __io_openat_prep(req, sqe); } +static int io_file_bitmap_get(struct io_ring_ctx *ctx) +{ + struct io_file_table *table = &ctx->file_table; + unsigned long nr = ctx->nr_user_files; + int ret; + + if (table->alloc_hint >= nr) + table->alloc_hint = 0; + + do { + ret = find_next_zero_bit(table->bitmap, nr, table->alloc_hint); + if (ret != nr) { + table->alloc_hint = ret + 1; + return ret; + } + if (!table->alloc_hint) + break; + + nr = table->alloc_hint; + table->alloc_hint = 0; + } while (1); + + return -ENFILE; +} + +static int io_fixed_fd_install(struct io_kiocb *req, unsigned int issue_flags, + struct file *file, unsigned int file_slot) +{ + bool alloc_slot = file_slot == IORING_FILE_INDEX_ALLOC; + struct io_ring_ctx *ctx = req->ctx; + int ret; + + if (alloc_slot) { + io_ring_submit_lock(ctx, issue_flags); + ret = io_file_bitmap_get(ctx); + if (unlikely(ret < 0)) { + io_ring_submit_unlock(ctx, issue_flags); + return ret; + } + + file_slot = ret; + } else { + file_slot--; + } + + ret = io_install_fixed_file(req, file, issue_flags, file_slot); + if (alloc_slot) { + io_ring_submit_unlock(ctx, issue_flags); + if (!ret) + return file_slot; + } + + return ret; +} + static int io_openat2(struct io_kiocb *req, unsigned int issue_flags) { struct open_flags op; @@ -4698,8 +5549,8 @@ static int io_openat2(struct io_kiocb *req, unsigned int issue_flags) if (!fixed) fd_install(ret, file); else - ret = io_install_fixed_file(req, file, issue_flags, - req->open.file_slot - 1); + ret = io_fixed_fd_install(req, issue_flags, file, + req->open.file_slot); err: putname(req->open.filename); req->flags &= ~REQ_F_NEED_CLEANUP; @@ -4720,7 +5571,7 @@ static int io_remove_buffers_prep(struct io_kiocb *req, struct io_provide_buf *p = &req->pbuf; u64 tmp; - if (sqe->ioprio || sqe->rw_flags || sqe->addr || sqe->len || sqe->off || + if (sqe->rw_flags || sqe->addr || sqe->len || sqe->off || sqe->splice_fd_in) return -EINVAL; @@ -4743,6 +5594,20 @@ static int __io_remove_buffers(struct io_ring_ctx *ctx, if (!nbufs) return 0; + if (bl->buf_nr_pages) { + int j; + + i = bl->buf_ring->tail - bl->head; + for (j = 0; j < bl->buf_nr_pages; j++) + unpin_user_page(bl->buf_pages[j]); + kvfree(bl->buf_pages); + bl->buf_pages = NULL; + bl->buf_nr_pages = 0; + /* make sure it's seen as empty */ + INIT_LIST_HEAD(&bl->buf_list); + return i; + } + /* the head kbuf is the list itself */ while (!list_empty(&bl->buf_list)) { struct io_buffer *nxt; @@ -4764,22 +5629,23 @@ static int io_remove_buffers(struct io_kiocb *req, unsigned int issue_flags) struct io_ring_ctx *ctx = req->ctx; struct io_buffer_list *bl; int ret = 0; - bool needs_lock = issue_flags & IO_URING_F_UNLOCKED; - io_ring_submit_lock(ctx, needs_lock); - - lockdep_assert_held(&ctx->uring_lock); + io_ring_submit_lock(ctx, issue_flags); ret = -ENOENT; bl = io_buffer_get_list(ctx, p->bgid); - if (bl) - ret = __io_remove_buffers(ctx, bl, p->nbufs); + if (bl) { + ret = -EINVAL; + /* can't use provide/remove buffers command on mapped buffers */ + if (!bl->buf_nr_pages) + ret = __io_remove_buffers(ctx, bl, p->nbufs); + } if (ret < 0) req_set_fail(req); /* complete before unlock, IOPOLL may need the lock */ __io_req_complete(req, issue_flags, ret, 0); - io_ring_submit_unlock(ctx, needs_lock); + io_ring_submit_unlock(ctx, issue_flags); return 0; } @@ -4790,7 +5656,7 @@ static int io_provide_buffers_prep(struct io_kiocb *req, struct io_provide_buf *p = &req->pbuf; u64 tmp; - if (sqe->ioprio || sqe->rw_flags || sqe->splice_fd_in) + if (sqe->rw_flags || sqe->splice_fd_in) return -EINVAL; tmp = READ_ONCE(sqe->fd); @@ -4887,26 +5753,56 @@ static int io_add_buffers(struct io_ring_ctx *ctx, struct io_provide_buf *pbuf, return i ? 0 : -ENOMEM; } +static __cold int io_init_bl_list(struct io_ring_ctx *ctx) +{ + int i; + + ctx->io_bl = kcalloc(BGID_ARRAY, sizeof(struct io_buffer_list), + GFP_KERNEL); + if (!ctx->io_bl) + return -ENOMEM; + + for (i = 0; i < BGID_ARRAY; i++) { + INIT_LIST_HEAD(&ctx->io_bl[i].buf_list); + ctx->io_bl[i].bgid = i; + } + + return 0; +} + static int io_provide_buffers(struct io_kiocb *req, unsigned int issue_flags) { struct io_provide_buf *p = &req->pbuf; struct io_ring_ctx *ctx = req->ctx; struct io_buffer_list *bl; int ret = 0; - bool needs_lock = issue_flags & IO_URING_F_UNLOCKED; - io_ring_submit_lock(ctx, needs_lock); + io_ring_submit_lock(ctx, issue_flags); - lockdep_assert_held(&ctx->uring_lock); + if (unlikely(p->bgid < BGID_ARRAY && !ctx->io_bl)) { + ret = io_init_bl_list(ctx); + if (ret) + goto err; + } bl = io_buffer_get_list(ctx, p->bgid); if (unlikely(!bl)) { - bl = kmalloc(sizeof(*bl), GFP_KERNEL); + bl = kzalloc(sizeof(*bl), GFP_KERNEL); if (!bl) { ret = -ENOMEM; goto err; } - io_buffer_add_list(ctx, bl, p->bgid); + INIT_LIST_HEAD(&bl->buf_list); + ret = io_buffer_add_list(ctx, bl, p->bgid); + if (ret) { + kfree(bl); + goto err; + } + } + /* can't add buffers via this command for a mapped buffer ring */ + if (bl->buf_nr_pages) { + ret = -EINVAL; + goto err; } ret = io_add_buffers(ctx, p, bl); @@ -4915,7 +5811,7 @@ err: req_set_fail(req); /* complete before unlock, IOPOLL may need the lock */ __io_req_complete(req, issue_flags, ret, 0); - io_ring_submit_unlock(ctx, needs_lock); + io_ring_submit_unlock(ctx, issue_flags); return 0; } @@ -4923,9 +5819,7 @@ static int io_epoll_ctl_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { #if defined(CONFIG_EPOLL) - if (sqe->ioprio || sqe->buf_index || sqe->splice_fd_in) - return -EINVAL; - if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + if (sqe->buf_index || sqe->splice_fd_in) return -EINVAL; req->epoll.epfd = READ_ONCE(sqe->fd); @@ -4969,9 +5863,7 @@ static int io_epoll_ctl(struct io_kiocb *req, unsigned int issue_flags) static int io_madvise_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { #if defined(CONFIG_ADVISE_SYSCALLS) && defined(CONFIG_MMU) - if (sqe->ioprio || sqe->buf_index || sqe->off || sqe->splice_fd_in) - return -EINVAL; - if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + if (sqe->buf_index || sqe->off || sqe->splice_fd_in) return -EINVAL; req->madvise.addr = READ_ONCE(sqe->addr); @@ -4993,8 +5885,6 @@ static int io_madvise(struct io_kiocb *req, unsigned int issue_flags) return -EAGAIN; ret = do_madvise(current->mm, ma->addr, ma->len, ma->advice); - if (ret < 0) - req_set_fail(req); io_req_complete(req, ret); return 0; #else @@ -5004,9 +5894,7 @@ static int io_madvise(struct io_kiocb *req, unsigned int issue_flags) static int io_fadvise_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { - if (sqe->ioprio || sqe->buf_index || sqe->addr || sqe->splice_fd_in) - return -EINVAL; - if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + if (sqe->buf_index || sqe->addr || sqe->splice_fd_in) return -EINVAL; req->fadvise.offset = READ_ONCE(sqe->off); @@ -5042,9 +5930,7 @@ static int io_statx_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { const char __user *path; - if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) - return -EINVAL; - if (sqe->ioprio || sqe->buf_index || sqe->splice_fd_in) + if (sqe->buf_index || sqe->splice_fd_in) return -EINVAL; if (req->flags & REQ_F_FIXED_FILE) return -EBADF; @@ -5080,19 +5966,13 @@ static int io_statx(struct io_kiocb *req, unsigned int issue_flags) ret = do_statx(ctx->dfd, ctx->filename, ctx->flags, ctx->mask, ctx->buffer); - - if (ret < 0) - req_set_fail(req); io_req_complete(req, ret); return 0; } static int io_close_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { - if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) - return -EINVAL; - if (sqe->ioprio || sqe->off || sqe->addr || sqe->len || - sqe->rw_flags || sqe->buf_index) + if (sqe->off || sqe->addr || sqe->len || sqe->rw_flags || sqe->buf_index) return -EINVAL; if (req->flags & REQ_F_FIXED_FILE) return -EBADF; @@ -5124,7 +6004,8 @@ static int io_close(struct io_kiocb *req, unsigned int issue_flags) spin_unlock(&files->file_lock); goto err; } - file = fdt->fd[close->fd]; + file = rcu_dereference_protected(fdt->fd[close->fd], + lockdep_is_held(&files->file_lock)); if (!file || file->f_op == &io_uring_fops) { spin_unlock(&files->file_lock); file = NULL; @@ -5158,12 +6039,7 @@ err: static int io_sfr_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { - struct io_ring_ctx *ctx = req->ctx; - - if (unlikely(ctx->flags & IORING_SETUP_IOPOLL)) - return -EINVAL; - if (unlikely(sqe->addr || sqe->ioprio || sqe->buf_index || - sqe->splice_fd_in)) + if (unlikely(sqe->addr || sqe->buf_index || sqe->splice_fd_in)) return -EINVAL; req->sync.off = READ_ONCE(sqe->off); @@ -5182,13 +6058,18 @@ static int io_sync_file_range(struct io_kiocb *req, unsigned int issue_flags) ret = sync_file_range(req->file, req->sync.off, req->sync.len, req->sync.flags); - if (ret < 0) - req_set_fail(req); io_req_complete(req, ret); return 0; } #if defined(CONFIG_NET) +static bool io_net_retry(struct socket *sock, int flags) +{ + if (!(flags & MSG_WAITALL)) + return false; + return sock->type == SOCK_STREAM || sock->type == SOCK_SEQPACKET; +} + static int io_setup_async_msg(struct io_kiocb *req, struct io_async_msghdr *kmsg) { @@ -5234,11 +6115,16 @@ static int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_sr_msg *sr = &req->sr_msg; - if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + if (unlikely(sqe->file_index)) + return -EINVAL; + if (unlikely(sqe->addr2 || sqe->file_index)) return -EINVAL; sr->umsg = u64_to_user_ptr(READ_ONCE(sqe->addr)); sr->len = READ_ONCE(sqe->len); + sr->flags = READ_ONCE(sqe->addr2); + if (sr->flags & ~IORING_RECVSEND_POLL_FIRST) + return -EINVAL; sr->msg_flags = READ_ONCE(sqe->msg_flags) | MSG_NOSIGNAL; if (sr->msg_flags & MSG_DONTWAIT) req->flags |= REQ_F_NOWAIT; @@ -5247,12 +6133,14 @@ static int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) if (req->ctx->compat) sr->msg_flags |= MSG_CMSG_COMPAT; #endif + sr->done_io = 0; return 0; } static int io_sendmsg(struct io_kiocb *req, unsigned int issue_flags) { struct io_async_msghdr iomsg, *kmsg; + struct io_sr_msg *sr = &req->sr_msg; struct socket *sock; unsigned flags; int min_ret = 0; @@ -5271,7 +6159,11 @@ static int io_sendmsg(struct io_kiocb *req, unsigned int issue_flags) kmsg = &iomsg; } - flags = req->sr_msg.msg_flags; + if (!(req->flags & REQ_F_POLLED) && + (sr->flags & IORING_RECVSEND_POLL_FIRST)) + return io_setup_async_msg(req, kmsg); + + flags = sr->msg_flags; if (issue_flags & IO_URING_F_NONBLOCK) flags |= MSG_DONTWAIT; if (flags & MSG_WAITALL) @@ -5284,12 +6176,21 @@ static int io_sendmsg(struct io_kiocb *req, unsigned int issue_flags) return io_setup_async_msg(req, kmsg); if (ret == -ERESTARTSYS) ret = -EINTR; + if (ret > 0 && io_net_retry(sock, flags)) { + sr->done_io += ret; + req->flags |= REQ_F_PARTIAL_IO; + return io_setup_async_msg(req, kmsg); + } req_set_fail(req); } /* fast path, check for non-NULL to avoid function call */ if (kmsg->free_iov) kfree(kmsg->free_iov); req->flags &= ~REQ_F_NEED_CLEANUP; + if (ret >= 0) + ret += sr->done_io; + else if (sr->done_io) + ret = sr->done_io; __io_req_complete(req, issue_flags, ret, 0); return 0; } @@ -5304,6 +6205,10 @@ static int io_send(struct io_kiocb *req, unsigned int issue_flags) int min_ret = 0; int ret; + if (!(req->flags & REQ_F_POLLED) && + (sr->flags & IORING_RECVSEND_POLL_FIRST)) + return -EAGAIN; + sock = sock_from_file(req->file); if (unlikely(!sock)) return -ENOTSOCK; @@ -5317,7 +6222,7 @@ static int io_send(struct io_kiocb *req, unsigned int issue_flags) msg.msg_controllen = 0; msg.msg_namelen = 0; - flags = req->sr_msg.msg_flags; + flags = sr->msg_flags; if (issue_flags & IO_URING_F_NONBLOCK) flags |= MSG_DONTWAIT; if (flags & MSG_WAITALL) @@ -5330,8 +6235,19 @@ static int io_send(struct io_kiocb *req, unsigned int issue_flags) return -EAGAIN; if (ret == -ERESTARTSYS) ret = -EINTR; + if (ret > 0 && io_net_retry(sock, flags)) { + sr->len -= ret; + sr->buf += ret; + sr->done_io += ret; + req->flags |= REQ_F_PARTIAL_IO; + return -EAGAIN; + } req_set_fail(req); } + if (ret >= 0) + ret += sr->done_io; + else if (sr->done_io) + ret = sr->done_io; __io_req_complete(req, issue_flags, ret, 0); return 0; } @@ -5423,14 +6339,6 @@ static int io_recvmsg_copy_hdr(struct io_kiocb *req, return __io_recvmsg_copy_hdr(req, iomsg); } -static struct io_buffer *io_recv_buffer_select(struct io_kiocb *req, - unsigned int issue_flags) -{ - struct io_sr_msg *sr = &req->sr_msg; - - return io_buffer_select(req, &sr->len, sr->bgid, issue_flags); -} - static int io_recvmsg_prep_async(struct io_kiocb *req) { int ret; @@ -5445,12 +6353,16 @@ static int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_sr_msg *sr = &req->sr_msg; - if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + if (unlikely(sqe->file_index)) + return -EINVAL; + if (unlikely(sqe->addr2 || sqe->file_index)) return -EINVAL; sr->umsg = u64_to_user_ptr(READ_ONCE(sqe->addr)); sr->len = READ_ONCE(sqe->len); - sr->bgid = READ_ONCE(sqe->buf_group); + sr->flags = READ_ONCE(sqe->addr2); + if (sr->flags & ~IORING_RECVSEND_POLL_FIRST) + return -EINVAL; sr->msg_flags = READ_ONCE(sqe->msg_flags) | MSG_NOSIGNAL; if (sr->msg_flags & MSG_DONTWAIT) req->flags |= REQ_F_NOWAIT; @@ -5463,19 +6375,12 @@ static int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) return 0; } -static bool io_net_retry(struct socket *sock, int flags) -{ - if (!(flags & MSG_WAITALL)) - return false; - return sock->type == SOCK_STREAM || sock->type == SOCK_SEQPACKET; -} - static int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) { struct io_async_msghdr iomsg, *kmsg; struct io_sr_msg *sr = &req->sr_msg; struct socket *sock; - struct io_buffer *kbuf; + unsigned int cflags; unsigned flags; int ret, min_ret = 0; bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; @@ -5493,24 +6398,30 @@ static int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) kmsg = &iomsg; } - if (req->flags & REQ_F_BUFFER_SELECT) { - kbuf = io_recv_buffer_select(req, issue_flags); - if (IS_ERR(kbuf)) - return PTR_ERR(kbuf); - kmsg->fast_iov[0].iov_base = u64_to_user_ptr(kbuf->addr); - kmsg->fast_iov[0].iov_len = req->sr_msg.len; - iov_iter_init(&kmsg->msg.msg_iter, READ, kmsg->fast_iov, - 1, req->sr_msg.len); + if (!(req->flags & REQ_F_POLLED) && + (sr->flags & IORING_RECVSEND_POLL_FIRST)) + return io_setup_async_msg(req, kmsg); + + if (io_do_buffer_select(req)) { + void __user *buf; + + buf = io_buffer_select(req, &sr->len, issue_flags); + if (!buf) + return -ENOBUFS; + kmsg->fast_iov[0].iov_base = buf; + kmsg->fast_iov[0].iov_len = sr->len; + iov_iter_init(&kmsg->msg.msg_iter, READ, kmsg->fast_iov, 1, + sr->len); } - flags = req->sr_msg.msg_flags; + flags = sr->msg_flags; if (force_nonblock) flags |= MSG_DONTWAIT; if (flags & MSG_WAITALL) min_ret = iov_iter_count(&kmsg->msg.msg_iter); - ret = __sys_recvmsg_sock(sock, &kmsg->msg, req->sr_msg.umsg, - kmsg->uaddr, flags); + kmsg->msg.msg_get_inq = 1; + ret = __sys_recvmsg_sock(sock, &kmsg->msg, sr->umsg, kmsg->uaddr, flags); if (ret < min_ret) { if (ret == -EAGAIN && force_nonblock) return io_setup_async_msg(req, kmsg); @@ -5534,45 +6445,54 @@ static int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) ret += sr->done_io; else if (sr->done_io) ret = sr->done_io; - __io_req_complete(req, issue_flags, ret, io_put_kbuf(req, issue_flags)); + cflags = io_put_kbuf(req, issue_flags); + if (kmsg->msg.msg_inq) + cflags |= IORING_CQE_F_SOCK_NONEMPTY; + __io_req_complete(req, issue_flags, ret, cflags); return 0; } static int io_recv(struct io_kiocb *req, unsigned int issue_flags) { - struct io_buffer *kbuf; struct io_sr_msg *sr = &req->sr_msg; struct msghdr msg; - void __user *buf = sr->buf; struct socket *sock; struct iovec iov; + unsigned int cflags; unsigned flags; int ret, min_ret = 0; bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; + if (!(req->flags & REQ_F_POLLED) && + (sr->flags & IORING_RECVSEND_POLL_FIRST)) + return -EAGAIN; + sock = sock_from_file(req->file); if (unlikely(!sock)) return -ENOTSOCK; - if (req->flags & REQ_F_BUFFER_SELECT) { - kbuf = io_recv_buffer_select(req, issue_flags); - if (IS_ERR(kbuf)) - return PTR_ERR(kbuf); - buf = u64_to_user_ptr(kbuf->addr); + if (io_do_buffer_select(req)) { + void __user *buf; + + buf = io_buffer_select(req, &sr->len, issue_flags); + if (!buf) + return -ENOBUFS; + sr->buf = buf; } - ret = import_single_range(READ, buf, sr->len, &iov, &msg.msg_iter); + ret = import_single_range(READ, sr->buf, sr->len, &iov, &msg.msg_iter); if (unlikely(ret)) goto out_free; msg.msg_name = NULL; + msg.msg_namelen = 0; msg.msg_control = NULL; + msg.msg_get_inq = 1; + msg.msg_flags = 0; msg.msg_controllen = 0; - msg.msg_namelen = 0; msg.msg_iocb = NULL; - msg.msg_flags = 0; - flags = req->sr_msg.msg_flags; + flags = sr->msg_flags; if (force_nonblock) flags |= MSG_DONTWAIT; if (flags & MSG_WAITALL) @@ -5601,36 +6521,49 @@ out_free: ret += sr->done_io; else if (sr->done_io) ret = sr->done_io; - __io_req_complete(req, issue_flags, ret, io_put_kbuf(req, issue_flags)); + cflags = io_put_kbuf(req, issue_flags); + if (msg.msg_inq) + cflags |= IORING_CQE_F_SOCK_NONEMPTY; + __io_req_complete(req, issue_flags, ret, cflags); return 0; } static int io_accept_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_accept *accept = &req->accept; + unsigned flags; - if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) - return -EINVAL; - if (sqe->ioprio || sqe->len || sqe->buf_index) + if (sqe->len || sqe->buf_index) return -EINVAL; accept->addr = u64_to_user_ptr(READ_ONCE(sqe->addr)); accept->addr_len = u64_to_user_ptr(READ_ONCE(sqe->addr2)); accept->flags = READ_ONCE(sqe->accept_flags); accept->nofile = rlimit(RLIMIT_NOFILE); + flags = READ_ONCE(sqe->ioprio); + if (flags & ~IORING_ACCEPT_MULTISHOT) + return -EINVAL; accept->file_slot = READ_ONCE(sqe->file_index); - if (accept->file_slot && (accept->flags & SOCK_CLOEXEC)) - return -EINVAL; + if (accept->file_slot) { + if (accept->flags & SOCK_CLOEXEC) + return -EINVAL; + if (flags & IORING_ACCEPT_MULTISHOT && + accept->file_slot != IORING_FILE_INDEX_ALLOC) + return -EINVAL; + } if (accept->flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK)) return -EINVAL; if (SOCK_NONBLOCK != O_NONBLOCK && (accept->flags & SOCK_NONBLOCK)) accept->flags = (accept->flags & ~SOCK_NONBLOCK) | O_NONBLOCK; + if (flags & IORING_ACCEPT_MULTISHOT) + req->flags |= REQ_F_APOLL_MULTISHOT; return 0; } static int io_accept(struct io_kiocb *req, unsigned int issue_flags) { + struct io_ring_ctx *ctx = req->ctx; struct io_accept *accept = &req->accept; bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; unsigned int file_flags = force_nonblock ? O_NONBLOCK : 0; @@ -5638,6 +6571,7 @@ static int io_accept(struct io_kiocb *req, unsigned int issue_flags) struct file *file; int ret, fd; +retry: if (!fixed) { fd = __get_unused_fd_flags(accept->flags, accept->nofile); if (unlikely(fd < 0)) @@ -5649,7 +6583,89 @@ static int io_accept(struct io_kiocb *req, unsigned int issue_flags) if (!fixed) put_unused_fd(fd); ret = PTR_ERR(file); - if (ret == -EAGAIN && force_nonblock) + if (ret == -EAGAIN && force_nonblock) { + /* + * if it's multishot and polled, we don't need to + * return EAGAIN to arm the poll infra since it + * has already been done + */ + if ((req->flags & IO_APOLL_MULTI_POLLED) == + IO_APOLL_MULTI_POLLED) + ret = 0; + return ret; + } + if (ret == -ERESTARTSYS) + ret = -EINTR; + req_set_fail(req); + } else if (!fixed) { + fd_install(fd, file); + ret = fd; + } else { + ret = io_fixed_fd_install(req, issue_flags, file, + accept->file_slot); + } + + if (!(req->flags & REQ_F_APOLL_MULTISHOT)) { + __io_req_complete(req, issue_flags, ret, 0); + return 0; + } + if (ret >= 0) { + bool filled; + + spin_lock(&ctx->completion_lock); + filled = io_fill_cqe_aux(ctx, req->cqe.user_data, ret, + IORING_CQE_F_MORE); + io_commit_cqring(ctx); + spin_unlock(&ctx->completion_lock); + if (filled) { + io_cqring_ev_posted(ctx); + goto retry; + } + ret = -ECANCELED; + } + + return ret; +} + +static int io_socket_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_socket *sock = &req->sock; + + if (sqe->addr || sqe->rw_flags || sqe->buf_index) + return -EINVAL; + + sock->domain = READ_ONCE(sqe->fd); + sock->type = READ_ONCE(sqe->off); + sock->protocol = READ_ONCE(sqe->len); + sock->file_slot = READ_ONCE(sqe->file_index); + sock->nofile = rlimit(RLIMIT_NOFILE); + + sock->flags = sock->type & ~SOCK_TYPE_MASK; + if (sock->file_slot && (sock->flags & SOCK_CLOEXEC)) + return -EINVAL; + if (sock->flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK)) + return -EINVAL; + return 0; +} + +static int io_socket(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_socket *sock = &req->sock; + bool fixed = !!sock->file_slot; + struct file *file; + int ret, fd; + + if (!fixed) { + fd = __get_unused_fd_flags(sock->flags, sock->nofile); + if (unlikely(fd < 0)) + return fd; + } + file = __sys_socket_file(sock->domain, sock->type, sock->protocol); + if (IS_ERR(file)) { + if (!fixed) + put_unused_fd(fd); + ret = PTR_ERR(file); + if (ret == -EAGAIN && (issue_flags & IO_URING_F_NONBLOCK)) return -EAGAIN; if (ret == -ERESTARTSYS) ret = -EINTR; @@ -5659,7 +6675,7 @@ static int io_accept(struct io_kiocb *req, unsigned int issue_flags) ret = fd; } else { ret = io_install_fixed_file(req, file, issue_flags, - accept->file_slot - 1); + sock->file_slot - 1); } __io_req_complete(req, issue_flags, ret, 0); return 0; @@ -5677,10 +6693,7 @@ static int io_connect_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_connect *conn = &req->connect; - if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) - return -EINVAL; - if (sqe->ioprio || sqe->len || sqe->buf_index || sqe->rw_flags || - sqe->splice_fd_in) + if (sqe->len || sqe->buf_index || sqe->rw_flags || sqe->splice_fd_in) return -EINVAL; conn->addr = u64_to_user_ptr(READ_ONCE(sqe->addr)); @@ -5753,112 +6766,11 @@ IO_NETOP_PREP_ASYNC(sendmsg); IO_NETOP_PREP_ASYNC(recvmsg); IO_NETOP_PREP_ASYNC(connect); IO_NETOP_PREP(accept); +IO_NETOP_PREP(socket); IO_NETOP_FN(send); IO_NETOP_FN(recv); #endif /* CONFIG_NET */ -#ifdef CONFIG_NET_RX_BUSY_POLL - -#define NAPI_TIMEOUT (60 * SEC_CONVERSION) - -struct napi_entry { - struct list_head list; - unsigned int napi_id; - unsigned long timeout; -}; - -/* - * Add busy poll NAPI ID from sk. - */ -static void io_add_napi(struct file *file, struct io_ring_ctx *ctx) -{ - unsigned int napi_id; - struct socket *sock; - struct sock *sk; - struct napi_entry *ne; - - if (!net_busy_loop_on()) - return; - - sock = sock_from_file(file); - if (!sock) - return; - - sk = sock->sk; - if (!sk) - return; - - napi_id = READ_ONCE(sk->sk_napi_id); - - /* Non-NAPI IDs can be rejected */ - if (napi_id < MIN_NAPI_ID) - return; - - spin_lock(&ctx->napi_lock); - list_for_each_entry(ne, &ctx->napi_list, list) { - if (ne->napi_id == napi_id) { - ne->timeout = jiffies + NAPI_TIMEOUT; - goto out; - } - } - - ne = kmalloc(sizeof(*ne), GFP_NOWAIT); - if (!ne) - goto out; - - ne->napi_id = napi_id; - ne->timeout = jiffies + NAPI_TIMEOUT; - list_add_tail(&ne->list, &ctx->napi_list); -out: - spin_unlock(&ctx->napi_lock); -} - -static inline void io_check_napi_entry_timeout(struct napi_entry *ne) -{ - if (time_after(jiffies, ne->timeout)) { - list_del(&ne->list); - kfree(ne); - } -} - -/* - * Busy poll if globally on and supporting sockets found - */ -static bool io_napi_busy_loop(struct list_head *napi_list) -{ - struct napi_entry *ne, *n; - - list_for_each_entry_safe(ne, n, napi_list, list) { - napi_busy_loop(ne->napi_id, NULL, NULL, true, - BUSY_POLL_BUDGET); - io_check_napi_entry_timeout(ne); - } - return !list_empty(napi_list); -} - -static void io_free_napi_list(struct io_ring_ctx *ctx) -{ - spin_lock(&ctx->napi_lock); - while (!list_empty(&ctx->napi_list)) { - struct napi_entry *ne = - list_first_entry(&ctx->napi_list, struct napi_entry, - list); - - list_del(&ne->list); - kfree(ne); - } - spin_unlock(&ctx->napi_lock); -} -#else -static inline void io_add_napi(struct file *file, struct io_ring_ctx *ctx) -{ -} - -static inline void io_free_napi_list(struct io_ring_ctx *ctx) -{ -} -#endif /* CONFIG_NET_RX_BUSY_POLL */ - struct io_poll_table { struct poll_table_struct pt; struct io_kiocb *req; @@ -5905,7 +6817,7 @@ static void io_poll_req_insert(struct io_kiocb *req) struct io_ring_ctx *ctx = req->ctx; struct hlist_head *list; - list = &ctx->cancel_hash[hash_long(req->user_data, ctx->cancel_hash_bits)]; + list = &ctx->cancel_hash[hash_long(req->cqe.user_data, ctx->cancel_hash_bits)]; hlist_add_head(&req->hash_node, list); } @@ -5964,23 +6876,23 @@ static void io_poll_remove_entries(struct io_kiocb *req) rcu_read_unlock(); } +static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags); /* * All poll tw should go through this. Checks for poll events, manages * references, does rewait, etc. * * Returns a negative error on failure. >0 when no action require, which is * either spurious wakeup or multishot CQE is served. 0 when it's done with - * the request, then the mask is stored in req->result. + * the request, then the mask is stored in req->cqe.res. */ -static int io_poll_check_events(struct io_kiocb *req) +static int io_poll_check_events(struct io_kiocb *req, bool *locked) { struct io_ring_ctx *ctx = req->ctx; - struct io_poll_iocb *poll = io_poll_get_single(req); - int v; + int v, ret; /* req->task == current here, checking PF_EXITING is safe */ if (unlikely(req->task->flags & PF_EXITING)) - io_poll_mark_cancelled(req); + return -ECANCELED; do { v = atomic_read(&req->poll_refs); @@ -5991,30 +6903,46 @@ static int io_poll_check_events(struct io_kiocb *req) if (v & IO_POLL_CANCEL_FLAG) return -ECANCELED; - if (!req->result) { - struct poll_table_struct pt = { ._key = req->cflags }; + if (!req->cqe.res) { + struct poll_table_struct pt = { ._key = req->apoll_events }; + unsigned flags = locked ? 0 : IO_URING_F_UNLOCKED; - req->result = vfs_poll(req->file, &pt) & req->cflags; + if (unlikely(!io_assign_file(req, flags))) + return -EBADF; + req->cqe.res = vfs_poll(req->file, &pt) & req->apoll_events; } - /* multishot, just fill an CQE and proceed */ - if (req->result && !(req->cflags & EPOLLONESHOT)) { - __poll_t mask = mangle_poll(req->result & poll->events); + if ((unlikely(!req->cqe.res))) + continue; + if (req->apoll_events & EPOLLONESHOT) + return 0; + + /* multishot, just fill a CQE and proceed */ + if (!(req->flags & REQ_F_APOLL_MULTISHOT)) { + __poll_t mask = mangle_poll(req->cqe.res & + req->apoll_events); bool filled; spin_lock(&ctx->completion_lock); - filled = io_fill_cqe_aux(ctx, req->user_data, mask, - IORING_CQE_F_MORE); + filled = io_fill_cqe_aux(ctx, req->cqe.user_data, + mask, IORING_CQE_F_MORE); io_commit_cqring(ctx); spin_unlock(&ctx->completion_lock); - if (unlikely(!filled)) - return -ECANCELED; - io_cqring_ev_posted(ctx); - io_add_napi(req->file, ctx); - } else if (req->result) { - return 0; + if (filled) { + io_cqring_ev_posted(ctx); + continue; + } + return -ECANCELED; } + io_tw_lock(req->ctx, locked); + if (unlikely(req->task->flags & PF_EXITING)) + return -EFAULT; + ret = io_issue_sqe(req, + IO_URING_F_NONBLOCK|IO_URING_F_COMPLETE_DEFER); + if (ret) + return ret; + /* * Release all references, retry if someone tried to restart * task_work while we were executing it. @@ -6029,21 +6957,21 @@ static void io_poll_task_func(struct io_kiocb *req, bool *locked) struct io_ring_ctx *ctx = req->ctx; int ret; - ret = io_poll_check_events(req); + ret = io_poll_check_events(req, locked); if (ret > 0) return; if (!ret) { - req->result = mangle_poll(req->result & req->poll.events); + req->cqe.res = mangle_poll(req->cqe.res & req->poll.events); } else { - req->result = ret; + req->cqe.res = ret; req_set_fail(req); } io_poll_remove_entries(req); spin_lock(&ctx->completion_lock); hash_del(&req->hash_node); - __io_req_complete_post(req, req->result, 0); + __io_req_complete_post(req, req->cqe.res, 0); io_commit_cqring(ctx); spin_unlock(&ctx->completion_lock); io_cqring_ev_posted(ctx); @@ -6054,7 +6982,7 @@ static void io_apoll_task_func(struct io_kiocb *req, bool *locked) struct io_ring_ctx *ctx = req->ctx; int ret; - ret = io_poll_check_events(req); + ret = io_poll_check_events(req, locked); if (ret > 0) return; @@ -6069,26 +6997,27 @@ static void io_apoll_task_func(struct io_kiocb *req, bool *locked) io_req_complete_failed(req, ret); } -static void __io_poll_execute(struct io_kiocb *req, int mask, int events) +static void __io_poll_execute(struct io_kiocb *req, int mask, __poll_t events) { - req->result = mask; + req->cqe.res = mask; /* * This is useful for poll that is armed on behalf of another * request, and where the wakeup path could be on a different * CPU. We want to avoid pulling in req->apoll->events for that * case. */ - req->cflags = events; + req->apoll_events = events; if (req->opcode == IORING_OP_POLL_ADD) req->io_task_work.func = io_poll_task_func; else req->io_task_work.func = io_apoll_task_func; - trace_io_uring_task_add(req->ctx, req, req->user_data, req->opcode, mask); - io_req_task_work_add(req, false); + trace_io_uring_task_add(req->ctx, req, req->cqe.user_data, req->opcode, mask); + io_req_task_work_add(req); } -static inline void io_poll_execute(struct io_kiocb *req, int res, int events) +static inline void io_poll_execute(struct io_kiocb *req, int res, + __poll_t events) { if (io_poll_get_ownership(req)) __io_poll_execute(req, res, events); @@ -6103,6 +7032,7 @@ static void io_poll_cancel_req(struct io_kiocb *req) #define wqe_to_req(wait) ((void *)((unsigned long) (wait)->private & ~1)) #define wqe_is_double(wait) ((unsigned long) (wait)->private & 1) +#define IO_ASYNC_POLL_COMMON (EPOLLONESHOT | EPOLLPRI) static int io_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, void *key) @@ -6137,7 +7067,7 @@ static int io_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, } /* for instances that support it check for an event match first */ - if (mask && !(mask & poll->events)) + if (mask && !(mask & (poll->events & ~IO_ASYNC_POLL_COMMON))) return 0; if (io_poll_get_ownership(req)) { @@ -6223,6 +7153,7 @@ static int __io_arm_poll_handler(struct io_kiocb *req, int v; INIT_HLIST_NODE(&req->hash_node); + req->work.cancel_seq = atomic_read(&ctx->cancel_seq); io_init_poll_iocb(poll, mask, io_poll_wake); poll->file = req->file; @@ -6261,7 +7192,6 @@ static int __io_arm_poll_handler(struct io_kiocb *req, __io_poll_execute(req, mask, poll->events); return 0; } - io_add_napi(req->file, req->ctx); /* * Release ownership. If someone tried to queue a tw while it was @@ -6294,28 +7224,34 @@ static int io_arm_poll_handler(struct io_kiocb *req, unsigned issue_flags) struct io_ring_ctx *ctx = req->ctx; struct async_poll *apoll; struct io_poll_table ipt; - __poll_t mask = EPOLLONESHOT | POLLERR | POLLPRI; + __poll_t mask = POLLPRI | POLLERR; int ret; if (!def->pollin && !def->pollout) return IO_APOLL_ABORTED; - if (!file_can_poll(req->file) || (req->flags & REQ_F_POLLED)) + if (!file_can_poll(req->file)) return IO_APOLL_ABORTED; + if ((req->flags & (REQ_F_POLLED|REQ_F_PARTIAL_IO)) == REQ_F_POLLED) + return IO_APOLL_ABORTED; + if (!(req->flags & REQ_F_APOLL_MULTISHOT)) + mask |= EPOLLONESHOT; if (def->pollin) { - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; /* If reading from MSG_ERRQUEUE using recvmsg, ignore POLLIN */ if ((req->opcode == IORING_OP_RECVMSG) && (req->sr_msg.msg_flags & MSG_ERRQUEUE)) - mask &= ~POLLIN; + mask &= ~EPOLLIN; } else { - mask |= POLLOUT | POLLWRNORM; + mask |= EPOLLOUT | EPOLLWRNORM; } if (def->poll_exclusive) mask |= EPOLLEXCLUSIVE; - if (!(issue_flags & IO_URING_F_UNLOCKED) && - !list_empty(&ctx->apoll_cache)) { + if (req->flags & REQ_F_POLLED) { + apoll = req->apoll; + } else if (!(issue_flags & IO_URING_F_UNLOCKED) && + !list_empty(&ctx->apoll_cache)) { apoll = list_first_entry(&ctx->apoll_cache, struct async_poll, poll.wait.entry); list_del_init(&apoll->poll.wait.entry); @@ -6335,7 +7271,7 @@ static int io_arm_poll_handler(struct io_kiocb *req, unsigned issue_flags) if (ret || ipt.error) return ret ? IO_APOLL_READY : IO_APOLL_ABORTED; - trace_io_uring_poll_arm(ctx, req, req->user_data, req->opcode, + trace_io_uring_poll_arm(ctx, req, req->cqe.user_data, req->opcode, mask, apoll->poll.events); return IO_APOLL_OK; } @@ -6368,24 +7304,53 @@ static __cold bool io_poll_remove_all(struct io_ring_ctx *ctx, return found; } -static struct io_kiocb *io_poll_find(struct io_ring_ctx *ctx, __u64 sqe_addr, - bool poll_only) +static struct io_kiocb *io_poll_find(struct io_ring_ctx *ctx, bool poll_only, + struct io_cancel_data *cd) __must_hold(&ctx->completion_lock) { struct hlist_head *list; struct io_kiocb *req; - list = &ctx->cancel_hash[hash_long(sqe_addr, ctx->cancel_hash_bits)]; + list = &ctx->cancel_hash[hash_long(cd->data, ctx->cancel_hash_bits)]; hlist_for_each_entry(req, list, hash_node) { - if (sqe_addr != req->user_data) + if (cd->data != req->cqe.user_data) continue; if (poll_only && req->opcode != IORING_OP_POLL_ADD) continue; + if (cd->flags & IORING_ASYNC_CANCEL_ALL) { + if (cd->seq == req->work.cancel_seq) + continue; + req->work.cancel_seq = cd->seq; + } return req; } return NULL; } +static struct io_kiocb *io_poll_file_find(struct io_ring_ctx *ctx, + struct io_cancel_data *cd) + __must_hold(&ctx->completion_lock) +{ + struct io_kiocb *req; + int i; + + for (i = 0; i < (1U << ctx->cancel_hash_bits); i++) { + struct hlist_head *list; + + list = &ctx->cancel_hash[i]; + hlist_for_each_entry(req, list, hash_node) { + if (!(cd->flags & IORING_ASYNC_CANCEL_ANY) && + req->file != cd->file) + continue; + if (cd->seq == req->work.cancel_seq) + continue; + req->work.cancel_seq = cd->seq; + return req; + } + } + return NULL; +} + static bool io_poll_disarm(struct io_kiocb *req) __must_hold(&ctx->completion_lock) { @@ -6396,12 +7361,15 @@ static bool io_poll_disarm(struct io_kiocb *req) return true; } -static int io_poll_cancel(struct io_ring_ctx *ctx, __u64 sqe_addr, - bool poll_only) +static int io_poll_cancel(struct io_ring_ctx *ctx, struct io_cancel_data *cd) __must_hold(&ctx->completion_lock) { - struct io_kiocb *req = io_poll_find(ctx, sqe_addr, poll_only); + struct io_kiocb *req; + if (cd->flags & (IORING_ASYNC_CANCEL_FD|IORING_ASYNC_CANCEL_ANY)) + req = io_poll_file_find(ctx, cd); + else + req = io_poll_find(ctx, false, cd); if (!req) return -ENOENT; io_poll_cancel_req(req); @@ -6428,9 +7396,7 @@ static int io_poll_update_prep(struct io_kiocb *req, struct io_poll_update *upd = &req->poll_update; u32 flags; - if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) - return -EINVAL; - if (sqe->ioprio || sqe->buf_index || sqe->splice_fd_in) + if (sqe->buf_index || sqe->splice_fd_in) return -EINVAL; flags = READ_ONCE(sqe->len); if (flags & ~(IORING_POLL_UPDATE_EVENTS | IORING_POLL_UPDATE_USER_DATA | @@ -6460,9 +7426,7 @@ static int io_poll_add_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe struct io_poll_iocb *poll = &req->poll; u32 flags; - if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) - return -EINVAL; - if (sqe->ioprio || sqe->buf_index || sqe->off || sqe->addr) + if (sqe->buf_index || sqe->off || sqe->addr) return -EINVAL; flags = READ_ONCE(sqe->len); if (flags & ~IORING_POLL_ADD_MULTI) @@ -6471,7 +7435,7 @@ static int io_poll_add_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe return -EINVAL; io_req_set_refcount(req); - req->cflags = poll->events = io_poll_parse_events(sqe, flags); + req->apoll_events = poll->events = io_poll_parse_events(sqe, flags); return 0; } @@ -6492,13 +7456,14 @@ static int io_poll_add(struct io_kiocb *req, unsigned int issue_flags) static int io_poll_update(struct io_kiocb *req, unsigned int issue_flags) { + struct io_cancel_data cd = { .data = req->poll_update.old_user_data, }; struct io_ring_ctx *ctx = req->ctx; struct io_kiocb *preq; int ret2, ret = 0; bool locked; spin_lock(&ctx->completion_lock); - preq = io_poll_find(ctx, req->poll_update.old_user_data, true); + preq = io_poll_find(ctx, true, &cd); if (!preq || !io_poll_disarm(preq)) { spin_unlock(&ctx->completion_lock); ret = preq ? -EALREADY : -ENOENT; @@ -6514,7 +7479,7 @@ static int io_poll_update(struct io_kiocb *req, unsigned int issue_flags) preq->poll.events |= IO_POLL_UNMASK; } if (req->poll_update.update_user_data) - preq->user_data = req->poll_update.new_user_data; + preq->cqe.user_data = req->poll_update.new_user_data; ret2 = io_poll_add(preq, issue_flags); /* successfully updated, don't complete poll request */ @@ -6523,7 +7488,7 @@ static int io_poll_update(struct io_kiocb *req, unsigned int issue_flags) } req_set_fail(preq); - preq->result = -ECANCELED; + preq->cqe.res = -ECANCELED; locked = !(issue_flags & IO_URING_F_UNLOCKED); io_req_task_complete(preq, &locked); out: @@ -6551,14 +7516,14 @@ static enum hrtimer_restart io_timeout_fn(struct hrtimer *timer) if (!(data->flags & IORING_TIMEOUT_ETIME_SUCCESS)) req_set_fail(req); - req->result = -ETIME; + req->cqe.res = -ETIME; req->io_task_work.func = io_req_task_complete; - io_req_task_work_add(req, false); + io_req_task_work_add(req); return HRTIMER_NORESTART; } static struct io_kiocb *io_timeout_extract(struct io_ring_ctx *ctx, - __u64 user_data) + struct io_cancel_data *cd) __must_hold(&ctx->timeout_lock) { struct io_timeout_data *io; @@ -6566,9 +7531,16 @@ static struct io_kiocb *io_timeout_extract(struct io_ring_ctx *ctx, bool found = false; list_for_each_entry(req, &ctx->timeout_list, timeout.list) { - found = user_data == req->user_data; - if (found) - break; + if (!(cd->flags & IORING_ASYNC_CANCEL_ANY) && + cd->data != req->cqe.user_data) + continue; + if (cd->flags & (IORING_ASYNC_CANCEL_ALL|IORING_ASYNC_CANCEL_ANY)) { + if (cd->seq == req->work.cancel_seq) + continue; + req->work.cancel_seq = cd->seq; + } + found = true; + break; } if (!found) return ERR_PTR(-ENOENT); @@ -6580,11 +7552,14 @@ static struct io_kiocb *io_timeout_extract(struct io_ring_ctx *ctx, return req; } -static int io_timeout_cancel(struct io_ring_ctx *ctx, __u64 user_data) +static int io_timeout_cancel(struct io_ring_ctx *ctx, struct io_cancel_data *cd) __must_hold(&ctx->completion_lock) - __must_hold(&ctx->timeout_lock) { - struct io_kiocb *req = io_timeout_extract(ctx, user_data); + struct io_kiocb *req; + + spin_lock_irq(&ctx->timeout_lock); + req = io_timeout_extract(ctx, cd); + spin_unlock_irq(&ctx->timeout_lock); if (IS_ERR(req)) return PTR_ERR(req); @@ -6617,7 +7592,7 @@ static int io_linked_timeout_update(struct io_ring_ctx *ctx, __u64 user_data, bool found = false; list_for_each_entry(req, &ctx->ltimeout_list, timeout.list) { - found = user_data == req->user_data; + found = user_data == req->cqe.user_data; if (found) break; } @@ -6637,7 +7612,8 @@ static int io_timeout_update(struct io_ring_ctx *ctx, __u64 user_data, struct timespec64 *ts, enum hrtimer_mode mode) __must_hold(&ctx->timeout_lock) { - struct io_kiocb *req = io_timeout_extract(ctx, user_data); + struct io_cancel_data cd = { .data = user_data, }; + struct io_kiocb *req = io_timeout_extract(ctx, &cd); struct io_timeout_data *data; if (IS_ERR(req)) @@ -6657,11 +7633,9 @@ static int io_timeout_remove_prep(struct io_kiocb *req, { struct io_timeout_rem *tr = &req->timeout_rem; - if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) - return -EINVAL; if (unlikely(req->flags & (REQ_F_FIXED_FILE | REQ_F_BUFFER_SELECT))) return -EINVAL; - if (sqe->ioprio || sqe->buf_index || sqe->len || sqe->splice_fd_in) + if (sqe->buf_index || sqe->len || sqe->splice_fd_in) return -EINVAL; tr->ltimeout = false; @@ -6702,10 +7676,10 @@ static int io_timeout_remove(struct io_kiocb *req, unsigned int issue_flags) int ret; if (!(req->timeout_rem.flags & IORING_TIMEOUT_UPDATE)) { + struct io_cancel_data cd = { .data = tr->addr, }; + spin_lock(&ctx->completion_lock); - spin_lock_irq(&ctx->timeout_lock); - ret = io_timeout_cancel(ctx, tr->addr); - spin_unlock_irq(&ctx->timeout_lock); + ret = io_timeout_cancel(ctx, &cd); spin_unlock(&ctx->completion_lock); } else { enum hrtimer_mode mode = io_translate_timeout_mode(tr->flags); @@ -6731,10 +7705,7 @@ static int io_timeout_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe, unsigned flags; u32 off = READ_ONCE(sqe->off); - if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) - return -EINVAL; - if (sqe->ioprio || sqe->buf_index || sqe->len != 1 || - sqe->splice_fd_in) + if (sqe->buf_index || sqe->len != 1 || sqe->splice_fd_in) return -EINVAL; if (off && is_timeout_link) return -EINVAL; @@ -6766,6 +7737,7 @@ static int io_timeout_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe, if (data->ts.tv_sec < 0 || data->ts.tv_nsec < 0) return -EINVAL; + INIT_LIST_HEAD(&req->timeout.list); data->mode = io_translate_timeout_mode(flags); hrtimer_init(&data->timer, io_timeout_get_clock(data), data->mode); @@ -6832,30 +7804,42 @@ add: return 0; } -struct io_cancel_data { - struct io_ring_ctx *ctx; - u64 user_data; -}; - static bool io_cancel_cb(struct io_wq_work *work, void *data) { struct io_kiocb *req = container_of(work, struct io_kiocb, work); struct io_cancel_data *cd = data; - return req->ctx == cd->ctx && req->user_data == cd->user_data; + if (req->ctx != cd->ctx) + return false; + if (cd->flags & IORING_ASYNC_CANCEL_ANY) { + ; + } else if (cd->flags & IORING_ASYNC_CANCEL_FD) { + if (req->file != cd->file) + return false; + } else { + if (req->cqe.user_data != cd->data) + return false; + } + if (cd->flags & (IORING_ASYNC_CANCEL_ALL|IORING_ASYNC_CANCEL_ANY)) { + if (cd->seq == req->work.cancel_seq) + return false; + req->work.cancel_seq = cd->seq; + } + return true; } -static int io_async_cancel_one(struct io_uring_task *tctx, u64 user_data, - struct io_ring_ctx *ctx) +static int io_async_cancel_one(struct io_uring_task *tctx, + struct io_cancel_data *cd) { - struct io_cancel_data data = { .ctx = ctx, .user_data = user_data, }; enum io_wq_cancel cancel_ret; int ret = 0; + bool all; if (!tctx || !tctx->io_wq) return -ENOENT; - cancel_ret = io_wq_cancel_cb(tctx->io_wq, io_cancel_cb, &data, false); + all = cd->flags & (IORING_ASYNC_CANCEL_ALL|IORING_ASYNC_CANCEL_ANY); + cancel_ret = io_wq_cancel_cb(tctx->io_wq, io_cancel_cb, cd, all); switch (cancel_ret) { case IO_WQ_CANCEL_OK: ret = 0; @@ -6871,14 +7855,14 @@ static int io_async_cancel_one(struct io_uring_task *tctx, u64 user_data, return ret; } -static int io_try_cancel_userdata(struct io_kiocb *req, u64 sqe_addr) +static int io_try_cancel(struct io_kiocb *req, struct io_cancel_data *cd) { struct io_ring_ctx *ctx = req->ctx; int ret; WARN_ON_ONCE(!io_wq_current_is_worker() && req->task != current); - ret = io_async_cancel_one(req->task->io_uring, sqe_addr, ctx); + ret = io_async_cancel_one(req->task->io_uring, cd); /* * Fall-through even for -EALREADY, as we may have poll armed * that need unarming. @@ -6887,56 +7871,98 @@ static int io_try_cancel_userdata(struct io_kiocb *req, u64 sqe_addr) return 0; spin_lock(&ctx->completion_lock); - ret = io_poll_cancel(ctx, sqe_addr, false); + ret = io_poll_cancel(ctx, cd); if (ret != -ENOENT) goto out; - - spin_lock_irq(&ctx->timeout_lock); - ret = io_timeout_cancel(ctx, sqe_addr); - spin_unlock_irq(&ctx->timeout_lock); + if (!(cd->flags & IORING_ASYNC_CANCEL_FD)) + ret = io_timeout_cancel(ctx, cd); out: spin_unlock(&ctx->completion_lock); return ret; } +#define CANCEL_FLAGS (IORING_ASYNC_CANCEL_ALL | IORING_ASYNC_CANCEL_FD | \ + IORING_ASYNC_CANCEL_ANY) + static int io_async_cancel_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { - if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) - return -EINVAL; - if (unlikely(req->flags & (REQ_F_FIXED_FILE | REQ_F_BUFFER_SELECT))) + if (unlikely(req->flags & REQ_F_BUFFER_SELECT)) return -EINVAL; - if (sqe->ioprio || sqe->off || sqe->len || sqe->cancel_flags || - sqe->splice_fd_in) + if (sqe->off || sqe->len || sqe->splice_fd_in) return -EINVAL; req->cancel.addr = READ_ONCE(sqe->addr); + req->cancel.flags = READ_ONCE(sqe->cancel_flags); + if (req->cancel.flags & ~CANCEL_FLAGS) + return -EINVAL; + if (req->cancel.flags & IORING_ASYNC_CANCEL_FD) { + if (req->cancel.flags & IORING_ASYNC_CANCEL_ANY) + return -EINVAL; + req->cancel.fd = READ_ONCE(sqe->fd); + } + return 0; } -static int io_async_cancel(struct io_kiocb *req, unsigned int issue_flags) +static int __io_async_cancel(struct io_cancel_data *cd, struct io_kiocb *req, + unsigned int issue_flags) { - struct io_ring_ctx *ctx = req->ctx; - u64 sqe_addr = req->cancel.addr; - bool needs_lock = issue_flags & IO_URING_F_UNLOCKED; + bool all = cd->flags & (IORING_ASYNC_CANCEL_ALL|IORING_ASYNC_CANCEL_ANY); + struct io_ring_ctx *ctx = cd->ctx; struct io_tctx_node *node; - int ret; + int ret, nr = 0; - ret = io_try_cancel_userdata(req, sqe_addr); - if (ret != -ENOENT) - goto done; + do { + ret = io_try_cancel(req, cd); + if (ret == -ENOENT) + break; + if (!all) + return ret; + nr++; + } while (1); /* slow path, try all io-wq's */ - io_ring_submit_lock(ctx, needs_lock); + io_ring_submit_lock(ctx, issue_flags); ret = -ENOENT; list_for_each_entry(node, &ctx->tctx_list, ctx_node) { struct io_uring_task *tctx = node->task->io_uring; - ret = io_async_cancel_one(tctx, req->cancel.addr, ctx); - if (ret != -ENOENT) - break; + ret = io_async_cancel_one(tctx, cd); + if (ret != -ENOENT) { + if (!all) + break; + nr++; + } } - io_ring_submit_unlock(ctx, needs_lock); + io_ring_submit_unlock(ctx, issue_flags); + return all ? nr : ret; +} + +static int io_async_cancel(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_cancel_data cd = { + .ctx = req->ctx, + .data = req->cancel.addr, + .flags = req->cancel.flags, + .seq = atomic_inc_return(&req->ctx->cancel_seq), + }; + int ret; + + if (cd.flags & IORING_ASYNC_CANCEL_FD) { + if (req->flags & REQ_F_FIXED_FILE) + req->file = io_file_get_fixed(req, req->cancel.fd, + issue_flags); + else + req->file = io_file_get_normal(req, req->cancel.fd); + if (!req->file) { + ret = -EBADF; + goto done; + } + cd.file = req->file; + } + + ret = __io_async_cancel(&cd, req, issue_flags); done: if (ret < 0) req_set_fail(req); @@ -6949,7 +7975,7 @@ static int io_rsrc_update_prep(struct io_kiocb *req, { if (unlikely(req->flags & (REQ_F_FIXED_FILE | REQ_F_BUFFER_SELECT))) return -EINVAL; - if (sqe->ioprio || sqe->rw_flags || sqe->splice_fd_in) + if (sqe->rw_flags || sqe->splice_fd_in) return -EINVAL; req->rsrc_update.offset = READ_ONCE(sqe->off); @@ -6963,7 +7989,6 @@ static int io_rsrc_update_prep(struct io_kiocb *req, static int io_files_update(struct io_kiocb *req, unsigned int issue_flags) { struct io_ring_ctx *ctx = req->ctx; - bool needs_lock = issue_flags & IO_URING_F_UNLOCKED; struct io_uring_rsrc_update2 up; int ret; @@ -6972,11 +7997,12 @@ static int io_files_update(struct io_kiocb *req, unsigned int issue_flags) up.nr = 0; up.tags = 0; up.resv = 0; + up.resv2 = 0; - io_ring_submit_lock(ctx, needs_lock); + io_ring_submit_lock(ctx, issue_flags); ret = __io_register_rsrc_update(ctx, IORING_RSRC_FILE, &up, req->rsrc_update.nr_args); - io_ring_submit_unlock(ctx, needs_lock); + io_ring_submit_unlock(ctx, issue_flags); if (ret < 0) req_set_fail(req); @@ -6988,15 +8014,14 @@ static int io_req_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { switch (req->opcode) { case IORING_OP_NOP: - return 0; + return io_nop_prep(req, sqe); case IORING_OP_READV: case IORING_OP_READ_FIXED: case IORING_OP_READ: - return io_read_prep(req, sqe); case IORING_OP_WRITEV: case IORING_OP_WRITE_FIXED: case IORING_OP_WRITE: - return io_write_prep(req, sqe); + return io_prep_rw(req, sqe); case IORING_OP_POLL_ADD: return io_poll_add_prep(req, sqe); case IORING_OP_POLL_REMOVE: @@ -7063,6 +8088,18 @@ static int io_req_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) return io_linkat_prep(req, sqe); case IORING_OP_MSG_RING: return io_msg_ring_prep(req, sqe); + case IORING_OP_FSETXATTR: + return io_fsetxattr_prep(req, sqe); + case IORING_OP_SETXATTR: + return io_setxattr_prep(req, sqe); + case IORING_OP_FGETXATTR: + return io_fgetxattr_prep(req, sqe); + case IORING_OP_GETXATTR: + return io_getxattr_prep(req, sqe); + case IORING_OP_SOCKET: + return io_socket_prep(req, sqe); + case IORING_OP_URING_CMD: + return io_uring_cmd_prep(req, sqe); } printk_once(KERN_WARNING "io_uring: unhandled opcode %d\n", @@ -7072,7 +8109,12 @@ static int io_req_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) static int io_req_prep_async(struct io_kiocb *req) { - if (!io_op_defs[req->opcode].needs_async_setup) + const struct io_op_def *def = &io_op_defs[req->opcode]; + + /* assign early for deferred execution for non-fixed file */ + if (def->needs_file && !(req->flags & REQ_F_FIXED_FILE)) + req->file = io_file_get_normal(req, req->cqe.fd); + if (!def->needs_async_setup) return 0; if (WARN_ON_ONCE(req_has_async_data(req))) return -EFAULT; @@ -7090,6 +8132,8 @@ static int io_req_prep_async(struct io_kiocb *req) return io_recvmsg_prep_async(req); case IORING_OP_CONNECT: return io_connect_prep_async(req); + case IORING_OP_URING_CMD: + return io_uring_cmd_prep_async(req); } printk_once(KERN_WARNING "io_uring: prep_async() bad opcode %d\n", req->opcode); @@ -7099,9 +8143,10 @@ static int io_req_prep_async(struct io_kiocb *req) static u32 io_get_sequence(struct io_kiocb *req) { u32 seq = req->ctx->cached_sq_head; + struct io_kiocb *cur; /* need original cached_sq_head, but it was increased for each req */ - io_for_each_link(req, req) + io_for_each_link(cur, req) seq--; return seq; } @@ -7144,7 +8189,7 @@ fail: goto queue; } - trace_io_uring_defer(ctx, req, req->user_data, req->opcode); + trace_io_uring_defer(ctx, req, req->cqe.user_data, req->opcode); de->req = req; de->seq = seq; list_add_tail(&de->list, &ctx->defer_list); @@ -7179,11 +8224,6 @@ static void io_clean_op(struct io_kiocb *req) kfree(io->free_iov); break; } - case IORING_OP_SPLICE: - case IORING_OP_TEE: - if (!(req->splice.flags & SPLICE_F_FD_IN_FIXED)) - io_put_file(req->splice.file_in); - break; case IORING_OP_OPENAT: case IORING_OP_OPENAT2: if (req->open.filename) @@ -7211,6 +8251,12 @@ static void io_clean_op(struct io_kiocb *req) if (req->statx.filename) putname(req->statx.filename); break; + case IORING_OP_SETXATTR: + case IORING_OP_FSETXATTR: + case IORING_OP_GETXATTR: + case IORING_OP_FGETXATTR: + __io_xattr_finish(req); + break; } } if ((req->flags & REQ_F_POLLED) && req->apoll) { @@ -7218,11 +8264,6 @@ static void io_clean_op(struct io_kiocb *req) kfree(req->apoll); req->apoll = NULL; } - if (req->flags & REQ_F_INFLIGHT) { - struct io_uring_task *tctx = req->task->io_uring; - - atomic_dec(&tctx->inflight_tracked); - } if (req->flags & REQ_F_CREDS) put_cred(req->creds); if (req->flags & REQ_F_ASYNC_DATA) { @@ -7232,11 +8273,27 @@ static void io_clean_op(struct io_kiocb *req) req->flags &= ~IO_REQ_CLEAN_FLAGS; } +static bool io_assign_file(struct io_kiocb *req, unsigned int issue_flags) +{ + if (req->file || !io_op_defs[req->opcode].needs_file) + return true; + + if (req->flags & REQ_F_FIXED_FILE) + req->file = io_file_get_fixed(req, req->cqe.fd, issue_flags); + else + req->file = io_file_get_normal(req, req->cqe.fd); + + return !!req->file; +} + static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags) { const struct cred *creds = NULL; int ret; + if (unlikely(!io_assign_file(req, issue_flags))) + return -EBADF; + if (unlikely((req->flags & REQ_F_CREDS) && req->creds != current_cred())) creds = override_creds(req->creds); @@ -7356,6 +8413,24 @@ static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags) case IORING_OP_MSG_RING: ret = io_msg_ring(req, issue_flags); break; + case IORING_OP_FSETXATTR: + ret = io_fsetxattr(req, issue_flags); + break; + case IORING_OP_SETXATTR: + ret = io_setxattr(req, issue_flags); + break; + case IORING_OP_FGETXATTR: + ret = io_fgetxattr(req, issue_flags); + break; + case IORING_OP_GETXATTR: + ret = io_getxattr(req, issue_flags); + break; + case IORING_OP_SOCKET: + ret = io_socket(req, issue_flags); + break; + case IORING_OP_URING_CMD: + ret = io_uring_cmd(req, issue_flags); + break; default: ret = -EINVAL; break; @@ -7386,10 +8461,10 @@ static struct io_wq_work *io_wq_free_work(struct io_wq_work *work) static void io_wq_submit_work(struct io_wq_work *work) { struct io_kiocb *req = container_of(work, struct io_kiocb, work); + const struct io_op_def *def = &io_op_defs[req->opcode]; unsigned int issue_flags = IO_URING_F_UNLOCKED; bool needs_poll = false; - struct io_kiocb *timeout; - int ret = 0; + int ret = 0, err = -ECANCELED; /* one will be dropped by ->io_free_work() after returning to io-wq */ if (!(req->flags & REQ_F_REFCOUNT)) @@ -7397,18 +8472,21 @@ static void io_wq_submit_work(struct io_wq_work *work) else req_ref_get(req); - timeout = io_prep_linked_timeout(req); - if (timeout) - io_queue_linked_timeout(timeout); + io_arm_ltimeout(req); /* either cancelled or io-wq is dying, so don't touch tctx->iowq */ if (work->flags & IO_WQ_WORK_CANCEL) { - io_req_task_queue_fail(req, -ECANCELED); +fail: + io_req_task_queue_fail(req, err); return; } + if (!io_assign_file(req, issue_flags)) { + err = -EBADF; + work->flags |= IO_WQ_WORK_CANCEL; + goto fail; + } if (req->flags & REQ_F_FORCE_ASYNC) { - const struct io_op_def *def = &io_op_defs[req->opcode]; bool opcode_poll = def->pollin || def->pollout; if (opcode_poll && file_can_poll(req->file)) { @@ -7427,6 +8505,8 @@ static void io_wq_submit_work(struct io_wq_work *work) * wait for request slots on the block side. */ if (!needs_poll) { + if (!(req->ctx->flags & IORING_SETUP_IOPOLL)) + break; cond_resched(); continue; } @@ -7465,54 +8545,69 @@ static void io_fixed_file_set(struct io_fixed_file *file_slot, struct file *file file_slot->file_ptr = file_ptr; } -static inline struct file *io_file_get_fixed(struct io_ring_ctx *ctx, - struct io_kiocb *req, int fd) +static inline struct file *io_file_get_fixed(struct io_kiocb *req, int fd, + unsigned int issue_flags) { - struct file *file; + struct io_ring_ctx *ctx = req->ctx; + struct file *file = NULL; unsigned long file_ptr; + io_ring_submit_lock(ctx, issue_flags); + if (unlikely((unsigned int)fd >= ctx->nr_user_files)) - return NULL; + goto out; fd = array_index_nospec(fd, ctx->nr_user_files); file_ptr = io_fixed_file_slot(&ctx->file_table, fd)->file_ptr; file = (struct file *) (file_ptr & FFS_MASK); file_ptr &= ~FFS_MASK; /* mask in overlapping REQ_F and FFS bits */ req->flags |= (file_ptr << REQ_F_SUPPORT_NOWAIT_BIT); - io_req_set_rsrc_node(req, ctx); + io_req_set_rsrc_node(req, ctx, 0); + WARN_ON_ONCE(file && !test_bit(fd, ctx->file_table.bitmap)); +out: + io_ring_submit_unlock(ctx, issue_flags); return file; } -static struct file *io_file_get_normal(struct io_ring_ctx *ctx, - struct io_kiocb *req, int fd) +/* + * Drop the file for requeue operations. Only used of req->file is the + * io_uring descriptor itself. + */ +static void io_drop_inflight_file(struct io_kiocb *req) +{ + if (unlikely(req->flags & REQ_F_INFLIGHT)) { + fput(req->file); + req->file = NULL; + req->flags &= ~REQ_F_INFLIGHT; + } +} + +static struct file *io_file_get_normal(struct io_kiocb *req, int fd) { struct file *file = fget(fd); - trace_io_uring_file_get(ctx, req, req->user_data, fd); + trace_io_uring_file_get(req->ctx, req, req->cqe.user_data, fd); /* we don't allow fixed io_uring files */ - if (file && unlikely(file->f_op == &io_uring_fops)) - io_req_track_inflight(req); + if (file && file->f_op == &io_uring_fops) + req->flags |= REQ_F_INFLIGHT; return file; } -static inline struct file *io_file_get(struct io_ring_ctx *ctx, - struct io_kiocb *req, int fd, bool fixed) -{ - if (fixed) - return io_file_get_fixed(ctx, req, fd); - else - return io_file_get_normal(ctx, req, fd); -} - static void io_req_task_link_timeout(struct io_kiocb *req, bool *locked) { struct io_kiocb *prev = req->timeout.prev; int ret = -ENOENT; if (prev) { - if (!(req->task->flags & PF_EXITING)) - ret = io_try_cancel_userdata(req, prev->user_data); + if (!(req->task->flags & PF_EXITING)) { + struct io_cancel_data cd = { + .ctx = req->ctx, + .data = prev->cqe.user_data, + }; + + ret = io_try_cancel(req, &cd); + } io_req_complete_post(req, ret ?: -ETIME, 0); io_put_req(prev); } else { @@ -7546,7 +8641,7 @@ static enum hrtimer_restart io_link_timeout_fn(struct hrtimer *timer) spin_unlock_irqrestore(&ctx->timeout_lock, flags); req->io_task_work.func = io_req_task_link_timeout; - io_req_task_work_add(req, false); + io_req_task_work_add(req); return HRTIMER_NORESTART; } @@ -7572,10 +8667,17 @@ static void io_queue_linked_timeout(struct io_kiocb *req) io_put_req(req); } -static void io_queue_sqe_arm_apoll(struct io_kiocb *req) +static void io_queue_async(struct io_kiocb *req, int ret) __must_hold(&req->ctx->uring_lock) { - struct io_kiocb *linked_timeout = io_prep_linked_timeout(req); + struct io_kiocb *linked_timeout; + + if (ret != -EAGAIN || (req->flags & REQ_F_NOWAIT)) { + io_req_complete_failed(req, ret); + return; + } + + linked_timeout = io_prep_linked_timeout(req); switch (io_arm_poll_handler(req, 0)) { case IO_APOLL_READY: @@ -7586,7 +8688,7 @@ static void io_queue_sqe_arm_apoll(struct io_kiocb *req) * Queued up for async execution, worker will release * submit reference when the iocb is actually submitted. */ - io_queue_async_work(req, NULL); + io_queue_iowq(req, NULL); break; case IO_APOLL_OK: break; @@ -7596,10 +8698,9 @@ static void io_queue_sqe_arm_apoll(struct io_kiocb *req) io_queue_linked_timeout(linked_timeout); } -static inline void __io_queue_sqe(struct io_kiocb *req) +static inline void io_queue_sqe(struct io_kiocb *req) __must_hold(&req->ctx->uring_lock) { - struct io_kiocb *linked_timeout; int ret; ret = io_issue_sqe(req, IO_URING_F_NONBLOCK|IO_URING_F_COMPLETE_DEFER); @@ -7612,22 +8713,23 @@ static inline void __io_queue_sqe(struct io_kiocb *req) * We async punt it if the file wasn't marked NOWAIT, or if the file * doesn't support non-blocking read/write attempts */ - if (likely(!ret)) { - linked_timeout = io_prep_linked_timeout(req); - if (linked_timeout) - io_queue_linked_timeout(linked_timeout); - } else if (ret == -EAGAIN && !(req->flags & REQ_F_NOWAIT)) { - io_queue_sqe_arm_apoll(req); - } else { - io_req_complete_failed(req, ret); - } + if (likely(!ret)) + io_arm_ltimeout(req); + else + io_queue_async(req, ret); } static void io_queue_sqe_fallback(struct io_kiocb *req) __must_hold(&req->ctx->uring_lock) { - if (req->flags & REQ_F_FAIL) { - io_req_complete_fail_submit(req); + if (unlikely(req->flags & REQ_F_FAIL)) { + /* + * We don't submit, fail them all, for that replace hardlinks + * with normal links. Extra REQ_F_LINK is tolerated. + */ + req->flags &= ~REQ_F_HARDLINK; + req->flags |= REQ_F_LINK; + io_req_complete_failed(req, req->cqe.res); } else if (unlikely(req->ctx->drain_active)) { io_drain_req(req); } else { @@ -7636,19 +8738,10 @@ static void io_queue_sqe_fallback(struct io_kiocb *req) if (unlikely(ret)) io_req_complete_failed(req, ret); else - io_queue_async_work(req, NULL); + io_queue_iowq(req, NULL); } } -static inline void io_queue_sqe(struct io_kiocb *req) - __must_hold(&req->ctx->uring_lock) -{ - if (likely(!(req->flags & (REQ_F_FORCE_ASYNC | REQ_F_FAIL)))) - __io_queue_sqe(req); - else - io_queue_sqe_fallback(req); -} - /* * Check SQE restrictions (opcode and flags). * @@ -7703,9 +8796,9 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, req->opcode = opcode = READ_ONCE(sqe->opcode); /* same numerical values with corresponding REQ_F_*, safe to copy */ req->flags = sqe_flags = READ_ONCE(sqe->flags); - req->user_data = READ_ONCE(sqe->user_data); + req->cqe.user_data = READ_ONCE(sqe->user_data); req->file = NULL; - req->fixed_rsrc_refs = NULL; + req->rsrc_node = NULL; req->task = current; if (unlikely(opcode >= IORING_OP_LAST)) { @@ -7716,9 +8809,11 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, /* enforce forwards compatibility on users */ if (sqe_flags & ~SQE_VALID_FLAGS) return -EINVAL; - if ((sqe_flags & IOSQE_BUFFER_SELECT) && - !io_op_defs[opcode].buffer_select) - return -EOPNOTSUPP; + if (sqe_flags & IOSQE_BUFFER_SELECT) { + if (!io_op_defs[opcode].buffer_select) + return -EOPNOTSUPP; + req->buf_index = READ_ONCE(sqe->buf_group); + } if (sqe_flags & IOSQE_CQE_SKIP_SUCCESS) ctx->drain_disabled = true; if (sqe_flags & IOSQE_IO_DRAIN) { @@ -7741,9 +8836,16 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, } } + if (!io_op_defs[opcode].ioprio && sqe->ioprio) + return -EINVAL; + if (!io_op_defs[opcode].iopoll && (ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; + if (io_op_defs[opcode].needs_file) { struct io_submit_state *state = &ctx->submit_state; + req->cqe.fd = READ_ONCE(sqe->fd); + /* * Plug now if we have more than 2 IO left after this, and the * target is potentially a read/write to block based storage. @@ -7753,11 +8855,6 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, state->need_plug = false; blk_start_plug_nr_ios(&state->plug, state->submit_nr); } - - req->file = io_file_get(ctx, req, READ_ONCE(sqe->fd), - (sqe_flags & IOSQE_FIXED_FILE)); - if (unlikely(!req->file)) - return -EBADF; } personality = READ_ONCE(sqe->personality); @@ -7779,7 +8876,44 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, return io_req_prep(req, sqe); } -static int io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, +static __cold int io_submit_fail_init(const struct io_uring_sqe *sqe, + struct io_kiocb *req, int ret) +{ + struct io_ring_ctx *ctx = req->ctx; + struct io_submit_link *link = &ctx->submit_state.link; + struct io_kiocb *head = link->head; + + trace_io_uring_req_failed(sqe, ctx, req, ret); + + /* + * Avoid breaking links in the middle as it renders links with SQPOLL + * unusable. Instead of failing eagerly, continue assembling the link if + * applicable and mark the head with REQ_F_FAIL. The link flushing code + * should find the flag and handle the rest. + */ + req_fail_link_node(req, ret); + if (head && !(head->flags & REQ_F_FAIL)) + req_fail_link_node(head, -ECANCELED); + + if (!(req->flags & IO_REQ_LINK_FLAGS)) { + if (head) { + link->last->link = req; + link->head = NULL; + req = head; + } + io_queue_sqe_fallback(req); + return ret; + } + + if (head) + link->last->link = req; + else + link->head = req; + link->last = req; + return 0; +} + +static inline int io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, const struct io_uring_sqe *sqe) __must_hold(&ctx->uring_lock) { @@ -7787,35 +8921,11 @@ static int io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, int ret; ret = io_init_req(ctx, req, sqe); - if (unlikely(ret)) { - trace_io_uring_req_failed(sqe, ctx, req, ret); - - /* fail even hard links since we don't submit */ - if (link->head) { - /* - * we can judge a link req is failed or cancelled by if - * REQ_F_FAIL is set, but the head is an exception since - * it may be set REQ_F_FAIL because of other req's failure - * so let's leverage req->result to distinguish if a head - * is set REQ_F_FAIL because of its failure or other req's - * failure so that we can set the correct ret code for it. - * init result here to avoid affecting the normal path. - */ - if (!(link->head->flags & REQ_F_FAIL)) - req_fail_link_node(link->head, -ECANCELED); - } else if (!(req->flags & (REQ_F_LINK | REQ_F_HARDLINK))) { - /* - * the current req is a normal req, we should return - * error and thus break the submittion loop. - */ - io_req_complete_failed(req, ret); - return ret; - } - req_fail_link_node(req, ret); - } + if (unlikely(ret)) + return io_submit_fail_init(sqe, req, ret); /* don't need @sqe from now on */ - trace_io_uring_submit_sqe(ctx, req, req->user_data, req->opcode, + trace_io_uring_submit_sqe(ctx, req, req->cqe.user_data, req->opcode, req->flags, true, ctx->flags & IORING_SETUP_SQPOLL); @@ -7826,29 +8936,32 @@ static int io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, * submitted sync once the chain is complete. If none of those * conditions are true (normal request), then just queue it. */ - if (link->head) { - struct io_kiocb *head = link->head; - - if (!(req->flags & REQ_F_FAIL)) { - ret = io_req_prep_async(req); - if (unlikely(ret)) { - req_fail_link_node(req, ret); - if (!(head->flags & REQ_F_FAIL)) - req_fail_link_node(head, -ECANCELED); - } - } - trace_io_uring_link(ctx, req, head); + if (unlikely(link->head)) { + ret = io_req_prep_async(req); + if (unlikely(ret)) + return io_submit_fail_init(sqe, req, ret); + + trace_io_uring_link(ctx, req, link->head); link->last->link = req; link->last = req; - if (req->flags & (REQ_F_LINK | REQ_F_HARDLINK)) + if (req->flags & IO_REQ_LINK_FLAGS) return 0; - /* last request of a link, enqueue the link */ + /* last request of the link, flush it */ + req = link->head; link->head = NULL; - req = head; - } else if (req->flags & (REQ_F_LINK | REQ_F_HARDLINK)) { - link->head = req; - link->last = req; + if (req->flags & (REQ_F_FORCE_ASYNC | REQ_F_FAIL)) + goto fallback; + + } else if (unlikely(req->flags & (IO_REQ_LINK_FLAGS | + REQ_F_FORCE_ASYNC | REQ_F_FAIL))) { + if (req->flags & IO_REQ_LINK_FLAGS) { + link->head = req; + link->last = req; + } else { +fallback: + io_queue_sqe_fallback(req); + } return 0; } @@ -7863,8 +8976,8 @@ static void io_submit_state_end(struct io_ring_ctx *ctx) { struct io_submit_state *state = &ctx->submit_state; - if (state->link.head) - io_queue_sqe(state->link.head); + if (unlikely(state->link.head)) + io_queue_sqe_fallback(state->link.head); /* flush only after queuing links as they can generate completions */ io_submit_flush_completions(ctx); if (state->plug_started) @@ -7918,8 +9031,12 @@ static const struct io_uring_sqe *io_get_sqe(struct io_ring_ctx *ctx) * though the application is the one updating it. */ head = READ_ONCE(ctx->sq_array[sq_idx]); - if (likely(head < ctx->sq_entries)) + if (likely(head < ctx->sq_entries)) { + /* double index for 128-byte SQEs, twice as long */ + if (ctx->flags & IORING_SETUP_SQE128) + head <<= 1; return &ctx->sq_sqes[head]; + } /* drop invalid entries */ ctx->cq_extra--; @@ -7932,54 +9049,52 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr) __must_hold(&ctx->uring_lock) { unsigned int entries = io_sqring_entries(ctx); - int submitted = 0; + unsigned int left; + int ret; if (unlikely(!entries)) return 0; /* make sure SQ entry isn't read before tail */ - nr = min3(nr, ctx->sq_entries, entries); - io_get_task_refs(nr); + ret = left = min3(nr, ctx->sq_entries, entries); + io_get_task_refs(left); + io_submit_state_start(&ctx->submit_state, left); - io_submit_state_start(&ctx->submit_state, nr); do { const struct io_uring_sqe *sqe; struct io_kiocb *req; - if (unlikely(!io_alloc_req_refill(ctx))) { - if (!submitted) - submitted = -EAGAIN; + if (unlikely(!io_alloc_req_refill(ctx))) break; - } req = io_alloc_req(ctx); sqe = io_get_sqe(ctx); if (unlikely(!sqe)) { - wq_stack_add_head(&req->comp_list, &ctx->submit_state.free_list); + io_req_add_to_cache(req, ctx); break; } - /* will complete beyond this point, count as submitted */ - submitted++; - if (io_submit_sqe(ctx, req, sqe)) { - /* - * Continue submitting even for sqe failure if the - * ring was setup with IORING_SETUP_SUBMIT_ALL - */ - if (!(ctx->flags & IORING_SETUP_SUBMIT_ALL)) - break; - } - } while (submitted < nr); - if (unlikely(submitted != nr)) { - int ref_used = (submitted == -EAGAIN) ? 0 : submitted; - int unused = nr - ref_used; + /* + * Continue submitting even for sqe failure if the + * ring was setup with IORING_SETUP_SUBMIT_ALL + */ + if (unlikely(io_submit_sqe(ctx, req, sqe)) && + !(ctx->flags & IORING_SETUP_SUBMIT_ALL)) { + left--; + break; + } + } while (--left); - current->io_uring->cached_refs += unused; + if (unlikely(left)) { + ret -= left; + /* try again if it submitted nothing and can't allocate a req */ + if (!ret && io_req_cache_empty(ctx)) + ret = -EAGAIN; + current->io_uring->cached_refs += left; } io_submit_state_end(ctx); /* Commit SQ ring head once we've consumed and submitted all SQEs */ io_commit_sqring(ctx); - - return submitted; + return ret; } static inline bool io_sqd_events_pending(struct io_sq_data *sqd) @@ -7987,23 +9102,6 @@ static inline bool io_sqd_events_pending(struct io_sq_data *sqd) return READ_ONCE(sqd->state); } -static inline void io_ring_set_wakeup_flag(struct io_ring_ctx *ctx) -{ - /* Tell userspace we may need a wakeup call */ - spin_lock(&ctx->completion_lock); - WRITE_ONCE(ctx->rings->sq_flags, - ctx->rings->sq_flags | IORING_SQ_NEED_WAKEUP); - spin_unlock(&ctx->completion_lock); -} - -static inline void io_ring_clear_wakeup_flag(struct io_ring_ctx *ctx) -{ - spin_lock(&ctx->completion_lock); - WRITE_ONCE(ctx->rings->sq_flags, - ctx->rings->sq_flags & ~IORING_SQ_NEED_WAKEUP); - spin_unlock(&ctx->completion_lock); -} - static int __io_sq_thread(struct io_ring_ctx *ctx, bool cap_entries) { unsigned int to_submit; @@ -8032,13 +9130,7 @@ static int __io_sq_thread(struct io_ring_ctx *ctx, bool cap_entries) !(ctx->flags & IORING_SETUP_R_DISABLED)) ret = io_submit_sqes(ctx, to_submit); mutex_unlock(&ctx->uring_lock); -#ifdef CONFIG_NET_RX_BUSY_POLL - spin_lock(&ctx->napi_lock); - if (!list_empty(&ctx->napi_list) && - io_napi_busy_loop(&ctx->napi_list)) - ++ret; - spin_unlock(&ctx->napi_lock); -#endif + if (to_submit && wq_has_sleeper(&ctx->sqo_sq_wait)) wake_up(&ctx->sqo_sq_wait); if (creds) @@ -8125,8 +9217,8 @@ static int io_sq_thread(void *data) bool needs_sched = true; list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) { - io_ring_set_wakeup_flag(ctx); - + atomic_or(IORING_SQ_NEED_WAKEUP, + &ctx->rings->sq_flags); if ((ctx->flags & IORING_SETUP_IOPOLL) && !wq_list_empty(&ctx->iopoll_list)) { needs_sched = false; @@ -8137,7 +9229,7 @@ static int io_sq_thread(void *data) * Ensure the store of the wakeup flag is not * reordered with the load of the SQ tail */ - smp_mb(); + smp_mb__after_atomic(); if (io_sqring_entries(ctx)) { needs_sched = false; @@ -8151,7 +9243,8 @@ static int io_sq_thread(void *data) mutex_lock(&sqd->lock); } list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) - io_ring_clear_wakeup_flag(ctx); + atomic_andnot(IORING_SQ_NEED_WAKEUP, + &ctx->rings->sq_flags); } finish_wait(&sqd->wait, &wait); @@ -8161,7 +9254,7 @@ static int io_sq_thread(void *data) io_uring_cancel_generic(true, sqd); sqd->thread = NULL; list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) - io_ring_set_wakeup_flag(ctx); + atomic_or(IORING_SQ_NEED_WAKEUP, &ctx->rings->sq_flags); io_run_task_work(); mutex_unlock(&sqd->lock); @@ -8176,9 +9269,6 @@ struct io_wait_queue { struct io_ring_ctx *ctx; unsigned cq_tail; unsigned nr_timeouts; -#ifdef CONFIG_NET_RX_BUSY_POLL - unsigned busy_poll_to; -#endif }; static inline bool io_should_wake(struct io_wait_queue *iowq) @@ -8204,7 +9294,8 @@ static int io_wake_function(struct wait_queue_entry *curr, unsigned int mode, * Cannot safely flush overflowed CQEs from here, ensure we wake up * the task, and the next invocation will do it. */ - if (io_should_wake(iowq) || test_bit(0, &iowq->ctx->check_cq_overflow)) + if (io_should_wake(iowq) || + test_bit(IO_CHECK_CQ_OVERFLOW_BIT, &iowq->ctx->check_cq)) return autoremove_wake_function(curr, mode, wake_flags, key); return -1; } @@ -8226,101 +9317,23 @@ static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx, ktime_t timeout) { int ret; + unsigned long check_cq; /* make sure we run task_work before checking for signals */ ret = io_run_task_work_sig(); if (ret || io_should_wake(iowq)) return ret; + check_cq = READ_ONCE(ctx->check_cq); /* let the caller flush overflows, retry */ - if (test_bit(0, &ctx->check_cq_overflow)) + if (check_cq & BIT(IO_CHECK_CQ_OVERFLOW_BIT)) return 1; - + if (unlikely(check_cq & BIT(IO_CHECK_CQ_DROPPED_BIT))) + return -EBADR; if (!schedule_hrtimeout(&timeout, HRTIMER_MODE_ABS)) return -ETIME; return 1; } -#ifdef CONFIG_NET_RX_BUSY_POLL -static void io_adjust_busy_loop_timeout(struct timespec64 *ts, - struct io_wait_queue *iowq) -{ - unsigned busy_poll_to = READ_ONCE(sysctl_net_busy_poll); - struct timespec64 pollto = ns_to_timespec64(1000 * (s64)busy_poll_to); - - if (timespec64_compare(ts, &pollto) > 0) { - *ts = timespec64_sub(*ts, pollto); - iowq->busy_poll_to = busy_poll_to; - } else { - u64 to = timespec64_to_ns(ts); - - do_div(to, 1000); - iowq->busy_poll_to = to; - ts->tv_sec = 0; - ts->tv_nsec = 0; - } -} - -static inline bool io_busy_loop_timeout(unsigned long start_time, - unsigned long bp_usec) -{ - if (bp_usec) { - unsigned long end_time = start_time + bp_usec; - unsigned long now = busy_loop_current_time(); - - return time_after(now, end_time); - } - return true; -} - -static bool io_busy_loop_end(void *p, unsigned long start_time) -{ - struct io_wait_queue *iowq = p; - - return signal_pending(current) || - io_should_wake(iowq) || - io_busy_loop_timeout(start_time, iowq->busy_poll_to); -} - -static void io_blocking_napi_busy_loop(struct list_head *napi_list, - struct io_wait_queue *iowq) -{ - unsigned long start_time = - list_is_singular(napi_list) ? 0 : - busy_loop_current_time(); - - do { - if (list_is_singular(napi_list)) { - struct napi_entry *ne = - list_first_entry(napi_list, - struct napi_entry, list); - - napi_busy_loop(ne->napi_id, io_busy_loop_end, iowq, - true, BUSY_POLL_BUDGET); - io_check_napi_entry_timeout(ne); - break; - } - } while (io_napi_busy_loop(napi_list) && - !io_busy_loop_end(iowq, start_time)); -} - -static void io_putback_napi_list(struct io_ring_ctx *ctx, - struct list_head *napi_list) -{ - struct napi_entry *cne, *lne; - - spin_lock(&ctx->napi_lock); - list_for_each_entry(cne, &ctx->napi_list, list) - list_for_each_entry(lne, napi_list, list) - if (cne->napi_id == lne->napi_id) { - list_del(&lne->list); - kfree(lne); - break; - } - list_splice(napi_list, &ctx->napi_list); - spin_unlock(&ctx->napi_lock); -} -#endif /* CONFIG_NET_RX_BUSY_POLL */ - /* * Wait until events become available, if we don't already have some. The * application must reap them itself, as they reside on the shared cq ring. @@ -8333,9 +9346,6 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, struct io_rings *rings = ctx->rings; ktime_t timeout = KTIME_MAX; int ret; -#ifdef CONFIG_NET_RX_BUSY_POLL - LIST_HEAD(local_napi_list); -#endif do { io_cqring_overflow_flush(ctx); @@ -8358,29 +9368,13 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, return ret; } -#ifdef CONFIG_NET_RX_BUSY_POLL - iowq.busy_poll_to = 0; - if (!(ctx->flags & IORING_SETUP_SQPOLL)) { - spin_lock(&ctx->napi_lock); - list_splice_init(&ctx->napi_list, &local_napi_list); - spin_unlock(&ctx->napi_lock); - } -#endif if (uts) { struct timespec64 ts; if (get_timespec64(&ts, uts)) return -EFAULT; -#ifdef CONFIG_NET_RX_BUSY_POLL - if (!list_empty(&local_napi_list)) - io_adjust_busy_loop_timeout(&ts, &iowq); -#endif timeout = ktime_add_ns(timespec64_to_ktime(ts), ktime_get_ns()); } -#ifdef CONFIG_NET_RX_BUSY_POLL - else if (!list_empty(&local_napi_list)) - iowq.busy_poll_to = READ_ONCE(sysctl_net_busy_poll); -#endif init_waitqueue_func_entry(&iowq.wq, io_wake_function); iowq.wq.private = current; @@ -8390,12 +9384,6 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, iowq.cq_tail = READ_ONCE(ctx->rings->cq.head) + min_events; trace_io_uring_cqring_wait(ctx, min_events); -#ifdef CONFIG_NET_RX_BUSY_POLL - if (iowq.busy_poll_to) - io_blocking_napi_busy_loop(&local_napi_list, &iowq); - if (!list_empty(&local_napi_list)) - io_putback_napi_list(ctx, &local_napi_list); -#endif do { /* if we can't even flush overflow, don't wait for more */ if (!io_cqring_overflow_flush(ctx)) { @@ -8405,10 +9393,10 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, prepare_to_wait_exclusive(&ctx->cq_wait, &iowq.wq, TASK_INTERRUPTIBLE); ret = io_cqring_wait_schedule(ctx, &iowq, timeout); - finish_wait(&ctx->cq_wait, &iowq.wq); cond_resched(); } while (ret > 0); + finish_wait(&ctx->cq_wait, &iowq.wq); restore_saved_sigmask_unless(ret == -EINTR); return READ_ONCE(rings->cq.head) == READ_ONCE(rings->cq.tail) ? ret : 0; @@ -8646,17 +9634,57 @@ static bool io_alloc_file_tables(struct io_file_table *table, unsigned nr_files) { table->files = kvcalloc(nr_files, sizeof(table->files[0]), GFP_KERNEL_ACCOUNT); - return !!table->files; + if (unlikely(!table->files)) + return false; + + table->bitmap = bitmap_zalloc(nr_files, GFP_KERNEL_ACCOUNT); + if (unlikely(!table->bitmap)) { + kvfree(table->files); + return false; + } + + return true; } static void io_free_file_tables(struct io_file_table *table) { kvfree(table->files); + bitmap_free(table->bitmap); table->files = NULL; + table->bitmap = NULL; +} + +static inline void io_file_bitmap_set(struct io_file_table *table, int bit) +{ + WARN_ON_ONCE(test_bit(bit, table->bitmap)); + __set_bit(bit, table->bitmap); + if (bit == table->alloc_hint) + table->alloc_hint++; +} + +static inline void io_file_bitmap_clear(struct io_file_table *table, int bit) +{ + __clear_bit(bit, table->bitmap); + table->alloc_hint = bit; } static void __io_sqe_files_unregister(struct io_ring_ctx *ctx) { +#if !defined(IO_URING_SCM_ALL) + int i; + + for (i = 0; i < ctx->nr_user_files; i++) { + struct file *file = io_file_from_index(ctx, i); + + if (!file) + continue; + if (io_fixed_file_slot(&ctx->file_table, i)->file_ptr & FFS_SCM) + continue; + io_file_bitmap_clear(&ctx->file_table, i); + fput(file); + } +#endif + #if defined(CONFIG_UNIX) if (ctx->ring_sock) { struct sock *sock = ctx->ring_sock->sk; @@ -8665,16 +9693,6 @@ static void __io_sqe_files_unregister(struct io_ring_ctx *ctx) while ((skb = skb_dequeue(&sock->sk_receive_queue)) != NULL) kfree_skb(skb); } -#else - int i; - - for (i = 0; i < ctx->nr_user_files; i++) { - struct file *file; - - file = io_file_from_index(ctx, i); - if (file) - fput(file); - } #endif io_free_file_tables(&ctx->file_table); io_rsrc_data_free(ctx->file_data); @@ -8819,103 +9837,66 @@ static struct io_sq_data *io_get_sq_data(struct io_uring_params *p, return sqd; } -#if defined(CONFIG_UNIX) /* * Ensure the UNIX gc is aware of our file set, so we are certain that * the io_uring can be safely unregistered on process exit, even if we have - * loops in the file referencing. + * loops in the file referencing. We account only files that can hold other + * files because otherwise they can't form a loop and so are not interesting + * for GC. */ -static int __io_sqe_files_scm(struct io_ring_ctx *ctx, int nr, int offset) +static int io_scm_file_account(struct io_ring_ctx *ctx, struct file *file) { +#if defined(CONFIG_UNIX) struct sock *sk = ctx->ring_sock->sk; + struct sk_buff_head *head = &sk->sk_receive_queue; struct scm_fp_list *fpl; struct sk_buff *skb; - int i, nr_files; - fpl = kzalloc(sizeof(*fpl), GFP_KERNEL); - if (!fpl) - return -ENOMEM; - - skb = alloc_skb(0, GFP_KERNEL); - if (!skb) { - kfree(fpl); - return -ENOMEM; - } + if (likely(!io_file_need_scm(file))) + return 0; - skb->sk = sk; + /* + * See if we can merge this file into an existing skb SCM_RIGHTS + * file set. If there's no room, fall back to allocating a new skb + * and filling it in. + */ + spin_lock_irq(&head->lock); + skb = skb_peek(head); + if (skb && UNIXCB(skb).fp->count < SCM_MAX_FD) + __skb_unlink(skb, head); + else + skb = NULL; + spin_unlock_irq(&head->lock); - nr_files = 0; - fpl->user = get_uid(current_user()); - for (i = 0; i < nr; i++) { - struct file *file = io_file_from_index(ctx, i + offset); + if (!skb) { + fpl = kzalloc(sizeof(*fpl), GFP_KERNEL); + if (!fpl) + return -ENOMEM; - if (!file) - continue; - fpl->fp[nr_files] = get_file(file); - unix_inflight(fpl->user, fpl->fp[nr_files]); - nr_files++; - } + skb = alloc_skb(0, GFP_KERNEL); + if (!skb) { + kfree(fpl); + return -ENOMEM; + } - if (nr_files) { + fpl->user = get_uid(current_user()); fpl->max = SCM_MAX_FD; - fpl->count = nr_files; + fpl->count = 0; + UNIXCB(skb).fp = fpl; + skb->sk = sk; skb->destructor = unix_destruct_scm; refcount_add(skb->truesize, &sk->sk_wmem_alloc); - skb_queue_head(&sk->sk_receive_queue, skb); - - for (i = 0; i < nr_files; i++) - fput(fpl->fp[i]); - } else { - kfree_skb(skb); - free_uid(fpl->user); - kfree(fpl); - } - - return 0; -} - -/* - * If UNIX sockets are enabled, fd passing can cause a reference cycle which - * causes regular reference counting to break down. We rely on the UNIX - * garbage collection to take care of this problem for us. - */ -static int io_sqe_files_scm(struct io_ring_ctx *ctx) -{ - unsigned left, total; - int ret = 0; - - total = 0; - left = ctx->nr_user_files; - while (left) { - unsigned this_files = min_t(unsigned, left, SCM_MAX_FD); - - ret = __io_sqe_files_scm(ctx, this_files, total); - if (ret) - break; - left -= this_files; - total += this_files; - } - - if (!ret) - return 0; - - while (total < ctx->nr_user_files) { - struct file *file = io_file_from_index(ctx, total); - - if (file) - fput(file); - total++; } - return ret; -} -#else -static int io_sqe_files_scm(struct io_ring_ctx *ctx) -{ + fpl = UNIXCB(skb).fp; + fpl->fp[fpl->count++] = get_file(file); + unix_inflight(fpl->user, file); + skb_queue_head(head, skb); + fput(file); +#endif return 0; } -#endif static void io_rsrc_file_put(struct io_ring_ctx *ctx, struct io_rsrc_put *prsrc) { @@ -8926,6 +9907,11 @@ static void io_rsrc_file_put(struct io_ring_ctx *ctx, struct io_rsrc_put *prsrc) struct sk_buff *skb; int i; + if (!io_file_need_scm(file)) { + fput(file); + return; + } + __skb_queue_head_init(&list); /* @@ -8990,15 +9976,17 @@ static void __io_rsrc_put_work(struct io_rsrc_node *ref_node) list_del(&prsrc->list); if (prsrc->tag) { - bool lock_ring = ctx->flags & IORING_SETUP_IOPOLL; + if (ctx->flags & IORING_SETUP_IOPOLL) + mutex_lock(&ctx->uring_lock); - io_ring_submit_lock(ctx, lock_ring); spin_lock(&ctx->completion_lock); io_fill_cqe_aux(ctx, prsrc->tag, 0, 0); io_commit_cqring(ctx); spin_unlock(&ctx->completion_lock); io_cqring_ev_posted(ctx); - io_ring_submit_unlock(ctx, lock_ring); + + if (ctx->flags & IORING_SETUP_IOPOLL) + mutex_unlock(&ctx->uring_lock); } rsrc_data->do_put(ctx, prsrc); @@ -9052,27 +10040,31 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, if (ret) return ret; - ret = -ENOMEM; - if (!io_alloc_file_tables(&ctx->file_table, nr_args)) - goto out_free; + if (!io_alloc_file_tables(&ctx->file_table, nr_args)) { + io_rsrc_data_free(ctx->file_data); + ctx->file_data = NULL; + return -ENOMEM; + } for (i = 0; i < nr_args; i++, ctx->nr_user_files++) { - if (copy_from_user(&fd, &fds[i], sizeof(fd))) { + struct io_fixed_file *file_slot; + + if (fds && copy_from_user(&fd, &fds[i], sizeof(fd))) { ret = -EFAULT; - goto out_fput; + goto fail; } /* allow sparse sets */ - if (fd == -1) { + if (!fds || fd == -1) { ret = -EINVAL; if (unlikely(*io_get_tag_slot(ctx->file_data, i))) - goto out_fput; + goto fail; continue; } file = fget(fd); ret = -EBADF; if (unlikely(!file)) - goto out_fput; + goto fail; /* * Don't allow io_uring instances to be registered. If UNIX @@ -9083,86 +10075,37 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, */ if (file->f_op == &io_uring_fops) { fput(file); - goto out_fput; + goto fail; } - io_fixed_file_set(io_fixed_file_slot(&ctx->file_table, i), file); - } - - ret = io_sqe_files_scm(ctx); - if (ret) { - __io_sqe_files_unregister(ctx); - return ret; - } - - io_rsrc_node_switch(ctx, NULL); - return ret; -out_fput: - for (i = 0; i < ctx->nr_user_files; i++) { - file = io_file_from_index(ctx, i); - if (file) + ret = io_scm_file_account(ctx, file); + if (ret) { fput(file); - } - io_free_file_tables(&ctx->file_table); - ctx->nr_user_files = 0; -out_free: - io_rsrc_data_free(ctx->file_data); - ctx->file_data = NULL; - return ret; -} - -static int io_sqe_file_register(struct io_ring_ctx *ctx, struct file *file, - int index) -{ -#if defined(CONFIG_UNIX) - struct sock *sock = ctx->ring_sock->sk; - struct sk_buff_head *head = &sock->sk_receive_queue; - struct sk_buff *skb; - - /* - * See if we can merge this file into an existing skb SCM_RIGHTS - * file set. If there's no room, fall back to allocating a new skb - * and filling it in. - */ - spin_lock_irq(&head->lock); - skb = skb_peek(head); - if (skb) { - struct scm_fp_list *fpl = UNIXCB(skb).fp; - - if (fpl->count < SCM_MAX_FD) { - __skb_unlink(skb, head); - spin_unlock_irq(&head->lock); - fpl->fp[fpl->count] = get_file(file); - unix_inflight(fpl->user, fpl->fp[fpl->count]); - fpl->count++; - spin_lock_irq(&head->lock); - __skb_queue_head(head, skb); - } else { - skb = NULL; + goto fail; } - } - spin_unlock_irq(&head->lock); - - if (skb) { - fput(file); - return 0; + file_slot = io_fixed_file_slot(&ctx->file_table, i); + io_fixed_file_set(file_slot, file); + io_file_bitmap_set(&ctx->file_table, i); } - return __io_sqe_files_scm(ctx, 1, index); -#else + io_rsrc_node_switch(ctx, NULL); return 0; -#endif +fail: + __io_sqe_files_unregister(ctx); + return ret; } static int io_queue_rsrc_removal(struct io_rsrc_data *data, unsigned idx, struct io_rsrc_node *node, void *rsrc) { + u64 *tag_slot = io_get_tag_slot(data, idx); struct io_rsrc_put *prsrc; prsrc = kzalloc(sizeof(*prsrc), GFP_KERNEL); if (!prsrc) return -ENOMEM; - prsrc->tag = *io_get_tag_slot(data, idx); + prsrc->tag = *tag_slot; + *tag_slot = 0; prsrc->rsrc = rsrc; list_add(&prsrc->list, &node->rsrc_list); return 0; @@ -9172,12 +10115,11 @@ static int io_install_fixed_file(struct io_kiocb *req, struct file *file, unsigned int issue_flags, u32 slot_index) { struct io_ring_ctx *ctx = req->ctx; - bool needs_lock = issue_flags & IO_URING_F_UNLOCKED; bool needs_switch = false; struct io_fixed_file *file_slot; int ret = -EBADF; - io_ring_submit_lock(ctx, needs_lock); + io_ring_submit_lock(ctx, issue_flags); if (file->f_op == &io_uring_fops) goto err; ret = -ENXIO; @@ -9203,22 +10145,20 @@ static int io_install_fixed_file(struct io_kiocb *req, struct file *file, if (ret) goto err; file_slot->file_ptr = 0; + io_file_bitmap_clear(&ctx->file_table, slot_index); needs_switch = true; } - *io_get_tag_slot(ctx->file_data, slot_index) = 0; - io_fixed_file_set(file_slot, file); - ret = io_sqe_file_register(ctx, file, slot_index); - if (ret) { - file_slot->file_ptr = 0; - goto err; + ret = io_scm_file_account(ctx, file); + if (!ret) { + *io_get_tag_slot(ctx->file_data, slot_index) = 0; + io_fixed_file_set(file_slot, file); + io_file_bitmap_set(&ctx->file_table, slot_index); } - - ret = 0; err: if (needs_switch) io_rsrc_node_switch(ctx, ctx->file_data); - io_ring_submit_unlock(ctx, needs_lock); + io_ring_submit_unlock(ctx, issue_flags); if (ret) fput(file); return ret; @@ -9228,12 +10168,11 @@ static int io_close_fixed(struct io_kiocb *req, unsigned int issue_flags) { unsigned int offset = req->close.file_slot - 1; struct io_ring_ctx *ctx = req->ctx; - bool needs_lock = issue_flags & IO_URING_F_UNLOCKED; struct io_fixed_file *file_slot; struct file *file; - int ret, i; + int ret; - io_ring_submit_lock(ctx, needs_lock); + io_ring_submit_lock(ctx, issue_flags); ret = -ENXIO; if (unlikely(!ctx->file_data)) goto out; @@ -9244,8 +10183,8 @@ static int io_close_fixed(struct io_kiocb *req, unsigned int issue_flags) if (ret) goto out; - i = array_index_nospec(offset, ctx->nr_user_files); - file_slot = io_fixed_file_slot(&ctx->file_table, i); + offset = array_index_nospec(offset, ctx->nr_user_files); + file_slot = io_fixed_file_slot(&ctx->file_table, offset); ret = -EBADF; if (!file_slot->file_ptr) goto out; @@ -9256,10 +10195,11 @@ static int io_close_fixed(struct io_kiocb *req, unsigned int issue_flags) goto out; file_slot->file_ptr = 0; + io_file_bitmap_clear(&ctx->file_table, offset); io_rsrc_node_switch(ctx, ctx->file_data); ret = 0; out: - io_ring_submit_unlock(ctx, needs_lock); + io_ring_submit_unlock(ctx, issue_flags); return ret; } @@ -9301,11 +10241,11 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx, if (file_slot->file_ptr) { file = (struct file *)(file_slot->file_ptr & FFS_MASK); - err = io_queue_rsrc_removal(data, up->offset + done, - ctx->rsrc_node, file); + err = io_queue_rsrc_removal(data, i, ctx->rsrc_node, file); if (err) break; file_slot->file_ptr = 0; + io_file_bitmap_clear(&ctx->file_table, i); needs_switch = true; } if (fd != -1) { @@ -9327,14 +10267,14 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx, err = -EBADF; break; } - *io_get_tag_slot(data, up->offset + done) = tag; - io_fixed_file_set(file_slot, file); - err = io_sqe_file_register(ctx, file, i); + err = io_scm_file_account(ctx, file); if (err) { - file_slot->file_ptr = 0; fput(file); break; } + *io_get_tag_slot(data, i) = tag; + io_fixed_file_set(file_slot, file); + io_file_bitmap_set(&ctx->file_table, i); } } @@ -9411,11 +10351,10 @@ static __cold int io_uring_alloc_task_context(struct task_struct *task, xa_init(&tctx->xa); init_waitqueue_head(&tctx->wait); atomic_set(&tctx->in_idle, 0); - atomic_set(&tctx->inflight_tracked, 0); task->io_uring = tctx; spin_lock_init(&tctx->task_lock); INIT_WQ_LIST(&tctx->task_list); - INIT_WQ_LIST(&tctx->prior_task_list); + INIT_WQ_LIST(&tctx->prio_task_list); init_task_work(&tctx->task_work, tctx_task_work); return 0; } @@ -9593,8 +10532,8 @@ static void *io_mem_alloc(size_t size) return (void *) __get_free_pages(gfp, get_order(size)); } -static unsigned long rings_size(unsigned sq_entries, unsigned cq_entries, - size_t *sq_offset) +static unsigned long rings_size(struct io_ring_ctx *ctx, unsigned int sq_entries, + unsigned int cq_entries, size_t *sq_offset) { struct io_rings *rings; size_t off, sq_array_size; @@ -9602,6 +10541,10 @@ static unsigned long rings_size(unsigned sq_entries, unsigned cq_entries, off = struct_size(rings, cqes, cq_entries); if (off == SIZE_MAX) return SIZE_MAX; + if (ctx->flags & IORING_SETUP_CQE32) { + if (check_shl_overflow(off, 1, &off)) + return SIZE_MAX; + } #ifdef CONFIG_SMP off = ALIGN(off, SMP_CACHE_BYTES); @@ -9763,30 +10706,18 @@ static int io_buffer_account_pin(struct io_ring_ctx *ctx, struct page **pages, return ret; } -static int io_sqe_buffer_register(struct io_ring_ctx *ctx, struct iovec *iov, - struct io_mapped_ubuf **pimu, - struct page **last_hpage) +static struct page **io_pin_pages(unsigned long ubuf, unsigned long len, + int *npages) { - struct io_mapped_ubuf *imu = NULL; + unsigned long start, end, nr_pages; struct vm_area_struct **vmas = NULL; struct page **pages = NULL; - unsigned long off, start, end, ubuf; - size_t size; - int ret, pret, nr_pages, i; + int i, pret, ret = -ENOMEM; - if (!iov->iov_base) { - *pimu = ctx->dummy_ubuf; - return 0; - } - - ubuf = (unsigned long) iov->iov_base; - end = (ubuf + iov->iov_len + PAGE_SIZE - 1) >> PAGE_SHIFT; + end = (ubuf + len + PAGE_SIZE - 1) >> PAGE_SHIFT; start = ubuf >> PAGE_SHIFT; nr_pages = end - start; - *pimu = NULL; - ret = -ENOMEM; - pages = kvmalloc_array(nr_pages, sizeof(struct page *), GFP_KERNEL); if (!pages) goto done; @@ -9796,10 +10727,6 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, struct iovec *iov, if (!vmas) goto done; - imu = kvmalloc(struct_size(imu, bvec, nr_pages), GFP_KERNEL); - if (!imu) - goto done; - ret = 0; mmap_read_lock(current->mm); pret = pin_user_pages(ubuf, nr_pages, FOLL_WRITE | FOLL_LONGTERM, @@ -9817,6 +10744,7 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, struct iovec *iov, break; } } + *npages = nr_pages; } else { ret = pret < 0 ? pret : -EFAULT; } @@ -9830,14 +10758,53 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, struct iovec *iov, unpin_user_pages(pages, pret); goto done; } + ret = 0; +done: + kvfree(vmas); + if (ret < 0) { + kvfree(pages); + pages = ERR_PTR(ret); + } + return pages; +} + +static int io_sqe_buffer_register(struct io_ring_ctx *ctx, struct iovec *iov, + struct io_mapped_ubuf **pimu, + struct page **last_hpage) +{ + struct io_mapped_ubuf *imu = NULL; + struct page **pages = NULL; + unsigned long off; + size_t size; + int ret, nr_pages, i; + + if (!iov->iov_base) { + *pimu = ctx->dummy_ubuf; + return 0; + } + + *pimu = NULL; + ret = -ENOMEM; + + pages = io_pin_pages((unsigned long) iov->iov_base, iov->iov_len, + &nr_pages); + if (IS_ERR(pages)) { + ret = PTR_ERR(pages); + pages = NULL; + goto done; + } - ret = io_buffer_account_pin(ctx, pages, pret, imu, last_hpage); + imu = kvmalloc(struct_size(imu, bvec, nr_pages), GFP_KERNEL); + if (!imu) + goto done; + + ret = io_buffer_account_pin(ctx, pages, nr_pages, imu, last_hpage); if (ret) { - unpin_user_pages(pages, pret); + unpin_user_pages(pages, nr_pages); goto done; } - off = ubuf & ~PAGE_MASK; + off = (unsigned long) iov->iov_base & ~PAGE_MASK; size = iov->iov_len; for (i = 0; i < nr_pages; i++) { size_t vec_len; @@ -9850,8 +10817,8 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, struct iovec *iov, size -= vec_len; } /* store original address for later verification */ - imu->ubuf = ubuf; - imu->ubuf_end = ubuf + iov->iov_len; + imu->ubuf = (unsigned long) iov->iov_base; + imu->ubuf_end = imu->ubuf + iov->iov_len; imu->nr_bvecs = nr_pages; *pimu = imu; ret = 0; @@ -9859,7 +10826,6 @@ done: if (ret) kvfree(imu); kvfree(pages); - kvfree(vmas); return ret; } @@ -9918,12 +10884,17 @@ static int io_sqe_buffers_register(struct io_ring_ctx *ctx, void __user *arg, } for (i = 0; i < nr_args; i++, ctx->nr_user_bufs++) { - ret = io_copy_iov(ctx, &iov, arg, i); - if (ret) - break; - ret = io_buffer_validate(&iov); - if (ret) - break; + if (arg) { + ret = io_copy_iov(ctx, &iov, arg, i); + if (ret) + break; + ret = io_buffer_validate(&iov); + if (ret) + break; + } else { + memset(&iov, 0, sizeof(iov)); + } + if (!iov.iov_base && *io_get_tag_slot(data, i)) { ret = -EINVAL; break; @@ -9986,7 +10957,7 @@ static int __io_sqe_buffers_update(struct io_ring_ctx *ctx, i = array_index_nospec(offset, ctx->nr_user_bufs); if (ctx->user_bufs[i] != ctx->dummy_ubuf) { - err = io_queue_rsrc_removal(ctx->buf_data, offset, + err = io_queue_rsrc_removal(ctx->buf_data, i, ctx->rsrc_node, ctx->user_bufs[i]); if (unlikely(err)) { io_buffer_unmap(ctx, &imu); @@ -10062,19 +11033,19 @@ static int io_eventfd_unregister(struct io_ring_ctx *ctx) static void io_destroy_buffers(struct io_ring_ctx *ctx) { + struct io_buffer_list *bl; + unsigned long index; int i; - for (i = 0; i < (1U << IO_BUFFERS_HASH_BITS); i++) { - struct list_head *list = &ctx->io_buffers[i]; - - while (!list_empty(list)) { - struct io_buffer_list *bl; + for (i = 0; i < BGID_ARRAY; i++) { + if (!ctx->io_bl) + break; + __io_remove_buffers(ctx, &ctx->io_bl[i], -1U); + } - bl = list_first_entry(list, struct io_buffer_list, list); - __io_remove_buffers(ctx, bl, -1U); - list_del(&bl->list); - kfree(bl); - } + xa_for_each(&ctx->io_bl_xa, index, bl) { + xa_erase(&ctx->io_bl_xa, bl->bgid); + __io_remove_buffers(ctx, bl, -1U); } while (!list_empty(&ctx->io_buffers_pages)) { @@ -10094,7 +11065,7 @@ static void io_req_caches_free(struct io_ring_ctx *ctx) mutex_lock(&ctx->uring_lock); io_flush_cached_locked_reqs(ctx, state); - while (state->free_list.next) { + while (!io_req_cache_empty(ctx)) { struct io_wq_work_node *node; struct io_kiocb *req; @@ -10181,10 +11152,10 @@ static __cold void io_ring_ctx_free(struct io_ring_ctx *ctx) io_req_caches_free(ctx); if (ctx->hash_map) io_wq_put_hash(ctx->hash_map); - io_free_napi_list(ctx); kfree(ctx->cancel_hash); kfree(ctx->dummy_ubuf); - kfree(ctx->io_buffers); + kfree(ctx->io_bl); + xa_destroy(&ctx->io_bl_xa); kfree(ctx); } @@ -10215,7 +11186,8 @@ static __poll_t io_uring_poll(struct file *file, poll_table *wait) * Users may get EPOLLIN meanwhile seeing nothing in cqring, this * pushs them to do the flush. */ - if (io_cqring_events(ctx) || test_bit(0, &ctx->check_cq_overflow)) + if (io_cqring_events(ctx) || + test_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq)) mask |= EPOLLIN | EPOLLRDNORM; return mask; @@ -10347,8 +11319,7 @@ static __cold bool io_kill_timeouts(struct io_ring_ctx *ctx, } } spin_unlock_irq(&ctx->timeout_lock); - if (canceled != 0) - io_commit_cqring(ctx); + io_commit_cqring(ctx); spin_unlock(&ctx->completion_lock); if (canceled != 0) io_cqring_ev_posted(ctx); @@ -10368,11 +11339,13 @@ static __cold void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx) io_unregister_personality(ctx, index); mutex_unlock(&ctx->uring_lock); - io_kill_timeouts(ctx, NULL, true); - io_poll_remove_all(ctx, NULL, true); - - /* if we failed setting up the ctx, we might not have any rings */ - io_iopoll_try_reap_events(ctx); + /* failed during ring init, it couldn't have issued any requests */ + if (ctx->rings) { + io_kill_timeouts(ctx, NULL, true); + io_poll_remove_all(ctx, NULL, true); + /* if we failed setting up the ctx, we might not have any rings */ + io_iopoll_try_reap_events(ctx); + } INIT_WORK(&ctx->exit_work, io_ring_exit_work); /* @@ -10464,6 +11437,10 @@ static __cold void io_uring_try_cancel_requests(struct io_ring_ctx *ctx, struct io_task_cancel cancel = { .task = task, .all = cancel_all, }; struct io_uring_task *tctx = task ? task->io_uring : NULL; + /* failed during ring init, it couldn't have issued any requests */ + if (!ctx->rings) + return; + while (1) { enum io_wq_cancel cret; bool ret = false; @@ -10604,7 +11581,7 @@ static __cold void io_uring_clean_tctx(struct io_uring_task *tctx) static s64 tctx_inflight(struct io_uring_task *tctx, bool tracked) { if (tracked) - return atomic_read(&tctx->inflight_tracked); + return 0; return percpu_counter_sum(&tctx->inflight); } @@ -10755,6 +11732,11 @@ static int io_ringfd_register(struct io_ring_ctx *ctx, void __user *__arg, break; } + if (reg.resv) { + ret = -EINVAL; + break; + } + if (reg.offset == -1U) { start = 0; end = IO_RINGFD_REG_MAX; @@ -10801,7 +11783,7 @@ static int io_ringfd_unregister(struct io_ring_ctx *ctx, void __user *__arg, ret = -EFAULT; break; } - if (reg.offset >= IO_RINGFD_REG_MAX) { + if (reg.resv || reg.data || reg.offset >= IO_RINGFD_REG_MAX) { ret = -EINVAL; break; } @@ -10904,6 +11886,19 @@ static int io_sqpoll_wait_sq(struct io_ring_ctx *ctx) return 0; } +static int io_validate_ext_arg(unsigned flags, const void __user *argp, size_t argsz) +{ + if (flags & IORING_ENTER_EXT_ARG) { + struct io_uring_getevents_arg arg; + + if (argsz != sizeof(arg)) + return -EINVAL; + if (copy_from_user(&arg, argp, sizeof(arg))) + return -EFAULT; + } + return 0; +} + static int io_get_ext_arg(unsigned flags, const void __user *argp, size_t *argsz, struct __kernel_timespec __user **ts, const sigset_t __user **sig) @@ -10928,6 +11923,8 @@ static int io_get_ext_arg(unsigned flags, const void __user *argp, size_t *argsz return -EINVAL; if (copy_from_user(&arg, argp, sizeof(arg))) return -EFAULT; + if (arg.pad) + return -EINVAL; *sig = u64_to_user_ptr(arg.sigmask); *argsz = arg.sigmask_sz; *ts = u64_to_user_ptr(arg.ts); @@ -10939,7 +11936,6 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit, size_t, argsz) { struct io_ring_ctx *ctx; - int submitted = 0; struct fd f; long ret; @@ -11002,39 +11998,64 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit, if (ret) goto out; } - submitted = to_submit; + ret = to_submit; } else if (to_submit) { ret = io_uring_add_tctx_node(ctx); if (unlikely(ret)) goto out; - mutex_lock(&ctx->uring_lock); - submitted = io_submit_sqes(ctx, to_submit); - mutex_unlock(&ctx->uring_lock); - if (submitted != to_submit) + mutex_lock(&ctx->uring_lock); + ret = io_submit_sqes(ctx, to_submit); + if (ret != to_submit) { + mutex_unlock(&ctx->uring_lock); goto out; + } + if ((flags & IORING_ENTER_GETEVENTS) && ctx->syscall_iopoll) + goto iopoll_locked; + mutex_unlock(&ctx->uring_lock); } if (flags & IORING_ENTER_GETEVENTS) { - const sigset_t __user *sig; - struct __kernel_timespec __user *ts; - - ret = io_get_ext_arg(flags, argp, &argsz, &ts, &sig); - if (unlikely(ret)) - goto out; + int ret2; + if (ctx->syscall_iopoll) { + /* + * We disallow the app entering submit/complete with + * polling, but we still need to lock the ring to + * prevent racing with polled issue that got punted to + * a workqueue. + */ + mutex_lock(&ctx->uring_lock); +iopoll_locked: + ret2 = io_validate_ext_arg(flags, argp, argsz); + if (likely(!ret2)) { + min_complete = min(min_complete, + ctx->cq_entries); + ret2 = io_iopoll_check(ctx, min_complete); + } + mutex_unlock(&ctx->uring_lock); + } else { + const sigset_t __user *sig; + struct __kernel_timespec __user *ts; + + ret2 = io_get_ext_arg(flags, argp, &argsz, &ts, &sig); + if (likely(!ret2)) { + min_complete = min(min_complete, + ctx->cq_entries); + ret2 = io_cqring_wait(ctx, min_complete, sig, + argsz, ts); + } + } - min_complete = min(min_complete, ctx->cq_entries); + if (!ret) { + ret = ret2; - /* - * When SETUP_IOPOLL and SETUP_SQPOLL are both enabled, user - * space applications don't need to do io completion events - * polling again, they can rely on io_sq_thread to do polling - * work, which can reduce cpu usage and uring_lock contention. - */ - if (ctx->flags & IORING_SETUP_IOPOLL && - !(ctx->flags & IORING_SETUP_SQPOLL)) { - ret = io_iopoll_check(ctx, min_complete); - } else { - ret = io_cqring_wait(ctx, min_complete, sig, argsz, ts); + /* + * EBADR indicates that one or more CQE were dropped. + * Once the user has been informed we can clear the bit + * as they are obviously ok with those drops. + */ + if (unlikely(ret2 == -EBADR)) + clear_bit(IO_CHECK_CQ_DROPPED_BIT, + &ctx->check_cq); } } @@ -11043,7 +12064,7 @@ out: out_fput: if (!(flags & IORING_ENTER_REGISTERED_RING)) fdput(f); - return submitted ? submitted : ret; + return ret; } #ifdef CONFIG_PROC_FS @@ -11090,10 +12111,15 @@ static __cold void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, unsigned int sq_tail = READ_ONCE(r->sq.tail); unsigned int cq_head = READ_ONCE(r->cq.head); unsigned int cq_tail = READ_ONCE(r->cq.tail); + unsigned int cq_shift = 0; unsigned int sq_entries, cq_entries; bool has_lock; + bool is_cqe32 = (ctx->flags & IORING_SETUP_CQE32); unsigned int i; + if (is_cqe32) + cq_shift = 1; + /* * we may get imprecise sqe and cqe info if uring is actively running * since we get cached_sq_head and cached_cq_tail without uring_lock @@ -11126,11 +12152,18 @@ static __cold void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, cq_entries = min(cq_tail - cq_head, ctx->cq_entries); for (i = 0; i < cq_entries; i++) { unsigned int entry = i + cq_head; - struct io_uring_cqe *cqe = &r->cqes[entry & cq_mask]; + struct io_uring_cqe *cqe = &r->cqes[(entry & cq_mask) << cq_shift]; - seq_printf(m, "%5u: user_data:%llu, res:%d, flag:%x\n", + if (!is_cqe32) { + seq_printf(m, "%5u: user_data:%llu, res:%d, flag:%x\n", entry & cq_mask, cqe->user_data, cqe->res, cqe->flags); + } else { + seq_printf(m, "%5u: user_data:%llu, res:%d, flag:%x, " + "extra1:%llu, extra2:%llu\n", + entry & cq_mask, cqe->user_data, cqe->res, + cqe->flags, cqe->big_cqe[0], cqe->big_cqe[1]); + } } /* @@ -11233,7 +12266,7 @@ static __cold int io_allocate_scq_urings(struct io_ring_ctx *ctx, ctx->sq_entries = p->sq_entries; ctx->cq_entries = p->cq_entries; - size = rings_size(p->sq_entries, p->cq_entries, &sq_array_offset); + size = rings_size(ctx, p->sq_entries, p->cq_entries, &sq_array_offset); if (size == SIZE_MAX) return -EOVERFLOW; @@ -11248,7 +12281,10 @@ static __cold int io_allocate_scq_urings(struct io_ring_ctx *ctx, rings->sq_ring_entries = p->sq_entries; rings->cq_ring_entries = p->cq_entries; - size = array_size(sizeof(struct io_uring_sqe), p->sq_entries); + if (p->flags & IORING_SETUP_SQE128) + size = array_size(2 * sizeof(struct io_uring_sqe), p->sq_entries); + else + size = array_size(sizeof(struct io_uring_sqe), p->sq_entries); if (size == SIZE_MAX) { io_mem_free(ctx->rings); ctx->rings = NULL; @@ -11360,11 +12396,41 @@ static __cold int io_uring_create(unsigned entries, struct io_uring_params *p, ctx = io_ring_ctx_alloc(p); if (!ctx) return -ENOMEM; + + /* + * When SETUP_IOPOLL and SETUP_SQPOLL are both enabled, user + * space applications don't need to do io completion events + * polling again, they can rely on io_sq_thread to do polling + * work, which can reduce cpu usage and uring_lock contention. + */ + if (ctx->flags & IORING_SETUP_IOPOLL && + !(ctx->flags & IORING_SETUP_SQPOLL)) + ctx->syscall_iopoll = 1; + ctx->compat = in_compat_syscall(); if (!capable(CAP_IPC_LOCK)) ctx->user = get_uid(current_user()); /* + * For SQPOLL, we just need a wakeup, always. For !SQPOLL, if + * COOP_TASKRUN is set, then IPIs are never needed by the app. + */ + ret = -EINVAL; + if (ctx->flags & IORING_SETUP_SQPOLL) { + /* IPI related flags don't make sense with SQPOLL */ + if (ctx->flags & (IORING_SETUP_COOP_TASKRUN | + IORING_SETUP_TASKRUN_FLAG)) + goto err; + ctx->notify_method = TWA_SIGNAL_NO_IPI; + } else if (ctx->flags & IORING_SETUP_COOP_TASKRUN) { + ctx->notify_method = TWA_SIGNAL_NO_IPI; + } else { + if (ctx->flags & IORING_SETUP_TASKRUN_FLAG) + goto err; + ctx->notify_method = TWA_SIGNAL; + } + + /* * This is just grabbed for accounting purposes. When a process exits, * the mm is exited and dropped before the files, hence we need to hang * on to this mm purely for the purposes of being able to unaccount @@ -11409,7 +12475,8 @@ static __cold int io_uring_create(unsigned entries, struct io_uring_params *p, IORING_FEAT_CUR_PERSONALITY | IORING_FEAT_FAST_POLL | IORING_FEAT_POLL_32BITS | IORING_FEAT_SQPOLL_NONFIXED | IORING_FEAT_EXT_ARG | IORING_FEAT_NATIVE_WORKERS | - IORING_FEAT_RSRC_TAGS | IORING_FEAT_CQE_SKIP; + IORING_FEAT_RSRC_TAGS | IORING_FEAT_CQE_SKIP | + IORING_FEAT_LINKED_FILE; if (copy_to_user(params, p, sizeof(*p))) { ret = -EFAULT; @@ -11460,10 +12527,12 @@ static long io_uring_setup(u32 entries, struct io_uring_params __user *params) if (p.flags & ~(IORING_SETUP_IOPOLL | IORING_SETUP_SQPOLL | IORING_SETUP_SQ_AFF | IORING_SETUP_CQSIZE | IORING_SETUP_CLAMP | IORING_SETUP_ATTACH_WQ | - IORING_SETUP_R_DISABLED | IORING_SETUP_SUBMIT_ALL)) + IORING_SETUP_R_DISABLED | IORING_SETUP_SUBMIT_ALL | + IORING_SETUP_COOP_TASKRUN | IORING_SETUP_TASKRUN_FLAG | + IORING_SETUP_SQE128 | IORING_SETUP_CQE32)) return -EINVAL; - return io_uring_create(entries, &p, params); + return io_uring_create(entries, &p, params); } SYSCALL_DEFINE2(io_uring_setup, u32, entries, @@ -11620,8 +12689,6 @@ static int __io_register_rsrc_update(struct io_ring_ctx *ctx, unsigned type, __u32 tmp; int err; - if (up->resv) - return -EINVAL; if (check_add_overflow(up->offset, nr_args, &tmp)) return -EOVERFLOW; err = io_rsrc_node_switch_start(ctx); @@ -11647,6 +12714,8 @@ static int io_register_files_update(struct io_ring_ctx *ctx, void __user *arg, memset(&up, 0, sizeof(up)); if (copy_from_user(&up, arg, sizeof(struct io_uring_rsrc_update))) return -EFAULT; + if (up.resv || up.resv2) + return -EINVAL; return __io_register_rsrc_update(ctx, IORING_RSRC_FILE, &up, nr_args); } @@ -11659,7 +12728,7 @@ static int io_register_rsrc_update(struct io_ring_ctx *ctx, void __user *arg, return -EINVAL; if (copy_from_user(&up, arg, sizeof(up))) return -EFAULT; - if (!up.nr || up.resv) + if (!up.nr || up.resv || up.resv2) return -EINVAL; return __io_register_rsrc_update(ctx, type, &up, up.nr); } @@ -11676,14 +12745,20 @@ static __cold int io_register_rsrc(struct io_ring_ctx *ctx, void __user *arg, memset(&rr, 0, sizeof(rr)); if (copy_from_user(&rr, arg, size)) return -EFAULT; - if (!rr.nr || rr.resv || rr.resv2) + if (!rr.nr || rr.resv2) + return -EINVAL; + if (rr.flags & ~IORING_RSRC_REGISTER_SPARSE) return -EINVAL; switch (type) { case IORING_RSRC_FILE: + if (rr.flags & IORING_RSRC_REGISTER_SPARSE && rr.data) + break; return io_sqe_files_register(ctx, u64_to_user_ptr(rr.data), rr.nr, u64_to_user_ptr(rr.tags)); case IORING_RSRC_BUFFER: + if (rr.flags & IORING_RSRC_REGISTER_SPARSE && rr.data) + break; return io_sqe_buffers_register(ctx, u64_to_user_ptr(rr.data), rr.nr, u64_to_user_ptr(rr.tags)); } @@ -11707,7 +12782,15 @@ static __cold int io_register_iowq_aff(struct io_ring_ctx *ctx, if (len > cpumask_size()) len = cpumask_size(); - if (copy_from_user(new_mask, arg, len)) { + if (in_compat_syscall()) { + ret = compat_get_bitmap(cpumask_bits(new_mask), + (const compat_ulong_t __user *)arg, + len * 8 /* CHAR_BIT */); + } else { + ret = copy_from_user(new_mask, arg, len); + } + + if (ret) { free_cpumask_var(new_mask); return -EFAULT; } @@ -11810,6 +12893,85 @@ err: return ret; } +static int io_register_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg) +{ + struct io_uring_buf_ring *br; + struct io_uring_buf_reg reg; + struct io_buffer_list *bl; + struct page **pages; + int nr_pages; + + if (copy_from_user(®, arg, sizeof(reg))) + return -EFAULT; + + if (reg.pad || reg.resv[0] || reg.resv[1] || reg.resv[2]) + return -EINVAL; + if (!reg.ring_addr) + return -EFAULT; + if (reg.ring_addr & ~PAGE_MASK) + return -EINVAL; + if (!is_power_of_2(reg.ring_entries)) + return -EINVAL; + + if (unlikely(reg.bgid < BGID_ARRAY && !ctx->io_bl)) { + int ret = io_init_bl_list(ctx); + if (ret) + return ret; + } + + bl = io_buffer_get_list(ctx, reg.bgid); + if (bl) { + /* if mapped buffer ring OR classic exists, don't allow */ + if (bl->buf_nr_pages || !list_empty(&bl->buf_list)) + return -EEXIST; + } else { + bl = kzalloc(sizeof(*bl), GFP_KERNEL); + if (!bl) + return -ENOMEM; + } + + pages = io_pin_pages(reg.ring_addr, + struct_size(br, bufs, reg.ring_entries), + &nr_pages); + if (IS_ERR(pages)) { + kfree(bl); + return PTR_ERR(pages); + } + + br = page_address(pages[0]); + bl->buf_pages = pages; + bl->buf_nr_pages = nr_pages; + bl->nr_entries = reg.ring_entries; + bl->buf_ring = br; + bl->mask = reg.ring_entries - 1; + io_buffer_add_list(ctx, bl, reg.bgid); + return 0; +} + +static int io_unregister_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg) +{ + struct io_uring_buf_reg reg; + struct io_buffer_list *bl; + + if (copy_from_user(®, arg, sizeof(reg))) + return -EFAULT; + if (reg.pad || reg.resv[0] || reg.resv[1] || reg.resv[2]) + return -EINVAL; + + bl = io_buffer_get_list(ctx, reg.bgid); + if (!bl) + return -ENOENT; + if (!bl->buf_nr_pages) + return -EINVAL; + + __io_remove_buffers(ctx, bl, -1U); + if (bl->bgid >= BGID_ARRAY) { + xa_erase(&ctx->io_bl_xa, bl->bgid); + kfree(bl); + } + return 0; +} + static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, void __user *arg, unsigned nr_args) __releases(ctx->uring_lock) @@ -11835,6 +12997,9 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, switch (opcode) { case IORING_REGISTER_BUFFERS: + ret = -EFAULT; + if (!arg) + break; ret = io_sqe_buffers_register(ctx, arg, nr_args, NULL); break; case IORING_UNREGISTER_BUFFERS: @@ -11844,6 +13009,9 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, ret = io_sqe_buffers_unregister(ctx); break; case IORING_REGISTER_FILES: + ret = -EFAULT; + if (!arg) + break; ret = io_sqe_files_register(ctx, arg, nr_args, NULL); break; case IORING_UNREGISTER_FILES: @@ -11938,6 +13106,18 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, case IORING_UNREGISTER_RING_FDS: ret = io_ringfd_unregister(ctx, arg, nr_args); break; + case IORING_REGISTER_PBUF_RING: + ret = -EINVAL; + if (!arg || nr_args != 1) + break; + ret = io_register_pbuf_ring(ctx, arg); + break; + case IORING_UNREGISTER_PBUF_RING: + ret = -EINVAL; + if (!arg || nr_args != 1) + break; + ret = io_unregister_pbuf_ring(ctx, arg); + break; default: ret = -EINVAL; break; @@ -12014,6 +13194,7 @@ static int __init io_uring_init(void) BUILD_BUG_SQE_ELEM(42, __u16, personality); BUILD_BUG_SQE_ELEM(44, __s32, splice_fd_in); BUILD_BUG_SQE_ELEM(44, __u32, file_index); + BUILD_BUG_SQE_ELEM(48, __u64, addr3); BUILD_BUG_ON(sizeof(struct io_uring_files_update) != sizeof(struct io_uring_rsrc_update)); @@ -12022,6 +13203,10 @@ static int __init io_uring_init(void) /* ->buf_index is u16 */ BUILD_BUG_ON(IORING_MAX_REG_BUFFERS >= (1u << 16)); + BUILD_BUG_ON(BGID_ARRAY * sizeof(struct io_buffer_list) > PAGE_SIZE); + BUILD_BUG_ON(offsetof(struct io_uring_buf_ring, bufs) != 0); + BUILD_BUG_ON(offsetof(struct io_uring_buf, resv) != + offsetof(struct io_uring_buf_ring, tail)); /* should fit into one byte */ BUILD_BUG_ON(SQE_VALID_FLAGS >= (1 << 8)); @@ -12031,6 +13216,10 @@ static int __init io_uring_init(void) BUILD_BUG_ON(ARRAY_SIZE(io_op_defs) != IORING_OP_LAST); BUILD_BUG_ON(__REQ_F_LAST_BIT > 8 * sizeof(int)); + BUILD_BUG_ON(sizeof(atomic_t) != sizeof(u32)); + + BUILD_BUG_ON(sizeof(struct io_uring_cmd) > 64); + req_cachep = KMEM_CACHE(io_kiocb, SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT); return 0; diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 8ce8720093b9..d2a9f699e17e 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -297,7 +297,7 @@ static loff_t iomap_readpage_iter(const struct iomap_iter *iter, /* * If the bio_alloc fails, try it again for a single page to * avoid having to deal with partial page reads. This emulates - * what do_mpage_readpage does. + * what do_mpage_read_folio does. */ if (!ctx->bio) { ctx->bio = bio_alloc(iomap->bdev, 1, REQ_OP_READ, @@ -320,10 +320,8 @@ done: return pos - orig_pos + plen; } -int -iomap_readpage(struct page *page, const struct iomap_ops *ops) +int iomap_read_folio(struct folio *folio, const struct iomap_ops *ops) { - struct folio *folio = page_folio(page); struct iomap_iter iter = { .inode = folio->mapping->host, .pos = folio_pos(folio), @@ -351,13 +349,13 @@ iomap_readpage(struct page *page, const struct iomap_ops *ops) } /* - * Just like mpage_readahead and block_read_full_page, we always - * return 0 and just mark the page as PageError on errors. This + * Just like mpage_readahead and block_read_full_folio, we always + * return 0 and just set the folio error flag on errors. This * should be cleaned up throughout the stack eventually. */ return 0; } -EXPORT_SYMBOL_GPL(iomap_readpage); +EXPORT_SYMBOL_GPL(iomap_read_folio); static loff_t iomap_readahead_iter(const struct iomap_iter *iter, struct iomap_readpage_ctx *ctx) @@ -454,25 +452,23 @@ bool iomap_is_partially_uptodate(struct folio *folio, size_t from, size_t count) } EXPORT_SYMBOL_GPL(iomap_is_partially_uptodate); -int -iomap_releasepage(struct page *page, gfp_t gfp_mask) +bool iomap_release_folio(struct folio *folio, gfp_t gfp_flags) { - struct folio *folio = page_folio(page); - - trace_iomap_releasepage(folio->mapping->host, folio_pos(folio), + trace_iomap_release_folio(folio->mapping->host, folio_pos(folio), folio_size(folio)); /* - * mm accommodates an old ext3 case where clean pages might not have had - * the dirty bit cleared. Thus, it can send actual dirty pages to - * ->releasepage() via shrink_active_list(); skip those here. + * mm accommodates an old ext3 case where clean folios might + * not have had the dirty bit cleared. Thus, it can send actual + * dirty folios to ->release_folio() via shrink_active_list(); + * skip those here. */ if (folio_test_dirty(folio) || folio_test_writeback(folio)) - return 0; + return false; iomap_page_release(folio); - return 1; + return true; } -EXPORT_SYMBOL_GPL(iomap_releasepage); +EXPORT_SYMBOL_GPL(iomap_release_folio); void iomap_invalidate_folio(struct folio *folio, size_t offset, size_t len) { @@ -531,7 +527,8 @@ iomap_write_failed(struct inode *inode, loff_t pos, unsigned len) * write started inside the existing inode size. */ if (pos + len > i_size) - truncate_pagecache_range(inode, max(pos, i_size), pos + len); + truncate_pagecache_range(inode, max(pos, i_size), + pos + len - 1); } static int iomap_read_folio_sync(loff_t block_start, struct folio *folio, @@ -663,10 +660,10 @@ static size_t __iomap_write_end(struct inode *inode, loff_t pos, size_t len, /* * The blocks that were entirely written will now be uptodate, so we - * don't have to worry about a readpage reading them and overwriting a + * don't have to worry about a read_folio reading them and overwriting a * partial write. However, if we've encountered a short write and only * partially written into a block, it will not be marked uptodate, so a - * readpage might come in and destroy our partial write. + * read_folio might come in and destroy our partial write. * * Do the simplest thing and just treat any short write to a * non-uptodate page as a zero-length write, and force the caller to @@ -733,7 +730,7 @@ static size_t iomap_write_end(struct iomap_iter *iter, loff_t pos, size_t len, folio_put(folio); if (ret < len) - iomap_write_failed(iter->inode, pos, len); + iomap_write_failed(iter->inode, pos + ret, len - ret); return ret; } @@ -1386,7 +1383,6 @@ iomap_writepage_map(struct iomap_writepage_ctx *wpc, if (wpc->ops->discard_folio) wpc->ops->discard_folio(folio, pos); if (!count) { - folio_clear_uptodate(folio); folio_unlock(folio); goto done; } @@ -1485,7 +1481,7 @@ iomap_do_writepage(struct page *page, struct writeback_control *wbc, void *data) * Skip the page if it's fully outside i_size, e.g. due to a * truncate operation that's in progress. We must redirty the * page so that reclaim stops reclaiming it. Otherwise - * iomap_vm_releasepage() is called on it and gets confused. + * iomap_release_folio() is called on it and gets confused. * * Note that the end_index is unsigned long. If the given * offset is greater than 16TB on a 32-bit system then if we diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c index b08f5dc31780..370c3241618a 100644 --- a/fs/iomap/direct-io.c +++ b/fs/iomap/direct-io.c @@ -51,12 +51,22 @@ struct iomap_dio { }; }; +static struct bio *iomap_dio_alloc_bio(const struct iomap_iter *iter, + struct iomap_dio *dio, unsigned short nr_vecs, unsigned int opf) +{ + if (dio->dops && dio->dops->bio_set) + return bio_alloc_bioset(iter->iomap.bdev, nr_vecs, opf, + GFP_KERNEL, dio->dops->bio_set); + return bio_alloc(iter->iomap.bdev, nr_vecs, opf, GFP_KERNEL); +} + static void iomap_dio_submit_bio(const struct iomap_iter *iter, struct iomap_dio *dio, struct bio *bio, loff_t pos) { atomic_inc(&dio->ref); - if (dio->iocb->ki_flags & IOCB_HIPRI) { + /* Sync dio can't be polled reliably */ + if ((dio->iocb->ki_flags & IOCB_HIPRI) && !is_sync_kiocb(dio->iocb)) { bio_set_polled(bio, dio->iocb); dio->submit.poll_bio = bio; } @@ -144,7 +154,7 @@ static inline void iomap_dio_set_error(struct iomap_dio *dio, int ret) cmpxchg(&dio->error, 0, ret); } -static void iomap_dio_bio_end_io(struct bio *bio) +void iomap_dio_bio_end_io(struct bio *bio) { struct iomap_dio *dio = bio->bi_private; bool should_dirty = (dio->flags & IOMAP_DIO_DIRTY); @@ -176,16 +186,16 @@ static void iomap_dio_bio_end_io(struct bio *bio) bio_put(bio); } } +EXPORT_SYMBOL_GPL(iomap_dio_bio_end_io); static void iomap_dio_zero(const struct iomap_iter *iter, struct iomap_dio *dio, loff_t pos, unsigned len) { struct inode *inode = file_inode(dio->iocb->ki_filp); struct page *page = ZERO_PAGE(0); - int flags = REQ_SYNC | REQ_IDLE; struct bio *bio; - bio = bio_alloc(iter->iomap.bdev, 1, REQ_OP_WRITE | flags, GFP_KERNEL); + bio = iomap_dio_alloc_bio(iter, dio, 1, REQ_OP_WRITE | REQ_SYNC | REQ_IDLE); fscrypt_set_bio_crypt_ctx(bio, inode, pos >> inode->i_blkbits, GFP_KERNEL); bio->bi_iter.bi_sector = iomap_sector(&iter->iomap, pos); @@ -265,8 +275,7 @@ static loff_t iomap_dio_bio_iter(const struct iomap_iter *iter, * cache flushes on IO completion. */ if (!(iomap->flags & (IOMAP_F_SHARED|IOMAP_F_DIRTY)) && - (dio->flags & IOMAP_DIO_WRITE_FUA) && - blk_queue_fua(bdev_get_queue(iomap->bdev))) + (dio->flags & IOMAP_DIO_WRITE_FUA) && bdev_fua(iomap->bdev)) use_fua = true; } @@ -311,7 +320,7 @@ static loff_t iomap_dio_bio_iter(const struct iomap_iter *iter, goto out; } - bio = bio_alloc(iomap->bdev, nr_pages, bio_opf, GFP_KERNEL); + bio = iomap_dio_alloc_bio(iter, dio, nr_pages, bio_opf); fscrypt_set_bio_crypt_ctx(bio, inode, pos >> inode->i_blkbits, GFP_KERNEL); bio->bi_iter.bi_sector = iomap_sector(iomap, pos); @@ -474,7 +483,7 @@ static loff_t iomap_dio_iter(const struct iomap_iter *iter, struct iomap_dio * __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, const struct iomap_ops *ops, const struct iomap_dio_ops *dops, - unsigned int dio_flags, size_t done_before) + unsigned int dio_flags, void *private, size_t done_before) { struct address_space *mapping = iocb->ki_filp->f_mapping; struct inode *inode = file_inode(iocb->ki_filp); @@ -483,6 +492,7 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, .pos = iocb->ki_pos, .len = iov_iter_count(iter), .flags = IOMAP_DIRECT, + .private = private, }; loff_t end = iomi.pos + iomi.len - 1, ret = 0; bool wait_for_completion = @@ -654,9 +664,7 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, if (!READ_ONCE(dio->submit.waiter)) break; - if (!dio->submit.poll_bio || - !bio_poll(dio->submit.poll_bio, NULL, 0)) - blk_io_schedule(); + blk_io_schedule(); } __set_current_state(TASK_RUNNING); } @@ -674,11 +682,12 @@ EXPORT_SYMBOL_GPL(__iomap_dio_rw); ssize_t iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, const struct iomap_ops *ops, const struct iomap_dio_ops *dops, - unsigned int dio_flags, size_t done_before) + unsigned int dio_flags, void *private, size_t done_before) { struct iomap_dio *dio; - dio = __iomap_dio_rw(iocb, iter, ops, dops, dio_flags, done_before); + dio = __iomap_dio_rw(iocb, iter, ops, dops, dio_flags, private, + done_before); if (IS_ERR_OR_NULL(dio)) return PTR_ERR_OR_ZERO(dio); return iomap_dio_complete(dio); diff --git a/fs/iomap/trace.h b/fs/iomap/trace.h index a6689a563c6e..d48868fc40d7 100644 --- a/fs/iomap/trace.h +++ b/fs/iomap/trace.h @@ -80,7 +80,7 @@ DEFINE_EVENT(iomap_range_class, name, \ TP_PROTO(struct inode *inode, loff_t off, u64 len),\ TP_ARGS(inode, off, len)) DEFINE_RANGE_EVENT(iomap_writepage); -DEFINE_RANGE_EVENT(iomap_releasepage); +DEFINE_RANGE_EVENT(iomap_release_folio); DEFINE_RANGE_EVENT(iomap_invalidate_folio); DEFINE_RANGE_EVENT(iomap_dio_invalidate_fail); diff --git a/fs/isofs/compress.c b/fs/isofs/compress.c index bc12ac7e2312..95a19f25d61c 100644 --- a/fs/isofs/compress.c +++ b/fs/isofs/compress.c @@ -296,8 +296,9 @@ static int zisofs_fill_pages(struct inode *inode, int full_page, int pcount, * per reference. We inject the additional pages into the page * cache as a form of readahead. */ -static int zisofs_readpage(struct file *file, struct page *page) +static int zisofs_read_folio(struct file *file, struct folio *folio) { + struct page *page = &folio->page; struct inode *inode = file_inode(file); struct address_space *mapping = inode->i_mapping; int err; @@ -369,7 +370,7 @@ static int zisofs_readpage(struct file *file, struct page *page) } const struct address_space_operations zisofs_aops = { - .readpage = zisofs_readpage, + .read_folio = zisofs_read_folio, /* No bmap operation supported */ }; diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c index d7491692aea3..88bf20303466 100644 --- a/fs/isofs/inode.c +++ b/fs/isofs/inode.c @@ -1174,9 +1174,9 @@ struct buffer_head *isofs_bread(struct inode *inode, sector_t block) return sb_bread(inode->i_sb, blknr); } -static int isofs_readpage(struct file *file, struct page *page) +static int isofs_read_folio(struct file *file, struct folio *folio) { - return mpage_readpage(page, isofs_get_block); + return mpage_read_folio(folio, isofs_get_block); } static void isofs_readahead(struct readahead_control *rac) @@ -1190,7 +1190,7 @@ static sector_t _isofs_bmap(struct address_space *mapping, sector_t block) } static const struct address_space_operations isofs_aops = { - .readpage = isofs_readpage, + .read_folio = isofs_read_folio, .readahead = isofs_readahead, .bmap = _isofs_bmap }; diff --git a/fs/isofs/rock.c b/fs/isofs/rock.c index 4880146babaf..48f58c6c9e69 100644 --- a/fs/isofs/rock.c +++ b/fs/isofs/rock.c @@ -687,11 +687,12 @@ int parse_rock_ridge_inode(struct iso_directory_record *de, struct inode *inode, } /* - * readpage() for symlinks: reads symlink contents into the page and either + * read_folio() for symlinks: reads symlink contents into the folio and either * makes it uptodate and returns 0 or returns error (-EIO) */ -static int rock_ridge_symlink_readpage(struct file *file, struct page *page) +static int rock_ridge_symlink_read_folio(struct file *file, struct folio *folio) { + struct page *page = &folio->page; struct inode *inode = page->mapping->host; struct iso_inode_info *ei = ISOFS_I(inode); struct isofs_sb_info *sbi = ISOFS_SB(inode->i_sb); @@ -804,5 +805,5 @@ error: } const struct address_space_operations isofs_symlink_aops = { - .readpage = rock_ridge_symlink_readpage + .read_folio = rock_ridge_symlink_read_folio }; diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index 5b9408e3b370..eb315e81f1a6 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -62,6 +62,7 @@ static void journal_end_buffer_io_sync(struct buffer_head *bh, int uptodate) */ static void release_buffer_page(struct buffer_head *bh) { + struct folio *folio; struct page *page; if (buffer_dirty(bh)) @@ -71,18 +72,19 @@ static void release_buffer_page(struct buffer_head *bh) page = bh->b_page; if (!page) goto nope; - if (page->mapping) + folio = page_folio(page); + if (folio->mapping) goto nope; /* OK, it's a truncated page */ - if (!trylock_page(page)) + if (!folio_trylock(folio)) goto nope; - get_page(page); + folio_get(folio); __brelse(bh); - try_to_free_buffers(page); - unlock_page(page); - put_page(page); + try_to_free_buffers(folio); + folio_unlock(folio); + folio_put(folio); return; nope: @@ -488,7 +490,6 @@ void jbd2_journal_commit_transaction(journal_t *journal) jbd2_journal_wait_updates(journal); commit_transaction->t_state = T_SWITCH; - write_unlock(&journal->j_state_lock); J_ASSERT (atomic_read(&commit_transaction->t_outstanding_credits) <= journal->j_max_transaction_buffers); @@ -508,6 +509,8 @@ void jbd2_journal_commit_transaction(journal_t *journal) * has reserved. This is consistent with the existing behaviour * that multiple jbd2_journal_get_write_access() calls to the same * buffer are perfectly permissible. + * We use journal->j_state_lock here to serialize processing of + * t_reserved_list with eviction of buffers from journal_unmap_buffer(). */ while (commit_transaction->t_reserved_list) { jh = commit_transaction->t_reserved_list; @@ -527,6 +530,7 @@ void jbd2_journal_commit_transaction(journal_t *journal) jbd2_journal_refile_buffer(journal, jh); } + write_unlock(&journal->j_state_lock); /* * Now try to drop any written-back buffers from the journal's * checkpoint lists. We do this *before* commit because it potentially diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index fcacafa4510d..c0cbeeaec2d1 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -1762,7 +1762,6 @@ static int __jbd2_journal_erase(journal_t *journal, unsigned int flags) unsigned long block, log_offset; /* logical */ unsigned long long phys_block, block_start, block_stop; /* physical */ loff_t byte_start, byte_stop, byte_count; - struct request_queue *q = bdev_get_queue(journal->j_dev); /* flags must be set to either discard or zeroout */ if ((flags & ~JBD2_JOURNAL_FLUSH_VALID) || !flags || @@ -1770,10 +1769,8 @@ static int __jbd2_journal_erase(journal_t *journal, unsigned int flags) (flags & JBD2_JOURNAL_FLUSH_ZEROOUT))) return -EINVAL; - if (!q) - return -ENXIO; - - if ((flags & JBD2_JOURNAL_FLUSH_DISCARD) && !blk_queue_discard(q)) + if ((flags & JBD2_JOURNAL_FLUSH_DISCARD) && + !bdev_max_discard_sectors(journal->j_dev)) return -EOPNOTSUPP; /* @@ -1828,7 +1825,7 @@ static int __jbd2_journal_erase(journal_t *journal, unsigned int flags) err = blkdev_issue_discard(journal->j_dev, byte_start >> SECTOR_SHIFT, byte_count >> SECTOR_SHIFT, - GFP_NOFS, 0); + GFP_NOFS); } else if (flags & JBD2_JOURNAL_FLUSH_ZEROOUT) { err = blkdev_issue_zeroout(journal->j_dev, byte_start >> SECTOR_SHIFT, diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index fcb9175016a5..e49bb0938376 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -2143,17 +2143,17 @@ out: * cannot happen because we never reallocate freed data as metadata * while the data is part of a transaction. Yes? * - * Return 0 on failure, 1 on success + * Return false on failure, true on success */ -int jbd2_journal_try_to_free_buffers(journal_t *journal, struct page *page) +bool jbd2_journal_try_to_free_buffers(journal_t *journal, struct folio *folio) { struct buffer_head *head; struct buffer_head *bh; - int ret = 0; + bool ret = false; - J_ASSERT(PageLocked(page)); + J_ASSERT(folio_test_locked(folio)); - head = page_buffers(page); + head = folio_buffers(folio); bh = head; do { struct journal_head *jh; @@ -2175,7 +2175,7 @@ int jbd2_journal_try_to_free_buffers(journal_t *journal, struct page *page) goto busy; } while ((bh = bh->b_this_page) != head); - ret = try_to_free_buffers(page); + ret = try_to_free_buffers(folio); busy: return ret; } @@ -2482,7 +2482,7 @@ int jbd2_journal_invalidate_folio(journal_t *journal, struct folio *folio, } while (bh != head); if (!partial_page) { - if (may_free && try_to_free_buffers(&folio->page)) + if (may_free && try_to_free_buffers(folio)) J_ASSERT(!folio_buffers(folio)); } return 0; diff --git a/fs/jffs2/file.c b/fs/jffs2/file.c index bd7d58d27bfc..ba86acbe12d3 100644 --- a/fs/jffs2/file.c +++ b/fs/jffs2/file.c @@ -25,9 +25,9 @@ static int jffs2_write_end(struct file *filp, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *pg, void *fsdata); static int jffs2_write_begin(struct file *filp, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, + loff_t pos, unsigned len, struct page **pagep, void **fsdata); -static int jffs2_readpage (struct file *filp, struct page *pg); +static int jffs2_read_folio(struct file *filp, struct folio *folio); int jffs2_fsync(struct file *filp, loff_t start, loff_t end, int datasync) { @@ -72,7 +72,7 @@ const struct inode_operations jffs2_file_inode_operations = const struct address_space_operations jffs2_file_address_operations = { - .readpage = jffs2_readpage, + .read_folio = jffs2_read_folio, .write_begin = jffs2_write_begin, .write_end = jffs2_write_end, }; @@ -110,27 +110,26 @@ static int jffs2_do_readpage_nolock (struct inode *inode, struct page *pg) return ret; } -int jffs2_do_readpage_unlock(void *data, struct page *pg) +int __jffs2_read_folio(struct file *file, struct folio *folio) { - int ret = jffs2_do_readpage_nolock(data, pg); - unlock_page(pg); + int ret = jffs2_do_readpage_nolock(folio->mapping->host, &folio->page); + folio_unlock(folio); return ret; } - -static int jffs2_readpage (struct file *filp, struct page *pg) +static int jffs2_read_folio(struct file *file, struct folio *folio) { - struct jffs2_inode_info *f = JFFS2_INODE_INFO(pg->mapping->host); + struct jffs2_inode_info *f = JFFS2_INODE_INFO(folio->mapping->host); int ret; mutex_lock(&f->sem); - ret = jffs2_do_readpage_unlock(pg->mapping->host, pg); + ret = __jffs2_read_folio(file, folio); mutex_unlock(&f->sem); return ret; } static int jffs2_write_begin(struct file *filp, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, + loff_t pos, unsigned len, struct page **pagep, void **fsdata) { struct page *pg; @@ -213,7 +212,7 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping, * page in read_cache_page(), which causes a deadlock. */ mutex_lock(&c->alloc_sem); - pg = grab_cache_page_write_begin(mapping, index, flags); + pg = grab_cache_page_write_begin(mapping, index); if (!pg) { ret = -ENOMEM; goto release_sem; diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c index 71f03a5d36ed..00a110f40e10 100644 --- a/fs/jffs2/fs.c +++ b/fs/jffs2/fs.c @@ -178,7 +178,7 @@ int jffs2_do_setattr (struct inode *inode, struct iattr *iattr) jffs2_complete_reservation(c); /* We have to do the truncate_setsize() without f->sem held, since - some pages may be locked and waiting for it in readpage(). + some pages may be locked and waiting for it in read_folio(). We are protected from a simultaneous write() extending i_size back past iattr->ia_size, because do_truncate() holds the generic inode semaphore. */ diff --git a/fs/jffs2/gc.c b/fs/jffs2/gc.c index 373b3b7c9f44..5c6602f3c189 100644 --- a/fs/jffs2/gc.c +++ b/fs/jffs2/gc.c @@ -1327,7 +1327,7 @@ static int jffs2_garbage_collect_dnode(struct jffs2_sb_info *c, struct jffs2_era * trying to write out, read_cache_page() will not deadlock. */ mutex_unlock(&f->sem); page = read_cache_page(inode->i_mapping, start >> PAGE_SHIFT, - jffs2_do_readpage_unlock, inode); + __jffs2_read_folio, NULL); if (IS_ERR(page)) { pr_warn("read_cache_page() returned error: %ld\n", PTR_ERR(page)); diff --git a/fs/jffs2/os-linux.h b/fs/jffs2/os-linux.h index 173eccac691d..921d782583d6 100644 --- a/fs/jffs2/os-linux.h +++ b/fs/jffs2/os-linux.h @@ -155,7 +155,7 @@ extern const struct file_operations jffs2_file_operations; extern const struct inode_operations jffs2_file_inode_operations; extern const struct address_space_operations jffs2_file_address_operations; int jffs2_fsync(struct file *, loff_t, loff_t, int); -int jffs2_do_readpage_unlock(void *data, struct page *pg); +int __jffs2_read_folio(struct file *file, struct folio *folio); /* ioctl.c */ long jffs2_ioctl(struct file *, unsigned int, unsigned long); diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c index d1943a7b4b04..a5dd7e53754a 100644 --- a/fs/jfs/inode.c +++ b/fs/jfs/inode.c @@ -293,9 +293,9 @@ static int jfs_writepages(struct address_space *mapping, return mpage_writepages(mapping, wbc, jfs_get_block); } -static int jfs_readpage(struct file *file, struct page *page) +static int jfs_read_folio(struct file *file, struct folio *folio) { - return mpage_readpage(page, jfs_get_block); + return mpage_read_folio(folio, jfs_get_block); } static void jfs_readahead(struct readahead_control *rac) @@ -314,13 +314,12 @@ static void jfs_write_failed(struct address_space *mapping, loff_t to) } static int jfs_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, + loff_t pos, unsigned len, struct page **pagep, void **fsdata) { int ret; - ret = nobh_write_begin(mapping, pos, len, flags, pagep, fsdata, - jfs_get_block); + ret = nobh_write_begin(mapping, pos, len, pagep, fsdata, jfs_get_block); if (unlikely(ret)) jfs_write_failed(mapping, pos + len); @@ -360,7 +359,7 @@ static ssize_t jfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) const struct address_space_operations jfs_aops = { .dirty_folio = block_dirty_folio, .invalidate_folio = block_invalidate_folio, - .readpage = jfs_readpage, + .read_folio = jfs_read_folio, .readahead = jfs_readahead, .writepage = jfs_writepage, .writepages = jfs_writepages, diff --git a/fs/jfs/ioctl.c b/fs/jfs/ioctl.c index 03a845ab4f00..1e7b177ece60 100644 --- a/fs/jfs/ioctl.c +++ b/fs/jfs/ioctl.c @@ -110,14 +110,13 @@ long jfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) case FITRIM: { struct super_block *sb = inode->i_sb; - struct request_queue *q = bdev_get_queue(sb->s_bdev); struct fstrim_range range; s64 ret = 0; if (!capable(CAP_SYS_ADMIN)) return -EPERM; - if (!blk_queue_discard(q)) { + if (!bdev_max_discard_sectors(sb->s_bdev)) { jfs_warn("FITRIM not supported on device"); return -EOPNOTSUPP; } @@ -127,7 +126,7 @@ long jfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) return -EFAULT; range.minlen = max_t(unsigned int, range.minlen, - q->limits.discard_granularity); + bdev_discard_granularity(sb->s_bdev)); ret = jfs_ioc_trim(inode, &range); if (ret < 0) diff --git a/fs/jfs/jfs_metapage.c b/fs/jfs/jfs_metapage.c index c4220ccdedef..387652ae14c2 100644 --- a/fs/jfs/jfs_metapage.c +++ b/fs/jfs/jfs_metapage.c @@ -467,8 +467,9 @@ err_out: return -EIO; } -static int metapage_readpage(struct file *fp, struct page *page) +static int metapage_read_folio(struct file *fp, struct folio *folio) { + struct page *page = &folio->page; struct inode *inode = page->mapping->host; struct bio *bio = NULL; int block_offset; @@ -523,29 +524,29 @@ add_failed: return -EIO; } -static int metapage_releasepage(struct page *page, gfp_t gfp_mask) +static bool metapage_release_folio(struct folio *folio, gfp_t gfp_mask) { struct metapage *mp; - int ret = 1; + bool ret = true; int offset; for (offset = 0; offset < PAGE_SIZE; offset += PSIZE) { - mp = page_to_mp(page, offset); + mp = page_to_mp(&folio->page, offset); if (!mp) continue; - jfs_info("metapage_releasepage: mp = 0x%p", mp); + jfs_info("metapage_release_folio: mp = 0x%p", mp); if (mp->count || mp->nohomeok || test_bit(META_dirty, &mp->flag)) { jfs_info("count = %ld, nohomeok = %d", mp->count, mp->nohomeok); - ret = 0; + ret = false; continue; } if (mp->lsn) remove_from_logsync(mp); - remove_metapage(page, mp); + remove_metapage(&folio->page, mp); INCREMENT(mpStat.pagefree); free_metapage(mp); } @@ -559,13 +560,13 @@ static void metapage_invalidate_folio(struct folio *folio, size_t offset, BUG_ON(folio_test_writeback(folio)); - metapage_releasepage(&folio->page, 0); + metapage_release_folio(folio, 0); } const struct address_space_operations jfs_metapage_aops = { - .readpage = metapage_readpage, + .read_folio = metapage_read_folio, .writepage = metapage_writepage, - .releasepage = metapage_releasepage, + .release_folio = metapage_release_folio, .invalidate_folio = metapage_invalidate_folio, .dirty_folio = filemap_dirty_folio, }; diff --git a/fs/jfs/super.c b/fs/jfs/super.c index f1a13a74cddf..85d4f44f2ac4 100644 --- a/fs/jfs/super.c +++ b/fs/jfs/super.c @@ -372,19 +372,16 @@ static int parse_options(char *options, struct super_block *sb, s64 *newLVSize, } case Opt_discard: - { - struct request_queue *q = bdev_get_queue(sb->s_bdev); /* if set to 1, even copying files will cause * trimming :O * -> user has more control over the online trimming */ sbi->minblks_trim = 64; - if (blk_queue_discard(q)) + if (bdev_max_discard_sectors(sb->s_bdev)) *flag |= JFS_DISCARD; else pr_err("JFS: discard option not supported on device\n"); break; - } case Opt_nodiscard: *flag &= ~JFS_DISCARD; @@ -392,10 +389,9 @@ static int parse_options(char *options, struct super_block *sb, s64 *newLVSize, case Opt_discard_minblk: { - struct request_queue *q = bdev_get_queue(sb->s_bdev); char *minblks_trim = args[0].from; int rc; - if (blk_queue_discard(q)) { + if (bdev_max_discard_sectors(sb->s_bdev)) { *flag |= JFS_DISCARD; rc = kstrtouint(minblks_trim, 0, &sbi->minblks_trim); diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index 61a8edc4ba8b..e205fde7163a 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -1406,7 +1406,12 @@ static void __kernfs_remove(struct kernfs_node *kn) */ void kernfs_remove(struct kernfs_node *kn) { - struct kernfs_root *root = kernfs_root(kn); + struct kernfs_root *root; + + if (!kn) + return; + + root = kernfs_root(kn); down_write(&root->kernfs_rwsem); __kernfs_remove(kn); diff --git a/fs/ksmbd/misc.c b/fs/ksmbd/misc.c index 60e7ac62c917..1e2076a53bed 100644 --- a/fs/ksmbd/misc.c +++ b/fs/ksmbd/misc.c @@ -158,19 +158,41 @@ out: * Return : windows path string or error */ -char *convert_to_nt_pathname(char *filename) +char *convert_to_nt_pathname(struct ksmbd_share_config *share, + struct path *path) { - char *ab_pathname; + char *pathname, *ab_pathname, *nt_pathname; + int share_path_len = share->path_sz; - if (strlen(filename) == 0) - filename = "\\"; + pathname = kmalloc(PATH_MAX, GFP_KERNEL); + if (!pathname) + return ERR_PTR(-EACCES); - ab_pathname = kstrdup(filename, GFP_KERNEL); - if (!ab_pathname) - return NULL; + ab_pathname = d_path(path, pathname, PATH_MAX); + if (IS_ERR(ab_pathname)) { + nt_pathname = ERR_PTR(-EACCES); + goto free_pathname; + } + + if (strncmp(ab_pathname, share->path, share_path_len)) { + nt_pathname = ERR_PTR(-EACCES); + goto free_pathname; + } + + nt_pathname = kzalloc(strlen(&ab_pathname[share_path_len]) + 2, GFP_KERNEL); + if (!nt_pathname) { + nt_pathname = ERR_PTR(-ENOMEM); + goto free_pathname; + } + if (ab_pathname[share_path_len] == '\0') + strcpy(nt_pathname, "/"); + strcat(nt_pathname, &ab_pathname[share_path_len]); + + ksmbd_conv_path_to_windows(nt_pathname); - ksmbd_conv_path_to_windows(ab_pathname); - return ab_pathname; +free_pathname: + kfree(pathname); + return nt_pathname; } int get_nlink(struct kstat *st) diff --git a/fs/ksmbd/misc.h b/fs/ksmbd/misc.h index 253366bd0951..aae2a252945f 100644 --- a/fs/ksmbd/misc.h +++ b/fs/ksmbd/misc.h @@ -14,7 +14,8 @@ struct ksmbd_file; int match_pattern(const char *str, size_t len, const char *pattern); int ksmbd_validate_filename(char *filename); int parse_stream_name(char *filename, char **stream_name, int *s_type); -char *convert_to_nt_pathname(char *filename); +char *convert_to_nt_pathname(struct ksmbd_share_config *share, + struct path *path); int get_nlink(struct kstat *st); void ksmbd_conv_path_to_unix(char *path); void ksmbd_strip_last_slash(char *path); diff --git a/fs/ksmbd/oplock.c b/fs/ksmbd/oplock.c index 23871b18a429..8b5560574d4c 100644 --- a/fs/ksmbd/oplock.c +++ b/fs/ksmbd/oplock.c @@ -1694,33 +1694,3 @@ out: read_unlock(&lease_list_lock); return ret_op; } - -int smb2_check_durable_oplock(struct ksmbd_file *fp, - struct lease_ctx_info *lctx, char *name) -{ - struct oplock_info *opinfo = opinfo_get(fp); - int ret = 0; - - if (opinfo && opinfo->is_lease) { - if (!lctx) { - pr_err("open does not include lease\n"); - ret = -EBADF; - goto out; - } - if (memcmp(opinfo->o_lease->lease_key, lctx->lease_key, - SMB2_LEASE_KEY_SIZE)) { - pr_err("invalid lease key\n"); - ret = -EBADF; - goto out; - } - if (name && strcmp(fp->filename, name)) { - pr_err("invalid name reconnect %s\n", name); - ret = -EINVAL; - goto out; - } - } -out: - if (opinfo) - opinfo_put(opinfo); - return ret; -} diff --git a/fs/ksmbd/oplock.h b/fs/ksmbd/oplock.h index 0cf7a2b5bbc0..09753448f779 100644 --- a/fs/ksmbd/oplock.h +++ b/fs/ksmbd/oplock.h @@ -124,6 +124,4 @@ struct oplock_info *lookup_lease_in_table(struct ksmbd_conn *conn, int find_same_lease_key(struct ksmbd_session *sess, struct ksmbd_inode *ci, struct lease_ctx_info *lctx); void destroy_lease_table(struct ksmbd_conn *conn); -int smb2_check_durable_oplock(struct ksmbd_file *fp, - struct lease_ctx_info *lctx, char *name); #endif /* __KSMBD_OPLOCK_H */ diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c index 3bf6c56c654c..16c803a9d996 100644 --- a/fs/ksmbd/smb2pdu.c +++ b/fs/ksmbd/smb2pdu.c @@ -11,6 +11,7 @@ #include <linux/statfs.h> #include <linux/ethtool.h> #include <linux/falloc.h> +#include <linux/mount.h> #include "glob.h" #include "smbfsctl.h" @@ -2918,7 +2919,6 @@ int smb2_open(struct ksmbd_work *work) goto err_out; } - fp->filename = name; fp->cdoption = req->CreateDisposition; fp->daccess = daccess; fp->saccess = req->ShareAccess; @@ -3270,14 +3270,13 @@ err_out1: if (!rsp->hdr.Status) rsp->hdr.Status = STATUS_UNEXPECTED_IO_ERROR; - if (!fp || !fp->filename) - kfree(name); if (fp) ksmbd_fd_put(work, fp); smb2_set_err_rsp(work); ksmbd_debug(SMB, "Error response: %x\n", rsp->hdr.Status); } + kfree(name); kfree(lc); return 0; @@ -3895,8 +3894,6 @@ int smb2_query_dir(struct ksmbd_work *work) ksmbd_debug(SMB, "Search pattern is %s\n", srch_ptr); } - ksmbd_debug(SMB, "Directory name is %s\n", dir_fp->filename); - if (srch_flag & SMB2_REOPEN || srch_flag & SMB2_RESTART_SCANS) { ksmbd_debug(SMB, "Restart directory scan\n"); generic_file_llseek(dir_fp->filp, 0, SEEK_SET); @@ -4390,9 +4387,9 @@ static int get_file_all_info(struct ksmbd_work *work, return -EACCES; } - filename = convert_to_nt_pathname(fp->filename); - if (!filename) - return -ENOMEM; + filename = convert_to_nt_pathname(work->tcon->share_conf, &fp->filp->f_path); + if (IS_ERR(filename)) + return PTR_ERR(filename); inode = file_inode(fp->filp); generic_fillattr(file_mnt_user_ns(fp->filp), inode, &stat); @@ -4999,15 +4996,17 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work, case FS_SECTOR_SIZE_INFORMATION: { struct smb3_fs_ss_info *info; + unsigned int sector_size = + min_t(unsigned int, path.mnt->mnt_sb->s_blocksize, 4096); info = (struct smb3_fs_ss_info *)(rsp->Buffer); - info->LogicalBytesPerSector = cpu_to_le32(stfs.f_bsize); + info->LogicalBytesPerSector = cpu_to_le32(sector_size); info->PhysicalBytesPerSectorForAtomicity = - cpu_to_le32(stfs.f_bsize); - info->PhysicalBytesPerSectorForPerf = cpu_to_le32(stfs.f_bsize); + cpu_to_le32(sector_size); + info->PhysicalBytesPerSectorForPerf = cpu_to_le32(sector_size); info->FSEffPhysicalBytesPerSectorForAtomicity = - cpu_to_le32(stfs.f_bsize); + cpu_to_le32(sector_size); info->Flags = cpu_to_le32(SSINFO_FLAGS_ALIGNED_DEVICE | SSINFO_FLAGS_PARTITION_ALIGNED_ON_DEVICE); info->ByteOffsetForSectorAlignment = 0; @@ -5683,8 +5682,7 @@ static int set_file_allocation_info(struct ksmbd_work *work, size = i_size_read(inode); rc = ksmbd_vfs_truncate(work, fp, alloc_blks * 512); if (rc) { - pr_err("truncate failed! filename : %s, err %d\n", - fp->filename, rc); + pr_err("truncate failed!, err %d\n", rc); return rc; } if (size < alloc_blks * 512) @@ -5714,12 +5712,10 @@ static int set_end_of_file_info(struct ksmbd_work *work, struct ksmbd_file *fp, * truncated range. */ if (inode->i_sb->s_magic != MSDOS_SUPER_MAGIC) { - ksmbd_debug(SMB, "filename : %s truncated to newsize %lld\n", - fp->filename, newsize); + ksmbd_debug(SMB, "truncated to newsize %lld\n", newsize); rc = ksmbd_vfs_truncate(work, fp, newsize); if (rc) { - ksmbd_debug(SMB, "truncate failed! filename : %s err %d\n", - fp->filename, rc); + ksmbd_debug(SMB, "truncate failed!, err %d\n", rc); if (rc != -EAGAIN) rc = -EBADF; return rc; @@ -5765,8 +5761,10 @@ static int set_rename_info(struct ksmbd_work *work, struct ksmbd_file *fp, if (parent_fp) { if (parent_fp->daccess & FILE_DELETE_LE) { pr_err("parent dir is opened with delete access\n"); + ksmbd_fd_put(work, parent_fp); return -ESHARE; } + ksmbd_fd_put(work, parent_fp); } next: return smb2_rename(work, fp, user_ns, rename_info, diff --git a/fs/ksmbd/vfs.c b/fs/ksmbd/vfs.c index 9cebb6ba555b..dcdd07c6efff 100644 --- a/fs/ksmbd/vfs.c +++ b/fs/ksmbd/vfs.c @@ -398,8 +398,7 @@ int ksmbd_vfs_read(struct ksmbd_work *work, struct ksmbd_file *fp, size_t count, nbytes = kernel_read(filp, rbuf, count, pos); if (nbytes < 0) { - pr_err("smb read failed for (%s), err = %zd\n", - fp->filename, nbytes); + pr_err("smb read failed, err = %zd\n", nbytes); return nbytes; } @@ -875,8 +874,7 @@ int ksmbd_vfs_truncate(struct ksmbd_work *work, err = vfs_truncate(&filp->f_path, size); if (err) - pr_err("truncate failed for filename : %s err %d\n", - fp->filename, err); + pr_err("truncate failed, err %d\n", err); return err; } diff --git a/fs/ksmbd/vfs_cache.c b/fs/ksmbd/vfs_cache.c index 29c1db66bd0f..c4d59d2735f0 100644 --- a/fs/ksmbd/vfs_cache.c +++ b/fs/ksmbd/vfs_cache.c @@ -328,7 +328,6 @@ static void __ksmbd_close_fd(struct ksmbd_file_table *ft, struct ksmbd_file *fp) kfree(smb_lock); } - kfree(fp->filename); if (ksmbd_stream_fd(fp)) kfree(fp->stream.name); kmem_cache_free(filp_cache, fp); @@ -497,6 +496,7 @@ struct ksmbd_file *ksmbd_lookup_fd_inode(struct inode *inode) list_for_each_entry(lfp, &ci->m_fp_list, node) { if (inode == file_inode(lfp->filp)) { atomic_dec(&ci->m_count); + lfp = ksmbd_fp_get(lfp); read_unlock(&ci->m_lock); return lfp; } diff --git a/fs/ksmbd/vfs_cache.h b/fs/ksmbd/vfs_cache.h index 36239ce31afd..fcb13413fa8d 100644 --- a/fs/ksmbd/vfs_cache.h +++ b/fs/ksmbd/vfs_cache.h @@ -62,7 +62,6 @@ struct ksmbd_inode { struct ksmbd_file { struct file *filp; - char *filename; u64 persistent_id; u64 volatile_id; diff --git a/fs/libfs.c b/fs/libfs.c index e64bdedef168..31b0ddf01c31 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -539,17 +539,17 @@ int simple_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, } EXPORT_SYMBOL(simple_setattr); -static int simple_readpage(struct file *file, struct page *page) +static int simple_read_folio(struct file *file, struct folio *folio) { - clear_highpage(page); - flush_dcache_page(page); - SetPageUptodate(page); - unlock_page(page); + folio_zero_range(folio, 0, folio_size(folio)); + flush_dcache_folio(folio); + folio_mark_uptodate(folio); + folio_unlock(folio); return 0; } int simple_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, + loff_t pos, unsigned len, struct page **pagep, void **fsdata) { struct page *page; @@ -557,7 +557,7 @@ int simple_write_begin(struct file *file, struct address_space *mapping, index = pos >> PAGE_SHIFT; - page = grab_cache_page_write_begin(mapping, index, flags); + page = grab_cache_page_write_begin(mapping, index); if (!page) return -ENOMEM; @@ -592,7 +592,7 @@ EXPORT_SYMBOL(simple_write_begin); * should extend on what's done here with a call to mark_inode_dirty() in the * case that i_size has changed. * - * Use *ONLY* with simple_readpage() + * Use *ONLY* with simple_read_folio() */ static int simple_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, @@ -628,7 +628,7 @@ static int simple_write_end(struct file *file, struct address_space *mapping, * Provides ramfs-style behavior: data in the pagecache, but no writeback. */ const struct address_space_operations ram_aops = { - .readpage = simple_readpage, + .read_folio = simple_read_folio, .write_begin = simple_write_begin, .write_end = simple_write_end, .dirty_folio = noop_dirty_folio, diff --git a/fs/minix/inode.c b/fs/minix/inode.c index f1a6610e4ee6..da8bdd1712a7 100644 --- a/fs/minix/inode.c +++ b/fs/minix/inode.c @@ -402,9 +402,9 @@ static int minix_writepage(struct page *page, struct writeback_control *wbc) return block_write_full_page(page, minix_get_block, wbc); } -static int minix_readpage(struct file *file, struct page *page) +static int minix_read_folio(struct file *file, struct folio *folio) { - return block_read_full_page(page,minix_get_block); + return block_read_full_folio(folio, minix_get_block); } int minix_prepare_chunk(struct page *page, loff_t pos, unsigned len) @@ -423,13 +423,12 @@ static void minix_write_failed(struct address_space *mapping, loff_t to) } static int minix_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, + loff_t pos, unsigned len, struct page **pagep, void **fsdata) { int ret; - ret = block_write_begin(mapping, pos, len, flags, pagep, - minix_get_block); + ret = block_write_begin(mapping, pos, len, pagep, minix_get_block); if (unlikely(ret)) minix_write_failed(mapping, pos + len); @@ -444,7 +443,7 @@ static sector_t minix_bmap(struct address_space *mapping, sector_t block) static const struct address_space_operations minix_aops = { .dirty_folio = block_dirty_folio, .invalidate_folio = block_invalidate_folio, - .readpage = minix_readpage, + .read_folio = minix_read_folio, .writepage = minix_writepage, .write_begin = minix_write_begin, .write_end = generic_write_end, diff --git a/fs/mpage.c b/fs/mpage.c index 1fe56f8c495f..0d25f44f5707 100644 --- a/fs/mpage.c +++ b/fs/mpage.c @@ -36,7 +36,7 @@ * * The mpage code never puts partial pages into a BIO (except for end-of-file). * If a page does not map to a contiguous run of blocks then it simply falls - * back to block_read_full_page(). + * back to block_read_full_folio(). * * Why is this? If a page's completion depends on a number of different BIOs * which can complete in any order (or at the same time) then determining the @@ -68,7 +68,7 @@ static struct bio *mpage_bio_submit(struct bio *bio) /* * support function for mpage_readahead. The fs supplied get_block might * return an up to date buffer. This is used to map that buffer into - * the page, which allows readpage to avoid triggering a duplicate call + * the page, which allows read_folio to avoid triggering a duplicate call * to get_block. * * The idea is to avoid adding buffers to pages that don't already have @@ -296,7 +296,7 @@ confused: if (args->bio) args->bio = mpage_bio_submit(args->bio); if (!PageUptodate(page)) - block_read_full_page(page, args->get_block); + block_read_full_folio(page_folio(page), args->get_block); else unlock_page(page); goto out; @@ -364,20 +364,22 @@ EXPORT_SYMBOL(mpage_readahead); /* * This isn't called much at all */ -int mpage_readpage(struct page *page, get_block_t get_block) +int mpage_read_folio(struct folio *folio, get_block_t get_block) { struct mpage_readpage_args args = { - .page = page, + .page = &folio->page, .nr_pages = 1, .get_block = get_block, }; + VM_BUG_ON_FOLIO(folio_test_large(folio), folio); + args.bio = do_mpage_readpage(&args); if (args.bio) mpage_bio_submit(args.bio); return 0; } -EXPORT_SYMBOL(mpage_readpage); +EXPORT_SYMBOL(mpage_read_folio); /* * Writing is not so simple. @@ -425,11 +427,11 @@ static void clean_buffers(struct page *page, unsigned first_unmapped) /* * we cannot drop the bh if the page is not uptodate or a concurrent - * readpage would fail to serialize with the bh and it would read from + * read_folio would fail to serialize with the bh and it would read from * disk before we reach the platter. */ if (buffer_heads_over_limit && PageUptodate(page)) - try_to_free_buffers(page); + try_to_free_buffers(page_folio(page)); } /* @@ -510,7 +512,7 @@ static int __mpage_writepage(struct page *page, struct writeback_control *wbc, /* * Page has buffers, but they are all unmapped. The page was * created by pagein or read over a hole which was handled by - * block_read_full_page(). If this address_space is also + * block_read_full_folio(). If this address_space is also * using mpage_readahead then this can rarely happen. */ goto confused; diff --git a/fs/namei.c b/fs/namei.c index 3f1829b3ab5b..896ade8b7400 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -22,6 +22,7 @@ #include <linux/fs.h> #include <linux/namei.h> #include <linux/pagemap.h> +#include <linux/sched/mm.h> #include <linux/fsnotify.h> #include <linux/personality.h> #include <linux/security.h> @@ -3673,18 +3674,14 @@ static struct dentry *filename_create(int dfd, struct filename *name, { struct dentry *dentry = ERR_PTR(-EEXIST); struct qstr last; + bool want_dir = lookup_flags & LOOKUP_DIRECTORY; + unsigned int reval_flag = lookup_flags & LOOKUP_REVAL; + unsigned int create_flags = LOOKUP_CREATE | LOOKUP_EXCL; int type; int err2; int error; - bool is_dir = (lookup_flags & LOOKUP_DIRECTORY); - /* - * Note that only LOOKUP_REVAL and LOOKUP_DIRECTORY matter here. Any - * other flags passed in are ignored! - */ - lookup_flags &= LOOKUP_REVAL; - - error = filename_parentat(dfd, name, lookup_flags, path, &last, &type); + error = filename_parentat(dfd, name, reval_flag, path, &last, &type); if (error) return ERR_PTR(error); @@ -3698,11 +3695,13 @@ static struct dentry *filename_create(int dfd, struct filename *name, /* don't fail immediately if it's r/o, at least try to report other errors */ err2 = mnt_want_write(path->mnt); /* - * Do the final lookup. + * Do the final lookup. Suppress 'create' if there is a trailing + * '/', and a directory wasn't requested. */ - lookup_flags |= LOOKUP_CREATE | LOOKUP_EXCL; + if (last.name[last.len] && !want_dir) + create_flags = 0; inode_lock_nested(path->dentry->d_inode, I_MUTEX_PARENT); - dentry = __lookup_hash(&last, path->dentry, lookup_flags); + dentry = __lookup_hash(&last, path->dentry, reval_flag | create_flags); if (IS_ERR(dentry)) goto unlock; @@ -3716,7 +3715,7 @@ static struct dentry *filename_create(int dfd, struct filename *name, * all is fine. Let's be bastards - you had / on the end, you've * been asking for (non-existent) directory. -ENOENT for you. */ - if (unlikely(!is_dir && last.name[last.len])) { + if (unlikely(!create_flags)) { error = -ENOENT; goto fail; } @@ -5003,28 +5002,28 @@ int page_readlink(struct dentry *dentry, char __user *buffer, int buflen) } EXPORT_SYMBOL(page_readlink); -/* - * The nofs argument instructs pagecache_write_begin to pass AOP_FLAG_NOFS - */ -int __page_symlink(struct inode *inode, const char *symname, int len, int nofs) +int page_symlink(struct inode *inode, const char *symname, int len) { struct address_space *mapping = inode->i_mapping; + const struct address_space_operations *aops = mapping->a_ops; + bool nofs = !mapping_gfp_constraint(mapping, __GFP_FS); struct page *page; void *fsdata; int err; - unsigned int flags = 0; - if (nofs) - flags |= AOP_FLAG_NOFS; + unsigned int flags; retry: - err = pagecache_write_begin(NULL, mapping, 0, len-1, - flags, &page, &fsdata); + if (nofs) + flags = memalloc_nofs_save(); + err = aops->write_begin(NULL, mapping, 0, len-1, &page, &fsdata); + if (nofs) + memalloc_nofs_restore(flags); if (err) goto fail; memcpy(page_address(page), symname, len-1); - err = pagecache_write_end(NULL, mapping, 0, len-1, len-1, + err = aops->write_end(NULL, mapping, 0, len-1, len-1, page, fsdata); if (err < 0) goto fail; @@ -5036,13 +5035,6 @@ retry: fail: return err; } -EXPORT_SYMBOL(__page_symlink); - -int page_symlink(struct inode *inode, const char *symname, int len) -{ - return __page_symlink(inode, symname, len, - !mapping_gfp_constraint(inode->i_mapping, __GFP_FS)); -} EXPORT_SYMBOL(page_symlink); const struct inode_operations page_symlink_inode_operations = { diff --git a/fs/namespace.c b/fs/namespace.c index a0a36bfa3aa0..41461f55c039 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -4026,8 +4026,9 @@ static int can_idmap_mount(const struct mount_kattr *kattr, struct mount *mnt) static inline bool mnt_allow_writers(const struct mount_kattr *kattr, const struct mount *mnt) { - return !(kattr->attr_set & MNT_READONLY) || - (mnt->mnt.mnt_flags & MNT_READONLY); + return (!(kattr->attr_set & MNT_READONLY) || + (mnt->mnt.mnt_flags & MNT_READONLY)) && + !kattr->mnt_userns; } static int mount_setattr_prepare(struct mount_kattr *kattr, struct mount *mnt) @@ -4058,10 +4059,22 @@ static int mount_setattr_prepare(struct mount_kattr *kattr, struct mount *mnt) if (err) { struct mount *p; - for (p = mnt; p != m; p = next_mnt(p, mnt)) { + /* + * If we had to call mnt_hold_writers() MNT_WRITE_HOLD will + * be set in @mnt_flags. The loop unsets MNT_WRITE_HOLD for all + * mounts and needs to take care to include the first mount. + */ + for (p = mnt; p; p = next_mnt(p, mnt)) { /* If we had to hold writers unblock them. */ if (p->mnt.mnt_flags & MNT_WRITE_HOLD) mnt_unhold_writers(p); + + /* + * We're done once the first mount we changed got + * MNT_WRITE_HOLD unset. + */ + if (p == m) + break; } } return err; diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c index 281a88a5b8dc..8742d22dfd2b 100644 --- a/fs/netfs/buffered_read.c +++ b/fs/netfs/buffered_read.c @@ -198,22 +198,21 @@ cleanup_free: EXPORT_SYMBOL(netfs_readahead); /** - * netfs_readpage - Helper to manage a readpage request + * netfs_read_folio - Helper to manage a read_folio request * @file: The file to read from - * @subpage: A subpage of the folio to read + * @folio: The folio to read * - * Fulfil a readpage request by drawing data from the cache if possible, or the - * netfs if not. Space beyond the EOF is zero-filled. Multiple I/O requests - * from different sources will get munged together. + * Fulfil a read_folio request by drawing data from the cache if + * possible, or the netfs if not. Space beyond the EOF is zero-filled. + * Multiple I/O requests from different sources will get munged together. * * The calling netfs must initialise a netfs context contiguous to the vfs * inode before calling this. * * This is usable whether or not caching is enabled. */ -int netfs_readpage(struct file *file, struct page *subpage) +int netfs_read_folio(struct file *file, struct folio *folio) { - struct folio *folio = page_folio(subpage); struct address_space *mapping = folio_file_mapping(folio); struct netfs_io_request *rreq; struct netfs_i_context *ctx = netfs_i_context(mapping->host); @@ -245,7 +244,7 @@ alloc_error: folio_unlock(folio); return ret; } -EXPORT_SYMBOL(netfs_readpage); +EXPORT_SYMBOL(netfs_read_folio); /* * Prepare a folio for writing without reading first @@ -302,7 +301,6 @@ zero_out: * @mapping: The mapping to read from * @pos: File position at which the write will begin * @len: The length of the write (may extend beyond the end of the folio chosen) - * @aop_flags: AOP_* flags * @_folio: Where to put the resultant folio * @_fsdata: Place for the netfs to store a cookie * @@ -329,22 +327,19 @@ zero_out: * This is usable whether or not caching is enabled. */ int netfs_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned int len, unsigned int aop_flags, - struct folio **_folio, void **_fsdata) + loff_t pos, unsigned int len, struct folio **_folio, + void **_fsdata) { struct netfs_io_request *rreq; struct netfs_i_context *ctx = netfs_i_context(file_inode(file )); struct folio *folio; - unsigned int fgp_flags; + unsigned int fgp_flags = FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE; pgoff_t index = pos >> PAGE_SHIFT; int ret; DEFINE_READAHEAD(ractl, file, NULL, mapping, index); retry: - fgp_flags = FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE; - if (aop_flags & AOP_FLAG_NOFS) - fgp_flags |= FGP_NOFS; folio = __filemap_get_folio(mapping, index, fgp_flags, mapping_gfp_mask(mapping)); if (!folio) diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig index 47a53b3362b6..14a72224b657 100644 --- a/fs/nfs/Kconfig +++ b/fs/nfs/Kconfig @@ -4,10 +4,6 @@ config NFS_FS depends on INET && FILE_LOCKING && MULTIUSER select LOCKD select SUNRPC - select CRYPTO - select CRYPTO_HASH - select XXHASH - select CRYPTO_XXHASH select NFS_ACL_SUPPORT if NFS_V3_ACL help Choose Y here if you want to access files residing on other diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index bac4cf1a308e..a8ecdd527662 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -39,7 +39,7 @@ #include <linux/sched.h> #include <linux/kmemleak.h> #include <linux/xattr.h> -#include <linux/xxhash.h> +#include <linux/hash.h> #include "delegation.h" #include "iostat.h" @@ -55,7 +55,7 @@ static int nfs_closedir(struct inode *, struct file *); static int nfs_readdir(struct file *, struct dir_context *); static int nfs_fsync_dir(struct file *, loff_t, loff_t, int); static loff_t nfs_llseek_dir(struct file *, loff_t, int); -static void nfs_readdir_clear_array(struct page*); +static void nfs_readdir_free_folio(struct folio *); const struct file_operations nfs_dir_operations = { .llseek = nfs_llseek_dir, @@ -67,7 +67,7 @@ const struct file_operations nfs_dir_operations = { }; const struct address_space_operations nfs_dir_aops = { - .freepage = nfs_readdir_clear_array, + .free_folio = nfs_readdir_free_folio, }; #define NFS_INIT_DTSIZE PAGE_SIZE @@ -228,6 +228,11 @@ static void nfs_readdir_clear_array(struct page *page) kunmap_atomic(array); } +static void nfs_readdir_free_folio(struct folio *folio) +{ + nfs_readdir_clear_array(&folio->page); +} + static void nfs_readdir_page_reinit_array(struct page *page, u64 last_cookie, u64 change_attr) { @@ -350,10 +355,7 @@ out: * of directory cookies. Content is addressed by the value of the * cookie index of the first readdir entry in a page. * - * The xxhash algorithm is chosen because it is fast, and is supposed - * to result in a decent flat distribution of hashes. - * - * We then select only the first 18 bits to avoid issues with excessive + * We select only the first 18 bits to avoid issues with excessive * memory use for the page cache XArray. 18 bits should allow the caching * of 262144 pages of sequences of readdir entries. Since each page holds * 127 readdir entries for a typical 64-bit system, that works out to a @@ -363,7 +365,7 @@ static pgoff_t nfs_readdir_page_cookie_hash(u64 cookie) { if (cookie == 0) return 0; - return xxhash(&cookie, sizeof(cookie), 0) & NFS_READDIR_COOKIE_MASK; + return hash_64(cookie, 18); } static bool nfs_readdir_page_validate(struct page *page, u64 last_cookie, @@ -1991,16 +1993,6 @@ const struct dentry_operations nfs4_dentry_operations = { }; EXPORT_SYMBOL_GPL(nfs4_dentry_operations); -static fmode_t flags_to_mode(int flags) -{ - fmode_t res = (__force fmode_t)flags & FMODE_EXEC; - if ((flags & O_ACCMODE) != O_WRONLY) - res |= FMODE_READ; - if ((flags & O_ACCMODE) != O_RDONLY) - res |= FMODE_WRITE; - return res; -} - static struct nfs_open_context *create_nfs_open_context(struct dentry *dentry, int open_flags, struct file *filp) { return alloc_nfs_open_context(dentry, flags_to_mode(open_flags), filp); diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 150b7fa8f0a7..d764b3ce7905 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -313,7 +313,7 @@ static bool nfs_want_read_modify_write(struct file *file, struct page *page, * increment the page use counts until he is done with the page. */ static int nfs_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, + loff_t pos, unsigned len, struct page **pagep, void **fsdata) { int ret; @@ -325,7 +325,7 @@ static int nfs_write_begin(struct file *file, struct address_space *mapping, file, mapping->host->i_ino, len, (long long) pos); start: - page = grab_cache_page_write_begin(mapping, index, flags); + page = grab_cache_page_write_begin(mapping, index); if (!page) return -ENOMEM; *pagep = page; @@ -337,7 +337,7 @@ start: } else if (!once_thru && nfs_want_read_modify_write(file, page, pos, len)) { once_thru = 1; - ret = nfs_readpage(file, page); + ret = nfs_read_folio(file, page_folio(page)); put_page(page); if (!ret) goto start; @@ -415,34 +415,31 @@ static void nfs_invalidate_folio(struct folio *folio, size_t offset, } /* - * Attempt to release the private state associated with a page - * - Called if either PG_private or PG_fscache is set on the page - * - Caller holds page lock - * - Return true (may release page) or false (may not) + * Attempt to release the private state associated with a folio + * - Called if either private or fscache flags are set on the folio + * - Caller holds folio lock + * - Return true (may release folio) or false (may not) */ -static int nfs_release_page(struct page *page, gfp_t gfp) +static bool nfs_release_folio(struct folio *folio, gfp_t gfp) { - dfprintk(PAGECACHE, "NFS: release_page(%p)\n", page); + dfprintk(PAGECACHE, "NFS: release_folio(%p)\n", folio); - /* If PagePrivate() is set, then the page is not freeable */ - if (PagePrivate(page)) - return 0; - return nfs_fscache_release_page(page, gfp); + /* If the private flag is set, then the folio is not freeable */ + if (folio_test_private(folio)) + return false; + return nfs_fscache_release_folio(folio, gfp); } -static void nfs_check_dirty_writeback(struct page *page, +static void nfs_check_dirty_writeback(struct folio *folio, bool *dirty, bool *writeback) { struct nfs_inode *nfsi; - struct address_space *mapping = page_file_mapping(page); - - if (!mapping || PageSwapCache(page)) - return; + struct address_space *mapping = folio->mapping; /* - * Check if an unstable page is currently being committed and - * if so, have the VM treat it as if the page is under writeback - * so it will not block due to pages that will shortly be freeable. + * Check if an unstable folio is currently being committed and + * if so, have the VM treat it as if the folio is under writeback + * so it will not block due to folios that will shortly be freeable. */ nfsi = NFS_I(mapping->host); if (atomic_read(&nfsi->commit_info.rpcs_out)) { @@ -451,11 +448,11 @@ static void nfs_check_dirty_writeback(struct page *page, } /* - * If PagePrivate() is set, then the page is not freeable and as the - * inode is not being committed, it's not going to be cleaned in the - * near future so treat it as dirty + * If the private flag is set, then the folio is not freeable + * and as the inode is not being committed, it's not going to + * be cleaned in the near future so treat it as dirty */ - if (PagePrivate(page)) + if (folio_test_private(folio)) *dirty = true; } @@ -517,7 +514,7 @@ static void nfs_swap_deactivate(struct file *file) } const struct address_space_operations nfs_file_aops = { - .readpage = nfs_readpage, + .read_folio = nfs_read_folio, .readahead = nfs_readahead, .dirty_folio = filemap_dirty_folio, .writepage = nfs_writepage, @@ -525,7 +522,7 @@ const struct address_space_operations nfs_file_aops = { .write_begin = nfs_write_begin, .write_end = nfs_write_end, .invalidate_folio = nfs_invalidate_folio, - .releasepage = nfs_release_page, + .release_folio = nfs_release_folio, .direct_IO = nfs_direct_IO, #ifdef CONFIG_MIGRATION .migratepage = nfs_migrate_page, diff --git a/fs/nfs/fs_context.c b/fs/nfs/fs_context.c index e2d59bb5e6bb..9a16897e8dc6 100644 --- a/fs/nfs/fs_context.c +++ b/fs/nfs/fs_context.c @@ -517,7 +517,7 @@ static int nfs_fs_context_parse_param(struct fs_context *fc, if (result.negated) ctx->flags &= ~NFS_MOUNT_SOFTREVAL; else - ctx->flags &= NFS_MOUNT_SOFTREVAL; + ctx->flags |= NFS_MOUNT_SOFTREVAL; break; case Opt_posix: if (result.negated) diff --git a/fs/nfs/fscache.h b/fs/nfs/fscache.h index 4e980cc04779..2a37af880978 100644 --- a/fs/nfs/fscache.h +++ b/fs/nfs/fscache.h @@ -48,14 +48,14 @@ extern void nfs_fscache_release_file(struct inode *, struct file *); extern int __nfs_fscache_read_page(struct inode *, struct page *); extern void __nfs_fscache_write_page(struct inode *, struct page *); -static inline int nfs_fscache_release_page(struct page *page, gfp_t gfp) +static inline bool nfs_fscache_release_folio(struct folio *folio, gfp_t gfp) { - if (PageFsCache(page)) { + if (folio_test_fscache(folio)) { if (current_is_kswapd() || !(gfp & __GFP_FS)) return false; - wait_on_page_fscache(page); - fscache_note_page_release(nfs_i_fscache(page->mapping->host)); - nfs_inc_fscache_stats(page->mapping->host, + folio_wait_fscache(folio); + fscache_note_page_release(nfs_i_fscache(folio->mapping->host)); + nfs_inc_fscache_stats(folio->mapping->host, NFSIOS_FSCACHE_PAGES_UNCACHED); } return true; @@ -129,9 +129,9 @@ static inline void nfs_fscache_open_file(struct inode *inode, struct file *filp) {} static inline void nfs_fscache_release_file(struct inode *inode, struct file *file) {} -static inline int nfs_fscache_release_page(struct page *page, gfp_t gfp) +static inline bool nfs_fscache_release_folio(struct folio *folio, gfp_t gfp) { - return 1; /* True: may release page */ + return true; /* may release folio */ } static inline int nfs_fscache_read_page(struct inode *inode, struct page *page) { diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 7eb3b08d702f..b4e46b0ffa2d 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -1180,7 +1180,6 @@ int nfs_open(struct inode *inode, struct file *filp) nfs_fscache_open_file(inode, filp); return 0; } -EXPORT_SYMBOL_GPL(nfs_open); /* * This function is called whenever some part of NFS notices that diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 57b0497105c8..7eefa16ed381 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -42,6 +42,16 @@ static inline bool nfs_lookup_is_soft_revalidate(const struct dentry *dentry) return true; } +static inline fmode_t flags_to_mode(int flags) +{ + fmode_t res = (__force fmode_t)flags & FMODE_EXEC; + if ((flags & O_ACCMODE) != O_WRONLY) + res |= FMODE_READ; + if ((flags & O_ACCMODE) != O_RDONLY) + res |= FMODE_WRITE; + return res; +} + /* * Note: RFC 1813 doesn't limit the number of auth flavors that * a server can return, so make something up. diff --git a/fs/nfs/nfs42xattr.c b/fs/nfs/nfs42xattr.c index ad3405c64b9e..e7b34f7e0614 100644 --- a/fs/nfs/nfs42xattr.c +++ b/fs/nfs/nfs42xattr.c @@ -997,7 +997,7 @@ int __init nfs4_xattr_cache_init(void) nfs4_xattr_cache_cachep = kmem_cache_create("nfs4_xattr_cache_cache", sizeof(struct nfs4_xattr_cache), 0, - (SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD|SLAB_ACCOUNT), + (SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD), nfs4_xattr_cache_init_once); if (nfs4_xattr_cache_cachep == NULL) return -ENOMEM; diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index d258933cf8c8..7b861e4f0533 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -32,6 +32,7 @@ nfs4_file_open(struct inode *inode, struct file *filp) struct dentry *parent = NULL; struct inode *dir; unsigned openflags = filp->f_flags; + fmode_t f_mode; struct iattr attr; int err; @@ -50,8 +51,9 @@ nfs4_file_open(struct inode *inode, struct file *filp) if (err) return err; + f_mode = filp->f_mode; if ((openflags & O_ACCMODE) == 3) - return nfs_open(inode, filp); + f_mode |= flags_to_mode(openflags); /* We can't create new files here */ openflags &= ~(O_CREAT|O_EXCL); @@ -59,7 +61,7 @@ nfs4_file_open(struct inode *inode, struct file *filp) parent = dget_parent(dentry); dir = d_inode(parent); - ctx = alloc_nfs_open_context(file_dentry(filp), filp->f_mode, filp); + ctx = alloc_nfs_open_context(file_dentry(filp), f_mode, filp); err = PTR_ERR(ctx); if (IS_ERR(ctx)) goto out; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index e3f5b380cefe..a79f66432bd3 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -363,6 +363,14 @@ static void nfs4_setup_readdir(u64 cookie, __be32 *verifier, struct dentry *dent kunmap_atomic(start); } +static void nfs4_fattr_set_prechange(struct nfs_fattr *fattr, u64 version) +{ + if (!(fattr->valid & NFS_ATTR_FATTR_PRECHANGE)) { + fattr->pre_change_attr = version; + fattr->valid |= NFS_ATTR_FATTR_PRECHANGE; + } +} + static void nfs4_test_and_free_stateid(struct nfs_server *server, nfs4_stateid *stateid, const struct cred *cred) @@ -6553,7 +6561,9 @@ static void nfs4_delegreturn_release(void *calldata) pnfs_roc_release(&data->lr.arg, &data->lr.res, data->res.lr_ret); if (inode) { - nfs_post_op_update_inode_force_wcc(inode, &data->fattr); + nfs4_fattr_set_prechange(&data->fattr, + inode_peek_iversion_raw(inode)); + nfs_refresh_inode(inode, &data->fattr); nfs_iput_and_deactive(inode); } kfree(calldata); @@ -9615,6 +9625,8 @@ nfs4_proc_layoutget(struct nfs4_layoutget *lgp, long *timeout) nfs4_init_sequence(&lgp->args.seq_args, &lgp->res.seq_res, 0, 0); task = rpc_run_task(&task_setup_data); + if (IS_ERR(task)) + return ERR_CAST(task); status = rpc_wait_for_completion_task(task); if (status != 0) diff --git a/fs/nfs/read.c b/fs/nfs/read.c index 5e7657374bc3..5a9b043662e9 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -333,8 +333,9 @@ out: * - The error flag is set for this page. This happens only when a * previous async read operation failed. */ -int nfs_readpage(struct file *file, struct page *page) +int nfs_read_folio(struct file *file, struct folio *folio) { + struct page *page = &folio->page; struct nfs_readdesc desc; struct inode *inode = page_file_mapping(page)->host; int ret; diff --git a/fs/nfs/symlink.c b/fs/nfs/symlink.c index 25ba299fdac2..0e27a2e4e68b 100644 --- a/fs/nfs/symlink.c +++ b/fs/nfs/symlink.c @@ -26,21 +26,21 @@ * and straight-forward than readdir caching. */ -static int nfs_symlink_filler(void *data, struct page *page) +static int nfs_symlink_filler(struct file *file, struct folio *folio) { - struct inode *inode = data; + struct inode *inode = folio->mapping->host; int error; - error = NFS_PROTO(inode)->readlink(inode, page, 0, PAGE_SIZE); + error = NFS_PROTO(inode)->readlink(inode, &folio->page, 0, PAGE_SIZE); if (error < 0) goto error; - SetPageUptodate(page); - unlock_page(page); + folio_mark_uptodate(folio); + folio_unlock(folio); return 0; error: - SetPageError(page); - unlock_page(page); + folio_set_error(folio); + folio_unlock(folio); return -EIO; } @@ -67,7 +67,7 @@ static const char *nfs_get_link(struct dentry *dentry, if (err) return err; page = read_cache_page(&inode->i_data, 0, nfs_symlink_filler, - inode); + NULL); if (IS_ERR(page)) return ERR_CAST(page); } diff --git a/fs/nfs/unlink.c b/fs/nfs/unlink.c index 5fa11e1aca4c..6f325e10056c 100644 --- a/fs/nfs/unlink.c +++ b/fs/nfs/unlink.c @@ -347,6 +347,7 @@ nfs_async_rename(struct inode *old_dir, struct inode *new_dir, data = kzalloc(sizeof(*data), GFP_KERNEL); if (data == NULL) return ERR_PTR(-ENOMEM); + task_setup_data.task = &data->task; task_setup_data.callback_data = data; data->cred = get_current_cred(); diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c index c08882f5867b..2c1b027774d4 100644 --- a/fs/nfsd/filecache.c +++ b/fs/nfsd/filecache.c @@ -237,6 +237,13 @@ nfsd_file_check_write_error(struct nfsd_file *nf) } static void +nfsd_file_flush(struct nfsd_file *nf) +{ + if (nf->nf_file && vfs_fsync(nf->nf_file, 1) != 0) + nfsd_reset_write_verifier(net_generic(nf->nf_net, nfsd_net_id)); +} + +static void nfsd_file_do_unhash(struct nfsd_file *nf) { lockdep_assert_held(&nfsd_file_hashtbl[nf->nf_hashval].nfb_lock); @@ -295,19 +302,15 @@ nfsd_file_put_noref(struct nfsd_file *nf) void nfsd_file_put(struct nfsd_file *nf) { - bool is_hashed; - set_bit(NFSD_FILE_REFERENCED, &nf->nf_flags); - if (refcount_read(&nf->nf_ref) > 2 || !nf->nf_file) { + if (test_bit(NFSD_FILE_HASHED, &nf->nf_flags) == 0) { + nfsd_file_flush(nf); nfsd_file_put_noref(nf); - return; + } else { + nfsd_file_put_noref(nf); + if (nf->nf_file) + nfsd_file_schedule_laundrette(); } - - filemap_flush(nf->nf_file->f_mapping); - is_hashed = test_bit(NFSD_FILE_HASHED, &nf->nf_flags) != 0; - nfsd_file_put_noref(nf); - if (is_hashed) - nfsd_file_schedule_laundrette(); if (atomic_long_read(&nfsd_filecache_count) >= NFSD_FILE_LRU_LIMIT) nfsd_file_gc(); } @@ -328,6 +331,7 @@ nfsd_file_dispose_list(struct list_head *dispose) while(!list_empty(dispose)) { nf = list_first_entry(dispose, struct nfsd_file, nf_lru); list_del(&nf->nf_lru); + nfsd_file_flush(nf); nfsd_file_put_noref(nf); } } @@ -341,6 +345,7 @@ nfsd_file_dispose_list_sync(struct list_head *dispose) while(!list_empty(dispose)) { nf = list_first_entry(dispose, struct nfsd_file, nf_lru); list_del(&nf->nf_lru); + nfsd_file_flush(nf); if (!refcount_dec_and_test(&nf->nf_ref)) continue; if (nfsd_file_free(nf)) diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c index 367551bddfc6..b5760801d377 100644 --- a/fs/nfsd/nfs2acl.c +++ b/fs/nfsd/nfs2acl.c @@ -249,34 +249,34 @@ nfsaclsvc_encode_getaclres(struct svc_rqst *rqstp, struct xdr_stream *xdr) int w; if (!svcxdr_encode_stat(xdr, resp->status)) - return 0; + return false; if (dentry == NULL || d_really_is_negative(dentry)) - return 1; + return true; inode = d_inode(dentry); if (!svcxdr_encode_fattr(rqstp, xdr, &resp->fh, &resp->stat)) - return 0; + return false; if (xdr_stream_encode_u32(xdr, resp->mask) < 0) - return 0; + return false; rqstp->rq_res.page_len = w = nfsacl_size( (resp->mask & NFS_ACL) ? resp->acl_access : NULL, (resp->mask & NFS_DFACL) ? resp->acl_default : NULL); while (w > 0) { if (!*(rqstp->rq_next_page++)) - return 1; + return true; w -= PAGE_SIZE; } if (!nfs_stream_encode_acl(xdr, inode, resp->acl_access, resp->mask & NFS_ACL, 0)) - return 0; + return false; if (!nfs_stream_encode_acl(xdr, inode, resp->acl_default, resp->mask & NFS_DFACL, NFS_ACL_DEFAULT)) - return 0; + return false; - return 1; + return true; } /* ACCESS */ @@ -286,17 +286,17 @@ nfsaclsvc_encode_accessres(struct svc_rqst *rqstp, struct xdr_stream *xdr) struct nfsd3_accessres *resp = rqstp->rq_resp; if (!svcxdr_encode_stat(xdr, resp->status)) - return 0; + return false; switch (resp->status) { case nfs_ok: if (!svcxdr_encode_fattr(rqstp, xdr, &resp->fh, &resp->stat)) - return 0; + return false; if (xdr_stream_encode_u32(xdr, resp->access) < 0) - return 0; + return false; break; } - return 1; + return true; } /* diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index 6045cea21f52..67f63cfeade5 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -63,10 +63,10 @@ void nilfs_inode_sub_blocks(struct inode *inode, int n) /** * nilfs_get_block() - get a file block on the filesystem (callback function) - * @inode - inode struct of the target file - * @blkoff - file block number - * @bh_result - buffer head to be mapped on - * @create - indicate whether allocating the block or not when it has not + * @inode: inode struct of the target file + * @blkoff: file block number + * @bh_result: buffer head to be mapped on + * @create: indicate whether allocating the block or not when it has not * been allocated yet. * * This function does not issue actual read request of the specified data @@ -140,14 +140,14 @@ int nilfs_get_block(struct inode *inode, sector_t blkoff, } /** - * nilfs_readpage() - implement readpage() method of nilfs_aops {} + * nilfs_read_folio() - implement read_folio() method of nilfs_aops {} * address_space_operations. - * @file - file struct of the file to be read - * @page - the page to be read + * @file: file struct of the file to be read + * @folio: the folio to be read */ -static int nilfs_readpage(struct file *file, struct page *page) +static int nilfs_read_folio(struct file *file, struct folio *folio) { - return mpage_readpage(page, nilfs_get_block); + return mpage_read_folio(folio, nilfs_get_block); } static void nilfs_readahead(struct readahead_control *rac) @@ -248,7 +248,7 @@ void nilfs_write_failed(struct address_space *mapping, loff_t to) } static int nilfs_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, + loff_t pos, unsigned len, struct page **pagep, void **fsdata) { @@ -258,8 +258,7 @@ static int nilfs_write_begin(struct file *file, struct address_space *mapping, if (unlikely(err)) return err; - err = block_write_begin(mapping, pos, len, flags, pagep, - nilfs_get_block); + err = block_write_begin(mapping, pos, len, pagep, nilfs_get_block); if (unlikely(err)) { nilfs_write_failed(mapping, pos + len); nilfs_transaction_abort(inode->i_sb); @@ -299,13 +298,12 @@ nilfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) const struct address_space_operations nilfs_aops = { .writepage = nilfs_writepage, - .readpage = nilfs_readpage, + .read_folio = nilfs_read_folio, .writepages = nilfs_writepages, .dirty_folio = nilfs_dirty_folio, .readahead = nilfs_readahead, .write_begin = nilfs_write_begin, .write_end = nilfs_write_end, - /* .releasepage = nilfs_releasepage, */ .invalidate_folio = block_invalidate_folio, .direct_IO = nilfs_direct_IO, .is_partially_uptodate = block_is_partially_uptodate, @@ -1088,6 +1086,7 @@ int __nilfs_mark_inode_dirty(struct inode *inode, int flags) /** * nilfs_dirty_inode - reflect changes on given inode to an inode block. * @inode: inode of the file to be registered. + * @flags: flags to determine the dirty state of the inode * * nilfs_dirty_inode() loads a inode block containing the specified * @inode and copies data from a nilfs_inode to a corresponding inode diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c index fec194a666f4..87e1004b606d 100644 --- a/fs/nilfs2/ioctl.c +++ b/fs/nilfs2/ioctl.c @@ -1052,20 +1052,20 @@ out: static int nilfs_ioctl_trim_fs(struct inode *inode, void __user *argp) { struct the_nilfs *nilfs = inode->i_sb->s_fs_info; - struct request_queue *q = bdev_get_queue(nilfs->ns_bdev); struct fstrim_range range; int ret; if (!capable(CAP_SYS_ADMIN)) return -EPERM; - if (!blk_queue_discard(q)) + if (!bdev_max_discard_sectors(nilfs->ns_bdev)) return -EOPNOTSUPP; if (copy_from_user(&range, argp, sizeof(range))) return -EFAULT; - range.minlen = max_t(u64, range.minlen, q->limits.discard_granularity); + range.minlen = max_t(u64, range.minlen, + bdev_discard_granularity(nilfs->ns_bdev)); down_read(&nilfs->ns_segctor_sem); ret = nilfs_sufile_trim_fs(nilfs->ns_sufile, &range); diff --git a/fs/nilfs2/recovery.c b/fs/nilfs2/recovery.c index 9e2ed76c0f25..0955b657938f 100644 --- a/fs/nilfs2/recovery.c +++ b/fs/nilfs2/recovery.c @@ -511,7 +511,7 @@ static int nilfs_recover_dsync_blocks(struct the_nilfs *nilfs, pos = rb->blkoff << inode->i_blkbits; err = block_write_begin(inode->i_mapping, pos, blocksize, - 0, &page, nilfs_get_block); + &page, nilfs_get_block); if (unlikely(err)) { loff_t isize = inode->i_size; diff --git a/fs/nilfs2/sufile.c b/fs/nilfs2/sufile.c index e385cca2004a..77ff8e95421f 100644 --- a/fs/nilfs2/sufile.c +++ b/fs/nilfs2/sufile.c @@ -1100,7 +1100,7 @@ int nilfs_sufile_trim_fs(struct inode *sufile, struct fstrim_range *range) ret = blkdev_issue_discard(nilfs->ns_bdev, start * sects_per_block, nblocks * sects_per_block, - GFP_NOFS, 0); + GFP_NOFS); if (ret < 0) { put_bh(su_bh); goto out_sem; @@ -1134,7 +1134,7 @@ int nilfs_sufile_trim_fs(struct inode *sufile, struct fstrim_range *range) ret = blkdev_issue_discard(nilfs->ns_bdev, start * sects_per_block, nblocks * sects_per_block, - GFP_NOFS, 0); + GFP_NOFS); if (!ret) ndiscarded += nblocks; } diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c index dd48a8f74d57..3b4a079c9617 100644 --- a/fs/nilfs2/the_nilfs.c +++ b/fs/nilfs2/the_nilfs.c @@ -672,7 +672,7 @@ int nilfs_discard_segments(struct the_nilfs *nilfs, __u64 *segnump, ret = blkdev_issue_discard(nilfs->ns_bdev, start * sects_per_block, nblocks * sects_per_block, - GFP_NOFS, 0); + GFP_NOFS); if (ret < 0) return ret; nblocks = 0; @@ -682,7 +682,7 @@ int nilfs_discard_segments(struct the_nilfs *nilfs, __u64 *segnump, ret = blkdev_issue_discard(nilfs->ns_bdev, start * sects_per_block, nblocks * sects_per_block, - GFP_NOFS, 0); + GFP_NOFS); return ret; } diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 9b32b76a9c30..a792e21c5309 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -1657,6 +1657,19 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, else mnt = path.mnt; + /* + * FAN_RENAME is not allowed on non-dir (for now). + * We shouldn't have allowed setting any dirent events in mask of + * non-dir, but because we always allowed it, error only if group + * was initialized with the new flag FAN_REPORT_TARGET_FID. + */ + ret = -ENOTDIR; + if (inode && !S_ISDIR(inode->i_mode) && + ((mask & FAN_RENAME) || + ((mask & FANOTIFY_DIRENT_EVENTS) && + FAN_GROUP_FLAG(group, FAN_REPORT_TARGET_FID)))) + goto path_put_and_out; + /* Mask out FAN_EVENT_ON_CHILD flag for sb/mount/non-dir marks */ if (mnt || !S_ISDIR(inode->i_mode)) { mask &= ~FAN_EVENT_ON_CHILD; diff --git a/fs/ntfs/aops.c b/fs/ntfs/aops.c index 90e3dad8ee45..9e3964ea2ea0 100644 --- a/fs/ntfs/aops.c +++ b/fs/ntfs/aops.c @@ -159,7 +159,7 @@ still_busy: * * Return 0 on success and -errno on error. * - * Contains an adapted version of fs/buffer.c::block_read_full_page(). + * Contains an adapted version of fs/buffer.c::block_read_full_folio(). */ static int ntfs_read_block(struct page *page) { @@ -358,16 +358,16 @@ handle_zblock: } /** - * ntfs_readpage - fill a @page of a @file with data from the device - * @file: open file to which the page @page belongs or NULL - * @page: page cache page to fill with data + * ntfs_read_folio - fill a @folio of a @file with data from the device + * @file: open file to which the folio @folio belongs or NULL + * @folio: page cache folio to fill with data * - * For non-resident attributes, ntfs_readpage() fills the @page of the open - * file @file by calling the ntfs version of the generic block_read_full_page() + * For non-resident attributes, ntfs_read_folio() fills the @folio of the open + * file @file by calling the ntfs version of the generic block_read_full_folio() * function, ntfs_read_block(), which in turn creates and reads in the buffers - * associated with the page asynchronously. + * associated with the folio asynchronously. * - * For resident attributes, OTOH, ntfs_readpage() fills @page by copying the + * For resident attributes, OTOH, ntfs_read_folio() fills @folio by copying the * data from the mft record (which at this stage is most likely in memory) and * fills the remainder with zeroes. Thus, in this case, I/O is synchronous, as * even if the mft record is not cached at this point in time, we need to wait @@ -375,8 +375,9 @@ handle_zblock: * * Return 0 on success and -errno on error. */ -static int ntfs_readpage(struct file *file, struct page *page) +static int ntfs_read_folio(struct file *file, struct folio *folio) { + struct page *page = &folio->page; loff_t i_size; struct inode *vi; ntfs_inode *ni, *base_ni; @@ -458,7 +459,7 @@ retry_readpage: } /* * If a parallel write made the attribute non-resident, drop the mft - * record and retry the readpage. + * record and retry the read_folio. */ if (unlikely(NInoNonResident(ni))) { unmap_mft_record(base_ni); @@ -637,10 +638,11 @@ static int ntfs_write_block(struct page *page, struct writeback_control *wbc) if (unlikely((block >= iblock) && (initialized_size < i_size))) { /* - * If this page is fully outside initialized size, zero - * out all pages between the current initialized size - * and the current page. Just use ntfs_readpage() to do - * the zeroing transparently. + * If this page is fully outside initialized + * size, zero out all pages between the current + * initialized size and the current page. Just + * use ntfs_read_folio() to do the zeroing + * transparently. */ if (block > iblock) { // TODO: @@ -798,7 +800,7 @@ lock_retry_remap: /* For the error case, need to reset bh to the beginning. */ bh = head; - /* Just an optimization, so ->readpage() is not called later. */ + /* Just an optimization, so ->read_folio() is not called later. */ if (unlikely(!PageUptodate(page))) { int uptodate = 1; do { @@ -1329,7 +1331,7 @@ done: * vfs inode dirty code path for the inode the mft record belongs to or via the * vm page dirty code path for the page the mft record is in. * - * Based on ntfs_readpage() and fs/buffer.c::block_write_full_page(). + * Based on ntfs_read_folio() and fs/buffer.c::block_write_full_page(). * * Return 0 on success and -errno on error. */ @@ -1651,7 +1653,7 @@ hole: * attributes. */ const struct address_space_operations ntfs_normal_aops = { - .readpage = ntfs_readpage, + .read_folio = ntfs_read_folio, #ifdef NTFS_RW .writepage = ntfs_writepage, .dirty_folio = block_dirty_folio, @@ -1666,7 +1668,7 @@ const struct address_space_operations ntfs_normal_aops = { * ntfs_compressed_aops - address space operations for compressed inodes */ const struct address_space_operations ntfs_compressed_aops = { - .readpage = ntfs_readpage, + .read_folio = ntfs_read_folio, #ifdef NTFS_RW .writepage = ntfs_writepage, .dirty_folio = block_dirty_folio, @@ -1681,7 +1683,7 @@ const struct address_space_operations ntfs_compressed_aops = { * and attributes */ const struct address_space_operations ntfs_mst_aops = { - .readpage = ntfs_readpage, /* Fill page with data. */ + .read_folio = ntfs_read_folio, /* Fill page with data. */ #ifdef NTFS_RW .writepage = ntfs_writepage, /* Write dirty page to disk. */ .dirty_folio = filemap_dirty_folio, diff --git a/fs/ntfs/aops.h b/fs/ntfs/aops.h index f0962d46bd67..934d5f79b9e7 100644 --- a/fs/ntfs/aops.h +++ b/fs/ntfs/aops.h @@ -37,9 +37,9 @@ static inline void ntfs_unmap_page(struct page *page) * Read a page from the page cache of the address space @mapping at position * @index, where @index is in units of PAGE_SIZE, and not in bytes. * - * If the page is not in memory it is loaded from disk first using the readpage - * method defined in the address space operations of @mapping and the page is - * added to the page cache of @mapping in the process. + * If the page is not in memory it is loaded from disk first using the + * read_folio method defined in the address space operations of @mapping + * and the page is added to the page cache of @mapping in the process. * * If the page belongs to an mst protected attribute and it is marked as such * in its ntfs inode (NInoMstProtected()) the mst fixups are applied but no diff --git a/fs/ntfs/attrib.c b/fs/ntfs/attrib.c index 2911c04a33e0..4de597a83b88 100644 --- a/fs/ntfs/attrib.c +++ b/fs/ntfs/attrib.c @@ -1719,7 +1719,7 @@ int ntfs_attr_make_non_resident(ntfs_inode *ni, const u32 data_size) vi->i_blocks = ni->allocated_size >> 9; write_unlock_irqrestore(&ni->size_lock, flags); /* - * This needs to be last since the address space operations ->readpage + * This needs to be last since the address space operations ->read_folio * and ->writepage can run concurrently with us as they are not * serialized on i_mutex. Note, we are not allowed to fail once we flip * this switch, which is another reason to do this last. diff --git a/fs/ntfs/compress.c b/fs/ntfs/compress.c index d2f9d6a0ee32..a60f543e7557 100644 --- a/fs/ntfs/compress.c +++ b/fs/ntfs/compress.c @@ -780,12 +780,12 @@ lock_retry_remap: /* Uncompressed cb, copy it to the destination pages. */ /* * TODO: As a big optimization, we could detect this case - * before we read all the pages and use block_read_full_page() + * before we read all the pages and use block_read_full_folio() * on all full pages instead (we still have to treat partial * pages especially but at least we are getting rid of the * synchronous io for the majority of pages. * Or if we choose not to do the read-ahead/-behind stuff, we - * could just return block_read_full_page(pages[xpage]) as long + * could just return block_read_full_folio(pages[xpage]) as long * as PAGE_SIZE <= cb_size. */ if (cb_max_ofs) diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c index 2ae25e48a41a..e1392a9b8ceb 100644 --- a/fs/ntfs/file.c +++ b/fs/ntfs/file.c @@ -251,14 +251,14 @@ do_non_resident_extend: * * TODO: For sparse pages could optimize this workload by using * the FsMisc / MiscFs page bit as a "PageIsSparse" bit. This - * would be set in readpage for sparse pages and here we would + * would be set in read_folio for sparse pages and here we would * not need to mark dirty any pages which have this bit set. * The only caveat is that we have to clear the bit everywhere * where we allocate any clusters that lie in the page or that * contain the page. * * TODO: An even greater optimization would be for us to only - * call readpage() on pages which are not in sparse regions as + * call read_folio() on pages which are not in sparse regions as * determined from the runlist. This would greatly reduce the * number of pages we read and make dirty in the case of sparse * files. diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c index efe0602b4e51..db0f1995aedd 100644 --- a/fs/ntfs/inode.c +++ b/fs/ntfs/inode.c @@ -1832,7 +1832,7 @@ int ntfs_read_inode_mount(struct inode *vi) /* Need this to sanity check attribute list references to $MFT. */ vi->i_generation = ni->seq_no = le16_to_cpu(m->sequence_number); - /* Provides readpage() for map_mft_record(). */ + /* Provides read_folio() for map_mft_record(). */ vi->i_mapping->a_ops = &ntfs_mst_aops; ctx = ntfs_attr_get_search_ctx(ni, m); @@ -2503,7 +2503,7 @@ retry_truncate: * between the old data_size, i.e. old_size, and the new_size * has not been zeroed. Fortunately, we do not need to zero it * either since on one hand it will either already be zero due - * to both readpage and writepage clearing partial page data + * to both read_folio and writepage clearing partial page data * beyond i_size in which case there is nothing to do or in the * case of the file being mmap()ped at the same time, POSIX * specifies that the behaviour is unspecified thus we do not diff --git a/fs/ntfs/mft.h b/fs/ntfs/mft.h index 17bfefc30271..49c001af16ed 100644 --- a/fs/ntfs/mft.h +++ b/fs/ntfs/mft.h @@ -79,7 +79,7 @@ extern int write_mft_record_nolock(ntfs_inode *ni, MFT_RECORD *m, int sync); * paths and via the page cache write back code paths or between writing * neighbouring mft records residing in the same page. * - * Locking the page also serializes us against ->readpage() if the page is not + * Locking the page also serializes us against ->read_folio() if the page is not * uptodate. * * On success, clean the mft record and return 0. On error, leave the mft diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c index 787b53b984ee..a4fcdc7927ca 100644 --- a/fs/ntfs3/file.c +++ b/fs/ntfs3/file.c @@ -22,20 +22,20 @@ static int ntfs_ioctl_fitrim(struct ntfs_sb_info *sbi, unsigned long arg) { struct fstrim_range __user *user_range; struct fstrim_range range; - struct request_queue *q = bdev_get_queue(sbi->sb->s_bdev); int err; if (!capable(CAP_SYS_ADMIN)) return -EPERM; - if (!blk_queue_discard(q)) + if (!bdev_max_discard_sectors(sbi->sb->s_bdev)) return -EOPNOTSUPP; user_range = (struct fstrim_range __user *)arg; if (copy_from_user(&range, user_range, sizeof(range))) return -EFAULT; - range.minlen = max_t(u32, range.minlen, q->limits.discard_granularity); + range.minlen = max_t(u32, range.minlen, + bdev_discard_granularity(sbi->sb->s_bdev)); err = ntfs_trim_fs(sbi, &range); if (err < 0) @@ -115,7 +115,6 @@ static int ntfs_extend_initialized_size(struct file *file, for (;;) { u32 zerofrom, len; struct page *page; - void *fsdata; u8 bits; CLST vcn, lcn, clen; @@ -157,16 +156,14 @@ static int ntfs_extend_initialized_size(struct file *file, if (pos + len > new_valid) len = new_valid - pos; - err = pagecache_write_begin(file, mapping, pos, len, 0, &page, - &fsdata); + err = ntfs_write_begin(file, mapping, pos, len, &page, NULL); if (err) goto out; zero_user_segment(page, zerofrom, PAGE_SIZE); /* This function in any case puts page. */ - err = pagecache_write_end(file, mapping, pos, len, len, page, - fsdata); + err = ntfs_write_end(file, mapping, pos, len, len, page, NULL); if (err < 0) goto out; pos += len; diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c index 9eab11e3b034..74f60c457f28 100644 --- a/fs/ntfs3/inode.c +++ b/fs/ntfs3/inode.c @@ -676,8 +676,9 @@ static sector_t ntfs_bmap(struct address_space *mapping, sector_t block) return generic_block_bmap(mapping, block, ntfs_get_block_bmap); } -static int ntfs_readpage(struct file *file, struct page *page) +static int ntfs_read_folio(struct file *file, struct folio *folio) { + struct page *page = &folio->page; int err; struct address_space *mapping = page->mapping; struct inode *inode = mapping->host; @@ -701,7 +702,7 @@ static int ntfs_readpage(struct file *file, struct page *page) } /* Normal + sparse files. */ - return mpage_readpage(page, ntfs_get_block); + return mpage_read_folio(folio, ntfs_get_block); } static void ntfs_readahead(struct readahead_control *rac) @@ -861,9 +862,8 @@ static int ntfs_get_block_write_begin(struct inode *inode, sector_t vbn, bh_result, create, GET_BLOCK_WRITE_BEGIN); } -static int ntfs_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, u32 len, u32 flags, struct page **pagep, - void **fsdata) +int ntfs_write_begin(struct file *file, struct address_space *mapping, + loff_t pos, u32 len, struct page **pagep, void **fsdata) { int err; struct inode *inode = mapping->host; @@ -872,7 +872,7 @@ static int ntfs_write_begin(struct file *file, struct address_space *mapping, *pagep = NULL; if (is_resident(ni)) { struct page *page = grab_cache_page_write_begin( - mapping, pos >> PAGE_SHIFT, flags); + mapping, pos >> PAGE_SHIFT); if (!page) { err = -ENOMEM; @@ -894,7 +894,7 @@ static int ntfs_write_begin(struct file *file, struct address_space *mapping, goto out; } - err = block_write_begin(mapping, pos, len, flags, pagep, + err = block_write_begin(mapping, pos, len, pagep, ntfs_get_block_write_begin); out: @@ -904,10 +904,9 @@ out: /* * ntfs_write_end - Address_space_operations::write_end. */ -static int ntfs_write_end(struct file *file, struct address_space *mapping, - loff_t pos, u32 len, u32 copied, struct page *page, - void *fsdata) - +int ntfs_write_end(struct file *file, struct address_space *mapping, + loff_t pos, u32 len, u32 copied, struct page *page, + void *fsdata) { struct inode *inode = mapping->host; struct ntfs_inode *ni = ntfs_i(inode); @@ -975,7 +974,7 @@ int reset_log_file(struct inode *inode) len = pos + PAGE_SIZE > log_size ? (log_size - pos) : PAGE_SIZE; - err = block_write_begin(mapping, pos, len, 0, &page, + err = block_write_begin(mapping, pos, len, &page, ntfs_get_block_write_begin); if (err) goto out; @@ -1942,7 +1941,7 @@ const struct inode_operations ntfs_link_inode_operations = { }; const struct address_space_operations ntfs_aops = { - .readpage = ntfs_readpage, + .read_folio = ntfs_read_folio, .readahead = ntfs_readahead, .writepage = ntfs_writepage, .writepages = ntfs_writepages, @@ -1954,7 +1953,7 @@ const struct address_space_operations ntfs_aops = { }; const struct address_space_operations ntfs_aops_cmpr = { - .readpage = ntfs_readpage, + .read_folio = ntfs_read_folio, .readahead = ntfs_readahead, }; // clang-format on diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h index fb825059d488..8de129a6419b 100644 --- a/fs/ntfs3/ntfs_fs.h +++ b/fs/ntfs3/ntfs_fs.h @@ -689,6 +689,11 @@ int ntfs_set_size(struct inode *inode, u64 new_size); int reset_log_file(struct inode *inode); int ntfs_get_block(struct inode *inode, sector_t vbn, struct buffer_head *bh_result, int create); +int ntfs_write_begin(struct file *file, struct address_space *mapping, + loff_t pos, u32 len, struct page **pagep, void **fsdata); +int ntfs_write_end(struct file *file, struct address_space *mapping, + loff_t pos, u32 len, u32 copied, struct page *page, + void *fsdata); int ntfs3_write_inode(struct inode *inode, struct writeback_control *wbc); int ntfs_sync_inode(struct inode *inode); int ntfs_flush_inodes(struct super_block *sb, struct inode *i1, diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c index 278dcf502410..5781b9e8e3d8 100644 --- a/fs/ntfs3/super.c +++ b/fs/ntfs3/super.c @@ -882,7 +882,6 @@ static int ntfs_fill_super(struct super_block *sb, struct fs_context *fc) int err; struct ntfs_sb_info *sbi = sb->s_fs_info; struct block_device *bdev = sb->s_bdev; - struct request_queue *rq; struct inode *inode; struct ntfs_inode *ni; size_t i, tt; @@ -912,15 +911,14 @@ static int ntfs_fill_super(struct super_block *sb, struct fs_context *fc) goto out; } - rq = bdev_get_queue(bdev); - if (blk_queue_discard(rq) && rq->limits.discard_granularity) { - sbi->discard_granularity = rq->limits.discard_granularity; + if (bdev_max_discard_sectors(bdev) && bdev_discard_granularity(bdev)) { + sbi->discard_granularity = bdev_discard_granularity(bdev); sbi->discard_granularity_mask_inv = ~(u64)(sbi->discard_granularity - 1); } /* Parse boot. */ - err = ntfs_init_from_boot(sb, rq ? queue_logical_block_size(rq) : 512, + err = ntfs_init_from_boot(sb, bdev_logical_block_size(bdev), bdev_nr_bytes(bdev)); if (err) goto out; @@ -1335,7 +1333,7 @@ int ntfs_discard(struct ntfs_sb_info *sbi, CLST lcn, CLST len) return 0; err = blkdev_issue_discard(sb->s_bdev, start >> 9, (end - start) >> 9, - GFP_NOFS, 0); + GFP_NOFS); if (err == -EOPNOTSUPP) sbi->flags |= NTFS_FLAGS_NODISCARD; diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c index 49f41074baad..51c93929a146 100644 --- a/fs/ocfs2/alloc.c +++ b/fs/ocfs2/alloc.c @@ -7427,7 +7427,7 @@ int ocfs2_truncate_inline(struct inode *inode, struct buffer_head *di_bh, /* * No need to worry about the data page here - it's been * truncated already and inline data doesn't need it for - * pushing zero's to disk, so we'll let readpage pick it up + * pushing zero's to disk, so we'll let read_folio pick it up * later. */ if (trunc) { diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index 4b9af65cb61b..35d40a67204c 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -275,8 +275,9 @@ out: return ret; } -static int ocfs2_readpage(struct file *file, struct page *page) +static int ocfs2_read_folio(struct file *file, struct folio *folio) { + struct page *page = &folio->page; struct inode *inode = page->mapping->host; struct ocfs2_inode_info *oi = OCFS2_I(inode); loff_t start = (loff_t)page->index << PAGE_SHIFT; @@ -309,7 +310,7 @@ static int ocfs2_readpage(struct file *file, struct page *page) /* * i_size might have just been updated as we grabed the meta lock. We * might now be discovering a truncate that hit on another node. - * block_read_full_page->get_block freaks out if it is asked to read + * block_read_full_folio->get_block freaks out if it is asked to read * beyond the end of a file, so we check here. Callers * (generic_file_read, vm_ops->fault) are clever enough to check i_size * and notice that the page they just read isn't needed. @@ -326,7 +327,7 @@ static int ocfs2_readpage(struct file *file, struct page *page) if (oi->ip_dyn_features & OCFS2_INLINE_DATA_FL) ret = ocfs2_readpage_inline(inode, page); else - ret = block_read_full_page(page, ocfs2_get_block); + ret = block_read_full_folio(page_folio(page), ocfs2_get_block); unlock = 0; out_alloc: @@ -497,11 +498,11 @@ bail: return status; } -static int ocfs2_releasepage(struct page *page, gfp_t wait) +static bool ocfs2_release_folio(struct folio *folio, gfp_t wait) { - if (!page_has_buffers(page)) - return 0; - return try_to_free_buffers(page); + if (!folio_buffers(folio)) + return false; + return try_to_free_buffers(folio); } static void ocfs2_figure_cluster_boundaries(struct ocfs2_super *osb, @@ -1881,7 +1882,7 @@ out: } static int ocfs2_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, + loff_t pos, unsigned len, struct page **pagep, void **fsdata) { int ret; @@ -1897,7 +1898,7 @@ static int ocfs2_write_begin(struct file *file, struct address_space *mapping, /* * Take alloc sem here to prevent concurrent lookups. That way * the mapping, zeroing and tree manipulation within - * ocfs2_write() will be safe against ->readpage(). This + * ocfs2_write() will be safe against ->read_folio(). This * should also serve to lock out allocation from a shared * writeable region. */ @@ -2454,7 +2455,7 @@ static ssize_t ocfs2_direct_IO(struct kiocb *iocb, struct iov_iter *iter) const struct address_space_operations ocfs2_aops = { .dirty_folio = block_dirty_folio, - .readpage = ocfs2_readpage, + .read_folio = ocfs2_read_folio, .readahead = ocfs2_readahead, .writepage = ocfs2_writepage, .write_begin = ocfs2_write_begin, @@ -2462,7 +2463,7 @@ const struct address_space_operations ocfs2_aops = { .bmap = ocfs2_bmap, .direct_IO = ocfs2_direct_IO, .invalidate_folio = block_invalidate_folio, - .releasepage = ocfs2_releasepage, + .release_folio = ocfs2_release_folio, .migratepage = buffer_migrate_page, .is_partially_uptodate = block_is_partially_uptodate, .error_remove_page = generic_error_remove_page, diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 01b7407a8893..7497cd592258 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -2526,7 +2526,7 @@ static ssize_t ocfs2_file_read_iter(struct kiocb *iocb, return -EOPNOTSUPP; /* - * buffered reads protect themselves in ->readpage(). O_DIRECT reads + * buffered reads protect themselves in ->read_folio(). O_DIRECT reads * need locks to protect pending reads from racing with truncate. */ if (direct_io) { diff --git a/fs/ocfs2/ioctl.c b/fs/ocfs2/ioctl.c index f59461d85da4..afd54ec66103 100644 --- a/fs/ocfs2/ioctl.c +++ b/fs/ocfs2/ioctl.c @@ -903,20 +903,19 @@ long ocfs2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) case FITRIM: { struct super_block *sb = inode->i_sb; - struct request_queue *q = bdev_get_queue(sb->s_bdev); struct fstrim_range range; int ret = 0; if (!capable(CAP_SYS_ADMIN)) return -EPERM; - if (!blk_queue_discard(q)) + if (!bdev_max_discard_sectors(sb->s_bdev)) return -EOPNOTSUPP; if (copy_from_user(&range, argp, sizeof(range))) return -EFAULT; - range.minlen = max_t(u64, q->limits.discard_granularity, + range.minlen = max_t(u64, bdev_discard_granularity(sb->s_bdev), range.minlen); ret = ocfs2_trim_fs(sb, &range); if (ret < 0) diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c index 7f6355cbb587..e04358a46b68 100644 --- a/fs/ocfs2/refcounttree.c +++ b/fs/ocfs2/refcounttree.c @@ -2961,12 +2961,14 @@ retry: } if (!PageUptodate(page)) { - ret = block_read_full_page(page, ocfs2_get_block); + struct folio *folio = page_folio(page); + + ret = block_read_full_folio(folio, ocfs2_get_block); if (ret) { mlog_errno(ret); goto unlock; } - lock_page(page); + folio_lock(folio); } if (page_has_buffers(page)) { diff --git a/fs/ocfs2/symlink.c b/fs/ocfs2/symlink.c index f755a4985821..d4c5fdcfa1e4 100644 --- a/fs/ocfs2/symlink.c +++ b/fs/ocfs2/symlink.c @@ -52,8 +52,9 @@ #include "buffer_head_io.h" -static int ocfs2_fast_symlink_readpage(struct file *unused, struct page *page) +static int ocfs2_fast_symlink_read_folio(struct file *f, struct folio *folio) { + struct page *page = &folio->page; struct inode *inode = page->mapping->host; struct buffer_head *bh = NULL; int status = ocfs2_read_inode_block(inode, &bh); @@ -81,7 +82,7 @@ static int ocfs2_fast_symlink_readpage(struct file *unused, struct page *page) } const struct address_space_operations ocfs2_fast_symlink_aops = { - .readpage = ocfs2_fast_symlink_readpage, + .read_folio = ocfs2_fast_symlink_read_folio, }; const struct inode_operations ocfs2_symlink_inode_operations = { diff --git a/fs/omfs/file.c b/fs/omfs/file.c index 3f297b541713..fa7fe2393ff6 100644 --- a/fs/omfs/file.c +++ b/fs/omfs/file.c @@ -284,9 +284,9 @@ out: return ret; } -static int omfs_readpage(struct file *file, struct page *page) +static int omfs_read_folio(struct file *file, struct folio *folio) { - return block_read_full_page(page, omfs_get_block); + return block_read_full_folio(folio, omfs_get_block); } static void omfs_readahead(struct readahead_control *rac) @@ -316,13 +316,12 @@ static void omfs_write_failed(struct address_space *mapping, loff_t to) } static int omfs_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, + loff_t pos, unsigned len, struct page **pagep, void **fsdata) { int ret; - ret = block_write_begin(mapping, pos, len, flags, pagep, - omfs_get_block); + ret = block_write_begin(mapping, pos, len, pagep, omfs_get_block); if (unlikely(ret)) omfs_write_failed(mapping, pos + len); @@ -374,7 +373,7 @@ const struct inode_operations omfs_file_inops = { const struct address_space_operations omfs_aops = { .dirty_folio = block_dirty_folio, .invalidate_folio = block_invalidate_folio, - .readpage = omfs_readpage, + .read_folio = omfs_read_folio, .readahead = omfs_readahead, .writepage = omfs_writepage, .writepages = omfs_writepages, diff --git a/fs/orangefs/inode.c b/fs/orangefs/inode.c index 79c1025d18ea..5ce27dde3c79 100644 --- a/fs/orangefs/inode.c +++ b/fs/orangefs/inode.c @@ -288,47 +288,45 @@ static void orangefs_readahead(struct readahead_control *rac) } } -static int orangefs_readpage(struct file *file, struct page *page) +static int orangefs_read_folio(struct file *file, struct folio *folio) { - struct folio *folio = page_folio(page); - struct inode *inode = page->mapping->host; + struct inode *inode = folio->mapping->host; struct iov_iter iter; struct bio_vec bv; ssize_t ret; - loff_t off; /* offset into this page */ + loff_t off; /* offset of this folio in the file */ if (folio_test_dirty(folio)) orangefs_launder_folio(folio); - off = page_offset(page); - bv.bv_page = page; - bv.bv_len = PAGE_SIZE; + off = folio_pos(folio); + bv.bv_page = &folio->page; + bv.bv_len = folio_size(folio); bv.bv_offset = 0; - iov_iter_bvec(&iter, READ, &bv, 1, PAGE_SIZE); + iov_iter_bvec(&iter, READ, &bv, 1, folio_size(folio)); ret = wait_for_direct_io(ORANGEFS_IO_READ, inode, &off, &iter, - PAGE_SIZE, inode->i_size, NULL, NULL, file); + folio_size(folio), inode->i_size, NULL, NULL, file); /* this will only zero remaining unread portions of the page data */ iov_iter_zero(~0U, &iter); /* takes care of potential aliasing */ - flush_dcache_page(page); + flush_dcache_folio(folio); if (ret < 0) { - SetPageError(page); + folio_set_error(folio); } else { - SetPageUptodate(page); - if (PageError(page)) - ClearPageError(page); + folio_mark_uptodate(folio); + if (folio_test_error(folio)) + folio_clear_error(folio); ret = 0; } - /* unlock the page after the ->readpage() routine completes */ - unlock_page(page); + /* unlock the folio after the ->read_folio() routine completes */ + folio_unlock(folio); return ret; } static int orangefs_write_begin(struct file *file, - struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, struct page **pagep, - void **fsdata) + struct address_space *mapping, loff_t pos, unsigned len, + struct page **pagep, void **fsdata) { struct orangefs_write_range *wr; struct folio *folio; @@ -338,7 +336,7 @@ static int orangefs_write_begin(struct file *file, index = pos >> PAGE_SHIFT; - page = grab_cache_page_write_begin(mapping, index, flags); + page = grab_cache_page_write_begin(mapping, index); if (!page) return -ENOMEM; @@ -487,14 +485,14 @@ static void orangefs_invalidate_folio(struct folio *folio, orangefs_launder_folio(folio); } -static int orangefs_releasepage(struct page *page, gfp_t foo) +static bool orangefs_release_folio(struct folio *folio, gfp_t foo) { - return !PagePrivate(page); + return !folio_test_private(folio); } -static void orangefs_freepage(struct page *page) +static void orangefs_free_folio(struct folio *folio) { - kfree(detach_page_private(page)); + kfree(folio_detach_private(folio)); } static int orangefs_launder_folio(struct folio *folio) @@ -632,14 +630,14 @@ out: static const struct address_space_operations orangefs_address_operations = { .writepage = orangefs_writepage, .readahead = orangefs_readahead, - .readpage = orangefs_readpage, + .read_folio = orangefs_read_folio, .writepages = orangefs_writepages, .dirty_folio = filemap_dirty_folio, .write_begin = orangefs_write_begin, .write_end = orangefs_write_end, .invalidate_folio = orangefs_invalidate_folio, - .releasepage = orangefs_releasepage, - .freepage = orangefs_freepage, + .release_folio = orangefs_release_folio, + .free_folio = orangefs_free_folio, .launder_folio = orangefs_launder_folio, .direct_IO = orangefs_direct_IO, }; diff --git a/fs/pipe.c b/fs/pipe.c index 9648ac15164a..e140ea150bbb 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -804,7 +804,7 @@ struct pipe_inode_info *alloc_pipe_info(void) if (too_many_pipe_buffers_hard(user_bufs) && pipe_is_unprivileged_user()) goto out_revert_acct; - pipe->bufs = kvcalloc(pipe_bufs, sizeof(struct pipe_buffer), + pipe->bufs = kcalloc(pipe_bufs, sizeof(struct pipe_buffer), GFP_KERNEL_ACCOUNT); if (pipe->bufs) { @@ -849,7 +849,7 @@ void free_pipe_info(struct pipe_inode_info *pipe) #endif if (pipe->tmp_page) __free_page(pipe->tmp_page); - kvfree(pipe->bufs); + kfree(pipe->bufs); kfree(pipe); } @@ -1264,7 +1264,8 @@ int pipe_resize_ring(struct pipe_inode_info *pipe, unsigned int nr_slots) if (nr_slots < n) return -EBUSY; - bufs = kvcalloc(nr_slots, sizeof(*bufs), GFP_KERNEL_ACCOUNT); + bufs = kcalloc(nr_slots, sizeof(*bufs), + GFP_KERNEL_ACCOUNT | __GFP_NOWARN); if (unlikely(!bufs)) return -ENOMEM; @@ -1291,7 +1292,7 @@ int pipe_resize_ring(struct pipe_inode_info *pipe, unsigned int nr_slots) head = n; tail = 0; - kvfree(pipe->bufs); + kfree(pipe->bufs); pipe->bufs = bufs; pipe->ring_size = nr_slots; if (pipe->max_usage > nr_slots) diff --git a/fs/posix_acl.c b/fs/posix_acl.c index 80acb6885cf9..962d32468eb4 100644 --- a/fs/posix_acl.c +++ b/fs/posix_acl.c @@ -759,9 +759,14 @@ static void posix_acl_fix_xattr_userns( } void posix_acl_fix_xattr_from_user(struct user_namespace *mnt_userns, + struct inode *inode, void *value, size_t size) { struct user_namespace *user_ns = current_user_ns(); + + /* Leave ids untouched on non-idmapped mounts. */ + if (no_idmapping(mnt_userns, i_user_ns(inode))) + mnt_userns = &init_user_ns; if ((user_ns == &init_user_ns) && (mnt_userns == &init_user_ns)) return; posix_acl_fix_xattr_userns(&init_user_ns, user_ns, mnt_userns, value, @@ -769,9 +774,14 @@ void posix_acl_fix_xattr_from_user(struct user_namespace *mnt_userns, } void posix_acl_fix_xattr_to_user(struct user_namespace *mnt_userns, + struct inode *inode, void *value, size_t size) { struct user_namespace *user_ns = current_user_ns(); + + /* Leave ids untouched on non-idmapped mounts. */ + if (no_idmapping(mnt_userns, i_user_ns(inode))) + mnt_userns = &init_user_ns; if ((user_ns == &init_user_ns) && (mnt_userns == &init_user_ns)) return; posix_acl_fix_xattr_userns(user_ns, &init_user_ns, mnt_userns, value, diff --git a/fs/proc/cpuinfo.c b/fs/proc/cpuinfo.c index 419760fd77bd..f38bda5b83ec 100644 --- a/fs/proc/cpuinfo.c +++ b/fs/proc/cpuinfo.c @@ -5,14 +5,10 @@ #include <linux/proc_fs.h> #include <linux/seq_file.h> -__weak void arch_freq_prepare_all(void) -{ -} - extern const struct seq_operations cpuinfo_op; + static int cpuinfo_open(struct inode *inode, struct file *file) { - arch_freq_prepare_all(); return seq_open(file, &cpuinfo_op); } diff --git a/fs/proc/fd.c b/fs/proc/fd.c index 172c86270b31..913bef0d2a36 100644 --- a/fs/proc/fd.c +++ b/fs/proc/fd.c @@ -72,7 +72,7 @@ out: return 0; } -static int seq_fdinfo_open(struct inode *inode, struct file *file) +static int proc_fdinfo_access_allowed(struct inode *inode) { bool allowed = false; struct task_struct *task = get_proc_task(inode); @@ -86,6 +86,16 @@ static int seq_fdinfo_open(struct inode *inode, struct file *file) if (!allowed) return -EACCES; + return 0; +} + +static int seq_fdinfo_open(struct inode *inode, struct file *file) +{ + int ret = proc_fdinfo_access_allowed(inode); + + if (ret) + return ret; + return single_open(file, seq_show, inode); } @@ -348,12 +358,23 @@ static int proc_readfdinfo(struct file *file, struct dir_context *ctx) proc_fdinfo_instantiate); } +static int proc_open_fdinfo(struct inode *inode, struct file *file) +{ + int ret = proc_fdinfo_access_allowed(inode); + + if (ret) + return ret; + + return 0; +} + const struct inode_operations proc_fdinfo_inode_operations = { .lookup = proc_lookupfdinfo, .setattr = proc_setattr, }; const struct file_operations proc_fdinfo_operations = { + .open = proc_open_fdinfo, .read = generic_read_dir, .iterate_shared = proc_readfdinfo, .llseek = generic_file_llseek, diff --git a/fs/qnx4/inode.c b/fs/qnx4/inode.c index a635bb6615e9..391ea402920d 100644 --- a/fs/qnx4/inode.c +++ b/fs/qnx4/inode.c @@ -245,17 +245,18 @@ static void qnx4_kill_sb(struct super_block *sb) } } -static int qnx4_readpage(struct file *file, struct page *page) +static int qnx4_read_folio(struct file *file, struct folio *folio) { - return block_read_full_page(page,qnx4_get_block); + return block_read_full_folio(folio, qnx4_get_block); } static sector_t qnx4_bmap(struct address_space *mapping, sector_t block) { return generic_block_bmap(mapping,block,qnx4_get_block); } + static const struct address_space_operations qnx4_aops = { - .readpage = qnx4_readpage, + .read_folio = qnx4_read_folio, .bmap = qnx4_bmap }; diff --git a/fs/qnx6/inode.c b/fs/qnx6/inode.c index 9d8e7e9788a1..b9895afca9d1 100644 --- a/fs/qnx6/inode.c +++ b/fs/qnx6/inode.c @@ -94,9 +94,9 @@ static int qnx6_check_blockptr(__fs32 ptr) return 1; } -static int qnx6_readpage(struct file *file, struct page *page) +static int qnx6_read_folio(struct file *file, struct folio *folio) { - return mpage_readpage(page, qnx6_get_block); + return mpage_read_folio(folio, qnx6_get_block); } static void qnx6_readahead(struct readahead_control *rac) @@ -496,7 +496,7 @@ static sector_t qnx6_bmap(struct address_space *mapping, sector_t block) return generic_block_bmap(mapping, block, qnx6_get_block); } static const struct address_space_operations qnx6_aops = { - .readpage = qnx6_readpage, + .read_folio = qnx6_read_folio, .readahead = qnx6_readahead, .bmap = qnx6_bmap }; diff --git a/fs/reiserfs/file.c b/fs/reiserfs/file.c index 203a47232707..6e228bfbe7ef 100644 --- a/fs/reiserfs/file.c +++ b/fs/reiserfs/file.c @@ -227,7 +227,7 @@ drop_write_lock: } /* * If this is a partial write which happened to make all buffers - * uptodate then we can optimize away a bogus readpage() for + * uptodate then we can optimize away a bogus read_folio() for * the next read(). Here we 'discover' whether the page went * uptodate as a result of this (potentially partial) write. */ diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index 36c59b25486c..0cffe054b78e 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -167,10 +167,10 @@ inline void make_le_item_head(struct item_head *ih, const struct cpu_key *key, * cutting the code is fine, since it really isn't in use yet and is easy * to add back in. But, Vladimir has a really good idea here. Think * about what happens for reading a file. For each page, - * The VFS layer calls reiserfs_readpage, who searches the tree to find + * The VFS layer calls reiserfs_read_folio, who searches the tree to find * an indirect item. This indirect item has X number of pointers, where * X is a big number if we've done the block allocation right. But, - * we only use one or two of these pointers during each call to readpage, + * we only use one or two of these pointers during each call to read_folio, * needlessly researching again later on. * * The size of the cache could be dynamic based on the size of the file. @@ -966,7 +966,7 @@ research: * it is important the set_buffer_uptodate is done * after the direct2indirect. The buffer might * contain valid data newer than the data on disk - * (read by readpage, changed, and then sent here by + * (read by read_folio, changed, and then sent here by * writepage). direct2indirect needs to know if unbh * was already up to date, so it can decide if the * data in unbh needs to be replaced with data from @@ -2733,9 +2733,9 @@ fail: goto done; } -static int reiserfs_readpage(struct file *f, struct page *page) +static int reiserfs_read_folio(struct file *f, struct folio *folio) { - return block_read_full_page(page, reiserfs_get_block); + return block_read_full_folio(folio, reiserfs_get_block); } static int reiserfs_writepage(struct page *page, struct writeback_control *wbc) @@ -2753,7 +2753,7 @@ static void reiserfs_truncate_failed_write(struct inode *inode) static int reiserfs_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, + loff_t pos, unsigned len, struct page **pagep, void **fsdata) { struct inode *inode; @@ -2764,7 +2764,7 @@ static int reiserfs_write_begin(struct file *file, inode = mapping->host; index = pos >> PAGE_SHIFT; - page = grab_cache_page_write_begin(mapping, index, flags); + page = grab_cache_page_write_begin(mapping, index); if (!page) return -ENOMEM; *pagep = page; @@ -3202,39 +3202,39 @@ static bool reiserfs_dirty_folio(struct address_space *mapping, } /* - * Returns 1 if the page's buffers were dropped. The page is locked. + * Returns true if the folio's buffers were dropped. The folio is locked. * * Takes j_dirty_buffers_lock to protect the b_assoc_buffers list_heads - * in the buffers at page_buffers(page). + * in the buffers at folio_buffers(folio). * * even in -o notail mode, we can't be sure an old mount without -o notail * didn't create files with tails. */ -static int reiserfs_releasepage(struct page *page, gfp_t unused_gfp_flags) +static bool reiserfs_release_folio(struct folio *folio, gfp_t unused_gfp_flags) { - struct inode *inode = page->mapping->host; + struct inode *inode = folio->mapping->host; struct reiserfs_journal *j = SB_JOURNAL(inode->i_sb); struct buffer_head *head; struct buffer_head *bh; - int ret = 1; + bool ret = true; - WARN_ON(PageChecked(page)); + WARN_ON(folio_test_checked(folio)); spin_lock(&j->j_dirty_buffers_lock); - head = page_buffers(page); + head = folio_buffers(folio); bh = head; do { if (bh->b_private) { if (!buffer_dirty(bh) && !buffer_locked(bh)) { reiserfs_free_jh(bh); } else { - ret = 0; + ret = false; break; } } bh = bh->b_this_page; } while (bh != head); if (ret) - ret = try_to_free_buffers(page); + ret = try_to_free_buffers(folio); spin_unlock(&j->j_dirty_buffers_lock); return ret; } @@ -3421,9 +3421,9 @@ out: const struct address_space_operations reiserfs_address_space_operations = { .writepage = reiserfs_writepage, - .readpage = reiserfs_readpage, + .read_folio = reiserfs_read_folio, .readahead = reiserfs_readahead, - .releasepage = reiserfs_releasepage, + .release_folio = reiserfs_release_folio, .invalidate_folio = reiserfs_invalidate_folio, .write_begin = reiserfs_write_begin, .write_end = reiserfs_write_end, diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c index b5b6f6201bed..d8cc9a366124 100644 --- a/fs/reiserfs/journal.c +++ b/fs/reiserfs/journal.c @@ -601,14 +601,14 @@ static int journal_list_still_alive(struct super_block *s, */ static void release_buffer_page(struct buffer_head *bh) { - struct page *page = bh->b_page; - if (!page->mapping && trylock_page(page)) { - get_page(page); + struct folio *folio = page_folio(bh->b_page); + if (!folio->mapping && folio_trylock(folio)) { + folio_get(folio); put_bh(bh); - if (!page->mapping) - try_to_free_buffers(page); - unlock_page(page); - put_page(page); + if (!folio->mapping) + try_to_free_buffers(folio); + folio_unlock(folio); + folio_put(folio); } else { put_bh(bh); } diff --git a/fs/romfs/super.c b/fs/romfs/super.c index 9e6bbb4219de..c59b230d55b4 100644 --- a/fs/romfs/super.c +++ b/fs/romfs/super.c @@ -18,7 +18,7 @@ * Changed for 2.1.19 modules * Jan 1997 Initial release * Jun 1997 2.1.43+ changes - * Proper page locking in readpage + * Proper page locking in read_folio * Changed to work with 2.1.45+ fs * Jul 1997 Fixed follow_link * 2.1.47 @@ -41,7 +41,7 @@ * dentries in lookup * clean up page flags setting * (error, uptodate, locking) in - * in readpage + * in read_folio * use init_special_inode for * fifos/sockets (and streamline) in * read_inode, fix _ops table order @@ -99,8 +99,9 @@ static struct inode *romfs_iget(struct super_block *sb, unsigned long pos); /* * read a page worth of data from the image */ -static int romfs_readpage(struct file *file, struct page *page) +static int romfs_read_folio(struct file *file, struct folio *folio) { + struct page *page = &folio->page; struct inode *inode = page->mapping->host; loff_t offset, size; unsigned long fillsize, pos; @@ -142,7 +143,7 @@ static int romfs_readpage(struct file *file, struct page *page) } static const struct address_space_operations romfs_aops = { - .readpage = romfs_readpage + .read_folio = romfs_read_folio }; /* diff --git a/fs/squashfs/block.c b/fs/squashfs/block.c index 622c844f6d11..8879d052f96c 100644 --- a/fs/squashfs/block.c +++ b/fs/squashfs/block.c @@ -86,17 +86,10 @@ static int squashfs_bio_read(struct super_block *sb, u64 index, int length, int error, i; struct bio *bio; - if (page_count <= BIO_MAX_VECS) { - bio = bio_alloc(sb->s_bdev, page_count, REQ_OP_READ, GFP_NOIO); - } else { - bio = bio_kmalloc(GFP_NOIO, page_count); - bio_set_dev(bio, sb->s_bdev); - bio->bi_opf = REQ_OP_READ; - } - + bio = bio_kmalloc(page_count, GFP_NOIO); if (!bio) return -ENOMEM; - + bio_init(bio, sb->s_bdev, bio->bi_inline_vecs, page_count, REQ_OP_READ); bio->bi_iter.bi_sector = block * (msblk->devblksize >> SECTOR_SHIFT); for (i = 0; i < page_count; ++i) { @@ -126,7 +119,8 @@ static int squashfs_bio_read(struct super_block *sb, u64 index, int length, out_free_bio: bio_free_pages(bio); - bio_put(bio); + bio_uninit(bio); + kfree(bio); return error; } @@ -190,7 +184,8 @@ int squashfs_read_data(struct super_block *sb, u64 index, int length, length |= data[0] << 8; } bio_free_pages(bio); - bio_put(bio); + bio_uninit(bio); + kfree(bio); compressed = SQUASHFS_COMPRESSED(length); length = SQUASHFS_COMPRESSED_SIZE(length); @@ -224,7 +219,8 @@ int squashfs_read_data(struct super_block *sb, u64 index, int length, out_free_bio: bio_free_pages(bio); - bio_put(bio); + bio_uninit(bio); + kfree(bio); out: if (res < 0) { ERROR("Failed to read block 0x%llx: %d\n", index, res); diff --git a/fs/squashfs/file.c b/fs/squashfs/file.c index 89d492916dea..a8e495d8eb86 100644 --- a/fs/squashfs/file.c +++ b/fs/squashfs/file.c @@ -444,8 +444,9 @@ static int squashfs_readpage_sparse(struct page *page, int expected) return 0; } -static int squashfs_readpage(struct file *file, struct page *page) +static int squashfs_read_folio(struct file *file, struct folio *folio) { + struct page *page = &folio->page; struct inode *inode = page->mapping->host; struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info; int index = page->index >> (msblk->block_log - PAGE_SHIFT); @@ -496,5 +497,5 @@ out: const struct address_space_operations squashfs_aops = { - .readpage = squashfs_readpage + .read_folio = squashfs_read_folio }; diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c index 4f74abbc1a54..6d594ba2ed28 100644 --- a/fs/squashfs/super.c +++ b/fs/squashfs/super.c @@ -148,7 +148,7 @@ static int squashfs_fill_super(struct super_block *sb, struct fs_context *fc) /* * squashfs provides 'backing_dev_info' in order to disable read-ahead. For - * squashfs, I/O is not deferred, it is done immediately in readpage, + * squashfs, I/O is not deferred, it is done immediately in read_folio, * which means the user would always have to wait their own I/O. So the effect * of readahead is very weak for squashfs. squashfs_bdi_init will set * sb->s_bdi->ra_pages and sb->s_bdi->io_pages to 0 and close readahead for diff --git a/fs/squashfs/symlink.c b/fs/squashfs/symlink.c index 1430613183e6..2bf977a52c2c 100644 --- a/fs/squashfs/symlink.c +++ b/fs/squashfs/symlink.c @@ -30,8 +30,9 @@ #include "squashfs.h" #include "xattr.h" -static int squashfs_symlink_readpage(struct file *file, struct page *page) +static int squashfs_symlink_read_folio(struct file *file, struct folio *folio) { + struct page *page = &folio->page; struct inode *inode = page->mapping->host; struct super_block *sb = inode->i_sb; struct squashfs_sb_info *msblk = sb->s_fs_info; @@ -101,7 +102,7 @@ error_out: const struct address_space_operations squashfs_symlink_aops = { - .readpage = squashfs_symlink_readpage + .read_folio = squashfs_symlink_read_folio }; const struct inode_operations squashfs_symlink_inode_ops = { diff --git a/fs/stat.c b/fs/stat.c index 7f734be0e57e..5c2c94464e8b 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -348,9 +348,6 @@ SYSCALL_DEFINE2(fstat, unsigned int, fd, struct __old_kernel_stat __user *, stat # define choose_32_64(a,b) b #endif -#define valid_dev(x) choose_32_64(old_valid_dev(x),true) -#define encode_dev(x) choose_32_64(old_encode_dev,new_encode_dev)(x) - #ifndef INIT_STRUCT_STAT_PADDING # define INIT_STRUCT_STAT_PADDING(st) memset(&st, 0, sizeof(st)) #endif @@ -359,7 +356,9 @@ static int cp_new_stat(struct kstat *stat, struct stat __user *statbuf) { struct stat tmp; - if (!valid_dev(stat->dev) || !valid_dev(stat->rdev)) + if (sizeof(tmp.st_dev) < 4 && !old_valid_dev(stat->dev)) + return -EOVERFLOW; + if (sizeof(tmp.st_rdev) < 4 && !old_valid_dev(stat->rdev)) return -EOVERFLOW; #if BITS_PER_LONG == 32 if (stat->size > MAX_NON_LFS) @@ -367,7 +366,7 @@ static int cp_new_stat(struct kstat *stat, struct stat __user *statbuf) #endif INIT_STRUCT_STAT_PADDING(tmp); - tmp.st_dev = encode_dev(stat->dev); + tmp.st_dev = new_encode_dev(stat->dev); tmp.st_ino = stat->ino; if (sizeof(tmp.st_ino) < sizeof(stat->ino) && tmp.st_ino != stat->ino) return -EOVERFLOW; @@ -377,7 +376,7 @@ static int cp_new_stat(struct kstat *stat, struct stat __user *statbuf) return -EOVERFLOW; SET_UID(tmp.st_uid, from_kuid_munged(current_user_ns(), stat->uid)); SET_GID(tmp.st_gid, from_kgid_munged(current_user_ns(), stat->gid)); - tmp.st_rdev = encode_dev(stat->rdev); + tmp.st_rdev = new_encode_dev(stat->rdev); tmp.st_size = stat->size; tmp.st_atime = stat->atime.tv_sec; tmp.st_mtime = stat->mtime.tv_sec; @@ -665,11 +664,13 @@ static int cp_compat_stat(struct kstat *stat, struct compat_stat __user *ubuf) { struct compat_stat tmp; - if (!old_valid_dev(stat->dev) || !old_valid_dev(stat->rdev)) + if (sizeof(tmp.st_dev) < 4 && !old_valid_dev(stat->dev)) + return -EOVERFLOW; + if (sizeof(tmp.st_rdev) < 4 && !old_valid_dev(stat->rdev)) return -EOVERFLOW; memset(&tmp, 0, sizeof(tmp)); - tmp.st_dev = old_encode_dev(stat->dev); + tmp.st_dev = new_encode_dev(stat->dev); tmp.st_ino = stat->ino; if (sizeof(tmp.st_ino) < sizeof(stat->ino) && tmp.st_ino != stat->ino) return -EOVERFLOW; @@ -679,7 +680,7 @@ static int cp_compat_stat(struct kstat *stat, struct compat_stat __user *ubuf) return -EOVERFLOW; SET_UID(tmp.st_uid, from_kuid_munged(current_user_ns(), stat->uid)); SET_GID(tmp.st_gid, from_kgid_munged(current_user_ns(), stat->gid)); - tmp.st_rdev = old_encode_dev(stat->rdev); + tmp.st_rdev = new_encode_dev(stat->rdev); if ((u64) stat->size > MAX_NON_LFS) return -EOVERFLOW; tmp.st_size = stat->size; diff --git a/fs/super.c b/fs/super.c index f1d4a193602d..60f57c7bc0a6 100644 --- a/fs/super.c +++ b/fs/super.c @@ -1204,7 +1204,7 @@ static int set_bdev_super(struct super_block *s, void *data) s->s_dev = s->s_bdev->bd_dev; s->s_bdi = bdi_get(s->s_bdev->bd_disk->bdi); - if (blk_queue_stable_writes(s->s_bdev->bd_disk->queue)) + if (bdev_stable_writes(s->s_bdev)) s->s_iflags |= SB_I_STABLE_WRITES; return 0; } diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index 42dcf96881b6..a12ac0356c69 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -703,19 +703,6 @@ int sysfs_change_owner(struct kobject *kobj, kuid_t kuid, kgid_t kgid) ktype = get_ktype(kobj); if (ktype) { - struct attribute **kattr; - - /* - * Change owner of the default attributes associated with the - * ktype of @kobj. - */ - for (kattr = ktype->default_attrs; kattr && *kattr; kattr++) { - error = sysfs_file_change_owner(kobj, (*kattr)->name, - kuid, kgid); - if (error) - return error; - } - /* * Change owner of the default groups associated with the * ktype of @kobj. diff --git a/fs/sysv/itree.c b/fs/sysv/itree.c index 409ab5e17803..d4ec9bb97de9 100644 --- a/fs/sysv/itree.c +++ b/fs/sysv/itree.c @@ -456,9 +456,9 @@ static int sysv_writepage(struct page *page, struct writeback_control *wbc) return block_write_full_page(page,get_block,wbc); } -static int sysv_readpage(struct file *file, struct page *page) +static int sysv_read_folio(struct file *file, struct folio *folio) { - return block_read_full_page(page,get_block); + return block_read_full_folio(folio, get_block); } int sysv_prepare_chunk(struct page *page, loff_t pos, unsigned len) @@ -477,12 +477,12 @@ static void sysv_write_failed(struct address_space *mapping, loff_t to) } static int sysv_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, + loff_t pos, unsigned len, struct page **pagep, void **fsdata) { int ret; - ret = block_write_begin(mapping, pos, len, flags, pagep, get_block); + ret = block_write_begin(mapping, pos, len, pagep, get_block); if (unlikely(ret)) sysv_write_failed(mapping, pos + len); @@ -497,7 +497,7 @@ static sector_t sysv_bmap(struct address_space *mapping, sector_t block) const struct address_space_operations sysv_aops = { .dirty_folio = block_dirty_folio, .invalidate_folio = block_invalidate_folio, - .readpage = sysv_readpage, + .read_folio = sysv_read_folio, .writepage = sysv_writepage, .write_begin = sysv_write_begin, .write_end = generic_write_end, diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index 0383fbdc95ff..04ced154960f 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -31,9 +31,9 @@ * in the "sys_write -> alloc_pages -> direct reclaim path". So, in * 'ubifs_writepage()' we are only guaranteed that the page is locked. * - * Similarly, @i_mutex is not always locked in 'ubifs_readpage()', e.g., the + * Similarly, @i_mutex is not always locked in 'ubifs_read_folio()', e.g., the * read-ahead path does not lock it ("sys_read -> generic_file_aio_read -> - * ondemand_readahead -> readpage"). In case of readahead, @I_SYNC flag is not + * ondemand_readahead -> read_folio"). In case of readahead, @I_SYNC flag is not * set as well. However, UBIFS disables readahead. */ @@ -215,8 +215,7 @@ static void release_existing_page_budget(struct ubifs_info *c) } static int write_begin_slow(struct address_space *mapping, - loff_t pos, unsigned len, struct page **pagep, - unsigned flags) + loff_t pos, unsigned len, struct page **pagep) { struct inode *inode = mapping->host; struct ubifs_info *c = inode->i_sb->s_fs_info; @@ -244,7 +243,7 @@ static int write_begin_slow(struct address_space *mapping, if (unlikely(err)) return err; - page = grab_cache_page_write_begin(mapping, index, flags); + page = grab_cache_page_write_begin(mapping, index); if (unlikely(!page)) { ubifs_release_budget(c, &req); return -ENOMEM; @@ -419,7 +418,7 @@ static int allocate_budget(struct ubifs_info *c, struct page *page, * without forcing write-back. The slow path does not make this assumption. */ static int ubifs_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, + loff_t pos, unsigned len, struct page **pagep, void **fsdata) { struct inode *inode = mapping->host; @@ -437,7 +436,7 @@ static int ubifs_write_begin(struct file *file, struct address_space *mapping, return -EROFS; /* Try out the fast-path part first */ - page = grab_cache_page_write_begin(mapping, index, flags); + page = grab_cache_page_write_begin(mapping, index); if (unlikely(!page)) return -ENOMEM; @@ -493,7 +492,7 @@ static int ubifs_write_begin(struct file *file, struct address_space *mapping, unlock_page(page); put_page(page); - return write_begin_slow(mapping, pos, len, pagep, flags); + return write_begin_slow(mapping, pos, len, pagep); } /* @@ -890,12 +889,14 @@ out_unlock: return err; } -static int ubifs_readpage(struct file *file, struct page *page) +static int ubifs_read_folio(struct file *file, struct folio *folio) { + struct page *page = &folio->page; + if (ubifs_bulk_read(page)) return 0; do_readpage(page); - unlock_page(page); + folio_unlock(folio); return 0; } @@ -1483,22 +1484,22 @@ static int ubifs_migrate_page(struct address_space *mapping, } #endif -static int ubifs_releasepage(struct page *page, gfp_t unused_gfp_flags) +static bool ubifs_release_folio(struct folio *folio, gfp_t unused_gfp_flags) { - struct inode *inode = page->mapping->host; + struct inode *inode = folio->mapping->host; struct ubifs_info *c = inode->i_sb->s_fs_info; /* * An attempt to release a dirty page without budgeting for it - should * not happen. */ - if (PageWriteback(page)) - return 0; - ubifs_assert(c, PagePrivate(page)); + if (folio_test_writeback(folio)) + return false; + ubifs_assert(c, folio_test_private(folio)); ubifs_assert(c, 0); - detach_page_private(page); - ClearPageChecked(page); - return 1; + folio_detach_private(folio); + folio_clear_checked(folio); + return true; } /* @@ -1642,7 +1643,7 @@ static int ubifs_symlink_getattr(struct user_namespace *mnt_userns, } const struct address_space_operations ubifs_file_address_operations = { - .readpage = ubifs_readpage, + .read_folio = ubifs_read_folio, .writepage = ubifs_writepage, .write_begin = ubifs_write_begin, .write_end = ubifs_write_end, @@ -1651,7 +1652,7 @@ const struct address_space_operations ubifs_file_address_operations = { #ifdef CONFIG_MIGRATION .migratepage = ubifs_migrate_page, #endif - .releasepage = ubifs_releasepage, + .release_folio = ubifs_release_folio, }; const struct inode_operations ubifs_file_inode_operations = { diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index bad67455215f..0978d01b0ea4 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -2191,7 +2191,7 @@ static int ubifs_fill_super(struct super_block *sb, void *data, int silent) /* * UBIFS provides 'backing_dev_info' in order to disable read-ahead. For - * UBIFS, I/O is not deferred, it is done immediately in readpage, + * UBIFS, I/O is not deferred, it is done immediately in read_folio, * which means the user would have to wait not just for their own I/O * but the read-ahead I/O as well i.e. completely pointless. * diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h index 008fa46ef61e..7d6d2f152e03 100644 --- a/fs/ubifs/ubifs.h +++ b/fs/ubifs/ubifs.h @@ -132,7 +132,7 @@ #define WORST_COMPR_FACTOR 2 #ifdef CONFIG_FS_ENCRYPTION -#define UBIFS_CIPHER_BLOCK_SIZE FS_CRYPTO_BLOCK_SIZE +#define UBIFS_CIPHER_BLOCK_SIZE FSCRYPT_CONTENTS_ALIGNMENT #else #define UBIFS_CIPHER_BLOCK_SIZE 0 #endif diff --git a/fs/udf/file.c b/fs/udf/file.c index 0f6bf2504437..09aef77269fe 100644 --- a/fs/udf/file.c +++ b/fs/udf/file.c @@ -57,11 +57,11 @@ static void __udf_adinicb_readpage(struct page *page) kunmap_atomic(kaddr); } -static int udf_adinicb_readpage(struct file *file, struct page *page) +static int udf_adinicb_read_folio(struct file *file, struct folio *folio) { - BUG_ON(!PageLocked(page)); - __udf_adinicb_readpage(page); - unlock_page(page); + BUG_ON(!folio_test_locked(folio)); + __udf_adinicb_readpage(&folio->page); + folio_unlock(folio); return 0; } @@ -87,14 +87,14 @@ static int udf_adinicb_writepage(struct page *page, static int udf_adinicb_write_begin(struct file *file, struct address_space *mapping, loff_t pos, - unsigned len, unsigned flags, struct page **pagep, + unsigned len, struct page **pagep, void **fsdata) { struct page *page; if (WARN_ON_ONCE(pos >= PAGE_SIZE)) return -EIO; - page = grab_cache_page_write_begin(mapping, 0, flags); + page = grab_cache_page_write_begin(mapping, 0); if (!page) return -ENOMEM; *pagep = page; @@ -127,7 +127,7 @@ static int udf_adinicb_write_end(struct file *file, struct address_space *mappin const struct address_space_operations udf_adinicb_aops = { .dirty_folio = block_dirty_folio, .invalidate_folio = block_invalidate_folio, - .readpage = udf_adinicb_readpage, + .read_folio = udf_adinicb_read_folio, .writepage = udf_adinicb_writepage, .write_begin = udf_adinicb_write_begin, .write_end = udf_adinicb_write_end, diff --git a/fs/udf/inode.c b/fs/udf/inode.c index ca4fa710e562..edc88716751a 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -193,9 +193,9 @@ static int udf_writepages(struct address_space *mapping, return mpage_writepages(mapping, wbc, udf_get_block); } -static int udf_readpage(struct file *file, struct page *page) +static int udf_read_folio(struct file *file, struct folio *folio) { - return mpage_readpage(page, udf_get_block); + return mpage_read_folio(folio, udf_get_block); } static void udf_readahead(struct readahead_control *rac) @@ -204,12 +204,12 @@ static void udf_readahead(struct readahead_control *rac) } static int udf_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, + loff_t pos, unsigned len, struct page **pagep, void **fsdata) { int ret; - ret = block_write_begin(mapping, pos, len, flags, pagep, udf_get_block); + ret = block_write_begin(mapping, pos, len, pagep, udf_get_block); if (unlikely(ret)) udf_write_failed(mapping, pos + len); return ret; @@ -237,7 +237,7 @@ static sector_t udf_bmap(struct address_space *mapping, sector_t block) const struct address_space_operations udf_aops = { .dirty_folio = block_dirty_folio, .invalidate_folio = block_invalidate_folio, - .readpage = udf_readpage, + .read_folio = udf_read_folio, .readahead = udf_readahead, .writepage = udf_writepage, .writepages = udf_writepages, diff --git a/fs/udf/namei.c b/fs/udf/namei.c index 0ed4861b038f..b3d5f97f16cd 100644 --- a/fs/udf/namei.c +++ b/fs/udf/namei.c @@ -75,11 +75,11 @@ int udf_write_fi(struct inode *inode, struct fileIdentDesc *cfi, if (fileident) { if (adinicb || (offset + lfi < 0)) { - memcpy(udf_get_fi_ident(sfi), fileident, lfi); + memcpy(sfi->impUse + liu, fileident, lfi); } else if (offset >= 0) { memcpy(fibh->ebh->b_data + offset, fileident, lfi); } else { - memcpy(udf_get_fi_ident(sfi), fileident, -offset); + memcpy(sfi->impUse + liu, fileident, -offset); memcpy(fibh->ebh->b_data, fileident - offset, lfi + offset); } @@ -88,11 +88,11 @@ int udf_write_fi(struct inode *inode, struct fileIdentDesc *cfi, offset += lfi; if (adinicb || (offset + padlen < 0)) { - memset(udf_get_fi_ident(sfi) + lfi, 0x00, padlen); + memset(sfi->impUse + liu + lfi, 0x00, padlen); } else if (offset >= 0) { memset(fibh->ebh->b_data + offset, 0x00, padlen); } else { - memset(udf_get_fi_ident(sfi) + lfi, 0x00, -offset); + memset(sfi->impUse + liu + lfi, 0x00, -offset); memset(fibh->ebh->b_data, 0x00, padlen + offset); } diff --git a/fs/udf/symlink.c b/fs/udf/symlink.c index 9b223421a3c5..f3642f9c23f8 100644 --- a/fs/udf/symlink.c +++ b/fs/udf/symlink.c @@ -101,8 +101,9 @@ static int udf_pc_to_char(struct super_block *sb, unsigned char *from, return 0; } -static int udf_symlink_filler(struct file *file, struct page *page) +static int udf_symlink_filler(struct file *file, struct folio *folio) { + struct page *page = &folio->page; struct inode *inode = page->mapping->host; struct buffer_head *bh = NULL; unsigned char *symlink; @@ -183,7 +184,7 @@ static int udf_symlink_getattr(struct user_namespace *mnt_userns, * symlinks can't do much... */ const struct address_space_operations udf_symlink_aops = { - .readpage = udf_symlink_filler, + .read_folio = udf_symlink_filler, }; const struct inode_operations udf_symlink_inode_operations = { diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c index d0dda01620f0..a873de7dec1c 100644 --- a/fs/ufs/inode.c +++ b/fs/ufs/inode.c @@ -390,7 +390,7 @@ out: /** * ufs_getfrag_block() - `get_block_t' function, interface between UFS and - * readpage, writepage and so on + * read_folio, writepage and so on */ static int ufs_getfrag_block(struct inode *inode, sector_t fragment, struct buffer_head *bh_result, int create) @@ -472,9 +472,9 @@ static int ufs_writepage(struct page *page, struct writeback_control *wbc) return block_write_full_page(page,ufs_getfrag_block,wbc); } -static int ufs_readpage(struct file *file, struct page *page) +static int ufs_read_folio(struct file *file, struct folio *folio) { - return block_read_full_page(page,ufs_getfrag_block); + return block_read_full_folio(folio, ufs_getfrag_block); } int ufs_prepare_chunk(struct page *page, loff_t pos, unsigned len) @@ -495,13 +495,12 @@ static void ufs_write_failed(struct address_space *mapping, loff_t to) } static int ufs_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, + loff_t pos, unsigned len, struct page **pagep, void **fsdata) { int ret; - ret = block_write_begin(mapping, pos, len, flags, pagep, - ufs_getfrag_block); + ret = block_write_begin(mapping, pos, len, pagep, ufs_getfrag_block); if (unlikely(ret)) ufs_write_failed(mapping, pos + len); @@ -528,7 +527,7 @@ static sector_t ufs_bmap(struct address_space *mapping, sector_t block) const struct address_space_operations ufs_aops = { .dirty_folio = block_dirty_folio, .invalidate_folio = block_invalidate_folio, - .readpage = ufs_readpage, + .read_folio = ufs_read_folio, .writepage = ufs_writepage, .write_begin = ufs_write_begin, .write_end = ufs_write_end, diff --git a/fs/vboxsf/file.c b/fs/vboxsf/file.c index d74e0d336995..572aa1c43b37 100644 --- a/fs/vboxsf/file.c +++ b/fs/vboxsf/file.c @@ -225,8 +225,9 @@ const struct inode_operations vboxsf_reg_iops = { .setattr = vboxsf_setattr }; -static int vboxsf_readpage(struct file *file, struct page *page) +static int vboxsf_read_folio(struct file *file, struct folio *folio) { + struct page *page = &folio->page; struct vboxsf_handle *sf_handle = file->private_data; loff_t off = page_offset(page); u32 nread = PAGE_SIZE; @@ -352,7 +353,7 @@ out: * page and it does not call SetPageUptodate for partial writes. */ const struct address_space_operations vboxsf_reg_aops = { - .readpage = vboxsf_readpage, + .read_folio = vboxsf_read_folio, .writepage = vboxsf_writepage, .dirty_folio = filemap_dirty_folio, .write_begin = simple_write_begin, diff --git a/fs/verity/Kconfig b/fs/verity/Kconfig index 24d1b54de807..54598cd80145 100644 --- a/fs/verity/Kconfig +++ b/fs/verity/Kconfig @@ -3,6 +3,7 @@ config FS_VERITY bool "FS Verity (read-only file-based authenticity protection)" select CRYPTO + select CRYPTO_HASH_INFO # SHA-256 is implied as it's intended to be the default hash algorithm. # To avoid bloat, other wanted algorithms must be selected explicitly. # Note that CRYPTO_SHA256 denotes the generic C implementation, but diff --git a/fs/verity/enable.c b/fs/verity/enable.c index 60a4372aa4d7..df6b499bf6a1 100644 --- a/fs/verity/enable.c +++ b/fs/verity/enable.c @@ -18,27 +18,26 @@ * Read a file data page for Merkle tree construction. Do aggressive readahead, * since we're sequentially reading the entire file. */ -static struct page *read_file_data_page(struct file *filp, pgoff_t index, +static struct page *read_file_data_page(struct file *file, pgoff_t index, struct file_ra_state *ra, unsigned long remaining_pages) { - struct page *page; + DEFINE_READAHEAD(ractl, file, ra, file->f_mapping, index); + struct folio *folio; - page = find_get_page_flags(filp->f_mapping, index, FGP_ACCESSED); - if (!page || !PageUptodate(page)) { - if (page) - put_page(page); + folio = __filemap_get_folio(ractl.mapping, index, FGP_ACCESSED, 0); + if (!folio || !folio_test_uptodate(folio)) { + if (folio) + folio_put(folio); else - page_cache_sync_readahead(filp->f_mapping, ra, filp, - index, remaining_pages); - page = read_mapping_page(filp->f_mapping, index, NULL); - if (IS_ERR(page)) - return page; + page_cache_sync_ra(&ractl, remaining_pages); + folio = read_cache_folio(ractl.mapping, index, NULL, file); + if (IS_ERR(folio)) + return &folio->page; } - if (PageReadahead(page)) - page_cache_async_readahead(filp->f_mapping, ra, filp, page, - index, remaining_pages); - return page; + if (folio_test_readahead(folio)) + page_cache_async_ra(&ractl, folio, remaining_pages); + return folio_file_page(folio, index); } static int build_merkle_tree_level(struct file *filp, unsigned int level, @@ -202,7 +201,7 @@ static int enable_verity(struct file *filp, const struct fsverity_operations *vops = inode->i_sb->s_vop; struct merkle_tree_params params = { }; struct fsverity_descriptor *desc; - size_t desc_size = sizeof(*desc) + arg->sig_size; + size_t desc_size = struct_size(desc, signature, arg->sig_size); struct fsverity_info *vi; int err; @@ -281,7 +280,7 @@ static int enable_verity(struct file *filp, * from disk. This is simpler, and it serves as an extra check that the * metadata we're writing is valid before actually enabling verity. */ - vi = fsverity_create_info(inode, desc, desc_size); + vi = fsverity_create_info(inode, desc); if (IS_ERR(vi)) { err = PTR_ERR(vi); goto rollback; diff --git a/fs/verity/fsverity_private.h b/fs/verity/fsverity_private.h index a7920434bae5..629785c95007 100644 --- a/fs/verity/fsverity_private.h +++ b/fs/verity/fsverity_private.h @@ -14,7 +14,6 @@ #define pr_fmt(fmt) "fs-verity: " fmt -#include <crypto/sha2.h> #include <linux/fsverity.h> #include <linux/mempool.h> @@ -26,12 +25,6 @@ struct ahash_request; */ #define FS_VERITY_MAX_LEVELS 8 -/* - * Largest digest size among all hash algorithms supported by fs-verity. - * Currently assumed to be <= size of fsverity_descriptor::root_hash. - */ -#define FS_VERITY_MAX_DIGEST_SIZE SHA512_DIGEST_SIZE - /* A hash algorithm supported by fs-verity */ struct fsverity_hash_alg { struct crypto_ahash *tfm; /* hash tfm, allocated on demand */ @@ -122,16 +115,14 @@ int fsverity_init_merkle_tree_params(struct merkle_tree_params *params, const u8 *salt, size_t salt_size); struct fsverity_info *fsverity_create_info(const struct inode *inode, - struct fsverity_descriptor *desc, - size_t desc_size); + struct fsverity_descriptor *desc); void fsverity_set_info(struct inode *inode, struct fsverity_info *vi); void fsverity_free_info(struct fsverity_info *vi); int fsverity_get_descriptor(struct inode *inode, - struct fsverity_descriptor **desc_ret, - size_t *desc_size_ret); + struct fsverity_descriptor **desc_ret); int __init fsverity_init_info_cache(void); void __init fsverity_exit_info_cache(void); diff --git a/fs/verity/measure.c b/fs/verity/measure.c index f0d7b30c62db..e99c00350c28 100644 --- a/fs/verity/measure.c +++ b/fs/verity/measure.c @@ -57,3 +57,46 @@ int fsverity_ioctl_measure(struct file *filp, void __user *_uarg) return 0; } EXPORT_SYMBOL_GPL(fsverity_ioctl_measure); + +/** + * fsverity_get_digest() - get a verity file's digest + * @inode: inode to get digest of + * @digest: (out) pointer to the digest + * @alg: (out) pointer to the hash algorithm enumeration + * + * Return the file hash algorithm and digest of an fsverity protected file. + * Assumption: before calling fsverity_get_digest(), the file must have been + * opened. + * + * Return: 0 on success, -errno on failure + */ +int fsverity_get_digest(struct inode *inode, + u8 digest[FS_VERITY_MAX_DIGEST_SIZE], + enum hash_algo *alg) +{ + const struct fsverity_info *vi; + const struct fsverity_hash_alg *hash_alg; + int i; + + vi = fsverity_get_info(inode); + if (!vi) + return -ENODATA; /* not a verity file */ + + hash_alg = vi->tree_params.hash_alg; + memset(digest, 0, FS_VERITY_MAX_DIGEST_SIZE); + + /* convert the verity hash algorithm name to a hash_algo_name enum */ + i = match_string(hash_algo_name, HASH_ALGO__LAST, hash_alg->name); + if (i < 0) + return -EINVAL; + *alg = i; + + if (WARN_ON_ONCE(hash_alg->digest_size != hash_digest_size[*alg])) + return -EINVAL; + memcpy(digest, vi->file_digest, hash_alg->digest_size); + + pr_debug("file digest %s:%*phN\n", hash_algo_name[*alg], + hash_digest_size[*alg], digest); + + return 0; +} diff --git a/fs/verity/open.c b/fs/verity/open.c index 92df87f5fa38..81ff94442f7b 100644 --- a/fs/verity/open.c +++ b/fs/verity/open.c @@ -147,8 +147,7 @@ static int compute_file_digest(struct fsverity_hash_alg *hash_alg, * fsverity_descriptor must have already undergone basic validation. */ struct fsverity_info *fsverity_create_info(const struct inode *inode, - struct fsverity_descriptor *desc, - size_t desc_size) + struct fsverity_descriptor *desc) { struct fsverity_info *vi; int err; @@ -264,8 +263,7 @@ static bool validate_fsverity_descriptor(struct inode *inode, * the filesystem, and do basic validation of it. */ int fsverity_get_descriptor(struct inode *inode, - struct fsverity_descriptor **desc_ret, - size_t *desc_size_ret) + struct fsverity_descriptor **desc_ret) { int res; struct fsverity_descriptor *desc; @@ -297,7 +295,6 @@ int fsverity_get_descriptor(struct inode *inode, } *desc_ret = desc; - *desc_size_ret = res; return 0; } @@ -306,17 +303,16 @@ static int ensure_verity_info(struct inode *inode) { struct fsverity_info *vi = fsverity_get_info(inode); struct fsverity_descriptor *desc; - size_t desc_size; int err; if (vi) return 0; - err = fsverity_get_descriptor(inode, &desc, &desc_size); + err = fsverity_get_descriptor(inode, &desc); if (err) return err; - vi = fsverity_create_info(inode, desc, desc_size); + vi = fsverity_create_info(inode, desc); if (IS_ERR(vi)) { err = PTR_ERR(vi); goto out_free_desc; diff --git a/fs/verity/read_metadata.c b/fs/verity/read_metadata.c index 7e2d0c7bdf0d..6ee849dc7bc1 100644 --- a/fs/verity/read_metadata.c +++ b/fs/verity/read_metadata.c @@ -101,7 +101,7 @@ static int fsverity_read_descriptor(struct inode *inode, size_t desc_size; int res; - res = fsverity_get_descriptor(inode, &desc, &desc_size); + res = fsverity_get_descriptor(inode, &desc); if (res) return res; @@ -119,10 +119,9 @@ static int fsverity_read_signature(struct inode *inode, void __user *buf, u64 offset, int length) { struct fsverity_descriptor *desc; - size_t desc_size; int res; - res = fsverity_get_descriptor(inode, &desc, &desc_size); + res = fsverity_get_descriptor(inode, &desc); if (res) return res; diff --git a/fs/xattr.c b/fs/xattr.c index 5c8c5175b385..e8dd03e4561e 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -25,6 +25,8 @@ #include <linux/uaccess.h> +#include "internal.h" + static const char * strcmp_prefix(const char *a, const char *a_prefix) { @@ -539,43 +541,76 @@ EXPORT_SYMBOL_GPL(vfs_removexattr); /* * Extended attribute SET operations */ -static long -setxattr(struct user_namespace *mnt_userns, struct dentry *d, - const char __user *name, const void __user *value, size_t size, - int flags) + +int setxattr_copy(const char __user *name, struct xattr_ctx *ctx) { int error; - void *kvalue = NULL; - char kname[XATTR_NAME_MAX + 1]; - if (flags & ~(XATTR_CREATE|XATTR_REPLACE)) + if (ctx->flags & ~(XATTR_CREATE|XATTR_REPLACE)) return -EINVAL; - error = strncpy_from_user(kname, name, sizeof(kname)); - if (error == 0 || error == sizeof(kname)) - error = -ERANGE; + error = strncpy_from_user(ctx->kname->name, name, + sizeof(ctx->kname->name)); + if (error == 0 || error == sizeof(ctx->kname->name)) + return -ERANGE; if (error < 0) return error; - if (size) { - if (size > XATTR_SIZE_MAX) + error = 0; + if (ctx->size) { + if (ctx->size > XATTR_SIZE_MAX) return -E2BIG; - kvalue = kvmalloc(size, GFP_KERNEL); - if (!kvalue) - return -ENOMEM; - if (copy_from_user(kvalue, value, size)) { - error = -EFAULT; - goto out; + + ctx->kvalue = vmemdup_user(ctx->cvalue, ctx->size); + if (IS_ERR(ctx->kvalue)) { + error = PTR_ERR(ctx->kvalue); + ctx->kvalue = NULL; } - if ((strcmp(kname, XATTR_NAME_POSIX_ACL_ACCESS) == 0) || - (strcmp(kname, XATTR_NAME_POSIX_ACL_DEFAULT) == 0)) - posix_acl_fix_xattr_from_user(mnt_userns, kvalue, size); } - error = vfs_setxattr(mnt_userns, d, kname, kvalue, size, flags); -out: - kvfree(kvalue); + return error; +} + +static void setxattr_convert(struct user_namespace *mnt_userns, + struct dentry *d, struct xattr_ctx *ctx) +{ + if (ctx->size && + ((strcmp(ctx->kname->name, XATTR_NAME_POSIX_ACL_ACCESS) == 0) || + (strcmp(ctx->kname->name, XATTR_NAME_POSIX_ACL_DEFAULT) == 0))) + posix_acl_fix_xattr_from_user(mnt_userns, d_inode(d), + ctx->kvalue, ctx->size); +} + +int do_setxattr(struct user_namespace *mnt_userns, struct dentry *dentry, + struct xattr_ctx *ctx) +{ + setxattr_convert(mnt_userns, dentry, ctx); + return vfs_setxattr(mnt_userns, dentry, ctx->kname->name, + ctx->kvalue, ctx->size, ctx->flags); +} + +static long +setxattr(struct user_namespace *mnt_userns, struct dentry *d, + const char __user *name, const void __user *value, size_t size, + int flags) +{ + struct xattr_name kname; + struct xattr_ctx ctx = { + .cvalue = value, + .kvalue = NULL, + .size = size, + .kname = &kname, + .flags = flags, + }; + int error; + error = setxattr_copy(name, &ctx); + if (error) + return error; + + error = do_setxattr(mnt_userns, d, &ctx); + + kvfree(ctx.kvalue); return error; } @@ -641,43 +676,61 @@ SYSCALL_DEFINE5(fsetxattr, int, fd, const char __user *, name, /* * Extended attribute GET operations */ -static ssize_t -getxattr(struct user_namespace *mnt_userns, struct dentry *d, - const char __user *name, void __user *value, size_t size) +ssize_t +do_getxattr(struct user_namespace *mnt_userns, struct dentry *d, + struct xattr_ctx *ctx) { ssize_t error; - void *kvalue = NULL; - char kname[XATTR_NAME_MAX + 1]; - - error = strncpy_from_user(kname, name, sizeof(kname)); - if (error == 0 || error == sizeof(kname)) - error = -ERANGE; - if (error < 0) - return error; + char *kname = ctx->kname->name; - if (size) { - if (size > XATTR_SIZE_MAX) - size = XATTR_SIZE_MAX; - kvalue = kvzalloc(size, GFP_KERNEL); - if (!kvalue) + if (ctx->size) { + if (ctx->size > XATTR_SIZE_MAX) + ctx->size = XATTR_SIZE_MAX; + ctx->kvalue = kvzalloc(ctx->size, GFP_KERNEL); + if (!ctx->kvalue) return -ENOMEM; } - error = vfs_getxattr(mnt_userns, d, kname, kvalue, size); + error = vfs_getxattr(mnt_userns, d, kname, ctx->kvalue, ctx->size); if (error > 0) { if ((strcmp(kname, XATTR_NAME_POSIX_ACL_ACCESS) == 0) || (strcmp(kname, XATTR_NAME_POSIX_ACL_DEFAULT) == 0)) - posix_acl_fix_xattr_to_user(mnt_userns, kvalue, error); - if (size && copy_to_user(value, kvalue, error)) + posix_acl_fix_xattr_to_user(mnt_userns, d_inode(d), + ctx->kvalue, error); + if (ctx->size && copy_to_user(ctx->value, ctx->kvalue, error)) error = -EFAULT; - } else if (error == -ERANGE && size >= XATTR_SIZE_MAX) { + } else if (error == -ERANGE && ctx->size >= XATTR_SIZE_MAX) { /* The file system tried to returned a value bigger than XATTR_SIZE_MAX bytes. Not possible. */ error = -E2BIG; } - kvfree(kvalue); + return error; +} + +static ssize_t +getxattr(struct user_namespace *mnt_userns, struct dentry *d, + const char __user *name, void __user *value, size_t size) +{ + ssize_t error; + struct xattr_name kname; + struct xattr_ctx ctx = { + .value = value, + .kvalue = NULL, + .size = size, + .kname = &kname, + .flags = 0, + }; + + error = strncpy_from_user(kname.name, name, sizeof(kname.name)); + if (error == 0 || error == sizeof(kname.name)) + error = -ERANGE; + if (error < 0) + return error; + + error = do_getxattr(mnt_userns, d, &ctx); + kvfree(ctx.kvalue); return error; } diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 90b7f4d127de..8ec38b25187b 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -464,7 +464,7 @@ xfs_discard_folio( int error; if (xfs_is_shutdown(mp)) - goto out_invalidate; + return; xfs_alert_ratelimited(mp, "page discard on page "PTR_FMT", inode 0x%llx, pos %llu.", @@ -474,8 +474,6 @@ xfs_discard_folio( i_blocks_per_folio(inode, folio) - pageoff_fsb); if (error && !xfs_is_shutdown(mp)) xfs_alert(mp, "page discard unable to remove delalloc mapping."); -out_invalidate: - iomap_invalidate_folio(folio, offset, folio_size(folio) - offset); } static const struct iomap_writeback_ops xfs_writeback_ops = { @@ -538,11 +536,11 @@ xfs_vm_bmap( } STATIC int -xfs_vm_readpage( +xfs_vm_read_folio( struct file *unused, - struct page *page) + struct folio *folio) { - return iomap_readpage(page, &xfs_read_iomap_ops); + return iomap_read_folio(folio, &xfs_read_iomap_ops); } STATIC void @@ -564,11 +562,11 @@ xfs_iomap_swapfile_activate( } const struct address_space_operations xfs_address_space_operations = { - .readpage = xfs_vm_readpage, + .read_folio = xfs_vm_read_folio, .readahead = xfs_vm_readahead, .writepages = xfs_vm_writepages, .dirty_folio = filemap_dirty_folio, - .releasepage = iomap_releasepage, + .release_folio = iomap_release_folio, .invalidate_folio = iomap_invalidate_folio, .bmap = xfs_vm_bmap, .direct_IO = noop_direct_IO, diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index e1afb9e503e1..bf4e60871068 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -406,7 +406,7 @@ xfs_buf_alloc_pages( STATIC int _xfs_buf_map_pages( struct xfs_buf *bp, - uint flags) + xfs_buf_flags_t flags) { ASSERT(bp->b_flags & _XBF_PAGES); if (bp->b_page_count == 1) { @@ -868,7 +868,7 @@ xfs_buf_read_uncached( struct xfs_buftarg *target, xfs_daddr_t daddr, size_t numblks, - int flags, + xfs_buf_flags_t flags, struct xfs_buf **bpp, const struct xfs_buf_ops *ops) { @@ -903,7 +903,7 @@ int xfs_buf_get_uncached( struct xfs_buftarg *target, size_t numblks, - int flags, + xfs_buf_flags_t flags, struct xfs_buf **bpp) { int error; diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h index edcb6254fa6a..1ee3056ff9cf 100644 --- a/fs/xfs/xfs_buf.h +++ b/fs/xfs/xfs_buf.h @@ -22,28 +22,28 @@ struct xfs_buf; #define XFS_BUF_DADDR_NULL ((xfs_daddr_t) (-1LL)) -#define XBF_READ (1 << 0) /* buffer intended for reading from device */ -#define XBF_WRITE (1 << 1) /* buffer intended for writing to device */ -#define XBF_READ_AHEAD (1 << 2) /* asynchronous read-ahead */ -#define XBF_NO_IOACCT (1 << 3) /* bypass I/O accounting (non-LRU bufs) */ -#define XBF_ASYNC (1 << 4) /* initiator will not wait for completion */ -#define XBF_DONE (1 << 5) /* all pages in the buffer uptodate */ -#define XBF_STALE (1 << 6) /* buffer has been staled, do not find it */ -#define XBF_WRITE_FAIL (1 << 7) /* async writes have failed on this buffer */ +#define XBF_READ (1u << 0) /* buffer intended for reading from device */ +#define XBF_WRITE (1u << 1) /* buffer intended for writing to device */ +#define XBF_READ_AHEAD (1u << 2) /* asynchronous read-ahead */ +#define XBF_NO_IOACCT (1u << 3) /* bypass I/O accounting (non-LRU bufs) */ +#define XBF_ASYNC (1u << 4) /* initiator will not wait for completion */ +#define XBF_DONE (1u << 5) /* all pages in the buffer uptodate */ +#define XBF_STALE (1u << 6) /* buffer has been staled, do not find it */ +#define XBF_WRITE_FAIL (1u << 7) /* async writes have failed on this buffer */ /* buffer type flags for write callbacks */ -#define _XBF_INODES (1 << 16)/* inode buffer */ -#define _XBF_DQUOTS (1 << 17)/* dquot buffer */ -#define _XBF_LOGRECOVERY (1 << 18)/* log recovery buffer */ +#define _XBF_INODES (1u << 16)/* inode buffer */ +#define _XBF_DQUOTS (1u << 17)/* dquot buffer */ +#define _XBF_LOGRECOVERY (1u << 18)/* log recovery buffer */ /* flags used only internally */ -#define _XBF_PAGES (1 << 20)/* backed by refcounted pages */ -#define _XBF_KMEM (1 << 21)/* backed by heap memory */ -#define _XBF_DELWRI_Q (1 << 22)/* buffer on a delwri queue */ +#define _XBF_PAGES (1u << 20)/* backed by refcounted pages */ +#define _XBF_KMEM (1u << 21)/* backed by heap memory */ +#define _XBF_DELWRI_Q (1u << 22)/* buffer on a delwri queue */ /* flags used only as arguments to access routines */ -#define XBF_TRYLOCK (1 << 30)/* lock requested, but do not wait */ -#define XBF_UNMAPPED (1 << 31)/* do not map the buffer */ +#define XBF_TRYLOCK (1u << 30)/* lock requested, but do not wait */ +#define XBF_UNMAPPED (1u << 31)/* do not map the buffer */ typedef unsigned int xfs_buf_flags_t; @@ -58,7 +58,7 @@ typedef unsigned int xfs_buf_flags_t; { XBF_WRITE_FAIL, "WRITE_FAIL" }, \ { _XBF_INODES, "INODES" }, \ { _XBF_DQUOTS, "DQUOTS" }, \ - { _XBF_LOGRECOVERY, "LOG_RECOVERY" }, \ + { _XBF_LOGRECOVERY, "LOG_RECOVERY" }, \ { _XBF_PAGES, "PAGES" }, \ { _XBF_KMEM, "KMEM" }, \ { _XBF_DELWRI_Q, "DELWRI_Q" }, \ @@ -247,11 +247,11 @@ xfs_buf_readahead( return xfs_buf_readahead_map(target, &map, 1, ops); } -int xfs_buf_get_uncached(struct xfs_buftarg *target, size_t numblks, int flags, - struct xfs_buf **bpp); +int xfs_buf_get_uncached(struct xfs_buftarg *target, size_t numblks, + xfs_buf_flags_t flags, struct xfs_buf **bpp); int xfs_buf_read_uncached(struct xfs_buftarg *target, xfs_daddr_t daddr, - size_t numblks, int flags, struct xfs_buf **bpp, - const struct xfs_buf_ops *ops); + size_t numblks, xfs_buf_flags_t flags, struct xfs_buf **bpp, + const struct xfs_buf_ops *ops); int _xfs_buf_read(struct xfs_buf *bp, xfs_buf_flags_t flags); void xfs_buf_hold(struct xfs_buf *bp); diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c index 0191de8ce9ce..c6fe3f6ebb6b 100644 --- a/fs/xfs/xfs_discard.c +++ b/fs/xfs/xfs_discard.c @@ -114,7 +114,7 @@ xfs_trim_extents( } trace_xfs_discard_extent(mp, agno, fbno, flen); - error = blkdev_issue_discard(bdev, dbno, dlen, GFP_NOFS, 0); + error = blkdev_issue_discard(bdev, dbno, dlen, GFP_NOFS); if (error) goto out_del_cursor; *blocks_trimmed += flen; @@ -152,8 +152,8 @@ xfs_ioc_trim( struct xfs_mount *mp, struct fstrim_range __user *urange) { - struct request_queue *q = bdev_get_queue(mp->m_ddev_targp->bt_bdev); - unsigned int granularity = q->limits.discard_granularity; + unsigned int granularity = + bdev_discard_granularity(mp->m_ddev_targp->bt_bdev); struct fstrim_range range; xfs_daddr_t start, end, minlen; xfs_agnumber_t start_agno, end_agno, agno; @@ -162,7 +162,7 @@ xfs_ioc_trim( if (!capable(CAP_SYS_ADMIN)) return -EPERM; - if (!blk_queue_discard(q)) + if (!bdev_max_discard_sectors(mp->m_ddev_targp->bt_bdev)) return -EOPNOTSUPP; /* diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 5bddb1e9e0b3..85c412107a10 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -225,7 +225,7 @@ xfs_file_dio_read( ret = xfs_ilock_iocb(iocb, XFS_IOLOCK_SHARED); if (ret) return ret; - ret = iomap_dio_rw(iocb, to, &xfs_read_iomap_ops, NULL, 0, 0); + ret = iomap_dio_rw(iocb, to, &xfs_read_iomap_ops, NULL, 0, NULL, 0); xfs_iunlock(ip, XFS_IOLOCK_SHARED); return ret; @@ -534,7 +534,7 @@ xfs_file_dio_write_aligned( } trace_xfs_file_direct_write(iocb, from); ret = iomap_dio_rw(iocb, from, &xfs_direct_write_iomap_ops, - &xfs_dio_write_ops, 0, 0); + &xfs_dio_write_ops, 0, NULL, 0); out_unlock: if (iolock) xfs_iunlock(ip, iolock); @@ -612,7 +612,7 @@ retry_exclusive: trace_xfs_file_direct_write(iocb, from); ret = iomap_dio_rw(iocb, from, &xfs_direct_write_iomap_ops, - &xfs_dio_write_ops, flags, 0); + &xfs_dio_write_ops, flags, NULL, 0); /* * Retry unaligned I/O with exclusive blocking semantics if the DIO diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 9de6205fe134..39ae53efb3ab 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -2594,14 +2594,13 @@ xfs_ifree_cluster( } /* - * This is called to return an inode to the inode free list. - * The inode should already be truncated to 0 length and have - * no pages associated with it. This routine also assumes that - * the inode is already a part of the transaction. + * This is called to return an inode to the inode free list. The inode should + * already be truncated to 0 length and have no pages associated with it. This + * routine also assumes that the inode is already a part of the transaction. * - * The on-disk copy of the inode will have been added to the list - * of unlinked inodes in the AGI. We need to remove the inode from - * that list atomically with respect to freeing it here. + * The on-disk copy of the inode will have been added to the list of unlinked + * inodes in the AGI. We need to remove the inode from that list atomically with + * respect to freeing it here. */ int xfs_ifree( @@ -2623,13 +2622,16 @@ xfs_ifree( pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino)); /* - * Pull the on-disk inode from the AGI unlinked list. + * Free the inode first so that we guarantee that the AGI lock is going + * to be taken before we remove the inode from the unlinked list. This + * makes the AGI lock -> unlinked list modification order the same as + * used in O_TMPFILE creation. */ - error = xfs_iunlink_remove(tp, pag, ip); + error = xfs_difree(tp, pag, ip->i_ino, &xic); if (error) - goto out; + return error; - error = xfs_difree(tp, pag, ip->i_ino, &xic); + error = xfs_iunlink_remove(tp, pag, ip); if (error) goto out; diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c index ba57323bfdce..c9f55e4f0957 100644 --- a/fs/xfs/xfs_log_cil.c +++ b/fs/xfs/xfs_log_cil.c @@ -605,7 +605,7 @@ xlog_discard_busy_extents( error = __blkdev_issue_discard(mp->m_ddev_targp->bt_bdev, XFS_AGB_TO_DADDR(mp, busyp->agno, busyp->bno), XFS_FSB_TO_BB(mp, busyp->length), - GFP_NOFS, 0, &bio); + GFP_NOFS, &bio); if (error && error != -EOPNOTSUPP) { xfs_info(mp, "discard failed for extent [0x%llx,%u], error %d", diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 54be9d64093e..a276b8111f63 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -1608,14 +1608,10 @@ xfs_fs_fill_super( goto out_filestream_unmount; } - if (xfs_has_discard(mp)) { - struct request_queue *q = bdev_get_queue(sb->s_bdev); - - if (!blk_queue_discard(q)) { - xfs_warn(mp, "mounting with \"discard\" option, but " - "the device does not support discard"); - mp->m_features &= ~XFS_FEAT_DISCARD; - } + if (xfs_has_discard(mp) && !bdev_max_discard_sectors(sb->s_bdev)) { + xfs_warn(mp, + "mounting with \"discard\" option, but the device does not support discard"); + mp->m_features &= ~XFS_FEAT_DISCARD; } if (xfs_has_reflink(mp)) { diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h index de177842b951..0c82673238f4 100644 --- a/fs/xfs/xfs_trans.h +++ b/fs/xfs/xfs_trans.h @@ -175,7 +175,7 @@ xfs_trans_get_buf( struct xfs_buftarg *target, xfs_daddr_t blkno, int numblks, - uint flags, + xfs_buf_flags_t flags, struct xfs_buf **bpp) { DEFINE_SINGLE_BUF_MAP(map, blkno, numblks); diff --git a/fs/zonefs/Makefile b/fs/zonefs/Makefile index 33c1a4f1132e..9fe54f5319f2 100644 --- a/fs/zonefs/Makefile +++ b/fs/zonefs/Makefile @@ -3,4 +3,4 @@ ccflags-y += -I$(src) obj-$(CONFIG_ZONEFS_FS) += zonefs.o -zonefs-y := super.o +zonefs-y := super.o sysfs.o diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c index 3614c7834007..bcb21aea990a 100644 --- a/fs/zonefs/super.c +++ b/fs/zonefs/super.c @@ -27,6 +27,39 @@ #define CREATE_TRACE_POINTS #include "trace.h" +/* + * Manage the active zone count. Called with zi->i_truncate_mutex held. + */ +static void zonefs_account_active(struct inode *inode) +{ + struct zonefs_sb_info *sbi = ZONEFS_SB(inode->i_sb); + struct zonefs_inode_info *zi = ZONEFS_I(inode); + + lockdep_assert_held(&zi->i_truncate_mutex); + + if (zi->i_ztype != ZONEFS_ZTYPE_SEQ) + return; + + /* + * If the zone is active, that is, if it is explicitly open or + * partially written, check if it was already accounted as active. + */ + if ((zi->i_flags & ZONEFS_ZONE_OPEN) || + (zi->i_wpoffset > 0 && zi->i_wpoffset < zi->i_max_size)) { + if (!(zi->i_flags & ZONEFS_ZONE_ACTIVE)) { + zi->i_flags |= ZONEFS_ZONE_ACTIVE; + atomic_inc(&sbi->s_active_seq_files); + } + return; + } + + /* The zone is not active. If it was, update the active count */ + if (zi->i_flags & ZONEFS_ZONE_ACTIVE) { + zi->i_flags &= ~ZONEFS_ZONE_ACTIVE; + atomic_dec(&sbi->s_active_seq_files); + } +} + static inline int zonefs_zone_mgmt(struct inode *inode, enum req_opf op) { @@ -35,6 +68,17 @@ static inline int zonefs_zone_mgmt(struct inode *inode, lockdep_assert_held(&zi->i_truncate_mutex); + /* + * With ZNS drives, closing an explicitly open zone that has not been + * written will change the zone state to "closed", that is, the zone + * will remain active. Since this can then cause failure of explicit + * open operation on other zones if the drive active zone resources + * are exceeded, make sure that the zone does not remain active by + * resetting it. + */ + if (op == REQ_OP_ZONE_CLOSE && !zi->i_wpoffset) + op = REQ_OP_ZONE_RESET; + trace_zonefs_zone_mgmt(inode, op); ret = blkdev_zone_mgmt(inode->i_sb->s_bdev, op, zi->i_zsector, zi->i_zone_size >> SECTOR_SHIFT, GFP_NOFS); @@ -57,8 +101,13 @@ static inline void zonefs_i_size_write(struct inode *inode, loff_t isize) * A full zone is no longer open/active and does not need * explicit closing. */ - if (isize >= zi->i_max_size) - zi->i_flags &= ~ZONEFS_ZONE_OPEN; + if (isize >= zi->i_max_size) { + struct zonefs_sb_info *sbi = ZONEFS_SB(inode->i_sb); + + if (zi->i_flags & ZONEFS_ZONE_ACTIVE) + atomic_dec(&sbi->s_active_seq_files); + zi->i_flags &= ~(ZONEFS_ZONE_OPEN | ZONEFS_ZONE_ACTIVE); + } } static int zonefs_iomap_begin(struct inode *inode, loff_t offset, loff_t length, @@ -113,9 +162,9 @@ static const struct iomap_ops zonefs_iomap_ops = { .iomap_begin = zonefs_iomap_begin, }; -static int zonefs_readpage(struct file *unused, struct page *page) +static int zonefs_read_folio(struct file *unused, struct folio *folio) { - return iomap_readpage(page, &zonefs_iomap_ops); + return iomap_read_folio(folio, &zonefs_iomap_ops); } static void zonefs_readahead(struct readahead_control *rac) @@ -181,12 +230,12 @@ static int zonefs_swap_activate(struct swap_info_struct *sis, } static const struct address_space_operations zonefs_file_aops = { - .readpage = zonefs_readpage, + .read_folio = zonefs_read_folio, .readahead = zonefs_readahead, .writepage = zonefs_writepage, .writepages = zonefs_writepages, .dirty_folio = filemap_dirty_folio, - .releasepage = iomap_releasepage, + .release_folio = iomap_release_folio, .invalidate_folio = iomap_invalidate_folio, .migratepage = iomap_migrate_page, .is_partially_uptodate = iomap_is_partially_uptodate, @@ -386,6 +435,7 @@ static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx, zonefs_update_stats(inode, data_size); zonefs_i_size_write(inode, data_size); zi->i_wpoffset = data_size; + zonefs_account_active(inode); return 0; } @@ -497,6 +547,7 @@ static int zonefs_file_truncate(struct inode *inode, loff_t isize) zonefs_update_stats(inode, isize); truncate_setsize(inode, isize); zi->i_wpoffset = isize; + zonefs_account_active(inode); unlock: mutex_unlock(&zi->i_truncate_mutex); @@ -678,13 +729,12 @@ static ssize_t zonefs_file_dio_append(struct kiocb *iocb, struct iov_iter *from) struct inode *inode = file_inode(iocb->ki_filp); struct zonefs_inode_info *zi = ZONEFS_I(inode); struct block_device *bdev = inode->i_sb->s_bdev; - unsigned int max; + unsigned int max = bdev_max_zone_append_sectors(bdev); struct bio *bio; ssize_t size; int nr_pages; ssize_t ret; - max = queue_max_zone_append_sectors(bdev_get_queue(bdev)); max = ALIGN_DOWN(max << SECTOR_SHIFT, inode->i_sb->s_blocksize); iov_iter_truncate(from, max); @@ -850,13 +900,20 @@ static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from) ret = zonefs_file_dio_append(iocb, from); else ret = iomap_dio_rw(iocb, from, &zonefs_iomap_ops, - &zonefs_write_dio_ops, 0, 0); + &zonefs_write_dio_ops, 0, NULL, 0); if (zi->i_ztype == ZONEFS_ZTYPE_SEQ && (ret > 0 || ret == -EIOCBQUEUED)) { if (ret > 0) count = ret; + + /* + * Update the zone write pointer offset assuming the write + * operation succeeded. If it did not, the error recovery path + * will correct it. Also do active seq file accounting. + */ mutex_lock(&zi->i_truncate_mutex); zi->i_wpoffset += count; + zonefs_account_active(inode); mutex_unlock(&zi->i_truncate_mutex); } @@ -985,7 +1042,7 @@ static ssize_t zonefs_file_read_iter(struct kiocb *iocb, struct iov_iter *to) } file_accessed(iocb->ki_filp); ret = iomap_dio_rw(iocb, to, &zonefs_iomap_ops, - &zonefs_read_dio_ops, 0, 0); + &zonefs_read_dio_ops, 0, NULL, 0); } else { ret = generic_file_read_iter(iocb, to); if (ret == -EIO) @@ -998,13 +1055,13 @@ inode_unlock: return ret; } -static inline bool zonefs_file_use_exp_open(struct inode *inode, struct file *file) +/* + * Write open accounting is done only for sequential files. + */ +static inline bool zonefs_seq_file_need_wro(struct inode *inode, + struct file *file) { struct zonefs_inode_info *zi = ZONEFS_I(inode); - struct zonefs_sb_info *sbi = ZONEFS_SB(inode->i_sb); - - if (!(sbi->s_mount_opts & ZONEFS_MNTOPT_EXPLICIT_OPEN)) - return false; if (zi->i_ztype != ZONEFS_ZTYPE_SEQ) return false; @@ -1015,28 +1072,34 @@ static inline bool zonefs_file_use_exp_open(struct inode *inode, struct file *fi return true; } -static int zonefs_open_zone(struct inode *inode) +static int zonefs_seq_file_write_open(struct inode *inode) { struct zonefs_inode_info *zi = ZONEFS_I(inode); - struct zonefs_sb_info *sbi = ZONEFS_SB(inode->i_sb); int ret = 0; mutex_lock(&zi->i_truncate_mutex); if (!zi->i_wr_refcnt) { - if (atomic_inc_return(&sbi->s_open_zones) > sbi->s_max_open_zones) { - atomic_dec(&sbi->s_open_zones); - ret = -EBUSY; - goto unlock; - } + struct zonefs_sb_info *sbi = ZONEFS_SB(inode->i_sb); + unsigned int wro = atomic_inc_return(&sbi->s_wro_seq_files); - if (i_size_read(inode) < zi->i_max_size) { - ret = zonefs_zone_mgmt(inode, REQ_OP_ZONE_OPEN); - if (ret) { - atomic_dec(&sbi->s_open_zones); + if (sbi->s_mount_opts & ZONEFS_MNTOPT_EXPLICIT_OPEN) { + + if (wro > sbi->s_max_wro_seq_files) { + atomic_dec(&sbi->s_wro_seq_files); + ret = -EBUSY; goto unlock; } - zi->i_flags |= ZONEFS_ZONE_OPEN; + + if (i_size_read(inode) < zi->i_max_size) { + ret = zonefs_zone_mgmt(inode, REQ_OP_ZONE_OPEN); + if (ret) { + atomic_dec(&sbi->s_wro_seq_files); + goto unlock; + } + zi->i_flags |= ZONEFS_ZONE_OPEN; + zonefs_account_active(inode); + } } } @@ -1056,30 +1119,31 @@ static int zonefs_file_open(struct inode *inode, struct file *file) if (ret) return ret; - if (zonefs_file_use_exp_open(inode, file)) - return zonefs_open_zone(inode); + if (zonefs_seq_file_need_wro(inode, file)) + return zonefs_seq_file_write_open(inode); return 0; } -static void zonefs_close_zone(struct inode *inode) +static void zonefs_seq_file_write_close(struct inode *inode) { struct zonefs_inode_info *zi = ZONEFS_I(inode); + struct super_block *sb = inode->i_sb; + struct zonefs_sb_info *sbi = ZONEFS_SB(sb); int ret = 0; mutex_lock(&zi->i_truncate_mutex); - zi->i_wr_refcnt--; - if (!zi->i_wr_refcnt) { - struct zonefs_sb_info *sbi = ZONEFS_SB(inode->i_sb); - struct super_block *sb = inode->i_sb; - /* - * If the file zone is full, it is not open anymore and we only - * need to decrement the open count. - */ - if (!(zi->i_flags & ZONEFS_ZONE_OPEN)) - goto dec; + zi->i_wr_refcnt--; + if (zi->i_wr_refcnt) + goto unlock; + /* + * The file zone may not be open anymore (e.g. the file was truncated to + * its maximum size or it was fully written). For this case, we only + * need to decrement the write open count. + */ + if (zi->i_flags & ZONEFS_ZONE_OPEN) { ret = zonefs_zone_mgmt(inode, REQ_OP_ZONE_CLOSE); if (ret) { __zonefs_io_error(inode, false); @@ -1091,14 +1155,23 @@ static void zonefs_close_zone(struct inode *inode) */ if (zi->i_flags & ZONEFS_ZONE_OPEN && !(sb->s_flags & SB_RDONLY)) { - zonefs_warn(sb, "closing zone failed, remounting filesystem read-only\n"); + zonefs_warn(sb, + "closing zone at %llu failed %d\n", + zi->i_zsector, ret); + zonefs_warn(sb, + "remounting filesystem read-only\n"); sb->s_flags |= SB_RDONLY; } + goto unlock; } + zi->i_flags &= ~ZONEFS_ZONE_OPEN; -dec: - atomic_dec(&sbi->s_open_zones); + zonefs_account_active(inode); } + + atomic_dec(&sbi->s_wro_seq_files); + +unlock: mutex_unlock(&zi->i_truncate_mutex); } @@ -1110,8 +1183,8 @@ static int zonefs_file_release(struct inode *inode, struct file *file) * the zone has gone offline or read-only). Make sure we don't fail the * close(2) for user-space. */ - if (zonefs_file_use_exp_open(inode, file)) - zonefs_close_zone(inode); + if (zonefs_seq_file_need_wro(inode, file)) + zonefs_seq_file_write_close(inode); return 0; } @@ -1142,6 +1215,7 @@ static struct inode *zonefs_alloc_inode(struct super_block *sb) inode_init_once(&zi->i_vnode); mutex_init(&zi->i_truncate_mutex); zi->i_wr_refcnt = 0; + zi->i_flags = 0; return &zi->i_vnode; } @@ -1293,12 +1367,13 @@ static void zonefs_init_dir_inode(struct inode *parent, struct inode *inode, inc_nlink(parent); } -static void zonefs_init_file_inode(struct inode *inode, struct blk_zone *zone, - enum zonefs_ztype type) +static int zonefs_init_file_inode(struct inode *inode, struct blk_zone *zone, + enum zonefs_ztype type) { struct super_block *sb = inode->i_sb; struct zonefs_sb_info *sbi = ZONEFS_SB(sb); struct zonefs_inode_info *zi = ZONEFS_I(inode); + int ret = 0; inode->i_ino = zone->start >> sbi->s_zone_sectors_shift; inode->i_mode = S_IFREG | sbi->s_perm; @@ -1323,6 +1398,29 @@ static void zonefs_init_file_inode(struct inode *inode, struct blk_zone *zone, sb->s_maxbytes = max(zi->i_max_size, sb->s_maxbytes); sbi->s_blocks += zi->i_max_size >> sb->s_blocksize_bits; sbi->s_used_blocks += zi->i_wpoffset >> sb->s_blocksize_bits; + + mutex_lock(&zi->i_truncate_mutex); + + /* + * For sequential zones, make sure that any open zone is closed first + * to ensure that the initial number of open zones is 0, in sync with + * the open zone accounting done when the mount option + * ZONEFS_MNTOPT_EXPLICIT_OPEN is used. + */ + if (type == ZONEFS_ZTYPE_SEQ && + (zone->cond == BLK_ZONE_COND_IMP_OPEN || + zone->cond == BLK_ZONE_COND_EXP_OPEN)) { + ret = zonefs_zone_mgmt(inode, REQ_OP_ZONE_CLOSE); + if (ret) + goto unlock; + } + + zonefs_account_active(inode); + +unlock: + mutex_unlock(&zi->i_truncate_mutex); + + return ret; } static struct dentry *zonefs_create_inode(struct dentry *parent, @@ -1332,6 +1430,7 @@ static struct dentry *zonefs_create_inode(struct dentry *parent, struct inode *dir = d_inode(parent); struct dentry *dentry; struct inode *inode; + int ret; dentry = d_alloc_name(parent, name); if (!dentry) @@ -1342,10 +1441,16 @@ static struct dentry *zonefs_create_inode(struct dentry *parent, goto dput; inode->i_ctime = inode->i_mtime = inode->i_atime = dir->i_ctime; - if (zone) - zonefs_init_file_inode(inode, zone, type); - else + if (zone) { + ret = zonefs_init_file_inode(inode, zone, type); + if (ret) { + iput(inode); + goto dput; + } + } else { zonefs_init_dir_inode(dir, inode, type); + } + d_add(dentry, inode); dir->i_size++; @@ -1652,14 +1757,18 @@ static int zonefs_fill_super(struct super_block *sb, void *data, int silent) sbi->s_gid = GLOBAL_ROOT_GID; sbi->s_perm = 0640; sbi->s_mount_opts = ZONEFS_MNTOPT_ERRORS_RO; - sbi->s_max_open_zones = bdev_max_open_zones(sb->s_bdev); - atomic_set(&sbi->s_open_zones, 0); - if (!sbi->s_max_open_zones && + + atomic_set(&sbi->s_wro_seq_files, 0); + sbi->s_max_wro_seq_files = bdev_max_open_zones(sb->s_bdev); + if (!sbi->s_max_wro_seq_files && sbi->s_mount_opts & ZONEFS_MNTOPT_EXPLICIT_OPEN) { zonefs_info(sb, "No open zones limit. Ignoring explicit_open mount option\n"); sbi->s_mount_opts &= ~ZONEFS_MNTOPT_EXPLICIT_OPEN; } + atomic_set(&sbi->s_active_seq_files, 0); + sbi->s_max_active_seq_files = bdev_max_active_zones(sb->s_bdev); + ret = zonefs_read_super(sb); if (ret) return ret; @@ -1674,6 +1783,10 @@ static int zonefs_fill_super(struct super_block *sb, void *data, int silent) if (ret) goto cleanup; + ret = zonefs_sysfs_register(sb); + if (ret) + goto cleanup; + zonefs_info(sb, "Mounting %u zones", blkdev_nr_zones(sb->s_bdev->bd_disk)); @@ -1719,6 +1832,8 @@ static void zonefs_kill_super(struct super_block *sb) if (sb->s_root) d_genocide(sb->s_root); + + zonefs_sysfs_unregister(sb); kill_block_super(sb); kfree(sbi); } @@ -1766,16 +1881,26 @@ static int __init zonefs_init(void) return ret; ret = register_filesystem(&zonefs_type); - if (ret) { - zonefs_destroy_inodecache(); - return ret; - } + if (ret) + goto destroy_inodecache; + + ret = zonefs_sysfs_init(); + if (ret) + goto unregister_fs; return 0; + +unregister_fs: + unregister_filesystem(&zonefs_type); +destroy_inodecache: + zonefs_destroy_inodecache(); + + return ret; } static void __exit zonefs_exit(void) { + zonefs_sysfs_exit(); zonefs_destroy_inodecache(); unregister_filesystem(&zonefs_type); } diff --git a/fs/zonefs/sysfs.c b/fs/zonefs/sysfs.c new file mode 100644 index 000000000000..9cb6755ce39a --- /dev/null +++ b/fs/zonefs/sysfs.c @@ -0,0 +1,139 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Simple file system for zoned block devices exposing zones as files. + * + * Copyright (C) 2022 Western Digital Corporation or its affiliates. + */ +#include <linux/fs.h> +#include <linux/seq_file.h> +#include <linux/blkdev.h> + +#include "zonefs.h" + +struct zonefs_sysfs_attr { + struct attribute attr; + ssize_t (*show)(struct zonefs_sb_info *sbi, char *buf); +}; + +static inline struct zonefs_sysfs_attr *to_attr(struct attribute *attr) +{ + return container_of(attr, struct zonefs_sysfs_attr, attr); +} + +#define ZONEFS_SYSFS_ATTR_RO(name) \ +static struct zonefs_sysfs_attr zonefs_sysfs_attr_##name = __ATTR_RO(name) + +#define ATTR_LIST(name) &zonefs_sysfs_attr_##name.attr + +static ssize_t zonefs_sysfs_attr_show(struct kobject *kobj, + struct attribute *attr, char *buf) +{ + struct zonefs_sb_info *sbi = + container_of(kobj, struct zonefs_sb_info, s_kobj); + struct zonefs_sysfs_attr *zonefs_attr = + container_of(attr, struct zonefs_sysfs_attr, attr); + + if (!zonefs_attr->show) + return 0; + + return zonefs_attr->show(sbi, buf); +} + +static ssize_t max_wro_seq_files_show(struct zonefs_sb_info *sbi, char *buf) +{ + return sysfs_emit(buf, "%u\n", sbi->s_max_wro_seq_files); +} +ZONEFS_SYSFS_ATTR_RO(max_wro_seq_files); + +static ssize_t nr_wro_seq_files_show(struct zonefs_sb_info *sbi, char *buf) +{ + return sysfs_emit(buf, "%d\n", atomic_read(&sbi->s_wro_seq_files)); +} +ZONEFS_SYSFS_ATTR_RO(nr_wro_seq_files); + +static ssize_t max_active_seq_files_show(struct zonefs_sb_info *sbi, char *buf) +{ + return sysfs_emit(buf, "%u\n", sbi->s_max_active_seq_files); +} +ZONEFS_SYSFS_ATTR_RO(max_active_seq_files); + +static ssize_t nr_active_seq_files_show(struct zonefs_sb_info *sbi, char *buf) +{ + return sysfs_emit(buf, "%d\n", atomic_read(&sbi->s_active_seq_files)); +} +ZONEFS_SYSFS_ATTR_RO(nr_active_seq_files); + +static struct attribute *zonefs_sysfs_attrs[] = { + ATTR_LIST(max_wro_seq_files), + ATTR_LIST(nr_wro_seq_files), + ATTR_LIST(max_active_seq_files), + ATTR_LIST(nr_active_seq_files), + NULL, +}; +ATTRIBUTE_GROUPS(zonefs_sysfs); + +static void zonefs_sysfs_sb_release(struct kobject *kobj) +{ + struct zonefs_sb_info *sbi = + container_of(kobj, struct zonefs_sb_info, s_kobj); + + complete(&sbi->s_kobj_unregister); +} + +static const struct sysfs_ops zonefs_sysfs_attr_ops = { + .show = zonefs_sysfs_attr_show, +}; + +static struct kobj_type zonefs_sb_ktype = { + .default_groups = zonefs_sysfs_groups, + .sysfs_ops = &zonefs_sysfs_attr_ops, + .release = zonefs_sysfs_sb_release, +}; + +static struct kobject *zonefs_sysfs_root; + +int zonefs_sysfs_register(struct super_block *sb) +{ + struct zonefs_sb_info *sbi = ZONEFS_SB(sb); + int ret; + + init_completion(&sbi->s_kobj_unregister); + ret = kobject_init_and_add(&sbi->s_kobj, &zonefs_sb_ktype, + zonefs_sysfs_root, "%s", sb->s_id); + if (ret) { + kobject_put(&sbi->s_kobj); + wait_for_completion(&sbi->s_kobj_unregister); + return ret; + } + + sbi->s_sysfs_registered = true; + + return 0; +} + +void zonefs_sysfs_unregister(struct super_block *sb) +{ + struct zonefs_sb_info *sbi = ZONEFS_SB(sb); + + if (!sbi || !sbi->s_sysfs_registered) + return; + + kobject_del(&sbi->s_kobj); + kobject_put(&sbi->s_kobj); + wait_for_completion(&sbi->s_kobj_unregister); +} + +int __init zonefs_sysfs_init(void) +{ + zonefs_sysfs_root = kobject_create_and_add("zonefs", fs_kobj); + if (!zonefs_sysfs_root) + return -ENOMEM; + + return 0; +} + +void zonefs_sysfs_exit(void) +{ + kobject_put(zonefs_sysfs_root); + zonefs_sysfs_root = NULL; +} diff --git a/fs/zonefs/zonefs.h b/fs/zonefs/zonefs.h index 7b147907c328..4b3de66c3233 100644 --- a/fs/zonefs/zonefs.h +++ b/fs/zonefs/zonefs.h @@ -12,6 +12,7 @@ #include <linux/uuid.h> #include <linux/mutex.h> #include <linux/rwsem.h> +#include <linux/kobject.h> /* * Maximum length of file names: this only needs to be large enough to fit @@ -39,6 +40,7 @@ static inline enum zonefs_ztype zonefs_zone_type(struct blk_zone *zone) } #define ZONEFS_ZONE_OPEN (1 << 0) +#define ZONEFS_ZONE_ACTIVE (1 << 1) /* * In-memory inode data. @@ -182,8 +184,15 @@ struct zonefs_sb_info { loff_t s_blocks; loff_t s_used_blocks; - unsigned int s_max_open_zones; - atomic_t s_open_zones; + unsigned int s_max_wro_seq_files; + atomic_t s_wro_seq_files; + + unsigned int s_max_active_seq_files; + atomic_t s_active_seq_files; + + bool s_sysfs_registered; + struct kobject s_kobj; + struct completion s_kobj_unregister; }; static inline struct zonefs_sb_info *ZONEFS_SB(struct super_block *sb) @@ -198,4 +207,9 @@ static inline struct zonefs_sb_info *ZONEFS_SB(struct super_block *sb) #define zonefs_warn(sb, format, args...) \ pr_warn("zonefs (%s) WARNING: " format, sb->s_id, ## args) +int zonefs_sysfs_register(struct super_block *sb); +void zonefs_sysfs_unregister(struct super_block *sb); +int zonefs_sysfs_init(void); +void zonefs_sysfs_exit(void); + #endif diff --git a/include/acpi/acbuffer.h b/include/acpi/acbuffer.h index 3e8d969b22fe..8cbfcbca7b7e 100644 --- a/include/acpi/acbuffer.h +++ b/include/acpi/acbuffer.h @@ -3,7 +3,7 @@ * * Name: acbuffer.h - Support for buffers returned by ACPI predefined names * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/acconfig.h b/include/acpi/acconfig.h index 0362cbb72359..c3ae3ea88e17 100644 --- a/include/acpi/acconfig.h +++ b/include/acpi/acconfig.h @@ -3,7 +3,7 @@ * * Name: acconfig.h - Global configuration constants * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/acexcep.h b/include/acpi/acexcep.h index ea3b1c41bc79..28943c900be7 100644 --- a/include/acpi/acexcep.h +++ b/include/acpi/acexcep.h @@ -3,7 +3,7 @@ * * Name: acexcep.h - Exception codes returned by the ACPI subsystem * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/acnames.h b/include/acpi/acnames.h index 30869ab77fba..6f22e92b1744 100644 --- a/include/acpi/acnames.h +++ b/include/acpi/acnames.h @@ -3,7 +3,7 @@ * * Name: acnames.h - Global names and strings * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/acoutput.h b/include/acpi/acoutput.h index 5a3875744678..73781aae2119 100644 --- a/include/acpi/acoutput.h +++ b/include/acpi/acoutput.h @@ -3,7 +3,7 @@ * * Name: acoutput.h -- debug output * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/acpi.h b/include/acpi/acpi.h index 6f6282a862bc..416e59bcf149 100644 --- a/include/acpi/acpi.h +++ b/include/acpi/acpi.h @@ -3,7 +3,7 @@ * * Name: acpi.h - Master public include file used to interface to ACPICA * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index 3f7f01f03869..772590e2eddb 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -481,6 +481,8 @@ void acpi_initialize_hp_context(struct acpi_device *adev, extern struct bus_type acpi_bus_type; int acpi_bus_for_each_dev(int (*fn)(struct device *, void *), void *data); +int acpi_dev_for_each_child(struct acpi_device *adev, + int (*fn)(struct acpi_device *, void *), void *data); /* * Events @@ -509,7 +511,6 @@ extern int unregister_acpi_notifier(struct notifier_block *); * External Functions */ -int acpi_bus_get_device(acpi_handle handle, struct acpi_device **device); struct acpi_device *acpi_fetch_acpi_dev(acpi_handle handle); acpi_status acpi_bus_get_status_handle(acpi_handle handle, unsigned long long *sta); @@ -523,6 +524,7 @@ int acpi_device_fix_up_power(struct acpi_device *device); int acpi_bus_update_power(acpi_handle handle, int *state_p); int acpi_device_update_power(struct acpi_device *device, int *state_p); bool acpi_bus_power_manageable(acpi_handle handle); +void acpi_dev_power_up_children_with_adr(struct acpi_device *adev); int acpi_device_power_add_dependent(struct acpi_device *adev, struct device *dev); void acpi_device_power_remove_dependent(struct acpi_device *adev, diff --git a/include/acpi/acpiosxf.h b/include/acpi/acpiosxf.h index 690c369b717a..52844cc5eeb5 100644 --- a/include/acpi/acpiosxf.h +++ b/include/acpi/acpiosxf.h @@ -5,7 +5,7 @@ * interfaces must be implemented by OSL to interface the * ACPI components to the host operating system. * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h index 7417731472b7..67c0b9e734b6 100644 --- a/include/acpi/acpixf.h +++ b/include/acpi/acpixf.h @@ -3,7 +3,7 @@ * * Name: acpixf.h - External interfaces to the ACPI subsystem * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ @@ -12,7 +12,7 @@ /* Current ACPICA subsystem version in YYYYMMDD format */ -#define ACPI_CA_VERSION 0x20211217 +#define ACPI_CA_VERSION 0x20220331 #include <acpi/acconfig.h> #include <acpi/actypes.h> diff --git a/include/acpi/acrestyp.h b/include/acpi/acrestyp.h index 8e2319bbd0a2..a7fb8ddb3dc6 100644 --- a/include/acpi/acrestyp.h +++ b/include/acpi/acrestyp.h @@ -3,7 +3,7 @@ * * Name: acrestyp.h - Defines, types, and structures for resource descriptors * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/actbl.h b/include/acpi/actbl.h index f9cda909f92c..c6af579f74f4 100644 --- a/include/acpi/actbl.h +++ b/include/acpi/actbl.h @@ -3,7 +3,7 @@ * * Name: actbl.h - Basic ACPI Table Definitions * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/actbl1.h b/include/acpi/actbl1.h index 159070edd031..15c78678c5d3 100644 --- a/include/acpi/actbl1.h +++ b/include/acpi/actbl1.h @@ -3,7 +3,7 @@ * * Name: actbl1.h - Additional ACPI table definitions * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ @@ -373,17 +373,21 @@ struct acpi_cedt_cfmws { u32 interleave_targets[]; }; +struct acpi_cedt_cfmws_target_element { + u32 interleave_target; +}; + /* Values for Interleave Arithmetic field above */ -#define ACPI_CEDT_CFMWS_ARITHMETIC_MODULO (0) +#define ACPI_CEDT_CFMWS_ARITHMETIC_MODULO (0) /* Values for Restrictions field above */ -#define ACPI_CEDT_CFMWS_RESTRICT_TYPE2 (1) -#define ACPI_CEDT_CFMWS_RESTRICT_TYPE3 (1<<1) -#define ACPI_CEDT_CFMWS_RESTRICT_VOLATILE (1<<2) -#define ACPI_CEDT_CFMWS_RESTRICT_PMEM (1<<3) -#define ACPI_CEDT_CFMWS_RESTRICT_FIXED (1<<4) +#define ACPI_CEDT_CFMWS_RESTRICT_TYPE2 (1) +#define ACPI_CEDT_CFMWS_RESTRICT_TYPE3 (1<<1) +#define ACPI_CEDT_CFMWS_RESTRICT_VOLATILE (1<<2) +#define ACPI_CEDT_CFMWS_RESTRICT_PMEM (1<<3) +#define ACPI_CEDT_CFMWS_RESTRICT_FIXED (1<<4) /******************************************************************************* * diff --git a/include/acpi/actbl2.h b/include/acpi/actbl2.h index 16847c8d9d5f..655102bc6d14 100644 --- a/include/acpi/actbl2.h +++ b/include/acpi/actbl2.h @@ -3,7 +3,7 @@ * * Name: actbl2.h - ACPI Table Definitions (tables not in ACPI spec) * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ @@ -25,6 +25,7 @@ * the wrong signature. */ #define ACPI_SIG_AGDI "AGDI" /* Arm Generic Diagnostic Dump and Reset Device Interface */ +#define ACPI_SIG_APMT "APMT" /* Arm Performance Monitoring Unit table */ #define ACPI_SIG_BDAT "BDAT" /* BIOS Data ACPI Table */ #define ACPI_SIG_IORT "IORT" /* IO Remapping Table */ #define ACPI_SIG_IVRS "IVRS" /* I/O Virtualization Reporting Structure */ @@ -260,6 +261,85 @@ struct acpi_table_agdi { /******************************************************************************* * + * APMT - ARM Performance Monitoring Unit Table + * + * Conforms to: + * ARM Performance Monitoring Unit Architecture 1.0 Platform Design Document + * ARM DEN0117 v1.0 November 25, 2021 + * + ******************************************************************************/ + +struct acpi_table_apmt { + struct acpi_table_header header; /* Common ACPI table header */ +}; + +#define ACPI_APMT_NODE_ID_LENGTH 4 + +/* + * APMT subtables + */ +struct acpi_apmt_node { + u16 length; + u8 flags; + u8 type; + u32 id; + u64 inst_primary; + u32 inst_secondary; + u64 base_address0; + u64 base_address1; + u32 ovflw_irq; + u32 reserved; + u32 ovflw_irq_flags; + u32 proc_affinity; + u32 impl_id; +}; + +/* Masks for Flags field above */ + +#define ACPI_APMT_FLAGS_DUAL_PAGE (1<<0) +#define ACPI_APMT_FLAGS_AFFINITY (1<<1) +#define ACPI_APMT_FLAGS_ATOMIC (1<<2) + +/* Values for Flags dual page field above */ + +#define ACPI_APMT_FLAGS_DUAL_PAGE_NSUPP (0<<0) +#define ACPI_APMT_FLAGS_DUAL_PAGE_SUPP (1<<0) + +/* Values for Flags processor affinity field above */ +#define ACPI_APMT_FLAGS_AFFINITY_PROC (0<<1) +#define ACPI_APMT_FLAGS_AFFINITY_PROC_CONTAINER (1<<1) + +/* Values for Flags 64-bit atomic field above */ +#define ACPI_APMT_FLAGS_ATOMIC_NSUPP (0<<2) +#define ACPI_APMT_FLAGS_ATOMIC_SUPP (1<<2) + +/* Values for Type field above */ + +enum acpi_apmt_node_type { + ACPI_APMT_NODE_TYPE_MC = 0x00, + ACPI_APMT_NODE_TYPE_SMMU = 0x01, + ACPI_APMT_NODE_TYPE_PCIE_ROOT = 0x02, + ACPI_APMT_NODE_TYPE_ACPI = 0x03, + ACPI_APMT_NODE_TYPE_CACHE = 0x04, + ACPI_APMT_NODE_TYPE_COUNT +}; + +/* Masks for ovflw_irq_flags field above */ + +#define ACPI_APMT_OVFLW_IRQ_FLAGS_MODE (1<<0) +#define ACPI_APMT_OVFLW_IRQ_FLAGS_TYPE (1<<1) + +/* Values for ovflw_irq_flags mode field above */ + +#define ACPI_APMT_OVFLW_IRQ_FLAGS_MODE_LEVEL (0<<0) +#define ACPI_APMT_OVFLW_IRQ_FLAGS_MODE_EDGE (1<<0) + +/* Values for ovflw_irq_flags type field above */ + +#define ACPI_APMT_OVFLW_IRQ_FLAGS_TYPE_WIRED (0<<1) + +/******************************************************************************* + * * BDAT - BIOS Data ACPI Table * * Conforms to "BIOS Data ACPI Table", Interface Specification v4.0 Draft 5 @@ -277,7 +357,7 @@ struct acpi_table_bdat { * IORT - IO Remapping Table * * Conforms to "IO Remapping Table System Software on ARM Platforms", - * Document number: ARM DEN 0049E.b, Feb 2021 + * Document number: ARM DEN 0049E.d, Feb 2022 * ******************************************************************************/ @@ -374,7 +454,8 @@ struct acpi_iort_root_complex { u32 ats_attribute; u32 pci_segment_number; u8 memory_address_limit; /* Memory address size limit */ - u8 reserved[3]; /* Reserved, must be zero */ + u16 pasid_capabilities; /* PASID Capabilities */ + u8 reserved[1]; /* Reserved, must be zero */ }; /* Masks for ats_attribute field above */ @@ -383,6 +464,9 @@ struct acpi_iort_root_complex { #define ACPI_IORT_PRI_SUPPORTED (1<<1) /* The root complex PRI support */ #define ACPI_IORT_PASID_FWD_SUPPORTED (1<<2) /* The root complex PASID forward support */ +/* Masks for pasid_capabilities field above */ +#define ACPI_IORT_PASID_MAX_WIDTH (0x1F) /* Bits 0-4 */ + struct acpi_iort_smmu { u64 base_address; /* SMMU base address */ u64 span; /* Length of memory range */ @@ -458,6 +542,25 @@ struct acpi_iort_rmr { u32 rmr_offset; }; +/* Masks for Flags field above */ +#define ACPI_IORT_RMR_REMAP_PERMITTED (1) +#define ACPI_IORT_RMR_ACCESS_PRIVILEGE (1<<1) + +/* + * Macro to access the Access Attributes in flags field above: + * Access Attributes is encoded in bits 9:2 + */ +#define ACPI_IORT_RMR_ACCESS_ATTRIBUTES(flags) (((flags) >> 2) & 0xFF) + +/* Values for above Access Attributes */ + +#define ACPI_IORT_RMR_ATTR_DEVICE_NGNRNE 0x00 +#define ACPI_IORT_RMR_ATTR_DEVICE_NGNRE 0x01 +#define ACPI_IORT_RMR_ATTR_DEVICE_NGRE 0x02 +#define ACPI_IORT_RMR_ATTR_DEVICE_GRE 0x03 +#define ACPI_IORT_RMR_ATTR_NORMAL_NC 0x04 +#define ACPI_IORT_RMR_ATTR_NORMAL_IWB_OWB 0x05 + struct acpi_iort_rmr_desc { u64 base_address; u64 length; @@ -762,7 +865,8 @@ enum acpi_madt_type { ACPI_MADT_TYPE_GENERIC_REDISTRIBUTOR = 14, ACPI_MADT_TYPE_GENERIC_TRANSLATOR = 15, ACPI_MADT_TYPE_MULTIPROC_WAKEUP = 16, - ACPI_MADT_TYPE_RESERVED = 17 /* 17 and greater are reserved */ + ACPI_MADT_TYPE_RESERVED = 17, /* 17 to 0x7F are reserved */ + ACPI_MADT_TYPE_OEM_RESERVED = 0x80 /* 0x80 to 0xFF are reserved for OEM use */ }; /* @@ -978,8 +1082,8 @@ struct acpi_madt_multiproc_wakeup { u64 base_address; }; -#define ACPI_MULTIPROC_WAKEUP_MB_OS_SIZE 2032 -#define ACPI_MULTIPROC_WAKEUP_MB_FIRMWARE_SIZE 2048 +#define ACPI_MULTIPROC_WAKEUP_MB_OS_SIZE 2032 +#define ACPI_MULTIPROC_WAKEUP_MB_FIRMWARE_SIZE 2048 struct acpi_madt_multiproc_wakeup_mailbox { u16 command; @@ -992,6 +1096,12 @@ struct acpi_madt_multiproc_wakeup_mailbox { #define ACPI_MP_WAKE_COMMAND_WAKEUP 1 +/* 17: OEM data */ + +struct acpi_madt_oem_data { + u8 oem_data[0]; +}; + /* * Common flags fields for MADT subtables */ @@ -1597,7 +1707,7 @@ struct acpi_nhlt_mic_device_specific_config { /* Values for array_type_ext above */ -#define ACPI_NHLT_ARRAY_TYPE_RESERVED 0x09 // 9 and below are reserved +#define ACPI_NHLT_ARRAY_TYPE_RESERVED 0x09 /* 9 and below are reserved */ #define ACPI_NHLT_SMALL_LINEAR_2ELEMENT 0x0A #define ACPI_NHLT_BIG_LINEAR_2ELEMENT 0x0B #define ACPI_NHLT_FIRST_GEOMETRY_LINEAR_4ELEMENT 0x0C @@ -1617,17 +1727,17 @@ struct acpi_nhlt_vendor_mic_count { struct acpi_nhlt_vendor_mic_config { u8 type; u8 panel; - u16 speaker_position_distance; // mm - u16 horizontal_offset; // mm - u16 vertical_offset; // mm - u8 frequency_low_band; // 5*hz - u8 frequency_high_band; // 500*hz - u16 direction_angle; // -180 - + 180 - u16 elevation_angle; // -180 - + 180 - u16 work_vertical_angle_begin; // -180 - + 180 with 2 deg step - u16 work_vertical_angle_end; // -180 - + 180 with 2 deg step - u16 work_horizontal_angle_begin; // -180 - + 180 with 2 deg step - u16 work_horizontal_angle_end; // -180 - + 180 with 2 deg step + u16 speaker_position_distance; /* mm */ + u16 horizontal_offset; /* mm */ + u16 vertical_offset; /* mm */ + u8 frequency_low_band; /* 5*Hz */ + u8 frequency_high_band; /* 500*Hz */ + u16 direction_angle; /* -180 - + 180 */ + u16 elevation_angle; /* -180 - + 180 */ + u16 work_vertical_angle_begin; /* -180 - + 180 with 2 deg step */ + u16 work_vertical_angle_end; /* -180 - + 180 with 2 deg step */ + u16 work_horizontal_angle_begin; /* -180 - + 180 with 2 deg step */ + u16 work_horizontal_angle_end; /* -180 - + 180 with 2 deg step */ }; /* Values for Type field above */ @@ -1638,9 +1748,9 @@ struct acpi_nhlt_vendor_mic_config { #define ACPI_NHLT_MIC_SUPER_CARDIOID 3 #define ACPI_NHLT_MIC_HYPER_CARDIOID 4 #define ACPI_NHLT_MIC_8_SHAPED 5 -#define ACPI_NHLT_MIC_RESERVED6 6 // 6 is reserved +#define ACPI_NHLT_MIC_RESERVED6 6 /* 6 is reserved */ #define ACPI_NHLT_MIC_VENDOR_DEFINED 7 -#define ACPI_NHLT_MIC_RESERVED 8 // 8 and above are reserved +#define ACPI_NHLT_MIC_RESERVED 8 /* 8 and above are reserved */ /* Values for Panel field above */ @@ -1650,12 +1760,12 @@ struct acpi_nhlt_vendor_mic_config { #define ACPI_NHLT_MIC_POSITION_RIGHT 3 #define ACPI_NHLT_MIC_POSITION_FRONT 4 #define ACPI_NHLT_MIC_POSITION_BACK 5 -#define ACPI_NHLT_MIC_POSITION_RESERVED 6 // 6 and above are reserved +#define ACPI_NHLT_MIC_POSITION_RESERVED 6 /* 6 and above are reserved */ struct acpi_nhlt_vendor_mic_device_specific_config { struct acpi_nhlt_mic_device_specific_config mic_array_device_config; u8 number_of_microphones; - struct acpi_nhlt_vendor_mic_config mic_config[]; // indexed by number_of_microphones + struct acpi_nhlt_vendor_mic_config mic_config[]; /* Indexed by number_of_microphones */ }; /* Microphone SNR and Sensitivity extension */ @@ -1668,32 +1778,23 @@ struct acpi_nhlt_mic_snr_sensitivity_extension { /* Render device with feedback */ struct acpi_nhlt_render_feedback_device_specific_config { - u8 feedback_virtual_slot; // render slot in case of capture - u16 feedback_channels; // informative only + u8 feedback_virtual_slot; /* Render slot in case of capture */ + u16 feedback_channels; /* Informative only */ u16 feedback_valid_bits_per_sample; }; -/* Linux-specific structures */ +/* Non documented structures */ -struct acpi_nhlt_linux_specific_count { +struct acpi_nhlt_device_info_count { u8 structure_count; }; -struct acpi_nhlt_linux_specific_data { +struct acpi_nhlt_device_info { u8 device_id[16]; u8 device_instance_id; u8 device_port_id; }; -struct acpi_nhlt_linux_specific_data_b { - u8 specific_data[18]; -}; - -struct acpi_nhlt_table_terminator { - u32 terminator_value; - u32 terminator_signature; -}; - /******************************************************************************* * * PCCT - Platform Communications Channel Table (ACPI 5.0) @@ -2319,7 +2420,7 @@ struct acpi_table_rgrt { u16 version; u8 image_type; u8 reserved; - u8 image[0]; + u8 image[]; }; /* image_type values */ diff --git a/include/acpi/actbl3.h b/include/acpi/actbl3.h index edbf1ad8206d..7b9571e00cc4 100644 --- a/include/acpi/actbl3.h +++ b/include/acpi/actbl3.h @@ -3,7 +3,7 @@ * * Name: actbl3.h - ACPI Table Definitions * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/actypes.h b/include/acpi/actypes.h index 02c1fa16e638..3491e454b2ab 100644 --- a/include/acpi/actypes.h +++ b/include/acpi/actypes.h @@ -3,7 +3,7 @@ * * Name: actypes.h - Common data types for the entire ACPI subsystem * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ @@ -539,14 +539,14 @@ typedef u64 acpi_integer; * Can be used with access_width of struct acpi_generic_address and access_size of * struct acpi_resource_generic_register. */ -#define ACPI_ACCESS_BIT_SHIFT 2 -#define ACPI_ACCESS_BYTE_SHIFT -1 -#define ACPI_ACCESS_BIT_MAX (31 - ACPI_ACCESS_BIT_SHIFT) -#define ACPI_ACCESS_BYTE_MAX (31 - ACPI_ACCESS_BYTE_SHIFT) -#define ACPI_ACCESS_BIT_DEFAULT (8 - ACPI_ACCESS_BIT_SHIFT) -#define ACPI_ACCESS_BYTE_DEFAULT (8 - ACPI_ACCESS_BYTE_SHIFT) -#define ACPI_ACCESS_BIT_WIDTH(size) (1 << ((size) + ACPI_ACCESS_BIT_SHIFT)) -#define ACPI_ACCESS_BYTE_WIDTH(size) (1 << ((size) + ACPI_ACCESS_BYTE_SHIFT)) +#define ACPI_ACCESS_BIT_SHIFT 2 +#define ACPI_ACCESS_BYTE_SHIFT -1 +#define ACPI_ACCESS_BIT_MAX (31 - ACPI_ACCESS_BIT_SHIFT) +#define ACPI_ACCESS_BYTE_MAX (31 - ACPI_ACCESS_BYTE_SHIFT) +#define ACPI_ACCESS_BIT_DEFAULT (8 - ACPI_ACCESS_BIT_SHIFT) +#define ACPI_ACCESS_BYTE_DEFAULT (8 - ACPI_ACCESS_BYTE_SHIFT) +#define ACPI_ACCESS_BIT_WIDTH(size) (1 << ((size) + ACPI_ACCESS_BIT_SHIFT)) +#define ACPI_ACCESS_BYTE_WIDTH(size) (1 << ((size) + ACPI_ACCESS_BYTE_SHIFT)) /******************************************************************************* * @@ -1303,6 +1303,7 @@ typedef enum { #define ACPI_OSI_WIN_10_RS5 0x13 #define ACPI_OSI_WIN_10_19H1 0x14 #define ACPI_OSI_WIN_10_20H1 0x15 +#define ACPI_OSI_WIN_11 0x16 /* Definitions of getopt */ diff --git a/include/acpi/acuuid.h b/include/acpi/acuuid.h index bc24388ce94e..8f1e7c489df5 100644 --- a/include/acpi/acuuid.h +++ b/include/acpi/acuuid.h @@ -3,7 +3,7 @@ * * Name: acuuid.h - ACPI-related UUID/GUID definitions * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/apei.h b/include/acpi/apei.h index afaca3a075e8..dc60f7db5524 100644 --- a/include/acpi/apei.h +++ b/include/acpi/apei.h @@ -46,6 +46,8 @@ int erst_get_record_id_next(int *pos, u64 *record_id); void erst_get_record_id_end(void); ssize_t erst_read(u64 record_id, struct cper_record_header *record, size_t buflen); +ssize_t erst_read_record(u64 record_id, struct cper_record_header *record, + size_t buflen, size_t recordlen, const guid_t *creatorid); int erst_clear(u64 record_id); int arch_apei_enable_cmcff(struct acpi_hest_header *hest_hdr, void *data); diff --git a/include/acpi/cppc_acpi.h b/include/acpi/cppc_acpi.h index 92b7ea8d8f5e..c6108581d97d 100644 --- a/include/acpi/cppc_acpi.h +++ b/include/acpi/cppc_acpi.h @@ -141,6 +141,7 @@ extern int cppc_set_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls); extern int cppc_set_enable(int cpu, bool enable); extern int cppc_get_perf_caps(int cpu, struct cppc_perf_caps *caps); extern bool acpi_cpc_valid(void); +extern bool cppc_allow_fast_switch(void); extern int acpi_get_psd_map(unsigned int cpu, struct cppc_cpudata *cpu_data); extern unsigned int cppc_get_transition_latency(int cpu); extern bool cpc_ffh_supported(void); @@ -175,6 +176,10 @@ static inline bool acpi_cpc_valid(void) { return false; } +static inline bool cppc_allow_fast_switch(void) +{ + return false; +} static inline unsigned int cppc_get_transition_latency(int cpu) { return CPUFREQ_ETERNAL; diff --git a/include/acpi/platform/acenv.h b/include/acpi/platform/acenv.h index e8958e0d1646..03eb3d977075 100644 --- a/include/acpi/platform/acenv.h +++ b/include/acpi/platform/acenv.h @@ -3,7 +3,7 @@ * * Name: acenv.h - Host and compiler configuration * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/platform/acenvex.h b/include/acpi/platform/acenvex.h index 277fe2fa4d9b..3a6b1db9a984 100644 --- a/include/acpi/platform/acenvex.h +++ b/include/acpi/platform/acenvex.h @@ -3,7 +3,7 @@ * * Name: acenvex.h - Extra host and compiler configuration * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/platform/acgcc.h b/include/acpi/platform/acgcc.h index 33ad282bd338..ac80111f503c 100644 --- a/include/acpi/platform/acgcc.h +++ b/include/acpi/platform/acgcc.h @@ -3,7 +3,7 @@ * * Name: acgcc.h - GCC specific defines, etc. * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/platform/acgccex.h b/include/acpi/platform/acgccex.h index 738d52865e0a..302ea1b724b9 100644 --- a/include/acpi/platform/acgccex.h +++ b/include/acpi/platform/acgccex.h @@ -3,7 +3,7 @@ * * Name: acgccex.h - Extra GCC specific defines, etc. * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/platform/acintel.h b/include/acpi/platform/acintel.h index 550fe9a8cd6c..85b1ae86ee63 100644 --- a/include/acpi/platform/acintel.h +++ b/include/acpi/platform/acintel.h @@ -3,7 +3,7 @@ * * Name: acintel.h - VC specific defines, etc. * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/platform/aclinux.h b/include/acpi/platform/aclinux.h index cec41e004ecf..a5550dd4d507 100644 --- a/include/acpi/platform/aclinux.h +++ b/include/acpi/platform/aclinux.h @@ -3,7 +3,7 @@ * * Name: aclinux.h - OS specific defines, etc. for Linux * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/platform/aclinuxex.h b/include/acpi/platform/aclinuxex.h index 5f642b07ad64..28c72744decf 100644 --- a/include/acpi/platform/aclinuxex.h +++ b/include/acpi/platform/aclinuxex.h @@ -3,7 +3,7 @@ * * Name: aclinuxex.h - Extra OS specific defines, etc. for Linux * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/include/asm-generic/bug.h b/include/asm-generic/bug.h index edb0e2a602a8..ba1f860af38b 100644 --- a/include/asm-generic/bug.h +++ b/include/asm-generic/bug.h @@ -21,6 +21,12 @@ #include <linux/panic.h> #include <linux/printk.h> +struct warn_args; +struct pt_regs; + +void __warn(const char *file, int line, void *caller, unsigned taint, + struct pt_regs *regs, struct warn_args *args); + #ifdef CONFIG_BUG #ifdef CONFIG_GENERIC_BUG @@ -110,11 +116,6 @@ extern __printf(1, 2) void __warn_printk(const char *fmt, ...); #endif /* used internally by panic.c */ -struct warn_args; -struct pt_regs; - -void __warn(const char *file, int line, void *caller, unsigned taint, - struct pt_regs *regs, struct warn_args *args); #ifndef WARN_ON #define WARN_ON(condition) ({ \ diff --git a/include/asm-generic/mshyperv.h b/include/asm-generic/mshyperv.h index c08758b6b364..c05d2ce9b6cd 100644 --- a/include/asm-generic/mshyperv.h +++ b/include/asm-generic/mshyperv.h @@ -269,6 +269,7 @@ bool hv_isolation_type_snp(void); u64 hv_ghcb_hypercall(u64 control, void *input, void *output, u32 input_size); void hyperv_cleanup(void); bool hv_query_ext_cap(u64 cap_query); +void hv_setup_dma_ops(struct device *dev, bool coherent); void *hv_map_memory(void *addr, unsigned long size); void hv_unmap_memory(void *addr); #else /* CONFIG_HYPERV */ diff --git a/include/asm-generic/qrwlock.h b/include/asm-generic/qrwlock.h index 7ae0ece07b4e..d4cd4cc4389c 100644 --- a/include/asm-generic/qrwlock.h +++ b/include/asm-generic/qrwlock.h @@ -33,8 +33,8 @@ extern void queued_read_lock_slowpath(struct qrwlock *lock); extern void queued_write_lock_slowpath(struct qrwlock *lock); /** - * queued_read_trylock - try to acquire read lock of a queue rwlock - * @lock : Pointer to queue rwlock structure + * queued_read_trylock - try to acquire read lock of a queued rwlock + * @lock : Pointer to queued rwlock structure * Return: 1 if lock acquired, 0 if failed */ static inline int queued_read_trylock(struct qrwlock *lock) @@ -52,8 +52,8 @@ static inline int queued_read_trylock(struct qrwlock *lock) } /** - * queued_write_trylock - try to acquire write lock of a queue rwlock - * @lock : Pointer to queue rwlock structure + * queued_write_trylock - try to acquire write lock of a queued rwlock + * @lock : Pointer to queued rwlock structure * Return: 1 if lock acquired, 0 if failed */ static inline int queued_write_trylock(struct qrwlock *lock) @@ -68,8 +68,8 @@ static inline int queued_write_trylock(struct qrwlock *lock) _QW_LOCKED)); } /** - * queued_read_lock - acquire read lock of a queue rwlock - * @lock: Pointer to queue rwlock structure + * queued_read_lock - acquire read lock of a queued rwlock + * @lock: Pointer to queued rwlock structure */ static inline void queued_read_lock(struct qrwlock *lock) { @@ -84,8 +84,8 @@ static inline void queued_read_lock(struct qrwlock *lock) } /** - * queued_write_lock - acquire write lock of a queue rwlock - * @lock : Pointer to queue rwlock structure + * queued_write_lock - acquire write lock of a queued rwlock + * @lock : Pointer to queued rwlock structure */ static inline void queued_write_lock(struct qrwlock *lock) { @@ -98,8 +98,8 @@ static inline void queued_write_lock(struct qrwlock *lock) } /** - * queued_read_unlock - release read lock of a queue rwlock - * @lock : Pointer to queue rwlock structure + * queued_read_unlock - release read lock of a queued rwlock + * @lock : Pointer to queued rwlock structure */ static inline void queued_read_unlock(struct qrwlock *lock) { @@ -110,8 +110,8 @@ static inline void queued_read_unlock(struct qrwlock *lock) } /** - * queued_write_unlock - release write lock of a queue rwlock - * @lock : Pointer to queue rwlock structure + * queued_write_unlock - release write lock of a queued rwlock + * @lock : Pointer to queued rwlock structure */ static inline void queued_write_unlock(struct qrwlock *lock) { @@ -120,7 +120,7 @@ static inline void queued_write_unlock(struct qrwlock *lock) /** * queued_rwlock_is_contended - check if the lock is contended - * @lock : Pointer to queue rwlock structure + * @lock : Pointer to queued rwlock structure * Return: 1 if lock contended, 0 otherwise */ static inline int queued_rwlock_is_contended(struct qrwlock *lock) @@ -130,7 +130,7 @@ static inline int queued_rwlock_is_contended(struct qrwlock *lock) /* * Remapping rwlock architecture specific functions to the corresponding - * queue rwlock functions. + * queued rwlock functions. */ #define arch_read_lock(l) queued_read_lock(l) #define arch_write_lock(l) queued_write_lock(l) diff --git a/include/asm-generic/qrwlock_types.h b/include/asm-generic/qrwlock_types.h index c36f1d5a2572..12392c14c4d0 100644 --- a/include/asm-generic/qrwlock_types.h +++ b/include/asm-generic/qrwlock_types.h @@ -7,7 +7,7 @@ #include <asm/spinlock_types.h> /* - * The queue read/write lock data structure + * The queued read/write lock data structure */ typedef struct qrwlock { diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index fd7feb5c7894..eee6f7763a39 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -565,10 +565,14 @@ static inline void tlb_flush_p4d_range(struct mmu_gather *tlb, #define tlb_remove_huge_tlb_entry(h, tlb, ptep, address) \ do { \ unsigned long _sz = huge_page_size(h); \ - if (_sz == PMD_SIZE) \ - tlb_flush_pmd_range(tlb, address, _sz); \ - else if (_sz == PUD_SIZE) \ + if (_sz >= P4D_SIZE) \ + tlb_flush_p4d_range(tlb, address, _sz); \ + else if (_sz >= PUD_SIZE) \ tlb_flush_pud_range(tlb, address, _sz); \ + else if (_sz >= PMD_SIZE) \ + tlb_flush_pmd_range(tlb, address, _sz); \ + else \ + tlb_flush_pte_range(tlb, address, _sz); \ __tlb_remove_tlb_entry(tlb, ptep, address); \ } while (0) diff --git a/include/asm-generic/unaligned.h b/include/asm-generic/unaligned.h index 8fc637379899..df30f11b4a46 100644 --- a/include/asm-generic/unaligned.h +++ b/include/asm-generic/unaligned.h @@ -143,7 +143,7 @@ static inline void put_unaligned_be48(const u64 val, void *p) static inline u64 __get_unaligned_be48(const u8 *p) { - return (u64)p[0] << 40 | (u64)p[1] << 32 | p[2] << 24 | + return (u64)p[0] << 40 | (u64)p[1] << 32 | (u64)p[2] << 24 | p[3] << 16 | p[4] << 8 | p[5]; } diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 69138e9db787..7515a465ec03 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -126,13 +126,13 @@ */ #define SCHED_DATA \ STRUCT_ALIGN(); \ - __begin_sched_classes = .; \ - *(__idle_sched_class) \ - *(__fair_sched_class) \ - *(__rt_sched_class) \ - *(__dl_sched_class) \ + __sched_class_highest = .; \ *(__stop_sched_class) \ - __end_sched_classes = .; + *(__dl_sched_class) \ + *(__rt_sched_class) \ + *(__fair_sched_class) \ + *(__idle_sched_class) \ + __sched_class_lowest = .; /* The actual configuration determine if the init/exit sections * are handled as text/data or they can be discarded (which diff --git a/include/clocksource/timer-goldfish.h b/include/clocksource/timer-goldfish.h new file mode 100644 index 000000000000..05a3a4f610d6 --- /dev/null +++ b/include/clocksource/timer-goldfish.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * goldfish-timer clocksource + * Registers definition for the goldfish-timer device + */ + +#ifndef _CLOCKSOURCE_TIMER_GOLDFISH_H +#define _CLOCKSOURCE_TIMER_GOLDFISH_H + +/* + * TIMER_TIME_LOW get low bits of current time and update TIMER_TIME_HIGH + * TIMER_TIME_HIGH get high bits of time at last TIMER_TIME_LOW read + * TIMER_ALARM_LOW set low bits of alarm and activate it + * TIMER_ALARM_HIGH set high bits of next alarm + * TIMER_IRQ_ENABLED enable alarm interrupt + * TIMER_CLEAR_ALARM disarm an existing alarm + * TIMER_ALARM_STATUS alarm status (running or not) + * TIMER_CLEAR_INTERRUPT clear interrupt + */ +#define TIMER_TIME_LOW 0x00 +#define TIMER_TIME_HIGH 0x04 +#define TIMER_ALARM_LOW 0x08 +#define TIMER_ALARM_HIGH 0x0c +#define TIMER_IRQ_ENABLED 0x10 +#define TIMER_CLEAR_ALARM 0x14 +#define TIMER_ALARM_STATUS 0x18 +#define TIMER_CLEAR_INTERRUPT 0x1c + +extern int goldfish_timer_init(int irq, void __iomem *base); + +#endif /* _CLOCKSOURCE_TIMER_GOLDFISH_H */ diff --git a/include/dt-bindings/clock/microchip,mpfs-clock.h b/include/dt-bindings/clock/microchip,mpfs-clock.h index 73f2a9324857..4048669bf756 100644 --- a/include/dt-bindings/clock/microchip,mpfs-clock.h +++ b/include/dt-bindings/clock/microchip,mpfs-clock.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ /* * Daire McNamara,<daire.mcnamara@microchip.com> - * Copyright (C) 2020 Microchip Technology Inc. All rights reserved. + * Copyright (C) 2020-2022 Microchip Technology Inc. All rights reserved. */ #ifndef _DT_BINDINGS_CLK_MICROCHIP_MPFS_H_ @@ -42,4 +42,7 @@ #define CLK_ATHENA 31 #define CLK_CFM 32 +#define CLK_RTCREF 33 +#define CLK_MSSPLL 34 + #endif /* _DT_BINDINGS_CLK_MICROCHIP_MPFS_H_ */ diff --git a/include/keys/system_keyring.h b/include/keys/system_keyring.h index 2419a735420f..91e080efb918 100644 --- a/include/keys/system_keyring.h +++ b/include/keys/system_keyring.h @@ -10,6 +10,13 @@ #include <linux/key.h> +enum blacklist_hash_type { + /* TBSCertificate hash */ + BLACKLIST_HASH_X509_TBS = 1, + /* Raw data hash */ + BLACKLIST_HASH_BINARY = 2, +}; + #ifdef CONFIG_SYSTEM_TRUSTED_KEYRING extern int restrict_link_by_builtin_trusted(struct key *keyring, @@ -54,13 +61,14 @@ static inline void __init set_machine_trusted_keys(struct key *keyring) extern struct pkcs7_message *pkcs7; #ifdef CONFIG_SYSTEM_BLACKLIST_KEYRING -extern int mark_hash_blacklisted(const char *hash); +extern int mark_hash_blacklisted(const u8 *hash, size_t hash_len, + enum blacklist_hash_type hash_type); extern int is_hash_blacklisted(const u8 *hash, size_t hash_len, - const char *type); + enum blacklist_hash_type hash_type); extern int is_binary_blacklisted(const u8 *hash, size_t hash_len); #else static inline int is_hash_blacklisted(const u8 *hash, size_t hash_len, - const char *type) + enum blacklist_hash_type hash_type) { return 0; } diff --git a/include/keys/trusted-type.h b/include/keys/trusted-type.h index d89fa2579ac0..4eb64548a74f 100644 --- a/include/keys/trusted-type.h +++ b/include/keys/trusted-type.h @@ -64,7 +64,7 @@ struct trusted_key_ops { /* Unseal a key. */ int (*unseal)(struct trusted_key_payload *p, char *datablob); - /* Get a randomized key. */ + /* Optional: Get a randomized key. */ int (*get_random)(unsigned char *key, size_t key_len); /* Exit key interface. */ diff --git a/include/keys/trusted_caam.h b/include/keys/trusted_caam.h new file mode 100644 index 000000000000..73fe2f32f65e --- /dev/null +++ b/include/keys/trusted_caam.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2021 Pengutronix, Ahmad Fatoum <kernel@pengutronix.de> + */ + +#ifndef __CAAM_TRUSTED_KEY_H +#define __CAAM_TRUSTED_KEY_H + +extern struct trusted_key_ops trusted_key_caam_ops; + +#endif diff --git a/include/linux/acpi.h b/include/linux/acpi.h index d7136d13aa44..03465db16b68 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -574,6 +574,7 @@ acpi_status acpi_run_osc(acpi_handle handle, struct acpi_osc_context *context); #define OSC_SB_OSLPI_SUPPORT 0x00000100 #define OSC_SB_CPC_DIVERSE_HIGH_SUPPORT 0x00001000 #define OSC_SB_GENERIC_INITIATOR_SUPPORT 0x00002000 +#define OSC_SB_CPC_FLEXIBLE_ADR_SPACE 0x00004000 #define OSC_SB_NATIVE_USB4_SUPPORT 0x00040000 #define OSC_SB_PRM_SUPPORT 0x00200000 @@ -581,6 +582,7 @@ extern bool osc_sb_apei_support_acked; extern bool osc_pc_lpi_support_confirmed; extern bool osc_sb_native_usb4_support_confirmed; extern bool osc_sb_cppc_not_supported; +extern bool osc_cpc_flexible_adr_space_confirmed; /* USB4 Capabilities */ #define OSC_USB_USB3_TUNNELING 0x00000001 diff --git a/include/linux/amba/mmci.h b/include/linux/amba/mmci.h index c92ebc39fc1f..6f96dc2209c0 100644 --- a/include/linux/amba/mmci.h +++ b/include/linux/amba/mmci.h @@ -13,17 +13,11 @@ * @ocr_mask: available voltages on the 4 pins from the block, this * is ignored if a regulator is used, see the MMC_VDD_* masks in * mmc/host.h - * @ios_handler: a callback function to act on specfic ios changes, - * used for example to control a levelshifter - * mask into a value to be binary (or set some other custom bits - * in MMCIPWR) or:ed and written into the MMCIPWR register of the - * block. May also control external power based on the power_mode. * @status: if no GPIO line was given to the block in this function will * be called to determine whether a card is present in the MMC slot or not */ struct mmci_platform_data { unsigned int ocr_mask; - int (*ios_handler)(struct device *, struct mmc_ios *); unsigned int (*status)(struct device *); }; diff --git a/include/linux/atomic/atomic-arch-fallback.h b/include/linux/atomic/atomic-arch-fallback.h index 6db58d180866..77bc5522e61c 100644 --- a/include/linux/atomic/atomic-arch-fallback.h +++ b/include/linux/atomic/atomic-arch-fallback.h @@ -147,6 +147,76 @@ #endif /* arch_try_cmpxchg_relaxed */ +#ifndef arch_try_cmpxchg64_relaxed +#ifdef arch_try_cmpxchg64 +#define arch_try_cmpxchg64_acquire arch_try_cmpxchg64 +#define arch_try_cmpxchg64_release arch_try_cmpxchg64 +#define arch_try_cmpxchg64_relaxed arch_try_cmpxchg64 +#endif /* arch_try_cmpxchg64 */ + +#ifndef arch_try_cmpxchg64 +#define arch_try_cmpxchg64(_ptr, _oldp, _new) \ +({ \ + typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ + ___r = arch_cmpxchg64((_ptr), ___o, (_new)); \ + if (unlikely(___r != ___o)) \ + *___op = ___r; \ + likely(___r == ___o); \ +}) +#endif /* arch_try_cmpxchg64 */ + +#ifndef arch_try_cmpxchg64_acquire +#define arch_try_cmpxchg64_acquire(_ptr, _oldp, _new) \ +({ \ + typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ + ___r = arch_cmpxchg64_acquire((_ptr), ___o, (_new)); \ + if (unlikely(___r != ___o)) \ + *___op = ___r; \ + likely(___r == ___o); \ +}) +#endif /* arch_try_cmpxchg64_acquire */ + +#ifndef arch_try_cmpxchg64_release +#define arch_try_cmpxchg64_release(_ptr, _oldp, _new) \ +({ \ + typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ + ___r = arch_cmpxchg64_release((_ptr), ___o, (_new)); \ + if (unlikely(___r != ___o)) \ + *___op = ___r; \ + likely(___r == ___o); \ +}) +#endif /* arch_try_cmpxchg64_release */ + +#ifndef arch_try_cmpxchg64_relaxed +#define arch_try_cmpxchg64_relaxed(_ptr, _oldp, _new) \ +({ \ + typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ + ___r = arch_cmpxchg64_relaxed((_ptr), ___o, (_new)); \ + if (unlikely(___r != ___o)) \ + *___op = ___r; \ + likely(___r == ___o); \ +}) +#endif /* arch_try_cmpxchg64_relaxed */ + +#else /* arch_try_cmpxchg64_relaxed */ + +#ifndef arch_try_cmpxchg64_acquire +#define arch_try_cmpxchg64_acquire(...) \ + __atomic_op_acquire(arch_try_cmpxchg64, __VA_ARGS__) +#endif + +#ifndef arch_try_cmpxchg64_release +#define arch_try_cmpxchg64_release(...) \ + __atomic_op_release(arch_try_cmpxchg64, __VA_ARGS__) +#endif + +#ifndef arch_try_cmpxchg64 +#define arch_try_cmpxchg64(...) \ + __atomic_op_fence(arch_try_cmpxchg64, __VA_ARGS__) +#endif + +#endif /* arch_try_cmpxchg64_relaxed */ + #ifndef arch_atomic_read_acquire static __always_inline int arch_atomic_read_acquire(const atomic_t *v) @@ -2386,4 +2456,4 @@ arch_atomic64_dec_if_positive(atomic64_t *v) #endif #endif /* _LINUX_ATOMIC_FALLBACK_H */ -// 8e2cc06bc0d2c0967d2f8424762bd48555ee40ae +// b5e87bdd5ede61470c29f7a7e4de781af3770f09 diff --git a/include/linux/atomic/atomic-instrumented.h b/include/linux/atomic/atomic-instrumented.h index 5d69b143c28e..7a139ec030b0 100644 --- a/include/linux/atomic/atomic-instrumented.h +++ b/include/linux/atomic/atomic-instrumented.h @@ -2006,6 +2006,44 @@ atomic_long_dec_if_positive(atomic_long_t *v) arch_try_cmpxchg_relaxed(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) +#define try_cmpxchg64(ptr, oldp, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + typeof(oldp) __ai_oldp = (oldp); \ + kcsan_mb(); \ + instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ + arch_try_cmpxchg64(__ai_ptr, __ai_oldp, __VA_ARGS__); \ +}) + +#define try_cmpxchg64_acquire(ptr, oldp, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + typeof(oldp) __ai_oldp = (oldp); \ + instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ + arch_try_cmpxchg64_acquire(__ai_ptr, __ai_oldp, __VA_ARGS__); \ +}) + +#define try_cmpxchg64_release(ptr, oldp, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + typeof(oldp) __ai_oldp = (oldp); \ + kcsan_release(); \ + instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ + arch_try_cmpxchg64_release(__ai_ptr, __ai_oldp, __VA_ARGS__); \ +}) + +#define try_cmpxchg64_relaxed(ptr, oldp, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + typeof(oldp) __ai_oldp = (oldp); \ + instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ + arch_try_cmpxchg64_relaxed(__ai_ptr, __ai_oldp, __VA_ARGS__); \ +}) + #define cmpxchg_local(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ @@ -2045,4 +2083,4 @@ atomic_long_dec_if_positive(atomic_long_t *v) }) #endif /* _LINUX_ATOMIC_INSTRUMENTED_H */ -// 87c974b93032afd42143613434d1a7788fa598f9 +// 764f741eb77a7ad565dc8d99ce2837d5542e8aee diff --git a/include/linux/audit.h b/include/linux/audit.h index d06134ac6245..cece70231138 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -339,7 +339,7 @@ static inline void audit_uring_entry(u8 op) } static inline void audit_uring_exit(int success, long code) { - if (unlikely(!audit_dummy_context())) + if (unlikely(audit_context())) __audit_uring_exit(success, code); } static inline void audit_syscall_entry(int major, unsigned long a0, diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 87ce24d238f3..2bd073fa6bb5 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -17,8 +17,6 @@ #include <linux/backing-dev-defs.h> #include <linux/slab.h> -struct blkcg; - static inline struct backing_dev_info *bdi_get(struct backing_dev_info *bdi) { kref_get(&bdi->refcnt); @@ -154,7 +152,7 @@ struct bdi_writeback *wb_get_create(struct backing_dev_info *bdi, struct cgroup_subsys_state *memcg_css, gfp_t gfp); void wb_memcg_offline(struct mem_cgroup *memcg); -void wb_blkcg_offline(struct blkcg *blkcg); +void wb_blkcg_offline(struct cgroup_subsys_state *css); /** * inode_cgwb_enabled - test whether cgroup writeback is enabled on an inode @@ -378,7 +376,7 @@ static inline void wb_memcg_offline(struct mem_cgroup *memcg) { } -static inline void wb_blkcg_offline(struct blkcg *blkcg) +static inline void wb_blkcg_offline(struct cgroup_subsys_state *css) { } diff --git a/include/linux/bio.h b/include/linux/bio.h index 278cc81cc1e7..1cf3738ef1ea 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -269,6 +269,7 @@ struct folio_iter { size_t offset; size_t length; /* private: for use by the iterator */ + struct folio *_next; size_t _seg_count; int _i; }; @@ -283,6 +284,7 @@ static inline void bio_first_folio(struct folio_iter *fi, struct bio *bio, PAGE_SIZE * (bvec->bv_page - &fi->folio->page); fi->_seg_count = bvec->bv_len; fi->length = min(folio_size(fi->folio) - fi->offset, fi->_seg_count); + fi->_next = folio_next(fi->folio); fi->_i = i; } @@ -290,9 +292,10 @@ static inline void bio_next_folio(struct folio_iter *fi, struct bio *bio) { fi->_seg_count -= fi->length; if (fi->_seg_count) { - fi->folio = folio_next(fi->folio); + fi->folio = fi->_next; fi->offset = 0; fi->length = min(folio_size(fi->folio), fi->_seg_count); + fi->_next = folio_next(fi->folio); } else if (fi->_i + 1 < bio->bi_vcnt) { bio_first_folio(fi, bio, fi->_i + 1); } else { @@ -405,9 +408,7 @@ extern int bioset_init_from_src(struct bio_set *bs, struct bio_set *src); struct bio *bio_alloc_bioset(struct block_device *bdev, unsigned short nr_vecs, unsigned int opf, gfp_t gfp_mask, struct bio_set *bs); -struct bio *bio_alloc_kiocb(struct kiocb *kiocb, struct block_device *bdev, - unsigned short nr_vecs, unsigned int opf, struct bio_set *bs); -struct bio *bio_kmalloc(gfp_t gfp_mask, unsigned short nr_iovecs); +struct bio *bio_kmalloc(unsigned short nr_vecs, gfp_t gfp_mask); extern void bio_put(struct bio *); struct bio *bio_alloc_clone(struct block_device *bdev, struct bio *bio_src, @@ -782,6 +783,12 @@ static inline void bio_set_polled(struct bio *bio, struct kiocb *kiocb) bio->bi_opf |= REQ_NOWAIT; } +static inline void bio_clear_polled(struct bio *bio) +{ + /* can't support alloc cache if we turn off polling */ + bio->bi_opf &= ~(REQ_POLLED | REQ_ALLOC_CACHE); +} + struct bio *blk_next_bio(struct bio *bio, struct block_device *bdev, unsigned int nr_pages, unsigned int opf, gfp_t gfp); diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 652cd05b0924..9f40dbc65f82 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -14,265 +14,39 @@ * Nauman Rafique <nauman@google.com> */ -#include <linux/cgroup.h> -#include <linux/percpu.h> -#include <linux/percpu_counter.h> -#include <linux/u64_stats_sync.h> -#include <linux/seq_file.h> -#include <linux/radix-tree.h> -#include <linux/blkdev.h> -#include <linux/atomic.h> -#include <linux/kthread.h> -#include <linux/fs.h> +#include <linux/types.h> + +struct bio; +struct cgroup_subsys_state; +struct request_queue; #define FC_APPID_LEN 129 #ifdef CONFIG_BLK_CGROUP - -enum blkg_iostat_type { - BLKG_IOSTAT_READ, - BLKG_IOSTAT_WRITE, - BLKG_IOSTAT_DISCARD, - - BLKG_IOSTAT_NR, -}; - -struct blkcg_gq; -struct blkg_policy_data; - -struct blkcg { - struct cgroup_subsys_state css; - spinlock_t lock; - refcount_t online_pin; - - struct radix_tree_root blkg_tree; - struct blkcg_gq __rcu *blkg_hint; - struct hlist_head blkg_list; - - struct blkcg_policy_data *cpd[BLKCG_MAX_POLS]; - - struct list_head all_blkcgs_node; -#ifdef CONFIG_BLK_CGROUP_FC_APPID - char fc_app_id[FC_APPID_LEN]; -#endif -#ifdef CONFIG_CGROUP_WRITEBACK - struct list_head cgwb_list; -#endif -}; - -struct blkg_iostat { - u64 bytes[BLKG_IOSTAT_NR]; - u64 ios[BLKG_IOSTAT_NR]; -}; - -struct blkg_iostat_set { - struct u64_stats_sync sync; - struct blkg_iostat cur; - struct blkg_iostat last; -}; - -/* association between a blk cgroup and a request queue */ -struct blkcg_gq { - /* Pointer to the associated request_queue */ - struct request_queue *q; - struct list_head q_node; - struct hlist_node blkcg_node; - struct blkcg *blkcg; - - /* all non-root blkcg_gq's are guaranteed to have access to parent */ - struct blkcg_gq *parent; - - /* reference count */ - struct percpu_ref refcnt; - - /* is this blkg online? protected by both blkcg and q locks */ - bool online; - - struct blkg_iostat_set __percpu *iostat_cpu; - struct blkg_iostat_set iostat; - - struct blkg_policy_data *pd[BLKCG_MAX_POLS]; - - spinlock_t async_bio_lock; - struct bio_list async_bios; - union { - struct work_struct async_bio_work; - struct work_struct free_work; - }; - - atomic_t use_delay; - atomic64_t delay_nsec; - atomic64_t delay_start; - u64 last_delay; - int last_use; - - struct rcu_head rcu_head; -}; - extern struct cgroup_subsys_state * const blkcg_root_css; -void blkcg_destroy_blkgs(struct blkcg *blkcg); void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay); void blkcg_maybe_throttle_current(void); - -static inline struct blkcg *css_to_blkcg(struct cgroup_subsys_state *css) -{ - return css ? container_of(css, struct blkcg, css) : NULL; -} - -/** - * bio_blkcg - grab the blkcg associated with a bio - * @bio: target bio - * - * This returns the blkcg associated with a bio, %NULL if not associated. - * Callers are expected to either handle %NULL or know association has been - * done prior to calling this. - */ -static inline struct blkcg *bio_blkcg(struct bio *bio) -{ - if (bio && bio->bi_blkg) - return bio->bi_blkg->blkcg; - return NULL; -} - -static inline bool blk_cgroup_congested(void) -{ - struct cgroup_subsys_state *css; - bool ret = false; - - rcu_read_lock(); - css = kthread_blkcg(); - if (!css) - css = task_css(current, io_cgrp_id); - while (css) { - if (atomic_read(&css->cgroup->congestion_count)) { - ret = true; - break; - } - css = css->parent; - } - rcu_read_unlock(); - return ret; -} - -/** - * blkcg_parent - get the parent of a blkcg - * @blkcg: blkcg of interest - * - * Return the parent blkcg of @blkcg. Can be called anytime. - */ -static inline struct blkcg *blkcg_parent(struct blkcg *blkcg) -{ - return css_to_blkcg(blkcg->css.parent); -} - -/** - * blkcg_pin_online - pin online state - * @blkcg: blkcg of interest - * - * While pinned, a blkcg is kept online. This is primarily used to - * impedance-match blkg and cgwb lifetimes so that blkg doesn't go offline - * while an associated cgwb is still active. - */ -static inline void blkcg_pin_online(struct blkcg *blkcg) -{ - refcount_inc(&blkcg->online_pin); -} - -/** - * blkcg_unpin_online - unpin online state - * @blkcg: blkcg of interest - * - * This is primarily used to impedance-match blkg and cgwb lifetimes so - * that blkg doesn't go offline while an associated cgwb is still active. - * When this count goes to zero, all active cgwbs have finished so the - * blkcg can continue destruction by calling blkcg_destroy_blkgs(). - */ -static inline void blkcg_unpin_online(struct blkcg *blkcg) -{ - do { - if (!refcount_dec_and_test(&blkcg->online_pin)) - break; - blkcg_destroy_blkgs(blkcg); - blkcg = blkcg_parent(blkcg); - } while (blkcg); -} +bool blk_cgroup_congested(void); +void blkcg_pin_online(struct cgroup_subsys_state *blkcg_css); +void blkcg_unpin_online(struct cgroup_subsys_state *blkcg_css); +struct list_head *blkcg_get_cgwb_list(struct cgroup_subsys_state *css); +struct cgroup_subsys_state *bio_blkcg_css(struct bio *bio); #else /* CONFIG_BLK_CGROUP */ -struct blkcg { -}; - -struct blkcg_gq { -}; - #define blkcg_root_css ((struct cgroup_subsys_state *)ERR_PTR(-EINVAL)) static inline void blkcg_maybe_throttle_current(void) { } static inline bool blk_cgroup_congested(void) { return false; } - -#ifdef CONFIG_BLOCK static inline void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay) { } -static inline struct blkcg *bio_blkcg(struct bio *bio) { return NULL; } -#endif /* CONFIG_BLOCK */ - -#endif /* CONFIG_BLK_CGROUP */ - -#ifdef CONFIG_BLK_CGROUP_FC_APPID -/* - * Sets the fc_app_id field associted to blkcg - * @app_id: application identifier - * @cgrp_id: cgroup id - * @app_id_len: size of application identifier - */ -static inline int blkcg_set_fc_appid(char *app_id, u64 cgrp_id, size_t app_id_len) -{ - struct cgroup *cgrp; - struct cgroup_subsys_state *css; - struct blkcg *blkcg; - int ret = 0; - - if (app_id_len > FC_APPID_LEN) - return -EINVAL; - - cgrp = cgroup_get_from_id(cgrp_id); - if (!cgrp) - return -ENOENT; - css = cgroup_get_e_css(cgrp, &io_cgrp_subsys); - if (!css) { - ret = -ENOENT; - goto out_cgrp_put; - } - blkcg = css_to_blkcg(css); - /* - * There is a slight race condition on setting the appid. - * Worst case an I/O may not find the right id. - * This is no different from the I/O we let pass while obtaining - * the vmid from the fabric. - * Adding the overhead of a lock is not necessary. - */ - strlcpy(blkcg->fc_app_id, app_id, app_id_len); - css_put(css); -out_cgrp_put: - cgroup_put(cgrp); - return ret; -} - -/** - * blkcg_get_fc_appid - get the fc app identifier associated with a bio - * @bio: target bio - * - * On success return the fc_app_id, on failure return NULL - */ -static inline char *blkcg_get_fc_appid(struct bio *bio) +static inline struct cgroup_subsys_state *bio_blkcg_css(struct bio *bio) { - if (bio && bio->bi_blkg && - (bio->bi_blkg->blkcg->fc_app_id[0] != '\0')) - return bio->bi_blkg->blkcg->fc_app_id; return NULL; } -#else -static inline int blkcg_set_fc_appid(char *buf, u64 id, size_t len) { return -EINVAL; } -static inline char *blkcg_get_fc_appid(struct bio *bio) { return NULL; } -#endif /*CONFIG_BLK_CGROUP_FC_APPID*/ +#endif /* CONFIG_BLK_CGROUP */ + +int blkcg_set_fc_appid(char *app_id, u64 cgrp_id, size_t app_id_len); +char *blkcg_get_fc_appid(struct bio *bio); + #endif /* _BLK_CGROUP_H */ diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 7aa5c54901a9..9f07061418db 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -163,7 +163,6 @@ struct request { struct rb_node rb_node; /* sort/lookup */ struct bio_vec special_vec; void *completion_data; - int error_count; /* for legacy drivers, don't use */ }; diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 1973ef9bd40f..c007d58d2703 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -44,7 +44,7 @@ struct block_device { unsigned long bd_stamp; bool bd_read_only; /* read-only policy */ dev_t bd_dev; - int bd_openers; + atomic_t bd_openers; struct inode * bd_inode; /* will die */ struct super_block * bd_super; void * bd_claiming; @@ -246,9 +246,8 @@ typedef unsigned int blk_qc_t; struct bio { struct bio *bi_next; /* request queue link */ struct block_device *bi_bdev; - unsigned int bi_opf; /* bottom bits req flags, - * top bits REQ_OP. Use - * accessors. + unsigned int bi_opf; /* bottom bits REQ_OP, top bits + * req_flags. */ unsigned short bi_flags; /* BIO_* below */ unsigned short bi_ioprio; @@ -329,7 +328,6 @@ enum { BIO_QOS_MERGED, /* but went through rq_qos merge path */ BIO_REMAPPED, BIO_ZONE_WRITE_LOCKED, /* Owns a zoned device zone write lock */ - BIO_PERCPU_CACHE, /* can participate in per-cpu alloc cache */ BIO_FLAG_LAST }; @@ -409,15 +407,17 @@ enum req_flag_bits { * work item to avoid such priority inversions. */ __REQ_CGROUP_PUNT, + __REQ_POLLED, /* caller polls for completion using bio_poll */ + __REQ_ALLOC_CACHE, /* allocate IO from cache if available */ + __REQ_SWAP, /* swap I/O */ + __REQ_DRV, /* for driver use */ - /* command specific flags for REQ_OP_WRITE_ZEROES: */ + /* + * Command specific flags, keep last: + */ + /* for REQ_OP_WRITE_ZEROES: */ __REQ_NOUNMAP, /* do not free blocks when zeroing */ - __REQ_POLLED, /* caller polls for completion using bio_poll */ - - /* for driver use */ - __REQ_DRV, - __REQ_SWAP, /* swapping request. */ __REQ_NR_BITS, /* stops here */ }; @@ -439,6 +439,7 @@ enum req_flag_bits { #define REQ_NOUNMAP (1ULL << __REQ_NOUNMAP) #define REQ_POLLED (1ULL << __REQ_POLLED) +#define REQ_ALLOC_CACHE (1ULL << __REQ_ALLOC_CACHE) #define REQ_DRV (1ULL << __REQ_DRV) #define REQ_SWAP (1ULL << __REQ_SWAP) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 60d016138997..1b24c1fb3bb1 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -176,6 +176,21 @@ static inline bool disk_live(struct gendisk *disk) return !inode_unhashed(disk->part0->bd_inode); } +/** + * disk_openers - returns how many openers are there for a disk + * @disk: disk to check + * + * This returns the number of openers for a disk. Note that this value is only + * stable if disk->open_mutex is held. + * + * Note: Due to a quirk in the block layer open code, each open partition is + * only counted once even if there are multiple openers. + */ +static inline unsigned int disk_openers(struct gendisk *disk) +{ + return atomic_read(&disk->part0->bd_openers); +} + /* * The gendisk is refcounted by the part0 block_device, and the bd_device * therein is also used for device model presentation in sysfs. @@ -248,6 +263,7 @@ struct queue_limits { unsigned int io_opt; unsigned int max_discard_sectors; unsigned int max_hw_discard_sectors; + unsigned int max_secure_erase_sectors; unsigned int max_write_zeroes_sectors; unsigned int max_zone_append_sectors; unsigned int discard_granularity; @@ -540,10 +556,8 @@ struct request_queue { #define QUEUE_FLAG_NONROT 6 /* non-rotational device (SSD) */ #define QUEUE_FLAG_VIRT QUEUE_FLAG_NONROT /* paravirt device */ #define QUEUE_FLAG_IO_STAT 7 /* do disk/partitions IO accounting */ -#define QUEUE_FLAG_DISCARD 8 /* supports DISCARD */ #define QUEUE_FLAG_NOXMERGES 9 /* No extended merges */ #define QUEUE_FLAG_ADD_RANDOM 10 /* Contributes to random pool */ -#define QUEUE_FLAG_SECERASE 11 /* supports secure erase */ #define QUEUE_FLAG_SAME_FORCE 12 /* force complete on same CPU */ #define QUEUE_FLAG_DEAD 13 /* queue tear-down finished */ #define QUEUE_FLAG_INIT_DONE 14 /* queue is initialized */ @@ -582,11 +596,8 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q); test_bit(QUEUE_FLAG_STABLE_WRITES, &(q)->queue_flags) #define blk_queue_io_stat(q) test_bit(QUEUE_FLAG_IO_STAT, &(q)->queue_flags) #define blk_queue_add_random(q) test_bit(QUEUE_FLAG_ADD_RANDOM, &(q)->queue_flags) -#define blk_queue_discard(q) test_bit(QUEUE_FLAG_DISCARD, &(q)->queue_flags) #define blk_queue_zone_resetall(q) \ test_bit(QUEUE_FLAG_ZONE_RESETALL, &(q)->queue_flags) -#define blk_queue_secure_erase(q) \ - (test_bit(QUEUE_FLAG_SECERASE, &(q)->queue_flags)) #define blk_queue_dax(q) test_bit(QUEUE_FLAG_DAX, &(q)->queue_flags) #define blk_queue_pci_p2pdma(q) \ test_bit(QUEUE_FLAG_PCI_P2PDMA, &(q)->queue_flags) @@ -602,7 +613,6 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q); REQ_FAILFAST_DRIVER)) #define blk_queue_quiesced(q) test_bit(QUEUE_FLAG_QUIESCED, &(q)->queue_flags) #define blk_queue_pm_only(q) atomic_read(&(q)->pm_only) -#define blk_queue_fua(q) test_bit(QUEUE_FLAG_FUA, &(q)->queue_flags) #define blk_queue_registered(q) test_bit(QUEUE_FLAG_REGISTERED, &(q)->queue_flags) #define blk_queue_nowait(q) test_bit(QUEUE_FLAG_NOWAIT, &(q)->queue_flags) @@ -950,6 +960,8 @@ extern void blk_queue_chunk_sectors(struct request_queue *, unsigned int); extern void blk_queue_max_segments(struct request_queue *, unsigned short); extern void blk_queue_max_discard_segments(struct request_queue *, unsigned short); +void blk_queue_max_secure_erase_sectors(struct request_queue *q, + unsigned int max_sectors); extern void blk_queue_max_segment_size(struct request_queue *, unsigned int); extern void blk_queue_max_discard_sectors(struct request_queue *q, unsigned int max_discard_sectors); @@ -1090,13 +1102,12 @@ static inline long nr_blockdev_pages(void) extern void blk_io_schedule(void); -#define BLKDEV_DISCARD_SECURE (1 << 0) /* issue a secure erase */ - -extern int blkdev_issue_discard(struct block_device *bdev, sector_t sector, - sector_t nr_sects, gfp_t gfp_mask, unsigned long flags); -extern int __blkdev_issue_discard(struct block_device *bdev, sector_t sector, - sector_t nr_sects, gfp_t gfp_mask, int flags, - struct bio **biop); +int blkdev_issue_discard(struct block_device *bdev, sector_t sector, + sector_t nr_sects, gfp_t gfp_mask); +int __blkdev_issue_discard(struct block_device *bdev, sector_t sector, + sector_t nr_sects, gfp_t gfp_mask, struct bio **biop); +int blkdev_issue_secure_erase(struct block_device *bdev, sector_t sector, + sector_t nr_sects, gfp_t gfp); #define BLKDEV_ZERO_NOUNMAP (1 << 0) /* do not free blocks */ #define BLKDEV_ZERO_NOFALLBACK (1 << 1) /* don't write explicit zeroes */ @@ -1115,7 +1126,7 @@ static inline int sb_issue_discard(struct super_block *sb, sector_t block, SECTOR_SHIFT), nr_blocks << (sb->s_blocksize_bits - SECTOR_SHIFT), - gfp_mask, flags); + gfp_mask); } static inline int sb_issue_zeroout(struct super_block *sb, sector_t block, sector_t nr_blocks, gfp_t gfp_mask) @@ -1189,6 +1200,12 @@ static inline unsigned int queue_max_zone_append_sectors(const struct request_qu return min(l->max_zone_append_sectors, l->max_sectors); } +static inline unsigned int +bdev_max_zone_append_sectors(struct block_device *bdev) +{ + return queue_max_zone_append_sectors(bdev_get_queue(bdev)); +} + static inline unsigned queue_logical_block_size(const struct request_queue *q) { int retval = 512; @@ -1246,84 +1263,54 @@ bdev_zone_write_granularity(struct block_device *bdev) return queue_zone_write_granularity(bdev_get_queue(bdev)); } -static inline int queue_alignment_offset(const struct request_queue *q) -{ - if (q->limits.misaligned) - return -1; +int bdev_alignment_offset(struct block_device *bdev); +unsigned int bdev_discard_alignment(struct block_device *bdev); - return q->limits.alignment_offset; +static inline unsigned int bdev_max_discard_sectors(struct block_device *bdev) +{ + return bdev_get_queue(bdev)->limits.max_discard_sectors; } -static inline int queue_limit_alignment_offset(struct queue_limits *lim, sector_t sector) +static inline unsigned int bdev_discard_granularity(struct block_device *bdev) { - unsigned int granularity = max(lim->physical_block_size, lim->io_min); - unsigned int alignment = sector_div(sector, granularity >> SECTOR_SHIFT) - << SECTOR_SHIFT; + return bdev_get_queue(bdev)->limits.discard_granularity; +} - return (granularity + lim->alignment_offset - alignment) % granularity; +static inline unsigned int +bdev_max_secure_erase_sectors(struct block_device *bdev) +{ + return bdev_get_queue(bdev)->limits.max_secure_erase_sectors; } -static inline int bdev_alignment_offset(struct block_device *bdev) +static inline unsigned int bdev_write_zeroes_sectors(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); - if (q->limits.misaligned) - return -1; - if (bdev_is_partition(bdev)) - return queue_limit_alignment_offset(&q->limits, - bdev->bd_start_sect); - return q->limits.alignment_offset; + if (q) + return q->limits.max_write_zeroes_sectors; + + return 0; } -static inline int queue_discard_alignment(const struct request_queue *q) +static inline bool bdev_nonrot(struct block_device *bdev) { - if (q->limits.discard_misaligned) - return -1; - - return q->limits.discard_alignment; + return blk_queue_nonrot(bdev_get_queue(bdev)); } -static inline int queue_limit_discard_alignment(struct queue_limits *lim, sector_t sector) +static inline bool bdev_stable_writes(struct block_device *bdev) { - unsigned int alignment, granularity, offset; - - if (!lim->max_discard_sectors) - return 0; - - /* Why are these in bytes, not sectors? */ - alignment = lim->discard_alignment >> SECTOR_SHIFT; - granularity = lim->discard_granularity >> SECTOR_SHIFT; - if (!granularity) - return 0; - - /* Offset of the partition start in 'granularity' sectors */ - offset = sector_div(sector, granularity); - - /* And why do we do this modulus *again* in blkdev_issue_discard()? */ - offset = (granularity + alignment - offset) % granularity; - - /* Turn it back into bytes, gaah */ - return offset << SECTOR_SHIFT; + return test_bit(QUEUE_FLAG_STABLE_WRITES, + &bdev_get_queue(bdev)->queue_flags); } -static inline int bdev_discard_alignment(struct block_device *bdev) +static inline bool bdev_write_cache(struct block_device *bdev) { - struct request_queue *q = bdev_get_queue(bdev); - - if (bdev_is_partition(bdev)) - return queue_limit_discard_alignment(&q->limits, - bdev->bd_start_sect); - return q->limits.discard_alignment; + return test_bit(QUEUE_FLAG_WC, &bdev_get_queue(bdev)->queue_flags); } -static inline unsigned int bdev_write_zeroes_sectors(struct block_device *bdev) +static inline bool bdev_fua(struct block_device *bdev) { - struct request_queue *q = bdev_get_queue(bdev); - - if (q) - return q->limits.max_write_zeroes_sectors; - - return 0; + return test_bit(QUEUE_FLAG_FUA, &bdev_get_queue(bdev)->queue_flags); } static inline enum blk_zoned_model bdev_zoned_model(struct block_device *bdev) @@ -1491,9 +1478,10 @@ static inline void blk_wake_io_task(struct task_struct *waiter) wake_up_process(waiter); } -unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors, - unsigned int op); -void disk_end_io_acct(struct gendisk *disk, unsigned int op, +unsigned long bdev_start_io_acct(struct block_device *bdev, + unsigned int sectors, unsigned int op, + unsigned long start_time); +void bdev_end_io_acct(struct block_device *bdev, unsigned int op, unsigned long start_time); void bio_start_io_acct_time(struct bio *bio, unsigned long start_time); @@ -1547,6 +1535,7 @@ int truncate_bdev_range(struct block_device *bdev, fmode_t mode, loff_t lstart, #ifdef CONFIG_BLOCK void invalidate_bdev(struct block_device *bdev); int sync_blockdev(struct block_device *bdev); +int sync_blockdev_range(struct block_device *bdev, loff_t lstart, loff_t lend); int sync_blockdev_nowait(struct block_device *bdev); void sync_bdevs(bool wait); void printk_all_partitions(void); diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index 22501a293fa5..623e22492afa 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -27,12 +27,10 @@ struct blk_trace { atomic_t dropped; }; -struct blkcg; - extern int blk_trace_ioctl(struct block_device *, unsigned, char __user *); extern void blk_trace_shutdown(struct request_queue *); -extern __printf(3, 4) -void __trace_note_message(struct blk_trace *, struct blkcg *blkcg, const char *fmt, ...); +__printf(3, 4) void __blk_trace_note_message(struct blk_trace *bt, + struct cgroup_subsys_state *css, const char *fmt, ...); /** * blk_add_trace_msg - Add a (simple) message to the blktrace stream @@ -47,14 +45,14 @@ void __trace_note_message(struct blk_trace *, struct blkcg *blkcg, const char *f * NOTE: Can not use 'static inline' due to presence of var args... * **/ -#define blk_add_cgroup_trace_msg(q, cg, fmt, ...) \ +#define blk_add_cgroup_trace_msg(q, css, fmt, ...) \ do { \ struct blk_trace *bt; \ \ rcu_read_lock(); \ bt = rcu_dereference((q)->blk_trace); \ if (unlikely(bt)) \ - __trace_note_message(bt, cg, fmt, ##__VA_ARGS__);\ + __blk_trace_note_message(bt, css, fmt, ##__VA_ARGS__);\ rcu_read_unlock(); \ } while (0) #define blk_add_trace_msg(q, fmt, ...) \ diff --git a/include/linux/bpf.h b/include/linux/bpf.h index bdb5298735ce..ecc3d3ec41cf 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2085,6 +2085,8 @@ void bpf_offload_dev_netdev_unregister(struct bpf_offload_dev *offdev, struct net_device *netdev); bool bpf_offload_dev_match(struct bpf_prog *prog, struct net_device *netdev); +void unpriv_ebpf_notify(int new_state); + #if defined(CONFIG_NET) && defined(CONFIG_BPF_SYSCALL) int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr); diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index c1fc4af47f69..3a9d2d7cc6b7 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -570,9 +570,11 @@ static inline u32 type_flag(u32 type) return type & ~BPF_BASE_TYPE_MASK; } +/* only use after check_attach_btf_id() */ static inline enum bpf_prog_type resolve_prog_type(struct bpf_prog *prog) { - return prog->aux->dst_prog ? prog->aux->dst_prog->type : prog->type; + return prog->type == BPF_PROG_TYPE_EXT ? + prog->aux->dst_prog->type : prog->type; } #endif /* _LINUX_BPF_VERIFIER_H */ diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index bcb4fe9b8575..c9d1463bb20f 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -146,7 +146,7 @@ BUFFER_FNS(Defer_Completion, defer_completion) #define page_has_buffers(page) PagePrivate(page) #define folio_buffers(folio) folio_get_private(folio) -void buffer_check_dirty_writeback(struct page *page, +void buffer_check_dirty_writeback(struct folio *folio, bool *dirty, bool *writeback); /* @@ -158,7 +158,7 @@ void mark_buffer_write_io_error(struct buffer_head *bh); void touch_buffer(struct buffer_head *bh); void set_bh_page(struct buffer_head *bh, struct page *page, unsigned long offset); -int try_to_free_buffers(struct page *); +bool try_to_free_buffers(struct folio *); struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size, bool retry); void create_empty_buffers(struct page *, unsigned long, @@ -223,10 +223,10 @@ int block_write_full_page(struct page *page, get_block_t *get_block, int __block_write_full_page(struct inode *inode, struct page *page, get_block_t *get_block, struct writeback_control *wbc, bh_end_io_t *handler); -int block_read_full_page(struct page*, get_block_t*); +int block_read_full_folio(struct folio *, get_block_t *); bool block_is_partially_uptodate(struct folio *, size_t from, size_t count); int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len, - unsigned flags, struct page **pagep, get_block_t *get_block); + struct page **pagep, get_block_t *get_block); int __block_write_begin(struct page *page, loff_t pos, unsigned len, get_block_t *get_block); int block_write_end(struct file *, struct address_space *, @@ -238,7 +238,7 @@ int generic_write_end(struct file *, struct address_space *, void page_zero_new_buffers(struct page *page, unsigned from, unsigned to); void clean_page_buffers(struct page *page); int cont_write_begin(struct file *, struct address_space *, loff_t, - unsigned, unsigned, struct page **, void **, + unsigned, struct page **, void **, get_block_t *, loff_t *); int generic_cont_expand_simple(struct inode *inode, loff_t size); int block_commit_write(struct page *page, unsigned from, unsigned to); @@ -258,7 +258,7 @@ static inline vm_fault_t block_page_mkwrite_return(int err) } sector_t generic_block_bmap(struct address_space *, sector_t, get_block_t *); int block_truncate_page(struct address_space *, loff_t, get_block_t *); -int nobh_write_begin(struct address_space *, loff_t, unsigned, unsigned, +int nobh_write_begin(struct address_space *, loff_t, unsigned len, struct page **, void **, get_block_t*); int nobh_write_end(struct file *, struct address_space *, loff_t, unsigned, unsigned, @@ -402,7 +402,7 @@ bool block_dirty_folio(struct address_space *mapping, struct folio *folio); #else /* CONFIG_BLOCK */ static inline void buffer_init(void) {} -static inline int try_to_free_buffers(struct page *page) { return 1; } +static inline bool try_to_free_buffers(struct folio *folio) { return true; } static inline int inode_has_buffers(struct inode *inode) { return 0; } static inline void invalidate_inode_buffers(struct inode *inode) {} static inline int remove_inode_buffers(struct inode *inode) { return 1; } diff --git a/include/linux/cc_platform.h b/include/linux/cc_platform.h index efd8205282da..cb0d6cd1c12f 100644 --- a/include/linux/cc_platform.h +++ b/include/linux/cc_platform.h @@ -72,6 +72,24 @@ enum cc_attr { * Examples include TDX guest & SEV. */ CC_ATTR_GUEST_UNROLL_STRING_IO, + + /** + * @CC_ATTR_SEV_SNP: Guest SNP is active. + * + * The platform/OS is running as a guest/virtual machine and actively + * using AMD SEV-SNP features. + */ + CC_ATTR_GUEST_SEV_SNP, + + /** + * @CC_ATTR_HOTPLUG_DISABLED: Hotplug is not supported or disabled. + * + * The platform/OS is running as a guest/virtual machine does not + * support CPU hotplug feature. + * + * Examples include TDX Guest. + */ + CC_ATTR_HOTPLUG_DISABLED, }; #ifdef CONFIG_ARCH_HAS_CC_PLATFORM diff --git a/include/linux/cdrom.h b/include/linux/cdrom.h index 0a89f111e00e..67caa909e3e6 100644 --- a/include/linux/cdrom.h +++ b/include/linux/cdrom.h @@ -77,7 +77,6 @@ struct cdrom_device_ops { int (*tray_move) (struct cdrom_device_info *, int); int (*lock_door) (struct cdrom_device_info *, int); int (*select_speed) (struct cdrom_device_info *, int); - int (*select_disc) (struct cdrom_device_info *, int); int (*get_last_session) (struct cdrom_device_info *, struct cdrom_multisession *); int (*get_mcn) (struct cdrom_device_info *, diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 3431011f364d..cba8a6ffc329 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -287,6 +287,9 @@ struct ceph_osd_linger_request { rados_watcherrcb_t errcb; void *data; + struct ceph_pagelist *request_pl; + struct page **notify_id_pages; + struct page ***preply_pages; size_t *preply_len; }; diff --git a/include/linux/compat.h b/include/linux/compat.h index 1c758b0e0359..01fddf72a81f 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -235,6 +235,7 @@ typedef struct compat_siginfo { struct { compat_ulong_t _data; u32 _type; + u32 _flags; } _perf; }; } _sigfault; diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index babb1347148c..c84fec767445 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -69,6 +69,16 @@ #define __nocfi __attribute__((__no_sanitize__("cfi"))) #define __cficanonical __attribute__((__cfi_canonical_jump_table__)) +#if defined(CONFIG_CFI_CLANG) +/* + * With CONFIG_CFI_CLANG, the compiler replaces function address + * references with the address of the function's CFI jump table + * entry. The function_nocfi macro always returns the address of the + * actual function instead. + */ +#define function_nocfi(x) __builtin_function_start(x) +#endif + /* * Turn individual warnings and errors on and off locally, depending * on version. diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 52299c957c98..a0c55eeaeaf1 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -66,14 +66,6 @@ __builtin_unreachable(); \ } while (0) -#if defined(RANDSTRUCT_PLUGIN) && !defined(__CHECKER__) -#define __randomize_layout __attribute__((randomize_layout)) -#define __no_randomize_layout __attribute__((no_randomize_layout)) -/* This anon struct can add padding, so only enable it under randstruct. */ -#define randomized_struct_fields_start struct { -#define randomized_struct_fields_end } __randomize_layout; -#endif - /* * GCC 'asm goto' miscompiles certain code sequences: * diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 219aa5ddbc73..01ce94b58b42 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -109,7 +109,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, #endif /* Unreachable code */ -#ifdef CONFIG_STACK_VALIDATION +#ifdef CONFIG_OBJTOOL /* * These macros help objtool understand GCC code flow for unreachable code. * The __COUNTER__ based labels are a hack to make each instance of the macros @@ -128,10 +128,10 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, /* Annotate a C jump table to allow objtool to follow the code flow */ #define __annotate_jump_table __section(".rodata..c_jump_table") -#else +#else /* !CONFIG_OBJTOOL */ #define annotate_unreachable() #define __annotate_jump_table -#endif +#endif /* CONFIG_OBJTOOL */ #ifndef unreachable # define unreachable() do { \ diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 1c2c33ae1b37..d08dfcb0ac68 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -242,15 +242,15 @@ struct ftrace_likely_data { # define __latent_entropy #endif -#ifndef __randomize_layout +#if defined(RANDSTRUCT) && !defined(__CHECKER__) +# define __randomize_layout __designated_init __attribute__((randomize_layout)) +# define __no_randomize_layout __attribute__((no_randomize_layout)) +/* This anon struct can add padding, so only enable it under randstruct. */ +# define randomized_struct_fields_start struct { +# define randomized_struct_fields_end } __randomize_layout; +#else # define __randomize_layout __designated_init -#endif - -#ifndef __no_randomize_layout # define __no_randomize_layout -#endif - -#ifndef randomized_struct_fields_start # define randomized_struct_fields_start # define randomized_struct_fields_end #endif diff --git a/include/linux/console.h b/include/linux/console.h index 7cd758a4f44e..143653090c48 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -16,6 +16,7 @@ #include <linux/atomic.h> #include <linux/types.h> +#include <linux/mutex.h> struct vc_data; struct console_font_op; @@ -151,6 +152,24 @@ struct console { int cflag; uint ispeed; uint ospeed; + u64 seq; + unsigned long dropped; + struct task_struct *thread; + bool blocked; + + /* + * The per-console lock is used by printing kthreads to synchronize + * this console with callers of console_lock(). This is necessary in + * order to allow printing kthreads to run in parallel to each other, + * while each safely accessing the @blocked field and synchronizing + * against direct printing via console_lock/console_unlock. + * + * Note: For synchronizing against direct printing via + * console_trylock/console_unlock, see the static global + * variable @console_kthreads_active. + */ + struct mutex lock; + void *data; struct console *next; }; diff --git a/include/linux/cper.h b/include/linux/cper.h index 6a511a1078ca..eacb7dd7b3af 100644 --- a/include/linux/cper.h +++ b/include/linux/cper.h @@ -558,6 +558,7 @@ extern const char *const cper_proc_error_type_strs[4]; u64 cper_next_record_id(void); const char *cper_severity_str(unsigned int); const char *cper_mem_err_type_str(unsigned int); +const char *cper_mem_err_status_str(u64 status); void cper_print_bits(const char *prefix, unsigned int bits, const char * const strs[], unsigned int strs_size); void cper_mem_err_pack(const struct cper_sec_mem_err *, @@ -568,5 +569,7 @@ void cper_print_proc_arm(const char *pfx, const struct cper_sec_proc_arm *proc); void cper_print_proc_ia(const char *pfx, const struct cper_sec_proc_ia *proc); +int cper_mem_err_location(struct cper_mem_err_compact *mem, char *msg); +int cper_dimm_err_location(struct cper_mem_err_compact *mem, char *msg); #endif diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 9cf51e41e697..54dc2f9a2d56 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -167,7 +167,7 @@ static inline int suspend_disable_secondary_cpus(void) { return 0; } static inline void suspend_enable_secondary_cpus(void) { } #endif /* !CONFIG_PM_SLEEP_SMP */ -void cpu_startup_entry(enum cpuhp_state state); +void __noreturn cpu_startup_entry(enum cpuhp_state state); void cpu_idle_poll_ctrl(bool enable); diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 35c7d6db4139..d5595d57f4e5 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -1199,7 +1199,6 @@ static inline void sched_cpufreq_governor_change(struct cpufreq_policy *policy, struct cpufreq_governor *old_gov) { } #endif -extern void arch_freq_prepare_all(void); extern unsigned int arch_freq_get_on_cpu(int cpu); #ifndef arch_set_freq_scale diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 82e33137f917..b66c5f389159 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -222,6 +222,7 @@ enum cpuhp_state { CPUHP_AP_PERF_S390_SF_ONLINE, CPUHP_AP_PERF_ARM_CCI_ONLINE, CPUHP_AP_PERF_ARM_CCN_ONLINE, + CPUHP_AP_PERF_ARM_HISI_CPA_ONLINE, CPUHP_AP_PERF_ARM_HISI_DDRC_ONLINE, CPUHP_AP_PERF_ARM_HISI_HHA_ONLINE, CPUHP_AP_PERF_ARM_HISI_L3_ONLINE, diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h index 142474b4af96..dc10bee75a72 100644 --- a/include/linux/devfreq.h +++ b/include/linux/devfreq.h @@ -38,6 +38,7 @@ enum devfreq_timer { struct devfreq; struct devfreq_governor; +struct devfreq_cpu_data; struct thermal_cooling_device; /** @@ -288,6 +289,11 @@ struct devfreq_simple_ondemand_data { #endif #if IS_ENABLED(CONFIG_DEVFREQ_GOV_PASSIVE) +enum devfreq_parent_dev_type { + DEVFREQ_PARENT_DEV, + CPUFREQ_PARENT_DEV, +}; + /** * struct devfreq_passive_data - ``void *data`` fed to struct devfreq * and devfreq_add_device @@ -299,8 +305,11 @@ struct devfreq_simple_ondemand_data { * using governors except for passive governor. * If the devfreq device has the specific method to decide * the next frequency, should use this callback. - * @this: the devfreq instance of own device. - * @nb: the notifier block for DEVFREQ_TRANSITION_NOTIFIER list + * @parent_type: the parent type of the device. + * @this: the devfreq instance of own device. + * @nb: the notifier block for DEVFREQ_TRANSITION_NOTIFIER or + * CPUFREQ_TRANSITION_NOTIFIER list. + * @cpu_data_list: the list of cpu frequency data for all cpufreq_policy. * * The devfreq_passive_data have to set the devfreq instance of parent * device with governors except for the passive governor. But, don't need to @@ -314,9 +323,13 @@ struct devfreq_passive_data { /* Optional callback to decide the next frequency of passvice device */ int (*get_target_freq)(struct devfreq *this, unsigned long *freq); + /* Should set the type of parent device */ + enum devfreq_parent_dev_type parent_type; + /* For passive governor's internal use. Don't need to set them */ struct devfreq *this; struct notifier_block nb; + struct list_head cpu_data_list; }; #endif diff --git a/include/linux/dma-buf-map.h b/include/linux/dma-buf-map.h deleted file mode 100644 index 19fa0b5ae5ec..000000000000 --- a/include/linux/dma-buf-map.h +++ /dev/null @@ -1,266 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Pointer to dma-buf-mapped memory, plus helpers. - */ - -#ifndef __DMA_BUF_MAP_H__ -#define __DMA_BUF_MAP_H__ - -#include <linux/io.h> -#include <linux/string.h> - -/** - * DOC: overview - * - * Calling dma-buf's vmap operation returns a pointer to the buffer's memory. - * Depending on the location of the buffer, users may have to access it with - * I/O operations or memory load/store operations. For example, copying to - * system memory could be done with memcpy(), copying to I/O memory would be - * done with memcpy_toio(). - * - * .. code-block:: c - * - * void *vaddr = ...; // pointer to system memory - * memcpy(vaddr, src, len); - * - * void *vaddr_iomem = ...; // pointer to I/O memory - * memcpy_toio(vaddr, _iomem, src, len); - * - * When using dma-buf's vmap operation, the returned pointer is encoded as - * :c:type:`struct dma_buf_map <dma_buf_map>`. - * :c:type:`struct dma_buf_map <dma_buf_map>` stores the buffer's address in - * system or I/O memory and a flag that signals the required method of - * accessing the buffer. Use the returned instance and the helper functions - * to access the buffer's memory in the correct way. - * - * The type :c:type:`struct dma_buf_map <dma_buf_map>` and its helpers are - * actually independent from the dma-buf infrastructure. When sharing buffers - * among devices, drivers have to know the location of the memory to access - * the buffers in a safe way. :c:type:`struct dma_buf_map <dma_buf_map>` - * solves this problem for dma-buf and its users. If other drivers or - * sub-systems require similar functionality, the type could be generalized - * and moved to a more prominent header file. - * - * Open-coding access to :c:type:`struct dma_buf_map <dma_buf_map>` is - * considered bad style. Rather then accessing its fields directly, use one - * of the provided helper functions, or implement your own. For example, - * instances of :c:type:`struct dma_buf_map <dma_buf_map>` can be initialized - * statically with DMA_BUF_MAP_INIT_VADDR(), or at runtime with - * dma_buf_map_set_vaddr(). These helpers will set an address in system memory. - * - * .. code-block:: c - * - * struct dma_buf_map map = DMA_BUF_MAP_INIT_VADDR(0xdeadbeaf); - * - * dma_buf_map_set_vaddr(&map, 0xdeadbeaf); - * - * To set an address in I/O memory, use dma_buf_map_set_vaddr_iomem(). - * - * .. code-block:: c - * - * dma_buf_map_set_vaddr_iomem(&map, 0xdeadbeaf); - * - * Instances of struct dma_buf_map do not have to be cleaned up, but - * can be cleared to NULL with dma_buf_map_clear(). Cleared mappings - * always refer to system memory. - * - * .. code-block:: c - * - * dma_buf_map_clear(&map); - * - * Test if a mapping is valid with either dma_buf_map_is_set() or - * dma_buf_map_is_null(). - * - * .. code-block:: c - * - * if (dma_buf_map_is_set(&map) != dma_buf_map_is_null(&map)) - * // always true - * - * Instances of :c:type:`struct dma_buf_map <dma_buf_map>` can be compared - * for equality with dma_buf_map_is_equal(). Mappings the point to different - * memory spaces, system or I/O, are never equal. That's even true if both - * spaces are located in the same address space, both mappings contain the - * same address value, or both mappings refer to NULL. - * - * .. code-block:: c - * - * struct dma_buf_map sys_map; // refers to system memory - * struct dma_buf_map io_map; // refers to I/O memory - * - * if (dma_buf_map_is_equal(&sys_map, &io_map)) - * // always false - * - * A set up instance of struct dma_buf_map can be used to access or manipulate - * the buffer memory. Depending on the location of the memory, the provided - * helpers will pick the correct operations. Data can be copied into the memory - * with dma_buf_map_memcpy_to(). The address can be manipulated with - * dma_buf_map_incr(). - * - * .. code-block:: c - * - * const void *src = ...; // source buffer - * size_t len = ...; // length of src - * - * dma_buf_map_memcpy_to(&map, src, len); - * dma_buf_map_incr(&map, len); // go to first byte after the memcpy - */ - -/** - * struct dma_buf_map - Pointer to vmap'ed dma-buf memory. - * @vaddr_iomem: The buffer's address if in I/O memory - * @vaddr: The buffer's address if in system memory - * @is_iomem: True if the dma-buf memory is located in I/O - * memory, or false otherwise. - */ -struct dma_buf_map { - union { - void __iomem *vaddr_iomem; - void *vaddr; - }; - bool is_iomem; -}; - -/** - * DMA_BUF_MAP_INIT_VADDR - Initializes struct dma_buf_map to an address in system memory - * @vaddr_: A system-memory address - */ -#define DMA_BUF_MAP_INIT_VADDR(vaddr_) \ - { \ - .vaddr = (vaddr_), \ - .is_iomem = false, \ - } - -/** - * dma_buf_map_set_vaddr - Sets a dma-buf mapping structure to an address in system memory - * @map: The dma-buf mapping structure - * @vaddr: A system-memory address - * - * Sets the address and clears the I/O-memory flag. - */ -static inline void dma_buf_map_set_vaddr(struct dma_buf_map *map, void *vaddr) -{ - map->vaddr = vaddr; - map->is_iomem = false; -} - -/** - * dma_buf_map_set_vaddr_iomem - Sets a dma-buf mapping structure to an address in I/O memory - * @map: The dma-buf mapping structure - * @vaddr_iomem: An I/O-memory address - * - * Sets the address and the I/O-memory flag. - */ -static inline void dma_buf_map_set_vaddr_iomem(struct dma_buf_map *map, - void __iomem *vaddr_iomem) -{ - map->vaddr_iomem = vaddr_iomem; - map->is_iomem = true; -} - -/** - * dma_buf_map_is_equal - Compares two dma-buf mapping structures for equality - * @lhs: The dma-buf mapping structure - * @rhs: A dma-buf mapping structure to compare with - * - * Two dma-buf mapping structures are equal if they both refer to the same type of memory - * and to the same address within that memory. - * - * Returns: - * True is both structures are equal, or false otherwise. - */ -static inline bool dma_buf_map_is_equal(const struct dma_buf_map *lhs, - const struct dma_buf_map *rhs) -{ - if (lhs->is_iomem != rhs->is_iomem) - return false; - else if (lhs->is_iomem) - return lhs->vaddr_iomem == rhs->vaddr_iomem; - else - return lhs->vaddr == rhs->vaddr; -} - -/** - * dma_buf_map_is_null - Tests for a dma-buf mapping to be NULL - * @map: The dma-buf mapping structure - * - * Depending on the state of struct dma_buf_map.is_iomem, tests if the - * mapping is NULL. - * - * Returns: - * True if the mapping is NULL, or false otherwise. - */ -static inline bool dma_buf_map_is_null(const struct dma_buf_map *map) -{ - if (map->is_iomem) - return !map->vaddr_iomem; - return !map->vaddr; -} - -/** - * dma_buf_map_is_set - Tests is the dma-buf mapping has been set - * @map: The dma-buf mapping structure - * - * Depending on the state of struct dma_buf_map.is_iomem, tests if the - * mapping has been set. - * - * Returns: - * True if the mapping is been set, or false otherwise. - */ -static inline bool dma_buf_map_is_set(const struct dma_buf_map *map) -{ - return !dma_buf_map_is_null(map); -} - -/** - * dma_buf_map_clear - Clears a dma-buf mapping structure - * @map: The dma-buf mapping structure - * - * Clears all fields to zero; including struct dma_buf_map.is_iomem. So - * mapping structures that were set to point to I/O memory are reset for - * system memory. Pointers are cleared to NULL. This is the default. - */ -static inline void dma_buf_map_clear(struct dma_buf_map *map) -{ - if (map->is_iomem) { - map->vaddr_iomem = NULL; - map->is_iomem = false; - } else { - map->vaddr = NULL; - } -} - -/** - * dma_buf_map_memcpy_to - Memcpy into dma-buf mapping - * @dst: The dma-buf mapping structure - * @src: The source buffer - * @len: The number of byte in src - * - * Copies data into a dma-buf mapping. The source buffer is in system - * memory. Depending on the buffer's location, the helper picks the correct - * method of accessing the memory. - */ -static inline void dma_buf_map_memcpy_to(struct dma_buf_map *dst, const void *src, size_t len) -{ - if (dst->is_iomem) - memcpy_toio(dst->vaddr_iomem, src, len); - else - memcpy(dst->vaddr, src, len); -} - -/** - * dma_buf_map_incr - Increments the address stored in a dma-buf mapping - * @map: The dma-buf mapping structure - * @incr: The number of bytes to increment - * - * Increments the address stored in a dma-buf mapping. Depending on the - * buffer's location, the correct value will be updated. - */ -static inline void dma_buf_map_incr(struct dma_buf_map *map, size_t incr) -{ - if (map->is_iomem) - map->vaddr_iomem += incr; - else - map->vaddr += incr; -} - -#endif /* __DMA_BUF_MAP_H__ */ diff --git a/include/linux/dma-fence-array.h b/include/linux/dma-fence-array.h index fec374f69e12..ec7f25def392 100644 --- a/include/linux/dma-fence-array.h +++ b/include/linux/dma-fence-array.h @@ -61,6 +61,21 @@ to_dma_fence_array(struct dma_fence *fence) return container_of(fence, struct dma_fence_array, base); } +/** + * dma_fence_array_for_each - iterate over all fences in array + * @fence: current fence + * @index: index into the array + * @head: potential dma_fence_array object + * + * Test if @array is a dma_fence_array object and if yes iterate over all fences + * in the array. If not just iterate over the fence in @array itself. + * + * For a deep dive iterator see dma_fence_unwrap_for_each(). + */ +#define dma_fence_array_for_each(fence, index, head) \ + for (index = 0, fence = dma_fence_array_first(head); fence; \ + ++(index), fence = dma_fence_array_next(head, index)) + struct dma_fence_array *dma_fence_array_create(int num_fences, struct dma_fence **fences, u64 context, unsigned seqno, @@ -68,4 +83,8 @@ struct dma_fence_array *dma_fence_array_create(int num_fences, bool dma_fence_match_context(struct dma_fence *fence, u64 context); +struct dma_fence *dma_fence_array_first(struct dma_fence *head); +struct dma_fence *dma_fence_array_next(struct dma_fence *head, + unsigned int index); + #endif /* __LINUX_DMA_FENCE_ARRAY_H */ diff --git a/include/linux/dma-fence-chain.h b/include/linux/dma-fence-chain.h index 10d51bcdf7b7..4bdf0b96da28 100644 --- a/include/linux/dma-fence-chain.h +++ b/include/linux/dma-fence-chain.h @@ -112,6 +112,8 @@ static inline void dma_fence_chain_free(struct dma_fence_chain *chain) * * Iterate over all fences in the chain. We keep a reference to the current * fence while inside the loop which must be dropped when breaking out. + * + * For a deep dive iterator see dma_fence_unwrap_for_each(). */ #define dma_fence_chain_for_each(iter, head) \ for (iter = dma_fence_get(head); iter; \ diff --git a/include/linux/dma-fence-unwrap.h b/include/linux/dma-fence-unwrap.h new file mode 100644 index 000000000000..77e335a1bcac --- /dev/null +++ b/include/linux/dma-fence-unwrap.h @@ -0,0 +1,95 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * fence-chain: chain fences together in a timeline + * + * Copyright (C) 2022 Advanced Micro Devices, Inc. + * Authors: + * Christian König <christian.koenig@amd.com> + */ + +#ifndef __LINUX_DMA_FENCE_UNWRAP_H +#define __LINUX_DMA_FENCE_UNWRAP_H + +#include <linux/dma-fence-chain.h> +#include <linux/dma-fence-array.h> + +/** + * struct dma_fence_unwrap - cursor into the container structure + * + * Should be used with dma_fence_unwrap_for_each() iterator macro. + */ +struct dma_fence_unwrap { + /** + * @chain: potential dma_fence_chain, but can be other fence as well + */ + struct dma_fence *chain; + /** + * @array: potential dma_fence_array, but can be other fence as well + */ + struct dma_fence *array; + /** + * @index: last returned index if @array is really a dma_fence_array + */ + unsigned int index; +}; + +/* Internal helper to start new array iteration, don't use directly */ +static inline struct dma_fence * +__dma_fence_unwrap_array(struct dma_fence_unwrap * cursor) +{ + cursor->array = dma_fence_chain_contained(cursor->chain); + cursor->index = 0; + return dma_fence_array_first(cursor->array); +} + +/** + * dma_fence_unwrap_first - return the first fence from fence containers + * @head: the entrypoint into the containers + * @cursor: current position inside the containers + * + * Unwraps potential dma_fence_chain/dma_fence_array containers and return the + * first fence. + */ +static inline struct dma_fence * +dma_fence_unwrap_first(struct dma_fence *head, struct dma_fence_unwrap *cursor) +{ + cursor->chain = dma_fence_get(head); + return __dma_fence_unwrap_array(cursor); +} + +/** + * dma_fence_unwrap_next - return the next fence from a fence containers + * @cursor: current position inside the containers + * + * Continue unwrapping the dma_fence_chain/dma_fence_array containers and return + * the next fence from them. + */ +static inline struct dma_fence * +dma_fence_unwrap_next(struct dma_fence_unwrap *cursor) +{ + struct dma_fence *tmp; + + ++cursor->index; + tmp = dma_fence_array_next(cursor->array, cursor->index); + if (tmp) + return tmp; + + cursor->chain = dma_fence_chain_walk(cursor->chain); + return __dma_fence_unwrap_array(cursor); +} + +/** + * dma_fence_unwrap_for_each - iterate over all fences in containers + * @fence: current fence + * @cursor: current position inside the containers + * @head: starting point for the iterator + * + * Unwrap dma_fence_chain and dma_fence_array containers and deep dive into all + * potential fences in them. If @head is just a normal fence only that one is + * returned. + */ +#define dma_fence_unwrap_for_each(fence, cursor, head) \ + for (fence = dma_fence_unwrap_first(head, cursor); fence; \ + fence = dma_fence_unwrap_next(cursor)) + +#endif diff --git a/include/linux/efi.h b/include/linux/efi.h index ccd4d3f91c98..db424f3dc3f2 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -213,6 +213,8 @@ struct capsule_info { size_t page_bytes_remain; }; +int efi_capsule_setup_info(struct capsule_info *cap_info, void *kbuff, + size_t hdr_bytes); int __efi_capsule_setup_info(struct capsule_info *cap_info); /* @@ -383,6 +385,7 @@ void efi_native_runtime_setup(void); #define EFI_LOAD_FILE_PROTOCOL_GUID EFI_GUID(0x56ec3091, 0x954c, 0x11d2, 0x8e, 0x3f, 0x00, 0xa0, 0xc9, 0x69, 0x72, 0x3b) #define EFI_LOAD_FILE2_PROTOCOL_GUID EFI_GUID(0x4006c0c1, 0xfcb3, 0x403e, 0x99, 0x6d, 0x4a, 0x6c, 0x87, 0x24, 0xe0, 0x6d) #define EFI_RT_PROPERTIES_TABLE_GUID EFI_GUID(0xeb66918a, 0x7eef, 0x402a, 0x84, 0x2e, 0x93, 0x1d, 0x21, 0xc3, 0x8a, 0xe9) +#define EFI_DXE_SERVICES_TABLE_GUID EFI_GUID(0x05ad34ba, 0x6f02, 0x4214, 0x95, 0x2e, 0x4d, 0xa0, 0x39, 0x8e, 0x2b, 0xb9) #define EFI_IMAGE_SECURITY_DATABASE_GUID EFI_GUID(0xd719b2cb, 0x3d3a, 0x4596, 0xa3, 0xbc, 0xda, 0xd0, 0x0e, 0x67, 0x65, 0x6f) #define EFI_SHIM_LOCK_GUID EFI_GUID(0x605dab50, 0xe046, 0x4300, 0xab, 0xb6, 0x3d, 0xd8, 0x10, 0xdd, 0x8b, 0x23) @@ -390,6 +393,7 @@ void efi_native_runtime_setup(void); #define EFI_CERT_SHA256_GUID EFI_GUID(0xc1c41626, 0x504c, 0x4092, 0xac, 0xa9, 0x41, 0xf9, 0x36, 0x93, 0x43, 0x28) #define EFI_CERT_X509_GUID EFI_GUID(0xa5c059a1, 0x94e4, 0x4aa7, 0x87, 0xb5, 0xab, 0x15, 0x5c, 0x2b, 0xf0, 0x72) #define EFI_CERT_X509_SHA256_GUID EFI_GUID(0x3bd2a492, 0x96c0, 0x4079, 0xb4, 0x20, 0xfc, 0xf9, 0x8e, 0xf1, 0x03, 0xed) +#define EFI_CC_BLOB_GUID EFI_GUID(0x067b1f5f, 0xcf26, 0x44c5, 0x85, 0x54, 0x93, 0xd7, 0x77, 0x91, 0x2d, 0x42) /* * This GUID is used to pass to the kernel proper the struct screen_info @@ -405,6 +409,20 @@ void efi_native_runtime_setup(void); #define LINUX_EFI_MEMRESERVE_TABLE_GUID EFI_GUID(0x888eb0c6, 0x8ede, 0x4ff5, 0xa8, 0xf0, 0x9a, 0xee, 0x5c, 0xb9, 0x77, 0xc2) #define LINUX_EFI_INITRD_MEDIA_GUID EFI_GUID(0x5568e427, 0x68fc, 0x4f3d, 0xac, 0x74, 0xca, 0x55, 0x52, 0x31, 0xcc, 0x68) #define LINUX_EFI_MOK_VARIABLE_TABLE_GUID EFI_GUID(0xc451ed2b, 0x9694, 0x45d3, 0xba, 0xba, 0xed, 0x9f, 0x89, 0x88, 0xa3, 0x89) +#define LINUX_EFI_COCO_SECRET_AREA_GUID EFI_GUID(0xadf956ad, 0xe98c, 0x484c, 0xae, 0x11, 0xb5, 0x1c, 0x7d, 0x33, 0x64, 0x47) + +#define RISCV_EFI_BOOT_PROTOCOL_GUID EFI_GUID(0xccd15fec, 0x6f73, 0x4eec, 0x83, 0x95, 0x3e, 0x69, 0xe4, 0xb9, 0x40, 0xbf) + +/* + * This GUID may be installed onto the kernel image's handle as a NULL protocol + * to signal to the stub that the placement of the image should be respected, + * and moving the image in physical memory is undesirable. To ensure + * compatibility with 64k pages kernels with virtually mapped stacks, and to + * avoid defeating physical randomization, this protocol should only be + * installed if the image was placed at a randomized 128k aligned address in + * memory. + */ +#define LINUX_EFI_LOADED_IMAGE_FIXED_GUID EFI_GUID(0xf5a37b6d, 0x3344, 0x42a5, 0xb6, 0xbb, 0x97, 0x86, 0x48, 0xc1, 0x89, 0x0a) /* OEM GUIDs */ #define DELLEMC_EFI_RCI2_TABLE_GUID EFI_GUID(0x2d9f28a2, 0xa886, 0x456a, 0x97, 0xa8, 0xf1, 0x1e, 0xf2, 0x4f, 0xf4, 0x55) @@ -435,6 +453,7 @@ typedef struct { } efi_config_table_type_t; #define EFI_SYSTEM_TABLE_SIGNATURE ((u64)0x5453595320494249ULL) +#define EFI_DXE_SERVICES_TABLE_SIGNATURE ((u64)0x565245535f455844ULL) #define EFI_2_30_SYSTEM_TABLE_REVISION ((2 << 16) | (30)) #define EFI_2_20_SYSTEM_TABLE_REVISION ((2 << 16) | (20)) @@ -596,6 +615,7 @@ extern struct efi { unsigned long tpm_log; /* TPM2 Event Log table */ unsigned long tpm_final_log; /* TPM2 Final Events Log table */ unsigned long mokvar_table; /* MOK variable config table */ + unsigned long coco_secret; /* Confidential computing secret table */ efi_get_time_t *get_time; efi_set_time_t *set_time; @@ -1335,4 +1355,12 @@ extern void efifb_setup_from_dmi(struct screen_info *si, const char *opt); static inline void efifb_setup_from_dmi(struct screen_info *si, const char *opt) { } #endif +struct linux_efi_coco_secret_area { + u64 base_pa; + u64 size; +}; + +/* Header of a populated EFI secret area */ +#define EFI_SECRET_TABLE_HEADER_GUID EFI_GUID(0x1e74f542, 0x71dd, 0x4d66, 0x96, 0x3e, 0xef, 0x42, 0x87, 0xff, 0x17, 0x3b) + #endif /* _LINUX_EFI_H */ diff --git a/include/linux/elfcore.h b/include/linux/elfcore.h index f8e206e82476..346a8b56cdc8 100644 --- a/include/linux/elfcore.h +++ b/include/linux/elfcore.h @@ -84,15 +84,6 @@ static inline void elf_core_copy_regs(elf_gregset_t *elfregs, struct pt_regs *re #endif } -static inline void elf_core_copy_kernel_regs(elf_gregset_t *elfregs, struct pt_regs *regs) -{ -#ifdef ELF_CORE_COPY_KERNEL_REGS - ELF_CORE_COPY_KERNEL_REGS((*elfregs), regs); -#else - elf_core_copy_regs(elfregs, regs); -#endif -} - static inline int elf_core_copy_task_regs(struct task_struct *t, elf_gregset_t* elfregs) { #if defined (ELF_CORE_COPY_TASK_REGS) diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index 9f3c400bc52d..8419bffb4398 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -67,11 +67,16 @@ struct em_perf_domain { * * EM_PERF_DOMAIN_SKIP_INEFFICIENCIES: Skip inefficient states when estimating * energy consumption. + * + * EM_PERF_DOMAIN_ARTIFICIAL: The power values are artificial and might be + * created by platform missing real power information */ #define EM_PERF_DOMAIN_MILLIWATTS BIT(0) #define EM_PERF_DOMAIN_SKIP_INEFFICIENCIES BIT(1) +#define EM_PERF_DOMAIN_ARTIFICIAL BIT(2) #define em_span_cpus(em) (to_cpumask((em)->cpus)) +#define em_is_artificial(em) ((em)->flags & EM_PERF_DOMAIN_ARTIFICIAL) #ifdef CONFIG_ENERGY_MODEL #define EM_MAX_POWER 0xFFFF @@ -96,11 +101,11 @@ struct em_data_callback { /** * active_power() - Provide power at the next performance state of * a device + * @dev : Device for which we do this operation (can be a CPU) * @power : Active power at the performance state * (modified) * @freq : Frequency at the performance state in kHz * (modified) - * @dev : Device for which we do this operation (can be a CPU) * * active_power() must find the lowest performance state of 'dev' above * 'freq' and update 'power' and 'freq' to the matching active power @@ -112,11 +117,32 @@ struct em_data_callback { * * Return 0 on success. */ - int (*active_power)(unsigned long *power, unsigned long *freq, - struct device *dev); + int (*active_power)(struct device *dev, unsigned long *power, + unsigned long *freq); + + /** + * get_cost() - Provide the cost at the given performance state of + * a device + * @dev : Device for which we do this operation (can be a CPU) + * @freq : Frequency at the performance state in kHz + * @cost : The cost value for the performance state + * (modified) + * + * In case of CPUs, the cost is the one of a single CPU in the domain. + * It is expected to fit in the [0, EM_MAX_POWER] range due to internal + * usage in EAS calculation. + * + * Return 0 on success, or appropriate error value in case of failure. + */ + int (*get_cost)(struct device *dev, unsigned long freq, + unsigned long *cost); }; -#define EM_DATA_CB(_active_power_cb) { .active_power = &_active_power_cb } #define EM_SET_ACTIVE_POWER_CB(em_cb, cb) ((em_cb).active_power = cb) +#define EM_ADV_DATA_CB(_active_power_cb, _cost_cb) \ + { .active_power = _active_power_cb, \ + .get_cost = _cost_cb } +#define EM_DATA_CB(_active_power_cb) \ + EM_ADV_DATA_CB(_active_power_cb, NULL) struct em_perf_domain *em_cpu_get(int cpu); struct em_perf_domain *em_pd_get(struct device *dev); @@ -264,6 +290,7 @@ static inline int em_pd_nr_perf_states(struct em_perf_domain *pd) #else struct em_data_callback {}; +#define EM_ADV_DATA_CB(_active_power_cb, _cost_cb) { } #define EM_DATA_CB(_active_power_cb) { } #define EM_SET_ACTIVE_POWER_CB(em_cb, cb) do { } while (0) diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h index ab78bd4c2eb0..c92ac75d6556 100644 --- a/include/linux/entry-common.h +++ b/include/linux/entry-common.h @@ -63,7 +63,7 @@ ARCH_EXIT_TO_USER_MODE_WORK) /** - * arch_check_user_regs - Architecture specific sanity check for user mode regs + * arch_enter_from_user_mode - Architecture specific sanity check for user mode regs * @regs: Pointer to currents pt_regs * * Defaults to an empty implementation. Can be replaced by architecture @@ -73,10 +73,10 @@ * section. Use __always_inline so the compiler cannot push it out of line * and make it instrumentable. */ -static __always_inline void arch_check_user_regs(struct pt_regs *regs); +static __always_inline void arch_enter_from_user_mode(struct pt_regs *regs); -#ifndef arch_check_user_regs -static __always_inline void arch_check_user_regs(struct pt_regs *regs) {} +#ifndef arch_enter_from_user_mode +static __always_inline void arch_enter_from_user_mode(struct pt_regs *regs) {} #endif /** diff --git a/include/linux/fs.h b/include/linux/fs.h index bbde95387a23..f58ae40235ab 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -262,7 +262,7 @@ struct iattr { * trying again. The aop will be taking reasonable * precautions not to livelock. If the caller held a page * reference, it should drop it before retrying. Returned - * by readpage(). + * by read_folio(). * * address_space_operation functions return these large constants to indicate * special semantics to the caller. These are much larger than the bytes in a @@ -275,10 +275,6 @@ enum positive_aop_returns { AOP_TRUNCATED_PAGE = 0x80001, }; -#define AOP_FLAG_NOFS 0x0002 /* used by filesystem to direct - * helper code (eg buffer layer) - * to clear GFP_FS from alloc */ - /* * oh the beauties of C type declarations. */ @@ -339,7 +335,7 @@ static inline bool is_sync_kiocb(struct kiocb *kiocb) struct address_space_operations { int (*writepage)(struct page *page, struct writeback_control *wbc); - int (*readpage)(struct file *, struct page *); + int (*read_folio)(struct file *, struct folio *); /* Write back some dirty pages from this mapping. */ int (*writepages)(struct address_space *, struct writeback_control *); @@ -350,7 +346,7 @@ struct address_space_operations { void (*readahead)(struct readahead_control *); int (*write_begin)(struct file *, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, + loff_t pos, unsigned len, struct page **pagep, void **fsdata); int (*write_end)(struct file *, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, @@ -359,8 +355,8 @@ struct address_space_operations { /* Unfortunately this kludge is needed for FIBMAP. Don't use it */ sector_t (*bmap)(struct address_space *, sector_t); void (*invalidate_folio) (struct folio *, size_t offset, size_t len); - int (*releasepage) (struct page *, gfp_t); - void (*freepage)(struct page *); + bool (*release_folio)(struct folio *, gfp_t); + void (*free_folio)(struct folio *folio); ssize_t (*direct_IO)(struct kiocb *, struct iov_iter *iter); /* * migrate the contents of a page to the specified target. If @@ -373,7 +369,7 @@ struct address_space_operations { int (*launder_folio)(struct folio *); bool (*is_partially_uptodate) (struct folio *, size_t from, size_t count); - void (*is_dirty_writeback) (struct page *, bool *, bool *); + void (*is_dirty_writeback) (struct folio *, bool *dirty, bool *wb); int (*error_remove_page)(struct address_space *, struct page *); /* swapfile support */ @@ -384,18 +380,6 @@ struct address_space_operations { extern const struct address_space_operations empty_aops; -/* - * pagecache_write_begin/pagecache_write_end must be used by general code - * to write into the pagecache. - */ -int pagecache_write_begin(struct file *, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, - struct page **pagep, void **fsdata); - -int pagecache_write_end(struct file *, struct address_space *mapping, - loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata); - /** * struct address_space - Contents of a cacheable, mappable object. * @host: Owner, either the inode or the block_device. @@ -1708,6 +1692,11 @@ static inline bool __sb_start_write_trylock(struct super_block *sb, int level) #define __sb_writers_release(sb, lev) \ percpu_rwsem_release(&(sb)->s_writers.rw_sem[(lev)-1], 1, _THIS_IP_) +static inline bool sb_write_started(const struct super_block *sb) +{ + return lockdep_is_held_type(sb->s_writers.rw_sem + SB_FREEZE_WRITE - 1, 1); +} + /** * sb_end_write - drop write access to a superblock * @sb: the super we wrote to @@ -1953,6 +1942,7 @@ struct dir_context { #define REMAP_FILE_ADVISORY (REMAP_FILE_CAN_SHORTEN) struct iov_iter; +struct io_uring_cmd; struct file_operations { struct module *owner; @@ -1995,6 +1985,7 @@ struct file_operations { struct file *file_out, loff_t pos_out, loff_t len, unsigned int remap_flags); int (*fadvise)(struct file *, loff_t, loff_t, int); + int (*uring_cmd)(struct io_uring_cmd *ioucmd, unsigned int issue_flags); } __randomize_layout; struct inode_operations { @@ -3109,8 +3100,6 @@ extern int page_readlink(struct dentry *, char __user *, int); extern const char *page_get_link(struct dentry *, struct inode *, struct delayed_call *); extern void page_put_link(void *); -extern int __page_symlink(struct inode *inode, const char *symname, int len, - int nofs); extern int page_symlink(struct inode *inode, const char *symname, int len); extern const struct inode_operations page_symlink_inode_operations; extern void kfree_link(void *); @@ -3185,7 +3174,7 @@ extern int noop_fsync(struct file *, loff_t, loff_t, int); extern ssize_t noop_direct_IO(struct kiocb *iocb, struct iov_iter *iter); extern int simple_empty(struct dentry *); extern int simple_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, + loff_t pos, unsigned len, struct page **pagep, void **fsdata); extern const struct address_space_operations ram_aops; extern int always_delete_dentry(const struct dentry *); diff --git a/include/linux/fscache.h b/include/linux/fscache.h index 6727fb0db619..72585c9729a2 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -39,6 +39,7 @@ struct fscache_cookie; #define FSCACHE_ADV_SINGLE_CHUNK 0x01 /* The object is a single chunk of data */ #define FSCACHE_ADV_WRITE_CACHE 0x00 /* Do cache if written to locally */ #define FSCACHE_ADV_WRITE_NOCACHE 0x02 /* Don't cache if written to locally */ +#define FSCACHE_ADV_WANT_CACHE_SIZE 0x04 /* Retrieve cache size at runtime */ #define FSCACHE_INVAL_DIO_WRITE 0x01 /* Invalidate due to DIO write */ @@ -573,7 +574,6 @@ int fscache_write(struct netfs_cache_resources *cres, /** * fscache_clear_page_bits - Clear the PG_fscache bits from a set of pages - * @cookie: The cookie representing the cache object * @mapping: The netfs inode to use as the source * @start: The start position in @mapping * @len: The amount of data to unlock @@ -582,8 +582,7 @@ int fscache_write(struct netfs_cache_resources *cres, * Clear the PG_fscache flag from a sequence of pages and wake up anyone who's * waiting. */ -static inline void fscache_clear_page_bits(struct fscache_cookie *cookie, - struct address_space *mapping, +static inline void fscache_clear_page_bits(struct address_space *mapping, loff_t start, size_t len, bool caching) { diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index 50d92d805bd8..e60d57c99cb6 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -18,10 +18,21 @@ #include <linux/slab.h> #include <uapi/linux/fscrypt.h> -#define FS_CRYPTO_BLOCK_SIZE 16 +/* + * The lengths of all file contents blocks must be divisible by this value. + * This is needed to ensure that all contents encryption modes will work, as + * some of the supported modes don't support arbitrarily byte-aligned messages. + * + * Since the needed alignment is 16 bytes, most filesystems will meet this + * requirement naturally, as typical block sizes are powers of 2. However, if a + * filesystem can generate arbitrarily byte-aligned block lengths (e.g., via + * compression), then it will need to pad to this alignment before encryption. + */ +#define FSCRYPT_CONTENTS_ALIGNMENT 16 union fscrypt_policy; struct fscrypt_info; +struct fs_parameter; struct seq_file; struct fscrypt_str { @@ -279,10 +290,19 @@ struct fscrypt_dummy_policy { const union fscrypt_policy *policy; }; +int fscrypt_parse_test_dummy_encryption(const struct fs_parameter *param, + struct fscrypt_dummy_policy *dummy_policy); +bool fscrypt_dummy_policies_equal(const struct fscrypt_dummy_policy *p1, + const struct fscrypt_dummy_policy *p2); int fscrypt_set_test_dummy_encryption(struct super_block *sb, const char *arg, struct fscrypt_dummy_policy *dummy_policy); void fscrypt_show_test_dummy_encryption(struct seq_file *seq, char sep, struct super_block *sb); +static inline bool +fscrypt_is_dummy_policy_set(const struct fscrypt_dummy_policy *dummy_policy) +{ + return dummy_policy->policy != NULL; +} static inline void fscrypt_free_dummy_policy(struct fscrypt_dummy_policy *dummy_policy) { @@ -293,6 +313,8 @@ fscrypt_free_dummy_policy(struct fscrypt_dummy_policy *dummy_policy) /* keyring.c */ void fscrypt_sb_free(struct super_block *sb); int fscrypt_ioctl_add_key(struct file *filp, void __user *arg); +int fscrypt_add_test_dummy_key(struct super_block *sb, + const struct fscrypt_dummy_policy *dummy_policy); int fscrypt_ioctl_remove_key(struct file *filp, void __user *arg); int fscrypt_ioctl_remove_key_all_users(struct file *filp, void __user *arg); int fscrypt_ioctl_get_key_status(struct file *filp, void __user *arg); @@ -467,12 +489,32 @@ static inline int fscrypt_set_context(struct inode *inode, void *fs_data) struct fscrypt_dummy_policy { }; +static inline int +fscrypt_parse_test_dummy_encryption(const struct fs_parameter *param, + struct fscrypt_dummy_policy *dummy_policy) +{ + return -EINVAL; +} + +static inline bool +fscrypt_dummy_policies_equal(const struct fscrypt_dummy_policy *p1, + const struct fscrypt_dummy_policy *p2) +{ + return true; +} + static inline void fscrypt_show_test_dummy_encryption(struct seq_file *seq, char sep, struct super_block *sb) { } +static inline bool +fscrypt_is_dummy_policy_set(const struct fscrypt_dummy_policy *dummy_policy) +{ + return false; +} + static inline void fscrypt_free_dummy_policy(struct fscrypt_dummy_policy *dummy_policy) { @@ -488,6 +530,13 @@ static inline int fscrypt_ioctl_add_key(struct file *filp, void __user *arg) return -EOPNOTSUPP; } +static inline int +fscrypt_add_test_dummy_key(struct super_block *sb, + const struct fscrypt_dummy_policy *dummy_policy) +{ + return 0; +} + static inline int fscrypt_ioctl_remove_key(struct file *filp, void __user *arg) { return -EOPNOTSUPP; diff --git a/include/linux/fsverity.h b/include/linux/fsverity.h index a7afc800bd8d..7af030fa3c36 100644 --- a/include/linux/fsverity.h +++ b/include/linux/fsverity.h @@ -12,8 +12,16 @@ #define _LINUX_FSVERITY_H #include <linux/fs.h> +#include <crypto/hash_info.h> +#include <crypto/sha2.h> #include <uapi/linux/fsverity.h> +/* + * Largest digest size among all hash algorithms supported by fs-verity. + * Currently assumed to be <= size of fsverity_descriptor::root_hash. + */ +#define FS_VERITY_MAX_DIGEST_SIZE SHA512_DIGEST_SIZE + /* Verity operations for filesystems */ struct fsverity_operations { @@ -131,6 +139,9 @@ int fsverity_ioctl_enable(struct file *filp, const void __user *arg); /* measure.c */ int fsverity_ioctl_measure(struct file *filp, void __user *arg); +int fsverity_get_digest(struct inode *inode, + u8 digest[FS_VERITY_MAX_DIGEST_SIZE], + enum hash_algo *alg); /* open.c */ @@ -170,6 +181,13 @@ static inline int fsverity_ioctl_measure(struct file *filp, void __user *arg) return -EOPNOTSUPP; } +static inline int fsverity_get_digest(struct inode *inode, + u8 digest[FS_VERITY_MAX_DIGEST_SIZE], + enum hash_algo *alg) +{ + return -EOPNOTSUPP; +} + /* open.c */ static inline int fsverity_file_open(struct inode *inode, struct file *filp) diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h index 3a532ba66f6c..9a81c4410b9f 100644 --- a/include/linux/fwnode.h +++ b/include/linux/fwnode.h @@ -113,6 +113,9 @@ struct fwnode_operations { bool (*device_is_available)(const struct fwnode_handle *fwnode); const void *(*device_get_match_data)(const struct fwnode_handle *fwnode, const struct device *dev); + bool (*device_dma_supported)(const struct fwnode_handle *fwnode); + enum dev_dma_attr + (*device_get_dma_attr)(const struct fwnode_handle *fwnode); bool (*property_present)(const struct fwnode_handle *fwnode, const char *propname); int (*property_read_int_array)(const struct fwnode_handle *fwnode, @@ -145,15 +148,17 @@ struct fwnode_operations { (*graph_get_port_parent)(struct fwnode_handle *fwnode); int (*graph_parse_endpoint)(const struct fwnode_handle *fwnode, struct fwnode_endpoint *endpoint); + void __iomem *(*iomap)(struct fwnode_handle *fwnode, int index); + int (*irq_get)(const struct fwnode_handle *fwnode, unsigned int index); int (*add_links)(struct fwnode_handle *fwnode); }; -#define fwnode_has_op(fwnode, op) \ - ((fwnode) && (fwnode)->ops && (fwnode)->ops->op) +#define fwnode_has_op(fwnode, op) \ + (!IS_ERR_OR_NULL(fwnode) && (fwnode)->ops && (fwnode)->ops->op) + #define fwnode_call_int_op(fwnode, op, ...) \ - (fwnode ? (fwnode_has_op(fwnode, op) ? \ - (fwnode)->ops->op(fwnode, ## __VA_ARGS__) : -ENXIO) : \ - -EINVAL) + (fwnode_has_op(fwnode, op) ? \ + (fwnode)->ops->op(fwnode, ## __VA_ARGS__) : (IS_ERR_OR_NULL(fwnode) ? -EINVAL : -ENXIO)) #define fwnode_call_bool_op(fwnode, op, ...) \ (fwnode_has_op(fwnode, op) ? \ diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 761f8f1885c7..3e3d36fc2109 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -613,9 +613,11 @@ static inline struct page *alloc_pages_node(int nid, gfp_t gfp_mask, #ifdef CONFIG_NUMA struct page *alloc_pages(gfp_t gfp, unsigned int order); struct folio *folio_alloc(gfp_t gfp, unsigned order); -extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order, +struct page *alloc_pages_vma(gfp_t gfp_mask, int order, struct vm_area_struct *vma, unsigned long addr, bool hugepage); +struct folio *vma_alloc_folio(gfp_t gfp, int order, struct vm_area_struct *vma, + unsigned long addr, bool hugepage); #define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ alloc_pages_vma(gfp_mask, order, vma, addr, true) #else @@ -627,8 +629,10 @@ static inline struct folio *folio_alloc(gfp_t gfp, unsigned int order) { return __folio_alloc_node(gfp, order, numa_node_id()); } -#define alloc_pages_vma(gfp_mask, order, vma, addr, false)\ +#define alloc_pages_vma(gfp_mask, order, vma, addr, hugepage) \ alloc_pages(gfp_mask, order) +#define vma_alloc_folio(gfp, order, vma, addr, hugepage) \ + folio_alloc(gfp, order) #define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ alloc_pages(gfp_mask, order) #endif diff --git a/include/linux/goldfish.h b/include/linux/goldfish.h index 12be1601fd84..bcc17f95b906 100644 --- a/include/linux/goldfish.h +++ b/include/linux/goldfish.h @@ -8,14 +8,21 @@ /* Helpers for Goldfish virtual platform */ +#ifndef gf_ioread32 +#define gf_ioread32 ioread32 +#endif +#ifndef gf_iowrite32 +#define gf_iowrite32 iowrite32 +#endif + static inline void gf_write_ptr(const void *ptr, void __iomem *portl, void __iomem *porth) { const unsigned long addr = (unsigned long)ptr; - __raw_writel(lower_32_bits(addr), portl); + gf_iowrite32(lower_32_bits(addr), portl); #ifdef CONFIG_64BIT - __raw_writel(upper_32_bits(addr), porth); + gf_iowrite32(upper_32_bits(addr), porth); #endif } @@ -23,9 +30,9 @@ static inline void gf_write_dma_addr(const dma_addr_t addr, void __iomem *portl, void __iomem *porth) { - __raw_writel(lower_32_bits(addr), portl); + gf_iowrite32(lower_32_bits(addr), portl); #ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT - __raw_writel(upper_32_bits(addr), porth); + gf_iowrite32(upper_32_bits(addr), porth); #endif } diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h index c3aa8b330e1c..e71f6e1bfafe 100644 --- a/include/linux/gpio/consumer.h +++ b/include/linux/gpio/consumer.h @@ -688,7 +688,7 @@ void acpi_dev_remove_driver_gpios(struct acpi_device *adev); int devm_acpi_dev_add_driver_gpios(struct device *dev, const struct acpi_gpio_mapping *gpios); -struct gpio_desc *acpi_get_and_request_gpiod(char *path, int pin, char *label); +struct gpio_desc *acpi_get_and_request_gpiod(char *path, unsigned int pin, char *label); #else /* CONFIG_GPIOLIB && CONFIG_ACPI */ @@ -705,6 +705,12 @@ static inline int devm_acpi_dev_add_driver_gpios(struct device *dev, return -ENXIO; } +static inline struct gpio_desc *acpi_get_and_request_gpiod(char *path, unsigned int pin, + char *label) +{ + return ERR_PTR(-ENOSYS); +} + #endif /* CONFIG_GPIOLIB && CONFIG_ACPI */ diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 98c93510640e..cb689264f3e9 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -222,6 +222,15 @@ struct gpio_irq_chip { bool per_parent_data; /** + * @initialized: + * + * Flag to track GPIO chip irq member's initialization. + * This flag will make sure GPIO chip irq members are not used + * before they are initialized. + */ + bool initialized; + + /** * @init_hw: optional routine to initialize hardware before * an IRQ chip will be added. This is quite useful when * a particular driver wants to clear IRQ related registers @@ -579,6 +588,22 @@ void gpiochip_relres_irq(struct gpio_chip *gc, unsigned int offset); void gpiochip_disable_irq(struct gpio_chip *gc, unsigned int offset); void gpiochip_enable_irq(struct gpio_chip *gc, unsigned int offset); +/* irq_data versions of the above */ +int gpiochip_irq_reqres(struct irq_data *data); +void gpiochip_irq_relres(struct irq_data *data); + +/* Paste this in your irq_chip structure */ +#define GPIOCHIP_IRQ_RESOURCE_HELPERS \ + .irq_request_resources = gpiochip_irq_reqres, \ + .irq_release_resources = gpiochip_irq_relres + +static inline void gpio_irq_chip_set_chip(struct gpio_irq_chip *girq, + const struct irq_chip *chip) +{ + /* Yes, dropping const is ugly, but it isn't like we have a choice */ + girq->chip = (struct irq_chip *)chip; +} + /* Line status inquiry for drivers */ bool gpiochip_line_is_open_drain(struct gpio_chip *gc, unsigned int offset); bool gpiochip_line_is_open_source(struct gpio_chip *gc, unsigned int offset); diff --git a/include/linux/highmem-internal.h b/include/linux/highmem-internal.h index a77be5630209..337bd9f32921 100644 --- a/include/linux/highmem-internal.h +++ b/include/linux/highmem-internal.h @@ -149,6 +149,11 @@ static inline void totalhigh_pages_add(long count) atomic_long_add(count, &_totalhigh_pages); } +static inline bool is_kmap_addr(const void *x) +{ + unsigned long addr = (unsigned long)x; + return addr >= PKMAP_ADDR(0) && addr < PKMAP_ADDR(LAST_PKMAP); +} #else /* CONFIG_HIGHMEM */ static inline struct page *kmap_to_page(void *addr) @@ -234,6 +239,11 @@ static inline void __kunmap_atomic(void *addr) static inline unsigned int nr_free_highpages(void) { return 0; } static inline unsigned long totalhigh_pages(void) { return 0UL; } +static inline bool is_kmap_addr(const void *x) +{ + return false; +} + #endif /* CONFIG_HIGHMEM */ /* diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 53c1b6082a4c..ac2a1d758a80 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -169,6 +169,7 @@ long hugetlb_unreserve_pages(struct inode *inode, long start, long end, long freed); bool isolate_huge_page(struct page *page, struct list_head *list); int get_hwpoison_huge_page(struct page *page, bool *hugetlb); +int get_huge_page_for_hwpoison(unsigned long pfn, int flags); void putback_active_hugepage(struct page *page); void move_hugetlb_state(struct page *oldpage, struct page *newpage, int reason); void free_huge_page(struct page *page); @@ -378,6 +379,11 @@ static inline int get_hwpoison_huge_page(struct page *page, bool *hugetlb) return 0; } +static inline int get_huge_page_for_hwpoison(unsigned long pfn, int flags) +{ + return 0; +} + static inline void putback_active_hugepage(struct page *page) { } diff --git a/include/linux/hwmon.h b/include/linux/hwmon.h index eba380b76d15..14325f93c6b2 100644 --- a/include/linux/hwmon.h +++ b/include/linux/hwmon.h @@ -450,6 +450,9 @@ hwmon_device_register_with_info(struct device *dev, const struct hwmon_chip_info *info, const struct attribute_group **extra_groups); struct device * +hwmon_device_register_for_thermal(struct device *dev, const char *name, + void *drvdata); +struct device * devm_hwmon_device_register_with_info(struct device *dev, const char *name, void *drvdata, const struct hwmon_chip_info *info, @@ -461,6 +464,9 @@ void devm_hwmon_device_unregister(struct device *dev); int hwmon_notify_event(struct device *dev, enum hwmon_sensor_types type, u32 attr, int channel); +char *hwmon_sanitize_name(const char *name); +char *devm_hwmon_sanitize_name(struct device *dev, const char *name); + /** * hwmon_is_bad_char - Is the char invalid in a hwmon name * @ch: the char to be considered diff --git a/include/linux/iio/adc/qcom-vadc-common.h b/include/linux/iio/adc/qcom-vadc-common.h index ce78d4804994..aa21b032e861 100644 --- a/include/linux/iio/adc/qcom-vadc-common.h +++ b/include/linux/iio/adc/qcom-vadc-common.h @@ -152,6 +152,8 @@ int qcom_adc5_hw_scale(enum vadc_scale_fn_type scaletype, u16 qcom_adc_tm5_temp_volt_scale(unsigned int prescale_ratio, u32 full_scale_code_volt, int temp); +u16 qcom_adc_tm5_gen2_temp_res_scale(int temp); + int qcom_adc5_prescaling_from_dt(u32 num, u32 den); int qcom_adc5_hw_settle_time_from_dt(u32 value, const unsigned int *hw_settle); diff --git a/include/linux/instrumentation.h b/include/linux/instrumentation.h index 24359b4a9605..bc7babe91b2e 100644 --- a/include/linux/instrumentation.h +++ b/include/linux/instrumentation.h @@ -2,7 +2,7 @@ #ifndef __LINUX_INSTRUMENTATION_H #define __LINUX_INSTRUMENTATION_H -#if defined(CONFIG_DEBUG_ENTRY) && defined(CONFIG_STACK_VALIDATION) +#ifdef CONFIG_NOINSTR_VALIDATION #include <linux/stringify.h> @@ -53,9 +53,9 @@ ".popsection\n\t" : : "i" (c)); \ }) #define instrumentation_end() __instrumentation_end(__COUNTER__) -#else +#else /* !CONFIG_NOINSTR_VALIDATION */ # define instrumentation_begin() do { } while(0) # define instrumentation_end() do { } while(0) -#endif +#endif /* CONFIG_NOINSTR_VALIDATION */ #endif /* __LINUX_INSTRUMENTATION_H */ diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index f40754caaefa..a92bce40b04b 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -222,24 +222,6 @@ devm_request_any_context_irq(struct device *dev, unsigned int irq, extern void devm_free_irq(struct device *dev, unsigned int irq, void *dev_id); -/* - * On lockdep we dont want to enable hardirqs in hardirq - * context. Use local_irq_enable_in_hardirq() to annotate - * kernel code that has to do this nevertheless (pretty much - * the only valid case is for old/broken hardware that is - * insanely slow). - * - * NOTE: in theory this might break fragile code that relies - * on hardirq delivery - in practice we dont seem to have such - * places left. So the only effect should be slightly increased - * irqs-off latencies. - */ -#ifdef CONFIG_LOCKDEP -# define local_irq_enable_in_hardirq() do { } while (0) -#else -# define local_irq_enable_in_hardirq() local_irq_enable() -#endif - bool irq_has_action(unsigned int irq); extern void disable_irq_nosync(unsigned int irq); extern bool disable_hardirq(unsigned int irq); @@ -607,6 +589,15 @@ struct softirq_action asmlinkage void do_softirq(void); asmlinkage void __do_softirq(void); +#ifdef CONFIG_PREEMPT_RT +extern void do_softirq_post_smp_call_flush(unsigned int was_pending); +#else +static inline void do_softirq_post_smp_call_flush(unsigned int unused) +{ + do_softirq(); +} +#endif + extern void open_softirq(int nr, void (*action)(struct softirq_action *)); extern void softirq_init(void); extern void __raise_softirq_irqoff(unsigned int nr); diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h index 1814e698d861..4a2f6cc5a492 100644 --- a/include/linux/io_uring.h +++ b/include/linux/io_uring.h @@ -5,11 +5,37 @@ #include <linux/sched.h> #include <linux/xarray.h> +enum io_uring_cmd_flags { + IO_URING_F_COMPLETE_DEFER = 1, + IO_URING_F_UNLOCKED = 2, + /* int's last bit, sign checks are usually faster than a bit test */ + IO_URING_F_NONBLOCK = INT_MIN, + + /* ctx state flags, for URING_CMD */ + IO_URING_F_SQE128 = 4, + IO_URING_F_CQE32 = 8, + IO_URING_F_IOPOLL = 16, +}; + +struct io_uring_cmd { + struct file *file; + const void *cmd; + /* callback to defer completions to task context */ + void (*task_work_cb)(struct io_uring_cmd *cmd); + u32 cmd_op; + u32 pad; + u8 pdu[32]; /* available inline for free use */ +}; + #if defined(CONFIG_IO_URING) +void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret, ssize_t res2); +void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd, + void (*task_work_cb)(struct io_uring_cmd *)); struct sock *io_uring_get_socket(struct file *file); void __io_uring_cancel(bool cancel_all); void __io_uring_free(struct task_struct *tsk); void io_uring_unreg_ringfd(void); +const char *io_uring_get_opcode(u8 opcode); static inline void io_uring_files_cancel(void) { @@ -29,6 +55,14 @@ static inline void io_uring_free(struct task_struct *tsk) __io_uring_free(tsk); } #else +static inline void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret, + ssize_t ret2) +{ +} +static inline void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd, + void (*task_work_cb)(struct io_uring_cmd *)) +{ +} static inline struct sock *io_uring_get_socket(struct file *file) { return NULL; @@ -42,6 +76,10 @@ static inline void io_uring_files_cancel(void) static inline void io_uring_free(struct task_struct *tsk) { } +static inline const char *io_uring_get_opcode(u8 opcode) +{ + return ""; +} #endif #endif diff --git a/include/linux/iomap.h b/include/linux/iomap.h index b76f0dd149fb..e552097c67e0 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -188,6 +188,7 @@ struct iomap_iter { unsigned flags; struct iomap iomap; struct iomap srcmap; + void *private; }; int iomap_iter(struct iomap_iter *iter, const struct iomap_ops *ops); @@ -225,10 +226,10 @@ static inline const struct iomap *iomap_iter_srcmap(const struct iomap_iter *i) ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from, const struct iomap_ops *ops); -int iomap_readpage(struct page *page, const struct iomap_ops *ops); +int iomap_read_folio(struct folio *folio, const struct iomap_ops *ops); void iomap_readahead(struct readahead_control *, const struct iomap_ops *ops); bool iomap_is_partially_uptodate(struct folio *, size_t from, size_t count); -int iomap_releasepage(struct page *page, gfp_t gfp_mask); +bool iomap_release_folio(struct folio *folio, gfp_t gfp_flags); void iomap_invalidate_folio(struct folio *folio, size_t offset, size_t len); #ifdef CONFIG_MIGRATION int iomap_migrate_page(struct address_space *mapping, struct page *newpage, @@ -320,6 +321,16 @@ struct iomap_dio_ops { unsigned flags); void (*submit_io)(const struct iomap_iter *iter, struct bio *bio, loff_t file_offset); + + /* + * Filesystems wishing to attach private information to a direct io bio + * must provide a ->submit_io method that attaches the additional + * information to the bio and changes the ->bi_end_io callback to a + * custom function. This function should, at a minimum, perform any + * relevant post-processing of the bio and end with a call to + * iomap_dio_bio_end_io. + */ + struct bio_set *bio_set; }; /* @@ -344,11 +355,12 @@ struct iomap_dio_ops { ssize_t iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, const struct iomap_ops *ops, const struct iomap_dio_ops *dops, - unsigned int dio_flags, size_t done_before); + unsigned int dio_flags, void *private, size_t done_before); struct iomap_dio *__iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, const struct iomap_ops *ops, const struct iomap_dio_ops *dops, - unsigned int dio_flags, size_t done_before); + unsigned int dio_flags, void *private, size_t done_before); ssize_t iomap_dio_complete(struct iomap_dio *dio); +void iomap_dio_bio_end_io(struct bio *bio); #ifdef CONFIG_SWAP struct file; diff --git a/include/linux/ipmi.h b/include/linux/ipmi.h index 163831a087ef..a1c9c0d48ebf 100644 --- a/include/linux/ipmi.h +++ b/include/linux/ipmi.h @@ -72,6 +72,11 @@ struct ipmi_recv_msg { unsigned char msg_data[IPMI_MAX_MSG_LENGTH]; }; +#define INIT_IPMI_RECV_MSG(done_handler) \ +{ \ + .done = done_handler \ +} + /* Allocate and free the receive message. */ void ipmi_free_recv_msg(struct ipmi_recv_msg *msg); diff --git a/include/linux/ipmi_smi.h b/include/linux/ipmi_smi.h index 9277d21c2690..5d69820d8b02 100644 --- a/include/linux/ipmi_smi.h +++ b/include/linux/ipmi_smi.h @@ -125,6 +125,12 @@ struct ipmi_smi_msg { void (*done)(struct ipmi_smi_msg *msg); }; +#define INIT_IPMI_SMI_MSG(done_handler) \ +{ \ + .done = done_handler, \ + .type = IPMI_SMI_MSG_TYPE_NORMAL \ +} + struct ipmi_smi_handlers { struct module *owner; diff --git a/include/linux/irq.h b/include/linux/irq.h index f92788ccdba2..505308253d23 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -569,6 +569,7 @@ struct irq_chip { * IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND: Invokes __enable_irq()/__disable_irq() for wake irqs * in the suspend path if they are in disabled state * IRQCHIP_AFFINITY_PRE_STARTUP: Default affinity update before startup + * IRQCHIP_IMMUTABLE: Don't ever change anything in this chip */ enum { IRQCHIP_SET_TYPE_MASKED = (1 << 0), @@ -582,6 +583,7 @@ enum { IRQCHIP_SUPPORTS_NMI = (1 << 8), IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND = (1 << 9), IRQCHIP_AFFINITY_PRE_STARTUP = (1 << 10), + IRQCHIP_IMMUTABLE = (1 << 11), }; #include <linux/irqdesc.h> diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 12d91f0dedf9..728691365464 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -127,6 +127,8 @@ #define GICR_PIDR2 GICD_PIDR2 #define GICR_CTLR_ENABLE_LPIS (1UL << 0) +#define GICR_CTLR_CES (1UL << 1) +#define GICR_CTLR_IR (1UL << 2) #define GICR_CTLR_RWP (1UL << 3) #define GICR_TYPER_CPU_NUMBER(r) (((r) >> 8) & 0xffff) diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h index 4b140938b03e..5ec0fa71399e 100644 --- a/include/linux/irqflags.h +++ b/include/linux/irqflags.h @@ -20,13 +20,13 @@ #ifdef CONFIG_PROVE_LOCKING extern void lockdep_softirqs_on(unsigned long ip); extern void lockdep_softirqs_off(unsigned long ip); - extern void lockdep_hardirqs_on_prepare(unsigned long ip); + extern void lockdep_hardirqs_on_prepare(void); extern void lockdep_hardirqs_on(unsigned long ip); extern void lockdep_hardirqs_off(unsigned long ip); #else static inline void lockdep_softirqs_on(unsigned long ip) { } static inline void lockdep_softirqs_off(unsigned long ip) { } - static inline void lockdep_hardirqs_on_prepare(unsigned long ip) { } + static inline void lockdep_hardirqs_on_prepare(void) { } static inline void lockdep_hardirqs_on(unsigned long ip) { } static inline void lockdep_hardirqs_off(unsigned long ip) { } #endif diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index de9536680b2b..e79d6e0b14e8 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1529,7 +1529,7 @@ extern int jbd2_journal_dirty_metadata (handle_t *, struct buffer_head *); extern int jbd2_journal_forget (handle_t *, struct buffer_head *); int jbd2_journal_invalidate_folio(journal_t *, struct folio *, size_t offset, size_t length); -extern int jbd2_journal_try_to_free_buffers(journal_t *journal, struct page *page); +bool jbd2_journal_try_to_free_buffers(journal_t *journal, struct folio *folio); extern int jbd2_journal_stop(handle_t *); extern int jbd2_journal_flush(journal_t *journal, unsigned int flags); extern void jbd2_journal_lock_updates (journal_t *); diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 08ba5995aa8b..fe6efb24d151 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -64,15 +64,6 @@ ) /** - * lower_48_bits() - return bits 0-47 of a number - * @n: the number we're accessing - */ -static inline u64 lower_48_bits(u64 n) -{ - return n & ((1ull << 48) - 1); -} - -/** * upper_32_bits - return bits 32-63 of a number * @n: the number we're accessing * @@ -294,7 +285,7 @@ static inline char *hex_byte_pack_upper(char *buf, u8 byte) return buf; } -extern int hex_to_bin(char ch); +extern int hex_to_bin(unsigned char ch); extern int __must_check hex2bin(u8 *dst, const char *src, size_t count); extern char *bin2hex(char *dst, const void *src, size_t count); diff --git a/include/linux/kfence.h b/include/linux/kfence.h index f49e64222628..726857a4b680 100644 --- a/include/linux/kfence.h +++ b/include/linux/kfence.h @@ -204,6 +204,22 @@ static __always_inline __must_check bool kfence_free(void *addr) */ bool __must_check kfence_handle_page_fault(unsigned long addr, bool is_write, struct pt_regs *regs); +#ifdef CONFIG_PRINTK +struct kmem_obj_info; +/** + * __kfence_obj_info() - fill kmem_obj_info struct + * @kpp: kmem_obj_info to be filled + * @object: the object + * + * Return: + * * false - not a KFENCE object + * * true - a KFENCE object, filled @kpp + * + * Copies information to @kpp for KFENCE objects. + */ +bool __kfence_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab); +#endif + #else /* CONFIG_KFENCE */ static inline bool is_kfence_address(const void *addr) { return false; } @@ -221,6 +237,14 @@ static inline bool __must_check kfence_handle_page_fault(unsigned long addr, boo return false; } +#ifdef CONFIG_PRINTK +struct kmem_obj_info; +static inline bool __kfence_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab) +{ + return false; +} +#endif + #endif #endif /* _LINUX_KFENCE_H */ diff --git a/include/linux/kobject.h b/include/linux/kobject.h index c7b47399b36a..57fb972fea05 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -120,7 +120,6 @@ extern char *kobject_get_path(struct kobject *kobj, gfp_t flag); struct kobj_type { void (*release)(struct kobject *kobj); const struct sysfs_ops *sysfs_ops; - struct attribute **default_attrs; /* use default_groups instead */ const struct attribute_group **default_groups; const struct kobj_ns_type_operations *(*child_ns_type)(struct kobject *kobj); const void *(*namespace)(struct kobject *kobj); diff --git a/include/linux/kthread.h b/include/linux/kthread.h index de5d75bafd66..30e5bec81d2b 100644 --- a/include/linux/kthread.h +++ b/include/linux/kthread.h @@ -222,9 +222,5 @@ void kthread_associate_blkcg(struct cgroup_subsys_state *css); struct cgroup_subsys_state *kthread_blkcg(void); #else static inline void kthread_associate_blkcg(struct cgroup_subsys_state *css) { } -static inline struct cgroup_subsys_state *kthread_blkcg(void) -{ - return NULL; -} #endif #endif /* _LINUX_KTHREAD_H */ diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 3f9b22c4983a..4640393f20ab 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -315,7 +315,10 @@ struct kvm_vcpu { int cpu; int vcpu_id; /* id given by userspace at creation */ int vcpu_idx; /* index in kvm->vcpus array */ - int srcu_idx; + int ____srcu_idx; /* Don't use this directly. You've been warned. */ +#ifdef CONFIG_PROVE_RCU + int srcu_depth; +#endif int mode; u64 requests; unsigned long guest_debug; @@ -450,7 +453,7 @@ static __always_inline void guest_state_enter_irqoff(void) { instrumentation_begin(); trace_hardirqs_on_prepare(); - lockdep_hardirqs_on_prepare(CALLER_ADDR0); + lockdep_hardirqs_on_prepare(); instrumentation_end(); guest_context_enter_irqoff(); @@ -840,6 +843,25 @@ static inline void kvm_vm_bugged(struct kvm *kvm) unlikely(__ret); \ }) +static inline void kvm_vcpu_srcu_read_lock(struct kvm_vcpu *vcpu) +{ +#ifdef CONFIG_PROVE_RCU + WARN_ONCE(vcpu->srcu_depth++, + "KVM: Illegal vCPU srcu_idx LOCK, depth=%d", vcpu->srcu_depth - 1); +#endif + vcpu->____srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); +} + +static inline void kvm_vcpu_srcu_read_unlock(struct kvm_vcpu *vcpu) +{ + srcu_read_unlock(&vcpu->kvm->srcu, vcpu->____srcu_idx); + +#ifdef CONFIG_PROVE_RCU + WARN_ONCE(--vcpu->srcu_depth, + "KVM: Illegal vCPU srcu_idx UNLOCK, depth=%d", vcpu->srcu_depth); +#endif +} + static inline bool kvm_dirty_log_manual_protect_and_init_set(struct kvm *kvm) { return !!(kvm->manual_dirty_log_protect & KVM_DIRTY_LOG_INITIALLY_SET); @@ -2197,6 +2219,8 @@ static inline long kvm_arch_vcpu_async_ioctl(struct file *filp, void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, unsigned long start, unsigned long end); +void kvm_arch_guest_memory_reclaimed(struct kvm *kvm); + #ifdef CONFIG_HAVE_KVM_VCPU_RUN_PID_CHANGE int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu); #else diff --git a/include/linux/libata.h b/include/linux/libata.h index 9b1d3d8b1252..732de9014626 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -820,7 +820,6 @@ struct ata_port { unsigned int cbl; /* cable type; ATA_CBL_xxx */ struct ata_queued_cmd qcmd[ATA_MAX_QUEUE + 1]; - unsigned long sas_tag_allocated; /* for sas tag allocation only */ u64 qc_active; int nr_active_links; /* #links with active qcs */ unsigned int sas_last_tag; /* track next tag hw expects */ @@ -1111,7 +1110,7 @@ extern void ata_unpack_xfermask(unsigned long xfer_mask, unsigned long *udma_mask); extern u8 ata_xfer_mask2mode(unsigned long xfer_mask); extern unsigned long ata_xfer_mode2mask(u8 xfer_mode); -extern int ata_xfer_mode2shift(unsigned long xfer_mode); +extern int ata_xfer_mode2shift(u8 xfer_mode); extern const char *ata_mode_string(unsigned long xfer_mask); extern unsigned long ata_id_xfermask(const u16 *id); extern int ata_std_qc_defer(struct ata_queued_cmd *qc); diff --git a/include/linux/linkage.h b/include/linux/linkage.h index acb1ad2356f1..1feab6136b5b 100644 --- a/include/linux/linkage.h +++ b/include/linux/linkage.h @@ -171,12 +171,9 @@ /* SYM_ALIAS -- use only if you have to */ #ifndef SYM_ALIAS -#define SYM_ALIAS(alias, name, sym_type, linkage) \ - linkage(alias) ASM_NL \ - .set alias, name ASM_NL \ - .type alias sym_type ASM_NL \ - .set .L__sym_size_##alias, .L__sym_size_##name ASM_NL \ - .size alias, .L__sym_size_##alias +#define SYM_ALIAS(alias, name, linkage) \ + linkage(alias) ASM_NL \ + .set alias, name ASM_NL #endif /* === code annotations === */ @@ -261,7 +258,7 @@ */ #ifndef SYM_FUNC_ALIAS #define SYM_FUNC_ALIAS(alias, name) \ - SYM_ALIAS(alias, name, SYM_T_FUNC, SYM_L_GLOBAL) + SYM_ALIAS(alias, name, SYM_L_GLOBAL) #endif /* @@ -269,7 +266,7 @@ */ #ifndef SYM_FUNC_ALIAS_LOCAL #define SYM_FUNC_ALIAS_LOCAL(alias, name) \ - SYM_ALIAS(alias, name, SYM_T_FUNC, SYM_L_LOCAL) + SYM_ALIAS(alias, name, SYM_L_LOCAL) #endif /* @@ -277,7 +274,7 @@ */ #ifndef SYM_FUNC_ALIAS_WEAK #define SYM_FUNC_ALIAS_WEAK(alias, name) \ - SYM_ALIAS(alias, name, SYM_T_FUNC, SYM_L_WEAK) + SYM_ALIAS(alias, name, SYM_L_WEAK) #endif /* SYM_CODE_START -- use for non-C (special) functions */ diff --git a/include/linux/local_lock_internal.h b/include/linux/local_lock_internal.h index 6d635e8306d6..975e33b793a7 100644 --- a/include/linux/local_lock_internal.h +++ b/include/linux/local_lock_internal.h @@ -44,9 +44,9 @@ static inline void local_lock_debug_init(local_lock_t *l) } #else /* CONFIG_DEBUG_LOCK_ALLOC */ # define LOCAL_LOCK_DEBUG_INIT(lockname) -# define local_lock_acquire(__ll) do { typecheck(local_lock_t *, __ll); } while (0) -# define local_lock_release(__ll) do { typecheck(local_lock_t *, __ll); } while (0) -# define local_lock_debug_init(__ll) do { typecheck(local_lock_t *, __ll); } while (0) +static inline void local_lock_acquire(local_lock_t *l) { } +static inline void local_lock_release(local_lock_t *l) { } +static inline void local_lock_debug_init(local_lock_t *l) { } #endif /* !CONFIG_DEBUG_LOCK_ALLOC */ #define INIT_LOCAL_LOCK(lockname) { LOCAL_LOCK_DEBUG_INIT(lockname) } diff --git a/include/linux/lsm_audit.h b/include/linux/lsm_audit.h index 17d02eda9538..97a8b21eb033 100644 --- a/include/linux/lsm_audit.h +++ b/include/linux/lsm_audit.h @@ -76,6 +76,7 @@ struct common_audit_data { #define LSM_AUDIT_DATA_IBENDPORT 14 #define LSM_AUDIT_DATA_LOCKDOWN 15 #define LSM_AUDIT_DATA_NOTIFICATION 16 +#define LSM_AUDIT_DATA_ANONINODE 17 union { struct path path; struct dentry *dentry; @@ -96,6 +97,7 @@ struct common_audit_data { struct lsm_ibpkey_audit *ibpkey; struct lsm_ibendport_audit *ibendport; int reason; + const char *anonclass; } u; /* this union contains LSM specific data */ union { diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index db924fe379c9..eafa1d2489fd 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -100,7 +100,7 @@ LSM_HOOK(int, 0, path_link, struct dentry *old_dentry, const struct path *new_dir, struct dentry *new_dentry) LSM_HOOK(int, 0, path_rename, const struct path *old_dir, struct dentry *old_dentry, const struct path *new_dir, - struct dentry *new_dentry) + struct dentry *new_dentry, unsigned int flags) LSM_HOOK(int, 0, path_chmod, const struct path *path, umode_t mode) LSM_HOOK(int, 0, path_chown, const struct path *path, kuid_t uid, kgid_t gid) LSM_HOOK(int, 0, path_chroot, const struct path *path) diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 419b5febc3ca..91c8146649f5 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -358,6 +358,7 @@ * @old_dentry contains the dentry structure of the old link. * @new_dir contains the path structure for parent of the new link. * @new_dentry contains the dentry structure of the new link. + * @flags may contain rename options such as RENAME_EXCHANGE. * Return 0 if permission is granted. * @path_chmod: * Check for permission to change a mode of the file @path. The new @@ -1595,7 +1596,7 @@ struct security_hook_list { struct hlist_node list; struct hlist_head *head; union security_list_options hook; - char *lsm; + const char *lsm; } __randomize_layout; /* @@ -1630,7 +1631,7 @@ extern struct security_hook_heads security_hook_heads; extern char *lsm_names; extern void security_add_hooks(struct security_hook_list *hooks, int count, - char *lsm); + const char *lsm); #define LSM_FLAG_LEGACY_MAJOR BIT(0) #define LSM_FLAG_EXCLUSIVE BIT(1) diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index a68dce3873fc..89b14729d59f 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1012,6 +1012,7 @@ static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec, } void mem_cgroup_flush_stats(void); +void mem_cgroup_flush_stats_delayed(void); void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val); @@ -1455,6 +1456,10 @@ static inline void mem_cgroup_flush_stats(void) { } +static inline void mem_cgroup_flush_stats_delayed(void) +{ +} + static inline void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val) { diff --git a/include/linux/mm.h b/include/linux/mm.h index e34edb775334..b0183450e484 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2677,6 +2677,7 @@ extern int install_special_mapping(struct mm_struct *mm, unsigned long flags, struct page **pages); unsigned long randomize_stack_top(unsigned long stack_top); +unsigned long randomize_page(unsigned long start, unsigned long range); extern unsigned long get_unmapped_area(struct file *, unsigned long, unsigned long, unsigned long, unsigned long); @@ -3197,6 +3198,14 @@ extern int sysctl_memory_failure_recovery; extern void shake_page(struct page *p); extern atomic_long_t num_poisoned_pages __read_mostly; extern int soft_offline_page(unsigned long pfn, int flags); +#ifdef CONFIG_MEMORY_FAILURE +extern int __get_huge_page_for_hwpoison(unsigned long pfn, int flags); +#else +static inline int __get_huge_page_for_hwpoison(unsigned long pfn, int flags) +{ + return 0; +} +#endif #ifndef arch_memory_failure static inline int arch_memory_failure(unsigned long pfn, int flags) diff --git a/include/linux/mmc/core.h b/include/linux/mmc/core.h index 71101d1ec825..6efec0b9820c 100644 --- a/include/linux/mmc/core.h +++ b/include/linux/mmc/core.h @@ -175,8 +175,8 @@ void mmc_wait_for_req(struct mmc_host *host, struct mmc_request *mrq); int mmc_wait_for_cmd(struct mmc_host *host, struct mmc_command *cmd, int retries); -int mmc_hw_reset(struct mmc_host *host); -int mmc_sw_reset(struct mmc_host *host); +int mmc_hw_reset(struct mmc_card *card); +int mmc_sw_reset(struct mmc_card *card); void mmc_set_data_timeout(struct mmc_data *data, const struct mmc_card *card); #endif /* LINUX_MMC_CORE_H */ diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 7afb57cab00b..c193c50ccd78 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -181,7 +181,7 @@ struct mmc_host_ops { unsigned int max_dtr, int host_drv, int card_drv, int *drv_type); /* Reset the eMMC card via RST_n */ - void (*hw_reset)(struct mmc_host *host); + void (*card_hw_reset)(struct mmc_host *host); void (*card_event)(struct mmc_host *host); /* diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 962b14d403e8..46ffab808f03 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1397,13 +1397,16 @@ static inline unsigned long *section_to_usemap(struct mem_section *ms) static inline struct mem_section *__nr_to_section(unsigned long nr) { + unsigned long root = SECTION_NR_TO_ROOT(nr); + + if (unlikely(root >= NR_SECTION_ROOTS)) + return NULL; + #ifdef CONFIG_SPARSEMEM_EXTREME - if (!mem_section) + if (!mem_section || !mem_section[root]) return NULL; #endif - if (!mem_section[SECTION_NR_TO_ROOT(nr)]) - return NULL; - return &mem_section[SECTION_NR_TO_ROOT(nr)][nr & SECTION_ROOT_MASK]; + return &mem_section[root][nr & SECTION_ROOT_MASK]; } extern size_t mem_section_usage_size(void); diff --git a/include/linux/mpage.h b/include/linux/mpage.h index f4f5e90a6844..43986f7ec4dd 100644 --- a/include/linux/mpage.h +++ b/include/linux/mpage.h @@ -16,7 +16,7 @@ struct writeback_control; struct readahead_control; void mpage_readahead(struct readahead_control *, get_block_t get_block); -int mpage_readpage(struct page *page, get_block_t get_block); +int mpage_read_folio(struct folio *folio, get_block_t get_block); int mpage_writepages(struct address_space *mapping, struct writeback_control *wbc, get_block_t get_block); int mpage_writepage(struct page *page, get_block_t *get_block, diff --git a/include/linux/mtd/cfi.h b/include/linux/mtd/cfi.h index fd1ecb821106..d88bb56c18e2 100644 --- a/include/linux/mtd/cfi.h +++ b/include/linux/mtd/cfi.h @@ -286,6 +286,7 @@ struct cfi_private { map_word sector_erase_cmd; unsigned long chipshift; /* Because they're of the same type */ const char *im_name; /* inter_module name for cmdset_setup */ + unsigned long quirks; struct flchip chips[]; /* per-chip data structure for each chip */ }; diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h index 151607e9d64a..955aee14b0f7 100644 --- a/include/linux/mtd/mtd.h +++ b/include/linux/mtd/mtd.h @@ -389,10 +389,8 @@ struct mtd_info { /* List of partitions attached to this MTD device */ struct list_head partitions; - union { - struct mtd_part part; - struct mtd_master master; - }; + struct mtd_part part; + struct mtd_master master; }; static inline struct mtd_info *mtd_get_master(struct mtd_info *mtd) diff --git a/drivers/mtd/nand/raw/mtk_ecc.h b/include/linux/mtd/nand-ecc-mtk.h index 0e48c36e6ca0..0e48c36e6ca0 100644 --- a/drivers/mtd/nand/raw/mtk_ecc.h +++ b/include/linux/mtd/nand-ecc-mtk.h diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index 5e25a7b75ae2..1ede4c89805a 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -47,8 +47,6 @@ #define SPINOR_OP_RDID 0x9f /* Read JEDEC ID */ #define SPINOR_OP_RDSFDP 0x5a /* Read SFDP */ #define SPINOR_OP_RDCR 0x35 /* Read configuration register */ -#define SPINOR_OP_RDEAR 0xc8 /* Read Extended Address Register */ -#define SPINOR_OP_WREAR 0xc5 /* Write Extended Address Register */ #define SPINOR_OP_SRSTEN 0x66 /* Software Reset Enable */ #define SPINOR_OP_SRST 0x99 /* Software Reset */ #define SPINOR_OP_GBULK 0x98 /* Global Block Unlock */ @@ -365,6 +363,7 @@ struct spi_nor_flash_parameter; * @write_proto: the SPI protocol for write operations * @reg_proto: the SPI protocol for read_reg/write_reg/erase operations * @sfdp: the SFDP data of the flash + * @debugfs_root: pointer to the debugfs directory * @controller_ops: SPI NOR controller driver specific operations. * @params: [FLASH-SPECIFIC] SPI NOR flash parameters and settings. * The structure includes legacy flash parameters and @@ -394,6 +393,7 @@ struct spi_nor { u32 flags; enum spi_nor_cmd_ext cmd_ext_type; struct sfdp *sfdp; + struct dentry *debugfs_root; const struct spi_nor_controller_ops *controller_ops; diff --git a/include/linux/mtd/spinand.h b/include/linux/mtd/spinand.h index 3aa28240a77f..5584d3bb6556 100644 --- a/include/linux/mtd/spinand.h +++ b/include/linux/mtd/spinand.h @@ -266,6 +266,7 @@ extern const struct spinand_manufacturer micron_spinand_manufacturer; extern const struct spinand_manufacturer paragon_spinand_manufacturer; extern const struct spinand_manufacturer toshiba_spinand_manufacturer; extern const struct spinand_manufacturer winbond_spinand_manufacturer; +extern const struct spinand_manufacturer xtx_spinand_manufacturer; /** * struct spinand_op_variants - SPI NAND operation variants diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index 2c6b9e416225..7c2d77d75a88 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -169,7 +169,7 @@ enum { #define NETIF_F_HW_HSR_FWD __NETIF_F(HW_HSR_FWD) #define NETIF_F_HW_HSR_DUP __NETIF_F(HW_HSR_DUP) -/* Finds the next feature with the highest number of the range of start till 0. +/* Finds the next feature with the highest number of the range of start-1 till 0. */ static inline int find_next_netdev_feature(u64 feature, unsigned long start) { @@ -188,7 +188,7 @@ static inline int find_next_netdev_feature(u64 feature, unsigned long start) for ((bit) = find_next_netdev_feature((mask_addr), \ NETDEV_FEATURE_COUNT); \ (bit) >= 0; \ - (bit) = find_next_netdev_feature((mask_addr), (bit) - 1)) + (bit) = find_next_netdev_feature((mask_addr), (bit))) /* Features valid for ethtool to change */ /* = all defined minus driver/device-class-related */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 59e27a2b7bf0..f736c020cde2 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -199,10 +199,10 @@ struct net_device_stats { * Try to fit them in a single cache line, for dev_get_stats() sake. */ struct net_device_core_stats { - local_t rx_dropped; - local_t tx_dropped; - local_t rx_nohandler; -} __aligned(4 * sizeof(local_t)); + unsigned long rx_dropped; + unsigned long tx_dropped; + unsigned long rx_nohandler; +} __aligned(4 * sizeof(unsigned long)); #include <linux/cache.h> #include <linux/skbuff.h> @@ -900,7 +900,7 @@ struct net_device_path_stack { struct net_device_path_ctx { const struct net_device *dev; - const u8 *daddr; + u8 daddr[ETH_ALEN]; int num_vlans; struct { @@ -3843,15 +3843,15 @@ static __always_inline bool __is_skb_forwardable(const struct net_device *dev, return false; } -struct net_device_core_stats *netdev_core_stats_alloc(struct net_device *dev); +struct net_device_core_stats __percpu *netdev_core_stats_alloc(struct net_device *dev); -static inline struct net_device_core_stats *dev_core_stats(struct net_device *dev) +static inline struct net_device_core_stats __percpu *dev_core_stats(struct net_device *dev) { /* This READ_ONCE() pairs with the write in netdev_core_stats_alloc() */ struct net_device_core_stats __percpu *p = READ_ONCE(dev->core_stats); if (likely(p)) - return this_cpu_ptr(p); + return p; return netdev_core_stats_alloc(dev); } @@ -3859,14 +3859,11 @@ static inline struct net_device_core_stats *dev_core_stats(struct net_device *de #define DEV_CORE_STATS_INC(FIELD) \ static inline void dev_core_stats_##FIELD##_inc(struct net_device *dev) \ { \ - struct net_device_core_stats *p; \ + struct net_device_core_stats __percpu *p; \ \ - preempt_disable(); \ p = dev_core_stats(dev); \ - \ if (p) \ - local_inc(&p->FIELD); \ - preempt_enable(); \ + this_cpu_inc(p->FIELD); \ } DEV_CORE_STATS_INC(rx_dropped) DEV_CORE_STATS_INC(tx_dropped) diff --git a/include/linux/netfs.h b/include/linux/netfs.h index c7bf1eaf51d5..77fa6a61706a 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -159,6 +159,7 @@ struct netfs_io_subrequest { #define NETFS_SREQ_SHORT_IO 2 /* Set if the I/O was short */ #define NETFS_SREQ_SEEK_DATA_READ 3 /* Set if ->read() should SEEK_DATA first */ #define NETFS_SREQ_NO_PROGRESS 4 /* Set if we didn't manage to read any data */ +#define NETFS_SREQ_ONDEMAND 5 /* Set if it's from on-demand read mode */ }; enum netfs_io_origin { @@ -274,9 +275,9 @@ struct netfs_cache_ops { struct readahead_control; extern void netfs_readahead(struct readahead_control *); -extern int netfs_readpage(struct file *, struct page *); +int netfs_read_folio(struct file *, struct folio *); extern int netfs_write_begin(struct file *, struct address_space *, - loff_t, unsigned int, unsigned int, struct folio **, + loff_t, unsigned int, struct folio **, void **); extern void netfs_subreq_terminated(struct netfs_io_subrequest *, ssize_t, bool); @@ -295,7 +296,7 @@ extern void netfs_stats_show(struct seq_file *); */ static inline struct netfs_i_context *netfs_i_context(struct inode *inode) { - return (struct netfs_i_context *)(inode + 1); + return (void *)inode + sizeof(*inode); } /** @@ -307,7 +308,7 @@ static inline struct netfs_i_context *netfs_i_context(struct inode *inode) */ static inline struct inode *netfs_inode(struct netfs_i_context *ctx) { - return ((struct inode *)ctx) - 1; + return (void *)ctx - sizeof(struct inode); } /** diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index b48b9259e02c..1bba71757d62 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -594,7 +594,7 @@ static inline bool nfs_have_writebacks(const struct inode *inode) /* * linux/fs/nfs/read.c */ -extern int nfs_readpage(struct file *, struct page *); +int nfs_read_folio(struct file *, struct folio *); void nfs_readahead(struct readahead_control *); /* diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 49ba486aea5f..2863e5a69c6a 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1694,6 +1694,7 @@ struct nfs_unlinkdata { struct nfs_renamedata { struct nfs_renameargs args; struct nfs_renameres res; + struct rpc_task task; const struct cred *cred; struct inode *old_dir; struct dentry *old_dentry; diff --git a/include/linux/nvme.h b/include/linux/nvme.h index f626a445d1a8..29ec3e3481ff 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -137,6 +137,7 @@ enum { NVME_REG_CMBMSC = 0x0050, /* Controller Memory Buffer Memory * Space Control */ + NVME_REG_CRTO = 0x0068, /* Controller Ready Timeouts */ NVME_REG_PMRCAP = 0x0e00, /* Persistent Memory Capabilities */ NVME_REG_PMRCTL = 0x0e04, /* Persistent Memory Region Control */ NVME_REG_PMRSTS = 0x0e08, /* Persistent Memory Region Status */ @@ -161,6 +162,9 @@ enum { #define NVME_CMB_BIR(cmbloc) ((cmbloc) & 0x7) #define NVME_CMB_OFST(cmbloc) (((cmbloc) >> 12) & 0xfffff) +#define NVME_CRTO_CRIMT(crto) ((crto) >> 16) +#define NVME_CRTO_CRWMT(crto) ((crto) & 0xffff) + enum { NVME_CMBSZ_SQS = 1 << 0, NVME_CMBSZ_CQS = 1 << 1, @@ -204,8 +208,10 @@ enum { NVME_CC_SHN_MASK = 3 << NVME_CC_SHN_SHIFT, NVME_CC_IOSQES = NVME_NVM_IOSQES << NVME_CC_IOSQES_SHIFT, NVME_CC_IOCQES = NVME_NVM_IOCQES << NVME_CC_IOCQES_SHIFT, - NVME_CAP_CSS_NVM = 1 << 0, - NVME_CAP_CSS_CSI = 1 << 6, + NVME_CC_CRIME = 1 << 24, +}; + +enum { NVME_CSTS_RDY = 1 << 0, NVME_CSTS_CFS = 1 << 1, NVME_CSTS_NSSRO = 1 << 4, @@ -214,10 +220,23 @@ enum { NVME_CSTS_SHST_OCCUR = 1 << 2, NVME_CSTS_SHST_CMPLT = 2 << 2, NVME_CSTS_SHST_MASK = 3 << 2, +}; + +enum { NVME_CMBMSC_CRE = 1 << 0, NVME_CMBMSC_CMSE = 1 << 1, }; +enum { + NVME_CAP_CSS_NVM = 1 << 0, + NVME_CAP_CSS_CSI = 1 << 6, +}; + +enum { + NVME_CAP_CRMS_CRIMS = 1ULL << 59, + NVME_CAP_CRMS_CRWMS = 1ULL << 60, +}; + struct nvme_id_power_state { __le16 max_power; /* centiwatts */ __u8 rsvd2; @@ -405,6 +424,21 @@ struct nvme_id_ns { __u8 vs[3712]; }; +/* I/O Command Set Independent Identify Namespace Data Structure */ +struct nvme_id_ns_cs_indep { + __u8 nsfeat; + __u8 nmic; + __u8 rescap; + __u8 fpi; + __le32 anagrpid; + __u8 nsattr; + __u8 rsvd9; + __le16 nvmsetid; + __le16 endgid; + __u8 nstat; + __u8 rsvd15[4081]; +}; + struct nvme_zns_lbafe { __le64 zsze; __u8 zdes; @@ -469,6 +503,7 @@ enum { NVME_ID_CNS_NS_DESC_LIST = 0x03, NVME_ID_CNS_CS_NS = 0x05, NVME_ID_CNS_CS_CTRL = 0x06, + NVME_ID_CNS_NS_CS_INDEP = 0x08, NVME_ID_CNS_NS_PRESENT_LIST = 0x10, NVME_ID_CNS_NS_PRESENT = 0x11, NVME_ID_CNS_CTRL_NS_LIST = 0x12, @@ -523,6 +558,10 @@ enum { }; enum { + NVME_NSTAT_NRDY = 1 << 0, +}; + +enum { NVME_NVM_NS_16B_GUARD = 0, NVME_NVM_NS_32B_GUARD = 1, NVME_NVM_NS_64B_GUARD = 2, @@ -1583,6 +1622,7 @@ enum { NVME_SC_NS_WRITE_PROTECTED = 0x20, NVME_SC_CMD_INTERRUPTED = 0x21, NVME_SC_TRANSIENT_TR_ERR = 0x22, + NVME_SC_ADMIN_COMMAND_MEDIA_NOT_READY = 0x24, NVME_SC_INVALID_IO_CMD_SET = 0x2C, NVME_SC_LBA_RANGE = 0x80, @@ -1679,9 +1719,11 @@ enum { /* * Path-related Errors: */ + NVME_SC_INTERNAL_PATH_ERROR = 0x300, NVME_SC_ANA_PERSISTENT_LOSS = 0x301, NVME_SC_ANA_INACCESSIBLE = 0x302, NVME_SC_ANA_TRANSITION = 0x303, + NVME_SC_CTRL_PATH_ERROR = 0x360, NVME_SC_HOST_PATH_ERROR = 0x370, NVME_SC_HOST_ABORTED_CMD = 0x371, diff --git a/include/linux/objtool.h b/include/linux/objtool.h index 586d35720f13..6491fa8fba6d 100644 --- a/include/linux/objtool.h +++ b/include/linux/objtool.h @@ -38,7 +38,9 @@ struct unwind_hint { #define UNWIND_HINT_TYPE_REGS_PARTIAL 2 #define UNWIND_HINT_TYPE_FUNC 3 -#ifdef CONFIG_STACK_VALIDATION +#ifdef CONFIG_OBJTOOL + +#include <asm/asm.h> #ifndef __ASSEMBLY__ @@ -137,7 +139,7 @@ struct unwind_hint { .macro STACK_FRAME_NON_STANDARD func:req .pushsection .discard.func_stack_frame_non_standard, "aw" - .long \func - . + _ASM_PTR \func .popsection .endm @@ -157,7 +159,7 @@ struct unwind_hint { #endif /* __ASSEMBLY__ */ -#else /* !CONFIG_STACK_VALIDATION */ +#else /* !CONFIG_OBJTOOL */ #ifndef __ASSEMBLY__ @@ -179,6 +181,6 @@ struct unwind_hint { .endm #endif -#endif /* CONFIG_STACK_VALIDATION */ +#endif /* CONFIG_OBJTOOL */ #endif /* _LINUX_OBJTOOL_H */ diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 9d8eeaa67d05..af10149a6c31 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -516,7 +516,7 @@ PAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL) /* * Private page markings that may be used by the filesystem that owns the page * for its own purposes. - * - PG_private and PG_private_2 cause releasepage() and co to be invoked + * - PG_private and PG_private_2 cause release_folio() and co to be invoked */ PAGEFLAG(Private, private, PF_ANY) PAGEFLAG(Private2, private_2, PF_ANY) TESTSCFLAG(Private2, private_2, PF_ANY) diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 993994cd943a..ce96866fbec4 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -492,7 +492,7 @@ static inline gfp_t readahead_gfp_mask(struct address_space *x) return mapping_gfp_mask(x) | __GFP_NORETRY | __GFP_NOWARN; } -typedef int filler_t(void *, struct page *); +typedef int filler_t(struct file *, struct folio *); pgoff_t page_cache_next_miss(struct address_space *mapping, pgoff_t index, unsigned long max_scan); @@ -735,7 +735,7 @@ static inline unsigned find_get_pages_tag(struct address_space *mapping, } struct page *grab_cache_page_write_begin(struct address_space *mapping, - pgoff_t index, unsigned flags); + pgoff_t index); /* * Returns locked page at given index in given cache, creating it if needed. @@ -747,9 +747,9 @@ static inline struct page *grab_cache_page(struct address_space *mapping, } struct folio *read_cache_folio(struct address_space *, pgoff_t index, - filler_t *filler, void *data); + filler_t *filler, struct file *file); struct page *read_cache_page(struct address_space *, pgoff_t index, - filler_t *filler, void *data); + filler_t *filler, struct file *file); extern struct page * read_cache_page_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp_mask); @@ -888,6 +888,18 @@ bool __folio_lock_or_retry(struct folio *folio, struct mm_struct *mm, void unlock_page(struct page *page); void folio_unlock(struct folio *folio); +/** + * folio_trylock() - Attempt to lock a folio. + * @folio: The folio to attempt to lock. + * + * Sometimes it is undesirable to wait for a folio to be unlocked (eg + * when the locks are being taken in the wrong order, or if making + * progress through a batch of folios is more important than processing + * them in order). Usually folio_lock() is the correct function to call. + * + * Context: Any context. + * Return: Whether the lock was successfully acquired. + */ static inline bool folio_trylock(struct folio *folio) { return likely(!test_and_set_bit_lock(PG_locked, folio_flags(folio, 0))); @@ -901,6 +913,28 @@ static inline int trylock_page(struct page *page) return folio_trylock(page_folio(page)); } +/** + * folio_lock() - Lock this folio. + * @folio: The folio to lock. + * + * The folio lock protects against many things, probably more than it + * should. It is primarily held while a folio is being brought uptodate, + * either from its backing file or from swap. It is also held while a + * folio is being truncated from its address_space, so holding the lock + * is sufficient to keep folio->mapping stable. + * + * The folio lock is also held while write() is modifying the page to + * provide POSIX atomicity guarantees (as long as the write does not + * cross a page boundary). Other modifications to the data in the folio + * do not hold the folio lock and can race with writes, eg DMA and stores + * to mapped pages. + * + * Context: May sleep. If you need to acquire the locks of two or + * more folios, they must be in order of ascending index, if they are + * in the same address_space. If they are in different address_spaces, + * acquire the lock of the folio which belongs to the address_space which + * has the lowest address in memory first. + */ static inline void folio_lock(struct folio *folio) { might_sleep(); @@ -908,8 +942,16 @@ static inline void folio_lock(struct folio *folio) __folio_lock(folio); } -/* - * lock_page may only be called if we have the page's inode pinned. +/** + * lock_page() - Lock the folio containing this page. + * @page: The page to lock. + * + * See folio_lock() for a description of what the lock protects. + * This is a legacy function and new code should probably use folio_lock() + * instead. + * + * Context: May sleep. Pages in the same folio share a lock, so do not + * attempt to lock two pages which share a folio. */ static inline void lock_page(struct page *page) { @@ -921,6 +963,16 @@ static inline void lock_page(struct page *page) __folio_lock(folio); } +/** + * folio_lock_killable() - Lock this folio, interruptible by a fatal signal. + * @folio: The folio to lock. + * + * Attempts to lock the folio, like folio_lock(), except that the sleep + * to acquire the lock is interruptible by a fatal signal. + * + * Context: May sleep; see folio_lock(). + * Return: 0 if the lock was acquired; -EINTR if a fatal signal was received. + */ static inline int folio_lock_killable(struct folio *folio) { might_sleep(); @@ -967,8 +1019,8 @@ int folio_wait_bit_killable(struct folio *folio, int bit_nr); * Wait for a folio to be unlocked. * * This must be called with the caller "holding" the folio, - * ie with increased "page->count" so that the folio won't - * go away during the wait.. + * ie with increased folio reference count so that the folio won't + * go away during the wait. */ static inline void folio_wait_locked(struct folio *folio) { @@ -1015,10 +1067,6 @@ static inline void folio_cancel_dirty(struct folio *folio) if (folio_test_dirty(folio)) __folio_cancel_dirty(folio); } -static inline void cancel_dirty_page(struct page *page) -{ - folio_cancel_dirty(page_folio(page)); -} bool folio_clear_dirty_for_io(struct folio *folio); bool clear_page_dirty_for_io(struct page *page); void folio_invalidate(struct folio *folio, size_t offset, size_t length); @@ -1046,6 +1094,7 @@ void folio_add_wait_queue(struct folio *folio, wait_queue_entry_t *waiter); * Fault in userspace address range. */ size_t fault_in_writeable(char __user *uaddr, size_t size); +size_t fault_in_subpage_writeable(char __user *uaddr, size_t size); size_t fault_in_safe_writeable(const char __user *uaddr, size_t size); size_t fault_in_readable(const char __user *uaddr, size_t size); @@ -1190,7 +1239,7 @@ void page_cache_sync_readahead(struct address_space *mapping, * @mapping: address_space which holds the pagecache and I/O vectors * @ra: file_ra_state which holds the readahead state * @file: Used by the filesystem for authentication. - * @page: The page at @index which triggered the readahead call. + * @folio: The folio at @index which triggered the readahead call. * @index: Index of first page to be read. * @req_count: Total number of pages being read by the caller. * @@ -1202,10 +1251,10 @@ void page_cache_sync_readahead(struct address_space *mapping, static inline void page_cache_async_readahead(struct address_space *mapping, struct file_ra_state *ra, struct file *file, - struct page *page, pgoff_t index, unsigned long req_count) + struct folio *folio, pgoff_t index, unsigned long req_count) { DEFINE_READAHEAD(ractl, file, ra, mapping, index); - page_cache_async_ra(&ractl, page_folio(page), req_count); + page_cache_async_ra(&ractl, folio, req_count); } static inline struct folio *__readahead_folio(struct readahead_control *ractl) diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index af97dd427501..da759560eec5 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1063,6 +1063,22 @@ static inline void perf_sample_data_init(struct perf_sample_data *data, data->txn = 0; } +/* + * Clear all bitfields in the perf_branch_entry. + * The to and from fields are not cleared because they are + * systematically modified by caller. + */ +static inline void perf_clear_branch_entry_bitfields(struct perf_branch_entry *br) +{ + br->mispred = 0; + br->predicted = 0; + br->in_tx = 0; + br->abort = 0; + br->cycles = 0; + br->type = 0; + br->reserved = 0; +} + extern void perf_output_sample(struct perf_output_handle *handle, struct perf_event_header *header, struct perf_sample_data *data, @@ -1660,4 +1676,10 @@ typedef int (perf_snapshot_branch_stack_t)(struct perf_branch_entry *entries, unsigned int cnt); DECLARE_STATIC_CALL(perf_snapshot_branch_stack, perf_snapshot_branch_stack_t); +#ifndef PERF_NEEDS_LOPWR_CB +static inline void perf_lopwr_cb(bool mode) +{ +} +#endif + #endif /* _LINUX_PERF_EVENT_H */ diff --git a/include/linux/platform_data/mlxreg.h b/include/linux/platform_data/mlxreg.h index 40185f9d7c14..a6bd74e29b6b 100644 --- a/include/linux/platform_data/mlxreg.h +++ b/include/linux/platform_data/mlxreg.h @@ -216,6 +216,8 @@ struct mlxreg_core_platform_data { * @mask_low: low aggregation interrupt common mask; * @deferred_nr: I2C adapter number must be exist prior probing execution; * @shift_nr: I2C adapter numbers must be incremented by this value; + * @handle: handle to be passed by callback; + * @completion_notify: callback to notify when platform driver probing is done; */ struct mlxreg_core_hotplug_platform_data { struct mlxreg_core_item *items; @@ -228,6 +230,8 @@ struct mlxreg_core_hotplug_platform_data { u32 mask_low; int deferred_nr; int shift_nr; + void *handle; + int (*completion_notify)(void *handle, int id); }; #endif /* __LINUX_PLATFORM_DATA_MLXREG_H */ diff --git a/include/linux/mmc/sh_mmcif.h b/include/linux/platform_data/sh_mmcif.h index e25533b95d9f..6eb914f958f9 100644 --- a/include/linux/mmc/sh_mmcif.h +++ b/include/linux/platform_data/sh_mmcif.h @@ -1,7 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * include/linux/mmc/sh_mmcif.h - * * platform data for eMMC driver * * Copyright (C) 2010 Renesas Solutions Corp. diff --git a/include/linux/platform_data/x86/pmc_atom.h b/include/linux/platform_data/x86/pmc_atom.h index 022bcea9edec..6807839c718b 100644 --- a/include/linux/platform_data/x86/pmc_atom.h +++ b/include/linux/platform_data/x86/pmc_atom.h @@ -144,6 +144,5 @@ #define SLEEP_ENABLE 0x2000 extern int pmc_atom_read(int offset, u32 *value); -extern int pmc_atom_write(int offset, u32 value); #endif /* PMC_ATOM_H */ diff --git a/include/linux/pm.h b/include/linux/pm.h index e65b3ab28377..ffe941958501 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -368,13 +368,13 @@ const struct dev_pm_ops name = { \ #ifdef CONFIG_PM #define _EXPORT_DEV_PM_OPS(name, suspend_fn, resume_fn, runtime_suspend_fn, \ - runtime_resume_fn, idle_fn, sec) \ + runtime_resume_fn, idle_fn, sec, ns) \ _DEFINE_DEV_PM_OPS(name, suspend_fn, resume_fn, runtime_suspend_fn, \ runtime_resume_fn, idle_fn); \ - _EXPORT_SYMBOL(name, sec) + __EXPORT_SYMBOL(name, sec, ns) #else #define _EXPORT_DEV_PM_OPS(name, suspend_fn, resume_fn, runtime_suspend_fn, \ - runtime_resume_fn, idle_fn, sec) \ + runtime_resume_fn, idle_fn, sec, ns) \ static __maybe_unused _DEFINE_DEV_PM_OPS(__static_##name, suspend_fn, \ resume_fn, runtime_suspend_fn, \ runtime_resume_fn, idle_fn) @@ -391,9 +391,13 @@ static __maybe_unused _DEFINE_DEV_PM_OPS(__static_##name, suspend_fn, \ _DEFINE_DEV_PM_OPS(name, suspend_fn, resume_fn, NULL, NULL, NULL) #define EXPORT_SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn) \ - _EXPORT_DEV_PM_OPS(name, suspend_fn, resume_fn, NULL, NULL, NULL, "") + _EXPORT_DEV_PM_OPS(name, suspend_fn, resume_fn, NULL, NULL, NULL, "", "") #define EXPORT_GPL_SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn) \ - _EXPORT_DEV_PM_OPS(name, suspend_fn, resume_fn, NULL, NULL, NULL, "_gpl") + _EXPORT_DEV_PM_OPS(name, suspend_fn, resume_fn, NULL, NULL, NULL, "_gpl", "") +#define EXPORT_NS_SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn, ns) \ + _EXPORT_DEV_PM_OPS(name, suspend_fn, resume_fn, NULL, NULL, NULL, "", #ns) +#define EXPORT_NS_GPL_SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn, ns) \ + _EXPORT_DEV_PM_OPS(name, suspend_fn, resume_fn, NULL, NULL, NULL, "_gpl", #ns) /* Deprecated. Use DEFINE_SIMPLE_DEV_PM_OPS() instead. */ #define SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn) \ diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 67017c9390c8..ebc351698090 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -91,6 +91,14 @@ struct gpd_dev_ops { int (*stop)(struct device *dev); }; +struct genpd_governor_data { + s64 max_off_time_ns; + bool max_off_time_changed; + ktime_t next_wakeup; + bool cached_power_down_ok; + bool cached_power_down_state_idx; +}; + struct genpd_power_state { s64 power_off_latency_ns; s64 power_on_latency_ns; @@ -98,7 +106,7 @@ struct genpd_power_state { u64 usage; u64 rejected; struct fwnode_handle *fwnode; - ktime_t idle_time; + u64 idle_time; void *data; }; @@ -114,6 +122,7 @@ struct generic_pm_domain { struct list_head child_links; /* Links with PM domain as a child */ struct list_head dev_list; /* List of devices */ struct dev_power_governor *gov; + struct genpd_governor_data *gd; /* Data used by a genpd governor. */ struct work_struct power_off_work; struct fwnode_handle *provider; /* Identity of the domain provider */ bool has_provider; @@ -134,11 +143,6 @@ struct generic_pm_domain { int (*set_performance_state)(struct generic_pm_domain *genpd, unsigned int state); struct gpd_dev_ops dev_ops; - s64 max_off_time_ns; /* Maximum allowed "suspended" time. */ - ktime_t next_wakeup; /* Maintained by the domain governor */ - bool max_off_time_changed; - bool cached_power_down_ok; - bool cached_power_down_state_idx; int (*attach_dev)(struct generic_pm_domain *domain, struct device *dev); void (*detach_dev)(struct generic_pm_domain *domain, @@ -149,8 +153,8 @@ struct generic_pm_domain { unsigned int state_count); unsigned int state_count; /* number of states */ unsigned int state_idx; /* state that genpd will go to when off */ - ktime_t on_time; - ktime_t accounting_time; + u64 on_time; + u64 accounting_time; const struct genpd_lock_ops *lock_ops; union { struct mutex mlock; @@ -182,6 +186,7 @@ struct gpd_timing_data { s64 suspend_latency_ns; s64 resume_latency_ns; s64 effective_constraint_ns; + ktime_t next_wakeup; bool constraint_changed; bool cached_suspend_ok; }; @@ -193,14 +198,13 @@ struct pm_domain_data { struct generic_pm_domain_data { struct pm_domain_data base; - struct gpd_timing_data td; + struct gpd_timing_data *td; struct notifier_block nb; struct notifier_block *power_nb; int cpu; unsigned int performance_state; unsigned int default_pstate; unsigned int rpm_pstate; - ktime_t next_wakeup; void *data; }; diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index 2bff6a10095d..9e4d056967c6 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -41,10 +41,16 @@ #define EXPORT_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn) \ _EXPORT_DEV_PM_OPS(name, pm_runtime_force_suspend, pm_runtime_force_resume, \ - suspend_fn, resume_fn, idle_fn, "") + suspend_fn, resume_fn, idle_fn, "", "") #define EXPORT_GPL_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn) \ _EXPORT_DEV_PM_OPS(name, pm_runtime_force_suspend, pm_runtime_force_resume, \ - suspend_fn, resume_fn, idle_fn, "_gpl") + suspend_fn, resume_fn, idle_fn, "_gpl", "") +#define EXPORT_NS_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn, ns) \ + _EXPORT_DEV_PM_OPS(name, pm_runtime_force_suspend, pm_runtime_force_resume, \ + suspend_fn, resume_fn, idle_fn, "", #ns) +#define EXPORT_NS_GPL_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn, ns) \ + _EXPORT_DEV_PM_OPS(name, pm_runtime_force_suspend, pm_runtime_force_resume, \ + suspend_fn, resume_fn, idle_fn, "_gpl", #ns) #ifdef CONFIG_PM extern struct workqueue_struct *pm_wq; diff --git a/include/linux/polynomial.h b/include/linux/polynomial.h new file mode 100644 index 000000000000..9e074a0bb6fa --- /dev/null +++ b/include/linux/polynomial.h @@ -0,0 +1,35 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2020 BAIKAL ELECTRONICS, JSC + */ + +#ifndef _POLYNOMIAL_H +#define _POLYNOMIAL_H + +/* + * struct polynomial_term - one term descriptor of a polynomial + * @deg: degree of the term. + * @coef: multiplication factor of the term. + * @divider: distributed divider per each degree. + * @divider_leftover: divider leftover, which couldn't be redistributed. + */ +struct polynomial_term { + unsigned int deg; + long coef; + long divider; + long divider_leftover; +}; + +/* + * struct polynomial - a polynomial descriptor + * @total_divider: total data divider. + * @terms: polynomial terms, last term must have degree of 0 + */ +struct polynomial { + long total_divider; + struct polynomial_term terms[]; +}; + +long polynomial_calc(const struct polynomial *poly, long data); + +#endif diff --git a/include/linux/posix_acl_xattr.h b/include/linux/posix_acl_xattr.h index 060e8d203181..1766e1de6956 100644 --- a/include/linux/posix_acl_xattr.h +++ b/include/linux/posix_acl_xattr.h @@ -34,15 +34,19 @@ posix_acl_xattr_count(size_t size) #ifdef CONFIG_FS_POSIX_ACL void posix_acl_fix_xattr_from_user(struct user_namespace *mnt_userns, + struct inode *inode, void *value, size_t size); void posix_acl_fix_xattr_to_user(struct user_namespace *mnt_userns, + struct inode *inode, void *value, size_t size); #else static inline void posix_acl_fix_xattr_from_user(struct user_namespace *mnt_userns, + struct inode *inode, void *value, size_t size) { } static inline void posix_acl_fix_xattr_to_user(struct user_namespace *mnt_userns, + struct inode *inode, void *value, size_t size) { } diff --git a/include/linux/prandom.h b/include/linux/prandom.h index 056d31317e49..deace5fb4e62 100644 --- a/include/linux/prandom.h +++ b/include/linux/prandom.h @@ -10,62 +10,16 @@ #include <linux/types.h> #include <linux/percpu.h> +#include <linux/random.h> -u32 prandom_u32(void); -void prandom_bytes(void *buf, size_t nbytes); -void prandom_seed(u32 seed); -void prandom_reseed_late(void); - -DECLARE_PER_CPU(unsigned long, net_rand_noise); - -#define PRANDOM_ADD_NOISE(a, b, c, d) \ - prandom_u32_add_noise((unsigned long)(a), (unsigned long)(b), \ - (unsigned long)(c), (unsigned long)(d)) - -#if BITS_PER_LONG == 64 -/* - * The core SipHash round function. Each line can be executed in - * parallel given enough CPU resources. - */ -#define PRND_SIPROUND(v0, v1, v2, v3) ( \ - v0 += v1, v1 = rol64(v1, 13), v2 += v3, v3 = rol64(v3, 16), \ - v1 ^= v0, v0 = rol64(v0, 32), v3 ^= v2, \ - v0 += v3, v3 = rol64(v3, 21), v2 += v1, v1 = rol64(v1, 17), \ - v3 ^= v0, v1 ^= v2, v2 = rol64(v2, 32) \ -) - -#define PRND_K0 (0x736f6d6570736575 ^ 0x6c7967656e657261) -#define PRND_K1 (0x646f72616e646f6d ^ 0x7465646279746573) - -#elif BITS_PER_LONG == 32 -/* - * On 32-bit machines, we use HSipHash, a reduced-width version of SipHash. - * This is weaker, but 32-bit machines are not used for high-traffic - * applications, so there is less output for an attacker to analyze. - */ -#define PRND_SIPROUND(v0, v1, v2, v3) ( \ - v0 += v1, v1 = rol32(v1, 5), v2 += v3, v3 = rol32(v3, 8), \ - v1 ^= v0, v0 = rol32(v0, 16), v3 ^= v2, \ - v0 += v3, v3 = rol32(v3, 7), v2 += v1, v1 = rol32(v1, 13), \ - v3 ^= v0, v1 ^= v2, v2 = rol32(v2, 16) \ -) -#define PRND_K0 0x6c796765 -#define PRND_K1 0x74656462 - -#else -#error Unsupported BITS_PER_LONG -#endif +static inline u32 prandom_u32(void) +{ + return get_random_u32(); +} -static inline void prandom_u32_add_noise(unsigned long a, unsigned long b, - unsigned long c, unsigned long d) +static inline void prandom_bytes(void *buf, size_t nbytes) { - /* - * This is not used cryptographically; it's just - * a convenient 4-word hash function. (3 xor, 2 add, 2 rol) - */ - a ^= raw_cpu_read(net_rand_noise); - PRND_SIPROUND(a, b, c, d); - raw_cpu_write(net_rand_noise, d); + return get_random_bytes(buf, nbytes); } struct rnd_state { @@ -117,7 +71,6 @@ static inline void prandom_seed_state(struct rnd_state *state, u64 seed) state->s2 = __seed(i, 8U); state->s3 = __seed(i, 16U); state->s4 = __seed(i, 128U); - PRANDOM_ADD_NOISE(state, i, 0, 0); } /* Pseudo random number generator from numerical recipes. */ diff --git a/include/linux/printk.h b/include/linux/printk.h index 1522df223c0f..cd26aab0ab2a 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -170,6 +170,11 @@ extern void __printk_safe_exit(void); #define printk_deferred_enter __printk_safe_enter #define printk_deferred_exit __printk_safe_exit +extern void printk_prefer_direct_enter(void); +extern void printk_prefer_direct_exit(void); + +extern bool pr_flush(int timeout_ms, bool reset_on_progress); + /* * Please don't use printk_ratelimit(), because it shares ratelimiting state * with all other unrelated printk_ratelimit() callsites. Instead use @@ -220,6 +225,19 @@ static inline void printk_deferred_exit(void) { } +static inline void printk_prefer_direct_enter(void) +{ +} + +static inline void printk_prefer_direct_exit(void) +{ +} + +static inline bool pr_flush(int timeout_ms, bool reset_on_progress) +{ + return true; +} + static inline int printk_ratelimit(void) { return 0; @@ -277,45 +295,57 @@ static inline void printk_trigger_flush(void) #endif #ifdef CONFIG_SMP -extern int __printk_cpu_trylock(void); -extern void __printk_wait_on_cpu_lock(void); -extern void __printk_cpu_unlock(void); +extern int __printk_cpu_sync_try_get(void); +extern void __printk_cpu_sync_wait(void); +extern void __printk_cpu_sync_put(void); + +#else + +#define __printk_cpu_sync_try_get() true +#define __printk_cpu_sync_wait() +#define __printk_cpu_sync_put() +#endif /* CONFIG_SMP */ /** - * printk_cpu_lock_irqsave() - Acquire the printk cpu-reentrant spinning - * lock and disable interrupts. + * printk_cpu_sync_get_irqsave() - Disable interrupts and acquire the printk + * cpu-reentrant spinning lock. * @flags: Stack-allocated storage for saving local interrupt state, - * to be passed to printk_cpu_unlock_irqrestore(). + * to be passed to printk_cpu_sync_put_irqrestore(). * * If the lock is owned by another CPU, spin until it becomes available. * Interrupts are restored while spinning. + * + * CAUTION: This function must be used carefully. It does not behave like a + * typical lock. Here are important things to watch out for... + * + * * This function is reentrant on the same CPU. Therefore the calling + * code must not assume exclusive access to data if code accessing the + * data can run reentrant or within NMI context on the same CPU. + * + * * If there exists usage of this function from NMI context, it becomes + * unsafe to perform any type of locking or spinning to wait for other + * CPUs after calling this function from any context. This includes + * using spinlocks or any other busy-waiting synchronization methods. */ -#define printk_cpu_lock_irqsave(flags) \ - for (;;) { \ - local_irq_save(flags); \ - if (__printk_cpu_trylock()) \ - break; \ - local_irq_restore(flags); \ - __printk_wait_on_cpu_lock(); \ +#define printk_cpu_sync_get_irqsave(flags) \ + for (;;) { \ + local_irq_save(flags); \ + if (__printk_cpu_sync_try_get()) \ + break; \ + local_irq_restore(flags); \ + __printk_cpu_sync_wait(); \ } /** - * printk_cpu_unlock_irqrestore() - Release the printk cpu-reentrant spinning - * lock and restore interrupts. - * @flags: Caller's saved interrupt state, from printk_cpu_lock_irqsave(). + * printk_cpu_sync_put_irqrestore() - Release the printk cpu-reentrant spinning + * lock and restore interrupts. + * @flags: Caller's saved interrupt state, from printk_cpu_sync_get_irqsave(). */ -#define printk_cpu_unlock_irqrestore(flags) \ +#define printk_cpu_sync_put_irqrestore(flags) \ do { \ - __printk_cpu_unlock(); \ + __printk_cpu_sync_put(); \ local_irq_restore(flags); \ - } while (0) \ - -#else - -#define printk_cpu_lock_irqsave(flags) ((void)flags) -#define printk_cpu_unlock_irqrestore(flags) ((void)flags) - -#endif /* CONFIG_SMP */ + } while (0) extern int kptr_restrict; diff --git a/include/linux/property.h b/include/linux/property.h index 4cd4b326941f..fc24d45632eb 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -83,15 +83,19 @@ struct fwnode_handle *fwnode_find_reference(const struct fwnode_handle *fwnode, const char *fwnode_get_name(const struct fwnode_handle *fwnode); const char *fwnode_get_name_prefix(const struct fwnode_handle *fwnode); + struct fwnode_handle *fwnode_get_parent(const struct fwnode_handle *fwnode); -struct fwnode_handle *fwnode_get_next_parent( - struct fwnode_handle *fwnode); +struct fwnode_handle *fwnode_get_next_parent(struct fwnode_handle *fwnode); + +#define fwnode_for_each_parent_node(fwnode, parent) \ + for (parent = fwnode_get_parent(fwnode); parent; \ + parent = fwnode_get_next_parent(parent)) + struct device *fwnode_get_next_parent_dev(struct fwnode_handle *fwnode); unsigned int fwnode_count_parents(const struct fwnode_handle *fwn); struct fwnode_handle *fwnode_get_nth_parent(struct fwnode_handle *fwn, unsigned int depth); -bool fwnode_is_ancestor_of(struct fwnode_handle *test_ancestor, - struct fwnode_handle *test_child); +bool fwnode_is_ancestor_of(struct fwnode_handle *ancestor, struct fwnode_handle *child); struct fwnode_handle *fwnode_get_next_child_node( const struct fwnode_handle *fwnode, struct fwnode_handle *child); struct fwnode_handle *fwnode_get_next_available_child_node( diff --git a/include/linux/random.h b/include/linux/random.h index f673fbb838b3..fae0c84027fd 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -12,45 +12,32 @@ struct notifier_block; -extern void add_device_randomness(const void *, size_t); -extern void add_bootloader_randomness(const void *, size_t); +void add_device_randomness(const void *buf, size_t len); +void add_bootloader_randomness(const void *buf, size_t len); +void add_input_randomness(unsigned int type, unsigned int code, + unsigned int value) __latent_entropy; +void add_interrupt_randomness(int irq) __latent_entropy; +void add_hwgenerator_randomness(const void *buf, size_t len, size_t entropy); #if defined(LATENT_ENTROPY_PLUGIN) && !defined(__CHECKER__) static inline void add_latent_entropy(void) { - add_device_randomness((const void *)&latent_entropy, - sizeof(latent_entropy)); + add_device_randomness((const void *)&latent_entropy, sizeof(latent_entropy)); } #else -static inline void add_latent_entropy(void) {} +static inline void add_latent_entropy(void) { } #endif -extern void add_input_randomness(unsigned int type, unsigned int code, - unsigned int value) __latent_entropy; -extern void add_interrupt_randomness(int irq) __latent_entropy; -extern void add_hwgenerator_randomness(const void *buffer, size_t count, - size_t entropy); #if IS_ENABLED(CONFIG_VMGENID) -extern void add_vmfork_randomness(const void *unique_vm_id, size_t size); -extern int register_random_vmfork_notifier(struct notifier_block *nb); -extern int unregister_random_vmfork_notifier(struct notifier_block *nb); +void add_vmfork_randomness(const void *unique_vm_id, size_t len); +int register_random_vmfork_notifier(struct notifier_block *nb); +int unregister_random_vmfork_notifier(struct notifier_block *nb); #else static inline int register_random_vmfork_notifier(struct notifier_block *nb) { return 0; } static inline int unregister_random_vmfork_notifier(struct notifier_block *nb) { return 0; } #endif -extern void get_random_bytes(void *buf, size_t nbytes); -extern int wait_for_random_bytes(void); -extern int __init rand_initialize(void); -extern bool rng_is_initialized(void); -extern int register_random_ready_notifier(struct notifier_block *nb); -extern int unregister_random_ready_notifier(struct notifier_block *nb); -extern size_t __must_check get_random_bytes_arch(void *buf, size_t nbytes); - -#ifndef MODULE -extern const struct file_operations random_fops, urandom_fops; -#endif - +void get_random_bytes(void *buf, size_t len); u32 get_random_u32(void); u64 get_random_u64(void); static inline unsigned int get_random_int(void) @@ -82,11 +69,14 @@ static inline unsigned long get_random_long(void) static inline unsigned long get_random_canary(void) { - unsigned long val = get_random_long(); - - return val & CANARY_MASK; + return get_random_long() & CANARY_MASK; } +int __init random_init(const char *command_line); +bool rng_is_initialized(void); +bool rng_has_arch_random(void); +int wait_for_random_bytes(void); + /* Calls wait_for_random_bytes() and then calls get_random_bytes(buf, nbytes). * Returns the result of the call to wait_for_random_bytes. */ static inline int get_random_bytes_wait(void *buf, size_t nbytes) @@ -96,22 +86,20 @@ static inline int get_random_bytes_wait(void *buf, size_t nbytes) return ret; } -#define declare_get_random_var_wait(var) \ - static inline int get_random_ ## var ## _wait(var *out) { \ +#define declare_get_random_var_wait(name, ret_type) \ + static inline int get_random_ ## name ## _wait(ret_type *out) { \ int ret = wait_for_random_bytes(); \ if (unlikely(ret)) \ return ret; \ - *out = get_random_ ## var(); \ + *out = get_random_ ## name(); \ return 0; \ } -declare_get_random_var_wait(u32) -declare_get_random_var_wait(u64) -declare_get_random_var_wait(int) -declare_get_random_var_wait(long) +declare_get_random_var_wait(u32, u32) +declare_get_random_var_wait(u64, u32) +declare_get_random_var_wait(int, unsigned int) +declare_get_random_var_wait(long, unsigned long) #undef declare_get_random_var -unsigned long randomize_page(unsigned long start, unsigned long range); - /* * This is designed to be standalone for just prandom * users, but for now we include it from <linux/random.h> @@ -122,22 +110,10 @@ unsigned long randomize_page(unsigned long start, unsigned long range); #ifdef CONFIG_ARCH_RANDOM # include <asm/archrandom.h> #else -static inline bool __must_check arch_get_random_long(unsigned long *v) -{ - return false; -} -static inline bool __must_check arch_get_random_int(unsigned int *v) -{ - return false; -} -static inline bool __must_check arch_get_random_seed_long(unsigned long *v) -{ - return false; -} -static inline bool __must_check arch_get_random_seed_int(unsigned int *v) -{ - return false; -} +static inline bool __must_check arch_get_random_long(unsigned long *v) { return false; } +static inline bool __must_check arch_get_random_int(unsigned int *v) { return false; } +static inline bool __must_check arch_get_random_seed_long(unsigned long *v) { return false; } +static inline bool __must_check arch_get_random_seed_int(unsigned int *v) { return false; } #endif /* @@ -161,8 +137,12 @@ static inline bool __init arch_get_random_long_early(unsigned long *v) #endif #ifdef CONFIG_SMP -extern int random_prepare_cpu(unsigned int cpu); -extern int random_online_cpu(unsigned int cpu); +int random_prepare_cpu(unsigned int cpu); +int random_online_cpu(unsigned int cpu); +#endif + +#ifndef MODULE +extern const struct file_operations random_fops, urandom_fops; #endif #endif /* _LINUX_RANDOM_H */ diff --git a/include/linux/randomize_kstack.h b/include/linux/randomize_kstack.h index 1468caf001c0..5d868505a94e 100644 --- a/include/linux/randomize_kstack.h +++ b/include/linux/randomize_kstack.h @@ -40,10 +40,14 @@ DECLARE_PER_CPU(u32, kstack_offset); */ #define KSTACK_OFFSET_MAX(x) ((x) & 0x3FF) -/* - * These macros must be used during syscall entry when interrupts and +/** + * add_random_kstack_offset - Increase stack utilization by previously + * chosen random offset + * + * This should be used in the syscall entry path when interrupts and * preempt are disabled, and after user registers have been stored to - * the stack. + * the stack. For testing the resulting entropy, please see: + * tools/testing/selftests/lkdtm/stack-entropy.sh */ #define add_random_kstack_offset() do { \ if (static_branch_maybe(CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT, \ @@ -55,6 +59,23 @@ DECLARE_PER_CPU(u32, kstack_offset); } \ } while (0) +/** + * choose_random_kstack_offset - Choose the random offset for the next + * add_random_kstack_offset() + * + * This should only be used during syscall exit when interrupts and + * preempt are disabled. This position in the syscall flow is done to + * frustrate attacks from userspace attempting to learn the next offset: + * - Maximize the timing uncertainty visible from userspace: if the + * offset is chosen at syscall entry, userspace has much more control + * over the timing between choosing offsets. "How long will we be in + * kernel mode?" tends to be more difficult to predict than "how long + * will we be in user mode?" + * - Reduce the lifetime of the new offset sitting in memory during + * kernel mode execution. Exposure of "thread-local" memory content + * (e.g. current, percpu, etc) tends to be easier than arbitrary + * location memory exposure. + */ #define choose_random_kstack_offset(rand) do { \ if (static_branch_maybe(CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT, \ &randomize_kstack_offset)) { \ diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index e7c39c200e2b..1a32036c918c 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -196,6 +196,7 @@ void synchronize_rcu_tasks_rude(void); void exit_tasks_rcu_start(void); void exit_tasks_rcu_finish(void); #else /* #ifdef CONFIG_TASKS_RCU_GENERIC */ +#define rcu_tasks_classic_qs(t, preempt) do { } while (0) #define rcu_tasks_qs(t, preempt) do { } while (0) #define rcu_note_voluntary_context_switch(t) do { } while (0) #define call_rcu_tasks call_rcu diff --git a/include/linux/regmap.h b/include/linux/regmap.h index de81a94d7b30..8952fa3d0d59 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -299,6 +299,12 @@ typedef void (*regmap_unlock)(void *); * if the function require special handling with lock and reg * handling and the operation cannot be represented as a simple * update_bits operation on a bus such as SPI, I2C, etc. + * @read: Optional callback that if filled will be used to perform all the + * bulk reads from the registers. Data is returned in the buffer used + * to transmit data. + * @write: Same as above for writing. + * @max_raw_read: Max raw read size that can be used on the device. + * @max_raw_write: Max raw write size that can be used on the device. * @fast_io: Register IO is fast. Use a spinlock instead of a mutex * to perform locking. This field is ignored if custom lock/unlock * functions are used (see fields lock/unlock of struct regmap_config). @@ -385,6 +391,12 @@ struct regmap_config { int (*reg_write)(void *context, unsigned int reg, unsigned int val); int (*reg_update_bits)(void *context, unsigned int reg, unsigned int mask, unsigned int val); + /* Bulk read/write */ + int (*read)(void *context, const void *reg_buf, size_t reg_size, + void *val_buf, size_t val_size); + int (*write)(void *context, const void *data, size_t count); + size_t max_raw_read; + size_t max_raw_write; bool fast_io; diff --git a/include/linux/regulator/mt6358-regulator.h b/include/linux/regulator/mt6358-regulator.h index 1cc304946d09..bdcf83cd719e 100644 --- a/include/linux/regulator/mt6358-regulator.h +++ b/include/linux/regulator/mt6358-regulator.h @@ -48,9 +48,54 @@ enum { MT6358_ID_VLDO28, MT6358_ID_VAUD28, MT6358_ID_VSIM2, + MT6358_ID_VCORE_SSHUB, + MT6358_ID_VSRAM_OTHERS_SSHUB, MT6358_ID_RG_MAX, }; +enum { + MT6366_ID_VDRAM1 = 0, + MT6366_ID_VCORE, + MT6366_ID_VPA, + MT6366_ID_VPROC11, + MT6366_ID_VPROC12, + MT6366_ID_VGPU, + MT6366_ID_VS2, + MT6366_ID_VMODEM, + MT6366_ID_VS1, + MT6366_ID_VDRAM2, + MT6366_ID_VSIM1, + MT6366_ID_VIBR, + MT6366_ID_VRF12, + MT6366_ID_VIO18, + MT6366_ID_VUSB, + MT6366_ID_VCN18, + MT6366_ID_VFE28, + MT6366_ID_VSRAM_PROC11, + MT6366_ID_VCN28, + MT6366_ID_VSRAM_OTHERS, + MT6366_ID_VSRAM_GPU, + MT6366_ID_VXO22, + MT6366_ID_VEFUSE, + MT6366_ID_VAUX18, + MT6366_ID_VMCH, + MT6366_ID_VBIF28, + MT6366_ID_VSRAM_PROC12, + MT6366_ID_VEMC, + MT6366_ID_VIO28, + MT6366_ID_VA12, + MT6366_ID_VRF18, + MT6366_ID_VCN33_BT, + MT6366_ID_VCN33_WIFI, + MT6366_ID_VMC, + MT6366_ID_VAUD28, + MT6366_ID_VSIM2, + MT6366_ID_VCORE_SSHUB, + MT6366_ID_VSRAM_OTHERS_SSHUB, + MT6366_ID_RG_MAX, +}; + #define MT6358_MAX_REGULATOR MT6358_ID_RG_MAX +#define MT6366_MAX_REGULATOR MT6366_ID_RG_MAX #endif /* __LINUX_REGULATOR_MT6358_H */ diff --git a/include/linux/regulator/pca9450.h b/include/linux/regulator/pca9450.h index 71902f41c919..3c01c2bf84f5 100644 --- a/include/linux/regulator/pca9450.h +++ b/include/linux/regulator/pca9450.h @@ -226,4 +226,11 @@ enum { #define WDOG_B_CFG_COLD_LDO12 0x80 #define WDOG_B_CFG_COLD 0xC0 +/* PCA9450_REG_CONFIG2 bits */ +#define I2C_LT_MASK 0x03 +#define I2C_LT_FORCE_DISABLE 0x00 +#define I2C_LT_ON_STANDBY_RUN 0x01 +#define I2C_LT_ON_RUN 0x02 +#define I2C_LT_FORCE_ENABLE 0x03 + #endif /* __LINUX_REG_PCA9450_H__ */ diff --git a/include/linux/remoteproc/mtk_scp.h b/include/linux/remoteproc/mtk_scp.h index b47416f7aeb8..7c2b7cc9fe6c 100644 --- a/include/linux/remoteproc/mtk_scp.h +++ b/include/linux/remoteproc/mtk_scp.h @@ -41,6 +41,8 @@ enum scp_ipi_id { SCP_IPI_ISP_FRAME, SCP_IPI_FD_CMD, SCP_IPI_CROS_HOST_CMD, + SCP_IPI_VDEC_LAT, + SCP_IPI_VDEC_CORE, SCP_IPI_NS_SERVICE = 0xFF, SCP_IPI_MAX = 0x100, }; diff --git a/include/linux/sched.h b/include/linux/sched.h index d5e3c00b74e1..b89c8571187b 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -941,6 +941,9 @@ struct task_struct { #ifdef CONFIG_IOMMU_SVA unsigned pasid_activated:1; #endif +#ifdef CONFIG_CPU_SUP_INTEL + unsigned reported_split_lock:1; +#endif unsigned long atomic_flags; /* Flags requiring atomic access. */ @@ -1443,6 +1446,7 @@ struct task_struct { int pagefault_disabled; #ifdef CONFIG_MMU struct task_struct *oom_reaper_list; + struct timer_list oom_reaper_timer; #endif #ifdef CONFIG_VMAP_STACK struct vm_struct *stack_vm_area; @@ -2117,6 +2121,47 @@ static inline void cond_resched_rcu(void) #endif } +#ifdef CONFIG_PREEMPT_DYNAMIC + +extern bool preempt_model_none(void); +extern bool preempt_model_voluntary(void); +extern bool preempt_model_full(void); + +#else + +static inline bool preempt_model_none(void) +{ + return IS_ENABLED(CONFIG_PREEMPT_NONE); +} +static inline bool preempt_model_voluntary(void) +{ + return IS_ENABLED(CONFIG_PREEMPT_VOLUNTARY); +} +static inline bool preempt_model_full(void) +{ + return IS_ENABLED(CONFIG_PREEMPT); +} + +#endif + +static inline bool preempt_model_rt(void) +{ + return IS_ENABLED(CONFIG_PREEMPT_RT); +} + +/* + * Does the preemption model allow non-cooperative preemption? + * + * For !CONFIG_PREEMPT_DYNAMIC kernels this is an exact match with + * CONFIG_PREEMPTION; for CONFIG_PREEMPT_DYNAMIC this doesn't work as the + * kernel is *built* with CONFIG_PREEMPTION=y but may run with e.g. the + * PREEMPT_NONE model. + */ +static inline bool preempt_model_preemptible(void) +{ + return preempt_model_full() || preempt_model_rt(); +} + /* * Does a critical section need to be broken due to another * task waiting?: (technically does not depend on CONFIG_PREEMPTION, @@ -2337,20 +2382,6 @@ static inline void rseq_syscall(struct pt_regs *regs) #endif -const struct sched_avg *sched_trace_cfs_rq_avg(struct cfs_rq *cfs_rq); -char *sched_trace_cfs_rq_path(struct cfs_rq *cfs_rq, char *str, int len); -int sched_trace_cfs_rq_cpu(struct cfs_rq *cfs_rq); - -const struct sched_avg *sched_trace_rq_avg_rt(struct rq *rq); -const struct sched_avg *sched_trace_rq_avg_dl(struct rq *rq); -const struct sched_avg *sched_trace_rq_avg_irq(struct rq *rq); - -int sched_trace_rq_cpu(struct rq *rq); -int sched_trace_rq_cpu_capacity(struct rq *rq); -int sched_trace_rq_nr_running(struct rq *rq); - -const struct cpumask *sched_trace_rd_span(struct root_domain *rd); - #ifdef CONFIG_SCHED_CORE extern void sched_core_free(struct task_struct *tsk); extern void sched_core_fork(struct task_struct *p); @@ -2361,4 +2392,6 @@ static inline void sched_core_free(struct task_struct *tsk) { } static inline void sched_core_fork(struct task_struct *p) { } #endif +extern void sched_set_stop_task(int cpu, struct task_struct *stop); + #endif diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index a80356e9dc69..1ad1f4bfa025 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -136,6 +136,14 @@ static inline void mm_update_next_owner(struct mm_struct *mm) #endif /* CONFIG_MEMCG */ #ifdef CONFIG_MMU +#ifndef arch_get_mmap_end +#define arch_get_mmap_end(addr) (TASK_SIZE) +#endif + +#ifndef arch_get_mmap_base +#define arch_get_mmap_base(addr, base) (base) +#endif + extern void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack); extern unsigned long diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 3c8b34876744..20ed5ba2bde4 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -320,7 +320,7 @@ int send_sig_mceerr(int code, void __user *, short, struct task_struct *); int force_sig_bnderr(void __user *addr, void __user *lower, void __user *upper); int force_sig_pkuerr(void __user *addr, u32 pkey); -int force_sig_perf(void __user *addr, u32 type, u64 sig_data); +int send_sig_perf(void __user *addr, u32 type, u64 sig_data); int force_sig_ptrace_errno_trap(int errno, void __user *addr); int force_sig_fault_trapno(int sig, int code, void __user *addr, int trapno); @@ -356,13 +356,22 @@ static inline void clear_notify_signal(void) } /* + * Returns 'true' if kick_process() is needed to force a transition from + * user -> kernel to guarantee expedient run of TWA_SIGNAL based task_work. + */ +static inline bool __set_notify_signal(struct task_struct *task) +{ + return !test_and_set_tsk_thread_flag(task, TIF_NOTIFY_SIGNAL) && + !wake_up_state(task, TASK_INTERRUPTIBLE); +} + +/* * Called to break out of interruptible wait loops, and enter the * exit_to_user_mode_loop(). */ static inline void set_notify_signal(struct task_struct *task) { - if (!test_and_set_tsk_thread_flag(task, TIF_NOTIFY_SIGNAL) && - !wake_up_state(task, TASK_INTERRUPTIBLE)) + if (__set_notify_signal(task)) kick_process(task); } diff --git a/include/linux/sched/task_stack.h b/include/linux/sched/task_stack.h index 892562ebbd3a..5e799a47431e 100644 --- a/include/linux/sched/task_stack.h +++ b/include/linux/sched/task_stack.h @@ -16,7 +16,7 @@ * try_get_task_stack() instead. task_stack_page will return a pointer * that could get freed out from under you. */ -static inline void *task_stack_page(const struct task_struct *task) +static __always_inline void *task_stack_page(const struct task_struct *task) { return task->stack; } diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h index 0c564e5d40ff..d31d76be4982 100644 --- a/include/linux/seccomp.h +++ b/include/linux/seccomp.h @@ -8,7 +8,8 @@ SECCOMP_FILTER_FLAG_LOG | \ SECCOMP_FILTER_FLAG_SPEC_ALLOW | \ SECCOMP_FILTER_FLAG_NEW_LISTENER | \ - SECCOMP_FILTER_FLAG_TSYNC_ESRCH) + SECCOMP_FILTER_FLAG_TSYNC_ESRCH | \ + SECCOMP_FILTER_FLAG_WAIT_KILLABLE_RECV) /* sizeof() the first published struct seccomp_notif_addfd */ #define SECCOMP_NOTIFY_ADDFD_SIZE_VER0 24 diff --git a/include/linux/security.h b/include/linux/security.h index 25b3ef71f495..7fc4e9f49f54 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -121,10 +121,12 @@ enum lockdown_reason { LOCKDOWN_DEBUGFS, LOCKDOWN_XMON_WR, LOCKDOWN_BPF_WRITE_USER, + LOCKDOWN_DBG_WRITE_KERNEL, LOCKDOWN_INTEGRITY_MAX, LOCKDOWN_KCORE, LOCKDOWN_KPROBES, LOCKDOWN_BPF_READ_KERNEL, + LOCKDOWN_DBG_READ_KERNEL, LOCKDOWN_PERF, LOCKDOWN_TRACEFS, LOCKDOWN_XMON_RW, diff --git a/include/linux/siphash.h b/include/linux/siphash.h index cce8a9acc76c..3af1428da559 100644 --- a/include/linux/siphash.h +++ b/include/linux/siphash.h @@ -138,4 +138,32 @@ static inline u32 hsiphash(const void *data, size_t len, return ___hsiphash_aligned(data, len, key); } +/* + * These macros expose the raw SipHash and HalfSipHash permutations. + * Do not use them directly! If you think you have a use for them, + * be sure to CC the maintainer of this file explaining why. + */ + +#define SIPHASH_PERMUTATION(a, b, c, d) ( \ + (a) += (b), (b) = rol64((b), 13), (b) ^= (a), (a) = rol64((a), 32), \ + (c) += (d), (d) = rol64((d), 16), (d) ^= (c), \ + (a) += (d), (d) = rol64((d), 21), (d) ^= (a), \ + (c) += (b), (b) = rol64((b), 17), (b) ^= (c), (c) = rol64((c), 32)) + +#define SIPHASH_CONST_0 0x736f6d6570736575ULL +#define SIPHASH_CONST_1 0x646f72616e646f6dULL +#define SIPHASH_CONST_2 0x6c7967656e657261ULL +#define SIPHASH_CONST_3 0x7465646279746573ULL + +#define HSIPHASH_PERMUTATION(a, b, c, d) ( \ + (a) += (b), (b) = rol32((b), 5), (b) ^= (a), (a) = rol32((a), 16), \ + (c) += (d), (d) = rol32((d), 8), (d) ^= (c), \ + (a) += (d), (d) = rol32((d), 7), (d) ^= (a), \ + (c) += (b), (b) = rol32((b), 13), (b) ^= (c), (c) = rol32((c), 16)) + +#define HSIPHASH_CONST_0 0U +#define HSIPHASH_CONST_1 0U +#define HSIPHASH_CONST_2 0x6c796765U +#define HSIPHASH_CONST_3 0x74656462U + #endif /* _LINUX_SIPHASH_H */ diff --git a/include/linux/slab.h b/include/linux/slab.h index 373b3ef99f4e..58bb9392775d 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -112,6 +112,13 @@ #define SLAB_KASAN 0 #endif +/* + * Ignore user specified debugging flags. + * Intended for caches created for self-tests so they have only flags + * specified in the code and other flags are ignored. + */ +#define SLAB_NO_USER_FLAGS ((slab_flags_t __force)0x10000000U) + /* The following flags affect the page allocator grouping pages by mobility */ /* Objects are reclaimable */ #define SLAB_RECLAIM_ACCOUNT ((slab_flags_t __force)0x00020000U) @@ -190,7 +197,7 @@ void kmem_dump_obj(void *object); /* * Some archs want to perform DMA into kmalloc caches and need a guaranteed * alignment larger than the alignment of a 64-bit integer. - * Setting ARCH_KMALLOC_MINALIGN in arch headers allows that. + * Setting ARCH_DMA_MINALIGN in arch headers allows that. */ #if defined(ARCH_DMA_MINALIGN) && ARCH_DMA_MINALIGN > 8 #define ARCH_KMALLOC_MINALIGN ARCH_DMA_MINALIGN @@ -210,9 +217,9 @@ void kmem_dump_obj(void *object); #endif /* - * kmalloc and friends return ARCH_KMALLOC_MINALIGN aligned - * pointers. kmem_cache_alloc and friends return ARCH_SLAB_MINALIGN - * aligned pointers. + * kmem_cache_alloc and friends return pointers aligned to ARCH_SLAB_MINALIGN. + * kmalloc and friends return pointers aligned to both ARCH_KMALLOC_MINALIGN + * and ARCH_SLAB_MINALIGN, but here we only assume the former alignment. */ #define __assume_kmalloc_alignment __assume_aligned(ARCH_KMALLOC_MINALIGN) #define __assume_slab_alignment __assume_aligned(ARCH_SLAB_MINALIGN) diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index 33c5c0e3bd8d..f9c68a9dac04 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -105,7 +105,6 @@ struct kmem_cache { struct kmem_cache_order_objects oo; /* Allocation and freeing of slabs */ - struct kmem_cache_order_objects max; struct kmem_cache_order_objects min; gfp_t allocflags; /* gfp flags to use on each alloc */ int refcount; /* Refcount for slab cache destroy */ diff --git a/include/linux/socket.h b/include/linux/socket.h index 6f85f5d957ef..17311ad9f9af 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -50,6 +50,9 @@ struct linger { struct msghdr { void *msg_name; /* ptr to socket address structure */ int msg_namelen; /* size of socket address structure */ + + int msg_inq; /* output, data left in socket */ + struct iov_iter msg_iter; /* data */ /* @@ -62,8 +65,9 @@ struct msghdr { void __user *msg_control_user; }; bool msg_control_is_user : 1; - __kernel_size_t msg_controllen; /* ancillary data buffer length */ + bool msg_get_inq : 1;/* return INQ after receive */ unsigned int msg_flags; /* flags on received message */ + __kernel_size_t msg_controllen; /* ancillary data buffer length */ struct kiocb *msg_iocb; /* ptr to iocb for async requests */ }; @@ -434,6 +438,7 @@ extern struct file *do_accept(struct file *file, unsigned file_flags, extern int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr, int __user *upeer_addrlen, int flags); extern int __sys_socket(int family, int type, int protocol); +extern struct file *__sys_socket_file(int family, int type, int protocol); extern int __sys_bind(int fd, struct sockaddr __user *umyaddr, int addrlen); extern int __sys_connect_file(struct file *file, struct sockaddr_storage *addr, int addrlen, int file_flags); diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 5f8c063ddff4..df70eb1a671e 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -347,6 +347,7 @@ extern struct spi_device *spi_new_ancillary_device(struct spi_device *spi, u8 ch * @max_message_size: function that returns the max message size for * a &spi_device; may be %NULL, so the default %SIZE_MAX will be used. * @io_mutex: mutex for physical bus access + * @add_lock: mutex to avoid adding devices to the same chipselect * @bus_lock_spinlock: spinlock for SPI bus locking * @bus_lock_mutex: mutex for exclusion of multiple callers * @bus_lock_flag: indicates that the SPI bus is locked for exclusive use @@ -361,6 +362,7 @@ extern struct spi_device *spi_new_ancillary_device(struct spi_device *spi, u8 ch * @transfer: adds a message to the controller's transfer queue. * @cleanup: frees controller-specific state * @can_dma: determine whether this controller supports DMA + * @dma_map_dev: device which can be used for DMA mapping * @queued: whether this controller is providing an internal message queue * @kworker: pointer to thread struct for message pump * @pump_messages: work struct for scheduling work to the message pump diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index cb1f4351e8ba..e3014319d1ad 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -47,11 +47,9 @@ struct srcu_data { */ struct srcu_node { spinlock_t __private lock; - unsigned long srcu_have_cbs[4]; /* GP seq for children */ - /* having CBs, but only */ - /* is > ->srcu_gq_seq. */ - unsigned long srcu_data_have_cbs[4]; /* Which srcu_data structs */ - /* have CBs for given GP? */ + unsigned long srcu_have_cbs[4]; /* GP seq for children having CBs, but only */ + /* if greater than ->srcu_gq_seq. */ + unsigned long srcu_data_have_cbs[4]; /* Which srcu_data structs have CBs for given GP? */ unsigned long srcu_gp_seq_needed_exp; /* Furthest future exp GP. */ struct srcu_node *srcu_parent; /* Next up in tree. */ int grplo; /* Least CPU for node. */ @@ -62,18 +60,24 @@ struct srcu_node { * Per-SRCU-domain structure, similar in function to rcu_state. */ struct srcu_struct { - struct srcu_node node[NUM_RCU_NODES]; /* Combining tree. */ + struct srcu_node *node; /* Combining tree. */ struct srcu_node *level[RCU_NUM_LVLS + 1]; /* First node at each level. */ + int srcu_size_state; /* Small-to-big transition state. */ struct mutex srcu_cb_mutex; /* Serialize CB preparation. */ - spinlock_t __private lock; /* Protect counters */ + spinlock_t __private lock; /* Protect counters and size state. */ struct mutex srcu_gp_mutex; /* Serialize GP work. */ unsigned int srcu_idx; /* Current rdr array element. */ unsigned long srcu_gp_seq; /* Grace-period seq #. */ unsigned long srcu_gp_seq_needed; /* Latest gp_seq needed. */ unsigned long srcu_gp_seq_needed_exp; /* Furthest future exp GP. */ + unsigned long srcu_gp_start; /* Last GP start timestamp (jiffies) */ unsigned long srcu_last_gp_end; /* Last GP end timestamp (ns) */ + unsigned long srcu_size_jiffies; /* Current contention-measurement interval. */ + unsigned long srcu_n_lock_retries; /* Contention events in current interval. */ + unsigned long srcu_n_exp_nodelay; /* # expedited no-delays in current GP phase. */ struct srcu_data __percpu *sda; /* Per-CPU srcu_data array. */ + bool sda_is_static; /* May ->sda be passed to free_percpu()? */ unsigned long srcu_barrier_seq; /* srcu_barrier seq #. */ struct mutex srcu_barrier_mutex; /* Serialize barrier ops. */ struct completion srcu_barrier_completion; @@ -81,10 +85,23 @@ struct srcu_struct { atomic_t srcu_barrier_cpu_cnt; /* # CPUs not yet posting a */ /* callback for the barrier */ /* operation. */ + unsigned long reschedule_jiffies; + unsigned long reschedule_count; struct delayed_work work; struct lockdep_map dep_map; }; +/* Values for size state variable (->srcu_size_state). */ +#define SRCU_SIZE_SMALL 0 +#define SRCU_SIZE_ALLOC 1 +#define SRCU_SIZE_WAIT_BARRIER 2 +#define SRCU_SIZE_WAIT_CALL 3 +#define SRCU_SIZE_WAIT_CBS1 4 +#define SRCU_SIZE_WAIT_CBS2 5 +#define SRCU_SIZE_WAIT_CBS3 6 +#define SRCU_SIZE_WAIT_CBS4 7 +#define SRCU_SIZE_BIG 8 + /* Values for state variable (bottom bits of ->srcu_gp_seq). */ #define SRCU_STATE_IDLE 0 #define SRCU_STATE_SCAN1 1 @@ -121,6 +138,7 @@ struct srcu_struct { #ifdef MODULE # define __DEFINE_SRCU(name, is_static) \ is_static struct srcu_struct name; \ + extern struct srcu_struct * const __srcu_struct_##name; \ struct srcu_struct * const __srcu_struct_##name \ __section("___srcu_struct_ptrs") = &name #else diff --git a/include/linux/stackdepot.h b/include/linux/stackdepot.h index 17f992fe6355..bc2797955de9 100644 --- a/include/linux/stackdepot.h +++ b/include/linux/stackdepot.h @@ -20,18 +20,36 @@ depot_stack_handle_t __stack_depot_save(unsigned long *entries, gfp_t gfp_flags, bool can_alloc); /* - * Every user of stack depot has to call this during its own init when it's - * decided that it will be calling stack_depot_save() later. + * Every user of stack depot has to call stack_depot_init() during its own init + * when it's decided that it will be calling stack_depot_save() later. This is + * recommended for e.g. modules initialized later in the boot process, when + * slab_is_available() is true. * * The alternative is to select STACKDEPOT_ALWAYS_INIT to have stack depot * enabled as part of mm_init(), for subsystems where it's known at compile time * that stack depot will be used. + * + * Another alternative is to call stack_depot_want_early_init(), when the + * decision to use stack depot is taken e.g. when evaluating kernel boot + * parameters, which precedes the enablement point in mm_init(). + * + * stack_depot_init() and stack_depot_want_early_init() can be called regardless + * of CONFIG_STACKDEPOT and are no-op when disabled. The actual save/fetch/print + * functions should only be called from code that makes sure CONFIG_STACKDEPOT + * is enabled. */ +#ifdef CONFIG_STACKDEPOT int stack_depot_init(void); -#ifdef CONFIG_STACKDEPOT_ALWAYS_INIT -static inline int stack_depot_early_init(void) { return stack_depot_init(); } +void __init stack_depot_want_early_init(void); + +/* This is supposed to be called only from mm_init() */ +int __init stack_depot_early_init(void); #else +static inline int stack_depot_init(void) { return 0; } + +static inline void stack_depot_want_early_init(void) { } + static inline int stack_depot_early_init(void) { return 0; } #endif diff --git a/include/linux/stackleak.h b/include/linux/stackleak.h index ccaab2043fcd..c36e7a3b45e7 100644 --- a/include/linux/stackleak.h +++ b/include/linux/stackleak.h @@ -15,9 +15,62 @@ #ifdef CONFIG_GCC_PLUGIN_STACKLEAK #include <asm/stacktrace.h> +/* + * The lowest address on tsk's stack which we can plausibly erase. + */ +static __always_inline unsigned long +stackleak_task_low_bound(const struct task_struct *tsk) +{ + /* + * The lowest unsigned long on the task stack contains STACK_END_MAGIC, + * which we must not corrupt. + */ + return (unsigned long)end_of_stack(tsk) + sizeof(unsigned long); +} + +/* + * The address immediately after the highest address on tsk's stack which we + * can plausibly erase. + */ +static __always_inline unsigned long +stackleak_task_high_bound(const struct task_struct *tsk) +{ + /* + * The task's pt_regs lives at the top of the task stack and will be + * overwritten by exception entry, so there's no need to erase them. + */ + return (unsigned long)task_pt_regs(tsk); +} + +/* + * Find the address immediately above the poisoned region of the stack, where + * that region falls between 'low' (inclusive) and 'high' (exclusive). + */ +static __always_inline unsigned long +stackleak_find_top_of_poison(const unsigned long low, const unsigned long high) +{ + const unsigned int depth = STACKLEAK_SEARCH_DEPTH / sizeof(unsigned long); + unsigned int poison_count = 0; + unsigned long poison_high = high; + unsigned long sp = high; + + while (sp > low && poison_count < depth) { + sp -= sizeof(unsigned long); + + if (*(unsigned long *)sp == STACKLEAK_POISON) { + poison_count++; + } else { + poison_count = 0; + poison_high = sp; + } + } + + return poison_high; +} + static inline void stackleak_task_init(struct task_struct *t) { - t->lowest_stack = (unsigned long)end_of_stack(t) + sizeof(unsigned long); + t->lowest_stack = stackleak_task_low_bound(t); # ifdef CONFIG_STACKLEAK_METRICS t->prev_lowest_stack = t->lowest_stack; # endif diff --git a/include/linux/static_call.h b/include/linux/static_call.h index 3e56a9751c06..df53bed9d71f 100644 --- a/include/linux/static_call.h +++ b/include/linux/static_call.h @@ -180,13 +180,13 @@ extern int static_call_text_reserved(void *start, void *end); extern long __static_call_return0(void); -#define __DEFINE_STATIC_CALL(name, _func, _func_init) \ +#define DEFINE_STATIC_CALL(name, _func) \ DECLARE_STATIC_CALL(name, _func); \ struct static_call_key STATIC_CALL_KEY(name) = { \ - .func = _func_init, \ + .func = _func, \ .type = 1, \ }; \ - ARCH_DEFINE_STATIC_CALL_TRAMP(name, _func_init) + ARCH_DEFINE_STATIC_CALL_TRAMP(name, _func) #define DEFINE_STATIC_CALL_NULL(name, _func) \ DECLARE_STATIC_CALL(name, _func); \ @@ -196,6 +196,14 @@ extern long __static_call_return0(void); }; \ ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name) +#define DEFINE_STATIC_CALL_RET0(name, _func) \ + DECLARE_STATIC_CALL(name, _func); \ + struct static_call_key STATIC_CALL_KEY(name) = { \ + .func = __static_call_return0, \ + .type = 1, \ + }; \ + ARCH_DEFINE_STATIC_CALL_RET0_TRAMP(name) + #define static_call_cond(name) (void)__static_call(name) #define EXPORT_STATIC_CALL(name) \ @@ -217,12 +225,12 @@ extern long __static_call_return0(void); static inline int static_call_init(void) { return 0; } -#define __DEFINE_STATIC_CALL(name, _func, _func_init) \ +#define DEFINE_STATIC_CALL(name, _func) \ DECLARE_STATIC_CALL(name, _func); \ struct static_call_key STATIC_CALL_KEY(name) = { \ - .func = _func_init, \ + .func = _func, \ }; \ - ARCH_DEFINE_STATIC_CALL_TRAMP(name, _func_init) + ARCH_DEFINE_STATIC_CALL_TRAMP(name, _func) #define DEFINE_STATIC_CALL_NULL(name, _func) \ DECLARE_STATIC_CALL(name, _func); \ @@ -231,6 +239,12 @@ static inline int static_call_init(void) { return 0; } }; \ ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name) +#define DEFINE_STATIC_CALL_RET0(name, _func) \ + DECLARE_STATIC_CALL(name, _func); \ + struct static_call_key STATIC_CALL_KEY(name) = { \ + .func = __static_call_return0, \ + }; \ + ARCH_DEFINE_STATIC_CALL_RET0_TRAMP(name) #define static_call_cond(name) (void)__static_call(name) @@ -248,10 +262,7 @@ static inline int static_call_text_reserved(void *start, void *end) return 0; } -static inline long __static_call_return0(void) -{ - return 0; -} +extern long __static_call_return0(void); #define EXPORT_STATIC_CALL(name) \ EXPORT_SYMBOL(STATIC_CALL_KEY(name)); \ @@ -281,11 +292,14 @@ static inline long __static_call_return0(void) .func = _func_init, \ } +#define DEFINE_STATIC_CALL(name, _func) \ + __DEFINE_STATIC_CALL(name, _func, _func) + #define DEFINE_STATIC_CALL_NULL(name, _func) \ - DECLARE_STATIC_CALL(name, _func); \ - struct static_call_key STATIC_CALL_KEY(name) = { \ - .func = NULL, \ - } + __DEFINE_STATIC_CALL(name, _func, NULL) + +#define DEFINE_STATIC_CALL_RET0(name, _func) \ + __DEFINE_STATIC_CALL(name, _func, __static_call_return0) static inline void __static_call_nop(void) { } @@ -327,10 +341,4 @@ static inline int static_call_text_reserved(void *start, void *end) #endif /* CONFIG_HAVE_STATIC_CALL */ -#define DEFINE_STATIC_CALL(name, _func) \ - __DEFINE_STATIC_CALL(name, _func, _func) - -#define DEFINE_STATIC_CALL_RET0(name, _func) \ - __DEFINE_STATIC_CALL(name, _func, __static_call_return0) - #endif /* _LINUX_STATIC_CALL_H */ diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 24eea1b05ca2..29917850f079 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -270,5 +270,6 @@ struct plat_stmmacenet_data { int msi_rx_base_vec; int msi_tx_base_vec; bool use_phy_wol; + bool sph_disable; }; #endif diff --git a/include/linux/stop_machine.h b/include/linux/stop_machine.h index 46fb3ebdd16e..ea7a74ea7389 100644 --- a/include/linux/stop_machine.h +++ b/include/linux/stop_machine.h @@ -124,6 +124,22 @@ int stop_machine(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus); */ int stop_machine_cpuslocked(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus); +/** + * stop_core_cpuslocked: - stop all threads on just one core + * @cpu: any cpu in the targeted core + * @fn: the function to run + * @data: the data ptr for @fn() + * + * Same as above, but instead of every CPU, only the logical CPUs of a + * single core are affected. + * + * Context: Must be called from within a cpus_read_lock() protected region. + * + * Return: 0 if all executions of @fn returned 0, any non zero return + * value if any returned non zero. + */ +int stop_core_cpuslocked(unsigned int cpu, cpu_stop_fn_t fn, void *data); + int stop_machine_from_inactive_cpu(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus); #else /* CONFIG_SMP || CONFIG_HOTPLUG_CPU */ diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index 267b7aeaf1a6..90501404fa49 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -160,6 +160,7 @@ struct rpc_add_xprt_test { #define RPC_CLNT_CREATE_NO_RETRANS_TIMEOUT (1UL << 9) #define RPC_CLNT_CREATE_SOFTERR (1UL << 10) #define RPC_CLNT_CREATE_REUSEPORT (1UL << 11) +#define RPC_CLNT_CREATE_CONNECTED (1UL << 12) struct rpc_clnt *rpc_create(struct rpc_create_args *args); struct rpc_clnt *rpc_bind_new_program(struct rpc_clnt *, diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index a5dda4987e8b..217711fc9cac 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -395,6 +395,7 @@ struct svc_deferred_req { size_t addrlen; struct sockaddr_storage daddr; /* where reply must come from */ size_t daddrlen; + void *xprt_ctxt; struct cache_deferred_req handle; size_t xprt_hlen; int argslen; diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 45a9530d3839..522bbf937957 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -144,7 +144,7 @@ struct rpc_xprt_ops { unsigned short (*get_srcport)(struct rpc_xprt *xprt); int (*buf_alloc)(struct rpc_task *task); void (*buf_free)(struct rpc_task *task); - void (*prepare_request)(struct rpc_rqst *req); + int (*prepare_request)(struct rpc_rqst *req); int (*send_request)(struct rpc_rqst *req); void (*wait_for_reply_request)(struct rpc_task *task); void (*timer)(struct rpc_xprt *xprt, struct rpc_task *task); @@ -358,10 +358,9 @@ int xprt_reserve_xprt_cong(struct rpc_xprt *xprt, struct rpc_task *task); void xprt_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task); void xprt_free_slot(struct rpc_xprt *xprt, struct rpc_rqst *req); -void xprt_request_prepare(struct rpc_rqst *req); bool xprt_prepare_transmit(struct rpc_task *task); void xprt_request_enqueue_transmit(struct rpc_task *task); -void xprt_request_enqueue_receive(struct rpc_task *task); +int xprt_request_enqueue_receive(struct rpc_task *task); void xprt_request_wait_receive(struct rpc_task *task); void xprt_request_dequeue_xprt(struct rpc_task *task); bool xprt_request_need_retransmit(struct rpc_task *task); diff --git a/include/linux/suspend.h b/include/linux/suspend.h index 300273ff40cc..70f2921e2e70 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -542,22 +542,56 @@ static inline void unlock_system_sleep(void) {} #ifdef CONFIG_PM_SLEEP_DEBUG extern bool pm_print_times_enabled; extern bool pm_debug_messages_on; -extern __printf(2, 3) void __pm_pr_dbg(bool defer, const char *fmt, ...); +static inline int pm_dyn_debug_messages_on(void) +{ +#ifdef CONFIG_DYNAMIC_DEBUG + return 1; +#else + return 0; +#endif +} +#ifndef pr_fmt +#define pr_fmt(fmt) "PM: " fmt +#endif +#define __pm_pr_dbg(fmt, ...) \ + do { \ + if (pm_debug_messages_on) \ + printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__); \ + else if (pm_dyn_debug_messages_on()) \ + pr_debug(fmt, ##__VA_ARGS__); \ + } while (0) +#define __pm_deferred_pr_dbg(fmt, ...) \ + do { \ + if (pm_debug_messages_on) \ + printk_deferred(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__); \ + } while (0) #else #define pm_print_times_enabled (false) #define pm_debug_messages_on (false) #include <linux/printk.h> -#define __pm_pr_dbg(defer, fmt, ...) \ - no_printk(KERN_DEBUG fmt, ##__VA_ARGS__) +#define __pm_pr_dbg(fmt, ...) \ + no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) +#define __pm_deferred_pr_dbg(fmt, ...) \ + no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #endif +/** + * pm_pr_dbg - print pm sleep debug messages + * + * If pm_debug_messages_on is enabled, print message. + * If pm_debug_messages_on is disabled and CONFIG_DYNAMIC_DEBUG is enabled, + * print message only from instances explicitly enabled on dynamic debug's + * control. + * If pm_debug_messages_on is disabled and CONFIG_DYNAMIC_DEBUG is disabled, + * don't print message. + */ #define pm_pr_dbg(fmt, ...) \ - __pm_pr_dbg(false, fmt, ##__VA_ARGS__) + __pm_pr_dbg(fmt, ##__VA_ARGS__) #define pm_deferred_pr_dbg(fmt, ...) \ - __pm_pr_dbg(true, fmt, ##__VA_ARGS__) + __pm_deferred_pr_dbg(fmt, ##__VA_ARGS__) #ifdef CONFIG_PM_AUTOSLEEP diff --git a/include/linux/t10-pi.h b/include/linux/t10-pi.h index a4b1af581f69..248f4ac95642 100644 --- a/include/linux/t10-pi.h +++ b/include/linux/t10-pi.h @@ -59,6 +59,15 @@ struct crc64_pi_tuple { __u8 ref_tag[6]; }; +/** + * lower_48_bits() - return bits 0-47 of a number + * @n: the number we're accessing + */ +static inline u64 lower_48_bits(u64 n) +{ + return n & ((1ull << 48) - 1); +} + static inline u64 ext_pi_ref_tag(struct request *rq) { unsigned int shift = ilog2(queue_logical_block_size(rq->q)); diff --git a/include/linux/task_work.h b/include/linux/task_work.h index 897494b597ba..795ef5a68429 100644 --- a/include/linux/task_work.h +++ b/include/linux/task_work.h @@ -17,6 +17,7 @@ enum task_work_notify_mode { TWA_NONE, TWA_RESUME, TWA_SIGNAL, + TWA_SIGNAL_NO_IPI, }; static inline bool task_work_pending(struct task_struct *task) diff --git a/include/linux/thermal.h b/include/linux/thermal.h index c314893970b3..365733b428d8 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -299,6 +299,8 @@ struct thermal_zone_params { * temperature. * @set_trip_temp: a pointer to a function that sets the trip temperature on * hardware. + * @change_mode: a pointer to a function that notifies the thermal zone + * mode change. */ struct thermal_zone_of_device_ops { int (*get_temp)(void *, int *); @@ -306,6 +308,7 @@ struct thermal_zone_of_device_ops { int (*set_trips)(void *, int, int); int (*set_emul_temp)(void *, int); int (*set_trip_temp)(void *, int, int); + int (*change_mode) (void *, enum thermal_device_mode); }; /* Function declarations */ diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 78a98bdff76d..fe1e467ba046 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -177,6 +177,7 @@ static inline u64 ktime_get_raw_ns(void) extern u64 ktime_get_mono_fast_ns(void); extern u64 ktime_get_raw_fast_ns(void); extern u64 ktime_get_boot_fast_ns(void); +extern u64 ktime_get_tai_fast_ns(void); extern u64 ktime_get_real_fast_ns(void); /* diff --git a/include/linux/timer.h b/include/linux/timer.h index fda13c9d1256..648f00105f58 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -196,14 +196,6 @@ extern void init_timers(void); struct hrtimer; extern enum hrtimer_restart it_real_fn(struct hrtimer *); -#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) -struct ctl_table; - -extern unsigned int sysctl_timer_migration; -int timer_migration_handler(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos); -#endif - unsigned long __round_jiffies(unsigned long j, int cpu); unsigned long __round_jiffies_relative(unsigned long j, int cpu); unsigned long round_jiffies(unsigned long j); diff --git a/include/linux/timex.h b/include/linux/timex.h index 059b18eb1f1f..3871b06bd302 100644 --- a/include/linux/timex.h +++ b/include/linux/timex.h @@ -62,6 +62,8 @@ #include <linux/types.h> #include <linux/param.h> +unsigned long random_get_entropy_fallback(void); + #include <asm/timex.h> #ifndef random_get_entropy @@ -74,8 +76,14 @@ * * By default we use get_cycles() for this purpose, but individual * architectures may override this in their asm/timex.h header file. + * If a given arch does not have get_cycles(), then we fallback to + * using random_get_entropy_fallback(). */ -#define random_get_entropy() get_cycles() +#ifdef get_cycles +#define random_get_entropy() ((unsigned long)get_cycles()) +#else +#define random_get_entropy() random_get_entropy_fallback() +#endif #endif /* diff --git a/include/linux/topology.h b/include/linux/topology.h index f19bc3626297..4564faafd0e1 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -240,13 +240,6 @@ static inline const struct cpumask *cpu_smt_mask(int cpu) } #endif -#if defined(CONFIG_SCHED_CLUSTER) && !defined(cpu_cluster_mask) -static inline const struct cpumask *cpu_cluster_mask(int cpu) -{ - return topology_cluster_cpumask(cpu); -} -#endif - static inline const struct cpumask *cpu_cpu_mask(int cpu) { return cpumask_of_node(cpu_to_node(cpu)); diff --git a/include/linux/torture.h b/include/linux/torture.h index 63fa4196e51c..7038104463e4 100644 --- a/include/linux/torture.h +++ b/include/linux/torture.h @@ -118,7 +118,7 @@ void _torture_stop_kthread(char *m, struct task_struct **tp); _torture_stop_kthread("Stopping " #n " task", &(tp)) #ifdef CONFIG_PREEMPTION -#define torture_preempt_schedule() preempt_schedule() +#define torture_preempt_schedule() __preempt_schedule() #else #define torture_preempt_schedule() do { } while (0) #endif diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 546179418ffa..5a328cf02b75 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -231,6 +231,28 @@ static inline bool pagefault_disabled(void) */ #define faulthandler_disabled() (pagefault_disabled() || in_atomic()) +#ifndef CONFIG_ARCH_HAS_SUBPAGE_FAULTS + +/** + * probe_subpage_writeable: probe the user range for write faults at sub-page + * granularity (e.g. arm64 MTE) + * @uaddr: start of address range + * @size: size of address range + * + * Returns 0 on success, the number of bytes not probed on fault. + * + * It is expected that the caller checked for the write permission of each + * page in the range either by put_user() or GUP. The architecture port can + * implement a more efficient get_user() probing if the same sub-page faults + * are triggered by either a read or a write. + */ +static inline size_t probe_subpage_writeable(char __user *uaddr, size_t size) +{ + return 0; +} + +#endif /* CONFIG_ARCH_HAS_SUBPAGE_FAULTS */ + #ifndef ARCH_HAS_NOCACHE_UACCESS static inline __must_check unsigned long diff --git a/include/linux/usb/pd_bdo.h b/include/linux/usb/pd_bdo.h index 033fe3e17141..7c25b88d79f9 100644 --- a/include/linux/usb/pd_bdo.h +++ b/include/linux/usb/pd_bdo.h @@ -15,7 +15,7 @@ #define BDO_MODE_CARRIER2 (5 << 28) #define BDO_MODE_CARRIER3 (6 << 28) #define BDO_MODE_EYE (7 << 28) -#define BDO_MODE_TESTDATA (8 << 28) +#define BDO_MODE_TESTDATA (8U << 28) #define BDO_MODE_MASK(mode) ((mode) & 0xf0000000) diff --git a/include/linux/vermagic.h b/include/linux/vermagic.h index 329d63babaeb..a54046bf37e5 100644 --- a/include/linux/vermagic.h +++ b/include/linux/vermagic.h @@ -32,11 +32,11 @@ #else #define MODULE_VERMAGIC_MODVERSIONS "" #endif -#ifdef RANDSTRUCT_PLUGIN -#include <generated/randomize_layout_hash.h> -#define MODULE_RANDSTRUCT_PLUGIN "RANDSTRUCT_PLUGIN_" RANDSTRUCT_HASHED_SEED +#ifdef RANDSTRUCT +#include <generated/randstruct_hash.h> +#define MODULE_RANDSTRUCT "RANDSTRUCT_" RANDSTRUCT_HASHED_SEED #else -#define MODULE_RANDSTRUCT_PLUGIN +#define MODULE_RANDSTRUCT #endif #define VERMAGIC_STRING \ @@ -44,6 +44,6 @@ MODULE_VERMAGIC_SMP MODULE_VERMAGIC_PREEMPT \ MODULE_VERMAGIC_MODULE_UNLOAD MODULE_VERMAGIC_MODVERSIONS \ MODULE_ARCH_VERMAGIC \ - MODULE_RANDSTRUCT_PLUGIN + MODULE_RANDSTRUCT #endif /* _LINUX_VERMAGIC_H */ diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h index 74a4a0f17b28..48f2dd3c568c 100644 --- a/include/linux/vfio_pci_core.h +++ b/include/linux/vfio_pci_core.h @@ -133,6 +133,8 @@ struct vfio_pci_core_device { struct mutex ioeventfds_lock; struct list_head ioeventfds_list; struct vfio_pci_vf_token *vf_token; + struct list_head sriov_pfs_item; + struct vfio_pci_core_device *sriov_pf_core_dev; struct notifier_block nb; struct mutex vma_lock; struct list_head vma_list; diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index dafdc7f48c01..b341dd62aa4d 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -23,8 +23,6 @@ struct virtio_shm_region { * any of @get/@set, @get_status/@set_status, or @get_features/ * @finalize_features are NOT safe to be called from an atomic * context. - * @enable_cbs: enable the callbacks - * vdev: the virtio_device * @get: read the value of a configuration field * vdev: the virtio_device * offset: the offset of the configuration field @@ -78,7 +76,6 @@ struct virtio_shm_region { */ typedef void vq_callback_t(struct virtqueue *); struct virtio_config_ops { - void (*enable_cbs)(struct virtio_device *vdev); void (*get)(struct virtio_device *vdev, unsigned offset, void *buf, unsigned len); void (*set)(struct virtio_device *vdev, unsigned offset, @@ -233,9 +230,6 @@ void virtio_device_ready(struct virtio_device *dev) { unsigned status = dev->config->get_status(dev); - if (dev->config->enable_cbs) - dev->config->enable_cbs(dev); - BUG_ON(status & VIRTIO_CONFIG_S_DRIVER_OK); dev->config->set_status(dev, status | VIRTIO_CONFIG_S_DRIVER_OK); } diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 3b1df7da402d..b159c2789961 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -26,7 +26,7 @@ struct notifier_block; /* in notifier.h */ #define VM_KASAN 0x00000080 /* has allocated kasan shadow memory */ #define VM_FLUSH_RESET_PERMS 0x00000100 /* reset direct map and flush TLB on unmap, can't be freed in atomic context */ #define VM_MAP_PUT_PAGES 0x00000200 /* put pages and free array in vfree */ -#define VM_NO_HUGE_VMAP 0x00000400 /* force PAGE_SIZE pte mapping */ +#define VM_ALLOW_HUGE_VMAP 0x00000400 /* Allow for huge pages on archs with HAVE_ARCH_HUGE_VMALLOC */ #if (defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)) && \ !defined(CONFIG_KASAN_VMALLOC) @@ -153,7 +153,7 @@ extern void *__vmalloc_node_range(unsigned long size, unsigned long align, const void *caller) __alloc_size(1); void *__vmalloc_node(unsigned long size, unsigned long align, gfp_t gfp_mask, int node, const void *caller) __alloc_size(1); -void *vmalloc_no_huge(unsigned long size) __alloc_size(1); +void *vmalloc_huge(unsigned long size, gfp_t gfp_mask) __alloc_size(1); extern void *__vmalloc_array(size_t n, size_t size, gfp_t flags) __alloc_size(1, 2); extern void *vmalloc_array(size_t n, size_t size) __alloc_size(1, 2); diff --git a/include/media/cec.h b/include/media/cec.h index 77346f757036..abee41ae02d0 100644 --- a/include/media/cec.h +++ b/include/media/cec.h @@ -118,6 +118,7 @@ struct cec_adap_ops { int (*adap_monitor_all_enable)(struct cec_adapter *adap, bool enable); int (*adap_monitor_pin_enable)(struct cec_adapter *adap, bool enable); int (*adap_log_addr)(struct cec_adapter *adap, u8 logical_addr); + void (*adap_configured)(struct cec_adapter *adap, bool configured); int (*adap_transmit)(struct cec_adapter *adap, u8 attempts, u32 signal_free_time, struct cec_msg *msg); void (*adap_status)(struct cec_adapter *adap, struct seq_file *file); @@ -163,6 +164,13 @@ struct cec_adap_ops { * @wait_queue: queue of transmits waiting for a reply * @transmitting: CEC messages currently being transmitted * @transmit_in_progress: true if a transmit is in progress + * @transmit_in_progress_aborted: true if a transmit is in progress is to be + * aborted. This happens if the logical address is + * invalidated while the transmit is ongoing. In that + * case the transmit will finish, but will not retransmit + * and be marked as ABORTED. + * @xfer_timeout_ms: the transfer timeout in ms. + * If 0, then timeout after 2.1 ms. * @kthread_config: kthread used to configure a CEC adapter * @config_completion: used to signal completion of the config kthread * @kthread: main CEC processing thread @@ -175,7 +183,9 @@ struct cec_adap_ops { * @needs_hpd: if true, then the HDMI HotPlug Detect pin must be high * in order to transmit or receive CEC messages. This is usually a HW * limitation. + * @is_enabled: the CEC adapter is enabled * @is_configuring: the CEC adapter is configuring (i.e. claiming LAs) + * @must_reconfigure: while configuring, the PA changed, so reclaim LAs * @is_configured: the CEC adapter is configured (i.e. has claimed LAs) * @cec_pin_is_high: if true then the CEC pin is high. Only used with the * CEC pin framework. @@ -217,6 +227,8 @@ struct cec_adapter { struct list_head wait_queue; struct cec_data *transmitting; bool transmit_in_progress; + bool transmit_in_progress_aborted; + unsigned int xfer_timeout_ms; struct task_struct *kthread_config; struct completion config_completion; @@ -231,7 +243,9 @@ struct cec_adapter { u16 phys_addr; bool needs_hpd; + bool is_enabled; bool is_configuring; + bool must_reconfigure; bool is_configured; bool cec_pin_is_high; bool adap_controls_phys_addr; diff --git a/include/media/dvb-usb-ids.h b/include/media/dvb-usb-ids.h index b0a535d6893a..1b7d10f3d4aa 100644 --- a/include/media/dvb-usb-ids.h +++ b/include/media/dvb-usb-ids.h @@ -10,81 +10,88 @@ #ifndef _DVB_USB_IDS_H_ #define _DVB_USB_IDS_H_ +#include <linux/usb.h> + +#define DVB_USB_DEV(pid, vid) \ + [vid] = { USB_DEVICE(USB_VID_ ## pid, USB_PID_ ## vid) } + +#define DVB_USB_DEV_VER(pid, vid, lo, hi) \ + [vid] = { USB_DEVICE_VER(USB_VID_ ## pid, USB_PID_ ## vid, lo, hi) } + /* Vendor IDs */ -#define USB_VID_ADSTECH 0x06e1 -#define USB_VID_AFATECH 0x15a4 + +#define USB_VID_774 0x7a69 +#define USB_VID_ADSTECH 0x06e1 +#define USB_VID_AFATECH 0x15a4 #define USB_VID_ALCOR_MICRO 0x058f #define USB_VID_ALINK 0x05e3 +#define USB_VID_AME 0x06be #define USB_VID_AMT 0x1c73 #define USB_VID_ANCHOR 0x0547 -#define USB_VID_ANSONIC 0x10b9 +#define USB_VID_ANSONIC 0x10b9 #define USB_VID_ANUBIS_ELECTRONIC 0x10fd #define USB_VID_ASUS 0x0b05 #define USB_VID_AVERMEDIA 0x07ca +#define USB_VID_AZUREWAVE 0x13d3 #define USB_VID_COMPRO 0x185b #define USB_VID_COMPRO_UNK 0x145f #define USB_VID_CONEXANT 0x0572 -#define USB_VID_CYPRESS 0x04b4 -#define USB_VID_DEXATEK 0x1d19 +#define USB_VID_CYPRESS 0x04b4 +#define USB_VID_DEXATEK 0x1d19 #define USB_VID_DIBCOM 0x10b8 #define USB_VID_DPOSH 0x1498 #define USB_VID_DVICO 0x0fe9 #define USB_VID_E3C 0x18b4 #define USB_VID_ELGATO 0x0fd9 #define USB_VID_EMPIA 0xeb1a +#define USB_VID_EVOLUTEPC 0x1e59 #define USB_VID_GENPIX 0x09c0 +#define USB_VID_GIGABYTE 0x1044 +#define USB_VID_GOTVIEW 0x1fe1 #define USB_VID_GRANDTEC 0x5032 #define USB_VID_GTEK 0x1f4d -#define USB_VID_HANFTEK 0x15f4 +#define USB_VID_HAMA 0x147f +#define USB_VID_HANFTEK 0x15f4 #define USB_VID_HAUPPAUGE 0x2040 +#define USB_VID_HUMAX_COEX 0x10b9 #define USB_VID_HYPER_PALTEK 0x1025 #define USB_VID_INTEL 0x8086 -#define USB_VID_ITETECH 0x048d +#define USB_VID_ITETECH 0x048d #define USB_VID_KWORLD 0xeb2a #define USB_VID_KWORLD_2 0x1b80 #define USB_VID_KYE 0x0458 -#define USB_VID_LEADTEK 0x0413 +#define USB_VID_LEADTEK 0x0413 #define USB_VID_LITEON 0x04ca #define USB_VID_MEDION 0x1660 +#define USB_VID_MICROSOFT 0x045e #define USB_VID_MIGLIA 0x18f3 #define USB_VID_MSI 0x0db0 #define USB_VID_MSI_2 0x1462 #define USB_VID_OPERA1 0x695c -#define USB_VID_PINNACLE 0x2304 #define USB_VID_PCTV 0x2013 +#define USB_VID_PINNACLE 0x2304 #define USB_VID_PIXELVIEW 0x1554 -#define USB_VID_REALTEK 0x0bda +#define USB_VID_PROF_1 0x3011 +#define USB_VID_PROF_2 0x3034 +#define USB_VID_REALTEK 0x0bda +#define USB_VID_SONY 0x1415 +#define USB_VID_TECHNISAT 0x14f7 #define USB_VID_TECHNOTREND 0x0b48 +#define USB_VID_TELESTAR 0x10b9 #define USB_VID_TERRATEC 0x0ccd #define USB_VID_TERRATEC_2 0x153b -#define USB_VID_TELESTAR 0x10b9 -#define USB_VID_VISIONPLUS 0x13d3 -#define USB_VID_SONY 0x1415 -#define USB_PID_TEVII_S421 0xd421 -#define USB_PID_TEVII_S480_1 0xd481 -#define USB_PID_TEVII_S480_2 0xd482 -#define USB_PID_TEVII_S630 0xd630 -#define USB_PID_TEVII_S632 0xd632 -#define USB_PID_TEVII_S650 0xd650 -#define USB_PID_TEVII_S660 0xd660 -#define USB_PID_TEVII_S662 0xd662 -#define USB_VID_TWINHAN 0x1822 +#define USB_VID_TEVII 0x9022 +#define USB_VID_TWINHAN 0x1822 #define USB_VID_ULTIMA_ELECTRONIC 0x05d8 -#define USB_VID_UNIWILL 0x1584 +#define USB_VID_UNIWILL 0x1584 +#define USB_VID_VISIONPLUS 0x13d3 #define USB_VID_WIDEVIEW 0x14aa -#define USB_VID_GIGABYTE 0x1044 -#define USB_VID_YUAN 0x1164 #define USB_VID_XTENSIONS 0x1ae7 +#define USB_VID_YUAN 0x1164 #define USB_VID_ZYDAS 0x0ace -#define USB_VID_HUMAX_COEX 0x10b9 -#define USB_VID_774 0x7a69 -#define USB_VID_EVOLUTEPC 0x1e59 -#define USB_VID_AZUREWAVE 0x13d3 -#define USB_VID_TECHNISAT 0x14f7 -#define USB_VID_HAMA 0x147f -#define USB_VID_MICROSOFT 0x045e /* Product IDs */ + #define USB_PID_ADSTECH_USB2_COLD 0xa333 #define USB_PID_ADSTECH_USB2_WARM 0xa334 #define USB_PID_AFATECH_AF9005 0x9020 @@ -95,341 +102,370 @@ #define USB_PID_AFATECH_AF9035_1002 0x1002 #define USB_PID_AFATECH_AF9035_1003 0x1003 #define USB_PID_AFATECH_AF9035_9035 0x9035 -#define USB_PID_TREKSTOR_DVBT 0x901b -#define USB_PID_TREKSTOR_TERRES_2_0 0xC803 #define USB_PID_ALINK_DTU 0xf170 +#define USB_PID_AME_DTV5100 0xa232 +#define USB_PID_ANCHOR_NEBULA_DIGITV 0x0201 #define USB_PID_ANSONIC_DVBT_USB 0x6000 +#define USB_PID_ANUBIS_LIFEVIEW_TV_WALKER_TWIN_COLD 0x0514 +#define USB_PID_ANUBIS_LIFEVIEW_TV_WALKER_TWIN_WARM 0x0513 +#define USB_PID_ANUBIS_MSI_DIGI_VOX_MINI_II 0x1513 #define USB_PID_ANYSEE 0x861f -#define USB_PID_AZUREWAVE_AD_TU700 0x3237 -#define USB_PID_AZUREWAVE_6007 0x0ccd -#define USB_PID_AVERMEDIA_DVBT_USB_COLD 0x0001 -#define USB_PID_AVERMEDIA_DVBT_USB_WARM 0x0002 +#define USB_PID_ASUS_U3000 0x171f +#define USB_PID_ASUS_U3000H 0x1736 +#define USB_PID_ASUS_U3100 0x173f +#define USB_PID_ASUS_U3100MINI_PLUS 0x1779 +#define USB_PID_AVERMEDIA_1867 0x1867 +#define USB_PID_AVERMEDIA_A309 0xa309 +#define USB_PID_AVERMEDIA_A310 0xa310 +#define USB_PID_AVERMEDIA_A805 0xa805 +#define USB_PID_AVERMEDIA_A815M 0x815a +#define USB_PID_AVERMEDIA_A835 0xa835 +#define USB_PID_AVERMEDIA_A835B_1835 0x1835 +#define USB_PID_AVERMEDIA_A835B_2835 0x2835 +#define USB_PID_AVERMEDIA_A835B_3835 0x3835 +#define USB_PID_AVERMEDIA_A835B_4835 0x4835 +#define USB_PID_AVERMEDIA_A850 0x850a +#define USB_PID_AVERMEDIA_A850T 0x850b +#define USB_PID_AVERMEDIA_A867 0xa867 +#define USB_PID_AVERMEDIA_B835 0xb835 #define USB_PID_AVERMEDIA_DVBT_USB2_COLD 0xa800 #define USB_PID_AVERMEDIA_DVBT_USB2_WARM 0xa801 +#define USB_PID_AVERMEDIA_EXPRESS 0xb568 +#define USB_PID_AVERMEDIA_H335 0x0335 +#define USB_PID_AVERMEDIA_HYBRID_ULTRA_USB_M039R 0x0039 +#define USB_PID_AVERMEDIA_HYBRID_ULTRA_USB_M039R_ATSC 0x1039 +#define USB_PID_AVERMEDIA_HYBRID_ULTRA_USB_M039R_DVBT 0x2039 +#define USB_PID_AVERMEDIA_MCE_USB_M038 0x1228 +#define USB_PID_AVERMEDIA_TD110 0xa110 +#define USB_PID_AVERMEDIA_TD310 0x1871 +#define USB_PID_AVERMEDIA_TWINSTAR 0x0825 +#define USB_PID_AVERMEDIA_VOLAR 0xa807 +#define USB_PID_AVERMEDIA_VOLAR_2 0xb808 +#define USB_PID_AVERMEDIA_VOLAR_A868R 0xa868 +#define USB_PID_AVERMEDIA_VOLAR_X 0xa815 +#define USB_PID_AVERMEDIA_VOLAR_X_2 0x8150 +#define USB_PID_AZUREWAVE_6007 0x0ccd +#define USB_PID_AZUREWAVE_AD_TU700 0x3237 +#define USB_PID_AZUREWAVE_AZ6027 0x3275 +#define USB_PID_AZUREWAVE_TWINHAN_VP7049 0x3219 #define USB_PID_COMPRO_DVBU2000_COLD 0xd000 -#define USB_PID_COMPRO_DVBU2000_WARM 0xd001 #define USB_PID_COMPRO_DVBU2000_UNK_COLD 0x010c #define USB_PID_COMPRO_DVBU2000_UNK_WARM 0x010d +#define USB_PID_COMPRO_DVBU2000_WARM 0xd001 #define USB_PID_COMPRO_VIDEOMATE_U500 0x1e78 #define USB_PID_COMPRO_VIDEOMATE_U500_PC 0x1e80 #define USB_PID_CONCEPTRONIC_CTVDIGRCU 0xe397 #define USB_PID_CONEXANT_D680_DMB 0x86d6 -#define USB_PID_CREATIX_CTX1921 0x1921 +#define USB_PID_CPYTO_REDI_PC50A 0xa803 +#define USB_PID_CTVDIGDUAL_V2 0xe410 +#define USB_PID_CYPRESS_DW2101 0x2101 +#define USB_PID_CYPRESS_DW2102 0x2102 +#define USB_PID_CYPRESS_DW2104 0x2104 +#define USB_PID_CYPRESS_DW3101 0x3101 +#define USB_PID_CYPRESS_OPERA1_COLD 0x2830 #define USB_PID_DELOCK_USB2_DVBT 0xb803 +#define USB_PID_DIBCOM_ANCHOR_2135_COLD 0x2131 #define USB_PID_DIBCOM_HOOK_DEFAULT 0x0064 #define USB_PID_DIBCOM_HOOK_DEFAULT_REENUM 0x0065 #define USB_PID_DIBCOM_MOD3000_COLD 0x0bb8 #define USB_PID_DIBCOM_MOD3000_WARM 0x0bb9 #define USB_PID_DIBCOM_MOD3001_COLD 0x0bc6 #define USB_PID_DIBCOM_MOD3001_WARM 0x0bc7 -#define USB_PID_DIBCOM_STK7700P 0x1e14 +#define USB_PID_DIBCOM_NIM7090 0x1bb2 +#define USB_PID_DIBCOM_NIM8096MD 0x1fa8 +#define USB_PID_DIBCOM_NIM9090M 0x2383 +#define USB_PID_DIBCOM_NIM9090MD 0x2384 +#define USB_PID_DIBCOM_STK7070P 0x1ebc +#define USB_PID_DIBCOM_STK7070PD 0x1ebe +#define USB_PID_DIBCOM_STK7700D 0x1ef0 +#define USB_PID_DIBCOM_STK7700P 0x1e14 #define USB_PID_DIBCOM_STK7700P_PC 0x1e78 -#define USB_PID_DIBCOM_STK7700D 0x1ef0 #define USB_PID_DIBCOM_STK7700_U7000 0x7001 -#define USB_PID_DIBCOM_STK7070P 0x1ebc -#define USB_PID_DIBCOM_STK7070PD 0x1ebe -#define USB_PID_DIBCOM_STK807XP 0x1f90 +#define USB_PID_DIBCOM_STK7770P 0x1e80 +#define USB_PID_DIBCOM_STK807XP 0x1f90 #define USB_PID_DIBCOM_STK807XPVR 0x1f98 -#define USB_PID_DIBCOM_STK8096GP 0x1fa0 -#define USB_PID_DIBCOM_STK8096PVR 0x1faa -#define USB_PID_DIBCOM_NIM8096MD 0x1fa8 -#define USB_PID_DIBCOM_TFE8096P 0x1f9C -#define USB_PID_DIBCOM_ANCHOR_2135_COLD 0x2131 -#define USB_PID_DIBCOM_STK7770P 0x1e80 -#define USB_PID_DIBCOM_NIM7090 0x1bb2 +#define USB_PID_DIBCOM_STK8096GP 0x1fa0 +#define USB_PID_DIBCOM_STK8096PVR 0x1faa #define USB_PID_DIBCOM_TFE7090PVR 0x1bb4 -#define USB_PID_DIBCOM_TFE7790P 0x1e6e -#define USB_PID_DIBCOM_NIM9090M 0x2383 -#define USB_PID_DIBCOM_NIM9090MD 0x2384 +#define USB_PID_DIBCOM_TFE7790P 0x1e6e +#define USB_PID_DIBCOM_TFE8096P 0x1f9C +#define USB_PID_DIGITALNOW_BLUEBIRD_DUAL_1_COLD 0xdb54 +#define USB_PID_DIGITALNOW_BLUEBIRD_DUAL_1_WARM 0xdb55 #define USB_PID_DPOSH_M9206_COLD 0x9206 #define USB_PID_DPOSH_M9206_WARM 0xa090 +#define USB_PID_DVICO_BLUEBIRD_DUAL_1_COLD 0xdb50 +#define USB_PID_DVICO_BLUEBIRD_DUAL_1_WARM 0xdb51 +#define USB_PID_DVICO_BLUEBIRD_DUAL_2_COLD 0xdb58 +#define USB_PID_DVICO_BLUEBIRD_DUAL_2_WARM 0xdb59 +#define USB_PID_DVICO_BLUEBIRD_DUAL_4 0xdb78 +#define USB_PID_DVICO_BLUEBIRD_DUAL_4_REV_2 0xdb98 +#define USB_PID_DVICO_BLUEBIRD_DVB_T_NANO_2 0xdb70 +#define USB_PID_DVICO_BLUEBIRD_DVB_T_NANO_2_NFW_WARM 0xdb71 +#define USB_PID_DVICO_BLUEBIRD_LG064F_COLD 0xd500 +#define USB_PID_DVICO_BLUEBIRD_LG064F_WARM 0xd501 +#define USB_PID_DVICO_BLUEBIRD_LGDT 0xd820 +#define USB_PID_DVICO_BLUEBIRD_LGZ201_COLD 0xdb00 +#define USB_PID_DVICO_BLUEBIRD_LGZ201_WARM 0xdb01 +#define USB_PID_DVICO_BLUEBIRD_TH7579_COLD 0xdb10 +#define USB_PID_DVICO_BLUEBIRD_TH7579_WARM 0xdb11 #define USB_PID_E3C_EC168 0x1689 #define USB_PID_E3C_EC168_2 0xfffa #define USB_PID_E3C_EC168_3 0xfffb #define USB_PID_E3C_EC168_4 0x1001 #define USB_PID_E3C_EC168_5 0x1002 +#define USB_PID_ELGATO_EYETV_DIVERSITY 0x0011 +#define USB_PID_ELGATO_EYETV_DTT 0x0021 +#define USB_PID_ELGATO_EYETV_DTT_2 0x003f +#define USB_PID_ELGATO_EYETV_DTT_Dlx 0x0020 +#define USB_PID_ELGATO_EYETV_SAT 0x002a +#define USB_PID_ELGATO_EYETV_SAT_V2 0x0025 +#define USB_PID_ELGATO_EYETV_SAT_V3 0x0036 +#define USB_PID_EMPIA_DIGIVOX_MINI_SL_COLD 0xe360 +#define USB_PID_EMPIA_DIGIVOX_MINI_SL_WARM 0xe361 +#define USB_PID_EMPIA_VSTREAM_COLD 0x17de +#define USB_PID_EMPIA_VSTREAM_WARM 0x17df +#define USB_PID_EVOLUTEPC_TVWAY_PLUS 0x0002 +#define USB_PID_EVOLVEO_XTRATV_STICK 0xa115 #define USB_PID_FREECOM_DVBT 0x0160 #define USB_PID_FREECOM_DVBT_2 0x0161 -#define USB_PID_UNIWILL_STK7700P 0x6003 +#define USB_PID_FRIIO_WHITE 0x0001 +#define USB_PID_GENIATECH_SU3000 0x3000 +#define USB_PID_GENIATECH_T220 0xd220 +#define USB_PID_GENIATECH_X3M_SPC1400HD 0x3100 #define USB_PID_GENIUS_TVGO_DVB_T03 0x4012 +#define USB_PID_GENPIX_8PSK_REV_1_COLD 0x0200 +#define USB_PID_GENPIX_8PSK_REV_1_WARM 0x0201 +#define USB_PID_GENPIX_8PSK_REV_2 0x0202 +#define USB_PID_GENPIX_SKYWALKER_1 0x0203 +#define USB_PID_GENPIX_SKYWALKER_2 0x0206 +#define USB_PID_GENPIX_SKYWALKER_CW3K 0x0204 +#define USB_PID_GIGABYTE_U7000 0x7001 +#define USB_PID_GIGABYTE_U8000 0x7002 +#define USB_PID_GOTVIEW_SAT_HD 0x5456 +#define USB_PID_GRANDTEC_DVBT_USB2_COLD 0x0bc6 +#define USB_PID_GRANDTEC_DVBT_USB2_WARM 0x0bc7 #define USB_PID_GRANDTEC_DVBT_USB_COLD 0x0fa0 #define USB_PID_GRANDTEC_DVBT_USB_WARM 0x0fa1 -#define USB_PID_GOTVIEW_SAT_HD 0x5456 +#define USB_PID_GRANDTEC_MOD3000_COLD 0x0bb8 +#define USB_PID_GRANDTEC_MOD3000_WARM 0x0bb9 +#define USB_PID_HAMA_DVBT_HYBRID 0x2758 +#define USB_PID_HANFTEK_UMT_010_COLD 0x0001 +#define USB_PID_HANFTEK_UMT_010_WARM 0x0015 +#define USB_PID_HAUPPAUGE_MAX_S2 0xd900 +#define USB_PID_HAUPPAUGE_MYTV_T 0x7080 +#define USB_PID_HAUPPAUGE_NOVA_TD_STICK 0x9580 +#define USB_PID_HAUPPAUGE_NOVA_TD_STICK_52009 0x5200 +#define USB_PID_HAUPPAUGE_NOVA_T_500 0x9941 +#define USB_PID_HAUPPAUGE_NOVA_T_500_2 0x9950 +#define USB_PID_HAUPPAUGE_NOVA_T_500_3 0x8400 +#define USB_PID_HAUPPAUGE_NOVA_T_STICK 0x7050 +#define USB_PID_HAUPPAUGE_NOVA_T_STICK_2 0x7060 +#define USB_PID_HAUPPAUGE_NOVA_T_STICK_3 0x7070 +#define USB_PID_HAUPPAUGE_TIGER_ATSC 0xb200 +#define USB_PID_HAUPPAUGE_TIGER_ATSC_B210 0xb210 +#define USB_PID_HAUPPAUGE_WINTV_NOVA_T_USB2_COLD 0x9300 +#define USB_PID_HAUPPAUGE_WINTV_NOVA_T_USB2_WARM 0x9301 +#define USB_PID_HUMAX_DVB_T_STICK_HIGH_SPEED_COLD 0x5000 +#define USB_PID_HUMAX_DVB_T_STICK_HIGH_SPEED_WARM 0x5001 #define USB_PID_INTEL_CE9500 0x9500 #define USB_PID_ITETECH_IT9135 0x9135 #define USB_PID_ITETECH_IT9135_9005 0x9005 #define USB_PID_ITETECH_IT9135_9006 0x9006 #define USB_PID_ITETECH_IT9303 0x9306 -#define USB_PID_KWORLD_399U 0xe399 -#define USB_PID_KWORLD_399U_2 0xe400 #define USB_PID_KWORLD_395U 0xe396 #define USB_PID_KWORLD_395U_2 0xe39b #define USB_PID_KWORLD_395U_3 0xe395 #define USB_PID_KWORLD_395U_4 0xe39a +#define USB_PID_KWORLD_399U 0xe399 +#define USB_PID_KWORLD_399U_2 0xe400 #define USB_PID_KWORLD_MC810 0xc810 -#define USB_PID_KWORLD_PC160_2T 0xc160 +#define USB_PID_KWORLD_PC160_2T 0xc160 #define USB_PID_KWORLD_PC160_T 0xc161 #define USB_PID_KWORLD_UB383_T 0xe383 #define USB_PID_KWORLD_UB499_2T_T09 0xe409 #define USB_PID_KWORLD_VSTREAM_COLD 0x17de -#define USB_PID_KWORLD_VSTREAM_WARM 0x17df +#define USB_PID_KYE_DVB_T_COLD 0x701e +#define USB_PID_KYE_DVB_T_WARM 0x701f +#define USB_PID_LEADTEK_WINFAST_DTV_DONGLE_COLD 0x6025 +#define USB_PID_LEADTEK_WINFAST_DTV_DONGLE_H 0x60f6 +#define USB_PID_LEADTEK_WINFAST_DTV_DONGLE_STK7700P 0x6f00 +#define USB_PID_LEADTEK_WINFAST_DTV_DONGLE_STK7700P_2 0x6f01 +#define USB_PID_LEADTEK_WINFAST_DTV_DONGLE_WARM 0x6026 +#define USB_PID_LITEON_DVB_T_COLD 0xf000 +#define USB_PID_LITEON_DVB_T_WARM 0xf001 +#define USB_PID_MEDION_CREATIX_CTX1921 0x1921 +#define USB_PID_MEDION_MD95700 0x0932 +#define USB_PID_MICROSOFT_XBOX_ONE_TUNER 0x02d5 +#define USB_PID_MIGLIA_WT220U_ZAP250_COLD 0x0220 +#define USB_PID_MSI_DIGIVOX_DUO 0x8801 +#define USB_PID_MSI_DIGI_VOX_MINI_III 0x8807 +#define USB_PID_MSI_MEGASKY580 0x5580 +#define USB_PID_MSI_MEGASKY580_55801 0x5581 +#define USB_PID_MYGICA_D689 0xd811 +#define USB_PID_MYGICA_T230 0xc688 +#define USB_PID_MYGICA_T230A 0x689a +#define USB_PID_MYGICA_T230C 0xc689 +#define USB_PID_MYGICA_T230C2 0xc68a +#define USB_PID_MYGICA_T230C2_LITE 0xc69a +#define USB_PID_MYGICA_T230C_LITE 0xc699 +#define USB_PID_NOXON_DAB_STICK 0x00b3 +#define USB_PID_NOXON_DAB_STICK_REV2 0x00e0 +#define USB_PID_NOXON_DAB_STICK_REV3 0x00b4 +#define USB_PID_OPERA1_WARM 0x3829 +#define USB_PID_PCTV_2002E 0x025c +#define USB_PID_PCTV_2002E_SE 0x025d +#define USB_PID_PCTV_200E 0x020e +#define USB_PID_PCTV_78E 0x025a +#define USB_PID_PCTV_79E 0x0262 +#define USB_PID_PCTV_DIBCOM_STK8096PVR 0x1faa +#define USB_PID_PCTV_PINNACLE_PCTV282E 0x0248 +#define USB_PID_PCTV_PINNACLE_PCTV73ESE 0x0245 +#define USB_PID_PINNACLE_EXPRESSCARD_320CX 0x022e +#define USB_PID_PINNACLE_PCTV2000E 0x022c +#define USB_PID_PINNACLE_PCTV282E 0x0248 +#define USB_PID_PINNACLE_PCTV340E 0x023d +#define USB_PID_PINNACLE_PCTV340E_SE 0x023e +#define USB_PID_PINNACLE_PCTV71E 0x022b +#define USB_PID_PINNACLE_PCTV72E 0x0236 +#define USB_PID_PINNACLE_PCTV73A 0x0243 +#define USB_PID_PINNACLE_PCTV73E 0x0237 +#define USB_PID_PINNACLE_PCTV73ESE 0x0245 +#define USB_PID_PINNACLE_PCTV74E 0x0246 +#define USB_PID_PINNACLE_PCTV801E 0x023a +#define USB_PID_PINNACLE_PCTV801E_SE 0x023b +#define USB_PID_PINNACLE_PCTV_400E 0x020f +#define USB_PID_PINNACLE_PCTV_450E 0x0222 +#define USB_PID_PINNACLE_PCTV_452E 0x021f +#define USB_PID_PINNACLE_PCTV_DUAL_DIVERSITY_DVB_T 0x0229 +#define USB_PID_PINNACLE_PCTV_DVB_T_FLASH 0x0228 +#define USB_PID_PIXELVIEW_SBTVD 0x5010 #define USB_PID_PROF_1100 0xb012 -#define USB_PID_TERRATEC_CINERGY_S 0x0064 -#define USB_PID_TERRATEC_CINERGY_T_USB_XE 0x0055 -#define USB_PID_TERRATEC_CINERGY_T_USB_XE_REV2 0x0069 -#define USB_PID_TERRATEC_CINERGY_T_STICK 0x0093 -#define USB_PID_TERRATEC_CINERGY_T_STICK_RC 0x0097 -#define USB_PID_TERRATEC_CINERGY_T_STICK_DUAL_RC 0x0099 -#define USB_PID_TERRATEC_CINERGY_T_STICK_BLACK_REV1 0x00a9 -#define USB_PID_TERRATEC_CINERGY_TC2_STICK 0x10b2 -#define USB_PID_TWINHAN_VP7041_COLD 0x3201 -#define USB_PID_TWINHAN_VP7041_WARM 0x3202 -#define USB_PID_TWINHAN_VP7020_COLD 0x3203 -#define USB_PID_TWINHAN_VP7020_WARM 0x3204 -#define USB_PID_TWINHAN_VP7045_COLD 0x3205 -#define USB_PID_TWINHAN_VP7045_WARM 0x3206 -#define USB_PID_TWINHAN_VP7021_COLD 0x3207 -#define USB_PID_TWINHAN_VP7021_WARM 0x3208 -#define USB_PID_TWINHAN_VP7049 0x3219 -#define USB_PID_TINYTWIN 0x3226 -#define USB_PID_TINYTWIN_2 0xe402 -#define USB_PID_TINYTWIN_3 0x9016 -#define USB_PID_DNTV_TINYUSB2_COLD 0x3223 -#define USB_PID_DNTV_TINYUSB2_WARM 0x3224 -#define USB_PID_ULTIMA_TVBOX_COLD 0x8105 -#define USB_PID_ULTIMA_TVBOX_WARM 0x8106 -#define USB_PID_ULTIMA_TVBOX_AN2235_COLD 0x8107 -#define USB_PID_ULTIMA_TVBOX_AN2235_WARM 0x8108 -#define USB_PID_ULTIMA_TVBOX_ANCHOR_COLD 0x2235 -#define USB_PID_ULTIMA_TVBOX_USB2_COLD 0x8109 -#define USB_PID_ULTIMA_TVBOX_USB2_WARM 0x810a -#define USB_PID_ARTEC_T14_COLD 0x810b -#define USB_PID_ARTEC_T14_WARM 0x810c -#define USB_PID_ARTEC_T14BR 0x810f -#define USB_PID_ULTIMA_TVBOX_USB2_FX_COLD 0x8613 -#define USB_PID_ULTIMA_TVBOX_USB2_FX_WARM 0x1002 -#define USB_PID_UNK_HYPER_PALTEK_COLD 0x005e -#define USB_PID_UNK_HYPER_PALTEK_WARM 0x005f -#define USB_PID_HANFTEK_UMT_010_COLD 0x0001 -#define USB_PID_HANFTEK_UMT_010_WARM 0x0015 -#define USB_PID_DTT200U_COLD 0x0201 -#define USB_PID_DTT200U_WARM 0x0301 -#define USB_PID_WT220U_ZAP250_COLD 0x0220 -#define USB_PID_WT220U_COLD 0x0222 -#define USB_PID_WT220U_WARM 0x0221 -#define USB_PID_WT220U_FC_COLD 0x0225 -#define USB_PID_WT220U_FC_WARM 0x0226 -#define USB_PID_WT220U_ZL0353_COLD 0x022a -#define USB_PID_WT220U_ZL0353_WARM 0x022b -#define USB_PID_WINTV_NOVA_T_USB2_COLD 0x9300 -#define USB_PID_WINTV_NOVA_T_USB2_WARM 0x9301 -#define USB_PID_HAUPPAUGE_NOVA_T_500 0x9941 -#define USB_PID_HAUPPAUGE_NOVA_T_500_2 0x9950 -#define USB_PID_HAUPPAUGE_NOVA_T_500_3 0x8400 -#define USB_PID_HAUPPAUGE_NOVA_T_STICK 0x7050 -#define USB_PID_HAUPPAUGE_NOVA_T_STICK_2 0x7060 -#define USB_PID_HAUPPAUGE_NOVA_T_STICK_3 0x7070 -#define USB_PID_HAUPPAUGE_MYTV_T 0x7080 -#define USB_PID_HAUPPAUGE_NOVA_TD_STICK 0x9580 -#define USB_PID_HAUPPAUGE_NOVA_TD_STICK_52009 0x5200 -#define USB_PID_HAUPPAUGE_TIGER_ATSC 0xb200 -#define USB_PID_HAUPPAUGE_TIGER_ATSC_B210 0xb210 -#define USB_PID_AVERMEDIA_EXPRESS 0xb568 -#define USB_PID_AVERMEDIA_VOLAR 0xa807 -#define USB_PID_AVERMEDIA_VOLAR_2 0xb808 -#define USB_PID_AVERMEDIA_VOLAR_A868R 0xa868 -#define USB_PID_AVERMEDIA_MCE_USB_M038 0x1228 -#define USB_PID_AVERMEDIA_HYBRID_ULTRA_USB_M039R 0x0039 -#define USB_PID_AVERMEDIA_HYBRID_ULTRA_USB_M039R_ATSC 0x1039 -#define USB_PID_AVERMEDIA_HYBRID_ULTRA_USB_M039R_DVBT 0x2039 -#define USB_PID_AVERMEDIA_VOLAR_X 0xa815 -#define USB_PID_AVERMEDIA_VOLAR_X_2 0x8150 -#define USB_PID_AVERMEDIA_A309 0xa309 -#define USB_PID_AVERMEDIA_A310 0xa310 -#define USB_PID_AVERMEDIA_A850 0x850a -#define USB_PID_AVERMEDIA_A850T 0x850b -#define USB_PID_AVERMEDIA_A805 0xa805 -#define USB_PID_AVERMEDIA_A815M 0x815a -#define USB_PID_AVERMEDIA_A835 0xa835 -#define USB_PID_AVERMEDIA_B835 0xb835 -#define USB_PID_AVERMEDIA_A835B_1835 0x1835 -#define USB_PID_AVERMEDIA_A835B_2835 0x2835 -#define USB_PID_AVERMEDIA_A835B_3835 0x3835 -#define USB_PID_AVERMEDIA_A835B_4835 0x4835 -#define USB_PID_AVERMEDIA_1867 0x1867 -#define USB_PID_AVERMEDIA_A867 0xa867 -#define USB_PID_AVERMEDIA_H335 0x0335 -#define USB_PID_AVERMEDIA_TD110 0xa110 -#define USB_PID_AVERMEDIA_TD310 0x1871 -#define USB_PID_AVERMEDIA_TWINSTAR 0x0825 -#define USB_PID_TECHNOTREND_CONNECT_S2400 0x3006 -#define USB_PID_TECHNOTREND_CONNECT_S2400_8KEEPROM 0x3009 -#define USB_PID_TECHNOTREND_CONNECT_CT3650 0x300d -#define USB_PID_TECHNOTREND_CONNECT_S2_4600 0x3011 -#define USB_PID_TECHNOTREND_CONNECT_CT2_4650_CI 0x3012 +#define USB_PID_PROF_7500 0x7500 +#define USB_PID_PROLECTRIX_DV107669 0xd803 +#define USB_PID_REALTEK_RTL2831U 0x2831 +#define USB_PID_REALTEK_RTL2832U 0x2832 +#define USB_PID_SIGMATEK_DVB_110 0x6610 +#define USB_PID_SONY_PLAYTV 0x0003 +#define USB_PID_SVEON_STV20 0xe39d +#define USB_PID_SVEON_STV20_RTL2832U 0xd39d +#define USB_PID_SVEON_STV21 0xd3b0 +#define USB_PID_SVEON_STV22 0xe401 +#define USB_PID_SVEON_STV22_IT9137 0xe411 +#define USB_PID_SVEON_STV27 0xd3af +#define USB_PID_TECHNISAT_AIRSTAR_TELESTICK_2 0x0004 +#define USB_PID_TECHNISAT_USB2_CABLESTAR_HDCI 0x0003 +#define USB_PID_TECHNISAT_USB2_DVB_S2 0x0500 +#define USB_PID_TECHNISAT_USB2_HDCI_V1 0x0001 +#define USB_PID_TECHNISAT_USB2_HDCI_V2 0x0002 +#define USB_PID_TECHNOTREND_CONNECT_CT2_4650_CI 0x3012 #define USB_PID_TECHNOTREND_CONNECT_CT2_4650_CI_2 0x3015 -#define USB_PID_TECHNOTREND_TVSTICK_CT2_4400 0x3014 +#define USB_PID_TECHNOTREND_CONNECT_CT3650 0x300d +#define USB_PID_TECHNOTREND_CONNECT_S2400 0x3006 +#define USB_PID_TECHNOTREND_CONNECT_S2400_8KEEPROM 0x3009 +#define USB_PID_TECHNOTREND_CONNECT_S2_3600 0x3007 +#define USB_PID_TECHNOTREND_CONNECT_S2_3650_CI 0x300a +#define USB_PID_TECHNOTREND_CONNECT_S2_4600 0x3011 #define USB_PID_TECHNOTREND_CONNECT_S2_4650_CI 0x3017 +#define USB_PID_TECHNOTREND_TVSTICK_CT2_4400 0x3014 +#define USB_PID_TELESTAR_STARSTICK_2 0x8000 #define USB_PID_TERRATEC_CINERGY_DT_XS_DIVERSITY 0x005a #define USB_PID_TERRATEC_CINERGY_DT_XS_DIVERSITY_2 0x0081 -#define USB_PID_TERRATEC_CINERGY_HT_USB_XE 0x0058 #define USB_PID_TERRATEC_CINERGY_HT_EXPRESS 0x0060 -#define USB_PID_TERRATEC_CINERGY_T_EXPRESS 0x0062 -#define USB_PID_TERRATEC_CINERGY_T_XXS 0x0078 -#define USB_PID_TERRATEC_CINERGY_T_XXS_2 0x00ab +#define USB_PID_TERRATEC_CINERGY_HT_USB_XE 0x0058 +#define USB_PID_TERRATEC_CINERGY_S 0x0064 +#define USB_PID_TERRATEC_CINERGY_S2_1 0x1181 +#define USB_PID_TERRATEC_CINERGY_S2_2 0x1182 +#define USB_PID_TERRATEC_CINERGY_S2_BOX 0x0105 #define USB_PID_TERRATEC_CINERGY_S2_R1 0x00a8 #define USB_PID_TERRATEC_CINERGY_S2_R2 0x00b0 #define USB_PID_TERRATEC_CINERGY_S2_R3 0x0102 #define USB_PID_TERRATEC_CINERGY_S2_R4 0x0105 -#define USB_PID_TERRATEC_CINERGY_S2_1 0x1181 -#define USB_PID_TERRATEC_CINERGY_S2_2 0x1182 +#define USB_PID_TERRATEC_CINERGY_T2 0x0038 +#define USB_PID_TERRATEC_CINERGY_TC2_STICK 0x10b2 +#define USB_PID_TERRATEC_CINERGY_T_EXPRESS 0x0062 +#define USB_PID_TERRATEC_CINERGY_T_STICK 0x0093 +#define USB_PID_TERRATEC_CINERGY_T_STICK_BLACK_REV1 0x00a9 +#define USB_PID_TERRATEC_CINERGY_T_STICK_DUAL_RC 0x0099 +#define USB_PID_TERRATEC_CINERGY_T_STICK_RC 0x0097 +#define USB_PID_TERRATEC_CINERGY_T_USB_XE 0x0055 +#define USB_PID_TERRATEC_CINERGY_T_USB_XE_REV2 0x0069 +#define USB_PID_TERRATEC_CINERGY_T_XXS 0x0078 +#define USB_PID_TERRATEC_CINERGY_T_XXS_2 0x00ab +#define USB_PID_TERRATEC_DVBS2CI_V1 0x10a4 +#define USB_PID_TERRATEC_DVBS2CI_V2 0x10ac #define USB_PID_TERRATEC_H7 0x10b4 #define USB_PID_TERRATEC_H7_2 0x10a3 #define USB_PID_TERRATEC_H7_3 0x10a5 #define USB_PID_TERRATEC_T1 0x10ae #define USB_PID_TERRATEC_T3 0x10a0 #define USB_PID_TERRATEC_T5 0x10a1 -#define USB_PID_NOXON_DAB_STICK 0x00b3 -#define USB_PID_NOXON_DAB_STICK_REV2 0x00e0 -#define USB_PID_NOXON_DAB_STICK_REV3 0x00b4 -#define USB_PID_PINNACLE_EXPRESSCARD_320CX 0x022e -#define USB_PID_PINNACLE_PCTV2000E 0x022c -#define USB_PID_PINNACLE_PCTV_DVB_T_FLASH 0x0228 -#define USB_PID_PINNACLE_PCTV_DUAL_DIVERSITY_DVB_T 0x0229 -#define USB_PID_PINNACLE_PCTV71E 0x022b -#define USB_PID_PINNACLE_PCTV72E 0x0236 -#define USB_PID_PINNACLE_PCTV73E 0x0237 -#define USB_PID_PINNACLE_PCTV310E 0x3211 -#define USB_PID_PINNACLE_PCTV801E 0x023a -#define USB_PID_PINNACLE_PCTV801E_SE 0x023b -#define USB_PID_PINNACLE_PCTV340E 0x023d -#define USB_PID_PINNACLE_PCTV340E_SE 0x023e -#define USB_PID_PINNACLE_PCTV73A 0x0243 -#define USB_PID_PINNACLE_PCTV73ESE 0x0245 -#define USB_PID_PINNACLE_PCTV74E 0x0246 -#define USB_PID_PINNACLE_PCTV282E 0x0248 -#define USB_PID_PIXELVIEW_SBTVD 0x5010 -#define USB_PID_PCTV_200E 0x020e -#define USB_PID_PCTV_400E 0x020f -#define USB_PID_PCTV_450E 0x0222 -#define USB_PID_PCTV_452E 0x021f -#define USB_PID_PCTV_78E 0x025a -#define USB_PID_PCTV_79E 0x0262 -#define USB_PID_REALTEK_RTL2831U 0x2831 -#define USB_PID_REALTEK_RTL2832U 0x2832 -#define USB_PID_TECHNOTREND_CONNECT_S2_3600 0x3007 -#define USB_PID_TECHNOTREND_CONNECT_S2_3650_CI 0x300a -#define USB_PID_NEBULA_DIGITV 0x0201 -#define USB_PID_DVICO_BLUEBIRD_LGDT 0xd820 -#define USB_PID_DVICO_BLUEBIRD_LG064F_COLD 0xd500 -#define USB_PID_DVICO_BLUEBIRD_LG064F_WARM 0xd501 -#define USB_PID_DVICO_BLUEBIRD_LGZ201_COLD 0xdb00 -#define USB_PID_DVICO_BLUEBIRD_LGZ201_WARM 0xdb01 -#define USB_PID_DVICO_BLUEBIRD_TH7579_COLD 0xdb10 -#define USB_PID_DVICO_BLUEBIRD_TH7579_WARM 0xdb11 -#define USB_PID_DVICO_BLUEBIRD_DUAL_1_COLD 0xdb50 -#define USB_PID_DVICO_BLUEBIRD_DUAL_1_WARM 0xdb51 -#define USB_PID_DVICO_BLUEBIRD_DUAL_2_COLD 0xdb58 -#define USB_PID_DVICO_BLUEBIRD_DUAL_2_WARM 0xdb59 -#define USB_PID_DVICO_BLUEBIRD_DUAL_4 0xdb78 -#define USB_PID_DVICO_BLUEBIRD_DUAL_4_REV_2 0xdb98 -#define USB_PID_DVICO_BLUEBIRD_DVB_T_NANO_2 0xdb70 -#define USB_PID_DVICO_BLUEBIRD_DVB_T_NANO_2_NFW_WARM 0xdb71 -#define USB_PID_DIGITALNOW_BLUEBIRD_DUAL_1_COLD 0xdb54 -#define USB_PID_DIGITALNOW_BLUEBIRD_DUAL_1_WARM 0xdb55 -#define USB_PID_MEDION_MD95700 0x0932 -#define USB_PID_MSI_MEGASKY580 0x5580 -#define USB_PID_MSI_MEGASKY580_55801 0x5581 -#define USB_PID_KYE_DVB_T_COLD 0x701e -#define USB_PID_KYE_DVB_T_WARM 0x701f -#define USB_PID_LITEON_DVB_T_COLD 0xf000 -#define USB_PID_LITEON_DVB_T_WARM 0xf001 -#define USB_PID_DIGIVOX_MINI_SL_COLD 0xe360 -#define USB_PID_DIGIVOX_MINI_SL_WARM 0xe361 -#define USB_PID_GRANDTEC_DVBT_USB2_COLD 0x0bc6 -#define USB_PID_GRANDTEC_DVBT_USB2_WARM 0x0bc7 +#define USB_PID_TEVII_S421 0xd421 +#define USB_PID_TEVII_S480_1 0xd481 +#define USB_PID_TEVII_S480_2 0xd482 +#define USB_PID_TEVII_S482_1 0xd483 +#define USB_PID_TEVII_S482_2 0xd484 +#define USB_PID_TEVII_S630 0xd630 +#define USB_PID_TEVII_S632 0xd632 +#define USB_PID_TEVII_S650 0xd650 +#define USB_PID_TEVII_S660 0xd660 +#define USB_PID_TEVII_S662 0xd662 +#define USB_PID_TINYTWIN 0x3226 +#define USB_PID_TINYTWIN_2 0xe402 +#define USB_PID_TINYTWIN_3 0x9016 +#define USB_PID_TREKSTOR_DVBT 0x901b +#define USB_PID_TREKSTOR_TERRES_2_0 0xC803 +#define USB_PID_TURBOX_DTT_2000 0xd3a4 +#define USB_PID_TWINHAN_VP7021_WARM 0x3208 +#define USB_PID_TWINHAN_VP7041_COLD 0x3201 +#define USB_PID_TWINHAN_VP7041_WARM 0x3202 +#define USB_PID_ULTIMA_ARTEC_T14BR 0x810f +#define USB_PID_ULTIMA_ARTEC_T14_COLD 0x810b +#define USB_PID_ULTIMA_ARTEC_T14_WARM 0x810c +#define USB_PID_ULTIMA_TVBOX_AN2235_COLD 0x8107 +#define USB_PID_ULTIMA_TVBOX_AN2235_WARM 0x8108 +#define USB_PID_ULTIMA_TVBOX_ANCHOR_COLD 0x2235 +#define USB_PID_ULTIMA_TVBOX_COLD 0x8105 +#define USB_PID_ULTIMA_TVBOX_USB2_COLD 0x8109 +#define USB_PID_ULTIMA_TVBOX_USB2_FX_COLD 0x8613 +#define USB_PID_ULTIMA_TVBOX_USB2_FX_WARM 0x1002 +#define USB_PID_ULTIMA_TVBOX_USB2_WARM 0x810a +#define USB_PID_ULTIMA_TVBOX_WARM 0x8106 +#define USB_PID_UNIWILL_STK7700P 0x6003 +#define USB_PID_UNK_HYPER_PALTEK_COLD 0x005e +#define USB_PID_UNK_HYPER_PALTEK_WARM 0x005f +#define USB_PID_VISIONPLUS_PINNACLE_PCTV310E 0x3211 +#define USB_PID_VISIONPLUS_TINYUSB2_COLD 0x3223 +#define USB_PID_VISIONPLUS_TINYUSB2_WARM 0x3224 +#define USB_PID_VISIONPLUS_VP7020_COLD 0x3203 +#define USB_PID_VISIONPLUS_VP7020_WARM 0x3204 +#define USB_PID_VISIONPLUS_VP7021_COLD 0x3207 +#define USB_PID_VISIONPLUS_VP7041_COLD 0x3201 +#define USB_PID_VISIONPLUS_VP7041_WARM 0x3202 +#define USB_PID_VISIONPLUS_VP7045_COLD 0x3205 +#define USB_PID_VISIONPLUS_VP7045_WARM 0x3206 +#define USB_PID_WIDEVIEW_DTT200U_COLD 0x0201 +#define USB_PID_WIDEVIEW_DTT200U_WARM 0x0301 +#define USB_PID_WIDEVIEW_DVBT_USB_COLD 0x0001 +#define USB_PID_WIDEVIEW_DVBT_USB_WARM 0x0002 +#define USB_PID_WIDEVIEW_WT220U_COLD 0x0222 +#define USB_PID_WIDEVIEW_WT220U_FC_COLD 0x0225 +#define USB_PID_WIDEVIEW_WT220U_FC_WARM 0x0226 +#define USB_PID_WIDEVIEW_WT220U_WARM 0x0221 +#define USB_PID_WIDEVIEW_WT220U_ZAP250_COLD 0x0220 +#define USB_PID_WIDEVIEW_WT220U_ZL0353_COLD 0x022a +#define USB_PID_WIDEVIEW_WT220U_ZL0353_WARM 0x022b #define USB_PID_WINFAST_DTV2000DS 0x6a04 #define USB_PID_WINFAST_DTV2000DS_PLUS 0x6f12 -#define USB_PID_WINFAST_DTV_DONGLE_COLD 0x6025 -#define USB_PID_WINFAST_DTV_DONGLE_WARM 0x6026 -#define USB_PID_WINFAST_DTV_DONGLE_STK7700P 0x6f00 -#define USB_PID_WINFAST_DTV_DONGLE_H 0x60f6 -#define USB_PID_WINFAST_DTV_DONGLE_STK7700P_2 0x6f01 -#define USB_PID_WINFAST_DTV_DONGLE_GOLD 0x6029 +#define USB_PID_WINFAST_DTV_DONGLE_GOLD 0x6029 #define USB_PID_WINFAST_DTV_DONGLE_MINID 0x6f0f -#define USB_PID_GENPIX_8PSK_REV_1_COLD 0x0200 -#define USB_PID_GENPIX_8PSK_REV_1_WARM 0x0201 -#define USB_PID_GENPIX_8PSK_REV_2 0x0202 -#define USB_PID_GENPIX_SKYWALKER_1 0x0203 -#define USB_PID_GENPIX_SKYWALKER_CW3K 0x0204 -#define USB_PID_GENPIX_SKYWALKER_2 0x0206 -#define USB_PID_SIGMATEK_DVB_110 0x6610 -#define USB_PID_MSI_DIGI_VOX_MINI_II 0x1513 -#define USB_PID_MSI_DIGIVOX_DUO 0x8801 -#define USB_PID_OPERA1_COLD 0x2830 -#define USB_PID_OPERA1_WARM 0x3829 -#define USB_PID_LIFEVIEW_TV_WALKER_TWIN_COLD 0x0514 -#define USB_PID_LIFEVIEW_TV_WALKER_TWIN_WARM 0x0513 -#define USB_PID_GIGABYTE_U7000 0x7001 -#define USB_PID_GIGABYTE_U8000 0x7002 -#define USB_PID_ASUS_U3000 0x171f -#define USB_PID_ASUS_U3000H 0x1736 -#define USB_PID_ASUS_U3100 0x173f -#define USB_PID_ASUS_U3100MINI_PLUS 0x1779 +#define USB_PID_WINTV_SOLOHD 0x0264 +#define USB_PID_WINTV_SOLOHD_2 0x8268 +#define USB_PID_XTENSIONS_XD_380 0x0381 #define USB_PID_YUAN_EC372S 0x1edc -#define USB_PID_YUAN_STK7700PH 0x1f08 -#define USB_PID_YUAN_PD378S 0x2edc #define USB_PID_YUAN_MC770 0x0871 +#define USB_PID_YUAN_PD378S 0x2edc #define USB_PID_YUAN_STK7700D 0x1efc -#define USB_PID_YUAN_STK7700D_2 0x1e8c -#define USB_PID_DW2102 0x2102 -#define USB_PID_DW2104 0x2104 -#define USB_PID_DW3101 0x3101 -#define USB_PID_XTENSIONS_XD_380 0x0381 -#define USB_PID_TELESTAR_STARSTICK_2 0x8000 -#define USB_PID_MSI_DIGI_VOX_MINI_III 0x8807 -#define USB_PID_SONY_PLAYTV 0x0003 -#define USB_PID_MYGICA_D689 0xd811 -#define USB_PID_MYGICA_T230 0xc688 -#define USB_PID_MYGICA_T230C 0xc689 -#define USB_PID_MYGICA_T230C2 0xc68a -#define USB_PID_MYGICA_T230C_LITE 0xc699 -#define USB_PID_MYGICA_T230C2_LITE 0xc69a -#define USB_PID_MYGICA_T230A 0x689a -#define USB_PID_ELGATO_EYETV_DIVERSITY 0x0011 -#define USB_PID_ELGATO_EYETV_DTT 0x0021 -#define USB_PID_ELGATO_EYETV_DTT_2 0x003f -#define USB_PID_ELGATO_EYETV_DTT_Dlx 0x0020 -#define USB_PID_ELGATO_EYETV_SAT 0x002a -#define USB_PID_ELGATO_EYETV_SAT_V2 0x0025 -#define USB_PID_ELGATO_EYETV_SAT_V3 0x0036 -#define USB_PID_DVB_T_USB_STICK_HIGH_SPEED_COLD 0x5000 -#define USB_PID_DVB_T_USB_STICK_HIGH_SPEED_WARM 0x5001 -#define USB_PID_FRIIO_WHITE 0x0001 -#define USB_PID_TVWAY_PLUS 0x0002 -#define USB_PID_SVEON_STV20 0xe39d -#define USB_PID_SVEON_STV20_RTL2832U 0xd39d -#define USB_PID_SVEON_STV21 0xd3b0 -#define USB_PID_SVEON_STV22 0xe401 -#define USB_PID_SVEON_STV22_IT9137 0xe411 -#define USB_PID_AZUREWAVE_AZ6027 0x3275 -#define USB_PID_TERRATEC_DVBS2CI_V1 0x10a4 -#define USB_PID_TERRATEC_DVBS2CI_V2 0x10ac -#define USB_PID_TECHNISAT_USB2_HDCI_V1 0x0001 -#define USB_PID_TECHNISAT_USB2_HDCI_V2 0x0002 -#define USB_PID_TECHNISAT_USB2_CABLESTAR_HDCI 0x0003 -#define USB_PID_TECHNISAT_AIRSTAR_TELESTICK_2 0x0004 -#define USB_PID_TECHNISAT_USB2_DVB_S2 0x0500 -#define USB_PID_CPYTO_REDI_PC50A 0xa803 -#define USB_PID_CTVDIGDUAL_V2 0xe410 -#define USB_PID_PCTV_2002E 0x025c -#define USB_PID_PCTV_2002E_SE 0x025d -#define USB_PID_SVEON_STV27 0xd3af -#define USB_PID_TURBOX_DTT_2000 0xd3a4 -#define USB_PID_WINTV_SOLOHD 0x0264 -#define USB_PID_WINTV_SOLOHD_2 0x8268 -#define USB_PID_EVOLVEO_XTRATV_STICK 0xa115 -#define USB_PID_HAMA_DVBT_HYBRID 0x2758 -#define USB_PID_XBOX_ONE_TUNER 0x02d5 -#define USB_PID_PROLECTRIX_DV107669 0xd803 +#define USB_PID_YUAN_STK7700D_2 0x1e8c +#define USB_PID_YUAN_STK7700PH 0x1f08 + #endif diff --git a/include/media/i2c/mt9t112.h b/include/media/i2c/mt9t112.h index e678b6ae8e2f..825b4a169da8 100644 --- a/include/media/i2c/mt9t112.h +++ b/include/media/i2c/mt9t112.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 */ /* mt9t112 Camera * * Copyright (C) 2009 Renesas Solutions Corp. diff --git a/include/media/i2c/wm8775.h b/include/media/i2c/wm8775.h index 83675817639e..6ccdeb3817ab 100644 --- a/include/media/i2c/wm8775.h +++ b/include/media/i2c/wm8775.h @@ -23,7 +23,7 @@ struct wm8775_platform_data { /* - * FIXME: Instead, we should parametrize the params + * FIXME: Instead, we should parameterize the params * that need different settings between ivtv, pvrusb2, and Nova-S */ bool is_nova_s; diff --git a/include/media/media-device.h b/include/media/media-device.h index 1345e6da688a..a10b30507524 100644 --- a/include/media/media-device.h +++ b/include/media/media-device.h @@ -13,12 +13,13 @@ #include <linux/list.h> #include <linux/mutex.h> +#include <linux/pci.h> +#include <linux/platform_device.h> #include <media/media-devnode.h> #include <media/media-entity.h> struct ida; -struct device; struct media_device; /** @@ -181,8 +182,7 @@ struct media_device { atomic_t request_id; }; -/* We don't need to include pci.h or usb.h here */ -struct pci_dev; +/* We don't need to include usb.h here */ struct usb_device; #ifdef CONFIG_MEDIA_CONTROLLER @@ -219,6 +219,15 @@ static inline __must_check int media_entity_enum_init( * So drivers need to first initialize the media device, register any entity * within the media device, create pad to pad links and then finally register * the media device by calling media_device_register() as a final step. + * + * The caller is responsible for initializing the media device before + * registration. The following fields must be set: + * + * - dev must point to the parent device + * - model must be filled with the device model name + * + * The bus_info field is set by media_device_init() for PCI and platform devices + * if the field begins with '\0'. */ void media_device_init(struct media_device *mdev); @@ -243,28 +252,25 @@ void media_device_cleanup(struct media_device *mdev); * The caller is responsible for initializing the &media_device structure * before registration. The following fields of &media_device must be set: * - * - &media_entity.dev must point to the parent device (usually a &pci_dev, - * &usb_interface or &platform_device instance). - * - * - &media_entity.model must be filled with the device model name as a + * - &media_device.model must be filled with the device model name as a * NUL-terminated UTF-8 string. The device/model revision must not be * stored in this field. * * The following fields are optional: * - * - &media_entity.serial is a unique serial number stored as a + * - &media_device.serial is a unique serial number stored as a * NUL-terminated ASCII string. The field is big enough to store a GUID * in text form. If the hardware doesn't provide a unique serial number * this field must be left empty. * - * - &media_entity.bus_info represents the location of the device in the + * - &media_device.bus_info represents the location of the device in the * system as a NUL-terminated ASCII string. For PCI/PCIe devices - * &media_entity.bus_info must be set to "PCI:" (or "PCIe:") followed by + * &media_device.bus_info must be set to "PCI:" (or "PCIe:") followed by * the value of pci_name(). For USB devices,the usb_make_path() function * must be used. This field is used by applications to distinguish between * otherwise identical devices that don't provide a serial number. * - * - &media_entity.hw_revision is the hardware device revision in a + * - &media_device.hw_revision is the hardware device revision in a * driver-specific format. When possible the revision should be formatted * with the KERNEL_VERSION() macro. * @@ -496,4 +502,27 @@ static inline void __media_device_usb_init(struct media_device *mdev, #define media_device_usb_init(mdev, udev, name) \ __media_device_usb_init(mdev, udev, name, KBUILD_MODNAME) +/** + * media_set_bus_info() - Set bus_info field + * + * @bus_info: Variable where to write the bus info (char array) + * @bus_info_size: Length of the bus_info + * @dev: Related struct device + * + * Sets bus information based on &dev. This is currently done for PCI and + * platform devices. dev is required to be non-NULL for this to happen. + * + * This function is not meant to be called from drivers. + */ +static inline void +media_set_bus_info(char *bus_info, size_t bus_info_size, struct device *dev) +{ + if (!dev) + strscpy(bus_info, "no bus info", bus_info_size); + else if (dev_is_platform(dev)) + snprintf(bus_info, bus_info_size, "platform:%s", dev_name(dev)); + else if (dev_is_pci(dev)) + snprintf(bus_info, bus_info_size, "PCI:%s", dev_name(dev)); +} + #endif diff --git a/include/media/media-entity.h b/include/media/media-entity.h index 742918962d46..a9a1c0ec5d1c 100644 --- a/include/media/media-entity.h +++ b/include/media/media-entity.h @@ -1030,7 +1030,6 @@ __must_check media_devnode_create(struct media_device *mdev, * removed. */ void media_devnode_remove(struct media_intf_devnode *devnode); -struct media_link * /** * media_create_intf_link() - creates a link between an entity and an interface @@ -1061,6 +1060,7 @@ struct media_link * * the interface and media_device_register_entity() should be called for the * interface that will be part of the link. */ +struct media_link * __must_check media_create_intf_link(struct media_entity *entity, struct media_interface *intf, u32 flags); @@ -1121,4 +1121,23 @@ void media_remove_intf_links(struct media_interface *intf); (((entity)->ops && (entity)->ops->operation) ? \ (entity)->ops->operation((entity) , ##args) : -ENOIOCTLCMD) +/** + * media_create_ancillary_link() - create an ancillary link between two + * instances of &media_entity + * + * @primary: pointer to the primary &media_entity + * @ancillary: pointer to the ancillary &media_entity + * + * Create an ancillary link between two entities, indicating that they + * represent two connected pieces of hardware that form a single logical unit. + * A typical example is a camera lens controller being linked to the sensor that + * it is supporting. + * + * The function sets both MEDIA_LNK_FL_ENABLED and MEDIA_LNK_FL_IMMUTABLE for + * the new link. + */ +struct media_link * +media_create_ancillary_link(struct media_entity *primary, + struct media_entity *ancillary); + #endif diff --git a/include/media/mipi-csi2.h b/include/media/mipi-csi2.h index 392794e5badd..c3d8f12234b1 100644 --- a/include/media/mipi-csi2.h +++ b/include/media/mipi-csi2.h @@ -31,6 +31,7 @@ #define MIPI_CSI2_DT_RGB565 0x22 #define MIPI_CSI2_DT_RGB666 0x23 #define MIPI_CSI2_DT_RGB888 0x24 +#define MIPI_CSI2_DT_RAW28 0x26 #define MIPI_CSI2_DT_RAW24 0x27 #define MIPI_CSI2_DT_RAW6 0x28 #define MIPI_CSI2_DT_RAW7 0x29 diff --git a/include/media/v4l2-fwnode.h b/include/media/v4l2-fwnode.h index feb132df45a3..15e4ab672223 100644 --- a/include/media/v4l2-fwnode.h +++ b/include/media/v4l2-fwnode.h @@ -173,6 +173,7 @@ struct v4l2_fwnode_connector { * @V4L2_FWNODE_BUS_TYPE_CSI2_DPHY: MIPI CSI-2 bus, D-PHY physical layer * @V4L2_FWNODE_BUS_TYPE_PARALLEL: Camera Parallel Interface bus * @V4L2_FWNODE_BUS_TYPE_BT656: BT.656 video format bus-type + * @V4L2_FWNODE_BUS_TYPE_DPI: Video Parallel Interface bus * @NR_OF_V4L2_FWNODE_BUS_TYPE: Number of bus-types */ enum v4l2_fwnode_bus_type { @@ -183,6 +184,7 @@ enum v4l2_fwnode_bus_type { V4L2_FWNODE_BUS_TYPE_CSI2_DPHY, V4L2_FWNODE_BUS_TYPE_PARALLEL, V4L2_FWNODE_BUS_TYPE_BT656, + V4L2_FWNODE_BUS_TYPE_DPI, NR_OF_V4L2_FWNODE_BUS_TYPE }; diff --git a/include/media/v4l2-h264.h b/include/media/v4l2-h264.h index 4b1c71c935e0..0d9eaa956123 100644 --- a/include/media/v4l2-h264.h +++ b/include/media/v4l2-h264.h @@ -15,12 +15,13 @@ /** * struct v4l2_h264_reflist_builder - Reference list builder object * - * @refs.pic_order_count: reference picture order count + * @refs.top_field_order_cnt: top field order count + * @refs.bottom_field_order_cnt: bottom field order count * @refs.frame_num: reference frame number - * @refs.pic_num: reference picture number * @refs.longterm: set to true for a long term reference * @refs: array of references * @cur_pic_order_count: picture order count of the frame being decoded + * @cur_pic_fields: fields present in the frame being decoded * @unordered_reflist: unordered list of references. Will be used to generate * ordered P/B0/B1 lists * @num_valid: number of valid references in the refs array @@ -31,13 +32,16 @@ */ struct v4l2_h264_reflist_builder { struct { - s32 pic_order_count; + s32 top_field_order_cnt; + s32 bottom_field_order_cnt; int frame_num; - u32 pic_num; u16 longterm : 1; } refs[V4L2_H264_NUM_DPB_ENTRIES]; + s32 cur_pic_order_count; - u8 unordered_reflist[V4L2_H264_NUM_DPB_ENTRIES]; + u8 cur_pic_fields; + + struct v4l2_h264_reference unordered_reflist[V4L2_H264_REF_LIST_LEN]; u8 num_valid; }; @@ -51,10 +55,10 @@ v4l2_h264_init_reflist_builder(struct v4l2_h264_reflist_builder *b, * v4l2_h264_build_b_ref_lists() - Build the B0/B1 reference lists * * @builder: reference list builder context - * @b0_reflist: 16-bytes array used to store the B0 reference list. Each entry - * is an index in the DPB - * @b1_reflist: 16-bytes array used to store the B1 reference list. Each entry - * is an index in the DPB + * @b0_reflist: 32 sized array used to store the B0 reference list. Each entry + * is a v4l2_h264_reference structure + * @b1_reflist: 32 sized array used to store the B1 reference list. Each entry + * is a v4l2_h264_reference structure * * This functions builds the B0/B1 reference lists. This procedure is described * in section '8.2.4 Decoding process for reference picture lists construction' @@ -63,14 +67,15 @@ v4l2_h264_init_reflist_builder(struct v4l2_h264_reflist_builder *b, */ void v4l2_h264_build_b_ref_lists(const struct v4l2_h264_reflist_builder *builder, - u8 *b0_reflist, u8 *b1_reflist); + struct v4l2_h264_reference *b0_reflist, + struct v4l2_h264_reference *b1_reflist); /** * v4l2_h264_build_p_ref_list() - Build the P reference list * * @builder: reference list builder context - * @reflist: 16-bytes array used to store the P reference list. Each entry - * is an index in the DPB + * @reflist: 32 sized array used to store the P reference list. Each entry + * is a v4l2_h264_reference structure * * This functions builds the P reference lists. This procedure is describe in * section '8.2.4 Decoding process for reference picture lists construction' @@ -79,6 +84,6 @@ v4l2_h264_build_b_ref_lists(const struct v4l2_h264_reflist_builder *builder, */ void v4l2_h264_build_p_ref_list(const struct v4l2_h264_reflist_builder *builder, - u8 *reflist); + struct v4l2_h264_reference *reflist); #endif /* _MEDIA_V4L2_H264_H */ diff --git a/include/media/v4l2-mediabus.h b/include/media/v4l2-mediabus.h index e0db3bcff9ed..f67a74daf799 100644 --- a/include/media/v4l2-mediabus.h +++ b/include/media/v4l2-mediabus.h @@ -129,6 +129,7 @@ struct v4l2_mbus_config_mipi_csi1 { * @V4L2_MBUS_CCP2: CCP2 (Compact Camera Port 2) * @V4L2_MBUS_CSI2_DPHY: MIPI CSI-2 serial interface, with D-PHY * @V4L2_MBUS_CSI2_CPHY: MIPI CSI-2 serial interface, with C-PHY + * @V4L2_MBUS_DPI: MIPI VIDEO DPI interface * @V4L2_MBUS_INVALID: invalid bus type (keep as last) */ enum v4l2_mbus_type { @@ -139,6 +140,7 @@ enum v4l2_mbus_type { V4L2_MBUS_CCP2, V4L2_MBUS_CSI2_DPHY, V4L2_MBUS_CSI2_CPHY, + V4L2_MBUS_DPI, V4L2_MBUS_INVALID, }; diff --git a/include/media/v4l2-subdev.h b/include/media/v4l2-subdev.h index 6c153b33bb04..b661e1817470 100644 --- a/include/media/v4l2-subdev.h +++ b/include/media/v4l2-subdev.h @@ -313,6 +313,17 @@ struct v4l2_subdev_audio_ops { }; /** + * struct v4l2_mbus_frame_desc_entry_csi2 + * + * @vc: CSI-2 virtual channel + * @dt: CSI-2 data type ID + */ +struct v4l2_mbus_frame_desc_entry_csi2 { + u8 vc; + u8 dt; +}; + +/** * enum v4l2_mbus_frame_desc_flags - media bus frame description flags * * @V4L2_MBUS_FRAME_DESC_FL_LEN_MAX: @@ -335,21 +346,46 @@ enum v4l2_mbus_frame_desc_flags { * %FRAME_DESC_FL_BLOB is not set. * @length: number of octets per frame, valid if @flags * %V4L2_MBUS_FRAME_DESC_FL_LEN_MAX is set. + * @bus: Bus-specific frame descriptor parameters + * @bus.csi2: CSI-2-specific bus configuration */ struct v4l2_mbus_frame_desc_entry { enum v4l2_mbus_frame_desc_flags flags; u32 pixelcode; u32 length; + union { + struct v4l2_mbus_frame_desc_entry_csi2 csi2; + } bus; }; #define V4L2_FRAME_DESC_ENTRY_MAX 4 /** + * enum v4l2_mbus_frame_desc_type - media bus frame description type + * + * @V4L2_MBUS_FRAME_DESC_TYPE_UNDEFINED: + * Undefined frame desc type. Drivers should not use this, it is + * for backwards compatibility. + * @V4L2_MBUS_FRAME_DESC_TYPE_PARALLEL: + * Parallel media bus. + * @V4L2_MBUS_FRAME_DESC_TYPE_CSI2: + * CSI-2 media bus. Frame desc parameters must be set in + * &struct v4l2_mbus_frame_desc_entry->csi2. + */ +enum v4l2_mbus_frame_desc_type { + V4L2_MBUS_FRAME_DESC_TYPE_UNDEFINED = 0, + V4L2_MBUS_FRAME_DESC_TYPE_PARALLEL, + V4L2_MBUS_FRAME_DESC_TYPE_CSI2, +}; + +/** * struct v4l2_mbus_frame_desc - media bus data frame description + * @type: type of the bus (enum v4l2_mbus_frame_desc_type) * @entry: frame descriptors array * @num_entries: number of entries in @entry array */ struct v4l2_mbus_frame_desc { + enum v4l2_mbus_frame_desc_type type; struct v4l2_mbus_frame_desc_entry entry[V4L2_FRAME_DESC_ENTRY_MAX]; unsigned short num_entries; }; @@ -645,6 +681,9 @@ struct v4l2_subdev_ir_ops { * This structure only needs to be passed to the pad op if the 'which' field * of the main argument is set to %V4L2_SUBDEV_FORMAT_TRY. For * %V4L2_SUBDEV_FORMAT_ACTIVE it is safe to pass %NULL. + * + * Note: This struct is also used in active state, and the 'try' prefix is + * historical and to be removed. */ struct v4l2_subdev_pad_config { struct v4l2_mbus_framefmt try_fmt; @@ -655,6 +694,8 @@ struct v4l2_subdev_pad_config { /** * struct v4l2_subdev_state - Used for storing subdev state information. * + * @_lock: default for 'lock' + * @lock: mutex for the state. May be replaced by the user. * @pads: &struct v4l2_subdev_pad_config array * * This structure only needs to be passed to the pad op if the 'which' field @@ -662,6 +703,9 @@ struct v4l2_subdev_pad_config { * %V4L2_SUBDEV_FORMAT_ACTIVE it is safe to pass %NULL. */ struct v4l2_subdev_state { + /* lock for the struct v4l2_subdev_state fields */ + struct mutex _lock; + struct mutex *lock; struct v4l2_subdev_pad_config *pads; }; @@ -885,6 +929,12 @@ struct v4l2_subdev_platform_data { * @subdev_notifier: A sub-device notifier implicitly registered for the sub- * device using v4l2_async_register_subdev_sensor(). * @pdata: common part of subdevice platform data + * @state_lock: A pointer to a lock used for all the subdev's states, set by the + * driver. This is optional. If NULL, each state instance will get + * a lock of its own. + * @active_state: Active state for the subdev (NULL for subdevs tracking the + * state internally). Initialized by calling + * v4l2_subdev_init_finalize(). * * Each instance of a subdev driver should create this struct, either * stand-alone or embedded in a larger struct. @@ -916,6 +966,20 @@ struct v4l2_subdev { struct v4l2_async_notifier *notifier; struct v4l2_async_notifier *subdev_notifier; struct v4l2_subdev_platform_data *pdata; + struct mutex *state_lock; + + /* + * The fields below are private, and should only be accessed via + * appropriate functions. + */ + + /* + * TODO: active_state should most likely be changed from a pointer to an + * embedded field. For the time being it's kept as a pointer to more + * easily catch uses of active_state in the cases where the driver + * doesn't support it. + */ + struct v4l2_subdev_state *active_state; }; @@ -970,7 +1034,7 @@ struct v4l2_subdev_fh { #if defined(CONFIG_VIDEO_V4L2_SUBDEV_API) /** - * v4l2_subdev_get_try_format - ancillary routine to call + * v4l2_subdev_get_pad_format - ancillary routine to call * &struct v4l2_subdev_pad_config->try_fmt * * @sd: pointer to &struct v4l2_subdev @@ -978,7 +1042,7 @@ struct v4l2_subdev_fh { * @pad: index of the pad in the &struct v4l2_subdev_state->pads array */ static inline struct v4l2_mbus_framefmt * -v4l2_subdev_get_try_format(struct v4l2_subdev *sd, +v4l2_subdev_get_pad_format(struct v4l2_subdev *sd, struct v4l2_subdev_state *state, unsigned int pad) { @@ -988,7 +1052,7 @@ v4l2_subdev_get_try_format(struct v4l2_subdev *sd, } /** - * v4l2_subdev_get_try_crop - ancillary routine to call + * v4l2_subdev_get_pad_crop - ancillary routine to call * &struct v4l2_subdev_pad_config->try_crop * * @sd: pointer to &struct v4l2_subdev @@ -996,7 +1060,7 @@ v4l2_subdev_get_try_format(struct v4l2_subdev *sd, * @pad: index of the pad in the &struct v4l2_subdev_state->pads array. */ static inline struct v4l2_rect * -v4l2_subdev_get_try_crop(struct v4l2_subdev *sd, +v4l2_subdev_get_pad_crop(struct v4l2_subdev *sd, struct v4l2_subdev_state *state, unsigned int pad) { @@ -1006,7 +1070,7 @@ v4l2_subdev_get_try_crop(struct v4l2_subdev *sd, } /** - * v4l2_subdev_get_try_compose - ancillary routine to call + * v4l2_subdev_get_pad_compose - ancillary routine to call * &struct v4l2_subdev_pad_config->try_compose * * @sd: pointer to &struct v4l2_subdev @@ -1014,7 +1078,7 @@ v4l2_subdev_get_try_crop(struct v4l2_subdev *sd, * @pad: index of the pad in the &struct v4l2_subdev_state->pads array. */ static inline struct v4l2_rect * -v4l2_subdev_get_try_compose(struct v4l2_subdev *sd, +v4l2_subdev_get_pad_compose(struct v4l2_subdev *sd, struct v4l2_subdev_state *state, unsigned int pad) { @@ -1023,7 +1087,20 @@ v4l2_subdev_get_try_compose(struct v4l2_subdev *sd, return &state->pads[pad].try_compose; } -#endif +/* + * Temprary helpers until uses of v4l2_subdev_get_try_* functions have been + * renamed + */ +#define v4l2_subdev_get_try_format(sd, state, pad) \ + v4l2_subdev_get_pad_format(sd, state, pad) + +#define v4l2_subdev_get_try_crop(sd, state, pad) \ + v4l2_subdev_get_pad_crop(sd, state, pad) + +#define v4l2_subdev_get_try_compose(sd, state, pad) \ + v4l2_subdev_get_pad_compose(sd, state, pad) + +#endif /* CONFIG_VIDEO_V4L2_SUBDEV_API */ extern const struct v4l2_file_operations v4l2_subdev_fops; @@ -1122,20 +1199,166 @@ int v4l2_subdev_link_validate_default(struct v4l2_subdev *sd, int v4l2_subdev_link_validate(struct media_link *link); /** - * v4l2_subdev_alloc_state - allocate v4l2_subdev_state + * __v4l2_subdev_state_alloc - allocate v4l2_subdev_state * * @sd: pointer to &struct v4l2_subdev for which the state is being allocated. + * @lock_name: name of the state lock + * @key: lock_class_key for the lock + * + * Must call __v4l2_subdev_state_free() when state is no longer needed. * - * Must call v4l2_subdev_free_state() when state is no longer needed. + * Not to be called directly by the drivers. */ -struct v4l2_subdev_state *v4l2_subdev_alloc_state(struct v4l2_subdev *sd); +struct v4l2_subdev_state *__v4l2_subdev_state_alloc(struct v4l2_subdev *sd, + const char *lock_name, + struct lock_class_key *key); /** - * v4l2_subdev_free_state - free a v4l2_subdev_state + * __v4l2_subdev_state_free - free a v4l2_subdev_state * * @state: v4l2_subdev_state to be freed. + * + * Not to be called directly by the drivers. + */ +void __v4l2_subdev_state_free(struct v4l2_subdev_state *state); + +/** + * v4l2_subdev_init_finalize() - Finalizes the initialization of the subdevice + * @sd: The subdev + * + * This function finalizes the initialization of the subdev, including + * allocation of the active state for the subdev. + * + * This function must be called by the subdev drivers that use the centralized + * active state, after the subdev struct has been initialized and + * media_entity_pads_init() has been called, but before registering the + * subdev. + * + * The user must call v4l2_subdev_cleanup() when the subdev is being removed. + */ +#define v4l2_subdev_init_finalize(sd) \ + ({ \ + static struct lock_class_key __key; \ + const char *name = KBUILD_BASENAME \ + ":" __stringify(__LINE__) ":sd->active_state->lock"; \ + __v4l2_subdev_init_finalize(sd, name, &__key); \ + }) + +int __v4l2_subdev_init_finalize(struct v4l2_subdev *sd, const char *name, + struct lock_class_key *key); + +/** + * v4l2_subdev_cleanup() - Releases the resources allocated by the subdevice + * @sd: The subdevice + * + * This function will release the resources allocated in + * v4l2_subdev_init_finalize. */ -void v4l2_subdev_free_state(struct v4l2_subdev_state *state); +void v4l2_subdev_cleanup(struct v4l2_subdev *sd); + +/** + * v4l2_subdev_lock_state() - Locks the subdev state + * @state: The subdevice state + * + * Locks the given subdev state. + * + * The state must be unlocked with v4l2_subdev_unlock_state() after use. + */ +static inline void v4l2_subdev_lock_state(struct v4l2_subdev_state *state) +{ + mutex_lock(state->lock); +} + +/** + * v4l2_subdev_unlock_state() - Unlocks the subdev state + * @state: The subdevice state + * + * Unlocks the given subdev state. + */ +static inline void v4l2_subdev_unlock_state(struct v4l2_subdev_state *state) +{ + mutex_unlock(state->lock); +} + +/** + * v4l2_subdev_get_unlocked_active_state() - Checks that the active subdev state + * is unlocked and returns it + * @sd: The subdevice + * + * Returns the active state for the subdevice, or NULL if the subdev does not + * support active state. If the state is not NULL, calls + * lockdep_assert_not_held() to issue a warning if the state is locked. + * + * This function is to be used e.g. when getting the active state for the sole + * purpose of passing it forward, without accessing the state fields. + */ +static inline struct v4l2_subdev_state * +v4l2_subdev_get_unlocked_active_state(struct v4l2_subdev *sd) +{ + if (sd->active_state) + lockdep_assert_not_held(sd->active_state->lock); + return sd->active_state; +} + +/** + * v4l2_subdev_get_locked_active_state() - Checks that the active subdev state + * is locked and returns it + * + * @sd: The subdevice + * + * Returns the active state for the subdevice, or NULL if the subdev does not + * support active state. If the state is not NULL, calls lockdep_assert_held() + * to issue a warning if the state is not locked. + * + * This function is to be used when the caller knows that the active state is + * already locked. + */ +static inline struct v4l2_subdev_state * +v4l2_subdev_get_locked_active_state(struct v4l2_subdev *sd) +{ + if (sd->active_state) + lockdep_assert_held(sd->active_state->lock); + return sd->active_state; +} + +/** + * v4l2_subdev_lock_and_get_active_state() - Locks and returns the active subdev + * state for the subdevice + * @sd: The subdevice + * + * Returns the locked active state for the subdevice, or NULL if the subdev + * does not support active state. + * + * The state must be unlocked with v4l2_subdev_unlock_state() after use. + */ +static inline struct v4l2_subdev_state * +v4l2_subdev_lock_and_get_active_state(struct v4l2_subdev *sd) +{ + if (sd->active_state) + v4l2_subdev_lock_state(sd->active_state); + return sd->active_state; +} + +#if defined(CONFIG_VIDEO_V4L2_SUBDEV_API) + +/** + * v4l2_subdev_get_fmt() - Fill format based on state + * @sd: subdevice + * @state: subdevice state + * @format: pointer to &struct v4l2_subdev_format + * + * Fill @format->format field based on the information in the @format struct. + * + * This function can be used by the subdev drivers which support active state to + * implement v4l2_subdev_pad_ops.get_fmt if the subdev driver does not need to + * do anything special in their get_fmt op. + * + * Returns 0 on success, error value otherwise. + */ +int v4l2_subdev_get_fmt(struct v4l2_subdev *sd, struct v4l2_subdev_state *state, + struct v4l2_subdev_format *format); + +#endif /* CONFIG_VIDEO_V4L2_SUBDEV_API */ #endif /* CONFIG_MEDIA_CONTROLLER */ @@ -1181,6 +1404,36 @@ extern const struct v4l2_subdev_ops v4l2_subdev_call_wrappers; }) /** + * v4l2_subdev_call_state_active - call an operation of a v4l2_subdev which + * takes state as a parameter, passing the + * subdev its active state. + * + * @sd: pointer to the &struct v4l2_subdev + * @o: name of the element at &struct v4l2_subdev_ops that contains @f. + * Each element there groups a set of callbacks functions. + * @f: callback function to be called. + * The callback functions are defined in groups, according to + * each element at &struct v4l2_subdev_ops. + * @args: arguments for @f. + * + * This is similar to v4l2_subdev_call(), except that this version can only be + * used for ops that take a subdev state as a parameter. The macro will get the + * active state, lock it before calling the op and unlock it after the call. + */ +#define v4l2_subdev_call_state_active(sd, o, f, args...) \ + ({ \ + int __result; \ + struct v4l2_subdev_state *state; \ + state = v4l2_subdev_get_unlocked_active_state(sd); \ + if (state) \ + v4l2_subdev_lock_state(state); \ + __result = v4l2_subdev_call(sd, o, f, state, ##args); \ + if (state) \ + v4l2_subdev_unlock_state(state); \ + __result; \ + }) + +/** * v4l2_subdev_has_op - Checks if a subdev defines a certain operation. * * @sd: pointer to the &struct v4l2_subdev @@ -1204,4 +1457,4 @@ extern const struct v4l2_subdev_ops v4l2_subdev_call_wrappers; void v4l2_subdev_notify_event(struct v4l2_subdev *sd, const struct v4l2_event *ev); -#endif +#endif /* _V4L2_SUBDEV_H */ diff --git a/include/media/videobuf2-v4l2.h b/include/media/videobuf2-v4l2.h index b66585e304e2..d818d9707695 100644 --- a/include/media/videobuf2-v4l2.h +++ b/include/media/videobuf2-v4l2.h @@ -302,10 +302,29 @@ __poll_t vb2_poll(struct vb2_queue *q, struct file *file, poll_table *wait); * The following functions are not part of the vb2 core API, but are simple * helper functions that you can use in your struct v4l2_file_operations, * struct v4l2_ioctl_ops and struct vb2_ops. They will serialize if vb2_queue->lock - * or video_device->lock is set, and they will set and test vb2_queue->owner - * to check if the calling filehandle is permitted to do the queuing operation. + * or video_device->lock is set, and they will set and test the queue owner + * (vb2_queue->owner) to check if the calling filehandle is permitted to do the + * queuing operation. */ +/** + * vb2_queue_is_busy() - check if the queue is busy + * @q: pointer to &struct vb2_queue with videobuf2 queue. + * @file: file through which the vb2 queue access is performed + * + * The queue is considered busy if it has an owner and the owner is not the + * @file. + * + * Queue ownership is acquired and checked by some of the v4l2_ioctl_ops helpers + * below. Drivers can also use this function directly when they need to + * open-code ioctl handlers, for instance to add additional checks between the + * queue ownership test and the call to the corresponding vb2 operation. + */ +static inline bool vb2_queue_is_busy(struct vb2_queue *q, struct file *file) +{ + return q->owner && q->owner != file->private_data; +} + /* struct v4l2_ioctl_ops helpers */ int vb2_ioctl_reqbufs(struct file *file, void *priv, diff --git a/include/memory/renesas-rpc-if.h b/include/memory/renesas-rpc-if.h index 7c93f5177532..9c0ad64b8d29 100644 --- a/include/memory/renesas-rpc-if.h +++ b/include/memory/renesas-rpc-if.h @@ -72,6 +72,7 @@ struct rpcif { enum rpcif_type type; enum rpcif_data_dir dir; u8 bus_size; + u8 xfer_size; void *buffer; u32 xferlen; u32 smcr; diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 5cb095b09a94..69ef31cea582 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -578,6 +578,7 @@ enum { #define HCI_ERROR_CONNECTION_TIMEOUT 0x08 #define HCI_ERROR_REJ_LIMITED_RESOURCES 0x0d #define HCI_ERROR_REJ_BAD_ADDR 0x0f +#define HCI_ERROR_INVALID_PARAMETERS 0x12 #define HCI_ERROR_REMOTE_USER_TERM 0x13 #define HCI_ERROR_REMOTE_LOW_RESOURCES 0x14 #define HCI_ERROR_REMOTE_POWER_OFF 0x15 diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index d5377740e99c..62d7b81b1cb7 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -36,6 +36,9 @@ /* HCI priority */ #define HCI_PRIO_MAX 7 +/* HCI maximum id value */ +#define HCI_MAX_ID 10000 + /* HCI Core structures */ struct inquiry_data { bdaddr_t bdaddr; @@ -1156,7 +1159,7 @@ int hci_conn_switch_role(struct hci_conn *conn, __u8 role); void hci_conn_enter_active_mode(struct hci_conn *conn, __u8 force_active); -void hci_le_conn_failed(struct hci_conn *conn, u8 status); +void hci_conn_failed(struct hci_conn *conn, u8 status); /* * hci_conn_get() and hci_conn_put() are used to control the life-time of an diff --git a/include/net/esp.h b/include/net/esp.h index 90cd02ff77ef..9c5637d41d95 100644 --- a/include/net/esp.h +++ b/include/net/esp.h @@ -4,8 +4,6 @@ #include <linux/skbuff.h> -#define ESP_SKB_FRAG_MAXSIZE (PAGE_SIZE << SKB_FRAG_PAGE_ORDER) - struct ip_esp_hdr; static inline struct ip_esp_hdr *ip_esp_hdr(const struct sk_buff *skb) diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h index aa33e1092e2c..9f65f1bfbd24 100644 --- a/include/net/flow_dissector.h +++ b/include/net/flow_dissector.h @@ -59,6 +59,8 @@ struct flow_dissector_key_vlan { __be16 vlan_tci; }; __be16 vlan_tpid; + __be16 vlan_eth_type; + u16 padding; }; struct flow_dissector_mpls_lse { diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index f72ec113ae56..98e1ec1a14f0 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -425,7 +425,7 @@ static inline void sk_rcv_saddr_set(struct sock *sk, __be32 addr) } int __inet_hash_connect(struct inet_timewait_death_row *death_row, - struct sock *sk, u32 port_offset, + struct sock *sk, u64 port_offset, int (*check_established)(struct inet_timewait_death_row *, struct sock *, __u16, struct inet_timewait_sock **)); diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h index 463ae5d33eb0..5b47545f22d3 100644 --- a/include/net/inet_timewait_sock.h +++ b/include/net/inet_timewait_sock.h @@ -71,7 +71,6 @@ struct inet_timewait_sock { tw_tos : 8; u32 tw_txhash; u32 tw_priority; - u32 tw_bslot; /* bind bucket slot */ struct timer_list tw_timer; struct inet_bind_bucket *tw_tb; }; @@ -110,6 +109,8 @@ static inline void inet_twsk_reschedule(struct inet_timewait_sock *tw, int timeo void inet_twsk_deschedule_put(struct inet_timewait_sock *tw); +void inet_twsk_purge(struct inet_hashinfo *hashinfo, int family); + static inline struct net *twsk_net(const struct inet_timewait_sock *twsk) { diff --git a/include/net/ip.h b/include/net/ip.h index 3984f2c39c4b..0161137914cf 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -56,6 +56,7 @@ struct inet_skb_parm { #define IPSKB_DOREDIRECT BIT(5) #define IPSKB_FRAG_PMTU BIT(6) #define IPSKB_L3SLAVE BIT(7) +#define IPSKB_NOPOLICY BIT(8) u16 frag_max_size; }; diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h index a38c4f1e4e5c..74b369bddf49 100644 --- a/include/net/ip6_tunnel.h +++ b/include/net/ip6_tunnel.h @@ -58,7 +58,7 @@ struct ip6_tnl { /* These fields used only by GRE */ __u32 i_seqno; /* The last seen seqno */ - __u32 o_seqno; /* The last output seqno */ + atomic_t o_seqno; /* The last output seqno */ int hlen; /* tun_hlen + encap_hlen */ int tun_hlen; /* Precalculated header length */ int encap_hlen; /* Encap header length (FOU,GUE) */ diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 0219fe907b26..c24fa934221d 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -116,7 +116,7 @@ struct ip_tunnel { /* These four fields used only by GRE */ u32 i_seqno; /* The last seen seqno */ - u32 o_seqno; /* The last output seqno */ + atomic_t o_seqno; /* The last output seqno */ int tun_hlen; /* Precalculated header length */ /* These four fields used only by ERSPAN */ @@ -243,11 +243,18 @@ static inline __be32 tunnel_id_to_key32(__be64 tun_id) static inline void ip_tunnel_init_flow(struct flowi4 *fl4, int proto, __be32 daddr, __be32 saddr, - __be32 key, __u8 tos, int oif, + __be32 key, __u8 tos, + struct net *net, int oif, __u32 mark, __u32 tun_inner_hash) { memset(fl4, 0, sizeof(*fl4)); - fl4->flowi4_oif = oif; + + if (oif) { + fl4->flowi4_l3mdev = l3mdev_master_upper_ifindex_by_index_rcu(net, oif); + /* Legacy VRF/l3mdev use case */ + fl4->flowi4_oif = fl4->flowi4_l3mdev ? 0 : oif; + } + fl4->daddr = daddr; fl4->saddr = saddr; fl4->flowi4_tos = tos; diff --git a/include/net/mctp.h b/include/net/mctp.h index d37268fe6825..82800d521c3d 100644 --- a/include/net/mctp.h +++ b/include/net/mctp.h @@ -36,8 +36,6 @@ struct mctp_hdr { #define MCTP_HDR_TAG_SHIFT 0 #define MCTP_HDR_TAG_MASK GENMASK(2, 0) -#define MCTP_HEADER_MAXLEN 4 - #define MCTP_INITIAL_DEFAULT_NET 1 static inline bool mctp_address_unicast(mctp_eid_t eid) diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index 3d83b64471d3..b4af4837d80b 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -75,8 +75,8 @@ struct netns_ipv6 { struct list_head fib6_walkers; rwlock_t fib6_walker_lock; spinlock_t fib6_gc_lock; - unsigned int ip6_rt_gc_expire; - unsigned long ip6_rt_last_gc; + atomic_t ip6_rt_gc_expire; + unsigned long ip6_rt_last_gc; unsigned char flowlabel_has_excl; #ifdef CONFIG_IPV6_MULTIPLE_TABLES bool fib6_has_custom_rules; diff --git a/include/net/secure_seq.h b/include/net/secure_seq.h index d7d2495f83c2..dac91aa38c5a 100644 --- a/include/net/secure_seq.h +++ b/include/net/secure_seq.h @@ -4,8 +4,8 @@ #include <linux/types.h> -u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport); -u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr, +u64 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport); +u64 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr, __be16 dport); u32 secure_tcp_seq(__be32 saddr, __be32 daddr, __be16 sport, __be16 dport); diff --git a/include/net/tc_act/tc_pedit.h b/include/net/tc_act/tc_pedit.h index 748cf87a4d7e..3e02709a1df6 100644 --- a/include/net/tc_act/tc_pedit.h +++ b/include/net/tc_act/tc_pedit.h @@ -14,6 +14,7 @@ struct tcf_pedit { struct tc_action common; unsigned char tcfp_nkeys; unsigned char tcfp_flags; + u32 tcfp_off_max_hint; struct tc_pedit_key *tcfp_keys; struct tcf_pedit_key_ex *tcfp_keys_ex; }; diff --git a/include/net/tcp.h b/include/net/tcp.h index 70ca4a5e330a..cc1295037533 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -480,6 +480,7 @@ int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th, u32 cookie); struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb); struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops, + const struct tcp_request_sock_ops *af_ops, struct sock *sk, struct sk_buff *skb); #ifdef CONFIG_SYN_COOKIES @@ -620,6 +621,7 @@ void tcp_synack_rtt_meas(struct sock *sk, struct request_sock *req); void tcp_reset(struct sock *sk, struct sk_buff *skb); void tcp_skb_mark_lost_uncond_verify(struct tcp_sock *tp, struct sk_buff *skb); void tcp_fin(struct sock *sk); +void tcp_check_space(struct sock *sk); /* tcp_timer.c */ void tcp_init_xmit_timers(struct sock *); @@ -1042,6 +1044,7 @@ struct rate_sample { int losses; /* number of packets marked lost upon ACK */ u32 acked_sacked; /* number of packets newly (S)ACKed upon ACK */ u32 prior_in_flight; /* in flight before this ACK */ + u32 last_end_seq; /* end_seq of most recently ACKed packet */ bool is_app_limited; /* is sample from packet with bubble in pipe? */ bool is_retrans; /* is sample from retransmission? */ bool is_ack_delayed; /* is this (likely) a delayed ACK? */ @@ -1164,6 +1167,11 @@ void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost, bool is_sack_reneg, struct rate_sample *rs); void tcp_rate_check_app_limited(struct sock *sk); +static inline bool tcp_skb_sent_after(u64 t1, u64 t2, u32 seq1, u32 seq2) +{ + return t1 > t2 || (t1 == t2 && after(seq1, seq2)); +} + /* These functions determine how the current flow behaves in respect of SACK * handling. SACK is negotiated with the peer, and therefore it can vary * between different flows. diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 6fb899ff5afc..d2efddce65d4 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1093,6 +1093,18 @@ static inline bool __xfrm_check_nopolicy(struct net *net, struct sk_buff *skb, return false; } +static inline bool __xfrm_check_dev_nopolicy(struct sk_buff *skb, + int dir, unsigned short family) +{ + if (dir != XFRM_POLICY_OUT && family == AF_INET) { + /* same dst may be used for traffic originating from + * devices with different policy settings. + */ + return IPCB(skb)->flags & IPSKB_NOPOLICY; + } + return skb_dst(skb) && (skb_dst(skb)->flags & DST_NOPOLICY); +} + static inline int __xfrm_policy_check2(struct sock *sk, int dir, struct sk_buff *skb, unsigned int family, int reverse) @@ -1104,7 +1116,7 @@ static inline int __xfrm_policy_check2(struct sock *sk, int dir, return __xfrm_policy_check(sk, ndir, skb, family); return __xfrm_check_nopolicy(net, skb, dir) || - (skb_dst(skb) && (skb_dst(skb)->flags & DST_NOPOLICY)) || + __xfrm_check_dev_nopolicy(skb, dir, family) || __xfrm_policy_check(sk, ndir, skb, family); } diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h index 5554ee75e7da..647722e847b4 100644 --- a/include/net/xsk_buff_pool.h +++ b/include/net/xsk_buff_pool.h @@ -97,6 +97,7 @@ int xp_assign_dev(struct xsk_buff_pool *pool, struct net_device *dev, u16 queue_id, u16 flags); int xp_assign_dev_shared(struct xsk_buff_pool *pool, struct xdp_umem *umem, struct net_device *dev, u16 queue_id); +int xp_alloc_tx_descs(struct xsk_buff_pool *pool, struct xdp_sock *xs); void xp_destroy(struct xsk_buff_pool *pool); void xp_get_pool(struct xsk_buff_pool *pool); bool xp_put_pool(struct xsk_buff_pool *pool); diff --git a/include/scsi/libiscsi.h b/include/scsi/libiscsi.h index e76c94697c1b..d0a24779c52d 100644 --- a/include/scsi/libiscsi.h +++ b/include/scsi/libiscsi.h @@ -53,8 +53,10 @@ enum { #define ISID_SIZE 6 -/* Connection suspend "bit" */ -#define ISCSI_SUSPEND_BIT 1 +/* Connection flags */ +#define ISCSI_CONN_FLAG_SUSPEND_TX BIT(0) +#define ISCSI_CONN_FLAG_SUSPEND_RX BIT(1) +#define ISCSI_CONN_FLAG_BOUND BIT(2) #define ISCSI_ITT_MASK 0x1fff #define ISCSI_TOTAL_CMDS_MAX 4096 @@ -211,8 +213,7 @@ struct iscsi_conn { struct list_head cmdqueue; /* data-path cmd queue */ struct list_head requeue; /* tasks needing another run */ struct work_struct xmitwork; /* per-conn. xmit workqueue */ - unsigned long suspend_tx; /* suspend Tx */ - unsigned long suspend_rx; /* suspend Rx */ + unsigned long flags; /* ISCSI_CONN_FLAGs */ /* negotiated params */ unsigned max_recv_dlength; /* initiator_max_recv_dsl*/ diff --git a/include/scsi/scsi_transport_iscsi.h b/include/scsi/scsi_transport_iscsi.h index 38e4a67f5922..9acb8422f680 100644 --- a/include/scsi/scsi_transport_iscsi.h +++ b/include/scsi/scsi_transport_iscsi.h @@ -211,6 +211,8 @@ struct iscsi_cls_conn { struct mutex ep_mutex; struct iscsi_endpoint *ep; + /* Used when accessing flags and queueing work. */ + spinlock_t lock; unsigned long flags; struct work_struct cleanup_work; @@ -295,7 +297,7 @@ extern void iscsi_host_for_each_session(struct Scsi_Host *shost, struct iscsi_endpoint { void *dd_data; /* LLD private data */ struct device dev; - uint64_t id; + int id; struct iscsi_cls_conn *conn; }; diff --git a/include/soc/fsl/caam-blob.h b/include/soc/fsl/caam-blob.h new file mode 100644 index 000000000000..937cac52f36d --- /dev/null +++ b/include/soc/fsl/caam-blob.h @@ -0,0 +1,103 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2020 Pengutronix, Ahmad Fatoum <kernel@pengutronix.de> + */ + +#ifndef __CAAM_BLOB_GEN +#define __CAAM_BLOB_GEN + +#include <linux/types.h> +#include <linux/errno.h> + +#define CAAM_BLOB_KEYMOD_LENGTH 16 +#define CAAM_BLOB_OVERHEAD (32 + 16) +#define CAAM_BLOB_MAX_LEN 4096 + +struct caam_blob_priv; + +/** + * struct caam_blob_info - information for CAAM blobbing + * @input: pointer to input buffer (must be DMAable) + * @input_len: length of @input buffer in bytes. + * @output: pointer to output buffer (must be DMAable) + * @output_len: length of @output buffer in bytes. + * @key_mod: key modifier + * @key_mod_len: length of @key_mod in bytes. + * May not exceed %CAAM_BLOB_KEYMOD_LENGTH + */ +struct caam_blob_info { + void *input; + size_t input_len; + + void *output; + size_t output_len; + + const void *key_mod; + size_t key_mod_len; +}; + +/** + * caam_blob_gen_init - initialize blob generation + * Return: pointer to new &struct caam_blob_priv instance on success + * and ``ERR_PTR(-ENODEV)`` if CAAM has no hardware blobbing support + * or no job ring could be allocated. + */ +struct caam_blob_priv *caam_blob_gen_init(void); + +/** + * caam_blob_gen_exit - free blob generation resources + * @priv: instance returned by caam_blob_gen_init() + */ +void caam_blob_gen_exit(struct caam_blob_priv *priv); + +/** + * caam_process_blob - encapsulate or decapsulate blob + * @priv: instance returned by caam_blob_gen_init() + * @info: pointer to blobbing info describing key, blob and + * key modifier buffers. + * @encap: true for encapsulation, false for decapsulation + * + * Return: %0 and sets ``info->output_len`` on success and a negative + * error code otherwise. + */ +int caam_process_blob(struct caam_blob_priv *priv, + struct caam_blob_info *info, bool encap); + +/** + * caam_encap_blob - encapsulate blob + * @priv: instance returned by caam_blob_gen_init() + * @info: pointer to blobbing info describing input key, + * output blob and key modifier buffers. + * + * Return: %0 and sets ``info->output_len`` on success and + * a negative error code otherwise. + */ +static inline int caam_encap_blob(struct caam_blob_priv *priv, + struct caam_blob_info *info) +{ + if (info->output_len < info->input_len + CAAM_BLOB_OVERHEAD) + return -EINVAL; + + return caam_process_blob(priv, info, true); +} + +/** + * caam_decap_blob - decapsulate blob + * @priv: instance returned by caam_blob_gen_init() + * @info: pointer to blobbing info describing output key, + * input blob and key modifier buffers. + * + * Return: %0 and sets ``info->output_len`` on success and + * a negative error code otherwise. + */ +static inline int caam_decap_blob(struct caam_blob_priv *priv, + struct caam_blob_info *info) +{ + if (info->input_len < CAAM_BLOB_OVERHEAD || + info->output_len < info->input_len - CAAM_BLOB_OVERHEAD) + return -EINVAL; + + return caam_process_blob(priv, info, false); +} + +#endif diff --git a/include/soc/mscc/ocelot_vcap.h b/include/soc/mscc/ocelot_vcap.h index 7b2bf9b1fe69..de26c992f821 100644 --- a/include/soc/mscc/ocelot_vcap.h +++ b/include/soc/mscc/ocelot_vcap.h @@ -681,7 +681,6 @@ struct ocelot_vcap_id { struct ocelot_vcap_filter { struct list_head list; - struct list_head trap_list; enum ocelot_vcap_filter_type type; int block_id; @@ -695,6 +694,7 @@ struct ocelot_vcap_filter { struct ocelot_vcap_stats stats; /* For VCAP IS1 and IS2 */ bool take_ts; + bool is_trap; unsigned long ingress_port_mask; /* For VCAP ES0 */ struct ocelot_vcap_port ingress_port; diff --git a/include/soc/rockchip/pm_domains.h b/include/soc/rockchip/pm_domains.h new file mode 100644 index 000000000000..7dbd941fc937 --- /dev/null +++ b/include/soc/rockchip/pm_domains.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright 2022, The Chromium OS Authors. All rights reserved. + */ + +#ifndef __SOC_ROCKCHIP_PM_DOMAINS_H__ +#define __SOC_ROCKCHIP_PM_DOMAINS_H__ + +#ifdef CONFIG_ROCKCHIP_PM_DOMAINS + +int rockchip_pmu_block(void); +void rockchip_pmu_unblock(void); + +#else /* CONFIG_ROCKCHIP_PM_DOMAINS */ + +static inline int rockchip_pmu_block(void) +{ + return 0; +} + +static inline void rockchip_pmu_unblock(void) { } + +#endif /* CONFIG_ROCKCHIP_PM_DOMAINS */ + +#endif /* __SOC_ROCKCHIP_PM_DOMAINS_H__ */ diff --git a/include/sound/core.h b/include/sound/core.h index b7e9b58d3c78..6d4cc49584c6 100644 --- a/include/sound/core.h +++ b/include/sound/core.h @@ -284,6 +284,7 @@ int snd_card_disconnect(struct snd_card *card); void snd_card_disconnect_sync(struct snd_card *card); int snd_card_free(struct snd_card *card); int snd_card_free_when_closed(struct snd_card *card); +int snd_card_free_on_error(struct device *dev, int ret); void snd_card_set_id(struct snd_card *card, const char *id); int snd_card_register(struct snd_card *card); int snd_card_info_init(void); diff --git a/include/sound/memalloc.h b/include/sound/memalloc.h index 653dfffb3ac8..8d79cebf95f3 100644 --- a/include/sound/memalloc.h +++ b/include/sound/memalloc.h @@ -51,6 +51,11 @@ struct snd_dma_device { #define SNDRV_DMA_TYPE_DEV_SG SNDRV_DMA_TYPE_DEV /* no SG-buf support */ #define SNDRV_DMA_TYPE_DEV_WC_SG SNDRV_DMA_TYPE_DEV_WC #endif +/* fallback types, don't use those directly */ +#ifdef CONFIG_SND_DMA_SGBUF +#define SNDRV_DMA_TYPE_DEV_SG_FALLBACK 10 +#define SNDRV_DMA_TYPE_DEV_WC_SG_FALLBACK 11 +#endif /* * info for buffer allocation diff --git a/include/sound/soc-component.h b/include/sound/soc-component.h index a52080407b98..766dc6f009c0 100644 --- a/include/sound/soc-component.h +++ b/include/sound/soc-component.h @@ -179,6 +179,10 @@ struct snd_soc_component_driver { struct snd_pcm_hw_params *params); bool use_dai_pcm_id; /* use DAI link PCM ID as PCM device number */ int be_pcm_base; /* base device ID for all BE PCMs */ + +#ifdef CONFIG_DEBUG_FS + const char *debugfs_prefix; +#endif }; struct snd_soc_component { diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h index 675f3a1fe613..773963a1e0b5 100644 --- a/include/target/target_core_backend.h +++ b/include/target/target_core_backend.h @@ -14,7 +14,7 @@ #define TRANSPORT_FLAG_PASSTHROUGH_ALUA 0x2 #define TRANSPORT_FLAG_PASSTHROUGH_PGR 0x4 -struct request_queue; +struct block_device; struct scatterlist; struct target_backend_ops { @@ -117,7 +117,7 @@ sense_reason_t passthrough_parse_cdb(struct se_cmd *cmd, bool target_sense_desc_format(struct se_device *dev); sector_t target_to_linux_sector(struct se_device *dev, sector_t lb); bool target_configure_unmap_from_queue(struct se_dev_attrib *attrib, - struct request_queue *q); + struct block_device *bdev); static inline bool target_dev_configured(struct se_device *se_dev) { diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h index f068ff30d654..290f07eb050a 100644 --- a/include/trace/events/btrfs.h +++ b/include/trace/events/btrfs.h @@ -24,7 +24,7 @@ struct btrfs_free_cluster; struct map_lookup; struct extent_buffer; struct btrfs_work; -struct __btrfs_workqueue; +struct btrfs_workqueue; struct btrfs_qgroup_extent_record; struct btrfs_qgroup; struct extent_io_tree; @@ -1457,42 +1457,36 @@ DEFINE_EVENT(btrfs__work, btrfs_ordered_sched, TP_ARGS(work) ); -DECLARE_EVENT_CLASS(btrfs__workqueue, +DECLARE_EVENT_CLASS(btrfs_workqueue, - TP_PROTO(const struct __btrfs_workqueue *wq, - const char *name, int high), + TP_PROTO(const struct btrfs_workqueue *wq, const char *name), - TP_ARGS(wq, name, high), + TP_ARGS(wq, name), TP_STRUCT__entry_btrfs( __field( const void *, wq ) __string( name, name ) - __field( int , high ) ), TP_fast_assign_btrfs(btrfs_workqueue_owner(wq), __entry->wq = wq; __assign_str(name, name); - __entry->high = high; ), - TP_printk_btrfs("name=%s%s wq=%p", __get_str(name), - __print_flags(__entry->high, "", - {(WQ_HIGHPRI), "-high"}), + TP_printk_btrfs("name=%s wq=%p", __get_str(name), __entry->wq) ); -DEFINE_EVENT(btrfs__workqueue, btrfs_workqueue_alloc, +DEFINE_EVENT(btrfs_workqueue, btrfs_workqueue_alloc, - TP_PROTO(const struct __btrfs_workqueue *wq, - const char *name, int high), + TP_PROTO(const struct btrfs_workqueue *wq, const char *name), - TP_ARGS(wq, name, high) + TP_ARGS(wq, name) ); -DECLARE_EVENT_CLASS(btrfs__workqueue_done, +DECLARE_EVENT_CLASS(btrfs_workqueue_done, - TP_PROTO(const struct __btrfs_workqueue *wq), + TP_PROTO(const struct btrfs_workqueue *wq), TP_ARGS(wq), @@ -1507,9 +1501,9 @@ DECLARE_EVENT_CLASS(btrfs__workqueue_done, TP_printk_btrfs("wq=%p", __entry->wq) ); -DEFINE_EVENT(btrfs__workqueue_done, btrfs_workqueue_destroy, +DEFINE_EVENT(btrfs_workqueue_done, btrfs_workqueue_destroy, - TP_PROTO(const struct __btrfs_workqueue *wq), + TP_PROTO(const struct btrfs_workqueue *wq), TP_ARGS(wq) ); diff --git a/include/trace/events/cachefiles.h b/include/trace/events/cachefiles.h index 311c14a20e70..d8d4d73fe7b6 100644 --- a/include/trace/events/cachefiles.h +++ b/include/trace/events/cachefiles.h @@ -31,6 +31,8 @@ enum cachefiles_obj_ref_trace { cachefiles_obj_see_lookup_failed, cachefiles_obj_see_withdraw_cookie, cachefiles_obj_see_withdrawal, + cachefiles_obj_get_ondemand_fd, + cachefiles_obj_put_ondemand_fd, }; enum fscache_why_object_killed { @@ -671,6 +673,180 @@ TRACE_EVENT(cachefiles_io_error, __entry->error) ); +TRACE_EVENT(cachefiles_ondemand_open, + TP_PROTO(struct cachefiles_object *obj, struct cachefiles_msg *msg, + struct cachefiles_open *load), + + TP_ARGS(obj, msg, load), + + TP_STRUCT__entry( + __field(unsigned int, obj ) + __field(unsigned int, msg_id ) + __field(unsigned int, object_id ) + __field(unsigned int, fd ) + __field(unsigned int, flags ) + ), + + TP_fast_assign( + __entry->obj = obj ? obj->debug_id : 0; + __entry->msg_id = msg->msg_id; + __entry->object_id = msg->object_id; + __entry->fd = load->fd; + __entry->flags = load->flags; + ), + + TP_printk("o=%08x mid=%x oid=%x fd=%d f=%x", + __entry->obj, + __entry->msg_id, + __entry->object_id, + __entry->fd, + __entry->flags) + ); + +TRACE_EVENT(cachefiles_ondemand_copen, + TP_PROTO(struct cachefiles_object *obj, unsigned int msg_id, + long len), + + TP_ARGS(obj, msg_id, len), + + TP_STRUCT__entry( + __field(unsigned int, obj ) + __field(unsigned int, msg_id ) + __field(long, len ) + ), + + TP_fast_assign( + __entry->obj = obj ? obj->debug_id : 0; + __entry->msg_id = msg_id; + __entry->len = len; + ), + + TP_printk("o=%08x mid=%x l=%lx", + __entry->obj, + __entry->msg_id, + __entry->len) + ); + +TRACE_EVENT(cachefiles_ondemand_close, + TP_PROTO(struct cachefiles_object *obj, struct cachefiles_msg *msg), + + TP_ARGS(obj, msg), + + TP_STRUCT__entry( + __field(unsigned int, obj ) + __field(unsigned int, msg_id ) + __field(unsigned int, object_id ) + ), + + TP_fast_assign( + __entry->obj = obj ? obj->debug_id : 0; + __entry->msg_id = msg->msg_id; + __entry->object_id = msg->object_id; + ), + + TP_printk("o=%08x mid=%x oid=%x", + __entry->obj, + __entry->msg_id, + __entry->object_id) + ); + +TRACE_EVENT(cachefiles_ondemand_read, + TP_PROTO(struct cachefiles_object *obj, struct cachefiles_msg *msg, + struct cachefiles_read *load), + + TP_ARGS(obj, msg, load), + + TP_STRUCT__entry( + __field(unsigned int, obj ) + __field(unsigned int, msg_id ) + __field(unsigned int, object_id ) + __field(loff_t, start ) + __field(size_t, len ) + ), + + TP_fast_assign( + __entry->obj = obj ? obj->debug_id : 0; + __entry->msg_id = msg->msg_id; + __entry->object_id = msg->object_id; + __entry->start = load->off; + __entry->len = load->len; + ), + + TP_printk("o=%08x mid=%x oid=%x s=%llx l=%zx", + __entry->obj, + __entry->msg_id, + __entry->object_id, + __entry->start, + __entry->len) + ); + +TRACE_EVENT(cachefiles_ondemand_cread, + TP_PROTO(struct cachefiles_object *obj, unsigned int msg_id), + + TP_ARGS(obj, msg_id), + + TP_STRUCT__entry( + __field(unsigned int, obj ) + __field(unsigned int, msg_id ) + ), + + TP_fast_assign( + __entry->obj = obj ? obj->debug_id : 0; + __entry->msg_id = msg_id; + ), + + TP_printk("o=%08x mid=%x", + __entry->obj, + __entry->msg_id) + ); + +TRACE_EVENT(cachefiles_ondemand_fd_write, + TP_PROTO(struct cachefiles_object *obj, struct inode *backer, + loff_t start, size_t len), + + TP_ARGS(obj, backer, start, len), + + TP_STRUCT__entry( + __field(unsigned int, obj ) + __field(unsigned int, backer ) + __field(loff_t, start ) + __field(size_t, len ) + ), + + TP_fast_assign( + __entry->obj = obj ? obj->debug_id : 0; + __entry->backer = backer->i_ino; + __entry->start = start; + __entry->len = len; + ), + + TP_printk("o=%08x iB=%x s=%llx l=%zx", + __entry->obj, + __entry->backer, + __entry->start, + __entry->len) + ); + +TRACE_EVENT(cachefiles_ondemand_fd_release, + TP_PROTO(struct cachefiles_object *obj, int object_id), + + TP_ARGS(obj, object_id), + + TP_STRUCT__entry( + __field(unsigned int, obj ) + __field(unsigned int, object_id ) + ), + + TP_fast_assign( + __entry->obj = obj ? obj->debug_id : 0; + __entry->object_id = object_id; + ), + + TP_printk("o=%08x oid=%x", + __entry->obj, + __entry->object_id) + ); + #endif /* _TRACE_CACHEFILES_H */ /* This part must be outside protection */ diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index d06ffffad434..229e8fae66a3 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -335,17 +335,15 @@ TRACE_EVENT(ext4_begin_ordered_truncate, DECLARE_EVENT_CLASS(ext4__write_begin, - TP_PROTO(struct inode *inode, loff_t pos, unsigned int len, - unsigned int flags), + TP_PROTO(struct inode *inode, loff_t pos, unsigned int len), - TP_ARGS(inode, pos, len, flags), + TP_ARGS(inode, pos, len), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( loff_t, pos ) __field( unsigned int, len ) - __field( unsigned int, flags ) ), TP_fast_assign( @@ -353,29 +351,26 @@ DECLARE_EVENT_CLASS(ext4__write_begin, __entry->ino = inode->i_ino; __entry->pos = pos; __entry->len = len; - __entry->flags = flags; ), - TP_printk("dev %d,%d ino %lu pos %lld len %u flags %u", + TP_printk("dev %d,%d ino %lu pos %lld len %u", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, - __entry->pos, __entry->len, __entry->flags) + __entry->pos, __entry->len) ); DEFINE_EVENT(ext4__write_begin, ext4_write_begin, - TP_PROTO(struct inode *inode, loff_t pos, unsigned int len, - unsigned int flags), + TP_PROTO(struct inode *inode, loff_t pos, unsigned int len), - TP_ARGS(inode, pos, len, flags) + TP_ARGS(inode, pos, len) ); DEFINE_EVENT(ext4__write_begin, ext4_da_write_begin, - TP_PROTO(struct inode *inode, loff_t pos, unsigned int len, - unsigned int flags), + TP_PROTO(struct inode *inode, loff_t pos, unsigned int len), - TP_ARGS(inode, pos, len, flags) + TP_ARGS(inode, pos, len) ); DECLARE_EVENT_CLASS(ext4__write_end, diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h index 1779e133cea0..bea654a85e6b 100644 --- a/include/trace/events/f2fs.h +++ b/include/trace/events/f2fs.h @@ -1159,17 +1159,15 @@ DEFINE_EVENT_CONDITION(f2fs__bio, f2fs_submit_write_bio, TRACE_EVENT(f2fs_write_begin, - TP_PROTO(struct inode *inode, loff_t pos, unsigned int len, - unsigned int flags), + TP_PROTO(struct inode *inode, loff_t pos, unsigned int len), - TP_ARGS(inode, pos, len, flags), + TP_ARGS(inode, pos, len), TP_STRUCT__entry( __field(dev_t, dev) __field(ino_t, ino) __field(loff_t, pos) __field(unsigned int, len) - __field(unsigned int, flags) ), TP_fast_assign( @@ -1177,14 +1175,12 @@ TRACE_EVENT(f2fs_write_begin, __entry->ino = inode->i_ino; __entry->pos = pos; __entry->len = len; - __entry->flags = flags; ), - TP_printk("dev = (%d,%d), ino = %lu, pos = %llu, len = %u, flags = %u", + TP_printk("dev = (%d,%d), ino = %lu, pos = %llu, len = %u", show_dev_ino(__entry), (unsigned long long)__entry->pos, - __entry->len, - __entry->flags) + __entry->len) ); TRACE_EVENT(f2fs_write_end, diff --git a/include/trace/events/intel_ifs.h b/include/trace/events/intel_ifs.h new file mode 100644 index 000000000000..d7353024016c --- /dev/null +++ b/include/trace/events/intel_ifs.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM intel_ifs + +#if !defined(_TRACE_IFS_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_IFS_H + +#include <linux/ktime.h> +#include <linux/tracepoint.h> + +TRACE_EVENT(ifs_status, + + TP_PROTO(int cpu, union ifs_scan activate, union ifs_status status), + + TP_ARGS(cpu, activate, status), + + TP_STRUCT__entry( + __field( u64, status ) + __field( int, cpu ) + __field( u8, start ) + __field( u8, stop ) + ), + + TP_fast_assign( + __entry->cpu = cpu; + __entry->start = activate.start; + __entry->stop = activate.stop; + __entry->status = status.data; + ), + + TP_printk("cpu: %d, start: %.2x, stop: %.2x, status: %llx", + __entry->cpu, + __entry->start, + __entry->stop, + __entry->status) +); + +#endif /* _TRACE_IFS_H */ + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/include/trace/events/io_uring.h b/include/trace/events/io_uring.h index cddf5b6fbeb4..66fcc5a1a5b1 100644 --- a/include/trace/events/io_uring.h +++ b/include/trace/events/io_uring.h @@ -7,6 +7,7 @@ #include <linux/tracepoint.h> #include <uapi/linux/io_uring.h> +#include <linux/io_uring.h> struct io_wq_work; @@ -147,7 +148,7 @@ TRACE_EVENT(io_uring_queue_async_work, TP_PROTO(void *ctx, void * req, unsigned long long user_data, u8 opcode, unsigned int flags, struct io_wq_work *work, int rw), - TP_ARGS(ctx, req, user_data, flags, opcode, work, rw), + TP_ARGS(ctx, req, user_data, opcode, flags, work, rw), TP_STRUCT__entry ( __field( void *, ctx ) @@ -169,8 +170,9 @@ TRACE_EVENT(io_uring_queue_async_work, __entry->rw = rw; ), - TP_printk("ring %p, request %p, user_data 0x%llx, opcode %d, flags 0x%x, %s queue, work %p", - __entry->ctx, __entry->req, __entry->user_data, __entry->opcode, + TP_printk("ring %p, request %p, user_data 0x%llx, opcode %s, flags 0x%x, %s queue, work %p", + __entry->ctx, __entry->req, __entry->user_data, + io_uring_get_opcode(__entry->opcode), __entry->flags, __entry->rw ? "hashed" : "normal", __entry->work) ); @@ -205,8 +207,9 @@ TRACE_EVENT(io_uring_defer, __entry->opcode = opcode; ), - TP_printk("ring %p, request %p, user_data 0x%llx, opcode %d", - __entry->ctx, __entry->req, __entry->data, __entry->opcode) + TP_printk("ring %p, request %p, user_data 0x%llx, opcode %s", + __entry->ctx, __entry->req, __entry->data, + io_uring_get_opcode(__entry->opcode)) ); /** @@ -305,9 +308,9 @@ TRACE_EVENT(io_uring_fail_link, __entry->link = link; ), - TP_printk("ring %p, request %p, user_data 0x%llx, opcode %d, link %p", - __entry->ctx, __entry->req, __entry->user_data, __entry->opcode, - __entry->link) + TP_printk("ring %p, request %p, user_data 0x%llx, opcode %s, link %p", + __entry->ctx, __entry->req, __entry->user_data, + io_uring_get_opcode(__entry->opcode), __entry->link) ); /** @@ -318,13 +321,16 @@ TRACE_EVENT(io_uring_fail_link, * @user_data: user data associated with the request * @res: result of the request * @cflags: completion flags + * @extra1: extra 64-bit data for CQE32 + * @extra2: extra 64-bit data for CQE32 * */ TRACE_EVENT(io_uring_complete, - TP_PROTO(void *ctx, void *req, u64 user_data, int res, unsigned cflags), + TP_PROTO(void *ctx, void *req, u64 user_data, int res, unsigned cflags, + u64 extra1, u64 extra2), - TP_ARGS(ctx, req, user_data, res, cflags), + TP_ARGS(ctx, req, user_data, res, cflags, extra1, extra2), TP_STRUCT__entry ( __field( void *, ctx ) @@ -332,6 +338,8 @@ TRACE_EVENT(io_uring_complete, __field( u64, user_data ) __field( int, res ) __field( unsigned, cflags ) + __field( u64, extra1 ) + __field( u64, extra2 ) ), TP_fast_assign( @@ -340,12 +348,17 @@ TRACE_EVENT(io_uring_complete, __entry->user_data = user_data; __entry->res = res; __entry->cflags = cflags; + __entry->extra1 = extra1; + __entry->extra2 = extra2; ), - TP_printk("ring %p, req %p, user_data 0x%llx, result %d, cflags 0x%x", + TP_printk("ring %p, req %p, user_data 0x%llx, result %d, cflags 0x%x " + "extra1 %llu extra2 %llu ", __entry->ctx, __entry->req, __entry->user_data, - __entry->res, __entry->cflags) + __entry->res, __entry->cflags, + (unsigned long long) __entry->extra1, + (unsigned long long) __entry->extra2) ); /** @@ -389,9 +402,9 @@ TRACE_EVENT(io_uring_submit_sqe, __entry->sq_thread = sq_thread; ), - TP_printk("ring %p, req %p, user_data 0x%llx, opcode %d, flags 0x%x, " + TP_printk("ring %p, req %p, user_data 0x%llx, opcode %s, flags 0x%x, " "non block %d, sq_thread %d", __entry->ctx, __entry->req, - __entry->user_data, __entry->opcode, + __entry->user_data, io_uring_get_opcode(__entry->opcode), __entry->flags, __entry->force_nonblock, __entry->sq_thread) ); @@ -433,8 +446,9 @@ TRACE_EVENT(io_uring_poll_arm, __entry->events = events; ), - TP_printk("ring %p, req %p, user_data 0x%llx, opcode %d, mask 0x%x, events 0x%x", - __entry->ctx, __entry->req, __entry->user_data, __entry->opcode, + TP_printk("ring %p, req %p, user_data 0x%llx, opcode %s, mask 0x%x, events 0x%x", + __entry->ctx, __entry->req, __entry->user_data, + io_uring_get_opcode(__entry->opcode), __entry->mask, __entry->events) ); @@ -470,8 +484,9 @@ TRACE_EVENT(io_uring_task_add, __entry->mask = mask; ), - TP_printk("ring %p, req %p, user_data 0x%llx, opcode %d, mask %x", - __entry->ctx, __entry->req, __entry->user_data, __entry->opcode, + TP_printk("ring %p, req %p, user_data 0x%llx, opcode %s, mask %x", + __entry->ctx, __entry->req, __entry->user_data, + io_uring_get_opcode(__entry->opcode), __entry->mask) ); @@ -506,7 +521,7 @@ TRACE_EVENT(io_uring_req_failed, __field( u16, personality ) __field( u32, file_index ) __field( u64, pad1 ) - __field( u64, pad2 ) + __field( u64, addr3 ) __field( int, error ) ), @@ -520,27 +535,69 @@ TRACE_EVENT(io_uring_req_failed, __entry->off = sqe->off; __entry->addr = sqe->addr; __entry->len = sqe->len; - __entry->op_flags = sqe->rw_flags; + __entry->op_flags = sqe->poll32_events; __entry->buf_index = sqe->buf_index; __entry->personality = sqe->personality; __entry->file_index = sqe->file_index; __entry->pad1 = sqe->__pad2[0]; - __entry->pad2 = sqe->__pad2[1]; + __entry->addr3 = sqe->addr3; __entry->error = error; ), TP_printk("ring %p, req %p, user_data 0x%llx, " - "op %d, flags 0x%x, prio=%d, off=%llu, addr=%llu, " + "opcode %s, flags 0x%x, prio=%d, off=%llu, addr=%llu, " "len=%u, rw_flags=0x%x, buf_index=%d, " - "personality=%d, file_index=%d, pad=0x%llx/%llx, error=%d", + "personality=%d, file_index=%d, pad=0x%llx, addr3=%llx, " + "error=%d", __entry->ctx, __entry->req, __entry->user_data, - __entry->opcode, __entry->flags, __entry->ioprio, + io_uring_get_opcode(__entry->opcode), + __entry->flags, __entry->ioprio, (unsigned long long)__entry->off, (unsigned long long) __entry->addr, __entry->len, __entry->op_flags, __entry->buf_index, __entry->personality, __entry->file_index, (unsigned long long) __entry->pad1, - (unsigned long long) __entry->pad2, __entry->error) + (unsigned long long) __entry->addr3, __entry->error) +); + + +/* + * io_uring_cqe_overflow - a CQE overflowed + * + * @ctx: pointer to a ring context structure + * @user_data: user data associated with the request + * @res: CQE result + * @cflags: CQE flags + * @ocqe: pointer to the overflow cqe (if available) + * + */ +TRACE_EVENT(io_uring_cqe_overflow, + + TP_PROTO(void *ctx, unsigned long long user_data, s32 res, u32 cflags, + void *ocqe), + + TP_ARGS(ctx, user_data, res, cflags, ocqe), + + TP_STRUCT__entry ( + __field( void *, ctx ) + __field( unsigned long long, user_data ) + __field( s32, res ) + __field( u32, cflags ) + __field( void *, ocqe ) + ), + + TP_fast_assign( + __entry->ctx = ctx; + __entry->user_data = user_data; + __entry->res = res; + __entry->cflags = cflags; + __entry->ocqe = ocqe; + ), + + TP_printk("ring %p, user_data 0x%llx, res %d, flags %x, " + "overflow_cqe %p", + __entry->ctx, __entry->user_data, __entry->res, + __entry->cflags, __entry->ocqe) ); #endif /* _TRACE_IO_URING_H */ diff --git a/include/trace/events/lock.h b/include/trace/events/lock.h index d7512129a324..9ebd081e057e 100644 --- a/include/trace/events/lock.h +++ b/include/trace/events/lock.h @@ -5,11 +5,22 @@ #if !defined(_TRACE_LOCK_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_LOCK_H -#include <linux/lockdep.h> +#include <linux/sched.h> #include <linux/tracepoint.h> +/* flags for lock:contention_begin */ +#define LCB_F_SPIN (1U << 0) +#define LCB_F_READ (1U << 1) +#define LCB_F_WRITE (1U << 2) +#define LCB_F_RT (1U << 3) +#define LCB_F_PERCPU (1U << 4) +#define LCB_F_MUTEX (1U << 5) + + #ifdef CONFIG_LOCKDEP +#include <linux/lockdep.h> + TRACE_EVENT(lock_acquire, TP_PROTO(struct lockdep_map *lock, unsigned int subclass, @@ -78,8 +89,54 @@ DEFINE_EVENT(lock, lock_acquired, TP_ARGS(lock, ip) ); -#endif -#endif +#endif /* CONFIG_LOCK_STAT */ +#endif /* CONFIG_LOCKDEP */ + +TRACE_EVENT(contention_begin, + + TP_PROTO(void *lock, unsigned int flags), + + TP_ARGS(lock, flags), + + TP_STRUCT__entry( + __field(void *, lock_addr) + __field(unsigned int, flags) + ), + + TP_fast_assign( + __entry->lock_addr = lock; + __entry->flags = flags; + ), + + TP_printk("%p (flags=%s)", __entry->lock_addr, + __print_flags(__entry->flags, "|", + { LCB_F_SPIN, "SPIN" }, + { LCB_F_READ, "READ" }, + { LCB_F_WRITE, "WRITE" }, + { LCB_F_RT, "RT" }, + { LCB_F_PERCPU, "PERCPU" }, + { LCB_F_MUTEX, "MUTEX" } + )) +); + +TRACE_EVENT(contention_end, + + TP_PROTO(void *lock, int ret), + + TP_ARGS(lock, ret), + + TP_STRUCT__entry( + __field(void *, lock_addr) + __field(int, ret) + ), + + TP_fast_assign( + __entry->lock_addr = lock; + __entry->ret = ret; + ), + + TP_printk("%p (ret=%d)", __entry->lock_addr, __entry->ret) +); #endif /* _TRACE_LOCK_H */ diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h index 65e786756321..fbb99a61f714 100644 --- a/include/trace/events/sched.h +++ b/include/trace/events/sched.h @@ -222,11 +222,11 @@ static inline long __trace_sched_switch_state(bool preempt, TRACE_EVENT(sched_switch, TP_PROTO(bool preempt, - unsigned int prev_state, struct task_struct *prev, - struct task_struct *next), + struct task_struct *next, + unsigned int prev_state), - TP_ARGS(preempt, prev_state, prev, next), + TP_ARGS(preempt, prev, next, prev_state), TP_STRUCT__entry( __array( char, prev_comm, TASK_COMM_LEN ) diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index 0f34f13ebd55..3995c58a1c51 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -1004,7 +1004,6 @@ DEFINE_RPC_XPRT_LIFETIME_EVENT(connect); DEFINE_RPC_XPRT_LIFETIME_EVENT(disconnect_auto); DEFINE_RPC_XPRT_LIFETIME_EVENT(disconnect_done); DEFINE_RPC_XPRT_LIFETIME_EVENT(disconnect_force); -DEFINE_RPC_XPRT_LIFETIME_EVENT(disconnect_cleanup); DEFINE_RPC_XPRT_LIFETIME_EVENT(destroy); DECLARE_EVENT_CLASS(rpc_xprt_event, @@ -2016,17 +2015,18 @@ DECLARE_EVENT_CLASS(svc_deferred_event, TP_STRUCT__entry( __field(const void *, dr) __field(u32, xid) - __string(addr, dr->xprt->xpt_remotebuf) + __array(__u8, addr, INET6_ADDRSTRLEN + 10) ), TP_fast_assign( __entry->dr = dr; __entry->xid = be32_to_cpu(*(__be32 *)(dr->args + (dr->xprt_hlen>>2))); - __assign_str(addr, dr->xprt->xpt_remotebuf); + snprintf(__entry->addr, sizeof(__entry->addr) - 1, + "%pISpc", (struct sockaddr *)&dr->addr); ), - TP_printk("addr=%s dr=%p xid=0x%08x", __get_str(addr), __entry->dr, + TP_printk("addr=%s dr=%p xid=0x%08x", __entry->addr, __entry->dr, __entry->xid) ); diff --git a/include/trace/events/timer.h b/include/trace/events/timer.h index 6ad031c71be7..2e713a7d9aa3 100644 --- a/include/trace/events/timer.h +++ b/include/trace/events/timer.h @@ -48,6 +48,7 @@ DEFINE_EVENT(timer_class, timer_init, * timer_start - called when the timer is started * @timer: pointer to struct timer_list * @expires: the timers expiry time + * @flags: the timers flags */ TRACE_EVENT(timer_start, @@ -84,6 +85,7 @@ TRACE_EVENT(timer_start, /** * timer_expire_entry - called immediately before the timer callback * @timer: pointer to struct timer_list + * @baseclk: value of timer_base::clk when timer expires * * Allows to determine the timer latency. */ @@ -190,7 +192,8 @@ TRACE_EVENT(hrtimer_init, /** * hrtimer_start - called when the hrtimer is started - * @hrtimer: pointer to struct hrtimer + * @hrtimer: pointer to struct hrtimer + * @mode: the hrtimers mode */ TRACE_EVENT(hrtimer_start, diff --git a/include/uapi/asm-generic/siginfo.h b/include/uapi/asm-generic/siginfo.h index 3ba180f550d7..ffbe4cec9f32 100644 --- a/include/uapi/asm-generic/siginfo.h +++ b/include/uapi/asm-generic/siginfo.h @@ -99,6 +99,7 @@ union __sifields { struct { unsigned long _data; __u32 _type; + __u32 _flags; } _perf; }; } _sigfault; @@ -164,6 +165,7 @@ typedef struct siginfo { #define si_pkey _sifields._sigfault._addr_pkey._pkey #define si_perf_data _sifields._sigfault._perf._data #define si_perf_type _sifields._sigfault._perf._type +#define si_perf_flags _sifields._sigfault._perf._flags #define si_band _sifields._sigpoll._band #define si_fd _sifields._sigpoll._fd #define si_call_addr _sifields._sigsys._call_addr @@ -271,6 +273,11 @@ typedef struct siginfo { */ /* + * Flags for si_perf_flags if SIGTRAP si_code is TRAP_PERF. + */ +#define TRAP_PERF_FLAG_ASYNC (1u << 0) + +/* * SIGCHLD si_codes */ #define CLD_EXITED 1 /* child has exited */ diff --git a/include/uapi/linux/btrfs_tree.h b/include/uapi/linux/btrfs_tree.h index b069752a8ecf..d4117152d907 100644 --- a/include/uapi/linux/btrfs_tree.h +++ b/include/uapi/linux/btrfs_tree.h @@ -880,19 +880,6 @@ struct btrfs_dev_replace_item { #define BTRFS_BLOCK_GROUP_RESERVED (BTRFS_AVAIL_ALLOC_BIT_SINGLE | \ BTRFS_SPACE_INFO_GLOBAL_RSV) -enum btrfs_raid_types { - BTRFS_RAID_RAID10, - BTRFS_RAID_RAID1, - BTRFS_RAID_DUP, - BTRFS_RAID_RAID0, - BTRFS_RAID_SINGLE, - BTRFS_RAID_RAID5, - BTRFS_RAID_RAID6, - BTRFS_RAID_RAID1C3, - BTRFS_RAID_RAID1C4, - BTRFS_NR_RAID_TYPES -}; - #define BTRFS_BLOCK_GROUP_TYPE_MASK (BTRFS_BLOCK_GROUP_DATA | \ BTRFS_BLOCK_GROUP_SYSTEM | \ BTRFS_BLOCK_GROUP_METADATA) diff --git a/include/uapi/linux/cachefiles.h b/include/uapi/linux/cachefiles.h new file mode 100644 index 000000000000..78caa73e5343 --- /dev/null +++ b/include/uapi/linux/cachefiles.h @@ -0,0 +1,68 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _LINUX_CACHEFILES_H +#define _LINUX_CACHEFILES_H + +#include <linux/types.h> +#include <linux/ioctl.h> + +/* + * Fscache ensures that the maximum length of cookie key is 255. The volume key + * is controlled by netfs, and generally no bigger than 255. + */ +#define CACHEFILES_MSG_MAX_SIZE 1024 + +enum cachefiles_opcode { + CACHEFILES_OP_OPEN, + CACHEFILES_OP_CLOSE, + CACHEFILES_OP_READ, +}; + +/* + * Message Header + * + * @msg_id a unique ID identifying this message + * @opcode message type, CACHEFILE_OP_* + * @len message length, including message header and following data + * @object_id a unique ID identifying a cache file + * @data message type specific payload + */ +struct cachefiles_msg { + __u32 msg_id; + __u32 opcode; + __u32 len; + __u32 object_id; + __u8 data[]; +}; + +/* + * @data contains the volume_key followed directly by the cookie_key. volume_key + * is a NUL-terminated string; @volume_key_size indicates the size of the volume + * key in bytes. cookie_key is binary data, which is netfs specific; + * @cookie_key_size indicates the size of the cookie key in bytes. + * + * @fd identifies an anon_fd referring to the cache file. + */ +struct cachefiles_open { + __u32 volume_key_size; + __u32 cookie_key_size; + __u32 fd; + __u32 flags; + __u8 data[]; +}; + +/* + * @off indicates the starting offset of the requested file range + * @len indicates the length of the requested file range + */ +struct cachefiles_read { + __u64 off; + __u64 len; +}; + +/* + * Reply for READ request + * @arg for this ioctl is the @id field of READ request. + */ +#define CACHEFILES_IOC_READ_COMPLETE _IOW(0x98, 1, int) + +#endif diff --git a/include/uapi/linux/cdrom.h b/include/uapi/linux/cdrom.h index 804ff8d98f71..011e594e4a0d 100644 --- a/include/uapi/linux/cdrom.h +++ b/include/uapi/linux/cdrom.h @@ -103,7 +103,7 @@ #define CDROMREADALL 0x5318 /* read all 2646 bytes */ /* - * These ioctls are (now) only in ide-cd.c for controlling + * These ioctls were only in (now removed) ide-cd.c for controlling * drive spindown time. They should be implemented in the * Uniform driver, via generic packet commands, GPCMD_MODE_SELECT_10, * GPCMD_MODE_SENSE_10 and the GPMODE_POWER_PAGE... diff --git a/include/uapi/linux/cec.h b/include/uapi/linux/cec.h index de936f5e446d..1d48da926216 100644 --- a/include/uapi/linux/cec.h +++ b/include/uapi/linux/cec.h @@ -142,6 +142,26 @@ static inline void cec_msg_set_reply_to(struct cec_msg *msg, msg->reply = msg->timeout = 0; } +/** + * cec_msg_recv_is_tx_result - return true if this message contains the + * result of an earlier non-blocking transmit + * @msg: the message structure from CEC_RECEIVE + */ +static inline int cec_msg_recv_is_tx_result(const struct cec_msg *msg) +{ + return msg->sequence && msg->tx_status && !msg->rx_status; +} + +/** + * cec_msg_recv_is_rx_result - return true if this message contains the + * reply of an earlier non-blocking transmit + * @msg: the message structure from CEC_RECEIVE + */ +static inline int cec_msg_recv_is_rx_result(const struct cec_msg *msg) +{ + return msg->sequence && !msg->tx_status && msg->rx_status; +} + /* cec_msg flags field */ #define CEC_MSG_FL_REPLY_TO_FOLLOWERS (1 << 0) #define CEC_MSG_FL_RAW (1 << 1) diff --git a/include/uapi/linux/dma-buf.h b/include/uapi/linux/dma-buf.h index 8e4a2ca0bcbf..b1523cb8ab30 100644 --- a/include/uapi/linux/dma-buf.h +++ b/include/uapi/linux/dma-buf.h @@ -92,7 +92,7 @@ struct dma_buf_sync { * between them in actual uapi, they're just different numbers. */ #define DMA_BUF_SET_NAME _IOW(DMA_BUF_BASE, 1, const char *) -#define DMA_BUF_SET_NAME_A _IOW(DMA_BUF_BASE, 1, u32) -#define DMA_BUF_SET_NAME_B _IOW(DMA_BUF_BASE, 1, u64) +#define DMA_BUF_SET_NAME_A _IOW(DMA_BUF_BASE, 1, __u32) +#define DMA_BUF_SET_NAME_B _IOW(DMA_BUF_BASE, 1, __u64) #endif diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index 787c657bfae8..429bec8dd70a 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -42,7 +42,7 @@ typedef __s64 Elf64_Sxword; /* ARM MTE memory tag segment type */ -#define PT_ARM_MEMTAG_MTE (PT_LOPROC + 0x1) +#define PT_AARCH64_MEMTAG_MTE (PT_LOPROC + 0x2) /* * Extended Numbering @@ -431,6 +431,8 @@ typedef struct elf64_shdr { #define NT_ARM_PACG_KEYS 0x408 /* ARM pointer authentication generic key */ #define NT_ARM_TAGGED_ADDR_CTRL 0x409 /* arm64 tagged address control (prctl()) */ #define NT_ARM_PAC_ENABLED_KEYS 0x40a /* arm64 ptr auth enabled keys (prctl()) */ +#define NT_ARM_SSVE 0x40b /* ARM Streaming SVE registers */ +#define NT_ARM_ZA 0x40c /* ARM SME ZA registers */ #define NT_ARC_V2 0x600 /* ARCv2 accumulator/extra registers */ #define NT_VMCOREDD 0x700 /* Vmcore Device Dump Note */ #define NT_MIPS_DSP 0x800 /* MIPS DSP ASE registers */ diff --git a/include/uapi/linux/fb.h b/include/uapi/linux/fb.h index 4c14e8be7267..3a49913d006c 100644 --- a/include/uapi/linux/fb.h +++ b/include/uapi/linux/fb.h @@ -182,7 +182,7 @@ struct fb_fix_screeninfo { * * For pseudocolor: offset and length should be the same for all color * components. Offset specifies the position of the least significant bit - * of the pallette index in a pixel value. Length indicates the number + * of the palette index in a pixel value. Length indicates the number * of available palette entries (i.e. # of entries = 1 << length). */ struct fb_bitfield { diff --git a/include/uapi/linux/input-event-codes.h b/include/uapi/linux/input-event-codes.h index 7989d9483ea7..dff8e7f17074 100644 --- a/include/uapi/linux/input-event-codes.h +++ b/include/uapi/linux/input-event-codes.h @@ -662,6 +662,27 @@ /* Select an area of screen to be copied */ #define KEY_SELECTIVE_SCREENSHOT 0x27a +/* Move the focus to the next or previous user controllable element within a UI container */ +#define KEY_NEXT_ELEMENT 0x27b +#define KEY_PREVIOUS_ELEMENT 0x27c + +/* Toggle Autopilot engagement */ +#define KEY_AUTOPILOT_ENGAGE_TOGGLE 0x27d + +/* Shortcut Keys */ +#define KEY_MARK_WAYPOINT 0x27e +#define KEY_SOS 0x27f +#define KEY_NAV_CHART 0x280 +#define KEY_FISHING_CHART 0x281 +#define KEY_SINGLE_RANGE_RADAR 0x282 +#define KEY_DUAL_RANGE_RADAR 0x283 +#define KEY_RADAR_OVERLAY 0x284 +#define KEY_TRADITIONAL_SONAR 0x285 +#define KEY_CLEARVU_SONAR 0x286 +#define KEY_SIDEVU_SONAR 0x287 +#define KEY_NAV_INFO 0x288 +#define KEY_BRIGHTNESS_MENU 0x289 + /* * Some keyboards have keys which do not have a defined meaning, these keys * are intended to be programmed / bound to macros by the user. For most diff --git a/include/uapi/linux/input.h b/include/uapi/linux/input.h index ee3127461ee0..ef4257ab3026 100644 --- a/include/uapi/linux/input.h +++ b/include/uapi/linux/input.h @@ -271,6 +271,7 @@ struct input_mask { #define BUS_RMI 0x1D #define BUS_CEC 0x1E #define BUS_INTEL_ISHTP 0x1F +#define BUS_AMD_SFH 0x20 /* * MT_TOOL types diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 784adc6f6ed2..53e7dae92e42 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -22,6 +22,7 @@ struct io_uring_sqe { union { __u64 off; /* offset into file */ __u64 addr2; + __u32 cmd_op; }; union { __u64 addr; /* pointer to buffer or iovecs */ @@ -45,6 +46,7 @@ struct io_uring_sqe { __u32 rename_flags; __u32 unlink_flags; __u32 hardlink_flags; + __u32 xattr_flags; }; __u64 user_data; /* data to be passed back at completion time */ /* pack this to avoid bogus arm OABI complaints */ @@ -60,9 +62,28 @@ struct io_uring_sqe { __s32 splice_fd_in; __u32 file_index; }; - __u64 __pad2[2]; + union { + struct { + __u64 addr3; + __u64 __pad2[1]; + }; + /* + * If the ring is initialized with IORING_SETUP_SQE128, then + * this field is used for 80 bytes of arbitrary command data + */ + __u8 cmd[0]; + }; }; +/* + * If sqe->file_index is set to this for opcodes that instantiate a new + * direct descriptor (like openat/openat2/accept), then io_uring will allocate + * an available direct descriptor instead of having the application pass one + * in. The picked direct descriptor will be returned in cqe->res, or -ENFILE + * if the space is full. + */ +#define IORING_FILE_INDEX_ALLOC (~0U) + enum { IOSQE_FIXED_FILE_BIT, IOSQE_IO_DRAIN_BIT, @@ -102,8 +123,25 @@ enum { #define IORING_SETUP_ATTACH_WQ (1U << 5) /* attach to existing wq */ #define IORING_SETUP_R_DISABLED (1U << 6) /* start with ring disabled */ #define IORING_SETUP_SUBMIT_ALL (1U << 7) /* continue submit on error */ +/* + * Cooperative task running. When requests complete, they often require + * forcing the submitter to transition to the kernel to complete. If this + * flag is set, work will be done when the task transitions anyway, rather + * than force an inter-processor interrupt reschedule. This avoids interrupting + * a task running in userspace, and saves an IPI. + */ +#define IORING_SETUP_COOP_TASKRUN (1U << 8) +/* + * If COOP_TASKRUN is set, get notified if task work is available for + * running and a kernel transition would be needed to run it. This sets + * IORING_SQ_TASKRUN in the sq ring flags. Not valid with COOP_TASKRUN. + */ +#define IORING_SETUP_TASKRUN_FLAG (1U << 9) -enum { +#define IORING_SETUP_SQE128 (1U << 10) /* SQEs are 128 byte */ +#define IORING_SETUP_CQE32 (1U << 11) /* CQEs are 32 byte */ + +enum io_uring_op { IORING_OP_NOP, IORING_OP_READV, IORING_OP_WRITEV, @@ -145,6 +183,12 @@ enum { IORING_OP_SYMLINKAT, IORING_OP_LINKAT, IORING_OP_MSG_RING, + IORING_OP_FSETXATTR, + IORING_OP_SETXATTR, + IORING_OP_FGETXATTR, + IORING_OP_GETXATTR, + IORING_OP_SOCKET, + IORING_OP_URING_CMD, /* this goes last, obviously */ IORING_OP_LAST, @@ -188,12 +232,45 @@ enum { #define IORING_POLL_UPDATE_USER_DATA (1U << 2) /* + * ASYNC_CANCEL flags. + * + * IORING_ASYNC_CANCEL_ALL Cancel all requests that match the given key + * IORING_ASYNC_CANCEL_FD Key off 'fd' for cancelation rather than the + * request 'user_data' + * IORING_ASYNC_CANCEL_ANY Match any request + */ +#define IORING_ASYNC_CANCEL_ALL (1U << 0) +#define IORING_ASYNC_CANCEL_FD (1U << 1) +#define IORING_ASYNC_CANCEL_ANY (1U << 2) + +/* + * send/sendmsg and recv/recvmsg flags (sqe->addr2) + * + * IORING_RECVSEND_POLL_FIRST If set, instead of first attempting to send + * or receive and arm poll if that yields an + * -EAGAIN result, arm poll upfront and skip + * the initial transfer attempt. + */ +#define IORING_RECVSEND_POLL_FIRST (1U << 0) + +/* + * accept flags stored in sqe->ioprio + */ +#define IORING_ACCEPT_MULTISHOT (1U << 0) + +/* * IO completion data structure (Completion Queue Entry) */ struct io_uring_cqe { __u64 user_data; /* sqe->data submission passed back */ __s32 res; /* result code for this event */ __u32 flags; + + /* + * If the ring is initialized with IORING_SETUP_CQE32, then this field + * contains 16-bytes of padding, doubling the size of the CQE. + */ + __u64 big_cqe[]; }; /* @@ -201,9 +278,11 @@ struct io_uring_cqe { * * IORING_CQE_F_BUFFER If set, the upper 16 bits are the buffer ID * IORING_CQE_F_MORE If set, parent SQE will generate more CQE entries + * IORING_CQE_F_SOCK_NONEMPTY If set, more data to read after socket recv */ #define IORING_CQE_F_BUFFER (1U << 0) #define IORING_CQE_F_MORE (1U << 1) +#define IORING_CQE_F_SOCK_NONEMPTY (1U << 2) enum { IORING_CQE_BUFFER_SHIFT = 16, @@ -236,6 +315,7 @@ struct io_sqring_offsets { */ #define IORING_SQ_NEED_WAKEUP (1U << 0) /* needs io_uring_enter wakeup */ #define IORING_SQ_CQ_OVERFLOW (1U << 1) /* CQ ring is overflown */ +#define IORING_SQ_TASKRUN (1U << 2) /* task should enter the kernel */ struct io_cqring_offsets { __u32 head; @@ -296,6 +376,7 @@ struct io_uring_params { #define IORING_FEAT_NATIVE_WORKERS (1U << 9) #define IORING_FEAT_RSRC_TAGS (1U << 10) #define IORING_FEAT_CQE_SKIP (1U << 11) +#define IORING_FEAT_LINKED_FILE (1U << 12) /* * io_uring_register(2) opcodes and arguments @@ -332,6 +413,10 @@ enum { IORING_REGISTER_RING_FDS = 20, IORING_UNREGISTER_RING_FDS = 21, + /* register ring based provide buffer group */ + IORING_REGISTER_PBUF_RING = 22, + IORING_UNREGISTER_PBUF_RING = 23, + /* this goes last */ IORING_REGISTER_LAST }; @@ -349,9 +434,15 @@ struct io_uring_files_update { __aligned_u64 /* __s32 * */ fds; }; +/* + * Register a fully sparse file space, rather than pass in an array of all + * -1 file descriptors. + */ +#define IORING_RSRC_REGISTER_SPARSE (1U << 0) + struct io_uring_rsrc_register { __u32 nr; - __u32 resv; + __u32 flags; __u64 resv2; __aligned_u64 data; __aligned_u64 tags; @@ -403,6 +494,38 @@ struct io_uring_restriction { __u32 resv2[3]; }; +struct io_uring_buf { + __u64 addr; + __u32 len; + __u16 bid; + __u16 resv; +}; + +struct io_uring_buf_ring { + union { + /* + * To avoid spilling into more pages than we need to, the + * ring tail is overlaid with the io_uring_buf->resv field. + */ + struct { + __u64 resv1; + __u32 resv2; + __u16 resv3; + __u16 tail; + }; + struct io_uring_buf bufs[0]; + }; +}; + +/* argument for IORING_(UN)REGISTER_PBUF_RING */ +struct io_uring_buf_reg { + __u64 ring_addr; + __u32 ring_entries; + __u16 bgid; + __u16 pad; + __u64 resv[3]; +}; + /* * io_uring_restriction->opcode values */ diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 91a6fe4e02c0..6a184d260c7f 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -445,7 +445,13 @@ struct kvm_run { #define KVM_SYSTEM_EVENT_RESET 2 #define KVM_SYSTEM_EVENT_CRASH 3 __u32 type; - __u64 flags; + __u32 ndata; + union { +#ifndef __KERNEL__ + __u64 flags; +#endif + __u64 data[16]; + }; } system_event; /* KVM_EXIT_S390_STSI */ struct { @@ -1144,6 +1150,8 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_S390_MEM_OP_EXTENSION 211 #define KVM_CAP_PMU_CAPABILITY 212 #define KVM_CAP_DISABLE_QUIRKS2 213 +/* #define KVM_CAP_VM_TSC_CONTROL 214 */ +#define KVM_CAP_SYSTEM_EVENT_DATA 215 #ifdef KVM_CAP_IRQ_ROUTING diff --git a/include/uapi/linux/landlock.h b/include/uapi/linux/landlock.h index b3d952067f59..23df4e0e8ace 100644 --- a/include/uapi/linux/landlock.h +++ b/include/uapi/linux/landlock.h @@ -21,8 +21,14 @@ struct landlock_ruleset_attr { /** * @handled_access_fs: Bitmask of actions (cf. `Filesystem flags`_) * that is handled by this ruleset and should then be forbidden if no - * rule explicitly allow them. This is needed for backward - * compatibility reasons. + * rule explicitly allow them: it is a deny-by-default list that should + * contain as much Landlock access rights as possible. Indeed, all + * Landlock filesystem access rights that are not part of + * handled_access_fs are allowed. This is needed for backward + * compatibility reasons. One exception is the + * LANDLOCK_ACCESS_FS_REFER access right, which is always implicitly + * handled, but must still be explicitly handled to add new rules with + * this access right. */ __u64 handled_access_fs; }; @@ -33,7 +39,9 @@ struct landlock_ruleset_attr { * - %LANDLOCK_CREATE_RULESET_VERSION: Get the highest supported Landlock ABI * version. */ +/* clang-format off */ #define LANDLOCK_CREATE_RULESET_VERSION (1U << 0) +/* clang-format on */ /** * enum landlock_rule_type - Landlock rule type @@ -60,8 +68,9 @@ struct landlock_path_beneath_attr { */ __u64 allowed_access; /** - * @parent_fd: File descriptor, open with ``O_PATH``, which identifies - * the parent directory of a file hierarchy, or just a file. + * @parent_fd: File descriptor, preferably opened with ``O_PATH``, + * which identifies the parent directory of a file hierarchy, or just a + * file. */ __s32 parent_fd; /* @@ -109,6 +118,22 @@ struct landlock_path_beneath_attr { * - %LANDLOCK_ACCESS_FS_MAKE_FIFO: Create (or rename or link) a named pipe. * - %LANDLOCK_ACCESS_FS_MAKE_BLOCK: Create (or rename or link) a block device. * - %LANDLOCK_ACCESS_FS_MAKE_SYM: Create (or rename or link) a symbolic link. + * - %LANDLOCK_ACCESS_FS_REFER: Link or rename a file from or to a different + * directory (i.e. reparent a file hierarchy). This access right is + * available since the second version of the Landlock ABI. This is also the + * only access right which is always considered handled by any ruleset in + * such a way that reparenting a file hierarchy is always denied by default. + * To avoid privilege escalation, it is not enough to add a rule with this + * access right. When linking or renaming a file, the destination directory + * hierarchy must also always have the same or a superset of restrictions of + * the source hierarchy. If it is not the case, or if the domain doesn't + * handle this access right, such actions are denied by default with errno + * set to EXDEV. Linking also requires a LANDLOCK_ACCESS_FS_MAKE_* access + * right on the destination directory, and renaming also requires a + * LANDLOCK_ACCESS_FS_REMOVE_* access right on the source's (file or + * directory) parent. Otherwise, such actions are denied with errno set to + * EACCES. The EACCES errno prevails over EXDEV to let user space + * efficiently deal with an unrecoverable error. * * .. warning:: * @@ -120,6 +145,7 @@ struct landlock_path_beneath_attr { * :manpage:`access(2)`. * Future Landlock evolutions will enable to restrict them. */ +/* clang-format off */ #define LANDLOCK_ACCESS_FS_EXECUTE (1ULL << 0) #define LANDLOCK_ACCESS_FS_WRITE_FILE (1ULL << 1) #define LANDLOCK_ACCESS_FS_READ_FILE (1ULL << 2) @@ -133,5 +159,7 @@ struct landlock_path_beneath_attr { #define LANDLOCK_ACCESS_FS_MAKE_FIFO (1ULL << 10) #define LANDLOCK_ACCESS_FS_MAKE_BLOCK (1ULL << 11) #define LANDLOCK_ACCESS_FS_MAKE_SYM (1ULL << 12) +#define LANDLOCK_ACCESS_FS_REFER (1ULL << 13) +/* clang-format on */ #endif /* _UAPI_LINUX_LANDLOCK_H */ diff --git a/include/uapi/linux/lirc.h b/include/uapi/linux/lirc.h index 23b0f2c8ba81..8d7ca7c6af42 100644 --- a/include/uapi/linux/lirc.h +++ b/include/uapi/linux/lirc.h @@ -84,6 +84,13 @@ #define LIRC_CAN_SEND(x) ((x)&LIRC_CAN_SEND_MASK) #define LIRC_CAN_REC(x) ((x)&LIRC_CAN_REC_MASK) +/* + * Unused features. These features were never implemented, in tree or + * out of tree. These definitions are here so not to break the lircd build. + */ +#define LIRC_CAN_SET_REC_FILTER 0 +#define LIRC_CAN_NOTIFY_DECODE 0 + /*** IOCTL commands for lirc driver ***/ #define LIRC_GET_FEATURES _IOR('i', 0x00000000, __u32) diff --git a/include/uapi/linux/loop.h b/include/uapi/linux/loop.h index 98e60801195e..6f63527dd2ed 100644 --- a/include/uapi/linux/loop.h +++ b/include/uapi/linux/loop.h @@ -1,11 +1,6 @@ /* SPDX-License-Identifier: GPL-1.0+ WITH Linux-syscall-note */ /* - * include/linux/loop.h - * - * Written by Theodore Ts'o, 3/29/93. - * - * Copyright 1993 by Theodore Ts'o. Redistribution of this file is - * permitted under the GNU General Public License. + * Copyright 1993 by Theodore Ts'o. */ #ifndef _UAPI_LINUX_LOOP_H #define _UAPI_LINUX_LOOP_H diff --git a/include/uapi/linux/media.h b/include/uapi/linux/media.h index 200fa8462b90..3ddadaea849f 100644 --- a/include/uapi/linux/media.h +++ b/include/uapi/linux/media.h @@ -20,9 +20,6 @@ #ifndef __LINUX_MEDIA_H #define __LINUX_MEDIA_H -#ifndef __KERNEL__ -#include <stdint.h> -#endif #include <linux/ioctl.h> #include <linux/types.h> @@ -226,6 +223,7 @@ struct media_pad_desc { #define MEDIA_LNK_FL_LINK_TYPE (0xf << 28) # define MEDIA_LNK_FL_DATA_LINK (0 << 28) # define MEDIA_LNK_FL_INTERFACE_LINK (1 << 28) +# define MEDIA_LNK_FL_ANCILLARY_LINK (2 << 28) struct media_link_desc { struct media_pad_desc source; diff --git a/include/uapi/linux/nvme_ioctl.h b/include/uapi/linux/nvme_ioctl.h index b2e43185e3b5..2f76cba67166 100644 --- a/include/uapi/linux/nvme_ioctl.h +++ b/include/uapi/linux/nvme_ioctl.h @@ -70,6 +70,28 @@ struct nvme_passthru_cmd64 { __u64 result; }; +/* same as struct nvme_passthru_cmd64, minus the 8b result field */ +struct nvme_uring_cmd { + __u8 opcode; + __u8 flags; + __u16 rsvd1; + __u32 nsid; + __u32 cdw2; + __u32 cdw3; + __u64 metadata; + __u64 addr; + __u32 metadata_len; + __u32 data_len; + __u32 cdw10; + __u32 cdw11; + __u32 cdw12; + __u32 cdw13; + __u32 cdw14; + __u32 cdw15; + __u32 timeout_ms; + __u32 rsvd2; +}; + #define nvme_admin_cmd nvme_passthru_cmd #define NVME_IOCTL_ID _IO('N', 0x40) @@ -83,4 +105,10 @@ struct nvme_passthru_cmd64 { #define NVME_IOCTL_IO64_CMD _IOWR('N', 0x48, struct nvme_passthru_cmd64) #define NVME_IOCTL_IO64_CMD_VEC _IOWR('N', 0x49, struct nvme_passthru_cmd64) +/* io_uring async commands: */ +#define NVME_URING_CMD_IO _IOWR('N', 0x80, struct nvme_uring_cmd) +#define NVME_URING_CMD_IO_VEC _IOWR('N', 0x81, struct nvme_uring_cmd) +#define NVME_URING_CMD_ADMIN _IOWR('N', 0x82, struct nvme_uring_cmd) +#define NVME_URING_CMD_ADMIN_VEC _IOWR('N', 0x83, struct nvme_uring_cmd) + #endif /* _UAPI_LINUX_NVME_IOCTL_H */ diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index e998764f0262..a5e06dcbba13 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -272,6 +272,15 @@ struct prctl_mm_map { # define PR_SCHED_CORE_SCOPE_THREAD_GROUP 1 # define PR_SCHED_CORE_SCOPE_PROCESS_GROUP 2 +/* arm64 Scalable Matrix Extension controls */ +/* Flag values must be in sync with SVE versions */ +#define PR_SME_SET_VL 63 /* set task vector length */ +# define PR_SME_SET_VL_ONEXEC (1 << 18) /* defer effect until exec */ +#define PR_SME_GET_VL 64 /* get task vector length */ +/* Bits common to PR_SME_SET_VL and PR_SME_GET_VL */ +# define PR_SME_VL_LEN_MASK 0xffff +# define PR_SME_VL_INHERIT (1 << 17) /* inherit across exec */ + #define PR_SET_VMA 0x53564d41 # define PR_SET_VMA_ANON_NAME 0 diff --git a/include/uapi/linux/rfkill.h b/include/uapi/linux/rfkill.h index 283c5a7b3f2c..db6c8588c1d0 100644 --- a/include/uapi/linux/rfkill.h +++ b/include/uapi/linux/rfkill.h @@ -184,7 +184,7 @@ struct rfkill_event_ext { #define RFKILL_IOC_NOINPUT 1 #define RFKILL_IOCTL_NOINPUT _IO(RFKILL_IOC_MAGIC, RFKILL_IOC_NOINPUT) #define RFKILL_IOC_MAX_SIZE 2 -#define RFKILL_IOCTL_MAX_SIZE _IOW(RFKILL_IOC_MAGIC, RFKILL_IOC_EXT_SIZE, __u32) +#define RFKILL_IOCTL_MAX_SIZE _IOW(RFKILL_IOC_MAGIC, RFKILL_IOC_MAX_SIZE, __u32) /* and that's all userspace gets */ diff --git a/include/uapi/linux/seccomp.h b/include/uapi/linux/seccomp.h index 78074254ab98..0fdc6ef02b94 100644 --- a/include/uapi/linux/seccomp.h +++ b/include/uapi/linux/seccomp.h @@ -23,6 +23,8 @@ #define SECCOMP_FILTER_FLAG_SPEC_ALLOW (1UL << 2) #define SECCOMP_FILTER_FLAG_NEW_LISTENER (1UL << 3) #define SECCOMP_FILTER_FLAG_TSYNC_ESRCH (1UL << 4) +/* Received notifications wait in killable state (only respond to fatal signals) */ +#define SECCOMP_FILTER_FLAG_WAIT_KILLABLE_RECV (1UL << 5) /* * All BPF programs must return a 32-bit value. diff --git a/include/uapi/linux/sev-guest.h b/include/uapi/linux/sev-guest.h new file mode 100644 index 000000000000..256aaeff7e65 --- /dev/null +++ b/include/uapi/linux/sev-guest.h @@ -0,0 +1,80 @@ +/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */ +/* + * Userspace interface for AMD SEV and SNP guest driver. + * + * Copyright (C) 2021 Advanced Micro Devices, Inc. + * + * Author: Brijesh Singh <brijesh.singh@amd.com> + * + * SEV API specification is available at: https://developer.amd.com/sev/ + */ + +#ifndef __UAPI_LINUX_SEV_GUEST_H_ +#define __UAPI_LINUX_SEV_GUEST_H_ + +#include <linux/types.h> + +struct snp_report_req { + /* user data that should be included in the report */ + __u8 user_data[64]; + + /* The vmpl level to be included in the report */ + __u32 vmpl; + + /* Must be zero filled */ + __u8 rsvd[28]; +}; + +struct snp_report_resp { + /* response data, see SEV-SNP spec for the format */ + __u8 data[4000]; +}; + +struct snp_derived_key_req { + __u32 root_key_select; + __u32 rsvd; + __u64 guest_field_select; + __u32 vmpl; + __u32 guest_svn; + __u64 tcb_version; +}; + +struct snp_derived_key_resp { + /* response data, see SEV-SNP spec for the format */ + __u8 data[64]; +}; + +struct snp_guest_request_ioctl { + /* message version number (must be non-zero) */ + __u8 msg_version; + + /* Request and response structure address */ + __u64 req_data; + __u64 resp_data; + + /* firmware error code on failure (see psp-sev.h) */ + __u64 fw_err; +}; + +struct snp_ext_report_req { + struct snp_report_req data; + + /* where to copy the certificate blob */ + __u64 certs_address; + + /* length of the certificate blob */ + __u32 certs_len; +}; + +#define SNP_GUEST_REQ_IOC_TYPE 'S' + +/* Get SNP attestation report */ +#define SNP_GET_REPORT _IOWR(SNP_GUEST_REQ_IOC_TYPE, 0x0, struct snp_guest_request_ioctl) + +/* Get a derived key from the root */ +#define SNP_GET_DERIVED_KEY _IOWR(SNP_GUEST_REQ_IOC_TYPE, 0x1, struct snp_guest_request_ioctl) + +/* Get SNP extended report as defined in the GHCB specification version 2. */ +#define SNP_GET_EXT_REPORT _IOWR(SNP_GUEST_REQ_IOC_TYPE, 0x2, struct snp_guest_request_ioctl) + +#endif /* __UAPI_LINUX_SEV_GUEST_H_ */ diff --git a/include/uapi/linux/spi/spi.h b/include/uapi/linux/spi/spi.h index 236a85f08ded..9d5f58059703 100644 --- a/include/uapi/linux/spi/spi.h +++ b/include/uapi/linux/spi/spi.h @@ -27,6 +27,7 @@ #define SPI_TX_OCTAL _BITUL(13) /* transmit with 8 wires */ #define SPI_RX_OCTAL _BITUL(14) /* receive with 8 wires */ #define SPI_3WIRE_HIZ _BITUL(15) /* high impedance turnaround */ +#define SPI_RX_CPHA_FLIP _BITUL(16) /* flip CPHA on Rx only xfer */ /* * All the bits defined above should be covered by SPI_MODE_USER_MASK. @@ -36,6 +37,6 @@ * These bits must not overlap. A static assert check should make sure of that. * If adding extra bits, make sure to increase the bit index below as well. */ -#define SPI_MODE_USER_MASK (_BITUL(16) - 1) +#define SPI_MODE_USER_MASK (_BITUL(17) - 1) #endif /* _UAPI_SPI_H */ diff --git a/include/uapi/linux/stddef.h b/include/uapi/linux/stddef.h index 3021ea25a284..7837ba4fe728 100644 --- a/include/uapi/linux/stddef.h +++ b/include/uapi/linux/stddef.h @@ -1,4 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI_LINUX_STDDEF_H +#define _UAPI_LINUX_STDDEF_H + #include <linux/compiler_types.h> #ifndef __always_inline @@ -41,3 +44,4 @@ struct { } __empty_ ## NAME; \ TYPE NAME[]; \ } +#endif diff --git a/include/uapi/linux/types.h b/include/uapi/linux/types.h index c4dc597f3dcf..308433be33c2 100644 --- a/include/uapi/linux/types.h +++ b/include/uapi/linux/types.h @@ -26,6 +26,9 @@ #define __bitwise #endif +/* The kernel doesn't use this legacy form, but user space does */ +#define __bitwise__ __bitwise + typedef __u16 __bitwise __le16; typedef __u16 __bitwise __be16; typedef __u32 __bitwise __le32; diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h index bb40129446d4..dfff69ed88f7 100644 --- a/include/uapi/linux/v4l2-controls.h +++ b/include/uapi/linux/v4l2-controls.h @@ -449,6 +449,11 @@ enum v4l2_mpeg_video_multi_slice_mode { #define V4L2_CID_MPEG_VIDEO_USE_LTR_FRAMES (V4L2_CID_CODEC_BASE+234) #define V4L2_CID_MPEG_VIDEO_DEC_CONCEAL_COLOR (V4L2_CID_CODEC_BASE+235) #define V4L2_CID_MPEG_VIDEO_INTRA_REFRESH_PERIOD (V4L2_CID_CODEC_BASE+236) +#define V4L2_CID_MPEG_VIDEO_INTRA_REFRESH_PERIOD_TYPE (V4L2_CID_CODEC_BASE+237) +enum v4l2_mpeg_video_intra_refresh_period_type { + V4L2_CID_MPEG_VIDEO_INTRA_REFRESH_PERIOD_TYPE_RANDOM = 0, + V4L2_CID_MPEG_VIDEO_INTRA_REFRESH_PERIOD_TYPE_CYCLIC = 1, +}; /* CIDs for the MPEG-2 Part 2 (H.262) codec */ #define V4L2_CID_MPEG_VIDEO_MPEG2_LEVEL (V4L2_CID_CODEC_BASE+270) diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 3768a0a80830..343b95107fce 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -569,6 +569,7 @@ struct v4l2_pix_format { /* Grey bit-packed formats */ #define V4L2_PIX_FMT_Y10BPACK v4l2_fourcc('Y', '1', '0', 'B') /* 10 Greyscale bit-packed */ #define V4L2_PIX_FMT_Y10P v4l2_fourcc('Y', '1', '0', 'P') /* 10 Greyscale, MIPI RAW10 packed */ +#define V4L2_PIX_FMT_IPU3_Y10 v4l2_fourcc('i', 'p', '3', 'y') /* IPU3 packed 10-bit greyscale */ /* Palette formats */ #define V4L2_PIX_FMT_PAL8 v4l2_fourcc('P', 'A', 'L', '8') /* 8 8-bit palette */ @@ -746,8 +747,10 @@ struct v4l2_pix_format { #define V4L2_PIX_FMT_INZI v4l2_fourcc('I', 'N', 'Z', 'I') /* Intel Planar Greyscale 10-bit and Depth 16-bit */ #define V4L2_PIX_FMT_CNF4 v4l2_fourcc('C', 'N', 'F', '4') /* Intel 4-bit packed depth confidence information */ #define V4L2_PIX_FMT_HI240 v4l2_fourcc('H', 'I', '2', '4') /* BTTV 8-bit dithered RGB */ +#define V4L2_PIX_FMT_QC08C v4l2_fourcc('Q', '0', '8', 'C') /* Qualcomm 8-bit compressed */ +#define V4L2_PIX_FMT_QC10C v4l2_fourcc('Q', '1', '0', 'C') /* Qualcomm 10-bit compressed */ -/* 10bit raw bayer packed, 32 bytes for every 25 pixels, last LSB 6 bits unused */ +/* 10bit raw packed, 32 bytes for every 25 pixels, last LSB 6 bits unused */ #define V4L2_PIX_FMT_IPU3_SBGGR10 v4l2_fourcc('i', 'p', '3', 'b') /* IPU3 packed 10-bit BGGR bayer */ #define V4L2_PIX_FMT_IPU3_SGBRG10 v4l2_fourcc('i', 'p', '3', 'g') /* IPU3 packed 10-bit GBRG bayer */ #define V4L2_PIX_FMT_IPU3_SGRBG10 v4l2_fourcc('i', 'p', '3', 'G') /* IPU3 packed 10-bit GRBG bayer */ diff --git a/include/uapi/linux/virtio_ids.h b/include/uapi/linux/virtio_ids.h index 80d76b75bccd..7aa2eb766205 100644 --- a/include/uapi/linux/virtio_ids.h +++ b/include/uapi/linux/virtio_ids.h @@ -73,12 +73,12 @@ * Virtio Transitional IDs */ -#define VIRTIO_TRANS_ID_NET 1000 /* transitional virtio net */ -#define VIRTIO_TRANS_ID_BLOCK 1001 /* transitional virtio block */ -#define VIRTIO_TRANS_ID_BALLOON 1002 /* transitional virtio balloon */ -#define VIRTIO_TRANS_ID_CONSOLE 1003 /* transitional virtio console */ -#define VIRTIO_TRANS_ID_SCSI 1004 /* transitional virtio SCSI */ -#define VIRTIO_TRANS_ID_RNG 1005 /* transitional virtio rng */ -#define VIRTIO_TRANS_ID_9P 1009 /* transitional virtio 9p console */ +#define VIRTIO_TRANS_ID_NET 0x1000 /* transitional virtio net */ +#define VIRTIO_TRANS_ID_BLOCK 0x1001 /* transitional virtio block */ +#define VIRTIO_TRANS_ID_BALLOON 0x1002 /* transitional virtio balloon */ +#define VIRTIO_TRANS_ID_CONSOLE 0x1003 /* transitional virtio console */ +#define VIRTIO_TRANS_ID_SCSI 0x1004 /* transitional virtio SCSI */ +#define VIRTIO_TRANS_ID_RNG 0x1005 /* transitional virtio rng */ +#define VIRTIO_TRANS_ID_9P 0x1009 /* transitional virtio 9p console */ #endif /* _LINUX_VIRTIO_IDS_H */ diff --git a/include/xen/grant_table.h b/include/xen/grant_table.h index dfd5bf31cfb9..7d0f2f0037b8 100644 --- a/include/xen/grant_table.h +++ b/include/xen/grant_table.h @@ -57,8 +57,6 @@ #define INVALID_GRANT_REF ((grant_ref_t)-1) #define INVALID_GRANT_HANDLE ((grant_handle_t)-1) -#define GNTTAB_RESERVED_XENSTORE 1 - /* NR_GRANT_FRAMES must be less than or equal to that configured in Xen */ #define NR_GRANT_FRAMES 4 diff --git a/include/xen/interface/grant_table.h b/include/xen/interface/grant_table.h index 3eeabbc7ee09..cebbd99f1f84 100644 --- a/include/xen/interface/grant_table.h +++ b/include/xen/interface/grant_table.h @@ -19,7 +19,8 @@ /* Some rough guidelines on accessing and updating grant-table entries * in a concurrency-safe manner. For more information, Linux contains a - * reference implementation for guest OSes (arch/xen/kernel/grant_table.c). + * reference implementation for guest OSes (drivers/xen/grant_table.c, see + * http://git.kernel.org/?p=linux/kernel/git/torvalds/linux.git;a=blob;f=drivers/xen/grant-table.c;hb=HEAD * * NB. WMB is a no-op on current-generation x86 processors. However, a * compiler barrier will still be required. @@ -80,8 +81,9 @@ typedef uint32_t grant_ref_t; */ /* - * Version 1 of the grant table entry structure is maintained purely - * for backwards compatibility. New guests should use version 2. + * Version 1 of the grant table entry structure is maintained largely for + * backwards compatibility. New guests are recommended to support using + * version 2 to overcome version 1 limitations, but to default to version 1. */ struct grant_entry_v1 { /* GTF_xxx: various type and flag information. [XEN,GST] */ @@ -89,12 +91,21 @@ struct grant_entry_v1 { /* The domain being granted foreign privileges. [GST] */ domid_t domid; /* - * GTF_permit_access: Frame that @domid is allowed to map and access. [GST] - * GTF_accept_transfer: Frame whose ownership transferred by @domid. [XEN] + * GTF_permit_access: GFN that @domid is allowed to map and access. [GST] + * GTF_accept_transfer: GFN that @domid is allowed to transfer into. [GST] + * GTF_transfer_completed: MFN whose ownership transferred by @domid + * (non-translated guests only). [XEN] */ uint32_t frame; }; +/* The first few grant table entries will be preserved across grant table + * version changes and may be pre-populated at domain creation by tools. + */ +#define GNTTAB_NR_RESERVED_ENTRIES 8 +#define GNTTAB_RESERVED_CONSOLE 0 +#define GNTTAB_RESERVED_XENSTORE 1 + /* * Type of grant entry. * GTF_invalid: This grant entry grants no privileges. @@ -111,10 +122,13 @@ struct grant_entry_v1 { #define GTF_type_mask (3U<<0) /* - * Subflags for GTF_permit_access. + * Subflags for GTF_permit_access and GTF_transitive. * GTF_readonly: Restrict @domid to read-only mappings and accesses. [GST] * GTF_reading: Grant entry is currently mapped for reading by @domid. [XEN] * GTF_writing: Grant entry is currently mapped for writing by @domid. [XEN] + * Further subflags for GTF_permit_access only. + * GTF_PAT, GTF_PWT, GTF_PCD: (x86) cache attribute flags to be used for + * mappings of the grant [GST] * GTF_sub_page: Grant access to only a subrange of the page. @domid * will only be allowed to copy from the grant, and not * map it. [GST] @@ -125,6 +139,12 @@ struct grant_entry_v1 { #define GTF_reading (1U<<_GTF_reading) #define _GTF_writing (4) #define GTF_writing (1U<<_GTF_writing) +#define _GTF_PWT (5) +#define GTF_PWT (1U<<_GTF_PWT) +#define _GTF_PCD (6) +#define GTF_PCD (1U<<_GTF_PCD) +#define _GTF_PAT (7) +#define GTF_PAT (1U<<_GTF_PAT) #define _GTF_sub_page (8) #define GTF_sub_page (1U<<_GTF_sub_page) @@ -164,8 +184,7 @@ struct grant_entry_header { }; /* - * Version 2 of the grant entry structure, here is a union because three - * different types are suppotted: full_page, sub_page and transitive. + * Version 2 of the grant entry structure. */ union grant_entry_v2 { struct grant_entry_header hdr; @@ -180,9 +199,9 @@ union grant_entry_v2 { * field of the same name in the V1 entry structure. */ struct { - struct grant_entry_header hdr; - uint32_t pad0; - uint64_t frame; + struct grant_entry_header hdr; + uint32_t pad0; + uint64_t frame; } full_page; /* @@ -191,10 +210,10 @@ union grant_entry_v2 { * in frame @frame. */ struct { - struct grant_entry_header hdr; - uint16_t page_off; - uint16_t length; - uint64_t frame; + struct grant_entry_header hdr; + uint16_t page_off; + uint16_t length; + uint64_t frame; } sub_page; /* @@ -202,12 +221,15 @@ union grant_entry_v2 { * grant @gref in domain @trans_domid, as if it was the local * domain. Obviously, the transitive access must be compatible * with the original grant. + * + * The current version of Xen does not allow transitive grants + * to be mapped. */ struct { - struct grant_entry_header hdr; - domid_t trans_domid; - uint16_t pad0; - grant_ref_t gref; + struct grant_entry_header hdr; + domid_t trans_domid; + uint16_t pad0; + grant_ref_t gref; } transitive; uint32_t __spacer[4]; /* Pad to a power of two */ @@ -219,6 +241,21 @@ typedef uint16_t grant_status_t; * GRANT TABLE QUERIES AND USES */ +#define GNTTABOP_map_grant_ref 0 +#define GNTTABOP_unmap_grant_ref 1 +#define GNTTABOP_setup_table 2 +#define GNTTABOP_dump_table 3 +#define GNTTABOP_transfer 4 +#define GNTTABOP_copy 5 +#define GNTTABOP_query_size 6 +#define GNTTABOP_unmap_and_replace 7 +#define GNTTABOP_set_version 8 +#define GNTTABOP_get_status_frames 9 +#define GNTTABOP_get_version 10 +#define GNTTABOP_swap_grant_ref 11 +#define GNTTABOP_cache_flush 12 +/* ` } */ + /* * Handle to track a mapping created via a grant reference. */ @@ -227,7 +264,7 @@ typedef uint32_t grant_handle_t; /* * GNTTABOP_map_grant_ref: Map the grant entry (<dom>,<ref>) for access * by devices and/or host CPUs. If successful, <handle> is a tracking number - * that must be presented later to destroy the mapping(s). On error, <handle> + * that must be presented later to destroy the mapping(s). On error, <status> * is a negative status code. * NOTES: * 1. If GNTMAP_device_map is specified then <dev_bus_addr> is the address @@ -241,7 +278,6 @@ typedef uint32_t grant_handle_t; * host mapping is destroyed by other means then it is *NOT* guaranteed * to be accounted to the correct grant reference! */ -#define GNTTABOP_map_grant_ref 0 struct gnttab_map_grant_ref { /* IN parameters. */ uint64_t host_addr; @@ -266,7 +302,6 @@ DEFINE_GUEST_HANDLE_STRUCT(gnttab_map_grant_ref); * 3. After executing a batch of unmaps, it is guaranteed that no stale * mappings will remain in the device or host TLBs. */ -#define GNTTABOP_unmap_grant_ref 1 struct gnttab_unmap_grant_ref { /* IN parameters. */ uint64_t host_addr; @@ -286,7 +321,6 @@ DEFINE_GUEST_HANDLE_STRUCT(gnttab_unmap_grant_ref); * 2. Only a sufficiently-privileged domain may specify <dom> != DOMID_SELF. * 3. Xen may not support more than a single grant-table page per domain. */ -#define GNTTABOP_setup_table 2 struct gnttab_setup_table { /* IN parameters. */ domid_t dom; @@ -301,7 +335,6 @@ DEFINE_GUEST_HANDLE_STRUCT(gnttab_setup_table); * GNTTABOP_dump_table: Dump the contents of the grant table to the * xen console. Debugging use only. */ -#define GNTTABOP_dump_table 3 struct gnttab_dump_table { /* IN parameters. */ domid_t dom; @@ -311,17 +344,17 @@ struct gnttab_dump_table { DEFINE_GUEST_HANDLE_STRUCT(gnttab_dump_table); /* - * GNTTABOP_transfer_grant_ref: Transfer <frame> to a foreign domain. The - * foreign domain has previously registered its interest in the transfer via - * <domid, ref>. + * GNTTABOP_transfer: Transfer <frame> to a foreign domain. The foreign domain + * has previously registered its interest in the transfer via <domid, ref>. * * Note that, even if the transfer fails, the specified page no longer belongs * to the calling domain *unless* the error is GNTST_bad_page. + * + * Note further that only PV guests can use this operation. */ -#define GNTTABOP_transfer 4 struct gnttab_transfer { /* IN parameters. */ - xen_pfn_t mfn; + xen_pfn_t mfn; domid_t domid; grant_ref_t ref; /* OUT parameters. */ @@ -352,21 +385,20 @@ DEFINE_GUEST_HANDLE_STRUCT(gnttab_transfer); #define _GNTCOPY_dest_gref (1) #define GNTCOPY_dest_gref (1<<_GNTCOPY_dest_gref) -#define GNTTABOP_copy 5 struct gnttab_copy { - /* IN parameters. */ - struct { - union { - grant_ref_t ref; - xen_pfn_t gmfn; - } u; - domid_t domid; - uint16_t offset; - } source, dest; - uint16_t len; - uint16_t flags; /* GNTCOPY_* */ - /* OUT parameters. */ - int16_t status; + /* IN parameters. */ + struct gnttab_copy_ptr { + union { + grant_ref_t ref; + xen_pfn_t gmfn; + } u; + domid_t domid; + uint16_t offset; + } source, dest; + uint16_t len; + uint16_t flags; /* GNTCOPY_* */ + /* OUT parameters. */ + int16_t status; }; DEFINE_GUEST_HANDLE_STRUCT(gnttab_copy); @@ -377,7 +409,6 @@ DEFINE_GUEST_HANDLE_STRUCT(gnttab_copy); * 1. <dom> may be specified as DOMID_SELF. * 2. Only a sufficiently-privileged domain may specify <dom> != DOMID_SELF. */ -#define GNTTABOP_query_size 6 struct gnttab_query_size { /* IN parameters. */ domid_t dom; @@ -399,7 +430,6 @@ DEFINE_GUEST_HANDLE_STRUCT(gnttab_query_size); * 2. After executing a batch of unmaps, it is guaranteed that no stale * mappings will remain in the device or host TLBs. */ -#define GNTTABOP_unmap_and_replace 7 struct gnttab_unmap_and_replace { /* IN parameters. */ uint64_t host_addr; @@ -412,14 +442,12 @@ DEFINE_GUEST_HANDLE_STRUCT(gnttab_unmap_and_replace); /* * GNTTABOP_set_version: Request a particular version of the grant - * table shared table structure. This operation can only be performed - * once in any given domain. It must be performed before any grants - * are activated; otherwise, the domain will be stuck with version 1. - * The only defined versions are 1 and 2. + * table shared table structure. This operation may be used to toggle + * between different versions, but must be performed while no grants + * are active. The only defined versions are 1 and 2. */ -#define GNTTABOP_set_version 8 struct gnttab_set_version { - /* IN parameters */ + /* IN/OUT parameters */ uint32_t version; }; DEFINE_GUEST_HANDLE_STRUCT(gnttab_set_version); @@ -436,7 +464,6 @@ DEFINE_GUEST_HANDLE_STRUCT(gnttab_set_version); * 1. <dom> may be specified as DOMID_SELF. * 2. Only a sufficiently-privileged domain may specify <dom> != DOMID_SELF. */ -#define GNTTABOP_get_status_frames 9 struct gnttab_get_status_frames { /* IN parameters. */ uint32_t nr_frames; @@ -451,7 +478,6 @@ DEFINE_GUEST_HANDLE_STRUCT(gnttab_get_status_frames); * GNTTABOP_get_version: Get the grant table version which is in * effect for domain <dom>. */ -#define GNTTABOP_get_version 10 struct gnttab_get_version { /* IN parameters */ domid_t dom; @@ -462,26 +488,37 @@ struct gnttab_get_version { DEFINE_GUEST_HANDLE_STRUCT(gnttab_get_version); /* + * GNTTABOP_swap_grant_ref: Swap the contents of two grant entries. + */ +struct gnttab_swap_grant_ref { + /* IN parameters */ + grant_ref_t ref_a; + grant_ref_t ref_b; + /* OUT parameters */ + int16_t status; /* GNTST_* */ +}; +DEFINE_GUEST_HANDLE_STRUCT(gnttab_swap_grant_ref); + +/* * Issue one or more cache maintenance operations on a portion of a * page granted to the calling domain by a foreign domain. */ -#define GNTTABOP_cache_flush 12 struct gnttab_cache_flush { union { uint64_t dev_bus_addr; grant_ref_t ref; } a; - uint16_t offset; /* offset from start of grant */ - uint16_t length; /* size within the grant */ -#define GNTTAB_CACHE_CLEAN (1<<0) -#define GNTTAB_CACHE_INVAL (1<<1) -#define GNTTAB_CACHE_SOURCE_GREF (1<<31) + uint16_t offset; /* offset from start of grant */ + uint16_t length; /* size within the grant */ +#define GNTTAB_CACHE_CLEAN (1u<<0) +#define GNTTAB_CACHE_INVAL (1u<<1) +#define GNTTAB_CACHE_SOURCE_GREF (1u<<31) uint32_t op; }; DEFINE_GUEST_HANDLE_STRUCT(gnttab_cache_flush); /* - * Bitfield values for update_pin_status.flags. + * Bitfield values for gnttab_map_grant_ref.flags. */ /* Map the grant entry for access by I/O devices. */ #define _GNTMAP_device_map (0) @@ -531,6 +568,7 @@ DEFINE_GUEST_HANDLE_STRUCT(gnttab_cache_flush); #define GNTST_bad_copy_arg (-10) /* copy arguments cross page boundary. */ #define GNTST_address_too_big (-11) /* transfer page address too large. */ #define GNTST_eagain (-12) /* Operation not done; try again. */ +#define GNTST_no_space (-13) /* Out of space (handles etc). */ #define GNTTABOP_error_msgs { \ "okay", \ @@ -545,7 +583,8 @@ DEFINE_GUEST_HANDLE_STRUCT(gnttab_cache_flush); "bad page", \ "copy arguments cross page boundary", \ "page address size too large", \ - "operation not done; try again" \ + "operation not done; try again", \ + "out of space", \ } #endif /* __XEN_PUBLIC_GRANT_TABLE_H__ */ diff --git a/include/xen/interface/io/ring.h b/include/xen/interface/io/ring.h index 2470ec45ebb2..ba4c4274b714 100644 --- a/include/xen/interface/io/ring.h +++ b/include/xen/interface/io/ring.h @@ -72,9 +72,8 @@ typedef unsigned int RING_IDX; * of the shared memory area (PAGE_SIZE, for instance). To initialise * the front half: * - * mytag_front_ring_t front_ring; - * SHARED_RING_INIT((mytag_sring_t *)shared_page); - * FRONT_RING_INIT(&front_ring, (mytag_sring_t *)shared_page, PAGE_SIZE); + * mytag_front_ring_t ring; + * XEN_FRONT_RING_INIT(&ring, (mytag_sring_t *)shared_page, PAGE_SIZE); * * Initializing the back follows similarly (note that only the front * initializes the shared ring): @@ -146,6 +145,11 @@ struct __name##_back_ring { \ #define FRONT_RING_INIT(_r, _s, __size) FRONT_RING_ATTACH(_r, _s, 0, __size) +#define XEN_FRONT_RING_INIT(r, s, size) do { \ + SHARED_RING_INIT(s); \ + FRONT_RING_INIT(r, s, size); \ +} while (0) + #define BACK_RING_ATTACH(_r, _s, _i, __size) do { \ (_r)->rsp_prod_pvt = (_i); \ (_r)->req_cons = (_i); \ @@ -170,16 +174,21 @@ struct __name##_back_ring { \ (RING_FREE_REQUESTS(_r) == 0) /* Test if there are outstanding messages to be processed on a ring. */ -#define RING_HAS_UNCONSUMED_RESPONSES(_r) \ +#define XEN_RING_NR_UNCONSUMED_RESPONSES(_r) \ ((_r)->sring->rsp_prod - (_r)->rsp_cons) -#define RING_HAS_UNCONSUMED_REQUESTS(_r) ({ \ +#define XEN_RING_NR_UNCONSUMED_REQUESTS(_r) ({ \ unsigned int req = (_r)->sring->req_prod - (_r)->req_cons; \ unsigned int rsp = RING_SIZE(_r) - \ ((_r)->req_cons - (_r)->rsp_prod_pvt); \ req < rsp ? req : rsp; \ }) +#define RING_HAS_UNCONSUMED_RESPONSES(_r) \ + (!!XEN_RING_NR_UNCONSUMED_RESPONSES(_r)) +#define RING_HAS_UNCONSUMED_REQUESTS(_r) \ + (!!XEN_RING_NR_UNCONSUMED_REQUESTS(_r)) + /* Direct access to individual ring elements, by index. */ #define RING_GET_REQUEST(_r, _idx) \ (&((_r)->sring->ring[((_idx) & (RING_SIZE(_r) - 1))].req)) diff --git a/include/xen/interface/io/vscsiif.h b/include/xen/interface/io/vscsiif.h index 1f6047d3de44..7ea4dc9611c4 100644 --- a/include/xen/interface/io/vscsiif.h +++ b/include/xen/interface/io/vscsiif.h @@ -43,7 +43,7 @@ * * A string specifying the backend device: either a 4-tuple "h:c:t:l" * (host, controller, target, lun, all integers), or a WWN (e.g. - * "naa.60014054ac780582"). + * "naa.60014054ac780582:0"). * * v-dev * Values: string @@ -87,6 +87,75 @@ * response structures. */ +/* + * Xenstore format in practice + * =========================== + * + * The backend driver uses a single_host:many_devices notation to manage domU + * devices. Everything is stored in /local/domain/<backend_domid>/backend/vscsi/. + * The xenstore layout looks like this (dom0 is assumed to be the backend_domid): + * + * <domid>/<vhost>/feature-host = "0" + * <domid>/<vhost>/frontend = "/local/domain/<domid>/device/vscsi/0" + * <domid>/<vhost>/frontend-id = "<domid>" + * <domid>/<vhost>/online = "1" + * <domid>/<vhost>/state = "4" + * <domid>/<vhost>/vscsi-devs/dev-0/p-dev = "8:0:2:1" or "naa.wwn:lun" + * <domid>/<vhost>/vscsi-devs/dev-0/state = "4" + * <domid>/<vhost>/vscsi-devs/dev-0/v-dev = "0:0:0:0" + * <domid>/<vhost>/vscsi-devs/dev-1/p-dev = "8:0:2:2" + * <domid>/<vhost>/vscsi-devs/dev-1/state = "4" + * <domid>/<vhost>/vscsi-devs/dev-1/v-dev = "0:0:1:0" + * + * The frontend driver maintains its state in + * /local/domain/<domid>/device/vscsi/. + * + * <vhost>/backend = "/local/domain/0/backend/vscsi/<domid>/<vhost>" + * <vhost>/backend-id = "0" + * <vhost>/event-channel = "20" + * <vhost>/ring-ref = "43" + * <vhost>/state = "4" + * <vhost>/vscsi-devs/dev-0/state = "4" + * <vhost>/vscsi-devs/dev-1/state = "4" + * + * In addition to the entries for backend and frontend these flags are stored + * for the toolstack: + * + * <domid>/<vhost>/vscsi-devs/dev-1/p-devname = "/dev/$device" + * <domid>/<vhost>/libxl_ctrl_index = "0" + * + * + * Backend/frontend protocol + * ========================= + * + * To create a vhost along with a device: + * <domid>/<vhost>/feature-host = "0" + * <domid>/<vhost>/frontend = "/local/domain/<domid>/device/vscsi/0" + * <domid>/<vhost>/frontend-id = "<domid>" + * <domid>/<vhost>/online = "1" + * <domid>/<vhost>/state = "1" + * <domid>/<vhost>/vscsi-devs/dev-0/p-dev = "8:0:2:1" + * <domid>/<vhost>/vscsi-devs/dev-0/state = "1" + * <domid>/<vhost>/vscsi-devs/dev-0/v-dev = "0:0:0:0" + * Wait for <domid>/<vhost>/state + <domid>/<vhost>/vscsi-devs/dev-0/state become 4 + * + * To add another device to a vhost: + * <domid>/<vhost>/state = "7" + * <domid>/<vhost>/vscsi-devs/dev-1/p-dev = "8:0:2:2" + * <domid>/<vhost>/vscsi-devs/dev-1/state = "1" + * <domid>/<vhost>/vscsi-devs/dev-1/v-dev = "0:0:1:0" + * Wait for <domid>/<vhost>/state + <domid>/<vhost>/vscsi-devs/dev-1/state become 4 + * + * To remove a device from a vhost: + * <domid>/<vhost>/state = "7" + * <domid>/<vhost>/vscsi-devs/dev-1/state = "5" + * Wait for <domid>/<vhost>/state to become 4 + * Wait for <domid>/<vhost>/vscsi-devs/dev-1/state become 6 + * Remove <domid>/<vhost>/vscsi-devs/dev-1/{state,p-dev,v-dev,p-devname} + * Remove <domid>/<vhost>/vscsi-devs/dev-1/ + * + */ + /* Requests from the frontend to the backend */ /* @@ -117,7 +186,8 @@ * (plus the set VSCSIIF_SG_GRANT bit), the number of scsiif_request_segment * elements referencing the target data buffers is calculated from the lengths * of the seg[] elements (the sum of all valid seg[].length divided by the - * size of one scsiif_request_segment structure). + * size of one scsiif_request_segment structure). The frontend may use a mix of + * direct and indirect requests. */ #define VSCSIIF_ACT_SCSI_CDB 1 @@ -154,12 +224,14 @@ /* * based on Linux kernel 2.6.18, still valid + * * Changing these values requires support of multiple protocols via the rings * as "old clients" will blindly use these values and the resulting structure * sizes. */ #define VSCSIIF_MAX_COMMAND_SIZE 16 #define VSCSIIF_SENSE_BUFFERSIZE 96 +#define VSCSIIF_PAGE_SIZE 4096 struct scsiif_request_segment { grant_ref_t gref; @@ -167,7 +239,8 @@ struct scsiif_request_segment { uint16_t length; }; -#define VSCSIIF_SG_PER_PAGE (PAGE_SIZE / sizeof(struct scsiif_request_segment)) +#define VSCSIIF_SG_PER_PAGE (VSCSIIF_PAGE_SIZE / \ + sizeof(struct scsiif_request_segment)) /* Size of one request is 252 bytes */ struct vscsiif_request { @@ -207,6 +280,58 @@ struct vscsiif_response { uint32_t reserved[36]; }; +/* SCSI I/O status from vscsiif_response->rslt */ +#define XEN_VSCSIIF_RSLT_STATUS(x) ((x) & 0x00ff) + +/* Host I/O status from vscsiif_response->rslt */ +#define XEN_VSCSIIF_RSLT_HOST(x) (((x) & 0x00ff0000) >> 16) +#define XEN_VSCSIIF_RSLT_HOST_OK 0 +/* Couldn't connect before timeout */ +#define XEN_VSCSIIF_RSLT_HOST_NO_CONNECT 1 +/* Bus busy through timeout */ +#define XEN_VSCSIIF_RSLT_HOST_BUS_BUSY 2 +/* Timed out for other reason */ +#define XEN_VSCSIIF_RSLT_HOST_TIME_OUT 3 +/* Bad target */ +#define XEN_VSCSIIF_RSLT_HOST_BAD_TARGET 4 +/* Abort for some other reason */ +#define XEN_VSCSIIF_RSLT_HOST_ABORT 5 +/* Parity error */ +#define XEN_VSCSIIF_RSLT_HOST_PARITY 6 +/* Internal error */ +#define XEN_VSCSIIF_RSLT_HOST_ERROR 7 +/* Reset by somebody */ +#define XEN_VSCSIIF_RSLT_HOST_RESET 8 +/* Unexpected interrupt */ +#define XEN_VSCSIIF_RSLT_HOST_BAD_INTR 9 +/* Force command past mid-layer */ +#define XEN_VSCSIIF_RSLT_HOST_PASSTHROUGH 10 +/* Retry requested */ +#define XEN_VSCSIIF_RSLT_HOST_SOFT_ERROR 11 +/* Hidden retry requested */ +#define XEN_VSCSIIF_RSLT_HOST_IMM_RETRY 12 +/* Requeue command requested */ +#define XEN_VSCSIIF_RSLT_HOST_REQUEUE 13 +/* Transport error disrupted I/O */ +#define XEN_VSCSIIF_RSLT_HOST_TRANSPORT_DISRUPTED 14 +/* Transport class fastfailed */ +#define XEN_VSCSIIF_RSLT_HOST_TRANSPORT_FAILFAST 15 +/* Permanent target failure */ +#define XEN_VSCSIIF_RSLT_HOST_TARGET_FAILURE 16 +/* Permanent nexus failure on path */ +#define XEN_VSCSIIF_RSLT_HOST_NEXUS_FAILURE 17 +/* Space allocation on device failed */ +#define XEN_VSCSIIF_RSLT_HOST_ALLOC_FAILURE 18 +/* Medium error */ +#define XEN_VSCSIIF_RSLT_HOST_MEDIUM_ERROR 19 +/* Transport marginal errors */ +#define XEN_VSCSIIF_RSLT_HOST_TRANSPORT_MARGINAL 20 + +/* Result values of reset operations */ +#define XEN_VSCSIIF_RSLT_RESET_SUCCESS 0x2002 +#define XEN_VSCSIIF_RSLT_RESET_FAILED 0x2003 + DEFINE_RING_TYPES(vscsiif, struct vscsiif_request, struct vscsiif_response); -#endif /*__XEN__PUBLIC_IO_SCSI_H__*/ + +#endif /*__XEN__PUBLIC_IO_SCSI_H__*/ diff --git a/include/xen/interface/io/xs_wire.h b/include/xen/interface/io/xs_wire.h index d40a44f09b16..b62365478ac0 100644 --- a/include/xen/interface/io/xs_wire.h +++ b/include/xen/interface/io/xs_wire.h @@ -10,7 +10,8 @@ enum xsd_sockmsg_type { - XS_DEBUG, + XS_CONTROL, +#define XS_DEBUG XS_CONTROL XS_DIRECTORY, XS_READ, XS_GET_PERMS, @@ -30,8 +31,13 @@ enum xsd_sockmsg_type XS_IS_DOMAIN_INTRODUCED, XS_RESUME, XS_SET_TARGET, - XS_RESTRICT, - XS_RESET_WATCHES, + /* XS_RESTRICT has been removed */ + XS_RESET_WATCHES = XS_SET_TARGET + 2, + XS_DIRECTORY_PART, + + XS_TYPE_COUNT, /* Number of valid types. */ + + XS_INVALID = 0xffff /* Guaranteed to remain an invalid type */ }; #define XS_WRITE_NONE "NONE" @@ -59,7 +65,8 @@ static struct xsd_errors xsd_errors[] __attribute__((unused)) = { XSD_ERROR(EROFS), XSD_ERROR(EBUSY), XSD_ERROR(EAGAIN), - XSD_ERROR(EISCONN) + XSD_ERROR(EISCONN), + XSD_ERROR(E2BIG) }; struct xsd_sockmsg @@ -87,9 +94,31 @@ struct xenstore_domain_interface { char rsp[XENSTORE_RING_SIZE]; /* Replies and async watch events. */ XENSTORE_RING_IDX req_cons, req_prod; XENSTORE_RING_IDX rsp_cons, rsp_prod; + uint32_t server_features; /* Bitmap of features supported by the server */ + uint32_t connection; + uint32_t error; }; /* Violating this is very bad. See docs/misc/xenstore.txt. */ #define XENSTORE_PAYLOAD_MAX 4096 +/* Violating these just gets you an error back */ +#define XENSTORE_ABS_PATH_MAX 3072 +#define XENSTORE_REL_PATH_MAX 2048 + +/* The ability to reconnect a ring */ +#define XENSTORE_SERVER_FEATURE_RECONNECTION 1 +/* The presence of the "error" field in the ring page */ +#define XENSTORE_SERVER_FEATURE_ERROR 2 + +/* Valid values for the connection field */ +#define XENSTORE_CONNECTED 0 /* the steady-state */ +#define XENSTORE_RECONNECT 1 /* guest has initiated a reconnect */ + +/* Valid values for the error field */ +#define XENSTORE_ERROR_NONE 0 /* No error */ +#define XENSTORE_ERROR_COMM 1 /* Communication problem */ +#define XENSTORE_ERROR_RINGIDX 2 /* Invalid ring index */ +#define XENSTORE_ERROR_PROTO 3 /* Protocol violation (payload too long) */ + #endif /* _XS_WIRE_H */ diff --git a/include/xen/xenbus.h b/include/xen/xenbus.h index b13eb86395e0..eaa932b99d8a 100644 --- a/include/xen/xenbus.h +++ b/include/xen/xenbus.h @@ -224,8 +224,10 @@ int xenbus_watch_pathfmt(struct xenbus_device *dev, struct xenbus_watch *watch, const char *pathfmt, ...); int xenbus_switch_state(struct xenbus_device *dev, enum xenbus_state new_state); -int xenbus_grant_ring(struct xenbus_device *dev, void *vaddr, +int xenbus_setup_ring(struct xenbus_device *dev, gfp_t gfp, void **vaddr, unsigned int nr_pages, grant_ref_t *grefs); +void xenbus_teardown_ring(void **vaddr, unsigned int nr_pages, + grant_ref_t *grefs); int xenbus_map_ring_valloc(struct xenbus_device *dev, grant_ref_t *gnt_refs, unsigned int nr_grefs, void **vaddr); diff --git a/init/Kconfig b/init/Kconfig index ddcbefe535e9..adc57f989d87 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1875,6 +1875,7 @@ config SLUB_DEBUG default y bool "Enable SLUB debugging support" if EXPERT depends on SLUB && SYSFS + select STACKDEPOT if STACKTRACE_SUPPORT help SLUB has extensive debug support features. Disabling these can result in significant savings in code size. This also disables diff --git a/init/main.c b/init/main.c index 98182c3c2c4b..f057c49f1d9d 100644 --- a/init/main.c +++ b/init/main.c @@ -1035,21 +1035,18 @@ asmlinkage __visible void __init __no_sanitize_address start_kernel(void) softirq_init(); timekeeping_init(); kfence_init(); + time_init(); /* * For best initial stack canary entropy, prepare it after: * - setup_arch() for any UEFI RNG entropy and boot cmdline access - * - timekeeping_init() for ktime entropy used in rand_initialize() - * - rand_initialize() to get any arch-specific entropy like RDRAND - * - add_latent_entropy() to get any latent entropy - * - adding command line entropy + * - timekeeping_init() for ktime entropy used in random_init() + * - time_init() for making random_get_entropy() work on some platforms + * - random_init() to initialize the RNG from from early entropy sources */ - rand_initialize(); - add_latent_entropy(); - add_device_randomness(command_line, strlen(command_line)); + random_init(command_line); boot_init_stack_canary(); - time_init(); perf_event_init(); profile_init(); call_function_init(); diff --git a/kernel/Makefile b/kernel/Makefile index 471d71935e90..847a82bfe0e3 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -114,7 +114,8 @@ obj-$(CONFIG_CPU_PM) += cpu_pm.o obj-$(CONFIG_BPF) += bpf/ obj-$(CONFIG_KCSAN) += kcsan/ obj-$(CONFIG_SHADOW_CALL_STACK) += scs.o -obj-$(CONFIG_HAVE_STATIC_CALL_INLINE) += static_call.o +obj-$(CONFIG_HAVE_STATIC_CALL) += static_call.o +obj-$(CONFIG_HAVE_STATIC_CALL_INLINE) += static_call_inline.o obj-$(CONFIG_CFI_CLANG) += cfi.o obj-$(CONFIG_PERF_EVENTS) += events/ diff --git a/kernel/auditsc.c b/kernel/auditsc.c index ea2ee1181921..f3a2abd6d1a1 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -1959,6 +1959,12 @@ void __audit_uring_exit(int success, long code) { struct audit_context *ctx = audit_context(); + if (ctx->dummy) { + if (ctx->context != AUDIT_CTX_URING) + return; + goto out; + } + if (ctx->context == AUDIT_CTX_SYSCALL) { /* * NOTE: See the note in __audit_uring_entry() about the case diff --git a/kernel/bpf/Kconfig b/kernel/bpf/Kconfig index d56ee177d5f8..2dfe1079f772 100644 --- a/kernel/bpf/Kconfig +++ b/kernel/bpf/Kconfig @@ -27,6 +27,7 @@ config BPF_SYSCALL bool "Enable bpf() system call" select BPF select IRQ_WORK + select TASKS_RCU if PREEMPTION select TASKS_TRACE_RCU select BINARY_PRINTF select NET_SOCK_MSG if NET diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 9390bfd9f1cd..71a418858a5e 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -3390,8 +3390,11 @@ static struct notifier_block cpuset_track_online_nodes_nb = { */ void __init cpuset_init_smp(void) { - cpumask_copy(top_cpuset.cpus_allowed, cpu_active_mask); - top_cpuset.mems_allowed = node_states[N_MEMORY]; + /* + * cpus_allowd/mems_allowed set to v2 values in the initial + * cpuset_bind() call will be reset to v1 values in another + * cpuset_bind() call when v1 cpuset is mounted. + */ top_cpuset.old_mems_allowed = top_cpuset.mems_allowed; cpumask_copy(top_cpuset.effective_cpus, cpu_active_mask); diff --git a/kernel/configs/x86_debug.config b/kernel/configs/x86_debug.config new file mode 100644 index 000000000000..dcd86f32f4ed --- /dev/null +++ b/kernel/configs/x86_debug.config @@ -0,0 +1,18 @@ +CONFIG_X86_DEBUG_FPU=y +CONFIG_LOCK_STAT=y +CONFIG_DEBUG_VM=y +CONFIG_DEBUG_VM_VMACACHE=y +CONFIG_DEBUG_VM_RB=y +CONFIG_DEBUG_SLAB=y +CONFIG_DEBUG_KMEMLEAK=y +CONFIG_DEBUG_PAGEALLOC=y +CONFIG_SLUB_DEBUG_ON=y +CONFIG_KMEMCHECK=y +CONFIG_DEBUG_OBJECTS=y +CONFIG_DEBUG_OBJECTS_ENABLE_DEFAULT=1 +CONFIG_GCOV_KERNEL=y +CONFIG_LOCKDEP=y +CONFIG_PROVE_LOCKING=y +CONFIG_SCHEDSTATS=y +CONFIG_VMLINUX_VALIDATION=y +CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y diff --git a/kernel/cpu.c b/kernel/cpu.c index 5797c2a7a93f..bbad5e375d3b 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -35,6 +35,7 @@ #include <linux/percpu-rwsem.h> #include <linux/cpuset.h> #include <linux/random.h> +#include <linux/cc_platform.h> #include <trace/events/power.h> #define CREATE_TRACE_POINTS @@ -71,7 +72,6 @@ struct cpuhp_cpu_state { bool rollback; bool single; bool bringup; - int cpu; struct hlist_node *node; struct hlist_node *last; enum cpuhp_state cb_state; @@ -475,7 +475,7 @@ static inline bool cpu_smt_allowed(unsigned int cpu) { return true; } #endif static inline enum cpuhp_state -cpuhp_set_state(struct cpuhp_cpu_state *st, enum cpuhp_state target) +cpuhp_set_state(int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state target) { enum cpuhp_state prev_state = st->state; bool bringup = st->state < target; @@ -486,14 +486,15 @@ cpuhp_set_state(struct cpuhp_cpu_state *st, enum cpuhp_state target) st->target = target; st->single = false; st->bringup = bringup; - if (cpu_dying(st->cpu) != !bringup) - set_cpu_dying(st->cpu, !bringup); + if (cpu_dying(cpu) != !bringup) + set_cpu_dying(cpu, !bringup); return prev_state; } static inline void -cpuhp_reset_state(struct cpuhp_cpu_state *st, enum cpuhp_state prev_state) +cpuhp_reset_state(int cpu, struct cpuhp_cpu_state *st, + enum cpuhp_state prev_state) { bool bringup = !st->bringup; @@ -520,8 +521,8 @@ cpuhp_reset_state(struct cpuhp_cpu_state *st, enum cpuhp_state prev_state) } st->bringup = bringup; - if (cpu_dying(st->cpu) != !bringup) - set_cpu_dying(st->cpu, !bringup); + if (cpu_dying(cpu) != !bringup) + set_cpu_dying(cpu, !bringup); } /* Regular hotplug invocation of the AP hotplug thread */ @@ -541,15 +542,16 @@ static void __cpuhp_kick_ap(struct cpuhp_cpu_state *st) wait_for_ap_thread(st, st->bringup); } -static int cpuhp_kick_ap(struct cpuhp_cpu_state *st, enum cpuhp_state target) +static int cpuhp_kick_ap(int cpu, struct cpuhp_cpu_state *st, + enum cpuhp_state target) { enum cpuhp_state prev_state; int ret; - prev_state = cpuhp_set_state(st, target); + prev_state = cpuhp_set_state(cpu, st, target); __cpuhp_kick_ap(st); if ((ret = st->result)) { - cpuhp_reset_state(st, prev_state); + cpuhp_reset_state(cpu, st, prev_state); __cpuhp_kick_ap(st); } @@ -581,7 +583,7 @@ static int bringup_wait_for_ap(unsigned int cpu) if (st->target <= CPUHP_AP_ONLINE_IDLE) return 0; - return cpuhp_kick_ap(st, st->target); + return cpuhp_kick_ap(cpu, st, st->target); } static int bringup_cpu(unsigned int cpu) @@ -704,7 +706,7 @@ static int cpuhp_up_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, ret, cpu, cpuhp_get_step(st->state)->name, st->state); - cpuhp_reset_state(st, prev_state); + cpuhp_reset_state(cpu, st, prev_state); if (can_rollback_cpu(st)) WARN_ON(cpuhp_invoke_callback_range(false, cpu, st, prev_state)); @@ -715,15 +717,6 @@ static int cpuhp_up_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, /* * The cpu hotplug threads manage the bringup and teardown of the cpus */ -static void cpuhp_create(unsigned int cpu) -{ - struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); - - init_completion(&st->done_up); - init_completion(&st->done_down); - st->cpu = cpu; -} - static int cpuhp_should_run(unsigned int cpu) { struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); @@ -875,7 +868,7 @@ static int cpuhp_kick_ap_work(unsigned int cpu) cpuhp_lock_release(true); trace_cpuhp_enter(cpu, st->target, prev_state, cpuhp_kick_ap_work); - ret = cpuhp_kick_ap(st, st->target); + ret = cpuhp_kick_ap(cpu, st, st->target); trace_cpuhp_exit(cpu, st->state, prev_state, ret); return ret; @@ -883,15 +876,27 @@ static int cpuhp_kick_ap_work(unsigned int cpu) static struct smp_hotplug_thread cpuhp_threads = { .store = &cpuhp_state.thread, - .create = &cpuhp_create, .thread_should_run = cpuhp_should_run, .thread_fn = cpuhp_thread_fun, .thread_comm = "cpuhp/%u", .selfparking = true, }; +static __init void cpuhp_init_state(void) +{ + struct cpuhp_cpu_state *st; + int cpu; + + for_each_possible_cpu(cpu) { + st = per_cpu_ptr(&cpuhp_state, cpu); + init_completion(&st->done_up); + init_completion(&st->done_down); + } +} + void __init cpuhp_threads_init(void) { + cpuhp_init_state(); BUG_ON(smpboot_register_percpu_thread(&cpuhp_threads)); kthread_unpark(this_cpu_read(cpuhp_state.thread)); } @@ -1107,7 +1112,7 @@ static int cpuhp_down_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, ret, cpu, cpuhp_get_step(st->state)->name, st->state); - cpuhp_reset_state(st, prev_state); + cpuhp_reset_state(cpu, st, prev_state); if (st->state < prev_state) WARN_ON(cpuhp_invoke_callback_range(true, cpu, st, @@ -1134,7 +1139,7 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, cpuhp_tasks_frozen = tasks_frozen; - prev_state = cpuhp_set_state(st, target); + prev_state = cpuhp_set_state(cpu, st, target); /* * If the current CPU state is in the range of the AP hotplug thread, * then we need to kick the thread. @@ -1165,7 +1170,7 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, ret = cpuhp_down_callbacks(cpu, st, target); if (ret && st->state < prev_state) { if (st->state == CPUHP_TEARDOWN_CPU) { - cpuhp_reset_state(st, prev_state); + cpuhp_reset_state(cpu, st, prev_state); __cpuhp_kick_ap(st); } else { WARN(1, "DEAD callback error for CPU%d", cpu); @@ -1186,6 +1191,12 @@ out: static int cpu_down_maps_locked(unsigned int cpu, enum cpuhp_state target) { + /* + * If the platform does not support hotplug, report it explicitly to + * differentiate it from a transient offlining failure. + */ + if (cc_platform_has(CC_ATTR_HOTPLUG_DISABLED)) + return -EOPNOTSUPP; if (cpu_hotplug_disabled) return -EBUSY; return _cpu_down(cpu, 0, target); @@ -1352,7 +1363,7 @@ static int _cpu_up(unsigned int cpu, int tasks_frozen, enum cpuhp_state target) cpuhp_tasks_frozen = tasks_frozen; - cpuhp_set_state(st, target); + cpuhp_set_state(cpu, st, target); /* * If the current CPU state is in the range of the AP hotplug thread, * then we need to kick the thread once more. diff --git a/kernel/crash_core.c b/kernel/crash_core.c index 256cf6db573c..4d57c03714f4 100644 --- a/kernel/crash_core.c +++ b/kernel/crash_core.c @@ -243,9 +243,8 @@ static int __init __parse_crashkernel(char *cmdline, *crash_base = 0; ck_cmdline = get_last_crashkernel(cmdline, name, suffix); - if (!ck_cmdline) - return -EINVAL; + return -ENOENT; ck_cmdline += strlen(name); diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c index da06a5553835..7beceb447211 100644 --- a/kernel/debug/debug_core.c +++ b/kernel/debug/debug_core.c @@ -53,6 +53,7 @@ #include <linux/vmacache.h> #include <linux/rcupdate.h> #include <linux/irq.h> +#include <linux/security.h> #include <asm/cacheflush.h> #include <asm/byteorder.h> @@ -752,6 +753,29 @@ cpu_master_loop: continue; kgdb_connected = 0; } else { + /* + * This is a brutal way to interfere with the debugger + * and prevent gdb being used to poke at kernel memory. + * This could cause trouble if lockdown is applied when + * there is already an active gdb session. For now the + * answer is simply "don't do that". Typically lockdown + * *will* be applied before the debug core gets started + * so only developers using kgdb for fairly advanced + * early kernel debug can be biten by this. Hopefully + * they are sophisticated enough to take care of + * themselves, especially with help from the lockdown + * message printed on the console! + */ + if (security_locked_down(LOCKDOWN_DBG_WRITE_KERNEL)) { + if (IS_ENABLED(CONFIG_KGDB_KDB)) { + /* Switch back to kdb if possible... */ + dbg_kdb_mode = 1; + continue; + } else { + /* ... otherwise just bail */ + break; + } + } error = gdb_serial_stub(ks); } diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index 0852a537dad4..ead4da947127 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -45,6 +45,7 @@ #include <linux/proc_fs.h> #include <linux/uaccess.h> #include <linux/slab.h> +#include <linux/security.h> #include "kdb_private.h" #undef MODULE_PARAM_PREFIX @@ -166,10 +167,62 @@ struct task_struct *kdb_curr_task(int cpu) } /* - * Check whether the flags of the current command and the permissions - * of the kdb console has allow a command to be run. + * Update the permissions flags (kdb_cmd_enabled) to match the + * current lockdown state. + * + * Within this function the calls to security_locked_down() are "lazy". We + * avoid calling them if the current value of kdb_cmd_enabled already excludes + * flags that might be subject to lockdown. Additionally we deliberately check + * the lockdown flags independently (even though read lockdown implies write + * lockdown) since that results in both simpler code and clearer messages to + * the user on first-time debugger entry. + * + * The permission masks during a read+write lockdown permits the following + * flags: INSPECT, SIGNAL, REBOOT (and ALWAYS_SAFE). + * + * The INSPECT commands are not blocked during lockdown because they are + * not arbitrary memory reads. INSPECT covers the backtrace family (sometimes + * forcing them to have no arguments) and lsmod. These commands do expose + * some kernel state but do not allow the developer seated at the console to + * choose what state is reported. SIGNAL and REBOOT should not be controversial, + * given these are allowed for root during lockdown already. + */ +static void kdb_check_for_lockdown(void) +{ + const int write_flags = KDB_ENABLE_MEM_WRITE | + KDB_ENABLE_REG_WRITE | + KDB_ENABLE_FLOW_CTRL; + const int read_flags = KDB_ENABLE_MEM_READ | + KDB_ENABLE_REG_READ; + + bool need_to_lockdown_write = false; + bool need_to_lockdown_read = false; + + if (kdb_cmd_enabled & (KDB_ENABLE_ALL | write_flags)) + need_to_lockdown_write = + security_locked_down(LOCKDOWN_DBG_WRITE_KERNEL); + + if (kdb_cmd_enabled & (KDB_ENABLE_ALL | read_flags)) + need_to_lockdown_read = + security_locked_down(LOCKDOWN_DBG_READ_KERNEL); + + /* De-compose KDB_ENABLE_ALL if required */ + if (need_to_lockdown_write || need_to_lockdown_read) + if (kdb_cmd_enabled & KDB_ENABLE_ALL) + kdb_cmd_enabled = KDB_ENABLE_MASK & ~KDB_ENABLE_ALL; + + if (need_to_lockdown_write) + kdb_cmd_enabled &= ~write_flags; + + if (need_to_lockdown_read) + kdb_cmd_enabled &= ~read_flags; +} + +/* + * Check whether the flags of the current command, the permissions of the kdb + * console and the lockdown state allow a command to be run. */ -static inline bool kdb_check_flags(kdb_cmdflags_t flags, int permissions, +static bool kdb_check_flags(kdb_cmdflags_t flags, int permissions, bool no_args) { /* permissions comes from userspace so needs massaging slightly */ @@ -1180,6 +1233,9 @@ static int kdb_local(kdb_reason_t reason, int error, struct pt_regs *regs, kdb_curr_task(raw_smp_processor_id()); KDB_DEBUG_STATE("kdb_local 1", reason); + + kdb_check_for_lockdown(); + kdb_go_count = 0; if (reason == KDB_REASON_DEBUG) { /* special case below */ diff --git a/kernel/dma/direct.h b/kernel/dma/direct.h index 4632b0f4f72e..8a6cd53dbe8c 100644 --- a/kernel/dma/direct.h +++ b/kernel/dma/direct.h @@ -114,6 +114,7 @@ static inline void dma_direct_unmap_page(struct device *dev, dma_addr_t addr, dma_direct_sync_single_for_cpu(dev, addr, size, dir); if (unlikely(is_swiotlb_buffer(dev, phys))) - swiotlb_tbl_unmap_single(dev, phys, size, dir, attrs); + swiotlb_tbl_unmap_single(dev, phys, size, dir, + attrs | DMA_ATTR_SKIP_CPU_SYNC); } #endif /* _KERNEL_DMA_DIRECT_H */ diff --git a/kernel/entry/common.c b/kernel/entry/common.c index e57a224d6b79..032f164abe7c 100644 --- a/kernel/entry/common.c +++ b/kernel/entry/common.c @@ -17,7 +17,7 @@ /* See comment for enter_from_user_mode() in entry-common.h */ static __always_inline void __enter_from_user_mode(struct pt_regs *regs) { - arch_check_user_regs(regs); + arch_enter_from_user_mode(regs); lockdep_hardirqs_off(CALLER_ADDR0); CT_WARN_ON(ct_state() != CONTEXT_USER); @@ -126,7 +126,7 @@ static __always_inline void __exit_to_user_mode(void) { instrumentation_begin(); trace_hardirqs_on_prepare(); - lockdep_hardirqs_on_prepare(CALLER_ADDR0); + lockdep_hardirqs_on_prepare(); instrumentation_end(); user_enter_irqoff(); @@ -392,7 +392,7 @@ DEFINE_STATIC_CALL(irqentry_exit_cond_resched, raw_irqentry_exit_cond_resched); DEFINE_STATIC_KEY_TRUE(sk_dynamic_irqentry_exit_cond_resched); void dynamic_irqentry_exit_cond_resched(void) { - if (!static_key_unlikely(&sk_dynamic_irqentry_exit_cond_resched)) + if (!static_branch_unlikely(&sk_dynamic_irqentry_exit_cond_resched)) return; raw_irqentry_exit_cond_resched(); } @@ -416,7 +416,7 @@ noinstr void irqentry_exit(struct pt_regs *regs, irqentry_state_t state) instrumentation_begin(); /* Tell the tracer that IRET will enable interrupts */ trace_hardirqs_on_prepare(); - lockdep_hardirqs_on_prepare(CALLER_ADDR0); + lockdep_hardirqs_on_prepare(); instrumentation_end(); rcu_irq_exit(); lockdep_hardirqs_on(CALLER_ADDR0); @@ -465,7 +465,7 @@ void noinstr irqentry_nmi_exit(struct pt_regs *regs, irqentry_state_t irq_state) ftrace_nmi_exit(); if (irq_state.lockdep) { trace_hardirqs_on_prepare(); - lockdep_hardirqs_on_prepare(CALLER_ADDR0); + lockdep_hardirqs_on_prepare(); } instrumentation_end(); diff --git a/kernel/events/core.c b/kernel/events/core.c index cfde994ce61c..950b25c3f210 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -574,8 +574,7 @@ static void cpu_ctx_sched_out(struct perf_cpu_context *cpuctx, enum event_type_t event_type); static void cpu_ctx_sched_in(struct perf_cpu_context *cpuctx, - enum event_type_t event_type, - struct task_struct *task); + enum event_type_t event_type); static void update_context_time(struct perf_event_context *ctx); static u64 perf_event_time(struct perf_event *event); @@ -781,7 +780,6 @@ static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx, static inline void update_cgrp_time_from_event(struct perf_event *event) { struct perf_cgroup_info *info; - struct perf_cgroup *cgrp; /* * ensure we access cgroup data only when needed and @@ -790,21 +788,19 @@ static inline void update_cgrp_time_from_event(struct perf_event *event) if (!is_cgroup_event(event)) return; - cgrp = perf_cgroup_from_task(current, event->ctx); + info = this_cpu_ptr(event->cgrp->info); /* * Do not update time when cgroup is not active */ - if (cgroup_is_descendant(cgrp->css.cgroup, event->cgrp->css.cgroup)) { - info = this_cpu_ptr(event->cgrp->info); + if (info->active) __update_cgrp_time(info, perf_clock(), true); - } } static inline void -perf_cgroup_set_timestamp(struct task_struct *task, - struct perf_event_context *ctx) +perf_cgroup_set_timestamp(struct perf_cpu_context *cpuctx) { - struct perf_cgroup *cgrp; + struct perf_event_context *ctx = &cpuctx->ctx; + struct perf_cgroup *cgrp = cpuctx->cgrp; struct perf_cgroup_info *info; struct cgroup_subsys_state *css; @@ -813,10 +809,10 @@ perf_cgroup_set_timestamp(struct task_struct *task, * ensure we do not access cgroup data * unless we have the cgroup pinned (css_get) */ - if (!task || !ctx->nr_cgroups) + if (!cgrp) return; - cgrp = perf_cgroup_from_task(task, ctx); + WARN_ON_ONCE(!ctx->nr_cgroups); for (css = &cgrp->css; css; css = css->parent) { cgrp = container_of(css, struct perf_cgroup, css); @@ -828,17 +824,12 @@ perf_cgroup_set_timestamp(struct task_struct *task, static DEFINE_PER_CPU(struct list_head, cgrp_cpuctx_list); -#define PERF_CGROUP_SWOUT 0x1 /* cgroup switch out every event */ -#define PERF_CGROUP_SWIN 0x2 /* cgroup switch in events based on task */ - /* * reschedule events based on the cgroup constraint of task. - * - * mode SWOUT : schedule out everything - * mode SWIN : schedule in based on cgroup for next */ -static void perf_cgroup_switch(struct task_struct *task, int mode) +static void perf_cgroup_switch(struct task_struct *task) { + struct perf_cgroup *cgrp; struct perf_cpu_context *cpuctx, *tmp; struct list_head *list; unsigned long flags; @@ -849,35 +840,31 @@ static void perf_cgroup_switch(struct task_struct *task, int mode) */ local_irq_save(flags); + cgrp = perf_cgroup_from_task(task, NULL); + list = this_cpu_ptr(&cgrp_cpuctx_list); list_for_each_entry_safe(cpuctx, tmp, list, cgrp_cpuctx_entry) { WARN_ON_ONCE(cpuctx->ctx.nr_cgroups == 0); + if (READ_ONCE(cpuctx->cgrp) == cgrp) + continue; perf_ctx_lock(cpuctx, cpuctx->task_ctx); perf_pmu_disable(cpuctx->ctx.pmu); - if (mode & PERF_CGROUP_SWOUT) { - cpu_ctx_sched_out(cpuctx, EVENT_ALL); - /* - * must not be done before ctxswout due - * to event_filter_match() in event_sched_out() - */ - cpuctx->cgrp = NULL; - } + cpu_ctx_sched_out(cpuctx, EVENT_ALL); + /* + * must not be done before ctxswout due + * to update_cgrp_time_from_cpuctx() in + * ctx_sched_out() + */ + cpuctx->cgrp = cgrp; + /* + * set cgrp before ctxsw in to allow + * perf_cgroup_set_timestamp() in ctx_sched_in() + * to not have to pass task around + */ + cpu_ctx_sched_in(cpuctx, EVENT_ALL); - if (mode & PERF_CGROUP_SWIN) { - WARN_ON_ONCE(cpuctx->cgrp); - /* - * set cgrp before ctxsw in to allow - * event_filter_match() to not have to pass - * task around - * we pass the cpuctx->ctx to perf_cgroup_from_task() - * because cgorup events are only per-cpu - */ - cpuctx->cgrp = perf_cgroup_from_task(task, - &cpuctx->ctx); - cpu_ctx_sched_in(cpuctx, EVENT_ALL, task); - } perf_pmu_enable(cpuctx->ctx.pmu); perf_ctx_unlock(cpuctx, cpuctx->task_ctx); } @@ -885,58 +872,6 @@ static void perf_cgroup_switch(struct task_struct *task, int mode) local_irq_restore(flags); } -static inline void perf_cgroup_sched_out(struct task_struct *task, - struct task_struct *next) -{ - struct perf_cgroup *cgrp1; - struct perf_cgroup *cgrp2 = NULL; - - rcu_read_lock(); - /* - * we come here when we know perf_cgroup_events > 0 - * we do not need to pass the ctx here because we know - * we are holding the rcu lock - */ - cgrp1 = perf_cgroup_from_task(task, NULL); - cgrp2 = perf_cgroup_from_task(next, NULL); - - /* - * only schedule out current cgroup events if we know - * that we are switching to a different cgroup. Otherwise, - * do no touch the cgroup events. - */ - if (cgrp1 != cgrp2) - perf_cgroup_switch(task, PERF_CGROUP_SWOUT); - - rcu_read_unlock(); -} - -static inline void perf_cgroup_sched_in(struct task_struct *prev, - struct task_struct *task) -{ - struct perf_cgroup *cgrp1; - struct perf_cgroup *cgrp2 = NULL; - - rcu_read_lock(); - /* - * we come here when we know perf_cgroup_events > 0 - * we do not need to pass the ctx here because we know - * we are holding the rcu lock - */ - cgrp1 = perf_cgroup_from_task(task, NULL); - cgrp2 = perf_cgroup_from_task(prev, NULL); - - /* - * only need to schedule in cgroup events if we are changing - * cgroup during ctxsw. Cgroup events were not scheduled - * out of ctxsw out if that was not the case. - */ - if (cgrp1 != cgrp2) - perf_cgroup_switch(task, PERF_CGROUP_SWIN); - - rcu_read_unlock(); -} - static int perf_cgroup_ensure_storage(struct perf_event *event, struct cgroup_subsys_state *css) { @@ -1032,22 +967,10 @@ perf_cgroup_event_enable(struct perf_event *event, struct perf_event_context *ct */ cpuctx = container_of(ctx, struct perf_cpu_context, ctx); - /* - * Since setting cpuctx->cgrp is conditional on the current @cgrp - * matching the event's cgroup, we must do this for every new event, - * because if the first would mismatch, the second would not try again - * and we would leave cpuctx->cgrp unset. - */ - if (ctx->is_active && !cpuctx->cgrp) { - struct perf_cgroup *cgrp = perf_cgroup_from_task(current, ctx); - - if (cgroup_is_descendant(cgrp->css.cgroup, event->cgrp->css.cgroup)) - cpuctx->cgrp = cgrp; - } - if (ctx->nr_cgroups++) return; + cpuctx->cgrp = perf_cgroup_from_task(current, ctx); list_add(&cpuctx->cgrp_cpuctx_entry, per_cpu_ptr(&cgrp_cpuctx_list, event->cpu)); } @@ -1069,9 +992,7 @@ perf_cgroup_event_disable(struct perf_event *event, struct perf_event_context *c if (--ctx->nr_cgroups) return; - if (ctx->is_active && cpuctx->cgrp) - cpuctx->cgrp = NULL; - + cpuctx->cgrp = NULL; list_del(&cpuctx->cgrp_cpuctx_entry); } @@ -1100,16 +1021,6 @@ static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx, { } -static inline void perf_cgroup_sched_out(struct task_struct *task, - struct task_struct *next) -{ -} - -static inline void perf_cgroup_sched_in(struct task_struct *prev, - struct task_struct *task) -{ -} - static inline int perf_cgroup_connect(pid_t pid, struct perf_event *event, struct perf_event_attr *attr, struct perf_event *group_leader) @@ -1118,13 +1029,7 @@ static inline int perf_cgroup_connect(pid_t pid, struct perf_event *event, } static inline void -perf_cgroup_set_timestamp(struct task_struct *task, - struct perf_event_context *ctx) -{ -} - -static inline void -perf_cgroup_switch(struct task_struct *task, struct task_struct *next) +perf_cgroup_set_timestamp(struct perf_cpu_context *cpuctx) { } @@ -1147,6 +1052,10 @@ static inline void perf_cgroup_event_disable(struct perf_event *event, struct perf_event_context *ctx) { } + +static void perf_cgroup_switch(struct task_struct *task) +{ +} #endif /* @@ -2713,8 +2622,7 @@ static void ctx_sched_out(struct perf_event_context *ctx, static void ctx_sched_in(struct perf_event_context *ctx, struct perf_cpu_context *cpuctx, - enum event_type_t event_type, - struct task_struct *task); + enum event_type_t event_type); static void task_ctx_sched_out(struct perf_cpu_context *cpuctx, struct perf_event_context *ctx, @@ -2730,15 +2638,14 @@ static void task_ctx_sched_out(struct perf_cpu_context *cpuctx, } static void perf_event_sched_in(struct perf_cpu_context *cpuctx, - struct perf_event_context *ctx, - struct task_struct *task) + struct perf_event_context *ctx) { - cpu_ctx_sched_in(cpuctx, EVENT_PINNED, task); + cpu_ctx_sched_in(cpuctx, EVENT_PINNED); if (ctx) - ctx_sched_in(ctx, cpuctx, EVENT_PINNED, task); - cpu_ctx_sched_in(cpuctx, EVENT_FLEXIBLE, task); + ctx_sched_in(ctx, cpuctx, EVENT_PINNED); + cpu_ctx_sched_in(cpuctx, EVENT_FLEXIBLE); if (ctx) - ctx_sched_in(ctx, cpuctx, EVENT_FLEXIBLE, task); + ctx_sched_in(ctx, cpuctx, EVENT_FLEXIBLE); } /* @@ -2788,7 +2695,7 @@ static void ctx_resched(struct perf_cpu_context *cpuctx, else if (ctx_event_type & EVENT_PINNED) cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE); - perf_event_sched_in(cpuctx, task_ctx, current); + perf_event_sched_in(cpuctx, task_ctx); perf_pmu_enable(cpuctx->ctx.pmu); } @@ -3011,7 +2918,7 @@ static void __perf_event_enable(struct perf_event *event, return; if (!event_filter_match(event)) { - ctx_sched_in(ctx, cpuctx, EVENT_TIME, current); + ctx_sched_in(ctx, cpuctx, EVENT_TIME); return; } @@ -3020,7 +2927,7 @@ static void __perf_event_enable(struct perf_event *event, * then don't put it on unless the group is on. */ if (leader != event && leader->state != PERF_EVENT_STATE_ACTIVE) { - ctx_sched_in(ctx, cpuctx, EVENT_TIME, current); + ctx_sched_in(ctx, cpuctx, EVENT_TIME); return; } @@ -3668,7 +3575,7 @@ void __perf_event_task_sched_out(struct task_struct *task, * cgroup event are system-wide mode only */ if (atomic_read(this_cpu_ptr(&perf_cgroup_events))) - perf_cgroup_sched_out(task, next); + perf_cgroup_switch(next); } /* @@ -3865,8 +3772,7 @@ ctx_flexible_sched_in(struct perf_event_context *ctx, static void ctx_sched_in(struct perf_event_context *ctx, struct perf_cpu_context *cpuctx, - enum event_type_t event_type, - struct task_struct *task) + enum event_type_t event_type) { int is_active = ctx->is_active; @@ -3878,7 +3784,7 @@ ctx_sched_in(struct perf_event_context *ctx, if (is_active ^ EVENT_TIME) { /* start ctx time */ __update_context_time(ctx, false); - perf_cgroup_set_timestamp(task, ctx); + perf_cgroup_set_timestamp(cpuctx); /* * CPU-release for the below ->is_active store, * see __load_acquire() in perf_event_time_now() @@ -3909,12 +3815,11 @@ ctx_sched_in(struct perf_event_context *ctx, } static void cpu_ctx_sched_in(struct perf_cpu_context *cpuctx, - enum event_type_t event_type, - struct task_struct *task) + enum event_type_t event_type) { struct perf_event_context *ctx = &cpuctx->ctx; - ctx_sched_in(ctx, cpuctx, event_type, task); + ctx_sched_in(ctx, cpuctx, event_type); } static void perf_event_context_sched_in(struct perf_event_context *ctx, @@ -3956,7 +3861,7 @@ static void perf_event_context_sched_in(struct perf_event_context *ctx, */ if (!RB_EMPTY_ROOT(&ctx->pinned_groups.tree)) cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE); - perf_event_sched_in(cpuctx, ctx, task); + perf_event_sched_in(cpuctx, ctx); if (cpuctx->sched_cb_usage && pmu->sched_task) pmu->sched_task(cpuctx->task_ctx, true); @@ -3984,16 +3889,6 @@ void __perf_event_task_sched_in(struct task_struct *prev, struct perf_event_context *ctx; int ctxn; - /* - * If cgroup events exist on this CPU, then we need to check if we have - * to switch in PMU state; cgroup event are system-wide mode only. - * - * Since cgroup events are CPU events, we must schedule these in before - * we schedule in the task events. - */ - if (atomic_read(this_cpu_ptr(&perf_cgroup_events))) - perf_cgroup_sched_in(prev, task); - for_each_task_context_nr(ctxn) { ctx = task->perf_event_ctxp[ctxn]; if (likely(!ctx)) @@ -4267,7 +4162,7 @@ static bool perf_rotate_context(struct perf_cpu_context *cpuctx) if (cpu_event) rotate_ctx(&cpuctx->ctx, cpu_event); - perf_event_sched_in(cpuctx, task_ctx, current); + perf_event_sched_in(cpuctx, task_ctx); perf_pmu_enable(cpuctx->ctx.pmu); perf_ctx_unlock(cpuctx, cpuctx->task_ctx); @@ -4339,7 +4234,7 @@ static void perf_event_enable_on_exec(int ctxn) clone_ctx = unclone_ctx(ctx); ctx_resched(cpuctx, ctx, event_type); } else { - ctx_sched_in(ctx, cpuctx, EVENT_TIME, current); + ctx_sched_in(ctx, cpuctx, EVENT_TIME); } perf_ctx_unlock(cpuctx, ctx); @@ -6352,7 +6247,7 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma) again: mutex_lock(&event->mmap_mutex); if (event->rb) { - if (event->rb->nr_pages != nr_pages) { + if (data_page_nr(event->rb) != nr_pages) { ret = -EINVAL; goto unlock; } @@ -6533,8 +6428,8 @@ static void perf_sigtrap(struct perf_event *event) if (current->flags & PF_EXITING) return; - force_sig_perf((void __user *)event->pending_addr, - event->attr.type, event->attr.sig_data); + send_sig_perf((void __user *)event->pending_addr, + event->attr.type, event->attr.sig_data); } static void perf_pending_event_disable(struct perf_event *event) @@ -11635,6 +11530,9 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, event->state = PERF_EVENT_STATE_INACTIVE; + if (parent_event) + event->event_caps = parent_event->event_caps; + if (event->attr.sigtrap) atomic_set(&event->event_limit, 1); @@ -12319,6 +12217,9 @@ SYSCALL_DEFINE5(perf_event_open, * Do not allow to attach to a group in a different task * or CPU context. If we're moving SW events, we'll fix * this up later, so allow that. + * + * Racy, not holding group_leader->ctx->mutex, see comment with + * perf_event_ctx_lock(). */ if (!move_group && group_leader->ctx != ctx) goto err_context; @@ -12384,6 +12285,7 @@ SYSCALL_DEFINE5(perf_event_open, } else { perf_event_ctx_unlock(group_leader, gctx); move_group = 0; + goto not_move_group; } } @@ -12400,7 +12302,17 @@ SYSCALL_DEFINE5(perf_event_open, } } else { mutex_lock(&ctx->mutex); + + /* + * Now that we hold ctx->lock, (re)validate group_leader->ctx == ctx, + * see the group_leader && !move_group test earlier. + */ + if (group_leader && group_leader->ctx != ctx) { + err = -EINVAL; + goto err_locked; + } } +not_move_group: if (ctx->task == TASK_TOMBSTONE) { err = -ESRCH; @@ -13562,7 +13474,7 @@ static int __perf_cgroup_move(void *info) { struct task_struct *task = info; rcu_read_lock(); - perf_cgroup_switch(task, PERF_CGROUP_SWOUT | PERF_CGROUP_SWIN); + perf_cgroup_switch(task); rcu_read_unlock(); return 0; } diff --git a/kernel/events/internal.h b/kernel/events/internal.h index 082832738c8f..5150d5f84c03 100644 --- a/kernel/events/internal.h +++ b/kernel/events/internal.h @@ -116,6 +116,11 @@ static inline int page_order(struct perf_buffer *rb) } #endif +static inline int data_page_nr(struct perf_buffer *rb) +{ + return rb->nr_pages << page_order(rb); +} + static inline unsigned long perf_data_size(struct perf_buffer *rb) { return rb->nr_pages << (PAGE_SHIFT + page_order(rb)); diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index 52868716ec35..fb35b926024c 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -859,11 +859,6 @@ void rb_free(struct perf_buffer *rb) } #else -static int data_page_nr(struct perf_buffer *rb) -{ - return rb->nr_pages << page_order(rb); -} - static struct page * __perf_mmap_to_page(struct perf_buffer *rb, unsigned long pgoff) { diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 6418083901d4..a9bc3c98f76a 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -787,10 +787,10 @@ static int __copy_insn(struct address_space *mapping, struct file *filp, struct page *page; /* * Ensure that the page that has the original instruction is populated - * and in page-cache. If ->readpage == NULL it must be shmem_mapping(), + * and in page-cache. If ->read_folio == NULL it must be shmem_mapping(), * see uprobe_register(). */ - if (mapping->a_ops->readpage) + if (mapping->a_ops->read_folio) page = read_mapping_page(mapping, offset >> PAGE_SHIFT, filp); else page = shmem_read_mapping_page(mapping, offset >> PAGE_SHIFT); @@ -1143,7 +1143,8 @@ static int __uprobe_register(struct inode *inode, loff_t offset, return -EINVAL; /* copy_insn() uses read_mapping_page() or shmem_read_mapping_page() */ - if (!inode->i_mapping->a_ops->readpage && !shmem_mapping(inode->i_mapping)) + if (!inode->i_mapping->a_ops->read_folio && + !shmem_mapping(inode->i_mapping)) return -EIO; /* Racy, just to catch the obvious mistakes */ if (offset > i_size_read(inode)) diff --git a/kernel/fork.c b/kernel/fork.c index 9796897560ab..254ab63c1106 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -792,6 +792,7 @@ void __mmdrop(struct mm_struct *mm) mmu_notifier_subscriptions_destroy(mm); check_mm(mm); put_user_ns(mm->user_ns); + mm_pasid_drop(mm); free_mm(mm); } EXPORT_SYMBOL_GPL(__mmdrop); @@ -1045,6 +1046,11 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node) #ifdef CONFIG_MEMCG tsk->active_memcg = NULL; #endif + +#ifdef CONFIG_CPU_SUP_INTEL + tsk->reported_split_lock = 0; +#endif + return tsk; free_stack: @@ -1190,7 +1196,6 @@ static inline void __mmput(struct mm_struct *mm) } if (mm->binfmt) module_put(mm->binfmt->module); - mm_pasid_drop(mm); mmdrop(mm); } diff --git a/kernel/futex/pi.c b/kernel/futex/pi.c index 183b28c32c83..ce2889f12375 100644 --- a/kernel/futex/pi.c +++ b/kernel/futex/pi.c @@ -1005,7 +1005,7 @@ retry_private: rt_mutex_init_waiter(&rt_waiter); /* - * On PREEMPT_RT_FULL, when hb->lock becomes an rt_mutex, we must not + * On PREEMPT_RT, when hb->lock becomes an rt_mutex, we must not * hold it while doing rt_mutex_start_proxy(), because then it will * include hb->lock in the blocking chain, even through we'll not in * fact hold it while blocking. This will lead it to report -EDEADLK diff --git a/kernel/hung_task.c b/kernel/hung_task.c index 52501e5f7655..02a65d554340 100644 --- a/kernel/hung_task.c +++ b/kernel/hung_task.c @@ -127,6 +127,8 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout) * complain: */ if (sysctl_hung_task_warnings) { + printk_prefer_direct_enter(); + if (sysctl_hung_task_warnings > 0) sysctl_hung_task_warnings--; pr_err("INFO: task %s:%d blocked for more than %ld seconds.\n", @@ -142,6 +144,8 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout) if (sysctl_hung_task_all_cpu_backtrace) hung_task_show_all_bt = true; + + printk_prefer_direct_exit(); } touch_nmi_watchdog(); @@ -204,12 +208,17 @@ static void check_hung_uninterruptible_tasks(unsigned long timeout) } unlock: rcu_read_unlock(); - if (hung_task_show_lock) + if (hung_task_show_lock) { + printk_prefer_direct_enter(); debug_show_all_locks(); + printk_prefer_direct_exit(); + } if (hung_task_show_all_bt) { hung_task_show_all_bt = false; + printk_prefer_direct_enter(); trigger_all_cpu_backtrace(); + printk_prefer_direct_exit(); } if (hung_task_call_panic) diff --git a/kernel/irq/affinity.c b/kernel/irq/affinity.c index f7ff8919dc9b..d9a5c1d65a79 100644 --- a/kernel/irq/affinity.c +++ b/kernel/irq/affinity.c @@ -258,7 +258,7 @@ static int __irq_build_affinity_masks(unsigned int startvec, nodemask_t nodemsk = NODE_MASK_NONE; struct node_vectors *node_vectors; - if (!cpumask_weight(cpu_mask)) + if (cpumask_empty(cpu_mask)) return 0; nodes = get_nodes_in_cpumask(node_to_cpumask, cpu_mask, &nodemsk); @@ -269,8 +269,9 @@ static int __irq_build_affinity_masks(unsigned int startvec, */ if (numvecs <= nodes) { for_each_node_mask(n, nodemsk) { - cpumask_or(&masks[curvec].mask, &masks[curvec].mask, - node_to_cpumask[n]); + /* Ensure that only CPUs which are in both masks are set */ + cpumask_and(nmsk, cpu_mask, node_to_cpumask[n]); + cpumask_or(&masks[curvec].mask, &masks[curvec].mask, nmsk); if (++curvec == last_affv) curvec = firstvec; } diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index 54af0deb239b..e6b8e564b37f 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -1573,17 +1573,12 @@ static struct device *irq_get_parent_device(struct irq_data *data) int irq_chip_pm_get(struct irq_data *data) { struct device *dev = irq_get_parent_device(data); - int retval; + int retval = 0; - if (IS_ENABLED(CONFIG_PM) && dev) { - retval = pm_runtime_get_sync(dev); - if (retval < 0) { - pm_runtime_put_noidle(dev); - return retval; - } - } + if (IS_ENABLED(CONFIG_PM) && dev) + retval = pm_runtime_resume_and_get(dev); - return 0; + return retval; } /** diff --git a/kernel/irq/debugfs.c b/kernel/irq/debugfs.c index 2b43f5f5033d..bc8e40cf2b65 100644 --- a/kernel/irq/debugfs.c +++ b/kernel/irq/debugfs.c @@ -58,6 +58,7 @@ static const struct irq_bit_descr irqchip_flags[] = { BIT_MASK_DESCR(IRQCHIP_SUPPORTS_LEVEL_MSI), BIT_MASK_DESCR(IRQCHIP_SUPPORTS_NMI), BIT_MASK_DESCR(IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND), + BIT_MASK_DESCR(IRQCHIP_IMMUTABLE), }; static void diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index 99cbdf55a8bd..f09c60393e55 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -29,12 +29,14 @@ extern struct irqaction chained_action; * IRQTF_WARNED - warning "IRQ_WAKE_THREAD w/o thread_fn" has been printed * IRQTF_AFFINITY - irq thread is requested to adjust affinity * IRQTF_FORCED_THREAD - irq action is force threaded + * IRQTF_READY - signals that irq thread is ready */ enum { IRQTF_RUNTHREAD, IRQTF_WARNED, IRQTF_AFFINITY, IRQTF_FORCED_THREAD, + IRQTF_READY, }; /* diff --git a/kernel/irq/irq_sim.c b/kernel/irq/irq_sim.c index 0cd02efa3a74..dd76323ea3fd 100644 --- a/kernel/irq/irq_sim.c +++ b/kernel/irq/irq_sim.c @@ -181,7 +181,7 @@ struct irq_domain *irq_domain_create_sim(struct fwnode_handle *fwnode, goto err_free_bitmap; work_ctx->irq_count = num_irqs; - init_irq_work(&work_ctx->work, irq_sim_handle_irq); + work_ctx->work = IRQ_WORK_INIT_HARD(irq_sim_handle_irq); return work_ctx->domain; diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index 939d21cd55c3..d323b180b0f3 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -407,6 +407,7 @@ static struct irq_desc *alloc_desc(int irq, int node, unsigned int flags, lockdep_set_class(&desc->lock, &irq_desc_lock_class); mutex_init(&desc->request_mutex); init_rcu_head(&desc->rcu); + init_waitqueue_head(&desc->wait_for_threads); desc_set_defaults(irq, desc, node, affinity, owner); irqd_set(&desc->irq_data, flags); @@ -575,6 +576,7 @@ int __init early_irq_init(void) raw_spin_lock_init(&desc[i].lock); lockdep_set_class(&desc[i].lock, &irq_desc_lock_class); mutex_init(&desc[i].request_mutex); + init_waitqueue_head(&desc[i].wait_for_threads); desc_set_defaults(i, &desc[i], node, NULL, NULL); } return arch_early_irq_init(); @@ -699,7 +701,6 @@ EXPORT_SYMBOL_GPL(generic_handle_irq_safe); */ int generic_handle_domain_irq(struct irq_domain *domain, unsigned int hwirq) { - WARN_ON_ONCE(!in_hardirq()); return handle_irq_desc(irq_resolve_mapping(domain, hwirq)); } EXPORT_SYMBOL_GPL(generic_handle_domain_irq); diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index c03f71d5ec10..8c396319d5ac 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -222,11 +222,16 @@ int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask, { struct irq_desc *desc = irq_data_to_desc(data); struct irq_chip *chip = irq_data_get_irq_chip(data); + const struct cpumask *prog_mask; int ret; + static DEFINE_RAW_SPINLOCK(tmp_mask_lock); + static struct cpumask tmp_mask; + if (!chip || !chip->irq_set_affinity) return -EINVAL; + raw_spin_lock(&tmp_mask_lock); /* * If this is a managed interrupt and housekeeping is enabled on * it check whether the requested affinity mask intersects with @@ -248,24 +253,34 @@ int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask, */ if (irqd_affinity_is_managed(data) && housekeeping_enabled(HK_TYPE_MANAGED_IRQ)) { - const struct cpumask *hk_mask, *prog_mask; - - static DEFINE_RAW_SPINLOCK(tmp_mask_lock); - static struct cpumask tmp_mask; + const struct cpumask *hk_mask; hk_mask = housekeeping_cpumask(HK_TYPE_MANAGED_IRQ); - raw_spin_lock(&tmp_mask_lock); cpumask_and(&tmp_mask, mask, hk_mask); if (!cpumask_intersects(&tmp_mask, cpu_online_mask)) prog_mask = mask; else prog_mask = &tmp_mask; - ret = chip->irq_set_affinity(data, prog_mask, force); - raw_spin_unlock(&tmp_mask_lock); } else { - ret = chip->irq_set_affinity(data, mask, force); + prog_mask = mask; } + + /* + * Make sure we only provide online CPUs to the irqchip, + * unless we are being asked to force the affinity (in which + * case we do as we are told). + */ + cpumask_and(&tmp_mask, prog_mask, cpu_online_mask); + if (!force && !cpumask_empty(&tmp_mask)) + ret = chip->irq_set_affinity(data, &tmp_mask, force); + else if (force) + ret = chip->irq_set_affinity(data, mask, force); + else + ret = -EINVAL; + + raw_spin_unlock(&tmp_mask_lock); + switch (ret) { case IRQ_SET_MASK_OK: case IRQ_SET_MASK_OK_DONE: @@ -1249,6 +1264,31 @@ static void irq_wake_secondary(struct irq_desc *desc, struct irqaction *action) } /* + * Internal function to notify that a interrupt thread is ready. + */ +static void irq_thread_set_ready(struct irq_desc *desc, + struct irqaction *action) +{ + set_bit(IRQTF_READY, &action->thread_flags); + wake_up(&desc->wait_for_threads); +} + +/* + * Internal function to wake up a interrupt thread and wait until it is + * ready. + */ +static void wake_up_and_wait_for_irq_thread_ready(struct irq_desc *desc, + struct irqaction *action) +{ + if (!action || !action->thread) + return; + + wake_up_process(action->thread); + wait_event(desc->wait_for_threads, + test_bit(IRQTF_READY, &action->thread_flags)); +} + +/* * Interrupt handler thread */ static int irq_thread(void *data) @@ -1259,6 +1299,8 @@ static int irq_thread(void *data) irqreturn_t (*handler_fn)(struct irq_desc *desc, struct irqaction *action); + irq_thread_set_ready(desc, action); + sched_set_fifo(current); if (force_irqthreads() && test_bit(IRQTF_FORCED_THREAD, @@ -1683,8 +1725,6 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) } if (!shared) { - init_waitqueue_head(&desc->wait_for_threads); - /* Setup the type (level, edge polarity) if configured: */ if (new->flags & IRQF_TRIGGER_MASK) { ret = __irq_set_trigger(desc, @@ -1780,14 +1820,8 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) irq_setup_timings(desc, new); - /* - * Strictly no need to wake it up, but hung_task complains - * when no hard interrupt wakes the thread up. - */ - if (new->thread) - wake_up_process(new->thread); - if (new->secondary) - wake_up_process(new->secondary->thread); + wake_up_and_wait_for_irq_thread_ready(desc, new); + wake_up_and_wait_for_irq_thread_ready(desc, new->secondary); register_irq_proc(irq, desc); new->dir = NULL; diff --git a/kernel/irq/matrix.c b/kernel/irq/matrix.c index bbfb26489aa1..1698e77645ac 100644 --- a/kernel/irq/matrix.c +++ b/kernel/irq/matrix.c @@ -286,7 +286,7 @@ void irq_matrix_remove_managed(struct irq_matrix *m, const struct cpumask *msk) int irq_matrix_alloc_managed(struct irq_matrix *m, const struct cpumask *msk, unsigned int *mapped_cpu) { - unsigned int bit, cpu, end = m->alloc_end; + unsigned int bit, cpu, end; struct cpumap *cm; if (cpumask_empty(msk)) diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index 2bdfce5edafd..a9ee535293eb 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -818,6 +818,21 @@ static int msi_init_virq(struct irq_domain *domain, int virq, unsigned int vflag irqd_clr_can_reserve(irqd); if (vflags & VIRQ_NOMASK_QUIRK) irqd_set_msi_nomask_quirk(irqd); + + /* + * If the interrupt is managed but no CPU is available to + * service it, shut it down until better times. Note that + * we only do this on the !RESERVE path as x86 (the only + * architecture using this flag) deals with this in a + * different way by using a catch-all vector. + */ + if ((vflags & VIRQ_ACTIVATE) && + irqd_affinity_is_managed(irqd) && + !cpumask_intersects(irq_data_get_affinity_mask(irqd), + cpu_online_mask)) { + irqd_set_managed_shutdown(irqd); + return 0; + } } if (!(vflags & VIRQ_ACTIVATE)) diff --git a/kernel/irq_work.c b/kernel/irq_work.c index f7df715ec28e..7afa40fe5cc4 100644 --- a/kernel/irq_work.c +++ b/kernel/irq_work.c @@ -137,7 +137,7 @@ bool irq_work_queue_on(struct irq_work *work, int cpu) if (!irq_work_claim(work)) return false; - kasan_record_aux_stack(work); + kasan_record_aux_stack_noalloc(work); preempt_disable(); if (cpu != smp_processor_id()) { diff --git a/kernel/kcov.c b/kernel/kcov.c index 475524bd900a..b3732b210593 100644 --- a/kernel/kcov.c +++ b/kernel/kcov.c @@ -475,8 +475,11 @@ static int kcov_mmap(struct file *filep, struct vm_area_struct *vma) vma->vm_flags |= VM_DONTEXPAND; for (off = 0; off < size; off += PAGE_SIZE) { page = vmalloc_to_page(kcov->area + off); - if (vm_insert_page(vma, vma->vm_start + off, page)) - WARN_ONCE(1, "vm_insert_page() failed"); + res = vm_insert_page(vma, vma->vm_start + off, page); + if (res) { + pr_warn_once("kcov: vm_insert_page() failed\n"); + return res; + } } return 0; exit: diff --git a/kernel/kcsan/kcsan_test.c b/kernel/kcsan/kcsan_test.c index a36fca063a73..767dfacd6ed3 100644 --- a/kernel/kcsan/kcsan_test.c +++ b/kernel/kcsan/kcsan_test.c @@ -1380,13 +1380,14 @@ static const void *nthreads_gen_params(const void *prev, char *desc) else nthreads *= 2; - if (!IS_ENABLED(CONFIG_PREEMPT) || !IS_ENABLED(CONFIG_KCSAN_INTERRUPT_WATCHER)) { + if (!preempt_model_preemptible() || + !IS_ENABLED(CONFIG_KCSAN_INTERRUPT_WATCHER)) { /* * Without any preemption, keep 2 CPUs free for other tasks, one * of which is the main test case function checking for * completion or failure. */ - const long min_unused_cpus = IS_ENABLED(CONFIG_PREEMPT_NONE) ? 2 : 0; + const long min_unused_cpus = preempt_model_none() ? 2 : 0; const long min_required_cpus = 2 + min_unused_cpus; if (num_online_cpus() < min_required_cpus) { diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index 68480f731192..be4b54c2c615 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -1078,7 +1078,7 @@ void crash_save_cpu(struct pt_regs *regs, int cpu) return; memset(&prstatus, 0, sizeof(prstatus)); prstatus.common.pr_pid = current->pid; - elf_core_copy_kernel_regs(&prstatus.pr_reg, regs); + elf_core_copy_regs(&prstatus.pr_reg, regs); buf = append_elf_note(buf, KEXEC_CORE_NOTE_NAME, NT_PRSTATUS, &prstatus, sizeof(prstatus)); final_note(buf); diff --git a/kernel/kprobes.c b/kernel/kprobes.c index dbe57df2e199..dd58c0be9ce2 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -2126,7 +2126,7 @@ static void kretprobe_rethook_handler(struct rethook_node *rh, void *data, struct kprobe_ctlblk *kcb; /* The data must NOT be null. This means rethook data structure is broken. */ - if (WARN_ON_ONCE(!data)) + if (WARN_ON_ONCE(!data) || !rp->handler) return; __this_cpu_write(current_kprobe, &rp->kp); diff --git a/kernel/kthread.c b/kernel/kthread.c index 50265f69a135..544fd4097406 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -1522,5 +1522,4 @@ struct cgroup_subsys_state *kthread_blkcg(void) } return NULL; } -EXPORT_SYMBOL(kthread_blkcg); #endif diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index c06cab6546ed..a6e671b8608d 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -60,7 +60,6 @@ #include "lockdep_internals.h" -#define CREATE_TRACE_POINTS #include <trace/events/lock.h> #ifdef CONFIG_PROVE_LOCKING @@ -1380,7 +1379,7 @@ static struct lock_list *alloc_list_entry(void) */ static int add_lock_to_list(struct lock_class *this, struct lock_class *links_to, struct list_head *head, - unsigned long ip, u16 distance, u8 dep, + u16 distance, u8 dep, const struct lock_trace *trace) { struct lock_list *entry; @@ -3133,19 +3132,15 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev, * to the previous lock's dependency list: */ ret = add_lock_to_list(hlock_class(next), hlock_class(prev), - &hlock_class(prev)->locks_after, - next->acquire_ip, distance, - calc_dep(prev, next), - *trace); + &hlock_class(prev)->locks_after, distance, + calc_dep(prev, next), *trace); if (!ret) return 0; ret = add_lock_to_list(hlock_class(prev), hlock_class(next), - &hlock_class(next)->locks_before, - next->acquire_ip, distance, - calc_depb(prev, next), - *trace); + &hlock_class(next)->locks_before, distance, + calc_depb(prev, next), *trace); if (!ret) return 0; @@ -4236,14 +4231,13 @@ static void __trace_hardirqs_on_caller(void) /** * lockdep_hardirqs_on_prepare - Prepare for enabling interrupts - * @ip: Caller address * * Invoked before a possible transition to RCU idle from exit to user or * guest mode. This ensures that all RCU operations are done before RCU * stops watching. After the RCU transition lockdep_hardirqs_on() has to be * invoked to set the final state. */ -void lockdep_hardirqs_on_prepare(unsigned long ip) +void lockdep_hardirqs_on_prepare(void) { if (unlikely(!debug_locks)) return; @@ -4840,8 +4834,7 @@ EXPORT_SYMBOL_GPL(__lockdep_no_validate__); static void print_lock_nested_lock_not_held(struct task_struct *curr, - struct held_lock *hlock, - unsigned long ip) + struct held_lock *hlock) { if (!debug_locks_off()) return; @@ -5017,7 +5010,7 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass, chain_key = iterate_chain_key(chain_key, hlock_id(hlock)); if (nest_lock && !__lock_is_held(nest_lock, -1)) { - print_lock_nested_lock_not_held(curr, hlock, ip); + print_lock_nested_lock_not_held(curr, hlock); return 0; } diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index 5e3585950ec8..d973fe6041bf 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -30,6 +30,9 @@ #include <linux/debug_locks.h> #include <linux/osq_lock.h> +#define CREATE_TRACE_POINTS +#include <trace/events/lock.h> + #ifndef CONFIG_PREEMPT_RT #include "mutex.h" @@ -599,12 +602,14 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas preempt_disable(); mutex_acquire_nest(&lock->dep_map, subclass, 0, nest_lock, ip); + trace_contention_begin(lock, LCB_F_MUTEX | LCB_F_SPIN); if (__mutex_trylock(lock) || mutex_optimistic_spin(lock, ww_ctx, NULL)) { /* got the lock, yay! */ lock_acquired(&lock->dep_map, ip); if (ww_ctx) ww_mutex_set_context_fastpath(ww, ww_ctx); + trace_contention_end(lock, 0); preempt_enable(); return 0; } @@ -641,6 +646,7 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas } set_current_state(state); + trace_contention_begin(lock, LCB_F_MUTEX); for (;;) { bool first; @@ -680,10 +686,16 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas * state back to RUNNING and fall through the next schedule(), * or we must see its unlock and acquire. */ - if (__mutex_trylock_or_handoff(lock, first) || - (first && mutex_optimistic_spin(lock, ww_ctx, &waiter))) + if (__mutex_trylock_or_handoff(lock, first)) break; + if (first) { + trace_contention_begin(lock, LCB_F_MUTEX | LCB_F_SPIN); + if (mutex_optimistic_spin(lock, ww_ctx, &waiter)) + break; + trace_contention_begin(lock, LCB_F_MUTEX); + } + raw_spin_lock(&lock->wait_lock); } raw_spin_lock(&lock->wait_lock); @@ -707,6 +719,7 @@ acquired: skip_wait: /* got the lock - cleanup and rejoice! */ lock_acquired(&lock->dep_map, ip); + trace_contention_end(lock, 0); if (ww_ctx) ww_mutex_lock_acquired(ww, ww_ctx); @@ -719,6 +732,7 @@ err: __set_current_state(TASK_RUNNING); __mutex_remove_waiter(lock, &waiter); err_early_kill: + trace_contention_end(lock, ret); raw_spin_unlock(&lock->wait_lock); debug_mutex_free_waiter(&waiter); mutex_release(&lock->dep_map, ip); diff --git a/kernel/locking/percpu-rwsem.c b/kernel/locking/percpu-rwsem.c index c9fdae94e098..5fe4c5495ba3 100644 --- a/kernel/locking/percpu-rwsem.c +++ b/kernel/locking/percpu-rwsem.c @@ -9,6 +9,7 @@ #include <linux/sched/task.h> #include <linux/sched/debug.h> #include <linux/errno.h> +#include <trace/events/lock.h> int __percpu_init_rwsem(struct percpu_rw_semaphore *sem, const char *name, struct lock_class_key *key) @@ -171,9 +172,11 @@ bool __sched __percpu_down_read(struct percpu_rw_semaphore *sem, bool try) if (try) return false; + trace_contention_begin(sem, LCB_F_PERCPU | LCB_F_READ); preempt_enable(); percpu_rwsem_wait(sem, /* .reader = */ true); preempt_disable(); + trace_contention_end(sem, 0); return true; } @@ -216,6 +219,7 @@ void __sched percpu_down_write(struct percpu_rw_semaphore *sem) { might_sleep(); rwsem_acquire(&sem->dep_map, 0, 0, _RET_IP_); + trace_contention_begin(sem, LCB_F_PERCPU | LCB_F_WRITE); /* Notify readers to take the slow path. */ rcu_sync_enter(&sem->rss); @@ -237,6 +241,7 @@ void __sched percpu_down_write(struct percpu_rw_semaphore *sem) /* Wait for all active readers to complete. */ rcuwait_wait_event(&sem->writer, readers_active_check(sem), TASK_UNINTERRUPTIBLE); + trace_contention_end(sem, 0); } EXPORT_SYMBOL_GPL(percpu_down_write); diff --git a/kernel/locking/qrwlock.c b/kernel/locking/qrwlock.c index ec36b73f4733..2e1600906c9f 100644 --- a/kernel/locking/qrwlock.c +++ b/kernel/locking/qrwlock.c @@ -12,10 +12,11 @@ #include <linux/percpu.h> #include <linux/hardirq.h> #include <linux/spinlock.h> +#include <trace/events/lock.h> /** - * queued_read_lock_slowpath - acquire read lock of a queue rwlock - * @lock: Pointer to queue rwlock structure + * queued_read_lock_slowpath - acquire read lock of a queued rwlock + * @lock: Pointer to queued rwlock structure */ void queued_read_lock_slowpath(struct qrwlock *lock) { @@ -34,6 +35,8 @@ void queued_read_lock_slowpath(struct qrwlock *lock) } atomic_sub(_QR_BIAS, &lock->cnts); + trace_contention_begin(lock, LCB_F_SPIN | LCB_F_READ); + /* * Put the reader into the wait queue */ @@ -51,17 +54,21 @@ void queued_read_lock_slowpath(struct qrwlock *lock) * Signal the next one in queue to become queue head */ arch_spin_unlock(&lock->wait_lock); + + trace_contention_end(lock, 0); } EXPORT_SYMBOL(queued_read_lock_slowpath); /** - * queued_write_lock_slowpath - acquire write lock of a queue rwlock - * @lock : Pointer to queue rwlock structure + * queued_write_lock_slowpath - acquire write lock of a queued rwlock + * @lock : Pointer to queued rwlock structure */ void queued_write_lock_slowpath(struct qrwlock *lock) { int cnts; + trace_contention_begin(lock, LCB_F_SPIN | LCB_F_WRITE); + /* Put the writer into the wait queue */ arch_spin_lock(&lock->wait_lock); @@ -79,5 +86,7 @@ void queued_write_lock_slowpath(struct qrwlock *lock) } while (!atomic_try_cmpxchg_acquire(&lock->cnts, &cnts, _QW_LOCKED)); unlock: arch_spin_unlock(&lock->wait_lock); + + trace_contention_end(lock, 0); } EXPORT_SYMBOL(queued_write_lock_slowpath); diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c index cbff6ba53d56..65a9a10caa6f 100644 --- a/kernel/locking/qspinlock.c +++ b/kernel/locking/qspinlock.c @@ -22,6 +22,7 @@ #include <linux/prefetch.h> #include <asm/byteorder.h> #include <asm/qspinlock.h> +#include <trace/events/lock.h> /* * Include queued spinlock statistics code @@ -401,6 +402,8 @@ pv_queue: idx = node->count++; tail = encode_tail(smp_processor_id(), idx); + trace_contention_begin(lock, LCB_F_SPIN); + /* * 4 nodes are allocated based on the assumption that there will * not be nested NMIs taking spinlocks. That may not be true in @@ -554,6 +557,8 @@ locked: pv_kick_node(lock, next); release: + trace_contention_end(lock, 0); + /* * release the node */ diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 8555c4efe97c..7779ee8abc2a 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -24,6 +24,8 @@ #include <linux/sched/wake_q.h> #include <linux/ww_mutex.h> +#include <trace/events/lock.h> + #include "rtmutex_common.h" #ifndef WW_RT @@ -1579,6 +1581,8 @@ static int __sched __rt_mutex_slowlock(struct rt_mutex_base *lock, set_current_state(state); + trace_contention_begin(lock, LCB_F_RT); + ret = task_blocks_on_rt_mutex(lock, waiter, current, ww_ctx, chwalk); if (likely(!ret)) ret = rt_mutex_slowlock_block(lock, ww_ctx, state, NULL, waiter); @@ -1601,6 +1605,9 @@ static int __sched __rt_mutex_slowlock(struct rt_mutex_base *lock, * unconditionally. We might have to fix that up. */ fixup_rt_mutex_waiters(lock); + + trace_contention_end(lock, ret); + return ret; } @@ -1683,6 +1690,8 @@ static void __sched rtlock_slowlock_locked(struct rt_mutex_base *lock) /* Save current state and set state to TASK_RTLOCK_WAIT */ current_save_and_set_rtlock_wait_state(); + trace_contention_begin(lock, LCB_F_RT); + task_blocks_on_rt_mutex(lock, &waiter, current, NULL, RT_MUTEX_MIN_CHAINWALK); for (;;) { @@ -1712,6 +1721,8 @@ static void __sched rtlock_slowlock_locked(struct rt_mutex_base *lock) */ fixup_rt_mutex_waiters(lock); debug_rt_mutex_free_waiter(&waiter); + + trace_contention_end(lock, 0); } static __always_inline void __sched rtlock_slowlock(struct rt_mutex_base *lock) diff --git a/kernel/locking/rwbase_rt.c b/kernel/locking/rwbase_rt.c index 6fd3162e4098..c201aadb9301 100644 --- a/kernel/locking/rwbase_rt.c +++ b/kernel/locking/rwbase_rt.c @@ -112,6 +112,8 @@ static int __sched __rwbase_read_lock(struct rwbase_rt *rwb, * Reader2 to call up_read(), which might be unbound. */ + trace_contention_begin(rwb, LCB_F_RT | LCB_F_READ); + /* * For rwlocks this returns 0 unconditionally, so the below * !ret conditionals are optimized out. @@ -130,6 +132,8 @@ static int __sched __rwbase_read_lock(struct rwbase_rt *rwb, raw_spin_unlock_irq(&rtm->wait_lock); if (!ret) rwbase_rtmutex_unlock(rtm); + + trace_contention_end(rwb, ret); return ret; } @@ -247,11 +251,13 @@ static int __sched rwbase_write_lock(struct rwbase_rt *rwb, goto out_unlock; rwbase_set_and_save_current_state(state); + trace_contention_begin(rwb, LCB_F_RT | LCB_F_WRITE); for (;;) { /* Optimized out for rwlocks */ if (rwbase_signal_pending_state(state, current)) { rwbase_restore_current_state(); __rwbase_write_unlock(rwb, 0, flags); + trace_contention_end(rwb, -EINTR); return -EINTR; } @@ -265,6 +271,7 @@ static int __sched rwbase_write_lock(struct rwbase_rt *rwb, set_current_state(state); } rwbase_restore_current_state(); + trace_contention_end(rwb, 0); out_unlock: raw_spin_unlock_irqrestore(&rtm->wait_lock, flags); diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c index acde5d6f1254..9d1db4a54d34 100644 --- a/kernel/locking/rwsem.c +++ b/kernel/locking/rwsem.c @@ -27,6 +27,7 @@ #include <linux/export.h> #include <linux/rwsem.h> #include <linux/atomic.h> +#include <trace/events/lock.h> #ifndef CONFIG_PREEMPT_RT #include "lock_events.h" @@ -375,16 +376,19 @@ rwsem_add_waiter(struct rw_semaphore *sem, struct rwsem_waiter *waiter) * * Both rwsem_mark_wake() and rwsem_try_write_lock() contain a full 'copy' of * this function. Modify with care. + * + * Return: true if wait_list isn't empty and false otherwise */ -static inline void +static inline bool rwsem_del_waiter(struct rw_semaphore *sem, struct rwsem_waiter *waiter) { lockdep_assert_held(&sem->wait_lock); list_del(&waiter->list); if (likely(!list_empty(&sem->wait_list))) - return; + return true; atomic_long_andnot(RWSEM_FLAG_HANDOFF | RWSEM_FLAG_WAITERS, &sem->count); + return false; } /* @@ -559,6 +563,33 @@ static void rwsem_mark_wake(struct rw_semaphore *sem, } /* + * Remove a waiter and try to wake up other waiters in the wait queue + * This function is called from the out_nolock path of both the reader and + * writer slowpaths with wait_lock held. It releases the wait_lock and + * optionally wake up waiters before it returns. + */ +static inline void +rwsem_del_wake_waiter(struct rw_semaphore *sem, struct rwsem_waiter *waiter, + struct wake_q_head *wake_q) + __releases(&sem->wait_lock) +{ + bool first = rwsem_first_waiter(sem) == waiter; + + wake_q_init(wake_q); + + /* + * If the wait_list isn't empty and the waiter to be deleted is + * the first waiter, we wake up the remaining waiters as they may + * be eligible to acquire or spin on the lock. + */ + if (rwsem_del_waiter(sem, waiter) && first) + rwsem_mark_wake(sem, RWSEM_WAKE_ANY, wake_q); + raw_spin_unlock_irq(&sem->wait_lock); + if (!wake_q_empty(wake_q)) + wake_up_q(wake_q); +} + +/* * This function must be called with the sem->wait_lock held to prevent * race conditions between checking the rwsem wait list and setting the * sem->count accordingly. @@ -901,7 +932,7 @@ done: */ static inline void clear_nonspinnable(struct rw_semaphore *sem) { - if (rwsem_test_oflags(sem, RWSEM_NONSPINNABLE)) + if (unlikely(rwsem_test_oflags(sem, RWSEM_NONSPINNABLE))) atomic_long_andnot(RWSEM_NONSPINNABLE, &sem->owner); } @@ -926,6 +957,31 @@ rwsem_spin_on_owner(struct rw_semaphore *sem) #endif /* + * Prepare to wake up waiter(s) in the wait queue by putting them into the + * given wake_q if the rwsem lock owner isn't a writer. If rwsem is likely + * reader-owned, wake up read lock waiters in queue front or wake up any + * front waiter otherwise. + + * This is being called from both reader and writer slow paths. + */ +static inline void rwsem_cond_wake_waiter(struct rw_semaphore *sem, long count, + struct wake_q_head *wake_q) +{ + enum rwsem_wake_type wake_type; + + if (count & RWSEM_WRITER_MASK) + return; + + if (count & RWSEM_READER_MASK) { + wake_type = RWSEM_WAKE_READERS; + } else { + wake_type = RWSEM_WAKE_ANY; + clear_nonspinnable(sem); + } + rwsem_mark_wake(sem, wake_type, wake_q); +} + +/* * Wait for the read lock to be granted */ static struct rw_semaphore __sched * @@ -935,7 +991,6 @@ rwsem_down_read_slowpath(struct rw_semaphore *sem, long count, unsigned int stat long rcnt = (count >> RWSEM_READER_SHIFT); struct rwsem_waiter waiter; DEFINE_WAKE_Q(wake_q); - bool wake = false; /* * To prevent a constant stream of readers from starving a sleeping @@ -977,12 +1032,11 @@ queue: if (list_empty(&sem->wait_list)) { /* * In case the wait queue is empty and the lock isn't owned - * by a writer or has the handoff bit set, this reader can - * exit the slowpath and return immediately as its - * RWSEM_READER_BIAS has already been set in the count. + * by a writer, this reader can exit the slowpath and return + * immediately as its RWSEM_READER_BIAS has already been set + * in the count. */ - if (!(atomic_long_read(&sem->count) & - (RWSEM_WRITER_MASK | RWSEM_FLAG_HANDOFF))) { + if (!(atomic_long_read(&sem->count) & RWSEM_WRITER_MASK)) { /* Provide lock ACQUIRE */ smp_acquire__after_ctrl_dep(); raw_spin_unlock_irq(&sem->wait_lock); @@ -997,22 +1051,13 @@ queue: /* we're now waiting on the lock, but no longer actively locking */ count = atomic_long_add_return(adjustment, &sem->count); - /* - * If there are no active locks, wake the front queued process(es). - * - * If there are no writers and we are first in the queue, - * wake our own waiter to join the existing active readers ! - */ - if (!(count & RWSEM_LOCK_MASK)) { - clear_nonspinnable(sem); - wake = true; - } - if (wake || (!(count & RWSEM_WRITER_MASK) && - (adjustment & RWSEM_FLAG_WAITERS))) - rwsem_mark_wake(sem, RWSEM_WAKE_ANY, &wake_q); - + rwsem_cond_wake_waiter(sem, count, &wake_q); raw_spin_unlock_irq(&sem->wait_lock); - wake_up_q(&wake_q); + + if (!wake_q_empty(&wake_q)) + wake_up_q(&wake_q); + + trace_contention_begin(sem, LCB_F_READ); /* wait to be given the lock */ for (;;) { @@ -1035,13 +1080,14 @@ queue: __set_current_state(TASK_RUNNING); lockevent_inc(rwsem_rlock); + trace_contention_end(sem, 0); return sem; out_nolock: - rwsem_del_waiter(sem, &waiter); - raw_spin_unlock_irq(&sem->wait_lock); + rwsem_del_wake_waiter(sem, &waiter, &wake_q); __set_current_state(TASK_RUNNING); lockevent_inc(rwsem_rlock_fail); + trace_contention_end(sem, -EINTR); return ERR_PTR(-EINTR); } @@ -1051,7 +1097,6 @@ out_nolock: static struct rw_semaphore __sched * rwsem_down_write_slowpath(struct rw_semaphore *sem, int state) { - long count; struct rwsem_waiter waiter; DEFINE_WAKE_Q(wake_q); @@ -1075,23 +1120,8 @@ rwsem_down_write_slowpath(struct rw_semaphore *sem, int state) /* we're now waiting on the lock */ if (rwsem_first_waiter(sem) != &waiter) { - count = atomic_long_read(&sem->count); - - /* - * If there were already threads queued before us and: - * 1) there are no active locks, wake the front - * queued process(es) as the handoff bit might be set. - * 2) there are no active writers and some readers, the lock - * must be read owned; so we try to wake any read lock - * waiters that were queued ahead of us. - */ - if (count & RWSEM_WRITER_MASK) - goto wait; - - rwsem_mark_wake(sem, (count & RWSEM_READER_MASK) - ? RWSEM_WAKE_READERS - : RWSEM_WAKE_ANY, &wake_q); - + rwsem_cond_wake_waiter(sem, atomic_long_read(&sem->count), + &wake_q); if (!wake_q_empty(&wake_q)) { /* * We want to minimize wait_lock hold time especially @@ -1099,16 +1129,16 @@ rwsem_down_write_slowpath(struct rw_semaphore *sem, int state) */ raw_spin_unlock_irq(&sem->wait_lock); wake_up_q(&wake_q); - wake_q_init(&wake_q); /* Used again, reinit */ raw_spin_lock_irq(&sem->wait_lock); } } else { atomic_long_or(RWSEM_FLAG_WAITERS, &sem->count); } -wait: /* wait until we successfully acquire the lock */ set_current_state(state); + trace_contention_begin(sem, LCB_F_WRITE); + for (;;) { if (rwsem_try_write_lock(sem, &waiter)) { /* rwsem_try_write_lock() implies ACQUIRE on success */ @@ -1148,17 +1178,15 @@ trylock_again: __set_current_state(TASK_RUNNING); raw_spin_unlock_irq(&sem->wait_lock); lockevent_inc(rwsem_wlock); + trace_contention_end(sem, 0); return sem; out_nolock: __set_current_state(TASK_RUNNING); raw_spin_lock_irq(&sem->wait_lock); - rwsem_del_waiter(sem, &waiter); - if (!list_empty(&sem->wait_list)) - rwsem_mark_wake(sem, RWSEM_WAKE_ANY, &wake_q); - raw_spin_unlock_irq(&sem->wait_lock); - wake_up_q(&wake_q); + rwsem_del_wake_waiter(sem, &waiter, &wake_q); lockevent_inc(rwsem_wlock_fail); + trace_contention_end(sem, -EINTR); return ERR_PTR(-EINTR); } diff --git a/kernel/locking/semaphore.c b/kernel/locking/semaphore.c index 9ee381e4d2a4..f2654d2fe43a 100644 --- a/kernel/locking/semaphore.c +++ b/kernel/locking/semaphore.c @@ -32,6 +32,7 @@ #include <linux/semaphore.h> #include <linux/spinlock.h> #include <linux/ftrace.h> +#include <trace/events/lock.h> static noinline void __down(struct semaphore *sem); static noinline int __down_interruptible(struct semaphore *sem); @@ -205,7 +206,7 @@ struct semaphore_waiter { * constant, and thus optimised away by the compiler. Likewise the * 'timeout' parameter for the cases without timeouts. */ -static inline int __sched __down_common(struct semaphore *sem, long state, +static inline int __sched ___down_common(struct semaphore *sem, long state, long timeout) { struct semaphore_waiter waiter; @@ -236,6 +237,18 @@ static inline int __sched __down_common(struct semaphore *sem, long state, return -EINTR; } +static inline int __sched __down_common(struct semaphore *sem, long state, + long timeout) +{ + int ret; + + trace_contention_begin(sem, 0); + ret = ___down_common(sem, state, timeout); + trace_contention_end(sem, ret); + + return ret; +} + static noinline void __sched __down(struct semaphore *sem) { __down_common(sem, TASK_UNINTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT); diff --git a/kernel/panic.c b/kernel/panic.c index eb4dfb932c85..6737b2332275 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -48,7 +48,7 @@ unsigned int __read_mostly sysctl_oops_all_cpu_backtrace; int panic_on_oops = CONFIG_PANIC_ON_OOPS_VALUE; static unsigned long tainted_mask = - IS_ENABLED(CONFIG_GCC_PLUGIN_RANDSTRUCT) ? (1 << TAINT_RANDSTRUCT) : 0; + IS_ENABLED(CONFIG_RANDSTRUCT) ? (1 << TAINT_RANDSTRUCT) : 0; static int pause_on_oops; static int pause_on_oops_flag; static DEFINE_SPINLOCK(pause_on_oops_lock); @@ -579,6 +579,8 @@ void __warn(const char *file, int line, void *caller, unsigned taint, { disable_trace_on_warning(); + printk_prefer_direct_enter(); + if (file) pr_warn("WARNING: CPU: %d PID: %d at %s:%d %pS\n", raw_smp_processor_id(), current->pid, file, line, @@ -608,6 +610,8 @@ void __warn(const char *file, int line, void *caller, unsigned taint, /* Just a warning, don't kill lockdep. */ add_taint(taint, LOCKDEP_STILL_OK); + + printk_prefer_direct_exit(); } #ifndef __WARN_FLAGS diff --git a/kernel/power/Makefile b/kernel/power/Makefile index 5899260a8bef..874ad834dc8d 100644 --- a/kernel/power/Makefile +++ b/kernel/power/Makefile @@ -1,6 +1,10 @@ # SPDX-License-Identifier: GPL-2.0 -ccflags-$(CONFIG_PM_DEBUG) := -DDEBUG +ifeq ($(CONFIG_DYNAMIC_DEBUG), y) +CFLAGS_swap.o := -DDEBUG +CFLAGS_snapshot.o := -DDEBUG +CFLAGS_energy_model.o := -DDEBUG +endif KASAN_SANITIZE_snapshot.o := n diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c index 0153b0ca7b23..6c373f2960e7 100644 --- a/kernel/power/energy_model.c +++ b/kernel/power/energy_model.c @@ -54,28 +54,15 @@ static int em_debug_cpus_show(struct seq_file *s, void *unused) } DEFINE_SHOW_ATTRIBUTE(em_debug_cpus); -static int em_debug_units_show(struct seq_file *s, void *unused) +static int em_debug_flags_show(struct seq_file *s, void *unused) { struct em_perf_domain *pd = s->private; - char *units = (pd->flags & EM_PERF_DOMAIN_MILLIWATTS) ? - "milliWatts" : "bogoWatts"; - seq_printf(s, "%s\n", units); + seq_printf(s, "%#lx\n", pd->flags); return 0; } -DEFINE_SHOW_ATTRIBUTE(em_debug_units); - -static int em_debug_skip_inefficiencies_show(struct seq_file *s, void *unused) -{ - struct em_perf_domain *pd = s->private; - int enabled = (pd->flags & EM_PERF_DOMAIN_SKIP_INEFFICIENCIES) ? 1 : 0; - - seq_printf(s, "%d\n", enabled); - - return 0; -} -DEFINE_SHOW_ATTRIBUTE(em_debug_skip_inefficiencies); +DEFINE_SHOW_ATTRIBUTE(em_debug_flags); static void em_debug_create_pd(struct device *dev) { @@ -89,9 +76,8 @@ static void em_debug_create_pd(struct device *dev) debugfs_create_file("cpus", 0444, d, dev->em_pd->cpus, &em_debug_cpus_fops); - debugfs_create_file("units", 0444, d, dev->em_pd, &em_debug_units_fops); - debugfs_create_file("skip-inefficiencies", 0444, d, dev->em_pd, - &em_debug_skip_inefficiencies_fops); + debugfs_create_file("flags", 0444, d, dev->em_pd, + &em_debug_flags_fops); /* Create a sub-directory for each performance state */ for (i = 0; i < dev->em_pd->nr_perf_states; i++) @@ -121,7 +107,8 @@ static void em_debug_remove_pd(struct device *dev) {} #endif static int em_create_perf_table(struct device *dev, struct em_perf_domain *pd, - int nr_states, struct em_data_callback *cb) + int nr_states, struct em_data_callback *cb, + unsigned long flags) { unsigned long power, freq, prev_freq = 0, prev_cost = ULONG_MAX; struct em_perf_state *table; @@ -139,7 +126,7 @@ static int em_create_perf_table(struct device *dev, struct em_perf_domain *pd, * lowest performance state of 'dev' above 'freq' and updates * 'power' and 'freq' accordingly. */ - ret = cb->active_power(&power, &freq, dev); + ret = cb->active_power(dev, &power, &freq); if (ret) { dev_err(dev, "EM: invalid perf. state: %d\n", ret); @@ -173,10 +160,22 @@ static int em_create_perf_table(struct device *dev, struct em_perf_domain *pd, /* Compute the cost of each performance state. */ fmax = (u64) table[nr_states - 1].frequency; for (i = nr_states - 1; i >= 0; i--) { - unsigned long power_res = em_scale_power(table[i].power); + unsigned long power_res, cost; + + if (flags & EM_PERF_DOMAIN_ARTIFICIAL) { + ret = cb->get_cost(dev, table[i].frequency, &cost); + if (ret || !cost || cost > EM_MAX_POWER) { + dev_err(dev, "EM: invalid cost %lu %d\n", + cost, ret); + goto free_ps_table; + } + } else { + power_res = em_scale_power(table[i].power); + cost = div64_u64(fmax * power_res, table[i].frequency); + } + + table[i].cost = cost; - table[i].cost = div64_u64(fmax * power_res, - table[i].frequency); if (table[i].cost >= prev_cost) { table[i].flags = EM_PERF_STATE_INEFFICIENT; dev_dbg(dev, "EM: OPP:%lu is inefficient\n", @@ -197,7 +196,8 @@ free_ps_table: } static int em_create_pd(struct device *dev, int nr_states, - struct em_data_callback *cb, cpumask_t *cpus) + struct em_data_callback *cb, cpumask_t *cpus, + unsigned long flags) { struct em_perf_domain *pd; struct device *cpu_dev; @@ -215,7 +215,7 @@ static int em_create_pd(struct device *dev, int nr_states, return -ENOMEM; } - ret = em_create_perf_table(dev, pd, nr_states, cb); + ret = em_create_perf_table(dev, pd, nr_states, cb, flags); if (ret) { kfree(pd); return ret; @@ -259,6 +259,8 @@ static void em_cpufreq_update_efficiencies(struct device *dev) found++; } + cpufreq_cpu_put(policy); + if (!found) return; @@ -332,6 +334,7 @@ int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states, bool milliwatts) { unsigned long cap, prev_cap = 0; + unsigned long flags = 0; int cpu, ret; if (!dev || !nr_states || !cb) @@ -378,12 +381,16 @@ int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states, } } - ret = em_create_pd(dev, nr_states, cb, cpus); + if (milliwatts) + flags |= EM_PERF_DOMAIN_MILLIWATTS; + else if (cb->get_cost) + flags |= EM_PERF_DOMAIN_ARTIFICIAL; + + ret = em_create_pd(dev, nr_states, cb, cpus, flags); if (ret) goto unlock; - if (milliwatts) - dev->em_pd->flags |= EM_PERF_DOMAIN_MILLIWATTS; + dev->em_pd->flags |= flags; em_cpufreq_update_efficiencies(dev); diff --git a/kernel/power/main.c b/kernel/power/main.c index 7e646079fbeb..5242bf2ee469 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -545,35 +545,6 @@ static int __init pm_debug_messages_setup(char *str) } __setup("pm_debug_messages", pm_debug_messages_setup); -/** - * __pm_pr_dbg - Print a suspend debug message to the kernel log. - * @defer: Whether or not to use printk_deferred() to print the message. - * @fmt: Message format. - * - * The message will be emitted if enabled through the pm_debug_messages - * sysfs attribute. - */ -void __pm_pr_dbg(bool defer, const char *fmt, ...) -{ - struct va_format vaf; - va_list args; - - if (!pm_debug_messages_on) - return; - - va_start(args, fmt); - - vaf.fmt = fmt; - vaf.va = &args; - - if (defer) - printk_deferred(KERN_DEBUG "PM: %pV", &vaf); - else - printk(KERN_DEBUG "PM: %pV", &vaf); - - va_end(args); -} - #else /* !CONFIG_PM_SLEEP_DEBUG */ static inline void pm_print_times_init(void) {} #endif /* CONFIG_PM_SLEEP_DEBUG */ diff --git a/kernel/power/process.c b/kernel/power/process.c index 11b570fcf049..3068601e585a 100644 --- a/kernel/power/process.c +++ b/kernel/power/process.c @@ -6,9 +6,6 @@ * Originally from swsusp. */ - -#undef DEBUG - #include <linux/interrupt.h> #include <linux/oom.h> #include <linux/suspend.h> diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index 330d49937692..2a406753af90 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -326,7 +326,7 @@ static void *chain_alloc(struct chain_allocator *ca, unsigned int size) return ret; } -/** +/* * Data types related to memory bitmaps. * * Memory bitmap is a structure consisting of many linked lists of @@ -427,6 +427,10 @@ struct memory_bitmap { /** * alloc_rtree_node - Allocate a new node and add it to the radix tree. + * @gfp_mask: GFP mask for the allocation. + * @safe_needed: Get pages not used before hibernation (restore only) + * @ca: Pointer to a linked list of pages ("a chain") to allocate from + * @list: Radix Tree node to add. * * This function is used to allocate inner nodes as well as the * leave nodes of the radix tree. It also adds the node to the @@ -902,7 +906,7 @@ static bool rtree_next_node(struct memory_bitmap *bm) } /** - * memory_bm_rtree_next_pfn - Find the next set bit in a memory bitmap. + * memory_bm_next_pfn - Find the next set bit in a memory bitmap. * @bm: Memory bitmap. * * Starting from the last returned position this function searches for the next @@ -1937,7 +1941,7 @@ static inline int get_highmem_buffer(int safe_needed) } /** - * alloc_highmem_image_pages - Allocate some highmem pages for the image. + * alloc_highmem_pages - Allocate some highmem pages for the image. * * Try to allocate as many pages as needed, but if the number of free highmem * pages is less than that, allocate them all. @@ -2224,7 +2228,7 @@ static int check_header(struct swsusp_info *info) } /** - * load header - Check the image header and copy the data from it. + * load_header - Check the image header and copy the data from it. */ static int load_header(struct swsusp_info *info) { diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index da03c15ecc89..a3e1035929b0 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -224,6 +224,33 @@ int devkmsg_sysctl_set_loglvl(struct ctl_table *table, int write, static int nr_ext_console_drivers; /* + * Used to synchronize printing kthreads against direct printing via + * console_trylock/console_unlock. + * + * Values: + * -1 = console kthreads atomically blocked (via global trylock) + * 0 = no kthread printing, console not locked (via trylock) + * >0 = kthread(s) actively printing + * + * Note: For synchronizing against direct printing via + * console_lock/console_unlock, see the @lock variable in + * struct console. + */ +static atomic_t console_kthreads_active = ATOMIC_INIT(0); + +#define console_kthreads_atomic_tryblock() \ + (atomic_cmpxchg(&console_kthreads_active, 0, -1) == 0) +#define console_kthreads_atomic_unblock() \ + atomic_cmpxchg(&console_kthreads_active, -1, 0) +#define console_kthreads_atomically_blocked() \ + (atomic_read(&console_kthreads_active) == -1) + +#define console_kthread_printing_tryenter() \ + atomic_inc_unless_negative(&console_kthreads_active) +#define console_kthread_printing_exit() \ + atomic_dec(&console_kthreads_active) + +/* * Helper macros to handle lockdep when locking/unlocking console_sem. We use * macros instead of functions so that _RET_IP_ contains useful information. */ @@ -271,19 +298,49 @@ static bool panic_in_progress(void) } /* - * This is used for debugging the mess that is the VT code by - * keeping track if we have the console semaphore held. It's - * definitely not the perfect debug tool (we don't know if _WE_ - * hold it and are racing, but it helps tracking those weird code - * paths in the console code where we end up in places I want - * locked without the console semaphore held). + * Tracks whether kthread printers are all blocked. A value of true implies + * that the console is locked via console_lock() or the console is suspended. + * Writing to this variable requires holding @console_sem. */ -static int console_locked, console_suspended; +static bool console_kthreads_blocked; + +/* + * Block all kthread printers from a schedulable context. + * + * Requires holding @console_sem. + */ +static void console_kthreads_block(void) +{ + struct console *con; + + for_each_console(con) { + mutex_lock(&con->lock); + con->blocked = true; + mutex_unlock(&con->lock); + } + + console_kthreads_blocked = true; +} /* - * If exclusive_console is non-NULL then only this console is to be printed to. + * Unblock all kthread printers from a schedulable context. + * + * Requires holding @console_sem. */ -static struct console *exclusive_console; +static void console_kthreads_unblock(void) +{ + struct console *con; + + for_each_console(con) { + mutex_lock(&con->lock); + con->blocked = false; + mutex_unlock(&con->lock); + } + + console_kthreads_blocked = false; +} + +static int console_suspended; /* * Array of consoles built from command line options (console=) @@ -366,7 +423,75 @@ static int console_msg_format = MSG_FORMAT_DEFAULT; /* syslog_lock protects syslog_* variables and write access to clear_seq. */ static DEFINE_MUTEX(syslog_lock); +/* + * A flag to signify if printk_activate_kthreads() has already started the + * kthread printers. If true, any later registered consoles must start their + * own kthread directly. The flag is write protected by the console_lock. + */ +static bool printk_kthreads_available; + #ifdef CONFIG_PRINTK +static atomic_t printk_prefer_direct = ATOMIC_INIT(0); + +/** + * printk_prefer_direct_enter - cause printk() calls to attempt direct + * printing to all enabled consoles + * + * Since it is not possible to call into the console printing code from any + * context, there is no guarantee that direct printing will occur. + * + * This globally effects all printk() callers. + * + * Context: Any context. + */ +void printk_prefer_direct_enter(void) +{ + atomic_inc(&printk_prefer_direct); +} + +/** + * printk_prefer_direct_exit - restore printk() behavior + * + * Context: Any context. + */ +void printk_prefer_direct_exit(void) +{ + WARN_ON(atomic_dec_if_positive(&printk_prefer_direct) < 0); +} + +/* + * Calling printk() always wakes kthread printers so that they can + * flush the new message to their respective consoles. Also, if direct + * printing is allowed, printk() tries to flush the messages directly. + * + * Direct printing is allowed in situations when the kthreads + * are not available or the system is in a problematic state. + * + * See the implementation about possible races. + */ +static inline bool allow_direct_printing(void) +{ + /* + * Checking kthread availability is a possible race because the + * kthread printers can become permanently disabled during runtime. + * However, doing that requires holding the console_lock, so any + * pending messages will be direct printed by console_unlock(). + */ + if (!printk_kthreads_available) + return true; + + /* + * Prefer direct printing when the system is in a problematic state. + * The context that sets this state will always see the updated value. + * The other contexts do not care. Anyway, direct printing is just a + * best effort. The direct output is only possible when console_lock + * is not already taken and no kthread printers are actively printing. + */ + return (system_state > SYSTEM_RUNNING || + oops_in_progress || + atomic_read(&printk_prefer_direct)); +} + DECLARE_WAIT_QUEUE_HEAD(log_wait); /* All 3 protected by @syslog_lock. */ /* the next printk record to read by syslog(READ) or /proc/kmsg */ @@ -374,12 +499,6 @@ static u64 syslog_seq; static size_t syslog_partial; static bool syslog_time; -/* All 3 protected by @console_sem. */ -/* the next printk record to write to the console */ -static u64 console_seq; -static u64 exclusive_console_stop_seq; -static unsigned long console_dropped; - struct latched_seq { seqcount_latch_t latch; u64 val[2]; @@ -405,6 +524,9 @@ static struct latched_seq clear_seq = { /* the maximum size of a formatted record (i.e. with prefix added per line) */ #define CONSOLE_LOG_MAX 1024 +/* the maximum size for a dropped text message */ +#define DROPPED_TEXT_MAX 64 + /* the maximum size allowed to be reserved for a record */ #define LOG_LINE_MAX (CONSOLE_LOG_MAX - PREFIX_MAX) @@ -746,8 +868,19 @@ static ssize_t devkmsg_read(struct file *file, char __user *buf, goto out; } + /* + * Guarantee this task is visible on the waitqueue before + * checking the wake condition. + * + * The full memory barrier within set_current_state() of + * prepare_to_wait_event() pairs with the full memory barrier + * within wq_has_sleeper(). + * + * This pairs with __wake_up_klogd:A. + */ ret = wait_event_interruptible(log_wait, - prb_read_valid(prb, atomic64_read(&user->seq), r)); + prb_read_valid(prb, + atomic64_read(&user->seq), r)); /* LMM(devkmsg_read:A) */ if (ret) goto out; } @@ -1513,7 +1646,18 @@ static int syslog_print(char __user *buf, int size) seq = syslog_seq; mutex_unlock(&syslog_lock); - len = wait_event_interruptible(log_wait, prb_read_valid(prb, seq, NULL)); + /* + * Guarantee this task is visible on the waitqueue before + * checking the wake condition. + * + * The full memory barrier within set_current_state() of + * prepare_to_wait_event() pairs with the full memory barrier + * within wq_has_sleeper(). + * + * This pairs with __wake_up_klogd:A. + */ + len = wait_event_interruptible(log_wait, + prb_read_valid(prb, seq, NULL)); /* LMM(syslog_print:A) */ mutex_lock(&syslog_lock); if (len) @@ -1911,47 +2055,24 @@ static int console_trylock_spinning(void) } /* - * Call the console drivers, asking them to write out - * log_buf[start] to log_buf[end - 1]. - * The console_lock must be held. + * Call the specified console driver, asking it to write out the specified + * text and length. If @dropped_text is non-NULL and any records have been + * dropped, a dropped message will be written out first. */ -static void call_console_drivers(const char *ext_text, size_t ext_len, - const char *text, size_t len) +static void call_console_driver(struct console *con, const char *text, size_t len, + char *dropped_text) { - static char dropped_text[64]; - size_t dropped_len = 0; - struct console *con; - - trace_console_rcuidle(text, len); + size_t dropped_len; - if (!console_drivers) - return; - - if (console_dropped) { - dropped_len = snprintf(dropped_text, sizeof(dropped_text), + if (con->dropped && dropped_text) { + dropped_len = snprintf(dropped_text, DROPPED_TEXT_MAX, "** %lu printk messages dropped **\n", - console_dropped); - console_dropped = 0; + con->dropped); + con->dropped = 0; + con->write(con, dropped_text, dropped_len); } - for_each_console(con) { - if (exclusive_console && con != exclusive_console) - continue; - if (!(con->flags & CON_ENABLED)) - continue; - if (!con->write) - continue; - if (!cpu_online(smp_processor_id()) && - !(con->flags & CON_ANYTIME)) - continue; - if (con->flags & CON_EXTENDED) - con->write(con, ext_text, ext_len); - else { - if (dropped_len) - con->write(con, dropped_text, dropped_len); - con->write(con, text, len); - } - } + con->write(con, text, len); } /* @@ -2026,8 +2147,10 @@ static u8 *__printk_recursion_counter(void) int printk_delay_msec __read_mostly; -static inline void printk_delay(void) +static inline void printk_delay(int level) { + boot_delay_msec(level); + if (unlikely(printk_delay_msec)) { int m = printk_delay_msec; @@ -2041,7 +2164,7 @@ static inline void printk_delay(void) static inline u32 printk_caller_id(void) { return in_task() ? task_pid_nr(current) : - 0x80000000 + raw_smp_processor_id(); + 0x80000000 + smp_processor_id(); } /** @@ -2115,6 +2238,8 @@ static u16 printk_sprint(char *text, u16 size, int facility, } } + trace_console_rcuidle(text, text_len); + return text_len; } @@ -2123,7 +2248,6 @@ int vprintk_store(int facility, int level, const struct dev_printk_info *dev_info, const char *fmt, va_list args) { - const u32 caller_id = printk_caller_id(); struct prb_reserved_entry e; enum printk_info_flags flags = 0; struct printk_record r; @@ -2133,10 +2257,14 @@ int vprintk_store(int facility, int level, u8 *recursion_ptr; u16 reserve_size; va_list args2; + u32 caller_id; u16 text_len; int ret = 0; u64 ts_nsec; + if (!printk_enter_irqsave(recursion_ptr, irqflags)) + return 0; + /* * Since the duration of printk() can vary depending on the message * and state of the ringbuffer, grab the timestamp now so that it is @@ -2145,8 +2273,7 @@ int vprintk_store(int facility, int level, */ ts_nsec = local_clock(); - if (!printk_enter_irqsave(recursion_ptr, irqflags)) - return 0; + caller_id = printk_caller_id(); /* * The sprintf needs to come first since the syslog prefix might be @@ -2250,23 +2377,25 @@ asmlinkage int vprintk_emit(int facility, int level, in_sched = true; } - boot_delay_msec(level); - printk_delay(); + printk_delay(level); printed_len = vprintk_store(facility, level, dev_info, fmt, args); /* If called from the scheduler, we can not call up(). */ - if (!in_sched) { + if (!in_sched && allow_direct_printing()) { /* - * Disable preemption to avoid being preempted while holding - * console_sem which would prevent anyone from printing to - * console + * The caller may be holding system-critical or + * timing-sensitive locks. Disable preemption during direct + * printing of all remaining records to all consoles so that + * this context can return as soon as possible. Hopefully + * another printk() caller will take over the printing. */ preempt_disable(); /* * Try to acquire and then immediately release the console - * semaphore. The release will print out buffers and wake up - * /dev/kmsg and syslog() users. + * semaphore. The release will print out buffers. With the + * spinning variant, this context tries to take over the + * printing from another printing context. */ if (console_trylock_spinning()) console_unlock(); @@ -2297,18 +2426,21 @@ asmlinkage __visible int _printk(const char *fmt, ...) } EXPORT_SYMBOL(_printk); +static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progress); + +static void printk_start_kthread(struct console *con); + #else /* CONFIG_PRINTK */ #define CONSOLE_LOG_MAX 0 +#define DROPPED_TEXT_MAX 0 #define printk_time false #define prb_read_valid(rb, seq, r) false #define prb_first_valid_seq(rb) 0 +#define prb_next_seq(rb) 0 static u64 syslog_seq; -static u64 console_seq; -static u64 exclusive_console_stop_seq; -static unsigned long console_dropped; static size_t record_print_text(const struct printk_record *r, bool syslog, bool time) @@ -2325,9 +2457,14 @@ static ssize_t msg_print_ext_body(char *buf, size_t size, struct dev_printk_info *dev_info) { return 0; } static void console_lock_spinning_enable(void) { } static int console_lock_spinning_disable_and_check(void) { return 0; } -static void call_console_drivers(const char *ext_text, size_t ext_len, - const char *text, size_t len) {} +static void call_console_driver(struct console *con, const char *text, size_t len, + char *dropped_text) +{ +} static bool suppress_message_printing(int level) { return false; } +static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progress) { return true; } +static void printk_start_kthread(struct console *con) { } +static bool allow_direct_printing(void) { return true; } #endif /* CONFIG_PRINTK */ @@ -2515,6 +2652,7 @@ void suspend_console(void) if (!console_suspend_enabled) return; pr_info("Suspending console(s) (use no_console_suspend to debug)\n"); + pr_flush(1000, true); console_lock(); console_suspended = 1; up_console_sem(); @@ -2527,6 +2665,7 @@ void resume_console(void) down_console_sem(); console_suspended = 0; console_unlock(); + pr_flush(1000, true); } /** @@ -2544,6 +2683,14 @@ static int console_cpu_notify(unsigned int cpu) /* If trylock fails, someone else is doing the printing */ if (console_trylock()) console_unlock(); + else { + /* + * If a new CPU comes online, the conditions for + * printer_should_wake() may have changed for some + * kthread printer with !CON_ANYTIME. + */ + wake_up_klogd(); + } } return 0; } @@ -2563,7 +2710,7 @@ void console_lock(void) down_console_sem(); if (console_suspended) return; - console_locked = 1; + console_kthreads_block(); console_may_schedule = 1; } EXPORT_SYMBOL(console_lock); @@ -2584,33 +2731,32 @@ int console_trylock(void) up_console_sem(); return 0; } - console_locked = 1; + if (!console_kthreads_atomic_tryblock()) { + up_console_sem(); + return 0; + } console_may_schedule = 0; return 1; } EXPORT_SYMBOL(console_trylock); -int is_console_locked(void) -{ - return console_locked; -} -EXPORT_SYMBOL(is_console_locked); - /* - * Check if we have any console that is capable of printing while cpu is - * booting or shutting down. Requires console_sem. + * This is used to help to make sure that certain paths within the VT code are + * running with the console lock held. It is definitely not the perfect debug + * tool (it is not known if the VT code is the task holding the console lock), + * but it helps tracking those weird code paths in the console code such as + * when the console is suspended: where the console is not locked but no + * console printing may occur. + * + * Note: This returns true when the console is suspended but is not locked. + * This is intentional because the VT code must consider that situation + * the same as if the console was locked. */ -static int have_callable_console(void) +int is_console_locked(void) { - struct console *con; - - for_each_console(con) - if ((con->flags & CON_ENABLED) && - (con->flags & CON_ANYTIME)) - return 1; - - return 0; + return (console_kthreads_blocked || atomic_read(&console_kthreads_active)); } +EXPORT_SYMBOL(is_console_locked); /* * Return true when this CPU should unlock console_sem without pushing all @@ -2631,132 +2777,125 @@ static bool abandon_console_lock_in_panic(void) return atomic_read(&panic_cpu) != raw_smp_processor_id(); } +static inline bool __console_is_usable(short flags) +{ + if (!(flags & CON_ENABLED)) + return false; + + /* + * Console drivers may assume that per-cpu resources have been + * allocated. So unless they're explicitly marked as being able to + * cope (CON_ANYTIME) don't call them until this CPU is officially up. + */ + if (!cpu_online(raw_smp_processor_id()) && + !(flags & CON_ANYTIME)) + return false; + + return true; +} + /* - * Can we actually use the console at this time on this cpu? + * Check if the given console is currently capable and allowed to print + * records. * - * Console drivers may assume that per-cpu resources have been allocated. So - * unless they're explicitly marked as being able to cope (CON_ANYTIME) don't - * call them until this CPU is officially up. + * Requires holding the console_lock. */ -static inline int can_use_console(void) +static inline bool console_is_usable(struct console *con) { - return cpu_online(raw_smp_processor_id()) || have_callable_console(); + if (!con->write) + return false; + + return __console_is_usable(con->flags); } -/** - * console_unlock - unlock the console system +static void __console_unlock(void) +{ + /* + * Depending on whether console_lock() or console_trylock() was used, + * appropriately allow the kthread printers to continue. + */ + if (console_kthreads_blocked) + console_kthreads_unblock(); + else + console_kthreads_atomic_unblock(); + + /* + * New records may have arrived while the console was locked. + * Wake the kthread printers to print them. + */ + wake_up_klogd(); + + up_console_sem(); +} + +/* + * Print one record for the given console. The record printed is whatever + * record is the next available record for the given console. * - * Releases the console_lock which the caller holds on the console system - * and the console driver list. + * @text is a buffer of size CONSOLE_LOG_MAX. * - * While the console_lock was held, console output may have been buffered - * by printk(). If this is the case, console_unlock(); emits - * the output prior to releasing the lock. + * If extended messages should be printed, @ext_text is a buffer of size + * CONSOLE_EXT_LOG_MAX. Otherwise @ext_text must be NULL. * - * If there is output waiting, we wake /dev/kmsg and syslog() users. + * If dropped messages should be printed, @dropped_text is a buffer of size + * DROPPED_TEXT_MAX. Otherwise @dropped_text must be NULL. * - * console_unlock(); may be called from any context. + * @handover will be set to true if a printk waiter has taken over the + * console_lock, in which case the caller is no longer holding the + * console_lock. Otherwise it is set to false. A NULL pointer may be provided + * to disable allowing the console_lock to be taken over by a printk waiter. + * + * Returns false if the given console has no next record to print, otherwise + * true. + * + * Requires the console_lock if @handover is non-NULL. + * Requires con->lock otherwise. */ -void console_unlock(void) +static bool __console_emit_next_record(struct console *con, char *text, char *ext_text, + char *dropped_text, bool *handover) { - static char ext_text[CONSOLE_EXT_LOG_MAX]; - static char text[CONSOLE_LOG_MAX]; - static int panic_console_dropped; - unsigned long flags; - bool do_cond_resched, retry; + static atomic_t panic_console_dropped = ATOMIC_INIT(0); struct printk_info info; struct printk_record r; - u64 __maybe_unused next_seq; - - if (console_suspended) { - up_console_sem(); - return; - } - - prb_rec_init_rd(&r, &info, text, sizeof(text)); - - /* - * Console drivers are called with interrupts disabled, so - * @console_may_schedule should be cleared before; however, we may - * end up dumping a lot of lines, for example, if called from - * console registration path, and should invoke cond_resched() - * between lines if allowable. Not doing so can cause a very long - * scheduling stall on a slow console leading to RCU stall and - * softlockup warnings which exacerbate the issue with more - * messages practically incapacitating the system. - * - * console_trylock() is not able to detect the preemptive - * context reliably. Therefore the value must be stored before - * and cleared after the "again" goto label. - */ - do_cond_resched = console_may_schedule; -again: - console_may_schedule = 0; - - /* - * We released the console_sem lock, so we need to recheck if - * cpu is online and (if not) is there at least one CON_ANYTIME - * console. - */ - if (!can_use_console()) { - console_locked = 0; - up_console_sem(); - return; - } + unsigned long flags; + char *write_text; + size_t len; - for (;;) { - size_t ext_len = 0; - int handover; - size_t len; + prb_rec_init_rd(&r, &info, text, CONSOLE_LOG_MAX); -skip: - if (!prb_read_valid(prb, console_seq, &r)) - break; + if (handover) + *handover = false; - if (console_seq != r.info->seq) { - console_dropped += r.info->seq - console_seq; - console_seq = r.info->seq; - if (panic_in_progress() && panic_console_dropped++ > 10) { - suppress_panic_printk = 1; - pr_warn_once("Too many dropped messages. Suppress messages on non-panic CPUs to prevent livelock.\n"); - } - } + if (!prb_read_valid(prb, con->seq, &r)) + return false; - if (suppress_message_printing(r.info->level)) { - /* - * Skip record we have buffered and already printed - * directly to the console when we received it, and - * record that has level above the console loglevel. - */ - console_seq++; - goto skip; + if (con->seq != r.info->seq) { + con->dropped += r.info->seq - con->seq; + con->seq = r.info->seq; + if (panic_in_progress() && + atomic_fetch_inc_relaxed(&panic_console_dropped) > 10) { + suppress_panic_printk = 1; + pr_warn_once("Too many dropped messages. Suppress messages on non-panic CPUs to prevent livelock.\n"); } + } - /* Output to all consoles once old messages replayed. */ - if (unlikely(exclusive_console && - console_seq >= exclusive_console_stop_seq)) { - exclusive_console = NULL; - } + /* Skip record that has level above the console loglevel. */ + if (suppress_message_printing(r.info->level)) { + con->seq++; + goto skip; + } - /* - * Handle extended console text first because later - * record_print_text() will modify the record buffer in-place. - */ - if (nr_ext_console_drivers) { - ext_len = info_print_ext_header(ext_text, - sizeof(ext_text), - r.info); - ext_len += msg_print_ext_body(ext_text + ext_len, - sizeof(ext_text) - ext_len, - &r.text_buf[0], - r.info->text_len, - &r.info->dev_info); - } - len = record_print_text(&r, - console_msg_format & MSG_FORMAT_SYSLOG, - printk_time); - console_seq++; + if (ext_text) { + write_text = ext_text; + len = info_print_ext_header(ext_text, CONSOLE_EXT_LOG_MAX, r.info); + len += msg_print_ext_body(ext_text + len, CONSOLE_EXT_LOG_MAX - len, + &r.text_buf[0], r.info->text_len, &r.info->dev_info); + } else { + write_text = text; + len = record_print_text(&r, console_msg_format & MSG_FORMAT_SYSLOG, printk_time); + } + if (handover) { /* * While actively printing out messages, if another printk() * were to occur on another CPU, it may wait for this one to @@ -2770,38 +2909,187 @@ skip: printk_safe_enter_irqsave(flags); console_lock_spinning_enable(); - stop_critical_timings(); /* don't trace print latency */ - call_console_drivers(ext_text, ext_len, text, len); - start_critical_timings(); + /* don't trace irqsoff print latency */ + stop_critical_timings(); + } - handover = console_lock_spinning_disable_and_check(); - printk_safe_exit_irqrestore(flags); - if (handover) - return; + call_console_driver(con, write_text, len, dropped_text); - /* Allow panic_cpu to take over the consoles safely */ - if (abandon_console_lock_in_panic()) - break; + con->seq++; + + if (handover) { + start_critical_timings(); + *handover = console_lock_spinning_disable_and_check(); + printk_safe_exit_irqrestore(flags); + } +skip: + return true; +} - if (do_cond_resched) - cond_resched(); +/* + * Print a record for a given console, but allow another printk() caller to + * take over the console_lock and continue printing. + * + * Requires the console_lock, but depending on @handover after the call, the + * caller may no longer have the console_lock. + * + * See __console_emit_next_record() for argument and return details. + */ +static bool console_emit_next_record_transferable(struct console *con, char *text, char *ext_text, + char *dropped_text, bool *handover) +{ + /* + * Handovers are only supported if threaded printers are atomically + * blocked. The context taking over the console_lock may be atomic. + */ + if (!console_kthreads_atomically_blocked()) { + *handover = false; + handover = NULL; } - /* Get consistent value of the next-to-be-used sequence number. */ - next_seq = console_seq; + return __console_emit_next_record(con, text, ext_text, dropped_text, handover); +} - console_locked = 0; - up_console_sem(); +/* + * Print out all remaining records to all consoles. + * + * @do_cond_resched is set by the caller. It can be true only in schedulable + * context. + * + * @next_seq is set to the sequence number after the last available record. + * The value is valid only when this function returns true. It means that all + * usable consoles are completely flushed. + * + * @handover will be set to true if a printk waiter has taken over the + * console_lock, in which case the caller is no longer holding the + * console_lock. Otherwise it is set to false. + * + * Returns true when there was at least one usable console and all messages + * were flushed to all usable consoles. A returned false informs the caller + * that everything was not flushed (either there were no usable consoles or + * another context has taken over printing or it is a panic situation and this + * is not the panic CPU or direct printing is not preferred). Regardless the + * reason, the caller should assume it is not useful to immediately try again. + * + * Requires the console_lock. + */ +static bool console_flush_all(bool do_cond_resched, u64 *next_seq, bool *handover) +{ + static char dropped_text[DROPPED_TEXT_MAX]; + static char ext_text[CONSOLE_EXT_LOG_MAX]; + static char text[CONSOLE_LOG_MAX]; + bool any_usable = false; + struct console *con; + bool any_progress; + + *next_seq = 0; + *handover = false; + + do { + /* Let the kthread printers do the work if they can. */ + if (!allow_direct_printing()) + return false; + + any_progress = false; + + for_each_console(con) { + bool progress; + + if (!console_is_usable(con)) + continue; + any_usable = true; + + if (con->flags & CON_EXTENDED) { + /* Extended consoles do not print "dropped messages". */ + progress = console_emit_next_record_transferable(con, &text[0], + &ext_text[0], NULL, handover); + } else { + progress = console_emit_next_record_transferable(con, &text[0], + NULL, &dropped_text[0], handover); + } + if (*handover) + return false; + + /* Track the next of the highest seq flushed. */ + if (con->seq > *next_seq) + *next_seq = con->seq; + + if (!progress) + continue; + any_progress = true; + + /* Allow panic_cpu to take over the consoles safely. */ + if (abandon_console_lock_in_panic()) + return false; + + if (do_cond_resched) + cond_resched(); + } + } while (any_progress); + + return any_usable; +} + +/** + * console_unlock - unlock the console system + * + * Releases the console_lock which the caller holds on the console system + * and the console driver list. + * + * While the console_lock was held, console output may have been buffered + * by printk(). If this is the case, console_unlock(); emits + * the output prior to releasing the lock. + * + * console_unlock(); may be called from any context. + */ +void console_unlock(void) +{ + bool do_cond_resched; + bool handover; + bool flushed; + u64 next_seq; + + if (console_suspended) { + up_console_sem(); + return; + } /* - * Someone could have filled up the buffer again, so re-check if there's - * something to flush. In case we cannot trylock the console_sem again, - * there's a new owner and the console_unlock() from them will do the - * flush, no worries. + * Console drivers are called with interrupts disabled, so + * @console_may_schedule should be cleared before; however, we may + * end up dumping a lot of lines, for example, if called from + * console registration path, and should invoke cond_resched() + * between lines if allowable. Not doing so can cause a very long + * scheduling stall on a slow console leading to RCU stall and + * softlockup warnings which exacerbate the issue with more + * messages practically incapacitating the system. Therefore, create + * a local to use for the printing loop. */ - retry = prb_read_valid(prb, next_seq, NULL); - if (retry && !abandon_console_lock_in_panic() && console_trylock()) - goto again; + do_cond_resched = console_may_schedule; + + do { + console_may_schedule = 0; + + flushed = console_flush_all(do_cond_resched, &next_seq, &handover); + if (!handover) + __console_unlock(); + + /* + * Abort if there was a failure to flush all messages to all + * usable consoles. Either it is not possible to flush (in + * which case it would be an infinite loop of retrying) or + * another context has taken over printing. + */ + if (!flushed) + break; + + /* + * Some context may have added new records after + * console_flush_all() but before unlocking the console. + * Re-check if there is a new record to flush. If the trylock + * fails, another context is already handling the printing. + */ + } while (prb_read_valid(prb, next_seq, NULL) && console_trylock()); } EXPORT_SYMBOL(console_unlock); @@ -2832,15 +3120,21 @@ void console_unblank(void) if (oops_in_progress) { if (down_trylock_console_sem() != 0) return; + if (!console_kthreads_atomic_tryblock()) { + up_console_sem(); + return; + } } else console_lock(); - console_locked = 1; console_may_schedule = 0; for_each_console(c) if ((c->flags & CON_ENABLED) && c->unblank) c->unblank(); console_unlock(); + + if (!oops_in_progress) + pr_flush(1000, true); } /** @@ -2861,8 +3155,14 @@ void console_flush_on_panic(enum con_flush_mode mode) console_trylock(); console_may_schedule = 0; - if (mode == CONSOLE_REPLAY_ALL) - console_seq = prb_first_valid_seq(prb); + if (mode == CONSOLE_REPLAY_ALL) { + struct console *c; + u64 seq; + + seq = prb_first_valid_seq(prb); + for_each_console(c) + c->seq = seq; + } console_unlock(); } @@ -2893,6 +3193,7 @@ struct tty_driver *console_device(int *index) */ void console_stop(struct console *console) { + __pr_flush(console, 1000, true); console_lock(); console->flags &= ~CON_ENABLED; console_unlock(); @@ -2904,6 +3205,7 @@ void console_start(struct console *console) console_lock(); console->flags |= CON_ENABLED; console_unlock(); + __pr_flush(console, 1000, true); } EXPORT_SYMBOL(console_start); @@ -2990,6 +3292,11 @@ static void try_enable_default_console(struct console *newcon) newcon->flags |= CON_CONSDEV; } +#define con_printk(lvl, con, fmt, ...) \ + printk(lvl pr_fmt("%sconsole [%s%d] " fmt), \ + (con->flags & CON_BOOT) ? "boot" : "", \ + con->name, con->index, ##__VA_ARGS__) + /* * The console driver calls this routine during kernel initialization * to register the console printing procedure with printk() and to @@ -3097,27 +3404,24 @@ void register_console(struct console *newcon) if (newcon->flags & CON_EXTENDED) nr_ext_console_drivers++; - if (newcon->flags & CON_PRINTBUFFER) { - /* - * console_unlock(); will print out the buffered messages - * for us. - * - * We're about to replay the log buffer. Only do this to the - * just-registered console to avoid excessive message spam to - * the already-registered consoles. - * - * Set exclusive_console with disabled interrupts to reduce - * race window with eventual console_flush_on_panic() that - * ignores console_lock. - */ - exclusive_console = newcon; - exclusive_console_stop_seq = console_seq; + newcon->dropped = 0; + newcon->thread = NULL; + newcon->blocked = true; + mutex_init(&newcon->lock); + if (newcon->flags & CON_PRINTBUFFER) { /* Get a consistent copy of @syslog_seq. */ mutex_lock(&syslog_lock); - console_seq = syslog_seq; + newcon->seq = syslog_seq; mutex_unlock(&syslog_lock); + } else { + /* Begin with next message. */ + newcon->seq = prb_next_seq(prb); } + + if (printk_kthreads_available) + printk_start_kthread(newcon); + console_unlock(); console_sysfs_notify(); @@ -3128,9 +3432,7 @@ void register_console(struct console *newcon) * users know there might be something in the kernel's log buffer that * went to the bootconsole (that they do not see on the real console) */ - pr_info("%sconsole [%s%d] enabled\n", - (newcon->flags & CON_BOOT) ? "boot" : "" , - newcon->name, newcon->index); + con_printk(KERN_INFO, newcon, "enabled\n"); if (bootcon_enabled && ((newcon->flags & (CON_CONSDEV | CON_BOOT)) == CON_CONSDEV) && !keep_bootcon) { @@ -3146,12 +3448,11 @@ EXPORT_SYMBOL(register_console); int unregister_console(struct console *console) { + struct task_struct *thd; struct console *con; int res; - pr_info("%sconsole [%s%d] disabled\n", - (console->flags & CON_BOOT) ? "boot" : "" , - console->name, console->index); + con_printk(KERN_INFO, console, "disabled\n"); res = _braille_unregister_console(console); if (res < 0) @@ -3188,7 +3489,20 @@ int unregister_console(struct console *console) console_drivers->flags |= CON_CONSDEV; console->flags &= ~CON_ENABLED; + + /* + * console->thread can only be cleared under the console lock. But + * stopping the thread must be done without the console lock. The + * task that clears @thread is the task that stops the kthread. + */ + thd = console->thread; + console->thread = NULL; + console_unlock(); + + if (thd) + kthread_stop(thd); + console_sysfs_notify(); if (console->exit) @@ -3284,12 +3598,294 @@ static int __init printk_late_init(void) } late_initcall(printk_late_init); +static int __init printk_activate_kthreads(void) +{ + struct console *con; + + console_lock(); + printk_kthreads_available = true; + for_each_console(con) + printk_start_kthread(con); + console_unlock(); + + return 0; +} +early_initcall(printk_activate_kthreads); + #if defined CONFIG_PRINTK +/* If @con is specified, only wait for that console. Otherwise wait for all. */ +static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progress) +{ + int remaining = timeout_ms; + struct console *c; + u64 last_diff = 0; + u64 printk_seq; + u64 diff; + u64 seq; + + might_sleep(); + + seq = prb_next_seq(prb); + + for (;;) { + diff = 0; + + console_lock(); + for_each_console(c) { + if (con && con != c) + continue; + if (!console_is_usable(c)) + continue; + printk_seq = c->seq; + if (printk_seq < seq) + diff += seq - printk_seq; + } + console_unlock(); + + if (diff != last_diff && reset_on_progress) + remaining = timeout_ms; + + if (diff == 0 || remaining == 0) + break; + + if (remaining < 0) { + /* no timeout limit */ + msleep(100); + } else if (remaining < 100) { + msleep(remaining); + remaining = 0; + } else { + msleep(100); + remaining -= 100; + } + + last_diff = diff; + } + + return (diff == 0); +} + +/** + * pr_flush() - Wait for printing threads to catch up. + * + * @timeout_ms: The maximum time (in ms) to wait. + * @reset_on_progress: Reset the timeout if forward progress is seen. + * + * A value of 0 for @timeout_ms means no waiting will occur. A value of -1 + * represents infinite waiting. + * + * If @reset_on_progress is true, the timeout will be reset whenever any + * printer has been seen to make some forward progress. + * + * Context: Process context. May sleep while acquiring console lock. + * Return: true if all enabled printers are caught up. + */ +bool pr_flush(int timeout_ms, bool reset_on_progress) +{ + return __pr_flush(NULL, timeout_ms, reset_on_progress); +} +EXPORT_SYMBOL(pr_flush); + +static void __printk_fallback_preferred_direct(void) +{ + printk_prefer_direct_enter(); + pr_err("falling back to preferred direct printing\n"); + printk_kthreads_available = false; +} + +/* + * Enter preferred direct printing, but never exit. Mark console threads as + * unavailable. The system is then forever in preferred direct printing and + * any printing threads will exit. + * + * Must *not* be called under console_lock. Use + * __printk_fallback_preferred_direct() if already holding console_lock. + */ +static void printk_fallback_preferred_direct(void) +{ + console_lock(); + __printk_fallback_preferred_direct(); + console_unlock(); +} + +/* + * Print a record for a given console, not allowing another printk() caller + * to take over. This is appropriate for contexts that do not have the + * console_lock. + * + * See __console_emit_next_record() for argument and return details. + */ +static bool console_emit_next_record(struct console *con, char *text, char *ext_text, + char *dropped_text) +{ + return __console_emit_next_record(con, text, ext_text, dropped_text, NULL); +} + +static bool printer_should_wake(struct console *con, u64 seq) +{ + short flags; + + if (kthread_should_stop() || !printk_kthreads_available) + return true; + + if (con->blocked || + console_kthreads_atomically_blocked()) { + return false; + } + + /* + * This is an unsafe read from con->flags, but a false positive is + * not a problem. Worst case it would allow the printer to wake up + * although it is disabled. But the printer will notice that when + * attempting to print and instead go back to sleep. + */ + flags = data_race(READ_ONCE(con->flags)); + + if (!__console_is_usable(flags)) + return false; + + return prb_read_valid(prb, seq, NULL); +} + +static int printk_kthread_func(void *data) +{ + struct console *con = data; + char *dropped_text = NULL; + char *ext_text = NULL; + u64 seq = 0; + char *text; + int error; + + text = kmalloc(CONSOLE_LOG_MAX, GFP_KERNEL); + if (!text) { + con_printk(KERN_ERR, con, "failed to allocate text buffer\n"); + printk_fallback_preferred_direct(); + goto out; + } + + if (con->flags & CON_EXTENDED) { + ext_text = kmalloc(CONSOLE_EXT_LOG_MAX, GFP_KERNEL); + if (!ext_text) { + con_printk(KERN_ERR, con, "failed to allocate ext_text buffer\n"); + printk_fallback_preferred_direct(); + goto out; + } + } else { + dropped_text = kmalloc(DROPPED_TEXT_MAX, GFP_KERNEL); + if (!dropped_text) { + con_printk(KERN_ERR, con, "failed to allocate dropped_text buffer\n"); + printk_fallback_preferred_direct(); + goto out; + } + } + + con_printk(KERN_INFO, con, "printing thread started\n"); + + for (;;) { + /* + * Guarantee this task is visible on the waitqueue before + * checking the wake condition. + * + * The full memory barrier within set_current_state() of + * prepare_to_wait_event() pairs with the full memory barrier + * within wq_has_sleeper(). + * + * This pairs with __wake_up_klogd:A. + */ + error = wait_event_interruptible(log_wait, + printer_should_wake(con, seq)); /* LMM(printk_kthread_func:A) */ + + if (kthread_should_stop() || !printk_kthreads_available) + break; + + if (error) + continue; + + error = mutex_lock_interruptible(&con->lock); + if (error) + continue; + + if (con->blocked || + !console_kthread_printing_tryenter()) { + /* Another context has locked the console_lock. */ + mutex_unlock(&con->lock); + continue; + } + + /* + * Although this context has not locked the console_lock, it + * is known that the console_lock is not locked and it is not + * possible for any other context to lock the console_lock. + * Therefore it is safe to read con->flags. + */ + + if (!__console_is_usable(con->flags)) { + console_kthread_printing_exit(); + mutex_unlock(&con->lock); + continue; + } + + /* + * Even though the printk kthread is always preemptible, it is + * still not allowed to call cond_resched() from within + * console drivers. The task may become non-preemptible in the + * console driver call chain. For example, vt_console_print() + * takes a spinlock and then can call into fbcon_redraw(), + * which can conditionally invoke cond_resched(). + */ + console_may_schedule = 0; + console_emit_next_record(con, text, ext_text, dropped_text); + + seq = con->seq; + + console_kthread_printing_exit(); + + mutex_unlock(&con->lock); + } + + con_printk(KERN_INFO, con, "printing thread stopped\n"); +out: + kfree(dropped_text); + kfree(ext_text); + kfree(text); + + console_lock(); + /* + * If this kthread is being stopped by another task, con->thread will + * already be NULL. That is fine. The important thing is that it is + * NULL after the kthread exits. + */ + con->thread = NULL; + console_unlock(); + + return 0; +} + +/* Must be called under console_lock. */ +static void printk_start_kthread(struct console *con) +{ + /* + * Do not start a kthread if there is no write() callback. The + * kthreads assume the write() callback exists. + */ + if (!con->write) + return; + + con->thread = kthread_run(printk_kthread_func, con, + "pr/%s%d", con->name, con->index); + if (IS_ERR(con->thread)) { + con->thread = NULL; + con_printk(KERN_ERR, con, "unable to start printing thread\n"); + __printk_fallback_preferred_direct(); + return; + } +} + /* * Delayed printk version, for scheduler-internal messages: */ -#define PRINTK_PENDING_WAKEUP 0x01 -#define PRINTK_PENDING_OUTPUT 0x02 +#define PRINTK_PENDING_WAKEUP 0x01 +#define PRINTK_PENDING_DIRECT_OUTPUT 0x02 static DEFINE_PER_CPU(int, printk_pending); @@ -3297,41 +3893,71 @@ static void wake_up_klogd_work_func(struct irq_work *irq_work) { int pending = this_cpu_xchg(printk_pending, 0); - if (pending & PRINTK_PENDING_OUTPUT) { + if (pending & PRINTK_PENDING_DIRECT_OUTPUT) { + printk_prefer_direct_enter(); + /* If trylock fails, someone else is doing the printing */ if (console_trylock()) console_unlock(); + + printk_prefer_direct_exit(); } if (pending & PRINTK_PENDING_WAKEUP) - wake_up_interruptible(&log_wait); + wake_up_interruptible_all(&log_wait); } static DEFINE_PER_CPU(struct irq_work, wake_up_klogd_work) = IRQ_WORK_INIT_LAZY(wake_up_klogd_work_func); -void wake_up_klogd(void) +static void __wake_up_klogd(int val) { if (!printk_percpu_data_ready()) return; preempt_disable(); - if (waitqueue_active(&log_wait)) { - this_cpu_or(printk_pending, PRINTK_PENDING_WAKEUP); + /* + * Guarantee any new records can be seen by tasks preparing to wait + * before this context checks if the wait queue is empty. + * + * The full memory barrier within wq_has_sleeper() pairs with the full + * memory barrier within set_current_state() of + * prepare_to_wait_event(), which is called after ___wait_event() adds + * the waiter but before it has checked the wait condition. + * + * This pairs with devkmsg_read:A, syslog_print:A, and + * printk_kthread_func:A. + */ + if (wq_has_sleeper(&log_wait) || /* LMM(__wake_up_klogd:A) */ + (val & PRINTK_PENDING_DIRECT_OUTPUT)) { + this_cpu_or(printk_pending, val); irq_work_queue(this_cpu_ptr(&wake_up_klogd_work)); } preempt_enable(); } +void wake_up_klogd(void) +{ + __wake_up_klogd(PRINTK_PENDING_WAKEUP); +} + void defer_console_output(void) { - if (!printk_percpu_data_ready()) - return; + /* + * New messages may have been added directly to the ringbuffer + * using vprintk_store(), so wake any waiters as well. + */ + int val = PRINTK_PENDING_WAKEUP; - preempt_disable(); - this_cpu_or(printk_pending, PRINTK_PENDING_OUTPUT); - irq_work_queue(this_cpu_ptr(&wake_up_klogd_work)); - preempt_enable(); + /* + * Make sure that some context will print the messages when direct + * printing is allowed. This happens in situations when the kthreads + * may not be as reliable or perhaps unusable. + */ + if (allow_direct_printing()) + val |= PRINTK_PENDING_DIRECT_OUTPUT; + + __wake_up_klogd(val); } void printk_trigger_flush(void) @@ -3667,26 +4293,26 @@ EXPORT_SYMBOL_GPL(kmsg_dump_rewind); #endif #ifdef CONFIG_SMP -static atomic_t printk_cpulock_owner = ATOMIC_INIT(-1); -static atomic_t printk_cpulock_nested = ATOMIC_INIT(0); +static atomic_t printk_cpu_sync_owner = ATOMIC_INIT(-1); +static atomic_t printk_cpu_sync_nested = ATOMIC_INIT(0); /** - * __printk_wait_on_cpu_lock() - Busy wait until the printk cpu-reentrant - * spinning lock is not owned by any CPU. + * __printk_cpu_sync_wait() - Busy wait until the printk cpu-reentrant + * spinning lock is not owned by any CPU. * * Context: Any context. */ -void __printk_wait_on_cpu_lock(void) +void __printk_cpu_sync_wait(void) { do { cpu_relax(); - } while (atomic_read(&printk_cpulock_owner) != -1); + } while (atomic_read(&printk_cpu_sync_owner) != -1); } -EXPORT_SYMBOL(__printk_wait_on_cpu_lock); +EXPORT_SYMBOL(__printk_cpu_sync_wait); /** - * __printk_cpu_trylock() - Try to acquire the printk cpu-reentrant - * spinning lock. + * __printk_cpu_sync_try_get() - Try to acquire the printk cpu-reentrant + * spinning lock. * * If no processor has the lock, the calling processor takes the lock and * becomes the owner. If the calling processor is already the owner of the @@ -3695,7 +4321,7 @@ EXPORT_SYMBOL(__printk_wait_on_cpu_lock); * Context: Any context. Expects interrupts to be disabled. * Return: 1 on success, otherwise 0. */ -int __printk_cpu_trylock(void) +int __printk_cpu_sync_try_get(void) { int cpu; int old; @@ -3705,79 +4331,80 @@ int __printk_cpu_trylock(void) /* * Guarantee loads and stores from this CPU when it is the lock owner * are _not_ visible to the previous lock owner. This pairs with - * __printk_cpu_unlock:B. + * __printk_cpu_sync_put:B. * * Memory barrier involvement: * - * If __printk_cpu_trylock:A reads from __printk_cpu_unlock:B, then - * __printk_cpu_unlock:A can never read from __printk_cpu_trylock:B. + * If __printk_cpu_sync_try_get:A reads from __printk_cpu_sync_put:B, + * then __printk_cpu_sync_put:A can never read from + * __printk_cpu_sync_try_get:B. * * Relies on: * - * RELEASE from __printk_cpu_unlock:A to __printk_cpu_unlock:B + * RELEASE from __printk_cpu_sync_put:A to __printk_cpu_sync_put:B * of the previous CPU * matching - * ACQUIRE from __printk_cpu_trylock:A to __printk_cpu_trylock:B - * of this CPU + * ACQUIRE from __printk_cpu_sync_try_get:A to + * __printk_cpu_sync_try_get:B of this CPU */ - old = atomic_cmpxchg_acquire(&printk_cpulock_owner, -1, - cpu); /* LMM(__printk_cpu_trylock:A) */ + old = atomic_cmpxchg_acquire(&printk_cpu_sync_owner, -1, + cpu); /* LMM(__printk_cpu_sync_try_get:A) */ if (old == -1) { /* * This CPU is now the owner and begins loading/storing - * data: LMM(__printk_cpu_trylock:B) + * data: LMM(__printk_cpu_sync_try_get:B) */ return 1; } else if (old == cpu) { /* This CPU is already the owner. */ - atomic_inc(&printk_cpulock_nested); + atomic_inc(&printk_cpu_sync_nested); return 1; } return 0; } -EXPORT_SYMBOL(__printk_cpu_trylock); +EXPORT_SYMBOL(__printk_cpu_sync_try_get); /** - * __printk_cpu_unlock() - Release the printk cpu-reentrant spinning lock. + * __printk_cpu_sync_put() - Release the printk cpu-reentrant spinning lock. * * The calling processor must be the owner of the lock. * * Context: Any context. Expects interrupts to be disabled. */ -void __printk_cpu_unlock(void) +void __printk_cpu_sync_put(void) { - if (atomic_read(&printk_cpulock_nested)) { - atomic_dec(&printk_cpulock_nested); + if (atomic_read(&printk_cpu_sync_nested)) { + atomic_dec(&printk_cpu_sync_nested); return; } /* * This CPU is finished loading/storing data: - * LMM(__printk_cpu_unlock:A) + * LMM(__printk_cpu_sync_put:A) */ /* * Guarantee loads and stores from this CPU when it was the * lock owner are visible to the next lock owner. This pairs - * with __printk_cpu_trylock:A. + * with __printk_cpu_sync_try_get:A. * * Memory barrier involvement: * - * If __printk_cpu_trylock:A reads from __printk_cpu_unlock:B, - * then __printk_cpu_trylock:B reads from __printk_cpu_unlock:A. + * If __printk_cpu_sync_try_get:A reads from __printk_cpu_sync_put:B, + * then __printk_cpu_sync_try_get:B reads from __printk_cpu_sync_put:A. * * Relies on: * - * RELEASE from __printk_cpu_unlock:A to __printk_cpu_unlock:B + * RELEASE from __printk_cpu_sync_put:A to __printk_cpu_sync_put:B * of this CPU * matching - * ACQUIRE from __printk_cpu_trylock:A to __printk_cpu_trylock:B - * of the next CPU + * ACQUIRE from __printk_cpu_sync_try_get:A to + * __printk_cpu_sync_try_get:B of the next CPU */ - atomic_set_release(&printk_cpulock_owner, - -1); /* LMM(__printk_cpu_unlock:B) */ + atomic_set_release(&printk_cpu_sync_owner, + -1); /* LMM(__printk_cpu_sync_put:B) */ } -EXPORT_SYMBOL(__printk_cpu_unlock); +EXPORT_SYMBOL(__printk_cpu_sync_put); #endif /* CONFIG_SMP */ diff --git a/kernel/rcu/Kconfig b/kernel/rcu/Kconfig index bf8e341e75b4..1c630e573548 100644 --- a/kernel/rcu/Kconfig +++ b/kernel/rcu/Kconfig @@ -77,31 +77,56 @@ config TASKS_RCU_GENERIC This option enables generic infrastructure code supporting task-based RCU implementations. Not for manual selection. +config FORCE_TASKS_RCU + bool "Force selection of TASKS_RCU" + depends on RCU_EXPERT + select TASKS_RCU + default n + help + This option force-enables a task-based RCU implementation + that uses only voluntary context switch (not preemption!), + idle, and user-mode execution as quiescent states. Not for + manual selection in most cases. + config TASKS_RCU - def_bool PREEMPTION + bool + default n + select IRQ_WORK + +config FORCE_TASKS_RUDE_RCU + bool "Force selection of Tasks Rude RCU" + depends on RCU_EXPERT + select TASKS_RUDE_RCU + default n help - This option enables a task-based RCU implementation that uses - only voluntary context switch (not preemption!), idle, and - user-mode execution as quiescent states. Not for manual selection. + This option force-enables a task-based RCU implementation + that uses only context switch (including preemption) and + user-mode execution as quiescent states. It forces IPIs and + context switches on all online CPUs, including idle ones, + so use with caution. Not for manual selection in most cases. config TASKS_RUDE_RCU - def_bool 0 + bool + default n + select IRQ_WORK + +config FORCE_TASKS_TRACE_RCU + bool "Force selection of Tasks Trace RCU" + depends on RCU_EXPERT + select TASKS_TRACE_RCU + default n help This option enables a task-based RCU implementation that uses - only context switch (including preemption) and user-mode - execution as quiescent states. It forces IPIs and context - switches on all online CPUs, including idle ones, so use - with caution. + explicit rcu_read_lock_trace() read-side markers, and allows + these readers to appear in the idle loop as well as on the + CPU hotplug code paths. It can force IPIs on online CPUs, + including idle ones, so use with caution. Not for manual + selection in most cases. config TASKS_TRACE_RCU - def_bool 0 + bool + default n select IRQ_WORK - help - This option enables a task-based RCU implementation that uses - explicit rcu_read_lock_trace() read-side markers, and allows - these readers to appear in the idle loop as well as on the CPU - hotplug code paths. It can force IPIs on online CPUs, including - idle ones, so use with caution. config RCU_STALL_COMMON def_bool TREE_RCU @@ -195,6 +220,20 @@ config RCU_BOOST_DELAY Accept the default if unsure. +config RCU_EXP_KTHREAD + bool "Perform RCU expedited work in a real-time kthread" + depends on RCU_BOOST && RCU_EXPERT + default !PREEMPT_RT && NR_CPUS <= 32 + help + Use this option to further reduce the latencies of expedited + grace periods at the expense of being more disruptive. + + This option is disabled by default on PREEMPT_RT=y kernels which + disable expedited grace periods after boot by unconditionally + setting rcupdate.rcu_normal_after_boot=1. + + Accept the default if unsure. + config RCU_NOCB_CPU bool "Offload RCU callback processing from boot-selected CPUs" depends on TREE_RCU @@ -225,7 +264,7 @@ config RCU_NOCB_CPU config TASKS_TRACE_RCU_READ_MB bool "Tasks Trace RCU readers use memory barriers in user and idle" - depends on RCU_EXPERT + depends on RCU_EXPERT && TASKS_TRACE_RCU default PREEMPT_RT || NR_CPUS < 8 help Use this option to further reduce the number of IPIs sent diff --git a/kernel/rcu/Kconfig.debug b/kernel/rcu/Kconfig.debug index 4fd64999300f..9b64e55d4f61 100644 --- a/kernel/rcu/Kconfig.debug +++ b/kernel/rcu/Kconfig.debug @@ -28,9 +28,6 @@ config RCU_SCALE_TEST depends on DEBUG_KERNEL select TORTURE_TEST select SRCU - select TASKS_RCU - select TASKS_RUDE_RCU - select TASKS_TRACE_RCU default n help This option provides a kernel module that runs performance @@ -47,9 +44,6 @@ config RCU_TORTURE_TEST depends on DEBUG_KERNEL select TORTURE_TEST select SRCU - select TASKS_RCU - select TASKS_RUDE_RCU - select TASKS_TRACE_RCU default n help This option provides a kernel module that runs torture tests @@ -66,9 +60,6 @@ config RCU_REF_SCALE_TEST depends on DEBUG_KERNEL select TORTURE_TEST select SRCU - select TASKS_RCU - select TASKS_RUDE_RCU - select TASKS_TRACE_RCU default n help This option provides a kernel module that runs performance tests @@ -91,6 +82,20 @@ config RCU_CPU_STALL_TIMEOUT RCU grace period persists, additional CPU stall warnings are printed at more widely spaced intervals. +config RCU_EXP_CPU_STALL_TIMEOUT + int "Expedited RCU CPU stall timeout in milliseconds" + depends on RCU_STALL_COMMON + range 0 21000 + default 20 if ANDROID + default 0 if !ANDROID + help + If a given expedited RCU grace period extends more than the + specified number of milliseconds, a CPU stall warning is printed. + If the RCU grace period persists, additional CPU stall warnings + are printed at more widely spaced intervals. A value of zero + says to use the RCU_CPU_STALL_TIMEOUT value converted from + seconds to milliseconds. + config RCU_TRACE bool "Enable tracing for RCU" depends on DEBUG_KERNEL diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h index 24b5f2c2de87..152492d52715 100644 --- a/kernel/rcu/rcu.h +++ b/kernel/rcu/rcu.h @@ -210,7 +210,9 @@ static inline bool rcu_stall_is_suppressed_at_boot(void) extern int rcu_cpu_stall_ftrace_dump; extern int rcu_cpu_stall_suppress; extern int rcu_cpu_stall_timeout; +extern int rcu_exp_cpu_stall_timeout; int rcu_jiffies_till_stall_check(void); +int rcu_exp_jiffies_till_stall_check(void); static inline bool rcu_stall_is_suppressed(void) { @@ -523,6 +525,8 @@ static inline bool rcu_check_boost_fail(unsigned long gp_state, int *cpup) { ret static inline void show_rcu_gp_kthreads(void) { } static inline int rcu_get_gp_kthreads_prio(void) { return 0; } static inline void rcu_fwd_progress_check(unsigned long j) { } +static inline void rcu_gp_slow_register(atomic_t *rgssp) { } +static inline void rcu_gp_slow_unregister(atomic_t *rgssp) { } #else /* #ifdef CONFIG_TINY_RCU */ bool rcu_dynticks_zero_in_eqs(int cpu, int *vp); unsigned long rcu_get_gp_seq(void); @@ -534,14 +538,19 @@ int rcu_get_gp_kthreads_prio(void); void rcu_fwd_progress_check(unsigned long j); void rcu_force_quiescent_state(void); extern struct workqueue_struct *rcu_gp_wq; +#ifdef CONFIG_RCU_EXP_KTHREAD +extern struct kthread_worker *rcu_exp_gp_kworker; +extern struct kthread_worker *rcu_exp_par_gp_kworker; +#else /* !CONFIG_RCU_EXP_KTHREAD */ extern struct workqueue_struct *rcu_par_gp_wq; +#endif /* CONFIG_RCU_EXP_KTHREAD */ +void rcu_gp_slow_register(atomic_t *rgssp); +void rcu_gp_slow_unregister(atomic_t *rgssp); #endif /* #else #ifdef CONFIG_TINY_RCU */ #ifdef CONFIG_RCU_NOCB_CPU -bool rcu_is_nocb_cpu(int cpu); void rcu_bind_current_to_nocb(void); #else -static inline bool rcu_is_nocb_cpu(int cpu) { return false; } static inline void rcu_bind_current_to_nocb(void) { } #endif diff --git a/kernel/rcu/rcu_segcblist.c b/kernel/rcu/rcu_segcblist.c index 81145c3ece25..c54ea2b6a36b 100644 --- a/kernel/rcu/rcu_segcblist.c +++ b/kernel/rcu/rcu_segcblist.c @@ -505,10 +505,10 @@ void rcu_segcblist_advance(struct rcu_segcblist *rsclp, unsigned long seq) WRITE_ONCE(rsclp->tails[j], rsclp->tails[RCU_DONE_TAIL]); /* - * Callbacks moved, so clean up the misordered ->tails[] pointers - * that now point into the middle of the list of ready-to-invoke - * callbacks. The overall effect is to copy down the later pointers - * into the gap that was created by the now-ready segments. + * Callbacks moved, so there might be an empty RCU_WAIT_TAIL + * and a non-empty RCU_NEXT_READY_TAIL. If so, copy the + * RCU_NEXT_READY_TAIL segment to fill the RCU_WAIT_TAIL gap + * created by the now-ready-to-invoke segments. */ for (j = RCU_WAIT_TAIL; i < RCU_NEXT_TAIL; i++, j++) { if (rsclp->tails[j] == rsclp->tails[RCU_NEXT_TAIL]) diff --git a/kernel/rcu/rcuscale.c b/kernel/rcu/rcuscale.c index 5e4f1f83d38e..277a5bfb37d4 100644 --- a/kernel/rcu/rcuscale.c +++ b/kernel/rcu/rcuscale.c @@ -268,6 +268,8 @@ static struct rcu_scale_ops srcud_ops = { .name = "srcud" }; +#ifdef CONFIG_TASKS_RCU + /* * Definitions for RCU-tasks scalability testing. */ @@ -295,6 +297,16 @@ static struct rcu_scale_ops tasks_ops = { .name = "tasks" }; +#define TASKS_OPS &tasks_ops, + +#else // #ifdef CONFIG_TASKS_RCU + +#define TASKS_OPS + +#endif // #else // #ifdef CONFIG_TASKS_RCU + +#ifdef CONFIG_TASKS_TRACE_RCU + /* * Definitions for RCU-tasks-trace scalability testing. */ @@ -324,6 +336,14 @@ static struct rcu_scale_ops tasks_tracing_ops = { .name = "tasks-tracing" }; +#define TASKS_TRACING_OPS &tasks_tracing_ops, + +#else // #ifdef CONFIG_TASKS_TRACE_RCU + +#define TASKS_TRACING_OPS + +#endif // #else // #ifdef CONFIG_TASKS_TRACE_RCU + static unsigned long rcuscale_seq_diff(unsigned long new, unsigned long old) { if (!cur_ops->gp_diff) @@ -797,7 +817,7 @@ rcu_scale_init(void) long i; int firsterr = 0; static struct rcu_scale_ops *scale_ops[] = { - &rcu_ops, &srcu_ops, &srcud_ops, &tasks_ops, &tasks_tracing_ops + &rcu_ops, &srcu_ops, &srcud_ops, TASKS_OPS TASKS_TRACING_OPS }; if (!torture_init_begin(scale_type, verbose)) diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index 55d049c39608..7120165a9342 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -738,6 +738,50 @@ static struct rcu_torture_ops busted_srcud_ops = { }; /* + * Definitions for trivial CONFIG_PREEMPT=n-only torture testing. + * This implementation does not necessarily work well with CPU hotplug. + */ + +static void synchronize_rcu_trivial(void) +{ + int cpu; + + for_each_online_cpu(cpu) { + rcutorture_sched_setaffinity(current->pid, cpumask_of(cpu)); + WARN_ON_ONCE(raw_smp_processor_id() != cpu); + } +} + +static int rcu_torture_read_lock_trivial(void) __acquires(RCU) +{ + preempt_disable(); + return 0; +} + +static void rcu_torture_read_unlock_trivial(int idx) __releases(RCU) +{ + preempt_enable(); +} + +static struct rcu_torture_ops trivial_ops = { + .ttype = RCU_TRIVIAL_FLAVOR, + .init = rcu_sync_torture_init, + .readlock = rcu_torture_read_lock_trivial, + .read_delay = rcu_read_delay, /* just reuse rcu's version. */ + .readunlock = rcu_torture_read_unlock_trivial, + .readlock_held = torture_readlock_not_held, + .get_gp_seq = rcu_no_completed, + .sync = synchronize_rcu_trivial, + .exp_sync = synchronize_rcu_trivial, + .fqs = NULL, + .stats = NULL, + .irq_capable = 1, + .name = "trivial" +}; + +#ifdef CONFIG_TASKS_RCU + +/* * Definitions for RCU-tasks torture testing. */ @@ -780,47 +824,16 @@ static struct rcu_torture_ops tasks_ops = { .name = "tasks" }; -/* - * Definitions for trivial CONFIG_PREEMPT=n-only torture testing. - * This implementation does not necessarily work well with CPU hotplug. - */ +#define TASKS_OPS &tasks_ops, -static void synchronize_rcu_trivial(void) -{ - int cpu; +#else // #ifdef CONFIG_TASKS_RCU - for_each_online_cpu(cpu) { - rcutorture_sched_setaffinity(current->pid, cpumask_of(cpu)); - WARN_ON_ONCE(raw_smp_processor_id() != cpu); - } -} +#define TASKS_OPS -static int rcu_torture_read_lock_trivial(void) __acquires(RCU) -{ - preempt_disable(); - return 0; -} +#endif // #else #ifdef CONFIG_TASKS_RCU -static void rcu_torture_read_unlock_trivial(int idx) __releases(RCU) -{ - preempt_enable(); -} -static struct rcu_torture_ops trivial_ops = { - .ttype = RCU_TRIVIAL_FLAVOR, - .init = rcu_sync_torture_init, - .readlock = rcu_torture_read_lock_trivial, - .read_delay = rcu_read_delay, /* just reuse rcu's version. */ - .readunlock = rcu_torture_read_unlock_trivial, - .readlock_held = torture_readlock_not_held, - .get_gp_seq = rcu_no_completed, - .sync = synchronize_rcu_trivial, - .exp_sync = synchronize_rcu_trivial, - .fqs = NULL, - .stats = NULL, - .irq_capable = 1, - .name = "trivial" -}; +#ifdef CONFIG_TASKS_RUDE_RCU /* * Definitions for rude RCU-tasks torture testing. @@ -851,6 +864,17 @@ static struct rcu_torture_ops tasks_rude_ops = { .name = "tasks-rude" }; +#define TASKS_RUDE_OPS &tasks_rude_ops, + +#else // #ifdef CONFIG_TASKS_RUDE_RCU + +#define TASKS_RUDE_OPS + +#endif // #else #ifdef CONFIG_TASKS_RUDE_RCU + + +#ifdef CONFIG_TASKS_TRACE_RCU + /* * Definitions for tracing RCU-tasks torture testing. */ @@ -893,6 +917,15 @@ static struct rcu_torture_ops tasks_tracing_ops = { .name = "tasks-tracing" }; +#define TASKS_TRACING_OPS &tasks_tracing_ops, + +#else // #ifdef CONFIG_TASKS_TRACE_RCU + +#define TASKS_TRACING_OPS + +#endif // #else #ifdef CONFIG_TASKS_TRACE_RCU + + static unsigned long rcutorture_seq_diff(unsigned long new, unsigned long old) { if (!cur_ops->gp_diff) @@ -1178,7 +1211,7 @@ rcu_torture_writer(void *arg) " GP expediting controlled from boot/sysfs for %s.\n", torture_type, cur_ops->name); if (WARN_ONCE(nsynctypes == 0, - "rcu_torture_writer: No update-side primitives.\n")) { + "%s: No update-side primitives.\n", __func__)) { /* * No updates primitives, so don't try updating. * The resulting test won't be testing much, hence the @@ -1186,6 +1219,7 @@ rcu_torture_writer(void *arg) */ rcu_torture_writer_state = RTWS_STOPPING; torture_kthread_stopping("rcu_torture_writer"); + return 0; } do { @@ -1322,6 +1356,17 @@ rcu_torture_fakewriter(void *arg) VERBOSE_TOROUT_STRING("rcu_torture_fakewriter task started"); set_user_nice(current, MAX_NICE); + if (WARN_ONCE(nsynctypes == 0, + "%s: No update-side primitives.\n", __func__)) { + /* + * No updates primitives, so don't try updating. + * The resulting test won't be testing much, hence the + * above WARN_ONCE(). + */ + torture_kthread_stopping("rcu_torture_fakewriter"); + return 0; + } + do { torture_hrtimeout_jiffies(torture_random(&rand) % 10, &rand); if (cur_ops->cb_barrier != NULL && @@ -2916,10 +2961,12 @@ rcu_torture_cleanup(void) pr_info("%s: Invoking %pS().\n", __func__, cur_ops->cb_barrier); cur_ops->cb_barrier(); } + rcu_gp_slow_unregister(NULL); return; } if (!cur_ops) { torture_cleanup_end(); + rcu_gp_slow_unregister(NULL); return; } @@ -3016,6 +3063,7 @@ rcu_torture_cleanup(void) else rcu_torture_print_module_parms(cur_ops, "End of test: SUCCESS"); torture_cleanup_end(); + rcu_gp_slow_unregister(&rcu_fwd_cb_nodelay); } #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD @@ -3096,9 +3144,9 @@ rcu_torture_init(void) int flags = 0; unsigned long gp_seq = 0; static struct rcu_torture_ops *torture_ops[] = { - &rcu_ops, &rcu_busted_ops, &srcu_ops, &srcud_ops, - &busted_srcud_ops, &tasks_ops, &tasks_rude_ops, - &tasks_tracing_ops, &trivial_ops, + &rcu_ops, &rcu_busted_ops, &srcu_ops, &srcud_ops, &busted_srcud_ops, + TASKS_OPS TASKS_RUDE_OPS TASKS_TRACING_OPS + &trivial_ops, }; if (!torture_init_begin(torture_type, verbose)) @@ -3320,6 +3368,7 @@ rcu_torture_init(void) if (object_debug) rcu_test_debug_objects(); torture_init_end(); + rcu_gp_slow_register(&rcu_fwd_cb_nodelay); return 0; unwind: diff --git a/kernel/rcu/refscale.c b/kernel/rcu/refscale.c index 5489ff7f478e..909644abee67 100644 --- a/kernel/rcu/refscale.c +++ b/kernel/rcu/refscale.c @@ -207,6 +207,8 @@ static struct ref_scale_ops srcu_ops = { .name = "srcu" }; +#ifdef CONFIG_TASKS_RCU + // Definitions for RCU Tasks ref scale testing: Empty read markers. // These definitions also work for RCU Rude readers. static void rcu_tasks_ref_scale_read_section(const int nloops) @@ -232,6 +234,16 @@ static struct ref_scale_ops rcu_tasks_ops = { .name = "rcu-tasks" }; +#define RCU_TASKS_OPS &rcu_tasks_ops, + +#else // #ifdef CONFIG_TASKS_RCU + +#define RCU_TASKS_OPS + +#endif // #else // #ifdef CONFIG_TASKS_RCU + +#ifdef CONFIG_TASKS_TRACE_RCU + // Definitions for RCU Tasks Trace ref scale testing. static void rcu_trace_ref_scale_read_section(const int nloops) { @@ -261,6 +273,14 @@ static struct ref_scale_ops rcu_trace_ops = { .name = "rcu-trace" }; +#define RCU_TRACE_OPS &rcu_trace_ops, + +#else // #ifdef CONFIG_TASKS_TRACE_RCU + +#define RCU_TRACE_OPS + +#endif // #else // #ifdef CONFIG_TASKS_TRACE_RCU + // Definitions for reference count static atomic_t refcnt; @@ -790,7 +810,7 @@ ref_scale_init(void) long i; int firsterr = 0; static struct ref_scale_ops *scale_ops[] = { - &rcu_ops, &srcu_ops, &rcu_trace_ops, &rcu_tasks_ops, &refcnt_ops, &rwlock_ops, + &rcu_ops, &srcu_ops, RCU_TRACE_OPS RCU_TASKS_OPS &refcnt_ops, &rwlock_ops, &rwsem_ops, &lock_ops, &lock_irq_ops, &acqrel_ops, &clock_ops, }; diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c index 6833d8887181..50ba70f019de 100644 --- a/kernel/rcu/srcutree.c +++ b/kernel/rcu/srcutree.c @@ -24,6 +24,7 @@ #include <linux/smp.h> #include <linux/delay.h> #include <linux/module.h> +#include <linux/slab.h> #include <linux/srcu.h> #include "rcu.h" @@ -38,6 +39,35 @@ module_param(exp_holdoff, ulong, 0444); static ulong counter_wrap_check = (ULONG_MAX >> 2); module_param(counter_wrap_check, ulong, 0444); +/* + * Control conversion to SRCU_SIZE_BIG: + * 0: Don't convert at all. + * 1: Convert at init_srcu_struct() time. + * 2: Convert when rcutorture invokes srcu_torture_stats_print(). + * 3: Decide at boot time based on system shape (default). + * 0x1x: Convert when excessive contention encountered. + */ +#define SRCU_SIZING_NONE 0 +#define SRCU_SIZING_INIT 1 +#define SRCU_SIZING_TORTURE 2 +#define SRCU_SIZING_AUTO 3 +#define SRCU_SIZING_CONTEND 0x10 +#define SRCU_SIZING_IS(x) ((convert_to_big & ~SRCU_SIZING_CONTEND) == x) +#define SRCU_SIZING_IS_NONE() (SRCU_SIZING_IS(SRCU_SIZING_NONE)) +#define SRCU_SIZING_IS_INIT() (SRCU_SIZING_IS(SRCU_SIZING_INIT)) +#define SRCU_SIZING_IS_TORTURE() (SRCU_SIZING_IS(SRCU_SIZING_TORTURE)) +#define SRCU_SIZING_IS_CONTEND() (convert_to_big & SRCU_SIZING_CONTEND) +static int convert_to_big = SRCU_SIZING_AUTO; +module_param(convert_to_big, int, 0444); + +/* Number of CPUs to trigger init_srcu_struct()-time transition to big. */ +static int big_cpu_lim __read_mostly = 128; +module_param(big_cpu_lim, int, 0444); + +/* Contention events per jiffy to initiate transition to big. */ +static int small_contention_lim __read_mostly = 100; +module_param(small_contention_lim, int, 0444); + /* Early-boot callback-management, so early that no lock is required! */ static LIST_HEAD(srcu_boot_list); static bool __read_mostly srcu_init_done; @@ -48,39 +78,90 @@ static void process_srcu(struct work_struct *work); static void srcu_delay_timer(struct timer_list *t); /* Wrappers for lock acquisition and release, see raw_spin_lock_rcu_node(). */ -#define spin_lock_rcu_node(p) \ -do { \ - spin_lock(&ACCESS_PRIVATE(p, lock)); \ - smp_mb__after_unlock_lock(); \ +#define spin_lock_rcu_node(p) \ +do { \ + spin_lock(&ACCESS_PRIVATE(p, lock)); \ + smp_mb__after_unlock_lock(); \ } while (0) #define spin_unlock_rcu_node(p) spin_unlock(&ACCESS_PRIVATE(p, lock)) -#define spin_lock_irq_rcu_node(p) \ -do { \ - spin_lock_irq(&ACCESS_PRIVATE(p, lock)); \ - smp_mb__after_unlock_lock(); \ +#define spin_lock_irq_rcu_node(p) \ +do { \ + spin_lock_irq(&ACCESS_PRIVATE(p, lock)); \ + smp_mb__after_unlock_lock(); \ } while (0) -#define spin_unlock_irq_rcu_node(p) \ +#define spin_unlock_irq_rcu_node(p) \ spin_unlock_irq(&ACCESS_PRIVATE(p, lock)) -#define spin_lock_irqsave_rcu_node(p, flags) \ -do { \ - spin_lock_irqsave(&ACCESS_PRIVATE(p, lock), flags); \ - smp_mb__after_unlock_lock(); \ +#define spin_lock_irqsave_rcu_node(p, flags) \ +do { \ + spin_lock_irqsave(&ACCESS_PRIVATE(p, lock), flags); \ + smp_mb__after_unlock_lock(); \ } while (0) -#define spin_unlock_irqrestore_rcu_node(p, flags) \ - spin_unlock_irqrestore(&ACCESS_PRIVATE(p, lock), flags) \ +#define spin_trylock_irqsave_rcu_node(p, flags) \ +({ \ + bool ___locked = spin_trylock_irqsave(&ACCESS_PRIVATE(p, lock), flags); \ + \ + if (___locked) \ + smp_mb__after_unlock_lock(); \ + ___locked; \ +}) + +#define spin_unlock_irqrestore_rcu_node(p, flags) \ + spin_unlock_irqrestore(&ACCESS_PRIVATE(p, lock), flags) \ /* - * Initialize SRCU combining tree. Note that statically allocated + * Initialize SRCU per-CPU data. Note that statically allocated * srcu_struct structures might already have srcu_read_lock() and * srcu_read_unlock() running against them. So if the is_static parameter * is set, don't initialize ->srcu_lock_count[] and ->srcu_unlock_count[]. */ -static void init_srcu_struct_nodes(struct srcu_struct *ssp) +static void init_srcu_struct_data(struct srcu_struct *ssp) +{ + int cpu; + struct srcu_data *sdp; + + /* + * Initialize the per-CPU srcu_data array, which feeds into the + * leaves of the srcu_node tree. + */ + WARN_ON_ONCE(ARRAY_SIZE(sdp->srcu_lock_count) != + ARRAY_SIZE(sdp->srcu_unlock_count)); + for_each_possible_cpu(cpu) { + sdp = per_cpu_ptr(ssp->sda, cpu); + spin_lock_init(&ACCESS_PRIVATE(sdp, lock)); + rcu_segcblist_init(&sdp->srcu_cblist); + sdp->srcu_cblist_invoking = false; + sdp->srcu_gp_seq_needed = ssp->srcu_gp_seq; + sdp->srcu_gp_seq_needed_exp = ssp->srcu_gp_seq; + sdp->mynode = NULL; + sdp->cpu = cpu; + INIT_WORK(&sdp->work, srcu_invoke_callbacks); + timer_setup(&sdp->delay_work, srcu_delay_timer, 0); + sdp->ssp = ssp; + } +} + +/* Invalid seq state, used during snp node initialization */ +#define SRCU_SNP_INIT_SEQ 0x2 + +/* + * Check whether sequence number corresponding to snp node, + * is invalid. + */ +static inline bool srcu_invl_snp_seq(unsigned long s) +{ + return rcu_seq_state(s) == SRCU_SNP_INIT_SEQ; +} + +/* + * Allocated and initialize SRCU combining tree. Returns @true if + * allocation succeeded and @false otherwise. + */ +static bool init_srcu_struct_nodes(struct srcu_struct *ssp, gfp_t gfp_flags) { int cpu; int i; @@ -92,6 +173,9 @@ static void init_srcu_struct_nodes(struct srcu_struct *ssp) /* Initialize geometry if it has not already been initialized. */ rcu_init_geometry(); + ssp->node = kcalloc(rcu_num_nodes, sizeof(*ssp->node), gfp_flags); + if (!ssp->node) + return false; /* Work out the overall tree geometry. */ ssp->level[0] = &ssp->node[0]; @@ -105,10 +189,10 @@ static void init_srcu_struct_nodes(struct srcu_struct *ssp) WARN_ON_ONCE(ARRAY_SIZE(snp->srcu_have_cbs) != ARRAY_SIZE(snp->srcu_data_have_cbs)); for (i = 0; i < ARRAY_SIZE(snp->srcu_have_cbs); i++) { - snp->srcu_have_cbs[i] = 0; + snp->srcu_have_cbs[i] = SRCU_SNP_INIT_SEQ; snp->srcu_data_have_cbs[i] = 0; } - snp->srcu_gp_seq_needed_exp = 0; + snp->srcu_gp_seq_needed_exp = SRCU_SNP_INIT_SEQ; snp->grplo = -1; snp->grphi = -1; if (snp == &ssp->node[0]) { @@ -129,39 +213,31 @@ static void init_srcu_struct_nodes(struct srcu_struct *ssp) * Initialize the per-CPU srcu_data array, which feeds into the * leaves of the srcu_node tree. */ - WARN_ON_ONCE(ARRAY_SIZE(sdp->srcu_lock_count) != - ARRAY_SIZE(sdp->srcu_unlock_count)); level = rcu_num_lvls - 1; snp_first = ssp->level[level]; for_each_possible_cpu(cpu) { sdp = per_cpu_ptr(ssp->sda, cpu); - spin_lock_init(&ACCESS_PRIVATE(sdp, lock)); - rcu_segcblist_init(&sdp->srcu_cblist); - sdp->srcu_cblist_invoking = false; - sdp->srcu_gp_seq_needed = ssp->srcu_gp_seq; - sdp->srcu_gp_seq_needed_exp = ssp->srcu_gp_seq; sdp->mynode = &snp_first[cpu / levelspread[level]]; for (snp = sdp->mynode; snp != NULL; snp = snp->srcu_parent) { if (snp->grplo < 0) snp->grplo = cpu; snp->grphi = cpu; } - sdp->cpu = cpu; - INIT_WORK(&sdp->work, srcu_invoke_callbacks); - timer_setup(&sdp->delay_work, srcu_delay_timer, 0); - sdp->ssp = ssp; sdp->grpmask = 1 << (cpu - sdp->mynode->grplo); } + smp_store_release(&ssp->srcu_size_state, SRCU_SIZE_WAIT_BARRIER); + return true; } /* * Initialize non-compile-time initialized fields, including the - * associated srcu_node and srcu_data structures. The is_static - * parameter is passed through to init_srcu_struct_nodes(), and - * also tells us that ->sda has already been wired up to srcu_data. + * associated srcu_node and srcu_data structures. The is_static parameter + * tells us that ->sda has already been wired up to srcu_data. */ static int init_srcu_struct_fields(struct srcu_struct *ssp, bool is_static) { + ssp->srcu_size_state = SRCU_SIZE_SMALL; + ssp->node = NULL; mutex_init(&ssp->srcu_cb_mutex); mutex_init(&ssp->srcu_gp_mutex); ssp->srcu_idx = 0; @@ -170,13 +246,25 @@ static int init_srcu_struct_fields(struct srcu_struct *ssp, bool is_static) mutex_init(&ssp->srcu_barrier_mutex); atomic_set(&ssp->srcu_barrier_cpu_cnt, 0); INIT_DELAYED_WORK(&ssp->work, process_srcu); + ssp->sda_is_static = is_static; if (!is_static) ssp->sda = alloc_percpu(struct srcu_data); if (!ssp->sda) return -ENOMEM; - init_srcu_struct_nodes(ssp); + init_srcu_struct_data(ssp); ssp->srcu_gp_seq_needed_exp = 0; ssp->srcu_last_gp_end = ktime_get_mono_fast_ns(); + if (READ_ONCE(ssp->srcu_size_state) == SRCU_SIZE_SMALL && SRCU_SIZING_IS_INIT()) { + if (!init_srcu_struct_nodes(ssp, GFP_ATOMIC)) { + if (!ssp->sda_is_static) { + free_percpu(ssp->sda); + ssp->sda = NULL; + return -ENOMEM; + } + } else { + WRITE_ONCE(ssp->srcu_size_state, SRCU_SIZE_BIG); + } + } smp_store_release(&ssp->srcu_gp_seq_needed, 0); /* Init done. */ return 0; } @@ -214,6 +302,86 @@ EXPORT_SYMBOL_GPL(init_srcu_struct); #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ /* + * Initiate a transition to SRCU_SIZE_BIG with lock held. + */ +static void __srcu_transition_to_big(struct srcu_struct *ssp) +{ + lockdep_assert_held(&ACCESS_PRIVATE(ssp, lock)); + smp_store_release(&ssp->srcu_size_state, SRCU_SIZE_ALLOC); +} + +/* + * Initiate an idempotent transition to SRCU_SIZE_BIG. + */ +static void srcu_transition_to_big(struct srcu_struct *ssp) +{ + unsigned long flags; + + /* Double-checked locking on ->srcu_size-state. */ + if (smp_load_acquire(&ssp->srcu_size_state) != SRCU_SIZE_SMALL) + return; + spin_lock_irqsave_rcu_node(ssp, flags); + if (smp_load_acquire(&ssp->srcu_size_state) != SRCU_SIZE_SMALL) { + spin_unlock_irqrestore_rcu_node(ssp, flags); + return; + } + __srcu_transition_to_big(ssp); + spin_unlock_irqrestore_rcu_node(ssp, flags); +} + +/* + * Check to see if the just-encountered contention event justifies + * a transition to SRCU_SIZE_BIG. + */ +static void spin_lock_irqsave_check_contention(struct srcu_struct *ssp) +{ + unsigned long j; + + if (!SRCU_SIZING_IS_CONTEND() || ssp->srcu_size_state) + return; + j = jiffies; + if (ssp->srcu_size_jiffies != j) { + ssp->srcu_size_jiffies = j; + ssp->srcu_n_lock_retries = 0; + } + if (++ssp->srcu_n_lock_retries <= small_contention_lim) + return; + __srcu_transition_to_big(ssp); +} + +/* + * Acquire the specified srcu_data structure's ->lock, but check for + * excessive contention, which results in initiation of a transition + * to SRCU_SIZE_BIG. But only if the srcutree.convert_to_big module + * parameter permits this. + */ +static void spin_lock_irqsave_sdp_contention(struct srcu_data *sdp, unsigned long *flags) +{ + struct srcu_struct *ssp = sdp->ssp; + + if (spin_trylock_irqsave_rcu_node(sdp, *flags)) + return; + spin_lock_irqsave_rcu_node(ssp, *flags); + spin_lock_irqsave_check_contention(ssp); + spin_unlock_irqrestore_rcu_node(ssp, *flags); + spin_lock_irqsave_rcu_node(sdp, *flags); +} + +/* + * Acquire the specified srcu_struct structure's ->lock, but check for + * excessive contention, which results in initiation of a transition + * to SRCU_SIZE_BIG. But only if the srcutree.convert_to_big module + * parameter permits this. + */ +static void spin_lock_irqsave_ssp_contention(struct srcu_struct *ssp, unsigned long *flags) +{ + if (spin_trylock_irqsave_rcu_node(ssp, *flags)) + return; + spin_lock_irqsave_rcu_node(ssp, *flags); + spin_lock_irqsave_check_contention(ssp); +} + +/* * First-use initialization of statically allocated srcu_struct * structure. Wiring up the combining tree is more than can be * done with compile-time initialization, so this check is added @@ -343,7 +511,10 @@ static bool srcu_readers_active(struct srcu_struct *ssp) return sum; } -#define SRCU_INTERVAL 1 +#define SRCU_INTERVAL 1 // Base delay if no expedited GPs pending. +#define SRCU_MAX_INTERVAL 10 // Maximum incremental delay from slow readers. +#define SRCU_MAX_NODELAY_PHASE 1 // Maximum per-GP-phase consecutive no-delay instances. +#define SRCU_MAX_NODELAY 100 // Maximum consecutive no-delay instances. /* * Return grace-period delay, zero if there are expedited grace @@ -351,10 +522,18 @@ static bool srcu_readers_active(struct srcu_struct *ssp) */ static unsigned long srcu_get_delay(struct srcu_struct *ssp) { - if (ULONG_CMP_LT(READ_ONCE(ssp->srcu_gp_seq), - READ_ONCE(ssp->srcu_gp_seq_needed_exp))) - return 0; - return SRCU_INTERVAL; + unsigned long jbase = SRCU_INTERVAL; + + if (ULONG_CMP_LT(READ_ONCE(ssp->srcu_gp_seq), READ_ONCE(ssp->srcu_gp_seq_needed_exp))) + jbase = 0; + if (rcu_seq_state(READ_ONCE(ssp->srcu_gp_seq))) + jbase += jiffies - READ_ONCE(ssp->srcu_gp_start); + if (!jbase) { + WRITE_ONCE(ssp->srcu_n_exp_nodelay, READ_ONCE(ssp->srcu_n_exp_nodelay) + 1); + if (READ_ONCE(ssp->srcu_n_exp_nodelay) > SRCU_MAX_NODELAY_PHASE) + jbase = 1; + } + return jbase > SRCU_MAX_INTERVAL ? SRCU_MAX_INTERVAL : jbase; } /** @@ -382,13 +561,20 @@ void cleanup_srcu_struct(struct srcu_struct *ssp) return; /* Forgot srcu_barrier(), so just leak it! */ } if (WARN_ON(rcu_seq_state(READ_ONCE(ssp->srcu_gp_seq)) != SRCU_STATE_IDLE) || + WARN_ON(rcu_seq_current(&ssp->srcu_gp_seq) != ssp->srcu_gp_seq_needed) || WARN_ON(srcu_readers_active(ssp))) { - pr_info("%s: Active srcu_struct %p state: %d\n", - __func__, ssp, rcu_seq_state(READ_ONCE(ssp->srcu_gp_seq))); + pr_info("%s: Active srcu_struct %p read state: %d gp state: %lu/%lu\n", + __func__, ssp, rcu_seq_state(READ_ONCE(ssp->srcu_gp_seq)), + rcu_seq_current(&ssp->srcu_gp_seq), ssp->srcu_gp_seq_needed); return; /* Caller forgot to stop doing call_srcu()? */ } - free_percpu(ssp->sda); - ssp->sda = NULL; + if (!ssp->sda_is_static) { + free_percpu(ssp->sda); + ssp->sda = NULL; + } + kfree(ssp->node); + ssp->node = NULL; + ssp->srcu_size_state = SRCU_SIZE_SMALL; } EXPORT_SYMBOL_GPL(cleanup_srcu_struct); @@ -434,9 +620,13 @@ EXPORT_SYMBOL_GPL(__srcu_read_unlock); */ static void srcu_gp_start(struct srcu_struct *ssp) { - struct srcu_data *sdp = this_cpu_ptr(ssp->sda); + struct srcu_data *sdp; int state; + if (smp_load_acquire(&ssp->srcu_size_state) < SRCU_SIZE_WAIT_BARRIER) + sdp = per_cpu_ptr(ssp->sda, 0); + else + sdp = this_cpu_ptr(ssp->sda); lockdep_assert_held(&ACCESS_PRIVATE(ssp, lock)); WARN_ON_ONCE(ULONG_CMP_GE(ssp->srcu_gp_seq, ssp->srcu_gp_seq_needed)); spin_lock_rcu_node(sdp); /* Interrupts already disabled. */ @@ -445,6 +635,8 @@ static void srcu_gp_start(struct srcu_struct *ssp) (void)rcu_segcblist_accelerate(&sdp->srcu_cblist, rcu_seq_snap(&ssp->srcu_gp_seq)); spin_unlock_rcu_node(sdp); /* Interrupts remain disabled. */ + WRITE_ONCE(ssp->srcu_gp_start, jiffies); + WRITE_ONCE(ssp->srcu_n_exp_nodelay, 0); smp_mb(); /* Order prior store to ->srcu_gp_seq_needed vs. GP start. */ rcu_seq_start(&ssp->srcu_gp_seq); state = rcu_seq_state(ssp->srcu_gp_seq); @@ -517,7 +709,9 @@ static void srcu_gp_end(struct srcu_struct *ssp) int idx; unsigned long mask; struct srcu_data *sdp; + unsigned long sgsne; struct srcu_node *snp; + int ss_state; /* Prevent more than one additional grace period. */ mutex_lock(&ssp->srcu_cb_mutex); @@ -526,7 +720,7 @@ static void srcu_gp_end(struct srcu_struct *ssp) spin_lock_irq_rcu_node(ssp); idx = rcu_seq_state(ssp->srcu_gp_seq); WARN_ON_ONCE(idx != SRCU_STATE_SCAN2); - cbdelay = srcu_get_delay(ssp); + cbdelay = !!srcu_get_delay(ssp); WRITE_ONCE(ssp->srcu_last_gp_end, ktime_get_mono_fast_ns()); rcu_seq_end(&ssp->srcu_gp_seq); gpseq = rcu_seq_current(&ssp->srcu_gp_seq); @@ -537,38 +731,45 @@ static void srcu_gp_end(struct srcu_struct *ssp) /* A new grace period can start at this point. But only one. */ /* Initiate callback invocation as needed. */ - idx = rcu_seq_ctr(gpseq) % ARRAY_SIZE(snp->srcu_have_cbs); - srcu_for_each_node_breadth_first(ssp, snp) { - spin_lock_irq_rcu_node(snp); - cbs = false; - last_lvl = snp >= ssp->level[rcu_num_lvls - 1]; - if (last_lvl) - cbs = snp->srcu_have_cbs[idx] == gpseq; - snp->srcu_have_cbs[idx] = gpseq; - rcu_seq_set_state(&snp->srcu_have_cbs[idx], 1); - if (ULONG_CMP_LT(snp->srcu_gp_seq_needed_exp, gpseq)) - WRITE_ONCE(snp->srcu_gp_seq_needed_exp, gpseq); - mask = snp->srcu_data_have_cbs[idx]; - snp->srcu_data_have_cbs[idx] = 0; - spin_unlock_irq_rcu_node(snp); - if (cbs) - srcu_schedule_cbs_snp(ssp, snp, mask, cbdelay); - - /* Occasionally prevent srcu_data counter wrap. */ - if (!(gpseq & counter_wrap_check) && last_lvl) - for (cpu = snp->grplo; cpu <= snp->grphi; cpu++) { - sdp = per_cpu_ptr(ssp->sda, cpu); - spin_lock_irqsave_rcu_node(sdp, flags); - if (ULONG_CMP_GE(gpseq, - sdp->srcu_gp_seq_needed + 100)) - sdp->srcu_gp_seq_needed = gpseq; - if (ULONG_CMP_GE(gpseq, - sdp->srcu_gp_seq_needed_exp + 100)) - sdp->srcu_gp_seq_needed_exp = gpseq; - spin_unlock_irqrestore_rcu_node(sdp, flags); - } + ss_state = smp_load_acquire(&ssp->srcu_size_state); + if (ss_state < SRCU_SIZE_WAIT_BARRIER) { + srcu_schedule_cbs_sdp(per_cpu_ptr(ssp->sda, 0), cbdelay); + } else { + idx = rcu_seq_ctr(gpseq) % ARRAY_SIZE(snp->srcu_have_cbs); + srcu_for_each_node_breadth_first(ssp, snp) { + spin_lock_irq_rcu_node(snp); + cbs = false; + last_lvl = snp >= ssp->level[rcu_num_lvls - 1]; + if (last_lvl) + cbs = ss_state < SRCU_SIZE_BIG || snp->srcu_have_cbs[idx] == gpseq; + snp->srcu_have_cbs[idx] = gpseq; + rcu_seq_set_state(&snp->srcu_have_cbs[idx], 1); + sgsne = snp->srcu_gp_seq_needed_exp; + if (srcu_invl_snp_seq(sgsne) || ULONG_CMP_LT(sgsne, gpseq)) + WRITE_ONCE(snp->srcu_gp_seq_needed_exp, gpseq); + if (ss_state < SRCU_SIZE_BIG) + mask = ~0; + else + mask = snp->srcu_data_have_cbs[idx]; + snp->srcu_data_have_cbs[idx] = 0; + spin_unlock_irq_rcu_node(snp); + if (cbs) + srcu_schedule_cbs_snp(ssp, snp, mask, cbdelay); + } } + /* Occasionally prevent srcu_data counter wrap. */ + if (!(gpseq & counter_wrap_check)) + for_each_possible_cpu(cpu) { + sdp = per_cpu_ptr(ssp->sda, cpu); + spin_lock_irqsave_rcu_node(sdp, flags); + if (ULONG_CMP_GE(gpseq, sdp->srcu_gp_seq_needed + 100)) + sdp->srcu_gp_seq_needed = gpseq; + if (ULONG_CMP_GE(gpseq, sdp->srcu_gp_seq_needed_exp + 100)) + sdp->srcu_gp_seq_needed_exp = gpseq; + spin_unlock_irqrestore_rcu_node(sdp, flags); + } + /* Callback initiation done, allow grace periods after next. */ mutex_unlock(&ssp->srcu_cb_mutex); @@ -583,6 +784,14 @@ static void srcu_gp_end(struct srcu_struct *ssp) } else { spin_unlock_irq_rcu_node(ssp); } + + /* Transition to big if needed. */ + if (ss_state != SRCU_SIZE_SMALL && ss_state != SRCU_SIZE_BIG) { + if (ss_state == SRCU_SIZE_ALLOC) + init_srcu_struct_nodes(ssp, GFP_KERNEL); + else + smp_store_release(&ssp->srcu_size_state, ss_state + 1); + } } /* @@ -596,20 +805,24 @@ static void srcu_funnel_exp_start(struct srcu_struct *ssp, struct srcu_node *snp unsigned long s) { unsigned long flags; + unsigned long sgsne; - for (; snp != NULL; snp = snp->srcu_parent) { - if (rcu_seq_done(&ssp->srcu_gp_seq, s) || - ULONG_CMP_GE(READ_ONCE(snp->srcu_gp_seq_needed_exp), s)) - return; - spin_lock_irqsave_rcu_node(snp, flags); - if (ULONG_CMP_GE(snp->srcu_gp_seq_needed_exp, s)) { + if (snp) + for (; snp != NULL; snp = snp->srcu_parent) { + sgsne = READ_ONCE(snp->srcu_gp_seq_needed_exp); + if (rcu_seq_done(&ssp->srcu_gp_seq, s) || + (!srcu_invl_snp_seq(sgsne) && ULONG_CMP_GE(sgsne, s))) + return; + spin_lock_irqsave_rcu_node(snp, flags); + sgsne = snp->srcu_gp_seq_needed_exp; + if (!srcu_invl_snp_seq(sgsne) && ULONG_CMP_GE(sgsne, s)) { + spin_unlock_irqrestore_rcu_node(snp, flags); + return; + } + WRITE_ONCE(snp->srcu_gp_seq_needed_exp, s); spin_unlock_irqrestore_rcu_node(snp, flags); - return; } - WRITE_ONCE(snp->srcu_gp_seq_needed_exp, s); - spin_unlock_irqrestore_rcu_node(snp, flags); - } - spin_lock_irqsave_rcu_node(ssp, flags); + spin_lock_irqsave_ssp_contention(ssp, &flags); if (ULONG_CMP_LT(ssp->srcu_gp_seq_needed_exp, s)) WRITE_ONCE(ssp->srcu_gp_seq_needed_exp, s); spin_unlock_irqrestore_rcu_node(ssp, flags); @@ -630,39 +843,47 @@ static void srcu_funnel_gp_start(struct srcu_struct *ssp, struct srcu_data *sdp, { unsigned long flags; int idx = rcu_seq_ctr(s) % ARRAY_SIZE(sdp->mynode->srcu_have_cbs); - struct srcu_node *snp = sdp->mynode; + unsigned long sgsne; + struct srcu_node *snp; + struct srcu_node *snp_leaf; unsigned long snp_seq; - /* Each pass through the loop does one level of the srcu_node tree. */ - for (; snp != NULL; snp = snp->srcu_parent) { - if (rcu_seq_done(&ssp->srcu_gp_seq, s) && snp != sdp->mynode) - return; /* GP already done and CBs recorded. */ - spin_lock_irqsave_rcu_node(snp, flags); - if (ULONG_CMP_GE(snp->srcu_have_cbs[idx], s)) { + /* Ensure that snp node tree is fully initialized before traversing it */ + if (smp_load_acquire(&ssp->srcu_size_state) < SRCU_SIZE_WAIT_BARRIER) + snp_leaf = NULL; + else + snp_leaf = sdp->mynode; + + if (snp_leaf) + /* Each pass through the loop does one level of the srcu_node tree. */ + for (snp = snp_leaf; snp != NULL; snp = snp->srcu_parent) { + if (rcu_seq_done(&ssp->srcu_gp_seq, s) && snp != snp_leaf) + return; /* GP already done and CBs recorded. */ + spin_lock_irqsave_rcu_node(snp, flags); snp_seq = snp->srcu_have_cbs[idx]; - if (snp == sdp->mynode && snp_seq == s) - snp->srcu_data_have_cbs[idx] |= sdp->grpmask; - spin_unlock_irqrestore_rcu_node(snp, flags); - if (snp == sdp->mynode && snp_seq != s) { - srcu_schedule_cbs_sdp(sdp, do_norm - ? SRCU_INTERVAL - : 0); + if (!srcu_invl_snp_seq(snp_seq) && ULONG_CMP_GE(snp_seq, s)) { + if (snp == snp_leaf && snp_seq == s) + snp->srcu_data_have_cbs[idx] |= sdp->grpmask; + spin_unlock_irqrestore_rcu_node(snp, flags); + if (snp == snp_leaf && snp_seq != s) { + srcu_schedule_cbs_sdp(sdp, do_norm ? SRCU_INTERVAL : 0); + return; + } + if (!do_norm) + srcu_funnel_exp_start(ssp, snp, s); return; } - if (!do_norm) - srcu_funnel_exp_start(ssp, snp, s); - return; + snp->srcu_have_cbs[idx] = s; + if (snp == snp_leaf) + snp->srcu_data_have_cbs[idx] |= sdp->grpmask; + sgsne = snp->srcu_gp_seq_needed_exp; + if (!do_norm && (srcu_invl_snp_seq(sgsne) || ULONG_CMP_LT(sgsne, s))) + WRITE_ONCE(snp->srcu_gp_seq_needed_exp, s); + spin_unlock_irqrestore_rcu_node(snp, flags); } - snp->srcu_have_cbs[idx] = s; - if (snp == sdp->mynode) - snp->srcu_data_have_cbs[idx] |= sdp->grpmask; - if (!do_norm && ULONG_CMP_LT(snp->srcu_gp_seq_needed_exp, s)) - WRITE_ONCE(snp->srcu_gp_seq_needed_exp, s); - spin_unlock_irqrestore_rcu_node(snp, flags); - } /* Top of tree, must ensure the grace period will be started. */ - spin_lock_irqsave_rcu_node(ssp, flags); + spin_lock_irqsave_ssp_contention(ssp, &flags); if (ULONG_CMP_LT(ssp->srcu_gp_seq_needed, s)) { /* * Record need for grace period s. Pair with load @@ -678,9 +899,15 @@ static void srcu_funnel_gp_start(struct srcu_struct *ssp, struct srcu_data *sdp, rcu_seq_state(ssp->srcu_gp_seq) == SRCU_STATE_IDLE) { WARN_ON_ONCE(ULONG_CMP_GE(ssp->srcu_gp_seq, ssp->srcu_gp_seq_needed)); srcu_gp_start(ssp); + + // And how can that list_add() in the "else" clause + // possibly be safe for concurrent execution? Well, + // it isn't. And it does not have to be. After all, it + // can only be executed during early boot when there is only + // the one boot CPU running with interrupts still disabled. if (likely(srcu_init_done)) queue_delayed_work(rcu_gp_wq, &ssp->work, - srcu_get_delay(ssp)); + !!srcu_get_delay(ssp)); else if (list_empty(&ssp->work.work.entry)) list_add(&ssp->work.work.entry, &srcu_boot_list); } @@ -814,11 +1041,17 @@ static unsigned long srcu_gp_start_if_needed(struct srcu_struct *ssp, bool needgp = false; unsigned long s; struct srcu_data *sdp; + struct srcu_node *sdp_mynode; + int ss_state; check_init_srcu_struct(ssp); idx = srcu_read_lock(ssp); - sdp = raw_cpu_ptr(ssp->sda); - spin_lock_irqsave_rcu_node(sdp, flags); + ss_state = smp_load_acquire(&ssp->srcu_size_state); + if (ss_state < SRCU_SIZE_WAIT_CALL) + sdp = per_cpu_ptr(ssp->sda, 0); + else + sdp = raw_cpu_ptr(ssp->sda); + spin_lock_irqsave_sdp_contention(sdp, &flags); if (rhp) rcu_segcblist_enqueue(&sdp->srcu_cblist, rhp); rcu_segcblist_advance(&sdp->srcu_cblist, @@ -834,10 +1067,17 @@ static unsigned long srcu_gp_start_if_needed(struct srcu_struct *ssp, needexp = true; } spin_unlock_irqrestore_rcu_node(sdp, flags); + + /* Ensure that snp node tree is fully initialized before traversing it */ + if (ss_state < SRCU_SIZE_WAIT_BARRIER) + sdp_mynode = NULL; + else + sdp_mynode = sdp->mynode; + if (needgp) srcu_funnel_gp_start(ssp, sdp, s, do_norm); else if (needexp) - srcu_funnel_exp_start(ssp, sdp->mynode, s); + srcu_funnel_exp_start(ssp, sdp_mynode, s); srcu_read_unlock(ssp, idx); return s; } @@ -1097,6 +1337,28 @@ static void srcu_barrier_cb(struct rcu_head *rhp) complete(&ssp->srcu_barrier_completion); } +/* + * Enqueue an srcu_barrier() callback on the specified srcu_data + * structure's ->cblist. but only if that ->cblist already has at least one + * callback enqueued. Note that if a CPU already has callbacks enqueue, + * it must have already registered the need for a future grace period, + * so all we need do is enqueue a callback that will use the same grace + * period as the last callback already in the queue. + */ +static void srcu_barrier_one_cpu(struct srcu_struct *ssp, struct srcu_data *sdp) +{ + spin_lock_irq_rcu_node(sdp); + atomic_inc(&ssp->srcu_barrier_cpu_cnt); + sdp->srcu_barrier_head.func = srcu_barrier_cb; + debug_rcu_head_queue(&sdp->srcu_barrier_head); + if (!rcu_segcblist_entrain(&sdp->srcu_cblist, + &sdp->srcu_barrier_head)) { + debug_rcu_head_unqueue(&sdp->srcu_barrier_head); + atomic_dec(&ssp->srcu_barrier_cpu_cnt); + } + spin_unlock_irq_rcu_node(sdp); +} + /** * srcu_barrier - Wait until all in-flight call_srcu() callbacks complete. * @ssp: srcu_struct on which to wait for in-flight callbacks. @@ -1104,7 +1366,7 @@ static void srcu_barrier_cb(struct rcu_head *rhp) void srcu_barrier(struct srcu_struct *ssp) { int cpu; - struct srcu_data *sdp; + int idx; unsigned long s = rcu_seq_snap(&ssp->srcu_barrier_seq); check_init_srcu_struct(ssp); @@ -1120,27 +1382,13 @@ void srcu_barrier(struct srcu_struct *ssp) /* Initial count prevents reaching zero until all CBs are posted. */ atomic_set(&ssp->srcu_barrier_cpu_cnt, 1); - /* - * Each pass through this loop enqueues a callback, but only - * on CPUs already having callbacks enqueued. Note that if - * a CPU already has callbacks enqueue, it must have already - * registered the need for a future grace period, so all we - * need do is enqueue a callback that will use the same - * grace period as the last callback already in the queue. - */ - for_each_possible_cpu(cpu) { - sdp = per_cpu_ptr(ssp->sda, cpu); - spin_lock_irq_rcu_node(sdp); - atomic_inc(&ssp->srcu_barrier_cpu_cnt); - sdp->srcu_barrier_head.func = srcu_barrier_cb; - debug_rcu_head_queue(&sdp->srcu_barrier_head); - if (!rcu_segcblist_entrain(&sdp->srcu_cblist, - &sdp->srcu_barrier_head)) { - debug_rcu_head_unqueue(&sdp->srcu_barrier_head); - atomic_dec(&ssp->srcu_barrier_cpu_cnt); - } - spin_unlock_irq_rcu_node(sdp); - } + idx = srcu_read_lock(ssp); + if (smp_load_acquire(&ssp->srcu_size_state) < SRCU_SIZE_WAIT_BARRIER) + srcu_barrier_one_cpu(ssp, per_cpu_ptr(ssp->sda, 0)); + else + for_each_possible_cpu(cpu) + srcu_barrier_one_cpu(ssp, per_cpu_ptr(ssp->sda, cpu)); + srcu_read_unlock(ssp, idx); /* Remove the initial count, at which point reaching zero can happen. */ if (atomic_dec_and_test(&ssp->srcu_barrier_cpu_cnt)) @@ -1214,6 +1462,7 @@ static void srcu_advance_state(struct srcu_struct *ssp) srcu_flip(ssp); spin_lock_irq_rcu_node(ssp); rcu_seq_set_state(&ssp->srcu_gp_seq, SRCU_STATE_SCAN2); + ssp->srcu_n_exp_nodelay = 0; spin_unlock_irq_rcu_node(ssp); } @@ -1228,6 +1477,7 @@ static void srcu_advance_state(struct srcu_struct *ssp) mutex_unlock(&ssp->srcu_gp_mutex); return; /* readers present, retry later. */ } + ssp->srcu_n_exp_nodelay = 0; srcu_gp_end(ssp); /* Releases ->srcu_gp_mutex. */ } } @@ -1318,12 +1568,28 @@ static void srcu_reschedule(struct srcu_struct *ssp, unsigned long delay) */ static void process_srcu(struct work_struct *work) { + unsigned long curdelay; + unsigned long j; struct srcu_struct *ssp; ssp = container_of(work, struct srcu_struct, work.work); srcu_advance_state(ssp); - srcu_reschedule(ssp, srcu_get_delay(ssp)); + curdelay = srcu_get_delay(ssp); + if (curdelay) { + WRITE_ONCE(ssp->reschedule_count, 0); + } else { + j = jiffies; + if (READ_ONCE(ssp->reschedule_jiffies) == j) { + WRITE_ONCE(ssp->reschedule_count, READ_ONCE(ssp->reschedule_count) + 1); + if (READ_ONCE(ssp->reschedule_count) > SRCU_MAX_NODELAY) + curdelay = 1; + } else { + WRITE_ONCE(ssp->reschedule_count, 1); + WRITE_ONCE(ssp->reschedule_jiffies, j); + } + } + srcu_reschedule(ssp, curdelay); } void srcutorture_get_gp_data(enum rcutorture_type test_type, @@ -1337,43 +1603,69 @@ void srcutorture_get_gp_data(enum rcutorture_type test_type, } EXPORT_SYMBOL_GPL(srcutorture_get_gp_data); +static const char * const srcu_size_state_name[] = { + "SRCU_SIZE_SMALL", + "SRCU_SIZE_ALLOC", + "SRCU_SIZE_WAIT_BARRIER", + "SRCU_SIZE_WAIT_CALL", + "SRCU_SIZE_WAIT_CBS1", + "SRCU_SIZE_WAIT_CBS2", + "SRCU_SIZE_WAIT_CBS3", + "SRCU_SIZE_WAIT_CBS4", + "SRCU_SIZE_BIG", + "SRCU_SIZE_???", +}; + void srcu_torture_stats_print(struct srcu_struct *ssp, char *tt, char *tf) { int cpu; int idx; unsigned long s0 = 0, s1 = 0; + int ss_state = READ_ONCE(ssp->srcu_size_state); + int ss_state_idx = ss_state; idx = ssp->srcu_idx & 0x1; - pr_alert("%s%s Tree SRCU g%ld per-CPU(idx=%d):", - tt, tf, rcu_seq_current(&ssp->srcu_gp_seq), idx); - for_each_possible_cpu(cpu) { - unsigned long l0, l1; - unsigned long u0, u1; - long c0, c1; - struct srcu_data *sdp; - - sdp = per_cpu_ptr(ssp->sda, cpu); - u0 = data_race(sdp->srcu_unlock_count[!idx]); - u1 = data_race(sdp->srcu_unlock_count[idx]); - - /* - * Make sure that a lock is always counted if the corresponding - * unlock is counted. - */ - smp_rmb(); - - l0 = data_race(sdp->srcu_lock_count[!idx]); - l1 = data_race(sdp->srcu_lock_count[idx]); - - c0 = l0 - u0; - c1 = l1 - u1; - pr_cont(" %d(%ld,%ld %c)", - cpu, c0, c1, - "C."[rcu_segcblist_empty(&sdp->srcu_cblist)]); - s0 += c0; - s1 += c1; + if (ss_state < 0 || ss_state >= ARRAY_SIZE(srcu_size_state_name)) + ss_state_idx = ARRAY_SIZE(srcu_size_state_name) - 1; + pr_alert("%s%s Tree SRCU g%ld state %d (%s)", + tt, tf, rcu_seq_current(&ssp->srcu_gp_seq), ss_state, + srcu_size_state_name[ss_state_idx]); + if (!ssp->sda) { + // Called after cleanup_srcu_struct(), perhaps. + pr_cont(" No per-CPU srcu_data structures (->sda == NULL).\n"); + } else { + pr_cont(" per-CPU(idx=%d):", idx); + for_each_possible_cpu(cpu) { + unsigned long l0, l1; + unsigned long u0, u1; + long c0, c1; + struct srcu_data *sdp; + + sdp = per_cpu_ptr(ssp->sda, cpu); + u0 = data_race(sdp->srcu_unlock_count[!idx]); + u1 = data_race(sdp->srcu_unlock_count[idx]); + + /* + * Make sure that a lock is always counted if the corresponding + * unlock is counted. + */ + smp_rmb(); + + l0 = data_race(sdp->srcu_lock_count[!idx]); + l1 = data_race(sdp->srcu_lock_count[idx]); + + c0 = l0 - u0; + c1 = l1 - u1; + pr_cont(" %d(%ld,%ld %c)", + cpu, c0, c1, + "C."[rcu_segcblist_empty(&sdp->srcu_cblist)]); + s0 += c0; + s1 += c1; + } + pr_cont(" T(%ld,%ld)\n", s0, s1); } - pr_cont(" T(%ld,%ld)\n", s0, s1); + if (SRCU_SIZING_IS_TORTURE()) + srcu_transition_to_big(ssp); } EXPORT_SYMBOL_GPL(srcu_torture_stats_print); @@ -1390,6 +1682,17 @@ void __init srcu_init(void) { struct srcu_struct *ssp; + /* Decide on srcu_struct-size strategy. */ + if (SRCU_SIZING_IS(SRCU_SIZING_AUTO)) { + if (nr_cpu_ids >= big_cpu_lim) { + convert_to_big = SRCU_SIZING_INIT; // Don't bother waiting for contention. + pr_info("%s: Setting srcu_struct sizes to big.\n", __func__); + } else { + convert_to_big = SRCU_SIZING_NONE | SRCU_SIZING_CONTEND; + pr_info("%s: Setting srcu_struct sizes based on contention.\n", __func__); + } + } + /* * Once that is set, call_srcu() can follow the normal path and * queue delayed work. This must follow RCU workqueues creation @@ -1400,6 +1703,8 @@ void __init srcu_init(void) ssp = list_first_entry(&srcu_boot_list, struct srcu_struct, work.work.entry); list_del_init(&ssp->work.work.entry); + if (SRCU_SIZING_IS(SRCU_SIZING_INIT) && ssp->srcu_size_state == SRCU_SIZE_SMALL) + ssp->srcu_size_state = SRCU_SIZE_ALLOC; queue_work(rcu_gp_wq, &ssp->work.work); } } diff --git a/kernel/rcu/sync.c b/kernel/rcu/sync.c index 33d896d85902..5cefc702158f 100644 --- a/kernel/rcu/sync.c +++ b/kernel/rcu/sync.c @@ -111,7 +111,7 @@ static void rcu_sync_func(struct rcu_head *rhp) * a slowpath during the update. After this function returns, all * subsequent calls to rcu_sync_is_idle() will return false, which * tells readers to stay off their fastpaths. A later call to - * rcu_sync_exit() re-enables reader slowpaths. + * rcu_sync_exit() re-enables reader fastpaths. * * When called in isolation, rcu_sync_enter() must wait for a grace * period, however, closely spaced calls to rcu_sync_enter() can diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h index 99cf3a13954c..3925e32159b5 100644 --- a/kernel/rcu/tasks.h +++ b/kernel/rcu/tasks.h @@ -46,7 +46,7 @@ struct rcu_tasks_percpu { /** * struct rcu_tasks - Definition for a Tasks-RCU-like mechanism. - * @cbs_wq: Wait queue allowing new callback to get kthread's attention. + * @cbs_wait: RCU wait allowing a new callback to get kthread's attention. * @cbs_gbl_lock: Lock protecting callback list. * @kthread_ptr: This flavor's grace-period/callback-invocation kthread. * @gp_func: This flavor's grace-period-wait function. @@ -77,7 +77,7 @@ struct rcu_tasks_percpu { * @kname: This flavor's kthread name. */ struct rcu_tasks { - struct wait_queue_head cbs_wq; + struct rcuwait cbs_wait; raw_spinlock_t cbs_gbl_lock; int gp_state; int gp_sleep; @@ -113,11 +113,11 @@ static void call_rcu_tasks_iw_wakeup(struct irq_work *iwp); #define DEFINE_RCU_TASKS(rt_name, gp, call, n) \ static DEFINE_PER_CPU(struct rcu_tasks_percpu, rt_name ## __percpu) = { \ .lock = __RAW_SPIN_LOCK_UNLOCKED(rt_name ## __percpu.cbs_pcpu_lock), \ - .rtp_irq_work = IRQ_WORK_INIT(call_rcu_tasks_iw_wakeup), \ + .rtp_irq_work = IRQ_WORK_INIT_HARD(call_rcu_tasks_iw_wakeup), \ }; \ static struct rcu_tasks rt_name = \ { \ - .cbs_wq = __WAIT_QUEUE_HEAD_INITIALIZER(rt_name.cbs_wq), \ + .cbs_wait = __RCUWAIT_INITIALIZER(rt_name.wait), \ .cbs_gbl_lock = __RAW_SPIN_LOCK_UNLOCKED(rt_name.cbs_gbl_lock), \ .gp_func = gp, \ .call_func = call, \ @@ -143,6 +143,11 @@ module_param(rcu_task_ipi_delay, int, 0644); #define RCU_TASK_STALL_TIMEOUT (HZ * 60 * 10) static int rcu_task_stall_timeout __read_mostly = RCU_TASK_STALL_TIMEOUT; module_param(rcu_task_stall_timeout, int, 0644); +#define RCU_TASK_STALL_INFO (HZ * 10) +static int rcu_task_stall_info __read_mostly = RCU_TASK_STALL_INFO; +module_param(rcu_task_stall_info, int, 0644); +static int rcu_task_stall_info_mult __read_mostly = 3; +module_param(rcu_task_stall_info_mult, int, 0444); static int rcu_task_enqueue_lim __read_mostly = -1; module_param(rcu_task_enqueue_lim, int, 0444); @@ -261,14 +266,16 @@ static void call_rcu_tasks_iw_wakeup(struct irq_work *iwp) struct rcu_tasks_percpu *rtpcp = container_of(iwp, struct rcu_tasks_percpu, rtp_irq_work); rtp = rtpcp->rtpp; - wake_up(&rtp->cbs_wq); + rcuwait_wake_up(&rtp->cbs_wait); } // Enqueue a callback for the specified flavor of Tasks RCU. static void call_rcu_tasks_generic(struct rcu_head *rhp, rcu_callback_t func, struct rcu_tasks *rtp) { + int chosen_cpu; unsigned long flags; + int ideal_cpu; unsigned long j; bool needadjust = false; bool needwake; @@ -278,8 +285,9 @@ static void call_rcu_tasks_generic(struct rcu_head *rhp, rcu_callback_t func, rhp->func = func; local_irq_save(flags); rcu_read_lock(); - rtpcp = per_cpu_ptr(rtp->rtpcpu, - smp_processor_id() >> READ_ONCE(rtp->percpu_enqueue_shift)); + ideal_cpu = smp_processor_id() >> READ_ONCE(rtp->percpu_enqueue_shift); + chosen_cpu = cpumask_next(ideal_cpu - 1, cpu_possible_mask); + rtpcp = per_cpu_ptr(rtp->rtpcpu, chosen_cpu); if (!raw_spin_trylock_rcu_node(rtpcp)) { // irqs already disabled. raw_spin_lock_rcu_node(rtpcp); // irqs already disabled. j = jiffies; @@ -460,7 +468,7 @@ static void rcu_tasks_invoke_cbs(struct rcu_tasks *rtp, struct rcu_tasks_percpu } } - if (rcu_segcblist_empty(&rtpcp->cblist)) + if (rcu_segcblist_empty(&rtpcp->cblist) || !cpu_possible(cpu)) return; raw_spin_lock_irqsave_rcu_node(rtpcp, flags); rcu_segcblist_advance(&rtpcp->cblist, rcu_seq_current(&rtp->tasks_gp_seq)); @@ -509,7 +517,9 @@ static int __noreturn rcu_tasks_kthread(void *arg) set_tasks_gp_state(rtp, RTGS_WAIT_CBS); /* If there were none, wait a bit and start over. */ - wait_event_idle(rtp->cbs_wq, (needgpcb = rcu_tasks_need_gpcb(rtp))); + rcuwait_wait_event(&rtp->cbs_wait, + (needgpcb = rcu_tasks_need_gpcb(rtp)), + TASK_IDLE); if (needgpcb & 0x2) { // Wait for one grace period. @@ -548,8 +558,15 @@ static void __init rcu_spawn_tasks_kthread_generic(struct rcu_tasks *rtp) static void __init rcu_tasks_bootup_oddness(void) { #if defined(CONFIG_TASKS_RCU) || defined(CONFIG_TASKS_TRACE_RCU) + int rtsimc; + if (rcu_task_stall_timeout != RCU_TASK_STALL_TIMEOUT) pr_info("\tTasks-RCU CPU stall warnings timeout set to %d (rcu_task_stall_timeout).\n", rcu_task_stall_timeout); + rtsimc = clamp(rcu_task_stall_info_mult, 1, 10); + if (rtsimc != rcu_task_stall_info_mult) { + pr_info("\tTasks-RCU CPU stall info multiplier clamped to %d (rcu_task_stall_info_mult).\n", rtsimc); + rcu_task_stall_info_mult = rtsimc; + } #endif /* #ifdef CONFIG_TASKS_RCU */ #ifdef CONFIG_TASKS_RCU pr_info("\tTrampoline variant of Tasks RCU enabled.\n"); @@ -568,7 +585,17 @@ static void __init rcu_tasks_bootup_oddness(void) /* Dump out rcutorture-relevant state common to all RCU-tasks flavors. */ static void show_rcu_tasks_generic_gp_kthread(struct rcu_tasks *rtp, char *s) { - struct rcu_tasks_percpu *rtpcp = per_cpu_ptr(rtp->rtpcpu, 0); // for_each... + int cpu; + bool havecbs = false; + + for_each_possible_cpu(cpu) { + struct rcu_tasks_percpu *rtpcp = per_cpu_ptr(rtp->rtpcpu, cpu); + + if (!data_race(rcu_segcblist_empty(&rtpcp->cblist))) { + havecbs = true; + break; + } + } pr_info("%s: %s(%d) since %lu g:%lu i:%lu/%lu %c%c %s\n", rtp->kname, tasks_gp_state_getname(rtp), data_race(rtp->gp_state), @@ -576,7 +603,7 @@ static void show_rcu_tasks_generic_gp_kthread(struct rcu_tasks *rtp, char *s) data_race(rcu_seq_current(&rtp->tasks_gp_seq)), data_race(rtp->n_ipis_fails), data_race(rtp->n_ipis), ".k"[!!data_race(rtp->kthread_ptr)], - ".C"[!data_race(rcu_segcblist_empty(&rtpcp->cblist))], + ".C"[havecbs], s); } #endif // #ifndef CONFIG_TINY_RCU @@ -592,10 +619,15 @@ static void exit_tasks_rcu_finish_trace(struct task_struct *t); /* Wait for one RCU-tasks grace period. */ static void rcu_tasks_wait_gp(struct rcu_tasks *rtp) { - struct task_struct *g, *t; - unsigned long lastreport; - LIST_HEAD(holdouts); + struct task_struct *g; int fract; + LIST_HEAD(holdouts); + unsigned long j; + unsigned long lastinfo; + unsigned long lastreport; + bool reported = false; + int rtsi; + struct task_struct *t; set_tasks_gp_state(rtp, RTGS_PRE_WAIT_GP); rtp->pregp_func(); @@ -621,30 +653,50 @@ static void rcu_tasks_wait_gp(struct rcu_tasks *rtp) * is empty, we are done. */ lastreport = jiffies; + lastinfo = lastreport; + rtsi = READ_ONCE(rcu_task_stall_info); // Start off with initial wait and slowly back off to 1 HZ wait. fract = rtp->init_fract; while (!list_empty(&holdouts)) { + ktime_t exp; bool firstreport; bool needreport; int rtst; - /* Slowly back off waiting for holdouts */ + // Slowly back off waiting for holdouts set_tasks_gp_state(rtp, RTGS_WAIT_SCAN_HOLDOUTS); - schedule_timeout_idle(fract); + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) { + schedule_timeout_idle(fract); + } else { + exp = jiffies_to_nsecs(fract); + __set_current_state(TASK_IDLE); + schedule_hrtimeout_range(&exp, jiffies_to_nsecs(HZ / 2), HRTIMER_MODE_REL_HARD); + } if (fract < HZ) fract++; rtst = READ_ONCE(rcu_task_stall_timeout); needreport = rtst > 0 && time_after(jiffies, lastreport + rtst); - if (needreport) + if (needreport) { lastreport = jiffies; + reported = true; + } firstreport = true; WARN_ON(signal_pending(current)); set_tasks_gp_state(rtp, RTGS_SCAN_HOLDOUTS); rtp->holdouts_func(&holdouts, needreport, &firstreport); + + // Print pre-stall informational messages if needed. + j = jiffies; + if (rtsi > 0 && !reported && time_after(j, lastinfo + rtsi)) { + lastinfo = j; + rtsi = rtsi * rcu_task_stall_info_mult; + pr_info("%s: %s grace period %lu is %lu jiffies old.\n", + __func__, rtp->kname, rtp->tasks_gp_seq, j - rtp->gp_start); + } } set_tasks_gp_state(rtp, RTGS_POST_GP); @@ -950,6 +1002,9 @@ static void rcu_tasks_be_rude(struct work_struct *work) // Wait for one rude RCU-tasks grace period. static void rcu_tasks_rude_wait_gp(struct rcu_tasks *rtp) { + if (num_online_cpus() <= 1) + return; // Fastpath for only one CPU. + rtp->n_ipis += cpumask_weight(cpu_online_mask); schedule_on_each_cpu(rcu_tasks_be_rude); } diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index a4b8189455d5..c25ba442044a 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -1679,6 +1679,8 @@ static bool __note_gp_changes(struct rcu_node *rnp, struct rcu_data *rdp) rdp->gp_seq = rnp->gp_seq; /* Remember new grace-period state. */ if (ULONG_CMP_LT(rdp->gp_seq_needed, rnp->gp_seq_needed) || rdp->gpwrap) WRITE_ONCE(rdp->gp_seq_needed, rnp->gp_seq_needed); + if (IS_ENABLED(CONFIG_PROVE_RCU) && READ_ONCE(rdp->gpwrap)) + WRITE_ONCE(rdp->last_sched_clock, jiffies); WRITE_ONCE(rdp->gpwrap, false); rcu_gpnum_ovf(rnp, rdp); return ret; @@ -1705,11 +1707,37 @@ static void note_gp_changes(struct rcu_data *rdp) rcu_gp_kthread_wake(); } +static atomic_t *rcu_gp_slow_suppress; + +/* Register a counter to suppress debugging grace-period delays. */ +void rcu_gp_slow_register(atomic_t *rgssp) +{ + WARN_ON_ONCE(rcu_gp_slow_suppress); + + WRITE_ONCE(rcu_gp_slow_suppress, rgssp); +} +EXPORT_SYMBOL_GPL(rcu_gp_slow_register); + +/* Unregister a counter, with NULL for not caring which. */ +void rcu_gp_slow_unregister(atomic_t *rgssp) +{ + WARN_ON_ONCE(rgssp && rgssp != rcu_gp_slow_suppress); + + WRITE_ONCE(rcu_gp_slow_suppress, NULL); +} +EXPORT_SYMBOL_GPL(rcu_gp_slow_unregister); + +static bool rcu_gp_slow_is_suppressed(void) +{ + atomic_t *rgssp = READ_ONCE(rcu_gp_slow_suppress); + + return rgssp && atomic_read(rgssp); +} + static void rcu_gp_slow(int delay) { - if (delay > 0 && - !(rcu_seq_ctr(rcu_state.gp_seq) % - (rcu_num_nodes * PER_RCU_NODE_PERIOD * delay))) + if (!rcu_gp_slow_is_suppressed() && delay > 0 && + !(rcu_seq_ctr(rcu_state.gp_seq) % (rcu_num_nodes * PER_RCU_NODE_PERIOD * delay))) schedule_timeout_idle(delay); } @@ -2096,14 +2124,29 @@ static noinline void rcu_gp_cleanup(void) /* Advance CBs to reduce false positives below. */ offloaded = rcu_rdp_is_offloaded(rdp); if ((offloaded || !rcu_accelerate_cbs(rnp, rdp)) && needgp) { + + // We get here if a grace period was needed (“needgp”) + // and the above call to rcu_accelerate_cbs() did not set + // the RCU_GP_FLAG_INIT bit in ->gp_state (which records + // the need for another grace period). The purpose + // of the “offloaded” check is to avoid invoking + // rcu_accelerate_cbs() on an offloaded CPU because we do not + // hold the ->nocb_lock needed to safely access an offloaded + // ->cblist. We do not want to acquire that lock because + // it can be heavily contended during callback floods. + WRITE_ONCE(rcu_state.gp_flags, RCU_GP_FLAG_INIT); WRITE_ONCE(rcu_state.gp_req_activity, jiffies); - trace_rcu_grace_period(rcu_state.name, - rcu_state.gp_seq, - TPS("newreq")); + trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq, TPS("newreq")); } else { - WRITE_ONCE(rcu_state.gp_flags, - rcu_state.gp_flags & RCU_GP_FLAG_INIT); + + // We get here either if there is no need for an + // additional grace period or if rcu_accelerate_cbs() has + // already set the RCU_GP_FLAG_INIT bit in ->gp_flags. + // So all we need to do is to clear all of the other + // ->gp_flags bits. + + WRITE_ONCE(rcu_state.gp_flags, rcu_state.gp_flags & RCU_GP_FLAG_INIT); } raw_spin_unlock_irq_rcu_node(rnp); @@ -2609,6 +2652,13 @@ static void rcu_do_batch(struct rcu_data *rdp) */ void rcu_sched_clock_irq(int user) { + unsigned long j; + + if (IS_ENABLED(CONFIG_PROVE_RCU)) { + j = jiffies; + WARN_ON_ONCE(time_before(j, __this_cpu_read(rcu_data.last_sched_clock))); + __this_cpu_write(rcu_data.last_sched_clock, j); + } trace_rcu_utilization(TPS("Start scheduler-tick")); lockdep_assert_irqs_disabled(); raw_cpu_inc(rcu_data.ticks_this_gp); @@ -2624,6 +2674,8 @@ void rcu_sched_clock_irq(int user) rcu_flavor_sched_clock_irq(user); if (rcu_pending(user)) invoke_rcu_core(); + if (user) + rcu_tasks_classic_qs(current, false); lockdep_assert_irqs_disabled(); trace_rcu_utilization(TPS("End scheduler-tick")); @@ -3717,7 +3769,9 @@ static int rcu_blocking_is_gp(void) { int ret; - if (IS_ENABLED(CONFIG_PREEMPTION)) + // Invoking preempt_model_*() too early gets a splat. + if (rcu_scheduler_active == RCU_SCHEDULER_INACTIVE || + preempt_model_full() || preempt_model_rt()) return rcu_scheduler_active == RCU_SCHEDULER_INACTIVE; might_sleep(); /* Check for RCU read-side critical section. */ preempt_disable(); @@ -4179,6 +4233,7 @@ rcu_boot_init_percpu_data(int cpu) rdp->rcu_ofl_gp_flags = RCU_GP_CLEANED; rdp->rcu_onl_gp_seq = rcu_state.gp_seq; rdp->rcu_onl_gp_flags = RCU_GP_CLEANED; + rdp->last_sched_clock = jiffies; rdp->cpu = cpu; rcu_boot_init_nocb_percpu_data(rdp); } @@ -4471,6 +4526,51 @@ static int rcu_pm_notify(struct notifier_block *self, return NOTIFY_OK; } +#ifdef CONFIG_RCU_EXP_KTHREAD +struct kthread_worker *rcu_exp_gp_kworker; +struct kthread_worker *rcu_exp_par_gp_kworker; + +static void __init rcu_start_exp_gp_kworkers(void) +{ + const char *par_gp_kworker_name = "rcu_exp_par_gp_kthread_worker"; + const char *gp_kworker_name = "rcu_exp_gp_kthread_worker"; + struct sched_param param = { .sched_priority = kthread_prio }; + + rcu_exp_gp_kworker = kthread_create_worker(0, gp_kworker_name); + if (IS_ERR_OR_NULL(rcu_exp_gp_kworker)) { + pr_err("Failed to create %s!\n", gp_kworker_name); + return; + } + + rcu_exp_par_gp_kworker = kthread_create_worker(0, par_gp_kworker_name); + if (IS_ERR_OR_NULL(rcu_exp_par_gp_kworker)) { + pr_err("Failed to create %s!\n", par_gp_kworker_name); + kthread_destroy_worker(rcu_exp_gp_kworker); + return; + } + + sched_setscheduler_nocheck(rcu_exp_gp_kworker->task, SCHED_FIFO, ¶m); + sched_setscheduler_nocheck(rcu_exp_par_gp_kworker->task, SCHED_FIFO, + ¶m); +} + +static inline void rcu_alloc_par_gp_wq(void) +{ +} +#else /* !CONFIG_RCU_EXP_KTHREAD */ +struct workqueue_struct *rcu_par_gp_wq; + +static void __init rcu_start_exp_gp_kworkers(void) +{ +} + +static inline void rcu_alloc_par_gp_wq(void) +{ + rcu_par_gp_wq = alloc_workqueue("rcu_par_gp", WQ_MEM_RECLAIM, 0); + WARN_ON(!rcu_par_gp_wq); +} +#endif /* CONFIG_RCU_EXP_KTHREAD */ + /* * Spawn the kthreads that handle RCU's grace periods. */ @@ -4480,6 +4580,7 @@ static int __init rcu_spawn_gp_kthread(void) struct rcu_node *rnp; struct sched_param sp; struct task_struct *t; + struct rcu_data *rdp = this_cpu_ptr(&rcu_data); rcu_scheduler_fully_active = 1; t = kthread_create(rcu_gp_kthread, NULL, "%s", rcu_state.name); @@ -4497,9 +4598,17 @@ static int __init rcu_spawn_gp_kthread(void) smp_store_release(&rcu_state.gp_kthread, t); /* ^^^ */ raw_spin_unlock_irqrestore_rcu_node(rnp, flags); wake_up_process(t); - rcu_spawn_nocb_kthreads(); - rcu_spawn_boost_kthreads(); + /* This is a pre-SMP initcall, we expect a single CPU */ + WARN_ON(num_online_cpus() > 1); + /* + * Those kthreads couldn't be created on rcu_init() -> rcutree_prepare_cpu() + * due to rcu_scheduler_fully_active. + */ + rcu_spawn_cpu_nocb_kthread(smp_processor_id()); + rcu_spawn_one_boost_kthread(rdp->mynode); rcu_spawn_core_kthreads(); + /* Create kthread worker for expedited GPs */ + rcu_start_exp_gp_kworkers(); return 0; } early_initcall(rcu_spawn_gp_kthread); @@ -4745,7 +4854,6 @@ static void __init rcu_dump_rcu_node_tree(void) } struct workqueue_struct *rcu_gp_wq; -struct workqueue_struct *rcu_par_gp_wq; static void __init kfree_rcu_batch_init(void) { @@ -4782,7 +4890,7 @@ static void __init kfree_rcu_batch_init(void) void __init rcu_init(void) { - int cpu; + int cpu = smp_processor_id(); rcu_early_boot_tests(); @@ -4802,17 +4910,15 @@ void __init rcu_init(void) * or the scheduler are operational. */ pm_notifier(rcu_pm_notify, 0); - for_each_online_cpu(cpu) { - rcutree_prepare_cpu(cpu); - rcu_cpu_starting(cpu); - rcutree_online_cpu(cpu); - } + WARN_ON(num_online_cpus() > 1); // Only one CPU this early in boot. + rcutree_prepare_cpu(cpu); + rcu_cpu_starting(cpu); + rcutree_online_cpu(cpu); /* Create workqueue for Tree SRCU and for expedited GPs. */ rcu_gp_wq = alloc_workqueue("rcu_gp", WQ_MEM_RECLAIM, 0); WARN_ON(!rcu_gp_wq); - rcu_par_gp_wq = alloc_workqueue("rcu_par_gp", WQ_MEM_RECLAIM, 0); - WARN_ON(!rcu_par_gp_wq); + rcu_alloc_par_gp_wq(); /* Fill in default value for rcutree.qovld boot parameter. */ /* -After- the rcu_node ->lock fields are initialized! */ diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index 926673ebe355..2ccf5845957d 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -10,6 +10,7 @@ */ #include <linux/cache.h> +#include <linux/kthread.h> #include <linux/spinlock.h> #include <linux/rtmutex.h> #include <linux/threads.h> @@ -23,7 +24,11 @@ /* Communicate arguments to a workqueue handler. */ struct rcu_exp_work { unsigned long rew_s; +#ifdef CONFIG_RCU_EXP_KTHREAD + struct kthread_work rew_work; +#else struct work_struct rew_work; +#endif /* CONFIG_RCU_EXP_KTHREAD */ }; /* RCU's kthread states for tracing. */ @@ -254,6 +259,7 @@ struct rcu_data { unsigned long rcu_onl_gp_seq; /* ->gp_seq at last online. */ short rcu_onl_gp_flags; /* ->gp_flags at last online. */ unsigned long last_fqs_resched; /* Time of last rcu_resched(). */ + unsigned long last_sched_clock; /* Jiffies of last rcu_sched_clock_irq(). */ int cpu; }; @@ -364,6 +370,7 @@ struct rcu_state { arch_spinlock_t ofl_lock ____cacheline_internodealigned_in_smp; /* Synchronize offline with */ /* GP pre-initialization. */ + int nocb_is_setup; /* nocb is setup from boot */ }; /* Values for rcu_state structure's gp_flags field. */ @@ -421,7 +428,6 @@ static void rcu_preempt_boost_start_gp(struct rcu_node *rnp); static bool rcu_is_callbacks_kthread(void); static void rcu_cpu_kthread_setup(unsigned int cpu); static void rcu_spawn_one_boost_kthread(struct rcu_node *rnp); -static void __init rcu_spawn_boost_kthreads(void); static bool rcu_preempt_has_tasks(struct rcu_node *rnp); static bool rcu_preempt_need_deferred_qs(struct task_struct *t); static void rcu_preempt_deferred_qs(struct task_struct *t); @@ -439,7 +445,6 @@ static int rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp, int level); static bool do_nocb_deferred_wakeup(struct rcu_data *rdp); static void rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp); static void rcu_spawn_cpu_nocb_kthread(int cpu); -static void __init rcu_spawn_nocb_kthreads(void); static void show_rcu_nocb_state(struct rcu_data *rdp); static void rcu_nocb_lock(struct rcu_data *rdp); static void rcu_nocb_unlock(struct rcu_data *rdp); diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h index 60197ea24ceb..0f70f62039a9 100644 --- a/kernel/rcu/tree_exp.h +++ b/kernel/rcu/tree_exp.h @@ -334,15 +334,13 @@ fastpath: * Select the CPUs within the specified rcu_node that the upcoming * expedited grace period needs to wait for. */ -static void sync_rcu_exp_select_node_cpus(struct work_struct *wp) +static void __sync_rcu_exp_select_node_cpus(struct rcu_exp_work *rewp) { int cpu; unsigned long flags; unsigned long mask_ofl_test; unsigned long mask_ofl_ipi; int ret; - struct rcu_exp_work *rewp = - container_of(wp, struct rcu_exp_work, rew_work); struct rcu_node *rnp = container_of(rewp, struct rcu_node, rew); raw_spin_lock_irqsave_rcu_node(rnp, flags); @@ -417,13 +415,119 @@ retry_ipi: rcu_report_exp_cpu_mult(rnp, mask_ofl_test, false); } +static void rcu_exp_sel_wait_wake(unsigned long s); + +#ifdef CONFIG_RCU_EXP_KTHREAD +static void sync_rcu_exp_select_node_cpus(struct kthread_work *wp) +{ + struct rcu_exp_work *rewp = + container_of(wp, struct rcu_exp_work, rew_work); + + __sync_rcu_exp_select_node_cpus(rewp); +} + +static inline bool rcu_gp_par_worker_started(void) +{ + return !!READ_ONCE(rcu_exp_par_gp_kworker); +} + +static inline void sync_rcu_exp_select_cpus_queue_work(struct rcu_node *rnp) +{ + kthread_init_work(&rnp->rew.rew_work, sync_rcu_exp_select_node_cpus); + /* + * Use rcu_exp_par_gp_kworker, because flushing a work item from + * another work item on the same kthread worker can result in + * deadlock. + */ + kthread_queue_work(rcu_exp_par_gp_kworker, &rnp->rew.rew_work); +} + +static inline void sync_rcu_exp_select_cpus_flush_work(struct rcu_node *rnp) +{ + kthread_flush_work(&rnp->rew.rew_work); +} + +/* + * Work-queue handler to drive an expedited grace period forward. + */ +static void wait_rcu_exp_gp(struct kthread_work *wp) +{ + struct rcu_exp_work *rewp; + + rewp = container_of(wp, struct rcu_exp_work, rew_work); + rcu_exp_sel_wait_wake(rewp->rew_s); +} + +static inline void synchronize_rcu_expedited_queue_work(struct rcu_exp_work *rew) +{ + kthread_init_work(&rew->rew_work, wait_rcu_exp_gp); + kthread_queue_work(rcu_exp_gp_kworker, &rew->rew_work); +} + +static inline void synchronize_rcu_expedited_destroy_work(struct rcu_exp_work *rew) +{ +} +#else /* !CONFIG_RCU_EXP_KTHREAD */ +static void sync_rcu_exp_select_node_cpus(struct work_struct *wp) +{ + struct rcu_exp_work *rewp = + container_of(wp, struct rcu_exp_work, rew_work); + + __sync_rcu_exp_select_node_cpus(rewp); +} + +static inline bool rcu_gp_par_worker_started(void) +{ + return !!READ_ONCE(rcu_par_gp_wq); +} + +static inline void sync_rcu_exp_select_cpus_queue_work(struct rcu_node *rnp) +{ + int cpu = find_next_bit(&rnp->ffmask, BITS_PER_LONG, -1); + + INIT_WORK(&rnp->rew.rew_work, sync_rcu_exp_select_node_cpus); + /* If all offline, queue the work on an unbound CPU. */ + if (unlikely(cpu > rnp->grphi - rnp->grplo)) + cpu = WORK_CPU_UNBOUND; + else + cpu += rnp->grplo; + queue_work_on(cpu, rcu_par_gp_wq, &rnp->rew.rew_work); +} + +static inline void sync_rcu_exp_select_cpus_flush_work(struct rcu_node *rnp) +{ + flush_work(&rnp->rew.rew_work); +} + +/* + * Work-queue handler to drive an expedited grace period forward. + */ +static void wait_rcu_exp_gp(struct work_struct *wp) +{ + struct rcu_exp_work *rewp; + + rewp = container_of(wp, struct rcu_exp_work, rew_work); + rcu_exp_sel_wait_wake(rewp->rew_s); +} + +static inline void synchronize_rcu_expedited_queue_work(struct rcu_exp_work *rew) +{ + INIT_WORK_ONSTACK(&rew->rew_work, wait_rcu_exp_gp); + queue_work(rcu_gp_wq, &rew->rew_work); +} + +static inline void synchronize_rcu_expedited_destroy_work(struct rcu_exp_work *rew) +{ + destroy_work_on_stack(&rew->rew_work); +} +#endif /* CONFIG_RCU_EXP_KTHREAD */ + /* * Select the nodes that the upcoming expedited grace period needs * to wait for. */ static void sync_rcu_exp_select_cpus(void) { - int cpu; struct rcu_node *rnp; trace_rcu_exp_grace_period(rcu_state.name, rcu_exp_gp_seq_endval(), TPS("reset")); @@ -435,28 +539,21 @@ static void sync_rcu_exp_select_cpus(void) rnp->exp_need_flush = false; if (!READ_ONCE(rnp->expmask)) continue; /* Avoid early boot non-existent wq. */ - if (!READ_ONCE(rcu_par_gp_wq) || + if (!rcu_gp_par_worker_started() || rcu_scheduler_active != RCU_SCHEDULER_RUNNING || rcu_is_last_leaf_node(rnp)) { - /* No workqueues yet or last leaf, do direct call. */ + /* No worker started yet or last leaf, do direct call. */ sync_rcu_exp_select_node_cpus(&rnp->rew.rew_work); continue; } - INIT_WORK(&rnp->rew.rew_work, sync_rcu_exp_select_node_cpus); - cpu = find_next_bit(&rnp->ffmask, BITS_PER_LONG, -1); - /* If all offline, queue the work on an unbound CPU. */ - if (unlikely(cpu > rnp->grphi - rnp->grplo)) - cpu = WORK_CPU_UNBOUND; - else - cpu += rnp->grplo; - queue_work_on(cpu, rcu_par_gp_wq, &rnp->rew.rew_work); + sync_rcu_exp_select_cpus_queue_work(rnp); rnp->exp_need_flush = true; } - /* Wait for workqueue jobs (if any) to complete. */ + /* Wait for jobs (if any) to complete. */ rcu_for_each_leaf_node(rnp) if (rnp->exp_need_flush) - flush_work(&rnp->rew.rew_work); + sync_rcu_exp_select_cpus_flush_work(rnp); } /* @@ -496,7 +593,7 @@ static void synchronize_rcu_expedited_wait(void) struct rcu_node *rnp_root = rcu_get_root(); trace_rcu_exp_grace_period(rcu_state.name, rcu_exp_gp_seq_endval(), TPS("startwait")); - jiffies_stall = rcu_jiffies_till_stall_check(); + jiffies_stall = rcu_exp_jiffies_till_stall_check(); jiffies_start = jiffies; if (tick_nohz_full_enabled() && rcu_inkernel_boot_has_ended()) { if (synchronize_rcu_expedited_wait_once(1)) @@ -571,7 +668,7 @@ static void synchronize_rcu_expedited_wait(void) dump_cpu_task(cpu); } } - jiffies_stall = 3 * rcu_jiffies_till_stall_check() + 3; + jiffies_stall = 3 * rcu_exp_jiffies_till_stall_check() + 3; } } @@ -622,17 +719,6 @@ static void rcu_exp_sel_wait_wake(unsigned long s) rcu_exp_wait_wake(s); } -/* - * Work-queue handler to drive an expedited grace period forward. - */ -static void wait_rcu_exp_gp(struct work_struct *wp) -{ - struct rcu_exp_work *rewp; - - rewp = container_of(wp, struct rcu_exp_work, rew_work); - rcu_exp_sel_wait_wake(rewp->rew_s); -} - #ifdef CONFIG_PREEMPT_RCU /* @@ -848,20 +934,19 @@ void synchronize_rcu_expedited(void) } else { /* Marshall arguments & schedule the expedited grace period. */ rew.rew_s = s; - INIT_WORK_ONSTACK(&rew.rew_work, wait_rcu_exp_gp); - queue_work(rcu_gp_wq, &rew.rew_work); + synchronize_rcu_expedited_queue_work(&rew); } /* Wait for expedited grace period to complete. */ rnp = rcu_get_root(); wait_event(rnp->exp_wq[rcu_seq_ctr(s) & 0x3], sync_exp_work_done(s)); - smp_mb(); /* Workqueue actions happen before return. */ + smp_mb(); /* Work actions happen before return. */ /* Let the next expedited grace period start. */ mutex_unlock(&rcu_state.exp_mutex); if (likely(!boottime)) - destroy_work_on_stack(&rew.rew_work); + synchronize_rcu_expedited_destroy_work(&rew); } EXPORT_SYMBOL_GPL(synchronize_rcu_expedited); diff --git a/kernel/rcu/tree_nocb.h b/kernel/rcu/tree_nocb.h index 636d0546a4e9..46694e13398a 100644 --- a/kernel/rcu/tree_nocb.h +++ b/kernel/rcu/tree_nocb.h @@ -60,9 +60,6 @@ static inline bool rcu_current_is_nocb_kthread(struct rcu_data *rdp) * Parse the boot-time rcu_nocb_mask CPU list from the kernel parameters. * If the list is invalid, a warning is emitted and all CPUs are offloaded. */ - -static bool rcu_nocb_is_setup; - static int __init rcu_nocb_setup(char *str) { alloc_bootmem_cpumask_var(&rcu_nocb_mask); @@ -72,7 +69,7 @@ static int __init rcu_nocb_setup(char *str) cpumask_setall(rcu_nocb_mask); } } - rcu_nocb_is_setup = true; + rcu_state.nocb_is_setup = true; return 1; } __setup("rcu_nocbs", rcu_nocb_setup); @@ -215,14 +212,6 @@ static void rcu_init_one_nocb(struct rcu_node *rnp) init_swait_queue_head(&rnp->nocb_gp_wq[1]); } -/* Is the specified CPU a no-CBs CPU? */ -bool rcu_is_nocb_cpu(int cpu) -{ - if (cpumask_available(rcu_nocb_mask)) - return cpumask_test_cpu(cpu, rcu_nocb_mask); - return false; -} - static bool __wake_nocb_gp(struct rcu_data *rdp_gp, struct rcu_data *rdp, bool force, unsigned long flags) @@ -1180,10 +1169,10 @@ void __init rcu_init_nohz(void) return; } } - rcu_nocb_is_setup = true; + rcu_state.nocb_is_setup = true; } - if (!rcu_nocb_is_setup) + if (!rcu_state.nocb_is_setup) return; #if defined(CONFIG_NO_HZ_FULL) @@ -1241,7 +1230,7 @@ static void rcu_spawn_cpu_nocb_kthread(int cpu) struct task_struct *t; struct sched_param sp; - if (!rcu_scheduler_fully_active || !rcu_nocb_is_setup) + if (!rcu_scheduler_fully_active || !rcu_state.nocb_is_setup) return; /* If there already is an rcuo kthread, then nothing to do. */ @@ -1277,22 +1266,6 @@ static void rcu_spawn_cpu_nocb_kthread(int cpu) WRITE_ONCE(rdp->nocb_gp_kthread, rdp_gp->nocb_gp_kthread); } -/* - * Once the scheduler is running, spawn rcuo kthreads for all online - * no-CBs CPUs. This assumes that the early_initcall()s happen before - * non-boot CPUs come online -- if this changes, we will need to add - * some mutual exclusion. - */ -static void __init rcu_spawn_nocb_kthreads(void) -{ - int cpu; - - if (rcu_nocb_is_setup) { - for_each_online_cpu(cpu) - rcu_spawn_cpu_nocb_kthread(cpu); - } -} - /* How many CB CPU IDs per GP kthread? Default of -1 for sqrt(nr_cpu_ids). */ static int rcu_nocb_gp_stride = -1; module_param(rcu_nocb_gp_stride, int, 0444); @@ -1549,10 +1522,6 @@ static void rcu_spawn_cpu_nocb_kthread(int cpu) { } -static void __init rcu_spawn_nocb_kthreads(void) -{ -} - static void show_rcu_nocb_state(struct rcu_data *rdp) { } diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 8360d86db1c0..c8ba0fe17267 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -486,6 +486,7 @@ rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags) t->rcu_read_unlock_special.s = 0; if (special.b.need_qs) { if (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD)) { + rdp->cpu_no_qs.b.norm = false; rcu_report_qs_rdp(rdp); udelay(rcu_unlock_delay); } else { @@ -660,7 +661,13 @@ static void rcu_read_unlock_special(struct task_struct *t) expboost && !rdp->defer_qs_iw_pending && cpu_online(rdp->cpu)) { // Get scheduler to re-evaluate and call hooks. // If !IRQ_WORK, FQS scan will eventually IPI. - init_irq_work(&rdp->defer_qs_iw, rcu_preempt_deferred_qs_handler); + if (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD) && + IS_ENABLED(CONFIG_PREEMPT_RT)) + rdp->defer_qs_iw = IRQ_WORK_INIT_HARD( + rcu_preempt_deferred_qs_handler); + else + init_irq_work(&rdp->defer_qs_iw, + rcu_preempt_deferred_qs_handler); rdp->defer_qs_iw_pending = true; irq_work_queue_on(&rdp->defer_qs_iw, rdp->cpu); } @@ -1124,7 +1131,8 @@ static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags) __releases(rnp->lock) { raw_lockdep_assert_held_rcu_node(rnp); - if (!rcu_preempt_blocked_readers_cgp(rnp) && rnp->exp_tasks == NULL) { + if (!rnp->boost_kthread_task || + (!rcu_preempt_blocked_readers_cgp(rnp) && !rnp->exp_tasks)) { raw_spin_unlock_irqrestore_rcu_node(rnp, flags); return; } @@ -1226,18 +1234,6 @@ static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu) free_cpumask_var(cm); } -/* - * Spawn boost kthreads -- called as soon as the scheduler is running. - */ -static void __init rcu_spawn_boost_kthreads(void) -{ - struct rcu_node *rnp; - - rcu_for_each_leaf_node(rnp) - if (rcu_rnp_online_cpus(rnp)) - rcu_spawn_one_boost_kthread(rnp); -} - #else /* #ifdef CONFIG_RCU_BOOST */ static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags) @@ -1263,10 +1259,6 @@ static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu) { } -static void __init rcu_spawn_boost_kthreads(void) -{ -} - #endif /* #else #ifdef CONFIG_RCU_BOOST */ /* diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h index 0c5d8516516a..4995c078cff9 100644 --- a/kernel/rcu/tree_stall.h +++ b/kernel/rcu/tree_stall.h @@ -25,6 +25,34 @@ int sysctl_max_rcu_stall_to_panic __read_mostly; #define RCU_STALL_MIGHT_DIV 8 #define RCU_STALL_MIGHT_MIN (2 * HZ) +int rcu_exp_jiffies_till_stall_check(void) +{ + int cpu_stall_timeout = READ_ONCE(rcu_exp_cpu_stall_timeout); + int exp_stall_delay_delta = 0; + int till_stall_check; + + // Zero says to use rcu_cpu_stall_timeout, but in milliseconds. + if (!cpu_stall_timeout) + cpu_stall_timeout = jiffies_to_msecs(rcu_jiffies_till_stall_check()); + + // Limit check must be consistent with the Kconfig limits for + // CONFIG_RCU_EXP_CPU_STALL_TIMEOUT, so check the allowed range. + // The minimum clamped value is "2UL", because at least one full + // tick has to be guaranteed. + till_stall_check = clamp(msecs_to_jiffies(cpu_stall_timeout), 2UL, 21UL * HZ); + + if (cpu_stall_timeout && jiffies_to_msecs(till_stall_check) != cpu_stall_timeout) + WRITE_ONCE(rcu_exp_cpu_stall_timeout, jiffies_to_msecs(till_stall_check)); + +#ifdef CONFIG_PROVE_RCU + /* Add extra ~25% out of till_stall_check. */ + exp_stall_delay_delta = ((till_stall_check * 25) / 100) + 1; +#endif + + return till_stall_check + exp_stall_delay_delta; +} +EXPORT_SYMBOL_GPL(rcu_exp_jiffies_till_stall_check); + /* Limit-check stall timeouts specified at boottime and runtime. */ int rcu_jiffies_till_stall_check(void) { @@ -565,9 +593,9 @@ static void print_other_cpu_stall(unsigned long gp_seq, unsigned long gps) for_each_possible_cpu(cpu) totqlen += rcu_get_n_cbs_cpu(cpu); - pr_cont("\t(detected by %d, t=%ld jiffies, g=%ld, q=%lu)\n", + pr_cont("\t(detected by %d, t=%ld jiffies, g=%ld, q=%lu ncpus=%d)\n", smp_processor_id(), (long)(jiffies - gps), - (long)rcu_seq_current(&rcu_state.gp_seq), totqlen); + (long)rcu_seq_current(&rcu_state.gp_seq), totqlen, rcu_state.n_online_cpus); if (ndetected) { rcu_dump_cpu_stacks(); @@ -619,6 +647,7 @@ static void print_cpu_stall(unsigned long gps) * See Documentation/RCU/stallwarn.rst for info on how to debug * RCU CPU stall warnings. */ + printk_prefer_direct_enter(); trace_rcu_stall_warning(rcu_state.name, TPS("SelfDetected")); pr_err("INFO: %s self-detected stall on CPU\n", rcu_state.name); raw_spin_lock_irqsave_rcu_node(rdp->mynode, flags); @@ -626,9 +655,9 @@ static void print_cpu_stall(unsigned long gps) raw_spin_unlock_irqrestore_rcu_node(rdp->mynode, flags); for_each_possible_cpu(cpu) totqlen += rcu_get_n_cbs_cpu(cpu); - pr_cont("\t(t=%lu jiffies g=%ld q=%lu)\n", + pr_cont("\t(t=%lu jiffies g=%ld q=%lu ncpus=%d)\n", jiffies - gps, - (long)rcu_seq_current(&rcu_state.gp_seq), totqlen); + (long)rcu_seq_current(&rcu_state.gp_seq), totqlen, rcu_state.n_online_cpus); rcu_check_gp_kthread_expired_fqs_timer(); rcu_check_gp_kthread_starvation(); @@ -656,6 +685,7 @@ static void print_cpu_stall(unsigned long gps) */ set_tsk_need_resched(current); set_preempt_need_resched(); + printk_prefer_direct_exit(); } static void check_cpu_stall(struct rcu_data *rdp) diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c index 180ff9c41fa8..fc7fef575606 100644 --- a/kernel/rcu/update.c +++ b/kernel/rcu/update.c @@ -506,6 +506,8 @@ EXPORT_SYMBOL_GPL(rcu_cpu_stall_suppress); module_param(rcu_cpu_stall_suppress, int, 0644); int rcu_cpu_stall_timeout __read_mostly = CONFIG_RCU_CPU_STALL_TIMEOUT; module_param(rcu_cpu_stall_timeout, int, 0644); +int rcu_exp_cpu_stall_timeout __read_mostly = CONFIG_RCU_EXP_CPU_STALL_TIMEOUT; +module_param(rcu_exp_cpu_stall_timeout, int, 0644); #endif /* #ifdef CONFIG_RCU_STALL_COMMON */ // Suppress boot-time RCU CPU stall warnings and rcutorture writer stall diff --git a/kernel/reboot.c b/kernel/reboot.c index 6bcc5d6a6572..4177645e74d6 100644 --- a/kernel/reboot.c +++ b/kernel/reboot.c @@ -447,9 +447,11 @@ static int __orderly_reboot(void) ret = run_cmd(reboot_cmd); if (ret) { + printk_prefer_direct_enter(); pr_warn("Failed to start orderly reboot: forcing the issue\n"); emergency_sync(); kernel_restart(NULL); + printk_prefer_direct_exit(); } return ret; @@ -462,6 +464,7 @@ static int __orderly_poweroff(bool force) ret = run_cmd(poweroff_cmd); if (ret && force) { + printk_prefer_direct_enter(); pr_warn("Failed to start orderly shutdown: forcing the issue\n"); /* @@ -471,6 +474,7 @@ static int __orderly_poweroff(bool force) */ emergency_sync(); kernel_power_off(); + printk_prefer_direct_exit(); } return ret; @@ -528,6 +532,8 @@ EXPORT_SYMBOL_GPL(orderly_reboot); */ static void hw_failure_emergency_poweroff_func(struct work_struct *work) { + printk_prefer_direct_enter(); + /* * We have reached here after the emergency shutdown waiting period has * expired. This means orderly_poweroff has not been able to shut off @@ -544,6 +550,8 @@ static void hw_failure_emergency_poweroff_func(struct work_struct *work) */ pr_emerg("Hardware protection shutdown failed. Trying emergency restart\n"); emergency_restart(); + + printk_prefer_direct_exit(); } static DECLARE_DELAYED_WORK(hw_failure_emergency_poweroff_work, @@ -582,11 +590,13 @@ void hw_protection_shutdown(const char *reason, int ms_until_forced) { static atomic_t allow_proceed = ATOMIC_INIT(1); + printk_prefer_direct_enter(); + pr_emerg("HARDWARE PROTECTION shutdown (%s)\n", reason); /* Shutdown should be initiated only once. */ if (!atomic_dec_and_test(&allow_proceed)) - return; + goto out; /* * Queue a backup emergency shutdown in the event of @@ -594,6 +604,8 @@ void hw_protection_shutdown(const char *reason, int ms_until_forced) */ hw_failure_emergency_poweroff(ms_until_forced); orderly_poweroff(true); +out: + printk_prefer_direct_exit(); } EXPORT_SYMBOL_GPL(hw_protection_shutdown); diff --git a/kernel/scftorture.c b/kernel/scftorture.c index dcb0410950e4..5d113aa59e77 100644 --- a/kernel/scftorture.c +++ b/kernel/scftorture.c @@ -267,9 +267,10 @@ static void scf_handler(void *scfc_in) } this_cpu_inc(scf_invoked_count); if (longwait <= 0) { - if (!(r & 0xffc0)) + if (!(r & 0xffc0)) { udelay(r & 0x3f); - goto out; + goto out; + } } if (r & 0xfff) goto out; diff --git a/kernel/sched/build_policy.c b/kernel/sched/build_policy.c index e0104b45029a..d9dc9ab3773f 100644 --- a/kernel/sched/build_policy.c +++ b/kernel/sched/build_policy.c @@ -15,6 +15,7 @@ /* Headers: */ #include <linux/sched/clock.h> #include <linux/sched/cputime.h> +#include <linux/sched/hotplug.h> #include <linux/sched/posix-timers.h> #include <linux/sched/rt.h> @@ -31,6 +32,7 @@ #include <uapi/linux/sched/types.h> #include "sched.h" +#include "smp.h" #include "autogroup.h" #include "stats.h" diff --git a/kernel/sched/build_utility.c b/kernel/sched/build_utility.c index eec0849b2aae..99bdd96f454f 100644 --- a/kernel/sched/build_utility.c +++ b/kernel/sched/build_utility.c @@ -14,6 +14,7 @@ #include <linux/sched/debug.h> #include <linux/sched/isolation.h> #include <linux/sched/loadavg.h> +#include <linux/sched/nohz.h> #include <linux/sched/mm.h> #include <linux/sched/rseq_api.h> #include <linux/sched/task_stack.h> diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c index d9272d9061a3..e374c0c923da 100644 --- a/kernel/sched/clock.c +++ b/kernel/sched/clock.c @@ -287,7 +287,7 @@ again: clock = wrap_max(clock, min_clock); clock = wrap_min(clock, max_clock); - if (cmpxchg64(&scd->clock, old_clock, clock) != old_clock) + if (!try_cmpxchg64(&scd->clock, &old_clock, clock)) goto again; return clock; @@ -349,7 +349,7 @@ again: val = remote_clock; } - if (cmpxchg64(ptr, old_val, val) != old_val) + if (!try_cmpxchg64(ptr, &old_val, val)) goto again; return val; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index d575b4914925..a247f8d9d417 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -26,7 +26,10 @@ #include <linux/topology.h> #include <linux/sched/clock.h> #include <linux/sched/cond_resched.h> +#include <linux/sched/cputime.h> #include <linux/sched/debug.h> +#include <linux/sched/hotplug.h> +#include <linux/sched/init.h> #include <linux/sched/isolation.h> #include <linux/sched/loadavg.h> #include <linux/sched/mm.h> @@ -610,10 +613,10 @@ void double_rq_lock(struct rq *rq1, struct rq *rq2) swap(rq1, rq2); raw_spin_rq_lock(rq1); - if (__rq_lockp(rq1) == __rq_lockp(rq2)) - return; + if (__rq_lockp(rq1) != __rq_lockp(rq2)) + raw_spin_rq_lock_nested(rq2, SINGLE_DEPTH_NESTING); - raw_spin_rq_lock_nested(rq2, SINGLE_DEPTH_NESTING); + double_rq_clock_clear_update(rq1, rq2); } #endif @@ -2190,7 +2193,7 @@ void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags) { if (p->sched_class == rq->curr->sched_class) rq->curr->sched_class->check_preempt_curr(rq, p, flags); - else if (p->sched_class > rq->curr->sched_class) + else if (sched_class_above(p->sched_class, rq->curr->sched_class)) resched_curr(rq); /* @@ -2408,7 +2411,7 @@ static int migration_cpu_stop(void *data) * __migrate_task() such that we will not miss enforcing cpus_ptr * during wakeups, see set_cpus_allowed_ptr()'s TASK_WAKING test. */ - flush_smp_call_function_from_idle(); + flush_smp_call_function_queue(); raw_spin_lock(&p->pi_lock); rq_lock(rq, &rf); @@ -5689,7 +5692,7 @@ __pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) * higher scheduling class, because otherwise those lose the * opportunity to pull in more work from other CPUs. */ - if (likely(prev->sched_class <= &fair_sched_class && + if (likely(!sched_class_above(prev->sched_class, &fair_sched_class) && rq->nr_running == rq->cfs.h_nr_running)) { p = pick_next_task_fair(rq, prev, rf); @@ -5752,6 +5755,8 @@ static inline struct task_struct *pick_task(struct rq *rq) extern void task_vruntime_update(struct rq *rq, struct task_struct *p, bool in_fi); +static void queue_core_balance(struct rq *rq); + static struct task_struct * pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) { @@ -5801,7 +5806,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) } rq->core_pick = NULL; - return next; + goto out; } put_prev_task_balance(rq, prev, rf); @@ -5851,7 +5856,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) */ WARN_ON_ONCE(fi_before); task_vruntime_update(rq, next, false); - goto done; + goto out_set_next; } } @@ -5970,8 +5975,12 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) resched_curr(rq_i); } -done: +out_set_next: set_next_task(rq, next); +out: + if (rq->core->core_forceidle_count && next == rq->idle) + queue_core_balance(rq); + return next; } @@ -6000,7 +6009,7 @@ static bool try_steal_cookie(int this, int that) if (p == src->core_pick || p == src->curr) goto next; - if (!cpumask_test_cpu(this, &p->cpus_mask)) + if (!is_cpu_allowed(p, this)) goto next; if (p->core_occupation > dst->idle->core_occupation) @@ -6066,7 +6075,7 @@ static void sched_core_balance(struct rq *rq) static DEFINE_PER_CPU(struct callback_head, core_balance_head); -void queue_core_balance(struct rq *rq) +static void queue_core_balance(struct rq *rq) { if (!sched_core_enabled(rq)) return; @@ -6376,7 +6385,7 @@ static void __sched notrace __schedule(unsigned int sched_mode) migrate_disable_switch(rq, prev); psi_sched_switch(prev, next, !task_on_rq_queued(prev)); - trace_sched_switch(sched_mode & SM_MASK_PREEMPT, prev_state, prev, next); + trace_sched_switch(sched_mode & SM_MASK_PREEMPT, prev, next, prev_state); /* Also unlocks the rq: */ rq = context_switch(rq, prev, next, &rf); @@ -8409,6 +8418,18 @@ static void __init preempt_dynamic_init(void) } } +#define PREEMPT_MODEL_ACCESSOR(mode) \ + bool preempt_model_##mode(void) \ + { \ + WARN_ON_ONCE(preempt_dynamic_mode == preempt_dynamic_undefined); \ + return preempt_dynamic_mode == preempt_dynamic_##mode; \ + } \ + EXPORT_SYMBOL_GPL(preempt_model_##mode) + +PREEMPT_MODEL_ACCESSOR(none); +PREEMPT_MODEL_ACCESSOR(voluntary); +PREEMPT_MODEL_ACCESSOR(full); + #else /* !CONFIG_PREEMPT_DYNAMIC */ static inline void preempt_dynamic_init(void) { } @@ -9451,11 +9472,11 @@ void __init sched_init(void) int i; /* Make sure the linker didn't screw up */ - BUG_ON(&idle_sched_class + 1 != &fair_sched_class || - &fair_sched_class + 1 != &rt_sched_class || - &rt_sched_class + 1 != &dl_sched_class); + BUG_ON(&idle_sched_class != &fair_sched_class + 1 || + &fair_sched_class != &rt_sched_class + 1 || + &rt_sched_class != &dl_sched_class + 1); #ifdef CONFIG_SMP - BUG_ON(&dl_sched_class + 1 != &stop_sched_class); + BUG_ON(&dl_sched_class != &stop_sched_class + 1); #endif wait_bit_init(); diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index fb4255ae0b2c..936817ae142f 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -1220,8 +1220,6 @@ int dl_runtime_exceeded(struct sched_dl_entity *dl_se) return (dl_se->runtime <= 0); } -extern bool sched_rt_bandwidth_account(struct rt_rq *rt_rq); - /* * This function implements the GRUB accounting rule: * according to the GRUB reclaiming algorithm, the runtime is @@ -1832,6 +1830,7 @@ out: static void migrate_task_rq_dl(struct task_struct *p, int new_cpu __maybe_unused) { + struct rq_flags rf; struct rq *rq; if (READ_ONCE(p->__state) != TASK_WAKING) @@ -1843,7 +1842,7 @@ static void migrate_task_rq_dl(struct task_struct *p, int new_cpu __maybe_unused * from try_to_wake_up(). Hence, p->pi_lock is locked, but * rq->lock is not... So, lock it */ - raw_spin_rq_lock(rq); + rq_lock(rq, &rf); if (p->dl.dl_non_contending) { update_rq_clock(rq); sub_running_bw(&p->dl, &rq->dl); @@ -1859,7 +1858,7 @@ static void migrate_task_rq_dl(struct task_struct *p, int new_cpu __maybe_unused put_task_struct(p); } sub_rq_bw(&p->dl, &rq->dl); - raw_spin_rq_unlock(rq); + rq_unlock(rq, &rf); } static void check_preempt_equal_dl(struct rq *rq, struct task_struct *p) @@ -2319,13 +2318,7 @@ retry: deactivate_task(rq, next_task, 0); set_task_cpu(next_task, later_rq->cpu); - - /* - * Update the later_rq clock here, because the clock is used - * by the cpufreq_update_util() inside __add_running_bw(). - */ - update_rq_clock(later_rq); - activate_task(later_rq, next_task, ENQUEUE_NOCLOCK); + activate_task(later_rq, next_task, 0); ret = 1; resched_curr(later_rq); diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index d4bd299d67ab..906b2c7c48d1 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -36,6 +36,7 @@ #include <linux/sched/cond_resched.h> #include <linux/sched/cputime.h> #include <linux/sched/isolation.h> +#include <linux/sched/nohz.h> #include <linux/cpuidle.h> #include <linux/interrupt.h> @@ -313,19 +314,6 @@ const struct sched_class fair_sched_class; #define for_each_sched_entity(se) \ for (; se; se = se->parent) -static inline void cfs_rq_tg_path(struct cfs_rq *cfs_rq, char *path, int len) -{ - if (!path) - return; - - if (cfs_rq && task_group_is_autogroup(cfs_rq->tg)) - autogroup_path(cfs_rq->tg, path, len); - else if (cfs_rq && cfs_rq->tg->css.cgroup) - cgroup_path(cfs_rq->tg->css.cgroup, path, len); - else - strlcpy(path, "(null)", len); -} - static inline bool list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq) { struct rq *rq = rq_of(cfs_rq); @@ -493,12 +481,6 @@ static int se_is_idle(struct sched_entity *se) #define for_each_sched_entity(se) \ for (; se; se = NULL) -static inline void cfs_rq_tg_path(struct cfs_rq *cfs_rq, char *path, int len) -{ - if (path) - strlcpy(path, "(null)", len); -} - static inline bool list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq) { return true; @@ -3829,11 +3811,11 @@ static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s se->avg.runnable_sum = se->avg.runnable_avg * divider; - se->avg.load_sum = divider; - if (se_weight(se)) { - se->avg.load_sum = - div_u64(se->avg.load_avg * se->avg.load_sum, se_weight(se)); - } + se->avg.load_sum = se->avg.load_avg * divider; + if (se_weight(se) < se->avg.load_sum) + se->avg.load_sum = div_u64(se->avg.load_sum, se_weight(se)); + else + se->avg.load_sum = 1; enqueue_load_avg(cfs_rq, se); cfs_rq->avg.util_avg += se->avg.util_avg; @@ -4846,11 +4828,11 @@ static int tg_unthrottle_up(struct task_group *tg, void *data) cfs_rq->throttle_count--; if (!cfs_rq->throttle_count) { - cfs_rq->throttled_clock_task_time += rq_clock_task(rq) - - cfs_rq->throttled_clock_task; + cfs_rq->throttled_clock_pelt_time += rq_clock_pelt(rq) - + cfs_rq->throttled_clock_pelt; /* Add cfs_rq with load or one or more already running entities to the list */ - if (!cfs_rq_is_decayed(cfs_rq) || cfs_rq->nr_running) + if (!cfs_rq_is_decayed(cfs_rq)) list_add_leaf_cfs_rq(cfs_rq); } @@ -4864,7 +4846,7 @@ static int tg_throttle_down(struct task_group *tg, void *data) /* group is entering throttled state, stop time */ if (!cfs_rq->throttle_count) { - cfs_rq->throttled_clock_task = rq_clock_task(rq); + cfs_rq->throttled_clock_pelt = rq_clock_pelt(rq); list_del_leaf_cfs_rq(cfs_rq); } cfs_rq->throttle_count++; @@ -5308,7 +5290,7 @@ static void sync_throttle(struct task_group *tg, int cpu) pcfs_rq = tg->parent->cfs_rq[cpu]; cfs_rq->throttle_count = pcfs_rq->throttle_count; - cfs_rq->throttled_clock_task = rq_clock_task(cpu_rq(cpu)); + cfs_rq->throttled_clock_pelt = rq_clock_pelt(cpu_rq(cpu)); } /* conditionally throttle active cfs_rq's from put_prev_entity() */ @@ -6544,108 +6526,19 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target) } /* - * cpu_util_without: compute cpu utilization without any contributions from *p - * @cpu: the CPU which utilization is requested - * @p: the task which utilization should be discounted - * - * The utilization of a CPU is defined by the utilization of tasks currently - * enqueued on that CPU as well as tasks which are currently sleeping after an - * execution on that CPU. - * - * This method returns the utilization of the specified CPU by discounting the - * utilization of the specified task, whenever the task is currently - * contributing to the CPU utilization. - */ -static unsigned long cpu_util_without(int cpu, struct task_struct *p) -{ - struct cfs_rq *cfs_rq; - unsigned int util; - - /* Task has no contribution or is new */ - if (cpu != task_cpu(p) || !READ_ONCE(p->se.avg.last_update_time)) - return cpu_util_cfs(cpu); - - cfs_rq = &cpu_rq(cpu)->cfs; - util = READ_ONCE(cfs_rq->avg.util_avg); - - /* Discount task's util from CPU's util */ - lsub_positive(&util, task_util(p)); - - /* - * Covered cases: - * - * a) if *p is the only task sleeping on this CPU, then: - * cpu_util (== task_util) > util_est (== 0) - * and thus we return: - * cpu_util_without = (cpu_util - task_util) = 0 - * - * b) if other tasks are SLEEPING on this CPU, which is now exiting - * IDLE, then: - * cpu_util >= task_util - * cpu_util > util_est (== 0) - * and thus we discount *p's blocked utilization to return: - * cpu_util_without = (cpu_util - task_util) >= 0 - * - * c) if other tasks are RUNNABLE on that CPU and - * util_est > cpu_util - * then we use util_est since it returns a more restrictive - * estimation of the spare capacity on that CPU, by just - * considering the expected utilization of tasks already - * runnable on that CPU. - * - * Cases a) and b) are covered by the above code, while case c) is - * covered by the following code when estimated utilization is - * enabled. - */ - if (sched_feat(UTIL_EST)) { - unsigned int estimated = - READ_ONCE(cfs_rq->avg.util_est.enqueued); - - /* - * Despite the following checks we still have a small window - * for a possible race, when an execl's select_task_rq_fair() - * races with LB's detach_task(): - * - * detach_task() - * p->on_rq = TASK_ON_RQ_MIGRATING; - * ---------------------------------- A - * deactivate_task() \ - * dequeue_task() + RaceTime - * util_est_dequeue() / - * ---------------------------------- B - * - * The additional check on "current == p" it's required to - * properly fix the execl regression and it helps in further - * reducing the chances for the above race. - */ - if (unlikely(task_on_rq_queued(p) || current == p)) - lsub_positive(&estimated, _task_util_est(p)); - - util = max(util, estimated); - } - - /* - * Utilization (estimated) can exceed the CPU capacity, thus let's - * clamp to the maximum CPU capacity to ensure consistency with - * cpu_util. - */ - return min_t(unsigned long, util, capacity_orig_of(cpu)); -} - -/* - * Predicts what cpu_util(@cpu) would return if @p was migrated (and enqueued) - * to @dst_cpu. + * Predicts what cpu_util(@cpu) would return if @p was removed from @cpu + * (@dst_cpu = -1) or migrated to @dst_cpu. */ static unsigned long cpu_util_next(int cpu, struct task_struct *p, int dst_cpu) { struct cfs_rq *cfs_rq = &cpu_rq(cpu)->cfs; - unsigned long util_est, util = READ_ONCE(cfs_rq->avg.util_avg); + unsigned long util = READ_ONCE(cfs_rq->avg.util_avg); /* - * If @p migrates from @cpu to another, remove its contribution. Or, - * if @p migrates from another CPU to @cpu, add its contribution. In - * the other cases, @cpu is not impacted by the migration, so the - * util_avg should already be correct. + * If @dst_cpu is -1 or @p migrates from @cpu to @dst_cpu remove its + * contribution. If @p migrates from another CPU to @cpu add its + * contribution. In all the other cases @cpu is not impacted by the + * migration so its util_avg is already correct. */ if (task_cpu(p) == cpu && dst_cpu != cpu) lsub_positive(&util, task_util(p)); @@ -6653,16 +6546,40 @@ static unsigned long cpu_util_next(int cpu, struct task_struct *p, int dst_cpu) util += task_util(p); if (sched_feat(UTIL_EST)) { + unsigned long util_est; + util_est = READ_ONCE(cfs_rq->avg.util_est.enqueued); /* - * During wake-up, the task isn't enqueued yet and doesn't - * appear in the cfs_rq->avg.util_est.enqueued of any rq, - * so just add it (if needed) to "simulate" what will be - * cpu_util after the task has been enqueued. + * During wake-up @p isn't enqueued yet and doesn't contribute + * to any cpu_rq(cpu)->cfs.avg.util_est.enqueued. + * If @dst_cpu == @cpu add it to "simulate" cpu_util after @p + * has been enqueued. + * + * During exec (@dst_cpu = -1) @p is enqueued and does + * contribute to cpu_rq(cpu)->cfs.util_est.enqueued. + * Remove it to "simulate" cpu_util without @p's contribution. + * + * Despite the task_on_rq_queued(@p) check there is still a + * small window for a possible race when an exec + * select_task_rq_fair() races with LB's detach_task(). + * + * detach_task() + * deactivate_task() + * p->on_rq = TASK_ON_RQ_MIGRATING; + * -------------------------------- A + * dequeue_task() \ + * dequeue_task_fair() + Race Time + * util_est_dequeue() / + * -------------------------------- B + * + * The additional check "current == p" is required to further + * reduce the race window. */ if (dst_cpu == cpu) util_est += _task_util_est(p); + else if (unlikely(task_on_rq_queued(p) || current == p)) + lsub_positive(&util_est, _task_util_est(p)); util = max(util, util_est); } @@ -6671,6 +6588,28 @@ static unsigned long cpu_util_next(int cpu, struct task_struct *p, int dst_cpu) } /* + * cpu_util_without: compute cpu utilization without any contributions from *p + * @cpu: the CPU which utilization is requested + * @p: the task which utilization should be discounted + * + * The utilization of a CPU is defined by the utilization of tasks currently + * enqueued on that CPU as well as tasks which are currently sleeping after an + * execution on that CPU. + * + * This method returns the utilization of the specified CPU by discounting the + * utilization of the specified task, whenever the task is currently + * contributing to the CPU utilization. + */ +static unsigned long cpu_util_without(int cpu, struct task_struct *p) +{ + /* Task has no contribution or is new */ + if (cpu != task_cpu(p) || !READ_ONCE(p->se.avg.last_update_time)) + return cpu_util_cfs(cpu); + + return cpu_util_next(cpu, p, -1); +} + +/* * compute_energy(): Estimates the energy that @pd would consume if @p was * migrated to @dst_cpu. compute_energy() predicts what will be the utilization * landscape of @pd's CPUs after the task migration, and uses the Energy Model @@ -9460,8 +9399,6 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s local->avg_load = (local->group_load * SCHED_CAPACITY_SCALE) / local->group_capacity; - sds->avg_load = (sds->total_load * SCHED_CAPACITY_SCALE) / - sds->total_capacity; /* * If the local group is more loaded than the selected * busiest group don't try to pull any tasks. @@ -9470,6 +9407,9 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s env->imbalance = 0; return; } + + sds->avg_load = (sds->total_load * SCHED_CAPACITY_SCALE) / + sds->total_capacity; } /* @@ -9495,7 +9435,7 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s * busiest \ local has_spare fully_busy misfit asym imbalanced overloaded * has_spare nr_idle balanced N/A N/A balanced balanced * fully_busy nr_idle nr_idle N/A N/A balanced balanced - * misfit_task force N/A N/A N/A force force + * misfit_task force N/A N/A N/A N/A N/A * asym_packing force force N/A N/A force force * imbalanced force force N/A N/A force force * overloaded force force N/A N/A force avg_load @@ -11881,101 +11821,3 @@ __init void init_sched_fair_class(void) #endif /* SMP */ } - -/* - * Helper functions to facilitate extracting info from tracepoints. - */ - -const struct sched_avg *sched_trace_cfs_rq_avg(struct cfs_rq *cfs_rq) -{ -#ifdef CONFIG_SMP - return cfs_rq ? &cfs_rq->avg : NULL; -#else - return NULL; -#endif -} -EXPORT_SYMBOL_GPL(sched_trace_cfs_rq_avg); - -char *sched_trace_cfs_rq_path(struct cfs_rq *cfs_rq, char *str, int len) -{ - if (!cfs_rq) { - if (str) - strlcpy(str, "(null)", len); - else - return NULL; - } - - cfs_rq_tg_path(cfs_rq, str, len); - return str; -} -EXPORT_SYMBOL_GPL(sched_trace_cfs_rq_path); - -int sched_trace_cfs_rq_cpu(struct cfs_rq *cfs_rq) -{ - return cfs_rq ? cpu_of(rq_of(cfs_rq)) : -1; -} -EXPORT_SYMBOL_GPL(sched_trace_cfs_rq_cpu); - -const struct sched_avg *sched_trace_rq_avg_rt(struct rq *rq) -{ -#ifdef CONFIG_SMP - return rq ? &rq->avg_rt : NULL; -#else - return NULL; -#endif -} -EXPORT_SYMBOL_GPL(sched_trace_rq_avg_rt); - -const struct sched_avg *sched_trace_rq_avg_dl(struct rq *rq) -{ -#ifdef CONFIG_SMP - return rq ? &rq->avg_dl : NULL; -#else - return NULL; -#endif -} -EXPORT_SYMBOL_GPL(sched_trace_rq_avg_dl); - -const struct sched_avg *sched_trace_rq_avg_irq(struct rq *rq) -{ -#if defined(CONFIG_SMP) && defined(CONFIG_HAVE_SCHED_AVG_IRQ) - return rq ? &rq->avg_irq : NULL; -#else - return NULL; -#endif -} -EXPORT_SYMBOL_GPL(sched_trace_rq_avg_irq); - -int sched_trace_rq_cpu(struct rq *rq) -{ - return rq ? cpu_of(rq) : -1; -} -EXPORT_SYMBOL_GPL(sched_trace_rq_cpu); - -int sched_trace_rq_cpu_capacity(struct rq *rq) -{ - return rq ? -#ifdef CONFIG_SMP - rq->cpu_capacity -#else - SCHED_CAPACITY_SCALE -#endif - : -1; -} -EXPORT_SYMBOL_GPL(sched_trace_rq_cpu_capacity); - -const struct cpumask *sched_trace_rd_span(struct root_domain *rd) -{ -#ifdef CONFIG_SMP - return rd ? rd->span : NULL; -#else - return NULL; -#endif -} -EXPORT_SYMBOL_GPL(sched_trace_rd_span); - -int sched_trace_rq_nr_running(struct rq *rq) -{ - return rq ? rq->nr_running : -1; -} -EXPORT_SYMBOL_GPL(sched_trace_rq_nr_running); diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 8f8b5020e76a..328cccbee444 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -102,7 +102,7 @@ void __cpuidle default_idle_call(void) * last -- this is very similar to the entry code. */ trace_hardirqs_on_prepare(); - lockdep_hardirqs_on_prepare(_THIS_IP_); + lockdep_hardirqs_on_prepare(); rcu_idle_enter(); lockdep_hardirqs_on(_THIS_IP_); @@ -327,7 +327,7 @@ static void do_idle(void) * RCU relies on this call to be done outside of an RCU read-side * critical section. */ - flush_smp_call_function_from_idle(); + flush_smp_call_function_queue(); schedule_idle(); if (unlikely(klp_patch_pending(current))) @@ -434,7 +434,6 @@ static void set_next_task_idle(struct rq *rq, struct task_struct *next, bool fir { update_idle_core(rq); schedstat_inc(rq->sched_goidle); - queue_core_balance(rq); } #ifdef CONFIG_SMP diff --git a/kernel/sched/pelt.h b/kernel/sched/pelt.h index c336f5f481bc..4ff2ed4f8fa1 100644 --- a/kernel/sched/pelt.h +++ b/kernel/sched/pelt.h @@ -145,9 +145,9 @@ static inline u64 rq_clock_pelt(struct rq *rq) static inline u64 cfs_rq_clock_pelt(struct cfs_rq *cfs_rq) { if (unlikely(cfs_rq->throttle_count)) - return cfs_rq->throttled_clock_task - cfs_rq->throttled_clock_task_time; + return cfs_rq->throttled_clock_pelt - cfs_rq->throttled_clock_pelt_time; - return rq_clock_pelt(rq_of(cfs_rq)) - cfs_rq->throttled_clock_task_time; + return rq_clock_pelt(rq_of(cfs_rq)) - cfs_rq->throttled_clock_pelt_time; } #else static inline u64 cfs_rq_clock_pelt(struct cfs_rq *cfs_rq) diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index a4fa3aadfcba..a337f3e35997 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -1060,14 +1060,17 @@ int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res) mutex_unlock(&group->avgs_lock); for (full = 0; full < 2; full++) { - unsigned long avg[3]; - u64 total; + unsigned long avg[3] = { 0, }; + u64 total = 0; int w; - for (w = 0; w < 3; w++) - avg[w] = group->avg[res * 2 + full][w]; - total = div_u64(group->total[PSI_AVGS][res * 2 + full], - NSEC_PER_USEC); + /* CPU FULL is undefined at the system level */ + if (!(group == &psi_system && res == PSI_CPU && full)) { + for (w = 0; w < 3; w++) + avg[w] = group->avg[res * 2 + full][w]; + total = div_u64(group->total[PSI_AVGS][res * 2 + full], + NSEC_PER_USEC); + } seq_printf(m, "%s avg10=%lu.%02lu avg60=%lu.%02lu avg300=%lu.%02lu total=%llu\n", full ? "full" : "some", @@ -1117,7 +1120,8 @@ struct psi_trigger *psi_trigger_create(struct psi_group *group, t->state = state; t->threshold = threshold_us * NSEC_PER_USEC; t->win.size = window_us * NSEC_PER_USEC; - window_reset(&t->win, 0, 0, 0); + window_reset(&t->win, sched_clock(), + group->total[PSI_POLL][t->state], 0); t->event = 0; t->last_event_time = 0; diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index a32c46889af8..7891c0f0e1ff 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -871,6 +871,7 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun) int enqueue = 0; struct rt_rq *rt_rq = sched_rt_period_rt_rq(rt_b, i); struct rq *rq = rq_of_rt_rq(rt_rq); + struct rq_flags rf; int skip; /* @@ -885,7 +886,7 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun) if (skip) continue; - raw_spin_rq_lock(rq); + rq_lock(rq, &rf); update_rq_clock(rq); if (rt_rq->rt_time) { @@ -923,7 +924,7 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun) if (enqueue) sched_rt_rq_enqueue(rt_rq); - raw_spin_rq_unlock(rq); + rq_unlock(rq, &rf); } if (!throttled && (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF)) diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 58263f90c559..2ce18584dca3 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -603,8 +603,8 @@ struct cfs_rq { s64 runtime_remaining; u64 throttled_clock; - u64 throttled_clock_task; - u64 throttled_clock_task_time; + u64 throttled_clock_pelt; + u64 throttled_clock_pelt_time; int throttled; int throttle_count; struct list_head throttled_list; @@ -1232,8 +1232,6 @@ static inline bool sched_group_cookie_match(struct rq *rq, return false; } -extern void queue_core_balance(struct rq *rq); - static inline bool sched_core_enqueued(struct task_struct *p) { return !RB_EMPTY_NODE(&p->core_node); @@ -1267,10 +1265,6 @@ static inline raw_spinlock_t *__rq_lockp(struct rq *rq) return &rq->__lock; } -static inline void queue_core_balance(struct rq *rq) -{ -} - static inline bool sched_cpu_cookie_match(struct rq *rq, struct task_struct *p) { return true; @@ -1833,12 +1827,7 @@ static inline void dirty_sched_domain_sysctl(int cpu) #endif extern int sched_update_scaling(void); - -extern void flush_smp_call_function_from_idle(void); - -#else /* !CONFIG_SMP: */ -static inline void flush_smp_call_function_from_idle(void) { } -#endif +#endif /* CONFIG_SMP */ #include "stats.h" @@ -2188,6 +2177,8 @@ static inline void set_next_task(struct rq *rq, struct task_struct *next) * * include/asm-generic/vmlinux.lds.h * + * *CAREFUL* they are laid out in *REVERSE* order!!! + * * Also enforce alignment on the instance, not the type, to guarantee layout. */ #define DEFINE_SCHED_CLASS(name) \ @@ -2196,17 +2187,16 @@ const struct sched_class name##_sched_class \ __section("__" #name "_sched_class") /* Defined in include/asm-generic/vmlinux.lds.h */ -extern struct sched_class __begin_sched_classes[]; -extern struct sched_class __end_sched_classes[]; - -#define sched_class_highest (__end_sched_classes - 1) -#define sched_class_lowest (__begin_sched_classes - 1) +extern struct sched_class __sched_class_highest[]; +extern struct sched_class __sched_class_lowest[]; #define for_class_range(class, _from, _to) \ - for (class = (_from); class != (_to); class--) + for (class = (_from); class < (_to); class++) #define for_each_class(class) \ - for_class_range(class, sched_class_highest, sched_class_lowest) + for_class_range(class, __sched_class_highest, __sched_class_lowest) + +#define sched_class_above(_a, _b) ((_a) < (_b)) extern const struct sched_class stop_sched_class; extern const struct sched_class dl_sched_class; @@ -2315,6 +2305,7 @@ extern void resched_cpu(int cpu); extern struct rt_bandwidth def_rt_bandwidth; extern void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime); +extern bool sched_rt_bandwidth_account(struct rt_rq *rt_rq); extern void init_dl_bandwidth(struct dl_bandwidth *dl_b, u64 period, u64 runtime); extern void init_dl_task_timer(struct sched_dl_entity *dl_se); @@ -2484,6 +2475,24 @@ unsigned long arch_scale_freq_capacity(int cpu) } #endif +#ifdef CONFIG_SCHED_DEBUG +/* + * In double_lock_balance()/double_rq_lock(), we use raw_spin_rq_lock() to + * acquire rq lock instead of rq_lock(). So at the end of these two functions + * we need to call double_rq_clock_clear_update() to clear RQCF_UPDATED of + * rq->clock_update_flags to avoid the WARN_DOUBLE_CLOCK warning. + */ +static inline void double_rq_clock_clear_update(struct rq *rq1, struct rq *rq2) +{ + rq1->clock_update_flags &= (RQCF_REQ_SKIP|RQCF_ACT_SKIP); + /* rq1 == rq2 for !CONFIG_SMP, so just clear RQCF_UPDATED once. */ +#ifdef CONFIG_SMP + rq2->clock_update_flags &= (RQCF_REQ_SKIP|RQCF_ACT_SKIP); +#endif +} +#else +static inline void double_rq_clock_clear_update(struct rq *rq1, struct rq *rq2) {} +#endif #ifdef CONFIG_SMP @@ -2549,14 +2558,15 @@ static inline int _double_lock_balance(struct rq *this_rq, struct rq *busiest) __acquires(busiest->lock) __acquires(this_rq->lock) { - if (__rq_lockp(this_rq) == __rq_lockp(busiest)) - return 0; - - if (likely(raw_spin_rq_trylock(busiest))) + if (__rq_lockp(this_rq) == __rq_lockp(busiest) || + likely(raw_spin_rq_trylock(busiest))) { + double_rq_clock_clear_update(this_rq, busiest); return 0; + } if (rq_order_less(this_rq, busiest)) { raw_spin_rq_lock_nested(busiest, SINGLE_DEPTH_NESTING); + double_rq_clock_clear_update(this_rq, busiest); return 0; } @@ -2650,6 +2660,7 @@ static inline void double_rq_lock(struct rq *rq1, struct rq *rq2) BUG_ON(rq1 != rq2); raw_spin_rq_lock(rq1); __acquire(rq2->lock); /* Fake it out ;) */ + double_rq_clock_clear_update(rq1, rq2); } /* diff --git a/kernel/sched/smp.h b/kernel/sched/smp.h index 9620e323162c..2eb23dd0f285 100644 --- a/kernel/sched/smp.h +++ b/kernel/sched/smp.h @@ -7,3 +7,9 @@ extern void sched_ttwu_pending(void *arg); extern void send_call_function_single_ipi(int cpu); + +#ifdef CONFIG_SMP +extern void flush_smp_call_function_queue(void); +#else +static inline void flush_smp_call_function_queue(void) { } +#endif diff --git a/kernel/seccomp.c b/kernel/seccomp.c index b5ac87f6dbd4..e9852d1b4a5e 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -200,6 +200,8 @@ static inline void seccomp_cache_prepare(struct seccomp_filter *sfilter) * the filter can be freed. * @cache: cache of arch/syscall mappings to actions * @log: true if all actions except for SECCOMP_RET_ALLOW should be logged + * @wait_killable_recv: Put notifying process in killable state once the + * notification is received by the userspace listener. * @prev: points to a previously installed, or inherited, filter * @prog: the BPF program to evaluate * @notif: the struct that holds all notification related information @@ -220,6 +222,7 @@ struct seccomp_filter { refcount_t refs; refcount_t users; bool log; + bool wait_killable_recv; struct action_cache cache; struct seccomp_filter *prev; struct bpf_prog *prog; @@ -893,6 +896,10 @@ static long seccomp_attach_filter(unsigned int flags, if (flags & SECCOMP_FILTER_FLAG_LOG) filter->log = true; + /* Set wait killable flag, if present. */ + if (flags & SECCOMP_FILTER_FLAG_WAIT_KILLABLE_RECV) + filter->wait_killable_recv = true; + /* * If there is an existing filter, make it the prev and don't drop its * task reference. @@ -1080,6 +1087,12 @@ static void seccomp_handle_addfd(struct seccomp_kaddfd *addfd, struct seccomp_kn complete(&addfd->completion); } +static bool should_sleep_killable(struct seccomp_filter *match, + struct seccomp_knotif *n) +{ + return match->wait_killable_recv && n->state == SECCOMP_NOTIFY_SENT; +} + static int seccomp_do_user_notification(int this_syscall, struct seccomp_filter *match, const struct seccomp_data *sd) @@ -1100,7 +1113,7 @@ static int seccomp_do_user_notification(int this_syscall, n.data = sd; n.id = seccomp_next_notify_id(match); init_completion(&n.ready); - list_add(&n.list, &match->notif->notifications); + list_add_tail(&n.list, &match->notif->notifications); INIT_LIST_HEAD(&n.addfd); up(&match->notif->request); @@ -1110,11 +1123,25 @@ static int seccomp_do_user_notification(int this_syscall, * This is where we wait for a reply from userspace. */ do { + bool wait_killable = should_sleep_killable(match, &n); + mutex_unlock(&match->notify_lock); - err = wait_for_completion_interruptible(&n.ready); + if (wait_killable) + err = wait_for_completion_killable(&n.ready); + else + err = wait_for_completion_interruptible(&n.ready); mutex_lock(&match->notify_lock); - if (err != 0) + + if (err != 0) { + /* + * Check to see if the notifcation got picked up and + * whether we should switch to wait killable. + */ + if (!wait_killable && should_sleep_killable(match, &n)) + continue; + goto interrupted; + } addfd = list_first_entry_or_null(&n.addfd, struct seccomp_kaddfd, list); @@ -1484,6 +1511,9 @@ out: mutex_lock(&filter->notify_lock); knotif = find_notification(filter, unotif.id); if (knotif) { + /* Reset the process to make sure it's not stuck */ + if (should_sleep_killable(filter, knotif)) + complete(&knotif->ready); knotif->state = SECCOMP_NOTIFY_INIT; up(&filter->notif->request); } @@ -1829,6 +1859,14 @@ static long seccomp_set_mode_filter(unsigned int flags, ((flags & SECCOMP_FILTER_FLAG_TSYNC_ESRCH) == 0)) return -EINVAL; + /* + * The SECCOMP_FILTER_FLAG_WAIT_KILLABLE_SENT flag doesn't make sense + * without the SECCOMP_FILTER_FLAG_NEW_LISTENER flag. + */ + if ((flags & SECCOMP_FILTER_FLAG_WAIT_KILLABLE_RECV) && + ((flags & SECCOMP_FILTER_FLAG_NEW_LISTENER) == 0)) + return -EINVAL; + /* Prepare the new filter before holding any locks. */ prepared = seccomp_prepare_user_filter(filter); if (IS_ERR(prepared)) diff --git a/kernel/signal.c b/kernel/signal.c index 30cd1ca43bcd..e43bc2a692f5 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1805,7 +1805,7 @@ int force_sig_pkuerr(void __user *addr, u32 pkey) } #endif -int force_sig_perf(void __user *addr, u32 type, u64 sig_data) +int send_sig_perf(void __user *addr, u32 type, u64 sig_data) { struct kernel_siginfo info; @@ -1817,7 +1817,18 @@ int force_sig_perf(void __user *addr, u32 type, u64 sig_data) info.si_perf_data = sig_data; info.si_perf_type = type; - return force_sig_info(&info); + /* + * Signals generated by perf events should not terminate the whole + * process if SIGTRAP is blocked, however, delivering the signal + * asynchronously is better than not delivering at all. But tell user + * space if the signal was asynchronous, so it can clearly be + * distinguished from normal synchronous ones. + */ + info.si_perf_flags = sigismember(¤t->blocked, info.si_signo) ? + TRAP_PERF_FLAG_ASYNC : + 0; + + return send_sig_info(info.si_signo, &info, current); } /** @@ -3432,6 +3443,7 @@ void copy_siginfo_to_external32(struct compat_siginfo *to, to->si_addr = ptr_to_compat(from->si_addr); to->si_perf_data = from->si_perf_data; to->si_perf_type = from->si_perf_type; + to->si_perf_flags = from->si_perf_flags; break; case SIL_CHLD: to->si_pid = from->si_pid; @@ -3509,6 +3521,7 @@ static int post_copy_siginfo_from_user32(kernel_siginfo_t *to, to->si_addr = compat_ptr(from->si_addr); to->si_perf_data = from->si_perf_data; to->si_perf_type = from->si_perf_type; + to->si_perf_flags = from->si_perf_flags; break; case SIL_CHLD: to->si_pid = from->si_pid; @@ -4722,6 +4735,7 @@ static inline void siginfo_buildtime_checks(void) CHECK_OFFSET(si_pkey); CHECK_OFFSET(si_perf_data); CHECK_OFFSET(si_perf_type); + CHECK_OFFSET(si_perf_flags); /* sigpoll */ CHECK_OFFSET(si_band); diff --git a/kernel/smp.c b/kernel/smp.c index 01a7c1706a58..dd215f439426 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -96,7 +96,7 @@ static DEFINE_PER_CPU_ALIGNED(struct call_function_data, cfd_data); static DEFINE_PER_CPU_SHARED_ALIGNED(struct llist_head, call_single_queue); -static void flush_smp_call_function_queue(bool warn_cpu_offline); +static void __flush_smp_call_function_queue(bool warn_cpu_offline); int smpcfd_prepare_cpu(unsigned int cpu) { @@ -141,7 +141,7 @@ int smpcfd_dying_cpu(unsigned int cpu) * ensure that the outgoing CPU doesn't go offline with work * still pending. */ - flush_smp_call_function_queue(false); + __flush_smp_call_function_queue(false); irq_work_run(); return 0; } @@ -183,7 +183,9 @@ static DEFINE_PER_CPU(smp_call_func_t, cur_csd_func); static DEFINE_PER_CPU(void *, cur_csd_info); static DEFINE_PER_CPU(struct cfd_seq_local, cfd_seq_local); -#define CSD_LOCK_TIMEOUT (5ULL * NSEC_PER_SEC) +static ulong csd_lock_timeout = 5000; /* CSD lock timeout in milliseconds. */ +module_param(csd_lock_timeout, ulong, 0444); + static atomic_t csd_bug_count = ATOMIC_INIT(0); static u64 cfd_seq; @@ -329,6 +331,7 @@ static bool csd_lock_wait_toolong(struct __call_single_data *csd, u64 ts0, u64 * u64 ts2, ts_delta; call_single_data_t *cpu_cur_csd; unsigned int flags = READ_ONCE(csd->node.u_flags); + unsigned long long csd_lock_timeout_ns = csd_lock_timeout * NSEC_PER_MSEC; if (!(flags & CSD_FLAG_LOCK)) { if (!unlikely(*bug_id)) @@ -341,7 +344,7 @@ static bool csd_lock_wait_toolong(struct __call_single_data *csd, u64 ts0, u64 * ts2 = sched_clock(); ts_delta = ts2 - *ts1; - if (likely(ts_delta <= CSD_LOCK_TIMEOUT)) + if (likely(ts_delta <= csd_lock_timeout_ns || csd_lock_timeout_ns == 0)) return false; firsttime = !*bug_id; @@ -541,11 +544,11 @@ void generic_smp_call_function_single_interrupt(void) { cfd_seq_store(this_cpu_ptr(&cfd_seq_local)->gotipi, CFD_SEQ_NOCPU, smp_processor_id(), CFD_SEQ_GOTIPI); - flush_smp_call_function_queue(true); + __flush_smp_call_function_queue(true); } /** - * flush_smp_call_function_queue - Flush pending smp-call-function callbacks + * __flush_smp_call_function_queue - Flush pending smp-call-function callbacks * * @warn_cpu_offline: If set to 'true', warn if callbacks were queued on an * offline CPU. Skip this check if set to 'false'. @@ -558,7 +561,7 @@ void generic_smp_call_function_single_interrupt(void) * Loop through the call_single_queue and run all the queued callbacks. * Must be called with interrupts disabled. */ -static void flush_smp_call_function_queue(bool warn_cpu_offline) +static void __flush_smp_call_function_queue(bool warn_cpu_offline) { call_single_data_t *csd, *csd_next; struct llist_node *entry, *prev; @@ -579,7 +582,7 @@ static void flush_smp_call_function_queue(bool warn_cpu_offline) /* There shouldn't be any pending callbacks on an offline CPU. */ if (unlikely(warn_cpu_offline && !cpu_online(smp_processor_id()) && - !warned && !llist_empty(head))) { + !warned && entry != NULL)) { warned = true; WARN(1, "IPI on offline CPU %d\n", smp_processor_id()); @@ -681,8 +684,22 @@ static void flush_smp_call_function_queue(bool warn_cpu_offline) smp_processor_id(), CFD_SEQ_HDLEND); } -void flush_smp_call_function_from_idle(void) + +/** + * flush_smp_call_function_queue - Flush pending smp-call-function callbacks + * from task context (idle, migration thread) + * + * When TIF_POLLING_NRFLAG is supported and a CPU is in idle and has it + * set, then remote CPUs can avoid sending IPIs and wake the idle CPU by + * setting TIF_NEED_RESCHED. The idle task on the woken up CPU has to + * handle queued SMP function calls before scheduling. + * + * The migration thread has to ensure that an eventually pending wakeup has + * been handled before it migrates a task. + */ +void flush_smp_call_function_queue(void) { + unsigned int was_pending; unsigned long flags; if (llist_empty(this_cpu_ptr(&call_single_queue))) @@ -691,9 +708,11 @@ void flush_smp_call_function_from_idle(void) cfd_seq_store(this_cpu_ptr(&cfd_seq_local)->idle, CFD_SEQ_NOCPU, smp_processor_id(), CFD_SEQ_IDLE); local_irq_save(flags); - flush_smp_call_function_queue(true); + /* Get the already pending soft interrupts for RT enabled kernels */ + was_pending = local_softirq_pending(); + __flush_smp_call_function_queue(true); if (local_softirq_pending()) - do_softirq(); + do_softirq_post_smp_call_flush(was_pending); local_irq_restore(flags); } diff --git a/kernel/smpboot.c b/kernel/smpboot.c index f6bc0bc8a2aa..b9f54544e749 100644 --- a/kernel/smpboot.c +++ b/kernel/smpboot.c @@ -392,6 +392,13 @@ int cpu_check_up_prepare(int cpu) */ return -EAGAIN; + case CPU_UP_PREPARE: + /* + * Timeout while waiting for the CPU to show up. Allow to try + * again later. + */ + return 0; + default: /* Should not happen. Famous last words. */ diff --git a/kernel/softirq.c b/kernel/softirq.c index fac801815554..9f0aef8aa9ff 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -294,6 +294,19 @@ static inline void invoke_softirq(void) wakeup_softirqd(); } +/* + * flush_smp_call_function_queue() can raise a soft interrupt in a function + * call. On RT kernels this is undesired and the only known functionality + * in the block layer which does this is disabled on RT. If soft interrupts + * get raised which haven't been raised before the flush, warn so it can be + * investigated. + */ +void do_softirq_post_smp_call_flush(unsigned int was_pending) +{ + if (WARN_ON_ONCE(was_pending != local_softirq_pending())) + invoke_softirq(); +} + #else /* CONFIG_PREEMPT_RT */ /* diff --git a/kernel/stackleak.c b/kernel/stackleak.c index ddb5a7f48d69..c2c33d2202e9 100644 --- a/kernel/stackleak.c +++ b/kernel/stackleak.c @@ -70,59 +70,81 @@ late_initcall(stackleak_sysctls_init); #define skip_erasing() false #endif /* CONFIG_STACKLEAK_RUNTIME_DISABLE */ -asmlinkage void noinstr stackleak_erase(void) +static __always_inline void __stackleak_erase(bool on_task_stack) { - /* It would be nice not to have 'kstack_ptr' and 'boundary' on stack */ - unsigned long kstack_ptr = current->lowest_stack; - unsigned long boundary = (unsigned long)end_of_stack(current); - unsigned int poison_count = 0; - const unsigned int depth = STACKLEAK_SEARCH_DEPTH / sizeof(unsigned long); - - if (skip_erasing()) - return; - - /* Check that 'lowest_stack' value is sane */ - if (unlikely(kstack_ptr - boundary >= THREAD_SIZE)) - kstack_ptr = boundary; + const unsigned long task_stack_low = stackleak_task_low_bound(current); + const unsigned long task_stack_high = stackleak_task_high_bound(current); + unsigned long erase_low, erase_high; - /* Search for the poison value in the kernel stack */ - while (kstack_ptr > boundary && poison_count <= depth) { - if (*(unsigned long *)kstack_ptr == STACKLEAK_POISON) - poison_count++; - else - poison_count = 0; - - kstack_ptr -= sizeof(unsigned long); - } - - /* - * One 'long int' at the bottom of the thread stack is reserved and - * should not be poisoned (see CONFIG_SCHED_STACK_END_CHECK=y). - */ - if (kstack_ptr == boundary) - kstack_ptr += sizeof(unsigned long); + erase_low = stackleak_find_top_of_poison(task_stack_low, + current->lowest_stack); #ifdef CONFIG_STACKLEAK_METRICS - current->prev_lowest_stack = kstack_ptr; + current->prev_lowest_stack = erase_low; #endif /* - * Now write the poison value to the kernel stack. Start from - * 'kstack_ptr' and move up till the new 'boundary'. We assume that - * the stack pointer doesn't change when we write poison. + * Write poison to the task's stack between 'erase_low' and + * 'erase_high'. + * + * If we're running on a different stack (e.g. an entry trampoline + * stack) we can erase everything below the pt_regs at the top of the + * task stack. + * + * If we're running on the task stack itself, we must not clobber any + * stack used by this function and its caller. We assume that this + * function has a fixed-size stack frame, and the current stack pointer + * doesn't change while we write poison. */ - if (on_thread_stack()) - boundary = current_stack_pointer; + if (on_task_stack) + erase_high = current_stack_pointer; else - boundary = current_top_of_stack(); + erase_high = task_stack_high; - while (kstack_ptr < boundary) { - *(unsigned long *)kstack_ptr = STACKLEAK_POISON; - kstack_ptr += sizeof(unsigned long); + while (erase_low < erase_high) { + *(unsigned long *)erase_low = STACKLEAK_POISON; + erase_low += sizeof(unsigned long); } /* Reset the 'lowest_stack' value for the next syscall */ - current->lowest_stack = current_top_of_stack() - THREAD_SIZE/64; + current->lowest_stack = task_stack_high; +} + +/* + * Erase and poison the portion of the task stack used since the last erase. + * Can be called from the task stack or an entry stack when the task stack is + * no longer in use. + */ +asmlinkage void noinstr stackleak_erase(void) +{ + if (skip_erasing()) + return; + + __stackleak_erase(on_thread_stack()); +} + +/* + * Erase and poison the portion of the task stack used since the last erase. + * Can only be called from the task stack. + */ +asmlinkage void noinstr stackleak_erase_on_task_stack(void) +{ + if (skip_erasing()) + return; + + __stackleak_erase(true); +} + +/* + * Erase and poison the portion of the task stack used since the last erase. + * Can only be called from a stack other than the task stack. + */ +asmlinkage void noinstr stackleak_erase_off_task_stack(void) +{ + if (skip_erasing()) + return; + + __stackleak_erase(false); } void __used __no_caller_saved_registers noinstr stackleak_track_stack(void) @@ -139,8 +161,7 @@ void __used __no_caller_saved_registers noinstr stackleak_track_stack(void) /* 'lowest_stack' should be aligned on the register width boundary */ sp = ALIGN(sp, sizeof(unsigned long)); if (sp < current->lowest_stack && - sp >= (unsigned long)task_stack_page(current) + - sizeof(unsigned long)) { + sp >= stackleak_task_low_bound(current)) { current->lowest_stack = sp; } } diff --git a/kernel/static_call.c b/kernel/static_call.c index f2b8baea35d2..e9c3e69f3837 100644 --- a/kernel/static_call.c +++ b/kernel/static_call.c @@ -1,549 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 -#include <linux/init.h> #include <linux/static_call.h> -#include <linux/bug.h> -#include <linux/smp.h> -#include <linux/sort.h> -#include <linux/slab.h> -#include <linux/module.h> -#include <linux/cpu.h> -#include <linux/processor.h> -#include <asm/sections.h> - -extern struct static_call_site __start_static_call_sites[], - __stop_static_call_sites[]; -extern struct static_call_tramp_key __start_static_call_tramp_key[], - __stop_static_call_tramp_key[]; - -static bool static_call_initialized; - -/* mutex to protect key modules/sites */ -static DEFINE_MUTEX(static_call_mutex); - -static void static_call_lock(void) -{ - mutex_lock(&static_call_mutex); -} - -static void static_call_unlock(void) -{ - mutex_unlock(&static_call_mutex); -} - -static inline void *static_call_addr(struct static_call_site *site) -{ - return (void *)((long)site->addr + (long)&site->addr); -} - -static inline unsigned long __static_call_key(const struct static_call_site *site) -{ - return (long)site->key + (long)&site->key; -} - -static inline struct static_call_key *static_call_key(const struct static_call_site *site) -{ - return (void *)(__static_call_key(site) & ~STATIC_CALL_SITE_FLAGS); -} - -/* These assume the key is word-aligned. */ -static inline bool static_call_is_init(struct static_call_site *site) -{ - return __static_call_key(site) & STATIC_CALL_SITE_INIT; -} - -static inline bool static_call_is_tail(struct static_call_site *site) -{ - return __static_call_key(site) & STATIC_CALL_SITE_TAIL; -} - -static inline void static_call_set_init(struct static_call_site *site) -{ - site->key = (__static_call_key(site) | STATIC_CALL_SITE_INIT) - - (long)&site->key; -} - -static int static_call_site_cmp(const void *_a, const void *_b) -{ - const struct static_call_site *a = _a; - const struct static_call_site *b = _b; - const struct static_call_key *key_a = static_call_key(a); - const struct static_call_key *key_b = static_call_key(b); - - if (key_a < key_b) - return -1; - - if (key_a > key_b) - return 1; - - return 0; -} - -static void static_call_site_swap(void *_a, void *_b, int size) -{ - long delta = (unsigned long)_a - (unsigned long)_b; - struct static_call_site *a = _a; - struct static_call_site *b = _b; - struct static_call_site tmp = *a; - - a->addr = b->addr - delta; - a->key = b->key - delta; - - b->addr = tmp.addr + delta; - b->key = tmp.key + delta; -} - -static inline void static_call_sort_entries(struct static_call_site *start, - struct static_call_site *stop) -{ - sort(start, stop - start, sizeof(struct static_call_site), - static_call_site_cmp, static_call_site_swap); -} - -static inline bool static_call_key_has_mods(struct static_call_key *key) -{ - return !(key->type & 1); -} - -static inline struct static_call_mod *static_call_key_next(struct static_call_key *key) -{ - if (!static_call_key_has_mods(key)) - return NULL; - - return key->mods; -} - -static inline struct static_call_site *static_call_key_sites(struct static_call_key *key) -{ - if (static_call_key_has_mods(key)) - return NULL; - - return (struct static_call_site *)(key->type & ~1); -} - -void __static_call_update(struct static_call_key *key, void *tramp, void *func) -{ - struct static_call_site *site, *stop; - struct static_call_mod *site_mod, first; - - cpus_read_lock(); - static_call_lock(); - - if (key->func == func) - goto done; - - key->func = func; - - arch_static_call_transform(NULL, tramp, func, false); - - /* - * If uninitialized, we'll not update the callsites, but they still - * point to the trampoline and we just patched that. - */ - if (WARN_ON_ONCE(!static_call_initialized)) - goto done; - - first = (struct static_call_mod){ - .next = static_call_key_next(key), - .mod = NULL, - .sites = static_call_key_sites(key), - }; - - for (site_mod = &first; site_mod; site_mod = site_mod->next) { - bool init = system_state < SYSTEM_RUNNING; - struct module *mod = site_mod->mod; - - if (!site_mod->sites) { - /* - * This can happen if the static call key is defined in - * a module which doesn't use it. - * - * It also happens in the has_mods case, where the - * 'first' entry has no sites associated with it. - */ - continue; - } - - stop = __stop_static_call_sites; - - if (mod) { -#ifdef CONFIG_MODULES - stop = mod->static_call_sites + - mod->num_static_call_sites; - init = mod->state == MODULE_STATE_COMING; -#endif - } - - for (site = site_mod->sites; - site < stop && static_call_key(site) == key; site++) { - void *site_addr = static_call_addr(site); - - if (!init && static_call_is_init(site)) - continue; - - if (!kernel_text_address((unsigned long)site_addr)) { - /* - * This skips patching built-in __exit, which - * is part of init_section_contains() but is - * not part of kernel_text_address(). - * - * Skipping built-in __exit is fine since it - * will never be executed. - */ - WARN_ONCE(!static_call_is_init(site), - "can't patch static call site at %pS", - site_addr); - continue; - } - - arch_static_call_transform(site_addr, NULL, func, - static_call_is_tail(site)); - } - } - -done: - static_call_unlock(); - cpus_read_unlock(); -} -EXPORT_SYMBOL_GPL(__static_call_update); - -static int __static_call_init(struct module *mod, - struct static_call_site *start, - struct static_call_site *stop) -{ - struct static_call_site *site; - struct static_call_key *key, *prev_key = NULL; - struct static_call_mod *site_mod; - - if (start == stop) - return 0; - - static_call_sort_entries(start, stop); - - for (site = start; site < stop; site++) { - void *site_addr = static_call_addr(site); - - if ((mod && within_module_init((unsigned long)site_addr, mod)) || - (!mod && init_section_contains(site_addr, 1))) - static_call_set_init(site); - - key = static_call_key(site); - if (key != prev_key) { - prev_key = key; - - /* - * For vmlinux (!mod) avoid the allocation by storing - * the sites pointer in the key itself. Also see - * __static_call_update()'s @first. - * - * This allows architectures (eg. x86) to call - * static_call_init() before memory allocation works. - */ - if (!mod) { - key->sites = site; - key->type |= 1; - goto do_transform; - } - - site_mod = kzalloc(sizeof(*site_mod), GFP_KERNEL); - if (!site_mod) - return -ENOMEM; - - /* - * When the key has a direct sites pointer, extract - * that into an explicit struct static_call_mod, so we - * can have a list of modules. - */ - if (static_call_key_sites(key)) { - site_mod->mod = NULL; - site_mod->next = NULL; - site_mod->sites = static_call_key_sites(key); - - key->mods = site_mod; - - site_mod = kzalloc(sizeof(*site_mod), GFP_KERNEL); - if (!site_mod) - return -ENOMEM; - } - - site_mod->mod = mod; - site_mod->sites = site; - site_mod->next = static_call_key_next(key); - key->mods = site_mod; - } - -do_transform: - arch_static_call_transform(site_addr, NULL, key->func, - static_call_is_tail(site)); - } - - return 0; -} - -static int addr_conflict(struct static_call_site *site, void *start, void *end) -{ - unsigned long addr = (unsigned long)static_call_addr(site); - - if (addr <= (unsigned long)end && - addr + CALL_INSN_SIZE > (unsigned long)start) - return 1; - - return 0; -} - -static int __static_call_text_reserved(struct static_call_site *iter_start, - struct static_call_site *iter_stop, - void *start, void *end, bool init) -{ - struct static_call_site *iter = iter_start; - - while (iter < iter_stop) { - if (init || !static_call_is_init(iter)) { - if (addr_conflict(iter, start, end)) - return 1; - } - iter++; - } - - return 0; -} - -#ifdef CONFIG_MODULES - -static int __static_call_mod_text_reserved(void *start, void *end) -{ - struct module *mod; - int ret; - - preempt_disable(); - mod = __module_text_address((unsigned long)start); - WARN_ON_ONCE(__module_text_address((unsigned long)end) != mod); - if (!try_module_get(mod)) - mod = NULL; - preempt_enable(); - - if (!mod) - return 0; - - ret = __static_call_text_reserved(mod->static_call_sites, - mod->static_call_sites + mod->num_static_call_sites, - start, end, mod->state == MODULE_STATE_COMING); - - module_put(mod); - - return ret; -} - -static unsigned long tramp_key_lookup(unsigned long addr) -{ - struct static_call_tramp_key *start = __start_static_call_tramp_key; - struct static_call_tramp_key *stop = __stop_static_call_tramp_key; - struct static_call_tramp_key *tramp_key; - - for (tramp_key = start; tramp_key != stop; tramp_key++) { - unsigned long tramp; - - tramp = (long)tramp_key->tramp + (long)&tramp_key->tramp; - if (tramp == addr) - return (long)tramp_key->key + (long)&tramp_key->key; - } - - return 0; -} - -static int static_call_add_module(struct module *mod) -{ - struct static_call_site *start = mod->static_call_sites; - struct static_call_site *stop = start + mod->num_static_call_sites; - struct static_call_site *site; - - for (site = start; site != stop; site++) { - unsigned long s_key = __static_call_key(site); - unsigned long addr = s_key & ~STATIC_CALL_SITE_FLAGS; - unsigned long key; - - /* - * Is the key is exported, 'addr' points to the key, which - * means modules are allowed to call static_call_update() on - * it. - * - * Otherwise, the key isn't exported, and 'addr' points to the - * trampoline so we need to lookup the key. - * - * We go through this dance to prevent crazy modules from - * abusing sensitive static calls. - */ - if (!kernel_text_address(addr)) - continue; - - key = tramp_key_lookup(addr); - if (!key) { - pr_warn("Failed to fixup __raw_static_call() usage at: %ps\n", - static_call_addr(site)); - return -EINVAL; - } - - key |= s_key & STATIC_CALL_SITE_FLAGS; - site->key = key - (long)&site->key; - } - - return __static_call_init(mod, start, stop); -} - -static void static_call_del_module(struct module *mod) -{ - struct static_call_site *start = mod->static_call_sites; - struct static_call_site *stop = mod->static_call_sites + - mod->num_static_call_sites; - struct static_call_key *key, *prev_key = NULL; - struct static_call_mod *site_mod, **prev; - struct static_call_site *site; - - for (site = start; site < stop; site++) { - key = static_call_key(site); - if (key == prev_key) - continue; - - prev_key = key; - - for (prev = &key->mods, site_mod = key->mods; - site_mod && site_mod->mod != mod; - prev = &site_mod->next, site_mod = site_mod->next) - ; - - if (!site_mod) - continue; - - *prev = site_mod->next; - kfree(site_mod); - } -} - -static int static_call_module_notify(struct notifier_block *nb, - unsigned long val, void *data) -{ - struct module *mod = data; - int ret = 0; - - cpus_read_lock(); - static_call_lock(); - - switch (val) { - case MODULE_STATE_COMING: - ret = static_call_add_module(mod); - if (ret) { - WARN(1, "Failed to allocate memory for static calls"); - static_call_del_module(mod); - } - break; - case MODULE_STATE_GOING: - static_call_del_module(mod); - break; - } - - static_call_unlock(); - cpus_read_unlock(); - - return notifier_from_errno(ret); -} - -static struct notifier_block static_call_module_nb = { - .notifier_call = static_call_module_notify, -}; - -#else - -static inline int __static_call_mod_text_reserved(void *start, void *end) -{ - return 0; -} - -#endif /* CONFIG_MODULES */ - -int static_call_text_reserved(void *start, void *end) -{ - bool init = system_state < SYSTEM_RUNNING; - int ret = __static_call_text_reserved(__start_static_call_sites, - __stop_static_call_sites, start, end, init); - - if (ret) - return ret; - - return __static_call_mod_text_reserved(start, end); -} - -int __init static_call_init(void) -{ - int ret; - - if (static_call_initialized) - return 0; - - cpus_read_lock(); - static_call_lock(); - ret = __static_call_init(NULL, __start_static_call_sites, - __stop_static_call_sites); - static_call_unlock(); - cpus_read_unlock(); - - if (ret) { - pr_err("Failed to allocate memory for static_call!\n"); - BUG(); - } - - static_call_initialized = true; - -#ifdef CONFIG_MODULES - register_module_notifier(&static_call_module_nb); -#endif - return 0; -} -early_initcall(static_call_init); long __static_call_return0(void) { return 0; } EXPORT_SYMBOL_GPL(__static_call_return0); - -#ifdef CONFIG_STATIC_CALL_SELFTEST - -static int func_a(int x) -{ - return x+1; -} - -static int func_b(int x) -{ - return x+2; -} - -DEFINE_STATIC_CALL(sc_selftest, func_a); - -static struct static_call_data { - int (*func)(int); - int val; - int expect; -} static_call_data [] __initdata = { - { NULL, 2, 3 }, - { func_b, 2, 4 }, - { func_a, 2, 3 } -}; - -static int __init test_static_call_init(void) -{ - int i; - - for (i = 0; i < ARRAY_SIZE(static_call_data); i++ ) { - struct static_call_data *scd = &static_call_data[i]; - - if (scd->func) - static_call_update(sc_selftest, scd->func); - - WARN_ON(static_call(sc_selftest)(scd->val) != scd->expect); - } - - return 0; -} -early_initcall(test_static_call_init); - -#endif /* CONFIG_STATIC_CALL_SELFTEST */ diff --git a/kernel/static_call_inline.c b/kernel/static_call_inline.c new file mode 100644 index 000000000000..dc5665b62814 --- /dev/null +++ b/kernel/static_call_inline.c @@ -0,0 +1,543 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/init.h> +#include <linux/static_call.h> +#include <linux/bug.h> +#include <linux/smp.h> +#include <linux/sort.h> +#include <linux/slab.h> +#include <linux/module.h> +#include <linux/cpu.h> +#include <linux/processor.h> +#include <asm/sections.h> + +extern struct static_call_site __start_static_call_sites[], + __stop_static_call_sites[]; +extern struct static_call_tramp_key __start_static_call_tramp_key[], + __stop_static_call_tramp_key[]; + +static bool static_call_initialized; + +/* mutex to protect key modules/sites */ +static DEFINE_MUTEX(static_call_mutex); + +static void static_call_lock(void) +{ + mutex_lock(&static_call_mutex); +} + +static void static_call_unlock(void) +{ + mutex_unlock(&static_call_mutex); +} + +static inline void *static_call_addr(struct static_call_site *site) +{ + return (void *)((long)site->addr + (long)&site->addr); +} + +static inline unsigned long __static_call_key(const struct static_call_site *site) +{ + return (long)site->key + (long)&site->key; +} + +static inline struct static_call_key *static_call_key(const struct static_call_site *site) +{ + return (void *)(__static_call_key(site) & ~STATIC_CALL_SITE_FLAGS); +} + +/* These assume the key is word-aligned. */ +static inline bool static_call_is_init(struct static_call_site *site) +{ + return __static_call_key(site) & STATIC_CALL_SITE_INIT; +} + +static inline bool static_call_is_tail(struct static_call_site *site) +{ + return __static_call_key(site) & STATIC_CALL_SITE_TAIL; +} + +static inline void static_call_set_init(struct static_call_site *site) +{ + site->key = (__static_call_key(site) | STATIC_CALL_SITE_INIT) - + (long)&site->key; +} + +static int static_call_site_cmp(const void *_a, const void *_b) +{ + const struct static_call_site *a = _a; + const struct static_call_site *b = _b; + const struct static_call_key *key_a = static_call_key(a); + const struct static_call_key *key_b = static_call_key(b); + + if (key_a < key_b) + return -1; + + if (key_a > key_b) + return 1; + + return 0; +} + +static void static_call_site_swap(void *_a, void *_b, int size) +{ + long delta = (unsigned long)_a - (unsigned long)_b; + struct static_call_site *a = _a; + struct static_call_site *b = _b; + struct static_call_site tmp = *a; + + a->addr = b->addr - delta; + a->key = b->key - delta; + + b->addr = tmp.addr + delta; + b->key = tmp.key + delta; +} + +static inline void static_call_sort_entries(struct static_call_site *start, + struct static_call_site *stop) +{ + sort(start, stop - start, sizeof(struct static_call_site), + static_call_site_cmp, static_call_site_swap); +} + +static inline bool static_call_key_has_mods(struct static_call_key *key) +{ + return !(key->type & 1); +} + +static inline struct static_call_mod *static_call_key_next(struct static_call_key *key) +{ + if (!static_call_key_has_mods(key)) + return NULL; + + return key->mods; +} + +static inline struct static_call_site *static_call_key_sites(struct static_call_key *key) +{ + if (static_call_key_has_mods(key)) + return NULL; + + return (struct static_call_site *)(key->type & ~1); +} + +void __static_call_update(struct static_call_key *key, void *tramp, void *func) +{ + struct static_call_site *site, *stop; + struct static_call_mod *site_mod, first; + + cpus_read_lock(); + static_call_lock(); + + if (key->func == func) + goto done; + + key->func = func; + + arch_static_call_transform(NULL, tramp, func, false); + + /* + * If uninitialized, we'll not update the callsites, but they still + * point to the trampoline and we just patched that. + */ + if (WARN_ON_ONCE(!static_call_initialized)) + goto done; + + first = (struct static_call_mod){ + .next = static_call_key_next(key), + .mod = NULL, + .sites = static_call_key_sites(key), + }; + + for (site_mod = &first; site_mod; site_mod = site_mod->next) { + bool init = system_state < SYSTEM_RUNNING; + struct module *mod = site_mod->mod; + + if (!site_mod->sites) { + /* + * This can happen if the static call key is defined in + * a module which doesn't use it. + * + * It also happens in the has_mods case, where the + * 'first' entry has no sites associated with it. + */ + continue; + } + + stop = __stop_static_call_sites; + + if (mod) { +#ifdef CONFIG_MODULES + stop = mod->static_call_sites + + mod->num_static_call_sites; + init = mod->state == MODULE_STATE_COMING; +#endif + } + + for (site = site_mod->sites; + site < stop && static_call_key(site) == key; site++) { + void *site_addr = static_call_addr(site); + + if (!init && static_call_is_init(site)) + continue; + + if (!kernel_text_address((unsigned long)site_addr)) { + /* + * This skips patching built-in __exit, which + * is part of init_section_contains() but is + * not part of kernel_text_address(). + * + * Skipping built-in __exit is fine since it + * will never be executed. + */ + WARN_ONCE(!static_call_is_init(site), + "can't patch static call site at %pS", + site_addr); + continue; + } + + arch_static_call_transform(site_addr, NULL, func, + static_call_is_tail(site)); + } + } + +done: + static_call_unlock(); + cpus_read_unlock(); +} +EXPORT_SYMBOL_GPL(__static_call_update); + +static int __static_call_init(struct module *mod, + struct static_call_site *start, + struct static_call_site *stop) +{ + struct static_call_site *site; + struct static_call_key *key, *prev_key = NULL; + struct static_call_mod *site_mod; + + if (start == stop) + return 0; + + static_call_sort_entries(start, stop); + + for (site = start; site < stop; site++) { + void *site_addr = static_call_addr(site); + + if ((mod && within_module_init((unsigned long)site_addr, mod)) || + (!mod && init_section_contains(site_addr, 1))) + static_call_set_init(site); + + key = static_call_key(site); + if (key != prev_key) { + prev_key = key; + + /* + * For vmlinux (!mod) avoid the allocation by storing + * the sites pointer in the key itself. Also see + * __static_call_update()'s @first. + * + * This allows architectures (eg. x86) to call + * static_call_init() before memory allocation works. + */ + if (!mod) { + key->sites = site; + key->type |= 1; + goto do_transform; + } + + site_mod = kzalloc(sizeof(*site_mod), GFP_KERNEL); + if (!site_mod) + return -ENOMEM; + + /* + * When the key has a direct sites pointer, extract + * that into an explicit struct static_call_mod, so we + * can have a list of modules. + */ + if (static_call_key_sites(key)) { + site_mod->mod = NULL; + site_mod->next = NULL; + site_mod->sites = static_call_key_sites(key); + + key->mods = site_mod; + + site_mod = kzalloc(sizeof(*site_mod), GFP_KERNEL); + if (!site_mod) + return -ENOMEM; + } + + site_mod->mod = mod; + site_mod->sites = site; + site_mod->next = static_call_key_next(key); + key->mods = site_mod; + } + +do_transform: + arch_static_call_transform(site_addr, NULL, key->func, + static_call_is_tail(site)); + } + + return 0; +} + +static int addr_conflict(struct static_call_site *site, void *start, void *end) +{ + unsigned long addr = (unsigned long)static_call_addr(site); + + if (addr <= (unsigned long)end && + addr + CALL_INSN_SIZE > (unsigned long)start) + return 1; + + return 0; +} + +static int __static_call_text_reserved(struct static_call_site *iter_start, + struct static_call_site *iter_stop, + void *start, void *end, bool init) +{ + struct static_call_site *iter = iter_start; + + while (iter < iter_stop) { + if (init || !static_call_is_init(iter)) { + if (addr_conflict(iter, start, end)) + return 1; + } + iter++; + } + + return 0; +} + +#ifdef CONFIG_MODULES + +static int __static_call_mod_text_reserved(void *start, void *end) +{ + struct module *mod; + int ret; + + preempt_disable(); + mod = __module_text_address((unsigned long)start); + WARN_ON_ONCE(__module_text_address((unsigned long)end) != mod); + if (!try_module_get(mod)) + mod = NULL; + preempt_enable(); + + if (!mod) + return 0; + + ret = __static_call_text_reserved(mod->static_call_sites, + mod->static_call_sites + mod->num_static_call_sites, + start, end, mod->state == MODULE_STATE_COMING); + + module_put(mod); + + return ret; +} + +static unsigned long tramp_key_lookup(unsigned long addr) +{ + struct static_call_tramp_key *start = __start_static_call_tramp_key; + struct static_call_tramp_key *stop = __stop_static_call_tramp_key; + struct static_call_tramp_key *tramp_key; + + for (tramp_key = start; tramp_key != stop; tramp_key++) { + unsigned long tramp; + + tramp = (long)tramp_key->tramp + (long)&tramp_key->tramp; + if (tramp == addr) + return (long)tramp_key->key + (long)&tramp_key->key; + } + + return 0; +} + +static int static_call_add_module(struct module *mod) +{ + struct static_call_site *start = mod->static_call_sites; + struct static_call_site *stop = start + mod->num_static_call_sites; + struct static_call_site *site; + + for (site = start; site != stop; site++) { + unsigned long s_key = __static_call_key(site); + unsigned long addr = s_key & ~STATIC_CALL_SITE_FLAGS; + unsigned long key; + + /* + * Is the key is exported, 'addr' points to the key, which + * means modules are allowed to call static_call_update() on + * it. + * + * Otherwise, the key isn't exported, and 'addr' points to the + * trampoline so we need to lookup the key. + * + * We go through this dance to prevent crazy modules from + * abusing sensitive static calls. + */ + if (!kernel_text_address(addr)) + continue; + + key = tramp_key_lookup(addr); + if (!key) { + pr_warn("Failed to fixup __raw_static_call() usage at: %ps\n", + static_call_addr(site)); + return -EINVAL; + } + + key |= s_key & STATIC_CALL_SITE_FLAGS; + site->key = key - (long)&site->key; + } + + return __static_call_init(mod, start, stop); +} + +static void static_call_del_module(struct module *mod) +{ + struct static_call_site *start = mod->static_call_sites; + struct static_call_site *stop = mod->static_call_sites + + mod->num_static_call_sites; + struct static_call_key *key, *prev_key = NULL; + struct static_call_mod *site_mod, **prev; + struct static_call_site *site; + + for (site = start; site < stop; site++) { + key = static_call_key(site); + if (key == prev_key) + continue; + + prev_key = key; + + for (prev = &key->mods, site_mod = key->mods; + site_mod && site_mod->mod != mod; + prev = &site_mod->next, site_mod = site_mod->next) + ; + + if (!site_mod) + continue; + + *prev = site_mod->next; + kfree(site_mod); + } +} + +static int static_call_module_notify(struct notifier_block *nb, + unsigned long val, void *data) +{ + struct module *mod = data; + int ret = 0; + + cpus_read_lock(); + static_call_lock(); + + switch (val) { + case MODULE_STATE_COMING: + ret = static_call_add_module(mod); + if (ret) { + WARN(1, "Failed to allocate memory for static calls"); + static_call_del_module(mod); + } + break; + case MODULE_STATE_GOING: + static_call_del_module(mod); + break; + } + + static_call_unlock(); + cpus_read_unlock(); + + return notifier_from_errno(ret); +} + +static struct notifier_block static_call_module_nb = { + .notifier_call = static_call_module_notify, +}; + +#else + +static inline int __static_call_mod_text_reserved(void *start, void *end) +{ + return 0; +} + +#endif /* CONFIG_MODULES */ + +int static_call_text_reserved(void *start, void *end) +{ + bool init = system_state < SYSTEM_RUNNING; + int ret = __static_call_text_reserved(__start_static_call_sites, + __stop_static_call_sites, start, end, init); + + if (ret) + return ret; + + return __static_call_mod_text_reserved(start, end); +} + +int __init static_call_init(void) +{ + int ret; + + if (static_call_initialized) + return 0; + + cpus_read_lock(); + static_call_lock(); + ret = __static_call_init(NULL, __start_static_call_sites, + __stop_static_call_sites); + static_call_unlock(); + cpus_read_unlock(); + + if (ret) { + pr_err("Failed to allocate memory for static_call!\n"); + BUG(); + } + + static_call_initialized = true; + +#ifdef CONFIG_MODULES + register_module_notifier(&static_call_module_nb); +#endif + return 0; +} +early_initcall(static_call_init); + +#ifdef CONFIG_STATIC_CALL_SELFTEST + +static int func_a(int x) +{ + return x+1; +} + +static int func_b(int x) +{ + return x+2; +} + +DEFINE_STATIC_CALL(sc_selftest, func_a); + +static struct static_call_data { + int (*func)(int); + int val; + int expect; +} static_call_data [] __initdata = { + { NULL, 2, 3 }, + { func_b, 2, 4 }, + { func_a, 2, 3 } +}; + +static int __init test_static_call_init(void) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(static_call_data); i++ ) { + struct static_call_data *scd = &static_call_data[i]; + + if (scd->func) + static_call_update(sc_selftest, scd->func); + + WARN_ON(static_call(sc_selftest)(scd->val) != scd->expect); + } + + return 0; +} +early_initcall(test_static_call_init); + +#endif /* CONFIG_STATIC_CALL_SELFTEST */ diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c index cbc30271ea4d..cedb17ba158a 100644 --- a/kernel/stop_machine.c +++ b/kernel/stop_machine.c @@ -535,8 +535,6 @@ void stop_machine_park(int cpu) kthread_park(stopper->thread); } -extern void sched_set_stop_task(int cpu, struct task_struct *stop); - static void cpu_stop_create(unsigned int cpu) { sched_set_stop_task(cpu, per_cpu(cpu_stopper.thread, cpu)); @@ -633,6 +631,27 @@ int stop_machine(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus) } EXPORT_SYMBOL_GPL(stop_machine); +#ifdef CONFIG_SCHED_SMT +int stop_core_cpuslocked(unsigned int cpu, cpu_stop_fn_t fn, void *data) +{ + const struct cpumask *smt_mask = cpu_smt_mask(cpu); + + struct multi_stop_data msdata = { + .fn = fn, + .data = data, + .num_threads = cpumask_weight(smt_mask), + .active_cpus = smt_mask, + }; + + lockdep_assert_cpus_held(); + + /* Set the initial state and stop all online cpus. */ + set_state(&msdata, MULTI_STOP_PREPARE); + return stop_cpus(smt_mask, multi_cpu_stop, &msdata); +} +EXPORT_SYMBOL_GPL(stop_core_cpuslocked); +#endif + /** * stop_machine_from_inactive_cpu - stop_machine() from inactive CPU * @fn: the function to run diff --git a/kernel/sys.c b/kernel/sys.c index 374f83e95239..b911fa6d81ab 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -117,6 +117,12 @@ #ifndef SVE_GET_VL # define SVE_GET_VL() (-EINVAL) #endif +#ifndef SME_SET_VL +# define SME_SET_VL(a) (-EINVAL) +#endif +#ifndef SME_GET_VL +# define SME_GET_VL() (-EINVAL) +#endif #ifndef PAC_RESET_KEYS # define PAC_RESET_KEYS(a, b) (-EINVAL) #endif @@ -2541,6 +2547,12 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, case PR_SVE_GET_VL: error = SVE_GET_VL(); break; + case PR_SME_SET_VL: + error = SME_SET_VL(arg2); + break; + case PR_SME_GET_VL: + error = SME_GET_VL(); + break; case PR_GET_SPECULATION_CTRL: if (arg3 || arg4 || arg5) return -EINVAL; diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 830aaf8ca08e..5b7b1a82ae6a 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -2288,17 +2288,6 @@ static struct ctl_table kern_table[] = { .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, -#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) - { - .procname = "timer_migration", - .data = &sysctl_timer_migration, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = timer_migration_handler, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, -#endif #ifdef CONFIG_BPF_SYSCALL { .procname = "unprivileged_bpf_disabled", diff --git a/kernel/task_work.c b/kernel/task_work.c index c59e1a49bc40..dff75bcde151 100644 --- a/kernel/task_work.c +++ b/kernel/task_work.c @@ -12,12 +12,22 @@ static struct callback_head work_exited; /* all we need is ->next == NULL */ * @notify: how to notify the targeted task * * Queue @work for task_work_run() below and notify the @task if @notify - * is @TWA_RESUME or @TWA_SIGNAL. @TWA_SIGNAL works like signals, in that the - * it will interrupt the targeted task and run the task_work. @TWA_RESUME - * work is run only when the task exits the kernel and returns to user mode, - * or before entering guest mode. Fails if the @task is exiting/exited and thus - * it can't process this @work. Otherwise @work->func() will be called when the - * @task goes through one of the aforementioned transitions, or exits. + * is @TWA_RESUME, @TWA_SIGNAL, or @TWA_SIGNAL_NO_IPI. + * + * @TWA_SIGNAL works like signals, in that the it will interrupt the targeted + * task and run the task_work, regardless of whether the task is currently + * running in the kernel or userspace. + * @TWA_SIGNAL_NO_IPI works like @TWA_SIGNAL, except it doesn't send a + * reschedule IPI to force the targeted task to reschedule and run task_work. + * This can be advantageous if there's no strict requirement that the + * task_work be run as soon as possible, just whenever the task enters the + * kernel anyway. + * @TWA_RESUME work is run only when the task exits the kernel and returns to + * user mode, or before entering guest mode. + * + * Fails if the @task is exiting/exited and thus it can't process this @work. + * Otherwise @work->func() will be called when the @task goes through one of + * the aforementioned transitions, or exits. * * If the targeted task is exiting, then an error is returned and the work item * is not queued. It's up to the caller to arrange for an alternative mechanism @@ -53,6 +63,9 @@ int task_work_add(struct task_struct *task, struct callback_head *work, case TWA_SIGNAL: set_notify_signal(task); break; + case TWA_SIGNAL_NO_IPI: + __set_notify_signal(task); + break; default: WARN_ON_ONCE(1); break; diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index 003ccf338d20..5d85014d59b5 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -690,7 +690,7 @@ static ssize_t unbind_device_store(struct device *dev, { char name[CS_NAME_LEN]; ssize_t ret = sysfs_get_uname(buf, name, count); - struct clock_event_device *ce; + struct clock_event_device *ce = NULL, *iter; if (ret < 0) return ret; @@ -698,9 +698,10 @@ static ssize_t unbind_device_store(struct device *dev, ret = -ENODEV; mutex_lock(&clockevents_mutex); raw_spin_lock_irq(&clockevents_lock); - list_for_each_entry(ce, &clockevent_devices, list) { - if (!strcmp(ce->name, name)) { - ret = __clockevents_try_unbind(ce, dev->id); + list_for_each_entry(iter, &clockevent_devices, list) { + if (!strcmp(iter->name, name)) { + ret = __clockevents_try_unbind(iter, dev->id); + ce = iter; break; } } diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index 95d7ca35bdf2..cee5da1e54c4 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -343,7 +343,7 @@ void clocksource_verify_percpu(struct clocksource *cs) cpus_read_lock(); preempt_disable(); clocksource_verify_choose_cpus(); - if (cpumask_weight(&cpus_chosen) == 0) { + if (cpumask_empty(&cpus_chosen)) { preempt_enable(); cpus_read_unlock(); pr_warn("Not enough CPUs to check clocksource '%s'.\n", cs->name); diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c index b1b9b12899f5..8464c5acc913 100644 --- a/kernel/time/sched_clock.c +++ b/kernel/time/sched_clock.c @@ -8,6 +8,7 @@ #include <linux/jiffies.h> #include <linux/ktime.h> #include <linux/kernel.h> +#include <linux/math.h> #include <linux/moduleparam.h> #include <linux/sched.h> #include <linux/sched/clock.h> @@ -199,15 +200,13 @@ sched_clock_register(u64 (*read)(void), int bits, unsigned long rate) r = rate; if (r >= 4000000) { - r /= 1000000; + r = DIV_ROUND_CLOSEST(r, 1000000); r_unit = 'M'; + } else if (r >= 4000) { + r = DIV_ROUND_CLOSEST(r, 1000); + r_unit = 'k'; } else { - if (r >= 1000) { - r /= 1000; - r_unit = 'k'; - } else { - r_unit = ' '; - } + r_unit = ' '; } /* Calculate the ns resolution of this counter */ diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 2d76c91b85de..58a11f859ac7 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -188,7 +188,7 @@ static void tick_sched_do_timer(struct tick_sched *ts, ktime_t now) */ if (unlikely(tick_do_timer_cpu == TICK_DO_TIMER_NONE)) { #ifdef CONFIG_NO_HZ_FULL - WARN_ON(tick_nohz_full_running); + WARN_ON_ONCE(tick_nohz_full_running); #endif tick_do_timer_cpu = cpu; } @@ -928,6 +928,8 @@ static void tick_nohz_stop_tick(struct tick_sched *ts, int cpu) if (unlikely(expires == KTIME_MAX)) { if (ts->nohz_mode == NOHZ_MODE_HIGHRES) hrtimer_cancel(&ts->sched_timer); + else + tick_program_event(KTIME_MAX, 1); return; } @@ -1364,9 +1366,15 @@ static void tick_nohz_handler(struct clock_event_device *dev) tick_sched_do_timer(ts, now); tick_sched_handle(ts, regs); - /* No need to reprogram if we are running tickless */ - if (unlikely(ts->tick_stopped)) + if (unlikely(ts->tick_stopped)) { + /* + * The clockevent device is not reprogrammed, so change the + * clock event device to ONESHOT_STOPPED to avoid spurious + * interrupts on devices which might not be truly one shot. + */ + tick_program_event(KTIME_MAX, 1); return; + } hrtimer_forward(&ts->sched_timer, now, TICK_NSEC); tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1); @@ -1538,7 +1546,7 @@ void tick_cancel_sched_timer(int cpu) } #endif -/** +/* * Async notification about clocksource changes */ void tick_clock_notify(void) @@ -1559,7 +1567,7 @@ void tick_oneshot_notify(void) set_bit(0, &ts->check_clocks); } -/** +/* * Check, if a change happened, which makes oneshot possible. * * Called cyclic from the hrtimer softirq (driven by the timer diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index dcdcb85121e4..8e4b3c32fcf9 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -17,6 +17,7 @@ #include <linux/clocksource.h> #include <linux/jiffies.h> #include <linux/time.h> +#include <linux/timex.h> #include <linux/tick.h> #include <linux/stop_machine.h> #include <linux/pvclock_gtod.h> @@ -429,6 +430,14 @@ static void update_fast_timekeeper(const struct tk_read_base *tkr, memcpy(base + 1, base, sizeof(*base)); } +static __always_inline u64 fast_tk_get_delta_ns(struct tk_read_base *tkr) +{ + u64 delta, cycles = tk_clock_read(tkr); + + delta = clocksource_delta(cycles, tkr->cycle_last, tkr->mask); + return timekeeping_delta_to_ns(tkr, delta); +} + static __always_inline u64 __ktime_get_fast_ns(struct tk_fast *tkf) { struct tk_read_base *tkr; @@ -439,12 +448,7 @@ static __always_inline u64 __ktime_get_fast_ns(struct tk_fast *tkf) seq = raw_read_seqcount_latch(&tkf->seq); tkr = tkf->base + (seq & 0x01); now = ktime_to_ns(tkr->base); - - now += timekeeping_delta_to_ns(tkr, - clocksource_delta( - tk_clock_read(tkr), - tkr->cycle_last, - tkr->mask)); + now += fast_tk_get_delta_ns(tkr); } while (read_seqcount_latch_retry(&tkf->seq, seq)); return now; @@ -482,7 +486,7 @@ static __always_inline u64 __ktime_get_fast_ns(struct tk_fast *tkf) * of the following timestamps. Callers need to be aware of that and * deal with it. */ -u64 ktime_get_mono_fast_ns(void) +u64 notrace ktime_get_mono_fast_ns(void) { return __ktime_get_fast_ns(&tk_fast_mono); } @@ -494,7 +498,7 @@ EXPORT_SYMBOL_GPL(ktime_get_mono_fast_ns); * Contrary to ktime_get_mono_fast_ns() this is always correct because the * conversion factor is not affected by NTP/PTP correction. */ -u64 ktime_get_raw_fast_ns(void) +u64 notrace ktime_get_raw_fast_ns(void) { return __ktime_get_fast_ns(&tk_fast_raw); } @@ -528,10 +532,27 @@ u64 notrace ktime_get_boot_fast_ns(void) { struct timekeeper *tk = &tk_core.timekeeper; - return (ktime_get_mono_fast_ns() + ktime_to_ns(tk->offs_boot)); + return (ktime_get_mono_fast_ns() + ktime_to_ns(data_race(tk->offs_boot))); } EXPORT_SYMBOL_GPL(ktime_get_boot_fast_ns); +/** + * ktime_get_tai_fast_ns - NMI safe and fast access to tai clock. + * + * The same limitations as described for ktime_get_boot_fast_ns() apply. The + * mono time and the TAI offset are not read atomically which may yield wrong + * readouts. However, an update of the TAI offset is an rare event e.g., caused + * by settime or adjtimex with an offset. The user of this function has to deal + * with the possibility of wrong timestamps in post processing. + */ +u64 notrace ktime_get_tai_fast_ns(void) +{ + struct timekeeper *tk = &tk_core.timekeeper; + + return (ktime_get_mono_fast_ns() + ktime_to_ns(data_race(tk->offs_tai))); +} +EXPORT_SYMBOL_GPL(ktime_get_tai_fast_ns); + static __always_inline u64 __ktime_get_real_fast(struct tk_fast *tkf, u64 *mono) { struct tk_read_base *tkr; @@ -543,10 +564,7 @@ static __always_inline u64 __ktime_get_real_fast(struct tk_fast *tkf, u64 *mono) tkr = tkf->base + (seq & 0x01); basem = ktime_to_ns(tkr->base); baser = ktime_to_ns(tkr->base_real); - - delta = timekeeping_delta_to_ns(tkr, - clocksource_delta(tk_clock_read(tkr), - tkr->cycle_last, tkr->mask)); + delta = fast_tk_get_delta_ns(tkr); } while (read_seqcount_latch_retry(&tkf->seq, seq)); if (mono) @@ -2380,6 +2398,20 @@ static int timekeeping_validate_timex(const struct __kernel_timex *txc) return 0; } +/** + * random_get_entropy_fallback - Returns the raw clock source value, + * used by random.c for platforms with no valid random_get_entropy(). + */ +unsigned long random_get_entropy_fallback(void) +{ + struct tk_read_base *tkr = &tk_core.timekeeper.tkr_mono; + struct clocksource *clock = READ_ONCE(tkr->clock); + + if (unlikely(timekeeping_suspended || !clock)) + return 0; + return clock->read(clock); +} +EXPORT_SYMBOL_GPL(random_get_entropy_fallback); /** * do_adjtimex() - Accessor function to NTP __do_adjtimex function diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 85f1021ad459..717fcb9fb14a 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -44,6 +44,7 @@ #include <linux/slab.h> #include <linux/compat.h> #include <linux/random.h> +#include <linux/sysctl.h> #include <linux/uaccess.h> #include <asm/unistd.h> @@ -223,7 +224,7 @@ static void timer_update_keys(struct work_struct *work); static DECLARE_WORK(timer_update_work, timer_update_keys); #ifdef CONFIG_SMP -unsigned int sysctl_timer_migration = 1; +static unsigned int sysctl_timer_migration = 1; DEFINE_STATIC_KEY_FALSE(timers_migration_enabled); @@ -234,7 +235,42 @@ static void timers_update_migration(void) else static_branch_disable(&timers_migration_enabled); } -#else + +#ifdef CONFIG_SYSCTL +static int timer_migration_handler(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + int ret; + + mutex_lock(&timer_keys_mutex); + ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); + if (!ret && write) + timers_update_migration(); + mutex_unlock(&timer_keys_mutex); + return ret; +} + +static struct ctl_table timer_sysctl[] = { + { + .procname = "timer_migration", + .data = &sysctl_timer_migration, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = timer_migration_handler, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + {} +}; + +static int __init timer_sysctl_init(void) +{ + register_sysctl("kernel", timer_sysctl); + return 0; +} +device_initcall(timer_sysctl_init); +#endif /* CONFIG_SYSCTL */ +#else /* CONFIG_SMP */ static inline void timers_update_migration(void) { } #endif /* !CONFIG_SMP */ @@ -251,19 +287,6 @@ void timers_update_nohz(void) schedule_work(&timer_update_work); } -int timer_migration_handler(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) -{ - int ret; - - mutex_lock(&timer_keys_mutex); - ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); - if (!ret && write) - timers_update_migration(); - mutex_unlock(&timer_keys_mutex); - return ret; -} - static inline bool is_timers_nohz_active(void) { return static_branch_unlikely(&timers_nohz_active); @@ -502,7 +525,7 @@ static inline unsigned calc_index(unsigned long expires, unsigned lvl, * * Round up with level granularity to prevent this. */ - expires = (expires + LVL_GRAN(lvl)) >> LVL_SHIFT(lvl); + expires = (expires >> LVL_SHIFT(lvl)) + 1; *bucket_expiry = expires << LVL_SHIFT(lvl); return LVL_OFFS(lvl) + (expires & LVL_MASK); } @@ -615,9 +638,39 @@ static void internal_add_timer(struct timer_base *base, struct timer_list *timer static const struct debug_obj_descr timer_debug_descr; +struct timer_hint { + void (*function)(struct timer_list *t); + long offset; +}; + +#define TIMER_HINT(fn, container, timr, hintfn) \ + { \ + .function = fn, \ + .offset = offsetof(container, hintfn) - \ + offsetof(container, timr) \ + } + +static const struct timer_hint timer_hints[] = { + TIMER_HINT(delayed_work_timer_fn, + struct delayed_work, timer, work.func), + TIMER_HINT(kthread_delayed_work_timer_fn, + struct kthread_delayed_work, timer, work.func), +}; + static void *timer_debug_hint(void *addr) { - return ((struct timer_list *) addr)->function; + struct timer_list *timer = addr; + int i; + + for (i = 0; i < ARRAY_SIZE(timer_hints); i++) { + if (timer_hints[i].function == timer->function) { + void (**fn)(void) = addr + timer_hints[i].offset; + + return *fn; + } + } + + return timer->function; } static bool timer_is_static_object(void *addr) @@ -1722,11 +1775,14 @@ static inline void __run_timers(struct timer_base *base) time_after_eq(jiffies, base->next_expiry)) { levels = collect_expired_timers(base, heads); /* - * The only possible reason for not finding any expired - * timer at this clk is that all matching timers have been - * dequeued. + * The two possible reasons for not finding any expired + * timer at this clk are that all matching timers have been + * dequeued or no timer has been queued since + * base::next_expiry was set to base::clk + + * NEXT_TIMER_MAX_DELTA. */ - WARN_ON_ONCE(!levels && !base->next_expiry_recalc); + WARN_ON_ONCE(!levels && !base->next_expiry_recalc + && base->timers_pending); base->clk++; base->next_expiry = __next_timer_interrupt(base); @@ -1777,8 +1833,6 @@ void update_process_times(int user_tick) { struct task_struct *p = current; - PRANDOM_ADD_NOISE(jiffies, user_tick, p, 0); - /* Note: this timer irq context must be accounted for as well. */ account_process_tick(p, user_tick); run_local_timers(); @@ -1950,6 +2004,7 @@ int timers_prepare_cpu(unsigned int cpu) base = per_cpu_ptr(&timer_bases[b], cpu); base->clk = jiffies; base->next_expiry = base->clk + NEXT_TIMER_MAX_DELTA; + base->next_expiry_recalc = false; base->timers_pending = false; base->is_idle = false; } diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 2c43e327a619..debbbb083286 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -144,6 +144,7 @@ config TRACING select BINARY_PRINTF select EVENT_TRACING select TRACE_CLOCK + select TASKS_RCU if PREEMPTION config GENERIC_TRACER bool @@ -728,6 +729,7 @@ config FTRACE_MCOUNT_USE_OBJTOOL depends on !FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY depends on !FTRACE_MCOUNT_USE_CC depends on FTRACE_MCOUNT_RECORD + select OBJTOOL config FTRACE_MCOUNT_USE_RECORDMCOUNT def_bool y diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 4d5629196d01..10a32b0f2deb 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -145,13 +145,14 @@ static void trace_note_time(struct blk_trace *bt) local_irq_restore(flags); } -void __trace_note_message(struct blk_trace *bt, struct blkcg *blkcg, - const char *fmt, ...) +void __blk_trace_note_message(struct blk_trace *bt, + struct cgroup_subsys_state *css, const char *fmt, ...) { int n; va_list args; unsigned long flags; char *buf; + u64 cgid = 0; if (unlikely(bt->trace_state != Blktrace_running && !blk_tracer_enabled)) @@ -170,17 +171,16 @@ void __trace_note_message(struct blk_trace *bt, struct blkcg *blkcg, n = vscnprintf(buf, BLK_TN_MAX_MSG, fmt, args); va_end(args); - if (!(blk_tracer_flags.val & TRACE_BLK_OPT_CGROUP)) - blkcg = NULL; #ifdef CONFIG_BLK_CGROUP - trace_note(bt, current->pid, BLK_TN_MESSAGE, buf, n, - blkcg ? cgroup_id(blkcg->css.cgroup) : 1); -#else - trace_note(bt, current->pid, BLK_TN_MESSAGE, buf, n, 0); + if (css && (blk_tracer_flags.val & TRACE_BLK_OPT_CGROUP)) + cgid = cgroup_id(css->cgroup); + else + cgid = 1; #endif + trace_note(bt, current->pid, BLK_TN_MESSAGE, buf, n, cgid); local_irq_restore(flags); } -EXPORT_SYMBOL_GPL(__trace_note_message); +EXPORT_SYMBOL_GPL(__blk_trace_note_message); static int act_log_check(struct blk_trace *bt, u32 what, sector_t sector, pid_t pid) @@ -411,7 +411,7 @@ static ssize_t blk_msg_write(struct file *filp, const char __user *buffer, return PTR_ERR(msg); bt = filp->private_data; - __trace_note_message(bt, NULL, "%s", msg); + __blk_trace_note_message(bt, NULL, "%s", msg); kfree(msg); return count; @@ -783,6 +783,7 @@ void blk_trace_shutdown(struct request_queue *q) #ifdef CONFIG_BLK_CGROUP static u64 blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio) { + struct cgroup_subsys_state *blkcg_css; struct blk_trace *bt; /* We don't use the 'bt' value here except as an optimization... */ @@ -790,9 +791,10 @@ static u64 blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio) if (!bt || !(blk_tracer_flags.val & TRACE_BLK_OPT_CGROUP)) return 0; - if (!bio->bi_blkg) + blkcg_css = bio_blkcg_css(bio); + if (!blkcg_css) return 0; - return cgroup_id(bio_blkcg(bio)->css.cgroup); + return cgroup_id(blkcg_css->cgroup); } #else static u64 blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio) diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 7fa2ebc07f60..d8553f46caa2 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -2349,11 +2349,11 @@ kprobe_multi_link_handler(struct fprobe *fp, unsigned long entry_ip, } static int -kprobe_multi_resolve_syms(const void *usyms, u32 cnt, +kprobe_multi_resolve_syms(const void __user *usyms, u32 cnt, unsigned long *addrs) { unsigned long addr, size; - const char **syms; + const char __user **syms; int err = -ENOMEM; unsigned int i; char *func; diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c index 8f4fb328133a..3fd5284f6487 100644 --- a/kernel/trace/fgraph.c +++ b/kernel/trace/fgraph.c @@ -30,6 +30,24 @@ int ftrace_graph_active; /* Both enabled by default (can be cleared by function_graph tracer flags */ static bool fgraph_sleep_time = true; +/* + * archs can override this function if they must do something + * to enable hook for graph tracer. + */ +int __weak ftrace_enable_ftrace_graph_caller(void) +{ + return 0; +} + +/* + * archs can override this function if they must do something + * to disable hook for graph tracer. + */ +int __weak ftrace_disable_ftrace_graph_caller(void) +{ + return 0; +} + /** * ftrace_graph_stop - set to permanently disable function graph tracing * @@ -404,9 +422,9 @@ free: static void ftrace_graph_probe_sched_switch(void *ignore, bool preempt, - unsigned int prev_state, struct task_struct *prev, - struct task_struct *next) + struct task_struct *next, + unsigned int prev_state) { unsigned long long timestamp; int index; diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 4f1d2f5e7263..af899b058c8d 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -7420,9 +7420,9 @@ ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops) static void ftrace_filter_pid_sched_switch_probe(void *data, bool preempt, - unsigned int prev_state, struct task_struct *prev, - struct task_struct *next) + struct task_struct *next, + unsigned int prev_state) { struct trace_array *tr = data; struct trace_pid_list *pid_list; diff --git a/kernel/trace/rethook.c b/kernel/trace/rethook.c index ab463a4d2b23..b56833700d23 100644 --- a/kernel/trace/rethook.c +++ b/kernel/trace/rethook.c @@ -65,7 +65,7 @@ static void rethook_free_rcu(struct rcu_head *head) */ void rethook_free(struct rethook *rh) { - rcu_assign_pointer(rh->handler, NULL); + WRITE_ONCE(rh->handler, NULL); call_rcu(&rh->rcu, rethook_free_rcu); } diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index f4de111fa18f..124f1897fd56 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -4289,17 +4289,11 @@ print_trace_header(struct seq_file *m, struct trace_iterator *iter) entries, total, buf->cpu, -#if defined(CONFIG_PREEMPT_NONE) - "server", -#elif defined(CONFIG_PREEMPT_VOLUNTARY) - "desktop", -#elif defined(CONFIG_PREEMPT) - "preempt", -#elif defined(CONFIG_PREEMPT_RT) - "preempt_rt", -#else + preempt_model_none() ? "server" : + preempt_model_voluntary() ? "desktop" : + preempt_model_full() ? "preempt" : + preempt_model_rt() ? "preempt_rt" : "unknown", -#endif /* These are reserved for later use */ 0, 0, 0, 0); #ifdef CONFIG_SMP diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index e11e167b7809..f97de82d1342 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -773,9 +773,9 @@ void trace_event_follow_fork(struct trace_array *tr, bool enable) static void event_filter_pid_sched_switch_probe_pre(void *data, bool preempt, - unsigned int prev_state, struct task_struct *prev, - struct task_struct *next) + struct task_struct *next, + unsigned int prev_state) { struct trace_array *tr = data; struct trace_pid_list *no_pid_list; @@ -799,9 +799,9 @@ event_filter_pid_sched_switch_probe_pre(void *data, bool preempt, static void event_filter_pid_sched_switch_probe_post(void *data, bool preempt, - unsigned int prev_state, struct task_struct *prev, - struct task_struct *next) + struct task_struct *next, + unsigned int prev_state) { struct trace_array *tr = data; struct trace_pid_list *no_pid_list; diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c index e9ae1f33a7f0..afb92e2f0aea 100644 --- a/kernel/trace/trace_osnoise.c +++ b/kernel/trace/trace_osnoise.c @@ -1168,9 +1168,9 @@ thread_exit(struct osnoise_variables *osn_var, struct task_struct *t) */ static void trace_sched_switch_callback(void *data, bool preempt, - unsigned int prev_state, struct task_struct *p, - struct task_struct *n) + struct task_struct *n, + unsigned int prev_state) { struct osnoise_variables *osn_var = this_cpu_osn_var(); diff --git a/kernel/trace/trace_preemptirq.c b/kernel/trace/trace_preemptirq.c index f4938040c228..95b58bd757ce 100644 --- a/kernel/trace/trace_preemptirq.c +++ b/kernel/trace/trace_preemptirq.c @@ -46,7 +46,7 @@ void trace_hardirqs_on(void) this_cpu_write(tracing_irq_cpu, 0); } - lockdep_hardirqs_on_prepare(CALLER_ADDR0); + lockdep_hardirqs_on_prepare(); lockdep_hardirqs_on(CALLER_ADDR0); } EXPORT_SYMBOL(trace_hardirqs_on); @@ -94,7 +94,7 @@ __visible void trace_hardirqs_on_caller(unsigned long caller_addr) this_cpu_write(tracing_irq_cpu, 0); } - lockdep_hardirqs_on_prepare(CALLER_ADDR0); + lockdep_hardirqs_on_prepare(); lockdep_hardirqs_on(CALLER_ADDR0); } EXPORT_SYMBOL(trace_hardirqs_on_caller); diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c index 45796d8bd4b2..c9ffdcfe622e 100644 --- a/kernel/trace/trace_sched_switch.c +++ b/kernel/trace/trace_sched_switch.c @@ -22,8 +22,8 @@ static DEFINE_MUTEX(sched_register_mutex); static void probe_sched_switch(void *ignore, bool preempt, - unsigned int prev_state, - struct task_struct *prev, struct task_struct *next) + struct task_struct *prev, struct task_struct *next, + unsigned int prev_state) { int flags; diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index 46429f9a96fa..330aee1c1a49 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -426,8 +426,8 @@ tracing_sched_wakeup_trace(struct trace_array *tr, static void notrace probe_wakeup_sched_switch(void *ignore, bool preempt, - unsigned int prev_state, - struct task_struct *prev, struct task_struct *next) + struct task_struct *prev, struct task_struct *next, + unsigned int prev_state) { struct trace_array_cpu *data; u64 T0, T1, delta; diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 9166220457bc..40024e03d422 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -424,6 +424,8 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) /* Start period for the next softlockup warning. */ update_report_ts(); + printk_prefer_direct_enter(); + pr_emerg("BUG: soft lockup - CPU#%d stuck for %us! [%s:%d]\n", smp_processor_id(), duration, current->comm, task_pid_nr(current)); @@ -442,6 +444,8 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) add_taint(TAINT_SOFTLOCKUP, LOCKDEP_STILL_OK); if (softlockup_panic) panic("softlockup: hung tasks"); + + printk_prefer_direct_exit(); } return HRTIMER_RESTART; diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c index 247bf0b1582c..701f35f0e2d4 100644 --- a/kernel/watchdog_hld.c +++ b/kernel/watchdog_hld.c @@ -135,6 +135,8 @@ static void watchdog_overflow_callback(struct perf_event *event, if (__this_cpu_read(hard_watchdog_warn) == true) return; + printk_prefer_direct_enter(); + pr_emerg("Watchdog detected hard LOCKUP on cpu %d\n", this_cpu); print_modules(); @@ -155,6 +157,8 @@ static void watchdog_overflow_callback(struct perf_event *event, if (hardlockup_panic) nmi_panic(regs, "Hard LOCKUP"); + printk_prefer_direct_exit(); + __this_cpu_write(hard_watchdog_warn, true); return; } diff --git a/lib/Kconfig b/lib/Kconfig index 087e06b4cdfd..6a843639814f 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -737,3 +737,6 @@ config PLDMFW config ASN1_ENCODER tristate + +config POLYNOMIAL + tristate diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 075cd25363ac..388fb808ff18 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -485,24 +485,25 @@ config FRAME_POINTER larger and slower, but it gives very useful debugging information in case of kernel bugs. (precise oopses/stacktraces/warnings) +config OBJTOOL + bool + config STACK_VALIDATION bool "Compile-time stack metadata validation" - depends on HAVE_STACK_VALIDATION + depends on HAVE_STACK_VALIDATION && UNWINDER_FRAME_POINTER + select OBJTOOL default n help - Add compile-time checks to validate stack metadata, including frame - pointers (if CONFIG_FRAME_POINTER is enabled). This helps ensure - that runtime stack traces are more reliable. - - This is also a prerequisite for generation of ORC unwind data, which - is needed for CONFIG_UNWINDER_ORC. + Validate frame pointer rules at compile-time. This helps ensure that + runtime stack traces are more reliable. For more information, see tools/objtool/Documentation/stack-validation.txt. -config VMLINUX_VALIDATION +config NOINSTR_VALIDATION bool - depends on STACK_VALIDATION && DEBUG_ENTRY + depends on HAVE_NOINSTR_VALIDATION && DEBUG_ENTRY + select OBJTOOL default y config VMLINUX_MAP @@ -709,6 +710,7 @@ config DEBUG_SLAB config SLUB_DEBUG_ON bool "SLUB debugging on by default" depends on SLUB && SLUB_DEBUG + select STACKDEPOT_ALWAYS_INIT if STACKTRACE_SUPPORT default n help Boot with debugging on by default. SLUB boots by default with @@ -1616,8 +1618,7 @@ config WARN_ALL_UNSEEDED_RANDOM so architecture maintainers really need to do what they can to get the CRNG seeded sooner after the system is booted. However, since users cannot do anything actionable to - address this, by default the kernel will issue only a single - warning for the first use of unseeded randomness. + address this, by default this option is disabled. Say Y here if you want to receive warnings for all uses of unseeded randomness. This will be of use primarily for @@ -2035,10 +2036,11 @@ config KCOV bool "Code coverage for fuzzing" depends on ARCH_HAS_KCOV depends on CC_HAS_SANCOV_TRACE_PC || GCC_PLUGINS - depends on !ARCH_WANTS_NO_INSTR || STACK_VALIDATION || \ + depends on !ARCH_WANTS_NO_INSTR || HAVE_NOINSTR_HACK || \ GCC_VERSION >= 120000 || CLANG_VERSION >= 130000 select DEBUG_FS select GCC_PLUGIN_SANCOV if !CC_HAS_SANCOV_TRACE_PC + select OBJTOOL if HAVE_NOINSTR_HACK help KCOV exposes kernel code coverage information in a form suitable for coverage-guided fuzzing (randomized testing). diff --git a/lib/Kconfig.kcsan b/lib/Kconfig.kcsan index de022445fbba..47a693c45864 100644 --- a/lib/Kconfig.kcsan +++ b/lib/Kconfig.kcsan @@ -187,7 +187,9 @@ config KCSAN_WEAK_MEMORY # We can either let objtool nop __tsan_func_{entry,exit}() and builtin # atomics instrumentation in .noinstr.text, or use a compiler that can # implement __no_kcsan to really remove all instrumentation. - depends on STACK_VALIDATION || CC_IS_GCC || CLANG_VERSION >= 140000 + depends on !ARCH_WANTS_NO_INSTR || HAVE_NOINSTR_HACK || \ + CC_IS_GCC || CLANG_VERSION >= 140000 + select OBJTOOL if HAVE_NOINSTR_HACK help Enable support for modeling a subset of weak memory, which allows detecting a subset of data races due to missing memory barriers. diff --git a/lib/Kconfig.ubsan b/lib/Kconfig.ubsan index f3c57ed51838..c4fe15d38b60 100644 --- a/lib/Kconfig.ubsan +++ b/lib/Kconfig.ubsan @@ -94,7 +94,7 @@ config UBSAN_UNREACHABLE bool "Perform checking for unreachable code" # objtool already handles unreachable checking and gets angry about # seeing UBSan instrumentation located in unreachable places. - depends on !STACK_VALIDATION + depends on !(OBJTOOL && (STACK_VALIDATION || UNWINDER_ORC || X86_SMAP)) depends on $(cc-option,-fsanitize=unreachable) help This option enables -fsanitize=unreachable which checks for control diff --git a/lib/Makefile b/lib/Makefile index 6b9ffc1bd1ee..89fcae891361 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -263,6 +263,8 @@ obj-$(CONFIG_MEMREGION) += memregion.o obj-$(CONFIG_STMP_DEVICE) += stmp_device.o obj-$(CONFIG_IRQ_POLL) += irq_poll.o +obj-$(CONFIG_POLYNOMIAL) += polynomial.o + # stackdepot.c should not be instrumented or call instrumented functions. # Prevent the compiler from calling builtins like memcmp() or bcmp() from this # file. diff --git a/lib/bug.c b/lib/bug.c index 45a0584f6541..c223a2575b72 100644 --- a/lib/bug.c +++ b/lib/bug.c @@ -6,8 +6,7 @@ CONFIG_BUG - emit BUG traps. Nothing happens without this. CONFIG_GENERIC_BUG - enable this code. - CONFIG_GENERIC_BUG_RELATIVE_POINTERS - use 32-bit pointers relative to - the containing struct bug_entry for bug_addr and file. + CONFIG_GENERIC_BUG_RELATIVE_POINTERS - use 32-bit relative pointers for bug_addr and file CONFIG_DEBUG_BUGVERBOSE - emit full file+line information for each BUG CONFIG_BUG and CONFIG_DEBUG_BUGVERBOSE are potentially user-settable @@ -53,10 +52,10 @@ extern struct bug_entry __start___bug_table[], __stop___bug_table[]; static inline unsigned long bug_addr(const struct bug_entry *bug) { -#ifndef CONFIG_GENERIC_BUG_RELATIVE_POINTERS - return bug->bug_addr; +#ifdef CONFIG_GENERIC_BUG_RELATIVE_POINTERS + return (unsigned long)&bug->bug_addr_disp + bug->bug_addr_disp; #else - return (unsigned long)bug + bug->bug_addr_disp; + return bug->bug_addr; #endif } @@ -131,10 +130,10 @@ void bug_get_file_line(struct bug_entry *bug, const char **file, unsigned int *line) { #ifdef CONFIG_DEBUG_BUGVERBOSE -#ifndef CONFIG_GENERIC_BUG_RELATIVE_POINTERS - *file = bug->file; +#ifdef CONFIG_GENERIC_BUG_RELATIVE_POINTERS + *file = (const char *)&bug->file_disp + bug->file_disp; #else - *file = (const char *)bug + bug->file_disp; + *file = bug->file; #endif *line = bug->line; #else diff --git a/lib/debugobjects.c b/lib/debugobjects.c index 6946f8e204e3..337d797a7141 100644 --- a/lib/debugobjects.c +++ b/lib/debugobjects.c @@ -1,11 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Generic infrastructure for lifetime debugging of objects. * - * Started by Thomas Gleixner - * * Copyright (C) 2008, Thomas Gleixner <tglx@linutronix.de> - * - * For licencing details see kernel-base/COPYING */ #define pr_fmt(fmt) "ODEBUG: " fmt diff --git a/lib/dim/net_dim.c b/lib/dim/net_dim.c index 06811d866775..53f6b9c6e936 100644 --- a/lib/dim/net_dim.c +++ b/lib/dim/net_dim.c @@ -12,41 +12,41 @@ * Each profile size must be of NET_DIM_PARAMS_NUM_PROFILES */ #define NET_DIM_PARAMS_NUM_PROFILES 5 -#define NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE 256 -#define NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE 128 +#define NET_DIM_DEFAULT_RX_CQ_PKTS_FROM_EQE 256 +#define NET_DIM_DEFAULT_TX_CQ_PKTS_FROM_EQE 128 #define NET_DIM_DEF_PROFILE_CQE 1 #define NET_DIM_DEF_PROFILE_EQE 1 #define NET_DIM_RX_EQE_PROFILES { \ - {1, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \ - {8, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \ - {64, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \ - {128, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \ - {256, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \ + {.usec = 1, .pkts = NET_DIM_DEFAULT_RX_CQ_PKTS_FROM_EQE,}, \ + {.usec = 8, .pkts = NET_DIM_DEFAULT_RX_CQ_PKTS_FROM_EQE,}, \ + {.usec = 64, .pkts = NET_DIM_DEFAULT_RX_CQ_PKTS_FROM_EQE,}, \ + {.usec = 128, .pkts = NET_DIM_DEFAULT_RX_CQ_PKTS_FROM_EQE,}, \ + {.usec = 256, .pkts = NET_DIM_DEFAULT_RX_CQ_PKTS_FROM_EQE,} \ } #define NET_DIM_RX_CQE_PROFILES { \ - {2, 256}, \ - {8, 128}, \ - {16, 64}, \ - {32, 64}, \ - {64, 64} \ + {.usec = 2, .pkts = 256,}, \ + {.usec = 8, .pkts = 128,}, \ + {.usec = 16, .pkts = 64,}, \ + {.usec = 32, .pkts = 64,}, \ + {.usec = 64, .pkts = 64,} \ } #define NET_DIM_TX_EQE_PROFILES { \ - {1, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE}, \ - {8, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE}, \ - {32, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE}, \ - {64, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE}, \ - {128, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE} \ + {.usec = 1, .pkts = NET_DIM_DEFAULT_TX_CQ_PKTS_FROM_EQE,}, \ + {.usec = 8, .pkts = NET_DIM_DEFAULT_TX_CQ_PKTS_FROM_EQE,}, \ + {.usec = 32, .pkts = NET_DIM_DEFAULT_TX_CQ_PKTS_FROM_EQE,}, \ + {.usec = 64, .pkts = NET_DIM_DEFAULT_TX_CQ_PKTS_FROM_EQE,}, \ + {.usec = 128, .pkts = NET_DIM_DEFAULT_TX_CQ_PKTS_FROM_EQE,} \ } #define NET_DIM_TX_CQE_PROFILES { \ - {5, 128}, \ - {8, 64}, \ - {16, 32}, \ - {32, 32}, \ - {64, 32} \ + {.usec = 5, .pkts = 128,}, \ + {.usec = 8, .pkts = 64,}, \ + {.usec = 16, .pkts = 32,}, \ + {.usec = 32, .pkts = 32,}, \ + {.usec = 64, .pkts = 32,} \ } static const struct dim_cq_moder diff --git a/lib/dump_stack.c b/lib/dump_stack.c index 6b7f1bf6715d..83471e81501a 100644 --- a/lib/dump_stack.c +++ b/lib/dump_stack.c @@ -102,9 +102,9 @@ asmlinkage __visible void dump_stack_lvl(const char *log_lvl) * Permit this cpu to perform nested stack dumps while serialising * against other CPUs */ - printk_cpu_lock_irqsave(flags); + printk_cpu_sync_get_irqsave(flags); __dump_stack(log_lvl); - printk_cpu_unlock_irqrestore(flags); + printk_cpu_sync_put_irqrestore(flags); } EXPORT_SYMBOL(dump_stack_lvl); diff --git a/lib/hexdump.c b/lib/hexdump.c index 9301578f98e8..06833d404398 100644 --- a/lib/hexdump.c +++ b/lib/hexdump.c @@ -22,15 +22,33 @@ EXPORT_SYMBOL(hex_asc_upper); * * hex_to_bin() converts one hex digit to its actual value or -1 in case of bad * input. + * + * This function is used to load cryptographic keys, so it is coded in such a + * way that there are no conditions or memory accesses that depend on data. + * + * Explanation of the logic: + * (ch - '9' - 1) is negative if ch <= '9' + * ('0' - 1 - ch) is negative if ch >= '0' + * we "and" these two values, so the result is negative if ch is in the range + * '0' ... '9' + * we are only interested in the sign, so we do a shift ">> 8"; note that right + * shift of a negative value is implementation-defined, so we cast the + * value to (unsigned) before the shift --- we have 0xffffff if ch is in + * the range '0' ... '9', 0 otherwise + * we "and" this value with (ch - '0' + 1) --- we have a value 1 ... 10 if ch is + * in the range '0' ... '9', 0 otherwise + * we add this value to -1 --- we have a value 0 ... 9 if ch is in the range '0' + * ... '9', -1 otherwise + * the next line is similar to the previous one, but we need to decode both + * uppercase and lowercase letters, so we use (ch & 0xdf), which converts + * lowercase to uppercase */ -int hex_to_bin(char ch) +int hex_to_bin(unsigned char ch) { - if ((ch >= '0') && (ch <= '9')) - return ch - '0'; - ch = tolower(ch); - if ((ch >= 'a') && (ch <= 'f')) - return ch - 'a' + 10; - return -1; + unsigned char cu = ch & 0xdf; + return -1 + + ((ch - '0' + 1) & (unsigned)((ch - '9' - 1) & ('0' - 1 - ch)) >> 8) + + ((cu - 'A' + 11) & (unsigned)((cu - 'F' - 1) & ('A' - 1 - cu)) >> 8); } EXPORT_SYMBOL(hex_to_bin); @@ -45,10 +63,13 @@ EXPORT_SYMBOL(hex_to_bin); int hex2bin(u8 *dst, const char *src, size_t count) { while (count--) { - int hi = hex_to_bin(*src++); - int lo = hex_to_bin(*src++); + int hi, lo; - if ((hi < 0) || (lo < 0)) + hi = hex_to_bin(*src++); + if (unlikely(hi < 0)) + return -EINVAL; + lo = hex_to_bin(*src++); + if (unlikely(lo < 0)) return -EINVAL; *dst++ = (hi << 4) | lo; diff --git a/lib/irq_poll.c b/lib/irq_poll.c index 2f17b488d58e..2d5329a42105 100644 --- a/lib/irq_poll.c +++ b/lib/irq_poll.c @@ -188,14 +188,18 @@ EXPORT_SYMBOL(irq_poll_init); static int irq_poll_cpu_dead(unsigned int cpu) { /* - * If a CPU goes away, splice its entries to the current CPU - * and trigger a run of the softirq + * If a CPU goes away, splice its entries to the current CPU and + * set the POLL softirq bit. The local_bh_disable()/enable() pair + * ensures that it is handled. Otherwise the current CPU could + * reach idle with the POLL softirq pending. */ + local_bh_disable(); local_irq_disable(); list_splice_init(&per_cpu(blk_cpu_iopoll, cpu), this_cpu_ptr(&blk_cpu_iopoll)); __raise_softirq_irqoff(IRQ_POLL_SOFTIRQ); local_irq_enable(); + local_bh_enable(); return 0; } diff --git a/lib/kobject.c b/lib/kobject.c index 56fa037501b5..5f0e71ab292c 100644 --- a/lib/kobject.c +++ b/lib/kobject.c @@ -54,32 +54,6 @@ void kobject_get_ownership(struct kobject *kobj, kuid_t *uid, kgid_t *gid) kobj->ktype->get_ownership(kobj, uid, gid); } -/* - * populate_dir - populate directory with attributes. - * @kobj: object we're working on. - * - * Most subsystems have a set of default attributes that are associated - * with an object that registers with them. This is a helper called during - * object registration that loops through the default attributes of the - * subsystem and creates attributes files for them in sysfs. - */ -static int populate_dir(struct kobject *kobj) -{ - const struct kobj_type *t = get_ktype(kobj); - struct attribute *attr; - int error = 0; - int i; - - if (t && t->default_attrs) { - for (i = 0; (attr = t->default_attrs[i]) != NULL; i++) { - error = sysfs_create_file(kobj, attr); - if (error) - break; - } - } - return error; -} - static int create_dir(struct kobject *kobj) { const struct kobj_type *ktype = get_ktype(kobj); @@ -90,12 +64,6 @@ static int create_dir(struct kobject *kobj) if (error) return error; - error = populate_dir(kobj); - if (error) { - sysfs_remove_dir(kobj); - return error; - } - if (ktype) { error = sysfs_create_groups(kobj, ktype->default_groups); if (error) { diff --git a/lib/lz4/lz4_decompress.c b/lib/lz4/lz4_decompress.c index 926f4823d5ea..fd1728d94bab 100644 --- a/lib/lz4/lz4_decompress.c +++ b/lib/lz4/lz4_decompress.c @@ -271,8 +271,12 @@ static FORCE_INLINE int LZ4_decompress_generic( ip += length; op += length; - /* Necessarily EOF, due to parsing restrictions */ - if (!partialDecoding || (cpy == oend)) + /* Necessarily EOF when !partialDecoding. + * When partialDecoding, it is EOF if we've either + * filled the output buffer or + * can't proceed with reading an offset for following match. + */ + if (!partialDecoding || (cpy == oend) || (ip >= (iend - 2))) break; } else { /* may overwrite up to WILDCOPYLENGTH beyond cpy */ diff --git a/lib/nmi_backtrace.c b/lib/nmi_backtrace.c index 199ab201d501..d01aec6ae15c 100644 --- a/lib/nmi_backtrace.c +++ b/lib/nmi_backtrace.c @@ -99,7 +99,7 @@ bool nmi_cpu_backtrace(struct pt_regs *regs) * Allow nested NMI backtraces while serializing * against other CPUs. */ - printk_cpu_lock_irqsave(flags); + printk_cpu_sync_get_irqsave(flags); if (!READ_ONCE(backtrace_idle) && regs && cpu_in_idle(instruction_pointer(regs))) { pr_warn("NMI backtrace for cpu %d skipped: idling at %pS\n", cpu, (void *)instruction_pointer(regs)); @@ -110,7 +110,7 @@ bool nmi_cpu_backtrace(struct pt_regs *regs) else dump_stack(); } - printk_cpu_unlock_irqrestore(flags); + printk_cpu_sync_put_irqrestore(flags); cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask)); return true; } diff --git a/lib/percpu-refcount.c b/lib/percpu-refcount.c index af9302141bcf..e5c5315da274 100644 --- a/lib/percpu-refcount.c +++ b/lib/percpu-refcount.c @@ -76,6 +76,7 @@ int percpu_ref_init(struct percpu_ref *ref, percpu_ref_func_t *release, data = kzalloc(sizeof(*ref->data), gfp); if (!data) { free_percpu((void __percpu *)ref->percpu_count_ptr); + ref->percpu_count_ptr = 0; return -ENOMEM; } diff --git a/lib/polynomial.c b/lib/polynomial.c new file mode 100644 index 000000000000..66d383445fec --- /dev/null +++ b/lib/polynomial.c @@ -0,0 +1,108 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Generic polynomial calculation using integer coefficients. + * + * Copyright (C) 2020 BAIKAL ELECTRONICS, JSC + * + * Authors: + * Maxim Kaurkin <maxim.kaurkin@baikalelectronics.ru> + * Serge Semin <Sergey.Semin@baikalelectronics.ru> + * + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/polynomial.h> + +/* + * Originally this was part of drivers/hwmon/bt1-pvt.c. + * There the following conversion is used and should serve as an example here: + * + * The original translation formulae of the temperature (in degrees of Celsius) + * to PVT data and vice-versa are following: + * + * N = 1.8322e-8*(T^4) + 2.343e-5*(T^3) + 8.7018e-3*(T^2) + 3.9269*(T^1) + + * 1.7204e2 + * T = -1.6743e-11*(N^4) + 8.1542e-8*(N^3) + -1.8201e-4*(N^2) + + * 3.1020e-1*(N^1) - 4.838e1 + * + * where T = [-48.380, 147.438]C and N = [0, 1023]. + * + * They must be accordingly altered to be suitable for the integer arithmetics. + * The technique is called 'factor redistribution', which just makes sure the + * multiplications and divisions are made so to have a result of the operations + * within the integer numbers limit. In addition we need to translate the + * formulae to accept millidegrees of Celsius. Here what they look like after + * the alterations: + * + * N = (18322e-20*(T^4) + 2343e-13*(T^3) + 87018e-9*(T^2) + 39269e-3*T + + * 17204e2) / 1e4 + * T = -16743e-12*(D^4) + 81542e-9*(D^3) - 182010e-6*(D^2) + 310200e-3*D - + * 48380 + * where T = [-48380, 147438] mC and N = [0, 1023]. + * + * static const struct polynomial poly_temp_to_N = { + * .total_divider = 10000, + * .terms = { + * {4, 18322, 10000, 10000}, + * {3, 2343, 10000, 10}, + * {2, 87018, 10000, 10}, + * {1, 39269, 1000, 1}, + * {0, 1720400, 1, 1} + * } + * }; + * + * static const struct polynomial poly_N_to_temp = { + * .total_divider = 1, + * .terms = { + * {4, -16743, 1000, 1}, + * {3, 81542, 1000, 1}, + * {2, -182010, 1000, 1}, + * {1, 310200, 1000, 1}, + * {0, -48380, 1, 1} + * } + * }; + */ + +/** + * polynomial_calc - calculate a polynomial using integer arithmetic + * + * @poly: pointer to the descriptor of the polynomial + * @data: input value of the polynimal + * + * Calculate the result of a polynomial using only integer arithmetic. For + * this to work without too much loss of precision the coefficients has to + * be altered. This is called factor redistribution. + * + * Returns the result of the polynomial calculation. + */ +long polynomial_calc(const struct polynomial *poly, long data) +{ + const struct polynomial_term *term = poly->terms; + long total_divider = poly->total_divider ?: 1; + long tmp, ret = 0; + int deg; + + /* + * Here is the polynomial calculation function, which performs the + * redistributed terms calculations. It's pretty straightforward. + * We walk over each degree term up to the free one, and perform + * the redistributed multiplication of the term coefficient, its + * divider (as for the rationale fraction representation), data + * power and the rational fraction divider leftover. Then all of + * this is collected in a total sum variable, which value is + * normalized by the total divider before being returned. + */ + do { + tmp = term->coef; + for (deg = 0; deg < term->deg; ++deg) + tmp = mult_frac(tmp, data, term->divider); + ret += tmp / term->divider_leftover; + } while ((term++)->deg); + + return ret / total_divider; +} +EXPORT_SYMBOL_GPL(polynomial_calc); + +MODULE_DESCRIPTION("Generic polynomial calculations"); +MODULE_LICENSE("GPL"); diff --git a/lib/random32.c b/lib/random32.c index 976632003ec6..d5d9029362cb 100644 --- a/lib/random32.c +++ b/lib/random32.c @@ -245,25 +245,13 @@ static struct prandom_test2 { { 407983964U, 921U, 728767059U }, }; -static u32 __extract_hwseed(void) -{ - unsigned int val = 0; - - (void)(arch_get_random_seed_int(&val) || - arch_get_random_int(&val)); - - return val; -} - -static void prandom_seed_early(struct rnd_state *state, u32 seed, - bool mix_with_hwseed) +static void prandom_state_selftest_seed(struct rnd_state *state, u32 seed) { #define LCG(x) ((x) * 69069U) /* super-duper LCG */ -#define HWSEED() (mix_with_hwseed ? __extract_hwseed() : 0) - state->s1 = __seed(HWSEED() ^ LCG(seed), 2U); - state->s2 = __seed(HWSEED() ^ LCG(state->s1), 8U); - state->s3 = __seed(HWSEED() ^ LCG(state->s2), 16U); - state->s4 = __seed(HWSEED() ^ LCG(state->s3), 128U); + state->s1 = __seed(LCG(seed), 2U); + state->s2 = __seed(LCG(state->s1), 8U); + state->s3 = __seed(LCG(state->s2), 16U); + state->s4 = __seed(LCG(state->s3), 128U); } static int __init prandom_state_selftest(void) @@ -274,7 +262,7 @@ static int __init prandom_state_selftest(void) for (i = 0; i < ARRAY_SIZE(test1); i++) { struct rnd_state state; - prandom_seed_early(&state, test1[i].seed, false); + prandom_state_selftest_seed(&state, test1[i].seed); prandom_warmup(&state); if (test1[i].result != prandom_u32_state(&state)) @@ -289,7 +277,7 @@ static int __init prandom_state_selftest(void) for (i = 0; i < ARRAY_SIZE(test2); i++) { struct rnd_state state; - prandom_seed_early(&state, test2[i].seed, false); + prandom_state_selftest_seed(&state, test2[i].seed); prandom_warmup(&state); for (j = 0; j < test2[i].iteration - 1; j++) @@ -310,324 +298,3 @@ static int __init prandom_state_selftest(void) } core_initcall(prandom_state_selftest); #endif - -/* - * The prandom_u32() implementation is now completely separate from the - * prandom_state() functions, which are retained (for now) for compatibility. - * - * Because of (ab)use in the networking code for choosing random TCP/UDP port - * numbers, which open DoS possibilities if guessable, we want something - * stronger than a standard PRNG. But the performance requirements of - * the network code do not allow robust crypto for this application. - * - * So this is a homebrew Junior Spaceman implementation, based on the - * lowest-latency trustworthy crypto primitive available, SipHash. - * (The authors of SipHash have not been consulted about this abuse of - * their work.) - * - * Standard SipHash-2-4 uses 2n+4 rounds to hash n words of input to - * one word of output. This abbreviated version uses 2 rounds per word - * of output. - */ - -struct siprand_state { - unsigned long v0; - unsigned long v1; - unsigned long v2; - unsigned long v3; -}; - -static DEFINE_PER_CPU(struct siprand_state, net_rand_state) __latent_entropy; -DEFINE_PER_CPU(unsigned long, net_rand_noise); -EXPORT_PER_CPU_SYMBOL(net_rand_noise); - -/* - * This is the core CPRNG function. As "pseudorandom", this is not used - * for truly valuable things, just intended to be a PITA to guess. - * For maximum speed, we do just two SipHash rounds per word. This is - * the same rate as 4 rounds per 64 bits that SipHash normally uses, - * so hopefully it's reasonably secure. - * - * There are two changes from the official SipHash finalization: - * - We omit some constants XORed with v2 in the SipHash spec as irrelevant; - * they are there only to make the output rounds distinct from the input - * rounds, and this application has no input rounds. - * - Rather than returning v0^v1^v2^v3, return v1+v3. - * If you look at the SipHash round, the last operation on v3 is - * "v3 ^= v0", so "v0 ^ v3" just undoes that, a waste of time. - * Likewise "v1 ^= v2". (The rotate of v2 makes a difference, but - * it still cancels out half of the bits in v2 for no benefit.) - * Second, since the last combining operation was xor, continue the - * pattern of alternating xor/add for a tiny bit of extra non-linearity. - */ -static inline u32 siprand_u32(struct siprand_state *s) -{ - unsigned long v0 = s->v0, v1 = s->v1, v2 = s->v2, v3 = s->v3; - unsigned long n = raw_cpu_read(net_rand_noise); - - v3 ^= n; - PRND_SIPROUND(v0, v1, v2, v3); - PRND_SIPROUND(v0, v1, v2, v3); - v0 ^= n; - s->v0 = v0; s->v1 = v1; s->v2 = v2; s->v3 = v3; - return v1 + v3; -} - - -/** - * prandom_u32 - pseudo random number generator - * - * A 32 bit pseudo-random number is generated using a fast - * algorithm suitable for simulation. This algorithm is NOT - * considered safe for cryptographic use. - */ -u32 prandom_u32(void) -{ - struct siprand_state *state = get_cpu_ptr(&net_rand_state); - u32 res = siprand_u32(state); - - put_cpu_ptr(&net_rand_state); - return res; -} -EXPORT_SYMBOL(prandom_u32); - -/** - * prandom_bytes - get the requested number of pseudo-random bytes - * @buf: where to copy the pseudo-random bytes to - * @bytes: the requested number of bytes - */ -void prandom_bytes(void *buf, size_t bytes) -{ - struct siprand_state *state = get_cpu_ptr(&net_rand_state); - u8 *ptr = buf; - - while (bytes >= sizeof(u32)) { - put_unaligned(siprand_u32(state), (u32 *)ptr); - ptr += sizeof(u32); - bytes -= sizeof(u32); - } - - if (bytes > 0) { - u32 rem = siprand_u32(state); - - do { - *ptr++ = (u8)rem; - rem >>= BITS_PER_BYTE; - } while (--bytes > 0); - } - put_cpu_ptr(&net_rand_state); -} -EXPORT_SYMBOL(prandom_bytes); - -/** - * prandom_seed - add entropy to pseudo random number generator - * @entropy: entropy value - * - * Add some additional seed material to the prandom pool. - * The "entropy" is actually our IP address (the only caller is - * the network code), not for unpredictability, but to ensure that - * different machines are initialized differently. - */ -void prandom_seed(u32 entropy) -{ - int i; - - add_device_randomness(&entropy, sizeof(entropy)); - - for_each_possible_cpu(i) { - struct siprand_state *state = per_cpu_ptr(&net_rand_state, i); - unsigned long v0 = state->v0, v1 = state->v1; - unsigned long v2 = state->v2, v3 = state->v3; - - do { - v3 ^= entropy; - PRND_SIPROUND(v0, v1, v2, v3); - PRND_SIPROUND(v0, v1, v2, v3); - v0 ^= entropy; - } while (unlikely(!v0 || !v1 || !v2 || !v3)); - - WRITE_ONCE(state->v0, v0); - WRITE_ONCE(state->v1, v1); - WRITE_ONCE(state->v2, v2); - WRITE_ONCE(state->v3, v3); - } -} -EXPORT_SYMBOL(prandom_seed); - -/* - * Generate some initially weak seeding values to allow - * the prandom_u32() engine to be started. - */ -static int __init prandom_init_early(void) -{ - int i; - unsigned long v0, v1, v2, v3; - - if (!arch_get_random_long(&v0)) - v0 = jiffies; - if (!arch_get_random_long(&v1)) - v1 = random_get_entropy(); - v2 = v0 ^ PRND_K0; - v3 = v1 ^ PRND_K1; - - for_each_possible_cpu(i) { - struct siprand_state *state; - - v3 ^= i; - PRND_SIPROUND(v0, v1, v2, v3); - PRND_SIPROUND(v0, v1, v2, v3); - v0 ^= i; - - state = per_cpu_ptr(&net_rand_state, i); - state->v0 = v0; state->v1 = v1; - state->v2 = v2; state->v3 = v3; - } - - return 0; -} -core_initcall(prandom_init_early); - - -/* Stronger reseeding when available, and periodically thereafter. */ -static void prandom_reseed(struct timer_list *unused); - -static DEFINE_TIMER(seed_timer, prandom_reseed); - -static void prandom_reseed(struct timer_list *unused) -{ - unsigned long expires; - int i; - - /* - * Reinitialize each CPU's PRNG with 128 bits of key. - * No locking on the CPUs, but then somewhat random results are, - * well, expected. - */ - for_each_possible_cpu(i) { - struct siprand_state *state; - unsigned long v0 = get_random_long(), v2 = v0 ^ PRND_K0; - unsigned long v1 = get_random_long(), v3 = v1 ^ PRND_K1; -#if BITS_PER_LONG == 32 - int j; - - /* - * On 32-bit machines, hash in two extra words to - * approximate 128-bit key length. Not that the hash - * has that much security, but this prevents a trivial - * 64-bit brute force. - */ - for (j = 0; j < 2; j++) { - unsigned long m = get_random_long(); - - v3 ^= m; - PRND_SIPROUND(v0, v1, v2, v3); - PRND_SIPROUND(v0, v1, v2, v3); - v0 ^= m; - } -#endif - /* - * Probably impossible in practice, but there is a - * theoretical risk that a race between this reseeding - * and the target CPU writing its state back could - * create the all-zero SipHash fixed point. - * - * To ensure that never happens, ensure the state - * we write contains no zero words. - */ - state = per_cpu_ptr(&net_rand_state, i); - WRITE_ONCE(state->v0, v0 ? v0 : -1ul); - WRITE_ONCE(state->v1, v1 ? v1 : -1ul); - WRITE_ONCE(state->v2, v2 ? v2 : -1ul); - WRITE_ONCE(state->v3, v3 ? v3 : -1ul); - } - - /* reseed every ~60 seconds, in [40 .. 80) interval with slack */ - expires = round_jiffies(jiffies + 40 * HZ + prandom_u32_max(40 * HZ)); - mod_timer(&seed_timer, expires); -} - -/* - * The random ready callback can be called from almost any interrupt. - * To avoid worrying about whether it's safe to delay that interrupt - * long enough to seed all CPUs, just schedule an immediate timer event. - */ -static int prandom_timer_start(struct notifier_block *nb, - unsigned long action, void *data) -{ - mod_timer(&seed_timer, jiffies); - return 0; -} - -#ifdef CONFIG_RANDOM32_SELFTEST -/* Principle: True 32-bit random numbers will all have 16 differing bits on - * average. For each 32-bit number, there are 601M numbers differing by 16 - * bits, and 89% of the numbers differ by at least 12 bits. Note that more - * than 16 differing bits also implies a correlation with inverted bits. Thus - * we take 1024 random numbers and compare each of them to the other ones, - * counting the deviation of correlated bits to 16. Constants report 32, - * counters 32-log2(TEST_SIZE), and pure randoms, around 6 or lower. With the - * u32 total, TEST_SIZE may be as large as 4096 samples. - */ -#define TEST_SIZE 1024 -static int __init prandom32_state_selftest(void) -{ - unsigned int x, y, bits, samples; - u32 xor, flip; - u32 total; - u32 *data; - - data = kmalloc(sizeof(*data) * TEST_SIZE, GFP_KERNEL); - if (!data) - return 0; - - for (samples = 0; samples < TEST_SIZE; samples++) - data[samples] = prandom_u32(); - - flip = total = 0; - for (x = 0; x < samples; x++) { - for (y = 0; y < samples; y++) { - if (x == y) - continue; - xor = data[x] ^ data[y]; - flip |= xor; - bits = hweight32(xor); - total += (bits - 16) * (bits - 16); - } - } - - /* We'll return the average deviation as 2*sqrt(corr/samples), which - * is also sqrt(4*corr/samples) which provides a better resolution. - */ - bits = int_sqrt(total / (samples * (samples - 1)) * 4); - if (bits > 6) - pr_warn("prandom32: self test failed (at least %u bits" - " correlated, fixed_mask=%#x fixed_value=%#x\n", - bits, ~flip, data[0] & ~flip); - else - pr_info("prandom32: self test passed (less than %u bits" - " correlated)\n", - bits+1); - kfree(data); - return 0; -} -core_initcall(prandom32_state_selftest); -#endif /* CONFIG_RANDOM32_SELFTEST */ - -/* - * Start periodic full reseeding as soon as strong - * random numbers are available. - */ -static int __init prandom_init_late(void) -{ - static struct notifier_block random_ready = { - .notifier_call = prandom_timer_start - }; - int ret = register_random_ready_notifier(&random_ready); - - if (ret == -EALREADY) { - prandom_timer_start(&random_ready, 0, NULL); - ret = 0; - } - return ret; -} -late_initcall(prandom_init_late); diff --git a/lib/siphash.c b/lib/siphash.c index 72b9068ab57b..71d315a6ad62 100644 --- a/lib/siphash.c +++ b/lib/siphash.c @@ -18,19 +18,13 @@ #include <asm/word-at-a-time.h> #endif -#define SIPROUND \ - do { \ - v0 += v1; v1 = rol64(v1, 13); v1 ^= v0; v0 = rol64(v0, 32); \ - v2 += v3; v3 = rol64(v3, 16); v3 ^= v2; \ - v0 += v3; v3 = rol64(v3, 21); v3 ^= v0; \ - v2 += v1; v1 = rol64(v1, 17); v1 ^= v2; v2 = rol64(v2, 32); \ - } while (0) +#define SIPROUND SIPHASH_PERMUTATION(v0, v1, v2, v3) #define PREAMBLE(len) \ - u64 v0 = 0x736f6d6570736575ULL; \ - u64 v1 = 0x646f72616e646f6dULL; \ - u64 v2 = 0x6c7967656e657261ULL; \ - u64 v3 = 0x7465646279746573ULL; \ + u64 v0 = SIPHASH_CONST_0; \ + u64 v1 = SIPHASH_CONST_1; \ + u64 v2 = SIPHASH_CONST_2; \ + u64 v3 = SIPHASH_CONST_3; \ u64 b = ((u64)(len)) << 56; \ v3 ^= key->key[1]; \ v2 ^= key->key[0]; \ @@ -389,19 +383,13 @@ u32 hsiphash_4u32(const u32 first, const u32 second, const u32 third, } EXPORT_SYMBOL(hsiphash_4u32); #else -#define HSIPROUND \ - do { \ - v0 += v1; v1 = rol32(v1, 5); v1 ^= v0; v0 = rol32(v0, 16); \ - v2 += v3; v3 = rol32(v3, 8); v3 ^= v2; \ - v0 += v3; v3 = rol32(v3, 7); v3 ^= v0; \ - v2 += v1; v1 = rol32(v1, 13); v1 ^= v2; v2 = rol32(v2, 16); \ - } while (0) +#define HSIPROUND HSIPHASH_PERMUTATION(v0, v1, v2, v3) #define HPREAMBLE(len) \ - u32 v0 = 0; \ - u32 v1 = 0; \ - u32 v2 = 0x6c796765U; \ - u32 v3 = 0x74656462U; \ + u32 v0 = HSIPHASH_CONST_0; \ + u32 v1 = HSIPHASH_CONST_1; \ + u32 v2 = HSIPHASH_CONST_2; \ + u32 v3 = HSIPHASH_CONST_3; \ u32 b = ((u32)(len)) << 24; \ v3 ^= key->key[1]; \ v2 ^= key->key[0]; \ diff --git a/lib/slub_kunit.c b/lib/slub_kunit.c index 8662dc6cb509..7a0564d7cb7a 100644 --- a/lib/slub_kunit.c +++ b/lib/slub_kunit.c @@ -12,7 +12,7 @@ static int slab_errors; static void test_clobber_zone(struct kunit *test) { struct kmem_cache *s = kmem_cache_create("TestSlub_RZ_alloc", 64, 0, - SLAB_RED_ZONE, NULL); + SLAB_RED_ZONE|SLAB_NO_USER_FLAGS, NULL); u8 *p = kmem_cache_alloc(s, GFP_KERNEL); kasan_disable_current(); @@ -30,7 +30,7 @@ static void test_clobber_zone(struct kunit *test) static void test_next_pointer(struct kunit *test) { struct kmem_cache *s = kmem_cache_create("TestSlub_next_ptr_free", 64, 0, - SLAB_POISON, NULL); + SLAB_POISON|SLAB_NO_USER_FLAGS, NULL); u8 *p = kmem_cache_alloc(s, GFP_KERNEL); unsigned long tmp; unsigned long *ptr_addr; @@ -75,7 +75,7 @@ static void test_next_pointer(struct kunit *test) static void test_first_word(struct kunit *test) { struct kmem_cache *s = kmem_cache_create("TestSlub_1th_word_free", 64, 0, - SLAB_POISON, NULL); + SLAB_POISON|SLAB_NO_USER_FLAGS, NULL); u8 *p = kmem_cache_alloc(s, GFP_KERNEL); kmem_cache_free(s, p); @@ -90,7 +90,7 @@ static void test_first_word(struct kunit *test) static void test_clobber_50th_byte(struct kunit *test) { struct kmem_cache *s = kmem_cache_create("TestSlub_50th_word_free", 64, 0, - SLAB_POISON, NULL); + SLAB_POISON|SLAB_NO_USER_FLAGS, NULL); u8 *p = kmem_cache_alloc(s, GFP_KERNEL); kmem_cache_free(s, p); @@ -106,7 +106,7 @@ static void test_clobber_50th_byte(struct kunit *test) static void test_clobber_redzone_free(struct kunit *test) { struct kmem_cache *s = kmem_cache_create("TestSlub_RZ_free", 64, 0, - SLAB_RED_ZONE, NULL); + SLAB_RED_ZONE|SLAB_NO_USER_FLAGS, NULL); u8 *p = kmem_cache_alloc(s, GFP_KERNEL); kasan_disable_current(); diff --git a/lib/stackdepot.c b/lib/stackdepot.c index bf5ba9af0500..5ca0d086ef4a 100644 --- a/lib/stackdepot.c +++ b/lib/stackdepot.c @@ -66,6 +66,9 @@ struct stack_record { unsigned long entries[]; /* Variable-sized array of entries. */ }; +static bool __stack_depot_want_early_init __initdata = IS_ENABLED(CONFIG_STACKDEPOT_ALWAYS_INIT); +static bool __stack_depot_early_init_passed __initdata; + static void *stack_slabs[STACK_ALLOC_MAX_SLABS]; static int depot_index; @@ -162,38 +165,58 @@ static int __init is_stack_depot_disabled(char *str) } early_param("stack_depot_disable", is_stack_depot_disabled); -/* - * __ref because of memblock_alloc(), which will not be actually called after - * the __init code is gone, because at that point slab_is_available() is true - */ -__ref int stack_depot_init(void) +void __init stack_depot_want_early_init(void) +{ + /* Too late to request early init now */ + WARN_ON(__stack_depot_early_init_passed); + + __stack_depot_want_early_init = true; +} + +int __init stack_depot_early_init(void) +{ + size_t size; + + /* This is supposed to be called only once, from mm_init() */ + if (WARN_ON(__stack_depot_early_init_passed)) + return 0; + + __stack_depot_early_init_passed = true; + + if (!__stack_depot_want_early_init || stack_depot_disable) + return 0; + + size = (STACK_HASH_SIZE * sizeof(struct stack_record *)); + pr_info("Stack Depot early init allocating hash table with memblock_alloc, %zu bytes\n", + size); + stack_table = memblock_alloc(size, SMP_CACHE_BYTES); + + if (!stack_table) { + pr_err("Stack Depot hash table allocation failed, disabling\n"); + stack_depot_disable = true; + return -ENOMEM; + } + + return 0; +} + +int stack_depot_init(void) { static DEFINE_MUTEX(stack_depot_init_mutex); + int ret = 0; mutex_lock(&stack_depot_init_mutex); if (!stack_depot_disable && !stack_table) { - size_t size = (STACK_HASH_SIZE * sizeof(struct stack_record *)); - int i; - - if (slab_is_available()) { - pr_info("Stack Depot allocating hash table with kvmalloc\n"); - stack_table = kvmalloc(size, GFP_KERNEL); - } else { - pr_info("Stack Depot allocating hash table with memblock_alloc\n"); - stack_table = memblock_alloc(size, SMP_CACHE_BYTES); - } - if (stack_table) { - for (i = 0; i < STACK_HASH_SIZE; i++) - stack_table[i] = NULL; - } else { + pr_info("Stack Depot allocating hash table with kvcalloc\n"); + stack_table = kvcalloc(STACK_HASH_SIZE, sizeof(struct stack_record *), GFP_KERNEL); + if (!stack_table) { pr_err("Stack Depot hash table allocation failed, disabling\n"); stack_depot_disable = true; - mutex_unlock(&stack_depot_init_mutex); - return -ENOMEM; + ret = -ENOMEM; } } mutex_unlock(&stack_depot_init_mutex); - return 0; + return ret; } EXPORT_SYMBOL_GPL(stack_depot_init); diff --git a/lib/strncpy_from_user.c b/lib/strncpy_from_user.c index 08fc72d3ed16..6432b8c3e431 100644 --- a/lib/strncpy_from_user.c +++ b/lib/strncpy_from_user.c @@ -25,7 +25,7 @@ * hit it), 'max' is the address space maximum (and we return * -EFAULT if we hit it). */ -static inline long do_strncpy_from_user(char *dst, const char __user *src, +static __always_inline long do_strncpy_from_user(char *dst, const char __user *src, unsigned long count, unsigned long max) { const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS; diff --git a/lib/strnlen_user.c b/lib/strnlen_user.c index bffa0ebf9f8b..feeb935a2299 100644 --- a/lib/strnlen_user.c +++ b/lib/strnlen_user.c @@ -20,7 +20,7 @@ * if it fits in a aligned 'long'. The caller needs to check * the return value against "> max". */ -static inline long do_strnlen_user(const char __user *src, unsigned long count, unsigned long max) +static __always_inline long do_strnlen_user(const char __user *src, unsigned long count, unsigned long max) { const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS; unsigned long align, res = 0; diff --git a/lib/vsprintf.c b/lib/vsprintf.c index 40d26a07a133..fb77f7bfd126 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -750,61 +750,38 @@ static int __init debug_boot_weak_hash_enable(char *str) } early_param("debug_boot_weak_hash", debug_boot_weak_hash_enable); -static DEFINE_STATIC_KEY_TRUE(not_filled_random_ptr_key); -static siphash_key_t ptr_key __read_mostly; +static DEFINE_STATIC_KEY_FALSE(filled_random_ptr_key); static void enable_ptr_key_workfn(struct work_struct *work) { - get_random_bytes(&ptr_key, sizeof(ptr_key)); - /* Needs to run from preemptible context */ - static_branch_disable(¬_filled_random_ptr_key); + static_branch_enable(&filled_random_ptr_key); } -static DECLARE_WORK(enable_ptr_key_work, enable_ptr_key_workfn); - -static int fill_random_ptr_key(struct notifier_block *nb, - unsigned long action, void *data) -{ - /* This may be in an interrupt handler. */ - queue_work(system_unbound_wq, &enable_ptr_key_work); - return 0; -} - -static struct notifier_block random_ready = { - .notifier_call = fill_random_ptr_key -}; - -static int __init initialize_ptr_random(void) -{ - int key_size = sizeof(ptr_key); - int ret; - - /* Use hw RNG if available. */ - if (get_random_bytes_arch(&ptr_key, key_size) == key_size) { - static_branch_disable(¬_filled_random_ptr_key); - return 0; - } - - ret = register_random_ready_notifier(&random_ready); - if (!ret) { - return 0; - } else if (ret == -EALREADY) { - /* This is in preemptible context */ - enable_ptr_key_workfn(&enable_ptr_key_work); - return 0; - } - - return ret; -} -early_initcall(initialize_ptr_random); - /* Maps a pointer to a 32 bit unique identifier. */ static inline int __ptr_to_hashval(const void *ptr, unsigned long *hashval_out) { + static siphash_key_t ptr_key __read_mostly; unsigned long hashval; - if (static_branch_unlikely(¬_filled_random_ptr_key)) - return -EAGAIN; + if (!static_branch_likely(&filled_random_ptr_key)) { + static bool filled = false; + static DEFINE_SPINLOCK(filling); + static DECLARE_WORK(enable_ptr_key_work, enable_ptr_key_workfn); + unsigned long flags; + + if (!system_unbound_wq || + (!rng_is_initialized() && !rng_has_arch_random()) || + !spin_trylock_irqsave(&filling, flags)) + return -EAGAIN; + + if (!filled) { + get_random_bytes(&ptr_key, sizeof(ptr_key)); + queue_work(system_unbound_wq, &enable_ptr_key_work); + filled = true; + } + spin_unlock_irqrestore(&filling, flags); + } + #ifdef CONFIG_64BIT hashval = (unsigned long)siphash_1u64((u64)ptr, &ptr_key); diff --git a/lib/xarray.c b/lib/xarray.c index 4acc88ea7c21..54e646e8e6ee 100644 --- a/lib/xarray.c +++ b/lib/xarray.c @@ -207,6 +207,8 @@ static void *xas_descend(struct xa_state *xas, struct xa_node *node) if (xa_is_sibling(entry)) { offset = xa_to_sibling(entry); entry = xa_entry(xas->xa, node, offset); + if (node->shift && xa_is_node(entry)) + entry = XA_RETRY_ENTRY; } xas->xa_offset = offset; diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 7176af65b103..ff60bd7d74e0 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only +#include <linux/blkdev.h> #include <linux/wait.h> #include <linux/rbtree.h> #include <linux/kthread.h> @@ -390,7 +391,6 @@ static void cgwb_release_workfn(struct work_struct *work) { struct bdi_writeback *wb = container_of(work, struct bdi_writeback, release_work); - struct blkcg *blkcg = css_to_blkcg(wb->blkcg_css); struct backing_dev_info *bdi = wb->bdi; mutex_lock(&wb->bdi->cgwb_release_mutex); @@ -401,7 +401,7 @@ static void cgwb_release_workfn(struct work_struct *work) mutex_unlock(&wb->bdi->cgwb_release_mutex); /* triggers blkg destruction if no online users left */ - blkcg_unpin_online(blkcg); + blkcg_unpin_online(wb->blkcg_css); fprop_local_destroy_percpu(&wb->memcg_completions); @@ -446,7 +446,6 @@ static int cgwb_create(struct backing_dev_info *bdi, { struct mem_cgroup *memcg; struct cgroup_subsys_state *blkcg_css; - struct blkcg *blkcg; struct list_head *memcg_cgwb_list, *blkcg_cgwb_list; struct bdi_writeback *wb; unsigned long flags; @@ -454,9 +453,8 @@ static int cgwb_create(struct backing_dev_info *bdi, memcg = mem_cgroup_from_css(memcg_css); blkcg_css = cgroup_get_e_css(memcg_css->cgroup, &io_cgrp_subsys); - blkcg = css_to_blkcg(blkcg_css); memcg_cgwb_list = &memcg->cgwb_list; - blkcg_cgwb_list = &blkcg->cgwb_list; + blkcg_cgwb_list = blkcg_get_cgwb_list(blkcg_css); /* look up again under lock and discard on blkcg mismatch */ spin_lock_irqsave(&cgwb_lock, flags); @@ -511,7 +509,7 @@ static int cgwb_create(struct backing_dev_info *bdi, list_add_tail_rcu(&wb->bdi_node, &bdi->wb_list); list_add(&wb->memcg_node, memcg_cgwb_list); list_add(&wb->blkcg_node, blkcg_cgwb_list); - blkcg_pin_online(blkcg); + blkcg_pin_online(blkcg_css); css_get(memcg_css); css_get(blkcg_css); } @@ -724,18 +722,19 @@ void wb_memcg_offline(struct mem_cgroup *memcg) /** * wb_blkcg_offline - kill all wb's associated with a blkcg being offlined - * @blkcg: blkcg being offlined + * @css: blkcg being offlined * * Also prevents creation of any new wb's associated with @blkcg. */ -void wb_blkcg_offline(struct blkcg *blkcg) +void wb_blkcg_offline(struct cgroup_subsys_state *css) { struct bdi_writeback *wb, *next; + struct list_head *list = blkcg_get_cgwb_list(css); spin_lock_irq(&cgwb_lock); - list_for_each_entry_safe(wb, next, &blkcg->cgwb_list, blkcg_node) + list_for_each_entry_safe(wb, next, list, blkcg_node) cgwb_kill(wb); - blkcg->cgwb_list.next = NULL; /* prevent new wb's */ + list->next = NULL; /* prevent new wb's */ spin_unlock_irq(&cgwb_lock); } diff --git a/mm/compaction.c b/mm/compaction.c index c3e37aa9ff9e..fe915db6149b 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -26,6 +26,11 @@ #include "internal.h" #ifdef CONFIG_COMPACTION +/* + * Fragmentation score check interval for proactive compaction purposes. + */ +#define HPAGE_FRAG_CHECK_INTERVAL_MSEC (500) + static inline void count_compact_event(enum vm_event_item item) { count_vm_event(item); @@ -51,11 +56,6 @@ static inline void count_compact_events(enum vm_event_item item, long delta) #define pageblock_end_pfn(pfn) block_end_pfn(pfn, pageblock_order) /* - * Fragmentation score check interval for proactive compaction purposes. - */ -static const unsigned int HPAGE_FRAG_CHECK_INTERVAL_MSEC = 500; - -/* * Page order with-respect-to which proactive compaction * calculates external fragmentation, which is used as * the "fragmentation score" of a node/zone. diff --git a/mm/filemap.c b/mm/filemap.c index 3a5ffb5587cd..fa0ca674450f 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -225,12 +225,12 @@ void __filemap_remove_folio(struct folio *folio, void *shadow) void filemap_free_folio(struct address_space *mapping, struct folio *folio) { - void (*freepage)(struct page *); + void (*free_folio)(struct folio *); int refs = 1; - freepage = mapping->a_ops->freepage; - if (freepage) - freepage(&folio->page); + free_folio = mapping->a_ops->free_folio; + if (free_folio) + free_folio(folio); if (folio_test_large(folio) && !folio_test_hugetlb(folio)) refs = folio_nr_pages(folio); @@ -807,7 +807,7 @@ void replace_page_cache_page(struct page *old, struct page *new) struct folio *fold = page_folio(old); struct folio *fnew = page_folio(new); struct address_space *mapping = old->mapping; - void (*freepage)(struct page *) = mapping->a_ops->freepage; + void (*free_folio)(struct folio *) = mapping->a_ops->free_folio; pgoff_t offset = old->index; XA_STATE(xas, &mapping->i_pages, offset); @@ -835,9 +835,9 @@ void replace_page_cache_page(struct page *old, struct page *new) if (PageSwapBacked(new)) __inc_lruvec_page_state(new, NR_SHMEM); xas_unlock_irq(&xas); - if (freepage) - freepage(old); - put_page(old); + if (free_folio) + free_folio(fold); + folio_put(fold); } EXPORT_SYMBOL_GPL(replace_page_cache_page); @@ -1063,12 +1063,6 @@ void __init pagecache_init(void) init_waitqueue_head(&folio_wait_table[i]); page_writeback_init(); - - /* - * tmpfs uses the ZERO_PAGE for reading holes: it is up-to-date, - * and splice's page_cache_pipe_buf_confirm() needs to see that. - */ - SetPageUptodate(ZERO_PAGE(0)); } /* @@ -2420,12 +2414,12 @@ static int filemap_read_folio(struct file *file, struct address_space *mapping, /* * A previous I/O error may have been due to temporary failures, - * eg. multipath errors. PG_error will be set again if readpage + * eg. multipath errors. PG_error will be set again if read_folio * fails. */ folio_clear_error(folio); /* Start the actual read. The read will unlock the page. */ - error = mapping->a_ops->readpage(file, &folio->page); + error = mapping->a_ops->read_folio(file, folio); if (error) return error; @@ -2642,7 +2636,7 @@ err: * @already_read: Number of bytes already read by the caller. * * Copies data from the page cache. If the data is not currently present, - * uses the readahead and readpage address_space operations to fetch it. + * uses the readahead and read_folio address_space operations to fetch it. * * Return: Total number of bytes copied, including those already read by * the caller. If an error happens before any bytes are copied, returns @@ -3453,7 +3447,7 @@ int generic_file_mmap(struct file *file, struct vm_area_struct *vma) { struct address_space *mapping = file->f_mapping; - if (!mapping->a_ops->readpage) + if (!mapping->a_ops->read_folio) return -ENOEXEC; file_accessed(file); vma->vm_ops = &generic_file_vm_ops; @@ -3489,10 +3483,13 @@ EXPORT_SYMBOL(generic_file_mmap); EXPORT_SYMBOL(generic_file_readonly_mmap); static struct folio *do_read_cache_folio(struct address_space *mapping, - pgoff_t index, filler_t filler, void *data, gfp_t gfp) + pgoff_t index, filler_t filler, struct file *file, gfp_t gfp) { struct folio *folio; int err; + + if (!filler) + filler = mapping->a_ops->read_folio; repeat: folio = filemap_get_folio(mapping, index); if (!folio) { @@ -3509,11 +3506,7 @@ repeat: } filler: - if (filler) - err = filler(data, &folio->page); - else - err = mapping->a_ops->readpage(data, &folio->page); - + err = filler(file, folio); if (err < 0) { folio_put(folio); return ERR_PTR(err); @@ -3563,44 +3556,44 @@ out: } /** - * read_cache_folio - read into page cache, fill it if needed - * @mapping: the page's address_space - * @index: the page index - * @filler: function to perform the read - * @data: first arg to filler(data, page) function, often left as NULL + * read_cache_folio - Read into page cache, fill it if needed. + * @mapping: The address_space to read from. + * @index: The index to read. + * @filler: Function to perform the read, or NULL to use aops->read_folio(). + * @file: Passed to filler function, may be NULL if not required. * - * Read into the page cache. If a page already exists, and PageUptodate() is - * not set, try to fill the page and wait for it to become unlocked. - * - * If the page does not get brought uptodate, return -EIO. + * Read one page into the page cache. If it succeeds, the folio returned + * will contain @index, but it may not be the first page of the folio. * - * The function expects mapping->invalidate_lock to be already held. + * If the filler function returns an error, it will be returned to the + * caller. * - * Return: up to date page on success, ERR_PTR() on failure. + * Context: May sleep. Expects mapping->invalidate_lock to be held. + * Return: An uptodate folio on success, ERR_PTR() on failure. */ struct folio *read_cache_folio(struct address_space *mapping, pgoff_t index, - filler_t filler, void *data) + filler_t filler, struct file *file) { - return do_read_cache_folio(mapping, index, filler, data, + return do_read_cache_folio(mapping, index, filler, file, mapping_gfp_mask(mapping)); } EXPORT_SYMBOL(read_cache_folio); static struct page *do_read_cache_page(struct address_space *mapping, - pgoff_t index, filler_t *filler, void *data, gfp_t gfp) + pgoff_t index, filler_t *filler, struct file *file, gfp_t gfp) { struct folio *folio; - folio = do_read_cache_folio(mapping, index, filler, data, gfp); + folio = do_read_cache_folio(mapping, index, filler, file, gfp); if (IS_ERR(folio)) return &folio->page; return folio_file_page(folio, index); } struct page *read_cache_page(struct address_space *mapping, - pgoff_t index, filler_t *filler, void *data) + pgoff_t index, filler_t *filler, struct file *file) { - return do_read_cache_page(mapping, index, filler, data, + return do_read_cache_page(mapping, index, filler, file, mapping_gfp_mask(mapping)); } EXPORT_SYMBOL(read_cache_page); @@ -3628,27 +3621,6 @@ struct page *read_cache_page_gfp(struct address_space *mapping, } EXPORT_SYMBOL(read_cache_page_gfp); -int pagecache_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, - struct page **pagep, void **fsdata) -{ - const struct address_space_operations *aops = mapping->a_ops; - - return aops->write_begin(file, mapping, pos, len, flags, - pagep, fsdata); -} -EXPORT_SYMBOL(pagecache_write_begin); - -int pagecache_write_end(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) -{ - const struct address_space_operations *aops = mapping->a_ops; - - return aops->write_end(file, mapping, pos, len, copied, page, fsdata); -} -EXPORT_SYMBOL(pagecache_write_end); - /* * Warn about a page cache invalidation failure during a direct I/O write. */ @@ -3760,7 +3732,6 @@ ssize_t generic_perform_write(struct kiocb *iocb, struct iov_iter *i) const struct address_space_operations *a_ops = mapping->a_ops; long status = 0; ssize_t written = 0; - unsigned int flags = 0; do { struct page *page; @@ -3790,7 +3761,7 @@ again: break; } - status = a_ops->write_begin(file, mapping, pos, bytes, flags, + status = a_ops->write_begin(file, mapping, pos, bytes, &page, &fsdata); if (unlikely(status < 0)) break; @@ -3984,8 +3955,8 @@ bool filemap_release_folio(struct folio *folio, gfp_t gfp) if (folio_test_writeback(folio)) return false; - if (mapping && mapping->a_ops->releasepage) - return mapping->a_ops->releasepage(&folio->page, gfp); - return try_to_free_buffers(&folio->page); + if (mapping && mapping->a_ops->release_folio) + return mapping->a_ops->release_folio(folio, gfp); + return try_to_free_buffers(folio); } EXPORT_SYMBOL(filemap_release_folio); diff --git a/mm/folio-compat.c b/mm/folio-compat.c index 46fa179e32fb..20bc15b57d93 100644 --- a/mm/folio-compat.c +++ b/mm/folio-compat.c @@ -131,12 +131,10 @@ struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index, EXPORT_SYMBOL(pagecache_get_page); struct page *grab_cache_page_write_begin(struct address_space *mapping, - pgoff_t index, unsigned flags) + pgoff_t index) { unsigned fgp_flags = FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE; - if (flags & AOP_FLAG_NOFS) - fgp_flags |= FGP_NOFS; return pagecache_get_page(mapping, index, fgp_flags, mapping_gfp_mask(mapping)); } diff --git a/mm/gup.c b/mm/gup.c index f598a037eb04..501bc150792c 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -1648,6 +1648,35 @@ out: } EXPORT_SYMBOL(fault_in_writeable); +/** + * fault_in_subpage_writeable - fault in an address range for writing + * @uaddr: start of address range + * @size: size of address range + * + * Fault in a user address range for writing while checking for permissions at + * sub-page granularity (e.g. arm64 MTE). This function should be used when + * the caller cannot guarantee forward progress of a copy_to_user() loop. + * + * Returns the number of bytes not faulted in (like copy_to_user() and + * copy_from_user()). + */ +size_t fault_in_subpage_writeable(char __user *uaddr, size_t size) +{ + size_t faulted_in; + + /* + * Attempt faulting in at page granularity first for page table + * permission checking. The arch-specific probe_subpage_writeable() + * functions may not check for this. + */ + faulted_in = size - fault_in_writeable(uaddr, size); + if (faulted_in) + faulted_in -= probe_subpage_writeable(uaddr, faulted_in); + + return size - faulted_in; +} +EXPORT_SYMBOL(fault_in_subpage_writeable); + /* * fault_in_safe_writeable - fault in an address range for writing * @uaddr: start of address range diff --git a/mm/highmem.c b/mm/highmem.c index 0cc0c4da7ed9..1a692997fac4 100644 --- a/mm/highmem.c +++ b/mm/highmem.c @@ -624,7 +624,7 @@ void __kmap_local_sched_out(void) /* With debug all even slots are unmapped and act as guard */ if (IS_ENABLED(CONFIG_DEBUG_KMAP_LOCAL) && !(i & 0x01)) { - WARN_ON_ONCE(!pte_none(pteval)); + WARN_ON_ONCE(pte_val(pteval) != 0); continue; } if (WARN_ON_ONCE(pte_none(pteval))) @@ -661,7 +661,7 @@ void __kmap_local_sched_in(void) /* With debug all even slots are unmapped and act as guard */ if (IS_ENABLED(CONFIG_DEBUG_KMAP_LOCAL) && !(i & 0x01)) { - WARN_ON_ONCE(!pte_none(pteval)); + WARN_ON_ONCE(pte_val(pteval) != 0); continue; } if (WARN_ON_ONCE(pte_none(pteval))) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 2fe38212e07c..910a138e9859 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2145,15 +2145,14 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, * pmd against. Otherwise we can end up replacing wrong folio. */ VM_BUG_ON(freeze && !folio); - if (folio) { - VM_WARN_ON_ONCE(!folio_test_locked(folio)); - if (folio != page_folio(pmd_page(*pmd))) - goto out; - } + VM_WARN_ON_ONCE(folio && !folio_test_locked(folio)); if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd) || - is_pmd_migration_entry(*pmd)) + is_pmd_migration_entry(*pmd)) { + if (folio && folio != page_folio(pmd_page(*pmd))) + goto out; __split_huge_pmd_locked(vma, pmd, range.start, freeze); + } out: spin_unlock(ptl); @@ -2496,11 +2495,16 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) struct address_space *mapping = NULL; int extra_pins, ret; pgoff_t end; + bool is_hzp; - VM_BUG_ON_PAGE(is_huge_zero_page(head), head); VM_BUG_ON_PAGE(!PageLocked(head), head); VM_BUG_ON_PAGE(!PageCompound(head), head); + is_hzp = is_huge_zero_page(head); + VM_WARN_ON_ONCE_PAGE(is_hzp, head); + if (is_hzp) + return -EBUSY; + if (PageWriteback(head)) return -EBUSY; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index b34f50156f7e..3fc721789743 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3475,7 +3475,6 @@ static int demote_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed) { int nr_nodes, node; struct page *page; - int rc = 0; lockdep_assert_held(&hugetlb_lock); @@ -3486,15 +3485,19 @@ static int demote_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed) } for_each_node_mask_to_free(h, nr_nodes, node, nodes_allowed) { - if (!list_empty(&h->hugepage_freelists[node])) { - page = list_entry(h->hugepage_freelists[node].next, - struct page, lru); - rc = demote_free_huge_page(h, page); - break; + list_for_each_entry(page, &h->hugepage_freelists[node], lru) { + if (PageHWPoison(page)) + continue; + + return demote_free_huge_page(h, page); } } - return rc; + /* + * Only way to get here is if all pages on free lists are poisoned. + * Return -EBUSY so that caller will not retry. + */ + return -EBUSY; } #define HSTATE_ATTR_RO(_name) \ @@ -6782,6 +6785,16 @@ int get_hwpoison_huge_page(struct page *page, bool *hugetlb) return ret; } +int get_huge_page_for_hwpoison(unsigned long pfn, int flags) +{ + int ret; + + spin_lock_irq(&hugetlb_lock); + ret = __get_huge_page_for_hwpoison(pfn, flags); + spin_unlock_irq(&hugetlb_lock); + return ret; +} + void putback_active_hugepage(struct page *page) { spin_lock_irq(&hugetlb_lock); diff --git a/mm/kasan/hw_tags.c b/mm/kasan/hw_tags.c index 07a76c46daa5..9e1b6544bfa8 100644 --- a/mm/kasan/hw_tags.c +++ b/mm/kasan/hw_tags.c @@ -336,8 +336,6 @@ void __kasan_poison_vmalloc(const void *start, unsigned long size) #endif -#if IS_ENABLED(CONFIG_KASAN_KUNIT_TEST) - void kasan_enable_tagging(void) { if (kasan_arg_mode == KASAN_ARG_MODE_ASYNC) @@ -347,6 +345,9 @@ void kasan_enable_tagging(void) else hw_enable_tagging_sync(); } + +#if IS_ENABLED(CONFIG_KASAN_KUNIT_TEST) + EXPORT_SYMBOL_GPL(kasan_enable_tagging); void kasan_force_async_fault(void) diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h index d79b83d673b1..b01b4bbe0409 100644 --- a/mm/kasan/kasan.h +++ b/mm/kasan/kasan.h @@ -355,25 +355,27 @@ static inline const void *arch_kasan_set_tag(const void *addr, u8 tag) #define hw_set_mem_tag_range(addr, size, tag, init) \ arch_set_mem_tag_range((addr), (size), (tag), (init)) +void kasan_enable_tagging(void); + #else /* CONFIG_KASAN_HW_TAGS */ #define hw_enable_tagging_sync() #define hw_enable_tagging_async() #define hw_enable_tagging_asymm() +static inline void kasan_enable_tagging(void) { } + #endif /* CONFIG_KASAN_HW_TAGS */ #if defined(CONFIG_KASAN_HW_TAGS) && IS_ENABLED(CONFIG_KASAN_KUNIT_TEST) -void kasan_enable_tagging(void); void kasan_force_async_fault(void); -#else /* CONFIG_KASAN_HW_TAGS || CONFIG_KASAN_KUNIT_TEST */ +#else /* CONFIG_KASAN_HW_TAGS && CONFIG_KASAN_KUNIT_TEST */ -static inline void kasan_enable_tagging(void) { } static inline void kasan_force_async_fault(void) { } -#endif /* CONFIG_KASAN_HW_TAGS || CONFIG_KASAN_KUNIT_TEST */ +#endif /* CONFIG_KASAN_HW_TAGS && CONFIG_KASAN_KUNIT_TEST */ #ifdef CONFIG_KASAN_SW_TAGS u8 kasan_random_tag(void); diff --git a/mm/kasan/quarantine.c b/mm/kasan/quarantine.c index 08291ed33e93..0a9def8ce5e8 100644 --- a/mm/kasan/quarantine.c +++ b/mm/kasan/quarantine.c @@ -315,6 +315,13 @@ static void per_cpu_remove_cache(void *arg) struct qlist_head *q; q = this_cpu_ptr(&cpu_quarantine); + /* + * Ensure the ordering between the writing to q->offline and + * per_cpu_remove_cache. Prevent cpu_quarantine from being corrupted + * by interrupt. + */ + if (READ_ONCE(q->offline)) + return; qlist_move_cache(q, &to_free, cache); qlist_free_all(&to_free, cache); } diff --git a/mm/kfence/core.c b/mm/kfence/core.c index a203747ad2c0..11a954763be9 100644 --- a/mm/kfence/core.c +++ b/mm/kfence/core.c @@ -231,27 +231,6 @@ static bool kfence_unprotect(unsigned long addr) return !KFENCE_WARN_ON(!kfence_protect_page(ALIGN_DOWN(addr, PAGE_SIZE), false)); } -static inline struct kfence_metadata *addr_to_metadata(unsigned long addr) -{ - long index; - - /* The checks do not affect performance; only called from slow-paths. */ - - if (!is_kfence_address((void *)addr)) - return NULL; - - /* - * May be an invalid index if called with an address at the edge of - * __kfence_pool, in which case we would report an "invalid access" - * error. - */ - index = (addr - (unsigned long)__kfence_pool) / (PAGE_SIZE * 2) - 1; - if (index < 0 || index >= CONFIG_KFENCE_NUM_OBJECTS) - return NULL; - - return &kfence_metadata[index]; -} - static inline unsigned long metadata_to_pageaddr(const struct kfence_metadata *meta) { unsigned long offset = (meta - kfence_metadata + 1) * PAGE_SIZE * 2; @@ -642,6 +621,16 @@ static bool __init kfence_init_pool_early(void) * fails for the first page, and therefore expect addr==__kfence_pool in * most failure cases. */ + for (char *p = (char *)addr; p < __kfence_pool + KFENCE_POOL_SIZE; p += PAGE_SIZE) { + struct slab *slab = virt_to_slab(p); + + if (!slab) + continue; +#ifdef CONFIG_MEMCG + slab->memcg_data = 0; +#endif + __folio_clear_slab(slab_folio(slab)); + } memblock_free_late(__pa(addr), KFENCE_POOL_SIZE - (addr - (unsigned long)__kfence_pool)); __kfence_pool = NULL; return false; diff --git a/mm/kfence/kfence.h b/mm/kfence/kfence.h index 9a6c4b1b12a8..600f2e2431d6 100644 --- a/mm/kfence/kfence.h +++ b/mm/kfence/kfence.h @@ -96,6 +96,27 @@ struct kfence_metadata { extern struct kfence_metadata kfence_metadata[CONFIG_KFENCE_NUM_OBJECTS]; +static inline struct kfence_metadata *addr_to_metadata(unsigned long addr) +{ + long index; + + /* The checks do not affect performance; only called from slow-paths. */ + + if (!is_kfence_address((void *)addr)) + return NULL; + + /* + * May be an invalid index if called with an address at the edge of + * __kfence_pool, in which case we would report an "invalid access" + * error. + */ + index = (addr - (unsigned long)__kfence_pool) / (PAGE_SIZE * 2) - 1; + if (index < 0 || index >= CONFIG_KFENCE_NUM_OBJECTS) + return NULL; + + return &kfence_metadata[index]; +} + /* KFENCE error types for report generation. */ enum kfence_error_type { KFENCE_ERROR_OOB, /* Detected a out-of-bounds access. */ diff --git a/mm/kfence/report.c b/mm/kfence/report.c index f93a7b2a338b..f5a6d8ba3e21 100644 --- a/mm/kfence/report.c +++ b/mm/kfence/report.c @@ -273,3 +273,50 @@ void kfence_report_error(unsigned long address, bool is_write, struct pt_regs *r /* We encountered a memory safety error, taint the kernel! */ add_taint(TAINT_BAD_PAGE, LOCKDEP_STILL_OK); } + +#ifdef CONFIG_PRINTK +static void kfence_to_kp_stack(const struct kfence_track *track, void **kp_stack) +{ + int i, j; + + i = get_stack_skipnr(track->stack_entries, track->num_stack_entries, NULL); + for (j = 0; i < track->num_stack_entries && j < KS_ADDRS_COUNT; ++i, ++j) + kp_stack[j] = (void *)track->stack_entries[i]; + if (j < KS_ADDRS_COUNT) + kp_stack[j] = NULL; +} + +bool __kfence_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab) +{ + struct kfence_metadata *meta = addr_to_metadata((unsigned long)object); + unsigned long flags; + + if (!meta) + return false; + + /* + * If state is UNUSED at least show the pointer requested; the rest + * would be garbage data. + */ + kpp->kp_ptr = object; + + /* Requesting info an a never-used object is almost certainly a bug. */ + if (WARN_ON(meta->state == KFENCE_OBJECT_UNUSED)) + return true; + + raw_spin_lock_irqsave(&meta->lock, flags); + + kpp->kp_slab = slab; + kpp->kp_slab_cache = meta->cache; + kpp->kp_objp = (void *)meta->addr; + kfence_to_kp_stack(&meta->alloc_track, kpp->kp_stack); + if (meta->state == KFENCE_OBJECT_FREED) + kfence_to_kp_stack(&meta->free_track, kpp->kp_free_stack); + /* get_stack_skipnr() ensures the first entry is outside allocator. */ + kpp->kp_ret = kpp->kp_stack[0]; + + raw_spin_unlock_irqrestore(&meta->lock, flags); + + return true; +} +#endif diff --git a/mm/kmemleak.c b/mm/kmemleak.c index acd7cbb82e16..a182f5ddaf68 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -1132,7 +1132,7 @@ EXPORT_SYMBOL(kmemleak_no_scan); void __ref kmemleak_alloc_phys(phys_addr_t phys, size_t size, int min_count, gfp_t gfp) { - if (!IS_ENABLED(CONFIG_HIGHMEM) || PHYS_PFN(phys) < max_low_pfn) + if (PHYS_PFN(phys) >= min_low_pfn && PHYS_PFN(phys) < max_low_pfn) kmemleak_alloc(__va(phys), size, min_count, gfp); } EXPORT_SYMBOL(kmemleak_alloc_phys); @@ -1146,7 +1146,7 @@ EXPORT_SYMBOL(kmemleak_alloc_phys); */ void __ref kmemleak_free_part_phys(phys_addr_t phys, size_t size) { - if (!IS_ENABLED(CONFIG_HIGHMEM) || PHYS_PFN(phys) < max_low_pfn) + if (PHYS_PFN(phys) >= min_low_pfn && PHYS_PFN(phys) < max_low_pfn) kmemleak_free_part(__va(phys), size); } EXPORT_SYMBOL(kmemleak_free_part_phys); @@ -1158,7 +1158,7 @@ EXPORT_SYMBOL(kmemleak_free_part_phys); */ void __ref kmemleak_not_leak_phys(phys_addr_t phys) { - if (!IS_ENABLED(CONFIG_HIGHMEM) || PHYS_PFN(phys) < max_low_pfn) + if (PHYS_PFN(phys) >= min_low_pfn && PHYS_PFN(phys) < max_low_pfn) kmemleak_not_leak(__va(phys)); } EXPORT_SYMBOL(kmemleak_not_leak_phys); @@ -1170,7 +1170,7 @@ EXPORT_SYMBOL(kmemleak_not_leak_phys); */ void __ref kmemleak_ignore_phys(phys_addr_t phys) { - if (!IS_ENABLED(CONFIG_HIGHMEM) || PHYS_PFN(phys) < max_low_pfn) + if (PHYS_PFN(phys) >= min_low_pfn && PHYS_PFN(phys) < max_low_pfn) kmemleak_ignore(__va(phys)); } EXPORT_SYMBOL(kmemleak_ignore_phys); diff --git a/mm/list_lru.c b/mm/list_lru.c index c669d87001a6..ba76428ceece 100644 --- a/mm/list_lru.c +++ b/mm/list_lru.c @@ -395,12 +395,6 @@ static void memcg_reparent_list_lru_node(struct list_lru *lru, int nid, struct list_lru_one *src, *dst; /* - * If there is no lru entry in this nlru, we can skip it immediately. - */ - if (!READ_ONCE(nlru->nr_items)) - return; - - /* * Since list_lru_{add,del} may be called under an IRQ-safe lock, * we have to use IRQ-safe primitives here to avoid deadlock. */ diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 725f76723220..598fece89e2b 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -587,6 +587,9 @@ static DECLARE_DEFERRABLE_WORK(stats_flush_dwork, flush_memcg_stats_dwork); static DEFINE_SPINLOCK(stats_flush_lock); static DEFINE_PER_CPU(unsigned int, stats_updates); static atomic_t stats_flush_threshold = ATOMIC_INIT(0); +static u64 flush_next_time; + +#define FLUSH_TIME (2UL*HZ) /* * Accessors to ensure that preemption is disabled on PREEMPT_RT because it can @@ -637,6 +640,7 @@ static void __mem_cgroup_flush_stats(void) if (!spin_trylock_irqsave(&stats_flush_lock, flag)) return; + flush_next_time = jiffies_64 + 2*FLUSH_TIME; cgroup_rstat_flush_irqsafe(root_mem_cgroup->css.cgroup); atomic_set(&stats_flush_threshold, 0); spin_unlock_irqrestore(&stats_flush_lock, flag); @@ -648,10 +652,16 @@ void mem_cgroup_flush_stats(void) __mem_cgroup_flush_stats(); } +void mem_cgroup_flush_stats_delayed(void) +{ + if (time_after64(jiffies_64, flush_next_time)) + mem_cgroup_flush_stats(); +} + static void flush_memcg_stats_dwork(struct work_struct *w) { __mem_cgroup_flush_stats(); - queue_delayed_work(system_unbound_wq, &stats_flush_dwork, 2UL*HZ); + queue_delayed_work(system_unbound_wq, &stats_flush_dwork, FLUSH_TIME); } /** diff --git a/mm/memory-failure.c b/mm/memory-failure.c index dcb6bb9cf731..d4a4adcca01f 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1274,7 +1274,7 @@ try_again: } out: if (ret == -EIO) - dump_page(p, "hwpoison: unhandlable page"); + pr_err("Memory failure: %#lx: unhandlable page.\n", page_to_pfn(p)); return ret; } @@ -1498,50 +1498,113 @@ static int try_to_split_thp_page(struct page *page, const char *msg) return 0; } -static int memory_failure_hugetlb(unsigned long pfn, int flags) +/* + * Called from hugetlb code with hugetlb_lock held. + * + * Return values: + * 0 - free hugepage + * 1 - in-use hugepage + * 2 - not a hugepage + * -EBUSY - the hugepage is busy (try to retry) + * -EHWPOISON - the hugepage is already hwpoisoned + */ +int __get_huge_page_for_hwpoison(unsigned long pfn, int flags) +{ + struct page *page = pfn_to_page(pfn); + struct page *head = compound_head(page); + int ret = 2; /* fallback to normal page handling */ + bool count_increased = false; + + if (!PageHeadHuge(head)) + goto out; + + if (flags & MF_COUNT_INCREASED) { + ret = 1; + count_increased = true; + } else if (HPageFreed(head) || HPageMigratable(head)) { + ret = get_page_unless_zero(head); + if (ret) + count_increased = true; + } else { + ret = -EBUSY; + goto out; + } + + if (TestSetPageHWPoison(head)) { + ret = -EHWPOISON; + goto out; + } + + return ret; +out: + if (count_increased) + put_page(head); + return ret; +} + +#ifdef CONFIG_HUGETLB_PAGE +/* + * Taking refcount of hugetlb pages needs extra care about race conditions + * with basic operations like hugepage allocation/free/demotion. + * So some of prechecks for hwpoison (pinning, and testing/setting + * PageHWPoison) should be done in single hugetlb_lock range. + */ +static int try_memory_failure_hugetlb(unsigned long pfn, int flags, int *hugetlb) { - struct page *p = pfn_to_page(pfn); - struct page *head = compound_head(p); int res; + struct page *p = pfn_to_page(pfn); + struct page *head; unsigned long page_flags; + bool retry = true; - if (TestSetPageHWPoison(head)) { - pr_err("Memory failure: %#lx: already hardware poisoned\n", - pfn); - res = -EHWPOISON; - if (flags & MF_ACTION_REQUIRED) + *hugetlb = 1; +retry: + res = get_huge_page_for_hwpoison(pfn, flags); + if (res == 2) { /* fallback to normal page handling */ + *hugetlb = 0; + return 0; + } else if (res == -EHWPOISON) { + pr_err("Memory failure: %#lx: already hardware poisoned\n", pfn); + if (flags & MF_ACTION_REQUIRED) { + head = compound_head(p); res = kill_accessing_process(current, page_to_pfn(head), flags); + } return res; + } else if (res == -EBUSY) { + if (retry) { + retry = false; + goto retry; + } + action_result(pfn, MF_MSG_UNKNOWN, MF_IGNORED); + return res; + } + + head = compound_head(p); + lock_page(head); + + if (hwpoison_filter(p)) { + ClearPageHWPoison(head); + res = -EOPNOTSUPP; + goto out; } num_poisoned_pages_inc(); - if (!(flags & MF_COUNT_INCREASED)) { - res = get_hwpoison_page(p, flags); - if (!res) { - lock_page(head); - if (hwpoison_filter(p)) { - if (TestClearPageHWPoison(head)) - num_poisoned_pages_dec(); - unlock_page(head); - return -EOPNOTSUPP; - } - unlock_page(head); - res = MF_FAILED; - if (__page_handle_poison(p)) { - page_ref_inc(p); - res = MF_RECOVERED; - } - action_result(pfn, MF_MSG_FREE_HUGE, res); - return res == MF_RECOVERED ? 0 : -EBUSY; - } else if (res < 0) { - action_result(pfn, MF_MSG_UNKNOWN, MF_IGNORED); - return -EBUSY; + /* + * Handling free hugepage. The possible race with hugepage allocation + * or demotion can be prevented by PageHWPoison flag. + */ + if (res == 0) { + unlock_page(head); + res = MF_FAILED; + if (__page_handle_poison(p)) { + page_ref_inc(p); + res = MF_RECOVERED; } + action_result(pfn, MF_MSG_FREE_HUGE, res); + return res == MF_RECOVERED ? 0 : -EBUSY; } - lock_page(head); - /* * The page could have changed compound pages due to race window. * If this happens just bail out. @@ -1554,14 +1617,6 @@ static int memory_failure_hugetlb(unsigned long pfn, int flags) page_flags = head->flags; - if (hwpoison_filter(p)) { - if (TestClearPageHWPoison(head)) - num_poisoned_pages_dec(); - put_page(p); - res = -EOPNOTSUPP; - goto out; - } - /* * TODO: hwpoison for pud-sized hugetlb doesn't work right now, so * simply disable it. In order to make it work properly, we need @@ -1588,6 +1643,12 @@ out: unlock_page(head); return res; } +#else +static inline int try_memory_failure_hugetlb(unsigned long pfn, int flags, int *hugetlb) +{ + return 0; +} +#endif static int memory_failure_dev_pagemap(unsigned long pfn, int flags, struct dev_pagemap *pgmap) @@ -1712,6 +1773,7 @@ int memory_failure(unsigned long pfn, int flags) int res = 0; unsigned long page_flags; bool retry = true; + int hugetlb = 0; if (!sysctl_memory_failure_recovery) panic("Memory failure on page %lx", pfn); @@ -1739,10 +1801,9 @@ int memory_failure(unsigned long pfn, int flags) } try_again: - if (PageHuge(p)) { - res = memory_failure_hugetlb(pfn, flags); + res = try_memory_failure_hugetlb(pfn, flags, &hugetlb); + if (hugetlb) goto unlock_mutex; - } if (TestSetPageHWPoison(p)) { pr_err("Memory failure: %#lx: already hardware poisoned\n", diff --git a/mm/memory.c b/mm/memory.c index 76e3af9639d9..2a12028a3749 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -555,11 +555,11 @@ static void print_bad_pte(struct vm_area_struct *vma, unsigned long addr, dump_page(page, "bad pte"); pr_alert("addr:%px vm_flags:%08lx anon_vma:%px mapping:%px index:%lx\n", (void *)addr, vma->vm_flags, vma->anon_vma, mapping, index); - pr_alert("file:%pD fault:%ps mmap:%ps readpage:%ps\n", + pr_alert("file:%pD fault:%ps mmap:%ps read_folio:%ps\n", vma->vm_file, vma->vm_ops ? vma->vm_ops->fault : NULL, vma->vm_file ? vma->vm_file->f_op->mmap : NULL, - mapping ? mapping->a_ops->readpage : NULL); + mapping ? mapping->a_ops->read_folio : NULL); dump_stack(); add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); } diff --git a/mm/mempolicy.c b/mm/mempolicy.c index a2516d31db6c..8c74107a2b15 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1191,8 +1191,10 @@ int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, */ static struct page *new_page(struct page *page, unsigned long start) { + struct folio *dst, *src = page_folio(page); struct vm_area_struct *vma; unsigned long address; + gfp_t gfp = GFP_HIGHUSER_MOVABLE | __GFP_RETRY_MAYFAIL; vma = find_vma(current->mm, start); while (vma) { @@ -1202,24 +1204,19 @@ static struct page *new_page(struct page *page, unsigned long start) vma = vma->vm_next; } - if (PageHuge(page)) { - return alloc_huge_page_vma(page_hstate(compound_head(page)), + if (folio_test_hugetlb(src)) + return alloc_huge_page_vma(page_hstate(&src->page), vma, address); - } else if (PageTransHuge(page)) { - struct page *thp; - thp = alloc_hugepage_vma(GFP_TRANSHUGE, vma, address, - HPAGE_PMD_ORDER); - if (!thp) - return NULL; - prep_transhuge_page(thp); - return thp; - } + if (folio_test_large(src)) + gfp = GFP_TRANSHUGE; + /* - * if !vma, alloc_page_vma() will use task or system default policy + * if !vma, vma_alloc_folio() will use task or system default policy */ - return alloc_page_vma(GFP_HIGHUSER_MOVABLE | __GFP_RETRY_MAYFAIL, - vma, address); + dst = vma_alloc_folio(gfp, folio_order(src), vma, address, + folio_test_large(src)); + return &dst->page; } #else @@ -2227,6 +2224,19 @@ out: } EXPORT_SYMBOL(alloc_pages_vma); +struct folio *vma_alloc_folio(gfp_t gfp, int order, struct vm_area_struct *vma, + unsigned long addr, bool hugepage) +{ + struct folio *folio; + + folio = (struct folio *)alloc_pages_vma(gfp, order, vma, addr, + hugepage); + if (folio && order > 1) + prep_transhuge_page(&folio->page); + + return folio; +} + /** * alloc_pages - Allocate pages. * @gfp: GFP flags. @@ -2733,6 +2743,7 @@ alloc_new: mpol_new = kmem_cache_alloc(policy_cache, GFP_KERNEL); if (!mpol_new) goto err_out; + atomic_set(&mpol_new->refcnt, 1); goto restart; } diff --git a/mm/migrate.c b/mm/migrate.c index de175e2fdba5..21d82636c291 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1013,7 +1013,7 @@ static int __unmap_and_move(struct page *page, struct page *newpage, if (!page->mapping) { VM_BUG_ON_PAGE(PageAnon(page), page); if (page_has_private(page)) { - try_to_free_buffers(page); + try_to_free_buffers(folio); goto out_unlock_both; } } else if (page_mapped(page)) { @@ -1520,10 +1520,11 @@ out: struct page *alloc_migration_target(struct page *page, unsigned long private) { + struct folio *folio = page_folio(page); struct migration_target_control *mtc; gfp_t gfp_mask; unsigned int order = 0; - struct page *new_page = NULL; + struct folio *new_folio = NULL; int nid; int zidx; @@ -1531,34 +1532,31 @@ struct page *alloc_migration_target(struct page *page, unsigned long private) gfp_mask = mtc->gfp_mask; nid = mtc->nid; if (nid == NUMA_NO_NODE) - nid = page_to_nid(page); + nid = folio_nid(folio); - if (PageHuge(page)) { - struct hstate *h = page_hstate(compound_head(page)); + if (folio_test_hugetlb(folio)) { + struct hstate *h = page_hstate(&folio->page); gfp_mask = htlb_modify_alloc_mask(h, gfp_mask); return alloc_huge_page_nodemask(h, nid, mtc->nmask, gfp_mask); } - if (PageTransHuge(page)) { + if (folio_test_large(folio)) { /* * clear __GFP_RECLAIM to make the migration callback * consistent with regular THP allocations. */ gfp_mask &= ~__GFP_RECLAIM; gfp_mask |= GFP_TRANSHUGE; - order = HPAGE_PMD_ORDER; + order = folio_order(folio); } - zidx = zone_idx(page_zone(page)); + zidx = zone_idx(folio_zone(folio)); if (is_highmem_idx(zidx) || zidx == ZONE_MOVABLE) gfp_mask |= __GFP_HIGHMEM; - new_page = __alloc_pages(gfp_mask, order, nid, mtc->nmask); - - if (new_page && PageTransHuge(new_page)) - prep_transhuge_page(new_page); + new_folio = __folio_alloc(gfp_mask, order, nid, mtc->nmask); - return new_page; + return &new_folio->page; } #ifdef CONFIG_NUMA @@ -1999,32 +1997,20 @@ static struct page *alloc_misplaced_dst_page(struct page *page, unsigned long data) { int nid = (int) data; - struct page *newpage; - - newpage = __alloc_pages_node(nid, - (GFP_HIGHUSER_MOVABLE | - __GFP_THISNODE | __GFP_NOMEMALLOC | - __GFP_NORETRY | __GFP_NOWARN) & - ~__GFP_RECLAIM, 0); - - return newpage; -} - -static struct page *alloc_misplaced_dst_page_thp(struct page *page, - unsigned long data) -{ - int nid = (int) data; - struct page *newpage; - - newpage = alloc_pages_node(nid, (GFP_TRANSHUGE_LIGHT | __GFP_THISNODE), - HPAGE_PMD_ORDER); - if (!newpage) - goto out; - - prep_transhuge_page(newpage); + int order = compound_order(page); + gfp_t gfp = __GFP_THISNODE; + struct folio *new; + + if (order > 0) + gfp |= GFP_TRANSHUGE_LIGHT; + else { + gfp |= GFP_HIGHUSER_MOVABLE | __GFP_NOMEMALLOC | __GFP_NORETRY | + __GFP_NOWARN; + gfp &= ~__GFP_RECLAIM; + } + new = __folio_alloc_node(gfp, order, nid); -out: - return newpage; + return &new->page; } static int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page) @@ -2082,23 +2068,9 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, int nr_remaining; unsigned int nr_succeeded; LIST_HEAD(migratepages); - new_page_t *new; - bool compound; int nr_pages = thp_nr_pages(page); /* - * PTE mapped THP or HugeTLB page can't reach here so the page could - * be either base page or THP. And it must be head page if it is - * THP. - */ - compound = PageTransHuge(page); - - if (compound) - new = alloc_misplaced_dst_page_thp; - else - new = alloc_misplaced_dst_page; - - /* * Don't migrate file pages that are mapped in multiple processes * with execute permissions as they are probably shared libraries. */ @@ -2118,9 +2090,9 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, goto out; list_add(&page->lru, &migratepages); - nr_remaining = migrate_pages(&migratepages, *new, NULL, node, - MIGRATE_ASYNC, MR_NUMA_MISPLACED, - &nr_succeeded); + nr_remaining = migrate_pages(&migratepages, alloc_misplaced_dst_page, + NULL, node, MIGRATE_ASYNC, + MR_NUMA_MISPLACED, &nr_succeeded); if (nr_remaining) { if (!list_empty(&migratepages)) { list_del(&page->lru); diff --git a/mm/mmap.c b/mm/mmap.c index 3aa839f81e63..313b57d55a63 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2117,14 +2117,6 @@ unsigned long vm_unmapped_area(struct vm_unmapped_area_info *info) return addr; } -#ifndef arch_get_mmap_end -#define arch_get_mmap_end(addr) (TASK_SIZE) -#endif - -#ifndef arch_get_mmap_base -#define arch_get_mmap_base(addr, base) (base) -#endif - /* Get an address range which is currently unmapped. * For shmat() with addr=0. * diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c index 459d195d2ff6..f45ff1b7626a 100644 --- a/mm/mmu_notifier.c +++ b/mm/mmu_notifier.c @@ -1036,6 +1036,18 @@ int mmu_interval_notifier_insert_locked( } EXPORT_SYMBOL_GPL(mmu_interval_notifier_insert_locked); +static bool +mmu_interval_seq_released(struct mmu_notifier_subscriptions *subscriptions, + unsigned long seq) +{ + bool ret; + + spin_lock(&subscriptions->lock); + ret = subscriptions->invalidate_seq != seq; + spin_unlock(&subscriptions->lock); + return ret; +} + /** * mmu_interval_notifier_remove - Remove a interval notifier * @interval_sub: Interval subscription to unregister @@ -1083,7 +1095,7 @@ void mmu_interval_notifier_remove(struct mmu_interval_notifier *interval_sub) lock_map_release(&__mmu_notifier_invalidate_range_start_map); if (seq) wait_event(subscriptions->wq, - READ_ONCE(subscriptions->invalidate_seq) != seq); + mmu_interval_seq_released(subscriptions, seq)); /* pairs with mmgrab in mmu_interval_notifier_insert() */ mmdrop(mm); diff --git a/mm/mremap.c b/mm/mremap.c index 9d76da79594d..0b93fac76851 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -486,6 +486,9 @@ unsigned long move_page_tables(struct vm_area_struct *vma, pmd_t *old_pmd, *new_pmd; pud_t *old_pud, *new_pud; + if (!len) + return 0; + old_end = old_addr + len; flush_cache_range(vma, old_addr, old_end); @@ -944,7 +947,7 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, return -EINTR; vma = vma_lookup(mm, addr); if (!vma) { - ret = EFAULT; + ret = -EFAULT; goto out; } diff --git a/mm/nommu.c b/mm/nommu.c index 55a9e48a7a02..9d7afc2d959e 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -226,6 +226,8 @@ void *vmalloc(unsigned long size) } EXPORT_SYMBOL(vmalloc); +void *vmalloc_huge(unsigned long size, gfp_t gfp_mask) __weak __alias(__vmalloc); + /* * vzalloc - allocate virtually contiguous memory with zero fill * diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 7ec38194f8e1..49d7df39b02d 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -632,7 +632,7 @@ done: */ set_bit(MMF_OOM_SKIP, &mm->flags); - /* Drop a reference taken by wake_oom_reaper */ + /* Drop a reference taken by queue_oom_reaper */ put_task_struct(tsk); } @@ -644,12 +644,12 @@ static int oom_reaper(void *unused) struct task_struct *tsk = NULL; wait_event_freezable(oom_reaper_wait, oom_reaper_list != NULL); - spin_lock(&oom_reaper_lock); + spin_lock_irq(&oom_reaper_lock); if (oom_reaper_list != NULL) { tsk = oom_reaper_list; oom_reaper_list = tsk->oom_reaper_list; } - spin_unlock(&oom_reaper_lock); + spin_unlock_irq(&oom_reaper_lock); if (tsk) oom_reap_task(tsk); @@ -658,22 +658,48 @@ static int oom_reaper(void *unused) return 0; } -static void wake_oom_reaper(struct task_struct *tsk) +static void wake_oom_reaper(struct timer_list *timer) { - /* mm is already queued? */ - if (test_and_set_bit(MMF_OOM_REAP_QUEUED, &tsk->signal->oom_mm->flags)) - return; + struct task_struct *tsk = container_of(timer, struct task_struct, + oom_reaper_timer); + struct mm_struct *mm = tsk->signal->oom_mm; + unsigned long flags; - get_task_struct(tsk); + /* The victim managed to terminate on its own - see exit_mmap */ + if (test_bit(MMF_OOM_SKIP, &mm->flags)) { + put_task_struct(tsk); + return; + } - spin_lock(&oom_reaper_lock); + spin_lock_irqsave(&oom_reaper_lock, flags); tsk->oom_reaper_list = oom_reaper_list; oom_reaper_list = tsk; - spin_unlock(&oom_reaper_lock); + spin_unlock_irqrestore(&oom_reaper_lock, flags); trace_wake_reaper(tsk->pid); wake_up(&oom_reaper_wait); } +/* + * Give the OOM victim time to exit naturally before invoking the oom_reaping. + * The timers timeout is arbitrary... the longer it is, the longer the worst + * case scenario for the OOM can take. If it is too small, the oom_reaper can + * get in the way and release resources needed by the process exit path. + * e.g. The futex robust list can sit in Anon|Private memory that gets reaped + * before the exit path is able to wake the futex waiters. + */ +#define OOM_REAPER_DELAY (2*HZ) +static void queue_oom_reaper(struct task_struct *tsk) +{ + /* mm is already queued? */ + if (test_and_set_bit(MMF_OOM_REAP_QUEUED, &tsk->signal->oom_mm->flags)) + return; + + get_task_struct(tsk); + timer_setup(&tsk->oom_reaper_timer, wake_oom_reaper, 0); + tsk->oom_reaper_timer.expires = jiffies + OOM_REAPER_DELAY; + add_timer(&tsk->oom_reaper_timer); +} + static int __init oom_init(void) { oom_reaper_th = kthread_run(oom_reaper, NULL, "oom_reaper"); @@ -681,7 +707,7 @@ static int __init oom_init(void) } subsys_initcall(oom_init) #else -static inline void wake_oom_reaper(struct task_struct *tsk) +static inline void queue_oom_reaper(struct task_struct *tsk) { } #endif /* CONFIG_MMU */ @@ -932,7 +958,7 @@ static void __oom_kill_process(struct task_struct *victim, const char *message) rcu_read_unlock(); if (can_oom_reap) - wake_oom_reaper(victim); + queue_oom_reaper(victim); mmdrop(mm); put_task_struct(victim); @@ -968,7 +994,7 @@ static void oom_kill_process(struct oom_control *oc, const char *message) task_lock(victim); if (task_will_free_mem(victim)) { mark_oom_victim(victim); - wake_oom_reaper(victim); + queue_oom_reaper(victim); task_unlock(victim); put_task_struct(victim); return; @@ -1067,7 +1093,7 @@ bool out_of_memory(struct oom_control *oc) */ if (task_will_free_mem(current)) { mark_oom_victim(current); - wake_oom_reaper(current); + queue_oom_reaper(current); return true; } diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 7e2da284e427..fa1117db4610 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2602,10 +2602,12 @@ EXPORT_SYMBOL(folio_redirty_for_writepage); * folio_mark_dirty - Mark a folio as being modified. * @folio: The folio. * - * For folios with a mapping this should be done with the folio lock held - * for the benefit of asynchronous memory errors who prefer a consistent - * dirty state. This rule can be broken in some special cases, - * but should be better not to. + * The folio may not be truncated while this function is running. + * Holding the folio lock is sufficient to prevent truncation, but some + * callers cannot acquire a sleeping lock. These callers instead hold + * the page table lock for a page table which contains at least one page + * in this folio. Truncation will block on the page table lock as it + * unmaps pages before removing the folio from its mapping. * * Return: True if the folio was newly dirtied, false if it was already dirty. */ diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 2db95780e003..0e42038382c1 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -128,7 +128,7 @@ static DEFINE_MUTEX(pcp_batch_high_lock); struct pagesets { local_lock_t lock; }; -static DEFINE_PER_CPU(struct pagesets, pagesets) __maybe_unused = { +static DEFINE_PER_CPU(struct pagesets, pagesets) = { .lock = INIT_LOCAL_LOCK(lock), }; @@ -6131,7 +6131,7 @@ static int build_zonerefs_node(pg_data_t *pgdat, struct zoneref *zonerefs) do { zone_type--; zone = pgdat->node_zones + zone_type; - if (managed_zone(zone)) { + if (populated_zone(zone)) { zoneref_set_zone(zone, &zonerefs[nr_zones++]); check_highest_zone(zone_type); } @@ -8919,7 +8919,7 @@ void *__init alloc_large_system_hash(const char *tablename, table = memblock_alloc_raw(size, SMP_CACHE_BYTES); } else if (get_order(size) >= MAX_ORDER || hashdist) { - table = __vmalloc(size, gfp_flags); + table = vmalloc_huge(size, gfp_flags); virt = true; if (table) huge = is_vm_area_hugepages(table); diff --git a/mm/page_io.c b/mm/page_io.c index b417f000b49e..a9444e67ec20 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -51,54 +51,6 @@ void end_swap_bio_write(struct bio *bio) bio_put(bio); } -static void swap_slot_free_notify(struct page *page) -{ - struct swap_info_struct *sis; - struct gendisk *disk; - swp_entry_t entry; - - /* - * There is no guarantee that the page is in swap cache - the software - * suspend code (at least) uses end_swap_bio_read() against a non- - * swapcache page. So we must check PG_swapcache before proceeding with - * this optimization. - */ - if (unlikely(!PageSwapCache(page))) - return; - - sis = page_swap_info(page); - if (data_race(!(sis->flags & SWP_BLKDEV))) - return; - - /* - * The swap subsystem performs lazy swap slot freeing, - * expecting that the page will be swapped out again. - * So we can avoid an unnecessary write if the page - * isn't redirtied. - * This is good for real swap storage because we can - * reduce unnecessary I/O and enhance wear-leveling - * if an SSD is used as the as swap device. - * But if in-memory swap device (eg zram) is used, - * this causes a duplicated copy between uncompressed - * data in VM-owned memory and compressed data in - * zram-owned memory. So let's free zram-owned memory - * and make the VM-owned decompressed page *dirty*, - * so the page should be swapped out somewhere again if - * we again wish to reclaim it. - */ - disk = sis->bdev->bd_disk; - entry.val = page_private(page); - if (disk->fops->swap_slot_free_notify && __swap_count(entry) == 1) { - unsigned long offset; - - offset = swp_offset(entry); - - SetPageDirty(page); - disk->fops->swap_slot_free_notify(sis->bdev, - offset); - } -} - static void end_swap_bio_read(struct bio *bio) { struct page *page = bio_first_page_all(bio); @@ -114,7 +66,6 @@ static void end_swap_bio_read(struct bio *bio) } SetPageUptodate(page); - swap_slot_free_notify(page); out: unlock_page(page); WRITE_ONCE(bio->bi_private, NULL); @@ -385,7 +336,7 @@ int swap_readpage(struct page *page, bool synchronous) struct file *swap_file = sis->swap_file; struct address_space *mapping = swap_file->f_mapping; - ret = mapping->a_ops->readpage(swap_file, page); + ret = mapping->a_ops->read_folio(swap_file, page_folio(page)); if (!ret) count_vm_event(PSWPIN); goto out; @@ -394,11 +345,6 @@ int swap_readpage(struct page *page, bool synchronous) if (sis->flags & SWP_SYNCHRONOUS_IO) { ret = bdev_read_page(sis->bdev, swap_page_sector(page), page); if (!ret) { - if (trylock_page(page)) { - swap_slot_free_notify(page); - unlock_page(page); - } - count_vm_event(PSWPIN); goto out; } @@ -414,7 +360,6 @@ int swap_readpage(struct page *page, bool synchronous) * attempt to access it in the page fault retry time check. */ if (synchronous) { - bio->bi_opf |= REQ_POLLED; get_task_struct(current); bio->bi_private = current; } @@ -426,8 +371,7 @@ int swap_readpage(struct page *page, bool synchronous) if (!READ_ONCE(bio->bi_private)) break; - if (!bio_poll(bio, NULL, 0)) - blk_io_schedule(); + blk_io_schedule(); } __set_current_state(TASK_RUNNING); bio_put(bio); diff --git a/mm/page_owner.c b/mm/page_owner.c index fb3a05fdebdb..2743062e92c2 100644 --- a/mm/page_owner.c +++ b/mm/page_owner.c @@ -45,7 +45,12 @@ static void init_early_allocated_pages(void); static int __init early_page_owner_param(char *buf) { - return kstrtobool(buf, &page_owner_enabled); + int ret = kstrtobool(buf, &page_owner_enabled); + + if (page_owner_enabled) + stack_depot_want_early_init(); + + return ret; } early_param("page_owner", early_page_owner_param); @@ -83,8 +88,6 @@ static __init void init_page_owner(void) if (!page_owner_enabled) return; - stack_depot_init(); - register_dummy_stack(); register_failure_stack(); register_early_stack(); diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c index 1187f9c1ec5b..14a5cda73dee 100644 --- a/mm/page_vma_mapped.c +++ b/mm/page_vma_mapped.c @@ -163,7 +163,8 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw) return not_found(pvmw); if (unlikely(is_vm_hugetlb_page(vma))) { - unsigned long size = pvmw->nr_pages * PAGE_SIZE; + struct hstate *hstate = hstate_vma(vma); + unsigned long size = huge_page_size(hstate); /* The only possible mapping was handled on last iteration */ if (pvmw->pte) return not_found(pvmw); @@ -173,8 +174,7 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw) if (!pvmw->pte) return false; - pvmw->ptl = huge_pte_lockptr(size_to_hstate(size), mm, - pvmw->pte); + pvmw->ptl = huge_pte_lockptr(hstate, mm, pvmw->pte); spin_lock(pvmw->ptl); if (!check_pte(pvmw)) return not_found(pvmw); diff --git a/mm/readahead.c b/mm/readahead.c index 8e3775829513..b78921b54754 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -15,7 +15,7 @@ * explicitly requested by the application. Readahead only ever * attempts to read folios that are not yet in the page cache. If a * folio is present but not up-to-date, readahead will not try to read - * it. In that case a simple ->readpage() will be requested. + * it. In that case a simple ->read_folio() will be requested. * * Readahead is triggered when an application read request (whether a * system call or a page fault) finds that the requested folio is not in @@ -78,7 +78,7 @@ * address space operation, for which mpage_readahead() is a canonical * implementation. ->readahead() should normally initiate reads on all * folios, but may fail to read any or all folios without causing an I/O - * error. The page cache reading code will issue a ->readpage() request + * error. The page cache reading code will issue a ->read_folio() request * for any folio which ->readahead() did not read, and only an error * from this will be final. * @@ -110,9 +110,10 @@ * were not fetched with readahead_folio(). This will allow a * subsequent synchronous readahead request to try them again. If they * are left in the page cache, then they will be read individually using - * ->readpage() which may be less efficient. + * ->read_folio() which may be less efficient. */ +#include <linux/blkdev.h> #include <linux/kernel.h> #include <linux/dax.h> #include <linux/gfp.h> @@ -145,7 +146,7 @@ EXPORT_SYMBOL_GPL(file_ra_state_init); static void read_pages(struct readahead_control *rac) { const struct address_space_operations *aops = rac->mapping->a_ops; - struct page *page; + struct folio *folio; struct blk_plug plug; if (!readahead_count(rac)) @@ -156,24 +157,23 @@ static void read_pages(struct readahead_control *rac) if (aops->readahead) { aops->readahead(rac); /* - * Clean up the remaining pages. The sizes in ->ra + * Clean up the remaining folios. The sizes in ->ra * may be used to size the next readahead, so make sure * they accurately reflect what happened. */ - while ((page = readahead_page(rac))) { - rac->ra->size -= 1; - if (rac->ra->async_size > 0) { - rac->ra->async_size -= 1; - delete_from_page_cache(page); + while ((folio = readahead_folio(rac)) != NULL) { + unsigned long nr = folio_nr_pages(folio); + + rac->ra->size -= nr; + if (rac->ra->async_size >= nr) { + rac->ra->async_size -= nr; + filemap_remove_folio(folio); } - unlock_page(page); - put_page(page); + folio_unlock(folio); } } else { - while ((page = readahead_page(rac))) { - aops->readpage(rac->file, page); - put_page(page); - } + while ((folio = readahead_folio(rac)) != NULL) + aops->read_folio(rac->file, folio); } blk_finish_plug(&plug); @@ -254,8 +254,8 @@ void page_cache_ra_unbounded(struct readahead_control *ractl, } /* - * Now start the IO. We ignore I/O errors - if the page is not - * uptodate then the caller will launch readpage again, and + * Now start the IO. We ignore I/O errors - if the folio is not + * uptodate then the caller will launch read_folio again, and * will then handle the error. */ read_pages(ractl); @@ -303,7 +303,7 @@ void force_page_cache_ra(struct readahead_control *ractl, struct backing_dev_info *bdi = inode_to_bdi(mapping->host); unsigned long max_pages, index; - if (unlikely(!mapping->a_ops->readpage && !mapping->a_ops->readahead)) + if (unlikely(!mapping->a_ops->read_folio && !mapping->a_ops->readahead)) return; /* @@ -474,7 +474,8 @@ static inline int ra_alloc_folio(struct readahead_control *ractl, pgoff_t index, if (!folio) return -ENOMEM; - if (mark - index < (1UL << order)) + mark = round_up(mark, 1UL << order); + if (index == mark) folio_set_readahead(folio); err = filemap_add_folio(ractl->mapping, folio, index, gfp); if (err) @@ -555,8 +556,9 @@ static void ondemand_readahead(struct readahead_control *ractl, struct file_ra_state *ra = ractl->ra; unsigned long max_pages = ra->ra_pages; unsigned long add_pages; - unsigned long index = readahead_index(ractl); - pgoff_t prev_index; + pgoff_t index = readahead_index(ractl); + pgoff_t expected, prev_index; + unsigned int order = folio ? folio_order(folio) : 0; /* * If the request exceeds the readahead window, allow the read to @@ -575,8 +577,9 @@ static void ondemand_readahead(struct readahead_control *ractl, * It's the expected callback index, assume sequential access. * Ramp up sizes, and push forward the readahead window. */ - if ((index == (ra->start + ra->size - ra->async_size) || - index == (ra->start + ra->size))) { + expected = round_up(ra->start + ra->size - ra->async_size, + 1UL << order); + if (index == expected || index == (ra->start + ra->size)) { ra->start += ra->size; ra->size = get_next_ra_size(ra, max_pages); ra->async_size = ra->size; @@ -662,7 +665,7 @@ readit: } ractl->_index = ra->start; - page_cache_ra_order(ractl, ra, folio ? folio_order(folio) : 0); + page_cache_ra_order(ractl, ra, order); } void page_cache_sync_ra(struct readahead_control *ractl, diff --git a/mm/secretmem.c b/mm/secretmem.c index 098638d3b8a4..206ed6b40c1d 100644 --- a/mm/secretmem.c +++ b/mm/secretmem.c @@ -145,19 +145,35 @@ static int secretmem_migratepage(struct address_space *mapping, return -EBUSY; } -static void secretmem_freepage(struct page *page) +static void secretmem_free_folio(struct folio *folio) { - set_direct_map_default_noflush(page); - clear_highpage(page); + set_direct_map_default_noflush(&folio->page); + folio_zero_segment(folio, 0, folio_size(folio)); } const struct address_space_operations secretmem_aops = { .dirty_folio = noop_dirty_folio, - .freepage = secretmem_freepage, + .free_folio = secretmem_free_folio, .migratepage = secretmem_migratepage, .isolate_page = secretmem_isolate_page, }; +static int secretmem_setattr(struct user_namespace *mnt_userns, + struct dentry *dentry, struct iattr *iattr) +{ + struct inode *inode = d_inode(dentry); + unsigned int ia_valid = iattr->ia_valid; + + if ((ia_valid & ATTR_SIZE) && inode->i_size) + return -EINVAL; + + return simple_setattr(mnt_userns, dentry, iattr); +} + +static const struct inode_operations secretmem_iops = { + .setattr = secretmem_setattr, +}; + static struct vfsmount *secretmem_mnt; static struct file *secretmem_file_create(unsigned long flags) @@ -177,6 +193,7 @@ static struct file *secretmem_file_create(unsigned long flags) mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER); mapping_set_unevictable(inode->i_mapping); + inode->i_op = &secretmem_iops; inode->i_mapping->a_ops = &secretmem_aops; /* pretend we are a normal file with zero size */ diff --git a/mm/shmem.c b/mm/shmem.c index 529c9ad3e926..f3e8de8ff75c 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -2426,7 +2426,7 @@ static int shmem_initxattrs(struct inode *, const struct xattr *, void *); static int shmem_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, + loff_t pos, unsigned len, struct page **pagep, void **fsdata) { struct inode *inode = mapping->host; @@ -2513,7 +2513,6 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to) pgoff_t end_index; unsigned long nr, ret; loff_t i_size = i_size_read(inode); - bool got_page; end_index = i_size >> PAGE_SHIFT; if (index > end_index) @@ -2570,24 +2569,34 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to) */ if (!offset) mark_page_accessed(page); - got_page = true; + /* + * Ok, we have the page, and it's up-to-date, so + * now we can copy it to user space... + */ + ret = copy_page_to_iter(page, offset, nr, to); + put_page(page); + + } else if (iter_is_iovec(to)) { + /* + * Copy to user tends to be so well optimized, but + * clear_user() not so much, that it is noticeably + * faster to copy the zero page instead of clearing. + */ + ret = copy_page_to_iter(ZERO_PAGE(0), offset, nr, to); } else { - page = ZERO_PAGE(0); - got_page = false; + /* + * But submitting the same page twice in a row to + * splice() - or others? - can result in confusion: + * so don't attempt that optimization on pipes etc. + */ + ret = iov_iter_zero(nr, to); } - /* - * Ok, we have the page, and it's up-to-date, so - * now we can copy it to user space... - */ - ret = copy_page_to_iter(page, offset, nr, to); retval += ret; offset += ret; index += offset >> PAGE_SHIFT; offset &= ~PAGE_MASK; - if (got_page) - put_page(page); if (!iov_iter_count(to)) break; if (ret < nr) { @@ -4153,7 +4162,7 @@ int shmem_zero_setup(struct vm_area_struct *vma) * * This behaves as a tmpfs "read_cache_page_gfp(mapping, index, gfp)", * with any new page allocations done using the specified allocation flags. - * But read_cache_page_gfp() uses the ->readpage() method: which does not + * But read_cache_page_gfp() uses the ->read_folio() method: which does not * suit tmpfs, since it may have pages in swapcache, and needs to find those * for itself; although drivers/gpu/drm i915 and ttm rely upon this support. * diff --git a/mm/slab.c b/mm/slab.c index b04e40078bdf..a301f266efd1 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -619,18 +619,6 @@ static inline int cache_free_alien(struct kmem_cache *cachep, void *objp) return 0; } -static inline void *alternate_node_alloc(struct kmem_cache *cachep, - gfp_t flags) -{ - return NULL; -} - -static inline void *____cache_alloc_node(struct kmem_cache *cachep, - gfp_t flags, int nodeid) -{ - return NULL; -} - static inline gfp_t gfp_exact_node(gfp_t flags) { return flags & ~__GFP_NOFAIL; @@ -638,9 +626,6 @@ static inline gfp_t gfp_exact_node(gfp_t flags) #else /* CONFIG_NUMA */ -static void *____cache_alloc_node(struct kmem_cache *, gfp_t, int); -static void *alternate_node_alloc(struct kmem_cache *, gfp_t); - static struct alien_cache *__alloc_alien_cache(int node, int entries, int batch, gfp_t gfp) { @@ -796,7 +781,7 @@ static inline int cache_free_alien(struct kmem_cache *cachep, void *objp) int slab_node = slab_nid(virt_to_slab(objp)); int node = numa_mem_id(); /* - * Make sure we are not freeing a object from another node to the array + * Make sure we are not freeing an object from another node to the array * cache on this cpu. */ if (likely(node == slab_node)) @@ -847,7 +832,7 @@ static int init_cache_node(struct kmem_cache *cachep, int node, gfp_t gfp) /* * The kmem_cache_nodes don't come and go as CPUs - * come and go. slab_mutex is sufficient + * come and go. slab_mutex provides sufficient * protection here. */ cachep->node[node] = n; @@ -860,7 +845,7 @@ static int init_cache_node(struct kmem_cache *cachep, int node, gfp_t gfp) * Allocates and initializes node for a node on each slab cache, used for * either memory or cpu hotplug. If memory is being hot-added, the kmem_cache_node * will be allocated off-node since memory is not yet online for the new node. - * When hotplugging memory or a cpu, existing node are not replaced if + * When hotplugging memory or a cpu, existing nodes are not replaced if * already in use. * * Must hold slab_mutex. @@ -1061,7 +1046,7 @@ int slab_prepare_cpu(unsigned int cpu) * offline. * * Even if all the cpus of a node are down, we don't free the - * kmem_cache_node of any cache. This to avoid a race between cpu_down, and + * kmem_cache_node of any cache. This is to avoid a race between cpu_down, and * a kmalloc allocation from another cpu for memory from the node of * the cpu going down. The kmem_cache_node structure is usually allocated from * kmem_cache_create() and gets destroyed at kmem_cache_destroy(). @@ -1905,7 +1890,7 @@ static bool set_on_slab_cache(struct kmem_cache *cachep, * @flags: SLAB flags * * Returns a ptr to the cache on success, NULL on failure. - * Cannot be called within a int, but can be interrupted. + * Cannot be called within an int, but can be interrupted. * The @ctor is run when new pages are allocated by the cache. * * The flags are @@ -3056,6 +3041,8 @@ out: } #ifdef CONFIG_NUMA +static void *____cache_alloc_node(struct kmem_cache *, gfp_t, int); + /* * Try allocating on another node if PFA_SPREAD_SLAB is a mempolicy is set. * @@ -3151,7 +3138,7 @@ retry: } /* - * A interface to enable slab creation on nodeid + * An interface to enable slab creation on nodeid */ static void *____cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid) @@ -3665,7 +3652,7 @@ EXPORT_SYMBOL(__kmalloc_node_track_caller); #endif /* CONFIG_NUMA */ #ifdef CONFIG_PRINTK -void kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab) +void __kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab) { struct kmem_cache *cachep; unsigned int objnr; diff --git a/mm/slab.h b/mm/slab.h index fd7ae2024897..db9fb5c8dae7 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -331,7 +331,7 @@ static inline slab_flags_t kmem_cache_flags(unsigned int object_size, SLAB_ACCOUNT) #elif defined(CONFIG_SLUB) #define SLAB_CACHE_FLAGS (SLAB_NOLEAKTRACE | SLAB_RECLAIM_ACCOUNT | \ - SLAB_TEMPORARY | SLAB_ACCOUNT) + SLAB_TEMPORARY | SLAB_ACCOUNT | SLAB_NO_USER_FLAGS) #else #define SLAB_CACHE_FLAGS (SLAB_NOLEAKTRACE) #endif @@ -350,7 +350,8 @@ static inline slab_flags_t kmem_cache_flags(unsigned int object_size, SLAB_NOLEAKTRACE | \ SLAB_RECLAIM_ACCOUNT | \ SLAB_TEMPORARY | \ - SLAB_ACCOUNT) + SLAB_ACCOUNT | \ + SLAB_NO_USER_FLAGS) bool __kmem_cache_empty(struct kmem_cache *); int __kmem_cache_shutdown(struct kmem_cache *); @@ -868,7 +869,7 @@ struct kmem_obj_info { void *kp_stack[KS_ADDRS_COUNT]; void *kp_free_stack[KS_ADDRS_COUNT]; }; -void kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab); +void __kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab); #endif #ifdef CONFIG_HAVE_HARDENED_USERCOPY_ALLOCATOR diff --git a/mm/slab_common.c b/mm/slab_common.c index 6ee64d6208b3..d1f3133847ad 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -24,6 +24,7 @@ #include <asm/tlbflush.h> #include <asm/page.h> #include <linux/memcontrol.h> +#include <linux/stackdepot.h> #define CREATE_TRACE_POINTS #include <trace/events/kmem.h> @@ -314,9 +315,13 @@ kmem_cache_create_usercopy(const char *name, * If no slub_debug was enabled globally, the static key is not yet * enabled by setup_slub_debug(). Enable it if the cache is being * created with any of the debugging flags passed explicitly. + * It's also possible that this is the first cache created with + * SLAB_STORE_USER and we should init stack_depot for it. */ if (flags & SLAB_DEBUG_FLAGS) static_branch_enable(&slub_debug_enabled); + if (flags & SLAB_STORE_USER) + stack_depot_init(); #endif mutex_lock(&slab_mutex); @@ -555,6 +560,13 @@ bool kmem_valid_obj(void *object) } EXPORT_SYMBOL_GPL(kmem_valid_obj); +static void kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab) +{ + if (__kfence_obj_info(kpp, object, slab)) + return; + __kmem_obj_info(kpp, object, slab); +} + /** * kmem_dump_obj - Print available slab provenance information * @object: slab object for which to find provenance information. @@ -590,6 +602,8 @@ void kmem_dump_obj(void *object) pr_cont(" slab%s %s", cp, kp.kp_slab_cache->name); else pr_cont(" slab%s", cp); + if (is_kfence_address(object)) + pr_cont(" (kfence)"); if (kp.kp_objp) pr_cont(" start %px", kp.kp_objp); if (kp.kp_data_offset) @@ -849,6 +863,8 @@ new_kmalloc_cache(int idx, enum kmalloc_cache_type type, slab_flags_t flags) return; } flags |= SLAB_ACCOUNT; + } else if (IS_ENABLED(CONFIG_ZONE_DMA) && (type == KMALLOC_DMA)) { + flags |= SLAB_CACHE_DMA; } kmalloc_caches[type][idx] = create_kmalloc_cache( @@ -877,7 +893,7 @@ void __init create_kmalloc_caches(slab_flags_t flags) /* * Including KMALLOC_CGROUP if CONFIG_MEMCG_KMEM defined */ - for (type = KMALLOC_NORMAL; type <= KMALLOC_RECLAIM; type++) { + for (type = KMALLOC_NORMAL; type < NR_KMALLOC_TYPES; type++) { for (i = KMALLOC_SHIFT_LOW; i <= KMALLOC_SHIFT_HIGH; i++) { if (!kmalloc_caches[type][i]) new_kmalloc_cache(i, type, flags); @@ -898,20 +914,6 @@ void __init create_kmalloc_caches(slab_flags_t flags) /* Kmalloc array is now usable */ slab_state = UP; - -#ifdef CONFIG_ZONE_DMA - for (i = 0; i <= KMALLOC_SHIFT_HIGH; i++) { - struct kmem_cache *s = kmalloc_caches[KMALLOC_NORMAL][i]; - - if (s) { - kmalloc_caches[KMALLOC_DMA][i] = create_kmalloc_cache( - kmalloc_info[i].name[KMALLOC_DMA], - kmalloc_info[i].size, - SLAB_CACHE_DMA | flags, 0, - kmalloc_info[i].size); - } - } -#endif } #endif /* !CONFIG_SLOB */ diff --git a/mm/slob.c b/mm/slob.c index dfa6808dff36..40ea6e2d4ccd 100644 --- a/mm/slob.c +++ b/mm/slob.c @@ -463,7 +463,7 @@ out: } #ifdef CONFIG_PRINTK -void kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab) +void __kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab) { kpp->kp_ptr = object; kpp->kp_slab = slab; diff --git a/mm/slub.c b/mm/slub.c index 74d92aa4a3a2..e5535020e0fd 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -26,6 +26,7 @@ #include <linux/cpuset.h> #include <linux/mempolicy.h> #include <linux/ctype.h> +#include <linux/stackdepot.h> #include <linux/debugobjects.h> #include <linux/kallsyms.h> #include <linux/kfence.h> @@ -37,6 +38,7 @@ #include <linux/memcontrol.h> #include <linux/random.h> #include <kunit/test.h> +#include <linux/sort.h> #include <linux/debugfs.h> #include <trace/events/kmem.h> @@ -264,8 +266,8 @@ static inline bool kmem_cache_has_cpu_partial(struct kmem_cache *s) #define TRACK_ADDRS_COUNT 16 struct track { unsigned long addr; /* Called from address */ -#ifdef CONFIG_STACKTRACE - unsigned long addrs[TRACK_ADDRS_COUNT]; /* Called from address */ +#ifdef CONFIG_STACKDEPOT + depot_stack_handle_t handle; #endif int cpu; /* Was running on cpu */ int pid; /* Pid context */ @@ -724,57 +726,51 @@ static struct track *get_track(struct kmem_cache *s, void *object, return kasan_reset_tag(p + alloc); } -static void set_track(struct kmem_cache *s, void *object, +static void noinline set_track(struct kmem_cache *s, void *object, enum track_item alloc, unsigned long addr) { struct track *p = get_track(s, object, alloc); - if (addr) { -#ifdef CONFIG_STACKTRACE - unsigned int nr_entries; - - metadata_access_enable(); - nr_entries = stack_trace_save(kasan_reset_tag(p->addrs), - TRACK_ADDRS_COUNT, 3); - metadata_access_disable(); +#ifdef CONFIG_STACKDEPOT + unsigned long entries[TRACK_ADDRS_COUNT]; + unsigned int nr_entries; - if (nr_entries < TRACK_ADDRS_COUNT) - p->addrs[nr_entries] = 0; + nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 3); + p->handle = stack_depot_save(entries, nr_entries, GFP_NOWAIT); #endif - p->addr = addr; - p->cpu = smp_processor_id(); - p->pid = current->pid; - p->when = jiffies; - } else { - memset(p, 0, sizeof(struct track)); - } + + p->addr = addr; + p->cpu = smp_processor_id(); + p->pid = current->pid; + p->when = jiffies; } static void init_tracking(struct kmem_cache *s, void *object) { + struct track *p; + if (!(s->flags & SLAB_STORE_USER)) return; - set_track(s, object, TRACK_FREE, 0UL); - set_track(s, object, TRACK_ALLOC, 0UL); + p = get_track(s, object, TRACK_ALLOC); + memset(p, 0, 2*sizeof(struct track)); } static void print_track(const char *s, struct track *t, unsigned long pr_time) { + depot_stack_handle_t handle __maybe_unused; + if (!t->addr) return; pr_err("%s in %pS age=%lu cpu=%u pid=%d\n", s, (void *)t->addr, pr_time - t->when, t->cpu, t->pid); -#ifdef CONFIG_STACKTRACE - { - int i; - for (i = 0; i < TRACK_ADDRS_COUNT; i++) - if (t->addrs[i]) - pr_err("\t%pS\n", (void *)t->addrs[i]); - else - break; - } +#ifdef CONFIG_STACKDEPOT + handle = READ_ONCE(t->handle); + if (handle) + stack_depot_print(handle); + else + pr_err("object allocation/free stack trace missing\n"); #endif } @@ -1021,7 +1017,7 @@ static int check_pad_bytes(struct kmem_cache *s, struct slab *slab, u8 *p) } /* Check the pad bytes at the end of a slab page */ -static int slab_pad_check(struct kmem_cache *s, struct slab *slab) +static void slab_pad_check(struct kmem_cache *s, struct slab *slab) { u8 *start; u8 *fault; @@ -1031,21 +1027,21 @@ static int slab_pad_check(struct kmem_cache *s, struct slab *slab) int remainder; if (!(s->flags & SLAB_POISON)) - return 1; + return; start = slab_address(slab); length = slab_size(slab); end = start + length; remainder = length % s->size; if (!remainder) - return 1; + return; pad = end - remainder; metadata_access_enable(); fault = memchr_inv(kasan_reset_tag(pad), POISON_INUSE, remainder); metadata_access_disable(); if (!fault) - return 1; + return; while (end > fault && end[-1] == POISON_INUSE) end--; @@ -1054,7 +1050,6 @@ static int slab_pad_check(struct kmem_cache *s, struct slab *slab) print_section(KERN_ERR, "Padding ", pad, remainder); restore_bytes(s, "slab padding", POISON_INUSE, fault, end); - return 0; } static int check_object(struct kmem_cache *s, struct slab *slab, @@ -1268,8 +1263,7 @@ static inline void dec_slabs_node(struct kmem_cache *s, int node, int objects) } /* Object debug checks for alloc/free paths */ -static void setup_object_debug(struct kmem_cache *s, struct slab *slab, - void *object) +static void setup_object_debug(struct kmem_cache *s, void *object) { if (!kmem_cache_debug_flags(s, SLAB_STORE_USER|SLAB_RED_ZONE|__OBJECT_POISON)) return; @@ -1534,6 +1528,8 @@ static int __init setup_slub_debug(char *str) global_slub_debug_changed = true; } else { slab_list_specified = true; + if (flags & SLAB_STORE_USER) + stack_depot_want_early_init(); } } @@ -1551,6 +1547,8 @@ static int __init setup_slub_debug(char *str) } out: slub_debug = global_flags; + if (slub_debug & SLAB_STORE_USER) + stack_depot_want_early_init(); if (slub_debug != 0 || slub_debug_string) static_branch_enable(&slub_debug_enabled); else @@ -1584,6 +1582,9 @@ slab_flags_t kmem_cache_flags(unsigned int object_size, slab_flags_t block_flags; slab_flags_t slub_debug_local = slub_debug; + if (flags & SLAB_NO_USER_FLAGS) + return flags; + /* * If the slab cache is for debugging (e.g. kmemleak) then * don't store user (stack trace) information by default, @@ -1628,8 +1629,7 @@ slab_flags_t kmem_cache_flags(unsigned int object_size, return flags | slub_debug_local; } #else /* !CONFIG_SLUB_DEBUG */ -static inline void setup_object_debug(struct kmem_cache *s, - struct slab *slab, void *object) {} +static inline void setup_object_debug(struct kmem_cache *s, void *object) {} static inline void setup_slab_debug(struct kmem_cache *s, struct slab *slab, void *addr) {} @@ -1641,8 +1641,7 @@ static inline int free_debug_processing( void *head, void *tail, int bulk_cnt, unsigned long addr) { return 0; } -static inline int slab_pad_check(struct kmem_cache *s, struct slab *slab) - { return 1; } +static inline void slab_pad_check(struct kmem_cache *s, struct slab *slab) {} static inline int check_object(struct kmem_cache *s, struct slab *slab, void *object, u8 val) { return 1; } static inline void add_full(struct kmem_cache *s, struct kmem_cache_node *n, @@ -1772,10 +1771,9 @@ static inline bool slab_free_freelist_hook(struct kmem_cache *s, return *head != NULL; } -static void *setup_object(struct kmem_cache *s, struct slab *slab, - void *object) +static void *setup_object(struct kmem_cache *s, void *object) { - setup_object_debug(s, slab, object); + setup_object_debug(s, object); object = kasan_init_slab_obj(s, object); if (unlikely(s->ctor)) { kasan_unpoison_object_data(s, object); @@ -1894,13 +1892,13 @@ static bool shuffle_freelist(struct kmem_cache *s, struct slab *slab) /* First entry is used as the base of the freelist */ cur = next_freelist_entry(s, slab, &pos, start, page_limit, freelist_count); - cur = setup_object(s, slab, cur); + cur = setup_object(s, cur); slab->freelist = cur; for (idx = 1; idx < slab->objects; idx++) { next = next_freelist_entry(s, slab, &pos, start, page_limit, freelist_count); - next = setup_object(s, slab, next); + next = setup_object(s, next); set_freepointer(s, cur, next); cur = next; } @@ -1939,7 +1937,7 @@ static struct slab *allocate_slab(struct kmem_cache *s, gfp_t flags, int node) */ alloc_gfp = (flags | __GFP_NOWARN | __GFP_NORETRY) & ~__GFP_NOFAIL; if ((alloc_gfp & __GFP_DIRECT_RECLAIM) && oo_order(oo) > oo_order(s->min)) - alloc_gfp = (alloc_gfp | __GFP_NOMEMALLOC) & ~(__GFP_RECLAIM|__GFP_NOFAIL); + alloc_gfp = (alloc_gfp | __GFP_NOMEMALLOC) & ~__GFP_RECLAIM; slab = alloc_slab_page(alloc_gfp, node, oo); if (unlikely(!slab)) { @@ -1971,11 +1969,11 @@ static struct slab *allocate_slab(struct kmem_cache *s, gfp_t flags, int node) if (!shuffle) { start = fixup_red_left(s, start); - start = setup_object(s, slab, start); + start = setup_object(s, start); slab->freelist = start; for (idx = 0, p = start; idx < slab->objects - 1; idx++) { next = p + s->size; - next = setup_object(s, slab, next); + next = setup_object(s, next); set_freepointer(s, p, next); p = next; } @@ -2910,7 +2908,6 @@ redo: */ if (!node_isset(node, slab_nodes)) { node = NUMA_NO_NODE; - goto redo; } else { stat(s, ALLOC_NODE_MISMATCH); goto deactivate_slab; @@ -4165,8 +4162,6 @@ static int calculate_sizes(struct kmem_cache *s) */ s->oo = oo_make(order, size); s->min = oo_make(get_order(size), size); - if (oo_objects(s->oo) > oo_objects(s->max)) - s->max = s->oo; return !!oo_objects(s->oo); } @@ -4312,7 +4307,7 @@ int __kmem_cache_shutdown(struct kmem_cache *s) } #ifdef CONFIG_PRINTK -void kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab) +void __kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab) { void *base; int __maybe_unused i; @@ -4344,18 +4339,26 @@ void kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab) objp = fixup_red_left(s, objp); trackp = get_track(s, objp, TRACK_ALLOC); kpp->kp_ret = (void *)trackp->addr; -#ifdef CONFIG_STACKTRACE - for (i = 0; i < KS_ADDRS_COUNT && i < TRACK_ADDRS_COUNT; i++) { - kpp->kp_stack[i] = (void *)trackp->addrs[i]; - if (!kpp->kp_stack[i]) - break; - } +#ifdef CONFIG_STACKDEPOT + { + depot_stack_handle_t handle; + unsigned long *entries; + unsigned int nr_entries; - trackp = get_track(s, objp, TRACK_FREE); - for (i = 0; i < KS_ADDRS_COUNT && i < TRACK_ADDRS_COUNT; i++) { - kpp->kp_free_stack[i] = (void *)trackp->addrs[i]; - if (!kpp->kp_free_stack[i]) - break; + handle = READ_ONCE(trackp->handle); + if (handle) { + nr_entries = stack_depot_fetch(handle, &entries); + for (i = 0; i < KS_ADDRS_COUNT && i < nr_entries; i++) + kpp->kp_stack[i] = (void *)entries[i]; + } + + trackp = get_track(s, objp, TRACK_FREE); + handle = READ_ONCE(trackp->handle); + if (handle) { + nr_entries = stack_depot_fetch(handle, &entries); + for (i = 0; i < KS_ADDRS_COUNT && i < nr_entries; i++) + kpp->kp_free_stack[i] = (void *)entries[i]; + } } #endif #endif @@ -5057,6 +5060,7 @@ EXPORT_SYMBOL(validate_slab_cache); */ struct location { + depot_stack_handle_t handle; unsigned long count; unsigned long addr; long long sum_time; @@ -5109,9 +5113,13 @@ static int add_location(struct loc_track *t, struct kmem_cache *s, { long start, end, pos; struct location *l; - unsigned long caddr; + unsigned long caddr, chandle; unsigned long age = jiffies - track->when; + depot_stack_handle_t handle = 0; +#ifdef CONFIG_STACKDEPOT + handle = READ_ONCE(track->handle); +#endif start = -1; end = t->count; @@ -5126,7 +5134,8 @@ static int add_location(struct loc_track *t, struct kmem_cache *s, break; caddr = t->loc[pos].addr; - if (track->addr == caddr) { + chandle = t->loc[pos].handle; + if ((track->addr == caddr) && (handle == chandle)) { l = &t->loc[pos]; l->count++; @@ -5151,6 +5160,8 @@ static int add_location(struct loc_track *t, struct kmem_cache *s, if (track->addr < caddr) end = pos; + else if (track->addr == caddr && handle < chandle) + end = pos; else start = pos; } @@ -5173,6 +5184,7 @@ static int add_location(struct loc_track *t, struct kmem_cache *s, l->max_time = age; l->min_pid = track->pid; l->max_pid = track->pid; + l->handle = handle; cpumask_clear(to_cpumask(l->cpus)); cpumask_set_cpu(track->cpu, to_cpumask(l->cpus)); nodes_clear(l->nodes); @@ -6082,6 +6094,21 @@ static int slab_debugfs_show(struct seq_file *seq, void *v) seq_printf(seq, " nodes=%*pbl", nodemask_pr_args(&l->nodes)); +#ifdef CONFIG_STACKDEPOT + { + depot_stack_handle_t handle; + unsigned long *entries; + unsigned int nr_entries, j; + + handle = READ_ONCE(l->handle); + if (handle) { + nr_entries = stack_depot_fetch(handle, &entries); + seq_puts(seq, "\n"); + for (j = 0; j < nr_entries; j++) + seq_printf(seq, " %pS\n", (void *)entries[j]); + } + } +#endif seq_puts(seq, "\n"); } @@ -6106,6 +6133,17 @@ static void *slab_debugfs_next(struct seq_file *seq, void *v, loff_t *ppos) return NULL; } +static int cmp_loc_by_count(const void *a, const void *b, const void *data) +{ + struct location *loc1 = (struct location *)a; + struct location *loc2 = (struct location *)b; + + if (loc1->count > loc2->count) + return -1; + else + return 1; +} + static void *slab_debugfs_start(struct seq_file *seq, loff_t *ppos) { struct loc_track *t = seq->private; @@ -6167,6 +6205,10 @@ static int slab_debug_trace_open(struct inode *inode, struct file *filep) spin_unlock_irqrestore(&n->list_lock, flags); } + /* Sort locations by count */ + sort_r(t->loc, t->count, sizeof(struct location), + cmp_loc_by_count, NULL, NULL); + bitmap_free(obj_map); return 0; } diff --git a/mm/swapfile.c b/mm/swapfile.c index 63c61f8b2611..6aec1b24f440 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -6,6 +6,7 @@ * Swap reorganised 29.12.95, Stephen Tweedie */ +#include <linux/blkdev.h> #include <linux/mm.h> #include <linux/sched/mm.h> #include <linux/sched/task.h> @@ -179,7 +180,7 @@ static int discard_swap(struct swap_info_struct *si) nr_blocks = ((sector_t)se->nr_pages - 1) << (PAGE_SHIFT - 9); if (nr_blocks) { err = blkdev_issue_discard(si->bdev, start_block, - nr_blocks, GFP_KERNEL, 0); + nr_blocks, GFP_KERNEL); if (err) return err; cond_resched(); @@ -190,7 +191,7 @@ static int discard_swap(struct swap_info_struct *si) nr_blocks = (sector_t)se->nr_pages << (PAGE_SHIFT - 9); err = blkdev_issue_discard(si->bdev, start_block, - nr_blocks, GFP_KERNEL, 0); + nr_blocks, GFP_KERNEL); if (err) break; @@ -254,7 +255,7 @@ static void discard_swap_cluster(struct swap_info_struct *si, start_block <<= PAGE_SHIFT - 9; nr_blocks <<= PAGE_SHIFT - 9; if (blkdev_issue_discard(si->bdev, start_block, - nr_blocks, GFP_NOIO, 0)) + nr_blocks, GFP_NOIO)) break; se = next_se(se); @@ -2466,7 +2467,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) if (p->flags & SWP_CONTINUED) free_swap_count_continuations(p); - if (!p->bdev || !blk_queue_nonrot(bdev_get_queue(p->bdev))) + if (!p->bdev || !bdev_nonrot(p->bdev)) atomic_dec(&nr_rotate_swap); mutex_lock(&swapon_mutex); @@ -2761,7 +2762,7 @@ static int claim_swapfile(struct swap_info_struct *p, struct inode *inode) * write only restriction. Hence zoned block devices are not * suitable for swapping. Disallow them here. */ - if (blk_queue_is_zoned(p->bdev->bd_disk->queue)) + if (bdev_is_zoned(p->bdev)) return -EINVAL; p->flags |= SWP_BLKDEV; } else if (S_ISREG(inode->i_mode)) { @@ -2957,20 +2958,6 @@ static int setup_swap_map_and_extents(struct swap_info_struct *p, return nr_extents; } -/* - * Helper to sys_swapon determining if a given swap - * backing device queue supports DISCARD operations. - */ -static bool swap_discardable(struct swap_info_struct *si) -{ - struct request_queue *q = bdev_get_queue(si->bdev); - - if (!blk_queue_discard(q)) - return false; - - return true; -} - SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) { struct swap_info_struct *p; @@ -3041,7 +3028,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) /* * Read the swap header. */ - if (!mapping->a_ops->readpage) { + if (!mapping->a_ops->read_folio) { error = -EINVAL; goto bad_swap_unlock_inode; } @@ -3065,13 +3052,13 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) goto bad_swap_unlock_inode; } - if (p->bdev && blk_queue_stable_writes(p->bdev->bd_disk->queue)) + if (p->bdev && bdev_stable_writes(p->bdev)) p->flags |= SWP_STABLE_WRITES; if (p->bdev && p->bdev->bd_disk->fops->rw_page) p->flags |= SWP_SYNCHRONOUS_IO; - if (p->bdev && blk_queue_nonrot(bdev_get_queue(p->bdev))) { + if (p->bdev && bdev_nonrot(p->bdev)) { int cpu; unsigned long ci, nr_cluster; @@ -3132,7 +3119,8 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) sizeof(long), GFP_KERNEL); - if (p->bdev && (swap_flags & SWAP_FLAG_DISCARD) && swap_discardable(p)) { + if ((swap_flags & SWAP_FLAG_DISCARD) && + p->bdev && bdev_max_discard_sectors(p->bdev)) { /* * When discard is enabled for swap with no particular * policy flagged, we set all swap discard flags here in diff --git a/mm/usercopy.c b/mm/usercopy.c index 2c235d5c2364..baeacc735b83 100644 --- a/mm/usercopy.c +++ b/mm/usercopy.c @@ -17,6 +17,7 @@ #include <linux/sched/task.h> #include <linux/sched/task_stack.h> #include <linux/thread_info.h> +#include <linux/vmalloc.h> #include <linux/atomic.h> #include <linux/jump_label.h> #include <asm/sections.h> @@ -157,91 +158,47 @@ static inline void check_bogus_address(const unsigned long ptr, unsigned long n, usercopy_abort("null address", NULL, to_user, ptr, n); } -/* Checks for allocs that are marked in some way as spanning multiple pages. */ -static inline void check_page_span(const void *ptr, unsigned long n, - struct page *page, bool to_user) +static inline void check_heap_object(const void *ptr, unsigned long n, + bool to_user) { -#ifdef CONFIG_HARDENED_USERCOPY_PAGESPAN - const void *end = ptr + n - 1; - struct page *endpage; - bool is_reserved, is_cma; + struct folio *folio; - /* - * Sometimes the kernel data regions are not marked Reserved (see - * check below). And sometimes [_sdata,_edata) does not cover - * rodata and/or bss, so check each range explicitly. - */ + if (is_kmap_addr(ptr)) { + unsigned long page_end = (unsigned long)ptr | (PAGE_SIZE - 1); - /* Allow reads of kernel rodata region (if not marked as Reserved). */ - if (ptr >= (const void *)__start_rodata && - end <= (const void *)__end_rodata) { - if (!to_user) - usercopy_abort("rodata", NULL, to_user, 0, n); + if ((unsigned long)ptr + n - 1 > page_end) + usercopy_abort("kmap", NULL, to_user, + offset_in_page(ptr), n); return; } - /* Allow kernel data region (if not marked as Reserved). */ - if (ptr >= (const void *)_sdata && end <= (const void *)_edata) - return; + if (is_vmalloc_addr(ptr)) { + struct vm_struct *area = find_vm_area(ptr); + unsigned long offset; - /* Allow kernel bss region (if not marked as Reserved). */ - if (ptr >= (const void *)__bss_start && - end <= (const void *)__bss_stop) - return; - - /* Is the object wholly within one base page? */ - if (likely(((unsigned long)ptr & (unsigned long)PAGE_MASK) == - ((unsigned long)end & (unsigned long)PAGE_MASK))) - return; + if (!area) { + usercopy_abort("vmalloc", "no area", to_user, 0, n); + return; + } - /* Allow if fully inside the same compound (__GFP_COMP) page. */ - endpage = virt_to_head_page(end); - if (likely(endpage == page)) + offset = ptr - area->addr; + if (offset + n > get_vm_area_size(area)) + usercopy_abort("vmalloc", NULL, to_user, offset, n); return; - - /* - * Reject if range is entirely either Reserved (i.e. special or - * device memory), or CMA. Otherwise, reject since the object spans - * several independently allocated pages. - */ - is_reserved = PageReserved(page); - is_cma = is_migrate_cma_page(page); - if (!is_reserved && !is_cma) - usercopy_abort("spans multiple pages", NULL, to_user, 0, n); - - for (ptr += PAGE_SIZE; ptr <= end; ptr += PAGE_SIZE) { - page = virt_to_head_page(ptr); - if (is_reserved && !PageReserved(page)) - usercopy_abort("spans Reserved and non-Reserved pages", - NULL, to_user, 0, n); - if (is_cma && !is_migrate_cma_page(page)) - usercopy_abort("spans CMA and non-CMA pages", NULL, - to_user, 0, n); } -#endif -} - -static inline void check_heap_object(const void *ptr, unsigned long n, - bool to_user) -{ - struct folio *folio; if (!virt_addr_valid(ptr)) return; - /* - * When CONFIG_HIGHMEM=y, kmap_to_page() will give either the - * highmem page or fallback to virt_to_page(). The following - * is effectively a highmem-aware virt_to_slab(). - */ - folio = page_folio(kmap_to_page((void *)ptr)); + folio = virt_to_folio(ptr); if (folio_test_slab(folio)) { /* Check slab allocator for flags and size. */ __check_heap_object(ptr, n, folio_slab(folio), to_user); - } else { - /* Verify object does not incorrectly span multiple pages. */ - check_page_span(ptr, n, folio_page(folio, 0), to_user); + } else if (folio_test_large(folio)) { + unsigned long offset = ptr - folio_address(folio); + if (offset + n > folio_size(folio)) + usercopy_abort("page alloc", NULL, to_user, offset, n); } } diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 0cb8e5ef1713..e9bb6db002aa 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -72,12 +72,15 @@ int mfill_atomic_install_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, _dst_pte = pte_mkdirty(_dst_pte); if (page_in_cache && !vm_shared) writable = false; - if (writable) { - if (wp_copy) - _dst_pte = pte_mkuffd_wp(_dst_pte); - else - _dst_pte = pte_mkwrite(_dst_pte); - } + + /* + * Always mark a PTE as write-protected when needed, regardless of + * VM_WRITE, which the user might change. + */ + if (wp_copy) + _dst_pte = pte_mkuffd_wp(_dst_pte); + else if (writable) + _dst_pte = pte_mkwrite(_dst_pte); dst_pte = pte_offset_map_lock(dst_mm, dst_pmd, dst_addr, &ptl); diff --git a/mm/util.c b/mm/util.c index 54e5e761a9a9..ac63e5ca8b21 100644 --- a/mm/util.c +++ b/mm/util.c @@ -343,6 +343,38 @@ unsigned long randomize_stack_top(unsigned long stack_top) #endif } +/** + * randomize_page - Generate a random, page aligned address + * @start: The smallest acceptable address the caller will take. + * @range: The size of the area, starting at @start, within which the + * random address must fall. + * + * If @start + @range would overflow, @range is capped. + * + * NOTE: Historical use of randomize_range, which this replaces, presumed that + * @start was already page aligned. We now align it regardless. + * + * Return: A page aligned address within [start, start + range). On error, + * @start is returned. + */ +unsigned long randomize_page(unsigned long start, unsigned long range) +{ + if (!PAGE_ALIGNED(start)) { + range -= PAGE_ALIGN(start) - start; + start = PAGE_ALIGN(start); + } + + if (start > ULONG_MAX - range) + range = ULONG_MAX - start; + + range >>= PAGE_SHIFT; + + if (range == 0) + return start; + + return start + (get_random_long() % range << PAGE_SHIFT); +} + #ifdef CONFIG_ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT unsigned long arch_randomize_brk(struct mm_struct *mm) { @@ -592,8 +624,15 @@ void *kvmalloc_node(size_t size, gfp_t flags, int node) return NULL; } - return __vmalloc_node(size, 1, flags, node, - __builtin_return_address(0)); + /* + * kvmalloc() can always use VM_ALLOW_HUGE_VMAP, + * since the callers already cannot assume anything + * about the resulting pointer, and cannot play + * protection games. + */ + return __vmalloc_node_range(size, 1, VMALLOC_START, VMALLOC_END, + flags, PAGE_KERNEL, VM_ALLOW_HUGE_VMAP, + node, __builtin_return_address(0)); } EXPORT_SYMBOL(kvmalloc_node); diff --git a/mm/vmalloc.c b/mm/vmalloc.c index e163372d3967..cadfbb5155ea 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1671,17 +1671,6 @@ static DEFINE_MUTEX(vmap_purge_lock); /* for per-CPU blocks */ static void purge_fragmented_blocks_allcpus(void); -#ifdef CONFIG_X86_64 -/* - * called before a call to iounmap() if the caller wants vm_area_struct's - * immediately freed. - */ -void set_iounmap_nonlazy(void) -{ - atomic_long_set(&vmap_lazy_nr, lazy_max_pages()+1); -} -#endif /* CONFIG_X86_64 */ - /* * Purges all lazily-freed vmap areas. */ @@ -2664,15 +2653,18 @@ static void __vunmap(const void *addr, int deallocate_pages) vm_remove_mappings(area, deallocate_pages); if (deallocate_pages) { - unsigned int page_order = vm_area_page_order(area); - int i, step = 1U << page_order; + int i; - for (i = 0; i < area->nr_pages; i += step) { + for (i = 0; i < area->nr_pages; i++) { struct page *page = area->pages[i]; BUG_ON(!page); - mod_memcg_page_state(page, MEMCG_VMALLOC, -step); - __free_pages(page, page_order); + mod_memcg_page_state(page, MEMCG_VMALLOC, -1); + /* + * High-order allocs for huge vmallocs are split, so + * can be freed as an array of order-0 allocations + */ + __free_pages(page, 0); cond_resched(); } atomic_long_sub(area->nr_pages, &nr_vmalloc_pages); @@ -2925,12 +2917,7 @@ vm_area_alloc_pages(gfp_t gfp, int nid, if (nr != nr_pages_request) break; } - } else - /* - * Compound pages required for remap_vmalloc_page if - * high-order pages. - */ - gfp |= __GFP_COMP; + } /* High-order pages or fallback path if "bulk" fails. */ @@ -2944,6 +2931,15 @@ vm_area_alloc_pages(gfp_t gfp, int nid, page = alloc_pages_node(nid, gfp, order); if (unlikely(!page)) break; + /* + * Higher order allocations must be able to be treated as + * indepdenent small pages by callers (as they can with + * small-page vmallocs). Some drivers do their own refcounting + * on vmalloc_to_page() pages, some use page->mapping, + * page->lru, etc. + */ + if (order) + split_page(page, order); /* * Careful, we allocate and map page-order pages, but @@ -3003,11 +2999,10 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, atomic_long_add(area->nr_pages, &nr_vmalloc_pages); if (gfp_mask & __GFP_ACCOUNT) { - int i, step = 1U << page_order; + int i; - for (i = 0; i < area->nr_pages; i += step) - mod_memcg_page_state(area->pages[i], MEMCG_VMALLOC, - step); + for (i = 0; i < area->nr_pages; i++) + mod_memcg_page_state(area->pages[i], MEMCG_VMALLOC, 1); } /* @@ -3106,7 +3101,7 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align, return NULL; } - if (vmap_allow_huge && !(vm_flags & VM_NO_HUGE_VMAP)) { + if (vmap_allow_huge && (vm_flags & VM_ALLOW_HUGE_VMAP)) { unsigned long size_per_node; /* @@ -3273,21 +3268,24 @@ void *vmalloc(unsigned long size) EXPORT_SYMBOL(vmalloc); /** - * vmalloc_no_huge - allocate virtually contiguous memory using small pages - * @size: allocation size + * vmalloc_huge - allocate virtually contiguous memory, allow huge pages + * @size: allocation size + * @gfp_mask: flags for the page level allocator * - * Allocate enough non-huge pages to cover @size from the page level + * Allocate enough pages to cover @size from the page level * allocator and map them into contiguous kernel virtual space. + * If @size is greater than or equal to PMD_SIZE, allow using + * huge pages for the memory * * Return: pointer to the allocated memory or %NULL on error */ -void *vmalloc_no_huge(unsigned long size) +void *vmalloc_huge(unsigned long size, gfp_t gfp_mask) { return __vmalloc_node_range(size, 1, VMALLOC_START, VMALLOC_END, - GFP_KERNEL, PAGE_KERNEL, VM_NO_HUGE_VMAP, + gfp_mask, PAGE_KERNEL, VM_ALLOW_HUGE_VMAP, NUMA_NO_NODE, __builtin_return_address(0)); } -EXPORT_SYMBOL(vmalloc_no_huge); +EXPORT_SYMBOL_GPL(vmalloc_huge); /** * vzalloc - allocate virtually contiguous memory with zero fill diff --git a/mm/vmscan.c b/mm/vmscan.c index 1678802e03e7..edc89f26b738 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1181,7 +1181,7 @@ static pageout_t pageout(struct folio *folio, struct address_space *mapping) * folio->mapping == NULL while being dirty with clean buffers. */ if (folio_test_private(folio)) { - if (try_to_free_buffers(&folio->page)) { + if (try_to_free_buffers(folio)) { folio_clear_dirty(folio); pr_info("%s: orphaned folio\n", __func__); return PAGE_CLEAN; @@ -1282,9 +1282,9 @@ static int __remove_mapping(struct address_space *mapping, struct folio *folio, xa_unlock_irq(&mapping->i_pages); put_swap_page(&folio->page, swap); } else { - void (*freepage)(struct page *); + void (*free_folio)(struct folio *); - freepage = mapping->a_ops->freepage; + free_folio = mapping->a_ops->free_folio; /* * Remember a shadow entry for reclaimed file cache in * order to detect refaults, thus thrashing, later on. @@ -1310,8 +1310,8 @@ static int __remove_mapping(struct address_space *mapping, struct folio *folio, inode_add_lru(mapping->host); spin_unlock(&mapping->host->i_lock); - if (freepage != NULL) - freepage(&folio->page); + if (free_folio) + free_folio(folio); } return 1; @@ -1451,7 +1451,7 @@ static void folio_check_dirty_writeback(struct folio *folio, mapping = folio_mapping(folio); if (mapping && mapping->a_ops->is_dirty_writeback) - mapping->a_ops->is_dirty_writeback(&folio->page, dirty, writeback); + mapping->a_ops->is_dirty_writeback(folio, dirty, writeback); } static struct page *alloc_demote_page(struct page *page, unsigned long node) diff --git a/mm/workingset.c b/mm/workingset.c index 8a3828acc0bf..592569a8974c 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -355,7 +355,7 @@ void workingset_refault(struct folio *folio, void *shadow) mod_lruvec_state(lruvec, WORKINGSET_REFAULT_BASE + file, nr); - mem_cgroup_flush_stats(); + mem_cgroup_flush_stats_delayed(); /* * Compare the distance to the existing workingset size. We * don't activate pages that couldn't stay resident even if diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c index 0899a729a23f..c120c7c6d25f 100644 --- a/net/batman-adv/fragmentation.c +++ b/net/batman-adv/fragmentation.c @@ -475,6 +475,17 @@ int batadv_frag_send_packet(struct sk_buff *skb, goto free_skb; } + /* GRO might have added fragments to the fragment list instead of + * frags[]. But this is not handled by skb_split and must be + * linearized to avoid incorrect length information after all + * batman-adv fragments were created and submitted to the + * hard-interface + */ + if (skb_has_frag_list(skb) && __skb_linearize(skb)) { + ret = -ENOMEM; + goto free_skb; + } + /* Create one header to be copied to all fragments */ frag_header.packet_type = BATADV_UNICAST_FRAG; frag_header.version = BATADV_COMPAT_VERSION; diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 84312c836549..fe803bee419a 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -670,7 +670,7 @@ static void le_conn_timeout(struct work_struct *work) /* Disable LE Advertising */ le_disable_advertising(hdev); hci_dev_lock(hdev); - hci_le_conn_failed(conn, HCI_ERROR_ADVERTISING_TIMEOUT); + hci_conn_failed(conn, HCI_ERROR_ADVERTISING_TIMEOUT); hci_dev_unlock(hdev); return; } @@ -873,7 +873,7 @@ struct hci_dev *hci_get_route(bdaddr_t *dst, bdaddr_t *src, uint8_t src_type) EXPORT_SYMBOL(hci_get_route); /* This function requires the caller holds hdev->lock */ -void hci_le_conn_failed(struct hci_conn *conn, u8 status) +static void hci_le_conn_failed(struct hci_conn *conn, u8 status) { struct hci_dev *hdev = conn->hdev; struct hci_conn_params *params; @@ -886,8 +886,6 @@ void hci_le_conn_failed(struct hci_conn *conn, u8 status) params->conn = NULL; } - conn->state = BT_CLOSED; - /* If the status indicates successful cancellation of * the attempt (i.e. Unknown Connection Id) there's no point of * notifying failure since we'll go back to keep trying to @@ -899,10 +897,6 @@ void hci_le_conn_failed(struct hci_conn *conn, u8 status) mgmt_connect_failed(hdev, &conn->dst, conn->type, conn->dst_type, status); - hci_connect_cfm(conn, status); - - hci_conn_del(conn); - /* Since we may have temporarily stopped the background scanning in * favor of connection establishment, we should restart it. */ @@ -914,6 +908,28 @@ void hci_le_conn_failed(struct hci_conn *conn, u8 status) hci_enable_advertising(hdev); } +/* This function requires the caller holds hdev->lock */ +void hci_conn_failed(struct hci_conn *conn, u8 status) +{ + struct hci_dev *hdev = conn->hdev; + + bt_dev_dbg(hdev, "status 0x%2.2x", status); + + switch (conn->type) { + case LE_LINK: + hci_le_conn_failed(conn, status); + break; + case ACL_LINK: + mgmt_connect_failed(hdev, &conn->dst, conn->type, + conn->dst_type, status); + break; + } + + conn->state = BT_CLOSED; + hci_connect_cfm(conn, status); + hci_conn_del(conn); +} + static void create_le_conn_complete(struct hci_dev *hdev, void *data, int err) { struct hci_conn *conn = data; diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index b4782a6c1025..45c2dd2e1590 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -2555,10 +2555,10 @@ int hci_register_dev(struct hci_dev *hdev) */ switch (hdev->dev_type) { case HCI_PRIMARY: - id = ida_simple_get(&hci_index_ida, 0, 0, GFP_KERNEL); + id = ida_simple_get(&hci_index_ida, 0, HCI_MAX_ID, GFP_KERNEL); break; case HCI_AMP: - id = ida_simple_get(&hci_index_ida, 1, 0, GFP_KERNEL); + id = ida_simple_get(&hci_index_ida, 1, HCI_MAX_ID, GFP_KERNEL); break; default: return -EINVAL; @@ -2567,7 +2567,7 @@ int hci_register_dev(struct hci_dev *hdev) if (id < 0) return id; - sprintf(hdev->name, "hci%d", id); + snprintf(hdev->name, sizeof(hdev->name), "hci%d", id); hdev->id = id; BT_DBG("%p name %s bus %d", hdev, hdev->name, hdev->bus); diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index abaabfae19cc..66451661283c 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -2834,7 +2834,7 @@ static void hci_cs_le_create_conn(struct hci_dev *hdev, u8 status) bt_dev_dbg(hdev, "status 0x%2.2x", status); /* All connection failure handling is taken care of by the - * hci_le_conn_failed function which is triggered by the HCI + * hci_conn_failed function which is triggered by the HCI * request completion callbacks used for connecting. */ if (status) @@ -2859,7 +2859,7 @@ static void hci_cs_le_ext_create_conn(struct hci_dev *hdev, u8 status) bt_dev_dbg(hdev, "status 0x%2.2x", status); /* All connection failure handling is taken care of by the - * hci_le_conn_failed function which is triggered by the HCI + * hci_conn_failed function which is triggered by the HCI * request completion callbacks used for connecting. */ if (status) @@ -3067,18 +3067,20 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, void *data, { struct hci_ev_conn_complete *ev = data; struct hci_conn *conn; + u8 status = ev->status; - if (__le16_to_cpu(ev->handle) > HCI_CONN_HANDLE_MAX) { - bt_dev_err(hdev, "Ignoring HCI_Connection_Complete for invalid handle"); - return; - } - - bt_dev_dbg(hdev, "status 0x%2.2x", ev->status); + bt_dev_dbg(hdev, "status 0x%2.2x", status); hci_dev_lock(hdev); conn = hci_conn_hash_lookup_ba(hdev, ev->link_type, &ev->bdaddr); if (!conn) { + /* In case of error status and there is no connection pending + * just unlock as there is nothing to cleanup. + */ + if (ev->status) + goto unlock; + /* Connection may not exist if auto-connected. Check the bredr * allowlist to see if this device is allowed to auto connect. * If link is an ACL type, create a connection class @@ -3122,8 +3124,14 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, void *data, goto unlock; } - if (!ev->status) { + if (!status) { conn->handle = __le16_to_cpu(ev->handle); + if (conn->handle > HCI_CONN_HANDLE_MAX) { + bt_dev_err(hdev, "Invalid handle: 0x%4.4x > 0x%4.4x", + conn->handle, HCI_CONN_HANDLE_MAX); + status = HCI_ERROR_INVALID_PARAMETERS; + goto done; + } if (conn->type == ACL_LINK) { conn->state = BT_CONFIG; @@ -3164,19 +3172,14 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, void *data, hci_send_cmd(hdev, HCI_OP_CHANGE_CONN_PTYPE, sizeof(cp), &cp); } - } else { - conn->state = BT_CLOSED; - if (conn->type == ACL_LINK) - mgmt_connect_failed(hdev, &conn->dst, conn->type, - conn->dst_type, ev->status); } if (conn->type == ACL_LINK) hci_sco_setup(conn, ev->status); - if (ev->status) { - hci_connect_cfm(conn, ev->status); - hci_conn_del(conn); +done: + if (status) { + hci_conn_failed(conn, status); } else if (ev->link_type == SCO_LINK) { switch (conn->setting & SCO_AIRMODE_MASK) { case SCO_AIRMODE_CVSD: @@ -3185,7 +3188,7 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, void *data, break; } - hci_connect_cfm(conn, ev->status); + hci_connect_cfm(conn, status); } unlock: @@ -4676,6 +4679,7 @@ static void hci_sync_conn_complete_evt(struct hci_dev *hdev, void *data, { struct hci_ev_sync_conn_complete *ev = data; struct hci_conn *conn; + u8 status = ev->status; switch (ev->link_type) { case SCO_LINK: @@ -4690,12 +4694,7 @@ static void hci_sync_conn_complete_evt(struct hci_dev *hdev, void *data, return; } - if (__le16_to_cpu(ev->handle) > HCI_CONN_HANDLE_MAX) { - bt_dev_err(hdev, "Ignoring HCI_Sync_Conn_Complete for invalid handle"); - return; - } - - bt_dev_dbg(hdev, "status 0x%2.2x", ev->status); + bt_dev_dbg(hdev, "status 0x%2.2x", status); hci_dev_lock(hdev); @@ -4729,9 +4728,17 @@ static void hci_sync_conn_complete_evt(struct hci_dev *hdev, void *data, goto unlock; } - switch (ev->status) { + switch (status) { case 0x00: conn->handle = __le16_to_cpu(ev->handle); + if (conn->handle > HCI_CONN_HANDLE_MAX) { + bt_dev_err(hdev, "Invalid handle: 0x%4.4x > 0x%4.4x", + conn->handle, HCI_CONN_HANDLE_MAX); + status = HCI_ERROR_INVALID_PARAMETERS; + conn->state = BT_CLOSED; + break; + } + conn->state = BT_CONNECTED; conn->type = ev->link_type; @@ -4775,8 +4782,8 @@ static void hci_sync_conn_complete_evt(struct hci_dev *hdev, void *data, } } - hci_connect_cfm(conn, ev->status); - if (ev->status) + hci_connect_cfm(conn, status); + if (status) hci_conn_del(conn); unlock: @@ -5527,11 +5534,6 @@ static void le_conn_complete_evt(struct hci_dev *hdev, u8 status, struct smp_irk *irk; u8 addr_type; - if (handle > HCI_CONN_HANDLE_MAX) { - bt_dev_err(hdev, "Ignoring HCI_LE_Connection_Complete for invalid handle"); - return; - } - hci_dev_lock(hdev); /* All controllers implicitly stop advertising in the event of a @@ -5541,6 +5543,12 @@ static void le_conn_complete_evt(struct hci_dev *hdev, u8 status, conn = hci_lookup_le_connect(hdev); if (!conn) { + /* In case of error status and there is no connection pending + * just unlock as there is nothing to cleanup. + */ + if (status) + goto unlock; + conn = hci_conn_add(hdev, LE_LINK, bdaddr, role); if (!conn) { bt_dev_err(hdev, "no memory for new connection"); @@ -5603,8 +5611,14 @@ static void le_conn_complete_evt(struct hci_dev *hdev, u8 status, conn->dst_type = ev_bdaddr_type(hdev, conn->dst_type, NULL); + if (handle > HCI_CONN_HANDLE_MAX) { + bt_dev_err(hdev, "Invalid handle: 0x%4.4x > 0x%4.4x", handle, + HCI_CONN_HANDLE_MAX); + status = HCI_ERROR_INVALID_PARAMETERS; + } + if (status) { - hci_le_conn_failed(conn, status); + hci_conn_failed(conn, status); goto unlock; } diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index 8f4c5698913d..13600bf120b0 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -4408,12 +4408,21 @@ static int hci_reject_conn_sync(struct hci_dev *hdev, struct hci_conn *conn, static int hci_abort_conn_sync(struct hci_dev *hdev, struct hci_conn *conn, u8 reason) { + int err; + switch (conn->state) { case BT_CONNECTED: case BT_CONFIG: return hci_disconnect_sync(hdev, conn, reason); case BT_CONNECT: - return hci_connect_cancel_sync(hdev, conn); + err = hci_connect_cancel_sync(hdev, conn); + /* Cleanup hci_conn object if it cannot be cancelled as it + * likelly means the controller and host stack are out of sync. + */ + if (err) + hci_conn_failed(conn, err); + + return err; case BT_CONNECT2: return hci_reject_conn_sync(hdev, conn, reason); default: diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index e7b9c2636d10..af709c182674 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -108,6 +108,7 @@ struct xdp_test_data { struct page_pool *pp; struct xdp_frame **frames; struct sk_buff **skbs; + struct xdp_mem_info mem; u32 batch_size; u32 frame_cnt; }; @@ -147,7 +148,6 @@ static void xdp_test_run_init_page(struct page *page, void *arg) static int xdp_test_run_setup(struct xdp_test_data *xdp, struct xdp_buff *orig_ctx) { - struct xdp_mem_info mem = {}; struct page_pool *pp; int err = -ENOMEM; struct page_pool_params pp_params = { @@ -174,7 +174,7 @@ static int xdp_test_run_setup(struct xdp_test_data *xdp, struct xdp_buff *orig_c } /* will copy 'mem.id' into pp->xdp_mem_id */ - err = xdp_reg_mem_model(&mem, MEM_TYPE_PAGE_POOL, pp); + err = xdp_reg_mem_model(&xdp->mem, MEM_TYPE_PAGE_POOL, pp); if (err) goto err_mmodel; @@ -202,6 +202,7 @@ err_skbs: static void xdp_test_run_teardown(struct xdp_test_data *xdp) { + xdp_unreg_mem_model(&xdp->mem); page_pool_destroy(xdp->pp); kfree(xdp->frames); kfree(xdp->skbs); diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 196417859c4a..68b3e850bcb9 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -39,6 +39,13 @@ static int br_pass_frame_up(struct sk_buff *skb) dev_sw_netstats_rx_add(brdev, skb->len); vg = br_vlan_group_rcu(br); + + /* Reset the offload_fwd_mark because there could be a stacked + * bridge above, and it should not think this bridge it doing + * that bridge's work forwarding out its ports. + */ + br_switchdev_frame_unmark(skb); + /* Bridge is just like any other port. Make sure the * packet is allowed except in promisc mode when someone * may be running packet capture. diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c index 8cc44c367231..18affda2b522 100644 --- a/net/bridge/br_switchdev.c +++ b/net/bridge/br_switchdev.c @@ -353,6 +353,8 @@ static int br_switchdev_vlan_attr_replay(struct net_device *br_dev, attr.orig_dev = br_dev; vg = br_vlan_group(br); + if (!vg) + return 0; list_for_each_entry(v, &vg->vlan_list, vlist) { if (v->msti) { diff --git a/net/can/isotp.c b/net/can/isotp.c index bafb0fb5f0e0..1e7c6a460ef9 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -906,6 +906,7 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) struct canfd_frame *cf; int ae = (so->opt.flags & CAN_ISOTP_EXTEND_ADDR) ? 1 : 0; int wait_tx_done = (so->opt.flags & CAN_ISOTP_WAIT_TX_DONE) ? 1 : 0; + s64 hrtimer_sec = 0; int off; int err; @@ -1004,7 +1005,9 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) isotp_create_fframe(cf, so, ae); /* start timeout for FC */ - hrtimer_start(&so->txtimer, ktime_set(1, 0), HRTIMER_MODE_REL_SOFT); + hrtimer_sec = 1; + hrtimer_start(&so->txtimer, ktime_set(hrtimer_sec, 0), + HRTIMER_MODE_REL_SOFT); } /* send the first or only CAN frame */ @@ -1017,6 +1020,11 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) if (err) { pr_notice_once("can-isotp: %s: can_send_ret %pe\n", __func__, ERR_PTR(err)); + + /* no transmission -> no timeout monitoring */ + if (hrtimer_sec) + hrtimer_cancel(&so->txtimer); + goto err_out_drop; } @@ -1181,6 +1189,11 @@ static int isotp_bind(struct socket *sock, struct sockaddr *uaddr, int len) lock_sock(sk); + if (so->bound) { + err = -EINVAL; + goto out; + } + /* do not register frame reception for functional addressing */ if (so->opt.flags & CAN_ISOTP_SF_BROADCAST) do_rx_reg = 0; @@ -1191,10 +1204,6 @@ static int isotp_bind(struct socket *sock, struct sockaddr *uaddr, int len) goto out; } - if (so->bound && addr->can_ifindex == so->ifindex && - rx_id == so->rxid && tx_id == so->txid) - goto out; - dev = dev_get_by_index(net, addr->can_ifindex); if (!dev) { err = -ENODEV; @@ -1229,22 +1238,6 @@ static int isotp_bind(struct socket *sock, struct sockaddr *uaddr, int len) dev_put(dev); - if (so->bound && do_rx_reg) { - /* unregister old filter */ - if (so->ifindex) { - dev = dev_get_by_index(net, so->ifindex); - if (dev) { - can_rx_unregister(net, dev, so->rxid, - SINGLE_MASK(so->rxid), - isotp_rcv, sk); - can_rx_unregister(net, dev, so->txid, - SINGLE_MASK(so->txid), - isotp_rcv_echo, sk); - dev_put(dev); - } - } - } - /* switch to new settings */ so->ifindex = ifindex; so->rxid = rx_id; diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 1c5815530e0d..9d82bb42e958 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -537,43 +537,6 @@ static void request_init(struct ceph_osd_request *req) target_init(&req->r_t); } -/* - * This is ugly, but it allows us to reuse linger registration and ping - * requests, keeping the structure of the code around send_linger{_ping}() - * reasonable. Setting up a min_nr=2 mempool for each linger request - * and dealing with copying ops (this blasts req only, watch op remains - * intact) isn't any better. - */ -static void request_reinit(struct ceph_osd_request *req) -{ - struct ceph_osd_client *osdc = req->r_osdc; - bool mempool = req->r_mempool; - unsigned int num_ops = req->r_num_ops; - u64 snapid = req->r_snapid; - struct ceph_snap_context *snapc = req->r_snapc; - bool linger = req->r_linger; - struct ceph_msg *request_msg = req->r_request; - struct ceph_msg *reply_msg = req->r_reply; - - dout("%s req %p\n", __func__, req); - WARN_ON(kref_read(&req->r_kref) != 1); - request_release_checks(req); - - WARN_ON(kref_read(&request_msg->kref) != 1); - WARN_ON(kref_read(&reply_msg->kref) != 1); - target_destroy(&req->r_t); - - request_init(req); - req->r_osdc = osdc; - req->r_mempool = mempool; - req->r_num_ops = num_ops; - req->r_snapid = snapid; - req->r_snapc = snapc; - req->r_linger = linger; - req->r_request = request_msg; - req->r_reply = reply_msg; -} - struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc, struct ceph_snap_context *snapc, unsigned int num_ops, @@ -918,14 +881,30 @@ EXPORT_SYMBOL(osd_req_op_xattr_init); * @watch_opcode: CEPH_OSD_WATCH_OP_* */ static void osd_req_op_watch_init(struct ceph_osd_request *req, int which, - u64 cookie, u8 watch_opcode) + u8 watch_opcode, u64 cookie, u32 gen) { struct ceph_osd_req_op *op; op = osd_req_op_init(req, which, CEPH_OSD_OP_WATCH, 0); op->watch.cookie = cookie; op->watch.op = watch_opcode; - op->watch.gen = 0; + op->watch.gen = gen; +} + +/* + * prot_ver, timeout and notify payload (may be empty) should already be + * encoded in @request_pl + */ +static void osd_req_op_notify_init(struct ceph_osd_request *req, int which, + u64 cookie, struct ceph_pagelist *request_pl) +{ + struct ceph_osd_req_op *op; + + op = osd_req_op_init(req, which, CEPH_OSD_OP_NOTIFY, 0); + op->notify.cookie = cookie; + + ceph_osd_data_pagelist_init(&op->notify.request_data, request_pl); + op->indata_len = request_pl->length; } /* @@ -2385,7 +2364,11 @@ again: if (ceph_test_opt(osdc->client, ABORT_ON_FULL)) { err = -ENOSPC; } else { - pr_warn_ratelimited("FULL or reached pool quota\n"); + if (ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL)) + pr_warn_ratelimited("cluster is full (osdmap FULL)\n"); + else + pr_warn_ratelimited("pool %lld is full or reached quota\n", + req->r_t.base_oloc.pool); req->r_t.paused = true; maybe_request_map(osdc); } @@ -2727,10 +2710,13 @@ static void linger_release(struct kref *kref) WARN_ON(!list_empty(&lreq->pending_lworks)); WARN_ON(lreq->osd); - if (lreq->reg_req) - ceph_osdc_put_request(lreq->reg_req); - if (lreq->ping_req) - ceph_osdc_put_request(lreq->ping_req); + if (lreq->request_pl) + ceph_pagelist_release(lreq->request_pl); + if (lreq->notify_id_pages) + ceph_release_page_vector(lreq->notify_id_pages, 1); + + ceph_osdc_put_request(lreq->reg_req); + ceph_osdc_put_request(lreq->ping_req); target_destroy(&lreq->t); kfree(lreq); } @@ -2999,6 +2985,12 @@ static void linger_commit_cb(struct ceph_osd_request *req) struct ceph_osd_linger_request *lreq = req->r_priv; mutex_lock(&lreq->lock); + if (req != lreq->reg_req) { + dout("%s lreq %p linger_id %llu unknown req (%p != %p)\n", + __func__, lreq, lreq->linger_id, req, lreq->reg_req); + goto out; + } + dout("%s lreq %p linger_id %llu result %d\n", __func__, lreq, lreq->linger_id, req->r_result); linger_reg_commit_complete(lreq, req->r_result); @@ -3022,6 +3014,7 @@ static void linger_commit_cb(struct ceph_osd_request *req) } } +out: mutex_unlock(&lreq->lock); linger_put(lreq); } @@ -3044,6 +3037,12 @@ static void linger_reconnect_cb(struct ceph_osd_request *req) struct ceph_osd_linger_request *lreq = req->r_priv; mutex_lock(&lreq->lock); + if (req != lreq->reg_req) { + dout("%s lreq %p linger_id %llu unknown req (%p != %p)\n", + __func__, lreq, lreq->linger_id, req, lreq->reg_req); + goto out; + } + dout("%s lreq %p linger_id %llu result %d last_error %d\n", __func__, lreq, lreq->linger_id, req->r_result, lreq->last_error); if (req->r_result < 0) { @@ -3053,46 +3052,64 @@ static void linger_reconnect_cb(struct ceph_osd_request *req) } } +out: mutex_unlock(&lreq->lock); linger_put(lreq); } static void send_linger(struct ceph_osd_linger_request *lreq) { - struct ceph_osd_request *req = lreq->reg_req; - struct ceph_osd_req_op *op = &req->r_ops[0]; + struct ceph_osd_client *osdc = lreq->osdc; + struct ceph_osd_request *req; + int ret; - verify_osdc_wrlocked(req->r_osdc); + verify_osdc_wrlocked(osdc); + mutex_lock(&lreq->lock); dout("%s lreq %p linger_id %llu\n", __func__, lreq, lreq->linger_id); - if (req->r_osd) - cancel_linger_request(req); + if (lreq->reg_req) { + if (lreq->reg_req->r_osd) + cancel_linger_request(lreq->reg_req); + ceph_osdc_put_request(lreq->reg_req); + } + + req = ceph_osdc_alloc_request(osdc, NULL, 1, true, GFP_NOIO); + BUG_ON(!req); - request_reinit(req); target_copy(&req->r_t, &lreq->t); req->r_mtime = lreq->mtime; - mutex_lock(&lreq->lock); if (lreq->is_watch && lreq->committed) { - WARN_ON(op->op != CEPH_OSD_OP_WATCH || - op->watch.cookie != lreq->linger_id); - op->watch.op = CEPH_OSD_WATCH_OP_RECONNECT; - op->watch.gen = ++lreq->register_gen; + osd_req_op_watch_init(req, 0, CEPH_OSD_WATCH_OP_RECONNECT, + lreq->linger_id, ++lreq->register_gen); dout("lreq %p reconnect register_gen %u\n", lreq, - op->watch.gen); + req->r_ops[0].watch.gen); req->r_callback = linger_reconnect_cb; } else { - if (!lreq->is_watch) + if (lreq->is_watch) { + osd_req_op_watch_init(req, 0, CEPH_OSD_WATCH_OP_WATCH, + lreq->linger_id, 0); + } else { lreq->notify_id = 0; - else - WARN_ON(op->watch.op != CEPH_OSD_WATCH_OP_WATCH); + + refcount_inc(&lreq->request_pl->refcnt); + osd_req_op_notify_init(req, 0, lreq->linger_id, + lreq->request_pl); + ceph_osd_data_pages_init( + osd_req_op_data(req, 0, notify, response_data), + lreq->notify_id_pages, PAGE_SIZE, 0, false, false); + } dout("lreq %p register\n", lreq); req->r_callback = linger_commit_cb; } - mutex_unlock(&lreq->lock); + + ret = ceph_osdc_alloc_messages(req, GFP_NOIO); + BUG_ON(ret); req->r_priv = linger_get(lreq); req->r_linger = true; + lreq->reg_req = req; + mutex_unlock(&lreq->lock); submit_request(req, true); } @@ -3102,6 +3119,12 @@ static void linger_ping_cb(struct ceph_osd_request *req) struct ceph_osd_linger_request *lreq = req->r_priv; mutex_lock(&lreq->lock); + if (req != lreq->ping_req) { + dout("%s lreq %p linger_id %llu unknown req (%p != %p)\n", + __func__, lreq, lreq->linger_id, req, lreq->ping_req); + goto out; + } + dout("%s lreq %p linger_id %llu result %d ping_sent %lu last_error %d\n", __func__, lreq, lreq->linger_id, req->r_result, lreq->ping_sent, lreq->last_error); @@ -3117,6 +3140,7 @@ static void linger_ping_cb(struct ceph_osd_request *req) lreq->register_gen, req->r_ops[0].watch.gen); } +out: mutex_unlock(&lreq->lock); linger_put(lreq); } @@ -3124,8 +3148,8 @@ static void linger_ping_cb(struct ceph_osd_request *req) static void send_linger_ping(struct ceph_osd_linger_request *lreq) { struct ceph_osd_client *osdc = lreq->osdc; - struct ceph_osd_request *req = lreq->ping_req; - struct ceph_osd_req_op *op = &req->r_ops[0]; + struct ceph_osd_request *req; + int ret; if (ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSERD)) { dout("%s PAUSERD\n", __func__); @@ -3137,19 +3161,26 @@ static void send_linger_ping(struct ceph_osd_linger_request *lreq) __func__, lreq, lreq->linger_id, lreq->ping_sent, lreq->register_gen); - if (req->r_osd) - cancel_linger_request(req); + if (lreq->ping_req) { + if (lreq->ping_req->r_osd) + cancel_linger_request(lreq->ping_req); + ceph_osdc_put_request(lreq->ping_req); + } - request_reinit(req); - target_copy(&req->r_t, &lreq->t); + req = ceph_osdc_alloc_request(osdc, NULL, 1, true, GFP_NOIO); + BUG_ON(!req); - WARN_ON(op->op != CEPH_OSD_OP_WATCH || - op->watch.cookie != lreq->linger_id || - op->watch.op != CEPH_OSD_WATCH_OP_PING); - op->watch.gen = lreq->register_gen; + target_copy(&req->r_t, &lreq->t); + osd_req_op_watch_init(req, 0, CEPH_OSD_WATCH_OP_PING, lreq->linger_id, + lreq->register_gen); req->r_callback = linger_ping_cb; + + ret = ceph_osdc_alloc_messages(req, GFP_NOIO); + BUG_ON(ret); + req->r_priv = linger_get(lreq); req->r_linger = true; + lreq->ping_req = req; ceph_osdc_get_request(req); account_request(req); @@ -3165,12 +3196,6 @@ static void linger_submit(struct ceph_osd_linger_request *lreq) down_write(&osdc->lock); linger_register(lreq); - if (lreq->is_watch) { - lreq->reg_req->r_ops[0].watch.cookie = lreq->linger_id; - lreq->ping_req->r_ops[0].watch.cookie = lreq->linger_id; - } else { - lreq->reg_req->r_ops[0].notify.cookie = lreq->linger_id; - } calc_target(osdc, &lreq->t, false); osd = lookup_create_osd(osdc, lreq->t.osd, true); @@ -3202,9 +3227,9 @@ static void cancel_linger_map_check(struct ceph_osd_linger_request *lreq) */ static void __linger_cancel(struct ceph_osd_linger_request *lreq) { - if (lreq->is_watch && lreq->ping_req->r_osd) + if (lreq->ping_req && lreq->ping_req->r_osd) cancel_linger_request(lreq->ping_req); - if (lreq->reg_req->r_osd) + if (lreq->reg_req && lreq->reg_req->r_osd) cancel_linger_request(lreq->reg_req); cancel_linger_map_check(lreq); unlink_linger(lreq->osd, lreq); @@ -4566,8 +4591,13 @@ int ceph_osdc_start_request(struct ceph_osd_client *osdc, EXPORT_SYMBOL(ceph_osdc_start_request); /* - * Unregister a registered request. The request is not completed: - * ->r_result isn't set and __complete_request() isn't called. + * Unregister request. If @req was registered, it isn't completed: + * r_result isn't set and __complete_request() isn't invoked. + * + * If @req wasn't registered, this call may have raced with + * handle_reply(), in which case r_result would already be set and + * __complete_request() would be getting invoked, possibly even + * concurrently with this call. */ void ceph_osdc_cancel_request(struct ceph_osd_request *req) { @@ -4653,43 +4683,6 @@ again: } EXPORT_SYMBOL(ceph_osdc_sync); -static struct ceph_osd_request * -alloc_linger_request(struct ceph_osd_linger_request *lreq) -{ - struct ceph_osd_request *req; - - req = ceph_osdc_alloc_request(lreq->osdc, NULL, 1, false, GFP_NOIO); - if (!req) - return NULL; - - ceph_oid_copy(&req->r_base_oid, &lreq->t.base_oid); - ceph_oloc_copy(&req->r_base_oloc, &lreq->t.base_oloc); - return req; -} - -static struct ceph_osd_request * -alloc_watch_request(struct ceph_osd_linger_request *lreq, u8 watch_opcode) -{ - struct ceph_osd_request *req; - - req = alloc_linger_request(lreq); - if (!req) - return NULL; - - /* - * Pass 0 for cookie because we don't know it yet, it will be - * filled in by linger_submit(). - */ - osd_req_op_watch_init(req, 0, 0, watch_opcode); - - if (ceph_osdc_alloc_messages(req, GFP_NOIO)) { - ceph_osdc_put_request(req); - return NULL; - } - - return req; -} - /* * Returns a handle, caller owns a ref. */ @@ -4719,18 +4712,6 @@ ceph_osdc_watch(struct ceph_osd_client *osdc, lreq->t.flags = CEPH_OSD_FLAG_WRITE; ktime_get_real_ts64(&lreq->mtime); - lreq->reg_req = alloc_watch_request(lreq, CEPH_OSD_WATCH_OP_WATCH); - if (!lreq->reg_req) { - ret = -ENOMEM; - goto err_put_lreq; - } - - lreq->ping_req = alloc_watch_request(lreq, CEPH_OSD_WATCH_OP_PING); - if (!lreq->ping_req) { - ret = -ENOMEM; - goto err_put_lreq; - } - linger_submit(lreq); ret = linger_reg_commit_wait(lreq); if (ret) { @@ -4768,8 +4749,8 @@ int ceph_osdc_unwatch(struct ceph_osd_client *osdc, ceph_oloc_copy(&req->r_base_oloc, &lreq->t.base_oloc); req->r_flags = CEPH_OSD_FLAG_WRITE; ktime_get_real_ts64(&req->r_mtime); - osd_req_op_watch_init(req, 0, lreq->linger_id, - CEPH_OSD_WATCH_OP_UNWATCH); + osd_req_op_watch_init(req, 0, CEPH_OSD_WATCH_OP_UNWATCH, + lreq->linger_id, 0); ret = ceph_osdc_alloc_messages(req, GFP_NOIO); if (ret) @@ -4855,35 +4836,6 @@ out_put_req: } EXPORT_SYMBOL(ceph_osdc_notify_ack); -static int osd_req_op_notify_init(struct ceph_osd_request *req, int which, - u64 cookie, u32 prot_ver, u32 timeout, - void *payload, u32 payload_len) -{ - struct ceph_osd_req_op *op; - struct ceph_pagelist *pl; - int ret; - - op = osd_req_op_init(req, which, CEPH_OSD_OP_NOTIFY, 0); - op->notify.cookie = cookie; - - pl = ceph_pagelist_alloc(GFP_NOIO); - if (!pl) - return -ENOMEM; - - ret = ceph_pagelist_encode_32(pl, 1); /* prot_ver */ - ret |= ceph_pagelist_encode_32(pl, timeout); - ret |= ceph_pagelist_encode_32(pl, payload_len); - ret |= ceph_pagelist_append(pl, payload, payload_len); - if (ret) { - ceph_pagelist_release(pl); - return -ENOMEM; - } - - ceph_osd_data_pagelist_init(&op->notify.request_data, pl); - op->indata_len = pl->length; - return 0; -} - /* * @timeout: in seconds * @@ -4902,7 +4854,6 @@ int ceph_osdc_notify(struct ceph_osd_client *osdc, size_t *preply_len) { struct ceph_osd_linger_request *lreq; - struct page **pages; int ret; WARN_ON(!timeout); @@ -4915,41 +4866,35 @@ int ceph_osdc_notify(struct ceph_osd_client *osdc, if (!lreq) return -ENOMEM; - lreq->preply_pages = preply_pages; - lreq->preply_len = preply_len; - - ceph_oid_copy(&lreq->t.base_oid, oid); - ceph_oloc_copy(&lreq->t.base_oloc, oloc); - lreq->t.flags = CEPH_OSD_FLAG_READ; - - lreq->reg_req = alloc_linger_request(lreq); - if (!lreq->reg_req) { + lreq->request_pl = ceph_pagelist_alloc(GFP_NOIO); + if (!lreq->request_pl) { ret = -ENOMEM; goto out_put_lreq; } - /* - * Pass 0 for cookie because we don't know it yet, it will be - * filled in by linger_submit(). - */ - ret = osd_req_op_notify_init(lreq->reg_req, 0, 0, 1, timeout, - payload, payload_len); - if (ret) + ret = ceph_pagelist_encode_32(lreq->request_pl, 1); /* prot_ver */ + ret |= ceph_pagelist_encode_32(lreq->request_pl, timeout); + ret |= ceph_pagelist_encode_32(lreq->request_pl, payload_len); + ret |= ceph_pagelist_append(lreq->request_pl, payload, payload_len); + if (ret) { + ret = -ENOMEM; goto out_put_lreq; + } /* for notify_id */ - pages = ceph_alloc_page_vector(1, GFP_NOIO); - if (IS_ERR(pages)) { - ret = PTR_ERR(pages); + lreq->notify_id_pages = ceph_alloc_page_vector(1, GFP_NOIO); + if (IS_ERR(lreq->notify_id_pages)) { + ret = PTR_ERR(lreq->notify_id_pages); + lreq->notify_id_pages = NULL; goto out_put_lreq; } - ceph_osd_data_pages_init(osd_req_op_data(lreq->reg_req, 0, notify, - response_data), - pages, PAGE_SIZE, 0, false, true); - ret = ceph_osdc_alloc_messages(lreq->reg_req, GFP_NOIO); - if (ret) - goto out_put_lreq; + lreq->preply_pages = preply_pages; + lreq->preply_len = preply_len; + + ceph_oid_copy(&lreq->t.base_oid, oid); + ceph_oloc_copy(&lreq->t.base_oloc, oloc); + lreq->t.flags = CEPH_OSD_FLAG_READ; linger_submit(lreq); ret = linger_reg_commit_wait(lreq); diff --git a/net/core/dev.c b/net/core/dev.c index 8c6c08446556..191ec76d4c3b 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -681,11 +681,11 @@ int dev_fill_forward_path(const struct net_device *dev, const u8 *daddr, const struct net_device *last_dev; struct net_device_path_ctx ctx = { .dev = dev, - .daddr = daddr, }; struct net_device_path *path; int ret = 0; + memcpy(ctx.daddr, daddr, sizeof(ctx.daddr)); stack->num_paths = 0; while (ctx.dev && ctx.dev->netdev_ops->ndo_fill_forward_path) { last_dev = ctx.dev; @@ -3527,7 +3527,6 @@ static int xmit_one(struct sk_buff *skb, struct net_device *dev, dev_queue_xmit_nit(skb, dev); len = skb->len; - PRANDOM_ADD_NOISE(skb, dev, txq, len + jiffies); trace_net_dev_start_xmit(skb, dev); rc = netdev_start_xmit(skb, dev, txq, more); trace_net_dev_xmit(skb, rc, dev, len); @@ -4168,7 +4167,6 @@ static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev) if (!skb) goto out; - PRANDOM_ADD_NOISE(skb, dev, txq, jiffies); HARD_TX_LOCK(dev, txq, cpu); if (!netif_xmit_stopped(txq)) { @@ -4234,7 +4232,6 @@ int __dev_direct_xmit(struct sk_buff *skb, u16 queue_id) skb_set_queue_mapping(skb, queue_id); txq = skb_get_tx_queue(dev, skb); - PRANDOM_ADD_NOISE(skb, dev, txq, jiffies); local_bh_disable(); @@ -10304,7 +10301,7 @@ void netdev_stats_to_stats64(struct rtnl_link_stats64 *stats64, } EXPORT_SYMBOL(netdev_stats_to_stats64); -struct net_device_core_stats *netdev_core_stats_alloc(struct net_device *dev) +struct net_device_core_stats __percpu *netdev_core_stats_alloc(struct net_device *dev) { struct net_device_core_stats __percpu *p; @@ -10315,11 +10312,7 @@ struct net_device_core_stats *netdev_core_stats_alloc(struct net_device *dev) free_percpu(p); /* This READ_ONCE() pairs with the cmpxchg() above */ - p = READ_ONCE(dev->core_stats); - if (!p) - return NULL; - - return this_cpu_ptr(p); + return READ_ONCE(dev->core_stats); } EXPORT_SYMBOL(netdev_core_stats_alloc); @@ -10356,9 +10349,9 @@ struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev, for_each_possible_cpu(i) { core_stats = per_cpu_ptr(p, i); - storage->rx_dropped += local_read(&core_stats->rx_dropped); - storage->tx_dropped += local_read(&core_stats->tx_dropped); - storage->rx_nohandler += local_read(&core_stats->rx_nohandler); + storage->rx_dropped += READ_ONCE(core_stats->rx_dropped); + storage->tx_dropped += READ_ONCE(core_stats->tx_dropped); + storage->rx_nohandler += READ_ONCE(core_stats->rx_nohandler); } } return storage; diff --git a/net/core/filter.c b/net/core/filter.c index a7044e98765e..64470a727ef7 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -7016,24 +7016,33 @@ BPF_CALL_5(bpf_tcp_check_syncookie, struct sock *, sk, void *, iph, u32, iph_len if (!th->ack || th->rst || th->syn) return -ENOENT; + if (unlikely(iph_len < sizeof(struct iphdr))) + return -EINVAL; + if (tcp_synq_no_recent_overflow(sk)) return -ENOENT; cookie = ntohl(th->ack_seq) - 1; - switch (sk->sk_family) { - case AF_INET: - if (unlikely(iph_len < sizeof(struct iphdr))) + /* Both struct iphdr and struct ipv6hdr have the version field at the + * same offset so we can cast to the shorter header (struct iphdr). + */ + switch (((struct iphdr *)iph)->version) { + case 4: + if (sk->sk_family == AF_INET6 && ipv6_only_sock(sk)) return -EINVAL; ret = __cookie_v4_check((struct iphdr *)iph, th, cookie); break; #if IS_BUILTIN(CONFIG_IPV6) - case AF_INET6: + case 6: if (unlikely(iph_len < sizeof(struct ipv6hdr))) return -EINVAL; + if (sk->sk_family != AF_INET6) + return -EINVAL; + ret = __cookie_v6_check((struct ipv6hdr *)iph, th, cookie); break; #endif /* CONFIG_IPV6 */ diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 03b6e649c428..6f7ec72016dc 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -1032,7 +1032,7 @@ bool __skb_flow_dissect(const struct net *net, key_eth_addrs = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS, target_container); - memcpy(key_eth_addrs, ð->h_dest, sizeof(*key_eth_addrs)); + memcpy(key_eth_addrs, eth, sizeof(*key_eth_addrs)); } proto_again: @@ -1183,6 +1183,7 @@ proto_again: VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT; } key_vlan->vlan_tpid = saved_vlan_tpid; + key_vlan->vlan_eth_type = proto; } fdret = FLOW_DISSECT_RET_PROTO_AGAIN; diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c index 349480ef68a5..8b6b5e72b217 100644 --- a/net/core/lwt_bpf.c +++ b/net/core/lwt_bpf.c @@ -159,10 +159,8 @@ static int bpf_output(struct net *net, struct sock *sk, struct sk_buff *skb) return dst->lwtstate->orig_output(net, sk, skb); } -static int xmit_check_hhlen(struct sk_buff *skb) +static int xmit_check_hhlen(struct sk_buff *skb, int hh_len) { - int hh_len = skb_dst(skb)->dev->hard_header_len; - if (skb_headroom(skb) < hh_len) { int nhead = HH_DATA_ALIGN(hh_len - skb_headroom(skb)); @@ -274,6 +272,7 @@ static int bpf_xmit(struct sk_buff *skb) bpf = bpf_lwt_lwtunnel(dst->lwtstate); if (bpf->xmit.prog) { + int hh_len = dst->dev->hard_header_len; __be16 proto = skb->protocol; int ret; @@ -291,7 +290,7 @@ static int bpf_xmit(struct sk_buff *skb) /* If the header was expanded, headroom might be too * small for L2 header to come, expand as needed. */ - ret = xmit_check_hhlen(skb); + ret = xmit_check_hhlen(skb, hh_len); if (unlikely(ret)) return ret; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 159c9c61e6af..d1381ea6d52e 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -5242,6 +5242,8 @@ static int rtnl_offload_xstats_fill(struct sk_buff *skb, struct net_device *dev, *prividx = attr_id_l3_stats; size_l3 = rtnl_offload_xstats_get_size_stats(dev, t_l3); + if (!size_l3) + goto skip_l3_stats; attr = nla_reserve_64bit(skb, attr_id_l3_stats, size_l3, IFLA_OFFLOAD_XSTATS_UNSPEC); if (!attr) @@ -5253,6 +5255,7 @@ static int rtnl_offload_xstats_fill(struct sk_buff *skb, struct net_device *dev, return err; have_data = true; +skip_l3_stats: *prividx = 0; } diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c index 9b8443774449..5f85e01d4093 100644 --- a/net/core/secure_seq.c +++ b/net/core/secure_seq.c @@ -22,6 +22,8 @@ static siphash_aligned_key_t net_secret; static siphash_aligned_key_t ts_secret; +#define EPHEMERAL_PORT_SHUFFLE_PERIOD (10 * HZ) + static __always_inline void net_secret_init(void) { net_get_random_once(&net_secret, sizeof(net_secret)); @@ -94,17 +96,19 @@ u32 secure_tcpv6_seq(const __be32 *saddr, const __be32 *daddr, } EXPORT_SYMBOL(secure_tcpv6_seq); -u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr, +u64 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr, __be16 dport) { const struct { struct in6_addr saddr; struct in6_addr daddr; + unsigned int timeseed; __be16 dport; } __aligned(SIPHASH_ALIGNMENT) combined = { .saddr = *(struct in6_addr *)saddr, .daddr = *(struct in6_addr *)daddr, - .dport = dport + .timeseed = jiffies / EPHEMERAL_PORT_SHUFFLE_PERIOD, + .dport = dport, }; net_secret_init(); return siphash(&combined, offsetofend(typeof(combined), dport), @@ -142,11 +146,13 @@ u32 secure_tcp_seq(__be32 saddr, __be32 daddr, } EXPORT_SYMBOL_GPL(secure_tcp_seq); -u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport) +u64 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport) { net_secret_init(); - return siphash_3u32((__force u32)saddr, (__force u32)daddr, - (__force u16)dport, &net_secret); + return siphash_4u32((__force u32)saddr, (__force u32)daddr, + (__force u16)dport, + jiffies / EPHEMERAL_PORT_SHUFFLE_PERIOD, + &net_secret); } EXPORT_SYMBOL_GPL(secure_ipv4_port_ephemeral); #endif diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 10bde7c6db44..c90c74de90d5 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3897,7 +3897,7 @@ struct sk_buff *skb_segment_list(struct sk_buff *skb, unsigned int delta_len = 0; struct sk_buff *tail = NULL; struct sk_buff *nskb, *tmp; - int err; + int len_diff, err; skb_push(skb, -skb_network_offset(skb) + offset); @@ -3937,9 +3937,11 @@ struct sk_buff *skb_segment_list(struct sk_buff *skb, skb_push(nskb, -skb_network_offset(nskb) + offset); skb_release_head_state(nskb); + len_diff = skb_network_header_len(nskb) - skb_network_header_len(skb); __copy_skb_header(nskb, skb); skb_headers_offset_update(nskb, skb_headroom(nskb) - skb_headroom(skb)); + nskb->transport_header += len_diff; skb_copy_from_linear_data_offset(skb, -tnl_hlen, nskb->data - tnl_hlen, offset + tnl_hlen); @@ -5276,11 +5278,18 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, if (skb_cloned(to)) return false; - /* The page pool signature of struct page will eventually figure out - * which pages can be recycled or not but for now let's prohibit slab - * allocated and page_pool allocated SKBs from being coalesced. + /* In general, avoid mixing slab allocated and page_pool allocated + * pages within the same SKB. However when @to is not pp_recycle and + * @from is cloned, we can transition frag pages from page_pool to + * reference counted. + * + * On the other hand, don't allow coalescing two pp_recycle SKBs if + * @from is cloned, in case the SKB is using page_pool fragment + * references (PP_FLAG_PAGE_FRAG). Since we only take full page + * references for cloned SKBs at the moment that would result in + * inconsistent reference counts. */ - if (to->pp_recycle != from->pp_recycle) + if (to->pp_recycle != (from->pp_recycle && !skb_cloned(from))) return false; if (len <= skb_tailroom(to)) { diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index ae662567a6cb..0ea29270d7e5 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -1030,9 +1030,15 @@ static void __net_exit dccp_v4_exit_net(struct net *net) inet_ctl_sock_destroy(pn->v4_ctl_sk); } +static void __net_exit dccp_v4_exit_batch(struct list_head *net_exit_list) +{ + inet_twsk_purge(&dccp_hashinfo, AF_INET); +} + static struct pernet_operations dccp_v4_ops = { .init = dccp_v4_init_net, .exit = dccp_v4_exit_net, + .exit_batch = dccp_v4_exit_batch, .id = &dccp_v4_pernet_id, .size = sizeof(struct dccp_v4_pernet), }; diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index eab3bd1ee9a0..fa663518fa0e 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -1115,9 +1115,15 @@ static void __net_exit dccp_v6_exit_net(struct net *net) inet_ctl_sock_destroy(pn->v6_ctl_sk); } +static void __net_exit dccp_v6_exit_batch(struct list_head *net_exit_list) +{ + inet_twsk_purge(&dccp_hashinfo, AF_INET6); +} + static struct pernet_operations dccp_v6_ops = { .init = dccp_v6_init_net, .exit = dccp_v6_exit_net, + .exit_batch = dccp_v6_exit_batch, .id = &dccp_v6_pernet_id, .size = sizeof(struct dccp_v6_pernet), }; diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c index 0ee7d4c0c955..a09ba642b5e7 100644 --- a/net/decnet/dn_dev.c +++ b/net/decnet/dn_dev.c @@ -854,7 +854,7 @@ static void dn_send_endnode_hello(struct net_device *dev, struct dn_ifaddr *ifa) memcpy(msg->neighbor, dn_hiord, ETH_ALEN); if (dn_db->router) { - struct dn_neigh *dn = (struct dn_neigh *)dn_db->router; + struct dn_neigh *dn = container_of(dn_db->router, struct dn_neigh, n); dn_dn2eth(msg->neighbor, dn->addr); } @@ -902,7 +902,7 @@ static void dn_send_router_hello(struct net_device *dev, struct dn_ifaddr *ifa) { int n; struct dn_dev *dn_db = rcu_dereference_raw(dev->dn_ptr); - struct dn_neigh *dn = (struct dn_neigh *)dn_db->router; + struct dn_neigh *dn = container_of(dn_db->router, struct dn_neigh, n); struct sk_buff *skb; size_t size; unsigned char *ptr; diff --git a/net/decnet/dn_neigh.c b/net/decnet/dn_neigh.c index 94b306f6d551..fbd98ac853ea 100644 --- a/net/decnet/dn_neigh.c +++ b/net/decnet/dn_neigh.c @@ -426,7 +426,8 @@ int dn_neigh_router_hello(struct net *net, struct sock *sk, struct sk_buff *skb) if (!dn_db->router) { dn_db->router = neigh_clone(neigh); } else { - if (msg->priority > ((struct dn_neigh *)dn_db->router)->priority) + if (msg->priority > container_of(dn_db->router, + struct dn_neigh, n)->priority) neigh_release(xchg(&dn_db->router, neigh_clone(neigh))); } } diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index 7e85f2a1ae25..d1d78a463a06 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -1120,7 +1120,7 @@ source_ok: /* Ok then, we assume its directly connected and move on */ select_source: if (neigh) - gateway = ((struct dn_neigh *)neigh)->addr; + gateway = container_of(neigh, struct dn_neigh, n)->addr; if (gateway == 0) gateway = fld.daddr; if (fld.saddr == 0) { @@ -1429,7 +1429,7 @@ static int dn_route_input_slow(struct sk_buff *skb) /* Use the default router if there is one */ neigh = neigh_clone(dn_db->router); if (neigh) { - gateway = ((struct dn_neigh *)neigh)->addr; + gateway = container_of(neigh, struct dn_neigh, n)->addr; goto make_route; } diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index ca6af86964bc..cf933225df32 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -562,7 +562,6 @@ static void dsa_port_teardown(struct dsa_port *dp) { struct devlink_port *dlp = &dp->devlink_port; struct dsa_switch *ds = dp->ds; - struct net_device *slave; if (!dp->setup) return; @@ -584,11 +583,9 @@ static void dsa_port_teardown(struct dsa_port *dp) dsa_port_link_unregister_of(dp); break; case DSA_PORT_TYPE_USER: - slave = dp->slave; - - if (slave) { + if (dp->slave) { + dsa_slave_destroy(dp->slave); dp->slave = NULL; - dsa_slave_destroy(slave); } break; } @@ -1147,17 +1144,17 @@ static int dsa_tree_setup(struct dsa_switch_tree *dst) if (err) goto teardown_cpu_ports; - err = dsa_tree_setup_master(dst); + err = dsa_tree_setup_ports(dst); if (err) goto teardown_switches; - err = dsa_tree_setup_ports(dst); + err = dsa_tree_setup_master(dst); if (err) - goto teardown_master; + goto teardown_ports; err = dsa_tree_setup_lags(dst); if (err) - goto teardown_ports; + goto teardown_master; dst->setup = true; @@ -1165,10 +1162,10 @@ static int dsa_tree_setup(struct dsa_switch_tree *dst) return 0; -teardown_ports: - dsa_tree_teardown_ports(dst); teardown_master: dsa_tree_teardown_master(dst); +teardown_ports: + dsa_tree_teardown_ports(dst); teardown_switches: dsa_tree_teardown_switches(dst); teardown_cpu_ports: @@ -1186,10 +1183,10 @@ static void dsa_tree_teardown(struct dsa_switch_tree *dst) dsa_tree_teardown_lags(dst); - dsa_tree_teardown_ports(dst); - dsa_tree_teardown_master(dst); + dsa_tree_teardown_ports(dst); + dsa_tree_teardown_switches(dst); dsa_tree_teardown_cpu_ports(dst); diff --git a/net/dsa/master.c b/net/dsa/master.c index 991c2930d631..2851e44c4cf0 100644 --- a/net/dsa/master.c +++ b/net/dsa/master.c @@ -335,11 +335,24 @@ static const struct attribute_group dsa_group = { .attrs = dsa_slave_attrs, }; +static void dsa_master_reset_mtu(struct net_device *dev) +{ + int err; + + err = dev_set_mtu(dev, ETH_DATA_LEN); + if (err) + netdev_dbg(dev, + "Unable to reset MTU to exclude DSA overheads\n"); +} + int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp) { + const struct dsa_device_ops *tag_ops = cpu_dp->tag_ops; struct dsa_switch *ds = cpu_dp->ds; struct device_link *consumer_link; - int ret; + int mtu, ret; + + mtu = ETH_DATA_LEN + dsa_tag_protocol_overhead(tag_ops); /* The DSA master must use SET_NETDEV_DEV for this to work. */ consumer_link = device_link_add(ds->dev, dev->dev.parent, @@ -349,6 +362,15 @@ int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp) "Failed to create a device link to DSA switch %s\n", dev_name(ds->dev)); + /* The switch driver may not implement ->port_change_mtu(), case in + * which dsa_slave_change_mtu() will not update the master MTU either, + * so we need to do that here. + */ + ret = dev_set_mtu(dev, mtu); + if (ret) + netdev_warn(dev, "error %d setting MTU to %d to include DSA overhead\n", + ret, mtu); + /* If we use a tagging format that doesn't have an ethertype * field, make sure that all packets from this point on get * sent to the tag format's receive function. @@ -384,6 +406,7 @@ void dsa_master_teardown(struct net_device *dev) sysfs_remove_group(&dev->dev.kobj, &dsa_group); dsa_netdev_ops_set(dev, NULL); dsa_master_ethtool_teardown(dev); + dsa_master_reset_mtu(dev); dsa_master_set_promiscuity(dev, -1); dev->dsa_ptr = NULL; diff --git a/net/dsa/port.c b/net/dsa/port.c index 32d472a82241..bdccb613285d 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -451,6 +451,7 @@ out_rollback_unoffload: switchdev_bridge_port_unoffload(brport_dev, dp, &dsa_slave_switchdev_notifier, &dsa_slave_switchdev_blocking_notifier); + dsa_flush_workqueue(); out_rollback_unbridge: dsa_broadcast(DSA_NOTIFIER_BRIDGE_LEAVE, &info); out_rollback: @@ -1620,8 +1621,10 @@ int dsa_port_link_register_of(struct dsa_port *dp) if (ds->ops->phylink_mac_link_down) ds->ops->phylink_mac_link_down(ds, port, MLO_AN_FIXED, PHY_INTERFACE_MODE_NA); + of_node_put(phy_np); return dsa_port_phylink_register(dp); } + of_node_put(phy_np); return 0; } diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 41c69a6e7854..8022d50584db 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -285,7 +285,7 @@ static void dsa_port_manage_cpu_flood(struct dsa_port *dp) if (other_dp->slave->flags & IFF_ALLMULTI) flags.val |= BR_MCAST_FLOOD; if (other_dp->slave->flags & IFF_PROMISC) - flags.val |= BR_FLOOD; + flags.val |= BR_FLOOD | BR_MCAST_FLOOD; } err = dsa_port_pre_bridge_flags(dp, flags, NULL); diff --git a/net/dsa/tag_hellcreek.c b/net/dsa/tag_hellcreek.c index f64b805303cd..eb204ad36eee 100644 --- a/net/dsa/tag_hellcreek.c +++ b/net/dsa/tag_hellcreek.c @@ -21,6 +21,14 @@ static struct sk_buff *hellcreek_xmit(struct sk_buff *skb, struct dsa_port *dp = dsa_slave_to_port(dev); u8 *tag; + /* Calculate checksums (if required) before adding the trailer tag to + * avoid including it in calculations. That would lead to wrong + * checksums after the switch strips the tag. + */ + if (skb->ip_summed == CHECKSUM_PARTIAL && + skb_checksum_help(skb)) + return NULL; + /* Tag encoding */ tag = skb_put(skb, HELLCREEK_TAG_LEN); *tag = BIT(dp->index); diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 53a6b14dc50a..3d6d33ac20cc 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -536,10 +536,8 @@ static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh, return ret; } - if (!(ifa->ifa_flags & IFA_F_SECONDARY)) { - prandom_seed((__force u32) ifa->ifa_local); + if (!(ifa->ifa_flags & IFA_F_SECONDARY)) ifap = last_primary; - } rcu_assign_pointer(ifa->ifa_next, *ifap); rcu_assign_pointer(*ifap, ifa); diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 70e6c87fbe3d..d747166bb291 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -446,7 +446,6 @@ int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info * struct page *page; struct sk_buff *trailer; int tailen = esp->tailen; - unsigned int allocsz; /* this is non-NULL only with TCP/UDP Encapsulation */ if (x->encap) { @@ -456,8 +455,8 @@ int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info * return err; } - allocsz = ALIGN(skb->data_len + tailen, L1_CACHE_BYTES); - if (allocsz > ESP_SKB_FRAG_MAXSIZE) + if (ALIGN(tailen, L1_CACHE_BYTES) > PAGE_SIZE || + ALIGN(skb->data_len, L1_CACHE_BYTES) > PAGE_SIZE) goto cow; if (!skb_cloned(skb)) { diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index cc8e84ef2ae4..ccb62038f6a4 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -889,8 +889,13 @@ int fib_nh_match(struct net *net, struct fib_config *cfg, struct fib_info *fi, } if (cfg->fc_oif || cfg->fc_gw_family) { - struct fib_nh *nh = fib_info_nh(fi, 0); + struct fib_nh *nh; + + /* cannot match on nexthop object attributes */ + if (fi->nh) + return 1; + nh = fib_info_nh(fi, 0); if (cfg->fc_encap) { if (fib_encap_match(net, cfg->fc_encap_type, cfg->fc_encap, nh, cfg, extack)) diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 2ad3c7b42d6d..1d9e6d5e9a76 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -2403,9 +2403,10 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct /* decrease mem now to avoid the memleak warning */ atomic_sub(struct_size(psl, sl_addr, psl->sl_max), &sk->sk_omem_alloc); - kfree_rcu(psl, rcu); } rcu_assign_pointer(pmc->sflist, newpsl); + if (psl) + kfree_rcu(psl, rcu); psl = newpsl; } rv = 1; /* > 0 for insert logic below if sl_count is 0 */ @@ -2507,11 +2508,13 @@ int ip_mc_msfilter(struct sock *sk, struct ip_msfilter *msf, int ifindex) /* decrease mem now to avoid the memleak warning */ atomic_sub(struct_size(psl, sl_addr, psl->sl_max), &sk->sk_omem_alloc); - kfree_rcu(psl, rcu); - } else + } else { (void) ip_mc_del_src(in_dev, &msf->imsf_multiaddr, pmc->sfmode, 0, NULL, 0); + } rcu_assign_pointer(pmc->sflist, newpsl); + if (psl) + kfree_rcu(psl, rcu); pmc->sfmode = msf->imsf_fmode; err = 0; done: diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 17440840a791..a5d57fa679ca 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -504,7 +504,7 @@ not_unique: return -EADDRNOTAVAIL; } -static u32 inet_sk_port_offset(const struct sock *sk) +static u64 inet_sk_port_offset(const struct sock *sk) { const struct inet_sock *inet = inet_sk(sk); @@ -726,15 +726,17 @@ EXPORT_SYMBOL_GPL(inet_unhash); * Note that we use 32bit integers (vs RFC 'short integers') * because 2^16 is not a multiple of num_ephemeral and this * property might be used by clever attacker. - * RFC claims using TABLE_LENGTH=10 buckets gives an improvement, - * we use 256 instead to really give more isolation and - * privacy, this only consumes 1 KB of kernel memory. + * RFC claims using TABLE_LENGTH=10 buckets gives an improvement, though + * attacks were since demonstrated, thus we use 65536 instead to really + * give more isolation and privacy, at the expense of 256kB of kernel + * memory. */ -#define INET_TABLE_PERTURB_SHIFT 8 -static u32 table_perturb[1 << INET_TABLE_PERTURB_SHIFT]; +#define INET_TABLE_PERTURB_SHIFT 16 +#define INET_TABLE_PERTURB_SIZE (1 << INET_TABLE_PERTURB_SHIFT) +static u32 *table_perturb; int __inet_hash_connect(struct inet_timewait_death_row *death_row, - struct sock *sk, u32 port_offset, + struct sock *sk, u64 port_offset, int (*check_established)(struct inet_timewait_death_row *, struct sock *, __u16, struct inet_timewait_sock **)) { @@ -774,10 +776,13 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, if (likely(remaining > 1)) remaining &= ~1U; - net_get_random_once(table_perturb, sizeof(table_perturb)); - index = hash_32(port_offset, INET_TABLE_PERTURB_SHIFT); + net_get_random_once(table_perturb, + INET_TABLE_PERTURB_SIZE * sizeof(*table_perturb)); + index = port_offset & (INET_TABLE_PERTURB_SIZE - 1); + + offset = READ_ONCE(table_perturb[index]) + (port_offset >> 32); + offset %= remaining; - offset = (READ_ONCE(table_perturb[index]) + port_offset) % remaining; /* In first pass we try ports of @low parity. * inet_csk_get_port() does the opposite choice. */ @@ -831,11 +836,12 @@ next_port: return -EADDRNOTAVAIL; ok: - /* If our first attempt found a candidate, skip next candidate - * in 1/16 of cases to add some noise. + /* Here we want to add a little bit of randomness to the next source + * port that will be chosen. We use a max() with a random here so that + * on low contention the randomness is maximal and on high contention + * it may be inexistent. */ - if (!i && !(prandom_u32() % 16)) - i = 2; + i = max_t(int, i, (prandom_u32() & 7) * 2); WRITE_ONCE(table_perturb[index], READ_ONCE(table_perturb[index]) + i + 2); /* Head lock still held and bh's disabled */ @@ -859,7 +865,7 @@ ok: int inet_hash_connect(struct inet_timewait_death_row *death_row, struct sock *sk) { - u32 port_offset = 0; + u64 port_offset = 0; if (!inet_sk(sk)->inet_num) port_offset = inet_sk_port_offset(sk); @@ -909,6 +915,12 @@ void __init inet_hashinfo2_init(struct inet_hashinfo *h, const char *name, low_limit, high_limit); init_hashinfo_lhash2(h); + + /* this one is used for source ports of outgoing connections */ + table_perturb = kmalloc_array(INET_TABLE_PERTURB_SIZE, + sizeof(*table_perturb), GFP_KERNEL); + if (!table_perturb) + panic("TCP: failed to alloc table_perturb"); } int inet_hashinfo2_init_mod(struct inet_hashinfo *h) diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index 9e0bbd026560..0ec501845cb3 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -52,7 +52,8 @@ static void inet_twsk_kill(struct inet_timewait_sock *tw) spin_unlock(lock); /* Disassociate with bind bucket. */ - bhead = &hashinfo->bhash[tw->tw_bslot]; + bhead = &hashinfo->bhash[inet_bhashfn(twsk_net(tw), tw->tw_num, + hashinfo->bhash_size)]; spin_lock(&bhead->lock); inet_twsk_bind_unhash(tw, hashinfo); @@ -111,12 +112,8 @@ void inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, Note, that any socket with inet->num != 0 MUST be bound in binding cache, even if it is closed. */ - /* Cache inet_bhashfn(), because 'struct net' might be no longer - * available later in inet_twsk_kill(). - */ - tw->tw_bslot = inet_bhashfn(twsk_net(tw), inet->inet_num, - hashinfo->bhash_size); - bhead = &hashinfo->bhash[tw->tw_bslot]; + bhead = &hashinfo->bhash[inet_bhashfn(twsk_net(tw), inet->inet_num, + hashinfo->bhash_size)]; spin_lock(&bhead->lock); tw->tw_tb = icsk->icsk_bind_hash; WARN_ON(!icsk->icsk_bind_hash); @@ -257,3 +254,50 @@ void __inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo, bool rearm) } } EXPORT_SYMBOL_GPL(__inet_twsk_schedule); + +void inet_twsk_purge(struct inet_hashinfo *hashinfo, int family) +{ + struct inet_timewait_sock *tw; + struct sock *sk; + struct hlist_nulls_node *node; + unsigned int slot; + + for (slot = 0; slot <= hashinfo->ehash_mask; slot++) { + struct inet_ehash_bucket *head = &hashinfo->ehash[slot]; +restart_rcu: + cond_resched(); + rcu_read_lock(); +restart: + sk_nulls_for_each_rcu(sk, node, &head->chain) { + if (sk->sk_state != TCP_TIME_WAIT) + continue; + tw = inet_twsk(sk); + if ((tw->tw_family != family) || + refcount_read(&twsk_net(tw)->ns.count)) + continue; + + if (unlikely(!refcount_inc_not_zero(&tw->tw_refcnt))) + continue; + + if (unlikely((tw->tw_family != family) || + refcount_read(&twsk_net(tw)->ns.count))) { + inet_twsk_put(tw); + goto restart; + } + + rcu_read_unlock(); + local_bh_disable(); + inet_twsk_deschedule_put(tw); + local_bh_enable(); + goto restart_rcu; + } + /* If the nulls value we got at the end of this lookup is + * not the expected one, we must restart lookup. + * We probably met an item that was moved to another chain. + */ + if (get_nulls_value(node) != slot) + goto restart; + rcu_read_unlock(); + } +} +EXPORT_SYMBOL_GPL(inet_twsk_purge); diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 99db2e41ed10..aacee9dd771b 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -459,14 +459,12 @@ static void __gre_xmit(struct sk_buff *skb, struct net_device *dev, __be16 proto) { struct ip_tunnel *tunnel = netdev_priv(dev); - - if (tunnel->parms.o_flags & TUNNEL_SEQ) - tunnel->o_seqno++; + __be16 flags = tunnel->parms.o_flags; /* Push GRE header. */ gre_build_header(skb, tunnel->tun_hlen, - tunnel->parms.o_flags, proto, tunnel->parms.o_key, - htonl(tunnel->o_seqno)); + flags, proto, tunnel->parms.o_key, + (flags & TUNNEL_SEQ) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) : 0); ip_tunnel_xmit(skb, dev, tnl_params, tnl_params->protocol); } @@ -504,7 +502,7 @@ static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev, (TUNNEL_CSUM | TUNNEL_KEY | TUNNEL_SEQ); gre_build_header(skb, tunnel_hlen, flags, proto, tunnel_id_to_key32(tun_info->key.tun_id), - (flags & TUNNEL_SEQ) ? htonl(tunnel->o_seqno++) : 0); + (flags & TUNNEL_SEQ) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) : 0); ip_md_tunnel_xmit(skb, dev, IPPROTO_GRE, tunnel_hlen); @@ -581,7 +579,7 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev) } gre_build_header(skb, 8, TUNNEL_SEQ, - proto, 0, htonl(tunnel->o_seqno++)); + proto, 0, htonl(atomic_fetch_inc(&tunnel->o_seqno))); ip_md_tunnel_xmit(skb, dev, IPPROTO_GRE, tunnel_hlen); @@ -605,8 +603,8 @@ static int gre_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) key = &info->key; ip_tunnel_init_flow(&fl4, IPPROTO_GRE, key->u.ipv4.dst, key->u.ipv4.src, tunnel_id_to_key32(key->tun_id), - key->tos & ~INET_ECN_MASK, 0, skb->mark, - skb_get_hash(skb)); + key->tos & ~INET_ECN_MASK, dev_net(dev), 0, + skb->mark, skb_get_hash(skb)); rt = ip_route_output_key(dev_net(dev), &fl4); if (IS_ERR(rt)) return PTR_ERR(rt); diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 5a473319d3a5..94017a8c3994 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -294,8 +294,8 @@ static int ip_tunnel_bind_dev(struct net_device *dev) ip_tunnel_init_flow(&fl4, iph->protocol, iph->daddr, iph->saddr, tunnel->parms.o_key, - RT_TOS(iph->tos), tunnel->parms.link, - tunnel->fwmark, 0); + RT_TOS(iph->tos), dev_net(dev), + tunnel->parms.link, tunnel->fwmark, 0); rt = ip_route_output_key(tunnel->net, &fl4); if (!IS_ERR(rt)) { @@ -570,7 +570,7 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, } ip_tunnel_init_flow(&fl4, proto, key->u.ipv4.dst, key->u.ipv4.src, tunnel_id_to_key32(key->tun_id), RT_TOS(tos), - 0, skb->mark, skb_get_hash(skb)); + dev_net(dev), 0, skb->mark, skb_get_hash(skb)); if (tunnel->encap.type != TUNNEL_ENCAP_NONE) goto tx_error; @@ -726,7 +726,8 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, } ip_tunnel_init_flow(&fl4, protocol, dst, tnl_params->saddr, - tunnel->parms.o_key, RT_TOS(tos), tunnel->parms.link, + tunnel->parms.o_key, RT_TOS(tos), + dev_net(dev), tunnel->parms.link, tunnel->fwmark, skb_get_hash(skb)); if (ip_tunnel_encap(skb, tunnel, &protocol, &fl4) < 0) diff --git a/net/ipv4/netfilter/nf_flow_table_ipv4.c b/net/ipv4/netfilter/nf_flow_table_ipv4.c deleted file mode 100644 index e69de29bb2d1..000000000000 --- a/net/ipv4/netfilter/nf_flow_table_ipv4.c +++ /dev/null diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 3ee947557b88..aa9a11b20d18 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -305,6 +305,7 @@ static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk, struct net *net = sock_net(sk); if (sk->sk_family == AF_INET) { struct sockaddr_in *addr = (struct sockaddr_in *) uaddr; + u32 tb_id = RT_TABLE_LOCAL; int chk_addr_ret; if (addr_len < sizeof(*addr)) @@ -318,7 +319,8 @@ static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk, pr_debug("ping_check_bind_addr(sk=%p,addr=%pI4,port=%d)\n", sk, &addr->sin_addr.s_addr, ntohs(addr->sin_port)); - chk_addr_ret = inet_addr_type(net, addr->sin_addr.s_addr); + tb_id = l3mdev_fib_table_by_index(net, sk->sk_bound_dev_if) ? : tb_id; + chk_addr_ret = inet_addr_type_table(net, addr->sin_addr.s_addr, tb_id); if (!inet_addr_valid_or_nonlocal(net, inet_sk(sk), addr->sin_addr.s_addr, @@ -355,6 +357,14 @@ static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk, return -ENODEV; } } + + if (!dev && sk->sk_bound_dev_if) { + dev = dev_get_by_index_rcu(net, sk->sk_bound_dev_if); + if (!dev) { + rcu_read_unlock(); + return -ENODEV; + } + } has_addr = pingv6_ops.ipv6_chk_addr(net, &addr->sin6_addr, dev, scoped); rcu_read_unlock(); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 98c6f3429593..ed01063d8f30 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1726,6 +1726,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, struct in_device *in_dev = __in_dev_get_rcu(dev); unsigned int flags = RTCF_MULTICAST; struct rtable *rth; + bool no_policy; u32 itag = 0; int err; @@ -1736,8 +1737,12 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, if (our) flags |= RTCF_LOCAL; + no_policy = IN_DEV_ORCONF(in_dev, NOPOLICY); + if (no_policy) + IPCB(skb)->flags |= IPSKB_NOPOLICY; + rth = rt_dst_alloc(dev_net(dev)->loopback_dev, flags, RTN_MULTICAST, - IN_DEV_ORCONF(in_dev, NOPOLICY), false); + no_policy, false); if (!rth) return -ENOBUFS; @@ -1753,6 +1758,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, #endif RT_CACHE_STAT_INC(in_slow_mc); + skb_dst_drop(skb); skb_dst_set(skb, &rth->dst); return 0; } @@ -1795,7 +1801,7 @@ static int __mkroute_input(struct sk_buff *skb, struct rtable *rth; int err; struct in_device *out_dev; - bool do_cache; + bool do_cache, no_policy; u32 itag = 0; /* get a working reference to the output device */ @@ -1840,6 +1846,10 @@ static int __mkroute_input(struct sk_buff *skb, } } + no_policy = IN_DEV_ORCONF(in_dev, NOPOLICY); + if (no_policy) + IPCB(skb)->flags |= IPSKB_NOPOLICY; + fnhe = find_exception(nhc, daddr); if (do_cache) { if (fnhe) @@ -1852,8 +1862,7 @@ static int __mkroute_input(struct sk_buff *skb, } } - rth = rt_dst_alloc(out_dev->dev, 0, res->type, - IN_DEV_ORCONF(in_dev, NOPOLICY), + rth = rt_dst_alloc(out_dev->dev, 0, res->type, no_policy, IN_DEV_ORCONF(out_dev, NOXFRM)); if (!rth) { err = -ENOBUFS; @@ -2228,6 +2237,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, struct rtable *rth; struct flowi4 fl4; bool do_cache = true; + bool no_policy; /* IP on this device is disabled. */ @@ -2346,6 +2356,10 @@ brd_input: RT_CACHE_STAT_INC(in_brd); local_input: + no_policy = IN_DEV_ORCONF(in_dev, NOPOLICY); + if (no_policy) + IPCB(skb)->flags |= IPSKB_NOPOLICY; + do_cache &= res->fi && !itag; if (do_cache) { struct fib_nh_common *nhc = FIB_RES_NHC(*res); @@ -2360,7 +2374,7 @@ local_input: rth = rt_dst_alloc(ip_rt_get_dev(net, res), flags | RTCF_LOCAL, res->type, - IN_DEV_ORCONF(in_dev, NOPOLICY), false); + no_policy, false); if (!rth) goto e_nobufs; diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 2cb3b852d148..f33c31dd7366 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -281,6 +281,7 @@ bool cookie_ecn_ok(const struct tcp_options_received *tcp_opt, EXPORT_SYMBOL(cookie_ecn_ok); struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops, + const struct tcp_request_sock_ops *af_ops, struct sock *sk, struct sk_buff *skb) { @@ -297,6 +298,10 @@ struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops, return NULL; treq = tcp_rsk(req); + + /* treq->af_specific might be used to perform TCP_MD5 lookup */ + treq->af_specific = af_ops; + treq->syn_tos = TCP_SKB_CB(skb)->ip_dsfield; #if IS_ENABLED(CONFIG_MPTCP) treq->is_mptcp = sk_is_mptcp(sk); @@ -364,7 +369,8 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) goto out; ret = NULL; - req = cookie_tcp_reqsk_alloc(&tcp_request_sock_ops, sk, skb); + req = cookie_tcp_reqsk_alloc(&tcp_request_sock_ops, + &tcp_request_sock_ipv4_ops, sk, skb); if (!req) goto out; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index cf18fbcbf123..bb7ef45408e1 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2335,8 +2335,10 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len, if (sk->sk_state == TCP_LISTEN) goto out; - if (tp->recvmsg_inq) + if (tp->recvmsg_inq) { *cmsg_flags = TCP_CMSG_INQ; + msg->msg_get_inq = 1; + } timeo = sock_rcvtimeo(sk, nonblock); /* Urgent data needs to be handled specially. */ @@ -2559,7 +2561,7 @@ recv_sndq: int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, int flags, int *addr_len) { - int cmsg_flags = 0, ret, inq; + int cmsg_flags = 0, ret; struct scm_timestamping_internal tss; if (unlikely(flags & MSG_ERRQUEUE)) @@ -2576,12 +2578,14 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, release_sock(sk); sk_defer_free_flush(sk); - if (cmsg_flags && ret >= 0) { + if ((cmsg_flags || msg->msg_get_inq) && ret >= 0) { if (cmsg_flags & TCP_CMSG_TS) tcp_recv_timestamp(msg, sk, &tss); - if (cmsg_flags & TCP_CMSG_INQ) { - inq = tcp_inq_hint(sk); - put_cmsg(msg, SOL_TCP, TCP_CM_INQ, sizeof(inq), &inq); + if (msg->msg_get_inq) { + msg->msg_inq = tcp_inq_hint(sk); + if (cmsg_flags & TCP_CMSG_INQ) + put_cmsg(msg, SOL_TCP, TCP_CM_INQ, + sizeof(msg->msg_inq), &msg->msg_inq); } } return ret; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 2088f93fa37b..60f99e9fb6d1 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3867,7 +3867,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) tcp_process_tlp_ack(sk, ack, flag); if (tcp_ack_is_dubious(sk, flag)) { - if (!(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP))) { + if (!(flag & (FLAG_SND_UNA_ADVANCED | + FLAG_NOT_DUP | FLAG_DSACKING_ACK))) { num_dupack = 1; /* Consider if pure acks were aggregated in tcp_add_backlog() */ if (!(flag & FLAG_DATA)) @@ -5454,7 +5455,17 @@ static void tcp_new_space(struct sock *sk) INDIRECT_CALL_1(sk->sk_write_space, sk_stream_write_space, sk); } -static void tcp_check_space(struct sock *sk) +/* Caller made space either from: + * 1) Freeing skbs in rtx queues (after tp->snd_una has advanced) + * 2) Sent skbs from output queue (and thus advancing tp->snd_nxt) + * + * We might be able to generate EPOLLOUT to the application if: + * 1) Space consumed in output/rtx queues is below sk->sk_sndbuf/2 + * 2) notsent amount (tp->write_seq - tp->snd_nxt) became + * small enough that tcp_stream_memory_free() decides it + * is time to generate EPOLLOUT. + */ +void tcp_check_space(struct sock *sk) { /* pairs with tcp_poll() */ smp_mb(); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index f9cec624068d..457f5b5d5d4a 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -3173,6 +3173,8 @@ static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list) { struct net *net; + inet_twsk_purge(&tcp_hashinfo, AF_INET); + list_for_each_entry(net, net_exit_list, exit_list) tcp_fastopen_ctx_destroy(net); } diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 6366df7aaf2a..6854bb1fb32b 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -531,7 +531,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->tsoffset = treq->ts_off; #ifdef CONFIG_TCP_MD5SIG newtp->md5sig_info = NULL; /*XXX*/ - if (newtp->af_specific->md5_lookup(sk, newsk)) + if (treq->af_specific->req_md5_lookup(sk, req_to_sk(req))) newtp->tcp_header_len += TCPOLEN_MD5SIG_ALIGNED; #endif if (skb->len >= TCP_MSS_DEFAULT + newtp->tcp_header_len) diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 9ede847f4199..1ca2f28c9981 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -82,6 +82,7 @@ static void tcp_event_new_data_sent(struct sock *sk, struct sk_buff *skb) NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPORIGDATASENT, tcp_skb_pcount(skb)); + tcp_check_space(sk); } /* SND.NXT, if window was not shrunk or the amount of shrunk was less than one diff --git a/net/ipv4/tcp_rate.c b/net/ipv4/tcp_rate.c index fbab921670cc..9a8e014d9b5b 100644 --- a/net/ipv4/tcp_rate.c +++ b/net/ipv4/tcp_rate.c @@ -74,27 +74,32 @@ void tcp_rate_skb_sent(struct sock *sk, struct sk_buff *skb) * * If an ACK (s)acks multiple skbs (e.g., stretched-acks), this function is * called multiple times. We favor the information from the most recently - * sent skb, i.e., the skb with the highest prior_delivered count. + * sent skb, i.e., the skb with the most recently sent time and the highest + * sequence. */ void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb, struct rate_sample *rs) { struct tcp_sock *tp = tcp_sk(sk); struct tcp_skb_cb *scb = TCP_SKB_CB(skb); + u64 tx_tstamp; if (!scb->tx.delivered_mstamp) return; + tx_tstamp = tcp_skb_timestamp_us(skb); if (!rs->prior_delivered || - after(scb->tx.delivered, rs->prior_delivered)) { + tcp_skb_sent_after(tx_tstamp, tp->first_tx_mstamp, + scb->end_seq, rs->last_end_seq)) { rs->prior_delivered_ce = scb->tx.delivered_ce; rs->prior_delivered = scb->tx.delivered; rs->prior_mstamp = scb->tx.delivered_mstamp; rs->is_app_limited = scb->tx.is_app_limited; rs->is_retrans = scb->sacked & TCPCB_RETRANS; + rs->last_end_seq = scb->end_seq; /* Record send time of most recently ACKed packet: */ - tp->first_tx_mstamp = tcp_skb_timestamp_us(skb); + tp->first_tx_mstamp = tx_tstamp; /* Find the duration of the "send phase" of this window: */ rs->interval_us = tcp_stamp_us_delta(tp->first_tx_mstamp, scb->tx.first_tx_mstamp); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index b22504176588..e7c68fa12fae 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -3972,8 +3972,6 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp) addrconf_join_solict(dev, &ifp->addr); - prandom_seed((__force u32) ifp->addr.s6_addr32[3]); - read_lock_bh(&idev->lock); spin_lock(&ifp->lock); if (ifp->state == INET6_IFADDR_STATE_DEAD) diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 55d604c9b3b3..f2120e92caf1 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -482,7 +482,6 @@ int esp6_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info struct page *page; struct sk_buff *trailer; int tailen = esp->tailen; - unsigned int allocsz; if (x->encap) { int err = esp6_output_encap(x, skb, esp); @@ -491,8 +490,8 @@ int esp6_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info return err; } - allocsz = ALIGN(skb->data_len + tailen, L1_CACHE_BYTES); - if (allocsz > ESP_SKB_FRAG_MAXSIZE) + if (ALIGN(tailen, L1_CACHE_BYTES) > PAGE_SIZE || + ALIGN(skb->data_len, L1_CACHE_BYTES) > PAGE_SIZE) goto cow; if (!skb_cloned(skb)) { diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index 4740afecf7c6..32ccac10bd62 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -308,7 +308,7 @@ not_unique: return -EADDRNOTAVAIL; } -static u32 inet6_sk_port_offset(const struct sock *sk) +static u64 inet6_sk_port_offset(const struct sock *sk) { const struct inet_sock *inet = inet_sk(sk); @@ -320,7 +320,7 @@ static u32 inet6_sk_port_offset(const struct sock *sk) int inet6_hash_connect(struct inet_timewait_death_row *death_row, struct sock *sk) { - u32 port_offset = 0; + u64 port_offset = 0; if (!inet_sk(sk)->inet_num) port_offset = inet6_sk_port_offset(sk); diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 8753e9cec326..5136959b3dc5 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -724,6 +724,7 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb, { struct ip6_tnl *tunnel = netdev_priv(dev); __be16 protocol; + __be16 flags; if (dev->type == ARPHRD_ETHER) IPCB(skb)->flags = 0; @@ -733,16 +734,13 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb, else fl6->daddr = tunnel->parms.raddr; - if (skb_cow_head(skb, dev->needed_headroom ?: tunnel->hlen)) - return -ENOMEM; - /* Push GRE header. */ protocol = (dev->type == ARPHRD_ETHER) ? htons(ETH_P_TEB) : proto; if (tunnel->parms.collect_md) { struct ip_tunnel_info *tun_info; const struct ip_tunnel_key *key; - __be16 flags; + int tun_hlen; tun_info = skb_tunnel_info_txcheck(skb); if (IS_ERR(tun_info) || @@ -760,21 +758,27 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb, dsfield = key->tos; flags = key->tun_flags & (TUNNEL_CSUM | TUNNEL_KEY | TUNNEL_SEQ); - tunnel->tun_hlen = gre_calc_hlen(flags); + tun_hlen = gre_calc_hlen(flags); - gre_build_header(skb, tunnel->tun_hlen, + if (skb_cow_head(skb, dev->needed_headroom ?: tun_hlen + tunnel->encap_hlen)) + return -ENOMEM; + + gre_build_header(skb, tun_hlen, flags, protocol, tunnel_id_to_key32(tun_info->key.tun_id), - (flags & TUNNEL_SEQ) ? htonl(tunnel->o_seqno++) + (flags & TUNNEL_SEQ) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) : 0); } else { - if (tunnel->parms.o_flags & TUNNEL_SEQ) - tunnel->o_seqno++; + if (skb_cow_head(skb, dev->needed_headroom ?: tunnel->hlen)) + return -ENOMEM; + + flags = tunnel->parms.o_flags; - gre_build_header(skb, tunnel->tun_hlen, tunnel->parms.o_flags, + gre_build_header(skb, tunnel->tun_hlen, flags, protocol, tunnel->parms.o_key, - htonl(tunnel->o_seqno)); + (flags & TUNNEL_SEQ) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) + : 0); } return ip6_tnl_xmit(skb, dev, dsfield, fl6, encap_limit, pmtu, @@ -1052,7 +1056,7 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, /* Push GRE header. */ proto = (t->parms.erspan_ver == 1) ? htons(ETH_P_ERSPAN) : htons(ETH_P_ERSPAN2); - gre_build_header(skb, 8, TUNNEL_SEQ, proto, 0, htonl(t->o_seqno++)); + gre_build_header(skb, 8, TUNNEL_SEQ, proto, 0, htonl(atomic_fetch_inc(&t->o_seqno))); /* TooBig packet may have updated dst->dev's mtu */ if (!t->parms.collect_md && dst && dst_mtu(dst) > dst->dev->mtu) diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index e23f058166af..fa63ef2bd99c 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -485,7 +485,7 @@ int ip6_forward(struct sk_buff *skb) goto drop; if (!net->ipv6.devconf_all->disable_policy && - !idev->cnf.disable_policy && + (!idev || !idev->cnf.disable_policy) && !xfrm6_policy_check(NULL, XFRM_POLICY_FWD, skb)) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS); goto drop; diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index a9775c830194..4e74bc61a3db 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -1653,7 +1653,6 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, sockptr_t optval, mifi_t mifi; struct net *net = sock_net(sk); struct mr_table *mrt; - bool do_wrmifwhole; if (sk->sk_type != SOCK_RAW || inet_sk(sk)->inet_num != IPPROTO_ICMPV6) @@ -1761,6 +1760,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, sockptr_t optval, #ifdef CONFIG_IPV6_PIMSM_V2 case MRT6_PIM: { + bool do_wrmifwhole; int v; if (optlen != sizeof(v)) diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 909f937befd7..7f695c39d9a8 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -460,10 +460,10 @@ int ip6_mc_source(int add, int omode, struct sock *sk, newpsl->sl_addr[i] = psl->sl_addr[i]; atomic_sub(struct_size(psl, sl_addr, psl->sl_max), &sk->sk_omem_alloc); - kfree_rcu(psl, rcu); } + rcu_assign_pointer(pmc->sflist, newpsl); + kfree_rcu(psl, rcu); psl = newpsl; - rcu_assign_pointer(pmc->sflist, psl); } rv = 1; /* > 0 for insert logic below if sl_count is 0 */ for (i = 0; i < psl->sl_count; i++) { @@ -565,12 +565,12 @@ int ip6_mc_msfilter(struct sock *sk, struct group_filter *gsf, psl->sl_count, psl->sl_addr, 0); atomic_sub(struct_size(psl, sl_addr, psl->sl_max), &sk->sk_omem_alloc); - kfree_rcu(psl, rcu); } else { ip6_mc_del_src(idev, group, pmc->sfmode, 0, NULL, 0); } - mutex_unlock(&idev->mc_lock); rcu_assign_pointer(pmc->sflist, newpsl); + mutex_unlock(&idev->mc_lock); + kfree_rcu(psl, rcu); pmc->sfmode = gsf->gf_fmode; err = 0; done: diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index 1da332450d98..8ce60ab89015 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -24,14 +24,13 @@ int ip6_route_me_harder(struct net *net, struct sock *sk_partial, struct sk_buff { const struct ipv6hdr *iph = ipv6_hdr(skb); struct sock *sk = sk_to_full_sk(sk_partial); + struct net_device *dev = skb_dst(skb)->dev; struct flow_keys flkeys; unsigned int hh_len; struct dst_entry *dst; int strict = (ipv6_addr_type(&iph->daddr) & (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL)); struct flowi6 fl6 = { - .flowi6_oif = sk && sk->sk_bound_dev_if ? sk->sk_bound_dev_if : - strict ? skb_dst(skb)->dev->ifindex : 0, .flowi6_mark = skb->mark, .flowi6_uid = sock_net_uid(net, sk), .daddr = iph->daddr, @@ -39,6 +38,13 @@ int ip6_route_me_harder(struct net *net, struct sock *sk_partial, struct sk_buff }; int err; + if (sk && sk->sk_bound_dev_if) + fl6.flowi6_oif = sk->sk_bound_dev_if; + else if (strict) + fl6.flowi6_oif = dev->ifindex; + else + fl6.flowi6_oif = l3mdev_master_ifindex(dev); + fib6_rules_early_flow_dissect(net, skb, &fl6, &flkeys); dst = ip6_route_output(net, sk, &fl6); err = dst->error; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 2fa10e60cccd..c4b6ce017d5e 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -3292,6 +3292,7 @@ static int ip6_dst_gc(struct dst_ops *ops) int rt_elasticity = net->ipv6.sysctl.ip6_rt_gc_elasticity; int rt_gc_timeout = net->ipv6.sysctl.ip6_rt_gc_timeout; unsigned long rt_last_gc = net->ipv6.ip6_rt_last_gc; + unsigned int val; int entries; entries = dst_entries_get_fast(ops); @@ -3302,13 +3303,13 @@ static int ip6_dst_gc(struct dst_ops *ops) entries <= rt_max_size) goto out; - net->ipv6.ip6_rt_gc_expire++; - fib6_run_gc(net->ipv6.ip6_rt_gc_expire, net, true); + fib6_run_gc(atomic_inc_return(&net->ipv6.ip6_rt_gc_expire), net, true); entries = dst_entries_get_slow(ops); if (entries < ops->gc_thresh) - net->ipv6.ip6_rt_gc_expire = rt_gc_timeout>>1; + atomic_set(&net->ipv6.ip6_rt_gc_expire, rt_gc_timeout >> 1); out: - net->ipv6.ip6_rt_gc_expire -= net->ipv6.ip6_rt_gc_expire>>rt_elasticity; + val = atomic_read(&net->ipv6.ip6_rt_gc_expire); + atomic_set(&net->ipv6.ip6_rt_gc_expire, val - (val >> rt_elasticity)); return entries > rt_max_size; } @@ -4484,7 +4485,7 @@ static int ip6_pkt_drop(struct sk_buff *skb, u8 code, int ipstats_mib_noroutes) struct inet6_dev *idev; int type; - if (netif_is_l3_master(skb->dev) && + if (netif_is_l3_master(skb->dev) || dst->dev == net->loopback_dev) idev = __in6_dev_get_safely(dev_get_by_index_rcu(net, IP6CB(skb)->iif)); else @@ -6509,7 +6510,7 @@ static int __net_init ip6_route_net_init(struct net *net) net->ipv6.sysctl.ip6_rt_min_advmss = IPV6_MIN_MTU - 20 - 40; net->ipv6.sysctl.skip_notify_on_dev_down = 0; - net->ipv6.ip6_rt_gc_expire = 30*HZ; + atomic_set(&net->ipv6.ip6_rt_gc_expire, 30*HZ); ret = 0; out: diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index d1b61d00368e..9cc123f000fb 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -170,7 +170,8 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) goto out; ret = NULL; - req = cookie_tcp_reqsk_alloc(&tcp6_request_sock_ops, sk, skb); + req = cookie_tcp_reqsk_alloc(&tcp6_request_sock_ops, + &tcp_request_sock_ipv6_ops, sk, skb); if (!req) goto out; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 13678d3908fa..faaddaf43c90 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -2207,9 +2207,15 @@ static void __net_exit tcpv6_net_exit(struct net *net) inet_ctl_sock_destroy(net->ipv6.tcp_sk); } +static void __net_exit tcpv6_net_exit_batch(struct list_head *net_exit_list) +{ + inet_twsk_purge(&tcp_hashinfo, AF_INET6); +} + static struct pernet_operations tcpv6_net_ops = { .init = tcpv6_net_init, .exit = tcpv6_net_exit, + .exit_batch = tcpv6_net_exit_batch, }; int __init tcpv6_init(void) diff --git a/net/key/af_key.c b/net/key/af_key.c index fd51db3be91c..339d95df19d3 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -2826,8 +2826,10 @@ static int pfkey_process(struct sock *sk, struct sk_buff *skb, const struct sadb void *ext_hdrs[SADB_EXT_MAX]; int err; - pfkey_broadcast(skb_clone(skb, GFP_KERNEL), GFP_KERNEL, - BROADCAST_PROMISC_ONLY, NULL, sock_net(sk)); + err = pfkey_broadcast(skb_clone(skb, GFP_KERNEL), GFP_KERNEL, + BROADCAST_PROMISC_ONLY, NULL, sock_net(sk)); + if (err) + return err; memset(ext_hdrs, 0, sizeof(ext_hdrs)); err = parse_exthdrs(skb, hdr, ext_hdrs); @@ -2898,7 +2900,7 @@ static int count_ah_combs(const struct xfrm_tmpl *t) break; if (!aalg->pfkey_supported) continue; - if (aalg_tmpl_set(t, aalg)) + if (aalg_tmpl_set(t, aalg) && aalg->available) sz += sizeof(struct sadb_comb); } return sz + sizeof(struct sadb_prop); @@ -2916,7 +2918,7 @@ static int count_esp_combs(const struct xfrm_tmpl *t) if (!ealg->pfkey_supported) continue; - if (!(ealg_tmpl_set(t, ealg))) + if (!(ealg_tmpl_set(t, ealg) && ealg->available)) continue; for (k = 1; ; k++) { @@ -2927,7 +2929,7 @@ static int count_esp_combs(const struct xfrm_tmpl *t) if (!aalg->pfkey_supported) continue; - if (aalg_tmpl_set(t, aalg)) + if (aalg_tmpl_set(t, aalg) && aalg->available) sz += sizeof(struct sadb_comb); } } diff --git a/net/l3mdev/l3mdev.c b/net/l3mdev/l3mdev.c index 4eb8892fb2ff..ca10916340b0 100644 --- a/net/l3mdev/l3mdev.c +++ b/net/l3mdev/l3mdev.c @@ -147,7 +147,7 @@ int l3mdev_master_upper_ifindex_by_index_rcu(struct net *net, int ifindex) dev = dev_get_by_index_rcu(net, ifindex); while (dev && !netif_is_l3_master(dev)) - dev = netdev_master_upper_dev_get(dev); + dev = netdev_master_upper_dev_get_rcu(dev); return dev ? dev->ifindex : 0; } diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c index 9479f2787ea7..88d9cc945a21 100644 --- a/net/mac80211/debugfs_sta.c +++ b/net/mac80211/debugfs_sta.c @@ -441,7 +441,7 @@ static ssize_t sta_ht_capa_read(struct file *file, char __user *userbuf, #define PRINT_HT_CAP(_cond, _str) \ do { \ if (_cond) \ - p += scnprintf(p, sizeof(buf)+buf-p, "\t" _str "\n"); \ + p += scnprintf(p, bufsz + buf - p, "\t" _str "\n"); \ } while (0) char *buf, *p; int i; diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 1b30c724ca8d..dc8aec1a5d3d 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -3657,6 +3657,12 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, cbss->transmitted_bss->bssid); bss_conf->bssid_indicator = cbss->max_bssid_indicator; bss_conf->bssid_index = cbss->bssid_index; + } else { + bss_conf->nontransmitted = false; + memset(bss_conf->transmitter_bssid, 0, + sizeof(bss_conf->transmitter_bssid)); + bss_conf->bssid_indicator = 0; + bss_conf->bssid_index = 0; } /* diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index beb6b92eb780..88d797fa82ff 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -1405,8 +1405,7 @@ static void ieee80211_rx_reorder_ampdu(struct ieee80211_rx_data *rx, goto dont_reorder; /* not part of a BA session */ - if (ack_policy != IEEE80211_QOS_CTL_ACK_POLICY_BLOCKACK && - ack_policy != IEEE80211_QOS_CTL_ACK_POLICY_NORMAL) + if (ack_policy == IEEE80211_QOS_CTL_ACK_POLICY_NOACK) goto dont_reorder; /* new, potentially un-ordered, ampdu frame - process it */ diff --git a/net/mctp/af_mctp.c b/net/mctp/af_mctp.c index f0702d920d8d..e22b0cbb2f35 100644 --- a/net/mctp/af_mctp.c +++ b/net/mctp/af_mctp.c @@ -93,13 +93,13 @@ out_release: static int mctp_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { DECLARE_SOCKADDR(struct sockaddr_mctp *, addr, msg->msg_name); - const int hlen = MCTP_HEADER_MAXLEN + sizeof(struct mctp_hdr); int rc, addrlen = msg->msg_namelen; struct sock *sk = sock->sk; struct mctp_sock *msk = container_of(sk, struct mctp_sock, sk); struct mctp_skb_cb *cb; struct mctp_route *rt; - struct sk_buff *skb; + struct sk_buff *skb = NULL; + int hlen; if (addr) { const u8 tagbits = MCTP_TAG_MASK | MCTP_TAG_OWNER | @@ -129,6 +129,34 @@ static int mctp_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) if (addr->smctp_network == MCTP_NET_ANY) addr->smctp_network = mctp_default_net(sock_net(sk)); + /* direct addressing */ + if (msk->addr_ext && addrlen >= sizeof(struct sockaddr_mctp_ext)) { + DECLARE_SOCKADDR(struct sockaddr_mctp_ext *, + extaddr, msg->msg_name); + struct net_device *dev; + + rc = -EINVAL; + rcu_read_lock(); + dev = dev_get_by_index_rcu(sock_net(sk), extaddr->smctp_ifindex); + /* check for correct halen */ + if (dev && extaddr->smctp_halen == dev->addr_len) { + hlen = LL_RESERVED_SPACE(dev) + sizeof(struct mctp_hdr); + rc = 0; + } + rcu_read_unlock(); + if (rc) + goto err_free; + rt = NULL; + } else { + rt = mctp_route_lookup(sock_net(sk), addr->smctp_network, + addr->smctp_addr.s_addr); + if (!rt) { + rc = -EHOSTUNREACH; + goto err_free; + } + hlen = LL_RESERVED_SPACE(rt->dev->dev) + sizeof(struct mctp_hdr); + } + skb = sock_alloc_send_skb(sk, hlen + 1 + len, msg->msg_flags & MSG_DONTWAIT, &rc); if (!skb) @@ -147,8 +175,8 @@ static int mctp_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) cb = __mctp_cb(skb); cb->net = addr->smctp_network; - /* direct addressing */ - if (msk->addr_ext && addrlen >= sizeof(struct sockaddr_mctp_ext)) { + if (!rt) { + /* fill extended address in cb */ DECLARE_SOCKADDR(struct sockaddr_mctp_ext *, extaddr, msg->msg_name); @@ -159,17 +187,9 @@ static int mctp_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) } cb->ifindex = extaddr->smctp_ifindex; + /* smctp_halen is checked above */ cb->halen = extaddr->smctp_halen; memcpy(cb->haddr, extaddr->smctp_haddr, cb->halen); - - rt = NULL; - } else { - rt = mctp_route_lookup(sock_net(sk), addr->smctp_network, - addr->smctp_addr.s_addr); - if (!rt) { - rc = -EHOSTUNREACH; - goto err_free; - } } rc = mctp_local_output(sk, rt, skb, addr->smctp_addr.s_addr, diff --git a/net/mctp/device.c b/net/mctp/device.c index f49be882e98e..99a3bda8852f 100644 --- a/net/mctp/device.c +++ b/net/mctp/device.c @@ -313,6 +313,7 @@ void mctp_dev_hold(struct mctp_dev *mdev) void mctp_dev_put(struct mctp_dev *mdev) { if (mdev && refcount_dec_and_test(&mdev->refs)) { + kfree(mdev->addrs); dev_put(mdev->dev); kfree_rcu(mdev, rcu); } @@ -441,7 +442,6 @@ static void mctp_unregister(struct net_device *dev) mctp_route_remove_dev(mdev); mctp_neigh_remove_dev(mdev); - kfree(mdev->addrs); mctp_dev_put(mdev); } diff --git a/net/mctp/route.c b/net/mctp/route.c index d5e7db83fe9d..3b24b8d18b5b 100644 --- a/net/mctp/route.c +++ b/net/mctp/route.c @@ -503,6 +503,11 @@ static int mctp_route_output(struct mctp_route *route, struct sk_buff *skb) if (cb->ifindex) { /* direct route; use the hwaddr we stashed in sendmsg */ + if (cb->halen != skb->dev->addr_len) { + /* sanity check, sendmsg should have already caught this */ + kfree_skb(skb); + return -EMSGSIZE; + } daddr = cb->haddr; } else { /* If lookup fails let the device handle daddr==NULL */ @@ -512,7 +517,7 @@ static int mctp_route_output(struct mctp_route *route, struct sk_buff *skb) rc = dev_hard_header(skb, skb->dev, ntohs(skb->protocol), daddr, skb->dev->dev_addr, skb->len); - if (rc) { + if (rc < 0) { kfree_skb(skb); return -EHOSTUNREACH; } @@ -756,7 +761,7 @@ static int mctp_do_fragment_route(struct mctp_route *rt, struct sk_buff *skb, { const unsigned int hlen = sizeof(struct mctp_hdr); struct mctp_hdr *hdr, *hdr2; - unsigned int pos, size; + unsigned int pos, size, headroom; struct sk_buff *skb2; int rc; u8 seq; @@ -770,6 +775,9 @@ static int mctp_do_fragment_route(struct mctp_route *rt, struct sk_buff *skb, return -EMSGSIZE; } + /* keep same headroom as the original skb */ + headroom = skb_headroom(skb); + /* we've got the header */ skb_pull(skb, hlen); @@ -777,7 +785,7 @@ static int mctp_do_fragment_route(struct mctp_route *rt, struct sk_buff *skb, /* size of message payload */ size = min(mtu - hlen, skb->len - pos); - skb2 = alloc_skb(MCTP_HEADER_MAXLEN + hlen + size, GFP_KERNEL); + skb2 = alloc_skb(headroom + hlen + size, GFP_KERNEL); if (!skb2) { rc = -ENOMEM; break; @@ -793,7 +801,7 @@ static int mctp_do_fragment_route(struct mctp_route *rt, struct sk_buff *skb, skb_set_owner_w(skb2, skb->sk); /* establish packet */ - skb_reserve(skb2, MCTP_HEADER_MAXLEN); + skb_reserve(skb2, headroom); skb_reset_network_header(skb2); skb_put(skb2, hlen + size); skb2->transport_header = skb2->network_header + hlen; diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 325383646f5c..b548cec86c9d 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -107,7 +107,7 @@ static void mptcp_parse_option(const struct sk_buff *skb, ptr += 2; } if (opsize == TCPOLEN_MPTCP_MPC_ACK_DATA_CSUM) { - mp_opt->csum = (__force __sum16)get_unaligned_be16(ptr); + mp_opt->csum = get_unaligned((__force __sum16 *)ptr); mp_opt->suboptions |= OPTION_MPTCP_CSUMREQD; ptr += 2; } @@ -221,7 +221,7 @@ static void mptcp_parse_option(const struct sk_buff *skb, if (opsize == expected_opsize + TCPOLEN_MPTCP_DSS_CHECKSUM) { mp_opt->suboptions |= OPTION_MPTCP_CSUMREQD; - mp_opt->csum = (__force __sum16)get_unaligned_be16(ptr); + mp_opt->csum = get_unaligned((__force __sum16 *)ptr); ptr += 2; } @@ -1240,7 +1240,7 @@ static void mptcp_set_rwin(const struct tcp_sock *tp) WRITE_ONCE(msk->rcv_wnd_sent, ack_seq); } -u16 __mptcp_make_csum(u64 data_seq, u32 subflow_seq, u16 data_len, __wsum sum) +__sum16 __mptcp_make_csum(u64 data_seq, u32 subflow_seq, u16 data_len, __wsum sum) { struct csum_pseudo_header header; __wsum csum; @@ -1256,15 +1256,25 @@ u16 __mptcp_make_csum(u64 data_seq, u32 subflow_seq, u16 data_len, __wsum sum) header.csum = 0; csum = csum_partial(&header, sizeof(header), sum); - return (__force u16)csum_fold(csum); + return csum_fold(csum); } -static u16 mptcp_make_csum(const struct mptcp_ext *mpext) +static __sum16 mptcp_make_csum(const struct mptcp_ext *mpext) { return __mptcp_make_csum(mpext->data_seq, mpext->subflow_seq, mpext->data_len, ~csum_unfold(mpext->csum)); } +static void put_len_csum(u16 len, __sum16 csum, void *data) +{ + __sum16 *sumptr = data + 2; + __be16 *ptr = data; + + put_unaligned_be16(len, ptr); + + put_unaligned(csum, sumptr); +} + void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp, struct mptcp_out_options *opts) { @@ -1340,8 +1350,9 @@ void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp, put_unaligned_be32(mpext->subflow_seq, ptr); ptr += 1; if (opts->csum_reqd) { - put_unaligned_be32(mpext->data_len << 16 | - mptcp_make_csum(mpext), ptr); + put_len_csum(mpext->data_len, + mptcp_make_csum(mpext), + ptr); } else { put_unaligned_be32(mpext->data_len << 16 | TCPOPT_NOP << 8 | TCPOPT_NOP, ptr); @@ -1392,11 +1403,12 @@ void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp, goto mp_capable_done; if (opts->csum_reqd) { - put_unaligned_be32(opts->data_len << 16 | - __mptcp_make_csum(opts->data_seq, - opts->subflow_seq, - opts->data_len, - ~csum_unfold(opts->csum)), ptr); + put_len_csum(opts->data_len, + __mptcp_make_csum(opts->data_seq, + opts->subflow_seq, + opts->data_len, + ~csum_unfold(opts->csum)), + ptr); } else { put_unaligned_be32(opts->data_len << 16 | TCPOPT_NOP << 8 | TCPOPT_NOP, ptr); diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index 01809eef29b4..aa51b100e033 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -178,14 +178,13 @@ void mptcp_pm_subflow_check_next(struct mptcp_sock *msk, const struct sock *ssk, struct mptcp_pm_data *pm = &msk->pm; bool update_subflows; - update_subflows = (ssk->sk_state == TCP_CLOSE) && - (subflow->request_join || subflow->mp_join); + update_subflows = subflow->request_join || subflow->mp_join; if (!READ_ONCE(pm->work_pending) && !update_subflows) return; spin_lock_bh(&pm->lock); if (update_subflows) - pm->subflows--; + __mptcp_pm_close_subflow(msk); /* Even if this subflow is not really established, tell the PM to try * to pick the next ones, if possible. diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 3c1a3036550f..5655a63aa6a8 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -443,7 +443,8 @@ struct mptcp_subflow_context { can_ack : 1, /* only after processing the remote a key */ disposable : 1, /* ctx can be free at ulp release time */ stale : 1, /* unable to snd/rcv data, do not use for xmit */ - local_id_valid : 1; /* local_id is correctly initialized */ + local_id_valid : 1, /* local_id is correctly initialized */ + valid_csum_seen : 1; /* at least one csum validated */ enum mptcp_data_avail data_avail; u32 remote_nonce; u64 thmac; @@ -723,7 +724,7 @@ void mptcp_token_destroy(struct mptcp_sock *msk); void mptcp_crypto_key_sha(u64 key, u32 *token, u64 *idsn); void mptcp_crypto_hmac_sha(u64 key1, u64 key2, u8 *msg, int len, void *hmac); -u16 __mptcp_make_csum(u64 data_seq, u32 subflow_seq, u16 data_len, __wsum sum); +__sum16 __mptcp_make_csum(u64 data_seq, u32 subflow_seq, u16 data_len, __wsum sum); void __init mptcp_pm_init(void); void mptcp_pm_data_init(struct mptcp_sock *msk); @@ -833,6 +834,20 @@ unsigned int mptcp_pm_get_add_addr_accept_max(const struct mptcp_sock *msk); unsigned int mptcp_pm_get_subflows_max(const struct mptcp_sock *msk); unsigned int mptcp_pm_get_local_addr_max(const struct mptcp_sock *msk); +/* called under PM lock */ +static inline void __mptcp_pm_close_subflow(struct mptcp_sock *msk) +{ + if (--msk->pm.subflows < mptcp_pm_get_subflows_max(msk)) + WRITE_ONCE(msk->pm.accept_subflow, true); +} + +static inline void mptcp_pm_close_subflow(struct mptcp_sock *msk) +{ + spin_lock_bh(&msk->pm.lock); + __mptcp_pm_close_subflow(msk); + spin_unlock_bh(&msk->pm.lock); +} + void mptcp_sockopt_sync(struct mptcp_sock *msk, struct sock *ssk); void mptcp_sockopt_sync_locked(struct mptcp_sock *msk, struct sock *ssk); diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index aba260f547da..be76ada89d96 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -888,7 +888,7 @@ static enum mapping_status validate_data_csum(struct sock *ssk, struct sk_buff * { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); u32 offset, seq, delta; - u16 csum; + __sum16 csum; int len; if (!csum_reqd) @@ -955,11 +955,14 @@ static enum mapping_status validate_data_csum(struct sock *ssk, struct sk_buff * subflow->map_data_csum); if (unlikely(csum)) { MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DATACSUMERR); - subflow->send_mp_fail = 1; - MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_MPFAILTX); + if (subflow->mp_join || subflow->valid_csum_seen) { + subflow->send_mp_fail = 1; + MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_MPFAILTX); + } return subflow->mp_join ? MAPPING_INVALID : MAPPING_DUMMY; } + subflow->valid_csum_seen = 1; return MAPPING_OK; } @@ -1141,6 +1144,18 @@ static void subflow_sched_work_if_closed(struct mptcp_sock *msk, struct sock *ss } } +static bool subflow_can_fallback(struct mptcp_subflow_context *subflow) +{ + struct mptcp_sock *msk = mptcp_sk(subflow->conn); + + if (subflow->mp_join) + return false; + else if (READ_ONCE(msk->csum_enabled)) + return !subflow->valid_csum_seen; + else + return !subflow->fully_established; +} + static bool subflow_check_data_avail(struct sock *ssk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); @@ -1218,7 +1233,7 @@ fallback: return true; } - if (subflow->mp_join || subflow->fully_established) { + if (!subflow_can_fallback(subflow)) { /* fatal protocol error, close the socket. * subflow_error_report() will introduce the appropriate barriers */ @@ -1422,20 +1437,20 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc, struct sockaddr_storage addr; int remote_id = remote->id; int local_id = loc->id; + int err = -ENOTCONN; struct socket *sf; struct sock *ssk; u32 remote_token; int addrlen; int ifindex; u8 flags; - int err; if (!mptcp_is_fully_established(sk)) - return -ENOTCONN; + goto err_out; err = mptcp_subflow_create_socket(sk, &sf); if (err) - return err; + goto err_out; ssk = sf->sk; subflow = mptcp_subflow_ctx(ssk); @@ -1492,6 +1507,12 @@ failed_unlink: failed: subflow->disposable = 1; sock_release(sf); + +err_out: + /* we account subflows before the creation, and this failures will not + * be caught by sk_state_change() + */ + mptcp_pm_close_subflow(msk); return err; } diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index 2c467c422dc6..fb67f1ca2495 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -1495,7 +1495,7 @@ int __init ip_vs_conn_init(void) pr_info("Connection hash table configured " "(size=%d, memory=%ldKbytes)\n", ip_vs_conn_tab_size, - (long)(ip_vs_conn_tab_size*sizeof(struct list_head))/1024); + (long)(ip_vs_conn_tab_size*sizeof(*ip_vs_conn_tab))/1024); IP_VS_DBG(0, "Each connection entry needs %zd bytes at least\n", sizeof(struct ip_vs_conn)); diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 8ec55cd72572..204a5cdff5b1 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -556,24 +556,14 @@ static bool tcp_in_window(struct nf_conn *ct, } } - } else if (((state->state == TCP_CONNTRACK_SYN_SENT - && dir == IP_CT_DIR_ORIGINAL) - || (state->state == TCP_CONNTRACK_SYN_RECV - && dir == IP_CT_DIR_REPLY)) - && after(end, sender->td_end)) { + } else if (tcph->syn && + after(end, sender->td_end) && + (state->state == TCP_CONNTRACK_SYN_SENT || + state->state == TCP_CONNTRACK_SYN_RECV)) { /* * RFC 793: "if a TCP is reinitialized ... then it need * not wait at all; it must only be sure to use sequence * numbers larger than those recently used." - */ - sender->td_end = - sender->td_maxend = end; - sender->td_maxwin = (win == 0 ? 1 : win); - - tcp_options(skb, dataoff, tcph, sender); - } else if (tcph->syn && dir == IP_CT_DIR_REPLY && - state->state == TCP_CONNTRACK_SYN_SENT) { - /* Retransmitted syn-ack, or syn (simultaneous open). * * Re-init state for this direction, just like for the first * syn(-ack) reply, it might differ in seq, ack or tcp options. @@ -581,7 +571,8 @@ static bool tcp_in_window(struct nf_conn *ct, tcp_init_sender(sender, receiver, skb, dataoff, tcph, end, win); - if (!tcph->ack) + + if (dir == IP_CT_DIR_REPLY && !tcph->ack) return true; } diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 3e1afd10a9b6..55aa55b252b2 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -823,7 +823,7 @@ static struct ctl_table nf_ct_sysctl_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, -#if IS_ENABLED(CONFIG_NFT_FLOW_OFFLOAD) +#if IS_ENABLED(CONFIG_NF_FLOW_TABLE) [NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD] = { .procname = "nf_flowtable_udp_timeout", .maxlen = sizeof(unsigned int), diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 3db256da919b..f2def06d1070 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -179,12 +179,11 @@ EXPORT_SYMBOL_GPL(flow_offload_route_init); static void flow_offload_fixup_tcp(struct ip_ct_tcp *tcp) { - tcp->state = TCP_CONNTRACK_ESTABLISHED; tcp->seen[0].td_maxwin = 0; tcp->seen[1].td_maxwin = 0; } -static void flow_offload_fixup_ct_timeout(struct nf_conn *ct) +static void flow_offload_fixup_ct(struct nf_conn *ct) { struct net *net = nf_ct_net(ct); int l4num = nf_ct_protonum(ct); @@ -193,7 +192,9 @@ static void flow_offload_fixup_ct_timeout(struct nf_conn *ct) if (l4num == IPPROTO_TCP) { struct nf_tcp_net *tn = nf_tcp_pernet(net); - timeout = tn->timeouts[TCP_CONNTRACK_ESTABLISHED]; + flow_offload_fixup_tcp(&ct->proto.tcp); + + timeout = tn->timeouts[ct->proto.tcp.state]; timeout -= tn->offload_timeout; } else if (l4num == IPPROTO_UDP) { struct nf_udp_net *tn = nf_udp_pernet(net); @@ -211,18 +212,6 @@ static void flow_offload_fixup_ct_timeout(struct nf_conn *ct) WRITE_ONCE(ct->timeout, nfct_time_stamp + timeout); } -static void flow_offload_fixup_ct_state(struct nf_conn *ct) -{ - if (nf_ct_protonum(ct) == IPPROTO_TCP) - flow_offload_fixup_tcp(&ct->proto.tcp); -} - -static void flow_offload_fixup_ct(struct nf_conn *ct) -{ - flow_offload_fixup_ct_state(ct); - flow_offload_fixup_ct_timeout(ct); -} - static void flow_offload_route_release(struct flow_offload *flow) { nft_flow_dst_release(flow, FLOW_OFFLOAD_DIR_ORIGINAL); @@ -335,8 +324,10 @@ void flow_offload_refresh(struct nf_flowtable *flow_table, u32 timeout; timeout = nf_flowtable_time_stamp + flow_offload_get_timeout(flow); - if (READ_ONCE(flow->timeout) != timeout) + if (timeout - READ_ONCE(flow->timeout) > HZ) WRITE_ONCE(flow->timeout, timeout); + else + return; if (likely(!nf_flowtable_hw_offload(flow_table))) return; @@ -359,22 +350,14 @@ static void flow_offload_del(struct nf_flowtable *flow_table, rhashtable_remove_fast(&flow_table->rhashtable, &flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].node, nf_flow_offload_rhash_params); - - clear_bit(IPS_OFFLOAD_BIT, &flow->ct->status); - - if (nf_flow_has_expired(flow)) - flow_offload_fixup_ct(flow->ct); - else - flow_offload_fixup_ct_timeout(flow->ct); - flow_offload_free(flow); } void flow_offload_teardown(struct flow_offload *flow) { + clear_bit(IPS_OFFLOAD_BIT, &flow->ct->status); set_bit(NF_FLOW_TEARDOWN, &flow->flags); - - flow_offload_fixup_ct_state(flow->ct); + flow_offload_fixup_ct(flow->ct); } EXPORT_SYMBOL_GPL(flow_offload_teardown); @@ -438,33 +421,12 @@ nf_flow_table_iterate(struct nf_flowtable *flow_table, return err; } -static bool flow_offload_stale_dst(struct flow_offload_tuple *tuple) -{ - struct dst_entry *dst; - - if (tuple->xmit_type == FLOW_OFFLOAD_XMIT_NEIGH || - tuple->xmit_type == FLOW_OFFLOAD_XMIT_XFRM) { - dst = tuple->dst_cache; - if (!dst_check(dst, tuple->dst_cookie)) - return true; - } - - return false; -} - -static bool nf_flow_has_stale_dst(struct flow_offload *flow) -{ - return flow_offload_stale_dst(&flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple) || - flow_offload_stale_dst(&flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple); -} - static void nf_flow_offload_gc_step(struct nf_flowtable *flow_table, struct flow_offload *flow, void *data) { if (nf_flow_has_expired(flow) || - nf_ct_is_dying(flow->ct) || - nf_flow_has_stale_dst(flow)) - set_bit(NF_FLOW_TEARDOWN, &flow->flags); + nf_ct_is_dying(flow->ct)) + flow_offload_teardown(flow); if (test_bit(NF_FLOW_TEARDOWN, &flow->flags)) { if (test_bit(NF_FLOW_HW, &flow->flags)) { diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c index 32c0eb1b4821..b350fe9d00b0 100644 --- a/net/netfilter/nf_flow_table_ip.c +++ b/net/netfilter/nf_flow_table_ip.c @@ -248,6 +248,15 @@ static bool nf_flow_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu) return true; } +static inline bool nf_flow_dst_check(struct flow_offload_tuple *tuple) +{ + if (tuple->xmit_type != FLOW_OFFLOAD_XMIT_NEIGH && + tuple->xmit_type != FLOW_OFFLOAD_XMIT_XFRM) + return true; + + return dst_check(tuple->dst_cache, tuple->dst_cookie); +} + static unsigned int nf_flow_xmit_xfrm(struct sk_buff *skb, const struct nf_hook_state *state, struct dst_entry *dst) @@ -367,6 +376,11 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, if (nf_flow_state_check(flow, iph->protocol, skb, thoff)) return NF_ACCEPT; + if (!nf_flow_dst_check(&tuplehash->tuple)) { + flow_offload_teardown(flow); + return NF_ACCEPT; + } + if (skb_try_make_writable(skb, thoff + hdrsize)) return NF_DROP; @@ -624,6 +638,11 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb, if (nf_flow_state_check(flow, ip6h->nexthdr, skb, thoff)) return NF_ACCEPT; + if (!nf_flow_dst_check(&tuplehash->tuple)) { + flow_offload_teardown(flow); + return NF_ACCEPT; + } + if (skb_try_make_writable(skb, thoff + hdrsize)) return NF_DROP; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 5ddfdb2adaf1..a096b9fbbbdf 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -5526,7 +5526,7 @@ int nft_set_elem_expr_clone(const struct nft_ctx *ctx, struct nft_set *set, int err, i, k; for (i = 0; i < set->num_exprs; i++) { - expr = kzalloc(set->exprs[i]->ops->size, GFP_KERNEL); + expr = kzalloc(set->exprs[i]->ops->size, GFP_KERNEL_ACCOUNT); if (!expr) goto err_expr; @@ -8342,16 +8342,7 @@ EXPORT_SYMBOL_GPL(nf_tables_trans_destroy_flush_work); static bool nft_expr_reduce(struct nft_regs_track *track, const struct nft_expr *expr) { - if (!expr->ops->reduce) { - pr_warn_once("missing reduce for expression %s ", - expr->ops->type->name); - return false; - } - - if (nft_reduce_is_readonly(expr)) - return false; - - return expr->ops->reduce(track, expr); + return false; } static int nf_tables_commit_chain_prepare(struct net *net, struct nft_chain *chain) @@ -9363,7 +9354,7 @@ int nft_parse_u32_check(const struct nlattr *attr, int max, u32 *dest) } EXPORT_SYMBOL_GPL(nft_parse_u32_check); -static unsigned int nft_parse_register(const struct nlattr *attr, u32 *preg) +static int nft_parse_register(const struct nlattr *attr, u32 *preg) { unsigned int reg; diff --git a/net/netfilter/nft_bitwise.c b/net/netfilter/nft_bitwise.c index 38caa66632b4..f590ee1c8a1b 100644 --- a/net/netfilter/nft_bitwise.c +++ b/net/netfilter/nft_bitwise.c @@ -290,7 +290,7 @@ static bool nft_bitwise_reduce(struct nft_regs_track *track, if (!track->regs[priv->sreg].selector) return false; - bitwise = nft_expr_priv(expr); + bitwise = nft_expr_priv(track->regs[priv->dreg].selector); if (track->regs[priv->sreg].selector == track->regs[priv->dreg].selector && track->regs[priv->sreg].num_reg == 0 && track->regs[priv->dreg].bitwise && @@ -442,7 +442,7 @@ static bool nft_bitwise_fast_reduce(struct nft_regs_track *track, if (!track->regs[priv->sreg].selector) return false; - bitwise = nft_expr_priv(expr); + bitwise = nft_expr_priv(track->regs[priv->dreg].selector); if (track->regs[priv->sreg].selector == track->regs[priv->dreg].selector && track->regs[priv->dreg].bitwise && track->regs[priv->dreg].bitwise->ops == expr->ops && diff --git a/net/netfilter/nft_connlimit.c b/net/netfilter/nft_connlimit.c index 9de1462e4ac4..d657f999a11b 100644 --- a/net/netfilter/nft_connlimit.c +++ b/net/netfilter/nft_connlimit.c @@ -77,7 +77,7 @@ static int nft_connlimit_do_init(const struct nft_ctx *ctx, invert = true; } - priv->list = kmalloc(sizeof(*priv->list), GFP_KERNEL); + priv->list = kmalloc(sizeof(*priv->list), GFP_KERNEL_ACCOUNT); if (!priv->list) return -ENOMEM; diff --git a/net/netfilter/nft_counter.c b/net/netfilter/nft_counter.c index da9083605a61..f4d3573e8782 100644 --- a/net/netfilter/nft_counter.c +++ b/net/netfilter/nft_counter.c @@ -62,7 +62,7 @@ static int nft_counter_do_init(const struct nlattr * const tb[], struct nft_counter __percpu *cpu_stats; struct nft_counter *this_cpu; - cpu_stats = alloc_percpu(struct nft_counter); + cpu_stats = alloc_percpu_gfp(struct nft_counter, GFP_KERNEL_ACCOUNT); if (cpu_stats == NULL) return -ENOMEM; diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c index 900d48c810a1..6f0b07fe648d 100644 --- a/net/netfilter/nft_flow_offload.c +++ b/net/netfilter/nft_flow_offload.c @@ -36,6 +36,15 @@ static void nft_default_forward_path(struct nf_flow_route *route, route->tuple[dir].xmit_type = nft_xmit_type(dst_cache); } +static bool nft_is_valid_ether_device(const struct net_device *dev) +{ + if (!dev || (dev->flags & IFF_LOOPBACK) || dev->type != ARPHRD_ETHER || + dev->addr_len != ETH_ALEN || !is_valid_ether_addr(dev->dev_addr)) + return false; + + return true; +} + static int nft_dev_fill_forward_path(const struct nf_flow_route *route, const struct dst_entry *dst_cache, const struct nf_conn *ct, @@ -47,6 +56,9 @@ static int nft_dev_fill_forward_path(const struct nf_flow_route *route, struct neighbour *n; u8 nud_state; + if (!nft_is_valid_ether_device(dev)) + goto out; + n = dst_neigh_lookup(dst_cache, daddr); if (!n) return -1; @@ -60,6 +72,7 @@ static int nft_dev_fill_forward_path(const struct nf_flow_route *route, if (!(nud_state & NUD_VALID)) return -1; +out: return dev_fill_forward_path(dev, ha, stack); } @@ -78,15 +91,6 @@ struct nft_forward_info { enum flow_offload_xmit_type xmit_type; }; -static bool nft_is_valid_ether_device(const struct net_device *dev) -{ - if (!dev || (dev->flags & IFF_LOOPBACK) || dev->type != ARPHRD_ETHER || - dev->addr_len != ETH_ALEN || !is_valid_ether_addr(dev->dev_addr)) - return false; - - return true; -} - static void nft_dev_path_info(const struct net_device_path_stack *stack, struct nft_forward_info *info, unsigned char *ha, struct nf_flowtable *flowtable) @@ -119,7 +123,8 @@ static void nft_dev_path_info(const struct net_device_path_stack *stack, info->indev = NULL; break; } - info->outdev = path->dev; + if (!info->outdev) + info->outdev = path->dev; info->encap[info->num_encaps].id = path->encap.id; info->encap[info->num_encaps].proto = path->encap.proto; info->num_encaps++; @@ -293,7 +298,8 @@ static void nft_flow_offload_eval(const struct nft_expr *expr, case IPPROTO_TCP: tcph = skb_header_pointer(pkt->skb, nft_thoff(pkt), sizeof(_tcph), &_tcph); - if (unlikely(!tcph || tcph->fin || tcph->rst)) + if (unlikely(!tcph || tcph->fin || tcph->rst || + !nf_conntrack_tcp_established(ct))) goto out; break; case IPPROTO_UDP: diff --git a/net/netfilter/nft_last.c b/net/netfilter/nft_last.c index 43d0d4aadb1f..bb15a55dad5c 100644 --- a/net/netfilter/nft_last.c +++ b/net/netfilter/nft_last.c @@ -30,7 +30,7 @@ static int nft_last_init(const struct nft_ctx *ctx, const struct nft_expr *expr, u64 last_jiffies; int err; - last = kzalloc(sizeof(*last), GFP_KERNEL); + last = kzalloc(sizeof(*last), GFP_KERNEL_ACCOUNT); if (!last) return -ENOMEM; diff --git a/net/netfilter/nft_limit.c b/net/netfilter/nft_limit.c index d4a6cf3cd697..04ea8b9bf202 100644 --- a/net/netfilter/nft_limit.c +++ b/net/netfilter/nft_limit.c @@ -90,7 +90,7 @@ static int nft_limit_init(struct nft_limit_priv *priv, priv->rate); } - priv->limit = kmalloc(sizeof(*priv->limit), GFP_KERNEL); + priv->limit = kmalloc(sizeof(*priv->limit), GFP_KERNEL_ACCOUNT); if (!priv->limit) return -ENOMEM; diff --git a/net/netfilter/nft_quota.c b/net/netfilter/nft_quota.c index d7db57ed3bc1..e6b0df68feea 100644 --- a/net/netfilter/nft_quota.c +++ b/net/netfilter/nft_quota.c @@ -90,7 +90,7 @@ static int nft_quota_do_init(const struct nlattr * const tb[], return -EOPNOTSUPP; } - priv->consumed = kmalloc(sizeof(*priv->consumed), GFP_KERNEL); + priv->consumed = kmalloc(sizeof(*priv->consumed), GFP_KERNEL_ACCOUNT); if (!priv->consumed) return -ENOMEM; diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index d600a566da32..7325bee7d144 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -349,7 +349,11 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, *ext = &rbe->ext; return -EEXIST; } else { - p = &parent->rb_left; + overlap = false; + if (nft_rbtree_interval_end(rbe)) + p = &parent->rb_left; + else + p = &parent->rb_right; } } diff --git a/net/netfilter/nft_socket.c b/net/netfilter/nft_socket.c index bd3792f080ed..05ae5a338b6f 100644 --- a/net/netfilter/nft_socket.c +++ b/net/netfilter/nft_socket.c @@ -37,12 +37,11 @@ static void nft_socket_wildcard(const struct nft_pktinfo *pkt, #ifdef CONFIG_SOCK_CGROUP_DATA static noinline bool -nft_sock_get_eval_cgroupv2(u32 *dest, const struct nft_pktinfo *pkt, u32 level) +nft_sock_get_eval_cgroupv2(u32 *dest, struct sock *sk, const struct nft_pktinfo *pkt, u32 level) { - struct sock *sk = skb_to_full_sk(pkt->skb); struct cgroup *cgrp; - if (!sk || !sk_fullsock(sk) || !net_eq(nft_net(pkt), sock_net(sk))) + if (!sk_fullsock(sk)) return false; cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); @@ -55,6 +54,32 @@ nft_sock_get_eval_cgroupv2(u32 *dest, const struct nft_pktinfo *pkt, u32 level) } #endif +static struct sock *nft_socket_do_lookup(const struct nft_pktinfo *pkt) +{ + const struct net_device *indev = nft_in(pkt); + const struct sk_buff *skb = pkt->skb; + struct sock *sk = NULL; + + if (!indev) + return NULL; + + switch (nft_pf(pkt)) { + case NFPROTO_IPV4: + sk = nf_sk_lookup_slow_v4(nft_net(pkt), skb, indev); + break; +#if IS_ENABLED(CONFIG_NF_TABLES_IPV6) + case NFPROTO_IPV6: + sk = nf_sk_lookup_slow_v6(nft_net(pkt), skb, indev); + break; +#endif + default: + WARN_ON_ONCE(1); + break; + } + + return sk; +} + static void nft_socket_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) @@ -68,20 +93,7 @@ static void nft_socket_eval(const struct nft_expr *expr, sk = NULL; if (!sk) - switch(nft_pf(pkt)) { - case NFPROTO_IPV4: - sk = nf_sk_lookup_slow_v4(nft_net(pkt), skb, nft_in(pkt)); - break; -#if IS_ENABLED(CONFIG_NF_TABLES_IPV6) - case NFPROTO_IPV6: - sk = nf_sk_lookup_slow_v6(nft_net(pkt), skb, nft_in(pkt)); - break; -#endif - default: - WARN_ON_ONCE(1); - regs->verdict.code = NFT_BREAK; - return; - } + sk = nft_socket_do_lookup(pkt); if (!sk) { regs->verdict.code = NFT_BREAK; @@ -109,7 +121,7 @@ static void nft_socket_eval(const struct nft_expr *expr, break; #ifdef CONFIG_SOCK_CGROUP_DATA case NFT_SOCKET_CGROUPV2: - if (!nft_sock_get_eval_cgroupv2(dest, pkt, priv->level)) { + if (!nft_sock_get_eval_cgroupv2(dest, sk, pkt, priv->level)) { regs->verdict.code = NFT_BREAK; return; } @@ -225,6 +237,16 @@ static bool nft_socket_reduce(struct nft_regs_track *track, return nft_expr_reduce_bitwise(track, expr); } +static int nft_socket_validate(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nft_data **data) +{ + return nft_chain_validate_hooks(ctx->chain, + (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_LOCAL_IN) | + (1 << NF_INET_LOCAL_OUT)); +} + static struct nft_expr_type nft_socket_type; static const struct nft_expr_ops nft_socket_ops = { .type = &nft_socket_type, @@ -232,6 +254,7 @@ static const struct nft_expr_ops nft_socket_ops = { .eval = nft_socket_eval, .init = nft_socket_init, .dump = nft_socket_dump, + .validate = nft_socket_validate, .reduce = nft_socket_reduce, }; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 47a876ccd288..73e9c0a9c187 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1975,7 +1975,6 @@ static int netlink_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, copied = len; } - skb_reset_transport_header(data_skb); err = skb_copy_datagram_msg(data_skb, 0, msg, copied); if (msg->msg_name) { @@ -2263,6 +2262,13 @@ static int netlink_dump(struct sock *sk) * single netdev. The outcome is MSG_TRUNC error. */ skb_reserve(skb, skb_tailroom(skb) - alloc_size); + + /* Make sure malicious BPF programs can not read unitialized memory + * from skb->head -> skb->data + */ + skb_reset_network_header(skb); + skb_reset_mac_header(skb); + netlink_skb_set_owner_r(skb, sk); if (nlk->dump_done_errno > 0) { diff --git a/net/nfc/core.c b/net/nfc/core.c index dc7a2404efdf..5b286e1e0a6f 100644 --- a/net/nfc/core.c +++ b/net/nfc/core.c @@ -38,7 +38,7 @@ int nfc_fw_download(struct nfc_dev *dev, const char *firmware_name) device_lock(&dev->dev); - if (!device_is_registered(&dev->dev)) { + if (dev->shutting_down) { rc = -ENODEV; goto error; } @@ -94,7 +94,7 @@ int nfc_dev_up(struct nfc_dev *dev) device_lock(&dev->dev); - if (!device_is_registered(&dev->dev)) { + if (dev->shutting_down) { rc = -ENODEV; goto error; } @@ -142,7 +142,7 @@ int nfc_dev_down(struct nfc_dev *dev) device_lock(&dev->dev); - if (!device_is_registered(&dev->dev)) { + if (dev->shutting_down) { rc = -ENODEV; goto error; } @@ -207,7 +207,7 @@ int nfc_start_poll(struct nfc_dev *dev, u32 im_protocols, u32 tm_protocols) device_lock(&dev->dev); - if (!device_is_registered(&dev->dev)) { + if (dev->shutting_down) { rc = -ENODEV; goto error; } @@ -246,7 +246,7 @@ int nfc_stop_poll(struct nfc_dev *dev) device_lock(&dev->dev); - if (!device_is_registered(&dev->dev)) { + if (dev->shutting_down) { rc = -ENODEV; goto error; } @@ -291,7 +291,7 @@ int nfc_dep_link_up(struct nfc_dev *dev, int target_index, u8 comm_mode) device_lock(&dev->dev); - if (!device_is_registered(&dev->dev)) { + if (dev->shutting_down) { rc = -ENODEV; goto error; } @@ -335,7 +335,7 @@ int nfc_dep_link_down(struct nfc_dev *dev) device_lock(&dev->dev); - if (!device_is_registered(&dev->dev)) { + if (dev->shutting_down) { rc = -ENODEV; goto error; } @@ -401,7 +401,7 @@ int nfc_activate_target(struct nfc_dev *dev, u32 target_idx, u32 protocol) device_lock(&dev->dev); - if (!device_is_registered(&dev->dev)) { + if (dev->shutting_down) { rc = -ENODEV; goto error; } @@ -448,7 +448,7 @@ int nfc_deactivate_target(struct nfc_dev *dev, u32 target_idx, u8 mode) device_lock(&dev->dev); - if (!device_is_registered(&dev->dev)) { + if (dev->shutting_down) { rc = -ENODEV; goto error; } @@ -495,7 +495,7 @@ int nfc_data_exchange(struct nfc_dev *dev, u32 target_idx, struct sk_buff *skb, device_lock(&dev->dev); - if (!device_is_registered(&dev->dev)) { + if (dev->shutting_down) { rc = -ENODEV; kfree_skb(skb); goto error; @@ -552,7 +552,7 @@ int nfc_enable_se(struct nfc_dev *dev, u32 se_idx) device_lock(&dev->dev); - if (!device_is_registered(&dev->dev)) { + if (dev->shutting_down) { rc = -ENODEV; goto error; } @@ -601,7 +601,7 @@ int nfc_disable_se(struct nfc_dev *dev, u32 se_idx) device_lock(&dev->dev); - if (!device_is_registered(&dev->dev)) { + if (dev->shutting_down) { rc = -ENODEV; goto error; } @@ -1134,6 +1134,7 @@ int nfc_register_device(struct nfc_dev *dev) dev->rfkill = NULL; } } + dev->shutting_down = false; device_unlock(&dev->dev); rc = nfc_genl_device_added(dev); @@ -1166,12 +1167,10 @@ void nfc_unregister_device(struct nfc_dev *dev) rfkill_unregister(dev->rfkill); rfkill_destroy(dev->rfkill); } + dev->shutting_down = true; device_unlock(&dev->dev); if (dev->ops->check_presence) { - device_lock(&dev->dev); - dev->shutting_down = true; - device_unlock(&dev->dev); del_timer_sync(&dev->check_pres_timer); cancel_work_sync(&dev->check_pres_work); } diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c index d2537383a3e8..6a193cce2a75 100644 --- a/net/nfc/nci/core.c +++ b/net/nfc/nci/core.c @@ -560,6 +560,10 @@ static int nci_close_device(struct nci_dev *ndev) mutex_lock(&ndev->req_lock); if (!test_and_clear_bit(NCI_UP, &ndev->flags)) { + /* Need to flush the cmd wq in case + * there is a queued/running cmd_work + */ + flush_workqueue(ndev->cmd_wq); del_timer_sync(&ndev->cmd_timer); del_timer_sync(&ndev->data_timer); mutex_unlock(&ndev->req_lock); diff --git a/net/nfc/nci/data.c b/net/nfc/nci/data.c index 6055dc9a82aa..aa5e712adf07 100644 --- a/net/nfc/nci/data.c +++ b/net/nfc/nci/data.c @@ -118,7 +118,7 @@ static int nci_queue_tx_data_frags(struct nci_dev *ndev, skb_frag = nci_skb_alloc(ndev, (NCI_DATA_HDR_SIZE + frag_len), - GFP_KERNEL); + GFP_ATOMIC); if (skb_frag == NULL) { rc = -ENOMEM; goto free_exit; diff --git a/net/nfc/nci/hci.c b/net/nfc/nci/hci.c index 19703a649b5a..78c4b6addf15 100644 --- a/net/nfc/nci/hci.c +++ b/net/nfc/nci/hci.c @@ -153,7 +153,7 @@ static int nci_hci_send_data(struct nci_dev *ndev, u8 pipe, i = 0; skb = nci_skb_alloc(ndev, conn_info->max_pkt_payload_len + - NCI_DATA_HDR_SIZE, GFP_KERNEL); + NCI_DATA_HDR_SIZE, GFP_ATOMIC); if (!skb) return -ENOMEM; @@ -184,7 +184,7 @@ static int nci_hci_send_data(struct nci_dev *ndev, u8 pipe, if (i < data_len) { skb = nci_skb_alloc(ndev, conn_info->max_pkt_payload_len + - NCI_DATA_HDR_SIZE, GFP_KERNEL); + NCI_DATA_HDR_SIZE, GFP_ATOMIC); if (!skb) return -ENOMEM; diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index f184b0db79d4..7c62417ccfd7 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -1244,7 +1244,7 @@ int nfc_genl_fw_download_done(struct nfc_dev *dev, const char *firmware_name, struct sk_buff *msg; void *hdr; - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); if (!msg) return -ENOMEM; @@ -1260,7 +1260,7 @@ int nfc_genl_fw_download_done(struct nfc_dev *dev, const char *firmware_name, genlmsg_end(msg, hdr); - genlmsg_multicast(&nfc_genl_family, msg, 0, 0, GFP_KERNEL); + genlmsg_multicast(&nfc_genl_family, msg, 0, 0, GFP_ATOMIC); return 0; diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 7056cb1b8ba0..1b5d73079dc9 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -1051,7 +1051,7 @@ static int clone(struct datapath *dp, struct sk_buff *skb, int rem = nla_len(attr); bool dont_clone_flow_key; - /* The first action is always 'OVS_CLONE_ATTR_ARG'. */ + /* The first action is always 'OVS_CLONE_ATTR_EXEC'. */ clone_arg = nla_data(attr); dont_clone_flow_key = nla_get_u32(clone_arg); actions = nla_next(clone_arg, &rem); diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index cc282a58b75b..4c09cf8a0ab2 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -2317,6 +2317,62 @@ static struct sw_flow_actions *nla_alloc_flow_actions(int size) return sfa; } +static void ovs_nla_free_nested_actions(const struct nlattr *actions, int len); + +static void ovs_nla_free_check_pkt_len_action(const struct nlattr *action) +{ + const struct nlattr *a; + int rem; + + nla_for_each_nested(a, action, rem) { + switch (nla_type(a)) { + case OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_LESS_EQUAL: + case OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_GREATER: + ovs_nla_free_nested_actions(nla_data(a), nla_len(a)); + break; + } + } +} + +static void ovs_nla_free_clone_action(const struct nlattr *action) +{ + const struct nlattr *a = nla_data(action); + int rem = nla_len(action); + + switch (nla_type(a)) { + case OVS_CLONE_ATTR_EXEC: + /* The real list of actions follows this attribute. */ + a = nla_next(a, &rem); + ovs_nla_free_nested_actions(a, rem); + break; + } +} + +static void ovs_nla_free_dec_ttl_action(const struct nlattr *action) +{ + const struct nlattr *a = nla_data(action); + + switch (nla_type(a)) { + case OVS_DEC_TTL_ATTR_ACTION: + ovs_nla_free_nested_actions(nla_data(a), nla_len(a)); + break; + } +} + +static void ovs_nla_free_sample_action(const struct nlattr *action) +{ + const struct nlattr *a = nla_data(action); + int rem = nla_len(action); + + switch (nla_type(a)) { + case OVS_SAMPLE_ATTR_ARG: + /* The real list of actions follows this attribute. */ + a = nla_next(a, &rem); + ovs_nla_free_nested_actions(a, rem); + break; + } +} + static void ovs_nla_free_set_action(const struct nlattr *a) { const struct nlattr *ovs_key = nla_data(a); @@ -2330,25 +2386,54 @@ static void ovs_nla_free_set_action(const struct nlattr *a) } } -void ovs_nla_free_flow_actions(struct sw_flow_actions *sf_acts) +static void ovs_nla_free_nested_actions(const struct nlattr *actions, int len) { const struct nlattr *a; int rem; - if (!sf_acts) + /* Whenever new actions are added, the need to update this + * function should be considered. + */ + BUILD_BUG_ON(OVS_ACTION_ATTR_MAX != 23); + + if (!actions) return; - nla_for_each_attr(a, sf_acts->actions, sf_acts->actions_len, rem) { + nla_for_each_attr(a, actions, len, rem) { switch (nla_type(a)) { - case OVS_ACTION_ATTR_SET: - ovs_nla_free_set_action(a); + case OVS_ACTION_ATTR_CHECK_PKT_LEN: + ovs_nla_free_check_pkt_len_action(a); + break; + + case OVS_ACTION_ATTR_CLONE: + ovs_nla_free_clone_action(a); break; + case OVS_ACTION_ATTR_CT: ovs_ct_free_action(a); break; + + case OVS_ACTION_ATTR_DEC_TTL: + ovs_nla_free_dec_ttl_action(a); + break; + + case OVS_ACTION_ATTR_SAMPLE: + ovs_nla_free_sample_action(a); + break; + + case OVS_ACTION_ATTR_SET: + ovs_nla_free_set_action(a); + break; } } +} + +void ovs_nla_free_flow_actions(struct sw_flow_actions *sf_acts) +{ + if (!sf_acts) + return; + ovs_nla_free_nested_actions(sf_acts->actions, sf_acts->actions_len); kfree(sf_acts); } @@ -2380,7 +2465,7 @@ static struct nlattr *reserve_sfa_size(struct sw_flow_actions **sfa, new_acts_size = max(next_offset + req_size, ksize(*sfa) * 2); if (new_acts_size > MAX_ACTIONS_BUFSIZE) { - if ((MAX_ACTIONS_BUFSIZE - next_offset) < req_size) { + if ((next_offset + req_size) > MAX_ACTIONS_BUFSIZE) { OVS_NLERR(log, "Flow action size exceeds max %u", MAX_ACTIONS_BUFSIZE); return ERR_PTR(-EMSGSIZE); @@ -3458,7 +3543,9 @@ static int clone_action_to_attr(const struct nlattr *attr, if (!start) return -EMSGSIZE; - err = ovs_nla_put_actions(nla_data(attr), rem, skb); + /* Skipping the OVS_CLONE_ATTR_EXEC that is always the first attribute. */ + attr = nla_next(nla_data(attr), &rem); + err = ovs_nla_put_actions(attr, rem, skb); if (err) nla_nest_cancel(skb, start); diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index c39c09899fd0..002d2b9c69dd 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2858,8 +2858,9 @@ tpacket_error: status = TP_STATUS_SEND_REQUEST; err = po->xmit(skb); - if (unlikely(err > 0)) { - err = net_xmit_errno(err); + if (unlikely(err != 0)) { + if (err > 0) + err = net_xmit_errno(err); if (err && __packet_get_status(po, ph) == TP_STATUS_AVAILABLE) { /* skb was destructed already */ @@ -3060,8 +3061,12 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) skb->no_fcs = 1; err = po->xmit(skb); - if (err > 0 && (err = net_xmit_errno(err)) != 0) - goto out_unlock; + if (unlikely(err != 0)) { + if (err > 0) + err = net_xmit_errno(err); + if (err) + goto out_unlock; + } dev_put(dev); diff --git a/net/rds/tcp.c b/net/rds/tcp.c index 5327d130c4b5..73ee2771093d 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -487,14 +487,27 @@ struct rds_tcp_net { /* All module specific customizations to the RDS-TCP socket should be done in * rds_tcp_tune() and applied after socket creation. */ -void rds_tcp_tune(struct socket *sock) +bool rds_tcp_tune(struct socket *sock) { struct sock *sk = sock->sk; struct net *net = sock_net(sk); - struct rds_tcp_net *rtn = net_generic(net, rds_tcp_netid); + struct rds_tcp_net *rtn; tcp_sock_set_nodelay(sock->sk); lock_sock(sk); + /* TCP timer functions might access net namespace even after + * a process which created this net namespace terminated. + */ + if (!sk->sk_net_refcnt) { + if (!maybe_get_net(net)) { + release_sock(sk); + return false; + } + sk->sk_net_refcnt = 1; + netns_tracker_alloc(net, &sk->ns_tracker, GFP_KERNEL); + sock_inuse_add(net, 1); + } + rtn = net_generic(net, rds_tcp_netid); if (rtn->sndbuf_size > 0) { sk->sk_sndbuf = rtn->sndbuf_size; sk->sk_userlocks |= SOCK_SNDBUF_LOCK; @@ -504,6 +517,7 @@ void rds_tcp_tune(struct socket *sock) sk->sk_userlocks |= SOCK_RCVBUF_LOCK; } release_sock(sk); + return true; } static void rds_tcp_accept_worker(struct work_struct *work) diff --git a/net/rds/tcp.h b/net/rds/tcp.h index dc8d745d6857..f8b5930d7b34 100644 --- a/net/rds/tcp.h +++ b/net/rds/tcp.h @@ -49,7 +49,7 @@ struct rds_tcp_statistics { }; /* tcp.c */ -void rds_tcp_tune(struct socket *sock); +bool rds_tcp_tune(struct socket *sock); void rds_tcp_set_callbacks(struct socket *sock, struct rds_conn_path *cp); void rds_tcp_reset_callbacks(struct socket *sock, struct rds_conn_path *cp); void rds_tcp_restore_callbacks(struct socket *sock, diff --git a/net/rds/tcp_connect.c b/net/rds/tcp_connect.c index 5461d77fff4f..f0c477c5d1db 100644 --- a/net/rds/tcp_connect.c +++ b/net/rds/tcp_connect.c @@ -124,7 +124,10 @@ int rds_tcp_conn_path_connect(struct rds_conn_path *cp) if (ret < 0) goto out; - rds_tcp_tune(sock); + if (!rds_tcp_tune(sock)) { + ret = -EINVAL; + goto out; + } if (isv6) { sin6.sin6_family = AF_INET6; diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c index 09cadd556d1e..7edf2e69d3fe 100644 --- a/net/rds/tcp_listen.c +++ b/net/rds/tcp_listen.c @@ -133,7 +133,10 @@ int rds_tcp_accept_one(struct socket *sock) __module_get(new_sock->ops->owner); rds_tcp_keepalive(new_sock); - rds_tcp_tune(new_sock); + if (!rds_tcp_tune(new_sock)) { + ret = -EINVAL; + goto out; + } inet = inet_sk(new_sock->sk); diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c index a4111408ffd0..6a1611b0e303 100644 --- a/net/rxrpc/local_object.c +++ b/net/rxrpc/local_object.c @@ -117,6 +117,7 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net) local, srx->transport_type, srx->transport.family); udp_conf.family = srx->transport.family; + udp_conf.use_udp_checksums = true; if (udp_conf.family == AF_INET) { udp_conf.local_ip = srx->transport.sin.sin_addr; udp_conf.local_udp_port = srx->transport.sin.sin_port; @@ -124,6 +125,8 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net) } else { udp_conf.local_ip6 = srx->transport.sin6.sin6_addr; udp_conf.local_udp_port = srx->transport.sin6.sin6_port; + udp_conf.use_udp6_tx_checksums = true; + udp_conf.use_udp6_rx_checksums = true; #endif } ret = udp_sock_create(net, &udp_conf, &local->socket); diff --git a/net/rxrpc/net_ns.c b/net/rxrpc/net_ns.c index 25bbc4cc8b13..cc7e30733feb 100644 --- a/net/rxrpc/net_ns.c +++ b/net/rxrpc/net_ns.c @@ -115,6 +115,8 @@ static __net_exit void rxrpc_exit_net(struct net *net) rxnet->live = false; del_timer_sync(&rxnet->peer_keepalive_timer); cancel_work_sync(&rxnet->peer_keepalive_work); + /* Remove the timer again as the worker may have restarted it. */ + del_timer_sync(&rxnet->peer_keepalive_timer); rxrpc_destroy_all_calls(rxnet); rxrpc_destroy_all_connections(rxnet); rxrpc_destroy_all_peers(rxnet); diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index 31fcd279c177..211c757bfc3c 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -149,7 +149,7 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, struct nlattr *pattr; struct tcf_pedit *p; int ret = 0, err; - int ksize; + int i, ksize; u32 index; if (!nla) { @@ -228,6 +228,22 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, p->tcfp_nkeys = parm->nkeys; } memcpy(p->tcfp_keys, parm->keys, ksize); + p->tcfp_off_max_hint = 0; + for (i = 0; i < p->tcfp_nkeys; ++i) { + u32 cur = p->tcfp_keys[i].off; + + /* sanitize the shift value for any later use */ + p->tcfp_keys[i].shift = min_t(size_t, BITS_PER_TYPE(int) - 1, + p->tcfp_keys[i].shift); + + /* The AT option can read a single byte, we can bound the actual + * value with uchar max. + */ + cur += (0xff & p->tcfp_keys[i].offmask) >> p->tcfp_keys[i].shift; + + /* Each key touches 4 bytes starting from the computed offset */ + p->tcfp_off_max_hint = max(p->tcfp_off_max_hint, cur + 4); + } p->tcfp_flags = parm->flags; goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); @@ -308,13 +324,18 @@ static int tcf_pedit_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_pedit *p = to_pedit(a); + u32 max_offset; int i; - if (skb_unclone(skb, GFP_ATOMIC)) - return p->tcf_action; - spin_lock(&p->tcf_lock); + max_offset = (skb_transport_header_was_set(skb) ? + skb_transport_offset(skb) : + skb_network_offset(skb)) + + p->tcfp_off_max_hint; + if (skb_ensure_writable(skb, min(skb->len, max_offset))) + goto unlock; + tcf_lastuse_update(&p->tcf_tm); if (p->tcfp_nkeys > 0) { @@ -403,6 +424,7 @@ bad: p->tcf_qstats.overlimits++; done: bstats_update(&p->tcf_bstats, skb); +unlock: spin_unlock(&p->tcf_lock); return p->tcf_action; } diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 2957f8f5cea7..f0699f39afdb 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -1672,10 +1672,10 @@ static int tcf_chain_tp_insert(struct tcf_chain *chain, if (chain->flushing) return -EAGAIN; + RCU_INIT_POINTER(tp->next, tcf_chain_tp_prev(chain, chain_info)); if (*chain_info->pprev == chain->filter_chain) tcf_chain0_head_change(chain, tp); tcf_proto_get(tp); - RCU_INIT_POINTER(tp->next, tcf_chain_tp_prev(chain, chain_info)); rcu_assign_pointer(*chain_info->pprev, tp); return 0; diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index c80fc49c0da1..ed5e6f08e74a 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -1013,6 +1013,7 @@ static int fl_set_key_mpls(struct nlattr **tb, static void fl_set_key_vlan(struct nlattr **tb, __be16 ethertype, int vlan_id_key, int vlan_prio_key, + int vlan_next_eth_type_key, struct flow_dissector_key_vlan *key_val, struct flow_dissector_key_vlan *key_mask) { @@ -1031,6 +1032,11 @@ static void fl_set_key_vlan(struct nlattr **tb, } key_val->vlan_tpid = ethertype; key_mask->vlan_tpid = cpu_to_be16(~0); + if (tb[vlan_next_eth_type_key]) { + key_val->vlan_eth_type = + nla_get_be16(tb[vlan_next_eth_type_key]); + key_mask->vlan_eth_type = cpu_to_be16(~0); + } } static void fl_set_key_flag(u32 flower_key, u32 flower_mask, @@ -1602,8 +1608,9 @@ static int fl_set_key(struct net *net, struct nlattr **tb, if (eth_type_vlan(ethertype)) { fl_set_key_vlan(tb, ethertype, TCA_FLOWER_KEY_VLAN_ID, - TCA_FLOWER_KEY_VLAN_PRIO, &key->vlan, - &mask->vlan); + TCA_FLOWER_KEY_VLAN_PRIO, + TCA_FLOWER_KEY_VLAN_ETH_TYPE, + &key->vlan, &mask->vlan); if (tb[TCA_FLOWER_KEY_VLAN_ETH_TYPE]) { ethertype = nla_get_be16(tb[TCA_FLOWER_KEY_VLAN_ETH_TYPE]); @@ -1611,6 +1618,7 @@ static int fl_set_key(struct net *net, struct nlattr **tb, fl_set_key_vlan(tb, ethertype, TCA_FLOWER_KEY_CVLAN_ID, TCA_FLOWER_KEY_CVLAN_PRIO, + TCA_FLOWER_KEY_CVLAN_ETH_TYPE, &key->cvlan, &mask->cvlan); fl_set_key_val(tb, &key->basic.n_proto, TCA_FLOWER_KEY_CVLAN_ETH_TYPE, @@ -3002,13 +3010,13 @@ static int fl_dump_key(struct sk_buff *skb, struct net *net, goto nla_put_failure; if (mask->basic.n_proto) { - if (mask->cvlan.vlan_tpid) { + if (mask->cvlan.vlan_eth_type) { if (nla_put_be16(skb, TCA_FLOWER_KEY_CVLAN_ETH_TYPE, key->basic.n_proto)) goto nla_put_failure; - } else if (mask->vlan.vlan_tpid) { + } else if (mask->vlan.vlan_eth_type) { if (nla_put_be16(skb, TCA_FLOWER_KEY_VLAN_ETH_TYPE, - key->basic.n_proto)) + key->vlan.vlan_eth_type)) goto nla_put_failure; } } diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index cf5649292ee0..4d27300c287c 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -386,14 +386,19 @@ static int u32_init(struct tcf_proto *tp) return 0; } -static int u32_destroy_key(struct tc_u_knode *n, bool free_pf) +static void __u32_destroy_key(struct tc_u_knode *n) { struct tc_u_hnode *ht = rtnl_dereference(n->ht_down); tcf_exts_destroy(&n->exts); - tcf_exts_put_net(&n->exts); if (ht && --ht->refcnt == 0) kfree(ht); + kfree(n); +} + +static void u32_destroy_key(struct tc_u_knode *n, bool free_pf) +{ + tcf_exts_put_net(&n->exts); #ifdef CONFIG_CLS_U32_PERF if (free_pf) free_percpu(n->pf); @@ -402,8 +407,7 @@ static int u32_destroy_key(struct tc_u_knode *n, bool free_pf) if (free_pf) free_percpu(n->pcpu_success); #endif - kfree(n); - return 0; + __u32_destroy_key(n); } /* u32_delete_key_rcu should be called when free'ing a copied @@ -811,10 +815,6 @@ static struct tc_u_knode *u32_init_knode(struct net *net, struct tcf_proto *tp, new->flags = n->flags; RCU_INIT_POINTER(new->ht_down, ht); - /* bump reference count as long as we hold pointer to structure */ - if (ht) - ht->refcnt++; - #ifdef CONFIG_CLS_U32_PERF /* Statistics may be incremented by readers during update * so we must keep them in tact. When the node is later destroyed @@ -836,6 +836,10 @@ static struct tc_u_knode *u32_init_knode(struct net *net, struct tcf_proto *tp, return NULL; } + /* bump reference count as long as we hold pointer to structure */ + if (ht) + ht->refcnt++; + return new; } @@ -900,13 +904,13 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, extack); if (err) { - u32_destroy_key(new, false); + __u32_destroy_key(new); return err; } err = u32_replace_hw_knode(tp, new, flags, extack); if (err) { - u32_destroy_key(new, false); + __u32_destroy_key(new); return err; } diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index 377f896bdedc..b9c71a304d39 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -417,7 +417,8 @@ static int taprio_enqueue_one(struct sk_buff *skb, struct Qdisc *sch, { struct taprio_sched *q = qdisc_priv(sch); - if (skb->sk && sock_flag(skb->sk, SOCK_TXTIME)) { + /* sk_flags are only safe to use on full sockets. */ + if (skb->sk && sk_fullsock(skb->sk) && sock_flag(skb->sk, SOCK_TXTIME)) { if (!is_valid_interval(skb, sch)) return qdisc_drop(skb, sch, to_free); } else if (TXTIME_ASSIST_IS_ENABLED(q->flags)) { diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index a18609f608fb..e213aaf45d67 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -914,6 +914,7 @@ static void sctp_outq_flush_ctrl(struct sctp_flush_ctx *ctx) ctx->asoc->base.sk->sk_err = -error; return; } + ctx->asoc->stats.octrlchunks++; break; case SCTP_CID_ABORT: @@ -938,7 +939,10 @@ static void sctp_outq_flush_ctrl(struct sctp_flush_ctx *ctx) case SCTP_CID_HEARTBEAT: if (chunk->pmtu_probe) { - sctp_packet_singleton(ctx->transport, chunk, ctx->gfp); + error = sctp_packet_singleton(ctx->transport, + chunk, ctx->gfp); + if (!error) + ctx->asoc->stats.octrlchunks++; break; } fallthrough; diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index b3815b568e8e..463c4a58d2c3 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -458,6 +458,10 @@ void sctp_generate_reconf_event(struct timer_list *t) goto out_unlock; } + /* This happens when the response arrives after the timer is triggered. */ + if (!asoc->strreset_chunk) + goto out_unlock; + error = sctp_do_sm(net, SCTP_EVENT_T_TIMEOUT, SCTP_ST_TIMEOUT(SCTP_EVENT_TIMEOUT_RECONF), asoc->state, asoc->ep, asoc, diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 7f342bc12735..52edee1322fc 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -781,7 +781,7 @@ enum sctp_disposition sctp_sf_do_5_1D_ce(struct net *net, } } - if (security_sctp_assoc_request(new_asoc, chunk->skb)) { + if (security_sctp_assoc_request(new_asoc, chunk->head_skb ?: chunk->skb)) { sctp_association_free(new_asoc); return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); } @@ -932,7 +932,7 @@ enum sctp_disposition sctp_sf_do_5_1E_ca(struct net *net, /* Set peer label for connection. */ if (security_sctp_assoc_established((struct sctp_association *)asoc, - chunk->skb)) + chunk->head_skb ?: chunk->skb)) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); /* Verify that the chunk length for the COOKIE-ACK is OK. @@ -2262,7 +2262,7 @@ enum sctp_disposition sctp_sf_do_5_2_4_dupcook( } /* Update socket peer label if first association. */ - if (security_sctp_assoc_request(new_asoc, chunk->skb)) { + if (security_sctp_assoc_request(new_asoc, chunk->head_skb ?: chunk->skb)) { sctp_association_free(new_asoc); return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); } diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 3e1a9600be5e..7b0427658056 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -5636,7 +5636,7 @@ int sctp_do_peeloff(struct sock *sk, sctp_assoc_t id, struct socket **sockp) * Set the daddr and initialize id to something more random and also * copy over any ip options. */ - sp->pf->to_sk_daddr(&asoc->peer.primary_addr, sk); + sp->pf->to_sk_daddr(&asoc->peer.primary_addr, sock->sk); sp->pf->copy_ip_options(sk, sock->sk); /* Populate the fields of the newsk from the oldsk and migrate the diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index f0d118e9f155..fce16b9d6e1a 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -121,6 +121,7 @@ static struct sock *smc_tcp_syn_recv_sock(const struct sock *sk, bool *own_req) { struct smc_sock *smc; + struct sock *child; smc = smc_clcsock_user_data(sk); @@ -134,8 +135,17 @@ static struct sock *smc_tcp_syn_recv_sock(const struct sock *sk, } /* passthrough to original syn recv sock fct */ - return smc->ori_af_ops->syn_recv_sock(sk, skb, req, dst, req_unhash, - own_req); + child = smc->ori_af_ops->syn_recv_sock(sk, skb, req, dst, req_unhash, + own_req); + /* child must not inherit smc or its ops */ + if (child) { + rcu_assign_sk_user_data(child, NULL); + + /* v4-mapped sockets don't inherit parent ops. Don't restore. */ + if (inet_csk(child)->icsk_af_ops == inet_csk(sk)->icsk_af_ops) + inet_csk(child)->icsk_af_ops = smc->ori_af_ops; + } + return child; drop: dst_release(dst); @@ -233,11 +243,27 @@ struct proto smc_proto6 = { }; EXPORT_SYMBOL_GPL(smc_proto6); +static void smc_fback_restore_callbacks(struct smc_sock *smc) +{ + struct sock *clcsk = smc->clcsock->sk; + + write_lock_bh(&clcsk->sk_callback_lock); + clcsk->sk_user_data = NULL; + + smc_clcsock_restore_cb(&clcsk->sk_state_change, &smc->clcsk_state_change); + smc_clcsock_restore_cb(&clcsk->sk_data_ready, &smc->clcsk_data_ready); + smc_clcsock_restore_cb(&clcsk->sk_write_space, &smc->clcsk_write_space); + smc_clcsock_restore_cb(&clcsk->sk_error_report, &smc->clcsk_error_report); + + write_unlock_bh(&clcsk->sk_callback_lock); +} + static void smc_restore_fallback_changes(struct smc_sock *smc) { if (smc->clcsock->file) { /* non-accepted sockets have no file yet */ smc->clcsock->file->private_data = smc->sk.sk_socket; smc->clcsock->file = NULL; + smc_fback_restore_callbacks(smc); } } @@ -363,6 +389,7 @@ static struct sock *smc_sock_alloc(struct net *net, struct socket *sock, sk->sk_prot->hash(sk); sk_refcnt_debug_inc(sk); mutex_init(&smc->clcsock_release_lock); + smc_init_saved_callbacks(smc); return sk; } @@ -734,47 +761,73 @@ out: static void smc_fback_state_change(struct sock *clcsk) { - struct smc_sock *smc = - smc_clcsock_user_data(clcsk); + struct smc_sock *smc; - if (!smc) - return; - smc_fback_forward_wakeup(smc, clcsk, smc->clcsk_state_change); + read_lock_bh(&clcsk->sk_callback_lock); + smc = smc_clcsock_user_data(clcsk); + if (smc) + smc_fback_forward_wakeup(smc, clcsk, + smc->clcsk_state_change); + read_unlock_bh(&clcsk->sk_callback_lock); } static void smc_fback_data_ready(struct sock *clcsk) { - struct smc_sock *smc = - smc_clcsock_user_data(clcsk); + struct smc_sock *smc; - if (!smc) - return; - smc_fback_forward_wakeup(smc, clcsk, smc->clcsk_data_ready); + read_lock_bh(&clcsk->sk_callback_lock); + smc = smc_clcsock_user_data(clcsk); + if (smc) + smc_fback_forward_wakeup(smc, clcsk, + smc->clcsk_data_ready); + read_unlock_bh(&clcsk->sk_callback_lock); } static void smc_fback_write_space(struct sock *clcsk) { - struct smc_sock *smc = - smc_clcsock_user_data(clcsk); + struct smc_sock *smc; - if (!smc) - return; - smc_fback_forward_wakeup(smc, clcsk, smc->clcsk_write_space); + read_lock_bh(&clcsk->sk_callback_lock); + smc = smc_clcsock_user_data(clcsk); + if (smc) + smc_fback_forward_wakeup(smc, clcsk, + smc->clcsk_write_space); + read_unlock_bh(&clcsk->sk_callback_lock); } static void smc_fback_error_report(struct sock *clcsk) { - struct smc_sock *smc = - smc_clcsock_user_data(clcsk); + struct smc_sock *smc; - if (!smc) - return; - smc_fback_forward_wakeup(smc, clcsk, smc->clcsk_error_report); + read_lock_bh(&clcsk->sk_callback_lock); + smc = smc_clcsock_user_data(clcsk); + if (smc) + smc_fback_forward_wakeup(smc, clcsk, + smc->clcsk_error_report); + read_unlock_bh(&clcsk->sk_callback_lock); +} + +static void smc_fback_replace_callbacks(struct smc_sock *smc) +{ + struct sock *clcsk = smc->clcsock->sk; + + write_lock_bh(&clcsk->sk_callback_lock); + clcsk->sk_user_data = (void *)((uintptr_t)smc | SK_USER_DATA_NOCOPY); + + smc_clcsock_replace_cb(&clcsk->sk_state_change, smc_fback_state_change, + &smc->clcsk_state_change); + smc_clcsock_replace_cb(&clcsk->sk_data_ready, smc_fback_data_ready, + &smc->clcsk_data_ready); + smc_clcsock_replace_cb(&clcsk->sk_write_space, smc_fback_write_space, + &smc->clcsk_write_space); + smc_clcsock_replace_cb(&clcsk->sk_error_report, smc_fback_error_report, + &smc->clcsk_error_report); + + write_unlock_bh(&clcsk->sk_callback_lock); } static int smc_switch_to_fallback(struct smc_sock *smc, int reason_code) { - struct sock *clcsk; int rc = 0; mutex_lock(&smc->clcsock_release_lock); @@ -782,10 +835,7 @@ static int smc_switch_to_fallback(struct smc_sock *smc, int reason_code) rc = -EBADF; goto out; } - clcsk = smc->clcsock->sk; - if (smc->use_fallback) - goto out; smc->use_fallback = true; smc->fallback_rsn = reason_code; smc_stat_fallback(smc); @@ -800,18 +850,7 @@ static int smc_switch_to_fallback(struct smc_sock *smc, int reason_code) * in smc sk->sk_wq and they should be woken up * as clcsock's wait queue is woken up. */ - smc->clcsk_state_change = clcsk->sk_state_change; - smc->clcsk_data_ready = clcsk->sk_data_ready; - smc->clcsk_write_space = clcsk->sk_write_space; - smc->clcsk_error_report = clcsk->sk_error_report; - - clcsk->sk_state_change = smc_fback_state_change; - clcsk->sk_data_ready = smc_fback_data_ready; - clcsk->sk_write_space = smc_fback_write_space; - clcsk->sk_error_report = smc_fback_error_report; - - smc->clcsock->sk->sk_user_data = - (void *)((uintptr_t)smc | SK_USER_DATA_NOCOPY); + smc_fback_replace_callbacks(smc); } out: mutex_unlock(&smc->clcsock_release_lock); @@ -1465,6 +1504,8 @@ static void smc_connect_work(struct work_struct *work) smc->sk.sk_state = SMC_CLOSED; if (rc == -EPIPE || rc == -EAGAIN) smc->sk.sk_err = EPIPE; + else if (rc == -ECONNREFUSED) + smc->sk.sk_err = ECONNREFUSED; else if (signal_pending(current)) smc->sk.sk_err = -sock_intr_errno(timeo); sock_put(&smc->sk); /* passive closing */ @@ -1584,6 +1625,19 @@ static int smc_clcsock_accept(struct smc_sock *lsmc, struct smc_sock **new_smc) * function; switch it back to the original sk_data_ready function */ new_clcsock->sk->sk_data_ready = lsmc->clcsk_data_ready; + + /* if new clcsock has also inherited the fallback-specific callback + * functions, switch them back to the original ones. + */ + if (lsmc->use_fallback) { + if (lsmc->clcsk_state_change) + new_clcsock->sk->sk_state_change = lsmc->clcsk_state_change; + if (lsmc->clcsk_write_space) + new_clcsock->sk->sk_write_space = lsmc->clcsk_write_space; + if (lsmc->clcsk_error_report) + new_clcsock->sk->sk_error_report = lsmc->clcsk_error_report; + } + (*new_smc)->clcsock = new_clcsock; out: return rc; @@ -2343,17 +2397,20 @@ out: static void smc_clcsock_data_ready(struct sock *listen_clcsock) { - struct smc_sock *lsmc = - smc_clcsock_user_data(listen_clcsock); + struct smc_sock *lsmc; + read_lock_bh(&listen_clcsock->sk_callback_lock); + lsmc = smc_clcsock_user_data(listen_clcsock); if (!lsmc) - return; + goto out; lsmc->clcsk_data_ready(listen_clcsock); if (lsmc->sk.sk_state == SMC_LISTEN) { sock_hold(&lsmc->sk); /* sock_put in smc_tcp_listen_work() */ if (!queue_work(smc_tcp_ls_wq, &lsmc->tcp_listen_work)) sock_put(&lsmc->sk); } +out: + read_unlock_bh(&listen_clcsock->sk_callback_lock); } static int smc_listen(struct socket *sock, int backlog) @@ -2385,10 +2442,12 @@ static int smc_listen(struct socket *sock, int backlog) /* save original sk_data_ready function and establish * smc-specific sk_data_ready function */ - smc->clcsk_data_ready = smc->clcsock->sk->sk_data_ready; - smc->clcsock->sk->sk_data_ready = smc_clcsock_data_ready; + write_lock_bh(&smc->clcsock->sk->sk_callback_lock); smc->clcsock->sk->sk_user_data = (void *)((uintptr_t)smc | SK_USER_DATA_NOCOPY); + smc_clcsock_replace_cb(&smc->clcsock->sk->sk_data_ready, + smc_clcsock_data_ready, &smc->clcsk_data_ready); + write_unlock_bh(&smc->clcsock->sk->sk_callback_lock); /* save original ops */ smc->ori_af_ops = inet_csk(smc->clcsock->sk)->icsk_af_ops; @@ -2403,7 +2462,11 @@ static int smc_listen(struct socket *sock, int backlog) rc = kernel_listen(smc->clcsock, backlog); if (rc) { - smc->clcsock->sk->sk_data_ready = smc->clcsk_data_ready; + write_lock_bh(&smc->clcsock->sk->sk_callback_lock); + smc_clcsock_restore_cb(&smc->clcsock->sk->sk_data_ready, + &smc->clcsk_data_ready); + smc->clcsock->sk->sk_user_data = NULL; + write_unlock_bh(&smc->clcsock->sk->sk_callback_lock); goto out; } sk->sk_max_ack_backlog = backlog; @@ -2664,8 +2727,10 @@ static int smc_shutdown(struct socket *sock, int how) if (smc->use_fallback) { rc = kernel_sock_shutdown(smc->clcsock, how); sk->sk_shutdown = smc->clcsock->sk->sk_shutdown; - if (sk->sk_shutdown == SHUTDOWN_MASK) + if (sk->sk_shutdown == SHUTDOWN_MASK) { sk->sk_state = SMC_CLOSED; + sock_put(sk); + } goto out; } switch (how) { diff --git a/net/smc/smc.h b/net/smc/smc.h index ea0620529ebe..5ed765ea0c73 100644 --- a/net/smc/smc.h +++ b/net/smc/smc.h @@ -288,12 +288,41 @@ static inline struct smc_sock *smc_sk(const struct sock *sk) return (struct smc_sock *)sk; } +static inline void smc_init_saved_callbacks(struct smc_sock *smc) +{ + smc->clcsk_state_change = NULL; + smc->clcsk_data_ready = NULL; + smc->clcsk_write_space = NULL; + smc->clcsk_error_report = NULL; +} + static inline struct smc_sock *smc_clcsock_user_data(const struct sock *clcsk) { return (struct smc_sock *) ((uintptr_t)clcsk->sk_user_data & ~SK_USER_DATA_NOCOPY); } +/* save target_cb in saved_cb, and replace target_cb with new_cb */ +static inline void smc_clcsock_replace_cb(void (**target_cb)(struct sock *), + void (*new_cb)(struct sock *), + void (**saved_cb)(struct sock *)) +{ + /* only save once */ + if (!*saved_cb) + *saved_cb = *target_cb; + *target_cb = new_cb; +} + +/* restore target_cb to saved_cb, and reset saved_cb to NULL */ +static inline void smc_clcsock_restore_cb(void (**target_cb)(struct sock *), + void (**saved_cb)(struct sock *)) +{ + if (!*saved_cb) + return; + *target_cb = *saved_cb; + *saved_cb = NULL; +} + extern struct workqueue_struct *smc_hs_wq; /* wq for handshake work */ extern struct workqueue_struct *smc_close_wq; /* wq for close work */ diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index ce27399b38b1..f9f3f59c79de 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -191,7 +191,8 @@ static int smc_nl_ueid_dumpinfo(struct sk_buff *skb, u32 portid, u32 seq, flags, SMC_NETLINK_DUMP_UEID); if (!hdr) return -ENOMEM; - snprintf(ueid_str, sizeof(ueid_str), "%s", ueid); + memcpy(ueid_str, ueid, SMC_MAX_EID_LEN); + ueid_str[SMC_MAX_EID_LEN] = 0; if (nla_put_string(skb, SMC_NLA_EID_TABLE_ENTRY, ueid_str)) { genlmsg_cancel(skb, hdr); return -EMSGSIZE; @@ -252,7 +253,8 @@ int smc_nl_dump_seid(struct sk_buff *skb, struct netlink_callback *cb) goto end; smc_ism_get_system_eid(&seid); - snprintf(seid_str, sizeof(seid_str), "%s", seid); + memcpy(seid_str, seid, SMC_MAX_EID_LEN); + seid_str[SMC_MAX_EID_LEN] = 0; if (nla_put_string(skb, SMC_NLA_SEID_ENTRY, seid_str)) goto err; read_lock(&smc_clc_eid_table.lock); diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c index 676cb2333d3c..31db7438857c 100644 --- a/net/smc/smc_close.c +++ b/net/smc/smc_close.c @@ -214,8 +214,11 @@ again: sk->sk_state = SMC_CLOSED; sk->sk_state_change(sk); /* wake up accept */ if (smc->clcsock && smc->clcsock->sk) { - smc->clcsock->sk->sk_data_ready = smc->clcsk_data_ready; + write_lock_bh(&smc->clcsock->sk->sk_callback_lock); + smc_clcsock_restore_cb(&smc->clcsock->sk->sk_data_ready, + &smc->clcsk_data_ready); smc->clcsock->sk->sk_user_data = NULL; + write_unlock_bh(&smc->clcsock->sk->sk_callback_lock); rc = kernel_sock_shutdown(smc->clcsock, SHUT_RDWR); } smc_close_cleanup_listen(sk); diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c index 7984f8883472..7055ed10e316 100644 --- a/net/smc/smc_pnet.c +++ b/net/smc/smc_pnet.c @@ -311,8 +311,9 @@ static struct smc_ib_device *smc_pnet_find_ib(char *ib_name) list_for_each_entry(ibdev, &smc_ib_devices.list, list) { if (!strncmp(ibdev->ibdev->name, ib_name, sizeof(ibdev->ibdev->name)) || - !strncmp(dev_name(ibdev->ibdev->dev.parent), ib_name, - IB_DEVICE_NAME_MAX - 1)) { + (ibdev->ibdev->dev.parent && + !strncmp(dev_name(ibdev->ibdev->dev.parent), ib_name, + IB_DEVICE_NAME_MAX - 1))) { goto out; } } diff --git a/net/smc/smc_rx.c b/net/smc/smc_rx.c index 51e8eb2933ff..338b9ef806e8 100644 --- a/net/smc/smc_rx.c +++ b/net/smc/smc_rx.c @@ -355,12 +355,12 @@ int smc_rx_recvmsg(struct smc_sock *smc, struct msghdr *msg, } break; } + if (!timeo) + return -EAGAIN; if (signal_pending(current)) { read_done = sock_intr_errno(timeo); break; } - if (!timeo) - return -EAGAIN; } if (!smc_rx_data_available(conn)) { diff --git a/net/socket.c b/net/socket.c index 6887840682bb..bb6a1a12fbde 100644 --- a/net/socket.c +++ b/net/socket.c @@ -504,7 +504,7 @@ static int sock_map_fd(struct socket *sock, int flags) struct socket *sock_from_file(struct file *file) { if (file->f_op == &socket_file_ops) - return file->private_data; /* set in sock_map_fd */ + return file->private_data; /* set in sock_alloc_file */ return NULL; } @@ -1538,11 +1538,10 @@ int sock_create_kern(struct net *net, int family, int type, int protocol, struct } EXPORT_SYMBOL(sock_create_kern); -int __sys_socket(int family, int type, int protocol) +static struct socket *__sys_socket_create(int family, int type, int protocol) { - int retval; struct socket *sock; - int flags; + int retval; /* Check the SOCK_* constants for consistency. */ BUILD_BUG_ON(SOCK_CLOEXEC != O_CLOEXEC); @@ -1550,17 +1549,50 @@ int __sys_socket(int family, int type, int protocol) BUILD_BUG_ON(SOCK_CLOEXEC & SOCK_TYPE_MASK); BUILD_BUG_ON(SOCK_NONBLOCK & SOCK_TYPE_MASK); - flags = type & ~SOCK_TYPE_MASK; - if (flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK)) - return -EINVAL; + if ((type & ~SOCK_TYPE_MASK) & ~(SOCK_CLOEXEC | SOCK_NONBLOCK)) + return ERR_PTR(-EINVAL); type &= SOCK_TYPE_MASK; + retval = sock_create(family, type, protocol, &sock); + if (retval < 0) + return ERR_PTR(retval); + + return sock; +} + +struct file *__sys_socket_file(int family, int type, int protocol) +{ + struct socket *sock; + struct file *file; + int flags; + + sock = __sys_socket_create(family, type, protocol); + if (IS_ERR(sock)) + return ERR_CAST(sock); + + flags = type & ~SOCK_TYPE_MASK; if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK)) flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK; - retval = sock_create(family, type, protocol, &sock); - if (retval < 0) - return retval; + file = sock_alloc_file(sock, flags, NULL); + if (IS_ERR(file)) + sock_release(sock); + + return file; +} + +int __sys_socket(int family, int type, int protocol) +{ + struct socket *sock; + int flags; + + sock = __sys_socket_create(family, type, protocol); + if (IS_ERR(sock)) + return PTR_ERR(sock); + + flags = type & ~SOCK_TYPE_MASK; + if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK)) + flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK; return sock_map_fd(sock, flags & (O_CLOEXEC | O_NONBLOCK)); } diff --git a/net/sunrpc/auth_gss/gss_rpc_upcall.c b/net/sunrpc/auth_gss/gss_rpc_upcall.c index 61c276bddaf2..f549e4c05def 100644 --- a/net/sunrpc/auth_gss/gss_rpc_upcall.c +++ b/net/sunrpc/auth_gss/gss_rpc_upcall.c @@ -98,6 +98,7 @@ static int gssp_rpc_create(struct net *net, struct rpc_clnt **_clnt) * done without the correct namespace: */ .flags = RPC_CLNT_CREATE_NOPING | + RPC_CLNT_CREATE_CONNECTED | RPC_CLNT_CREATE_NO_IDLE_TIMEOUT }; struct rpc_clnt *clnt; diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 8bf2af8546d2..e2c6eca0271b 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -76,6 +76,7 @@ static int rpc_encode_header(struct rpc_task *task, static int rpc_decode_header(struct rpc_task *task, struct xdr_stream *xdr); static int rpc_ping(struct rpc_clnt *clnt); +static int rpc_ping_noreply(struct rpc_clnt *clnt); static void rpc_check_timeout(struct rpc_task *task); static void rpc_register_client(struct rpc_clnt *clnt) @@ -483,6 +484,12 @@ static struct rpc_clnt *rpc_create_xprt(struct rpc_create_args *args, rpc_shutdown_client(clnt); return ERR_PTR(err); } + } else if (args->flags & RPC_CLNT_CREATE_CONNECTED) { + int err = rpc_ping_noreply(clnt); + if (err != 0) { + rpc_shutdown_client(clnt); + return ERR_PTR(err); + } } clnt->cl_softrtry = 1; @@ -1065,10 +1072,13 @@ rpc_task_get_next_xprt(struct rpc_clnt *clnt) static void rpc_task_set_transport(struct rpc_task *task, struct rpc_clnt *clnt) { - if (task->tk_xprt && - !(test_bit(XPRT_OFFLINE, &task->tk_xprt->state) && - (task->tk_flags & RPC_TASK_MOVEABLE))) - return; + if (task->tk_xprt) { + if (!(test_bit(XPRT_OFFLINE, &task->tk_xprt->state) && + (task->tk_flags & RPC_TASK_MOVEABLE))) + return; + xprt_release(task); + xprt_put(task->tk_xprt); + } if (task->tk_flags & RPC_TASK_NO_ROUND_ROBIN) task->tk_xprt = rpc_task_get_first_xprt(clnt); else @@ -1127,6 +1137,8 @@ struct rpc_task *rpc_run_task(const struct rpc_task_setup *task_setup_data) struct rpc_task *task; task = rpc_new_task(task_setup_data); + if (IS_ERR(task)) + return task; if (!RPC_IS_ASYNC(task)) task->tk_flags |= RPC_TASK_CRED_NOREF; @@ -1227,6 +1239,11 @@ struct rpc_task *rpc_run_bc_task(struct rpc_rqst *req) * Create an rpc_task to send the data */ task = rpc_new_task(&task_setup_data); + if (IS_ERR(task)) { + xprt_free_bc_request(req); + return task; + } + xprt_init_bc_request(req, task); task->tk_action = call_bc_encode; @@ -1858,6 +1875,9 @@ call_encode(struct rpc_task *task) xprt_request_dequeue_xprt(task); /* Encode here so that rpcsec_gss can use correct sequence number. */ rpc_xdr_encode(task); + /* Add task to reply queue before transmission to avoid races */ + if (task->tk_status == 0 && rpc_reply_expected(task)) + task->tk_status = xprt_request_enqueue_receive(task); /* Did the encode result in an error condition? */ if (task->tk_status != 0) { /* Was the error nonfatal? */ @@ -1881,9 +1901,6 @@ call_encode(struct rpc_task *task) return; } - /* Add task to reply queue before transmission to avoid races */ - if (rpc_reply_expected(task)) - xprt_request_enqueue_receive(task); xprt_request_enqueue_transmit(task); out: task->tk_action = call_transmit; @@ -2200,6 +2217,7 @@ call_transmit_status(struct rpc_task *task) * socket just returned a connection error, * then hold onto the transport lock. */ + case -ENOMEM: case -ENOBUFS: rpc_delay(task, HZ>>2); fallthrough; @@ -2283,6 +2301,7 @@ call_bc_transmit_status(struct rpc_task *task) case -ENOTCONN: case -EPIPE: break; + case -ENOMEM: case -ENOBUFS: rpc_delay(task, HZ>>2); fallthrough; @@ -2365,6 +2384,11 @@ call_status(struct rpc_task *task) case -EPIPE: case -EAGAIN: break; + case -ENFILE: + case -ENOBUFS: + case -ENOMEM: + rpc_delay(task, HZ>>2); + break; case -EIO: /* shutdown or soft timeout */ goto out_exit; @@ -2692,6 +2716,10 @@ static const struct rpc_procinfo rpcproc_null = { .p_decode = rpcproc_decode_null, }; +static const struct rpc_procinfo rpcproc_null_noreply = { + .p_encode = rpcproc_encode_null, +}; + static void rpc_null_call_prepare(struct rpc_task *task, void *data) { @@ -2745,6 +2773,28 @@ static int rpc_ping(struct rpc_clnt *clnt) return status; } +static int rpc_ping_noreply(struct rpc_clnt *clnt) +{ + struct rpc_message msg = { + .rpc_proc = &rpcproc_null_noreply, + }; + struct rpc_task_setup task_setup_data = { + .rpc_client = clnt, + .rpc_message = &msg, + .callback_ops = &rpc_null_ops, + .flags = RPC_TASK_SOFT | RPC_TASK_SOFTCONN | RPC_TASK_NULLCREDS, + }; + struct rpc_task *task; + int status; + + task = rpc_run_task(&task_setup_data); + if (IS_ERR(task)) + return PTR_ERR(task); + status = task->tk_status; + rpc_put_task(task); + return status; +} + struct rpc_cb_add_xprt_calldata { struct rpc_xprt_switch *xps; struct rpc_xprt *xprt; diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index b258b87a3ec2..7f70c1e608b7 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -1128,6 +1128,11 @@ struct rpc_task *rpc_new_task(const struct rpc_task_setup *setup_data) if (task == NULL) { task = rpc_alloc_task(); + if (task == NULL) { + rpc_release_calldata(setup_data->callback_ops, + setup_data->callback_data); + return ERR_PTR(-ENOMEM); + } flags = RPC_TASK_DYNAMIC; } diff --git a/net/sunrpc/socklib.c b/net/sunrpc/socklib.c index 05b38bf68316..71ba4cf513bc 100644 --- a/net/sunrpc/socklib.c +++ b/net/sunrpc/socklib.c @@ -221,12 +221,6 @@ static int xprt_send_kvec(struct socket *sock, struct msghdr *msg, static int xprt_send_pagedata(struct socket *sock, struct msghdr *msg, struct xdr_buf *xdr, size_t base) { - int err; - - err = xdr_alloc_bvec(xdr, rpc_task_gfp_mask()); - if (err < 0) - return err; - iov_iter_bvec(&msg->msg_iter, WRITE, xdr->bvec, xdr_buf_pagecount(xdr), xdr->page_len + xdr->page_base); return xprt_sendmsg(sock, msg, base + xdr->page_base); diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 297c49855038..5b59e2103526 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -1231,6 +1231,8 @@ static struct cache_deferred_req *svc_defer(struct cache_req *req) dr->daddr = rqstp->rq_daddr; dr->argslen = rqstp->rq_arg.len >> 2; dr->xprt_hlen = rqstp->rq_xprt_hlen; + dr->xprt_ctxt = rqstp->rq_xprt_ctxt; + rqstp->rq_xprt_ctxt = NULL; /* back up head to the start of the buffer and copy */ skip = rqstp->rq_arg.len - rqstp->rq_arg.head[0].iov_len; @@ -1269,6 +1271,7 @@ static noinline int svc_deferred_recv(struct svc_rqst *rqstp) rqstp->rq_xprt_hlen = dr->xprt_hlen; rqstp->rq_daddr = dr->daddr; rqstp->rq_respages = rqstp->rq_pages; + rqstp->rq_xprt_ctxt = dr->xprt_ctxt; svc_xprt_received(rqstp->rq_xprt); return (dr->argslen<<2) - dr->xprt_hlen; } diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 478f857cdaed..cc35ec433400 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -579,15 +579,18 @@ static int svc_udp_sendto(struct svc_rqst *rqstp) if (svc_xprt_is_dead(xprt)) goto out_notconn; + err = xdr_alloc_bvec(xdr, GFP_KERNEL); + if (err < 0) + goto out_unlock; + err = xprt_sock_sendmsg(svsk->sk_sock, &msg, xdr, 0, 0, &sent); - xdr_free_bvec(xdr); if (err == -ECONNREFUSED) { /* ICMP error on earlier request. */ err = xprt_sock_sendmsg(svsk->sk_sock, &msg, xdr, 0, 0, &sent); - xdr_free_bvec(xdr); } + xdr_free_bvec(xdr); trace_svcsock_udp_send(xprt, err); - +out_unlock: mutex_unlock(&xprt->xpt_mutex); if (err < 0) return err; @@ -1096,7 +1099,9 @@ static int svc_tcp_sendmsg(struct socket *sock, struct xdr_buf *xdr, int ret; *sentp = 0; - xdr_alloc_bvec(xdr, GFP_KERNEL); + ret = xdr_alloc_bvec(xdr, GFP_KERNEL); + if (ret < 0) + return ret; ret = kernel_sendmsg(sock, &msg, &rm, 1, rm.iov_len); if (ret < 0) diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 515501f79290..86d62cffba0d 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -69,10 +69,11 @@ /* * Local functions */ -static void xprt_init(struct rpc_xprt *xprt, struct net *net); +static void xprt_init(struct rpc_xprt *xprt, struct net *net); static __be32 xprt_alloc_xid(struct rpc_xprt *xprt); -static void xprt_destroy(struct rpc_xprt *xprt); -static void xprt_request_init(struct rpc_task *task); +static void xprt_destroy(struct rpc_xprt *xprt); +static void xprt_request_init(struct rpc_task *task); +static int xprt_request_prepare(struct rpc_rqst *req); static DEFINE_SPINLOCK(xprt_list_lock); static LIST_HEAD(xprt_list); @@ -929,12 +930,7 @@ void xprt_connect(struct rpc_task *task) if (!xprt_lock_write(xprt, task)) return; - if (test_and_clear_bit(XPRT_CLOSE_WAIT, &xprt->state)) { - trace_xprt_disconnect_cleanup(xprt); - xprt->ops->close(xprt); - } - - if (!xprt_connected(xprt)) { + if (!xprt_connected(xprt) && !test_bit(XPRT_CLOSE_WAIT, &xprt->state)) { task->tk_rqstp->rq_connect_cookie = xprt->connect_cookie; rpc_sleep_on_timeout(&xprt->pending, task, NULL, xprt_request_timeout(task->tk_rqstp)); @@ -1143,16 +1139,19 @@ xprt_request_need_enqueue_receive(struct rpc_task *task, struct rpc_rqst *req) * @task: RPC task * */ -void +int xprt_request_enqueue_receive(struct rpc_task *task) { struct rpc_rqst *req = task->tk_rqstp; struct rpc_xprt *xprt = req->rq_xprt; + int ret; if (!xprt_request_need_enqueue_receive(task, req)) - return; + return 0; - xprt_request_prepare(task->tk_rqstp); + ret = xprt_request_prepare(task->tk_rqstp); + if (ret) + return ret; spin_lock(&xprt->queue_lock); /* Update the softirq receive buffer */ @@ -1166,6 +1165,7 @@ xprt_request_enqueue_receive(struct rpc_task *task) /* Turn off autodisconnect */ del_singleshot_timer_sync(&xprt->timer); + return 0; } /** @@ -1452,14 +1452,16 @@ xprt_request_dequeue_xprt(struct rpc_task *task) * * Calls into the transport layer to do whatever is needed to prepare * the request for transmission or receive. + * Returns error, or zero. */ -void +static int xprt_request_prepare(struct rpc_rqst *req) { struct rpc_xprt *xprt = req->rq_xprt; if (xprt->ops->prepare_request) - xprt->ops->prepare_request(req); + return xprt->ops->prepare_request(req); + return 0; } /** diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c index cf76a6ad127b..864131a9fc6e 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c @@ -831,7 +831,7 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp) goto out_err; if (ret == 0) goto out_drop; - rqstp->rq_xprt_hlen = ret; + rqstp->rq_xprt_hlen = 0; if (svc_rdma_is_reverse_direction_reply(xprt, ctxt)) goto out_backchannel; diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 78af7518f263..650102a9c86a 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -822,12 +822,17 @@ static int xs_stream_nospace(struct rpc_rqst *req, bool vm_wait) return ret; } -static void +static int xs_stream_prepare_request(struct rpc_rqst *req) { + gfp_t gfp = rpc_task_gfp_mask(); + int ret; + + ret = xdr_alloc_bvec(&req->rq_snd_buf, gfp); + if (ret < 0) + return ret; xdr_free_bvec(&req->rq_rcv_buf); - req->rq_task->tk_status = xdr_alloc_bvec( - &req->rq_rcv_buf, GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN); + return xdr_alloc_bvec(&req->rq_rcv_buf, gfp); } /* @@ -879,7 +884,7 @@ static int xs_local_send_request(struct rpc_rqst *req) /* Close the stream if the previous transmission was incomplete */ if (xs_send_request_was_aborted(transport, req)) { - xs_close(xprt); + xprt_force_disconnect(xprt); return -ENOTCONN; } @@ -915,7 +920,7 @@ static int xs_local_send_request(struct rpc_rqst *req) -status); fallthrough; case -EPIPE: - xs_close(xprt); + xprt_force_disconnect(xprt); status = -ENOTCONN; } @@ -956,6 +961,9 @@ static int xs_udp_send_request(struct rpc_rqst *req) if (!xprt_request_get_cong(xprt, req)) return -EBADSLT; + status = xdr_alloc_bvec(xdr, rpc_task_gfp_mask()); + if (status < 0) + return status; req->rq_xtime = ktime_get(); status = xprt_sock_sendmsg(transport->sock, &msg, xdr, 0, 0, &sent); @@ -1185,6 +1193,16 @@ static void xs_reset_transport(struct sock_xprt *transport) if (sk == NULL) return; + /* + * Make sure we're calling this in a context from which it is safe + * to call __fput_sync(). In practice that means rpciod and the + * system workqueue. + */ + if (!(current->flags & PF_WQ_WORKER)) { + WARN_ON_ONCE(1); + set_bit(XPRT_CLOSE_WAIT, &xprt->state); + return; + } if (atomic_read(&transport->xprt.swapper)) sk_clear_memalloc(sk); @@ -1208,7 +1226,7 @@ static void xs_reset_transport(struct sock_xprt *transport) mutex_unlock(&transport->recv_mutex); trace_rpc_socket_close(xprt, sock); - fput(filp); + __fput_sync(filp); xprt_disconnect_done(xprt); } @@ -1401,6 +1419,26 @@ static size_t xs_tcp_bc_maxpayload(struct rpc_xprt *xprt) #endif /* CONFIG_SUNRPC_BACKCHANNEL */ /** + * xs_local_state_change - callback to handle AF_LOCAL socket state changes + * @sk: socket whose state has changed + * + */ +static void xs_local_state_change(struct sock *sk) +{ + struct rpc_xprt *xprt; + struct sock_xprt *transport; + + if (!(xprt = xprt_from_sock(sk))) + return; + transport = container_of(xprt, struct sock_xprt, xprt); + if (sk->sk_shutdown & SHUTDOWN_MASK) { + clear_bit(XPRT_CONNECTED, &xprt->state); + /* Trigger the socket release */ + xs_run_error_worker(transport, XPRT_SOCK_WAKE_DISCONNECT); + } +} + +/** * xs_tcp_state_change - callback to handle TCP socket state changes * @sk: socket whose state has changed * @@ -1848,6 +1886,7 @@ static int xs_local_finish_connecting(struct rpc_xprt *xprt, sk->sk_user_data = xprt; sk->sk_data_ready = xs_data_ready; sk->sk_write_space = xs_udp_write_space; + sk->sk_state_change = xs_local_state_change; sk->sk_error_report = xs_error_report; xprt_clear_connected(xprt); @@ -1932,6 +1971,9 @@ static void xs_local_connect(struct rpc_xprt *xprt, struct rpc_task *task) struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); int ret; + if (transport->file) + goto force_disconnect; + if (RPC_IS_ASYNC(task)) { /* * We want the AF_LOCAL connect to be resolved in the @@ -1944,11 +1986,17 @@ static void xs_local_connect(struct rpc_xprt *xprt, struct rpc_task *task) */ task->tk_rpc_status = -ENOTCONN; rpc_exit(task, -ENOTCONN); - return; + goto out_wake; } ret = xs_local_setup_socket(transport); if (ret && !RPC_IS_SOFTCONN(task)) msleep_interruptible(15000); + return; +force_disconnect: + xprt_force_disconnect(xprt); +out_wake: + xprt_clear_connecting(xprt); + xprt_wake_pending_tasks(xprt, -ENOTCONN); } #if IS_ENABLED(CONFIG_SUNRPC_SWAP) @@ -2544,6 +2592,9 @@ static int bc_sendto(struct rpc_rqst *req) int err; req->rq_xtime = ktime_get(); + err = xdr_alloc_bvec(xdr, rpc_task_gfp_mask()); + if (err < 0) + return err; err = xprt_sock_sendmsg(transport->sock, &msg, xdr, 0, marker, &sent); xdr_free_bvec(xdr); if (err < 0 || sent != (xdr->len + sizeof(marker))) @@ -2824,9 +2875,6 @@ static struct rpc_xprt *xs_setup_local(struct xprt_create *args) } xprt_set_bound(xprt); xs_format_peer_addresses(xprt, "local", RPCBIND_NETID_LOCAL); - ret = ERR_PTR(xs_local_setup_socket(transport)); - if (ret) - goto out_err; break; default: ret = ERR_PTR(-EAFNOSUPPORT); diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index 12f7b56771d9..3919fe2c58c5 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -483,11 +483,13 @@ handle_error: copy = min_t(size_t, size, (pfrag->size - pfrag->offset)); copy = min_t(size_t, copy, (max_open_record_len - record->len)); - rc = tls_device_copy_data(page_address(pfrag->page) + - pfrag->offset, copy, msg_iter); - if (rc) - goto handle_error; - tls_append_frag(record, pfrag, copy); + if (copy) { + rc = tls_device_copy_data(page_address(pfrag->page) + + pfrag->offset, copy, msg_iter); + if (rc) + goto handle_error; + tls_append_frag(record, pfrag, copy); + } size -= copy; if (!size) { @@ -1345,7 +1347,10 @@ static int tls_device_down(struct net_device *netdev) /* Device contexts for RX and TX will be freed in on sk_destruct * by tls_device_free_ctx. rx_conf and tx_conf stay in TLS_HW. + * Now release the ref taken above. */ + if (refcount_dec_and_test(&ctx->refcount)) + tls_device_free_ctx(ctx); } up_write(&device_offload_lock); diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 0024a692f0f8..a8976ef95528 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -1496,7 +1496,7 @@ static int decrypt_internal(struct sock *sk, struct sk_buff *skb, if (prot->version == TLS_1_3_VERSION || prot->cipher_type == TLS_CIPHER_CHACHA20_POLY1305) memcpy(iv + iv_offset, tls_ctx->rx.iv, - crypto_aead_ivsize(ctx->aead_recv)); + prot->iv_size + prot->salt_size); else memcpy(iv + iv_offset, tls_ctx->rx.iv, prot->salt_size); diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index e71a312faa1e..36367e7e3e0a 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1808,11 +1808,9 @@ static int maybe_init_creds(struct scm_cookie *scm, static bool unix_skb_scm_eq(struct sk_buff *skb, struct scm_cookie *scm) { - const struct unix_skb_parms *u = &UNIXCB(skb); - - return u->pid == scm->pid && - uid_eq(u->uid, scm->creds.uid) && - gid_eq(u->gid, scm->creds.gid) && + return UNIXCB(skb).pid == scm->pid && + uid_eq(UNIXCB(skb).uid, scm->creds.uid) && + gid_eq(UNIXCB(skb).gid, scm->creds.gid) && unix_secdata_eq(scm, skb); } diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index ee1c2b6b6971..1a3551b6d18b 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -528,7 +528,8 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { .len = IEEE80211_MAX_MESH_ID_LEN }, [NL80211_ATTR_MPATH_NEXT_HOP] = NLA_POLICY_ETH_ADDR_COMPAT, - [NL80211_ATTR_REG_ALPHA2] = { .type = NLA_STRING, .len = 2 }, + /* allow 3 for NUL-termination, we used to declare this NLA_STRING */ + [NL80211_ATTR_REG_ALPHA2] = NLA_POLICY_RANGE(NLA_BINARY, 2, 3), [NL80211_ATTR_REG_RULES] = { .type = NLA_NESTED }, [NL80211_ATTR_BSS_CTS_PROT] = { .type = NLA_U8 }, @@ -3172,6 +3173,15 @@ int nl80211_parse_chandef(struct cfg80211_registered_device *rdev, } else if (attrs[NL80211_ATTR_CHANNEL_WIDTH]) { chandef->width = nla_get_u32(attrs[NL80211_ATTR_CHANNEL_WIDTH]); + if (chandef->chan->band == NL80211_BAND_S1GHZ) { + /* User input error for channel width doesn't match channel */ + if (chandef->width != ieee80211_s1g_channel_width(chandef->chan)) { + NL_SET_ERR_MSG_ATTR(extack, + attrs[NL80211_ATTR_CHANNEL_WIDTH], + "bad channel width"); + return -EINVAL; + } + } if (attrs[NL80211_ATTR_CENTER_FREQ1]) { chandef->center_freq1 = nla_get_u32(attrs[NL80211_ATTR_CENTER_FREQ1]); @@ -11656,18 +11666,23 @@ static int nl80211_set_tx_bitrate_mask(struct sk_buff *skb, struct cfg80211_bitrate_mask mask; struct cfg80211_registered_device *rdev = info->user_ptr[0]; struct net_device *dev = info->user_ptr[1]; + struct wireless_dev *wdev = dev->ieee80211_ptr; int err; if (!rdev->ops->set_bitrate_mask) return -EOPNOTSUPP; + wdev_lock(wdev); err = nl80211_parse_tx_bitrate_mask(info, info->attrs, NL80211_ATTR_TX_RATES, &mask, dev, true); if (err) - return err; + goto out; - return rdev_set_bitrate_mask(rdev, dev, NULL, &mask); + err = rdev_set_bitrate_mask(rdev, dev, NULL, &mask); +out: + wdev_unlock(wdev); + return err; } static int nl80211_register_mgmt(struct sk_buff *skb, struct genl_info *info) diff --git a/net/wireless/scan.c b/net/wireless/scan.c index b2fdac96bab0..6d82bd9eaf8c 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -1829,7 +1829,7 @@ int cfg80211_get_ies_channel_number(const u8 *ie, size_t ielen, if (tmp && tmp->datalen >= sizeof(struct ieee80211_s1g_oper_ie)) { struct ieee80211_s1g_oper_ie *s1gop = (void *)tmp->data; - return s1gop->primary_ch; + return s1gop->oper_ch; } } else { tmp = cfg80211_find_elem(WLAN_EID_DS_PARAMS, ie, ielen); @@ -2018,11 +2018,13 @@ cfg80211_inform_single_bss_data(struct wiphy *wiphy, /* this is a nontransmitting bss, we need to add it to * transmitting bss' list if it is not there */ + spin_lock_bh(&rdev->bss_lock); if (cfg80211_add_nontrans_list(non_tx_data->tx_bss, &res->pub)) { if (__cfg80211_unlink_bss(rdev, res)) rdev->bss_generation++; } + spin_unlock_bh(&rdev->bss_lock); } trace_cfg80211_return_bss(&res->pub); diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 2c34caee0fd1..3a9348030e20 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -639,7 +639,7 @@ static int __xsk_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len if (sk_can_busy_loop(sk)) sk_busy_loop(sk, 1); /* only support non-blocking sockets */ - if (xsk_no_wakeup(sk)) + if (xs->zc && xsk_no_wakeup(sk)) return 0; pool = xs->pool; @@ -967,6 +967,19 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len) xp_get_pool(umem_xs->pool); xs->pool = umem_xs->pool; + + /* If underlying shared umem was created without Tx + * ring, allocate Tx descs array that Tx batching API + * utilizes + */ + if (xs->tx && !xs->pool->tx_descs) { + err = xp_alloc_tx_descs(xs->pool, xs); + if (err) { + xp_put_pool(xs->pool); + sockfd_put(sock); + goto out_unlock; + } + } } xdp_get_umem(umem_xs->umem); diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c index af040ffa14ff..87bdd71c7bb6 100644 --- a/net/xdp/xsk_buff_pool.c +++ b/net/xdp/xsk_buff_pool.c @@ -42,6 +42,16 @@ void xp_destroy(struct xsk_buff_pool *pool) kvfree(pool); } +int xp_alloc_tx_descs(struct xsk_buff_pool *pool, struct xdp_sock *xs) +{ + pool->tx_descs = kvcalloc(xs->tx->nentries, sizeof(*pool->tx_descs), + GFP_KERNEL); + if (!pool->tx_descs) + return -ENOMEM; + + return 0; +} + struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs, struct xdp_umem *umem) { @@ -59,11 +69,9 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs, if (!pool->heads) goto out; - if (xs->tx) { - pool->tx_descs = kcalloc(xs->tx->nentries, sizeof(*pool->tx_descs), GFP_KERNEL); - if (!pool->tx_descs) + if (xs->tx) + if (xp_alloc_tx_descs(pool, xs)) goto out; - } pool->chunk_mask = ~((u64)umem->chunk_size - 1); pool->addrs_cnt = umem->size; diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 19aa994f5d2c..f1876ea61fdc 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -2593,12 +2593,14 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy, if (xfrm[i]->props.mode != XFRM_MODE_TRANSPORT) { __u32 mark = 0; + int oif; if (xfrm[i]->props.smark.v || xfrm[i]->props.smark.m) mark = xfrm_smark_get(fl->flowi_mark, xfrm[i]); family = xfrm[i]->props.family; - dst = xfrm_dst_lookup(xfrm[i], tos, fl->flowi_oif, + oif = fl->flowi_oif ? : fl->flowi_l3mdev; + dst = xfrm_dst_lookup(xfrm[i], tos, oif, &saddr, &daddr, family, mark); err = PTR_ERR(dst); if (IS_ERR(dst)) @@ -3742,7 +3744,7 @@ static int stale_bundle(struct dst_entry *dst) void xfrm_dst_ifdown(struct dst_entry *dst, struct net_device *dev) { while ((dst = xfrm_dst_child(dst)) && dst->xfrm && dst->dev == dev) { - dst->dev = dev_net(dev)->loopback_dev; + dst->dev = blackhole_netdev; dev_hold(dst->dev); dev_put(dev); } diff --git a/samples/landlock/sandboxer.c b/samples/landlock/sandboxer.c index 8859fc193542..3e404e51ec64 100644 --- a/samples/landlock/sandboxer.c +++ b/samples/landlock/sandboxer.c @@ -22,9 +22,9 @@ #include <unistd.h> #ifndef landlock_create_ruleset -static inline int landlock_create_ruleset( - const struct landlock_ruleset_attr *const attr, - const size_t size, const __u32 flags) +static inline int +landlock_create_ruleset(const struct landlock_ruleset_attr *const attr, + const size_t size, const __u32 flags) { return syscall(__NR_landlock_create_ruleset, attr, size, flags); } @@ -32,17 +32,18 @@ static inline int landlock_create_ruleset( #ifndef landlock_add_rule static inline int landlock_add_rule(const int ruleset_fd, - const enum landlock_rule_type rule_type, - const void *const rule_attr, const __u32 flags) + const enum landlock_rule_type rule_type, + const void *const rule_attr, + const __u32 flags) { - return syscall(__NR_landlock_add_rule, ruleset_fd, rule_type, - rule_attr, flags); + return syscall(__NR_landlock_add_rule, ruleset_fd, rule_type, rule_attr, + flags); } #endif #ifndef landlock_restrict_self static inline int landlock_restrict_self(const int ruleset_fd, - const __u32 flags) + const __u32 flags) { return syscall(__NR_landlock_restrict_self, ruleset_fd, flags); } @@ -70,14 +71,17 @@ static int parse_path(char *env_path, const char ***const path_list) return num_paths; } +/* clang-format off */ + #define ACCESS_FILE ( \ LANDLOCK_ACCESS_FS_EXECUTE | \ LANDLOCK_ACCESS_FS_WRITE_FILE | \ LANDLOCK_ACCESS_FS_READ_FILE) -static int populate_ruleset( - const char *const env_var, const int ruleset_fd, - const __u64 allowed_access) +/* clang-format on */ + +static int populate_ruleset(const char *const env_var, const int ruleset_fd, + const __u64 allowed_access) { int num_paths, i, ret = 1; char *env_path_name; @@ -107,12 +111,10 @@ static int populate_ruleset( for (i = 0; i < num_paths; i++) { struct stat statbuf; - path_beneath.parent_fd = open(path_list[i], O_PATH | - O_CLOEXEC); + path_beneath.parent_fd = open(path_list[i], O_PATH | O_CLOEXEC); if (path_beneath.parent_fd < 0) { fprintf(stderr, "Failed to open \"%s\": %s\n", - path_list[i], - strerror(errno)); + path_list[i], strerror(errno)); goto out_free_name; } if (fstat(path_beneath.parent_fd, &statbuf)) { @@ -123,9 +125,10 @@ static int populate_ruleset( if (!S_ISDIR(statbuf.st_mode)) path_beneath.allowed_access &= ACCESS_FILE; if (landlock_add_rule(ruleset_fd, LANDLOCK_RULE_PATH_BENEATH, - &path_beneath, 0)) { - fprintf(stderr, "Failed to update the ruleset with \"%s\": %s\n", - path_list[i], strerror(errno)); + &path_beneath, 0)) { + fprintf(stderr, + "Failed to update the ruleset with \"%s\": %s\n", + path_list[i], strerror(errno)); close(path_beneath.parent_fd); goto out_free_name; } @@ -139,6 +142,8 @@ out_free_name: return ret; } +/* clang-format off */ + #define ACCESS_FS_ROUGHLY_READ ( \ LANDLOCK_ACCESS_FS_EXECUTE | \ LANDLOCK_ACCESS_FS_READ_FILE | \ @@ -154,64 +159,89 @@ out_free_name: LANDLOCK_ACCESS_FS_MAKE_SOCK | \ LANDLOCK_ACCESS_FS_MAKE_FIFO | \ LANDLOCK_ACCESS_FS_MAKE_BLOCK | \ - LANDLOCK_ACCESS_FS_MAKE_SYM) + LANDLOCK_ACCESS_FS_MAKE_SYM | \ + LANDLOCK_ACCESS_FS_REFER) + +#define ACCESS_ABI_2 ( \ + LANDLOCK_ACCESS_FS_REFER) + +/* clang-format on */ int main(const int argc, char *const argv[], char *const *const envp) { const char *cmd_path; char *const *cmd_argv; - int ruleset_fd; + int ruleset_fd, abi; + __u64 access_fs_ro = ACCESS_FS_ROUGHLY_READ, + access_fs_rw = ACCESS_FS_ROUGHLY_READ | ACCESS_FS_ROUGHLY_WRITE; struct landlock_ruleset_attr ruleset_attr = { - .handled_access_fs = ACCESS_FS_ROUGHLY_READ | - ACCESS_FS_ROUGHLY_WRITE, + .handled_access_fs = access_fs_rw, }; if (argc < 2) { - fprintf(stderr, "usage: %s=\"...\" %s=\"...\" %s <cmd> [args]...\n\n", - ENV_FS_RO_NAME, ENV_FS_RW_NAME, argv[0]); - fprintf(stderr, "Launch a command in a restricted environment.\n\n"); + fprintf(stderr, + "usage: %s=\"...\" %s=\"...\" %s <cmd> [args]...\n\n", + ENV_FS_RO_NAME, ENV_FS_RW_NAME, argv[0]); + fprintf(stderr, + "Launch a command in a restricted environment.\n\n"); fprintf(stderr, "Environment variables containing paths, " "each separated by a colon:\n"); - fprintf(stderr, "* %s: list of paths allowed to be used in a read-only way.\n", - ENV_FS_RO_NAME); - fprintf(stderr, "* %s: list of paths allowed to be used in a read-write way.\n", - ENV_FS_RW_NAME); - fprintf(stderr, "\nexample:\n" - "%s=\"/bin:/lib:/usr:/proc:/etc:/dev/urandom\" " - "%s=\"/dev/null:/dev/full:/dev/zero:/dev/pts:/tmp\" " - "%s bash -i\n", - ENV_FS_RO_NAME, ENV_FS_RW_NAME, argv[0]); + fprintf(stderr, + "* %s: list of paths allowed to be used in a read-only way.\n", + ENV_FS_RO_NAME); + fprintf(stderr, + "* %s: list of paths allowed to be used in a read-write way.\n", + ENV_FS_RW_NAME); + fprintf(stderr, + "\nexample:\n" + "%s=\"/bin:/lib:/usr:/proc:/etc:/dev/urandom\" " + "%s=\"/dev/null:/dev/full:/dev/zero:/dev/pts:/tmp\" " + "%s bash -i\n", + ENV_FS_RO_NAME, ENV_FS_RW_NAME, argv[0]); return 1; } - ruleset_fd = landlock_create_ruleset(&ruleset_attr, sizeof(ruleset_attr), 0); - if (ruleset_fd < 0) { + abi = landlock_create_ruleset(NULL, 0, LANDLOCK_CREATE_RULESET_VERSION); + if (abi < 0) { const int err = errno; - perror("Failed to create a ruleset"); + perror("Failed to check Landlock compatibility"); switch (err) { case ENOSYS: - fprintf(stderr, "Hint: Landlock is not supported by the current kernel. " - "To support it, build the kernel with " - "CONFIG_SECURITY_LANDLOCK=y and prepend " - "\"landlock,\" to the content of CONFIG_LSM.\n"); + fprintf(stderr, + "Hint: Landlock is not supported by the current kernel. " + "To support it, build the kernel with " + "CONFIG_SECURITY_LANDLOCK=y and prepend " + "\"landlock,\" to the content of CONFIG_LSM.\n"); break; case EOPNOTSUPP: - fprintf(stderr, "Hint: Landlock is currently disabled. " - "It can be enabled in the kernel configuration by " - "prepending \"landlock,\" to the content of CONFIG_LSM, " - "or at boot time by setting the same content to the " - "\"lsm\" kernel parameter.\n"); + fprintf(stderr, + "Hint: Landlock is currently disabled. " + "It can be enabled in the kernel configuration by " + "prepending \"landlock,\" to the content of CONFIG_LSM, " + "or at boot time by setting the same content to the " + "\"lsm\" kernel parameter.\n"); break; } return 1; } - if (populate_ruleset(ENV_FS_RO_NAME, ruleset_fd, - ACCESS_FS_ROUGHLY_READ)) { + /* Best-effort security. */ + if (abi < 2) { + ruleset_attr.handled_access_fs &= ~ACCESS_ABI_2; + access_fs_ro &= ~ACCESS_ABI_2; + access_fs_rw &= ~ACCESS_ABI_2; + } + + ruleset_fd = + landlock_create_ruleset(&ruleset_attr, sizeof(ruleset_attr), 0); + if (ruleset_fd < 0) { + perror("Failed to create a ruleset"); + return 1; + } + if (populate_ruleset(ENV_FS_RO_NAME, ruleset_fd, access_fs_ro)) { goto err_close_ruleset; } - if (populate_ruleset(ENV_FS_RW_NAME, ruleset_fd, - ACCESS_FS_ROUGHLY_READ | ACCESS_FS_ROUGHLY_WRITE)) { + if (populate_ruleset(ENV_FS_RW_NAME, ruleset_fd, access_fs_rw)) { goto err_close_ruleset; } if (prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0)) { @@ -228,7 +258,7 @@ int main(const int argc, char *const argv[], char *const *const envp) cmd_argv = argv + 1; execvpe(cmd_path, cmd_argv, envp); fprintf(stderr, "Failed to execute \"%s\": %s\n", cmd_path, - strerror(errno)); + strerror(errno)); fprintf(stderr, "Hint: access to the binary, the interpreter or " "shared libraries may be denied.\n"); return 1; diff --git a/samples/trace_events/trace_custom_sched.h b/samples/trace_events/trace_custom_sched.h index 9fdd8e7c2a45..951388334a3f 100644 --- a/samples/trace_events/trace_custom_sched.h +++ b/samples/trace_events/trace_custom_sched.h @@ -25,11 +25,11 @@ TRACE_CUSTOM_EVENT(sched_switch, * that the custom event is using. */ TP_PROTO(bool preempt, - unsigned int prev_state, struct task_struct *prev, - struct task_struct *next), + struct task_struct *next, + unsigned int prev_state), - TP_ARGS(preempt, prev_state, prev, next), + TP_ARGS(preempt, prev, next, prev_state), /* * The next fields are where the customization happens. diff --git a/scripts/Makefile.build b/scripts/Makefile.build index 9717e6f6fb31..f89d3fcff39f 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -222,25 +222,29 @@ cmd_record_mcount = $(if $(findstring $(strip $(CC_FLAGS_FTRACE)),$(_c_flags)), $(sub_cmd_record_mcount)) endif # CONFIG_FTRACE_MCOUNT_USE_RECORDMCOUNT -ifdef CONFIG_STACK_VALIDATION +ifdef CONFIG_OBJTOOL objtool := $(objtree)/tools/objtool/objtool objtool_args = \ - $(if $(CONFIG_UNWINDER_ORC),orc generate,check) \ - $(if $(part-of-module), --module) \ - $(if $(CONFIG_X86_KERNEL_IBT), --lto --ibt) \ - $(if $(CONFIG_FRAME_POINTER),, --no-fp) \ - $(if $(CONFIG_GCOV_KERNEL)$(CONFIG_LTO_CLANG), --no-unreachable)\ - $(if $(CONFIG_RETPOLINE), --retpoline) \ - $(if $(CONFIG_X86_SMAP), --uaccess) \ + $(if $(CONFIG_HAVE_JUMP_LABEL_HACK), --hacks=jump_label) \ + $(if $(CONFIG_HAVE_NOINSTR_HACK), --hacks=noinstr) \ + $(if $(CONFIG_X86_KERNEL_IBT), --ibt) \ $(if $(CONFIG_FTRACE_MCOUNT_USE_OBJTOOL), --mcount) \ - $(if $(CONFIG_SLS), --sls) + $(if $(CONFIG_UNWINDER_ORC), --orc) \ + $(if $(CONFIG_RETPOLINE), --retpoline) \ + $(if $(CONFIG_SLS), --sls) \ + $(if $(CONFIG_STACK_VALIDATION), --stackval) \ + $(if $(CONFIG_HAVE_STATIC_CALL_INLINE), --static-call) \ + --uaccess \ + $(if $(linked-object), --link) \ + $(if $(part-of-module), --module) \ + $(if $(CONFIG_GCOV_KERNEL), --no-unreachable) cmd_objtool = $(if $(objtool-enabled), ; $(objtool) $(objtool_args) $@) cmd_gen_objtooldep = $(if $(objtool-enabled), { echo ; echo '$@: $$(wildcard $(objtool))' ; } >> $(dot-target).cmd) -endif # CONFIG_STACK_VALIDATION +endif # CONFIG_OBJTOOL ifneq ($(CONFIG_LTO_CLANG)$(CONFIG_X86_KERNEL_IBT),) @@ -303,6 +307,7 @@ quiet_cmd_cc_prelink_modules = LD [M] $@ # modules into native code $(obj)/%.prelink.o: objtool-enabled = y $(obj)/%.prelink.o: part-of-module := y +$(obj)/%.prelink.o: linked-object := y $(obj)/%.prelink.o: $(obj)/%.o FORCE $(call if_changed,cc_prelink_modules) diff --git a/scripts/Makefile.gcc-plugins b/scripts/Makefile.gcc-plugins index f67153b260c0..692d64a70542 100644 --- a/scripts/Makefile.gcc-plugins +++ b/scripts/Makefile.gcc-plugins @@ -8,8 +8,6 @@ ifdef CONFIG_GCC_PLUGIN_LATENT_ENTROPY endif export DISABLE_LATENT_ENTROPY_PLUGIN -gcc-plugin-$(CONFIG_GCC_PLUGIN_SANCOV) += sancov_plugin.so - gcc-plugin-$(CONFIG_GCC_PLUGIN_STRUCTLEAK) += structleak_plugin.so gcc-plugin-cflags-$(CONFIG_GCC_PLUGIN_STRUCTLEAK_VERBOSE) \ += -fplugin-arg-structleak_plugin-verbose @@ -24,12 +22,6 @@ export DISABLE_STRUCTLEAK_PLUGIN gcc-plugin-cflags-$(CONFIG_GCC_PLUGIN_STRUCTLEAK) \ += -DSTRUCTLEAK_PLUGIN -gcc-plugin-$(CONFIG_GCC_PLUGIN_RANDSTRUCT) += randomize_layout_plugin.so -gcc-plugin-cflags-$(CONFIG_GCC_PLUGIN_RANDSTRUCT) \ - += -DRANDSTRUCT_PLUGIN -gcc-plugin-cflags-$(CONFIG_GCC_PLUGIN_RANDSTRUCT_PERFORMANCE) \ - += -fplugin-arg-randomize_layout_plugin-performance-mode - gcc-plugin-$(CONFIG_GCC_PLUGIN_STACKLEAK) += stackleak_plugin.so gcc-plugin-cflags-$(CONFIG_GCC_PLUGIN_STACKLEAK) \ += -DSTACKLEAK_PLUGIN @@ -53,13 +45,19 @@ export DISABLE_ARM_SSP_PER_TASK_PLUGIN # All the plugin CFLAGS are collected here in case a build target needs to # filter them out of the KBUILD_CFLAGS. GCC_PLUGINS_CFLAGS := $(strip $(addprefix -fplugin=$(objtree)/scripts/gcc-plugins/, $(gcc-plugin-y)) $(gcc-plugin-cflags-y)) -# The sancov_plugin.so is included via CFLAGS_KCOV, so it is removed here. -GCC_PLUGINS_CFLAGS := $(filter-out %/sancov_plugin.so, $(GCC_PLUGINS_CFLAGS)) export GCC_PLUGINS_CFLAGS # Add the flags to the build! KBUILD_CFLAGS += $(GCC_PLUGINS_CFLAGS) -# All enabled GCC plugins are collected here for building below. -GCC_PLUGIN := $(gcc-plugin-y) +# Some plugins are enabled outside of this Makefile, but they still need to +# be included in GCC_PLUGIN so they can get built. +gcc-plugin-external-$(CONFIG_GCC_PLUGIN_SANCOV) \ + += sancov_plugin.so +gcc-plugin-external-$(CONFIG_GCC_PLUGIN_RANDSTRUCT) \ + += randomize_layout_plugin.so + +# All enabled GCC plugins are collected here for building in +# scripts/gcc-scripts/Makefile. +GCC_PLUGIN := $(gcc-plugin-y) $(gcc-plugin-external-y) export GCC_PLUGIN diff --git a/scripts/Makefile.randstruct b/scripts/Makefile.randstruct new file mode 100644 index 000000000000..24e283e89893 --- /dev/null +++ b/scripts/Makefile.randstruct @@ -0,0 +1,17 @@ +# SPDX-License-Identifier: GPL-2.0 + +randstruct-cflags-y += -DRANDSTRUCT + +ifdef CONFIG_GCC_PLUGIN_RANDSTRUCT +randstruct-cflags-y \ + += -fplugin=$(objtree)/scripts/gcc-plugins/randomize_layout_plugin.so +randstruct-cflags-$(CONFIG_RANDSTRUCT_PERFORMANCE) \ + += -fplugin-arg-randomize_layout_plugin-performance-mode +else +randstruct-cflags-y \ + += -frandomize-layout-seed-file=$(objtree)/scripts/basic/randstruct.seed +endif + +export RANDSTRUCT_CFLAGS := $(randstruct-cflags-y) + +KBUILD_CFLAGS += $(RANDSTRUCT_CFLAGS) diff --git a/scripts/atomic/gen-atomic-fallback.sh b/scripts/atomic/gen-atomic-fallback.sh index 8e2da71f1d5f..3a07695e3c89 100755 --- a/scripts/atomic/gen-atomic-fallback.sh +++ b/scripts/atomic/gen-atomic-fallback.sh @@ -164,41 +164,44 @@ gen_xchg_fallbacks() gen_try_cmpxchg_fallback() { + local cmpxchg="$1"; shift; local order="$1"; shift; cat <<EOF -#ifndef arch_try_cmpxchg${order} -#define arch_try_cmpxchg${order}(_ptr, _oldp, _new) \\ +#ifndef arch_try_${cmpxchg}${order} +#define arch_try_${cmpxchg}${order}(_ptr, _oldp, _new) \\ ({ \\ typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \\ - ___r = arch_cmpxchg${order}((_ptr), ___o, (_new)); \\ + ___r = arch_${cmpxchg}${order}((_ptr), ___o, (_new)); \\ if (unlikely(___r != ___o)) \\ *___op = ___r; \\ likely(___r == ___o); \\ }) -#endif /* arch_try_cmpxchg${order} */ +#endif /* arch_try_${cmpxchg}${order} */ EOF } gen_try_cmpxchg_fallbacks() { - printf "#ifndef arch_try_cmpxchg_relaxed\n" - printf "#ifdef arch_try_cmpxchg\n" + local cmpxchg="$1"; shift; - gen_basic_fallbacks "arch_try_cmpxchg" + printf "#ifndef arch_try_${cmpxchg}_relaxed\n" + printf "#ifdef arch_try_${cmpxchg}\n" - printf "#endif /* arch_try_cmpxchg */\n\n" + gen_basic_fallbacks "arch_try_${cmpxchg}" + + printf "#endif /* arch_try_${cmpxchg} */\n\n" for order in "" "_acquire" "_release" "_relaxed"; do - gen_try_cmpxchg_fallback "${order}" + gen_try_cmpxchg_fallback "${cmpxchg}" "${order}" done - printf "#else /* arch_try_cmpxchg_relaxed */\n" + printf "#else /* arch_try_${cmpxchg}_relaxed */\n" - gen_order_fallbacks "arch_try_cmpxchg" + gen_order_fallbacks "arch_try_${cmpxchg}" - printf "#endif /* arch_try_cmpxchg_relaxed */\n\n" + printf "#endif /* arch_try_${cmpxchg}_relaxed */\n\n" } cat << EOF @@ -218,7 +221,9 @@ for xchg in "arch_xchg" "arch_cmpxchg" "arch_cmpxchg64"; do gen_xchg_fallbacks "${xchg}" done -gen_try_cmpxchg_fallbacks +for cmpxchg in "cmpxchg" "cmpxchg64"; do + gen_try_cmpxchg_fallbacks "${cmpxchg}" +done grep '^[a-z]' "$1" | while read name meta args; do gen_proto "${meta}" "${name}" "atomic" "int" ${args} diff --git a/scripts/atomic/gen-atomic-instrumented.sh b/scripts/atomic/gen-atomic-instrumented.sh index 68f902731d01..77c06526a574 100755 --- a/scripts/atomic/gen-atomic-instrumented.sh +++ b/scripts/atomic/gen-atomic-instrumented.sh @@ -166,7 +166,7 @@ grep '^[a-z]' "$1" | while read name meta args; do done -for xchg in "xchg" "cmpxchg" "cmpxchg64" "try_cmpxchg"; do +for xchg in "xchg" "cmpxchg" "cmpxchg64" "try_cmpxchg" "try_cmpxchg64"; do for order in "" "_acquire" "_release" "_relaxed"; do gen_xchg "${xchg}" "${order}" "" printf "\n" diff --git a/scripts/basic/.gitignore b/scripts/basic/.gitignore index 961c91c8a884..07c195f605a1 100644 --- a/scripts/basic/.gitignore +++ b/scripts/basic/.gitignore @@ -1,2 +1,3 @@ # SPDX-License-Identifier: GPL-2.0-only /fixdep +/randstruct.seed diff --git a/scripts/basic/Makefile b/scripts/basic/Makefile index eeb6a38c5551..dd289a6725ac 100644 --- a/scripts/basic/Makefile +++ b/scripts/basic/Makefile @@ -3,3 +3,14 @@ # fixdep: used to generate dependency information during build process hostprogs-always-y += fixdep + +# randstruct: the seed is needed before building the gcc-plugin or +# before running a Clang kernel build. +gen-randstruct-seed := $(srctree)/scripts/gen-randstruct-seed.sh +quiet_cmd_create_randstruct_seed = GENSEED $@ +cmd_create_randstruct_seed = \ + $(CONFIG_SHELL) $(gen-randstruct-seed) \ + $@ $(objtree)/include/generated/randstruct_hash.h +$(obj)/randstruct.seed: $(gen-randstruct-seed) FORCE + $(call if_changed,create_randstruct_seed) +always-$(CONFIG_RANDSTRUCT) += randstruct.seed diff --git a/scripts/check-blacklist-hashes.awk b/scripts/check-blacklist-hashes.awk new file mode 100755 index 000000000000..107c1d3204d4 --- /dev/null +++ b/scripts/check-blacklist-hashes.awk @@ -0,0 +1,37 @@ +#!/usr/bin/awk -f +# SPDX-License-Identifier: GPL-2.0 +# +# Copyright © 2020, Microsoft Corporation. All rights reserved. +# +# Author: Mickaël Salaün <mic@linux.microsoft.com> +# +# Check that a CONFIG_SYSTEM_BLACKLIST_HASH_LIST file contains a valid array of +# hash strings. Such string must start with a prefix ("tbs" or "bin"), then a +# colon (":"), and finally an even number of hexadecimal lowercase characters +# (up to 128). + +BEGIN { + RS = "," +} +{ + if (!match($0, "^[ \t\n\r]*\"([^\"]*)\"[ \t\n\r]*$", part1)) { + print "Not a string (item " NR "):", $0; + exit 1; + } + if (!match(part1[1], "^(tbs|bin):(.*)$", part2)) { + print "Unknown prefix (item " NR "):", part1[1]; + exit 1; + } + if (!match(part2[2], "^([0-9a-f]+)$", part3)) { + print "Not a lowercase hexadecimal string (item " NR "):", part2[2]; + exit 1; + } + if (length(part3[1]) > 128) { + print "Hash string too long (item " NR "):", part3[1]; + exit 1; + } + if (length(part3[1]) % 2 == 1) { + print "Not an even number of hexadecimal characters (item " NR "):", part3[1]; + exit 1; + } +} diff --git a/scripts/faddr2line b/scripts/faddr2line index 6c6439f69a72..0e6268d59883 100755 --- a/scripts/faddr2line +++ b/scripts/faddr2line @@ -44,17 +44,6 @@ set -o errexit set -o nounset -READELF="${CROSS_COMPILE:-}readelf" -ADDR2LINE="${CROSS_COMPILE:-}addr2line" -SIZE="${CROSS_COMPILE:-}size" -NM="${CROSS_COMPILE:-}nm" - -command -v awk >/dev/null 2>&1 || die "awk isn't installed" -command -v ${READELF} >/dev/null 2>&1 || die "readelf isn't installed" -command -v ${ADDR2LINE} >/dev/null 2>&1 || die "addr2line isn't installed" -command -v ${SIZE} >/dev/null 2>&1 || die "size isn't installed" -command -v ${NM} >/dev/null 2>&1 || die "nm isn't installed" - usage() { echo "usage: faddr2line [--list] <object file> <func+offset> <func+offset>..." >&2 exit 1 @@ -69,6 +58,14 @@ die() { exit 1 } +READELF="${CROSS_COMPILE:-}readelf" +ADDR2LINE="${CROSS_COMPILE:-}addr2line" +AWK="awk" + +command -v ${AWK} >/dev/null 2>&1 || die "${AWK} isn't installed" +command -v ${READELF} >/dev/null 2>&1 || die "${READELF} isn't installed" +command -v ${ADDR2LINE} >/dev/null 2>&1 || die "${ADDR2LINE} isn't installed" + # Try to figure out the source directory prefix so we can remove it from the # addr2line output. HACK ALERT: This assumes that start_kernel() is in # init/main.c! This only works for vmlinux. Otherwise it falls back to @@ -76,7 +73,7 @@ die() { find_dir_prefix() { local objfile=$1 - local start_kernel_addr=$(${READELF} -sW $objfile | awk '$8 == "start_kernel" {printf "0x%s", $2}') + local start_kernel_addr=$(${READELF} --symbols --wide $objfile | ${AWK} '$8 == "start_kernel" {printf "0x%s", $2}') [[ -z $start_kernel_addr ]] && return local file_line=$(${ADDR2LINE} -e $objfile $start_kernel_addr) @@ -97,86 +94,133 @@ __faddr2line() { local dir_prefix=$3 local print_warnings=$4 - local func=${func_addr%+*} + local sym_name=${func_addr%+*} local offset=${func_addr#*+} offset=${offset%/*} - local size= - [[ $func_addr =~ "/" ]] && size=${func_addr#*/} + local user_size= + [[ $func_addr =~ "/" ]] && user_size=${func_addr#*/} - if [[ -z $func ]] || [[ -z $offset ]] || [[ $func = $func_addr ]]; then + if [[ -z $sym_name ]] || [[ -z $offset ]] || [[ $sym_name = $func_addr ]]; then warn "bad func+offset $func_addr" DONE=1 return fi # Go through each of the object's symbols which match the func name. - # In rare cases there might be duplicates. - file_end=$(${SIZE} -Ax $objfile | awk '$1 == ".text" {print $2}') - while read symbol; do - local fields=($symbol) - local sym_base=0x${fields[0]} - local sym_type=${fields[1]} - local sym_end=${fields[3]} - - # calculate the size - local sym_size=$(($sym_end - $sym_base)) + # In rare cases there might be duplicates, in which case we print all + # matches. + while read line; do + local fields=($line) + local sym_addr=0x${fields[1]} + local sym_elf_size=${fields[2]} + local sym_sec=${fields[6]} + + # Get the section size: + local sec_size=$(${READELF} --section-headers --wide $objfile | + sed 's/\[ /\[/' | + ${AWK} -v sec=$sym_sec '$1 == "[" sec "]" { print "0x" $6; exit }') + + if [[ -z $sec_size ]]; then + warn "bad section size: section: $sym_sec" + DONE=1 + return + fi + + # Calculate the symbol size. + # + # Unfortunately we can't use the ELF size, because kallsyms + # also includes the padding bytes in its size calculation. For + # kallsyms, the size calculation is the distance between the + # symbol and the next symbol in a sorted list. + local sym_size + local cur_sym_addr + local found=0 + while read line; do + local fields=($line) + cur_sym_addr=0x${fields[1]} + local cur_sym_elf_size=${fields[2]} + local cur_sym_name=${fields[7]:-} + + if [[ $cur_sym_addr = $sym_addr ]] && + [[ $cur_sym_elf_size = $sym_elf_size ]] && + [[ $cur_sym_name = $sym_name ]]; then + found=1 + continue + fi + + if [[ $found = 1 ]]; then + sym_size=$(($cur_sym_addr - $sym_addr)) + [[ $sym_size -lt $sym_elf_size ]] && continue; + found=2 + break + fi + done < <(${READELF} --symbols --wide $objfile | ${AWK} -v sec=$sym_sec '$7 == sec' | sort --key=2) + + if [[ $found = 0 ]]; then + warn "can't find symbol: sym_name: $sym_name sym_sec: $sym_sec sym_addr: $sym_addr sym_elf_size: $sym_elf_size" + DONE=1 + return + fi + + # If nothing was found after the symbol, assume it's the last + # symbol in the section. + [[ $found = 1 ]] && sym_size=$(($sec_size - $sym_addr)) + if [[ -z $sym_size ]] || [[ $sym_size -le 0 ]]; then - warn "bad symbol size: base: $sym_base end: $sym_end" + warn "bad symbol size: sym_addr: $sym_addr cur_sym_addr: $cur_sym_addr" DONE=1 return fi + sym_size=0x$(printf %x $sym_size) - # calculate the address - local addr=$(($sym_base + $offset)) + # Calculate the section address from user-supplied offset: + local addr=$(($sym_addr + $offset)) if [[ -z $addr ]] || [[ $addr = 0 ]]; then - warn "bad address: $sym_base + $offset" + warn "bad address: $sym_addr + $offset" DONE=1 return fi addr=0x$(printf %x $addr) - # weed out non-function symbols - if [[ $sym_type != t ]] && [[ $sym_type != T ]]; then - [[ $print_warnings = 1 ]] && - echo "skipping $func address at $addr due to non-function symbol of type '$sym_type'" - continue - fi - - # if the user provided a size, make sure it matches the symbol's size - if [[ -n $size ]] && [[ $size -ne $sym_size ]]; then + # If the user provided a size, make sure it matches the symbol's size: + if [[ -n $user_size ]] && [[ $user_size -ne $sym_size ]]; then [[ $print_warnings = 1 ]] && - echo "skipping $func address at $addr due to size mismatch ($size != $sym_size)" + echo "skipping $sym_name address at $addr due to size mismatch ($user_size != $sym_size)" continue; fi - # make sure the provided offset is within the symbol's range + # Make sure the provided offset is within the symbol's range: if [[ $offset -gt $sym_size ]]; then [[ $print_warnings = 1 ]] && - echo "skipping $func address at $addr due to size mismatch ($offset > $sym_size)" + echo "skipping $sym_name address at $addr due to size mismatch ($offset > $sym_size)" continue fi - # separate multiple entries with a blank line + # In case of duplicates or multiple addresses specified on the + # cmdline, separate multiple entries with a blank line: [[ $FIRST = 0 ]] && echo FIRST=0 - # pass real address to addr2line - echo "$func+$offset/$sym_size:" - local file_lines=$(${ADDR2LINE} -fpie $objfile $addr | sed "s; $dir_prefix\(\./\)*; ;") - [[ -z $file_lines ]] && return + echo "$sym_name+$offset/$sym_size:" + # Pass section address to addr2line and strip absolute paths + # from the output: + local output=$(${ADDR2LINE} -fpie $objfile $addr | sed "s; $dir_prefix\(\./\)*; ;") + [[ -z $output ]] && continue + + # Default output (non --list): if [[ $LIST = 0 ]]; then - echo "$file_lines" | while read -r line + echo "$output" | while read -r line do echo $line done DONE=1; - return + continue fi - # show each line with context - echo "$file_lines" | while read -r line + # For --list, show each line with its corresponding source code: + echo "$output" | while read -r line do echo echo $line @@ -184,12 +228,12 @@ __faddr2line() { n1=$[$n-5] n2=$[$n+5] f=$(echo $line | sed 's/.*at \(.\+\):.*/\1/g') - awk 'NR>=strtonum("'$n1'") && NR<=strtonum("'$n2'") { if (NR=='$n') printf(">%d<", NR); else printf(" %d ", NR); printf("\t%s\n", $0)}' $f + ${AWK} 'NR>=strtonum("'$n1'") && NR<=strtonum("'$n2'") { if (NR=='$n') printf(">%d<", NR); else printf(" %d ", NR); printf("\t%s\n", $0)}' $f done DONE=1 - done < <(${NM} -n $objfile | awk -v fn=$func -v end=$file_end '$3 == fn { found=1; line=$0; start=$1; next } found == 1 { found=0; print line, "0x"$1 } END {if (found == 1) print line, end; }') + done < <(${READELF} --symbols --wide $objfile | ${AWK} -v fn=$sym_name '$4 == "FUNC" && $8 == fn') } [[ $# -lt 2 ]] && usage diff --git a/scripts/gcc-plugins/Kconfig b/scripts/gcc-plugins/Kconfig index 51d81c3f03d6..e383cda05367 100644 --- a/scripts/gcc-plugins/Kconfig +++ b/scripts/gcc-plugins/Kconfig @@ -46,44 +46,6 @@ config GCC_PLUGIN_LATENT_ENTROPY * https://grsecurity.net/ * https://pax.grsecurity.net/ -config GCC_PLUGIN_RANDSTRUCT - bool "Randomize layout of sensitive kernel structures" - select MODVERSIONS if MODULES - help - If you say Y here, the layouts of structures that are entirely - function pointers (and have not been manually annotated with - __no_randomize_layout), or structures that have been explicitly - marked with __randomize_layout, will be randomized at compile-time. - This can introduce the requirement of an additional information - exposure vulnerability for exploits targeting these structure - types. - - Enabling this feature will introduce some performance impact, - slightly increase memory usage, and prevent the use of forensic - tools like Volatility against the system (unless the kernel - source tree isn't cleaned after kernel installation). - - The seed used for compilation is located at - scripts/gcc-plugins/randomize_layout_seed.h. It remains after - a make clean to allow for external modules to be compiled with - the existing seed and will be removed by a make mrproper or - make distclean. - - This plugin was ported from grsecurity/PaX. More information at: - * https://grsecurity.net/ - * https://pax.grsecurity.net/ - -config GCC_PLUGIN_RANDSTRUCT_PERFORMANCE - bool "Use cacheline-aware structure randomization" - depends on GCC_PLUGIN_RANDSTRUCT - depends on !COMPILE_TEST # do not reduce test coverage - help - If you say Y here, the RANDSTRUCT randomization will make a - best effort at restricting randomization to cacheline-sized - groups of elements. It will further not randomize bitfields - in structures. This reduces the performance hit of RANDSTRUCT - at the cost of weakened randomization. - config GCC_PLUGIN_ARM_SSP_PER_TASK bool depends on GCC_PLUGINS && ARM diff --git a/scripts/gcc-plugins/Makefile b/scripts/gcc-plugins/Makefile index 1952d3bb80c6..6f0aecad5d67 100644 --- a/scripts/gcc-plugins/Makefile +++ b/scripts/gcc-plugins/Makefile @@ -1,12 +1,17 @@ # SPDX-License-Identifier: GPL-2.0 -$(obj)/randomize_layout_plugin.so: $(objtree)/$(obj)/randomize_layout_seed.h -quiet_cmd_create_randomize_layout_seed = GENSEED $@ +$(obj)/randomize_layout_plugin.so: $(obj)/randomize_layout_seed.h +quiet_cmd_create_randomize_layout_seed = SEEDHDR $@ cmd_create_randomize_layout_seed = \ - $(CONFIG_SHELL) $(srctree)/$(src)/gen-random-seed.sh $@ $(objtree)/include/generated/randomize_layout_hash.h -$(objtree)/$(obj)/randomize_layout_seed.h: FORCE + SEED=$$(cat $(filter-out FORCE,$^) </dev/null); \ + echo '/*' > $@; \ + echo ' * This file is automatically generated. Keep it private.' >> $@; \ + echo ' * Exposing this value will expose the layout of randomized structures.' >> $@; \ + echo ' */' >> $@; \ + echo "const char *randstruct_seed = \"$$SEED\";" >> $@ +$(obj)/randomize_layout_seed.h: $(objtree)/scripts/basic/randstruct.seed FORCE $(call if_changed,create_randomize_layout_seed) -targets += randomize_layout_seed.h randomize_layout_hash.h +targets += randomize_layout_seed.h # Build rules for plugins # @@ -23,10 +28,11 @@ GCC_PLUGINS_DIR = $(shell $(CC) -print-file-name=plugin) plugin_cxxflags = -Wp,-MMD,$(depfile) $(KBUILD_HOSTCXXFLAGS) -fPIC \ -include $(srctree)/include/linux/compiler-version.h \ - -I $(GCC_PLUGINS_DIR)/include -I $(obj) -std=gnu++11 \ - -fno-rtti -fno-exceptions -fasynchronous-unwind-tables \ - -ggdb -Wno-narrowing -Wno-unused-variable \ - -Wno-format-diag + -include $(objtree)/include/generated/utsrelease.h \ + -I $(GCC_PLUGINS_DIR)/include -I $(obj) -std=gnu++11 \ + -fno-rtti -fno-exceptions -fasynchronous-unwind-tables \ + -ggdb -Wno-narrowing -Wno-unused-variable \ + -Wno-format-diag plugin_ldflags = -shared diff --git a/scripts/gcc-plugins/gen-random-seed.sh b/scripts/gcc-plugins/gen-random-seed.sh deleted file mode 100755 index 68af5cc20a64..000000000000 --- a/scripts/gcc-plugins/gen-random-seed.sh +++ /dev/null @@ -1,9 +0,0 @@ -#!/bin/sh -# SPDX-License-Identifier: GPL-2.0 - -if [ ! -f "$1" ]; then - SEED=`od -A n -t x8 -N 32 /dev/urandom | tr -d ' \n'` - echo "const char *randstruct_seed = \"$SEED\";" > "$1" - HASH=`echo -n "$SEED" | sha256sum | cut -d" " -f1 | tr -d ' \n'` - echo "#define RANDSTRUCT_HASHED_SEED \"$HASH\"" > "$2" -fi diff --git a/scripts/gcc-plugins/latent_entropy_plugin.c b/scripts/gcc-plugins/latent_entropy_plugin.c index 589454bce930..5d415b2572a8 100644 --- a/scripts/gcc-plugins/latent_entropy_plugin.c +++ b/scripts/gcc-plugins/latent_entropy_plugin.c @@ -82,29 +82,35 @@ __visible int plugin_is_GPL_compatible; static GTY(()) tree latent_entropy_decl; static struct plugin_info latent_entropy_plugin_info = { - .version = "201606141920vanilla", + .version = UTS_RELEASE, .help = "disable\tturn off latent entropy instrumentation\n", }; -static unsigned HOST_WIDE_INT seed; -/* - * get_random_seed() (this is a GCC function) generates the seed. - * This is a simple random generator without any cryptographic security because - * the entropy doesn't come from here. - */ +static unsigned HOST_WIDE_INT deterministic_seed; +static unsigned HOST_WIDE_INT rnd_buf[32]; +static size_t rnd_idx = ARRAY_SIZE(rnd_buf); +static int urandom_fd = -1; + static unsigned HOST_WIDE_INT get_random_const(void) { - unsigned int i; - unsigned HOST_WIDE_INT ret = 0; - - for (i = 0; i < 8 * sizeof(ret); i++) { - ret = (ret << 1) | (seed & 1); - seed >>= 1; - if (ret & 1) - seed ^= 0xD800000000000000ULL; + if (deterministic_seed) { + unsigned HOST_WIDE_INT w = deterministic_seed; + w ^= w << 13; + w ^= w >> 7; + w ^= w << 17; + deterministic_seed = w; + return deterministic_seed; } - return ret; + if (urandom_fd < 0) { + urandom_fd = open("/dev/urandom", O_RDONLY); + gcc_assert(urandom_fd >= 0); + } + if (rnd_idx >= ARRAY_SIZE(rnd_buf)) { + gcc_assert(read(urandom_fd, rnd_buf, sizeof(rnd_buf)) == sizeof(rnd_buf)); + rnd_idx = 0; + } + return rnd_buf[rnd_idx++]; } static tree tree_get_random_const(tree type) @@ -537,8 +543,6 @@ static void latent_entropy_start_unit(void *gcc_data __unused, tree type, id; int quals; - seed = get_random_seed(false); - if (in_lto_p) return; @@ -573,6 +577,12 @@ __visible int plugin_init(struct plugin_name_args *plugin_info, const struct plugin_argument * const argv = plugin_info->argv; int i; + /* + * Call get_random_seed() with noinit=true, so that this returns + * 0 in the case where no seed has been passed via -frandom-seed. + */ + deterministic_seed = get_random_seed(true); + static const struct ggc_root_tab gt_ggc_r_gt_latent_entropy[] = { { .base = &latent_entropy_decl, diff --git a/scripts/gcc-plugins/randomize_layout_plugin.c b/scripts/gcc-plugins/randomize_layout_plugin.c index 334741a31d0a..ea2aea570404 100644 --- a/scripts/gcc-plugins/randomize_layout_plugin.c +++ b/scripts/gcc-plugins/randomize_layout_plugin.c @@ -34,29 +34,11 @@ __visible int plugin_is_GPL_compatible; static int performance_mode; static struct plugin_info randomize_layout_plugin_info = { - .version = "201402201816vanilla", + .version = UTS_RELEASE, .help = "disable\t\t\tdo not activate plugin\n" "performance-mode\tenable cacheline-aware layout randomization\n" }; -struct whitelist_entry { - const char *pathname; - const char *lhs; - const char *rhs; -}; - -static const struct whitelist_entry whitelist[] = { - /* NIU overloads mapping with page struct */ - { "drivers/net/ethernet/sun/niu.c", "page", "address_space" }, - /* unix_skb_parms via UNIXCB() buffer */ - { "net/unix/af_unix.c", "unix_skb_parms", "char" }, - /* big_key payload.data struct splashing */ - { "security/keys/big_key.c", "path", "void *" }, - /* walk struct security_hook_heads as an array of struct hlist_head */ - { "security/security.c", "hlist_head", "security_hook_heads" }, - { } -}; - /* from old Linux dcache.h */ static inline unsigned long partial_name_hash(unsigned long c, unsigned long prevhash) @@ -742,60 +724,6 @@ static void handle_local_var_initializers(void) } } -static bool type_name_eq(gimple stmt, const_tree type_tree, const char *wanted_name) -{ - const char *type_name; - - if (type_tree == NULL_TREE) - return false; - - switch (TREE_CODE(type_tree)) { - case RECORD_TYPE: - type_name = TYPE_NAME_POINTER(type_tree); - break; - case INTEGER_TYPE: - if (TYPE_PRECISION(type_tree) == CHAR_TYPE_SIZE) - type_name = "char"; - else { - INFORM(gimple_location(stmt), "found non-char INTEGER_TYPE cast comparison: %qT\n", type_tree); - debug_tree(type_tree); - return false; - } - break; - case POINTER_TYPE: - if (TREE_CODE(TREE_TYPE(type_tree)) == VOID_TYPE) { - type_name = "void *"; - break; - } else { - INFORM(gimple_location(stmt), "found non-void POINTER_TYPE cast comparison %qT\n", type_tree); - debug_tree(type_tree); - return false; - } - default: - INFORM(gimple_location(stmt), "unhandled cast comparison: %qT\n", type_tree); - debug_tree(type_tree); - return false; - } - - return strcmp(type_name, wanted_name) == 0; -} - -static bool whitelisted_cast(gimple stmt, const_tree lhs_tree, const_tree rhs_tree) -{ - const struct whitelist_entry *entry; - expanded_location xloc = expand_location(gimple_location(stmt)); - - for (entry = whitelist; entry->pathname; entry++) { - if (!strstr(xloc.file, entry->pathname)) - continue; - - if (type_name_eq(stmt, lhs_tree, entry->lhs) && type_name_eq(stmt, rhs_tree, entry->rhs)) - return true; - } - - return false; -} - /* * iterate over all statements to find "bad" casts: * those where the address of the start of a structure is cast @@ -872,10 +800,7 @@ static unsigned int find_bad_casts_execute(void) #ifndef __DEBUG_PLUGIN if (lookup_attribute("randomize_performed", TYPE_ATTRIBUTES(ptr_lhs_type))) #endif - { - if (!whitelisted_cast(stmt, ptr_lhs_type, ptr_rhs_type)) - MISMATCH(gimple_location(stmt), "rhs", ptr_lhs_type, ptr_rhs_type); - } + MISMATCH(gimple_location(stmt), "rhs", ptr_lhs_type, ptr_rhs_type); continue; } @@ -898,10 +823,7 @@ static unsigned int find_bad_casts_execute(void) #ifndef __DEBUG_PLUGIN if (lookup_attribute("randomize_performed", TYPE_ATTRIBUTES(op0_type))) #endif - { - if (!whitelisted_cast(stmt, ptr_lhs_type, op0_type)) - MISMATCH(gimple_location(stmt), "op0", ptr_lhs_type, op0_type); - } + MISMATCH(gimple_location(stmt), "op0", ptr_lhs_type, op0_type); } else { const_tree ssa_name_var = SSA_NAME_VAR(rhs1); /* skip bogus type casts introduced by container_of */ @@ -911,10 +833,7 @@ static unsigned int find_bad_casts_execute(void) #ifndef __DEBUG_PLUGIN if (lookup_attribute("randomize_performed", TYPE_ATTRIBUTES(ptr_rhs_type))) #endif - { - if (!whitelisted_cast(stmt, ptr_lhs_type, ptr_rhs_type)) - MISMATCH(gimple_location(stmt), "ssa", ptr_lhs_type, ptr_rhs_type); - } + MISMATCH(gimple_location(stmt), "ssa", ptr_lhs_type, ptr_rhs_type); } } diff --git a/scripts/gcc-plugins/sancov_plugin.c b/scripts/gcc-plugins/sancov_plugin.c index 23bd023a283b..f3d629555b84 100644 --- a/scripts/gcc-plugins/sancov_plugin.c +++ b/scripts/gcc-plugins/sancov_plugin.c @@ -26,7 +26,7 @@ __visible int plugin_is_GPL_compatible; tree sancov_fndecl; static struct plugin_info sancov_plugin_info = { - .version = "20160402", + .version = UTS_RELEASE, .help = "sancov plugin\n", }; diff --git a/scripts/gcc-plugins/stackleak_plugin.c b/scripts/gcc-plugins/stackleak_plugin.c index 42f0252ee2a4..de817d54b8af 100644 --- a/scripts/gcc-plugins/stackleak_plugin.c +++ b/scripts/gcc-plugins/stackleak_plugin.c @@ -44,7 +44,7 @@ static bool verbose = false; static GTY(()) tree track_function_decl; static struct plugin_info stackleak_plugin_info = { - .version = "201707101337", + .version = UTS_RELEASE, .help = "track-min-size=nn\ttrack stack for functions with a stack frame size >= nn bytes\n" "arch=target_arch\tspecify target build arch\n" "disable\t\tdo not activate the plugin\n" diff --git a/scripts/gcc-plugins/structleak_plugin.c b/scripts/gcc-plugins/structleak_plugin.c index 74e319288389..86b608a24ec0 100644 --- a/scripts/gcc-plugins/structleak_plugin.c +++ b/scripts/gcc-plugins/structleak_plugin.c @@ -37,7 +37,7 @@ __visible int plugin_is_GPL_compatible; static struct plugin_info structleak_plugin_info = { - .version = "20190125vanilla", + .version = UTS_RELEASE, .help = "disable\tdo not activate plugin\n" "byref\tinit structs passed by reference\n" "byref-all\tinit anything passed by reference\n" diff --git a/scripts/gen-randstruct-seed.sh b/scripts/gen-randstruct-seed.sh new file mode 100755 index 000000000000..61017b36c464 --- /dev/null +++ b/scripts/gen-randstruct-seed.sh @@ -0,0 +1,7 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 + +SEED=$(od -A n -t x8 -N 32 /dev/urandom | tr -d ' \n') +echo "$SEED" > "$1" +HASH=$(echo -n "$SEED" | sha256sum | cut -d" " -f1) +echo "#define RANDSTRUCT_HASHED_SEED \"$HASH\"" > "$2" diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh index 20f44504a644..d7f26f02f142 100755 --- a/scripts/link-vmlinux.sh +++ b/scripts/link-vmlinux.sh @@ -108,16 +108,22 @@ objtool_link() local objtoolcmd; local objtoolopt; - if is_enabled CONFIG_STACK_VALIDATION && \ - ( is_enabled CONFIG_LTO_CLANG || is_enabled CONFIG_X86_KERNEL_IBT ); then + if ! is_enabled CONFIG_OBJTOOL; then + return; + fi - # Don't perform vmlinux validation unless explicitly requested, - # but run objtool on vmlinux.o now that we have an object file. - if is_enabled CONFIG_UNWINDER_ORC; then - objtoolcmd="orc generate" + if is_enabled CONFIG_LTO_CLANG || is_enabled CONFIG_X86_KERNEL_IBT; then + + # For LTO and IBT, objtool doesn't run on individual + # translation units. Run everything on vmlinux instead. + + if is_enabled CONFIG_HAVE_JUMP_LABEL_HACK; then + objtoolopt="${objtoolopt} --hacks=jump_label" fi - objtoolopt="${objtoolopt} --lto" + if is_enabled CONFIG_HAVE_NOINSTR_HACK; then + objtoolopt="${objtoolopt} --hacks=noinstr" + fi if is_enabled CONFIG_X86_KERNEL_IBT; then objtoolopt="${objtoolopt} --ibt" @@ -126,34 +132,44 @@ objtool_link() if is_enabled CONFIG_FTRACE_MCOUNT_USE_OBJTOOL; then objtoolopt="${objtoolopt} --mcount" fi - fi - if is_enabled CONFIG_VMLINUX_VALIDATION; then - objtoolopt="${objtoolopt} --noinstr" - fi - - if [ -n "${objtoolopt}" ]; then - if [ -z "${objtoolcmd}" ]; then - objtoolcmd="check" - fi - objtoolopt="${objtoolopt} --vmlinux" - if ! is_enabled CONFIG_FRAME_POINTER; then - objtoolopt="${objtoolopt} --no-fp" - fi - if is_enabled CONFIG_GCOV_KERNEL || is_enabled CONFIG_LTO_CLANG; then - objtoolopt="${objtoolopt} --no-unreachable" + if is_enabled CONFIG_UNWINDER_ORC; then + objtoolopt="${objtoolopt} --orc" fi + if is_enabled CONFIG_RETPOLINE; then objtoolopt="${objtoolopt} --retpoline" fi - if is_enabled CONFIG_X86_SMAP; then - objtoolopt="${objtoolopt} --uaccess" - fi + if is_enabled CONFIG_SLS; then objtoolopt="${objtoolopt} --sls" fi + + if is_enabled CONFIG_STACK_VALIDATION; then + objtoolopt="${objtoolopt} --stackval" + fi + + if is_enabled CONFIG_HAVE_STATIC_CALL_INLINE; then + objtoolopt="${objtoolopt} --static-call" + fi + + objtoolopt="${objtoolopt} --uaccess" + fi + + if is_enabled CONFIG_NOINSTR_VALIDATION; then + objtoolopt="${objtoolopt} --noinstr" + fi + + if [ -n "${objtoolopt}" ]; then + + if is_enabled CONFIG_GCOV_KERNEL; then + objtoolopt="${objtoolopt} --no-unreachable" + fi + + objtoolopt="${objtoolopt} --link" + info OBJTOOL ${1} - tools/objtool/objtool ${objtoolcmd} ${objtoolopt} ${1} + tools/objtool/objtool ${objtoolopt} ${1} fi } diff --git a/scripts/min-tool-version.sh b/scripts/min-tool-version.sh index 7c20252a90c6..250925aab101 100755 --- a/scripts/min-tool-version.sh +++ b/scripts/min-tool-version.sh @@ -24,9 +24,8 @@ icc) echo 16.0.3 ;; llvm) - # https://lore.kernel.org/r/YMtib5hKVyNknZt3@osiris/ if [ "$SRCARCH" = s390 ]; then - echo 13.0.0 + echo 14.0.0 else echo 11.0.0 fi diff --git a/scripts/objdump-func b/scripts/objdump-func new file mode 100755 index 000000000000..4eb463dd9f52 --- /dev/null +++ b/scripts/objdump-func @@ -0,0 +1,29 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Disassemble a single function. +# +# usage: objdump-func <file> <func> + +set -o errexit +set -o nounset + +OBJDUMP="${CROSS_COMPILE:-}objdump" + +command -v gawk >/dev/null 2>&1 || die "gawk isn't installed" + +usage() { + echo "usage: objdump-func <file> <func>" >&2 + exit 1 +} + +[[ $# -lt 2 ]] && usage + +OBJ=$1; shift +FUNC=$1; shift + +# Secret feature to allow adding extra objdump args at the end +EXTRA_ARGS=$@ + +# Note this also matches compiler-added suffixes like ".cold", etc +${OBJDUMP} -wdr $EXTRA_ARGS $OBJ | gawk -M -v f=$FUNC '/^$/ { P=0; } $0 ~ "<" f "(\\..*)?>:" { P=1; O=strtonum("0x" $1); } { if (P) { o=strtonum("0x" $1); printf("%04x ", o-O); print $0; } }' diff --git a/scripts/package/builddeb b/scripts/package/builddeb index 91a502bb97e8..67cd420dcf89 100755 --- a/scripts/package/builddeb +++ b/scripts/package/builddeb @@ -67,7 +67,7 @@ deploy_kernel_headers () { ) > debian/hdrsrcfiles { - if is_enabled CONFIG_STACK_VALIDATION; then + if is_enabled CONFIG_OBJTOOL; then echo tools/objtool/objtool fi diff --git a/scripts/selinux/genheaders/genheaders.c b/scripts/selinux/genheaders/genheaders.c index f355b3e0e968..15520806889e 100644 --- a/scripts/selinux/genheaders/genheaders.c +++ b/scripts/selinux/genheaders/genheaders.c @@ -59,35 +59,27 @@ int main(int argc, char *argv[]) exit(2); } - for (i = 0; secclass_map[i].name; i++) { - struct security_class_mapping *map = &secclass_map[i]; - map->name = stoupperx(map->name); - for (j = 0; map->perms[j]; j++) - map->perms[j] = stoupperx(map->perms[j]); - } - - isids_len = sizeof(initial_sid_to_string) / sizeof (char *); - for (i = 1; i < isids_len; i++) { - const char *s = initial_sid_to_string[i]; - - if (s) - initial_sid_to_string[i] = stoupperx(s); - } - fprintf(fout, "/* This file is automatically generated. Do not edit. */\n"); fprintf(fout, "#ifndef _SELINUX_FLASK_H_\n#define _SELINUX_FLASK_H_\n\n"); for (i = 0; secclass_map[i].name; i++) { - struct security_class_mapping *map = &secclass_map[i]; - fprintf(fout, "#define SECCLASS_%-39s %2d\n", map->name, i+1); + char *name = stoupperx(secclass_map[i].name); + + fprintf(fout, "#define SECCLASS_%-39s %2d\n", name, i+1); + free(name); } fprintf(fout, "\n"); + isids_len = sizeof(initial_sid_to_string) / sizeof(char *); for (i = 1; i < isids_len; i++) { const char *s = initial_sid_to_string[i]; - if (s) - fprintf(fout, "#define SECINITSID_%-39s %2d\n", s, i); + if (s) { + char *sidname = stoupperx(s); + + fprintf(fout, "#define SECINITSID_%-39s %2d\n", sidname, i); + free(sidname); + } } fprintf(fout, "\n#define SECINITSID_NUM %d\n", i-1); fprintf(fout, "\nstatic inline bool security_is_socket_class(u16 kern_tclass)\n"); @@ -96,10 +88,14 @@ int main(int argc, char *argv[]) fprintf(fout, "\tswitch (kern_tclass) {\n"); for (i = 0; secclass_map[i].name; i++) { static char s[] = "SOCKET"; - struct security_class_mapping *map = &secclass_map[i]; - int len = strlen(map->name), l = sizeof(s) - 1; - if (len >= l && memcmp(map->name + len - l, s, l) == 0) - fprintf(fout, "\tcase SECCLASS_%s:\n", map->name); + int len, l; + char *name = stoupperx(secclass_map[i].name); + + len = strlen(name); + l = sizeof(s) - 1; + if (len >= l && memcmp(name + len - l, s, l) == 0) + fprintf(fout, "\tcase SECCLASS_%s:\n", name); + free(name); } fprintf(fout, "\t\tsock = true;\n"); fprintf(fout, "\t\tbreak;\n"); @@ -110,33 +106,52 @@ int main(int argc, char *argv[]) fprintf(fout, "}\n"); fprintf(fout, "\n#endif\n"); - fclose(fout); + + if (fclose(fout) != 0) { + fprintf(stderr, "Could not successfully close %s: %s\n", + argv[1], strerror(errno)); + exit(4); + } fout = fopen(argv[2], "w"); if (!fout) { fprintf(stderr, "Could not open %s for writing: %s\n", argv[2], strerror(errno)); - exit(4); + exit(5); } fprintf(fout, "/* This file is automatically generated. Do not edit. */\n"); fprintf(fout, "#ifndef _SELINUX_AV_PERMISSIONS_H_\n#define _SELINUX_AV_PERMISSIONS_H_\n\n"); for (i = 0; secclass_map[i].name; i++) { - struct security_class_mapping *map = &secclass_map[i]; - int len = strlen(map->name); + const struct security_class_mapping *map = &secclass_map[i]; + int len; + char *name = stoupperx(map->name); + + len = strlen(name); for (j = 0; map->perms[j]; j++) { + char *permname; + if (j >= 32) { fprintf(stderr, "Too many permissions to fit into an access vector at (%s, %s).\n", map->name, map->perms[j]); exit(5); } - fprintf(fout, "#define %s__%-*s 0x%08xU\n", map->name, - 39-len, map->perms[j], 1U<<j); + permname = stoupperx(map->perms[j]); + fprintf(fout, "#define %s__%-*s 0x%08xU\n", name, + 39-len, permname, 1U<<j); + free(permname); } + free(name); } fprintf(fout, "\n#endif\n"); - fclose(fout); + + if (fclose(fout) != 0) { + fprintf(stderr, "Could not successfully close %s: %s\n", + argv[2], strerror(errno)); + exit(6); + } + exit(0); } diff --git a/scripts/selinux/mdp/mdp.c b/scripts/selinux/mdp/mdp.c index 105c1c31a316..1415604c3d24 100644 --- a/scripts/selinux/mdp/mdp.c +++ b/scripts/selinux/mdp/mdp.c @@ -82,7 +82,7 @@ int main(int argc, char *argv[]) /* print out the class permissions */ for (i = 0; secclass_map[i].name; i++) { - struct security_class_mapping *map = &secclass_map[i]; + const struct security_class_mapping *map = &secclass_map[i]; fprintf(fout, "class %s\n", map->name); fprintf(fout, "{\n"); for (j = 0; map->perms[j]; j++) @@ -103,7 +103,7 @@ int main(int argc, char *argv[]) #define SYSTEMLOW "s0" #define SYSTEMHIGH "s1:c0.c1" for (i = 0; secclass_map[i].name; i++) { - struct security_class_mapping *map = &secclass_map[i]; + const struct security_class_mapping *map = &secclass_map[i]; fprintf(fout, "mlsconstrain %s {\n", map->name); for (j = 0; map->perms[j]; j++) diff --git a/security/Kconfig b/security/Kconfig index 9b2c4925585a..f29e4c656983 100644 --- a/security/Kconfig +++ b/security/Kconfig @@ -160,20 +160,9 @@ config HARDENED_USERCOPY copy_from_user() functions) by rejecting memory ranges that are larger than the specified heap object, span multiple separately allocated pages, are not on the process stack, - or are part of the kernel text. This kills entire classes + or are part of the kernel text. This prevents entire classes of heap overflow exploits and similar kernel memory exposures. -config HARDENED_USERCOPY_PAGESPAN - bool "Refuse to copy allocations that span multiple pages" - depends on HARDENED_USERCOPY - depends on BROKEN - help - When a multi-page allocation is done without __GFP_COMP, - hardened usercopy will reject attempts to copy it. There are, - however, several cases of this in the kernel that have not all - been removed. This config is intended to be used only while - trying to find such users. - config FORTIFY_SOURCE bool "Harden common str/mem functions against buffer overflows" depends on ARCH_HAS_FORTIFY_SOURCE diff --git a/security/Kconfig.hardening b/security/Kconfig.hardening index ded4d7c0d132..bd2aabb2c60f 100644 --- a/security/Kconfig.hardening +++ b/security/Kconfig.hardening @@ -266,4 +266,77 @@ config ZERO_CALL_USED_REGS endmenu +config CC_HAS_RANDSTRUCT + def_bool $(cc-option,-frandomize-layout-seed-file=/dev/null) + +choice + prompt "Randomize layout of sensitive kernel structures" + default RANDSTRUCT_FULL if COMPILE_TEST && (GCC_PLUGINS || CC_HAS_RANDSTRUCT) + default RANDSTRUCT_NONE + help + If you enable this, the layouts of structures that are entirely + function pointers (and have not been manually annotated with + __no_randomize_layout), or structures that have been explicitly + marked with __randomize_layout, will be randomized at compile-time. + This can introduce the requirement of an additional information + exposure vulnerability for exploits targeting these structure + types. + + Enabling this feature will introduce some performance impact, + slightly increase memory usage, and prevent the use of forensic + tools like Volatility against the system (unless the kernel + source tree isn't cleaned after kernel installation). + + The seed used for compilation is in scripts/basic/randomize.seed. + It remains after a "make clean" to allow for external modules to + be compiled with the existing seed and will be removed by a + "make mrproper" or "make distclean". This file should not be made + public, or the structure layout can be determined. + + config RANDSTRUCT_NONE + bool "Disable structure layout randomization" + help + Build normally: no structure layout randomization. + + config RANDSTRUCT_FULL + bool "Fully randomize structure layout" + depends on CC_HAS_RANDSTRUCT || GCC_PLUGINS + select MODVERSIONS if MODULES + help + Fully randomize the member layout of sensitive + structures as much as possible, which may have both a + memory size and performance impact. + + One difference between the Clang and GCC plugin + implementations is the handling of bitfields. The GCC + plugin treats them as fully separate variables, + introducing sometimes significant padding. Clang tries + to keep adjacent bitfields together, but with their bit + ordering randomized. + + config RANDSTRUCT_PERFORMANCE + bool "Limit randomization of structure layout to cache-lines" + depends on GCC_PLUGINS + select MODVERSIONS if MODULES + help + Randomization of sensitive kernel structures will make a + best effort at restricting randomization to cacheline-sized + groups of members. It will further not randomize bitfields + in structures. This reduces the performance hit of RANDSTRUCT + at the cost of weakened randomization. +endchoice + +config RANDSTRUCT + def_bool !RANDSTRUCT_NONE + +config GCC_PLUGIN_RANDSTRUCT + def_bool GCC_PLUGINS && RANDSTRUCT + help + Use GCC plugin to randomize structure layout. + + This plugin was ported from grsecurity/PaX. More + information at: + * https://grsecurity.net/ + * https://pax.grsecurity.net/ + endmenu diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c index 4f0eecb67dde..900bc540656a 100644 --- a/security/apparmor/lsm.c +++ b/security/apparmor/lsm.c @@ -354,13 +354,16 @@ static int apparmor_path_link(struct dentry *old_dentry, const struct path *new_ } static int apparmor_path_rename(const struct path *old_dir, struct dentry *old_dentry, - const struct path *new_dir, struct dentry *new_dentry) + const struct path *new_dir, struct dentry *new_dentry, + const unsigned int flags) { struct aa_label *label; int error = 0; if (!path_mediated_fs(old_dentry)) return 0; + if ((flags & RENAME_EXCHANGE) && !path_mediated_fs(new_dentry)) + return 0; label = begin_current_label_crit_section(); if (!unconfined(label)) { @@ -374,10 +377,27 @@ static int apparmor_path_rename(const struct path *old_dir, struct dentry *old_d d_backing_inode(old_dentry)->i_mode }; - error = aa_path_perm(OP_RENAME_SRC, label, &old_path, 0, - MAY_READ | AA_MAY_GETATTR | MAY_WRITE | - AA_MAY_SETATTR | AA_MAY_DELETE, - &cond); + if (flags & RENAME_EXCHANGE) { + struct path_cond cond_exchange = { + i_uid_into_mnt(mnt_userns, d_backing_inode(new_dentry)), + d_backing_inode(new_dentry)->i_mode + }; + + error = aa_path_perm(OP_RENAME_SRC, label, &new_path, 0, + MAY_READ | AA_MAY_GETATTR | MAY_WRITE | + AA_MAY_SETATTR | AA_MAY_DELETE, + &cond_exchange); + if (!error) + error = aa_path_perm(OP_RENAME_DEST, label, &old_path, + 0, MAY_WRITE | AA_MAY_SETATTR | + AA_MAY_CREATE, &cond_exchange); + } + + if (!error) + error = aa_path_perm(OP_RENAME_SRC, label, &old_path, 0, + MAY_READ | AA_MAY_GETATTR | MAY_WRITE | + AA_MAY_SETATTR | AA_MAY_DELETE, + &cond); if (!error) error = aa_path_perm(OP_RENAME_DEST, label, &new_path, 0, MAY_WRITE | AA_MAY_SETATTR | diff --git a/security/integrity/digsig.c b/security/integrity/digsig.c index c8c8a4a4e7a0..8a82a6c7f48a 100644 --- a/security/integrity/digsig.c +++ b/security/integrity/digsig.c @@ -75,7 +75,8 @@ int integrity_digsig_verify(const unsigned int id, const char *sig, int siglen, /* v1 API expect signature without xattr type */ return digsig_verify(keyring, sig + 1, siglen - 1, digest, digestlen); - case 2: + case 2: /* regular file data hash based signature */ + case 3: /* struct ima_file_id data based signature */ return asymmetric_verify(keyring, sig, siglen, digest, digestlen); } diff --git a/security/integrity/evm/evm.h b/security/integrity/evm/evm.h index 0d44f41d16f8..f8b8c5004fc7 100644 --- a/security/integrity/evm/evm.h +++ b/security/integrity/evm/evm.h @@ -38,9 +38,6 @@ extern int evm_initialized; extern int evm_hmac_attrs; -extern struct crypto_shash *hmac_tfm; -extern struct crypto_shash *hash_tfm; - /* List of EVM protected security xattrs */ extern struct list_head evm_config_xattrnames; diff --git a/security/integrity/evm/evm_crypto.c b/security/integrity/evm/evm_crypto.c index 0450d79afdc8..a733aff02006 100644 --- a/security/integrity/evm/evm_crypto.c +++ b/security/integrity/evm/evm_crypto.c @@ -26,7 +26,7 @@ static unsigned char evmkey[MAX_KEY_SIZE]; static const int evmkey_len = MAX_KEY_SIZE; -struct crypto_shash *hmac_tfm; +static struct crypto_shash *hmac_tfm; static struct crypto_shash *evm_tfm[HASH_ALGO__LAST]; static DEFINE_MUTEX(mutex); diff --git a/security/integrity/evm/evm_main.c b/security/integrity/evm/evm_main.c index 7d87772f0ce6..cc88f02c7562 100644 --- a/security/integrity/evm/evm_main.c +++ b/security/integrity/evm/evm_main.c @@ -436,7 +436,7 @@ static enum integrity_status evm_verify_current_integrity(struct dentry *dentry) struct inode *inode = d_backing_inode(dentry); if (!evm_key_loaded() || !S_ISREG(inode->i_mode) || evm_fixmode) - return 0; + return INTEGRITY_PASS; return evm_verify_hmac(dentry, NULL, NULL, 0, NULL); } diff --git a/security/integrity/ima/Kconfig b/security/integrity/ima/Kconfig index f3a9cc201c8c..7249f16257c7 100644 --- a/security/integrity/ima/Kconfig +++ b/security/integrity/ima/Kconfig @@ -69,10 +69,9 @@ choice hash, defined as 20 bytes, and a null terminated pathname, limited to 255 characters. The 'ima-ng' measurement list template permits both larger hash digests and longer - pathnames. + pathnames. The configured default template can be replaced + by specifying "ima_template=" on the boot command line. - config IMA_TEMPLATE - bool "ima" config IMA_NG_TEMPLATE bool "ima-ng (default)" config IMA_SIG_TEMPLATE @@ -82,7 +81,6 @@ endchoice config IMA_DEFAULT_TEMPLATE string depends on IMA - default "ima" if IMA_TEMPLATE default "ima-ng" if IMA_NG_TEMPLATE default "ima-sig" if IMA_SIG_TEMPLATE @@ -102,19 +100,19 @@ choice config IMA_DEFAULT_HASH_SHA256 bool "SHA256" - depends on CRYPTO_SHA256=y && !IMA_TEMPLATE + depends on CRYPTO_SHA256=y config IMA_DEFAULT_HASH_SHA512 bool "SHA512" - depends on CRYPTO_SHA512=y && !IMA_TEMPLATE + depends on CRYPTO_SHA512=y config IMA_DEFAULT_HASH_WP512 bool "WP512" - depends on CRYPTO_WP512=y && !IMA_TEMPLATE + depends on CRYPTO_WP512=y config IMA_DEFAULT_HASH_SM3 bool "SM3" - depends on CRYPTO_SM3=y && !IMA_TEMPLATE + depends on CRYPTO_SM3=y endchoice config IMA_DEFAULT_HASH diff --git a/security/integrity/ima/ima_api.c b/security/integrity/ima/ima_api.c index c6805af46211..c1e76282b5ee 100644 --- a/security/integrity/ima/ima_api.c +++ b/security/integrity/ima/ima_api.c @@ -14,6 +14,7 @@ #include <linux/xattr.h> #include <linux/evm.h> #include <linux/iversion.h> +#include <linux/fsverity.h> #include "ima.h" @@ -200,6 +201,32 @@ int ima_get_action(struct user_namespace *mnt_userns, struct inode *inode, allowed_algos); } +static int ima_get_verity_digest(struct integrity_iint_cache *iint, + struct ima_max_digest_data *hash) +{ + enum hash_algo verity_alg; + int ret; + + /* + * On failure, 'measure' policy rules will result in a file data + * hash containing 0's. + */ + ret = fsverity_get_digest(iint->inode, hash->digest, &verity_alg); + if (ret) + return ret; + + /* + * Unlike in the case of actually calculating the file hash, in + * the fsverity case regardless of the hash algorithm, return + * the verity digest to be included in the measurement list. A + * mismatch between the verity algorithm and the xattr signature + * algorithm, if one exists, will be detected later. + */ + hash->hdr.algo = verity_alg; + hash->hdr.length = hash_digest_size[verity_alg]; + return 0; +} + /* * ima_collect_measurement - collect file measurement * @@ -242,16 +269,30 @@ int ima_collect_measurement(struct integrity_iint_cache *iint, */ i_version = inode_query_iversion(inode); hash.hdr.algo = algo; + hash.hdr.length = hash_digest_size[algo]; /* Initialize hash digest to 0's in case of failure */ memset(&hash.digest, 0, sizeof(hash.digest)); - if (buf) + if (iint->flags & IMA_VERITY_REQUIRED) { + result = ima_get_verity_digest(iint, &hash); + switch (result) { + case 0: + break; + case -ENODATA: + audit_cause = "no-verity-digest"; + break; + default: + audit_cause = "invalid-verity-digest"; + break; + } + } else if (buf) { result = ima_calc_buffer_hash(buf, size, &hash.hdr); - else + } else { result = ima_calc_file_hash(file, &hash.hdr); + } - if (result && result != -EBADF && result != -EINVAL) + if (result == -ENOMEM) goto out; length = sizeof(hash.hdr) + hash.hdr.length; diff --git a/security/integrity/ima/ima_appraise.c b/security/integrity/ima/ima_appraise.c index 17232bbfb9f9..cdb84dccd24e 100644 --- a/security/integrity/ima/ima_appraise.c +++ b/security/integrity/ima/ima_appraise.c @@ -13,7 +13,9 @@ #include <linux/magic.h> #include <linux/ima.h> #include <linux/evm.h> +#include <linux/fsverity.h> #include <keys/system_keyring.h> +#include <uapi/linux/fsverity.h> #include "ima.h" @@ -183,13 +185,18 @@ enum hash_algo ima_get_hash_algo(const struct evm_ima_xattr_data *xattr_value, return ima_hash_algo; switch (xattr_value->type) { + case IMA_VERITY_DIGSIG: + sig = (typeof(sig))xattr_value; + if (sig->version != 3 || xattr_len <= sizeof(*sig) || + sig->hash_algo >= HASH_ALGO__LAST) + return ima_hash_algo; + return sig->hash_algo; case EVM_IMA_XATTR_DIGSIG: sig = (typeof(sig))xattr_value; if (sig->version != 2 || xattr_len <= sizeof(*sig) || sig->hash_algo >= HASH_ALGO__LAST) return ima_hash_algo; return sig->hash_algo; - break; case IMA_XATTR_DIGEST_NG: /* first byte contains algorithm id */ ret = xattr_value->data[0]; @@ -226,6 +233,40 @@ int ima_read_xattr(struct dentry *dentry, } /* + * calc_file_id_hash - calculate the hash of the ima_file_id struct data + * @type: xattr type [enum evm_ima_xattr_type] + * @algo: hash algorithm [enum hash_algo] + * @digest: pointer to the digest to be hashed + * @hash: (out) pointer to the hash + * + * IMA signature version 3 disambiguates the data that is signed by + * indirectly signing the hash of the ima_file_id structure data. + * + * Signing the ima_file_id struct is currently only supported for + * IMA_VERITY_DIGSIG type xattrs. + * + * Return 0 on success, error code otherwise. + */ +static int calc_file_id_hash(enum evm_ima_xattr_type type, + enum hash_algo algo, const u8 *digest, + struct ima_digest_data *hash) +{ + struct ima_file_id file_id = { + .hash_type = IMA_VERITY_DIGSIG, .hash_algorithm = algo}; + unsigned int unused = HASH_MAX_DIGESTSIZE - hash_digest_size[algo]; + + if (type != IMA_VERITY_DIGSIG) + return -EINVAL; + + memcpy(file_id.hash, digest, hash_digest_size[algo]); + + hash->algo = algo; + hash->length = hash_digest_size[algo]; + + return ima_calc_buffer_hash(&file_id, sizeof(file_id) - unused, hash); +} + +/* * xattr_verify - verify xattr digest or signature * * Verify whether the hash or signature matches the file contents. @@ -236,7 +277,10 @@ static int xattr_verify(enum ima_hooks func, struct integrity_iint_cache *iint, struct evm_ima_xattr_data *xattr_value, int xattr_len, enum integrity_status *status, const char **cause) { + struct ima_max_digest_data hash; + struct signature_v2_hdr *sig; int rc = -EINVAL, hash_start = 0; + int mask; switch (xattr_value->type) { case IMA_XATTR_DIGEST_NG: @@ -246,7 +290,10 @@ static int xattr_verify(enum ima_hooks func, struct integrity_iint_cache *iint, case IMA_XATTR_DIGEST: if (*status != INTEGRITY_PASS_IMMUTABLE) { if (iint->flags & IMA_DIGSIG_REQUIRED) { - *cause = "IMA-signature-required"; + if (iint->flags & IMA_VERITY_REQUIRED) + *cause = "verity-signature-required"; + else + *cause = "IMA-signature-required"; *status = INTEGRITY_FAIL; break; } @@ -274,6 +321,20 @@ static int xattr_verify(enum ima_hooks func, struct integrity_iint_cache *iint, break; case EVM_IMA_XATTR_DIGSIG: set_bit(IMA_DIGSIG, &iint->atomic_flags); + + mask = IMA_DIGSIG_REQUIRED | IMA_VERITY_REQUIRED; + if ((iint->flags & mask) == mask) { + *cause = "verity-signature-required"; + *status = INTEGRITY_FAIL; + break; + } + + sig = (typeof(sig))xattr_value; + if (sig->version >= 3) { + *cause = "invalid-signature-version"; + *status = INTEGRITY_FAIL; + break; + } rc = integrity_digsig_verify(INTEGRITY_KEYRING_IMA, (const char *)xattr_value, xattr_len, @@ -297,6 +358,44 @@ static int xattr_verify(enum ima_hooks func, struct integrity_iint_cache *iint, *status = INTEGRITY_PASS; } break; + case IMA_VERITY_DIGSIG: + set_bit(IMA_DIGSIG, &iint->atomic_flags); + + if (iint->flags & IMA_DIGSIG_REQUIRED) { + if (!(iint->flags & IMA_VERITY_REQUIRED)) { + *cause = "IMA-signature-required"; + *status = INTEGRITY_FAIL; + break; + } + } + + sig = (typeof(sig))xattr_value; + if (sig->version != 3) { + *cause = "invalid-signature-version"; + *status = INTEGRITY_FAIL; + break; + } + + rc = calc_file_id_hash(IMA_VERITY_DIGSIG, iint->ima_hash->algo, + iint->ima_hash->digest, &hash.hdr); + if (rc) { + *cause = "sigv3-hashing-error"; + *status = INTEGRITY_FAIL; + break; + } + + rc = integrity_digsig_verify(INTEGRITY_KEYRING_IMA, + (const char *)xattr_value, + xattr_len, hash.digest, + hash.hdr.length); + if (rc) { + *cause = "invalid-verity-signature"; + *status = INTEGRITY_FAIL; + } else { + *status = INTEGRITY_PASS; + } + + break; default: *status = INTEGRITY_UNKNOWN; *cause = "unknown-ima-data"; @@ -396,8 +495,15 @@ int ima_appraise_measurement(enum ima_hooks func, if (rc && rc != -ENODATA) goto out; - cause = iint->flags & IMA_DIGSIG_REQUIRED ? - "IMA-signature-required" : "missing-hash"; + if (iint->flags & IMA_DIGSIG_REQUIRED) { + if (iint->flags & IMA_VERITY_REQUIRED) + cause = "verity-signature-required"; + else + cause = "IMA-signature-required"; + } else { + cause = "missing-hash"; + } + status = INTEGRITY_NOLABEL; if (file->f_mode & FMODE_CREATED) iint->flags |= IMA_NEW_FILE; diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c index 3d3f8c5c502b..040b03ddc1c7 100644 --- a/security/integrity/ima/ima_main.c +++ b/security/integrity/ima/ima_main.c @@ -335,7 +335,7 @@ static int process_measurement(struct file *file, const struct cred *cred, hash_algo = ima_get_hash_algo(xattr_value, xattr_len); rc = ima_collect_measurement(iint, file, buf, size, hash_algo, modsig); - if (rc != 0 && rc != -EBADF && rc != -EINVAL) + if (rc == -ENOMEM) goto out_locked; if (!pathbuf) /* ima_rdwr_violation possibly pre-fetched */ @@ -432,7 +432,7 @@ int ima_file_mmap(struct file *file, unsigned long prot) int ima_file_mprotect(struct vm_area_struct *vma, unsigned long prot) { struct ima_template_desc *template = NULL; - struct file *file = vma->vm_file; + struct file *file; char filename[NAME_MAX]; char *pathbuf = NULL; const char *pathname = NULL; diff --git a/security/integrity/ima/ima_policy.c b/security/integrity/ima/ima_policy.c index eea6e92500b8..73917413365b 100644 --- a/security/integrity/ima/ima_policy.c +++ b/security/integrity/ima/ima_policy.c @@ -1023,6 +1023,7 @@ enum policy_opt { Opt_fowner_gt, Opt_fgroup_gt, Opt_uid_lt, Opt_euid_lt, Opt_gid_lt, Opt_egid_lt, Opt_fowner_lt, Opt_fgroup_lt, + Opt_digest_type, Opt_appraise_type, Opt_appraise_flag, Opt_appraise_algos, Opt_permit_directio, Opt_pcr, Opt_template, Opt_keyrings, Opt_label, Opt_err @@ -1065,6 +1066,7 @@ static const match_table_t policy_tokens = { {Opt_egid_lt, "egid<%s"}, {Opt_fowner_lt, "fowner<%s"}, {Opt_fgroup_lt, "fgroup<%s"}, + {Opt_digest_type, "digest_type=%s"}, {Opt_appraise_type, "appraise_type=%s"}, {Opt_appraise_flag, "appraise_flag=%s"}, {Opt_appraise_algos, "appraise_algos=%s"}, @@ -1172,6 +1174,21 @@ static void check_template_modsig(const struct ima_template_desc *template) #undef MSG } +/* + * Warn if the template does not contain the given field. + */ +static void check_template_field(const struct ima_template_desc *template, + const char *field, const char *msg) +{ + int i; + + for (i = 0; i < template->num_fields; i++) + if (!strcmp(template->fields[i]->field_id, field)) + return; + + pr_notice_once("%s", msg); +} + static bool ima_validate_rule(struct ima_rule_entry *entry) { /* Ensure that the action is set and is compatible with the flags */ @@ -1214,7 +1231,8 @@ static bool ima_validate_rule(struct ima_rule_entry *entry) IMA_INMASK | IMA_EUID | IMA_PCR | IMA_FSNAME | IMA_GID | IMA_EGID | IMA_FGROUP | IMA_DIGSIG_REQUIRED | - IMA_PERMIT_DIRECTIO | IMA_VALIDATE_ALGOS)) + IMA_PERMIT_DIRECTIO | IMA_VALIDATE_ALGOS | + IMA_VERITY_REQUIRED)) return false; break; @@ -1292,6 +1310,18 @@ static bool ima_validate_rule(struct ima_rule_entry *entry) !(entry->flags & IMA_MODSIG_ALLOWED)) return false; + /* + * Unlike for regular IMA 'appraise' policy rules where security.ima + * xattr may contain either a file hash or signature, the security.ima + * xattr for fsverity must contain a file signature (sigv3). Ensure + * that 'appraise' rules for fsverity require file signatures by + * checking the IMA_DIGSIG_REQUIRED flag is set. + */ + if (entry->action == APPRAISE && + (entry->flags & IMA_VERITY_REQUIRED) && + !(entry->flags & IMA_DIGSIG_REQUIRED)) + return false; + return true; } @@ -1707,16 +1737,39 @@ static int ima_parse_rule(char *rule, struct ima_rule_entry *entry) LSM_SUBJ_TYPE, AUDIT_SUBJ_TYPE); break; + case Opt_digest_type: + ima_log_string(ab, "digest_type", args[0].from); + if (entry->flags & IMA_DIGSIG_REQUIRED) + result = -EINVAL; + else if ((strcmp(args[0].from, "verity")) == 0) + entry->flags |= IMA_VERITY_REQUIRED; + else + result = -EINVAL; + break; case Opt_appraise_type: ima_log_string(ab, "appraise_type", args[0].from); - if ((strcmp(args[0].from, "imasig")) == 0) - entry->flags |= IMA_DIGSIG_REQUIRED; - else if (IS_ENABLED(CONFIG_IMA_APPRAISE_MODSIG) && - strcmp(args[0].from, "imasig|modsig") == 0) - entry->flags |= IMA_DIGSIG_REQUIRED | + + if ((strcmp(args[0].from, "imasig")) == 0) { + if (entry->flags & IMA_VERITY_REQUIRED) + result = -EINVAL; + else + entry->flags |= IMA_DIGSIG_REQUIRED; + } else if (strcmp(args[0].from, "sigv3") == 0) { + /* Only fsverity supports sigv3 for now */ + if (entry->flags & IMA_VERITY_REQUIRED) + entry->flags |= IMA_DIGSIG_REQUIRED; + else + result = -EINVAL; + } else if (IS_ENABLED(CONFIG_IMA_APPRAISE_MODSIG) && + strcmp(args[0].from, "imasig|modsig") == 0) { + if (entry->flags & IMA_VERITY_REQUIRED) + result = -EINVAL; + else + entry->flags |= IMA_DIGSIG_REQUIRED | IMA_MODSIG_ALLOWED; - else + } else { result = -EINVAL; + } break; case Opt_appraise_flag: ima_log_string(ab, "appraise_flag", args[0].from); @@ -1797,6 +1850,15 @@ static int ima_parse_rule(char *rule, struct ima_rule_entry *entry) check_template_modsig(template_desc); } + /* d-ngv2 template field recommended for unsigned fs-verity digests */ + if (!result && entry->action == MEASURE && + entry->flags & IMA_VERITY_REQUIRED) { + template_desc = entry->template ? entry->template : + ima_template_desc_current(); + check_template_field(template_desc, "d-ngv2", + "verity rules should include d-ngv2"); + } + audit_log_format(ab, "res=%d", !result); audit_log_end(ab); return result; @@ -2149,11 +2211,15 @@ int ima_policy_show(struct seq_file *m, void *v) if (entry->template) seq_printf(m, "template=%s ", entry->template->name); if (entry->flags & IMA_DIGSIG_REQUIRED) { - if (entry->flags & IMA_MODSIG_ALLOWED) + if (entry->flags & IMA_VERITY_REQUIRED) + seq_puts(m, "appraise_type=sigv3 "); + else if (entry->flags & IMA_MODSIG_ALLOWED) seq_puts(m, "appraise_type=imasig|modsig "); else seq_puts(m, "appraise_type=imasig "); } + if (entry->flags & IMA_VERITY_REQUIRED) + seq_puts(m, "digest_type=verity "); if (entry->flags & IMA_CHECK_BLACKLIST) seq_puts(m, "appraise_flag=check_blacklist "); if (entry->flags & IMA_PERMIT_DIRECTIO) diff --git a/security/integrity/ima/ima_template.c b/security/integrity/ima/ima_template.c index db1ad6d7a57f..c25079faa208 100644 --- a/security/integrity/ima/ima_template.c +++ b/security/integrity/ima/ima_template.c @@ -20,6 +20,8 @@ static struct ima_template_desc builtin_templates[] = { {.name = IMA_TEMPLATE_IMA_NAME, .fmt = IMA_TEMPLATE_IMA_FMT}, {.name = "ima-ng", .fmt = "d-ng|n-ng"}, {.name = "ima-sig", .fmt = "d-ng|n-ng|sig"}, + {.name = "ima-ngv2", .fmt = "d-ngv2|n-ng"}, + {.name = "ima-sigv2", .fmt = "d-ngv2|n-ng|sig"}, {.name = "ima-buf", .fmt = "d-ng|n-ng|buf"}, {.name = "ima-modsig", .fmt = "d-ng|n-ng|sig|d-modsig|modsig"}, {.name = "evm-sig", @@ -38,6 +40,8 @@ static const struct ima_template_field supported_fields[] = { .field_show = ima_show_template_string}, {.field_id = "d-ng", .field_init = ima_eventdigest_ng_init, .field_show = ima_show_template_digest_ng}, + {.field_id = "d-ngv2", .field_init = ima_eventdigest_ngv2_init, + .field_show = ima_show_template_digest_ngv2}, {.field_id = "n-ng", .field_init = ima_eventname_ng_init, .field_show = ima_show_template_string}, {.field_id = "sig", .field_init = ima_eventsig_init, diff --git a/security/integrity/ima/ima_template_lib.c b/security/integrity/ima/ima_template_lib.c index 7155d17a3b75..c877f01a5471 100644 --- a/security/integrity/ima/ima_template_lib.c +++ b/security/integrity/ima/ima_template_lib.c @@ -24,11 +24,24 @@ static bool ima_template_hash_algo_allowed(u8 algo) enum data_formats { DATA_FMT_DIGEST = 0, DATA_FMT_DIGEST_WITH_ALGO, + DATA_FMT_DIGEST_WITH_TYPE_AND_ALGO, DATA_FMT_STRING, DATA_FMT_HEX, DATA_FMT_UINT }; +enum digest_type { + DIGEST_TYPE_IMA, + DIGEST_TYPE_VERITY, + DIGEST_TYPE__LAST +}; + +#define DIGEST_TYPE_NAME_LEN_MAX 7 /* including NUL */ +static const char * const digest_type_name[DIGEST_TYPE__LAST] = { + [DIGEST_TYPE_IMA] = "ima", + [DIGEST_TYPE_VERITY] = "verity" +}; + static int ima_write_template_field_data(const void *data, const u32 datalen, enum data_formats datafmt, struct ima_field_data *field_data) @@ -72,8 +85,9 @@ static void ima_show_template_data_ascii(struct seq_file *m, u32 buflen = field_data->len; switch (datafmt) { + case DATA_FMT_DIGEST_WITH_TYPE_AND_ALGO: case DATA_FMT_DIGEST_WITH_ALGO: - buf_ptr = strnchr(field_data->data, buflen, ':'); + buf_ptr = strrchr(field_data->data, ':'); if (buf_ptr != field_data->data) seq_printf(m, "%s", field_data->data); @@ -178,6 +192,14 @@ void ima_show_template_digest_ng(struct seq_file *m, enum ima_show_type show, field_data); } +void ima_show_template_digest_ngv2(struct seq_file *m, enum ima_show_type show, + struct ima_field_data *field_data) +{ + ima_show_template_field_data(m, show, + DATA_FMT_DIGEST_WITH_TYPE_AND_ALGO, + field_data); +} + void ima_show_template_string(struct seq_file *m, enum ima_show_type show, struct ima_field_data *field_data) { @@ -265,26 +287,35 @@ int ima_parse_buf(void *bufstartp, void *bufendp, void **bufcurp, } static int ima_eventdigest_init_common(const u8 *digest, u32 digestsize, - u8 hash_algo, + u8 digest_type, u8 hash_algo, struct ima_field_data *field_data) { /* * digest formats: * - DATA_FMT_DIGEST: digest - * - DATA_FMT_DIGEST_WITH_ALGO: [<hash algo>] + ':' + '\0' + digest, - * where <hash algo> is provided if the hash algorithm is not - * SHA1 or MD5 + * - DATA_FMT_DIGEST_WITH_ALGO: <hash algo> + ':' + '\0' + digest, + * - DATA_FMT_DIGEST_WITH_TYPE_AND_ALGO: + * <digest type> + ':' + <hash algo> + ':' + '\0' + digest, + * + * where 'DATA_FMT_DIGEST' is the original digest format ('d') + * with a hash size limitation of 20 bytes, + * where <digest type> is either "ima" or "verity", + * where <hash algo> is the hash_algo_name[] string. */ - u8 buffer[CRYPTO_MAX_ALG_NAME + 2 + IMA_MAX_DIGEST_SIZE] = { 0 }; + u8 buffer[DIGEST_TYPE_NAME_LEN_MAX + CRYPTO_MAX_ALG_NAME + 2 + + IMA_MAX_DIGEST_SIZE] = { 0 }; enum data_formats fmt = DATA_FMT_DIGEST; u32 offset = 0; - if (hash_algo < HASH_ALGO__LAST) { + if (digest_type < DIGEST_TYPE__LAST && hash_algo < HASH_ALGO__LAST) { + fmt = DATA_FMT_DIGEST_WITH_TYPE_AND_ALGO; + offset += 1 + sprintf(buffer, "%s:%s:", + digest_type_name[digest_type], + hash_algo_name[hash_algo]); + } else if (hash_algo < HASH_ALGO__LAST) { fmt = DATA_FMT_DIGEST_WITH_ALGO; - offset += snprintf(buffer, CRYPTO_MAX_ALG_NAME + 1, "%s", - hash_algo_name[hash_algo]); - buffer[offset] = ':'; - offset += 2; + offset += 1 + sprintf(buffer, "%s:", + hash_algo_name[hash_algo]); } if (digest) @@ -359,7 +390,8 @@ int ima_eventdigest_init(struct ima_event_data *event_data, cur_digestsize = hash.hdr.length; out: return ima_eventdigest_init_common(cur_digest, cur_digestsize, - HASH_ALGO__LAST, field_data); + DIGEST_TYPE__LAST, HASH_ALGO__LAST, + field_data); } /* @@ -368,8 +400,32 @@ out: int ima_eventdigest_ng_init(struct ima_event_data *event_data, struct ima_field_data *field_data) { - u8 *cur_digest = NULL, hash_algo = HASH_ALGO_SHA1; + u8 *cur_digest = NULL, hash_algo = ima_hash_algo; + u32 cur_digestsize = 0; + + if (event_data->violation) /* recording a violation. */ + goto out; + + cur_digest = event_data->iint->ima_hash->digest; + cur_digestsize = event_data->iint->ima_hash->length; + + hash_algo = event_data->iint->ima_hash->algo; +out: + return ima_eventdigest_init_common(cur_digest, cur_digestsize, + DIGEST_TYPE__LAST, hash_algo, + field_data); +} + +/* + * This function writes the digest of an event (without size limit), + * prefixed with both the digest type and hash algorithm. + */ +int ima_eventdigest_ngv2_init(struct ima_event_data *event_data, + struct ima_field_data *field_data) +{ + u8 *cur_digest = NULL, hash_algo = ima_hash_algo; u32 cur_digestsize = 0; + u8 digest_type = DIGEST_TYPE_IMA; if (event_data->violation) /* recording a violation. */ goto out; @@ -378,9 +434,12 @@ int ima_eventdigest_ng_init(struct ima_event_data *event_data, cur_digestsize = event_data->iint->ima_hash->length; hash_algo = event_data->iint->ima_hash->algo; + if (event_data->iint->flags & IMA_VERITY_REQUIRED) + digest_type = DIGEST_TYPE_VERITY; out: return ima_eventdigest_init_common(cur_digest, cur_digestsize, - hash_algo, field_data); + digest_type, hash_algo, + field_data); } /* @@ -415,7 +474,8 @@ int ima_eventdigest_modsig_init(struct ima_event_data *event_data, } return ima_eventdigest_init_common(cur_digest, cur_digestsize, - hash_algo, field_data); + DIGEST_TYPE__LAST, hash_algo, + field_data); } static int ima_eventname_init_common(struct ima_event_data *event_data, @@ -475,7 +535,9 @@ int ima_eventsig_init(struct ima_event_data *event_data, { struct evm_ima_xattr_data *xattr_value = event_data->xattr_value; - if ((!xattr_value) || (xattr_value->type != EVM_IMA_XATTR_DIGSIG)) + if (!xattr_value || + (xattr_value->type != EVM_IMA_XATTR_DIGSIG && + xattr_value->type != IMA_VERITY_DIGSIG)) return ima_eventevmsig_init(event_data, field_data); return ima_write_template_field_data(xattr_value, event_data->xattr_len, diff --git a/security/integrity/ima/ima_template_lib.h b/security/integrity/ima/ima_template_lib.h index c71f1de95753..9f7c335f304f 100644 --- a/security/integrity/ima/ima_template_lib.h +++ b/security/integrity/ima/ima_template_lib.h @@ -21,6 +21,8 @@ void ima_show_template_digest(struct seq_file *m, enum ima_show_type show, struct ima_field_data *field_data); void ima_show_template_digest_ng(struct seq_file *m, enum ima_show_type show, struct ima_field_data *field_data); +void ima_show_template_digest_ngv2(struct seq_file *m, enum ima_show_type show, + struct ima_field_data *field_data); void ima_show_template_string(struct seq_file *m, enum ima_show_type show, struct ima_field_data *field_data); void ima_show_template_sig(struct seq_file *m, enum ima_show_type show, @@ -38,6 +40,8 @@ int ima_eventname_init(struct ima_event_data *event_data, struct ima_field_data *field_data); int ima_eventdigest_ng_init(struct ima_event_data *event_data, struct ima_field_data *field_data); +int ima_eventdigest_ngv2_init(struct ima_event_data *event_data, + struct ima_field_data *field_data); int ima_eventdigest_modsig_init(struct ima_event_data *event_data, struct ima_field_data *field_data); int ima_eventname_ng_init(struct ima_event_data *event_data, diff --git a/security/integrity/integrity.h b/security/integrity/integrity.h index 3510e413ea17..7167a6e99bdc 100644 --- a/security/integrity/integrity.h +++ b/security/integrity/integrity.h @@ -40,6 +40,7 @@ #define IMA_FAIL_UNVERIFIABLE_SIGS 0x10000000 #define IMA_MODSIG_ALLOWED 0x20000000 #define IMA_CHECK_BLACKLIST 0x40000000 +#define IMA_VERITY_REQUIRED 0x80000000 #define IMA_DO_MASK (IMA_MEASURE | IMA_APPRAISE | IMA_AUDIT | \ IMA_HASH | IMA_APPRAISE_SUBMASK) @@ -78,6 +79,7 @@ enum evm_ima_xattr_type { EVM_IMA_XATTR_DIGSIG, IMA_XATTR_DIGEST_NG, EVM_XATTR_PORTABLE_DIGSIG, + IMA_VERITY_DIGSIG, IMA_XATTR_LAST }; @@ -92,7 +94,7 @@ struct evm_xattr { u8 digest[SHA1_DIGEST_SIZE]; } __packed; -#define IMA_MAX_DIGEST_SIZE 64 +#define IMA_MAX_DIGEST_SIZE HASH_MAX_DIGESTSIZE struct ima_digest_data { u8 algo; @@ -121,7 +123,14 @@ struct ima_max_digest_data { } __packed; /* - * signature format v2 - for using with asymmetric keys + * signature header format v2 - for using with asymmetric keys + * + * The signature_v2_hdr struct includes a signature format version + * to simplify defining new signature formats. + * + * signature format: + * version 2: regular file data hash based signature + * version 3: struct ima_file_id data based signature */ struct signature_v2_hdr { uint8_t type; /* xattr type */ @@ -132,6 +141,20 @@ struct signature_v2_hdr { uint8_t sig[]; /* signature payload */ } __packed; +/* + * IMA signature version 3 disambiguates the data that is signed, by + * indirectly signing the hash of the ima_file_id structure data, + * containing either the fsverity_descriptor struct digest or, in the + * future, the regular IMA file hash. + * + * (The hash of the ima_file_id structure is only of the portion used.) + */ +struct ima_file_id { + __u8 hash_type; /* xattr type [enum evm_ima_xattr_type] */ + __u8 hash_algorithm; /* Digest algorithm [enum hash_algo] */ + __u8 hash[HASH_MAX_DIGESTSIZE]; +} __packed; + /* integrity data associated with an inode */ struct integrity_iint_cache { struct rb_node rb_node; /* rooted in integrity_iint_tree */ diff --git a/security/integrity/platform_certs/keyring_handler.c b/security/integrity/platform_certs/keyring_handler.c index 1db4d3b4356d..8a1124e4d769 100644 --- a/security/integrity/platform_certs/keyring_handler.c +++ b/security/integrity/platform_certs/keyring_handler.c @@ -17,34 +17,12 @@ static efi_guid_t efi_cert_x509_sha256_guid __initdata = static efi_guid_t efi_cert_sha256_guid __initdata = EFI_CERT_SHA256_GUID; /* - * Blacklist a hash. - */ -static __init void uefi_blacklist_hash(const char *source, const void *data, - size_t len, const char *type, - size_t type_len) -{ - char *hash, *p; - - hash = kmalloc(type_len + len * 2 + 1, GFP_KERNEL); - if (!hash) - return; - p = memcpy(hash, type, type_len); - p += type_len; - bin2hex(p, data, len); - p += len * 2; - *p = 0; - - mark_hash_blacklisted(hash); - kfree(hash); -} - -/* * Blacklist an X509 TBS hash. */ static __init void uefi_blacklist_x509_tbs(const char *source, const void *data, size_t len) { - uefi_blacklist_hash(source, data, len, "tbs:", 4); + mark_hash_blacklisted(data, len, BLACKLIST_HASH_X509_TBS); } /* @@ -53,7 +31,7 @@ static __init void uefi_blacklist_x509_tbs(const char *source, static __init void uefi_blacklist_binary(const char *source, const void *data, size_t len) { - uefi_blacklist_hash(source, data, len, "bin:", 4); + mark_hash_blacklisted(data, len, BLACKLIST_HASH_BINARY); } /* @@ -73,7 +51,7 @@ __init efi_element_handler_t get_handler_for_db(const efi_guid_t *sig_type) { if (efi_guidcmp(*sig_type, efi_cert_x509_guid) == 0) return add_to_platform_keyring; - return 0; + return NULL; } /* @@ -88,7 +66,7 @@ __init efi_element_handler_t get_handler_for_mok(const efi_guid_t *sig_type) else return add_to_platform_keyring; } - return 0; + return NULL; } /* @@ -103,5 +81,5 @@ __init efi_element_handler_t get_handler_for_dbx(const efi_guid_t *sig_type) return uefi_blacklist_binary; if (efi_guidcmp(*sig_type, efi_cert_x509_guid) == 0) return uefi_revocation_list_x509; - return 0; + return NULL; } diff --git a/security/integrity/platform_certs/keyring_handler.h b/security/integrity/platform_certs/keyring_handler.h index 284558f30411..212d894a8c0c 100644 --- a/security/integrity/platform_certs/keyring_handler.h +++ b/security/integrity/platform_certs/keyring_handler.h @@ -35,3 +35,11 @@ efi_element_handler_t get_handler_for_mok(const efi_guid_t *sig_type); efi_element_handler_t get_handler_for_dbx(const efi_guid_t *sig_type); #endif + +#ifndef UEFI_QUIRK_SKIP_CERT +#define UEFI_QUIRK_SKIP_CERT(vendor, product) \ + .matches = { \ + DMI_MATCH(DMI_BOARD_VENDOR, vendor), \ + DMI_MATCH(DMI_PRODUCT_NAME, product), \ + }, +#endif diff --git a/security/integrity/platform_certs/load_uefi.c b/security/integrity/platform_certs/load_uefi.c index 5f45c3c07dbd..093894a640dc 100644 --- a/security/integrity/platform_certs/load_uefi.c +++ b/security/integrity/platform_certs/load_uefi.c @@ -3,6 +3,7 @@ #include <linux/kernel.h> #include <linux/sched.h> #include <linux/cred.h> +#include <linux/dmi.h> #include <linux/err.h> #include <linux/efi.h> #include <linux/slab.h> @@ -13,6 +14,31 @@ #include "keyring_handler.h" /* + * On T2 Macs reading the db and dbx efi variables to load UEFI Secure Boot + * certificates causes occurrence of a page fault in Apple's firmware and + * a crash disabling EFI runtime services. The following quirk skips reading + * these variables. + */ +static const struct dmi_system_id uefi_skip_cert[] = { + { UEFI_QUIRK_SKIP_CERT("Apple Inc.", "MacBookPro15,1") }, + { UEFI_QUIRK_SKIP_CERT("Apple Inc.", "MacBookPro15,2") }, + { UEFI_QUIRK_SKIP_CERT("Apple Inc.", "MacBookPro15,3") }, + { UEFI_QUIRK_SKIP_CERT("Apple Inc.", "MacBookPro15,4") }, + { UEFI_QUIRK_SKIP_CERT("Apple Inc.", "MacBookPro16,1") }, + { UEFI_QUIRK_SKIP_CERT("Apple Inc.", "MacBookPro16,2") }, + { UEFI_QUIRK_SKIP_CERT("Apple Inc.", "MacBookPro16,3") }, + { UEFI_QUIRK_SKIP_CERT("Apple Inc.", "MacBookPro16,4") }, + { UEFI_QUIRK_SKIP_CERT("Apple Inc.", "MacBookAir8,1") }, + { UEFI_QUIRK_SKIP_CERT("Apple Inc.", "MacBookAir8,2") }, + { UEFI_QUIRK_SKIP_CERT("Apple Inc.", "MacBookAir9,1") }, + { UEFI_QUIRK_SKIP_CERT("Apple Inc.", "MacMini8,1") }, + { UEFI_QUIRK_SKIP_CERT("Apple Inc.", "MacPro7,1") }, + { UEFI_QUIRK_SKIP_CERT("Apple Inc.", "iMac20,1") }, + { UEFI_QUIRK_SKIP_CERT("Apple Inc.", "iMac20,2") }, + { } +}; + +/* * Look to see if a UEFI variable called MokIgnoreDB exists and return true if * it does. * @@ -138,6 +164,13 @@ static int __init load_uefi_certs(void) unsigned long dbsize = 0, dbxsize = 0, mokxsize = 0; efi_status_t status; int rc = 0; + const struct dmi_system_id *dmi_id; + + dmi_id = dmi_first_match(uefi_skip_cert); + if (dmi_id) { + pr_err("Reading UEFI Secure Boot Certs is not supported on T2 Macs.\n"); + return false; + } if (!efi_rt_services_supported(EFI_RT_SUPPORTED_GET_VARIABLE)) return false; diff --git a/security/keys/Kconfig b/security/keys/Kconfig index 0e30b361e1c1..abb03a1b2a5c 100644 --- a/security/keys/Kconfig +++ b/security/keys/Kconfig @@ -70,23 +70,19 @@ config BIG_KEYS config TRUSTED_KEYS tristate "TRUSTED KEYS" - depends on KEYS && TCG_TPM - select CRYPTO - select CRYPTO_HMAC - select CRYPTO_SHA1 - select CRYPTO_HASH_INFO - select ASN1_ENCODER - select OID_REGISTRY - select ASN1 + depends on KEYS help This option provides support for creating, sealing, and unsealing keys in the kernel. Trusted keys are random number symmetric keys, - generated and RSA-sealed by the TPM. The TPM only unseals the keys, - if the boot PCRs and other criteria match. Userspace will only ever - see encrypted blobs. + generated and sealed by a trust source selected at kernel boot-time. + Userspace will only ever see encrypted blobs. If you are unsure as to whether this is required, answer N. +if TRUSTED_KEYS +source "security/keys/trusted-keys/Kconfig" +endif + config ENCRYPTED_KEYS tristate "ENCRYPTED KEYS" depends on KEYS diff --git a/security/keys/big_key.c b/security/keys/big_key.c index d17e5f09eeb8..c3367622c683 100644 --- a/security/keys/big_key.c +++ b/security/keys/big_key.c @@ -20,12 +20,13 @@ /* * Layout of key payload words. */ -enum { - big_key_data, - big_key_path, - big_key_path_2nd_part, - big_key_len, +struct big_key_payload { + u8 *data; + struct path path; + size_t length; }; +#define to_big_key_payload(payload) \ + (struct big_key_payload *)((payload).data) /* * If the data is under this limit, there's no point creating a shm file to @@ -55,7 +56,7 @@ struct key_type key_type_big_key = { */ int big_key_preparse(struct key_preparsed_payload *prep) { - struct path *path = (struct path *)&prep->payload.data[big_key_path]; + struct big_key_payload *payload = to_big_key_payload(prep->payload); struct file *file; u8 *buf, *enckey; ssize_t written; @@ -63,13 +64,15 @@ int big_key_preparse(struct key_preparsed_payload *prep) size_t enclen = datalen + CHACHA20POLY1305_AUTHTAG_SIZE; int ret; + BUILD_BUG_ON(sizeof(*payload) != sizeof(prep->payload.data)); + if (datalen <= 0 || datalen > 1024 * 1024 || !prep->data) return -EINVAL; /* Set an arbitrary quota */ prep->quotalen = 16; - prep->payload.data[big_key_len] = (void *)(unsigned long)datalen; + payload->length = datalen; if (datalen > BIG_KEY_FILE_THRESHOLD) { /* Create a shmem file to store the data in. This will permit the data @@ -117,9 +120,9 @@ int big_key_preparse(struct key_preparsed_payload *prep) /* Pin the mount and dentry to the key so that we can open it again * later */ - prep->payload.data[big_key_data] = enckey; - *path = file->f_path; - path_get(path); + payload->data = enckey; + payload->path = file->f_path; + path_get(&payload->path); fput(file); kvfree_sensitive(buf, enclen); } else { @@ -129,7 +132,7 @@ int big_key_preparse(struct key_preparsed_payload *prep) if (!data) return -ENOMEM; - prep->payload.data[big_key_data] = data; + payload->data = data; memcpy(data, prep->data, prep->datalen); } return 0; @@ -148,12 +151,11 @@ error: */ void big_key_free_preparse(struct key_preparsed_payload *prep) { - if (prep->datalen > BIG_KEY_FILE_THRESHOLD) { - struct path *path = (struct path *)&prep->payload.data[big_key_path]; + struct big_key_payload *payload = to_big_key_payload(prep->payload); - path_put(path); - } - kfree_sensitive(prep->payload.data[big_key_data]); + if (prep->datalen > BIG_KEY_FILE_THRESHOLD) + path_put(&payload->path); + kfree_sensitive(payload->data); } /* @@ -162,13 +164,12 @@ void big_key_free_preparse(struct key_preparsed_payload *prep) */ void big_key_revoke(struct key *key) { - struct path *path = (struct path *)&key->payload.data[big_key_path]; + struct big_key_payload *payload = to_big_key_payload(key->payload); /* clear the quota */ key_payload_reserve(key, 0); - if (key_is_positive(key) && - (size_t)key->payload.data[big_key_len] > BIG_KEY_FILE_THRESHOLD) - vfs_truncate(path, 0); + if (key_is_positive(key) && payload->length > BIG_KEY_FILE_THRESHOLD) + vfs_truncate(&payload->path, 0); } /* @@ -176,17 +177,15 @@ void big_key_revoke(struct key *key) */ void big_key_destroy(struct key *key) { - size_t datalen = (size_t)key->payload.data[big_key_len]; - - if (datalen > BIG_KEY_FILE_THRESHOLD) { - struct path *path = (struct path *)&key->payload.data[big_key_path]; + struct big_key_payload *payload = to_big_key_payload(key->payload); - path_put(path); - path->mnt = NULL; - path->dentry = NULL; + if (payload->length > BIG_KEY_FILE_THRESHOLD) { + path_put(&payload->path); + payload->path.mnt = NULL; + payload->path.dentry = NULL; } - kfree_sensitive(key->payload.data[big_key_data]); - key->payload.data[big_key_data] = NULL; + kfree_sensitive(payload->data); + payload->data = NULL; } /* @@ -211,14 +210,14 @@ int big_key_update(struct key *key, struct key_preparsed_payload *prep) */ void big_key_describe(const struct key *key, struct seq_file *m) { - size_t datalen = (size_t)key->payload.data[big_key_len]; + struct big_key_payload *payload = to_big_key_payload(key->payload); seq_puts(m, key->description); if (key_is_positive(key)) seq_printf(m, ": %zu [%s]", - datalen, - datalen > BIG_KEY_FILE_THRESHOLD ? "file" : "buff"); + payload->length, + payload->length > BIG_KEY_FILE_THRESHOLD ? "file" : "buff"); } /* @@ -227,16 +226,16 @@ void big_key_describe(const struct key *key, struct seq_file *m) */ long big_key_read(const struct key *key, char *buffer, size_t buflen) { - size_t datalen = (size_t)key->payload.data[big_key_len]; + struct big_key_payload *payload = to_big_key_payload(key->payload); + size_t datalen = payload->length; long ret; if (!buffer || buflen < datalen) return datalen; if (datalen > BIG_KEY_FILE_THRESHOLD) { - struct path *path = (struct path *)&key->payload.data[big_key_path]; struct file *file; - u8 *buf, *enckey = (u8 *)key->payload.data[big_key_data]; + u8 *buf, *enckey = payload->data; size_t enclen = datalen + CHACHA20POLY1305_AUTHTAG_SIZE; loff_t pos = 0; @@ -244,7 +243,7 @@ long big_key_read(const struct key *key, char *buffer, size_t buflen) if (!buf) return -ENOMEM; - file = dentry_open(path, O_RDONLY, current_cred()); + file = dentry_open(&payload->path, O_RDONLY, current_cred()); if (IS_ERR(file)) { ret = PTR_ERR(file); goto error; @@ -274,7 +273,7 @@ error: kvfree_sensitive(buf, enclen); } else { ret = datalen; - memcpy(buffer, key->payload.data[big_key_data], datalen); + memcpy(buffer, payload->data, datalen); } return ret; diff --git a/security/keys/trusted-keys/Kconfig b/security/keys/trusted-keys/Kconfig new file mode 100644 index 000000000000..dbfdd8536468 --- /dev/null +++ b/security/keys/trusted-keys/Kconfig @@ -0,0 +1,38 @@ +config TRUSTED_KEYS_TPM + bool "TPM-based trusted keys" + depends on TCG_TPM >= TRUSTED_KEYS + default y + select CRYPTO + select CRYPTO_HMAC + select CRYPTO_SHA1 + select CRYPTO_HASH_INFO + select ASN1_ENCODER + select OID_REGISTRY + select ASN1 + help + Enable use of the Trusted Platform Module (TPM) as trusted key + backend. Trusted keys are random number symmetric keys, + which will be generated and RSA-sealed by the TPM. + The TPM only unseals the keys, if the boot PCRs and other + criteria match. + +config TRUSTED_KEYS_TEE + bool "TEE-based trusted keys" + depends on TEE >= TRUSTED_KEYS + default y + help + Enable use of the Trusted Execution Environment (TEE) as trusted + key backend. + +config TRUSTED_KEYS_CAAM + bool "CAAM-based trusted keys" + depends on CRYPTO_DEV_FSL_CAAM_JR >= TRUSTED_KEYS + select CRYPTO_DEV_FSL_CAAM_BLOB_GEN + default y + help + Enable use of NXP's Cryptographic Accelerator and Assurance Module + (CAAM) as trusted key backend. + +if !TRUSTED_KEYS_TPM && !TRUSTED_KEYS_TEE && !TRUSTED_KEYS_CAAM +comment "No trust source selected!" +endif diff --git a/security/keys/trusted-keys/Makefile b/security/keys/trusted-keys/Makefile index feb8b6c3cc79..735aa0bc08ef 100644 --- a/security/keys/trusted-keys/Makefile +++ b/security/keys/trusted-keys/Makefile @@ -5,10 +5,12 @@ obj-$(CONFIG_TRUSTED_KEYS) += trusted.o trusted-y += trusted_core.o -trusted-y += trusted_tpm1.o +trusted-$(CONFIG_TRUSTED_KEYS_TPM) += trusted_tpm1.o $(obj)/trusted_tpm2.o: $(obj)/tpm2key.asn1.h -trusted-y += trusted_tpm2.o -trusted-y += tpm2key.asn1.o +trusted-$(CONFIG_TRUSTED_KEYS_TPM) += trusted_tpm2.o +trusted-$(CONFIG_TRUSTED_KEYS_TPM) += tpm2key.asn1.o -trusted-$(CONFIG_TEE) += trusted_tee.o +trusted-$(CONFIG_TRUSTED_KEYS_TEE) += trusted_tee.o + +trusted-$(CONFIG_TRUSTED_KEYS_CAAM) += trusted_caam.o diff --git a/security/keys/trusted-keys/trusted_caam.c b/security/keys/trusted-keys/trusted_caam.c new file mode 100644 index 000000000000..e3415c520c0a --- /dev/null +++ b/security/keys/trusted-keys/trusted_caam.c @@ -0,0 +1,80 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2021 Pengutronix, Ahmad Fatoum <kernel@pengutronix.de> + */ + +#include <keys/trusted_caam.h> +#include <keys/trusted-type.h> +#include <linux/build_bug.h> +#include <linux/key-type.h> +#include <soc/fsl/caam-blob.h> + +static struct caam_blob_priv *blobifier; + +#define KEYMOD "SECURE_KEY" + +static_assert(MAX_KEY_SIZE + CAAM_BLOB_OVERHEAD <= CAAM_BLOB_MAX_LEN); +static_assert(MAX_BLOB_SIZE <= CAAM_BLOB_MAX_LEN); + +static int trusted_caam_seal(struct trusted_key_payload *p, char *datablob) +{ + int ret; + struct caam_blob_info info = { + .input = p->key, .input_len = p->key_len, + .output = p->blob, .output_len = MAX_BLOB_SIZE, + .key_mod = KEYMOD, .key_mod_len = sizeof(KEYMOD) - 1, + }; + + ret = caam_encap_blob(blobifier, &info); + if (ret) + return ret; + + p->blob_len = info.output_len; + return 0; +} + +static int trusted_caam_unseal(struct trusted_key_payload *p, char *datablob) +{ + int ret; + struct caam_blob_info info = { + .input = p->blob, .input_len = p->blob_len, + .output = p->key, .output_len = MAX_KEY_SIZE, + .key_mod = KEYMOD, .key_mod_len = sizeof(KEYMOD) - 1, + }; + + ret = caam_decap_blob(blobifier, &info); + if (ret) + return ret; + + p->key_len = info.output_len; + return 0; +} + +static int trusted_caam_init(void) +{ + int ret; + + blobifier = caam_blob_gen_init(); + if (IS_ERR(blobifier)) + return PTR_ERR(blobifier); + + ret = register_key_type(&key_type_trusted); + if (ret) + caam_blob_gen_exit(blobifier); + + return ret; +} + +static void trusted_caam_exit(void) +{ + unregister_key_type(&key_type_trusted); + caam_blob_gen_exit(blobifier); +} + +struct trusted_key_ops trusted_key_caam_ops = { + .migratable = 0, /* non-migratable */ + .init = trusted_caam_init, + .seal = trusted_caam_seal, + .unseal = trusted_caam_unseal, + .exit = trusted_caam_exit, +}; diff --git a/security/keys/trusted-keys/trusted_core.c b/security/keys/trusted-keys/trusted_core.c index 9b9d3ef79cbe..c6fc50d67214 100644 --- a/security/keys/trusted-keys/trusted_core.c +++ b/security/keys/trusted-keys/trusted_core.c @@ -9,6 +9,7 @@ #include <keys/user-type.h> #include <keys/trusted-type.h> #include <keys/trusted_tee.h> +#include <keys/trusted_caam.h> #include <keys/trusted_tpm.h> #include <linux/capability.h> #include <linux/err.h> @@ -16,23 +17,31 @@ #include <linux/key-type.h> #include <linux/module.h> #include <linux/parser.h> +#include <linux/random.h> #include <linux/rcupdate.h> #include <linux/slab.h> #include <linux/static_call.h> #include <linux/string.h> #include <linux/uaccess.h> +static char *trusted_rng = "default"; +module_param_named(rng, trusted_rng, charp, 0); +MODULE_PARM_DESC(rng, "Select trusted key RNG"); + static char *trusted_key_source; module_param_named(source, trusted_key_source, charp, 0); -MODULE_PARM_DESC(source, "Select trusted keys source (tpm or tee)"); +MODULE_PARM_DESC(source, "Select trusted keys source (tpm, tee or caam)"); static const struct trusted_key_source trusted_key_sources[] = { -#if IS_REACHABLE(CONFIG_TCG_TPM) +#if defined(CONFIG_TRUSTED_KEYS_TPM) { "tpm", &trusted_key_tpm_ops }, #endif -#if IS_REACHABLE(CONFIG_TEE) +#if defined(CONFIG_TRUSTED_KEYS_TEE) { "tee", &trusted_key_tee_ops }, #endif +#if defined(CONFIG_TRUSTED_KEYS_CAAM) + { "caam", &trusted_key_caam_ops }, +#endif }; DEFINE_STATIC_CALL_NULL(trusted_key_init, *trusted_key_sources[0].ops->init); @@ -312,8 +321,14 @@ struct key_type key_type_trusted = { }; EXPORT_SYMBOL_GPL(key_type_trusted); +static int kernel_get_random(unsigned char *key, size_t key_len) +{ + return get_random_bytes_wait(key, key_len) ?: key_len; +} + static int __init init_trusted(void) { + int (*get_random)(unsigned char *key, size_t key_len); int i, ret = 0; for (i = 0; i < ARRAY_SIZE(trusted_key_sources); i++) { @@ -322,6 +337,28 @@ static int __init init_trusted(void) strlen(trusted_key_sources[i].name))) continue; + /* + * We always support trusted.rng="kernel" and "default" as + * well as trusted.rng=$trusted.source if the trust source + * defines its own get_random callback. + */ + get_random = trusted_key_sources[i].ops->get_random; + if (trusted_rng && strcmp(trusted_rng, "default")) { + if (!strcmp(trusted_rng, "kernel")) { + get_random = kernel_get_random; + } else if (strcmp(trusted_rng, trusted_key_sources[i].name) || + !get_random) { + pr_warn("Unsupported RNG. Supported: kernel"); + if (get_random) + pr_cont(", %s", trusted_key_sources[i].name); + pr_cont(", default\n"); + return -EINVAL; + } + } + + if (!get_random) + get_random = kernel_get_random; + static_call_update(trusted_key_init, trusted_key_sources[i].ops->init); static_call_update(trusted_key_seal, @@ -329,7 +366,7 @@ static int __init init_trusted(void) static_call_update(trusted_key_unseal, trusted_key_sources[i].ops->unseal); static_call_update(trusted_key_get_random, - trusted_key_sources[i].ops->get_random); + get_random); static_call_update(trusted_key_exit, trusted_key_sources[i].ops->exit); migratable = trusted_key_sources[i].ops->migratable; diff --git a/security/landlock/cred.c b/security/landlock/cred.c index 6725af24c684..ec6c37f04a19 100644 --- a/security/landlock/cred.c +++ b/security/landlock/cred.c @@ -15,7 +15,7 @@ #include "setup.h" static int hook_cred_prepare(struct cred *const new, - const struct cred *const old, const gfp_t gfp) + const struct cred *const old, const gfp_t gfp) { struct landlock_ruleset *const old_dom = landlock_cred(old)->domain; @@ -42,5 +42,5 @@ static struct security_hook_list landlock_hooks[] __lsm_ro_after_init = { __init void landlock_add_cred_hooks(void) { security_add_hooks(landlock_hooks, ARRAY_SIZE(landlock_hooks), - LANDLOCK_NAME); + LANDLOCK_NAME); } diff --git a/security/landlock/cred.h b/security/landlock/cred.h index 5f99d3decade..af89ab00e6d1 100644 --- a/security/landlock/cred.h +++ b/security/landlock/cred.h @@ -20,8 +20,8 @@ struct landlock_cred_security { struct landlock_ruleset *domain; }; -static inline struct landlock_cred_security *landlock_cred( - const struct cred *cred) +static inline struct landlock_cred_security * +landlock_cred(const struct cred *cred) { return cred->security + landlock_blob_sizes.lbs_cred; } @@ -34,8 +34,8 @@ static inline const struct landlock_ruleset *landlock_get_current_domain(void) /* * The call needs to come from an RCU read-side critical section. */ -static inline const struct landlock_ruleset *landlock_get_task_domain( - const struct task_struct *const task) +static inline const struct landlock_ruleset * +landlock_get_task_domain(const struct task_struct *const task) { return landlock_cred(__task_cred(task))->domain; } diff --git a/security/landlock/fs.c b/security/landlock/fs.c index 97b8e421f617..ec5a6247cd3e 100644 --- a/security/landlock/fs.c +++ b/security/landlock/fs.c @@ -4,6 +4,7 @@ * * Copyright © 2016-2020 Mickaël Salaün <mic@digikod.net> * Copyright © 2018-2020 ANSSI + * Copyright © 2021-2022 Microsoft Corporation */ #include <linux/atomic.h> @@ -141,23 +142,26 @@ retry: } /* All access rights that can be tied to files. */ +/* clang-format off */ #define ACCESS_FILE ( \ LANDLOCK_ACCESS_FS_EXECUTE | \ LANDLOCK_ACCESS_FS_WRITE_FILE | \ LANDLOCK_ACCESS_FS_READ_FILE) +/* clang-format on */ /* * @path: Should have been checked by get_path_from_fd(). */ int landlock_append_fs_rule(struct landlock_ruleset *const ruleset, - const struct path *const path, u32 access_rights) + const struct path *const path, + access_mask_t access_rights) { int err; struct landlock_object *object; /* Files only get access rights that make sense. */ - if (!d_is_dir(path->dentry) && (access_rights | ACCESS_FILE) != - ACCESS_FILE) + if (!d_is_dir(path->dentry) && + (access_rights | ACCESS_FILE) != ACCESS_FILE) return -EINVAL; if (WARN_ON_ONCE(ruleset->num_layers != 1)) return -EINVAL; @@ -180,84 +184,352 @@ int landlock_append_fs_rule(struct landlock_ruleset *const ruleset, /* Access-control management */ -static inline u64 unmask_layers( - const struct landlock_ruleset *const domain, - const struct path *const path, const u32 access_request, - u64 layer_mask) +/* + * The lifetime of the returned rule is tied to @domain. + * + * Returns NULL if no rule is found or if @dentry is negative. + */ +static inline const struct landlock_rule * +find_rule(const struct landlock_ruleset *const domain, + const struct dentry *const dentry) { const struct landlock_rule *rule; const struct inode *inode; - size_t i; - if (d_is_negative(path->dentry)) - /* Ignore nonexistent leafs. */ - return layer_mask; - inode = d_backing_inode(path->dentry); + /* Ignores nonexistent leafs. */ + if (d_is_negative(dentry)) + return NULL; + + inode = d_backing_inode(dentry); rcu_read_lock(); - rule = landlock_find_rule(domain, - rcu_dereference(landlock_inode(inode)->object)); + rule = landlock_find_rule( + domain, rcu_dereference(landlock_inode(inode)->object)); rcu_read_unlock(); + return rule; +} + +/* + * @layer_masks is read and may be updated according to the access request and + * the matching rule. + * + * Returns true if the request is allowed (i.e. relevant layer masks for the + * request are empty). + */ +static inline bool +unmask_layers(const struct landlock_rule *const rule, + const access_mask_t access_request, + layer_mask_t (*const layer_masks)[LANDLOCK_NUM_ACCESS_FS]) +{ + size_t layer_level; + + if (!access_request || !layer_masks) + return true; if (!rule) - return layer_mask; + return false; /* * An access is granted if, for each policy layer, at least one rule - * encountered on the pathwalk grants the requested accesses, - * regardless of their position in the layer stack. We must then check + * encountered on the pathwalk grants the requested access, + * regardless of its position in the layer stack. We must then check * the remaining layers for each inode, from the first added layer to - * the last one. + * the last one. When there is multiple requested accesses, for each + * policy layer, the full set of requested accesses may not be granted + * by only one rule, but by the union (binary OR) of multiple rules. + * E.g. /a/b <execute> + /a <read> => /a/b <execute + read> */ - for (i = 0; i < rule->num_layers; i++) { - const struct landlock_layer *const layer = &rule->layers[i]; - const u64 layer_level = BIT_ULL(layer->level - 1); + for (layer_level = 0; layer_level < rule->num_layers; layer_level++) { + const struct landlock_layer *const layer = + &rule->layers[layer_level]; + const layer_mask_t layer_bit = BIT_ULL(layer->level - 1); + const unsigned long access_req = access_request; + unsigned long access_bit; + bool is_empty; - /* Checks that the layer grants access to the full request. */ - if ((layer->access & access_request) == access_request) { - layer_mask &= ~layer_level; - - if (layer_mask == 0) - return layer_mask; + /* + * Records in @layer_masks which layer grants access to each + * requested access. + */ + is_empty = true; + for_each_set_bit(access_bit, &access_req, + ARRAY_SIZE(*layer_masks)) { + if (layer->access & BIT_ULL(access_bit)) + (*layer_masks)[access_bit] &= ~layer_bit; + is_empty = is_empty && !(*layer_masks)[access_bit]; } + if (is_empty) + return true; } - return layer_mask; + return false; } -static int check_access_path(const struct landlock_ruleset *const domain, - const struct path *const path, u32 access_request) +/* + * Allows access to pseudo filesystems that will never be mountable (e.g. + * sockfs, pipefs), but can still be reachable through + * /proc/<pid>/fd/<file-descriptor> + */ +static inline bool is_nouser_or_private(const struct dentry *dentry) { - bool allowed = false; - struct path walker_path; - u64 layer_mask; - size_t i; + return (dentry->d_sb->s_flags & SB_NOUSER) || + (d_is_positive(dentry) && + unlikely(IS_PRIVATE(d_backing_inode(dentry)))); +} - /* Make sure all layers can be checked. */ - BUILD_BUG_ON(BITS_PER_TYPE(layer_mask) < LANDLOCK_MAX_NUM_LAYERS); +static inline access_mask_t +get_handled_accesses(const struct landlock_ruleset *const domain) +{ + access_mask_t access_dom = 0; + unsigned long access_bit; + + for (access_bit = 0; access_bit < LANDLOCK_NUM_ACCESS_FS; + access_bit++) { + size_t layer_level; + + for (layer_level = 0; layer_level < domain->num_layers; + layer_level++) { + if (domain->fs_access_masks[layer_level] & + BIT_ULL(access_bit)) { + access_dom |= BIT_ULL(access_bit); + break; + } + } + } + return access_dom; +} + +static inline access_mask_t +init_layer_masks(const struct landlock_ruleset *const domain, + const access_mask_t access_request, + layer_mask_t (*const layer_masks)[LANDLOCK_NUM_ACCESS_FS]) +{ + access_mask_t handled_accesses = 0; + size_t layer_level; + memset(layer_masks, 0, sizeof(*layer_masks)); + /* An empty access request can happen because of O_WRONLY | O_RDWR. */ if (!access_request) return 0; + + /* Saves all handled accesses per layer. */ + for (layer_level = 0; layer_level < domain->num_layers; layer_level++) { + const unsigned long access_req = access_request; + unsigned long access_bit; + + for_each_set_bit(access_bit, &access_req, + ARRAY_SIZE(*layer_masks)) { + if (domain->fs_access_masks[layer_level] & + BIT_ULL(access_bit)) { + (*layer_masks)[access_bit] |= + BIT_ULL(layer_level); + handled_accesses |= BIT_ULL(access_bit); + } + } + } + return handled_accesses; +} + +/* + * Check that a destination file hierarchy has more restrictions than a source + * file hierarchy. This is only used for link and rename actions. + * + * @layer_masks_child2: Optional child masks. + */ +static inline bool no_more_access( + const layer_mask_t (*const layer_masks_parent1)[LANDLOCK_NUM_ACCESS_FS], + const layer_mask_t (*const layer_masks_child1)[LANDLOCK_NUM_ACCESS_FS], + const bool child1_is_directory, + const layer_mask_t (*const layer_masks_parent2)[LANDLOCK_NUM_ACCESS_FS], + const layer_mask_t (*const layer_masks_child2)[LANDLOCK_NUM_ACCESS_FS], + const bool child2_is_directory) +{ + unsigned long access_bit; + + for (access_bit = 0; access_bit < ARRAY_SIZE(*layer_masks_parent2); + access_bit++) { + /* Ignores accesses that only make sense for directories. */ + const bool is_file_access = + !!(BIT_ULL(access_bit) & ACCESS_FILE); + + if (child1_is_directory || is_file_access) { + /* + * Checks if the destination restrictions are a + * superset of the source ones (i.e. inherited access + * rights without child exceptions): + * restrictions(parent2) >= restrictions(child1) + */ + if ((((*layer_masks_parent1)[access_bit] & + (*layer_masks_child1)[access_bit]) | + (*layer_masks_parent2)[access_bit]) != + (*layer_masks_parent2)[access_bit]) + return false; + } + + if (!layer_masks_child2) + continue; + if (child2_is_directory || is_file_access) { + /* + * Checks inverted restrictions for RENAME_EXCHANGE: + * restrictions(parent1) >= restrictions(child2) + */ + if ((((*layer_masks_parent2)[access_bit] & + (*layer_masks_child2)[access_bit]) | + (*layer_masks_parent1)[access_bit]) != + (*layer_masks_parent1)[access_bit]) + return false; + } + } + return true; +} + +/* + * Removes @layer_masks accesses that are not requested. + * + * Returns true if the request is allowed, false otherwise. + */ +static inline bool +scope_to_request(const access_mask_t access_request, + layer_mask_t (*const layer_masks)[LANDLOCK_NUM_ACCESS_FS]) +{ + const unsigned long access_req = access_request; + unsigned long access_bit; + + if (WARN_ON_ONCE(!layer_masks)) + return true; + + for_each_clear_bit(access_bit, &access_req, ARRAY_SIZE(*layer_masks)) + (*layer_masks)[access_bit] = 0; + return !memchr_inv(layer_masks, 0, sizeof(*layer_masks)); +} + +/* + * Returns true if there is at least one access right different than + * LANDLOCK_ACCESS_FS_REFER. + */ +static inline bool +is_eacces(const layer_mask_t (*const layer_masks)[LANDLOCK_NUM_ACCESS_FS], + const access_mask_t access_request) +{ + unsigned long access_bit; + /* LANDLOCK_ACCESS_FS_REFER alone must return -EXDEV. */ + const unsigned long access_check = access_request & + ~LANDLOCK_ACCESS_FS_REFER; + + if (!layer_masks) + return false; + + for_each_set_bit(access_bit, &access_check, ARRAY_SIZE(*layer_masks)) { + if ((*layer_masks)[access_bit]) + return true; + } + return false; +} + +/** + * check_access_path_dual - Check accesses for requests with a common path + * + * @domain: Domain to check against. + * @path: File hierarchy to walk through. + * @access_request_parent1: Accesses to check, once @layer_masks_parent1 is + * equal to @layer_masks_parent2 (if any). This is tied to the unique + * requested path for most actions, or the source in case of a refer action + * (i.e. rename or link), or the source and destination in case of + * RENAME_EXCHANGE. + * @layer_masks_parent1: Pointer to a matrix of layer masks per access + * masks, identifying the layers that forbid a specific access. Bits from + * this matrix can be unset according to the @path walk. An empty matrix + * means that @domain allows all possible Landlock accesses (i.e. not only + * those identified by @access_request_parent1). This matrix can + * initially refer to domain layer masks and, when the accesses for the + * destination and source are the same, to requested layer masks. + * @dentry_child1: Dentry to the initial child of the parent1 path. This + * pointer must be NULL for non-refer actions (i.e. not link nor rename). + * @access_request_parent2: Similar to @access_request_parent1 but for a + * request involving a source and a destination. This refers to the + * destination, except in case of RENAME_EXCHANGE where it also refers to + * the source. Must be set to 0 when using a simple path request. + * @layer_masks_parent2: Similar to @layer_masks_parent1 but for a refer + * action. This must be NULL otherwise. + * @dentry_child2: Dentry to the initial child of the parent2 path. This + * pointer is only set for RENAME_EXCHANGE actions and must be NULL + * otherwise. + * + * This helper first checks that the destination has a superset of restrictions + * compared to the source (if any) for a common path. Because of + * RENAME_EXCHANGE actions, source and destinations may be swapped. It then + * checks that the collected accesses and the remaining ones are enough to + * allow the request. + * + * Returns: + * - 0 if the access request is granted; + * - -EACCES if it is denied because of access right other than + * LANDLOCK_ACCESS_FS_REFER; + * - -EXDEV if the renaming or linking would be a privileged escalation + * (according to each layered policies), or if LANDLOCK_ACCESS_FS_REFER is + * not allowed by the source or the destination. + */ +static int check_access_path_dual( + const struct landlock_ruleset *const domain, + const struct path *const path, + const access_mask_t access_request_parent1, + layer_mask_t (*const layer_masks_parent1)[LANDLOCK_NUM_ACCESS_FS], + const struct dentry *const dentry_child1, + const access_mask_t access_request_parent2, + layer_mask_t (*const layer_masks_parent2)[LANDLOCK_NUM_ACCESS_FS], + const struct dentry *const dentry_child2) +{ + bool allowed_parent1 = false, allowed_parent2 = false, is_dom_check, + child1_is_directory = true, child2_is_directory = true; + struct path walker_path; + access_mask_t access_masked_parent1, access_masked_parent2; + layer_mask_t _layer_masks_child1[LANDLOCK_NUM_ACCESS_FS], + _layer_masks_child2[LANDLOCK_NUM_ACCESS_FS]; + layer_mask_t(*layer_masks_child1)[LANDLOCK_NUM_ACCESS_FS] = NULL, + (*layer_masks_child2)[LANDLOCK_NUM_ACCESS_FS] = NULL; + + if (!access_request_parent1 && !access_request_parent2) + return 0; if (WARN_ON_ONCE(!domain || !path)) return 0; - /* - * Allows access to pseudo filesystems that will never be mountable - * (e.g. sockfs, pipefs), but can still be reachable through - * /proc/<pid>/fd/<file-descriptor> . - */ - if ((path->dentry->d_sb->s_flags & SB_NOUSER) || - (d_is_positive(path->dentry) && - unlikely(IS_PRIVATE(d_backing_inode(path->dentry))))) + if (is_nouser_or_private(path->dentry)) return 0; - if (WARN_ON_ONCE(domain->num_layers < 1)) + if (WARN_ON_ONCE(domain->num_layers < 1 || !layer_masks_parent1)) return -EACCES; - /* Saves all layers handling a subset of requested accesses. */ - layer_mask = 0; - for (i = 0; i < domain->num_layers; i++) { - if (domain->fs_access_masks[i] & access_request) - layer_mask |= BIT_ULL(i); + if (unlikely(layer_masks_parent2)) { + if (WARN_ON_ONCE(!dentry_child1)) + return -EACCES; + /* + * For a double request, first check for potential privilege + * escalation by looking at domain handled accesses (which are + * a superset of the meaningful requested accesses). + */ + access_masked_parent1 = access_masked_parent2 = + get_handled_accesses(domain); + is_dom_check = true; + } else { + if (WARN_ON_ONCE(dentry_child1 || dentry_child2)) + return -EACCES; + /* For a simple request, only check for requested accesses. */ + access_masked_parent1 = access_request_parent1; + access_masked_parent2 = access_request_parent2; + is_dom_check = false; + } + + if (unlikely(dentry_child1)) { + unmask_layers(find_rule(domain, dentry_child1), + init_layer_masks(domain, LANDLOCK_MASK_ACCESS_FS, + &_layer_masks_child1), + &_layer_masks_child1); + layer_masks_child1 = &_layer_masks_child1; + child1_is_directory = d_is_dir(dentry_child1); + } + if (unlikely(dentry_child2)) { + unmask_layers(find_rule(domain, dentry_child2), + init_layer_masks(domain, LANDLOCK_MASK_ACCESS_FS, + &_layer_masks_child2), + &_layer_masks_child2); + layer_masks_child2 = &_layer_masks_child2; + child2_is_directory = d_is_dir(dentry_child2); } - /* An access request not handled by the domain is allowed. */ - if (layer_mask == 0) - return 0; walker_path = *path; path_get(&walker_path); @@ -267,15 +539,54 @@ static int check_access_path(const struct landlock_ruleset *const domain, */ while (true) { struct dentry *parent_dentry; + const struct landlock_rule *rule; - layer_mask = unmask_layers(domain, &walker_path, - access_request, layer_mask); - if (layer_mask == 0) { - /* Stops when a rule from each layer grants access. */ - allowed = true; - break; + /* + * If at least all accesses allowed on the destination are + * already allowed on the source, respectively if there is at + * least as much as restrictions on the destination than on the + * source, then we can safely refer files from the source to + * the destination without risking a privilege escalation. + * This also applies in the case of RENAME_EXCHANGE, which + * implies checks on both direction. This is crucial for + * standalone multilayered security policies. Furthermore, + * this helps avoid policy writers to shoot themselves in the + * foot. + */ + if (unlikely(is_dom_check && + no_more_access( + layer_masks_parent1, layer_masks_child1, + child1_is_directory, layer_masks_parent2, + layer_masks_child2, + child2_is_directory))) { + allowed_parent1 = scope_to_request( + access_request_parent1, layer_masks_parent1); + allowed_parent2 = scope_to_request( + access_request_parent2, layer_masks_parent2); + + /* Stops when all accesses are granted. */ + if (allowed_parent1 && allowed_parent2) + break; + + /* + * Now, downgrades the remaining checks from domain + * handled accesses to requested accesses. + */ + is_dom_check = false; + access_masked_parent1 = access_request_parent1; + access_masked_parent2 = access_request_parent2; } + rule = find_rule(domain, walker_path.dentry); + allowed_parent1 = unmask_layers(rule, access_masked_parent1, + layer_masks_parent1); + allowed_parent2 = unmask_layers(rule, access_masked_parent2, + layer_masks_parent2); + + /* Stops when a rule from each layer grants access. */ + if (allowed_parent1 && allowed_parent2) + break; + jump_up: if (walker_path.dentry == walker_path.mnt->mnt_root) { if (follow_up(&walker_path)) { @@ -286,7 +597,6 @@ jump_up: * Stops at the real root. Denies access * because not all layers have granted access. */ - allowed = false; break; } } @@ -296,7 +606,8 @@ jump_up: * access to internal filesystems (e.g. nsfs, which is * reachable through /proc/<pid>/ns/<namespace>). */ - allowed = !!(walker_path.mnt->mnt_flags & MNT_INTERNAL); + allowed_parent1 = allowed_parent2 = + !!(walker_path.mnt->mnt_flags & MNT_INTERNAL); break; } parent_dentry = dget_parent(walker_path.dentry); @@ -304,11 +615,40 @@ jump_up: walker_path.dentry = parent_dentry; } path_put(&walker_path); - return allowed ? 0 : -EACCES; + + if (allowed_parent1 && allowed_parent2) + return 0; + + /* + * This prioritizes EACCES over EXDEV for all actions, including + * renames with RENAME_EXCHANGE. + */ + if (likely(is_eacces(layer_masks_parent1, access_request_parent1) || + is_eacces(layer_masks_parent2, access_request_parent2))) + return -EACCES; + + /* + * Gracefully forbids reparenting if the destination directory + * hierarchy is not a superset of restrictions of the source directory + * hierarchy, or if LANDLOCK_ACCESS_FS_REFER is not allowed by the + * source or the destination. + */ + return -EXDEV; +} + +static inline int check_access_path(const struct landlock_ruleset *const domain, + const struct path *const path, + access_mask_t access_request) +{ + layer_mask_t layer_masks[LANDLOCK_NUM_ACCESS_FS] = {}; + + access_request = init_layer_masks(domain, access_request, &layer_masks); + return check_access_path_dual(domain, path, access_request, + &layer_masks, NULL, 0, NULL, NULL); } static inline int current_check_access_path(const struct path *const path, - const u32 access_request) + const access_mask_t access_request) { const struct landlock_ruleset *const dom = landlock_get_current_domain(); @@ -318,6 +658,239 @@ static inline int current_check_access_path(const struct path *const path, return check_access_path(dom, path, access_request); } +static inline access_mask_t get_mode_access(const umode_t mode) +{ + switch (mode & S_IFMT) { + case S_IFLNK: + return LANDLOCK_ACCESS_FS_MAKE_SYM; + case 0: + /* A zero mode translates to S_IFREG. */ + case S_IFREG: + return LANDLOCK_ACCESS_FS_MAKE_REG; + case S_IFDIR: + return LANDLOCK_ACCESS_FS_MAKE_DIR; + case S_IFCHR: + return LANDLOCK_ACCESS_FS_MAKE_CHAR; + case S_IFBLK: + return LANDLOCK_ACCESS_FS_MAKE_BLOCK; + case S_IFIFO: + return LANDLOCK_ACCESS_FS_MAKE_FIFO; + case S_IFSOCK: + return LANDLOCK_ACCESS_FS_MAKE_SOCK; + default: + WARN_ON_ONCE(1); + return 0; + } +} + +static inline access_mask_t maybe_remove(const struct dentry *const dentry) +{ + if (d_is_negative(dentry)) + return 0; + return d_is_dir(dentry) ? LANDLOCK_ACCESS_FS_REMOVE_DIR : + LANDLOCK_ACCESS_FS_REMOVE_FILE; +} + +/** + * collect_domain_accesses - Walk through a file path and collect accesses + * + * @domain: Domain to check against. + * @mnt_root: Last directory to check. + * @dir: Directory to start the walk from. + * @layer_masks_dom: Where to store the collected accesses. + * + * This helper is useful to begin a path walk from the @dir directory to a + * @mnt_root directory used as a mount point. This mount point is the common + * ancestor between the source and the destination of a renamed and linked + * file. While walking from @dir to @mnt_root, we record all the domain's + * allowed accesses in @layer_masks_dom. + * + * This is similar to check_access_path_dual() but much simpler because it only + * handles walking on the same mount point and only check one set of accesses. + * + * Returns: + * - true if all the domain access rights are allowed for @dir; + * - false if the walk reached @mnt_root. + */ +static bool collect_domain_accesses( + const struct landlock_ruleset *const domain, + const struct dentry *const mnt_root, struct dentry *dir, + layer_mask_t (*const layer_masks_dom)[LANDLOCK_NUM_ACCESS_FS]) +{ + unsigned long access_dom; + bool ret = false; + + if (WARN_ON_ONCE(!domain || !mnt_root || !dir || !layer_masks_dom)) + return true; + if (is_nouser_or_private(dir)) + return true; + + access_dom = init_layer_masks(domain, LANDLOCK_MASK_ACCESS_FS, + layer_masks_dom); + + dget(dir); + while (true) { + struct dentry *parent_dentry; + + /* Gets all layers allowing all domain accesses. */ + if (unmask_layers(find_rule(domain, dir), access_dom, + layer_masks_dom)) { + /* + * Stops when all handled accesses are allowed by at + * least one rule in each layer. + */ + ret = true; + break; + } + + /* We should not reach a root other than @mnt_root. */ + if (dir == mnt_root || WARN_ON_ONCE(IS_ROOT(dir))) + break; + + parent_dentry = dget_parent(dir); + dput(dir); + dir = parent_dentry; + } + dput(dir); + return ret; +} + +/** + * current_check_refer_path - Check if a rename or link action is allowed + * + * @old_dentry: File or directory requested to be moved or linked. + * @new_dir: Destination parent directory. + * @new_dentry: Destination file or directory. + * @removable: Sets to true if it is a rename operation. + * @exchange: Sets to true if it is a rename operation with RENAME_EXCHANGE. + * + * Because of its unprivileged constraints, Landlock relies on file hierarchies + * (and not only inodes) to tie access rights to files. Being able to link or + * rename a file hierarchy brings some challenges. Indeed, moving or linking a + * file (i.e. creating a new reference to an inode) can have an impact on the + * actions allowed for a set of files if it would change its parent directory + * (i.e. reparenting). + * + * To avoid trivial access right bypasses, Landlock first checks if the file or + * directory requested to be moved would gain new access rights inherited from + * its new hierarchy. Before returning any error, Landlock then checks that + * the parent source hierarchy and the destination hierarchy would allow the + * link or rename action. If it is not the case, an error with EACCES is + * returned to inform user space that there is no way to remove or create the + * requested source file type. If it should be allowed but the new inherited + * access rights would be greater than the source access rights, then the + * kernel returns an error with EXDEV. Prioritizing EACCES over EXDEV enables + * user space to abort the whole operation if there is no way to do it, or to + * manually copy the source to the destination if this remains allowed, e.g. + * because file creation is allowed on the destination directory but not direct + * linking. + * + * To achieve this goal, the kernel needs to compare two file hierarchies: the + * one identifying the source file or directory (including itself), and the + * destination one. This can be seen as a multilayer partial ordering problem. + * The kernel walks through these paths and collects in a matrix the access + * rights that are denied per layer. These matrices are then compared to see + * if the destination one has more (or the same) restrictions as the source + * one. If this is the case, the requested action will not return EXDEV, which + * doesn't mean the action is allowed. The parent hierarchy of the source + * (i.e. parent directory), and the destination hierarchy must also be checked + * to verify that they explicitly allow such action (i.e. referencing, + * creation and potentially removal rights). The kernel implementation is then + * required to rely on potentially four matrices of access rights: one for the + * source file or directory (i.e. the child), a potentially other one for the + * other source/destination (in case of RENAME_EXCHANGE), one for the source + * parent hierarchy and a last one for the destination hierarchy. These + * ephemeral matrices take some space on the stack, which limits the number of + * layers to a deemed reasonable number: 16. + * + * Returns: + * - 0 if access is allowed; + * - -EXDEV if @old_dentry would inherit new access rights from @new_dir; + * - -EACCES if file removal or creation is denied. + */ +static int current_check_refer_path(struct dentry *const old_dentry, + const struct path *const new_dir, + struct dentry *const new_dentry, + const bool removable, const bool exchange) +{ + const struct landlock_ruleset *const dom = + landlock_get_current_domain(); + bool allow_parent1, allow_parent2; + access_mask_t access_request_parent1, access_request_parent2; + struct path mnt_dir; + layer_mask_t layer_masks_parent1[LANDLOCK_NUM_ACCESS_FS], + layer_masks_parent2[LANDLOCK_NUM_ACCESS_FS]; + + if (!dom) + return 0; + if (WARN_ON_ONCE(dom->num_layers < 1)) + return -EACCES; + if (unlikely(d_is_negative(old_dentry))) + return -ENOENT; + if (exchange) { + if (unlikely(d_is_negative(new_dentry))) + return -ENOENT; + access_request_parent1 = + get_mode_access(d_backing_inode(new_dentry)->i_mode); + } else { + access_request_parent1 = 0; + } + access_request_parent2 = + get_mode_access(d_backing_inode(old_dentry)->i_mode); + if (removable) { + access_request_parent1 |= maybe_remove(old_dentry); + access_request_parent2 |= maybe_remove(new_dentry); + } + + /* The mount points are the same for old and new paths, cf. EXDEV. */ + if (old_dentry->d_parent == new_dir->dentry) { + /* + * The LANDLOCK_ACCESS_FS_REFER access right is not required + * for same-directory referer (i.e. no reparenting). + */ + access_request_parent1 = init_layer_masks( + dom, access_request_parent1 | access_request_parent2, + &layer_masks_parent1); + return check_access_path_dual(dom, new_dir, + access_request_parent1, + &layer_masks_parent1, NULL, 0, + NULL, NULL); + } + + /* Backward compatibility: no reparenting support. */ + if (!(get_handled_accesses(dom) & LANDLOCK_ACCESS_FS_REFER)) + return -EXDEV; + + access_request_parent1 |= LANDLOCK_ACCESS_FS_REFER; + access_request_parent2 |= LANDLOCK_ACCESS_FS_REFER; + + /* Saves the common mount point. */ + mnt_dir.mnt = new_dir->mnt; + mnt_dir.dentry = new_dir->mnt->mnt_root; + + /* new_dir->dentry is equal to new_dentry->d_parent */ + allow_parent1 = collect_domain_accesses(dom, mnt_dir.dentry, + old_dentry->d_parent, + &layer_masks_parent1); + allow_parent2 = collect_domain_accesses( + dom, mnt_dir.dentry, new_dir->dentry, &layer_masks_parent2); + + if (allow_parent1 && allow_parent2) + return 0; + + /* + * To be able to compare source and destination domain access rights, + * take into account the @old_dentry access rights aggregated with its + * parent access rights. This will be useful to compare with the + * destination parent access rights. + */ + return check_access_path_dual(dom, &mnt_dir, access_request_parent1, + &layer_masks_parent1, old_dentry, + access_request_parent2, + &layer_masks_parent2, + exchange ? new_dentry : NULL); +} + /* Inode hooks */ static void hook_inode_free_security(struct inode *const inode) @@ -436,8 +1009,8 @@ static void hook_sb_delete(struct super_block *const sb) if (prev_inode) iput(prev_inode); /* Waits for pending iput() in release_inode(). */ - wait_var_event(&landlock_superblock(sb)->inode_refs, !atomic_long_read( - &landlock_superblock(sb)->inode_refs)); + wait_var_event(&landlock_superblock(sb)->inode_refs, + !atomic_long_read(&landlock_superblock(sb)->inode_refs)); } /* @@ -459,8 +1032,8 @@ static void hook_sb_delete(struct super_block *const sb) * a dedicated user space option would be required (e.g. as a ruleset flag). */ static int hook_sb_mount(const char *const dev_name, - const struct path *const path, const char *const type, - const unsigned long flags, void *const data) + const struct path *const path, const char *const type, + const unsigned long flags, void *const data) { if (!landlock_get_current_domain()) return 0; @@ -468,7 +1041,7 @@ static int hook_sb_mount(const char *const dev_name, } static int hook_move_mount(const struct path *const from_path, - const struct path *const to_path) + const struct path *const to_path) { if (!landlock_get_current_domain()) return 0; @@ -502,7 +1075,7 @@ static int hook_sb_remount(struct super_block *const sb, void *const mnt_opts) * view of the filesystem. */ static int hook_sb_pivotroot(const struct path *const old_path, - const struct path *const new_path) + const struct path *const new_path) { if (!landlock_get_current_domain()) return 0; @@ -511,97 +1084,34 @@ static int hook_sb_pivotroot(const struct path *const old_path, /* Path hooks */ -static inline u32 get_mode_access(const umode_t mode) -{ - switch (mode & S_IFMT) { - case S_IFLNK: - return LANDLOCK_ACCESS_FS_MAKE_SYM; - case 0: - /* A zero mode translates to S_IFREG. */ - case S_IFREG: - return LANDLOCK_ACCESS_FS_MAKE_REG; - case S_IFDIR: - return LANDLOCK_ACCESS_FS_MAKE_DIR; - case S_IFCHR: - return LANDLOCK_ACCESS_FS_MAKE_CHAR; - case S_IFBLK: - return LANDLOCK_ACCESS_FS_MAKE_BLOCK; - case S_IFIFO: - return LANDLOCK_ACCESS_FS_MAKE_FIFO; - case S_IFSOCK: - return LANDLOCK_ACCESS_FS_MAKE_SOCK; - default: - WARN_ON_ONCE(1); - return 0; - } -} - -/* - * Creating multiple links or renaming may lead to privilege escalations if not - * handled properly. Indeed, we must be sure that the source doesn't gain more - * privileges by being accessible from the destination. This is getting more - * complex when dealing with multiple layers. The whole picture can be seen as - * a multilayer partial ordering problem. A future version of Landlock will - * deal with that. - */ static int hook_path_link(struct dentry *const old_dentry, - const struct path *const new_dir, - struct dentry *const new_dentry) -{ - const struct landlock_ruleset *const dom = - landlock_get_current_domain(); - - if (!dom) - return 0; - /* The mount points are the same for old and new paths, cf. EXDEV. */ - if (old_dentry->d_parent != new_dir->dentry) - /* Gracefully forbids reparenting. */ - return -EXDEV; - if (unlikely(d_is_negative(old_dentry))) - return -ENOENT; - return check_access_path(dom, new_dir, - get_mode_access(d_backing_inode(old_dentry)->i_mode)); -} - -static inline u32 maybe_remove(const struct dentry *const dentry) + const struct path *const new_dir, + struct dentry *const new_dentry) { - if (d_is_negative(dentry)) - return 0; - return d_is_dir(dentry) ? LANDLOCK_ACCESS_FS_REMOVE_DIR : - LANDLOCK_ACCESS_FS_REMOVE_FILE; + return current_check_refer_path(old_dentry, new_dir, new_dentry, false, + false); } static int hook_path_rename(const struct path *const old_dir, - struct dentry *const old_dentry, - const struct path *const new_dir, - struct dentry *const new_dentry) + struct dentry *const old_dentry, + const struct path *const new_dir, + struct dentry *const new_dentry, + const unsigned int flags) { - const struct landlock_ruleset *const dom = - landlock_get_current_domain(); - - if (!dom) - return 0; - /* The mount points are the same for old and new paths, cf. EXDEV. */ - if (old_dir->dentry != new_dir->dentry) - /* Gracefully forbids reparenting. */ - return -EXDEV; - if (unlikely(d_is_negative(old_dentry))) - return -ENOENT; - /* RENAME_EXCHANGE is handled because directories are the same. */ - return check_access_path(dom, old_dir, maybe_remove(old_dentry) | - maybe_remove(new_dentry) | - get_mode_access(d_backing_inode(old_dentry)->i_mode)); + /* old_dir refers to old_dentry->d_parent and new_dir->mnt */ + return current_check_refer_path(old_dentry, new_dir, new_dentry, true, + !!(flags & RENAME_EXCHANGE)); } static int hook_path_mkdir(const struct path *const dir, - struct dentry *const dentry, const umode_t mode) + struct dentry *const dentry, const umode_t mode) { return current_check_access_path(dir, LANDLOCK_ACCESS_FS_MAKE_DIR); } static int hook_path_mknod(const struct path *const dir, - struct dentry *const dentry, const umode_t mode, - const unsigned int dev) + struct dentry *const dentry, const umode_t mode, + const unsigned int dev) { const struct landlock_ruleset *const dom = landlock_get_current_domain(); @@ -612,28 +1122,29 @@ static int hook_path_mknod(const struct path *const dir, } static int hook_path_symlink(const struct path *const dir, - struct dentry *const dentry, const char *const old_name) + struct dentry *const dentry, + const char *const old_name) { return current_check_access_path(dir, LANDLOCK_ACCESS_FS_MAKE_SYM); } static int hook_path_unlink(const struct path *const dir, - struct dentry *const dentry) + struct dentry *const dentry) { return current_check_access_path(dir, LANDLOCK_ACCESS_FS_REMOVE_FILE); } static int hook_path_rmdir(const struct path *const dir, - struct dentry *const dentry) + struct dentry *const dentry) { return current_check_access_path(dir, LANDLOCK_ACCESS_FS_REMOVE_DIR); } /* File hooks */ -static inline u32 get_file_access(const struct file *const file) +static inline access_mask_t get_file_access(const struct file *const file) { - u32 access = 0; + access_mask_t access = 0; if (file->f_mode & FMODE_READ) { /* A directory can only be opened in read mode. */ @@ -688,5 +1199,5 @@ static struct security_hook_list landlock_hooks[] __lsm_ro_after_init = { __init void landlock_add_fs_hooks(void) { security_add_hooks(landlock_hooks, ARRAY_SIZE(landlock_hooks), - LANDLOCK_NAME); + LANDLOCK_NAME); } diff --git a/security/landlock/fs.h b/security/landlock/fs.h index 187284b421c9..8db7acf9109b 100644 --- a/security/landlock/fs.h +++ b/security/landlock/fs.h @@ -50,14 +50,14 @@ struct landlock_superblock_security { atomic_long_t inode_refs; }; -static inline struct landlock_inode_security *landlock_inode( - const struct inode *const inode) +static inline struct landlock_inode_security * +landlock_inode(const struct inode *const inode) { return inode->i_security + landlock_blob_sizes.lbs_inode; } -static inline struct landlock_superblock_security *landlock_superblock( - const struct super_block *const superblock) +static inline struct landlock_superblock_security * +landlock_superblock(const struct super_block *const superblock) { return superblock->s_security + landlock_blob_sizes.lbs_superblock; } @@ -65,6 +65,7 @@ static inline struct landlock_superblock_security *landlock_superblock( __init void landlock_add_fs_hooks(void); int landlock_append_fs_rule(struct landlock_ruleset *const ruleset, - const struct path *const path, u32 access_hierarchy); + const struct path *const path, + access_mask_t access_hierarchy); #endif /* _SECURITY_LANDLOCK_FS_H */ diff --git a/security/landlock/limits.h b/security/landlock/limits.h index 2a0a1095ee27..b54184ab9439 100644 --- a/security/landlock/limits.h +++ b/security/landlock/limits.h @@ -9,13 +9,19 @@ #ifndef _SECURITY_LANDLOCK_LIMITS_H #define _SECURITY_LANDLOCK_LIMITS_H +#include <linux/bitops.h> #include <linux/limits.h> #include <uapi/linux/landlock.h> -#define LANDLOCK_MAX_NUM_LAYERS 64 +/* clang-format off */ + +#define LANDLOCK_MAX_NUM_LAYERS 16 #define LANDLOCK_MAX_NUM_RULES U32_MAX -#define LANDLOCK_LAST_ACCESS_FS LANDLOCK_ACCESS_FS_MAKE_SYM +#define LANDLOCK_LAST_ACCESS_FS LANDLOCK_ACCESS_FS_REFER #define LANDLOCK_MASK_ACCESS_FS ((LANDLOCK_LAST_ACCESS_FS << 1) - 1) +#define LANDLOCK_NUM_ACCESS_FS __const_hweight64(LANDLOCK_MASK_ACCESS_FS) + +/* clang-format on */ #endif /* _SECURITY_LANDLOCK_LIMITS_H */ diff --git a/security/landlock/object.c b/security/landlock/object.c index d674fdf9ff04..1f50612f0185 100644 --- a/security/landlock/object.c +++ b/security/landlock/object.c @@ -17,9 +17,9 @@ #include "object.h" -struct landlock_object *landlock_create_object( - const struct landlock_object_underops *const underops, - void *const underobj) +struct landlock_object * +landlock_create_object(const struct landlock_object_underops *const underops, + void *const underobj) { struct landlock_object *new_object; diff --git a/security/landlock/object.h b/security/landlock/object.h index 3f80674c6c8d..5f28c35e8aa8 100644 --- a/security/landlock/object.h +++ b/security/landlock/object.h @@ -76,9 +76,9 @@ struct landlock_object { }; }; -struct landlock_object *landlock_create_object( - const struct landlock_object_underops *const underops, - void *const underobj); +struct landlock_object * +landlock_create_object(const struct landlock_object_underops *const underops, + void *const underobj); void landlock_put_object(struct landlock_object *const object); diff --git a/security/landlock/ptrace.c b/security/landlock/ptrace.c index f55b82446de2..4c5b9cd71286 100644 --- a/security/landlock/ptrace.c +++ b/security/landlock/ptrace.c @@ -30,7 +30,7 @@ * means a subset of) the @child domain. */ static bool domain_scope_le(const struct landlock_ruleset *const parent, - const struct landlock_ruleset *const child) + const struct landlock_ruleset *const child) { const struct landlock_hierarchy *walker; @@ -48,7 +48,7 @@ static bool domain_scope_le(const struct landlock_ruleset *const parent, } static bool task_is_scoped(const struct task_struct *const parent, - const struct task_struct *const child) + const struct task_struct *const child) { bool is_scoped; const struct landlock_ruleset *dom_parent, *dom_child; @@ -62,7 +62,7 @@ static bool task_is_scoped(const struct task_struct *const parent, } static int task_ptrace(const struct task_struct *const parent, - const struct task_struct *const child) + const struct task_struct *const child) { /* Quick return for non-landlocked tasks. */ if (!landlocked(parent)) @@ -86,7 +86,7 @@ static int task_ptrace(const struct task_struct *const parent, * granted, -errno if denied. */ static int hook_ptrace_access_check(struct task_struct *const child, - const unsigned int mode) + const unsigned int mode) { return task_ptrace(current, child); } @@ -116,5 +116,5 @@ static struct security_hook_list landlock_hooks[] __lsm_ro_after_init = { __init void landlock_add_ptrace_hooks(void) { security_add_hooks(landlock_hooks, ARRAY_SIZE(landlock_hooks), - LANDLOCK_NAME); + LANDLOCK_NAME); } diff --git a/security/landlock/ruleset.c b/security/landlock/ruleset.c index ec72b9262bf3..996484f98bfd 100644 --- a/security/landlock/ruleset.c +++ b/security/landlock/ruleset.c @@ -28,8 +28,9 @@ static struct landlock_ruleset *create_ruleset(const u32 num_layers) { struct landlock_ruleset *new_ruleset; - new_ruleset = kzalloc(struct_size(new_ruleset, fs_access_masks, - num_layers), GFP_KERNEL_ACCOUNT); + new_ruleset = + kzalloc(struct_size(new_ruleset, fs_access_masks, num_layers), + GFP_KERNEL_ACCOUNT); if (!new_ruleset) return ERR_PTR(-ENOMEM); refcount_set(&new_ruleset->usage, 1); @@ -44,7 +45,8 @@ static struct landlock_ruleset *create_ruleset(const u32 num_layers) return new_ruleset; } -struct landlock_ruleset *landlock_create_ruleset(const u32 fs_access_mask) +struct landlock_ruleset * +landlock_create_ruleset(const access_mask_t fs_access_mask) { struct landlock_ruleset *new_ruleset; @@ -66,11 +68,10 @@ static void build_check_rule(void) BUILD_BUG_ON(rule.num_layers < LANDLOCK_MAX_NUM_LAYERS); } -static struct landlock_rule *create_rule( - struct landlock_object *const object, - const struct landlock_layer (*const layers)[], - const u32 num_layers, - const struct landlock_layer *const new_layer) +static struct landlock_rule * +create_rule(struct landlock_object *const object, + const struct landlock_layer (*const layers)[], const u32 num_layers, + const struct landlock_layer *const new_layer) { struct landlock_rule *new_rule; u32 new_num_layers; @@ -85,7 +86,7 @@ static struct landlock_rule *create_rule( new_num_layers = num_layers; } new_rule = kzalloc(struct_size(new_rule, layers, new_num_layers), - GFP_KERNEL_ACCOUNT); + GFP_KERNEL_ACCOUNT); if (!new_rule) return ERR_PTR(-ENOMEM); RB_CLEAR_NODE(&new_rule->node); @@ -94,7 +95,7 @@ static struct landlock_rule *create_rule( new_rule->num_layers = new_num_layers; /* Copies the original layer stack. */ memcpy(new_rule->layers, layers, - flex_array_size(new_rule, layers, num_layers)); + flex_array_size(new_rule, layers, num_layers)); if (new_layer) /* Adds a copy of @new_layer on the layer stack. */ new_rule->layers[new_rule->num_layers - 1] = *new_layer; @@ -142,9 +143,9 @@ static void build_check_ruleset(void) * access rights. */ static int insert_rule(struct landlock_ruleset *const ruleset, - struct landlock_object *const object, - const struct landlock_layer (*const layers)[], - size_t num_layers) + struct landlock_object *const object, + const struct landlock_layer (*const layers)[], + size_t num_layers) { struct rb_node **walker_node; struct rb_node *parent_node = NULL; @@ -156,8 +157,8 @@ static int insert_rule(struct landlock_ruleset *const ruleset, return -ENOENT; walker_node = &(ruleset->root.rb_node); while (*walker_node) { - struct landlock_rule *const this = rb_entry(*walker_node, - struct landlock_rule, node); + struct landlock_rule *const this = + rb_entry(*walker_node, struct landlock_rule, node); if (this->object != object) { parent_node = *walker_node; @@ -194,7 +195,7 @@ static int insert_rule(struct landlock_ruleset *const ruleset, * ruleset and a domain. */ new_rule = create_rule(object, &this->layers, this->num_layers, - &(*layers)[0]); + &(*layers)[0]); if (IS_ERR(new_rule)) return PTR_ERR(new_rule); rb_replace_node(&this->node, &new_rule->node, &ruleset->root); @@ -228,13 +229,14 @@ static void build_check_layer(void) /* @ruleset must be locked by the caller. */ int landlock_insert_rule(struct landlock_ruleset *const ruleset, - struct landlock_object *const object, const u32 access) + struct landlock_object *const object, + const access_mask_t access) { - struct landlock_layer layers[] = {{ + struct landlock_layer layers[] = { { .access = access, /* When @level is zero, insert_rule() extends @ruleset. */ .level = 0, - }}; + } }; build_check_layer(); return insert_rule(ruleset, object, &layers, ARRAY_SIZE(layers)); @@ -257,7 +259,7 @@ static void put_hierarchy(struct landlock_hierarchy *hierarchy) } static int merge_ruleset(struct landlock_ruleset *const dst, - struct landlock_ruleset *const src) + struct landlock_ruleset *const src) { struct landlock_rule *walker_rule, *next_rule; int err = 0; @@ -282,11 +284,11 @@ static int merge_ruleset(struct landlock_ruleset *const dst, dst->fs_access_masks[dst->num_layers - 1] = src->fs_access_masks[0]; /* Merges the @src tree. */ - rbtree_postorder_for_each_entry_safe(walker_rule, next_rule, - &src->root, node) { - struct landlock_layer layers[] = {{ + rbtree_postorder_for_each_entry_safe(walker_rule, next_rule, &src->root, + node) { + struct landlock_layer layers[] = { { .level = dst->num_layers, - }}; + } }; if (WARN_ON_ONCE(walker_rule->num_layers != 1)) { err = -EINVAL; @@ -298,7 +300,7 @@ static int merge_ruleset(struct landlock_ruleset *const dst, } layers[0].access = walker_rule->layers[0].access; err = insert_rule(dst, walker_rule->object, &layers, - ARRAY_SIZE(layers)); + ARRAY_SIZE(layers)); if (err) goto out_unlock; } @@ -310,7 +312,7 @@ out_unlock: } static int inherit_ruleset(struct landlock_ruleset *const parent, - struct landlock_ruleset *const child) + struct landlock_ruleset *const child) { struct landlock_rule *walker_rule, *next_rule; int err = 0; @@ -325,9 +327,10 @@ static int inherit_ruleset(struct landlock_ruleset *const parent, /* Copies the @parent tree. */ rbtree_postorder_for_each_entry_safe(walker_rule, next_rule, - &parent->root, node) { + &parent->root, node) { err = insert_rule(child, walker_rule->object, - &walker_rule->layers, walker_rule->num_layers); + &walker_rule->layers, + walker_rule->num_layers); if (err) goto out_unlock; } @@ -338,7 +341,7 @@ static int inherit_ruleset(struct landlock_ruleset *const parent, } /* Copies the parent layer stack and leaves a space for the new layer. */ memcpy(child->fs_access_masks, parent->fs_access_masks, - flex_array_size(parent, fs_access_masks, parent->num_layers)); + flex_array_size(parent, fs_access_masks, parent->num_layers)); if (WARN_ON_ONCE(!parent->hierarchy)) { err = -EINVAL; @@ -358,8 +361,7 @@ static void free_ruleset(struct landlock_ruleset *const ruleset) struct landlock_rule *freeme, *next; might_sleep(); - rbtree_postorder_for_each_entry_safe(freeme, next, &ruleset->root, - node) + rbtree_postorder_for_each_entry_safe(freeme, next, &ruleset->root, node) free_rule(freeme); put_hierarchy(ruleset->hierarchy); kfree(ruleset); @@ -397,9 +399,9 @@ void landlock_put_ruleset_deferred(struct landlock_ruleset *const ruleset) * Returns the intersection of @parent and @ruleset, or returns @parent if * @ruleset is empty, or returns a duplicate of @ruleset if @parent is empty. */ -struct landlock_ruleset *landlock_merge_ruleset( - struct landlock_ruleset *const parent, - struct landlock_ruleset *const ruleset) +struct landlock_ruleset * +landlock_merge_ruleset(struct landlock_ruleset *const parent, + struct landlock_ruleset *const ruleset) { struct landlock_ruleset *new_dom; u32 num_layers; @@ -421,8 +423,8 @@ struct landlock_ruleset *landlock_merge_ruleset( new_dom = create_ruleset(num_layers); if (IS_ERR(new_dom)) return new_dom; - new_dom->hierarchy = kzalloc(sizeof(*new_dom->hierarchy), - GFP_KERNEL_ACCOUNT); + new_dom->hierarchy = + kzalloc(sizeof(*new_dom->hierarchy), GFP_KERNEL_ACCOUNT); if (!new_dom->hierarchy) { err = -ENOMEM; goto out_put_dom; @@ -449,9 +451,9 @@ out_put_dom: /* * The returned access has the same lifetime as @ruleset. */ -const struct landlock_rule *landlock_find_rule( - const struct landlock_ruleset *const ruleset, - const struct landlock_object *const object) +const struct landlock_rule * +landlock_find_rule(const struct landlock_ruleset *const ruleset, + const struct landlock_object *const object) { const struct rb_node *node; @@ -459,8 +461,8 @@ const struct landlock_rule *landlock_find_rule( return NULL; node = ruleset->root.rb_node; while (node) { - struct landlock_rule *this = rb_entry(node, - struct landlock_rule, node); + struct landlock_rule *this = + rb_entry(node, struct landlock_rule, node); if (this->object == object) return this; diff --git a/security/landlock/ruleset.h b/security/landlock/ruleset.h index 2d3ed7ec5a0a..d43231b783e4 100644 --- a/security/landlock/ruleset.h +++ b/security/landlock/ruleset.h @@ -9,13 +9,26 @@ #ifndef _SECURITY_LANDLOCK_RULESET_H #define _SECURITY_LANDLOCK_RULESET_H +#include <linux/bitops.h> +#include <linux/build_bug.h> #include <linux/mutex.h> #include <linux/rbtree.h> #include <linux/refcount.h> #include <linux/workqueue.h> +#include "limits.h" #include "object.h" +typedef u16 access_mask_t; +/* Makes sure all filesystem access rights can be stored. */ +static_assert(BITS_PER_TYPE(access_mask_t) >= LANDLOCK_NUM_ACCESS_FS); +/* Makes sure for_each_set_bit() and for_each_clear_bit() calls are OK. */ +static_assert(sizeof(unsigned long) >= sizeof(access_mask_t)); + +typedef u16 layer_mask_t; +/* Makes sure all layers can be checked. */ +static_assert(BITS_PER_TYPE(layer_mask_t) >= LANDLOCK_MAX_NUM_LAYERS); + /** * struct landlock_layer - Access rights for a given layer */ @@ -28,7 +41,7 @@ struct landlock_layer { * @access: Bitfield of allowed actions on the kernel object. They are * relative to the object type (e.g. %LANDLOCK_ACTION_FS_READ). */ - u16 access; + access_mask_t access; }; /** @@ -135,26 +148,28 @@ struct landlock_ruleset { * layers are set once and never changed for the * lifetime of the ruleset. */ - u16 fs_access_masks[]; + access_mask_t fs_access_masks[]; }; }; }; -struct landlock_ruleset *landlock_create_ruleset(const u32 fs_access_mask); +struct landlock_ruleset * +landlock_create_ruleset(const access_mask_t fs_access_mask); void landlock_put_ruleset(struct landlock_ruleset *const ruleset); void landlock_put_ruleset_deferred(struct landlock_ruleset *const ruleset); int landlock_insert_rule(struct landlock_ruleset *const ruleset, - struct landlock_object *const object, const u32 access); + struct landlock_object *const object, + const access_mask_t access); -struct landlock_ruleset *landlock_merge_ruleset( - struct landlock_ruleset *const parent, - struct landlock_ruleset *const ruleset); +struct landlock_ruleset * +landlock_merge_ruleset(struct landlock_ruleset *const parent, + struct landlock_ruleset *const ruleset); -const struct landlock_rule *landlock_find_rule( - const struct landlock_ruleset *const ruleset, - const struct landlock_object *const object); +const struct landlock_rule * +landlock_find_rule(const struct landlock_ruleset *const ruleset, + const struct landlock_object *const object); static inline void landlock_get_ruleset(struct landlock_ruleset *const ruleset) { diff --git a/security/landlock/syscalls.c b/security/landlock/syscalls.c index 7e27ce394020..735a0865ea11 100644 --- a/security/landlock/syscalls.c +++ b/security/landlock/syscalls.c @@ -43,9 +43,10 @@ * @src: User space pointer or NULL. * @usize: (Alleged) size of the data pointed to by @src. */ -static __always_inline int copy_min_struct_from_user(void *const dst, - const size_t ksize, const size_t ksize_min, - const void __user *const src, const size_t usize) +static __always_inline int +copy_min_struct_from_user(void *const dst, const size_t ksize, + const size_t ksize_min, const void __user *const src, + const size_t usize) { /* Checks buffer inconsistencies. */ BUILD_BUG_ON(!dst); @@ -93,7 +94,7 @@ static void build_check_abi(void) /* Ruleset handling */ static int fop_ruleset_release(struct inode *const inode, - struct file *const filp) + struct file *const filp) { struct landlock_ruleset *ruleset = filp->private_data; @@ -102,15 +103,15 @@ static int fop_ruleset_release(struct inode *const inode, } static ssize_t fop_dummy_read(struct file *const filp, char __user *const buf, - const size_t size, loff_t *const ppos) + const size_t size, loff_t *const ppos) { /* Dummy handler to enable FMODE_CAN_READ. */ return -EINVAL; } static ssize_t fop_dummy_write(struct file *const filp, - const char __user *const buf, const size_t size, - loff_t *const ppos) + const char __user *const buf, const size_t size, + loff_t *const ppos) { /* Dummy handler to enable FMODE_CAN_WRITE. */ return -EINVAL; @@ -128,7 +129,7 @@ static const struct file_operations ruleset_fops = { .write = fop_dummy_write, }; -#define LANDLOCK_ABI_VERSION 1 +#define LANDLOCK_ABI_VERSION 2 /** * sys_landlock_create_ruleset - Create a new ruleset @@ -168,22 +169,23 @@ SYSCALL_DEFINE3(landlock_create_ruleset, return -EOPNOTSUPP; if (flags) { - if ((flags == LANDLOCK_CREATE_RULESET_VERSION) - && !attr && !size) + if ((flags == LANDLOCK_CREATE_RULESET_VERSION) && !attr && + !size) return LANDLOCK_ABI_VERSION; return -EINVAL; } /* Copies raw user space buffer. */ err = copy_min_struct_from_user(&ruleset_attr, sizeof(ruleset_attr), - offsetofend(typeof(ruleset_attr), handled_access_fs), - attr, size); + offsetofend(typeof(ruleset_attr), + handled_access_fs), + attr, size); if (err) return err; /* Checks content (and 32-bits cast). */ if ((ruleset_attr.handled_access_fs | LANDLOCK_MASK_ACCESS_FS) != - LANDLOCK_MASK_ACCESS_FS) + LANDLOCK_MASK_ACCESS_FS) return -EINVAL; /* Checks arguments and transforms to kernel struct. */ @@ -193,7 +195,7 @@ SYSCALL_DEFINE3(landlock_create_ruleset, /* Creates anonymous FD referring to the ruleset. */ ruleset_fd = anon_inode_getfd("[landlock-ruleset]", &ruleset_fops, - ruleset, O_RDWR | O_CLOEXEC); + ruleset, O_RDWR | O_CLOEXEC); if (ruleset_fd < 0) landlock_put_ruleset(ruleset); return ruleset_fd; @@ -204,7 +206,7 @@ SYSCALL_DEFINE3(landlock_create_ruleset, * landlock_put_ruleset() on the return value. */ static struct landlock_ruleset *get_ruleset_from_fd(const int fd, - const fmode_t mode) + const fmode_t mode) { struct fd ruleset_f; struct landlock_ruleset *ruleset; @@ -244,8 +246,8 @@ static int get_path_from_fd(const s32 fd, struct path *const path) struct fd f; int err = 0; - BUILD_BUG_ON(!__same_type(fd, - ((struct landlock_path_beneath_attr *)NULL)->parent_fd)); + BUILD_BUG_ON(!__same_type( + fd, ((struct landlock_path_beneath_attr *)NULL)->parent_fd)); /* Handles O_PATH. */ f = fdget_raw(fd); @@ -257,10 +259,10 @@ static int get_path_from_fd(const s32 fd, struct path *const path) * pipefs). */ if ((f.file->f_op == &ruleset_fops) || - (f.file->f_path.mnt->mnt_flags & MNT_INTERNAL) || - (f.file->f_path.dentry->d_sb->s_flags & SB_NOUSER) || - d_is_negative(f.file->f_path.dentry) || - IS_PRIVATE(d_backing_inode(f.file->f_path.dentry))) { + (f.file->f_path.mnt->mnt_flags & MNT_INTERNAL) || + (f.file->f_path.dentry->d_sb->s_flags & SB_NOUSER) || + d_is_negative(f.file->f_path.dentry) || + IS_PRIVATE(d_backing_inode(f.file->f_path.dentry))) { err = -EBADFD; goto out_fdput; } @@ -290,19 +292,18 @@ out_fdput: * * - EOPNOTSUPP: Landlock is supported by the kernel but disabled at boot time; * - EINVAL: @flags is not 0, or inconsistent access in the rule (i.e. - * &landlock_path_beneath_attr.allowed_access is not a subset of the rule's - * accesses); + * &landlock_path_beneath_attr.allowed_access is not a subset of the + * ruleset handled accesses); * - ENOMSG: Empty accesses (e.g. &landlock_path_beneath_attr.allowed_access); * - EBADF: @ruleset_fd is not a file descriptor for the current thread, or a * member of @rule_attr is not a file descriptor as expected; * - EBADFD: @ruleset_fd is not a ruleset file descriptor, or a member of - * @rule_attr is not the expected file descriptor type (e.g. file open - * without O_PATH); + * @rule_attr is not the expected file descriptor type; * - EPERM: @ruleset_fd has no write access to the underlying ruleset; * - EFAULT: @rule_attr inconsistency. */ -SYSCALL_DEFINE4(landlock_add_rule, - const int, ruleset_fd, const enum landlock_rule_type, rule_type, +SYSCALL_DEFINE4(landlock_add_rule, const int, ruleset_fd, + const enum landlock_rule_type, rule_type, const void __user *const, rule_attr, const __u32, flags) { struct landlock_path_beneath_attr path_beneath_attr; @@ -317,20 +318,24 @@ SYSCALL_DEFINE4(landlock_add_rule, if (flags) return -EINVAL; - if (rule_type != LANDLOCK_RULE_PATH_BENEATH) - return -EINVAL; - - /* Copies raw user space buffer, only one type for now. */ - res = copy_from_user(&path_beneath_attr, rule_attr, - sizeof(path_beneath_attr)); - if (res) - return -EFAULT; - /* Gets and checks the ruleset. */ ruleset = get_ruleset_from_fd(ruleset_fd, FMODE_CAN_WRITE); if (IS_ERR(ruleset)) return PTR_ERR(ruleset); + if (rule_type != LANDLOCK_RULE_PATH_BENEATH) { + err = -EINVAL; + goto out_put_ruleset; + } + + /* Copies raw user space buffer, only one type for now. */ + res = copy_from_user(&path_beneath_attr, rule_attr, + sizeof(path_beneath_attr)); + if (res) { + err = -EFAULT; + goto out_put_ruleset; + } + /* * Informs about useless rule: empty allowed_access (i.e. deny rules) * are ignored in path walks. @@ -344,7 +349,7 @@ SYSCALL_DEFINE4(landlock_add_rule, * (ruleset->fs_access_masks[0] is automatically upgraded to 64-bits). */ if ((path_beneath_attr.allowed_access | ruleset->fs_access_masks[0]) != - ruleset->fs_access_masks[0]) { + ruleset->fs_access_masks[0]) { err = -EINVAL; goto out_put_ruleset; } @@ -356,7 +361,7 @@ SYSCALL_DEFINE4(landlock_add_rule, /* Imports the new rule. */ err = landlock_append_fs_rule(ruleset, &path, - path_beneath_attr.allowed_access); + path_beneath_attr.allowed_access); path_put(&path); out_put_ruleset: @@ -389,8 +394,8 @@ out_put_ruleset: * - E2BIG: The maximum number of stacked rulesets is reached for the current * thread. */ -SYSCALL_DEFINE2(landlock_restrict_self, - const int, ruleset_fd, const __u32, flags) +SYSCALL_DEFINE2(landlock_restrict_self, const int, ruleset_fd, const __u32, + flags) { struct landlock_ruleset *new_dom, *ruleset; struct cred *new_cred; @@ -400,18 +405,18 @@ SYSCALL_DEFINE2(landlock_restrict_self, if (!landlock_initialized) return -EOPNOTSUPP; - /* No flag for now. */ - if (flags) - return -EINVAL; - /* * Similar checks as for seccomp(2), except that an -EPERM may be * returned. */ if (!task_no_new_privs(current) && - !ns_capable_noaudit(current_user_ns(), CAP_SYS_ADMIN)) + !ns_capable_noaudit(current_user_ns(), CAP_SYS_ADMIN)) return -EPERM; + /* No flag for now. */ + if (flags) + return -EINVAL; + /* Gets and checks the ruleset. */ ruleset = get_ruleset_from_fd(ruleset_fd, FMODE_CAN_READ); if (IS_ERR(ruleset)) diff --git a/security/loadpin/loadpin.c b/security/loadpin/loadpin.c index b12f7d986b1e..ad4e6756c038 100644 --- a/security/loadpin/loadpin.c +++ b/security/loadpin/loadpin.c @@ -78,11 +78,8 @@ static void check_pinning_enforcement(struct super_block *mnt_sb) * device, allow sysctl to change modes for testing. */ if (mnt_sb->s_bdev) { - char bdev[BDEVNAME_SIZE]; - ro = bdev_read_only(mnt_sb->s_bdev); - bdevname(mnt_sb->s_bdev, bdev); - pr_info("%s (%u:%u): %s\n", bdev, + pr_info("%pg (%u:%u): %s\n", mnt_sb->s_bdev, MAJOR(mnt_sb->s_bdev->bd_dev), MINOR(mnt_sb->s_bdev->bd_dev), ro ? "read-only" : "writable"); diff --git a/security/lsm_audit.c b/security/lsm_audit.c index 1897cbf6fc69..78a278f28e49 100644 --- a/security/lsm_audit.c +++ b/security/lsm_audit.c @@ -433,6 +433,9 @@ static void dump_common_audit_data(struct audit_buffer *ab, audit_log_format(ab, " lockdown_reason=\"%s\"", lockdown_reasons[a->u.reason]); break; + case LSM_AUDIT_DATA_ANONINODE: + audit_log_format(ab, " anonclass=%s", a->u.anonclass); + break; } /* switch (a->type) */ } diff --git a/security/security.c b/security/security.c index b7cf5cbfdc67..188b8f782220 100644 --- a/security/security.c +++ b/security/security.c @@ -59,10 +59,12 @@ const char *const lockdown_reasons[LOCKDOWN_CONFIDENTIALITY_MAX+1] = { [LOCKDOWN_DEBUGFS] = "debugfs access", [LOCKDOWN_XMON_WR] = "xmon write access", [LOCKDOWN_BPF_WRITE_USER] = "use of bpf to write user RAM", + [LOCKDOWN_DBG_WRITE_KERNEL] = "use of kgdb/kdb to write kernel RAM", [LOCKDOWN_INTEGRITY_MAX] = "integrity", [LOCKDOWN_KCORE] = "/proc/kcore access", [LOCKDOWN_KPROBES] = "use of kprobes", [LOCKDOWN_BPF_READ_KERNEL] = "use of bpf to read kernel RAM", + [LOCKDOWN_DBG_READ_KERNEL] = "use of kgdb/kdb to read kernel RAM", [LOCKDOWN_PERF] = "unsafe use of perf", [LOCKDOWN_TRACEFS] = "use of tracefs", [LOCKDOWN_XMON_RW] = "xmon read and write access", @@ -365,13 +367,12 @@ static void __init ordered_lsm_init(void) int __init early_security_init(void) { - int i; - struct hlist_head *list = (struct hlist_head *) &security_hook_heads; struct lsm_info *lsm; - for (i = 0; i < sizeof(security_hook_heads) / sizeof(struct hlist_head); - i++) - INIT_HLIST_HEAD(&list[i]); +#define LSM_HOOK(RET, DEFAULT, NAME, ...) \ + INIT_HLIST_HEAD(&security_hook_heads.NAME); +#include "linux/lsm_hook_defs.h" +#undef LSM_HOOK for (lsm = __start_early_lsm_info; lsm < __end_early_lsm_info; lsm++) { if (!lsm->enabled) @@ -478,7 +479,7 @@ static int lsm_append(const char *new, char **result) * Each LSM has to register its hooks with the infrastructure. */ void __init security_add_hooks(struct security_hook_list *hooks, int count, - char *lsm) + const char *lsm) { int i; @@ -1197,15 +1198,8 @@ int security_path_rename(const struct path *old_dir, struct dentry *old_dentry, (d_is_positive(new_dentry) && IS_PRIVATE(d_backing_inode(new_dentry))))) return 0; - if (flags & RENAME_EXCHANGE) { - int err = call_int_hook(path_rename, 0, new_dir, new_dentry, - old_dir, old_dentry); - if (err) - return err; - } - return call_int_hook(path_rename, 0, old_dir, old_dentry, new_dir, - new_dentry); + new_dentry, flags); } EXPORT_SYMBOL(security_path_rename); diff --git a/security/selinux/avc.c b/security/selinux/avc.c index abcd9740d10f..9a43af0ebd7d 100644 --- a/security/selinux/avc.c +++ b/security/selinux/avc.c @@ -668,7 +668,7 @@ static void avc_audit_pre_callback(struct audit_buffer *ab, void *a) struct common_audit_data *ad = a; struct selinux_audit_data *sad = ad->selinux_audit_data; u32 av = sad->audited; - const char **perms; + const char *const *perms; int i, perm; audit_log_format(ab, "avc: %s ", sad->denied ? "denied" : "granted"); @@ -1059,7 +1059,7 @@ int avc_has_extended_perms(struct selinux_state *state, node = avc_lookup(state->avc, ssid, tsid, tclass); if (unlikely(!node)) { - node = avc_compute_av(state, ssid, tsid, tclass, &avd, xp_node); + avc_compute_av(state, ssid, tsid, tclass, &avd, xp_node); } else { memcpy(&avd, &node->ae.avd, sizeof(avd)); xp_node = node->ae.xp_node; @@ -1151,7 +1151,7 @@ inline int avc_has_perm_noaudit(struct selinux_state *state, node = avc_lookup(state->avc, ssid, tsid, tclass); if (unlikely(!node)) - node = avc_compute_av(state, ssid, tsid, tclass, avd, &xp_node); + avc_compute_av(state, ssid, tsid, tclass, avd, &xp_node); else memcpy(avd, &node->ae.avd, sizeof(*avd)); diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index e9e959343de9..beceb89f68d9 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -145,7 +145,7 @@ static int __init checkreqprot_setup(char *str) if (!kstrtoul(str, 0, &checkreqprot)) { selinux_checkreqprot_boot = checkreqprot ? 1 : 0; if (checkreqprot) - pr_warn("SELinux: checkreqprot set to 1 via kernel parameter. This is deprecated and will be rejected in a future kernel release.\n"); + pr_err("SELinux: checkreqprot set to 1 via kernel parameter. This is deprecated and will be rejected in a future kernel release.\n"); } return 1; } @@ -2964,8 +2964,8 @@ static int selinux_inode_init_security_anon(struct inode *inode, * allowed to actually create this type of anonymous inode. */ - ad.type = LSM_AUDIT_DATA_INODE; - ad.u.inode = inode; + ad.type = LSM_AUDIT_DATA_ANONINODE; + ad.u.anonclass = name ? (const char *)name->name : "?"; return avc_has_perm(&selinux_state, tsec->sid, @@ -6487,7 +6487,6 @@ static int selinux_setprocattr(const char *name, void *value, size_t size) goto abort_change; /* Only allow single threaded processes to change context */ - error = -EPERM; if (!current_is_single_threaded()) { error = security_bounded_transition(&selinux_state, tsec->sid, sid); @@ -7294,6 +7293,8 @@ static __init int selinux_init(void) memset(&selinux_state, 0, sizeof(selinux_state)); enforcing_set(&selinux_state, selinux_enforcing_boot); + if (CONFIG_SECURITY_SELINUX_CHECKREQPROT_VALUE) + pr_err("SELinux: CONFIG_SECURITY_SELINUX_CHECKREQPROT_VALUE is non-zero. This is deprecated and will be rejected in a future kernel release.\n"); checkreqprot_set(&selinux_state, selinux_checkreqprot_boot); selinux_avc_init(&selinux_state.avc); mutex_init(&selinux_state.status_lock); diff --git a/security/selinux/include/audit.h b/security/selinux/include/audit.h index 073a3d34a0d2..1cba83d17f41 100644 --- a/security/selinux/include/audit.h +++ b/security/selinux/include/audit.h @@ -12,6 +12,9 @@ #ifndef _SELINUX_AUDIT_H #define _SELINUX_AUDIT_H +#include <linux/audit.h> +#include <linux/types.h> + /** * selinux_audit_rule_init - alloc/init an selinux audit rule structure. * @field: the field this rule refers to @@ -51,7 +54,7 @@ int selinux_audit_rule_match(u32 sid, u32 field, u32 op, void *rule); * @rule: rule to be checked * Returns 1 if there are selinux fields specified in the rule, 0 otherwise. */ -int selinux_audit_rule_known(struct audit_krule *krule); +int selinux_audit_rule_known(struct audit_krule *rule); #endif /* _SELINUX_AUDIT_H */ diff --git a/security/selinux/include/avc.h b/security/selinux/include/avc.h index 00f78be48283..2b372f98f2d7 100644 --- a/security/selinux/include/avc.h +++ b/security/selinux/include/avc.h @@ -104,6 +104,7 @@ int slow_avc_audit(struct selinux_state *state, /** * avc_audit - Audit the granting or denial of permissions. + * @state: SELinux state * @ssid: source security identifier * @tsid: target security identifier * @tclass: target security class diff --git a/security/selinux/include/avc_ss.h b/security/selinux/include/avc_ss.h index 88c384c5c09e..42912c917fd4 100644 --- a/security/selinux/include/avc_ss.h +++ b/security/selinux/include/avc_ss.h @@ -7,7 +7,7 @@ #ifndef _SELINUX_AVC_SS_H_ #define _SELINUX_AVC_SS_H_ -#include "flask.h" +#include <linux/types.h> struct selinux_avc; int avc_ss_reset(struct selinux_avc *avc, u32 seqno); @@ -18,7 +18,7 @@ struct security_class_mapping { const char *perms[sizeof(u32) * 8 + 1]; }; -extern struct security_class_mapping secclass_map[]; +extern const struct security_class_mapping secclass_map[]; #endif /* _SELINUX_AVC_SS_H_ */ diff --git a/security/selinux/include/classmap.h b/security/selinux/include/classmap.h index 35aac62a662e..ff757ae5f253 100644 --- a/security/selinux/include/classmap.h +++ b/security/selinux/include/classmap.h @@ -38,7 +38,7 @@ * Note: The name for any socket class should be suffixed by "socket", * and doesn't contain more than one substr of "socket". */ -struct security_class_mapping secclass_map[] = { +const struct security_class_mapping secclass_map[] = { { "security", { "compute_av", "compute_create", "compute_member", "check_context", "load_policy", "compute_relabel", diff --git a/security/selinux/include/ibpkey.h b/security/selinux/include/ibpkey.h index e6ac1d23320b..c992f83b0aae 100644 --- a/security/selinux/include/ibpkey.h +++ b/security/selinux/include/ibpkey.h @@ -14,6 +14,8 @@ #ifndef _SELINUX_IB_PKEY_H #define _SELINUX_IB_PKEY_H +#include <linux/types.h> + #ifdef CONFIG_SECURITY_INFINIBAND void sel_ib_pkey_flush(void); int sel_ib_pkey_sid(u64 subnet_prefix, u16 pkey, u32 *sid); diff --git a/security/selinux/include/initial_sid_to_string.h b/security/selinux/include/initial_sid_to_string.h index 5d332aeb8b6c..60820517aa43 100644 --- a/security/selinux/include/initial_sid_to_string.h +++ b/security/selinux/include/initial_sid_to_string.h @@ -1,6 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -static const char *initial_sid_to_string[] = -{ +static const char *const initial_sid_to_string[] = { NULL, "kernel", "security", diff --git a/security/selinux/include/netnode.h b/security/selinux/include/netnode.h index e3f784a85840..9b8b655a8cd3 100644 --- a/security/selinux/include/netnode.h +++ b/security/selinux/include/netnode.h @@ -17,6 +17,8 @@ #ifndef _SELINUX_NETNODE_H #define _SELINUX_NETNODE_H +#include <linux/types.h> + void sel_netnode_flush(void); int sel_netnode_sid(void *addr, u16 family, u32 *sid); diff --git a/security/selinux/include/netport.h b/security/selinux/include/netport.h index 31bc16e29cd1..9096a8289948 100644 --- a/security/selinux/include/netport.h +++ b/security/selinux/include/netport.h @@ -16,6 +16,8 @@ #ifndef _SELINUX_NETPORT_H #define _SELINUX_NETPORT_H +#include <linux/types.h> + void sel_netport_flush(void); int sel_netport_sid(u8 protocol, u16 pnum, u32 *sid); diff --git a/security/selinux/include/policycap.h b/security/selinux/include/policycap.h index 2680aa21205c..f35d3458e71d 100644 --- a/security/selinux/include/policycap.h +++ b/security/selinux/include/policycap.h @@ -16,6 +16,6 @@ enum { }; #define POLICYDB_CAP_MAX (__POLICYDB_CAP_MAX - 1) -extern const char *selinux_policycap_names[__POLICYDB_CAP_MAX]; +extern const char *const selinux_policycap_names[__POLICYDB_CAP_MAX]; #endif /* _SELINUX_POLICYCAP_H_ */ diff --git a/security/selinux/include/policycap_names.h b/security/selinux/include/policycap_names.h index 100da7d043db..2a87fc3702b8 100644 --- a/security/selinux/include/policycap_names.h +++ b/security/selinux/include/policycap_names.h @@ -5,7 +5,7 @@ #include "policycap.h" /* Policy capability names */ -const char *selinux_policycap_names[__POLICYDB_CAP_MAX] = { +const char *const selinux_policycap_names[__POLICYDB_CAP_MAX] = { "network_peer_controls", "open_perms", "extended_socket_class", diff --git a/security/selinux/include/security.h b/security/selinux/include/security.h index ace4bd13e808..393aff41d3ef 100644 --- a/security/selinux/include/security.h +++ b/security/selinux/include/security.h @@ -16,6 +16,8 @@ #include <linux/rcupdate.h> #include <linux/refcount.h> #include <linux/workqueue.h> +#include <linux/delay.h> +#include <linux/printk.h> #include "flask.h" #include "policycap.h" @@ -150,6 +152,8 @@ static inline bool checkreqprot_get(const struct selinux_state *state) static inline void checkreqprot_set(struct selinux_state *state, bool value) { + if (value) + pr_err("SELinux: https://github.com/SELinuxProject/selinux-kernel/wiki/DEPRECATE-checkreqprot\n"); WRITE_ONCE(state->checkreqprot, value); } diff --git a/security/selinux/include/xfrm.h b/security/selinux/include/xfrm.h index 74159400eeee..c75839860200 100644 --- a/security/selinux/include/xfrm.h +++ b/security/selinux/include/xfrm.h @@ -8,7 +8,9 @@ #ifndef _SELINUX_XFRM_H_ #define _SELINUX_XFRM_H_ +#include <linux/lsm_audit.h> #include <net/flow.h> +#include <net/xfrm.h> int selinux_xfrm_policy_alloc(struct xfrm_sec_ctx **ctxp, struct xfrm_user_sec_ctx *uctx, diff --git a/security/selinux/nlmsgtab.c b/security/selinux/nlmsgtab.c index d8ceee9e0d6f..2ee7b4ed43ef 100644 --- a/security/selinux/nlmsgtab.c +++ b/security/selinux/nlmsgtab.c @@ -25,8 +25,7 @@ struct nlmsg_perm { u32 perm; }; -static const struct nlmsg_perm nlmsg_route_perms[] = -{ +static const struct nlmsg_perm nlmsg_route_perms[] = { { RTM_NEWLINK, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, { RTM_DELLINK, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, { RTM_GETLINK, NETLINK_ROUTE_SOCKET__NLMSG_READ }, @@ -97,16 +96,14 @@ static const struct nlmsg_perm nlmsg_route_perms[] = { RTM_GETTUNNEL, NETLINK_ROUTE_SOCKET__NLMSG_READ }, }; -static const struct nlmsg_perm nlmsg_tcpdiag_perms[] = -{ +static const struct nlmsg_perm nlmsg_tcpdiag_perms[] = { { TCPDIAG_GETSOCK, NETLINK_TCPDIAG_SOCKET__NLMSG_READ }, { DCCPDIAG_GETSOCK, NETLINK_TCPDIAG_SOCKET__NLMSG_READ }, { SOCK_DIAG_BY_FAMILY, NETLINK_TCPDIAG_SOCKET__NLMSG_READ }, { SOCK_DESTROY, NETLINK_TCPDIAG_SOCKET__NLMSG_WRITE }, }; -static const struct nlmsg_perm nlmsg_xfrm_perms[] = -{ +static const struct nlmsg_perm nlmsg_xfrm_perms[] = { { XFRM_MSG_NEWSA, NETLINK_XFRM_SOCKET__NLMSG_WRITE }, { XFRM_MSG_DELSA, NETLINK_XFRM_SOCKET__NLMSG_WRITE }, { XFRM_MSG_GETSA, NETLINK_XFRM_SOCKET__NLMSG_READ }, @@ -134,8 +131,7 @@ static const struct nlmsg_perm nlmsg_xfrm_perms[] = { XFRM_MSG_GETDEFAULT, NETLINK_XFRM_SOCKET__NLMSG_READ }, }; -static const struct nlmsg_perm nlmsg_audit_perms[] = -{ +static const struct nlmsg_perm nlmsg_audit_perms[] = { { AUDIT_GET, NETLINK_AUDIT_SOCKET__NLMSG_READ }, { AUDIT_SET, NETLINK_AUDIT_SOCKET__NLMSG_WRITE }, { AUDIT_LIST, NETLINK_AUDIT_SOCKET__NLMSG_READPRIV }, diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c index 097c6d866ec4..8fcdd494af27 100644 --- a/security/selinux/selinuxfs.c +++ b/security/selinux/selinuxfs.c @@ -293,6 +293,8 @@ static ssize_t sel_write_disable(struct file *file, const char __user *buf, * kernel releases until eventually it is removed */ pr_err("SELinux: Runtime disable is deprecated, use selinux=0 on the kernel cmdline.\n"); + pr_err("SELinux: https://github.com/SELinuxProject/selinux-kernel/wiki/DEPRECATE-runtime-disable\n"); + ssleep(5); if (count >= PAGE_SIZE) return -ENOMEM; @@ -755,11 +757,13 @@ static ssize_t sel_write_checkreqprot(struct file *file, const char __user *buf, char comm[sizeof(current->comm)]; memcpy(comm, current->comm, sizeof(comm)); - pr_warn_once("SELinux: %s (%d) set checkreqprot to 1. This is deprecated and will be rejected in a future kernel release.\n", - comm, current->pid); + pr_err("SELinux: %s (%d) set checkreqprot to 1. This is deprecated and will be rejected in a future kernel release.\n", + comm, current->pid); } checkreqprot_set(fsi->state, (new_value ? 1 : 0)); + if (new_value) + ssleep(5); length = count; selinux_ima_measure_state(fsi->state); diff --git a/security/selinux/ss/avtab.c b/security/selinux/ss/avtab.c index cfdae20792e1..8480ec6c6e75 100644 --- a/security/selinux/ss/avtab.c +++ b/security/selinux/ss/avtab.c @@ -40,15 +40,15 @@ static inline int avtab_hash(const struct avtab_key *keyp, u32 mask) u32 hash = 0; -#define mix(input) { \ - u32 v = input; \ - v *= c1; \ - v = (v << r1) | (v >> (32 - r1)); \ - v *= c2; \ - hash ^= v; \ - hash = (hash << r2) | (hash >> (32 - r2)); \ - hash = hash * m + n; \ -} +#define mix(input) do { \ + u32 v = input; \ + v *= c1; \ + v = (v << r1) | (v >> (32 - r1)); \ + v *= c2; \ + hash ^= v; \ + hash = (hash << r2) | (hash >> (32 - r2)); \ + hash = hash * m + n; \ + } while (0) mix(keyp->target_class); mix(keyp->target_type); @@ -385,7 +385,7 @@ void avtab_hash_eval(struct avtab *h, char *tag) chain2_len_sum); } -static uint16_t spec_order[] = { +static const uint16_t spec_order[] = { AVTAB_ALLOWED, AVTAB_AUDITDENY, AVTAB_AUDITALLOW, diff --git a/security/selinux/ss/hashtab.c b/security/selinux/ss/hashtab.c index 0ae4e4e57a40..3fb8f9026e9b 100644 --- a/security/selinux/ss/hashtab.c +++ b/security/selinux/ss/hashtab.c @@ -179,7 +179,8 @@ int hashtab_duplicate(struct hashtab *new, struct hashtab *orig, kmem_cache_free(hashtab_node_cachep, cur); } } - kmem_cache_free(hashtab_node_cachep, new); + kfree(new->htable); + memset(new, 0, sizeof(*new)); return -ENOMEM; } diff --git a/security/selinux/ss/policydb.c b/security/selinux/ss/policydb.c index d036e1238e77..adcfb63b3550 100644 --- a/security/selinux/ss/policydb.c +++ b/security/selinux/ss/policydb.c @@ -61,7 +61,7 @@ struct policydb_compat_info { }; /* These need to be updated if SYM_NUM or OCON_NUM changes */ -static struct policydb_compat_info policydb_compat[] = { +static const struct policydb_compat_info policydb_compat[] = { { .version = POLICYDB_VERSION_BASE, .sym_num = SYM_NUM - 3, @@ -159,18 +159,16 @@ static struct policydb_compat_info policydb_compat[] = { }, }; -static struct policydb_compat_info *policydb_lookup_compat(int version) +static const struct policydb_compat_info *policydb_lookup_compat(int version) { int i; - struct policydb_compat_info *info = NULL; for (i = 0; i < ARRAY_SIZE(policydb_compat); i++) { - if (policydb_compat[i].version == version) { - info = &policydb_compat[i]; - break; - } + if (policydb_compat[i].version == version) + return &policydb_compat[i]; } - return info; + + return NULL; } /* @@ -314,8 +312,7 @@ static int cat_destroy(void *key, void *datum, void *p) return 0; } -static int (*destroy_f[SYM_NUM]) (void *key, void *datum, void *datap) = -{ +static int (*const destroy_f[SYM_NUM]) (void *key, void *datum, void *datap) = { common_destroy, cls_destroy, role_destroy, @@ -670,8 +667,7 @@ static int cat_index(void *key, void *datum, void *datap) return 0; } -static int (*index_f[SYM_NUM]) (void *key, void *datum, void *datap) = -{ +static int (*const index_f[SYM_NUM]) (void *key, void *datum, void *datap) = { common_index, class_index, role_index, @@ -1639,8 +1635,8 @@ bad: return rc; } -static int (*read_f[SYM_NUM]) (struct policydb *p, struct symtab *s, void *fp) = -{ +static int (*const read_f[SYM_NUM]) (struct policydb *p, + struct symtab *s, void *fp) = { common_read, class_read, role_read, @@ -2211,7 +2207,7 @@ out: return rc; } -static int ocontext_read(struct policydb *p, struct policydb_compat_info *info, +static int ocontext_read(struct policydb *p, const struct policydb_compat_info *info, void *fp) { int i, j, rc; @@ -2407,7 +2403,7 @@ int policydb_read(struct policydb *p, void *fp) u32 len, nprim, nel, perm; char *policydb_str; - struct policydb_compat_info *info; + const struct policydb_compat_info *info; policydb_init(p); @@ -3241,9 +3237,7 @@ static int user_write(void *vkey, void *datum, void *ptr) return 0; } -static int (*write_f[SYM_NUM]) (void *key, void *datum, - void *datap) = -{ +static int (*const write_f[SYM_NUM]) (void *key, void *datum, void *datap) = { common_write, class_write, role_write, @@ -3254,7 +3248,7 @@ static int (*write_f[SYM_NUM]) (void *key, void *datum, cat_write, }; -static int ocontext_write(struct policydb *p, struct policydb_compat_info *info, +static int ocontext_write(struct policydb *p, const struct policydb_compat_info *info, void *fp) { unsigned int i, j, rc; @@ -3611,7 +3605,7 @@ int policydb_write(struct policydb *p, void *fp) __le32 buf[4]; u32 config; size_t len; - struct policydb_compat_info *info; + const struct policydb_compat_info *info; /* * refuse to write policy older than compressed avtab diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c index 6901dc07680d..69b2734311a6 100644 --- a/security/selinux/ss/services.c +++ b/security/selinux/ss/services.c @@ -99,7 +99,7 @@ static void context_struct_compute_av(struct policydb *policydb, struct extended_perms *xperms); static int selinux_set_mapping(struct policydb *pol, - struct security_class_mapping *map, + const struct security_class_mapping *map, struct selinux_map *out_map) { u16 i, j; @@ -121,7 +121,7 @@ static int selinux_set_mapping(struct policydb *pol, /* Store the raw class and permission values */ j = 0; while (map[j].name) { - struct security_class_mapping *p_in = map + (j++); + const struct security_class_mapping *p_in = map + (j++); struct selinux_mapping *p_out = out_map->mapping + j; /* An empty class string skips ahead */ @@ -358,27 +358,27 @@ static int constraint_expr_eval(struct policydb *policydb, l2 = &(tcontext->range.level[1]); goto mls_ops; mls_ops: - switch (e->op) { - case CEXPR_EQ: - s[++sp] = mls_level_eq(l1, l2); - continue; - case CEXPR_NEQ: - s[++sp] = !mls_level_eq(l1, l2); - continue; - case CEXPR_DOM: - s[++sp] = mls_level_dom(l1, l2); - continue; - case CEXPR_DOMBY: - s[++sp] = mls_level_dom(l2, l1); - continue; - case CEXPR_INCOMP: - s[++sp] = mls_level_incomp(l2, l1); - continue; - default: - BUG(); - return 0; - } - break; + switch (e->op) { + case CEXPR_EQ: + s[++sp] = mls_level_eq(l1, l2); + continue; + case CEXPR_NEQ: + s[++sp] = !mls_level_eq(l1, l2); + continue; + case CEXPR_DOM: + s[++sp] = mls_level_dom(l1, l2); + continue; + case CEXPR_DOMBY: + s[++sp] = mls_level_dom(l2, l1); + continue; + case CEXPR_INCOMP: + s[++sp] = mls_level_incomp(l2, l1); + continue; + default: + BUG(); + return 0; + } + break; default: BUG(); return 0; @@ -2980,7 +2980,6 @@ int security_fs_use(struct selinux_state *state, struct super_block *sb) } retry: - rc = 0; rcu_read_lock(); policy = rcu_dereference(state->policy); policydb = &policy->policydb; diff --git a/security/smack/smackfs.c b/security/smack/smackfs.c index 658eab05599e..9e61014073cc 100644 --- a/security/smack/smackfs.c +++ b/security/smack/smackfs.c @@ -1192,7 +1192,6 @@ static ssize_t smk_write_net4addr(struct file *file, const char __user *buf, rc = -EINVAL; goto free_out; } - m = BEBITS; masks = 32; } if (masks > BEBITS) { diff --git a/security/tomoyo/tomoyo.c b/security/tomoyo/tomoyo.c index b6a31901f289..71e82d855ebf 100644 --- a/security/tomoyo/tomoyo.c +++ b/security/tomoyo/tomoyo.c @@ -264,17 +264,26 @@ static int tomoyo_path_link(struct dentry *old_dentry, const struct path *new_di * @old_dentry: Pointer to "struct dentry". * @new_parent: Pointer to "struct path". * @new_dentry: Pointer to "struct dentry". + * @flags: Rename options. * * Returns 0 on success, negative value otherwise. */ static int tomoyo_path_rename(const struct path *old_parent, struct dentry *old_dentry, const struct path *new_parent, - struct dentry *new_dentry) + struct dentry *new_dentry, + const unsigned int flags) { struct path path1 = { .mnt = old_parent->mnt, .dentry = old_dentry }; struct path path2 = { .mnt = new_parent->mnt, .dentry = new_dentry }; + if (flags & RENAME_EXCHANGE) { + const int err = tomoyo_path2_perm(TOMOYO_TYPE_RENAME, &path2, + &path1); + + if (err) + return err; + } return tomoyo_path2_perm(TOMOYO_TYPE_RENAME, &path1, &path2); } diff --git a/sound/core/init.c b/sound/core/init.c index 31ba7024e3ad..726a8353201f 100644 --- a/sound/core/init.c +++ b/sound/core/init.c @@ -209,6 +209,12 @@ static void __snd_card_release(struct device *dev, void *data) * snd_card_register(), the very first devres action to call snd_card_free() * is added automatically. In that way, the resource disconnection is assured * at first, then released in the expected order. + * + * If an error happens at the probe before snd_card_register() is called and + * there have been other devres resources, you'd need to free the card manually + * via snd_card_free() call in the error; otherwise it may lead to UAF due to + * devres call orders. You can use snd_card_free_on_error() helper for + * handling it more easily. */ int snd_devm_card_new(struct device *parent, int idx, const char *xid, struct module *module, size_t extra_size, @@ -235,6 +241,28 @@ int snd_devm_card_new(struct device *parent, int idx, const char *xid, } EXPORT_SYMBOL_GPL(snd_devm_card_new); +/** + * snd_card_free_on_error - a small helper for handling devm probe errors + * @dev: the managed device object + * @ret: the return code from the probe callback + * + * This function handles the explicit snd_card_free() call at the error from + * the probe callback. It's just a small helper for simplifying the error + * handling with the managed devices. + */ +int snd_card_free_on_error(struct device *dev, int ret) +{ + struct snd_card *card; + + if (!ret) + return 0; + card = devres_find(dev, __snd_card_release, NULL, NULL); + if (card) + snd_card_free(card); + return ret; +} +EXPORT_SYMBOL_GPL(snd_card_free_on_error); + static int snd_card_init(struct snd_card *card, struct device *parent, int idx, const char *xid, struct module *module, size_t extra_size) diff --git a/sound/core/memalloc.c b/sound/core/memalloc.c index 6fd763d4d15b..15dc7160ba34 100644 --- a/sound/core/memalloc.c +++ b/sound/core/memalloc.c @@ -499,6 +499,10 @@ static const struct snd_malloc_ops snd_dma_wc_ops = { }; #endif /* CONFIG_X86 */ +#ifdef CONFIG_SND_DMA_SGBUF +static void *snd_dma_sg_fallback_alloc(struct snd_dma_buffer *dmab, size_t size); +#endif + /* * Non-contiguous pages allocator */ @@ -509,8 +513,18 @@ static void *snd_dma_noncontig_alloc(struct snd_dma_buffer *dmab, size_t size) sgt = dma_alloc_noncontiguous(dmab->dev.dev, size, dmab->dev.dir, DEFAULT_GFP, 0); - if (!sgt) + if (!sgt) { +#ifdef CONFIG_SND_DMA_SGBUF + if (dmab->dev.type == SNDRV_DMA_TYPE_DEV_WC_SG) + dmab->dev.type = SNDRV_DMA_TYPE_DEV_WC_SG_FALLBACK; + else + dmab->dev.type = SNDRV_DMA_TYPE_DEV_SG_FALLBACK; + return snd_dma_sg_fallback_alloc(dmab, size); +#else return NULL; +#endif + } + dmab->dev.need_sync = dma_need_sync(dmab->dev.dev, sg_dma_address(sgt->sgl)); p = dma_vmap_noncontiguous(dmab->dev.dev, size, sgt); @@ -633,6 +647,8 @@ static void *snd_dma_sg_wc_alloc(struct snd_dma_buffer *dmab, size_t size) if (!p) return NULL; + if (dmab->dev.type != SNDRV_DMA_TYPE_DEV_WC_SG) + return p; for_each_sgtable_page(sgt, &iter, 0) set_memory_wc(sg_wc_address(&iter), 1); return p; @@ -665,6 +681,95 @@ static const struct snd_malloc_ops snd_dma_sg_wc_ops = { .get_page = snd_dma_noncontig_get_page, .get_chunk_size = snd_dma_noncontig_get_chunk_size, }; + +/* Fallback SG-buffer allocations for x86 */ +struct snd_dma_sg_fallback { + size_t count; + struct page **pages; + dma_addr_t *addrs; +}; + +static void __snd_dma_sg_fallback_free(struct snd_dma_buffer *dmab, + struct snd_dma_sg_fallback *sgbuf) +{ + size_t i; + + if (sgbuf->count && dmab->dev.type == SNDRV_DMA_TYPE_DEV_WC_SG_FALLBACK) + set_pages_array_wb(sgbuf->pages, sgbuf->count); + for (i = 0; i < sgbuf->count && sgbuf->pages[i]; i++) + dma_free_coherent(dmab->dev.dev, PAGE_SIZE, + page_address(sgbuf->pages[i]), + sgbuf->addrs[i]); + kvfree(sgbuf->pages); + kvfree(sgbuf->addrs); + kfree(sgbuf); +} + +static void *snd_dma_sg_fallback_alloc(struct snd_dma_buffer *dmab, size_t size) +{ + struct snd_dma_sg_fallback *sgbuf; + struct page **pages; + size_t i, count; + void *p; + + sgbuf = kzalloc(sizeof(*sgbuf), GFP_KERNEL); + if (!sgbuf) + return NULL; + count = PAGE_ALIGN(size) >> PAGE_SHIFT; + pages = kvcalloc(count, sizeof(*pages), GFP_KERNEL); + if (!pages) + goto error; + sgbuf->pages = pages; + sgbuf->addrs = kvcalloc(count, sizeof(*sgbuf->addrs), GFP_KERNEL); + if (!sgbuf->addrs) + goto error; + + for (i = 0; i < count; sgbuf->count++, i++) { + p = dma_alloc_coherent(dmab->dev.dev, PAGE_SIZE, + &sgbuf->addrs[i], DEFAULT_GFP); + if (!p) + goto error; + sgbuf->pages[i] = virt_to_page(p); + } + + if (dmab->dev.type == SNDRV_DMA_TYPE_DEV_WC_SG_FALLBACK) + set_pages_array_wc(pages, count); + p = vmap(pages, count, VM_MAP, PAGE_KERNEL); + if (!p) + goto error; + dmab->private_data = sgbuf; + return p; + + error: + __snd_dma_sg_fallback_free(dmab, sgbuf); + return NULL; +} + +static void snd_dma_sg_fallback_free(struct snd_dma_buffer *dmab) +{ + vunmap(dmab->area); + __snd_dma_sg_fallback_free(dmab, dmab->private_data); +} + +static int snd_dma_sg_fallback_mmap(struct snd_dma_buffer *dmab, + struct vm_area_struct *area) +{ + struct snd_dma_sg_fallback *sgbuf = dmab->private_data; + + if (dmab->dev.type == SNDRV_DMA_TYPE_DEV_WC_SG_FALLBACK) + area->vm_page_prot = pgprot_writecombine(area->vm_page_prot); + return vm_map_pages(area, sgbuf->pages, sgbuf->count); +} + +static const struct snd_malloc_ops snd_dma_sg_fallback_ops = { + .alloc = snd_dma_sg_fallback_alloc, + .free = snd_dma_sg_fallback_free, + .mmap = snd_dma_sg_fallback_mmap, + /* reuse vmalloc helpers */ + .get_addr = snd_dma_vmalloc_get_addr, + .get_page = snd_dma_vmalloc_get_page, + .get_chunk_size = snd_dma_vmalloc_get_chunk_size, +}; #endif /* CONFIG_SND_DMA_SGBUF */ /* @@ -736,6 +841,10 @@ static const struct snd_malloc_ops *dma_ops[] = { #ifdef CONFIG_GENERIC_ALLOCATOR [SNDRV_DMA_TYPE_DEV_IRAM] = &snd_dma_iram_ops, #endif /* CONFIG_GENERIC_ALLOCATOR */ +#ifdef CONFIG_SND_DMA_SGBUF + [SNDRV_DMA_TYPE_DEV_SG_FALLBACK] = &snd_dma_sg_fallback_ops, + [SNDRV_DMA_TYPE_DEV_WC_SG_FALLBACK] = &snd_dma_sg_fallback_ops, +#endif #endif /* CONFIG_HAS_DMA */ }; diff --git a/sound/core/pcm_misc.c b/sound/core/pcm_misc.c index 4866aed97aac..5588b6a1ee8b 100644 --- a/sound/core/pcm_misc.c +++ b/sound/core/pcm_misc.c @@ -433,7 +433,7 @@ int snd_pcm_format_set_silence(snd_pcm_format_t format, void *data, unsigned int return 0; width = pcm_formats[(INT)format].phys; /* physical width */ pat = pcm_formats[(INT)format].silence; - if (! width) + if (!width || !pat) return -EINVAL; /* signed or 1 byte data */ if (pcm_formats[(INT)format].signd == 1 || width <= 8) { diff --git a/sound/drivers/mtpav.c b/sound/drivers/mtpav.c index 11235baaf6fa..f212f233ea61 100644 --- a/sound/drivers/mtpav.c +++ b/sound/drivers/mtpav.c @@ -693,8 +693,6 @@ static int snd_mtpav_probe(struct platform_device *dev) mtp_card->outmidihwport = 0xffffffff; timer_setup(&mtp_card->timer, snd_mtpav_output_timer, 0); - card->private_free = snd_mtpav_free; - err = snd_mtpav_get_RAWMIDI(mtp_card); if (err < 0) return err; @@ -716,6 +714,8 @@ static int snd_mtpav_probe(struct platform_device *dev) if (err < 0) return err; + card->private_free = snd_mtpav_free; + platform_set_drvdata(dev, card); printk(KERN_INFO "Motu MidiTimePiece on parallel port irq: %d ioport: 0x%lx\n", irq, port); return 0; diff --git a/sound/firewire/fireworks/fireworks_hwdep.c b/sound/firewire/fireworks/fireworks_hwdep.c index 626c0c34b0b6..3a53914277d3 100644 --- a/sound/firewire/fireworks/fireworks_hwdep.c +++ b/sound/firewire/fireworks/fireworks_hwdep.c @@ -34,6 +34,7 @@ hwdep_read_resp_buf(struct snd_efw *efw, char __user *buf, long remained, type = SNDRV_FIREWIRE_EVENT_EFW_RESPONSE; if (copy_to_user(buf, &type, sizeof(type))) return -EFAULT; + count += sizeof(type); remained -= sizeof(type); buf += sizeof(type); diff --git a/sound/hda/hdac_i915.c b/sound/hda/hdac_i915.c index efe810af28c5..3f35972e1cf7 100644 --- a/sound/hda/hdac_i915.c +++ b/sound/hda/hdac_i915.c @@ -116,16 +116,24 @@ static int i915_component_master_match(struct device *dev, int subcomponent, return 0; } -/* check whether intel graphics is present */ -static bool i915_gfx_present(void) +/* check whether Intel graphics is present and reachable */ +static int i915_gfx_present(struct pci_dev *hdac_pci) { - static const struct pci_device_id ids[] = { - { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_ANY_ID), - .class = PCI_BASE_CLASS_DISPLAY << 16, - .class_mask = 0xff << 16 }, - {} - }; - return pci_dev_present(ids); + unsigned int class = PCI_BASE_CLASS_DISPLAY << 16; + struct pci_dev *display_dev = NULL; + bool match = false; + + do { + display_dev = pci_get_class(class, display_dev); + + if (display_dev && display_dev->vendor == PCI_VENDOR_ID_INTEL && + connectivity_check(display_dev, hdac_pci)) { + pci_dev_put(display_dev); + match = true; + } + } while (!match && display_dev); + + return match; } /** @@ -145,7 +153,7 @@ int snd_hdac_i915_init(struct hdac_bus *bus) struct drm_audio_component *acomp; int err; - if (!i915_gfx_present()) + if (!i915_gfx_present(to_pci_dev(bus->dev))) return -ENODEV; err = snd_hdac_acomp_init(bus, NULL, diff --git a/sound/hda/intel-dsp-config.c b/sound/hda/intel-dsp-config.c index 70fd8b13938e..a8fe01764b25 100644 --- a/sound/hda/intel-dsp-config.c +++ b/sound/hda/intel-dsp-config.c @@ -390,26 +390,49 @@ static const struct config_entry config_table[] = { /* Alder Lake */ #if IS_ENABLED(CONFIG_SND_SOC_SOF_ALDERLAKE) + /* Alderlake-S */ { .flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC_OR_SOUNDWIRE, .device = 0x7ad0, }, + /* RaptorLake-S */ { .flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC_OR_SOUNDWIRE, - .device = 0x51c8, + .device = 0x7a50, }, + /* Alderlake-P */ { .flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC_OR_SOUNDWIRE, - .device = 0x51cc, + .device = 0x51c8, }, { .flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC_OR_SOUNDWIRE, .device = 0x51cd, }, + /* Alderlake-PS */ + { + .flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC_OR_SOUNDWIRE, + .device = 0x51c9, + }, + /* Alderlake-M */ + { + .flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC_OR_SOUNDWIRE, + .device = 0x51cc, + }, + /* Alderlake-N */ { .flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC_OR_SOUNDWIRE, .device = 0x54c8, }, + /* RaptorLake-P */ + { + .flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC_OR_SOUNDWIRE, + .device = 0x51ca, + }, + { + .flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC_OR_SOUNDWIRE, + .device = 0x51cb, + }, #endif }; diff --git a/sound/isa/galaxy/galaxy.c b/sound/isa/galaxy/galaxy.c index ea001c80149d..3164eb8510fa 100644 --- a/sound/isa/galaxy/galaxy.c +++ b/sound/isa/galaxy/galaxy.c @@ -478,7 +478,7 @@ static void snd_galaxy_free(struct snd_card *card) galaxy_set_config(galaxy, galaxy->config); } -static int snd_galaxy_probe(struct device *dev, unsigned int n) +static int __snd_galaxy_probe(struct device *dev, unsigned int n) { struct snd_galaxy *galaxy; struct snd_wss *chip; @@ -598,6 +598,11 @@ static int snd_galaxy_probe(struct device *dev, unsigned int n) return 0; } +static int snd_galaxy_probe(struct device *dev, unsigned int n) +{ + return snd_card_free_on_error(dev, __snd_galaxy_probe(dev, n)); +} + static struct isa_driver snd_galaxy_driver = { .match = snd_galaxy_match, .probe = snd_galaxy_probe, diff --git a/sound/isa/sc6000.c b/sound/isa/sc6000.c index 26ab7ff80768..60398fced046 100644 --- a/sound/isa/sc6000.c +++ b/sound/isa/sc6000.c @@ -537,7 +537,7 @@ static void snd_sc6000_free(struct snd_card *card) sc6000_setup_board(vport, 0); } -static int snd_sc6000_probe(struct device *devptr, unsigned int dev) +static int __snd_sc6000_probe(struct device *devptr, unsigned int dev) { static const int possible_irqs[] = { 5, 7, 9, 10, 11, -1 }; static const int possible_dmas[] = { 1, 3, 0, -1 }; @@ -662,6 +662,11 @@ static int snd_sc6000_probe(struct device *devptr, unsigned int dev) return 0; } +static int snd_sc6000_probe(struct device *devptr, unsigned int dev) +{ + return snd_card_free_on_error(devptr, __snd_sc6000_probe(devptr, dev)); +} + static struct isa_driver snd_sc6000_driver = { .match = snd_sc6000_match, .probe = snd_sc6000_probe, diff --git a/sound/isa/wavefront/wavefront_synth.c b/sound/isa/wavefront/wavefront_synth.c index 69cbc79fbb71..2aaaa6807174 100644 --- a/sound/isa/wavefront/wavefront_synth.c +++ b/sound/isa/wavefront/wavefront_synth.c @@ -1094,7 +1094,8 @@ wavefront_send_sample (snd_wavefront_t *dev, if (dataptr < data_end) { - __get_user (sample_short, dataptr); + if (get_user(sample_short, dataptr)) + return -EFAULT; dataptr += skip; if (data_is_unsigned) { /* GUS ? */ diff --git a/sound/oss/dmasound/dmasound.h b/sound/oss/dmasound/dmasound.h index c1c52b479da2..ad8ce6a1c25c 100644 --- a/sound/oss/dmasound/dmasound.h +++ b/sound/oss/dmasound/dmasound.h @@ -88,11 +88,7 @@ static inline int ioctl_return(int __user *addr, int value) */ extern int dmasound_init(void); -#ifdef MODULE extern void dmasound_deinit(void); -#else -#define dmasound_deinit() do { } while (0) -#endif /* description of the set-up applies to either hard or soft settings */ @@ -114,9 +110,7 @@ typedef struct { void *(*dma_alloc)(unsigned int, gfp_t); void (*dma_free)(void *, unsigned int); int (*irqinit)(void); -#ifdef MODULE void (*irqcleanup)(void); -#endif void (*init)(void); void (*silence)(void); int (*setFormat)(int); diff --git a/sound/oss/dmasound/dmasound_core.c b/sound/oss/dmasound/dmasound_core.c index 0c95828ac0b1..164335d3c200 100644 --- a/sound/oss/dmasound/dmasound_core.c +++ b/sound/oss/dmasound/dmasound_core.c @@ -206,12 +206,10 @@ module_param(writeBufSize, int, 0); MODULE_LICENSE("GPL"); -#ifdef MODULE static int sq_unit = -1; static int mixer_unit = -1; static int state_unit = -1; static int irq_installed; -#endif /* MODULE */ /* control over who can modify resources shared between play/record */ static fmode_t shared_resource_owner; @@ -391,9 +389,6 @@ static const struct file_operations mixer_fops = static void mixer_init(void) { -#ifndef MODULE - int mixer_unit; -#endif mixer_unit = register_sound_mixer(&mixer_fops, -1); if (mixer_unit < 0) return; @@ -1171,9 +1166,6 @@ static const struct file_operations sq_fops = static int sq_init(void) { const struct file_operations *fops = &sq_fops; -#ifndef MODULE - int sq_unit; -#endif sq_unit = register_sound_dsp(fops, -1); if (sq_unit < 0) { @@ -1366,9 +1358,6 @@ static const struct file_operations state_fops = { static int state_init(void) { -#ifndef MODULE - int state_unit; -#endif state_unit = register_sound_special(&state_fops, SND_DEV_STATUS); if (state_unit < 0) return state_unit ; @@ -1386,10 +1375,9 @@ static int state_init(void) int dmasound_init(void) { int res ; -#ifdef MODULE + if (irq_installed) return -EBUSY; -#endif /* Set up sound queue, /dev/audio and /dev/dsp. */ @@ -1408,9 +1396,7 @@ int dmasound_init(void) printk(KERN_ERR "DMA sound driver: Interrupt initialization failed\n"); return -ENODEV; } -#ifdef MODULE irq_installed = 1; -#endif printk(KERN_INFO "%s DMA sound driver rev %03d installed\n", dmasound.mach.name, (DMASOUND_CORE_REVISION<<4) + @@ -1424,8 +1410,6 @@ int dmasound_init(void) return 0; } -#ifdef MODULE - void dmasound_deinit(void) { if (irq_installed) { @@ -1444,9 +1428,7 @@ void dmasound_deinit(void) unregister_sound_dsp(sq_unit); } -#else /* !MODULE */ - -static int dmasound_setup(char *str) +static int __maybe_unused dmasound_setup(char *str) { int ints[6], size; @@ -1489,8 +1471,6 @@ static int dmasound_setup(char *str) __setup("dmasound=", dmasound_setup); -#endif /* !MODULE */ - /* * Conversion tables */ @@ -1577,9 +1557,7 @@ char dmasound_alaw2dma8[] = { EXPORT_SYMBOL(dmasound); EXPORT_SYMBOL(dmasound_init); -#ifdef MODULE EXPORT_SYMBOL(dmasound_deinit); -#endif EXPORT_SYMBOL(dmasound_write_sq); EXPORT_SYMBOL(dmasound_catchRadius); #ifdef HAS_8BIT_TABLES diff --git a/sound/pci/ad1889.c b/sound/pci/ad1889.c index bba4dae8dcc7..50e30704bf6f 100644 --- a/sound/pci/ad1889.c +++ b/sound/pci/ad1889.c @@ -844,8 +844,8 @@ snd_ad1889_create(struct snd_card *card, struct pci_dev *pci) } static int -snd_ad1889_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +__snd_ad1889_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { int err; static int devno; @@ -904,6 +904,12 @@ snd_ad1889_probe(struct pci_dev *pci, return 0; } +static int snd_ad1889_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_ad1889_probe(pci, pci_id)); +} + static const struct pci_device_id snd_ad1889_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_ANALOG_DEVICES, PCI_DEVICE_ID_AD1889JS) }, { 0, }, diff --git a/sound/pci/ali5451/ali5451.c b/sound/pci/ali5451/ali5451.c index 92eb59db106d..2378a39abaeb 100644 --- a/sound/pci/ali5451/ali5451.c +++ b/sound/pci/ali5451/ali5451.c @@ -2124,8 +2124,8 @@ static int snd_ali_create(struct snd_card *card, return 0; } -static int snd_ali_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_ali_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { struct snd_card *card; struct snd_ali *codec; @@ -2170,6 +2170,12 @@ static int snd_ali_probe(struct pci_dev *pci, return 0; } +static int snd_ali_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_ali_probe(pci, pci_id)); +} + static struct pci_driver ali5451_driver = { .name = KBUILD_MODNAME, .id_table = snd_ali_ids, diff --git a/sound/pci/als300.c b/sound/pci/als300.c index b86565dcdbe4..c70aff060120 100644 --- a/sound/pci/als300.c +++ b/sound/pci/als300.c @@ -708,7 +708,7 @@ static int snd_als300_probe(struct pci_dev *pci, err = snd_als300_create(card, pci, chip_type); if (err < 0) - return err; + goto error; strcpy(card->driver, "ALS300"); if (chip->chip_type == DEVICE_ALS300_PLUS) @@ -723,11 +723,15 @@ static int snd_als300_probe(struct pci_dev *pci, err = snd_card_register(card); if (err < 0) - return err; + goto error; pci_set_drvdata(pci, card); dev++; return 0; + + error: + snd_card_free(card); + return err; } static struct pci_driver als300_driver = { diff --git a/sound/pci/als4000.c b/sound/pci/als4000.c index 535eccd124be..f33aeb692a11 100644 --- a/sound/pci/als4000.c +++ b/sound/pci/als4000.c @@ -806,8 +806,8 @@ static void snd_card_als4000_free( struct snd_card *card ) snd_als4000_free_gameport(acard); } -static int snd_card_als4000_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_card_als4000_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { static int dev; struct snd_card *card; @@ -930,6 +930,12 @@ static int snd_card_als4000_probe(struct pci_dev *pci, return 0; } +static int snd_card_als4000_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_card_als4000_probe(pci, pci_id)); +} + #ifdef CONFIG_PM_SLEEP static int snd_als4000_suspend(struct device *dev) { diff --git a/sound/pci/atiixp.c b/sound/pci/atiixp.c index b8e035d5930d..43d01f1847ed 100644 --- a/sound/pci/atiixp.c +++ b/sound/pci/atiixp.c @@ -1572,8 +1572,8 @@ static int snd_atiixp_init(struct snd_card *card, struct pci_dev *pci) } -static int snd_atiixp_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_atiixp_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { struct snd_card *card; struct atiixp *chip; @@ -1623,6 +1623,12 @@ static int snd_atiixp_probe(struct pci_dev *pci, return 0; } +static int snd_atiixp_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_atiixp_probe(pci, pci_id)); +} + static struct pci_driver atiixp_driver = { .name = KBUILD_MODNAME, .id_table = snd_atiixp_ids, diff --git a/sound/pci/atiixp_modem.c b/sound/pci/atiixp_modem.c index 178dce8ef1e9..8864c4c3c7e1 100644 --- a/sound/pci/atiixp_modem.c +++ b/sound/pci/atiixp_modem.c @@ -1201,8 +1201,8 @@ static int snd_atiixp_init(struct snd_card *card, struct pci_dev *pci) } -static int snd_atiixp_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_atiixp_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { struct snd_card *card; struct atiixp_modem *chip; @@ -1247,6 +1247,12 @@ static int snd_atiixp_probe(struct pci_dev *pci, return 0; } +static int snd_atiixp_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_atiixp_probe(pci, pci_id)); +} + static struct pci_driver atiixp_modem_driver = { .name = KBUILD_MODNAME, .id_table = snd_atiixp_ids, diff --git a/sound/pci/au88x0/au88x0.c b/sound/pci/au88x0/au88x0.c index 342ef2a6655e..eb234153691b 100644 --- a/sound/pci/au88x0/au88x0.c +++ b/sound/pci/au88x0/au88x0.c @@ -193,7 +193,7 @@ snd_vortex_create(struct snd_card *card, struct pci_dev *pci) // constructor -- see "Constructor" sub-section static int -snd_vortex_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) +__snd_vortex_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) { static int dev; struct snd_card *card; @@ -310,6 +310,12 @@ snd_vortex_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) return 0; } +static int +snd_vortex_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_vortex_probe(pci, pci_id)); +} + // pci_driver definition static struct pci_driver vortex_driver = { .name = KBUILD_MODNAME, diff --git a/sound/pci/aw2/aw2-alsa.c b/sound/pci/aw2/aw2-alsa.c index d56f126d6fdd..29a4bcdec237 100644 --- a/sound/pci/aw2/aw2-alsa.c +++ b/sound/pci/aw2/aw2-alsa.c @@ -275,7 +275,7 @@ static int snd_aw2_probe(struct pci_dev *pci, /* (3) Create main component */ err = snd_aw2_create(card, pci); if (err < 0) - return err; + goto error; /* initialize mutex */ mutex_init(&chip->mtx); @@ -294,13 +294,17 @@ static int snd_aw2_probe(struct pci_dev *pci, /* (6) Register card instance */ err = snd_card_register(card); if (err < 0) - return err; + goto error; /* (7) Set PCI driver data */ pci_set_drvdata(pci, card); dev++; return 0; + + error: + snd_card_free(card); + return err; } /* open callback */ diff --git a/sound/pci/azt3328.c b/sound/pci/azt3328.c index 089050470ff2..7f329dfc5404 100644 --- a/sound/pci/azt3328.c +++ b/sound/pci/azt3328.c @@ -2427,7 +2427,7 @@ snd_azf3328_create(struct snd_card *card, } static int -snd_azf3328_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) +__snd_azf3328_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) { static int dev; struct snd_card *card; @@ -2520,6 +2520,12 @@ snd_azf3328_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) return 0; } +static int +snd_azf3328_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_azf3328_probe(pci, pci_id)); +} + #ifdef CONFIG_PM_SLEEP static inline void snd_azf3328_suspend_regs(const struct snd_azf3328 *chip, diff --git a/sound/pci/bt87x.c b/sound/pci/bt87x.c index d23f93163841..621985bfee5d 100644 --- a/sound/pci/bt87x.c +++ b/sound/pci/bt87x.c @@ -805,8 +805,8 @@ static int snd_bt87x_detect_card(struct pci_dev *pci) return SND_BT87X_BOARD_UNKNOWN; } -static int snd_bt87x_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_bt87x_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { static int dev; struct snd_card *card; @@ -889,6 +889,12 @@ static int snd_bt87x_probe(struct pci_dev *pci, return 0; } +static int snd_bt87x_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_bt87x_probe(pci, pci_id)); +} + /* default entries for all Bt87x cards - it's not exported */ /* driver_data is set to 0 to call detection */ static const struct pci_device_id snd_bt87x_default_ids[] = { diff --git a/sound/pci/ca0106/ca0106_main.c b/sound/pci/ca0106/ca0106_main.c index 8577f9fa5ea6..cf1bac7a435f 100644 --- a/sound/pci/ca0106/ca0106_main.c +++ b/sound/pci/ca0106/ca0106_main.c @@ -1725,8 +1725,8 @@ static int snd_ca0106_midi(struct snd_ca0106 *chip, unsigned int channel) } -static int snd_ca0106_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_ca0106_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { static int dev; struct snd_card *card; @@ -1786,6 +1786,12 @@ static int snd_ca0106_probe(struct pci_dev *pci, return 0; } +static int snd_ca0106_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_ca0106_probe(pci, pci_id)); +} + #ifdef CONFIG_PM_SLEEP static int snd_ca0106_suspend(struct device *dev) { diff --git a/sound/pci/cmipci.c b/sound/pci/cmipci.c index dab801d9d3b4..727db6d43391 100644 --- a/sound/pci/cmipci.c +++ b/sound/pci/cmipci.c @@ -3247,15 +3247,19 @@ static int snd_cmipci_probe(struct pci_dev *pci, err = snd_cmipci_create(card, pci, dev); if (err < 0) - return err; + goto error; err = snd_card_register(card); if (err < 0) - return err; + goto error; pci_set_drvdata(pci, card); dev++; return 0; + + error: + snd_card_free(card); + return err; } #ifdef CONFIG_PM_SLEEP diff --git a/sound/pci/cs4281.c b/sound/pci/cs4281.c index e7367402b84a..0c9cadf7b3b8 100644 --- a/sound/pci/cs4281.c +++ b/sound/pci/cs4281.c @@ -1827,8 +1827,8 @@ static void snd_cs4281_opl3_command(struct snd_opl3 *opl3, unsigned short cmd, spin_unlock_irqrestore(&opl3->reg_lock, flags); } -static int snd_cs4281_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_cs4281_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { static int dev; struct snd_card *card; @@ -1888,6 +1888,12 @@ static int snd_cs4281_probe(struct pci_dev *pci, return 0; } +static int snd_cs4281_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_cs4281_probe(pci, pci_id)); +} + /* * Power Management */ diff --git a/sound/pci/cs5535audio/cs5535audio.c b/sound/pci/cs5535audio/cs5535audio.c index 499fa0148f9a..440b8f9b40c9 100644 --- a/sound/pci/cs5535audio/cs5535audio.c +++ b/sound/pci/cs5535audio/cs5535audio.c @@ -281,8 +281,8 @@ static int snd_cs5535audio_create(struct snd_card *card, return 0; } -static int snd_cs5535audio_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_cs5535audio_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { static int dev; struct snd_card *card; @@ -331,6 +331,12 @@ static int snd_cs5535audio_probe(struct pci_dev *pci, return 0; } +static int snd_cs5535audio_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_cs5535audio_probe(pci, pci_id)); +} + static struct pci_driver cs5535audio_driver = { .name = KBUILD_MODNAME, .id_table = snd_cs5535audio_ids, diff --git a/sound/pci/echoaudio/echoaudio.c b/sound/pci/echoaudio/echoaudio.c index 25b012ef5c3e..c70c3ac4e99a 100644 --- a/sound/pci/echoaudio/echoaudio.c +++ b/sound/pci/echoaudio/echoaudio.c @@ -1970,8 +1970,8 @@ static int snd_echo_create(struct snd_card *card, } /* constructor */ -static int snd_echo_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_echo_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { static int dev; struct snd_card *card; @@ -2139,6 +2139,11 @@ static int snd_echo_probe(struct pci_dev *pci, return 0; } +static int snd_echo_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_echo_probe(pci, pci_id)); +} #if defined(CONFIG_PM_SLEEP) diff --git a/sound/pci/emu10k1/emu10k1x.c b/sound/pci/emu10k1/emu10k1x.c index c49c44dc1082..89043392f3ec 100644 --- a/sound/pci/emu10k1/emu10k1x.c +++ b/sound/pci/emu10k1/emu10k1x.c @@ -1491,8 +1491,8 @@ static int snd_emu10k1x_midi(struct emu10k1x *emu) return 0; } -static int snd_emu10k1x_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_emu10k1x_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { static int dev; struct snd_card *card; @@ -1554,6 +1554,12 @@ static int snd_emu10k1x_probe(struct pci_dev *pci, return 0; } +static int snd_emu10k1x_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_emu10k1x_probe(pci, pci_id)); +} + // PCI IDs static const struct pci_device_id snd_emu10k1x_ids[] = { { PCI_VDEVICE(CREATIVE, 0x0006), 0 }, /* Dell OEM version (EMU10K1) */ diff --git a/sound/pci/ens1370.c b/sound/pci/ens1370.c index 2651f0c64c06..94efe347a97a 100644 --- a/sound/pci/ens1370.c +++ b/sound/pci/ens1370.c @@ -2304,8 +2304,8 @@ static irqreturn_t snd_audiopci_interrupt(int irq, void *dev_id) return IRQ_HANDLED; } -static int snd_audiopci_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_audiopci_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { static int dev; struct snd_card *card; @@ -2369,6 +2369,12 @@ static int snd_audiopci_probe(struct pci_dev *pci, return 0; } +static int snd_audiopci_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_audiopci_probe(pci, pci_id)); +} + static struct pci_driver ens137x_driver = { .name = KBUILD_MODNAME, .id_table = snd_audiopci_ids, diff --git a/sound/pci/es1938.c b/sound/pci/es1938.c index 00b976f42a3d..e34ec6f89e7e 100644 --- a/sound/pci/es1938.c +++ b/sound/pci/es1938.c @@ -1716,8 +1716,8 @@ static int snd_es1938_mixer(struct es1938 *chip) } -static int snd_es1938_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_es1938_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { static int dev; struct snd_card *card; @@ -1796,6 +1796,12 @@ static int snd_es1938_probe(struct pci_dev *pci, return 0; } +static int snd_es1938_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_es1938_probe(pci, pci_id)); +} + static struct pci_driver es1938_driver = { .name = KBUILD_MODNAME, .id_table = snd_es1938_ids, diff --git a/sound/pci/es1968.c b/sound/pci/es1968.c index 6a8a02a9ecf4..4a7e20bb11bc 100644 --- a/sound/pci/es1968.c +++ b/sound/pci/es1968.c @@ -2741,8 +2741,8 @@ static int snd_es1968_create(struct snd_card *card, /* */ -static int snd_es1968_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_es1968_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { static int dev; struct snd_card *card; @@ -2848,6 +2848,12 @@ static int snd_es1968_probe(struct pci_dev *pci, return 0; } +static int snd_es1968_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_es1968_probe(pci, pci_id)); +} + static struct pci_driver es1968_driver = { .name = KBUILD_MODNAME, .id_table = snd_es1968_ids, diff --git a/sound/pci/fm801.c b/sound/pci/fm801.c index 9c22ff19e56d..62b3cb126c6d 100644 --- a/sound/pci/fm801.c +++ b/sound/pci/fm801.c @@ -1268,8 +1268,8 @@ static int snd_fm801_create(struct snd_card *card, return 0; } -static int snd_card_fm801_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_card_fm801_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { static int dev; struct snd_card *card; @@ -1333,6 +1333,12 @@ static int snd_card_fm801_probe(struct pci_dev *pci, return 0; } +static int snd_card_fm801_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_card_fm801_probe(pci, pci_id)); +} + #ifdef CONFIG_PM_SLEEP static const unsigned char saved_regs[] = { FM801_PCM_VOL, FM801_I2S_VOL, FM801_FM_VOL, FM801_REC_SRC, diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index 3e086eebf88d..31fe41795571 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -1395,7 +1395,7 @@ static int hdmi_find_pcm_slot(struct hdmi_spec *spec, last_try: /* the last try; check the empty slots in pins */ - for (i = 0; i < spec->num_nids; i++) { + for (i = 0; i < spec->pcm_used; i++) { if (!test_bit(i, &spec->pcm_bitmap)) return i; } @@ -2325,7 +2325,9 @@ static int generic_hdmi_build_pcms(struct hda_codec *codec) * dev_num is the device entry number in a pin */ - if (codec->mst_no_extra_pcms) + if (spec->dyn_pcm_no_legacy && codec->mst_no_extra_pcms) + pcm_num = spec->num_cvts; + else if (codec->mst_no_extra_pcms) pcm_num = spec->num_nids; else pcm_num = spec->num_nids + spec->dev_num - 1; @@ -4551,6 +4553,7 @@ HDA_CODEC_ENTRY(0x80862819, "DG2 HDMI", patch_i915_adlp_hdmi), HDA_CODEC_ENTRY(0x8086281a, "Jasperlake HDMI", patch_i915_icl_hdmi), HDA_CODEC_ENTRY(0x8086281b, "Elkhartlake HDMI", patch_i915_icl_hdmi), HDA_CODEC_ENTRY(0x8086281c, "Alderlake-P HDMI", patch_i915_adlp_hdmi), +HDA_CODEC_ENTRY(0x8086281f, "Raptorlake-P HDMI", patch_i915_adlp_hdmi), HDA_CODEC_ENTRY(0x80862880, "CedarTrail HDMI", patch_generic_hdmi), HDA_CODEC_ENTRY(0x80862882, "Valleyview2 HDMI", patch_i915_byt_hdmi), HDA_CODEC_ENTRY(0x80862883, "Braswell HDMI", patch_i915_byt_hdmi), diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 4e12af24b4d3..ad292df7d805 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -937,6 +937,9 @@ static int alc_init(struct hda_codec *codec) return 0; } +#define alc_free snd_hda_gen_free + +#ifdef CONFIG_PM static inline void alc_shutup(struct hda_codec *codec) { struct alc_spec *spec = codec->spec; @@ -950,9 +953,6 @@ static inline void alc_shutup(struct hda_codec *codec) alc_shutup_pins(codec); } -#define alc_free snd_hda_gen_free - -#ifdef CONFIG_PM static void alc_power_eapd(struct hda_codec *codec) { alc_auto_setup_eapd(codec, false); @@ -966,9 +966,7 @@ static int alc_suspend(struct hda_codec *codec) spec->power_hook(codec); return 0; } -#endif -#ifdef CONFIG_PM static int alc_resume(struct hda_codec *codec) { struct alc_spec *spec = codec->spec; @@ -2619,6 +2617,7 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = { SND_PCI_QUIRK(0x1558, 0x65e1, "Clevo PB51[ED][DF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), SND_PCI_QUIRK(0x1558, 0x65e5, "Clevo PC50D[PRS](?:-D|-G)?", ALC1220_FIXUP_CLEVO_PB51ED_PINS), SND_PCI_QUIRK(0x1558, 0x65f1, "Clevo PC50HS", ALC1220_FIXUP_CLEVO_PB51ED_PINS), + SND_PCI_QUIRK(0x1558, 0x65f5, "Clevo PD50PN[NRT]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), SND_PCI_QUIRK(0x1558, 0x67d1, "Clevo PB71[ER][CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), SND_PCI_QUIRK(0x1558, 0x67e1, "Clevo PB71[DE][CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), SND_PCI_QUIRK(0x1558, 0x67e5, "Clevo PC70D[PRS](?:-D|-G)?", ALC1220_FIXUP_CLEVO_PB51ED_PINS), @@ -6779,6 +6778,41 @@ static void alc256_fixup_mic_no_presence_and_resume(struct hda_codec *codec, } } +static void alc_fixup_dell4_mic_no_presence_quiet(struct hda_codec *codec, + const struct hda_fixup *fix, + int action) +{ + struct alc_spec *spec = codec->spec; + struct hda_input_mux *imux = &spec->gen.input_mux; + int i; + + alc269_fixup_limit_int_mic_boost(codec, fix, action); + + switch (action) { + case HDA_FIXUP_ACT_PRE_PROBE: + /** + * Set the vref of pin 0x19 (Headset Mic) and pin 0x1b (Headphone Mic) + * to Hi-Z to avoid pop noises at startup and when plugging and + * unplugging headphones. + */ + snd_hda_codec_set_pin_target(codec, 0x19, PIN_VREFHIZ); + snd_hda_codec_set_pin_target(codec, 0x1b, PIN_VREFHIZ); + break; + case HDA_FIXUP_ACT_PROBE: + /** + * Make the internal mic (0x12) the default input source to + * prevent pop noises on cold boot. + */ + for (i = 0; i < imux->num_items; i++) { + if (spec->gen.imux_pins[i] == 0x12) { + spec->gen.cur_mux[0] = i; + break; + } + } + break; + } +} + enum { ALC269_FIXUP_GPIO2, ALC269_FIXUP_SONY_VAIO, @@ -6820,6 +6854,7 @@ enum { ALC269_FIXUP_DELL2_MIC_NO_PRESENCE, ALC269_FIXUP_DELL3_MIC_NO_PRESENCE, ALC269_FIXUP_DELL4_MIC_NO_PRESENCE, + ALC269_FIXUP_DELL4_MIC_NO_PRESENCE_QUIET, ALC269_FIXUP_HEADSET_MODE, ALC269_FIXUP_HEADSET_MODE_NO_HP_MIC, ALC269_FIXUP_ASPIRE_HEADSET_MIC, @@ -7005,11 +7040,13 @@ enum { ALC285_FIXUP_LEGION_Y9000X_AUTOMUTE, ALC287_FIXUP_LEGION_16ACHG6, ALC287_FIXUP_CS35L41_I2C_2, + ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED, ALC245_FIXUP_CS35L41_SPI_2, ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED, ALC245_FIXUP_CS35L41_SPI_4, ALC245_FIXUP_CS35L41_SPI_4_HP_GPIO_LED, ALC285_FIXUP_HP_SPEAKERS_MICMUTE_LED, + ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE, }; static const struct hda_fixup alc269_fixups[] = { @@ -8767,6 +8804,14 @@ static const struct hda_fixup alc269_fixups[] = { [ALC287_FIXUP_CS35L41_I2C_2] = { .type = HDA_FIXUP_FUNC, .v.func = cs35l41_fixup_i2c_two, + .chained = true, + .chain_id = ALC269_FIXUP_THINKPAD_ACPI, + }, + [ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED] = { + .type = HDA_FIXUP_FUNC, + .v.func = cs35l41_fixup_i2c_two, + .chained = true, + .chain_id = ALC285_FIXUP_HP_MUTE_LED, }, [ALC245_FIXUP_CS35L41_SPI_2] = { .type = HDA_FIXUP_FUNC, @@ -8798,6 +8843,21 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC285_FIXUP_HP_MUTE_LED, }, + [ALC269_FIXUP_DELL4_MIC_NO_PRESENCE_QUIET] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc_fixup_dell4_mic_no_presence_quiet, + .chained = true, + .chain_id = ALC269_FIXUP_DELL4_MIC_NO_PRESENCE, + }, + [ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x19, 0x02a1112c }, /* use as headset mic, without its own jack detect */ + { } + }, + .chained = true, + .chain_id = ALC269_FIXUP_HEADSET_MODE_NO_HP_MIC + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -8888,6 +8948,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1028, 0x09bf, "Dell Precision", ALC233_FIXUP_ASUS_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x0a2e, "Dell", ALC236_FIXUP_DELL_AIO_HEADSET_MIC), SND_PCI_QUIRK(0x1028, 0x0a30, "Dell", ALC236_FIXUP_DELL_AIO_HEADSET_MIC), + SND_PCI_QUIRK(0x1028, 0x0a38, "Dell Latitude 7520", ALC269_FIXUP_DELL4_MIC_NO_PRESENCE_QUIET), SND_PCI_QUIRK(0x1028, 0x0a58, "Dell", ALC255_FIXUP_DELL_HEADSET_MIC), SND_PCI_QUIRK(0x1028, 0x0a61, "Dell XPS 15 9510", ALC289_FIXUP_DUAL_SPK), SND_PCI_QUIRK(0x1028, 0x0a62, "Dell Precision 5560", ALC289_FIXUP_DUAL_SPK), @@ -9015,21 +9076,22 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8896, "HP EliteBook 855 G8 Notebook PC", ALC285_FIXUP_HP_MUTE_LED), SND_PCI_QUIRK(0x103c, 0x8898, "HP EliteBook 845 G8 Notebook PC", ALC285_FIXUP_HP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x103c, 0x88d0, "HP Pavilion 15-eh1xxx (mainboard 88D0)", ALC287_FIXUP_HP_GPIO_LED), - SND_PCI_QUIRK(0x103c, 0x896e, "HP EliteBook x360 830 G9", ALC245_FIXUP_CS35L41_SPI_2), - SND_PCI_QUIRK(0x103c, 0x8971, "HP EliteBook 830 G9", ALC245_FIXUP_CS35L41_SPI_2), - SND_PCI_QUIRK(0x103c, 0x8972, "HP EliteBook 840 G9", ALC245_FIXUP_CS35L41_SPI_2), - SND_PCI_QUIRK(0x103c, 0x8973, "HP EliteBook 860 G9", ALC245_FIXUP_CS35L41_SPI_2), - SND_PCI_QUIRK(0x103c, 0x8974, "HP EliteBook 840 Aero G9", ALC245_FIXUP_CS35L41_SPI_2), - SND_PCI_QUIRK(0x103c, 0x8975, "HP EliteBook x360 840 Aero G9", ALC245_FIXUP_CS35L41_SPI_2), + SND_PCI_QUIRK(0x103c, 0x896e, "HP EliteBook x360 830 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8971, "HP EliteBook 830 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8972, "HP EliteBook 840 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8973, "HP EliteBook 860 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8974, "HP EliteBook 840 Aero G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8975, "HP EliteBook x360 840 Aero G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8981, "HP Elite Dragonfly G3", ALC245_FIXUP_CS35L41_SPI_4), SND_PCI_QUIRK(0x103c, 0x898e, "HP EliteBook 835 G9", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x898f, "HP EliteBook 835 G9", ALC287_FIXUP_CS35L41_I2C_2), - SND_PCI_QUIRK(0x103c, 0x8991, "HP EliteBook 845 G9", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x103c, 0x8991, "HP EliteBook 845 G9", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8992, "HP EliteBook 845 G9", ALC287_FIXUP_CS35L41_I2C_2), - SND_PCI_QUIRK(0x103c, 0x8994, "HP EliteBook 855 G9", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x103c, 0x8994, "HP EliteBook 855 G9", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8995, "HP EliteBook 855 G9", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x89a4, "HP ProBook 440 G9", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x89a6, "HP ProBook 450 G9", ALC236_FIXUP_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x89aa, "HP EliteBook 630 G9", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x89ac, "HP EliteBook 640 G9", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x89ae, "HP EliteBook 650 G9", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x89c3, "Zbook Studio G9", ALC245_FIXUP_CS35L41_SPI_4_HP_GPIO_LED), @@ -9162,6 +9224,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1558, 0x8562, "Clevo NH[57][0-9]RZ[Q]", ALC269_FIXUP_DMIC), SND_PCI_QUIRK(0x1558, 0x8668, "Clevo NP50B[BE]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x866d, "Clevo NP5[05]PN[HJK]", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x867c, "Clevo NP7[01]PNP", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x867d, "Clevo NP7[01]PN[HJK]", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x8680, "Clevo NJ50LU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x8686, "Clevo NH50[CZ]U", ALC256_FIXUP_MIC_NO_PRESENCE_AND_RESUME), @@ -9236,6 +9299,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x3813, "Legion 7i 15IMHG05", ALC287_FIXUP_LEGION_15IMHG05_SPEAKERS), SND_PCI_QUIRK(0x17aa, 0x3818, "Lenovo C940", ALC298_FIXUP_LENOVO_SPK_VOLUME), SND_PCI_QUIRK(0x17aa, 0x3819, "Lenovo 13s Gen2 ITL", ALC287_FIXUP_13S_GEN2_SPEAKERS), + SND_PCI_QUIRK(0x17aa, 0x3820, "Yoga Duet 7 13ITL6", ALC287_FIXUP_YOGA7_14ITL_SPEAKERS), SND_PCI_QUIRK(0x17aa, 0x3824, "Legion Y9000X 2020", ALC285_FIXUP_LEGION_Y9000X_SPEAKERS), SND_PCI_QUIRK(0x17aa, 0x3827, "Ideapad S740", ALC285_FIXUP_IDEAPAD_S740_COEF), SND_PCI_QUIRK(0x17aa, 0x3834, "Lenovo IdeaPad Slim 9i 14ITL5", ALC287_FIXUP_YOGA7_14ITL_SPEAKERS), @@ -9264,6 +9328,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x505d, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), SND_PCI_QUIRK(0x17aa, 0x505f, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), SND_PCI_QUIRK(0x17aa, 0x5062, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), + SND_PCI_QUIRK(0x17aa, 0x508b, "Thinkpad X12 Gen 1", ALC287_FIXUP_LEGION_15IMHG05_SPEAKERS), SND_PCI_QUIRK(0x17aa, 0x5109, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x17aa, 0x511e, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), SND_PCI_QUIRK(0x17aa, 0x511f, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), @@ -9277,6 +9342,14 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1c06, 0x2013, "Lemote A1802", ALC269_FIXUP_LEMOTE_A1802), SND_PCI_QUIRK(0x1c06, 0x2015, "Lemote A190X", ALC269_FIXUP_LEMOTE_A190X), SND_PCI_QUIRK(0x1d05, 0x1132, "TongFang PHxTxX1", ALC256_FIXUP_SET_COEF_DEFAULTS), + SND_PCI_QUIRK(0x1d05, 0x1096, "TongFang GMxMRxx", ALC269_FIXUP_NO_SHUTUP), + SND_PCI_QUIRK(0x1d05, 0x1100, "TongFang GKxNRxx", ALC269_FIXUP_NO_SHUTUP), + SND_PCI_QUIRK(0x1d05, 0x1111, "TongFang GMxZGxx", ALC269_FIXUP_NO_SHUTUP), + SND_PCI_QUIRK(0x1d05, 0x1119, "TongFang GMxZGxx", ALC269_FIXUP_NO_SHUTUP), + SND_PCI_QUIRK(0x1d05, 0x1129, "TongFang GMxZGxx", ALC269_FIXUP_NO_SHUTUP), + SND_PCI_QUIRK(0x1d05, 0x1147, "TongFang GMxTGxx", ALC269_FIXUP_NO_SHUTUP), + SND_PCI_QUIRK(0x1d05, 0x115c, "TongFang GMxTGxx", ALC269_FIXUP_NO_SHUTUP), + SND_PCI_QUIRK(0x1d05, 0x121b, "TongFang GMxAGxx", ALC269_FIXUP_NO_SHUTUP), SND_PCI_QUIRK(0x1d72, 0x1602, "RedmiBook", ALC255_FIXUP_XIAOMI_HEADSET_MIC), SND_PCI_QUIRK(0x1d72, 0x1701, "XiaomiNotebook Pro", ALC298_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1d72, 0x1901, "RedmiBook 14", ALC256_FIXUP_ASUS_HEADSET_MIC), @@ -9284,6 +9357,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x8086, 0x2074, "Intel NUC 8", ALC233_FIXUP_INTEL_NUC8_DMIC), SND_PCI_QUIRK(0x8086, 0x2080, "Intel NUC 8 Rugged", ALC256_FIXUP_INTEL_NUC8_RUGGED), SND_PCI_QUIRK(0x8086, 0x2081, "Intel NUC 10", ALC256_FIXUP_INTEL_NUC10), + SND_PCI_QUIRK(0xf111, 0x0001, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE), #if 0 /* Below is a quirk table taken from the old code. diff --git a/sound/pci/ice1712/ice1724.c b/sound/pci/ice1712/ice1724.c index f6275868877a..6fab2ad85bbe 100644 --- a/sound/pci/ice1712/ice1724.c +++ b/sound/pci/ice1712/ice1724.c @@ -2519,8 +2519,8 @@ static int snd_vt1724_create(struct snd_card *card, * */ -static int snd_vt1724_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_vt1724_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { static int dev; struct snd_card *card; @@ -2662,6 +2662,12 @@ static int snd_vt1724_probe(struct pci_dev *pci, return 0; } +static int snd_vt1724_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_vt1724_probe(pci, pci_id)); +} + #ifdef CONFIG_PM_SLEEP static int snd_vt1724_suspend(struct device *dev) { diff --git a/sound/pci/intel8x0.c b/sound/pci/intel8x0.c index a51032b3ac4d..ae285c0a629c 100644 --- a/sound/pci/intel8x0.c +++ b/sound/pci/intel8x0.c @@ -3109,8 +3109,8 @@ static int check_default_spdif_aclink(struct pci_dev *pci) return 0; } -static int snd_intel8x0_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_intel8x0_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { struct snd_card *card; struct intel8x0 *chip; @@ -3189,6 +3189,12 @@ static int snd_intel8x0_probe(struct pci_dev *pci, return 0; } +static int snd_intel8x0_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_intel8x0_probe(pci, pci_id)); +} + static struct pci_driver intel8x0_driver = { .name = KBUILD_MODNAME, .id_table = snd_intel8x0_ids, diff --git a/sound/pci/intel8x0m.c b/sound/pci/intel8x0m.c index 7de3cb2f17b5..2845cc006d0c 100644 --- a/sound/pci/intel8x0m.c +++ b/sound/pci/intel8x0m.c @@ -1178,8 +1178,8 @@ static struct shortname_table { { 0 }, }; -static int snd_intel8x0m_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_intel8x0m_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { struct snd_card *card; struct intel8x0m *chip; @@ -1225,6 +1225,12 @@ static int snd_intel8x0m_probe(struct pci_dev *pci, return 0; } +static int snd_intel8x0m_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_intel8x0m_probe(pci, pci_id)); +} + static struct pci_driver intel8x0m_driver = { .name = KBUILD_MODNAME, .id_table = snd_intel8x0m_ids, diff --git a/sound/pci/korg1212/korg1212.c b/sound/pci/korg1212/korg1212.c index 5c9e240ff6a9..33b4f95d65b3 100644 --- a/sound/pci/korg1212/korg1212.c +++ b/sound/pci/korg1212/korg1212.c @@ -2355,7 +2355,7 @@ snd_korg1212_probe(struct pci_dev *pci, err = snd_korg1212_create(card, pci); if (err < 0) - return err; + goto error; strcpy(card->driver, "korg1212"); strcpy(card->shortname, "korg1212"); @@ -2366,10 +2366,14 @@ snd_korg1212_probe(struct pci_dev *pci, err = snd_card_register(card); if (err < 0) - return err; + goto error; pci_set_drvdata(pci, card); dev++; return 0; + + error: + snd_card_free(card); + return err; } static struct pci_driver korg1212_driver = { diff --git a/sound/pci/lola/lola.c b/sound/pci/lola/lola.c index 5269a1d396a5..1aa30e90b86a 100644 --- a/sound/pci/lola/lola.c +++ b/sound/pci/lola/lola.c @@ -637,8 +637,8 @@ static int lola_create(struct snd_card *card, struct pci_dev *pci, int dev) return 0; } -static int lola_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __lola_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { static int dev; struct snd_card *card; @@ -687,6 +687,12 @@ static int lola_probe(struct pci_dev *pci, return 0; } +static int lola_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __lola_probe(pci, pci_id)); +} + /* PCI IDs */ static const struct pci_device_id lola_ids[] = { { PCI_VDEVICE(DIGIGRAM, 0x0001) }, diff --git a/sound/pci/lx6464es/lx6464es.c b/sound/pci/lx6464es/lx6464es.c index 168a1084f730..bd9b6148dd6f 100644 --- a/sound/pci/lx6464es/lx6464es.c +++ b/sound/pci/lx6464es/lx6464es.c @@ -1019,7 +1019,7 @@ static int snd_lx6464es_probe(struct pci_dev *pci, err = snd_lx6464es_create(card, pci); if (err < 0) { dev_err(card->dev, "error during snd_lx6464es_create\n"); - return err; + goto error; } strcpy(card->driver, "LX6464ES"); @@ -1036,12 +1036,16 @@ static int snd_lx6464es_probe(struct pci_dev *pci, err = snd_card_register(card); if (err < 0) - return err; + goto error; dev_dbg(chip->card->dev, "initialization successful\n"); pci_set_drvdata(pci, card); dev++; return 0; + + error: + snd_card_free(card); + return err; } static struct pci_driver lx6464es_driver = { diff --git a/sound/pci/maestro3.c b/sound/pci/maestro3.c index 056838ead21d..261850775c80 100644 --- a/sound/pci/maestro3.c +++ b/sound/pci/maestro3.c @@ -2637,7 +2637,7 @@ snd_m3_create(struct snd_card *card, struct pci_dev *pci, /* */ static int -snd_m3_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) +__snd_m3_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) { static int dev; struct snd_card *card; @@ -2702,6 +2702,12 @@ snd_m3_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) return 0; } +static int +snd_m3_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_m3_probe(pci, pci_id)); +} + static struct pci_driver m3_driver = { .name = KBUILD_MODNAME, .id_table = snd_m3_ids, diff --git a/sound/pci/nm256/nm256.c b/sound/pci/nm256/nm256.c index c9c178504959..f99a1e96e923 100644 --- a/sound/pci/nm256/nm256.c +++ b/sound/pci/nm256/nm256.c @@ -1573,7 +1573,6 @@ snd_nm256_create(struct snd_card *card, struct pci_dev *pci) chip->coeffs_current = 0; snd_nm256_init_chip(chip); - card->private_free = snd_nm256_free; // pci_set_master(pci); /* needed? */ return 0; @@ -1680,6 +1679,7 @@ static int snd_nm256_probe(struct pci_dev *pci, err = snd_card_register(card); if (err < 0) return err; + card->private_free = snd_nm256_free; pci_set_drvdata(pci, card); return 0; diff --git a/sound/pci/oxygen/oxygen_lib.c b/sound/pci/oxygen/oxygen_lib.c index 4fb3f2484fdb..92ffe9dc20c5 100644 --- a/sound/pci/oxygen/oxygen_lib.c +++ b/sound/pci/oxygen/oxygen_lib.c @@ -576,7 +576,7 @@ static void oxygen_card_free(struct snd_card *card) mutex_destroy(&chip->mutex); } -int oxygen_pci_probe(struct pci_dev *pci, int index, char *id, +static int __oxygen_pci_probe(struct pci_dev *pci, int index, char *id, struct module *owner, const struct pci_device_id *ids, int (*get_model)(struct oxygen *chip, @@ -701,6 +701,16 @@ int oxygen_pci_probe(struct pci_dev *pci, int index, char *id, pci_set_drvdata(pci, card); return 0; } + +int oxygen_pci_probe(struct pci_dev *pci, int index, char *id, + struct module *owner, + const struct pci_device_id *ids, + int (*get_model)(struct oxygen *chip, + const struct pci_device_id *id)) +{ + return snd_card_free_on_error(&pci->dev, + __oxygen_pci_probe(pci, index, id, owner, ids, get_model)); +} EXPORT_SYMBOL(oxygen_pci_probe); #ifdef CONFIG_PM_SLEEP diff --git a/sound/pci/riptide/riptide.c b/sound/pci/riptide/riptide.c index 5a987c683c41..b37c877c2c16 100644 --- a/sound/pci/riptide/riptide.c +++ b/sound/pci/riptide/riptide.c @@ -2023,7 +2023,7 @@ static void snd_riptide_joystick_remove(struct pci_dev *pci) #endif static int -snd_card_riptide_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) +__snd_card_riptide_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) { static int dev; struct snd_card *card; @@ -2124,6 +2124,12 @@ snd_card_riptide_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) return 0; } +static int +snd_card_riptide_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_card_riptide_probe(pci, pci_id)); +} + static struct pci_driver driver = { .name = KBUILD_MODNAME, .id_table = snd_riptide_ids, diff --git a/sound/pci/rme32.c b/sound/pci/rme32.c index 5b6bd9f0b2f7..9c0ac025e143 100644 --- a/sound/pci/rme32.c +++ b/sound/pci/rme32.c @@ -1875,7 +1875,7 @@ static void snd_rme32_card_free(struct snd_card *card) } static int -snd_rme32_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) +__snd_rme32_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) { static int dev; struct rme32 *rme32; @@ -1927,6 +1927,12 @@ snd_rme32_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) return 0; } +static int +snd_rme32_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_rme32_probe(pci, pci_id)); +} + static struct pci_driver rme32_driver = { .name = KBUILD_MODNAME, .id_table = snd_rme32_ids, diff --git a/sound/pci/rme96.c b/sound/pci/rme96.c index 8fc811504920..bccb7e0d3d11 100644 --- a/sound/pci/rme96.c +++ b/sound/pci/rme96.c @@ -2430,8 +2430,8 @@ static void snd_rme96_card_free(struct snd_card *card) } static int -snd_rme96_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +__snd_rme96_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { static int dev; struct rme96 *rme96; @@ -2498,6 +2498,12 @@ snd_rme96_probe(struct pci_dev *pci, return 0; } +static int snd_rme96_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_rme96_probe(pci, pci_id)); +} + static struct pci_driver rme96_driver = { .name = KBUILD_MODNAME, .id_table = snd_rme96_ids, diff --git a/sound/pci/rme9652/hdsp.c b/sound/pci/rme9652/hdsp.c index 96c12dfb24cf..3db641318d3a 100644 --- a/sound/pci/rme9652/hdsp.c +++ b/sound/pci/rme9652/hdsp.c @@ -5444,17 +5444,21 @@ static int snd_hdsp_probe(struct pci_dev *pci, hdsp->pci = pci; err = snd_hdsp_create(card, hdsp); if (err) - return err; + goto error; strcpy(card->shortname, "Hammerfall DSP"); sprintf(card->longname, "%s at 0x%lx, irq %d", hdsp->card_name, hdsp->port, hdsp->irq); err = snd_card_register(card); if (err) - return err; + goto error; pci_set_drvdata(pci, card); dev++; return 0; + + error: + snd_card_free(card); + return err; } static struct pci_driver hdsp_driver = { diff --git a/sound/pci/rme9652/hdspm.c b/sound/pci/rme9652/hdspm.c index ff06ee82607c..fa1812e7a49d 100644 --- a/sound/pci/rme9652/hdspm.c +++ b/sound/pci/rme9652/hdspm.c @@ -6895,7 +6895,7 @@ static int snd_hdspm_probe(struct pci_dev *pci, err = snd_hdspm_create(card, hdspm); if (err < 0) - return err; + goto error; if (hdspm->io_type != MADIface) { snprintf(card->shortname, sizeof(card->shortname), "%s_%x", @@ -6914,12 +6914,16 @@ static int snd_hdspm_probe(struct pci_dev *pci, err = snd_card_register(card); if (err < 0) - return err; + goto error; pci_set_drvdata(pci, card); dev++; return 0; + + error: + snd_card_free(card); + return err; } static struct pci_driver hdspm_driver = { diff --git a/sound/pci/rme9652/rme9652.c b/sound/pci/rme9652/rme9652.c index 7755e19aa776..1d614fe89a6a 100644 --- a/sound/pci/rme9652/rme9652.c +++ b/sound/pci/rme9652/rme9652.c @@ -2572,7 +2572,7 @@ static int snd_rme9652_probe(struct pci_dev *pci, rme9652->pci = pci; err = snd_rme9652_create(card, rme9652, precise_ptr[dev]); if (err) - return err; + goto error; strcpy(card->shortname, rme9652->card_name); @@ -2580,10 +2580,14 @@ static int snd_rme9652_probe(struct pci_dev *pci, card->shortname, rme9652->port, rme9652->irq); err = snd_card_register(card); if (err) - return err; + goto error; pci_set_drvdata(pci, card); dev++; return 0; + + error: + snd_card_free(card); + return err; } static struct pci_driver rme9652_driver = { diff --git a/sound/pci/sis7019.c b/sound/pci/sis7019.c index 0b722b0e0604..fabe393607f8 100644 --- a/sound/pci/sis7019.c +++ b/sound/pci/sis7019.c @@ -1331,8 +1331,8 @@ static int sis_chip_create(struct snd_card *card, return 0; } -static int snd_sis7019_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_sis7019_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { struct snd_card *card; struct sis7019 *sis; @@ -1352,8 +1352,8 @@ static int snd_sis7019_probe(struct pci_dev *pci, if (!codecs) codecs = SIS_PRIMARY_CODEC_PRESENT; - rc = snd_card_new(&pci->dev, index, id, THIS_MODULE, - sizeof(*sis), &card); + rc = snd_devm_card_new(&pci->dev, index, id, THIS_MODULE, + sizeof(*sis), &card); if (rc < 0) return rc; @@ -1386,6 +1386,12 @@ static int snd_sis7019_probe(struct pci_dev *pci, return 0; } +static int snd_sis7019_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_sis7019_probe(pci, pci_id)); +} + static struct pci_driver sis7019_driver = { .name = KBUILD_MODNAME, .id_table = snd_sis7019_ids, diff --git a/sound/pci/sonicvibes.c b/sound/pci/sonicvibes.c index c8c49881008f..f91cbf6eeca0 100644 --- a/sound/pci/sonicvibes.c +++ b/sound/pci/sonicvibes.c @@ -1387,8 +1387,8 @@ static int snd_sonicvibes_midi(struct sonicvibes *sonic, return 0; } -static int snd_sonic_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_sonic_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { static int dev; struct snd_card *card; @@ -1459,6 +1459,12 @@ static int snd_sonic_probe(struct pci_dev *pci, return 0; } +static int snd_sonic_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_sonic_probe(pci, pci_id)); +} + static struct pci_driver sonicvibes_driver = { .name = KBUILD_MODNAME, .id_table = snd_sonic_ids, diff --git a/sound/pci/via82xx.c b/sound/pci/via82xx.c index 65514f7e42d7..361b83fd721e 100644 --- a/sound/pci/via82xx.c +++ b/sound/pci/via82xx.c @@ -2458,8 +2458,8 @@ static int check_dxs_list(struct pci_dev *pci, int revision) return VIA_DXS_48K; }; -static int snd_via82xx_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_via82xx_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { struct snd_card *card; struct via82xx *chip; @@ -2569,6 +2569,12 @@ static int snd_via82xx_probe(struct pci_dev *pci, return 0; } +static int snd_via82xx_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_via82xx_probe(pci, pci_id)); +} + static struct pci_driver via82xx_driver = { .name = KBUILD_MODNAME, .id_table = snd_via82xx_ids, diff --git a/sound/pci/via82xx_modem.c b/sound/pci/via82xx_modem.c index 234f7fbed236..ca7f024bf8ec 100644 --- a/sound/pci/via82xx_modem.c +++ b/sound/pci/via82xx_modem.c @@ -1103,8 +1103,8 @@ static int snd_via82xx_create(struct snd_card *card, } -static int snd_via82xx_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_via82xx_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { struct snd_card *card; struct via82xx_modem *chip; @@ -1157,6 +1157,12 @@ static int snd_via82xx_probe(struct pci_dev *pci, return 0; } +static int snd_via82xx_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_via82xx_probe(pci, pci_id)); +} + static struct pci_driver via82xx_modem_driver = { .name = KBUILD_MODNAME, .id_table = snd_via82xx_modem_ids, diff --git a/sound/soc/atmel/mchp-pdmc.c b/sound/soc/atmel/mchp-pdmc.c index 1a7802fbf23c..a3856c73e221 100644 --- a/sound/soc/atmel/mchp-pdmc.c +++ b/sound/soc/atmel/mchp-pdmc.c @@ -966,6 +966,7 @@ static int mchp_pdmc_process(struct snd_pcm_substream *substream, static struct snd_dmaengine_pcm_config mchp_pdmc_config = { .process = mchp_pdmc_process, + .prepare_slave_config = snd_dmaengine_pcm_prepare_slave_config, }; static int mchp_pdmc_probe(struct platform_device *pdev) diff --git a/sound/soc/atmel/sam9g20_wm8731.c b/sound/soc/atmel/sam9g20_wm8731.c index 33e43013ff77..0d639a33ad96 100644 --- a/sound/soc/atmel/sam9g20_wm8731.c +++ b/sound/soc/atmel/sam9g20_wm8731.c @@ -46,35 +46,6 @@ */ #undef ENABLE_MIC_INPUT -static struct clk *mclk; - -static int at91sam9g20ek_set_bias_level(struct snd_soc_card *card, - struct snd_soc_dapm_context *dapm, - enum snd_soc_bias_level level) -{ - static int mclk_on; - int ret = 0; - - switch (level) { - case SND_SOC_BIAS_ON: - case SND_SOC_BIAS_PREPARE: - if (!mclk_on) - ret = clk_enable(mclk); - if (ret == 0) - mclk_on = 1; - break; - - case SND_SOC_BIAS_OFF: - case SND_SOC_BIAS_STANDBY: - if (mclk_on) - clk_disable(mclk); - mclk_on = 0; - break; - } - - return ret; -} - static const struct snd_soc_dapm_widget at91sam9g20ek_dapm_widgets[] = { SND_SOC_DAPM_MIC("Int Mic", NULL), SND_SOC_DAPM_SPK("Ext Spk", NULL), @@ -135,7 +106,6 @@ static struct snd_soc_card snd_soc_at91sam9g20ek = { .owner = THIS_MODULE, .dai_link = &at91sam9g20ek_dai, .num_links = 1, - .set_bias_level = at91sam9g20ek_set_bias_level, .dapm_widgets = at91sam9g20ek_dapm_widgets, .num_dapm_widgets = ARRAY_SIZE(at91sam9g20ek_dapm_widgets), @@ -148,7 +118,6 @@ static int at91sam9g20ek_audio_probe(struct platform_device *pdev) { struct device_node *np = pdev->dev.of_node; struct device_node *codec_np, *cpu_np; - struct clk *pllb; struct snd_soc_card *card = &snd_soc_at91sam9g20ek; int ret; @@ -162,31 +131,6 @@ static int at91sam9g20ek_audio_probe(struct platform_device *pdev) return -EINVAL; } - /* - * Codec MCLK is supplied by PCK0 - set it up. - */ - mclk = clk_get(NULL, "pck0"); - if (IS_ERR(mclk)) { - dev_err(&pdev->dev, "Failed to get MCLK\n"); - ret = PTR_ERR(mclk); - goto err; - } - - pllb = clk_get(NULL, "pllb"); - if (IS_ERR(pllb)) { - dev_err(&pdev->dev, "Failed to get PLLB\n"); - ret = PTR_ERR(pllb); - goto err_mclk; - } - ret = clk_set_parent(mclk, pllb); - clk_put(pllb); - if (ret != 0) { - dev_err(&pdev->dev, "Failed to set MCLK parent\n"); - goto err_mclk; - } - - clk_set_rate(mclk, MCLK_RATE); - card->dev = &pdev->dev; /* Parse device node info */ @@ -230,9 +174,6 @@ static int at91sam9g20ek_audio_probe(struct platform_device *pdev) return ret; -err_mclk: - clk_put(mclk); - mclk = NULL; err: atmel_ssc_put_audio(0); return ret; @@ -242,8 +183,6 @@ static int at91sam9g20ek_audio_remove(struct platform_device *pdev) { struct snd_soc_card *card = platform_get_drvdata(pdev); - clk_disable(mclk); - mclk = NULL; snd_soc_unregister_card(card); atmel_ssc_put_audio(0); diff --git a/sound/soc/codecs/cs35l41-lib.c b/sound/soc/codecs/cs35l41-lib.c index e5a56bcbb223..aa6823fbd1a4 100644 --- a/sound/soc/codecs/cs35l41-lib.c +++ b/sound/soc/codecs/cs35l41-lib.c @@ -822,8 +822,8 @@ int cs35l41_otp_unpack(struct device *dev, struct regmap *regmap) word_offset = otp_map_match->word_offset; for (i = 0; i < otp_map_match->num_elements; i++) { - dev_dbg(dev, "bitoffset= %d, word_offset=%d, bit_sum mod 32=%d\n", - bit_offset, word_offset, bit_sum % 32); + dev_dbg(dev, "bitoffset= %d, word_offset=%d, bit_sum mod 32=%d otp_map[i].size = %d\n", + bit_offset, word_offset, bit_sum % 32, otp_map[i].size); if (bit_offset + otp_map[i].size - 1 >= 32) { otp_val = (otp_mem[word_offset] & GENMASK(31, bit_offset)) >> bit_offset; @@ -831,12 +831,14 @@ int cs35l41_otp_unpack(struct device *dev, struct regmap *regmap) GENMASK(bit_offset + otp_map[i].size - 33, 0)) << (32 - bit_offset); bit_offset += otp_map[i].size - 32; - } else { + } else if (bit_offset + otp_map[i].size - 1 >= 0) { otp_val = (otp_mem[word_offset] & GENMASK(bit_offset + otp_map[i].size - 1, bit_offset) ) >> bit_offset; bit_offset += otp_map[i].size; - } + } else /* both bit_offset and otp_map[i].size are 0 */ + otp_val = 0; + bit_sum += otp_map[i].size; if (bit_offset == 32) { diff --git a/sound/soc/codecs/da7219.c b/sound/soc/codecs/da7219.c index 13009d08b09a..c7493549a9a5 100644 --- a/sound/soc/codecs/da7219.c +++ b/sound/soc/codecs/da7219.c @@ -446,7 +446,7 @@ static int da7219_tonegen_freq_put(struct snd_kcontrol *kcontrol, struct soc_mixer_control *mixer_ctrl = (struct soc_mixer_control *) kcontrol->private_value; unsigned int reg = mixer_ctrl->reg; - __le16 val; + __le16 val_new, val_old; int ret; /* @@ -454,13 +454,19 @@ static int da7219_tonegen_freq_put(struct snd_kcontrol *kcontrol, * Therefore we need to convert to little endian here to align with * HW registers. */ - val = cpu_to_le16(ucontrol->value.integer.value[0]); + val_new = cpu_to_le16(ucontrol->value.integer.value[0]); mutex_lock(&da7219->ctrl_lock); - ret = regmap_raw_write(da7219->regmap, reg, &val, sizeof(val)); + ret = regmap_raw_read(da7219->regmap, reg, &val_old, sizeof(val_old)); + if (ret == 0 && (val_old != val_new)) + ret = regmap_raw_write(da7219->regmap, reg, + &val_new, sizeof(val_new)); mutex_unlock(&da7219->ctrl_lock); - return ret; + if (ret < 0) + return ret; + + return val_old != val_new; } diff --git a/sound/soc/codecs/lpass-rx-macro.c b/sound/soc/codecs/lpass-rx-macro.c index 6884ae505e33..3143f9cd7277 100644 --- a/sound/soc/codecs/lpass-rx-macro.c +++ b/sound/soc/codecs/lpass-rx-macro.c @@ -3566,12 +3566,16 @@ static int rx_macro_probe(struct platform_device *pdev) return PTR_ERR(rx->pds); base = devm_platform_ioremap_resource(pdev, 0); - if (IS_ERR(base)) - return PTR_ERR(base); + if (IS_ERR(base)) { + ret = PTR_ERR(base); + goto err; + } rx->regmap = devm_regmap_init_mmio(dev, base, &rx_regmap_config); - if (IS_ERR(rx->regmap)) - return PTR_ERR(rx->regmap); + if (IS_ERR(rx->regmap)) { + ret = PTR_ERR(rx->regmap); + goto err; + } dev_set_drvdata(dev, rx); @@ -3632,6 +3636,8 @@ err_mclk: err_dcodec: clk_disable_unprepare(rx->macro); err: + lpass_macro_pds_exit(rx->pds); + return ret; } diff --git a/sound/soc/codecs/lpass-tx-macro.c b/sound/soc/codecs/lpass-tx-macro.c index 714a411d5337..55503ba480bb 100644 --- a/sound/soc/codecs/lpass-tx-macro.c +++ b/sound/soc/codecs/lpass-tx-macro.c @@ -1828,8 +1828,10 @@ static int tx_macro_probe(struct platform_device *pdev) return PTR_ERR(tx->pds); base = devm_platform_ioremap_resource(pdev, 0); - if (IS_ERR(base)) - return PTR_ERR(base); + if (IS_ERR(base)) { + ret = PTR_ERR(base); + goto err; + } /* Update defaults for lpass sc7280 */ if (of_device_is_compatible(np, "qcom,sc7280-lpass-tx-macro")) { @@ -1846,8 +1848,10 @@ static int tx_macro_probe(struct platform_device *pdev) } tx->regmap = devm_regmap_init_mmio(dev, base, &tx_regmap_config); - if (IS_ERR(tx->regmap)) - return PTR_ERR(tx->regmap); + if (IS_ERR(tx->regmap)) { + ret = PTR_ERR(tx->regmap); + goto err; + } dev_set_drvdata(dev, tx); @@ -1907,6 +1911,8 @@ err_mclk: err_dcodec: clk_disable_unprepare(tx->macro); err: + lpass_macro_pds_exit(tx->pds); + return ret; } diff --git a/sound/soc/codecs/lpass-va-macro.c b/sound/soc/codecs/lpass-va-macro.c index f3cb596058e0..d18b56e60433 100644 --- a/sound/soc/codecs/lpass-va-macro.c +++ b/sound/soc/codecs/lpass-va-macro.c @@ -1434,8 +1434,10 @@ static int va_macro_probe(struct platform_device *pdev) va->dmic_clk_div = VA_MACRO_CLK_DIV_2; } else { ret = va_macro_validate_dmic_sample_rate(sample_rate, va); - if (!ret) - return -EINVAL; + if (!ret) { + ret = -EINVAL; + goto err; + } } base = devm_platform_ioremap_resource(pdev, 0); @@ -1492,6 +1494,8 @@ err_mclk: err_dcodec: clk_disable_unprepare(va->macro); err: + lpass_macro_pds_exit(va->pds); + return ret; } diff --git a/sound/soc/codecs/max98090.c b/sound/soc/codecs/max98090.c index b45ec35cd63c..62b41ca050a2 100644 --- a/sound/soc/codecs/max98090.c +++ b/sound/soc/codecs/max98090.c @@ -413,6 +413,9 @@ static int max98090_put_enab_tlv(struct snd_kcontrol *kcontrol, val = (val >> mc->shift) & mask; + if (sel < 0 || sel > mc->max) + return -EINVAL; + *select = sel; /* Setting a volume is only valid if it is already On */ @@ -427,7 +430,7 @@ static int max98090_put_enab_tlv(struct snd_kcontrol *kcontrol, mask << mc->shift, sel << mc->shift); - return 0; + return *select != val; } static const char *max98090_perf_pwr_text[] = diff --git a/sound/soc/codecs/msm8916-wcd-digital.c b/sound/soc/codecs/msm8916-wcd-digital.c index 9ad7fc0baf07..20a07c92b2fc 100644 --- a/sound/soc/codecs/msm8916-wcd-digital.c +++ b/sound/soc/codecs/msm8916-wcd-digital.c @@ -1206,9 +1206,16 @@ static int msm8916_wcd_digital_probe(struct platform_device *pdev) dev_set_drvdata(dev, priv); - return devm_snd_soc_register_component(dev, &msm8916_wcd_digital, + ret = devm_snd_soc_register_component(dev, &msm8916_wcd_digital, msm8916_wcd_digital_dai, ARRAY_SIZE(msm8916_wcd_digital_dai)); + if (ret) + goto err_mclk; + + return 0; + +err_mclk: + clk_disable_unprepare(priv->mclk); err_clk: clk_disable_unprepare(priv->ahbclk); return ret; diff --git a/sound/soc/codecs/rk817_codec.c b/sound/soc/codecs/rk817_codec.c index 8fffe378618d..cce6f4e7992f 100644 --- a/sound/soc/codecs/rk817_codec.c +++ b/sound/soc/codecs/rk817_codec.c @@ -489,7 +489,7 @@ static int rk817_platform_probe(struct platform_device *pdev) rk817_codec_parse_dt_property(&pdev->dev, rk817_codec_data); - rk817_codec_data->mclk = clk_get(pdev->dev.parent, "mclk"); + rk817_codec_data->mclk = devm_clk_get(pdev->dev.parent, "mclk"); if (IS_ERR(rk817_codec_data->mclk)) { dev_dbg(&pdev->dev, "Unable to get mclk\n"); ret = -ENXIO; diff --git a/sound/soc/codecs/rt5682.c b/sound/soc/codecs/rt5682.c index be68d573a490..2b6c6d6b9771 100644 --- a/sound/soc/codecs/rt5682.c +++ b/sound/soc/codecs/rt5682.c @@ -1100,6 +1100,15 @@ void rt5682_jack_detect_handler(struct work_struct *work) return; } + if (rt5682->is_sdw) { + if (pm_runtime_status_suspended(rt5682->slave->dev.parent)) { + dev_dbg(&rt5682->slave->dev, + "%s: parent device is pm_runtime_status_suspended, skipping jack detection\n", + __func__); + return; + } + } + dapm = snd_soc_component_get_dapm(rt5682->component); snd_soc_dapm_mutex_lock(dapm); @@ -2822,14 +2831,11 @@ static int rt5682_bclk_set_rate(struct clk_hw *hw, unsigned long rate, for_each_component_dais(component, dai) if (dai->id == RT5682_AIF1) - break; - if (!dai) { - dev_err(rt5682->i2c_dev, "dai %d not found in component\n", - RT5682_AIF1); - return -ENODEV; - } + return rt5682_set_bclk1_ratio(dai, factor); - return rt5682_set_bclk1_ratio(dai, factor); + dev_err(rt5682->i2c_dev, "dai %d not found in component\n", + RT5682_AIF1); + return -ENODEV; } static const struct clk_ops rt5682_dai_clk_ops[RT5682_DAI_NUM_CLKS] = { diff --git a/sound/soc/codecs/rt5682s.c b/sound/soc/codecs/rt5682s.c index 1cba8ec7cedb..b55f3ac3a267 100644 --- a/sound/soc/codecs/rt5682s.c +++ b/sound/soc/codecs/rt5682s.c @@ -2687,14 +2687,11 @@ static int rt5682s_bclk_set_rate(struct clk_hw *hw, unsigned long rate, for_each_component_dais(component, dai) if (dai->id == RT5682S_AIF1) - break; - if (!dai) { - dev_err(component->dev, "dai %d not found in component\n", - RT5682S_AIF1); - return -ENODEV; - } + return rt5682s_set_bclk1_ratio(dai, factor); - return rt5682s_set_bclk1_ratio(dai, factor); + dev_err(component->dev, "dai %d not found in component\n", + RT5682S_AIF1); + return -ENODEV; } static const struct clk_ops rt5682s_dai_clk_ops[RT5682S_DAI_NUM_CLKS] = { diff --git a/sound/soc/codecs/rt711.c b/sound/soc/codecs/rt711.c index 6770825d037a..ea25fd58d43a 100644 --- a/sound/soc/codecs/rt711.c +++ b/sound/soc/codecs/rt711.c @@ -245,6 +245,13 @@ static void rt711_jack_detect_handler(struct work_struct *work) if (!rt711->component->card->instantiated) return; + if (pm_runtime_status_suspended(rt711->slave->dev.parent)) { + dev_dbg(&rt711->slave->dev, + "%s: parent device is pm_runtime_status_suspended, skipping jack detection\n", + __func__); + return; + } + reg = RT711_VERB_GET_PIN_SENSE | RT711_HP_OUT; ret = regmap_read(rt711->regmap, reg, &jack_status); if (ret < 0) diff --git a/sound/soc/codecs/rt9120.c b/sound/soc/codecs/rt9120.c index 7aa1772a915f..6e0d7cf0c8c9 100644 --- a/sound/soc/codecs/rt9120.c +++ b/sound/soc/codecs/rt9120.c @@ -341,7 +341,6 @@ static int rt9120_get_reg_size(unsigned int reg) { switch (reg) { case 0x00: - case 0x09: case 0x20 ... 0x27: return 2; case 0x30 ... 0x3D: diff --git a/sound/soc/codecs/wcd934x.c b/sound/soc/codecs/wcd934x.c index 1e75e93cf28f..6298ebe96e94 100644 --- a/sound/soc/codecs/wcd934x.c +++ b/sound/soc/codecs/wcd934x.c @@ -1274,29 +1274,7 @@ static int wcd934x_set_sido_input_src(struct wcd934x_codec *wcd, int sido_src) if (sido_src == wcd->sido_input_src) return 0; - if (sido_src == SIDO_SOURCE_INTERNAL) { - regmap_update_bits(wcd->regmap, WCD934X_ANA_BUCK_CTL, - WCD934X_ANA_BUCK_HI_ACCU_EN_MASK, 0); - usleep_range(100, 110); - regmap_update_bits(wcd->regmap, WCD934X_ANA_BUCK_CTL, - WCD934X_ANA_BUCK_HI_ACCU_PRE_ENX_MASK, 0x0); - usleep_range(100, 110); - regmap_update_bits(wcd->regmap, WCD934X_ANA_RCO, - WCD934X_ANA_RCO_BG_EN_MASK, 0); - usleep_range(100, 110); - regmap_update_bits(wcd->regmap, WCD934X_ANA_BUCK_CTL, - WCD934X_ANA_BUCK_PRE_EN1_MASK, - WCD934X_ANA_BUCK_PRE_EN1_ENABLE); - usleep_range(100, 110); - regmap_update_bits(wcd->regmap, WCD934X_ANA_BUCK_CTL, - WCD934X_ANA_BUCK_PRE_EN2_MASK, - WCD934X_ANA_BUCK_PRE_EN2_ENABLE); - usleep_range(100, 110); - regmap_update_bits(wcd->regmap, WCD934X_ANA_BUCK_CTL, - WCD934X_ANA_BUCK_HI_ACCU_EN_MASK, - WCD934X_ANA_BUCK_HI_ACCU_ENABLE); - usleep_range(100, 110); - } else if (sido_src == SIDO_SOURCE_RCO_BG) { + if (sido_src == SIDO_SOURCE_RCO_BG) { regmap_update_bits(wcd->regmap, WCD934X_ANA_RCO, WCD934X_ANA_RCO_BG_EN_MASK, WCD934X_ANA_RCO_BG_ENABLE); @@ -1382,8 +1360,6 @@ static int wcd934x_disable_ana_bias_and_syclk(struct wcd934x_codec *wcd) regmap_update_bits(wcd->regmap, WCD934X_CLK_SYS_MCLK_PRG, WCD934X_EXT_CLK_BUF_EN_MASK | WCD934X_MCLK_EN_MASK, 0x0); - wcd934x_set_sido_input_src(wcd, SIDO_SOURCE_INTERNAL); - regmap_update_bits(wcd->regmap, WCD934X_ANA_BIAS, WCD934X_ANA_BIAS_EN_MASK, 0); regmap_update_bits(wcd->regmap, WCD934X_ANA_BIAS, diff --git a/sound/soc/codecs/wm8731.c b/sound/soc/codecs/wm8731.c index 5d4949c2ec9b..b14c6d104e6d 100644 --- a/sound/soc/codecs/wm8731.c +++ b/sound/soc/codecs/wm8731.c @@ -602,7 +602,7 @@ static int wm8731_hw_init(struct device *dev, struct wm8731_priv *wm8731) ret = wm8731_reset(wm8731->regmap); if (ret < 0) { dev_err(dev, "Failed to issue reset: %d\n", ret); - goto err_regulator_enable; + goto err; } /* Clear POWEROFF, keep everything else disabled */ @@ -619,10 +619,7 @@ static int wm8731_hw_init(struct device *dev, struct wm8731_priv *wm8731) regcache_mark_dirty(wm8731->regmap); -err_regulator_enable: - /* Regulators will be enabled by bias management */ - regulator_bulk_disable(ARRAY_SIZE(wm8731->supplies), wm8731->supplies); - +err: return ret; } @@ -760,21 +757,27 @@ static int wm8731_i2c_probe(struct i2c_client *i2c, ret = PTR_ERR(wm8731->regmap); dev_err(&i2c->dev, "Failed to allocate register map: %d\n", ret); - return ret; + goto err_regulator_enable; } ret = wm8731_hw_init(&i2c->dev, wm8731); if (ret != 0) - return ret; + goto err_regulator_enable; ret = devm_snd_soc_register_component(&i2c->dev, &soc_component_dev_wm8731, &wm8731_dai, 1); if (ret != 0) { dev_err(&i2c->dev, "Failed to register CODEC: %d\n", ret); - return ret; + goto err_regulator_enable; } return 0; + +err_regulator_enable: + /* Regulators will be enabled by bias management */ + regulator_bulk_disable(ARRAY_SIZE(wm8731->supplies), wm8731->supplies); + + return ret; } static const struct i2c_device_id wm8731_i2c_id[] = { diff --git a/sound/soc/codecs/wm8958-dsp2.c b/sound/soc/codecs/wm8958-dsp2.c index e4018ba3b19a..7878c7a58ff1 100644 --- a/sound/soc/codecs/wm8958-dsp2.c +++ b/sound/soc/codecs/wm8958-dsp2.c @@ -530,7 +530,7 @@ static int wm8958_mbc_put(struct snd_kcontrol *kcontrol, wm8958_dsp_apply(component, mbc, wm8994->mbc_ena[mbc]); - return 0; + return 1; } #define WM8958_MBC_SWITCH(xname, xval) {\ @@ -656,7 +656,7 @@ static int wm8958_vss_put(struct snd_kcontrol *kcontrol, wm8958_dsp_apply(component, vss, wm8994->vss_ena[vss]); - return 0; + return 1; } @@ -730,7 +730,7 @@ static int wm8958_hpf_put(struct snd_kcontrol *kcontrol, wm8958_dsp_apply(component, hpf % 3, ucontrol->value.integer.value[0]); - return 0; + return 1; } #define WM8958_HPF_SWITCH(xname, xval) {\ @@ -824,7 +824,7 @@ static int wm8958_enh_eq_put(struct snd_kcontrol *kcontrol, wm8958_dsp_apply(component, eq, ucontrol->value.integer.value[0]); - return 0; + return 1; } #define WM8958_ENH_EQ_SWITCH(xname, xval) {\ diff --git a/sound/soc/fsl/fsl_sai.c b/sound/soc/fsl/fsl_sai.c index 4650a6931a94..ffc24afb5a7a 100644 --- a/sound/soc/fsl/fsl_sai.c +++ b/sound/soc/fsl/fsl_sai.c @@ -372,7 +372,7 @@ static int fsl_sai_set_bclk(struct snd_soc_dai *dai, bool tx, u32 freq) continue; if (ratio == 1 && !support_1_1_ratio) continue; - else if (ratio & 1) + if ((ratio & 1) && ratio > 1) continue; diff = abs((long)clk_rate - ratio * freq); diff --git a/sound/soc/generic/simple-card-utils.c b/sound/soc/generic/simple-card-utils.c index 8e037835bc58..da0c27828ce6 100644 --- a/sound/soc/generic/simple-card-utils.c +++ b/sound/soc/generic/simple-card-utils.c @@ -322,7 +322,7 @@ void asoc_simple_shutdown(struct snd_pcm_substream *substream) if (props->mclk_fs && !dai->clk_fixed && !snd_soc_dai_active(cpu_dai)) snd_soc_dai_set_sysclk(cpu_dai, - 0, 0, SND_SOC_CLOCK_IN); + 0, 0, SND_SOC_CLOCK_OUT); asoc_simple_clk_disable(dai); } @@ -364,13 +364,15 @@ static int asoc_simple_set_tdm(struct snd_soc_dai *dai, struct snd_pcm_hw_params *params) { int sample_bits = params_width(params); - int slot_width = simple_dai->slot_width; - int slot_count = simple_dai->slots; + int slot_width, slot_count; int i, ret; if (!simple_dai || !simple_dai->tdm_width_map) return 0; + slot_width = simple_dai->slot_width; + slot_count = simple_dai->slots; + if (slot_width == 0) slot_width = sample_bits; diff --git a/sound/soc/intel/boards/sof_es8336.c b/sound/soc/intel/boards/sof_es8336.c index 5e0529aa4f1d..9d617831dd20 100644 --- a/sound/soc/intel/boards/sof_es8336.c +++ b/sound/soc/intel/boards/sof_es8336.c @@ -27,9 +27,11 @@ #define SOF_ES8336_SSP_CODEC(quirk) ((quirk) & GENMASK(3, 0)) #define SOF_ES8336_SSP_CODEC_MASK (GENMASK(3, 0)) -#define SOF_ES8336_TGL_GPIO_QUIRK BIT(4) +#define SOF_ES8336_SPEAKERS_EN_GPIO1_QUIRK BIT(4) #define SOF_ES8336_ENABLE_DMIC BIT(5) #define SOF_ES8336_JD_INVERTED BIT(6) +#define SOF_ES8336_HEADPHONE_GPIO BIT(7) +#define SOC_ES8336_HEADSET_MIC1 BIT(8) static unsigned long quirk; @@ -39,7 +41,7 @@ MODULE_PARM_DESC(quirk, "Board-specific quirk override"); struct sof_es8336_private { struct device *codec_dev; - struct gpio_desc *gpio_pa; + struct gpio_desc *gpio_speakers, *gpio_headphone; struct snd_soc_jack jack; struct list_head hdmi_pcm_list; bool speaker_en; @@ -51,19 +53,31 @@ struct sof_hdmi_pcm { int device; }; -static const struct acpi_gpio_params pa_enable_gpio = { 0, 0, true }; -static const struct acpi_gpio_mapping acpi_es8336_gpios[] = { - { "pa-enable-gpios", &pa_enable_gpio, 1 }, +static const struct acpi_gpio_params enable_gpio0 = { 0, 0, true }; +static const struct acpi_gpio_params enable_gpio1 = { 1, 0, true }; + +static const struct acpi_gpio_mapping acpi_speakers_enable_gpio0[] = { + { "speakers-enable-gpios", &enable_gpio0, 1 }, { } }; -static const struct acpi_gpio_params quirk_pa_enable_gpio = { 1, 0, true }; -static const struct acpi_gpio_mapping quirk_acpi_es8336_gpios[] = { - { "pa-enable-gpios", &quirk_pa_enable_gpio, 1 }, +static const struct acpi_gpio_mapping acpi_speakers_enable_gpio1[] = { + { "speakers-enable-gpios", &enable_gpio1, 1 }, +}; + +static const struct acpi_gpio_mapping acpi_enable_both_gpios[] = { + { "speakers-enable-gpios", &enable_gpio0, 1 }, + { "headphone-enable-gpios", &enable_gpio1, 1 }, { } }; -static const struct acpi_gpio_mapping *gpio_mapping = acpi_es8336_gpios; +static const struct acpi_gpio_mapping acpi_enable_both_gpios_rev_order[] = { + { "speakers-enable-gpios", &enable_gpio1, 1 }, + { "headphone-enable-gpios", &enable_gpio0, 1 }, + { } +}; + +static const struct acpi_gpio_mapping *gpio_mapping = acpi_speakers_enable_gpio0; static void log_quirks(struct device *dev) { @@ -71,10 +85,14 @@ static void log_quirks(struct device *dev) dev_info(dev, "quirk SSP%ld\n", SOF_ES8336_SSP_CODEC(quirk)); if (quirk & SOF_ES8336_ENABLE_DMIC) dev_info(dev, "quirk DMIC enabled\n"); - if (quirk & SOF_ES8336_TGL_GPIO_QUIRK) - dev_info(dev, "quirk TGL GPIO enabled\n"); + if (quirk & SOF_ES8336_SPEAKERS_EN_GPIO1_QUIRK) + dev_info(dev, "Speakers GPIO1 quirk enabled\n"); + if (quirk & SOF_ES8336_HEADPHONE_GPIO) + dev_info(dev, "quirk headphone GPIO enabled\n"); if (quirk & SOF_ES8336_JD_INVERTED) dev_info(dev, "quirk JD inverted enabled\n"); + if (quirk & SOC_ES8336_HEADSET_MIC1) + dev_info(dev, "quirk headset at mic1 port enabled\n"); } static int sof_es8316_speaker_power_event(struct snd_soc_dapm_widget *w, @@ -83,12 +101,23 @@ static int sof_es8316_speaker_power_event(struct snd_soc_dapm_widget *w, struct snd_soc_card *card = w->dapm->card; struct sof_es8336_private *priv = snd_soc_card_get_drvdata(card); + if (priv->speaker_en == !SND_SOC_DAPM_EVENT_ON(event)) + return 0; + + priv->speaker_en = !SND_SOC_DAPM_EVENT_ON(event); + + if (SND_SOC_DAPM_EVENT_ON(event)) + msleep(70); + + gpiod_set_value_cansleep(priv->gpio_speakers, priv->speaker_en); + + if (!(quirk & SOF_ES8336_HEADPHONE_GPIO)) + return 0; + if (SND_SOC_DAPM_EVENT_ON(event)) - priv->speaker_en = false; - else - priv->speaker_en = true; + msleep(70); - gpiod_set_value_cansleep(priv->gpio_pa, priv->speaker_en); + gpiod_set_value_cansleep(priv->gpio_headphone, priv->speaker_en); return 0; } @@ -114,18 +143,23 @@ static const struct snd_soc_dapm_route sof_es8316_audio_map[] = { /* * There is no separate speaker output instead the speakers are muxed to - * the HP outputs. The mux is controlled by the "Speaker Power" supply. + * the HP outputs. The mux is controlled Speaker and/or headphone switch. */ {"Speaker", NULL, "HPOL"}, {"Speaker", NULL, "HPOR"}, {"Speaker", NULL, "Speaker Power"}, }; -static const struct snd_soc_dapm_route sof_es8316_intmic_in1_map[] = { +static const struct snd_soc_dapm_route sof_es8316_headset_mic2_map[] = { {"MIC1", NULL, "Internal Mic"}, {"MIC2", NULL, "Headset Mic"}, }; +static const struct snd_soc_dapm_route sof_es8316_headset_mic1_map[] = { + {"MIC2", NULL, "Internal Mic"}, + {"MIC1", NULL, "Headset Mic"}, +}; + static const struct snd_soc_dapm_route dmic_map[] = { /* digital mics */ {"DMic", NULL, "SoC DMIC"}, @@ -199,8 +233,13 @@ static int sof_es8316_init(struct snd_soc_pcm_runtime *runtime) card->dapm.idle_bias_off = true; - custom_map = sof_es8316_intmic_in1_map; - num_routes = ARRAY_SIZE(sof_es8316_intmic_in1_map); + if (quirk & SOC_ES8336_HEADSET_MIC1) { + custom_map = sof_es8316_headset_mic1_map; + num_routes = ARRAY_SIZE(sof_es8316_headset_mic1_map); + } else { + custom_map = sof_es8316_headset_mic2_map; + num_routes = ARRAY_SIZE(sof_es8316_headset_mic2_map); + } ret = snd_soc_dapm_add_routes(&card->dapm, custom_map, num_routes); if (ret) @@ -233,8 +272,14 @@ static int sof_es8336_quirk_cb(const struct dmi_system_id *id) { quirk = (unsigned long)id->driver_data; - if (quirk & SOF_ES8336_TGL_GPIO_QUIRK) - gpio_mapping = quirk_acpi_es8336_gpios; + if (quirk & SOF_ES8336_HEADPHONE_GPIO) { + if (quirk & SOF_ES8336_SPEAKERS_EN_GPIO1_QUIRK) + gpio_mapping = acpi_enable_both_gpios; + else + gpio_mapping = acpi_enable_both_gpios_rev_order; + } else if (quirk & SOF_ES8336_SPEAKERS_EN_GPIO1_QUIRK) { + gpio_mapping = acpi_speakers_enable_gpio1; + } return 1; } @@ -257,7 +302,16 @@ static const struct dmi_system_id sof_es8336_quirk_table[] = { DMI_MATCH(DMI_SYS_VENDOR, "IP3 tech"), DMI_MATCH(DMI_BOARD_NAME, "WN1"), }, - .driver_data = (void *)(SOF_ES8336_TGL_GPIO_QUIRK) + .driver_data = (void *)(SOF_ES8336_SPEAKERS_EN_GPIO1_QUIRK) + }, + { + .callback = sof_es8336_quirk_cb, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "HUAWEI"), + DMI_MATCH(DMI_BOARD_NAME, "BOHB-WAX9-PCB-B2"), + }, + .driver_data = (void *)(SOF_ES8336_HEADPHONE_GPIO | + SOC_ES8336_HEADSET_MIC1) }, {} }; @@ -585,10 +639,17 @@ static int sof_es8336_probe(struct platform_device *pdev) if (ret) dev_warn(codec_dev, "unable to add GPIO mapping table\n"); - priv->gpio_pa = gpiod_get_optional(codec_dev, "pa-enable", GPIOD_OUT_LOW); - if (IS_ERR(priv->gpio_pa)) { - ret = dev_err_probe(dev, PTR_ERR(priv->gpio_pa), - "could not get pa-enable GPIO\n"); + priv->gpio_speakers = gpiod_get_optional(codec_dev, "speakers-enable", GPIOD_OUT_LOW); + if (IS_ERR(priv->gpio_speakers)) { + ret = dev_err_probe(dev, PTR_ERR(priv->gpio_speakers), + "could not get speakers-enable GPIO\n"); + goto err_put_codec; + } + + priv->gpio_headphone = gpiod_get_optional(codec_dev, "headphone-enable", GPIOD_OUT_LOW); + if (IS_ERR(priv->gpio_headphone)) { + ret = dev_err_probe(dev, PTR_ERR(priv->gpio_headphone), + "could not get headphone-enable GPIO\n"); goto err_put_codec; } @@ -604,7 +665,7 @@ static int sof_es8336_probe(struct platform_device *pdev) ret = devm_snd_soc_register_card(dev, card); if (ret) { - gpiod_put(priv->gpio_pa); + gpiod_put(priv->gpio_speakers); dev_err(dev, "snd_soc_register_card failed: %d\n", ret); goto err_put_codec; } @@ -622,7 +683,7 @@ static int sof_es8336_remove(struct platform_device *pdev) struct snd_soc_card *card = platform_get_drvdata(pdev); struct sof_es8336_private *priv = snd_soc_card_get_drvdata(card); - gpiod_put(priv->gpio_pa); + gpiod_put(priv->gpio_speakers); device_remove_software_node(priv->codec_dev); put_device(priv->codec_dev); diff --git a/sound/soc/intel/boards/sof_rt5682.c b/sound/soc/intel/boards/sof_rt5682.c index ebec4d15edaa..7126fcb63d90 100644 --- a/sound/soc/intel/boards/sof_rt5682.c +++ b/sound/soc/intel/boards/sof_rt5682.c @@ -212,6 +212,19 @@ static const struct dmi_system_id sof_rt5682_quirk_table[] = { SOF_SSP_BT_OFFLOAD_PRESENT), }, + { + .callback = sof_rt5682_quirk_cb, + .matches = { + DMI_MATCH(DMI_PRODUCT_FAMILY, "Google_Brya"), + DMI_MATCH(DMI_OEM_STRING, "AUDIO-MAX98360_ALC5682I_I2S_AMP_SSP2"), + }, + .driver_data = (void *)(SOF_RT5682_MCLK_EN | + SOF_RT5682_SSP_CODEC(0) | + SOF_SPEAKER_AMP_PRESENT | + SOF_MAX98360A_SPEAKER_AMP_PRESENT | + SOF_RT5682_SSP_AMP(2) | + SOF_RT5682_NUM_HDMIDEV(4)), + }, {} }; diff --git a/sound/soc/intel/common/soc-acpi-intel-tgl-match.c b/sound/soc/intel/common/soc-acpi-intel-tgl-match.c index 6edc9b7108cd..ef19150e7b2e 100644 --- a/sound/soc/intel/common/soc-acpi-intel-tgl-match.c +++ b/sound/soc/intel/common/soc-acpi-intel-tgl-match.c @@ -132,13 +132,13 @@ static const struct snd_soc_acpi_adr_device mx8373_1_adr[] = { { .adr = 0x000123019F837300ull, .num_endpoints = 1, - .endpoints = &spk_l_endpoint, + .endpoints = &spk_r_endpoint, .name_prefix = "Right" }, { .adr = 0x000127019F837300ull, .num_endpoints = 1, - .endpoints = &spk_r_endpoint, + .endpoints = &spk_l_endpoint, .name_prefix = "Left" } }; diff --git a/sound/soc/meson/aiu-acodec-ctrl.c b/sound/soc/meson/aiu-acodec-ctrl.c index 27a6d3259c50..3776b073a3db 100644 --- a/sound/soc/meson/aiu-acodec-ctrl.c +++ b/sound/soc/meson/aiu-acodec-ctrl.c @@ -58,7 +58,7 @@ static int aiu_acodec_ctrl_mux_put_enum(struct snd_kcontrol *kcontrol, snd_soc_dapm_mux_update_power(dapm, kcontrol, mux, e, NULL); - return 0; + return 1; } static SOC_ENUM_SINGLE_DECL(aiu_acodec_ctrl_mux_enum, AIU_ACODEC_CTRL, @@ -193,6 +193,9 @@ static const struct snd_soc_component_driver aiu_acodec_ctrl_component = { .of_xlate_dai_name = aiu_acodec_of_xlate_dai_name, .endianness = 1, .non_legacy_dai_naming = 1, +#ifdef CONFIG_DEBUG_FS + .debugfs_prefix = "acodec", +#endif }; int aiu_acodec_ctrl_register_component(struct device *dev) diff --git a/sound/soc/meson/aiu-codec-ctrl.c b/sound/soc/meson/aiu-codec-ctrl.c index c3ea733fce91..286ac4983d40 100644 --- a/sound/soc/meson/aiu-codec-ctrl.c +++ b/sound/soc/meson/aiu-codec-ctrl.c @@ -57,7 +57,7 @@ static int aiu_codec_ctrl_mux_put_enum(struct snd_kcontrol *kcontrol, snd_soc_dapm_mux_update_power(dapm, kcontrol, mux, e, NULL); - return 0; + return 1; } static SOC_ENUM_SINGLE_DECL(aiu_hdmi_ctrl_mux_enum, AIU_HDMI_CLK_DATA_CTRL, @@ -140,6 +140,9 @@ static const struct snd_soc_component_driver aiu_hdmi_ctrl_component = { .of_xlate_dai_name = aiu_hdmi_of_xlate_dai_name, .endianness = 1, .non_legacy_dai_naming = 1, +#ifdef CONFIG_DEBUG_FS + .debugfs_prefix = "hdmi", +#endif }; int aiu_hdmi_ctrl_register_component(struct device *dev) diff --git a/sound/soc/meson/aiu.c b/sound/soc/meson/aiu.c index d299a70db7e5..88e611e64d14 100644 --- a/sound/soc/meson/aiu.c +++ b/sound/soc/meson/aiu.c @@ -103,6 +103,9 @@ static const struct snd_soc_component_driver aiu_cpu_component = { .pointer = aiu_fifo_pointer, .probe = aiu_cpu_component_probe, .remove = aiu_cpu_component_remove, +#ifdef CONFIG_DEBUG_FS + .debugfs_prefix = "cpu", +#endif }; static struct snd_soc_dai_driver aiu_cpu_dai_drv[] = { diff --git a/sound/soc/meson/axg-card.c b/sound/soc/meson/axg-card.c index cbbaa55d92a6..2b77010c2c5c 100644 --- a/sound/soc/meson/axg-card.c +++ b/sound/soc/meson/axg-card.c @@ -320,7 +320,6 @@ static int axg_card_add_link(struct snd_soc_card *card, struct device_node *np, dai_link->cpus = cpu; dai_link->num_cpus = 1; - dai_link->nonatomic = true; ret = meson_card_parse_dai(card, np, &dai_link->cpus->of_node, &dai_link->cpus->dai_name); diff --git a/sound/soc/meson/axg-tdm-interface.c b/sound/soc/meson/axg-tdm-interface.c index 0c31934a9630..e076ced30025 100644 --- a/sound/soc/meson/axg-tdm-interface.c +++ b/sound/soc/meson/axg-tdm-interface.c @@ -351,29 +351,13 @@ static int axg_tdm_iface_hw_free(struct snd_pcm_substream *substream, return 0; } -static int axg_tdm_iface_trigger(struct snd_pcm_substream *substream, - int cmd, +static int axg_tdm_iface_prepare(struct snd_pcm_substream *substream, struct snd_soc_dai *dai) { - struct axg_tdm_stream *ts = - snd_soc_dai_get_dma_data(dai, substream); - - switch (cmd) { - case SNDRV_PCM_TRIGGER_START: - case SNDRV_PCM_TRIGGER_RESUME: - case SNDRV_PCM_TRIGGER_PAUSE_RELEASE: - axg_tdm_stream_start(ts); - break; - case SNDRV_PCM_TRIGGER_SUSPEND: - case SNDRV_PCM_TRIGGER_PAUSE_PUSH: - case SNDRV_PCM_TRIGGER_STOP: - axg_tdm_stream_stop(ts); - break; - default: - return -EINVAL; - } + struct axg_tdm_stream *ts = snd_soc_dai_get_dma_data(dai, substream); - return 0; + /* Force all attached formatters to update */ + return axg_tdm_stream_reset(ts); } static int axg_tdm_iface_remove_dai(struct snd_soc_dai *dai) @@ -413,8 +397,8 @@ static const struct snd_soc_dai_ops axg_tdm_iface_ops = { .set_fmt = axg_tdm_iface_set_fmt, .startup = axg_tdm_iface_startup, .hw_params = axg_tdm_iface_hw_params, + .prepare = axg_tdm_iface_prepare, .hw_free = axg_tdm_iface_hw_free, - .trigger = axg_tdm_iface_trigger, }; /* TDM Backend DAIs */ diff --git a/sound/soc/meson/g12a-tohdmitx.c b/sound/soc/meson/g12a-tohdmitx.c index 9b2b59536ced..6c99052feafd 100644 --- a/sound/soc/meson/g12a-tohdmitx.c +++ b/sound/soc/meson/g12a-tohdmitx.c @@ -67,7 +67,7 @@ static int g12a_tohdmitx_i2s_mux_put_enum(struct snd_kcontrol *kcontrol, snd_soc_dapm_mux_update_power(dapm, kcontrol, mux, e, NULL); - return 0; + return 1; } static SOC_ENUM_SINGLE_DECL(g12a_tohdmitx_i2s_mux_enum, TOHDMITX_CTRL0, diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c index ce153ac2c3ab..8c7da82a62ca 100644 --- a/sound/soc/soc-core.c +++ b/sound/soc/soc-core.c @@ -2587,6 +2587,11 @@ int snd_soc_component_initialize(struct snd_soc_component *component, component->dev = dev; component->driver = driver; +#ifdef CONFIG_DEBUG_FS + if (!component->debugfs_prefix) + component->debugfs_prefix = driver->debugfs_prefix; +#endif + return 0; } EXPORT_SYMBOL_GPL(snd_soc_component_initialize); diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c index b435b5c4cfb7..ca917a849c42 100644 --- a/sound/soc/soc-dapm.c +++ b/sound/soc/soc-dapm.c @@ -1687,8 +1687,7 @@ static void dapm_seq_run(struct snd_soc_card *card, switch (w->id) { case snd_soc_dapm_pre: if (!w->event) - list_for_each_entry_safe_continue(w, n, list, - power_list); + continue; if (event == SND_SOC_DAPM_STREAM_START) ret = w->event(w, @@ -1700,8 +1699,7 @@ static void dapm_seq_run(struct snd_soc_card *card, case snd_soc_dapm_post: if (!w->event) - list_for_each_entry_safe_continue(w, n, list, - power_list); + continue; if (event == SND_SOC_DAPM_STREAM_START) ret = w->event(w, diff --git a/sound/soc/soc-generic-dmaengine-pcm.c b/sound/soc/soc-generic-dmaengine-pcm.c index 2ab2ddc1294d..285441d6aeed 100644 --- a/sound/soc/soc-generic-dmaengine-pcm.c +++ b/sound/soc/soc-generic-dmaengine-pcm.c @@ -86,10 +86,10 @@ static int dmaengine_pcm_hw_params(struct snd_soc_component *component, memset(&slave_config, 0, sizeof(slave_config)); - if (pcm->config && pcm->config->prepare_slave_config) - prepare_slave_config = pcm->config->prepare_slave_config; - else + if (!pcm->config) prepare_slave_config = snd_dmaengine_pcm_prepare_slave_config; + else + prepare_slave_config = pcm->config->prepare_slave_config; if (prepare_slave_config) { int ret = prepare_slave_config(substream, params, &slave_config); diff --git a/sound/soc/soc-ops.c b/sound/soc/soc-ops.c index a0ca58ba1627..e693070f51fe 100644 --- a/sound/soc/soc-ops.c +++ b/sound/soc/soc-ops.c @@ -461,7 +461,7 @@ int snd_soc_put_volsw_sx(struct snd_kcontrol *kcontrol, ret = err; } } - return err; + return ret; } EXPORT_SYMBOL_GPL(snd_soc_put_volsw_sx); @@ -519,7 +519,15 @@ int snd_soc_put_volsw_range(struct snd_kcontrol *kcontrol, unsigned int mask = (1 << fls(max)) - 1; unsigned int invert = mc->invert; unsigned int val, val_mask; - int err, ret; + int err, ret, tmp; + + tmp = ucontrol->value.integer.value[0]; + if (tmp < 0) + return -EINVAL; + if (mc->platform_max && tmp > mc->platform_max) + return -EINVAL; + if (tmp > mc->max - mc->min + 1) + return -EINVAL; if (invert) val = (max - ucontrol->value.integer.value[0]) & mask; @@ -534,6 +542,14 @@ int snd_soc_put_volsw_range(struct snd_kcontrol *kcontrol, ret = err; if (snd_soc_volsw_is_stereo(mc)) { + tmp = ucontrol->value.integer.value[1]; + if (tmp < 0) + return -EINVAL; + if (mc->platform_max && tmp > mc->platform_max) + return -EINVAL; + if (tmp > mc->max - mc->min + 1) + return -EINVAL; + if (invert) val = (max - ucontrol->value.integer.value[1]) & mask; else diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c index 9a954680d492..11c9853e9e80 100644 --- a/sound/soc/soc-pcm.c +++ b/sound/soc/soc-pcm.c @@ -1214,7 +1214,7 @@ static int dpcm_be_connect(struct snd_soc_pcm_runtime *fe, be_substream->pcm->nonatomic = 1; } - dpcm = kzalloc(sizeof(struct snd_soc_dpcm), GFP_ATOMIC); + dpcm = kzalloc(sizeof(struct snd_soc_dpcm), GFP_KERNEL); if (!dpcm) return -ENOMEM; diff --git a/sound/soc/soc-topology.c b/sound/soc/soc-topology.c index 72e50df7052c..3bb90a819650 100644 --- a/sound/soc/soc-topology.c +++ b/sound/soc/soc-topology.c @@ -1436,12 +1436,12 @@ static int soc_tplg_dapm_widget_create(struct soc_tplg *tplg, template.num_kcontrols = le32_to_cpu(w->num_kcontrols); kc = devm_kcalloc(tplg->dev, le32_to_cpu(w->num_kcontrols), sizeof(*kc), GFP_KERNEL); if (!kc) - goto err; + goto hdr_err; kcontrol_type = devm_kcalloc(tplg->dev, le32_to_cpu(w->num_kcontrols), sizeof(unsigned int), GFP_KERNEL); if (!kcontrol_type) - goto err; + goto hdr_err; for (i = 0; i < le32_to_cpu(w->num_kcontrols); i++) { control_hdr = (struct snd_soc_tplg_ctl_hdr *)tplg->pos; diff --git a/sound/soc/sof/sof-pci-dev.c b/sound/soc/sof/sof-pci-dev.c index 4c9596742844..7fa2649e56e5 100644 --- a/sound/soc/sof/sof-pci-dev.c +++ b/sound/soc/sof/sof-pci-dev.c @@ -83,7 +83,14 @@ static const struct dmi_system_id sof_tplg_table[] = { }, .driver_data = "sof-adl-max98357a-rt5682-2way.tplg", }, - + { + .callback = sof_tplg_cb, + .matches = { + DMI_MATCH(DMI_PRODUCT_FAMILY, "Google_Brya"), + DMI_MATCH(DMI_OEM_STRING, "AUDIO-MAX98360_ALC5682I_I2S_AMP_SSP2"), + }, + .driver_data = "sof-adl-max98357a-rt5682.tplg", + }, {} }; @@ -146,6 +153,11 @@ int sof_pci_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) dev_dbg(&pci->dev, "PCI DSP detected"); + if (!desc) { + dev_err(dev, "error: no matching PCI descriptor\n"); + return -ENODEV; + } + if (!desc->ops) { dev_err(dev, "error: no matching PCI descriptor ops\n"); return -ENODEV; diff --git a/sound/soc/sof/topology.c b/sound/soc/sof/topology.c index 9b11e9795a7a..3e5b319b44c7 100644 --- a/sound/soc/sof/topology.c +++ b/sound/soc/sof/topology.c @@ -904,8 +904,10 @@ static int sof_control_load(struct snd_soc_component *scomp, int index, return -ENOMEM; scontrol->name = kstrdup(hdr->name, GFP_KERNEL); - if (!scontrol->name) + if (!scontrol->name) { + kfree(scontrol); return -ENOMEM; + } scontrol->scomp = scomp; scontrol->access = kc->access; @@ -941,11 +943,13 @@ static int sof_control_load(struct snd_soc_component *scomp, int index, default: dev_warn(scomp->dev, "control type not supported %d:%d:%d\n", hdr->ops.get, hdr->ops.put, hdr->ops.info); + kfree(scontrol->name); kfree(scontrol); return 0; } if (ret < 0) { + kfree(scontrol->name); kfree(scontrol); return ret; } @@ -1068,6 +1072,46 @@ static int sof_connect_dai_widget(struct snd_soc_component *scomp, return 0; } +static void sof_disconnect_dai_widget(struct snd_soc_component *scomp, + struct snd_soc_dapm_widget *w) +{ + struct snd_soc_card *card = scomp->card; + struct snd_soc_pcm_runtime *rtd; + struct snd_soc_dai *cpu_dai; + int i; + + if (!w->sname) + return; + + list_for_each_entry(rtd, &card->rtd_list, list) { + /* does stream match DAI link ? */ + if (!rtd->dai_link->stream_name || + strcmp(w->sname, rtd->dai_link->stream_name)) + continue; + + switch (w->id) { + case snd_soc_dapm_dai_out: + for_each_rtd_cpu_dais(rtd, i, cpu_dai) { + if (cpu_dai->capture_widget == w) { + cpu_dai->capture_widget = NULL; + break; + } + } + break; + case snd_soc_dapm_dai_in: + for_each_rtd_cpu_dais(rtd, i, cpu_dai) { + if (cpu_dai->playback_widget == w) { + cpu_dai->playback_widget = NULL; + break; + } + } + break; + default: + break; + } + } +} + /* bind PCM ID to host component ID */ static int spcm_bind(struct snd_soc_component *scomp, struct snd_sof_pcm *spcm, int dir) @@ -1353,6 +1397,9 @@ static int sof_widget_unload(struct snd_soc_component *scomp, if (dai) list_del(&dai->list); + + sof_disconnect_dai_widget(scomp, widget); + break; default: break; @@ -1380,6 +1427,7 @@ static int sof_widget_unload(struct snd_soc_component *scomp, } kfree(scontrol->ipc_control_data); list_del(&scontrol->list); + kfree(scontrol->name); kfree(scontrol); } diff --git a/sound/usb/midi.c b/sound/usb/midi.c index 2c01649c70f6..7c6ca2b433a5 100644 --- a/sound/usb/midi.c +++ b/sound/usb/midi.c @@ -1194,6 +1194,7 @@ static void snd_usbmidi_output_drain(struct snd_rawmidi_substream *substream) } while (drain_urbs && timeout); finish_wait(&ep->drain_wait, &wait); } + port->active = 0; spin_unlock_irq(&ep->buffer_lock); } diff --git a/sound/usb/mixer_maps.c b/sound/usb/mixer_maps.c index 64f5544d0a0a..7ef7a8abcc2b 100644 --- a/sound/usb/mixer_maps.c +++ b/sound/usb/mixer_maps.c @@ -599,6 +599,10 @@ static const struct usbmix_ctl_map usbmix_ctl_maps[] = { .id = USB_ID(0x0db0, 0x419c), .map = msi_mpg_x570s_carbon_max_wifi_alc4080_map, }, + { /* MSI MAG X570S Torpedo Max */ + .id = USB_ID(0x0db0, 0xa073), + .map = msi_mpg_x570s_carbon_max_wifi_alc4080_map, + }, { /* MSI TRX40 */ .id = USB_ID(0x0db0, 0x543d), .map = trx40_mobo_map, diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c index cec6e91afea2..6d699065e81a 100644 --- a/sound/usb/pcm.c +++ b/sound/usb/pcm.c @@ -669,9 +669,9 @@ static const struct snd_pcm_hardware snd_usb_hardware = SNDRV_PCM_INFO_PAUSE, .channels_min = 1, .channels_max = 256, - .buffer_bytes_max = 1024 * 1024, + .buffer_bytes_max = INT_MAX, /* limited by BUFFER_TIME later */ .period_bytes_min = 64, - .period_bytes_max = 512 * 1024, + .period_bytes_max = INT_MAX, /* limited by PERIOD_TIME later */ .periods_min = 2, .periods_max = 1024, }; @@ -1064,6 +1064,18 @@ static int setup_hw_info(struct snd_pcm_runtime *runtime, struct snd_usb_substre return err; } + /* set max period and buffer sizes for 1 and 2 seconds, respectively */ + err = snd_pcm_hw_constraint_minmax(runtime, + SNDRV_PCM_HW_PARAM_PERIOD_TIME, + 0, 1000000); + if (err < 0) + return err; + err = snd_pcm_hw_constraint_minmax(runtime, + SNDRV_PCM_HW_PARAM_BUFFER_TIME, + 0, 2000000); + if (err < 0) + return err; + /* additional hw constraints for implicit fb */ err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_FORMAT, hw_rule_format_implicit_fb, subs, diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h index 0ea39565e623..40a5e3eb4ef2 100644 --- a/sound/usb/quirks-table.h +++ b/sound/usb/quirks-table.h @@ -3235,6 +3235,15 @@ YAMAHA_DEVICE(0x7010, "UB99"), } }, +/* Rane SL-1 */ +{ + USB_DEVICE(0x13e5, 0x0001), + .driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) { + .ifnum = QUIRK_ANY_INTERFACE, + .type = QUIRK_AUDIO_STANDARD_INTERFACE + } +}, + /* disabled due to regression for other devices; * see https://bugzilla.kernel.org/show_bug.cgi?id=199905 */ diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index ab9f3da49941..fbbe59054c3f 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1822,6 +1822,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_IGNORE_CTL_ERROR), DEVICE_FLG(0x06f8, 0xd002, /* Hercules DJ Console (Macintosh Edition) */ QUIRK_FLAG_IGNORE_CTL_ERROR), + DEVICE_FLG(0x0711, 0x5800, /* MCT Trigger 5 USB-to-HDMI */ + QUIRK_FLAG_GET_SAMPLE_RATE), DEVICE_FLG(0x074d, 0x3553, /* Outlaw RR2150 (Micronas UAC3553B) */ QUIRK_FLAG_GET_SAMPLE_RATE), DEVICE_FLG(0x08bb, 0x2702, /* LineX FM Transmitter */ diff --git a/sound/usb/usbaudio.h b/sound/usb/usbaudio.h index 167834133b9b..b8359a0aa008 100644 --- a/sound/usb/usbaudio.h +++ b/sound/usb/usbaudio.h @@ -8,7 +8,7 @@ */ /* handling of USB vendor/product ID pairs as 32-bit numbers */ -#define USB_ID(vendor, product) (((vendor) << 16) | (product)) +#define USB_ID(vendor, product) (((unsigned int)(vendor) << 16) | (product)) #define USB_ID_VENDOR(id) ((id) >> 16) #define USB_ID_PRODUCT(id) ((u16)(id)) diff --git a/sound/x86/intel_hdmi_audio.c b/sound/x86/intel_hdmi_audio.c index b00634663346..0d828e35b401 100644 --- a/sound/x86/intel_hdmi_audio.c +++ b/sound/x86/intel_hdmi_audio.c @@ -1652,7 +1652,7 @@ static void hdmi_lpe_audio_free(struct snd_card *card) * This function is called when the i915 driver creates the * hdmi-lpe-audio platform device. */ -static int hdmi_lpe_audio_probe(struct platform_device *pdev) +static int __hdmi_lpe_audio_probe(struct platform_device *pdev) { struct snd_card *card; struct snd_intelhad_card *card_ctx; @@ -1815,6 +1815,11 @@ static int hdmi_lpe_audio_probe(struct platform_device *pdev) return 0; } +static int hdmi_lpe_audio_probe(struct platform_device *pdev) +{ + return snd_card_free_on_error(&pdev->dev, __hdmi_lpe_audio_probe(pdev)); +} + static const struct dev_pm_ops hdmi_lpe_audio_pm = { SET_SYSTEM_SLEEP_PM_OPS(hdmi_lpe_audio_suspend, hdmi_lpe_audio_resume) }; diff --git a/sound/xen/xen_snd_front_evtchnl.c b/sound/xen/xen_snd_front_evtchnl.c index ecbc294fc59a..26d1b3987887 100644 --- a/sound/xen/xen_snd_front_evtchnl.c +++ b/sound/xen/xen_snd_front_evtchnl.c @@ -143,12 +143,12 @@ void xen_snd_front_evtchnl_flush(struct xen_snd_front_evtchnl *channel) static void evtchnl_free(struct xen_snd_front_info *front_info, struct xen_snd_front_evtchnl *channel) { - unsigned long page = 0; + void *page = NULL; if (channel->type == EVTCHNL_TYPE_REQ) - page = (unsigned long)channel->u.req.ring.sring; + page = channel->u.req.ring.sring; else if (channel->type == EVTCHNL_TYPE_EVT) - page = (unsigned long)channel->u.evt.page; + page = channel->u.evt.page; if (!page) return; @@ -167,10 +167,7 @@ static void evtchnl_free(struct xen_snd_front_info *front_info, xenbus_free_evtchn(front_info->xb_dev, channel->port); /* End access and free the page. */ - if (channel->gref != GRANT_INVALID_REF) - gnttab_end_foreign_access(channel->gref, page); - else - free_page(page); + xenbus_teardown_ring(&page, 1, &channel->gref); memset(channel, 0, sizeof(*channel)); } @@ -196,8 +193,7 @@ static int evtchnl_alloc(struct xen_snd_front_info *front_info, int index, enum xen_snd_front_evtchnl_type type) { struct xenbus_device *xb_dev = front_info->xb_dev; - unsigned long page; - grant_ref_t gref; + void *page; irq_handler_t handler; char *handler_name = NULL; int ret; @@ -207,12 +203,9 @@ static int evtchnl_alloc(struct xen_snd_front_info *front_info, int index, channel->index = index; channel->front_info = front_info; channel->state = EVTCHNL_STATE_DISCONNECTED; - channel->gref = GRANT_INVALID_REF; - page = get_zeroed_page(GFP_KERNEL); - if (!page) { - ret = -ENOMEM; + ret = xenbus_setup_ring(xb_dev, GFP_KERNEL, &page, 1, &channel->gref); + if (ret) goto fail; - } handler_name = kasprintf(GFP_KERNEL, "%s-%s", XENSND_DRIVER_NAME, type == EVTCHNL_TYPE_REQ ? @@ -226,33 +219,18 @@ static int evtchnl_alloc(struct xen_snd_front_info *front_info, int index, mutex_init(&channel->ring_io_lock); if (type == EVTCHNL_TYPE_REQ) { - struct xen_sndif_sring *sring = (struct xen_sndif_sring *)page; + struct xen_sndif_sring *sring = page; init_completion(&channel->u.req.completion); mutex_init(&channel->u.req.req_io_lock); - SHARED_RING_INIT(sring); - FRONT_RING_INIT(&channel->u.req.ring, sring, XEN_PAGE_SIZE); - - ret = xenbus_grant_ring(xb_dev, sring, 1, &gref); - if (ret < 0) { - channel->u.req.ring.sring = NULL; - goto fail; - } + XEN_FRONT_RING_INIT(&channel->u.req.ring, sring, XEN_PAGE_SIZE); handler = evtchnl_interrupt_req; } else { - ret = gnttab_grant_foreign_access(xb_dev->otherend_id, - virt_to_gfn((void *)page), 0); - if (ret < 0) - goto fail; - - channel->u.evt.page = (struct xensnd_event_page *)page; - gref = ret; + channel->u.evt.page = page; handler = evtchnl_interrupt_evt; } - channel->gref = gref; - ret = xenbus_alloc_evtchn(xb_dev, &channel->port); if (ret < 0) goto fail; @@ -279,8 +257,6 @@ static int evtchnl_alloc(struct xen_snd_front_info *front_info, int index, return 0; fail: - if (page) - free_page(page); kfree(handler_name); dev_err(&xb_dev->dev, "Failed to allocate ring: %d\n", ret); return ret; diff --git a/sound/xen/xen_snd_front_evtchnl.h b/sound/xen/xen_snd_front_evtchnl.h index cbe51fd1ec15..3675fba70564 100644 --- a/sound/xen/xen_snd_front_evtchnl.h +++ b/sound/xen/xen_snd_front_evtchnl.h @@ -15,15 +15,6 @@ struct xen_snd_front_info; -#ifndef GRANT_INVALID_REF -/* - * FIXME: usage of grant reference 0 as invalid grant reference: - * grant reference 0 is valid, but never exposed to a PV driver, - * because of the fact it is already in use/reserved by the PV console. - */ -#define GRANT_INVALID_REF 0 -#endif - /* Timeout in ms to wait for backend to respond. */ #define VSND_WAIT_BACK_MS 3000 diff --git a/tools/Makefile b/tools/Makefile index db2f7b8ebed5..c074e42fd92f 100644 --- a/tools/Makefile +++ b/tools/Makefile @@ -24,6 +24,7 @@ help: @echo ' intel-speed-select - Intel Speed Select tool' @echo ' kvm_stat - top-like utility for displaying kvm statistics' @echo ' leds - LEDs tools' + @echo ' nolibc - nolibc headers testing and installation' @echo ' objtool - an ELF object analysis tool' @echo ' pci - PCI tools' @echo ' perf - Linux performance measurement and analysis tool' @@ -31,6 +32,9 @@ help: @echo ' bootconfig - boot config tool' @echo ' spi - spi tools' @echo ' tmon - thermal monitoring and tuning tool' + @echo ' thermometer - temperature capture tool' + @echo ' thermal-engine - thermal monitoring tool' + @echo ' thermal - thermal library' @echo ' tracing - misc tracing tools' @echo ' turbostat - Intel CPU idle stats and freq reporting tool' @echo ' usb - USB testing tools' @@ -74,6 +78,9 @@ bpf/%: FORCE libapi: FORCE $(call descend,lib/api) +nolibc_%: FORCE + $(call descend,include/nolibc,$(patsubst nolibc_%,%,$@)) + # The perf build does not follow the descend function setup, # invoking it via it's own make rule. PERF_O = $(if $(O),$(O)/tools/perf,) @@ -85,12 +92,21 @@ perf: FORCE selftests: FORCE $(call descend,testing/$@) +thermal: FORCE + $(call descend,lib/$@) + turbostat x86_energy_perf_policy intel-speed-select: FORCE $(call descend,power/x86/$@) tmon: FORCE $(call descend,thermal/$@) +thermometer: FORCE + $(call descend,thermal/$@) + +thermal-engine: FORCE thermal + $(call descend,thermal/$@) + freefall: FORCE $(call descend,laptop/$@) @@ -101,7 +117,7 @@ all: acpi cgroup counter cpupower gpio hv firewire \ perf selftests bootconfig spi turbostat usb \ virtio vm bpf x86_energy_perf_policy \ tmon freefall iio objtool kvm_stat wmi \ - pci debugging tracing + pci debugging tracing thermal thermometer thermal-engine acpi_install: $(call descend,power/$(@:_install=),install) @@ -115,12 +131,21 @@ cgroup_install counter_install firewire_install gpio_install hv_install iio_inst selftests_install: $(call descend,testing/$(@:_install=),install) +thermal_install: + $(call descend,lib/$(@:_install=),install) + turbostat_install x86_energy_perf_policy_install intel-speed-select_install: $(call descend,power/x86/$(@:_install=),install) tmon_install: $(call descend,thermal/$(@:_install=),install) +thermometer_install: + $(call descend,thermal/$(@:_install=),install) + +thermal-engine_install: + $(call descend,thermal/$(@:_install=),install) + freefall_install: $(call descend,laptop/$(@:_install=),install) @@ -133,7 +158,7 @@ install: acpi_install cgroup_install counter_install cpupower_install gpio_insta virtio_install vm_install bpf_install x86_energy_perf_policy_install \ tmon_install freefall_install objtool_install kvm_stat_install \ wmi_install pci_install debugging_install intel-speed-select_install \ - tracing_install + tracing_install thermometer_install thermal-engine_install acpi_clean: $(call descend,power/acpi,clean) @@ -160,9 +185,18 @@ perf_clean: selftests_clean: $(call descend,testing/$(@:_clean=),clean) +thermal_clean: + $(call descend,lib/thermal,clean) + turbostat_clean x86_energy_perf_policy_clean intel-speed-select_clean: $(call descend,power/x86/$(@:_clean=),clean) +thermometer_clean: + $(call descend,thermal/thermometer,clean) + +thermal-engine_clean: + $(call descend,thermal/thermal-engine,clean) + tmon_clean: $(call descend,thermal/tmon,clean) @@ -177,6 +211,6 @@ clean: acpi_clean cgroup_clean counter_clean cpupower_clean hv_clean firewire_cl vm_clean bpf_clean iio_clean x86_energy_perf_policy_clean tmon_clean \ freefall_clean build_clean libbpf_clean libsubcmd_clean \ gpio_clean objtool_clean leds_clean wmi_clean pci_clean firmware_clean debugging_clean \ - intel-speed-select_clean tracing_clean + intel-speed-select_clean tracing_clean thermal_clean thermometer_clean thermal-engine_clean .PHONY: FORCE diff --git a/tools/arch/arm64/include/asm/cputype.h b/tools/arch/arm64/include/asm/cputype.h index 9afcc6467a09..e09d6908a21d 100644 --- a/tools/arch/arm64/include/asm/cputype.h +++ b/tools/arch/arm64/include/asm/cputype.h @@ -75,6 +75,7 @@ #define ARM_CPU_PART_CORTEX_A77 0xD0D #define ARM_CPU_PART_NEOVERSE_V1 0xD40 #define ARM_CPU_PART_CORTEX_A78 0xD41 +#define ARM_CPU_PART_CORTEX_A78AE 0xD42 #define ARM_CPU_PART_CORTEX_X1 0xD44 #define ARM_CPU_PART_CORTEX_A510 0xD46 #define ARM_CPU_PART_CORTEX_A710 0xD47 @@ -130,6 +131,7 @@ #define MIDR_CORTEX_A77 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A77) #define MIDR_NEOVERSE_V1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V1) #define MIDR_CORTEX_A78 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78) +#define MIDR_CORTEX_A78AE MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78AE) #define MIDR_CORTEX_X1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1) #define MIDR_CORTEX_A510 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A510) #define MIDR_CORTEX_A710 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A710) diff --git a/tools/arch/x86/include/asm/amd-ibs.h b/tools/arch/x86/include/asm/amd-ibs.h index 174e7d83fcbd..765e9e752d03 100644 --- a/tools/arch/x86/include/asm/amd-ibs.h +++ b/tools/arch/x86/include/asm/amd-ibs.h @@ -49,7 +49,7 @@ union ibs_op_ctl { }; }; -/* MSR 0xc0011035: IBS Op Data 2 */ +/* MSR 0xc0011035: IBS Op Data 1 */ union ibs_op_data { __u64 val; struct { diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h index 1231d63f836d..1ae0fab7d902 100644 --- a/tools/arch/x86/include/asm/disabled-features.h +++ b/tools/arch/x86/include/asm/disabled-features.h @@ -10,12 +10,6 @@ * cpu_feature_enabled(). */ -#ifdef CONFIG_X86_SMAP -# define DISABLE_SMAP 0 -#else -# define DISABLE_SMAP (1<<(X86_FEATURE_SMAP & 31)) -#endif - #ifdef CONFIG_X86_UMIP # define DISABLE_UMIP 0 #else @@ -80,7 +74,7 @@ #define DISABLED_MASK6 0 #define DISABLED_MASK7 (DISABLE_PTI) #define DISABLED_MASK8 0 -#define DISABLED_MASK9 (DISABLE_SMAP|DISABLE_SGX) +#define DISABLED_MASK9 (DISABLE_SGX) #define DISABLED_MASK10 0 #define DISABLED_MASK11 0 #define DISABLED_MASK12 0 diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index 0eb90d21049e..ee15311b6be1 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -128,9 +128,9 @@ #define TSX_CTRL_RTM_DISABLE BIT(0) /* Disable RTM feature */ #define TSX_CTRL_CPUID_CLEAR BIT(1) /* Disable TSX enumeration */ -/* SRBDS support */ #define MSR_IA32_MCU_OPT_CTRL 0x00000123 -#define RNGDS_MITG_DIS BIT(0) +#define RNGDS_MITG_DIS BIT(0) /* SRBDS support */ +#define RTM_ALLOW BIT(1) /* TSX development mode */ #define MSR_IA32_SYSENTER_CS 0x00000174 #define MSR_IA32_SYSENTER_ESP 0x00000175 diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c index 91af2850b505..7678af364793 100644 --- a/tools/bpf/bpftool/gen.c +++ b/tools/bpf/bpftool/gen.c @@ -828,8 +828,10 @@ codegen_maps_skeleton(struct bpf_object *obj, size_t map_cnt, bool mmaped) s->map_cnt = %zu; \n\ s->map_skel_sz = sizeof(*s->maps); \n\ s->maps = (struct bpf_map_skeleton *)calloc(s->map_cnt, s->map_skel_sz);\n\ - if (!s->maps) \n\ + if (!s->maps) { \n\ + err = -ENOMEM; \n\ goto err; \n\ + } \n\ ", map_cnt ); @@ -870,8 +872,10 @@ codegen_progs_skeleton(struct bpf_object *obj, size_t prog_cnt, bool populate_li s->prog_cnt = %zu; \n\ s->prog_skel_sz = sizeof(*s->progs); \n\ s->progs = (struct bpf_prog_skeleton *)calloc(s->prog_cnt, s->prog_skel_sz);\n\ - if (!s->progs) \n\ + if (!s->progs) { \n\ + err = -ENOMEM; \n\ goto err; \n\ + } \n\ ", prog_cnt ); @@ -1182,10 +1186,13 @@ static int do_skeleton(int argc, char **argv) %1$s__create_skeleton(struct %1$s *obj) \n\ { \n\ struct bpf_object_skeleton *s; \n\ + int err; \n\ \n\ s = (struct bpf_object_skeleton *)calloc(1, sizeof(*s));\n\ - if (!s) \n\ + if (!s) { \n\ + err = -ENOMEM; \n\ goto err; \n\ + } \n\ \n\ s->sz = sizeof(*s); \n\ s->name = \"%1$s\"; \n\ @@ -1206,7 +1213,7 @@ static int do_skeleton(int argc, char **argv) return 0; \n\ err: \n\ bpf_object__destroy_skeleton(s); \n\ - return -ENOMEM; \n\ + return err; \n\ } \n\ \n\ static inline const void *%2$s__elf_bytes(size_t *sz) \n\ @@ -1466,12 +1473,12 @@ static int do_subskeleton(int argc, char **argv) \n\ obj = (struct %1$s *)calloc(1, sizeof(*obj)); \n\ if (!obj) { \n\ - errno = ENOMEM; \n\ + err = -ENOMEM; \n\ goto err; \n\ } \n\ s = (struct bpf_object_subskeleton *)calloc(1, sizeof(*s));\n\ if (!s) { \n\ - errno = ENOMEM; \n\ + err = -ENOMEM; \n\ goto err; \n\ } \n\ s->sz = sizeof(*s); \n\ @@ -1483,7 +1490,7 @@ static int do_subskeleton(int argc, char **argv) s->var_cnt = %2$d; \n\ s->vars = (struct bpf_var_skeleton *)calloc(%2$d, sizeof(*s->vars));\n\ if (!s->vars) { \n\ - errno = ENOMEM; \n\ + err = -ENOMEM; \n\ goto err; \n\ } \n\ ", @@ -1538,6 +1545,7 @@ static int do_subskeleton(int argc, char **argv) return obj; \n\ err: \n\ %1$s__destroy(obj); \n\ + errno = -err; \n\ return NULL; \n\ } \n\ \n\ diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature index ae61f464043a..c6a48d0ef9ff 100644 --- a/tools/build/Makefile.feature +++ b/tools/build/Makefile.feature @@ -98,6 +98,7 @@ FEATURE_TESTS_EXTRA := \ llvm-version \ clang \ libbpf \ + libbpf-btf__load_from_kernel_by_id \ libpfm4 \ libdebuginfod \ clang-bpf-co-re diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile index 1480910c792e..cb4a2a4fa2e4 100644 --- a/tools/build/feature/Makefile +++ b/tools/build/feature/Makefile @@ -57,6 +57,7 @@ FILES= \ test-lzma.bin \ test-bpf.bin \ test-libbpf.bin \ + test-libbpf-btf__load_from_kernel_by_id.bin \ test-get_cpuid.bin \ test-sdt.bin \ test-cxx.bin \ @@ -217,9 +218,16 @@ strip-libs = $(filter-out -l%,$(1)) PERL_EMBED_LDOPTS = $(shell perl -MExtUtils::Embed -e ldopts 2>/dev/null) PERL_EMBED_LDFLAGS = $(call strip-libs,$(PERL_EMBED_LDOPTS)) PERL_EMBED_LIBADD = $(call grep-libs,$(PERL_EMBED_LDOPTS)) -PERL_EMBED_CCOPTS = `perl -MExtUtils::Embed -e ccopts 2>/dev/null` +PERL_EMBED_CCOPTS = $(shell perl -MExtUtils::Embed -e ccopts 2>/dev/null) FLAGS_PERL_EMBED=$(PERL_EMBED_CCOPTS) $(PERL_EMBED_LDOPTS) +ifeq ($(CC_NO_CLANG), 0) + PERL_EMBED_LDOPTS := $(filter-out -specs=%,$(PERL_EMBED_LDOPTS)) + PERL_EMBED_CCOPTS := $(filter-out -flto=auto -ffat-lto-objects, $(PERL_EMBED_CCOPTS)) + PERL_EMBED_CCOPTS := $(filter-out -specs=%,$(PERL_EMBED_CCOPTS)) + FLAGS_PERL_EMBED += -Wno-compound-token-split-by-macro +endif + $(OUTPUT)test-libperl.bin: $(BUILD) $(FLAGS_PERL_EMBED) @@ -280,6 +288,9 @@ $(OUTPUT)test-bpf.bin: $(OUTPUT)test-libbpf.bin: $(BUILD) -lbpf +$(OUTPUT)test-libbpf-btf__load_from_kernel_by_id.bin: + $(BUILD) -lbpf + $(OUTPUT)test-sdt.bin: $(BUILD) diff --git a/tools/build/feature/test-libbpf-btf__load_from_kernel_by_id.c b/tools/build/feature/test-libbpf-btf__load_from_kernel_by_id.c new file mode 100644 index 000000000000..f7c084428735 --- /dev/null +++ b/tools/build/feature/test-libbpf-btf__load_from_kernel_by_id.c @@ -0,0 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <bpf/libbpf.h> + +int main(void) +{ + return btf__load_from_kernel_by_id(20151128, NULL); +} diff --git a/tools/certs/print-cert-tbs-hash.sh b/tools/certs/print-cert-tbs-hash.sh new file mode 100755 index 000000000000..c93df5387ec9 --- /dev/null +++ b/tools/certs/print-cert-tbs-hash.sh @@ -0,0 +1,91 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Copyright © 2020, Microsoft Corporation. All rights reserved. +# +# Author: Mickaël Salaün <mic@linux.microsoft.com> +# +# Compute and print the To Be Signed (TBS) hash of a certificate. This is used +# as description of keys in the blacklist keyring to identify certificates. +# This output should be redirected, without newline, in a file (hash0.txt) and +# signed to create a PKCS#7 file (hash0.p7s). Both of these files can then be +# loaded in the kernel with. +# +# Exemple on a workstation: +# ./print-cert-tbs-hash.sh certificate-to-invalidate.pem > hash0.txt +# openssl smime -sign -in hash0.txt -inkey builtin-private-key.pem \ +# -signer builtin-certificate.pem -certfile certificate-chain.pem \ +# -noattr -binary -outform DER -out hash0.p7s +# +# Exemple on a managed system: +# keyctl padd blacklist "$(< hash0.txt)" %:.blacklist < hash0.p7s + +set -u -e -o pipefail + +CERT="${1:-}" +BASENAME="$(basename -- "${BASH_SOURCE[0]}")" + +if [ $# -ne 1 ] || [ ! -f "${CERT}" ]; then + echo "usage: ${BASENAME} <certificate>" >&2 + exit 1 +fi + +# Checks that it is indeed a certificate (PEM or DER encoded) and exclude the +# optional PEM text header. +if ! PEM="$(openssl x509 -inform DER -in "${CERT}" 2>/dev/null || openssl x509 -in "${CERT}")"; then + echo "ERROR: Failed to parse certificate" >&2 + exit 1 +fi + +# TBSCertificate starts at the second entry. +# Cf. https://tools.ietf.org/html/rfc3280#section-4.1 +# +# Exemple of first lines printed by openssl asn1parse: +# 0:d=0 hl=4 l= 763 cons: SEQUENCE +# 4:d=1 hl=4 l= 483 cons: SEQUENCE +# 8:d=2 hl=2 l= 3 cons: cont [ 0 ] +# 10:d=3 hl=2 l= 1 prim: INTEGER :02 +# 13:d=2 hl=2 l= 20 prim: INTEGER :3CEB2CB8818D968AC00EEFE195F0DF9665328B7B +# 35:d=2 hl=2 l= 13 cons: SEQUENCE +# 37:d=3 hl=2 l= 9 prim: OBJECT :sha256WithRSAEncryption +RANGE_AND_DIGEST_RE=' +2s/^\s*\([0-9]\+\):d=\s*[0-9]\+\s\+hl=\s*[0-9]\+\s\+l=\s*\([0-9]\+\)\s\+cons:\s*SEQUENCE\s*$/\1 \2/p; +7s/^\s*[0-9]\+:d=\s*[0-9]\+\s\+hl=\s*[0-9]\+\s\+l=\s*[0-9]\+\s\+prim:\s*OBJECT\s*:\(.*\)$/\1/p; +' + +RANGE_AND_DIGEST=($(echo "${PEM}" | \ + openssl asn1parse -in - | \ + sed -n -e "${RANGE_AND_DIGEST_RE}")) + +if [ "${#RANGE_AND_DIGEST[@]}" != 3 ]; then + echo "ERROR: Failed to parse TBSCertificate." >&2 + exit 1 +fi + +OFFSET="${RANGE_AND_DIGEST[0]}" +END="$(( OFFSET + RANGE_AND_DIGEST[1] ))" +DIGEST="${RANGE_AND_DIGEST[2]}" + +# The signature hash algorithm is used by Linux to blacklist certificates. +# Cf. crypto/asymmetric_keys/x509_cert_parser.c:x509_note_pkey_algo() +DIGEST_MATCH="" +while read -r DIGEST_ITEM; do + if [ -z "${DIGEST_ITEM}" ]; then + break + fi + if echo "${DIGEST}" | grep -qiF "${DIGEST_ITEM}"; then + DIGEST_MATCH="${DIGEST_ITEM}" + break + fi +done < <(openssl list -digest-commands | tr ' ' '\n' | sort -ur) + +if [ -z "${DIGEST_MATCH}" ]; then + echo "ERROR: Unknown digest algorithm: ${DIGEST}" >&2 + exit 1 +fi + +echo "${PEM}" | \ + openssl x509 -in - -outform DER | \ + dd "bs=1" "skip=${OFFSET}" "count=${END}" "status=none" | \ + openssl dgst "-${DIGEST_MATCH}" - | \ + awk '{printf "tbs:" $2}' diff --git a/tools/include/linux/objtool.h b/tools/include/linux/objtool.h index 586d35720f13..6491fa8fba6d 100644 --- a/tools/include/linux/objtool.h +++ b/tools/include/linux/objtool.h @@ -38,7 +38,9 @@ struct unwind_hint { #define UNWIND_HINT_TYPE_REGS_PARTIAL 2 #define UNWIND_HINT_TYPE_FUNC 3 -#ifdef CONFIG_STACK_VALIDATION +#ifdef CONFIG_OBJTOOL + +#include <asm/asm.h> #ifndef __ASSEMBLY__ @@ -137,7 +139,7 @@ struct unwind_hint { .macro STACK_FRAME_NON_STANDARD func:req .pushsection .discard.func_stack_frame_non_standard, "aw" - .long \func - . + _ASM_PTR \func .popsection .endm @@ -157,7 +159,7 @@ struct unwind_hint { #endif /* __ASSEMBLY__ */ -#else /* !CONFIG_STACK_VALIDATION */ +#else /* !CONFIG_OBJTOOL */ #ifndef __ASSEMBLY__ @@ -179,6 +181,6 @@ struct unwind_hint { .endm #endif -#endif /* CONFIG_STACK_VALIDATION */ +#endif /* CONFIG_OBJTOOL */ #endif /* _LINUX_OBJTOOL_H */ diff --git a/tools/include/linux/slab.h b/tools/include/linux/slab.h index f41d8a0eb1a4..0616409513eb 100644 --- a/tools/include/linux/slab.h +++ b/tools/include/linux/slab.h @@ -28,7 +28,13 @@ static inline void *kzalloc(size_t size, gfp_t gfp) return kmalloc(size, gfp | __GFP_ZERO); } -void *kmem_cache_alloc(struct kmem_cache *cachep, int flags); +struct list_lru; + +void *kmem_cache_alloc_lru(struct kmem_cache *cachep, struct list_lru *, int flags); +static inline void *kmem_cache_alloc(struct kmem_cache *cachep, int flags) +{ + return kmem_cache_alloc_lru(cachep, NULL, flags); +} void kmem_cache_free(struct kmem_cache *cachep, void *objp); struct kmem_cache *kmem_cache_create(const char *name, unsigned int size, diff --git a/tools/include/nolibc/Makefile b/tools/include/nolibc/Makefile new file mode 100644 index 000000000000..7a16d917c185 --- /dev/null +++ b/tools/include/nolibc/Makefile @@ -0,0 +1,42 @@ +# SPDX-License-Identifier: GPL-2.0 +# Makefile for nolibc installation and tests +include ../../scripts/Makefile.include + +# we're in ".../tools/include/nolibc" +ifeq ($(srctree),) +srctree := $(patsubst %/tools/include/,%,$(dir $(CURDIR))) +endif + +nolibc_arch := $(patsubst arm64,aarch64,$(ARCH)) +arch_file := arch-$(nolibc_arch).h +all_files := ctype.h errno.h nolibc.h signal.h std.h stdio.h stdlib.h string.h \ + sys.h time.h types.h unistd.h + +# install all headers needed to support a bare-metal compiler +all: + +# Note: when ARCH is "x86" we concatenate both x86_64 and i386 +headers: + $(Q)mkdir -p $(OUTPUT)sysroot + $(Q)mkdir -p $(OUTPUT)sysroot/include + $(Q)cp $(all_files) $(OUTPUT)sysroot/include/ + $(Q)if [ "$(ARCH)" = "x86" ]; then \ + sed -e \ + 's,^#ifndef _NOLIBC_ARCH_X86_64_H,#if !defined(_NOLIBC_ARCH_X86_64_H) \&\& defined(__x86_64__),' \ + arch-x86_64.h; \ + sed -e \ + 's,^#ifndef _NOLIBC_ARCH_I386_H,#if !defined(_NOLIBC_ARCH_I386_H) \&\& !defined(__x86_64__),' \ + arch-i386.h; \ + elif [ -e "$(arch_file)" ]; then \ + cat $(arch_file); \ + else \ + echo "Fatal: architecture $(ARCH) not yet supported by nolibc." >&2; \ + exit 1; \ + fi > $(OUTPUT)sysroot/include/arch.h + +headers_standalone: headers + $(Q)$(MAKE) -C $(srctree) headers + $(Q)$(MAKE) -C $(srctree) headers_install INSTALL_HDR_PATH=$(OUTPUT)/sysroot + +clean: + $(call QUIET_CLEAN, nolibc) rm -rf "$(OUTPUT)sysroot" diff --git a/tools/include/nolibc/arch-aarch64.h b/tools/include/nolibc/arch-aarch64.h new file mode 100644 index 000000000000..f68baf8f395f --- /dev/null +++ b/tools/include/nolibc/arch-aarch64.h @@ -0,0 +1,199 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* + * AARCH64 specific definitions for NOLIBC + * Copyright (C) 2017-2022 Willy Tarreau <w@1wt.eu> + */ + +#ifndef _NOLIBC_ARCH_AARCH64_H +#define _NOLIBC_ARCH_AARCH64_H + +/* O_* macros for fcntl/open are architecture-specific */ +#define O_RDONLY 0 +#define O_WRONLY 1 +#define O_RDWR 2 +#define O_CREAT 0x40 +#define O_EXCL 0x80 +#define O_NOCTTY 0x100 +#define O_TRUNC 0x200 +#define O_APPEND 0x400 +#define O_NONBLOCK 0x800 +#define O_DIRECTORY 0x4000 + +/* The struct returned by the newfstatat() syscall. Differs slightly from the + * x86_64's stat one by field ordering, so be careful. + */ +struct sys_stat_struct { + unsigned long st_dev; + unsigned long st_ino; + unsigned int st_mode; + unsigned int st_nlink; + unsigned int st_uid; + unsigned int st_gid; + + unsigned long st_rdev; + unsigned long __pad1; + long st_size; + int st_blksize; + int __pad2; + + long st_blocks; + long st_atime; + unsigned long st_atime_nsec; + long st_mtime; + + unsigned long st_mtime_nsec; + long st_ctime; + unsigned long st_ctime_nsec; + unsigned int __unused[2]; +}; + +/* Syscalls for AARCH64 : + * - registers are 64-bit + * - stack is 16-byte aligned + * - syscall number is passed in x8 + * - arguments are in x0, x1, x2, x3, x4, x5 + * - the system call is performed by calling svc 0 + * - syscall return comes in x0. + * - the arguments are cast to long and assigned into the target registers + * which are then simply passed as registers to the asm code, so that we + * don't have to experience issues with register constraints. + * + * On aarch64, select() is not implemented so we have to use pselect6(). + */ +#define __ARCH_WANT_SYS_PSELECT6 + +#define my_syscall0(num) \ +({ \ + register long _num __asm__ ("x8") = (num); \ + register long _arg1 __asm__ ("x0"); \ + \ + __asm__ volatile ( \ + "svc #0\n" \ + : "=r"(_arg1) \ + : "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#define my_syscall1(num, arg1) \ +({ \ + register long _num __asm__ ("x8") = (num); \ + register long _arg1 __asm__ ("x0") = (long)(arg1); \ + \ + __asm__ volatile ( \ + "svc #0\n" \ + : "=r"(_arg1) \ + : "r"(_arg1), \ + "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#define my_syscall2(num, arg1, arg2) \ +({ \ + register long _num __asm__ ("x8") = (num); \ + register long _arg1 __asm__ ("x0") = (long)(arg1); \ + register long _arg2 __asm__ ("x1") = (long)(arg2); \ + \ + __asm__ volatile ( \ + "svc #0\n" \ + : "=r"(_arg1) \ + : "r"(_arg1), "r"(_arg2), \ + "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#define my_syscall3(num, arg1, arg2, arg3) \ +({ \ + register long _num __asm__ ("x8") = (num); \ + register long _arg1 __asm__ ("x0") = (long)(arg1); \ + register long _arg2 __asm__ ("x1") = (long)(arg2); \ + register long _arg3 __asm__ ("x2") = (long)(arg3); \ + \ + __asm__ volatile ( \ + "svc #0\n" \ + : "=r"(_arg1) \ + : "r"(_arg1), "r"(_arg2), "r"(_arg3), \ + "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#define my_syscall4(num, arg1, arg2, arg3, arg4) \ +({ \ + register long _num __asm__ ("x8") = (num); \ + register long _arg1 __asm__ ("x0") = (long)(arg1); \ + register long _arg2 __asm__ ("x1") = (long)(arg2); \ + register long _arg3 __asm__ ("x2") = (long)(arg3); \ + register long _arg4 __asm__ ("x3") = (long)(arg4); \ + \ + __asm__ volatile ( \ + "svc #0\n" \ + : "=r"(_arg1) \ + : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), \ + "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \ +({ \ + register long _num __asm__ ("x8") = (num); \ + register long _arg1 __asm__ ("x0") = (long)(arg1); \ + register long _arg2 __asm__ ("x1") = (long)(arg2); \ + register long _arg3 __asm__ ("x2") = (long)(arg3); \ + register long _arg4 __asm__ ("x3") = (long)(arg4); \ + register long _arg5 __asm__ ("x4") = (long)(arg5); \ + \ + __asm__ volatile ( \ + "svc #0\n" \ + : "=r" (_arg1) \ + : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \ + "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#define my_syscall6(num, arg1, arg2, arg3, arg4, arg5, arg6) \ +({ \ + register long _num __asm__ ("x8") = (num); \ + register long _arg1 __asm__ ("x0") = (long)(arg1); \ + register long _arg2 __asm__ ("x1") = (long)(arg2); \ + register long _arg3 __asm__ ("x2") = (long)(arg3); \ + register long _arg4 __asm__ ("x3") = (long)(arg4); \ + register long _arg5 __asm__ ("x4") = (long)(arg5); \ + register long _arg6 __asm__ ("x5") = (long)(arg6); \ + \ + __asm__ volatile ( \ + "svc #0\n" \ + : "=r" (_arg1) \ + : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \ + "r"(_arg6), "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +/* startup code */ +__asm__ (".section .text\n" + ".weak _start\n" + "_start:\n" + "ldr x0, [sp]\n" // argc (x0) was in the stack + "add x1, sp, 8\n" // argv (x1) = sp + "lsl x2, x0, 3\n" // envp (x2) = 8*argc ... + "add x2, x2, 8\n" // + 8 (skip null) + "add x2, x2, x1\n" // + argv + "and sp, x1, -16\n" // sp must be 16-byte aligned in the callee + "bl main\n" // main() returns the status code, we'll exit with it. + "mov x8, 93\n" // NR_exit == 93 + "svc #0\n" + ""); + +#endif // _NOLIBC_ARCH_AARCH64_H diff --git a/tools/include/nolibc/arch-arm.h b/tools/include/nolibc/arch-arm.h new file mode 100644 index 000000000000..f31be8e967d6 --- /dev/null +++ b/tools/include/nolibc/arch-arm.h @@ -0,0 +1,204 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* + * ARM specific definitions for NOLIBC + * Copyright (C) 2017-2022 Willy Tarreau <w@1wt.eu> + */ + +#ifndef _NOLIBC_ARCH_ARM_H +#define _NOLIBC_ARCH_ARM_H + +/* O_* macros for fcntl/open are architecture-specific */ +#define O_RDONLY 0 +#define O_WRONLY 1 +#define O_RDWR 2 +#define O_CREAT 0x40 +#define O_EXCL 0x80 +#define O_NOCTTY 0x100 +#define O_TRUNC 0x200 +#define O_APPEND 0x400 +#define O_NONBLOCK 0x800 +#define O_DIRECTORY 0x4000 + +/* The struct returned by the stat() syscall, 32-bit only, the syscall returns + * exactly 56 bytes (stops before the unused array). In big endian, the format + * differs as devices are returned as short only. + */ +struct sys_stat_struct { +#if defined(__ARMEB__) + unsigned short st_dev; + unsigned short __pad1; +#else + unsigned long st_dev; +#endif + unsigned long st_ino; + unsigned short st_mode; + unsigned short st_nlink; + unsigned short st_uid; + unsigned short st_gid; + +#if defined(__ARMEB__) + unsigned short st_rdev; + unsigned short __pad2; +#else + unsigned long st_rdev; +#endif + unsigned long st_size; + unsigned long st_blksize; + unsigned long st_blocks; + + unsigned long st_atime; + unsigned long st_atime_nsec; + unsigned long st_mtime; + unsigned long st_mtime_nsec; + + unsigned long st_ctime; + unsigned long st_ctime_nsec; + unsigned long __unused[2]; +}; + +/* Syscalls for ARM in ARM or Thumb modes : + * - registers are 32-bit + * - stack is 8-byte aligned + * ( http://infocenter.arm.com/help/index.jsp?topic=/com.arm.doc.faqs/ka4127.html) + * - syscall number is passed in r7 + * - arguments are in r0, r1, r2, r3, r4, r5 + * - the system call is performed by calling svc #0 + * - syscall return comes in r0. + * - only lr is clobbered. + * - the arguments are cast to long and assigned into the target registers + * which are then simply passed as registers to the asm code, so that we + * don't have to experience issues with register constraints. + * - the syscall number is always specified last in order to allow to force + * some registers before (gcc refuses a %-register at the last position). + * + * Also, ARM supports the old_select syscall if newselect is not available + */ +#define __ARCH_WANT_SYS_OLD_SELECT + +#define my_syscall0(num) \ +({ \ + register long _num __asm__ ("r7") = (num); \ + register long _arg1 __asm__ ("r0"); \ + \ + __asm__ volatile ( \ + "svc #0\n" \ + : "=r"(_arg1) \ + : "r"(_num) \ + : "memory", "cc", "lr" \ + ); \ + _arg1; \ +}) + +#define my_syscall1(num, arg1) \ +({ \ + register long _num __asm__ ("r7") = (num); \ + register long _arg1 __asm__ ("r0") = (long)(arg1); \ + \ + __asm__ volatile ( \ + "svc #0\n" \ + : "=r"(_arg1) \ + : "r"(_arg1), \ + "r"(_num) \ + : "memory", "cc", "lr" \ + ); \ + _arg1; \ +}) + +#define my_syscall2(num, arg1, arg2) \ +({ \ + register long _num __asm__ ("r7") = (num); \ + register long _arg1 __asm__ ("r0") = (long)(arg1); \ + register long _arg2 __asm__ ("r1") = (long)(arg2); \ + \ + __asm__ volatile ( \ + "svc #0\n" \ + : "=r"(_arg1) \ + : "r"(_arg1), "r"(_arg2), \ + "r"(_num) \ + : "memory", "cc", "lr" \ + ); \ + _arg1; \ +}) + +#define my_syscall3(num, arg1, arg2, arg3) \ +({ \ + register long _num __asm__ ("r7") = (num); \ + register long _arg1 __asm__ ("r0") = (long)(arg1); \ + register long _arg2 __asm__ ("r1") = (long)(arg2); \ + register long _arg3 __asm__ ("r2") = (long)(arg3); \ + \ + __asm__ volatile ( \ + "svc #0\n" \ + : "=r"(_arg1) \ + : "r"(_arg1), "r"(_arg2), "r"(_arg3), \ + "r"(_num) \ + : "memory", "cc", "lr" \ + ); \ + _arg1; \ +}) + +#define my_syscall4(num, arg1, arg2, arg3, arg4) \ +({ \ + register long _num __asm__ ("r7") = (num); \ + register long _arg1 __asm__ ("r0") = (long)(arg1); \ + register long _arg2 __asm__ ("r1") = (long)(arg2); \ + register long _arg3 __asm__ ("r2") = (long)(arg3); \ + register long _arg4 __asm__ ("r3") = (long)(arg4); \ + \ + __asm__ volatile ( \ + "svc #0\n" \ + : "=r"(_arg1) \ + : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), \ + "r"(_num) \ + : "memory", "cc", "lr" \ + ); \ + _arg1; \ +}) + +#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \ +({ \ + register long _num __asm__ ("r7") = (num); \ + register long _arg1 __asm__ ("r0") = (long)(arg1); \ + register long _arg2 __asm__ ("r1") = (long)(arg2); \ + register long _arg3 __asm__ ("r2") = (long)(arg3); \ + register long _arg4 __asm__ ("r3") = (long)(arg4); \ + register long _arg5 __asm__ ("r4") = (long)(arg5); \ + \ + __asm__ volatile ( \ + "svc #0\n" \ + : "=r" (_arg1) \ + : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \ + "r"(_num) \ + : "memory", "cc", "lr" \ + ); \ + _arg1; \ +}) + +/* startup code */ +__asm__ (".section .text\n" + ".weak _start\n" + "_start:\n" +#if defined(__THUMBEB__) || defined(__THUMBEL__) + /* We enter here in 32-bit mode but if some previous functions were in + * 16-bit mode, the assembler cannot know, so we need to tell it we're in + * 32-bit now, then switch to 16-bit (is there a better way to do it than + * adding 1 by hand ?) and tell the asm we're now in 16-bit mode so that + * it generates correct instructions. Note that we do not support thumb1. + */ + ".code 32\n" + "add r0, pc, #1\n" + "bx r0\n" + ".code 16\n" +#endif + "pop {%r0}\n" // argc was in the stack + "mov %r1, %sp\n" // argv = sp + "add %r2, %r1, %r0, lsl #2\n" // envp = argv + 4*argc ... + "add %r2, %r2, $4\n" // ... + 4 + "and %r3, %r1, $-8\n" // AAPCS : sp must be 8-byte aligned in the + "mov %sp, %r3\n" // callee, an bl doesn't push (lr=pc) + "bl main\n" // main() returns the status code, we'll exit with it. + "movs r7, $1\n" // NR_exit == 1 + "svc $0x00\n" + ""); + +#endif // _NOLIBC_ARCH_ARM_H diff --git a/tools/include/nolibc/arch-i386.h b/tools/include/nolibc/arch-i386.h new file mode 100644 index 000000000000..d7e7212346e2 --- /dev/null +++ b/tools/include/nolibc/arch-i386.h @@ -0,0 +1,219 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* + * i386 specific definitions for NOLIBC + * Copyright (C) 2017-2022 Willy Tarreau <w@1wt.eu> + */ + +#ifndef _NOLIBC_ARCH_I386_H +#define _NOLIBC_ARCH_I386_H + +/* O_* macros for fcntl/open are architecture-specific */ +#define O_RDONLY 0 +#define O_WRONLY 1 +#define O_RDWR 2 +#define O_CREAT 0x40 +#define O_EXCL 0x80 +#define O_NOCTTY 0x100 +#define O_TRUNC 0x200 +#define O_APPEND 0x400 +#define O_NONBLOCK 0x800 +#define O_DIRECTORY 0x10000 + +/* The struct returned by the stat() syscall, 32-bit only, the syscall returns + * exactly 56 bytes (stops before the unused array). + */ +struct sys_stat_struct { + unsigned long st_dev; + unsigned long st_ino; + unsigned short st_mode; + unsigned short st_nlink; + unsigned short st_uid; + unsigned short st_gid; + + unsigned long st_rdev; + unsigned long st_size; + unsigned long st_blksize; + unsigned long st_blocks; + + unsigned long st_atime; + unsigned long st_atime_nsec; + unsigned long st_mtime; + unsigned long st_mtime_nsec; + + unsigned long st_ctime; + unsigned long st_ctime_nsec; + unsigned long __unused[2]; +}; + +/* Syscalls for i386 : + * - mostly similar to x86_64 + * - registers are 32-bit + * - syscall number is passed in eax + * - arguments are in ebx, ecx, edx, esi, edi, ebp respectively + * - all registers are preserved (except eax of course) + * - the system call is performed by calling int $0x80 + * - syscall return comes in eax + * - the arguments are cast to long and assigned into the target registers + * which are then simply passed as registers to the asm code, so that we + * don't have to experience issues with register constraints. + * - the syscall number is always specified last in order to allow to force + * some registers before (gcc refuses a %-register at the last position). + * + * Also, i386 supports the old_select syscall if newselect is not available + */ +#define __ARCH_WANT_SYS_OLD_SELECT + +#define my_syscall0(num) \ +({ \ + long _ret; \ + register long _num __asm__ ("eax") = (num); \ + \ + __asm__ volatile ( \ + "int $0x80\n" \ + : "=a" (_ret) \ + : "0"(_num) \ + : "memory", "cc" \ + ); \ + _ret; \ +}) + +#define my_syscall1(num, arg1) \ +({ \ + long _ret; \ + register long _num __asm__ ("eax") = (num); \ + register long _arg1 __asm__ ("ebx") = (long)(arg1); \ + \ + __asm__ volatile ( \ + "int $0x80\n" \ + : "=a" (_ret) \ + : "r"(_arg1), \ + "0"(_num) \ + : "memory", "cc" \ + ); \ + _ret; \ +}) + +#define my_syscall2(num, arg1, arg2) \ +({ \ + long _ret; \ + register long _num __asm__ ("eax") = (num); \ + register long _arg1 __asm__ ("ebx") = (long)(arg1); \ + register long _arg2 __asm__ ("ecx") = (long)(arg2); \ + \ + __asm__ volatile ( \ + "int $0x80\n" \ + : "=a" (_ret) \ + : "r"(_arg1), "r"(_arg2), \ + "0"(_num) \ + : "memory", "cc" \ + ); \ + _ret; \ +}) + +#define my_syscall3(num, arg1, arg2, arg3) \ +({ \ + long _ret; \ + register long _num __asm__ ("eax") = (num); \ + register long _arg1 __asm__ ("ebx") = (long)(arg1); \ + register long _arg2 __asm__ ("ecx") = (long)(arg2); \ + register long _arg3 __asm__ ("edx") = (long)(arg3); \ + \ + __asm__ volatile ( \ + "int $0x80\n" \ + : "=a" (_ret) \ + : "r"(_arg1), "r"(_arg2), "r"(_arg3), \ + "0"(_num) \ + : "memory", "cc" \ + ); \ + _ret; \ +}) + +#define my_syscall4(num, arg1, arg2, arg3, arg4) \ +({ \ + long _ret; \ + register long _num __asm__ ("eax") = (num); \ + register long _arg1 __asm__ ("ebx") = (long)(arg1); \ + register long _arg2 __asm__ ("ecx") = (long)(arg2); \ + register long _arg3 __asm__ ("edx") = (long)(arg3); \ + register long _arg4 __asm__ ("esi") = (long)(arg4); \ + \ + __asm__ volatile ( \ + "int $0x80\n" \ + : "=a" (_ret) \ + : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), \ + "0"(_num) \ + : "memory", "cc" \ + ); \ + _ret; \ +}) + +#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \ +({ \ + long _ret; \ + register long _num __asm__ ("eax") = (num); \ + register long _arg1 __asm__ ("ebx") = (long)(arg1); \ + register long _arg2 __asm__ ("ecx") = (long)(arg2); \ + register long _arg3 __asm__ ("edx") = (long)(arg3); \ + register long _arg4 __asm__ ("esi") = (long)(arg4); \ + register long _arg5 __asm__ ("edi") = (long)(arg5); \ + \ + __asm__ volatile ( \ + "int $0x80\n" \ + : "=a" (_ret) \ + : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \ + "0"(_num) \ + : "memory", "cc" \ + ); \ + _ret; \ +}) + +#define my_syscall6(num, arg1, arg2, arg3, arg4, arg5, arg6) \ +({ \ + long _eax = (long)(num); \ + long _arg6 = (long)(arg6); /* Always in memory */ \ + __asm__ volatile ( \ + "pushl %[_arg6]\n\t" \ + "pushl %%ebp\n\t" \ + "movl 4(%%esp),%%ebp\n\t" \ + "int $0x80\n\t" \ + "popl %%ebp\n\t" \ + "addl $4,%%esp\n\t" \ + : "+a"(_eax) /* %eax */ \ + : "b"(arg1), /* %ebx */ \ + "c"(arg2), /* %ecx */ \ + "d"(arg3), /* %edx */ \ + "S"(arg4), /* %esi */ \ + "D"(arg5), /* %edi */ \ + [_arg6]"m"(_arg6) /* memory */ \ + : "memory", "cc" \ + ); \ + _eax; \ +}) + +/* startup code */ +/* + * i386 System V ABI mandates: + * 1) last pushed argument must be 16-byte aligned. + * 2) The deepest stack frame should be set to zero + * + */ +__asm__ (".section .text\n" + ".weak _start\n" + "_start:\n" + "pop %eax\n" // argc (first arg, %eax) + "mov %esp, %ebx\n" // argv[] (second arg, %ebx) + "lea 4(%ebx,%eax,4),%ecx\n" // then a NULL then envp (third arg, %ecx) + "xor %ebp, %ebp\n" // zero the stack frame + "and $-16, %esp\n" // x86 ABI : esp must be 16-byte aligned before + "sub $4, %esp\n" // the call instruction (args are aligned) + "push %ecx\n" // push all registers on the stack so that we + "push %ebx\n" // support both regparm and plain stack modes + "push %eax\n" + "call main\n" // main() returns the status code in %eax + "mov %eax, %ebx\n" // retrieve exit code (32-bit int) + "movl $1, %eax\n" // NR_exit == 1 + "int $0x80\n" // exit now + "hlt\n" // ensure it does not + ""); + +#endif // _NOLIBC_ARCH_I386_H diff --git a/tools/include/nolibc/arch-mips.h b/tools/include/nolibc/arch-mips.h new file mode 100644 index 000000000000..5fc5b8029bff --- /dev/null +++ b/tools/include/nolibc/arch-mips.h @@ -0,0 +1,215 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* + * MIPS specific definitions for NOLIBC + * Copyright (C) 2017-2022 Willy Tarreau <w@1wt.eu> + */ + +#ifndef _NOLIBC_ARCH_MIPS_H +#define _NOLIBC_ARCH_MIPS_H + +/* O_* macros for fcntl/open are architecture-specific */ +#define O_RDONLY 0 +#define O_WRONLY 1 +#define O_RDWR 2 +#define O_APPEND 0x0008 +#define O_NONBLOCK 0x0080 +#define O_CREAT 0x0100 +#define O_TRUNC 0x0200 +#define O_EXCL 0x0400 +#define O_NOCTTY 0x0800 +#define O_DIRECTORY 0x10000 + +/* The struct returned by the stat() syscall. 88 bytes are returned by the + * syscall. + */ +struct sys_stat_struct { + unsigned int st_dev; + long st_pad1[3]; + unsigned long st_ino; + unsigned int st_mode; + unsigned int st_nlink; + unsigned int st_uid; + unsigned int st_gid; + unsigned int st_rdev; + long st_pad2[2]; + long st_size; + long st_pad3; + + long st_atime; + long st_atime_nsec; + long st_mtime; + long st_mtime_nsec; + + long st_ctime; + long st_ctime_nsec; + long st_blksize; + long st_blocks; + long st_pad4[14]; +}; + +/* Syscalls for MIPS ABI O32 : + * - WARNING! there's always a delayed slot! + * - WARNING again, the syntax is different, registers take a '$' and numbers + * do not. + * - registers are 32-bit + * - stack is 8-byte aligned + * - syscall number is passed in v0 (starts at 0xfa0). + * - arguments are in a0, a1, a2, a3, then the stack. The caller needs to + * leave some room in the stack for the callee to save a0..a3 if needed. + * - Many registers are clobbered, in fact only a0..a2 and s0..s8 are + * preserved. See: https://www.linux-mips.org/wiki/Syscall as well as + * scall32-o32.S in the kernel sources. + * - the system call is performed by calling "syscall" + * - syscall return comes in v0, and register a3 needs to be checked to know + * if an error occurred, in which case errno is in v0. + * - the arguments are cast to long and assigned into the target registers + * which are then simply passed as registers to the asm code, so that we + * don't have to experience issues with register constraints. + */ + +#define my_syscall0(num) \ +({ \ + register long _num __asm__ ("v0") = (num); \ + register long _arg4 __asm__ ("a3"); \ + \ + __asm__ volatile ( \ + "addiu $sp, $sp, -32\n" \ + "syscall\n" \ + "addiu $sp, $sp, 32\n" \ + : "=r"(_num), "=r"(_arg4) \ + : "r"(_num) \ + : "memory", "cc", "at", "v1", "hi", "lo", \ + "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9" \ + ); \ + _arg4 ? -_num : _num; \ +}) + +#define my_syscall1(num, arg1) \ +({ \ + register long _num __asm__ ("v0") = (num); \ + register long _arg1 __asm__ ("a0") = (long)(arg1); \ + register long _arg4 __asm__ ("a3"); \ + \ + __asm__ volatile ( \ + "addiu $sp, $sp, -32\n" \ + "syscall\n" \ + "addiu $sp, $sp, 32\n" \ + : "=r"(_num), "=r"(_arg4) \ + : "0"(_num), \ + "r"(_arg1) \ + : "memory", "cc", "at", "v1", "hi", "lo", \ + "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9" \ + ); \ + _arg4 ? -_num : _num; \ +}) + +#define my_syscall2(num, arg1, arg2) \ +({ \ + register long _num __asm__ ("v0") = (num); \ + register long _arg1 __asm__ ("a0") = (long)(arg1); \ + register long _arg2 __asm__ ("a1") = (long)(arg2); \ + register long _arg4 __asm__ ("a3"); \ + \ + __asm__ volatile ( \ + "addiu $sp, $sp, -32\n" \ + "syscall\n" \ + "addiu $sp, $sp, 32\n" \ + : "=r"(_num), "=r"(_arg4) \ + : "0"(_num), \ + "r"(_arg1), "r"(_arg2) \ + : "memory", "cc", "at", "v1", "hi", "lo", \ + "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9" \ + ); \ + _arg4 ? -_num : _num; \ +}) + +#define my_syscall3(num, arg1, arg2, arg3) \ +({ \ + register long _num __asm__ ("v0") = (num); \ + register long _arg1 __asm__ ("a0") = (long)(arg1); \ + register long _arg2 __asm__ ("a1") = (long)(arg2); \ + register long _arg3 __asm__ ("a2") = (long)(arg3); \ + register long _arg4 __asm__ ("a3"); \ + \ + __asm__ volatile ( \ + "addiu $sp, $sp, -32\n" \ + "syscall\n" \ + "addiu $sp, $sp, 32\n" \ + : "=r"(_num), "=r"(_arg4) \ + : "0"(_num), \ + "r"(_arg1), "r"(_arg2), "r"(_arg3) \ + : "memory", "cc", "at", "v1", "hi", "lo", \ + "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9" \ + ); \ + _arg4 ? -_num : _num; \ +}) + +#define my_syscall4(num, arg1, arg2, arg3, arg4) \ +({ \ + register long _num __asm__ ("v0") = (num); \ + register long _arg1 __asm__ ("a0") = (long)(arg1); \ + register long _arg2 __asm__ ("a1") = (long)(arg2); \ + register long _arg3 __asm__ ("a2") = (long)(arg3); \ + register long _arg4 __asm__ ("a3") = (long)(arg4); \ + \ + __asm__ volatile ( \ + "addiu $sp, $sp, -32\n" \ + "syscall\n" \ + "addiu $sp, $sp, 32\n" \ + : "=r" (_num), "=r"(_arg4) \ + : "0"(_num), \ + "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4) \ + : "memory", "cc", "at", "v1", "hi", "lo", \ + "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9" \ + ); \ + _arg4 ? -_num : _num; \ +}) + +#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \ +({ \ + register long _num __asm__ ("v0") = (num); \ + register long _arg1 __asm__ ("a0") = (long)(arg1); \ + register long _arg2 __asm__ ("a1") = (long)(arg2); \ + register long _arg3 __asm__ ("a2") = (long)(arg3); \ + register long _arg4 __asm__ ("a3") = (long)(arg4); \ + register long _arg5 = (long)(arg5); \ + \ + __asm__ volatile ( \ + "addiu $sp, $sp, -32\n" \ + "sw %7, 16($sp)\n" \ + "syscall\n " \ + "addiu $sp, $sp, 32\n" \ + : "=r" (_num), "=r"(_arg4) \ + : "0"(_num), \ + "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5) \ + : "memory", "cc", "at", "v1", "hi", "lo", \ + "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9" \ + ); \ + _arg4 ? -_num : _num; \ +}) + +/* startup code, note that it's called __start on MIPS */ +__asm__ (".section .text\n" + ".weak __start\n" + ".set nomips16\n" + ".set noreorder\n" + ".option pic0\n" + ".ent __start\n" + "__start:\n" + "lw $a0,($sp)\n" // argc was in the stack + "addiu $a1, $sp, 4\n" // argv = sp + 4 + "sll $a2, $a0, 2\n" // a2 = argc * 4 + "add $a2, $a2, $a1\n" // envp = argv + 4*argc ... + "addiu $a2, $a2, 4\n" // ... + 4 + "li $t0, -8\n" + "and $sp, $sp, $t0\n" // sp must be 8-byte aligned + "addiu $sp,$sp,-16\n" // the callee expects to save a0..a3 there! + "jal main\n" // main() returns the status code, we'll exit with it. + "nop\n" // delayed slot + "move $a0, $v0\n" // retrieve 32-bit exit code from v0 + "li $v0, 4001\n" // NR_exit == 4001 + "syscall\n" + ".end __start\n" + ""); + +#endif // _NOLIBC_ARCH_MIPS_H diff --git a/tools/include/nolibc/arch-riscv.h b/tools/include/nolibc/arch-riscv.h new file mode 100644 index 000000000000..95e2b7924925 --- /dev/null +++ b/tools/include/nolibc/arch-riscv.h @@ -0,0 +1,204 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* + * RISCV (32 and 64) specific definitions for NOLIBC + * Copyright (C) 2017-2022 Willy Tarreau <w@1wt.eu> + */ + +#ifndef _NOLIBC_ARCH_RISCV_H +#define _NOLIBC_ARCH_RISCV_H + +/* O_* macros for fcntl/open are architecture-specific */ +#define O_RDONLY 0 +#define O_WRONLY 1 +#define O_RDWR 2 +#define O_CREAT 0x100 +#define O_EXCL 0x200 +#define O_NOCTTY 0x400 +#define O_TRUNC 0x1000 +#define O_APPEND 0x2000 +#define O_NONBLOCK 0x4000 +#define O_DIRECTORY 0x200000 + +struct sys_stat_struct { + unsigned long st_dev; /* Device. */ + unsigned long st_ino; /* File serial number. */ + unsigned int st_mode; /* File mode. */ + unsigned int st_nlink; /* Link count. */ + unsigned int st_uid; /* User ID of the file's owner. */ + unsigned int st_gid; /* Group ID of the file's group. */ + unsigned long st_rdev; /* Device number, if device. */ + unsigned long __pad1; + long st_size; /* Size of file, in bytes. */ + int st_blksize; /* Optimal block size for I/O. */ + int __pad2; + long st_blocks; /* Number 512-byte blocks allocated. */ + long st_atime; /* Time of last access. */ + unsigned long st_atime_nsec; + long st_mtime; /* Time of last modification. */ + unsigned long st_mtime_nsec; + long st_ctime; /* Time of last status change. */ + unsigned long st_ctime_nsec; + unsigned int __unused4; + unsigned int __unused5; +}; + +#if __riscv_xlen == 64 +#define PTRLOG "3" +#define SZREG "8" +#elif __riscv_xlen == 32 +#define PTRLOG "2" +#define SZREG "4" +#endif + +/* Syscalls for RISCV : + * - stack is 16-byte aligned + * - syscall number is passed in a7 + * - arguments are in a0, a1, a2, a3, a4, a5 + * - the system call is performed by calling ecall + * - syscall return comes in a0 + * - the arguments are cast to long and assigned into the target + * registers which are then simply passed as registers to the asm code, + * so that we don't have to experience issues with register constraints. + * + * On riscv, select() is not implemented so we have to use pselect6(). + */ +#define __ARCH_WANT_SYS_PSELECT6 + +#define my_syscall0(num) \ +({ \ + register long _num __asm__ ("a7") = (num); \ + register long _arg1 __asm__ ("a0"); \ + \ + __asm__ volatile ( \ + "ecall\n\t" \ + : "=r"(_arg1) \ + : "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#define my_syscall1(num, arg1) \ +({ \ + register long _num __asm__ ("a7") = (num); \ + register long _arg1 __asm__ ("a0") = (long)(arg1); \ + \ + __asm__ volatile ( \ + "ecall\n" \ + : "+r"(_arg1) \ + : "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#define my_syscall2(num, arg1, arg2) \ +({ \ + register long _num __asm__ ("a7") = (num); \ + register long _arg1 __asm__ ("a0") = (long)(arg1); \ + register long _arg2 __asm__ ("a1") = (long)(arg2); \ + \ + __asm__ volatile ( \ + "ecall\n" \ + : "+r"(_arg1) \ + : "r"(_arg2), \ + "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#define my_syscall3(num, arg1, arg2, arg3) \ +({ \ + register long _num __asm__ ("a7") = (num); \ + register long _arg1 __asm__ ("a0") = (long)(arg1); \ + register long _arg2 __asm__ ("a1") = (long)(arg2); \ + register long _arg3 __asm__ ("a2") = (long)(arg3); \ + \ + __asm__ volatile ( \ + "ecall\n\t" \ + : "+r"(_arg1) \ + : "r"(_arg2), "r"(_arg3), \ + "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#define my_syscall4(num, arg1, arg2, arg3, arg4) \ +({ \ + register long _num __asm__ ("a7") = (num); \ + register long _arg1 __asm__ ("a0") = (long)(arg1); \ + register long _arg2 __asm__ ("a1") = (long)(arg2); \ + register long _arg3 __asm__ ("a2") = (long)(arg3); \ + register long _arg4 __asm__ ("a3") = (long)(arg4); \ + \ + __asm__ volatile ( \ + "ecall\n" \ + : "+r"(_arg1) \ + : "r"(_arg2), "r"(_arg3), "r"(_arg4), \ + "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \ +({ \ + register long _num __asm__ ("a7") = (num); \ + register long _arg1 __asm__ ("a0") = (long)(arg1); \ + register long _arg2 __asm__ ("a1") = (long)(arg2); \ + register long _arg3 __asm__ ("a2") = (long)(arg3); \ + register long _arg4 __asm__ ("a3") = (long)(arg4); \ + register long _arg5 __asm__ ("a4") = (long)(arg5); \ + \ + __asm__ volatile ( \ + "ecall\n" \ + : "+r"(_arg1) \ + : "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \ + "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#define my_syscall6(num, arg1, arg2, arg3, arg4, arg5, arg6) \ +({ \ + register long _num __asm__ ("a7") = (num); \ + register long _arg1 __asm__ ("a0") = (long)(arg1); \ + register long _arg2 __asm__ ("a1") = (long)(arg2); \ + register long _arg3 __asm__ ("a2") = (long)(arg3); \ + register long _arg4 __asm__ ("a3") = (long)(arg4); \ + register long _arg5 __asm__ ("a4") = (long)(arg5); \ + register long _arg6 __asm__ ("a5") = (long)(arg6); \ + \ + __asm__ volatile ( \ + "ecall\n" \ + : "+r"(_arg1) \ + : "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), "r"(_arg6), \ + "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +/* startup code */ +__asm__ (".section .text\n" + ".weak _start\n" + "_start:\n" + ".option push\n" + ".option norelax\n" + "lla gp, __global_pointer$\n" + ".option pop\n" + "ld a0, 0(sp)\n" // argc (a0) was in the stack + "add a1, sp, "SZREG"\n" // argv (a1) = sp + "slli a2, a0, "PTRLOG"\n" // envp (a2) = SZREG*argc ... + "add a2, a2, "SZREG"\n" // + SZREG (skip null) + "add a2,a2,a1\n" // + argv + "andi sp,a1,-16\n" // sp must be 16-byte aligned + "call main\n" // main() returns the status code, we'll exit with it. + "li a7, 93\n" // NR_exit == 93 + "ecall\n" + ""); + +#endif // _NOLIBC_ARCH_RISCV_H diff --git a/tools/include/nolibc/arch-x86_64.h b/tools/include/nolibc/arch-x86_64.h new file mode 100644 index 000000000000..0e1e9eb8545d --- /dev/null +++ b/tools/include/nolibc/arch-x86_64.h @@ -0,0 +1,215 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* + * x86_64 specific definitions for NOLIBC + * Copyright (C) 2017-2022 Willy Tarreau <w@1wt.eu> + */ + +#ifndef _NOLIBC_ARCH_X86_64_H +#define _NOLIBC_ARCH_X86_64_H + +/* O_* macros for fcntl/open are architecture-specific */ +#define O_RDONLY 0 +#define O_WRONLY 1 +#define O_RDWR 2 +#define O_CREAT 0x40 +#define O_EXCL 0x80 +#define O_NOCTTY 0x100 +#define O_TRUNC 0x200 +#define O_APPEND 0x400 +#define O_NONBLOCK 0x800 +#define O_DIRECTORY 0x10000 + +/* The struct returned by the stat() syscall, equivalent to stat64(). The + * syscall returns 116 bytes and stops in the middle of __unused. + */ +struct sys_stat_struct { + unsigned long st_dev; + unsigned long st_ino; + unsigned long st_nlink; + unsigned int st_mode; + unsigned int st_uid; + + unsigned int st_gid; + unsigned int __pad0; + unsigned long st_rdev; + long st_size; + long st_blksize; + + long st_blocks; + unsigned long st_atime; + unsigned long st_atime_nsec; + unsigned long st_mtime; + + unsigned long st_mtime_nsec; + unsigned long st_ctime; + unsigned long st_ctime_nsec; + long __unused[3]; +}; + +/* Syscalls for x86_64 : + * - registers are 64-bit + * - syscall number is passed in rax + * - arguments are in rdi, rsi, rdx, r10, r8, r9 respectively + * - the system call is performed by calling the syscall instruction + * - syscall return comes in rax + * - rcx and r11 are clobbered, others are preserved. + * - the arguments are cast to long and assigned into the target registers + * which are then simply passed as registers to the asm code, so that we + * don't have to experience issues with register constraints. + * - the syscall number is always specified last in order to allow to force + * some registers before (gcc refuses a %-register at the last position). + * - see also x86-64 ABI section A.2 AMD64 Linux Kernel Conventions, A.2.1 + * Calling Conventions. + * + * Link x86-64 ABI: https://gitlab.com/x86-psABIs/x86-64-ABI/-/wikis/home + * + */ + +#define my_syscall0(num) \ +({ \ + long _ret; \ + register long _num __asm__ ("rax") = (num); \ + \ + __asm__ volatile ( \ + "syscall\n" \ + : "=a"(_ret) \ + : "0"(_num) \ + : "rcx", "r11", "memory", "cc" \ + ); \ + _ret; \ +}) + +#define my_syscall1(num, arg1) \ +({ \ + long _ret; \ + register long _num __asm__ ("rax") = (num); \ + register long _arg1 __asm__ ("rdi") = (long)(arg1); \ + \ + __asm__ volatile ( \ + "syscall\n" \ + : "=a"(_ret) \ + : "r"(_arg1), \ + "0"(_num) \ + : "rcx", "r11", "memory", "cc" \ + ); \ + _ret; \ +}) + +#define my_syscall2(num, arg1, arg2) \ +({ \ + long _ret; \ + register long _num __asm__ ("rax") = (num); \ + register long _arg1 __asm__ ("rdi") = (long)(arg1); \ + register long _arg2 __asm__ ("rsi") = (long)(arg2); \ + \ + __asm__ volatile ( \ + "syscall\n" \ + : "=a"(_ret) \ + : "r"(_arg1), "r"(_arg2), \ + "0"(_num) \ + : "rcx", "r11", "memory", "cc" \ + ); \ + _ret; \ +}) + +#define my_syscall3(num, arg1, arg2, arg3) \ +({ \ + long _ret; \ + register long _num __asm__ ("rax") = (num); \ + register long _arg1 __asm__ ("rdi") = (long)(arg1); \ + register long _arg2 __asm__ ("rsi") = (long)(arg2); \ + register long _arg3 __asm__ ("rdx") = (long)(arg3); \ + \ + __asm__ volatile ( \ + "syscall\n" \ + : "=a"(_ret) \ + : "r"(_arg1), "r"(_arg2), "r"(_arg3), \ + "0"(_num) \ + : "rcx", "r11", "memory", "cc" \ + ); \ + _ret; \ +}) + +#define my_syscall4(num, arg1, arg2, arg3, arg4) \ +({ \ + long _ret; \ + register long _num __asm__ ("rax") = (num); \ + register long _arg1 __asm__ ("rdi") = (long)(arg1); \ + register long _arg2 __asm__ ("rsi") = (long)(arg2); \ + register long _arg3 __asm__ ("rdx") = (long)(arg3); \ + register long _arg4 __asm__ ("r10") = (long)(arg4); \ + \ + __asm__ volatile ( \ + "syscall\n" \ + : "=a"(_ret) \ + : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), \ + "0"(_num) \ + : "rcx", "r11", "memory", "cc" \ + ); \ + _ret; \ +}) + +#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \ +({ \ + long _ret; \ + register long _num __asm__ ("rax") = (num); \ + register long _arg1 __asm__ ("rdi") = (long)(arg1); \ + register long _arg2 __asm__ ("rsi") = (long)(arg2); \ + register long _arg3 __asm__ ("rdx") = (long)(arg3); \ + register long _arg4 __asm__ ("r10") = (long)(arg4); \ + register long _arg5 __asm__ ("r8") = (long)(arg5); \ + \ + __asm__ volatile ( \ + "syscall\n" \ + : "=a"(_ret) \ + : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \ + "0"(_num) \ + : "rcx", "r11", "memory", "cc" \ + ); \ + _ret; \ +}) + +#define my_syscall6(num, arg1, arg2, arg3, arg4, arg5, arg6) \ +({ \ + long _ret; \ + register long _num __asm__ ("rax") = (num); \ + register long _arg1 __asm__ ("rdi") = (long)(arg1); \ + register long _arg2 __asm__ ("rsi") = (long)(arg2); \ + register long _arg3 __asm__ ("rdx") = (long)(arg3); \ + register long _arg4 __asm__ ("r10") = (long)(arg4); \ + register long _arg5 __asm__ ("r8") = (long)(arg5); \ + register long _arg6 __asm__ ("r9") = (long)(arg6); \ + \ + __asm__ volatile ( \ + "syscall\n" \ + : "=a"(_ret) \ + : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \ + "r"(_arg6), "0"(_num) \ + : "rcx", "r11", "memory", "cc" \ + ); \ + _ret; \ +}) + +/* startup code */ +/* + * x86-64 System V ABI mandates: + * 1) %rsp must be 16-byte aligned right before the function call. + * 2) The deepest stack frame should be zero (the %rbp). + * + */ +__asm__ (".section .text\n" + ".weak _start\n" + "_start:\n" + "pop %rdi\n" // argc (first arg, %rdi) + "mov %rsp, %rsi\n" // argv[] (second arg, %rsi) + "lea 8(%rsi,%rdi,8),%rdx\n" // then a NULL then envp (third arg, %rdx) + "xor %ebp, %ebp\n" // zero the stack frame + "and $-16, %rsp\n" // x86 ABI : esp must be 16-byte aligned before call + "call main\n" // main() returns the status code, we'll exit with it. + "mov %eax, %edi\n" // retrieve exit code (32 bit) + "mov $60, %eax\n" // NR_exit == 60 + "syscall\n" // really exit + "hlt\n" // ensure it does not return + ""); + +#endif // _NOLIBC_ARCH_X86_64_H diff --git a/tools/include/nolibc/arch.h b/tools/include/nolibc/arch.h new file mode 100644 index 000000000000..4c6992321b0d --- /dev/null +++ b/tools/include/nolibc/arch.h @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* + * Copyright (C) 2017-2022 Willy Tarreau <w@1wt.eu> + */ + +/* Below comes the architecture-specific code. For each architecture, we have + * the syscall declarations and the _start code definition. This is the only + * global part. On all architectures the kernel puts everything in the stack + * before jumping to _start just above us, without any return address (_start + * is not a function but an entry pint). So at the stack pointer we find argc. + * Then argv[] begins, and ends at the first NULL. Then we have envp which + * starts and ends with a NULL as well. So envp=argv+argc+1. + */ + +#ifndef _NOLIBC_ARCH_H +#define _NOLIBC_ARCH_H + +#if defined(__x86_64__) +#include "arch-x86_64.h" +#elif defined(__i386__) || defined(__i486__) || defined(__i586__) || defined(__i686__) +#include "arch-i386.h" +#elif defined(__ARM_EABI__) +#include "arch-arm.h" +#elif defined(__aarch64__) +#include "arch-aarch64.h" +#elif defined(__mips__) && defined(_ABIO32) +#include "arch-mips.h" +#elif defined(__riscv) +#include "arch-riscv.h" +#endif + +#endif /* _NOLIBC_ARCH_H */ diff --git a/tools/include/nolibc/ctype.h b/tools/include/nolibc/ctype.h new file mode 100644 index 000000000000..e3000b2992d7 --- /dev/null +++ b/tools/include/nolibc/ctype.h @@ -0,0 +1,99 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* + * ctype function definitions for NOLIBC + * Copyright (C) 2017-2021 Willy Tarreau <w@1wt.eu> + */ + +#ifndef _NOLIBC_CTYPE_H +#define _NOLIBC_CTYPE_H + +#include "std.h" + +/* + * As much as possible, please keep functions alphabetically sorted. + */ + +static __attribute__((unused)) +int isascii(int c) +{ + /* 0x00..0x7f */ + return (unsigned int)c <= 0x7f; +} + +static __attribute__((unused)) +int isblank(int c) +{ + return c == '\t' || c == ' '; +} + +static __attribute__((unused)) +int iscntrl(int c) +{ + /* 0x00..0x1f, 0x7f */ + return (unsigned int)c < 0x20 || c == 0x7f; +} + +static __attribute__((unused)) +int isdigit(int c) +{ + return (unsigned int)(c - '0') < 10; +} + +static __attribute__((unused)) +int isgraph(int c) +{ + /* 0x21..0x7e */ + return (unsigned int)(c - 0x21) < 0x5e; +} + +static __attribute__((unused)) +int islower(int c) +{ + return (unsigned int)(c - 'a') < 26; +} + +static __attribute__((unused)) +int isprint(int c) +{ + /* 0x20..0x7e */ + return (unsigned int)(c - 0x20) < 0x5f; +} + +static __attribute__((unused)) +int isspace(int c) +{ + /* \t is 0x9, \n is 0xA, \v is 0xB, \f is 0xC, \r is 0xD */ + return ((unsigned int)c == ' ') || (unsigned int)(c - 0x09) < 5; +} + +static __attribute__((unused)) +int isupper(int c) +{ + return (unsigned int)(c - 'A') < 26; +} + +static __attribute__((unused)) +int isxdigit(int c) +{ + return isdigit(c) || (unsigned int)(c - 'A') < 6 || (unsigned int)(c - 'a') < 6; +} + +static __attribute__((unused)) +int isalpha(int c) +{ + return islower(c) || isupper(c); +} + +static __attribute__((unused)) +int isalnum(int c) +{ + return isalpha(c) || isdigit(c); +} + +static __attribute__((unused)) +int ispunct(int c) +{ + return isgraph(c) && !isalnum(c); +} + +#endif /* _NOLIBC_CTYPE_H */ diff --git a/tools/include/nolibc/errno.h b/tools/include/nolibc/errno.h new file mode 100644 index 000000000000..06893d6dfb7a --- /dev/null +++ b/tools/include/nolibc/errno.h @@ -0,0 +1,27 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* + * Minimal errno definitions for NOLIBC + * Copyright (C) 2017-2022 Willy Tarreau <w@1wt.eu> + */ + +#ifndef _NOLIBC_ERRNO_H +#define _NOLIBC_ERRNO_H + +#include <asm/errno.h> + +/* this way it will be removed if unused */ +static int errno; + +#ifndef NOLIBC_IGNORE_ERRNO +#define SET_ERRNO(v) do { errno = (v); } while (0) +#else +#define SET_ERRNO(v) do { } while (0) +#endif + + +/* errno codes all ensure that they will not conflict with a valid pointer + * because they all correspond to the highest addressable memory page. + */ +#define MAX_ERRNO 4095 + +#endif /* _NOLIBC_ERRNO_H */ diff --git a/tools/include/nolibc/nolibc.h b/tools/include/nolibc/nolibc.h index c1c285fe494a..b2bc48d3cfe4 100644 --- a/tools/include/nolibc/nolibc.h +++ b/tools/include/nolibc/nolibc.h @@ -57,22 +57,32 @@ * having to specify anything. * * Finally some very common libc-level functions are provided. It is the case - * for a few functions usually found in string.h, ctype.h, or stdlib.h. Nothing - * is currently provided regarding stdio emulation. + * for a few functions usually found in string.h, ctype.h, or stdlib.h. * - * The macro NOLIBC is always defined, so that it is possible for a program to - * check this macro to know if it is being built against and decide to disable - * some features or simply not to include some standard libc files. - * - * Ideally this file should be split in multiple files for easier long term - * maintenance, but provided as a single file as it is now, it's quite - * convenient to use. Maybe some variations involving a set of includes at the - * top could work. + * The nolibc.h file is only a convenient entry point which includes all other + * files. It also defines the NOLIBC macro, so that it is possible for a + * program to check this macro to know if it is being built against and decide + * to disable some features or simply not to include some standard libc files. * * A simple static executable may be built this way : * $ gcc -fno-asynchronous-unwind-tables -fno-ident -s -Os -nostdlib \ * -static -include nolibc.h -o hello hello.c -lgcc * + * Simple programs meant to be reasonably portable to various libc and using + * only a few common includes, may also be built by simply making the include + * path point to the nolibc directory: + * $ gcc -fno-asynchronous-unwind-tables -fno-ident -s -Os -nostdlib \ + * -I../nolibc -o hello hello.c -lgcc + * + * The available standard (but limited) include files are: + * ctype.h, errno.h, signal.h, stdio.h, stdlib.h, string.h, time.h + * + * In addition, the following ones are expected to be provided by the compiler: + * float.h, stdarg.h, stddef.h + * + * The following ones which are part to the C standard are not provided: + * assert.h, locale.h, math.h, setjmp.h, limits.h + * * A very useful calling convention table may be found here : * http://man7.org/linux/man-pages/man2/syscall.2.html * @@ -80,2502 +90,22 @@ * https://w3challs.com/syscalls/ * */ +#ifndef _NOLIBC_H +#define _NOLIBC_H -#include <asm/unistd.h> -#include <asm/ioctls.h> -#include <asm/errno.h> -#include <linux/fs.h> -#include <linux/loop.h> -#include <linux/time.h> +#include "std.h" +#include "arch.h" +#include "types.h" +#include "sys.h" +#include "ctype.h" +#include "signal.h" +#include "stdio.h" +#include "stdlib.h" +#include "string.h" +#include "time.h" +#include "unistd.h" +/* Used by programs to avoid std includes */ #define NOLIBC -/* this way it will be removed if unused */ -static int errno; - -#ifndef NOLIBC_IGNORE_ERRNO -#define SET_ERRNO(v) do { errno = (v); } while (0) -#else -#define SET_ERRNO(v) do { } while (0) -#endif - -/* errno codes all ensure that they will not conflict with a valid pointer - * because they all correspond to the highest addressable memory page. - */ -#define MAX_ERRNO 4095 - -/* Declare a few quite common macros and types that usually are in stdlib.h, - * stdint.h, ctype.h, unistd.h and a few other common locations. - */ - -#define NULL ((void *)0) - -/* stdint types */ -typedef unsigned char uint8_t; -typedef signed char int8_t; -typedef unsigned short uint16_t; -typedef signed short int16_t; -typedef unsigned int uint32_t; -typedef signed int int32_t; -typedef unsigned long long uint64_t; -typedef signed long long int64_t; -typedef unsigned long size_t; -typedef signed long ssize_t; -typedef unsigned long uintptr_t; -typedef signed long intptr_t; -typedef signed long ptrdiff_t; - -/* for stat() */ -typedef unsigned int dev_t; -typedef unsigned long ino_t; -typedef unsigned int mode_t; -typedef signed int pid_t; -typedef unsigned int uid_t; -typedef unsigned int gid_t; -typedef unsigned long nlink_t; -typedef signed long off_t; -typedef signed long blksize_t; -typedef signed long blkcnt_t; -typedef signed long time_t; - -/* for poll() */ -struct pollfd { - int fd; - short int events; - short int revents; -}; - -/* for getdents64() */ -struct linux_dirent64 { - uint64_t d_ino; - int64_t d_off; - unsigned short d_reclen; - unsigned char d_type; - char d_name[]; -}; - -/* commonly an fd_set represents 256 FDs */ -#define FD_SETSIZE 256 -typedef struct { uint32_t fd32[FD_SETSIZE/32]; } fd_set; - -/* needed by wait4() */ -struct rusage { - struct timeval ru_utime; - struct timeval ru_stime; - long ru_maxrss; - long ru_ixrss; - long ru_idrss; - long ru_isrss; - long ru_minflt; - long ru_majflt; - long ru_nswap; - long ru_inblock; - long ru_oublock; - long ru_msgsnd; - long ru_msgrcv; - long ru_nsignals; - long ru_nvcsw; - long ru_nivcsw; -}; - -/* stat flags (WARNING, octal here) */ -#define S_IFDIR 0040000 -#define S_IFCHR 0020000 -#define S_IFBLK 0060000 -#define S_IFREG 0100000 -#define S_IFIFO 0010000 -#define S_IFLNK 0120000 -#define S_IFSOCK 0140000 -#define S_IFMT 0170000 - -#define S_ISDIR(mode) (((mode) & S_IFDIR) == S_IFDIR) -#define S_ISCHR(mode) (((mode) & S_IFCHR) == S_IFCHR) -#define S_ISBLK(mode) (((mode) & S_IFBLK) == S_IFBLK) -#define S_ISREG(mode) (((mode) & S_IFREG) == S_IFREG) -#define S_ISFIFO(mode) (((mode) & S_IFIFO) == S_IFIFO) -#define S_ISLNK(mode) (((mode) & S_IFLNK) == S_IFLNK) -#define S_ISSOCK(mode) (((mode) & S_IFSOCK) == S_IFSOCK) - -#define DT_UNKNOWN 0 -#define DT_FIFO 1 -#define DT_CHR 2 -#define DT_DIR 4 -#define DT_BLK 6 -#define DT_REG 8 -#define DT_LNK 10 -#define DT_SOCK 12 - -/* all the *at functions */ -#ifndef AT_FDCWD -#define AT_FDCWD -100 -#endif - -/* lseek */ -#define SEEK_SET 0 -#define SEEK_CUR 1 -#define SEEK_END 2 - -/* reboot */ -#define LINUX_REBOOT_MAGIC1 0xfee1dead -#define LINUX_REBOOT_MAGIC2 0x28121969 -#define LINUX_REBOOT_CMD_HALT 0xcdef0123 -#define LINUX_REBOOT_CMD_POWER_OFF 0x4321fedc -#define LINUX_REBOOT_CMD_RESTART 0x01234567 -#define LINUX_REBOOT_CMD_SW_SUSPEND 0xd000fce2 - - -/* The format of the struct as returned by the libc to the application, which - * significantly differs from the format returned by the stat() syscall flavours. - */ -struct stat { - dev_t st_dev; /* ID of device containing file */ - ino_t st_ino; /* inode number */ - mode_t st_mode; /* protection */ - nlink_t st_nlink; /* number of hard links */ - uid_t st_uid; /* user ID of owner */ - gid_t st_gid; /* group ID of owner */ - dev_t st_rdev; /* device ID (if special file) */ - off_t st_size; /* total size, in bytes */ - blksize_t st_blksize; /* blocksize for file system I/O */ - blkcnt_t st_blocks; /* number of 512B blocks allocated */ - time_t st_atime; /* time of last access */ - time_t st_mtime; /* time of last modification */ - time_t st_ctime; /* time of last status change */ -}; - -#define WEXITSTATUS(status) (((status) & 0xff00) >> 8) -#define WIFEXITED(status) (((status) & 0x7f) == 0) - -/* for SIGCHLD */ -#include <asm/signal.h> - -/* Below comes the architecture-specific code. For each architecture, we have - * the syscall declarations and the _start code definition. This is the only - * global part. On all architectures the kernel puts everything in the stack - * before jumping to _start just above us, without any return address (_start - * is not a function but an entry pint). So at the stack pointer we find argc. - * Then argv[] begins, and ends at the first NULL. Then we have envp which - * starts and ends with a NULL as well. So envp=argv+argc+1. - */ - -#if defined(__x86_64__) -/* Syscalls for x86_64 : - * - registers are 64-bit - * - syscall number is passed in rax - * - arguments are in rdi, rsi, rdx, r10, r8, r9 respectively - * - the system call is performed by calling the syscall instruction - * - syscall return comes in rax - * - rcx and r11 are clobbered, others are preserved. - * - the arguments are cast to long and assigned into the target registers - * which are then simply passed as registers to the asm code, so that we - * don't have to experience issues with register constraints. - * - the syscall number is always specified last in order to allow to force - * some registers before (gcc refuses a %-register at the last position). - * - see also x86-64 ABI section A.2 AMD64 Linux Kernel Conventions, A.2.1 - * Calling Conventions. - * - * Link x86-64 ABI: https://gitlab.com/x86-psABIs/x86-64-ABI/-/wikis/x86-64-psABI - * - */ - -#define my_syscall0(num) \ -({ \ - long _ret; \ - register long _num asm("rax") = (num); \ - \ - asm volatile ( \ - "syscall\n" \ - : "=a"(_ret) \ - : "0"(_num) \ - : "rcx", "r11", "memory", "cc" \ - ); \ - _ret; \ -}) - -#define my_syscall1(num, arg1) \ -({ \ - long _ret; \ - register long _num asm("rax") = (num); \ - register long _arg1 asm("rdi") = (long)(arg1); \ - \ - asm volatile ( \ - "syscall\n" \ - : "=a"(_ret) \ - : "r"(_arg1), \ - "0"(_num) \ - : "rcx", "r11", "memory", "cc" \ - ); \ - _ret; \ -}) - -#define my_syscall2(num, arg1, arg2) \ -({ \ - long _ret; \ - register long _num asm("rax") = (num); \ - register long _arg1 asm("rdi") = (long)(arg1); \ - register long _arg2 asm("rsi") = (long)(arg2); \ - \ - asm volatile ( \ - "syscall\n" \ - : "=a"(_ret) \ - : "r"(_arg1), "r"(_arg2), \ - "0"(_num) \ - : "rcx", "r11", "memory", "cc" \ - ); \ - _ret; \ -}) - -#define my_syscall3(num, arg1, arg2, arg3) \ -({ \ - long _ret; \ - register long _num asm("rax") = (num); \ - register long _arg1 asm("rdi") = (long)(arg1); \ - register long _arg2 asm("rsi") = (long)(arg2); \ - register long _arg3 asm("rdx") = (long)(arg3); \ - \ - asm volatile ( \ - "syscall\n" \ - : "=a"(_ret) \ - : "r"(_arg1), "r"(_arg2), "r"(_arg3), \ - "0"(_num) \ - : "rcx", "r11", "memory", "cc" \ - ); \ - _ret; \ -}) - -#define my_syscall4(num, arg1, arg2, arg3, arg4) \ -({ \ - long _ret; \ - register long _num asm("rax") = (num); \ - register long _arg1 asm("rdi") = (long)(arg1); \ - register long _arg2 asm("rsi") = (long)(arg2); \ - register long _arg3 asm("rdx") = (long)(arg3); \ - register long _arg4 asm("r10") = (long)(arg4); \ - \ - asm volatile ( \ - "syscall\n" \ - : "=a"(_ret) \ - : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), \ - "0"(_num) \ - : "rcx", "r11", "memory", "cc" \ - ); \ - _ret; \ -}) - -#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \ -({ \ - long _ret; \ - register long _num asm("rax") = (num); \ - register long _arg1 asm("rdi") = (long)(arg1); \ - register long _arg2 asm("rsi") = (long)(arg2); \ - register long _arg3 asm("rdx") = (long)(arg3); \ - register long _arg4 asm("r10") = (long)(arg4); \ - register long _arg5 asm("r8") = (long)(arg5); \ - \ - asm volatile ( \ - "syscall\n" \ - : "=a"(_ret) \ - : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \ - "0"(_num) \ - : "rcx", "r11", "memory", "cc" \ - ); \ - _ret; \ -}) - -#define my_syscall6(num, arg1, arg2, arg3, arg4, arg5, arg6) \ -({ \ - long _ret; \ - register long _num asm("rax") = (num); \ - register long _arg1 asm("rdi") = (long)(arg1); \ - register long _arg2 asm("rsi") = (long)(arg2); \ - register long _arg3 asm("rdx") = (long)(arg3); \ - register long _arg4 asm("r10") = (long)(arg4); \ - register long _arg5 asm("r8") = (long)(arg5); \ - register long _arg6 asm("r9") = (long)(arg6); \ - \ - asm volatile ( \ - "syscall\n" \ - : "=a"(_ret) \ - : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \ - "r"(_arg6), "0"(_num) \ - : "rcx", "r11", "memory", "cc" \ - ); \ - _ret; \ -}) - -/* startup code */ -/* - * x86-64 System V ABI mandates: - * 1) %rsp must be 16-byte aligned right before the function call. - * 2) The deepest stack frame should be zero (the %rbp). - * - */ -asm(".section .text\n" - ".global _start\n" - "_start:\n" - "pop %rdi\n" // argc (first arg, %rdi) - "mov %rsp, %rsi\n" // argv[] (second arg, %rsi) - "lea 8(%rsi,%rdi,8),%rdx\n" // then a NULL then envp (third arg, %rdx) - "xor %ebp, %ebp\n" // zero the stack frame - "and $-16, %rsp\n" // x86 ABI : esp must be 16-byte aligned before call - "call main\n" // main() returns the status code, we'll exit with it. - "mov %eax, %edi\n" // retrieve exit code (32 bit) - "mov $60, %eax\n" // NR_exit == 60 - "syscall\n" // really exit - "hlt\n" // ensure it does not return - ""); - -/* fcntl / open */ -#define O_RDONLY 0 -#define O_WRONLY 1 -#define O_RDWR 2 -#define O_CREAT 0x40 -#define O_EXCL 0x80 -#define O_NOCTTY 0x100 -#define O_TRUNC 0x200 -#define O_APPEND 0x400 -#define O_NONBLOCK 0x800 -#define O_DIRECTORY 0x10000 - -/* The struct returned by the stat() syscall, equivalent to stat64(). The - * syscall returns 116 bytes and stops in the middle of __unused. - */ -struct sys_stat_struct { - unsigned long st_dev; - unsigned long st_ino; - unsigned long st_nlink; - unsigned int st_mode; - unsigned int st_uid; - - unsigned int st_gid; - unsigned int __pad0; - unsigned long st_rdev; - long st_size; - long st_blksize; - - long st_blocks; - unsigned long st_atime; - unsigned long st_atime_nsec; - unsigned long st_mtime; - - unsigned long st_mtime_nsec; - unsigned long st_ctime; - unsigned long st_ctime_nsec; - long __unused[3]; -}; - -#elif defined(__i386__) || defined(__i486__) || defined(__i586__) || defined(__i686__) -/* Syscalls for i386 : - * - mostly similar to x86_64 - * - registers are 32-bit - * - syscall number is passed in eax - * - arguments are in ebx, ecx, edx, esi, edi, ebp respectively - * - all registers are preserved (except eax of course) - * - the system call is performed by calling int $0x80 - * - syscall return comes in eax - * - the arguments are cast to long and assigned into the target registers - * which are then simply passed as registers to the asm code, so that we - * don't have to experience issues with register constraints. - * - the syscall number is always specified last in order to allow to force - * some registers before (gcc refuses a %-register at the last position). - * - * Also, i386 supports the old_select syscall if newselect is not available - */ -#define __ARCH_WANT_SYS_OLD_SELECT - -#define my_syscall0(num) \ -({ \ - long _ret; \ - register long _num asm("eax") = (num); \ - \ - asm volatile ( \ - "int $0x80\n" \ - : "=a" (_ret) \ - : "0"(_num) \ - : "memory", "cc" \ - ); \ - _ret; \ -}) - -#define my_syscall1(num, arg1) \ -({ \ - long _ret; \ - register long _num asm("eax") = (num); \ - register long _arg1 asm("ebx") = (long)(arg1); \ - \ - asm volatile ( \ - "int $0x80\n" \ - : "=a" (_ret) \ - : "r"(_arg1), \ - "0"(_num) \ - : "memory", "cc" \ - ); \ - _ret; \ -}) - -#define my_syscall2(num, arg1, arg2) \ -({ \ - long _ret; \ - register long _num asm("eax") = (num); \ - register long _arg1 asm("ebx") = (long)(arg1); \ - register long _arg2 asm("ecx") = (long)(arg2); \ - \ - asm volatile ( \ - "int $0x80\n" \ - : "=a" (_ret) \ - : "r"(_arg1), "r"(_arg2), \ - "0"(_num) \ - : "memory", "cc" \ - ); \ - _ret; \ -}) - -#define my_syscall3(num, arg1, arg2, arg3) \ -({ \ - long _ret; \ - register long _num asm("eax") = (num); \ - register long _arg1 asm("ebx") = (long)(arg1); \ - register long _arg2 asm("ecx") = (long)(arg2); \ - register long _arg3 asm("edx") = (long)(arg3); \ - \ - asm volatile ( \ - "int $0x80\n" \ - : "=a" (_ret) \ - : "r"(_arg1), "r"(_arg2), "r"(_arg3), \ - "0"(_num) \ - : "memory", "cc" \ - ); \ - _ret; \ -}) - -#define my_syscall4(num, arg1, arg2, arg3, arg4) \ -({ \ - long _ret; \ - register long _num asm("eax") = (num); \ - register long _arg1 asm("ebx") = (long)(arg1); \ - register long _arg2 asm("ecx") = (long)(arg2); \ - register long _arg3 asm("edx") = (long)(arg3); \ - register long _arg4 asm("esi") = (long)(arg4); \ - \ - asm volatile ( \ - "int $0x80\n" \ - : "=a" (_ret) \ - : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), \ - "0"(_num) \ - : "memory", "cc" \ - ); \ - _ret; \ -}) - -#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \ -({ \ - long _ret; \ - register long _num asm("eax") = (num); \ - register long _arg1 asm("ebx") = (long)(arg1); \ - register long _arg2 asm("ecx") = (long)(arg2); \ - register long _arg3 asm("edx") = (long)(arg3); \ - register long _arg4 asm("esi") = (long)(arg4); \ - register long _arg5 asm("edi") = (long)(arg5); \ - \ - asm volatile ( \ - "int $0x80\n" \ - : "=a" (_ret) \ - : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \ - "0"(_num) \ - : "memory", "cc" \ - ); \ - _ret; \ -}) - -/* startup code */ -/* - * i386 System V ABI mandates: - * 1) last pushed argument must be 16-byte aligned. - * 2) The deepest stack frame should be set to zero - * - */ -asm(".section .text\n" - ".global _start\n" - "_start:\n" - "pop %eax\n" // argc (first arg, %eax) - "mov %esp, %ebx\n" // argv[] (second arg, %ebx) - "lea 4(%ebx,%eax,4),%ecx\n" // then a NULL then envp (third arg, %ecx) - "xor %ebp, %ebp\n" // zero the stack frame - "and $-16, %esp\n" // x86 ABI : esp must be 16-byte aligned before - "sub $4, %esp\n" // the call instruction (args are aligned) - "push %ecx\n" // push all registers on the stack so that we - "push %ebx\n" // support both regparm and plain stack modes - "push %eax\n" - "call main\n" // main() returns the status code in %eax - "mov %eax, %ebx\n" // retrieve exit code (32-bit int) - "movl $1, %eax\n" // NR_exit == 1 - "int $0x80\n" // exit now - "hlt\n" // ensure it does not - ""); - -/* fcntl / open */ -#define O_RDONLY 0 -#define O_WRONLY 1 -#define O_RDWR 2 -#define O_CREAT 0x40 -#define O_EXCL 0x80 -#define O_NOCTTY 0x100 -#define O_TRUNC 0x200 -#define O_APPEND 0x400 -#define O_NONBLOCK 0x800 -#define O_DIRECTORY 0x10000 - -/* The struct returned by the stat() syscall, 32-bit only, the syscall returns - * exactly 56 bytes (stops before the unused array). - */ -struct sys_stat_struct { - unsigned long st_dev; - unsigned long st_ino; - unsigned short st_mode; - unsigned short st_nlink; - unsigned short st_uid; - unsigned short st_gid; - - unsigned long st_rdev; - unsigned long st_size; - unsigned long st_blksize; - unsigned long st_blocks; - - unsigned long st_atime; - unsigned long st_atime_nsec; - unsigned long st_mtime; - unsigned long st_mtime_nsec; - - unsigned long st_ctime; - unsigned long st_ctime_nsec; - unsigned long __unused[2]; -}; - -#elif defined(__ARM_EABI__) -/* Syscalls for ARM in ARM or Thumb modes : - * - registers are 32-bit - * - stack is 8-byte aligned - * ( http://infocenter.arm.com/help/index.jsp?topic=/com.arm.doc.faqs/ka4127.html) - * - syscall number is passed in r7 - * - arguments are in r0, r1, r2, r3, r4, r5 - * - the system call is performed by calling svc #0 - * - syscall return comes in r0. - * - only lr is clobbered. - * - the arguments are cast to long and assigned into the target registers - * which are then simply passed as registers to the asm code, so that we - * don't have to experience issues with register constraints. - * - the syscall number is always specified last in order to allow to force - * some registers before (gcc refuses a %-register at the last position). - * - * Also, ARM supports the old_select syscall if newselect is not available - */ -#define __ARCH_WANT_SYS_OLD_SELECT - -#define my_syscall0(num) \ -({ \ - register long _num asm("r7") = (num); \ - register long _arg1 asm("r0"); \ - \ - asm volatile ( \ - "svc #0\n" \ - : "=r"(_arg1) \ - : "r"(_num) \ - : "memory", "cc", "lr" \ - ); \ - _arg1; \ -}) - -#define my_syscall1(num, arg1) \ -({ \ - register long _num asm("r7") = (num); \ - register long _arg1 asm("r0") = (long)(arg1); \ - \ - asm volatile ( \ - "svc #0\n" \ - : "=r"(_arg1) \ - : "r"(_arg1), \ - "r"(_num) \ - : "memory", "cc", "lr" \ - ); \ - _arg1; \ -}) - -#define my_syscall2(num, arg1, arg2) \ -({ \ - register long _num asm("r7") = (num); \ - register long _arg1 asm("r0") = (long)(arg1); \ - register long _arg2 asm("r1") = (long)(arg2); \ - \ - asm volatile ( \ - "svc #0\n" \ - : "=r"(_arg1) \ - : "r"(_arg1), "r"(_arg2), \ - "r"(_num) \ - : "memory", "cc", "lr" \ - ); \ - _arg1; \ -}) - -#define my_syscall3(num, arg1, arg2, arg3) \ -({ \ - register long _num asm("r7") = (num); \ - register long _arg1 asm("r0") = (long)(arg1); \ - register long _arg2 asm("r1") = (long)(arg2); \ - register long _arg3 asm("r2") = (long)(arg3); \ - \ - asm volatile ( \ - "svc #0\n" \ - : "=r"(_arg1) \ - : "r"(_arg1), "r"(_arg2), "r"(_arg3), \ - "r"(_num) \ - : "memory", "cc", "lr" \ - ); \ - _arg1; \ -}) - -#define my_syscall4(num, arg1, arg2, arg3, arg4) \ -({ \ - register long _num asm("r7") = (num); \ - register long _arg1 asm("r0") = (long)(arg1); \ - register long _arg2 asm("r1") = (long)(arg2); \ - register long _arg3 asm("r2") = (long)(arg3); \ - register long _arg4 asm("r3") = (long)(arg4); \ - \ - asm volatile ( \ - "svc #0\n" \ - : "=r"(_arg1) \ - : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), \ - "r"(_num) \ - : "memory", "cc", "lr" \ - ); \ - _arg1; \ -}) - -#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \ -({ \ - register long _num asm("r7") = (num); \ - register long _arg1 asm("r0") = (long)(arg1); \ - register long _arg2 asm("r1") = (long)(arg2); \ - register long _arg3 asm("r2") = (long)(arg3); \ - register long _arg4 asm("r3") = (long)(arg4); \ - register long _arg5 asm("r4") = (long)(arg5); \ - \ - asm volatile ( \ - "svc #0\n" \ - : "=r" (_arg1) \ - : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \ - "r"(_num) \ - : "memory", "cc", "lr" \ - ); \ - _arg1; \ -}) - -/* startup code */ -asm(".section .text\n" - ".global _start\n" - "_start:\n" -#if defined(__THUMBEB__) || defined(__THUMBEL__) - /* We enter here in 32-bit mode but if some previous functions were in - * 16-bit mode, the assembler cannot know, so we need to tell it we're in - * 32-bit now, then switch to 16-bit (is there a better way to do it than - * adding 1 by hand ?) and tell the asm we're now in 16-bit mode so that - * it generates correct instructions. Note that we do not support thumb1. - */ - ".code 32\n" - "add r0, pc, #1\n" - "bx r0\n" - ".code 16\n" -#endif - "pop {%r0}\n" // argc was in the stack - "mov %r1, %sp\n" // argv = sp - "add %r2, %r1, %r0, lsl #2\n" // envp = argv + 4*argc ... - "add %r2, %r2, $4\n" // ... + 4 - "and %r3, %r1, $-8\n" // AAPCS : sp must be 8-byte aligned in the - "mov %sp, %r3\n" // callee, an bl doesn't push (lr=pc) - "bl main\n" // main() returns the status code, we'll exit with it. - "movs r7, $1\n" // NR_exit == 1 - "svc $0x00\n" - ""); - -/* fcntl / open */ -#define O_RDONLY 0 -#define O_WRONLY 1 -#define O_RDWR 2 -#define O_CREAT 0x40 -#define O_EXCL 0x80 -#define O_NOCTTY 0x100 -#define O_TRUNC 0x200 -#define O_APPEND 0x400 -#define O_NONBLOCK 0x800 -#define O_DIRECTORY 0x4000 - -/* The struct returned by the stat() syscall, 32-bit only, the syscall returns - * exactly 56 bytes (stops before the unused array). In big endian, the format - * differs as devices are returned as short only. - */ -struct sys_stat_struct { -#if defined(__ARMEB__) - unsigned short st_dev; - unsigned short __pad1; -#else - unsigned long st_dev; -#endif - unsigned long st_ino; - unsigned short st_mode; - unsigned short st_nlink; - unsigned short st_uid; - unsigned short st_gid; -#if defined(__ARMEB__) - unsigned short st_rdev; - unsigned short __pad2; -#else - unsigned long st_rdev; -#endif - unsigned long st_size; - unsigned long st_blksize; - unsigned long st_blocks; - unsigned long st_atime; - unsigned long st_atime_nsec; - unsigned long st_mtime; - unsigned long st_mtime_nsec; - unsigned long st_ctime; - unsigned long st_ctime_nsec; - unsigned long __unused[2]; -}; - -#elif defined(__aarch64__) -/* Syscalls for AARCH64 : - * - registers are 64-bit - * - stack is 16-byte aligned - * - syscall number is passed in x8 - * - arguments are in x0, x1, x2, x3, x4, x5 - * - the system call is performed by calling svc 0 - * - syscall return comes in x0. - * - the arguments are cast to long and assigned into the target registers - * which are then simply passed as registers to the asm code, so that we - * don't have to experience issues with register constraints. - * - * On aarch64, select() is not implemented so we have to use pselect6(). - */ -#define __ARCH_WANT_SYS_PSELECT6 - -#define my_syscall0(num) \ -({ \ - register long _num asm("x8") = (num); \ - register long _arg1 asm("x0"); \ - \ - asm volatile ( \ - "svc #0\n" \ - : "=r"(_arg1) \ - : "r"(_num) \ - : "memory", "cc" \ - ); \ - _arg1; \ -}) - -#define my_syscall1(num, arg1) \ -({ \ - register long _num asm("x8") = (num); \ - register long _arg1 asm("x0") = (long)(arg1); \ - \ - asm volatile ( \ - "svc #0\n" \ - : "=r"(_arg1) \ - : "r"(_arg1), \ - "r"(_num) \ - : "memory", "cc" \ - ); \ - _arg1; \ -}) - -#define my_syscall2(num, arg1, arg2) \ -({ \ - register long _num asm("x8") = (num); \ - register long _arg1 asm("x0") = (long)(arg1); \ - register long _arg2 asm("x1") = (long)(arg2); \ - \ - asm volatile ( \ - "svc #0\n" \ - : "=r"(_arg1) \ - : "r"(_arg1), "r"(_arg2), \ - "r"(_num) \ - : "memory", "cc" \ - ); \ - _arg1; \ -}) - -#define my_syscall3(num, arg1, arg2, arg3) \ -({ \ - register long _num asm("x8") = (num); \ - register long _arg1 asm("x0") = (long)(arg1); \ - register long _arg2 asm("x1") = (long)(arg2); \ - register long _arg3 asm("x2") = (long)(arg3); \ - \ - asm volatile ( \ - "svc #0\n" \ - : "=r"(_arg1) \ - : "r"(_arg1), "r"(_arg2), "r"(_arg3), \ - "r"(_num) \ - : "memory", "cc" \ - ); \ - _arg1; \ -}) - -#define my_syscall4(num, arg1, arg2, arg3, arg4) \ -({ \ - register long _num asm("x8") = (num); \ - register long _arg1 asm("x0") = (long)(arg1); \ - register long _arg2 asm("x1") = (long)(arg2); \ - register long _arg3 asm("x2") = (long)(arg3); \ - register long _arg4 asm("x3") = (long)(arg4); \ - \ - asm volatile ( \ - "svc #0\n" \ - : "=r"(_arg1) \ - : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), \ - "r"(_num) \ - : "memory", "cc" \ - ); \ - _arg1; \ -}) - -#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \ -({ \ - register long _num asm("x8") = (num); \ - register long _arg1 asm("x0") = (long)(arg1); \ - register long _arg2 asm("x1") = (long)(arg2); \ - register long _arg3 asm("x2") = (long)(arg3); \ - register long _arg4 asm("x3") = (long)(arg4); \ - register long _arg5 asm("x4") = (long)(arg5); \ - \ - asm volatile ( \ - "svc #0\n" \ - : "=r" (_arg1) \ - : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \ - "r"(_num) \ - : "memory", "cc" \ - ); \ - _arg1; \ -}) - -#define my_syscall6(num, arg1, arg2, arg3, arg4, arg5, arg6) \ -({ \ - register long _num asm("x8") = (num); \ - register long _arg1 asm("x0") = (long)(arg1); \ - register long _arg2 asm("x1") = (long)(arg2); \ - register long _arg3 asm("x2") = (long)(arg3); \ - register long _arg4 asm("x3") = (long)(arg4); \ - register long _arg5 asm("x4") = (long)(arg5); \ - register long _arg6 asm("x5") = (long)(arg6); \ - \ - asm volatile ( \ - "svc #0\n" \ - : "=r" (_arg1) \ - : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \ - "r"(_arg6), "r"(_num) \ - : "memory", "cc" \ - ); \ - _arg1; \ -}) - -/* startup code */ -asm(".section .text\n" - ".global _start\n" - "_start:\n" - "ldr x0, [sp]\n" // argc (x0) was in the stack - "add x1, sp, 8\n" // argv (x1) = sp - "lsl x2, x0, 3\n" // envp (x2) = 8*argc ... - "add x2, x2, 8\n" // + 8 (skip null) - "add x2, x2, x1\n" // + argv - "and sp, x1, -16\n" // sp must be 16-byte aligned in the callee - "bl main\n" // main() returns the status code, we'll exit with it. - "mov x8, 93\n" // NR_exit == 93 - "svc #0\n" - ""); - -/* fcntl / open */ -#define O_RDONLY 0 -#define O_WRONLY 1 -#define O_RDWR 2 -#define O_CREAT 0x40 -#define O_EXCL 0x80 -#define O_NOCTTY 0x100 -#define O_TRUNC 0x200 -#define O_APPEND 0x400 -#define O_NONBLOCK 0x800 -#define O_DIRECTORY 0x4000 - -/* The struct returned by the newfstatat() syscall. Differs slightly from the - * x86_64's stat one by field ordering, so be careful. - */ -struct sys_stat_struct { - unsigned long st_dev; - unsigned long st_ino; - unsigned int st_mode; - unsigned int st_nlink; - unsigned int st_uid; - unsigned int st_gid; - - unsigned long st_rdev; - unsigned long __pad1; - long st_size; - int st_blksize; - int __pad2; - - long st_blocks; - long st_atime; - unsigned long st_atime_nsec; - long st_mtime; - - unsigned long st_mtime_nsec; - long st_ctime; - unsigned long st_ctime_nsec; - unsigned int __unused[2]; -}; - -#elif defined(__mips__) && defined(_ABIO32) -/* Syscalls for MIPS ABI O32 : - * - WARNING! there's always a delayed slot! - * - WARNING again, the syntax is different, registers take a '$' and numbers - * do not. - * - registers are 32-bit - * - stack is 8-byte aligned - * - syscall number is passed in v0 (starts at 0xfa0). - * - arguments are in a0, a1, a2, a3, then the stack. The caller needs to - * leave some room in the stack for the callee to save a0..a3 if needed. - * - Many registers are clobbered, in fact only a0..a2 and s0..s8 are - * preserved. See: https://www.linux-mips.org/wiki/Syscall as well as - * scall32-o32.S in the kernel sources. - * - the system call is performed by calling "syscall" - * - syscall return comes in v0, and register a3 needs to be checked to know - * if an error occurred, in which case errno is in v0. - * - the arguments are cast to long and assigned into the target registers - * which are then simply passed as registers to the asm code, so that we - * don't have to experience issues with register constraints. - */ - -#define my_syscall0(num) \ -({ \ - register long _num asm("v0") = (num); \ - register long _arg4 asm("a3"); \ - \ - asm volatile ( \ - "addiu $sp, $sp, -32\n" \ - "syscall\n" \ - "addiu $sp, $sp, 32\n" \ - : "=r"(_num), "=r"(_arg4) \ - : "r"(_num) \ - : "memory", "cc", "at", "v1", "hi", "lo", \ - "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9" \ - ); \ - _arg4 ? -_num : _num; \ -}) - -#define my_syscall1(num, arg1) \ -({ \ - register long _num asm("v0") = (num); \ - register long _arg1 asm("a0") = (long)(arg1); \ - register long _arg4 asm("a3"); \ - \ - asm volatile ( \ - "addiu $sp, $sp, -32\n" \ - "syscall\n" \ - "addiu $sp, $sp, 32\n" \ - : "=r"(_num), "=r"(_arg4) \ - : "0"(_num), \ - "r"(_arg1) \ - : "memory", "cc", "at", "v1", "hi", "lo", \ - "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9" \ - ); \ - _arg4 ? -_num : _num; \ -}) - -#define my_syscall2(num, arg1, arg2) \ -({ \ - register long _num asm("v0") = (num); \ - register long _arg1 asm("a0") = (long)(arg1); \ - register long _arg2 asm("a1") = (long)(arg2); \ - register long _arg4 asm("a3"); \ - \ - asm volatile ( \ - "addiu $sp, $sp, -32\n" \ - "syscall\n" \ - "addiu $sp, $sp, 32\n" \ - : "=r"(_num), "=r"(_arg4) \ - : "0"(_num), \ - "r"(_arg1), "r"(_arg2) \ - : "memory", "cc", "at", "v1", "hi", "lo", \ - "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9" \ - ); \ - _arg4 ? -_num : _num; \ -}) - -#define my_syscall3(num, arg1, arg2, arg3) \ -({ \ - register long _num asm("v0") = (num); \ - register long _arg1 asm("a0") = (long)(arg1); \ - register long _arg2 asm("a1") = (long)(arg2); \ - register long _arg3 asm("a2") = (long)(arg3); \ - register long _arg4 asm("a3"); \ - \ - asm volatile ( \ - "addiu $sp, $sp, -32\n" \ - "syscall\n" \ - "addiu $sp, $sp, 32\n" \ - : "=r"(_num), "=r"(_arg4) \ - : "0"(_num), \ - "r"(_arg1), "r"(_arg2), "r"(_arg3) \ - : "memory", "cc", "at", "v1", "hi", "lo", \ - "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9" \ - ); \ - _arg4 ? -_num : _num; \ -}) - -#define my_syscall4(num, arg1, arg2, arg3, arg4) \ -({ \ - register long _num asm("v0") = (num); \ - register long _arg1 asm("a0") = (long)(arg1); \ - register long _arg2 asm("a1") = (long)(arg2); \ - register long _arg3 asm("a2") = (long)(arg3); \ - register long _arg4 asm("a3") = (long)(arg4); \ - \ - asm volatile ( \ - "addiu $sp, $sp, -32\n" \ - "syscall\n" \ - "addiu $sp, $sp, 32\n" \ - : "=r" (_num), "=r"(_arg4) \ - : "0"(_num), \ - "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4) \ - : "memory", "cc", "at", "v1", "hi", "lo", \ - "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9" \ - ); \ - _arg4 ? -_num : _num; \ -}) - -#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \ -({ \ - register long _num asm("v0") = (num); \ - register long _arg1 asm("a0") = (long)(arg1); \ - register long _arg2 asm("a1") = (long)(arg2); \ - register long _arg3 asm("a2") = (long)(arg3); \ - register long _arg4 asm("a3") = (long)(arg4); \ - register long _arg5 = (long)(arg5); \ - \ - asm volatile ( \ - "addiu $sp, $sp, -32\n" \ - "sw %7, 16($sp)\n" \ - "syscall\n " \ - "addiu $sp, $sp, 32\n" \ - : "=r" (_num), "=r"(_arg4) \ - : "0"(_num), \ - "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5) \ - : "memory", "cc", "at", "v1", "hi", "lo", \ - "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9" \ - ); \ - _arg4 ? -_num : _num; \ -}) - -/* startup code, note that it's called __start on MIPS */ -asm(".section .text\n" - ".set nomips16\n" - ".global __start\n" - ".set noreorder\n" - ".option pic0\n" - ".ent __start\n" - "__start:\n" - "lw $a0,($sp)\n" // argc was in the stack - "addiu $a1, $sp, 4\n" // argv = sp + 4 - "sll $a2, $a0, 2\n" // a2 = argc * 4 - "add $a2, $a2, $a1\n" // envp = argv + 4*argc ... - "addiu $a2, $a2, 4\n" // ... + 4 - "li $t0, -8\n" - "and $sp, $sp, $t0\n" // sp must be 8-byte aligned - "addiu $sp,$sp,-16\n" // the callee expects to save a0..a3 there! - "jal main\n" // main() returns the status code, we'll exit with it. - "nop\n" // delayed slot - "move $a0, $v0\n" // retrieve 32-bit exit code from v0 - "li $v0, 4001\n" // NR_exit == 4001 - "syscall\n" - ".end __start\n" - ""); - -/* fcntl / open */ -#define O_RDONLY 0 -#define O_WRONLY 1 -#define O_RDWR 2 -#define O_APPEND 0x0008 -#define O_NONBLOCK 0x0080 -#define O_CREAT 0x0100 -#define O_TRUNC 0x0200 -#define O_EXCL 0x0400 -#define O_NOCTTY 0x0800 -#define O_DIRECTORY 0x10000 - -/* The struct returned by the stat() syscall. 88 bytes are returned by the - * syscall. - */ -struct sys_stat_struct { - unsigned int st_dev; - long st_pad1[3]; - unsigned long st_ino; - unsigned int st_mode; - unsigned int st_nlink; - unsigned int st_uid; - unsigned int st_gid; - unsigned int st_rdev; - long st_pad2[2]; - long st_size; - long st_pad3; - long st_atime; - long st_atime_nsec; - long st_mtime; - long st_mtime_nsec; - long st_ctime; - long st_ctime_nsec; - long st_blksize; - long st_blocks; - long st_pad4[14]; -}; - -#elif defined(__riscv) - -#if __riscv_xlen == 64 -#define PTRLOG "3" -#define SZREG "8" -#elif __riscv_xlen == 32 -#define PTRLOG "2" -#define SZREG "4" -#endif - -/* Syscalls for RISCV : - * - stack is 16-byte aligned - * - syscall number is passed in a7 - * - arguments are in a0, a1, a2, a3, a4, a5 - * - the system call is performed by calling ecall - * - syscall return comes in a0 - * - the arguments are cast to long and assigned into the target - * registers which are then simply passed as registers to the asm code, - * so that we don't have to experience issues with register constraints. - */ - -#define my_syscall0(num) \ -({ \ - register long _num asm("a7") = (num); \ - register long _arg1 asm("a0"); \ - \ - asm volatile ( \ - "ecall\n\t" \ - : "=r"(_arg1) \ - : "r"(_num) \ - : "memory", "cc" \ - ); \ - _arg1; \ -}) - -#define my_syscall1(num, arg1) \ -({ \ - register long _num asm("a7") = (num); \ - register long _arg1 asm("a0") = (long)(arg1); \ - \ - asm volatile ( \ - "ecall\n" \ - : "+r"(_arg1) \ - : "r"(_num) \ - : "memory", "cc" \ - ); \ - _arg1; \ -}) - -#define my_syscall2(num, arg1, arg2) \ -({ \ - register long _num asm("a7") = (num); \ - register long _arg1 asm("a0") = (long)(arg1); \ - register long _arg2 asm("a1") = (long)(arg2); \ - \ - asm volatile ( \ - "ecall\n" \ - : "+r"(_arg1) \ - : "r"(_arg2), \ - "r"(_num) \ - : "memory", "cc" \ - ); \ - _arg1; \ -}) - -#define my_syscall3(num, arg1, arg2, arg3) \ -({ \ - register long _num asm("a7") = (num); \ - register long _arg1 asm("a0") = (long)(arg1); \ - register long _arg2 asm("a1") = (long)(arg2); \ - register long _arg3 asm("a2") = (long)(arg3); \ - \ - asm volatile ( \ - "ecall\n\t" \ - : "+r"(_arg1) \ - : "r"(_arg2), "r"(_arg3), \ - "r"(_num) \ - : "memory", "cc" \ - ); \ - _arg1; \ -}) - -#define my_syscall4(num, arg1, arg2, arg3, arg4) \ -({ \ - register long _num asm("a7") = (num); \ - register long _arg1 asm("a0") = (long)(arg1); \ - register long _arg2 asm("a1") = (long)(arg2); \ - register long _arg3 asm("a2") = (long)(arg3); \ - register long _arg4 asm("a3") = (long)(arg4); \ - \ - asm volatile ( \ - "ecall\n" \ - : "+r"(_arg1) \ - : "r"(_arg2), "r"(_arg3), "r"(_arg4), \ - "r"(_num) \ - : "memory", "cc" \ - ); \ - _arg1; \ -}) - -#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \ -({ \ - register long _num asm("a7") = (num); \ - register long _arg1 asm("a0") = (long)(arg1); \ - register long _arg2 asm("a1") = (long)(arg2); \ - register long _arg3 asm("a2") = (long)(arg3); \ - register long _arg4 asm("a3") = (long)(arg4); \ - register long _arg5 asm("a4") = (long)(arg5); \ - \ - asm volatile ( \ - "ecall\n" \ - : "+r"(_arg1) \ - : "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \ - "r"(_num) \ - : "memory", "cc" \ - ); \ - _arg1; \ -}) - -#define my_syscall6(num, arg1, arg2, arg3, arg4, arg5, arg6) \ -({ \ - register long _num asm("a7") = (num); \ - register long _arg1 asm("a0") = (long)(arg1); \ - register long _arg2 asm("a1") = (long)(arg2); \ - register long _arg3 asm("a2") = (long)(arg3); \ - register long _arg4 asm("a3") = (long)(arg4); \ - register long _arg5 asm("a4") = (long)(arg5); \ - register long _arg6 asm("a5") = (long)(arg6); \ - \ - asm volatile ( \ - "ecall\n" \ - : "+r"(_arg1) \ - : "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), "r"(_arg6), \ - "r"(_num) \ - : "memory", "cc" \ - ); \ - _arg1; \ -}) - -/* startup code */ -asm(".section .text\n" - ".global _start\n" - "_start:\n" - ".option push\n" - ".option norelax\n" - "lla gp, __global_pointer$\n" - ".option pop\n" - "ld a0, 0(sp)\n" // argc (a0) was in the stack - "add a1, sp, "SZREG"\n" // argv (a1) = sp - "slli a2, a0, "PTRLOG"\n" // envp (a2) = SZREG*argc ... - "add a2, a2, "SZREG"\n" // + SZREG (skip null) - "add a2,a2,a1\n" // + argv - "andi sp,a1,-16\n" // sp must be 16-byte aligned - "call main\n" // main() returns the status code, we'll exit with it. - "li a7, 93\n" // NR_exit == 93 - "ecall\n" - ""); - -/* fcntl / open */ -#define O_RDONLY 0 -#define O_WRONLY 1 -#define O_RDWR 2 -#define O_CREAT 0x100 -#define O_EXCL 0x200 -#define O_NOCTTY 0x400 -#define O_TRUNC 0x1000 -#define O_APPEND 0x2000 -#define O_NONBLOCK 0x4000 -#define O_DIRECTORY 0x200000 - -struct sys_stat_struct { - unsigned long st_dev; /* Device. */ - unsigned long st_ino; /* File serial number. */ - unsigned int st_mode; /* File mode. */ - unsigned int st_nlink; /* Link count. */ - unsigned int st_uid; /* User ID of the file's owner. */ - unsigned int st_gid; /* Group ID of the file's group. */ - unsigned long st_rdev; /* Device number, if device. */ - unsigned long __pad1; - long st_size; /* Size of file, in bytes. */ - int st_blksize; /* Optimal block size for I/O. */ - int __pad2; - long st_blocks; /* Number 512-byte blocks allocated. */ - long st_atime; /* Time of last access. */ - unsigned long st_atime_nsec; - long st_mtime; /* Time of last modification. */ - unsigned long st_mtime_nsec; - long st_ctime; /* Time of last status change. */ - unsigned long st_ctime_nsec; - unsigned int __unused4; - unsigned int __unused5; -}; - -#endif - - -/* Below are the C functions used to declare the raw syscalls. They try to be - * architecture-agnostic, and return either a success or -errno. Declaring them - * static will lead to them being inlined in most cases, but it's still possible - * to reference them by a pointer if needed. - */ -static __attribute__((unused)) -void *sys_brk(void *addr) -{ - return (void *)my_syscall1(__NR_brk, addr); -} - -static __attribute__((noreturn,unused)) -void sys_exit(int status) -{ - my_syscall1(__NR_exit, status & 255); - while(1); // shut the "noreturn" warnings. -} - -static __attribute__((unused)) -int sys_chdir(const char *path) -{ - return my_syscall1(__NR_chdir, path); -} - -static __attribute__((unused)) -int sys_chmod(const char *path, mode_t mode) -{ -#ifdef __NR_fchmodat - return my_syscall4(__NR_fchmodat, AT_FDCWD, path, mode, 0); -#elif defined(__NR_chmod) - return my_syscall2(__NR_chmod, path, mode); -#else -#error Neither __NR_fchmodat nor __NR_chmod defined, cannot implement sys_chmod() -#endif -} - -static __attribute__((unused)) -int sys_chown(const char *path, uid_t owner, gid_t group) -{ -#ifdef __NR_fchownat - return my_syscall5(__NR_fchownat, AT_FDCWD, path, owner, group, 0); -#elif defined(__NR_chown) - return my_syscall3(__NR_chown, path, owner, group); -#else -#error Neither __NR_fchownat nor __NR_chown defined, cannot implement sys_chown() -#endif -} - -static __attribute__((unused)) -int sys_chroot(const char *path) -{ - return my_syscall1(__NR_chroot, path); -} - -static __attribute__((unused)) -int sys_close(int fd) -{ - return my_syscall1(__NR_close, fd); -} - -static __attribute__((unused)) -int sys_dup(int fd) -{ - return my_syscall1(__NR_dup, fd); -} - -#ifdef __NR_dup3 -static __attribute__((unused)) -int sys_dup3(int old, int new, int flags) -{ - return my_syscall3(__NR_dup3, old, new, flags); -} -#endif - -static __attribute__((unused)) -int sys_dup2(int old, int new) -{ -#ifdef __NR_dup3 - return my_syscall3(__NR_dup3, old, new, 0); -#elif defined(__NR_dup2) - return my_syscall2(__NR_dup2, old, new); -#else -#error Neither __NR_dup3 nor __NR_dup2 defined, cannot implement sys_dup2() -#endif -} - -static __attribute__((unused)) -int sys_execve(const char *filename, char *const argv[], char *const envp[]) -{ - return my_syscall3(__NR_execve, filename, argv, envp); -} - -static __attribute__((unused)) -pid_t sys_fork(void) -{ -#ifdef __NR_clone - /* note: some archs only have clone() and not fork(). Different archs - * have a different API, but most archs have the flags on first arg and - * will not use the rest with no other flag. - */ - return my_syscall5(__NR_clone, SIGCHLD, 0, 0, 0, 0); -#elif defined(__NR_fork) - return my_syscall0(__NR_fork); -#else -#error Neither __NR_clone nor __NR_fork defined, cannot implement sys_fork() -#endif -} - -static __attribute__((unused)) -int sys_fsync(int fd) -{ - return my_syscall1(__NR_fsync, fd); -} - -static __attribute__((unused)) -int sys_getdents64(int fd, struct linux_dirent64 *dirp, int count) -{ - return my_syscall3(__NR_getdents64, fd, dirp, count); -} - -static __attribute__((unused)) -pid_t sys_getpgid(pid_t pid) -{ - return my_syscall1(__NR_getpgid, pid); -} - -static __attribute__((unused)) -pid_t sys_getpgrp(void) -{ - return sys_getpgid(0); -} - -static __attribute__((unused)) -pid_t sys_getpid(void) -{ - return my_syscall0(__NR_getpid); -} - -static __attribute__((unused)) -pid_t sys_gettid(void) -{ - return my_syscall0(__NR_gettid); -} - -static __attribute__((unused)) -int sys_gettimeofday(struct timeval *tv, struct timezone *tz) -{ - return my_syscall2(__NR_gettimeofday, tv, tz); -} - -static __attribute__((unused)) -int sys_ioctl(int fd, unsigned long req, void *value) -{ - return my_syscall3(__NR_ioctl, fd, req, value); -} - -static __attribute__((unused)) -int sys_kill(pid_t pid, int signal) -{ - return my_syscall2(__NR_kill, pid, signal); -} - -static __attribute__((unused)) -int sys_link(const char *old, const char *new) -{ -#ifdef __NR_linkat - return my_syscall5(__NR_linkat, AT_FDCWD, old, AT_FDCWD, new, 0); -#elif defined(__NR_link) - return my_syscall2(__NR_link, old, new); -#else -#error Neither __NR_linkat nor __NR_link defined, cannot implement sys_link() -#endif -} - -static __attribute__((unused)) -off_t sys_lseek(int fd, off_t offset, int whence) -{ - return my_syscall3(__NR_lseek, fd, offset, whence); -} - -static __attribute__((unused)) -int sys_mkdir(const char *path, mode_t mode) -{ -#ifdef __NR_mkdirat - return my_syscall3(__NR_mkdirat, AT_FDCWD, path, mode); -#elif defined(__NR_mkdir) - return my_syscall2(__NR_mkdir, path, mode); -#else -#error Neither __NR_mkdirat nor __NR_mkdir defined, cannot implement sys_mkdir() -#endif -} - -static __attribute__((unused)) -long sys_mknod(const char *path, mode_t mode, dev_t dev) -{ -#ifdef __NR_mknodat - return my_syscall4(__NR_mknodat, AT_FDCWD, path, mode, dev); -#elif defined(__NR_mknod) - return my_syscall3(__NR_mknod, path, mode, dev); -#else -#error Neither __NR_mknodat nor __NR_mknod defined, cannot implement sys_mknod() -#endif -} - -static __attribute__((unused)) -int sys_mount(const char *src, const char *tgt, const char *fst, - unsigned long flags, const void *data) -{ - return my_syscall5(__NR_mount, src, tgt, fst, flags, data); -} - -static __attribute__((unused)) -int sys_open(const char *path, int flags, mode_t mode) -{ -#ifdef __NR_openat - return my_syscall4(__NR_openat, AT_FDCWD, path, flags, mode); -#elif defined(__NR_open) - return my_syscall3(__NR_open, path, flags, mode); -#else -#error Neither __NR_openat nor __NR_open defined, cannot implement sys_open() -#endif -} - -static __attribute__((unused)) -int sys_pivot_root(const char *new, const char *old) -{ - return my_syscall2(__NR_pivot_root, new, old); -} - -static __attribute__((unused)) -int sys_poll(struct pollfd *fds, int nfds, int timeout) -{ -#if defined(__NR_ppoll) - struct timespec t; - - if (timeout >= 0) { - t.tv_sec = timeout / 1000; - t.tv_nsec = (timeout % 1000) * 1000000; - } - return my_syscall4(__NR_ppoll, fds, nfds, (timeout >= 0) ? &t : NULL, NULL); -#elif defined(__NR_poll) - return my_syscall3(__NR_poll, fds, nfds, timeout); -#else -#error Neither __NR_ppoll nor __NR_poll defined, cannot implement sys_poll() -#endif -} - -static __attribute__((unused)) -ssize_t sys_read(int fd, void *buf, size_t count) -{ - return my_syscall3(__NR_read, fd, buf, count); -} - -static __attribute__((unused)) -ssize_t sys_reboot(int magic1, int magic2, int cmd, void *arg) -{ - return my_syscall4(__NR_reboot, magic1, magic2, cmd, arg); -} - -static __attribute__((unused)) -int sys_sched_yield(void) -{ - return my_syscall0(__NR_sched_yield); -} - -static __attribute__((unused)) -int sys_select(int nfds, fd_set *rfds, fd_set *wfds, fd_set *efds, struct timeval *timeout) -{ -#if defined(__ARCH_WANT_SYS_OLD_SELECT) && !defined(__NR__newselect) - struct sel_arg_struct { - unsigned long n; - fd_set *r, *w, *e; - struct timeval *t; - } arg = { .n = nfds, .r = rfds, .w = wfds, .e = efds, .t = timeout }; - return my_syscall1(__NR_select, &arg); -#elif defined(__ARCH_WANT_SYS_PSELECT6) && defined(__NR_pselect6) - struct timespec t; - - if (timeout) { - t.tv_sec = timeout->tv_sec; - t.tv_nsec = timeout->tv_usec * 1000; - } - return my_syscall6(__NR_pselect6, nfds, rfds, wfds, efds, timeout ? &t : NULL, NULL); -#elif defined(__NR__newselect) || defined(__NR_select) -#ifndef __NR__newselect -#define __NR__newselect __NR_select -#endif - return my_syscall5(__NR__newselect, nfds, rfds, wfds, efds, timeout); -#else -#error None of __NR_select, __NR_pselect6, nor __NR__newselect defined, cannot implement sys_select() -#endif -} - -static __attribute__((unused)) -int sys_setpgid(pid_t pid, pid_t pgid) -{ - return my_syscall2(__NR_setpgid, pid, pgid); -} - -static __attribute__((unused)) -pid_t sys_setsid(void) -{ - return my_syscall0(__NR_setsid); -} - -static __attribute__((unused)) -int sys_stat(const char *path, struct stat *buf) -{ - struct sys_stat_struct stat; - long ret; - -#ifdef __NR_newfstatat - /* only solution for arm64 */ - ret = my_syscall4(__NR_newfstatat, AT_FDCWD, path, &stat, 0); -#elif defined(__NR_stat) - ret = my_syscall2(__NR_stat, path, &stat); -#else -#error Neither __NR_newfstatat nor __NR_stat defined, cannot implement sys_stat() -#endif - buf->st_dev = stat.st_dev; - buf->st_ino = stat.st_ino; - buf->st_mode = stat.st_mode; - buf->st_nlink = stat.st_nlink; - buf->st_uid = stat.st_uid; - buf->st_gid = stat.st_gid; - buf->st_rdev = stat.st_rdev; - buf->st_size = stat.st_size; - buf->st_blksize = stat.st_blksize; - buf->st_blocks = stat.st_blocks; - buf->st_atime = stat.st_atime; - buf->st_mtime = stat.st_mtime; - buf->st_ctime = stat.st_ctime; - return ret; -} - - -static __attribute__((unused)) -int sys_symlink(const char *old, const char *new) -{ -#ifdef __NR_symlinkat - return my_syscall3(__NR_symlinkat, old, AT_FDCWD, new); -#elif defined(__NR_symlink) - return my_syscall2(__NR_symlink, old, new); -#else -#error Neither __NR_symlinkat nor __NR_symlink defined, cannot implement sys_symlink() -#endif -} - -static __attribute__((unused)) -mode_t sys_umask(mode_t mode) -{ - return my_syscall1(__NR_umask, mode); -} - -static __attribute__((unused)) -int sys_umount2(const char *path, int flags) -{ - return my_syscall2(__NR_umount2, path, flags); -} - -static __attribute__((unused)) -int sys_unlink(const char *path) -{ -#ifdef __NR_unlinkat - return my_syscall3(__NR_unlinkat, AT_FDCWD, path, 0); -#elif defined(__NR_unlink) - return my_syscall1(__NR_unlink, path); -#else -#error Neither __NR_unlinkat nor __NR_unlink defined, cannot implement sys_unlink() -#endif -} - -static __attribute__((unused)) -pid_t sys_wait4(pid_t pid, int *status, int options, struct rusage *rusage) -{ - return my_syscall4(__NR_wait4, pid, status, options, rusage); -} - -static __attribute__((unused)) -pid_t sys_waitpid(pid_t pid, int *status, int options) -{ - return sys_wait4(pid, status, options, 0); -} - -static __attribute__((unused)) -pid_t sys_wait(int *status) -{ - return sys_waitpid(-1, status, 0); -} - -static __attribute__((unused)) -ssize_t sys_write(int fd, const void *buf, size_t count) -{ - return my_syscall3(__NR_write, fd, buf, count); -} - - -/* Below are the libc-compatible syscalls which return x or -1 and set errno. - * They rely on the functions above. Similarly they're marked static so that it - * is possible to assign pointers to them if needed. - */ - -static __attribute__((unused)) -int brk(void *addr) -{ - void *ret = sys_brk(addr); - - if (!ret) { - SET_ERRNO(ENOMEM); - return -1; - } - return 0; -} - -static __attribute__((noreturn,unused)) -void exit(int status) -{ - sys_exit(status); -} - -static __attribute__((unused)) -int chdir(const char *path) -{ - int ret = sys_chdir(path); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -int chmod(const char *path, mode_t mode) -{ - int ret = sys_chmod(path, mode); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -int chown(const char *path, uid_t owner, gid_t group) -{ - int ret = sys_chown(path, owner, group); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -int chroot(const char *path) -{ - int ret = sys_chroot(path); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -int close(int fd) -{ - int ret = sys_close(fd); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -int dup(int fd) -{ - int ret = sys_dup(fd); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -int dup2(int old, int new) -{ - int ret = sys_dup2(old, new); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -#ifdef __NR_dup3 -static __attribute__((unused)) -int dup3(int old, int new, int flags) -{ - int ret = sys_dup3(old, new, flags); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} -#endif - -static __attribute__((unused)) -int execve(const char *filename, char *const argv[], char *const envp[]) -{ - int ret = sys_execve(filename, argv, envp); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -pid_t fork(void) -{ - pid_t ret = sys_fork(); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -int fsync(int fd) -{ - int ret = sys_fsync(fd); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -int getdents64(int fd, struct linux_dirent64 *dirp, int count) -{ - int ret = sys_getdents64(fd, dirp, count); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -pid_t getpgid(pid_t pid) -{ - pid_t ret = sys_getpgid(pid); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -pid_t getpgrp(void) -{ - pid_t ret = sys_getpgrp(); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -pid_t getpid(void) -{ - pid_t ret = sys_getpid(); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -pid_t gettid(void) -{ - pid_t ret = sys_gettid(); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -int gettimeofday(struct timeval *tv, struct timezone *tz) -{ - int ret = sys_gettimeofday(tv, tz); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -int ioctl(int fd, unsigned long req, void *value) -{ - int ret = sys_ioctl(fd, req, value); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -int kill(pid_t pid, int signal) -{ - int ret = sys_kill(pid, signal); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -int link(const char *old, const char *new) -{ - int ret = sys_link(old, new); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -off_t lseek(int fd, off_t offset, int whence) -{ - off_t ret = sys_lseek(fd, offset, whence); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -int mkdir(const char *path, mode_t mode) -{ - int ret = sys_mkdir(path, mode); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -int mknod(const char *path, mode_t mode, dev_t dev) -{ - int ret = sys_mknod(path, mode, dev); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -int mount(const char *src, const char *tgt, - const char *fst, unsigned long flags, - const void *data) -{ - int ret = sys_mount(src, tgt, fst, flags, data); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -int open(const char *path, int flags, mode_t mode) -{ - int ret = sys_open(path, flags, mode); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -int pivot_root(const char *new, const char *old) -{ - int ret = sys_pivot_root(new, old); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -int poll(struct pollfd *fds, int nfds, int timeout) -{ - int ret = sys_poll(fds, nfds, timeout); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -ssize_t read(int fd, void *buf, size_t count) -{ - ssize_t ret = sys_read(fd, buf, count); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -int reboot(int cmd) -{ - int ret = sys_reboot(LINUX_REBOOT_MAGIC1, LINUX_REBOOT_MAGIC2, cmd, 0); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -void *sbrk(intptr_t inc) -{ - void *ret; - - /* first call to find current end */ - if ((ret = sys_brk(0)) && (sys_brk(ret + inc) == ret + inc)) - return ret + inc; - - SET_ERRNO(ENOMEM); - return (void *)-1; -} - -static __attribute__((unused)) -int sched_yield(void) -{ - int ret = sys_sched_yield(); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -int select(int nfds, fd_set *rfds, fd_set *wfds, fd_set *efds, struct timeval *timeout) -{ - int ret = sys_select(nfds, rfds, wfds, efds, timeout); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -int setpgid(pid_t pid, pid_t pgid) -{ - int ret = sys_setpgid(pid, pgid); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -pid_t setsid(void) -{ - pid_t ret = sys_setsid(); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -unsigned int sleep(unsigned int seconds) -{ - struct timeval my_timeval = { seconds, 0 }; - - if (sys_select(0, 0, 0, 0, &my_timeval) < 0) - return my_timeval.tv_sec + !!my_timeval.tv_usec; - else - return 0; -} - -static __attribute__((unused)) -int msleep(unsigned int msecs) -{ - struct timeval my_timeval = { msecs / 1000, (msecs % 1000) * 1000 }; - - if (sys_select(0, 0, 0, 0, &my_timeval) < 0) - return (my_timeval.tv_sec * 1000) + - (my_timeval.tv_usec / 1000) + - !!(my_timeval.tv_usec % 1000); - else - return 0; -} - -static __attribute__((unused)) -int stat(const char *path, struct stat *buf) -{ - int ret = sys_stat(path, buf); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -int symlink(const char *old, const char *new) -{ - int ret = sys_symlink(old, new); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -int tcsetpgrp(int fd, pid_t pid) -{ - return ioctl(fd, TIOCSPGRP, &pid); -} - -static __attribute__((unused)) -mode_t umask(mode_t mode) -{ - return sys_umask(mode); -} - -static __attribute__((unused)) -int umount2(const char *path, int flags) -{ - int ret = sys_umount2(path, flags); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -int unlink(const char *path) -{ - int ret = sys_unlink(path); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -pid_t wait4(pid_t pid, int *status, int options, struct rusage *rusage) -{ - pid_t ret = sys_wait4(pid, status, options, rusage); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -pid_t waitpid(pid_t pid, int *status, int options) -{ - pid_t ret = sys_waitpid(pid, status, options); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -pid_t wait(int *status) -{ - pid_t ret = sys_wait(status); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -ssize_t write(int fd, const void *buf, size_t count) -{ - ssize_t ret = sys_write(fd, buf, count); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -/* some size-optimized reimplementations of a few common str* and mem* - * functions. They're marked static, except memcpy() and raise() which are used - * by libgcc on ARM, so they are marked weak instead in order not to cause an - * error when building a program made of multiple files (not recommended). - */ - -static __attribute__((unused)) -void *memmove(void *dst, const void *src, size_t len) -{ - ssize_t pos = (dst <= src) ? -1 : (long)len; - void *ret = dst; - - while (len--) { - pos += (dst <= src) ? 1 : -1; - ((char *)dst)[pos] = ((char *)src)[pos]; - } - return ret; -} - -static __attribute__((unused)) -void *memset(void *dst, int b, size_t len) -{ - char *p = dst; - - while (len--) - *(p++) = b; - return dst; -} - -static __attribute__((unused)) -int memcmp(const void *s1, const void *s2, size_t n) -{ - size_t ofs = 0; - char c1 = 0; - - while (ofs < n && !(c1 = ((char *)s1)[ofs] - ((char *)s2)[ofs])) { - ofs++; - } - return c1; -} - -static __attribute__((unused)) -char *strcpy(char *dst, const char *src) -{ - char *ret = dst; - - while ((*dst++ = *src++)); - return ret; -} - -static __attribute__((unused)) -char *strchr(const char *s, int c) -{ - while (*s) { - if (*s == (char)c) - return (char *)s; - s++; - } - return NULL; -} - -static __attribute__((unused)) -char *strrchr(const char *s, int c) -{ - const char *ret = NULL; - - while (*s) { - if (*s == (char)c) - ret = s; - s++; - } - return (char *)ret; -} - -static __attribute__((unused)) -size_t nolibc_strlen(const char *str) -{ - size_t len; - - for (len = 0; str[len]; len++); - return len; -} - -#define strlen(str) ({ \ - __builtin_constant_p((str)) ? \ - __builtin_strlen((str)) : \ - nolibc_strlen((str)); \ -}) - -static __attribute__((unused)) -int isdigit(int c) -{ - return (unsigned int)(c - '0') <= 9; -} - -static __attribute__((unused)) -long atol(const char *s) -{ - unsigned long ret = 0; - unsigned long d; - int neg = 0; - - if (*s == '-') { - neg = 1; - s++; - } - - while (1) { - d = (*s++) - '0'; - if (d > 9) - break; - ret *= 10; - ret += d; - } - - return neg ? -ret : ret; -} - -static __attribute__((unused)) -int atoi(const char *s) -{ - return atol(s); -} - -static __attribute__((unused)) -const char *ltoa(long in) -{ - /* large enough for -9223372036854775808 */ - static char buffer[21]; - char *pos = buffer + sizeof(buffer) - 1; - int neg = in < 0; - unsigned long n = neg ? -in : in; - - *pos-- = '\0'; - do { - *pos-- = '0' + n % 10; - n /= 10; - if (pos < buffer) - return pos + 1; - } while (n); - - if (neg) - *pos-- = '-'; - return pos + 1; -} - -__attribute__((weak,unused)) -void *memcpy(void *dst, const void *src, size_t len) -{ - return memmove(dst, src, len); -} - -/* needed by libgcc for divide by zero */ -__attribute__((weak,unused)) -int raise(int signal) -{ - return kill(getpid(), signal); -} - -/* Here come a few helper functions */ - -static __attribute__((unused)) -void FD_ZERO(fd_set *set) -{ - memset(set, 0, sizeof(*set)); -} - -static __attribute__((unused)) -void FD_SET(int fd, fd_set *set) -{ - if (fd < 0 || fd >= FD_SETSIZE) - return; - set->fd32[fd / 32] |= 1 << (fd & 31); -} - -/* WARNING, it only deals with the 4096 first majors and 256 first minors */ -static __attribute__((unused)) -dev_t makedev(unsigned int major, unsigned int minor) -{ - return ((major & 0xfff) << 8) | (minor & 0xff); -} +#endif /* _NOLIBC_H */ diff --git a/tools/include/nolibc/signal.h b/tools/include/nolibc/signal.h new file mode 100644 index 000000000000..ef47e71e2be3 --- /dev/null +++ b/tools/include/nolibc/signal.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* + * signal function definitions for NOLIBC + * Copyright (C) 2017-2022 Willy Tarreau <w@1wt.eu> + */ + +#ifndef _NOLIBC_SIGNAL_H +#define _NOLIBC_SIGNAL_H + +#include "std.h" +#include "arch.h" +#include "types.h" +#include "sys.h" + +/* This one is not marked static as it's needed by libgcc for divide by zero */ +__attribute__((weak,unused,section(".text.nolibc_raise"))) +int raise(int signal) +{ + return sys_kill(sys_getpid(), signal); +} + +#endif /* _NOLIBC_SIGNAL_H */ diff --git a/tools/include/nolibc/std.h b/tools/include/nolibc/std.h new file mode 100644 index 000000000000..1747ae125392 --- /dev/null +++ b/tools/include/nolibc/std.h @@ -0,0 +1,49 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* + * Standard definitions and types for NOLIBC + * Copyright (C) 2017-2021 Willy Tarreau <w@1wt.eu> + */ + +#ifndef _NOLIBC_STD_H +#define _NOLIBC_STD_H + +/* Declare a few quite common macros and types that usually are in stdlib.h, + * stdint.h, ctype.h, unistd.h and a few other common locations. Please place + * integer type definitions and generic macros here, but avoid OS-specific and + * syscall-specific stuff, as this file is expected to be included very early. + */ + +/* note: may already be defined */ +#ifndef NULL +#define NULL ((void *)0) +#endif + +/* stdint types */ +typedef unsigned char uint8_t; +typedef signed char int8_t; +typedef unsigned short uint16_t; +typedef signed short int16_t; +typedef unsigned int uint32_t; +typedef signed int int32_t; +typedef unsigned long long uint64_t; +typedef signed long long int64_t; +typedef unsigned long size_t; +typedef signed long ssize_t; +typedef unsigned long uintptr_t; +typedef signed long intptr_t; +typedef signed long ptrdiff_t; + +/* those are commonly provided by sys/types.h */ +typedef unsigned int dev_t; +typedef unsigned long ino_t; +typedef unsigned int mode_t; +typedef signed int pid_t; +typedef unsigned int uid_t; +typedef unsigned int gid_t; +typedef unsigned long nlink_t; +typedef signed long off_t; +typedef signed long blksize_t; +typedef signed long blkcnt_t; +typedef signed long time_t; + +#endif /* _NOLIBC_STD_H */ diff --git a/tools/include/nolibc/stdio.h b/tools/include/nolibc/stdio.h new file mode 100644 index 000000000000..15dedf8d0902 --- /dev/null +++ b/tools/include/nolibc/stdio.h @@ -0,0 +1,306 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* + * minimal stdio function definitions for NOLIBC + * Copyright (C) 2017-2021 Willy Tarreau <w@1wt.eu> + */ + +#ifndef _NOLIBC_STDIO_H +#define _NOLIBC_STDIO_H + +#include <stdarg.h> + +#include "std.h" +#include "arch.h" +#include "errno.h" +#include "types.h" +#include "sys.h" +#include "stdlib.h" +#include "string.h" + +#ifndef EOF +#define EOF (-1) +#endif + +/* just define FILE as a non-empty type */ +typedef struct FILE { + char dummy[1]; +} FILE; + +/* We define the 3 common stdio files as constant invalid pointers that + * are easily recognized. + */ +static __attribute__((unused)) FILE* const stdin = (FILE*)-3; +static __attribute__((unused)) FILE* const stdout = (FILE*)-2; +static __attribute__((unused)) FILE* const stderr = (FILE*)-1; + +/* getc(), fgetc(), getchar() */ + +#define getc(stream) fgetc(stream) + +static __attribute__((unused)) +int fgetc(FILE* stream) +{ + unsigned char ch; + int fd; + + if (stream < stdin || stream > stderr) + return EOF; + + fd = 3 + (long)stream; + + if (read(fd, &ch, 1) <= 0) + return EOF; + return ch; +} + +static __attribute__((unused)) +int getchar(void) +{ + return fgetc(stdin); +} + + +/* putc(), fputc(), putchar() */ + +#define putc(c, stream) fputc(c, stream) + +static __attribute__((unused)) +int fputc(int c, FILE* stream) +{ + unsigned char ch = c; + int fd; + + if (stream < stdin || stream > stderr) + return EOF; + + fd = 3 + (long)stream; + + if (write(fd, &ch, 1) <= 0) + return EOF; + return ch; +} + +static __attribute__((unused)) +int putchar(int c) +{ + return fputc(c, stdout); +} + + +/* fwrite(), puts(), fputs(). Note that puts() emits '\n' but not fputs(). */ + +/* internal fwrite()-like function which only takes a size and returns 0 on + * success or EOF on error. It automatically retries on short writes. + */ +static __attribute__((unused)) +int _fwrite(const void *buf, size_t size, FILE *stream) +{ + ssize_t ret; + int fd; + + if (stream < stdin || stream > stderr) + return EOF; + + fd = 3 + (long)stream; + + while (size) { + ret = write(fd, buf, size); + if (ret <= 0) + return EOF; + size -= ret; + buf += ret; + } + return 0; +} + +static __attribute__((unused)) +size_t fwrite(const void *s, size_t size, size_t nmemb, FILE *stream) +{ + size_t written; + + for (written = 0; written < nmemb; written++) { + if (_fwrite(s, size, stream) != 0) + break; + s += size; + } + return written; +} + +static __attribute__((unused)) +int fputs(const char *s, FILE *stream) +{ + return _fwrite(s, strlen(s), stream); +} + +static __attribute__((unused)) +int puts(const char *s) +{ + if (fputs(s, stdout) == EOF) + return EOF; + return putchar('\n'); +} + + +/* fgets() */ +static __attribute__((unused)) +char *fgets(char *s, int size, FILE *stream) +{ + int ofs; + int c; + + for (ofs = 0; ofs + 1 < size;) { + c = fgetc(stream); + if (c == EOF) + break; + s[ofs++] = c; + if (c == '\n') + break; + } + if (ofs < size) + s[ofs] = 0; + return ofs ? s : NULL; +} + + +/* minimal vfprintf(). It supports the following formats: + * - %[l*]{d,u,c,x,p} + * - %s + * - unknown modifiers are ignored. + */ +static __attribute__((unused)) +int vfprintf(FILE *stream, const char *fmt, va_list args) +{ + char escape, lpref, c; + unsigned long long v; + unsigned int written; + size_t len, ofs; + char tmpbuf[21]; + const char *outstr; + + written = ofs = escape = lpref = 0; + while (1) { + c = fmt[ofs++]; + + if (escape) { + /* we're in an escape sequence, ofs == 1 */ + escape = 0; + if (c == 'c' || c == 'd' || c == 'u' || c == 'x' || c == 'p') { + char *out = tmpbuf; + + if (c == 'p') + v = va_arg(args, unsigned long); + else if (lpref) { + if (lpref > 1) + v = va_arg(args, unsigned long long); + else + v = va_arg(args, unsigned long); + } else + v = va_arg(args, unsigned int); + + if (c == 'd') { + /* sign-extend the value */ + if (lpref == 0) + v = (long long)(int)v; + else if (lpref == 1) + v = (long long)(long)v; + } + + switch (c) { + case 'c': + out[0] = v; + out[1] = 0; + break; + case 'd': + i64toa_r(v, out); + break; + case 'u': + u64toa_r(v, out); + break; + case 'p': + *(out++) = '0'; + *(out++) = 'x'; + /* fall through */ + default: /* 'x' and 'p' above */ + u64toh_r(v, out); + break; + } + outstr = tmpbuf; + } + else if (c == 's') { + outstr = va_arg(args, char *); + if (!outstr) + outstr="(null)"; + } + else if (c == '%') { + /* queue it verbatim */ + continue; + } + else { + /* modifiers or final 0 */ + if (c == 'l') { + /* long format prefix, maintain the escape */ + lpref++; + } + escape = 1; + goto do_escape; + } + len = strlen(outstr); + goto flush_str; + } + + /* not an escape sequence */ + if (c == 0 || c == '%') { + /* flush pending data on escape or end */ + escape = 1; + lpref = 0; + outstr = fmt; + len = ofs - 1; + flush_str: + if (_fwrite(outstr, len, stream) != 0) + break; + + written += len; + do_escape: + if (c == 0) + break; + fmt += ofs; + ofs = 0; + continue; + } + + /* literal char, just queue it */ + } + return written; +} + +static __attribute__((unused)) +int fprintf(FILE *stream, const char *fmt, ...) +{ + va_list args; + int ret; + + va_start(args, fmt); + ret = vfprintf(stream, fmt, args); + va_end(args); + return ret; +} + +static __attribute__((unused)) +int printf(const char *fmt, ...) +{ + va_list args; + int ret; + + va_start(args, fmt); + ret = vfprintf(stdout, fmt, args); + va_end(args); + return ret; +} + +static __attribute__((unused)) +void perror(const char *msg) +{ + fprintf(stderr, "%s%serrno=%d\n", (msg && *msg) ? msg : "", (msg && *msg) ? ": " : "", errno); +} + +#endif /* _NOLIBC_STDIO_H */ diff --git a/tools/include/nolibc/stdlib.h b/tools/include/nolibc/stdlib.h new file mode 100644 index 000000000000..8fd32eaf8037 --- /dev/null +++ b/tools/include/nolibc/stdlib.h @@ -0,0 +1,423 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* + * stdlib function definitions for NOLIBC + * Copyright (C) 2017-2021 Willy Tarreau <w@1wt.eu> + */ + +#ifndef _NOLIBC_STDLIB_H +#define _NOLIBC_STDLIB_H + +#include "std.h" +#include "arch.h" +#include "types.h" +#include "sys.h" +#include "string.h" + +struct nolibc_heap { + size_t len; + char user_p[] __attribute__((__aligned__)); +}; + +/* Buffer used to store int-to-ASCII conversions. Will only be implemented if + * any of the related functions is implemented. The area is large enough to + * store "18446744073709551615" or "-9223372036854775808" and the final zero. + */ +static __attribute__((unused)) char itoa_buffer[21]; + +/* + * As much as possible, please keep functions alphabetically sorted. + */ + +/* must be exported, as it's used by libgcc for various divide functions */ +__attribute__((weak,unused,noreturn,section(".text.nolibc_abort"))) +void abort(void) +{ + sys_kill(sys_getpid(), SIGABRT); + for (;;); +} + +static __attribute__((unused)) +long atol(const char *s) +{ + unsigned long ret = 0; + unsigned long d; + int neg = 0; + + if (*s == '-') { + neg = 1; + s++; + } + + while (1) { + d = (*s++) - '0'; + if (d > 9) + break; + ret *= 10; + ret += d; + } + + return neg ? -ret : ret; +} + +static __attribute__((unused)) +int atoi(const char *s) +{ + return atol(s); +} + +static __attribute__((unused)) +void free(void *ptr) +{ + struct nolibc_heap *heap; + + if (!ptr) + return; + + heap = container_of(ptr, struct nolibc_heap, user_p); + munmap(heap, heap->len); +} + +/* getenv() tries to find the environment variable named <name> in the + * environment array pointed to by global variable "environ" which must be + * declared as a char **, and must be terminated by a NULL (it is recommended + * to set this variable to the "envp" argument of main()). If the requested + * environment variable exists its value is returned otherwise NULL is + * returned. getenv() is forcefully inlined so that the reference to "environ" + * will be dropped if unused, even at -O0. + */ +static __attribute__((unused)) +char *_getenv(const char *name, char **environ) +{ + int idx, i; + + if (environ) { + for (idx = 0; environ[idx]; idx++) { + for (i = 0; name[i] && name[i] == environ[idx][i];) + i++; + if (!name[i] && environ[idx][i] == '=') + return &environ[idx][i+1]; + } + } + return NULL; +} + +static inline __attribute__((unused,always_inline)) +char *getenv(const char *name) +{ + extern char **environ; + return _getenv(name, environ); +} + +static __attribute__((unused)) +void *malloc(size_t len) +{ + struct nolibc_heap *heap; + + /* Always allocate memory with size multiple of 4096. */ + len = sizeof(*heap) + len; + len = (len + 4095UL) & -4096UL; + heap = mmap(NULL, len, PROT_READ|PROT_WRITE, MAP_ANONYMOUS|MAP_PRIVATE, + -1, 0); + if (__builtin_expect(heap == MAP_FAILED, 0)) + return NULL; + + heap->len = len; + return heap->user_p; +} + +static __attribute__((unused)) +void *calloc(size_t size, size_t nmemb) +{ + void *orig; + size_t res = 0; + + if (__builtin_expect(__builtin_mul_overflow(nmemb, size, &res), 0)) { + SET_ERRNO(ENOMEM); + return NULL; + } + + /* + * No need to zero the heap, the MAP_ANONYMOUS in malloc() + * already does it. + */ + return malloc(res); +} + +static __attribute__((unused)) +void *realloc(void *old_ptr, size_t new_size) +{ + struct nolibc_heap *heap; + size_t user_p_len; + void *ret; + + if (!old_ptr) + return malloc(new_size); + + heap = container_of(old_ptr, struct nolibc_heap, user_p); + user_p_len = heap->len - sizeof(*heap); + /* + * Don't realloc() if @user_p_len >= @new_size, this block of + * memory is still enough to handle the @new_size. Just return + * the same pointer. + */ + if (user_p_len >= new_size) + return old_ptr; + + ret = malloc(new_size); + if (__builtin_expect(!ret, 0)) + return NULL; + + memcpy(ret, heap->user_p, heap->len); + munmap(heap, heap->len); + return ret; +} + +/* Converts the unsigned long integer <in> to its hex representation into + * buffer <buffer>, which must be long enough to store the number and the + * trailing zero (17 bytes for "ffffffffffffffff" or 9 for "ffffffff"). The + * buffer is filled from the first byte, and the number of characters emitted + * (not counting the trailing zero) is returned. The function is constructed + * in a way to optimize the code size and avoid any divide that could add a + * dependency on large external functions. + */ +static __attribute__((unused)) +int utoh_r(unsigned long in, char *buffer) +{ + signed char pos = (~0UL > 0xfffffffful) ? 60 : 28; + int digits = 0; + int dig; + + do { + dig = in >> pos; + in -= (uint64_t)dig << pos; + pos -= 4; + if (dig || digits || pos < 0) { + if (dig > 9) + dig += 'a' - '0' - 10; + buffer[digits++] = '0' + dig; + } + } while (pos >= 0); + + buffer[digits] = 0; + return digits; +} + +/* converts unsigned long <in> to an hex string using the static itoa_buffer + * and returns the pointer to that string. + */ +static inline __attribute__((unused)) +char *utoh(unsigned long in) +{ + utoh_r(in, itoa_buffer); + return itoa_buffer; +} + +/* Converts the unsigned long integer <in> to its string representation into + * buffer <buffer>, which must be long enough to store the number and the + * trailing zero (21 bytes for 18446744073709551615 in 64-bit, 11 for + * 4294967295 in 32-bit). The buffer is filled from the first byte, and the + * number of characters emitted (not counting the trailing zero) is returned. + * The function is constructed in a way to optimize the code size and avoid + * any divide that could add a dependency on large external functions. + */ +static __attribute__((unused)) +int utoa_r(unsigned long in, char *buffer) +{ + unsigned long lim; + int digits = 0; + int pos = (~0UL > 0xfffffffful) ? 19 : 9; + int dig; + + do { + for (dig = 0, lim = 1; dig < pos; dig++) + lim *= 10; + + if (digits || in >= lim || !pos) { + for (dig = 0; in >= lim; dig++) + in -= lim; + buffer[digits++] = '0' + dig; + } + } while (pos--); + + buffer[digits] = 0; + return digits; +} + +/* Converts the signed long integer <in> to its string representation into + * buffer <buffer>, which must be long enough to store the number and the + * trailing zero (21 bytes for -9223372036854775808 in 64-bit, 12 for + * -2147483648 in 32-bit). The buffer is filled from the first byte, and the + * number of characters emitted (not counting the trailing zero) is returned. + */ +static __attribute__((unused)) +int itoa_r(long in, char *buffer) +{ + char *ptr = buffer; + int len = 0; + + if (in < 0) { + in = -in; + *(ptr++) = '-'; + len++; + } + len += utoa_r(in, ptr); + return len; +} + +/* for historical compatibility, same as above but returns the pointer to the + * buffer. + */ +static inline __attribute__((unused)) +char *ltoa_r(long in, char *buffer) +{ + itoa_r(in, buffer); + return buffer; +} + +/* converts long integer <in> to a string using the static itoa_buffer and + * returns the pointer to that string. + */ +static inline __attribute__((unused)) +char *itoa(long in) +{ + itoa_r(in, itoa_buffer); + return itoa_buffer; +} + +/* converts long integer <in> to a string using the static itoa_buffer and + * returns the pointer to that string. Same as above, for compatibility. + */ +static inline __attribute__((unused)) +char *ltoa(long in) +{ + itoa_r(in, itoa_buffer); + return itoa_buffer; +} + +/* converts unsigned long integer <in> to a string using the static itoa_buffer + * and returns the pointer to that string. + */ +static inline __attribute__((unused)) +char *utoa(unsigned long in) +{ + utoa_r(in, itoa_buffer); + return itoa_buffer; +} + +/* Converts the unsigned 64-bit integer <in> to its hex representation into + * buffer <buffer>, which must be long enough to store the number and the + * trailing zero (17 bytes for "ffffffffffffffff"). The buffer is filled from + * the first byte, and the number of characters emitted (not counting the + * trailing zero) is returned. The function is constructed in a way to optimize + * the code size and avoid any divide that could add a dependency on large + * external functions. + */ +static __attribute__((unused)) +int u64toh_r(uint64_t in, char *buffer) +{ + signed char pos = 60; + int digits = 0; + int dig; + + do { + if (sizeof(long) >= 8) { + dig = (in >> pos) & 0xF; + } else { + /* 32-bit platforms: avoid a 64-bit shift */ + uint32_t d = (pos >= 32) ? (in >> 32) : in; + dig = (d >> (pos & 31)) & 0xF; + } + if (dig > 9) + dig += 'a' - '0' - 10; + pos -= 4; + if (dig || digits || pos < 0) + buffer[digits++] = '0' + dig; + } while (pos >= 0); + + buffer[digits] = 0; + return digits; +} + +/* converts uint64_t <in> to an hex string using the static itoa_buffer and + * returns the pointer to that string. + */ +static inline __attribute__((unused)) +char *u64toh(uint64_t in) +{ + u64toh_r(in, itoa_buffer); + return itoa_buffer; +} + +/* Converts the unsigned 64-bit integer <in> to its string representation into + * buffer <buffer>, which must be long enough to store the number and the + * trailing zero (21 bytes for 18446744073709551615). The buffer is filled from + * the first byte, and the number of characters emitted (not counting the + * trailing zero) is returned. The function is constructed in a way to optimize + * the code size and avoid any divide that could add a dependency on large + * external functions. + */ +static __attribute__((unused)) +int u64toa_r(uint64_t in, char *buffer) +{ + unsigned long long lim; + int digits = 0; + int pos = 19; /* start with the highest possible digit */ + int dig; + + do { + for (dig = 0, lim = 1; dig < pos; dig++) + lim *= 10; + + if (digits || in >= lim || !pos) { + for (dig = 0; in >= lim; dig++) + in -= lim; + buffer[digits++] = '0' + dig; + } + } while (pos--); + + buffer[digits] = 0; + return digits; +} + +/* Converts the signed 64-bit integer <in> to its string representation into + * buffer <buffer>, which must be long enough to store the number and the + * trailing zero (21 bytes for -9223372036854775808). The buffer is filled from + * the first byte, and the number of characters emitted (not counting the + * trailing zero) is returned. + */ +static __attribute__((unused)) +int i64toa_r(int64_t in, char *buffer) +{ + char *ptr = buffer; + int len = 0; + + if (in < 0) { + in = -in; + *(ptr++) = '-'; + len++; + } + len += u64toa_r(in, ptr); + return len; +} + +/* converts int64_t <in> to a string using the static itoa_buffer and returns + * the pointer to that string. + */ +static inline __attribute__((unused)) +char *i64toa(int64_t in) +{ + i64toa_r(in, itoa_buffer); + return itoa_buffer; +} + +/* converts uint64_t <in> to a string using the static itoa_buffer and returns + * the pointer to that string. + */ +static inline __attribute__((unused)) +char *u64toa(uint64_t in) +{ + u64toa_r(in, itoa_buffer); + return itoa_buffer; +} + +#endif /* _NOLIBC_STDLIB_H */ diff --git a/tools/include/nolibc/string.h b/tools/include/nolibc/string.h new file mode 100644 index 000000000000..bef35bee9c44 --- /dev/null +++ b/tools/include/nolibc/string.h @@ -0,0 +1,285 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* + * string function definitions for NOLIBC + * Copyright (C) 2017-2021 Willy Tarreau <w@1wt.eu> + */ + +#ifndef _NOLIBC_STRING_H +#define _NOLIBC_STRING_H + +#include "std.h" + +static void *malloc(size_t len); + +/* + * As much as possible, please keep functions alphabetically sorted. + */ + +static __attribute__((unused)) +int memcmp(const void *s1, const void *s2, size_t n) +{ + size_t ofs = 0; + char c1 = 0; + + while (ofs < n && !(c1 = ((char *)s1)[ofs] - ((char *)s2)[ofs])) { + ofs++; + } + return c1; +} + +static __attribute__((unused)) +void *_nolibc_memcpy_up(void *dst, const void *src, size_t len) +{ + size_t pos = 0; + + while (pos < len) { + ((char *)dst)[pos] = ((const char *)src)[pos]; + pos++; + } + return dst; +} + +static __attribute__((unused)) +void *_nolibc_memcpy_down(void *dst, const void *src, size_t len) +{ + while (len) { + len--; + ((char *)dst)[len] = ((const char *)src)[len]; + } + return dst; +} + +/* might be ignored by the compiler without -ffreestanding, then found as + * missing. + */ +__attribute__((weak,unused,section(".text.nolibc_memmove"))) +void *memmove(void *dst, const void *src, size_t len) +{ + size_t dir, pos; + + pos = len; + dir = -1; + + if (dst < src) { + pos = -1; + dir = 1; + } + + while (len) { + pos += dir; + ((char *)dst)[pos] = ((const char *)src)[pos]; + len--; + } + return dst; +} + +/* must be exported, as it's used by libgcc on ARM */ +__attribute__((weak,unused,section(".text.nolibc_memcpy"))) +void *memcpy(void *dst, const void *src, size_t len) +{ + return _nolibc_memcpy_up(dst, src, len); +} + +/* might be ignored by the compiler without -ffreestanding, then found as + * missing. + */ +__attribute__((weak,unused,section(".text.nolibc_memset"))) +void *memset(void *dst, int b, size_t len) +{ + char *p = dst; + + while (len--) + *(p++) = b; + return dst; +} + +static __attribute__((unused)) +char *strchr(const char *s, int c) +{ + while (*s) { + if (*s == (char)c) + return (char *)s; + s++; + } + return NULL; +} + +static __attribute__((unused)) +int strcmp(const char *a, const char *b) +{ + unsigned int c; + int diff; + + while (!(diff = (unsigned char)*a++ - (c = (unsigned char)*b++)) && c) + ; + return diff; +} + +static __attribute__((unused)) +char *strcpy(char *dst, const char *src) +{ + char *ret = dst; + + while ((*dst++ = *src++)); + return ret; +} + +/* this function is only used with arguments that are not constants or when + * it's not known because optimizations are disabled. + */ +static __attribute__((unused)) +size_t nolibc_strlen(const char *str) +{ + size_t len; + + for (len = 0; str[len]; len++); + return len; +} + +/* do not trust __builtin_constant_p() at -O0, as clang will emit a test and + * the two branches, then will rely on an external definition of strlen(). + */ +#if defined(__OPTIMIZE__) +#define strlen(str) ({ \ + __builtin_constant_p((str)) ? \ + __builtin_strlen((str)) : \ + nolibc_strlen((str)); \ +}) +#else +#define strlen(str) nolibc_strlen((str)) +#endif + +static __attribute__((unused)) +size_t strnlen(const char *str, size_t maxlen) +{ + size_t len; + + for (len = 0; (len < maxlen) && str[len]; len++); + return len; +} + +static __attribute__((unused)) +char *strdup(const char *str) +{ + size_t len; + char *ret; + + len = strlen(str); + ret = malloc(len + 1); + if (__builtin_expect(ret != NULL, 1)) + memcpy(ret, str, len + 1); + + return ret; +} + +static __attribute__((unused)) +char *strndup(const char *str, size_t maxlen) +{ + size_t len; + char *ret; + + len = strnlen(str, maxlen); + ret = malloc(len + 1); + if (__builtin_expect(ret != NULL, 1)) { + memcpy(ret, str, len); + ret[len] = '\0'; + } + + return ret; +} + +static __attribute__((unused)) +size_t strlcat(char *dst, const char *src, size_t size) +{ + size_t len; + char c; + + for (len = 0; dst[len]; len++) + ; + + for (;;) { + c = *src; + if (len < size) + dst[len] = c; + if (!c) + break; + len++; + src++; + } + + return len; +} + +static __attribute__((unused)) +size_t strlcpy(char *dst, const char *src, size_t size) +{ + size_t len; + char c; + + for (len = 0;;) { + c = src[len]; + if (len < size) + dst[len] = c; + if (!c) + break; + len++; + } + return len; +} + +static __attribute__((unused)) +char *strncat(char *dst, const char *src, size_t size) +{ + char *orig = dst; + + while (*dst) + dst++; + + while (size && (*dst = *src)) { + src++; + dst++; + size--; + } + + *dst = 0; + return orig; +} + +static __attribute__((unused)) +int strncmp(const char *a, const char *b, size_t size) +{ + unsigned int c; + int diff = 0; + + while (size-- && + !(diff = (unsigned char)*a++ - (c = (unsigned char)*b++)) && c) + ; + + return diff; +} + +static __attribute__((unused)) +char *strncpy(char *dst, const char *src, size_t size) +{ + size_t len; + + for (len = 0; len < size; len++) + if ((dst[len] = *src)) + src++; + return dst; +} + +static __attribute__((unused)) +char *strrchr(const char *s, int c) +{ + const char *ret = NULL; + + while (*s) { + if (*s == (char)c) + ret = s; + s++; + } + return (char *)ret; +} + +#endif /* _NOLIBC_STRING_H */ diff --git a/tools/include/nolibc/sys.h b/tools/include/nolibc/sys.h new file mode 100644 index 000000000000..08491070387b --- /dev/null +++ b/tools/include/nolibc/sys.h @@ -0,0 +1,1247 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* + * Syscall definitions for NOLIBC (those in man(2)) + * Copyright (C) 2017-2021 Willy Tarreau <w@1wt.eu> + */ + +#ifndef _NOLIBC_SYS_H +#define _NOLIBC_SYS_H + +#include <stdarg.h> +#include "std.h" + +/* system includes */ +#include <asm/unistd.h> +#include <asm/signal.h> // for SIGCHLD +#include <asm/ioctls.h> +#include <asm/mman.h> +#include <linux/fs.h> +#include <linux/loop.h> +#include <linux/time.h> + +#include "arch.h" +#include "errno.h" +#include "types.h" + + +/* Functions in this file only describe syscalls. They're declared static so + * that the compiler usually decides to inline them while still being allowed + * to pass a pointer to one of their instances. Each syscall exists in two + * versions: + * - the "internal" ones, which matches the raw syscall interface at the + * kernel level, which may sometimes slightly differ from the documented + * libc-level ones. For example most of them return either a valid value + * or -errno. All of these are prefixed with "sys_". They may be called + * by non-portable applications if desired. + * + * - the "exported" ones, whose interface must closely match the one + * documented in man(2), that applications are supposed to expect. These + * ones rely on the internal ones, and set errno. + * + * Each syscall will be defined with the two functions, sorted in alphabetical + * order applied to the exported names. + * + * In case of doubt about the relevance of a function here, only those which + * set errno should be defined here. Wrappers like those appearing in man(3) + * should not be placed here. + */ + + +/* + * int brk(void *addr); + * void *sbrk(intptr_t inc) + */ + +static __attribute__((unused)) +void *sys_brk(void *addr) +{ + return (void *)my_syscall1(__NR_brk, addr); +} + +static __attribute__((unused)) +int brk(void *addr) +{ + void *ret = sys_brk(addr); + + if (!ret) { + SET_ERRNO(ENOMEM); + return -1; + } + return 0; +} + +static __attribute__((unused)) +void *sbrk(intptr_t inc) +{ + void *ret; + + /* first call to find current end */ + if ((ret = sys_brk(0)) && (sys_brk(ret + inc) == ret + inc)) + return ret + inc; + + SET_ERRNO(ENOMEM); + return (void *)-1; +} + + +/* + * int chdir(const char *path); + */ + +static __attribute__((unused)) +int sys_chdir(const char *path) +{ + return my_syscall1(__NR_chdir, path); +} + +static __attribute__((unused)) +int chdir(const char *path) +{ + int ret = sys_chdir(path); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* + * int chmod(const char *path, mode_t mode); + */ + +static __attribute__((unused)) +int sys_chmod(const char *path, mode_t mode) +{ +#ifdef __NR_fchmodat + return my_syscall4(__NR_fchmodat, AT_FDCWD, path, mode, 0); +#elif defined(__NR_chmod) + return my_syscall2(__NR_chmod, path, mode); +#else +#error Neither __NR_fchmodat nor __NR_chmod defined, cannot implement sys_chmod() +#endif +} + +static __attribute__((unused)) +int chmod(const char *path, mode_t mode) +{ + int ret = sys_chmod(path, mode); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* + * int chown(const char *path, uid_t owner, gid_t group); + */ + +static __attribute__((unused)) +int sys_chown(const char *path, uid_t owner, gid_t group) +{ +#ifdef __NR_fchownat + return my_syscall5(__NR_fchownat, AT_FDCWD, path, owner, group, 0); +#elif defined(__NR_chown) + return my_syscall3(__NR_chown, path, owner, group); +#else +#error Neither __NR_fchownat nor __NR_chown defined, cannot implement sys_chown() +#endif +} + +static __attribute__((unused)) +int chown(const char *path, uid_t owner, gid_t group) +{ + int ret = sys_chown(path, owner, group); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* + * int chroot(const char *path); + */ + +static __attribute__((unused)) +int sys_chroot(const char *path) +{ + return my_syscall1(__NR_chroot, path); +} + +static __attribute__((unused)) +int chroot(const char *path) +{ + int ret = sys_chroot(path); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* + * int close(int fd); + */ + +static __attribute__((unused)) +int sys_close(int fd) +{ + return my_syscall1(__NR_close, fd); +} + +static __attribute__((unused)) +int close(int fd) +{ + int ret = sys_close(fd); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* + * int dup(int fd); + */ + +static __attribute__((unused)) +int sys_dup(int fd) +{ + return my_syscall1(__NR_dup, fd); +} + +static __attribute__((unused)) +int dup(int fd) +{ + int ret = sys_dup(fd); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* + * int dup2(int old, int new); + */ + +static __attribute__((unused)) +int sys_dup2(int old, int new) +{ +#ifdef __NR_dup3 + return my_syscall3(__NR_dup3, old, new, 0); +#elif defined(__NR_dup2) + return my_syscall2(__NR_dup2, old, new); +#else +#error Neither __NR_dup3 nor __NR_dup2 defined, cannot implement sys_dup2() +#endif +} + +static __attribute__((unused)) +int dup2(int old, int new) +{ + int ret = sys_dup2(old, new); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* + * int dup3(int old, int new, int flags); + */ + +#ifdef __NR_dup3 +static __attribute__((unused)) +int sys_dup3(int old, int new, int flags) +{ + return my_syscall3(__NR_dup3, old, new, flags); +} + +static __attribute__((unused)) +int dup3(int old, int new, int flags) +{ + int ret = sys_dup3(old, new, flags); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} +#endif + + +/* + * int execve(const char *filename, char *const argv[], char *const envp[]); + */ + +static __attribute__((unused)) +int sys_execve(const char *filename, char *const argv[], char *const envp[]) +{ + return my_syscall3(__NR_execve, filename, argv, envp); +} + +static __attribute__((unused)) +int execve(const char *filename, char *const argv[], char *const envp[]) +{ + int ret = sys_execve(filename, argv, envp); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* + * void exit(int status); + */ + +static __attribute__((noreturn,unused)) +void sys_exit(int status) +{ + my_syscall1(__NR_exit, status & 255); + while(1); // shut the "noreturn" warnings. +} + +static __attribute__((noreturn,unused)) +void exit(int status) +{ + sys_exit(status); +} + + +/* + * pid_t fork(void); + */ + +static __attribute__((unused)) +pid_t sys_fork(void) +{ +#ifdef __NR_clone + /* note: some archs only have clone() and not fork(). Different archs + * have a different API, but most archs have the flags on first arg and + * will not use the rest with no other flag. + */ + return my_syscall5(__NR_clone, SIGCHLD, 0, 0, 0, 0); +#elif defined(__NR_fork) + return my_syscall0(__NR_fork); +#else +#error Neither __NR_clone nor __NR_fork defined, cannot implement sys_fork() +#endif +} + +static __attribute__((unused)) +pid_t fork(void) +{ + pid_t ret = sys_fork(); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* + * int fsync(int fd); + */ + +static __attribute__((unused)) +int sys_fsync(int fd) +{ + return my_syscall1(__NR_fsync, fd); +} + +static __attribute__((unused)) +int fsync(int fd) +{ + int ret = sys_fsync(fd); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* + * int getdents64(int fd, struct linux_dirent64 *dirp, int count); + */ + +static __attribute__((unused)) +int sys_getdents64(int fd, struct linux_dirent64 *dirp, int count) +{ + return my_syscall3(__NR_getdents64, fd, dirp, count); +} + +static __attribute__((unused)) +int getdents64(int fd, struct linux_dirent64 *dirp, int count) +{ + int ret = sys_getdents64(fd, dirp, count); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* + * pid_t getpgid(pid_t pid); + */ + +static __attribute__((unused)) +pid_t sys_getpgid(pid_t pid) +{ + return my_syscall1(__NR_getpgid, pid); +} + +static __attribute__((unused)) +pid_t getpgid(pid_t pid) +{ + pid_t ret = sys_getpgid(pid); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* + * pid_t getpgrp(void); + */ + +static __attribute__((unused)) +pid_t sys_getpgrp(void) +{ + return sys_getpgid(0); +} + +static __attribute__((unused)) +pid_t getpgrp(void) +{ + return sys_getpgrp(); +} + + +/* + * pid_t getpid(void); + */ + +static __attribute__((unused)) +pid_t sys_getpid(void) +{ + return my_syscall0(__NR_getpid); +} + +static __attribute__((unused)) +pid_t getpid(void) +{ + return sys_getpid(); +} + + +/* + * pid_t getppid(void); + */ + +static __attribute__((unused)) +pid_t sys_getppid(void) +{ + return my_syscall0(__NR_getppid); +} + +static __attribute__((unused)) +pid_t getppid(void) +{ + return sys_getppid(); +} + + +/* + * pid_t gettid(void); + */ + +static __attribute__((unused)) +pid_t sys_gettid(void) +{ + return my_syscall0(__NR_gettid); +} + +static __attribute__((unused)) +pid_t gettid(void) +{ + return sys_gettid(); +} + + +/* + * int gettimeofday(struct timeval *tv, struct timezone *tz); + */ + +static __attribute__((unused)) +int sys_gettimeofday(struct timeval *tv, struct timezone *tz) +{ + return my_syscall2(__NR_gettimeofday, tv, tz); +} + +static __attribute__((unused)) +int gettimeofday(struct timeval *tv, struct timezone *tz) +{ + int ret = sys_gettimeofday(tv, tz); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* + * int ioctl(int fd, unsigned long req, void *value); + */ + +static __attribute__((unused)) +int sys_ioctl(int fd, unsigned long req, void *value) +{ + return my_syscall3(__NR_ioctl, fd, req, value); +} + +static __attribute__((unused)) +int ioctl(int fd, unsigned long req, void *value) +{ + int ret = sys_ioctl(fd, req, value); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + +/* + * int kill(pid_t pid, int signal); + */ + +static __attribute__((unused)) +int sys_kill(pid_t pid, int signal) +{ + return my_syscall2(__NR_kill, pid, signal); +} + +static __attribute__((unused)) +int kill(pid_t pid, int signal) +{ + int ret = sys_kill(pid, signal); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* + * int link(const char *old, const char *new); + */ + +static __attribute__((unused)) +int sys_link(const char *old, const char *new) +{ +#ifdef __NR_linkat + return my_syscall5(__NR_linkat, AT_FDCWD, old, AT_FDCWD, new, 0); +#elif defined(__NR_link) + return my_syscall2(__NR_link, old, new); +#else +#error Neither __NR_linkat nor __NR_link defined, cannot implement sys_link() +#endif +} + +static __attribute__((unused)) +int link(const char *old, const char *new) +{ + int ret = sys_link(old, new); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* + * off_t lseek(int fd, off_t offset, int whence); + */ + +static __attribute__((unused)) +off_t sys_lseek(int fd, off_t offset, int whence) +{ + return my_syscall3(__NR_lseek, fd, offset, whence); +} + +static __attribute__((unused)) +off_t lseek(int fd, off_t offset, int whence) +{ + off_t ret = sys_lseek(fd, offset, whence); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* + * int mkdir(const char *path, mode_t mode); + */ + +static __attribute__((unused)) +int sys_mkdir(const char *path, mode_t mode) +{ +#ifdef __NR_mkdirat + return my_syscall3(__NR_mkdirat, AT_FDCWD, path, mode); +#elif defined(__NR_mkdir) + return my_syscall2(__NR_mkdir, path, mode); +#else +#error Neither __NR_mkdirat nor __NR_mkdir defined, cannot implement sys_mkdir() +#endif +} + +static __attribute__((unused)) +int mkdir(const char *path, mode_t mode) +{ + int ret = sys_mkdir(path, mode); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* + * int mknod(const char *path, mode_t mode, dev_t dev); + */ + +static __attribute__((unused)) +long sys_mknod(const char *path, mode_t mode, dev_t dev) +{ +#ifdef __NR_mknodat + return my_syscall4(__NR_mknodat, AT_FDCWD, path, mode, dev); +#elif defined(__NR_mknod) + return my_syscall3(__NR_mknod, path, mode, dev); +#else +#error Neither __NR_mknodat nor __NR_mknod defined, cannot implement sys_mknod() +#endif +} + +static __attribute__((unused)) +int mknod(const char *path, mode_t mode, dev_t dev) +{ + int ret = sys_mknod(path, mode, dev); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + +#ifndef MAP_SHARED +#define MAP_SHARED 0x01 /* Share changes */ +#define MAP_PRIVATE 0x02 /* Changes are private */ +#define MAP_SHARED_VALIDATE 0x03 /* share + validate extension flags */ +#endif + +#ifndef MAP_FAILED +#define MAP_FAILED ((void *)-1) +#endif + +static __attribute__((unused)) +void *sys_mmap(void *addr, size_t length, int prot, int flags, int fd, + off_t offset) +{ +#ifndef my_syscall6 + /* Function not implemented. */ + return -ENOSYS; +#else + + int n; + +#if defined(__i386__) + n = __NR_mmap2; + offset >>= 12; +#else + n = __NR_mmap; +#endif + + return (void *)my_syscall6(n, addr, length, prot, flags, fd, offset); +#endif +} + +static __attribute__((unused)) +void *mmap(void *addr, size_t length, int prot, int flags, int fd, off_t offset) +{ + void *ret = sys_mmap(addr, length, prot, flags, fd, offset); + + if ((unsigned long)ret >= -4095UL) { + SET_ERRNO(-(long)ret); + ret = MAP_FAILED; + } + return ret; +} + +static __attribute__((unused)) +int sys_munmap(void *addr, size_t length) +{ + return my_syscall2(__NR_munmap, addr, length); +} + +static __attribute__((unused)) +int munmap(void *addr, size_t length) +{ + int ret = sys_munmap(addr, length); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + +/* + * int mount(const char *source, const char *target, + * const char *fstype, unsigned long flags, + * const void *data); + */ +static __attribute__((unused)) +int sys_mount(const char *src, const char *tgt, const char *fst, + unsigned long flags, const void *data) +{ + return my_syscall5(__NR_mount, src, tgt, fst, flags, data); +} + +static __attribute__((unused)) +int mount(const char *src, const char *tgt, + const char *fst, unsigned long flags, + const void *data) +{ + int ret = sys_mount(src, tgt, fst, flags, data); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* + * int open(const char *path, int flags[, mode_t mode]); + */ + +static __attribute__((unused)) +int sys_open(const char *path, int flags, mode_t mode) +{ +#ifdef __NR_openat + return my_syscall4(__NR_openat, AT_FDCWD, path, flags, mode); +#elif defined(__NR_open) + return my_syscall3(__NR_open, path, flags, mode); +#else +#error Neither __NR_openat nor __NR_open defined, cannot implement sys_open() +#endif +} + +static __attribute__((unused)) +int open(const char *path, int flags, ...) +{ + mode_t mode = 0; + int ret; + + if (flags & O_CREAT) { + va_list args; + + va_start(args, flags); + mode = va_arg(args, mode_t); + va_end(args); + } + + ret = sys_open(path, flags, mode); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* + * int pivot_root(const char *new, const char *old); + */ + +static __attribute__((unused)) +int sys_pivot_root(const char *new, const char *old) +{ + return my_syscall2(__NR_pivot_root, new, old); +} + +static __attribute__((unused)) +int pivot_root(const char *new, const char *old) +{ + int ret = sys_pivot_root(new, old); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* + * int poll(struct pollfd *fds, int nfds, int timeout); + */ + +static __attribute__((unused)) +int sys_poll(struct pollfd *fds, int nfds, int timeout) +{ +#if defined(__NR_ppoll) + struct timespec t; + + if (timeout >= 0) { + t.tv_sec = timeout / 1000; + t.tv_nsec = (timeout % 1000) * 1000000; + } + return my_syscall4(__NR_ppoll, fds, nfds, (timeout >= 0) ? &t : NULL, NULL); +#elif defined(__NR_poll) + return my_syscall3(__NR_poll, fds, nfds, timeout); +#else +#error Neither __NR_ppoll nor __NR_poll defined, cannot implement sys_poll() +#endif +} + +static __attribute__((unused)) +int poll(struct pollfd *fds, int nfds, int timeout) +{ + int ret = sys_poll(fds, nfds, timeout); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* + * ssize_t read(int fd, void *buf, size_t count); + */ + +static __attribute__((unused)) +ssize_t sys_read(int fd, void *buf, size_t count) +{ + return my_syscall3(__NR_read, fd, buf, count); +} + +static __attribute__((unused)) +ssize_t read(int fd, void *buf, size_t count) +{ + ssize_t ret = sys_read(fd, buf, count); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* + * int reboot(int cmd); + * <cmd> is among LINUX_REBOOT_CMD_* + */ + +static __attribute__((unused)) +ssize_t sys_reboot(int magic1, int magic2, int cmd, void *arg) +{ + return my_syscall4(__NR_reboot, magic1, magic2, cmd, arg); +} + +static __attribute__((unused)) +int reboot(int cmd) +{ + int ret = sys_reboot(LINUX_REBOOT_MAGIC1, LINUX_REBOOT_MAGIC2, cmd, 0); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* + * int sched_yield(void); + */ + +static __attribute__((unused)) +int sys_sched_yield(void) +{ + return my_syscall0(__NR_sched_yield); +} + +static __attribute__((unused)) +int sched_yield(void) +{ + int ret = sys_sched_yield(); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* + * int select(int nfds, fd_set *read_fds, fd_set *write_fds, + * fd_set *except_fds, struct timeval *timeout); + */ + +static __attribute__((unused)) +int sys_select(int nfds, fd_set *rfds, fd_set *wfds, fd_set *efds, struct timeval *timeout) +{ +#if defined(__ARCH_WANT_SYS_OLD_SELECT) && !defined(__NR__newselect) + struct sel_arg_struct { + unsigned long n; + fd_set *r, *w, *e; + struct timeval *t; + } arg = { .n = nfds, .r = rfds, .w = wfds, .e = efds, .t = timeout }; + return my_syscall1(__NR_select, &arg); +#elif defined(__ARCH_WANT_SYS_PSELECT6) && defined(__NR_pselect6) + struct timespec t; + + if (timeout) { + t.tv_sec = timeout->tv_sec; + t.tv_nsec = timeout->tv_usec * 1000; + } + return my_syscall6(__NR_pselect6, nfds, rfds, wfds, efds, timeout ? &t : NULL, NULL); +#elif defined(__NR__newselect) || defined(__NR_select) +#ifndef __NR__newselect +#define __NR__newselect __NR_select +#endif + return my_syscall5(__NR__newselect, nfds, rfds, wfds, efds, timeout); +#else +#error None of __NR_select, __NR_pselect6, nor __NR__newselect defined, cannot implement sys_select() +#endif +} + +static __attribute__((unused)) +int select(int nfds, fd_set *rfds, fd_set *wfds, fd_set *efds, struct timeval *timeout) +{ + int ret = sys_select(nfds, rfds, wfds, efds, timeout); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* + * int setpgid(pid_t pid, pid_t pgid); + */ + +static __attribute__((unused)) +int sys_setpgid(pid_t pid, pid_t pgid) +{ + return my_syscall2(__NR_setpgid, pid, pgid); +} + +static __attribute__((unused)) +int setpgid(pid_t pid, pid_t pgid) +{ + int ret = sys_setpgid(pid, pgid); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* + * pid_t setsid(void); + */ + +static __attribute__((unused)) +pid_t sys_setsid(void) +{ + return my_syscall0(__NR_setsid); +} + +static __attribute__((unused)) +pid_t setsid(void) +{ + pid_t ret = sys_setsid(); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* + * int stat(const char *path, struct stat *buf); + * Warning: the struct stat's layout is arch-dependent. + */ + +static __attribute__((unused)) +int sys_stat(const char *path, struct stat *buf) +{ + struct sys_stat_struct stat; + long ret; + +#ifdef __NR_newfstatat + /* only solution for arm64 */ + ret = my_syscall4(__NR_newfstatat, AT_FDCWD, path, &stat, 0); +#elif defined(__NR_stat) + ret = my_syscall2(__NR_stat, path, &stat); +#else +#error Neither __NR_newfstatat nor __NR_stat defined, cannot implement sys_stat() +#endif + buf->st_dev = stat.st_dev; + buf->st_ino = stat.st_ino; + buf->st_mode = stat.st_mode; + buf->st_nlink = stat.st_nlink; + buf->st_uid = stat.st_uid; + buf->st_gid = stat.st_gid; + buf->st_rdev = stat.st_rdev; + buf->st_size = stat.st_size; + buf->st_blksize = stat.st_blksize; + buf->st_blocks = stat.st_blocks; + buf->st_atime = stat.st_atime; + buf->st_mtime = stat.st_mtime; + buf->st_ctime = stat.st_ctime; + return ret; +} + +static __attribute__((unused)) +int stat(const char *path, struct stat *buf) +{ + int ret = sys_stat(path, buf); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* + * int symlink(const char *old, const char *new); + */ + +static __attribute__((unused)) +int sys_symlink(const char *old, const char *new) +{ +#ifdef __NR_symlinkat + return my_syscall3(__NR_symlinkat, old, AT_FDCWD, new); +#elif defined(__NR_symlink) + return my_syscall2(__NR_symlink, old, new); +#else +#error Neither __NR_symlinkat nor __NR_symlink defined, cannot implement sys_symlink() +#endif +} + +static __attribute__((unused)) +int symlink(const char *old, const char *new) +{ + int ret = sys_symlink(old, new); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* + * mode_t umask(mode_t mode); + */ + +static __attribute__((unused)) +mode_t sys_umask(mode_t mode) +{ + return my_syscall1(__NR_umask, mode); +} + +static __attribute__((unused)) +mode_t umask(mode_t mode) +{ + return sys_umask(mode); +} + + +/* + * int umount2(const char *path, int flags); + */ + +static __attribute__((unused)) +int sys_umount2(const char *path, int flags) +{ + return my_syscall2(__NR_umount2, path, flags); +} + +static __attribute__((unused)) +int umount2(const char *path, int flags) +{ + int ret = sys_umount2(path, flags); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* + * int unlink(const char *path); + */ + +static __attribute__((unused)) +int sys_unlink(const char *path) +{ +#ifdef __NR_unlinkat + return my_syscall3(__NR_unlinkat, AT_FDCWD, path, 0); +#elif defined(__NR_unlink) + return my_syscall1(__NR_unlink, path); +#else +#error Neither __NR_unlinkat nor __NR_unlink defined, cannot implement sys_unlink() +#endif +} + +static __attribute__((unused)) +int unlink(const char *path) +{ + int ret = sys_unlink(path); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* + * pid_t wait(int *status); + * pid_t wait4(pid_t pid, int *status, int options, struct rusage *rusage); + * pid_t waitpid(pid_t pid, int *status, int options); + */ + +static __attribute__((unused)) +pid_t sys_wait4(pid_t pid, int *status, int options, struct rusage *rusage) +{ + return my_syscall4(__NR_wait4, pid, status, options, rusage); +} + +static __attribute__((unused)) +pid_t wait(int *status) +{ + pid_t ret = sys_wait4(-1, status, 0, NULL); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + +static __attribute__((unused)) +pid_t wait4(pid_t pid, int *status, int options, struct rusage *rusage) +{ + pid_t ret = sys_wait4(pid, status, options, rusage); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +static __attribute__((unused)) +pid_t waitpid(pid_t pid, int *status, int options) +{ + pid_t ret = sys_wait4(pid, status, options, NULL); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* + * ssize_t write(int fd, const void *buf, size_t count); + */ + +static __attribute__((unused)) +ssize_t sys_write(int fd, const void *buf, size_t count) +{ + return my_syscall3(__NR_write, fd, buf, count); +} + +static __attribute__((unused)) +ssize_t write(int fd, const void *buf, size_t count) +{ + ssize_t ret = sys_write(fd, buf, count); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +#endif /* _NOLIBC_SYS_H */ diff --git a/tools/include/nolibc/time.h b/tools/include/nolibc/time.h new file mode 100644 index 000000000000..d18b7661fdd7 --- /dev/null +++ b/tools/include/nolibc/time.h @@ -0,0 +1,28 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* + * time function definitions for NOLIBC + * Copyright (C) 2017-2022 Willy Tarreau <w@1wt.eu> + */ + +#ifndef _NOLIBC_TIME_H +#define _NOLIBC_TIME_H + +#include "std.h" +#include "arch.h" +#include "types.h" +#include "sys.h" + +static __attribute__((unused)) +time_t time(time_t *tptr) +{ + struct timeval tv; + + /* note, cannot fail here */ + sys_gettimeofday(&tv, NULL); + + if (tptr) + *tptr = tv.tv_sec; + return tv.tv_sec; +} + +#endif /* _NOLIBC_TIME_H */ diff --git a/tools/include/nolibc/types.h b/tools/include/nolibc/types.h new file mode 100644 index 000000000000..959997034e55 --- /dev/null +++ b/tools/include/nolibc/types.h @@ -0,0 +1,205 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* + * Special types used by various syscalls for NOLIBC + * Copyright (C) 2017-2021 Willy Tarreau <w@1wt.eu> + */ + +#ifndef _NOLIBC_TYPES_H +#define _NOLIBC_TYPES_H + +#include "std.h" +#include <linux/time.h> + + +/* Only the generic macros and types may be defined here. The arch-specific + * ones such as the O_RDONLY and related macros used by fcntl() and open(), or + * the layout of sys_stat_struct must not be defined here. + */ + +/* stat flags (WARNING, octal here) */ +#define S_IFDIR 0040000 +#define S_IFCHR 0020000 +#define S_IFBLK 0060000 +#define S_IFREG 0100000 +#define S_IFIFO 0010000 +#define S_IFLNK 0120000 +#define S_IFSOCK 0140000 +#define S_IFMT 0170000 + +#define S_ISDIR(mode) (((mode) & S_IFDIR) == S_IFDIR) +#define S_ISCHR(mode) (((mode) & S_IFCHR) == S_IFCHR) +#define S_ISBLK(mode) (((mode) & S_IFBLK) == S_IFBLK) +#define S_ISREG(mode) (((mode) & S_IFREG) == S_IFREG) +#define S_ISFIFO(mode) (((mode) & S_IFIFO) == S_IFIFO) +#define S_ISLNK(mode) (((mode) & S_IFLNK) == S_IFLNK) +#define S_ISSOCK(mode) (((mode) & S_IFSOCK) == S_IFSOCK) + +/* dirent types */ +#define DT_UNKNOWN 0x0 +#define DT_FIFO 0x1 +#define DT_CHR 0x2 +#define DT_DIR 0x4 +#define DT_BLK 0x6 +#define DT_REG 0x8 +#define DT_LNK 0xa +#define DT_SOCK 0xc + +/* commonly an fd_set represents 256 FDs */ +#ifndef FD_SETSIZE +#define FD_SETSIZE 256 +#endif + +/* PATH_MAX and MAXPATHLEN are often used and found with plenty of different + * values. + */ +#ifndef PATH_MAX +#define PATH_MAX 4096 +#endif + +#ifndef MAXPATHLEN +#define MAXPATHLEN (PATH_MAX) +#endif + +/* Special FD used by all the *at functions */ +#ifndef AT_FDCWD +#define AT_FDCWD (-100) +#endif + +/* whence values for lseek() */ +#define SEEK_SET 0 +#define SEEK_CUR 1 +#define SEEK_END 2 + +/* cmd for reboot() */ +#define LINUX_REBOOT_MAGIC1 0xfee1dead +#define LINUX_REBOOT_MAGIC2 0x28121969 +#define LINUX_REBOOT_CMD_HALT 0xcdef0123 +#define LINUX_REBOOT_CMD_POWER_OFF 0x4321fedc +#define LINUX_REBOOT_CMD_RESTART 0x01234567 +#define LINUX_REBOOT_CMD_SW_SUSPEND 0xd000fce2 + +/* Macros used on waitpid()'s return status */ +#define WEXITSTATUS(status) (((status) & 0xff00) >> 8) +#define WIFEXITED(status) (((status) & 0x7f) == 0) + +/* waitpid() flags */ +#define WNOHANG 1 + +/* standard exit() codes */ +#define EXIT_SUCCESS 0 +#define EXIT_FAILURE 1 + +/* for select() */ +typedef struct { + uint32_t fd32[(FD_SETSIZE + 31) / 32]; +} fd_set; + +#define FD_CLR(fd, set) do { \ + fd_set *__set = (set); \ + int __fd = (fd); \ + if (__fd >= 0) \ + __set->fd32[__fd / 32] &= ~(1U << (__fd & 31)); \ + } while (0) + +#define FD_SET(fd, set) do { \ + fd_set *__set = (set); \ + int __fd = (fd); \ + if (__fd >= 0) \ + __set->fd32[__fd / 32] |= 1U << (__fd & 31); \ + } while (0) + +#define FD_ISSET(fd, set) ({ \ + fd_set *__set = (set); \ + int __fd = (fd); \ + int __r = 0; \ + if (__fd >= 0) \ + __r = !!(__set->fd32[__fd / 32] & 1U << (__fd & 31)); \ + __r; \ + }) + +#define FD_ZERO(set) do { \ + fd_set *__set = (set); \ + int __idx; \ + for (__idx = 0; __idx < (FD_SETSIZE+31) / 32; __idx ++) \ + __set->fd32[__idx] = 0; \ + } while (0) + +/* for poll() */ +#define POLLIN 0x0001 +#define POLLPRI 0x0002 +#define POLLOUT 0x0004 +#define POLLERR 0x0008 +#define POLLHUP 0x0010 +#define POLLNVAL 0x0020 + +struct pollfd { + int fd; + short int events; + short int revents; +}; + +/* for getdents64() */ +struct linux_dirent64 { + uint64_t d_ino; + int64_t d_off; + unsigned short d_reclen; + unsigned char d_type; + char d_name[]; +}; + +/* needed by wait4() */ +struct rusage { + struct timeval ru_utime; + struct timeval ru_stime; + long ru_maxrss; + long ru_ixrss; + long ru_idrss; + long ru_isrss; + long ru_minflt; + long ru_majflt; + long ru_nswap; + long ru_inblock; + long ru_oublock; + long ru_msgsnd; + long ru_msgrcv; + long ru_nsignals; + long ru_nvcsw; + long ru_nivcsw; +}; + +/* The format of the struct as returned by the libc to the application, which + * significantly differs from the format returned by the stat() syscall flavours. + */ +struct stat { + dev_t st_dev; /* ID of device containing file */ + ino_t st_ino; /* inode number */ + mode_t st_mode; /* protection */ + nlink_t st_nlink; /* number of hard links */ + uid_t st_uid; /* user ID of owner */ + gid_t st_gid; /* group ID of owner */ + dev_t st_rdev; /* device ID (if special file) */ + off_t st_size; /* total size, in bytes */ + blksize_t st_blksize; /* blocksize for file system I/O */ + blkcnt_t st_blocks; /* number of 512B blocks allocated */ + time_t st_atime; /* time of last access */ + time_t st_mtime; /* time of last modification */ + time_t st_ctime; /* time of last status change */ +}; + +/* WARNING, it only deals with the 4096 first majors and 256 first minors */ +#define makedev(major, minor) ((dev_t)((((major) & 0xfff) << 8) | ((minor) & 0xff))) +#define major(dev) ((unsigned int)(((dev) >> 8) & 0xfff)) +#define minor(dev) ((unsigned int)(((dev) & 0xff)) + +#ifndef offsetof +#define offsetof(TYPE, FIELD) ((size_t) &((TYPE *)0)->FIELD) +#endif + +#ifndef container_of +#define container_of(PTR, TYPE, FIELD) ({ \ + __typeof__(((TYPE *)0)->FIELD) *__FIELD_PTR = (PTR); \ + (TYPE *)((char *) __FIELD_PTR - offsetof(TYPE, FIELD)); \ +}) +#endif + +#endif /* _NOLIBC_TYPES_H */ diff --git a/tools/include/nolibc/unistd.h b/tools/include/nolibc/unistd.h new file mode 100644 index 000000000000..1c25e20ee360 --- /dev/null +++ b/tools/include/nolibc/unistd.h @@ -0,0 +1,54 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* + * unistd function definitions for NOLIBC + * Copyright (C) 2017-2022 Willy Tarreau <w@1wt.eu> + */ + +#ifndef _NOLIBC_UNISTD_H +#define _NOLIBC_UNISTD_H + +#include "std.h" +#include "arch.h" +#include "types.h" +#include "sys.h" + + +static __attribute__((unused)) +int msleep(unsigned int msecs) +{ + struct timeval my_timeval = { msecs / 1000, (msecs % 1000) * 1000 }; + + if (sys_select(0, 0, 0, 0, &my_timeval) < 0) + return (my_timeval.tv_sec * 1000) + + (my_timeval.tv_usec / 1000) + + !!(my_timeval.tv_usec % 1000); + else + return 0; +} + +static __attribute__((unused)) +unsigned int sleep(unsigned int seconds) +{ + struct timeval my_timeval = { seconds, 0 }; + + if (sys_select(0, 0, 0, 0, &my_timeval) < 0) + return my_timeval.tv_sec + !!my_timeval.tv_usec; + else + return 0; +} + +static __attribute__((unused)) +int usleep(unsigned int usecs) +{ + struct timeval my_timeval = { usecs / 1000000, usecs % 1000000 }; + + return sys_select(0, 0, 0, 0, &my_timeval); +} + +static __attribute__((unused)) +int tcsetpgrp(int fd, pid_t pid) +{ + return ioctl(fd, TIOCSPGRP, &pid); +} + +#endif /* _NOLIBC_UNISTD_H */ diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 91a6fe4e02c0..6a184d260c7f 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -445,7 +445,13 @@ struct kvm_run { #define KVM_SYSTEM_EVENT_RESET 2 #define KVM_SYSTEM_EVENT_CRASH 3 __u32 type; - __u64 flags; + __u32 ndata; + union { +#ifndef __KERNEL__ + __u64 flags; +#endif + __u64 data[16]; + }; } system_event; /* KVM_EXIT_S390_STSI */ struct { @@ -1144,6 +1150,8 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_S390_MEM_OP_EXTENSION 211 #define KVM_CAP_PMU_CAPABILITY 212 #define KVM_CAP_DISABLE_QUIRKS2 213 +/* #define KVM_CAP_VM_TSC_CONTROL 214 */ +#define KVM_CAP_SYSTEM_EVENT_DATA 215 #ifdef KVM_CAP_IRQ_ROUTING diff --git a/tools/include/uapi/linux/vhost.h b/tools/include/uapi/linux/vhost.h index c998860d7bbc..5d99e7c242a2 100644 --- a/tools/include/uapi/linux/vhost.h +++ b/tools/include/uapi/linux/vhost.h @@ -150,4 +150,11 @@ /* Get the valid iova range */ #define VHOST_VDPA_GET_IOVA_RANGE _IOR(VHOST_VIRTIO, 0x78, \ struct vhost_vdpa_iova_range) + +/* Get the config size */ +#define VHOST_VDPA_GET_CONFIG_SIZE _IOR(VHOST_VIRTIO, 0x79, __u32) + +/* Get the count of all virtqueues */ +#define VHOST_VDPA_GET_VQS_COUNT _IOR(VHOST_VIRTIO, 0x80, __u32) + #endif diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c index 1b15ba13c477..a09315538a30 100644 --- a/tools/lib/perf/evlist.c +++ b/tools/lib/perf/evlist.c @@ -577,7 +577,6 @@ int perf_evlist__mmap_ops(struct perf_evlist *evlist, { struct perf_evsel *evsel; const struct perf_cpu_map *cpus = evlist->user_requested_cpus; - const struct perf_thread_map *threads = evlist->threads; if (!ops || !ops->get || !ops->mmap) return -EINVAL; @@ -589,7 +588,7 @@ int perf_evlist__mmap_ops(struct perf_evlist *evlist, perf_evlist__for_each_entry(evlist, evsel) { if ((evsel->attr.read_format & PERF_FORMAT_ID) && evsel->sample_id == NULL && - perf_evsel__alloc_id(evsel, perf_cpu_map__nr(cpus), threads->nr) < 0) + perf_evsel__alloc_id(evsel, evsel->fd->max_x, evsel->fd->max_y) < 0) return -ENOMEM; } diff --git a/tools/lib/subcmd/parse-options.c b/tools/lib/subcmd/parse-options.c index 39ebf6192016..9fa75943f2ed 100644 --- a/tools/lib/subcmd/parse-options.c +++ b/tools/lib/subcmd/parse-options.c @@ -806,9 +806,9 @@ static int option__cmp(const void *va, const void *vb) static struct option *options__order(const struct option *opts) { - int nr_opts = 0, len; + int nr_opts = 0, nr_group = 0, len; const struct option *o = opts; - struct option *ordered; + struct option *opt, *ordered, *group; for (o = opts; o->type != OPTION_END; o++) ++nr_opts; @@ -819,7 +819,18 @@ static struct option *options__order(const struct option *opts) goto out; memcpy(ordered, opts, len); - qsort(ordered, nr_opts, sizeof(*o), option__cmp); + /* sort each option group individually */ + for (opt = group = ordered; opt->type != OPTION_END; opt++) { + if (opt->type == OPTION_GROUP) { + qsort(group, nr_group, sizeof(*opt), option__cmp); + group = opt + 1; + nr_group = 0; + continue; + } + nr_group++; + } + qsort(group, nr_group, sizeof(*opt), option__cmp); + out: return ordered; } diff --git a/tools/lib/thermal/.gitignore b/tools/lib/thermal/.gitignore new file mode 100644 index 000000000000..5d2aeda80fea --- /dev/null +++ b/tools/lib/thermal/.gitignore @@ -0,0 +1,2 @@ +libthermal.so* +libthermal.pc diff --git a/tools/lib/thermal/Build b/tools/lib/thermal/Build new file mode 100644 index 000000000000..4a892d9e24f9 --- /dev/null +++ b/tools/lib/thermal/Build @@ -0,0 +1,5 @@ +libthermal-y += commands.o +libthermal-y += events.o +libthermal-y += thermal_nl.o +libthermal-y += sampling.o +libthermal-y += thermal.o diff --git a/tools/lib/thermal/Makefile b/tools/lib/thermal/Makefile new file mode 100644 index 000000000000..2d0d255fd0e1 --- /dev/null +++ b/tools/lib/thermal/Makefile @@ -0,0 +1,165 @@ +# SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +# Most of this file is copied from tools/lib/perf/Makefile + +LIBTHERMAL_VERSION = 0 +LIBTHERMAL_PATCHLEVEL = 0 +LIBTHERMAL_EXTRAVERSION = 1 + +MAKEFLAGS += --no-print-directory + +ifeq ($(srctree),) +srctree := $(patsubst %/,%,$(dir $(CURDIR))) +srctree := $(patsubst %/,%,$(dir $(srctree))) +srctree := $(patsubst %/,%,$(dir $(srctree))) +# $(info Determined 'srctree' to be $(srctree)) +endif + +INSTALL = install + +# Use DESTDIR for installing into a different root directory. +# This is useful for building a package. The program will be +# installed in this directory as if it was the root directory. +# Then the build tool can move it later. +DESTDIR ?= +DESTDIR_SQ = '$(subst ','\'',$(DESTDIR))' + +include $(srctree)/tools/scripts/Makefile.include +include $(srctree)/tools/scripts/Makefile.arch + +ifeq ($(LP64), 1) + libdir_relative = lib64 +else + libdir_relative = lib +endif + +prefix ?= +libdir = $(prefix)/$(libdir_relative) + +# Shell quotes +libdir_SQ = $(subst ','\'',$(libdir)) +libdir_relative_SQ = $(subst ','\'',$(libdir_relative)) + +ifeq ("$(origin V)", "command line") + VERBOSE = $(V) +endif +ifndef VERBOSE + VERBOSE = 0 +endif + +ifeq ($(VERBOSE),1) + Q = +else + Q = @ +endif + +# Set compile option CFLAGS +ifdef EXTRA_CFLAGS + CFLAGS := $(EXTRA_CFLAGS) +else + CFLAGS := -g -Wall +endif + +INCLUDES = \ +-I/usr/include/libnl3 \ +-I$(srctree)/tools/lib/thermal/include \ +-I$(srctree)/tools/lib/ \ +-I$(srctree)/tools/include \ +-I$(srctree)/tools/arch/$(SRCARCH)/include/ \ +-I$(srctree)/tools/arch/$(SRCARCH)/include/uapi \ +-I$(srctree)/tools/include/uapi + +# Append required CFLAGS +override CFLAGS += $(EXTRA_WARNINGS) +override CFLAGS += -Werror -Wall +override CFLAGS += -fPIC +override CFLAGS += $(INCLUDES) +override CFLAGS += -fvisibility=hidden +override CFGLAS += -Wl,-L. +override CFGLAS += -Wl,-lthermal + +all: + +export srctree OUTPUT CC LD CFLAGS V +export DESTDIR DESTDIR_SQ + +include $(srctree)/tools/build/Makefile.include + +VERSION_SCRIPT := libthermal.map + +PATCHLEVEL = $(LIBTHERMAL_PATCHLEVEL) +EXTRAVERSION = $(LIBTHERMAL_EXTRAVERSION) +VERSION = $(LIBTHERMAL_VERSION).$(LIBTHERMAL_PATCHLEVEL).$(LIBTHERMAL_EXTRAVERSION) + +LIBTHERMAL_SO := $(OUTPUT)libthermal.so.$(VERSION) +LIBTHERMAL_A := $(OUTPUT)libthermal.a +LIBTHERMAL_IN := $(OUTPUT)libthermal-in.o +LIBTHERMAL_PC := $(OUTPUT)libthermal.pc +LIBTHERMAL_ALL := $(LIBTHERMAL_A) $(OUTPUT)libthermal.so* + +THERMAL_UAPI := include/uapi/linux/thermal.h + +$(THERMAL_UAPI): FORCE + ln -sf $(srctree)/$@ $(srctree)/tools/$@ + +$(LIBTHERMAL_IN): FORCE + $(Q)$(MAKE) $(build)=libthermal + +$(LIBTHERMAL_A): $(LIBTHERMAL_IN) + $(QUIET_AR)$(RM) $@ && $(AR) rcs $@ $(LIBTHERMAL_IN) + +$(LIBTHERMAL_SO): $(LIBTHERMAL_IN) + $(QUIET_LINK)$(CC) --shared -Wl,-soname,libthermal.so \ + -Wl,--version-script=$(VERSION_SCRIPT) $^ -o $@ + @ln -sf $(@F) $(OUTPUT)libthermal.so + @ln -sf $(@F) $(OUTPUT)libthermal.so.$(LIBTHERMAL_VERSION) + + +libs: $(THERMAL_UAPI) $(LIBTHERMAL_A) $(LIBTHERMAL_SO) $(LIBTHERMAL_PC) + +all: fixdep + $(Q)$(MAKE) libs + +clean: + $(call QUIET_CLEAN, libthermal) $(RM) $(LIBTHERMAL_A) \ + *.o *~ *.a *.so *.so.$(VERSION) *.so.$(LIBTHERMAL_VERSION) .*.d .*.cmd LIBTHERMAL-CFLAGS $(LIBTHERMAL_PC) + +$(LIBTHERMAL_PC): + $(QUIET_GEN)sed -e "s|@PREFIX@|$(prefix)|" \ + -e "s|@LIBDIR@|$(libdir_SQ)|" \ + -e "s|@VERSION@|$(VERSION)|" \ + < libthermal.pc.template > $@ + +define do_install_mkdir + if [ ! -d '$(DESTDIR_SQ)$1' ]; then \ + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$1'; \ + fi +endef + +define do_install + if [ ! -d '$(DESTDIR_SQ)$2' ]; then \ + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$2'; \ + fi; \ + $(INSTALL) $1 $(if $3,-m $3,) '$(DESTDIR_SQ)$2' +endef + +install_lib: libs + $(call QUIET_INSTALL, $(LIBTHERMAL_ALL)) \ + $(call do_install_mkdir,$(libdir_SQ)); \ + cp -fpR $(LIBTHERMAL_ALL) $(DESTDIR)$(libdir_SQ) + +install_headers: + $(call QUIET_INSTALL, headers) \ + $(call do_install,include/thermal.h,$(prefix)/include/thermal,644); \ + +install_pkgconfig: $(LIBTHERMAL_PC) + $(call QUIET_INSTALL, $(LIBTHERMAL_PC)) \ + $(call do_install,$(LIBTHERMAL_PC),$(libdir_SQ)/pkgconfig,644) + +install_doc: + $(Q)$(MAKE) -C Documentation install-man install-html install-examples + +install: install_lib install_headers install_pkgconfig + +FORCE: + +.PHONY: all install clean FORCE diff --git a/tools/lib/thermal/commands.c b/tools/lib/thermal/commands.c new file mode 100644 index 000000000000..73d4d4e8d6ec --- /dev/null +++ b/tools/lib/thermal/commands.c @@ -0,0 +1,349 @@ +// SPDX-License-Identifier: LGPL-2.1+ +// Copyright (C) 2022, Linaro Ltd - Daniel Lezcano <daniel.lezcano@linaro.org> +#define _GNU_SOURCE +#include <errno.h> +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> + +#include <thermal.h> +#include "thermal_nl.h" + +static struct nla_policy thermal_genl_policy[THERMAL_GENL_ATTR_MAX + 1] = { + /* Thermal zone */ + [THERMAL_GENL_ATTR_TZ] = { .type = NLA_NESTED }, + [THERMAL_GENL_ATTR_TZ_ID] = { .type = NLA_U32 }, + [THERMAL_GENL_ATTR_TZ_TEMP] = { .type = NLA_U32 }, + [THERMAL_GENL_ATTR_TZ_TRIP] = { .type = NLA_NESTED }, + [THERMAL_GENL_ATTR_TZ_TRIP_ID] = { .type = NLA_U32 }, + [THERMAL_GENL_ATTR_TZ_TRIP_TEMP] = { .type = NLA_U32 }, + [THERMAL_GENL_ATTR_TZ_TRIP_TYPE] = { .type = NLA_U32 }, + [THERMAL_GENL_ATTR_TZ_TRIP_HYST] = { .type = NLA_U32 }, + [THERMAL_GENL_ATTR_TZ_MODE] = { .type = NLA_U32 }, + [THERMAL_GENL_ATTR_TZ_CDEV_WEIGHT] = { .type = NLA_U32 }, + [THERMAL_GENL_ATTR_TZ_NAME] = { .type = NLA_STRING }, + + /* Governor(s) */ + [THERMAL_GENL_ATTR_TZ_GOV] = { .type = NLA_NESTED }, + [THERMAL_GENL_ATTR_TZ_GOV_NAME] = { .type = NLA_STRING }, + + /* Cooling devices */ + [THERMAL_GENL_ATTR_CDEV] = { .type = NLA_NESTED }, + [THERMAL_GENL_ATTR_CDEV_ID] = { .type = NLA_U32 }, + [THERMAL_GENL_ATTR_CDEV_CUR_STATE] = { .type = NLA_U32 }, + [THERMAL_GENL_ATTR_CDEV_MAX_STATE] = { .type = NLA_U32 }, + [THERMAL_GENL_ATTR_CDEV_NAME] = { .type = NLA_STRING }, +}; + +static int parse_tz_get(struct genl_info *info, struct thermal_zone **tz) +{ + struct nlattr *attr; + struct thermal_zone *__tz = NULL; + size_t size = 0; + int rem; + + nla_for_each_nested(attr, info->attrs[THERMAL_GENL_ATTR_TZ], rem) { + + if (nla_type(attr) == THERMAL_GENL_ATTR_TZ_ID) { + + size++; + + __tz = realloc(__tz, sizeof(*__tz) * (size + 2)); + if (!__tz) + return THERMAL_ERROR; + + __tz[size - 1].id = nla_get_u32(attr); + } + + + if (nla_type(attr) == THERMAL_GENL_ATTR_TZ_NAME) + nla_strlcpy(__tz[size - 1].name, attr, + THERMAL_NAME_LENGTH); + } + + if (__tz) + __tz[size].id = -1; + + *tz = __tz; + + return THERMAL_SUCCESS; +} + +static int parse_cdev_get(struct genl_info *info, struct thermal_cdev **cdev) +{ + struct nlattr *attr; + struct thermal_cdev *__cdev = NULL; + size_t size = 0; + int rem; + + nla_for_each_nested(attr, info->attrs[THERMAL_GENL_ATTR_CDEV], rem) { + + if (nla_type(attr) == THERMAL_GENL_ATTR_CDEV_ID) { + + size++; + + __cdev = realloc(__cdev, sizeof(*__cdev) * (size + 2)); + if (!__cdev) + return THERMAL_ERROR; + + __cdev[size - 1].id = nla_get_u32(attr); + } + + if (nla_type(attr) == THERMAL_GENL_ATTR_CDEV_NAME) { + nla_strlcpy(__cdev[size - 1].name, attr, + THERMAL_NAME_LENGTH); + } + + if (nla_type(attr) == THERMAL_GENL_ATTR_CDEV_CUR_STATE) + __cdev[size - 1].cur_state = nla_get_u32(attr); + + if (nla_type(attr) == THERMAL_GENL_ATTR_CDEV_MAX_STATE) + __cdev[size - 1].max_state = nla_get_u32(attr); + } + + if (__cdev) + __cdev[size].id = -1; + + *cdev = __cdev; + + return THERMAL_SUCCESS; +} + +static int parse_tz_get_trip(struct genl_info *info, struct thermal_zone *tz) +{ + struct nlattr *attr; + struct thermal_trip *__tt = NULL; + size_t size = 0; + int rem; + + nla_for_each_nested(attr, info->attrs[THERMAL_GENL_ATTR_TZ_TRIP], rem) { + + if (nla_type(attr) == THERMAL_GENL_ATTR_TZ_TRIP_ID) { + + size++; + + __tt = realloc(__tt, sizeof(*__tt) * (size + 2)); + if (!__tt) + return THERMAL_ERROR; + + __tt[size - 1].id = nla_get_u32(attr); + } + + if (nla_type(attr) == THERMAL_GENL_ATTR_TZ_TRIP_TYPE) + __tt[size - 1].type = nla_get_u32(attr); + + if (nla_type(attr) == THERMAL_GENL_ATTR_TZ_TRIP_TEMP) + __tt[size - 1].temp = nla_get_u32(attr); + + if (nla_type(attr) == THERMAL_GENL_ATTR_TZ_TRIP_HYST) + __tt[size - 1].hyst = nla_get_u32(attr); + } + + if (__tt) + __tt[size].id = -1; + + tz->trip = __tt; + + return THERMAL_SUCCESS; +} + +static int parse_tz_get_temp(struct genl_info *info, struct thermal_zone *tz) +{ + int id = -1; + + if (info->attrs[THERMAL_GENL_ATTR_TZ_ID]) + id = nla_get_u32(info->attrs[THERMAL_GENL_ATTR_TZ_ID]); + + if (tz->id != id) + return THERMAL_ERROR; + + if (info->attrs[THERMAL_GENL_ATTR_TZ_TEMP]) + tz->temp = nla_get_u32(info->attrs[THERMAL_GENL_ATTR_TZ_TEMP]); + + return THERMAL_SUCCESS; +} + +static int parse_tz_get_gov(struct genl_info *info, struct thermal_zone *tz) +{ + int id = -1; + + if (info->attrs[THERMAL_GENL_ATTR_TZ_ID]) + id = nla_get_u32(info->attrs[THERMAL_GENL_ATTR_TZ_ID]); + + if (tz->id != id) + return THERMAL_ERROR; + + if (info->attrs[THERMAL_GENL_ATTR_TZ_GOV_NAME]) { + nla_strlcpy(tz->governor, + info->attrs[THERMAL_GENL_ATTR_TZ_GOV_NAME], + THERMAL_NAME_LENGTH); + } + + return THERMAL_SUCCESS; +} + +static int handle_netlink(struct nl_cache_ops *unused, + struct genl_cmd *cmd, + struct genl_info *info, void *arg) +{ + int ret; + + switch (cmd->c_id) { + + case THERMAL_GENL_CMD_TZ_GET_ID: + ret = parse_tz_get(info, arg); + break; + + case THERMAL_GENL_CMD_CDEV_GET: + ret = parse_cdev_get(info, arg); + break; + + case THERMAL_GENL_CMD_TZ_GET_TEMP: + ret = parse_tz_get_temp(info, arg); + break; + + case THERMAL_GENL_CMD_TZ_GET_TRIP: + ret = parse_tz_get_trip(info, arg); + break; + + case THERMAL_GENL_CMD_TZ_GET_GOV: + ret = parse_tz_get_gov(info, arg); + break; + + default: + return THERMAL_ERROR; + } + + return ret; +} + +static struct genl_cmd thermal_cmds[] = { + { + .c_id = THERMAL_GENL_CMD_TZ_GET_ID, + .c_name = (char *)"List thermal zones", + .c_msg_parser = handle_netlink, + .c_maxattr = THERMAL_GENL_ATTR_MAX, + .c_attr_policy = thermal_genl_policy, + }, + { + .c_id = THERMAL_GENL_CMD_TZ_GET_GOV, + .c_name = (char *)"Get governor", + .c_msg_parser = handle_netlink, + .c_maxattr = THERMAL_GENL_ATTR_MAX, + .c_attr_policy = thermal_genl_policy, + }, + { + .c_id = THERMAL_GENL_CMD_TZ_GET_TEMP, + .c_name = (char *)"Get thermal zone temperature", + .c_msg_parser = handle_netlink, + .c_maxattr = THERMAL_GENL_ATTR_MAX, + .c_attr_policy = thermal_genl_policy, + }, + { + .c_id = THERMAL_GENL_CMD_TZ_GET_TRIP, + .c_name = (char *)"Get thermal zone trip points", + .c_msg_parser = handle_netlink, + .c_maxattr = THERMAL_GENL_ATTR_MAX, + .c_attr_policy = thermal_genl_policy, + }, + { + .c_id = THERMAL_GENL_CMD_CDEV_GET, + .c_name = (char *)"Get cooling devices", + .c_msg_parser = handle_netlink, + .c_maxattr = THERMAL_GENL_ATTR_MAX, + .c_attr_policy = thermal_genl_policy, + }, +}; + +static struct genl_ops thermal_cmd_ops = { + .o_name = (char *)"thermal", + .o_cmds = thermal_cmds, + .o_ncmds = ARRAY_SIZE(thermal_cmds), +}; + +static thermal_error_t thermal_genl_auto(struct thermal_handler *th, int id, int cmd, + int flags, void *arg) +{ + struct nl_msg *msg; + void *hdr; + + msg = nlmsg_alloc(); + if (!msg) + return THERMAL_ERROR; + + hdr = genlmsg_put(msg, NL_AUTO_PORT, NL_AUTO_SEQ, thermal_cmd_ops.o_id, + 0, flags, cmd, THERMAL_GENL_VERSION); + if (!hdr) + return THERMAL_ERROR; + + if (id >= 0 && nla_put_u32(msg, THERMAL_GENL_ATTR_TZ_ID, id)) + return THERMAL_ERROR; + + if (nl_send_msg(th->sk_cmd, th->cb_cmd, msg, genl_handle_msg, arg)) + return THERMAL_ERROR; + + nlmsg_free(msg); + + return THERMAL_SUCCESS; +} + +thermal_error_t thermal_cmd_get_tz(struct thermal_handler *th, struct thermal_zone **tz) +{ + return thermal_genl_auto(th, -1, THERMAL_GENL_CMD_TZ_GET_ID, + NLM_F_DUMP | NLM_F_ACK, tz); +} + +thermal_error_t thermal_cmd_get_cdev(struct thermal_handler *th, struct thermal_cdev **tc) +{ + return thermal_genl_auto(th, -1, THERMAL_GENL_CMD_CDEV_GET, + NLM_F_DUMP | NLM_F_ACK, tc); +} + +thermal_error_t thermal_cmd_get_trip(struct thermal_handler *th, struct thermal_zone *tz) +{ + return thermal_genl_auto(th, tz->id, THERMAL_GENL_CMD_TZ_GET_TRIP, + 0, tz); +} + +thermal_error_t thermal_cmd_get_governor(struct thermal_handler *th, struct thermal_zone *tz) +{ + return thermal_genl_auto(th, tz->id, THERMAL_GENL_CMD_TZ_GET_GOV, 0, tz); +} + +thermal_error_t thermal_cmd_get_temp(struct thermal_handler *th, struct thermal_zone *tz) +{ + return thermal_genl_auto(th, tz->id, THERMAL_GENL_CMD_TZ_GET_TEMP, 0, tz); +} + +thermal_error_t thermal_cmd_exit(struct thermal_handler *th) +{ + if (genl_unregister_family(&thermal_cmd_ops)) + return THERMAL_ERROR; + + nl_thermal_disconnect(th->sk_cmd, th->cb_cmd); + + return THERMAL_SUCCESS; +} + +thermal_error_t thermal_cmd_init(struct thermal_handler *th) +{ + int ret; + int family; + + if (nl_thermal_connect(&th->sk_cmd, &th->cb_cmd)) + return THERMAL_ERROR; + + ret = genl_register_family(&thermal_cmd_ops); + if (ret) + return THERMAL_ERROR; + + ret = genl_ops_resolve(th->sk_cmd, &thermal_cmd_ops); + if (ret) + return THERMAL_ERROR; + + family = genl_ctrl_resolve(th->sk_cmd, "nlctrl"); + if (family != GENL_ID_CTRL) + return THERMAL_ERROR; + + return THERMAL_SUCCESS; +} diff --git a/tools/lib/thermal/events.c b/tools/lib/thermal/events.c new file mode 100644 index 000000000000..a7a55d1a0c4c --- /dev/null +++ b/tools/lib/thermal/events.c @@ -0,0 +1,164 @@ +// SPDX-License-Identifier: LGPL-2.1+ +// Copyright (C) 2022, Linaro Ltd - Daniel Lezcano <daniel.lezcano@linaro.org> +#include <linux/netlink.h> +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> + + +#include <thermal.h> +#include "thermal_nl.h" + +/* + * Optimization: fill this array to tell which event we do want to pay + * attention to. That happens at init time with the ops + * structure. Each ops will enable the event and the general handler + * will be able to discard the event if there is not ops associated + * with it. + */ +static int enabled_ops[__THERMAL_GENL_EVENT_MAX]; + +static int handle_thermal_event(struct nl_msg *n, void *arg) +{ + struct nlmsghdr *nlh = nlmsg_hdr(n); + struct genlmsghdr *genlhdr = genlmsg_hdr(nlh); + struct nlattr *attrs[THERMAL_GENL_ATTR_MAX + 1]; + struct thermal_handler_param *thp = arg; + struct thermal_events_ops *ops = &thp->th->ops->events; + + genlmsg_parse(nlh, 0, attrs, THERMAL_GENL_ATTR_MAX, NULL); + + arg = thp->arg; + + /* + * This is an event we don't care of, bail out. + */ + if (!enabled_ops[genlhdr->cmd]) + return THERMAL_SUCCESS; + + switch (genlhdr->cmd) { + + case THERMAL_GENL_EVENT_TZ_CREATE: + return ops->tz_create(nla_get_string(attrs[THERMAL_GENL_ATTR_TZ_NAME]), + nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_ID]), arg); + + case THERMAL_GENL_EVENT_TZ_DELETE: + return ops->tz_delete(nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_ID]), arg); + + case THERMAL_GENL_EVENT_TZ_ENABLE: + return ops->tz_enable(nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_ID]), arg); + + case THERMAL_GENL_EVENT_TZ_DISABLE: + return ops->tz_disable(nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_ID]), arg); + + case THERMAL_GENL_EVENT_TZ_TRIP_CHANGE: + return ops->trip_change(nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_ID]), + nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_TRIP_ID]), + nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_TRIP_TYPE]), + nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_TRIP_TEMP]), + nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_TRIP_HYST]), arg); + + case THERMAL_GENL_EVENT_TZ_TRIP_ADD: + return ops->trip_add(nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_ID]), + nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_TRIP_ID]), + nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_TRIP_TYPE]), + nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_TRIP_TEMP]), + nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_TRIP_HYST]), arg); + + case THERMAL_GENL_EVENT_TZ_TRIP_DELETE: + return ops->trip_delete(nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_ID]), + nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_TRIP_ID]), arg); + + case THERMAL_GENL_EVENT_TZ_TRIP_UP: + return ops->trip_high(nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_ID]), + nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_TRIP_ID]), + nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_TEMP]), arg); + + case THERMAL_GENL_EVENT_TZ_TRIP_DOWN: + return ops->trip_low(nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_ID]), + nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_TRIP_ID]), + nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_TEMP]), arg); + + case THERMAL_GENL_EVENT_CDEV_ADD: + return ops->cdev_add(nla_get_string(attrs[THERMAL_GENL_ATTR_CDEV_NAME]), + nla_get_u32(attrs[THERMAL_GENL_ATTR_CDEV_ID]), + nla_get_u32(attrs[THERMAL_GENL_ATTR_CDEV_MAX_STATE]), arg); + + case THERMAL_GENL_EVENT_CDEV_DELETE: + return ops->cdev_delete(nla_get_u32(attrs[THERMAL_GENL_ATTR_CDEV_ID]), arg); + + case THERMAL_GENL_EVENT_CDEV_STATE_UPDATE: + return ops->cdev_update(nla_get_u32(attrs[THERMAL_GENL_ATTR_CDEV_ID]), + nla_get_u32(attrs[THERMAL_GENL_ATTR_CDEV_CUR_STATE]), arg); + + case THERMAL_GENL_EVENT_TZ_GOV_CHANGE: + return ops->gov_change(nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_ID]), + nla_get_string(attrs[THERMAL_GENL_ATTR_GOV_NAME]), arg); + default: + return -1; + } +} + +static void thermal_events_ops_init(struct thermal_events_ops *ops) +{ + enabled_ops[THERMAL_GENL_EVENT_TZ_CREATE] = !!ops->tz_create; + enabled_ops[THERMAL_GENL_EVENT_TZ_DELETE] = !!ops->tz_delete; + enabled_ops[THERMAL_GENL_EVENT_TZ_DISABLE] = !!ops->tz_disable; + enabled_ops[THERMAL_GENL_EVENT_TZ_ENABLE] = !!ops->tz_enable; + enabled_ops[THERMAL_GENL_EVENT_TZ_TRIP_UP] = !!ops->trip_high; + enabled_ops[THERMAL_GENL_EVENT_TZ_TRIP_DOWN] = !!ops->trip_low; + enabled_ops[THERMAL_GENL_EVENT_TZ_TRIP_CHANGE] = !!ops->trip_change; + enabled_ops[THERMAL_GENL_EVENT_TZ_TRIP_ADD] = !!ops->trip_add; + enabled_ops[THERMAL_GENL_EVENT_TZ_TRIP_DELETE] = !!ops->trip_delete; + enabled_ops[THERMAL_GENL_EVENT_CDEV_ADD] = !!ops->cdev_add; + enabled_ops[THERMAL_GENL_EVENT_CDEV_DELETE] = !!ops->cdev_delete; + enabled_ops[THERMAL_GENL_EVENT_CDEV_STATE_UPDATE] = !!ops->cdev_update; + enabled_ops[THERMAL_GENL_EVENT_TZ_GOV_CHANGE] = !!ops->gov_change; +} + +thermal_error_t thermal_events_handle(struct thermal_handler *th, void *arg) +{ + struct thermal_handler_param thp = { .th = th, .arg = arg }; + + if (!th) + return THERMAL_ERROR; + + if (nl_cb_set(th->cb_event, NL_CB_VALID, NL_CB_CUSTOM, + handle_thermal_event, &thp)) + return THERMAL_ERROR; + + return nl_recvmsgs(th->sk_event, th->cb_event); +} + +int thermal_events_fd(struct thermal_handler *th) +{ + if (!th) + return -1; + + return nl_socket_get_fd(th->sk_event); +} + +thermal_error_t thermal_events_exit(struct thermal_handler *th) +{ + if (nl_unsubscribe_thermal(th->sk_event, th->cb_event, + THERMAL_GENL_EVENT_GROUP_NAME)) + return THERMAL_ERROR; + + nl_thermal_disconnect(th->sk_event, th->cb_event); + + return THERMAL_SUCCESS; +} + +thermal_error_t thermal_events_init(struct thermal_handler *th) +{ + thermal_events_ops_init(&th->ops->events); + + if (nl_thermal_connect(&th->sk_event, &th->cb_event)) + return THERMAL_ERROR; + + if (nl_subscribe_thermal(th->sk_event, th->cb_event, + THERMAL_GENL_EVENT_GROUP_NAME)) + return THERMAL_ERROR; + + return THERMAL_SUCCESS; +} diff --git a/tools/lib/thermal/include/thermal.h b/tools/lib/thermal/include/thermal.h new file mode 100644 index 000000000000..1abc560602cf --- /dev/null +++ b/tools/lib/thermal/include/thermal.h @@ -0,0 +1,142 @@ +/* SPDX-License-Identifier: LGPL-2.1+ */ +/* Copyright (C) 2022, Linaro Ltd - Daniel Lezcano <daniel.lezcano@linaro.org> */ +#ifndef __LIBTHERMAL_H +#define __LIBTHERMAL_H + +#include <linux/thermal.h> + +#ifndef LIBTHERMAL_API +#define LIBTHERMAL_API __attribute__((visibility("default"))) +#endif + +#ifdef __cplusplus +extern "C" { +#endif + +struct thermal_sampling_ops { + int (*tz_temp)(int tz_id, int temp, void *arg); +}; + +struct thermal_events_ops { + int (*tz_create)(const char *name, int tz_id, void *arg); + int (*tz_delete)(int tz_id, void *arg); + int (*tz_enable)(int tz_id, void *arg); + int (*tz_disable)(int tz_id, void *arg); + int (*trip_high)(int tz_id, int trip_id, int temp, void *arg); + int (*trip_low)(int tz_id, int trip_id, int temp, void *arg); + int (*trip_add)(int tz_id, int trip_id, int type, int temp, int hyst, void *arg); + int (*trip_change)(int tz_id, int trip_id, int type, int temp, int hyst, void *arg); + int (*trip_delete)(int tz_id, int trip_id, void *arg); + int (*cdev_add)(const char *name, int cdev_id, int max_state, void *arg); + int (*cdev_delete)(int cdev_id, void *arg); + int (*cdev_update)(int cdev_id, int cur_state, void *arg); + int (*gov_change)(int tz_id, const char *gov_name, void *arg); +}; + +struct thermal_ops { + struct thermal_sampling_ops sampling; + struct thermal_events_ops events; +}; + +struct thermal_trip { + int id; + int type; + int temp; + int hyst; +}; + +struct thermal_zone { + int id; + int temp; + char name[THERMAL_NAME_LENGTH]; + char governor[THERMAL_NAME_LENGTH]; + struct thermal_trip *trip; +}; + +struct thermal_cdev { + int id; + char name[THERMAL_NAME_LENGTH]; + int max_state; + int min_state; + int cur_state; +}; + +typedef enum { + THERMAL_ERROR = -1, + THERMAL_SUCCESS = 0, +} thermal_error_t; + +struct thermal_handler; + +typedef int (*cb_tz_t)(struct thermal_zone *, void *); + +typedef int (*cb_tt_t)(struct thermal_trip *, void *); + +typedef int (*cb_tc_t)(struct thermal_cdev *, void *); + +LIBTHERMAL_API int for_each_thermal_zone(struct thermal_zone *tz, cb_tz_t cb, void *arg); + +LIBTHERMAL_API int for_each_thermal_trip(struct thermal_trip *tt, cb_tt_t cb, void *arg); + +LIBTHERMAL_API int for_each_thermal_cdev(struct thermal_cdev *cdev, cb_tc_t cb, void *arg); + +LIBTHERMAL_API struct thermal_zone *thermal_zone_find_by_name(struct thermal_zone *tz, + const char *name); + +LIBTHERMAL_API struct thermal_zone *thermal_zone_find_by_id(struct thermal_zone *tz, int id); + +LIBTHERMAL_API struct thermal_zone *thermal_zone_discover(struct thermal_handler *th); + +LIBTHERMAL_API struct thermal_handler *thermal_init(struct thermal_ops *ops); + +LIBTHERMAL_API void thermal_exit(struct thermal_handler *th); + +/* + * Netlink thermal events + */ +LIBTHERMAL_API thermal_error_t thermal_events_exit(struct thermal_handler *th); + +LIBTHERMAL_API thermal_error_t thermal_events_init(struct thermal_handler *th); + +LIBTHERMAL_API thermal_error_t thermal_events_handle(struct thermal_handler *th, void *arg); + +LIBTHERMAL_API int thermal_events_fd(struct thermal_handler *th); + +/* + * Netlink thermal commands + */ +LIBTHERMAL_API thermal_error_t thermal_cmd_exit(struct thermal_handler *th); + +LIBTHERMAL_API thermal_error_t thermal_cmd_init(struct thermal_handler *th); + +LIBTHERMAL_API thermal_error_t thermal_cmd_get_tz(struct thermal_handler *th, + struct thermal_zone **tz); + +LIBTHERMAL_API thermal_error_t thermal_cmd_get_cdev(struct thermal_handler *th, + struct thermal_cdev **tc); + +LIBTHERMAL_API thermal_error_t thermal_cmd_get_trip(struct thermal_handler *th, + struct thermal_zone *tz); + +LIBTHERMAL_API thermal_error_t thermal_cmd_get_governor(struct thermal_handler *th, + struct thermal_zone *tz); + +LIBTHERMAL_API thermal_error_t thermal_cmd_get_temp(struct thermal_handler *th, + struct thermal_zone *tz); + +/* + * Netlink thermal samples + */ +LIBTHERMAL_API thermal_error_t thermal_sampling_exit(struct thermal_handler *th); + +LIBTHERMAL_API thermal_error_t thermal_sampling_init(struct thermal_handler *th); + +LIBTHERMAL_API thermal_error_t thermal_sampling_handle(struct thermal_handler *th, void *arg); + +LIBTHERMAL_API int thermal_sampling_fd(struct thermal_handler *th); + +#endif /* __LIBTHERMAL_H */ + +#ifdef __cplusplus +} +#endif diff --git a/tools/lib/thermal/libthermal.map b/tools/lib/thermal/libthermal.map new file mode 100644 index 000000000000..d5e77738c7a4 --- /dev/null +++ b/tools/lib/thermal/libthermal.map @@ -0,0 +1,25 @@ +LIBTHERMAL_0.0.1 { + global: + thermal_init; + for_each_thermal_zone; + for_each_thermal_trip; + for_each_thermal_cdev; + thermal_zone_find_by_name; + thermal_zone_find_by_id; + thermal_zone_discover; + thermal_init; + thermal_events_init; + thermal_events_handle; + thermal_events_fd; + thermal_cmd_init; + thermal_cmd_get_tz; + thermal_cmd_get_cdev; + thermal_cmd_get_trip; + thermal_cmd_get_governor; + thermal_cmd_get_temp; + thermal_sampling_init; + thermal_sampling_handle; + thermal_sampling_fd; +local: + *; +}; diff --git a/tools/lib/thermal/libthermal.pc.template b/tools/lib/thermal/libthermal.pc.template new file mode 100644 index 000000000000..6f3769731b59 --- /dev/null +++ b/tools/lib/thermal/libthermal.pc.template @@ -0,0 +1,12 @@ +# SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) + +prefix=@PREFIX@ +libdir=@LIBDIR@ +includedir=${prefix}/include + +Name: libthermal +Description: thermal library +Requires: libnl-3.0 libnl-genl-3.0 +Version: @VERSION@ +Libs: -L${libdir} -lnl-genl-3 -lnl-3 +Cflags: -I${includedir} -I{include}/libnl3 diff --git a/tools/lib/thermal/sampling.c b/tools/lib/thermal/sampling.c new file mode 100644 index 000000000000..ee818f4e9654 --- /dev/null +++ b/tools/lib/thermal/sampling.c @@ -0,0 +1,75 @@ +// SPDX-License-Identifier: LGPL-2.1+ +// Copyright (C) 2022, Linaro Ltd - Daniel Lezcano <daniel.lezcano@linaro.org> +#include <errno.h> +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> + +#include <thermal.h> +#include "thermal_nl.h" + +static int handle_thermal_sample(struct nl_msg *n, void *arg) +{ + struct nlmsghdr *nlh = nlmsg_hdr(n); + struct genlmsghdr *genlhdr = genlmsg_hdr(nlh); + struct nlattr *attrs[THERMAL_GENL_ATTR_MAX + 1]; + struct thermal_handler_param *thp = arg; + struct thermal_handler *th = thp->th; + + genlmsg_parse(nlh, 0, attrs, THERMAL_GENL_ATTR_MAX, NULL); + + switch (genlhdr->cmd) { + + case THERMAL_GENL_SAMPLING_TEMP: + return th->ops->sampling.tz_temp( + nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_ID]), + nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_TEMP]), arg); + default: + return THERMAL_ERROR; + } +} + +thermal_error_t thermal_sampling_handle(struct thermal_handler *th, void *arg) +{ + struct thermal_handler_param thp = { .th = th, .arg = arg }; + + if (!th) + return THERMAL_ERROR; + + if (nl_cb_set(th->cb_sampling, NL_CB_VALID, NL_CB_CUSTOM, + handle_thermal_sample, &thp)) + return THERMAL_ERROR; + + return nl_recvmsgs(th->sk_sampling, th->cb_sampling); +} + +int thermal_sampling_fd(struct thermal_handler *th) +{ + if (!th) + return -1; + + return nl_socket_get_fd(th->sk_sampling); +} + +thermal_error_t thermal_sampling_exit(struct thermal_handler *th) +{ + if (nl_unsubscribe_thermal(th->sk_sampling, th->cb_sampling, + THERMAL_GENL_EVENT_GROUP_NAME)) + return THERMAL_ERROR; + + nl_thermal_disconnect(th->sk_sampling, th->cb_sampling); + + return THERMAL_SUCCESS; +} + +thermal_error_t thermal_sampling_init(struct thermal_handler *th) +{ + if (nl_thermal_connect(&th->sk_sampling, &th->cb_sampling)) + return THERMAL_ERROR; + + if (nl_subscribe_thermal(th->sk_sampling, th->cb_sampling, + THERMAL_GENL_SAMPLING_GROUP_NAME)) + return THERMAL_ERROR; + + return THERMAL_SUCCESS; +} diff --git a/tools/lib/thermal/thermal.c b/tools/lib/thermal/thermal.c new file mode 100644 index 000000000000..72a76dc205bc --- /dev/null +++ b/tools/lib/thermal/thermal.c @@ -0,0 +1,135 @@ +// SPDX-License-Identifier: LGPL-2.1+ +// Copyright (C) 2022, Linaro Ltd - Daniel Lezcano <daniel.lezcano@linaro.org> +#include <stdio.h> +#include <thermal.h> + +#include "thermal_nl.h" + +int for_each_thermal_cdev(struct thermal_cdev *cdev, cb_tc_t cb, void *arg) +{ + int i, ret = 0; + + if (!cdev) + return 0; + + for (i = 0; cdev[i].id != -1; i++) + ret |= cb(&cdev[i], arg); + + return ret; +} + +int for_each_thermal_trip(struct thermal_trip *tt, cb_tt_t cb, void *arg) +{ + int i, ret = 0; + + if (!tt) + return 0; + + for (i = 0; tt[i].id != -1; i++) + ret |= cb(&tt[i], arg); + + return ret; +} + +int for_each_thermal_zone(struct thermal_zone *tz, cb_tz_t cb, void *arg) +{ + int i, ret = 0; + + if (!tz) + return 0; + + for (i = 0; tz[i].id != -1; i++) + ret |= cb(&tz[i], arg); + + return ret; +} + +struct thermal_zone *thermal_zone_find_by_name(struct thermal_zone *tz, + const char *name) +{ + int i; + + if (!tz || !name) + return NULL; + + for (i = 0; tz[i].id != -1; i++) { + if (!strcmp(tz[i].name, name)) + return &tz[i]; + } + + return NULL; +} + +struct thermal_zone *thermal_zone_find_by_id(struct thermal_zone *tz, int id) +{ + int i; + + if (!tz || id < 0) + return NULL; + + for (i = 0; tz[i].id != -1; i++) { + if (tz[i].id == id) + return &tz[i]; + } + + return NULL; +} + +static int __thermal_zone_discover(struct thermal_zone *tz, void *th) +{ + if (thermal_cmd_get_trip(th, tz) < 0) + return -1; + + if (thermal_cmd_get_governor(th, tz)) + return -1; + + return 0; +} + +struct thermal_zone *thermal_zone_discover(struct thermal_handler *th) +{ + struct thermal_zone *tz; + + if (thermal_cmd_get_tz(th, &tz) < 0) + return NULL; + + if (for_each_thermal_zone(tz, __thermal_zone_discover, th)) + return NULL; + + return tz; +} + +void thermal_exit(struct thermal_handler *th) +{ + thermal_cmd_exit(th); + thermal_events_exit(th); + thermal_sampling_exit(th); + + free(th); +} + +struct thermal_handler *thermal_init(struct thermal_ops *ops) +{ + struct thermal_handler *th; + + th = malloc(sizeof(*th)); + if (!th) + return NULL; + th->ops = ops; + + if (thermal_events_init(th)) + goto out_free; + + if (thermal_sampling_init(th)) + goto out_free; + + if (thermal_cmd_init(th)) + goto out_free; + + return th; + +out_free: + free(th); + + return NULL; +} diff --git a/tools/lib/thermal/thermal_nl.c b/tools/lib/thermal/thermal_nl.c new file mode 100644 index 000000000000..b05cf9569858 --- /dev/null +++ b/tools/lib/thermal/thermal_nl.c @@ -0,0 +1,215 @@ +// SPDX-License-Identifier: LGPL-2.1+ +// Copyright (C) 2022, Linaro Ltd - Daniel Lezcano <daniel.lezcano@linaro.org> +#include <errno.h> +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> + +#include <thermal.h> +#include "thermal_nl.h" + +struct handler_args { + const char *group; + int id; +}; + +static __thread int err; +static __thread int done; + +static int nl_seq_check_handler(struct nl_msg *msg, void *arg) +{ + return NL_OK; +} + +static int nl_error_handler(struct sockaddr_nl *nla, struct nlmsgerr *nl_err, + void *arg) +{ + int *ret = arg; + + if (ret) + *ret = nl_err->error; + + return NL_STOP; +} + +static int nl_finish_handler(struct nl_msg *msg, void *arg) +{ + int *ret = arg; + + if (ret) + *ret = 1; + + return NL_OK; +} + +static int nl_ack_handler(struct nl_msg *msg, void *arg) +{ + int *ret = arg; + + if (ret) + *ret = 1; + + return NL_OK; +} + +int nl_send_msg(struct nl_sock *sock, struct nl_cb *cb, struct nl_msg *msg, + int (*rx_handler)(struct nl_msg *, void *), void *data) +{ + if (!rx_handler) + return THERMAL_ERROR; + + err = nl_send_auto_complete(sock, msg); + if (err < 0) + return err; + + nl_cb_set(cb, NL_CB_VALID, NL_CB_CUSTOM, rx_handler, data); + + err = done = 0; + + while (err == 0 && done == 0) + nl_recvmsgs(sock, cb); + + return err; +} + +static int nl_family_handler(struct nl_msg *msg, void *arg) +{ + struct handler_args *grp = arg; + struct nlattr *tb[CTRL_ATTR_MAX + 1]; + struct genlmsghdr *gnlh = nlmsg_data(nlmsg_hdr(msg)); + struct nlattr *mcgrp; + int rem_mcgrp; + + nla_parse(tb, CTRL_ATTR_MAX, genlmsg_attrdata(gnlh, 0), + genlmsg_attrlen(gnlh, 0), NULL); + + if (!tb[CTRL_ATTR_MCAST_GROUPS]) + return THERMAL_ERROR; + + nla_for_each_nested(mcgrp, tb[CTRL_ATTR_MCAST_GROUPS], rem_mcgrp) { + + struct nlattr *tb_mcgrp[CTRL_ATTR_MCAST_GRP_MAX + 1]; + + nla_parse(tb_mcgrp, CTRL_ATTR_MCAST_GRP_MAX, + nla_data(mcgrp), nla_len(mcgrp), NULL); + + if (!tb_mcgrp[CTRL_ATTR_MCAST_GRP_NAME] || + !tb_mcgrp[CTRL_ATTR_MCAST_GRP_ID]) + continue; + + if (strncmp(nla_data(tb_mcgrp[CTRL_ATTR_MCAST_GRP_NAME]), + grp->group, + nla_len(tb_mcgrp[CTRL_ATTR_MCAST_GRP_NAME]))) + continue; + + grp->id = nla_get_u32(tb_mcgrp[CTRL_ATTR_MCAST_GRP_ID]); + + break; + } + + return THERMAL_SUCCESS; +} + +static int nl_get_multicast_id(struct nl_sock *sock, struct nl_cb *cb, + const char *family, const char *group) +{ + struct nl_msg *msg; + int ret = 0, ctrlid; + struct handler_args grp = { + .group = group, + .id = -ENOENT, + }; + + msg = nlmsg_alloc(); + if (!msg) + return THERMAL_ERROR; + + ctrlid = genl_ctrl_resolve(sock, "nlctrl"); + + genlmsg_put(msg, 0, 0, ctrlid, 0, 0, CTRL_CMD_GETFAMILY, 0); + + nla_put_string(msg, CTRL_ATTR_FAMILY_NAME, family); + + ret = nl_send_msg(sock, cb, msg, nl_family_handler, &grp); + if (ret) + goto nla_put_failure; + + ret = grp.id; + +nla_put_failure: + nlmsg_free(msg); + return ret; +} + +int nl_thermal_connect(struct nl_sock **nl_sock, struct nl_cb **nl_cb) +{ + struct nl_cb *cb; + struct nl_sock *sock; + + cb = nl_cb_alloc(NL_CB_DEFAULT); + if (!cb) + return THERMAL_ERROR; + + sock = nl_socket_alloc(); + if (!sock) + goto out_cb_free; + + if (genl_connect(sock)) + goto out_socket_free; + + if (nl_cb_err(cb, NL_CB_CUSTOM, nl_error_handler, &err) || + nl_cb_set(cb, NL_CB_FINISH, NL_CB_CUSTOM, nl_finish_handler, &done) || + nl_cb_set(cb, NL_CB_ACK, NL_CB_CUSTOM, nl_ack_handler, &done) || + nl_cb_set(cb, NL_CB_SEQ_CHECK, NL_CB_CUSTOM, nl_seq_check_handler, &done)) + return THERMAL_ERROR; + + *nl_sock = sock; + *nl_cb = cb; + + return THERMAL_SUCCESS; + +out_socket_free: + nl_socket_free(sock); +out_cb_free: + nl_cb_put(cb); + return THERMAL_ERROR; +} + +void nl_thermal_disconnect(struct nl_sock *nl_sock, struct nl_cb *nl_cb) +{ + nl_close(nl_sock); + nl_socket_free(nl_sock); + nl_cb_put(nl_cb); +} + +int nl_unsubscribe_thermal(struct nl_sock *nl_sock, struct nl_cb *nl_cb, + const char *group) +{ + int mcid; + + mcid = nl_get_multicast_id(nl_sock, nl_cb, THERMAL_GENL_FAMILY_NAME, + group); + if (mcid < 0) + return THERMAL_ERROR; + + if (nl_socket_drop_membership(nl_sock, mcid)) + return THERMAL_ERROR; + + return THERMAL_SUCCESS; +} + +int nl_subscribe_thermal(struct nl_sock *nl_sock, struct nl_cb *nl_cb, + const char *group) +{ + int mcid; + + mcid = nl_get_multicast_id(nl_sock, nl_cb, THERMAL_GENL_FAMILY_NAME, + group); + if (mcid < 0) + return THERMAL_ERROR; + + if (nl_socket_add_membership(nl_sock, mcid)) + return THERMAL_ERROR; + + return THERMAL_SUCCESS; +} diff --git a/tools/lib/thermal/thermal_nl.h b/tools/lib/thermal/thermal_nl.h new file mode 100644 index 000000000000..ddf635642f07 --- /dev/null +++ b/tools/lib/thermal/thermal_nl.h @@ -0,0 +1,46 @@ +/* SPDX-License-Identifier: LGPL-2.1+ */ +/* Copyright (C) 2022, Linaro Ltd - Daniel Lezcano <daniel.lezcano@linaro.org> */ +#ifndef __THERMAL_H +#define __THERMAL_H + +#include <netlink/netlink.h> +#include <netlink/genl/genl.h> +#include <netlink/genl/mngt.h> +#include <netlink/genl/ctrl.h> + +struct thermal_handler { + int done; + int error; + struct thermal_ops *ops; + struct nl_msg *msg; + struct nl_sock *sk_event; + struct nl_sock *sk_sampling; + struct nl_sock *sk_cmd; + struct nl_cb *cb_cmd; + struct nl_cb *cb_event; + struct nl_cb *cb_sampling; +}; + +struct thermal_handler_param { + struct thermal_handler *th; + void *arg; +}; + +/* + * Low level netlink + */ +extern int nl_subscribe_thermal(struct nl_sock *nl_sock, struct nl_cb *nl_cb, + const char *group); + +extern int nl_unsubscribe_thermal(struct nl_sock *nl_sock, struct nl_cb *nl_cb, + const char *group); + +extern int nl_thermal_connect(struct nl_sock **nl_sock, struct nl_cb **nl_cb); + +extern void nl_thermal_disconnect(struct nl_sock *nl_sock, struct nl_cb *nl_cb); + +extern int nl_send_msg(struct nl_sock *sock, struct nl_cb *nl_cb, struct nl_msg *msg, + int (*rx_handler)(struct nl_msg *, void *), + void *data); + +#endif /* __THERMAL_H */ diff --git a/tools/memory-model/README b/tools/memory-model/README index 9edd402704c4..dab38904206a 100644 --- a/tools/memory-model/README +++ b/tools/memory-model/README @@ -54,7 +54,8 @@ klitmus7 Compatibility Table -- 4.14 7.48 -- 4.15 -- 4.19 7.49 -- 4.20 -- 5.5 7.54 -- - 5.6 -- 7.56 -- + 5.6 -- 5.16 7.56 -- + 5.17 -- 7.56.1 -- ============ ========== diff --git a/tools/objtool/Build b/tools/objtool/Build index b7222d5cc7bc..33f2ee5a46d3 100644 --- a/tools/objtool/Build +++ b/tools/objtool/Build @@ -2,17 +2,15 @@ objtool-y += arch/$(SRCARCH)/ objtool-y += weak.o -objtool-$(SUBCMD_CHECK) += check.o -objtool-$(SUBCMD_CHECK) += special.o -objtool-$(SUBCMD_ORC) += check.o -objtool-$(SUBCMD_ORC) += orc_gen.o -objtool-$(SUBCMD_ORC) += orc_dump.o - +objtool-y += check.o +objtool-y += special.o objtool-y += builtin-check.o -objtool-y += builtin-orc.o objtool-y += elf.o objtool-y += objtool.o +objtool-$(BUILD_ORC) += orc_gen.o +objtool-$(BUILD_ORC) += orc_dump.o + objtool-y += libstring.o objtool-y += libctype.o objtool-y += str_error_r.o diff --git a/tools/objtool/Documentation/stack-validation.txt b/tools/objtool/Documentation/objtool.txt index 30f38fdc0d56..8a671902a187 100644 --- a/tools/objtool/Documentation/stack-validation.txt +++ b/tools/objtool/Documentation/objtool.txt @@ -1,15 +1,103 @@ -Compile-time stack metadata validation -====================================== +Objtool +======= +The kernel CONFIG_OBJTOOL option enables a host tool named 'objtool' +which runs at compile time. It can do various validations and +transformations on .o files. -Overview +Objtool has become an integral part of the x86-64 kernel toolchain. The +kernel depends on it for a variety of security and performance features +(and other types of features as well). + + +Features -------- -The kernel CONFIG_STACK_VALIDATION option enables a host tool named -objtool which runs at compile time. It has a "check" subcommand which -analyzes every .o file and ensures the validity of its stack metadata. -It enforces a set of rules on asm code and C inline assembly code so -that stack traces can be reliable. +Objtool has the following features: + +- Stack unwinding metadata validation -- useful for helping to ensure + stack traces are reliable for live patching + +- ORC unwinder metadata generation -- a faster and more precise + alternative to frame pointer based unwinding + +- Retpoline validation -- ensures that all indirect calls go through + retpoline thunks, for Spectre v2 mitigations + +- Retpoline call site annotation -- annotates all retpoline thunk call + sites, enabling the kernel to patch them inline, to prevent "thunk + funneling" for both security and performance reasons + +- Non-instrumentation validation -- validates non-instrumentable + ("noinstr") code rules, preventing instrumentation in low-level C + entry code + +- Static call annotation -- annotates static call sites, enabling the + kernel to implement inline static calls, a faster alternative to some + indirect branches + +- Uaccess validation -- validates uaccess rules for a proper + implementation of Supervisor Mode Access Protection (SMAP) + +- Straight Line Speculation validation -- validates certain SLS + mitigations + +- Indirect Branch Tracking validation -- validates Intel CET IBT rules + to ensure that all functions referenced by function pointers have + corresponding ENDBR instructions + +- Indirect Branch Tracking annotation -- annotates unused ENDBR + instruction sites, enabling the kernel to "seal" them (replace them + with NOPs) to further harden IBT + +- Function entry annotation -- annotates function entries, enabling + kernel function tracing + +- Other toolchain hacks which will go unmentioned at this time... + +Each feature can be enabled individually or in combination using the +objtool cmdline. + + +Objects +------- + +Typically, objtool runs on every translation unit (TU, aka ".o file") in +the kernel. If a TU is part of a kernel module, the '--module' option +is added. + +However: + +- If noinstr validation is enabled, it also runs on vmlinux.o, with all + options removed and '--noinstr' added. + +- If IBT or LTO is enabled, it doesn't run on TUs at all. Instead it + runs on vmlinux.o and linked modules, with all options. + +In summary: + + A) Legacy mode: + TU: objtool [--module] <options> + vmlinux: N/A + module: N/A + + B) CONFIG_NOINSTR_VALIDATION=y && !(CONFIG_X86_KERNEL_IBT=y || CONFIG_LTO=y): + TU: objtool [--module] <options> // no --noinstr + vmlinux: objtool --noinstr // other options removed + module: N/A + + C) CONFIG_X86_KERNEL_IBT=y || CONFIG_LTO=y: + TU: N/A + vmlinux: objtool --noinstr <options> + module: objtool --module --noinstr <options> + + +Stack validation +---------------- + +Objtool's stack validation feature analyzes every .o file and ensures +the validity of its stack metadata. It enforces a set of rules on asm +code and C inline assembly code so that stack traces can be reliable. For each function, it recursively follows all possible code paths and validates the correct frame pointer state at each instruction. @@ -20,14 +108,6 @@ alternative execution paths to a given instruction (or set of instructions). Similarly, it knows how to follow switch statements, for which gcc sometimes uses jump tables. -(Objtool also has an 'orc generate' subcommand which generates debuginfo -for the ORC unwinder. See Documentation/x86/orc-unwinder.rst in the -kernel tree for more details.) - - -Why do we need stack metadata validation? ------------------------------------------ - Here are some of the benefits of validating stack metadata: a) More reliable stack traces for frame pointer enabled kernels @@ -113,9 +193,6 @@ c) Higher live patching compatibility rate For more details, see the livepatch documentation in the Linux kernel source tree at Documentation/livepatch/livepatch.rst. -Rules ------ - To achieve the validation, objtool enforces the following rules: 1. Each callable function must be annotated as such with the ELF @@ -177,7 +254,8 @@ Another possible cause for errors in C code is if the Makefile removes -fno-omit-frame-pointer or adds -fomit-frame-pointer to the gcc options. Here are some examples of common warnings reported by objtool, what -they mean, and suggestions for how to fix them. +they mean, and suggestions for how to fix them. When in doubt, ping +the objtool maintainers. 1. file.o: warning: objtool: func()+0x128: call without frame pointer save/setup @@ -358,3 +436,7 @@ ignore it: OBJECT_FILES_NON_STANDARD := y to the Makefile. + +NOTE: OBJECT_FILES_NON_STANDARD doesn't work for link time validation of +vmlinux.o or a linked module. So it should only be used for files which +aren't linked into vmlinux or a module. diff --git a/tools/objtool/Makefile b/tools/objtool/Makefile index 0dbd397f319d..e66d717c245d 100644 --- a/tools/objtool/Makefile +++ b/tools/objtool/Makefile @@ -39,15 +39,13 @@ CFLAGS += $(if $(elfshdr),,-DLIBELF_USE_DEPRECATED) AWK = awk -SUBCMD_CHECK := n -SUBCMD_ORC := n +BUILD_ORC := n ifeq ($(SRCARCH),x86) - SUBCMD_CHECK := y - SUBCMD_ORC := y + BUILD_ORC := y endif -export SUBCMD_CHECK SUBCMD_ORC +export BUILD_ORC export srctree OUTPUT CFLAGS SRCARCH AWK include $(srctree)/tools/build/Makefile.include @@ -65,7 +63,7 @@ $(LIBSUBCMD): fixdep FORCE clean: $(call QUIET_CLEAN, objtool) $(RM) $(OBJTOOL) $(Q)find $(OUTPUT) -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete - $(Q)$(RM) $(OUTPUT)arch/x86/inat-tables.c $(OUTPUT)fixdep + $(Q)$(RM) $(OUTPUT)arch/x86/lib/inat-tables.c $(OUTPUT)fixdep $(LIBSUBCMD) FORCE: diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c index 943cb41cddf7..8b990a52aada 100644 --- a/tools/objtool/arch/x86/decode.c +++ b/tools/objtool/arch/x86/decode.c @@ -581,7 +581,7 @@ int arch_decode_instruction(struct objtool_file *file, const struct section *sec break; case 0xc7: /* mov imm, r/m */ - if (!noinstr) + if (!opts.noinstr) break; if (insn.length == 3+4+4 && !strncmp(sec->name, ".init.text", 10)) { diff --git a/tools/objtool/arch/x86/special.c b/tools/objtool/arch/x86/special.c index e707d9bcd161..7c97b7391279 100644 --- a/tools/objtool/arch/x86/special.c +++ b/tools/objtool/arch/x86/special.c @@ -20,7 +20,7 @@ void arch_handle_alternative(unsigned short feature, struct special_alt *alt) * find paths that see the STAC but take the NOP instead of * CLAC and the other way around. */ - if (uaccess) + if (opts.uaccess) alt->skip_orig = true; else alt->skip_alt = true; diff --git a/tools/objtool/builtin-check.c b/tools/objtool/builtin-check.c index fc6975ab8b06..f4c3a5091737 100644 --- a/tools/objtool/builtin-check.c +++ b/tools/objtool/builtin-check.c @@ -3,28 +3,21 @@ * Copyright (C) 2015-2017 Josh Poimboeuf <jpoimboe@redhat.com> */ -/* - * objtool check: - * - * This command analyzes every .o file and ensures the validity of its stack - * trace metadata. It enforces a set of rules on asm code and C inline - * assembly code so that stack traces can be reliable. - * - * For more information, see tools/objtool/Documentation/stack-validation.txt. - */ - #include <subcmd/parse-options.h> #include <string.h> #include <stdlib.h> #include <objtool/builtin.h> #include <objtool/objtool.h> -bool no_fp, no_unreachable, retpoline, module, backtrace, uaccess, stats, - lto, vmlinux, mcount, noinstr, backup, sls, dryrun, - ibt; +#define ERROR(format, ...) \ + fprintf(stderr, \ + "error: objtool: " format "\n", \ + ##__VA_ARGS__) + +struct opts opts; static const char * const check_usage[] = { - "objtool check [<options>] file.o", + "objtool <actions> [<options>] file.o", NULL, }; @@ -33,22 +26,64 @@ static const char * const env_usage[] = { NULL, }; +static int parse_dump(const struct option *opt, const char *str, int unset) +{ + if (!str || !strcmp(str, "orc")) { + opts.dump_orc = true; + return 0; + } + + return -1; +} + +static int parse_hacks(const struct option *opt, const char *str, int unset) +{ + bool found = false; + + /* + * Use strstr() as a lazy method of checking for comma-separated + * options. + * + * No string provided == enable all options. + */ + + if (!str || strstr(str, "jump_label")) { + opts.hack_jump_label = true; + found = true; + } + + if (!str || strstr(str, "noinstr")) { + opts.hack_noinstr = true; + found = true; + } + + return found ? 0 : -1; +} + const struct option check_options[] = { - OPT_BOOLEAN('f', "no-fp", &no_fp, "Skip frame pointer validation"), - OPT_BOOLEAN('u', "no-unreachable", &no_unreachable, "Skip 'unreachable instruction' warnings"), - OPT_BOOLEAN('r', "retpoline", &retpoline, "Validate retpoline assumptions"), - OPT_BOOLEAN('m', "module", &module, "Indicates the object will be part of a kernel module"), - OPT_BOOLEAN('b', "backtrace", &backtrace, "unwind on error"), - OPT_BOOLEAN('a', "uaccess", &uaccess, "enable uaccess checking"), - OPT_BOOLEAN('s', "stats", &stats, "print statistics"), - OPT_BOOLEAN(0, "lto", <o, "whole-archive like runs"), - OPT_BOOLEAN('n', "noinstr", &noinstr, "noinstr validation for vmlinux.o"), - OPT_BOOLEAN('l', "vmlinux", &vmlinux, "vmlinux.o validation"), - OPT_BOOLEAN('M', "mcount", &mcount, "generate __mcount_loc"), - OPT_BOOLEAN('B', "backup", &backup, "create .orig files before modification"), - OPT_BOOLEAN('S', "sls", &sls, "validate straight-line-speculation"), - OPT_BOOLEAN(0, "dry-run", &dryrun, "don't write the modifications"), - OPT_BOOLEAN(0, "ibt", &ibt, "validate ENDBR placement"), + OPT_GROUP("Actions:"), + OPT_CALLBACK_OPTARG('h', "hacks", NULL, NULL, "jump_label,noinstr", "patch toolchain bugs/limitations", parse_hacks), + OPT_BOOLEAN('i', "ibt", &opts.ibt, "validate and annotate IBT"), + OPT_BOOLEAN('m', "mcount", &opts.mcount, "annotate mcount/fentry calls for ftrace"), + OPT_BOOLEAN('n', "noinstr", &opts.noinstr, "validate noinstr rules"), + OPT_BOOLEAN('o', "orc", &opts.orc, "generate ORC metadata"), + OPT_BOOLEAN('r', "retpoline", &opts.retpoline, "validate and annotate retpoline usage"), + OPT_BOOLEAN('l', "sls", &opts.sls, "validate straight-line-speculation mitigations"), + OPT_BOOLEAN('s', "stackval", &opts.stackval, "validate frame pointer rules"), + OPT_BOOLEAN('t', "static-call", &opts.static_call, "annotate static calls"), + OPT_BOOLEAN('u', "uaccess", &opts.uaccess, "validate uaccess rules for SMAP"), + OPT_CALLBACK_OPTARG(0, "dump", NULL, NULL, "orc", "dump metadata", parse_dump), + + OPT_GROUP("Options:"), + OPT_BOOLEAN(0, "backtrace", &opts.backtrace, "unwind on error"), + OPT_BOOLEAN(0, "backup", &opts.backup, "create .orig files before modification"), + OPT_BOOLEAN(0, "dry-run", &opts.dryrun, "don't write modifications"), + OPT_BOOLEAN(0, "link", &opts.link, "object is a linked object"), + OPT_BOOLEAN(0, "module", &opts.module, "object is part of a kernel module"), + OPT_BOOLEAN(0, "no-unreachable", &opts.no_unreachable, "skip 'unreachable instruction' warnings"), + OPT_BOOLEAN(0, "sec-address", &opts.sec_address, "print section addresses in warnings"), + OPT_BOOLEAN(0, "stats", &opts.stats, "print statistics"), + OPT_END(), }; @@ -79,7 +114,59 @@ int cmd_parse_options(int argc, const char **argv, const char * const usage[]) return argc; } -int cmd_check(int argc, const char **argv) +static bool opts_valid(void) +{ + if (opts.hack_jump_label || + opts.hack_noinstr || + opts.ibt || + opts.mcount || + opts.noinstr || + opts.orc || + opts.retpoline || + opts.sls || + opts.stackval || + opts.static_call || + opts.uaccess) { + if (opts.dump_orc) { + ERROR("--dump can't be combined with other options"); + return false; + } + + return true; + } + + if (opts.dump_orc) + return true; + + ERROR("At least one command required"); + return false; +} + +static bool link_opts_valid(struct objtool_file *file) +{ + if (opts.link) + return true; + + if (has_multiple_files(file->elf)) { + ERROR("Linked object detected, forcing --link"); + opts.link = true; + return true; + } + + if (opts.noinstr) { + ERROR("--noinstr requires --link"); + return false; + } + + if (opts.ibt) { + ERROR("--ibt requires --link"); + return false; + } + + return true; +} + +int objtool_run(int argc, const char **argv) { const char *objname; struct objtool_file *file; @@ -88,10 +175,19 @@ int cmd_check(int argc, const char **argv) argc = cmd_parse_options(argc, argv, check_usage); objname = argv[0]; + if (!opts_valid()) + return 1; + + if (opts.dump_orc) + return orc_dump(objname); + file = objtool_open_read(objname); if (!file) return 1; + if (!link_opts_valid(file)) + return 1; + ret = check(file); if (ret) return ret; diff --git a/tools/objtool/builtin-orc.c b/tools/objtool/builtin-orc.c deleted file mode 100644 index 17f8b9307738..000000000000 --- a/tools/objtool/builtin-orc.c +++ /dev/null @@ -1,73 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * Copyright (C) 2017 Josh Poimboeuf <jpoimboe@redhat.com> - */ - -/* - * objtool orc: - * - * This command analyzes a .o file and adds .orc_unwind and .orc_unwind_ip - * sections to it, which is used by the in-kernel ORC unwinder. - * - * This command is a superset of "objtool check". - */ - -#include <string.h> -#include <objtool/builtin.h> -#include <objtool/objtool.h> - -static const char *orc_usage[] = { - "objtool orc generate [<options>] file.o", - "objtool orc dump file.o", - NULL, -}; - -int cmd_orc(int argc, const char **argv) -{ - const char *objname; - - argc--; argv++; - if (argc <= 0) - usage_with_options(orc_usage, check_options); - - if (!strncmp(argv[0], "gen", 3)) { - struct objtool_file *file; - int ret; - - argc = cmd_parse_options(argc, argv, orc_usage); - objname = argv[0]; - - file = objtool_open_read(objname); - if (!file) - return 1; - - ret = check(file); - if (ret) - return ret; - - if (list_empty(&file->insn_list)) - return 0; - - ret = orc_create(file); - if (ret) - return ret; - - if (!file->elf->changed) - return 0; - - return elf_write(file->elf); - } - - if (!strcmp(argv[0], "dump")) { - if (argc != 2) - usage_with_options(orc_usage, check_options); - - objname = argv[1]; - - return orc_dump(objname); - } - - usage_with_options(orc_usage, check_options); - - return 0; -} diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 6de5085e3e5a..190b2f6e360a 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -5,6 +5,7 @@ #include <string.h> #include <stdlib.h> +#include <inttypes.h> #include <sys/mman.h> #include <arch/elf.h> @@ -184,6 +185,7 @@ static bool __dead_end_function(struct objtool_file *file, struct symbol *func, "do_group_exit", "stop_this_cpu", "__invalid_creds", + "cpu_startup_entry", }; if (!func) @@ -262,7 +264,8 @@ static void init_cfi_state(struct cfi_state *cfi) cfi->drap_offset = -1; } -static void init_insn_state(struct insn_state *state, struct section *sec) +static void init_insn_state(struct objtool_file *file, struct insn_state *state, + struct section *sec) { memset(state, 0, sizeof(*state)); init_cfi_state(&state->cfi); @@ -272,7 +275,7 @@ static void init_insn_state(struct insn_state *state, struct section *sec) * not correctly determine insn->call_dest->sec (external symbols do * not have a section). */ - if (vmlinux && noinstr && sec) + if (opts.link && opts.noinstr && sec) state->noinstr = sec->noinstr; } @@ -338,7 +341,7 @@ static void *cfi_hash_alloc(unsigned long size) if (cfi_hash == (void *)-1L) { WARN("mmap fail cfi_hash"); cfi_hash = NULL; - } else if (stats) { + } else if (opts.stats) { printf("cfi_bits: %d\n", cfi_bits); } @@ -433,7 +436,7 @@ static int decode_instructions(struct objtool_file *file) } } - if (stats) + if (opts.stats) printf("nr_insns: %lu\n", nr_insns); return 0; @@ -496,7 +499,7 @@ static int init_pv_ops(struct objtool_file *file) struct symbol *sym; int idx, nr; - if (!noinstr) + if (!opts.noinstr) return 0; file->pv_ops = NULL; @@ -559,12 +562,12 @@ static int add_dead_ends(struct objtool_file *file) else if (reloc->addend == reloc->sym->sec->sh.sh_size) { insn = find_last_insn(file, reloc->sym->sec); if (!insn) { - WARN("can't find unreachable insn at %s+0x%x", + WARN("can't find unreachable insn at %s+0x%" PRIx64, reloc->sym->sec->name, reloc->addend); return -1; } } else { - WARN("can't find unreachable insn at %s+0x%x", + WARN("can't find unreachable insn at %s+0x%" PRIx64, reloc->sym->sec->name, reloc->addend); return -1; } @@ -594,12 +597,12 @@ reachable: else if (reloc->addend == reloc->sym->sec->sh.sh_size) { insn = find_last_insn(file, reloc->sym->sec); if (!insn) { - WARN("can't find reachable insn at %s+0x%x", + WARN("can't find reachable insn at %s+0x%" PRIx64, reloc->sym->sec->name, reloc->addend); return -1; } } else { - WARN("can't find reachable insn at %s+0x%x", + WARN("can't find reachable insn at %s+0x%" PRIx64, reloc->sym->sec->name, reloc->addend); return -1; } @@ -667,7 +670,7 @@ static int create_static_call_sections(struct objtool_file *file) key_sym = find_symbol_by_name(file->elf, tmp); if (!key_sym) { - if (!module) { + if (!opts.module) { WARN("static_call: can't find static_call_key symbol: %s", tmp); return -1; } @@ -760,7 +763,7 @@ static int create_ibt_endbr_seal_sections(struct objtool_file *file) list_for_each_entry(insn, &file->endbr_list, call_node) idx++; - if (stats) { + if (opts.stats) { printf("ibt: ENDBR at function start: %d\n", file->nr_endbr); printf("ibt: ENDBR inside functions: %d\n", file->nr_endbr_int); printf("ibt: superfluous ENDBR: %d\n", idx); @@ -1027,7 +1030,7 @@ static void add_uaccess_safe(struct objtool_file *file) struct symbol *func; const char **name; - if (!uaccess) + if (!opts.uaccess) return; for (name = uaccess_safe_builtin; *name; name++) { @@ -1143,7 +1146,7 @@ static void annotate_call_site(struct objtool_file *file, * attribute so they need a little help, NOP out any such calls from * noinstr text. */ - if (insn->sec->noinstr && sym->profiling_func) { + if (opts.hack_noinstr && insn->sec->noinstr && sym->profiling_func) { if (reloc) { reloc->type = R_NONE; elf_write_reloc(file->elf, reloc); @@ -1155,10 +1158,21 @@ static void annotate_call_site(struct objtool_file *file, : arch_nop_insn(insn->len)); insn->type = sibling ? INSN_RETURN : INSN_NOP; + + if (sibling) { + /* + * We've replaced the tail-call JMP insn by two new + * insn: RET; INT3, except we only have a single struct + * insn here. Mark it retpoline_safe to avoid the SLS + * warning, instead of adding another insn. + */ + insn->retpoline_safe = true; + } + return; } - if (mcount && sym->fentry) { + if (opts.mcount && sym->fentry) { if (sibling) WARN_FUNC("Tail call to __fentry__ !?!?", insn->sec, insn->offset); @@ -1239,11 +1253,20 @@ static bool same_function(struct instruction *insn1, struct instruction *insn2) return insn1->func->pfunc == insn2->func->pfunc; } -static bool is_first_func_insn(struct instruction *insn) +static bool is_first_func_insn(struct objtool_file *file, struct instruction *insn) { - return insn->offset == insn->func->offset || - (insn->type == INSN_ENDBR && - insn->offset == insn->func->offset + insn->len); + if (insn->offset == insn->func->offset) + return true; + + if (opts.ibt) { + struct instruction *prev = prev_insn_same_sym(file, insn); + + if (prev && prev->type == INSN_ENDBR && + insn->offset == insn->func->offset + prev->len) + return true; + } + + return false; } /* @@ -1251,12 +1274,19 @@ static bool is_first_func_insn(struct instruction *insn) */ static int add_jump_destinations(struct objtool_file *file) { - struct instruction *insn; + struct instruction *insn, *jump_dest; struct reloc *reloc; struct section *dest_sec; unsigned long dest_off; for_each_insn(file, insn) { + if (insn->jump_dest) { + /* + * handle_group_alt() may have previously set + * 'jump_dest' for some alternatives. + */ + continue; + } if (!is_static_jump(insn)) continue; @@ -1271,7 +1301,10 @@ static int add_jump_destinations(struct objtool_file *file) add_retpoline_call(file, insn); continue; } else if (insn->func) { - /* internal or external sibling call (with reloc) */ + /* + * External sibling call or internal sibling call with + * STT_FUNC reloc. + */ add_call_dest(file, insn, reloc->sym, true); continue; } else if (reloc->sym->sec->idx) { @@ -1283,17 +1316,8 @@ static int add_jump_destinations(struct objtool_file *file) continue; } - insn->jump_dest = find_insn(file, dest_sec, dest_off); - if (!insn->jump_dest) { - - /* - * This is a special case where an alt instruction - * jumps past the end of the section. These are - * handled later in handle_group_alt(). - */ - if (!strcmp(insn->sec->name, ".altinstr_replacement")) - continue; - + jump_dest = find_insn(file, dest_sec, dest_off); + if (!jump_dest) { WARN_FUNC("can't find jump dest instruction at %s+0x%lx", insn->sec, insn->offset, dest_sec->name, dest_off); @@ -1303,8 +1327,8 @@ static int add_jump_destinations(struct objtool_file *file) /* * Cross-function jump. */ - if (insn->func && insn->jump_dest->func && - insn->func != insn->jump_dest->func) { + if (insn->func && jump_dest->func && + insn->func != jump_dest->func) { /* * For GCC 8+, create parent/child links for any cold @@ -1322,16 +1346,22 @@ static int add_jump_destinations(struct objtool_file *file) * subfunction is through a jump table. */ if (!strstr(insn->func->name, ".cold") && - strstr(insn->jump_dest->func->name, ".cold")) { - insn->func->cfunc = insn->jump_dest->func; - insn->jump_dest->func->pfunc = insn->func; + strstr(jump_dest->func->name, ".cold")) { + insn->func->cfunc = jump_dest->func; + jump_dest->func->pfunc = insn->func; - } else if (!same_function(insn, insn->jump_dest) && - is_first_func_insn(insn->jump_dest)) { - /* internal sibling call (without reloc) */ - add_call_dest(file, insn, insn->jump_dest->func, true); + } else if (!same_function(insn, jump_dest) && + is_first_func_insn(file, jump_dest)) { + /* + * Internal sibling call without reloc or with + * STT_SECTION reloc. + */ + add_call_dest(file, insn, jump_dest->func, true); + continue; } } + + insn->jump_dest = jump_dest; } return 0; @@ -1520,13 +1550,13 @@ static int handle_group_alt(struct objtool_file *file, continue; dest_off = arch_jump_destination(insn); - if (dest_off == special_alt->new_off + special_alt->new_len) + if (dest_off == special_alt->new_off + special_alt->new_len) { insn->jump_dest = next_insn_same_sec(file, last_orig_insn); - - if (!insn->jump_dest) { - WARN_FUNC("can't find alternative jump destination", - insn->sec, insn->offset); - return -1; + if (!insn->jump_dest) { + WARN_FUNC("can't find alternative jump destination", + insn->sec, insn->offset); + return -1; + } } } @@ -1564,7 +1594,7 @@ static int handle_jump_alt(struct objtool_file *file, return -1; } - if (special_alt->key_addend & 2) { + if (opts.hack_jump_label && special_alt->key_addend & 2) { struct reloc *reloc = insn_reloc(file, orig_insn); if (reloc) { @@ -1671,7 +1701,7 @@ static int add_special_section_alts(struct objtool_file *file) free(special_alt); } - if (stats) { + if (opts.stats) { printf("jl\\\tNOP\tJMP\n"); printf("short:\t%ld\t%ld\n", file->jl_nop_short, file->jl_short); printf("long:\t%ld\t%ld\n", file->jl_nop_long, file->jl_long); @@ -1917,7 +1947,7 @@ static int read_unwind_hints(struct objtool_file *file) insn->hint = true; - if (ibt && hint->type == UNWIND_HINT_TYPE_REGS_PARTIAL) { + if (opts.ibt && hint->type == UNWIND_HINT_TYPE_REGS_PARTIAL) { struct symbol *sym = find_symbol_by_offset(insn->sec, insn->offset); if (sym && sym->bind == STB_GLOBAL && @@ -2225,14 +2255,14 @@ static int decode_sections(struct objtool_file *file) return ret; /* - * Must be before add_special_section_alts() as that depends on - * jump_dest being set. + * Must be before add_jump_destinations(), which depends on 'func' + * being set for alternatives, to enable proper sibling call detection. */ - ret = add_jump_destinations(file); + ret = add_special_section_alts(file); if (ret) return ret; - ret = add_special_section_alts(file); + ret = add_jump_destinations(file); if (ret) return ret; @@ -2778,7 +2808,7 @@ static int update_cfi_state(struct instruction *insn, } /* detect when asm code uses rbp as a scratch register */ - if (!no_fp && insn->func && op->src.reg == CFI_BP && + if (opts.stackval && insn->func && op->src.reg == CFI_BP && cfa->base != CFI_BP) cfi->bp_scratch = true; break; @@ -3154,115 +3184,6 @@ static struct instruction *next_insn_to_validate(struct objtool_file *file, return next_insn_same_sec(file, insn); } -static struct instruction * -validate_ibt_reloc(struct objtool_file *file, struct reloc *reloc) -{ - struct instruction *dest; - struct section *sec; - unsigned long off; - - sec = reloc->sym->sec; - off = reloc->sym->offset; - - if ((reloc->sec->base->sh.sh_flags & SHF_EXECINSTR) && - (reloc->type == R_X86_64_PC32 || reloc->type == R_X86_64_PLT32)) - off += arch_dest_reloc_offset(reloc->addend); - else - off += reloc->addend; - - dest = find_insn(file, sec, off); - if (!dest) - return NULL; - - if (dest->type == INSN_ENDBR) { - if (!list_empty(&dest->call_node)) - list_del_init(&dest->call_node); - - return NULL; - } - - if (reloc->sym->static_call_tramp) - return NULL; - - return dest; -} - -static void warn_noendbr(const char *msg, struct section *sec, unsigned long offset, - struct instruction *dest) -{ - WARN_FUNC("%srelocation to !ENDBR: %s+0x%lx", sec, offset, msg, - dest->func ? dest->func->name : dest->sec->name, - dest->func ? dest->offset - dest->func->offset : dest->offset); -} - -static void validate_ibt_dest(struct objtool_file *file, struct instruction *insn, - struct instruction *dest) -{ - if (dest->func && dest->func == insn->func) { - /* - * Anything from->to self is either _THIS_IP_ or IRET-to-self. - * - * There is no sane way to annotate _THIS_IP_ since the compiler treats the - * relocation as a constant and is happy to fold in offsets, skewing any - * annotation we do, leading to vast amounts of false-positives. - * - * There's also compiler generated _THIS_IP_ through KCOV and - * such which we have no hope of annotating. - * - * As such, blanket accept self-references without issue. - */ - return; - } - - if (dest->noendbr) - return; - - warn_noendbr("", insn->sec, insn->offset, dest); -} - -static void validate_ibt_insn(struct objtool_file *file, struct instruction *insn) -{ - struct instruction *dest; - struct reloc *reloc; - - switch (insn->type) { - case INSN_CALL: - case INSN_CALL_DYNAMIC: - case INSN_JUMP_CONDITIONAL: - case INSN_JUMP_UNCONDITIONAL: - case INSN_JUMP_DYNAMIC: - case INSN_JUMP_DYNAMIC_CONDITIONAL: - case INSN_RETURN: - /* - * We're looking for code references setting up indirect code - * flow. As such, ignore direct code flow and the actual - * dynamic branches. - */ - return; - - case INSN_NOP: - /* - * handle_group_alt() will create INSN_NOP instruction that - * don't belong to any section, ignore all NOP since they won't - * carry a (useful) relocation anyway. - */ - return; - - default: - break; - } - - for (reloc = insn_reloc(file, insn); - reloc; - reloc = find_reloc_by_dest_range(file->elf, insn->sec, - reloc->offset + 1, - (insn->offset + insn->len) - (reloc->offset + 1))) { - dest = validate_ibt_reloc(file, reloc); - if (dest) - validate_ibt_dest(file, insn, dest); - } -} - /* * Follow the branch starting at the given instruction, and recursively follow * any other branches (jumps). Meanwhile, track the frame pointer state at @@ -3283,7 +3204,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, while (1) { next_insn = next_insn_to_validate(file, insn); - if (file->c_file && func && insn->func && func != insn->func->pfunc) { + if (func && insn->func && func != insn->func->pfunc) { WARN("%s() falls through to next function %s()", func->name, insn->func->name); return 1; @@ -3336,7 +3257,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, ret = validate_branch(file, func, alt->insn, state); if (ret) { - if (backtrace) + if (opts.backtrace) BT_FUNC("(alt)", insn); return ret; } @@ -3352,11 +3273,6 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, switch (insn->type) { case INSN_RETURN: - if (sls && !insn->retpoline_safe && - next_insn && next_insn->type != INSN_TRAP) { - WARN_FUNC("missing int3 after ret", - insn->sec, insn->offset); - } return validate_return(func, insn, &state); case INSN_CALL: @@ -3365,7 +3281,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, if (ret) return ret; - if (!no_fp && func && !is_fentry_call(insn) && + if (opts.stackval && func && !is_fentry_call(insn) && !has_valid_stack_frame(&state)) { WARN_FUNC("call without frame pointer save/setup", sec, insn->offset); @@ -3388,7 +3304,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, ret = validate_branch(file, func, insn->jump_dest, state); if (ret) { - if (backtrace) + if (opts.backtrace) BT_FUNC("(branch)", insn); return ret; } @@ -3400,13 +3316,6 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, break; case INSN_JUMP_DYNAMIC: - if (sls && !insn->retpoline_safe && - next_insn && next_insn->type != INSN_TRAP) { - WARN_FUNC("missing int3 after indirect jump", - insn->sec, insn->offset); - } - - /* fallthrough */ case INSN_JUMP_DYNAMIC_CONDITIONAL: if (is_sibling_call(insn)) { ret = validate_sibling_call(file, insn, &state); @@ -3472,9 +3381,6 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, break; } - if (ibt) - validate_ibt_insn(file, insn); - if (insn->dead_end) return 0; @@ -3501,7 +3407,7 @@ static int validate_unwind_hints(struct objtool_file *file, struct section *sec) if (!file->hints) return 0; - init_insn_state(&state, sec); + init_insn_state(file, &state, sec); if (sec) { insn = find_insn(file, sec, 0); @@ -3514,7 +3420,7 @@ static int validate_unwind_hints(struct objtool_file *file, struct section *sec) while (&insn->list != &file->insn_list && (!sec || insn->sec == sec)) { if (insn->hint && !insn->visited && !insn->ignore) { ret = validate_branch(file, insn->func, insn, state); - if (ret && backtrace) + if (ret && opts.backtrace) BT_FUNC("<=== (hint)", insn); warnings += ret; } @@ -3544,7 +3450,7 @@ static int validate_retpoline(struct objtool_file *file) * loaded late, they very much do need retpoline in their * .init.text */ - if (!strcmp(insn->sec->name, ".init.text") && !module) + if (!strcmp(insn->sec->name, ".init.text") && !opts.module) continue; WARN_FUNC("indirect %s found in RETPOLINE build", @@ -3587,14 +3493,14 @@ static bool ignore_unreachable_insn(struct objtool_file *file, struct instructio return true; /* - * Whole archive runs might encounder dead code from weak symbols. + * Whole archive runs might encounter dead code from weak symbols. * This is where the linker will have dropped the weak symbol in * favour of a regular symbol, but leaves the code in place. * * In this case we'll find a piece of code (whole function) that is not * covered by a !section symbol. Ignore them. */ - if (!insn->func && lto) { + if (opts.link && !insn->func) { int size = find_symbol_hole_containing(insn->sec, insn->offset); unsigned long end = insn->offset + size; @@ -3701,7 +3607,7 @@ static int validate_symbol(struct objtool_file *file, struct section *sec, state->uaccess = sym->uaccess_safe; ret = validate_branch(file, insn->func, insn, *state); - if (ret && backtrace) + if (ret && opts.backtrace) BT_FUNC("<=== (sym)", insn); return ret; } @@ -3716,7 +3622,7 @@ static int validate_section(struct objtool_file *file, struct section *sec) if (func->type != STT_FUNC) continue; - init_insn_state(&state, sec); + init_insn_state(file, &state, sec); set_func_state(&state.cfi); warnings += validate_symbol(file, sec, func, &state); @@ -3725,7 +3631,7 @@ static int validate_section(struct objtool_file *file, struct section *sec) return warnings; } -static int validate_vmlinux_functions(struct objtool_file *file) +static int validate_noinstr_sections(struct objtool_file *file) { struct section *sec; int warnings = 0; @@ -3760,51 +3666,208 @@ static int validate_functions(struct objtool_file *file) return warnings; } +static void mark_endbr_used(struct instruction *insn) +{ + if (!list_empty(&insn->call_node)) + list_del_init(&insn->call_node); +} + +static int validate_ibt_insn(struct objtool_file *file, struct instruction *insn) +{ + struct instruction *dest; + struct reloc *reloc; + unsigned long off; + int warnings = 0; + + /* + * Looking for function pointer load relocations. Ignore + * direct/indirect branches: + */ + switch (insn->type) { + case INSN_CALL: + case INSN_CALL_DYNAMIC: + case INSN_JUMP_CONDITIONAL: + case INSN_JUMP_UNCONDITIONAL: + case INSN_JUMP_DYNAMIC: + case INSN_JUMP_DYNAMIC_CONDITIONAL: + case INSN_RETURN: + case INSN_NOP: + return 0; + default: + break; + } + + for (reloc = insn_reloc(file, insn); + reloc; + reloc = find_reloc_by_dest_range(file->elf, insn->sec, + reloc->offset + 1, + (insn->offset + insn->len) - (reloc->offset + 1))) { + + /* + * static_call_update() references the trampoline, which + * doesn't have (or need) ENDBR. Skip warning in that case. + */ + if (reloc->sym->static_call_tramp) + continue; + + off = reloc->sym->offset; + if (reloc->type == R_X86_64_PC32 || reloc->type == R_X86_64_PLT32) + off += arch_dest_reloc_offset(reloc->addend); + else + off += reloc->addend; + + dest = find_insn(file, reloc->sym->sec, off); + if (!dest) + continue; + + if (dest->type == INSN_ENDBR) { + mark_endbr_used(dest); + continue; + } + + if (dest->func && dest->func == insn->func) { + /* + * Anything from->to self is either _THIS_IP_ or + * IRET-to-self. + * + * There is no sane way to annotate _THIS_IP_ since the + * compiler treats the relocation as a constant and is + * happy to fold in offsets, skewing any annotation we + * do, leading to vast amounts of false-positives. + * + * There's also compiler generated _THIS_IP_ through + * KCOV and such which we have no hope of annotating. + * + * As such, blanket accept self-references without + * issue. + */ + continue; + } + + if (dest->noendbr) + continue; + + WARN_FUNC("relocation to !ENDBR: %s", + insn->sec, insn->offset, + offstr(dest->sec, dest->offset)); + + warnings++; + } + + return warnings; +} + +static int validate_ibt_data_reloc(struct objtool_file *file, + struct reloc *reloc) +{ + struct instruction *dest; + + dest = find_insn(file, reloc->sym->sec, + reloc->sym->offset + reloc->addend); + if (!dest) + return 0; + + if (dest->type == INSN_ENDBR) { + mark_endbr_used(dest); + return 0; + } + + if (dest->noendbr) + return 0; + + WARN_FUNC("data relocation to !ENDBR: %s", + reloc->sec->base, reloc->offset, + offstr(dest->sec, dest->offset)); + + return 1; +} + +/* + * Validate IBT rules and remove used ENDBR instructions from the seal list. + * Unused ENDBR instructions will be annotated for sealing (i.e., replaced with + * NOPs) later, in create_ibt_endbr_seal_sections(). + */ static int validate_ibt(struct objtool_file *file) { struct section *sec; struct reloc *reloc; + struct instruction *insn; + int warnings = 0; + + for_each_insn(file, insn) + warnings += validate_ibt_insn(file, insn); for_each_sec(file, sec) { - bool is_data; - /* already done in validate_branch() */ + /* Already done by validate_ibt_insn() */ if (sec->sh.sh_flags & SHF_EXECINSTR) continue; if (!sec->reloc) continue; - if (!strncmp(sec->name, ".orc", 4)) + /* + * These sections can reference text addresses, but not with + * the intent to indirect branch to them. + */ + if (!strncmp(sec->name, ".discard", 8) || + !strncmp(sec->name, ".debug", 6) || + !strcmp(sec->name, ".altinstructions") || + !strcmp(sec->name, ".ibt_endbr_seal") || + !strcmp(sec->name, ".orc_unwind_ip") || + !strcmp(sec->name, ".parainstructions") || + !strcmp(sec->name, ".retpoline_sites") || + !strcmp(sec->name, ".smp_locks") || + !strcmp(sec->name, ".static_call_sites") || + !strcmp(sec->name, "_error_injection_whitelist") || + !strcmp(sec->name, "_kprobe_blacklist") || + !strcmp(sec->name, "__bug_table") || + !strcmp(sec->name, "__ex_table") || + !strcmp(sec->name, "__jump_table") || + !strcmp(sec->name, "__mcount_loc") || + !strcmp(sec->name, "__tracepoints")) continue; - if (!strncmp(sec->name, ".discard", 8)) - continue; + list_for_each_entry(reloc, &sec->reloc->reloc_list, list) + warnings += validate_ibt_data_reloc(file, reloc); + } - if (!strncmp(sec->name, ".debug", 6)) - continue; + return warnings; +} - if (!strcmp(sec->name, "_error_injection_whitelist")) - continue; +static int validate_sls(struct objtool_file *file) +{ + struct instruction *insn, *next_insn; + int warnings = 0; - if (!strcmp(sec->name, "_kprobe_blacklist")) - continue; + for_each_insn(file, insn) { + next_insn = next_insn_same_sec(file, insn); - is_data = strstr(sec->name, ".data") || strstr(sec->name, ".rodata"); + if (insn->retpoline_safe) + continue; - list_for_each_entry(reloc, &sec->reloc->reloc_list, list) { - struct instruction *dest; + switch (insn->type) { + case INSN_RETURN: + if (!next_insn || next_insn->type != INSN_TRAP) { + WARN_FUNC("missing int3 after ret", + insn->sec, insn->offset); + warnings++; + } - dest = validate_ibt_reloc(file, reloc); - if (is_data && dest && !dest->noendbr) { - warn_noendbr("data ", reloc->sym->sec, - reloc->sym->offset + reloc->addend, - dest); + break; + case INSN_JUMP_DYNAMIC: + if (!next_insn || next_insn->type != INSN_TRAP) { + WARN_FUNC("missing int3 after indirect jump", + insn->sec, insn->offset); + warnings++; } + break; + default: + break; } } - return 0; + return warnings; } static int validate_reachable_instructions(struct objtool_file *file) @@ -3829,16 +3892,6 @@ int check(struct objtool_file *file) { int ret, warnings = 0; - if (lto && !(vmlinux || module)) { - fprintf(stderr, "--lto requires: --vmlinux or --module\n"); - return 1; - } - - if (ibt && !lto) { - fprintf(stderr, "--ibt requires: --lto\n"); - return 1; - } - arch_initial_func_cfi_state(&initial_func_cfi); init_cfi_state(&init_cfi); init_cfi_state(&func_cfi); @@ -3859,73 +3912,89 @@ int check(struct objtool_file *file) if (list_empty(&file->insn_list)) goto out; - if (vmlinux && !lto) { - ret = validate_vmlinux_functions(file); + if (opts.retpoline) { + ret = validate_retpoline(file); if (ret < 0) - goto out; - + return ret; warnings += ret; - goto out; } - if (retpoline) { - ret = validate_retpoline(file); + if (opts.stackval || opts.orc || opts.uaccess) { + ret = validate_functions(file); if (ret < 0) - return ret; + goto out; warnings += ret; - } - ret = validate_functions(file); - if (ret < 0) - goto out; - warnings += ret; + ret = validate_unwind_hints(file, NULL); + if (ret < 0) + goto out; + warnings += ret; - ret = validate_unwind_hints(file, NULL); - if (ret < 0) - goto out; - warnings += ret; + if (!warnings) { + ret = validate_reachable_instructions(file); + if (ret < 0) + goto out; + warnings += ret; + } - if (ibt) { + } else if (opts.noinstr) { + ret = validate_noinstr_sections(file); + if (ret < 0) + goto out; + warnings += ret; + } + + if (opts.ibt) { ret = validate_ibt(file); if (ret < 0) goto out; warnings += ret; } - if (!warnings) { - ret = validate_reachable_instructions(file); + if (opts.sls) { + ret = validate_sls(file); if (ret < 0) goto out; warnings += ret; } - ret = create_static_call_sections(file); - if (ret < 0) - goto out; - warnings += ret; + if (opts.static_call) { + ret = create_static_call_sections(file); + if (ret < 0) + goto out; + warnings += ret; + } - if (retpoline) { + if (opts.retpoline) { ret = create_retpoline_sites_sections(file); if (ret < 0) goto out; warnings += ret; } - if (mcount) { + if (opts.mcount) { ret = create_mcount_loc_sections(file); if (ret < 0) goto out; warnings += ret; } - if (ibt) { + if (opts.ibt) { ret = create_ibt_endbr_seal_sections(file); if (ret < 0) goto out; warnings += ret; } - if (stats) { + if (opts.orc && !list_empty(&file->insn_list)) { + ret = orc_create(file); + if (ret < 0) + goto out; + warnings += ret; + } + + + if (opts.stats) { printf("nr_insns_visited: %ld\n", nr_insns_visited); printf("nr_cfi: %ld\n", nr_cfi); printf("nr_cfi_reused: %ld\n", nr_cfi_reused); diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c index d7b99a737496..c25e957c1e52 100644 --- a/tools/objtool/elf.c +++ b/tools/objtool/elf.c @@ -355,7 +355,7 @@ static int read_sections(struct elf *elf) elf_hash_add(section_name, &sec->name_hash, str_hash(sec->name)); } - if (stats) { + if (opts.stats) { printf("nr_sections: %lu\n", (unsigned long)sections_nr); printf("section_bits: %d\n", elf->section_bits); } @@ -374,9 +374,15 @@ static void elf_add_symbol(struct elf *elf, struct symbol *sym) struct list_head *entry; struct rb_node *pnode; + INIT_LIST_HEAD(&sym->pv_target); + sym->alias = sym; + sym->type = GELF_ST_TYPE(sym->sym.st_info); sym->bind = GELF_ST_BIND(sym->sym.st_info); + if (sym->type == STT_FILE) + elf->num_files++; + sym->offset = sym->sym.st_value; sym->len = sym->sym.st_size; @@ -435,8 +441,6 @@ static int read_symbols(struct elf *elf) return -1; } memset(sym, 0, sizeof(*sym)); - INIT_LIST_HEAD(&sym->pv_target); - sym->alias = sym; sym->idx = i; @@ -475,7 +479,7 @@ static int read_symbols(struct elf *elf) elf_add_symbol(elf, sym); } - if (stats) { + if (opts.stats) { printf("nr_symbols: %lu\n", (unsigned long)symbols_nr); printf("symbol_bits: %d\n", elf->symbol_bits); } @@ -546,7 +550,7 @@ static struct section *elf_create_reloc_section(struct elf *elf, int reltype); int elf_add_reloc(struct elf *elf, struct section *sec, unsigned long offset, - unsigned int type, struct symbol *sym, int addend) + unsigned int type, struct symbol *sym, s64 addend) { struct reloc *reloc; @@ -575,37 +579,239 @@ int elf_add_reloc(struct elf *elf, struct section *sec, unsigned long offset, return 0; } +/* + * Ensure that any reloc section containing references to @sym is marked + * changed such that it will get re-generated in elf_rebuild_reloc_sections() + * with the new symbol index. + */ +static void elf_dirty_reloc_sym(struct elf *elf, struct symbol *sym) +{ + struct section *sec; + + list_for_each_entry(sec, &elf->sections, list) { + struct reloc *reloc; + + if (sec->changed) + continue; + + list_for_each_entry(reloc, &sec->reloc_list, list) { + if (reloc->sym == sym) { + sec->changed = true; + break; + } + } + } +} + +/* + * The libelf API is terrible; gelf_update_sym*() takes a data block relative + * index value, *NOT* the symbol index. As such, iterate the data blocks and + * adjust index until it fits. + * + * If no data block is found, allow adding a new data block provided the index + * is only one past the end. + */ +static int elf_update_symbol(struct elf *elf, struct section *symtab, + struct section *symtab_shndx, struct symbol *sym) +{ + Elf32_Word shndx = sym->sec ? sym->sec->idx : SHN_UNDEF; + Elf_Data *symtab_data = NULL, *shndx_data = NULL; + Elf64_Xword entsize = symtab->sh.sh_entsize; + int max_idx, idx = sym->idx; + Elf_Scn *s, *t = NULL; + + s = elf_getscn(elf->elf, symtab->idx); + if (!s) { + WARN_ELF("elf_getscn"); + return -1; + } + + if (symtab_shndx) { + t = elf_getscn(elf->elf, symtab_shndx->idx); + if (!t) { + WARN_ELF("elf_getscn"); + return -1; + } + } + + for (;;) { + /* get next data descriptor for the relevant sections */ + symtab_data = elf_getdata(s, symtab_data); + if (t) + shndx_data = elf_getdata(t, shndx_data); + + /* end-of-list */ + if (!symtab_data) { + void *buf; + + if (idx) { + /* we don't do holes in symbol tables */ + WARN("index out of range"); + return -1; + } + + /* if @idx == 0, it's the next contiguous entry, create it */ + symtab_data = elf_newdata(s); + if (t) + shndx_data = elf_newdata(t); + + buf = calloc(1, entsize); + if (!buf) { + WARN("malloc"); + return -1; + } + + symtab_data->d_buf = buf; + symtab_data->d_size = entsize; + symtab_data->d_align = 1; + symtab_data->d_type = ELF_T_SYM; + + symtab->sh.sh_size += entsize; + symtab->changed = true; + + if (t) { + shndx_data->d_buf = &sym->sec->idx; + shndx_data->d_size = sizeof(Elf32_Word); + shndx_data->d_align = sizeof(Elf32_Word); + shndx_data->d_type = ELF_T_WORD; + + symtab_shndx->sh.sh_size += sizeof(Elf32_Word); + symtab_shndx->changed = true; + } + + break; + } + + /* empty blocks should not happen */ + if (!symtab_data->d_size) { + WARN("zero size data"); + return -1; + } + + /* is this the right block? */ + max_idx = symtab_data->d_size / entsize; + if (idx < max_idx) + break; + + /* adjust index and try again */ + idx -= max_idx; + } + + /* something went side-ways */ + if (idx < 0) { + WARN("negative index"); + return -1; + } + + /* setup extended section index magic and write the symbol */ + if (shndx >= SHN_UNDEF && shndx < SHN_LORESERVE) { + sym->sym.st_shndx = shndx; + if (!shndx_data) + shndx = 0; + } else { + sym->sym.st_shndx = SHN_XINDEX; + if (!shndx_data) { + WARN("no .symtab_shndx"); + return -1; + } + } + + if (!gelf_update_symshndx(symtab_data, shndx_data, idx, &sym->sym, shndx)) { + WARN_ELF("gelf_update_symshndx"); + return -1; + } + + return 0; +} + +static struct symbol * +elf_create_section_symbol(struct elf *elf, struct section *sec) +{ + struct section *symtab, *symtab_shndx; + Elf32_Word first_non_local, new_idx; + struct symbol *sym, *old; + + symtab = find_section_by_name(elf, ".symtab"); + if (symtab) { + symtab_shndx = find_section_by_name(elf, ".symtab_shndx"); + } else { + WARN("no .symtab"); + return NULL; + } + + sym = calloc(1, sizeof(*sym)); + if (!sym) { + perror("malloc"); + return NULL; + } + + sym->name = sec->name; + sym->sec = sec; + + // st_name 0 + sym->sym.st_info = GELF_ST_INFO(STB_LOCAL, STT_SECTION); + // st_other 0 + // st_value 0 + // st_size 0 + + /* + * Move the first global symbol, as per sh_info, into a new, higher + * symbol index. This fees up a spot for a new local symbol. + */ + first_non_local = symtab->sh.sh_info; + new_idx = symtab->sh.sh_size / symtab->sh.sh_entsize; + old = find_symbol_by_index(elf, first_non_local); + if (old) { + old->idx = new_idx; + + hlist_del(&old->hash); + elf_hash_add(symbol, &old->hash, old->idx); + + elf_dirty_reloc_sym(elf, old); + + if (elf_update_symbol(elf, symtab, symtab_shndx, old)) { + WARN("elf_update_symbol move"); + return NULL; + } + + new_idx = first_non_local; + } + + sym->idx = new_idx; + if (elf_update_symbol(elf, symtab, symtab_shndx, sym)) { + WARN("elf_update_symbol"); + return NULL; + } + + /* + * Either way, we added a LOCAL symbol. + */ + symtab->sh.sh_info += 1; + + elf_add_symbol(elf, sym); + + return sym; +} + int elf_add_reloc_to_insn(struct elf *elf, struct section *sec, unsigned long offset, unsigned int type, struct section *insn_sec, unsigned long insn_off) { - struct symbol *sym; - int addend; - - if (insn_sec->sym) { - sym = insn_sec->sym; - addend = insn_off; + struct symbol *sym = insn_sec->sym; + int addend = insn_off; - } else { + if (!sym) { /* - * The Clang assembler strips section symbols, so we have to - * reference the function symbol instead: + * Due to how weak functions work, we must use section based + * relocations. Symbol based relocations would result in the + * weak and non-weak function annotations being overlaid on the + * non-weak function after linking. */ - sym = find_symbol_containing(insn_sec, insn_off); - if (!sym) { - /* - * Hack alert. This happens when we need to reference - * the NOP pad insn immediately after the function. - */ - sym = find_symbol_containing(insn_sec, insn_off - 1); - } - - if (!sym) { - WARN("can't find symbol containing %s+0x%lx", insn_sec->name, insn_off); + sym = elf_create_section_symbol(elf, insn_sec); + if (!sym) return -1; - } - addend = insn_off - sym->offset; + insn_sec->sym = sym; } return elf_add_reloc(elf, sec, offset, type, sym, addend); @@ -700,7 +906,7 @@ static int read_relocs(struct elf *elf) tot_reloc += nr_reloc; } - if (stats) { + if (opts.stats) { printf("max_reloc: %lu\n", max_reloc); printf("tot_reloc: %lu\n", tot_reloc); printf("reloc_bits: %d\n", elf->reloc_bits); @@ -1079,7 +1285,7 @@ int elf_write(struct elf *elf) struct section *sec; Elf_Scn *s; - if (dryrun) + if (opts.dryrun) return 0; /* Update changed relocation sections and section headers: */ diff --git a/tools/objtool/include/objtool/builtin.h b/tools/objtool/include/objtool/builtin.h index c39dbfaef6dc..280ea18b7f2b 100644 --- a/tools/objtool/include/objtool/builtin.h +++ b/tools/objtool/include/objtool/builtin.h @@ -8,13 +8,37 @@ #include <subcmd/parse-options.h> extern const struct option check_options[]; -extern bool no_fp, no_unreachable, retpoline, module, backtrace, uaccess, stats, - lto, vmlinux, mcount, noinstr, backup, sls, dryrun, - ibt; + +struct opts { + /* actions: */ + bool dump_orc; + bool hack_jump_label; + bool hack_noinstr; + bool ibt; + bool mcount; + bool noinstr; + bool orc; + bool retpoline; + bool sls; + bool stackval; + bool static_call; + bool uaccess; + + /* options: */ + bool backtrace; + bool backup; + bool dryrun; + bool link; + bool module; + bool no_unreachable; + bool sec_address; + bool stats; +}; + +extern struct opts opts; extern int cmd_parse_options(int argc, const char **argv, const char * const usage[]); -extern int cmd_check(int argc, const char **argv); -extern int cmd_orc(int argc, const char **argv); +extern int objtool_run(int argc, const char **argv); #endif /* _BUILTIN_H */ diff --git a/tools/objtool/include/objtool/elf.h b/tools/objtool/include/objtool/elf.h index 22ba7e2b816e..adebfbc2b518 100644 --- a/tools/objtool/include/objtool/elf.h +++ b/tools/objtool/include/objtool/elf.h @@ -73,7 +73,7 @@ struct reloc { struct symbol *sym; unsigned long offset; unsigned int type; - int addend; + s64 addend; int idx; bool jump_table_start; }; @@ -86,7 +86,7 @@ struct elf { int fd; bool changed; char *name; - unsigned int text_size; + unsigned int text_size, num_files; struct list_head sections; int symbol_bits; @@ -131,11 +131,21 @@ static inline u32 reloc_hash(struct reloc *reloc) return sec_offset_hash(reloc->sec, reloc->offset); } +/* + * Try to see if it's a whole archive (vmlinux.o or module). + * + * Note this will miss the case where a module only has one source file. + */ +static inline bool has_multiple_files(struct elf *elf) +{ + return elf->num_files > 1; +} + struct elf *elf_open_read(const char *name, int flags); struct section *elf_create_section(struct elf *elf, const char *name, unsigned int sh_flags, size_t entsize, int nr); int elf_add_reloc(struct elf *elf, struct section *sec, unsigned long offset, - unsigned int type, struct symbol *sym, int addend); + unsigned int type, struct symbol *sym, s64 addend); int elf_add_reloc_to_insn(struct elf *elf, struct section *sec, unsigned long offset, unsigned int type, struct section *insn_sec, unsigned long insn_off); diff --git a/tools/objtool/include/objtool/objtool.h b/tools/objtool/include/objtool/objtool.h index 7a5c13a78f87..a6e72d916807 100644 --- a/tools/objtool/include/objtool/objtool.h +++ b/tools/objtool/include/objtool/objtool.h @@ -27,7 +27,7 @@ struct objtool_file { struct list_head static_call_list; struct list_head mcount_loc_list; struct list_head endbr_list; - bool ignore_unreachables, c_file, hints, rodata; + bool ignore_unreachables, hints, rodata; unsigned int nr_endbr; unsigned int nr_endbr_int; diff --git a/tools/objtool/include/objtool/warn.h b/tools/objtool/include/objtool/warn.h index 802cfda0a6f6..a3e79ae75f2e 100644 --- a/tools/objtool/include/objtool/warn.h +++ b/tools/objtool/include/objtool/warn.h @@ -11,34 +11,33 @@ #include <sys/types.h> #include <sys/stat.h> #include <fcntl.h> +#include <objtool/builtin.h> #include <objtool/elf.h> extern const char *objname; static inline char *offstr(struct section *sec, unsigned long offset) { - struct symbol *func; - char *name, *str; - unsigned long name_off; + bool is_text = (sec->sh.sh_flags & SHF_EXECINSTR); + struct symbol *sym = NULL; + char *str; + int len; - func = find_func_containing(sec, offset); - if (!func) - func = find_symbol_containing(sec, offset); - if (func) { - name = func->name; - name_off = offset - func->offset; + if (is_text) + sym = find_func_containing(sec, offset); + if (!sym) + sym = find_symbol_containing(sec, offset); + + if (sym) { + str = malloc(strlen(sym->name) + strlen(sec->name) + 40); + len = sprintf(str, "%s+0x%lx", sym->name, offset - sym->offset); + if (opts.sec_address) + sprintf(str+len, " (%s+0x%lx)", sec->name, offset); } else { - name = sec->name; - name_off = offset; + str = malloc(strlen(sec->name) + 20); + sprintf(str, "%s+0x%lx", sec->name, offset); } - str = malloc(strlen(name) + 20); - - if (func) - sprintf(str, "%s()+0x%lx", name, name_off); - else - sprintf(str, "%s+0x%lx", name, name_off); - return str; } diff --git a/tools/objtool/objtool.c b/tools/objtool/objtool.c index b09946f4e1d6..512669ce064c 100644 --- a/tools/objtool/objtool.c +++ b/tools/objtool/objtool.c @@ -3,16 +3,6 @@ * Copyright (C) 2015 Josh Poimboeuf <jpoimboe@redhat.com> */ -/* - * objtool: - * - * The 'check' subcmd analyzes every .o file and ensures the validity of its - * stack trace metadata. It enforces a set of rules on asm code and C inline - * assembly code so that stack traces can be reliable. - * - * For more information, see tools/objtool/Documentation/stack-validation.txt. - */ - #include <stdio.h> #include <stdbool.h> #include <string.h> @@ -26,20 +16,6 @@ #include <objtool/objtool.h> #include <objtool/warn.h> -struct cmd_struct { - const char *name; - int (*fn)(int, const char **); - const char *help; -}; - -static const char objtool_usage_string[] = - "objtool COMMAND [ARGS]"; - -static struct cmd_struct objtool_cmds[] = { - {"check", cmd_check, "Perform stack metadata validation on an object file" }, - {"orc", cmd_orc, "Generate in-place ORC unwind tables for an object file" }, -}; - bool help; const char *objname; @@ -118,7 +94,7 @@ struct objtool_file *objtool_open_read(const char *_objname) if (!file.elf) return NULL; - if (backup && !objtool_create_backup(objname)) { + if (opts.backup && !objtool_create_backup(objname)) { WARN("can't create backup file"); return NULL; } @@ -129,8 +105,7 @@ struct objtool_file *objtool_open_read(const char *_objname) INIT_LIST_HEAD(&file.static_call_list); INIT_LIST_HEAD(&file.mcount_loc_list); INIT_LIST_HEAD(&file.endbr_list); - file.c_file = !vmlinux && find_section_by_name(file.elf, ".comment"); - file.ignore_unreachables = no_unreachable; + file.ignore_unreachables = opts.no_unreachable; file.hints = false; return &file; @@ -138,7 +113,7 @@ struct objtool_file *objtool_open_read(const char *_objname) void objtool_pv_add(struct objtool_file *f, int idx, struct symbol *func) { - if (!noinstr) + if (!opts.noinstr) return; if (!f->pv_ops) { @@ -162,70 +137,6 @@ void objtool_pv_add(struct objtool_file *f, int idx, struct symbol *func) f->pv_ops[idx].clean = false; } -static void cmd_usage(void) -{ - unsigned int i, longest = 0; - - printf("\n usage: %s\n\n", objtool_usage_string); - - for (i = 0; i < ARRAY_SIZE(objtool_cmds); i++) { - if (longest < strlen(objtool_cmds[i].name)) - longest = strlen(objtool_cmds[i].name); - } - - puts(" Commands:"); - for (i = 0; i < ARRAY_SIZE(objtool_cmds); i++) { - printf(" %-*s ", longest, objtool_cmds[i].name); - puts(objtool_cmds[i].help); - } - - printf("\n"); - - if (!help) - exit(129); - exit(0); -} - -static void handle_options(int *argc, const char ***argv) -{ - while (*argc > 0) { - const char *cmd = (*argv)[0]; - - if (cmd[0] != '-') - break; - - if (!strcmp(cmd, "--help") || !strcmp(cmd, "-h")) { - help = true; - break; - } else { - fprintf(stderr, "Unknown option: %s\n", cmd); - cmd_usage(); - } - - (*argv)++; - (*argc)--; - } -} - -static void handle_internal_command(int argc, const char **argv) -{ - const char *cmd = argv[0]; - unsigned int i, ret; - - for (i = 0; i < ARRAY_SIZE(objtool_cmds); i++) { - struct cmd_struct *p = objtool_cmds+i; - - if (strcmp(p->name, cmd)) - continue; - - ret = p->fn(argc, argv); - - exit(ret); - } - - cmd_usage(); -} - int main(int argc, const char **argv) { static const char *UNUSED = "OBJTOOL_NOT_IMPLEMENTED"; @@ -234,14 +145,7 @@ int main(int argc, const char **argv) exec_cmd_init("objtool", UNUSED, UNUSED, UNUSED); pager_init(UNUSED); - argv++; - argc--; - handle_options(&argc, &argv); - - if (!argc || help) - cmd_usage(); - - handle_internal_command(argc, argv); + objtool_run(argc, argv); return 0; } diff --git a/tools/objtool/weak.c b/tools/objtool/weak.c index 8314e824db4a..d83f607733b0 100644 --- a/tools/objtool/weak.c +++ b/tools/objtool/weak.c @@ -15,17 +15,12 @@ return ENOSYS; \ }) -int __weak check(struct objtool_file *file) -{ - UNSUPPORTED("check subcommand"); -} - int __weak orc_dump(const char *_objname) { - UNSUPPORTED("orc"); + UNSUPPORTED("ORC"); } int __weak orc_create(struct objtool_file *file) { - UNSUPPORTED("orc"); + UNSUPPORTED("ORC"); } diff --git a/tools/perf/Documentation/perf.txt b/tools/perf/Documentation/perf.txt index 9c330cdfa973..71ebdf8125de 100644 --- a/tools/perf/Documentation/perf.txt +++ b/tools/perf/Documentation/perf.txt @@ -83,7 +83,7 @@ linkperf:perf-buildid-list[1], linkperf:perf-c2c[1], linkperf:perf-config[1], linkperf:perf-data[1], linkperf:perf-diff[1], linkperf:perf-evlist[1], linkperf:perf-ftrace[1], linkperf:perf-help[1], linkperf:perf-inject[1], -linkperf:perf-intel-pt[1], linkperf:perf-kallsyms[1], +linkperf:perf-intel-pt[1], linkperf:perf-iostat[1], linkperf:perf-kallsyms[1], linkperf:perf-kmem[1], linkperf:perf-kvm[1], linkperf:perf-lock[1], linkperf:perf-mem[1], linkperf:perf-probe[1], linkperf:perf-sched[1], linkperf:perf-script[1], linkperf:perf-test[1], diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 96ad944ca6a8..1bd64e7404b9 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -272,6 +272,9 @@ ifdef PYTHON_CONFIG PYTHON_EMBED_LIBADD := $(call grep-libs,$(PYTHON_EMBED_LDOPTS)) -lutil PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --includes 2>/dev/null) FLAGS_PYTHON_EMBED := $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS) + ifeq ($(CC_NO_CLANG), 0) + PYTHON_EMBED_CCOPTS := $(filter-out -ffat-lto-objects, $(PYTHON_EMBED_CCOPTS)) + endif endif FEATURE_CHECK_CFLAGS-libpython := $(PYTHON_EMBED_CCOPTS) @@ -550,9 +553,16 @@ ifndef NO_LIBELF ifeq ($(feature-libbpf), 1) EXTLIBS += -lbpf $(call detected,CONFIG_LIBBPF_DYNAMIC) + + $(call feature_check,libbpf-btf__load_from_kernel_by_id) + ifeq ($(feature-libbpf-btf__load_from_kernel_by_id), 1) + CFLAGS += -DHAVE_LIBBPF_BTF__LOAD_FROM_KERNEL_BY_ID + endif else dummy := $(error Error: No libbpf devel library found, please install libbpf-devel); endif + else + CFLAGS += -DHAVE_LIBBPF_BTF__LOAD_FROM_KERNEL_BY_ID endif endif @@ -790,6 +800,9 @@ else LDFLAGS += $(PERL_EMBED_LDFLAGS) EXTLIBS += $(PERL_EMBED_LIBADD) CFLAGS += -DHAVE_LIBPERL_SUPPORT + ifeq ($(CC_NO_CLANG), 0) + CFLAGS += -Wno-compound-token-split-by-macro + endif $(call detected,CONFIG_LIBPERL) endif endif diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c index 86e2e926aa0e..e8b577d33e53 100644 --- a/tools/perf/arch/arm64/util/arm-spe.c +++ b/tools/perf/arch/arm64/util/arm-spe.c @@ -148,6 +148,7 @@ static int arm_spe_recording_options(struct auxtrace_record *itr, bool privileged = perf_event_paranoid_check(-1); struct evsel *tracking_evsel; int err; + u64 bit; sper->evlist = evlist; @@ -239,6 +240,21 @@ static int arm_spe_recording_options(struct auxtrace_record *itr, arm_spe_set_timestamp(itr, arm_spe_evsel); } + /* + * Set this only so that perf report knows that SPE generates memory info. It has no effect + * on the opening of the event or the SPE data produced. + */ + evsel__set_sample_bit(arm_spe_evsel, DATA_SRC); + + /* + * The PHYS_ADDR flag does not affect the driver behaviour, it is used to + * inform that the resulting output's SPE samples contain physical addresses + * where applicable. + */ + bit = perf_pmu__format_bits(&arm_spe_pmu->format, "pa_enable"); + if (arm_spe_evsel->core.attr.config & bit) + evsel__set_sample_bit(arm_spe_evsel, PHYS_ADDR); + /* Add dummy event to keep tracking */ err = parse_events(evlist, "dummy:u", NULL); if (err) diff --git a/tools/perf/arch/arm64/util/machine.c b/tools/perf/arch/arm64/util/machine.c index d2ce31e28cd7..41c1596e5207 100644 --- a/tools/perf/arch/arm64/util/machine.c +++ b/tools/perf/arch/arm64/util/machine.c @@ -8,27 +8,6 @@ #include "callchain.h" #include "record.h" -/* On arm64, kernel text segment starts at high memory address, - * for example 0xffff 0000 8xxx xxxx. Modules start at a low memory - * address, like 0xffff 0000 00ax xxxx. When only small amount of - * memory is used by modules, gap between end of module's text segment - * and start of kernel text segment may reach 2G. - * Therefore do not fill this gap and do not assign it to the kernel dso map. - */ - -#define SYMBOL_LIMIT (1 << 12) /* 4K */ - -void arch__symbols__fixup_end(struct symbol *p, struct symbol *c) -{ - if ((strchr(p->name, '[') && strchr(c->name, '[') == NULL) || - (strchr(p->name, '[') == NULL && strchr(c->name, '['))) - /* Limit range of last symbol in module and kernel */ - p->end += SYMBOL_LIMIT; - else - p->end = c->start; - pr_debug4("%s sym:%s end:%#" PRIx64 "\n", __func__, p->name, p->end); -} - void arch__add_leaf_frame_record_opts(struct record_opts *opts) { opts->sample_user_regs |= sample_reg_masks[PERF_REG_ARM64_LR].mask; diff --git a/tools/perf/arch/powerpc/util/Build b/tools/perf/arch/powerpc/util/Build index 8a79c4126e5b..0115f3166568 100644 --- a/tools/perf/arch/powerpc/util/Build +++ b/tools/perf/arch/powerpc/util/Build @@ -1,5 +1,4 @@ perf-y += header.o -perf-y += machine.o perf-y += kvm-stat.o perf-y += perf_regs.o perf-y += mem-events.o diff --git a/tools/perf/arch/powerpc/util/machine.c b/tools/perf/arch/powerpc/util/machine.c deleted file mode 100644 index e652a1aa8132..000000000000 --- a/tools/perf/arch/powerpc/util/machine.c +++ /dev/null @@ -1,25 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 - -#include <inttypes.h> -#include <stdio.h> -#include <string.h> -#include <internal/lib.h> // page_size -#include "debug.h" -#include "symbol.h" - -/* On powerpc kernel text segment start at memory addresses, 0xc000000000000000 - * whereas the modules are located at very high memory addresses, - * for example 0xc00800000xxxxxxx. The gap between end of kernel text segment - * and beginning of first module's text segment is very high. - * Therefore do not fill this gap and do not assign it to the kernel dso map. - */ - -void arch__symbols__fixup_end(struct symbol *p, struct symbol *c) -{ - if (strchr(p->name, '[') == NULL && strchr(c->name, '[')) - /* Limit the range of last kernel symbol */ - p->end += page_size; - else - p->end = c->start; - pr_debug4("%s sym:%s end:%#" PRIx64 "\n", __func__, p->name, p->end); -} diff --git a/tools/perf/arch/s390/util/machine.c b/tools/perf/arch/s390/util/machine.c index 7644a4f6d4a4..98bc3f39d5f3 100644 --- a/tools/perf/arch/s390/util/machine.c +++ b/tools/perf/arch/s390/util/machine.c @@ -35,19 +35,3 @@ int arch__fix_module_text_start(u64 *start, u64 *size, const char *name) return 0; } - -/* On s390 kernel text segment start is located at very low memory addresses, - * for example 0x10000. Modules are located at very high memory addresses, - * for example 0x3ff xxxx xxxx. The gap between end of kernel text segment - * and beginning of first module's text segment is very big. - * Therefore do not fill this gap and do not assign it to the kernel dso map. - */ -void arch__symbols__fixup_end(struct symbol *p, struct symbol *c) -{ - if (strchr(p->name, '[') == NULL && strchr(c->name, '[')) - /* Last kernel symbol mapped to end of page */ - p->end = roundup(p->end, page_size); - else - p->end = c->start; - pr_debug4("%s sym:%s end:%#" PRIx64 "\n", __func__, p->name, p->end); -} diff --git a/tools/perf/arch/x86/util/perf_regs.c b/tools/perf/arch/x86/util/perf_regs.c index 207c56805c55..0ed177991ad0 100644 --- a/tools/perf/arch/x86/util/perf_regs.c +++ b/tools/perf/arch/x86/util/perf_regs.c @@ -9,6 +9,8 @@ #include "../../../util/perf_regs.h" #include "../../../util/debug.h" #include "../../../util/event.h" +#include "../../../util/pmu.h" +#include "../../../util/pmu-hybrid.h" const struct sample_reg sample_reg_masks[] = { SMPL_REG(AX, PERF_REG_X86_AX), @@ -284,12 +286,22 @@ uint64_t arch__intr_reg_mask(void) .disabled = 1, .exclude_kernel = 1, }; + struct perf_pmu *pmu; int fd; /* * In an unnamed union, init it here to build on older gcc versions */ attr.sample_period = 1; + if (perf_pmu__has_hybrid()) { + /* + * The same register set is supported among different hybrid PMUs. + * Only check the first available one. + */ + pmu = list_first_entry(&perf_pmu__hybrid_pmus, typeof(*pmu), hybrid_list); + attr.config |= (__u64)pmu->type << PERF_PMU_TYPE_SHIFT; + } + event_attr_init(&attr); fd = sys_perf_event_open(&attr, 0, -1, -1, 0); diff --git a/tools/perf/bench/epoll-ctl.c b/tools/perf/bench/epoll-ctl.c index 134612bde0cb..4256dc5d6236 100644 --- a/tools/perf/bench/epoll-ctl.c +++ b/tools/perf/bench/epoll-ctl.c @@ -222,13 +222,20 @@ static void init_fdmaps(struct worker *w, int pct) static int do_threads(struct worker *worker, struct perf_cpu_map *cpu) { pthread_attr_t thread_attr, *attrp = NULL; - cpu_set_t cpuset; + cpu_set_t *cpuset; unsigned int i, j; int ret = 0; + int nrcpus; + size_t size; if (!noaffinity) pthread_attr_init(&thread_attr); + nrcpus = perf_cpu_map__nr(cpu); + cpuset = CPU_ALLOC(nrcpus); + BUG_ON(!cpuset); + size = CPU_ALLOC_SIZE(nrcpus); + for (i = 0; i < nthreads; i++) { struct worker *w = &worker[i]; @@ -252,22 +259,28 @@ static int do_threads(struct worker *worker, struct perf_cpu_map *cpu) init_fdmaps(w, 50); if (!noaffinity) { - CPU_ZERO(&cpuset); - CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset); + CPU_ZERO_S(size, cpuset); + CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, + size, cpuset); - ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset); - if (ret) + ret = pthread_attr_setaffinity_np(&thread_attr, size, cpuset); + if (ret) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); + } attrp = &thread_attr; } ret = pthread_create(&w->thread, attrp, workerfn, (void *)(struct worker *) w); - if (ret) + if (ret) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_create"); + } } + CPU_FREE(cpuset); if (!noaffinity) pthread_attr_destroy(&thread_attr); diff --git a/tools/perf/bench/epoll-wait.c b/tools/perf/bench/epoll-wait.c index 37de970c9743..2728b0140853 100644 --- a/tools/perf/bench/epoll-wait.c +++ b/tools/perf/bench/epoll-wait.c @@ -291,9 +291,11 @@ static void print_summary(void) static int do_threads(struct worker *worker, struct perf_cpu_map *cpu) { pthread_attr_t thread_attr, *attrp = NULL; - cpu_set_t cpuset; + cpu_set_t *cpuset; unsigned int i, j; int ret = 0, events = EPOLLIN; + int nrcpus; + size_t size; if (oneshot) events |= EPOLLONESHOT; @@ -306,6 +308,11 @@ static int do_threads(struct worker *worker, struct perf_cpu_map *cpu) if (!noaffinity) pthread_attr_init(&thread_attr); + nrcpus = perf_cpu_map__nr(cpu); + cpuset = CPU_ALLOC(nrcpus); + BUG_ON(!cpuset); + size = CPU_ALLOC_SIZE(nrcpus); + for (i = 0; i < nthreads; i++) { struct worker *w = &worker[i]; @@ -341,22 +348,28 @@ static int do_threads(struct worker *worker, struct perf_cpu_map *cpu) } if (!noaffinity) { - CPU_ZERO(&cpuset); - CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset); + CPU_ZERO_S(size, cpuset); + CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, + size, cpuset); - ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset); - if (ret) + ret = pthread_attr_setaffinity_np(&thread_attr, size, cpuset); + if (ret) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); + } attrp = &thread_attr; } ret = pthread_create(&w->thread, attrp, workerfn, (void *)(struct worker *) w); - if (ret) + if (ret) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_create"); + } } + CPU_FREE(cpuset); if (!noaffinity) pthread_attr_destroy(&thread_attr); diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c index dbcecec4eeda..f05db4cf983d 100644 --- a/tools/perf/bench/futex-hash.c +++ b/tools/perf/bench/futex-hash.c @@ -122,12 +122,14 @@ static void print_summary(void) int bench_futex_hash(int argc, const char **argv) { int ret = 0; - cpu_set_t cpuset; + cpu_set_t *cpuset; struct sigaction act; unsigned int i; pthread_attr_t thread_attr; struct worker *worker = NULL; struct perf_cpu_map *cpu; + int nrcpus; + size_t size; argc = parse_options(argc, argv, options, bench_futex_hash_usage, 0); if (argc) { @@ -170,25 +172,35 @@ int bench_futex_hash(int argc, const char **argv) threads_starting = params.nthreads; pthread_attr_init(&thread_attr); gettimeofday(&bench__start, NULL); + + nrcpus = perf_cpu_map__nr(cpu); + cpuset = CPU_ALLOC(nrcpus); + BUG_ON(!cpuset); + size = CPU_ALLOC_SIZE(nrcpus); + for (i = 0; i < params.nthreads; i++) { worker[i].tid = i; worker[i].futex = calloc(params.nfutexes, sizeof(*worker[i].futex)); if (!worker[i].futex) goto errmem; - CPU_ZERO(&cpuset); - CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset); + CPU_ZERO_S(size, cpuset); - ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset); - if (ret) + CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, size, cpuset); + ret = pthread_attr_setaffinity_np(&thread_attr, size, cpuset); + if (ret) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); - + } ret = pthread_create(&worker[i].thread, &thread_attr, workerfn, (void *)(struct worker *) &worker[i]); - if (ret) + if (ret) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_create"); + } } + CPU_FREE(cpuset); pthread_attr_destroy(&thread_attr); pthread_mutex_lock(&thread_lock); diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c index 6fc9a3d55c1f..0abb3f7ee24f 100644 --- a/tools/perf/bench/futex-lock-pi.c +++ b/tools/perf/bench/futex-lock-pi.c @@ -120,11 +120,17 @@ static void *workerfn(void *arg) static void create_threads(struct worker *w, pthread_attr_t thread_attr, struct perf_cpu_map *cpu) { - cpu_set_t cpuset; + cpu_set_t *cpuset; unsigned int i; + int nrcpus = perf_cpu_map__nr(cpu); + size_t size; threads_starting = params.nthreads; + cpuset = CPU_ALLOC(nrcpus); + BUG_ON(!cpuset); + size = CPU_ALLOC_SIZE(nrcpus); + for (i = 0; i < params.nthreads; i++) { worker[i].tid = i; @@ -135,15 +141,20 @@ static void create_threads(struct worker *w, pthread_attr_t thread_attr, } else worker[i].futex = &global_futex; - CPU_ZERO(&cpuset); - CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset); + CPU_ZERO_S(size, cpuset); + CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, size, cpuset); - if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset)) + if (pthread_attr_setaffinity_np(&thread_attr, size, cpuset)) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); + } - if (pthread_create(&w[i].thread, &thread_attr, workerfn, &worker[i])) + if (pthread_create(&w[i].thread, &thread_attr, workerfn, &worker[i])) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_create"); + } } + CPU_FREE(cpuset); } int bench_futex_lock_pi(int argc, const char **argv) diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c index 2f59d5d1c509..b6faabfafb8e 100644 --- a/tools/perf/bench/futex-requeue.c +++ b/tools/perf/bench/futex-requeue.c @@ -123,22 +123,33 @@ static void *workerfn(void *arg __maybe_unused) static void block_threads(pthread_t *w, pthread_attr_t thread_attr, struct perf_cpu_map *cpu) { - cpu_set_t cpuset; + cpu_set_t *cpuset; unsigned int i; + int nrcpus = perf_cpu_map__nr(cpu); + size_t size; threads_starting = params.nthreads; + cpuset = CPU_ALLOC(nrcpus); + BUG_ON(!cpuset); + size = CPU_ALLOC_SIZE(nrcpus); + /* create and block all threads */ for (i = 0; i < params.nthreads; i++) { - CPU_ZERO(&cpuset); - CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset); + CPU_ZERO_S(size, cpuset); + CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, size, cpuset); - if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset)) + if (pthread_attr_setaffinity_np(&thread_attr, size, cpuset)) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); + } - if (pthread_create(&w[i], &thread_attr, workerfn, NULL)) + if (pthread_create(&w[i], &thread_attr, workerfn, NULL)) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_create"); + } } + CPU_FREE(cpuset); } static void toggle_done(int sig __maybe_unused, diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c index 861deb934745..e47f46a3a47e 100644 --- a/tools/perf/bench/futex-wake-parallel.c +++ b/tools/perf/bench/futex-wake-parallel.c @@ -144,22 +144,33 @@ static void *blocked_workerfn(void *arg __maybe_unused) static void block_threads(pthread_t *w, pthread_attr_t thread_attr, struct perf_cpu_map *cpu) { - cpu_set_t cpuset; + cpu_set_t *cpuset; unsigned int i; + int nrcpus = perf_cpu_map__nr(cpu); + size_t size; threads_starting = params.nthreads; + cpuset = CPU_ALLOC(nrcpus); + BUG_ON(!cpuset); + size = CPU_ALLOC_SIZE(nrcpus); + /* create and block all threads */ for (i = 0; i < params.nthreads; i++) { - CPU_ZERO(&cpuset); - CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset); + CPU_ZERO_S(size, cpuset); + CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, size, cpuset); - if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset)) + if (pthread_attr_setaffinity_np(&thread_attr, size, cpuset)) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); + } - if (pthread_create(&w[i], &thread_attr, blocked_workerfn, NULL)) + if (pthread_create(&w[i], &thread_attr, blocked_workerfn, NULL)) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_create"); + } } + CPU_FREE(cpuset); } static void print_run(struct thread_data *waking_worker, unsigned int run_num) diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c index cfda48bef1d7..201a3555f09a 100644 --- a/tools/perf/bench/futex-wake.c +++ b/tools/perf/bench/futex-wake.c @@ -97,22 +97,32 @@ static void print_summary(void) static void block_threads(pthread_t *w, pthread_attr_t thread_attr, struct perf_cpu_map *cpu) { - cpu_set_t cpuset; + cpu_set_t *cpuset; unsigned int i; - + size_t size; + int nrcpus = perf_cpu_map__nr(cpu); threads_starting = params.nthreads; + cpuset = CPU_ALLOC(nrcpus); + BUG_ON(!cpuset); + size = CPU_ALLOC_SIZE(nrcpus); + /* create and block all threads */ for (i = 0; i < params.nthreads; i++) { - CPU_ZERO(&cpuset); - CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset); + CPU_ZERO_S(size, cpuset); + CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, size, cpuset); - if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset)) + if (pthread_attr_setaffinity_np(&thread_attr, size, cpuset)) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); + } - if (pthread_create(&w[i], &thread_attr, workerfn, NULL)) + if (pthread_create(&w[i], &thread_attr, workerfn, NULL)) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_create"); + } } + CPU_FREE(cpuset); } static void toggle_done(int sig __maybe_unused, diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c index f2640179ada9..20eed1e53f80 100644 --- a/tools/perf/bench/numa.c +++ b/tools/perf/bench/numa.c @@ -34,6 +34,7 @@ #include <linux/numa.h> #include <linux/zalloc.h> +#include "../util/header.h" #include <numa.h> #include <numaif.h> @@ -54,7 +55,7 @@ struct thread_data { int curr_cpu; - cpu_set_t bind_cpumask; + cpu_set_t *bind_cpumask; int bind_node; u8 *process_data; int process_nr; @@ -266,71 +267,117 @@ static bool node_has_cpus(int node) return ret; } -static cpu_set_t bind_to_cpu(int target_cpu) +static cpu_set_t *bind_to_cpu(int target_cpu) { - cpu_set_t orig_mask, mask; - int ret; + int nrcpus = numa_num_possible_cpus(); + cpu_set_t *orig_mask, *mask; + size_t size; - ret = sched_getaffinity(0, sizeof(orig_mask), &orig_mask); - BUG_ON(ret); + orig_mask = CPU_ALLOC(nrcpus); + BUG_ON(!orig_mask); + size = CPU_ALLOC_SIZE(nrcpus); + CPU_ZERO_S(size, orig_mask); + + if (sched_getaffinity(0, size, orig_mask)) + goto err_out; - CPU_ZERO(&mask); + mask = CPU_ALLOC(nrcpus); + if (!mask) + goto err_out; + + CPU_ZERO_S(size, mask); if (target_cpu == -1) { int cpu; for (cpu = 0; cpu < g->p.nr_cpus; cpu++) - CPU_SET(cpu, &mask); + CPU_SET_S(cpu, size, mask); } else { - BUG_ON(target_cpu < 0 || target_cpu >= g->p.nr_cpus); - CPU_SET(target_cpu, &mask); + if (target_cpu < 0 || target_cpu >= g->p.nr_cpus) + goto err; + + CPU_SET_S(target_cpu, size, mask); } - ret = sched_setaffinity(0, sizeof(mask), &mask); - BUG_ON(ret); + if (sched_setaffinity(0, size, mask)) + goto err; return orig_mask; + +err: + CPU_FREE(mask); +err_out: + CPU_FREE(orig_mask); + + /* BUG_ON due to failure in allocation of orig_mask/mask */ + BUG_ON(-1); + return NULL; } -static cpu_set_t bind_to_node(int target_node) +static cpu_set_t *bind_to_node(int target_node) { - cpu_set_t orig_mask, mask; + int nrcpus = numa_num_possible_cpus(); + size_t size; + cpu_set_t *orig_mask, *mask; int cpu; - int ret; - ret = sched_getaffinity(0, sizeof(orig_mask), &orig_mask); - BUG_ON(ret); + orig_mask = CPU_ALLOC(nrcpus); + BUG_ON(!orig_mask); + size = CPU_ALLOC_SIZE(nrcpus); + CPU_ZERO_S(size, orig_mask); - CPU_ZERO(&mask); + if (sched_getaffinity(0, size, orig_mask)) + goto err_out; + + mask = CPU_ALLOC(nrcpus); + if (!mask) + goto err_out; + + CPU_ZERO_S(size, mask); if (target_node == NUMA_NO_NODE) { for (cpu = 0; cpu < g->p.nr_cpus; cpu++) - CPU_SET(cpu, &mask); + CPU_SET_S(cpu, size, mask); } else { struct bitmask *cpumask = numa_allocate_cpumask(); - BUG_ON(!cpumask); + if (!cpumask) + goto err; + if (!numa_node_to_cpus(target_node, cpumask)) { for (cpu = 0; cpu < (int)cpumask->size; cpu++) { if (numa_bitmask_isbitset(cpumask, cpu)) - CPU_SET(cpu, &mask); + CPU_SET_S(cpu, size, mask); } } numa_free_cpumask(cpumask); } - ret = sched_setaffinity(0, sizeof(mask), &mask); - BUG_ON(ret); + if (sched_setaffinity(0, size, mask)) + goto err; return orig_mask; + +err: + CPU_FREE(mask); +err_out: + CPU_FREE(orig_mask); + + /* BUG_ON due to failure in allocation of orig_mask/mask */ + BUG_ON(-1); + return NULL; } -static void bind_to_cpumask(cpu_set_t mask) +static void bind_to_cpumask(cpu_set_t *mask) { int ret; + size_t size = CPU_ALLOC_SIZE(numa_num_possible_cpus()); - ret = sched_setaffinity(0, sizeof(mask), &mask); - BUG_ON(ret); + ret = sched_setaffinity(0, size, mask); + if (ret) { + CPU_FREE(mask); + BUG_ON(ret); + } } static void mempol_restore(void) @@ -376,7 +423,7 @@ do { \ static u8 *alloc_data(ssize_t bytes0, int map_flags, int init_zero, int init_cpu0, int thp, int init_random) { - cpu_set_t orig_mask; + cpu_set_t *orig_mask = NULL; ssize_t bytes; u8 *buf; int ret; @@ -434,6 +481,7 @@ static u8 *alloc_data(ssize_t bytes0, int map_flags, /* Restore affinity: */ if (init_cpu0) { bind_to_cpumask(orig_mask); + CPU_FREE(orig_mask); mempol_restore(); } @@ -585,10 +633,16 @@ static int parse_setup_cpu_list(void) return -1; } + if (is_cpu_online(bind_cpu_0) != 1 || is_cpu_online(bind_cpu_1) != 1) { + printf("\nTest not applicable, bind_cpu_0 or bind_cpu_1 is offline\n"); + return -1; + } + BUG_ON(bind_cpu_0 < 0 || bind_cpu_1 < 0); BUG_ON(bind_cpu_0 > bind_cpu_1); for (bind_cpu = bind_cpu_0; bind_cpu <= bind_cpu_1; bind_cpu += step) { + size_t size = CPU_ALLOC_SIZE(g->p.nr_cpus); int i; for (i = 0; i < mul; i++) { @@ -608,10 +662,15 @@ static int parse_setup_cpu_list(void) tprintf("%2d", bind_cpu); } - CPU_ZERO(&td->bind_cpumask); + td->bind_cpumask = CPU_ALLOC(g->p.nr_cpus); + BUG_ON(!td->bind_cpumask); + CPU_ZERO_S(size, td->bind_cpumask); for (cpu = bind_cpu; cpu < bind_cpu+bind_len; cpu++) { - BUG_ON(cpu < 0 || cpu >= g->p.nr_cpus); - CPU_SET(cpu, &td->bind_cpumask); + if (cpu < 0 || cpu >= g->p.nr_cpus) { + CPU_FREE(td->bind_cpumask); + BUG_ON(-1); + } + CPU_SET_S(cpu, size, td->bind_cpumask); } t++; } @@ -752,8 +811,6 @@ static int parse_nodes_opt(const struct option *opt __maybe_unused, return parse_node_list(arg); } -#define BIT(x) (1ul << x) - static inline uint32_t lfsr_32(uint32_t lfsr) { const uint32_t taps = BIT(1) | BIT(5) | BIT(6) | BIT(31); @@ -1241,7 +1298,7 @@ static void *worker_thread(void *__tdata) * by migrating to CPU#0: */ if (first_task && g->p.perturb_secs && (int)(stop.tv_sec - last_perturbance) >= g->p.perturb_secs) { - cpu_set_t orig_mask; + cpu_set_t *orig_mask; int target_cpu; int this_cpu; @@ -1265,6 +1322,7 @@ static void *worker_thread(void *__tdata) printf(" (injecting perturbalance, moved to CPU#%d)\n", target_cpu); bind_to_cpumask(orig_mask); + CPU_FREE(orig_mask); } if (details >= 3) { @@ -1398,21 +1456,31 @@ static void init_thread_data(void) for (t = 0; t < g->p.nr_tasks; t++) { struct thread_data *td = g->threads + t; + size_t cpuset_size = CPU_ALLOC_SIZE(g->p.nr_cpus); int cpu; /* Allow all nodes by default: */ td->bind_node = NUMA_NO_NODE; /* Allow all CPUs by default: */ - CPU_ZERO(&td->bind_cpumask); + td->bind_cpumask = CPU_ALLOC(g->p.nr_cpus); + BUG_ON(!td->bind_cpumask); + CPU_ZERO_S(cpuset_size, td->bind_cpumask); for (cpu = 0; cpu < g->p.nr_cpus; cpu++) - CPU_SET(cpu, &td->bind_cpumask); + CPU_SET_S(cpu, cpuset_size, td->bind_cpumask); } } static void deinit_thread_data(void) { ssize_t size = sizeof(*g->threads)*g->p.nr_tasks; + int t; + + /* Free the bind_cpumask allocated for thread_data */ + for (t = 0; t < g->p.nr_tasks; t++) { + struct thread_data *td = g->threads + t; + CPU_FREE(td->bind_cpumask); + } free_data(g->threads, size); } @@ -1672,7 +1740,7 @@ static int __bench_numa(const char *name) "GB/sec,", "total-speed", "GB/sec total speed"); if (g->p.show_details >= 2) { - char tname[14 + 2 * 10 + 1]; + char tname[14 + 2 * 11 + 1]; struct thread_data *td; for (p = 0; p < g->p.nr_proc; p++) { for (t = 0; t < g->p.nr_threads; t++) { diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index ba74fab02e62..069825c48d40 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -989,8 +989,11 @@ static int record__thread_data_init_maps(struct record_thread *thread_data, stru struct mmap *overwrite_mmap = evlist->overwrite_mmap; struct perf_cpu_map *cpus = evlist->core.user_requested_cpus; - thread_data->nr_mmaps = bitmap_weight(thread_data->mask->maps.bits, - thread_data->mask->maps.nbits); + if (cpu_map__is_dummy(cpus)) + thread_data->nr_mmaps = nr_mmaps; + else + thread_data->nr_mmaps = bitmap_weight(thread_data->mask->maps.bits, + thread_data->mask->maps.nbits); if (mmap) { thread_data->maps = zalloc(thread_data->nr_mmaps * sizeof(struct mmap *)); if (!thread_data->maps) @@ -1007,16 +1010,17 @@ static int record__thread_data_init_maps(struct record_thread *thread_data, stru thread_data->nr_mmaps, thread_data->maps, thread_data->overwrite_maps); for (m = 0, tm = 0; m < nr_mmaps && tm < thread_data->nr_mmaps; m++) { - if (test_bit(cpus->map[m].cpu, thread_data->mask->maps.bits)) { + if (cpu_map__is_dummy(cpus) || + test_bit(cpus->map[m].cpu, thread_data->mask->maps.bits)) { if (thread_data->maps) { thread_data->maps[tm] = &mmap[m]; pr_debug2("thread_data[%p]: cpu%d: maps[%d] -> mmap[%d]\n", - thread_data, cpus->map[m].cpu, tm, m); + thread_data, perf_cpu_map__cpu(cpus, m).cpu, tm, m); } if (thread_data->overwrite_maps) { thread_data->overwrite_maps[tm] = &overwrite_mmap[m]; pr_debug2("thread_data[%p]: cpu%d: ow_maps[%d] -> ow_mmap[%d]\n", - thread_data, cpus->map[m].cpu, tm, m); + thread_data, perf_cpu_map__cpu(cpus, m).cpu, tm, m); } tm++; } @@ -3329,6 +3333,9 @@ static void record__mmap_cpu_mask_init(struct mmap_cpu_mask *mask, struct perf_c { int c; + if (cpu_map__is_dummy(cpus)) + return; + for (c = 0; c < cpus->nr; c++) set_bit(cpus->map[c].cpu, mask->bits); } @@ -3680,6 +3687,11 @@ static int record__init_thread_masks(struct record *rec) if (!record__threads_enabled(rec)) return record__init_thread_default_masks(rec, cpus); + if (cpu_map__is_dummy(cpus)) { + pr_err("--per-thread option is mutually exclusive to parallel streaming mode.\n"); + return -EINVAL; + } + switch (rec->opts.threads_spec) { case THREAD_SPEC__CPU: ret = record__init_thread_cpu_masks(rec, cpus); diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 1ad75c7ba074..afe4a5539ecc 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -353,6 +353,7 @@ static int report__setup_sample_type(struct report *rep) struct perf_session *session = rep->session; u64 sample_type = evlist__combined_sample_type(session->evlist); bool is_pipe = perf_data__is_pipe(session->data); + struct evsel *evsel; if (session->itrace_synth_opts->callchain || session->itrace_synth_opts->add_callchain || @@ -407,6 +408,19 @@ static int report__setup_sample_type(struct report *rep) } if (sort__mode == SORT_MODE__MEMORY) { + /* + * FIXUP: prior to kernel 5.18, Arm SPE missed to set + * PERF_SAMPLE_DATA_SRC bit in sample type. For backward + * compatibility, set the bit if it's an old perf data file. + */ + evlist__for_each_entry(session->evlist, evsel) { + if (strstr(evsel->name, "arm_spe") && + !(sample_type & PERF_SAMPLE_DATA_SRC)) { + evsel->core.attr.sample_type |= PERF_SAMPLE_DATA_SRC; + sample_type |= PERF_SAMPLE_DATA_SRC; + } + } + if (!is_pipe && !(sample_type & PERF_SAMPLE_DATA_SRC)) { ui__error("Selected --mem-mode but no mem data. " "Did you call perf record without -d?\n"); diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index a2f117936188..cf5eab5431b4 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -461,7 +461,7 @@ static int evsel__check_attr(struct evsel *evsel, struct perf_session *session) return -EINVAL; if (PRINT_FIELD(DATA_SRC) && - evsel__check_stype(evsel, PERF_SAMPLE_DATA_SRC, "DATA_SRC", PERF_OUTPUT_DATA_SRC)) + evsel__do_check_stype(evsel, PERF_SAMPLE_DATA_SRC, "DATA_SRC", PERF_OUTPUT_DATA_SRC, allow_user_set)) return -EINVAL; if (PRINT_FIELD(WEIGHT) && diff --git a/tools/perf/perf.c b/tools/perf/perf.c index 2f6b67189b42..0170cb0819d6 100644 --- a/tools/perf/perf.c +++ b/tools/perf/perf.c @@ -55,6 +55,7 @@ struct cmd_struct { }; static struct cmd_struct commands[] = { + { "archive", NULL, 0 }, { "buildid-cache", cmd_buildid_cache, 0 }, { "buildid-list", cmd_buildid_list, 0 }, { "config", cmd_config, 0 }, @@ -62,6 +63,7 @@ static struct cmd_struct commands[] = { { "diff", cmd_diff, 0 }, { "evlist", cmd_evlist, 0 }, { "help", cmd_help, 0 }, + { "iostat", NULL, 0 }, { "kallsyms", cmd_kallsyms, 0 }, { "list", cmd_list, 0 }, { "record", cmd_record, 0 }, @@ -360,6 +362,8 @@ static void handle_internal_command(int argc, const char **argv) for (i = 0; i < ARRAY_SIZE(commands); i++) { struct cmd_struct *p = commands+i; + if (p->fn == NULL) + continue; if (strcmp(p->cmd, cmd)) continue; exit(run_builtin(p, argc, argv)); @@ -434,7 +438,7 @@ void pthread__unblock_sigwinch(void) static int libperf_print(enum libperf_print_level level, const char *fmt, va_list ap) { - return eprintf(level, verbose, fmt, ap); + return veprintf(level, verbose, fmt, ap); } int main(int argc, const char **argv) diff --git a/tools/perf/tests/attr/README b/tools/perf/tests/attr/README index 454505d343fa..eb3f7d4bb324 100644 --- a/tools/perf/tests/attr/README +++ b/tools/perf/tests/attr/README @@ -60,6 +60,7 @@ Following tests are defined (with perf commands): perf record -R kill (test-record-raw) perf record -c 2 -e arm_spe_0// -- kill (test-record-spe-period) perf record -e arm_spe_0/period=3/ -- kill (test-record-spe-period-term) + perf record -e arm_spe_0/pa_enable=1/ -- kill (test-record-spe-physical-address) perf stat -e cycles kill (test-stat-basic) perf stat kill (test-stat-default) perf stat -d kill (test-stat-detailed-1) diff --git a/tools/perf/tests/attr/test-record-spe-physical-address b/tools/perf/tests/attr/test-record-spe-physical-address new file mode 100644 index 000000000000..7ebcf5012ce3 --- /dev/null +++ b/tools/perf/tests/attr/test-record-spe-physical-address @@ -0,0 +1,12 @@ +[config] +command = record +args = --no-bpf-event -e arm_spe_0/pa_enable=1/ -- kill >/dev/null 2>&1 +ret = 1 +arch = aarch64 + +[event-10:base-record-spe] +# 622727 is the decimal of IP|TID|TIME|CPU|IDENTIFIER|DATA_SRC|PHYS_ADDR +sample_type=622727 + +# dummy event +[event-1:base-record-spe] \ No newline at end of file diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c index 57b9591f7cbb..17c023823713 100644 --- a/tools/perf/tests/bpf.c +++ b/tools/perf/tests/bpf.c @@ -222,11 +222,11 @@ static int __test__bpf(int idx) ret = test_llvm__fetch_bpf_obj(&obj_buf, &obj_buf_sz, bpf_testcase_table[idx].prog_id, - true, NULL); + false, NULL); if (ret != TEST_OK || !obj_buf || !obj_buf_sz) { pr_debug("Unable to get BPF object, %s\n", bpf_testcase_table[idx].msg_compile_fail); - if (idx == 0) + if ((idx == 0) || (ret == TEST_SKIP)) return TEST_SKIP; else return TEST_FAIL; @@ -364,9 +364,11 @@ static int test__bpf_prologue_test(struct test_suite *test __maybe_unused, static struct test_case bpf_tests[] = { #ifdef HAVE_LIBBPF_SUPPORT TEST_CASE("Basic BPF filtering", basic_bpf_test), - TEST_CASE("BPF pinning", bpf_pinning), + TEST_CASE_REASON("BPF pinning", bpf_pinning, + "clang isn't installed or environment missing BPF support"), #ifdef HAVE_BPF_PROLOGUE - TEST_CASE("BPF prologue generation", bpf_prologue_test), + TEST_CASE_REASON("BPF prologue generation", bpf_prologue_test, + "clang isn't installed or environment missing BPF support"), #else TEST_CASE_REASON("BPF prologue generation", bpf_prologue_test, "not compiled in"), #endif diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c index fac3717d9ba1..d336cda94a11 100644 --- a/tools/perf/tests/builtin-test.c +++ b/tools/perf/tests/builtin-test.c @@ -279,6 +279,7 @@ static const char *shell_test__description(char *description, size_t size, { FILE *fp; char filename[PATH_MAX]; + int ch; path__join(filename, sizeof(filename), path, name); fp = fopen(filename, "r"); @@ -286,7 +287,9 @@ static const char *shell_test__description(char *description, size_t size, return NULL; /* Skip shebang */ - while (fgetc(fp) != '\n'); + do { + ch = fgetc(fp); + } while (ch != EOF && ch != '\n'); description = fgets(description, size, fp); fclose(fp); @@ -417,7 +420,8 @@ static int run_shell_tests(int argc, const char *argv[], int i, int width, .priv = &st, }; - if (!perf_test__matches(test_suite.desc, curr, argc, argv)) + if (test_suite.desc == NULL || + !perf_test__matches(test_suite.desc, curr, argc, argv)) continue; st.file = ent->d_name; diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c index 2dab2d262060..afdca7f2959f 100644 --- a/tools/perf/tests/dwarf-unwind.c +++ b/tools/perf/tests/dwarf-unwind.c @@ -122,7 +122,7 @@ NO_TAIL_CALL_ATTRIBUTE noinline int test_dwarf_unwind__thread(struct thread *thr } err = unwind__get_entries(unwind_entry, &cnt, thread, - &sample, MAX_STACK); + &sample, MAX_STACK, false); if (err) pr_debug("unwind failed\n"); else if (cnt != MAX_STACK) { diff --git a/tools/perf/tests/perf-time-to-tsc.c b/tools/perf/tests/perf-time-to-tsc.c index d12d0ad81801..4ad0dfbc8b21 100644 --- a/tools/perf/tests/perf-time-to-tsc.c +++ b/tools/perf/tests/perf-time-to-tsc.c @@ -47,6 +47,17 @@ } \ } +static int test__tsc_is_supported(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) +{ + if (!TSC_IS_SUPPORTED) { + pr_debug("Test not supported on this architecture\n"); + return TEST_SKIP; + } + + return TEST_OK; +} + /** * test__perf_time_to_tsc - test converting perf time to TSC. * @@ -70,7 +81,7 @@ static int test__perf_time_to_tsc(struct test_suite *test __maybe_unused, int su struct perf_cpu_map *cpus = NULL; struct evlist *evlist = NULL; struct evsel *evsel = NULL; - int err = -1, ret, i; + int err = TEST_FAIL, ret, i; const char *comm1, *comm2; struct perf_tsc_conversion tc; struct perf_event_mmap_page *pc; @@ -79,10 +90,6 @@ static int test__perf_time_to_tsc(struct test_suite *test __maybe_unused, int su u64 test_time, comm1_time = 0, comm2_time = 0; struct mmap *md; - if (!TSC_IS_SUPPORTED) { - pr_debug("Test not supported on this architecture"); - return TEST_SKIP; - } threads = thread_map__new(-1, getpid(), UINT_MAX); CHECK_NOT_NULL__(threads); @@ -116,6 +123,10 @@ static int test__perf_time_to_tsc(struct test_suite *test __maybe_unused, int su evsel->core.attr.enable_on_exec = 0; } + if (evlist__open(evlist) == -ENOENT) { + err = TEST_SKIP; + goto out_err; + } CHECK__(evlist__open(evlist)); CHECK__(evlist__mmap(evlist, UINT_MAX)); @@ -124,8 +135,8 @@ static int test__perf_time_to_tsc(struct test_suite *test __maybe_unused, int su ret = perf_read_tsc_conversion(pc, &tc); if (ret) { if (ret == -EOPNOTSUPP) { - fprintf(stderr, " (not supported)"); - return 0; + pr_debug("perf_read_tsc_conversion is not supported in current kernel\n"); + err = TEST_SKIP; } goto out_err; } @@ -191,7 +202,7 @@ next_event: test_tsc >= comm2_tsc) goto out_err; - err = 0; + err = TEST_OK; out_err: evlist__delete(evlist); @@ -200,4 +211,15 @@ out_err: return err; } -DEFINE_SUITE("Convert perf time to TSC", perf_time_to_tsc); +static struct test_case time_to_tsc_tests[] = { + TEST_CASE_REASON("TSC support", tsc_is_supported, + "This architecture does not support"), + TEST_CASE_REASON("Perf time to TSC", perf_time_to_tsc, + "perf_read_tsc_conversion is not supported"), + { .name = NULL, } +}; + +struct test_suite suite__perf_time_to_tsc = { + .desc = "Convert perf time to TSC", + .test_cases = time_to_tsc_tests, +}; diff --git a/tools/perf/tests/shell/stat_all_pmu.sh b/tools/perf/tests/shell/stat_all_pmu.sh index b30dba455f36..9c9ef33e0b3c 100755 --- a/tools/perf/tests/shell/stat_all_pmu.sh +++ b/tools/perf/tests/shell/stat_all_pmu.sh @@ -5,6 +5,16 @@ set -e for p in $(perf list --raw-dump pmu); do + # In powerpc, skip the events for hv_24x7 and hv_gpci. + # These events needs input values to be filled in for + # core, chip, partition id based on system. + # Example: hv_24x7/CPM_ADJUNCT_INST,domain=?,core=?/ + # hv_gpci/event,partition_id=?/ + # Hence skip these events for ppc. + if echo "$p" |grep -Eq 'hv_24x7|hv_gpci' ; then + echo "Skipping: Event '$p' in powerpc" + continue + fi echo "Testing $p" result=$(perf stat -e "$p" true 2>&1) if ! echo "$result" | grep -q "$p" && ! echo "$result" | grep -q "<not supported>" ; then diff --git a/tools/perf/tests/shell/test_arm_coresight.sh b/tools/perf/tests/shell/test_arm_coresight.sh index 6de53b7ef5ff..e4cb4f1806ff 100755 --- a/tools/perf/tests/shell/test_arm_coresight.sh +++ b/tools/perf/tests/shell/test_arm_coresight.sh @@ -29,7 +29,6 @@ cleanup_files() rm -f ${file} rm -f "${perfdata}.old" trap - exit term int - kill -2 $$ exit $glb_err } diff --git a/tools/perf/tests/topology.c b/tools/perf/tests/topology.c index ee1e3dcbc0bd..d23a9e322ff5 100644 --- a/tools/perf/tests/topology.c +++ b/tools/perf/tests/topology.c @@ -109,6 +109,17 @@ static int check_cpu_topology(char *path, struct perf_cpu_map *map) && strncmp(session->header.env.arch, "aarch64", 7)) return TEST_SKIP; + /* + * In powerpc pSeries platform, not all the topology information + * are exposed via sysfs. Due to restriction, detail like + * physical_package_id will be set to -1. Hence skip this + * test if physical_package_id returns -1 for cpu from perf_cpu_map. + */ + if (strncmp(session->header.env.arch, "powerpc", 7)) { + if (cpu__get_socket_id(perf_cpu_map__cpu(map, 0)) == -1) + return TEST_SKIP; + } + TEST_ASSERT_VAL("Session header CPU map not set", session->header.env.cpu); for (i = 0; i < session->header.env.nr_cpus_avail; i++) { diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index e4c641b240df..82cc396ef516 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -2047,6 +2047,7 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args) objdump_process.argv = objdump_argv; objdump_process.out = -1; objdump_process.err = -1; + objdump_process.no_stderr = 1; if (start_command(&objdump_process)) { pr_err("Failure starting to run %s\n", command); err = -1; diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c index d2b64e3f588b..1a80151baed9 100644 --- a/tools/perf/util/arm-spe.c +++ b/tools/perf/util/arm-spe.c @@ -1033,10 +1033,11 @@ arm_spe_synth_events(struct arm_spe *spe, struct perf_session *session) memset(&attr, 0, sizeof(struct perf_event_attr)); attr.size = sizeof(struct perf_event_attr); attr.type = PERF_TYPE_HARDWARE; - attr.sample_type = evsel->core.attr.sample_type & PERF_SAMPLE_MASK; + attr.sample_type = evsel->core.attr.sample_type & + (PERF_SAMPLE_MASK | PERF_SAMPLE_PHYS_ADDR); attr.sample_type |= PERF_SAMPLE_IP | PERF_SAMPLE_TID | PERF_SAMPLE_PERIOD | PERF_SAMPLE_DATA_SRC | - PERF_SAMPLE_WEIGHT; + PERF_SAMPLE_WEIGHT | PERF_SAMPLE_ADDR; if (spe->timeless_decoding) attr.sample_type &= ~(u64)PERF_SAMPLE_TIME; else diff --git a/tools/perf/util/arm64-frame-pointer-unwind-support.c b/tools/perf/util/arm64-frame-pointer-unwind-support.c index 2242a885fbd7..4940be4a0569 100644 --- a/tools/perf/util/arm64-frame-pointer-unwind-support.c +++ b/tools/perf/util/arm64-frame-pointer-unwind-support.c @@ -53,7 +53,7 @@ u64 get_leaf_frame_caller_aarch64(struct perf_sample *sample, struct thread *thr sample->user_regs.cache_regs[PERF_REG_ARM64_SP] = 0; } - ret = unwind__get_entries(add_entry, &entries, thread, sample, 2); + ret = unwind__get_entries(add_entry, &entries, thread, sample, 2, true); sample->user_regs = old_regs; if (ret || entries.length != 2) diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c index 94624733af7e..8271ab764eb5 100644 --- a/tools/perf/util/bpf-event.c +++ b/tools/perf/util/bpf-event.c @@ -22,7 +22,8 @@ #include "record.h" #include "util/synthetic-events.h" -struct btf * __weak btf__load_from_kernel_by_id(__u32 id) +#ifndef HAVE_LIBBPF_BTF__LOAD_FROM_KERNEL_BY_ID +struct btf *btf__load_from_kernel_by_id(__u32 id) { struct btf *btf; #pragma GCC diagnostic push @@ -32,6 +33,7 @@ struct btf * __weak btf__load_from_kernel_by_id(__u32 id) return err ? ERR_PTR(err) : btf; } +#endif int __weak bpf_prog_load(enum bpf_prog_type prog_type, const char *prog_name __maybe_unused, diff --git a/tools/perf/util/c++/clang.cpp b/tools/perf/util/c++/clang.cpp index df7b18fb6b6e..1aad7d6d34aa 100644 --- a/tools/perf/util/c++/clang.cpp +++ b/tools/perf/util/c++/clang.cpp @@ -20,7 +20,11 @@ #include "llvm/Option/Option.h" #include "llvm/Support/FileSystem.h" #include "llvm/Support/ManagedStatic.h" +#if CLANG_VERSION_MAJOR >= 14 +#include "llvm/MC/TargetRegistry.h" +#else #include "llvm/Support/TargetRegistry.h" +#endif #include "llvm/Support/TargetSelect.h" #include "llvm/Target/TargetMachine.h" #include "llvm/Target/TargetOptions.h" diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index d546ff724dbe..a27132e5a5ef 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -983,6 +983,57 @@ static int write_dir_format(struct feat_fd *ff, return do_write(ff, &data->dir.version, sizeof(data->dir.version)); } +/* + * Check whether a CPU is online + * + * Returns: + * 1 -> if CPU is online + * 0 -> if CPU is offline + * -1 -> error case + */ +int is_cpu_online(unsigned int cpu) +{ + char *str; + size_t strlen; + char buf[256]; + int status = -1; + struct stat statbuf; + + snprintf(buf, sizeof(buf), + "/sys/devices/system/cpu/cpu%d", cpu); + if (stat(buf, &statbuf) != 0) + return 0; + + /* + * Check if /sys/devices/system/cpu/cpux/online file + * exists. Some cases cpu0 won't have online file since + * it is not expected to be turned off generally. + * In kernels without CONFIG_HOTPLUG_CPU, this + * file won't exist + */ + snprintf(buf, sizeof(buf), + "/sys/devices/system/cpu/cpu%d/online", cpu); + if (stat(buf, &statbuf) != 0) + return 1; + + /* + * Read online file using sysfs__read_str. + * If read or open fails, return -1. + * If read succeeds, return value from file + * which gets stored in "str" + */ + snprintf(buf, sizeof(buf), + "devices/system/cpu/cpu%d/online", cpu); + + if (sysfs__read_str(buf, &str, &strlen) < 0) + return status; + + status = atoi(str); + + free(str); + return status; +} + #ifdef HAVE_LIBBPF_SUPPORT static int write_bpf_prog_info(struct feat_fd *ff, struct evlist *evlist __maybe_unused) diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h index c9e3265832d9..0eb4bc29a5a4 100644 --- a/tools/perf/util/header.h +++ b/tools/perf/util/header.h @@ -158,6 +158,7 @@ int do_write(struct feat_fd *fd, const void *buf, size_t size); int write_padded(struct feat_fd *fd, const void *bf, size_t count, size_t count_aligned); +int is_cpu_online(unsigned int cpu); /* * arch specific callback */ diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index b80048546451..95391236f5f6 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -2987,7 +2987,7 @@ static int thread__resolve_callchain_unwind(struct thread *thread, return 0; return unwind__get_entries(unwind_entry, cursor, - thread, sample, max_stack); + thread, sample, max_stack, false); } int thread__resolve_callchain(struct thread *thread, diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 24997925ae00..dd84fed698a3 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -1523,7 +1523,9 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, bool use_uncore_alias; LIST_HEAD(config_terms); - if (verbose > 1) { + pmu = parse_state->fake_pmu ?: perf_pmu__find(name); + + if (verbose > 1 && !(pmu && pmu->selectable)) { fprintf(stderr, "Attempting to add event pmu '%s' with '", name); if (head_config) { @@ -1536,7 +1538,6 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, fprintf(stderr, "' that may result in non-fatal errors\n"); } - pmu = parse_state->fake_pmu ?: perf_pmu__find(name); if (!pmu) { char *err_str; diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 3b8dfe603e50..a7f93f5a1ac8 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -1151,9 +1151,20 @@ static void branch_stack__printf(struct perf_sample *sample, bool callstack) struct branch_entry *entries = perf_sample__branch_entries(sample); uint64_t i; - printf("%s: nr:%" PRIu64 "\n", - !callstack ? "... branch stack" : "... branch callstack", - sample->branch_stack->nr); + if (!callstack) { + printf("%s: nr:%" PRIu64 "\n", "... branch stack", sample->branch_stack->nr); + } else { + /* the reason of adding 1 to nr is because after expanding + * branch stack it generates nr + 1 callstack records. e.g., + * B()->C() + * A()->B() + * the final callstack should be: + * C() + * B() + * A() + */ + printf("%s: nr:%" PRIu64 "\n", "... branch callstack", sample->branch_stack->nr+1); + } for (i = 0; i < sample->branch_stack->nr; i++) { struct branch_entry *e = &entries[i]; @@ -1169,8 +1180,13 @@ static void branch_stack__printf(struct perf_sample *sample, bool callstack) (unsigned)e->flags.reserved, e->flags.type ? branch_type_name(e->flags.type) : ""); } else { - printf("..... %2"PRIu64": %016" PRIx64 "\n", - i, i > 0 ? e->from : e->to); + if (i == 0) { + printf("..... %2"PRIu64": %016" PRIx64 "\n" + "..... %2"PRIu64": %016" PRIx64 "\n", + i, e->to, i+1, e->from); + } else { + printf("..... %2"PRIu64": %016" PRIx64 "\n", i+1, e->from); + } } } } @@ -2095,6 +2111,7 @@ prefetch_event(char *buf, u64 head, size_t mmap_size, bool needs_swap, union perf_event *error) { union perf_event *event; + u16 event_size; /* * Ensure we have enough space remaining to read @@ -2107,15 +2124,23 @@ prefetch_event(char *buf, u64 head, size_t mmap_size, if (needs_swap) perf_event_header__bswap(&event->header); - if (head + event->header.size <= mmap_size) + event_size = event->header.size; + if (head + event_size <= mmap_size) return event; /* We're not fetching the event so swap back again */ if (needs_swap) perf_event_header__bswap(&event->header); - pr_debug("%s: head=%#" PRIx64 " event->header_size=%#x, mmap_size=%#zx:" - " fuzzed or compressed perf.data?\n",__func__, head, event->header.size, mmap_size); + /* Check if the event fits into the next mmapped buf. */ + if (event_size <= mmap_size - head % page_size) { + /* Remap buf and fetch again. */ + return NULL; + } + + /* Invalid input. Event size should never exceed mmap_size. */ + pr_debug("%s: head=%#" PRIx64 " event->header.size=%#x, mmap_size=%#zx:" + " fuzzed or compressed perf.data?\n", __func__, head, event_size, mmap_size); return error; } @@ -2567,7 +2592,7 @@ int perf_session__process_events(struct perf_session *session) if (perf_data__is_pipe(session->data)) return __perf_session__process_pipe_events(session); - if (perf_data__is_dir(session->data)) + if (perf_data__is_dir(session->data) && session->data->dir.nr) return __perf_session__process_dir_events(session); return __perf_session__process_events(session); diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py index 483f05004e68..c255a2c90cd6 100644 --- a/tools/perf/util/setup.py +++ b/tools/perf/util/setup.py @@ -1,12 +1,14 @@ -from os import getenv +from os import getenv, path from subprocess import Popen, PIPE from re import sub cc = getenv("CC") cc_is_clang = b"clang version" in Popen([cc.split()[0], "-v"], stderr=PIPE).stderr.readline() +src_feature_tests = getenv('srctree') + '/tools/build/feature' def clang_has_option(option): - return [o for o in Popen([cc, option], stderr=PIPE).stderr.readlines() if b"unknown argument" in o] == [ ] + cc_output = Popen([cc, option, path.join(src_feature_tests, "test-hello.c") ], stderr=PIPE).stderr.readlines() + return [o for o in cc_output if ((b"unknown argument" in o) or (b"is not supported" in o))] == [ ] if cc_is_clang: from distutils.sysconfig import get_config_vars @@ -23,6 +25,8 @@ if cc_is_clang: vars[var] = sub("-fstack-protector-strong", "", vars[var]) if not clang_has_option("-fno-semantic-interposition"): vars[var] = sub("-fno-semantic-interposition", "", vars[var]) + if not clang_has_option("-ffat-lto-objects"): + vars[var] = sub("-ffat-lto-objects", "", vars[var]) from distutils.core import setup, Extension diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index ee6f03481215..c1af37e11f98 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <errno.h> +#include <linux/err.h> #include <inttypes.h> #include <math.h> #include <string.h> @@ -311,7 +312,7 @@ static int check_per_pkg(struct evsel *counter, struct perf_counts_values *vals, if (!mask) { mask = hashmap__new(pkg_id_hash, pkg_id_equal, NULL); - if (!mask) + if (IS_ERR(mask)) return -ENOMEM; counter->per_pkg_mask = mask; @@ -471,9 +472,10 @@ int perf_stat_process_counter(struct perf_stat_config *config, int perf_event__process_stat_event(struct perf_session *session, union perf_event *event) { - struct perf_counts_values count; + struct perf_counts_values count, *ptr; struct perf_record_stat *st = &event->stat; struct evsel *counter; + int cpu_map_idx; count.val = st->val; count.ena = st->ena; @@ -484,8 +486,18 @@ int perf_event__process_stat_event(struct perf_session *session, pr_err("Failed to resolve counter for stat event.\n"); return -EINVAL; } - - *perf_counts(counter->counts, st->cpu, st->thread) = count; + cpu_map_idx = perf_cpu_map__idx(evsel__cpus(counter), (struct perf_cpu){.cpu = st->cpu}); + if (cpu_map_idx == -1) { + pr_err("Invalid CPU %d for event %s.\n", st->cpu, evsel__name(counter)); + return -EINVAL; + } + ptr = perf_counts(counter->counts, cpu_map_idx, st->thread); + if (ptr == NULL) { + pr_err("Failed to find perf count for CPU %d thread %d on event %s.\n", + st->cpu, st->thread, evsel__name(counter)); + return -EINVAL; + } + *ptr = count; counter->supported = true; return 0; } diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 31cd59a2b66e..ecd377938eea 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -1290,7 +1290,7 @@ dso__load_sym_internal(struct dso *dso, struct map *map, struct symsrc *syms_ss, * For misannotated, zeroed, ASM function sizes. */ if (nr > 0) { - symbols__fixup_end(&dso->symbols); + symbols__fixup_end(&dso->symbols, false); symbols__fixup_duplicate(&dso->symbols); if (kmap) { /* diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index dea0fc495185..f72baf636724 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -101,11 +101,6 @@ static int prefix_underscores_count(const char *str) return tail - str; } -void __weak arch__symbols__fixup_end(struct symbol *p, struct symbol *c) -{ - p->end = c->start; -} - const char * __weak arch__normalize_symbol_name(const char *name) { return name; @@ -217,7 +212,8 @@ again: } } -void symbols__fixup_end(struct rb_root_cached *symbols) +/* Update zero-sized symbols using the address of the next symbol */ +void symbols__fixup_end(struct rb_root_cached *symbols, bool is_kallsyms) { struct rb_node *nd, *prevnd = rb_first_cached(symbols); struct symbol *curr, *prev; @@ -231,8 +227,29 @@ void symbols__fixup_end(struct rb_root_cached *symbols) prev = curr; curr = rb_entry(nd, struct symbol, rb_node); - if (prev->end == prev->start || prev->end != curr->start) - arch__symbols__fixup_end(prev, curr); + /* + * On some architecture kernel text segment start is located at + * some low memory address, while modules are located at high + * memory addresses (or vice versa). The gap between end of + * kernel text segment and beginning of first module's text + * segment is very big. Therefore do not fill this gap and do + * not assign it to the kernel dso map (kallsyms). + * + * In kallsyms, it determines module symbols using '[' character + * like in: + * ffffffffc1937000 T hdmi_driver_init [snd_hda_codec_hdmi] + */ + if (prev->end == prev->start) { + /* Last kernel/module symbol mapped to end of page */ + if (is_kallsyms && (!strchr(prev->name, '[') != + !strchr(curr->name, '['))) + prev->end = roundup(prev->end + 4096, 4096); + else + prev->end = curr->start; + + pr_debug4("%s sym:%s end:%#" PRIx64 "\n", + __func__, prev->name, prev->end); + } } /* Last entry */ @@ -1467,7 +1484,7 @@ int __dso__load_kallsyms(struct dso *dso, const char *filename, if (kallsyms__delta(kmap, filename, &delta)) return -1; - symbols__fixup_end(&dso->symbols); + symbols__fixup_end(&dso->symbols, true); symbols__fixup_duplicate(&dso->symbols); if (dso->kernel == DSO_SPACE__KERNEL_GUEST) @@ -1659,7 +1676,7 @@ int dso__load_bfd_symbols(struct dso *dso, const char *debugfile) #undef bfd_asymbol_section #endif - symbols__fixup_end(&dso->symbols); + symbols__fixup_end(&dso->symbols, false); symbols__fixup_duplicate(&dso->symbols); dso->adjust_symbols = 1; diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index fbf866d82dcc..0b893dcc8ea6 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -203,7 +203,7 @@ void __symbols__insert(struct rb_root_cached *symbols, struct symbol *sym, bool kernel); void symbols__insert(struct rb_root_cached *symbols, struct symbol *sym); void symbols__fixup_duplicate(struct rb_root_cached *symbols); -void symbols__fixup_end(struct rb_root_cached *symbols); +void symbols__fixup_end(struct rb_root_cached *symbols, bool is_kallsyms); void maps__fixup_end(struct maps *maps); typedef int (*mapfn_t)(u64 start, u64 len, u64 pgoff, void *data); @@ -241,7 +241,6 @@ const char *arch__normalize_symbol_name(const char *name); #define SYMBOL_A 0 #define SYMBOL_B 1 -void arch__symbols__fixup_end(struct symbol *p, struct symbol *c); int arch__compare_symbol_names(const char *namea, const char *nameb); int arch__compare_symbol_names_n(const char *namea, const char *nameb, unsigned int n); diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c index a74b517f7497..94aa40f6e348 100644 --- a/tools/perf/util/unwind-libdw.c +++ b/tools/perf/util/unwind-libdw.c @@ -200,7 +200,8 @@ frame_callback(Dwfl_Frame *state, void *arg) bool isactivation; if (!dwfl_frame_pc(state, &pc, NULL)) { - pr_err("%s", dwfl_errmsg(-1)); + if (!ui->best_effort) + pr_err("%s", dwfl_errmsg(-1)); return DWARF_CB_ABORT; } @@ -208,7 +209,8 @@ frame_callback(Dwfl_Frame *state, void *arg) report_module(pc, ui); if (!dwfl_frame_pc(state, &pc, &isactivation)) { - pr_err("%s", dwfl_errmsg(-1)); + if (!ui->best_effort) + pr_err("%s", dwfl_errmsg(-1)); return DWARF_CB_ABORT; } @@ -222,7 +224,8 @@ frame_callback(Dwfl_Frame *state, void *arg) int unwind__get_entries(unwind_entry_cb_t cb, void *arg, struct thread *thread, struct perf_sample *data, - int max_stack) + int max_stack, + bool best_effort) { struct unwind_info *ui, ui_buf = { .sample = data, @@ -231,6 +234,7 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg, .cb = cb, .arg = arg, .max_stack = max_stack, + .best_effort = best_effort }; Dwarf_Word ip; int err = -EINVAL, i; diff --git a/tools/perf/util/unwind-libdw.h b/tools/perf/util/unwind-libdw.h index 0cbd2650e280..8c88bc4f2304 100644 --- a/tools/perf/util/unwind-libdw.h +++ b/tools/perf/util/unwind-libdw.h @@ -20,6 +20,7 @@ struct unwind_info { void *arg; int max_stack; int idx; + bool best_effort; struct unwind_entry entries[]; }; diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c index 71a353349181..41e29fc7648a 100644 --- a/tools/perf/util/unwind-libunwind-local.c +++ b/tools/perf/util/unwind-libunwind-local.c @@ -96,6 +96,7 @@ struct unwind_info { struct perf_sample *sample; struct machine *machine; struct thread *thread; + bool best_effort; }; #define dw_read(ptr, type, end) ({ \ @@ -553,7 +554,8 @@ static int access_reg(unw_addr_space_t __maybe_unused as, ret = perf_reg_value(&val, &ui->sample->user_regs, id); if (ret) { - pr_err("unwind: can't read reg %d\n", regnum); + if (!ui->best_effort) + pr_err("unwind: can't read reg %d\n", regnum); return ret; } @@ -666,7 +668,7 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb, return -1; ret = unw_init_remote(&c, addr_space, ui); - if (ret) + if (ret && !ui->best_effort) display_error(ret); while (!ret && (unw_step(&c) > 0) && i < max_stack) { @@ -704,12 +706,14 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb, static int _unwind__get_entries(unwind_entry_cb_t cb, void *arg, struct thread *thread, - struct perf_sample *data, int max_stack) + struct perf_sample *data, int max_stack, + bool best_effort) { struct unwind_info ui = { .sample = data, .thread = thread, .machine = thread->maps->machine, + .best_effort = best_effort }; if (!data->user_regs.regs) diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c index e89a5479b361..509c287ee762 100644 --- a/tools/perf/util/unwind-libunwind.c +++ b/tools/perf/util/unwind-libunwind.c @@ -80,9 +80,11 @@ void unwind__finish_access(struct maps *maps) int unwind__get_entries(unwind_entry_cb_t cb, void *arg, struct thread *thread, - struct perf_sample *data, int max_stack) + struct perf_sample *data, int max_stack, + bool best_effort) { if (thread->maps->unwind_libunwind_ops) - return thread->maps->unwind_libunwind_ops->get_entries(cb, arg, thread, data, max_stack); + return thread->maps->unwind_libunwind_ops->get_entries(cb, arg, thread, data, + max_stack, best_effort); return 0; } diff --git a/tools/perf/util/unwind.h b/tools/perf/util/unwind.h index ab8ad469c8de..b2a03fa5289b 100644 --- a/tools/perf/util/unwind.h +++ b/tools/perf/util/unwind.h @@ -23,13 +23,19 @@ struct unwind_libunwind_ops { void (*finish_access)(struct maps *maps); int (*get_entries)(unwind_entry_cb_t cb, void *arg, struct thread *thread, - struct perf_sample *data, int max_stack); + struct perf_sample *data, int max_stack, bool best_effort); }; #ifdef HAVE_DWARF_UNWIND_SUPPORT +/* + * When best_effort is set, don't report errors and fail silently. This could + * be expanded in the future to be more permissive about things other than + * error messages. + */ int unwind__get_entries(unwind_entry_cb_t cb, void *arg, struct thread *thread, - struct perf_sample *data, int max_stack); + struct perf_sample *data, int max_stack, + bool best_effort); /* libunwind specific */ #ifdef HAVE_LIBUNWIND_SUPPORT #ifndef LIBUNWIND__ARCH_REG_ID @@ -65,7 +71,8 @@ unwind__get_entries(unwind_entry_cb_t cb __maybe_unused, void *arg __maybe_unused, struct thread *thread __maybe_unused, struct perf_sample *data __maybe_unused, - int max_stack __maybe_unused) + int max_stack __maybe_unused, + bool best_effort __maybe_unused) { return 0; } diff --git a/tools/power/acpi/common/cmfsize.c b/tools/power/acpi/common/cmfsize.c index 185b8c588e1d..38f9b9da8170 100644 --- a/tools/power/acpi/common/cmfsize.c +++ b/tools/power/acpi/common/cmfsize.c @@ -3,7 +3,7 @@ * * Module Name: cmfsize - Common get file size function * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/tools/power/acpi/common/getopt.c b/tools/power/acpi/common/getopt.c index 3c265bc917a1..96fd6cec78e2 100644 --- a/tools/power/acpi/common/getopt.c +++ b/tools/power/acpi/common/getopt.c @@ -3,7 +3,7 @@ * * Module Name: getopt * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c b/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c index ccabdbaae6a4..bd08f36df4a7 100644 --- a/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c +++ b/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c @@ -3,7 +3,7 @@ * * Module Name: oslinuxtbl - Linux OSL for obtaining ACPI tables * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/tools/power/acpi/os_specific/service_layers/osunixdir.c b/tools/power/acpi/os_specific/service_layers/osunixdir.c index edd99274cd12..5107892d054b 100644 --- a/tools/power/acpi/os_specific/service_layers/osunixdir.c +++ b/tools/power/acpi/os_specific/service_layers/osunixdir.c @@ -3,7 +3,7 @@ * * Module Name: osunixdir - Unix directory access interfaces * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/tools/power/acpi/os_specific/service_layers/osunixmap.c b/tools/power/acpi/os_specific/service_layers/osunixmap.c index fee0022560d5..6ff4edd8dc3b 100644 --- a/tools/power/acpi/os_specific/service_layers/osunixmap.c +++ b/tools/power/acpi/os_specific/service_layers/osunixmap.c @@ -3,7 +3,7 @@ * * Module Name: osunixmap - Unix OSL for file mappings * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/tools/power/acpi/os_specific/service_layers/osunixxf.c b/tools/power/acpi/os_specific/service_layers/osunixxf.c index 0861728da562..b3651a04d68c 100644 --- a/tools/power/acpi/os_specific/service_layers/osunixxf.c +++ b/tools/power/acpi/os_specific/service_layers/osunixxf.c @@ -3,7 +3,7 @@ * * Module Name: osunixxf - UNIX OSL interfaces * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/tools/power/acpi/tools/acpidump/acpidump.h b/tools/power/acpi/tools/acpidump/acpidump.h index e0ebc1dab1cc..153249c87fd7 100644 --- a/tools/power/acpi/tools/acpidump/acpidump.h +++ b/tools/power/acpi/tools/acpidump/acpidump.h @@ -3,7 +3,7 @@ * * Module Name: acpidump.h - Include file for acpi_dump utility * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/tools/power/acpi/tools/acpidump/apdump.c b/tools/power/acpi/tools/acpidump/apdump.c index 444e3d78bd89..d54dde02b87d 100644 --- a/tools/power/acpi/tools/acpidump/apdump.c +++ b/tools/power/acpi/tools/acpidump/apdump.c @@ -3,7 +3,7 @@ * * Module Name: apdump - Dump routines for ACPI tables (acpidump) * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/tools/power/acpi/tools/acpidump/apfiles.c b/tools/power/acpi/tools/acpidump/apfiles.c index da0c6e13042b..2d9b45a9b526 100644 --- a/tools/power/acpi/tools/acpidump/apfiles.c +++ b/tools/power/acpi/tools/acpidump/apfiles.c @@ -3,7 +3,7 @@ * * Module Name: apfiles - File-related functions for acpidump utility * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/tools/power/acpi/tools/acpidump/apmain.c b/tools/power/acpi/tools/acpidump/apmain.c index a4cf6042fcfd..44b23fc53dd9 100644 --- a/tools/power/acpi/tools/acpidump/apmain.c +++ b/tools/power/acpi/tools/acpidump/apmain.c @@ -3,7 +3,7 @@ * * Module Name: apmain - Main module for the acpidump utility * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/tools/power/x86/intel-speed-select/Makefile b/tools/power/x86/intel-speed-select/Makefile index 846f785e278d..7221f2f55e8b 100644 --- a/tools/power/x86/intel-speed-select/Makefile +++ b/tools/power/x86/intel-speed-select/Makefile @@ -42,7 +42,7 @@ ISST_IN := $(OUTPUT)intel-speed-select-in.o $(ISST_IN): prepare FORCE $(Q)$(MAKE) $(build)=intel-speed-select $(OUTPUT)intel-speed-select: $(ISST_IN) - $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $< -o $@ + $(QUIET_LINK)$(CC) $(CFLAGS) $< $(LDFLAGS) -o $@ clean: rm -f $(ALL_PROGRAMS) diff --git a/tools/power/x86/intel-speed-select/hfi-events.c b/tools/power/x86/intel-speed-select/hfi-events.c index e85676711372..761375062505 100644 --- a/tools/power/x86/intel-speed-select/hfi-events.c +++ b/tools/power/x86/intel-speed-select/hfi-events.c @@ -190,7 +190,7 @@ static int handle_event(struct nl_msg *n, void *arg) struct genlmsghdr *genlhdr = genlmsg_hdr(nlh); struct nlattr *attrs[THERMAL_GENL_ATTR_MAX + 1]; int ret; - struct perf_cap perf_cap; + struct perf_cap perf_cap = {0}; ret = genlmsg_parse(nlh, 0, attrs, THERMAL_GENL_ATTR_MAX, NULL); diff --git a/tools/power/x86/intel-speed-select/isst-config.c b/tools/power/x86/intel-speed-select/isst-config.c index 060390e88e37..9d35614995ee 100644 --- a/tools/power/x86/intel-speed-select/isst-config.c +++ b/tools/power/x86/intel-speed-select/isst-config.c @@ -1892,6 +1892,12 @@ static void set_fact_for_cpu(int cpu, void *arg1, void *arg2, void *arg3, int ret; int status = *(int *)arg4; + if (status && no_turbo()) { + isst_display_error_info_message(1, "Turbo mode is disabled", 0, 0); + ret = -1; + goto disp_results; + } + ret = isst_get_ctdp_levels(cpu, &pkg_dev); if (ret) { isst_display_error_info_message(1, "Failed to get number of levels", 0, 0); diff --git a/tools/power/x86/turbostat/Makefile b/tools/power/x86/turbostat/Makefile index f3e3c94ab9bd..92e139b9c792 100644 --- a/tools/power/x86/turbostat/Makefile +++ b/tools/power/x86/turbostat/Makefile @@ -9,7 +9,7 @@ ifeq ("$(origin O)", "command line") endif turbostat : turbostat.c -override CFLAGS += -O2 -Wall -I../../../include +override CFLAGS += -O2 -Wall -Wextra -I../../../include override CFLAGS += -DMSRHEADER='"../../../../arch/x86/include/asm/msr-index.h"' override CFLAGS += -DINTEL_FAMILY_HEADER='"../../../../arch/x86/include/asm/intel-family.h"' override CFLAGS += -D_FILE_OFFSET_BITS=64 diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8 index 9b17097bc3d7..1e7d3de55a94 100644 --- a/tools/power/x86/turbostat/turbostat.8 +++ b/tools/power/x86/turbostat/turbostat.8 @@ -292,7 +292,7 @@ starts a new interval. must be run as root. Alternatively, non-root users can be enabled to run turbostat this way: -# setcap cap_sys_rawio=ep ./turbostat +# setcap cap_sys_admin,cap_sys_rawio,cap_sys_nice=+ep ./turbostat # chmod +r /dev/cpu/*/msr diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index bc5ae0872fed..ede31a4287a0 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -3,7 +3,7 @@ * turbostat -- show CPU frequency and C-state residency * on modern Intel and AMD processors. * - * Copyright (c) 2021 Intel Corporation. + * Copyright (c) 2022 Intel Corporation. * Len Brown <len.brown@intel.com> */ @@ -37,6 +37,171 @@ #include <asm/unistd.h> #include <stdbool.h> +#define UNUSED(x) (void)(x) + +/* + * This list matches the column headers, except + * 1. built-in only, the sysfs counters are not here -- we learn of those at run-time + * 2. Core and CPU are moved to the end, we can't have strings that contain them + * matching on them for --show and --hide. + */ + +/* + * buffer size used by sscanf() for added column names + * Usually truncated to 7 characters, but also handles 18 columns for raw 64-bit counters + */ +#define NAME_BYTES 20 +#define PATH_BYTES 128 + +enum counter_scope { SCOPE_CPU, SCOPE_CORE, SCOPE_PACKAGE }; +enum counter_type { COUNTER_ITEMS, COUNTER_CYCLES, COUNTER_SECONDS, COUNTER_USEC }; +enum counter_format { FORMAT_RAW, FORMAT_DELTA, FORMAT_PERCENT }; + +struct msr_counter { + unsigned int msr_num; + char name[NAME_BYTES]; + char path[PATH_BYTES]; + unsigned int width; + enum counter_type type; + enum counter_format format; + struct msr_counter *next; + unsigned int flags; +#define FLAGS_HIDE (1 << 0) +#define FLAGS_SHOW (1 << 1) +#define SYSFS_PERCPU (1 << 1) +}; + +struct msr_counter bic[] = { + { 0x0, "usec", "", 0, 0, 0, NULL, 0 }, + { 0x0, "Time_Of_Day_Seconds", "", 0, 0, 0, NULL, 0 }, + { 0x0, "Package", "", 0, 0, 0, NULL, 0 }, + { 0x0, "Node", "", 0, 0, 0, NULL, 0 }, + { 0x0, "Avg_MHz", "", 0, 0, 0, NULL, 0 }, + { 0x0, "Busy%", "", 0, 0, 0, NULL, 0 }, + { 0x0, "Bzy_MHz", "", 0, 0, 0, NULL, 0 }, + { 0x0, "TSC_MHz", "", 0, 0, 0, NULL, 0 }, + { 0x0, "IRQ", "", 0, 0, 0, NULL, 0 }, + { 0x0, "SMI", "", 32, 0, FORMAT_DELTA, NULL, 0 }, + { 0x0, "sysfs", "", 0, 0, 0, NULL, 0 }, + { 0x0, "CPU%c1", "", 0, 0, 0, NULL, 0 }, + { 0x0, "CPU%c3", "", 0, 0, 0, NULL, 0 }, + { 0x0, "CPU%c6", "", 0, 0, 0, NULL, 0 }, + { 0x0, "CPU%c7", "", 0, 0, 0, NULL, 0 }, + { 0x0, "ThreadC", "", 0, 0, 0, NULL, 0 }, + { 0x0, "CoreTmp", "", 0, 0, 0, NULL, 0 }, + { 0x0, "CoreCnt", "", 0, 0, 0, NULL, 0 }, + { 0x0, "PkgTmp", "", 0, 0, 0, NULL, 0 }, + { 0x0, "GFX%rc6", "", 0, 0, 0, NULL, 0 }, + { 0x0, "GFXMHz", "", 0, 0, 0, NULL, 0 }, + { 0x0, "Pkg%pc2", "", 0, 0, 0, NULL, 0 }, + { 0x0, "Pkg%pc3", "", 0, 0, 0, NULL, 0 }, + { 0x0, "Pkg%pc6", "", 0, 0, 0, NULL, 0 }, + { 0x0, "Pkg%pc7", "", 0, 0, 0, NULL, 0 }, + { 0x0, "Pkg%pc8", "", 0, 0, 0, NULL, 0 }, + { 0x0, "Pkg%pc9", "", 0, 0, 0, NULL, 0 }, + { 0x0, "Pk%pc10", "", 0, 0, 0, NULL, 0 }, + { 0x0, "CPU%LPI", "", 0, 0, 0, NULL, 0 }, + { 0x0, "SYS%LPI", "", 0, 0, 0, NULL, 0 }, + { 0x0, "PkgWatt", "", 0, 0, 0, NULL, 0 }, + { 0x0, "CorWatt", "", 0, 0, 0, NULL, 0 }, + { 0x0, "GFXWatt", "", 0, 0, 0, NULL, 0 }, + { 0x0, "PkgCnt", "", 0, 0, 0, NULL, 0 }, + { 0x0, "RAMWatt", "", 0, 0, 0, NULL, 0 }, + { 0x0, "PKG_%", "", 0, 0, 0, NULL, 0 }, + { 0x0, "RAM_%", "", 0, 0, 0, NULL, 0 }, + { 0x0, "Pkg_J", "", 0, 0, 0, NULL, 0 }, + { 0x0, "Cor_J", "", 0, 0, 0, NULL, 0 }, + { 0x0, "GFX_J", "", 0, 0, 0, NULL, 0 }, + { 0x0, "RAM_J", "", 0, 0, 0, NULL, 0 }, + { 0x0, "Mod%c6", "", 0, 0, 0, NULL, 0 }, + { 0x0, "Totl%C0", "", 0, 0, 0, NULL, 0 }, + { 0x0, "Any%C0", "", 0, 0, 0, NULL, 0 }, + { 0x0, "GFX%C0", "", 0, 0, 0, NULL, 0 }, + { 0x0, "CPUGFX%", "", 0, 0, 0, NULL, 0 }, + { 0x0, "Core", "", 0, 0, 0, NULL, 0 }, + { 0x0, "CPU", "", 0, 0, 0, NULL, 0 }, + { 0x0, "APIC", "", 0, 0, 0, NULL, 0 }, + { 0x0, "X2APIC", "", 0, 0, 0, NULL, 0 }, + { 0x0, "Die", "", 0, 0, 0, NULL, 0 }, + { 0x0, "GFXAMHz", "", 0, 0, 0, NULL, 0 }, + { 0x0, "IPC", "", 0, 0, 0, NULL, 0 }, + { 0x0, "CoreThr", "", 0, 0, 0, NULL, 0 }, +}; + +#define MAX_BIC (sizeof(bic) / sizeof(struct msr_counter)) +#define BIC_USEC (1ULL << 0) +#define BIC_TOD (1ULL << 1) +#define BIC_Package (1ULL << 2) +#define BIC_Node (1ULL << 3) +#define BIC_Avg_MHz (1ULL << 4) +#define BIC_Busy (1ULL << 5) +#define BIC_Bzy_MHz (1ULL << 6) +#define BIC_TSC_MHz (1ULL << 7) +#define BIC_IRQ (1ULL << 8) +#define BIC_SMI (1ULL << 9) +#define BIC_sysfs (1ULL << 10) +#define BIC_CPU_c1 (1ULL << 11) +#define BIC_CPU_c3 (1ULL << 12) +#define BIC_CPU_c6 (1ULL << 13) +#define BIC_CPU_c7 (1ULL << 14) +#define BIC_ThreadC (1ULL << 15) +#define BIC_CoreTmp (1ULL << 16) +#define BIC_CoreCnt (1ULL << 17) +#define BIC_PkgTmp (1ULL << 18) +#define BIC_GFX_rc6 (1ULL << 19) +#define BIC_GFXMHz (1ULL << 20) +#define BIC_Pkgpc2 (1ULL << 21) +#define BIC_Pkgpc3 (1ULL << 22) +#define BIC_Pkgpc6 (1ULL << 23) +#define BIC_Pkgpc7 (1ULL << 24) +#define BIC_Pkgpc8 (1ULL << 25) +#define BIC_Pkgpc9 (1ULL << 26) +#define BIC_Pkgpc10 (1ULL << 27) +#define BIC_CPU_LPI (1ULL << 28) +#define BIC_SYS_LPI (1ULL << 29) +#define BIC_PkgWatt (1ULL << 30) +#define BIC_CorWatt (1ULL << 31) +#define BIC_GFXWatt (1ULL << 32) +#define BIC_PkgCnt (1ULL << 33) +#define BIC_RAMWatt (1ULL << 34) +#define BIC_PKG__ (1ULL << 35) +#define BIC_RAM__ (1ULL << 36) +#define BIC_Pkg_J (1ULL << 37) +#define BIC_Cor_J (1ULL << 38) +#define BIC_GFX_J (1ULL << 39) +#define BIC_RAM_J (1ULL << 40) +#define BIC_Mod_c6 (1ULL << 41) +#define BIC_Totl_c0 (1ULL << 42) +#define BIC_Any_c0 (1ULL << 43) +#define BIC_GFX_c0 (1ULL << 44) +#define BIC_CPUGFX (1ULL << 45) +#define BIC_Core (1ULL << 46) +#define BIC_CPU (1ULL << 47) +#define BIC_APIC (1ULL << 48) +#define BIC_X2APIC (1ULL << 49) +#define BIC_Die (1ULL << 50) +#define BIC_GFXACTMHz (1ULL << 51) +#define BIC_IPC (1ULL << 52) +#define BIC_CORE_THROT_CNT (1ULL << 53) + +#define BIC_TOPOLOGY (BIC_Package | BIC_Node | BIC_CoreCnt | BIC_PkgCnt | BIC_Core | BIC_CPU | BIC_Die ) +#define BIC_THERMAL_PWR ( BIC_CoreTmp | BIC_PkgTmp | BIC_PkgWatt | BIC_CorWatt | BIC_GFXWatt | BIC_RAMWatt | BIC_PKG__ | BIC_RAM__) +#define BIC_FREQUENCY ( BIC_Avg_MHz | BIC_Busy | BIC_Bzy_MHz | BIC_TSC_MHz | BIC_GFXMHz | BIC_GFXACTMHz ) +#define BIC_IDLE ( BIC_sysfs | BIC_CPU_c1 | BIC_CPU_c3 | BIC_CPU_c6 | BIC_CPU_c7 | BIC_GFX_rc6 | BIC_Pkgpc2 | BIC_Pkgpc3 | BIC_Pkgpc6 | BIC_Pkgpc7 | BIC_Pkgpc8 | BIC_Pkgpc9 | BIC_Pkgpc10 | BIC_CPU_LPI | BIC_SYS_LPI | BIC_Mod_c6 | BIC_Totl_c0 | BIC_Any_c0 | BIC_GFX_c0 | BIC_CPUGFX) +#define BIC_OTHER ( BIC_IRQ | BIC_SMI | BIC_ThreadC | BIC_CoreTmp | BIC_IPC) + +#define BIC_DISABLED_BY_DEFAULT (BIC_USEC | BIC_TOD | BIC_APIC | BIC_X2APIC) + +unsigned long long bic_enabled = (0xFFFFFFFFFFFFFFFFULL & ~BIC_DISABLED_BY_DEFAULT); +unsigned long long bic_present = BIC_USEC | BIC_TOD | BIC_sysfs | BIC_APIC | BIC_X2APIC; + +#define DO_BIC(COUNTER_NAME) (bic_enabled & bic_present & COUNTER_NAME) +#define DO_BIC_READ(COUNTER_NAME) (bic_present & COUNTER_NAME) +#define ENABLE_BIC(COUNTER_NAME) (bic_enabled |= COUNTER_NAME) +#define BIC_PRESENT(COUNTER_BIT) (bic_present |= COUNTER_BIT) +#define BIC_NOT_PRESENT(COUNTER_BIT) (bic_present &= ~COUNTER_BIT) +#define BIC_IS_ENABLED(COUNTER_BIT) (bic_enabled & COUNTER_BIT) + char *proc_stat = "/proc/stat"; FILE *outf; int *fd_percpu; @@ -48,6 +213,7 @@ struct timespec interval_ts = { 5, 0 }; unsigned int model_orig; unsigned int num_iterations; +unsigned int header_iterations; unsigned int debug; unsigned int quiet; unsigned int shown; @@ -159,13 +325,6 @@ int ignore_stdin; #define MAX(a, b) ((a) > (b) ? (a) : (b)) -/* - * buffer size used by sscanf() for added column names - * Usually truncated to 7 characters, but also handles 18 columns for raw 64-bit counters - */ -#define NAME_BYTES 20 -#define PATH_BYTES 128 - int backwards_count; char *progname; @@ -205,6 +364,7 @@ struct core_data { unsigned int core_temp_c; unsigned int core_energy; /* MSR_CORE_ENERGY_STAT */ unsigned int core_id; + unsigned long long core_throt_cnt; unsigned long long counter[MAX_ADDED_COUNTERS]; } *core_even, *core_odd; @@ -255,24 +415,6 @@ struct pkg_data { #define GET_PKG(pkg_base, pkg_no) (pkg_base + pkg_no) -enum counter_scope { SCOPE_CPU, SCOPE_CORE, SCOPE_PACKAGE }; -enum counter_type { COUNTER_ITEMS, COUNTER_CYCLES, COUNTER_SECONDS, COUNTER_USEC }; -enum counter_format { FORMAT_RAW, FORMAT_DELTA, FORMAT_PERCENT }; - -struct msr_counter { - unsigned int msr_num; - char name[NAME_BYTES]; - char path[PATH_BYTES]; - unsigned int width; - enum counter_type type; - enum counter_format format; - struct msr_counter *next; - unsigned int flags; -#define FLAGS_HIDE (1 << 0) -#define FLAGS_SHOW (1 << 1) -#define SYSFS_PERCPU (1 << 1) -}; - /* * The accumulated sum of MSR is defined as a monotonic * increasing MSR, it will be accumulated periodically, @@ -522,8 +664,10 @@ static int perf_instr_count_open(int cpu_num) /* counter for cpu_num, including user + kernel and all processes */ fd = perf_event_open(&pea, -1, cpu_num, -1, 0); - if (fd == -1) - err(-1, "cpu%d: perf instruction counter\n", cpu_num); + if (fd == -1) { + warn("cpu%d: perf instruction counter", cpu_num); + BIC_NOT_PRESENT(BIC_IPC); + } return fd; } @@ -550,143 +694,10 @@ int get_msr(int cpu, off_t offset, unsigned long long *msr) return 0; } -/* - * This list matches the column headers, except - * 1. built-in only, the sysfs counters are not here -- we learn of those at run-time - * 2. Core and CPU are moved to the end, we can't have strings that contain them - * matching on them for --show and --hide. - */ -struct msr_counter bic[] = { - { 0x0, "usec" }, - { 0x0, "Time_Of_Day_Seconds" }, - { 0x0, "Package" }, - { 0x0, "Node" }, - { 0x0, "Avg_MHz" }, - { 0x0, "Busy%" }, - { 0x0, "Bzy_MHz" }, - { 0x0, "TSC_MHz" }, - { 0x0, "IRQ" }, - { 0x0, "SMI", "", 32, 0, FORMAT_DELTA, NULL }, - { 0x0, "sysfs" }, - { 0x0, "CPU%c1" }, - { 0x0, "CPU%c3" }, - { 0x0, "CPU%c6" }, - { 0x0, "CPU%c7" }, - { 0x0, "ThreadC" }, - { 0x0, "CoreTmp" }, - { 0x0, "CoreCnt" }, - { 0x0, "PkgTmp" }, - { 0x0, "GFX%rc6" }, - { 0x0, "GFXMHz" }, - { 0x0, "Pkg%pc2" }, - { 0x0, "Pkg%pc3" }, - { 0x0, "Pkg%pc6" }, - { 0x0, "Pkg%pc7" }, - { 0x0, "Pkg%pc8" }, - { 0x0, "Pkg%pc9" }, - { 0x0, "Pk%pc10" }, - { 0x0, "CPU%LPI" }, - { 0x0, "SYS%LPI" }, - { 0x0, "PkgWatt" }, - { 0x0, "CorWatt" }, - { 0x0, "GFXWatt" }, - { 0x0, "PkgCnt" }, - { 0x0, "RAMWatt" }, - { 0x0, "PKG_%" }, - { 0x0, "RAM_%" }, - { 0x0, "Pkg_J" }, - { 0x0, "Cor_J" }, - { 0x0, "GFX_J" }, - { 0x0, "RAM_J" }, - { 0x0, "Mod%c6" }, - { 0x0, "Totl%C0" }, - { 0x0, "Any%C0" }, - { 0x0, "GFX%C0" }, - { 0x0, "CPUGFX%" }, - { 0x0, "Core" }, - { 0x0, "CPU" }, - { 0x0, "APIC" }, - { 0x0, "X2APIC" }, - { 0x0, "Die" }, - { 0x0, "GFXAMHz" }, - { 0x0, "IPC" }, -}; - -#define MAX_BIC (sizeof(bic) / sizeof(struct msr_counter)) -#define BIC_USEC (1ULL << 0) -#define BIC_TOD (1ULL << 1) -#define BIC_Package (1ULL << 2) -#define BIC_Node (1ULL << 3) -#define BIC_Avg_MHz (1ULL << 4) -#define BIC_Busy (1ULL << 5) -#define BIC_Bzy_MHz (1ULL << 6) -#define BIC_TSC_MHz (1ULL << 7) -#define BIC_IRQ (1ULL << 8) -#define BIC_SMI (1ULL << 9) -#define BIC_sysfs (1ULL << 10) -#define BIC_CPU_c1 (1ULL << 11) -#define BIC_CPU_c3 (1ULL << 12) -#define BIC_CPU_c6 (1ULL << 13) -#define BIC_CPU_c7 (1ULL << 14) -#define BIC_ThreadC (1ULL << 15) -#define BIC_CoreTmp (1ULL << 16) -#define BIC_CoreCnt (1ULL << 17) -#define BIC_PkgTmp (1ULL << 18) -#define BIC_GFX_rc6 (1ULL << 19) -#define BIC_GFXMHz (1ULL << 20) -#define BIC_Pkgpc2 (1ULL << 21) -#define BIC_Pkgpc3 (1ULL << 22) -#define BIC_Pkgpc6 (1ULL << 23) -#define BIC_Pkgpc7 (1ULL << 24) -#define BIC_Pkgpc8 (1ULL << 25) -#define BIC_Pkgpc9 (1ULL << 26) -#define BIC_Pkgpc10 (1ULL << 27) -#define BIC_CPU_LPI (1ULL << 28) -#define BIC_SYS_LPI (1ULL << 29) -#define BIC_PkgWatt (1ULL << 30) -#define BIC_CorWatt (1ULL << 31) -#define BIC_GFXWatt (1ULL << 32) -#define BIC_PkgCnt (1ULL << 33) -#define BIC_RAMWatt (1ULL << 34) -#define BIC_PKG__ (1ULL << 35) -#define BIC_RAM__ (1ULL << 36) -#define BIC_Pkg_J (1ULL << 37) -#define BIC_Cor_J (1ULL << 38) -#define BIC_GFX_J (1ULL << 39) -#define BIC_RAM_J (1ULL << 40) -#define BIC_Mod_c6 (1ULL << 41) -#define BIC_Totl_c0 (1ULL << 42) -#define BIC_Any_c0 (1ULL << 43) -#define BIC_GFX_c0 (1ULL << 44) -#define BIC_CPUGFX (1ULL << 45) -#define BIC_Core (1ULL << 46) -#define BIC_CPU (1ULL << 47) -#define BIC_APIC (1ULL << 48) -#define BIC_X2APIC (1ULL << 49) -#define BIC_Die (1ULL << 50) -#define BIC_GFXACTMHz (1ULL << 51) -#define BIC_IPC (1ULL << 52) - -#define BIC_TOPOLOGY (BIC_Package | BIC_Node | BIC_CoreCnt | BIC_PkgCnt | BIC_Core | BIC_CPU | BIC_Die ) -#define BIC_THERMAL_PWR ( BIC_CoreTmp | BIC_PkgTmp | BIC_PkgWatt | BIC_CorWatt | BIC_GFXWatt | BIC_RAMWatt | BIC_PKG__ | BIC_RAM__) -#define BIC_FREQUENCY ( BIC_Avg_MHz | BIC_Busy | BIC_Bzy_MHz | BIC_TSC_MHz | BIC_GFXMHz | BIC_GFXACTMHz ) -#define BIC_IDLE ( BIC_sysfs | BIC_CPU_c1 | BIC_CPU_c3 | BIC_CPU_c6 | BIC_CPU_c7 | BIC_GFX_rc6 | BIC_Pkgpc2 | BIC_Pkgpc3 | BIC_Pkgpc6 | BIC_Pkgpc7 | BIC_Pkgpc8 | BIC_Pkgpc9 | BIC_Pkgpc10 | BIC_CPU_LPI | BIC_SYS_LPI | BIC_Mod_c6 | BIC_Totl_c0 | BIC_Any_c0 | BIC_GFX_c0 | BIC_CPUGFX) -#define BIC_OTHER ( BIC_IRQ | BIC_SMI | BIC_ThreadC | BIC_CoreTmp | BIC_IPC) - -#define BIC_DISABLED_BY_DEFAULT (BIC_USEC | BIC_TOD | BIC_APIC | BIC_X2APIC) - -unsigned long long bic_enabled = (0xFFFFFFFFFFFFFFFFULL & ~BIC_DISABLED_BY_DEFAULT); -unsigned long long bic_present = BIC_USEC | BIC_TOD | BIC_sysfs | BIC_APIC | BIC_X2APIC; - -#define DO_BIC(COUNTER_NAME) (bic_enabled & bic_present & COUNTER_NAME) -#define DO_BIC_READ(COUNTER_NAME) (bic_present & COUNTER_NAME) -#define ENABLE_BIC(COUNTER_NAME) (bic_enabled |= COUNTER_NAME) -#define BIC_PRESENT(COUNTER_BIT) (bic_present |= COUNTER_BIT) -#define BIC_NOT_PRESENT(COUNTER_BIT) (bic_present &= ~COUNTER_BIT) -#define BIC_IS_ENABLED(COUNTER_BIT) (bic_enabled & COUNTER_BIT) - #define MAX_DEFERRED 16 +char *deferred_add_names[MAX_DEFERRED]; char *deferred_skip_names[MAX_DEFERRED]; +int deferred_add_index; int deferred_skip_index; /* @@ -720,6 +731,8 @@ void help(void) " -l, --list list column headers only\n" " -n, --num_iterations num\n" " number of the measurement iterations\n" + " -N, --header_iterations num\n" + " print header every num iterations\n" " -o, --out file\n" " create or truncate \"file\" for all output\n" " -q, --quiet skip decoding system configuration header\n" @@ -741,7 +754,7 @@ void help(void) */ unsigned long long bic_lookup(char *name_list, enum show_hide_mode mode) { - int i; + unsigned int i; unsigned long long retval = 0; while (name_list) { @@ -752,40 +765,51 @@ unsigned long long bic_lookup(char *name_list, enum show_hide_mode mode) if (comma) *comma = '\0'; - if (!strcmp(name_list, "all")) - return ~0; - if (!strcmp(name_list, "topology")) - return BIC_TOPOLOGY; - if (!strcmp(name_list, "power")) - return BIC_THERMAL_PWR; - if (!strcmp(name_list, "idle")) - return BIC_IDLE; - if (!strcmp(name_list, "frequency")) - return BIC_FREQUENCY; - if (!strcmp(name_list, "other")) - return BIC_OTHER; - if (!strcmp(name_list, "all")) - return 0; - for (i = 0; i < MAX_BIC; ++i) { if (!strcmp(name_list, bic[i].name)) { retval |= (1ULL << i); break; } + if (!strcmp(name_list, "all")) { + retval |= ~0; + break; + } else if (!strcmp(name_list, "topology")) { + retval |= BIC_TOPOLOGY; + break; + } else if (!strcmp(name_list, "power")) { + retval |= BIC_THERMAL_PWR; + break; + } else if (!strcmp(name_list, "idle")) { + retval |= BIC_IDLE; + break; + } else if (!strcmp(name_list, "frequency")) { + retval |= BIC_FREQUENCY; + break; + } else if (!strcmp(name_list, "other")) { + retval |= BIC_OTHER; + break; + } + } if (i == MAX_BIC) { if (mode == SHOW_LIST) { - fprintf(stderr, "Invalid counter name: %s\n", name_list); - exit(-1); - } - deferred_skip_names[deferred_skip_index++] = name_list; - if (debug) - fprintf(stderr, "deferred \"%s\"\n", name_list); - if (deferred_skip_index >= MAX_DEFERRED) { - fprintf(stderr, "More than max %d un-recognized --skip options '%s'\n", - MAX_DEFERRED, name_list); - help(); - exit(1); + deferred_add_names[deferred_add_index++] = name_list; + if (deferred_add_index >= MAX_DEFERRED) { + fprintf(stderr, "More than max %d un-recognized --add options '%s'\n", + MAX_DEFERRED, name_list); + help(); + exit(1); + } + } else { + deferred_skip_names[deferred_skip_index++] = name_list; + if (debug) + fprintf(stderr, "deferred \"%s\"\n", name_list); + if (deferred_skip_index >= MAX_DEFERRED) { + fprintf(stderr, "More than max %d un-recognized --skip options '%s'\n", + MAX_DEFERRED, name_list); + help(); + exit(1); + } } } @@ -872,6 +896,9 @@ void print_header(char *delim) if (DO_BIC(BIC_CoreTmp)) outp += sprintf(outp, "%sCoreTmp", (printed++ ? delim : "")); + if (DO_BIC(BIC_CORE_THROT_CNT)) + outp += sprintf(outp, "%sCoreThr", (printed++ ? delim : "")); + if (do_rapl && !rapl_joules) { if (DO_BIC(BIC_CorWatt) && (do_rapl & RAPL_PER_CORE_ENERGY)) outp += sprintf(outp, "%sCorWatt", (printed++ ? delim : "")); @@ -1011,6 +1038,7 @@ int dump_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p outp += sprintf(outp, "c6: %016llX\n", c->c6); outp += sprintf(outp, "c7: %016llX\n", c->c7); outp += sprintf(outp, "DTS: %dC\n", c->core_temp_c); + outp += sprintf(outp, "cpu_throt_count: %016llX\n", c->core_throt_cnt); outp += sprintf(outp, "Joules: %0X\n", c->core_energy); for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) { @@ -1225,6 +1253,10 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data if (DO_BIC(BIC_CoreTmp)) outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), c->core_temp_c); + /* Core throttle count */ + if (DO_BIC(BIC_CORE_THROT_CNT)) + outp += sprintf(outp, "%s%lld", (printed++ ? delim : ""), c->core_throt_cnt); + for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) { if (mp->format == FORMAT_RAW) { if (mp->width == 32) @@ -1311,6 +1343,7 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data if (DO_BIC(BIC_PkgWatt)) outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_pkg * rapl_energy_units / interval_float); + if (DO_BIC(BIC_CorWatt) && !(do_rapl & RAPL_PER_CORE_ENERGY)) outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_cores * rapl_energy_units / interval_float); @@ -1386,14 +1419,14 @@ void flush_output_stderr(void) void format_all_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) { - static int printed; + static int count; - if (!printed || !summary_only) + if ((!count || (header_iterations && !(count % header_iterations))) || !summary_only) print_header("\t"); format_counters(&average.threads, &average.cores, &average.packages); - printed = 1; + count++; if (summary_only) return; @@ -1467,6 +1500,7 @@ void delta_core(struct core_data *new, struct core_data *old) old->c6 = new->c6 - old->c6; old->c7 = new->c7 - old->c7; old->core_temp_c = new->core_temp_c; + old->core_throt_cnt = new->core_throt_cnt; old->mc6_us = new->mc6_us - old->mc6_us; DELTA_WRAP32(new->core_energy, old->core_energy); @@ -1626,6 +1660,7 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data c->mc6_us = 0; c->core_temp_c = 0; c->core_energy = 0; + c->core_throt_cnt = 0; p->pkg_wtd_core_c0 = 0; p->pkg_any_core_c0 = 0; @@ -1710,6 +1745,7 @@ int sum_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) average.cores.mc6_us += c->mc6_us; average.cores.core_temp_c = MAX(average.cores.core_temp_c, c->core_temp_c); + average.cores.core_throt_cnt = MAX(average.cores.core_throt_cnt, c->core_throt_cnt); average.cores.core_energy += c->core_energy; @@ -1987,6 +2023,26 @@ void get_apic_id(struct thread_data *t) fprintf(outf, "cpu%d: BIOS BUG: apic 0x%x x2apic 0x%x\n", t->cpu_id, t->apic_id, t->x2apic_id); } +int get_core_throt_cnt(int cpu, unsigned long long *cnt) +{ + char path[128 + PATH_BYTES]; + unsigned long long tmp; + FILE *fp; + int ret; + + sprintf(path, "/sys/devices/system/cpu/cpu%d/thermal_throttle/core_throttle_count", cpu); + fp = fopen(path, "r"); + if (!fp) + return -1; + ret = fscanf(fp, "%lld", &tmp); + if (ret != 1) + return -1; + fclose(fp); + *cnt = tmp; + + return 0; +} + /* * get_counters(...) * migrate to cpu @@ -2129,6 +2185,9 @@ retry: c->core_temp_c = tj_max - ((msr >> 16) & 0x7F); } + if (DO_BIC(BIC_CORE_THROT_CNT)) + get_core_throt_cnt(cpu, &c->core_throt_cnt); + if (do_rapl & RAPL_AMD_F17H) { if (get_msr(cpu, MSR_CORE_ENERGY_STAT, &msr)) return -14; @@ -2428,6 +2487,9 @@ int has_turbo_ratio_group_limits(int family, int model) if (!genuine_intel) return 0; + if (family != 6) + return 0; + switch (model) { case INTEL_FAM6_ATOM_GOLDMONT: case INTEL_FAM6_SKYLAKE_X: @@ -2435,8 +2497,9 @@ int has_turbo_ratio_group_limits(int family, int model) case INTEL_FAM6_ATOM_GOLDMONT_D: case INTEL_FAM6_ATOM_TREMONT_D: return 1; + default: + return 0; } - return 0; } static void dump_turbo_ratio_limits(int family, int model) @@ -3027,6 +3090,8 @@ void set_max_cpu_num(void) */ int count_cpus(int cpu) { + UNUSED(cpu); + topo.num_cpus++; return 0; } @@ -3361,6 +3426,9 @@ static int update_msr_sum(struct thread_data *t, struct core_data *c, struct pkg int i, ret; int cpu = t->cpu_id; + UNUSED(c); + UNUSED(p); + for (i = IDX_PKG_ENERGY; i < IDX_COUNT; i++) { unsigned long long msr_cur, msr_last; off_t offset; @@ -3387,6 +3455,8 @@ static int update_msr_sum(struct thread_data *t, struct core_data *c, struct pkg static void msr_record_handler(union sigval v) { + UNUSED(v); + for_all_cpus(update_msr_sum, EVEN_COUNTERS); } @@ -3439,6 +3509,9 @@ release_msr: /* * set_my_sched_priority(pri) * return previous + * + * if non-root, do this: + * # /sbin/setcap cap_sys_rawio,cap_sys_nice=+ep /usr/bin/turbostat */ int set_my_sched_priority(int priority) { @@ -3457,7 +3530,7 @@ int set_my_sched_priority(int priority) errno = 0; retval = getpriority(PRIO_PROCESS, 0); if (retval != priority) - err(-1, "getpriority(%d) != setpriority(%d)", retval, priority); + err(retval, "getpriority(%d) != setpriority(%d)", retval, priority); return original_priority; } @@ -3466,7 +3539,7 @@ void turbostat_loop() { int retval; int restarted = 0; - int done_iters = 0; + unsigned int done_iters = 0; setup_signal_handler(); @@ -3678,6 +3751,7 @@ int probe_nhm_msrs(unsigned int family, unsigned int model) break; case INTEL_FAM6_ATOM_SILVERMONT: /* BYT */ no_MSR_MISC_PWR_MGMT = 1; + /* FALLTHRU */ case INTEL_FAM6_ATOM_SILVERMONT_D: /* AVN */ pkg_cstate_limits = slv_pkg_cstate_limits; break; @@ -3721,6 +3795,9 @@ int has_slv_msrs(unsigned int family, unsigned int model) if (!genuine_intel) return 0; + if (family != 6) + return 0; + switch (model) { case INTEL_FAM6_ATOM_SILVERMONT: case INTEL_FAM6_ATOM_SILVERMONT_MID: @@ -3736,6 +3813,9 @@ int is_dnv(unsigned int family, unsigned int model) if (!genuine_intel) return 0; + if (family != 6) + return 0; + switch (model) { case INTEL_FAM6_ATOM_GOLDMONT_D: return 1; @@ -3749,6 +3829,9 @@ int is_bdx(unsigned int family, unsigned int model) if (!genuine_intel) return 0; + if (family != 6) + return 0; + switch (model) { case INTEL_FAM6_BROADWELL_X: return 1; @@ -3762,6 +3845,9 @@ int is_skx(unsigned int family, unsigned int model) if (!genuine_intel) return 0; + if (family != 6) + return 0; + switch (model) { case INTEL_FAM6_SKYLAKE_X: return 1; @@ -3775,6 +3861,9 @@ int is_icx(unsigned int family, unsigned int model) if (!genuine_intel) return 0; + if (family != 6) + return 0; + switch (model) { case INTEL_FAM6_ICELAKE_X: return 1; @@ -3787,6 +3876,9 @@ int is_ehl(unsigned int family, unsigned int model) if (!genuine_intel) return 0; + if (family != 6) + return 0; + switch (model) { case INTEL_FAM6_ATOM_TREMONT: return 1; @@ -3799,6 +3891,9 @@ int is_jvl(unsigned int family, unsigned int model) if (!genuine_intel) return 0; + if (family != 6) + return 0; + switch (model) { case INTEL_FAM6_ATOM_TREMONT_D: return 1; @@ -3811,6 +3906,9 @@ int has_turbo_ratio_limit(unsigned int family, unsigned int model) if (has_slv_msrs(family, model)) return 0; + if (family != 6) + return 0; + switch (model) { /* Nehalem compatible, but do not include turbo-ratio limit support */ case INTEL_FAM6_NEHALEM_EX: /* Nehalem-EX Xeon - Beckton */ @@ -4125,6 +4223,9 @@ int print_epb(struct thread_data *t, struct core_data *c, struct pkg_data *p) char *epb_string; int cpu, epb; + UNUSED(c); + UNUSED(p); + if (!has_epb) return 0; @@ -4171,6 +4272,9 @@ int print_hwp(struct thread_data *t, struct core_data *c, struct pkg_data *p) unsigned long long msr; int cpu; + UNUSED(c); + UNUSED(p); + if (!has_hwp) return 0; @@ -4254,6 +4358,9 @@ int print_perf_limit(struct thread_data *t, struct core_data *c, struct pkg_data unsigned long long msr; int cpu; + UNUSED(c); + UNUSED(p); + cpu = t->cpu_id; /* per-package */ @@ -4359,6 +4466,8 @@ double get_tdp_intel(unsigned int model) double get_tdp_amd(unsigned int family) { + UNUSED(family); + /* This is the max stock TDP of HEDT/Server Fam17h+ chips */ return 280.0; } @@ -4376,6 +4485,7 @@ static double rapl_dram_energy_units_probe(int model, double rapl_energy_units) case INTEL_FAM6_BROADWELL_X: /* BDX */ case INTEL_FAM6_SKYLAKE_X: /* SKX */ case INTEL_FAM6_XEON_PHI_KNL: /* KNL */ + case INTEL_FAM6_ICELAKE_X: /* ICX */ return (rapl_dram_energy_units = 15.3 / 1000000); default: return (rapl_energy_units); @@ -4559,6 +4669,8 @@ void rapl_probe_amd(unsigned int family, unsigned int model) unsigned int has_rapl = 0; double tdp; + UNUSED(model); + if (max_extended_level >= 0x80000007) { __cpuid(0x80000007, eax, ebx, ecx, edx); /* RAPL (Fam 17h+) */ @@ -4617,6 +4729,7 @@ void perf_limit_reasons_probe(unsigned int family, unsigned int model) case INTEL_FAM6_HASWELL_L: /* HSW */ case INTEL_FAM6_HASWELL_G: /* HSW */ do_gfx_perf_limit_reasons = 1; + /* FALLTHRU */ case INTEL_FAM6_HASWELL_X: /* HSX */ do_core_perf_limit_reasons = 1; do_ring_perf_limit_reasons = 1; @@ -4643,6 +4756,9 @@ int print_thermal(struct thread_data *t, struct core_data *c, struct pkg_data *p unsigned int dts, dts2; int cpu; + UNUSED(c); + UNUSED(p); + if (!(do_dts || do_ptm)) return 0; @@ -4698,7 +4814,7 @@ int print_thermal(struct thread_data *t, struct core_data *c, struct pkg_data *p void print_power_limit_msr(int cpu, unsigned long long msr, char *label) { - fprintf(outf, "cpu%d: %s: %sabled (%f Watts, %f sec, clamp %sabled)\n", + fprintf(outf, "cpu%d: %s: %sabled (%0.3f Watts, %f sec, clamp %sabled)\n", cpu, label, ((msr >> 15) & 1) ? "EN" : "DIS", ((msr >> 0) & 0x7FFF) * rapl_power_units, @@ -4714,6 +4830,9 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p) const char *msr_name; int cpu; + UNUSED(c); + UNUSED(p); + if (!do_rapl) return 0; @@ -4762,12 +4881,19 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p) cpu, msr, (msr >> 63) & 1 ? "" : "UN"); print_power_limit_msr(cpu, msr, "PKG Limit #1"); - fprintf(outf, "cpu%d: PKG Limit #2: %sabled (%f Watts, %f* sec, clamp %sabled)\n", + fprintf(outf, "cpu%d: PKG Limit #2: %sabled (%0.3f Watts, %f* sec, clamp %sabled)\n", cpu, ((msr >> 47) & 1) ? "EN" : "DIS", ((msr >> 32) & 0x7FFF) * rapl_power_units, (1.0 + (((msr >> 54) & 0x3) / 4.0)) * (1 << ((msr >> 49) & 0x1F)) * rapl_time_units, ((msr >> 48) & 1) ? "EN" : "DIS"); + + if (get_msr(cpu, MSR_VR_CURRENT_CONFIG, &msr)) + return -9; + + fprintf(outf, "cpu%d: MSR_VR_CURRENT_CONFIG: 0x%08llx\n", cpu, msr); + fprintf(outf, "cpu%d: PKG Limit #4: %f Watts (%slocked)\n", + cpu, ((msr >> 0) & 0x1FFF) * rapl_power_units, (msr >> 31) & 1 ? "" : "UN"); } if (do_rapl & RAPL_DRAM_POWER_INFO) { @@ -4830,6 +4956,9 @@ int has_snb_msrs(unsigned int family, unsigned int model) if (!genuine_intel) return 0; + if (family != 6) + return 0; + switch (model) { case INTEL_FAM6_SANDYBRIDGE: case INTEL_FAM6_SANDYBRIDGE_X: @@ -4873,6 +5002,9 @@ int has_c8910_msrs(unsigned int family, unsigned int model) if (!genuine_intel) return 0; + if (family != 6) + return 0; + switch (model) { case INTEL_FAM6_HASWELL_L: /* HSW */ case INTEL_FAM6_BROADWELL: /* BDW */ @@ -4899,6 +5031,9 @@ int has_skl_msrs(unsigned int family, unsigned int model) if (!genuine_intel) return 0; + if (family != 6) + return 0; + switch (model) { case INTEL_FAM6_SKYLAKE_L: /* SKL */ case INTEL_FAM6_CANNONLAKE_L: /* CNL */ @@ -4911,6 +5046,10 @@ int is_slm(unsigned int family, unsigned int model) { if (!genuine_intel) return 0; + + if (family != 6) + return 0; + switch (model) { case INTEL_FAM6_ATOM_SILVERMONT: /* BYT */ case INTEL_FAM6_ATOM_SILVERMONT_D: /* AVN */ @@ -4923,6 +5062,10 @@ int is_knl(unsigned int family, unsigned int model) { if (!genuine_intel) return 0; + + if (family != 6) + return 0; + switch (model) { case INTEL_FAM6_XEON_PHI_KNL: /* KNL */ return 1; @@ -4935,6 +5078,9 @@ int is_cnl(unsigned int family, unsigned int model) if (!genuine_intel) return 0; + if (family != 6) + return 0; + switch (model) { case INTEL_FAM6_CANNONLAKE_L: /* CNL */ return 1; @@ -4989,6 +5135,9 @@ int get_cpu_type(struct thread_data *t, struct core_data *c, struct pkg_data *p) { unsigned int eax, ebx, ecx, edx; + UNUSED(c); + UNUSED(p); + if (!genuine_intel) return 0; @@ -5025,6 +5174,9 @@ int set_temperature_target(struct thread_data *t, struct core_data *c, struct pk unsigned int tcc_default, tcc_offset; int cpu; + UNUSED(c); + UNUSED(p); + /* tj_max is used only for dts or ptm */ if (!(do_dts || do_ptm)) return 0; @@ -5572,6 +5724,11 @@ void process_cpuid() else BIC_NOT_PRESENT(BIC_CPU_LPI); + if (!access("/sys/devices/system/cpu/cpu0/thermal_throttle/core_throttle_count", R_OK)) + BIC_PRESENT(BIC_CORE_THROT_CNT); + else + BIC_NOT_PRESENT(BIC_CORE_THROT_CNT); + if (!access(sys_lpi_file_sysfs, R_OK)) { sys_lpi_file = sys_lpi_file_sysfs; BIC_PRESENT(BIC_SYS_LPI); @@ -5601,11 +5758,6 @@ int dir_filter(const struct dirent *dirp) return 0; } -int open_dev_cpu_msr(int dummy1) -{ - return 0; -} - void topology_probe() { int i; @@ -5896,6 +6048,9 @@ void turbostat_init() if (!quiet && do_irtl_snb) print_irtl(); + + if (DO_BIC(BIC_IPC)) + (void)get_instr_count_fd(base_cpu); } int fork_it(char **argv) @@ -5973,7 +6128,7 @@ int get_and_dump_counters(void) void print_version() { - fprintf(outf, "turbostat version 21.05.04" " - Len Brown <lenb@kernel.org>\n"); + fprintf(outf, "turbostat version 2022.04.16 - Len Brown <lenb@kernel.org>\n"); } int add_counter(unsigned int msr_num, char *path, char *name, @@ -6138,6 +6293,16 @@ next: } } +int is_deferred_add(char *name) +{ + int i; + + for (i = 0; i < deferred_add_index; ++i) + if (!strcmp(name, deferred_add_names[i])) + return 1; + return 0; +} + int is_deferred_skip(char *name) { int i; @@ -6156,9 +6321,6 @@ void probe_sysfs(void) int state; char *sp; - if (!DO_BIC(BIC_sysfs)) - return; - for (state = 10; state >= 0; --state) { sprintf(path, "/sys/devices/system/cpu/cpu%d/cpuidle/state%d/name", base_cpu, state); @@ -6181,6 +6343,9 @@ void probe_sysfs(void) sprintf(path, "cpuidle/state%d/time", state); + if (!DO_BIC(BIC_sysfs) && !is_deferred_add(name_buf)) + continue; + if (is_deferred_skip(name_buf)) continue; @@ -6206,6 +6371,9 @@ void probe_sysfs(void) sprintf(path, "cpuidle/state%d/usage", state); + if (!DO_BIC(BIC_sysfs) && !is_deferred_add(name_buf)) + continue; + if (is_deferred_skip(name_buf)) continue; @@ -6313,6 +6481,7 @@ void cmdline(int argc, char **argv) { "interval", required_argument, 0, 'i' }, { "IPC", no_argument, 0, 'I' }, { "num_iterations", required_argument, 0, 'n' }, + { "header_iterations", required_argument, 0, 'N' }, { "help", no_argument, 0, 'h' }, { "hide", required_argument, 0, 'H' }, // meh, -h taken by --help { "Joules", no_argument, 0, 'J' }, @@ -6394,6 +6563,14 @@ void cmdline(int argc, char **argv) exit(2); } break; + case 'N': + header_iterations = strtod(optarg, NULL); + + if (header_iterations <= 0) { + fprintf(outf, "iterations %d should be positive number\n", header_iterations); + exit(2); + } + break; case 's': /* * --show: show only those specified @@ -6432,6 +6609,8 @@ int main(int argc, char **argv) turbostat_init(); + msr_sum_record(); + /* dump counters and exit */ if (dump_only) return get_and_dump_counters(); @@ -6443,7 +6622,6 @@ int main(int argc, char **argv) return 0; } - msr_sum_record(); /* * if any params left, it must be a command to fork */ diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c index 65dbdda3a054..1da76ccde448 100644 --- a/tools/testing/nvdimm/test/nfit.c +++ b/tools/testing/nvdimm/test/nfit.c @@ -1842,7 +1842,7 @@ static int nfit_test_dimm_init(struct nfit_test *t) return 0; } -static void security_init(struct nfit_test *t) +static void nfit_security_init(struct nfit_test *t) { int i; @@ -1938,7 +1938,7 @@ static int nfit_test0_alloc(struct nfit_test *t) if (nfit_test_dimm_init(t)) return -ENOMEM; smart_init(t); - security_init(t); + nfit_security_init(t); return ars_state_init(&t->pdev.dev, &t->ars_state); } diff --git a/tools/testing/radix-tree/linux.c b/tools/testing/radix-tree/linux.c index 81539f543954..d5c1bcba86fe 100644 --- a/tools/testing/radix-tree/linux.c +++ b/tools/testing/radix-tree/linux.c @@ -25,7 +25,8 @@ struct kmem_cache { void (*ctor)(void *); }; -void *kmem_cache_alloc(struct kmem_cache *cachep, int gfp) +void *kmem_cache_alloc_lru(struct kmem_cache *cachep, struct list_lru *lru, + int gfp) { void *p; diff --git a/tools/testing/selftests/arm64/Makefile b/tools/testing/selftests/arm64/Makefile index 1e8d9a8f59df..9460cbe81bcc 100644 --- a/tools/testing/selftests/arm64/Makefile +++ b/tools/testing/selftests/arm64/Makefile @@ -17,16 +17,7 @@ top_srcdir = $(realpath ../../../../) # Additional include paths needed by kselftest.h and local headers CFLAGS += -I$(top_srcdir)/tools/testing/selftests/ -# Guessing where the Kernel headers could have been installed -# depending on ENV config -ifeq ($(KBUILD_OUTPUT),) -khdr_dir = $(top_srcdir)/usr/include -else -# the KSFT preferred location when KBUILD_OUTPUT is set -khdr_dir = $(KBUILD_OUTPUT)/kselftest/usr/include -endif - -CFLAGS += -I$(khdr_dir) +CFLAGS += $(KHDR_INCLUDES) export CFLAGS export top_srcdir diff --git a/tools/testing/selftests/arm64/abi/.gitignore b/tools/testing/selftests/arm64/abi/.gitignore index b79cf5814c23..b9e54417250d 100644 --- a/tools/testing/selftests/arm64/abi/.gitignore +++ b/tools/testing/selftests/arm64/abi/.gitignore @@ -1 +1,2 @@ syscall-abi +tpidr2 diff --git a/tools/testing/selftests/arm64/abi/Makefile b/tools/testing/selftests/arm64/abi/Makefile index 96eba974ac8d..c8d7f2495eb2 100644 --- a/tools/testing/selftests/arm64/abi/Makefile +++ b/tools/testing/selftests/arm64/abi/Makefile @@ -1,8 +1,15 @@ # SPDX-License-Identifier: GPL-2.0 # Copyright (C) 2021 ARM Limited -TEST_GEN_PROGS := syscall-abi +TEST_GEN_PROGS := syscall-abi tpidr2 include ../../lib.mk $(OUTPUT)/syscall-abi: syscall-abi.c syscall-abi-asm.S + +# Build with nolibc since TPIDR2 is intended to be actively managed by +# libc and we're trying to test the functionality that it depends on here. +$(OUTPUT)/tpidr2: tpidr2.c + $(CC) -fno-asynchronous-unwind-tables -fno-ident -s -Os -nostdlib \ + -static -include ../../../../include/nolibc/nolibc.h \ + -ffreestanding -Wall $^ -o $@ -lgcc diff --git a/tools/testing/selftests/arm64/abi/syscall-abi-asm.S b/tools/testing/selftests/arm64/abi/syscall-abi-asm.S index 983467cfcee0..b523c21c2278 100644 --- a/tools/testing/selftests/arm64/abi/syscall-abi-asm.S +++ b/tools/testing/selftests/arm64/abi/syscall-abi-asm.S @@ -9,15 +9,42 @@ // invoked is configured in x8 of the input GPR data. // // x0: SVE VL, 0 for FP only +// x1: SME VL // // GPRs: gpr_in, gpr_out // FPRs: fpr_in, fpr_out // Zn: z_in, z_out // Pn: p_in, p_out // FFR: ffr_in, ffr_out +// ZA: za_in, za_out +// SVCR: svcr_in, svcr_out + +#include "syscall-abi.h" .arch_extension sve +/* + * LDR (vector to ZA array): + * LDR ZA[\nw, #\offset], [X\nxbase, #\offset, MUL VL] + */ +.macro _ldr_za nw, nxbase, offset=0 + .inst 0xe1000000 \ + | (((\nw) & 3) << 13) \ + | ((\nxbase) << 5) \ + | ((\offset) & 7) +.endm + +/* + * STR (vector from ZA array): + * STR ZA[\nw, #\offset], [X\nxbase, #\offset, MUL VL] + */ +.macro _str_za nw, nxbase, offset=0 + .inst 0xe1200000 \ + | (((\nw) & 3) << 13) \ + | ((\nxbase) << 5) \ + | ((\offset) & 7) +.endm + .globl do_syscall do_syscall: // Store callee saved registers x19-x29 (80 bytes) plus x0 and x1 @@ -30,6 +57,24 @@ do_syscall: stp x25, x26, [sp, #80] stp x27, x28, [sp, #96] + // Set SVCR if we're doing SME + cbz x1, 1f + adrp x2, svcr_in + ldr x2, [x2, :lo12:svcr_in] + msr S3_3_C4_C2_2, x2 +1: + + // Load ZA if it's enabled - uses x12 as scratch due to SME LDR + tbz x2, #SVCR_ZA_SHIFT, 1f + mov w12, #0 + ldr x2, =za_in +2: _ldr_za 12, 2 + add x2, x2, x1 + add x12, x12, #1 + cmp x1, x12 + bne 2b +1: + // Load GPRs x8-x28, and save our SP/FP for later comparison ldr x2, =gpr_in add x2, x2, #64 @@ -68,7 +113,7 @@ do_syscall: ldp q30, q31, [x2, #16 * 30] 1: - // Load the SVE registers if we're doing SVE + // Load the SVE registers if we're doing SVE/SME cbz x0, 1f ldr x2, =z_in @@ -105,9 +150,14 @@ do_syscall: ldr z30, [x2, #30, MUL VL] ldr z31, [x2, #31, MUL VL] + // Only set a non-zero FFR, test patterns must be zero since the + // syscall should clear it - this lets us handle FA64. ldr x2, =ffr_in ldr p0, [x2, #0] + ldr x2, [x2, #0] + cbz x2, 2f wrffr p0.b +2: ldr x2, =p_in ldr p0, [x2, #0, MUL VL] @@ -169,6 +219,24 @@ do_syscall: stp q28, q29, [x2, #16 * 28] stp q30, q31, [x2, #16 * 30] + // Save SVCR if we're doing SME + cbz x1, 1f + mrs x2, S3_3_C4_C2_2 + adrp x3, svcr_out + str x2, [x3, :lo12:svcr_out] +1: + + // Save ZA if it's enabled - uses x12 as scratch due to SME STR + tbz x2, #SVCR_ZA_SHIFT, 1f + mov w12, #0 + ldr x2, =za_out +2: _str_za 12, 2 + add x2, x2, x1 + add x12, x12, #1 + cmp x1, x12 + bne 2b +1: + // Save the SVE state if we have some cbz x0, 1f @@ -224,6 +292,10 @@ do_syscall: str p14, [x2, #14, MUL VL] str p15, [x2, #15, MUL VL] + // Only save FFR if we wrote a value for SME + ldr x2, =ffr_in + ldr x2, [x2, #0] + cbz x2, 1f ldr x2, =ffr_out rdffr p0.b str p0, [x2, #0] @@ -237,4 +309,9 @@ do_syscall: ldp x27, x28, [sp, #96] ldp x29, x30, [sp], #112 + // Clear SVCR if we were doing SME so future tests don't have ZA + cbz x1, 1f + msr S3_3_C4_C2_2, xzr +1: + ret diff --git a/tools/testing/selftests/arm64/abi/syscall-abi.c b/tools/testing/selftests/arm64/abi/syscall-abi.c index 1e13b7523918..b632bfe9e022 100644 --- a/tools/testing/selftests/arm64/abi/syscall-abi.c +++ b/tools/testing/selftests/arm64/abi/syscall-abi.c @@ -18,9 +18,13 @@ #include "../../kselftest.h" +#include "syscall-abi.h" + #define NUM_VL ((SVE_VQ_MAX - SVE_VQ_MIN) + 1) -extern void do_syscall(int sve_vl); +static int default_sme_vl; + +extern void do_syscall(int sve_vl, int sme_vl); static void fill_random(void *buf, size_t size) { @@ -48,14 +52,15 @@ static struct syscall_cfg { uint64_t gpr_in[NUM_GPR]; uint64_t gpr_out[NUM_GPR]; -static void setup_gpr(struct syscall_cfg *cfg, int sve_vl) +static void setup_gpr(struct syscall_cfg *cfg, int sve_vl, int sme_vl, + uint64_t svcr) { fill_random(gpr_in, sizeof(gpr_in)); gpr_in[8] = cfg->syscall_nr; memset(gpr_out, 0, sizeof(gpr_out)); } -static int check_gpr(struct syscall_cfg *cfg, int sve_vl) +static int check_gpr(struct syscall_cfg *cfg, int sve_vl, int sme_vl, uint64_t svcr) { int errors = 0; int i; @@ -79,13 +84,15 @@ static int check_gpr(struct syscall_cfg *cfg, int sve_vl) uint64_t fpr_in[NUM_FPR * 2]; uint64_t fpr_out[NUM_FPR * 2]; -static void setup_fpr(struct syscall_cfg *cfg, int sve_vl) +static void setup_fpr(struct syscall_cfg *cfg, int sve_vl, int sme_vl, + uint64_t svcr) { fill_random(fpr_in, sizeof(fpr_in)); memset(fpr_out, 0, sizeof(fpr_out)); } -static int check_fpr(struct syscall_cfg *cfg, int sve_vl) +static int check_fpr(struct syscall_cfg *cfg, int sve_vl, int sme_vl, + uint64_t svcr) { int errors = 0; int i; @@ -109,13 +116,15 @@ static uint8_t z_zero[__SVE_ZREG_SIZE(SVE_VQ_MAX)]; uint8_t z_in[SVE_NUM_PREGS * __SVE_ZREG_SIZE(SVE_VQ_MAX)]; uint8_t z_out[SVE_NUM_PREGS * __SVE_ZREG_SIZE(SVE_VQ_MAX)]; -static void setup_z(struct syscall_cfg *cfg, int sve_vl) +static void setup_z(struct syscall_cfg *cfg, int sve_vl, int sme_vl, + uint64_t svcr) { fill_random(z_in, sizeof(z_in)); fill_random(z_out, sizeof(z_out)); } -static int check_z(struct syscall_cfg *cfg, int sve_vl) +static int check_z(struct syscall_cfg *cfg, int sve_vl, int sme_vl, + uint64_t svcr) { size_t reg_size = sve_vl; int errors = 0; @@ -126,13 +135,17 @@ static int check_z(struct syscall_cfg *cfg, int sve_vl) /* * After a syscall the low 128 bits of the Z registers should - * be preserved and the rest be zeroed or preserved. + * be preserved and the rest be zeroed or preserved, except if + * we were in streaming mode in which case the low 128 bits may + * also be cleared by the transition out of streaming mode. */ for (i = 0; i < SVE_NUM_ZREGS; i++) { void *in = &z_in[reg_size * i]; void *out = &z_out[reg_size * i]; - if (memcmp(in, out, SVE_VQ_BYTES) != 0) { + if ((memcmp(in, out, SVE_VQ_BYTES) != 0) && + !((svcr & SVCR_SM_MASK) && + memcmp(z_zero, out, SVE_VQ_BYTES) == 0)) { ksft_print_msg("%s SVE VL %d Z%d low 128 bits changed\n", cfg->name, sve_vl, i); errors++; @@ -145,13 +158,15 @@ static int check_z(struct syscall_cfg *cfg, int sve_vl) uint8_t p_in[SVE_NUM_PREGS * __SVE_PREG_SIZE(SVE_VQ_MAX)]; uint8_t p_out[SVE_NUM_PREGS * __SVE_PREG_SIZE(SVE_VQ_MAX)]; -static void setup_p(struct syscall_cfg *cfg, int sve_vl) +static void setup_p(struct syscall_cfg *cfg, int sve_vl, int sme_vl, + uint64_t svcr) { fill_random(p_in, sizeof(p_in)); fill_random(p_out, sizeof(p_out)); } -static int check_p(struct syscall_cfg *cfg, int sve_vl) +static int check_p(struct syscall_cfg *cfg, int sve_vl, int sme_vl, + uint64_t svcr) { size_t reg_size = sve_vq_from_vl(sve_vl) * 2; /* 1 bit per VL byte */ @@ -175,9 +190,20 @@ static int check_p(struct syscall_cfg *cfg, int sve_vl) uint8_t ffr_in[__SVE_PREG_SIZE(SVE_VQ_MAX)]; uint8_t ffr_out[__SVE_PREG_SIZE(SVE_VQ_MAX)]; -static void setup_ffr(struct syscall_cfg *cfg, int sve_vl) +static void setup_ffr(struct syscall_cfg *cfg, int sve_vl, int sme_vl, + uint64_t svcr) { /* + * If we are in streaming mode and do not have FA64 then FFR + * is unavailable. + */ + if ((svcr & SVCR_SM_MASK) && + !(getauxval(AT_HWCAP2) & HWCAP2_SME_FA64)) { + memset(&ffr_in, 0, sizeof(ffr_in)); + return; + } + + /* * It is only valid to set a contiguous set of bits starting * at 0. For now since we're expecting this to be cleared by * a syscall just set all bits. @@ -186,7 +212,8 @@ static void setup_ffr(struct syscall_cfg *cfg, int sve_vl) fill_random(ffr_out, sizeof(ffr_out)); } -static int check_ffr(struct syscall_cfg *cfg, int sve_vl) +static int check_ffr(struct syscall_cfg *cfg, int sve_vl, int sme_vl, + uint64_t svcr) { size_t reg_size = sve_vq_from_vl(sve_vl) * 2; /* 1 bit per VL byte */ int errors = 0; @@ -195,6 +222,10 @@ static int check_ffr(struct syscall_cfg *cfg, int sve_vl) if (!sve_vl) return 0; + if ((svcr & SVCR_SM_MASK) && + !(getauxval(AT_HWCAP2) & HWCAP2_SME_FA64)) + return 0; + /* After a syscall the P registers should be preserved or zeroed */ for (i = 0; i < reg_size; i++) if (ffr_out[i] && (ffr_in[i] != ffr_out[i])) @@ -206,8 +237,65 @@ static int check_ffr(struct syscall_cfg *cfg, int sve_vl) return errors; } -typedef void (*setup_fn)(struct syscall_cfg *cfg, int sve_vl); -typedef int (*check_fn)(struct syscall_cfg *cfg, int sve_vl); +uint64_t svcr_in, svcr_out; + +static void setup_svcr(struct syscall_cfg *cfg, int sve_vl, int sme_vl, + uint64_t svcr) +{ + svcr_in = svcr; +} + +static int check_svcr(struct syscall_cfg *cfg, int sve_vl, int sme_vl, + uint64_t svcr) +{ + int errors = 0; + + if (svcr_out & SVCR_SM_MASK) { + ksft_print_msg("%s Still in SM, SVCR %llx\n", + cfg->name, svcr_out); + errors++; + } + + if ((svcr_in & SVCR_ZA_MASK) != (svcr_out & SVCR_ZA_MASK)) { + ksft_print_msg("%s PSTATE.ZA changed, SVCR %llx != %llx\n", + cfg->name, svcr_in, svcr_out); + errors++; + } + + return errors; +} + +uint8_t za_in[SVE_NUM_PREGS * __SVE_ZREG_SIZE(SVE_VQ_MAX)]; +uint8_t za_out[SVE_NUM_PREGS * __SVE_ZREG_SIZE(SVE_VQ_MAX)]; + +static void setup_za(struct syscall_cfg *cfg, int sve_vl, int sme_vl, + uint64_t svcr) +{ + fill_random(za_in, sizeof(za_in)); + memset(za_out, 0, sizeof(za_out)); +} + +static int check_za(struct syscall_cfg *cfg, int sve_vl, int sme_vl, + uint64_t svcr) +{ + size_t reg_size = sme_vl * sme_vl; + int errors = 0; + + if (!(svcr & SVCR_ZA_MASK)) + return 0; + + if (memcmp(za_in, za_out, reg_size) != 0) { + ksft_print_msg("SME VL %d ZA does not match\n", sme_vl); + errors++; + } + + return errors; +} + +typedef void (*setup_fn)(struct syscall_cfg *cfg, int sve_vl, int sme_vl, + uint64_t svcr); +typedef int (*check_fn)(struct syscall_cfg *cfg, int sve_vl, int sme_vl, + uint64_t svcr); /* * Each set of registers has a setup function which is called before @@ -225,20 +313,23 @@ static struct { { setup_z, check_z }, { setup_p, check_p }, { setup_ffr, check_ffr }, + { setup_svcr, check_svcr }, + { setup_za, check_za }, }; -static bool do_test(struct syscall_cfg *cfg, int sve_vl) +static bool do_test(struct syscall_cfg *cfg, int sve_vl, int sme_vl, + uint64_t svcr) { int errors = 0; int i; for (i = 0; i < ARRAY_SIZE(regset); i++) - regset[i].setup(cfg, sve_vl); + regset[i].setup(cfg, sve_vl, sme_vl, svcr); - do_syscall(sve_vl); + do_syscall(sve_vl, sme_vl); for (i = 0; i < ARRAY_SIZE(regset); i++) - errors += regset[i].check(cfg, sve_vl); + errors += regset[i].check(cfg, sve_vl, sme_vl, svcr); return errors == 0; } @@ -246,9 +337,10 @@ static bool do_test(struct syscall_cfg *cfg, int sve_vl) static void test_one_syscall(struct syscall_cfg *cfg) { int sve_vq, sve_vl; + int sme_vq, sme_vl; /* FPSIMD only case */ - ksft_test_result(do_test(cfg, 0), + ksft_test_result(do_test(cfg, 0, default_sme_vl, 0), "%s FPSIMD\n", cfg->name); if (!(getauxval(AT_HWCAP) & HWCAP_SVE)) @@ -265,8 +357,36 @@ static void test_one_syscall(struct syscall_cfg *cfg) if (sve_vq != sve_vq_from_vl(sve_vl)) sve_vq = sve_vq_from_vl(sve_vl); - ksft_test_result(do_test(cfg, sve_vl), + ksft_test_result(do_test(cfg, sve_vl, default_sme_vl, 0), "%s SVE VL %d\n", cfg->name, sve_vl); + + if (!(getauxval(AT_HWCAP2) & HWCAP2_SME)) + continue; + + for (sme_vq = SVE_VQ_MAX; sme_vq > 0; --sme_vq) { + sme_vl = prctl(PR_SME_SET_VL, sme_vq * 16); + if (sme_vl == -1) + ksft_exit_fail_msg("PR_SME_SET_VL failed: %s (%d)\n", + strerror(errno), errno); + + sme_vl &= PR_SME_VL_LEN_MASK; + + if (sme_vq != sve_vq_from_vl(sme_vl)) + sme_vq = sve_vq_from_vl(sme_vl); + + ksft_test_result(do_test(cfg, sve_vl, sme_vl, + SVCR_ZA_MASK | SVCR_SM_MASK), + "%s SVE VL %d/SME VL %d SM+ZA\n", + cfg->name, sve_vl, sme_vl); + ksft_test_result(do_test(cfg, sve_vl, sme_vl, + SVCR_SM_MASK), + "%s SVE VL %d/SME VL %d SM\n", + cfg->name, sve_vl, sme_vl); + ksft_test_result(do_test(cfg, sve_vl, sme_vl, + SVCR_ZA_MASK), + "%s SVE VL %d/SME VL %d ZA\n", + cfg->name, sve_vl, sme_vl); + } } } @@ -299,14 +419,54 @@ int sve_count_vls(void) return vl_count; } +int sme_count_vls(void) +{ + unsigned int vq; + int vl_count = 0; + int vl; + + if (!(getauxval(AT_HWCAP2) & HWCAP2_SME)) + return 0; + + /* Ensure we configure a SME VL, used to flag if SVCR is set */ + default_sme_vl = 16; + + /* + * Enumerate up to SVE_VQ_MAX vector lengths + */ + for (vq = SVE_VQ_MAX; vq > 0; --vq) { + vl = prctl(PR_SME_SET_VL, vq * 16); + if (vl == -1) + ksft_exit_fail_msg("PR_SME_SET_VL failed: %s (%d)\n", + strerror(errno), errno); + + vl &= PR_SME_VL_LEN_MASK; + + if (vq != sve_vq_from_vl(vl)) + vq = sve_vq_from_vl(vl); + + vl_count++; + } + + return vl_count; +} + int main(void) { int i; + int tests = 1; /* FPSIMD */ srandom(getpid()); ksft_print_header(); - ksft_set_plan(ARRAY_SIZE(syscalls) * (sve_count_vls() + 1)); + tests += sve_count_vls(); + tests += (sve_count_vls() * sme_count_vls()) * 3; + ksft_set_plan(ARRAY_SIZE(syscalls) * tests); + + if (getauxval(AT_HWCAP2) & HWCAP2_SME_FA64) + ksft_print_msg("SME with FA64\n"); + else if (getauxval(AT_HWCAP2) & HWCAP2_SME) + ksft_print_msg("SME without FA64\n"); for (i = 0; i < ARRAY_SIZE(syscalls); i++) test_one_syscall(&syscalls[i]); diff --git a/tools/testing/selftests/arm64/abi/syscall-abi.h b/tools/testing/selftests/arm64/abi/syscall-abi.h new file mode 100644 index 000000000000..bda5a87ad381 --- /dev/null +++ b/tools/testing/selftests/arm64/abi/syscall-abi.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2021 ARM Limited. + */ + +#ifndef SYSCALL_ABI_H +#define SYSCALL_ABI_H + +#define SVCR_ZA_MASK 2 +#define SVCR_SM_MASK 1 + +#define SVCR_ZA_SHIFT 1 +#define SVCR_SM_SHIFT 0 + +#endif diff --git a/tools/testing/selftests/arm64/abi/tpidr2.c b/tools/testing/selftests/arm64/abi/tpidr2.c new file mode 100644 index 000000000000..351a098b503a --- /dev/null +++ b/tools/testing/selftests/arm64/abi/tpidr2.c @@ -0,0 +1,298 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <linux/sched.h> +#include <linux/wait.h> + +#define SYS_TPIDR2 "S3_3_C13_C0_5" + +#define EXPECTED_TESTS 5 + +static void putstr(const char *str) +{ + write(1, str, strlen(str)); +} + +static void putnum(unsigned int num) +{ + char c; + + if (num / 10) + putnum(num / 10); + + c = '0' + (num % 10); + write(1, &c, 1); +} + +static int tests_run; +static int tests_passed; +static int tests_failed; +static int tests_skipped; + +static void set_tpidr2(uint64_t val) +{ + asm volatile ( + "msr " SYS_TPIDR2 ", %0\n" + : + : "r"(val) + : "cc"); +} + +static uint64_t get_tpidr2(void) +{ + uint64_t val; + + asm volatile ( + "mrs %0, " SYS_TPIDR2 "\n" + : "=r"(val) + : + : "cc"); + + return val; +} + +static void print_summary(void) +{ + if (tests_passed + tests_failed + tests_skipped != EXPECTED_TESTS) + putstr("# UNEXPECTED TEST COUNT: "); + + putstr("# Totals: pass:"); + putnum(tests_passed); + putstr(" fail:"); + putnum(tests_failed); + putstr(" xfail:0 xpass:0 skip:"); + putnum(tests_skipped); + putstr(" error:0\n"); +} + +/* Processes should start with TPIDR2 == 0 */ +static int default_value(void) +{ + return get_tpidr2() == 0; +} + +/* If we set TPIDR2 we should read that value */ +static int write_read(void) +{ + set_tpidr2(getpid()); + + return getpid() == get_tpidr2(); +} + +/* If we set a value we should read the same value after scheduling out */ +static int write_sleep_read(void) +{ + set_tpidr2(getpid()); + + msleep(100); + + return getpid() == get_tpidr2(); +} + +/* + * If we fork the value in the parent should be unchanged and the + * child should start with the same value and be able to set its own + * value. + */ +static int write_fork_read(void) +{ + pid_t newpid, waiting, oldpid; + int status; + + set_tpidr2(getpid()); + + oldpid = getpid(); + newpid = fork(); + if (newpid == 0) { + /* In child */ + if (get_tpidr2() != oldpid) { + putstr("# TPIDR2 changed in child: "); + putnum(get_tpidr2()); + putstr("\n"); + exit(0); + } + + set_tpidr2(getpid()); + if (get_tpidr2() == getpid()) { + exit(1); + } else { + putstr("# Failed to set TPIDR2 in child\n"); + exit(0); + } + } + if (newpid < 0) { + putstr("# fork() failed: -"); + putnum(-newpid); + putstr("\n"); + return 0; + } + + for (;;) { + waiting = waitpid(newpid, &status, 0); + + if (waiting < 0) { + if (errno == EINTR) + continue; + putstr("# waitpid() failed: "); + putnum(errno); + putstr("\n"); + return 0; + } + if (waiting != newpid) { + putstr("# waitpid() returned wrong PID\n"); + return 0; + } + + if (!WIFEXITED(status)) { + putstr("# child did not exit\n"); + return 0; + } + + if (getpid() != get_tpidr2()) { + putstr("# TPIDR2 corrupted in parent\n"); + return 0; + } + + return WEXITSTATUS(status); + } +} + +/* + * sys_clone() has a lot of per architecture variation so just define + * it here rather than adding it to nolibc, plus the raw API is a + * little more convenient for this test. + */ +static int sys_clone(unsigned long clone_flags, unsigned long newsp, + int *parent_tidptr, unsigned long tls, + int *child_tidptr) +{ + return my_syscall5(__NR_clone, clone_flags, newsp, parent_tidptr, tls, + child_tidptr); +} + +/* + * If we clone with CLONE_SETTLS then the value in the parent should + * be unchanged and the child should start with zero and be able to + * set its own value. + */ +static int write_clone_read(void) +{ + int parent_tid, child_tid; + pid_t parent, waiting; + int ret, status; + + parent = getpid(); + set_tpidr2(parent); + + ret = sys_clone(CLONE_SETTLS, 0, &parent_tid, 0, &child_tid); + if (ret == -1) { + putstr("# clone() failed\n"); + putnum(errno); + putstr("\n"); + return 0; + } + + if (ret == 0) { + /* In child */ + if (get_tpidr2() != 0) { + putstr("# TPIDR2 non-zero in child: "); + putnum(get_tpidr2()); + putstr("\n"); + exit(0); + } + + if (gettid() == 0) + putstr("# Child TID==0\n"); + set_tpidr2(gettid()); + if (get_tpidr2() == gettid()) { + exit(1); + } else { + putstr("# Failed to set TPIDR2 in child\n"); + exit(0); + } + } + + for (;;) { + waiting = wait4(ret, &status, __WCLONE, NULL); + + if (waiting < 0) { + if (errno == EINTR) + continue; + putstr("# wait4() failed: "); + putnum(errno); + putstr("\n"); + return 0; + } + if (waiting != ret) { + putstr("# wait4() returned wrong PID "); + putnum(waiting); + putstr("\n"); + return 0; + } + + if (!WIFEXITED(status)) { + putstr("# child did not exit\n"); + return 0; + } + + if (parent != get_tpidr2()) { + putstr("# TPIDR2 corrupted in parent\n"); + return 0; + } + + return WEXITSTATUS(status); + } +} + +#define run_test(name) \ + if (name()) { \ + tests_passed++; \ + } else { \ + tests_failed++; \ + putstr("not "); \ + } \ + putstr("ok "); \ + putnum(++tests_run); \ + putstr(" " #name "\n"); + +int main(int argc, char **argv) +{ + int ret, i; + + putstr("TAP version 13\n"); + putstr("1.."); + putnum(EXPECTED_TESTS); + putstr("\n"); + + putstr("# PID: "); + putnum(getpid()); + putstr("\n"); + + /* + * This test is run with nolibc which doesn't support hwcap and + * it's probably disproportionate to implement so instead check + * for the default vector length configuration in /proc. + */ + ret = open("/proc/sys/abi/sme_default_vector_length", O_RDONLY, 0); + if (ret >= 0) { + run_test(default_value); + run_test(write_read); + run_test(write_sleep_read); + run_test(write_fork_read); + run_test(write_clone_read); + + } else { + putstr("# SME support not present\n"); + + for (i = 0; i < EXPECTED_TESTS; i++) { + putstr("ok "); + putnum(i); + putstr(" skipped, TPIDR2 not supported\n"); + } + + tests_skipped += EXPECTED_TESTS; + } + + print_summary(); + + return 0; +} diff --git a/tools/testing/selftests/arm64/bti/Makefile b/tools/testing/selftests/arm64/bti/Makefile index 73e013c082a6..ccdac414ad94 100644 --- a/tools/testing/selftests/arm64/bti/Makefile +++ b/tools/testing/selftests/arm64/bti/Makefile @@ -10,7 +10,7 @@ PROGS := $(patsubst %,gen/%,$(TEST_GEN_PROGS)) # cases for statically linked and dynamically lined binaries are # slightly different. -CFLAGS_NOBTI = -DBTI=0 +CFLAGS_NOBTI = -mbranch-protection=none -DBTI=0 CFLAGS_BTI = -mbranch-protection=standard -DBTI=1 CFLAGS_COMMON = -ffreestanding -Wall -Wextra $(CFLAGS) @@ -39,7 +39,7 @@ BTI_OBJS = \ teststubs-bti.o \ trampoline-bti.o gen/btitest: $(BTI_OBJS) - $(CC) $(CFLAGS_BTI) $(CFLAGS_COMMON) -nostdlib -o $@ $^ + $(CC) $(CFLAGS_BTI) $(CFLAGS_COMMON) -nostdlib -static -o $@ $^ NOBTI_OBJS = \ test-nobti.o \ @@ -50,7 +50,7 @@ NOBTI_OBJS = \ teststubs-nobti.o \ trampoline-nobti.o gen/nobtitest: $(NOBTI_OBJS) - $(CC) $(CFLAGS_BTI) $(CFLAGS_COMMON) -nostdlib -o $@ $^ + $(CC) $(CFLAGS_BTI) $(CFLAGS_COMMON) -nostdlib -static -o $@ $^ # Including KSFT lib.mk here will also mangle the TEST_GEN_PROGS list # to account for any OUTPUT target-dirs optionally provided by diff --git a/tools/testing/selftests/arm64/fp/.gitignore b/tools/testing/selftests/arm64/fp/.gitignore index c50d86331ed2..ea947af63882 100644 --- a/tools/testing/selftests/arm64/fp/.gitignore +++ b/tools/testing/selftests/arm64/fp/.gitignore @@ -1,8 +1,13 @@ fp-pidbench fpsimd-test +rdvl-sme rdvl-sve sve-probe-vls sve-ptrace sve-test +ssve-test vec-syscfg vlset +za-fork +za-ptrace +za-test diff --git a/tools/testing/selftests/arm64/fp/Makefile b/tools/testing/selftests/arm64/fp/Makefile index 95f0b877a060..a7c2286bf65b 100644 --- a/tools/testing/selftests/arm64/fp/Makefile +++ b/tools/testing/selftests/arm64/fp/Makefile @@ -1,24 +1,42 @@ # SPDX-License-Identifier: GPL-2.0 -CFLAGS += -I../../../../../usr/include/ -TEST_GEN_PROGS := sve-ptrace sve-probe-vls vec-syscfg -TEST_PROGS_EXTENDED := fp-pidbench fpsimd-test fpsimd-stress \ - rdvl-sve \ - sve-test sve-stress \ +# A proper top_srcdir is needed by KSFT(lib.mk) +top_srcdir = $(realpath ../../../../../) + +CFLAGS += -I$(top_srcdir)/usr/include/ + +TEST_GEN_PROGS := sve-ptrace sve-probe-vls vec-syscfg za-fork za-ptrace +TEST_GEN_PROGS_EXTENDED := fp-pidbench fpsimd-test \ + rdvl-sme rdvl-sve \ + sve-test \ + ssve-test \ + za-test \ vlset +TEST_PROGS_EXTENDED := fpsimd-stress sve-stress ssve-stress za-stress -all: $(TEST_GEN_PROGS) $(TEST_PROGS_EXTENDED) +EXTRA_CLEAN += $(OUTPUT)/asm-utils.o $(OUTPUT)/rdvl.o $(OUTPUT)/za-fork-asm.o -fp-pidbench: fp-pidbench.S asm-utils.o +# Build with nolibc to avoid effects due to libc's clone() support +$(OUTPUT)/fp-pidbench: fp-pidbench.S $(OUTPUT)/asm-utils.o + $(CC) -nostdlib $^ -o $@ +$(OUTPUT)/fpsimd-test: fpsimd-test.S $(OUTPUT)/asm-utils.o $(CC) -nostdlib $^ -o $@ -fpsimd-test: fpsimd-test.o asm-utils.o +$(OUTPUT)/rdvl-sve: rdvl-sve.c $(OUTPUT)/rdvl.o +$(OUTPUT)/rdvl-sme: rdvl-sme.c $(OUTPUT)/rdvl.o +$(OUTPUT)/sve-ptrace: sve-ptrace.c +$(OUTPUT)/sve-probe-vls: sve-probe-vls.c $(OUTPUT)/rdvl.o +$(OUTPUT)/sve-test: sve-test.S $(OUTPUT)/asm-utils.o $(CC) -nostdlib $^ -o $@ -rdvl-sve: rdvl-sve.o rdvl.o -sve-ptrace: sve-ptrace.o -sve-probe-vls: sve-probe-vls.o rdvl.o -sve-test: sve-test.o asm-utils.o +$(OUTPUT)/ssve-test: sve-test.S $(OUTPUT)/asm-utils.o + $(CC) -DSSVE -nostdlib $^ -o $@ +$(OUTPUT)/vec-syscfg: vec-syscfg.c $(OUTPUT)/rdvl.o +$(OUTPUT)/vlset: vlset.c +$(OUTPUT)/za-fork: za-fork.c $(OUTPUT)/za-fork-asm.o + $(CC) -fno-asynchronous-unwind-tables -fno-ident -s -Os -nostdlib \ + -include ../../../../include/nolibc/nolibc.h \ + -static -ffreestanding -Wall $^ -o $@ +$(OUTPUT)/za-ptrace: za-ptrace.c +$(OUTPUT)/za-test: za-test.S $(OUTPUT)/asm-utils.o $(CC) -nostdlib $^ -o $@ -vec-syscfg: vec-syscfg.o rdvl.o -vlset: vlset.o include ../../lib.mk diff --git a/tools/testing/selftests/arm64/fp/rdvl-sme.c b/tools/testing/selftests/arm64/fp/rdvl-sme.c new file mode 100644 index 000000000000..49b0b2e08bac --- /dev/null +++ b/tools/testing/selftests/arm64/fp/rdvl-sme.c @@ -0,0 +1,14 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <stdio.h> + +#include "rdvl.h" + +int main(void) +{ + int vl = rdvl_sme(); + + printf("%d\n", vl); + + return 0; +} diff --git a/tools/testing/selftests/arm64/fp/rdvl.S b/tools/testing/selftests/arm64/fp/rdvl.S index c916c1c9defd..20dc29996dc6 100644 --- a/tools/testing/selftests/arm64/fp/rdvl.S +++ b/tools/testing/selftests/arm64/fp/rdvl.S @@ -1,6 +1,8 @@ // SPDX-License-Identifier: GPL-2.0-only // Copyright (C) 2021 ARM Limited. +#include "sme-inst.h" + .arch_extension sve .globl rdvl_sve @@ -8,3 +10,11 @@ rdvl_sve: hint 34 // BTI C rdvl x0, #1 ret + +.globl rdvl_sme +rdvl_sme: + hint 34 // BTI C + + rdsvl 0, 1 + + ret diff --git a/tools/testing/selftests/arm64/fp/rdvl.h b/tools/testing/selftests/arm64/fp/rdvl.h index 7c9d953fc9e7..5d323679fbc9 100644 --- a/tools/testing/selftests/arm64/fp/rdvl.h +++ b/tools/testing/selftests/arm64/fp/rdvl.h @@ -3,6 +3,7 @@ #ifndef RDVL_H #define RDVL_H +int rdvl_sme(void); int rdvl_sve(void); #endif diff --git a/tools/testing/selftests/arm64/fp/sme-inst.h b/tools/testing/selftests/arm64/fp/sme-inst.h new file mode 100644 index 000000000000..7191e53ca1c0 --- /dev/null +++ b/tools/testing/selftests/arm64/fp/sme-inst.h @@ -0,0 +1,51 @@ +// SPDX-License-Identifier: GPL-2.0-only +// Copyright (C) 2021-2 ARM Limited. +// Original author: Mark Brown <broonie@kernel.org> + +#ifndef SME_INST_H +#define SME_INST_H + +/* + * RDSVL X\nx, #\imm + */ +.macro rdsvl nx, imm + .inst 0x4bf5800 \ + | (\imm << 5) \ + | (\nx) +.endm + +.macro smstop + msr S0_3_C4_C6_3, xzr +.endm + +.macro smstart_za + msr S0_3_C4_C5_3, xzr +.endm + +.macro smstart_sm + msr S0_3_C4_C3_3, xzr +.endm + +/* + * LDR (vector to ZA array): + * LDR ZA[\nw, #\offset], [X\nxbase, #\offset, MUL VL] + */ +.macro _ldr_za nw, nxbase, offset=0 + .inst 0xe1000000 \ + | (((\nw) & 3) << 13) \ + | ((\nxbase) << 5) \ + | ((\offset) & 7) +.endm + +/* + * STR (vector from ZA array): + * STR ZA[\nw, #\offset], [X\nxbase, #\offset, MUL VL] + */ +.macro _str_za nw, nxbase, offset=0 + .inst 0xe1200000 \ + | (((\nw) & 3) << 13) \ + | ((\nxbase) << 5) \ + | ((\offset) & 7) +.endm + +#endif diff --git a/tools/testing/selftests/arm64/fp/ssve-stress b/tools/testing/selftests/arm64/fp/ssve-stress new file mode 100644 index 000000000000..e2bd2cc184ad --- /dev/null +++ b/tools/testing/selftests/arm64/fp/ssve-stress @@ -0,0 +1,59 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0-only +# Copyright (C) 2015-2019 ARM Limited. +# Original author: Dave Martin <Dave.Martin@arm.com> + +set -ue + +NR_CPUS=`nproc` + +pids= +logs= + +cleanup () { + trap - INT TERM CHLD + set +e + + if [ -n "$pids" ]; then + kill $pids + wait $pids + pids= + fi + + if [ -n "$logs" ]; then + cat $logs + rm $logs + logs= + fi +} + +interrupt () { + cleanup + exit 0 +} + +child_died () { + cleanup + exit 1 +} + +trap interrupt INT TERM EXIT + +for x in `seq 0 $((NR_CPUS * 4))`; do + log=`mktemp` + logs=$logs\ $log + ./ssve-test >$log & + pids=$pids\ $! +done + +# Wait for all child processes to be created: +sleep 10 + +while :; do + kill -USR1 $pids +done & +pids=$pids\ $! + +wait + +exit 1 diff --git a/tools/testing/selftests/arm64/fp/sve-ptrace.c b/tools/testing/selftests/arm64/fp/sve-ptrace.c index 4c418b2021e0..8c4847977583 100644 --- a/tools/testing/selftests/arm64/fp/sve-ptrace.c +++ b/tools/testing/selftests/arm64/fp/sve-ptrace.c @@ -26,6 +26,10 @@ #define NT_ARM_SVE 0x405 #endif +#ifndef NT_ARM_SSVE +#define NT_ARM_SSVE 0x40b +#endif + struct vec_type { const char *name; unsigned long hwcap_type; @@ -42,11 +46,18 @@ static const struct vec_type vec_types[] = { .regset = NT_ARM_SVE, .prctl_set = PR_SVE_SET_VL, }, + { + .name = "Streaming SVE", + .hwcap_type = AT_HWCAP2, + .hwcap = HWCAP2_SME, + .regset = NT_ARM_SSVE, + .prctl_set = PR_SME_SET_VL, + }, }; -#define VL_TESTS (((SVE_VQ_MAX - SVE_VQ_MIN) + 1) * 3) +#define VL_TESTS (((SVE_VQ_MAX - SVE_VQ_MIN) + 1) * 4) #define FLAG_TESTS 2 -#define FPSIMD_TESTS 3 +#define FPSIMD_TESTS 2 #define EXPECTED_TESTS ((VL_TESTS + FLAG_TESTS + FPSIMD_TESTS) * ARRAY_SIZE(vec_types)) @@ -78,6 +89,15 @@ static int get_fpsimd(pid_t pid, struct user_fpsimd_state *fpsimd) return ptrace(PTRACE_GETREGSET, pid, NT_PRFPREG, &iov); } +static int set_fpsimd(pid_t pid, struct user_fpsimd_state *fpsimd) +{ + struct iovec iov; + + iov.iov_base = fpsimd; + iov.iov_len = sizeof(*fpsimd); + return ptrace(PTRACE_SETREGSET, pid, NT_PRFPREG, &iov); +} + static struct user_sve_header *get_sve(pid_t pid, const struct vec_type *type, void **buf, size_t *size) { @@ -240,28 +260,24 @@ static void check_u32(unsigned int vl, const char *reg, /* Access the FPSIMD registers via the SVE regset */ static void ptrace_sve_fpsimd(pid_t child, const struct vec_type *type) { - void *svebuf = NULL; - size_t svebufsz = 0; + void *svebuf; struct user_sve_header *sve; struct user_fpsimd_state *fpsimd, new_fpsimd; unsigned int i, j; unsigned char *p; + int ret; - /* New process should start with FPSIMD registers only */ - sve = get_sve(child, type, &svebuf, &svebufsz); - if (!sve) { - ksft_test_result_fail("get_sve(%s): %s\n", - type->name, strerror(errno)); - + svebuf = malloc(SVE_PT_SIZE(0, SVE_PT_REGS_FPSIMD)); + if (!svebuf) { + ksft_test_result_fail("Failed to allocate FPSIMD buffer\n"); return; - } else { - ksft_test_result_pass("get_sve(%s FPSIMD)\n", type->name); } - ksft_test_result((sve->flags & SVE_PT_REGS_MASK) == SVE_PT_REGS_FPSIMD, - "Got FPSIMD registers via %s\n", type->name); - if ((sve->flags & SVE_PT_REGS_MASK) != SVE_PT_REGS_FPSIMD) - goto out; + memset(svebuf, 0, SVE_PT_SIZE(0, SVE_PT_REGS_FPSIMD)); + sve = svebuf; + sve->flags = SVE_PT_REGS_FPSIMD; + sve->size = SVE_PT_SIZE(0, SVE_PT_REGS_FPSIMD); + sve->vl = 16; /* We don't care what the VL is */ /* Try to set a known FPSIMD state via PT_REGS_SVE */ fpsimd = (struct user_fpsimd_state *)((char *)sve + @@ -273,12 +289,11 @@ static void ptrace_sve_fpsimd(pid_t child, const struct vec_type *type) p[j] = j; } - if (set_sve(child, type, sve)) { - ksft_test_result_fail("set_sve(%s FPSIMD): %s\n", - type->name, strerror(errno)); - + ret = set_sve(child, type, sve); + ksft_test_result(ret == 0, "%s FPSIMD set via SVE: %d\n", + type->name, ret); + if (ret) goto out; - } /* Verify via the FPSIMD regset */ if (get_fpsimd(child, &new_fpsimd)) { @@ -395,7 +410,7 @@ out: free(write_buf); } -/* Validate attempting to set SVE data and read SVE data */ +/* Validate attempting to set SVE data and read it via the FPSIMD regset */ static void ptrace_set_sve_get_fpsimd_data(pid_t child, const struct vec_type *type, unsigned int vl) @@ -478,6 +493,115 @@ out: free(write_buf); } +/* Validate attempting to set FPSIMD data and read it via the SVE regset */ +static void ptrace_set_fpsimd_get_sve_data(pid_t child, + const struct vec_type *type, + unsigned int vl) +{ + void *read_buf = NULL; + unsigned char *p; + struct user_sve_header *read_sve; + unsigned int vq = sve_vq_from_vl(vl); + struct user_fpsimd_state write_fpsimd; + int ret, i, j; + size_t read_sve_size = 0; + size_t expected_size; + int errors = 0; + + if (__BYTE_ORDER == __BIG_ENDIAN) { + ksft_test_result_skip("Big endian not supported\n"); + return; + } + + for (i = 0; i < 32; ++i) { + p = (unsigned char *)&write_fpsimd.vregs[i]; + + for (j = 0; j < sizeof(write_fpsimd.vregs[i]); ++j) + p[j] = j; + } + + ret = set_fpsimd(child, &write_fpsimd); + if (ret != 0) { + ksft_test_result_fail("Failed to set FPSIMD state: %d\n)", + ret); + return; + } + + if (!get_sve(child, type, (void **)&read_buf, &read_sve_size)) { + ksft_test_result_fail("Failed to read %s VL %u data\n", + type->name, vl); + return; + } + read_sve = read_buf; + + if (read_sve->vl != vl) { + ksft_test_result_fail("Child VL != expected VL %d\n", + read_sve->vl, vl); + goto out; + } + + /* The kernel may return either SVE or FPSIMD format */ + switch (read_sve->flags & SVE_PT_REGS_MASK) { + case SVE_PT_REGS_FPSIMD: + expected_size = SVE_PT_FPSIMD_SIZE(vq, SVE_PT_REGS_FPSIMD); + if (read_sve_size < expected_size) { + ksft_test_result_fail("Read %d bytes, expected %d\n", + read_sve_size, expected_size); + goto out; + } + + ret = memcmp(&write_fpsimd, read_buf + SVE_PT_FPSIMD_OFFSET, + sizeof(write_fpsimd)); + if (ret != 0) { + ksft_print_msg("Read FPSIMD data mismatch\n"); + errors++; + } + break; + + case SVE_PT_REGS_SVE: + expected_size = SVE_PT_SVE_SIZE(vq, SVE_PT_REGS_SVE); + if (read_sve_size < expected_size) { + ksft_test_result_fail("Read %d bytes, expected %d\n", + read_sve_size, expected_size); + goto out; + } + + for (i = 0; i < __SVE_NUM_ZREGS; i++) { + __uint128_t tmp = 0; + + /* + * Z regs are stored endianness invariant, this won't + * work for big endian + */ + memcpy(&tmp, read_buf + SVE_PT_SVE_ZREG_OFFSET(vq, i), + sizeof(tmp)); + + if (tmp != write_fpsimd.vregs[i]) { + ksft_print_msg("Mismatch in FPSIMD for %s VL %u Z%d/V%d\n", + type->name, vl, i, i); + errors++; + } + } + + check_u32(vl, "FPSR", &write_fpsimd.fpsr, + read_buf + SVE_PT_SVE_FPSR_OFFSET(vq), &errors); + check_u32(vl, "FPCR", &write_fpsimd.fpcr, + read_buf + SVE_PT_SVE_FPCR_OFFSET(vq), &errors); + break; + default: + ksft_print_msg("Unexpected regs type %d\n", + read_sve->flags & SVE_PT_REGS_MASK); + errors++; + break; + } + + ksft_test_result(errors == 0, "Set FPSIMD, read via SVE for %s VL %u\n", + type->name, vl); + +out: + free(read_buf); +} + static int do_parent(pid_t child) { int ret = EXIT_FAILURE; @@ -548,11 +672,9 @@ static int do_parent(pid_t child) if (getauxval(vec_types[i].hwcap_type) & vec_types[i].hwcap) { ptrace_sve_fpsimd(child, &vec_types[i]); } else { - ksft_test_result_skip("%s FPSIMD get via SVE\n", - vec_types[i].name); ksft_test_result_skip("%s FPSIMD set via SVE\n", vec_types[i].name); - ksft_test_result_skip("%s set read via FPSIMD\n", + ksft_test_result_skip("%s FPSIMD read\n", vec_types[i].name); } @@ -585,11 +707,14 @@ static int do_parent(pid_t child) if (vl_supported) { ptrace_set_sve_get_sve_data(child, &vec_types[i], vl); ptrace_set_sve_get_fpsimd_data(child, &vec_types[i], vl); + ptrace_set_fpsimd_get_sve_data(child, &vec_types[i], vl); } else { ksft_test_result_skip("%s set SVE get SVE for VL %d\n", vec_types[i].name, vl); ksft_test_result_skip("%s set SVE get FPSIMD for VL %d\n", vec_types[i].name, vl); + ksft_test_result_skip("%s set FPSIMD get SVE for VL %d\n", + vec_types[i].name, vl); } } } diff --git a/tools/testing/selftests/arm64/fp/sve-test.S b/tools/testing/selftests/arm64/fp/sve-test.S index f5b1b48ffff2..589264231a2d 100644 --- a/tools/testing/selftests/arm64/fp/sve-test.S +++ b/tools/testing/selftests/arm64/fp/sve-test.S @@ -13,6 +13,7 @@ #include <asm/unistd.h> #include "assembler.h" #include "asm-offsets.h" +#include "sme-inst.h" #define NZR 32 #define NPR 16 @@ -156,6 +157,7 @@ endfunction // We fill the upper lanes of FFR with zeros. // Beware: corrupts P0. function setup_ffr +#ifndef SSVE mov x4, x30 and w0, w0, #0x3 @@ -178,6 +180,9 @@ function setup_ffr wrffr p0.b ret x4 +#else + ret +#endif endfunction // Trivial memory compare: compare x2 bytes starting at address x0 with @@ -260,6 +265,7 @@ endfunction // Beware -- corrupts P0. // Clobbers x0-x5. function check_ffr +#ifndef SSVE mov x3, x30 ldr x4, =scratch @@ -280,6 +286,9 @@ function check_ffr mov x2, x5 mov x30, x3 b memcmp +#else + ret +#endif endfunction // Any SVE register modified here can cause corruption in the main @@ -295,10 +304,12 @@ function irritator_handler movi v0.8b, #1 movi v9.16b, #2 movi v31.8b, #3 +#ifndef SSVE // And P0 rdffr p0.b // And FFR wrffr p15.b +#endif ret endfunction @@ -359,6 +370,11 @@ endfunction .globl _start function _start _start: +#ifdef SSVE + puts "Streaming mode " + smstart_sm +#endif + // Sanity-check and report the vector length rdvl x19, #8 @@ -407,6 +423,10 @@ _start: orr w2, w2, #SA_NODEFER bl setsignal +#ifdef SSVE + smstart_sm // syscalls will have exited streaming mode +#endif + mov x22, #0 // generation number, increments per iteration .Ltest_loop: rdvl x0, #8 diff --git a/tools/testing/selftests/arm64/fp/vec-syscfg.c b/tools/testing/selftests/arm64/fp/vec-syscfg.c index c90658811a83..9bcfcdc34ee9 100644 --- a/tools/testing/selftests/arm64/fp/vec-syscfg.c +++ b/tools/testing/selftests/arm64/fp/vec-syscfg.c @@ -51,6 +51,16 @@ static struct vec_data vec_data[] = { .prctl_set = PR_SVE_SET_VL, .default_vl_file = "/proc/sys/abi/sve_default_vector_length", }, + { + .name = "SME", + .hwcap_type = AT_HWCAP2, + .hwcap = HWCAP2_SME, + .rdvl = rdvl_sme, + .rdvl_binary = "./rdvl-sme", + .prctl_get = PR_SME_GET_VL, + .prctl_set = PR_SME_SET_VL, + .default_vl_file = "/proc/sys/abi/sme_default_vector_length", + }, }; static int stdio_read_integer(FILE *f, const char *what, int *val) diff --git a/tools/testing/selftests/arm64/fp/vlset.c b/tools/testing/selftests/arm64/fp/vlset.c index 308d27a68226..76912a581a95 100644 --- a/tools/testing/selftests/arm64/fp/vlset.c +++ b/tools/testing/selftests/arm64/fp/vlset.c @@ -22,12 +22,15 @@ static int inherit = 0; static int no_inherit = 0; static int force = 0; static unsigned long vl; +static int set_ctl = PR_SVE_SET_VL; +static int get_ctl = PR_SVE_GET_VL; static const struct option options[] = { { "force", no_argument, NULL, 'f' }, { "inherit", no_argument, NULL, 'i' }, { "max", no_argument, NULL, 'M' }, { "no-inherit", no_argument, &no_inherit, 1 }, + { "sme", no_argument, NULL, 's' }, { "help", no_argument, NULL, '?' }, {} }; @@ -50,6 +53,9 @@ static int parse_options(int argc, char **argv) case 'M': vl = SVE_VL_MAX; break; case 'f': force = 1; break; case 'i': inherit = 1; break; + case 's': set_ctl = PR_SME_SET_VL; + get_ctl = PR_SME_GET_VL; + break; case 0: break; default: goto error; } @@ -125,14 +131,14 @@ int main(int argc, char **argv) if (inherit) flags |= PR_SVE_VL_INHERIT; - t = prctl(PR_SVE_SET_VL, vl | flags); + t = prctl(set_ctl, vl | flags); if (t < 0) { fprintf(stderr, "%s: PR_SVE_SET_VL: %s\n", program_name, strerror(errno)); goto error; } - t = prctl(PR_SVE_GET_VL); + t = prctl(get_ctl); if (t == -1) { fprintf(stderr, "%s: PR_SVE_GET_VL: %s\n", program_name, strerror(errno)); diff --git a/tools/testing/selftests/arm64/fp/za-fork-asm.S b/tools/testing/selftests/arm64/fp/za-fork-asm.S new file mode 100644 index 000000000000..2fafadd491c3 --- /dev/null +++ b/tools/testing/selftests/arm64/fp/za-fork-asm.S @@ -0,0 +1,61 @@ +// SPDX-License-Identifier: GPL-2.0-only +// Copyright (C) 2021 ARM Limited. + +#include "sme-inst.h" + +.arch_extension sve + +#define MAGIC 42 + +#define MAXVL 2048 +#define MAXVL_B (MAXVL / 8) + +.pushsection .text +.data +.align 4 +scratch: + .space MAXVL_B +.popsection + +.globl fork_test +fork_test: + smstart_za + + // For simplicity just set one word in one vector, other tests + // cover general data corruption issues. + ldr x0, =scratch + mov x1, #MAGIC + str x1, [x0] + mov w12, wzr + _ldr_za 12, 0 // ZA.H[W12] loaded from [X0] + + // Tail call into the C portion that does the fork & verify + b fork_test_c + +.globl verify_fork +verify_fork: + // SVCR should have ZA=1, SM=0 + mrs x0, S3_3_C4_C2_2 + and x1, x0, #3 + cmp x1, #2 + beq 1f + mov x0, xzr + b 100f +1: + + // ZA should still have the value we loaded + ldr x0, =scratch + mov w12, wzr + _str_za 12, 0 // ZA.H[W12] stored to [X0] + ldr x1, [x0] + cmp x1, #MAGIC + beq 2f + mov x0, xzr + b 100f + +2: + // All tests passed + mov x0, #1 +100: + ret + diff --git a/tools/testing/selftests/arm64/fp/za-fork.c b/tools/testing/selftests/arm64/fp/za-fork.c new file mode 100644 index 000000000000..ff475c649e96 --- /dev/null +++ b/tools/testing/selftests/arm64/fp/za-fork.c @@ -0,0 +1,156 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2022 ARM Limited. + * Original author: Mark Brown <broonie@kernel.org> + */ + +// SPDX-License-Identifier: GPL-2.0-only + +#include <linux/sched.h> +#include <linux/wait.h> + +#define EXPECTED_TESTS 1 + +static void putstr(const char *str) +{ + write(1, str, strlen(str)); +} + +static void putnum(unsigned int num) +{ + char c; + + if (num / 10) + putnum(num / 10); + + c = '0' + (num % 10); + write(1, &c, 1); +} + +static int tests_run; +static int tests_passed; +static int tests_failed; +static int tests_skipped; + +static void print_summary(void) +{ + if (tests_passed + tests_failed + tests_skipped != EXPECTED_TESTS) + putstr("# UNEXPECTED TEST COUNT: "); + + putstr("# Totals: pass:"); + putnum(tests_passed); + putstr(" fail:"); + putnum(tests_failed); + putstr(" xfail:0 xpass:0 skip:"); + putnum(tests_skipped); + putstr(" error:0\n"); +} + +int fork_test(void); +int verify_fork(void); + +/* + * If we fork the value in the parent should be unchanged and the + * child should start with the same value. This is called from the + * fork_test() asm function. + */ +int fork_test_c(void) +{ + pid_t newpid, waiting; + int child_status, parent_result; + + newpid = fork(); + if (newpid == 0) { + /* In child */ + if (!verify_fork()) { + putstr("# ZA state invalid in child\n"); + exit(0); + } else { + exit(1); + } + } + if (newpid < 0) { + putstr("# fork() failed: -"); + putnum(-newpid); + putstr("\n"); + return 0; + } + + parent_result = verify_fork(); + if (!parent_result) + putstr("# ZA state invalid in parent\n"); + + for (;;) { + waiting = waitpid(newpid, &child_status, 0); + + if (waiting < 0) { + if (errno == EINTR) + continue; + putstr("# waitpid() failed: "); + putnum(errno); + putstr("\n"); + return 0; + } + if (waiting != newpid) { + putstr("# waitpid() returned wrong PID\n"); + return 0; + } + + if (!WIFEXITED(child_status)) { + putstr("# child did not exit\n"); + return 0; + } + + return WEXITSTATUS(child_status) && parent_result; + } +} + +#define run_test(name) \ + if (name()) { \ + tests_passed++; \ + } else { \ + tests_failed++; \ + putstr("not "); \ + } \ + putstr("ok "); \ + putnum(++tests_run); \ + putstr(" " #name "\n"); + +int main(int argc, char **argv) +{ + int ret, i; + + putstr("TAP version 13\n"); + putstr("1.."); + putnum(EXPECTED_TESTS); + putstr("\n"); + + putstr("# PID: "); + putnum(getpid()); + putstr("\n"); + + /* + * This test is run with nolibc which doesn't support hwcap and + * it's probably disproportionate to implement so instead check + * for the default vector length configuration in /proc. + */ + ret = open("/proc/sys/abi/sme_default_vector_length", O_RDONLY, 0); + if (ret >= 0) { + run_test(fork_test); + + } else { + putstr("# SME support not present\n"); + + for (i = 0; i < EXPECTED_TESTS; i++) { + putstr("ok "); + putnum(i); + putstr(" skipped\n"); + } + + tests_skipped += EXPECTED_TESTS; + } + + print_summary(); + + return 0; +} diff --git a/tools/testing/selftests/arm64/fp/za-ptrace.c b/tools/testing/selftests/arm64/fp/za-ptrace.c new file mode 100644 index 000000000000..bf6158654056 --- /dev/null +++ b/tools/testing/selftests/arm64/fp/za-ptrace.c @@ -0,0 +1,356 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2021 ARM Limited. + */ +#include <errno.h> +#include <stdbool.h> +#include <stddef.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> +#include <sys/auxv.h> +#include <sys/prctl.h> +#include <sys/ptrace.h> +#include <sys/types.h> +#include <sys/uio.h> +#include <sys/wait.h> +#include <asm/sigcontext.h> +#include <asm/ptrace.h> + +#include "../../kselftest.h" + +/* <linux/elf.h> and <sys/auxv.h> don't like each other, so: */ +#ifndef NT_ARM_ZA +#define NT_ARM_ZA 0x40c +#endif + +#define EXPECTED_TESTS (((SVE_VQ_MAX - SVE_VQ_MIN) + 1) * 3) + +static void fill_buf(char *buf, size_t size) +{ + int i; + + for (i = 0; i < size; i++) + buf[i] = random(); +} + +static int do_child(void) +{ + if (ptrace(PTRACE_TRACEME, -1, NULL, NULL)) + ksft_exit_fail_msg("PTRACE_TRACEME", strerror(errno)); + + if (raise(SIGSTOP)) + ksft_exit_fail_msg("raise(SIGSTOP)", strerror(errno)); + + return EXIT_SUCCESS; +} + +static struct user_za_header *get_za(pid_t pid, void **buf, size_t *size) +{ + struct user_za_header *za; + void *p; + size_t sz = sizeof(*za); + struct iovec iov; + + while (1) { + if (*size < sz) { + p = realloc(*buf, sz); + if (!p) { + errno = ENOMEM; + goto error; + } + + *buf = p; + *size = sz; + } + + iov.iov_base = *buf; + iov.iov_len = sz; + if (ptrace(PTRACE_GETREGSET, pid, NT_ARM_ZA, &iov)) + goto error; + + za = *buf; + if (za->size <= sz) + break; + + sz = za->size; + } + + return za; + +error: + return NULL; +} + +static int set_za(pid_t pid, const struct user_za_header *za) +{ + struct iovec iov; + + iov.iov_base = (void *)za; + iov.iov_len = za->size; + return ptrace(PTRACE_SETREGSET, pid, NT_ARM_ZA, &iov); +} + +/* Validate attempting to set the specfied VL via ptrace */ +static void ptrace_set_get_vl(pid_t child, unsigned int vl, bool *supported) +{ + struct user_za_header za; + struct user_za_header *new_za = NULL; + size_t new_za_size = 0; + int ret, prctl_vl; + + *supported = false; + + /* Check if the VL is supported in this process */ + prctl_vl = prctl(PR_SME_SET_VL, vl); + if (prctl_vl == -1) + ksft_exit_fail_msg("prctl(PR_SME_SET_VL) failed: %s (%d)\n", + strerror(errno), errno); + + /* If the VL is not supported then a supported VL will be returned */ + *supported = (prctl_vl == vl); + + /* Set the VL by doing a set with no register payload */ + memset(&za, 0, sizeof(za)); + za.size = sizeof(za); + za.vl = vl; + ret = set_za(child, &za); + if (ret != 0) { + ksft_test_result_fail("Failed to set VL %u\n", vl); + return; + } + + /* + * Read back the new register state and verify that we have the + * same VL that we got from prctl() on ourselves. + */ + if (!get_za(child, (void **)&new_za, &new_za_size)) { + ksft_test_result_fail("Failed to read VL %u\n", vl); + return; + } + + ksft_test_result(new_za->vl = prctl_vl, "Set VL %u\n", vl); + + free(new_za); +} + +/* Validate attempting to set no ZA data and read it back */ +static void ptrace_set_no_data(pid_t child, unsigned int vl) +{ + void *read_buf = NULL; + struct user_za_header write_za; + struct user_za_header *read_za; + size_t read_za_size = 0; + int ret; + + /* Set up some data and write it out */ + memset(&write_za, 0, sizeof(write_za)); + write_za.size = ZA_PT_ZA_OFFSET; + write_za.vl = vl; + + ret = set_za(child, &write_za); + if (ret != 0) { + ksft_test_result_fail("Failed to set VL %u no data\n", vl); + return; + } + + /* Read the data back */ + if (!get_za(child, (void **)&read_buf, &read_za_size)) { + ksft_test_result_fail("Failed to read VL %u no data\n", vl); + return; + } + read_za = read_buf; + + /* We might read more data if there's extensions we don't know */ + if (read_za->size < write_za.size) { + ksft_test_result_fail("VL %u wrote %d bytes, only read %d\n", + vl, write_za.size, read_za->size); + goto out_read; + } + + ksft_test_result(read_za->size == write_za.size, + "Disabled ZA for VL %u\n", vl); + +out_read: + free(read_buf); +} + +/* Validate attempting to set data and read it back */ +static void ptrace_set_get_data(pid_t child, unsigned int vl) +{ + void *write_buf; + void *read_buf = NULL; + struct user_za_header *write_za; + struct user_za_header *read_za; + size_t read_za_size = 0; + unsigned int vq = sve_vq_from_vl(vl); + int ret; + size_t data_size; + + data_size = ZA_PT_SIZE(vq); + write_buf = malloc(data_size); + if (!write_buf) { + ksft_test_result_fail("Error allocating %d byte buffer for VL %u\n", + data_size, vl); + return; + } + write_za = write_buf; + + /* Set up some data and write it out */ + memset(write_za, 0, data_size); + write_za->size = data_size; + write_za->vl = vl; + + fill_buf(write_buf + ZA_PT_ZA_OFFSET, ZA_PT_ZA_SIZE(vq)); + + ret = set_za(child, write_za); + if (ret != 0) { + ksft_test_result_fail("Failed to set VL %u data\n", vl); + goto out; + } + + /* Read the data back */ + if (!get_za(child, (void **)&read_buf, &read_za_size)) { + ksft_test_result_fail("Failed to read VL %u data\n", vl); + goto out; + } + read_za = read_buf; + + /* We might read more data if there's extensions we don't know */ + if (read_za->size < write_za->size) { + ksft_test_result_fail("VL %u wrote %d bytes, only read %d\n", + vl, write_za->size, read_za->size); + goto out_read; + } + + ksft_test_result(memcmp(write_buf + ZA_PT_ZA_OFFSET, + read_buf + ZA_PT_ZA_OFFSET, + ZA_PT_ZA_SIZE(vq)) == 0, + "Data match for VL %u\n", vl); + +out_read: + free(read_buf); +out: + free(write_buf); +} + +static int do_parent(pid_t child) +{ + int ret = EXIT_FAILURE; + pid_t pid; + int status; + siginfo_t si; + unsigned int vq, vl; + bool vl_supported; + + /* Attach to the child */ + while (1) { + int sig; + + pid = wait(&status); + if (pid == -1) { + perror("wait"); + goto error; + } + + /* + * This should never happen but it's hard to flag in + * the framework. + */ + if (pid != child) + continue; + + if (WIFEXITED(status) || WIFSIGNALED(status)) + ksft_exit_fail_msg("Child died unexpectedly\n"); + + if (!WIFSTOPPED(status)) + goto error; + + sig = WSTOPSIG(status); + + if (ptrace(PTRACE_GETSIGINFO, pid, NULL, &si)) { + if (errno == ESRCH) + goto disappeared; + + if (errno == EINVAL) { + sig = 0; /* bust group-stop */ + goto cont; + } + + ksft_test_result_fail("PTRACE_GETSIGINFO: %s\n", + strerror(errno)); + goto error; + } + + if (sig == SIGSTOP && si.si_code == SI_TKILL && + si.si_pid == pid) + break; + + cont: + if (ptrace(PTRACE_CONT, pid, NULL, sig)) { + if (errno == ESRCH) + goto disappeared; + + ksft_test_result_fail("PTRACE_CONT: %s\n", + strerror(errno)); + goto error; + } + } + + ksft_print_msg("Parent is %d, child is %d\n", getpid(), child); + + /* Step through every possible VQ */ + for (vq = SVE_VQ_MIN; vq <= SVE_VQ_MAX; vq++) { + vl = sve_vl_from_vq(vq); + + /* First, try to set this vector length */ + ptrace_set_get_vl(child, vl, &vl_supported); + + /* If the VL is supported validate data set/get */ + if (vl_supported) { + ptrace_set_no_data(child, vl); + ptrace_set_get_data(child, vl); + } else { + ksft_test_result_skip("Disabled ZA for VL %u\n", vl); + ksft_test_result_skip("Get and set data for VL %u\n", + vl); + } + } + + ret = EXIT_SUCCESS; + +error: + kill(child, SIGKILL); + +disappeared: + return ret; +} + +int main(void) +{ + int ret = EXIT_SUCCESS; + pid_t child; + + srandom(getpid()); + + ksft_print_header(); + + if (!(getauxval(AT_HWCAP2) & HWCAP2_SME)) { + ksft_set_plan(1); + ksft_exit_skip("SME not available\n"); + } + + ksft_set_plan(EXPECTED_TESTS); + + child = fork(); + if (!child) + return do_child(); + + if (do_parent(child)) + ret = EXIT_FAILURE; + + ksft_print_cnts(); + + return ret; +} diff --git a/tools/testing/selftests/arm64/fp/za-stress b/tools/testing/selftests/arm64/fp/za-stress new file mode 100644 index 000000000000..5ac386b55b95 --- /dev/null +++ b/tools/testing/selftests/arm64/fp/za-stress @@ -0,0 +1,59 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0-only +# Copyright (C) 2015-2019 ARM Limited. +# Original author: Dave Martin <Dave.Martin@arm.com> + +set -ue + +NR_CPUS=`nproc` + +pids= +logs= + +cleanup () { + trap - INT TERM CHLD + set +e + + if [ -n "$pids" ]; then + kill $pids + wait $pids + pids= + fi + + if [ -n "$logs" ]; then + cat $logs + rm $logs + logs= + fi +} + +interrupt () { + cleanup + exit 0 +} + +child_died () { + cleanup + exit 1 +} + +trap interrupt INT TERM EXIT + +for x in `seq 0 $((NR_CPUS * 4))`; do + log=`mktemp` + logs=$logs\ $log + ./za-test >$log & + pids=$pids\ $! +done + +# Wait for all child processes to be created: +sleep 10 + +while :; do + kill -USR1 $pids +done & +pids=$pids\ $! + +wait + +exit 1 diff --git a/tools/testing/selftests/arm64/fp/za-test.S b/tools/testing/selftests/arm64/fp/za-test.S new file mode 100644 index 000000000000..9ab6f9cd9623 --- /dev/null +++ b/tools/testing/selftests/arm64/fp/za-test.S @@ -0,0 +1,388 @@ +// SPDX-License-Identifier: GPL-2.0-only +// Copyright (C) 2021 ARM Limited. +// Original author: Mark Brown <broonie@kernel.org> +// +// Scalable Matrix Extension ZA context switch test +// Repeatedly writes unique test patterns into each ZA tile +// and reads them back to verify integrity. +// +// for x in `seq 1 NR_CPUS`; do sve-test & pids=$pids\ $! ; done +// (leave it running for as long as you want...) +// kill $pids + +#include <asm/unistd.h> +#include "assembler.h" +#include "asm-offsets.h" +#include "sme-inst.h" + +.arch_extension sve + +#define MAXVL 2048 +#define MAXVL_B (MAXVL / 8) + +// Declare some storage space to shadow ZA register contents and a +// scratch buffer for a vector. +.pushsection .text +.data +.align 4 +zaref: + .space MAXVL_B * MAXVL_B +scratch: + .space MAXVL_B +.popsection + +// Trivial memory copy: copy x2 bytes, starting at address x1, to address x0. +// Clobbers x0-x3 +function memcpy + cmp x2, #0 + b.eq 1f +0: ldrb w3, [x1], #1 + strb w3, [x0], #1 + subs x2, x2, #1 + b.ne 0b +1: ret +endfunction + +// Generate a test pattern for storage in ZA +// x0: pid +// x1: row in ZA +// x2: generation + +// These values are used to constuct a 32-bit pattern that is repeated in the +// scratch buffer as many times as will fit: +// bits 31:28 generation number (increments once per test_loop) +// bits 27:16 pid +// bits 15: 8 row number +// bits 7: 0 32-bit lane index + +function pattern + mov w3, wzr + bfi w3, w0, #16, #12 // PID + bfi w3, w1, #8, #8 // Row + bfi w3, w2, #28, #4 // Generation + + ldr x0, =scratch + mov w1, #MAXVL_B / 4 + +0: str w3, [x0], #4 + add w3, w3, #1 // Lane + subs w1, w1, #1 + b.ne 0b + + ret +endfunction + +// Get the address of shadow data for ZA horizontal vector xn +.macro _adrza xd, xn, nrtmp + ldr \xd, =zaref + rdsvl \nrtmp, 1 + madd \xd, x\nrtmp, \xn, \xd +.endm + +// Set up test pattern in a ZA horizontal vector +// x0: pid +// x1: row number +// x2: generation +function setup_za + mov x4, x30 + mov x12, x1 // Use x12 for vector select + + bl pattern // Get pattern in scratch buffer + _adrza x0, x12, 2 // Shadow buffer pointer to x0 and x5 + mov x5, x0 + ldr x1, =scratch + bl memcpy // length set up in x2 by _adrza + + _ldr_za 12, 5 // load vector w12 from pointer x5 + + ret x4 +endfunction + +// Trivial memory compare: compare x2 bytes starting at address x0 with +// bytes starting at address x1. +// Returns only if all bytes match; otherwise, the program is aborted. +// Clobbers x0-x5. +function memcmp + cbz x2, 2f + + stp x0, x1, [sp, #-0x20]! + str x2, [sp, #0x10] + + mov x5, #0 +0: ldrb w3, [x0, x5] + ldrb w4, [x1, x5] + add x5, x5, #1 + cmp w3, w4 + b.ne 1f + subs x2, x2, #1 + b.ne 0b + +1: ldr x2, [sp, #0x10] + ldp x0, x1, [sp], #0x20 + b.ne barf + +2: ret +endfunction + +// Verify that a ZA vector matches its shadow in memory, else abort +// x0: row number +// Clobbers x0-x7 and x12. +function check_za + mov x3, x30 + + mov x12, x0 + _adrza x5, x0, 6 // pointer to expected value in x5 + mov x4, x0 + ldr x7, =scratch // x7 is scratch + + mov x0, x7 // Poison scratch + mov x1, x6 + bl memfill_ae + + _str_za 12, 7 // save vector w12 to pointer x7 + + mov x0, x5 + mov x1, x7 + mov x2, x6 + mov x30, x3 + b memcmp +endfunction + +// Any SME register modified here can cause corruption in the main +// thread -- but *only* the locations modified here. +function irritator_handler + // Increment the irritation signal count (x23): + ldr x0, [x2, #ucontext_regs + 8 * 23] + add x0, x0, #1 + str x0, [x2, #ucontext_regs + 8 * 23] + + // Corrupt some random ZA data +#if 0 + adr x0, .text + (irritator_handler - .text) / 16 * 16 + movi v0.8b, #1 + movi v9.16b, #2 + movi v31.8b, #3 +#endif + + ret +endfunction + +function terminate_handler + mov w21, w0 + mov x20, x2 + + puts "Terminated by signal " + mov w0, w21 + bl putdec + puts ", no error, iterations=" + ldr x0, [x20, #ucontext_regs + 8 * 22] + bl putdec + puts ", signals=" + ldr x0, [x20, #ucontext_regs + 8 * 23] + bl putdecn + + mov x0, #0 + mov x8, #__NR_exit + svc #0 +endfunction + +// w0: signal number +// x1: sa_action +// w2: sa_flags +// Clobbers x0-x6,x8 +function setsignal + str x30, [sp, #-((sa_sz + 15) / 16 * 16 + 16)]! + + mov w4, w0 + mov x5, x1 + mov w6, w2 + + add x0, sp, #16 + mov x1, #sa_sz + bl memclr + + mov w0, w4 + add x1, sp, #16 + str w6, [x1, #sa_flags] + str x5, [x1, #sa_handler] + mov x2, #0 + mov x3, #sa_mask_sz + mov x8, #__NR_rt_sigaction + svc #0 + + cbz w0, 1f + + puts "sigaction failure\n" + b .Labort + +1: ldr x30, [sp], #((sa_sz + 15) / 16 * 16 + 16) + ret +endfunction + +// Main program entry point +.globl _start +function _start +_start: + puts "Streaming mode " + smstart_za + + // Sanity-check and report the vector length + + rdsvl 19, 8 + cmp x19, #128 + b.lo 1f + cmp x19, #2048 + b.hi 1f + tst x19, #(8 - 1) + b.eq 2f + +1: puts "bad vector length: " + mov x0, x19 + bl putdecn + b .Labort + +2: puts "vector length:\t" + mov x0, x19 + bl putdec + puts " bits\n" + + // Obtain our PID, to ensure test pattern uniqueness between processes + mov x8, #__NR_getpid + svc #0 + mov x20, x0 + + puts "PID:\t" + mov x0, x20 + bl putdecn + + mov x23, #0 // Irritation signal count + + mov w0, #SIGINT + adr x1, terminate_handler + mov w2, #SA_SIGINFO + bl setsignal + + mov w0, #SIGTERM + adr x1, terminate_handler + mov w2, #SA_SIGINFO + bl setsignal + + mov w0, #SIGUSR1 + adr x1, irritator_handler + mov w2, #SA_SIGINFO + orr w2, w2, #SA_NODEFER + bl setsignal + + mov x22, #0 // generation number, increments per iteration +.Ltest_loop: + rdsvl 0, 8 + cmp x0, x19 + b.ne vl_barf + + rdsvl 21, 1 // Set up ZA & shadow with test pattern +0: mov x0, x20 + sub x1, x21, #1 + mov x2, x22 + bl setup_za + subs x21, x21, #1 + b.ne 0b + + and x8, x22, #127 // Every 128 interations... + cbz x8, 0f + mov x8, #__NR_getpid // (otherwise minimal syscall) + b 1f +0: + mov x8, #__NR_sched_yield // ...encourage preemption +1: + svc #0 + + mrs x0, S3_3_C4_C2_2 // SVCR should have ZA=1,SM=0 + and x1, x0, #3 + cmp x1, #2 + b.ne svcr_barf + + rdsvl 21, 1 // Verify that the data made it through + rdsvl 24, 1 // Verify that the data made it through +0: sub x0, x24, x21 + bl check_za + subs x21, x21, #1 + bne 0b + + add x22, x22, #1 // Everything still working + b .Ltest_loop + +.Labort: + mov x0, #0 + mov x1, #SIGABRT + mov x8, #__NR_kill + svc #0 +endfunction + +function barf +// fpsimd.c acitivty log dump hack +// ldr w0, =0xdeadc0de +// mov w8, #__NR_exit +// svc #0 +// end hack + smstop + mov x10, x0 // expected data + mov x11, x1 // actual data + mov x12, x2 // data size + + puts "Mismatch: PID=" + mov x0, x20 + bl putdec + puts ", iteration=" + mov x0, x22 + bl putdec + puts ", row=" + mov x0, x21 + bl putdecn + puts "\tExpected [" + mov x0, x10 + mov x1, x12 + bl dumphex + puts "]\n\tGot [" + mov x0, x11 + mov x1, x12 + bl dumphex + puts "]\n" + + mov x8, #__NR_getpid + svc #0 +// fpsimd.c acitivty log dump hack +// ldr w0, =0xdeadc0de +// mov w8, #__NR_exit +// svc #0 +// ^ end of hack + mov x1, #SIGABRT + mov x8, #__NR_kill + svc #0 +// mov x8, #__NR_exit +// mov x1, #1 +// svc #0 +endfunction + +function vl_barf + mov x10, x0 + + puts "Bad active VL: " + mov x0, x10 + bl putdecn + + mov x8, #__NR_exit + mov x1, #1 + svc #0 +endfunction + +function svcr_barf + mov x10, x0 + + puts "Bad SVCR: " + mov x0, x10 + bl putdecn + + mov x8, #__NR_exit + mov x1, #1 + svc #0 +endfunction diff --git a/tools/testing/selftests/arm64/mte/.gitignore b/tools/testing/selftests/arm64/mte/.gitignore index d1fe4ddf1669..052d0f9f92b3 100644 --- a/tools/testing/selftests/arm64/mte/.gitignore +++ b/tools/testing/selftests/arm64/mte/.gitignore @@ -3,5 +3,6 @@ check_gcr_el1_cswitch check_tags_inclusion check_child_memory check_mmap_options +check_prctl check_ksm_options check_user_mem diff --git a/tools/testing/selftests/arm64/mte/check_child_memory.c b/tools/testing/selftests/arm64/mte/check_child_memory.c index 43bd94f853ba..7597fc632cad 100644 --- a/tools/testing/selftests/arm64/mte/check_child_memory.c +++ b/tools/testing/selftests/arm64/mte/check_child_memory.c @@ -85,9 +85,9 @@ static int check_child_memory_mapping(int mem_type, int mode, int mapping) { char *ptr; int run, result; - int item = sizeof(sizes)/sizeof(int); + int item = ARRAY_SIZE(sizes); - item = sizeof(sizes)/sizeof(int); + item = ARRAY_SIZE(sizes); mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG); for (run = 0; run < item; run++) { ptr = (char *)mte_allocate_memory_tag_range(sizes[run], mem_type, mapping, @@ -107,7 +107,7 @@ static int check_child_file_mapping(int mem_type, int mode, int mapping) { char *ptr, *map_ptr; int run, fd, map_size, result = KSFT_PASS; - int total = sizeof(sizes)/sizeof(int); + int total = ARRAY_SIZE(sizes); mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG); for (run = 0; run < total; run++) { @@ -144,7 +144,7 @@ static int check_child_file_mapping(int mem_type, int mode, int mapping) int main(int argc, char *argv[]) { int err; - int item = sizeof(sizes)/sizeof(int); + int item = ARRAY_SIZE(sizes); page_size = getpagesize(); if (!page_size) { diff --git a/tools/testing/selftests/arm64/mte/check_prctl.c b/tools/testing/selftests/arm64/mte/check_prctl.c new file mode 100644 index 000000000000..f139a33a43ef --- /dev/null +++ b/tools/testing/selftests/arm64/mte/check_prctl.c @@ -0,0 +1,119 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (C) 2022 ARM Limited + +#include <stdbool.h> +#include <stdio.h> +#include <string.h> + +#include <sys/auxv.h> +#include <sys/prctl.h> + +#include <asm/hwcap.h> + +#include "kselftest.h" + +static int set_tagged_addr_ctrl(int val) +{ + int ret; + + ret = prctl(PR_SET_TAGGED_ADDR_CTRL, val, 0, 0, 0); + if (ret < 0) + ksft_print_msg("PR_SET_TAGGED_ADDR_CTRL: failed %d %d (%s)\n", + ret, errno, strerror(errno)); + return ret; +} + +static int get_tagged_addr_ctrl(void) +{ + int ret; + + ret = prctl(PR_GET_TAGGED_ADDR_CTRL, 0, 0, 0, 0); + if (ret < 0) + ksft_print_msg("PR_GET_TAGGED_ADDR_CTRL failed: %d %d (%s)\n", + ret, errno, strerror(errno)); + return ret; +} + +/* + * Read the current mode without having done any configuration, should + * run first. + */ +void check_basic_read(void) +{ + int ret; + + ret = get_tagged_addr_ctrl(); + if (ret < 0) { + ksft_test_result_fail("check_basic_read\n"); + return; + } + + if (ret & PR_MTE_TCF_SYNC) + ksft_print_msg("SYNC enabled\n"); + if (ret & PR_MTE_TCF_ASYNC) + ksft_print_msg("ASYNC enabled\n"); + + /* Any configuration is valid */ + ksft_test_result_pass("check_basic_read\n"); +} + +/* + * Attempt to set a specified combination of modes. + */ +void set_mode_test(const char *name, int hwcap2, int mask) +{ + int ret; + + if ((getauxval(AT_HWCAP2) & hwcap2) != hwcap2) { + ksft_test_result_skip("%s\n", name); + return; + } + + ret = set_tagged_addr_ctrl(mask); + if (ret < 0) { + ksft_test_result_fail("%s\n", name); + return; + } + + ret = get_tagged_addr_ctrl(); + if (ret < 0) { + ksft_test_result_fail("%s\n", name); + return; + } + + if ((ret & PR_MTE_TCF_MASK) == mask) { + ksft_test_result_pass("%s\n", name); + } else { + ksft_print_msg("Got %x, expected %x\n", + (ret & PR_MTE_TCF_MASK), mask); + ksft_test_result_fail("%s\n", name); + } +} + +struct mte_mode { + int mask; + int hwcap2; + const char *name; +} mte_modes[] = { + { PR_MTE_TCF_NONE, 0, "NONE" }, + { PR_MTE_TCF_SYNC, HWCAP2_MTE, "SYNC" }, + { PR_MTE_TCF_ASYNC, HWCAP2_MTE, "ASYNC" }, + { PR_MTE_TCF_SYNC | PR_MTE_TCF_ASYNC, HWCAP2_MTE, "SYNC+ASYNC" }, +}; + +int main(void) +{ + int i; + + ksft_print_header(); + ksft_set_plan(5); + + check_basic_read(); + for (i = 0; i < ARRAY_SIZE(mte_modes); i++) + set_mode_test(mte_modes[i].name, mte_modes[i].hwcap2, + mte_modes[i].mask); + + ksft_print_cnts(); + + return 0; +} diff --git a/tools/testing/selftests/arm64/mte/check_tags_inclusion.c b/tools/testing/selftests/arm64/mte/check_tags_inclusion.c index deaef1f61076..2b1425b92b69 100644 --- a/tools/testing/selftests/arm64/mte/check_tags_inclusion.c +++ b/tools/testing/selftests/arm64/mte/check_tags_inclusion.c @@ -23,10 +23,13 @@ static int verify_mte_pointer_validity(char *ptr, int mode) { mte_initialize_current_context(mode, (uintptr_t)ptr, BUFFER_SIZE); /* Check the validity of the tagged pointer */ - memset((void *)ptr, '1', BUFFER_SIZE); + memset(ptr, '1', BUFFER_SIZE); mte_wait_after_trig(); - if (cur_mte_cxt.fault_valid) + if (cur_mte_cxt.fault_valid) { + ksft_print_msg("Unexpected fault recorded for %p-%p in mode %x\n", + ptr, ptr + BUFFER_SIZE, mode); return KSFT_FAIL; + } /* Proceed further for nonzero tags */ if (!MT_FETCH_TAG((uintptr_t)ptr)) return KSFT_PASS; @@ -34,27 +37,32 @@ static int verify_mte_pointer_validity(char *ptr, int mode) /* Check the validity outside the range */ ptr[BUFFER_SIZE] = '2'; mte_wait_after_trig(); - if (!cur_mte_cxt.fault_valid) + if (!cur_mte_cxt.fault_valid) { + ksft_print_msg("No valid fault recorded for %p in mode %x\n", + ptr, mode); return KSFT_FAIL; - else + } else { return KSFT_PASS; + } } static int check_single_included_tags(int mem_type, int mode) { char *ptr; - int tag, run, result = KSFT_PASS; + int tag, run, ret, result = KSFT_PASS; - ptr = (char *)mte_allocate_memory(BUFFER_SIZE + MT_GRANULE_SIZE, mem_type, 0, false); + ptr = mte_allocate_memory(BUFFER_SIZE + MT_GRANULE_SIZE, mem_type, 0, false); if (check_allocated_memory(ptr, BUFFER_SIZE + MT_GRANULE_SIZE, mem_type, false) != KSFT_PASS) return KSFT_FAIL; for (tag = 0; (tag < MT_TAG_COUNT) && (result == KSFT_PASS); tag++) { - mte_switch_mode(mode, MT_INCLUDE_VALID_TAG(tag)); + ret = mte_switch_mode(mode, MT_INCLUDE_VALID_TAG(tag)); + if (ret != 0) + result = KSFT_FAIL; /* Try to catch a excluded tag by a number of tries. */ for (run = 0; (run < RUNS) && (result == KSFT_PASS); run++) { - ptr = (char *)mte_insert_tags(ptr, BUFFER_SIZE); + ptr = mte_insert_tags(ptr, BUFFER_SIZE); /* Check tag value */ if (MT_FETCH_TAG((uintptr_t)ptr) == tag) { ksft_print_msg("FAIL: wrong tag = 0x%x with include mask=0x%x\n", @@ -66,7 +74,7 @@ static int check_single_included_tags(int mem_type, int mode) result = verify_mte_pointer_validity(ptr, mode); } } - mte_free_memory_tag_range((void *)ptr, BUFFER_SIZE, mem_type, 0, MT_GRANULE_SIZE); + mte_free_memory_tag_range(ptr, BUFFER_SIZE, mem_type, 0, MT_GRANULE_SIZE); return result; } @@ -76,7 +84,7 @@ static int check_multiple_included_tags(int mem_type, int mode) int tag, run, result = KSFT_PASS; unsigned long excl_mask = 0; - ptr = (char *)mte_allocate_memory(BUFFER_SIZE + MT_GRANULE_SIZE, mem_type, 0, false); + ptr = mte_allocate_memory(BUFFER_SIZE + MT_GRANULE_SIZE, mem_type, 0, false); if (check_allocated_memory(ptr, BUFFER_SIZE + MT_GRANULE_SIZE, mem_type, false) != KSFT_PASS) return KSFT_FAIL; @@ -86,7 +94,7 @@ static int check_multiple_included_tags(int mem_type, int mode) mte_switch_mode(mode, MT_INCLUDE_VALID_TAGS(excl_mask)); /* Try to catch a excluded tag by a number of tries. */ for (run = 0; (run < RUNS) && (result == KSFT_PASS); run++) { - ptr = (char *)mte_insert_tags(ptr, BUFFER_SIZE); + ptr = mte_insert_tags(ptr, BUFFER_SIZE); /* Check tag value */ if (MT_FETCH_TAG((uintptr_t)ptr) < tag) { ksft_print_msg("FAIL: wrong tag = 0x%x with include mask=0x%x\n", @@ -98,21 +106,23 @@ static int check_multiple_included_tags(int mem_type, int mode) result = verify_mte_pointer_validity(ptr, mode); } } - mte_free_memory_tag_range((void *)ptr, BUFFER_SIZE, mem_type, 0, MT_GRANULE_SIZE); + mte_free_memory_tag_range(ptr, BUFFER_SIZE, mem_type, 0, MT_GRANULE_SIZE); return result; } static int check_all_included_tags(int mem_type, int mode) { char *ptr; - int run, result = KSFT_PASS; + int run, ret, result = KSFT_PASS; - ptr = (char *)mte_allocate_memory(BUFFER_SIZE + MT_GRANULE_SIZE, mem_type, 0, false); + ptr = mte_allocate_memory(BUFFER_SIZE + MT_GRANULE_SIZE, mem_type, 0, false); if (check_allocated_memory(ptr, BUFFER_SIZE + MT_GRANULE_SIZE, mem_type, false) != KSFT_PASS) return KSFT_FAIL; - mte_switch_mode(mode, MT_INCLUDE_TAG_MASK); + ret = mte_switch_mode(mode, MT_INCLUDE_TAG_MASK); + if (ret != 0) + return KSFT_FAIL; /* Try to catch a excluded tag by a number of tries. */ for (run = 0; (run < RUNS) && (result == KSFT_PASS); run++) { ptr = (char *)mte_insert_tags(ptr, BUFFER_SIZE); @@ -122,20 +132,22 @@ static int check_all_included_tags(int mem_type, int mode) */ result = verify_mte_pointer_validity(ptr, mode); } - mte_free_memory_tag_range((void *)ptr, BUFFER_SIZE, mem_type, 0, MT_GRANULE_SIZE); + mte_free_memory_tag_range(ptr, BUFFER_SIZE, mem_type, 0, MT_GRANULE_SIZE); return result; } static int check_none_included_tags(int mem_type, int mode) { char *ptr; - int run; + int run, ret; - ptr = (char *)mte_allocate_memory(BUFFER_SIZE, mem_type, 0, false); + ptr = mte_allocate_memory(BUFFER_SIZE, mem_type, 0, false); if (check_allocated_memory(ptr, BUFFER_SIZE, mem_type, false) != KSFT_PASS) return KSFT_FAIL; - mte_switch_mode(mode, MT_EXCLUDE_TAG_MASK); + ret = mte_switch_mode(mode, MT_EXCLUDE_TAG_MASK); + if (ret != 0) + return KSFT_FAIL; /* Try to catch a excluded tag by a number of tries. */ for (run = 0; run < RUNS; run++) { ptr = (char *)mte_insert_tags(ptr, BUFFER_SIZE); @@ -147,12 +159,12 @@ static int check_none_included_tags(int mem_type, int mode) } mte_initialize_current_context(mode, (uintptr_t)ptr, BUFFER_SIZE); /* Check the write validity of the untagged pointer */ - memset((void *)ptr, '1', BUFFER_SIZE); + memset(ptr, '1', BUFFER_SIZE); mte_wait_after_trig(); if (cur_mte_cxt.fault_valid) break; } - mte_free_memory((void *)ptr, BUFFER_SIZE, mem_type, false); + mte_free_memory(ptr, BUFFER_SIZE, mem_type, false); if (cur_mte_cxt.fault_valid) return KSFT_FAIL; else diff --git a/tools/testing/selftests/arm64/mte/mte_common_util.c b/tools/testing/selftests/arm64/mte/mte_common_util.c index 0328a1e08f65..00ffd34c66d3 100644 --- a/tools/testing/selftests/arm64/mte/mte_common_util.c +++ b/tools/testing/selftests/arm64/mte/mte_common_util.c @@ -37,6 +37,10 @@ void mte_default_handler(int signum, siginfo_t *si, void *uc) if (si->si_code == SEGV_MTEAERR) { if (cur_mte_cxt.trig_si_code == si->si_code) cur_mte_cxt.fault_valid = true; + else + ksft_print_msg("Got unexpected SEGV_MTEAERR at pc=$lx, fault addr=%lx\n", + ((ucontext_t *)uc)->uc_mcontext.pc, + addr); return; } /* Compare the context for precise error */ @@ -124,13 +128,16 @@ static void *__mte_allocate_memory_range(size_t size, int mem_type, int mapping, int prot_flag, map_flag; size_t entire_size = size + range_before + range_after; - if (mem_type != USE_MALLOC && mem_type != USE_MMAP && - mem_type != USE_MPROTECT) { + switch (mem_type) { + case USE_MALLOC: + return malloc(entire_size) + range_before; + case USE_MMAP: + case USE_MPROTECT: + break; + default: ksft_print_msg("FAIL: Invalid allocate request\n"); return NULL; } - if (mem_type == USE_MALLOC) - return malloc(entire_size) + range_before; prot_flag = PROT_READ | PROT_WRITE; if (mem_type == USE_MMAP) @@ -269,18 +276,33 @@ int mte_switch_mode(int mte_option, unsigned long incl_mask) { unsigned long en = 0; - if (!(mte_option == MTE_SYNC_ERR || mte_option == MTE_ASYNC_ERR || - mte_option == MTE_NONE_ERR || incl_mask <= MTE_ALLOW_NON_ZERO_TAG)) { - ksft_print_msg("FAIL: Invalid mte config option\n"); + switch (mte_option) { + case MTE_NONE_ERR: + case MTE_SYNC_ERR: + case MTE_ASYNC_ERR: + break; + default: + ksft_print_msg("FAIL: Invalid MTE option %x\n", mte_option); + return -EINVAL; + } + + if (incl_mask & ~MT_INCLUDE_TAG_MASK) { + ksft_print_msg("FAIL: Invalid incl_mask %lx\n", incl_mask); return -EINVAL; } + en = PR_TAGGED_ADDR_ENABLE; - if (mte_option == MTE_SYNC_ERR) + switch (mte_option) { + case MTE_SYNC_ERR: en |= PR_MTE_TCF_SYNC; - else if (mte_option == MTE_ASYNC_ERR) + break; + case MTE_ASYNC_ERR: en |= PR_MTE_TCF_ASYNC; - else if (mte_option == MTE_NONE_ERR) + break; + case MTE_NONE_ERR: en |= PR_MTE_TCF_NONE; + break; + } en |= (incl_mask << PR_MTE_TAG_SHIFT); /* Enable address tagging ABI, mte error reporting mode and tag inclusion mask. */ diff --git a/tools/testing/selftests/arm64/mte/mte_common_util.h b/tools/testing/selftests/arm64/mte/mte_common_util.h index 195a7d1879e6..2d3e71724e55 100644 --- a/tools/testing/selftests/arm64/mte/mte_common_util.h +++ b/tools/testing/selftests/arm64/mte/mte_common_util.h @@ -75,10 +75,21 @@ unsigned int mte_get_pstate_tco(void); /* Test framework static inline functions/macros */ static inline void evaluate_test(int err, const char *msg) { - if (err == KSFT_PASS) + switch (err) { + case KSFT_PASS: ksft_test_result_pass(msg); - else if (err == KSFT_FAIL) + break; + case KSFT_FAIL: ksft_test_result_fail(msg); + break; + case KSFT_SKIP: + ksft_test_result_skip(msg); + break; + default: + ksft_test_result_error("Unknown return code %d from %s", + err, msg); + break; + } } static inline int check_allocated_memory(void *ptr, size_t size, diff --git a/tools/testing/selftests/arm64/signal/.gitignore b/tools/testing/selftests/arm64/signal/.gitignore index c1742755abb9..e8d2b57f73ec 100644 --- a/tools/testing/selftests/arm64/signal/.gitignore +++ b/tools/testing/selftests/arm64/signal/.gitignore @@ -1,5 +1,8 @@ # SPDX-License-Identifier: GPL-2.0-only mangle_* fake_sigreturn_* +sme_* +ssve_* sve_* +za_* !*.[ch] diff --git a/tools/testing/selftests/arm64/signal/test_signals.h b/tools/testing/selftests/arm64/signal/test_signals.h index f909b70d9e98..c70fdec7d7c4 100644 --- a/tools/testing/selftests/arm64/signal/test_signals.h +++ b/tools/testing/selftests/arm64/signal/test_signals.h @@ -34,11 +34,15 @@ enum { FSSBS_BIT, FSVE_BIT, + FSME_BIT, + FSME_FA64_BIT, FMAX_END }; #define FEAT_SSBS (1UL << FSSBS_BIT) #define FEAT_SVE (1UL << FSVE_BIT) +#define FEAT_SME (1UL << FSME_BIT) +#define FEAT_SME_FA64 (1UL << FSME_FA64_BIT) /* * A descriptor used to describe and configure a test case. diff --git a/tools/testing/selftests/arm64/signal/test_signals_utils.c b/tools/testing/selftests/arm64/signal/test_signals_utils.c index 5743897984b0..b588d10afd5b 100644 --- a/tools/testing/selftests/arm64/signal/test_signals_utils.c +++ b/tools/testing/selftests/arm64/signal/test_signals_utils.c @@ -27,6 +27,8 @@ static int sig_copyctx = SIGTRAP; static char const *const feats_names[FMAX_END] = { " SSBS ", " SVE ", + " SME ", + " FA64 ", }; #define MAX_FEATS_SZ 128 @@ -268,6 +270,10 @@ int test_init(struct tdescr *td) td->feats_supported |= FEAT_SSBS; if (getauxval(AT_HWCAP) & HWCAP_SVE) td->feats_supported |= FEAT_SVE; + if (getauxval(AT_HWCAP2) & HWCAP2_SME) + td->feats_supported |= FEAT_SME; + if (getauxval(AT_HWCAP2) & HWCAP2_SME_FA64) + td->feats_supported |= FEAT_SME_FA64; if (feats_ok(td)) { if (td->feats_required & td->feats_supported) fprintf(stderr, diff --git a/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_sme_change_vl.c b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_sme_change_vl.c new file mode 100644 index 000000000000..7ed762b7202f --- /dev/null +++ b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_sme_change_vl.c @@ -0,0 +1,92 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2021 ARM Limited + * + * Attempt to change the streaming SVE vector length in a signal + * handler, this is not supported and is expected to segfault. + */ + +#include <signal.h> +#include <ucontext.h> +#include <sys/prctl.h> + +#include "test_signals_utils.h" +#include "testcases.h" + +struct fake_sigframe sf; +static unsigned int vls[SVE_VQ_MAX]; +unsigned int nvls = 0; + +static bool sme_get_vls(struct tdescr *td) +{ + int vq, vl; + + /* + * Enumerate up to SVE_VQ_MAX vector lengths + */ + for (vq = SVE_VQ_MAX; vq > 0; --vq) { + vl = prctl(PR_SVE_SET_VL, vq * 16); + if (vl == -1) + return false; + + vl &= PR_SME_VL_LEN_MASK; + + /* Skip missing VLs */ + vq = sve_vq_from_vl(vl); + + vls[nvls++] = vl; + } + + /* We need at least two VLs */ + if (nvls < 2) { + fprintf(stderr, "Only %d VL supported\n", nvls); + return false; + } + + return true; +} + +static int fake_sigreturn_ssve_change_vl(struct tdescr *td, + siginfo_t *si, ucontext_t *uc) +{ + size_t resv_sz, offset; + struct _aarch64_ctx *head = GET_SF_RESV_HEAD(sf); + struct sve_context *sve; + + /* Get a signal context with a SME ZA frame in it */ + if (!get_current_context(td, &sf.uc)) + return 1; + + resv_sz = GET_SF_RESV_SIZE(sf); + head = get_header(head, SVE_MAGIC, resv_sz, &offset); + if (!head) { + fprintf(stderr, "No SVE context\n"); + return 1; + } + + if (head->size != sizeof(struct sve_context)) { + fprintf(stderr, "Register data present, aborting\n"); + return 1; + } + + sve = (struct sve_context *)head; + + /* No changes are supported; init left us at minimum VL so go to max */ + fprintf(stderr, "Attempting to change VL from %d to %d\n", + sve->vl, vls[0]); + sve->vl = vls[0]; + + fake_sigreturn(&sf, sizeof(sf), 0); + + return 1; +} + +struct tdescr tde = { + .name = "FAKE_SIGRETURN_SSVE_CHANGE", + .descr = "Attempt to change Streaming SVE VL", + .feats_required = FEAT_SME, + .sig_ok = SIGSEGV, + .timeout = 3, + .init = sme_get_vls, + .run = fake_sigreturn_ssve_change_vl, +}; diff --git a/tools/testing/selftests/arm64/signal/testcases/sme_trap_no_sm.c b/tools/testing/selftests/arm64/signal/testcases/sme_trap_no_sm.c new file mode 100644 index 000000000000..f9d76ae32bba --- /dev/null +++ b/tools/testing/selftests/arm64/signal/testcases/sme_trap_no_sm.c @@ -0,0 +1,38 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2021 ARM Limited + * + * Verify that using a streaming mode instruction without enabling it + * generates a SIGILL. + */ + +#include <signal.h> +#include <ucontext.h> +#include <sys/prctl.h> + +#include "test_signals_utils.h" +#include "testcases.h" + +int sme_trap_no_sm_trigger(struct tdescr *td) +{ + /* SMSTART ZA ; ADDHA ZA0.S, P0/M, P0/M, Z0.S */ + asm volatile(".inst 0xd503457f ; .inst 0xc0900000"); + + return 0; +} + +int sme_trap_no_sm_run(struct tdescr *td, siginfo_t *si, ucontext_t *uc) +{ + return 1; +} + +struct tdescr tde = { + .name = "SME trap without SM", + .descr = "Check that we get a SIGILL if we use streaming mode without enabling it", + .timeout = 3, + .feats_required = FEAT_SME, /* We need a SMSTART ZA */ + .sanity_disabled = true, + .trigger = sme_trap_no_sm_trigger, + .run = sme_trap_no_sm_run, + .sig_ok = SIGILL, +}; diff --git a/tools/testing/selftests/arm64/signal/testcases/sme_trap_non_streaming.c b/tools/testing/selftests/arm64/signal/testcases/sme_trap_non_streaming.c new file mode 100644 index 000000000000..e469ae5348e3 --- /dev/null +++ b/tools/testing/selftests/arm64/signal/testcases/sme_trap_non_streaming.c @@ -0,0 +1,45 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2021 ARM Limited + * + * Verify that using an instruction not supported in streaming mode + * traps when in streaming mode. + */ + +#include <signal.h> +#include <ucontext.h> +#include <sys/prctl.h> + +#include "test_signals_utils.h" +#include "testcases.h" + +int sme_trap_non_streaming_trigger(struct tdescr *td) +{ + /* + * The framework will handle SIGILL so we need to exit SM to + * stop any other code triggering a further SIGILL down the + * line from using a streaming-illegal instruction. + */ + asm volatile(".inst 0xd503437f; /* SMSTART ZA */ \ + cnt v0.16b, v0.16b; \ + .inst 0xd503447f /* SMSTOP ZA */"); + + return 0; +} + +int sme_trap_non_streaming_run(struct tdescr *td, siginfo_t *si, ucontext_t *uc) +{ + return 1; +} + +struct tdescr tde = { + .name = "SME SM trap unsupported instruction", + .descr = "Check that we get a SIGILL if we use an unsupported instruction in streaming mode", + .feats_required = FEAT_SME, + .feats_incompatible = FEAT_SME_FA64, + .timeout = 3, + .sanity_disabled = true, + .trigger = sme_trap_non_streaming_trigger, + .run = sme_trap_non_streaming_run, + .sig_ok = SIGILL, +}; diff --git a/tools/testing/selftests/arm64/signal/testcases/sme_trap_za.c b/tools/testing/selftests/arm64/signal/testcases/sme_trap_za.c new file mode 100644 index 000000000000..3a7747af4715 --- /dev/null +++ b/tools/testing/selftests/arm64/signal/testcases/sme_trap_za.c @@ -0,0 +1,36 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2021 ARM Limited + * + * Verify that accessing ZA without enabling it generates a SIGILL. + */ + +#include <signal.h> +#include <ucontext.h> +#include <sys/prctl.h> + +#include "test_signals_utils.h" +#include "testcases.h" + +int sme_trap_za_trigger(struct tdescr *td) +{ + /* ZERO ZA */ + asm volatile(".inst 0xc00800ff"); + + return 0; +} + +int sme_trap_za_run(struct tdescr *td, siginfo_t *si, ucontext_t *uc) +{ + return 1; +} + +struct tdescr tde = { + .name = "SME ZA trap", + .descr = "Check that we get a SIGILL if we access ZA without enabling", + .timeout = 3, + .sanity_disabled = true, + .trigger = sme_trap_za_trigger, + .run = sme_trap_za_run, + .sig_ok = SIGILL, +}; diff --git a/tools/testing/selftests/arm64/signal/testcases/sme_vl.c b/tools/testing/selftests/arm64/signal/testcases/sme_vl.c new file mode 100644 index 000000000000..13ff3b35cbaf --- /dev/null +++ b/tools/testing/selftests/arm64/signal/testcases/sme_vl.c @@ -0,0 +1,68 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2021 ARM Limited + * + * Check that the SME vector length reported in signal contexts is the + * expected one. + */ + +#include <signal.h> +#include <ucontext.h> +#include <sys/prctl.h> + +#include "test_signals_utils.h" +#include "testcases.h" + +struct fake_sigframe sf; +unsigned int vl; + +static bool get_sme_vl(struct tdescr *td) +{ + int ret = prctl(PR_SME_GET_VL); + if (ret == -1) + return false; + + vl = ret; + + return true; +} + +static int sme_vl(struct tdescr *td, siginfo_t *si, ucontext_t *uc) +{ + size_t resv_sz, offset; + struct _aarch64_ctx *head = GET_SF_RESV_HEAD(sf); + struct za_context *za; + + /* Get a signal context which should have a ZA frame in it */ + if (!get_current_context(td, &sf.uc)) + return 1; + + resv_sz = GET_SF_RESV_SIZE(sf); + head = get_header(head, ZA_MAGIC, resv_sz, &offset); + if (!head) { + fprintf(stderr, "No ZA context\n"); + return 1; + } + za = (struct za_context *)head; + + if (za->vl != vl) { + fprintf(stderr, "ZA sigframe VL %u, expected %u\n", + za->vl, vl); + return 1; + } else { + fprintf(stderr, "got expected VL %u\n", vl); + } + + td->pass = 1; + + return 0; +} + +struct tdescr tde = { + .name = "SME VL", + .descr = "Check that we get the right SME VL reported", + .feats_required = FEAT_SME, + .timeout = 3, + .init = get_sme_vl, + .run = sme_vl, +}; diff --git a/tools/testing/selftests/arm64/signal/testcases/ssve_regs.c b/tools/testing/selftests/arm64/signal/testcases/ssve_regs.c new file mode 100644 index 000000000000..9022a6cab4b3 --- /dev/null +++ b/tools/testing/selftests/arm64/signal/testcases/ssve_regs.c @@ -0,0 +1,135 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2021 ARM Limited + * + * Verify that the streaming SVE register context in signal frames is + * set up as expected. + */ + +#include <signal.h> +#include <ucontext.h> +#include <sys/prctl.h> + +#include "test_signals_utils.h" +#include "testcases.h" + +struct fake_sigframe sf; +static unsigned int vls[SVE_VQ_MAX]; +unsigned int nvls = 0; + +static bool sme_get_vls(struct tdescr *td) +{ + int vq, vl; + + /* + * Enumerate up to SVE_VQ_MAX vector lengths + */ + for (vq = SVE_VQ_MAX; vq > 0; --vq) { + vl = prctl(PR_SME_SET_VL, vq * 16); + if (vl == -1) + return false; + + vl &= PR_SME_VL_LEN_MASK; + + /* Skip missing VLs */ + vq = sve_vq_from_vl(vl); + + vls[nvls++] = vl; + } + + /* We need at least one VL */ + if (nvls < 1) { + fprintf(stderr, "Only %d VL supported\n", nvls); + return false; + } + + return true; +} + +static void setup_ssve_regs(void) +{ + /* smstart sm; real data is TODO */ + asm volatile(".inst 0xd503437f" : : : ); +} + +static int do_one_sme_vl(struct tdescr *td, siginfo_t *si, ucontext_t *uc, + unsigned int vl) +{ + size_t resv_sz, offset; + struct _aarch64_ctx *head = GET_SF_RESV_HEAD(sf); + struct sve_context *ssve; + int ret; + + fprintf(stderr, "Testing VL %d\n", vl); + + ret = prctl(PR_SME_SET_VL, vl); + if (ret != vl) { + fprintf(stderr, "Failed to set VL, got %d\n", ret); + return 1; + } + + /* + * Get a signal context which should have a SVE frame and registers + * in it. + */ + setup_ssve_regs(); + if (!get_current_context(td, &sf.uc)) + return 1; + + resv_sz = GET_SF_RESV_SIZE(sf); + head = get_header(head, SVE_MAGIC, resv_sz, &offset); + if (!head) { + fprintf(stderr, "No SVE context\n"); + return 1; + } + + ssve = (struct sve_context *)head; + if (ssve->vl != vl) { + fprintf(stderr, "Got VL %d, expected %d\n", ssve->vl, vl); + return 1; + } + + /* The actual size validation is done in get_current_context() */ + fprintf(stderr, "Got expected size %u and VL %d\n", + head->size, ssve->vl); + + return 0; +} + +static int sme_regs(struct tdescr *td, siginfo_t *si, ucontext_t *uc) +{ + int i; + + for (i = 0; i < nvls; i++) { + /* + * TODO: the signal test helpers can't currently cope + * with signal frames bigger than struct sigcontext, + * skip VLs that will trigger that. + */ + if (vls[i] > 64) { + printf("Skipping VL %u due to stack size\n", vls[i]); + continue; + } + + if (do_one_sme_vl(td, si, uc, vls[i])) + return 1; + } + + td->pass = 1; + + return 0; +} + +struct tdescr tde = { + .name = "Streaming SVE registers", + .descr = "Check that we get the right Streaming SVE registers reported", + /* + * We shouldn't require FA64 but things like memset() used in the + * helpers might use unsupported instructions so for now disable + * the test unless we've got the full instruction set. + */ + .feats_required = FEAT_SME | FEAT_SME_FA64, + .timeout = 3, + .init = sme_get_vls, + .run = sme_regs, +}; diff --git a/tools/testing/selftests/arm64/signal/testcases/testcases.c b/tools/testing/selftests/arm64/signal/testcases/testcases.c index 8c2a57fc2f9c..84c36bee4d82 100644 --- a/tools/testing/selftests/arm64/signal/testcases/testcases.c +++ b/tools/testing/selftests/arm64/signal/testcases/testcases.c @@ -75,6 +75,31 @@ bool validate_sve_context(struct sve_context *sve, char **err) return true; } +bool validate_za_context(struct za_context *za, char **err) +{ + /* Size will be rounded up to a multiple of 16 bytes */ + size_t regs_size + = ((ZA_SIG_CONTEXT_SIZE(sve_vq_from_vl(za->vl)) + 15) / 16) * 16; + + if (!za || !err) + return false; + + /* Either a bare za_context or a za_context followed by regs data */ + if ((za->head.size != sizeof(struct za_context)) && + (za->head.size != regs_size)) { + *err = "bad size for ZA context"; + return false; + } + + if (!sve_vl_valid(za->vl)) { + *err = "SME VL in ZA context invalid"; + + return false; + } + + return true; +} + bool validate_reserved(ucontext_t *uc, size_t resv_sz, char **err) { bool terminated = false; @@ -82,6 +107,7 @@ bool validate_reserved(ucontext_t *uc, size_t resv_sz, char **err) int flags = 0; struct extra_context *extra = NULL; struct sve_context *sve = NULL; + struct za_context *za = NULL; struct _aarch64_ctx *head = (struct _aarch64_ctx *)uc->uc_mcontext.__reserved; @@ -120,6 +146,13 @@ bool validate_reserved(ucontext_t *uc, size_t resv_sz, char **err) sve = (struct sve_context *)head; flags |= SVE_CTX; break; + case ZA_MAGIC: + if (flags & ZA_CTX) + *err = "Multiple ZA_MAGIC"; + /* Size is validated in validate_za_context() */ + za = (struct za_context *)head; + flags |= ZA_CTX; + break; case EXTRA_MAGIC: if (flags & EXTRA_CTX) *err = "Multiple EXTRA_MAGIC"; @@ -165,6 +198,9 @@ bool validate_reserved(ucontext_t *uc, size_t resv_sz, char **err) if (flags & SVE_CTX) if (!validate_sve_context(sve, err)) return false; + if (flags & ZA_CTX) + if (!validate_za_context(za, err)) + return false; head = GET_RESV_NEXT_HEAD(head); } diff --git a/tools/testing/selftests/arm64/signal/testcases/testcases.h b/tools/testing/selftests/arm64/signal/testcases/testcases.h index ad884c135314..49f1d5de7b5b 100644 --- a/tools/testing/selftests/arm64/signal/testcases/testcases.h +++ b/tools/testing/selftests/arm64/signal/testcases/testcases.h @@ -16,7 +16,8 @@ #define FPSIMD_CTX (1 << 0) #define SVE_CTX (1 << 1) -#define EXTRA_CTX (1 << 2) +#define ZA_CTX (1 << 2) +#define EXTRA_CTX (1 << 3) #define KSFT_BAD_MAGIC 0xdeadbeef diff --git a/tools/testing/selftests/arm64/signal/testcases/za_regs.c b/tools/testing/selftests/arm64/signal/testcases/za_regs.c new file mode 100644 index 000000000000..b94e4f99fcac --- /dev/null +++ b/tools/testing/selftests/arm64/signal/testcases/za_regs.c @@ -0,0 +1,128 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2021 ARM Limited + * + * Verify that the ZA register context in signal frames is set up as + * expected. + */ + +#include <signal.h> +#include <ucontext.h> +#include <sys/prctl.h> + +#include "test_signals_utils.h" +#include "testcases.h" + +struct fake_sigframe sf; +static unsigned int vls[SVE_VQ_MAX]; +unsigned int nvls = 0; + +static bool sme_get_vls(struct tdescr *td) +{ + int vq, vl; + + /* + * Enumerate up to SVE_VQ_MAX vector lengths + */ + for (vq = SVE_VQ_MAX; vq > 0; --vq) { + vl = prctl(PR_SVE_SET_VL, vq * 16); + if (vl == -1) + return false; + + vl &= PR_SME_VL_LEN_MASK; + + /* Skip missing VLs */ + vq = sve_vq_from_vl(vl); + + vls[nvls++] = vl; + } + + /* We need at least one VL */ + if (nvls < 1) { + fprintf(stderr, "Only %d VL supported\n", nvls); + return false; + } + + return true; +} + +static void setup_za_regs(void) +{ + /* smstart za; real data is TODO */ + asm volatile(".inst 0xd503457f" : : : ); +} + +static int do_one_sme_vl(struct tdescr *td, siginfo_t *si, ucontext_t *uc, + unsigned int vl) +{ + size_t resv_sz, offset; + struct _aarch64_ctx *head = GET_SF_RESV_HEAD(sf); + struct za_context *za; + + fprintf(stderr, "Testing VL %d\n", vl); + + if (prctl(PR_SME_SET_VL, vl) != vl) { + fprintf(stderr, "Failed to set VL\n"); + return 1; + } + + /* + * Get a signal context which should have a SVE frame and registers + * in it. + */ + setup_za_regs(); + if (!get_current_context(td, &sf.uc)) + return 1; + + resv_sz = GET_SF_RESV_SIZE(sf); + head = get_header(head, ZA_MAGIC, resv_sz, &offset); + if (!head) { + fprintf(stderr, "No ZA context\n"); + return 1; + } + + za = (struct za_context *)head; + if (za->vl != vl) { + fprintf(stderr, "Got VL %d, expected %d\n", za->vl, vl); + return 1; + } + + /* The actual size validation is done in get_current_context() */ + fprintf(stderr, "Got expected size %u and VL %d\n", + head->size, za->vl); + + return 0; +} + +static int sme_regs(struct tdescr *td, siginfo_t *si, ucontext_t *uc) +{ + int i; + + for (i = 0; i < nvls; i++) { + /* + * TODO: the signal test helpers can't currently cope + * with signal frames bigger than struct sigcontext, + * skip VLs that will trigger that. + */ + if (vls[i] > 32) { + printf("Skipping VL %u due to stack size\n", vls[i]); + continue; + } + + if (do_one_sme_vl(td, si, uc, vls[i])) + return 1; + } + + td->pass = 1; + + return 0; +} + +struct tdescr tde = { + .name = "ZA register", + .descr = "Check that we get the right ZA registers reported", + .feats_required = FEAT_SME, + .timeout = 3, + .init = sme_get_vls, + .run = sme_regs, +}; diff --git a/tools/testing/selftests/bpf/prog_tests/dummy_st_ops.c b/tools/testing/selftests/bpf/prog_tests/dummy_st_ops.c index 5aa52cc31dc2..c11832657d2b 100644 --- a/tools/testing/selftests/bpf/prog_tests/dummy_st_ops.c +++ b/tools/testing/selftests/bpf/prog_tests/dummy_st_ops.c @@ -2,6 +2,7 @@ /* Copyright (C) 2021. Huawei Technologies Co., Ltd */ #include <test_progs.h> #include "dummy_st_ops.skel.h" +#include "trace_dummy_st_ops.skel.h" /* Need to keep consistent with definition in include/linux/bpf.h */ struct bpf_dummy_ops_state { @@ -56,6 +57,7 @@ static void test_dummy_init_ptr_arg(void) .ctx_in = args, .ctx_size_in = sizeof(args), ); + struct trace_dummy_st_ops *trace_skel; struct dummy_st_ops *skel; int fd, err; @@ -64,12 +66,33 @@ static void test_dummy_init_ptr_arg(void) return; fd = bpf_program__fd(skel->progs.test_1); + + trace_skel = trace_dummy_st_ops__open(); + if (!ASSERT_OK_PTR(trace_skel, "trace_dummy_st_ops__open")) + goto done; + + err = bpf_program__set_attach_target(trace_skel->progs.fentry_test_1, + fd, "test_1"); + if (!ASSERT_OK(err, "set_attach_target(fentry_test_1)")) + goto done; + + err = trace_dummy_st_ops__load(trace_skel); + if (!ASSERT_OK(err, "load(trace_skel)")) + goto done; + + err = trace_dummy_st_ops__attach(trace_skel); + if (!ASSERT_OK(err, "attach(trace_skel)")) + goto done; + err = bpf_prog_test_run_opts(fd, &attr); ASSERT_OK(err, "test_run"); ASSERT_EQ(in_state.val, 0x5a, "test_ptr_ret"); ASSERT_EQ(attr.retval, exp_retval, "test_ret"); + ASSERT_EQ(trace_skel->bss->val, exp_retval, "fentry_val"); +done: dummy_st_ops__destroy(skel); + trace_dummy_st_ops__destroy(trace_skel); } static void test_dummy_multiple_args(void) diff --git a/tools/testing/selftests/bpf/progs/map_ptr_kern.c b/tools/testing/selftests/bpf/progs/map_ptr_kern.c index b64df94ec476..db388f593d0a 100644 --- a/tools/testing/selftests/bpf/progs/map_ptr_kern.c +++ b/tools/testing/selftests/bpf/progs/map_ptr_kern.c @@ -367,7 +367,7 @@ static inline int check_array_of_maps(void) VERIFY(check_default(&array_of_maps->map, map)); inner_map = bpf_map_lookup_elem(array_of_maps, &key); - VERIFY(inner_map != 0); + VERIFY(inner_map != NULL); VERIFY(inner_map->map.max_entries == INNER_MAX_ENTRIES); return 1; @@ -394,7 +394,7 @@ static inline int check_hash_of_maps(void) VERIFY(check_default(&hash_of_maps->map, map)); inner_map = bpf_map_lookup_elem(hash_of_maps, &key); - VERIFY(inner_map != 0); + VERIFY(inner_map != NULL); VERIFY(inner_map->map.max_entries == INNER_MAX_ENTRIES); return 1; diff --git a/tools/testing/selftests/bpf/progs/trace_dummy_st_ops.c b/tools/testing/selftests/bpf/progs/trace_dummy_st_ops.c new file mode 100644 index 000000000000..00a4be9d3074 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/trace_dummy_st_ops.c @@ -0,0 +1,21 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +int val = 0; + +SEC("fentry/test_1") +int BPF_PROG(fentry_test_1, __u64 *st_ops_ctx) +{ + __u64 state; + + /* Read the traced st_ops arg1 which is a pointer */ + bpf_probe_read_kernel(&state, sizeof(__u64), (void *)st_ops_ctx); + /* Read state->val */ + bpf_probe_read_kernel(&val, sizeof(__u32), (void *)state); + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c b/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c index b9e991d43155..e7775d3bbe08 100644 --- a/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c +++ b/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c @@ -18,8 +18,9 @@ #include "bpf_rlimit.h" #include "cgroup_helpers.h" -static int start_server(const struct sockaddr *addr, socklen_t len) +static int start_server(const struct sockaddr *addr, socklen_t len, bool dual) { + int mode = !dual; int fd; fd = socket(addr->sa_family, SOCK_STREAM, 0); @@ -28,6 +29,14 @@ static int start_server(const struct sockaddr *addr, socklen_t len) goto out; } + if (addr->sa_family == AF_INET6) { + if (setsockopt(fd, IPPROTO_IPV6, IPV6_V6ONLY, (char *)&mode, + sizeof(mode)) == -1) { + log_err("Failed to set the dual-stack mode"); + goto close_out; + } + } + if (bind(fd, addr, len) == -1) { log_err("Failed to bind server socket"); goto close_out; @@ -47,24 +56,17 @@ out: return fd; } -static int connect_to_server(int server_fd) +static int connect_to_server(const struct sockaddr *addr, socklen_t len) { - struct sockaddr_storage addr; - socklen_t len = sizeof(addr); int fd = -1; - if (getsockname(server_fd, (struct sockaddr *)&addr, &len)) { - log_err("Failed to get server addr"); - goto out; - } - - fd = socket(addr.ss_family, SOCK_STREAM, 0); + fd = socket(addr->sa_family, SOCK_STREAM, 0); if (fd == -1) { log_err("Failed to create client socket"); goto out; } - if (connect(fd, (const struct sockaddr *)&addr, len) == -1) { + if (connect(fd, (const struct sockaddr *)addr, len) == -1) { log_err("Fail to connect to server"); goto close_out; } @@ -116,7 +118,8 @@ err: return map_fd; } -static int run_test(int server_fd, int results_fd, bool xdp) +static int run_test(int server_fd, int results_fd, bool xdp, + const struct sockaddr *addr, socklen_t len) { int client = -1, srv_client = -1; int ret = 0; @@ -142,7 +145,7 @@ static int run_test(int server_fd, int results_fd, bool xdp) goto err; } - client = connect_to_server(server_fd); + client = connect_to_server(addr, len); if (client == -1) goto err; @@ -199,12 +202,30 @@ out: return ret; } +static bool get_port(int server_fd, in_port_t *port) +{ + struct sockaddr_in addr; + socklen_t len = sizeof(addr); + + if (getsockname(server_fd, (struct sockaddr *)&addr, &len)) { + log_err("Failed to get server addr"); + return false; + } + + /* sin_port and sin6_port are located at the same offset. */ + *port = addr.sin_port; + return true; +} + int main(int argc, char **argv) { struct sockaddr_in addr4; struct sockaddr_in6 addr6; + struct sockaddr_in addr4dual; + struct sockaddr_in6 addr6dual; int server = -1; int server_v6 = -1; + int server_dual = -1; int results = -1; int err = 0; bool xdp; @@ -224,25 +245,43 @@ int main(int argc, char **argv) addr4.sin_family = AF_INET; addr4.sin_addr.s_addr = htonl(INADDR_LOOPBACK); addr4.sin_port = 0; + memcpy(&addr4dual, &addr4, sizeof(addr4dual)); memset(&addr6, 0, sizeof(addr6)); addr6.sin6_family = AF_INET6; addr6.sin6_addr = in6addr_loopback; addr6.sin6_port = 0; - server = start_server((const struct sockaddr *)&addr4, sizeof(addr4)); - if (server == -1) + memset(&addr6dual, 0, sizeof(addr6dual)); + addr6dual.sin6_family = AF_INET6; + addr6dual.sin6_addr = in6addr_any; + addr6dual.sin6_port = 0; + + server = start_server((const struct sockaddr *)&addr4, sizeof(addr4), + false); + if (server == -1 || !get_port(server, &addr4.sin_port)) goto err; server_v6 = start_server((const struct sockaddr *)&addr6, - sizeof(addr6)); - if (server_v6 == -1) + sizeof(addr6), false); + if (server_v6 == -1 || !get_port(server_v6, &addr6.sin6_port)) + goto err; + + server_dual = start_server((const struct sockaddr *)&addr6dual, + sizeof(addr6dual), true); + if (server_dual == -1 || !get_port(server_dual, &addr4dual.sin_port)) + goto err; + + if (run_test(server, results, xdp, + (const struct sockaddr *)&addr4, sizeof(addr4))) goto err; - if (run_test(server, results, xdp)) + if (run_test(server_v6, results, xdp, + (const struct sockaddr *)&addr6, sizeof(addr6))) goto err; - if (run_test(server_v6, results, xdp)) + if (run_test(server_dual, results, xdp, + (const struct sockaddr *)&addr4dual, sizeof(addr4dual))) goto err; printf("ok\n"); @@ -252,6 +291,7 @@ err: out: close(server); close(server_v6); + close(server_dual); close(results); return err; } diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/vxlan_flooding_ipv6.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/vxlan_flooding_ipv6.sh index 429f7ee735cf..fd23c80eba31 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/vxlan_flooding_ipv6.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/vxlan_flooding_ipv6.sh @@ -159,6 +159,17 @@ flooding_remotes_add() local lsb local i + # Prevent unwanted packets from entering the bridge and interfering + # with the test. + tc qdisc add dev br0 clsact + tc filter add dev br0 egress protocol all pref 1 handle 1 \ + matchall skip_hw action drop + tc qdisc add dev $h1 clsact + tc filter add dev $h1 egress protocol all pref 1 handle 1 \ + flower skip_hw dst_mac de:ad:be:ef:13:37 action pass + tc filter add dev $h1 egress protocol all pref 2 handle 2 \ + matchall skip_hw action drop + for i in $(eval echo {1..$num_remotes}); do lsb=$((i + 1)) @@ -195,6 +206,12 @@ flooding_filters_del() done tc qdisc del dev $rp2 clsact + + tc filter del dev $h1 egress protocol all pref 2 handle 2 matchall + tc filter del dev $h1 egress protocol all pref 1 handle 1 flower + tc qdisc del dev $h1 clsact + tc filter del dev br0 egress protocol all pref 1 handle 1 matchall + tc qdisc del dev br0 clsact } flooding_check_packets() diff --git a/tools/testing/selftests/drivers/net/mlxsw/vxlan_flooding.sh b/tools/testing/selftests/drivers/net/mlxsw/vxlan_flooding.sh index fedcb7b35af9..af5ea50ed5c0 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/vxlan_flooding.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/vxlan_flooding.sh @@ -172,6 +172,17 @@ flooding_filters_add() local lsb local i + # Prevent unwanted packets from entering the bridge and interfering + # with the test. + tc qdisc add dev br0 clsact + tc filter add dev br0 egress protocol all pref 1 handle 1 \ + matchall skip_hw action drop + tc qdisc add dev $h1 clsact + tc filter add dev $h1 egress protocol all pref 1 handle 1 \ + flower skip_hw dst_mac de:ad:be:ef:13:37 action pass + tc filter add dev $h1 egress protocol all pref 2 handle 2 \ + matchall skip_hw action drop + tc qdisc add dev $rp2 clsact for i in $(eval echo {1..$num_remotes}); do @@ -194,6 +205,12 @@ flooding_filters_del() done tc qdisc del dev $rp2 clsact + + tc filter del dev $h1 egress protocol all pref 2 handle 2 matchall + tc filter del dev $h1 egress protocol all pref 1 handle 1 flower + tc qdisc del dev $h1 clsact + tc filter del dev br0 egress protocol all pref 1 handle 1 matchall + tc qdisc del dev br0 clsact } flooding_check_packets() diff --git a/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh b/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh index eaf8a04a7ca5..10e54bcca7a9 100755 --- a/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh +++ b/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh @@ -190,7 +190,7 @@ setup_prepare() tc filter add dev $eth0 ingress chain $(IS2 0 0) pref 1 \ protocol ipv4 flower skip_sw ip_proto udp dst_port 5201 \ - action police rate 50mbit burst 64k \ + action police rate 50mbit burst 64k conform-exceed drop/pipe \ action goto chain $(IS2 1 0) } diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h index 11779405dc80..25f4d54067c0 100644 --- a/tools/testing/selftests/kselftest_harness.h +++ b/tools/testing/selftests/kselftest_harness.h @@ -64,6 +64,7 @@ #include <sys/types.h> #include <sys/wait.h> #include <unistd.h> +#include <setjmp.h> #include "kselftest.h" @@ -183,7 +184,10 @@ struct __test_metadata *_metadata, \ struct __fixture_variant_metadata *variant) \ { \ - test_name(_metadata); \ + _metadata->setup_completed = true; \ + if (setjmp(_metadata->env) == 0) \ + test_name(_metadata); \ + __test_check_assert(_metadata); \ } \ static struct __test_metadata _##test_name##_object = \ { .name = #test_name, \ @@ -287,7 +291,9 @@ #define FIXTURE_TEARDOWN(fixture_name) \ void fixture_name##_teardown( \ struct __test_metadata __attribute__((unused)) *_metadata, \ - FIXTURE_DATA(fixture_name) __attribute__((unused)) *self) + FIXTURE_DATA(fixture_name) __attribute__((unused)) *self, \ + const FIXTURE_VARIANT(fixture_name) \ + __attribute__((unused)) *variant) /** * FIXTURE_VARIANT() - Optionally called once per fixture @@ -302,9 +308,9 @@ * ... * }; * - * Defines type of constant parameters provided to FIXTURE_SETUP() and TEST_F() - * as *variant*. Variants allow the same tests to be run with different - * arguments. + * Defines type of constant parameters provided to FIXTURE_SETUP(), TEST_F() and + * FIXTURE_TEARDOWN as *variant*. Variants allow the same tests to be run with + * different arguments. */ #define FIXTURE_VARIANT(fixture_name) struct _fixture_variant_##fixture_name @@ -356,10 +362,7 @@ * Defines a test that depends on a fixture (e.g., is part of a test case). * Very similar to TEST() except that *self* is the setup instance of fixture's * datatype exposed for use by the implementation. - * - * Warning: use of ASSERT_* here will skip TEARDOWN. */ -/* TODO(wad) register fixtures on dedicated test lists. */ #define TEST_F(fixture_name, test_name) \ __TEST_F_IMPL(fixture_name, test_name, -1, TEST_TIMEOUT_DEFAULT) @@ -381,12 +384,17 @@ /* fixture data is alloced, setup, and torn down per call. */ \ FIXTURE_DATA(fixture_name) self; \ memset(&self, 0, sizeof(FIXTURE_DATA(fixture_name))); \ - fixture_name##_setup(_metadata, &self, variant->data); \ - /* Let setup failure terminate early. */ \ - if (!_metadata->passed) \ - return; \ - fixture_name##_##test_name(_metadata, &self, variant->data); \ - fixture_name##_teardown(_metadata, &self); \ + if (setjmp(_metadata->env) == 0) { \ + fixture_name##_setup(_metadata, &self, variant->data); \ + /* Let setup failure terminate early. */ \ + if (!_metadata->passed) \ + return; \ + _metadata->setup_completed = true; \ + fixture_name##_##test_name(_metadata, &self, variant->data); \ + } \ + if (_metadata->setup_completed) \ + fixture_name##_teardown(_metadata, &self, variant->data); \ + __test_check_assert(_metadata); \ } \ static struct __test_metadata \ _##fixture_name##_##test_name##_object = { \ @@ -683,7 +691,7 @@ */ #define OPTIONAL_HANDLER(_assert) \ for (; _metadata->trigger; _metadata->trigger = \ - __bail(_assert, _metadata->no_print, _metadata->step)) + __bail(_assert, _metadata)) #define __INC_STEP(_metadata) \ /* Keep "step" below 255 (which is used for "SKIP" reporting). */ \ @@ -830,6 +838,9 @@ struct __test_metadata { bool timed_out; /* did this test timeout instead of exiting? */ __u8 step; bool no_print; /* manual trigger when TH_LOG_STREAM is not available */ + bool aborted; /* stopped test due to failed ASSERT */ + bool setup_completed; /* did setup finish? */ + jmp_buf env; /* for exiting out of test early */ struct __test_results *results; struct __test_metadata *prev, *next; }; @@ -848,16 +859,26 @@ static inline void __register_test(struct __test_metadata *t) __LIST_APPEND(t->fixture->tests, t); } -static inline int __bail(int for_realz, bool no_print, __u8 step) +static inline int __bail(int for_realz, struct __test_metadata *t) { + /* if this is ASSERT, return immediately. */ if (for_realz) { - if (no_print) - _exit(step); - abort(); + t->aborted = true; + longjmp(t->env, 1); } + /* otherwise, end the for loop and continue. */ return 0; } +static inline void __test_check_assert(struct __test_metadata *t) +{ + if (t->aborted) { + if (t->no_print) + _exit(t->step); + abort(); + } +} + struct __test_metadata *__active_test; static void __timeout_handler(int sig, siginfo_t *info, void *ucontext) { diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore index d1e8f5237469..0b0e4402bba6 100644 --- a/tools/testing/selftests/kvm/.gitignore +++ b/tools/testing/selftests/kvm/.gitignore @@ -3,6 +3,7 @@ /aarch64/debug-exceptions /aarch64/get-reg-list /aarch64/psci_cpu_on_test +/aarch64/vcpu_width_config /aarch64/vgic_init /aarch64/vgic_irq /s390x/memop @@ -33,6 +34,7 @@ /x86_64/state_test /x86_64/svm_vmcall_test /x86_64/svm_int_ctl_test +/x86_64/tsc_scaling_sync /x86_64/sync_regs_test /x86_64/tsc_msrs_test /x86_64/userspace_io_test diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 21c2dbd21a81..681b173aa87c 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -106,6 +106,7 @@ TEST_GEN_PROGS_aarch64 += aarch64/arch_timer TEST_GEN_PROGS_aarch64 += aarch64/debug-exceptions TEST_GEN_PROGS_aarch64 += aarch64/get-reg-list TEST_GEN_PROGS_aarch64 += aarch64/psci_cpu_on_test +TEST_GEN_PROGS_aarch64 += aarch64/vcpu_width_config TEST_GEN_PROGS_aarch64 += aarch64/vgic_init TEST_GEN_PROGS_aarch64 += aarch64/vgic_irq TEST_GEN_PROGS_aarch64 += demand_paging_test diff --git a/tools/testing/selftests/kvm/aarch64/arch_timer.c b/tools/testing/selftests/kvm/aarch64/arch_timer.c index b08d30bf71c5..3b940a101bc0 100644 --- a/tools/testing/selftests/kvm/aarch64/arch_timer.c +++ b/tools/testing/selftests/kvm/aarch64/arch_timer.c @@ -362,11 +362,12 @@ static void test_init_timer_irq(struct kvm_vm *vm) pr_debug("ptimer_irq: %d; vtimer_irq: %d\n", ptimer_irq, vtimer_irq); } +static int gic_fd; + static struct kvm_vm *test_vm_create(void) { struct kvm_vm *vm; unsigned int i; - int ret; int nr_vcpus = test_args.nr_vcpus; vm = vm_create_default_with_vcpus(nr_vcpus, 0, 0, guest_code, NULL); @@ -383,8 +384,8 @@ static struct kvm_vm *test_vm_create(void) ucall_init(vm, NULL); test_init_timer_irq(vm); - ret = vgic_v3_setup(vm, nr_vcpus, 64, GICD_BASE_GPA, GICR_BASE_GPA); - if (ret < 0) { + gic_fd = vgic_v3_setup(vm, nr_vcpus, 64, GICD_BASE_GPA, GICR_BASE_GPA); + if (gic_fd < 0) { print_skip("Failed to create vgic-v3"); exit(KSFT_SKIP); } @@ -395,6 +396,12 @@ static struct kvm_vm *test_vm_create(void) return vm; } +static void test_vm_cleanup(struct kvm_vm *vm) +{ + close(gic_fd); + kvm_vm_free(vm); +} + static void test_print_help(char *name) { pr_info("Usage: %s [-h] [-n nr_vcpus] [-i iterations] [-p timer_period_ms]\n", @@ -478,7 +485,7 @@ int main(int argc, char *argv[]) vm = test_vm_create(); test_run(vm); - kvm_vm_free(vm); + test_vm_cleanup(vm); return 0; } diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list.c b/tools/testing/selftests/kvm/aarch64/get-reg-list.c index f12147c43464..0b571f3fe64c 100644 --- a/tools/testing/selftests/kvm/aarch64/get-reg-list.c +++ b/tools/testing/selftests/kvm/aarch64/get-reg-list.c @@ -503,8 +503,13 @@ static void run_test(struct vcpu_config *c) ++missing_regs; if (new_regs || missing_regs) { + n = 0; + for_each_reg_filtered(i) + ++n; + printf("%s: Number blessed registers: %5lld\n", config_name(c), blessed_n); - printf("%s: Number registers: %5lld\n", config_name(c), reg_list->n); + printf("%s: Number registers: %5lld (includes %lld filtered registers)\n", + config_name(c), reg_list->n, reg_list->n - n); } if (new_regs) { @@ -683,9 +688,10 @@ static __u64 base_regs[] = { KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(spsr[4]), KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.fpsr), KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.fpcr), - KVM_REG_ARM_FW_REG(0), - KVM_REG_ARM_FW_REG(1), - KVM_REG_ARM_FW_REG(2), + KVM_REG_ARM_FW_REG(0), /* KVM_REG_ARM_PSCI_VERSION */ + KVM_REG_ARM_FW_REG(1), /* KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1 */ + KVM_REG_ARM_FW_REG(2), /* KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2 */ + KVM_REG_ARM_FW_REG(3), /* KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3 */ ARM64_SYS_REG(3, 3, 14, 3, 1), /* CNTV_CTL_EL0 */ ARM64_SYS_REG(3, 3, 14, 3, 2), /* CNTV_CVAL_EL0 */ ARM64_SYS_REG(3, 3, 14, 0, 2), diff --git a/tools/testing/selftests/kvm/aarch64/vcpu_width_config.c b/tools/testing/selftests/kvm/aarch64/vcpu_width_config.c new file mode 100644 index 000000000000..6e9402679229 --- /dev/null +++ b/tools/testing/selftests/kvm/aarch64/vcpu_width_config.c @@ -0,0 +1,122 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * vcpu_width_config - Test KVM_ARM_VCPU_INIT() with KVM_ARM_VCPU_EL1_32BIT. + * + * Copyright (c) 2022 Google LLC. + * + * This is a test that ensures that non-mixed-width vCPUs (all 64bit vCPUs + * or all 32bit vcPUs) can be configured and mixed-width vCPUs cannot be + * configured. + */ + +#include "kvm_util.h" +#include "processor.h" +#include "test_util.h" + + +/* + * Add a vCPU, run KVM_ARM_VCPU_INIT with @init1, and then + * add another vCPU, and run KVM_ARM_VCPU_INIT with @init2. + */ +static int add_init_2vcpus(struct kvm_vcpu_init *init1, + struct kvm_vcpu_init *init2) +{ + struct kvm_vm *vm; + int ret; + + vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR); + + vm_vcpu_add(vm, 0); + ret = _vcpu_ioctl(vm, 0, KVM_ARM_VCPU_INIT, init1); + if (ret) + goto free_exit; + + vm_vcpu_add(vm, 1); + ret = _vcpu_ioctl(vm, 1, KVM_ARM_VCPU_INIT, init2); + +free_exit: + kvm_vm_free(vm); + return ret; +} + +/* + * Add two vCPUs, then run KVM_ARM_VCPU_INIT for one vCPU with @init1, + * and run KVM_ARM_VCPU_INIT for another vCPU with @init2. + */ +static int add_2vcpus_init_2vcpus(struct kvm_vcpu_init *init1, + struct kvm_vcpu_init *init2) +{ + struct kvm_vm *vm; + int ret; + + vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR); + + vm_vcpu_add(vm, 0); + vm_vcpu_add(vm, 1); + + ret = _vcpu_ioctl(vm, 0, KVM_ARM_VCPU_INIT, init1); + if (ret) + goto free_exit; + + ret = _vcpu_ioctl(vm, 1, KVM_ARM_VCPU_INIT, init2); + +free_exit: + kvm_vm_free(vm); + return ret; +} + +/* + * Tests that two 64bit vCPUs can be configured, two 32bit vCPUs can be + * configured, and two mixed-width vCPUs cannot be configured. + * Each of those three cases, configure vCPUs in two different orders. + * The one is running KVM_CREATE_VCPU for 2 vCPUs, and then running + * KVM_ARM_VCPU_INIT for them. + * The other is running KVM_CREATE_VCPU and KVM_ARM_VCPU_INIT for a vCPU, + * and then run those commands for another vCPU. + */ +int main(void) +{ + struct kvm_vcpu_init init1, init2; + struct kvm_vm *vm; + int ret; + + if (!kvm_check_cap(KVM_CAP_ARM_EL1_32BIT)) { + print_skip("KVM_CAP_ARM_EL1_32BIT is not supported"); + exit(KSFT_SKIP); + } + + /* Get the preferred target type and copy that to init2 for later use */ + vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR); + vm_ioctl(vm, KVM_ARM_PREFERRED_TARGET, &init1); + kvm_vm_free(vm); + init2 = init1; + + /* Test with 64bit vCPUs */ + ret = add_init_2vcpus(&init1, &init1); + TEST_ASSERT(ret == 0, + "Configuring 64bit EL1 vCPUs failed unexpectedly"); + ret = add_2vcpus_init_2vcpus(&init1, &init1); + TEST_ASSERT(ret == 0, + "Configuring 64bit EL1 vCPUs failed unexpectedly"); + + /* Test with 32bit vCPUs */ + init1.features[0] = (1 << KVM_ARM_VCPU_EL1_32BIT); + ret = add_init_2vcpus(&init1, &init1); + TEST_ASSERT(ret == 0, + "Configuring 32bit EL1 vCPUs failed unexpectedly"); + ret = add_2vcpus_init_2vcpus(&init1, &init1); + TEST_ASSERT(ret == 0, + "Configuring 32bit EL1 vCPUs failed unexpectedly"); + + /* Test with mixed-width vCPUs */ + init1.features[0] = 0; + init2.features[0] = (1 << KVM_ARM_VCPU_EL1_32BIT); + ret = add_init_2vcpus(&init1, &init2); + TEST_ASSERT(ret != 0, + "Configuring mixed-width vCPUs worked unexpectedly"); + ret = add_2vcpus_init_2vcpus(&init1, &init2); + TEST_ASSERT(ret != 0, + "Configuring mixed-width vCPUs worked unexpectedly"); + + return 0; +} diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c index c9d9e513ca04..7b47ae4f952e 100644 --- a/tools/testing/selftests/kvm/dirty_log_perf_test.c +++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c @@ -18,11 +18,40 @@ #include "test_util.h" #include "perf_test_util.h" #include "guest_modes.h" + #ifdef __aarch64__ #include "aarch64/vgic.h" #define GICD_BASE_GPA 0x8000000ULL #define GICR_BASE_GPA 0x80A0000ULL + +static int gic_fd; + +static void arch_setup_vm(struct kvm_vm *vm, unsigned int nr_vcpus) +{ + /* + * The test can still run even if hardware does not support GICv3, as it + * is only an optimization to reduce guest exits. + */ + gic_fd = vgic_v3_setup(vm, nr_vcpus, 64, GICD_BASE_GPA, GICR_BASE_GPA); +} + +static void arch_cleanup_vm(struct kvm_vm *vm) +{ + if (gic_fd > 0) + close(gic_fd); +} + +#else /* __aarch64__ */ + +static void arch_setup_vm(struct kvm_vm *vm, unsigned int nr_vcpus) +{ +} + +static void arch_cleanup_vm(struct kvm_vm *vm) +{ +} + #endif /* How many host loops to run by default (one KVM_GET_DIRTY_LOG for each loop)*/ @@ -206,9 +235,7 @@ static void run_test(enum vm_guest_mode mode, void *arg) vm_enable_cap(vm, &cap); } -#ifdef __aarch64__ - vgic_v3_setup(vm, nr_vcpus, 64, GICD_BASE_GPA, GICR_BASE_GPA); -#endif + arch_setup_vm(vm, nr_vcpus); /* Start the iterations */ iteration = 0; @@ -302,6 +329,7 @@ static void run_test(enum vm_guest_mode mode, void *arg) } free_bitmaps(bitmaps, p->slots); + arch_cleanup_vm(vm); perf_test_destroy_vm(vm); } diff --git a/tools/testing/selftests/kvm/include/riscv/processor.h b/tools/testing/selftests/kvm/include/riscv/processor.h index dc284c6bdbc3..eca5c622efd2 100644 --- a/tools/testing/selftests/kvm/include/riscv/processor.h +++ b/tools/testing/selftests/kvm/include/riscv/processor.h @@ -101,7 +101,9 @@ static inline void set_reg(struct kvm_vm *vm, uint32_t vcpuid, uint64_t id, #define PGTBL_PTE_WRITE_SHIFT 2 #define PGTBL_PTE_READ_MASK 0x0000000000000002ULL #define PGTBL_PTE_READ_SHIFT 1 -#define PGTBL_PTE_PERM_MASK (PGTBL_PTE_EXECUTE_MASK | \ +#define PGTBL_PTE_PERM_MASK (PGTBL_PTE_ACCESSED_MASK | \ + PGTBL_PTE_DIRTY_MASK | \ + PGTBL_PTE_EXECUTE_MASK | \ PGTBL_PTE_WRITE_MASK | \ PGTBL_PTE_READ_MASK) #define PGTBL_PTE_VALID_MASK 0x0000000000000001ULL diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index 37db341d4cc5..d0d51adec76e 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -60,6 +60,23 @@ /* CPUID.0x8000_0001.EDX */ #define CPUID_GBPAGES (1ul << 26) +/* Page table bitfield declarations */ +#define PTE_PRESENT_MASK BIT_ULL(0) +#define PTE_WRITABLE_MASK BIT_ULL(1) +#define PTE_USER_MASK BIT_ULL(2) +#define PTE_ACCESSED_MASK BIT_ULL(5) +#define PTE_DIRTY_MASK BIT_ULL(6) +#define PTE_LARGE_MASK BIT_ULL(7) +#define PTE_GLOBAL_MASK BIT_ULL(8) +#define PTE_NX_MASK BIT_ULL(63) + +#define PAGE_SHIFT 12 +#define PAGE_SIZE (1ULL << PAGE_SHIFT) +#define PAGE_MASK (~(PAGE_SIZE-1)) + +#define PHYSICAL_PAGE_MASK GENMASK_ULL(51, 12) +#define PTE_GET_PFN(pte) (((pte) & PHYSICAL_PAGE_MASK) >> PAGE_SHIFT) + /* General Registers in 64-Bit Mode */ struct gpr64_regs { u64 rax; diff --git a/tools/testing/selftests/kvm/kvm_page_table_test.c b/tools/testing/selftests/kvm/kvm_page_table_test.c index ba1fdc3dcf4a..2c4a7563a4f8 100644 --- a/tools/testing/selftests/kvm/kvm_page_table_test.c +++ b/tools/testing/selftests/kvm/kvm_page_table_test.c @@ -278,7 +278,7 @@ static struct kvm_vm *pre_init_before_test(enum vm_guest_mode mode, void *arg) else guest_test_phys_mem = p->phys_offset; #ifdef __s390x__ - alignment = max(0x100000, alignment); + alignment = max(0x100000UL, alignment); #endif guest_test_phys_mem = align_down(guest_test_phys_mem, alignment); diff --git a/tools/testing/selftests/kvm/lib/riscv/processor.c b/tools/testing/selftests/kvm/lib/riscv/processor.c index d377f2603d98..3961487a4870 100644 --- a/tools/testing/selftests/kvm/lib/riscv/processor.c +++ b/tools/testing/selftests/kvm/lib/riscv/processor.c @@ -268,7 +268,7 @@ void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid, uint8_t indent) core.regs.t3, core.regs.t4, core.regs.t5, core.regs.t6); } -static void guest_hang(void) +static void __aligned(16) guest_hang(void) { while (1) ; diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index 9f000dfb5594..33ea5e9955d9 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -19,38 +19,6 @@ vm_vaddr_t exception_handlers; -/* Virtual translation table structure declarations */ -struct pageUpperEntry { - uint64_t present:1; - uint64_t writable:1; - uint64_t user:1; - uint64_t write_through:1; - uint64_t cache_disable:1; - uint64_t accessed:1; - uint64_t ignored_06:1; - uint64_t page_size:1; - uint64_t ignored_11_08:4; - uint64_t pfn:40; - uint64_t ignored_62_52:11; - uint64_t execute_disable:1; -}; - -struct pageTableEntry { - uint64_t present:1; - uint64_t writable:1; - uint64_t user:1; - uint64_t write_through:1; - uint64_t cache_disable:1; - uint64_t accessed:1; - uint64_t dirty:1; - uint64_t reserved_07:1; - uint64_t global:1; - uint64_t ignored_11_09:3; - uint64_t pfn:40; - uint64_t ignored_62_52:11; - uint64_t execute_disable:1; -}; - void regs_dump(FILE *stream, struct kvm_regs *regs, uint8_t indent) { @@ -195,23 +163,21 @@ static void *virt_get_pte(struct kvm_vm *vm, uint64_t pt_pfn, uint64_t vaddr, return &page_table[index]; } -static struct pageUpperEntry *virt_create_upper_pte(struct kvm_vm *vm, - uint64_t pt_pfn, - uint64_t vaddr, - uint64_t paddr, - int level, - enum x86_page_size page_size) +static uint64_t *virt_create_upper_pte(struct kvm_vm *vm, + uint64_t pt_pfn, + uint64_t vaddr, + uint64_t paddr, + int level, + enum x86_page_size page_size) { - struct pageUpperEntry *pte = virt_get_pte(vm, pt_pfn, vaddr, level); - - if (!pte->present) { - pte->writable = true; - pte->present = true; - pte->page_size = (level == page_size); - if (pte->page_size) - pte->pfn = paddr >> vm->page_shift; + uint64_t *pte = virt_get_pte(vm, pt_pfn, vaddr, level); + + if (!(*pte & PTE_PRESENT_MASK)) { + *pte = PTE_PRESENT_MASK | PTE_WRITABLE_MASK; + if (level == page_size) + *pte |= PTE_LARGE_MASK | (paddr & PHYSICAL_PAGE_MASK); else - pte->pfn = vm_alloc_page_table(vm) >> vm->page_shift; + *pte |= vm_alloc_page_table(vm) & PHYSICAL_PAGE_MASK; } else { /* * Entry already present. Assert that the caller doesn't want @@ -221,7 +187,7 @@ static struct pageUpperEntry *virt_create_upper_pte(struct kvm_vm *vm, TEST_ASSERT(level != page_size, "Cannot create hugepage at level: %u, vaddr: 0x%lx\n", page_size, vaddr); - TEST_ASSERT(!pte->page_size, + TEST_ASSERT(!(*pte & PTE_LARGE_MASK), "Cannot create page table at level: %u, vaddr: 0x%lx\n", level, vaddr); } @@ -232,8 +198,8 @@ void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, enum x86_page_size page_size) { const uint64_t pg_size = 1ull << ((page_size * 9) + 12); - struct pageUpperEntry *pml4e, *pdpe, *pde; - struct pageTableEntry *pte; + uint64_t *pml4e, *pdpe, *pde; + uint64_t *pte; TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K, "Unknown or unsupported guest mode, mode: 0x%x", vm->mode); @@ -257,24 +223,22 @@ void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, */ pml4e = virt_create_upper_pte(vm, vm->pgd >> vm->page_shift, vaddr, paddr, 3, page_size); - if (pml4e->page_size) + if (*pml4e & PTE_LARGE_MASK) return; - pdpe = virt_create_upper_pte(vm, pml4e->pfn, vaddr, paddr, 2, page_size); - if (pdpe->page_size) + pdpe = virt_create_upper_pte(vm, PTE_GET_PFN(*pml4e), vaddr, paddr, 2, page_size); + if (*pdpe & PTE_LARGE_MASK) return; - pde = virt_create_upper_pte(vm, pdpe->pfn, vaddr, paddr, 1, page_size); - if (pde->page_size) + pde = virt_create_upper_pte(vm, PTE_GET_PFN(*pdpe), vaddr, paddr, 1, page_size); + if (*pde & PTE_LARGE_MASK) return; /* Fill in page table entry. */ - pte = virt_get_pte(vm, pde->pfn, vaddr, 0); - TEST_ASSERT(!pte->present, + pte = virt_get_pte(vm, PTE_GET_PFN(*pde), vaddr, 0); + TEST_ASSERT(!(*pte & PTE_PRESENT_MASK), "PTE already present for 4k page at vaddr: 0x%lx\n", vaddr); - pte->pfn = paddr >> vm->page_shift; - pte->writable = true; - pte->present = 1; + *pte = PTE_PRESENT_MASK | PTE_WRITABLE_MASK | (paddr & PHYSICAL_PAGE_MASK); } void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr) @@ -282,22 +246,22 @@ void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr) __virt_pg_map(vm, vaddr, paddr, X86_PAGE_SIZE_4K); } -static struct pageTableEntry *_vm_get_page_table_entry(struct kvm_vm *vm, int vcpuid, +static uint64_t *_vm_get_page_table_entry(struct kvm_vm *vm, int vcpuid, uint64_t vaddr) { uint16_t index[4]; - struct pageUpperEntry *pml4e, *pdpe, *pde; - struct pageTableEntry *pte; + uint64_t *pml4e, *pdpe, *pde; + uint64_t *pte; struct kvm_cpuid_entry2 *entry; struct kvm_sregs sregs; int max_phy_addr; - /* Set the bottom 52 bits. */ - uint64_t rsvd_mask = 0x000fffffffffffff; + uint64_t rsvd_mask = 0; entry = kvm_get_supported_cpuid_index(0x80000008, 0); max_phy_addr = entry->eax & 0x000000ff; - /* Clear the bottom bits of the reserved mask. */ - rsvd_mask = (rsvd_mask >> max_phy_addr) << max_phy_addr; + /* Set the high bits in the reserved mask. */ + if (max_phy_addr < 52) + rsvd_mask = GENMASK_ULL(51, max_phy_addr); /* * SDM vol 3, fig 4-11 "Formats of CR3 and Paging-Structure Entries @@ -307,7 +271,7 @@ static struct pageTableEntry *_vm_get_page_table_entry(struct kvm_vm *vm, int vc */ vcpu_sregs_get(vm, vcpuid, &sregs); if ((sregs.efer & EFER_NX) == 0) { - rsvd_mask |= (1ull << 63); + rsvd_mask |= PTE_NX_MASK; } TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K, "Attempt to use " @@ -329,30 +293,29 @@ static struct pageTableEntry *_vm_get_page_table_entry(struct kvm_vm *vm, int vc index[3] = (vaddr >> 39) & 0x1ffu; pml4e = addr_gpa2hva(vm, vm->pgd); - TEST_ASSERT(pml4e[index[3]].present, + TEST_ASSERT(pml4e[index[3]] & PTE_PRESENT_MASK, "Expected pml4e to be present for gva: 0x%08lx", vaddr); - TEST_ASSERT((*(uint64_t*)(&pml4e[index[3]]) & - (rsvd_mask | (1ull << 7))) == 0, + TEST_ASSERT((pml4e[index[3]] & (rsvd_mask | PTE_LARGE_MASK)) == 0, "Unexpected reserved bits set."); - pdpe = addr_gpa2hva(vm, pml4e[index[3]].pfn * vm->page_size); - TEST_ASSERT(pdpe[index[2]].present, + pdpe = addr_gpa2hva(vm, PTE_GET_PFN(pml4e[index[3]]) * vm->page_size); + TEST_ASSERT(pdpe[index[2]] & PTE_PRESENT_MASK, "Expected pdpe to be present for gva: 0x%08lx", vaddr); - TEST_ASSERT(pdpe[index[2]].page_size == 0, + TEST_ASSERT(!(pdpe[index[2]] & PTE_LARGE_MASK), "Expected pdpe to map a pde not a 1-GByte page."); - TEST_ASSERT((*(uint64_t*)(&pdpe[index[2]]) & rsvd_mask) == 0, + TEST_ASSERT((pdpe[index[2]] & rsvd_mask) == 0, "Unexpected reserved bits set."); - pde = addr_gpa2hva(vm, pdpe[index[2]].pfn * vm->page_size); - TEST_ASSERT(pde[index[1]].present, + pde = addr_gpa2hva(vm, PTE_GET_PFN(pdpe[index[2]]) * vm->page_size); + TEST_ASSERT(pde[index[1]] & PTE_PRESENT_MASK, "Expected pde to be present for gva: 0x%08lx", vaddr); - TEST_ASSERT(pde[index[1]].page_size == 0, + TEST_ASSERT(!(pde[index[1]] & PTE_LARGE_MASK), "Expected pde to map a pte not a 2-MByte page."); - TEST_ASSERT((*(uint64_t*)(&pde[index[1]]) & rsvd_mask) == 0, + TEST_ASSERT((pde[index[1]] & rsvd_mask) == 0, "Unexpected reserved bits set."); - pte = addr_gpa2hva(vm, pde[index[1]].pfn * vm->page_size); - TEST_ASSERT(pte[index[0]].present, + pte = addr_gpa2hva(vm, PTE_GET_PFN(pde[index[1]]) * vm->page_size); + TEST_ASSERT(pte[index[0]] & PTE_PRESENT_MASK, "Expected pte to be present for gva: 0x%08lx", vaddr); return &pte[index[0]]; @@ -360,7 +323,7 @@ static struct pageTableEntry *_vm_get_page_table_entry(struct kvm_vm *vm, int vc uint64_t vm_get_page_table_entry(struct kvm_vm *vm, int vcpuid, uint64_t vaddr) { - struct pageTableEntry *pte = _vm_get_page_table_entry(vm, vcpuid, vaddr); + uint64_t *pte = _vm_get_page_table_entry(vm, vcpuid, vaddr); return *(uint64_t *)pte; } @@ -368,18 +331,17 @@ uint64_t vm_get_page_table_entry(struct kvm_vm *vm, int vcpuid, uint64_t vaddr) void vm_set_page_table_entry(struct kvm_vm *vm, int vcpuid, uint64_t vaddr, uint64_t pte) { - struct pageTableEntry *new_pte = _vm_get_page_table_entry(vm, vcpuid, - vaddr); + uint64_t *new_pte = _vm_get_page_table_entry(vm, vcpuid, vaddr); *(uint64_t *)new_pte = pte; } void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) { - struct pageUpperEntry *pml4e, *pml4e_start; - struct pageUpperEntry *pdpe, *pdpe_start; - struct pageUpperEntry *pde, *pde_start; - struct pageTableEntry *pte, *pte_start; + uint64_t *pml4e, *pml4e_start; + uint64_t *pdpe, *pdpe_start; + uint64_t *pde, *pde_start; + uint64_t *pte, *pte_start; if (!vm->pgd_created) return; @@ -389,58 +351,58 @@ void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) fprintf(stream, "%*s index hvaddr gpaddr " "addr w exec dirty\n", indent, ""); - pml4e_start = (struct pageUpperEntry *) addr_gpa2hva(vm, vm->pgd); + pml4e_start = (uint64_t *) addr_gpa2hva(vm, vm->pgd); for (uint16_t n1 = 0; n1 <= 0x1ffu; n1++) { pml4e = &pml4e_start[n1]; - if (!pml4e->present) + if (!(*pml4e & PTE_PRESENT_MASK)) continue; - fprintf(stream, "%*spml4e 0x%-3zx %p 0x%-12lx 0x%-10lx %u " + fprintf(stream, "%*spml4e 0x%-3zx %p 0x%-12lx 0x%-10llx %u " " %u\n", indent, "", pml4e - pml4e_start, pml4e, - addr_hva2gpa(vm, pml4e), (uint64_t) pml4e->pfn, - pml4e->writable, pml4e->execute_disable); + addr_hva2gpa(vm, pml4e), PTE_GET_PFN(*pml4e), + !!(*pml4e & PTE_WRITABLE_MASK), !!(*pml4e & PTE_NX_MASK)); - pdpe_start = addr_gpa2hva(vm, pml4e->pfn * vm->page_size); + pdpe_start = addr_gpa2hva(vm, *pml4e & PHYSICAL_PAGE_MASK); for (uint16_t n2 = 0; n2 <= 0x1ffu; n2++) { pdpe = &pdpe_start[n2]; - if (!pdpe->present) + if (!(*pdpe & PTE_PRESENT_MASK)) continue; - fprintf(stream, "%*spdpe 0x%-3zx %p 0x%-12lx 0x%-10lx " + fprintf(stream, "%*spdpe 0x%-3zx %p 0x%-12lx 0x%-10llx " "%u %u\n", indent, "", pdpe - pdpe_start, pdpe, addr_hva2gpa(vm, pdpe), - (uint64_t) pdpe->pfn, pdpe->writable, - pdpe->execute_disable); + PTE_GET_PFN(*pdpe), !!(*pdpe & PTE_WRITABLE_MASK), + !!(*pdpe & PTE_NX_MASK)); - pde_start = addr_gpa2hva(vm, pdpe->pfn * vm->page_size); + pde_start = addr_gpa2hva(vm, *pdpe & PHYSICAL_PAGE_MASK); for (uint16_t n3 = 0; n3 <= 0x1ffu; n3++) { pde = &pde_start[n3]; - if (!pde->present) + if (!(*pde & PTE_PRESENT_MASK)) continue; fprintf(stream, "%*spde 0x%-3zx %p " - "0x%-12lx 0x%-10lx %u %u\n", + "0x%-12lx 0x%-10llx %u %u\n", indent, "", pde - pde_start, pde, addr_hva2gpa(vm, pde), - (uint64_t) pde->pfn, pde->writable, - pde->execute_disable); + PTE_GET_PFN(*pde), !!(*pde & PTE_WRITABLE_MASK), + !!(*pde & PTE_NX_MASK)); - pte_start = addr_gpa2hva(vm, pde->pfn * vm->page_size); + pte_start = addr_gpa2hva(vm, *pde & PHYSICAL_PAGE_MASK); for (uint16_t n4 = 0; n4 <= 0x1ffu; n4++) { pte = &pte_start[n4]; - if (!pte->present) + if (!(*pte & PTE_PRESENT_MASK)) continue; fprintf(stream, "%*spte 0x%-3zx %p " - "0x%-12lx 0x%-10lx %u %u " + "0x%-12lx 0x%-10llx %u %u " " %u 0x%-10lx\n", indent, "", pte - pte_start, pte, addr_hva2gpa(vm, pte), - (uint64_t) pte->pfn, - pte->writable, - pte->execute_disable, - pte->dirty, + PTE_GET_PFN(*pte), + !!(*pte & PTE_WRITABLE_MASK), + !!(*pte & PTE_NX_MASK), + !!(*pte & PTE_DIRTY_MASK), ((uint64_t) n1 << 27) | ((uint64_t) n2 << 18) | ((uint64_t) n3 << 9) @@ -558,8 +520,8 @@ static void kvm_seg_set_kernel_data_64bit(struct kvm_vm *vm, uint16_t selector, vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva) { uint16_t index[4]; - struct pageUpperEntry *pml4e, *pdpe, *pde; - struct pageTableEntry *pte; + uint64_t *pml4e, *pdpe, *pde; + uint64_t *pte; TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K, "Attempt to use " "unknown or unsupported guest mode, mode: 0x%x", vm->mode); @@ -572,22 +534,22 @@ vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva) if (!vm->pgd_created) goto unmapped_gva; pml4e = addr_gpa2hva(vm, vm->pgd); - if (!pml4e[index[3]].present) + if (!(pml4e[index[3]] & PTE_PRESENT_MASK)) goto unmapped_gva; - pdpe = addr_gpa2hva(vm, pml4e[index[3]].pfn * vm->page_size); - if (!pdpe[index[2]].present) + pdpe = addr_gpa2hva(vm, PTE_GET_PFN(pml4e[index[3]]) * vm->page_size); + if (!(pdpe[index[2]] & PTE_PRESENT_MASK)) goto unmapped_gva; - pde = addr_gpa2hva(vm, pdpe[index[2]].pfn * vm->page_size); - if (!pde[index[1]].present) + pde = addr_gpa2hva(vm, PTE_GET_PFN(pdpe[index[2]]) * vm->page_size); + if (!(pde[index[1]] & PTE_PRESENT_MASK)) goto unmapped_gva; - pte = addr_gpa2hva(vm, pde[index[1]].pfn * vm->page_size); - if (!pte[index[0]].present) + pte = addr_gpa2hva(vm, PTE_GET_PFN(pde[index[1]]) * vm->page_size); + if (!(pte[index[0]] & PTE_PRESENT_MASK)) goto unmapped_gva; - return (pte[index[0]].pfn * vm->page_size) + (gva & 0xfffu); + return (PTE_GET_PFN(pte[index[0]]) * vm->page_size) + (gva & ~PAGE_MASK); unmapped_gva: TEST_FAIL("No mapping for vm virtual address, gva: 0x%lx", gva); diff --git a/tools/testing/selftests/kvm/x86_64/amx_test.c b/tools/testing/selftests/kvm/x86_64/amx_test.c index 52a3ef6629e8..76f65c22796f 100644 --- a/tools/testing/selftests/kvm/x86_64/amx_test.c +++ b/tools/testing/selftests/kvm/x86_64/amx_test.c @@ -29,7 +29,6 @@ #define X86_FEATURE_XSAVE (1 << 26) #define X86_FEATURE_OSXSAVE (1 << 27) -#define PAGE_SIZE (1 << 12) #define NUM_TILES 8 #define TILE_SIZE 1024 #define XSAVE_SIZE ((NUM_TILES * TILE_SIZE) + PAGE_SIZE) diff --git a/tools/testing/selftests/kvm/x86_64/emulator_error_test.c b/tools/testing/selftests/kvm/x86_64/emulator_error_test.c index f070ff0224fa..aeb3850f81bd 100644 --- a/tools/testing/selftests/kvm/x86_64/emulator_error_test.c +++ b/tools/testing/selftests/kvm/x86_64/emulator_error_test.c @@ -12,7 +12,6 @@ #include "vmx.h" #define VCPU_ID 1 -#define PAGE_SIZE 4096 #define MAXPHYADDR 36 #define MEM_REGION_GVA 0x0000123456789000 diff --git a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c index 0d06ffa95d9d..93d77574b255 100644 --- a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c +++ b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c @@ -208,7 +208,7 @@ static bool sanity_check_pmu(struct kvm_vm *vm) return success; } -static struct kvm_pmu_event_filter *make_pmu_event_filter(uint32_t nevents) +static struct kvm_pmu_event_filter *alloc_pmu_event_filter(uint32_t nevents) { struct kvm_pmu_event_filter *f; int size = sizeof(*f) + nevents * sizeof(f->events[0]); @@ -220,19 +220,29 @@ static struct kvm_pmu_event_filter *make_pmu_event_filter(uint32_t nevents) return f; } -static struct kvm_pmu_event_filter *event_filter(uint32_t action) + +static struct kvm_pmu_event_filter * +create_pmu_event_filter(const uint64_t event_list[], + int nevents, uint32_t action) { struct kvm_pmu_event_filter *f; int i; - f = make_pmu_event_filter(ARRAY_SIZE(event_list)); + f = alloc_pmu_event_filter(nevents); f->action = action; - for (i = 0; i < ARRAY_SIZE(event_list); i++) + for (i = 0; i < nevents; i++) f->events[i] = event_list[i]; return f; } +static struct kvm_pmu_event_filter *event_filter(uint32_t action) +{ + return create_pmu_event_filter(event_list, + ARRAY_SIZE(event_list), + action); +} + /* * Remove the first occurrence of 'event' (if any) from the filter's * event list. @@ -271,6 +281,22 @@ static uint64_t test_with_filter(struct kvm_vm *vm, return run_vm_to_sync(vm); } +static void test_amd_deny_list(struct kvm_vm *vm) +{ + uint64_t event = EVENT(0x1C2, 0); + struct kvm_pmu_event_filter *f; + uint64_t count; + + f = create_pmu_event_filter(&event, 1, KVM_PMU_EVENT_DENY); + count = test_with_filter(vm, f); + + free(f); + if (count != NUM_BRANCHES) + pr_info("%s: Branch instructions retired = %lu (expected %u)\n", + __func__, count, NUM_BRANCHES); + TEST_ASSERT(count, "Allowed PMU event is not counting"); +} + static void test_member_deny_list(struct kvm_vm *vm) { struct kvm_pmu_event_filter *f = event_filter(KVM_PMU_EVENT_DENY); @@ -453,6 +479,9 @@ int main(int argc, char *argv[]) exit(KSFT_SKIP); } + if (use_amd_pmu()) + test_amd_deny_list(vm); + test_without_filter(vm); test_member_deny_list(vm); test_member_allow_list(vm); diff --git a/tools/testing/selftests/kvm/x86_64/smm_test.c b/tools/testing/selftests/kvm/x86_64/smm_test.c index a626d40fdb48..b4e0c860769e 100644 --- a/tools/testing/selftests/kvm/x86_64/smm_test.c +++ b/tools/testing/selftests/kvm/x86_64/smm_test.c @@ -21,8 +21,6 @@ #define VCPU_ID 1 -#define PAGE_SIZE 4096 - #define SMRAM_SIZE 65536 #define SMRAM_MEMSLOT ((1 << 16) | 1) #define SMRAM_PAGES (SMRAM_SIZE / PAGE_SIZE) diff --git a/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c b/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c index e683d0ac3e45..19b35c607dc6 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c @@ -32,7 +32,6 @@ #define MSR_IA32_TSC_ADJUST 0x3b #endif -#define PAGE_SIZE 4096 #define VCPU_ID 5 #define TSC_ADJUST_VALUE (1ll << 32) diff --git a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c index 865e17146815..bcd370827859 100644 --- a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c +++ b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c @@ -23,7 +23,6 @@ #define SHINFO_REGION_GVA 0xc0000000ULL #define SHINFO_REGION_GPA 0xc0000000ULL #define SHINFO_REGION_SLOT 10 -#define PAGE_SIZE 4096 #define DUMMY_REGION_GPA (SHINFO_REGION_GPA + (2 * PAGE_SIZE)) #define DUMMY_REGION_SLOT 11 diff --git a/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c b/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c index adc94452b57c..b30fe9de1d4f 100644 --- a/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c +++ b/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c @@ -15,7 +15,6 @@ #define HCALL_REGION_GPA 0xc0000000ULL #define HCALL_REGION_SLOT 10 -#define PAGE_SIZE 4096 static struct kvm_vm *vm; diff --git a/tools/testing/selftests/landlock/base_test.c b/tools/testing/selftests/landlock/base_test.c index ca40abe9daa8..da9290817866 100644 --- a/tools/testing/selftests/landlock/base_test.c +++ b/tools/testing/selftests/landlock/base_test.c @@ -18,10 +18,11 @@ #include "common.h" #ifndef O_PATH -#define O_PATH 010000000 +#define O_PATH 010000000 #endif -TEST(inconsistent_attr) { +TEST(inconsistent_attr) +{ const long page_size = sysconf(_SC_PAGESIZE); char *const buf = malloc(page_size + 1); struct landlock_ruleset_attr *const ruleset_attr = (void *)buf; @@ -34,20 +35,26 @@ TEST(inconsistent_attr) { ASSERT_EQ(EINVAL, errno); ASSERT_EQ(-1, landlock_create_ruleset(ruleset_attr, 1, 0)); ASSERT_EQ(EINVAL, errno); + ASSERT_EQ(-1, landlock_create_ruleset(ruleset_attr, 7, 0)); + ASSERT_EQ(EINVAL, errno); ASSERT_EQ(-1, landlock_create_ruleset(NULL, 1, 0)); /* The size if less than sizeof(struct landlock_attr_enforce). */ ASSERT_EQ(EFAULT, errno); - ASSERT_EQ(-1, landlock_create_ruleset(NULL, - sizeof(struct landlock_ruleset_attr), 0)); + ASSERT_EQ(-1, landlock_create_ruleset( + NULL, sizeof(struct landlock_ruleset_attr), 0)); ASSERT_EQ(EFAULT, errno); ASSERT_EQ(-1, landlock_create_ruleset(ruleset_attr, page_size + 1, 0)); ASSERT_EQ(E2BIG, errno); - ASSERT_EQ(-1, landlock_create_ruleset(ruleset_attr, - sizeof(struct landlock_ruleset_attr), 0)); + /* Checks minimal valid attribute size. */ + ASSERT_EQ(-1, landlock_create_ruleset(ruleset_attr, 8, 0)); + ASSERT_EQ(ENOMSG, errno); + ASSERT_EQ(-1, landlock_create_ruleset( + ruleset_attr, + sizeof(struct landlock_ruleset_attr), 0)); ASSERT_EQ(ENOMSG, errno); ASSERT_EQ(-1, landlock_create_ruleset(ruleset_attr, page_size, 0)); ASSERT_EQ(ENOMSG, errno); @@ -63,38 +70,44 @@ TEST(inconsistent_attr) { free(buf); } -TEST(abi_version) { +TEST(abi_version) +{ const struct landlock_ruleset_attr ruleset_attr = { .handled_access_fs = LANDLOCK_ACCESS_FS_READ_FILE, }; - ASSERT_EQ(1, landlock_create_ruleset(NULL, 0, - LANDLOCK_CREATE_RULESET_VERSION)); + ASSERT_EQ(2, landlock_create_ruleset(NULL, 0, + LANDLOCK_CREATE_RULESET_VERSION)); ASSERT_EQ(-1, landlock_create_ruleset(&ruleset_attr, 0, - LANDLOCK_CREATE_RULESET_VERSION)); + LANDLOCK_CREATE_RULESET_VERSION)); ASSERT_EQ(EINVAL, errno); ASSERT_EQ(-1, landlock_create_ruleset(NULL, sizeof(ruleset_attr), - LANDLOCK_CREATE_RULESET_VERSION)); + LANDLOCK_CREATE_RULESET_VERSION)); ASSERT_EQ(EINVAL, errno); - ASSERT_EQ(-1, landlock_create_ruleset(&ruleset_attr, - sizeof(ruleset_attr), - LANDLOCK_CREATE_RULESET_VERSION)); + ASSERT_EQ(-1, + landlock_create_ruleset(&ruleset_attr, sizeof(ruleset_attr), + LANDLOCK_CREATE_RULESET_VERSION)); ASSERT_EQ(EINVAL, errno); ASSERT_EQ(-1, landlock_create_ruleset(NULL, 0, - LANDLOCK_CREATE_RULESET_VERSION | 1 << 31)); + LANDLOCK_CREATE_RULESET_VERSION | + 1 << 31)); ASSERT_EQ(EINVAL, errno); } -TEST(inval_create_ruleset_flags) { +/* Tests ordering of syscall argument checks. */ +TEST(create_ruleset_checks_ordering) +{ const int last_flag = LANDLOCK_CREATE_RULESET_VERSION; const int invalid_flag = last_flag << 1; + int ruleset_fd; const struct landlock_ruleset_attr ruleset_attr = { .handled_access_fs = LANDLOCK_ACCESS_FS_READ_FILE, }; + /* Checks priority for invalid flags. */ ASSERT_EQ(-1, landlock_create_ruleset(NULL, 0, invalid_flag)); ASSERT_EQ(EINVAL, errno); @@ -102,44 +115,121 @@ TEST(inval_create_ruleset_flags) { ASSERT_EQ(EINVAL, errno); ASSERT_EQ(-1, landlock_create_ruleset(NULL, sizeof(ruleset_attr), - invalid_flag)); + invalid_flag)); + ASSERT_EQ(EINVAL, errno); + + ASSERT_EQ(-1, + landlock_create_ruleset(&ruleset_attr, sizeof(ruleset_attr), + invalid_flag)); ASSERT_EQ(EINVAL, errno); - ASSERT_EQ(-1, landlock_create_ruleset(&ruleset_attr, - sizeof(ruleset_attr), invalid_flag)); + /* Checks too big ruleset_attr size. */ + ASSERT_EQ(-1, landlock_create_ruleset(&ruleset_attr, -1, 0)); + ASSERT_EQ(E2BIG, errno); + + /* Checks too small ruleset_attr size. */ + ASSERT_EQ(-1, landlock_create_ruleset(&ruleset_attr, 0, 0)); + ASSERT_EQ(EINVAL, errno); + ASSERT_EQ(-1, landlock_create_ruleset(&ruleset_attr, 1, 0)); ASSERT_EQ(EINVAL, errno); + + /* Checks valid call. */ + ruleset_fd = + landlock_create_ruleset(&ruleset_attr, sizeof(ruleset_attr), 0); + ASSERT_LE(0, ruleset_fd); + ASSERT_EQ(0, close(ruleset_fd)); } -TEST(empty_path_beneath_attr) { +/* Tests ordering of syscall argument checks. */ +TEST(add_rule_checks_ordering) +{ const struct landlock_ruleset_attr ruleset_attr = { .handled_access_fs = LANDLOCK_ACCESS_FS_EXECUTE, }; - const int ruleset_fd = landlock_create_ruleset(&ruleset_attr, - sizeof(ruleset_attr), 0); + struct landlock_path_beneath_attr path_beneath_attr = { + .allowed_access = LANDLOCK_ACCESS_FS_EXECUTE, + .parent_fd = -1, + }; + const int ruleset_fd = + landlock_create_ruleset(&ruleset_attr, sizeof(ruleset_attr), 0); ASSERT_LE(0, ruleset_fd); - /* Similar to struct landlock_path_beneath_attr.parent_fd = 0 */ + /* Checks invalid flags. */ + ASSERT_EQ(-1, landlock_add_rule(-1, 0, NULL, 1)); + ASSERT_EQ(EINVAL, errno); + + /* Checks invalid ruleset FD. */ + ASSERT_EQ(-1, landlock_add_rule(-1, 0, NULL, 0)); + ASSERT_EQ(EBADF, errno); + + /* Checks invalid rule type. */ + ASSERT_EQ(-1, landlock_add_rule(ruleset_fd, 0, NULL, 0)); + ASSERT_EQ(EINVAL, errno); + + /* Checks invalid rule attr. */ ASSERT_EQ(-1, landlock_add_rule(ruleset_fd, LANDLOCK_RULE_PATH_BENEATH, - NULL, 0)); + NULL, 0)); ASSERT_EQ(EFAULT, errno); + + /* Checks invalid path_beneath.parent_fd. */ + ASSERT_EQ(-1, landlock_add_rule(ruleset_fd, LANDLOCK_RULE_PATH_BENEATH, + &path_beneath_attr, 0)); + ASSERT_EQ(EBADF, errno); + + /* Checks valid call. */ + path_beneath_attr.parent_fd = + open("/tmp", O_PATH | O_NOFOLLOW | O_DIRECTORY | O_CLOEXEC); + ASSERT_LE(0, path_beneath_attr.parent_fd); + ASSERT_EQ(0, landlock_add_rule(ruleset_fd, LANDLOCK_RULE_PATH_BENEATH, + &path_beneath_attr, 0)); + ASSERT_EQ(0, close(path_beneath_attr.parent_fd)); ASSERT_EQ(0, close(ruleset_fd)); } -TEST(inval_fd_enforce) { +/* Tests ordering of syscall argument and permission checks. */ +TEST(restrict_self_checks_ordering) +{ + const struct landlock_ruleset_attr ruleset_attr = { + .handled_access_fs = LANDLOCK_ACCESS_FS_EXECUTE, + }; + struct landlock_path_beneath_attr path_beneath_attr = { + .allowed_access = LANDLOCK_ACCESS_FS_EXECUTE, + .parent_fd = -1, + }; + const int ruleset_fd = + landlock_create_ruleset(&ruleset_attr, sizeof(ruleset_attr), 0); + + ASSERT_LE(0, ruleset_fd); + path_beneath_attr.parent_fd = + open("/tmp", O_PATH | O_NOFOLLOW | O_DIRECTORY | O_CLOEXEC); + ASSERT_LE(0, path_beneath_attr.parent_fd); + ASSERT_EQ(0, landlock_add_rule(ruleset_fd, LANDLOCK_RULE_PATH_BENEATH, + &path_beneath_attr, 0)); + ASSERT_EQ(0, close(path_beneath_attr.parent_fd)); + + /* Checks unprivileged enforcement without no_new_privs. */ + drop_caps(_metadata); + ASSERT_EQ(-1, landlock_restrict_self(-1, -1)); + ASSERT_EQ(EPERM, errno); + ASSERT_EQ(-1, landlock_restrict_self(-1, 0)); + ASSERT_EQ(EPERM, errno); + ASSERT_EQ(-1, landlock_restrict_self(ruleset_fd, 0)); + ASSERT_EQ(EPERM, errno); + ASSERT_EQ(0, prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0)); + /* Checks invalid flags. */ + ASSERT_EQ(-1, landlock_restrict_self(-1, -1)); + ASSERT_EQ(EINVAL, errno); + + /* Checks invalid ruleset FD. */ ASSERT_EQ(-1, landlock_restrict_self(-1, 0)); ASSERT_EQ(EBADF, errno); -} - -TEST(unpriv_enforce_without_no_new_privs) { - int err; - drop_caps(_metadata); - err = landlock_restrict_self(-1, 0); - ASSERT_EQ(EPERM, errno); - ASSERT_EQ(err, -1); + /* Checks valid call. */ + ASSERT_EQ(0, landlock_restrict_self(ruleset_fd, 0)); + ASSERT_EQ(0, close(ruleset_fd)); } TEST(ruleset_fd_io) @@ -151,8 +241,8 @@ TEST(ruleset_fd_io) char buf; drop_caps(_metadata); - ruleset_fd = landlock_create_ruleset(&ruleset_attr, - sizeof(ruleset_attr), 0); + ruleset_fd = + landlock_create_ruleset(&ruleset_attr, sizeof(ruleset_attr), 0); ASSERT_LE(0, ruleset_fd); ASSERT_EQ(-1, write(ruleset_fd, ".", 1)); @@ -197,14 +287,15 @@ TEST(ruleset_fd_transfer) drop_caps(_metadata); /* Creates a test ruleset with a simple rule. */ - ruleset_fd_tx = landlock_create_ruleset(&ruleset_attr, - sizeof(ruleset_attr), 0); + ruleset_fd_tx = + landlock_create_ruleset(&ruleset_attr, sizeof(ruleset_attr), 0); ASSERT_LE(0, ruleset_fd_tx); - path_beneath_attr.parent_fd = open("/tmp", O_PATH | O_NOFOLLOW | - O_DIRECTORY | O_CLOEXEC); + path_beneath_attr.parent_fd = + open("/tmp", O_PATH | O_NOFOLLOW | O_DIRECTORY | O_CLOEXEC); ASSERT_LE(0, path_beneath_attr.parent_fd); - ASSERT_EQ(0, landlock_add_rule(ruleset_fd_tx, LANDLOCK_RULE_PATH_BENEATH, - &path_beneath_attr, 0)); + ASSERT_EQ(0, + landlock_add_rule(ruleset_fd_tx, LANDLOCK_RULE_PATH_BENEATH, + &path_beneath_attr, 0)); ASSERT_EQ(0, close(path_beneath_attr.parent_fd)); cmsg = CMSG_FIRSTHDR(&msg); @@ -215,7 +306,8 @@ TEST(ruleset_fd_transfer) memcpy(CMSG_DATA(cmsg), &ruleset_fd_tx, sizeof(ruleset_fd_tx)); /* Sends the ruleset FD over a socketpair and then close it. */ - ASSERT_EQ(0, socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, socket_fds)); + ASSERT_EQ(0, socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, + socket_fds)); ASSERT_EQ(sizeof(data_tx), sendmsg(socket_fds[0], &msg, 0)); ASSERT_EQ(0, close(socket_fds[0])); ASSERT_EQ(0, close(ruleset_fd_tx)); @@ -226,7 +318,8 @@ TEST(ruleset_fd_transfer) int ruleset_fd_rx; *(char *)msg.msg_iov->iov_base = '\0'; - ASSERT_EQ(sizeof(data_tx), recvmsg(socket_fds[1], &msg, MSG_CMSG_CLOEXEC)); + ASSERT_EQ(sizeof(data_tx), + recvmsg(socket_fds[1], &msg, MSG_CMSG_CLOEXEC)); ASSERT_EQ('.', *(char *)msg.msg_iov->iov_base); ASSERT_EQ(0, close(socket_fds[1])); cmsg = CMSG_FIRSTHDR(&msg); diff --git a/tools/testing/selftests/landlock/common.h b/tools/testing/selftests/landlock/common.h index 183b7e8e1b95..7ba18eb23783 100644 --- a/tools/testing/selftests/landlock/common.h +++ b/tools/testing/selftests/landlock/common.h @@ -25,6 +25,7 @@ * this to be possible, we must not call abort() but instead exit smoothly * (hence the step print). */ +/* clang-format off */ #define TEST_F_FORK(fixture_name, test_name) \ static void fixture_name##_##test_name##_child( \ struct __test_metadata *_metadata, \ @@ -71,11 +72,12 @@ FIXTURE_DATA(fixture_name) __attribute__((unused)) *self, \ const FIXTURE_VARIANT(fixture_name) \ __attribute__((unused)) *variant) +/* clang-format on */ #ifndef landlock_create_ruleset -static inline int landlock_create_ruleset( - const struct landlock_ruleset_attr *const attr, - const size_t size, const __u32 flags) +static inline int +landlock_create_ruleset(const struct landlock_ruleset_attr *const attr, + const size_t size, const __u32 flags) { return syscall(__NR_landlock_create_ruleset, attr, size, flags); } @@ -83,17 +85,18 @@ static inline int landlock_create_ruleset( #ifndef landlock_add_rule static inline int landlock_add_rule(const int ruleset_fd, - const enum landlock_rule_type rule_type, - const void *const rule_attr, const __u32 flags) + const enum landlock_rule_type rule_type, + const void *const rule_attr, + const __u32 flags) { - return syscall(__NR_landlock_add_rule, ruleset_fd, rule_type, - rule_attr, flags); + return syscall(__NR_landlock_add_rule, ruleset_fd, rule_type, rule_attr, + flags); } #endif #ifndef landlock_restrict_self static inline int landlock_restrict_self(const int ruleset_fd, - const __u32 flags) + const __u32 flags) { return syscall(__NR_landlock_restrict_self, ruleset_fd, flags); } @@ -111,69 +114,76 @@ static void _init_caps(struct __test_metadata *const _metadata, bool drop_all) }; cap_p = cap_get_proc(); - EXPECT_NE(NULL, cap_p) { + EXPECT_NE(NULL, cap_p) + { TH_LOG("Failed to cap_get_proc: %s", strerror(errno)); } - EXPECT_NE(-1, cap_clear(cap_p)) { + EXPECT_NE(-1, cap_clear(cap_p)) + { TH_LOG("Failed to cap_clear: %s", strerror(errno)); } if (!drop_all) { EXPECT_NE(-1, cap_set_flag(cap_p, CAP_PERMITTED, - ARRAY_SIZE(caps), caps, CAP_SET)) { + ARRAY_SIZE(caps), caps, CAP_SET)) + { TH_LOG("Failed to cap_set_flag: %s", strerror(errno)); } } - EXPECT_NE(-1, cap_set_proc(cap_p)) { + EXPECT_NE(-1, cap_set_proc(cap_p)) + { TH_LOG("Failed to cap_set_proc: %s", strerror(errno)); } - EXPECT_NE(-1, cap_free(cap_p)) { + EXPECT_NE(-1, cap_free(cap_p)) + { TH_LOG("Failed to cap_free: %s", strerror(errno)); } } /* We cannot put such helpers in a library because of kselftest_harness.h . */ -__attribute__((__unused__)) -static void disable_caps(struct __test_metadata *const _metadata) +__attribute__((__unused__)) static void +disable_caps(struct __test_metadata *const _metadata) { _init_caps(_metadata, false); } -__attribute__((__unused__)) -static void drop_caps(struct __test_metadata *const _metadata) +__attribute__((__unused__)) static void +drop_caps(struct __test_metadata *const _metadata) { _init_caps(_metadata, true); } static void _effective_cap(struct __test_metadata *const _metadata, - const cap_value_t caps, const cap_flag_value_t value) + const cap_value_t caps, const cap_flag_value_t value) { cap_t cap_p; cap_p = cap_get_proc(); - EXPECT_NE(NULL, cap_p) { + EXPECT_NE(NULL, cap_p) + { TH_LOG("Failed to cap_get_proc: %s", strerror(errno)); } - EXPECT_NE(-1, cap_set_flag(cap_p, CAP_EFFECTIVE, 1, &caps, value)) { + EXPECT_NE(-1, cap_set_flag(cap_p, CAP_EFFECTIVE, 1, &caps, value)) + { TH_LOG("Failed to cap_set_flag: %s", strerror(errno)); } - EXPECT_NE(-1, cap_set_proc(cap_p)) { + EXPECT_NE(-1, cap_set_proc(cap_p)) + { TH_LOG("Failed to cap_set_proc: %s", strerror(errno)); } - EXPECT_NE(-1, cap_free(cap_p)) { + EXPECT_NE(-1, cap_free(cap_p)) + { TH_LOG("Failed to cap_free: %s", strerror(errno)); } } -__attribute__((__unused__)) -static void set_cap(struct __test_metadata *const _metadata, - const cap_value_t caps) +__attribute__((__unused__)) static void +set_cap(struct __test_metadata *const _metadata, const cap_value_t caps) { _effective_cap(_metadata, caps, CAP_SET); } -__attribute__((__unused__)) -static void clear_cap(struct __test_metadata *const _metadata, - const cap_value_t caps) +__attribute__((__unused__)) static void +clear_cap(struct __test_metadata *const _metadata, const cap_value_t caps) { _effective_cap(_metadata, caps, CAP_CLEAR); } diff --git a/tools/testing/selftests/landlock/fs_test.c b/tools/testing/selftests/landlock/fs_test.c index 10c9a1e4ebd9..21a2ce8fa739 100644 --- a/tools/testing/selftests/landlock/fs_test.c +++ b/tools/testing/selftests/landlock/fs_test.c @@ -22,8 +22,21 @@ #include "common.h" -#define TMP_DIR "tmp" -#define BINARY_PATH "./true" +#ifndef renameat2 +int renameat2(int olddirfd, const char *oldpath, int newdirfd, + const char *newpath, unsigned int flags) +{ + return syscall(__NR_renameat2, olddirfd, oldpath, newdirfd, newpath, + flags); +} +#endif + +#ifndef RENAME_EXCHANGE +#define RENAME_EXCHANGE (1 << 1) +#endif + +#define TMP_DIR "tmp" +#define BINARY_PATH "./true" /* Paths (sibling number and depth) */ static const char dir_s1d1[] = TMP_DIR "/s1d1"; @@ -75,7 +88,7 @@ static const char dir_s3d3[] = TMP_DIR "/s3d1/s3d2/s3d3"; */ static void mkdir_parents(struct __test_metadata *const _metadata, - const char *const path) + const char *const path) { char *walker; const char *parent; @@ -90,9 +103,10 @@ static void mkdir_parents(struct __test_metadata *const _metadata, continue; walker[i] = '\0'; err = mkdir(parent, 0700); - ASSERT_FALSE(err && errno != EEXIST) { - TH_LOG("Failed to create directory \"%s\": %s", - parent, strerror(errno)); + ASSERT_FALSE(err && errno != EEXIST) + { + TH_LOG("Failed to create directory \"%s\": %s", parent, + strerror(errno)); } walker[i] = '/'; } @@ -100,22 +114,24 @@ static void mkdir_parents(struct __test_metadata *const _metadata, } static void create_directory(struct __test_metadata *const _metadata, - const char *const path) + const char *const path) { mkdir_parents(_metadata, path); - ASSERT_EQ(0, mkdir(path, 0700)) { + ASSERT_EQ(0, mkdir(path, 0700)) + { TH_LOG("Failed to create directory \"%s\": %s", path, - strerror(errno)); + strerror(errno)); } } static void create_file(struct __test_metadata *const _metadata, - const char *const path) + const char *const path) { mkdir_parents(_metadata, path); - ASSERT_EQ(0, mknod(path, S_IFREG | 0700, 0)) { + ASSERT_EQ(0, mknod(path, S_IFREG | 0700, 0)) + { TH_LOG("Failed to create file \"%s\": %s", path, - strerror(errno)); + strerror(errno)); } } @@ -130,7 +146,7 @@ static int remove_path(const char *const path) goto out; } if (unlink(path) && rmdir(path)) { - if (errno != ENOENT) + if (errno != ENOENT && errno != ENOTDIR) err = errno; goto out; } @@ -221,8 +237,9 @@ static void remove_layout1(struct __test_metadata *const _metadata) EXPECT_EQ(0, remove_path(dir_s3d2)); } -FIXTURE(layout1) { -}; +/* clang-format off */ +FIXTURE(layout1) {}; +/* clang-format on */ FIXTURE_SETUP(layout1) { @@ -242,7 +259,8 @@ FIXTURE_TEARDOWN(layout1) * This helper enables to use the ASSERT_* macros and print the line number * pointing to the test caller. */ -static int test_open_rel(const int dirfd, const char *const path, const int flags) +static int test_open_rel(const int dirfd, const char *const path, + const int flags) { int fd; @@ -291,23 +309,23 @@ TEST_F_FORK(layout1, inval) { struct landlock_path_beneath_attr path_beneath = { .allowed_access = LANDLOCK_ACCESS_FS_READ_FILE | - LANDLOCK_ACCESS_FS_WRITE_FILE, + LANDLOCK_ACCESS_FS_WRITE_FILE, .parent_fd = -1, }; struct landlock_ruleset_attr ruleset_attr = { .handled_access_fs = LANDLOCK_ACCESS_FS_READ_FILE | - LANDLOCK_ACCESS_FS_WRITE_FILE, + LANDLOCK_ACCESS_FS_WRITE_FILE, }; int ruleset_fd; - path_beneath.parent_fd = open(dir_s1d2, O_PATH | O_DIRECTORY | - O_CLOEXEC); + path_beneath.parent_fd = + open(dir_s1d2, O_PATH | O_DIRECTORY | O_CLOEXEC); ASSERT_LE(0, path_beneath.parent_fd); ruleset_fd = open(dir_s1d1, O_PATH | O_DIRECTORY | O_CLOEXEC); ASSERT_LE(0, ruleset_fd); ASSERT_EQ(-1, landlock_add_rule(ruleset_fd, LANDLOCK_RULE_PATH_BENEATH, - &path_beneath, 0)); + &path_beneath, 0)); /* Returns EBADF because ruleset_fd is not a landlock-ruleset FD. */ ASSERT_EQ(EBADF, errno); ASSERT_EQ(0, close(ruleset_fd)); @@ -315,55 +333,55 @@ TEST_F_FORK(layout1, inval) ruleset_fd = open(dir_s1d1, O_DIRECTORY | O_CLOEXEC); ASSERT_LE(0, ruleset_fd); ASSERT_EQ(-1, landlock_add_rule(ruleset_fd, LANDLOCK_RULE_PATH_BENEATH, - &path_beneath, 0)); + &path_beneath, 0)); /* Returns EBADFD because ruleset_fd is not a valid ruleset. */ ASSERT_EQ(EBADFD, errno); ASSERT_EQ(0, close(ruleset_fd)); /* Gets a real ruleset. */ - ruleset_fd = landlock_create_ruleset(&ruleset_attr, - sizeof(ruleset_attr), 0); + ruleset_fd = + landlock_create_ruleset(&ruleset_attr, sizeof(ruleset_attr), 0); ASSERT_LE(0, ruleset_fd); ASSERT_EQ(0, landlock_add_rule(ruleset_fd, LANDLOCK_RULE_PATH_BENEATH, - &path_beneath, 0)); + &path_beneath, 0)); ASSERT_EQ(0, close(path_beneath.parent_fd)); /* Tests without O_PATH. */ path_beneath.parent_fd = open(dir_s1d2, O_DIRECTORY | O_CLOEXEC); ASSERT_LE(0, path_beneath.parent_fd); ASSERT_EQ(0, landlock_add_rule(ruleset_fd, LANDLOCK_RULE_PATH_BENEATH, - &path_beneath, 0)); + &path_beneath, 0)); ASSERT_EQ(0, close(path_beneath.parent_fd)); /* Tests with a ruleset FD. */ path_beneath.parent_fd = ruleset_fd; ASSERT_EQ(-1, landlock_add_rule(ruleset_fd, LANDLOCK_RULE_PATH_BENEATH, - &path_beneath, 0)); + &path_beneath, 0)); ASSERT_EQ(EBADFD, errno); /* Checks unhandled allowed_access. */ - path_beneath.parent_fd = open(dir_s1d2, O_PATH | O_DIRECTORY | - O_CLOEXEC); + path_beneath.parent_fd = + open(dir_s1d2, O_PATH | O_DIRECTORY | O_CLOEXEC); ASSERT_LE(0, path_beneath.parent_fd); /* Test with legitimate values. */ path_beneath.allowed_access |= LANDLOCK_ACCESS_FS_EXECUTE; ASSERT_EQ(-1, landlock_add_rule(ruleset_fd, LANDLOCK_RULE_PATH_BENEATH, - &path_beneath, 0)); + &path_beneath, 0)); ASSERT_EQ(EINVAL, errno); path_beneath.allowed_access &= ~LANDLOCK_ACCESS_FS_EXECUTE; /* Test with unknown (64-bits) value. */ path_beneath.allowed_access |= (1ULL << 60); ASSERT_EQ(-1, landlock_add_rule(ruleset_fd, LANDLOCK_RULE_PATH_BENEATH, - &path_beneath, 0)); + &path_beneath, 0)); ASSERT_EQ(EINVAL, errno); path_beneath.allowed_access &= ~(1ULL << 60); /* Test with no access. */ path_beneath.allowed_access = 0; ASSERT_EQ(-1, landlock_add_rule(ruleset_fd, LANDLOCK_RULE_PATH_BENEATH, - &path_beneath, 0)); + &path_beneath, 0)); ASSERT_EQ(ENOMSG, errno); path_beneath.allowed_access &= ~(1ULL << 60); @@ -376,12 +394,14 @@ TEST_F_FORK(layout1, inval) ASSERT_EQ(0, close(ruleset_fd)); } +/* clang-format off */ + #define ACCESS_FILE ( \ LANDLOCK_ACCESS_FS_EXECUTE | \ LANDLOCK_ACCESS_FS_WRITE_FILE | \ LANDLOCK_ACCESS_FS_READ_FILE) -#define ACCESS_LAST LANDLOCK_ACCESS_FS_MAKE_SYM +#define ACCESS_LAST LANDLOCK_ACCESS_FS_REFER #define ACCESS_ALL ( \ ACCESS_FILE | \ @@ -394,55 +414,90 @@ TEST_F_FORK(layout1, inval) LANDLOCK_ACCESS_FS_MAKE_SOCK | \ LANDLOCK_ACCESS_FS_MAKE_FIFO | \ LANDLOCK_ACCESS_FS_MAKE_BLOCK | \ + LANDLOCK_ACCESS_FS_MAKE_SYM | \ ACCESS_LAST) -TEST_F_FORK(layout1, file_access_rights) +/* clang-format on */ + +TEST_F_FORK(layout1, file_and_dir_access_rights) { __u64 access; int err; - struct landlock_path_beneath_attr path_beneath = {}; + struct landlock_path_beneath_attr path_beneath_file = {}, + path_beneath_dir = {}; struct landlock_ruleset_attr ruleset_attr = { .handled_access_fs = ACCESS_ALL, }; - const int ruleset_fd = landlock_create_ruleset(&ruleset_attr, - sizeof(ruleset_attr), 0); + const int ruleset_fd = + landlock_create_ruleset(&ruleset_attr, sizeof(ruleset_attr), 0); ASSERT_LE(0, ruleset_fd); /* Tests access rights for files. */ - path_beneath.parent_fd = open(file1_s1d2, O_PATH | O_CLOEXEC); - ASSERT_LE(0, path_beneath.parent_fd); + path_beneath_file.parent_fd = open(file1_s1d2, O_PATH | O_CLOEXEC); + ASSERT_LE(0, path_beneath_file.parent_fd); + + /* Tests access rights for directories. */ + path_beneath_dir.parent_fd = + open(dir_s1d2, O_PATH | O_DIRECTORY | O_CLOEXEC); + ASSERT_LE(0, path_beneath_dir.parent_fd); + for (access = 1; access <= ACCESS_LAST; access <<= 1) { - path_beneath.allowed_access = access; + path_beneath_dir.allowed_access = access; + ASSERT_EQ(0, landlock_add_rule(ruleset_fd, + LANDLOCK_RULE_PATH_BENEATH, + &path_beneath_dir, 0)); + + path_beneath_file.allowed_access = access; err = landlock_add_rule(ruleset_fd, LANDLOCK_RULE_PATH_BENEATH, - &path_beneath, 0); - if ((access | ACCESS_FILE) == ACCESS_FILE) { + &path_beneath_file, 0); + if (access & ACCESS_FILE) { ASSERT_EQ(0, err); } else { ASSERT_EQ(-1, err); ASSERT_EQ(EINVAL, errno); } } - ASSERT_EQ(0, close(path_beneath.parent_fd)); + ASSERT_EQ(0, close(path_beneath_file.parent_fd)); + ASSERT_EQ(0, close(path_beneath_dir.parent_fd)); + ASSERT_EQ(0, close(ruleset_fd)); +} + +TEST_F_FORK(layout1, unknown_access_rights) +{ + __u64 access_mask; + + for (access_mask = 1ULL << 63; access_mask != ACCESS_LAST; + access_mask >>= 1) { + struct landlock_ruleset_attr ruleset_attr = { + .handled_access_fs = access_mask, + }; + + ASSERT_EQ(-1, landlock_create_ruleset(&ruleset_attr, + sizeof(ruleset_attr), 0)); + ASSERT_EQ(EINVAL, errno); + } } static void add_path_beneath(struct __test_metadata *const _metadata, - const int ruleset_fd, const __u64 allowed_access, - const char *const path) + const int ruleset_fd, const __u64 allowed_access, + const char *const path) { struct landlock_path_beneath_attr path_beneath = { .allowed_access = allowed_access, }; path_beneath.parent_fd = open(path, O_PATH | O_CLOEXEC); - ASSERT_LE(0, path_beneath.parent_fd) { + ASSERT_LE(0, path_beneath.parent_fd) + { TH_LOG("Failed to open directory \"%s\": %s", path, - strerror(errno)); + strerror(errno)); } ASSERT_EQ(0, landlock_add_rule(ruleset_fd, LANDLOCK_RULE_PATH_BENEATH, - &path_beneath, 0)) { + &path_beneath, 0)) + { TH_LOG("Failed to update the ruleset with \"%s\": %s", path, - strerror(errno)); + strerror(errno)); } ASSERT_EQ(0, close(path_beneath.parent_fd)); } @@ -452,6 +507,8 @@ struct rule { __u64 access; }; +/* clang-format off */ + #define ACCESS_RO ( \ LANDLOCK_ACCESS_FS_READ_FILE | \ LANDLOCK_ACCESS_FS_READ_DIR) @@ -460,39 +517,46 @@ struct rule { ACCESS_RO | \ LANDLOCK_ACCESS_FS_WRITE_FILE) +/* clang-format on */ + static int create_ruleset(struct __test_metadata *const _metadata, - const __u64 handled_access_fs, const struct rule rules[]) + const __u64 handled_access_fs, + const struct rule rules[]) { int ruleset_fd, i; struct landlock_ruleset_attr ruleset_attr = { .handled_access_fs = handled_access_fs, }; - ASSERT_NE(NULL, rules) { + ASSERT_NE(NULL, rules) + { TH_LOG("No rule list"); } - ASSERT_NE(NULL, rules[0].path) { + ASSERT_NE(NULL, rules[0].path) + { TH_LOG("Empty rule list"); } - ruleset_fd = landlock_create_ruleset(&ruleset_attr, - sizeof(ruleset_attr), 0); - ASSERT_LE(0, ruleset_fd) { + ruleset_fd = + landlock_create_ruleset(&ruleset_attr, sizeof(ruleset_attr), 0); + ASSERT_LE(0, ruleset_fd) + { TH_LOG("Failed to create a ruleset: %s", strerror(errno)); } for (i = 0; rules[i].path; i++) { add_path_beneath(_metadata, ruleset_fd, rules[i].access, - rules[i].path); + rules[i].path); } return ruleset_fd; } static void enforce_ruleset(struct __test_metadata *const _metadata, - const int ruleset_fd) + const int ruleset_fd) { ASSERT_EQ(0, prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0)); - ASSERT_EQ(0, landlock_restrict_self(ruleset_fd, 0)) { + ASSERT_EQ(0, landlock_restrict_self(ruleset_fd, 0)) + { TH_LOG("Failed to enforce ruleset: %s", strerror(errno)); } } @@ -503,13 +567,14 @@ TEST_F_FORK(layout1, proc_nsfs) { .path = "/dev/null", .access = LANDLOCK_ACCESS_FS_READ_FILE | - LANDLOCK_ACCESS_FS_WRITE_FILE, + LANDLOCK_ACCESS_FS_WRITE_FILE, }, - {} + {}, }; struct landlock_path_beneath_attr path_beneath; - const int ruleset_fd = create_ruleset(_metadata, rules[0].access | - LANDLOCK_ACCESS_FS_READ_DIR, rules); + const int ruleset_fd = create_ruleset( + _metadata, rules[0].access | LANDLOCK_ACCESS_FS_READ_DIR, + rules); ASSERT_LE(0, ruleset_fd); ASSERT_EQ(0, test_open("/proc/self/ns/mnt", O_RDONLY)); @@ -536,22 +601,23 @@ TEST_F_FORK(layout1, proc_nsfs) * references to a ruleset. */ path_beneath.allowed_access = LANDLOCK_ACCESS_FS_READ_FILE | - LANDLOCK_ACCESS_FS_WRITE_FILE, + LANDLOCK_ACCESS_FS_WRITE_FILE, path_beneath.parent_fd = open("/proc/self/ns/mnt", O_PATH | O_CLOEXEC); ASSERT_LE(0, path_beneath.parent_fd); ASSERT_EQ(-1, landlock_add_rule(ruleset_fd, LANDLOCK_RULE_PATH_BENEATH, - &path_beneath, 0)); + &path_beneath, 0)); ASSERT_EQ(EBADFD, errno); ASSERT_EQ(0, close(path_beneath.parent_fd)); } -TEST_F_FORK(layout1, unpriv) { +TEST_F_FORK(layout1, unpriv) +{ const struct rule rules[] = { { .path = dir_s1d2, .access = ACCESS_RO, }, - {} + {}, }; int ruleset_fd; @@ -577,9 +643,9 @@ TEST_F_FORK(layout1, effective_access) { .path = file1_s2d2, .access = LANDLOCK_ACCESS_FS_READ_FILE | - LANDLOCK_ACCESS_FS_WRITE_FILE, + LANDLOCK_ACCESS_FS_WRITE_FILE, }, - {} + {}, }; const int ruleset_fd = create_ruleset(_metadata, ACCESS_RW, rules); char buf; @@ -589,17 +655,23 @@ TEST_F_FORK(layout1, effective_access) enforce_ruleset(_metadata, ruleset_fd); ASSERT_EQ(0, close(ruleset_fd)); - /* Tests on a directory. */ + /* Tests on a directory (with or without O_PATH). */ ASSERT_EQ(EACCES, test_open("/", O_RDONLY)); + ASSERT_EQ(0, test_open("/", O_RDONLY | O_PATH)); ASSERT_EQ(EACCES, test_open(dir_s1d1, O_RDONLY)); + ASSERT_EQ(0, test_open(dir_s1d1, O_RDONLY | O_PATH)); ASSERT_EQ(EACCES, test_open(file1_s1d1, O_RDONLY)); + ASSERT_EQ(0, test_open(file1_s1d1, O_RDONLY | O_PATH)); + ASSERT_EQ(0, test_open(dir_s1d2, O_RDONLY)); ASSERT_EQ(0, test_open(file1_s1d2, O_RDONLY)); ASSERT_EQ(0, test_open(dir_s1d3, O_RDONLY)); ASSERT_EQ(0, test_open(file1_s1d3, O_RDONLY)); - /* Tests on a file. */ + /* Tests on a file (with or without O_PATH). */ ASSERT_EQ(EACCES, test_open(dir_s2d2, O_RDONLY)); + ASSERT_EQ(0, test_open(dir_s2d2, O_RDONLY | O_PATH)); + ASSERT_EQ(0, test_open(file1_s2d2, O_RDONLY)); /* Checks effective read and write actions. */ @@ -626,7 +698,7 @@ TEST_F_FORK(layout1, unhandled_access) .path = dir_s1d2, .access = ACCESS_RO, }, - {} + {}, }; /* Here, we only handle read accesses, not write accesses. */ const int ruleset_fd = create_ruleset(_metadata, ACCESS_RO, rules); @@ -653,14 +725,14 @@ TEST_F_FORK(layout1, ruleset_overlap) { .path = dir_s1d2, .access = LANDLOCK_ACCESS_FS_READ_FILE | - LANDLOCK_ACCESS_FS_WRITE_FILE, + LANDLOCK_ACCESS_FS_WRITE_FILE, }, { .path = dir_s1d2, .access = LANDLOCK_ACCESS_FS_READ_FILE | - LANDLOCK_ACCESS_FS_READ_DIR, + LANDLOCK_ACCESS_FS_READ_DIR, }, - {} + {}, }; const int ruleset_fd = create_ruleset(_metadata, ACCESS_RW, rules); @@ -687,6 +759,113 @@ TEST_F_FORK(layout1, ruleset_overlap) ASSERT_EQ(0, test_open(dir_s1d3, O_RDONLY | O_DIRECTORY)); } +TEST_F_FORK(layout1, layer_rule_unions) +{ + const struct rule layer1[] = { + { + .path = dir_s1d2, + .access = LANDLOCK_ACCESS_FS_READ_FILE, + }, + /* dir_s1d3 should allow READ_FILE and WRITE_FILE (O_RDWR). */ + { + .path = dir_s1d3, + .access = LANDLOCK_ACCESS_FS_WRITE_FILE, + }, + {}, + }; + const struct rule layer2[] = { + /* Doesn't change anything from layer1. */ + { + .path = dir_s1d2, + .access = LANDLOCK_ACCESS_FS_READ_FILE | + LANDLOCK_ACCESS_FS_WRITE_FILE, + }, + {}, + }; + const struct rule layer3[] = { + /* Only allows write (but not read) to dir_s1d3. */ + { + .path = dir_s1d2, + .access = LANDLOCK_ACCESS_FS_WRITE_FILE, + }, + {}, + }; + int ruleset_fd = create_ruleset(_metadata, ACCESS_RW, layer1); + + ASSERT_LE(0, ruleset_fd); + enforce_ruleset(_metadata, ruleset_fd); + ASSERT_EQ(0, close(ruleset_fd)); + + /* Checks s1d1 hierarchy with layer1. */ + ASSERT_EQ(EACCES, test_open(file1_s1d1, O_RDONLY)); + ASSERT_EQ(EACCES, test_open(file1_s1d1, O_WRONLY)); + ASSERT_EQ(EACCES, test_open(file1_s1d1, O_RDWR)); + ASSERT_EQ(EACCES, test_open(dir_s1d1, O_RDONLY | O_DIRECTORY)); + + /* Checks s1d2 hierarchy with layer1. */ + ASSERT_EQ(0, test_open(file1_s1d2, O_RDONLY)); + ASSERT_EQ(EACCES, test_open(file1_s1d2, O_WRONLY)); + ASSERT_EQ(EACCES, test_open(file1_s1d2, O_RDWR)); + ASSERT_EQ(EACCES, test_open(dir_s1d1, O_RDONLY | O_DIRECTORY)); + + /* Checks s1d3 hierarchy with layer1. */ + ASSERT_EQ(0, test_open(file1_s1d3, O_RDONLY)); + ASSERT_EQ(0, test_open(file1_s1d3, O_WRONLY)); + /* dir_s1d3 should allow READ_FILE and WRITE_FILE (O_RDWR). */ + ASSERT_EQ(0, test_open(file1_s1d3, O_RDWR)); + ASSERT_EQ(EACCES, test_open(dir_s1d1, O_RDONLY | O_DIRECTORY)); + + /* Doesn't change anything from layer1. */ + ruleset_fd = create_ruleset(_metadata, ACCESS_RW, layer2); + ASSERT_LE(0, ruleset_fd); + enforce_ruleset(_metadata, ruleset_fd); + ASSERT_EQ(0, close(ruleset_fd)); + + /* Checks s1d1 hierarchy with layer2. */ + ASSERT_EQ(EACCES, test_open(file1_s1d1, O_RDONLY)); + ASSERT_EQ(EACCES, test_open(file1_s1d1, O_WRONLY)); + ASSERT_EQ(EACCES, test_open(file1_s1d1, O_RDWR)); + ASSERT_EQ(EACCES, test_open(dir_s1d1, O_RDONLY | O_DIRECTORY)); + + /* Checks s1d2 hierarchy with layer2. */ + ASSERT_EQ(0, test_open(file1_s1d2, O_RDONLY)); + ASSERT_EQ(EACCES, test_open(file1_s1d2, O_WRONLY)); + ASSERT_EQ(EACCES, test_open(file1_s1d2, O_RDWR)); + ASSERT_EQ(EACCES, test_open(dir_s1d1, O_RDONLY | O_DIRECTORY)); + + /* Checks s1d3 hierarchy with layer2. */ + ASSERT_EQ(0, test_open(file1_s1d3, O_RDONLY)); + ASSERT_EQ(0, test_open(file1_s1d3, O_WRONLY)); + /* dir_s1d3 should allow READ_FILE and WRITE_FILE (O_RDWR). */ + ASSERT_EQ(0, test_open(file1_s1d3, O_RDWR)); + ASSERT_EQ(EACCES, test_open(dir_s1d1, O_RDONLY | O_DIRECTORY)); + + /* Only allows write (but not read) to dir_s1d3. */ + ruleset_fd = create_ruleset(_metadata, ACCESS_RW, layer3); + ASSERT_LE(0, ruleset_fd); + enforce_ruleset(_metadata, ruleset_fd); + ASSERT_EQ(0, close(ruleset_fd)); + + /* Checks s1d1 hierarchy with layer3. */ + ASSERT_EQ(EACCES, test_open(file1_s1d1, O_RDONLY)); + ASSERT_EQ(EACCES, test_open(file1_s1d1, O_WRONLY)); + ASSERT_EQ(EACCES, test_open(file1_s1d1, O_RDWR)); + ASSERT_EQ(EACCES, test_open(dir_s1d1, O_RDONLY | O_DIRECTORY)); + + /* Checks s1d2 hierarchy with layer3. */ + ASSERT_EQ(EACCES, test_open(file1_s1d2, O_RDONLY)); + ASSERT_EQ(EACCES, test_open(file1_s1d2, O_WRONLY)); + ASSERT_EQ(EACCES, test_open(file1_s1d2, O_RDWR)); + ASSERT_EQ(EACCES, test_open(dir_s1d1, O_RDONLY | O_DIRECTORY)); + + /* Checks s1d3 hierarchy with layer3. */ + ASSERT_EQ(EACCES, test_open(file1_s1d3, O_RDONLY)); + ASSERT_EQ(0, test_open(file1_s1d3, O_WRONLY)); + /* dir_s1d3 should now deny READ_FILE and WRITE_FILE (O_RDWR). */ + ASSERT_EQ(EACCES, test_open(file1_s1d3, O_RDWR)); + ASSERT_EQ(EACCES, test_open(dir_s1d1, O_RDONLY | O_DIRECTORY)); +} + TEST_F_FORK(layout1, non_overlapping_accesses) { const struct rule layer1[] = { @@ -694,22 +873,22 @@ TEST_F_FORK(layout1, non_overlapping_accesses) .path = dir_s1d2, .access = LANDLOCK_ACCESS_FS_MAKE_REG, }, - {} + {}, }; const struct rule layer2[] = { { .path = dir_s1d3, .access = LANDLOCK_ACCESS_FS_REMOVE_FILE, }, - {} + {}, }; int ruleset_fd; ASSERT_EQ(0, unlink(file1_s1d1)); ASSERT_EQ(0, unlink(file1_s1d2)); - ruleset_fd = create_ruleset(_metadata, LANDLOCK_ACCESS_FS_MAKE_REG, - layer1); + ruleset_fd = + create_ruleset(_metadata, LANDLOCK_ACCESS_FS_MAKE_REG, layer1); ASSERT_LE(0, ruleset_fd); enforce_ruleset(_metadata, ruleset_fd); ASSERT_EQ(0, close(ruleset_fd)); @@ -720,7 +899,7 @@ TEST_F_FORK(layout1, non_overlapping_accesses) ASSERT_EQ(0, unlink(file1_s1d2)); ruleset_fd = create_ruleset(_metadata, LANDLOCK_ACCESS_FS_REMOVE_FILE, - layer2); + layer2); ASSERT_LE(0, ruleset_fd); enforce_ruleset(_metadata, ruleset_fd); ASSERT_EQ(0, close(ruleset_fd)); @@ -758,7 +937,7 @@ TEST_F_FORK(layout1, interleaved_masked_accesses) .path = file1_s1d3, .access = LANDLOCK_ACCESS_FS_READ_FILE, }, - {} + {}, }; /* First rule with write restrictions. */ const struct rule layer2_read_write[] = { @@ -766,14 +945,14 @@ TEST_F_FORK(layout1, interleaved_masked_accesses) { .path = dir_s1d3, .access = LANDLOCK_ACCESS_FS_READ_FILE | - LANDLOCK_ACCESS_FS_WRITE_FILE, + LANDLOCK_ACCESS_FS_WRITE_FILE, }, /* ...but also denies read access via its grandparent directory. */ { .path = dir_s1d2, .access = LANDLOCK_ACCESS_FS_WRITE_FILE, }, - {} + {}, }; const struct rule layer3_read[] = { /* Allows read access via its great-grandparent directory. */ @@ -781,7 +960,7 @@ TEST_F_FORK(layout1, interleaved_masked_accesses) .path = dir_s1d1, .access = LANDLOCK_ACCESS_FS_READ_FILE, }, - {} + {}, }; const struct rule layer4_read_write[] = { /* @@ -792,7 +971,7 @@ TEST_F_FORK(layout1, interleaved_masked_accesses) .path = dir_s1d2, .access = LANDLOCK_ACCESS_FS_READ_FILE, }, - {} + {}, }; const struct rule layer5_read[] = { /* @@ -803,7 +982,7 @@ TEST_F_FORK(layout1, interleaved_masked_accesses) .path = dir_s1d2, .access = LANDLOCK_ACCESS_FS_READ_FILE, }, - {} + {}, }; const struct rule layer6_execute[] = { /* @@ -814,7 +993,7 @@ TEST_F_FORK(layout1, interleaved_masked_accesses) .path = dir_s2d1, .access = LANDLOCK_ACCESS_FS_EXECUTE, }, - {} + {}, }; const struct rule layer7_read_write[] = { /* @@ -825,12 +1004,12 @@ TEST_F_FORK(layout1, interleaved_masked_accesses) .path = dir_s1d2, .access = LANDLOCK_ACCESS_FS_WRITE_FILE, }, - {} + {}, }; int ruleset_fd; ruleset_fd = create_ruleset(_metadata, LANDLOCK_ACCESS_FS_READ_FILE, - layer1_read); + layer1_read); ASSERT_LE(0, ruleset_fd); enforce_ruleset(_metadata, ruleset_fd); ASSERT_EQ(0, close(ruleset_fd)); @@ -840,8 +1019,10 @@ TEST_F_FORK(layout1, interleaved_masked_accesses) ASSERT_EQ(EACCES, test_open(file2_s1d3, O_RDONLY)); ASSERT_EQ(0, test_open(file2_s1d3, O_WRONLY)); - ruleset_fd = create_ruleset(_metadata, LANDLOCK_ACCESS_FS_READ_FILE | - LANDLOCK_ACCESS_FS_WRITE_FILE, layer2_read_write); + ruleset_fd = create_ruleset(_metadata, + LANDLOCK_ACCESS_FS_READ_FILE | + LANDLOCK_ACCESS_FS_WRITE_FILE, + layer2_read_write); ASSERT_LE(0, ruleset_fd); enforce_ruleset(_metadata, ruleset_fd); ASSERT_EQ(0, close(ruleset_fd)); @@ -852,7 +1033,7 @@ TEST_F_FORK(layout1, interleaved_masked_accesses) ASSERT_EQ(0, test_open(file2_s1d3, O_WRONLY)); ruleset_fd = create_ruleset(_metadata, LANDLOCK_ACCESS_FS_READ_FILE, - layer3_read); + layer3_read); ASSERT_LE(0, ruleset_fd); enforce_ruleset(_metadata, ruleset_fd); ASSERT_EQ(0, close(ruleset_fd)); @@ -863,8 +1044,10 @@ TEST_F_FORK(layout1, interleaved_masked_accesses) ASSERT_EQ(0, test_open(file2_s1d3, O_WRONLY)); /* This time, denies write access for the file hierarchy. */ - ruleset_fd = create_ruleset(_metadata, LANDLOCK_ACCESS_FS_READ_FILE | - LANDLOCK_ACCESS_FS_WRITE_FILE, layer4_read_write); + ruleset_fd = create_ruleset(_metadata, + LANDLOCK_ACCESS_FS_READ_FILE | + LANDLOCK_ACCESS_FS_WRITE_FILE, + layer4_read_write); ASSERT_LE(0, ruleset_fd); enforce_ruleset(_metadata, ruleset_fd); ASSERT_EQ(0, close(ruleset_fd)); @@ -879,7 +1062,7 @@ TEST_F_FORK(layout1, interleaved_masked_accesses) ASSERT_EQ(EACCES, test_open(file2_s1d3, O_WRONLY)); ruleset_fd = create_ruleset(_metadata, LANDLOCK_ACCESS_FS_READ_FILE, - layer5_read); + layer5_read); ASSERT_LE(0, ruleset_fd); enforce_ruleset(_metadata, ruleset_fd); ASSERT_EQ(0, close(ruleset_fd)); @@ -891,7 +1074,7 @@ TEST_F_FORK(layout1, interleaved_masked_accesses) ASSERT_EQ(EACCES, test_open(file2_s1d3, O_RDONLY)); ruleset_fd = create_ruleset(_metadata, LANDLOCK_ACCESS_FS_EXECUTE, - layer6_execute); + layer6_execute); ASSERT_LE(0, ruleset_fd); enforce_ruleset(_metadata, ruleset_fd); ASSERT_EQ(0, close(ruleset_fd)); @@ -902,8 +1085,10 @@ TEST_F_FORK(layout1, interleaved_masked_accesses) ASSERT_EQ(EACCES, test_open(file2_s1d3, O_WRONLY)); ASSERT_EQ(EACCES, test_open(file2_s1d3, O_RDONLY)); - ruleset_fd = create_ruleset(_metadata, LANDLOCK_ACCESS_FS_READ_FILE | - LANDLOCK_ACCESS_FS_WRITE_FILE, layer7_read_write); + ruleset_fd = create_ruleset(_metadata, + LANDLOCK_ACCESS_FS_READ_FILE | + LANDLOCK_ACCESS_FS_WRITE_FILE, + layer7_read_write); ASSERT_LE(0, ruleset_fd); enforce_ruleset(_metadata, ruleset_fd); ASSERT_EQ(0, close(ruleset_fd)); @@ -921,9 +1106,9 @@ TEST_F_FORK(layout1, inherit_subset) { .path = dir_s1d2, .access = LANDLOCK_ACCESS_FS_READ_FILE | - LANDLOCK_ACCESS_FS_READ_DIR, + LANDLOCK_ACCESS_FS_READ_DIR, }, - {} + {}, }; const int ruleset_fd = create_ruleset(_metadata, ACCESS_RW, rules); @@ -949,7 +1134,7 @@ TEST_F_FORK(layout1, inherit_subset) * ANDed with the previous ones. */ add_path_beneath(_metadata, ruleset_fd, LANDLOCK_ACCESS_FS_WRITE_FILE, - dir_s1d2); + dir_s1d2); /* * According to ruleset_fd, dir_s1d2 should now have the * LANDLOCK_ACCESS_FS_READ_FILE and LANDLOCK_ACCESS_FS_WRITE_FILE @@ -1004,7 +1189,7 @@ TEST_F_FORK(layout1, inherit_subset) * that there was no rule tied to it before. */ add_path_beneath(_metadata, ruleset_fd, LANDLOCK_ACCESS_FS_WRITE_FILE, - dir_s1d3); + dir_s1d3); enforce_ruleset(_metadata, ruleset_fd); ASSERT_EQ(0, close(ruleset_fd)); @@ -1039,7 +1224,7 @@ TEST_F_FORK(layout1, inherit_superset) .path = dir_s1d3, .access = ACCESS_RO, }, - {} + {}, }; const int ruleset_fd = create_ruleset(_metadata, ACCESS_RW, rules); @@ -1054,8 +1239,10 @@ TEST_F_FORK(layout1, inherit_superset) ASSERT_EQ(0, test_open(file1_s1d3, O_RDONLY)); /* Now dir_s1d2, parent of dir_s1d3, gets a new rule tied to it. */ - add_path_beneath(_metadata, ruleset_fd, LANDLOCK_ACCESS_FS_READ_FILE | - LANDLOCK_ACCESS_FS_READ_DIR, dir_s1d2); + add_path_beneath(_metadata, ruleset_fd, + LANDLOCK_ACCESS_FS_READ_FILE | + LANDLOCK_ACCESS_FS_READ_DIR, + dir_s1d2); enforce_ruleset(_metadata, ruleset_fd); ASSERT_EQ(0, close(ruleset_fd)); @@ -1075,12 +1262,12 @@ TEST_F_FORK(layout1, max_layers) .path = dir_s1d2, .access = ACCESS_RO, }, - {} + {}, }; const int ruleset_fd = create_ruleset(_metadata, ACCESS_RW, rules); ASSERT_LE(0, ruleset_fd); - for (i = 0; i < 64; i++) + for (i = 0; i < 16; i++) enforce_ruleset(_metadata, ruleset_fd); for (i = 0; i < 2; i++) { @@ -1097,15 +1284,15 @@ TEST_F_FORK(layout1, empty_or_same_ruleset) int ruleset_fd; /* Tests empty handled_access_fs. */ - ruleset_fd = landlock_create_ruleset(&ruleset_attr, - sizeof(ruleset_attr), 0); + ruleset_fd = + landlock_create_ruleset(&ruleset_attr, sizeof(ruleset_attr), 0); ASSERT_LE(-1, ruleset_fd); ASSERT_EQ(ENOMSG, errno); /* Enforces policy which deny read access to all files. */ ruleset_attr.handled_access_fs = LANDLOCK_ACCESS_FS_READ_FILE; - ruleset_fd = landlock_create_ruleset(&ruleset_attr, - sizeof(ruleset_attr), 0); + ruleset_fd = + landlock_create_ruleset(&ruleset_attr, sizeof(ruleset_attr), 0); ASSERT_LE(0, ruleset_fd); enforce_ruleset(_metadata, ruleset_fd); ASSERT_EQ(EACCES, test_open(file1_s1d1, O_RDONLY)); @@ -1113,8 +1300,8 @@ TEST_F_FORK(layout1, empty_or_same_ruleset) /* Nests a policy which deny read access to all directories. */ ruleset_attr.handled_access_fs = LANDLOCK_ACCESS_FS_READ_DIR; - ruleset_fd = landlock_create_ruleset(&ruleset_attr, - sizeof(ruleset_attr), 0); + ruleset_fd = + landlock_create_ruleset(&ruleset_attr, sizeof(ruleset_attr), 0); ASSERT_LE(0, ruleset_fd); enforce_ruleset(_metadata, ruleset_fd); ASSERT_EQ(EACCES, test_open(file1_s1d1, O_RDONLY)); @@ -1137,7 +1324,7 @@ TEST_F_FORK(layout1, rule_on_mountpoint) .path = dir_s3d2, .access = ACCESS_RO, }, - {} + {}, }; const int ruleset_fd = create_ruleset(_metadata, ACCESS_RW, rules); @@ -1166,7 +1353,7 @@ TEST_F_FORK(layout1, rule_over_mountpoint) .path = dir_s3d1, .access = ACCESS_RO, }, - {} + {}, }; const int ruleset_fd = create_ruleset(_metadata, ACCESS_RW, rules); @@ -1194,7 +1381,7 @@ TEST_F_FORK(layout1, rule_over_root_allow_then_deny) .path = "/", .access = ACCESS_RO, }, - {} + {}, }; int ruleset_fd = create_ruleset(_metadata, ACCESS_RW, rules); @@ -1224,7 +1411,7 @@ TEST_F_FORK(layout1, rule_over_root_deny) .path = "/", .access = LANDLOCK_ACCESS_FS_READ_FILE, }, - {} + {}, }; const int ruleset_fd = create_ruleset(_metadata, ACCESS_RW, rules); @@ -1244,12 +1431,13 @@ TEST_F_FORK(layout1, rule_inside_mount_ns) .path = "s3d3", .access = ACCESS_RO, }, - {} + {}, }; int ruleset_fd; set_cap(_metadata, CAP_SYS_ADMIN); - ASSERT_EQ(0, syscall(SYS_pivot_root, dir_s3d2, dir_s3d3)) { + ASSERT_EQ(0, syscall(__NR_pivot_root, dir_s3d2, dir_s3d3)) + { TH_LOG("Failed to pivot root: %s", strerror(errno)); }; ASSERT_EQ(0, chdir("/")); @@ -1271,7 +1459,7 @@ TEST_F_FORK(layout1, mount_and_pivot) .path = dir_s3d2, .access = ACCESS_RO, }, - {} + {}, }; const int ruleset_fd = create_ruleset(_metadata, ACCESS_RW, rules); @@ -1282,7 +1470,7 @@ TEST_F_FORK(layout1, mount_and_pivot) set_cap(_metadata, CAP_SYS_ADMIN); ASSERT_EQ(-1, mount(NULL, dir_s3d2, NULL, MS_RDONLY, NULL)); ASSERT_EQ(EPERM, errno); - ASSERT_EQ(-1, syscall(SYS_pivot_root, dir_s3d2, dir_s3d3)); + ASSERT_EQ(-1, syscall(__NR_pivot_root, dir_s3d2, dir_s3d3)); ASSERT_EQ(EPERM, errno); clear_cap(_metadata, CAP_SYS_ADMIN); } @@ -1294,28 +1482,29 @@ TEST_F_FORK(layout1, move_mount) .path = dir_s3d2, .access = ACCESS_RO, }, - {} + {}, }; const int ruleset_fd = create_ruleset(_metadata, ACCESS_RW, rules); ASSERT_LE(0, ruleset_fd); set_cap(_metadata, CAP_SYS_ADMIN); - ASSERT_EQ(0, syscall(SYS_move_mount, AT_FDCWD, dir_s3d2, AT_FDCWD, - dir_s1d2, 0)) { + ASSERT_EQ(0, syscall(__NR_move_mount, AT_FDCWD, dir_s3d2, AT_FDCWD, + dir_s1d2, 0)) + { TH_LOG("Failed to move mount: %s", strerror(errno)); } - ASSERT_EQ(0, syscall(SYS_move_mount, AT_FDCWD, dir_s1d2, AT_FDCWD, - dir_s3d2, 0)); + ASSERT_EQ(0, syscall(__NR_move_mount, AT_FDCWD, dir_s1d2, AT_FDCWD, + dir_s3d2, 0)); clear_cap(_metadata, CAP_SYS_ADMIN); enforce_ruleset(_metadata, ruleset_fd); ASSERT_EQ(0, close(ruleset_fd)); set_cap(_metadata, CAP_SYS_ADMIN); - ASSERT_EQ(-1, syscall(SYS_move_mount, AT_FDCWD, dir_s3d2, AT_FDCWD, - dir_s1d2, 0)); + ASSERT_EQ(-1, syscall(__NR_move_mount, AT_FDCWD, dir_s3d2, AT_FDCWD, + dir_s1d2, 0)); ASSERT_EQ(EPERM, errno); clear_cap(_metadata, CAP_SYS_ADMIN); } @@ -1335,7 +1524,7 @@ TEST_F_FORK(layout1, release_inodes) .path = dir_s3d3, .access = ACCESS_RO, }, - {} + {}, }; const int ruleset_fd = create_ruleset(_metadata, ACCESS_RW, rules); @@ -1362,7 +1551,7 @@ enum relative_access { }; static void test_relative_path(struct __test_metadata *const _metadata, - const enum relative_access rel) + const enum relative_access rel) { /* * Common layer to check that chroot doesn't ignore it (i.e. a chroot @@ -1373,7 +1562,7 @@ static void test_relative_path(struct __test_metadata *const _metadata, .path = TMP_DIR, .access = ACCESS_RO, }, - {} + {}, }; const struct rule layer2_subs[] = { { @@ -1384,7 +1573,7 @@ static void test_relative_path(struct __test_metadata *const _metadata, .path = dir_s2d2, .access = ACCESS_RO, }, - {} + {}, }; int dirfd, ruleset_fd; @@ -1425,14 +1614,16 @@ static void test_relative_path(struct __test_metadata *const _metadata, break; case REL_CHROOT_ONLY: /* Do chroot into dir_s1d2 (relative to dir_s2d2). */ - ASSERT_EQ(0, chroot("../../s1d1/s1d2")) { + ASSERT_EQ(0, chroot("../../s1d1/s1d2")) + { TH_LOG("Failed to chroot: %s", strerror(errno)); } dirfd = AT_FDCWD; break; case REL_CHROOT_CHDIR: /* Do chroot into dir_s1d2. */ - ASSERT_EQ(0, chroot(".")) { + ASSERT_EQ(0, chroot(".")) + { TH_LOG("Failed to chroot: %s", strerror(errno)); } dirfd = AT_FDCWD; @@ -1440,7 +1631,7 @@ static void test_relative_path(struct __test_metadata *const _metadata, } ASSERT_EQ((rel == REL_CHROOT_CHDIR) ? 0 : EACCES, - test_open_rel(dirfd, "..", O_RDONLY)); + test_open_rel(dirfd, "..", O_RDONLY)); ASSERT_EQ(0, test_open_rel(dirfd, ".", O_RDONLY)); if (rel == REL_CHROOT_ONLY) { @@ -1462,11 +1653,13 @@ static void test_relative_path(struct __test_metadata *const _metadata, if (rel != REL_CHROOT_CHDIR) { ASSERT_EQ(EACCES, test_open_rel(dirfd, "../../s1d1", O_RDONLY)); ASSERT_EQ(0, test_open_rel(dirfd, "../../s1d1/s1d2", O_RDONLY)); - ASSERT_EQ(0, test_open_rel(dirfd, "../../s1d1/s1d2/s1d3", O_RDONLY)); + ASSERT_EQ(0, test_open_rel(dirfd, "../../s1d1/s1d2/s1d3", + O_RDONLY)); ASSERT_EQ(EACCES, test_open_rel(dirfd, "../../s2d1", O_RDONLY)); ASSERT_EQ(0, test_open_rel(dirfd, "../../s2d1/s2d2", O_RDONLY)); - ASSERT_EQ(0, test_open_rel(dirfd, "../../s2d1/s2d2/s2d3", O_RDONLY)); + ASSERT_EQ(0, test_open_rel(dirfd, "../../s2d1/s2d2/s2d3", + O_RDONLY)); } if (rel == REL_OPEN) @@ -1495,40 +1688,42 @@ TEST_F_FORK(layout1, relative_chroot_chdir) } static void copy_binary(struct __test_metadata *const _metadata, - const char *const dst_path) + const char *const dst_path) { int dst_fd, src_fd; struct stat statbuf; dst_fd = open(dst_path, O_WRONLY | O_TRUNC | O_CLOEXEC); - ASSERT_LE(0, dst_fd) { - TH_LOG("Failed to open \"%s\": %s", dst_path, - strerror(errno)); + ASSERT_LE(0, dst_fd) + { + TH_LOG("Failed to open \"%s\": %s", dst_path, strerror(errno)); } src_fd = open(BINARY_PATH, O_RDONLY | O_CLOEXEC); - ASSERT_LE(0, src_fd) { + ASSERT_LE(0, src_fd) + { TH_LOG("Failed to open \"" BINARY_PATH "\": %s", - strerror(errno)); + strerror(errno)); } ASSERT_EQ(0, fstat(src_fd, &statbuf)); - ASSERT_EQ(statbuf.st_size, sendfile(dst_fd, src_fd, 0, - statbuf.st_size)); + ASSERT_EQ(statbuf.st_size, + sendfile(dst_fd, src_fd, 0, statbuf.st_size)); ASSERT_EQ(0, close(src_fd)); ASSERT_EQ(0, close(dst_fd)); } -static void test_execute(struct __test_metadata *const _metadata, - const int err, const char *const path) +static void test_execute(struct __test_metadata *const _metadata, const int err, + const char *const path) { int status; - char *const argv[] = {(char *)path, NULL}; + char *const argv[] = { (char *)path, NULL }; const pid_t child = fork(); ASSERT_LE(0, child); if (child == 0) { - ASSERT_EQ(err ? -1 : 0, execve(path, argv, NULL)) { + ASSERT_EQ(err ? -1 : 0, execve(path, argv, NULL)) + { TH_LOG("Failed to execute \"%s\": %s", path, - strerror(errno)); + strerror(errno)); }; ASSERT_EQ(err, errno); _exit(_metadata->passed ? 2 : 1); @@ -1536,9 +1731,10 @@ static void test_execute(struct __test_metadata *const _metadata, } ASSERT_EQ(child, waitpid(child, &status, 0)); ASSERT_EQ(1, WIFEXITED(status)); - ASSERT_EQ(err ? 2 : 0, WEXITSTATUS(status)) { + ASSERT_EQ(err ? 2 : 0, WEXITSTATUS(status)) + { TH_LOG("Unexpected return code for \"%s\": %s", path, - strerror(errno)); + strerror(errno)); }; } @@ -1549,10 +1745,10 @@ TEST_F_FORK(layout1, execute) .path = dir_s1d2, .access = LANDLOCK_ACCESS_FS_EXECUTE, }, - {} + {}, }; - const int ruleset_fd = create_ruleset(_metadata, rules[0].access, - rules); + const int ruleset_fd = + create_ruleset(_metadata, rules[0].access, rules); ASSERT_LE(0, ruleset_fd); copy_binary(_metadata, file1_s1d1); @@ -1577,15 +1773,21 @@ TEST_F_FORK(layout1, execute) TEST_F_FORK(layout1, link) { - const struct rule rules[] = { + const struct rule layer1[] = { { .path = dir_s1d2, .access = LANDLOCK_ACCESS_FS_MAKE_REG, }, - {} + {}, }; - const int ruleset_fd = create_ruleset(_metadata, rules[0].access, - rules); + const struct rule layer2[] = { + { + .path = dir_s1d3, + .access = LANDLOCK_ACCESS_FS_REMOVE_FILE, + }, + {}, + }; + int ruleset_fd = create_ruleset(_metadata, layer1[0].access, layer1); ASSERT_LE(0, ruleset_fd); @@ -1598,14 +1800,30 @@ TEST_F_FORK(layout1, link) ASSERT_EQ(-1, link(file2_s1d1, file1_s1d1)); ASSERT_EQ(EACCES, errno); + /* Denies linking because of reparenting. */ ASSERT_EQ(-1, link(file1_s2d1, file1_s1d2)); ASSERT_EQ(EXDEV, errno); ASSERT_EQ(-1, link(file2_s1d2, file1_s1d3)); ASSERT_EQ(EXDEV, errno); + ASSERT_EQ(-1, link(file2_s1d3, file1_s1d2)); + ASSERT_EQ(EXDEV, errno); ASSERT_EQ(0, link(file2_s1d2, file1_s1d2)); ASSERT_EQ(0, link(file2_s1d3, file1_s1d3)); + + /* Prepares for next unlinks. */ + ASSERT_EQ(0, unlink(file2_s1d2)); + ASSERT_EQ(0, unlink(file2_s1d3)); + + ruleset_fd = create_ruleset(_metadata, layer2[0].access, layer2); + ASSERT_LE(0, ruleset_fd); + enforce_ruleset(_metadata, ruleset_fd); + ASSERT_EQ(0, close(ruleset_fd)); + + /* Checks that linkind doesn't require the ability to delete a file. */ + ASSERT_EQ(0, link(file1_s1d2, file2_s1d2)); + ASSERT_EQ(0, link(file1_s1d3, file2_s1d3)); } TEST_F_FORK(layout1, rename_file) @@ -1619,14 +1837,13 @@ TEST_F_FORK(layout1, rename_file) .path = dir_s2d2, .access = LANDLOCK_ACCESS_FS_REMOVE_FILE, }, - {} + {}, }; - const int ruleset_fd = create_ruleset(_metadata, rules[0].access, - rules); + const int ruleset_fd = + create_ruleset(_metadata, rules[0].access, rules); ASSERT_LE(0, ruleset_fd); - ASSERT_EQ(0, unlink(file1_s1d1)); ASSERT_EQ(0, unlink(file1_s1d2)); enforce_ruleset(_metadata, ruleset_fd); @@ -1662,9 +1879,15 @@ TEST_F_FORK(layout1, rename_file) ASSERT_EQ(-1, renameat2(AT_FDCWD, dir_s2d2, AT_FDCWD, file1_s2d1, RENAME_EXCHANGE)); ASSERT_EQ(EACCES, errno); + /* Checks that file1_s2d1 cannot be removed (instead of ENOTDIR). */ + ASSERT_EQ(-1, rename(dir_s2d2, file1_s2d1)); + ASSERT_EQ(EACCES, errno); ASSERT_EQ(-1, renameat2(AT_FDCWD, file1_s2d1, AT_FDCWD, dir_s2d2, RENAME_EXCHANGE)); ASSERT_EQ(EACCES, errno); + /* Checks that file1_s1d1 cannot be removed (instead of EISDIR). */ + ASSERT_EQ(-1, rename(file1_s1d1, dir_s1d2)); + ASSERT_EQ(EACCES, errno); /* Renames files with different parents. */ ASSERT_EQ(-1, rename(file1_s2d2, file1_s1d2)); @@ -1675,14 +1898,14 @@ TEST_F_FORK(layout1, rename_file) /* Exchanges and renames files with same parent. */ ASSERT_EQ(0, renameat2(AT_FDCWD, file2_s2d3, AT_FDCWD, file1_s2d3, - RENAME_EXCHANGE)); + RENAME_EXCHANGE)); ASSERT_EQ(0, rename(file2_s2d3, file1_s2d3)); /* Exchanges files and directories with same parent, twice. */ ASSERT_EQ(0, renameat2(AT_FDCWD, file1_s2d2, AT_FDCWD, dir_s2d3, - RENAME_EXCHANGE)); + RENAME_EXCHANGE)); ASSERT_EQ(0, renameat2(AT_FDCWD, file1_s2d2, AT_FDCWD, dir_s2d3, - RENAME_EXCHANGE)); + RENAME_EXCHANGE)); } TEST_F_FORK(layout1, rename_dir) @@ -1696,10 +1919,10 @@ TEST_F_FORK(layout1, rename_dir) .path = dir_s2d1, .access = LANDLOCK_ACCESS_FS_REMOVE_DIR, }, - {} + {}, }; - const int ruleset_fd = create_ruleset(_metadata, rules[0].access, - rules); + const int ruleset_fd = + create_ruleset(_metadata, rules[0].access, rules); ASSERT_LE(0, ruleset_fd); @@ -1727,22 +1950,743 @@ TEST_F_FORK(layout1, rename_dir) ASSERT_EQ(-1, renameat2(AT_FDCWD, dir_s1d1, AT_FDCWD, dir_s2d1, RENAME_EXCHANGE)); ASSERT_EQ(EACCES, errno); + /* Checks that dir_s1d2 cannot be removed (instead of ENOTDIR). */ + ASSERT_EQ(-1, rename(dir_s1d2, file1_s1d1)); + ASSERT_EQ(EACCES, errno); ASSERT_EQ(-1, renameat2(AT_FDCWD, file1_s1d1, AT_FDCWD, dir_s1d2, RENAME_EXCHANGE)); ASSERT_EQ(EACCES, errno); + /* Checks that dir_s1d2 cannot be removed (instead of EISDIR). */ + ASSERT_EQ(-1, rename(file1_s1d1, dir_s1d2)); + ASSERT_EQ(EACCES, errno); /* * Exchanges and renames directory to the same parent, which allows * directory removal. */ ASSERT_EQ(0, renameat2(AT_FDCWD, dir_s1d3, AT_FDCWD, file1_s1d2, - RENAME_EXCHANGE)); + RENAME_EXCHANGE)); ASSERT_EQ(0, unlink(dir_s1d3)); ASSERT_EQ(0, mkdir(dir_s1d3, 0700)); ASSERT_EQ(0, rename(file1_s1d2, dir_s1d3)); ASSERT_EQ(0, rmdir(dir_s1d3)); } +TEST_F_FORK(layout1, reparent_refer) +{ + const struct rule layer1[] = { + { + .path = dir_s1d2, + .access = LANDLOCK_ACCESS_FS_REFER, + }, + { + .path = dir_s2d2, + .access = LANDLOCK_ACCESS_FS_REFER, + }, + {}, + }; + int ruleset_fd = + create_ruleset(_metadata, LANDLOCK_ACCESS_FS_REFER, layer1); + + ASSERT_LE(0, ruleset_fd); + enforce_ruleset(_metadata, ruleset_fd); + ASSERT_EQ(0, close(ruleset_fd)); + + ASSERT_EQ(-1, rename(dir_s1d2, dir_s2d1)); + ASSERT_EQ(EXDEV, errno); + ASSERT_EQ(-1, rename(dir_s1d2, dir_s2d2)); + ASSERT_EQ(EXDEV, errno); + ASSERT_EQ(-1, rename(dir_s1d2, dir_s2d3)); + ASSERT_EQ(EXDEV, errno); + + ASSERT_EQ(-1, rename(dir_s1d3, dir_s2d1)); + ASSERT_EQ(EXDEV, errno); + ASSERT_EQ(-1, rename(dir_s1d3, dir_s2d2)); + ASSERT_EQ(EXDEV, errno); + /* + * Moving should only be allowed when the source and the destination + * parent directory have REFER. + */ + ASSERT_EQ(-1, rename(dir_s1d3, dir_s2d3)); + ASSERT_EQ(ENOTEMPTY, errno); + ASSERT_EQ(0, unlink(file1_s2d3)); + ASSERT_EQ(0, unlink(file2_s2d3)); + ASSERT_EQ(0, rename(dir_s1d3, dir_s2d3)); +} + +TEST_F_FORK(layout1, reparent_link) +{ + const struct rule layer1[] = { + { + .path = dir_s1d2, + .access = LANDLOCK_ACCESS_FS_MAKE_REG, + }, + { + .path = dir_s1d3, + .access = LANDLOCK_ACCESS_FS_REFER, + }, + { + .path = dir_s2d2, + .access = LANDLOCK_ACCESS_FS_REFER, + }, + { + .path = dir_s2d3, + .access = LANDLOCK_ACCESS_FS_MAKE_REG, + }, + {}, + }; + const int ruleset_fd = create_ruleset( + _metadata, + LANDLOCK_ACCESS_FS_MAKE_REG | LANDLOCK_ACCESS_FS_REFER, layer1); + + ASSERT_LE(0, ruleset_fd); + enforce_ruleset(_metadata, ruleset_fd); + ASSERT_EQ(0, close(ruleset_fd)); + + ASSERT_EQ(0, unlink(file1_s1d1)); + ASSERT_EQ(0, unlink(file1_s1d2)); + ASSERT_EQ(0, unlink(file1_s1d3)); + + /* Denies linking because of missing MAKE_REG. */ + ASSERT_EQ(-1, link(file2_s1d1, file1_s1d1)); + ASSERT_EQ(EACCES, errno); + /* Denies linking because of missing source and destination REFER. */ + ASSERT_EQ(-1, link(file1_s2d1, file1_s1d2)); + ASSERT_EQ(EXDEV, errno); + /* Denies linking because of missing source REFER. */ + ASSERT_EQ(-1, link(file1_s2d1, file1_s1d3)); + ASSERT_EQ(EXDEV, errno); + + /* Denies linking because of missing MAKE_REG. */ + ASSERT_EQ(-1, link(file1_s2d2, file1_s1d1)); + ASSERT_EQ(EACCES, errno); + /* Denies linking because of missing destination REFER. */ + ASSERT_EQ(-1, link(file1_s2d2, file1_s1d2)); + ASSERT_EQ(EXDEV, errno); + + /* Allows linking because of REFER and MAKE_REG. */ + ASSERT_EQ(0, link(file1_s2d2, file1_s1d3)); + ASSERT_EQ(0, unlink(file1_s2d2)); + /* Reverse linking denied because of missing MAKE_REG. */ + ASSERT_EQ(-1, link(file1_s1d3, file1_s2d2)); + ASSERT_EQ(EACCES, errno); + ASSERT_EQ(0, unlink(file1_s2d3)); + /* Checks reverse linking. */ + ASSERT_EQ(0, link(file1_s1d3, file1_s2d3)); + ASSERT_EQ(0, unlink(file1_s1d3)); + + /* + * This is OK for a file link, but it should not be allowed for a + * directory rename (because of the superset of access rights. + */ + ASSERT_EQ(0, link(file1_s2d3, file1_s1d3)); + ASSERT_EQ(0, unlink(file1_s1d3)); + + ASSERT_EQ(-1, link(file2_s1d2, file1_s1d3)); + ASSERT_EQ(EXDEV, errno); + ASSERT_EQ(-1, link(file2_s1d3, file1_s1d2)); + ASSERT_EQ(EXDEV, errno); + + ASSERT_EQ(0, link(file2_s1d2, file1_s1d2)); + ASSERT_EQ(0, link(file2_s1d3, file1_s1d3)); +} + +TEST_F_FORK(layout1, reparent_rename) +{ + /* Same rules as for reparent_link. */ + const struct rule layer1[] = { + { + .path = dir_s1d2, + .access = LANDLOCK_ACCESS_FS_MAKE_REG, + }, + { + .path = dir_s1d3, + .access = LANDLOCK_ACCESS_FS_REFER, + }, + { + .path = dir_s2d2, + .access = LANDLOCK_ACCESS_FS_REFER, + }, + { + .path = dir_s2d3, + .access = LANDLOCK_ACCESS_FS_MAKE_REG, + }, + {}, + }; + const int ruleset_fd = create_ruleset( + _metadata, + LANDLOCK_ACCESS_FS_MAKE_REG | LANDLOCK_ACCESS_FS_REFER, layer1); + + ASSERT_LE(0, ruleset_fd); + enforce_ruleset(_metadata, ruleset_fd); + ASSERT_EQ(0, close(ruleset_fd)); + + ASSERT_EQ(0, unlink(file1_s1d2)); + ASSERT_EQ(0, unlink(file1_s1d3)); + + /* Denies renaming because of missing MAKE_REG. */ + ASSERT_EQ(-1, renameat2(AT_FDCWD, file2_s1d1, AT_FDCWD, file1_s1d1, + RENAME_EXCHANGE)); + ASSERT_EQ(EACCES, errno); + ASSERT_EQ(-1, renameat2(AT_FDCWD, file1_s1d1, AT_FDCWD, file2_s1d1, + RENAME_EXCHANGE)); + ASSERT_EQ(EACCES, errno); + ASSERT_EQ(0, unlink(file1_s1d1)); + ASSERT_EQ(-1, rename(file2_s1d1, file1_s1d1)); + ASSERT_EQ(EACCES, errno); + /* Even denies same file exchange. */ + ASSERT_EQ(-1, renameat2(AT_FDCWD, file2_s1d1, AT_FDCWD, file2_s1d1, + RENAME_EXCHANGE)); + ASSERT_EQ(EACCES, errno); + + /* Denies renaming because of missing source and destination REFER. */ + ASSERT_EQ(-1, rename(file1_s2d1, file1_s1d2)); + ASSERT_EQ(EXDEV, errno); + /* + * Denies renaming because of missing MAKE_REG, source and destination + * REFER. + */ + ASSERT_EQ(-1, renameat2(AT_FDCWD, file1_s2d1, AT_FDCWD, file2_s1d1, + RENAME_EXCHANGE)); + ASSERT_EQ(EACCES, errno); + ASSERT_EQ(-1, renameat2(AT_FDCWD, file2_s1d1, AT_FDCWD, file1_s2d1, + RENAME_EXCHANGE)); + ASSERT_EQ(EACCES, errno); + + /* Denies renaming because of missing source REFER. */ + ASSERT_EQ(-1, rename(file1_s2d1, file1_s1d3)); + ASSERT_EQ(EXDEV, errno); + /* Denies renaming because of missing MAKE_REG. */ + ASSERT_EQ(-1, renameat2(AT_FDCWD, file1_s2d1, AT_FDCWD, file2_s1d3, + RENAME_EXCHANGE)); + ASSERT_EQ(EACCES, errno); + + /* Denies renaming because of missing MAKE_REG. */ + ASSERT_EQ(-1, rename(file1_s2d2, file1_s1d1)); + ASSERT_EQ(EACCES, errno); + /* Denies renaming because of missing destination REFER*/ + ASSERT_EQ(-1, rename(file1_s2d2, file1_s1d2)); + ASSERT_EQ(EXDEV, errno); + + /* Denies exchange because of one missing MAKE_REG. */ + ASSERT_EQ(-1, renameat2(AT_FDCWD, file1_s2d2, AT_FDCWD, file2_s1d3, + RENAME_EXCHANGE)); + ASSERT_EQ(EACCES, errno); + /* Allows renaming because of REFER and MAKE_REG. */ + ASSERT_EQ(0, rename(file1_s2d2, file1_s1d3)); + + /* Reverse renaming denied because of missing MAKE_REG. */ + ASSERT_EQ(-1, rename(file1_s1d3, file1_s2d2)); + ASSERT_EQ(EACCES, errno); + ASSERT_EQ(0, unlink(file1_s2d3)); + ASSERT_EQ(0, rename(file1_s1d3, file1_s2d3)); + + /* Tests reverse renaming. */ + ASSERT_EQ(0, rename(file1_s2d3, file1_s1d3)); + ASSERT_EQ(0, renameat2(AT_FDCWD, file2_s2d3, AT_FDCWD, file1_s1d3, + RENAME_EXCHANGE)); + ASSERT_EQ(0, rename(file1_s1d3, file1_s2d3)); + + /* + * This is OK for a file rename, but it should not be allowed for a + * directory rename (because of the superset of access rights). + */ + ASSERT_EQ(0, rename(file1_s2d3, file1_s1d3)); + ASSERT_EQ(0, rename(file1_s1d3, file1_s2d3)); + + /* + * Tests superset restrictions applied to directories. Not only the + * dir_s2d3's parent (dir_s2d2) should be taken into account but also + * access rights tied to dir_s2d3. dir_s2d2 is missing one access right + * compared to dir_s1d3/file1_s1d3 (MAKE_REG) but it is provided + * directly by the moved dir_s2d3. + */ + ASSERT_EQ(0, rename(dir_s2d3, file1_s1d3)); + ASSERT_EQ(0, rename(file1_s1d3, dir_s2d3)); + /* + * The first rename is allowed but not the exchange because dir_s1d3's + * parent (dir_s1d2) doesn't have REFER. + */ + ASSERT_EQ(-1, renameat2(AT_FDCWD, file1_s2d3, AT_FDCWD, dir_s1d3, + RENAME_EXCHANGE)); + ASSERT_EQ(EXDEV, errno); + ASSERT_EQ(-1, renameat2(AT_FDCWD, dir_s1d3, AT_FDCWD, file1_s2d3, + RENAME_EXCHANGE)); + ASSERT_EQ(EXDEV, errno); + ASSERT_EQ(-1, rename(file1_s2d3, dir_s1d3)); + ASSERT_EQ(EXDEV, errno); + + ASSERT_EQ(-1, rename(file2_s1d2, file1_s1d3)); + ASSERT_EQ(EXDEV, errno); + ASSERT_EQ(-1, rename(file2_s1d3, file1_s1d2)); + ASSERT_EQ(EXDEV, errno); + + /* Renaming in the same directory is always allowed. */ + ASSERT_EQ(0, rename(file2_s1d2, file1_s1d2)); + ASSERT_EQ(0, rename(file2_s1d3, file1_s1d3)); + + ASSERT_EQ(0, unlink(file1_s1d2)); + /* Denies because of missing source MAKE_REG and destination REFER. */ + ASSERT_EQ(-1, rename(dir_s2d3, file1_s1d2)); + ASSERT_EQ(EXDEV, errno); + + ASSERT_EQ(0, unlink(file1_s1d3)); + /* Denies because of missing source MAKE_REG and REFER. */ + ASSERT_EQ(-1, rename(dir_s2d2, file1_s1d3)); + ASSERT_EQ(EXDEV, errno); +} + +static void +reparent_exdev_layers_enforce1(struct __test_metadata *const _metadata) +{ + const struct rule layer1[] = { + { + .path = dir_s1d2, + .access = LANDLOCK_ACCESS_FS_REFER, + }, + { + /* Interesting for the layer2 tests. */ + .path = dir_s1d3, + .access = LANDLOCK_ACCESS_FS_MAKE_REG, + }, + { + .path = dir_s2d2, + .access = LANDLOCK_ACCESS_FS_REFER, + }, + { + .path = dir_s2d3, + .access = LANDLOCK_ACCESS_FS_MAKE_REG, + }, + {}, + }; + const int ruleset_fd = create_ruleset( + _metadata, + LANDLOCK_ACCESS_FS_MAKE_REG | LANDLOCK_ACCESS_FS_REFER, layer1); + + ASSERT_LE(0, ruleset_fd); + enforce_ruleset(_metadata, ruleset_fd); + ASSERT_EQ(0, close(ruleset_fd)); +} + +static void +reparent_exdev_layers_enforce2(struct __test_metadata *const _metadata) +{ + const struct rule layer2[] = { + { + .path = dir_s2d3, + .access = LANDLOCK_ACCESS_FS_MAKE_DIR, + }, + {}, + }; + /* + * Same checks as before but with a second layer and a new MAKE_DIR + * rule (and no explicit handling of REFER). + */ + const int ruleset_fd = + create_ruleset(_metadata, LANDLOCK_ACCESS_FS_MAKE_DIR, layer2); + + ASSERT_LE(0, ruleset_fd); + enforce_ruleset(_metadata, ruleset_fd); + ASSERT_EQ(0, close(ruleset_fd)); +} + +TEST_F_FORK(layout1, reparent_exdev_layers_rename1) +{ + ASSERT_EQ(0, unlink(file1_s2d2)); + ASSERT_EQ(0, unlink(file1_s2d3)); + + reparent_exdev_layers_enforce1(_metadata); + + /* + * Moving the dir_s1d3 directory below dir_s2d2 is allowed by Landlock + * because it doesn't inherit new access rights. + */ + ASSERT_EQ(0, rename(dir_s1d3, file1_s2d2)); + ASSERT_EQ(0, rename(file1_s2d2, dir_s1d3)); + + /* + * Moving the dir_s1d3 directory below dir_s2d3 is allowed, even if it + * gets a new inherited access rights (MAKE_REG), because MAKE_REG is + * already allowed for dir_s1d3. + */ + ASSERT_EQ(0, rename(dir_s1d3, file1_s2d3)); + ASSERT_EQ(0, rename(file1_s2d3, dir_s1d3)); + + /* + * However, moving the file1_s1d3 file below dir_s2d3 is allowed + * because it cannot inherit MAKE_REG right (which is dedicated to + * directories). + */ + ASSERT_EQ(0, rename(file1_s1d3, file1_s2d3)); + + reparent_exdev_layers_enforce2(_metadata); + + /* + * Moving the dir_s1d3 directory below dir_s2d2 is now denied because + * MAKE_DIR is not tied to dir_s2d2. + */ + ASSERT_EQ(-1, rename(dir_s1d3, file1_s2d2)); + ASSERT_EQ(EACCES, errno); + + /* + * Moving the dir_s1d3 directory below dir_s2d3 is forbidden because it + * would grants MAKE_REG and MAKE_DIR rights to it. + */ + ASSERT_EQ(-1, rename(dir_s1d3, file1_s2d3)); + ASSERT_EQ(EXDEV, errno); + + /* + * However, moving the file2_s1d3 file below dir_s2d3 is allowed + * because it cannot inherit MAKE_REG nor MAKE_DIR rights (which are + * dedicated to directories). + */ + ASSERT_EQ(0, rename(file2_s1d3, file1_s2d3)); +} + +TEST_F_FORK(layout1, reparent_exdev_layers_rename2) +{ + reparent_exdev_layers_enforce1(_metadata); + + /* Checks EACCES predominance over EXDEV. */ + ASSERT_EQ(-1, rename(file1_s1d1, file1_s2d2)); + ASSERT_EQ(EACCES, errno); + ASSERT_EQ(-1, rename(file1_s1d2, file1_s2d2)); + ASSERT_EQ(EACCES, errno); + ASSERT_EQ(-1, rename(file1_s1d1, file1_s2d3)); + ASSERT_EQ(EXDEV, errno); + /* Modify layout! */ + ASSERT_EQ(0, rename(file1_s1d2, file1_s2d3)); + + /* Without REFER source. */ + ASSERT_EQ(-1, rename(dir_s1d1, file1_s2d2)); + ASSERT_EQ(EXDEV, errno); + ASSERT_EQ(-1, rename(dir_s1d2, file1_s2d2)); + ASSERT_EQ(EXDEV, errno); + + reparent_exdev_layers_enforce2(_metadata); + + /* Checks EACCES predominance over EXDEV. */ + ASSERT_EQ(-1, rename(file1_s1d1, file1_s2d2)); + ASSERT_EQ(EACCES, errno); + /* Checks with actual file2_s1d2. */ + ASSERT_EQ(-1, rename(file2_s1d2, file1_s2d2)); + ASSERT_EQ(EACCES, errno); + ASSERT_EQ(-1, rename(file1_s1d1, file1_s2d3)); + ASSERT_EQ(EXDEV, errno); + /* Modify layout! */ + ASSERT_EQ(0, rename(file2_s1d2, file1_s2d3)); + + /* Without REFER source, EACCES wins over EXDEV. */ + ASSERT_EQ(-1, rename(dir_s1d1, file1_s2d2)); + ASSERT_EQ(EACCES, errno); + ASSERT_EQ(-1, rename(dir_s1d2, file1_s2d2)); + ASSERT_EQ(EACCES, errno); +} + +TEST_F_FORK(layout1, reparent_exdev_layers_exchange1) +{ + const char *const dir_file1_s1d2 = file1_s1d2, *const dir_file2_s2d3 = + file2_s2d3; + + ASSERT_EQ(0, unlink(file1_s1d2)); + ASSERT_EQ(0, mkdir(file1_s1d2, 0700)); + ASSERT_EQ(0, unlink(file2_s2d3)); + ASSERT_EQ(0, mkdir(file2_s2d3, 0700)); + + reparent_exdev_layers_enforce1(_metadata); + + /* Error predominance with file exchange: returns EXDEV and EACCES. */ + ASSERT_EQ(-1, renameat2(AT_FDCWD, file1_s1d1, AT_FDCWD, file1_s2d3, + RENAME_EXCHANGE)); + ASSERT_EQ(EACCES, errno); + ASSERT_EQ(-1, renameat2(AT_FDCWD, file1_s2d3, AT_FDCWD, file1_s1d1, + RENAME_EXCHANGE)); + ASSERT_EQ(EACCES, errno); + + /* + * Checks with directories which creation could be allowed, but denied + * because of access rights that would be inherited. + */ + ASSERT_EQ(-1, renameat2(AT_FDCWD, dir_file1_s1d2, AT_FDCWD, + dir_file2_s2d3, RENAME_EXCHANGE)); + ASSERT_EQ(EXDEV, errno); + ASSERT_EQ(-1, renameat2(AT_FDCWD, dir_file2_s2d3, AT_FDCWD, + dir_file1_s1d2, RENAME_EXCHANGE)); + ASSERT_EQ(EXDEV, errno); + + /* Checks with same access rights. */ + ASSERT_EQ(0, renameat2(AT_FDCWD, dir_s1d3, AT_FDCWD, dir_s2d3, + RENAME_EXCHANGE)); + ASSERT_EQ(0, renameat2(AT_FDCWD, dir_s2d3, AT_FDCWD, dir_s1d3, + RENAME_EXCHANGE)); + + /* Checks with different (child-only) access rights. */ + ASSERT_EQ(0, renameat2(AT_FDCWD, dir_s2d3, AT_FDCWD, dir_file1_s1d2, + RENAME_EXCHANGE)); + ASSERT_EQ(0, renameat2(AT_FDCWD, dir_file1_s1d2, AT_FDCWD, dir_s2d3, + RENAME_EXCHANGE)); + + /* + * Checks that exchange between file and directory are consistent. + * + * Moving a file (file1_s2d2) to a directory which only grants more + * directory-related access rights is allowed, and at the same time + * moving a directory (dir_file2_s2d3) to another directory which + * grants less access rights is allowed too. + * + * See layout1.reparent_exdev_layers_exchange3 for inverted arguments. + */ + ASSERT_EQ(0, renameat2(AT_FDCWD, file1_s2d2, AT_FDCWD, dir_file2_s2d3, + RENAME_EXCHANGE)); + /* + * However, moving back the directory is denied because it would get + * more access rights than the current state and because file creation + * is forbidden (in dir_s2d2). + */ + ASSERT_EQ(-1, renameat2(AT_FDCWD, dir_file2_s2d3, AT_FDCWD, file1_s2d2, + RENAME_EXCHANGE)); + ASSERT_EQ(EACCES, errno); + ASSERT_EQ(-1, renameat2(AT_FDCWD, file1_s2d2, AT_FDCWD, dir_file2_s2d3, + RENAME_EXCHANGE)); + ASSERT_EQ(EACCES, errno); + + reparent_exdev_layers_enforce2(_metadata); + + /* Error predominance with file exchange: returns EXDEV and EACCES. */ + ASSERT_EQ(-1, renameat2(AT_FDCWD, file1_s1d1, AT_FDCWD, file1_s2d3, + RENAME_EXCHANGE)); + ASSERT_EQ(EACCES, errno); + ASSERT_EQ(-1, renameat2(AT_FDCWD, file1_s2d3, AT_FDCWD, file1_s1d1, + RENAME_EXCHANGE)); + ASSERT_EQ(EACCES, errno); + + /* Checks with directories which creation is now denied. */ + ASSERT_EQ(-1, renameat2(AT_FDCWD, dir_file1_s1d2, AT_FDCWD, + dir_file2_s2d3, RENAME_EXCHANGE)); + ASSERT_EQ(EACCES, errno); + ASSERT_EQ(-1, renameat2(AT_FDCWD, dir_file2_s2d3, AT_FDCWD, + dir_file1_s1d2, RENAME_EXCHANGE)); + ASSERT_EQ(EACCES, errno); + + /* Checks with different (child-only) access rights. */ + ASSERT_EQ(-1, renameat2(AT_FDCWD, dir_s1d3, AT_FDCWD, dir_s2d3, + RENAME_EXCHANGE)); + /* Denied because of MAKE_DIR. */ + ASSERT_EQ(EACCES, errno); + ASSERT_EQ(-1, renameat2(AT_FDCWD, dir_s2d3, AT_FDCWD, dir_s1d3, + RENAME_EXCHANGE)); + ASSERT_EQ(EACCES, errno); + + /* Checks with different (child-only) access rights. */ + ASSERT_EQ(-1, renameat2(AT_FDCWD, dir_s2d3, AT_FDCWD, dir_file1_s1d2, + RENAME_EXCHANGE)); + /* Denied because of MAKE_DIR. */ + ASSERT_EQ(EACCES, errno); + ASSERT_EQ(-1, renameat2(AT_FDCWD, dir_file1_s1d2, AT_FDCWD, dir_s2d3, + RENAME_EXCHANGE)); + ASSERT_EQ(EACCES, errno); + + /* See layout1.reparent_exdev_layers_exchange2 for complement. */ +} + +TEST_F_FORK(layout1, reparent_exdev_layers_exchange2) +{ + const char *const dir_file2_s2d3 = file2_s2d3; + + ASSERT_EQ(0, unlink(file2_s2d3)); + ASSERT_EQ(0, mkdir(file2_s2d3, 0700)); + + reparent_exdev_layers_enforce1(_metadata); + reparent_exdev_layers_enforce2(_metadata); + + /* Checks that exchange between file and directory are consistent. */ + ASSERT_EQ(-1, renameat2(AT_FDCWD, file1_s2d2, AT_FDCWD, dir_file2_s2d3, + RENAME_EXCHANGE)); + ASSERT_EQ(EACCES, errno); + ASSERT_EQ(-1, renameat2(AT_FDCWD, dir_file2_s2d3, AT_FDCWD, file1_s2d2, + RENAME_EXCHANGE)); + ASSERT_EQ(EACCES, errno); +} + +TEST_F_FORK(layout1, reparent_exdev_layers_exchange3) +{ + const char *const dir_file2_s2d3 = file2_s2d3; + + ASSERT_EQ(0, unlink(file2_s2d3)); + ASSERT_EQ(0, mkdir(file2_s2d3, 0700)); + + reparent_exdev_layers_enforce1(_metadata); + + /* + * Checks that exchange between file and directory are consistent, + * including with inverted arguments (see + * layout1.reparent_exdev_layers_exchange1). + */ + ASSERT_EQ(0, renameat2(AT_FDCWD, dir_file2_s2d3, AT_FDCWD, file1_s2d2, + RENAME_EXCHANGE)); + ASSERT_EQ(-1, renameat2(AT_FDCWD, file1_s2d2, AT_FDCWD, dir_file2_s2d3, + RENAME_EXCHANGE)); + ASSERT_EQ(EACCES, errno); + ASSERT_EQ(-1, renameat2(AT_FDCWD, dir_file2_s2d3, AT_FDCWD, file1_s2d2, + RENAME_EXCHANGE)); + ASSERT_EQ(EACCES, errno); +} + +TEST_F_FORK(layout1, reparent_remove) +{ + const struct rule layer1[] = { + { + .path = dir_s1d1, + .access = LANDLOCK_ACCESS_FS_REFER | + LANDLOCK_ACCESS_FS_REMOVE_DIR, + }, + { + .path = dir_s1d2, + .access = LANDLOCK_ACCESS_FS_REMOVE_FILE, + }, + { + .path = dir_s2d1, + .access = LANDLOCK_ACCESS_FS_REFER | + LANDLOCK_ACCESS_FS_REMOVE_FILE, + }, + {}, + }; + const int ruleset_fd = create_ruleset( + _metadata, + LANDLOCK_ACCESS_FS_REFER | LANDLOCK_ACCESS_FS_REMOVE_DIR | + LANDLOCK_ACCESS_FS_REMOVE_FILE, + layer1); + + ASSERT_LE(0, ruleset_fd); + enforce_ruleset(_metadata, ruleset_fd); + ASSERT_EQ(0, close(ruleset_fd)); + + /* Access denied because of wrong/swapped remove file/dir. */ + ASSERT_EQ(-1, rename(file1_s1d1, dir_s2d2)); + ASSERT_EQ(EACCES, errno); + ASSERT_EQ(-1, rename(dir_s2d2, file1_s1d1)); + ASSERT_EQ(EACCES, errno); + ASSERT_EQ(-1, renameat2(AT_FDCWD, file1_s1d1, AT_FDCWD, dir_s2d2, + RENAME_EXCHANGE)); + ASSERT_EQ(EACCES, errno); + ASSERT_EQ(-1, renameat2(AT_FDCWD, file1_s1d1, AT_FDCWD, dir_s2d3, + RENAME_EXCHANGE)); + ASSERT_EQ(EACCES, errno); + + /* Access allowed thanks to the matching rights. */ + ASSERT_EQ(-1, rename(file1_s2d1, dir_s1d2)); + ASSERT_EQ(EISDIR, errno); + ASSERT_EQ(-1, rename(dir_s1d2, file1_s2d1)); + ASSERT_EQ(ENOTDIR, errno); + ASSERT_EQ(-1, rename(dir_s1d3, file1_s2d1)); + ASSERT_EQ(ENOTDIR, errno); + ASSERT_EQ(0, unlink(file1_s2d1)); + ASSERT_EQ(0, unlink(file1_s1d3)); + ASSERT_EQ(0, unlink(file2_s1d3)); + ASSERT_EQ(0, rename(dir_s1d3, file1_s2d1)); + + /* Effectively removes a file and a directory by exchanging them. */ + ASSERT_EQ(0, mkdir(dir_s1d3, 0700)); + ASSERT_EQ(0, renameat2(AT_FDCWD, file1_s2d2, AT_FDCWD, dir_s1d3, + RENAME_EXCHANGE)); + ASSERT_EQ(-1, renameat2(AT_FDCWD, file1_s2d2, AT_FDCWD, dir_s1d3, + RENAME_EXCHANGE)); + ASSERT_EQ(EACCES, errno); +} + +TEST_F_FORK(layout1, reparent_dom_superset) +{ + const struct rule layer1[] = { + { + .path = dir_s1d2, + .access = LANDLOCK_ACCESS_FS_REFER, + }, + { + .path = file1_s1d2, + .access = LANDLOCK_ACCESS_FS_EXECUTE, + }, + { + .path = dir_s1d3, + .access = LANDLOCK_ACCESS_FS_MAKE_SOCK | + LANDLOCK_ACCESS_FS_EXECUTE, + }, + { + .path = dir_s2d2, + .access = LANDLOCK_ACCESS_FS_REFER | + LANDLOCK_ACCESS_FS_EXECUTE | + LANDLOCK_ACCESS_FS_MAKE_SOCK, + }, + { + .path = dir_s2d3, + .access = LANDLOCK_ACCESS_FS_READ_FILE | + LANDLOCK_ACCESS_FS_MAKE_FIFO, + }, + {}, + }; + int ruleset_fd = create_ruleset(_metadata, + LANDLOCK_ACCESS_FS_REFER | + LANDLOCK_ACCESS_FS_EXECUTE | + LANDLOCK_ACCESS_FS_MAKE_SOCK | + LANDLOCK_ACCESS_FS_READ_FILE | + LANDLOCK_ACCESS_FS_MAKE_FIFO, + layer1); + + ASSERT_LE(0, ruleset_fd); + enforce_ruleset(_metadata, ruleset_fd); + ASSERT_EQ(0, close(ruleset_fd)); + + ASSERT_EQ(-1, rename(file1_s1d2, file1_s2d1)); + ASSERT_EQ(EXDEV, errno); + /* + * Moving file1_s1d2 beneath dir_s2d3 would grant it the READ_FILE + * access right. + */ + ASSERT_EQ(-1, rename(file1_s1d2, file1_s2d3)); + ASSERT_EQ(EXDEV, errno); + /* + * Moving file1_s1d2 should be allowed even if dir_s2d2 grants a + * superset of access rights compared to dir_s1d2, because file1_s1d2 + * already has these access rights anyway. + */ + ASSERT_EQ(0, rename(file1_s1d2, file1_s2d2)); + ASSERT_EQ(0, rename(file1_s2d2, file1_s1d2)); + + ASSERT_EQ(-1, rename(dir_s1d3, file1_s2d1)); + ASSERT_EQ(EXDEV, errno); + /* + * Moving dir_s1d3 beneath dir_s2d3 would grant it the MAKE_FIFO access + * right. + */ + ASSERT_EQ(-1, rename(dir_s1d3, file1_s2d3)); + ASSERT_EQ(EXDEV, errno); + /* + * Moving dir_s1d3 should be allowed even if dir_s2d2 grants a superset + * of access rights compared to dir_s1d2, because dir_s1d3 already has + * these access rights anyway. + */ + ASSERT_EQ(0, rename(dir_s1d3, file1_s2d2)); + ASSERT_EQ(0, rename(file1_s2d2, dir_s1d3)); + + /* + * Moving file1_s2d3 beneath dir_s1d2 is allowed, but moving it back + * will be denied because the new inherited access rights from dir_s1d2 + * will be less than the destination (original) dir_s2d3. This is a + * sinkhole scenario where we cannot move back files or directories. + */ + ASSERT_EQ(0, rename(file1_s2d3, file2_s1d2)); + ASSERT_EQ(-1, rename(file2_s1d2, file1_s2d3)); + ASSERT_EQ(EXDEV, errno); + ASSERT_EQ(0, unlink(file2_s1d2)); + ASSERT_EQ(0, unlink(file2_s2d3)); + /* + * Checks similar directory one-way move: dir_s2d3 loses EXECUTE and + * MAKE_SOCK which were inherited from dir_s1d3. + */ + ASSERT_EQ(0, rename(dir_s2d3, file2_s1d2)); + ASSERT_EQ(-1, rename(file2_s1d2, dir_s2d3)); + ASSERT_EQ(EXDEV, errno); +} + TEST_F_FORK(layout1, remove_dir) { const struct rule rules[] = { @@ -1750,10 +2694,10 @@ TEST_F_FORK(layout1, remove_dir) .path = dir_s1d2, .access = LANDLOCK_ACCESS_FS_REMOVE_DIR, }, - {} + {}, }; - const int ruleset_fd = create_ruleset(_metadata, rules[0].access, - rules); + const int ruleset_fd = + create_ruleset(_metadata, rules[0].access, rules); ASSERT_LE(0, ruleset_fd); @@ -1787,10 +2731,10 @@ TEST_F_FORK(layout1, remove_file) .path = dir_s1d2, .access = LANDLOCK_ACCESS_FS_REMOVE_FILE, }, - {} + {}, }; - const int ruleset_fd = create_ruleset(_metadata, rules[0].access, - rules); + const int ruleset_fd = + create_ruleset(_metadata, rules[0].access, rules); ASSERT_LE(0, ruleset_fd); enforce_ruleset(_metadata, ruleset_fd); @@ -1805,14 +2749,15 @@ TEST_F_FORK(layout1, remove_file) } static void test_make_file(struct __test_metadata *const _metadata, - const __u64 access, const mode_t mode, const dev_t dev) + const __u64 access, const mode_t mode, + const dev_t dev) { const struct rule rules[] = { { .path = dir_s1d2, .access = access, }, - {} + {}, }; const int ruleset_fd = create_ruleset(_metadata, access, rules); @@ -1820,9 +2765,10 @@ static void test_make_file(struct __test_metadata *const _metadata, ASSERT_EQ(0, unlink(file1_s1d1)); ASSERT_EQ(0, unlink(file2_s1d1)); - ASSERT_EQ(0, mknod(file2_s1d1, mode | 0400, dev)) { - TH_LOG("Failed to make file \"%s\": %s", - file2_s1d1, strerror(errno)); + ASSERT_EQ(0, mknod(file2_s1d1, mode | 0400, dev)) + { + TH_LOG("Failed to make file \"%s\": %s", file2_s1d1, + strerror(errno)); }; ASSERT_EQ(0, unlink(file1_s1d2)); @@ -1841,9 +2787,10 @@ static void test_make_file(struct __test_metadata *const _metadata, ASSERT_EQ(-1, rename(file2_s1d1, file1_s1d1)); ASSERT_EQ(EACCES, errno); - ASSERT_EQ(0, mknod(file1_s1d2, mode | 0400, dev)) { - TH_LOG("Failed to make file \"%s\": %s", - file1_s1d2, strerror(errno)); + ASSERT_EQ(0, mknod(file1_s1d2, mode | 0400, dev)) + { + TH_LOG("Failed to make file \"%s\": %s", file1_s1d2, + strerror(errno)); }; ASSERT_EQ(0, link(file1_s1d2, file2_s1d2)); ASSERT_EQ(0, unlink(file2_s1d2)); @@ -1860,7 +2807,7 @@ TEST_F_FORK(layout1, make_char) /* Creates a /dev/null device. */ set_cap(_metadata, CAP_MKNOD); test_make_file(_metadata, LANDLOCK_ACCESS_FS_MAKE_CHAR, S_IFCHR, - makedev(1, 3)); + makedev(1, 3)); } TEST_F_FORK(layout1, make_block) @@ -1868,7 +2815,7 @@ TEST_F_FORK(layout1, make_block) /* Creates a /dev/loop0 device. */ set_cap(_metadata, CAP_MKNOD); test_make_file(_metadata, LANDLOCK_ACCESS_FS_MAKE_BLOCK, S_IFBLK, - makedev(7, 0)); + makedev(7, 0)); } TEST_F_FORK(layout1, make_reg_1) @@ -1898,10 +2845,10 @@ TEST_F_FORK(layout1, make_sym) .path = dir_s1d2, .access = LANDLOCK_ACCESS_FS_MAKE_SYM, }, - {} + {}, }; - const int ruleset_fd = create_ruleset(_metadata, rules[0].access, - rules); + const int ruleset_fd = + create_ruleset(_metadata, rules[0].access, rules); ASSERT_LE(0, ruleset_fd); @@ -1943,10 +2890,10 @@ TEST_F_FORK(layout1, make_dir) .path = dir_s1d2, .access = LANDLOCK_ACCESS_FS_MAKE_DIR, }, - {} + {}, }; - const int ruleset_fd = create_ruleset(_metadata, rules[0].access, - rules); + const int ruleset_fd = + create_ruleset(_metadata, rules[0].access, rules); ASSERT_LE(0, ruleset_fd); @@ -1965,12 +2912,12 @@ TEST_F_FORK(layout1, make_dir) } static int open_proc_fd(struct __test_metadata *const _metadata, const int fd, - const int open_flags) + const int open_flags) { static const char path_template[] = "/proc/self/fd/%d"; char procfd_path[sizeof(path_template) + 10]; - const int procfd_path_size = snprintf(procfd_path, sizeof(procfd_path), - path_template, fd); + const int procfd_path_size = + snprintf(procfd_path, sizeof(procfd_path), path_template, fd); ASSERT_LT(procfd_path_size, sizeof(procfd_path)); return open(procfd_path, open_flags); @@ -1983,12 +2930,13 @@ TEST_F_FORK(layout1, proc_unlinked_file) .path = file1_s1d2, .access = LANDLOCK_ACCESS_FS_READ_FILE, }, - {} + {}, }; int reg_fd, proc_fd; - const int ruleset_fd = create_ruleset(_metadata, - LANDLOCK_ACCESS_FS_READ_FILE | - LANDLOCK_ACCESS_FS_WRITE_FILE, rules); + const int ruleset_fd = create_ruleset( + _metadata, + LANDLOCK_ACCESS_FS_READ_FILE | LANDLOCK_ACCESS_FS_WRITE_FILE, + rules); ASSERT_LE(0, ruleset_fd); enforce_ruleset(_metadata, ruleset_fd); @@ -2005,9 +2953,10 @@ TEST_F_FORK(layout1, proc_unlinked_file) ASSERT_EQ(0, close(proc_fd)); proc_fd = open_proc_fd(_metadata, reg_fd, O_RDWR | O_CLOEXEC); - ASSERT_EQ(-1, proc_fd) { - TH_LOG("Successfully opened /proc/self/fd/%d: %s", - reg_fd, strerror(errno)); + ASSERT_EQ(-1, proc_fd) + { + TH_LOG("Successfully opened /proc/self/fd/%d: %s", reg_fd, + strerror(errno)); } ASSERT_EQ(EACCES, errno); @@ -2023,13 +2972,13 @@ TEST_F_FORK(layout1, proc_pipe) { .path = dir_s1d2, .access = LANDLOCK_ACCESS_FS_READ_FILE | - LANDLOCK_ACCESS_FS_WRITE_FILE, + LANDLOCK_ACCESS_FS_WRITE_FILE, }, - {} + {}, }; /* Limits read and write access to files tied to the filesystem. */ - const int ruleset_fd = create_ruleset(_metadata, rules[0].access, - rules); + const int ruleset_fd = + create_ruleset(_metadata, rules[0].access, rules); ASSERT_LE(0, ruleset_fd); enforce_ruleset(_metadata, ruleset_fd); @@ -2041,7 +2990,8 @@ TEST_F_FORK(layout1, proc_pipe) /* Checks access to pipes through FD. */ ASSERT_EQ(0, pipe2(pipe_fds, O_CLOEXEC)); - ASSERT_EQ(1, write(pipe_fds[1], ".", 1)) { + ASSERT_EQ(1, write(pipe_fds[1], ".", 1)) + { TH_LOG("Failed to write in pipe: %s", strerror(errno)); } ASSERT_EQ(1, read(pipe_fds[0], &buf, 1)); @@ -2050,9 +3000,10 @@ TEST_F_FORK(layout1, proc_pipe) /* Checks write access to pipe through /proc/self/fd . */ proc_fd = open_proc_fd(_metadata, pipe_fds[1], O_WRONLY | O_CLOEXEC); ASSERT_LE(0, proc_fd); - ASSERT_EQ(1, write(proc_fd, ".", 1)) { + ASSERT_EQ(1, write(proc_fd, ".", 1)) + { TH_LOG("Failed to write through /proc/self/fd/%d: %s", - pipe_fds[1], strerror(errno)); + pipe_fds[1], strerror(errno)); } ASSERT_EQ(0, close(proc_fd)); @@ -2060,9 +3011,10 @@ TEST_F_FORK(layout1, proc_pipe) proc_fd = open_proc_fd(_metadata, pipe_fds[0], O_RDONLY | O_CLOEXEC); ASSERT_LE(0, proc_fd); buf = '\0'; - ASSERT_EQ(1, read(proc_fd, &buf, 1)) { + ASSERT_EQ(1, read(proc_fd, &buf, 1)) + { TH_LOG("Failed to read through /proc/self/fd/%d: %s", - pipe_fds[1], strerror(errno)); + pipe_fds[1], strerror(errno)); } ASSERT_EQ(0, close(proc_fd)); @@ -2070,8 +3022,9 @@ TEST_F_FORK(layout1, proc_pipe) ASSERT_EQ(0, close(pipe_fds[1])); } -FIXTURE(layout1_bind) { -}; +/* clang-format off */ +FIXTURE(layout1_bind) {}; +/* clang-format on */ FIXTURE_SETUP(layout1_bind) { @@ -2161,7 +3114,7 @@ TEST_F_FORK(layout1_bind, same_content_same_file) .path = dir_s2d1, .access = ACCESS_RW, }, - {} + {}, }; /* * Sets access rights on the same bind-mounted directories. The result @@ -2177,7 +3130,7 @@ TEST_F_FORK(layout1_bind, same_content_same_file) .path = dir_s2d2, .access = ACCESS_RW, }, - {} + {}, }; /* Only allow read-access to the s1d3 hierarchies. */ const struct rule layer3_source[] = { @@ -2185,7 +3138,7 @@ TEST_F_FORK(layout1_bind, same_content_same_file) .path = dir_s1d3, .access = LANDLOCK_ACCESS_FS_READ_FILE, }, - {} + {}, }; /* Removes all access rights. */ const struct rule layer4_destination[] = { @@ -2193,7 +3146,7 @@ TEST_F_FORK(layout1_bind, same_content_same_file) .path = bind_file1_s1d3, .access = LANDLOCK_ACCESS_FS_WRITE_FILE, }, - {} + {}, }; int ruleset_fd; @@ -2282,8 +3235,46 @@ TEST_F_FORK(layout1_bind, same_content_same_file) ASSERT_EQ(EACCES, test_open(bind_file1_s1d3, O_WRONLY)); } -#define LOWER_BASE TMP_DIR "/lower" -#define LOWER_DATA LOWER_BASE "/data" +TEST_F_FORK(layout1_bind, reparent_cross_mount) +{ + const struct rule layer1[] = { + { + /* dir_s2d1 is beneath the dir_s2d2 mount point. */ + .path = dir_s2d1, + .access = LANDLOCK_ACCESS_FS_REFER, + }, + { + .path = bind_dir_s1d3, + .access = LANDLOCK_ACCESS_FS_EXECUTE, + }, + {}, + }; + int ruleset_fd = create_ruleset( + _metadata, + LANDLOCK_ACCESS_FS_REFER | LANDLOCK_ACCESS_FS_EXECUTE, layer1); + + ASSERT_LE(0, ruleset_fd); + enforce_ruleset(_metadata, ruleset_fd); + ASSERT_EQ(0, close(ruleset_fd)); + + /* Checks basic denied move. */ + ASSERT_EQ(-1, rename(file1_s1d1, file1_s1d2)); + ASSERT_EQ(EXDEV, errno); + + /* Checks real cross-mount move (Landlock is not involved). */ + ASSERT_EQ(-1, rename(file1_s2d1, file1_s2d2)); + ASSERT_EQ(EXDEV, errno); + + /* Checks move that will give more accesses. */ + ASSERT_EQ(-1, rename(file1_s2d2, bind_file1_s1d3)); + ASSERT_EQ(EXDEV, errno); + + /* Checks legitimate downgrade move. */ + ASSERT_EQ(0, rename(bind_file1_s1d3, file1_s2d2)); +} + +#define LOWER_BASE TMP_DIR "/lower" +#define LOWER_DATA LOWER_BASE "/data" static const char lower_fl1[] = LOWER_DATA "/fl1"; static const char lower_dl1[] = LOWER_DATA "/dl1"; static const char lower_dl1_fl2[] = LOWER_DATA "/dl1/fl2"; @@ -2295,23 +3286,23 @@ static const char lower_do1_fl3[] = LOWER_DATA "/do1/fl3"; static const char (*lower_base_files[])[] = { &lower_fl1, &lower_fo1, - NULL + NULL, }; static const char (*lower_base_directories[])[] = { &lower_dl1, &lower_do1, - NULL + NULL, }; static const char (*lower_sub_files[])[] = { &lower_dl1_fl2, &lower_do1_fo2, &lower_do1_fl3, - NULL + NULL, }; -#define UPPER_BASE TMP_DIR "/upper" -#define UPPER_DATA UPPER_BASE "/data" -#define UPPER_WORK UPPER_BASE "/work" +#define UPPER_BASE TMP_DIR "/upper" +#define UPPER_DATA UPPER_BASE "/data" +#define UPPER_WORK UPPER_BASE "/work" static const char upper_fu1[] = UPPER_DATA "/fu1"; static const char upper_du1[] = UPPER_DATA "/du1"; static const char upper_du1_fu2[] = UPPER_DATA "/du1/fu2"; @@ -2323,22 +3314,22 @@ static const char upper_do1_fu3[] = UPPER_DATA "/do1/fu3"; static const char (*upper_base_files[])[] = { &upper_fu1, &upper_fo1, - NULL + NULL, }; static const char (*upper_base_directories[])[] = { &upper_du1, &upper_do1, - NULL + NULL, }; static const char (*upper_sub_files[])[] = { &upper_du1_fu2, &upper_do1_fo2, &upper_do1_fu3, - NULL + NULL, }; -#define MERGE_BASE TMP_DIR "/merge" -#define MERGE_DATA MERGE_BASE "/data" +#define MERGE_BASE TMP_DIR "/merge" +#define MERGE_DATA MERGE_BASE "/data" static const char merge_fl1[] = MERGE_DATA "/fl1"; static const char merge_dl1[] = MERGE_DATA "/dl1"; static const char merge_dl1_fl2[] = MERGE_DATA "/dl1/fl2"; @@ -2355,21 +3346,17 @@ static const char (*merge_base_files[])[] = { &merge_fl1, &merge_fu1, &merge_fo1, - NULL + NULL, }; static const char (*merge_base_directories[])[] = { &merge_dl1, &merge_du1, &merge_do1, - NULL + NULL, }; static const char (*merge_sub_files[])[] = { - &merge_dl1_fl2, - &merge_du1_fu2, - &merge_do1_fo2, - &merge_do1_fl3, - &merge_do1_fu3, - NULL + &merge_dl1_fl2, &merge_du1_fu2, &merge_do1_fo2, + &merge_do1_fl3, &merge_do1_fu3, NULL, }; /* @@ -2411,8 +3398,9 @@ static const char (*merge_sub_files[])[] = { * └── work */ -FIXTURE(layout2_overlay) { -}; +/* clang-format off */ +FIXTURE(layout2_overlay) {}; +/* clang-format on */ FIXTURE_SETUP(layout2_overlay) { @@ -2444,9 +3432,8 @@ FIXTURE_SETUP(layout2_overlay) set_cap(_metadata, CAP_SYS_ADMIN); set_cap(_metadata, CAP_DAC_OVERRIDE); ASSERT_EQ(0, mount("overlay", MERGE_DATA, "overlay", 0, - "lowerdir=" LOWER_DATA - ",upperdir=" UPPER_DATA - ",workdir=" UPPER_WORK)); + "lowerdir=" LOWER_DATA ",upperdir=" UPPER_DATA + ",workdir=" UPPER_WORK)); clear_cap(_metadata, CAP_DAC_OVERRIDE); clear_cap(_metadata, CAP_SYS_ADMIN); } @@ -2513,9 +3500,9 @@ TEST_F_FORK(layout2_overlay, no_restriction) ASSERT_EQ(0, test_open(merge_do1_fu3, O_RDONLY)); } -#define for_each_path(path_list, path_entry, i) \ - for (i = 0, path_entry = *path_list[i]; path_list[i]; \ - path_entry = *path_list[++i]) +#define for_each_path(path_list, path_entry, i) \ + for (i = 0, path_entry = *path_list[i]; path_list[i]; \ + path_entry = *path_list[++i]) TEST_F_FORK(layout2_overlay, same_content_different_file) { @@ -2533,7 +3520,7 @@ TEST_F_FORK(layout2_overlay, same_content_different_file) .path = MERGE_BASE, .access = ACCESS_RW, }, - {} + {}, }; const struct rule layer2_data[] = { { @@ -2548,7 +3535,7 @@ TEST_F_FORK(layout2_overlay, same_content_different_file) .path = MERGE_DATA, .access = ACCESS_RW, }, - {} + {}, }; /* Sets access right on directories inside both layers. */ const struct rule layer3_subdirs[] = { @@ -2580,7 +3567,7 @@ TEST_F_FORK(layout2_overlay, same_content_different_file) .path = merge_do1, .access = ACCESS_RW, }, - {} + {}, }; /* Tighten access rights to the files. */ const struct rule layer4_files[] = { @@ -2611,37 +3598,37 @@ TEST_F_FORK(layout2_overlay, same_content_different_file) { .path = merge_dl1_fl2, .access = LANDLOCK_ACCESS_FS_READ_FILE | - LANDLOCK_ACCESS_FS_WRITE_FILE, + LANDLOCK_ACCESS_FS_WRITE_FILE, }, { .path = merge_du1_fu2, .access = LANDLOCK_ACCESS_FS_READ_FILE | - LANDLOCK_ACCESS_FS_WRITE_FILE, + LANDLOCK_ACCESS_FS_WRITE_FILE, }, { .path = merge_do1_fo2, .access = LANDLOCK_ACCESS_FS_READ_FILE | - LANDLOCK_ACCESS_FS_WRITE_FILE, + LANDLOCK_ACCESS_FS_WRITE_FILE, }, { .path = merge_do1_fl3, .access = LANDLOCK_ACCESS_FS_READ_FILE | - LANDLOCK_ACCESS_FS_WRITE_FILE, + LANDLOCK_ACCESS_FS_WRITE_FILE, }, { .path = merge_do1_fu3, .access = LANDLOCK_ACCESS_FS_READ_FILE | - LANDLOCK_ACCESS_FS_WRITE_FILE, + LANDLOCK_ACCESS_FS_WRITE_FILE, }, - {} + {}, }; const struct rule layer5_merge_only[] = { { .path = MERGE_DATA, .access = LANDLOCK_ACCESS_FS_READ_FILE | - LANDLOCK_ACCESS_FS_WRITE_FILE, + LANDLOCK_ACCESS_FS_WRITE_FILE, }, - {} + {}, }; int ruleset_fd; size_t i; @@ -2659,7 +3646,8 @@ TEST_F_FORK(layout2_overlay, same_content_different_file) ASSERT_EQ(EACCES, test_open(path_entry, O_WRONLY)); } for_each_path(lower_base_directories, path_entry, i) { - ASSERT_EQ(EACCES, test_open(path_entry, O_RDONLY | O_DIRECTORY)); + ASSERT_EQ(EACCES, + test_open(path_entry, O_RDONLY | O_DIRECTORY)); } for_each_path(lower_sub_files, path_entry, i) { ASSERT_EQ(0, test_open(path_entry, O_RDONLY)); @@ -2671,7 +3659,8 @@ TEST_F_FORK(layout2_overlay, same_content_different_file) ASSERT_EQ(EACCES, test_open(path_entry, O_WRONLY)); } for_each_path(upper_base_directories, path_entry, i) { - ASSERT_EQ(EACCES, test_open(path_entry, O_RDONLY | O_DIRECTORY)); + ASSERT_EQ(EACCES, + test_open(path_entry, O_RDONLY | O_DIRECTORY)); } for_each_path(upper_sub_files, path_entry, i) { ASSERT_EQ(0, test_open(path_entry, O_RDONLY)); @@ -2756,7 +3745,8 @@ TEST_F_FORK(layout2_overlay, same_content_different_file) ASSERT_EQ(EACCES, test_open(path_entry, O_RDWR)); } for_each_path(merge_base_directories, path_entry, i) { - ASSERT_EQ(EACCES, test_open(path_entry, O_RDONLY | O_DIRECTORY)); + ASSERT_EQ(EACCES, + test_open(path_entry, O_RDONLY | O_DIRECTORY)); } for_each_path(merge_sub_files, path_entry, i) { ASSERT_EQ(0, test_open(path_entry, O_RDWR)); @@ -2781,7 +3771,8 @@ TEST_F_FORK(layout2_overlay, same_content_different_file) ASSERT_EQ(EACCES, test_open(path_entry, O_RDWR)); } for_each_path(merge_base_directories, path_entry, i) { - ASSERT_EQ(EACCES, test_open(path_entry, O_RDONLY | O_DIRECTORY)); + ASSERT_EQ(EACCES, + test_open(path_entry, O_RDONLY | O_DIRECTORY)); } for_each_path(merge_sub_files, path_entry, i) { ASSERT_EQ(0, test_open(path_entry, O_RDWR)); diff --git a/tools/testing/selftests/landlock/ptrace_test.c b/tools/testing/selftests/landlock/ptrace_test.c index 15fbef9cc849..c28ef98ff3ac 100644 --- a/tools/testing/selftests/landlock/ptrace_test.c +++ b/tools/testing/selftests/landlock/ptrace_test.c @@ -26,9 +26,10 @@ static void create_domain(struct __test_metadata *const _metadata) .handled_access_fs = LANDLOCK_ACCESS_FS_MAKE_BLOCK, }; - ruleset_fd = landlock_create_ruleset(&ruleset_attr, - sizeof(ruleset_attr), 0); - EXPECT_LE(0, ruleset_fd) { + ruleset_fd = + landlock_create_ruleset(&ruleset_attr, sizeof(ruleset_attr), 0); + EXPECT_LE(0, ruleset_fd) + { TH_LOG("Failed to create a ruleset: %s", strerror(errno)); } EXPECT_EQ(0, prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0)); @@ -43,7 +44,7 @@ static int test_ptrace_read(const pid_t pid) int procenv_path_size, fd; procenv_path_size = snprintf(procenv_path, sizeof(procenv_path), - path_template, pid); + path_template, pid); if (procenv_path_size >= sizeof(procenv_path)) return E2BIG; @@ -59,9 +60,12 @@ static int test_ptrace_read(const pid_t pid) return 0; } -FIXTURE(hierarchy) { }; +/* clang-format off */ +FIXTURE(hierarchy) {}; +/* clang-format on */ -FIXTURE_VARIANT(hierarchy) { +FIXTURE_VARIANT(hierarchy) +{ const bool domain_both; const bool domain_parent; const bool domain_child; @@ -83,7 +87,9 @@ FIXTURE_VARIANT(hierarchy) { * \ P2 -> P1 : allow * 'P2 */ +/* clang-format off */ FIXTURE_VARIANT_ADD(hierarchy, allow_without_domain) { + /* clang-format on */ .domain_both = false, .domain_parent = false, .domain_child = false, @@ -98,7 +104,9 @@ FIXTURE_VARIANT_ADD(hierarchy, allow_without_domain) { * | P2 | * '------' */ +/* clang-format off */ FIXTURE_VARIANT_ADD(hierarchy, allow_with_one_domain) { + /* clang-format on */ .domain_both = false, .domain_parent = false, .domain_child = true, @@ -112,7 +120,9 @@ FIXTURE_VARIANT_ADD(hierarchy, allow_with_one_domain) { * ' * P2 */ +/* clang-format off */ FIXTURE_VARIANT_ADD(hierarchy, deny_with_parent_domain) { + /* clang-format on */ .domain_both = false, .domain_parent = true, .domain_child = false, @@ -127,7 +137,9 @@ FIXTURE_VARIANT_ADD(hierarchy, deny_with_parent_domain) { * | P2 | * '------' */ +/* clang-format off */ FIXTURE_VARIANT_ADD(hierarchy, deny_with_sibling_domain) { + /* clang-format on */ .domain_both = false, .domain_parent = true, .domain_child = true, @@ -142,7 +154,9 @@ FIXTURE_VARIANT_ADD(hierarchy, deny_with_sibling_domain) { * | P2 | * '-------------' */ +/* clang-format off */ FIXTURE_VARIANT_ADD(hierarchy, allow_sibling_domain) { + /* clang-format on */ .domain_both = true, .domain_parent = false, .domain_child = false, @@ -158,7 +172,9 @@ FIXTURE_VARIANT_ADD(hierarchy, allow_sibling_domain) { * | '------' | * '-----------------' */ +/* clang-format off */ FIXTURE_VARIANT_ADD(hierarchy, allow_with_nested_domain) { + /* clang-format on */ .domain_both = true, .domain_parent = false, .domain_child = true, @@ -174,7 +190,9 @@ FIXTURE_VARIANT_ADD(hierarchy, allow_with_nested_domain) { * | P2 | * '-----------------' */ +/* clang-format off */ FIXTURE_VARIANT_ADD(hierarchy, deny_with_nested_and_parent_domain) { + /* clang-format on */ .domain_both = true, .domain_parent = true, .domain_child = false, @@ -192,17 +210,21 @@ FIXTURE_VARIANT_ADD(hierarchy, deny_with_nested_and_parent_domain) { * | '------' | * '-----------------' */ +/* clang-format off */ FIXTURE_VARIANT_ADD(hierarchy, deny_with_forked_domain) { + /* clang-format on */ .domain_both = true, .domain_parent = true, .domain_child = true, }; FIXTURE_SETUP(hierarchy) -{ } +{ +} FIXTURE_TEARDOWN(hierarchy) -{ } +{ +} /* Test PTRACE_TRACEME and PTRACE_ATTACH for parent and child. */ TEST_F(hierarchy, trace) @@ -330,7 +352,7 @@ TEST_F(hierarchy, trace) ASSERT_EQ(1, write(pipe_parent[1], ".", 1)); ASSERT_EQ(child, waitpid(child, &status, 0)); if (WIFSIGNALED(status) || !WIFEXITED(status) || - WEXITSTATUS(status) != EXIT_SUCCESS) + WEXITSTATUS(status) != EXIT_SUCCESS) _metadata->passed = 0; } diff --git a/tools/testing/selftests/mqueue/mq_perf_tests.c b/tools/testing/selftests/mqueue/mq_perf_tests.c index b019e0b8221c..84fda3b49073 100644 --- a/tools/testing/selftests/mqueue/mq_perf_tests.c +++ b/tools/testing/selftests/mqueue/mq_perf_tests.c @@ -180,6 +180,9 @@ void shutdown(int exit_val, char *err_cause, int line_no) if (in_shutdown++) return; + /* Free the cpu_set allocated using CPU_ALLOC in main function */ + CPU_FREE(cpu_set); + for (i = 0; i < num_cpus_to_pin; i++) if (cpu_threads[i]) { pthread_kill(cpu_threads[i], SIGUSR1); @@ -551,6 +554,12 @@ int main(int argc, char *argv[]) perror("sysconf(_SC_NPROCESSORS_ONLN)"); exit(1); } + + if (getuid() != 0) + ksft_exit_skip("Not running as root, but almost all tests " + "require root in order to modify\nsystem settings. " + "Exiting.\n"); + cpus_online = min(MAX_CPUS, sysconf(_SC_NPROCESSORS_ONLN)); cpu_set = CPU_ALLOC(cpus_online); if (cpu_set == NULL) { @@ -589,7 +598,7 @@ int main(int argc, char *argv[]) cpu_set)) { fprintf(stderr, "Any given CPU may " "only be given once.\n"); - exit(1); + goto err_code; } else CPU_SET_S(cpus_to_pin[cpu], cpu_set_size, cpu_set); @@ -607,7 +616,7 @@ int main(int argc, char *argv[]) queue_path = malloc(strlen(option) + 2); if (!queue_path) { perror("malloc()"); - exit(1); + goto err_code; } queue_path[0] = '/'; queue_path[1] = 0; @@ -622,17 +631,12 @@ int main(int argc, char *argv[]) fprintf(stderr, "Must pass at least one CPU to continuous " "mode.\n"); poptPrintUsage(popt_context, stderr, 0); - exit(1); + goto err_code; } else if (!continuous_mode) { num_cpus_to_pin = 1; cpus_to_pin[0] = cpus_online - 1; } - if (getuid() != 0) - ksft_exit_skip("Not running as root, but almost all tests " - "require root in order to modify\nsystem settings. " - "Exiting.\n"); - max_msgs = fopen(MAX_MSGS, "r+"); max_msgsize = fopen(MAX_MSGSIZE, "r+"); if (!max_msgs) @@ -740,4 +744,9 @@ int main(int argc, char *argv[]) sleep(1); } shutdown(0, "", 0); + +err_code: + CPU_FREE(cpu_set); + exit(1); + } diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 3fe2515aa616..e1f998defd10 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -25,12 +25,13 @@ TEST_PROGS += bareudp.sh TEST_PROGS += amt.sh TEST_PROGS += unicast_extensions.sh TEST_PROGS += udpgro_fwd.sh +TEST_PROGS += udpgro_frglist.sh TEST_PROGS += veth.sh TEST_PROGS += ioam6.sh TEST_PROGS += gro.sh TEST_PROGS += gre_gso.sh TEST_PROGS += cmsg_so_mark.sh -TEST_PROGS += cmsg_time.sh +TEST_PROGS += cmsg_time.sh cmsg_ipv6.sh TEST_PROGS += srv6_end_dt46_l3vpn_test.sh TEST_PROGS += srv6_end_dt4_l3vpn_test.sh TEST_PROGS += srv6_end_dt6_l3vpn_test.sh @@ -54,12 +55,15 @@ TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict tls TEST_GEN_FILES += toeplitz TEST_GEN_FILES += cmsg_sender +TEST_PROGS += test_vxlan_vnifiltering.sh TEST_FILES := settings KSFT_KHDR_INSTALL := 1 include ../lib.mk +include bpf/Makefile + $(OUTPUT)/reuseport_bpf_numa: LDLIBS += -lnuma $(OUTPUT)/tcp_mmap: LDLIBS += -lpthread $(OUTPUT)/tcp_inq: LDLIBS += -lpthread diff --git a/tools/testing/selftests/net/bpf/Makefile b/tools/testing/selftests/net/bpf/Makefile new file mode 100644 index 000000000000..f91bf14bbee7 --- /dev/null +++ b/tools/testing/selftests/net/bpf/Makefile @@ -0,0 +1,14 @@ +# SPDX-License-Identifier: GPL-2.0 + +CLANG ?= clang +CCINCLUDE += -I../../bpf +CCINCLUDE += -I../../../../../usr/include/ + +TEST_CUSTOM_PROGS = $(OUTPUT)/bpf/nat6to4.o +all: $(TEST_CUSTOM_PROGS) + +$(OUTPUT)/%.o: %.c + $(CLANG) -O2 -target bpf -c $< $(CCINCLUDE) -o $@ + +clean: + rm -f $(TEST_CUSTOM_PROGS) diff --git a/tools/testing/selftests/net/bpf/nat6to4.c b/tools/testing/selftests/net/bpf/nat6to4.c new file mode 100644 index 000000000000..ac54c36b25fc --- /dev/null +++ b/tools/testing/selftests/net/bpf/nat6to4.c @@ -0,0 +1,285 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * This code is taken from the Android Open Source Project and the author + * (Maciej Żenczykowski) has gave permission to relicense it under the + * GPLv2. Therefore this program is free software; + * You can redistribute it and/or modify it under the terms of the GNU + * General Public License version 2 as published by the Free Software + * Foundation + + * The original headers, including the original license headers, are + * included below for completeness. + * + * Copyright (C) 2019 The Android Open Source Project + * + * Licensed under the Apache License, Version 2.0 (the "License"); + * you may not use this file except in compliance with the License. + * You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +#include <linux/bpf.h> +#include <linux/if.h> +#include <linux/if_ether.h> +#include <linux/if_packet.h> +#include <linux/in.h> +#include <linux/in6.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/pkt_cls.h> +#include <linux/swab.h> +#include <stdbool.h> +#include <stdint.h> + + +#include <linux/udp.h> + +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +#define IP_DF 0x4000 // Flag: "Don't Fragment" + +SEC("schedcls/ingress6/nat_6") +int sched_cls_ingress6_nat_6_prog(struct __sk_buff *skb) +{ + const int l2_header_size = sizeof(struct ethhdr); + void *data = (void *)(long)skb->data; + const void *data_end = (void *)(long)skb->data_end; + const struct ethhdr * const eth = data; // used iff is_ethernet + const struct ipv6hdr * const ip6 = (void *)(eth + 1); + + // Require ethernet dst mac address to be our unicast address. + if (skb->pkt_type != PACKET_HOST) + return TC_ACT_OK; + + // Must be meta-ethernet IPv6 frame + if (skb->protocol != bpf_htons(ETH_P_IPV6)) + return TC_ACT_OK; + + // Must have (ethernet and) ipv6 header + if (data + l2_header_size + sizeof(*ip6) > data_end) + return TC_ACT_OK; + + // Ethertype - if present - must be IPv6 + if (eth->h_proto != bpf_htons(ETH_P_IPV6)) + return TC_ACT_OK; + + // IP version must be 6 + if (ip6->version != 6) + return TC_ACT_OK; + // Maximum IPv6 payload length that can be translated to IPv4 + if (bpf_ntohs(ip6->payload_len) > 0xFFFF - sizeof(struct iphdr)) + return TC_ACT_OK; + switch (ip6->nexthdr) { + case IPPROTO_TCP: // For TCP & UDP the checksum neutrality of the chosen IPv6 + case IPPROTO_UDP: // address means there is no need to update their checksums. + case IPPROTO_GRE: // We do not need to bother looking at GRE/ESP headers, + case IPPROTO_ESP: // since there is never a checksum to update. + break; + default: // do not know how to handle anything else + return TC_ACT_OK; + } + + struct ethhdr eth2; // used iff is_ethernet + + eth2 = *eth; // Copy over the ethernet header (src/dst mac) + eth2.h_proto = bpf_htons(ETH_P_IP); // But replace the ethertype + + struct iphdr ip = { + .version = 4, // u4 + .ihl = sizeof(struct iphdr) / sizeof(__u32), // u4 + .tos = (ip6->priority << 4) + (ip6->flow_lbl[0] >> 4), // u8 + .tot_len = bpf_htons(bpf_ntohs(ip6->payload_len) + sizeof(struct iphdr)), // u16 + .id = 0, // u16 + .frag_off = bpf_htons(IP_DF), // u16 + .ttl = ip6->hop_limit, // u8 + .protocol = ip6->nexthdr, // u8 + .check = 0, // u16 + .saddr = 0x0201a8c0, // u32 + .daddr = 0x0101a8c0, // u32 + }; + + // Calculate the IPv4 one's complement checksum of the IPv4 header. + __wsum sum4 = 0; + + for (int i = 0; i < sizeof(ip) / sizeof(__u16); ++i) + sum4 += ((__u16 *)&ip)[i]; + + // Note that sum4 is guaranteed to be non-zero by virtue of ip.version == 4 + sum4 = (sum4 & 0xFFFF) + (sum4 >> 16); // collapse u32 into range 1 .. 0x1FFFE + sum4 = (sum4 & 0xFFFF) + (sum4 >> 16); // collapse any potential carry into u16 + ip.check = (__u16)~sum4; // sum4 cannot be zero, so this is never 0xFFFF + + // Calculate the *negative* IPv6 16-bit one's complement checksum of the IPv6 header. + __wsum sum6 = 0; + // We'll end up with a non-zero sum due to ip6->version == 6 (which has '0' bits) + for (int i = 0; i < sizeof(*ip6) / sizeof(__u16); ++i) + sum6 += ~((__u16 *)ip6)[i]; // note the bitwise negation + + // Note that there is no L4 checksum update: we are relying on the checksum neutrality + // of the ipv6 address chosen by netd's ClatdController. + + // Packet mutations begin - point of no return, but if this first modification fails + // the packet is probably still pristine, so let clatd handle it. + if (bpf_skb_change_proto(skb, bpf_htons(ETH_P_IP), 0)) + return TC_ACT_OK; + bpf_csum_update(skb, sum6); + + data = (void *)(long)skb->data; + data_end = (void *)(long)skb->data_end; + if (data + l2_header_size + sizeof(struct iphdr) > data_end) + return TC_ACT_SHOT; + + struct ethhdr *new_eth = data; + + // Copy over the updated ethernet header + *new_eth = eth2; + + // Copy over the new ipv4 header. + *(struct iphdr *)(new_eth + 1) = ip; + return bpf_redirect(skb->ifindex, BPF_F_INGRESS); +} + +SEC("schedcls/egress4/snat4") +int sched_cls_egress4_snat4_prog(struct __sk_buff *skb) +{ + const int l2_header_size = sizeof(struct ethhdr); + void *data = (void *)(long)skb->data; + const void *data_end = (void *)(long)skb->data_end; + const struct ethhdr *const eth = data; // used iff is_ethernet + const struct iphdr *const ip4 = (void *)(eth + 1); + + // Must be meta-ethernet IPv4 frame + if (skb->protocol != bpf_htons(ETH_P_IP)) + return TC_ACT_OK; + + // Must have ipv4 header + if (data + l2_header_size + sizeof(struct ipv6hdr) > data_end) + return TC_ACT_OK; + + // Ethertype - if present - must be IPv4 + if (eth->h_proto != bpf_htons(ETH_P_IP)) + return TC_ACT_OK; + + // IP version must be 4 + if (ip4->version != 4) + return TC_ACT_OK; + + // We cannot handle IP options, just standard 20 byte == 5 dword minimal IPv4 header + if (ip4->ihl != 5) + return TC_ACT_OK; + + // Maximum IPv6 payload length that can be translated to IPv4 + if (bpf_htons(ip4->tot_len) > 0xFFFF - sizeof(struct ipv6hdr)) + return TC_ACT_OK; + + // Calculate the IPv4 one's complement checksum of the IPv4 header. + __wsum sum4 = 0; + + for (int i = 0; i < sizeof(*ip4) / sizeof(__u16); ++i) + sum4 += ((__u16 *)ip4)[i]; + + // Note that sum4 is guaranteed to be non-zero by virtue of ip4->version == 4 + sum4 = (sum4 & 0xFFFF) + (sum4 >> 16); // collapse u32 into range 1 .. 0x1FFFE + sum4 = (sum4 & 0xFFFF) + (sum4 >> 16); // collapse any potential carry into u16 + // for a correct checksum we should get *a* zero, but sum4 must be positive, ie 0xFFFF + if (sum4 != 0xFFFF) + return TC_ACT_OK; + + // Minimum IPv4 total length is the size of the header + if (bpf_ntohs(ip4->tot_len) < sizeof(*ip4)) + return TC_ACT_OK; + + // We are incapable of dealing with IPv4 fragments + if (ip4->frag_off & ~bpf_htons(IP_DF)) + return TC_ACT_OK; + + switch (ip4->protocol) { + case IPPROTO_TCP: // For TCP & UDP the checksum neutrality of the chosen IPv6 + case IPPROTO_GRE: // address means there is no need to update their checksums. + case IPPROTO_ESP: // We do not need to bother looking at GRE/ESP headers, + break; // since there is never a checksum to update. + + case IPPROTO_UDP: // See above comment, but must also have UDP header... + if (data + sizeof(*ip4) + sizeof(struct udphdr) > data_end) + return TC_ACT_OK; + const struct udphdr *uh = (const struct udphdr *)(ip4 + 1); + // If IPv4/UDP checksum is 0 then fallback to clatd so it can calculate the + // checksum. Otherwise the network or more likely the NAT64 gateway might + // drop the packet because in most cases IPv6/UDP packets with a zero checksum + // are invalid. See RFC 6935. TODO: calculate checksum via bpf_csum_diff() + if (!uh->check) + return TC_ACT_OK; + break; + + default: // do not know how to handle anything else + return TC_ACT_OK; + } + struct ethhdr eth2; // used iff is_ethernet + + eth2 = *eth; // Copy over the ethernet header (src/dst mac) + eth2.h_proto = bpf_htons(ETH_P_IPV6); // But replace the ethertype + + struct ipv6hdr ip6 = { + .version = 6, // __u8:4 + .priority = ip4->tos >> 4, // __u8:4 + .flow_lbl = {(ip4->tos & 0xF) << 4, 0, 0}, // __u8[3] + .payload_len = bpf_htons(bpf_ntohs(ip4->tot_len) - 20), // __be16 + .nexthdr = ip4->protocol, // __u8 + .hop_limit = ip4->ttl, // __u8 + }; + ip6.saddr.in6_u.u6_addr32[0] = bpf_htonl(0x20010db8); + ip6.saddr.in6_u.u6_addr32[1] = 0; + ip6.saddr.in6_u.u6_addr32[2] = 0; + ip6.saddr.in6_u.u6_addr32[3] = bpf_htonl(1); + ip6.daddr.in6_u.u6_addr32[0] = bpf_htonl(0x20010db8); + ip6.daddr.in6_u.u6_addr32[1] = 0; + ip6.daddr.in6_u.u6_addr32[2] = 0; + ip6.daddr.in6_u.u6_addr32[3] = bpf_htonl(2); + + // Calculate the IPv6 16-bit one's complement checksum of the IPv6 header. + __wsum sum6 = 0; + // We'll end up with a non-zero sum due to ip6.version == 6 + for (int i = 0; i < sizeof(ip6) / sizeof(__u16); ++i) + sum6 += ((__u16 *)&ip6)[i]; + + // Packet mutations begin - point of no return, but if this first modification fails + // the packet is probably still pristine, so let clatd handle it. + if (bpf_skb_change_proto(skb, bpf_htons(ETH_P_IPV6), 0)) + return TC_ACT_OK; + + // This takes care of updating the skb->csum field for a CHECKSUM_COMPLETE packet. + // In such a case, skb->csum is a 16-bit one's complement sum of the entire payload, + // thus we need to subtract out the ipv4 header's sum, and add in the ipv6 header's sum. + // However, we've already verified the ipv4 checksum is correct and thus 0. + // Thus we only need to add the ipv6 header's sum. + // + // bpf_csum_update() always succeeds if the skb is CHECKSUM_COMPLETE and returns an error + // (-ENOTSUPP) if it isn't. So we just ignore the return code (see above for more details). + bpf_csum_update(skb, sum6); + + // bpf_skb_change_proto() invalidates all pointers - reload them. + data = (void *)(long)skb->data; + data_end = (void *)(long)skb->data_end; + + // I cannot think of any valid way for this error condition to trigger, however I do + // believe the explicit check is required to keep the in kernel ebpf verifier happy. + if (data + l2_header_size + sizeof(ip6) > data_end) + return TC_ACT_SHOT; + + struct ethhdr *new_eth = data; + + // Copy over the updated ethernet header + *new_eth = eth2; + // Copy over the new ipv4 header. + *(struct ipv6hdr *)(new_eth + 1) = ip6; + return TC_ACT_OK; +} + +char _license[] SEC("license") = ("GPL"); diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh index 47c4d4b4a44a..54701c8b0cd7 100755 --- a/tools/testing/selftests/net/fcnal-test.sh +++ b/tools/testing/selftests/net/fcnal-test.sh @@ -810,10 +810,16 @@ ipv4_ping() setup set_sysctl net.ipv4.raw_l3mdev_accept=1 2>/dev/null ipv4_ping_novrf + setup + set_sysctl net.ipv4.ping_group_range='0 2147483647' 2>/dev/null + ipv4_ping_novrf log_subsection "With VRF" setup "yes" ipv4_ping_vrf + setup "yes" + set_sysctl net.ipv4.ping_group_range='0 2147483647' 2>/dev/null + ipv4_ping_vrf } ################################################################################ @@ -2348,10 +2354,16 @@ ipv6_ping() log_subsection "No VRF" setup ipv6_ping_novrf + setup + set_sysctl net.ipv4.ping_group_range='0 2147483647' 2>/dev/null + ipv6_ping_novrf log_subsection "With VRF" setup "yes" ipv6_ping_vrf + setup "yes" + set_sysctl net.ipv4.ping_group_range='0 2147483647' 2>/dev/null + ipv6_ping_vrf } ################################################################################ diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh index d444ee6aa3cb..b3bf5319bb0e 100755 --- a/tools/testing/selftests/net/fib_nexthops.sh +++ b/tools/testing/selftests/net/fib_nexthops.sh @@ -1208,6 +1208,20 @@ ipv4_fcnal() set +e check_nexthop "dev veth1" "" log_test $? 0 "Nexthops removed on admin down" + + # nexthop route delete warning: route add with nhid and delete + # using device + run_cmd "$IP li set dev veth1 up" + run_cmd "$IP nexthop add id 12 via 172.16.1.3 dev veth1" + out1=`dmesg | grep "WARNING:.*fib_nh_match.*" | wc -l` + run_cmd "$IP route add 172.16.101.1/32 nhid 12" + run_cmd "$IP route delete 172.16.101.1/32 dev veth1" + out2=`dmesg | grep "WARNING:.*fib_nh_match.*" | wc -l` + [ $out1 -eq $out2 ] + rc=$? + log_test $rc 0 "Delete nexthop route warning" + run_cmd "$IP route delete 172.16.101.1/32 nhid 12" + run_cmd "$IP nexthop del id 12" } ipv4_grp_fcnal() diff --git a/tools/testing/selftests/net/forwarding/Makefile b/tools/testing/selftests/net/forwarding/Makefile index 8fa97ae9af9e..e811090f7748 100644 --- a/tools/testing/selftests/net/forwarding/Makefile +++ b/tools/testing/selftests/net/forwarding/Makefile @@ -2,15 +2,31 @@ TEST_PROGS = bridge_igmp.sh \ bridge_locked_port.sh \ + bridge_mld.sh \ bridge_port_isolation.sh \ bridge_sticky_fdb.sh \ bridge_vlan_aware.sh \ + bridge_vlan_mcast.sh \ bridge_vlan_unaware.sh \ + custom_multipath_hash.sh \ + dual_vxlan_bridge.sh \ + ethtool_extended_state.sh \ ethtool.sh \ + gre_custom_multipath_hash.sh \ gre_inner_v4_multipath.sh \ gre_inner_v6_multipath.sh \ + gre_multipath_nh_res.sh \ + gre_multipath_nh.sh \ gre_multipath.sh \ + hw_stats_l3.sh \ ip6_forward_instats_vrf.sh \ + ip6gre_custom_multipath_hash.sh \ + ip6gre_flat_key.sh \ + ip6gre_flat_keys.sh \ + ip6gre_flat.sh \ + ip6gre_hier_key.sh \ + ip6gre_hier_keys.sh \ + ip6gre_hier.sh \ ip6gre_inner_v4_multipath.sh \ ip6gre_inner_v6_multipath.sh \ ipip_flat_gre_key.sh \ @@ -34,36 +50,53 @@ TEST_PROGS = bridge_igmp.sh \ mirror_gre_vlan_bridge_1q.sh \ mirror_gre_vlan.sh \ mirror_vlan.sh \ + pedit_dsfield.sh \ + pedit_ip.sh \ + pedit_l4port.sh \ + q_in_vni_ipv6.sh \ + q_in_vni.sh \ router_bridge.sh \ router_bridge_vlan.sh \ router_broadcast.sh \ + router_mpath_nh_res.sh \ router_mpath_nh.sh \ router_multicast.sh \ router_multipath.sh \ + router_nh.sh \ router.sh \ router_vid_1.sh \ sch_ets.sh \ + sch_red.sh \ sch_tbf_ets.sh \ sch_tbf_prio.sh \ sch_tbf_root.sh \ + skbedit_priority.sh \ tc_actions.sh \ tc_chains.sh \ tc_flower_router.sh \ tc_flower.sh \ tc_mpls_l2vpn.sh \ + tc_police.sh \ tc_shblocks.sh \ tc_vlan_modify.sh \ + vxlan_asymmetric_ipv6.sh \ vxlan_asymmetric.sh \ + vxlan_bridge_1d_ipv6.sh \ + vxlan_bridge_1d_port_8472_ipv6.sh \ vxlan_bridge_1d_port_8472.sh \ vxlan_bridge_1d.sh \ + vxlan_bridge_1q_ipv6.sh \ + vxlan_bridge_1q_port_8472_ipv6.sh \ vxlan_bridge_1q_port_8472.sh \ vxlan_bridge_1q.sh \ + vxlan_symmetric_ipv6.sh \ vxlan_symmetric.sh TEST_PROGS_EXTENDED := devlink_lib.sh \ ethtool_lib.sh \ fib_offload_lib.sh \ forwarding.config.sample \ + ip6gre_lib.sh \ ipip_lib.sh \ lib.sh \ mirror_gre_lib.sh \ diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q.sh b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q.sh index a3402cd8d5b6..9ff22f28032d 100755 --- a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q.sh +++ b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q.sh @@ -61,9 +61,12 @@ setup_prepare() vrf_prepare mirror_gre_topo_create + # Avoid changing br1's PVID while it is operational as a L3 interface. + ip link set dev br1 down ip link set dev $swp3 master br1 bridge vlan add dev br1 vid 555 pvid untagged self + ip link set dev br1 up ip address add dev br1 192.0.2.129/28 ip address add dev br1 2001:db8:2::1/64 diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 7314257d248a..48ef112f42c2 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -1444,6 +1444,33 @@ chk_prio_nr() [ "${dump_stats}" = 1 ] && dump_stats } +chk_subflow_nr() +{ + local need_title="$1" + local msg="$2" + local subflow_nr=$3 + local cnt1 + local cnt2 + + if [ -n "${need_title}" ]; then + printf "%03u %-36s %s" "${TEST_COUNT}" "${TEST_NAME}" "${msg}" + else + printf "%-${nr_blank}s %s" " " "${msg}" + fi + + cnt1=$(ss -N $ns1 -tOni | grep -c token) + cnt2=$(ss -N $ns2 -tOni | grep -c token) + if [ "$cnt1" != "$subflow_nr" -o "$cnt2" != "$subflow_nr" ]; then + echo "[fail] got $cnt1:$cnt2 subflows expected $subflow_nr" + fail_test + dump_stats=1 + else + echo "[ ok ]" + fi + + [ "${dump_stats}" = 1 ] && ( ss -N $ns1 -tOni ; ss -N $ns1 -tOni | grep token; ip -n $ns1 mptcp endpoint ) +} + chk_link_usage() { local ns=$1 @@ -2556,7 +2583,7 @@ fastclose_tests() fi } -implicit_tests() +endpoint_tests() { # userspace pm type prevents add_addr if reset "implicit EP"; then @@ -2578,6 +2605,23 @@ implicit_tests() $ns2 10.0.2.2 id 1 flags signal wait fi + + if reset "delete and re-add"; then + pm_nl_set_limits $ns1 1 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns2 10.0.2.2 id 2 dev ns2eth2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 4 0 0 slow & + + wait_mpj $ns2 + pm_nl_del_endpoint $ns2 2 10.0.2.2 + sleep 0.5 + chk_subflow_nr needtitle "after delete" 1 + + pm_nl_add_endpoint $ns2 10.0.2.2 dev ns2eth2 flags subflow + wait_mpj $ns2 + chk_subflow_nr "" "after re-add" 2 + wait + fi } # [$1: error message] @@ -2624,7 +2668,7 @@ all_tests_sorted=( d@deny_join_id0_tests m@fullmesh_tests z@fastclose_tests - I@implicit_tests + I@endpoint_tests ) all_tests_args="" diff --git a/tools/testing/selftests/net/so_txtime.c b/tools/testing/selftests/net/so_txtime.c index 59067f64b775..2672ac0b6d1f 100644 --- a/tools/testing/selftests/net/so_txtime.c +++ b/tools/testing/selftests/net/so_txtime.c @@ -421,7 +421,7 @@ static void usage(const char *progname) "Options:\n" " -4 only IPv4\n" " -6 only IPv6\n" - " -c <clock> monotonic (default) or tai\n" + " -c <clock> monotonic or tai (default)\n" " -D <addr> destination IP address (server)\n" " -S <addr> source IP address (client)\n" " -r run rx mode\n" @@ -475,7 +475,7 @@ static void parse_opts(int argc, char **argv) cfg_rx = true; break; case 't': - cfg_start_time_ns = strtol(optarg, NULL, 0); + cfg_start_time_ns = strtoll(optarg, NULL, 0); break; case 'm': cfg_mark = strtol(optarg, NULL, 0); diff --git a/tools/testing/selftests/net/udpgro_frglist.sh b/tools/testing/selftests/net/udpgro_frglist.sh new file mode 100755 index 000000000000..807b74c8fd80 --- /dev/null +++ b/tools/testing/selftests/net/udpgro_frglist.sh @@ -0,0 +1,101 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Run a series of udpgro benchmarks + +readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)" + +cleanup() { + local -r jobs="$(jobs -p)" + local -r ns="$(ip netns list|grep $PEER_NS)" + + [ -n "${jobs}" ] && kill -INT ${jobs} 2>/dev/null + [ -n "$ns" ] && ip netns del $ns 2>/dev/null +} +trap cleanup EXIT + +run_one() { + # use 'rx' as separator between sender args and receiver args + local -r all="$@" + local -r tx_args=${all%rx*} + local rx_args=${all#*rx} + + + + ip netns add "${PEER_NS}" + ip -netns "${PEER_NS}" link set lo up + ip link add type veth + ip link set dev veth0 up + ip addr add dev veth0 192.168.1.2/24 + ip addr add dev veth0 2001:db8::2/64 nodad + + ip link set dev veth1 netns "${PEER_NS}" + ip -netns "${PEER_NS}" addr add dev veth1 192.168.1.1/24 + ip -netns "${PEER_NS}" addr add dev veth1 2001:db8::1/64 nodad + ip -netns "${PEER_NS}" link set dev veth1 up + ip netns exec "${PEER_NS}" ethtool -K veth1 rx-gro-list on + + + ip -n "${PEER_NS}" link set veth1 xdp object ../bpf/xdp_dummy.o section xdp_dummy + tc -n "${PEER_NS}" qdisc add dev veth1 clsact + tc -n "${PEER_NS}" filter add dev veth1 ingress prio 4 protocol ipv6 bpf object-file ../bpf/nat6to4.o section schedcls/ingress6/nat_6 direct-action + tc -n "${PEER_NS}" filter add dev veth1 egress prio 4 protocol ip bpf object-file ../bpf/nat6to4.o section schedcls/egress4/snat4 direct-action + echo ${rx_args} + ip netns exec "${PEER_NS}" ./udpgso_bench_rx ${rx_args} -r & + + # Hack: let bg programs complete the startup + sleep 0.1 + ./udpgso_bench_tx ${tx_args} +} + +run_in_netns() { + local -r args=$@ + echo ${args} + ./in_netns.sh $0 __subprocess ${args} +} + +run_udp() { + local -r args=$@ + + echo "udp gso - over veth touching data" + run_in_netns ${args} -u -S 0 rx -4 -v + + echo "udp gso and gro - over veth touching data" + run_in_netns ${args} -S 0 rx -4 -G +} + +run_tcp() { + local -r args=$@ + + echo "tcp - over veth touching data" + run_in_netns ${args} -t rx -4 -t +} + +run_all() { + local -r core_args="-l 4" + local -r ipv4_args="${core_args} -4 -D 192.168.1.1" + local -r ipv6_args="${core_args} -6 -D 2001:db8::1" + + echo "ipv6" + run_tcp "${ipv6_args}" + run_udp "${ipv6_args}" +} + +if [ ! -f ../bpf/xdp_dummy.o ]; then + echo "Missing xdp_dummy helper. Build bpf selftest first" + exit -1 +fi + +if [ ! -f bpf/nat6to4.o ]; then + echo "Missing nat6to4 helper. Build bpfnat6to4.o selftest first" + exit -1 +fi + +if [[ $# -eq 0 ]]; then + run_all +elif [[ $1 == "__subprocess" ]]; then + shift + run_one $@ +else + run_in_netns $@ +fi diff --git a/tools/testing/selftests/pid_namespace/Makefile b/tools/testing/selftests/pid_namespace/Makefile index dcaefa224ca0..edafaca1aeb3 100644 --- a/tools/testing/selftests/pid_namespace/Makefile +++ b/tools/testing/selftests/pid_namespace/Makefile @@ -1,8 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 CFLAGS += -g -I../../../../usr/include/ -TEST_GEN_PROGS := regression_enomem +TEST_GEN_PROGS = regression_enomem -include ../lib.mk +LOCAL_HDRS += $(selfdir)/pidfd/pidfd.h -$(OUTPUT)/regression_enomem: regression_enomem.c ../pidfd/pidfd.h +include ../lib.mk diff --git a/tools/testing/selftests/pidfd/pidfd_wait.c b/tools/testing/selftests/pidfd/pidfd_wait.c index 17999e082aa7..070c1c876df1 100644 --- a/tools/testing/selftests/pidfd/pidfd_wait.c +++ b/tools/testing/selftests/pidfd/pidfd_wait.c @@ -95,7 +95,6 @@ TEST(wait_states) .flags = CLONE_PIDFD | CLONE_PARENT_SETTID, .exit_signal = SIGCHLD, }; - int ret; pid_t pid; siginfo_t info = { .si_signo = 0, diff --git a/tools/testing/selftests/proc/proc-pid-vm.c b/tools/testing/selftests/proc/proc-pid-vm.c index 18a3bde8bc96..28604c9f805c 100644 --- a/tools/testing/selftests/proc/proc-pid-vm.c +++ b/tools/testing/selftests/proc/proc-pid-vm.c @@ -46,6 +46,8 @@ #include <sys/time.h> #include <sys/resource.h> +#include "../kselftest.h" + static inline long sys_execveat(int dirfd, const char *pathname, char **argv, char **envp, int flags) { return syscall(SYS_execveat, dirfd, pathname, argv, envp, flags); @@ -368,7 +370,7 @@ int main(void) }; int i; - for (i = 0; i < sizeof(S)/sizeof(S[0]); i++) { + for (i = 0; i < ARRAY_SIZE(S); i++) { assert(memmem(buf, rv, S[i], strlen(S[i]))); } @@ -417,7 +419,7 @@ int main(void) }; int i; - for (i = 0; i < sizeof(S)/sizeof(S[0]); i++) { + for (i = 0; i < ARRAY_SIZE(S); i++) { assert(memmem(buf, rv, S[i], strlen(S[i]))); } } diff --git a/tools/testing/selftests/rcutorture/bin/functions.sh b/tools/testing/selftests/rcutorture/bin/functions.sh index c35ba24f994c..66d0414d8e4b 100644 --- a/tools/testing/selftests/rcutorture/bin/functions.sh +++ b/tools/testing/selftests/rcutorture/bin/functions.sh @@ -301,7 +301,7 @@ specify_qemu_cpus () { echo $2 -smp $3 ;; qemu-system-ppc64) - nt="`lscpu | grep '^NUMA node0' | sed -e 's/^[^,]*,\([0-9]*\),.*$/\1/'`" + nt="`lscpu | sed -n 's/^Thread(s) per core:\s*//p'`" echo $2 -smp cores=`expr \( $3 + $nt - 1 \) / $nt`,threads=$nt ;; esac diff --git a/tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh b/tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh index 5f682fc892dd..88983cba7956 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh @@ -36,7 +36,7 @@ do then egrep "error:|warning:|^ld: .*undefined reference to" < $i > $i.diags files="$files $i.diags $i" - elif ! test -f ${scenariobasedir}/vmlinux + elif ! test -f ${scenariobasedir}/vmlinux && ! test -f "${rundir}/re-run" then echo No ${scenariobasedir}/vmlinux file > $i.diags files="$files $i.diags $i" diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh index 0a5419982ab3..0789c5606d2a 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh @@ -33,7 +33,12 @@ do TORTURE_SUITE="`cat $i/../torture_suite`" configfile=`echo $i | sed -e 's,^.*/,,'` rm -f $i/console.log.*.diags - kvm-recheck-${TORTURE_SUITE}.sh $i + case "${TORTURE_SUITE}" in + X*) + ;; + *) + kvm-recheck-${TORTURE_SUITE}.sh $i + esac if test -f "$i/qemu-retval" && test "`cat $i/qemu-retval`" -ne 0 && test "`cat $i/qemu-retval`" -ne 137 then echo QEMU error, output: diff --git a/tools/testing/selftests/rcutorture/bin/kvm-remote.sh b/tools/testing/selftests/rcutorture/bin/kvm-remote.sh index 8c4c1e4792d0..0ff59bd8b640 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-remote.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-remote.sh @@ -138,14 +138,14 @@ chmod +x $T/bin/kvm-remote-*.sh # Check first to avoid the need for cleanup for system-name typos for i in $systems do - ncpus="`ssh $i getconf _NPROCESSORS_ONLN 2> /dev/null`" - echo $i: $ncpus CPUs " " `date` | tee -a "$oldrun/remote-log" + ncpus="`ssh -o BatchMode=yes $i getconf _NPROCESSORS_ONLN 2> /dev/null`" ret=$? if test "$ret" -ne 0 then echo System $i unreachable, giving up. | tee -a "$oldrun/remote-log" exit 4 fi + echo $i: $ncpus CPUs " " `date` | tee -a "$oldrun/remote-log" done # Download and expand the tarball on all systems. @@ -153,14 +153,14 @@ echo Build-products tarball: `du -h $T/binres.tgz` | tee -a "$oldrun/remote-log" for i in $systems do echo Downloading tarball to $i `date` | tee -a "$oldrun/remote-log" - cat $T/binres.tgz | ssh $i "cd /tmp; tar -xzf -" + cat $T/binres.tgz | ssh -o BatchMode=yes $i "cd /tmp; tar -xzf -" ret=$? tries=0 while test "$ret" -ne 0 do echo Unable to download $T/binres.tgz to system $i, waiting and then retrying. $tries prior retries. | tee -a "$oldrun/remote-log" sleep 60 - cat $T/binres.tgz | ssh $i "cd /tmp; tar -xzf -" + cat $T/binres.tgz | ssh -o BatchMode=yes $i "cd /tmp; tar -xzf -" ret=$? if test "$ret" -ne 0 then @@ -185,7 +185,7 @@ checkremotefile () { while : do - ssh $1 "test -f \"$2\"" + ssh -o BatchMode=yes $1 "test -f \"$2\"" ret=$? if test "$ret" -eq 255 then @@ -228,7 +228,7 @@ startbatches () { then continue # System still running last test, skip. fi - ssh "$i" "cd \"$resdir/$ds\"; touch remote.run; PATH=\"$T/bin:$PATH\" nohup kvm-remote-$curbatch.sh > kvm-remote-$curbatch.sh.out 2>&1 &" 1>&2 + ssh -o BatchMode=yes "$i" "cd \"$resdir/$ds\"; touch remote.run; PATH=\"$T/bin:$PATH\" nohup kvm-remote-$curbatch.sh > kvm-remote-$curbatch.sh.out 2>&1 &" 1>&2 ret=$? if test "$ret" -ne 0 then @@ -267,7 +267,7 @@ do sleep 30 done echo " ---" Collecting results from $i `date` | tee -a "$oldrun/remote-log" - ( cd "$oldrun"; ssh $i "cd $rundir; tar -czf - kvm-remote-*.sh.out */console.log */kvm-test-1-run*.sh.out */qemu[_-]pid */qemu-retval */qemu-affinity; rm -rf $T > /dev/null 2>&1" | tar -xzf - ) + ( cd "$oldrun"; ssh -o BatchMode=yes $i "cd $rundir; tar -czf - kvm-remote-*.sh.out */console.log */kvm-test-1-run*.sh.out */qemu[_-]pid */qemu-retval */qemu-affinity; rm -rf $T > /dev/null 2>&1" | tar -xzf - ) done ( kvm-end-run-stats.sh "$oldrun" "$starttime"; echo $? > $T/exitcode ) | tee -a "$oldrun/remote-log" diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh index 55b2c1533282..263e16aeca0e 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm.sh @@ -44,6 +44,7 @@ TORTURE_KCONFIG_KASAN_ARG="" TORTURE_KCONFIG_KCSAN_ARG="" TORTURE_KMAKE_ARG="" TORTURE_QEMU_MEM=512 +torture_qemu_mem_default=1 TORTURE_REMOTE= TORTURE_SHUTDOWN_GRACE=180 TORTURE_SUITE=rcu @@ -86,7 +87,7 @@ usage () { echo " --remote" echo " --results absolute-pathname" echo " --shutdown-grace seconds" - echo " --torture lock|rcu|rcuscale|refscale|scf" + echo " --torture lock|rcu|rcuscale|refscale|scf|X*" echo " --trust-make" exit 1 } @@ -180,6 +181,10 @@ do ;; --kasan) TORTURE_KCONFIG_KASAN_ARG="CONFIG_DEBUG_INFO=y CONFIG_KASAN=y"; export TORTURE_KCONFIG_KASAN_ARG + if test -n "$torture_qemu_mem_default" + then + TORTURE_QEMU_MEM=2G + fi ;; --kconfig|--kconfigs) checkarg --kconfig "(Kconfig options)" $# "$2" '^CONFIG_[A-Z0-9_]\+=\([ynm]\|[0-9]\+\)\( CONFIG_[A-Z0-9_]\+=\([ynm]\|[0-9]\+\)\)*$' '^error$' @@ -202,6 +207,7 @@ do --memory) checkarg --memory "(memory size)" $# "$2" '^[0-9]\+[MG]\?$' error TORTURE_QEMU_MEM=$2 + torture_qemu_mem_default= shift ;; --no-initrd) @@ -231,7 +237,7 @@ do shift ;; --torture) - checkarg --torture "(suite name)" "$#" "$2" '^\(lock\|rcu\|rcuscale\|refscale\|scf\)$' '^--' + checkarg --torture "(suite name)" "$#" "$2" '^\(lock\|rcu\|rcuscale\|refscale\|scf\|X.*\)$' '^--' TORTURE_SUITE=$2 TORTURE_MOD="`echo $TORTURE_SUITE | sed -e 's/^\(lock\|rcu\|scf\)$/\1torture/'`" shift diff --git a/tools/testing/selftests/rcutorture/bin/torture.sh b/tools/testing/selftests/rcutorture/bin/torture.sh index bfe09e2829c8..d477618e7261 100755 --- a/tools/testing/selftests/rcutorture/bin/torture.sh +++ b/tools/testing/selftests/rcutorture/bin/torture.sh @@ -54,6 +54,7 @@ do_kvfree=yes do_kasan=yes do_kcsan=no do_clocksourcewd=yes +do_rt=yes # doyesno - Helper function for yes/no arguments function doyesno () { @@ -82,6 +83,7 @@ usage () { echo " --do-rcuscale / --do-no-rcuscale" echo " --do-rcutorture / --do-no-rcutorture" echo " --do-refscale / --do-no-refscale" + echo " --do-rt / --do-no-rt" echo " --do-scftorture / --do-no-scftorture" echo " --duration [ <minutes> | <hours>h | <days>d ]" echo " --kcsan-kmake-arg kernel-make-arguments" @@ -118,6 +120,7 @@ do do_scftorture=yes do_rcuscale=yes do_refscale=yes + do_rt=yes do_kvfree=yes do_kasan=yes do_kcsan=yes @@ -148,6 +151,7 @@ do do_scftorture=no do_rcuscale=no do_refscale=no + do_rt=no do_kvfree=no do_kasan=no do_kcsan=no @@ -162,6 +166,9 @@ do --do-refscale|--do-no-refscale) do_refscale=`doyesno "$1" --do-refscale` ;; + --do-rt|--do-no-rt) + do_rt=`doyesno "$1" --do-rt` + ;; --do-scftorture|--do-no-scftorture) do_scftorture=`doyesno "$1" --do-scftorture` ;; @@ -322,6 +329,7 @@ then echo " --- make clean" > "$amcdir/Make.out" 2>&1 make -j$MAKE_ALLOTED_CPUS clean >> "$amcdir/Make.out" 2>&1 echo " --- make allmodconfig" >> "$amcdir/Make.out" 2>&1 + cp .config $amcdir make -j$MAKE_ALLOTED_CPUS allmodconfig >> "$amcdir/Make.out" 2>&1 echo " --- make " >> "$amcdir/Make.out" 2>&1 make -j$MAKE_ALLOTED_CPUS >> "$amcdir/Make.out" 2>&1 @@ -350,8 +358,19 @@ fi if test "$do_scftorture" = "yes" then - torture_bootargs="scftorture.nthreads=$HALF_ALLOTED_CPUS torture.disable_onoff_at_boot" - torture_set "scftorture" tools/testing/selftests/rcutorture/bin/kvm.sh --torture scf --allcpus --duration "$duration_scftorture" --configs "$configs_scftorture" --kconfig "CONFIG_NR_CPUS=$HALF_ALLOTED_CPUS" --memory 1G --trust-make + torture_bootargs="scftorture.nthreads=$HALF_ALLOTED_CPUS torture.disable_onoff_at_boot csdlock_debug=1" + torture_set "scftorture" tools/testing/selftests/rcutorture/bin/kvm.sh --torture scf --allcpus --duration "$duration_scftorture" --configs "$configs_scftorture" --kconfig "CONFIG_NR_CPUS=$HALF_ALLOTED_CPUS" --memory 2G --trust-make +fi + +if test "$do_rt" = "yes" +then + # With all post-boot grace periods forced to normal. + torture_bootargs="rcupdate.rcu_cpu_stall_suppress_at_boot=1 torture.disable_onoff_at_boot rcupdate.rcu_task_stall_timeout=30000 rcupdate.rcu_normal=1" + torture_set "rcurttorture" tools/testing/selftests/rcutorture/bin/kvm.sh --allcpus --duration "$duration_rcutorture" --configs "TREE03" --trust-make + + # With all post-boot grace periods forced to expedited. + torture_bootargs="rcupdate.rcu_cpu_stall_suppress_at_boot=1 torture.disable_onoff_at_boot rcupdate.rcu_task_stall_timeout=30000 rcupdate.rcu_expedited=1" + torture_set "rcurttorture-exp" tools/testing/selftests/rcutorture/bin/kvm.sh --allcpus --duration "$duration_rcutorture" --configs "TREE03" --trust-make fi if test "$do_refscale" = yes @@ -363,7 +382,7 @@ fi for prim in $primlist do torture_bootargs="refscale.scale_type="$prim" refscale.nreaders=$HALF_ALLOTED_CPUS refscale.loops=10000 refscale.holdoff=20 torture.disable_onoff_at_boot" - torture_set "refscale-$prim" tools/testing/selftests/rcutorture/bin/kvm.sh --torture refscale --allcpus --duration 5 --kconfig "CONFIG_NR_CPUS=$HALF_ALLOTED_CPUS" --bootargs "verbose_batched=$VERBOSE_BATCH_CPUS torture.verbose_sleep_frequency=8 torture.verbose_sleep_duration=$VERBOSE_BATCH_CPUS" --trust-make + torture_set "refscale-$prim" tools/testing/selftests/rcutorture/bin/kvm.sh --torture refscale --allcpus --duration 5 --kconfig "CONFIG_TASKS_TRACE_RCU=y CONFIG_NR_CPUS=$HALF_ALLOTED_CPUS" --bootargs "verbose_batched=$VERBOSE_BATCH_CPUS torture.verbose_sleep_frequency=8 torture.verbose_sleep_duration=$VERBOSE_BATCH_CPUS" --trust-make done if test "$do_rcuscale" = yes @@ -375,13 +394,13 @@ fi for prim in $primlist do torture_bootargs="rcuscale.scale_type="$prim" rcuscale.nwriters=$HALF_ALLOTED_CPUS rcuscale.holdoff=20 torture.disable_onoff_at_boot" - torture_set "rcuscale-$prim" tools/testing/selftests/rcutorture/bin/kvm.sh --torture rcuscale --allcpus --duration 5 --kconfig "CONFIG_NR_CPUS=$HALF_ALLOTED_CPUS" --trust-make + torture_set "rcuscale-$prim" tools/testing/selftests/rcutorture/bin/kvm.sh --torture rcuscale --allcpus --duration 5 --kconfig "CONFIG_TASKS_TRACE_RCU=y CONFIG_NR_CPUS=$HALF_ALLOTED_CPUS" --trust-make done if test "$do_kvfree" = "yes" then torture_bootargs="rcuscale.kfree_rcu_test=1 rcuscale.kfree_nthreads=16 rcuscale.holdoff=20 rcuscale.kfree_loops=10000 torture.disable_onoff_at_boot" - torture_set "rcuscale-kvfree" tools/testing/selftests/rcutorture/bin/kvm.sh --torture rcuscale --allcpus --duration 10 --kconfig "CONFIG_NR_CPUS=$HALF_ALLOTED_CPUS" --memory 1G --trust-make + torture_set "rcuscale-kvfree" tools/testing/selftests/rcutorture/bin/kvm.sh --torture rcuscale --allcpus --duration 10 --kconfig "CONFIG_NR_CPUS=$HALF_ALLOTED_CPUS" --memory 2G --trust-make fi if test "$do_clocksourcewd" = "yes" diff --git a/tools/testing/selftests/rcutorture/configs/rcu/RUDE01 b/tools/testing/selftests/rcutorture/configs/rcu/RUDE01 index 7093422050f6..6fd6acb94518 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/RUDE01 +++ b/tools/testing/selftests/rcutorture/configs/rcu/RUDE01 @@ -8,3 +8,5 @@ CONFIG_DEBUG_LOCK_ALLOC=y CONFIG_PROVE_LOCKING=y #CHECK#CONFIG_PROVE_RCU=y CONFIG_RCU_EXPERT=y +CONFIG_FORCE_TASKS_RUDE_RCU=y +#CHECK#CONFIG_TASKS_RUDE_RCU=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N index 2da8b49589a0..07f5e0a70ae7 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N +++ b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N @@ -6,3 +6,5 @@ CONFIG_PREEMPT_NONE=y CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=n #CHECK#CONFIG_RCU_EXPERT=n +CONFIG_KPROBES=n +CONFIG_FTRACE=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TASKS01 b/tools/testing/selftests/rcutorture/configs/rcu/TASKS01 index 3ca112444ce7..d84801b9a7ae 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TASKS01 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TASKS01 @@ -7,4 +7,5 @@ CONFIG_PREEMPT=y CONFIG_DEBUG_LOCK_ALLOC=y CONFIG_PROVE_LOCKING=y #CHECK#CONFIG_PROVE_RCU=y +CONFIG_TASKS_RCU=y CONFIG_RCU_EXPERT=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TASKS02 b/tools/testing/selftests/rcutorture/configs/rcu/TASKS02 index ad2be91e5ee7..2f9fcffff5ae 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TASKS02 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TASKS02 @@ -2,3 +2,7 @@ CONFIG_SMP=n CONFIG_PREEMPT_NONE=y CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=n +CONFIG_PREEMPT_DYNAMIC=n +#CHECK#CONFIG_TASKS_RCU=y +CONFIG_FORCE_TASKS_RCU=y +CONFIG_RCU_EXPERT=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TASKS02.boot b/tools/testing/selftests/rcutorture/configs/rcu/TASKS02.boot index cd2a188eeb6d..b9b6d67cbc5f 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TASKS02.boot +++ b/tools/testing/selftests/rcutorture/configs/rcu/TASKS02.boot @@ -1 +1,2 @@ rcutorture.torture_type=tasks +rcutorture.stat_interval=60 diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TASKS03 b/tools/testing/selftests/rcutorture/configs/rcu/TASKS03 index dc02083803ce..dea26c568678 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TASKS03 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TASKS03 @@ -7,3 +7,5 @@ CONFIG_HZ_PERIODIC=n CONFIG_NO_HZ_IDLE=n CONFIG_NO_HZ_FULL=y #CHECK#CONFIG_RCU_EXPERT=n +CONFIG_TASKS_RCU=y +CONFIG_RCU_EXPERT=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TRACE01 b/tools/testing/selftests/rcutorture/configs/rcu/TRACE01 index e4d74e5fc1d0..85b407467454 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TRACE01 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TRACE01 @@ -4,8 +4,11 @@ CONFIG_HOTPLUG_CPU=y CONFIG_PREEMPT_NONE=y CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=n +CONFIG_PREEMPT_DYNAMIC=n CONFIG_DEBUG_LOCK_ALLOC=n CONFIG_PROVE_LOCKING=n #CHECK#CONFIG_PROVE_RCU=n +CONFIG_FORCE_TASKS_TRACE_RCU=y +#CHECK#CONFIG_TASKS_TRACE_RCU=y CONFIG_TASKS_TRACE_RCU_READ_MB=y CONFIG_RCU_EXPERT=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TRACE02 b/tools/testing/selftests/rcutorture/configs/rcu/TRACE02 index 77541eeb4e9f..093ea6e8e65c 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TRACE02 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TRACE02 @@ -7,5 +7,7 @@ CONFIG_PREEMPT=y CONFIG_DEBUG_LOCK_ALLOC=y CONFIG_PROVE_LOCKING=y #CHECK#CONFIG_PROVE_RCU=y +CONFIG_FORCE_TASKS_TRACE_RCU=y +#CHECK#CONFIG_TASKS_TRACE_RCU=y CONFIG_TASKS_TRACE_RCU_READ_MB=n CONFIG_RCU_EXPERT=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE04 b/tools/testing/selftests/rcutorture/configs/rcu/TREE04 index 22ad0261728d..ae395981b5e5 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE04 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE04 @@ -1,8 +1,9 @@ CONFIG_SMP=y CONFIG_NR_CPUS=8 -CONFIG_PREEMPT_NONE=y -CONFIG_PREEMPT_VOLUNTARY=n +CONFIG_PREEMPT_NONE=n +CONFIG_PREEMPT_VOLUNTARY=y CONFIG_PREEMPT=n +CONFIG_PREEMPT_DYNAMIC=n #CHECK#CONFIG_TREE_RCU=y CONFIG_HZ_PERIODIC=n CONFIG_NO_HZ_IDLE=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE07 b/tools/testing/selftests/rcutorture/configs/rcu/TREE07 index 2789b47e4ecd..d30922d8c883 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE07 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE07 @@ -3,6 +3,7 @@ CONFIG_NR_CPUS=16 CONFIG_PREEMPT_NONE=y CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=n +CONFIG_PREEMPT_DYNAMIC=n #CHECK#CONFIG_TREE_RCU=y CONFIG_HZ_PERIODIC=n CONFIG_NO_HZ_IDLE=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE09 b/tools/testing/selftests/rcutorture/configs/rcu/TREE09 index 8523a7515cbf..fc45645bb5f4 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE09 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE09 @@ -13,3 +13,5 @@ CONFIG_DEBUG_LOCK_ALLOC=n CONFIG_RCU_BOOST=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n #CHECK#CONFIG_RCU_EXPERT=n +CONFIG_KPROBES=n +CONFIG_FTRACE=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE10 b/tools/testing/selftests/rcutorture/configs/rcu/TREE10 index 4a00539bfdd7..a323d8948b7c 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE10 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE10 @@ -3,6 +3,7 @@ CONFIG_NR_CPUS=56 CONFIG_PREEMPT_NONE=y CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=n +CONFIG_PREEMPT_DYNAMIC=n #CHECK#CONFIG_TREE_RCU=y CONFIG_HZ_PERIODIC=n CONFIG_NO_HZ_IDLE=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh index effa415f9b92..e2bc99c785e7 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh +++ b/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh @@ -9,7 +9,7 @@ # rcutorture_param_n_barrier_cbs bootparam-string # -# Adds n_barrier_cbs rcutorture module parameter to kernels having it. +# Adds n_barrier_cbs rcutorture module parameter if not already specified. rcutorture_param_n_barrier_cbs () { if echo $1 | grep -q "rcutorture\.n_barrier_cbs" then @@ -30,13 +30,25 @@ rcutorture_param_onoff () { fi } +# rcutorture_param_stat_interval bootparam-string +# +# Adds stat_interval rcutorture module parameter if not already specified. +rcutorture_param_stat_interval () { + if echo $1 | grep -q "rcutorture\.stat_interval" + then + : + else + echo rcutorture.stat_interval=15 + fi +} + # per_version_boot_params bootparam-string config-file seconds # # Adds per-version torture-module parameters to kernels supporting them. per_version_boot_params () { echo $1 `rcutorture_param_onoff "$1" "$2"` \ `rcutorture_param_n_barrier_cbs "$1"` \ - rcutorture.stat_interval=15 \ + `rcutorture_param_stat_interval "$1"` \ rcutorture.shutdown_secs=$3 \ rcutorture.test_no_idle_hz=1 \ rcutorture.verbose=1 diff --git a/tools/testing/selftests/rcutorture/configs/rcuscale/CFcommon b/tools/testing/selftests/rcutorture/configs/rcuscale/CFcommon index 90942bb5bebc..6a00157bee5b 100644 --- a/tools/testing/selftests/rcutorture/configs/rcuscale/CFcommon +++ b/tools/testing/selftests/rcutorture/configs/rcuscale/CFcommon @@ -1,5 +1,6 @@ CONFIG_RCU_SCALE_TEST=y CONFIG_PRINTK_TIME=y -CONFIG_TASKS_RCU_GENERIC=y -CONFIG_TASKS_RCU=y -CONFIG_TASKS_TRACE_RCU=y +CONFIG_FORCE_TASKS_RCU=y +#CHECK#CONFIG_TASKS_RCU=y +CONFIG_FORCE_TASKS_TRACE_RCU=y +#CHECK#CONFIG_TASKS_TRACE_RCU=y diff --git a/tools/testing/selftests/rcutorture/configs/rcuscale/TREE b/tools/testing/selftests/rcutorture/configs/rcuscale/TREE index f110d9ffbe4c..b10706fd03a4 100644 --- a/tools/testing/selftests/rcutorture/configs/rcuscale/TREE +++ b/tools/testing/selftests/rcutorture/configs/rcuscale/TREE @@ -16,3 +16,5 @@ CONFIG_RCU_BOOST=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n CONFIG_RCU_EXPERT=y CONFIG_RCU_TRACE=y +CONFIG_KPROBES=n +CONFIG_FTRACE=n diff --git a/tools/testing/selftests/rcutorture/configs/refscale/CFcommon b/tools/testing/selftests/rcutorture/configs/refscale/CFcommon index a98b58b54bb1..fbea3b13baba 100644 --- a/tools/testing/selftests/rcutorture/configs/refscale/CFcommon +++ b/tools/testing/selftests/rcutorture/configs/refscale/CFcommon @@ -1,2 +1,6 @@ CONFIG_RCU_REF_SCALE_TEST=y CONFIG_PRINTK_TIME=y +CONFIG_FORCE_TASKS_RCU=y +#CHECK#CONFIG_TASKS_RCU=y +CONFIG_FORCE_TASKS_TRACE_RCU=y +#CHECK#CONFIG_TASKS_TRACE_RCU=y diff --git a/tools/testing/selftests/rcutorture/configs/refscale/NOPREEMPT b/tools/testing/selftests/rcutorture/configs/refscale/NOPREEMPT index 7f06838a91e6..ef2b501a6971 100644 --- a/tools/testing/selftests/rcutorture/configs/refscale/NOPREEMPT +++ b/tools/testing/selftests/rcutorture/configs/refscale/NOPREEMPT @@ -15,3 +15,5 @@ CONFIG_PROVE_LOCKING=n CONFIG_RCU_BOOST=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n CONFIG_RCU_EXPERT=y +CONFIG_KPROBES=n +CONFIG_FTRACE=n diff --git a/tools/testing/selftests/rcutorture/configs/scf/NOPREEMPT b/tools/testing/selftests/rcutorture/configs/scf/NOPREEMPT index b8429d6c6ebc..3a59346b3de7 100644 --- a/tools/testing/selftests/rcutorture/configs/scf/NOPREEMPT +++ b/tools/testing/selftests/rcutorture/configs/scf/NOPREEMPT @@ -7,3 +7,5 @@ CONFIG_NO_HZ_IDLE=n CONFIG_NO_HZ_FULL=y CONFIG_DEBUG_LOCK_ALLOC=n CONFIG_PROVE_LOCKING=n +CONFIG_KPROBES=n +CONFIG_FTRACE=n diff --git a/tools/testing/selftests/rcutorture/configs/scf/PREEMPT b/tools/testing/selftests/rcutorture/configs/scf/PREEMPT index ae4992b141b0..cb37e08037d6 100644 --- a/tools/testing/selftests/rcutorture/configs/scf/PREEMPT +++ b/tools/testing/selftests/rcutorture/configs/scf/PREEMPT @@ -7,3 +7,4 @@ CONFIG_NO_HZ_IDLE=y CONFIG_NO_HZ_FULL=n CONFIG_DEBUG_LOCK_ALLOC=y CONFIG_PROVE_LOCKING=y +CONFIG_RCU_EXPERT=y diff --git a/tools/testing/selftests/rcutorture/configs/scf/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/scf/ver_functions.sh index d3d9e35d3d55..2d949e58f5a5 100644 --- a/tools/testing/selftests/rcutorture/configs/scf/ver_functions.sh +++ b/tools/testing/selftests/rcutorture/configs/scf/ver_functions.sh @@ -25,6 +25,5 @@ per_version_boot_params () { echo $1 `scftorture_param_onoff "$1" "$2"` \ scftorture.stat_interval=15 \ scftorture.shutdown_secs=$3 \ - scftorture.verbose=1 \ - scf + scftorture.verbose=1 } diff --git a/tools/testing/selftests/seccomp/Makefile b/tools/testing/selftests/seccomp/Makefile index 585f7a0c10cb..f017c382c036 100644 --- a/tools/testing/selftests/seccomp/Makefile +++ b/tools/testing/selftests/seccomp/Makefile @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 CFLAGS += -Wl,-no-as-needed -Wall -isystem ../../../../usr/include/ LDFLAGS += -lpthread +LDLIBS += -lcap TEST_GEN_PROGS := seccomp_bpf seccomp_benchmark include ../lib.mk diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index 9d126d7fabdb..136df5b76319 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -46,6 +46,7 @@ #include <sys/ioctl.h> #include <linux/kcmp.h> #include <sys/resource.h> +#include <sys/capability.h> #include <unistd.h> #include <sys/syscall.h> @@ -59,6 +60,8 @@ #define SKIP(s, ...) XFAIL(s, ##__VA_ARGS__) #endif +#define MIN(X, Y) ((X) < (Y) ? (X) : (Y)) + #ifndef PR_SET_PTRACER # define PR_SET_PTRACER 0x59616d61 #endif @@ -268,6 +271,10 @@ struct seccomp_notif_addfd_big { #define SECCOMP_FILTER_FLAG_TSYNC_ESRCH (1UL << 4) #endif +#ifndef SECCOMP_FILTER_FLAG_WAIT_KILLABLE_RECV +#define SECCOMP_FILTER_FLAG_WAIT_KILLABLE_RECV (1UL << 5) +#endif + #ifndef seccomp int seccomp(unsigned int op, unsigned int flags, void *args) { @@ -955,7 +962,7 @@ TEST(ERRNO_valid) ASSERT_EQ(0, ret); EXPECT_EQ(parent, syscall(__NR_getppid)); - EXPECT_EQ(-1, read(0, NULL, 0)); + EXPECT_EQ(-1, read(-1, NULL, 0)); EXPECT_EQ(E2BIG, errno); } @@ -974,7 +981,7 @@ TEST(ERRNO_zero) EXPECT_EQ(parent, syscall(__NR_getppid)); /* "errno" of 0 is ok. */ - EXPECT_EQ(0, read(0, NULL, 0)); + EXPECT_EQ(0, read(-1, NULL, 0)); } /* @@ -995,7 +1002,7 @@ TEST(ERRNO_capped) ASSERT_EQ(0, ret); EXPECT_EQ(parent, syscall(__NR_getppid)); - EXPECT_EQ(-1, read(0, NULL, 0)); + EXPECT_EQ(-1, read(-1, NULL, 0)); EXPECT_EQ(4095, errno); } @@ -1026,7 +1033,7 @@ TEST(ERRNO_order) ASSERT_EQ(0, ret); EXPECT_EQ(parent, syscall(__NR_getppid)); - EXPECT_EQ(-1, read(0, NULL, 0)); + EXPECT_EQ(-1, read(-1, NULL, 0)); EXPECT_EQ(12, errno); } @@ -2623,7 +2630,7 @@ void *tsync_sibling(void *data) ret = prctl(PR_GET_NO_NEW_PRIVS, 0, 0, 0, 0); if (!ret) return (void *)SIBLING_EXIT_NEWPRIVS; - read(0, NULL, 0); + read(-1, NULL, 0); return (void *)SIBLING_EXIT_UNKILLED; } @@ -3742,7 +3749,10 @@ TEST(user_notification_fault_recv) struct seccomp_notif req = {}; struct seccomp_notif_resp resp = {}; - ASSERT_EQ(unshare(CLONE_NEWUSER), 0); + ASSERT_EQ(unshare(CLONE_NEWUSER), 0) { + if (errno == EINVAL) + SKIP(return, "kernel missing CLONE_NEWUSER support"); + } listener = user_notif_syscall(__NR_getppid, SECCOMP_FILTER_FLAG_NEW_LISTENER); @@ -4231,6 +4241,421 @@ TEST(user_notification_addfd_rlimit) close(memfd); } +/* Make sure PTRACE_O_SUSPEND_SECCOMP requires CAP_SYS_ADMIN. */ +FIXTURE(O_SUSPEND_SECCOMP) { + pid_t pid; +}; + +FIXTURE_SETUP(O_SUSPEND_SECCOMP) +{ + ERRNO_FILTER(block_read, E2BIG); + cap_value_t cap_list[] = { CAP_SYS_ADMIN }; + cap_t caps; + + self->pid = 0; + + /* make sure we don't have CAP_SYS_ADMIN */ + caps = cap_get_proc(); + ASSERT_NE(NULL, caps); + ASSERT_EQ(0, cap_set_flag(caps, CAP_EFFECTIVE, 1, cap_list, CAP_CLEAR)); + ASSERT_EQ(0, cap_set_proc(caps)); + cap_free(caps); + + ASSERT_EQ(0, prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0)); + ASSERT_EQ(0, prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog_block_read)); + + self->pid = fork(); + ASSERT_GE(self->pid, 0); + + if (self->pid == 0) { + while (1) + pause(); + _exit(127); + } +} + +FIXTURE_TEARDOWN(O_SUSPEND_SECCOMP) +{ + if (self->pid) + kill(self->pid, SIGKILL); +} + +TEST_F(O_SUSPEND_SECCOMP, setoptions) +{ + int wstatus; + + ASSERT_EQ(0, ptrace(PTRACE_ATTACH, self->pid, NULL, 0)); + ASSERT_EQ(self->pid, wait(&wstatus)); + ASSERT_EQ(-1, ptrace(PTRACE_SETOPTIONS, self->pid, NULL, PTRACE_O_SUSPEND_SECCOMP)); + if (errno == EINVAL) + SKIP(return, "Kernel does not support PTRACE_O_SUSPEND_SECCOMP (missing CONFIG_CHECKPOINT_RESTORE?)"); + ASSERT_EQ(EPERM, errno); +} + +TEST_F(O_SUSPEND_SECCOMP, seize) +{ + int ret; + + ret = ptrace(PTRACE_SEIZE, self->pid, NULL, PTRACE_O_SUSPEND_SECCOMP); + ASSERT_EQ(-1, ret); + if (errno == EINVAL) + SKIP(return, "Kernel does not support PTRACE_O_SUSPEND_SECCOMP (missing CONFIG_CHECKPOINT_RESTORE?)"); + ASSERT_EQ(EPERM, errno); +} + +/* + * get_nth - Get the nth, space separated entry in a file. + * + * Returns the length of the read field. + * Throws error if field is zero-lengthed. + */ +static ssize_t get_nth(struct __test_metadata *_metadata, const char *path, + const unsigned int position, char **entry) +{ + char *line = NULL; + unsigned int i; + ssize_t nread; + size_t len = 0; + FILE *f; + + f = fopen(path, "r"); + ASSERT_NE(f, NULL) { + TH_LOG("Could not open %s: %s", path, strerror(errno)); + } + + for (i = 0; i < position; i++) { + nread = getdelim(&line, &len, ' ', f); + ASSERT_GE(nread, 0) { + TH_LOG("Failed to read %d entry in file %s", i, path); + } + } + fclose(f); + + ASSERT_GT(nread, 0) { + TH_LOG("Entry in file %s had zero length", path); + } + + *entry = line; + return nread - 1; +} + +/* For a given PID, get the task state (D, R, etc...) */ +static char get_proc_stat(struct __test_metadata *_metadata, pid_t pid) +{ + char proc_path[100] = {0}; + char status; + char *line; + + snprintf(proc_path, sizeof(proc_path), "/proc/%d/stat", pid); + ASSERT_EQ(get_nth(_metadata, proc_path, 3, &line), 1); + + status = *line; + free(line); + + return status; +} + +TEST(user_notification_fifo) +{ + struct seccomp_notif_resp resp = {}; + struct seccomp_notif req = {}; + int i, status, listener; + pid_t pid, pids[3]; + __u64 baseid; + long ret; + /* 100 ms */ + struct timespec delay = { .tv_nsec = 100000000 }; + + ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); + ASSERT_EQ(0, ret) { + TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!"); + } + + /* Setup a listener */ + listener = user_notif_syscall(__NR_getppid, + SECCOMP_FILTER_FLAG_NEW_LISTENER); + ASSERT_GE(listener, 0); + + pid = fork(); + ASSERT_GE(pid, 0); + + if (pid == 0) { + ret = syscall(__NR_getppid); + exit(ret != USER_NOTIF_MAGIC); + } + + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0); + baseid = req.id + 1; + + resp.id = req.id; + resp.error = 0; + resp.val = USER_NOTIF_MAGIC; + + /* check that we make sure flags == 0 */ + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp), 0); + + EXPECT_EQ(waitpid(pid, &status, 0), pid); + EXPECT_EQ(true, WIFEXITED(status)); + EXPECT_EQ(0, WEXITSTATUS(status)); + + /* Start children, and generate notifications */ + for (i = 0; i < ARRAY_SIZE(pids); i++) { + pid = fork(); + if (pid == 0) { + ret = syscall(__NR_getppid); + exit(ret != USER_NOTIF_MAGIC); + } + pids[i] = pid; + } + + /* This spins until all of the children are sleeping */ +restart_wait: + for (i = 0; i < ARRAY_SIZE(pids); i++) { + if (get_proc_stat(_metadata, pids[i]) != 'S') { + nanosleep(&delay, NULL); + goto restart_wait; + } + } + + /* Read the notifications in order (and respond) */ + for (i = 0; i < ARRAY_SIZE(pids); i++) { + memset(&req, 0, sizeof(req)); + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0); + EXPECT_EQ(req.id, baseid + i); + resp.id = req.id; + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp), 0); + } + + /* Make sure notifications were received */ + for (i = 0; i < ARRAY_SIZE(pids); i++) { + EXPECT_EQ(waitpid(pids[i], &status, 0), pids[i]); + EXPECT_EQ(true, WIFEXITED(status)); + EXPECT_EQ(0, WEXITSTATUS(status)); + } +} + +/* get_proc_syscall - Get the syscall in progress for a given pid + * + * Returns the current syscall number for a given process + * Returns -1 if not in syscall (running or blocked) + */ +static long get_proc_syscall(struct __test_metadata *_metadata, int pid) +{ + char proc_path[100] = {0}; + long ret = -1; + ssize_t nread; + char *line; + + snprintf(proc_path, sizeof(proc_path), "/proc/%d/syscall", pid); + nread = get_nth(_metadata, proc_path, 1, &line); + ASSERT_GT(nread, 0); + + if (!strncmp("running", line, MIN(7, nread))) + ret = strtol(line, NULL, 16); + + free(line); + return ret; +} + +/* Ensure non-fatal signals prior to receive are unmodified */ +TEST(user_notification_wait_killable_pre_notification) +{ + struct sigaction new_action = { + .sa_handler = signal_handler, + }; + int listener, status, sk_pair[2]; + pid_t pid; + long ret; + char c; + /* 100 ms */ + struct timespec delay = { .tv_nsec = 100000000 }; + + ASSERT_EQ(sigemptyset(&new_action.sa_mask), 0); + + ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); + ASSERT_EQ(0, ret) + { + TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!"); + } + + ASSERT_EQ(socketpair(PF_LOCAL, SOCK_SEQPACKET, 0, sk_pair), 0); + + listener = user_notif_syscall( + __NR_getppid, SECCOMP_FILTER_FLAG_NEW_LISTENER | + SECCOMP_FILTER_FLAG_WAIT_KILLABLE_RECV); + ASSERT_GE(listener, 0); + + /* + * Check that we can kill the process with SIGUSR1 prior to receiving + * the notification. SIGUSR1 is wired up to a custom signal handler, + * and make sure it gets called. + */ + pid = fork(); + ASSERT_GE(pid, 0); + + if (pid == 0) { + close(sk_pair[0]); + handled = sk_pair[1]; + + /* Setup the non-fatal sigaction without SA_RESTART */ + if (sigaction(SIGUSR1, &new_action, NULL)) { + perror("sigaction"); + exit(1); + } + + ret = syscall(__NR_getppid); + /* Make sure we got a return from a signal interruption */ + exit(ret != -1 || errno != EINTR); + } + + /* + * Make sure we've gotten to the seccomp user notification wait + * from getppid prior to sending any signals + */ + while (get_proc_syscall(_metadata, pid) != __NR_getppid && + get_proc_stat(_metadata, pid) != 'S') + nanosleep(&delay, NULL); + + /* Send non-fatal kill signal */ + EXPECT_EQ(kill(pid, SIGUSR1), 0); + + /* wait for process to exit (exit checks for EINTR) */ + EXPECT_EQ(waitpid(pid, &status, 0), pid); + EXPECT_EQ(true, WIFEXITED(status)); + EXPECT_EQ(0, WEXITSTATUS(status)); + + EXPECT_EQ(read(sk_pair[0], &c, 1), 1); +} + +/* Ensure non-fatal signals after receive are blocked */ +TEST(user_notification_wait_killable) +{ + struct sigaction new_action = { + .sa_handler = signal_handler, + }; + struct seccomp_notif_resp resp = {}; + struct seccomp_notif req = {}; + int listener, status, sk_pair[2]; + pid_t pid; + long ret; + char c; + /* 100 ms */ + struct timespec delay = { .tv_nsec = 100000000 }; + + ASSERT_EQ(sigemptyset(&new_action.sa_mask), 0); + + ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); + ASSERT_EQ(0, ret) + { + TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!"); + } + + ASSERT_EQ(socketpair(PF_LOCAL, SOCK_SEQPACKET, 0, sk_pair), 0); + + listener = user_notif_syscall( + __NR_getppid, SECCOMP_FILTER_FLAG_NEW_LISTENER | + SECCOMP_FILTER_FLAG_WAIT_KILLABLE_RECV); + ASSERT_GE(listener, 0); + + pid = fork(); + ASSERT_GE(pid, 0); + + if (pid == 0) { + close(sk_pair[0]); + handled = sk_pair[1]; + + /* Setup the sigaction without SA_RESTART */ + if (sigaction(SIGUSR1, &new_action, NULL)) { + perror("sigaction"); + exit(1); + } + + /* Make sure that the syscall is completed (no EINTR) */ + ret = syscall(__NR_getppid); + exit(ret != USER_NOTIF_MAGIC); + } + + /* + * Get the notification, to make move the notifying process into a + * non-preemptible (TASK_KILLABLE) state. + */ + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0); + /* Send non-fatal kill signal */ + EXPECT_EQ(kill(pid, SIGUSR1), 0); + + /* + * Make sure the task enters moves to TASK_KILLABLE by waiting for + * D (Disk Sleep) state after receiving non-fatal signal. + */ + while (get_proc_stat(_metadata, pid) != 'D') + nanosleep(&delay, NULL); + + resp.id = req.id; + resp.val = USER_NOTIF_MAGIC; + /* Make sure the notification is found and able to be replied to */ + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp), 0); + + /* + * Make sure that the signal handler does get called once we're back in + * userspace. + */ + EXPECT_EQ(read(sk_pair[0], &c, 1), 1); + /* wait for process to exit (exit checks for USER_NOTIF_MAGIC) */ + EXPECT_EQ(waitpid(pid, &status, 0), pid); + EXPECT_EQ(true, WIFEXITED(status)); + EXPECT_EQ(0, WEXITSTATUS(status)); +} + +/* Ensure fatal signals after receive are not blocked */ +TEST(user_notification_wait_killable_fatal) +{ + struct seccomp_notif req = {}; + int listener, status; + pid_t pid; + long ret; + /* 100 ms */ + struct timespec delay = { .tv_nsec = 100000000 }; + + ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); + ASSERT_EQ(0, ret) + { + TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!"); + } + + listener = user_notif_syscall( + __NR_getppid, SECCOMP_FILTER_FLAG_NEW_LISTENER | + SECCOMP_FILTER_FLAG_WAIT_KILLABLE_RECV); + ASSERT_GE(listener, 0); + + pid = fork(); + ASSERT_GE(pid, 0); + + if (pid == 0) { + /* This should never complete as it should get a SIGTERM */ + syscall(__NR_getppid); + exit(1); + } + + while (get_proc_stat(_metadata, pid) != 'S') + nanosleep(&delay, NULL); + + /* + * Get the notification, to make move the notifying process into a + * non-preemptible (TASK_KILLABLE) state. + */ + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0); + /* Kill the process with a fatal signal */ + EXPECT_EQ(kill(pid, SIGTERM), 0); + + /* + * Wait for the process to exit, and make sure the process terminated + * due to the SIGTERM signal. + */ + EXPECT_EQ(waitpid(pid, &status, 0), pid); + EXPECT_EQ(true, WIFSIGNALED(status)); + EXPECT_EQ(SIGTERM, WTERMSIG(status)); +} + /* * TODO: * - expand NNP testing diff --git a/tools/testing/selftests/vDSO/vdso_test_correctness.c b/tools/testing/selftests/vDSO/vdso_test_correctness.c index c4aea794725a..e691a3cf1491 100644 --- a/tools/testing/selftests/vDSO/vdso_test_correctness.c +++ b/tools/testing/selftests/vDSO/vdso_test_correctness.c @@ -20,6 +20,7 @@ #include <limits.h> #include "vdso_config.h" +#include "../kselftest.h" static const char **name; @@ -306,10 +307,8 @@ static void test_clock_gettime(void) return; } - for (int clock = 0; clock < sizeof(clocknames) / sizeof(clocknames[0]); - clock++) { + for (int clock = 0; clock < ARRAY_SIZE(clocknames); clock++) test_one_clock_gettime(clock, clocknames[clock]); - } /* Also test some invalid clock ids */ test_one_clock_gettime(-1, "invalid"); @@ -370,10 +369,8 @@ static void test_clock_gettime64(void) return; } - for (int clock = 0; clock < sizeof(clocknames) / sizeof(clocknames[0]); - clock++) { + for (int clock = 0; clock < ARRAY_SIZE(clocknames); clock++) test_one_clock_gettime64(clock, clocknames[clock]); - } /* Also test some invalid clock ids */ test_one_clock_gettime64(-1, "invalid"); diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile index 04a49e876a46..5b1ecd00695b 100644 --- a/tools/testing/selftests/vm/Makefile +++ b/tools/testing/selftests/vm/Makefile @@ -57,9 +57,9 @@ CAN_BUILD_I386 := $(shell ./../x86/check_cc.sh "$(CC)" ../x86/trivial_32bit_prog CAN_BUILD_X86_64 := $(shell ./../x86/check_cc.sh "$(CC)" ../x86/trivial_64bit_program.c) CAN_BUILD_WITH_NOPIE := $(shell ./../x86/check_cc.sh "$(CC)" ../x86/trivial_program.c -no-pie) -TARGETS := protection_keys -BINARIES_32 := $(TARGETS:%=%_32) -BINARIES_64 := $(TARGETS:%=%_64) +VMTARGETS := protection_keys +BINARIES_32 := $(VMTARGETS:%=%_32) +BINARIES_64 := $(VMTARGETS:%=%_64) ifeq ($(CAN_BUILD_WITH_NOPIE),1) CFLAGS += -no-pie @@ -112,7 +112,7 @@ $(BINARIES_32): CFLAGS += -m32 -mxsave $(BINARIES_32): LDLIBS += -lrt -ldl -lm $(BINARIES_32): $(OUTPUT)/%_32: %.c $(CC) $(CFLAGS) $(EXTRA_CFLAGS) $(notdir $^) $(LDLIBS) -o $@ -$(foreach t,$(TARGETS),$(eval $(call gen-target-rule-32,$(t)))) +$(foreach t,$(VMTARGETS),$(eval $(call gen-target-rule-32,$(t)))) endif ifeq ($(CAN_BUILD_X86_64),1) @@ -120,7 +120,7 @@ $(BINARIES_64): CFLAGS += -m64 -mxsave $(BINARIES_64): LDLIBS += -lrt -ldl $(BINARIES_64): $(OUTPUT)/%_64: %.c $(CC) $(CFLAGS) $(EXTRA_CFLAGS) $(notdir $^) $(LDLIBS) -o $@ -$(foreach t,$(TARGETS),$(eval $(call gen-target-rule-64,$(t)))) +$(foreach t,$(VMTARGETS),$(eval $(call gen-target-rule-64,$(t)))) endif # x86_64 users should be encouraged to install 32-bit libraries diff --git a/tools/testing/selftests/vm/mremap_test.c b/tools/testing/selftests/vm/mremap_test.c index 7c0b0617b9f8..db0270127aeb 100644 --- a/tools/testing/selftests/vm/mremap_test.c +++ b/tools/testing/selftests/vm/mremap_test.c @@ -6,9 +6,11 @@ #include <errno.h> #include <stdlib.h> +#include <stdio.h> #include <string.h> #include <sys/mman.h> #include <time.h> +#include <stdbool.h> #include "../kselftest.h" @@ -64,6 +66,59 @@ enum { } /* + * Returns false if the requested remap region overlaps with an + * existing mapping (e.g text, stack) else returns true. + */ +static bool is_remap_region_valid(void *addr, unsigned long long size) +{ + void *remap_addr = NULL; + bool ret = true; + + /* Use MAP_FIXED_NOREPLACE flag to ensure region is not mapped */ + remap_addr = mmap(addr, size, PROT_READ | PROT_WRITE, + MAP_FIXED_NOREPLACE | MAP_ANONYMOUS | MAP_SHARED, + -1, 0); + + if (remap_addr == MAP_FAILED) { + if (errno == EEXIST) + ret = false; + } else { + munmap(remap_addr, size); + } + + return ret; +} + +/* Returns mmap_min_addr sysctl tunable from procfs */ +static unsigned long long get_mmap_min_addr(void) +{ + FILE *fp; + int n_matched; + static unsigned long long addr; + + if (addr) + return addr; + + fp = fopen("/proc/sys/vm/mmap_min_addr", "r"); + if (fp == NULL) { + ksft_print_msg("Failed to open /proc/sys/vm/mmap_min_addr: %s\n", + strerror(errno)); + exit(KSFT_SKIP); + } + + n_matched = fscanf(fp, "%llu", &addr); + if (n_matched != 1) { + ksft_print_msg("Failed to read /proc/sys/vm/mmap_min_addr: %s\n", + strerror(errno)); + fclose(fp); + exit(KSFT_SKIP); + } + + fclose(fp); + return addr; +} + +/* * Returns the start address of the mapping on success, else returns * NULL on failure. */ @@ -71,11 +126,18 @@ static void *get_source_mapping(struct config c) { unsigned long long addr = 0ULL; void *src_addr = NULL; + unsigned long long mmap_min_addr; + + mmap_min_addr = get_mmap_min_addr(); + retry: addr += c.src_alignment; + if (addr < mmap_min_addr) + goto retry; + src_addr = mmap((void *) addr, c.region_size, PROT_READ | PROT_WRITE, - MAP_FIXED_NOREPLACE | MAP_ANONYMOUS | MAP_SHARED, - -1, 0); + MAP_FIXED_NOREPLACE | MAP_ANONYMOUS | MAP_SHARED, + -1, 0); if (src_addr == MAP_FAILED) { if (errno == EPERM || errno == EEXIST) goto retry; @@ -90,8 +152,10 @@ retry: * alignment in the tests. */ if (((unsigned long long) src_addr & (c.src_alignment - 1)) || - !((unsigned long long) src_addr & c.src_alignment)) + !((unsigned long long) src_addr & c.src_alignment)) { + munmap(src_addr, c.region_size); goto retry; + } if (!src_addr) goto error; @@ -140,9 +204,20 @@ static long long remap_region(struct config c, unsigned int threshold_mb, if (!((unsigned long long) addr & c.dest_alignment)) addr = (void *) ((unsigned long long) addr | c.dest_alignment); + /* Don't destroy existing mappings unless expected to overlap */ + while (!is_remap_region_valid(addr, c.region_size) && !c.overlapping) { + /* Check for unsigned overflow */ + if (addr + c.dest_alignment < addr) { + ksft_print_msg("Couldn't find a valid region to remap to\n"); + ret = -1; + goto out; + } + addr += c.dest_alignment; + } + clock_gettime(CLOCK_MONOTONIC, &t_start); dest_addr = mremap(src_addr, c.region_size, c.region_size, - MREMAP_MAYMOVE|MREMAP_FIXED, (char *) addr); + MREMAP_MAYMOVE|MREMAP_FIXED, (char *) addr); clock_gettime(CLOCK_MONOTONIC, &t_end); if (dest_addr == MAP_FAILED) { @@ -193,7 +268,7 @@ static void run_mremap_test_case(struct test test_case, int *failures, if (remap_time < 0) { if (test_case.expect_failure) - ksft_test_result_pass("%s\n\tExpected mremap failure\n", + ksft_test_result_xfail("%s\n\tExpected mremap failure\n", test_case.name); else { ksft_test_result_fail("%s\n", test_case.name); diff --git a/tools/testing/selftests/vm/run_vmtests.sh b/tools/testing/selftests/vm/run_vmtests.sh index 3b265f140c25..352ba00cf26b 100755 --- a/tools/testing/selftests/vm/run_vmtests.sh +++ b/tools/testing/selftests/vm/run_vmtests.sh @@ -291,11 +291,16 @@ echo "-------------------" echo "running mremap_test" echo "-------------------" ./mremap_test -if [ $? -ne 0 ]; then +ret_val=$? + +if [ $ret_val -eq 0 ]; then + echo "[PASS]" +elif [ $ret_val -eq $ksft_skip ]; then + echo "[SKIP]" + exitcode=$ksft_skip +else echo "[FAIL]" exitcode=1 -else - echo "[PASS]" fi echo "-----------------" diff --git a/tools/testing/selftests/wireguard/netns.sh b/tools/testing/selftests/wireguard/netns.sh index 8a9461aa0878..69c7796c7ca9 100755 --- a/tools/testing/selftests/wireguard/netns.sh +++ b/tools/testing/selftests/wireguard/netns.sh @@ -22,10 +22,12 @@ # interfaces in $ns1 and $ns2. See https://www.wireguard.com/netns/ for further # details on how this is accomplished. set -e +shopt -s extglob exec 3>&1 export LANG=C export WG_HIDE_KEYS=never +NPROC=( /sys/devices/system/cpu/cpu+([0-9]) ); NPROC=${#NPROC[@]} netns0="wg-test-$$-0" netns1="wg-test-$$-1" netns2="wg-test-$$-2" @@ -143,17 +145,15 @@ tests() { n1 iperf3 -Z -t 3 -b 0 -u -c fd00::2 # TCP over IPv4, in parallel - for max in 4 5 50; do - local pids=( ) - for ((i=0; i < max; ++i)) do - n2 iperf3 -p $(( 5200 + i )) -s -1 -B 192.168.241.2 & - pids+=( $! ); waitiperf $netns2 $! $(( 5200 + i )) - done - for ((i=0; i < max; ++i)) do - n1 iperf3 -Z -t 3 -p $(( 5200 + i )) -c 192.168.241.2 & - done - wait "${pids[@]}" + local pids=( ) i + for ((i=0; i < NPROC; ++i)) do + n2 iperf3 -p $(( 5200 + i )) -s -1 -B 192.168.241.2 & + pids+=( $! ); waitiperf $netns2 $! $(( 5200 + i )) done + for ((i=0; i < NPROC; ++i)) do + n1 iperf3 -Z -t 3 -p $(( 5200 + i )) -c 192.168.241.2 & + done + wait "${pids[@]}" } [[ $(ip1 link show dev wg0) =~ mtu\ ([0-9]+) ]] && orig_mtu="${BASH_REMATCH[1]}" @@ -280,7 +280,19 @@ read _ _ tx_bytes_before < <(n0 wg show wg1 transfer) ! n0 ping -W 1 -c 10 -f 192.168.241.2 || false sleep 1 read _ _ tx_bytes_after < <(n0 wg show wg1 transfer) -(( tx_bytes_after - tx_bytes_before < 70000 )) +if ! (( tx_bytes_after - tx_bytes_before < 70000 )); then + errstart=$'\x1b[37m\x1b[41m\x1b[1m' + errend=$'\x1b[0m' + echo "${errstart} ${errend}" + echo "${errstart} E R R O R ${errend}" + echo "${errstart} ${errend}" + echo "${errstart} This architecture does not do the right thing ${errend}" + echo "${errstart} with cross-namespace routing loops. This test ${errend}" + echo "${errstart} has thus technically failed but, as this issue ${errend}" + echo "${errstart} is as yet unsolved, these tests will continue ${errend}" + echo "${errstart} onward. :( ${errend}" + echo "${errstart} ${errend}" +fi ip0 link del wg1 ip1 link del wg0 diff --git a/tools/testing/selftests/wireguard/qemu/.gitignore b/tools/testing/selftests/wireguard/qemu/.gitignore index bfa15e6feb2f..42ab9d72b37b 100644 --- a/tools/testing/selftests/wireguard/qemu/.gitignore +++ b/tools/testing/selftests/wireguard/qemu/.gitignore @@ -1,3 +1,4 @@ # SPDX-License-Identifier: GPL-2.0-only build/ distfiles/ +ccache/ diff --git a/tools/testing/selftests/wireguard/qemu/Makefile b/tools/testing/selftests/wireguard/qemu/Makefile index 4bdd6c1a19d3..bca07b93eeb0 100644 --- a/tools/testing/selftests/wireguard/qemu/Makefile +++ b/tools/testing/selftests/wireguard/qemu/Makefile @@ -4,26 +4,24 @@ PWD := $(shell pwd) -CHOST := $(shell gcc -dumpmachine) -HOST_ARCH := $(firstword $(subst -, ,$(CHOST))) -ifneq (,$(ARCH)) -CBUILD := $(subst -gcc,,$(lastword $(subst /, ,$(firstword $(wildcard $(foreach bindir,$(subst :, ,$(PATH)),$(bindir)/$(ARCH)-*-gcc)))))) -ifeq (,$(CBUILD)) -$(error The toolchain for $(ARCH) is not installed) -endif -else -CBUILD := $(CHOST) -ARCH := $(firstword $(subst -, ,$(CBUILD))) -endif - # Set these from the environment to override KERNEL_PATH ?= $(PWD)/../../../../.. BUILD_PATH ?= $(PWD)/build/$(ARCH) DISTFILES_PATH ?= $(PWD)/distfiles NR_CPUS ?= 4 +ARCH ?= +CBUILD := $(shell gcc -dumpmachine) +HOST_ARCH := $(firstword $(subst -, ,$(CBUILD))) +ifeq ($(ARCH),) +ARCH := $(HOST_ARCH) +endif MIRROR := https://download.wireguard.com/qemu-test/distfiles/ +KERNEL_BUILD_PATH := $(BUILD_PATH)/kernel$(if $(findstring yes,$(DEBUG_KERNEL)),-debug) +rwildcard=$(foreach d,$(wildcard $1*),$(call rwildcard,$d/,$2) $(filter $(subst *,%,$2),$d)) +WIREGUARD_SOURCES := $(call rwildcard,$(KERNEL_PATH)/drivers/net/wireguard/,*) + default: qemu # variable name, tarball project name, version, tarball extension, default URI base @@ -36,42 +34,33 @@ $(call file_download,$$($(1)_NAME)$(4),$(5),$(6)) endef define file_download = -$(DISTFILES_PATH)/$(1): +$(DISTFILES_PATH)/$(1): | $(4) mkdir -p $(DISTFILES_PATH) - flock -x $$@.lock -c '[ -f $$@ ] && exit 0; wget -O $$@.tmp $(MIRROR)$(1) || wget -O $$@.tmp $(2)$(1) || rm -f $$@.tmp; [ -f $$@.tmp ] || exit 1; if echo "$(3) $$@.tmp" | sha256sum -c -; then mv $$@.tmp $$@; else rm -f $$@.tmp; exit 71; fi' + flock -x $$@.lock -c '[ -f $$@ ] && exit 0; wget -O $$@.tmp $(MIRROR)$(1) || wget -O $$@.tmp $(2)$(1) || rm -f $$@.tmp; [ -f $$@.tmp ] || exit 1; if ([ -n "$(4)" ] && sed -n "s#^\([a-f0-9]\{64\}\) \($(1)\)\$$$$#\1 $(DISTFILES_PATH)/\2.tmp#p" "$(4)" || echo "$(3) $$@.tmp") | sha256sum -c -; then mv $$@.tmp $$@; else rm -f $$@.tmp; exit 71; fi' endef -$(eval $(call tar_download,MUSL,musl,1.2.0,.tar.gz,https://musl.libc.org/releases/,c6de7b191139142d3f9a7b5b702c9cae1b5ee6e7f57e582da9328629408fd4e8)) -$(eval $(call tar_download,IPERF,iperf,3.7,.tar.gz,https://downloads.es.net/pub/iperf/,d846040224317caf2f75c843d309a950a7db23f9b44b94688ccbe557d6d1710c)) -$(eval $(call tar_download,BASH,bash,5.0,.tar.gz,https://ftp.gnu.org/gnu/bash/,b4a80f2ac66170b2913efbfb9f2594f1f76c7b1afd11f799e22035d63077fb4d)) -$(eval $(call tar_download,IPROUTE2,iproute2,5.6.0,.tar.xz,https://www.kernel.org/pub/linux/utils/net/iproute2/,1b5b0e25ce6e23da7526ea1da044e814ad85ba761b10dd29c2b027c056b04692)) -$(eval $(call tar_download,IPTABLES,iptables,1.8.4,.tar.bz2,https://www.netfilter.org/projects/iptables/files/,993a3a5490a544c2cbf2ef15cf7e7ed21af1845baf228318d5c36ef8827e157c)) -$(eval $(call tar_download,NMAP,nmap,7.80,.tar.bz2,https://nmap.org/dist/,fcfa5a0e42099e12e4bf7a68ebe6fde05553383a682e816a7ec9256ab4773faa)) +$(eval $(call tar_download,IPERF,iperf,3.11,.tar.gz,https://downloads.es.net/pub/iperf/,de8cb409fad61a0574f4cb07eb19ce1159707403ac2dc01b5d175e91240b7e5f)) +$(eval $(call tar_download,BASH,bash,5.1.16,.tar.gz,https://ftp.gnu.org/gnu/bash/,5bac17218d3911834520dad13cd1f85ab944e1c09ae1aba55906be1f8192f558)) +$(eval $(call tar_download,IPROUTE2,iproute2,5.17.0,.tar.gz,https://www.kernel.org/pub/linux/utils/net/iproute2/,bda331d5c4606138892f23a565d78fca18919b4d508a0b7ca8391c2da2db68b9)) +$(eval $(call tar_download,IPTABLES,iptables,1.8.7,.tar.bz2,https://www.netfilter.org/projects/iptables/files/,c109c96bb04998cd44156622d36f8e04b140701ec60531a10668cfdff5e8d8f0)) +$(eval $(call tar_download,NMAP,nmap,7.92,.tgz,https://nmap.org/dist/,064183ea642dc4c12b1ab3b5358ce1cef7d2e7e11ffa2849f16d339f5b717117)) $(eval $(call tar_download,IPUTILS,iputils,s20190709,.tar.gz,https://github.com/iputils/iputils/archive/s20190709.tar.gz/#,a15720dd741d7538dd2645f9f516d193636ae4300ff7dbc8bfca757bf166490a)) -$(eval $(call tar_download,WIREGUARD_TOOLS,wireguard-tools,1.0.20200206,.tar.xz,https://git.zx2c4.com/wireguard-tools/snapshot/,f5207248c6a3c3e3bfc9ab30b91c1897b00802ed861e1f9faaed873366078c64)) - -KERNEL_BUILD_PATH := $(BUILD_PATH)/kernel$(if $(findstring yes,$(DEBUG_KERNEL)),-debug) -rwildcard=$(foreach d,$(wildcard $1*),$(call rwildcard,$d/,$2) $(filter $(subst *,%,$2),$d)) -WIREGUARD_SOURCES := $(call rwildcard,$(KERNEL_PATH)/drivers/net/wireguard/,*) - -export CFLAGS ?= -O3 -pipe -export LDFLAGS ?= -export CPPFLAGS := -I$(BUILD_PATH)/include +$(eval $(call tar_download,WIREGUARD_TOOLS,wireguard-tools,1.0.20210914,.tar.xz,https://git.zx2c4.com/wireguard-tools/snapshot/,97ff31489217bb265b7ae850d3d0f335ab07d2652ba1feec88b734bc96bd05ac)) +export CFLAGS := -O3 -pipe ifeq ($(HOST_ARCH),$(ARCH)) -CROSS_COMPILE_FLAG := --host=$(CHOST) CFLAGS += -march=native -STRIP := strip -else -$(info Cross compilation: building for $(CBUILD) using $(CHOST)) -CROSS_COMPILE_FLAG := --build=$(CBUILD) --host=$(CHOST) -export CROSS_COMPILE=$(CBUILD)- -STRIP := $(CBUILD)-strip endif +export LDFLAGS := +export CPPFLAGS := + +QEMU_VPORT_RESULT := ifeq ($(ARCH),aarch64) +CHOST := aarch64-linux-musl QEMU_ARCH := aarch64 KERNEL_ARCH := arm64 KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/arm64/boot/Image +QEMU_VPORT_RESULT := virtio-serial-device ifeq ($(HOST_ARCH),$(ARCH)) QEMU_MACHINE := -cpu host -machine virt,gic_version=host,accel=kvm else @@ -79,9 +68,11 @@ QEMU_MACHINE := -cpu cortex-a53 -machine virt CFLAGS += -march=armv8-a -mtune=cortex-a53 endif else ifeq ($(ARCH),aarch64_be) +CHOST := aarch64_be-linux-musl QEMU_ARCH := aarch64 KERNEL_ARCH := arm64 KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/arm64/boot/Image +QEMU_VPORT_RESULT := virtio-serial-device ifeq ($(HOST_ARCH),$(ARCH)) QEMU_MACHINE := -cpu host -machine virt,gic_version=host,accel=kvm else @@ -89,9 +80,11 @@ QEMU_MACHINE := -cpu cortex-a53 -machine virt CFLAGS += -march=armv8-a -mtune=cortex-a53 endif else ifeq ($(ARCH),arm) +CHOST := arm-linux-musleabi QEMU_ARCH := arm KERNEL_ARCH := arm KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/arm/boot/zImage +QEMU_VPORT_RESULT := virtio-serial-device ifeq ($(HOST_ARCH),$(ARCH)) QEMU_MACHINE := -cpu host -machine virt,gic_version=host,accel=kvm else @@ -99,9 +92,11 @@ QEMU_MACHINE := -cpu cortex-a15 -machine virt CFLAGS += -march=armv7-a -mtune=cortex-a15 -mabi=aapcs-linux endif else ifeq ($(ARCH),armeb) +CHOST := armeb-linux-musleabi QEMU_ARCH := arm KERNEL_ARCH := arm KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/arm/boot/zImage +QEMU_VPORT_RESULT := virtio-serial-device ifeq ($(HOST_ARCH),$(ARCH)) QEMU_MACHINE := -cpu host -machine virt,gic_version=host,accel=kvm else @@ -110,6 +105,7 @@ CFLAGS += -march=armv7-a -mabi=aapcs-linux # We don't pass -mtune=cortex-a15 due LDFLAGS += -Wl,--be8 endif else ifeq ($(ARCH),x86_64) +CHOST := x86_64-linux-musl QEMU_ARCH := x86_64 KERNEL_ARCH := x86_64 KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/x86/boot/bzImage @@ -120,6 +116,7 @@ QEMU_MACHINE := -cpu Skylake-Server -machine q35 CFLAGS += -march=skylake-avx512 endif else ifeq ($(ARCH),i686) +CHOST := i686-linux-musl QEMU_ARCH := i386 KERNEL_ARCH := x86 KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/x86/boot/bzImage @@ -130,6 +127,7 @@ QEMU_MACHINE := -cpu coreduo -machine q35 CFLAGS += -march=prescott endif else ifeq ($(ARCH),mips64) +CHOST := mips64-linux-musl QEMU_ARCH := mips64 KERNEL_ARCH := mips KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux @@ -141,6 +139,7 @@ QEMU_MACHINE := -cpu MIPS64R2-generic -machine malta -smp 1 CFLAGS += -march=mips64r2 -EB endif else ifeq ($(ARCH),mips64el) +CHOST := mips64el-linux-musl QEMU_ARCH := mips64el KERNEL_ARCH := mips KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux @@ -152,6 +151,7 @@ QEMU_MACHINE := -cpu MIPS64R2-generic -machine malta -smp 1 CFLAGS += -march=mips64r2 -EL endif else ifeq ($(ARCH),mips) +CHOST := mips-linux-musl QEMU_ARCH := mips KERNEL_ARCH := mips KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux @@ -163,6 +163,7 @@ QEMU_MACHINE := -cpu 24Kf -machine malta -smp 1 CFLAGS += -march=mips32r2 -EB endif else ifeq ($(ARCH),mipsel) +CHOST := mipsel-linux-musl QEMU_ARCH := mipsel KERNEL_ARCH := mips KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux @@ -173,7 +174,18 @@ else QEMU_MACHINE := -cpu 24Kf -machine malta -smp 1 CFLAGS += -march=mips32r2 -EL endif +else ifeq ($(ARCH),powerpc64) +CHOST := powerpc64-linux-musl +QEMU_ARCH := ppc64 +KERNEL_ARCH := powerpc +KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux +ifeq ($(HOST_ARCH),$(ARCH)) +QEMU_MACHINE := -cpu host,accel=kvm -machine pseries +else +QEMU_MACHINE := -machine pseries +endif else ifeq ($(ARCH),powerpc64le) +CHOST := powerpc64le-linux-musl QEMU_ARCH := ppc64 KERNEL_ARCH := powerpc KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux @@ -182,8 +194,8 @@ QEMU_MACHINE := -cpu host,accel=kvm -machine pseries else QEMU_MACHINE := -machine pseries endif -CFLAGS += -mcpu=powerpc64le -mlong-double-64 else ifeq ($(ARCH),powerpc) +CHOST := powerpc-linux-musl QEMU_ARCH := ppc KERNEL_ARCH := powerpc KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/powerpc/boot/uImage @@ -192,26 +204,79 @@ QEMU_MACHINE := -cpu host,accel=kvm -machine ppce500 else QEMU_MACHINE := -machine ppce500 endif -CFLAGS += -mcpu=powerpc -mlong-double-64 -msecure-plt else ifeq ($(ARCH),m68k) +CHOST := m68k-linux-musl QEMU_ARCH := m68k KERNEL_ARCH := m68k KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux KERNEL_CMDLINE := $(shell sed -n 's/CONFIG_CMDLINE=\(.*\)/\1/p' arch/m68k.config) ifeq ($(HOST_ARCH),$(ARCH)) -QEMU_MACHINE := -cpu host,accel=kvm -machine q800 -smp 1 -append $(KERNEL_CMDLINE) +QEMU_MACHINE := -cpu host,accel=kvm -machine q800 -append $(KERNEL_CMDLINE) else QEMU_MACHINE := -machine q800 -smp 1 -append $(KERNEL_CMDLINE) endif +else ifeq ($(ARCH),riscv64) +CHOST := riscv64-linux-musl +QEMU_ARCH := riscv64 +KERNEL_ARCH := riscv +KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/riscv/boot/Image +QEMU_VPORT_RESULT := virtio-serial-device +ifeq ($(HOST_ARCH),$(ARCH)) +QEMU_MACHINE := -cpu host,accel=kvm -machine virt +else +QEMU_MACHINE := -cpu rv64 -machine virt +endif +else ifeq ($(ARCH),riscv32) +CHOST := riscv32-linux-musl +QEMU_ARCH := riscv32 +KERNEL_ARCH := riscv +KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/riscv/boot/Image +QEMU_VPORT_RESULT := virtio-serial-device +ifeq ($(HOST_ARCH),$(ARCH)) +QEMU_MACHINE := -cpu host,accel=kvm -machine virt +else +QEMU_MACHINE := -cpu rv32 -machine virt +endif +else ifeq ($(ARCH),s390x) +CHOST := s390x-linux-musl +QEMU_ARCH := s390x +KERNEL_ARCH := s390 +KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/s390/boot/bzImage +KERNEL_CMDLINE := $(shell sed -n 's/CONFIG_CMDLINE=\(.*\)/\1/p' arch/s390x.config) +QEMU_VPORT_RESULT := virtio-serial-ccw +ifeq ($(HOST_ARCH),$(ARCH)) +QEMU_MACHINE := -cpu host,accel=kvm -machine s390-ccw-virtio -append $(KERNEL_CMDLINE) +else +QEMU_MACHINE := -machine s390-ccw-virtio -append $(KERNEL_CMDLINE) +endif else -$(error I only build: x86_64, i686, arm, armeb, aarch64, aarch64_be, mips, mipsel, mips64, mips64el, powerpc64le, powerpc, m68k) +$(error I only build: x86_64, i686, arm, armeb, aarch64, aarch64_be, mips, mipsel, mips64, mips64el, powerpc64, powerpc64le, powerpc, m68k, riscv64, riscv32, s390x) +endif + +TOOLCHAIN_FILENAME := $(CHOST)-cross.tgz +TOOLCHAIN_TAR := $(DISTFILES_PATH)/$(TOOLCHAIN_FILENAME) +TOOLCHAIN_PATH := $(BUILD_PATH)/$(CHOST)-cross +TOOLCHAIN_DIR := https://download.wireguard.com/qemu-test/toolchains/20211123/ +$(eval $(call file_download,toolchain-sha256sums-20211123,$(TOOLCHAIN_DIR)SHA256SUMS#,83da033fd8c798df476c21d9612da2dfb896ec62fbed4ceec5eefc0e56b3f0c8)) +$(eval $(call file_download,$(TOOLCHAIN_FILENAME),$(TOOLCHAIN_DIR),,$(DISTFILES_PATH)/toolchain-sha256sums-20211123)) + +STRIP := $(CHOST)-strip +CROSS_COMPILE_FLAG := --build=$(CBUILD) --host=$(CHOST) +$(info Building for $(CHOST) using $(CBUILD)) +export CROSS_COMPILE := $(CHOST)- +export PATH := $(TOOLCHAIN_PATH)/bin:$(PATH) +export CC := $(CHOST)-gcc +CCACHE_PATH := $(shell which ccache 2>/dev/null) +ifneq ($(CCACHE_PATH),) +export KBUILD_BUILD_TIMESTAMP := Fri Jun 5 15:58:00 CEST 2015 +export PATH := $(TOOLCHAIN_PATH)/bin/ccache:$(PATH) +export CCACHE_SLOPPINESS := file_macro,time_macros +export CCACHE_DIR ?= $(PWD)/ccache endif -REAL_CC := $(CBUILD)-gcc -MUSL_CC := $(BUILD_PATH)/musl-gcc -export CC := $(MUSL_CC) -USERSPACE_DEPS := $(MUSL_CC) $(BUILD_PATH)/include/.installed $(BUILD_PATH)/include/linux/.installed +USERSPACE_DEPS := $(TOOLCHAIN_PATH)/.installed $(TOOLCHAIN_PATH)/$(CHOST)/include/linux/.installed +comma := , build: $(KERNEL_BZIMAGE) qemu: $(KERNEL_BZIMAGE) rm -f $(BUILD_PATH)/result @@ -222,13 +287,14 @@ qemu: $(KERNEL_BZIMAGE) $(QEMU_MACHINE) \ -m $$(grep -q CONFIG_DEBUG_KMEMLEAK=y $(KERNEL_BUILD_PATH)/.config && echo 1G || echo 256M) \ -serial stdio \ - -serial file:$(BUILD_PATH)/result \ + -chardev file,path=$(BUILD_PATH)/result,id=result \ + $(if $(QEMU_VPORT_RESULT),-device $(QEMU_VPORT_RESULT) -device virtserialport$(comma)chardev=result,-serial chardev:result) \ -no-reboot \ -monitor none \ -kernel $< grep -Fq success $(BUILD_PATH)/result -$(BUILD_PATH)/init-cpio-spec.txt: +$(BUILD_PATH)/init-cpio-spec.txt: $(TOOLCHAIN_PATH)/.installed $(BUILD_PATH)/init mkdir -p $(BUILD_PATH) echo "file /init $(BUILD_PATH)/init 755 0 0" > $@ echo "file /init.sh $(PWD)/../netns.sh 755 0 0" >> $@ @@ -246,10 +312,10 @@ $(BUILD_PATH)/init-cpio-spec.txt: echo "slink /bin/iptables xtables-legacy-multi 777 0 0" >> $@ echo "slink /bin/ping6 ping 777 0 0" >> $@ echo "dir /lib 755 0 0" >> $@ - echo "file /lib/libc.so $(MUSL_PATH)/lib/libc.so 755 0 0" >> $@ - echo "slink /lib/ld-linux.so.1 libc.so 777 0 0" >> $@ + echo "file /lib/libc.so $(TOOLCHAIN_PATH)/$(CHOST)/lib/libc.so 755 0 0" >> $@ + echo "slink $$($(CHOST)-readelf -p .interp '$(BUILD_PATH)/init'| grep -o '/lib/.*') libc.so 777 0 0" >> $@ -$(KERNEL_BUILD_PATH)/.config: kernel.config arch/$(ARCH).config +$(KERNEL_BUILD_PATH)/.config: $(TOOLCHAIN_PATH)/.installed kernel.config arch/$(ARCH).config mkdir -p $(KERNEL_BUILD_PATH) cp kernel.config $(KERNEL_BUILD_PATH)/minimal.config printf 'CONFIG_NR_CPUS=$(NR_CPUS)\nCONFIG_INITRAMFS_SOURCE="$(BUILD_PATH)/init-cpio-spec.txt"\n' >> $(KERNEL_BUILD_PATH)/minimal.config @@ -258,29 +324,24 @@ $(KERNEL_BUILD_PATH)/.config: kernel.config arch/$(ARCH).config cd $(KERNEL_BUILD_PATH) && ARCH=$(KERNEL_ARCH) $(KERNEL_PATH)/scripts/kconfig/merge_config.sh -n $(KERNEL_BUILD_PATH)/.config $(KERNEL_BUILD_PATH)/minimal.config $(if $(findstring yes,$(DEBUG_KERNEL)),cp debug.config $(KERNEL_BUILD_PATH) && cd $(KERNEL_BUILD_PATH) && ARCH=$(KERNEL_ARCH) $(KERNEL_PATH)/scripts/kconfig/merge_config.sh -n $(KERNEL_BUILD_PATH)/.config debug.config,) -$(KERNEL_BZIMAGE): $(KERNEL_BUILD_PATH)/.config $(BUILD_PATH)/init-cpio-spec.txt $(MUSL_PATH)/lib/libc.so $(IPERF_PATH)/src/iperf3 $(IPUTILS_PATH)/ping $(BASH_PATH)/bash $(IPROUTE2_PATH)/misc/ss $(IPROUTE2_PATH)/ip/ip $(IPTABLES_PATH)/iptables/xtables-legacy-multi $(NMAP_PATH)/ncat/ncat $(WIREGUARD_TOOLS_PATH)/src/wg $(BUILD_PATH)/init ../netns.sh $(WIREGUARD_SOURCES) +$(KERNEL_BZIMAGE): $(TOOLCHAIN_PATH)/.installed $(KERNEL_BUILD_PATH)/.config $(BUILD_PATH)/init-cpio-spec.txt $(IPERF_PATH)/src/iperf3 $(IPUTILS_PATH)/ping $(BASH_PATH)/bash $(IPROUTE2_PATH)/misc/ss $(IPROUTE2_PATH)/ip/ip $(IPTABLES_PATH)/iptables/xtables-legacy-multi $(NMAP_PATH)/ncat/ncat $(WIREGUARD_TOOLS_PATH)/src/wg $(BUILD_PATH)/init ../netns.sh $(WIREGUARD_SOURCES) $(MAKE) -C $(KERNEL_PATH) O=$(KERNEL_BUILD_PATH) ARCH=$(KERNEL_ARCH) CROSS_COMPILE=$(CROSS_COMPILE) -$(BUILD_PATH)/include/linux/.installed: | $(KERNEL_BUILD_PATH)/.config - $(MAKE) -C $(KERNEL_PATH) O=$(KERNEL_BUILD_PATH) INSTALL_HDR_PATH=$(BUILD_PATH) ARCH=$(KERNEL_ARCH) CROSS_COMPILE=$(CROSS_COMPILE) headers_install +$(TOOLCHAIN_PATH)/$(CHOST)/include/linux/.installed: | $(KERNEL_BUILD_PATH)/.config $(TOOLCHAIN_PATH)/.installed + rm -rf $(TOOLCHAIN_PATH)/$(CHOST)/include/linux + $(MAKE) -C $(KERNEL_PATH) O=$(KERNEL_BUILD_PATH) INSTALL_HDR_PATH=$(TOOLCHAIN_PATH)/$(CHOST) ARCH=$(KERNEL_ARCH) CROSS_COMPILE=$(CROSS_COMPILE) headers_install touch $@ -$(MUSL_PATH)/lib/libc.so: $(MUSL_TAR) +$(TOOLCHAIN_PATH)/.installed: $(TOOLCHAIN_TAR) mkdir -p $(BUILD_PATH) flock -s $<.lock tar -C $(BUILD_PATH) -xf $< - cd $(MUSL_PATH) && CC=$(REAL_CC) ./configure --prefix=/ --disable-static --build=$(CBUILD) - $(MAKE) -C $(MUSL_PATH) - $(STRIP) -s $@ - -$(BUILD_PATH)/include/.installed: $(MUSL_PATH)/lib/libc.so - $(MAKE) -C $(MUSL_PATH) DESTDIR=$(BUILD_PATH) install-headers + $(STRIP) -s $(TOOLCHAIN_PATH)/$(CHOST)/lib/libc.so +ifneq ($(CCACHE_PATH),) + mkdir -p $(TOOLCHAIN_PATH)/bin/ccache + ln -s $(CCACHE_PATH) $(TOOLCHAIN_PATH)/bin/ccache/$(CC) +endif touch $@ -$(MUSL_CC): $(MUSL_PATH)/lib/libc.so - sh $(MUSL_PATH)/tools/musl-gcc.specs.sh $(BUILD_PATH)/include $(MUSL_PATH)/lib /lib/ld-linux.so.1 > $(BUILD_PATH)/musl-gcc.specs - printf '#!/bin/sh\nexec "$(REAL_CC)" --specs="$(BUILD_PATH)/musl-gcc.specs" "$$@"\n' > $(BUILD_PATH)/musl-gcc - chmod +x $(BUILD_PATH)/musl-gcc - $(IPERF_PATH)/.installed: $(IPERF_TAR) mkdir -p $(BUILD_PATH) flock -s $<.lock tar -C $(BUILD_PATH) -xf $< @@ -289,6 +350,7 @@ $(IPERF_PATH)/.installed: $(IPERF_TAR) touch $@ $(IPERF_PATH)/src/iperf3: | $(IPERF_PATH)/.installed $(USERSPACE_DEPS) + cd $(IPERF_PATH) && autoreconf -fi cd $(IPERF_PATH) && CFLAGS="$(CFLAGS) -D_GNU_SOURCE" ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared --with-openssl=no $(MAKE) -C $(IPERF_PATH) $(STRIP) -s $@ @@ -304,7 +366,7 @@ $(WIREGUARD_TOOLS_PATH)/src/wg: | $(WIREGUARD_TOOLS_PATH)/.installed $(USERSPACE $(BUILD_PATH)/init: init.c | $(USERSPACE_DEPS) mkdir -p $(BUILD_PATH) - $(MUSL_CC) -o $@ $(CFLAGS) $(LDFLAGS) -std=gnu11 $< + $(CC) -o $@ $(CFLAGS) $(LDFLAGS) -std=gnu11 $< $(STRIP) -s $@ $(IPUTILS_PATH)/.installed: $(IPUTILS_TAR) @@ -323,15 +385,15 @@ $(BASH_PATH)/.installed: $(BASH_TAR) touch $@ $(BASH_PATH)/bash: | $(BASH_PATH)/.installed $(USERSPACE_DEPS) - cd $(BASH_PATH) && ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --without-bash-malloc --disable-debugger --disable-help-builtin --disable-history --disable-multibyte --disable-progcomp --disable-readline --disable-mem-scramble + cd $(BASH_PATH) && ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --without-bash-malloc --disable-debugger --disable-help-builtin --disable-history --disable-progcomp --disable-readline --disable-mem-scramble $(MAKE) -C $(BASH_PATH) $(STRIP) -s $@ $(IPROUTE2_PATH)/.installed: $(IPROUTE2_TAR) mkdir -p $(BUILD_PATH) flock -s $<.lock tar -C $(BUILD_PATH) -xf $< - printf 'CC:=$(CC)\nPKG_CONFIG:=pkg-config\nTC_CONFIG_XT:=n\nTC_CONFIG_ATM:=n\nTC_CONFIG_IPSET:=n\nIP_CONFIG_SETNS:=y\nHAVE_ELF:=n\nHAVE_MNL:=n\nHAVE_BERKELEY_DB:=n\nHAVE_LATEX:=n\nHAVE_PDFLATEX:=n\nCFLAGS+=-DHAVE_SETNS\n' > $(IPROUTE2_PATH)/config.mk - printf 'lib: snapshot\n\t$$(MAKE) -C lib\nip/ip: lib\n\t$$(MAKE) -C ip ip\nmisc/ss: lib\n\t$$(MAKE) -C misc ss\n' >> $(IPROUTE2_PATH)/Makefile + printf 'CC:=$(CC)\nPKG_CONFIG:=pkg-config\nTC_CONFIG_XT:=n\nTC_CONFIG_ATM:=n\nTC_CONFIG_IPSET:=n\nIP_CONFIG_SETNS:=y\nHAVE_ELF:=n\nHAVE_MNL:=n\nHAVE_BERKELEY_DB:=n\nHAVE_LATEX:=n\nHAVE_PDFLATEX:=n\nCFLAGS+=-DHAVE_SETNS -DHAVE_HANDLE_AT\n' > $(IPROUTE2_PATH)/config.mk + printf 'libutil.a.done:\n\tflock -x $$@.lock $$(MAKE) -C lib\n\ttouch $$@\nip/ip: libutil.a.done\n\t$$(MAKE) -C ip ip\nmisc/ss: libutil.a.done\n\t$$(MAKE) -C misc ss\n' >> $(IPROUTE2_PATH)/Makefile touch $@ $(IPROUTE2_PATH)/ip/ip: | $(IPROUTE2_PATH)/.installed $(USERSPACE_DEPS) @@ -370,8 +432,13 @@ clean: distclean: clean rm -rf $(DISTFILES_PATH) +cacheclean: clean +ifneq ($(CCACHE_DIR),) + rm -rf $(CCACHE_DIR) +endif + menuconfig: $(KERNEL_BUILD_PATH)/.config $(MAKE) -C $(KERNEL_PATH) O=$(KERNEL_BUILD_PATH) ARCH=$(KERNEL_ARCH) CROSS_COMPILE=$(CROSS_COMPILE) menuconfig -.PHONY: qemu build clean distclean menuconfig +.PHONY: qemu build clean distclean cacheclean menuconfig .DELETE_ON_ERROR: diff --git a/tools/testing/selftests/wireguard/qemu/arch/aarch64.config b/tools/testing/selftests/wireguard/qemu/arch/aarch64.config index 3d063bb247bb..09016880ce03 100644 --- a/tools/testing/selftests/wireguard/qemu/arch/aarch64.config +++ b/tools/testing/selftests/wireguard/qemu/arch/aarch64.config @@ -1,5 +1,8 @@ CONFIG_SERIAL_AMBA_PL011=y CONFIG_SERIAL_AMBA_PL011_CONSOLE=y +CONFIG_VIRTIO_MENU=y +CONFIG_VIRTIO_MMIO=y +CONFIG_VIRTIO_CONSOLE=y CONFIG_CMDLINE_BOOL=y -CONFIG_CMDLINE="console=ttyAMA0 wg.success=ttyAMA1" +CONFIG_CMDLINE="console=ttyAMA0 wg.success=vport0p1 panic_on_warn=1" CONFIG_FRAME_WARN=1280 diff --git a/tools/testing/selftests/wireguard/qemu/arch/aarch64_be.config b/tools/testing/selftests/wireguard/qemu/arch/aarch64_be.config index dbdc7e406a7b..19ff66e4c602 100644 --- a/tools/testing/selftests/wireguard/qemu/arch/aarch64_be.config +++ b/tools/testing/selftests/wireguard/qemu/arch/aarch64_be.config @@ -1,6 +1,9 @@ CONFIG_CPU_BIG_ENDIAN=y CONFIG_SERIAL_AMBA_PL011=y CONFIG_SERIAL_AMBA_PL011_CONSOLE=y +CONFIG_VIRTIO_MENU=y +CONFIG_VIRTIO_MMIO=y +CONFIG_VIRTIO_CONSOLE=y CONFIG_CMDLINE_BOOL=y -CONFIG_CMDLINE="console=ttyAMA0 wg.success=ttyAMA1" +CONFIG_CMDLINE="console=ttyAMA0 wg.success=vport0p1 panic_on_warn=1" CONFIG_FRAME_WARN=1280 diff --git a/tools/testing/selftests/wireguard/qemu/arch/arm.config b/tools/testing/selftests/wireguard/qemu/arch/arm.config index 148f49905418..fc7959bef9c2 100644 --- a/tools/testing/selftests/wireguard/qemu/arch/arm.config +++ b/tools/testing/selftests/wireguard/qemu/arch/arm.config @@ -4,6 +4,9 @@ CONFIG_ARCH_VIRT=y CONFIG_THUMB2_KERNEL=n CONFIG_SERIAL_AMBA_PL011=y CONFIG_SERIAL_AMBA_PL011_CONSOLE=y +CONFIG_VIRTIO_MENU=y +CONFIG_VIRTIO_MMIO=y +CONFIG_VIRTIO_CONSOLE=y CONFIG_CMDLINE_BOOL=y -CONFIG_CMDLINE="console=ttyAMA0 wg.success=ttyAMA1" +CONFIG_CMDLINE="console=ttyAMA0 wg.success=vport0p1 panic_on_warn=1" CONFIG_FRAME_WARN=1024 diff --git a/tools/testing/selftests/wireguard/qemu/arch/armeb.config b/tools/testing/selftests/wireguard/qemu/arch/armeb.config index bd76b07d00a2..f3066be81c19 100644 --- a/tools/testing/selftests/wireguard/qemu/arch/armeb.config +++ b/tools/testing/selftests/wireguard/qemu/arch/armeb.config @@ -4,7 +4,10 @@ CONFIG_ARCH_VIRT=y CONFIG_THUMB2_KERNEL=n CONFIG_SERIAL_AMBA_PL011=y CONFIG_SERIAL_AMBA_PL011_CONSOLE=y +CONFIG_VIRTIO_MENU=y +CONFIG_VIRTIO_MMIO=y +CONFIG_VIRTIO_CONSOLE=y CONFIG_CMDLINE_BOOL=y -CONFIG_CMDLINE="console=ttyAMA0 wg.success=ttyAMA1" +CONFIG_CMDLINE="console=ttyAMA0 wg.success=vport0p1 panic_on_warn=1" CONFIG_CPU_BIG_ENDIAN=y CONFIG_FRAME_WARN=1024 diff --git a/tools/testing/selftests/wireguard/qemu/arch/i686.config b/tools/testing/selftests/wireguard/qemu/arch/i686.config index a85025d7206e..6d90892a85a2 100644 --- a/tools/testing/selftests/wireguard/qemu/arch/i686.config +++ b/tools/testing/selftests/wireguard/qemu/arch/i686.config @@ -1,5 +1,6 @@ +CONFIG_ACPI=y CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_CMDLINE_BOOL=y -CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1" +CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1 panic_on_warn=1" CONFIG_FRAME_WARN=1024 diff --git a/tools/testing/selftests/wireguard/qemu/arch/m68k.config b/tools/testing/selftests/wireguard/qemu/arch/m68k.config index 62a15bdb877e..82c925e49beb 100644 --- a/tools/testing/selftests/wireguard/qemu/arch/m68k.config +++ b/tools/testing/selftests/wireguard/qemu/arch/m68k.config @@ -5,5 +5,5 @@ CONFIG_MAC=y CONFIG_SERIAL_PMACZILOG=y CONFIG_SERIAL_PMACZILOG_TTYS=y CONFIG_SERIAL_PMACZILOG_CONSOLE=y -CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1" +CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1 panic_on_warn=1" CONFIG_FRAME_WARN=1024 diff --git a/tools/testing/selftests/wireguard/qemu/arch/mips.config b/tools/testing/selftests/wireguard/qemu/arch/mips.config index df71d6b95546..d7ec63c17b30 100644 --- a/tools/testing/selftests/wireguard/qemu/arch/mips.config +++ b/tools/testing/selftests/wireguard/qemu/arch/mips.config @@ -7,5 +7,5 @@ CONFIG_POWER_RESET_SYSCON=y CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_CMDLINE_BOOL=y -CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1" +CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1 panic_on_warn=1" CONFIG_FRAME_WARN=1024 diff --git a/tools/testing/selftests/wireguard/qemu/arch/mips64.config b/tools/testing/selftests/wireguard/qemu/arch/mips64.config index 90c783f725c4..0994947e3392 100644 --- a/tools/testing/selftests/wireguard/qemu/arch/mips64.config +++ b/tools/testing/selftests/wireguard/qemu/arch/mips64.config @@ -10,5 +10,5 @@ CONFIG_POWER_RESET_SYSCON=y CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_CMDLINE_BOOL=y -CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1" +CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1 panic_on_warn=1" CONFIG_FRAME_WARN=1280 diff --git a/tools/testing/selftests/wireguard/qemu/arch/mips64el.config b/tools/testing/selftests/wireguard/qemu/arch/mips64el.config index 435b0b43e00c..591184342f47 100644 --- a/tools/testing/selftests/wireguard/qemu/arch/mips64el.config +++ b/tools/testing/selftests/wireguard/qemu/arch/mips64el.config @@ -11,5 +11,5 @@ CONFIG_POWER_RESET_SYSCON=y CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_CMDLINE_BOOL=y -CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1" +CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1 panic_on_warn=1" CONFIG_FRAME_WARN=1280 diff --git a/tools/testing/selftests/wireguard/qemu/arch/mipsel.config b/tools/testing/selftests/wireguard/qemu/arch/mipsel.config index 62bb50c4a85f..18a498293737 100644 --- a/tools/testing/selftests/wireguard/qemu/arch/mipsel.config +++ b/tools/testing/selftests/wireguard/qemu/arch/mipsel.config @@ -8,5 +8,5 @@ CONFIG_POWER_RESET_SYSCON=y CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_CMDLINE_BOOL=y -CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1" +CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1 panic_on_warn=1" CONFIG_FRAME_WARN=1024 diff --git a/tools/testing/selftests/wireguard/qemu/arch/powerpc.config b/tools/testing/selftests/wireguard/qemu/arch/powerpc.config index 57957093b71b..5e04882e8e35 100644 --- a/tools/testing/selftests/wireguard/qemu/arch/powerpc.config +++ b/tools/testing/selftests/wireguard/qemu/arch/powerpc.config @@ -6,5 +6,5 @@ CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_MATH_EMULATION=y CONFIG_CMDLINE_BOOL=y -CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1" +CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1 panic_on_warn=1" CONFIG_FRAME_WARN=1024 diff --git a/tools/testing/selftests/wireguard/qemu/arch/powerpc64.config b/tools/testing/selftests/wireguard/qemu/arch/powerpc64.config new file mode 100644 index 000000000000..737194b7619e --- /dev/null +++ b/tools/testing/selftests/wireguard/qemu/arch/powerpc64.config @@ -0,0 +1,13 @@ +CONFIG_PPC64=y +CONFIG_PPC_PSERIES=y +CONFIG_ALTIVEC=y +CONFIG_VSX=y +CONFIG_PPC_OF_BOOT_TRAMPOLINE=y +CONFIG_PPC_RADIX_MMU=y +CONFIG_HVC_CONSOLE=y +CONFIG_CPU_BIG_ENDIAN=y +CONFIG_CMDLINE_BOOL=y +CONFIG_CMDLINE="console=hvc0 wg.success=hvc1 panic_on_warn=1" +CONFIG_SECTION_MISMATCH_WARN_ONLY=y +CONFIG_FRAME_WARN=1280 +CONFIG_THREAD_SHIFT=14 diff --git a/tools/testing/selftests/wireguard/qemu/arch/powerpc64le.config b/tools/testing/selftests/wireguard/qemu/arch/powerpc64le.config index f52f1e2bc7f6..8148b9d1220a 100644 --- a/tools/testing/selftests/wireguard/qemu/arch/powerpc64le.config +++ b/tools/testing/selftests/wireguard/qemu/arch/powerpc64le.config @@ -7,7 +7,7 @@ CONFIG_PPC_RADIX_MMU=y CONFIG_HVC_CONSOLE=y CONFIG_CPU_LITTLE_ENDIAN=y CONFIG_CMDLINE_BOOL=y -CONFIG_CMDLINE="console=hvc0 wg.success=hvc1" +CONFIG_CMDLINE="console=hvc0 wg.success=hvc1 panic_on_warn=1" CONFIG_SECTION_MISMATCH_WARN_ONLY=y CONFIG_FRAME_WARN=1280 CONFIG_THREAD_SHIFT=14 diff --git a/tools/testing/selftests/wireguard/qemu/arch/riscv32.config b/tools/testing/selftests/wireguard/qemu/arch/riscv32.config new file mode 100644 index 000000000000..0bd0e72d95d4 --- /dev/null +++ b/tools/testing/selftests/wireguard/qemu/arch/riscv32.config @@ -0,0 +1,12 @@ +CONFIG_ARCH_RV32I=y +CONFIG_MMU=y +CONFIG_FPU=y +CONFIG_SOC_VIRT=y +CONFIG_SERIAL_8250=y +CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_SERIAL_OF_PLATFORM=y +CONFIG_VIRTIO_MENU=y +CONFIG_VIRTIO_MMIO=y +CONFIG_VIRTIO_CONSOLE=y +CONFIG_CMDLINE="console=ttyS0 wg.success=vport0p1 panic_on_warn=1" +CONFIG_CMDLINE_FORCE=y diff --git a/tools/testing/selftests/wireguard/qemu/arch/riscv64.config b/tools/testing/selftests/wireguard/qemu/arch/riscv64.config new file mode 100644 index 000000000000..dc266f3b1915 --- /dev/null +++ b/tools/testing/selftests/wireguard/qemu/arch/riscv64.config @@ -0,0 +1,12 @@ +CONFIG_ARCH_RV64I=y +CONFIG_MMU=y +CONFIG_FPU=y +CONFIG_SOC_VIRT=y +CONFIG_SERIAL_8250=y +CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_SERIAL_OF_PLATFORM=y +CONFIG_VIRTIO_MENU=y +CONFIG_VIRTIO_MMIO=y +CONFIG_VIRTIO_CONSOLE=y +CONFIG_CMDLINE="console=ttyS0 wg.success=vport0p1 panic_on_warn=1" +CONFIG_CMDLINE_FORCE=y diff --git a/tools/testing/selftests/wireguard/qemu/arch/s390x.config b/tools/testing/selftests/wireguard/qemu/arch/s390x.config new file mode 100644 index 000000000000..a7b44dca0b0a --- /dev/null +++ b/tools/testing/selftests/wireguard/qemu/arch/s390x.config @@ -0,0 +1,6 @@ +CONFIG_SCLP_VT220_TTY=y +CONFIG_SCLP_VT220_CONSOLE=y +CONFIG_VIRTIO_MENU=y +CONFIG_VIRTIO_CONSOLE=y +CONFIG_S390_GUEST=y +CONFIG_CMDLINE="console=ttysclp0 wg.success=vport0p1 panic_on_warn=1" diff --git a/tools/testing/selftests/wireguard/qemu/arch/x86_64.config b/tools/testing/selftests/wireguard/qemu/arch/x86_64.config index 00a1ef4869d5..efa00693e08b 100644 --- a/tools/testing/selftests/wireguard/qemu/arch/x86_64.config +++ b/tools/testing/selftests/wireguard/qemu/arch/x86_64.config @@ -1,5 +1,6 @@ +CONFIG_ACPI=y CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_CMDLINE_BOOL=y -CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1" +CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1 panic_on_warn=1" CONFIG_FRAME_WARN=1280 diff --git a/tools/testing/selftests/wireguard/qemu/init.c b/tools/testing/selftests/wireguard/qemu/init.c index 0b45055d9de0..2a0f48fac925 100644 --- a/tools/testing/selftests/wireguard/qemu/init.c +++ b/tools/testing/selftests/wireguard/qemu/init.c @@ -110,12 +110,6 @@ static void enable_logging(void) panic("write(exception-trace)"); close(fd); } - fd = open("/proc/sys/kernel/panic_on_warn", O_WRONLY); - if (fd >= 0) { - if (write(fd, "1\n", 2) != 2) - panic("write(panic_on_warn)"); - close(fd); - } } static void kmod_selftests(void) diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile index 53df7d3893d3..0388c4d60af0 100644 --- a/tools/testing/selftests/x86/Makefile +++ b/tools/testing/selftests/x86/Makefile @@ -92,6 +92,10 @@ warn_32bit_failure: echo "If you are using a Fedora-like distribution, try:"; \ echo ""; \ echo " yum install glibc-devel.*i686"; \ + echo ""; \ + echo "If you are using a SUSE-like distribution, try:"; \ + echo ""; \ + echo " zypper install gcc-32bit glibc-devel-static-32bit"; \ exit 0; endif diff --git a/tools/thermal/lib/Build b/tools/thermal/lib/Build new file mode 100644 index 000000000000..06f22760a272 --- /dev/null +++ b/tools/thermal/lib/Build @@ -0,0 +1,3 @@ +libthermal_tools-y += mainloop.o +libthermal_tools-y += log.o +libthermal_tools-y += uptimeofday.o diff --git a/tools/thermal/lib/Makefile b/tools/thermal/lib/Makefile new file mode 100644 index 000000000000..82db451935c5 --- /dev/null +++ b/tools/thermal/lib/Makefile @@ -0,0 +1,158 @@ +# SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +# Most of this file is copied from tools/lib/perf/Makefile + +LIBTHERMAL_TOOLS_VERSION = 0 +LIBTHERMAL_TOOLS_PATCHLEVEL = 0 +LIBTHERMAL_TOOLS_EXTRAVERSION = 1 + +MAKEFLAGS += --no-print-directory + +ifeq ($(srctree),) +srctree := $(patsubst %/,%,$(dir $(CURDIR))) +srctree := $(patsubst %/,%,$(dir $(srctree))) +srctree := $(patsubst %/,%,$(dir $(srctree))) +# $(info Determined 'srctree' to be $(srctree)) +endif + +INSTALL = install + +# Use DESTDIR for installing into a different root directory. +# This is useful for building a package. The program will be +# installed in this directory as if it was the root directory. +# Then the build tool can move it later. +DESTDIR ?= +DESTDIR_SQ = '$(subst ','\'',$(DESTDIR))' + +include $(srctree)/tools/scripts/Makefile.include +include $(srctree)/tools/scripts/Makefile.arch + +ifeq ($(LP64), 1) + libdir_relative = lib64 +else + libdir_relative = lib +endif + +prefix ?= +libdir = $(prefix)/$(libdir_relative) + +# Shell quotes +libdir_SQ = $(subst ','\'',$(libdir)) +libdir_relative_SQ = $(subst ','\'',$(libdir_relative)) + +ifeq ("$(origin V)", "command line") + VERBOSE = $(V) +endif +ifndef VERBOSE + VERBOSE = 0 +endif + +ifeq ($(VERBOSE),1) + Q = +else + Q = @ +endif + +# Set compile option CFLAGS +ifdef EXTRA_CFLAGS + CFLAGS := $(EXTRA_CFLAGS) +else + CFLAGS := -g -Wall +endif + +INCLUDES = \ +-I/usr/include/libnl3 \ +-I$(srctree)/tools/lib/thermal/include \ +-I$(srctree)/tools/lib/ \ +-I$(srctree)/tools/include \ +-I$(srctree)/tools/arch/$(SRCARCH)/include/ \ +-I$(srctree)/tools/arch/$(SRCARCH)/include/uapi \ +-I$(srctree)/tools/include/uapi + +# Append required CFLAGS +override CFLAGS += $(EXTRA_WARNINGS) +override CFLAGS += -Werror -Wall +override CFLAGS += -fPIC +override CFLAGS += $(INCLUDES) +override CFGLAS += -Wl,-L. +override CFGLAS += -Wl,-lthermal + +all: + +export srctree OUTPUT CC LD CFLAGS V +export DESTDIR DESTDIR_SQ + +include $(srctree)/tools/build/Makefile.include + +PATCHLEVEL = $(LIBTHERMAL_TOOLS_PATCHLEVEL) +EXTRAVERSION = $(LIBTHERMAL_TOOLS_EXTRAVERSION) +VERSION = $(LIBTHERMAL_TOOLS_VERSION).$(LIBTHERMAL_TOOLS_PATCHLEVEL).$(LIBTHERMAL_TOOLS_EXTRAVERSION) + +LIBTHERMAL_TOOLS_SO := $(OUTPUT)libthermal_tools.so.$(VERSION) +LIBTHERMAL_TOOLS_A := $(OUTPUT)libthermal_tools.a +LIBTHERMAL_TOOLS_IN := $(OUTPUT)libthermal_tools-in.o +LIBTHERMAL_TOOLS_PC := $(OUTPUT)libthermal_tools.pc + +LIBTHERMAL_TOOLS_ALL := $(LIBTHERMAL_TOOLS_A) $(OUTPUT)libthermal_tools.so* + +$(LIBTHERMAL_TOOLS_IN): FORCE + $(Q)$(MAKE) $(build)=libthermal_tools + +$(LIBTHERMAL_TOOLS_A): $(LIBTHERMAL_TOOLS_IN) + $(QUIET_AR)$(RM) $@ && $(AR) rcs $@ $(LIBTHERMAL_TOOLS_IN) + +$(LIBTHERMAL_TOOLS_SO): $(LIBTHERMAL_TOOLS_IN) + $(QUIET_LINK)$(CC) --shared -Wl,-soname,libthermal_tools.so $^ -o $@ + @ln -sf $(@F) $(OUTPUT)libthermal_tools.so + @ln -sf $(@F) $(OUTPUT)libthermal_tools.so.$(LIBTHERMAL_TOOLS_VERSION) + + +libs: $(LIBTHERMAL_TOOLS_A) $(LIBTHERMAL_TOOLS_SO) $(LIBTHERMAL_TOOLS_PC) + +all: fixdep + $(Q)$(MAKE) libs + +clean: + $(call QUIET_CLEAN, libthermal_tools) $(RM) $(LIBTHERMAL_TOOLS_A) \ + *.o *~ *.a *.so *.so.$(VERSION) *.so.$(LIBTHERMAL_TOOLS_VERSION) .*.d .*.cmd LIBTHERMAL_TOOLS-CFLAGS $(LIBTHERMAL_TOOLS_PC) + +$(LIBTHERMAL_TOOLS_PC): + $(QUIET_GEN)sed -e "s|@PREFIX@|$(prefix)|" \ + -e "s|@LIBDIR@|$(libdir_SQ)|" \ + -e "s|@VERSION@|$(VERSION)|" \ + < libthermal_tools.pc.template > $@ + +define do_install_mkdir + if [ ! -d '$(DESTDIR_SQ)$1' ]; then \ + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$1'; \ + fi +endef + +define do_install + if [ ! -d '$(DESTDIR_SQ)$2' ]; then \ + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$2'; \ + fi; \ + $(INSTALL) $1 $(if $3,-m $3,) '$(DESTDIR_SQ)$2' +endef + +install_lib: libs + $(call QUIET_INSTALL, $(LIBTHERMAL_TOOLS_ALL)) \ + $(call do_install_mkdir,$(libdir_SQ)); \ + cp -fpR $(LIBTHERMAL_TOOLS_ALL) $(DESTDIR)$(libdir_SQ) + +install_headers: + $(call QUIET_INSTALL, headers) \ + $(call do_install,include/thermal.h,$(prefix)/include/thermal,644); \ + +install_pkgconfig: $(LIBTHERMAL_TOOLS_PC) + $(call QUIET_INSTALL, $(LIBTHERMAL_TOOLS_PC)) \ + $(call do_install,$(LIBTHERMAL_TOOLS_PC),$(libdir_SQ)/pkgconfig,644) + +install_doc: + $(Q)$(MAKE) -C Documentation install-man install-html install-examples + +#install: install_lib install_headers install_pkgconfig install_doc +install: install_lib install_headers install_pkgconfig + +FORCE: + +.PHONY: all install clean FORCE diff --git a/tools/thermal/lib/libthermal_tools.pc.template b/tools/thermal/lib/libthermal_tools.pc.template new file mode 100644 index 000000000000..6f3769731b59 --- /dev/null +++ b/tools/thermal/lib/libthermal_tools.pc.template @@ -0,0 +1,12 @@ +# SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) + +prefix=@PREFIX@ +libdir=@LIBDIR@ +includedir=${prefix}/include + +Name: libthermal +Description: thermal library +Requires: libnl-3.0 libnl-genl-3.0 +Version: @VERSION@ +Libs: -L${libdir} -lnl-genl-3 -lnl-3 +Cflags: -I${includedir} -I{include}/libnl3 diff --git a/tools/thermal/lib/log.c b/tools/thermal/lib/log.c new file mode 100644 index 000000000000..597d6e7f7858 --- /dev/null +++ b/tools/thermal/lib/log.c @@ -0,0 +1,77 @@ +// SPDX-License-Identifier: LGPL-2.1+ +// Copyright (C) 2022, Linaro Ltd - Daniel Lezcano <daniel.lezcano@linaro.org> +#include <stdarg.h> +#include <stdio.h> +#include <string.h> +#include <syslog.h> +#include "log.h" + +static const char *__ident = "unknown"; +static int __options; + +static const char * const loglvl[] = { + [LOG_DEBUG] = "DEBUG", + [LOG_INFO] = "INFO", + [LOG_NOTICE] = "NOTICE", + [LOG_WARNING] = "WARN", + [LOG_ERR] = "ERROR", + [LOG_CRIT] = "CRITICAL", + [LOG_ALERT] = "ALERT", + [LOG_EMERG] = "EMERG", +}; + +int log_str2level(const char *lvl) +{ + int i; + + for (i = 0; i < sizeof(loglvl) / sizeof(loglvl[LOG_DEBUG]); i++) + if (!strcmp(lvl, loglvl[i])) + return i; + + return LOG_DEBUG; +} + +extern void logit(int level, const char *format, ...) +{ + va_list args; + + va_start(args, format); + + if (__options & TO_SYSLOG) + vsyslog(level, format, args); + + if (__options & TO_STDERR) + vfprintf(stderr, format, args); + + if (__options & TO_STDOUT) + vfprintf(stdout, format, args); + + va_end(args); +} + +int log_init(int level, const char *ident, int options) +{ + if (!options) + return -1; + + if (level > LOG_DEBUG) + return -1; + + if (!ident) + return -1; + + __ident = ident; + __options = options; + + if (options & TO_SYSLOG) { + openlog(__ident, options | LOG_NDELAY, LOG_USER); + setlogmask(LOG_UPTO(level)); + } + + return 0; +} + +void log_exit(void) +{ + closelog(); +} diff --git a/tools/thermal/lib/log.h b/tools/thermal/lib/log.h new file mode 100644 index 000000000000..be8ab5144938 --- /dev/null +++ b/tools/thermal/lib/log.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: LGPL-2.1+ */ +/* Copyright (C) 2022, Linaro Ltd - Daniel Lezcano <daniel.lezcano@linaro.org> */ +#ifndef __THERMAL_TOOLS_LOG_H +#define __THERMAL_TOOLS_LOG_H + +#include <syslog.h> + +#ifndef __maybe_unused +#define __maybe_unused __attribute__((__unused__)) +#endif + +#define TO_SYSLOG 0x1 +#define TO_STDOUT 0x2 +#define TO_STDERR 0x4 + +extern void logit(int level, const char *format, ...); + +#define DEBUG(fmt, ...) logit(LOG_DEBUG, "%s:%d: " fmt, __func__, __LINE__, ##__VA_ARGS__) +#define INFO(fmt, ...) logit(LOG_INFO, fmt, ##__VA_ARGS__) +#define NOTICE(fmt, ...) logit(LOG_NOTICE, fmt, ##__VA_ARGS__) +#define WARN(fmt, ...) logit(LOG_WARNING, fmt, ##__VA_ARGS__) +#define ERROR(fmt, ...) logit(LOG_ERR, fmt, ##__VA_ARGS__) +#define CRITICAL(fmt, ...) logit(LOG_CRIT, fmt, ##__VA_ARGS__) +#define ALERT(fmt, ...) logit(LOG_ALERT, fmt, ##__VA_ARGS__) +#define EMERG(fmt, ...) logit(LOG_EMERG, fmt, ##__VA_ARGS__) + +int log_init(int level, const char *ident, int options); +int log_str2level(const char *lvl); +void log_exit(void); + +#endif diff --git a/tools/thermal/lib/mainloop.c b/tools/thermal/lib/mainloop.c new file mode 100644 index 000000000000..94cbbcbd1c14 --- /dev/null +++ b/tools/thermal/lib/mainloop.c @@ -0,0 +1,120 @@ +// SPDX-License-Identifier: LGPL-2.1+ +// Copyright (C) 2022, Linaro Ltd - Daniel Lezcano <daniel.lezcano@linaro.org> +#include <stdlib.h> +#include <errno.h> +#include <unistd.h> +#include <signal.h> +#include <sys/epoll.h> +#include "mainloop.h" +#include "log.h" + +static int epfd = -1; +static unsigned short nrhandler; +static sig_atomic_t exit_mainloop; + +struct mainloop_data { + mainloop_callback_t cb; + void *data; + int fd; +}; + +static struct mainloop_data **mds; + +#define MAX_EVENTS 10 + +int mainloop(unsigned int timeout) +{ + int i, nfds; + struct epoll_event events[MAX_EVENTS]; + struct mainloop_data *md; + + if (epfd < 0) + return -1; + + for (;;) { + + nfds = epoll_wait(epfd, events, MAX_EVENTS, timeout); + + if (exit_mainloop || !nfds) + return 0; + + if (nfds < 0) { + if (errno == EINTR) + continue; + return -1; + } + + for (i = 0; i < nfds; i++) { + md = events[i].data.ptr; + + if (md->cb(md->fd, md->data) > 0) + return 0; + } + } +} + +int mainloop_add(int fd, mainloop_callback_t cb, void *data) +{ + struct epoll_event ev = { + .events = EPOLLIN, + }; + + struct mainloop_data *md; + + if (fd >= nrhandler) { + mds = realloc(mds, sizeof(*mds) * (fd + 1)); + if (!mds) + return -1; + nrhandler = fd + 1; + } + + md = malloc(sizeof(*md)); + if (!md) + return -1; + + md->data = data; + md->cb = cb; + md->fd = fd; + + mds[fd] = md; + ev.data.ptr = md; + + if (epoll_ctl(epfd, EPOLL_CTL_ADD, fd, &ev) < 0) { + free(md); + return -1; + } + + return 0; +} + +int mainloop_del(int fd) +{ + if (fd >= nrhandler) + return -1; + + if (epoll_ctl(epfd, EPOLL_CTL_DEL, fd, NULL) < 0) + return -1; + + free(mds[fd]); + + return 0; +} + +int mainloop_init(void) +{ + epfd = epoll_create(2); + if (epfd < 0) + return -1; + + return 0; +} + +void mainloop_exit(void) +{ + exit_mainloop = 1; +} + +void mainloop_fini(void) +{ + close(epfd); +} diff --git a/tools/thermal/lib/mainloop.h b/tools/thermal/lib/mainloop.h new file mode 100644 index 000000000000..89b61e89d905 --- /dev/null +++ b/tools/thermal/lib/mainloop.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: LGPL-2.1+ */ +/* Copyright (C) 2022, Linaro Ltd - Daniel Lezcano <daniel.lezcano@linaro.org> */ +#ifndef __THERMAL_TOOLS_MAINLOOP_H +#define __THERMAL_TOOLS_MAINLOOP_H + +typedef int (*mainloop_callback_t)(int fd, void *data); + +extern int mainloop(unsigned int timeout); +extern int mainloop_add(int fd, mainloop_callback_t cb, void *data); +extern int mainloop_del(int fd); +extern void mainloop_exit(void); +extern int mainloop_init(void); +extern void mainloop_fini(void); + +#endif diff --git a/tools/thermal/lib/thermal-tools.h b/tools/thermal/lib/thermal-tools.h new file mode 100644 index 000000000000..f43939a468a3 --- /dev/null +++ b/tools/thermal/lib/thermal-tools.h @@ -0,0 +1,10 @@ +/* SPDX-License-Identifier: LGPL-2.1+ */ +/* Copyright (C) 2022, Linaro Ltd - Daniel Lezcano <daniel.lezcano@linaro.org> */ +#ifndef __THERMAL_TOOLS +#define __THERMAL_TOOLS + +#include "log.h" +#include "mainloop.h" +#include "uptimeofday.h" + +#endif diff --git a/tools/thermal/lib/uptimeofday.c b/tools/thermal/lib/uptimeofday.c new file mode 100644 index 000000000000..dacb02956a68 --- /dev/null +++ b/tools/thermal/lib/uptimeofday.c @@ -0,0 +1,40 @@ +// SPDX-License-Identifier: LGPL-2.1+ +// Copyright (C) 2022, Linaro Ltd - Daniel Lezcano <daniel.lezcano@linaro.org> +#include <stdio.h> +#include <sys/time.h> +#include <linux/sysinfo.h> +#include "thermal-tools.h" + +static unsigned long __offset; +static struct timeval __tv; + +int uptimeofday_init(void) +{ + struct sysinfo info; + + if (sysinfo(&info)) + return -1; + + gettimeofday(&__tv, NULL); + + __offset = __tv.tv_sec - info.uptime; + + return 0; +} + +unsigned long getuptimeofday_ms(void) +{ + gettimeofday(&__tv, NULL); + + return ((__tv.tv_sec - __offset) * 1000) + (__tv.tv_usec / 1000); +} + +struct timespec msec_to_timespec(int msec) +{ + struct timespec tv = { + .tv_sec = (msec / 1000), + .tv_nsec = (msec % 1000) * 1000000, + }; + + return tv; +} diff --git a/tools/thermal/lib/uptimeofday.h b/tools/thermal/lib/uptimeofday.h new file mode 100644 index 000000000000..c0da5de41325 --- /dev/null +++ b/tools/thermal/lib/uptimeofday.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: LGPL-2.1+ */ +/* Copyright (C) 2022, Linaro Ltd - Daniel Lezcano <daniel.lezcano@linaro.org> */ +#ifndef __THERMAL_TOOLS_UPTIMEOFDAY_H +#define __THERMAL_TOOLS_UPTIMEOFDAY_H +#include <sys/sysinfo.h> +#include <sys/time.h> + +int uptimeofday_init(void); +unsigned long getuptimeofday_ms(void); +struct timespec msec_to_timespec(int msec); + +#endif diff --git a/tools/thermal/thermal-engine/Build b/tools/thermal/thermal-engine/Build new file mode 100644 index 000000000000..20c3c478b88d --- /dev/null +++ b/tools/thermal/thermal-engine/Build @@ -0,0 +1 @@ +thermal-engine-y += thermal-engine.o diff --git a/tools/thermal/thermal-engine/Makefile b/tools/thermal/thermal-engine/Makefile new file mode 100644 index 000000000000..6bd05ff89485 --- /dev/null +++ b/tools/thermal/thermal-engine/Makefile @@ -0,0 +1,28 @@ +# SPDX-License-Identifier: GPL-2.0 +# Makefile for thermal tools + +ifeq ($(srctree),) +srctree := $(patsubst %/,%,$(dir $(CURDIR))) +srctree := $(patsubst %/,%,$(dir $(srctree))) +srctree := $(patsubst %/,%,$(dir $(srctree))) +# $(info Determined 'srctree' to be $(srctree)) +endif + +CFLAGS = -Wall -Wextra +CFLAGS += -I$(srctree)/tools/thermal/lib +CFLAGS += -I$(srctree)/tools/lib/thermal/include + +LDFLAGS = -L$(srctree)/tools/thermal/lib +LDFLAGS += -L$(srctree)/tools/lib/thermal +LDFLAGS += -lthermal_tools +LDFLAGS += -lthermal +LDFLAGS += -lconfig +LDFLAGS += -lnl-genl-3 -lnl-3 + +VERSION = 0.0.1 + +all: thermal-engine +%: %.c + $(CC) $(CFLAGS) -D VERSION=\"$(VERSION)\" -o $@ $^ $(LDFLAGS) +clean: + $(RM) thermal-engine diff --git a/tools/thermal/thermal-engine/thermal-engine.c b/tools/thermal/thermal-engine/thermal-engine.c new file mode 100644 index 000000000000..9b1476a2680f --- /dev/null +++ b/tools/thermal/thermal-engine/thermal-engine.c @@ -0,0 +1,341 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Thermal monitoring tool based on the thermal netlink events. + * + * Copyright (C) 2022 Linaro Ltd. + * + * Author: Daniel Lezcano <daniel.lezcano@kernel.org> + */ +#include <errno.h> +#include <fcntl.h> +#include <getopt.h> +#include <libgen.h> +#include <limits.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <signal.h> +#include <unistd.h> + +#include <syslog.h> + +#include <sys/epoll.h> +#include <sys/stat.h> +#include <sys/types.h> + +#include <thermal.h> +#include "thermal-tools.h" + +struct options { + int loglevel; + int logopt; + int interactive; + int daemonize; +}; + +struct thermal_data { + struct thermal_zone *tz; + struct thermal_handler *th; +}; + +static int show_trip(struct thermal_trip *tt, __maybe_unused void *arg) +{ + INFO("trip id=%d, type=%d, temp=%d, hyst=%d\n", + tt->id, tt->type, tt->temp, tt->hyst); + + return 0; +} + +static int show_temp(struct thermal_zone *tz, __maybe_unused void *arg) +{ + thermal_cmd_get_temp(arg, tz); + + INFO("temperature: %d\n", tz->temp); + + return 0; +} + +static int show_governor(struct thermal_zone *tz, __maybe_unused void *arg) +{ + thermal_cmd_get_governor(arg, tz); + + INFO("governor: '%s'\n", tz->governor); + + return 0; +} + +static int show_tz(struct thermal_zone *tz, __maybe_unused void *arg) +{ + INFO("thermal zone '%s', id=%d\n", tz->name, tz->id); + + for_each_thermal_trip(tz->trip, show_trip, NULL); + + show_temp(tz, arg); + + show_governor(tz, arg); + + return 0; +} + +static int tz_create(const char *name, int tz_id, __maybe_unused void *arg) +{ + INFO("Thermal zone '%s'/%d created\n", name, tz_id); + + return 0; +} + +static int tz_delete(int tz_id, __maybe_unused void *arg) +{ + INFO("Thermal zone %d deleted\n", tz_id); + + return 0; +} + +static int tz_disable(int tz_id, void *arg) +{ + struct thermal_data *td = arg; + struct thermal_zone *tz = thermal_zone_find_by_id(td->tz, tz_id); + + INFO("Thermal zone %d ('%s') disabled\n", tz_id, tz->name); + + return 0; +} + +static int tz_enable(int tz_id, void *arg) +{ + struct thermal_data *td = arg; + struct thermal_zone *tz = thermal_zone_find_by_id(td->tz, tz_id); + + INFO("Thermal zone %d ('%s') enabled\n", tz_id, tz->name); + + return 0; +} + +static int trip_high(int tz_id, int trip_id, int temp, void *arg) +{ + struct thermal_data *td = arg; + struct thermal_zone *tz = thermal_zone_find_by_id(td->tz, tz_id); + + INFO("Thermal zone %d ('%s'): trip point %d crossed way up with %d °C\n", + tz_id, tz->name, trip_id, temp); + + return 0; +} + +static int trip_low(int tz_id, int trip_id, int temp, void *arg) +{ + struct thermal_data *td = arg; + struct thermal_zone *tz = thermal_zone_find_by_id(td->tz, tz_id); + + INFO("Thermal zone %d ('%s'): trip point %d crossed way down with %d °C\n", + tz_id, tz->name, trip_id, temp); + + return 0; +} + +static int trip_add(int tz_id, int trip_id, int type, int temp, int hyst, __maybe_unused void *arg) +{ + INFO("Trip point added %d: id=%d, type=%d, temp=%d, hyst=%d\n", + tz_id, trip_id, type, temp, hyst); + + return 0; +} + +static int trip_delete(int tz_id, int trip_id, __maybe_unused void *arg) +{ + INFO("Trip point deleted %d: id=%d\n", tz_id, trip_id); + + return 0; +} + +static int trip_change(int tz_id, int trip_id, int type, int temp, + int hyst, __maybe_unused void *arg) +{ + struct thermal_data *td = arg; + struct thermal_zone *tz = thermal_zone_find_by_id(td->tz, tz_id); + + INFO("Trip point changed %d: id=%d, type=%d, temp=%d, hyst=%d\n", + tz_id, trip_id, type, temp, hyst); + + tz->trip[trip_id].type = type; + tz->trip[trip_id].temp = temp; + tz->trip[trip_id].hyst = hyst; + + return 0; +} + +static int cdev_add(const char *name, int cdev_id, int max_state, __maybe_unused void *arg) +{ + INFO("Cooling device '%s'/%d (max state=%d) added\n", name, cdev_id, max_state); + + return 0; +} + +static int cdev_delete(int cdev_id, __maybe_unused void *arg) +{ + INFO("Cooling device %d deleted", cdev_id); + + return 0; +} + +static int cdev_update(int cdev_id, int cur_state, __maybe_unused void *arg) +{ + INFO("cdev:%d state:%d\n", cdev_id, cur_state); + + return 0; +} + +static int gov_change(int tz_id, const char *name, __maybe_unused void *arg) +{ + struct thermal_data *td = arg; + struct thermal_zone *tz = thermal_zone_find_by_id(td->tz, tz_id); + + INFO("%s: governor changed %s -> %s\n", tz->name, tz->governor, name); + + strcpy(tz->governor, name); + + return 0; +} + +static struct thermal_ops ops = { + .events.tz_create = tz_create, + .events.tz_delete = tz_delete, + .events.tz_disable = tz_disable, + .events.tz_enable = tz_enable, + .events.trip_high = trip_high, + .events.trip_low = trip_low, + .events.trip_add = trip_add, + .events.trip_delete = trip_delete, + .events.trip_change = trip_change, + .events.cdev_add = cdev_add, + .events.cdev_delete = cdev_delete, + .events.cdev_update = cdev_update, + .events.gov_change = gov_change +}; + +static int thermal_event(__maybe_unused int fd, __maybe_unused void *arg) +{ + struct thermal_data *td = arg; + + return thermal_events_handle(td->th, td); +} + +static void usage(const char *cmd) +{ + printf("%s : A thermal monitoring engine based on notifications\n", cmd); + printf("Usage: %s [options]\n", cmd); + printf("\t-h, --help\t\tthis help\n"); + printf("\t-d, --daemonize\n"); + printf("\t-l <level>, --loglevel <level>\tlog level: "); + printf("DEBUG, INFO, NOTICE, WARN, ERROR\n"); + printf("\t-s, --syslog\t\toutput to syslog\n"); + printf("\n"); + exit(0); +} + +static int options_init(int argc, char *argv[], struct options *options) +{ + int opt; + + struct option long_options[] = { + { "help", no_argument, NULL, 'h' }, + { "daemonize", no_argument, NULL, 'd' }, + { "syslog", no_argument, NULL, 's' }, + { "loglevel", required_argument, NULL, 'l' }, + { 0, 0, 0, 0 } + }; + + while (1) { + + int optindex = 0; + + opt = getopt_long(argc, argv, "l:dhs", long_options, &optindex); + if (opt == -1) + break; + + switch (opt) { + case 'l': + options->loglevel = log_str2level(optarg); + break; + case 'd': + options->daemonize = 1; + break; + case 's': + options->logopt = TO_SYSLOG; + break; + case 'h': + usage(basename(argv[0])); + break; + default: /* '?' */ + return -1; + } + } + + return 0; +} + +enum { + THERMAL_ENGINE_SUCCESS = 0, + THERMAL_ENGINE_OPTION_ERROR, + THERMAL_ENGINE_DAEMON_ERROR, + THERMAL_ENGINE_LOG_ERROR, + THERMAL_ENGINE_THERMAL_ERROR, + THERMAL_ENGINE_MAINLOOP_ERROR, +}; + +int main(int argc, char *argv[]) +{ + struct thermal_data td; + struct options options = { + .loglevel = LOG_INFO, + .logopt = TO_STDOUT, + }; + + if (options_init(argc, argv, &options)) { + ERROR("Usage: %s --help\n", argv[0]); + return THERMAL_ENGINE_OPTION_ERROR; + } + + if (options.daemonize && daemon(0, 0)) { + ERROR("Failed to daemonize: %p\n"); + return THERMAL_ENGINE_DAEMON_ERROR; + } + + if (log_init(options.loglevel, basename(argv[0]), options.logopt)) { + ERROR("Failed to initialize logging facility\n"); + return THERMAL_ENGINE_LOG_ERROR; + } + + td.th = thermal_init(&ops); + if (!td.th) { + ERROR("Failed to initialize the thermal library\n"); + return THERMAL_ENGINE_THERMAL_ERROR; + } + + td.tz = thermal_zone_discover(td.th); + if (!td.tz) { + ERROR("No thermal zone available\n"); + return THERMAL_ENGINE_THERMAL_ERROR; + } + + for_each_thermal_zone(td.tz, show_tz, td.th); + + if (mainloop_init()) { + ERROR("Failed to initialize the mainloop\n"); + return THERMAL_ENGINE_MAINLOOP_ERROR; + } + + if (mainloop_add(thermal_events_fd(td.th), thermal_event, &td)) { + ERROR("Failed to setup the mainloop\n"); + return THERMAL_ENGINE_MAINLOOP_ERROR; + } + + INFO("Waiting for thermal events ...\n"); + + if (mainloop(-1)) { + ERROR("Mainloop failed\n"); + return THERMAL_ENGINE_MAINLOOP_ERROR; + } + + return THERMAL_ENGINE_SUCCESS; +} diff --git a/tools/thermal/thermometer/Build b/tools/thermal/thermometer/Build new file mode 100644 index 000000000000..1b96c159c3c8 --- /dev/null +++ b/tools/thermal/thermometer/Build @@ -0,0 +1 @@ +thermometer-y += thermometer.o diff --git a/tools/thermal/thermometer/Makefile b/tools/thermal/thermometer/Makefile new file mode 100644 index 000000000000..d8f8bc82fe3b --- /dev/null +++ b/tools/thermal/thermometer/Makefile @@ -0,0 +1,26 @@ +# SPDX-License-Identifier: GPL-2.0 +# Makefile for cgroup tools + +ifeq ($(srctree),) +srctree := $(patsubst %/,%,$(dir $(CURDIR))) +srctree := $(patsubst %/,%,$(dir $(srctree))) +srctree := $(patsubst %/,%,$(dir $(srctree))) +# $(info Determined 'srctree' to be $(srctree)) +endif + +CFLAGS = -Wall -Wextra +CFLAGS += -I$(srctree)/tools/thermal/lib + +LDFLAGS = -L$(srctree)/tools/thermal/lib +LDFLAGS += -lthermal_tools +LDFLAGS += -lconfig + +VERSION = 0.0.1 +TARGET=thermometer + +all: $(TARGET) +%: %.c + $(CC) $(CFLAGS) -D VERSION=\"$(VERSION)\" -o $@ $^ $(LDFLAGS) + +clean: + $(RM) $(TARGET) diff --git a/tools/thermal/thermometer/thermometer.8 b/tools/thermal/thermometer/thermometer.8 new file mode 100644 index 000000000000..d090fbca4cba --- /dev/null +++ b/tools/thermal/thermometer/thermometer.8 @@ -0,0 +1,92 @@ +.TH THERMOMETER 8 +# SPDX-License-Identifier: GPL-2.0 +.SH NAME +\fBthermometer\fP - A thermal profiling tool + +.SH SYNOPSIS +.ft B +.B thermometer +.RB [ options ] +.RB [ command ] +.br +.SH DESCRIPTION +\fBthermometer \fP captures the thermal zones temperature at a +specified sampling period. It is optimized to reduce as much as +possible the overhead while doing the temperature acquisition in order +to prevent disrupting the running application we may want to profile. + +This low overhead also allows a high rate sampling for the temperature +which could be necessary to spot overshots and undershots. + +If no configuration file is specified, then all the thermal zones will +be monitored at 4Hz, so every 250ms. A configuration file specifies +the thermal zone names and the desired sampling period. A thermal zone +name can be a regular expression to specify a group of thermal zone. + +The sampling of the different thermal zones will be written into +separate files with the thermal zone name. It is possible to specify a +postfix to identify them for example for a specific scenario. The +output directory can be specified in addition. + +Without any parameters, \fBthermometer \fP captures all the thermal +zone temperatures every 250ms and write to the current directory the +captured files postfixed with the current date. + +If a running \fBduration\fP is specified or a \fBcommand\fP, the +capture ends at the end of the duration if the command did not +finished before. The \fBduration\fP can be specified alone as well as +the \fBcommand\fP. If none is specified, the capture will continue +indefinitively until interrupted by \fBSIGINT\fP or \fBSIGQUIT\fP. +.PP + +.SS Options +.PP +The \fB-h, --help\fP option shows a short usage help +.PP +The \fB-o <dir>, --output <dir>\fP option defines the output directory to put the +sampling files +.PP +The \fB-c <config>, --config <config>\fP option specifies the configuration file to use +.PP +The \fB-d <seconds>, --duration <seconds>\fP option specifies the duration of the capture +.PP +The \fB-l <loglevel>, --loglevel <loglevel>\fP option sets the loglevel [DEBUG,INFO,NOTICE,WARN,ERROR] +.PP +The \fB-p <string>, --postfix <string>\fP option appends \fBstring\fP at the end of the capture filenames +.PP +The \fB-s, --syslog\fP option sets the output to syslog, default is \fBstdout\fP +.PP +The \fB-w, --overwrite\fP overwrites the output files if they exist +.PP + +.PP + +.SS "Exit status:" +.TP +0 +if OK, +.TP +1 +Error with the options specified as parameters +.TP +2 +Error when configuring the logging facility +.TP +3 +Error when configuring the time +.TP +4 +Error in the initialization routine +.TP +5 +Error during the runtime + +.SH Capture file format + +Every file contains two columns. The first one is the uptime timestamp +in order to find a point in time since the system started up if there +is any thermal event. The second one is the temperature in milli +degree. The first line contains the label of each column. + +.SH AUTHOR +Daniel Lezcano <daniel.lezcano@kernel.org> diff --git a/tools/thermal/thermometer/thermometer.c b/tools/thermal/thermometer/thermometer.c new file mode 100644 index 000000000000..1a87a0a77f9f --- /dev/null +++ b/tools/thermal/thermometer/thermometer.c @@ -0,0 +1,572 @@ +// SPDX-License-Identifier: GPL-2.0-only +// Copyright (C) 2022, Linaro Ltd - Daniel Lezcano <daniel.lezcano@linaro.org> +#define _GNU_SOURCE +#include <dirent.h> +#include <fcntl.h> +#include <getopt.h> +#include <regex.h> +#include <signal.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/stat.h> +#include <sys/signalfd.h> +#include <sys/timerfd.h> +#include <sys/types.h> +#include <sys/wait.h> +#include <time.h> +#include <unistd.h> +#include <linux/thermal.h> + +#include <libconfig.h> +#include "thermal-tools.h" + +#define CLASS_THERMAL "/sys/class/thermal" + +enum { + THERMOMETER_SUCCESS = 0, + THERMOMETER_OPTION_ERROR, + THERMOMETER_LOG_ERROR, + THERMOMETER_CONFIG_ERROR, + THERMOMETER_TIME_ERROR, + THERMOMETER_INIT_ERROR, + THERMOMETER_RUNTIME_ERROR +}; + +struct options { + int loglvl; + int logopt; + int overwrite; + int duration; + const char *config; + char postfix[PATH_MAX]; + char output[PATH_MAX]; +}; + +struct tz_regex { + regex_t regex; + int polling; +}; + +struct configuration { + struct tz_regex *tz_regex; + int nr_tz_regex; + +}; + +struct tz { + FILE *file_out; + int fd_temp; + int fd_timer; + int polling; + const char *name; +}; + +struct thermometer { + struct tz *tz; + int nr_tz; +}; + +static struct tz_regex *configuration_tz_match(const char *expr, + struct configuration *config) +{ + int i; + + for (i = 0; i < config->nr_tz_regex; i++) { + + if (!regexec(&config->tz_regex[i].regex, expr, 0, NULL, 0)) + return &config->tz_regex[i]; + } + + return NULL; +} + +static int configuration_default_init(struct configuration *config) +{ + config->tz_regex = realloc(config->tz_regex, sizeof(*config->tz_regex) * + (config->nr_tz_regex + 1)); + + if (regcomp(&config->tz_regex[config->nr_tz_regex].regex, ".*", + REG_NOSUB | REG_EXTENDED)) { + ERROR("Invalid regular expression\n"); + return -1; + } + + config->tz_regex[config->nr_tz_regex].polling = 250; + config->nr_tz_regex = 1; + + return 0; +} + +static int configuration_init(const char *path, struct configuration *config) +{ + config_t cfg; + + config_setting_t *tz; + int i, length; + + if (path && access(path, F_OK)) { + ERROR("'%s' is not accessible\n", path); + return -1; + } + + if (!path && !config->nr_tz_regex) { + INFO("No thermal zones configured, using wildcard for all of them\n"); + return configuration_default_init(config); + } + + config_init(&cfg); + + if (!config_read_file(&cfg, path)) { + ERROR("Failed to parse %s:%d - %s\n", config_error_file(&cfg), + config_error_line(&cfg), config_error_text(&cfg)); + + return -1; + } + + tz = config_lookup(&cfg, "thermal-zones"); + if (!tz) { + ERROR("No thermal zone configured to be monitored\n"); + return -1; + } + + length = config_setting_length(tz); + + INFO("Found %d thermal zone(s) regular expression\n", length); + + for (i = 0; i < length; i++) { + + config_setting_t *node; + const char *name; + int polling; + + node = config_setting_get_elem(tz, i); + if (!node) { + ERROR("Missing node name '%d'\n", i); + return -1; + } + + if (!config_setting_lookup_string(node, "name", &name)) { + ERROR("Thermal zone name not found\n"); + return -1; + } + + if (!config_setting_lookup_int(node, "polling", &polling)) { + ERROR("Polling value not found"); + return -1; + } + + config->tz_regex = realloc(config->tz_regex, sizeof(*config->tz_regex) * + (config->nr_tz_regex + 1)); + + if (regcomp(&config->tz_regex[config->nr_tz_regex].regex, name, + REG_NOSUB | REG_EXTENDED)) { + ERROR("Invalid regular expression '%s'\n", name); + continue; + } + + config->tz_regex[config->nr_tz_regex].polling = polling; + config->nr_tz_regex++; + + INFO("Thermal zone regular expression '%s' with polling %d\n", + name, polling); + } + + return 0; +} + +static void usage(const char *cmd) +{ + printf("%s Version: %s\n", cmd, VERSION); + printf("Usage: %s [options]\n", cmd); + printf("\t-h, --help\t\tthis help\n"); + printf("\t-o, --output <dir>\toutput directory for temperature capture\n"); + printf("\t-c, --config <file>\tconfiguration file\n"); + printf("\t-d, --duration <seconds>\tcapture duration\n"); + printf("\t-l, --loglevel <level>\tlog level: "); + printf("DEBUG, INFO, NOTICE, WARN, ERROR\n"); + printf("\t-p, --postfix <string>\tpostfix to be happened at the end of the files\n"); + printf("\t-s, --syslog\t\toutput to syslog\n"); + printf("\t-w, --overwrite\t\toverwrite the temperature capture files if they exist\n"); + printf("\n"); + exit(0); +} + +static int options_init(int argc, char *argv[], struct options *options) +{ + int opt; + time_t now = time(NULL); + + struct option long_options[] = { + { "help", no_argument, NULL, 'h' }, + { "config", required_argument, NULL, 'c' }, + { "duration", required_argument, NULL, 'd' }, + { "loglevel", required_argument, NULL, 'l' }, + { "postfix", required_argument, NULL, 'p' }, + { "output", required_argument, NULL, 'o' }, + { "syslog", required_argument, NULL, 's' }, + { "overwrite", no_argument, NULL, 'w' }, + { 0, 0, 0, 0 } + }; + + strftime(options->postfix, sizeof(options->postfix), + "-%Y-%m-%d_%H:%M:%S", gmtime(&now)); + + while (1) { + + int optindex = 0; + + opt = getopt_long(argc, argv, "ho:c:d:l:p:sw", long_options, &optindex); + if (opt == -1) + break; + + switch (opt) { + case 'c': + options->config = optarg; + break; + case 'd': + options->duration = atoi(optarg) * 1000; + break; + case 'l': + options->loglvl = log_str2level(optarg); + break; + case 'h': + usage(basename(argv[0])); + break; + case 'p': + strcpy(options->postfix, optarg); + break; + case 'o': + strcpy(options->output, optarg); + break; + case 's': + options->logopt = TO_SYSLOG; + break; + case 'w': + options->overwrite = 1; + break; + default: /* '?' */ + ERROR("Usage: %s --help\n", argv[0]); + return -1; + } + } + + return 0; +} + +static int thermometer_add_tz(const char *path, const char *name, int polling, + struct thermometer *thermometer) +{ + int fd; + char tz_path[PATH_MAX]; + + sprintf(tz_path, CLASS_THERMAL"/%s/temp", path); + + fd = open(tz_path, O_RDONLY); + if (fd < 0) { + ERROR("Failed to open '%s': %m\n", tz_path); + return -1; + } + + thermometer->tz = realloc(thermometer->tz, + sizeof(*thermometer->tz) * (thermometer->nr_tz + 1)); + if (!thermometer->tz) { + ERROR("Failed to allocate thermometer->tz\n"); + return -1; + } + + thermometer->tz[thermometer->nr_tz].fd_temp = fd; + thermometer->tz[thermometer->nr_tz].name = strdup(name); + thermometer->tz[thermometer->nr_tz].polling = polling; + thermometer->nr_tz++; + + INFO("Added thermal zone '%s->%s (polling:%d)'\n", path, name, polling); + + return 0; +} + +static int thermometer_init(struct configuration *config, + struct thermometer *thermometer) +{ + DIR *dir; + struct dirent *dirent; + struct tz_regex *tz_regex; + const char *tz_dirname = "thermal_zone"; + + if (mainloop_init()) { + ERROR("Failed to start mainloop\n"); + return -1; + } + + dir = opendir(CLASS_THERMAL); + if (!dir) { + ERROR("failed to open '%s'\n", CLASS_THERMAL); + return -1; + } + + while ((dirent = readdir(dir))) { + char tz_type[THERMAL_NAME_LENGTH]; + char tz_path[PATH_MAX]; + FILE *tz_file; + + if (strncmp(dirent->d_name, tz_dirname, strlen(tz_dirname))) + continue; + + sprintf(tz_path, CLASS_THERMAL"/%s/type", dirent->d_name); + + tz_file = fopen(tz_path, "r"); + if (!tz_file) { + ERROR("Failed to open '%s': %m", tz_path); + continue; + } + + fscanf(tz_file, "%s", tz_type); + + fclose(tz_file); + + tz_regex = configuration_tz_match(tz_type, config); + if (!tz_regex) + continue; + + if (thermometer_add_tz(dirent->d_name, tz_type, + tz_regex->polling, thermometer)) + continue; + } + + closedir(dir); + + return 0; +} + +static int timer_temperature_callback(int fd, void *arg) +{ + struct tz *tz = arg; + char buf[16] = { 0 }; + + pread(tz->fd_temp, buf, sizeof(buf), 0); + + fprintf(tz->file_out, "%ld %s", getuptimeofday_ms(), buf); + + read(fd, buf, sizeof(buf)); + + return 0; +} + +static int thermometer_start(struct thermometer *thermometer, + struct options *options) +{ + struct itimerspec timer_it = { 0 }; + char *path; + FILE *f; + int i; + + INFO("Capturing %d thermal zone(s) temperature...\n", thermometer->nr_tz); + + if (access(options->output, F_OK) && mkdir(options->output, 0700)) { + ERROR("Failed to create directory '%s'\n", options->output); + return -1; + } + + for (i = 0; i < thermometer->nr_tz; i++) { + + asprintf(&path, "%s/%s%s", options->output, + thermometer->tz[i].name, options->postfix); + + if (!options->overwrite && !access(path, F_OK)) { + ERROR("'%s' already exists\n", path); + return -1; + } + + f = fopen(path, "w"); + if (!f) { + ERROR("Failed to create '%s':%m\n", path); + return -1; + } + + fprintf(f, "timestamp(ms) %s(°mC)\n", thermometer->tz[i].name); + + thermometer->tz[i].file_out = f; + + DEBUG("Created '%s' file for thermal zone '%s'\n", path, thermometer->tz[i].name); + + /* + * Create polling timer + */ + thermometer->tz[i].fd_timer = timerfd_create(CLOCK_MONOTONIC, 0); + if (thermometer->tz[i].fd_timer < 0) { + ERROR("Failed to create timer for '%s': %m\n", + thermometer->tz[i].name); + return -1; + } + + DEBUG("Watching '%s' every %d ms\n", + thermometer->tz[i].name, thermometer->tz[i].polling); + + timer_it.it_interval = timer_it.it_value = + msec_to_timespec(thermometer->tz[i].polling); + + if (timerfd_settime(thermometer->tz[i].fd_timer, 0, + &timer_it, NULL) < 0) + return -1; + + if (mainloop_add(thermometer->tz[i].fd_timer, + timer_temperature_callback, + &thermometer->tz[i])) + return -1; + } + + return 0; +} + +static int thermometer_execute(int argc, char *argv[], char *const envp[], pid_t *pid) +{ + if (!argc) + return 0; + + *pid = fork(); + if (*pid < 0) { + ERROR("Failed to fork process: %m"); + return -1; + } + + if (!(*pid)) { + execvpe(argv[0], argv, envp); + exit(1); + } + + return 0; +} + +static int kill_process(__maybe_unused int fd, void *arg) +{ + pid_t pid = *(pid_t *)arg; + + if (kill(pid, SIGTERM)) + ERROR("Failed to send SIGTERM signal to '%d': %p\n", pid); + else if (waitpid(pid, NULL, 0)) + ERROR("Failed to wait pid '%d': %p\n", pid); + + mainloop_exit(); + + return 0; +} + +static int exit_mainloop(__maybe_unused int fd, __maybe_unused void *arg) +{ + mainloop_exit(); + return 0; +} + +static int thermometer_wait(struct options *options, pid_t pid) +{ + int fd; + sigset_t mask; + + /* + * If there is a duration specified, we will exit the mainloop + * and gracefully close all the files which will flush the + * file system cache + */ + if (options->duration) { + struct itimerspec timer_it = { 0 }; + + timer_it.it_value = msec_to_timespec(options->duration); + + fd = timerfd_create(CLOCK_MONOTONIC, 0); + if (fd < 0) { + ERROR("Failed to create duration timer: %m\n"); + return -1; + } + + if (timerfd_settime(fd, 0, &timer_it, NULL)) { + ERROR("Failed to set timer time: %m\n"); + return -1; + } + + if (mainloop_add(fd, pid < 0 ? exit_mainloop : kill_process, &pid)) { + ERROR("Failed to set timer exit mainloop callback\n"); + return -1; + } + } + + /* + * We want to catch any keyboard interrupt, as well as child + * signals if any in order to exit properly + */ + sigemptyset(&mask); + sigaddset(&mask, SIGINT); + sigaddset(&mask, SIGQUIT); + sigaddset(&mask, SIGCHLD); + + if (sigprocmask(SIG_BLOCK, &mask, NULL)) { + ERROR("Failed to set sigprocmask: %m\n"); + return -1; + } + + fd = signalfd(-1, &mask, 0); + if (fd < 0) { + ERROR("Failed to set the signalfd: %m\n"); + return -1; + } + + if (mainloop_add(fd, exit_mainloop, NULL)) { + ERROR("Failed to set timer exit mainloop callback\n"); + return -1; + } + + return mainloop(-1); +} + +static int thermometer_stop(struct thermometer *thermometer) +{ + int i; + + INFO("Closing/flushing output files\n"); + + for (i = 0; i < thermometer->nr_tz; i++) + fclose(thermometer->tz[i].file_out); + + return 0; +} + +int main(int argc, char *argv[], char *const envp[]) +{ + struct options options = { + .loglvl = LOG_DEBUG, + .logopt = TO_STDOUT, + .output = ".", + }; + struct configuration config = { 0 }; + struct thermometer thermometer = { 0 }; + + pid_t pid = -1; + + if (options_init(argc, argv, &options)) + return THERMOMETER_OPTION_ERROR; + + if (log_init(options.loglvl, argv[0], options.logopt)) + return THERMOMETER_LOG_ERROR; + + if (configuration_init(options.config, &config)) + return THERMOMETER_CONFIG_ERROR; + + if (uptimeofday_init()) + return THERMOMETER_TIME_ERROR; + + if (thermometer_init(&config, &thermometer)) + return THERMOMETER_INIT_ERROR; + + if (thermometer_start(&thermometer, &options)) + return THERMOMETER_RUNTIME_ERROR; + + if (thermometer_execute(argc - optind, &argv[optind], envp, &pid)) + return THERMOMETER_RUNTIME_ERROR; + + if (thermometer_wait(&options, pid)) + return THERMOMETER_RUNTIME_ERROR; + + if (thermometer_stop(&thermometer)) + return THERMOMETER_RUNTIME_ERROR; + + return THERMOMETER_SUCCESS; +} diff --git a/tools/thermal/thermometer/thermometer.conf b/tools/thermal/thermometer/thermometer.conf new file mode 100644 index 000000000000..02c6dab3b1b3 --- /dev/null +++ b/tools/thermal/thermometer/thermometer.conf @@ -0,0 +1,5 @@ + +thermal-zones = ( + { name = "cpu[0-9]-thermal"; + polling = 100; } + ) diff --git a/virt/kvm/dirty_ring.c b/virt/kvm/dirty_ring.c index 222ecc81d7df..f4c2a6eb1666 100644 --- a/virt/kvm/dirty_ring.c +++ b/virt/kvm/dirty_ring.c @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ +// SPDX-License-Identifier: GPL-2.0-only /* * KVM dirty ring implementation * diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c index 59b1dd4a549e..2a3ed401ce46 100644 --- a/virt/kvm/eventfd.c +++ b/virt/kvm/eventfd.c @@ -77,7 +77,8 @@ irqfd_resampler_ack(struct kvm_irq_ack_notifier *kian) idx = srcu_read_lock(&kvm->irq_srcu); - list_for_each_entry_rcu(irqfd, &resampler->list, resampler_link) + list_for_each_entry_srcu(irqfd, &resampler->list, resampler_link, + srcu_read_lock_held(&kvm->irq_srcu)) eventfd_signal(irqfd->resamplefd, 1); srcu_read_unlock(&kvm->irq_srcu, idx); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 70e05af5ebea..5ab12214e18d 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -164,6 +164,10 @@ __weak void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, { } +__weak void kvm_arch_guest_memory_reclaimed(struct kvm *kvm) +{ +} + bool kvm_is_zone_device_pfn(kvm_pfn_t pfn) { /* @@ -357,6 +361,12 @@ void kvm_flush_remote_tlbs(struct kvm *kvm) EXPORT_SYMBOL_GPL(kvm_flush_remote_tlbs); #endif +static void kvm_flush_shadow_all(struct kvm *kvm) +{ + kvm_arch_flush_shadow_all(kvm); + kvm_arch_guest_memory_reclaimed(kvm); +} + #ifdef KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE static inline void *mmu_memory_cache_alloc_obj(struct kvm_mmu_memory_cache *mc, gfp_t gfp_flags) @@ -434,8 +444,8 @@ static void kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id) static void kvm_vcpu_destroy(struct kvm_vcpu *vcpu) { - kvm_dirty_ring_free(&vcpu->dirty_ring); kvm_arch_vcpu_destroy(vcpu); + kvm_dirty_ring_free(&vcpu->dirty_ring); /* * No need for rcu_read_lock as VCPU_RUN is the only place that changes @@ -485,12 +495,15 @@ typedef bool (*hva_handler_t)(struct kvm *kvm, struct kvm_gfn_range *range); typedef void (*on_lock_fn_t)(struct kvm *kvm, unsigned long start, unsigned long end); +typedef void (*on_unlock_fn_t)(struct kvm *kvm); + struct kvm_hva_range { unsigned long start; unsigned long end; pte_t pte; hva_handler_t handler; on_lock_fn_t on_lock; + on_unlock_fn_t on_unlock; bool flush_on_ret; bool may_block; }; @@ -578,8 +591,11 @@ static __always_inline int __kvm_handle_hva_range(struct kvm *kvm, if (range->flush_on_ret && ret) kvm_flush_remote_tlbs(kvm); - if (locked) + if (locked) { KVM_MMU_UNLOCK(kvm); + if (!IS_KVM_NULL_FN(range->on_unlock)) + range->on_unlock(kvm); + } srcu_read_unlock(&kvm->srcu, idx); @@ -600,6 +616,7 @@ static __always_inline int kvm_handle_hva_range(struct mmu_notifier *mn, .pte = pte, .handler = handler, .on_lock = (void *)kvm_null_fn, + .on_unlock = (void *)kvm_null_fn, .flush_on_ret = true, .may_block = false, }; @@ -619,6 +636,7 @@ static __always_inline int kvm_handle_hva_range_no_flush(struct mmu_notifier *mn .pte = __pte(0), .handler = handler, .on_lock = (void *)kvm_null_fn, + .on_unlock = (void *)kvm_null_fn, .flush_on_ret = false, .may_block = false, }; @@ -662,7 +680,7 @@ void kvm_inc_notifier_count(struct kvm *kvm, unsigned long start, kvm->mmu_notifier_range_end = end; } else { /* - * Fully tracking multiple concurrent ranges has dimishing + * Fully tracking multiple concurrent ranges has diminishing * returns. Keep things simple and just find the minimal range * which includes the current and new ranges. As there won't be * enough information to subtract a range after its invalidate @@ -687,6 +705,7 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn, .pte = __pte(0), .handler = kvm_unmap_gfn_range, .on_lock = kvm_inc_notifier_count, + .on_unlock = kvm_arch_guest_memory_reclaimed, .flush_on_ret = true, .may_block = mmu_notifier_range_blockable(range), }; @@ -741,6 +760,7 @@ static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn, .pte = __pte(0), .handler = (void *)kvm_null_fn, .on_lock = kvm_dec_notifier_count, + .on_unlock = (void *)kvm_null_fn, .flush_on_ret = false, .may_block = mmu_notifier_range_blockable(range), }; @@ -813,7 +833,7 @@ static void kvm_mmu_notifier_release(struct mmu_notifier *mn, int idx; idx = srcu_read_lock(&kvm->srcu); - kvm_arch_flush_shadow_all(kvm); + kvm_flush_shadow_all(kvm); srcu_read_unlock(&kvm->srcu, idx); } @@ -932,7 +952,7 @@ static void kvm_destroy_vm_debugfs(struct kvm *kvm) int kvm_debugfs_num_entries = kvm_vm_stats_header.num_desc + kvm_vcpu_stats_header.num_desc; - if (!kvm->debugfs_dentry) + if (IS_ERR(kvm->debugfs_dentry)) return; debugfs_remove_recursive(kvm->debugfs_dentry); @@ -1075,6 +1095,12 @@ static struct kvm *kvm_create_vm(unsigned long type) BUILD_BUG_ON(KVM_MEM_SLOTS_NUM > SHRT_MAX); + /* + * Force subsequent debugfs file creations to fail if the VM directory + * is not created (by kvm_create_vm_debugfs()). + */ + kvm->debugfs_dentry = ERR_PTR(-ENOENT); + if (init_srcu_struct(&kvm->srcu)) goto out_err_no_srcu; if (init_srcu_struct(&kvm->irq_srcu)) @@ -1219,7 +1245,7 @@ static void kvm_destroy_vm(struct kvm *kvm) WARN_ON(rcuwait_active(&kvm->mn_memslots_update_rcuwait)); kvm->mn_active_invalidate_count = 0; #else - kvm_arch_flush_shadow_all(kvm); + kvm_flush_shadow_all(kvm); #endif kvm_arch_destroy_vm(kvm); kvm_destroy_devices(kvm); @@ -1534,7 +1560,7 @@ static int kvm_prepare_memory_region(struct kvm *kvm, r = kvm_arch_prepare_memory_region(kvm, old, new, change); /* Free the bitmap on failure if it was allocated above. */ - if (r && new && new->dirty_bitmap && old && !old->dirty_bitmap) + if (r && new && new->dirty_bitmap && (!old || !old->dirty_bitmap)) kvm_destroy_dirty_bitmap(new); return r; @@ -1646,6 +1672,7 @@ static void kvm_invalidate_memslot(struct kvm *kvm, * - kvm_is_visible_gfn (mmu_check_root) */ kvm_arch_flush_shadow_memslot(kvm, old); + kvm_arch_guest_memory_reclaimed(kvm); /* Was released by kvm_swap_active_memslots, reacquire. */ mutex_lock(&kvm->slots_arch_lock); @@ -1793,7 +1820,7 @@ static int kvm_set_memslot(struct kvm *kvm, /* * No need to refresh new->arch, changes after dropping slots_arch_lock - * will directly hit the final, active memsot. Architectures are + * will directly hit the final, active memslot. Architectures are * responsible for knowing that new->arch may be stale. */ kvm_commit_memory_region(kvm, old, new, change); @@ -4327,6 +4354,7 @@ static long kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg) return 0; #endif case KVM_CAP_BINARY_STATS_FD: + case KVM_CAP_SYSTEM_EVENT_DATA: return 1; default: break; @@ -5479,7 +5507,7 @@ static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm) } add_uevent_var(env, "PID=%d", kvm->userspace_pid); - if (kvm->debugfs_dentry) { + if (!IS_ERR(kvm->debugfs_dentry)) { char *tmp, *p = kmalloc(PATH_MAX, GFP_KERNEL_ACCOUNT); if (p) { diff --git a/virt/kvm/kvm_mm.h b/virt/kvm/kvm_mm.h index 34ca40823260..41da467d99c9 100644 --- a/virt/kvm/kvm_mm.h +++ b/virt/kvm/kvm_mm.h @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0-only +/* SPDX-License-Identifier: GPL-2.0-only */ #ifndef __KVM_MM_H__ #define __KVM_MM_H__ 1 |